diff --git a/CREDITS b/CREDITS
index 8207cc6..af67a84 100644
--- a/CREDITS
+++ b/CREDITS
@@ -1507,6 +1507,14 @@
 S: Griffith, ACT 2603 
 S: Australia
 
+N: Andreas Herrmann
+E: herrmann.der.user@gmail.com
+E: herrmann.der.user@googlemail.com
+D: Key developer of x86/AMD64
+D: Author of AMD family 15h processor power monitoring driver
+D: Maintainer of AMD Athlon 64 and Opteron processor frequency driver
+S: Germany
+
 N: Sebastian Hetze
 E: she@lunetix.de
 D: German Linux Documentation,
diff --git a/Documentation/DocBook/device-drivers.tmpl b/Documentation/DocBook/device-drivers.tmpl
index 42a2d85..7b3fcc5 100644
--- a/Documentation/DocBook/device-drivers.tmpl
+++ b/Documentation/DocBook/device-drivers.tmpl
@@ -238,78 +238,26 @@
 !Iinclude/media/videobuf2-memops.h
      </sect1>
      <sect1><title>Digital TV (DVB) devices</title>
-!Idrivers/media/dvb-core/dvb_ca_en50221.h
-!Idrivers/media/dvb-core/dvb_frontend.h
+	<sect1><title>Digital TV Common functions</title>
 !Idrivers/media/dvb-core/dvb_math.h
 !Idrivers/media/dvb-core/dvb_ringbuffer.h
 !Idrivers/media/dvb-core/dvbdev.h
-	<sect1><title>Digital TV Demux API</title>
-	    <para>The kernel demux API defines a driver-internal interface for
-	    registering low-level, hardware specific driver to a hardware
-	    independent demux layer. It is only of interest for Digital TV
-	    device driver writers. The header file for this API is named
-	    <constant>demux.h</constant> and located in
-	    <constant>drivers/media/dvb-core</constant>.</para>
-
-	<para>The demux API should be implemented for each demux in the
-	system. It is used to select the TS source of a demux and to manage
-	the demux resources. When the demux client allocates a resource via
-	the demux API, it receives a pointer to the API of that
-	resource.</para>
-	<para>Each demux receives its TS input from a DVB front-end or from
-	memory, as set via this demux API. In a system with more than one
-	front-end, the API can be used to select one of the DVB front-ends
-	as a TS source for a demux, unless this is fixed in the HW platform.
-	The demux API only controls front-ends regarding to their connections
-	with demuxes; the APIs used to set the other front-end parameters,
-	such as tuning, are not defined in this document.</para>
-	<para>The functions that implement the abstract interface demux should
-	be defined static or module private and registered to the Demux
-	core for external access. It is not necessary to implement every
-	function in the struct <constant>dmx_demux</constant>. For example,
-	a demux interface might support Section filtering, but not PES
-	filtering. The API client is expected to check the value of any
-	function pointer before calling the function: the value of NULL means
-	that the &#8220;function is not available&#8221;.</para>
-	<para>Whenever the functions of the demux API modify shared data,
-	the possibilities of lost update and race condition problems should
-	be addressed, e.g. by protecting parts of code with mutexes.</para>
-	<para>Note that functions called from a bottom half context must not
-	sleep. Even a simple memory allocation without using GFP_ATOMIC can
-	result in a kernel thread being put to sleep if swapping is needed.
-	For example, the Linux kernel calls the functions of a network device
-	interface from a bottom half context. Thus, if a demux API function
-	is called from network device code, the function must not sleep.
-	</para>
-    </sect1>
-
-    <section id="demux_callback_api">
-	<title>Demux Callback API</title>
-	<para>This kernel-space API comprises the callback functions that
-	deliver filtered data to the demux client. Unlike the other DVB
-	kABIs, these functions are provided by the client and called from
-	the demux code.</para>
-	<para>The function pointers of this abstract interface are not
-	packed into a structure as in the other demux APIs, because the
-	callback functions are registered and used independent of each
-	other. As an example, it is possible for the API client to provide
-	several callback functions for receiving TS packets and no
-	callbacks for PES packets or sections.</para>
-	<para>The functions that implement the callback API need not be
-	re-entrant: when a demux driver calls one of these functions,
-	the driver is not allowed to call the function again before
-	the original call returns. If a callback is triggered by a
-	hardware interrupt, it is recommended to use the Linux
-	&#8220;bottom half&#8221; mechanism or start a tasklet instead of
-	making the callback function call directly from a hardware
-	interrupt.</para>
-	<para>This mechanism is implemented by
-	<link linkend='API-dmx-ts-cb'>dmx_ts_cb()</link> and
-	<link linkend='API-dmx-section-cb'>dmx_section_cb()</link>.</para>
-    </section>
-
+	</sect1>
+	<sect1><title>Digital TV Frontend kABI</title>
+!Pdrivers/media/dvb-core/dvb_frontend.h Digital TV Frontend
+!Idrivers/media/dvb-core/dvb_frontend.h
+	</sect1>
+	<sect1><title>Digital TV Demux kABI</title>
+!Pdrivers/media/dvb-core/demux.h Digital TV Demux
+	<sect1><title>Demux Callback API</title>
+!Pdrivers/media/dvb-core/demux.h Demux Callback
+	</sect1>
 !Idrivers/media/dvb-core/demux.h
-    </sect1>
+	</sect1>
+	<sect1><title>Digital TV Conditional Access kABI</title>
+!Idrivers/media/dvb-core/dvb_ca_en50221.h
+	</sect1>
+     </sect1>
     <sect1><title>Remote Controller devices</title>
 !Iinclude/media/rc-core.h
 !Iinclude/media/lirc_dev.h
diff --git a/Documentation/DocBook/media/Makefile b/Documentation/DocBook/media/Makefile
index 08527e7..2840ff4 100644
--- a/Documentation/DocBook/media/Makefile
+++ b/Documentation/DocBook/media/Makefile
@@ -199,8 +199,10 @@
 #
 
 install_media_images = \
-	$(Q)-mkdir $(MEDIA_OBJ_DIR)/media_api; \
-	cp $(OBJIMGFILES) $(MEDIA_SRC_DIR)/*.svg $(MEDIA_SRC_DIR)/v4l/*.svg $(MEDIA_OBJ_DIR)/media_api
+	$(Q)if [ "x$(findstring media_api.xml,$(DOCBOOKS))" != "x" ]; then \
+		mkdir -p $(MEDIA_OBJ_DIR)/media_api; \
+		cp $(OBJIMGFILES) $(MEDIA_SRC_DIR)/*.svg $(MEDIA_SRC_DIR)/v4l/*.svg $(MEDIA_OBJ_DIR)/media_api; \
+	fi
 
 $(MEDIA_OBJ_DIR)/%: $(MEDIA_SRC_DIR)/%.b64
 	$(Q)base64 -d $< >$@
diff --git a/Documentation/DocBook/media/dvb/dvbproperty.xml b/Documentation/DocBook/media/dvb/dvbproperty.xml
index 08227d4..e579ae5 100644
--- a/Documentation/DocBook/media/dvb/dvbproperty.xml
+++ b/Documentation/DocBook/media/dvb/dvbproperty.xml
@@ -76,7 +76,7 @@
 
 <para>NOTE: While it is possible to directly call the Kernel code like the
     above example, it is strongly recommended to use
-    <ulink url="http://linuxtv.org/docs/libdvbv5/index.html">libdvbv5</ulink>,
+    <ulink url="https://linuxtv.org/docs/libdvbv5/index.html">libdvbv5</ulink>,
     as it provides abstraction to work with the supported digital TV standards
     and provides methods for usual operations like program scanning and to
     read/write channel descriptor files.</para>
diff --git a/Documentation/DocBook/media/dvb/examples.xml b/Documentation/DocBook/media/dvb/examples.xml
index c9f68c7..837fb3b 100644
--- a/Documentation/DocBook/media/dvb/examples.xml
+++ b/Documentation/DocBook/media/dvb/examples.xml
@@ -3,7 +3,7 @@
 </para>
 <para>NOTE: This section is out of date, and the code below won't even
     compile. Please refer to the
-    <ulink url="http://linuxtv.org/docs/libdvbv5/index.html">libdvbv5</ulink>
+    <ulink url="https://linuxtv.org/docs/libdvbv5/index.html">libdvbv5</ulink>
     for updated/recommended examples.
 </para>
 
diff --git a/Documentation/DocBook/media/dvb/intro.xml b/Documentation/DocBook/media/dvb/intro.xml
index 51db156..b5b701f 100644
--- a/Documentation/DocBook/media/dvb/intro.xml
+++ b/Documentation/DocBook/media/dvb/intro.xml
@@ -32,7 +32,7 @@
 new standard Linux DVB API. As a commitment to the development of
 terminals based on open standards, Nokia and Convergence made it
 available to all Linux developers and published it on
-<ulink url="http://www.linuxtv.org/" /> in September 2000.
+<ulink url="https://linuxtv.org" /> in September 2000.
 Convergence is the maintainer of the Linux DVB API. Together with the
 LinuxTV community (i.e. you, the reader of this document), the Linux DVB
 API will be constantly reviewed and improved. With the Linux driver for
diff --git a/Documentation/DocBook/media/v4l/capture.c.xml b/Documentation/DocBook/media/v4l/capture.c.xml
index 1c5c49a..22126a9 100644
--- a/Documentation/DocBook/media/v4l/capture.c.xml
+++ b/Documentation/DocBook/media/v4l/capture.c.xml
@@ -5,7 +5,7 @@
  *  This program can be used and distributed without restrictions.
  *
  *      This program is provided with the V4L2 API
- * see http://linuxtv.org/docs.php for more information
+ * see https://linuxtv.org/docs.php for more information
  */
 
 #include &lt;stdio.h&gt;
diff --git a/Documentation/DocBook/media/v4l/compat.xml b/Documentation/DocBook/media/v4l/compat.xml
index 5701a08..5399e89 100644
--- a/Documentation/DocBook/media/v4l/compat.xml
+++ b/Documentation/DocBook/media/v4l/compat.xml
@@ -2666,7 +2666,7 @@
         <para>V4L2 does not support digital terrestrial, cable or
 satellite broadcast. A separate project aiming at digital receivers
 exists. You can find its homepage at <ulink
-url="http://linuxtv.org">http://linuxtv.org</ulink>. The Linux DVB API
+url="https://linuxtv.org">https://linuxtv.org</ulink>. The Linux DVB API
 has no connection to the V4L2 API except that drivers for hybrid
 hardware may support both.</para>
       </section>
diff --git a/Documentation/DocBook/media/v4l/io.xml b/Documentation/DocBook/media/v4l/io.xml
index da65403..144158b 100644
--- a/Documentation/DocBook/media/v4l/io.xml
+++ b/Documentation/DocBook/media/v4l/io.xml
@@ -699,7 +699,7 @@
 buffer. It depends on the negotiated data format and may change with
 each buffer for compressed variable size data like JPEG images.
 Drivers must set this field when <structfield>type</structfield>
-refers to an input stream, applications when it refers to an output stream.
+refers to a capture stream, applications when it refers to an output stream.
 If the application sets this to 0 for an output stream, then
 <structfield>bytesused</structfield> will be set to the size of the
 buffer (see the <structfield>length</structfield> field of this struct) by
@@ -720,14 +720,14 @@
 	    <entry>Indicates the field order of the image in the
 buffer, see <xref linkend="v4l2-field" />. This field is not used when
 the buffer contains VBI data. Drivers must set it when
-<structfield>type</structfield> refers to an input stream,
+<structfield>type</structfield> refers to a capture stream,
 applications when it refers to an output stream.</entry>
 	  </row>
 	  <row>
 	    <entry>struct timeval</entry>
 	    <entry><structfield>timestamp</structfield></entry>
 	    <entry></entry>
-	    <entry><para>For input streams this is time when the first data
+	    <entry><para>For capture streams this is time when the first data
 	    byte was captured, as returned by the
 	    <function>clock_gettime()</function> function for the relevant
 	    clock id; see <constant>V4L2_BUF_FLAG_TIMESTAMP_*</constant> in
@@ -866,7 +866,7 @@
 	    <entry></entry>
 	    <entry>The number of bytes occupied by data in the plane
 	      (its payload). Drivers must set this field when <structfield>type</structfield>
-	      refers to an input stream, applications when it refers to an output stream.
+	      refers to a capture stream, applications when it refers to an output stream.
 	      If the application sets this to 0 for an output stream, then
 	      <structfield>bytesused</structfield> will be set to the size of the
 	      plane (see the <structfield>length</structfield> field of this struct)
@@ -919,7 +919,7 @@
 	    <entry></entry>
 	    <entry>Offset in bytes to video data in the plane.
 	      Drivers must set this field when <structfield>type</structfield>
-	      refers to an input stream, applications when it refers to an output stream.
+	      refers to a capture stream, applications when it refers to an output stream.
 	      Note that data_offset is included in <structfield>bytesused</structfield>.
 	      So the size of the image in the plane is
 	      <structfield>bytesused</structfield>-<structfield>data_offset</structfield> at
diff --git a/Documentation/DocBook/media/v4l/v4l2.xml b/Documentation/DocBook/media/v4l/v4l2.xml
index 7e61643..42e626d 100644
--- a/Documentation/DocBook/media/v4l/v4l2.xml
+++ b/Documentation/DocBook/media/v4l/v4l2.xml
@@ -152,6 +152,16 @@
 (compat.xml), along with the possible impact on existing drivers and
 applications. -->
       <revision>
+	<revnumber>4.5</revnumber>
+	<date>2015-10-29</date>
+	<authorinitials>rr</authorinitials>
+	<revremark>Extend vidioc-g-ext-ctrls;. Replace ctrl_class with a new
+union with ctrl_class and which. Which is used to select the current value of
+the control or the default value.
+	</revremark>
+      </revision>
+
+      <revision>
 	<revnumber>4.4</revnumber>
 	<date>2015-05-26</date>
 	<authorinitials>ap</authorinitials>
diff --git a/Documentation/DocBook/media/v4l/vidioc-create-bufs.xml b/Documentation/DocBook/media/v4l/vidioc-create-bufs.xml
index 8ffe74f..d81fa0d 100644
--- a/Documentation/DocBook/media/v4l/vidioc-create-bufs.xml
+++ b/Documentation/DocBook/media/v4l/vidioc-create-bufs.xml
@@ -58,7 +58,7 @@
     <para>This ioctl is used to create buffers for <link linkend="mmap">memory
 mapped</link> or <link linkend="userp">user pointer</link> or <link
 linkend="dmabuf">DMA buffer</link> I/O. It can be used as an alternative or in
-addition to the <constant>VIDIOC_REQBUFS</constant> ioctl, when a tighter
+addition to the &VIDIOC-REQBUFS; ioctl, when a tighter
 control over buffers is required. This ioctl can be called multiple times to
 create buffers of different sizes.</para>
 
@@ -71,30 +71,28 @@
 
     <para>The <structfield>format</structfield> field specifies the image format
 that the buffers must be able to handle. The application has to fill in this
-&v4l2-format;. Usually this will be done using the
-<constant>VIDIOC_TRY_FMT</constant> or <constant>VIDIOC_G_FMT</constant> ioctl()
-to ensure that the requested format is supported by the driver. Unsupported
-formats will result in an error.</para>
+&v4l2-format;. Usually this will be done using the &VIDIOC-TRY-FMT; or &VIDIOC-G-FMT; ioctls
+to ensure that the requested format is supported by the driver.
+Based on the format's <structfield>type</structfield> field the requested buffer
+size (for single-planar) or plane sizes (for multi-planar formats) will be
+used for the allocated buffers. The driver may return an error if the size(s)
+are not supported by the hardware (usually because they are too small).</para>
 
     <para>The buffers created by this ioctl will have as minimum size the size
-defined by the <structfield>format.pix.sizeimage</structfield> field. If the
+defined by the <structfield>format.pix.sizeimage</structfield> field (or the
+corresponding fields for other format types). Usually if the
 <structfield>format.pix.sizeimage</structfield> field is less than the minimum
-required for the given format, then <structfield>sizeimage</structfield> will be
-increased by the driver to that minimum to allocate the buffers. If it is
-larger, then the value will be used as-is. The same applies to the
-<structfield>sizeimage</structfield> field of the
-<structname>v4l2_plane_pix_format</structname> structure in the case of
-multiplanar formats.</para>
+required for the given format, then an error will be returned since drivers will
+typically not allow this. If it is larger, then the value will be used as-is.
+In other words, the driver may reject the requested size, but if it is accepted
+the driver will use it unchanged.</para>
 
     <para>When the ioctl is called with a pointer to this structure the driver
 will attempt to allocate up to the requested number of buffers and store the
 actual number allocated and the starting index in the
 <structfield>count</structfield> and the <structfield>index</structfield> fields
 respectively. On return <structfield>count</structfield> can be smaller than
-the number requested. The driver may also increase buffer sizes if required,
-however, it will not update <structfield>sizeimage</structfield> field values.
-The user has to use <constant>VIDIOC_QUERYBUF</constant> to retrieve that
-information.</para>
+the number requested.</para>
 
     <table pgwide="1" frame="none" id="v4l2-create-buffers">
       <title>struct <structname>v4l2_create_buffers</structname></title>
diff --git a/Documentation/DocBook/media/v4l/vidioc-dbg-g-chip-info.xml b/Documentation/DocBook/media/v4l/vidioc-dbg-g-chip-info.xml
index 4c4603c..f14a3bb 100644
--- a/Documentation/DocBook/media/v4l/vidioc-dbg-g-chip-info.xml
+++ b/Documentation/DocBook/media/v4l/vidioc-dbg-g-chip-info.xml
@@ -99,7 +99,7 @@
     <para>We recommended the <application>v4l2-dbg</application>
 utility over calling this ioctl directly. It is available from the
 LinuxTV v4l-dvb repository; see <ulink
-url="http://linuxtv.org/repo/">http://linuxtv.org/repo/</ulink> for
+url="https://linuxtv.org/repo/">https://linuxtv.org/repo/</ulink> for
 access instructions.</para>
 
     <!-- Note for convenience vidioc-dbg-g-register.sgml
diff --git a/Documentation/DocBook/media/v4l/vidioc-dbg-g-register.xml b/Documentation/DocBook/media/v4l/vidioc-dbg-g-register.xml
index 3d038e7..5877f68 100644
--- a/Documentation/DocBook/media/v4l/vidioc-dbg-g-register.xml
+++ b/Documentation/DocBook/media/v4l/vidioc-dbg-g-register.xml
@@ -117,7 +117,7 @@
     <para>We recommended the <application>v4l2-dbg</application>
 utility over calling these ioctls directly. It is available from the
 LinuxTV v4l-dvb repository; see <ulink
-url="http://linuxtv.org/repo/">http://linuxtv.org/repo/</ulink> for
+url="https://linuxtv.org/repo/">https://linuxtv.org/repo/</ulink> for
 access instructions.</para>
 
     <!-- Note for convenience vidioc-dbg-g-chip-info.sgml
diff --git a/Documentation/DocBook/media/v4l/vidioc-enumstd.xml b/Documentation/DocBook/media/v4l/vidioc-enumstd.xml
index 8065099..f18454e 100644
--- a/Documentation/DocBook/media/v4l/vidioc-enumstd.xml
+++ b/Documentation/DocBook/media/v4l/vidioc-enumstd.xml
@@ -198,7 +198,7 @@
 <constant>V4L2_STD_ATSC_16_VSB</constant> are U.S. terrestrial digital
 TV standards. Presently the V4L2 API does not support digital TV. See
 also the Linux DVB API at <ulink
-url="http://linuxtv.org">http://linuxtv.org</ulink>.</para>
+url="https://linuxtv.org">https://linuxtv.org</ulink>.</para>
 <para><programlisting>
 #define V4L2_STD_PAL_BG         (V4L2_STD_PAL_B         |\
 				 V4L2_STD_PAL_B1        |\
diff --git a/Documentation/DocBook/media/v4l/vidioc-g-ext-ctrls.xml b/Documentation/DocBook/media/v4l/vidioc-g-ext-ctrls.xml
index 842536a..eb82f7e 100644
--- a/Documentation/DocBook/media/v4l/vidioc-g-ext-ctrls.xml
+++ b/Documentation/DocBook/media/v4l/vidioc-g-ext-ctrls.xml
@@ -61,7 +61,7 @@
 
     <para>Applications must always fill in the
 <structfield>count</structfield>,
-<structfield>ctrl_class</structfield>,
+<structfield>which</structfield>,
 <structfield>controls</structfield> and
 <structfield>reserved</structfield> fields of &v4l2-ext-controls;, and
 initialize the &v4l2-ext-control; array pointed to by the
@@ -109,7 +109,7 @@
 value or if an error is returned.</para>
 
     <para>When the <structfield>id</structfield> or
-<structfield>ctrl_class</structfield> is invalid drivers return an
+<structfield>which</structfield> is invalid drivers return an
 &EINVAL;. When the value is out of bounds drivers can choose to take
 the closest valid value or return an &ERANGE;, whatever seems more
 appropriate. In the first case the new value is set in
@@ -223,7 +223,12 @@
       <tgroup cols="3">
 	&cs-str;
 	<tbody valign="top">
+	 <row>
+	    <entry>union</entry>
+	    <entry>(anonymous)</entry>
+	  </row>
 	  <row>
+	    <entry></entry>
 	    <entry>__u32</entry>
 	    <entry><structfield>ctrl_class</structfield></entry>
 	    <entry>The control class to which all controls belong, see
@@ -235,6 +240,23 @@
 supports this feature.</entry>
 	  </row>
 	  <row>
+	    <entry></entry>
+	    <entry>__u32</entry>
+	    <entry><structfield>which</structfield></entry>
+	    <entry><para>Which value of the control to get/set/try. <constant>V4L2_CTRL_WHICH_CUR_VAL</constant>
+will return the current value of the control and <constant>V4L2_CTRL_WHICH_DEF_VAL</constant> will
+return the default value of the control. Please note that you can only get the default value of the
+control, you cannot set or try it.</para>
+<para>For backwards compatibility you can also use a control class here (see
+<xref linkend="ctrl-class" />). In that case all controls have to belong to that
+control class. This usage is deprecated, instead just use <constant>V4L2_CTRL_WHICH_CUR_VAL</constant>.
+There are some very old drivers that do not yet support <constant>V4L2_CTRL_WHICH_CUR_VAL</constant>
+and that require a control class here. You can test for such drivers by setting ctrl_class to
+<constant>V4L2_CTRL_WHICH_CUR_VAL</constant> and calling VIDIOC_TRY_EXT_CTRLS with a count of 0.
+If that fails, then the driver does not support <constant>V4L2_CTRL_WHICH_CUR_VAL</constant>.</para>
+</entry>
+	  </row>
+	  <row>
 	    <entry>__u32</entry>
 	    <entry><structfield>count</structfield></entry>
 	    <entry>The number of controls in the controls array. May
@@ -390,7 +412,7 @@
 	<listitem>
 	  <para>The &v4l2-ext-control; <structfield>id</structfield>
 is invalid, the &v4l2-ext-controls;
-<structfield>ctrl_class</structfield> is invalid, or the &v4l2-ext-control;
+<structfield>which</structfield> is invalid, or the &v4l2-ext-control;
 <structfield>value</structfield> was inappropriate (e.g. the given menu
 index is not supported by the driver). This error code is
 also returned by the <constant>VIDIOC_S_EXT_CTRLS</constant> and
diff --git a/Documentation/DocBook/media_api.tmpl b/Documentation/DocBook/media_api.tmpl
index 9203703..7b77e0f 100644
--- a/Documentation/DocBook/media_api.tmpl
+++ b/Documentation/DocBook/media_api.tmpl
@@ -19,10 +19,10 @@
 <!ENTITY cs-def                 "<colspec colname='c1' colwidth='3*' /><colspec colname='c2' colwidth='1*' /><colspec colname='c3' colwidth='4*' /><spanspec spanname='hspan' namest='c1' nameend='c3' />">
 
 <!-- Video for Linux mailing list address. -->
-<!ENTITY v4l-ml                 "<ulink url='http://www.linuxtv.org/lists.php'>http://www.linuxtv.org/lists.php</ulink>">
+<!ENTITY v4l-ml                 "<ulink url='https://linuxtv.org/lists.php'>https://linuxtv.org/lists.php</ulink>">
 
 <!-- LinuxTV v4l-dvb repository. -->
-<!ENTITY v4l-dvb		"<ulink url='http://linuxtv.org/repo/'>http://linuxtv.org/repo/</ulink>">
+<!ENTITY v4l-dvb		"<ulink url='https://linuxtv.org/repo/'>https://linuxtv.org/repo/</ulink>">
 <!ENTITY dash-ent-8             "<entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry>">
 <!ENTITY dash-ent-10            "<entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry>">
 <!ENTITY dash-ent-12            "<entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry>">
@@ -91,7 +91,7 @@
 	      components, like mixers, PCM capture, PCM playback, etc, which
 	      are controlled via ALSA API.</para>
 	<para>For additional information and for the latest development code,
-		see: <ulink url="http://linuxtv.org">http://linuxtv.org</ulink>.</para>
+		see: <ulink url="https://linuxtv.org">https://linuxtv.org</ulink>.</para>
 	<para>For discussing improvements, reporting troubles, sending new drivers, etc, please mail to: <ulink url="http://vger.kernel.org/vger-lists.html#linux-media">Linux Media Mailing List (LMML).</ulink>.</para>
 </preface>
 
diff --git a/Documentation/RCU/Design/Requirements/2013-08-is-it-dead.png b/Documentation/RCU/Design/Requirements/2013-08-is-it-dead.png
new file mode 100644
index 0000000..7496a55
--- /dev/null
+++ b/Documentation/RCU/Design/Requirements/2013-08-is-it-dead.png
Binary files differ
diff --git a/Documentation/RCU/Design/Requirements/GPpartitionReaders1.svg b/Documentation/RCU/Design/Requirements/GPpartitionReaders1.svg
new file mode 100644
index 0000000..4b4014f
--- /dev/null
+++ b/Documentation/RCU/Design/Requirements/GPpartitionReaders1.svg
@@ -0,0 +1,374 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   width="447.99197"
+   height="428.19299"
+   id="svg2"
+   version="1.1"
+   inkscape:version="0.48.3.1 r9886"
+   sodipodi:docname="GPpartitionReaders1.svg">
+  <defs
+     id="defs4">
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend"
+       style="overflow:visible">
+      <path
+         id="path3792"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lstart"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lstart"
+       style="overflow:visible">
+      <path
+         id="path3789"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(1.1,0,0,1.1,1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+  </defs>
+  <sodipodi:namedview
+     id="base"
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1.0"
+     inkscape:pageopacity="0.0"
+     inkscape:pageshadow="2"
+     inkscape:zoom="1.6184291"
+     inkscape:cx="223.99599"
+     inkscape:cy="214.0965"
+     inkscape:document-units="px"
+     inkscape:current-layer="layer1"
+     showgrid="false"
+     inkscape:window-width="979"
+     inkscape:window-height="836"
+     inkscape:window-x="571"
+     inkscape:window-y="335"
+     inkscape:window-maximized="0"
+     fit-margin-top="5"
+     fit-margin-left="5"
+     fit-margin-right="5"
+     fit-margin-bottom="5" />
+  <metadata
+     id="metadata7">
+    <rdf:RDF>
+      <cc:Work
+         rdf:about="">
+        <dc:format>image/svg+xml</dc:format>
+        <dc:type
+           rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+        <dc:title></dc:title>
+      </cc:Work>
+    </rdf:RDF>
+  </metadata>
+  <g
+     inkscape:label="Layer 1"
+     inkscape:groupmode="layer"
+     id="layer1"
+     transform="translate(-28.441125,-185.60612)">
+    <flowRoot
+       xml:space="preserve"
+       id="flowRoot2985"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"><flowRegion
+         id="flowRegion2987"><rect
+           id="rect2989"
+           width="82.85714"
+           height="11.428572"
+           x="240"
+           y="492.36218" /></flowRegion><flowPara
+         id="flowPara2991"></flowPara></flowRoot>    <g
+       id="g4433"
+       transform="translate(2,0)">
+      <text
+         sodipodi:linespacing="125%"
+         id="text2993"
+         y="-261.66608"
+         x="412.12299"
+         style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+         xml:space="preserve"
+         transform="matrix(0,1,-1,0,0,0)"><tspan
+           y="-261.66608"
+           x="412.12299"
+           id="tspan2995"
+           sodipodi:role="line">synchronize_rcu()</tspan></text>
+      <g
+         id="g4417"
+         transform="matrix(0,1,-1,0,730.90257,222.4928)">
+        <path
+           style="fill:none;stroke:#000000;stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1;marker-start:url(#Arrow2Lstart);marker-end:url(#Arrow2Lend)"
+           d="m 97.580736,477.4048 183.140664,0"
+           id="path2997"
+           inkscape:connector-curvature="0"
+           sodipodi:nodetypes="cc" />
+        <path
+           style="fill:none;stroke:#000000;stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1"
+           d="m 96.752718,465.38398 0,22.62742"
+           id="path4397"
+           inkscape:connector-curvature="0"
+           sodipodi:nodetypes="cc" />
+        <path
+           style="fill:none;stroke:#000000;stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1"
+           d="m 281.54942,465.38397 0,22.62742"
+           id="path4397-5"
+           inkscape:connector-curvature="0"
+           sodipodi:nodetypes="cc" />
+      </g>
+    </g>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="112.04738"
+       y="268.18076"
+       id="text4429"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4431"
+         x="112.04738"
+         y="268.18076">WRITE_ONCE(a, 1);</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="112.04738"
+       y="439.13766"
+       id="text4441"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4443"
+         x="112.04738"
+         y="439.13766">WRITE_ONCE(b, 1);</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="255.60869"
+       y="309.29346"
+       id="text4445"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4447"
+         x="255.60869"
+         y="309.29346">r1 = READ_ONCE(a);</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="255.14423"
+       y="520.61786"
+       id="text4449"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4451"
+         x="255.14423"
+         y="520.61786">WRITE_ONCE(c, 1);</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="396.10254"
+       y="384.71124"
+       id="text4453"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4455"
+         x="396.10254"
+         y="384.71124">r2 = READ_ONCE(b);</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="396.10254"
+       y="582.13617"
+       id="text4457"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4459"
+         x="396.10254"
+         y="582.13617">r3 = READ_ONCE(c);</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="112.08231"
+       y="213.91006"
+       id="text4461"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4463"
+         x="112.08231"
+         y="213.91006">thread0()</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="252.34512"
+       y="213.91006"
+       id="text4461-6"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4463-0"
+         x="252.34512"
+         y="213.91006">thread1()</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="396.42557"
+       y="213.91006"
+       id="text4461-2"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4463-2"
+         x="396.42557"
+         y="213.91006">thread2()</tspan></text>
+    <rect
+       style="fill:none;stroke:#000000;stroke-width:1;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       id="rect4495"
+       width="436.28488"
+       height="416.4859"
+       x="34.648232"
+       y="191.10612" />
+    <path
+       style="fill:none;stroke:#000000;stroke-width:1;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       d="m 183.14066,191.10612 0,417.193 -0.70711,0"
+       id="path4497"
+       inkscape:connector-curvature="0" />
+    <path
+       style="fill:none;stroke:#000000;stroke-width:1;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       d="m 325.13867,191.10612 0,417.193 -0.70711,0"
+       id="path4497-5"
+       inkscape:connector-curvature="0" />
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="111.75929"
+       y="251.53981"
+       id="text4429-8"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4431-9"
+         x="111.75929"
+         y="251.53981">rcu_read_lock();</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="396.10254"
+       y="367.91556"
+       id="text4429-8-9"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4431-9-4"
+         x="396.10254"
+         y="367.91556">rcu_read_lock();</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="396.10254"
+       y="597.40289"
+       id="text4429-8-9-3"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4431-9-4-4"
+         x="396.10254"
+         y="597.40289">rcu_read_unlock();</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="111.75929"
+       y="453.15311"
+       id="text4429-8-9-3-1"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4431-9-4-4-6"
+         x="111.75929"
+         y="453.15311">rcu_read_unlock();</tspan></text>
+    <path
+       style="fill:none;stroke:#000000;stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1"
+       d="m 33.941125,227.87568 436.284885,0 0,0.7071"
+       id="path4608"
+       inkscape:connector-curvature="0" />
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="394.94427"
+       y="345.66351"
+       id="text4648"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4650"
+         x="394.94427"
+         y="345.66351">QS</tspan></text>
+    <path
+       sodipodi:type="arc"
+       style="fill:none;stroke:#000000;stroke-width:1;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       id="path4652"
+       sodipodi:cx="358.85669"
+       sodipodi:cy="142.87541"
+       sodipodi:rx="10.960155"
+       sodipodi:ry="10.253048"
+       d="m 358.86939,132.62237 a 10.960155,10.253048 0 1 1 -0.0228,0"
+       transform="translate(36.441125,199.60612)"
+       sodipodi:start="4.7135481"
+       sodipodi:end="10.994651"
+       sodipodi:open="true" />
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="112.11968"
+       y="475.77856"
+       id="text4648-4"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4650-4"
+         x="112.11968"
+         y="475.77856">QS</tspan></text>
+    <path
+       sodipodi:type="arc"
+       style="fill:none;stroke:#000000;stroke-width:1;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       id="path4652-7"
+       sodipodi:cx="358.85669"
+       sodipodi:cy="142.87541"
+       sodipodi:rx="10.960155"
+       sodipodi:ry="10.253048"
+       d="m 358.86939,132.62237 a 10.960155,10.253048 0 1 1 -0.0228,0"
+       transform="translate(-246.38346,329.72117)"
+       sodipodi:start="4.7135481"
+       sodipodi:end="10.994651"
+       sodipodi:open="true" />
+    <path
+       sodipodi:type="arc"
+       style="fill:#ffffff;fill-opacity:1;stroke:#000000;stroke-width:1;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       id="path4652-7-7"
+       sodipodi:cx="358.85669"
+       sodipodi:cy="142.87541"
+       sodipodi:rx="10.960155"
+       sodipodi:ry="10.253048"
+       d="m 358.86939,132.62237 a 10.960155,10.253048 0 1 1 -0.0228,0"
+       transform="translate(-103.65246,202.90878)"
+       sodipodi:start="4.7135481"
+       sodipodi:end="10.994651"
+       sodipodi:open="true" />
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="254.85066"
+       y="348.96619"
+       id="text4648-4-3"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4650-4-5"
+         x="254.85066"
+         y="348.96619">QS</tspan></text>
+  </g>
+</svg>
diff --git a/Documentation/RCU/Design/Requirements/RCUApplicability.svg b/Documentation/RCU/Design/Requirements/RCUApplicability.svg
new file mode 100644
index 0000000..ebcbeee
--- /dev/null
+++ b/Documentation/RCU/Design/Requirements/RCUApplicability.svg
@@ -0,0 +1,237 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Creator: fig2dev Version 3.2 Patchlevel 5d -->
+
+<!-- CreationDate: Tue Mar  4 18:34:25 2014 -->
+
+<!-- Magnification: 3.000 -->
+
+<svg
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   width="1089.1382"
+   height="668.21368"
+   viewBox="-2121 -36 14554.634 8876.4061"
+   id="svg2"
+   version="1.1"
+   inkscape:version="0.48.3.1 r9886"
+   sodipodi:docname="RCUApplicability.svg">
+  <metadata
+     id="metadata40">
+    <rdf:RDF>
+      <cc:Work
+         rdf:about="">
+        <dc:format>image/svg+xml</dc:format>
+        <dc:type
+           rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+        <dc:title />
+      </cc:Work>
+    </rdf:RDF>
+  </metadata>
+  <defs
+     id="defs38" />
+  <sodipodi:namedview
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1"
+     objecttolerance="10"
+     gridtolerance="10"
+     guidetolerance="10"
+     inkscape:pageopacity="0"
+     inkscape:pageshadow="2"
+     inkscape:window-width="849"
+     inkscape:window-height="639"
+     id="namedview36"
+     showgrid="false"
+     inkscape:zoom="0.51326165"
+     inkscape:cx="544.56912"
+     inkscape:cy="334.10686"
+     inkscape:window-x="149"
+     inkscape:window-y="448"
+     inkscape:window-maximized="0"
+     inkscape:current-layer="g4"
+     fit-margin-top="5"
+     fit-margin-left="5"
+     fit-margin-right="5"
+     fit-margin-bottom="5" />
+  <g
+     style="fill:none;stroke-width:0.025in"
+     id="g4"
+     transform="translate(-2043.6828,14.791398)">
+    <!-- Line: box -->
+    <rect
+       x="0"
+       y="0"
+       width="14400"
+       height="8775"
+       rx="0"
+       style="fill:#ffa1a1;stroke:#000000;stroke-width:21;stroke-linecap:butt;stroke-linejoin:miter"
+       id="rect6" />
+    <!-- Line: box -->
+    <rect
+       x="1350"
+       y="0"
+       width="11700"
+       height="6075"
+       rx="0"
+       style="fill:#ffff00;stroke:#000000;stroke-width:21;stroke-linecap:butt;stroke-linejoin:miter"
+       id="rect8" />
+    <!-- Line: box -->
+    <rect
+       x="2700"
+       y="0"
+       width="9000"
+       height="4275"
+       rx="0"
+       style="fill:#00ff00;stroke:#000000;stroke-width:21;stroke-linecap:butt;stroke-linejoin:miter"
+       id="rect10" />
+    <!-- Line: box -->
+    <rect
+       x="4050"
+       y="0"
+       width="6300"
+       height="2475"
+       rx="0"
+       style="fill:#87cfff;stroke:#000000;stroke-width:21;stroke-linecap:butt;stroke-linejoin:miter"
+       id="rect12" />
+    <!-- Text -->
+    <text
+       xml:space="preserve"
+       x="7200"
+       y="900"
+       font-style="normal"
+       font-weight="normal"
+       font-size="324"
+       id="text14"
+       sodipodi:linespacing="125%"
+       style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"><tspan
+         style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"
+         id="tspan3017">Read-Mostly, Stale &amp;</tspan></text>
+    <!-- Text -->
+    <text
+       xml:space="preserve"
+       x="7200"
+       y="1350"
+       font-style="normal"
+       font-weight="normal"
+       font-size="324"
+       id="text16"
+       sodipodi:linespacing="125%"
+       style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"><tspan
+         style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"
+         id="tspan3019">Inconsistent Data OK</tspan></text>
+    <!-- Text -->
+    <text
+       xml:space="preserve"
+       x="7200"
+       y="1800"
+       font-style="normal"
+       font-weight="normal"
+       font-size="324"
+       id="text18"
+       sodipodi:linespacing="125%"
+       style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"><tspan
+         style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"
+         id="tspan3021">(RCU Works Great!!!)</tspan></text>
+    <!-- Text -->
+    <text
+       xml:space="preserve"
+       x="7200"
+       y="3825"
+       font-style="normal"
+       font-weight="normal"
+       font-size="324"
+       id="text20"
+       sodipodi:linespacing="125%"
+       style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"><tspan
+         style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"
+         id="tspan3023">(RCU Works Well)</tspan></text>
+    <!-- Text -->
+    <text
+       xml:space="preserve"
+       x="7200"
+       y="3375"
+       font-style="normal"
+       font-weight="normal"
+       font-size="324"
+       id="text22"
+       sodipodi:linespacing="125%"
+       style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"><tspan
+         style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"
+         id="tspan3025">Read-Mostly, Need Consistent Data</tspan></text>
+    <!-- Text -->
+    <text
+       xml:space="preserve"
+       x="7200"
+       y="5175"
+       font-style="normal"
+       font-weight="normal"
+       font-size="324"
+       id="text24"
+       sodipodi:linespacing="125%"
+       style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"><tspan
+         style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"
+         id="tspan3027">Read-Write, Need Consistent Data</tspan></text>
+    <!-- Text -->
+    <text
+       xml:space="preserve"
+       x="7200"
+       y="6975"
+       font-style="normal"
+       font-weight="normal"
+       font-size="324"
+       id="text26"
+       style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"
+       sodipodi:linespacing="125%">Update-Mostly, Need Consistent Data</text>
+    <!-- Text -->
+    <text
+       xml:space="preserve"
+       x="7200"
+       y="5625"
+       font-style="normal"
+       font-weight="normal"
+       font-size="324"
+       id="text28"
+       sodipodi:linespacing="125%"
+       style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"><tspan
+         style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"
+         id="tspan3029">(RCU Might Be OK...)</tspan></text>
+    <!-- Text -->
+    <text
+       xml:space="preserve"
+       x="7200"
+       y="7875"
+       font-style="normal"
+       font-weight="normal"
+       font-size="324"
+       id="text30"
+       style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"
+       sodipodi:linespacing="125%">(1) Provide Existence Guarantees For Update-Friendly Mechanisms</text>
+    <!-- Text -->
+    <text
+       xml:space="preserve"
+       x="7200"
+       y="8325"
+       font-style="normal"
+       font-weight="normal"
+       font-size="324"
+       id="text32"
+       style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"
+       sodipodi:linespacing="125%">(2) Provide Wait-Free Read-Side Primitives for Real-Time Use)</text>
+    <!-- Text -->
+    <text
+       xml:space="preserve"
+       x="7200"
+       y="7425"
+       font-style="normal"
+       font-weight="normal"
+       font-size="324"
+       id="text34"
+       style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"
+       sodipodi:linespacing="125%">(RCU is Very Unlikely to be the Right Tool For The Job, But it Can:</text>
+  </g>
+</svg>
diff --git a/Documentation/RCU/Design/Requirements/ReadersPartitionGP1.svg b/Documentation/RCU/Design/Requirements/ReadersPartitionGP1.svg
new file mode 100644
index 0000000..48cd162
--- /dev/null
+++ b/Documentation/RCU/Design/Requirements/ReadersPartitionGP1.svg
@@ -0,0 +1,639 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   width="735.25"
+   height="516.21875"
+   id="svg2"
+   version="1.1"
+   inkscape:version="0.48.3.1 r9886"
+   sodipodi:docname="ReadersPartitionGP1.svg">
+  <defs
+     id="defs4">
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend"
+       style="overflow:visible">
+      <path
+         id="path3792"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lstart"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lstart"
+       style="overflow:visible">
+      <path
+         id="path3789"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(1.1,0,0,1.1,1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lstart"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lstart-4"
+       style="overflow:visible">
+      <path
+         id="path3789-9"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(1.1,0,0,1.1,1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-4"
+       style="overflow:visible">
+      <path
+         id="path3792-4"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+  </defs>
+  <sodipodi:namedview
+     id="base"
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1.0"
+     inkscape:pageopacity="0.0"
+     inkscape:pageshadow="2"
+     inkscape:zoom="1.3670394"
+     inkscape:cx="367.26465"
+     inkscape:cy="258.46182"
+     inkscape:document-units="px"
+     inkscape:current-layer="g4433-6"
+     showgrid="false"
+     inkscape:window-width="1351"
+     inkscape:window-height="836"
+     inkscape:window-x="438"
+     inkscape:window-y="335"
+     inkscape:window-maximized="0"
+     fit-margin-top="5"
+     fit-margin-left="5"
+     fit-margin-right="5"
+     fit-margin-bottom="5" />
+  <metadata
+     id="metadata7">
+    <rdf:RDF>
+      <cc:Work
+         rdf:about="">
+        <dc:format>image/svg+xml</dc:format>
+        <dc:type
+           rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+        <dc:title />
+      </cc:Work>
+    </rdf:RDF>
+  </metadata>
+  <g
+     inkscape:label="Layer 1"
+     inkscape:groupmode="layer"
+     id="layer1"
+     transform="translate(-29.15625,-185.59375)">
+    <flowRoot
+       xml:space="preserve"
+       id="flowRoot2985"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"><flowRegion
+         id="flowRegion2987"><rect
+           id="rect2989"
+           width="82.85714"
+           height="11.428572"
+           x="240"
+           y="492.36218" /></flowRegion><flowPara
+         id="flowPara2991" /></flowRoot>    <g
+       id="g4433"
+       transform="translate(2,-12)">
+      <text
+         sodipodi:linespacing="125%"
+         id="text2993"
+         y="-261.66608"
+         x="436.12299"
+         style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+         xml:space="preserve"
+         transform="matrix(0,1,-1,0,0,0)"><tspan
+           y="-261.66608"
+           x="436.12299"
+           id="tspan2995"
+           sodipodi:role="line">synchronize_rcu()</tspan></text>
+      <g
+         id="g4417"
+         transform="matrix(0,1,-1,0,730.90257,222.4928)">
+        <path
+           style="fill:none;stroke:#000000;stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1;marker-start:url(#Arrow2Lstart);marker-end:url(#Arrow2Lend)"
+           d="M 97.580736,477.4048 327.57913,476.09759"
+           id="path2997"
+           inkscape:connector-curvature="0"
+           sodipodi:nodetypes="cc" />
+        <path
+           style="fill:none;stroke:#000000;stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1"
+           d="m 96.752718,465.38398 0,22.62742"
+           id="path4397"
+           inkscape:connector-curvature="0"
+           sodipodi:nodetypes="cc" />
+        <path
+           style="fill:none;stroke:#000000;stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1"
+           d="m 328.40703,465.38397 0,22.62742"
+           id="path4397-5"
+           inkscape:connector-curvature="0"
+           sodipodi:nodetypes="cc" />
+      </g>
+    </g>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="112.04738"
+       y="268.18076"
+       id="text4429"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4431"
+         x="112.04738"
+         y="268.18076">WRITE_ONCE(a, 1);</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="112.04738"
+       y="487.13766"
+       id="text4441"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4443"
+         x="112.04738"
+         y="487.13766">WRITE_ONCE(b, 1);</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="255.60869"
+       y="297.29346"
+       id="text4445"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4447"
+         x="255.60869"
+         y="297.29346">r1 = READ_ONCE(a);</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="255.14423"
+       y="554.61786"
+       id="text4449"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4451"
+         x="255.14423"
+         y="554.61786">WRITE_ONCE(c, 1);</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="396.10254"
+       y="370.71124"
+       id="text4453"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4455"
+         x="396.10254"
+         y="370.71124">WRITE_ONCE(d, 1);</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="396.10254"
+       y="572.13617"
+       id="text4457"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4459"
+         x="396.10254"
+         y="572.13617">r2 = READ_ONCE(c);</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="112.08231"
+       y="213.91006"
+       id="text4461"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4463"
+         x="112.08231"
+         y="213.91006">thread0()</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="252.34512"
+       y="213.91006"
+       id="text4461-6"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4463-0"
+         x="252.34512"
+         y="213.91006">thread1()</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="396.42557"
+       y="213.91006"
+       id="text4461-2"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4463-2"
+         x="396.42557"
+         y="213.91006">thread2()</tspan></text>
+    <rect
+       style="fill:none;stroke:#000000;stroke-width:1;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       id="rect4495"
+       width="724.25244"
+       height="505.21201"
+       x="34.648232"
+       y="191.10612" />
+    <path
+       style="fill:none;stroke:#000000;stroke-width:1;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       d="m 183.14066,191.10612 0,504.24243"
+       id="path4497"
+       inkscape:connector-curvature="0"
+       sodipodi:nodetypes="cc" />
+    <path
+       style="fill:none;stroke:#000000;stroke-width:1;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       d="m 325.13867,191.10612 0,504.24243"
+       id="path4497-5"
+       inkscape:connector-curvature="0"
+       sodipodi:nodetypes="cc" />
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="111.75929"
+       y="251.53981"
+       id="text4429-8"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4431-9"
+         x="111.75929"
+         y="251.53981">rcu_read_lock();</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="396.10254"
+       y="353.91556"
+       id="text4429-8-9"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4431-9-4"
+         x="396.10254"
+         y="353.91556">rcu_read_lock();</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="396.10254"
+       y="587.40289"
+       id="text4429-8-9-3"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4431-9-4-4"
+         x="396.10254"
+         y="587.40289">rcu_read_unlock();</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="111.75929"
+       y="501.15311"
+       id="text4429-8-9-3-1"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4431-9-4-4-6"
+         x="111.75929"
+         y="501.15311">rcu_read_unlock();</tspan></text>
+    <path
+       style="fill:none;stroke:#000000;stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1"
+       d="m 33.941125,227.87568 724.941765,0"
+       id="path4608"
+       inkscape:connector-curvature="0"
+       sodipodi:nodetypes="cc" />
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="394.94427"
+       y="331.66351"
+       id="text4648"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4650"
+         x="394.94427"
+         y="331.66351">QS</tspan></text>
+    <path
+       sodipodi:type="arc"
+       style="fill:none;stroke:#000000;stroke-width:1;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       id="path4652"
+       sodipodi:cx="358.85669"
+       sodipodi:cy="142.87541"
+       sodipodi:rx="10.960155"
+       sodipodi:ry="10.253048"
+       d="m 358.86939,132.62237 a 10.960155,10.253048 0 1 1 -0.0228,0"
+       transform="translate(36.441125,185.60612)"
+       sodipodi:start="4.7135481"
+       sodipodi:end="10.994651"
+       sodipodi:open="true" />
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="112.11968"
+       y="523.77856"
+       id="text4648-4"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4650-4"
+         x="112.11968"
+         y="523.77856">QS</tspan></text>
+    <path
+       sodipodi:type="arc"
+       style="fill:none;stroke:#000000;stroke-width:1;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       id="path4652-7"
+       sodipodi:cx="358.85669"
+       sodipodi:cy="142.87541"
+       sodipodi:rx="10.960155"
+       sodipodi:ry="10.253048"
+       d="m 358.86939,132.62237 a 10.960155,10.253048 0 1 1 -0.0228,0"
+       transform="translate(-246.38346,377.72117)"
+       sodipodi:start="4.7135481"
+       sodipodi:end="10.994651"
+       sodipodi:open="true" />
+    <path
+       sodipodi:type="arc"
+       style="fill:#ffffff;fill-opacity:1;stroke:#000000;stroke-width:1;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       id="path4652-7-7"
+       sodipodi:cx="358.85669"
+       sodipodi:cy="142.87541"
+       sodipodi:rx="10.960155"
+       sodipodi:ry="10.253048"
+       d="m 358.86939,132.62237 a 10.960155,10.253048 0 1 1 -0.0228,0"
+       transform="translate(-103.65246,190.90878)"
+       sodipodi:start="4.7135481"
+       sodipodi:end="10.994651"
+       sodipodi:open="true" />
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="254.85066"
+       y="336.96619"
+       id="text4648-4-3"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4650-4-5"
+         x="254.85066"
+         y="336.96619">QS</tspan></text>
+    <path
+       style="fill:none;stroke:#000000;stroke-width:1;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       d="m 470.93311,190.39903 0,504.24243"
+       id="path4497-5-6"
+       inkscape:connector-curvature="0"
+       sodipodi:nodetypes="cc" />
+    <path
+       style="fill:none;stroke:#000000;stroke-width:1;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       d="m 616.22755,190.38323 0,504.24243"
+       id="path4497-5-2"
+       inkscape:connector-curvature="0"
+       sodipodi:nodetypes="cc" />
+    <g
+       id="g4433-6"
+       transform="translate(288.0964,78.32827)">
+      <text
+         sodipodi:linespacing="125%"
+         id="text2993-7"
+         y="-261.66608"
+         x="440.12299"
+         style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+         xml:space="preserve"
+         transform="matrix(0,1,-1,0,0,0)"><tspan
+           y="-261.66608"
+           x="440.12299"
+           id="tspan2995-1"
+           sodipodi:role="line">synchronize_rcu()</tspan></text>
+      <g
+         id="g4417-1"
+         transform="matrix(0,1,-1,0,730.90257,222.4928)">
+        <path
+           style="fill:none;stroke:#000000;stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1;marker-start:url(#Arrow2Lstart);marker-end:url(#Arrow2Lend)"
+           d="M 97.580736,477.4048 328.5624,477.07246"
+           id="path2997-2"
+           inkscape:connector-curvature="0"
+           sodipodi:nodetypes="cc" />
+        <path
+           style="fill:none;stroke:#000000;stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1"
+           d="m 96.752718,465.38398 0,22.62742"
+           id="path4397-3"
+           inkscape:connector-curvature="0"
+           sodipodi:nodetypes="cc" />
+        <path
+           style="fill:none;stroke:#000000;stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1"
+           d="m 329.39039,465.38397 0,22.62742"
+           id="path4397-5-4"
+           inkscape:connector-curvature="0"
+           sodipodi:nodetypes="cc" />
+      </g>
+    </g>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="541.70508"
+       y="387.6217"
+       id="text4445-0"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4447-5"
+         x="541.70508"
+         y="387.6217">r3 = READ_ONCE(d);</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="541.2406"
+       y="646.94611"
+       id="text4449-6"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4451-6"
+         x="541.2406"
+         y="646.94611">WRITE_ONCE(e, 1);</tspan></text>
+    <path
+       sodipodi:type="arc"
+       style="fill:#ffffff;fill-opacity:1;stroke:#000000;stroke-width:1;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       id="path4652-7-7-5"
+       sodipodi:cx="358.85669"
+       sodipodi:cy="142.87541"
+       sodipodi:rx="10.960155"
+       sodipodi:ry="10.253048"
+       d="m 358.86939,132.62237 a 10.960155,10.253048 0 1 1 -0.0228,0"
+       transform="translate(182.44393,281.23704)"
+       sodipodi:start="4.7135481"
+       sodipodi:end="10.994651"
+       sodipodi:open="true" />
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="540.94702"
+       y="427.29443"
+       id="text4648-4-3-1"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4650-4-5-7"
+         x="540.94702"
+         y="427.29443">QS</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="686.27747"
+       y="461.83929"
+       id="text4453-7"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4455-1"
+         x="686.27747"
+         y="461.83929">r4 = READ_ONCE(b);</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="686.27747"
+       y="669.26422"
+       id="text4457-9"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4459-2"
+         x="686.27747"
+         y="669.26422">r5 = READ_ONCE(e);</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="686.27747"
+       y="445.04358"
+       id="text4429-8-9-33"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4431-9-4-2"
+         x="686.27747"
+         y="445.04358">rcu_read_lock();</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="686.27747"
+       y="684.53094"
+       id="text4429-8-9-3-8"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4431-9-4-4-5"
+         x="686.27747"
+         y="684.53094">rcu_read_unlock();</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="685.11914"
+       y="422.79153"
+       id="text4648-9"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4650-7"
+         x="685.11914"
+         y="422.79153">QS</tspan></text>
+    <path
+       sodipodi:type="arc"
+       style="fill:none;stroke:#000000;stroke-width:1;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       id="path4652-8"
+       sodipodi:cx="358.85669"
+       sodipodi:cy="142.87541"
+       sodipodi:rx="10.960155"
+       sodipodi:ry="10.253048"
+       d="m 358.86939,132.62237 a 10.960155,10.253048 0 1 1 -0.0228,0"
+       transform="translate(326.61602,276.73415)"
+       sodipodi:start="4.7135481"
+       sodipodi:end="10.994651"
+       sodipodi:open="true" />
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="397.85934"
+       y="609.59003"
+       id="text4648-5"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4650-77"
+         x="397.85934"
+         y="609.59003">QS</tspan></text>
+    <path
+       sodipodi:type="arc"
+       style="fill:none;stroke:#000000;stroke-width:1;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       id="path4652-80"
+       sodipodi:cx="358.85669"
+       sodipodi:cy="142.87541"
+       sodipodi:rx="10.960155"
+       sodipodi:ry="10.253048"
+       d="m 358.86939,132.62237 a 10.960155,10.253048 0 1 1 -0.0228,0"
+       transform="translate(39.356201,463.53264)"
+       sodipodi:start="4.7135481"
+       sodipodi:end="10.994651"
+       sodipodi:open="true" />
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="256.75986"
+       y="586.99133"
+       id="text4648-5-2"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4650-77-7"
+         x="256.75986"
+         y="586.99133">QS</tspan></text>
+    <path
+       sodipodi:type="arc"
+       style="fill:none;stroke:#000000;stroke-width:1;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       id="path4652-80-5"
+       sodipodi:cx="358.85669"
+       sodipodi:cy="142.87541"
+       sodipodi:rx="10.960155"
+       sodipodi:ry="10.253048"
+       d="m 358.86939,132.62237 a 10.960155,10.253048 0 1 1 -0.0228,0"
+       transform="translate(-101.74328,440.93395)"
+       sodipodi:start="4.7135481"
+       sodipodi:end="10.994651"
+       sodipodi:open="true" />
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="546.22791"
+       y="213.91006"
+       id="text4461-2-5"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4463-2-6"
+         x="546.22791"
+         y="213.91006">thread3()</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="684.00067"
+       y="213.91006"
+       id="text4461-2-1"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4463-2-0"
+         x="684.00067"
+         y="213.91006">thread4()</tspan></text>
+  </g>
+</svg>
diff --git a/Documentation/RCU/Design/Requirements/Requirements.html b/Documentation/RCU/Design/Requirements/Requirements.html
new file mode 100644
index 0000000..a725f99
--- /dev/null
+++ b/Documentation/RCU/Design/Requirements/Requirements.html
@@ -0,0 +1,2897 @@
+<!-- DO NOT HAND EDIT. -->
+<!-- Instead, edit Documentation/RCU/Design/Requirements/Requirements.htmlx and run 'sh htmlqqz.sh Documentation/RCU/Design/Requirements/Requirements' -->
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"
+        "http://www.w3.org/TR/html4/loose.dtd">
+        <html>
+        <head><title>A Tour Through RCU's Requirements [LWN.net]</title>
+        <meta HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=utf-8">
+
+<h1>A Tour Through RCU's Requirements</h1>
+
+<p>Copyright IBM Corporation, 2015</p>
+<p>Author: Paul E.&nbsp;McKenney</p>
+<p><i>The initial version of this document appeared in the
+<a href="https://lwn.net/">LWN</a> articles
+<a href="https://lwn.net/Articles/652156/">here</a>,
+<a href="https://lwn.net/Articles/652677/">here</a>, and
+<a href="https://lwn.net/Articles/653326/">here</a>.</i></p>
+
+<h2>Introduction</h2>
+
+<p>
+Read-copy update (RCU) is a synchronization mechanism that is often
+used as a replacement for reader-writer locking.
+RCU is unusual in that updaters do not block readers,
+which means that RCU's read-side primitives can be exceedingly fast
+and scalable.
+In addition, updaters can make useful forward progress concurrently
+with readers.
+However, all this concurrency between RCU readers and updaters does raise
+the question of exactly what RCU readers are doing, which in turn
+raises the question of exactly what RCU's requirements are.
+
+<p>
+This document therefore summarizes RCU's requirements, and can be thought
+of as an informal, high-level specification for RCU.
+It is important to understand that RCU's specification is primarily
+empirical in nature;
+in fact, I learned about many of these requirements the hard way.
+This situation might cause some consternation, however, not only
+has this learning process been a lot of fun, but it has also been
+a great privilege to work with so many people willing to apply
+technologies in interesting new ways.
+
+<p>
+All that aside, here are the categories of currently known RCU requirements:
+</p>
+
+<ol>
+<li>	<a href="#Fundamental Requirements">
+	Fundamental Requirements</a>
+<li>	<a href="#Fundamental Non-Requirements">Fundamental Non-Requirements</a>
+<li>	<a href="#Parallelism Facts of Life">
+	Parallelism Facts of Life</a>
+<li>	<a href="#Quality-of-Implementation Requirements">
+	Quality-of-Implementation Requirements</a>
+<li>	<a href="#Linux Kernel Complications">
+	Linux Kernel Complications</a>
+<li>	<a href="#Software-Engineering Requirements">
+	Software-Engineering Requirements</a>
+<li>	<a href="#Other RCU Flavors">
+	Other RCU Flavors</a>
+<li>	<a href="#Possible Future Changes">
+	Possible Future Changes</a>
+</ol>
+
+<p>
+This is followed by a <a href="#Summary">summary</a>,
+which is in turn followed by the inevitable
+<a href="#Answers to Quick Quizzes">answers to the quick quizzes</a>.
+
+<h2><a name="Fundamental Requirements">Fundamental Requirements</a></h2>
+
+<p>
+RCU's fundamental requirements are the closest thing RCU has to hard
+mathematical requirements.
+These are:
+
+<ol>
+<li>	<a href="#Grace-Period Guarantee">
+	Grace-Period Guarantee</a>
+<li>	<a href="#Publish-Subscribe Guarantee">
+	Publish-Subscribe Guarantee</a>
+<li>	<a href="#Memory-Barrier Guarantees">
+	Memory-Barrier Guarantees</a>
+<li>	<a href="#RCU Primitives Guaranteed to Execute Unconditionally">
+	RCU Primitives Guaranteed to Execute Unconditionally</a>
+<li>	<a href="#Guaranteed Read-to-Write Upgrade">
+	Guaranteed Read-to-Write Upgrade</a>
+</ol>
+
+<h3><a name="Grace-Period Guarantee">Grace-Period Guarantee</a></h3>
+
+<p>
+RCU's grace-period guarantee is unusual in being premeditated:
+Jack Slingwine and I had this guarantee firmly in mind when we started
+work on RCU (then called &ldquo;rclock&rdquo;) in the early 1990s.
+That said, the past two decades of experience with RCU have produced
+a much more detailed understanding of this guarantee.
+
+<p>
+RCU's grace-period guarantee allows updaters to wait for the completion
+of all pre-existing RCU read-side critical sections.
+An RCU read-side critical section
+begins with the marker <tt>rcu_read_lock()</tt> and ends with
+the marker <tt>rcu_read_unlock()</tt>.
+These markers may be nested, and RCU treats a nested set as one
+big RCU read-side critical section.
+Production-quality implementations of <tt>rcu_read_lock()</tt> and
+<tt>rcu_read_unlock()</tt> are extremely lightweight, and in
+fact have exactly zero overhead in Linux kernels built for production
+use with <tt>CONFIG_PREEMPT=n</tt>.
+
+<p>
+This guarantee allows ordering to be enforced with extremely low
+overhead to readers, for example:
+
+<blockquote>
+<pre>
+ 1 int x, y;
+ 2
+ 3 void thread0(void)
+ 4 {
+ 5   rcu_read_lock();
+ 6   r1 = READ_ONCE(x);
+ 7   r2 = READ_ONCE(y);
+ 8   rcu_read_unlock();
+ 9 }
+10
+11 void thread1(void)
+12 {
+13   WRITE_ONCE(x, 1);
+14   synchronize_rcu();
+15   WRITE_ONCE(y, 1);
+16 }
+</pre>
+</blockquote>
+
+<p>
+Because the <tt>synchronize_rcu()</tt> on line&nbsp;14 waits for
+all pre-existing readers, any instance of <tt>thread0()</tt> that
+loads a value of zero from <tt>x</tt> must complete before
+<tt>thread1()</tt> stores to <tt>y</tt>, so that instance must
+also load a value of zero from <tt>y</tt>.
+Similarly, any instance of <tt>thread0()</tt> that loads a value of
+one from <tt>y</tt> must have started after the
+<tt>synchronize_rcu()</tt> started, and must therefore also load
+a value of one from <tt>x</tt>.
+Therefore, the outcome:
+<blockquote>
+<pre>
+(r1 == 0 &amp;&amp; r2 == 1)
+</pre>
+</blockquote>
+cannot happen.
+
+<p><a name="Quick Quiz 1"><b>Quick Quiz 1</b>:</a>
+Wait a minute!
+You said that updaters can make useful forward progress concurrently
+with readers, but pre-existing readers will block
+<tt>synchronize_rcu()</tt>!!!
+Just who are you trying to fool???
+<br><a href="#qq1answer">Answer</a>
+
+<p>
+This scenario resembles one of the first uses of RCU in
+<a href="https://en.wikipedia.org/wiki/DYNIX">DYNIX/ptx</a>,
+which managed a distributed lock manager's transition into
+a state suitable for handling recovery from node failure,
+more or less as follows:
+
+<blockquote>
+<pre>
+ 1 #define STATE_NORMAL        0
+ 2 #define STATE_WANT_RECOVERY 1
+ 3 #define STATE_RECOVERING    2
+ 4 #define STATE_WANT_NORMAL   3
+ 5
+ 6 int state = STATE_NORMAL;
+ 7
+ 8 void do_something_dlm(void)
+ 9 {
+10   int state_snap;
+11
+12   rcu_read_lock();
+13   state_snap = READ_ONCE(state);
+14   if (state_snap == STATE_NORMAL)
+15     do_something();
+16   else
+17     do_something_carefully();
+18   rcu_read_unlock();
+19 }
+20
+21 void start_recovery(void)
+22 {
+23   WRITE_ONCE(state, STATE_WANT_RECOVERY);
+24   synchronize_rcu();
+25   WRITE_ONCE(state, STATE_RECOVERING);
+26   recovery();
+27   WRITE_ONCE(state, STATE_WANT_NORMAL);
+28   synchronize_rcu();
+29   WRITE_ONCE(state, STATE_NORMAL);
+30 }
+</pre>
+</blockquote>
+
+<p>
+The RCU read-side critical section in <tt>do_something_dlm()</tt>
+works with the <tt>synchronize_rcu()</tt> in <tt>start_recovery()</tt>
+to guarantee that <tt>do_something()</tt> never runs concurrently
+with <tt>recovery()</tt>, but with little or no synchronization
+overhead in <tt>do_something_dlm()</tt>.
+
+<p><a name="Quick Quiz 2"><b>Quick Quiz 2</b>:</a>
+Why is the <tt>synchronize_rcu()</tt> on line&nbsp;28 needed?
+<br><a href="#qq2answer">Answer</a>
+
+<p>
+In order to avoid fatal problems such as deadlocks,
+an RCU read-side critical section must not contain calls to
+<tt>synchronize_rcu()</tt>.
+Similarly, an RCU read-side critical section must not
+contain anything that waits, directly or indirectly, on completion of
+an invocation of <tt>synchronize_rcu()</tt>.
+
+<p>
+Although RCU's grace-period guarantee is useful in and of itself, with
+<a href="https://lwn.net/Articles/573497/">quite a few use cases</a>,
+it would be good to be able to use RCU to coordinate read-side
+access to linked data structures.
+For this, the grace-period guarantee is not sufficient, as can
+be seen in function <tt>add_gp_buggy()</tt> below.
+We will look at the reader's code later, but in the meantime, just think of
+the reader as locklessly picking up the <tt>gp</tt> pointer,
+and, if the value loaded is non-<tt>NULL</tt>, locklessly accessing the
+<tt>-&gt;a</tt> and <tt>-&gt;b</tt> fields.
+
+<blockquote>
+<pre>
+ 1 bool add_gp_buggy(int a, int b)
+ 2 {
+ 3   p = kmalloc(sizeof(*p), GFP_KERNEL);
+ 4   if (!p)
+ 5     return -ENOMEM;
+ 6   spin_lock(&amp;gp_lock);
+ 7   if (rcu_access_pointer(gp)) {
+ 8     spin_unlock(&amp;gp_lock);
+ 9     return false;
+10   }
+11   p-&gt;a = a;
+12   p-&gt;b = a;
+13   gp = p; /* ORDERING BUG */
+14   spin_unlock(&amp;gp_lock);
+15   return true;
+16 }
+</pre>
+</blockquote>
+
+<p>
+The problem is that both the compiler and weakly ordered CPUs are within
+their rights to reorder this code as follows:
+
+<blockquote>
+<pre>
+ 1 bool add_gp_buggy_optimized(int a, int b)
+ 2 {
+ 3   p = kmalloc(sizeof(*p), GFP_KERNEL);
+ 4   if (!p)
+ 5     return -ENOMEM;
+ 6   spin_lock(&amp;gp_lock);
+ 7   if (rcu_access_pointer(gp)) {
+ 8     spin_unlock(&amp;gp_lock);
+ 9     return false;
+10   }
+<b>11   gp = p; /* ORDERING BUG */
+12   p-&gt;a = a;
+13   p-&gt;b = a;</b>
+14   spin_unlock(&amp;gp_lock);
+15   return true;
+16 }
+</pre>
+</blockquote>
+
+<p>
+If an RCU reader fetches <tt>gp</tt> just after
+<tt>add_gp_buggy_optimized</tt> executes line&nbsp;11,
+it will see garbage in the <tt>-&gt;a</tt> and <tt>-&gt;b</tt>
+fields.
+And this is but one of many ways in which compiler and hardware optimizations
+could cause trouble.
+Therefore, we clearly need some way to prevent the compiler and the CPU from
+reordering in this manner, which brings us to the publish-subscribe
+guarantee discussed in the next section.
+
+<h3><a name="Publish-Subscribe Guarantee">Publish/Subscribe Guarantee</a></h3>
+
+<p>
+RCU's publish-subscribe guarantee allows data to be inserted
+into a linked data structure without disrupting RCU readers.
+The updater uses <tt>rcu_assign_pointer()</tt> to insert the
+new data, and readers use <tt>rcu_dereference()</tt> to
+access data, whether new or old.
+The following shows an example of insertion:
+
+<blockquote>
+<pre>
+ 1 bool add_gp(int a, int b)
+ 2 {
+ 3   p = kmalloc(sizeof(*p), GFP_KERNEL);
+ 4   if (!p)
+ 5     return -ENOMEM;
+ 6   spin_lock(&amp;gp_lock);
+ 7   if (rcu_access_pointer(gp)) {
+ 8     spin_unlock(&amp;gp_lock);
+ 9     return false;
+10   }
+11   p-&gt;a = a;
+12   p-&gt;b = a;
+13   rcu_assign_pointer(gp, p);
+14   spin_unlock(&amp;gp_lock);
+15   return true;
+16 }
+</pre>
+</blockquote>
+
+<p>
+The <tt>rcu_assign_pointer()</tt> on line&nbsp;13 is conceptually
+equivalent to a simple assignment statement, but also guarantees
+that its assignment will
+happen after the two assignments in lines&nbsp;11 and&nbsp;12,
+similar to the C11 <tt>memory_order_release</tt> store operation.
+It also prevents any number of &ldquo;interesting&rdquo; compiler
+optimizations, for example, the use of <tt>gp</tt> as a scratch
+location immediately preceding the assignment.
+
+<p><a name="Quick Quiz 3"><b>Quick Quiz 3</b>:</a>
+But <tt>rcu_assign_pointer()</tt> does nothing to prevent the
+two assignments to <tt>p-&gt;a</tt> and <tt>p-&gt;b</tt>
+from being reordered.
+Can't that also cause problems?
+<br><a href="#qq3answer">Answer</a>
+
+<p>
+It is tempting to assume that the reader need not do anything special
+to control its accesses to the RCU-protected data,
+as shown in <tt>do_something_gp_buggy()</tt> below:
+
+<blockquote>
+<pre>
+ 1 bool do_something_gp_buggy(void)
+ 2 {
+ 3   rcu_read_lock();
+ 4   p = gp;  /* OPTIMIZATIONS GALORE!!! */
+ 5   if (p) {
+ 6     do_something(p-&gt;a, p-&gt;b);
+ 7     rcu_read_unlock();
+ 8     return true;
+ 9   }
+10   rcu_read_unlock();
+11   return false;
+12 }
+</pre>
+</blockquote>
+
+<p>
+However, this temptation must be resisted because there are a
+surprisingly large number of ways that the compiler
+(to say nothing of
+<a href="https://h71000.www7.hp.com/wizard/wiz_2637.html">DEC Alpha CPUs</a>)
+can trip this code up.
+For but one example, if the compiler were short of registers, it
+might choose to refetch from <tt>gp</tt> rather than keeping
+a separate copy in <tt>p</tt> as follows:
+
+<blockquote>
+<pre>
+ 1 bool do_something_gp_buggy_optimized(void)
+ 2 {
+ 3   rcu_read_lock();
+ 4   if (gp) { /* OPTIMIZATIONS GALORE!!! */
+<b> 5     do_something(gp-&gt;a, gp-&gt;b);</b>
+ 6     rcu_read_unlock();
+ 7     return true;
+ 8   }
+ 9   rcu_read_unlock();
+10   return false;
+11 }
+</pre>
+</blockquote>
+
+<p>
+If this function ran concurrently with a series of updates that
+replaced the current structure with a new one,
+the fetches of <tt>gp-&gt;a</tt>
+and <tt>gp-&gt;b</tt> might well come from two different structures,
+which could cause serious confusion.
+To prevent this (and much else besides), <tt>do_something_gp()</tt> uses
+<tt>rcu_dereference()</tt> to fetch from <tt>gp</tt>:
+
+<blockquote>
+<pre>
+ 1 bool do_something_gp(void)
+ 2 {
+ 3   rcu_read_lock();
+ 4   p = rcu_dereference(gp);
+ 5   if (p) {
+ 6     do_something(p-&gt;a, p-&gt;b);
+ 7     rcu_read_unlock();
+ 8     return true;
+ 9   }
+10   rcu_read_unlock();
+11   return false;
+12 }
+</pre>
+</blockquote>
+
+<p>
+The <tt>rcu_dereference()</tt> uses volatile casts and (for DEC Alpha)
+memory barriers in the Linux kernel.
+Should a
+<a href="http://www.rdrop.com/users/paulmck/RCU/consume.2015.07.13a.pdf">high-quality implementation of C11 <tt>memory_order_consume</tt> [PDF]</a>
+ever appear, then <tt>rcu_dereference()</tt> could be implemented
+as a <tt>memory_order_consume</tt> load.
+Regardless of the exact implementation, a pointer fetched by
+<tt>rcu_dereference()</tt> may not be used outside of the
+outermost RCU read-side critical section containing that
+<tt>rcu_dereference()</tt>, unless protection of
+the corresponding data element has been passed from RCU to some
+other synchronization mechanism, most commonly locking or
+<a href="https://www.kernel.org/doc/Documentation/RCU/rcuref.txt">reference counting</a>.
+
+<p>
+In short, updaters use <tt>rcu_assign_pointer()</tt> and readers
+use <tt>rcu_dereference()</tt>, and these two RCU API elements
+work together to ensure that readers have a consistent view of
+newly added data elements.
+
+<p>
+Of course, it is also necessary to remove elements from RCU-protected
+data structures, for example, using the following process:
+
+<ol>
+<li>	Remove the data element from the enclosing structure.
+<li>	Wait for all pre-existing RCU read-side critical sections
+	to complete (because only pre-existing readers can possibly have
+	a reference to the newly removed data element).
+<li>	At this point, only the updater has a reference to the
+	newly removed data element, so it can safely reclaim
+	the data element, for example, by passing it to <tt>kfree()</tt>.
+</ol>
+
+This process is implemented by <tt>remove_gp_synchronous()</tt>:
+
+<blockquote>
+<pre>
+ 1 bool remove_gp_synchronous(void)
+ 2 {
+ 3   struct foo *p;
+ 4
+ 5   spin_lock(&amp;gp_lock);
+ 6   p = rcu_access_pointer(gp);
+ 7   if (!p) {
+ 8     spin_unlock(&amp;gp_lock);
+ 9     return false;
+10   }
+11   rcu_assign_pointer(gp, NULL);
+12   spin_unlock(&amp;gp_lock);
+13   synchronize_rcu();
+14   kfree(p);
+15   return true;
+16 }
+</pre>
+</blockquote>
+
+<p>
+This function is straightforward, with line&nbsp;13 waiting for a grace
+period before line&nbsp;14 frees the old data element.
+This waiting ensures that readers will reach line&nbsp;7 of
+<tt>do_something_gp()</tt> before the data element referenced by
+<tt>p</tt> is freed.
+The <tt>rcu_access_pointer()</tt> on line&nbsp;6 is similar to
+<tt>rcu_dereference()</tt>, except that:
+
+<ol>
+<li>	The value returned by <tt>rcu_access_pointer()</tt>
+	cannot be dereferenced.
+	If you want to access the value pointed to as well as
+	the pointer itself, use <tt>rcu_dereference()</tt>
+	instead of <tt>rcu_access_pointer()</tt>.
+<li>	The call to <tt>rcu_access_pointer()</tt> need not be
+	protected.
+	In contrast, <tt>rcu_dereference()</tt> must either be
+	within an RCU read-side critical section or in a code
+	segment where the pointer cannot change, for example, in
+	code protected by the corresponding update-side lock.
+</ol>
+
+<p><a name="Quick Quiz 4"><b>Quick Quiz 4</b>:</a>
+Without the <tt>rcu_dereference()</tt> or the
+<tt>rcu_access_pointer()</tt>, what destructive optimizations
+might the compiler make use of?
+<br><a href="#qq4answer">Answer</a>
+
+<p>
+In short, RCU's publish-subscribe guarantee is provided by the combination
+of <tt>rcu_assign_pointer()</tt> and <tt>rcu_dereference()</tt>.
+This guarantee allows data elements to be safely added to RCU-protected
+linked data structures without disrupting RCU readers.
+This guarantee can be used in combination with the grace-period
+guarantee to also allow data elements to be removed from RCU-protected
+linked data structures, again without disrupting RCU readers.
+
+<p>
+This guarantee was only partially premeditated.
+DYNIX/ptx used an explicit memory barrier for publication, but had nothing
+resembling <tt>rcu_dereference()</tt> for subscription, nor did it
+have anything resembling the <tt>smp_read_barrier_depends()</tt>
+that was later subsumed into <tt>rcu_dereference()</tt>.
+The need for these operations made itself known quite suddenly at a
+late-1990s meeting with the DEC Alpha architects, back in the days when
+DEC was still a free-standing company.
+It took the Alpha architects a good hour to convince me that any sort
+of barrier would ever be needed, and it then took me a good <i>two</i> hours
+to convince them that their documentation did not make this point clear.
+More recent work with the C and C++ standards committees have provided
+much education on tricks and traps from the compiler.
+In short, compilers were much less tricky in the early 1990s, but in
+2015, don't even think about omitting <tt>rcu_dereference()</tt>!
+
+<h3><a name="Memory-Barrier Guarantees">Memory-Barrier Guarantees</a></h3>
+
+<p>
+The previous section's simple linked-data-structure scenario clearly
+demonstrates the need for RCU's stringent memory-ordering guarantees on
+systems with more than one CPU:
+
+<ol>
+<li>	Each CPU that has an RCU read-side critical section that
+	begins before <tt>synchronize_rcu()</tt> starts is
+	guaranteed to execute a full memory barrier between the time
+	that the RCU read-side critical section ends and the time that
+	<tt>synchronize_rcu()</tt> returns.
+	Without this guarantee, a pre-existing RCU read-side critical section
+	might hold a reference to the newly removed <tt>struct foo</tt>
+	after the <tt>kfree()</tt> on line&nbsp;14 of
+	<tt>remove_gp_synchronous()</tt>.
+<li>	Each CPU that has an RCU read-side critical section that ends
+	after <tt>synchronize_rcu()</tt> returns is guaranteed
+	to execute a full memory barrier between the time that
+	<tt>synchronize_rcu()</tt> begins and the time that the RCU
+	read-side critical section begins.
+	Without this guarantee, a later RCU read-side critical section
+	running after the <tt>kfree()</tt> on line&nbsp;14 of
+	<tt>remove_gp_synchronous()</tt> might
+	later run <tt>do_something_gp()</tt> and find the
+	newly deleted <tt>struct foo</tt>.
+<li>	If the task invoking <tt>synchronize_rcu()</tt> remains
+	on a given CPU, then that CPU is guaranteed to execute a full
+	memory barrier sometime during the execution of
+	<tt>synchronize_rcu()</tt>.
+	This guarantee ensures that the <tt>kfree()</tt> on
+	line&nbsp;14 of <tt>remove_gp_synchronous()</tt> really does
+	execute after the removal on line&nbsp;11.
+<li>	If the task invoking <tt>synchronize_rcu()</tt> migrates
+	among a group of CPUs during that invocation, then each of the
+	CPUs in that group is guaranteed to execute a full memory barrier
+	sometime during the execution of <tt>synchronize_rcu()</tt>.
+	This guarantee also ensures that the <tt>kfree()</tt> on
+	line&nbsp;14 of <tt>remove_gp_synchronous()</tt> really does
+	execute after the removal on
+	line&nbsp;11, but also in the case where the thread executing the
+	<tt>synchronize_rcu()</tt> migrates in the meantime.
+</ol>
+
+<p><a name="Quick Quiz 5"><b>Quick Quiz 5</b>:</a>
+Given that multiple CPUs can start RCU read-side critical sections
+at any time without any ordering whatsoever, how can RCU possibly tell whether
+or not a given RCU read-side critical section starts before a
+given instance of <tt>synchronize_rcu()</tt>?
+<br><a href="#qq5answer">Answer</a>
+
+<p><a name="Quick Quiz 6"><b>Quick Quiz 6</b>:</a>
+The first and second guarantees require unbelievably strict ordering!
+Are all these memory barriers <i> really</i> required?
+<br><a href="#qq6answer">Answer</a>
+
+<p>
+Note that these memory-barrier requirements do not replace the fundamental
+RCU requirement that a grace period wait for all pre-existing readers.
+On the contrary, the memory barriers called out in this section must operate in
+such a way as to <i>enforce</i> this fundamental requirement.
+Of course, different implementations enforce this requirement in different
+ways, but enforce it they must.
+
+<h3><a name="RCU Primitives Guaranteed to Execute Unconditionally">RCU Primitives Guaranteed to Execute Unconditionally</a></h3>
+
+<p>
+The common-case RCU primitives are unconditional.
+They are invoked, they do their job, and they return, with no possibility
+of error, and no need to retry.
+This is a key RCU design philosophy.
+
+<p>
+However, this philosophy is pragmatic rather than pigheaded.
+If someone comes up with a good justification for a particular conditional
+RCU primitive, it might well be implemented and added.
+After all, this guarantee was reverse-engineered, not premeditated.
+The unconditional nature of the RCU primitives was initially an
+accident of implementation, and later experience with synchronization
+primitives with conditional primitives caused me to elevate this
+accident to a guarantee.
+Therefore, the justification for adding a conditional primitive to
+RCU would need to be based on detailed and compelling use cases.
+
+<h3><a name="Guaranteed Read-to-Write Upgrade">Guaranteed Read-to-Write Upgrade</a></h3>
+
+<p>
+As far as RCU is concerned, it is always possible to carry out an
+update within an RCU read-side critical section.
+For example, that RCU read-side critical section might search for
+a given data element, and then might acquire the update-side
+spinlock in order to update that element, all while remaining
+in that RCU read-side critical section.
+Of course, it is necessary to exit the RCU read-side critical section
+before invoking <tt>synchronize_rcu()</tt>, however, this
+inconvenience can be avoided through use of the
+<tt>call_rcu()</tt> and <tt>kfree_rcu()</tt> API members
+described later in this document.
+
+<p><a name="Quick Quiz 7"><b>Quick Quiz 7</b>:</a>
+But how does the upgrade-to-write operation exclude other readers?
+<br><a href="#qq7answer">Answer</a>
+
+<p>
+This guarantee allows lookup code to be shared between read-side
+and update-side code, and was premeditated, appearing in the earliest
+DYNIX/ptx RCU documentation.
+
+<h2><a name="Fundamental Non-Requirements">Fundamental Non-Requirements</a></h2>
+
+<p>
+RCU provides extremely lightweight readers, and its read-side guarantees,
+though quite useful, are correspondingly lightweight.
+It is therefore all too easy to assume that RCU is guaranteeing more
+than it really is.
+Of course, the list of things that RCU does not guarantee is infinitely
+long, however, the following sections list a few non-guarantees that
+have caused confusion.
+Except where otherwise noted, these non-guarantees were premeditated.
+
+<ol>
+<li>	<a href="#Readers Impose Minimal Ordering">
+	Readers Impose Minimal Ordering</a>
+<li>	<a href="#Readers Do Not Exclude Updaters">
+	Readers Do Not Exclude Updaters</a>
+<li>	<a href="#Updaters Only Wait For Old Readers">
+	Updaters Only Wait For Old Readers</a>
+<li>	<a href="#Grace Periods Don't Partition Read-Side Critical Sections">
+	Grace Periods Don't Partition Read-Side Critical Sections</a>
+<li>	<a href="#Read-Side Critical Sections Don't Partition Grace Periods">
+	Read-Side Critical Sections Don't Partition Grace Periods</a>
+<li>	<a href="#Disabling Preemption Does Not Block Grace Periods">
+	Disabling Preemption Does Not Block Grace Periods</a>
+</ol>
+
+<h3><a name="Readers Impose Minimal Ordering">Readers Impose Minimal Ordering</a></h3>
+
+<p>
+Reader-side markers such as <tt>rcu_read_lock()</tt> and
+<tt>rcu_read_unlock()</tt> provide absolutely no ordering guarantees
+except through their interaction with the grace-period APIs such as
+<tt>synchronize_rcu()</tt>.
+To see this, consider the following pair of threads:
+
+<blockquote>
+<pre>
+ 1 void thread0(void)
+ 2 {
+ 3   rcu_read_lock();
+ 4   WRITE_ONCE(x, 1);
+ 5   rcu_read_unlock();
+ 6   rcu_read_lock();
+ 7   WRITE_ONCE(y, 1);
+ 8   rcu_read_unlock();
+ 9 }
+10
+11 void thread1(void)
+12 {
+13   rcu_read_lock();
+14   r1 = READ_ONCE(y);
+15   rcu_read_unlock();
+16   rcu_read_lock();
+17   r2 = READ_ONCE(x);
+18   rcu_read_unlock();
+19 }
+</pre>
+</blockquote>
+
+<p>
+After <tt>thread0()</tt> and <tt>thread1()</tt> execute
+concurrently, it is quite possible to have
+
+<blockquote>
+<pre>
+(r1 == 1 &amp;&amp; r2 == 0)
+</pre>
+</blockquote>
+
+(that is, <tt>y</tt> appears to have been assigned before <tt>x</tt>),
+which would not be possible if <tt>rcu_read_lock()</tt> and
+<tt>rcu_read_unlock()</tt> had much in the way of ordering
+properties.
+But they do not, so the CPU is within its rights
+to do significant reordering.
+This is by design:  Any significant ordering constraints would slow down
+these fast-path APIs.
+
+<p><a name="Quick Quiz 8"><b>Quick Quiz 8</b>:</a>
+Can't the compiler also reorder this code?
+<br><a href="#qq8answer">Answer</a>
+
+<h3><a name="Readers Do Not Exclude Updaters">Readers Do Not Exclude Updaters</a></h3>
+
+<p>
+Neither <tt>rcu_read_lock()</tt> nor <tt>rcu_read_unlock()</tt>
+exclude updates.
+All they do is to prevent grace periods from ending.
+The following example illustrates this:
+
+<blockquote>
+<pre>
+ 1 void thread0(void)
+ 2 {
+ 3   rcu_read_lock();
+ 4   r1 = READ_ONCE(y);
+ 5   if (r1) {
+ 6     do_something_with_nonzero_x();
+ 7     r2 = READ_ONCE(x);
+ 8     WARN_ON(!r2); /* BUG!!! */
+ 9   }
+10   rcu_read_unlock();
+11 }
+12
+13 void thread1(void)
+14 {
+15   spin_lock(&amp;my_lock);
+16   WRITE_ONCE(x, 1);
+17   WRITE_ONCE(y, 1);
+18   spin_unlock(&amp;my_lock);
+19 }
+</pre>
+</blockquote>
+
+<p>
+If the <tt>thread0()</tt> function's <tt>rcu_read_lock()</tt>
+excluded the <tt>thread1()</tt> function's update,
+the <tt>WARN_ON()</tt> could never fire.
+But the fact is that <tt>rcu_read_lock()</tt> does not exclude
+much of anything aside from subsequent grace periods, of which
+<tt>thread1()</tt> has none, so the
+<tt>WARN_ON()</tt> can and does fire.
+
+<h3><a name="Updaters Only Wait For Old Readers">Updaters Only Wait For Old Readers</a></h3>
+
+<p>
+It might be tempting to assume that after <tt>synchronize_rcu()</tt>
+completes, there are no readers executing.
+This temptation must be avoided because
+new readers can start immediately after <tt>synchronize_rcu()</tt>
+starts, and <tt>synchronize_rcu()</tt> is under no
+obligation to wait for these new readers.
+
+<p><a name="Quick Quiz 9"><b>Quick Quiz 9</b>:</a>
+Suppose that synchronize_rcu() did wait until all readers had completed.
+Would the updater be able to rely on this?
+<br><a href="#qq9answer">Answer</a>
+
+<h3><a name="Grace Periods Don't Partition Read-Side Critical Sections">
+Grace Periods Don't Partition Read-Side Critical Sections</a></h3>
+
+<p>
+It is tempting to assume that if any part of one RCU read-side critical
+section precedes a given grace period, and if any part of another RCU
+read-side critical section follows that same grace period, then all of
+the first RCU read-side critical section must precede all of the second.
+However, this just isn't the case: A single grace period does not
+partition the set of RCU read-side critical sections.
+An example of this situation can be illustrated as follows, where
+<tt>x</tt>, <tt>y</tt>, and <tt>z</tt> are initially all zero:
+
+<blockquote>
+<pre>
+ 1 void thread0(void)
+ 2 {
+ 3   rcu_read_lock();
+ 4   WRITE_ONCE(a, 1);
+ 5   WRITE_ONCE(b, 1);
+ 6   rcu_read_unlock();
+ 7 }
+ 8
+ 9 void thread1(void)
+10 {
+11   r1 = READ_ONCE(a);
+12   synchronize_rcu();
+13   WRITE_ONCE(c, 1);
+14 }
+15
+16 void thread2(void)
+17 {
+18   rcu_read_lock();
+19   r2 = READ_ONCE(b);
+20   r3 = READ_ONCE(c);
+21   rcu_read_unlock();
+22 }
+</pre>
+</blockquote>
+
+<p>
+It turns out that the outcome:
+
+<blockquote>
+<pre>
+(r1 == 1 &amp;&amp; r2 == 0 &amp;&amp; r3 == 1)
+</pre>
+</blockquote>
+
+is entirely possible.
+The following figure show how this can happen, with each circled
+<tt>QS</tt> indicating the point at which RCU recorded a
+<i>quiescent state</i> for each thread, that is, a state in which
+RCU knows that the thread cannot be in the midst of an RCU read-side
+critical section that started before the current grace period:
+
+<p><img src="GPpartitionReaders1.svg" alt="GPpartitionReaders1.svg" width="60%"></p>
+
+<p>
+If it is necessary to partition RCU read-side critical sections in this
+manner, it is necessary to use two grace periods, where the first
+grace period is known to end before the second grace period starts:
+
+<blockquote>
+<pre>
+ 1 void thread0(void)
+ 2 {
+ 3   rcu_read_lock();
+ 4   WRITE_ONCE(a, 1);
+ 5   WRITE_ONCE(b, 1);
+ 6   rcu_read_unlock();
+ 7 }
+ 8
+ 9 void thread1(void)
+10 {
+11   r1 = READ_ONCE(a);
+12   synchronize_rcu();
+13   WRITE_ONCE(c, 1);
+14 }
+15
+16 void thread2(void)
+17 {
+18   r2 = READ_ONCE(c);
+19   synchronize_rcu();
+20   WRITE_ONCE(d, 1);
+21 }
+22
+23 void thread3(void)
+24 {
+25   rcu_read_lock();
+26   r3 = READ_ONCE(b);
+27   r4 = READ_ONCE(d);
+28   rcu_read_unlock();
+29 }
+</pre>
+</blockquote>
+
+<p>
+Here, if <tt>(r1 == 1)</tt>, then
+<tt>thread0()</tt>'s write to <tt>b</tt> must happen
+before the end of <tt>thread1()</tt>'s grace period.
+If in addition <tt>(r4 == 1)</tt>, then
+<tt>thread3()</tt>'s read from <tt>b</tt> must happen
+after the beginning of <tt>thread2()</tt>'s grace period.
+If it is also the case that <tt>(r2 == 1)</tt>, then the
+end of <tt>thread1()</tt>'s grace period must precede the
+beginning of <tt>thread2()</tt>'s grace period.
+This mean that the two RCU read-side critical sections cannot overlap,
+guaranteeing that <tt>(r3 == 1)</tt>.
+As a result, the outcome:
+
+<blockquote>
+<pre>
+(r1 == 1 &amp;&amp; r2 == 1 &amp;&amp; r3 == 0 &amp;&amp; r4 == 1)
+</pre>
+</blockquote>
+
+cannot happen.
+
+<p>
+This non-requirement was also non-premeditated, but became apparent
+when studying RCU's interaction with memory ordering.
+
+<h3><a name="Read-Side Critical Sections Don't Partition Grace Periods">
+Read-Side Critical Sections Don't Partition Grace Periods</a></h3>
+
+<p>
+It is also tempting to assume that if an RCU read-side critical section
+happens between a pair of grace periods, then those grace periods cannot
+overlap.
+However, this temptation leads nowhere good, as can be illustrated by
+the following, with all variables initially zero:
+
+<blockquote>
+<pre>
+ 1 void thread0(void)
+ 2 {
+ 3   rcu_read_lock();
+ 4   WRITE_ONCE(a, 1);
+ 5   WRITE_ONCE(b, 1);
+ 6   rcu_read_unlock();
+ 7 }
+ 8
+ 9 void thread1(void)
+10 {
+11   r1 = READ_ONCE(a);
+12   synchronize_rcu();
+13   WRITE_ONCE(c, 1);
+14 }
+15
+16 void thread2(void)
+17 {
+18   rcu_read_lock();
+19   WRITE_ONCE(d, 1);
+20   r2 = READ_ONCE(c);
+21   rcu_read_unlock();
+22 }
+23
+24 void thread3(void)
+25 {
+26   r3 = READ_ONCE(d);
+27   synchronize_rcu();
+28   WRITE_ONCE(e, 1);
+29 }
+30
+31 void thread4(void)
+32 {
+33   rcu_read_lock();
+34   r4 = READ_ONCE(b);
+35   r5 = READ_ONCE(e);
+36   rcu_read_unlock();
+37 }
+</pre>
+</blockquote>
+
+<p>
+In this case, the outcome:
+
+<blockquote>
+<pre>
+(r1 == 1 &amp;&amp; r2 == 1 &amp;&amp; r3 == 1 &amp;&amp; r4 == 0 &amp&amp; r5 == 1)
+</pre>
+</blockquote>
+
+is entirely possible, as illustrated below:
+
+<p><img src="ReadersPartitionGP1.svg" alt="ReadersPartitionGP1.svg" width="100%"></p>
+
+<p>
+Again, an RCU read-side critical section can overlap almost all of a
+given grace period, just so long as it does not overlap the entire
+grace period.
+As a result, an RCU read-side critical section cannot partition a pair
+of RCU grace periods.
+
+<p><a name="Quick Quiz 10"><b>Quick Quiz 10</b>:</a>
+How long a sequence of grace periods, each separated by an RCU read-side
+critical section, would be required to partition the RCU read-side
+critical sections at the beginning and end of the chain?
+<br><a href="#qq10answer">Answer</a>
+
+<h3><a name="Disabling Preemption Does Not Block Grace Periods">
+Disabling Preemption Does Not Block Grace Periods</a></h3>
+
+<p>
+There was a time when disabling preemption on any given CPU would block
+subsequent grace periods.
+However, this was an accident of implementation and is not a requirement.
+And in the current Linux-kernel implementation, disabling preemption
+on a given CPU in fact does not block grace periods, as Oleg Nesterov
+<a href="https://lkml.kernel.org/g/20150614193825.GA19582@redhat.com">demonstrated</a>.
+
+<p>
+If you need a preempt-disable region to block grace periods, you need to add
+<tt>rcu_read_lock()</tt> and <tt>rcu_read_unlock()</tt>, for example
+as follows:
+
+<blockquote>
+<pre>
+ 1 preempt_disable();
+ 2 rcu_read_lock();
+ 3 do_something();
+ 4 rcu_read_unlock();
+ 5 preempt_enable();
+ 6
+ 7 /* Spinlocks implicitly disable preemption. */
+ 8 spin_lock(&amp;mylock);
+ 9 rcu_read_lock();
+10 do_something();
+11 rcu_read_unlock();
+12 spin_unlock(&amp;mylock);
+</pre>
+</blockquote>
+
+<p>
+In theory, you could enter the RCU read-side critical section first,
+but it is more efficient to keep the entire RCU read-side critical
+section contained in the preempt-disable region as shown above.
+Of course, RCU read-side critical sections that extend outside of
+preempt-disable regions will work correctly, but such critical sections
+can be preempted, which forces <tt>rcu_read_unlock()</tt> to do
+more work.
+And no, this is <i>not</i> an invitation to enclose all of your RCU
+read-side critical sections within preempt-disable regions, because
+doing so would degrade real-time response.
+
+<p>
+This non-requirement appeared with preemptible RCU.
+If you need a grace period that waits on non-preemptible code regions, use
+<a href="#Sched Flavor">RCU-sched</a>.
+
+<h2><a name="Parallelism Facts of Life">Parallelism Facts of Life</a></h2>
+
+<p>
+These parallelism facts of life are by no means specific to RCU, but
+the RCU implementation must abide by them.
+They therefore bear repeating:
+
+<ol>
+<li>	Any CPU or task may be delayed at any time,
+	and any attempts to avoid these delays by disabling
+	preemption, interrupts, or whatever are completely futile.
+	This is most obvious in preemptible user-level
+	environments and in virtualized environments (where
+	a given guest OS's VCPUs can be preempted at any time by
+	the underlying hypervisor), but can also happen in bare-metal
+	environments due to ECC errors, NMIs, and other hardware
+	events.
+	Although a delay of more than about 20 seconds can result
+	in splats, the RCU implementation is obligated to use
+	algorithms that can tolerate extremely long delays, but where
+	&ldquo;extremely long&rdquo; is not long enough to allow
+	wrap-around when incrementing a 64-bit counter.
+<li>	Both the compiler and the CPU can reorder memory accesses.
+	Where it matters, RCU must use compiler directives and
+	memory-barrier instructions to preserve ordering.
+<li>	Conflicting writes to memory locations in any given cache line
+	will result in expensive cache misses.
+	Greater numbers of concurrent writes and more-frequent
+	concurrent writes will result in more dramatic slowdowns.
+	RCU is therefore obligated to use algorithms that have
+	sufficient locality to avoid significant performance and
+	scalability problems.
+<li>	As a rough rule of thumb, only one CPU's worth of processing
+	may be carried out under the protection of any given exclusive
+	lock.
+	RCU must therefore use scalable locking designs.
+<li>	Counters are finite, especially on 32-bit systems.
+	RCU's use of counters must therefore tolerate counter wrap,
+	or be designed such that counter wrap would take way more
+	time than a single system is likely to run.
+	An uptime of ten years is quite possible, a runtime
+	of a century much less so.
+	As an example of the latter, RCU's dyntick-idle nesting counter
+	allows 54 bits for interrupt nesting level (this counter
+	is 64 bits even on a 32-bit system).
+	Overflowing this counter requires 2<sup>54</sup>
+	half-interrupts on a given CPU without that CPU ever going idle.
+	If a half-interrupt happened every microsecond, it would take
+	570 years of runtime to overflow this counter, which is currently
+	believed to be an acceptably long time.
+<li>	Linux systems can have thousands of CPUs running a single
+	Linux kernel in a single shared-memory environment.
+	RCU must therefore pay close attention to high-end scalability.
+</ol>
+
+<p>
+This last parallelism fact of life means that RCU must pay special
+attention to the preceding facts of life.
+The idea that Linux might scale to systems with thousands of CPUs would
+have been met with some skepticism in the 1990s, but these requirements
+would have otherwise have been unsurprising, even in the early 1990s.
+
+<h2><a name="Quality-of-Implementation Requirements">Quality-of-Implementation Requirements</a></h2>
+
+<p>
+These sections list quality-of-implementation requirements.
+Although an RCU implementation that ignores these requirements could
+still be used, it would likely be subject to limitations that would
+make it inappropriate for industrial-strength production use.
+Classes of quality-of-implementation requirements are as follows:
+
+<ol>
+<li>	<a href="#Specialization">Specialization</a>
+<li>	<a href="#Performance and Scalability">Performance and Scalability</a>
+<li>	<a href="#Composability">Composability</a>
+<li>	<a href="#Corner Cases">Corner Cases</a>
+</ol>
+
+<p>
+These classes is covered in the following sections.
+
+<h3><a name="Specialization">Specialization</a></h3>
+
+<p>
+RCU is and always has been intended primarily for read-mostly situations, as
+illustrated by the following figure.
+This means that RCU's read-side primitives are optimized, often at the
+expense of its update-side primitives.
+
+<p><img src="RCUApplicability.svg" alt="RCUApplicability.svg" width="70%"></p>
+
+<p>
+This focus on read-mostly situations means that RCU must interoperate
+with other synchronization primitives.
+For example, the <tt>add_gp()</tt> and <tt>remove_gp_synchronous()</tt>
+examples discussed earlier use RCU to protect readers and locking to
+coordinate updaters.
+However, the need extends much farther, requiring that a variety of
+synchronization primitives be legal within RCU read-side critical sections,
+including spinlocks, sequence locks, atomic operations, reference
+counters, and memory barriers.
+
+<p><a name="Quick Quiz 11"><b>Quick Quiz 11</b>:</a>
+What about sleeping locks?
+<br><a href="#qq11answer">Answer</a>
+
+<p>
+It often comes as a surprise that many algorithms do not require a
+consistent view of data, but many can function in that mode,
+with network routing being the poster child.
+Internet routing algorithms take significant time to propagate
+updates, so that by the time an update arrives at a given system,
+that system has been sending network traffic the wrong way for
+a considerable length of time.
+Having a few threads continue to send traffic the wrong way for a
+few more milliseconds is clearly not a problem:  In the worst case,
+TCP retransmissions will eventually get the data where it needs to go.
+In general, when tracking the state of the universe outside of the
+computer, some level of inconsistency must be tolerated due to
+speed-of-light delays if nothing else.
+
+<p>
+Furthermore, uncertainty about external state is inherent in many cases.
+For example, a pair of veternarians might use heartbeat to determine
+whether or not a given cat was alive.
+But how long should they wait after the last heartbeat to decide that
+the cat is in fact dead?
+Waiting less than 400 milliseconds makes no sense because this would
+mean that a relaxed cat would be considered to cycle between death
+and life more than 100 times per minute.
+Moreover, just as with human beings, a cat's heart might stop for
+some period of time, so the exact wait period is a judgment call.
+One of our pair of veternarians might wait 30 seconds before pronouncing
+the cat dead, while the other might insist on waiting a full minute.
+The two veternarians would then disagree on the state of the cat during
+the final 30 seconds of the minute following the last heartbeat, as
+fancifully illustrated below:
+
+<p><img src="2013-08-is-it-dead.png" alt="2013-08-is-it-dead.png" width="431"></p>
+
+<p>
+Interestingly enough, this same situation applies to hardware.
+When push comes to shove, how do we tell whether or not some
+external server has failed?
+We send messages to it periodically, and declare it failed if we
+don't receive a response within a given period of time.
+Policy decisions can usually tolerate short
+periods of inconsistency.
+The policy was decided some time ago, and is only now being put into
+effect, so a few milliseconds of delay is normally inconsequential.
+
+<p>
+However, there are algorithms that absolutely must see consistent data.
+For example, the translation between a user-level SystemV semaphore
+ID to the corresponding in-kernel data structure is protected by RCU,
+but it is absolutely forbidden to update a semaphore that has just been
+removed.
+In the Linux kernel, this need for consistency is accommodated by acquiring
+spinlocks located in the in-kernel data structure from within
+the RCU read-side critical section, and this is indicated by the
+green box in the figure above.
+Many other techniques may be used, and are in fact used within the
+Linux kernel.
+
+<p>
+In short, RCU is not required to maintain consistency, and other
+mechanisms may be used in concert with RCU when consistency is required.
+RCU's specialization allows it to do its job extremely well, and its
+ability to interoperate with other synchronization mechanisms allows
+the right mix of synchronization tools to be used for a given job.
+
+<h3><a name="Performance and Scalability">Performance and Scalability</a></h3>
+
+<p>
+Energy efficiency is a critical component of performance today,
+and Linux-kernel RCU implementations must therefore avoid unnecessarily
+awakening idle CPUs.
+I cannot claim that this requirement was premeditated.
+In fact, I learned of it during a telephone conversation in which I
+was given &ldquo;frank and open&rdquo; feedback on the importance
+of energy efficiency in battery-powered systems and on specific
+energy-efficiency shortcomings of the Linux-kernel RCU implementation.
+In my experience, the battery-powered embedded community will consider
+any unnecessary wakeups to be extremely unfriendly acts.
+So much so that mere Linux-kernel-mailing-list posts are
+insufficient to vent their ire.
+
+<p>
+Memory consumption is not particularly important for in most
+situations, and has become decreasingly
+so as memory sizes have expanded and memory
+costs have plummeted.
+However, as I learned from Matt Mackall's
+<a href="http://elinux.org/Linux_Tiny-FAQ">bloatwatch</a>
+efforts, memory footprint is critically important on single-CPU systems with
+non-preemptible (<tt>CONFIG_PREEMPT=n</tt>) kernels, and thus
+<a href="https://lkml.kernel.org/g/20090113221724.GA15307@linux.vnet.ibm.com">tiny RCU</a>
+was born.
+Josh Triplett has since taken over the small-memory banner with his
+<a href="https://tiny.wiki.kernel.org/">Linux kernel tinification</a>
+project, which resulted in
+<a href="#Sleepable RCU">SRCU</a>
+becoming optional for those kernels not needing it.
+
+<p>
+The remaining performance requirements are, for the most part,
+unsurprising.
+For example, in keeping with RCU's read-side specialization,
+<tt>rcu_dereference()</tt> should have negligible overhead (for
+example, suppression of a few minor compiler optimizations).
+Similarly, in non-preemptible environments, <tt>rcu_read_lock()</tt> and
+<tt>rcu_read_unlock()</tt> should have exactly zero overhead.
+
+<p>
+In preemptible environments, in the case where the RCU read-side
+critical section was not preempted (as will be the case for the
+highest-priority real-time process), <tt>rcu_read_lock()</tt> and
+<tt>rcu_read_unlock()</tt> should have minimal overhead.
+In particular, they should not contain atomic read-modify-write
+operations, memory-barrier instructions, preemption disabling,
+interrupt disabling, or backwards branches.
+However, in the case where the RCU read-side critical section was preempted,
+<tt>rcu_read_unlock()</tt> may acquire spinlocks and disable interrupts.
+This is why it is better to nest an RCU read-side critical section
+within a preempt-disable region than vice versa, at least in cases
+where that critical section is short enough to avoid unduly degrading
+real-time latencies.
+
+<p>
+The <tt>synchronize_rcu()</tt> grace-period-wait primitive is
+optimized for throughput.
+It may therefore incur several milliseconds of latency in addition to
+the duration of the longest RCU read-side critical section.
+On the other hand, multiple concurrent invocations of
+<tt>synchronize_rcu()</tt> are required to use batching optimizations
+so that they can be satisfied by a single underlying grace-period-wait
+operation.
+For example, in the Linux kernel, it is not unusual for a single
+grace-period-wait operation to serve more than
+<a href="https://www.usenix.org/conference/2004-usenix-annual-technical-conference/making-rcu-safe-deep-sub-millisecond-response">1,000 separate invocations</a>
+of <tt>synchronize_rcu()</tt>, thus amortizing the per-invocation
+overhead down to nearly zero.
+However, the grace-period optimization is also required to avoid
+measurable degradation of real-time scheduling and interrupt latencies.
+
+<p>
+In some cases, the multi-millisecond <tt>synchronize_rcu()</tt>
+latencies are unacceptable.
+In these cases, <tt>synchronize_rcu_expedited()</tt> may be used
+instead, reducing the grace-period latency down to a few tens of
+microseconds on small systems, at least in cases where the RCU read-side
+critical sections are short.
+There are currently no special latency requirements for
+<tt>synchronize_rcu_expedited()</tt> on large systems, but,
+consistent with the empirical nature of the RCU specification,
+that is subject to change.
+However, there most definitely are scalability requirements:
+A storm of <tt>synchronize_rcu_expedited()</tt> invocations on 4096
+CPUs should at least make reasonable forward progress.
+In return for its shorter latencies, <tt>synchronize_rcu_expedited()</tt>
+is permitted to impose modest degradation of real-time latency
+on non-idle online CPUs.
+That said, it will likely be necessary to take further steps to reduce this
+degradation, hopefully to roughly that of a scheduling-clock interrupt.
+
+<p>
+There are a number of situations where even
+<tt>synchronize_rcu_expedited()</tt>'s reduced grace-period
+latency is unacceptable.
+In these situations, the asynchronous <tt>call_rcu()</tt> can be
+used in place of <tt>synchronize_rcu()</tt> as follows:
+
+<blockquote>
+<pre>
+ 1 struct foo {
+ 2   int a;
+ 3   int b;
+ 4   struct rcu_head rh;
+ 5 };
+ 6
+ 7 static void remove_gp_cb(struct rcu_head *rhp)
+ 8 {
+ 9   struct foo *p = container_of(rhp, struct foo, rh);
+10
+11   kfree(p);
+12 }
+13
+14 bool remove_gp_asynchronous(void)
+15 {
+16   struct foo *p;
+17
+18   spin_lock(&amp;gp_lock);
+19   p = rcu_dereference(gp);
+20   if (!p) {
+21     spin_unlock(&amp;gp_lock);
+22     return false;
+23   }
+24   rcu_assign_pointer(gp, NULL);
+25   call_rcu(&amp;p-&gt;rh, remove_gp_cb);
+26   spin_unlock(&amp;gp_lock);
+27   return true;
+28 }
+</pre>
+</blockquote>
+
+<p>
+A definition of <tt>struct foo</tt> is finally needed, and appears
+on lines&nbsp;1-5.
+The function <tt>remove_gp_cb()</tt> is passed to <tt>call_rcu()</tt>
+on line&nbsp;25, and will be invoked after the end of a subsequent
+grace period.
+This gets the same effect as <tt>remove_gp_synchronous()</tt>,
+but without forcing the updater to wait for a grace period to elapse.
+The <tt>call_rcu()</tt> function may be used in a number of
+situations where neither <tt>synchronize_rcu()</tt> nor
+<tt>synchronize_rcu_expedited()</tt> would be legal,
+including within preempt-disable code, <tt>local_bh_disable()</tt> code,
+interrupt-disable code, and interrupt handlers.
+However, even <tt>call_rcu()</tt> is illegal within NMI handlers.
+The callback function (<tt>remove_gp_cb()</tt> in this case) will be
+executed within softirq (software interrupt) environment within the
+Linux kernel,
+either within a real softirq handler or under the protection
+of <tt>local_bh_disable()</tt>.
+In both the Linux kernel and in userspace, it is bad practice to
+write an RCU callback function that takes too long.
+Long-running operations should be relegated to separate threads or
+(in the Linux kernel) workqueues.
+
+<p><a name="Quick Quiz 12"><b>Quick Quiz 12</b>:</a>
+Why does line&nbsp;19 use <tt>rcu_access_pointer()</tt>?
+After all, <tt>call_rcu()</tt> on line&nbsp;25 stores into the
+structure, which would interact badly with concurrent insertions.
+Doesn't this mean that <tt>rcu_dereference()</tt> is required?
+<br><a href="#qq12answer">Answer</a>
+
+<p>
+However, all that <tt>remove_gp_cb()</tt> is doing is
+invoking <tt>kfree()</tt> on the data element.
+This is a common idiom, and is supported by <tt>kfree_rcu()</tt>,
+which allows &ldquo;fire and forget&rdquo; operation as shown below:
+
+<blockquote>
+<pre>
+ 1 struct foo {
+ 2   int a;
+ 3   int b;
+ 4   struct rcu_head rh;
+ 5 };
+ 6
+ 7 bool remove_gp_faf(void)
+ 8 {
+ 9   struct foo *p;
+10
+11   spin_lock(&amp;gp_lock);
+12   p = rcu_dereference(gp);
+13   if (!p) {
+14     spin_unlock(&amp;gp_lock);
+15     return false;
+16   }
+17   rcu_assign_pointer(gp, NULL);
+18   kfree_rcu(p, rh);
+19   spin_unlock(&amp;gp_lock);
+20   return true;
+21 }
+</pre>
+</blockquote>
+
+<p>
+Note that <tt>remove_gp_faf()</tt> simply invokes
+<tt>kfree_rcu()</tt> and proceeds, without any need to pay any
+further attention to the subsequent grace period and <tt>kfree()</tt>.
+It is permissible to invoke <tt>kfree_rcu()</tt> from the same
+environments as for <tt>call_rcu()</tt>.
+Interestingly enough, DYNIX/ptx had the equivalents of
+<tt>call_rcu()</tt> and <tt>kfree_rcu()</tt>, but not
+<tt>synchronize_rcu()</tt>.
+This was due to the fact that RCU was not heavily used within DYNIX/ptx,
+so the very few places that needed something like
+<tt>synchronize_rcu()</tt> simply open-coded it.
+
+<p><a name="Quick Quiz 13"><b>Quick Quiz 13</b>:</a>
+Earlier it was claimed that <tt>call_rcu()</tt> and
+<tt>kfree_rcu()</tt> allowed updaters to avoid being blocked
+by readers.
+But how can that be correct, given that the invocation of the callback
+and the freeing of the memory (respectively) must still wait for
+a grace period to elapse?
+<br><a href="#qq13answer">Answer</a>
+
+<p>
+But what if the updater must wait for the completion of code to be
+executed after the end of the grace period, but has other tasks
+that can be carried out in the meantime?
+The polling-style <tt>get_state_synchronize_rcu()</tt> and
+<tt>cond_synchronize_rcu()</tt> functions may be used for this
+purpose, as shown below:
+
+<blockquote>
+<pre>
+ 1 bool remove_gp_poll(void)
+ 2 {
+ 3   struct foo *p;
+ 4   unsigned long s;
+ 5
+ 6   spin_lock(&amp;gp_lock);
+ 7   p = rcu_access_pointer(gp);
+ 8   if (!p) {
+ 9     spin_unlock(&amp;gp_lock);
+10     return false;
+11   }
+12   rcu_assign_pointer(gp, NULL);
+13   spin_unlock(&amp;gp_lock);
+14   s = get_state_synchronize_rcu();
+15   do_something_while_waiting();
+16   cond_synchronize_rcu(s);
+17   kfree(p);
+18   return true;
+19 }
+</pre>
+</blockquote>
+
+<p>
+On line&nbsp;14, <tt>get_state_synchronize_rcu()</tt> obtains a
+&ldquo;cookie&rdquo; from RCU,
+then line&nbsp;15 carries out other tasks,
+and finally, line&nbsp;16 returns immediately if a grace period has
+elapsed in the meantime, but otherwise waits as required.
+The need for <tt>get_state_synchronize_rcu</tt> and
+<tt>cond_synchronize_rcu()</tt> has appeared quite recently,
+so it is too early to tell whether they will stand the test of time.
+
+<p>
+RCU thus provides a range of tools to allow updaters to strike the
+required tradeoff between latency, flexibility and CPU overhead.
+
+<h3><a name="Composability">Composability</a></h3>
+
+<p>
+Composability has received much attention in recent years, perhaps in part
+due to the collision of multicore hardware with object-oriented techniques
+designed in single-threaded environments for single-threaded use.
+And in theory, RCU read-side critical sections may be composed, and in
+fact may be nested arbitrarily deeply.
+In practice, as with all real-world implementations of composable
+constructs, there are limitations.
+
+<p>
+Implementations of RCU for which <tt>rcu_read_lock()</tt>
+and <tt>rcu_read_unlock()</tt> generate no code, such as
+Linux-kernel RCU when <tt>CONFIG_PREEMPT=n</tt>, can be
+nested arbitrarily deeply.
+After all, there is no overhead.
+Except that if all these instances of <tt>rcu_read_lock()</tt>
+and <tt>rcu_read_unlock()</tt> are visible to the compiler,
+compilation will eventually fail due to exhausting memory,
+mass storage, or user patience, whichever comes first.
+If the nesting is not visible to the compiler, as is the case with
+mutually recursive functions each in its own translation unit,
+stack overflow will result.
+If the nesting takes the form of loops, either the control variable
+will overflow or (in the Linux kernel) you will get an RCU CPU stall warning.
+Nevertheless, this class of RCU implementations is one
+of the most composable constructs in existence.
+
+<p>
+RCU implementations that explicitly track nesting depth
+are limited by the nesting-depth counter.
+For example, the Linux kernel's preemptible RCU limits nesting to
+<tt>INT_MAX</tt>.
+This should suffice for almost all practical purposes.
+That said, a consecutive pair of RCU read-side critical sections
+between which there is an operation that waits for a grace period
+cannot be enclosed in another RCU read-side critical section.
+This is because it is not legal to wait for a grace period within
+an RCU read-side critical section:  To do so would result either
+in deadlock or
+in RCU implicitly splitting the enclosing RCU read-side critical
+section, neither of which is conducive to a long-lived and prosperous
+kernel.
+
+<p>
+It is worth noting that RCU is not alone in limiting composability.
+For example, many transactional-memory implementations prohibit
+composing a pair of transactions separated by an irrevocable
+operation (for example, a network receive operation).
+For another example, lock-based critical sections can be composed
+surprisingly freely, but only if deadlock is avoided.
+
+<p>
+In short, although RCU read-side critical sections are highly composable,
+care is required in some situations, just as is the case for any other
+composable synchronization mechanism.
+
+<h3><a name="Corner Cases">Corner Cases</a></h3>
+
+<p>
+A given RCU workload might have an endless and intense stream of
+RCU read-side critical sections, perhaps even so intense that there
+was never a point in time during which there was not at least one
+RCU read-side critical section in flight.
+RCU cannot allow this situation to block grace periods:  As long as
+all the RCU read-side critical sections are finite, grace periods
+must also be finite.
+
+<p>
+That said, preemptible RCU implementations could potentially result
+in RCU read-side critical sections being preempted for long durations,
+which has the effect of creating a long-duration RCU read-side
+critical section.
+This situation can arise only in heavily loaded systems, but systems using
+real-time priorities are of course more vulnerable.
+Therefore, RCU priority boosting is provided to help deal with this
+case.
+That said, the exact requirements on RCU priority boosting will likely
+evolve as more experience accumulates.
+
+<p>
+Other workloads might have very high update rates.
+Although one can argue that such workloads should instead use
+something other than RCU, the fact remains that RCU must
+handle such workloads gracefully.
+This requirement is another factor driving batching of grace periods,
+but it is also the driving force behind the checks for large numbers
+of queued RCU callbacks in the <tt>call_rcu()</tt> code path.
+Finally, high update rates should not delay RCU read-side critical
+sections, although some read-side delays can occur when using
+<tt>synchronize_rcu_expedited()</tt>, courtesy of this function's use
+of <tt>try_stop_cpus()</tt>.
+(In the future, <tt>synchronize_rcu_expedited()</tt> will be
+converted to use lighter-weight inter-processor interrupts (IPIs),
+but this will still disturb readers, though to a much smaller degree.)
+
+<p>
+Although all three of these corner cases were understood in the early
+1990s, a simple user-level test consisting of <tt>close(open(path))</tt>
+in a tight loop
+in the early 2000s suddenly provided a much deeper appreciation of the
+high-update-rate corner case.
+This test also motivated addition of some RCU code to react to high update
+rates, for example, if a given CPU finds itself with more than 10,000
+RCU callbacks queued, it will cause RCU to take evasive action by
+more aggressively starting grace periods and more aggressively forcing
+completion of grace-period processing.
+This evasive action causes the grace period to complete more quickly,
+but at the cost of restricting RCU's batching optimizations, thus
+increasing the CPU overhead incurred by that grace period.
+
+<h2><a name="Software-Engineering Requirements">
+Software-Engineering Requirements</a></h2>
+
+<p>
+Between Murphy's Law and &ldquo;To err is human&rdquo;, it is necessary to
+guard against mishaps and misuse:
+
+<ol>
+<li>	It is all too easy to forget to use <tt>rcu_read_lock()</tt>
+	everywhere that it is needed, so kernels built with
+	<tt>CONFIG_PROVE_RCU=y</tt> will spat if
+	<tt>rcu_dereference()</tt> is used outside of an
+	RCU read-side critical section.
+	Update-side code can use <tt>rcu_dereference_protected()</tt>,
+	which takes a
+	<a href="https://lwn.net/Articles/371986/">lockdep expression</a>
+	to indicate what is providing the protection.
+	If the indicated protection is not provided, a lockdep splat
+	is emitted.
+
+	<p>
+	Code shared between readers and updaters can use
+	<tt>rcu_dereference_check()</tt>, which also takes a
+	lockdep expression, and emits a lockdep splat if neither
+	<tt>rcu_read_lock()</tt> nor the indicated protection
+	is in place.
+	In addition, <tt>rcu_dereference_raw()</tt> is used in those
+	(hopefully rare) cases where the required protection cannot
+	be easily described.
+	Finally, <tt>rcu_read_lock_held()</tt> is provided to
+	allow a function to verify that it has been invoked within
+	an RCU read-side critical section.
+	I was made aware of this set of requirements shortly after Thomas
+	Gleixner audited a number of RCU uses.
+<li>	A given function might wish to check for RCU-related preconditions
+	upon entry, before using any other RCU API.
+	The <tt>rcu_lockdep_assert()</tt> does this job,
+	asserting the expression in kernels having lockdep enabled
+	and doing nothing otherwise.
+<li>	It is also easy to forget to use <tt>rcu_assign_pointer()</tt>
+	and <tt>rcu_dereference()</tt>, perhaps (incorrectly)
+	substituting a simple assignment.
+	To catch this sort of error, a given RCU-protected pointer may be
+	tagged with <tt>__rcu</tt>, after which running sparse
+	with <tt>CONFIG_SPARSE_RCU_POINTER=y</tt> will complain
+	about simple-assignment accesses to that pointer.
+	Arnd Bergmann made me aware of this requirement, and also
+	supplied the needed
+	<a href="https://lwn.net/Articles/376011/">patch series</a>.
+<li>	Kernels built with <tt>CONFIG_DEBUG_OBJECTS_RCU_HEAD=y</tt>
+	will splat if a data element is passed to <tt>call_rcu()</tt>
+	twice in a row, without a grace period in between.
+	(This error is similar to a double free.)
+	The corresponding <tt>rcu_head</tt> structures that are
+	dynamically allocated are automatically tracked, but
+	<tt>rcu_head</tt> structures allocated on the stack
+	must be initialized with <tt>init_rcu_head_on_stack()</tt>
+	and cleaned up with <tt>destroy_rcu_head_on_stack()</tt>.
+	Similarly, statically allocated non-stack <tt>rcu_head</tt>
+	structures must be initialized with <tt>init_rcu_head()</tt>
+	and cleaned up with <tt>destroy_rcu_head()</tt>.
+	Mathieu Desnoyers made me aware of this requirement, and also
+	supplied the needed
+	<a href="https://lkml.kernel.org/g/20100319013024.GA28456@Krystal">patch</a>.
+<li>	An infinite loop in an RCU read-side critical section will
+	eventually trigger an RCU CPU stall warning splat, with
+	the duration of &ldquo;eventually&rdquo; being controlled by the
+	<tt>RCU_CPU_STALL_TIMEOUT</tt> <tt>Kconfig</tt> option, or,
+	alternatively, by the
+	<tt>rcupdate.rcu_cpu_stall_timeout</tt> boot/sysfs
+	parameter.
+	However, RCU is not obligated to produce this splat
+	unless there is a grace period waiting on that particular
+	RCU read-side critical section.
+	<p>
+	Some extreme workloads might intentionally delay
+	RCU grace periods, and systems running those workloads can
+	be booted with <tt>rcupdate.rcu_cpu_stall_suppress</tt>
+	to suppress the splats.
+	This kernel parameter may also be set via <tt>sysfs</tt>.
+	Furthermore, RCU CPU stall warnings are counter-productive
+	during sysrq dumps and during panics.
+	RCU therefore supplies the <tt>rcu_sysrq_start()</tt> and
+	<tt>rcu_sysrq_end()</tt> API members to be called before
+	and after long sysrq dumps.
+	RCU also supplies the <tt>rcu_panic()</tt> notifier that is
+	automatically invoked at the beginning of a panic to suppress
+	further RCU CPU stall warnings.
+
+	<p>
+	This requirement made itself known in the early 1990s, pretty
+	much the first time that it was necessary to debug a CPU stall.
+	That said, the initial implementation in DYNIX/ptx was quite
+	generic in comparison with that of Linux.
+<li>	Although it would be very good to detect pointers leaking out
+	of RCU read-side critical sections, there is currently no
+	good way of doing this.
+	One complication is the need to distinguish between pointers
+	leaking and pointers that have been handed off from RCU to
+	some other synchronization mechanism, for example, reference
+	counting.
+<li>	In kernels built with <tt>CONFIG_RCU_TRACE=y</tt>, RCU-related
+	information is provided via both debugfs and event tracing.
+<li>	Open-coded use of <tt>rcu_assign_pointer()</tt> and
+	<tt>rcu_dereference()</tt> to create typical linked
+	data structures can be surprisingly error-prone.
+	Therefore, RCU-protected
+	<a href="https://lwn.net/Articles/609973/#RCU List APIs">linked lists</a>
+	and, more recently, RCU-protected
+	<a href="https://lwn.net/Articles/612100/">hash tables</a>
+	are available.
+	Many other special-purpose RCU-protected data structures are
+	available in the Linux kernel and the userspace RCU library.
+<li>	Some linked structures are created at compile time, but still
+	require <tt>__rcu</tt> checking.
+	The <tt>RCU_POINTER_INITIALIZER()</tt> macro serves this
+	purpose.
+<li>	It is not necessary to use <tt>rcu_assign_pointer()</tt>
+	when creating linked structures that are to be published via
+	a single external pointer.
+	The <tt>RCU_INIT_POINTER()</tt> macro is provided for
+	this task and also for assigning <tt>NULL</tt> pointers
+	at runtime.
+</ol>
+
+<p>
+This not a hard-and-fast list:  RCU's diagnostic capabilities will
+continue to be guided by the number and type of usage bugs found
+in real-world RCU usage.
+
+<h2><a name="Linux Kernel Complications">Linux Kernel Complications</a></h2>
+
+<p>
+The Linux kernel provides an interesting environment for all kinds of
+software, including RCU.
+Some of the relevant points of interest are as follows:
+
+<ol>
+<li>	<a href="#Configuration">Configuration</a>.
+<li>	<a href="#Firmware Interface">Firmware Interface</a>.
+<li>	<a href="#Early Boot">Early Boot</a>.
+<li>	<a href="#Interrupts and NMIs">
+	Interrupts and non-maskable interrupts (NMIs)</a>.
+<li>	<a href="#Loadable Modules">Loadable Modules</a>.
+<li>	<a href="#Hotplug CPU">Hotplug CPU</a>.
+<li>	<a href="#Scheduler and RCU">Scheduler and RCU</a>.
+<li>	<a href="#Tracing and RCU">Tracing and RCU</a>.
+<li>	<a href="#Energy Efficiency">Energy Efficiency</a>.
+<li>	<a href="#Memory Efficiency">Memory Efficiency</a>.
+<li>	<a href="#Performance, Scalability, Response Time, and Reliability">
+	Performance, Scalability, Response Time, and Reliability</a>.
+</ol>
+
+<p>
+This list is probably incomplete, but it does give a feel for the
+most notable Linux-kernel complications.
+Each of the following sections covers one of the above topics.
+
+<h3><a name="Configuration">Configuration</a></h3>
+
+<p>
+RCU's goal is automatic configuration, so that almost nobody
+needs to worry about RCU's <tt>Kconfig</tt> options.
+And for almost all users, RCU does in fact work well
+&ldquo;out of the box.&rdquo;
+
+<p>
+However, there are specialized use cases that are handled by
+kernel boot parameters and <tt>Kconfig</tt> options.
+Unfortunately, the <tt>Kconfig</tt> system will explicitly ask users
+about new <tt>Kconfig</tt> options, which requires almost all of them
+be hidden behind a <tt>CONFIG_RCU_EXPERT</tt> <tt>Kconfig</tt> option.
+
+<p>
+This all should be quite obvious, but the fact remains that
+Linus Torvalds recently had to
+<a href="https://lkml.kernel.org/g/CA+55aFy4wcCwaL4okTs8wXhGZ5h-ibecy_Meg9C4MNQrUnwMcg@mail.gmail.com">remind</a>
+me of this requirement.
+
+<h3><a name="Firmware Interface">Firmware Interface</a></h3>
+
+<p>
+In many cases, kernel obtains information about the system from the
+firmware, and sometimes things are lost in translation.
+Or the translation is accurate, but the original message is bogus.
+
+<p>
+For example, some systems' firmware overreports the number of CPUs,
+sometimes by a large factor.
+If RCU naively believed the firmware, as it used to do,
+it would create too many per-CPU kthreads.
+Although the resulting system will still run correctly, the extra
+kthreads needlessly consume memory and can cause confusion
+when they show up in <tt>ps</tt> listings.
+
+<p>
+RCU must therefore wait for a given CPU to actually come online before
+it can allow itself to believe that the CPU actually exists.
+The resulting &ldquo;ghost CPUs&rdquo; (which are never going to
+come online) cause a number of
+<a href="https://paulmck.livejournal.com/37494.html">interesting complications</a>.
+
+<h3><a name="Early Boot">Early Boot</a></h3>
+
+<p>
+The Linux kernel's boot sequence is an interesting process,
+and RCU is used early, even before <tt>rcu_init()</tt>
+is invoked.
+In fact, a number of RCU's primitives can be used as soon as the
+initial task's <tt>task_struct</tt> is available and the
+boot CPU's per-CPU variables are set up.
+The read-side primitives (<tt>rcu_read_lock()</tt>,
+<tt>rcu_read_unlock()</tt>, <tt>rcu_dereference()</tt>,
+and <tt>rcu_access_pointer()</tt>) will operate normally very early on,
+as will <tt>rcu_assign_pointer()</tt>.
+
+<p>
+Although <tt>call_rcu()</tt> may be invoked at any
+time during boot, callbacks are not guaranteed to be invoked until after
+the scheduler is fully up and running.
+This delay in callback invocation is due to the fact that RCU does not
+invoke callbacks until it is fully initialized, and this full initialization
+cannot occur until after the scheduler has initialized itself to the
+point where RCU can spawn and run its kthreads.
+In theory, it would be possible to invoke callbacks earlier,
+however, this is not a panacea because there would be severe restrictions
+on what operations those callbacks could invoke.
+
+<p>
+Perhaps surprisingly, <tt>synchronize_rcu()</tt>,
+<a href="#Bottom-Half Flavor"><tt>synchronize_rcu_bh()</tt></a>
+(<a href="#Bottom-Half Flavor">discussed below</a>),
+and
+<a href="#Sched Flavor"><tt>synchronize_sched()</tt></a>
+will all operate normally
+during very early boot, the reason being that there is only one CPU
+and preemption is disabled.
+This means that the call <tt>synchronize_rcu()</tt> (or friends)
+itself is a quiescent
+state and thus a grace period, so the early-boot implementation can
+be a no-op.
+
+<p>
+Both <tt>synchronize_rcu_bh()</tt> and <tt>synchronize_sched()</tt>
+continue to operate normally through the remainder of boot, courtesy
+of the fact that preemption is disabled across their RCU read-side
+critical sections and also courtesy of the fact that there is still
+only one CPU.
+However, once the scheduler starts initializing, preemption is enabled.
+There is still only a single CPU, but the fact that preemption is enabled
+means that the no-op implementation of <tt>synchronize_rcu()</tt> no
+longer works in <tt>CONFIG_PREEMPT=y</tt> kernels.
+Therefore, as soon as the scheduler starts initializing, the early-boot
+fastpath is disabled.
+This means that <tt>synchronize_rcu()</tt> switches to its runtime
+mode of operation where it posts callbacks, which in turn means that
+any call to <tt>synchronize_rcu()</tt> will block until the corresponding
+callback is invoked.
+Unfortunately, the callback cannot be invoked until RCU's runtime
+grace-period machinery is up and running, which cannot happen until
+the scheduler has initialized itself sufficiently to allow RCU's
+kthreads to be spawned.
+Therefore, invoking <tt>synchronize_rcu()</tt> during scheduler
+initialization can result in deadlock.
+
+<p><a name="Quick Quiz 14"><b>Quick Quiz 14</b>:</a>
+So what happens with <tt>synchronize_rcu()</tt> during
+scheduler initialization for <tt>CONFIG_PREEMPT=n</tt>
+kernels?
+<br><a href="#qq14answer">Answer</a>
+
+<p>
+I learned of these boot-time requirements as a result of a series of
+system hangs.
+
+<h3><a name="Interrupts and NMIs">Interrupts and NMIs</a></h3>
+
+<p>
+The Linux kernel has interrupts, and RCU read-side critical sections are
+legal within interrupt handlers and within interrupt-disabled regions
+of code, as are invocations of <tt>call_rcu()</tt>.
+
+<p>
+Some Linux-kernel architectures can enter an interrupt handler from
+non-idle process context, and then just never leave it, instead stealthily
+transitioning back to process context.
+This trick is sometimes used to invoke system calls from inside the kernel.
+These &ldquo;half-interrupts&rdquo; mean that RCU has to be very careful
+about how it counts interrupt nesting levels.
+I learned of this requirement the hard way during a rewrite
+of RCU's dyntick-idle code.
+
+<p>
+The Linux kernel has non-maskable interrupts (NMIs), and
+RCU read-side critical sections are legal within NMI handlers.
+Thankfully, RCU update-side primitives, including
+<tt>call_rcu()</tt>, are prohibited within NMI handlers.
+
+<p>
+The name notwithstanding, some Linux-kernel architectures
+can have nested NMIs, which RCU must handle correctly.
+Andy Lutomirski
+<a href="https://lkml.kernel.org/g/CALCETrXLq1y7e_dKFPgou-FKHB6Pu-r8+t-6Ds+8=va7anBWDA@mail.gmail.com">surprised me</a>
+with this requirement;
+he also kindly surprised me with
+<a href="https://lkml.kernel.org/g/CALCETrXSY9JpW3uE6H8WYk81sg56qasA2aqmjMPsq5dOtzso=g@mail.gmail.com">an algorithm</a>
+that meets this requirement.
+
+<h3><a name="Loadable Modules">Loadable Modules</a></h3>
+
+<p>
+The Linux kernel has loadable modules, and these modules can
+also be unloaded.
+After a given module has been unloaded, any attempt to call
+one of its functions results in a segmentation fault.
+The module-unload functions must therefore cancel any
+delayed calls to loadable-module functions, for example,
+any outstanding <tt>mod_timer()</tt> must be dealt with
+via <tt>del_timer_sync()</tt> or similar.
+
+<p>
+Unfortunately, there is no way to cancel an RCU callback;
+once you invoke <tt>call_rcu()</tt>, the callback function is
+going to eventually be invoked, unless the system goes down first.
+Because it is normally considered socially irresponsible to crash the system
+in response to a module unload request, we need some other way
+to deal with in-flight RCU callbacks.
+
+<p>
+RCU therefore provides
+<tt><a href="https://lwn.net/Articles/217484/">rcu_barrier()</a></tt>,
+which waits until all in-flight RCU callbacks have been invoked.
+If a module uses <tt>call_rcu()</tt>, its exit function should therefore
+prevent any future invocation of <tt>call_rcu()</tt>, then invoke
+<tt>rcu_barrier()</tt>.
+In theory, the underlying module-unload code could invoke
+<tt>rcu_barrier()</tt> unconditionally, but in practice this would
+incur unacceptable latencies.
+
+<p>
+Nikita Danilov noted this requirement for an analogous filesystem-unmount
+situation, and Dipankar Sarma incorporated <tt>rcu_barrier()</tt> into RCU.
+The need for <tt>rcu_barrier()</tt> for module unloading became
+apparent later.
+
+<h3><a name="Hotplug CPU">Hotplug CPU</a></h3>
+
+<p>
+The Linux kernel supports CPU hotplug, which means that CPUs
+can come and go.
+It is of course illegal to use any RCU API member from an offline CPU.
+This requirement was present from day one in DYNIX/ptx, but
+on the other hand, the Linux kernel's CPU-hotplug implementation
+is &ldquo;interesting.&rdquo;
+
+<p>
+The Linux-kernel CPU-hotplug implementation has notifiers that
+are used to allow the various kernel subsystems (including RCU)
+to respond appropriately to a given CPU-hotplug operation.
+Most RCU operations may be invoked from CPU-hotplug notifiers,
+including even normal synchronous grace-period operations
+such as <tt>synchronize_rcu()</tt>.
+However, expedited grace-period operations such as
+<tt>synchronize_rcu_expedited()</tt> are not supported,
+due to the fact that current implementations block CPU-hotplug
+operations, which could result in deadlock.
+
+<p>
+In addition, all-callback-wait operations such as
+<tt>rcu_barrier()</tt> are also not supported, due to the
+fact that there are phases of CPU-hotplug operations where
+the outgoing CPU's callbacks will not be invoked until after
+the CPU-hotplug operation ends, which could also result in deadlock.
+
+<h3><a name="Scheduler and RCU">Scheduler and RCU</a></h3>
+
+<p>
+RCU depends on the scheduler, and the scheduler uses RCU to
+protect some of its data structures.
+This means the scheduler is forbidden from acquiring
+the runqueue locks and the priority-inheritance locks
+in the middle of an outermost RCU read-side critical section unless either
+(1)&nbsp;it releases them before exiting that same
+RCU read-side critical section, or
+(2)&nbsp;interrupts are disabled across
+that entire RCU read-side critical section.
+This same prohibition also applies (recursively!) to any lock that is acquired
+while holding any lock to which this prohibition applies.
+Adhering to this rule prevents preemptible RCU from invoking
+<tt>rcu_read_unlock_special()</tt> while either runqueue or
+priority-inheritance locks are held, thus avoiding deadlock.
+
+<p>
+Prior to v4.4, it was only necessary to disable preemption across
+RCU read-side critical sections that acquired scheduler locks.
+In v4.4, expedited grace periods started using IPIs, and these
+IPIs could force a <tt>rcu_read_unlock()</tt> to take the slowpath.
+Therefore, this expedited-grace-period change required disabling of
+interrupts, not just preemption.
+
+<p>
+For RCU's part, the preemptible-RCU <tt>rcu_read_unlock()</tt>
+implementation must be written carefully to avoid similar deadlocks.
+In particular, <tt>rcu_read_unlock()</tt> must tolerate an
+interrupt where the interrupt handler invokes both
+<tt>rcu_read_lock()</tt> and <tt>rcu_read_unlock()</tt>.
+This possibility requires <tt>rcu_read_unlock()</tt> to use
+negative nesting levels to avoid destructive recursion via
+interrupt handler's use of RCU.
+
+<p>
+This pair of mutual scheduler-RCU requirements came as a
+<a href="https://lwn.net/Articles/453002/">complete surprise</a>.
+
+<p>
+As noted above, RCU makes use of kthreads, and it is necessary to
+avoid excessive CPU-time accumulation by these kthreads.
+This requirement was no surprise, but RCU's violation of it
+when running context-switch-heavy workloads when built with
+<tt>CONFIG_NO_HZ_FULL=y</tt>
+<a href="http://www.rdrop.com/users/paulmck/scalability/paper/BareMetal.2015.01.15b.pdf">did come as a surprise [PDF]</a>.
+RCU has made good progress towards meeting this requirement, even
+for context-switch-have <tt>CONFIG_NO_HZ_FULL=y</tt> workloads,
+but there is room for further improvement.
+
+<h3><a name="Tracing and RCU">Tracing and RCU</a></h3>
+
+<p>
+It is possible to use tracing on RCU code, but tracing itself
+uses RCU.
+For this reason, <tt>rcu_dereference_raw_notrace()</tt>
+is provided for use by tracing, which avoids the destructive
+recursion that could otherwise ensue.
+This API is also used by virtualization in some architectures,
+where RCU readers execute in environments in which tracing
+cannot be used.
+The tracing folks both located the requirement and provided the
+needed fix, so this surprise requirement was relatively painless.
+
+<h3><a name="Energy Efficiency">Energy Efficiency</a></h3>
+
+<p>
+Interrupting idle CPUs is considered socially unacceptable,
+especially by people with battery-powered embedded systems.
+RCU therefore conserves energy by detecting which CPUs are
+idle, including tracking CPUs that have been interrupted from idle.
+This is a large part of the energy-efficiency requirement,
+so I learned of this via an irate phone call.
+
+<p>
+Because RCU avoids interrupting idle CPUs, it is illegal to
+execute an RCU read-side critical section on an idle CPU.
+(Kernels built with <tt>CONFIG_PROVE_RCU=y</tt> will splat
+if you try it.)
+The <tt>RCU_NONIDLE()</tt> macro and <tt>_rcuidle</tt>
+event tracing is provided to work around this restriction.
+In addition, <tt>rcu_is_watching()</tt> may be used to
+test whether or not it is currently legal to run RCU read-side
+critical sections on this CPU.
+I learned of the need for diagnostics on the one hand
+and <tt>RCU_NONIDLE()</tt> on the other while inspecting
+idle-loop code.
+Steven Rostedt supplied <tt>_rcuidle</tt> event tracing,
+which is used quite heavily in the idle loop.
+
+<p>
+It is similarly socially unacceptable to interrupt an
+<tt>nohz_full</tt> CPU running in userspace.
+RCU must therefore track <tt>nohz_full</tt> userspace
+execution.
+And in
+<a href="https://lwn.net/Articles/558284/"><tt>CONFIG_NO_HZ_FULL_SYSIDLE=y</tt></a>
+kernels, RCU must separately track idle CPUs on the one hand and
+CPUs that are either idle or executing in userspace on the other.
+In both cases, RCU must be able to sample state at two points in
+time, and be able to determine whether or not some other CPU spent
+any time idle and/or executing in userspace.
+
+<p>
+These energy-efficiency requirements have proven quite difficult to
+understand and to meet, for example, there have been more than five
+clean-sheet rewrites of RCU's energy-efficiency code, the last of
+which was finally able to demonstrate
+<a href="http://www.rdrop.com/users/paulmck/realtime/paper/AMPenergy.2013.04.19a.pdf">real energy savings running on real hardware [PDF]</a>.
+As noted earlier,
+I learned of many of these requirements via angry phone calls:
+Flaming me on the Linux-kernel mailing list was apparently not
+sufficient to fully vent their ire at RCU's energy-efficiency bugs!
+
+<h3><a name="Memory Efficiency">Memory Efficiency</a></h3>
+
+<p>
+Although small-memory non-realtime systems can simply use Tiny RCU,
+code size is only one aspect of memory efficiency.
+Another aspect is the size of the <tt>rcu_head</tt> structure
+used by <tt>call_rcu()</tt> and <tt>kfree_rcu()</tt>.
+Although this structure contains nothing more than a pair of pointers,
+it does appear in many RCU-protected data structures, including
+some that are size critical.
+The <tt>page</tt> structure is a case in point, as evidenced by
+the many occurrences of the <tt>union</tt> keyword within that structure.
+
+<p>
+This need for memory efficiency is one reason that RCU uses hand-crafted
+singly linked lists to track the <tt>rcu_head</tt> structures that
+are waiting for a grace period to elapse.
+It is also the reason why <tt>rcu_head</tt> structures do not contain
+debug information, such as fields tracking the file and line of the
+<tt>call_rcu()</tt> or <tt>kfree_rcu()</tt> that posted them.
+Although this information might appear in debug-only kernel builds at some
+point, in the meantime, the <tt>-&gt;func</tt> field will often provide
+the needed debug information.
+
+<p>
+However, in some cases, the need for memory efficiency leads to even
+more extreme measures.
+Returning to the <tt>page</tt> structure, the <tt>rcu_head</tt> field
+shares storage with a great many other structures that are used at
+various points in the corresponding page's lifetime.
+In order to correctly resolve certain
+<a href="https://lkml.kernel.org/g/1439976106-137226-1-git-send-email-kirill.shutemov@linux.intel.com">race conditions</a>,
+the Linux kernel's memory-management subsystem needs a particular bit
+to remain zero during all phases of grace-period processing,
+and that bit happens to map to the bottom bit of the
+<tt>rcu_head</tt> structure's <tt>-&gt;next</tt> field.
+RCU makes this guarantee as long as <tt>call_rcu()</tt>
+is used to post the callback, as opposed to <tt>kfree_rcu()</tt>
+or some future &ldquo;lazy&rdquo;
+variant of <tt>call_rcu()</tt> that might one day be created for
+energy-efficiency purposes.
+
+<h3><a name="Performance, Scalability, Response Time, and Reliability">
+Performance, Scalability, Response Time, and Reliability</a></h3>
+
+<p>
+Expanding on the
+<a href="#Performance and Scalability">earlier discussion</a>,
+RCU is used heavily by hot code paths in performance-critical
+portions of the Linux kernel's networking, security, virtualization,
+and scheduling code paths.
+RCU must therefore use efficient implementations, especially in its
+read-side primitives.
+To that end, it would be good if preemptible RCU's implementation
+of <tt>rcu_read_lock()</tt> could be inlined, however, doing
+this requires resolving <tt>#include</tt> issues with the
+<tt>task_struct</tt> structure.
+
+<p>
+The Linux kernel supports hardware configurations with up to
+4096 CPUs, which means that RCU must be extremely scalable.
+Algorithms that involve frequent acquisitions of global locks or
+frequent atomic operations on global variables simply cannot be
+tolerated within the RCU implementation.
+RCU therefore makes heavy use of a combining tree based on the
+<tt>rcu_node</tt> structure.
+RCU is required to tolerate all CPUs continuously invoking any
+combination of RCU's runtime primitives with minimal per-operation
+overhead.
+In fact, in many cases, increasing load must <i>decrease</i> the
+per-operation overhead, witness the batching optimizations for
+<tt>synchronize_rcu()</tt>, <tt>call_rcu()</tt>,
+<tt>synchronize_rcu_expedited()</tt>, and <tt>rcu_barrier()</tt>.
+As a general rule, RCU must cheerfully accept whatever the
+rest of the Linux kernel decides to throw at it.
+
+<p>
+The Linux kernel is used for real-time workloads, especially
+in conjunction with the
+<a href="https://rt.wiki.kernel.org/index.php/Main_Page">-rt patchset</a>.
+The real-time-latency response requirements are such that the
+traditional approach of disabling preemption across RCU
+read-side critical sections is inappropriate.
+Kernels built with <tt>CONFIG_PREEMPT=y</tt> therefore
+use an RCU implementation that allows RCU read-side critical
+sections to be preempted.
+This requirement made its presence known after users made it
+clear that an earlier
+<a href="https://lwn.net/Articles/107930/">real-time patch</a>
+did not meet their needs, in conjunction with some
+<a href="https://lkml.kernel.org/g/20050318002026.GA2693@us.ibm.com">RCU issues</a>
+encountered by a very early version of the -rt patchset.
+
+<p>
+In addition, RCU must make do with a sub-100-microsecond real-time latency
+budget.
+In fact, on smaller systems with the -rt patchset, the Linux kernel
+provides sub-20-microsecond real-time latencies for the whole kernel,
+including RCU.
+RCU's scalability and latency must therefore be sufficient for
+these sorts of configurations.
+To my surprise, the sub-100-microsecond real-time latency budget
+<a href="http://www.rdrop.com/users/paulmck/realtime/paper/bigrt.2013.01.31a.LCA.pdf">
+applies to even the largest systems [PDF]</a>,
+up to and including systems with 4096 CPUs.
+This real-time requirement motivated the grace-period kthread, which
+also simplified handling of a number of race conditions.
+
+<p>
+Finally, RCU's status as a synchronization primitive means that
+any RCU failure can result in arbitrary memory corruption that can be
+extremely difficult to debug.
+This means that RCU must be extremely reliable, which in
+practice also means that RCU must have an aggressive stress-test
+suite.
+This stress-test suite is called <tt>rcutorture</tt>.
+
+<p>
+Although the need for <tt>rcutorture</tt> was no surprise,
+the current immense popularity of the Linux kernel is posing
+interesting&mdash;and perhaps unprecedented&mdash;validation
+challenges.
+To see this, keep in mind that there are well over one billion
+instances of the Linux kernel running today, given Android
+smartphones, Linux-powered televisions, and servers.
+This number can be expected to increase sharply with the advent of
+the celebrated Internet of Things.
+
+<p>
+Suppose that RCU contains a race condition that manifests on average
+once per million years of runtime.
+This bug will be occurring about three times per <i>day</i> across
+the installed base.
+RCU could simply hide behind hardware error rates, given that no one
+should really expect their smartphone to last for a million years.
+However, anyone taking too much comfort from this thought should
+consider the fact that in most jurisdictions, a successful multi-year
+test of a given mechanism, which might include a Linux kernel,
+suffices for a number of types of safety-critical certifications.
+In fact, rumor has it that the Linux kernel is already being used
+in production for safety-critical applications.
+I don't know about you, but I would feel quite bad if a bug in RCU
+killed someone.
+Which might explain my recent focus on validation and verification.
+
+<h2><a name="Other RCU Flavors">Other RCU Flavors</a></h2>
+
+<p>
+One of the more surprising things about RCU is that there are now
+no fewer than five <i>flavors</i>, or API families.
+In addition, the primary flavor that has been the sole focus up to
+this point has two different implementations, non-preemptible and
+preemptible.
+The other four flavors are listed below, with requirements for each
+described in a separate section.
+
+<ol>
+<li>	<a href="#Bottom-Half Flavor">Bottom-Half Flavor</a>
+<li>	<a href="#Sched Flavor">Sched Flavor</a>
+<li>	<a href="#Sleepable RCU">Sleepable RCU</a>
+<li>	<a href="#Tasks RCU">Tasks RCU</a>
+</ol>
+
+<h3><a name="Bottom-Half Flavor">Bottom-Half Flavor</a></h3>
+
+<p>
+The softirq-disable (AKA &ldquo;bottom-half&rdquo;,
+hence the &ldquo;_bh&rdquo; abbreviations)
+flavor of RCU, or <i>RCU-bh</i>, was developed by
+Dipankar Sarma to provide a flavor of RCU that could withstand the
+network-based denial-of-service attacks researched by Robert
+Olsson.
+These attacks placed so much networking load on the system
+that some of the CPUs never exited softirq execution,
+which in turn prevented those CPUs from ever executing a context switch,
+which, in the RCU implementation of that time, prevented grace periods
+from ever ending.
+The result was an out-of-memory condition and a system hang.
+
+<p>
+The solution was the creation of RCU-bh, which does
+<tt>local_bh_disable()</tt>
+across its read-side critical sections, and which uses the transition
+from one type of softirq processing to another as a quiescent state
+in addition to context switch, idle, user mode, and offline.
+This means that RCU-bh grace periods can complete even when some of
+the CPUs execute in softirq indefinitely, thus allowing algorithms
+based on RCU-bh to withstand network-based denial-of-service attacks.
+
+<p>
+Because
+<tt>rcu_read_lock_bh()</tt> and <tt>rcu_read_unlock_bh()</tt>
+disable and re-enable softirq handlers, any attempt to start a softirq
+handlers during the
+RCU-bh read-side critical section will be deferred.
+In this case, <tt>rcu_read_unlock_bh()</tt>
+will invoke softirq processing, which can take considerable time.
+One can of course argue that this softirq overhead should be associated
+with the code following the RCU-bh read-side critical section rather
+than <tt>rcu_read_unlock_bh()</tt>, but the fact
+is that most profiling tools cannot be expected to make this sort
+of fine distinction.
+For example, suppose that a three-millisecond-long RCU-bh read-side
+critical section executes during a time of heavy networking load.
+There will very likely be an attempt to invoke at least one softirq
+handler during that three milliseconds, but any such invocation will
+be delayed until the time of the <tt>rcu_read_unlock_bh()</tt>.
+This can of course make it appear at first glance as if
+<tt>rcu_read_unlock_bh()</tt> was executing very slowly.
+
+<p>
+The
+<a href="https://lwn.net/Articles/609973/#RCU Per-Flavor API Table">RCU-bh API</a>
+includes
+<tt>rcu_read_lock_bh()</tt>,
+<tt>rcu_read_unlock_bh()</tt>,
+<tt>rcu_dereference_bh()</tt>,
+<tt>rcu_dereference_bh_check()</tt>,
+<tt>synchronize_rcu_bh()</tt>,
+<tt>synchronize_rcu_bh_expedited()</tt>,
+<tt>call_rcu_bh()</tt>,
+<tt>rcu_barrier_bh()</tt>, and
+<tt>rcu_read_lock_bh_held()</tt>.
+
+<h3><a name="Sched Flavor">Sched Flavor</a></h3>
+
+<p>
+Before preemptible RCU, waiting for an RCU grace period had the
+side effect of also waiting for all pre-existing interrupt
+and NMI handlers.
+However, there are legitimate preemptible-RCU implementations that
+do not have this property, given that any point in the code outside
+of an RCU read-side critical section can be a quiescent state.
+Therefore, <i>RCU-sched</i> was created, which follows &ldquo;classic&rdquo;
+RCU in that an RCU-sched grace period waits for for pre-existing
+interrupt and NMI handlers.
+In kernels built with <tt>CONFIG_PREEMPT=n</tt>, the RCU and RCU-sched
+APIs have identical implementations, while kernels built with
+<tt>CONFIG_PREEMPT=y</tt> provide a separate implementation for each.
+
+<p>
+Note well that in <tt>CONFIG_PREEMPT=y</tt> kernels,
+<tt>rcu_read_lock_sched()</tt> and <tt>rcu_read_unlock_sched()</tt>
+disable and re-enable preemption, respectively.
+This means that if there was a preemption attempt during the
+RCU-sched read-side critical section, <tt>rcu_read_unlock_sched()</tt>
+will enter the scheduler, with all the latency and overhead entailed.
+Just as with <tt>rcu_read_unlock_bh()</tt>, this can make it look
+as if <tt>rcu_read_unlock_sched()</tt> was executing very slowly.
+However, the highest-priority task won't be preempted, so that task
+will enjoy low-overhead <tt>rcu_read_unlock_sched()</tt> invocations.
+
+<p>
+The
+<a href="https://lwn.net/Articles/609973/#RCU Per-Flavor API Table">RCU-sched API</a>
+includes
+<tt>rcu_read_lock_sched()</tt>,
+<tt>rcu_read_unlock_sched()</tt>,
+<tt>rcu_read_lock_sched_notrace()</tt>,
+<tt>rcu_read_unlock_sched_notrace()</tt>,
+<tt>rcu_dereference_sched()</tt>,
+<tt>rcu_dereference_sched_check()</tt>,
+<tt>synchronize_sched()</tt>,
+<tt>synchronize_rcu_sched_expedited()</tt>,
+<tt>call_rcu_sched()</tt>,
+<tt>rcu_barrier_sched()</tt>, and
+<tt>rcu_read_lock_sched_held()</tt>.
+However, anything that disables preemption also marks an RCU-sched
+read-side critical section, including
+<tt>preempt_disable()</tt> and <tt>preempt_enable()</tt>,
+<tt>local_irq_save()</tt> and <tt>local_irq_restore()</tt>,
+and so on.
+
+<h3><a name="Sleepable RCU">Sleepable RCU</a></h3>
+
+<p>
+For well over a decade, someone saying &ldquo;I need to block within
+an RCU read-side critical section&rdquo; was a reliable indication
+that this someone did not understand RCU.
+After all, if you are always blocking in an RCU read-side critical
+section, you can probably afford to use a higher-overhead synchronization
+mechanism.
+However, that changed with the advent of the Linux kernel's notifiers,
+whose RCU read-side critical
+sections almost never sleep, but sometimes need to.
+This resulted in the introduction of
+<a href="https://lwn.net/Articles/202847/">sleepable RCU</a>,
+or <i>SRCU</i>.
+
+<p>
+SRCU allows different domains to be defined, with each such domain
+defined by an instance of an <tt>srcu_struct</tt> structure.
+A pointer to this structure must be passed in to each SRCU function,
+for example, <tt>synchronize_srcu(&amp;ss)</tt>, where
+<tt>ss</tt> is the <tt>srcu_struct</tt> structure.
+The key benefit of these domains is that a slow SRCU reader in one
+domain does not delay an SRCU grace period in some other domain.
+That said, one consequence of these domains is that read-side code
+must pass a &ldquo;cookie&rdquo; from <tt>srcu_read_lock()</tt>
+to <tt>srcu_read_unlock()</tt>, for example, as follows:
+
+<blockquote>
+<pre>
+ 1 int idx;
+ 2
+ 3 idx = srcu_read_lock(&amp;ss);
+ 4 do_something();
+ 5 srcu_read_unlock(&amp;ss, idx);
+</pre>
+</blockquote>
+
+<p>
+As noted above, it is legal to block within SRCU read-side critical sections,
+however, with great power comes great responsibility.
+If you block forever in one of a given domain's SRCU read-side critical
+sections, then that domain's grace periods will also be blocked forever.
+Of course, one good way to block forever is to deadlock, which can
+happen if any operation in a given domain's SRCU read-side critical
+section can block waiting, either directly or indirectly, for that domain's
+grace period to elapse.
+For example, this results in a self-deadlock:
+
+<blockquote>
+<pre>
+ 1 int idx;
+ 2
+ 3 idx = srcu_read_lock(&amp;ss);
+ 4 do_something();
+ 5 synchronize_srcu(&amp;ss);
+ 6 srcu_read_unlock(&amp;ss, idx);
+</pre>
+</blockquote>
+
+<p>
+However, if line&nbsp;5 acquired a mutex that was held across
+a <tt>synchronize_srcu()</tt> for domain <tt>ss</tt>,
+deadlock would still be possible.
+Furthermore, if line&nbsp;5 acquired a mutex that was held across
+a <tt>synchronize_srcu()</tt> for some other domain <tt>ss1</tt>,
+and if an <tt>ss1</tt>-domain SRCU read-side critical section
+acquired another mutex that was held across as <tt>ss</tt>-domain
+<tt>synchronize_srcu()</tt>,
+deadlock would again be possible.
+Such a deadlock cycle could extend across an arbitrarily large number
+of different SRCU domains.
+Again, with great power comes great responsibility.
+
+<p>
+Unlike the other RCU flavors, SRCU read-side critical sections can
+run on idle and even offline CPUs.
+This ability requires that <tt>srcu_read_lock()</tt> and
+<tt>srcu_read_unlock()</tt> contain memory barriers, which means
+that SRCU readers will run a bit slower than would RCU readers.
+It also motivates the <tt>smp_mb__after_srcu_read_unlock()</tt>
+API, which, in combination with <tt>srcu_read_unlock()</tt>,
+guarantees a full memory barrier.
+
+<p>
+The
+<a href="https://lwn.net/Articles/609973/#RCU Per-Flavor API Table">SRCU API</a>
+includes
+<tt>srcu_read_lock()</tt>,
+<tt>srcu_read_unlock()</tt>,
+<tt>srcu_dereference()</tt>,
+<tt>srcu_dereference_check()</tt>,
+<tt>synchronize_srcu()</tt>,
+<tt>synchronize_srcu_expedited()</tt>,
+<tt>call_srcu()</tt>,
+<tt>srcu_barrier()</tt>, and
+<tt>srcu_read_lock_held()</tt>.
+It also includes
+<tt>DEFINE_SRCU()</tt>,
+<tt>DEFINE_STATIC_SRCU()</tt>, and
+<tt>init_srcu_struct()</tt>
+APIs for defining and initializing <tt>srcu_struct</tt> structures.
+
+<h3><a name="Tasks RCU">Tasks RCU</a></h3>
+
+<p>
+Some forms of tracing use &ldquo;tramopolines&rdquo; to handle the
+binary rewriting required to install different types of probes.
+It would be good to be able to free old trampolines, which sounds
+like a job for some form of RCU.
+However, because it is necessary to be able to install a trace
+anywhere in the code, it is not possible to use read-side markers
+such as <tt>rcu_read_lock()</tt> and <tt>rcu_read_unlock()</tt>.
+In addition, it does not work to have these markers in the trampoline
+itself, because there would need to be instructions following
+<tt>rcu_read_unlock()</tt>.
+Although <tt>synchronize_rcu()</tt> would guarantee that execution
+reached the <tt>rcu_read_unlock()</tt>, it would not be able to
+guarantee that execution had completely left the trampoline.
+
+<p>
+The solution, in the form of
+<a href="https://lwn.net/Articles/607117/"><i>Tasks RCU</i></a>,
+is to have implicit
+read-side critical sections that are delimited by voluntary context
+switches, that is, calls to <tt>schedule()</tt>,
+<tt>cond_resched_rcu_qs()</tt>, and
+<tt>synchronize_rcu_tasks()</tt>.
+In addition, transitions to and from userspace execution also delimit
+tasks-RCU read-side critical sections.
+
+<p>
+The tasks-RCU API is quite compact, consisting only of
+<tt>call_rcu_tasks()</tt>,
+<tt>synchronize_rcu_tasks()</tt>, and
+<tt>rcu_barrier_tasks()</tt>.
+
+<h2><a name="Possible Future Changes">Possible Future Changes</a></h2>
+
+<p>
+One of the tricks that RCU uses to attain update-side scalability is
+to increase grace-period latency with increasing numbers of CPUs.
+If this becomes a serious problem, it will be necessary to rework the
+grace-period state machine so as to avoid the need for the additional
+latency.
+
+<p>
+Expedited grace periods scan the CPUs, so their latency and overhead
+increases with increasing numbers of CPUs.
+If this becomes a serious problem on large systems, it will be necessary
+to do some redesign to avoid this scalability problem.
+
+<p>
+RCU disables CPU hotplug in a few places, perhaps most notably in the
+expedited grace-period and <tt>rcu_barrier()</tt> operations.
+If there is a strong reason to use expedited grace periods in CPU-hotplug
+notifiers, it will be necessary to avoid disabling CPU hotplug.
+This would introduce some complexity, so there had better be a <i>very</i>
+good reason.
+
+<p>
+The tradeoff between grace-period latency on the one hand and interruptions
+of other CPUs on the other hand may need to be re-examined.
+The desire is of course for zero grace-period latency as well as zero
+interprocessor interrupts undertaken during an expedited grace period
+operation.
+While this ideal is unlikely to be achievable, it is quite possible that
+further improvements can be made.
+
+<p>
+The multiprocessor implementations of RCU use a combining tree that
+groups CPUs so as to reduce lock contention and increase cache locality.
+However, this combining tree does not spread its memory across NUMA
+nodes nor does it align the CPU groups with hardware features such
+as sockets or cores.
+Such spreading and alignment is currently believed to be unnecessary
+because the hotpath read-side primitives do not access the combining
+tree, nor does <tt>call_rcu()</tt> in the common case.
+If you believe that your architecture needs such spreading and alignment,
+then your architecture should also benefit from the
+<tt>rcutree.rcu_fanout_leaf</tt> boot parameter, which can be set
+to the number of CPUs in a socket, NUMA node, or whatever.
+If the number of CPUs is too large, use a fraction of the number of
+CPUs.
+If the number of CPUs is a large prime number, well, that certainly
+is an &ldquo;interesting&rdquo; architectural choice!
+More flexible arrangements might be considered, but only if
+<tt>rcutree.rcu_fanout_leaf</tt> has proven inadequate, and only
+if the inadequacy has been demonstrated by a carefully run and
+realistic system-level workload.
+
+<p>
+Please note that arrangements that require RCU to remap CPU numbers will
+require extremely good demonstration of need and full exploration of
+alternatives.
+
+<p>
+There is an embarrassingly large number of flavors of RCU, and this
+number has been increasing over time.
+Perhaps it will be possible to combine some at some future date.
+
+<p>
+RCU's various kthreads are reasonably recent additions.
+It is quite likely that adjustments will be required to more gracefully
+handle extreme loads.
+It might also be necessary to be able to relate CPU utilization by
+RCU's kthreads and softirq handlers to the code that instigated this
+CPU utilization.
+For example, RCU callback overhead might be charged back to the
+originating <tt>call_rcu()</tt> instance, though probably not
+in production kernels.
+
+<h2><a name="Summary">Summary</a></h2>
+
+<p>
+This document has presented more than two decade's worth of RCU
+requirements.
+Given that the requirements keep changing, this will not be the last
+word on this subject, but at least it serves to get an important
+subset of the requirements set forth.
+
+<h2><a name="Acknowledgments">Acknowledgments</a></h2>
+
+I am grateful to Steven Rostedt, Lai Jiangshan, Ingo Molnar,
+Oleg Nesterov, Borislav Petkov, Peter Zijlstra, Boqun Feng, and
+Andy Lutomirski for their help in rendering
+this article human readable, and to Michelle Rankin for her support
+of this effort.
+Other contributions are acknowledged in the Linux kernel's git archive.
+The cartoon is copyright (c) 2013 by Melissa Broussard,
+and is provided
+under the terms of the Creative Commons Attribution-Share Alike 3.0
+United States license.
+
+<h3><a name="Answers to Quick Quizzes">
+Answers to Quick Quizzes</a></h3>
+
+<a name="qq1answer"></a>
+<p><b>Quick Quiz 1</b>:
+Wait a minute!
+You said that updaters can make useful forward progress concurrently
+with readers, but pre-existing readers will block
+<tt>synchronize_rcu()</tt>!!!
+Just who are you trying to fool???
+
+
+</p><p><b>Answer</b>:
+First, if updaters do not wish to be blocked by readers, they can use
+<tt>call_rcu()</tt> or <tt>kfree_rcu()</tt>, which will
+be discussed later.
+Second, even when using <tt>synchronize_rcu()</tt>, the other
+update-side code does run concurrently with readers, whether pre-existing
+or not.
+
+
+</p><p><a href="#Quick%20Quiz%201"><b>Back to Quick Quiz 1</b>.</a>
+
+<a name="qq2answer"></a>
+<p><b>Quick Quiz 2</b>:
+Why is the <tt>synchronize_rcu()</tt> on line&nbsp;28 needed?
+
+
+</p><p><b>Answer</b>:
+Without that extra grace period, memory reordering could result in
+<tt>do_something_dlm()</tt> executing <tt>do_something()</tt>
+concurrently with the last bits of <tt>recovery()</tt>.
+
+
+</p><p><a href="#Quick%20Quiz%202"><b>Back to Quick Quiz 2</b>.</a>
+
+<a name="qq3answer"></a>
+<p><b>Quick Quiz 3</b>:
+But <tt>rcu_assign_pointer()</tt> does nothing to prevent the
+two assignments to <tt>p-&gt;a</tt> and <tt>p-&gt;b</tt>
+from being reordered.
+Can't that also cause problems?
+
+
+</p><p><b>Answer</b>:
+No, it cannot.
+The readers cannot see either of these two fields until
+the assignment to <tt>gp</tt>, by which time both fields are
+fully initialized.
+So reordering the assignments
+to <tt>p-&gt;a</tt> and <tt>p-&gt;b</tt> cannot possibly
+cause any problems.
+
+
+</p><p><a href="#Quick%20Quiz%203"><b>Back to Quick Quiz 3</b>.</a>
+
+<a name="qq4answer"></a>
+<p><b>Quick Quiz 4</b>:
+Without the <tt>rcu_dereference()</tt> or the
+<tt>rcu_access_pointer()</tt>, what destructive optimizations
+might the compiler make use of?
+
+
+</p><p><b>Answer</b>:
+Let's start with what happens to <tt>do_something_gp()</tt>
+if it fails to use <tt>rcu_dereference()</tt>.
+It could reuse a value formerly fetched from this same pointer.
+It could also fetch the pointer from <tt>gp</tt> in a byte-at-a-time
+manner, resulting in <i>load tearing</i>, in turn resulting a bytewise
+mash-up of two distince pointer values.
+It might even use value-speculation optimizations, where it makes a wrong
+guess, but by the time it gets around to checking the value, an update
+has changed the pointer to match the wrong guess.
+Too bad about any dereferences that returned pre-initialization garbage
+in the meantime!
+
+<p>
+For <tt>remove_gp_synchronous()</tt>, as long as all modifications
+to <tt>gp</tt> are carried out while holding <tt>gp_lock</tt>,
+the above optimizations are harmless.
+However,
+with <tt>CONFIG_SPARSE_RCU_POINTER=y</tt>,
+<tt>sparse</tt> will complain if you
+define <tt>gp</tt> with <tt>__rcu</tt> and then
+access it without using
+either <tt>rcu_access_pointer()</tt> or <tt>rcu_dereference()</tt>.
+
+
+</p><p><a href="#Quick%20Quiz%204"><b>Back to Quick Quiz 4</b>.</a>
+
+<a name="qq5answer"></a>
+<p><b>Quick Quiz 5</b>:
+Given that multiple CPUs can start RCU read-side critical sections
+at any time without any ordering whatsoever, how can RCU possibly tell whether
+or not a given RCU read-side critical section starts before a
+given instance of <tt>synchronize_rcu()</tt>?
+
+
+</p><p><b>Answer</b>:
+If RCU cannot tell whether or not a given
+RCU read-side critical section starts before a
+given instance of <tt>synchronize_rcu()</tt>,
+then it must assume that the RCU read-side critical section
+started first.
+In other words, a given instance of <tt>synchronize_rcu()</tt>
+can avoid waiting on a given RCU read-side critical section only
+if it can prove that <tt>synchronize_rcu()</tt> started first.
+
+
+</p><p><a href="#Quick%20Quiz%205"><b>Back to Quick Quiz 5</b>.</a>
+
+<a name="qq6answer"></a>
+<p><b>Quick Quiz 6</b>:
+The first and second guarantees require unbelievably strict ordering!
+Are all these memory barriers <i> really</i> required?
+
+
+</p><p><b>Answer</b>:
+Yes, they really are required.
+To see why the first guarantee is required, consider the following
+sequence of events:
+
+<ol>
+<li>	CPU 1: <tt>rcu_read_lock()</tt>
+<li>	CPU 1: <tt>q = rcu_dereference(gp);
+	/* Very likely to return p. */</tt>
+<li>	CPU 0: <tt>list_del_rcu(p);</tt>
+<li>	CPU 0: <tt>synchronize_rcu()</tt> starts.
+<li>	CPU 1: <tt>do_something_with(q-&gt;a);
+	/* No smp_mb(), so might happen after kfree(). */</tt>
+<li>	CPU 1: <tt>rcu_read_unlock()</tt>
+<li>	CPU 0: <tt>synchronize_rcu()</tt> returns.
+<li>	CPU 0: <tt>kfree(p);</tt>
+</ol>
+
+<p>
+Therefore, there absolutely must be a full memory barrier between the
+end of the RCU read-side critical section and the end of the
+grace period.
+
+<p>
+The sequence of events demonstrating the necessity of the second rule
+is roughly similar:
+
+<ol>
+<li>	CPU 0: <tt>list_del_rcu(p);</tt>
+<li>	CPU 0: <tt>synchronize_rcu()</tt> starts.
+<li>	CPU 1: <tt>rcu_read_lock()</tt>
+<li>	CPU 1: <tt>q = rcu_dereference(gp);
+	/* Might return p if no memory barrier. */</tt>
+<li>	CPU 0: <tt>synchronize_rcu()</tt> returns.
+<li>	CPU 0: <tt>kfree(p);</tt>
+<li>	CPU 1: <tt>do_something_with(q-&gt;a); /* Boom!!! */</tt>
+<li>	CPU 1: <tt>rcu_read_unlock()</tt>
+</ol>
+
+<p>
+And similarly, without a memory barrier between the beginning of the
+grace period and the beginning of the RCU read-side critical section,
+CPU&nbsp;1 might end up accessing the freelist.
+
+<p>
+The &ldquo;as if&rdquo; rule of course applies, so that any implementation
+that acts as if the appropriate memory barriers were in place is a
+correct implementation.
+That said, it is much easier to fool yourself into believing that you have
+adhered to the as-if rule than it is to actually adhere to it!
+
+
+</p><p><a href="#Quick%20Quiz%206"><b>Back to Quick Quiz 6</b>.</a>
+
+<a name="qq7answer"></a>
+<p><b>Quick Quiz 7</b>:
+But how does the upgrade-to-write operation exclude other readers?
+
+
+</p><p><b>Answer</b>:
+It doesn't, just like normal RCU updates, which also do not exclude
+RCU readers.
+
+
+</p><p><a href="#Quick%20Quiz%207"><b>Back to Quick Quiz 7</b>.</a>
+
+<a name="qq8answer"></a>
+<p><b>Quick Quiz 8</b>:
+Can't the compiler also reorder this code?
+
+
+</p><p><b>Answer</b>:
+No, the volatile casts in <tt>READ_ONCE()</tt> and
+<tt>WRITE_ONCE()</tt> prevent the compiler from reordering in
+this particular case.
+
+
+</p><p><a href="#Quick%20Quiz%208"><b>Back to Quick Quiz 8</b>.</a>
+
+<a name="qq9answer"></a>
+<p><b>Quick Quiz 9</b>:
+Suppose that synchronize_rcu() did wait until all readers had completed.
+Would the updater be able to rely on this?
+
+
+</p><p><b>Answer</b>:
+No.
+Even if <tt>synchronize_rcu()</tt> were to wait until
+all readers had completed, a new reader might start immediately after
+<tt>synchronize_rcu()</tt> completed.
+Therefore, the code following
+<tt>synchronize_rcu()</tt> cannot rely on there being no readers
+in any case.
+
+
+</p><p><a href="#Quick%20Quiz%209"><b>Back to Quick Quiz 9</b>.</a>
+
+<a name="qq10answer"></a>
+<p><b>Quick Quiz 10</b>:
+How long a sequence of grace periods, each separated by an RCU read-side
+critical section, would be required to partition the RCU read-side
+critical sections at the beginning and end of the chain?
+
+
+</p><p><b>Answer</b>:
+In theory, an infinite number.
+In practice, an unknown number that is sensitive to both implementation
+details and timing considerations.
+Therefore, even in practice, RCU users must abide by the theoretical rather
+than the practical answer.
+
+
+</p><p><a href="#Quick%20Quiz%2010"><b>Back to Quick Quiz 10</b>.</a>
+
+<a name="qq11answer"></a>
+<p><b>Quick Quiz 11</b>:
+What about sleeping locks?
+
+
+</p><p><b>Answer</b>:
+These are forbidden within Linux-kernel RCU read-side critical sections
+because it is not legal to place a quiescent state (in this case,
+voluntary context switch) within an RCU read-side critical section.
+However, sleeping locks may be used within userspace RCU read-side critical
+sections, and also within Linux-kernel sleepable RCU
+<a href="#Sleepable RCU">(SRCU)</a>
+read-side critical sections.
+In addition, the -rt patchset turns spinlocks into a sleeping locks so
+that the corresponding critical sections can be preempted, which
+also means that these sleeplockified spinlocks (but not other sleeping locks!)
+may be acquire within -rt-Linux-kernel RCU read-side critical sections.
+
+<p>
+Note that it <i>is</i> legal for a normal RCU read-side critical section
+to conditionally acquire a sleeping locks (as in <tt>mutex_trylock()</tt>),
+but only as long as it does not loop indefinitely attempting to
+conditionally acquire that sleeping locks.
+The key point is that things like <tt>mutex_trylock()</tt>
+either return with the mutex held, or return an error indication if
+the mutex was not immediately available.
+Either way, <tt>mutex_trylock()</tt> returns immediately without sleeping.
+
+
+</p><p><a href="#Quick%20Quiz%2011"><b>Back to Quick Quiz 11</b>.</a>
+
+<a name="qq12answer"></a>
+<p><b>Quick Quiz 12</b>:
+Why does line&nbsp;19 use <tt>rcu_access_pointer()</tt>?
+After all, <tt>call_rcu()</tt> on line&nbsp;25 stores into the
+structure, which would interact badly with concurrent insertions.
+Doesn't this mean that <tt>rcu_dereference()</tt> is required?
+
+
+</p><p><b>Answer</b>:
+Presumably the <tt>-&gt;gp_lock</tt> acquired on line&nbsp;18 excludes
+any changes, including any insertions that <tt>rcu_dereference()</tt>
+would protect against.
+Therefore, any insertions will be delayed until after <tt>-&gt;gp_lock</tt>
+is released on line&nbsp;25, which in turn means that
+<tt>rcu_access_pointer()</tt> suffices.
+
+
+</p><p><a href="#Quick%20Quiz%2012"><b>Back to Quick Quiz 12</b>.</a>
+
+<a name="qq13answer"></a>
+<p><b>Quick Quiz 13</b>:
+Earlier it was claimed that <tt>call_rcu()</tt> and
+<tt>kfree_rcu()</tt> allowed updaters to avoid being blocked
+by readers.
+But how can that be correct, given that the invocation of the callback
+and the freeing of the memory (respectively) must still wait for
+a grace period to elapse?
+
+
+</p><p><b>Answer</b>:
+We could define things this way, but keep in mind that this sort of
+definition would say that updates in garbage-collected languages
+cannot complete until the next time the garbage collector runs,
+which does not seem at all reasonable.
+The key point is that in most cases, an updater using either
+<tt>call_rcu()</tt> or <tt>kfree_rcu()</tt> can proceed to the
+next update as soon as it has invoked <tt>call_rcu()</tt> or
+<tt>kfree_rcu()</tt>, without having to wait for a subsequent
+grace period.
+
+
+</p><p><a href="#Quick%20Quiz%2013"><b>Back to Quick Quiz 13</b>.</a>
+
+<a name="qq14answer"></a>
+<p><b>Quick Quiz 14</b>:
+So what happens with <tt>synchronize_rcu()</tt> during
+scheduler initialization for <tt>CONFIG_PREEMPT=n</tt>
+kernels?
+
+
+</p><p><b>Answer</b>:
+In <tt>CONFIG_PREEMPT=n</tt> kernel, <tt>synchronize_rcu()</tt>
+maps directly to <tt>synchronize_sched()</tt>.
+Therefore, <tt>synchronize_rcu()</tt> works normally throughout
+boot in <tt>CONFIG_PREEMPT=n</tt> kernels.
+However, your code must also work in <tt>CONFIG_PREEMPT=y</tt> kernels,
+so it is still necessary to avoid invoking <tt>synchronize_rcu()</tt>
+during scheduler initialization.
+
+
+</p><p><a href="#Quick%20Quiz%2014"><b>Back to Quick Quiz 14</b>.</a>
+
+
+</body></html>
diff --git a/Documentation/RCU/Design/Requirements/Requirements.htmlx b/Documentation/RCU/Design/Requirements/Requirements.htmlx
new file mode 100644
index 0000000..3a97ba4
--- /dev/null
+++ b/Documentation/RCU/Design/Requirements/Requirements.htmlx
@@ -0,0 +1,2741 @@
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"
+        "http://www.w3.org/TR/html4/loose.dtd">
+        <html>
+        <head><title>A Tour Through RCU's Requirements [LWN.net]</title>
+        <meta HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=utf-8">
+
+<h1>A Tour Through RCU's Requirements</h1>
+
+<p>Copyright IBM Corporation, 2015</p>
+<p>Author: Paul E.&nbsp;McKenney</p>
+<p><i>The initial version of this document appeared in the
+<a href="https://lwn.net/">LWN</a> articles
+<a href="https://lwn.net/Articles/652156/">here</a>,
+<a href="https://lwn.net/Articles/652677/">here</a>, and
+<a href="https://lwn.net/Articles/653326/">here</a>.</i></p>
+
+<h2>Introduction</h2>
+
+<p>
+Read-copy update (RCU) is a synchronization mechanism that is often
+used as a replacement for reader-writer locking.
+RCU is unusual in that updaters do not block readers,
+which means that RCU's read-side primitives can be exceedingly fast
+and scalable.
+In addition, updaters can make useful forward progress concurrently
+with readers.
+However, all this concurrency between RCU readers and updaters does raise
+the question of exactly what RCU readers are doing, which in turn
+raises the question of exactly what RCU's requirements are.
+
+<p>
+This document therefore summarizes RCU's requirements, and can be thought
+of as an informal, high-level specification for RCU.
+It is important to understand that RCU's specification is primarily
+empirical in nature;
+in fact, I learned about many of these requirements the hard way.
+This situation might cause some consternation, however, not only
+has this learning process been a lot of fun, but it has also been
+a great privilege to work with so many people willing to apply
+technologies in interesting new ways.
+
+<p>
+All that aside, here are the categories of currently known RCU requirements:
+</p>
+
+<ol>
+<li>	<a href="#Fundamental Requirements">
+	Fundamental Requirements</a>
+<li>	<a href="#Fundamental Non-Requirements">Fundamental Non-Requirements</a>
+<li>	<a href="#Parallelism Facts of Life">
+	Parallelism Facts of Life</a>
+<li>	<a href="#Quality-of-Implementation Requirements">
+	Quality-of-Implementation Requirements</a>
+<li>	<a href="#Linux Kernel Complications">
+	Linux Kernel Complications</a>
+<li>	<a href="#Software-Engineering Requirements">
+	Software-Engineering Requirements</a>
+<li>	<a href="#Other RCU Flavors">
+	Other RCU Flavors</a>
+<li>	<a href="#Possible Future Changes">
+	Possible Future Changes</a>
+</ol>
+
+<p>
+This is followed by a <a href="#Summary">summary</a>,
+which is in turn followed by the inevitable
+<a href="#Answers to Quick Quizzes">answers to the quick quizzes</a>.
+
+<h2><a name="Fundamental Requirements">Fundamental Requirements</a></h2>
+
+<p>
+RCU's fundamental requirements are the closest thing RCU has to hard
+mathematical requirements.
+These are:
+
+<ol>
+<li>	<a href="#Grace-Period Guarantee">
+	Grace-Period Guarantee</a>
+<li>	<a href="#Publish-Subscribe Guarantee">
+	Publish-Subscribe Guarantee</a>
+<li>	<a href="#Memory-Barrier Guarantees">
+	Memory-Barrier Guarantees</a>
+<li>	<a href="#RCU Primitives Guaranteed to Execute Unconditionally">
+	RCU Primitives Guaranteed to Execute Unconditionally</a>
+<li>	<a href="#Guaranteed Read-to-Write Upgrade">
+	Guaranteed Read-to-Write Upgrade</a>
+</ol>
+
+<h3><a name="Grace-Period Guarantee">Grace-Period Guarantee</a></h3>
+
+<p>
+RCU's grace-period guarantee is unusual in being premeditated:
+Jack Slingwine and I had this guarantee firmly in mind when we started
+work on RCU (then called &ldquo;rclock&rdquo;) in the early 1990s.
+That said, the past two decades of experience with RCU have produced
+a much more detailed understanding of this guarantee.
+
+<p>
+RCU's grace-period guarantee allows updaters to wait for the completion
+of all pre-existing RCU read-side critical sections.
+An RCU read-side critical section
+begins with the marker <tt>rcu_read_lock()</tt> and ends with
+the marker <tt>rcu_read_unlock()</tt>.
+These markers may be nested, and RCU treats a nested set as one
+big RCU read-side critical section.
+Production-quality implementations of <tt>rcu_read_lock()</tt> and
+<tt>rcu_read_unlock()</tt> are extremely lightweight, and in
+fact have exactly zero overhead in Linux kernels built for production
+use with <tt>CONFIG_PREEMPT=n</tt>.
+
+<p>
+This guarantee allows ordering to be enforced with extremely low
+overhead to readers, for example:
+
+<blockquote>
+<pre>
+ 1 int x, y;
+ 2
+ 3 void thread0(void)
+ 4 {
+ 5   rcu_read_lock();
+ 6   r1 = READ_ONCE(x);
+ 7   r2 = READ_ONCE(y);
+ 8   rcu_read_unlock();
+ 9 }
+10
+11 void thread1(void)
+12 {
+13   WRITE_ONCE(x, 1);
+14   synchronize_rcu();
+15   WRITE_ONCE(y, 1);
+16 }
+</pre>
+</blockquote>
+
+<p>
+Because the <tt>synchronize_rcu()</tt> on line&nbsp;14 waits for
+all pre-existing readers, any instance of <tt>thread0()</tt> that
+loads a value of zero from <tt>x</tt> must complete before
+<tt>thread1()</tt> stores to <tt>y</tt>, so that instance must
+also load a value of zero from <tt>y</tt>.
+Similarly, any instance of <tt>thread0()</tt> that loads a value of
+one from <tt>y</tt> must have started after the
+<tt>synchronize_rcu()</tt> started, and must therefore also load
+a value of one from <tt>x</tt>.
+Therefore, the outcome:
+<blockquote>
+<pre>
+(r1 == 0 &amp;&amp; r2 == 1)
+</pre>
+</blockquote>
+cannot happen.
+
+<p>@@QQ@@
+Wait a minute!
+You said that updaters can make useful forward progress concurrently
+with readers, but pre-existing readers will block
+<tt>synchronize_rcu()</tt>!!!
+Just who are you trying to fool???
+<p>@@QQA@@
+First, if updaters do not wish to be blocked by readers, they can use
+<tt>call_rcu()</tt> or <tt>kfree_rcu()</tt>, which will
+be discussed later.
+Second, even when using <tt>synchronize_rcu()</tt>, the other
+update-side code does run concurrently with readers, whether pre-existing
+or not.
+<p>@@QQE@@
+
+<p>
+This scenario resembles one of the first uses of RCU in
+<a href="https://en.wikipedia.org/wiki/DYNIX">DYNIX/ptx</a>,
+which managed a distributed lock manager's transition into
+a state suitable for handling recovery from node failure,
+more or less as follows:
+
+<blockquote>
+<pre>
+ 1 #define STATE_NORMAL        0
+ 2 #define STATE_WANT_RECOVERY 1
+ 3 #define STATE_RECOVERING    2
+ 4 #define STATE_WANT_NORMAL   3
+ 5
+ 6 int state = STATE_NORMAL;
+ 7
+ 8 void do_something_dlm(void)
+ 9 {
+10   int state_snap;
+11
+12   rcu_read_lock();
+13   state_snap = READ_ONCE(state);
+14   if (state_snap == STATE_NORMAL)
+15     do_something();
+16   else
+17     do_something_carefully();
+18   rcu_read_unlock();
+19 }
+20
+21 void start_recovery(void)
+22 {
+23   WRITE_ONCE(state, STATE_WANT_RECOVERY);
+24   synchronize_rcu();
+25   WRITE_ONCE(state, STATE_RECOVERING);
+26   recovery();
+27   WRITE_ONCE(state, STATE_WANT_NORMAL);
+28   synchronize_rcu();
+29   WRITE_ONCE(state, STATE_NORMAL);
+30 }
+</pre>
+</blockquote>
+
+<p>
+The RCU read-side critical section in <tt>do_something_dlm()</tt>
+works with the <tt>synchronize_rcu()</tt> in <tt>start_recovery()</tt>
+to guarantee that <tt>do_something()</tt> never runs concurrently
+with <tt>recovery()</tt>, but with little or no synchronization
+overhead in <tt>do_something_dlm()</tt>.
+
+<p>@@QQ@@
+Why is the <tt>synchronize_rcu()</tt> on line&nbsp;28 needed?
+<p>@@QQA@@
+Without that extra grace period, memory reordering could result in
+<tt>do_something_dlm()</tt> executing <tt>do_something()</tt>
+concurrently with the last bits of <tt>recovery()</tt>.
+<p>@@QQE@@
+
+<p>
+In order to avoid fatal problems such as deadlocks,
+an RCU read-side critical section must not contain calls to
+<tt>synchronize_rcu()</tt>.
+Similarly, an RCU read-side critical section must not
+contain anything that waits, directly or indirectly, on completion of
+an invocation of <tt>synchronize_rcu()</tt>.
+
+<p>
+Although RCU's grace-period guarantee is useful in and of itself, with
+<a href="https://lwn.net/Articles/573497/">quite a few use cases</a>,
+it would be good to be able to use RCU to coordinate read-side
+access to linked data structures.
+For this, the grace-period guarantee is not sufficient, as can
+be seen in function <tt>add_gp_buggy()</tt> below.
+We will look at the reader's code later, but in the meantime, just think of
+the reader as locklessly picking up the <tt>gp</tt> pointer,
+and, if the value loaded is non-<tt>NULL</tt>, locklessly accessing the
+<tt>-&gt;a</tt> and <tt>-&gt;b</tt> fields.
+
+<blockquote>
+<pre>
+ 1 bool add_gp_buggy(int a, int b)
+ 2 {
+ 3   p = kmalloc(sizeof(*p), GFP_KERNEL);
+ 4   if (!p)
+ 5     return -ENOMEM;
+ 6   spin_lock(&amp;gp_lock);
+ 7   if (rcu_access_pointer(gp)) {
+ 8     spin_unlock(&amp;gp_lock);
+ 9     return false;
+10   }
+11   p-&gt;a = a;
+12   p-&gt;b = a;
+13   gp = p; /* ORDERING BUG */
+14   spin_unlock(&amp;gp_lock);
+15   return true;
+16 }
+</pre>
+</blockquote>
+
+<p>
+The problem is that both the compiler and weakly ordered CPUs are within
+their rights to reorder this code as follows:
+
+<blockquote>
+<pre>
+ 1 bool add_gp_buggy_optimized(int a, int b)
+ 2 {
+ 3   p = kmalloc(sizeof(*p), GFP_KERNEL);
+ 4   if (!p)
+ 5     return -ENOMEM;
+ 6   spin_lock(&amp;gp_lock);
+ 7   if (rcu_access_pointer(gp)) {
+ 8     spin_unlock(&amp;gp_lock);
+ 9     return false;
+10   }
+<b>11   gp = p; /* ORDERING BUG */
+12   p-&gt;a = a;
+13   p-&gt;b = a;</b>
+14   spin_unlock(&amp;gp_lock);
+15   return true;
+16 }
+</pre>
+</blockquote>
+
+<p>
+If an RCU reader fetches <tt>gp</tt> just after
+<tt>add_gp_buggy_optimized</tt> executes line&nbsp;11,
+it will see garbage in the <tt>-&gt;a</tt> and <tt>-&gt;b</tt>
+fields.
+And this is but one of many ways in which compiler and hardware optimizations
+could cause trouble.
+Therefore, we clearly need some way to prevent the compiler and the CPU from
+reordering in this manner, which brings us to the publish-subscribe
+guarantee discussed in the next section.
+
+<h3><a name="Publish-Subscribe Guarantee">Publish/Subscribe Guarantee</a></h3>
+
+<p>
+RCU's publish-subscribe guarantee allows data to be inserted
+into a linked data structure without disrupting RCU readers.
+The updater uses <tt>rcu_assign_pointer()</tt> to insert the
+new data, and readers use <tt>rcu_dereference()</tt> to
+access data, whether new or old.
+The following shows an example of insertion:
+
+<blockquote>
+<pre>
+ 1 bool add_gp(int a, int b)
+ 2 {
+ 3   p = kmalloc(sizeof(*p), GFP_KERNEL);
+ 4   if (!p)
+ 5     return -ENOMEM;
+ 6   spin_lock(&amp;gp_lock);
+ 7   if (rcu_access_pointer(gp)) {
+ 8     spin_unlock(&amp;gp_lock);
+ 9     return false;
+10   }
+11   p-&gt;a = a;
+12   p-&gt;b = a;
+13   rcu_assign_pointer(gp, p);
+14   spin_unlock(&amp;gp_lock);
+15   return true;
+16 }
+</pre>
+</blockquote>
+
+<p>
+The <tt>rcu_assign_pointer()</tt> on line&nbsp;13 is conceptually
+equivalent to a simple assignment statement, but also guarantees
+that its assignment will
+happen after the two assignments in lines&nbsp;11 and&nbsp;12,
+similar to the C11 <tt>memory_order_release</tt> store operation.
+It also prevents any number of &ldquo;interesting&rdquo; compiler
+optimizations, for example, the use of <tt>gp</tt> as a scratch
+location immediately preceding the assignment.
+
+<p>@@QQ@@
+But <tt>rcu_assign_pointer()</tt> does nothing to prevent the
+two assignments to <tt>p-&gt;a</tt> and <tt>p-&gt;b</tt>
+from being reordered.
+Can't that also cause problems?
+<p>@@QQA@@
+No, it cannot.
+The readers cannot see either of these two fields until
+the assignment to <tt>gp</tt>, by which time both fields are
+fully initialized.
+So reordering the assignments
+to <tt>p-&gt;a</tt> and <tt>p-&gt;b</tt> cannot possibly
+cause any problems.
+<p>@@QQE@@
+
+<p>
+It is tempting to assume that the reader need not do anything special
+to control its accesses to the RCU-protected data,
+as shown in <tt>do_something_gp_buggy()</tt> below:
+
+<blockquote>
+<pre>
+ 1 bool do_something_gp_buggy(void)
+ 2 {
+ 3   rcu_read_lock();
+ 4   p = gp;  /* OPTIMIZATIONS GALORE!!! */
+ 5   if (p) {
+ 6     do_something(p-&gt;a, p-&gt;b);
+ 7     rcu_read_unlock();
+ 8     return true;
+ 9   }
+10   rcu_read_unlock();
+11   return false;
+12 }
+</pre>
+</blockquote>
+
+<p>
+However, this temptation must be resisted because there are a
+surprisingly large number of ways that the compiler
+(to say nothing of
+<a href="https://h71000.www7.hp.com/wizard/wiz_2637.html">DEC Alpha CPUs</a>)
+can trip this code up.
+For but one example, if the compiler were short of registers, it
+might choose to refetch from <tt>gp</tt> rather than keeping
+a separate copy in <tt>p</tt> as follows:
+
+<blockquote>
+<pre>
+ 1 bool do_something_gp_buggy_optimized(void)
+ 2 {
+ 3   rcu_read_lock();
+ 4   if (gp) { /* OPTIMIZATIONS GALORE!!! */
+<b> 5     do_something(gp-&gt;a, gp-&gt;b);</b>
+ 6     rcu_read_unlock();
+ 7     return true;
+ 8   }
+ 9   rcu_read_unlock();
+10   return false;
+11 }
+</pre>
+</blockquote>
+
+<p>
+If this function ran concurrently with a series of updates that
+replaced the current structure with a new one,
+the fetches of <tt>gp-&gt;a</tt>
+and <tt>gp-&gt;b</tt> might well come from two different structures,
+which could cause serious confusion.
+To prevent this (and much else besides), <tt>do_something_gp()</tt> uses
+<tt>rcu_dereference()</tt> to fetch from <tt>gp</tt>:
+
+<blockquote>
+<pre>
+ 1 bool do_something_gp(void)
+ 2 {
+ 3   rcu_read_lock();
+ 4   p = rcu_dereference(gp);
+ 5   if (p) {
+ 6     do_something(p-&gt;a, p-&gt;b);
+ 7     rcu_read_unlock();
+ 8     return true;
+ 9   }
+10   rcu_read_unlock();
+11   return false;
+12 }
+</pre>
+</blockquote>
+
+<p>
+The <tt>rcu_dereference()</tt> uses volatile casts and (for DEC Alpha)
+memory barriers in the Linux kernel.
+Should a
+<a href="http://www.rdrop.com/users/paulmck/RCU/consume.2015.07.13a.pdf">high-quality implementation of C11 <tt>memory_order_consume</tt> [PDF]</a>
+ever appear, then <tt>rcu_dereference()</tt> could be implemented
+as a <tt>memory_order_consume</tt> load.
+Regardless of the exact implementation, a pointer fetched by
+<tt>rcu_dereference()</tt> may not be used outside of the
+outermost RCU read-side critical section containing that
+<tt>rcu_dereference()</tt>, unless protection of
+the corresponding data element has been passed from RCU to some
+other synchronization mechanism, most commonly locking or
+<a href="https://www.kernel.org/doc/Documentation/RCU/rcuref.txt">reference counting</a>.
+
+<p>
+In short, updaters use <tt>rcu_assign_pointer()</tt> and readers
+use <tt>rcu_dereference()</tt>, and these two RCU API elements
+work together to ensure that readers have a consistent view of
+newly added data elements.
+
+<p>
+Of course, it is also necessary to remove elements from RCU-protected
+data structures, for example, using the following process:
+
+<ol>
+<li>	Remove the data element from the enclosing structure.
+<li>	Wait for all pre-existing RCU read-side critical sections
+	to complete (because only pre-existing readers can possibly have
+	a reference to the newly removed data element).
+<li>	At this point, only the updater has a reference to the
+	newly removed data element, so it can safely reclaim
+	the data element, for example, by passing it to <tt>kfree()</tt>.
+</ol>
+
+This process is implemented by <tt>remove_gp_synchronous()</tt>:
+
+<blockquote>
+<pre>
+ 1 bool remove_gp_synchronous(void)
+ 2 {
+ 3   struct foo *p;
+ 4
+ 5   spin_lock(&amp;gp_lock);
+ 6   p = rcu_access_pointer(gp);
+ 7   if (!p) {
+ 8     spin_unlock(&amp;gp_lock);
+ 9     return false;
+10   }
+11   rcu_assign_pointer(gp, NULL);
+12   spin_unlock(&amp;gp_lock);
+13   synchronize_rcu();
+14   kfree(p);
+15   return true;
+16 }
+</pre>
+</blockquote>
+
+<p>
+This function is straightforward, with line&nbsp;13 waiting for a grace
+period before line&nbsp;14 frees the old data element.
+This waiting ensures that readers will reach line&nbsp;7 of
+<tt>do_something_gp()</tt> before the data element referenced by
+<tt>p</tt> is freed.
+The <tt>rcu_access_pointer()</tt> on line&nbsp;6 is similar to
+<tt>rcu_dereference()</tt>, except that:
+
+<ol>
+<li>	The value returned by <tt>rcu_access_pointer()</tt>
+	cannot be dereferenced.
+	If you want to access the value pointed to as well as
+	the pointer itself, use <tt>rcu_dereference()</tt>
+	instead of <tt>rcu_access_pointer()</tt>.
+<li>	The call to <tt>rcu_access_pointer()</tt> need not be
+	protected.
+	In contrast, <tt>rcu_dereference()</tt> must either be
+	within an RCU read-side critical section or in a code
+	segment where the pointer cannot change, for example, in
+	code protected by the corresponding update-side lock.
+</ol>
+
+<p>@@QQ@@
+Without the <tt>rcu_dereference()</tt> or the
+<tt>rcu_access_pointer()</tt>, what destructive optimizations
+might the compiler make use of?
+<p>@@QQA@@
+Let's start with what happens to <tt>do_something_gp()</tt>
+if it fails to use <tt>rcu_dereference()</tt>.
+It could reuse a value formerly fetched from this same pointer.
+It could also fetch the pointer from <tt>gp</tt> in a byte-at-a-time
+manner, resulting in <i>load tearing</i>, in turn resulting a bytewise
+mash-up of two distince pointer values.
+It might even use value-speculation optimizations, where it makes a wrong
+guess, but by the time it gets around to checking the value, an update
+has changed the pointer to match the wrong guess.
+Too bad about any dereferences that returned pre-initialization garbage
+in the meantime!
+
+<p>
+For <tt>remove_gp_synchronous()</tt>, as long as all modifications
+to <tt>gp</tt> are carried out while holding <tt>gp_lock</tt>,
+the above optimizations are harmless.
+However,
+with <tt>CONFIG_SPARSE_RCU_POINTER=y</tt>,
+<tt>sparse</tt> will complain if you
+define <tt>gp</tt> with <tt>__rcu</tt> and then
+access it without using
+either <tt>rcu_access_pointer()</tt> or <tt>rcu_dereference()</tt>.
+<p>@@QQE@@
+
+<p>
+In short, RCU's publish-subscribe guarantee is provided by the combination
+of <tt>rcu_assign_pointer()</tt> and <tt>rcu_dereference()</tt>.
+This guarantee allows data elements to be safely added to RCU-protected
+linked data structures without disrupting RCU readers.
+This guarantee can be used in combination with the grace-period
+guarantee to also allow data elements to be removed from RCU-protected
+linked data structures, again without disrupting RCU readers.
+
+<p>
+This guarantee was only partially premeditated.
+DYNIX/ptx used an explicit memory barrier for publication, but had nothing
+resembling <tt>rcu_dereference()</tt> for subscription, nor did it
+have anything resembling the <tt>smp_read_barrier_depends()</tt>
+that was later subsumed into <tt>rcu_dereference()</tt>.
+The need for these operations made itself known quite suddenly at a
+late-1990s meeting with the DEC Alpha architects, back in the days when
+DEC was still a free-standing company.
+It took the Alpha architects a good hour to convince me that any sort
+of barrier would ever be needed, and it then took me a good <i>two</i> hours
+to convince them that their documentation did not make this point clear.
+More recent work with the C and C++ standards committees have provided
+much education on tricks and traps from the compiler.
+In short, compilers were much less tricky in the early 1990s, but in
+2015, don't even think about omitting <tt>rcu_dereference()</tt>!
+
+<h3><a name="Memory-Barrier Guarantees">Memory-Barrier Guarantees</a></h3>
+
+<p>
+The previous section's simple linked-data-structure scenario clearly
+demonstrates the need for RCU's stringent memory-ordering guarantees on
+systems with more than one CPU:
+
+<ol>
+<li>	Each CPU that has an RCU read-side critical section that
+	begins before <tt>synchronize_rcu()</tt> starts is
+	guaranteed to execute a full memory barrier between the time
+	that the RCU read-side critical section ends and the time that
+	<tt>synchronize_rcu()</tt> returns.
+	Without this guarantee, a pre-existing RCU read-side critical section
+	might hold a reference to the newly removed <tt>struct foo</tt>
+	after the <tt>kfree()</tt> on line&nbsp;14 of
+	<tt>remove_gp_synchronous()</tt>.
+<li>	Each CPU that has an RCU read-side critical section that ends
+	after <tt>synchronize_rcu()</tt> returns is guaranteed
+	to execute a full memory barrier between the time that
+	<tt>synchronize_rcu()</tt> begins and the time that the RCU
+	read-side critical section begins.
+	Without this guarantee, a later RCU read-side critical section
+	running after the <tt>kfree()</tt> on line&nbsp;14 of
+	<tt>remove_gp_synchronous()</tt> might
+	later run <tt>do_something_gp()</tt> and find the
+	newly deleted <tt>struct foo</tt>.
+<li>	If the task invoking <tt>synchronize_rcu()</tt> remains
+	on a given CPU, then that CPU is guaranteed to execute a full
+	memory barrier sometime during the execution of
+	<tt>synchronize_rcu()</tt>.
+	This guarantee ensures that the <tt>kfree()</tt> on
+	line&nbsp;14 of <tt>remove_gp_synchronous()</tt> really does
+	execute after the removal on line&nbsp;11.
+<li>	If the task invoking <tt>synchronize_rcu()</tt> migrates
+	among a group of CPUs during that invocation, then each of the
+	CPUs in that group is guaranteed to execute a full memory barrier
+	sometime during the execution of <tt>synchronize_rcu()</tt>.
+	This guarantee also ensures that the <tt>kfree()</tt> on
+	line&nbsp;14 of <tt>remove_gp_synchronous()</tt> really does
+	execute after the removal on
+	line&nbsp;11, but also in the case where the thread executing the
+	<tt>synchronize_rcu()</tt> migrates in the meantime.
+</ol>
+
+<p>@@QQ@@
+Given that multiple CPUs can start RCU read-side critical sections
+at any time without any ordering whatsoever, how can RCU possibly tell whether
+or not a given RCU read-side critical section starts before a
+given instance of <tt>synchronize_rcu()</tt>?
+<p>@@QQA@@
+If RCU cannot tell whether or not a given
+RCU read-side critical section starts before a
+given instance of <tt>synchronize_rcu()</tt>,
+then it must assume that the RCU read-side critical section
+started first.
+In other words, a given instance of <tt>synchronize_rcu()</tt>
+can avoid waiting on a given RCU read-side critical section only
+if it can prove that <tt>synchronize_rcu()</tt> started first.
+<p>@@QQE@@
+
+<p>@@QQ@@
+The first and second guarantees require unbelievably strict ordering!
+Are all these memory barriers <i> really</i> required?
+<p>@@QQA@@
+Yes, they really are required.
+To see why the first guarantee is required, consider the following
+sequence of events:
+
+<ol>
+<li>	CPU 1: <tt>rcu_read_lock()</tt>
+<li>	CPU 1: <tt>q = rcu_dereference(gp);
+	/* Very likely to return p. */</tt>
+<li>	CPU 0: <tt>list_del_rcu(p);</tt>
+<li>	CPU 0: <tt>synchronize_rcu()</tt> starts.
+<li>	CPU 1: <tt>do_something_with(q-&gt;a);
+	/* No smp_mb(), so might happen after kfree(). */</tt>
+<li>	CPU 1: <tt>rcu_read_unlock()</tt>
+<li>	CPU 0: <tt>synchronize_rcu()</tt> returns.
+<li>	CPU 0: <tt>kfree(p);</tt>
+</ol>
+
+<p>
+Therefore, there absolutely must be a full memory barrier between the
+end of the RCU read-side critical section and the end of the
+grace period.
+
+<p>
+The sequence of events demonstrating the necessity of the second rule
+is roughly similar:
+
+<ol>
+<li>	CPU 0: <tt>list_del_rcu(p);</tt>
+<li>	CPU 0: <tt>synchronize_rcu()</tt> starts.
+<li>	CPU 1: <tt>rcu_read_lock()</tt>
+<li>	CPU 1: <tt>q = rcu_dereference(gp);
+	/* Might return p if no memory barrier. */</tt>
+<li>	CPU 0: <tt>synchronize_rcu()</tt> returns.
+<li>	CPU 0: <tt>kfree(p);</tt>
+<li>	CPU 1: <tt>do_something_with(q-&gt;a); /* Boom!!! */</tt>
+<li>	CPU 1: <tt>rcu_read_unlock()</tt>
+</ol>
+
+<p>
+And similarly, without a memory barrier between the beginning of the
+grace period and the beginning of the RCU read-side critical section,
+CPU&nbsp;1 might end up accessing the freelist.
+
+<p>
+The &ldquo;as if&rdquo; rule of course applies, so that any implementation
+that acts as if the appropriate memory barriers were in place is a
+correct implementation.
+That said, it is much easier to fool yourself into believing that you have
+adhered to the as-if rule than it is to actually adhere to it!
+<p>@@QQE@@
+
+<p>
+Note that these memory-barrier requirements do not replace the fundamental
+RCU requirement that a grace period wait for all pre-existing readers.
+On the contrary, the memory barriers called out in this section must operate in
+such a way as to <i>enforce</i> this fundamental requirement.
+Of course, different implementations enforce this requirement in different
+ways, but enforce it they must.
+
+<h3><a name="RCU Primitives Guaranteed to Execute Unconditionally">RCU Primitives Guaranteed to Execute Unconditionally</a></h3>
+
+<p>
+The common-case RCU primitives are unconditional.
+They are invoked, they do their job, and they return, with no possibility
+of error, and no need to retry.
+This is a key RCU design philosophy.
+
+<p>
+However, this philosophy is pragmatic rather than pigheaded.
+If someone comes up with a good justification for a particular conditional
+RCU primitive, it might well be implemented and added.
+After all, this guarantee was reverse-engineered, not premeditated.
+The unconditional nature of the RCU primitives was initially an
+accident of implementation, and later experience with synchronization
+primitives with conditional primitives caused me to elevate this
+accident to a guarantee.
+Therefore, the justification for adding a conditional primitive to
+RCU would need to be based on detailed and compelling use cases.
+
+<h3><a name="Guaranteed Read-to-Write Upgrade">Guaranteed Read-to-Write Upgrade</a></h3>
+
+<p>
+As far as RCU is concerned, it is always possible to carry out an
+update within an RCU read-side critical section.
+For example, that RCU read-side critical section might search for
+a given data element, and then might acquire the update-side
+spinlock in order to update that element, all while remaining
+in that RCU read-side critical section.
+Of course, it is necessary to exit the RCU read-side critical section
+before invoking <tt>synchronize_rcu()</tt>, however, this
+inconvenience can be avoided through use of the
+<tt>call_rcu()</tt> and <tt>kfree_rcu()</tt> API members
+described later in this document.
+
+<p>@@QQ@@
+But how does the upgrade-to-write operation exclude other readers?
+<p>@@QQA@@
+It doesn't, just like normal RCU updates, which also do not exclude
+RCU readers.
+<p>@@QQE@@
+
+<p>
+This guarantee allows lookup code to be shared between read-side
+and update-side code, and was premeditated, appearing in the earliest
+DYNIX/ptx RCU documentation.
+
+<h2><a name="Fundamental Non-Requirements">Fundamental Non-Requirements</a></h2>
+
+<p>
+RCU provides extremely lightweight readers, and its read-side guarantees,
+though quite useful, are correspondingly lightweight.
+It is therefore all too easy to assume that RCU is guaranteeing more
+than it really is.
+Of course, the list of things that RCU does not guarantee is infinitely
+long, however, the following sections list a few non-guarantees that
+have caused confusion.
+Except where otherwise noted, these non-guarantees were premeditated.
+
+<ol>
+<li>	<a href="#Readers Impose Minimal Ordering">
+	Readers Impose Minimal Ordering</a>
+<li>	<a href="#Readers Do Not Exclude Updaters">
+	Readers Do Not Exclude Updaters</a>
+<li>	<a href="#Updaters Only Wait For Old Readers">
+	Updaters Only Wait For Old Readers</a>
+<li>	<a href="#Grace Periods Don't Partition Read-Side Critical Sections">
+	Grace Periods Don't Partition Read-Side Critical Sections</a>
+<li>	<a href="#Read-Side Critical Sections Don't Partition Grace Periods">
+	Read-Side Critical Sections Don't Partition Grace Periods</a>
+<li>	<a href="#Disabling Preemption Does Not Block Grace Periods">
+	Disabling Preemption Does Not Block Grace Periods</a>
+</ol>
+
+<h3><a name="Readers Impose Minimal Ordering">Readers Impose Minimal Ordering</a></h3>
+
+<p>
+Reader-side markers such as <tt>rcu_read_lock()</tt> and
+<tt>rcu_read_unlock()</tt> provide absolutely no ordering guarantees
+except through their interaction with the grace-period APIs such as
+<tt>synchronize_rcu()</tt>.
+To see this, consider the following pair of threads:
+
+<blockquote>
+<pre>
+ 1 void thread0(void)
+ 2 {
+ 3   rcu_read_lock();
+ 4   WRITE_ONCE(x, 1);
+ 5   rcu_read_unlock();
+ 6   rcu_read_lock();
+ 7   WRITE_ONCE(y, 1);
+ 8   rcu_read_unlock();
+ 9 }
+10
+11 void thread1(void)
+12 {
+13   rcu_read_lock();
+14   r1 = READ_ONCE(y);
+15   rcu_read_unlock();
+16   rcu_read_lock();
+17   r2 = READ_ONCE(x);
+18   rcu_read_unlock();
+19 }
+</pre>
+</blockquote>
+
+<p>
+After <tt>thread0()</tt> and <tt>thread1()</tt> execute
+concurrently, it is quite possible to have
+
+<blockquote>
+<pre>
+(r1 == 1 &amp;&amp; r2 == 0)
+</pre>
+</blockquote>
+
+(that is, <tt>y</tt> appears to have been assigned before <tt>x</tt>),
+which would not be possible if <tt>rcu_read_lock()</tt> and
+<tt>rcu_read_unlock()</tt> had much in the way of ordering
+properties.
+But they do not, so the CPU is within its rights
+to do significant reordering.
+This is by design:  Any significant ordering constraints would slow down
+these fast-path APIs.
+
+<p>@@QQ@@
+Can't the compiler also reorder this code?
+<p>@@QQA@@
+No, the volatile casts in <tt>READ_ONCE()</tt> and
+<tt>WRITE_ONCE()</tt> prevent the compiler from reordering in
+this particular case.
+<p>@@QQE@@
+
+<h3><a name="Readers Do Not Exclude Updaters">Readers Do Not Exclude Updaters</a></h3>
+
+<p>
+Neither <tt>rcu_read_lock()</tt> nor <tt>rcu_read_unlock()</tt>
+exclude updates.
+All they do is to prevent grace periods from ending.
+The following example illustrates this:
+
+<blockquote>
+<pre>
+ 1 void thread0(void)
+ 2 {
+ 3   rcu_read_lock();
+ 4   r1 = READ_ONCE(y);
+ 5   if (r1) {
+ 6     do_something_with_nonzero_x();
+ 7     r2 = READ_ONCE(x);
+ 8     WARN_ON(!r2); /* BUG!!! */
+ 9   }
+10   rcu_read_unlock();
+11 }
+12
+13 void thread1(void)
+14 {
+15   spin_lock(&amp;my_lock);
+16   WRITE_ONCE(x, 1);
+17   WRITE_ONCE(y, 1);
+18   spin_unlock(&amp;my_lock);
+19 }
+</pre>
+</blockquote>
+
+<p>
+If the <tt>thread0()</tt> function's <tt>rcu_read_lock()</tt>
+excluded the <tt>thread1()</tt> function's update,
+the <tt>WARN_ON()</tt> could never fire.
+But the fact is that <tt>rcu_read_lock()</tt> does not exclude
+much of anything aside from subsequent grace periods, of which
+<tt>thread1()</tt> has none, so the
+<tt>WARN_ON()</tt> can and does fire.
+
+<h3><a name="Updaters Only Wait For Old Readers">Updaters Only Wait For Old Readers</a></h3>
+
+<p>
+It might be tempting to assume that after <tt>synchronize_rcu()</tt>
+completes, there are no readers executing.
+This temptation must be avoided because
+new readers can start immediately after <tt>synchronize_rcu()</tt>
+starts, and <tt>synchronize_rcu()</tt> is under no
+obligation to wait for these new readers.
+
+<p>@@QQ@@
+Suppose that synchronize_rcu() did wait until all readers had completed.
+Would the updater be able to rely on this?
+<p>@@QQA@@
+No.
+Even if <tt>synchronize_rcu()</tt> were to wait until
+all readers had completed, a new reader might start immediately after
+<tt>synchronize_rcu()</tt> completed.
+Therefore, the code following
+<tt>synchronize_rcu()</tt> cannot rely on there being no readers
+in any case.
+<p>@@QQE@@
+
+<h3><a name="Grace Periods Don't Partition Read-Side Critical Sections">
+Grace Periods Don't Partition Read-Side Critical Sections</a></h3>
+
+<p>
+It is tempting to assume that if any part of one RCU read-side critical
+section precedes a given grace period, and if any part of another RCU
+read-side critical section follows that same grace period, then all of
+the first RCU read-side critical section must precede all of the second.
+However, this just isn't the case: A single grace period does not
+partition the set of RCU read-side critical sections.
+An example of this situation can be illustrated as follows, where
+<tt>x</tt>, <tt>y</tt>, and <tt>z</tt> are initially all zero:
+
+<blockquote>
+<pre>
+ 1 void thread0(void)
+ 2 {
+ 3   rcu_read_lock();
+ 4   WRITE_ONCE(a, 1);
+ 5   WRITE_ONCE(b, 1);
+ 6   rcu_read_unlock();
+ 7 }
+ 8
+ 9 void thread1(void)
+10 {
+11   r1 = READ_ONCE(a);
+12   synchronize_rcu();
+13   WRITE_ONCE(c, 1);
+14 }
+15
+16 void thread2(void)
+17 {
+18   rcu_read_lock();
+19   r2 = READ_ONCE(b);
+20   r3 = READ_ONCE(c);
+21   rcu_read_unlock();
+22 }
+</pre>
+</blockquote>
+
+<p>
+It turns out that the outcome:
+
+<blockquote>
+<pre>
+(r1 == 1 &amp;&amp; r2 == 0 &amp;&amp; r3 == 1)
+</pre>
+</blockquote>
+
+is entirely possible.
+The following figure show how this can happen, with each circled
+<tt>QS</tt> indicating the point at which RCU recorded a
+<i>quiescent state</i> for each thread, that is, a state in which
+RCU knows that the thread cannot be in the midst of an RCU read-side
+critical section that started before the current grace period:
+
+<p><img src="GPpartitionReaders1.svg" alt="GPpartitionReaders1.svg" width="60%"></p>
+
+<p>
+If it is necessary to partition RCU read-side critical sections in this
+manner, it is necessary to use two grace periods, where the first
+grace period is known to end before the second grace period starts:
+
+<blockquote>
+<pre>
+ 1 void thread0(void)
+ 2 {
+ 3   rcu_read_lock();
+ 4   WRITE_ONCE(a, 1);
+ 5   WRITE_ONCE(b, 1);
+ 6   rcu_read_unlock();
+ 7 }
+ 8
+ 9 void thread1(void)
+10 {
+11   r1 = READ_ONCE(a);
+12   synchronize_rcu();
+13   WRITE_ONCE(c, 1);
+14 }
+15
+16 void thread2(void)
+17 {
+18   r2 = READ_ONCE(c);
+19   synchronize_rcu();
+20   WRITE_ONCE(d, 1);
+21 }
+22
+23 void thread3(void)
+24 {
+25   rcu_read_lock();
+26   r3 = READ_ONCE(b);
+27   r4 = READ_ONCE(d);
+28   rcu_read_unlock();
+29 }
+</pre>
+</blockquote>
+
+<p>
+Here, if <tt>(r1 == 1)</tt>, then
+<tt>thread0()</tt>'s write to <tt>b</tt> must happen
+before the end of <tt>thread1()</tt>'s grace period.
+If in addition <tt>(r4 == 1)</tt>, then
+<tt>thread3()</tt>'s read from <tt>b</tt> must happen
+after the beginning of <tt>thread2()</tt>'s grace period.
+If it is also the case that <tt>(r2 == 1)</tt>, then the
+end of <tt>thread1()</tt>'s grace period must precede the
+beginning of <tt>thread2()</tt>'s grace period.
+This mean that the two RCU read-side critical sections cannot overlap,
+guaranteeing that <tt>(r3 == 1)</tt>.
+As a result, the outcome:
+
+<blockquote>
+<pre>
+(r1 == 1 &amp;&amp; r2 == 1 &amp;&amp; r3 == 0 &amp;&amp; r4 == 1)
+</pre>
+</blockquote>
+
+cannot happen.
+
+<p>
+This non-requirement was also non-premeditated, but became apparent
+when studying RCU's interaction with memory ordering.
+
+<h3><a name="Read-Side Critical Sections Don't Partition Grace Periods">
+Read-Side Critical Sections Don't Partition Grace Periods</a></h3>
+
+<p>
+It is also tempting to assume that if an RCU read-side critical section
+happens between a pair of grace periods, then those grace periods cannot
+overlap.
+However, this temptation leads nowhere good, as can be illustrated by
+the following, with all variables initially zero:
+
+<blockquote>
+<pre>
+ 1 void thread0(void)
+ 2 {
+ 3   rcu_read_lock();
+ 4   WRITE_ONCE(a, 1);
+ 5   WRITE_ONCE(b, 1);
+ 6   rcu_read_unlock();
+ 7 }
+ 8
+ 9 void thread1(void)
+10 {
+11   r1 = READ_ONCE(a);
+12   synchronize_rcu();
+13   WRITE_ONCE(c, 1);
+14 }
+15
+16 void thread2(void)
+17 {
+18   rcu_read_lock();
+19   WRITE_ONCE(d, 1);
+20   r2 = READ_ONCE(c);
+21   rcu_read_unlock();
+22 }
+23
+24 void thread3(void)
+25 {
+26   r3 = READ_ONCE(d);
+27   synchronize_rcu();
+28   WRITE_ONCE(e, 1);
+29 }
+30
+31 void thread4(void)
+32 {
+33   rcu_read_lock();
+34   r4 = READ_ONCE(b);
+35   r5 = READ_ONCE(e);
+36   rcu_read_unlock();
+37 }
+</pre>
+</blockquote>
+
+<p>
+In this case, the outcome:
+
+<blockquote>
+<pre>
+(r1 == 1 &amp;&amp; r2 == 1 &amp;&amp; r3 == 1 &amp;&amp; r4 == 0 &amp&amp; r5 == 1)
+</pre>
+</blockquote>
+
+is entirely possible, as illustrated below:
+
+<p><img src="ReadersPartitionGP1.svg" alt="ReadersPartitionGP1.svg" width="100%"></p>
+
+<p>
+Again, an RCU read-side critical section can overlap almost all of a
+given grace period, just so long as it does not overlap the entire
+grace period.
+As a result, an RCU read-side critical section cannot partition a pair
+of RCU grace periods.
+
+<p>@@QQ@@
+How long a sequence of grace periods, each separated by an RCU read-side
+critical section, would be required to partition the RCU read-side
+critical sections at the beginning and end of the chain?
+<p>@@QQA@@
+In theory, an infinite number.
+In practice, an unknown number that is sensitive to both implementation
+details and timing considerations.
+Therefore, even in practice, RCU users must abide by the theoretical rather
+than the practical answer.
+<p>@@QQE@@
+
+<h3><a name="Disabling Preemption Does Not Block Grace Periods">
+Disabling Preemption Does Not Block Grace Periods</a></h3>
+
+<p>
+There was a time when disabling preemption on any given CPU would block
+subsequent grace periods.
+However, this was an accident of implementation and is not a requirement.
+And in the current Linux-kernel implementation, disabling preemption
+on a given CPU in fact does not block grace periods, as Oleg Nesterov
+<a href="https://lkml.kernel.org/g/20150614193825.GA19582@redhat.com">demonstrated</a>.
+
+<p>
+If you need a preempt-disable region to block grace periods, you need to add
+<tt>rcu_read_lock()</tt> and <tt>rcu_read_unlock()</tt>, for example
+as follows:
+
+<blockquote>
+<pre>
+ 1 preempt_disable();
+ 2 rcu_read_lock();
+ 3 do_something();
+ 4 rcu_read_unlock();
+ 5 preempt_enable();
+ 6
+ 7 /* Spinlocks implicitly disable preemption. */
+ 8 spin_lock(&amp;mylock);
+ 9 rcu_read_lock();
+10 do_something();
+11 rcu_read_unlock();
+12 spin_unlock(&amp;mylock);
+</pre>
+</blockquote>
+
+<p>
+In theory, you could enter the RCU read-side critical section first,
+but it is more efficient to keep the entire RCU read-side critical
+section contained in the preempt-disable region as shown above.
+Of course, RCU read-side critical sections that extend outside of
+preempt-disable regions will work correctly, but such critical sections
+can be preempted, which forces <tt>rcu_read_unlock()</tt> to do
+more work.
+And no, this is <i>not</i> an invitation to enclose all of your RCU
+read-side critical sections within preempt-disable regions, because
+doing so would degrade real-time response.
+
+<p>
+This non-requirement appeared with preemptible RCU.
+If you need a grace period that waits on non-preemptible code regions, use
+<a href="#Sched Flavor">RCU-sched</a>.
+
+<h2><a name="Parallelism Facts of Life">Parallelism Facts of Life</a></h2>
+
+<p>
+These parallelism facts of life are by no means specific to RCU, but
+the RCU implementation must abide by them.
+They therefore bear repeating:
+
+<ol>
+<li>	Any CPU or task may be delayed at any time,
+	and any attempts to avoid these delays by disabling
+	preemption, interrupts, or whatever are completely futile.
+	This is most obvious in preemptible user-level
+	environments and in virtualized environments (where
+	a given guest OS's VCPUs can be preempted at any time by
+	the underlying hypervisor), but can also happen in bare-metal
+	environments due to ECC errors, NMIs, and other hardware
+	events.
+	Although a delay of more than about 20 seconds can result
+	in splats, the RCU implementation is obligated to use
+	algorithms that can tolerate extremely long delays, but where
+	&ldquo;extremely long&rdquo; is not long enough to allow
+	wrap-around when incrementing a 64-bit counter.
+<li>	Both the compiler and the CPU can reorder memory accesses.
+	Where it matters, RCU must use compiler directives and
+	memory-barrier instructions to preserve ordering.
+<li>	Conflicting writes to memory locations in any given cache line
+	will result in expensive cache misses.
+	Greater numbers of concurrent writes and more-frequent
+	concurrent writes will result in more dramatic slowdowns.
+	RCU is therefore obligated to use algorithms that have
+	sufficient locality to avoid significant performance and
+	scalability problems.
+<li>	As a rough rule of thumb, only one CPU's worth of processing
+	may be carried out under the protection of any given exclusive
+	lock.
+	RCU must therefore use scalable locking designs.
+<li>	Counters are finite, especially on 32-bit systems.
+	RCU's use of counters must therefore tolerate counter wrap,
+	or be designed such that counter wrap would take way more
+	time than a single system is likely to run.
+	An uptime of ten years is quite possible, a runtime
+	of a century much less so.
+	As an example of the latter, RCU's dyntick-idle nesting counter
+	allows 54 bits for interrupt nesting level (this counter
+	is 64 bits even on a 32-bit system).
+	Overflowing this counter requires 2<sup>54</sup>
+	half-interrupts on a given CPU without that CPU ever going idle.
+	If a half-interrupt happened every microsecond, it would take
+	570 years of runtime to overflow this counter, which is currently
+	believed to be an acceptably long time.
+<li>	Linux systems can have thousands of CPUs running a single
+	Linux kernel in a single shared-memory environment.
+	RCU must therefore pay close attention to high-end scalability.
+</ol>
+
+<p>
+This last parallelism fact of life means that RCU must pay special
+attention to the preceding facts of life.
+The idea that Linux might scale to systems with thousands of CPUs would
+have been met with some skepticism in the 1990s, but these requirements
+would have otherwise have been unsurprising, even in the early 1990s.
+
+<h2><a name="Quality-of-Implementation Requirements">Quality-of-Implementation Requirements</a></h2>
+
+<p>
+These sections list quality-of-implementation requirements.
+Although an RCU implementation that ignores these requirements could
+still be used, it would likely be subject to limitations that would
+make it inappropriate for industrial-strength production use.
+Classes of quality-of-implementation requirements are as follows:
+
+<ol>
+<li>	<a href="#Specialization">Specialization</a>
+<li>	<a href="#Performance and Scalability">Performance and Scalability</a>
+<li>	<a href="#Composability">Composability</a>
+<li>	<a href="#Corner Cases">Corner Cases</a>
+</ol>
+
+<p>
+These classes is covered in the following sections.
+
+<h3><a name="Specialization">Specialization</a></h3>
+
+<p>
+RCU is and always has been intended primarily for read-mostly situations, as
+illustrated by the following figure.
+This means that RCU's read-side primitives are optimized, often at the
+expense of its update-side primitives.
+
+<p><img src="RCUApplicability.svg" alt="RCUApplicability.svg" width="70%"></p>
+
+<p>
+This focus on read-mostly situations means that RCU must interoperate
+with other synchronization primitives.
+For example, the <tt>add_gp()</tt> and <tt>remove_gp_synchronous()</tt>
+examples discussed earlier use RCU to protect readers and locking to
+coordinate updaters.
+However, the need extends much farther, requiring that a variety of
+synchronization primitives be legal within RCU read-side critical sections,
+including spinlocks, sequence locks, atomic operations, reference
+counters, and memory barriers.
+
+<p>@@QQ@@
+What about sleeping locks?
+<p>@@QQA@@
+These are forbidden within Linux-kernel RCU read-side critical sections
+because it is not legal to place a quiescent state (in this case,
+voluntary context switch) within an RCU read-side critical section.
+However, sleeping locks may be used within userspace RCU read-side critical
+sections, and also within Linux-kernel sleepable RCU
+<a href="#Sleepable RCU">(SRCU)</a>
+read-side critical sections.
+In addition, the -rt patchset turns spinlocks into a sleeping locks so
+that the corresponding critical sections can be preempted, which
+also means that these sleeplockified spinlocks (but not other sleeping locks!)
+may be acquire within -rt-Linux-kernel RCU read-side critical sections.
+
+<p>
+Note that it <i>is</i> legal for a normal RCU read-side critical section
+to conditionally acquire a sleeping locks (as in <tt>mutex_trylock()</tt>),
+but only as long as it does not loop indefinitely attempting to
+conditionally acquire that sleeping locks.
+The key point is that things like <tt>mutex_trylock()</tt>
+either return with the mutex held, or return an error indication if
+the mutex was not immediately available.
+Either way, <tt>mutex_trylock()</tt> returns immediately without sleeping.
+<p>@@QQE@@
+
+<p>
+It often comes as a surprise that many algorithms do not require a
+consistent view of data, but many can function in that mode,
+with network routing being the poster child.
+Internet routing algorithms take significant time to propagate
+updates, so that by the time an update arrives at a given system,
+that system has been sending network traffic the wrong way for
+a considerable length of time.
+Having a few threads continue to send traffic the wrong way for a
+few more milliseconds is clearly not a problem:  In the worst case,
+TCP retransmissions will eventually get the data where it needs to go.
+In general, when tracking the state of the universe outside of the
+computer, some level of inconsistency must be tolerated due to
+speed-of-light delays if nothing else.
+
+<p>
+Furthermore, uncertainty about external state is inherent in many cases.
+For example, a pair of veternarians might use heartbeat to determine
+whether or not a given cat was alive.
+But how long should they wait after the last heartbeat to decide that
+the cat is in fact dead?
+Waiting less than 400 milliseconds makes no sense because this would
+mean that a relaxed cat would be considered to cycle between death
+and life more than 100 times per minute.
+Moreover, just as with human beings, a cat's heart might stop for
+some period of time, so the exact wait period is a judgment call.
+One of our pair of veternarians might wait 30 seconds before pronouncing
+the cat dead, while the other might insist on waiting a full minute.
+The two veternarians would then disagree on the state of the cat during
+the final 30 seconds of the minute following the last heartbeat, as
+fancifully illustrated below:
+
+<p><img src="2013-08-is-it-dead.png" alt="2013-08-is-it-dead.png" width="431"></p>
+
+<p>
+Interestingly enough, this same situation applies to hardware.
+When push comes to shove, how do we tell whether or not some
+external server has failed?
+We send messages to it periodically, and declare it failed if we
+don't receive a response within a given period of time.
+Policy decisions can usually tolerate short
+periods of inconsistency.
+The policy was decided some time ago, and is only now being put into
+effect, so a few milliseconds of delay is normally inconsequential.
+
+<p>
+However, there are algorithms that absolutely must see consistent data.
+For example, the translation between a user-level SystemV semaphore
+ID to the corresponding in-kernel data structure is protected by RCU,
+but it is absolutely forbidden to update a semaphore that has just been
+removed.
+In the Linux kernel, this need for consistency is accommodated by acquiring
+spinlocks located in the in-kernel data structure from within
+the RCU read-side critical section, and this is indicated by the
+green box in the figure above.
+Many other techniques may be used, and are in fact used within the
+Linux kernel.
+
+<p>
+In short, RCU is not required to maintain consistency, and other
+mechanisms may be used in concert with RCU when consistency is required.
+RCU's specialization allows it to do its job extremely well, and its
+ability to interoperate with other synchronization mechanisms allows
+the right mix of synchronization tools to be used for a given job.
+
+<h3><a name="Performance and Scalability">Performance and Scalability</a></h3>
+
+<p>
+Energy efficiency is a critical component of performance today,
+and Linux-kernel RCU implementations must therefore avoid unnecessarily
+awakening idle CPUs.
+I cannot claim that this requirement was premeditated.
+In fact, I learned of it during a telephone conversation in which I
+was given &ldquo;frank and open&rdquo; feedback on the importance
+of energy efficiency in battery-powered systems and on specific
+energy-efficiency shortcomings of the Linux-kernel RCU implementation.
+In my experience, the battery-powered embedded community will consider
+any unnecessary wakeups to be extremely unfriendly acts.
+So much so that mere Linux-kernel-mailing-list posts are
+insufficient to vent their ire.
+
+<p>
+Memory consumption is not particularly important for in most
+situations, and has become decreasingly
+so as memory sizes have expanded and memory
+costs have plummeted.
+However, as I learned from Matt Mackall's
+<a href="http://elinux.org/Linux_Tiny-FAQ">bloatwatch</a>
+efforts, memory footprint is critically important on single-CPU systems with
+non-preemptible (<tt>CONFIG_PREEMPT=n</tt>) kernels, and thus
+<a href="https://lkml.kernel.org/g/20090113221724.GA15307@linux.vnet.ibm.com">tiny RCU</a>
+was born.
+Josh Triplett has since taken over the small-memory banner with his
+<a href="https://tiny.wiki.kernel.org/">Linux kernel tinification</a>
+project, which resulted in
+<a href="#Sleepable RCU">SRCU</a>
+becoming optional for those kernels not needing it.
+
+<p>
+The remaining performance requirements are, for the most part,
+unsurprising.
+For example, in keeping with RCU's read-side specialization,
+<tt>rcu_dereference()</tt> should have negligible overhead (for
+example, suppression of a few minor compiler optimizations).
+Similarly, in non-preemptible environments, <tt>rcu_read_lock()</tt> and
+<tt>rcu_read_unlock()</tt> should have exactly zero overhead.
+
+<p>
+In preemptible environments, in the case where the RCU read-side
+critical section was not preempted (as will be the case for the
+highest-priority real-time process), <tt>rcu_read_lock()</tt> and
+<tt>rcu_read_unlock()</tt> should have minimal overhead.
+In particular, they should not contain atomic read-modify-write
+operations, memory-barrier instructions, preemption disabling,
+interrupt disabling, or backwards branches.
+However, in the case where the RCU read-side critical section was preempted,
+<tt>rcu_read_unlock()</tt> may acquire spinlocks and disable interrupts.
+This is why it is better to nest an RCU read-side critical section
+within a preempt-disable region than vice versa, at least in cases
+where that critical section is short enough to avoid unduly degrading
+real-time latencies.
+
+<p>
+The <tt>synchronize_rcu()</tt> grace-period-wait primitive is
+optimized for throughput.
+It may therefore incur several milliseconds of latency in addition to
+the duration of the longest RCU read-side critical section.
+On the other hand, multiple concurrent invocations of
+<tt>synchronize_rcu()</tt> are required to use batching optimizations
+so that they can be satisfied by a single underlying grace-period-wait
+operation.
+For example, in the Linux kernel, it is not unusual for a single
+grace-period-wait operation to serve more than
+<a href="https://www.usenix.org/conference/2004-usenix-annual-technical-conference/making-rcu-safe-deep-sub-millisecond-response">1,000 separate invocations</a>
+of <tt>synchronize_rcu()</tt>, thus amortizing the per-invocation
+overhead down to nearly zero.
+However, the grace-period optimization is also required to avoid
+measurable degradation of real-time scheduling and interrupt latencies.
+
+<p>
+In some cases, the multi-millisecond <tt>synchronize_rcu()</tt>
+latencies are unacceptable.
+In these cases, <tt>synchronize_rcu_expedited()</tt> may be used
+instead, reducing the grace-period latency down to a few tens of
+microseconds on small systems, at least in cases where the RCU read-side
+critical sections are short.
+There are currently no special latency requirements for
+<tt>synchronize_rcu_expedited()</tt> on large systems, but,
+consistent with the empirical nature of the RCU specification,
+that is subject to change.
+However, there most definitely are scalability requirements:
+A storm of <tt>synchronize_rcu_expedited()</tt> invocations on 4096
+CPUs should at least make reasonable forward progress.
+In return for its shorter latencies, <tt>synchronize_rcu_expedited()</tt>
+is permitted to impose modest degradation of real-time latency
+on non-idle online CPUs.
+That said, it will likely be necessary to take further steps to reduce this
+degradation, hopefully to roughly that of a scheduling-clock interrupt.
+
+<p>
+There are a number of situations where even
+<tt>synchronize_rcu_expedited()</tt>'s reduced grace-period
+latency is unacceptable.
+In these situations, the asynchronous <tt>call_rcu()</tt> can be
+used in place of <tt>synchronize_rcu()</tt> as follows:
+
+<blockquote>
+<pre>
+ 1 struct foo {
+ 2   int a;
+ 3   int b;
+ 4   struct rcu_head rh;
+ 5 };
+ 6
+ 7 static void remove_gp_cb(struct rcu_head *rhp)
+ 8 {
+ 9   struct foo *p = container_of(rhp, struct foo, rh);
+10
+11   kfree(p);
+12 }
+13
+14 bool remove_gp_asynchronous(void)
+15 {
+16   struct foo *p;
+17
+18   spin_lock(&amp;gp_lock);
+19   p = rcu_dereference(gp);
+20   if (!p) {
+21     spin_unlock(&amp;gp_lock);
+22     return false;
+23   }
+24   rcu_assign_pointer(gp, NULL);
+25   call_rcu(&amp;p-&gt;rh, remove_gp_cb);
+26   spin_unlock(&amp;gp_lock);
+27   return true;
+28 }
+</pre>
+</blockquote>
+
+<p>
+A definition of <tt>struct foo</tt> is finally needed, and appears
+on lines&nbsp;1-5.
+The function <tt>remove_gp_cb()</tt> is passed to <tt>call_rcu()</tt>
+on line&nbsp;25, and will be invoked after the end of a subsequent
+grace period.
+This gets the same effect as <tt>remove_gp_synchronous()</tt>,
+but without forcing the updater to wait for a grace period to elapse.
+The <tt>call_rcu()</tt> function may be used in a number of
+situations where neither <tt>synchronize_rcu()</tt> nor
+<tt>synchronize_rcu_expedited()</tt> would be legal,
+including within preempt-disable code, <tt>local_bh_disable()</tt> code,
+interrupt-disable code, and interrupt handlers.
+However, even <tt>call_rcu()</tt> is illegal within NMI handlers.
+The callback function (<tt>remove_gp_cb()</tt> in this case) will be
+executed within softirq (software interrupt) environment within the
+Linux kernel,
+either within a real softirq handler or under the protection
+of <tt>local_bh_disable()</tt>.
+In both the Linux kernel and in userspace, it is bad practice to
+write an RCU callback function that takes too long.
+Long-running operations should be relegated to separate threads or
+(in the Linux kernel) workqueues.
+
+<p>@@QQ@@
+Why does line&nbsp;19 use <tt>rcu_access_pointer()</tt>?
+After all, <tt>call_rcu()</tt> on line&nbsp;25 stores into the
+structure, which would interact badly with concurrent insertions.
+Doesn't this mean that <tt>rcu_dereference()</tt> is required?
+<p>@@QQA@@
+Presumably the <tt>-&gt;gp_lock</tt> acquired on line&nbsp;18 excludes
+any changes, including any insertions that <tt>rcu_dereference()</tt>
+would protect against.
+Therefore, any insertions will be delayed until after <tt>-&gt;gp_lock</tt>
+is released on line&nbsp;25, which in turn means that
+<tt>rcu_access_pointer()</tt> suffices.
+<p>@@QQE@@
+
+<p>
+However, all that <tt>remove_gp_cb()</tt> is doing is
+invoking <tt>kfree()</tt> on the data element.
+This is a common idiom, and is supported by <tt>kfree_rcu()</tt>,
+which allows &ldquo;fire and forget&rdquo; operation as shown below:
+
+<blockquote>
+<pre>
+ 1 struct foo {
+ 2   int a;
+ 3   int b;
+ 4   struct rcu_head rh;
+ 5 };
+ 6
+ 7 bool remove_gp_faf(void)
+ 8 {
+ 9   struct foo *p;
+10
+11   spin_lock(&amp;gp_lock);
+12   p = rcu_dereference(gp);
+13   if (!p) {
+14     spin_unlock(&amp;gp_lock);
+15     return false;
+16   }
+17   rcu_assign_pointer(gp, NULL);
+18   kfree_rcu(p, rh);
+19   spin_unlock(&amp;gp_lock);
+20   return true;
+21 }
+</pre>
+</blockquote>
+
+<p>
+Note that <tt>remove_gp_faf()</tt> simply invokes
+<tt>kfree_rcu()</tt> and proceeds, without any need to pay any
+further attention to the subsequent grace period and <tt>kfree()</tt>.
+It is permissible to invoke <tt>kfree_rcu()</tt> from the same
+environments as for <tt>call_rcu()</tt>.
+Interestingly enough, DYNIX/ptx had the equivalents of
+<tt>call_rcu()</tt> and <tt>kfree_rcu()</tt>, but not
+<tt>synchronize_rcu()</tt>.
+This was due to the fact that RCU was not heavily used within DYNIX/ptx,
+so the very few places that needed something like
+<tt>synchronize_rcu()</tt> simply open-coded it.
+
+<p>@@QQ@@
+Earlier it was claimed that <tt>call_rcu()</tt> and
+<tt>kfree_rcu()</tt> allowed updaters to avoid being blocked
+by readers.
+But how can that be correct, given that the invocation of the callback
+and the freeing of the memory (respectively) must still wait for
+a grace period to elapse?
+<p>@@QQA@@
+We could define things this way, but keep in mind that this sort of
+definition would say that updates in garbage-collected languages
+cannot complete until the next time the garbage collector runs,
+which does not seem at all reasonable.
+The key point is that in most cases, an updater using either
+<tt>call_rcu()</tt> or <tt>kfree_rcu()</tt> can proceed to the
+next update as soon as it has invoked <tt>call_rcu()</tt> or
+<tt>kfree_rcu()</tt>, without having to wait for a subsequent
+grace period.
+<p>@@QQE@@
+
+<p>
+But what if the updater must wait for the completion of code to be
+executed after the end of the grace period, but has other tasks
+that can be carried out in the meantime?
+The polling-style <tt>get_state_synchronize_rcu()</tt> and
+<tt>cond_synchronize_rcu()</tt> functions may be used for this
+purpose, as shown below:
+
+<blockquote>
+<pre>
+ 1 bool remove_gp_poll(void)
+ 2 {
+ 3   struct foo *p;
+ 4   unsigned long s;
+ 5
+ 6   spin_lock(&amp;gp_lock);
+ 7   p = rcu_access_pointer(gp);
+ 8   if (!p) {
+ 9     spin_unlock(&amp;gp_lock);
+10     return false;
+11   }
+12   rcu_assign_pointer(gp, NULL);
+13   spin_unlock(&amp;gp_lock);
+14   s = get_state_synchronize_rcu();
+15   do_something_while_waiting();
+16   cond_synchronize_rcu(s);
+17   kfree(p);
+18   return true;
+19 }
+</pre>
+</blockquote>
+
+<p>
+On line&nbsp;14, <tt>get_state_synchronize_rcu()</tt> obtains a
+&ldquo;cookie&rdquo; from RCU,
+then line&nbsp;15 carries out other tasks,
+and finally, line&nbsp;16 returns immediately if a grace period has
+elapsed in the meantime, but otherwise waits as required.
+The need for <tt>get_state_synchronize_rcu</tt> and
+<tt>cond_synchronize_rcu()</tt> has appeared quite recently,
+so it is too early to tell whether they will stand the test of time.
+
+<p>
+RCU thus provides a range of tools to allow updaters to strike the
+required tradeoff between latency, flexibility and CPU overhead.
+
+<h3><a name="Composability">Composability</a></h3>
+
+<p>
+Composability has received much attention in recent years, perhaps in part
+due to the collision of multicore hardware with object-oriented techniques
+designed in single-threaded environments for single-threaded use.
+And in theory, RCU read-side critical sections may be composed, and in
+fact may be nested arbitrarily deeply.
+In practice, as with all real-world implementations of composable
+constructs, there are limitations.
+
+<p>
+Implementations of RCU for which <tt>rcu_read_lock()</tt>
+and <tt>rcu_read_unlock()</tt> generate no code, such as
+Linux-kernel RCU when <tt>CONFIG_PREEMPT=n</tt>, can be
+nested arbitrarily deeply.
+After all, there is no overhead.
+Except that if all these instances of <tt>rcu_read_lock()</tt>
+and <tt>rcu_read_unlock()</tt> are visible to the compiler,
+compilation will eventually fail due to exhausting memory,
+mass storage, or user patience, whichever comes first.
+If the nesting is not visible to the compiler, as is the case with
+mutually recursive functions each in its own translation unit,
+stack overflow will result.
+If the nesting takes the form of loops, either the control variable
+will overflow or (in the Linux kernel) you will get an RCU CPU stall warning.
+Nevertheless, this class of RCU implementations is one
+of the most composable constructs in existence.
+
+<p>
+RCU implementations that explicitly track nesting depth
+are limited by the nesting-depth counter.
+For example, the Linux kernel's preemptible RCU limits nesting to
+<tt>INT_MAX</tt>.
+This should suffice for almost all practical purposes.
+That said, a consecutive pair of RCU read-side critical sections
+between which there is an operation that waits for a grace period
+cannot be enclosed in another RCU read-side critical section.
+This is because it is not legal to wait for a grace period within
+an RCU read-side critical section:  To do so would result either
+in deadlock or
+in RCU implicitly splitting the enclosing RCU read-side critical
+section, neither of which is conducive to a long-lived and prosperous
+kernel.
+
+<p>
+It is worth noting that RCU is not alone in limiting composability.
+For example, many transactional-memory implementations prohibit
+composing a pair of transactions separated by an irrevocable
+operation (for example, a network receive operation).
+For another example, lock-based critical sections can be composed
+surprisingly freely, but only if deadlock is avoided.
+
+<p>
+In short, although RCU read-side critical sections are highly composable,
+care is required in some situations, just as is the case for any other
+composable synchronization mechanism.
+
+<h3><a name="Corner Cases">Corner Cases</a></h3>
+
+<p>
+A given RCU workload might have an endless and intense stream of
+RCU read-side critical sections, perhaps even so intense that there
+was never a point in time during which there was not at least one
+RCU read-side critical section in flight.
+RCU cannot allow this situation to block grace periods:  As long as
+all the RCU read-side critical sections are finite, grace periods
+must also be finite.
+
+<p>
+That said, preemptible RCU implementations could potentially result
+in RCU read-side critical sections being preempted for long durations,
+which has the effect of creating a long-duration RCU read-side
+critical section.
+This situation can arise only in heavily loaded systems, but systems using
+real-time priorities are of course more vulnerable.
+Therefore, RCU priority boosting is provided to help deal with this
+case.
+That said, the exact requirements on RCU priority boosting will likely
+evolve as more experience accumulates.
+
+<p>
+Other workloads might have very high update rates.
+Although one can argue that such workloads should instead use
+something other than RCU, the fact remains that RCU must
+handle such workloads gracefully.
+This requirement is another factor driving batching of grace periods,
+but it is also the driving force behind the checks for large numbers
+of queued RCU callbacks in the <tt>call_rcu()</tt> code path.
+Finally, high update rates should not delay RCU read-side critical
+sections, although some read-side delays can occur when using
+<tt>synchronize_rcu_expedited()</tt>, courtesy of this function's use
+of <tt>try_stop_cpus()</tt>.
+(In the future, <tt>synchronize_rcu_expedited()</tt> will be
+converted to use lighter-weight inter-processor interrupts (IPIs),
+but this will still disturb readers, though to a much smaller degree.)
+
+<p>
+Although all three of these corner cases were understood in the early
+1990s, a simple user-level test consisting of <tt>close(open(path))</tt>
+in a tight loop
+in the early 2000s suddenly provided a much deeper appreciation of the
+high-update-rate corner case.
+This test also motivated addition of some RCU code to react to high update
+rates, for example, if a given CPU finds itself with more than 10,000
+RCU callbacks queued, it will cause RCU to take evasive action by
+more aggressively starting grace periods and more aggressively forcing
+completion of grace-period processing.
+This evasive action causes the grace period to complete more quickly,
+but at the cost of restricting RCU's batching optimizations, thus
+increasing the CPU overhead incurred by that grace period.
+
+<h2><a name="Software-Engineering Requirements">
+Software-Engineering Requirements</a></h2>
+
+<p>
+Between Murphy's Law and &ldquo;To err is human&rdquo;, it is necessary to
+guard against mishaps and misuse:
+
+<ol>
+<li>	It is all too easy to forget to use <tt>rcu_read_lock()</tt>
+	everywhere that it is needed, so kernels built with
+	<tt>CONFIG_PROVE_RCU=y</tt> will spat if
+	<tt>rcu_dereference()</tt> is used outside of an
+	RCU read-side critical section.
+	Update-side code can use <tt>rcu_dereference_protected()</tt>,
+	which takes a
+	<a href="https://lwn.net/Articles/371986/">lockdep expression</a>
+	to indicate what is providing the protection.
+	If the indicated protection is not provided, a lockdep splat
+	is emitted.
+
+	<p>
+	Code shared between readers and updaters can use
+	<tt>rcu_dereference_check()</tt>, which also takes a
+	lockdep expression, and emits a lockdep splat if neither
+	<tt>rcu_read_lock()</tt> nor the indicated protection
+	is in place.
+	In addition, <tt>rcu_dereference_raw()</tt> is used in those
+	(hopefully rare) cases where the required protection cannot
+	be easily described.
+	Finally, <tt>rcu_read_lock_held()</tt> is provided to
+	allow a function to verify that it has been invoked within
+	an RCU read-side critical section.
+	I was made aware of this set of requirements shortly after Thomas
+	Gleixner audited a number of RCU uses.
+<li>	A given function might wish to check for RCU-related preconditions
+	upon entry, before using any other RCU API.
+	The <tt>rcu_lockdep_assert()</tt> does this job,
+	asserting the expression in kernels having lockdep enabled
+	and doing nothing otherwise.
+<li>	It is also easy to forget to use <tt>rcu_assign_pointer()</tt>
+	and <tt>rcu_dereference()</tt>, perhaps (incorrectly)
+	substituting a simple assignment.
+	To catch this sort of error, a given RCU-protected pointer may be
+	tagged with <tt>__rcu</tt>, after which running sparse
+	with <tt>CONFIG_SPARSE_RCU_POINTER=y</tt> will complain
+	about simple-assignment accesses to that pointer.
+	Arnd Bergmann made me aware of this requirement, and also
+	supplied the needed
+	<a href="https://lwn.net/Articles/376011/">patch series</a>.
+<li>	Kernels built with <tt>CONFIG_DEBUG_OBJECTS_RCU_HEAD=y</tt>
+	will splat if a data element is passed to <tt>call_rcu()</tt>
+	twice in a row, without a grace period in between.
+	(This error is similar to a double free.)
+	The corresponding <tt>rcu_head</tt> structures that are
+	dynamically allocated are automatically tracked, but
+	<tt>rcu_head</tt> structures allocated on the stack
+	must be initialized with <tt>init_rcu_head_on_stack()</tt>
+	and cleaned up with <tt>destroy_rcu_head_on_stack()</tt>.
+	Similarly, statically allocated non-stack <tt>rcu_head</tt>
+	structures must be initialized with <tt>init_rcu_head()</tt>
+	and cleaned up with <tt>destroy_rcu_head()</tt>.
+	Mathieu Desnoyers made me aware of this requirement, and also
+	supplied the needed
+	<a href="https://lkml.kernel.org/g/20100319013024.GA28456@Krystal">patch</a>.
+<li>	An infinite loop in an RCU read-side critical section will
+	eventually trigger an RCU CPU stall warning splat, with
+	the duration of &ldquo;eventually&rdquo; being controlled by the
+	<tt>RCU_CPU_STALL_TIMEOUT</tt> <tt>Kconfig</tt> option, or,
+	alternatively, by the
+	<tt>rcupdate.rcu_cpu_stall_timeout</tt> boot/sysfs
+	parameter.
+	However, RCU is not obligated to produce this splat
+	unless there is a grace period waiting on that particular
+	RCU read-side critical section.
+	<p>
+	Some extreme workloads might intentionally delay
+	RCU grace periods, and systems running those workloads can
+	be booted with <tt>rcupdate.rcu_cpu_stall_suppress</tt>
+	to suppress the splats.
+	This kernel parameter may also be set via <tt>sysfs</tt>.
+	Furthermore, RCU CPU stall warnings are counter-productive
+	during sysrq dumps and during panics.
+	RCU therefore supplies the <tt>rcu_sysrq_start()</tt> and
+	<tt>rcu_sysrq_end()</tt> API members to be called before
+	and after long sysrq dumps.
+	RCU also supplies the <tt>rcu_panic()</tt> notifier that is
+	automatically invoked at the beginning of a panic to suppress
+	further RCU CPU stall warnings.
+
+	<p>
+	This requirement made itself known in the early 1990s, pretty
+	much the first time that it was necessary to debug a CPU stall.
+	That said, the initial implementation in DYNIX/ptx was quite
+	generic in comparison with that of Linux.
+<li>	Although it would be very good to detect pointers leaking out
+	of RCU read-side critical sections, there is currently no
+	good way of doing this.
+	One complication is the need to distinguish between pointers
+	leaking and pointers that have been handed off from RCU to
+	some other synchronization mechanism, for example, reference
+	counting.
+<li>	In kernels built with <tt>CONFIG_RCU_TRACE=y</tt>, RCU-related
+	information is provided via both debugfs and event tracing.
+<li>	Open-coded use of <tt>rcu_assign_pointer()</tt> and
+	<tt>rcu_dereference()</tt> to create typical linked
+	data structures can be surprisingly error-prone.
+	Therefore, RCU-protected
+	<a href="https://lwn.net/Articles/609973/#RCU List APIs">linked lists</a>
+	and, more recently, RCU-protected
+	<a href="https://lwn.net/Articles/612100/">hash tables</a>
+	are available.
+	Many other special-purpose RCU-protected data structures are
+	available in the Linux kernel and the userspace RCU library.
+<li>	Some linked structures are created at compile time, but still
+	require <tt>__rcu</tt> checking.
+	The <tt>RCU_POINTER_INITIALIZER()</tt> macro serves this
+	purpose.
+<li>	It is not necessary to use <tt>rcu_assign_pointer()</tt>
+	when creating linked structures that are to be published via
+	a single external pointer.
+	The <tt>RCU_INIT_POINTER()</tt> macro is provided for
+	this task and also for assigning <tt>NULL</tt> pointers
+	at runtime.
+</ol>
+
+<p>
+This not a hard-and-fast list:  RCU's diagnostic capabilities will
+continue to be guided by the number and type of usage bugs found
+in real-world RCU usage.
+
+<h2><a name="Linux Kernel Complications">Linux Kernel Complications</a></h2>
+
+<p>
+The Linux kernel provides an interesting environment for all kinds of
+software, including RCU.
+Some of the relevant points of interest are as follows:
+
+<ol>
+<li>	<a href="#Configuration">Configuration</a>.
+<li>	<a href="#Firmware Interface">Firmware Interface</a>.
+<li>	<a href="#Early Boot">Early Boot</a>.
+<li>	<a href="#Interrupts and NMIs">
+	Interrupts and non-maskable interrupts (NMIs)</a>.
+<li>	<a href="#Loadable Modules">Loadable Modules</a>.
+<li>	<a href="#Hotplug CPU">Hotplug CPU</a>.
+<li>	<a href="#Scheduler and RCU">Scheduler and RCU</a>.
+<li>	<a href="#Tracing and RCU">Tracing and RCU</a>.
+<li>	<a href="#Energy Efficiency">Energy Efficiency</a>.
+<li>	<a href="#Memory Efficiency">Memory Efficiency</a>.
+<li>	<a href="#Performance, Scalability, Response Time, and Reliability">
+	Performance, Scalability, Response Time, and Reliability</a>.
+</ol>
+
+<p>
+This list is probably incomplete, but it does give a feel for the
+most notable Linux-kernel complications.
+Each of the following sections covers one of the above topics.
+
+<h3><a name="Configuration">Configuration</a></h3>
+
+<p>
+RCU's goal is automatic configuration, so that almost nobody
+needs to worry about RCU's <tt>Kconfig</tt> options.
+And for almost all users, RCU does in fact work well
+&ldquo;out of the box.&rdquo;
+
+<p>
+However, there are specialized use cases that are handled by
+kernel boot parameters and <tt>Kconfig</tt> options.
+Unfortunately, the <tt>Kconfig</tt> system will explicitly ask users
+about new <tt>Kconfig</tt> options, which requires almost all of them
+be hidden behind a <tt>CONFIG_RCU_EXPERT</tt> <tt>Kconfig</tt> option.
+
+<p>
+This all should be quite obvious, but the fact remains that
+Linus Torvalds recently had to
+<a href="https://lkml.kernel.org/g/CA+55aFy4wcCwaL4okTs8wXhGZ5h-ibecy_Meg9C4MNQrUnwMcg@mail.gmail.com">remind</a>
+me of this requirement.
+
+<h3><a name="Firmware Interface">Firmware Interface</a></h3>
+
+<p>
+In many cases, kernel obtains information about the system from the
+firmware, and sometimes things are lost in translation.
+Or the translation is accurate, but the original message is bogus.
+
+<p>
+For example, some systems' firmware overreports the number of CPUs,
+sometimes by a large factor.
+If RCU naively believed the firmware, as it used to do,
+it would create too many per-CPU kthreads.
+Although the resulting system will still run correctly, the extra
+kthreads needlessly consume memory and can cause confusion
+when they show up in <tt>ps</tt> listings.
+
+<p>
+RCU must therefore wait for a given CPU to actually come online before
+it can allow itself to believe that the CPU actually exists.
+The resulting &ldquo;ghost CPUs&rdquo; (which are never going to
+come online) cause a number of
+<a href="https://paulmck.livejournal.com/37494.html">interesting complications</a>.
+
+<h3><a name="Early Boot">Early Boot</a></h3>
+
+<p>
+The Linux kernel's boot sequence is an interesting process,
+and RCU is used early, even before <tt>rcu_init()</tt>
+is invoked.
+In fact, a number of RCU's primitives can be used as soon as the
+initial task's <tt>task_struct</tt> is available and the
+boot CPU's per-CPU variables are set up.
+The read-side primitives (<tt>rcu_read_lock()</tt>,
+<tt>rcu_read_unlock()</tt>, <tt>rcu_dereference()</tt>,
+and <tt>rcu_access_pointer()</tt>) will operate normally very early on,
+as will <tt>rcu_assign_pointer()</tt>.
+
+<p>
+Although <tt>call_rcu()</tt> may be invoked at any
+time during boot, callbacks are not guaranteed to be invoked until after
+the scheduler is fully up and running.
+This delay in callback invocation is due to the fact that RCU does not
+invoke callbacks until it is fully initialized, and this full initialization
+cannot occur until after the scheduler has initialized itself to the
+point where RCU can spawn and run its kthreads.
+In theory, it would be possible to invoke callbacks earlier,
+however, this is not a panacea because there would be severe restrictions
+on what operations those callbacks could invoke.
+
+<p>
+Perhaps surprisingly, <tt>synchronize_rcu()</tt>,
+<a href="#Bottom-Half Flavor"><tt>synchronize_rcu_bh()</tt></a>
+(<a href="#Bottom-Half Flavor">discussed below</a>),
+and
+<a href="#Sched Flavor"><tt>synchronize_sched()</tt></a>
+will all operate normally
+during very early boot, the reason being that there is only one CPU
+and preemption is disabled.
+This means that the call <tt>synchronize_rcu()</tt> (or friends)
+itself is a quiescent
+state and thus a grace period, so the early-boot implementation can
+be a no-op.
+
+<p>
+Both <tt>synchronize_rcu_bh()</tt> and <tt>synchronize_sched()</tt>
+continue to operate normally through the remainder of boot, courtesy
+of the fact that preemption is disabled across their RCU read-side
+critical sections and also courtesy of the fact that there is still
+only one CPU.
+However, once the scheduler starts initializing, preemption is enabled.
+There is still only a single CPU, but the fact that preemption is enabled
+means that the no-op implementation of <tt>synchronize_rcu()</tt> no
+longer works in <tt>CONFIG_PREEMPT=y</tt> kernels.
+Therefore, as soon as the scheduler starts initializing, the early-boot
+fastpath is disabled.
+This means that <tt>synchronize_rcu()</tt> switches to its runtime
+mode of operation where it posts callbacks, which in turn means that
+any call to <tt>synchronize_rcu()</tt> will block until the corresponding
+callback is invoked.
+Unfortunately, the callback cannot be invoked until RCU's runtime
+grace-period machinery is up and running, which cannot happen until
+the scheduler has initialized itself sufficiently to allow RCU's
+kthreads to be spawned.
+Therefore, invoking <tt>synchronize_rcu()</tt> during scheduler
+initialization can result in deadlock.
+
+<p>@@QQ@@
+So what happens with <tt>synchronize_rcu()</tt> during
+scheduler initialization for <tt>CONFIG_PREEMPT=n</tt>
+kernels?
+<p>@@QQA@@
+In <tt>CONFIG_PREEMPT=n</tt> kernel, <tt>synchronize_rcu()</tt>
+maps directly to <tt>synchronize_sched()</tt>.
+Therefore, <tt>synchronize_rcu()</tt> works normally throughout
+boot in <tt>CONFIG_PREEMPT=n</tt> kernels.
+However, your code must also work in <tt>CONFIG_PREEMPT=y</tt> kernels,
+so it is still necessary to avoid invoking <tt>synchronize_rcu()</tt>
+during scheduler initialization.
+<p>@@QQE@@
+
+<p>
+I learned of these boot-time requirements as a result of a series of
+system hangs.
+
+<h3><a name="Interrupts and NMIs">Interrupts and NMIs</a></h3>
+
+<p>
+The Linux kernel has interrupts, and RCU read-side critical sections are
+legal within interrupt handlers and within interrupt-disabled regions
+of code, as are invocations of <tt>call_rcu()</tt>.
+
+<p>
+Some Linux-kernel architectures can enter an interrupt handler from
+non-idle process context, and then just never leave it, instead stealthily
+transitioning back to process context.
+This trick is sometimes used to invoke system calls from inside the kernel.
+These &ldquo;half-interrupts&rdquo; mean that RCU has to be very careful
+about how it counts interrupt nesting levels.
+I learned of this requirement the hard way during a rewrite
+of RCU's dyntick-idle code.
+
+<p>
+The Linux kernel has non-maskable interrupts (NMIs), and
+RCU read-side critical sections are legal within NMI handlers.
+Thankfully, RCU update-side primitives, including
+<tt>call_rcu()</tt>, are prohibited within NMI handlers.
+
+<p>
+The name notwithstanding, some Linux-kernel architectures
+can have nested NMIs, which RCU must handle correctly.
+Andy Lutomirski
+<a href="https://lkml.kernel.org/g/CALCETrXLq1y7e_dKFPgou-FKHB6Pu-r8+t-6Ds+8=va7anBWDA@mail.gmail.com">surprised me</a>
+with this requirement;
+he also kindly surprised me with
+<a href="https://lkml.kernel.org/g/CALCETrXSY9JpW3uE6H8WYk81sg56qasA2aqmjMPsq5dOtzso=g@mail.gmail.com">an algorithm</a>
+that meets this requirement.
+
+<h3><a name="Loadable Modules">Loadable Modules</a></h3>
+
+<p>
+The Linux kernel has loadable modules, and these modules can
+also be unloaded.
+After a given module has been unloaded, any attempt to call
+one of its functions results in a segmentation fault.
+The module-unload functions must therefore cancel any
+delayed calls to loadable-module functions, for example,
+any outstanding <tt>mod_timer()</tt> must be dealt with
+via <tt>del_timer_sync()</tt> or similar.
+
+<p>
+Unfortunately, there is no way to cancel an RCU callback;
+once you invoke <tt>call_rcu()</tt>, the callback function is
+going to eventually be invoked, unless the system goes down first.
+Because it is normally considered socially irresponsible to crash the system
+in response to a module unload request, we need some other way
+to deal with in-flight RCU callbacks.
+
+<p>
+RCU therefore provides
+<tt><a href="https://lwn.net/Articles/217484/">rcu_barrier()</a></tt>,
+which waits until all in-flight RCU callbacks have been invoked.
+If a module uses <tt>call_rcu()</tt>, its exit function should therefore
+prevent any future invocation of <tt>call_rcu()</tt>, then invoke
+<tt>rcu_barrier()</tt>.
+In theory, the underlying module-unload code could invoke
+<tt>rcu_barrier()</tt> unconditionally, but in practice this would
+incur unacceptable latencies.
+
+<p>
+Nikita Danilov noted this requirement for an analogous filesystem-unmount
+situation, and Dipankar Sarma incorporated <tt>rcu_barrier()</tt> into RCU.
+The need for <tt>rcu_barrier()</tt> for module unloading became
+apparent later.
+
+<h3><a name="Hotplug CPU">Hotplug CPU</a></h3>
+
+<p>
+The Linux kernel supports CPU hotplug, which means that CPUs
+can come and go.
+It is of course illegal to use any RCU API member from an offline CPU.
+This requirement was present from day one in DYNIX/ptx, but
+on the other hand, the Linux kernel's CPU-hotplug implementation
+is &ldquo;interesting.&rdquo;
+
+<p>
+The Linux-kernel CPU-hotplug implementation has notifiers that
+are used to allow the various kernel subsystems (including RCU)
+to respond appropriately to a given CPU-hotplug operation.
+Most RCU operations may be invoked from CPU-hotplug notifiers,
+including even normal synchronous grace-period operations
+such as <tt>synchronize_rcu()</tt>.
+However, expedited grace-period operations such as
+<tt>synchronize_rcu_expedited()</tt> are not supported,
+due to the fact that current implementations block CPU-hotplug
+operations, which could result in deadlock.
+
+<p>
+In addition, all-callback-wait operations such as
+<tt>rcu_barrier()</tt> are also not supported, due to the
+fact that there are phases of CPU-hotplug operations where
+the outgoing CPU's callbacks will not be invoked until after
+the CPU-hotplug operation ends, which could also result in deadlock.
+
+<h3><a name="Scheduler and RCU">Scheduler and RCU</a></h3>
+
+<p>
+RCU depends on the scheduler, and the scheduler uses RCU to
+protect some of its data structures.
+This means the scheduler is forbidden from acquiring
+the runqueue locks and the priority-inheritance locks
+in the middle of an outermost RCU read-side critical section unless either
+(1)&nbsp;it releases them before exiting that same
+RCU read-side critical section, or
+(2)&nbsp;interrupts are disabled across
+that entire RCU read-side critical section.
+This same prohibition also applies (recursively!) to any lock that is acquired
+while holding any lock to which this prohibition applies.
+Adhering to this rule prevents preemptible RCU from invoking
+<tt>rcu_read_unlock_special()</tt> while either runqueue or
+priority-inheritance locks are held, thus avoiding deadlock.
+
+<p>
+Prior to v4.4, it was only necessary to disable preemption across
+RCU read-side critical sections that acquired scheduler locks.
+In v4.4, expedited grace periods started using IPIs, and these
+IPIs could force a <tt>rcu_read_unlock()</tt> to take the slowpath.
+Therefore, this expedited-grace-period change required disabling of
+interrupts, not just preemption.
+
+<p>
+For RCU's part, the preemptible-RCU <tt>rcu_read_unlock()</tt>
+implementation must be written carefully to avoid similar deadlocks.
+In particular, <tt>rcu_read_unlock()</tt> must tolerate an
+interrupt where the interrupt handler invokes both
+<tt>rcu_read_lock()</tt> and <tt>rcu_read_unlock()</tt>.
+This possibility requires <tt>rcu_read_unlock()</tt> to use
+negative nesting levels to avoid destructive recursion via
+interrupt handler's use of RCU.
+
+<p>
+This pair of mutual scheduler-RCU requirements came as a
+<a href="https://lwn.net/Articles/453002/">complete surprise</a>.
+
+<p>
+As noted above, RCU makes use of kthreads, and it is necessary to
+avoid excessive CPU-time accumulation by these kthreads.
+This requirement was no surprise, but RCU's violation of it
+when running context-switch-heavy workloads when built with
+<tt>CONFIG_NO_HZ_FULL=y</tt>
+<a href="http://www.rdrop.com/users/paulmck/scalability/paper/BareMetal.2015.01.15b.pdf">did come as a surprise [PDF]</a>.
+RCU has made good progress towards meeting this requirement, even
+for context-switch-have <tt>CONFIG_NO_HZ_FULL=y</tt> workloads,
+but there is room for further improvement.
+
+<h3><a name="Tracing and RCU">Tracing and RCU</a></h3>
+
+<p>
+It is possible to use tracing on RCU code, but tracing itself
+uses RCU.
+For this reason, <tt>rcu_dereference_raw_notrace()</tt>
+is provided for use by tracing, which avoids the destructive
+recursion that could otherwise ensue.
+This API is also used by virtualization in some architectures,
+where RCU readers execute in environments in which tracing
+cannot be used.
+The tracing folks both located the requirement and provided the
+needed fix, so this surprise requirement was relatively painless.
+
+<h3><a name="Energy Efficiency">Energy Efficiency</a></h3>
+
+<p>
+Interrupting idle CPUs is considered socially unacceptable,
+especially by people with battery-powered embedded systems.
+RCU therefore conserves energy by detecting which CPUs are
+idle, including tracking CPUs that have been interrupted from idle.
+This is a large part of the energy-efficiency requirement,
+so I learned of this via an irate phone call.
+
+<p>
+Because RCU avoids interrupting idle CPUs, it is illegal to
+execute an RCU read-side critical section on an idle CPU.
+(Kernels built with <tt>CONFIG_PROVE_RCU=y</tt> will splat
+if you try it.)
+The <tt>RCU_NONIDLE()</tt> macro and <tt>_rcuidle</tt>
+event tracing is provided to work around this restriction.
+In addition, <tt>rcu_is_watching()</tt> may be used to
+test whether or not it is currently legal to run RCU read-side
+critical sections on this CPU.
+I learned of the need for diagnostics on the one hand
+and <tt>RCU_NONIDLE()</tt> on the other while inspecting
+idle-loop code.
+Steven Rostedt supplied <tt>_rcuidle</tt> event tracing,
+which is used quite heavily in the idle loop.
+
+<p>
+It is similarly socially unacceptable to interrupt an
+<tt>nohz_full</tt> CPU running in userspace.
+RCU must therefore track <tt>nohz_full</tt> userspace
+execution.
+And in
+<a href="https://lwn.net/Articles/558284/"><tt>CONFIG_NO_HZ_FULL_SYSIDLE=y</tt></a>
+kernels, RCU must separately track idle CPUs on the one hand and
+CPUs that are either idle or executing in userspace on the other.
+In both cases, RCU must be able to sample state at two points in
+time, and be able to determine whether or not some other CPU spent
+any time idle and/or executing in userspace.
+
+<p>
+These energy-efficiency requirements have proven quite difficult to
+understand and to meet, for example, there have been more than five
+clean-sheet rewrites of RCU's energy-efficiency code, the last of
+which was finally able to demonstrate
+<a href="http://www.rdrop.com/users/paulmck/realtime/paper/AMPenergy.2013.04.19a.pdf">real energy savings running on real hardware [PDF]</a>.
+As noted earlier,
+I learned of many of these requirements via angry phone calls:
+Flaming me on the Linux-kernel mailing list was apparently not
+sufficient to fully vent their ire at RCU's energy-efficiency bugs!
+
+<h3><a name="Memory Efficiency">Memory Efficiency</a></h3>
+
+<p>
+Although small-memory non-realtime systems can simply use Tiny RCU,
+code size is only one aspect of memory efficiency.
+Another aspect is the size of the <tt>rcu_head</tt> structure
+used by <tt>call_rcu()</tt> and <tt>kfree_rcu()</tt>.
+Although this structure contains nothing more than a pair of pointers,
+it does appear in many RCU-protected data structures, including
+some that are size critical.
+The <tt>page</tt> structure is a case in point, as evidenced by
+the many occurrences of the <tt>union</tt> keyword within that structure.
+
+<p>
+This need for memory efficiency is one reason that RCU uses hand-crafted
+singly linked lists to track the <tt>rcu_head</tt> structures that
+are waiting for a grace period to elapse.
+It is also the reason why <tt>rcu_head</tt> structures do not contain
+debug information, such as fields tracking the file and line of the
+<tt>call_rcu()</tt> or <tt>kfree_rcu()</tt> that posted them.
+Although this information might appear in debug-only kernel builds at some
+point, in the meantime, the <tt>-&gt;func</tt> field will often provide
+the needed debug information.
+
+<p>
+However, in some cases, the need for memory efficiency leads to even
+more extreme measures.
+Returning to the <tt>page</tt> structure, the <tt>rcu_head</tt> field
+shares storage with a great many other structures that are used at
+various points in the corresponding page's lifetime.
+In order to correctly resolve certain
+<a href="https://lkml.kernel.org/g/1439976106-137226-1-git-send-email-kirill.shutemov@linux.intel.com">race conditions</a>,
+the Linux kernel's memory-management subsystem needs a particular bit
+to remain zero during all phases of grace-period processing,
+and that bit happens to map to the bottom bit of the
+<tt>rcu_head</tt> structure's <tt>-&gt;next</tt> field.
+RCU makes this guarantee as long as <tt>call_rcu()</tt>
+is used to post the callback, as opposed to <tt>kfree_rcu()</tt>
+or some future &ldquo;lazy&rdquo;
+variant of <tt>call_rcu()</tt> that might one day be created for
+energy-efficiency purposes.
+
+<h3><a name="Performance, Scalability, Response Time, and Reliability">
+Performance, Scalability, Response Time, and Reliability</a></h3>
+
+<p>
+Expanding on the
+<a href="#Performance and Scalability">earlier discussion</a>,
+RCU is used heavily by hot code paths in performance-critical
+portions of the Linux kernel's networking, security, virtualization,
+and scheduling code paths.
+RCU must therefore use efficient implementations, especially in its
+read-side primitives.
+To that end, it would be good if preemptible RCU's implementation
+of <tt>rcu_read_lock()</tt> could be inlined, however, doing
+this requires resolving <tt>#include</tt> issues with the
+<tt>task_struct</tt> structure.
+
+<p>
+The Linux kernel supports hardware configurations with up to
+4096 CPUs, which means that RCU must be extremely scalable.
+Algorithms that involve frequent acquisitions of global locks or
+frequent atomic operations on global variables simply cannot be
+tolerated within the RCU implementation.
+RCU therefore makes heavy use of a combining tree based on the
+<tt>rcu_node</tt> structure.
+RCU is required to tolerate all CPUs continuously invoking any
+combination of RCU's runtime primitives with minimal per-operation
+overhead.
+In fact, in many cases, increasing load must <i>decrease</i> the
+per-operation overhead, witness the batching optimizations for
+<tt>synchronize_rcu()</tt>, <tt>call_rcu()</tt>,
+<tt>synchronize_rcu_expedited()</tt>, and <tt>rcu_barrier()</tt>.
+As a general rule, RCU must cheerfully accept whatever the
+rest of the Linux kernel decides to throw at it.
+
+<p>
+The Linux kernel is used for real-time workloads, especially
+in conjunction with the
+<a href="https://rt.wiki.kernel.org/index.php/Main_Page">-rt patchset</a>.
+The real-time-latency response requirements are such that the
+traditional approach of disabling preemption across RCU
+read-side critical sections is inappropriate.
+Kernels built with <tt>CONFIG_PREEMPT=y</tt> therefore
+use an RCU implementation that allows RCU read-side critical
+sections to be preempted.
+This requirement made its presence known after users made it
+clear that an earlier
+<a href="https://lwn.net/Articles/107930/">real-time patch</a>
+did not meet their needs, in conjunction with some
+<a href="https://lkml.kernel.org/g/20050318002026.GA2693@us.ibm.com">RCU issues</a>
+encountered by a very early version of the -rt patchset.
+
+<p>
+In addition, RCU must make do with a sub-100-microsecond real-time latency
+budget.
+In fact, on smaller systems with the -rt patchset, the Linux kernel
+provides sub-20-microsecond real-time latencies for the whole kernel,
+including RCU.
+RCU's scalability and latency must therefore be sufficient for
+these sorts of configurations.
+To my surprise, the sub-100-microsecond real-time latency budget
+<a href="http://www.rdrop.com/users/paulmck/realtime/paper/bigrt.2013.01.31a.LCA.pdf">
+applies to even the largest systems [PDF]</a>,
+up to and including systems with 4096 CPUs.
+This real-time requirement motivated the grace-period kthread, which
+also simplified handling of a number of race conditions.
+
+<p>
+Finally, RCU's status as a synchronization primitive means that
+any RCU failure can result in arbitrary memory corruption that can be
+extremely difficult to debug.
+This means that RCU must be extremely reliable, which in
+practice also means that RCU must have an aggressive stress-test
+suite.
+This stress-test suite is called <tt>rcutorture</tt>.
+
+<p>
+Although the need for <tt>rcutorture</tt> was no surprise,
+the current immense popularity of the Linux kernel is posing
+interesting&mdash;and perhaps unprecedented&mdash;validation
+challenges.
+To see this, keep in mind that there are well over one billion
+instances of the Linux kernel running today, given Android
+smartphones, Linux-powered televisions, and servers.
+This number can be expected to increase sharply with the advent of
+the celebrated Internet of Things.
+
+<p>
+Suppose that RCU contains a race condition that manifests on average
+once per million years of runtime.
+This bug will be occurring about three times per <i>day</i> across
+the installed base.
+RCU could simply hide behind hardware error rates, given that no one
+should really expect their smartphone to last for a million years.
+However, anyone taking too much comfort from this thought should
+consider the fact that in most jurisdictions, a successful multi-year
+test of a given mechanism, which might include a Linux kernel,
+suffices for a number of types of safety-critical certifications.
+In fact, rumor has it that the Linux kernel is already being used
+in production for safety-critical applications.
+I don't know about you, but I would feel quite bad if a bug in RCU
+killed someone.
+Which might explain my recent focus on validation and verification.
+
+<h2><a name="Other RCU Flavors">Other RCU Flavors</a></h2>
+
+<p>
+One of the more surprising things about RCU is that there are now
+no fewer than five <i>flavors</i>, or API families.
+In addition, the primary flavor that has been the sole focus up to
+this point has two different implementations, non-preemptible and
+preemptible.
+The other four flavors are listed below, with requirements for each
+described in a separate section.
+
+<ol>
+<li>	<a href="#Bottom-Half Flavor">Bottom-Half Flavor</a>
+<li>	<a href="#Sched Flavor">Sched Flavor</a>
+<li>	<a href="#Sleepable RCU">Sleepable RCU</a>
+<li>	<a href="#Tasks RCU">Tasks RCU</a>
+</ol>
+
+<h3><a name="Bottom-Half Flavor">Bottom-Half Flavor</a></h3>
+
+<p>
+The softirq-disable (AKA &ldquo;bottom-half&rdquo;,
+hence the &ldquo;_bh&rdquo; abbreviations)
+flavor of RCU, or <i>RCU-bh</i>, was developed by
+Dipankar Sarma to provide a flavor of RCU that could withstand the
+network-based denial-of-service attacks researched by Robert
+Olsson.
+These attacks placed so much networking load on the system
+that some of the CPUs never exited softirq execution,
+which in turn prevented those CPUs from ever executing a context switch,
+which, in the RCU implementation of that time, prevented grace periods
+from ever ending.
+The result was an out-of-memory condition and a system hang.
+
+<p>
+The solution was the creation of RCU-bh, which does
+<tt>local_bh_disable()</tt>
+across its read-side critical sections, and which uses the transition
+from one type of softirq processing to another as a quiescent state
+in addition to context switch, idle, user mode, and offline.
+This means that RCU-bh grace periods can complete even when some of
+the CPUs execute in softirq indefinitely, thus allowing algorithms
+based on RCU-bh to withstand network-based denial-of-service attacks.
+
+<p>
+Because
+<tt>rcu_read_lock_bh()</tt> and <tt>rcu_read_unlock_bh()</tt>
+disable and re-enable softirq handlers, any attempt to start a softirq
+handlers during the
+RCU-bh read-side critical section will be deferred.
+In this case, <tt>rcu_read_unlock_bh()</tt>
+will invoke softirq processing, which can take considerable time.
+One can of course argue that this softirq overhead should be associated
+with the code following the RCU-bh read-side critical section rather
+than <tt>rcu_read_unlock_bh()</tt>, but the fact
+is that most profiling tools cannot be expected to make this sort
+of fine distinction.
+For example, suppose that a three-millisecond-long RCU-bh read-side
+critical section executes during a time of heavy networking load.
+There will very likely be an attempt to invoke at least one softirq
+handler during that three milliseconds, but any such invocation will
+be delayed until the time of the <tt>rcu_read_unlock_bh()</tt>.
+This can of course make it appear at first glance as if
+<tt>rcu_read_unlock_bh()</tt> was executing very slowly.
+
+<p>
+The
+<a href="https://lwn.net/Articles/609973/#RCU Per-Flavor API Table">RCU-bh API</a>
+includes
+<tt>rcu_read_lock_bh()</tt>,
+<tt>rcu_read_unlock_bh()</tt>,
+<tt>rcu_dereference_bh()</tt>,
+<tt>rcu_dereference_bh_check()</tt>,
+<tt>synchronize_rcu_bh()</tt>,
+<tt>synchronize_rcu_bh_expedited()</tt>,
+<tt>call_rcu_bh()</tt>,
+<tt>rcu_barrier_bh()</tt>, and
+<tt>rcu_read_lock_bh_held()</tt>.
+
+<h3><a name="Sched Flavor">Sched Flavor</a></h3>
+
+<p>
+Before preemptible RCU, waiting for an RCU grace period had the
+side effect of also waiting for all pre-existing interrupt
+and NMI handlers.
+However, there are legitimate preemptible-RCU implementations that
+do not have this property, given that any point in the code outside
+of an RCU read-side critical section can be a quiescent state.
+Therefore, <i>RCU-sched</i> was created, which follows &ldquo;classic&rdquo;
+RCU in that an RCU-sched grace period waits for for pre-existing
+interrupt and NMI handlers.
+In kernels built with <tt>CONFIG_PREEMPT=n</tt>, the RCU and RCU-sched
+APIs have identical implementations, while kernels built with
+<tt>CONFIG_PREEMPT=y</tt> provide a separate implementation for each.
+
+<p>
+Note well that in <tt>CONFIG_PREEMPT=y</tt> kernels,
+<tt>rcu_read_lock_sched()</tt> and <tt>rcu_read_unlock_sched()</tt>
+disable and re-enable preemption, respectively.
+This means that if there was a preemption attempt during the
+RCU-sched read-side critical section, <tt>rcu_read_unlock_sched()</tt>
+will enter the scheduler, with all the latency and overhead entailed.
+Just as with <tt>rcu_read_unlock_bh()</tt>, this can make it look
+as if <tt>rcu_read_unlock_sched()</tt> was executing very slowly.
+However, the highest-priority task won't be preempted, so that task
+will enjoy low-overhead <tt>rcu_read_unlock_sched()</tt> invocations.
+
+<p>
+The
+<a href="https://lwn.net/Articles/609973/#RCU Per-Flavor API Table">RCU-sched API</a>
+includes
+<tt>rcu_read_lock_sched()</tt>,
+<tt>rcu_read_unlock_sched()</tt>,
+<tt>rcu_read_lock_sched_notrace()</tt>,
+<tt>rcu_read_unlock_sched_notrace()</tt>,
+<tt>rcu_dereference_sched()</tt>,
+<tt>rcu_dereference_sched_check()</tt>,
+<tt>synchronize_sched()</tt>,
+<tt>synchronize_rcu_sched_expedited()</tt>,
+<tt>call_rcu_sched()</tt>,
+<tt>rcu_barrier_sched()</tt>, and
+<tt>rcu_read_lock_sched_held()</tt>.
+However, anything that disables preemption also marks an RCU-sched
+read-side critical section, including
+<tt>preempt_disable()</tt> and <tt>preempt_enable()</tt>,
+<tt>local_irq_save()</tt> and <tt>local_irq_restore()</tt>,
+and so on.
+
+<h3><a name="Sleepable RCU">Sleepable RCU</a></h3>
+
+<p>
+For well over a decade, someone saying &ldquo;I need to block within
+an RCU read-side critical section&rdquo; was a reliable indication
+that this someone did not understand RCU.
+After all, if you are always blocking in an RCU read-side critical
+section, you can probably afford to use a higher-overhead synchronization
+mechanism.
+However, that changed with the advent of the Linux kernel's notifiers,
+whose RCU read-side critical
+sections almost never sleep, but sometimes need to.
+This resulted in the introduction of
+<a href="https://lwn.net/Articles/202847/">sleepable RCU</a>,
+or <i>SRCU</i>.
+
+<p>
+SRCU allows different domains to be defined, with each such domain
+defined by an instance of an <tt>srcu_struct</tt> structure.
+A pointer to this structure must be passed in to each SRCU function,
+for example, <tt>synchronize_srcu(&amp;ss)</tt>, where
+<tt>ss</tt> is the <tt>srcu_struct</tt> structure.
+The key benefit of these domains is that a slow SRCU reader in one
+domain does not delay an SRCU grace period in some other domain.
+That said, one consequence of these domains is that read-side code
+must pass a &ldquo;cookie&rdquo; from <tt>srcu_read_lock()</tt>
+to <tt>srcu_read_unlock()</tt>, for example, as follows:
+
+<blockquote>
+<pre>
+ 1 int idx;
+ 2
+ 3 idx = srcu_read_lock(&amp;ss);
+ 4 do_something();
+ 5 srcu_read_unlock(&amp;ss, idx);
+</pre>
+</blockquote>
+
+<p>
+As noted above, it is legal to block within SRCU read-side critical sections,
+however, with great power comes great responsibility.
+If you block forever in one of a given domain's SRCU read-side critical
+sections, then that domain's grace periods will also be blocked forever.
+Of course, one good way to block forever is to deadlock, which can
+happen if any operation in a given domain's SRCU read-side critical
+section can block waiting, either directly or indirectly, for that domain's
+grace period to elapse.
+For example, this results in a self-deadlock:
+
+<blockquote>
+<pre>
+ 1 int idx;
+ 2
+ 3 idx = srcu_read_lock(&amp;ss);
+ 4 do_something();
+ 5 synchronize_srcu(&amp;ss);
+ 6 srcu_read_unlock(&amp;ss, idx);
+</pre>
+</blockquote>
+
+<p>
+However, if line&nbsp;5 acquired a mutex that was held across
+a <tt>synchronize_srcu()</tt> for domain <tt>ss</tt>,
+deadlock would still be possible.
+Furthermore, if line&nbsp;5 acquired a mutex that was held across
+a <tt>synchronize_srcu()</tt> for some other domain <tt>ss1</tt>,
+and if an <tt>ss1</tt>-domain SRCU read-side critical section
+acquired another mutex that was held across as <tt>ss</tt>-domain
+<tt>synchronize_srcu()</tt>,
+deadlock would again be possible.
+Such a deadlock cycle could extend across an arbitrarily large number
+of different SRCU domains.
+Again, with great power comes great responsibility.
+
+<p>
+Unlike the other RCU flavors, SRCU read-side critical sections can
+run on idle and even offline CPUs.
+This ability requires that <tt>srcu_read_lock()</tt> and
+<tt>srcu_read_unlock()</tt> contain memory barriers, which means
+that SRCU readers will run a bit slower than would RCU readers.
+It also motivates the <tt>smp_mb__after_srcu_read_unlock()</tt>
+API, which, in combination with <tt>srcu_read_unlock()</tt>,
+guarantees a full memory barrier.
+
+<p>
+The
+<a href="https://lwn.net/Articles/609973/#RCU Per-Flavor API Table">SRCU API</a>
+includes
+<tt>srcu_read_lock()</tt>,
+<tt>srcu_read_unlock()</tt>,
+<tt>srcu_dereference()</tt>,
+<tt>srcu_dereference_check()</tt>,
+<tt>synchronize_srcu()</tt>,
+<tt>synchronize_srcu_expedited()</tt>,
+<tt>call_srcu()</tt>,
+<tt>srcu_barrier()</tt>, and
+<tt>srcu_read_lock_held()</tt>.
+It also includes
+<tt>DEFINE_SRCU()</tt>,
+<tt>DEFINE_STATIC_SRCU()</tt>, and
+<tt>init_srcu_struct()</tt>
+APIs for defining and initializing <tt>srcu_struct</tt> structures.
+
+<h3><a name="Tasks RCU">Tasks RCU</a></h3>
+
+<p>
+Some forms of tracing use &ldquo;tramopolines&rdquo; to handle the
+binary rewriting required to install different types of probes.
+It would be good to be able to free old trampolines, which sounds
+like a job for some form of RCU.
+However, because it is necessary to be able to install a trace
+anywhere in the code, it is not possible to use read-side markers
+such as <tt>rcu_read_lock()</tt> and <tt>rcu_read_unlock()</tt>.
+In addition, it does not work to have these markers in the trampoline
+itself, because there would need to be instructions following
+<tt>rcu_read_unlock()</tt>.
+Although <tt>synchronize_rcu()</tt> would guarantee that execution
+reached the <tt>rcu_read_unlock()</tt>, it would not be able to
+guarantee that execution had completely left the trampoline.
+
+<p>
+The solution, in the form of
+<a href="https://lwn.net/Articles/607117/"><i>Tasks RCU</i></a>,
+is to have implicit
+read-side critical sections that are delimited by voluntary context
+switches, that is, calls to <tt>schedule()</tt>,
+<tt>cond_resched_rcu_qs()</tt>, and
+<tt>synchronize_rcu_tasks()</tt>.
+In addition, transitions to and from userspace execution also delimit
+tasks-RCU read-side critical sections.
+
+<p>
+The tasks-RCU API is quite compact, consisting only of
+<tt>call_rcu_tasks()</tt>,
+<tt>synchronize_rcu_tasks()</tt>, and
+<tt>rcu_barrier_tasks()</tt>.
+
+<h2><a name="Possible Future Changes">Possible Future Changes</a></h2>
+
+<p>
+One of the tricks that RCU uses to attain update-side scalability is
+to increase grace-period latency with increasing numbers of CPUs.
+If this becomes a serious problem, it will be necessary to rework the
+grace-period state machine so as to avoid the need for the additional
+latency.
+
+<p>
+Expedited grace periods scan the CPUs, so their latency and overhead
+increases with increasing numbers of CPUs.
+If this becomes a serious problem on large systems, it will be necessary
+to do some redesign to avoid this scalability problem.
+
+<p>
+RCU disables CPU hotplug in a few places, perhaps most notably in the
+expedited grace-period and <tt>rcu_barrier()</tt> operations.
+If there is a strong reason to use expedited grace periods in CPU-hotplug
+notifiers, it will be necessary to avoid disabling CPU hotplug.
+This would introduce some complexity, so there had better be a <i>very</i>
+good reason.
+
+<p>
+The tradeoff between grace-period latency on the one hand and interruptions
+of other CPUs on the other hand may need to be re-examined.
+The desire is of course for zero grace-period latency as well as zero
+interprocessor interrupts undertaken during an expedited grace period
+operation.
+While this ideal is unlikely to be achievable, it is quite possible that
+further improvements can be made.
+
+<p>
+The multiprocessor implementations of RCU use a combining tree that
+groups CPUs so as to reduce lock contention and increase cache locality.
+However, this combining tree does not spread its memory across NUMA
+nodes nor does it align the CPU groups with hardware features such
+as sockets or cores.
+Such spreading and alignment is currently believed to be unnecessary
+because the hotpath read-side primitives do not access the combining
+tree, nor does <tt>call_rcu()</tt> in the common case.
+If you believe that your architecture needs such spreading and alignment,
+then your architecture should also benefit from the
+<tt>rcutree.rcu_fanout_leaf</tt> boot parameter, which can be set
+to the number of CPUs in a socket, NUMA node, or whatever.
+If the number of CPUs is too large, use a fraction of the number of
+CPUs.
+If the number of CPUs is a large prime number, well, that certainly
+is an &ldquo;interesting&rdquo; architectural choice!
+More flexible arrangements might be considered, but only if
+<tt>rcutree.rcu_fanout_leaf</tt> has proven inadequate, and only
+if the inadequacy has been demonstrated by a carefully run and
+realistic system-level workload.
+
+<p>
+Please note that arrangements that require RCU to remap CPU numbers will
+require extremely good demonstration of need and full exploration of
+alternatives.
+
+<p>
+There is an embarrassingly large number of flavors of RCU, and this
+number has been increasing over time.
+Perhaps it will be possible to combine some at some future date.
+
+<p>
+RCU's various kthreads are reasonably recent additions.
+It is quite likely that adjustments will be required to more gracefully
+handle extreme loads.
+It might also be necessary to be able to relate CPU utilization by
+RCU's kthreads and softirq handlers to the code that instigated this
+CPU utilization.
+For example, RCU callback overhead might be charged back to the
+originating <tt>call_rcu()</tt> instance, though probably not
+in production kernels.
+
+<h2><a name="Summary">Summary</a></h2>
+
+<p>
+This document has presented more than two decade's worth of RCU
+requirements.
+Given that the requirements keep changing, this will not be the last
+word on this subject, but at least it serves to get an important
+subset of the requirements set forth.
+
+<h2><a name="Acknowledgments">Acknowledgments</a></h2>
+
+I am grateful to Steven Rostedt, Lai Jiangshan, Ingo Molnar,
+Oleg Nesterov, Borislav Petkov, Peter Zijlstra, Boqun Feng, and
+Andy Lutomirski for their help in rendering
+this article human readable, and to Michelle Rankin for her support
+of this effort.
+Other contributions are acknowledged in the Linux kernel's git archive.
+The cartoon is copyright (c) 2013 by Melissa Broussard,
+and is provided
+under the terms of the Creative Commons Attribution-Share Alike 3.0
+United States license.
+
+<p>@@QQAL@@
+
+</body></html>
diff --git a/Documentation/RCU/Design/htmlqqz.sh b/Documentation/RCU/Design/htmlqqz.sh
new file mode 100755
index 0000000..d354f06
--- /dev/null
+++ b/Documentation/RCU/Design/htmlqqz.sh
@@ -0,0 +1,108 @@
+#!/bin/sh
+#
+# Usage: sh htmlqqz.sh file
+#
+# Extracts and converts quick quizzes in a proto-HTML document file.htmlx.
+# Commands, all of which must be on a line by themselves:
+#
+#	"<p>@@QQ@@": Start of a quick quiz.
+#	"<p>@@QQA@@": Start of a quick-quiz answer.
+#	"<p>@@QQE@@": End of a quick-quiz answer, and thus of the quick quiz.
+#	"<p>@@QQAL@@": Place to put quick-quiz answer list.
+#
+# Places the result in file.html.
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, you can access it online at
+# http://www.gnu.org/licenses/gpl-2.0.html.
+#
+# Copyright (c) 2013 Paul E. McKenney, IBM Corporation.
+
+fn=$1
+if test ! -r $fn.htmlx
+then
+	echo "Error: $fn.htmlx unreadable."
+	exit 1
+fi
+
+echo "<!-- DO NOT HAND EDIT. -->" > $fn.html
+echo "<!-- Instead, edit $fn.htmlx and run 'sh htmlqqz.sh $fn' -->" >> $fn.html
+awk < $fn.htmlx >> $fn.html '
+
+state == "" && $1 != "<p>@@QQ@@" && $1 != "<p>@@QQAL@@" {
+	print $0;
+	if ($0 ~ /^<p>@@QQ/)
+		print "Bad Quick Quiz command: " NR " (expected <p>@@QQ@@ or <p>@@QQAL@@)." > "/dev/stderr"
+	next;
+}
+
+state == "" && $1 == "<p>@@QQ@@" {
+	qqn++;
+	qqlineno = NR;
+	haveqq = 1;
+	state = "qq";
+	print "<p><a name=\"Quick Quiz " qqn "\"><b>Quick Quiz " qqn "</b>:</a>"
+	next;
+}
+
+state == "qq" && $1 != "<p>@@QQA@@" {
+	qq[qqn] = qq[qqn] $0 "\n";
+	print $0
+	if ($0 ~ /^<p>@@QQ/)
+		print "Bad Quick Quiz command: " NR ". (expected <p>@@QQA@@)" > "/dev/stderr"
+	next;
+}
+
+state == "qq" && $1 == "<p>@@QQA@@" {
+	state = "qqa";
+	print "<br><a href=\"#qq" qqn "answer\">Answer</a>"
+	next;
+}
+
+state == "qqa" && $1 != "<p>@@QQE@@" {
+	qqa[qqn] = qqa[qqn] $0 "\n";
+	if ($0 ~ /^<p>@@QQ/)
+		print "Bad Quick Quiz command: " NR " (expected <p>@@QQE@@)." > "/dev/stderr"
+	next;
+}
+
+state == "qqa" && $1 == "<p>@@QQE@@" {
+	state = "";
+	next;
+}
+
+state == "" && $1 == "<p>@@QQAL@@" {
+	haveqq = "";
+	print "<h3><a name=\"Answers to Quick Quizzes\">"
+	print "Answers to Quick Quizzes</a></h3>"
+	print "";
+	for (i = 1; i <= qqn; i++) {
+		print "<a name=\"qq" i "answer\"></a>"
+		print "<p><b>Quick Quiz " i "</b>:"
+		print qq[i];
+		print "";
+		print "</p><p><b>Answer</b>:"
+		print qqa[i];
+		print "";
+		print "</p><p><a href=\"#Quick%20Quiz%20" i "\"><b>Back to Quick Quiz " i "</b>.</a>"
+		print "";
+	}
+	next;
+}
+
+END {
+	if (state != "")
+		print "Unterminated Quick Quiz: " qqlineno "." > "/dev/stderr"
+	else if (haveqq)
+		print "Missing \"<p>@@QQAL@@\", no Quick Quiz." > "/dev/stderr"
+}'
diff --git a/Documentation/arm64/silicon-errata.txt b/Documentation/arm64/silicon-errata.txt
new file mode 100644
index 0000000..58b71dd
--- /dev/null
+++ b/Documentation/arm64/silicon-errata.txt
@@ -0,0 +1,58 @@
+                Silicon Errata and Software Workarounds
+                =======================================
+
+Author: Will Deacon <will.deacon@arm.com>
+Date  : 27 November 2015
+
+It is an unfortunate fact of life that hardware is often produced with
+so-called "errata", which can cause it to deviate from the architecture
+under specific circumstances.  For hardware produced by ARM, these
+errata are broadly classified into the following categories:
+
+  Category A: A critical error without a viable workaround.
+  Category B: A significant or critical error with an acceptable
+              workaround.
+  Category C: A minor error that is not expected to occur under normal
+              operation.
+
+For more information, consult one of the "Software Developers Errata
+Notice" documents available on infocenter.arm.com (registration
+required).
+
+As far as Linux is concerned, Category B errata may require some special
+treatment in the operating system. For example, avoiding a particular
+sequence of code, or configuring the processor in a particular way. A
+less common situation may require similar actions in order to declassify
+a Category A erratum into a Category C erratum. These are collectively
+known as "software workarounds" and are only required in the minority of
+cases (e.g. those cases that both require a non-secure workaround *and*
+can be triggered by Linux).
+
+For software workarounds that may adversely impact systems unaffected by
+the erratum in question, a Kconfig entry is added under "Kernel
+Features" -> "ARM errata workarounds via the alternatives framework".
+These are enabled by default and patched in at runtime when an affected
+CPU is detected. For less-intrusive workarounds, a Kconfig option is not
+available and the code is structured (preferably with a comment) in such
+a way that the erratum will not be hit.
+
+This approach can make it slightly onerous to determine exactly which
+errata are worked around in an arbitrary kernel source tree, so this
+file acts as a registry of software workarounds in the Linux Kernel and
+will be updated when new workarounds are committed and backported to
+stable kernels.
+
+| Implementor    | Component       | Erratum ID      | Kconfig                 |
++----------------+-----------------+-----------------+-------------------------+
+| ARM            | Cortex-A53      | #826319         | ARM64_ERRATUM_826319    |
+| ARM            | Cortex-A53      | #827319         | ARM64_ERRATUM_827319    |
+| ARM            | Cortex-A53      | #824069         | ARM64_ERRATUM_824069    |
+| ARM            | Cortex-A53      | #819472         | ARM64_ERRATUM_819472    |
+| ARM            | Cortex-A53      | #845719         | ARM64_ERRATUM_845719    |
+| ARM            | Cortex-A53      | #843419         | ARM64_ERRATUM_843419    |
+| ARM            | Cortex-A57      | #832075         | ARM64_ERRATUM_832075    |
+| ARM            | Cortex-A57      | #852523         | N/A                     |
+| ARM            | Cortex-A57      | #834220         | ARM64_ERRATUM_834220    |
+|                |                 |                 |                         |
+| Cavium         | ThunderX ITS    | #22375, #24313  | CAVIUM_ERRATUM_22375    |
+| Cavium         | ThunderX GICv3  | #23154          | CAVIUM_ERRATUM_23154    |
diff --git a/Documentation/device-mapper/verity.txt b/Documentation/device-mapper/verity.txt
index e15bc1a..89fd8f9 100644
--- a/Documentation/device-mapper/verity.txt
+++ b/Documentation/device-mapper/verity.txt
@@ -18,11 +18,11 @@
 
     0 is the original format used in the Chromium OS.
       The salt is appended when hashing, digests are stored continuously and
-      the rest of the block is padded with zeros.
+      the rest of the block is padded with zeroes.
 
     1 is the current format that should be used for new devices.
       The salt is prepended when hashing and each digest is
-      padded with zeros to the power of two.
+      padded with zeroes to the power of two.
 
 <dev>
     This is the device containing data, the integrity of which needs to be
@@ -79,6 +79,37 @@
     not compatible with ignore_corruption and requires user space support to
     avoid restart loops.
 
+ignore_zero_blocks
+    Do not verify blocks that are expected to contain zeroes and always return
+    zeroes instead. This may be useful if the partition contains unused blocks
+    that are not guaranteed to contain zeroes.
+
+use_fec_from_device <fec_dev>
+    Use forward error correction (FEC) to recover from corruption if hash
+    verification fails. Use encoding data from the specified device. This
+    may be the same device where data and hash blocks reside, in which case
+    fec_start must be outside data and hash areas.
+
+    If the encoding data covers additional metadata, it must be accessible
+    on the hash device after the hash blocks.
+
+    Note: block sizes for data and hash devices must match. Also, if the
+    verity <dev> is encrypted the <fec_dev> should be too.
+
+fec_roots <num>
+    Number of generator roots. This equals to the number of parity bytes in
+    the encoding data. For example, in RS(M, N) encoding, the number of roots
+    is M-N.
+
+fec_blocks <num>
+    The number of encoding data blocks on the FEC device. The block size for
+    the FEC device is <data_block_size>.
+
+fec_start <offset>
+    This is the offset, in <data_block_size> blocks, from the start of the
+    FEC device to the beginning of the encoding data.
+
+
 Theory of operation
 ===================
 
@@ -98,6 +129,11 @@
 into the page cache. Block hashes are stored linearly, aligned to the nearest
 block size.
 
+If forward error correction (FEC) support is enabled any recovery of
+corrupted data will be verified using the cryptographic hash of the
+corresponding data. This is why combining error correction with
+integrity checking is essential.
+
 Hash Tree
 ---------
 
diff --git a/Documentation/devicetree/bindings/arm/l2cc.txt b/Documentation/devicetree/bindings/arm/l2c2x0.txt
similarity index 77%
rename from Documentation/devicetree/bindings/arm/l2cc.txt
rename to Documentation/devicetree/bindings/arm/l2c2x0.txt
index 06c88a4..fe0398c 100644
--- a/Documentation/devicetree/bindings/arm/l2cc.txt
+++ b/Documentation/devicetree/bindings/arm/l2c2x0.txt
@@ -1,7 +1,8 @@
 * ARM L2 Cache Controller
 
-ARM cores often have a separate level 2 cache controller. There are various
-implementations of the L2 cache controller with compatible programming models.
+ARM cores often have a separate L2C210/L2C220/L2C310 (also known as PL210/PL220/
+PL310 and variants) based level 2 cache controller. All these various implementations
+of the L2 cache controller have compatible programming models (Note 1).
 Some of the properties that are just prefixed "cache-*" are taken from section
 3.7.3 of the ePAPR v1.1 specification which can be found at:
 https://www.power.org/wp-content/uploads/2012/06/Power_ePAPR_APPROVED_v1.1.pdf
@@ -67,12 +68,17 @@
   disable if zero.
 - arm,prefetch-offset : Override prefetch offset value. Valid values are
   0-7, 15, 23, and 31.
-- arm,shared-override : The default behavior of the pl310 cache controller with
-  respect to the shareable attribute is to transform "normal memory
-  non-cacheable transactions" into "cacheable no allocate" (for reads) or
-  "write through no write allocate" (for writes).
+- arm,shared-override : The default behavior of the L220 or PL310 cache
+  controllers with respect to the shareable attribute is to transform "normal
+  memory non-cacheable transactions" into "cacheable no allocate" (for reads)
+  or "write through no write allocate" (for writes).
   On systems where this may cause DMA buffer corruption, this property must be
   specified to indicate that such transforms are precluded.
+- arm,parity-enable : enable parity checking on the L2 cache (L220 or PL310).
+- arm,parity-disable : disable parity checking on the L2 cache (L220 or PL310).
+- arm,outer-sync-disable : disable the outer sync operation on the L2 cache.
+  Some core tiles, especially ARM PB11MPCore have a faulty L220 cache that
+  will randomly hang unless outer sync operations are disabled.
 - prefetch-data : Data prefetch. Value: <0> (forcibly disable), <1>
   (forcibly enable), property absent (retain settings set by firmware)
 - prefetch-instr : Instruction prefetch. Value: <0> (forcibly disable),
@@ -91,3 +97,9 @@
         cache-level = <2>;
 	interrupts = <45>;
 };
+
+Note 1: The description in this document doesn't apply to integrated L2
+	cache controllers as found in e.g. Cortex-A15/A7/A57/A53. These
+	integrated L2 controllers are assumed to be all preconfigured by
+	early secure boot code. Thus no need to deal with their configuration
+	in the kernel at all.
diff --git a/Documentation/devicetree/bindings/arm/pmu.txt b/Documentation/devicetree/bindings/arm/pmu.txt
index 97ba45a..5651883 100644
--- a/Documentation/devicetree/bindings/arm/pmu.txt
+++ b/Documentation/devicetree/bindings/arm/pmu.txt
@@ -9,8 +9,9 @@
 - compatible : should be one of
 	"apm,potenza-pmu"
 	"arm,armv8-pmuv3"
-	"arm.cortex-a57-pmu"
-	"arm.cortex-a53-pmu"
+	"arm,cortex-a72-pmu"
+	"arm,cortex-a57-pmu"
+	"arm,cortex-a53-pmu"
 	"arm,cortex-a17-pmu"
 	"arm,cortex-a15-pmu"
 	"arm,cortex-a12-pmu"
diff --git a/Documentation/devicetree/bindings/ata/brcm,sata-brcmstb.txt b/Documentation/devicetree/bindings/ata/brcm,sata-brcmstb.txt
index 20ac9bb..6087283 100644
--- a/Documentation/devicetree/bindings/ata/brcm,sata-brcmstb.txt
+++ b/Documentation/devicetree/bindings/ata/brcm,sata-brcmstb.txt
@@ -4,7 +4,9 @@
 Each SATA controller should have its own node.
 
 Required properties:
-- compatible         : compatible list, may contain "brcm,bcm7445-ahci" and/or
+- compatible         : should be one or more of
+                       "brcm,bcm7425-ahci"
+                       "brcm,bcm7445-ahci"
                        "brcm,sata3-ahci"
 - reg                : register mappings for AHCI and SATA_TOP_CTRL
 - reg-names          : "ahci" and "top-ctrl"
diff --git a/Documentation/devicetree/bindings/ata/sata_rcar.txt b/Documentation/devicetree/bindings/ata/sata_rcar.txt
index 2493a5a3..0764f9a 100644
--- a/Documentation/devicetree/bindings/ata/sata_rcar.txt
+++ b/Documentation/devicetree/bindings/ata/sata_rcar.txt
@@ -8,6 +8,7 @@
 			  - "renesas,sata-r8a7790" for R-Car H2 other than ES1
 			  - "renesas,sata-r8a7791" for R-Car M2-W
 			  - "renesas,sata-r8a7793" for R-Car M2-N
+			  - "renesas,sata-r8a7795" for R-Car H3
 - reg			: address and length of the SATA registers;
 - interrupts		: must consist of one interrupt specifier.
 - clocks		: must contain a reference to the functional clock.
diff --git a/Documentation/devicetree/bindings/crypto/rockchip-crypto.txt b/Documentation/devicetree/bindings/crypto/rockchip-crypto.txt
new file mode 100644
index 0000000..096df34
--- /dev/null
+++ b/Documentation/devicetree/bindings/crypto/rockchip-crypto.txt
@@ -0,0 +1,29 @@
+Rockchip Electronics And Security Accelerator
+
+Required properties:
+- compatible: Should be "rockchip,rk3288-crypto"
+- reg: Base physical address of the engine and length of memory mapped
+       region
+- interrupts: Interrupt number
+- clocks: Reference to the clocks about crypto
+- clock-names: "aclk" used to clock data
+	       "hclk" used to clock data
+	       "sclk" used to clock crypto accelerator
+	       "apb_pclk" used to clock dma
+- resets: Must contain an entry for each entry in reset-names.
+	  See ../reset/reset.txt for details.
+- reset-names: Must include the name "crypto-rst".
+
+Examples:
+
+	crypto: cypto-controller@ff8a0000 {
+		compatible = "rockchip,rk3288-crypto";
+		reg = <0xff8a0000 0x4000>;
+		interrupts = <GIC_SPI 48 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&cru ACLK_CRYPTO>, <&cru HCLK_CRYPTO>,
+			 <&cru SCLK_CRYPTO>, <&cru ACLK_DMAC1>;
+		clock-names = "aclk", "hclk", "sclk", "apb_pclk";
+		resets = <&cru SRST_CRYPTO>;
+		reset-names = "crypto-rst";
+		status = "okay";
+	};
diff --git a/Documentation/devicetree/bindings/interrupt-controller/allwinner,sun67i-sc-nmi.txt b/Documentation/devicetree/bindings/interrupt-controller/allwinner,sunxi-nmi.txt
similarity index 93%
rename from Documentation/devicetree/bindings/interrupt-controller/allwinner,sun67i-sc-nmi.txt
rename to Documentation/devicetree/bindings/interrupt-controller/allwinner,sunxi-nmi.txt
index d1c5cda..81cd369 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/allwinner,sun67i-sc-nmi.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/allwinner,sunxi-nmi.txt
@@ -4,7 +4,7 @@
 Required properties:
 
 - compatible : should be "allwinner,sun7i-a20-sc-nmi" or
-  "allwinner,sun6i-a31-sc-nmi"
+  "allwinner,sun6i-a31-sc-nmi" or "allwinner,sun9i-a80-nmi"
 - reg : Specifies base physical address and size of the registers.
 - interrupt-controller : Identifies the node as an interrupt controller
 - #interrupt-cells : Specifies the number of cells needed to encode an
diff --git a/Documentation/devicetree/bindings/interrupt-controller/arm,gic.txt b/Documentation/devicetree/bindings/interrupt-controller/arm,gic.txt
index cc56021..5a1cb4b 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/arm,gic.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/arm,gic.txt
@@ -18,6 +18,7 @@
 	"arm,cortex-a9-gic"
 	"arm,gic-400"
 	"arm,pl390"
+	"arm,tc11mp-gic"
 	"brcm,brahma-b15-gic"
 	"qcom,msm-8660-qgic"
 	"qcom,msm-qgic2"
diff --git a/Documentation/devicetree/bindings/interrupt-controller/hisilicon,mbigen-v2.txt b/Documentation/devicetree/bindings/interrupt-controller/hisilicon,mbigen-v2.txt
new file mode 100644
index 0000000..720f7c9
--- /dev/null
+++ b/Documentation/devicetree/bindings/interrupt-controller/hisilicon,mbigen-v2.txt
@@ -0,0 +1,74 @@
+Hisilicon mbigen device tree bindings.
+=======================================
+
+Mbigen means: message based interrupt generator.
+
+MBI is kind of msi interrupt only used on Non-PCI devices.
+
+To reduce the wired interrupt number connected to GIC,
+Hisilicon designed mbigen to collect and generate interrupt.
+
+
+Non-pci devices can connect to mbigen and generate the
+interrupt by writing ITS register.
+
+The mbigen chip and devices connect to mbigen have the following properties:
+
+Mbigen main node required properties:
+-------------------------------------------
+- compatible: Should be "hisilicon,mbigen-v2"
+
+- reg: Specifies the base physical address and size of the Mbigen
+  registers.
+
+- interrupt controller: Identifies the node as an interrupt controller
+
+- msi-parent: Specifies the MSI controller this mbigen use.
+  For more detail information,please refer to the generic msi-parent binding in
+  Documentation/devicetree/bindings/interrupt-controller/msi.txt.
+
+- num-pins: the total number of pins implemented in this Mbigen
+  instance.
+
+- #interrupt-cells : Specifies the number of cells needed to encode an
+  interrupt source. The value must be 2.
+
+  The 1st cell is hardware pin number of the interrupt.This number is local to
+  each mbigen chip and in the range from 0 to the maximum interrupts number
+  of the mbigen.
+
+  The 2nd cell is the interrupt trigger type.
+	The value of this cell should be:
+	1: rising edge triggered
+	or
+	4: high level triggered
+
+Examples:
+
+	mbigen_device_gmac:intc {
+			compatible = "hisilicon,mbigen-v2";
+			reg = <0x0 0xc0080000 0x0 0x10000>;
+			interrupt-controller;
+			msi-parent = <&its_dsa 0x40b1c>;
+			num-pins = <9>;
+			#interrupt-cells = <2>;
+	};
+
+Devices connect to mbigen required properties:
+----------------------------------------------------
+-interrupt-parent: Specifies the mbigen device node which device connected.
+
+-interrupts:Specifies the interrupt source.
+ For the specific information of each cell in this property,please refer to
+ the "interrupt-cells" description mentioned above.
+
+Examples:
+	gmac0: ethernet@c2080000 {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		reg = <0 0xc2080000 0 0x20000>,
+		      <0 0xc0000000 0 0x1000>;
+		interrupt-parent  = <&mbigen_device_gmac>;
+		interrupts =	<656 1>,
+				<657 1>;
+	};
diff --git a/Documentation/devicetree/bindings/interrupt-controller/technologic,ts4800.txt b/Documentation/devicetree/bindings/interrupt-controller/technologic,ts4800.txt
new file mode 100644
index 0000000..7f15f1b
--- /dev/null
+++ b/Documentation/devicetree/bindings/interrupt-controller/technologic,ts4800.txt
@@ -0,0 +1,16 @@
+TS-4800 FPGA interrupt controller
+
+TS-4800 FPGA has an internal interrupt controller. When one of the
+interrupts is triggered, the SoC is notified, usually using a GPIO as
+parent interrupt source.
+
+Required properties:
+- compatible: should be "technologic,ts4800-irqc"
+- interrupt-controller: identifies the node as an interrupt controller
+- reg: physical base address of the controller and length of memory mapped
+  region
+- #interrupt-cells: specifies the number of cells needed to encode an interrupt
+  source, should be 1.
+- interrupt-parent: phandle to the parent interrupt controller this one is
+  cascaded from
+- interrupts: specifies the interrupt line in the interrupt-parent controller
diff --git a/Documentation/devicetree/bindings/media/stih407-c8sectpfe.txt b/Documentation/devicetree/bindings/media/stih407-c8sectpfe.txt
index d4def76..cc51b1f 100644
--- a/Documentation/devicetree/bindings/media/stih407-c8sectpfe.txt
+++ b/Documentation/devicetree/bindings/media/stih407-c8sectpfe.txt
@@ -35,7 +35,7 @@
 
 - tsin-num	: tsin id of the InputBlock (must be between 0 to 6)
 - i2c-bus	: phandle to the I2C bus DT node which the demodulators & tuners on this tsin channel are connected.
-- rst-gpio	: reset gpio for this tsin channel.
+- reset-gpios	: reset gpio for this tsin channel.
 
 Optional properties (tsin (child) node):
 
@@ -55,27 +55,27 @@
 		status = "okay";
 		reg = <0x08a20000 0x10000>, <0x08a00000 0x4000>;
 		reg-names = "stfe", "stfe-ram";
-		interrupts = <0 34 0>, <0 35 0>;
+		interrupts = <GIC_SPI 34 IRQ_TYPE_NONE>, <GIC_SPI 35 IRQ_TYPE_NONE>;
 		interrupt-names = "stfe-error-irq", "stfe-idle-irq";
-
-		pinctrl-names	= "tsin0-serial", "tsin0-parallel", "tsin3-serial",
-				"tsin4-serial", "tsin5-serial";
-
 		pinctrl-0	= <&pinctrl_tsin0_serial>;
 		pinctrl-1	= <&pinctrl_tsin0_parallel>;
 		pinctrl-2	= <&pinctrl_tsin3_serial>;
 		pinctrl-3	= <&pinctrl_tsin4_serial_alt3>;
 		pinctrl-4	= <&pinctrl_tsin5_serial_alt1>;
-
+		pinctrl-names	= "tsin0-serial",
+				  "tsin0-parallel",
+				  "tsin3-serial",
+				  "tsin4-serial",
+				  "tsin5-serial";
 		clocks = <&clk_s_c0_flexgen CLK_PROC_STFE>;
-		clock-names = "stfe";
+		clock-names = "c8sectpfe";
 
 		/* tsin0 is TSA on NIMA */
 		tsin0: port@0 {
 			tsin-num		= <0>;
 			serial-not-parallel;
 			i2c-bus			= <&ssc2>;
-			rst-gpio		= <&pio15 4 0>;
+			reset-gpios		= <&pio15 4 GPIO_ACTIVE_HIGH>;
 			dvb-card		= <STV0367_TDA18212_NIMA_1>;
 		};
 
@@ -83,7 +83,7 @@
 			tsin-num		= <3>;
 			serial-not-parallel;
 			i2c-bus			= <&ssc3>;
-			rst-gpio		= <&pio15 7 0>;
+			reset-gpios		= <&pio15 7 GPIO_ACTIVE_HIGH>;
 			dvb-card		= <STV0367_TDA18212_NIMB_1>;
 		};
 	};
diff --git a/Documentation/devicetree/bindings/mmc/renesas,mmcif.txt b/Documentation/devicetree/bindings/mmc/renesas,mmcif.txt
index cae29eb..ff611fa 100644
--- a/Documentation/devicetree/bindings/mmc/renesas,mmcif.txt
+++ b/Documentation/devicetree/bindings/mmc/renesas,mmcif.txt
@@ -11,6 +11,7 @@
 	- "renesas,mmcif-r8a7740" for the MMCIF found in r8a7740 SoCs
 	- "renesas,mmcif-r8a7790" for the MMCIF found in r8a7790 SoCs
 	- "renesas,mmcif-r8a7791" for the MMCIF found in r8a7791 SoCs
+	- "renesas,mmcif-r8a7793" for the MMCIF found in r8a7793 SoCs
 	- "renesas,mmcif-r8a7794" for the MMCIF found in r8a7794 SoCs
 
 - clocks: reference to the functional clock
diff --git a/Documentation/devicetree/bindings/pinctrl/allwinner,sunxi-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/allwinner,sunxi-pinctrl.txt
index b321b26..9213b27 100644
--- a/Documentation/devicetree/bindings/pinctrl/allwinner,sunxi-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/allwinner,sunxi-pinctrl.txt
@@ -17,7 +17,10 @@
   "allwinner,sun8i-a23-pinctrl"
   "allwinner,sun8i-a23-r-pinctrl"
   "allwinner,sun8i-a33-pinctrl"
+  "allwinner,sun9i-a80-pinctrl"
+  "allwinner,sun9i-a80-r-pinctrl"
   "allwinner,sun8i-a83t-pinctrl"
+  "allwinner,sun8i-h3-pinctrl"
 
 - reg: Should contain the register physical address and length for the
   pin controller.
diff --git a/Documentation/devicetree/bindings/pinctrl/brcm,cygnus-gpio.txt b/Documentation/devicetree/bindings/pinctrl/brcm,iproc-gpio.txt
similarity index 93%
rename from Documentation/devicetree/bindings/pinctrl/brcm,cygnus-gpio.txt
rename to Documentation/devicetree/bindings/pinctrl/brcm,iproc-gpio.txt
index 16589fb6..e427792 100644
--- a/Documentation/devicetree/bindings/pinctrl/brcm,cygnus-gpio.txt
+++ b/Documentation/devicetree/bindings/pinctrl/brcm,iproc-gpio.txt
@@ -1,4 +1,4 @@
-Broadcom Cygnus GPIO/PINCONF Controller
+Broadcom iProc GPIO/PINCONF Controller
 
 Required properties:
 
@@ -7,9 +7,12 @@
     "brcm,cygnus-crmu-gpio" or "brcm,iproc-gpio"
 
 - reg:
-    Define the base and range of the I/O address space that contains the Cygnus
+    Define the base and range of the I/O address space that contains SoC
 GPIO/PINCONF controller registers
 
+- ngpios:
+    Total number of in-use slots in GPIO controller
+
 - #gpio-cells:
     Must be two. The first cell is the GPIO pin number (within the
 controller's pin space) and the second cell is used for the following:
@@ -57,6 +60,7 @@
 		compatible = "brcm,cygnus-ccm-gpio";
 		reg = <0x1800a000 0x50>,
 		      <0x0301d164 0x20>;
+		ngpios = <24>;
 		#gpio-cells = <2>;
 		gpio-controller;
 		interrupts = <GIC_SPI 84 IRQ_TYPE_LEVEL_HIGH>;
@@ -78,6 +82,7 @@
 	gpio_asiu: gpio@180a5000 {
 		compatible = "brcm,cygnus-asiu-gpio";
 		reg = <0x180a5000 0x668>;
+		ngpios = <146>;
 		#gpio-cells = <2>;
 		gpio-controller;
 		interrupts = <GIC_SPI 174 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/Documentation/devicetree/bindings/pinctrl/brcm,nsp-gpio.txt b/Documentation/devicetree/bindings/pinctrl/brcm,nsp-gpio.txt
new file mode 100644
index 0000000..0844168
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/brcm,nsp-gpio.txt
@@ -0,0 +1,80 @@
+Broadcom Northstar plus (NSP) GPIO/PINCONF Controller
+
+Required properties:
+- compatible:
+    Must be "brcm,nsp-gpio-a"
+
+- reg:
+    Should contain the register physical address and length for each of
+    GPIO base, IO control registers
+
+- #gpio-cells:
+    Must be two. The first cell is the GPIO pin number (within the
+    controller's pin space) and the second cell is used for the following:
+    bit[0]: polarity (0 for active high and 1 for active low)
+
+- gpio-controller:
+    Specifies that the node is a GPIO controller
+
+- ngpios:
+    Number of gpios supported (58x25 supports 32 and 58x23 supports 24)
+
+Optional properties:
+- interrupts:
+    Interrupt ID
+
+- interrupt-controller:
+    Specifies that the node is an interrupt controller
+
+- gpio-ranges:
+    Specifies the mapping between gpio controller and pin-controllers pins.
+    This requires 4 fields in cells defined as -
+    1. Phandle of pin-controller.
+    2. GPIO base pin offset.
+    3  Pin-control base pin offset.
+    4. number of gpio pins which are linearly mapped from pin base.
+
+Supported generic PINCONF properties in child nodes:
+- pins:
+    The list of pins (within the controller's own pin space) that properties
+    in the node apply to. Pin names are "gpio-<pin>"
+
+- bias-disable:
+    Disable pin bias
+
+- bias-pull-up:
+    Enable internal pull up resistor
+
+- bias-pull-down:
+    Enable internal pull down resistor
+
+- drive-strength:
+    Valid drive strength values include 2, 4, 6, 8, 10, 12, 14, 16 (mA)
+
+Example:
+
+	gpioa: gpio@18000020 {
+		compatible = "brcm,nsp-gpio-a";
+		reg = <0x18000020 0x100>,
+		      <0x1803f1c4 0x1c>;
+		#gpio-cells = <2>;
+		gpio-controller;
+		ngpios = <32>;
+		gpio-ranges = <&pinctrl 0 0 31>;
+		interrupt-controller;
+		interrupts = <GIC_SPI 85 IRQ_TYPE_LEVEL_HIGH>;
+
+		/* Hog a few default settings */
+		pinctrl-names = "default";
+		pinctrl-0 = <&led>;
+		led: led {
+			pins = "gpio-1";
+			bias-pull-up;
+		};
+
+		pwr: pwr {
+			gpio-hog;
+			gpios = <3 1>;
+			output-high;
+		};
+	};
diff --git a/Documentation/devicetree/bindings/pinctrl/lantiq,pinctrl-xway.txt b/Documentation/devicetree/bindings/pinctrl/lantiq,pinctrl-xway.txt
index e89b467..8e5216b 100644
--- a/Documentation/devicetree/bindings/pinctrl/lantiq,pinctrl-xway.txt
+++ b/Documentation/devicetree/bindings/pinctrl/lantiq,pinctrl-xway.txt
@@ -1,7 +1,16 @@
 Lantiq XWAY pinmux controller
 
 Required properties:
-- compatible: "lantiq,pinctrl-xway" or "lantiq,pinctrl-xr9"
+- compatible: "lantiq,pinctrl-xway", (DEPRECATED: Use "lantiq,pinctrl-danube")
+	      "lantiq,pinctrl-xr9", (DEPRECATED: Use "lantiq,xrx100-pinctrl" or
+					"lantiq,xrx200-pinctrl")
+	      "lantiq,pinctrl-ase", (DEPRECATED: Use "lantiq,ase-pinctrl")
+	      "lantiq,<chip>-pinctrl", where <chip> is:
+		"ase" (XWAY AMAZON Family)
+		"danube" (XWAY DANUBE Family)
+		"xrx100" (XWAY xRX100 Family)
+		"xrx200" (XWAY xRX200 Family)
+		"xrx300" (XWAY xRX300 Family)
 - reg: Should contain the physical address and length of the gpio/pinmux
   register range
 
@@ -36,19 +45,87 @@
 
 Valid values for group and function names:
 
+XWAY: (DEPRECATED: Use DANUBE)
   mux groups:
     exin0, exin1, exin2, jtag, ebu a23, ebu a24, ebu a25, ebu clk, ebu cs1,
     ebu wait, nand ale, nand cs1, nand cle, spi, spi_cs1, spi_cs2, spi_cs3,
-    spi_cs4, spi_cs5, spi_cs6, asc0, asc0 cts rts, stp, nmi , gpt1, gpt2,
+    spi_cs4, spi_cs5, spi_cs6, asc0, asc0 cts rts, stp, nmi, gpt1, gpt2,
     gpt3, clkout0, clkout1, clkout2, clkout3, gnt1, gnt2, gnt3, req1, req2,
     req3
 
-  additional mux groups (XR9 only):
-    mdio, nand rdy, nand rd, exin3, exin4, gnt4, req4
+  functions:
+    spi, asc, cgu, jtag, exin, stp, gpt, nmi, pci, ebu
+
+XR9: ( DEPRECATED: Use xRX100/xRX200)
+  mux groups:
+    exin0, exin1, exin2, exin3, exin4, jtag, ebu a23, ebu a24, ebu a25,
+    ebu clk, ebu cs1, ebu wait, nand ale, nand cs1, nand cle, nand rdy,
+    nand rd, spi, spi_cs1, spi_cs2, spi_cs3, spi_cs4, spi_cs5, spi_cs6,
+    asc0, asc0 cts rts, stp, nmi, gpt1, gpt2, gpt3, clkout0, clkout1,
+    clkout2, clkout3, gnt1, gnt2, gnt3, gnt4, req1, req2, req3, req4, mdio,
+    gphy0 led0, gphy0 led1, gphy0 led2, gphy1 led0, gphy1 led1, gphy1 led2
 
   functions:
-    spi, asc, cgu, jtag, exin, stp, gpt, nmi, pci, ebu, mdio
+    spi, asc, cgu, jtag, exin, stp, gpt, nmi, pci, ebu, mdio, gphy
 
+AMAZON:
+  mux groups:
+    exin0, exin1, exin2, jtag, spi_di, spi_do, spi_clk, spi_cs1, spi_cs2,
+    spi_cs3, spi_cs4, spi_cs5, spi_cs6, asc, stp, gpt1, gpt2, gpt3, clkout0,
+    clkout1, clkout2, mdio, dfe led0, dfe led1, ephy led0, ephy led1, ephy led2
+
+  functions:
+    spi, asc, cgu, jtag, exin, stp, gpt, mdio, ephy, dfe
+
+DANUBE:
+  mux groups:
+    exin0, exin1, exin2, jtag, ebu a23, ebu a24, ebu a25, ebu clk, ebu cs1,
+    ebu wait, nand ale, nand cs1, nand cle, spi_di, spi_do, spi_clk, spi_cs1,
+    spi_cs2, spi_cs3, spi_cs4, spi_cs5, spi_cs6, asc0, asc0 cts rts, stp, nmi,
+    gpt1, gpt2, gpt3, clkout0, clkout1, clkout2, clkout3, gnt1, gnt2, gnt3,
+    req1, req2, req3, dfe led0, dfe led1
+
+  functions:
+    spi, asc, cgu, jtag, exin, stp, gpt, nmi, pci, ebu, dfe
+
+xRX100:
+  mux groups:
+    exin0, exin1, exin2, exin3, exin4, ebu a23, ebu a24, ebu a25, ebu clk,
+    ebu cs1, ebu wait, nand ale, nand cs1, nand cle, nand rdy, nand rd,
+    spi_di, spi_do, spi_clk, spi_cs1, spi_cs2, spi_cs3, spi_cs4, spi_cs5,
+    spi_cs6, asc0, asc0 cts rts, stp, nmi, gpt1, gpt2, gpt3, clkout0, clkout1,
+    clkout2, clkout3, gnt1, gnt2, gnt3, gnt4, req1, req2, req3, req4, mdio,
+    dfe led0, dfe led1
+
+  functions:
+    spi, asc, cgu, exin, stp, gpt, nmi, pci, ebu, mdio, dfe
+
+xRX200:
+  mux groups:
+    exin0, exin1, exin2, exin3, exin4, ebu a23, ebu a24, ebu a25, ebu clk,
+    ebu cs1, ebu wait, nand ale, nand cs1, nand cle, nand rdy, nand rd,
+    spi_di, spi_do, spi_clk, spi_cs1, spi_cs2, spi_cs3, spi_cs4, spi_cs5,
+    spi_cs6, usif uart_rx, usif uart_tx, usif uart_rts, usif uart_cts,
+    usif uart_dtr, usif uart_dsr, usif uart_dcd, usif uart_ri, usif spi_di,
+    usif spi_do, usif spi_clk, usif spi_cs0, usif spi_cs1, usif spi_cs2,
+    stp, nmi, gpt1, gpt2, gpt3, clkout0, clkout1, clkout2, clkout3, gnt1,
+    gnt2, gnt3, gnt4, req1, req2, req3, req4, mdio, dfe led0, dfe led1,
+    gphy0 led0, gphy0 led1, gphy0 led2, gphy1 led0, gphy1 led1, gphy1 led2
+
+  functions:
+    spi, usif, cgu, exin, stp, gpt, nmi, pci, ebu, mdio, dfe, gphy
+
+xRX300:
+  mux groups:
+    exin0, exin1, exin2, exin4, nand ale, nand cs0, nand cs1, nand cle,
+    nand rdy, nand rd, nand_d0, nand_d1, nand_d2, nand_d3, nand_d4, nand_d5,
+    nand_d6, nand_d7, nand_d1, nand wr, nand wp, nand se, spi_di, spi_do,
+    spi_clk, spi_cs1, spi_cs4, spi_cs6, usif uart_rx, usif uart_tx,
+    usif spi_di, usif spi_do, usif spi_clk, usif spi_cs0, stp, clkout2,
+    mdio, dfe led0, dfe led1, ephy0 led0, ephy0 led1, ephy1 led0, ephy1 led1
+
+  functions:
+    spi, usif, cgu, exin, stp, ebu, mdio, dfe, ephy
 
 
 Definition of pin configurations:
@@ -62,15 +139,32 @@
     0: none, 1: down, 2: up.
 - lantiq,open-drain: Boolean, enables open-drain on the defined pin.
 
-Valid values for XWAY pin names:
+Valid values for XWAY pin names: (DEPRECATED: Use DANUBE)
   Pinconf pins can be referenced via the names io0-io31.
 
-Valid values for XR9 pin names:
+Valid values for XR9 pin names: (DEPRECATED: Use xrX100/xRX200)
   Pinconf pins can be referenced via the names io0-io55.
 
+Valid values for AMAZON pin names:
+  Pinconf pins can be referenced via the names io0-io31.
+
+Valid values for DANUBE pin names:
+  Pinconf pins can be referenced via the names io0-io31.
+
+Valid values for xRX100 pin names:
+  Pinconf pins can be referenced via the names io0-io55.
+
+Valid values for xRX200 pin names:
+  Pinconf pins can be referenced via the names io0-io49.
+
+Valid values for xRX300 pin names:
+  Pinconf pins can be referenced via the names io0-io1,io3-io6,io8-io11,
+						io13-io19,io23-io27,io34-io36,
+						io42-io43,io48-io61.
+
 Example:
 	gpio: pinmux@E100B10 {
-		compatible = "lantiq,pinctrl-xway";
+		compatible = "lantiq,danube-pinctrl";
 		pinctrl-names = "default";
 		pinctrl-0 = <&state_default>;
 
diff --git a/Documentation/devicetree/bindings/pinctrl/pinctrl-mt65xx.txt b/Documentation/devicetree/bindings/pinctrl/pinctrl-mt65xx.txt
index 0480bc3..9ffb0b2 100644
--- a/Documentation/devicetree/bindings/pinctrl/pinctrl-mt65xx.txt
+++ b/Documentation/devicetree/bindings/pinctrl/pinctrl-mt65xx.txt
@@ -4,10 +4,11 @@
 
 Required properties:
 - compatible: value should be one of the following.
-    (a) "mediatek,mt8135-pinctrl", compatible with mt8135 pinctrl.
-    (b) "mediatek,mt8173-pinctrl", compatible with mt8173 pinctrl.
-    (c) "mediatek,mt6397-pinctrl", compatible with mt6397 pinctrl.
-    (d) "mediatek,mt8127-pinctrl", compatible with mt8127 pinctrl.
+	"mediatek,mt2701-pinctrl", compatible with mt2701 pinctrl.
+	"mediatek,mt6397-pinctrl", compatible with mt6397 pinctrl.
+	"mediatek,mt8127-pinctrl", compatible with mt8127 pinctrl.
+	"mediatek,mt8135-pinctrl", compatible with mt8135 pinctrl.
+	"mediatek,mt8173-pinctrl", compatible with mt8173 pinctrl.
 - pins-are-numbered: Specify the subnodes are using numbered pinmux to
   specify pins.
 - gpio-controller : Marks the device node as a gpio controller.
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8996-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/qcom,msm8996-pinctrl.txt
new file mode 100644
index 0000000..e312a71
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8996-pinctrl.txt
@@ -0,0 +1,199 @@
+Qualcomm MSM8996 TLMM block
+
+This binding describes the Top Level Mode Multiplexer block found in the
+MSM8996 platform.
+
+- compatible:
+	Usage: required
+	Value type: <string>
+	Definition: must be "qcom,msm8996-pinctrl"
+
+- reg:
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: the base address and size of the TLMM register space.
+
+- interrupts:
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: should specify the TLMM summary IRQ.
+
+- interrupt-controller:
+	Usage: required
+	Value type: <none>
+	Definition: identifies this node as an interrupt controller
+
+- #interrupt-cells:
+	Usage: required
+	Value type: <u32>
+	Definition: must be 2. Specifying the pin number and flags, as defined
+		    in <dt-bindings/interrupt-controller/irq.h>
+
+- gpio-controller:
+	Usage: required
+	Value type: <none>
+	Definition: identifies this node as a gpio controller
+
+- #gpio-cells:
+	Usage: required
+	Value type: <u32>
+	Definition: must be 2. Specifying the pin number and flags, as defined
+		    in <dt-bindings/gpio/gpio.h>
+
+Please refer to ../gpio/gpio.txt and ../interrupt-controller/interrupts.txt for
+a general description of GPIO and interrupt bindings.
+
+Please refer to pinctrl-bindings.txt in this directory for details of the
+common pinctrl bindings used by client devices, including the meaning of the
+phrase "pin configuration node".
+
+The pin configuration nodes act as a container for an arbitrary number of
+subnodes. Each of these subnodes represents some desired configuration for a
+pin, a group, or a list of pins or groups. This configuration can include the
+mux function to select on those pin(s)/group(s), and various pin configuration
+parameters, such as pull-up, drive strength, etc.
+
+
+PIN CONFIGURATION NODES:
+
+The name of each subnode is not important; all subnodes should be enumerated
+and processed purely based on their content.
+
+Each subnode only affects those parameters that are explicitly listed. In
+other words, a subnode that lists a mux function but no pin configuration
+parameters implies no information about any pin configuration parameters.
+Similarly, a pin subnode that describes a pullup parameter implies no
+information about e.g. the mux function.
+
+
+The following generic properties as defined in pinctrl-bindings.txt are valid
+to specify in a pin configuration subnode:
+
+- pins:
+	Usage: required
+	Value type: <string-array>
+	Definition: List of gpio pins affected by the properties specified in
+		    this subnode.
+
+		    Valid pins are:
+		      gpio0-gpio149
+		        Supports mux, bias and drive-strength
+
+		      sdc1_clk, sdc1_cmd, sdc1_data sdc2_clk, sdc2_cmd,
+		      sdc2_data sdc1_rclk
+		        Supports bias and drive-strength
+
+- function:
+	Usage: required
+	Value type: <string>
+	Definition: Specify the alternative function to be configured for the
+		    specified pins. Functions are only valid for gpio pins.
+		    Valid values are:
+
+		    blsp_uart1, blsp_spi1, blsp_i2c1, blsp_uim1, atest_tsens,
+		    bimc_dte1, dac_calib0, blsp_spi8, blsp_uart8, blsp_uim8,
+		    qdss_cti_trig_out_b, bimc_dte0, dac_calib1, qdss_cti_trig_in_b,
+		    dac_calib2, atest_tsens2, atest_usb1, blsp_spi10, blsp_uart10,
+		    blsp_uim10, atest_bbrx1, atest_usb13, atest_bbrx0, atest_usb12,
+		    mdp_vsync, edp_lcd, blsp_i2c10, atest_gpsadc1, atest_usb11,
+		    atest_gpsadc0, edp_hot, atest_usb10, m_voc, dac_gpio, atest_char,
+		    cam_mclk, pll_bypassnl, qdss_stm7, blsp_i2c8, qdss_tracedata_b,
+		    pll_reset, qdss_stm6, qdss_stm5, qdss_stm4, atest_usb2, cci_i2c,
+		    qdss_stm3, dac_calib3, atest_usb23, atest_char3, dac_calib4,
+		    qdss_stm2, atest_usb22, atest_char2, qdss_stm1, dac_calib5,
+		    atest_usb21, atest_char1, dbg_out, qdss_stm0, dac_calib6,
+		    atest_usb20, atest_char0, dac_calib10, qdss_stm10,
+		    qdss_cti_trig_in_a, cci_timer4, blsp_spi6, blsp_uart6, blsp_uim6,
+		    blsp2_spi, qdss_stm9, qdss_cti_trig_out_a, dac_calib11,
+		    qdss_stm8, cci_timer0, qdss_stm13, dac_calib7, cci_timer1,
+		    qdss_stm12, dac_calib8, cci_timer2, blsp1_spi, qdss_stm11,
+		    dac_calib9, cci_timer3, cci_async, dac_calib12, blsp_i2c6,
+		    qdss_tracectl_a, dac_calib13, qdss_traceclk_a, dac_calib14,
+		    dac_calib15, hdmi_rcv, dac_calib16, hdmi_cec, pwr_modem,
+		    dac_calib17, hdmi_ddc, pwr_nav, dac_calib18, pwr_crypto,
+		    dac_calib19, hdmi_hot, dac_calib20, dac_calib21, pci_e0,
+		    dac_calib22, dac_calib23, dac_calib24, tsif1_sync, dac_calib25,
+		    sd_write, tsif1_error, blsp_spi2, blsp_uart2, blsp_uim2,
+		    qdss_cti, blsp_i2c2, blsp_spi3, blsp_uart3, blsp_uim3, blsp_i2c3,
+		    uim3, blsp_spi9, blsp_uart9, blsp_uim9, blsp10_spi, blsp_i2c9,
+		    blsp_spi7, blsp_uart7, blsp_uim7, qdss_tracedata_a, blsp_i2c7,
+		    qua_mi2s, gcc_gp1_clk_a, ssc_irq, uim4, blsp_spi11, blsp_uart11,
+		    blsp_uim11, gcc_gp2_clk_a, gcc_gp3_clk_a, blsp_i2c11, cri_trng0,
+		    cri_trng1, cri_trng, qdss_stm18, pri_mi2s, qdss_stm17, blsp_spi4,
+		    blsp_uart4, blsp_uim4, qdss_stm16, qdss_stm15, blsp_i2c4,
+		    qdss_stm14, dac_calib26, spkr_i2s, audio_ref, lpass_slimbus,
+		    isense_dbg, tsense_pwm1, tsense_pwm2, btfm_slimbus, ter_mi2s,
+		    qdss_stm22, qdss_stm21, qdss_stm20, qdss_stm19, gcc_gp1_clk_b,
+		    sec_mi2s, blsp_spi5, blsp_uart5, blsp_uim5, gcc_gp2_clk_b,
+		    gcc_gp3_clk_b, blsp_i2c5, blsp_spi12, blsp_uart12, blsp_uim12,
+		    qdss_stm25, qdss_stm31, blsp_i2c12, qdss_stm30, qdss_stm29,
+		    tsif1_clk, qdss_stm28, tsif1_en, tsif1_data, sdc4_cmd, qdss_stm27,
+		    qdss_traceclk_b, tsif2_error, sdc43, vfr_1, qdss_stm26, tsif2_clk,
+		    sdc4_clk, qdss_stm24, tsif2_en, sdc42, qdss_stm23, qdss_tracectl_b,
+		    sd_card, tsif2_data, sdc41, tsif2_sync, sdc40, mdp_vsync_p_b,
+		    ldo_en, mdp_vsync_s_b, ldo_update, blsp11_uart_tx_b, blsp11_uart_rx_b,
+		    blsp11_i2c_sda_b, prng_rosc, blsp11_i2c_scl_b, uim2, uim1, uim_batt,
+		    pci_e2, pa_indicator, adsp_ext, ddr_bist, qdss_tracedata_11,
+		    qdss_tracedata_12, modem_tsync, nav_dr, nav_pps, pci_e1, gsm_tx,
+		    qspi_cs, ssbi2, ssbi1, mss_lte, qspi_clk, qspi0, qspi1, qspi2, qspi3,
+		    gpio
+
+- bias-disable:
+	Usage: optional
+	Value type: <none>
+	Definition: The specified pins should be configued as no pull.
+
+- bias-pull-down:
+	Usage: optional
+	Value type: <none>
+	Definition: The specified pins should be configued as pull down.
+
+- bias-pull-up:
+	Usage: optional
+	Value type: <none>
+	Definition: The specified pins should be configued as pull up.
+
+- output-high:
+	Usage: optional
+	Value type: <none>
+	Definition: The specified pins are configured in output mode, driven
+		    high.
+		    Not valid for sdc pins.
+
+- output-low:
+	Usage: optional
+	Value type: <none>
+	Definition: The specified pins are configured in output mode, driven
+		    low.
+		    Not valid for sdc pins.
+
+- drive-strength:
+	Usage: optional
+	Value type: <u32>
+	Definition: Selects the drive strength for the specified pins, in mA.
+		    Valid values are: 2, 4, 6, 8, 10, 12, 14 and 16
+
+Example:
+
+	tlmm: pinctrl@01010000 {
+		compatible = "qcom,msm8996-pinctrl";
+		reg = <0x01010000 0x300000>;
+		interrupts = <0 208 0>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+
+		uart_console_active: uart_console_active {
+			mux {
+				pins = "gpio4", "gpio5";
+				function = "blsp_uart8";
+			};
+
+			config {
+				pins = "gpio4", "gpio5";
+				drive-strength = <2>;
+				bias-disable;
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.txt b/Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.txt
index 1ae63c0..a90c812 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.txt
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.txt
@@ -14,6 +14,7 @@
 		    "qcom,pm8917-gpio"
 		    "qcom,pm8921-gpio"
 		    "qcom,pm8941-gpio"
+		    "qcom,pm8994-gpio"
 		    "qcom,pma8084-gpio"
 
 - reg:
@@ -79,6 +80,7 @@
 		    gpio1-gpio38 for pm8917
 		    gpio1-gpio44 for pm8921
 		    gpio1-gpio36 for pm8941
+		    gpio1-gpio22 for pm8994
 		    gpio1-gpio22 for pma8084
 
 - function:
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,pmic-mpp.txt b/Documentation/devicetree/bindings/pinctrl/qcom,pmic-mpp.txt
index d7803a2..d74e631 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,pmic-mpp.txt
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,pmic-mpp.txt
@@ -15,6 +15,7 @@
 		    "qcom,pm8917-mpp",
 		    "qcom,pm8921-mpp",
 		    "qcom,pm8941-mpp",
+		    "qcom,pm8994-mpp",
 		    "qcom,pma8084-mpp",
 
 - reg:
diff --git a/Documentation/devicetree/bindings/pinctrl/rockchip,pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/rockchip,pinctrl.txt
index 391ef4b..0cd701b 100644
--- a/Documentation/devicetree/bindings/pinctrl/rockchip,pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/rockchip,pinctrl.txt
@@ -21,7 +21,8 @@
 Required properties for iomux controller:
   - compatible: one of "rockchip,rk2928-pinctrl", "rockchip,rk3066a-pinctrl"
 		       "rockchip,rk3066b-pinctrl", "rockchip,rk3188-pinctrl"
-		       "rockchip,rk3288-pinctrl", "rockchip,rk3368-pinctrl"
+		       "rockchip,rk3228-pinctrl", "rockchip,rk3288-pinctrl"
+		       "rockchip,rk3368-pinctrl"
   - rockchip,grf: phandle referencing a syscon providing the
 	 "general register files"
 
diff --git a/Documentation/devicetree/bindings/pinctrl/samsung-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/samsung-pinctrl.txt
index 9d2a995..6db16b9 100644
--- a/Documentation/devicetree/bindings/pinctrl/samsung-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/samsung-pinctrl.txt
@@ -17,6 +17,7 @@
   - "samsung,exynos4x12-pinctrl": for Exynos4x12 compatible pin-controller.
   - "samsung,exynos5250-pinctrl": for Exynos5250 compatible pin-controller.
   - "samsung,exynos5260-pinctrl": for Exynos5260 compatible pin-controller.
+  - "samsung,exynos5410-pinctrl": for Exynos5410 compatible pin-controller.
   - "samsung,exynos5420-pinctrl": for Exynos5420 compatible pin-controller.
   - "samsung,exynos7-pinctrl": for Exynos7 compatible pin-controller.
 
diff --git a/Documentation/dvb/README.dvb-usb b/Documentation/dvb/README.dvb-usb
index 8eb9226..669dc6c 100644
--- a/Documentation/dvb/README.dvb-usb
+++ b/Documentation/dvb/README.dvb-usb
@@ -45,7 +45,7 @@
 See the LinuxTV DVB Wiki at www.linuxtv.org for a complete list of
 cards/drivers/firmwares:
 
-http://www.linuxtv.org/wiki/index.php/DVB_USB
+https://linuxtv.org/wiki/index.php/DVB_USB
 
 0. History & News:
   2005-06-30 - added support for WideView WT-220U (Thanks to Steve Chang)
@@ -121,7 +121,7 @@
 Have a look at the Wikipage for the DVB-USB-drivers to find out, which firmware
 you need for your device:
 
-http://www.linuxtv.org/wiki/index.php/DVB_USB
+https://linuxtv.org/wiki/index.php/DVB_USB
 
 1.2. Compiling
 
diff --git a/Documentation/dvb/faq.txt b/Documentation/dvb/faq.txt
index 97b1373..a0be920 100644
--- a/Documentation/dvb/faq.txt
+++ b/Documentation/dvb/faq.txt
@@ -76,7 +76,7 @@
 		the TuxBox CVS many interesting DVB applications and the dBox2
 		DVB source
 
-	http://www.linuxtv.org/downloads/	
+	https://linuxtv.org/downloads
 		DVB Swiss Army Knife library and utilities
 
 	http://www.nenie.org/misc/mpsys/
diff --git a/Documentation/dvb/get_dvb_firmware b/Documentation/dvb/get_dvb_firmware
index 91b43d2..1a0a041 100755
--- a/Documentation/dvb/get_dvb_firmware
+++ b/Documentation/dvb/get_dvb_firmware
@@ -152,7 +152,7 @@
 
 sub av7110 {
     my $sourcefile = "dvb-ttpci-01.fw-261d";
-    my $url = "http://www.linuxtv.org/downloads/firmware/$sourcefile";
+    my $url = "https://linuxtv.org/downloads/firmware/$sourcefile";
     my $hash = "603431b6259715a8e88f376a53b64e2f";
     my $outfile = "dvb-ttpci-01.fw";
 
@@ -303,7 +303,7 @@
 }
 
 sub dibusb {
-	my $url = "http://www.linuxtv.org/downloads/firmware/dvb-usb-dibusb-5.0.0.11.fw";
+	my $url = "https://linuxtv.org/downloads/firmware/dvb-usb-dibusb-5.0.0.11.fw";
 	my $outfile = "dvb-dibusb-5.0.0.11.fw";
 	my $hash = "fa490295a527360ca16dcdf3224ca243";
 
@@ -351,7 +351,7 @@
 
 sub or51211 {
     my $fwfile = "dvb-fe-or51211.fw";
-    my $url = "http://linuxtv.org/downloads/firmware/$fwfile";
+    my $url = "https://linuxtv.org/downloads/firmware/$fwfile";
     my $hash = "d830949c771a289505bf9eafc225d491";
 
     checkstandard();
@@ -364,7 +364,7 @@
 
 sub cx231xx {
     my $fwfile = "v4l-cx231xx-avcore-01.fw";
-    my $url = "http://linuxtv.org/downloads/firmware/$fwfile";
+    my $url = "https://linuxtv.org/downloads/firmware/$fwfile";
     my $hash = "7d3bb956dc9df0eafded2b56ba57cc42";
 
     checkstandard();
@@ -376,7 +376,7 @@
 }
 
 sub cx18 {
-    my $url = "http://linuxtv.org/downloads/firmware/";
+    my $url = "https://linuxtv.org/downloads/firmware/";
 
     my %files = (
 	'v4l-cx23418-apu.fw' => '588f081b562f5c653a3db1ad8f65939a',
@@ -450,7 +450,7 @@
 }
 
 sub cx23885 {
-    my $url = "http://linuxtv.org/downloads/firmware/";
+    my $url = "https://linuxtv.org/downloads/firmware/";
 
     my %files = (
 	'v4l-cx23885-avcore-01.fw' => 'a9f8f5d901a7fb42f552e1ee6384f3bb',
@@ -472,7 +472,7 @@
 }
 
 sub pvrusb2 {
-    my $url = "http://linuxtv.org/downloads/firmware/";
+    my $url = "https://linuxtv.org/downloads/firmware/";
 
     my %files = (
 	'v4l-cx25840.fw'           => 'dadb79e9904fc8af96e8111d9cb59320',
@@ -494,7 +494,7 @@
 
 sub or51132_qam {
     my $fwfile = "dvb-fe-or51132-qam.fw";
-    my $url = "http://linuxtv.org/downloads/firmware/$fwfile";
+    my $url = "https://linuxtv.org/downloads/firmware/$fwfile";
     my $hash = "7702e8938612de46ccadfe9b413cb3b5";
 
     checkstandard();
@@ -507,7 +507,7 @@
 
 sub or51132_vsb {
     my $fwfile = "dvb-fe-or51132-vsb.fw";
-    my $url = "http://linuxtv.org/downloads/firmware/$fwfile";
+    my $url = "https://linuxtv.org/downloads/firmware/$fwfile";
     my $hash = "c16208e02f36fc439a557ad4c613364a";
 
     checkstandard();
@@ -519,7 +519,7 @@
 }
 
 sub bluebird {
-	my $url = "http://www.linuxtv.org/download/dvb/firmware/dvb-usb-bluebird-01.fw";
+	my $url = "https://linuxtv.org/download/dvb/firmware/dvb-usb-bluebird-01.fw";
 	my $outfile = "dvb-usb-bluebird-01.fw";
 	my $hash = "658397cb9eba9101af9031302671f49d";
 
@@ -677,7 +677,7 @@
 }
 
 sub drxk_terratec_h5 {
-    my $url = "http://www.linuxtv.org/downloads/firmware/";
+    my $url = "https://linuxtv.org/downloads/firmware/";
     my $hash = "19000dada8e2741162ccc50cc91fa7f1";
     my $fwfile = "dvb-usb-terratec-h5-drxk.fw";
 
diff --git a/Documentation/dvb/readme.txt b/Documentation/dvb/readme.txt
index 0b0380c..8996504 100644
--- a/Documentation/dvb/readme.txt
+++ b/Documentation/dvb/readme.txt
@@ -2,12 +2,12 @@
 =============================================
 
 The main development site and CVS repository for these
-drivers is http://linuxtv.org/.
+drivers is https://linuxtv.org.
 
 The developer mailing list linux-dvb is also hosted there,
-see http://linuxtv.org/lists.php. Please check
-the archive http://linuxtv.org/pipermail/linux-dvb/
-and the Wiki http://linuxtv.org/wiki/
+see https://linuxtv.org/lists.php. Please check
+the archive https://linuxtv.org/pipermail/linux-dvb/
+and the Wiki https://linuxtv.org/wiki/
 before asking newbie questions on the list.
 
 API documentation, utilities and test/example programs
@@ -16,7 +16,7 @@
 We plan to split this into separate packages, but it's not
 been done yet.
 
-http://linuxtv.org/downloads/
+https://linuxtv.org/downloads/
 
 What's inside this directory:
 
diff --git a/Documentation/edac.txt b/Documentation/edac.txt
index 80841a2..f89cfd8 100644
--- a/Documentation/edac.txt
+++ b/Documentation/edac.txt
@@ -1,9 +1,13 @@
 EDAC - Error Detection And Correction
 =====================================
 
-"bluesmoke" was the name for this device driver when it was "out-of-tree"
-and maintained at sourceforge.net.  When it was pushed into 2.6.16 for the
-first time, it was renamed to 'EDAC'.
+"bluesmoke" was the name for this device driver when it
+was "out-of-tree" and maintained at sourceforge.net -
+bluesmoke.sourceforge.net. That site is mostly archaic now and can be
+used only for historical purposes.
+
+When the subsystem was pushed into 2.6.16 for the first time, it was
+renamed to 'EDAC'.
 
 PURPOSE
 -------
diff --git a/Documentation/features/seccomp/seccomp-filter/arch-support.txt b/Documentation/features/seccomp/seccomp-filter/arch-support.txt
index 76d39d6..4f66ec1 100644
--- a/Documentation/features/seccomp/seccomp-filter/arch-support.txt
+++ b/Documentation/features/seccomp/seccomp-filter/arch-support.txt
@@ -33,7 +33,7 @@
     |          sh: | TODO |
     |       sparc: | TODO |
     |        tile: |  ok  |
-    |          um: | TODO |
+    |          um: |  ok  |
     |   unicore32: | TODO |
     |         x86: |  ok  |
     |      xtensa: | TODO |
diff --git a/Documentation/features/time/irq-time-acct/arch-support.txt b/Documentation/features/time/irq-time-acct/arch-support.txt
index e633162..4199ffec 100644
--- a/Documentation/features/time/irq-time-acct/arch-support.txt
+++ b/Documentation/features/time/irq-time-acct/arch-support.txt
@@ -9,7 +9,7 @@
     |       alpha: |  ..  |
     |         arc: | TODO |
     |         arm: |  ok  |
-    |       arm64: |  ..  |
+    |       arm64: |  ok  |
     |       avr32: | TODO |
     |    blackfin: | TODO |
     |         c6x: | TODO |
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 06d4434..619af9b 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -50,8 +50,7 @@
 	int (*rename2) (struct inode *, struct dentry *,
 			struct inode *, struct dentry *, unsigned int);
 	int (*readlink) (struct dentry *, char __user *,int);
-	const char *(*follow_link) (struct dentry *, void **);
-	void (*put_link) (struct inode *, void *);
+	const char *(*get_link) (struct dentry *, struct inode *, void **);
 	void (*truncate) (struct inode *);
 	int (*permission) (struct inode *, int, unsigned int);
 	int (*get_acl)(struct inode *, int);
@@ -83,8 +82,7 @@
 rename:		yes (all)	(see below)
 rename2:	yes (all)	(see below)
 readlink:	no
-follow_link:	no
-put_link:	no
+get_link:	no
 setattr:	yes
 permission:	no (may not block if called in rcu-walk mode)
 get_acl:	no
diff --git a/Documentation/filesystems/configfs/configfs.txt b/Documentation/filesystems/configfs/configfs.txt
index af68efd..e5fe521 100644
--- a/Documentation/filesystems/configfs/configfs.txt
+++ b/Documentation/filesystems/configfs/configfs.txt
@@ -51,15 +51,27 @@
 An item is created via mkdir(2).  The item's attributes will also
 appear at this time.  readdir(3) can determine what the attributes are,
 read(2) can query their default values, and write(2) can store new
-values.  Like sysfs, attributes should be ASCII text files, preferably
-with only one value per file.  The same efficiency caveats from sysfs
-apply.  Don't mix more than one attribute in one attribute file.
+values.  Don't mix more than one attribute in one attribute file.
 
-Like sysfs, configfs expects write(2) to store the entire buffer at
-once.  When writing to configfs attributes, userspace processes should
-first read the entire file, modify the portions they wish to change, and
-then write the entire buffer back.  Attribute files have a maximum size
-of one page (PAGE_SIZE, 4096 on i386).
+There are two types of configfs attributes:
+
+* Normal attributes, which similar to sysfs attributes, are small ASCII text
+files, with a maximum size of one page (PAGE_SIZE, 4096 on i386).  Preferably
+only one value per file should be used, and the same caveats from sysfs apply.
+Configfs expects write(2) to store the entire buffer at once.  When writing to
+normal configfs attributes, userspace processes should first read the entire
+file, modify the portions they wish to change, and then write the entire
+buffer back.
+
+* Binary attributes, which are somewhat similar to sysfs binary attributes,
+but with a few slight changes to semantics.  The PAGE_SIZE limitation does not
+apply, but the whole binary item must fit in single kernel vmalloc'ed buffer.
+The write(2) calls from user space are buffered, and the attributes'
+write_bin_attribute method will be invoked on the final close, therefore it is
+imperative for user-space to check the return code of close(2) in order to
+verify that the operation finished successfully.
+To avoid a malicious user OOMing the kernel, there's a per-binary attribute
+maximum buffer value.
 
 When an item needs to be destroyed, remove it with rmdir(2).  An
 item cannot be destroyed if any other item has a link to it (via
@@ -171,6 +183,7 @@
 		struct configfs_item_operations         *ct_item_ops;
 		struct configfs_group_operations        *ct_group_ops;
 		struct configfs_attribute               **ct_attrs;
+		struct configfs_bin_attribute		**ct_bin_attrs;
 	};
 
 The most basic function of a config_item_type is to define what
@@ -201,6 +214,32 @@
 attribute is writable and provides a ->store  method, that method will be
 be called whenever userspace asks for a write(2) on the attribute.
 
+[struct configfs_bin_attribute]
+
+	struct configfs_attribute {
+		struct configfs_attribute	cb_attr;
+		void				*cb_private;
+		size_t				cb_max_size;
+	};
+
+The binary attribute is used when the one needs to use binary blob to
+appear as the contents of a file in the item's configfs directory.
+To do so add the binary attribute to the NULL-terminated array
+config_item_type->ct_bin_attrs, and the item appears in configfs, the
+attribute file will appear with the configfs_bin_attribute->cb_attr.ca_name
+filename.  configfs_bin_attribute->cb_attr.ca_mode specifies the file
+permissions.
+The cb_private member is provided for use by the driver, while the
+cb_max_size member specifies the maximum amount of vmalloc buffer
+to be used.
+
+If binary attribute is readable and the config_item provides a
+ct_item_ops->read_bin_attribute() method, that method will be called
+whenever userspace asks for a read(2) on the attribute.  The converse
+will happen for write(2). The reads/writes are bufferred so only a
+single read/write will occur; the attributes' need not concern itself
+with it.
+
 [struct config_group]
 
 A config_item cannot live in a vacuum.  The only way one can be created
diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting
index f24d1b8..0f88e60 100644
--- a/Documentation/filesystems/porting
+++ b/Documentation/filesystems/porting
@@ -504,3 +504,20 @@
 [mandatory]
 	__fd_install() & fd_install() can now sleep. Callers should not
 	hold a spinlock	or other resources that do not allow a schedule.
+--
+[mandatory]
+	any symlink that might use page_follow_link_light/page_put_link() must
+	have inode_nohighmem(inode) called before anything might start playing with
+	its pagecache.
+--
+[mandatory]
+	->follow_link() is replaced with ->get_link(); same API, except that
+		* ->get_link() gets inode as a separate argument
+		* ->get_link() may be called in RCU mode - in that case NULL
+		  dentry is passed
+--
+[mandatory]
+	->get_link() gets struct delayed_call *done now, and should do
+	set_delayed_call() where it used to set *cookie.
+	->put_link() is gone - just give the destructor to set_delayed_call()
+	in ->get_link().
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 8c6f07a..b02a7d5 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -350,8 +350,8 @@
 	int (*rename2) (struct inode *, struct dentry *,
 			struct inode *, struct dentry *, unsigned int);
 	int (*readlink) (struct dentry *, char __user *,int);
-	const char *(*follow_link) (struct dentry *, void **);
-	void (*put_link) (struct inode *, void *);
+	const char *(*get_link) (struct dentry *, struct inode *,
+				 struct delayed_call *);
 	int (*permission) (struct inode *, int);
 	int (*get_acl)(struct inode *, int);
 	int (*setattr) (struct dentry *, struct iattr *);
@@ -434,20 +434,19 @@
   readlink: called by the readlink(2) system call. Only required if
 	you want to support reading symbolic links
 
-  follow_link: called by the VFS to follow a symbolic link to the
+  get_link: called by the VFS to follow a symbolic link to the
 	inode it points to.  Only required if you want to support
 	symbolic links.  This method returns the symlink body
 	to traverse (and possibly resets the current position with
 	nd_jump_link()).  If the body won't go away until the inode
 	is gone, nothing else is needed; if it needs to be otherwise
-	pinned, the data needed to release whatever we'd grabbed
-	is to be stored in void * variable passed by address to
-	follow_link() instance.
-
-  put_link: called by the VFS to release resources allocated by
-	follow_link().  The cookie stored by follow_link() is passed
-	to this method as the last parameter; only called when
-	cookie isn't NULL.
+	pinned, arrange for its release by having get_link(..., ..., done)
+	do set_delayed_call(done, destructor, argument).
+	In that case destructor(argument) will be called once VFS is
+	done with the body you've returned.
+	May be called in RCU mode; that is indicated by NULL dentry
+	argument.  If request can't be handled without leaving RCU mode,
+	have it return ERR_PTR(-ECHILD).
 
   permission: called by the VFS to check for access rights on a POSIX-like
   	filesystem.
diff --git a/Documentation/hwmon/htu21 b/Documentation/hwmon/htu21
deleted file mode 100644
index f39a215..0000000
--- a/Documentation/hwmon/htu21
+++ /dev/null
@@ -1,46 +0,0 @@
-Kernel driver htu21
-===================
-
-Supported chips:
-  * Measurement Specialties HTU21D
-    Prefix: 'htu21'
-    Addresses scanned: none
-    Datasheet: Publicly available at the Measurement Specialties website
-    http://www.meas-spec.com/downloads/HTU21D.pdf
-
-
-Author:
-  William Markezana <william.markezana@meas-spec.com>
-
-Description
------------
-
-The HTU21D is a humidity and temperature sensor in a DFN package of
-only 3 x 3 mm footprint and 0.9 mm height.
-
-The devices communicate with the I2C protocol. All sensors are set to the
-same I2C address 0x40, so an entry with I2C_BOARD_INFO("htu21", 0x40) can
-be used in the board setup code.
-
-This driver does not auto-detect devices. You will have to instantiate the
-devices explicitly. Please see Documentation/i2c/instantiating-devices
-for details.
-
-sysfs-Interface
----------------
-
-temp1_input - temperature input
-humidity1_input - humidity input
-
-Notes
------
-
-The driver uses the default resolution settings of 12 bit for humidity and 14
-bit for temperature, which results in typical measurement times of 11 ms for
-humidity and 44 ms for temperature. To keep self heating below 0.1 degree
-Celsius, the device should not be active for more than 10% of the time. For
-this reason, the driver performs no more than two measurements per second and
-reports cached information if polled more frequently.
-
-Different resolutions, the on-chip heater, using the CRC checksum and reading
-the serial number are not supported yet.
diff --git a/Documentation/hwmon/ltc3815 b/Documentation/hwmon/ltc3815
new file mode 100644
index 0000000..eb7db2d
--- /dev/null
+++ b/Documentation/hwmon/ltc3815
@@ -0,0 +1,61 @@
+Kernel driver ltc3815
+=====================
+
+Supported chips:
+  * Linear Technology LTC3815
+    Prefix: 'ltc3815'
+    Addresses scanned: -
+    Datasheet: http://www.linear.com/product/ltc3815
+
+Author: Guenter Roeck <linux@roeck-us.net>
+
+
+Description
+-----------
+
+LTC3815 is a Monolithic Synchronous DC/DC Step-Down Converter.
+
+
+Usage Notes
+-----------
+
+This driver does not probe for PMBus devices. You will have to instantiate
+devices explicitly.
+
+Example: the following commands will load the driver for an LTC3815
+at address 0x20 on I2C bus #1:
+
+# modprobe ltc3815
+# echo ltc3815 0x20 > /sys/bus/i2c/devices/i2c-1/new_device
+
+
+Sysfs attributes
+----------------
+
+in1_label		"vin"
+in1_input		Measured input voltage.
+in1_alarm		Input voltage alarm.
+in1_highest		Highest input voltage.
+in1_reset_history	Reset input voltage history.
+
+in2_label		"vout1".
+in2_input		Measured output voltage.
+in2_alarm		Output voltage alarm.
+in2_highest		Highest output voltage.
+in2_reset_history	Reset output voltage history.
+
+temp1_input		Measured chip temperature.
+temp1_alarm		Temperature alarm.
+temp1_highest		Highest measured temperature.
+temp1_reset_history	Reset temperature history.
+
+curr1_label		"iin".
+curr1_input		Measured input current.
+curr1_highest		Highest input current.
+curr1_reset_history	Reset input current history.
+
+curr2_label		"iout1".
+curr2_input		Measured output current.
+curr2_alarm		Output current alarm.
+curr2_highest		Highest output current.
+curr2_reset_history	Reset output current history.
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 742f69d..1a8169b 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -472,6 +472,15 @@
 			Change the amount of debugging information output
 			when initialising the APIC and IO-APIC components.
 
+	apic_extnmi=	[APIC,X86] External NMI delivery setting
+			Format: { bsp (default) | all | none }
+			bsp:  External NMI is delivered only to CPU 0
+			all:  External NMIs are broadcast to all CPUs as a
+			      backup of CPU 0
+			none: External NMI is masked for all CPUs. This is
+			      useful so that a dump capture kernel won't be
+			      shot down by NMI
+
 	autoconf=	[IPV6]
 			See Documentation/networking/ipv6.txt.
 
@@ -3296,18 +3305,35 @@
 	rcutorture.verbose= [KNL]
 			Enable additional printk() statements.
 
+	rcupdate.rcu_cpu_stall_suppress= [KNL]
+			Suppress RCU CPU stall warning messages.
+
+	rcupdate.rcu_cpu_stall_timeout= [KNL]
+			Set timeout for RCU CPU stall warning messages.
+
 	rcupdate.rcu_expedited= [KNL]
 			Use expedited grace-period primitives, for
 			example, synchronize_rcu_expedited() instead
 			of synchronize_rcu().  This reduces latency,
 			but can increase CPU utilization, degrade
 			real-time latency, and degrade energy efficiency.
+			No effect on CONFIG_TINY_RCU kernels.
 
-	rcupdate.rcu_cpu_stall_suppress= [KNL]
-			Suppress RCU CPU stall warning messages.
+	rcupdate.rcu_normal= [KNL]
+			Use only normal grace-period primitives,
+			for example, synchronize_rcu() instead of
+			synchronize_rcu_expedited().  This improves
+			real-time latency, CPU utilization, and
+			energy efficiency, but can expose users to
+			increased grace-period latency.  This parameter
+			overrides rcupdate.rcu_expedited.  No effect on
+			CONFIG_TINY_RCU kernels.
 
-	rcupdate.rcu_cpu_stall_timeout= [KNL]
-			Set timeout for RCU CPU stall warning messages.
+	rcupdate.rcu_normal_after_boot= [KNL]
+			Once boot has completed (that is, after
+			rcu_end_inkernel_boot() has been invoked), use
+			only normal grace-period primitives.  No effect
+			on CONFIG_TINY_RCU kernels.
 
 	rcupdate.rcu_task_stall_timeout= [KNL]
 			Set timeout in jiffies for RCU task stall warning
@@ -4114,6 +4140,15 @@
 			or other driver-specific files in the
 			Documentation/watchdog/ directory.
 
+	workqueue.watchdog_thresh=
+			If CONFIG_WQ_WATCHDOG is configured, workqueue can
+			warn stall conditions and dump internal state to
+			help debugging.  0 disables workqueue stall
+			detection; otherwise, it's the stall threshold
+			duration in seconds.  The default value is 30 and
+			it can be updated at runtime by writing to the
+			corresponding sysfs file.
+
 	workqueue.disable_numa
 			By default, all work items queued to unbound
 			workqueues are affine to the NUMA nodes they're
diff --git a/Documentation/leds/leds-class.txt b/Documentation/leds/leds-class.txt
index 62261c0..d406d98 100644
--- a/Documentation/leds/leds-class.txt
+++ b/Documentation/leds/leds-class.txt
@@ -52,6 +52,19 @@
 of the name don't apply, just leave that section blank.
 
 
+Brightness setting API
+======================
+
+LED subsystem core exposes following API for setting brightness:
+
+    - led_set_brightness : it is guaranteed not to sleep, passing LED_OFF stops
+		blinking,
+    - led_set_brightness_sync : for use cases when immediate effect is desired -
+		it can block the caller for the time required for accessing
+		device registers and can sleep, passing LED_OFF stops hardware
+		blinking, returns -EBUSY if software blink fallback is enabled.
+
+
 Hardware accelerated blink of LEDs
 ==================================
 
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index aef9487..a61be39 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -194,7 +194,7 @@
  (*) On any given CPU, dependent memory accesses will be issued in order, with
      respect to itself.  This means that for:
 
-	WRITE_ONCE(Q, P); smp_read_barrier_depends(); D = READ_ONCE(*Q);
+	Q = READ_ONCE(P); smp_read_barrier_depends(); D = READ_ONCE(*Q);
 
      the CPU will issue the following memory operations:
 
@@ -202,9 +202,9 @@
 
      and always in that order.  On most systems, smp_read_barrier_depends()
      does nothing, but it is required for DEC Alpha.  The READ_ONCE()
-     and WRITE_ONCE() are required to prevent compiler mischief.  Please
-     note that you should normally use something like rcu_dereference()
-     instead of open-coding smp_read_barrier_depends().
+     is required to prevent compiler mischief.  Please note that you
+     should normally use something like rcu_dereference() instead of
+     open-coding smp_read_barrier_depends().
 
  (*) Overlapping loads and stores within a particular CPU will appear to be
      ordered within that CPU.  This means that for:
@@ -1673,8 +1673,8 @@
  (*) smp_store_mb(var, value)
 
      This assigns the value to the variable and then inserts a full memory
-     barrier after it, depending on the function.  It isn't guaranteed to
-     insert anything more than a compiler barrier in a UP compilation.
+     barrier after it.  It isn't guaranteed to insert anything more than a
+     compiler barrier in a UP compilation.
 
 
  (*) smp_mb__before_atomic();
diff --git a/Documentation/printk-formats.txt b/Documentation/printk-formats.txt
index b784c270..6389551 100644
--- a/Documentation/printk-formats.txt
+++ b/Documentation/printk-formats.txt
@@ -250,6 +250,12 @@
 
 	Passed by reference.
 
+block_device names:
+
+	%pg	sda, sda1 or loop0p1
+
+	For printing name of block_device pointers.
+
 struct va_format:
 
 	%pV
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index af70d15..73c6b1e 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -551,6 +551,21 @@
 
 ==============================================================
 
+panic_on_io_nmi:
+
+Controls the kernel's behavior when a CPU receives an NMI caused by
+an IO error.
+
+0: try to continue operation (default)
+
+1: panic immediately. The IO error triggered an NMI. This indicates a
+   serious system condition which could result in IO data corruption.
+   Rather than continuing, panicking might be a better choice. Some
+   servers issue this sort of NMI when the dump button is pushed,
+   and you can use this option to take a crash dump.
+
+==============================================================
+
 panic_on_oops:
 
 Controls the kernel's behaviour when an oops or BUG is encountered.
diff --git a/Documentation/trace/events-msr.txt b/Documentation/trace/events-msr.txt
new file mode 100644
index 0000000..78c383b
--- /dev/null
+++ b/Documentation/trace/events-msr.txt
@@ -0,0 +1,37 @@
+
+The x86 kernel supports tracing most MSR (Model Specific Register) accesses.
+To see the definition of the MSRs on Intel systems please see the SDM
+at http://www.intel.com/sdm (Volume 3)
+
+Available trace points:
+
+/sys/kernel/debug/tracing/events/msr/
+
+Trace MSR reads
+
+read_msr
+
+msr: MSR number
+val: Value written
+failed: 1 if the access failed, otherwise 0
+
+
+Trace MSR writes
+
+write_msr
+
+msr: MSR number
+val: Value written
+failed: 1 if the access failed, otherwise 0
+
+
+Trace RDPMC in kernel
+
+rdpmc
+
+The trace data can be post processed with the postprocess/decode_msr.py script
+
+cat /sys/kernel/debug/tracing/trace | decode_msr.py /usr/src/linux/include/asm/msr-index.h
+
+to add symbolic MSR names.
+
diff --git a/Documentation/trace/postprocess/decode_msr.py b/Documentation/trace/postprocess/decode_msr.py
new file mode 100644
index 0000000..0ab40e0
--- /dev/null
+++ b/Documentation/trace/postprocess/decode_msr.py
@@ -0,0 +1,37 @@
+#!/usr/bin/python
+# add symbolic names to read_msr / write_msr in trace
+# decode_msr msr-index.h < trace
+import sys
+import re
+
+msrs = dict()
+
+with open(sys.argv[1] if len(sys.argv) > 1 else "msr-index.h", "r") as f:
+	for j in f:
+		m = re.match(r'#define (MSR_\w+)\s+(0x[0-9a-fA-F]+)', j)
+		if m:
+			msrs[int(m.group(2), 16)] = m.group(1)
+
+extra_ranges = (
+	( "MSR_LASTBRANCH_%d_FROM_IP", 0x680, 0x69F ),
+	( "MSR_LASTBRANCH_%d_TO_IP", 0x6C0, 0x6DF ),
+	( "LBR_INFO_%d", 0xdc0, 0xddf ),
+)
+
+for j in sys.stdin:
+	m = re.search(r'(read|write)_msr:\s+([0-9a-f]+)', j)
+	if m:
+		r = None
+		num = int(m.group(2), 16)
+		if num in msrs:
+			r = msrs[num]
+		else:
+			for er in extra_ranges:
+				if er[1] <= num <= er[2]:
+					r = er[0] % (num - er[1],)
+					break
+		if r:
+			j = j.replace(" " + m.group(2), " " + r + "(" + m.group(2) + ")")
+	print j,
+
+
diff --git a/Documentation/video4linux/API.html b/Documentation/video4linux/API.html
index 256f8ef..eaf948c 100644
--- a/Documentation/video4linux/API.html
+++ b/Documentation/video4linux/API.html
@@ -9,7 +9,7 @@
   <table border="0">
    <tr>
     <td>
-     <a href="http://linuxtv.org/downloads/legacy/video4linux/API/V4L1_API.html">V4L original API</a>
+     <a href="https://linuxtv.org/downloads/legacy/video4linux/API/V4L1_API.html">V4L original API</a>
     </td>
     <td>
      Obsoleted by V4L2 API
diff --git a/Documentation/video4linux/CARDLIST.em28xx b/Documentation/video4linux/CARDLIST.em28xx
index 9e57ce4..6720999 100644
--- a/Documentation/video4linux/CARDLIST.em28xx
+++ b/Documentation/video4linux/CARDLIST.em28xx
@@ -41,8 +41,8 @@
  40 -> Plextor ConvertX PX-TV100U               (em2861)        [093b:a005]
  41 -> Kworld 350 U DVB-T                       (em2870)        [eb1a:e350]
  42 -> Kworld 355 U DVB-T                       (em2870)        [eb1a:e355,eb1a:e357,eb1a:e359]
- 43 -> Terratec Cinergy T XS                    (em2870)        [0ccd:0043]
- 44 -> Terratec Cinergy T XS (MT2060)           (em2870)
+ 43 -> Terratec Cinergy T XS                    (em2870)
+ 44 -> Terratec Cinergy T XS (MT2060)           (em2870)        [0ccd:0043]
  45 -> Pinnacle PCTV DVB-T                      (em2870)
  46 -> Compro, VideoMate U3                     (em2870)        [185b:2870]
  47 -> KWorld DVB-T 305U                        (em2880)        [eb1a:e305]
diff --git a/Documentation/video4linux/fimc.txt b/Documentation/video4linux/fimc.txt
index e0c6b8b..4fab231b 100644
--- a/Documentation/video4linux/fimc.txt
+++ b/Documentation/video4linux/fimc.txt
@@ -58,7 +58,7 @@
 4.1. Media device interface
 
 The driver supports Media Controller API as defined at
-http://linuxtv.org/downloads/v4l-dvb-apis/media_common.html
+https://linuxtv.org/downloads/v4l-dvb-apis/media_common.html
 The media device driver name is "SAMSUNG S5P FIMC".
 
 The purpose of this interface is to allow changing assignment of FIMC instances
@@ -83,11 +83,11 @@
 4.3. Capture video node
 
 The driver supports V4L2 Video Capture Interface as defined at:
-http://linuxtv.org/downloads/v4l-dvb-apis/devices.html
+https://linuxtv.org/downloads/v4l-dvb-apis/devices.html
 
 At the capture and mem-to-mem video nodes only the multi-planar API is
 supported. For more details see:
-http://linuxtv.org/downloads/v4l-dvb-apis/planar-apis.html
+https://linuxtv.org/downloads/v4l-dvb-apis/planar-apis.html
 
 4.4. Camera capture subdevs
 
diff --git a/Documentation/video4linux/omap4_camera.txt b/Documentation/video4linux/omap4_camera.txt
index 25d9b40..a6734aa 100644
--- a/Documentation/video4linux/omap4_camera.txt
+++ b/Documentation/video4linux/omap4_camera.txt
@@ -47,7 +47,7 @@
 File list
 ---------
 drivers/staging/media/omap4iss/
-include/media/omap4iss.h
+include/linux/platform_data/media/omap4iss.h
 
 References
 ----------
diff --git a/Documentation/video4linux/si4713.txt b/Documentation/video4linux/si4713.txt
index 2e7392a..2ddc6b0 100644
--- a/Documentation/video4linux/si4713.txt
+++ b/Documentation/video4linux/si4713.txt
@@ -157,7 +157,7 @@
 }
 
 The struct si4713_rnl and SI4713_IOC_MEASURE_RNL are defined under
-include/media/si4713.h.
+include/linux/platform_data/media/si4713.h.
 
 Stereo/Mono and RDS subchannels
 ===============================
diff --git a/Documentation/video4linux/v4l2-pci-skeleton.c b/Documentation/video4linux/v4l2-pci-skeleton.c
index 95ae828..79af0c0 100644
--- a/Documentation/video4linux/v4l2-pci-skeleton.c
+++ b/Documentation/video4linux/v4l2-pci-skeleton.c
@@ -163,11 +163,10 @@
  * minimum number: many DMA engines need a minimum of 2 buffers in the
  * queue and you need to have another available for userspace processing.
  */
-static int queue_setup(struct vb2_queue *vq, const void *parg,
+static int queue_setup(struct vb2_queue *vq,
 		       unsigned int *nbuffers, unsigned int *nplanes,
 		       unsigned int sizes[], void *alloc_ctxs[])
 {
-	const struct v4l2_format *fmt = parg;
 	struct skeleton *skel = vb2_get_drv_priv(vq);
 
 	skel->field = skel->format.field;
@@ -183,12 +182,12 @@
 
 	if (vq->num_buffers + *nbuffers < 3)
 		*nbuffers = 3 - vq->num_buffers;
-
-	if (fmt && fmt->fmt.pix.sizeimage < skel->format.sizeimage)
-		return -EINVAL;
-	*nplanes = 1;
-	sizes[0] = fmt ? fmt->fmt.pix.sizeimage : skel->format.sizeimage;
 	alloc_ctxs[0] = skel->alloc_ctx;
+
+	if (*nplanes)
+		return sizes[0] < skel->format.sizeimage ? -EINVAL : 0;
+	*nplanes = 1;
+	sizes[0] = skel->format.sizeimage;
 	return 0;
 }
 
@@ -509,7 +508,7 @@
 		return -EINVAL;
 
 	/* Return 0 if the new timings are the same as the current timings. */
-	if (v4l2_match_dv_timings(timings, &skel->timings, 0))
+	if (v4l2_match_dv_timings(timings, &skel->timings, 0, false))
 		return 0;
 
 	/*
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 092ee9f..053f613 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1451,6 +1451,7 @@
 		struct kvm_irq_routing_irqchip irqchip;
 		struct kvm_irq_routing_msi msi;
 		struct kvm_irq_routing_s390_adapter adapter;
+		struct kvm_irq_routing_hv_sint hv_sint;
 		__u32 pad[8];
 	} u;
 };
@@ -1459,6 +1460,7 @@
 #define KVM_IRQ_ROUTING_IRQCHIP 1
 #define KVM_IRQ_ROUTING_MSI 2
 #define KVM_IRQ_ROUTING_S390_ADAPTER 3
+#define KVM_IRQ_ROUTING_HV_SINT 4
 
 No flags are specified so far, the corresponding field must be set to zero.
 
@@ -1482,6 +1484,10 @@
 	__u32 adapter_id;
 };
 
+struct kvm_irq_routing_hv_sint {
+	__u32 vcpu;
+	__u32 sint;
+};
 
 4.53 KVM_ASSIGN_SET_MSIX_NR (deprecated)
 
@@ -3331,6 +3337,28 @@
 it is still asserted.  Vector is the LAPIC interrupt vector for which the
 EOI was received.
 
+		struct kvm_hyperv_exit {
+#define KVM_EXIT_HYPERV_SYNIC          1
+			__u32 type;
+			union {
+				struct {
+					__u32 msr;
+					__u64 control;
+					__u64 evt_page;
+					__u64 msg_page;
+				} synic;
+			} u;
+		};
+		/* KVM_EXIT_HYPERV */
+                struct kvm_hyperv_exit hyperv;
+Indicates that the VCPU exits into userspace to process some tasks
+related to Hyper-V emulation.
+Valid values for 'type' are:
+	KVM_EXIT_HYPERV_SYNIC -- synchronously notify user-space about
+Hyper-V SynIC state change. Notification is used to remap SynIC
+event/message pages and to enable/disable SynIC messages/events processing
+in userspace.
+
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -3685,3 +3713,16 @@
 H_RANDOM hypercall backed by a hardware random-number generator.
 If present, the kernel H_RANDOM handler can be enabled for guest use
 with the KVM_CAP_PPC_ENABLE_HCALL capability.
+
+8.2 KVM_CAP_HYPERV_SYNIC
+
+Architectures: x86
+This capability, if KVM_CHECK_EXTENSION indicates that it is
+available, means that that the kernel has an implementation of the
+Hyper-V Synthetic interrupt controller(SynIC). Hyper-V SynIC is
+used to support Windows Hyper-V based guest paravirt drivers(VMBus).
+
+In order to use SynIC, it has to be activated by setting this
+capability via KVM_ENABLE_CAP ioctl on the vcpu fd. Note that this
+will disable the use of APIC hardware virtualization even if supported
+by the CPU, as it's incompatible with SynIC auto-EOI behavior.
diff --git a/Documentation/virtual/kvm/devices/vm.txt b/Documentation/virtual/kvm/devices/vm.txt
index 2d09d1e..f083a16 100644
--- a/Documentation/virtual/kvm/devices/vm.txt
+++ b/Documentation/virtual/kvm/devices/vm.txt
@@ -37,7 +37,8 @@
 Allows userspace to query the actual limit and set a new limit for
 the maximum guest memory size. The limit will be rounded up to
 2048 MB, 4096 GB, 8192 TB respectively, as this limit is governed by
-the number of page table levels.
+the number of page table levels. In the case that there is no limit we will set
+the limit to KVM_S390_NO_MEM_LIMIT (U64_MAX).
 
 2. GROUP: KVM_S390_VM_CPU_MODEL
 Architectures: s390
diff --git a/Documentation/virtual/kvm/mmu.txt b/Documentation/virtual/kvm/mmu.txt
index 3a4d681..daf9c0f 100644
--- a/Documentation/virtual/kvm/mmu.txt
+++ b/Documentation/virtual/kvm/mmu.txt
@@ -203,10 +203,10 @@
     page cannot be destroyed.  See role.invalid.
   parent_ptes:
     The reverse mapping for the pte/ptes pointing at this page's spt. If
-    parent_ptes bit 0 is zero, only one spte points at this pages and
+    parent_ptes bit 0 is zero, only one spte points at this page and
     parent_ptes points at this single spte, otherwise, there exists multiple
     sptes pointing at this page and (parent_ptes & ~0x1) points at a data
-    structure with a list of parent_ptes.
+    structure with a list of parent sptes.
   unsync:
     If true, then the translations in this page may not match the guest's
     translation.  This is equivalent to the state of the tlb when a pte is
diff --git a/MAINTAINERS b/MAINTAINERS
index 74b84d4..14ef6ec 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -206,7 +206,7 @@
 A8293 MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/anttip/media_tree.git
@@ -404,7 +404,7 @@
 L:	linux-media@vger.kernel.org
 S:	Maintained
 F:	drivers/media/i2c/adp1653.c
-F:	include/media/adp1653.h
+F:	include/media/i2c/adp1653.h
 
 ADP5520 BACKLIGHT DRIVER WITH IO EXPANDER (ADP5520/ADP5501)
 M:	Michael Hennerich <michael.hennerich@analog.com>
@@ -475,7 +475,7 @@
 AF9013 MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/anttip/media_tree.git
@@ -485,7 +485,7 @@
 AF9033 MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/anttip/media_tree.git
@@ -531,7 +531,7 @@
 M:	Hans Verkuil <hverkuil@xs4all.nl>
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
-W:	http://linuxtv.org
+W:	https://linuxtv.org
 S:	Maintained
 F:	drivers/media/radio/radio-aimslab*
 
@@ -545,7 +545,7 @@
 AIRSPY MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/anttip/media_tree.git
@@ -623,9 +623,9 @@
 F:	include/linux/ccp.h
 
 AMD FAM15H PROCESSOR POWER MONITORING DRIVER
-M:	Andreas Herrmann <herrmann.der.user@googlemail.com>
+M:	Huang Rui <ray.huang@amd.com>
 L:	lm-sensors@lm-sensors.org
-S:	Maintained
+S:	Supported
 F:	Documentation/hwmon/fam15h_power
 F:	drivers/hwmon/fam15h_power.c
 
@@ -1782,7 +1782,7 @@
 T:	git git://linuxtv.org/media_tree.git
 S:	Maintained
 F:	drivers/media/i2c/as3645a.c
-F:	include/media/as3645a.h
+F:	include/media/i2c/as3645a.h
 
 ASC7621 HARDWARE MONITOR DRIVER
 M:	George Joseph <george.joseph@fairview5.com>
@@ -1905,7 +1905,6 @@
 M:	Ludovic Desroches <ludovic.desroches@atmel.com>
 S:	Maintained
 F:	drivers/mmc/host/atmel-mci.c
-F:	drivers/mmc/host/atmel-mci-regs.h
 
 ATMEL AT91 / AT32 SERIAL DRIVER
 M:	Nicolas Ferre <nicolas.ferre@atmel.com>
@@ -2073,7 +2072,7 @@
 AZ6007 DVB DRIVER
 M:	Mauro Carvalho Chehab <mchehab@osg.samsung.com>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org
+W:	https://linuxtv.org
 T:	git git://linuxtv.org/media_tree.git
 S:	Maintained
 F:	drivers/media/usb/dvb-usb-v2/az6007.c
@@ -2082,7 +2081,7 @@
 M:	Hans Verkuil <hverkuil@xs4all.nl>
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
-W:	http://linuxtv.org
+W:	https://linuxtv.org
 S:	Maintained
 F:	drivers/media/radio/radio-aztech*
 
@@ -2135,7 +2134,7 @@
 M:	Fabien Dessenne <fabien.dessenne@st.com>
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
-W:	http://linuxtv.org
+W:	https://linuxtv.org
 S:	Supported
 F:	drivers/media/platform/sti/bdisp
 
@@ -2528,7 +2527,7 @@
 BTTV VIDEO4LINUX DRIVER
 M:	Mauro Carvalho Chehab <mchehab@osg.samsung.com>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org
+W:	https://linuxtv.org
 T:	git git://linuxtv.org/media_tree.git
 S:	Odd fixes
 F:	Documentation/video4linux/bttv/
@@ -2567,7 +2566,7 @@
 M:	Hans Verkuil <hverkuil@xs4all.nl>
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
-W:	http://linuxtv.org
+W:	https://linuxtv.org
 S:	Maintained
 F:	drivers/media/radio/radio-cadet*
 
@@ -2860,7 +2859,7 @@
 M:	Hans Verkuil <hans.verkuil@cisco.com>
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
-W:	http://linuxtv.org
+W:	https://linuxtv.org
 S:	Supported
 F:	drivers/media/pci/cobalt/
 
@@ -2948,7 +2947,8 @@
 
 CONFIGFS
 M:	Joel Becker <jlbec@evilplan.org>
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jlbec/configfs.git
+M:	Christoph Hellwig <hch@lst.de>
+T:	git git://git.infradead.org/users/hch/configfs.git
 S:	Supported
 F:	fs/configfs/
 F:	include/linux/configfs.h
@@ -3105,6 +3105,15 @@
 F:	crypto/ansi_cprng.c
 F:	crypto/rng.c
 
+CS3308 MEDIA DRIVER
+M:	Hans Verkuil <hverkuil@xs4all.nl>
+L:	linux-media@vger.kernel.org
+T:	git git://linuxtv.org/media_tree.git
+W:	http://linuxtv.org
+S:	Odd Fixes
+F:	drivers/media/i2c/cs3308.c
+F:	drivers/media/i2c/cs3308.h
+
 CS5535 Audio ALSA driver
 M:	Jaya Kumar <jayakumar.alsa@gmail.com>
 S:	Maintained
@@ -3120,7 +3129,7 @@
 L:	ivtv-devel@ivtvdriver.org (subscribers-only)
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
-W:	http://linuxtv.org
+W:	https://linuxtv.org
 W:	http://www.ivtvdriver.org/index.php/Cx18
 S:	Maintained
 F:	Documentation/video4linux/cx18.txt
@@ -3131,7 +3140,7 @@
 M:	Hans Verkuil <hverkuil@xs4all.nl>
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
-W:	http://linuxtv.org
+W:	https://linuxtv.org
 S:	Maintained
 F:	drivers/media/common/cx2341x*
 F:	include/media/cx2341x*
@@ -3140,7 +3149,7 @@
 M:	Jemma Denson <jdenson@gmail.com>
 M:	Patrick Boettcher <patrick.boettcher@posteo.de>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 S:	Maintained
 F:	drivers/media/dvb-frontends/cx24120*
@@ -3148,7 +3157,7 @@
 CX88 VIDEO4LINUX DRIVER
 M:	Mauro Carvalho Chehab <mchehab@osg.samsung.com>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org
+W:	https://linuxtv.org
 T:	git git://linuxtv.org/media_tree.git
 S:	Odd fixes
 F:	Documentation/video4linux/cx88/
@@ -3157,7 +3166,7 @@
 CXD2820R MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/anttip/media_tree.git
@@ -3263,7 +3272,7 @@
 CYPRESS_FIRMWARE MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/anttip/media_tree.git
@@ -3770,14 +3779,14 @@
 M:	Hans Verkuil <hverkuil@xs4all.nl>
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
-W:	http://linuxtv.org
+W:	https://linuxtv.org
 S:	Odd Fixes
 F:	drivers/media/pci/dt3155/
 
 DVB_USB_AF9015 MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/anttip/media_tree.git
@@ -3787,7 +3796,7 @@
 DVB_USB_AF9035 MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/anttip/media_tree.git
@@ -3797,7 +3806,7 @@
 DVB_USB_ANYSEE MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/anttip/media_tree.git
@@ -3807,7 +3816,7 @@
 DVB_USB_AU6610 MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/anttip/media_tree.git
@@ -3817,7 +3826,7 @@
 DVB_USB_CE6230 MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/anttip/media_tree.git
@@ -3827,7 +3836,7 @@
 DVB_USB_CXUSB MEDIA DRIVER
 M:	Michael Krufky <mkrufky@linuxtv.org>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://github.com/mkrufky
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/media_tree.git
@@ -3837,7 +3846,7 @@
 DVB_USB_EC168 MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/anttip/media_tree.git
@@ -3847,7 +3856,7 @@
 DVB_USB_GL861 MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/anttip/media_tree.git
 S:	Maintained
@@ -3856,7 +3865,7 @@
 DVB_USB_MXL111SF MEDIA DRIVER
 M:	Michael Krufky <mkrufky@linuxtv.org>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://github.com/mkrufky
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/mkrufky/mxl111sf.git
@@ -3866,7 +3875,7 @@
 DVB_USB_RTL28XXU MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/anttip/media_tree.git
@@ -3876,7 +3885,7 @@
 DVB_USB_V2 MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/anttip/media_tree.git
@@ -3906,7 +3915,7 @@
 E4000 MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/anttip/media_tree.git
@@ -3922,7 +3931,7 @@
 EC100 MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/anttip/media_tree.git
@@ -3943,9 +3952,8 @@
 M:	Borislav Petkov <bp@alien8.de>
 M:	Mauro Carvalho Chehab <mchehab@osg.samsung.com>
 L:	linux-edac@vger.kernel.org
-W:	bluesmoke.sourceforge.net
-T:	git://git.kernel.org/pub/scm/linux/kernel/git/bp/bp.git#for-next
-T:	git://git.kernel.org/pub/linux/kernel/git/mchehab/linux-edac.git#linux_next
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/bp/bp.git for-next
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-edac.git linux_next
 S:	Supported
 F:	Documentation/edac.txt
 F:	drivers/edac/
@@ -3955,7 +3963,6 @@
 M:	Doug Thompson <dougthompson@xmission.com>
 M:	Borislav Petkov <bp@alien8.de>
 L:	linux-edac@vger.kernel.org
-W:	bluesmoke.sourceforge.net
 S:	Maintained
 F:	drivers/edac/amd64_edac*
 
@@ -3963,7 +3970,6 @@
 M:	Doug Thompson <dougthompson@xmission.com>
 M:	Robert Richter <rric@kernel.org>
 L:	linux-edac@vger.kernel.org
-W:	bluesmoke.sourceforge.net
 S:	Maintained
 F:	drivers/edac/highbank*
 
@@ -3972,7 +3978,6 @@
 M:	David Daney <david.daney@cavium.com>
 L:	linux-edac@vger.kernel.org
 L:	linux-mips@linux-mips.org
-W:	bluesmoke.sourceforge.net
 S:	Supported
 F:	drivers/edac/octeon_edac*
 
@@ -3980,63 +3985,54 @@
 M:	Mark Gross <mark.gross@intel.com>
 M:	Doug Thompson <dougthompson@xmission.com>
 L:	linux-edac@vger.kernel.org
-W:	bluesmoke.sourceforge.net
 S:	Maintained
 F:	drivers/edac/e752x_edac.c
 
 EDAC-E7XXX
 M:	Doug Thompson <dougthompson@xmission.com>
 L:	linux-edac@vger.kernel.org
-W:	bluesmoke.sourceforge.net
 S:	Maintained
 F:	drivers/edac/e7xxx_edac.c
 
 EDAC-GHES
 M:	Mauro Carvalho Chehab <mchehab@osg.samsung.com>
 L:	linux-edac@vger.kernel.org
-W:	bluesmoke.sourceforge.net
 S:	Maintained
 F:	drivers/edac/ghes_edac.c
 
 EDAC-I82443BXGX
 M:	Tim Small <tim@buttersideup.com>
 L:	linux-edac@vger.kernel.org
-W:	bluesmoke.sourceforge.net
 S:	Maintained
 F:	drivers/edac/i82443bxgx_edac.c
 
 EDAC-I3000
 M:	Jason Uhlenkott <juhlenko@akamai.com>
 L:	linux-edac@vger.kernel.org
-W:	bluesmoke.sourceforge.net
 S:	Maintained
 F:	drivers/edac/i3000_edac.c
 
 EDAC-I5000
 M:	Doug Thompson <dougthompson@xmission.com>
 L:	linux-edac@vger.kernel.org
-W:	bluesmoke.sourceforge.net
 S:	Maintained
 F:	drivers/edac/i5000_edac.c
 
 EDAC-I5400
 M:	Mauro Carvalho Chehab <mchehab@osg.samsung.com>
 L:	linux-edac@vger.kernel.org
-W:	bluesmoke.sourceforge.net
 S:	Maintained
 F:	drivers/edac/i5400_edac.c
 
 EDAC-I7300
 M:	Mauro Carvalho Chehab <mchehab@osg.samsung.com>
 L:	linux-edac@vger.kernel.org
-W:	bluesmoke.sourceforge.net
 S:	Maintained
 F:	drivers/edac/i7300_edac.c
 
 EDAC-I7CORE
 M:	Mauro Carvalho Chehab <mchehab@osg.samsung.com>
 L:	linux-edac@vger.kernel.org
-W:	bluesmoke.sourceforge.net
 S:	Maintained
 F:	drivers/edac/i7core_edac.c
 
@@ -4044,42 +4040,36 @@
 M:	Ranganathan Desikan <ravi@jetztechnologies.com>
 M:	"Arvind R." <arvino55@gmail.com>
 L:	linux-edac@vger.kernel.org
-W:	bluesmoke.sourceforge.net
 S:	Maintained
 F:	drivers/edac/i82975x_edac.c
 
 EDAC-IE31200
 M:	Jason Baron <jbaron@akamai.com>
 L:	linux-edac@vger.kernel.org
-W:	bluesmoke.sourceforge.net
 S:	Maintained
 F:	drivers/edac/ie31200_edac.c
 
 EDAC-MPC85XX
 M:	Johannes Thumshirn <morbidrsa@gmail.com>
 L:	linux-edac@vger.kernel.org
-W:	bluesmoke.sourceforge.net
 S:	Maintained
 F:	drivers/edac/mpc85xx_edac.[ch]
 
 EDAC-PASEMI
 M:	Egor Martovetsky <egor@pasemi.com>
 L:	linux-edac@vger.kernel.org
-W:	bluesmoke.sourceforge.net
 S:	Maintained
 F:	drivers/edac/pasemi_edac.c
 
 EDAC-R82600
 M:	Tim Small <tim@buttersideup.com>
 L:	linux-edac@vger.kernel.org
-W:	bluesmoke.sourceforge.net
 S:	Maintained
 F:	drivers/edac/r82600_edac.c
 
 EDAC-SBRIDGE
 M:	Mauro Carvalho Chehab <mchehab@osg.samsung.com>
 L:	linux-edac@vger.kernel.org
-W:	bluesmoke.sourceforge.net
 S:	Maintained
 F:	drivers/edac/sb_edac.c
 
@@ -4146,7 +4136,7 @@
 EM28XX VIDEO4LINUX DRIVER
 M:	Mauro Carvalho Chehab <mchehab@osg.samsung.com>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org
+W:	https://linuxtv.org
 T:	git git://linuxtv.org/media_tree.git
 S:	Maintained
 F:	drivers/media/usb/em28xx/
@@ -4286,7 +4276,7 @@
 FC2580 MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/anttip/media_tree.git
@@ -4609,7 +4599,7 @@
 L:	linux-media@vger.kernel.org
 S:	Maintained
 F:	drivers/media/i2c/m5mols/
-F:	include/media/m5mols.h
+F:	include/media/i2c/m5mols.h
 
 FUJITSU TABLET EXTRAS
 M:	Robert Gerlach <khnz@gmx.de>
@@ -4655,7 +4645,7 @@
 M:	Hans Verkuil <hverkuil@xs4all.nl>
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
-W:	http://linuxtv.org
+W:	https://linuxtv.org
 S:	Maintained
 F:	drivers/media/radio/radio-gemtek*
 
@@ -4863,7 +4853,7 @@
 M:	Hans Verkuil <hverkuil@xs4all.nl>
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
-W:	http://linuxtv.org
+W:	https://linuxtv.org
 S:	Odd Fixes
 F:	drivers/media/usb/hdpvr/
 
@@ -4882,7 +4872,7 @@
 HACKRF MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/anttip/media_tree.git
@@ -4925,7 +4915,7 @@
 HD29L2 MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/anttip/media_tree.git
@@ -5638,9 +5628,7 @@
 F:	drivers/hwtracing/intel_th/
 
 INTEL(R) TRUSTED EXECUTION TECHNOLOGY (TXT)
-M:	Richard L Maliszewski <richard.l.maliszewski@intel.com>
-M:	Gang Wei <gang.wei@intel.com>
-M:	Shane Wang <shane.wang@intel.com>
+M:	Ning Sun <ning.sun@intel.com>
 L:	tboot-devel@lists.sourceforge.net
 W:	http://tboot.sourceforge.net
 T:	hg http://tboot.hg.sourceforge.net:8000/hgroot/tboot/tboot
@@ -5838,7 +5826,7 @@
 M:	Hans Verkuil <hverkuil@xs4all.nl>
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
-W:	http://linuxtv.org
+W:	https://linuxtv.org
 S:	Maintained
 F:	drivers/media/radio/radio-isa*
 
@@ -5908,7 +5896,7 @@
 IT913X MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/anttip/media_tree.git
@@ -5929,7 +5917,7 @@
 IX2505V MEDIA DRIVER
 M:	Malcolm Priestley <tvboxspy@gmail.com>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 S:	Maintained
 F:	drivers/media/dvb-frontends/ix2505v*
@@ -6018,7 +6006,7 @@
 M:	Hans Verkuil <hverkuil@xs4all.nl>
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
-W:	http://linuxtv.org
+W:	https://linuxtv.org
 S:	Maintained
 F:	drivers/media/radio/radio-keene*
 
@@ -6118,6 +6106,7 @@
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 L:	kvmarm@lists.cs.columbia.edu
 W:	http://systems.cs.columbia.edu/projects/kvm-arm
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm.git
 S:	Supported
 F:	arch/arm/include/uapi/asm/kvm*
 F:	arch/arm/include/asm/kvm*
@@ -6270,7 +6259,7 @@
 LG2160 MEDIA DRIVER
 M:	Michael Krufky <mkrufky@linuxtv.org>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://github.com/mkrufky
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/mkrufky/tuners.git
@@ -6280,7 +6269,7 @@
 LGDT3305 MEDIA DRIVER
 M:	Michael Krufky <mkrufky@linuxtv.org>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://github.com/mkrufky
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/mkrufky/tuners.git
@@ -6537,7 +6526,7 @@
 LME2510 MEDIA DRIVER
 M:	Malcolm Priestley <tvboxspy@gmail.com>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 S:	Maintained
 F:	drivers/media/usb/dvb-usb-v2/lmedm04*
@@ -6643,7 +6632,7 @@
 M88DS3103 MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/anttip/media_tree.git
@@ -6653,7 +6642,7 @@
 M88RS2000 MEDIA DRIVER
 M:	Malcolm Priestley <tvboxspy@gmail.com>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 S:	Maintained
 F:	drivers/media/dvb-frontends/m88rs2000*
@@ -6832,7 +6821,7 @@
 M:	Hans Verkuil <hverkuil@xs4all.nl>
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
-W:	http://linuxtv.org
+W:	https://linuxtv.org
 S:	Maintained
 F:	drivers/media/radio/radio-maxiradio*
 
@@ -6854,7 +6843,7 @@
 MEDIA DRIVERS FOR ASCOT2E
 M:	Sergey Kozlov <serjk@netup.ru>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org
+W:	https://linuxtv.org
 W:	http://netup.tv/
 T:	git git://linuxtv.org/media_tree.git
 S:	Supported
@@ -6863,7 +6852,7 @@
 MEDIA DRIVERS FOR CXD2841ER
 M:	Sergey Kozlov <serjk@netup.ru>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://netup.tv/
 T:	git git://linuxtv.org/media_tree.git
 S:	Supported
@@ -6872,7 +6861,7 @@
 MEDIA DRIVERS FOR HORUS3A
 M:	Sergey Kozlov <serjk@netup.ru>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://netup.tv/
 T:	git git://linuxtv.org/media_tree.git
 S:	Supported
@@ -6881,7 +6870,7 @@
 MEDIA DRIVERS FOR LNBH25
 M:	Sergey Kozlov <serjk@netup.ru>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://netup.tv/
 T:	git git://linuxtv.org/media_tree.git
 S:	Supported
@@ -6890,7 +6879,7 @@
 MEDIA DRIVERS FOR NETUP PCI UNIVERSAL DVB devices
 M:	Sergey Kozlov <serjk@netup.ru>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://netup.tv/
 T:	git git://linuxtv.org/media_tree.git
 S:	Supported
@@ -6900,7 +6889,7 @@
 M:	Mauro Carvalho Chehab <mchehab@osg.samsung.com>
 P:	LinuxTV.org Project
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org
+W:	https://linuxtv.org
 Q:	http://patchwork.kernel.org/project/linux-media/list/
 T:	git git://linuxtv.org/media_tree.git
 S:	Maintained
@@ -6909,6 +6898,7 @@
 F:	Documentation/DocBook/media/
 F:	drivers/media/
 F:	drivers/staging/media/
+F:	include/linux/platform_data/media/
 F:	include/media/
 F:	include/uapi/linux/dvb/
 F:	include/uapi/linux/videodev2.h
@@ -7060,7 +7050,7 @@
 M:	Hans Verkuil <hverkuil@xs4all.nl>
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
-W:	http://linuxtv.org
+W:	https://linuxtv.org
 S:	Odd Fixes
 F:	drivers/media/radio/radio-miropcm20*
 
@@ -7096,7 +7086,7 @@
 MN88472 MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/anttip/media_tree.git
@@ -7107,7 +7097,7 @@
 MN88473 MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/anttip/media_tree.git
@@ -7162,7 +7152,7 @@
 MSI001 MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/anttip/media_tree.git
@@ -7172,7 +7162,7 @@
 MSI2500 MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/anttip/media_tree.git
@@ -7191,7 +7181,7 @@
 T:	git git://linuxtv.org/media_tree.git
 S:	Maintained
 F:	drivers/media/i2c/mt9m032.c
-F:	include/media/mt9m032.h
+F:	include/media/i2c/mt9m032.h
 
 MT9P031 APTINA CAMERA SENSOR
 M:	Laurent Pinchart <laurent.pinchart@ideasonboard.com>
@@ -7199,7 +7189,7 @@
 T:	git git://linuxtv.org/media_tree.git
 S:	Maintained
 F:	drivers/media/i2c/mt9p031.c
-F:	include/media/mt9p031.h
+F:	include/media/i2c/mt9p031.h
 
 MT9T001 APTINA CAMERA SENSOR
 M:	Laurent Pinchart <laurent.pinchart@ideasonboard.com>
@@ -7207,7 +7197,7 @@
 T:	git git://linuxtv.org/media_tree.git
 S:	Maintained
 F:	drivers/media/i2c/mt9t001.c
-F:	include/media/mt9t001.h
+F:	include/media/i2c/mt9t001.h
 
 MT9V032 APTINA CAMERA SENSOR
 M:	Laurent Pinchart <laurent.pinchart@ideasonboard.com>
@@ -7216,7 +7206,7 @@
 S:	Maintained
 F:	Documentation/devicetree/bindings/media/i2c/mt9v032.txt
 F:	drivers/media/i2c/mt9v032.c
-F:	include/media/mt9v032.h
+F:	include/media/i2c/mt9v032.h
 
 MULTIFUNCTION DEVICES (MFD)
 M:	Lee Jones <lee.jones@linaro.org>
@@ -7260,7 +7250,7 @@
 MXL5007T MEDIA DRIVER
 M:	Michael Krufky <mkrufky@linuxtv.org>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://github.com/mkrufky
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/mkrufky/tuners.git
@@ -8397,6 +8387,7 @@
 
 PIN CONTROLLER - RENESAS
 M:	Laurent Pinchart <laurent.pinchart@ideasonboard.com>
+M:	Geert Uytterhoeven <geert+renesas@glider.be>
 L:	linux-sh@vger.kernel.org
 S:	Maintained
 F:	drivers/pinctrl/sh-pfc/
@@ -8667,6 +8658,7 @@
 F:	arch/arm/mach-pxa/
 F:	drivers/dma/pxa*
 F:	drivers/pcmcia/pxa2xx*
+F:	drivers/pinctrl/pxa/
 F:	drivers/spi/spi-pxa2xx*
 F:	drivers/usb/gadget/udc/pxa2*
 F:	include/sound/pxa2xx-lib.h
@@ -8773,7 +8765,7 @@
 QT1010 MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/anttip/media_tree.git
@@ -9066,7 +9058,7 @@
 RTL2830 MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/anttip/media_tree.git
@@ -9076,7 +9068,7 @@
 RTL2832 MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/anttip/media_tree.git
@@ -9086,7 +9078,7 @@
 RTL2832_SDR MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/anttip/media_tree.git
@@ -9217,14 +9209,14 @@
 M:	Hans Verkuil <hverkuil@xs4all.nl>
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
-W:	http://linuxtv.org
+W:	https://linuxtv.org
 S:	Odd Fixes
 F:	drivers/media/i2c/saa6588*
 
 SAA7134 VIDEO4LINUX DRIVER
 M:	Mauro Carvalho Chehab <mchehab@osg.samsung.com>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org
+W:	https://linuxtv.org
 T:	git git://linuxtv.org/media_tree.git
 S:	Odd fixes
 F:	Documentation/video4linux/*.saa7134
@@ -9286,7 +9278,7 @@
 L:	linux-samsung-soc@vger.kernel.org (moderated for non-subscribers)
 S:	Maintained
 F:	drivers/media/platform/s3c-camif/
-F:	include/media/s3c_camif.h
+F:	include/media/drv-intf/s3c_camif.h
 
 SAMSUNG S5C73M3 CAMERA DRIVER
 M:	Kyungmin Park <kyungmin.park@samsung.com>
@@ -9394,7 +9386,7 @@
 S:	Maintained
 F:	drivers/thunderbolt/
 
-TIMEKEEPING, CLOCKSOURCE CORE, NTP
+TIMEKEEPING, CLOCKSOURCE CORE, NTP, ALARMTIMER
 M:	John Stultz <john.stultz@linaro.org>
 M:	Thomas Gleixner <tglx@linutronix.de>
 L:	linux-kernel@vger.kernel.org
@@ -9407,6 +9399,7 @@
 F:	include/uapi/linux/timex.h
 F:	kernel/time/clocksource.c
 F:	kernel/time/time*.c
+F:	kernel/time/alarmtimer.c
 F:	kernel/time/ntp.c
 F:	tools/testing/selftests/timers/
 
@@ -9661,7 +9654,7 @@
 SI2157 MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/anttip/media_tree.git
@@ -9671,7 +9664,7 @@
 SI2168 MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/anttip/media_tree.git
@@ -9682,7 +9675,7 @@
 M:	Hans Verkuil <hverkuil@xs4all.nl>
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
-W:	http://linuxtv.org
+W:	https://linuxtv.org
 S:	Odd Fixes
 F:	drivers/media/radio/si470x/radio-si470x-i2c.c
 
@@ -9690,7 +9683,7 @@
 M:	Hans Verkuil <hverkuil@xs4all.nl>
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
-W:	http://linuxtv.org
+W:	https://linuxtv.org
 S:	Maintained
 F:	drivers/media/radio/si470x/radio-si470x-common.c
 F:	drivers/media/radio/si470x/radio-si470x.h
@@ -9700,7 +9693,7 @@
 M:	Eduardo Valentin <edubezval@gmail.com>
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
-W:	http://linuxtv.org
+W:	https://linuxtv.org
 S:	Odd Fixes
 F:	drivers/media/radio/si4713/si4713.?
 
@@ -9708,7 +9701,7 @@
 M:	Eduardo Valentin <edubezval@gmail.com>
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
-W:	http://linuxtv.org
+W:	https://linuxtv.org
 S:	Odd Fixes
 F:	drivers/media/radio/si4713/radio-platform-si4713.c
 
@@ -9716,14 +9709,14 @@
 M:	Hans Verkuil <hverkuil@xs4all.nl>
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
-W:	http://linuxtv.org
+W:	https://linuxtv.org
 S:	Maintained
 F:	drivers/media/radio/si4713/radio-usb-si4713.c
 
 SIANO DVB DRIVER
 M:	Mauro Carvalho Chehab <mchehab@osg.samsung.com>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org
+W:	https://linuxtv.org
 T:	git git://linuxtv.org/media_tree.git
 S:	Odd fixes
 F:	drivers/media/common/siano/
@@ -9748,7 +9741,7 @@
 L:	linux-media@vger.kernel.org
 S:	Orphan
 F:	drivers/media/platform/sh_vou.c
-F:	include/media/sh_vou.h
+F:	include/media/drv-intf/sh_vou.h
 
 SIMPLE FIRMWARE INTERFACE (SFI)
 M:	Len Brown <lenb@kernel.org>
@@ -9789,7 +9782,7 @@
 TI DAVINCI SERIES MEDIA DRIVER
 M:	"Lad, Prabhakar" <prabhakar.csengg@gmail.com>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/mhadli/v4l-dvb-davinci_devices.git
 S:	Maintained
@@ -9799,7 +9792,7 @@
 TI AM437X VPFE DRIVER
 M:	"Lad, Prabhakar" <prabhakar.csengg@gmail.com>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/mhadli/v4l-dvb-davinci_devices.git
 S:	Maintained
@@ -9808,12 +9801,12 @@
 OV2659 OMNIVISION SENSOR DRIVER
 M:	"Lad, Prabhakar" <prabhakar.csengg@gmail.com>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/mhadli/v4l-dvb-davinci_devices.git
 S:	Maintained
 F:	drivers/media/i2c/ov2659.c
-F:	include/media/ov2659.h
+F:	include/media/i2c/ov2659.h
 
 SILICON MOTION SM712 FRAME BUFFER DRIVER
 M:	Sudip Mukherjee <sudipm.mukherjee@gmail.com>
@@ -9902,7 +9895,7 @@
 L:	linux-media@vger.kernel.org
 S:	Maintained
 F:	drivers/media/i2c/smiapp/
-F:	include/media/smiapp.h
+F:	include/media/i2c/smiapp.h
 F:	drivers/media/i2c/smiapp-pll.c
 F:	drivers/media/i2c/smiapp-pll.h
 F:	include/uapi/linux/smiapp.h
@@ -10066,7 +10059,7 @@
 SP2 MEDIA DRIVER
 M:	Olli Salonen <olli.salonen@iki.fi>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 S:	Maintained
 F:	drivers/media/dvb-frontends/sp2*
@@ -10428,7 +10421,7 @@
 TDA10071 MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/anttip/media_tree.git
@@ -10438,7 +10431,7 @@
 TDA18212 MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/anttip/media_tree.git
@@ -10448,7 +10441,7 @@
 TDA18218 MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/anttip/media_tree.git
@@ -10458,7 +10451,7 @@
 TDA18271 MEDIA DRIVER
 M:	Michael Krufky <mkrufky@linuxtv.org>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://github.com/mkrufky
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/mkrufky/tuners.git
@@ -10468,7 +10461,7 @@
 TDA827x MEDIA DRIVER
 M:	Michael Krufky <mkrufky@linuxtv.org>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://github.com/mkrufky
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/mkrufky/tuners.git
@@ -10478,7 +10471,7 @@
 TDA8290 MEDIA DRIVER
 M:	Michael Krufky <mkrufky@linuxtv.org>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://github.com/mkrufky
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/mkrufky/tuners.git
@@ -10489,14 +10482,14 @@
 M:	Hans Verkuil <hverkuil@xs4all.nl>
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
-W:	http://linuxtv.org
+W:	https://linuxtv.org
 S:	Maintained
 F:	drivers/media/i2c/tda9840*
 
 TEA5761 TUNER DRIVER
 M:	Mauro Carvalho Chehab <mchehab@osg.samsung.com>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org
+W:	https://linuxtv.org
 T:	git git://linuxtv.org/media_tree.git
 S:	Odd fixes
 F:	drivers/media/tuners/tea5761.*
@@ -10504,7 +10497,7 @@
 TEA5767 TUNER DRIVER
 M:	Mauro Carvalho Chehab <mchehab@osg.samsung.com>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org
+W:	https://linuxtv.org
 T:	git git://linuxtv.org/media_tree.git
 S:	Maintained
 F:	drivers/media/tuners/tea5767.*
@@ -10513,7 +10506,7 @@
 M:	Hans Verkuil <hverkuil@xs4all.nl>
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
-W:	http://linuxtv.org
+W:	https://linuxtv.org
 S:	Maintained
 F:	drivers/media/i2c/tea6415c*
 
@@ -10521,7 +10514,7 @@
 M:	Hans Verkuil <hverkuil@xs4all.nl>
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
-W:	http://linuxtv.org
+W:	https://linuxtv.org
 S:	Maintained
 F:	drivers/media/i2c/tea6420*
 
@@ -10619,7 +10612,7 @@
 M:	Hans Verkuil <hverkuil@xs4all.nl>
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
-W:	http://linuxtv.org
+W:	https://linuxtv.org
 S:	Maintained
 F:	drivers/media/radio/radio-raremono.c
 
@@ -10843,7 +10836,7 @@
 L:	linux-media@vger.kernel.org
 S:	Maintained
 F:	drivers/media/i2c/tc358743*
-F:	include/media/tc358743.h
+F:	include/media/i2c/tc358743.h
 
 TMIO MMC DRIVER
 M:	Ian Molton <ian@mnementh.co.uk>
@@ -10871,7 +10864,7 @@
 TM6000 VIDEO4LINUX DRIVER
 M:	Mauro Carvalho Chehab <mchehab@osg.samsung.com>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org
+W:	https://linuxtv.org
 T:	git git://linuxtv.org/media_tree.git
 S:	Odd fixes
 F:	drivers/media/usb/tm6000/
@@ -10880,7 +10873,7 @@
 M:	Hans Verkuil <hverkuil@xs4all.nl>
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
-W:	http://linuxtv.org
+W:	https://linuxtv.org
 S:	Odd Fixes
 F:	drivers/media/pci/tw68/
 
@@ -10941,7 +10934,7 @@
 TUA9001 MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org/
+W:	https://linuxtv.org
 W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/anttip/media_tree.git
@@ -11295,7 +11288,7 @@
 M:	Hans Verkuil <hverkuil@xs4all.nl>
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
-W:	http://linuxtv.org
+W:	https://linuxtv.org
 S:	Odd Fixes
 F:	drivers/media/usb/usbvision/
 
@@ -11509,7 +11502,7 @@
 M:	Hans Verkuil <hverkuil@xs4all.nl>
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
-W:	http://linuxtv.org
+W:	https://linuxtv.org
 S:	Maintained
 F:	drivers/media/platform/vivid/*
 
@@ -11798,7 +11791,7 @@
 XC2028/3028 TUNER DRIVER
 M:	Mauro Carvalho Chehab <mchehab@osg.samsung.com>
 L:	linux-media@vger.kernel.org
-W:	http://linuxtv.org
+W:	https://linuxtv.org
 T:	git git://linuxtv.org/media_tree.git
 S:	Maintained
 F:	drivers/media/tuners/tuner-xc2028.*
@@ -11967,7 +11960,7 @@
 L:	mjpeg-users@lists.sourceforge.net
 L:	linux-media@vger.kernel.org
 W:	http://mjpeg.sourceforge.net/driver-zoran/
-T:	hg http://linuxtv.org/hg/v4l-dvb
+T:	hg https://linuxtv.org/hg/v4l-dvb
 S:	Odd Fixes
 F:	drivers/media/pci/zoran/
 
diff --git a/Makefile b/Makefile
index 9d94ade..70dea02 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 4
 SUBLEVEL = 0
-EXTRAVERSION = -rc8
+EXTRAVERSION =
 NAME = Blurry Fish Butt
 
 # *DOCUMENTATION*
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 34e1569..426115f 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -20,6 +20,7 @@
 	select GENERIC_ALLOCATOR
 	select GENERIC_ATOMIC64 if (CPU_V7M || CPU_V6 || !CPU_32v6K || !AEABI)
 	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
+	select GENERIC_EARLY_IOREMAP
 	select GENERIC_IDLE_POLL_SETUP
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
@@ -33,10 +34,11 @@
 	select HARDIRQS_SW_RESEND
 	select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT)
 	select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6
-	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32
-	select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32
+	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU
+	select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU
 	select HAVE_ARCH_SECCOMP_FILTER if (AEABI && !OABI_COMPAT)
 	select HAVE_ARCH_TRACEHOOK
+	select HAVE_ARM_SMCCC if CPU_V7
 	select HAVE_BPF_JIT
 	select HAVE_CC_STACKPROTECTOR
 	select HAVE_CONTEXT_TRACKING
@@ -45,7 +47,7 @@
 	select HAVE_DMA_API_DEBUG
 	select HAVE_DMA_ATTRS
 	select HAVE_DMA_CONTIGUOUS if MMU
-	select HAVE_DYNAMIC_FTRACE if (!XIP_KERNEL) && !CPU_ENDIAN_BE32
+	select HAVE_DYNAMIC_FTRACE if (!XIP_KERNEL) && !CPU_ENDIAN_BE32 && MMU
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS if (CPU_V6 || CPU_V6K || CPU_V7) && MMU
 	select HAVE_FTRACE_MCOUNT_RECORD if (!XIP_KERNEL)
 	select HAVE_FUNCTION_GRAPH_TRACER if (!THUMB2_KERNEL)
@@ -611,6 +613,7 @@
 	select AUTO_ZRELADDR
 	select COMMON_CLK
 	select CLKDEV_LOOKUP
+	select CLKSRC_PXA
 	select CLKSRC_MMIO
 	select CLKSRC_OF
 	select GENERIC_CLOCKEVENTS
@@ -650,6 +653,8 @@
 	select ARCH_SPARSEMEM_ENABLE
 	select CLKDEV_LOOKUP
 	select CLKSRC_MMIO
+	select CLKSRC_PXA
+	select CLKSRC_OF if OF
 	select CPU_FREQ
 	select CPU_SA1100
 	select GENERIC_CLOCKEVENTS
@@ -799,6 +804,7 @@
 	bool "Dummy Virtual Machine" if ARCH_MULTI_V7
 	select ARM_AMBA
 	select ARM_GIC
+	select ARM_GIC_V2M if PCI_MSI
 	select ARM_GIC_V3
 	select ARM_PSCI
 	select HAVE_ARM_ARCH_TIMER
@@ -1422,7 +1428,7 @@
 
 config BL_SWITCHER
 	bool "big.LITTLE switcher support"
-	depends on BIG_LITTLE && MCPM && HOTPLUG_CPU
+	depends on BIG_LITTLE && MCPM && HOTPLUG_CPU && ARM_GIC
 	select ARM_CPU_SUSPEND
 	select CPU_PM
 	help
@@ -1481,7 +1487,7 @@
 
 config ARM_PSCI
 	bool "Support for the ARM Power State Coordination Interface (PSCI)"
-	depends on CPU_V7
+	depends on HAVE_ARM_SMCCC
 	select ARM_PSCI_FW
 	help
 	  Say Y here if you want Linux to communicate with system firmware
@@ -1604,6 +1610,24 @@
 config ARM_ASM_UNIFIED
 	bool
 
+config ARM_PATCH_IDIV
+	bool "Runtime patch udiv/sdiv instructions into __aeabi_{u}idiv()"
+	depends on CPU_32v7 && !XIP_KERNEL
+	default y
+	help
+	  The ARM compiler inserts calls to __aeabi_idiv() and
+	  __aeabi_uidiv() when it needs to perform division on signed
+	  and unsigned integers. Some v7 CPUs have support for the sdiv
+	  and udiv instructions that can be used to implement those
+	  functions.
+
+	  Enabling this option allows the kernel to modify itself to
+	  replace the first two instructions of these library functions
+	  with the sdiv or udiv plus "bx lr" instructions when the CPU
+	  it is running on supports them. Typically this will be faster
+	  and less power intensive than running the original library
+	  code to do integer division.
+
 config AEABI
 	bool "Use the ARM EABI to compile the kernel"
 	help
@@ -1800,6 +1824,25 @@
 config IOMMU_HELPER
 	def_bool SWIOTLB
 
+config PARAVIRT
+	bool "Enable paravirtualization code"
+	help
+	  This changes the kernel so it can modify itself when it is run
+	  under a hypervisor, potentially improving performance significantly
+	  over full virtualization.
+
+config PARAVIRT_TIME_ACCOUNTING
+	bool "Paravirtual steal time accounting"
+	select PARAVIRT
+	default n
+	help
+	  Select this option to enable fine granularity task steal time
+	  accounting. Time spent executing other tasks in parallel with
+	  the current vCPU is discounted from the vCPU power. To account for
+	  that, there can be a small performance impact.
+
+	  If in doubt, say N here.
+
 config XEN_DOM0
 	def_bool y
 	depends on XEN
@@ -1813,6 +1856,7 @@
 	select ARCH_DMA_ADDR_T_64BIT
 	select ARM_PSCI
 	select SWIOTLB_XEN
+	select PARAVIRT
 	help
 	  Say Y if you want to run Linux in a Virtual Machine on Xen on ARM.
 
@@ -2040,6 +2084,25 @@
 	  0xf8000000. This assumes the zImage being placed in the first 128MB
 	  from start of memory.
 
+config EFI_STUB
+	bool
+
+config EFI
+	bool "UEFI runtime support"
+	depends on OF && !CPU_BIG_ENDIAN && MMU && AUTO_ZRELADDR && !XIP_KERNEL
+	select UCS2_STRING
+	select EFI_PARAMS_FROM_FDT
+	select EFI_STUB
+	select EFI_ARMSTUB
+	select EFI_RUNTIME_WRAPPERS
+	---help---
+	  This option provides support for runtime services provided
+	  by UEFI firmware (such as non-volatile variables, realtime
+	  clock, and platform reset). A UEFI stub is also provided to
+	  allow the kernel to be booted as an EFI application. This
+	  is only useful for kernels that may run on systems that have
+	  UEFI firmware.
+
 endmenu
 
 menu "CPU Power Management"
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index 3f9a9eb..4c23a68 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -167,9 +167,11 @@
 	false; \
 fi
 
+efi-obj-$(CONFIG_EFI_STUB) := $(objtree)/drivers/firmware/efi/libstub/lib.a
+
 $(obj)/vmlinux: $(obj)/vmlinux.lds $(obj)/$(HEAD) $(obj)/piggy.$(suffix_y).o \
 		$(addprefix $(obj)/, $(OBJS)) $(lib1funcs) $(ashldi3) \
-		$(bswapsdi2) FORCE
+		$(bswapsdi2) $(efi-obj-y) FORCE
 	@$(check_for_multiple_zreladdr)
 	$(call if_changed,ld)
 	@$(check_for_bad_syms)
diff --git a/arch/arm/boot/compressed/efi-header.S b/arch/arm/boot/compressed/efi-header.S
new file mode 100644
index 0000000..9d5dc4f
--- /dev/null
+++ b/arch/arm/boot/compressed/efi-header.S
@@ -0,0 +1,130 @@
+/*
+ * Copyright (C) 2013-2015 Linaro Ltd
+ * Authors: Roy Franz <roy.franz@linaro.org>
+ *          Ard Biesheuvel <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+		.macro	__nop
+#ifdef CONFIG_EFI_STUB
+		@ This is almost but not quite a NOP, since it does clobber the
+		@ condition flags. But it is the best we can do for EFI, since
+		@ PE/COFF expects the magic string "MZ" at offset 0, while the
+		@ ARM/Linux boot protocol expects an executable instruction
+		@ there.
+		.inst	'M' | ('Z' << 8) | (0x1310 << 16)   @ tstne r0, #0x4d000
+#else
+		mov	r0, r0
+#endif
+		.endm
+
+		.macro	__EFI_HEADER
+#ifdef CONFIG_EFI_STUB
+		b	__efi_start
+
+		.set	start_offset, __efi_start - start
+		.org	start + 0x3c
+		@
+		@ The PE header can be anywhere in the file, but for
+		@ simplicity we keep it together with the MSDOS header
+		@ The offset to the PE/COFF header needs to be at offset
+		@ 0x3C in the MSDOS header.
+		@ The only 2 fields of the MSDOS header that are used are this
+		@ PE/COFF offset, and the "MZ" bytes at offset 0x0.
+		@
+		.long	pe_header - start	@ Offset to the PE header.
+
+pe_header:
+		.ascii	"PE\0\0"
+
+coff_header:
+		.short	0x01c2			@ ARM or Thumb
+		.short	2			@ nr_sections
+		.long	0 			@ TimeDateStamp
+		.long	0			@ PointerToSymbolTable
+		.long	1			@ NumberOfSymbols
+		.short	section_table - optional_header
+						@ SizeOfOptionalHeader
+		.short	0x306			@ Characteristics.
+						@ IMAGE_FILE_32BIT_MACHINE |
+						@ IMAGE_FILE_DEBUG_STRIPPED |
+						@ IMAGE_FILE_EXECUTABLE_IMAGE |
+						@ IMAGE_FILE_LINE_NUMS_STRIPPED
+
+optional_header:
+		.short	0x10b			@ PE32 format
+		.byte	0x02			@ MajorLinkerVersion
+		.byte	0x14			@ MinorLinkerVersion
+		.long	_end - __efi_start	@ SizeOfCode
+		.long	0			@ SizeOfInitializedData
+		.long	0			@ SizeOfUninitializedData
+		.long	efi_stub_entry - start	@ AddressOfEntryPoint
+		.long	start_offset		@ BaseOfCode
+		.long	0			@ data
+
+extra_header_fields:
+		.long	0			@ ImageBase
+		.long	0x200			@ SectionAlignment
+		.long	0x200			@ FileAlignment
+		.short	0			@ MajorOperatingSystemVersion
+		.short	0			@ MinorOperatingSystemVersion
+		.short	0			@ MajorImageVersion
+		.short	0			@ MinorImageVersion
+		.short	0			@ MajorSubsystemVersion
+		.short	0			@ MinorSubsystemVersion
+		.long	0			@ Win32VersionValue
+
+		.long	_end - start		@ SizeOfImage
+		.long	start_offset		@ SizeOfHeaders
+		.long	0			@ CheckSum
+		.short	0xa			@ Subsystem (EFI application)
+		.short	0			@ DllCharacteristics
+		.long	0			@ SizeOfStackReserve
+		.long	0			@ SizeOfStackCommit
+		.long	0			@ SizeOfHeapReserve
+		.long	0			@ SizeOfHeapCommit
+		.long	0			@ LoaderFlags
+		.long	0x6			@ NumberOfRvaAndSizes
+
+		.quad	0			@ ExportTable
+		.quad	0			@ ImportTable
+		.quad	0			@ ResourceTable
+		.quad	0			@ ExceptionTable
+		.quad	0			@ CertificationTable
+		.quad	0			@ BaseRelocationTable
+
+section_table:
+		@
+		@ The EFI application loader requires a relocation section
+		@ because EFI applications must be relocatable. This is a
+		@ dummy section as far as we are concerned.
+		@
+		.ascii	".reloc\0\0"
+		.long	0			@ VirtualSize
+		.long	0			@ VirtualAddress
+		.long	0			@ SizeOfRawData
+		.long	0			@ PointerToRawData
+		.long	0			@ PointerToRelocations
+		.long	0			@ PointerToLineNumbers
+		.short	0			@ NumberOfRelocations
+		.short	0			@ NumberOfLineNumbers
+		.long	0x42100040		@ Characteristics
+
+		.ascii	".text\0\0\0"
+		.long	_end - __efi_start	@ VirtualSize
+		.long	__efi_start		@ VirtualAddress
+		.long	_edata - __efi_start	@ SizeOfRawData
+		.long	__efi_start		@ PointerToRawData
+		.long	0			@ PointerToRelocations
+		.long	0			@ PointerToLineNumbers
+		.short	0			@ NumberOfRelocations
+		.short	0			@ NumberOfLineNumbers
+		.long	0xe0500020		@ Characteristics
+
+		.align	9
+__efi_start:
+#endif
+		.endm
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index 06e983f..af11c2f 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -12,6 +12,8 @@
 #include <asm/assembler.h>
 #include <asm/v7m.h>
 
+#include "efi-header.S"
+
  AR_CLASS(	.arch	armv7-a	)
  M_CLASS(	.arch	armv7-m	)
 
@@ -126,7 +128,7 @@
 start:
 		.type	start,#function
 		.rept	7
-		mov	r0, r0
+		__nop
 		.endr
    ARM(		mov	r0, r0		)
    ARM(		b	1f		)
@@ -139,7 +141,8 @@
 		.word	0x04030201	@ endianness flag
 
  THUMB(		.thumb			)
-1:
+1:		__EFI_HEADER
+
  ARM_BE8(	setend	be		)	@ go BE8 if compiled for BE8
  AR_CLASS(	mrs	r9, cpsr	)
 #ifdef CONFIG_ARM_VIRT_EXT
@@ -1353,6 +1356,53 @@
 
 reloc_code_end:
 
+#ifdef CONFIG_EFI_STUB
+		.align	2
+_start:		.long	start - .
+
+ENTRY(efi_stub_entry)
+		@ allocate space on stack for passing current zImage address
+		@ and for the EFI stub to return of new entry point of
+		@ zImage, as EFI stub may copy the kernel. Pointer address
+		@ is passed in r2. r0 and r1 are passed through from the
+		@ EFI firmware to efi_entry
+		adr	ip, _start
+		ldr	r3, [ip]
+		add	r3, r3, ip
+		stmfd	sp!, {r3, lr}
+		mov	r2, sp			@ pass zImage address in r2
+		bl	efi_entry
+
+		@ Check for error return from EFI stub. r0 has FDT address
+		@ or error code.
+		cmn	r0, #1
+		beq	efi_load_fail
+
+		@ Preserve return value of efi_entry() in r4
+		mov	r4, r0
+		bl	cache_clean_flush
+		bl	cache_off
+
+		@ Set parameters for booting zImage according to boot protocol
+		@ put FDT address in r2, it was returned by efi_entry()
+		@ r1 is the machine type, and r0 needs to be 0
+		mov	r0, #0
+		mov	r1, #0xFFFFFFFF
+		mov	r2, r4
+
+		@ Branch to (possibly) relocated zImage that is in [sp]
+		ldr	lr, [sp]
+		ldr	ip, =start_offset
+		add	lr, lr, ip
+		mov	pc, lr				@ no mode switch
+
+efi_load_fail:
+		@ Return EFI_LOAD_ERROR to EFI firmware on error.
+		ldr	r0, =0x80000001
+		ldmfd	sp!, {ip, pc}
+ENDPROC(efi_stub_entry)
+#endif
+
 		.align
 		.section ".stack", "aw", %nobits
 .L_user_stack:	.space	4096
diff --git a/arch/arm/boot/compressed/vmlinux.lds.S b/arch/arm/boot/compressed/vmlinux.lds.S
index 2b60b84..81c4931 100644
--- a/arch/arm/boot/compressed/vmlinux.lds.S
+++ b/arch/arm/boot/compressed/vmlinux.lds.S
@@ -48,6 +48,13 @@
     *(.rodata)
     *(.rodata.*)
   }
+  .data : {
+    /*
+     * The EFI stub always executes from RAM, and runs strictly before the
+     * decompressor, so we can make an exception for its r/w data, and keep it
+     */
+    *(.data.efistub)
+  }
   .piggydata : {
     *(.piggydata)
   }
diff --git a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi
index 314f59c..d0c7438 100644
--- a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi
+++ b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi
@@ -25,9 +25,9 @@
 		cache-sets = <512>;
 		cache-line-size = <32>;
 		/* At full speed latency must be >=2 */
-		arm,tag-latency = <2>;
-		arm,data-latency = <2 2>;
-		arm,dirty-latency = <2>;
+		arm,tag-latency = <8>;
+		arm,data-latency = <8 8>;
+		arm,dirty-latency = <8>;
 	};
 
 	mtu0: mtu@101e2000 {
diff --git a/arch/arm/boot/dts/stihxxx-b2120.dtsi b/arch/arm/boot/dts/stihxxx-b2120.dtsi
index ad21a42..133375b 100644
--- a/arch/arm/boot/dts/stihxxx-b2120.dtsi
+++ b/arch/arm/boot/dts/stihxxx-b2120.dtsi
@@ -6,6 +6,9 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
+#include <dt-bindings/clock/stih407-clks.h>
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/media/c8sectpfe.h>
 / {
 	soc {
 		sbc_serial0: serial@9530000 {
@@ -35,12 +38,18 @@
 			status = "okay";
 		};
 
-		i2c@9842000 {
+		ssc2: i2c@9842000 {
 			status = "okay";
+			clock-frequency = <100000>;
+			st,i2c-min-scl-pulse-width-us = <0>;
+			st,i2c-min-sda-pulse-width-us = <5>;
 		};
 
-		i2c@9843000 {
+		ssc3: i2c@9843000 {
 			status = "okay";
+			clock-frequency = <100000>;
+			st,i2c-min-scl-pulse-width-us = <0>;
+			st,i2c-min-sda-pulse-width-us = <5>;
 		};
 
 		i2c@9844000 {
@@ -93,5 +102,38 @@
 			phy-mode = "rgmii";
 			fixed-link = <0 1 1000 0 0>;
 		};
+
+		demux@08a20000 {
+			compatible	= "st,stih407-c8sectpfe";
+			status		= "okay";
+			reg		= <0x08a20000 0x10000>,
+					  <0x08a00000 0x4000>;
+			reg-names	= "c8sectpfe", "c8sectpfe-ram";
+			interrupts	= <GIC_SPI 34 IRQ_TYPE_NONE>,
+					  <GIC_SPI 35 IRQ_TYPE_NONE>;
+			interrupt-names	= "c8sectpfe-error-irq",
+					  "c8sectpfe-idle-irq";
+			pinctrl-0	= <&pinctrl_tsin0_serial>;
+			pinctrl-1	= <&pinctrl_tsin0_parallel>;
+			pinctrl-2	= <&pinctrl_tsin3_serial>;
+			pinctrl-3	= <&pinctrl_tsin4_serial_alt3>;
+			pinctrl-4	= <&pinctrl_tsin5_serial_alt1>;
+			pinctrl-names	= "tsin0-serial",
+					  "tsin0-parallel",
+					  "tsin3-serial",
+					  "tsin4-serial",
+					  "tsin5-serial";
+			clocks		= <&clk_s_c0_flexgen CLK_PROC_STFE>;
+			clock-names	= "c8sectpfe";
+
+			/* tsin0 is TSA on NIMA */
+			tsin0: port@0 {
+				tsin-num	= <0>;
+				serial-not-parallel;
+				i2c-bus		= <&ssc2>;
+				reset-gpios	= <&pio15 4 GPIO_ACTIVE_HIGH>;
+				dvb-card	= <STV0367_TDA18212_NIMA_1>;
+			};
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/versatile-ab.dts b/arch/arm/boot/dts/versatile-ab.dts
index 01f4019..3279bf1 100644
--- a/arch/arm/boot/dts/versatile-ab.dts
+++ b/arch/arm/boot/dts/versatile-ab.dts
@@ -110,7 +110,11 @@
 			interrupt-parent = <&vic>;
 			interrupts = <31>; /* Cascaded to vic */
 			clear-mask = <0xffffffff>;
-			valid-mask = <0xffc203f8>;
+			/*
+			 * Valid interrupt lines mask according to
+			 * table 4-36 page 4-50 of ARM DUI 0225D
+			 */
+			valid-mask = <0x0760031b>;
 		};
 
 		dma@10130000 {
@@ -266,8 +270,8 @@
 			};
 			mmc@5000 {
 				compatible = "arm,pl180", "arm,primecell";
-				reg = < 0x5000 0x1000>;
-				interrupts-extended = <&vic 22 &sic 2>;
+				reg = <0x5000 0x1000>;
+				interrupts-extended = <&vic 22 &sic 1>;
 				clocks = <&xtal24mhz>, <&pclk>;
 				clock-names = "mclk", "apb_pclk";
 			};
diff --git a/arch/arm/boot/dts/versatile-pb.dts b/arch/arm/boot/dts/versatile-pb.dts
index b83137f..33a8eb2 100644
--- a/arch/arm/boot/dts/versatile-pb.dts
+++ b/arch/arm/boot/dts/versatile-pb.dts
@@ -5,6 +5,16 @@
 	compatible = "arm,versatile-pb";
 
 	amba {
+		/* The Versatile PB is using more SIC IRQ lines than the AB */
+		sic: intc@10003000 {
+			clear-mask = <0xffffffff>;
+			/*
+			 * Valid interrupt lines mask according to
+			 * figure 3-30 page 3-74 of ARM DUI 0224B
+			 */
+			valid-mask = <0x7fe003ff>;
+		};
+
 		gpio2: gpio@101e6000 {
 			compatible = "arm,pl061", "arm,primecell";
 			reg = <0x101e6000 0x1000>;
@@ -67,6 +77,13 @@
 		};
 
 		fpga {
+			mmc@5000 {
+				/*
+				 * Overrides the interrupt assignment from
+				 * the Versatile AB board file.
+				 */
+				interrupts-extended = <&sic 22 &sic 23>;
+			};
 			uart@9000 {
 				compatible = "arm,pl011", "arm,primecell";
 				reg = <0x9000 0x1000>;
@@ -86,7 +103,8 @@
 			mmc@b000 {
 				compatible = "arm,pl180", "arm,primecell";
 				reg = <0xb000 0x1000>;
-				interrupts-extended = <&vic 23 &sic 2>;
+				interrupt-parent = <&sic>;
+				interrupts = <1>, <2>;
 				clocks = <&xtal24mhz>, <&pclk>;
 				clock-names = "mclk", "apb_pclk";
 			};
diff --git a/arch/arm/boot/dts/wm8650.dtsi b/arch/arm/boot/dts/wm8650.dtsi
index b1c59a7..e12213d 100644
--- a/arch/arm/boot/dts/wm8650.dtsi
+++ b/arch/arm/boot/dts/wm8650.dtsi
@@ -187,6 +187,15 @@
 			interrupts = <43>;
 		};
 
+		sdhc@d800a000 {
+			compatible = "wm,wm8505-sdhc";
+			reg = <0xd800a000 0x400>;
+			interrupts = <20>, <21>;
+			clocks = <&clksdhc>;
+			bus-width = <4>;
+			sdon-inverted;
+		};
+
 		fb: fb@d8050800 {
 			compatible = "wm,wm8505-fb";
 			reg = <0xd8050800 0x200>;
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index 69a22fd..cd7b198 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -366,6 +366,7 @@
 CONFIG_CHARGER_MAX14577=m
 CONFIG_CHARGER_MAX77693=m
 CONFIG_CHARGER_TPS65090=y
+CONFIG_AXP20X_POWER=m
 CONFIG_POWER_RESET_AS3722=y
 CONFIG_POWER_RESET_GPIO=y
 CONFIG_POWER_RESET_GPIO_RESTART=y
diff --git a/arch/arm/configs/sunxi_defconfig b/arch/arm/configs/sunxi_defconfig
index 3c36e16..b503a894 100644
--- a/arch/arm/configs/sunxi_defconfig
+++ b/arch/arm/configs/sunxi_defconfig
@@ -84,6 +84,7 @@
 CONFIG_SPI_SUN6I=y
 CONFIG_GPIO_SYSFS=y
 CONFIG_POWER_SUPPLY=y
+CONFIG_AXP20X_POWER=y
 CONFIG_THERMAL=y
 CONFIG_CPU_THERMAL=y
 CONFIG_WATCHDOG=y
diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild
index bd42530..16da638 100644
--- a/arch/arm/include/asm/Kbuild
+++ b/arch/arm/include/asm/Kbuild
@@ -3,6 +3,7 @@
 generic-y += bitsperlong.h
 generic-y += cputime.h
 generic-y += current.h
+generic-y += early_ioremap.h
 generic-y += emergency-restart.h
 generic-y += errno.h
 generic-y += exec.h
diff --git a/arch/arm/include/asm/bug.h b/arch/arm/include/asm/bug.h
index e7335a9..4e6e88a 100644
--- a/arch/arm/include/asm/bug.h
+++ b/arch/arm/include/asm/bug.h
@@ -5,8 +5,6 @@
 #include <linux/types.h>
 #include <asm/opcodes.h>
 
-#ifdef CONFIG_BUG
-
 /*
  * Use a suitable undefined instruction to use for ARM/Thumb2 bug handling.
  * We need to be careful not to conflict with those used by other modules and
@@ -47,7 +45,7 @@
 	unreachable();						\
 } while (0)
 
-#else  /* not CONFIG_DEBUG_BUGVERBOSE */
+#else
 
 #define __BUG(__file, __line, __value)				\
 do {								\
@@ -57,7 +55,6 @@
 #endif  /* CONFIG_DEBUG_BUGVERBOSE */
 
 #define HAVE_ARCH_BUG
-#endif  /* CONFIG_BUG */
 
 #include <asm-generic/bug.h>
 
diff --git a/arch/arm/include/asm/cpuidle.h b/arch/arm/include/asm/cpuidle.h
index 0f84249..3848259 100644
--- a/arch/arm/include/asm/cpuidle.h
+++ b/arch/arm/include/asm/cpuidle.h
@@ -30,7 +30,7 @@
 struct device_node;
 
 struct cpuidle_ops {
-	int (*suspend)(int cpu, unsigned long arg);
+	int (*suspend)(unsigned long arg);
 	int (*init)(struct device_node *, int cpu);
 };
 
diff --git a/arch/arm/include/asm/efi.h b/arch/arm/include/asm/efi.h
new file mode 100644
index 0000000..e0eea72
--- /dev/null
+++ b/arch/arm/include/asm/efi.h
@@ -0,0 +1,83 @@
+/*
+ * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ASM_ARM_EFI_H
+#define __ASM_ARM_EFI_H
+
+#include <asm/cacheflush.h>
+#include <asm/cachetype.h>
+#include <asm/early_ioremap.h>
+#include <asm/fixmap.h>
+#include <asm/highmem.h>
+#include <asm/mach/map.h>
+#include <asm/mmu_context.h>
+#include <asm/pgtable.h>
+
+#ifdef CONFIG_EFI
+void efi_init(void);
+
+int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md);
+
+#define efi_call_virt(f, ...)						\
+({									\
+	efi_##f##_t *__f;						\
+	efi_status_t __s;						\
+									\
+	efi_virtmap_load();						\
+	__f = efi.systab->runtime->f;					\
+	__s = __f(__VA_ARGS__);						\
+	efi_virtmap_unload();						\
+	__s;								\
+})
+
+#define __efi_call_virt(f, ...)						\
+({									\
+	efi_##f##_t *__f;						\
+									\
+	efi_virtmap_load();						\
+	__f = efi.systab->runtime->f;					\
+	__f(__VA_ARGS__);						\
+	efi_virtmap_unload();						\
+})
+
+static inline void efi_set_pgd(struct mm_struct *mm)
+{
+	check_and_switch_context(mm, NULL);
+}
+
+void efi_virtmap_load(void);
+void efi_virtmap_unload(void);
+
+#else
+#define efi_init()
+#endif /* CONFIG_EFI */
+
+/* arch specific definitions used by the stub code */
+
+#define efi_call_early(f, ...) sys_table_arg->boottime->f(__VA_ARGS__)
+
+/*
+ * A reasonable upper bound for the uncompressed kernel size is 32 MBytes,
+ * so we will reserve that amount of memory. We have no easy way to tell what
+ * the actuall size of code + data the uncompressed kernel will use.
+ * If this is insufficient, the decompressor will relocate itself out of the
+ * way before performing the decompression.
+ */
+#define MAX_UNCOMP_KERNEL_SIZE	SZ_32M
+
+/*
+ * The kernel zImage should preferably be located between 32 MB and 128 MB
+ * from the base of DRAM. The min address leaves space for a maximal size
+ * uncompressed image, and the max address is due to how the zImage decompressor
+ * picks a destination address.
+ */
+#define ZIMAGE_OFFSET_LIMIT	SZ_128M
+#define MIN_ZIMAGE_OFFSET	MAX_UNCOMP_KERNEL_SIZE
+#define MAX_FDT_OFFSET		ZIMAGE_OFFSET_LIMIT
+
+#endif /* _ASM_ARM_EFI_H */
diff --git a/arch/arm/include/asm/fixmap.h b/arch/arm/include/asm/fixmap.h
index 58cfe9f..5c17d2d 100644
--- a/arch/arm/include/asm/fixmap.h
+++ b/arch/arm/include/asm/fixmap.h
@@ -19,20 +19,47 @@
 	FIX_TEXT_POKE0,
 	FIX_TEXT_POKE1,
 
-	__end_of_fixed_addresses
+	__end_of_fixmap_region,
+
+	/*
+	 * Share the kmap() region with early_ioremap(): this is guaranteed
+	 * not to clash since early_ioremap() is only available before
+	 * paging_init(), and kmap() only after.
+	 */
+#define NR_FIX_BTMAPS		32
+#define FIX_BTMAPS_SLOTS	7
+#define TOTAL_FIX_BTMAPS	(NR_FIX_BTMAPS * FIX_BTMAPS_SLOTS)
+
+	FIX_BTMAP_END = __end_of_permanent_fixed_addresses,
+	FIX_BTMAP_BEGIN = FIX_BTMAP_END + TOTAL_FIX_BTMAPS - 1,
+	__end_of_early_ioremap_region
 };
 
+static const enum fixed_addresses __end_of_fixed_addresses =
+	__end_of_fixmap_region > __end_of_early_ioremap_region ?
+	__end_of_fixmap_region : __end_of_early_ioremap_region;
+
 #define FIXMAP_PAGE_COMMON	(L_PTE_YOUNG | L_PTE_PRESENT | L_PTE_XN | L_PTE_DIRTY)
 
 #define FIXMAP_PAGE_NORMAL	(FIXMAP_PAGE_COMMON | L_PTE_MT_WRITEBACK)
+#define FIXMAP_PAGE_RO		(FIXMAP_PAGE_NORMAL | L_PTE_RDONLY)
 
 /* Used by set_fixmap_(io|nocache), both meant for mapping a device */
 #define FIXMAP_PAGE_IO		(FIXMAP_PAGE_COMMON | L_PTE_MT_DEV_SHARED | L_PTE_SHARED)
 #define FIXMAP_PAGE_NOCACHE	FIXMAP_PAGE_IO
 
+#define __early_set_fixmap	__set_fixmap
+
+#ifdef CONFIG_MMU
+
 void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot);
 void __init early_fixmap_init(void);
 
 #include <asm-generic/fixmap.h>
 
+#else
+
+static inline void early_fixmap_init(void) { }
+
+#endif
 #endif
diff --git a/arch/arm/include/asm/hardirq.h b/arch/arm/include/asm/hardirq.h
index fe3ea77..3d7351c 100644
--- a/arch/arm/include/asm/hardirq.h
+++ b/arch/arm/include/asm/hardirq.h
@@ -5,7 +5,7 @@
 #include <linux/threads.h>
 #include <asm/irq.h>
 
-#define NR_IPI	8
+#define NR_IPI	7
 
 typedef struct {
 	unsigned int __softirq_pending;
diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h
index dc641dd..e22089f 100644
--- a/arch/arm/include/asm/kvm_arm.h
+++ b/arch/arm/include/asm/kvm_arm.h
@@ -19,6 +19,7 @@
 #ifndef __ARM_KVM_ARM_H__
 #define __ARM_KVM_ARM_H__
 
+#include <linux/const.h>
 #include <linux/types.h>
 
 /* Hyp Configuration Register (HCR) bits */
@@ -132,10 +133,9 @@
  * space.
  */
 #define KVM_PHYS_SHIFT	(40)
-#define KVM_PHYS_SIZE	(1ULL << KVM_PHYS_SHIFT)
-#define KVM_PHYS_MASK	(KVM_PHYS_SIZE - 1ULL)
-#define PTRS_PER_S2_PGD	(1ULL << (KVM_PHYS_SHIFT - 30))
-#define S2_PGD_ORDER	get_order(PTRS_PER_S2_PGD * sizeof(pgd_t))
+#define KVM_PHYS_SIZE	(_AC(1, ULL) << KVM_PHYS_SHIFT)
+#define KVM_PHYS_MASK	(KVM_PHYS_SIZE - _AC(1, ULL))
+#define PTRS_PER_S2_PGD	(_AC(1, ULL) << (KVM_PHYS_SHIFT - 30))
 
 /* Virtualization Translation Control Register (VTCR) bits */
 #define VTCR_SH0	(3 << 12)
@@ -162,17 +162,17 @@
 #define VTTBR_X		(5 - KVM_T0SZ)
 #endif
 #define VTTBR_BADDR_SHIFT (VTTBR_X - 1)
-#define VTTBR_BADDR_MASK  (((1LLU << (40 - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
-#define VTTBR_VMID_SHIFT  (48LLU)
-#define VTTBR_VMID_MASK	  (0xffLLU << VTTBR_VMID_SHIFT)
+#define VTTBR_BADDR_MASK  (((_AC(1, ULL) << (40 - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
+#define VTTBR_VMID_SHIFT  _AC(48, ULL)
+#define VTTBR_VMID_MASK(size)	(_AT(u64, (1 << size) - 1) << VTTBR_VMID_SHIFT)
 
 /* Hyp Syndrome Register (HSR) bits */
 #define HSR_EC_SHIFT	(26)
-#define HSR_EC		(0x3fU << HSR_EC_SHIFT)
-#define HSR_IL		(1U << 25)
+#define HSR_EC		(_AC(0x3f, UL) << HSR_EC_SHIFT)
+#define HSR_IL		(_AC(1, UL) << 25)
 #define HSR_ISS		(HSR_IL - 1)
 #define HSR_ISV_SHIFT	(24)
-#define HSR_ISV		(1U << HSR_ISV_SHIFT)
+#define HSR_ISV		(_AC(1, UL) << HSR_ISV_SHIFT)
 #define HSR_SRT_SHIFT	(16)
 #define HSR_SRT_MASK	(0xf << HSR_SRT_SHIFT)
 #define HSR_FSC		(0x3f)
@@ -180,9 +180,9 @@
 #define HSR_SSE		(1 << 21)
 #define HSR_WNR		(1 << 6)
 #define HSR_CV_SHIFT	(24)
-#define HSR_CV		(1U << HSR_CV_SHIFT)
+#define HSR_CV		(_AC(1, UL) << HSR_CV_SHIFT)
 #define HSR_COND_SHIFT	(20)
-#define HSR_COND	(0xfU << HSR_COND_SHIFT)
+#define HSR_COND	(_AC(0xf, UL) << HSR_COND_SHIFT)
 
 #define FSC_FAULT	(0x04)
 #define FSC_ACCESS	(0x08)
@@ -210,13 +210,13 @@
 #define HSR_EC_DABT	(0x24)
 #define HSR_EC_DABT_HYP	(0x25)
 
-#define HSR_WFI_IS_WFE		(1U << 0)
+#define HSR_WFI_IS_WFE		(_AC(1, UL) << 0)
 
-#define HSR_HVC_IMM_MASK	((1UL << 16) - 1)
+#define HSR_HVC_IMM_MASK	((_AC(1, UL) << 16) - 1)
 
-#define HSR_DABT_S1PTW		(1U << 7)
-#define HSR_DABT_CM		(1U << 8)
-#define HSR_DABT_EA		(1U << 9)
+#define HSR_DABT_S1PTW		(_AC(1, UL) << 7)
+#define HSR_DABT_CM		(_AC(1, UL) << 8)
+#define HSR_DABT_EA		(_AC(1, UL) << 9)
 
 #define kvm_arm_exception_type	\
 	{0, "RESET" }, 		\
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index 6692982c..f9f2779 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -150,6 +150,12 @@
 	u32 halt_successful_poll;
 	u32 halt_attempted_poll;
 	u32 halt_wakeup;
+	u32 hvc_exit_stat;
+	u64 wfe_exit_stat;
+	u64 wfi_exit_stat;
+	u64 mmio_exit_user;
+	u64 mmio_exit_kernel;
+	u64 exits;
 };
 
 int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init);
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index 405aa18..9203c21 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -279,6 +279,11 @@
 				       pgd_t *merged_hyp_pgd,
 				       unsigned long hyp_idmap_start) { }
 
+static inline unsigned int kvm_get_vmid_bits(void)
+{
+	return 8;
+}
+
 #endif	/* !__ASSEMBLY__ */
 
 #endif /* __ARM_KVM_MMU_H__ */
diff --git a/arch/arm/include/asm/mach/map.h b/arch/arm/include/asm/mach/map.h
index f98c7f3..9b7c328 100644
--- a/arch/arm/include/asm/mach/map.h
+++ b/arch/arm/include/asm/mach/map.h
@@ -42,6 +42,8 @@
 extern void iotable_init(struct map_desc *, int);
 extern void vm_reserve_area_early(unsigned long addr, unsigned long size,
 				  void *caller);
+extern void create_mapping_late(struct mm_struct *mm, struct map_desc *md,
+				bool ng);
 
 #ifdef CONFIG_DEBUG_LL
 extern void debug_ll_addr(unsigned long *paddr, unsigned long *vaddr);
diff --git a/arch/arm/include/asm/mmu_context.h b/arch/arm/include/asm/mmu_context.h
index 9b32f76..432ce81 100644
--- a/arch/arm/include/asm/mmu_context.h
+++ b/arch/arm/include/asm/mmu_context.h
@@ -26,7 +26,7 @@
 #ifdef CONFIG_CPU_HAS_ASID
 
 void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk);
-#define init_new_context(tsk,mm)	({ atomic64_set(&mm->context.id, 0); 0; })
+#define init_new_context(tsk,mm)	({ atomic64_set(&(mm)->context.id, 0); 0; })
 
 #ifdef CONFIG_ARM_ERRATA_798181
 void a15_erratum_get_cpumask(int this_cpu, struct mm_struct *mm,
diff --git a/arch/arm/include/asm/paravirt.h b/arch/arm/include/asm/paravirt.h
new file mode 100644
index 0000000..8435ff5
--- /dev/null
+++ b/arch/arm/include/asm/paravirt.h
@@ -0,0 +1,20 @@
+#ifndef _ASM_ARM_PARAVIRT_H
+#define _ASM_ARM_PARAVIRT_H
+
+#ifdef CONFIG_PARAVIRT
+struct static_key;
+extern struct static_key paravirt_steal_enabled;
+extern struct static_key paravirt_steal_rq_enabled;
+
+struct pv_time_ops {
+	unsigned long long (*steal_clock)(int cpu);
+};
+extern struct pv_time_ops pv_time_ops;
+
+static inline u64 paravirt_steal_clock(int cpu)
+{
+	return pv_time_ops.steal_clock(cpu);
+}
+#endif
+
+#endif
diff --git a/arch/arm/include/asm/psci.h b/arch/arm/include/asm/psci.h
index 68ee3ce..b4c6d99 100644
--- a/arch/arm/include/asm/psci.h
+++ b/arch/arm/include/asm/psci.h
@@ -16,7 +16,7 @@
 
 extern struct smp_operations psci_smp_ops;
 
-#ifdef CONFIG_ARM_PSCI
+#if defined(CONFIG_SMP) && defined(CONFIG_ARM_PSCI)
 bool psci_smp_available(void);
 #else
 static inline bool psci_smp_available(void) { return false; }
diff --git a/arch/arm/include/asm/setup.h b/arch/arm/include/asm/setup.h
index e0adb9f..3613d7e 100644
--- a/arch/arm/include/asm/setup.h
+++ b/arch/arm/include/asm/setup.h
@@ -25,4 +25,10 @@
 extern void early_print(const char *str, ...);
 extern void dump_machine_table(void);
 
+#ifdef CONFIG_ATAGS_PROC
+extern void save_atags(const struct tag *tags);
+#else
+static inline void save_atags(const struct tag *tags) { }
+#endif
+
 #endif
diff --git a/arch/arm/include/asm/xen/hypercall.h b/arch/arm/include/asm/xen/hypercall.h
index 712b50e..d769972 100644
--- a/arch/arm/include/asm/xen/hypercall.h
+++ b/arch/arm/include/asm/xen/hypercall.h
@@ -35,6 +35,7 @@
 
 #include <xen/interface/xen.h>
 #include <xen/interface/sched.h>
+#include <xen/interface/platform.h>
 
 long privcmd_call(unsigned call, unsigned long a1,
 		unsigned long a2, unsigned long a3,
@@ -49,6 +50,12 @@
 int HYPERVISOR_physdev_op(int cmd, void *arg);
 int HYPERVISOR_vcpu_op(int cmd, int vcpuid, void *extra_args);
 int HYPERVISOR_tmem_op(void *arg);
+int HYPERVISOR_platform_op_raw(void *arg);
+static inline int HYPERVISOR_platform_op(struct xen_platform_op *op)
+{
+	op->interface_version = XENPF_INTERFACE_VERSION;
+	return HYPERVISOR_platform_op_raw(op);
+}
 int HYPERVISOR_multicall(struct multicall_entry *calls, uint32_t nr);
 
 static inline int
diff --git a/arch/arm/include/asm/xen/interface.h b/arch/arm/include/asm/xen/interface.h
index 5006600..75d5968 100644
--- a/arch/arm/include/asm/xen/interface.h
+++ b/arch/arm/include/asm/xen/interface.h
@@ -27,6 +27,8 @@
 		(hnd).p = val;				\
 	} while (0)
 
+#define __HYPERVISOR_platform_op_raw __HYPERVISOR_platform_op
+
 #ifndef __ASSEMBLY__
 /* Explicitly size integers that represent pfns in the interface with
  * Xen so that we can have one ABI that works for 32 and 64 bit guests.
@@ -76,6 +78,7 @@
 	u32   version;
 	u32   sec;
 	u32   nsec;
+	u32   sec_hi;
 } __attribute__((__packed__));
 #endif
 
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index af9e59b..2c5f160 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -73,14 +73,15 @@
 obj-$(CONFIG_PERF_EVENTS)	+= perf_regs.o perf_callchain.o
 obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event_xscale.o perf_event_v6.o \
 				   perf_event_v7.o
-CFLAGS_pj4-cp0.o		:= -marm
 AFLAGS_iwmmxt.o			:= -Wa,-mcpu=iwmmxt
 obj-$(CONFIG_ARM_CPU_TOPOLOGY)  += topology.o
 obj-$(CONFIG_VDSO)		+= vdso.o
+obj-$(CONFIG_EFI)		+= efi.o
 
 ifneq ($(CONFIG_ARCH_EBSA110),y)
   obj-y		+= io.o
 endif
+obj-$(CONFIG_PARAVIRT)	+= paravirt.o
 
 head-y			:= head$(MMUEXT).o
 obj-$(CONFIG_DEBUG_LL)	+= debug.o
@@ -88,8 +89,9 @@
 
 obj-$(CONFIG_ARM_VIRT_EXT)	+= hyp-stub.o
 ifeq ($(CONFIG_ARM_PSCI),y)
-obj-y				+= psci-call.o
 obj-$(CONFIG_SMP)		+= psci_smp.o
 endif
 
+obj-$(CONFIG_HAVE_ARM_SMCCC)	+= smccc-call.o
+
 extra-y := $(head-y) vmlinux.lds
diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c
index f89811f..7e45f69 100644
--- a/arch/arm/kernel/armksyms.c
+++ b/arch/arm/kernel/armksyms.c
@@ -16,6 +16,7 @@
 #include <linux/syscalls.h>
 #include <linux/uaccess.h>
 #include <linux/io.h>
+#include <linux/arm-smccc.h>
 
 #include <asm/checksum.h>
 #include <asm/ftrace.h>
@@ -175,3 +176,8 @@
 EXPORT_SYMBOL(__pv_phys_pfn_offset);
 EXPORT_SYMBOL(__pv_offset);
 #endif
+
+#ifdef CONFIG_HAVE_ARM_SMCCC
+EXPORT_SYMBOL(arm_smccc_smc);
+EXPORT_SYMBOL(arm_smccc_hvc);
+#endif
diff --git a/arch/arm/kernel/atags.h b/arch/arm/kernel/atags.h
index ec4164d..edfa226 100644
--- a/arch/arm/kernel/atags.h
+++ b/arch/arm/kernel/atags.h
@@ -1,9 +1,3 @@
-#ifdef CONFIG_ATAGS_PROC
-extern void save_atags(struct tag *tags);
-#else
-static inline void save_atags(struct tag *tags) { }
-#endif
-
 void convert_to_tag_list(struct tag *tags);
 
 #ifdef CONFIG_ATAGS
diff --git a/arch/arm/kernel/cpuidle.c b/arch/arm/kernel/cpuidle.c
index 318da33..703926e 100644
--- a/arch/arm/kernel/cpuidle.c
+++ b/arch/arm/kernel/cpuidle.c
@@ -56,7 +56,7 @@
 	int cpu = smp_processor_id();
 
 	if (cpuidle_ops[cpu].suspend)
-		ret = cpuidle_ops[cpu].suspend(cpu, index);
+		ret = cpuidle_ops[cpu].suspend(index);
 
 	return ret;
 }
diff --git a/arch/arm/kernel/efi.c b/arch/arm/kernel/efi.c
new file mode 100644
index 0000000..ff8a9d8
--- /dev/null
+++ b/arch/arm/kernel/efi.c
@@ -0,0 +1,38 @@
+/*
+ * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/efi.h>
+#include <asm/efi.h>
+#include <asm/mach/map.h>
+#include <asm/mmu_context.h>
+
+int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md)
+{
+	struct map_desc desc = {
+		.virtual	= md->virt_addr,
+		.pfn		= __phys_to_pfn(md->phys_addr),
+		.length		= md->num_pages * EFI_PAGE_SIZE,
+	};
+
+	/*
+	 * Order is important here: memory regions may have all of the
+	 * bits below set (and usually do), so we check them in order of
+	 * preference.
+	 */
+	if (md->attribute & EFI_MEMORY_WB)
+		desc.type = MT_MEMORY_RWX;
+	else if (md->attribute & EFI_MEMORY_WT)
+		desc.type = MT_MEMORY_RWX_NONCACHED;
+	else if (md->attribute & EFI_MEMORY_WC)
+		desc.type = MT_DEVICE_WC;
+	else
+		desc.type = MT_DEVICE;
+
+	create_mapping_late(mm, &desc, true);
+	return 0;
+}
diff --git a/arch/arm/kernel/entry-v7m.S b/arch/arm/kernel/entry-v7m.S
index b6c8bb9..907534f 100644
--- a/arch/arm/kernel/entry-v7m.S
+++ b/arch/arm/kernel/entry-v7m.S
@@ -88,7 +88,7 @@
 	@ execute the pending work, including reschedule
 	get_thread_info tsk
 	mov	why, #0
-	b	ret_to_user
+	b	ret_to_user_from_irq
 ENDPROC(__pendsv_entry)
 
 /*
diff --git a/arch/arm/kernel/paravirt.c b/arch/arm/kernel/paravirt.c
new file mode 100644
index 0000000..53f371e
--- /dev/null
+++ b/arch/arm/kernel/paravirt.c
@@ -0,0 +1,25 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Copyright (C) 2013 Citrix Systems
+ *
+ * Author: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
+ */
+
+#include <linux/export.h>
+#include <linux/jump_label.h>
+#include <linux/types.h>
+#include <asm/paravirt.h>
+
+struct static_key paravirt_steal_enabled;
+struct static_key paravirt_steal_rq_enabled;
+
+struct pv_time_ops pv_time_ops;
+EXPORT_SYMBOL_GPL(pv_time_ops);
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 126dc67..4152158f 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -35,133 +35,117 @@
  * but the encodings are considered to be `reserved' in the case that
  * they are not available.
  */
-enum armv7_perf_types {
-	ARMV7_PERFCTR_PMNC_SW_INCR			= 0x00,
-	ARMV7_PERFCTR_L1_ICACHE_REFILL			= 0x01,
-	ARMV7_PERFCTR_ITLB_REFILL			= 0x02,
-	ARMV7_PERFCTR_L1_DCACHE_REFILL			= 0x03,
-	ARMV7_PERFCTR_L1_DCACHE_ACCESS			= 0x04,
-	ARMV7_PERFCTR_DTLB_REFILL			= 0x05,
-	ARMV7_PERFCTR_MEM_READ				= 0x06,
-	ARMV7_PERFCTR_MEM_WRITE				= 0x07,
-	ARMV7_PERFCTR_INSTR_EXECUTED			= 0x08,
-	ARMV7_PERFCTR_EXC_TAKEN				= 0x09,
-	ARMV7_PERFCTR_EXC_EXECUTED			= 0x0A,
-	ARMV7_PERFCTR_CID_WRITE				= 0x0B,
+#define ARMV7_PERFCTR_PMNC_SW_INCR			0x00
+#define ARMV7_PERFCTR_L1_ICACHE_REFILL			0x01
+#define ARMV7_PERFCTR_ITLB_REFILL			0x02
+#define ARMV7_PERFCTR_L1_DCACHE_REFILL			0x03
+#define ARMV7_PERFCTR_L1_DCACHE_ACCESS			0x04
+#define ARMV7_PERFCTR_DTLB_REFILL			0x05
+#define ARMV7_PERFCTR_MEM_READ				0x06
+#define ARMV7_PERFCTR_MEM_WRITE				0x07
+#define ARMV7_PERFCTR_INSTR_EXECUTED			0x08
+#define ARMV7_PERFCTR_EXC_TAKEN				0x09
+#define ARMV7_PERFCTR_EXC_EXECUTED			0x0A
+#define ARMV7_PERFCTR_CID_WRITE				0x0B
 
-	/*
-	 * ARMV7_PERFCTR_PC_WRITE is equivalent to HW_BRANCH_INSTRUCTIONS.
-	 * It counts:
-	 *  - all (taken) branch instructions,
-	 *  - instructions that explicitly write the PC,
-	 *  - exception generating instructions.
-	 */
-	ARMV7_PERFCTR_PC_WRITE				= 0x0C,
-	ARMV7_PERFCTR_PC_IMM_BRANCH			= 0x0D,
-	ARMV7_PERFCTR_PC_PROC_RETURN			= 0x0E,
-	ARMV7_PERFCTR_MEM_UNALIGNED_ACCESS		= 0x0F,
-	ARMV7_PERFCTR_PC_BRANCH_MIS_PRED		= 0x10,
-	ARMV7_PERFCTR_CLOCK_CYCLES			= 0x11,
-	ARMV7_PERFCTR_PC_BRANCH_PRED			= 0x12,
+/*
+ * ARMV7_PERFCTR_PC_WRITE is equivalent to HW_BRANCH_INSTRUCTIONS.
+ * It counts:
+ *  - all (taken) branch instructions,
+ *  - instructions that explicitly write the PC,
+ *  - exception generating instructions.
+ */
+#define ARMV7_PERFCTR_PC_WRITE				0x0C
+#define ARMV7_PERFCTR_PC_IMM_BRANCH			0x0D
+#define ARMV7_PERFCTR_PC_PROC_RETURN			0x0E
+#define ARMV7_PERFCTR_MEM_UNALIGNED_ACCESS		0x0F
+#define ARMV7_PERFCTR_PC_BRANCH_MIS_PRED		0x10
+#define ARMV7_PERFCTR_CLOCK_CYCLES			0x11
+#define ARMV7_PERFCTR_PC_BRANCH_PRED			0x12
 
-	/* These events are defined by the PMUv2 supplement (ARM DDI 0457A). */
-	ARMV7_PERFCTR_MEM_ACCESS			= 0x13,
-	ARMV7_PERFCTR_L1_ICACHE_ACCESS			= 0x14,
-	ARMV7_PERFCTR_L1_DCACHE_WB			= 0x15,
-	ARMV7_PERFCTR_L2_CACHE_ACCESS			= 0x16,
-	ARMV7_PERFCTR_L2_CACHE_REFILL			= 0x17,
-	ARMV7_PERFCTR_L2_CACHE_WB			= 0x18,
-	ARMV7_PERFCTR_BUS_ACCESS			= 0x19,
-	ARMV7_PERFCTR_MEM_ERROR				= 0x1A,
-	ARMV7_PERFCTR_INSTR_SPEC			= 0x1B,
-	ARMV7_PERFCTR_TTBR_WRITE			= 0x1C,
-	ARMV7_PERFCTR_BUS_CYCLES			= 0x1D,
+/* These events are defined by the PMUv2 supplement (ARM DDI 0457A). */
+#define ARMV7_PERFCTR_MEM_ACCESS			0x13
+#define ARMV7_PERFCTR_L1_ICACHE_ACCESS			0x14
+#define ARMV7_PERFCTR_L1_DCACHE_WB			0x15
+#define ARMV7_PERFCTR_L2_CACHE_ACCESS			0x16
+#define ARMV7_PERFCTR_L2_CACHE_REFILL			0x17
+#define ARMV7_PERFCTR_L2_CACHE_WB			0x18
+#define ARMV7_PERFCTR_BUS_ACCESS			0x19
+#define ARMV7_PERFCTR_MEM_ERROR				0x1A
+#define ARMV7_PERFCTR_INSTR_SPEC			0x1B
+#define ARMV7_PERFCTR_TTBR_WRITE			0x1C
+#define ARMV7_PERFCTR_BUS_CYCLES			0x1D
 
-	ARMV7_PERFCTR_CPU_CYCLES			= 0xFF
-};
+#define ARMV7_PERFCTR_CPU_CYCLES			0xFF
 
 /* ARMv7 Cortex-A8 specific event types */
-enum armv7_a8_perf_types {
-	ARMV7_A8_PERFCTR_L2_CACHE_ACCESS		= 0x43,
-	ARMV7_A8_PERFCTR_L2_CACHE_REFILL		= 0x44,
-	ARMV7_A8_PERFCTR_L1_ICACHE_ACCESS		= 0x50,
-	ARMV7_A8_PERFCTR_STALL_ISIDE			= 0x56,
-};
+#define ARMV7_A8_PERFCTR_L2_CACHE_ACCESS		0x43
+#define ARMV7_A8_PERFCTR_L2_CACHE_REFILL		0x44
+#define ARMV7_A8_PERFCTR_L1_ICACHE_ACCESS		0x50
+#define ARMV7_A8_PERFCTR_STALL_ISIDE			0x56
 
 /* ARMv7 Cortex-A9 specific event types */
-enum armv7_a9_perf_types {
-	ARMV7_A9_PERFCTR_INSTR_CORE_RENAME		= 0x68,
-	ARMV7_A9_PERFCTR_STALL_ICACHE			= 0x60,
-	ARMV7_A9_PERFCTR_STALL_DISPATCH			= 0x66,
-};
+#define ARMV7_A9_PERFCTR_INSTR_CORE_RENAME		0x68
+#define ARMV7_A9_PERFCTR_STALL_ICACHE			0x60
+#define ARMV7_A9_PERFCTR_STALL_DISPATCH			0x66
 
 /* ARMv7 Cortex-A5 specific event types */
-enum armv7_a5_perf_types {
-	ARMV7_A5_PERFCTR_PREFETCH_LINEFILL		= 0xc2,
-	ARMV7_A5_PERFCTR_PREFETCH_LINEFILL_DROP		= 0xc3,
-};
+#define ARMV7_A5_PERFCTR_PREFETCH_LINEFILL		0xc2
+#define ARMV7_A5_PERFCTR_PREFETCH_LINEFILL_DROP		0xc3
 
 /* ARMv7 Cortex-A15 specific event types */
-enum armv7_a15_perf_types {
-	ARMV7_A15_PERFCTR_L1_DCACHE_ACCESS_READ		= 0x40,
-	ARMV7_A15_PERFCTR_L1_DCACHE_ACCESS_WRITE	= 0x41,
-	ARMV7_A15_PERFCTR_L1_DCACHE_REFILL_READ		= 0x42,
-	ARMV7_A15_PERFCTR_L1_DCACHE_REFILL_WRITE	= 0x43,
+#define ARMV7_A15_PERFCTR_L1_DCACHE_ACCESS_READ		0x40
+#define ARMV7_A15_PERFCTR_L1_DCACHE_ACCESS_WRITE	0x41
+#define ARMV7_A15_PERFCTR_L1_DCACHE_REFILL_READ		0x42
+#define ARMV7_A15_PERFCTR_L1_DCACHE_REFILL_WRITE	0x43
 
-	ARMV7_A15_PERFCTR_DTLB_REFILL_L1_READ		= 0x4C,
-	ARMV7_A15_PERFCTR_DTLB_REFILL_L1_WRITE		= 0x4D,
+#define ARMV7_A15_PERFCTR_DTLB_REFILL_L1_READ		0x4C
+#define ARMV7_A15_PERFCTR_DTLB_REFILL_L1_WRITE		0x4D
 
-	ARMV7_A15_PERFCTR_L2_CACHE_ACCESS_READ		= 0x50,
-	ARMV7_A15_PERFCTR_L2_CACHE_ACCESS_WRITE		= 0x51,
-	ARMV7_A15_PERFCTR_L2_CACHE_REFILL_READ		= 0x52,
-	ARMV7_A15_PERFCTR_L2_CACHE_REFILL_WRITE		= 0x53,
+#define ARMV7_A15_PERFCTR_L2_CACHE_ACCESS_READ		0x50
+#define ARMV7_A15_PERFCTR_L2_CACHE_ACCESS_WRITE		0x51
+#define ARMV7_A15_PERFCTR_L2_CACHE_REFILL_READ		0x52
+#define ARMV7_A15_PERFCTR_L2_CACHE_REFILL_WRITE		0x53
 
-	ARMV7_A15_PERFCTR_PC_WRITE_SPEC			= 0x76,
-};
+#define ARMV7_A15_PERFCTR_PC_WRITE_SPEC			0x76
 
 /* ARMv7 Cortex-A12 specific event types */
-enum armv7_a12_perf_types {
-	ARMV7_A12_PERFCTR_L1_DCACHE_ACCESS_READ		= 0x40,
-	ARMV7_A12_PERFCTR_L1_DCACHE_ACCESS_WRITE	= 0x41,
+#define ARMV7_A12_PERFCTR_L1_DCACHE_ACCESS_READ		0x40
+#define ARMV7_A12_PERFCTR_L1_DCACHE_ACCESS_WRITE	0x41
 
-	ARMV7_A12_PERFCTR_L2_CACHE_ACCESS_READ		= 0x50,
-	ARMV7_A12_PERFCTR_L2_CACHE_ACCESS_WRITE		= 0x51,
+#define ARMV7_A12_PERFCTR_L2_CACHE_ACCESS_READ		0x50
+#define ARMV7_A12_PERFCTR_L2_CACHE_ACCESS_WRITE		0x51
 
-	ARMV7_A12_PERFCTR_PC_WRITE_SPEC			= 0x76,
+#define ARMV7_A12_PERFCTR_PC_WRITE_SPEC			0x76
 
-	ARMV7_A12_PERFCTR_PF_TLB_REFILL			= 0xe7,
-};
+#define ARMV7_A12_PERFCTR_PF_TLB_REFILL			0xe7
 
 /* ARMv7 Krait specific event types */
-enum krait_perf_types {
-	KRAIT_PMRESR0_GROUP0				= 0xcc,
-	KRAIT_PMRESR1_GROUP0				= 0xd0,
-	KRAIT_PMRESR2_GROUP0				= 0xd4,
-	KRAIT_VPMRESR0_GROUP0				= 0xd8,
+#define KRAIT_PMRESR0_GROUP0				0xcc
+#define KRAIT_PMRESR1_GROUP0				0xd0
+#define KRAIT_PMRESR2_GROUP0				0xd4
+#define KRAIT_VPMRESR0_GROUP0				0xd8
 
-	KRAIT_PERFCTR_L1_ICACHE_ACCESS			= 0x10011,
-	KRAIT_PERFCTR_L1_ICACHE_MISS			= 0x10010,
+#define KRAIT_PERFCTR_L1_ICACHE_ACCESS			0x10011
+#define KRAIT_PERFCTR_L1_ICACHE_MISS			0x10010
 
-	KRAIT_PERFCTR_L1_ITLB_ACCESS			= 0x12222,
-	KRAIT_PERFCTR_L1_DTLB_ACCESS			= 0x12210,
-};
+#define KRAIT_PERFCTR_L1_ITLB_ACCESS			0x12222
+#define KRAIT_PERFCTR_L1_DTLB_ACCESS			0x12210
 
 /* ARMv7 Scorpion specific event types */
-enum scorpion_perf_types {
-	SCORPION_LPM0_GROUP0				= 0x4c,
-	SCORPION_LPM1_GROUP0				= 0x50,
-	SCORPION_LPM2_GROUP0				= 0x54,
-	SCORPION_L2LPM_GROUP0				= 0x58,
-	SCORPION_VLPM_GROUP0				= 0x5c,
+#define SCORPION_LPM0_GROUP0				0x4c
+#define SCORPION_LPM1_GROUP0				0x50
+#define SCORPION_LPM2_GROUP0				0x54
+#define SCORPION_L2LPM_GROUP0				0x58
+#define SCORPION_VLPM_GROUP0				0x5c
 
-	SCORPION_ICACHE_ACCESS				= 0x10053,
-	SCORPION_ICACHE_MISS				= 0x10052,
+#define SCORPION_ICACHE_ACCESS				0x10053
+#define SCORPION_ICACHE_MISS				0x10052
 
-	SCORPION_DTLB_ACCESS				= 0x12013,
-	SCORPION_DTLB_MISS				= 0x12012,
+#define SCORPION_DTLB_ACCESS				0x12013
+#define SCORPION_DTLB_MISS				0x12012
 
-	SCORPION_ITLB_MISS				= 0x12021,
-};
+#define SCORPION_ITLB_MISS				0x12021
 
 /*
  * Cortex-A8 HW events mapping
@@ -547,6 +531,134 @@
 	[C(BPU)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
 };
 
+PMU_FORMAT_ATTR(event, "config:0-7");
+
+static struct attribute *armv7_pmu_format_attrs[] = {
+	&format_attr_event.attr,
+	NULL,
+};
+
+static struct attribute_group armv7_pmu_format_attr_group = {
+	.name = "format",
+	.attrs = armv7_pmu_format_attrs,
+};
+
+#define ARMV7_EVENT_ATTR_RESOLVE(m) #m
+#define ARMV7_EVENT_ATTR(name, config) \
+	PMU_EVENT_ATTR_STRING(name, armv7_event_attr_##name, \
+			      "event=" ARMV7_EVENT_ATTR_RESOLVE(config))
+
+ARMV7_EVENT_ATTR(sw_incr, ARMV7_PERFCTR_PMNC_SW_INCR);
+ARMV7_EVENT_ATTR(l1i_cache_refill, ARMV7_PERFCTR_L1_ICACHE_REFILL);
+ARMV7_EVENT_ATTR(l1i_tlb_refill, ARMV7_PERFCTR_ITLB_REFILL);
+ARMV7_EVENT_ATTR(l1d_cache_refill, ARMV7_PERFCTR_L1_DCACHE_REFILL);
+ARMV7_EVENT_ATTR(l1d_cache, ARMV7_PERFCTR_L1_DCACHE_ACCESS);
+ARMV7_EVENT_ATTR(l1d_tlb_refill, ARMV7_PERFCTR_DTLB_REFILL);
+ARMV7_EVENT_ATTR(ld_retired, ARMV7_PERFCTR_MEM_READ);
+ARMV7_EVENT_ATTR(st_retired, ARMV7_PERFCTR_MEM_WRITE);
+ARMV7_EVENT_ATTR(inst_retired, ARMV7_PERFCTR_INSTR_EXECUTED);
+ARMV7_EVENT_ATTR(exc_taken, ARMV7_PERFCTR_EXC_TAKEN);
+ARMV7_EVENT_ATTR(exc_return, ARMV7_PERFCTR_EXC_EXECUTED);
+ARMV7_EVENT_ATTR(cid_write_retired, ARMV7_PERFCTR_CID_WRITE);
+ARMV7_EVENT_ATTR(pc_write_retired, ARMV7_PERFCTR_PC_WRITE);
+ARMV7_EVENT_ATTR(br_immed_retired, ARMV7_PERFCTR_PC_IMM_BRANCH);
+ARMV7_EVENT_ATTR(br_return_retired, ARMV7_PERFCTR_PC_PROC_RETURN);
+ARMV7_EVENT_ATTR(unaligned_ldst_retired, ARMV7_PERFCTR_MEM_UNALIGNED_ACCESS);
+ARMV7_EVENT_ATTR(br_mis_pred, ARMV7_PERFCTR_PC_BRANCH_MIS_PRED);
+ARMV7_EVENT_ATTR(cpu_cycles, ARMV7_PERFCTR_CLOCK_CYCLES);
+ARMV7_EVENT_ATTR(br_pred, ARMV7_PERFCTR_PC_BRANCH_PRED);
+
+static struct attribute *armv7_pmuv1_event_attrs[] = {
+	&armv7_event_attr_sw_incr.attr.attr,
+	&armv7_event_attr_l1i_cache_refill.attr.attr,
+	&armv7_event_attr_l1i_tlb_refill.attr.attr,
+	&armv7_event_attr_l1d_cache_refill.attr.attr,
+	&armv7_event_attr_l1d_cache.attr.attr,
+	&armv7_event_attr_l1d_tlb_refill.attr.attr,
+	&armv7_event_attr_ld_retired.attr.attr,
+	&armv7_event_attr_st_retired.attr.attr,
+	&armv7_event_attr_inst_retired.attr.attr,
+	&armv7_event_attr_exc_taken.attr.attr,
+	&armv7_event_attr_exc_return.attr.attr,
+	&armv7_event_attr_cid_write_retired.attr.attr,
+	&armv7_event_attr_pc_write_retired.attr.attr,
+	&armv7_event_attr_br_immed_retired.attr.attr,
+	&armv7_event_attr_br_return_retired.attr.attr,
+	&armv7_event_attr_unaligned_ldst_retired.attr.attr,
+	&armv7_event_attr_br_mis_pred.attr.attr,
+	&armv7_event_attr_cpu_cycles.attr.attr,
+	&armv7_event_attr_br_pred.attr.attr,
+	NULL,
+};
+
+static struct attribute_group armv7_pmuv1_events_attr_group = {
+	.name = "events",
+	.attrs = armv7_pmuv1_event_attrs,
+};
+
+static const struct attribute_group *armv7_pmuv1_attr_groups[] = {
+	&armv7_pmuv1_events_attr_group,
+	&armv7_pmu_format_attr_group,
+	NULL,
+};
+
+ARMV7_EVENT_ATTR(mem_access, ARMV7_PERFCTR_MEM_ACCESS);
+ARMV7_EVENT_ATTR(l1i_cache, ARMV7_PERFCTR_L1_ICACHE_ACCESS);
+ARMV7_EVENT_ATTR(l1d_cache_wb, ARMV7_PERFCTR_L1_DCACHE_WB);
+ARMV7_EVENT_ATTR(l2d_cache, ARMV7_PERFCTR_L2_CACHE_ACCESS);
+ARMV7_EVENT_ATTR(l2d_cache_refill, ARMV7_PERFCTR_L2_CACHE_REFILL);
+ARMV7_EVENT_ATTR(l2d_cache_wb, ARMV7_PERFCTR_L2_CACHE_WB);
+ARMV7_EVENT_ATTR(bus_access, ARMV7_PERFCTR_BUS_ACCESS);
+ARMV7_EVENT_ATTR(memory_error, ARMV7_PERFCTR_MEM_ERROR);
+ARMV7_EVENT_ATTR(inst_spec, ARMV7_PERFCTR_INSTR_SPEC);
+ARMV7_EVENT_ATTR(ttbr_write_retired, ARMV7_PERFCTR_TTBR_WRITE);
+ARMV7_EVENT_ATTR(bus_cycles, ARMV7_PERFCTR_BUS_CYCLES);
+
+static struct attribute *armv7_pmuv2_event_attrs[] = {
+	&armv7_event_attr_sw_incr.attr.attr,
+	&armv7_event_attr_l1i_cache_refill.attr.attr,
+	&armv7_event_attr_l1i_tlb_refill.attr.attr,
+	&armv7_event_attr_l1d_cache_refill.attr.attr,
+	&armv7_event_attr_l1d_cache.attr.attr,
+	&armv7_event_attr_l1d_tlb_refill.attr.attr,
+	&armv7_event_attr_ld_retired.attr.attr,
+	&armv7_event_attr_st_retired.attr.attr,
+	&armv7_event_attr_inst_retired.attr.attr,
+	&armv7_event_attr_exc_taken.attr.attr,
+	&armv7_event_attr_exc_return.attr.attr,
+	&armv7_event_attr_cid_write_retired.attr.attr,
+	&armv7_event_attr_pc_write_retired.attr.attr,
+	&armv7_event_attr_br_immed_retired.attr.attr,
+	&armv7_event_attr_br_return_retired.attr.attr,
+	&armv7_event_attr_unaligned_ldst_retired.attr.attr,
+	&armv7_event_attr_br_mis_pred.attr.attr,
+	&armv7_event_attr_cpu_cycles.attr.attr,
+	&armv7_event_attr_br_pred.attr.attr,
+	&armv7_event_attr_mem_access.attr.attr,
+	&armv7_event_attr_l1i_cache.attr.attr,
+	&armv7_event_attr_l1d_cache_wb.attr.attr,
+	&armv7_event_attr_l2d_cache.attr.attr,
+	&armv7_event_attr_l2d_cache_refill.attr.attr,
+	&armv7_event_attr_l2d_cache_wb.attr.attr,
+	&armv7_event_attr_bus_access.attr.attr,
+	&armv7_event_attr_memory_error.attr.attr,
+	&armv7_event_attr_inst_spec.attr.attr,
+	&armv7_event_attr_ttbr_write_retired.attr.attr,
+	&armv7_event_attr_bus_cycles.attr.attr,
+	NULL,
+};
+
+static struct attribute_group armv7_pmuv2_events_attr_group = {
+	.name = "events",
+	.attrs = armv7_pmuv2_event_attrs,
+};
+
+static const struct attribute_group *armv7_pmuv2_attr_groups[] = {
+	&armv7_pmuv2_events_attr_group,
+	&armv7_pmu_format_attr_group,
+	NULL,
+};
+
 /*
  * Perf Events' indices
  */
@@ -1085,6 +1197,7 @@
 	armv7pmu_init(cpu_pmu);
 	cpu_pmu->name		= "armv7_cortex_a8";
 	cpu_pmu->map_event	= armv7_a8_map_event;
+	cpu_pmu->pmu.attr_groups = armv7_pmuv1_attr_groups;
 	return armv7_probe_num_events(cpu_pmu);
 }
 
@@ -1093,6 +1206,7 @@
 	armv7pmu_init(cpu_pmu);
 	cpu_pmu->name		= "armv7_cortex_a9";
 	cpu_pmu->map_event	= armv7_a9_map_event;
+	cpu_pmu->pmu.attr_groups = armv7_pmuv1_attr_groups;
 	return armv7_probe_num_events(cpu_pmu);
 }
 
@@ -1101,6 +1215,7 @@
 	armv7pmu_init(cpu_pmu);
 	cpu_pmu->name		= "armv7_cortex_a5";
 	cpu_pmu->map_event	= armv7_a5_map_event;
+	cpu_pmu->pmu.attr_groups = armv7_pmuv1_attr_groups;
 	return armv7_probe_num_events(cpu_pmu);
 }
 
@@ -1110,6 +1225,7 @@
 	cpu_pmu->name		= "armv7_cortex_a15";
 	cpu_pmu->map_event	= armv7_a15_map_event;
 	cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
+	cpu_pmu->pmu.attr_groups = armv7_pmuv2_attr_groups;
 	return armv7_probe_num_events(cpu_pmu);
 }
 
@@ -1119,6 +1235,7 @@
 	cpu_pmu->name		= "armv7_cortex_a7";
 	cpu_pmu->map_event	= armv7_a7_map_event;
 	cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
+	cpu_pmu->pmu.attr_groups = armv7_pmuv2_attr_groups;
 	return armv7_probe_num_events(cpu_pmu);
 }
 
@@ -1128,6 +1245,7 @@
 	cpu_pmu->name		= "armv7_cortex_a12";
 	cpu_pmu->map_event	= armv7_a12_map_event;
 	cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
+	cpu_pmu->pmu.attr_groups = armv7_pmuv2_attr_groups;
 	return armv7_probe_num_events(cpu_pmu);
 }
 
@@ -1135,6 +1253,7 @@
 {
 	int ret = armv7_a12_pmu_init(cpu_pmu);
 	cpu_pmu->name = "armv7_cortex_a17";
+	cpu_pmu->pmu.attr_groups = armv7_pmuv2_attr_groups;
 	return ret;
 }
 
diff --git a/arch/arm/kernel/pj4-cp0.c b/arch/arm/kernel/pj4-cp0.c
index 8153e36..7c9248b 100644
--- a/arch/arm/kernel/pj4-cp0.c
+++ b/arch/arm/kernel/pj4-cp0.c
@@ -66,9 +66,13 @@
 
 	__asm__ __volatile__ (
 		"mcr	p15, 0, %1, c1, c0, 2\n\t"
+#ifdef CONFIG_THUMB2_KERNEL
+		"isb\n\t"
+#else
 		"mrc	p15, 0, %0, c1, c0, 2\n\t"
 		"mov	%0, %0\n\t"
 		"sub	pc, pc, #4\n\t"
+#endif
 		: "=r" (temp) : "r" (value));
 }
 
diff --git a/arch/arm/kernel/psci-call.S b/arch/arm/kernel/psci-call.S
deleted file mode 100644
index a78e9e1..0000000
--- a/arch/arm/kernel/psci-call.S
+++ /dev/null
@@ -1,31 +0,0 @@
-/*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * Copyright (C) 2015 ARM Limited
- *
- * Author: Mark Rutland <mark.rutland@arm.com>
- */
-
-#include <linux/linkage.h>
-
-#include <asm/opcodes-sec.h>
-#include <asm/opcodes-virt.h>
-
-/* int __invoke_psci_fn_hvc(u32 function_id, u32 arg0, u32 arg1, u32 arg2) */
-ENTRY(__invoke_psci_fn_hvc)
-	__HVC(0)
-	bx	lr
-ENDPROC(__invoke_psci_fn_hvc)
-
-/* int __invoke_psci_fn_smc(u32 function_id, u32 arg0, u32 arg1, u32 arg2) */
-ENTRY(__invoke_psci_fn_smc)
-	__SMC(0)
-	bx	lr
-ENDPROC(__invoke_psci_fn_smc)
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 20edd34..7d0cba6f 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -7,6 +7,7 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
+#include <linux/efi.h>
 #include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/stddef.h>
@@ -37,7 +38,9 @@
 #include <asm/cp15.h>
 #include <asm/cpu.h>
 #include <asm/cputype.h>
+#include <asm/efi.h>
 #include <asm/elf.h>
+#include <asm/early_ioremap.h>
 #include <asm/fixmap.h>
 #include <asm/procinfo.h>
 #include <asm/psci.h>
@@ -375,6 +378,72 @@
 	printk("%s", buf);
 }
 
+#ifdef CONFIG_ARM_PATCH_IDIV
+
+static inline u32 __attribute_const__ sdiv_instruction(void)
+{
+	if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) {
+		/* "sdiv r0, r0, r1" */
+		u32 insn = __opcode_thumb32_compose(0xfb90, 0xf0f1);
+		return __opcode_to_mem_thumb32(insn);
+	}
+
+	/* "sdiv r0, r0, r1" */
+	return __opcode_to_mem_arm(0xe710f110);
+}
+
+static inline u32 __attribute_const__ udiv_instruction(void)
+{
+	if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) {
+		/* "udiv r0, r0, r1" */
+		u32 insn = __opcode_thumb32_compose(0xfbb0, 0xf0f1);
+		return __opcode_to_mem_thumb32(insn);
+	}
+
+	/* "udiv r0, r0, r1" */
+	return __opcode_to_mem_arm(0xe730f110);
+}
+
+static inline u32 __attribute_const__ bx_lr_instruction(void)
+{
+	if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) {
+		/* "bx lr; nop" */
+		u32 insn = __opcode_thumb32_compose(0x4770, 0x46c0);
+		return __opcode_to_mem_thumb32(insn);
+	}
+
+	/* "bx lr" */
+	return __opcode_to_mem_arm(0xe12fff1e);
+}
+
+static void __init patch_aeabi_idiv(void)
+{
+	extern void __aeabi_uidiv(void);
+	extern void __aeabi_idiv(void);
+	uintptr_t fn_addr;
+	unsigned int mask;
+
+	mask = IS_ENABLED(CONFIG_THUMB2_KERNEL) ? HWCAP_IDIVT : HWCAP_IDIVA;
+	if (!(elf_hwcap & mask))
+		return;
+
+	pr_info("CPU: div instructions available: patching division code\n");
+
+	fn_addr = ((uintptr_t)&__aeabi_uidiv) & ~1;
+	((u32 *)fn_addr)[0] = udiv_instruction();
+	((u32 *)fn_addr)[1] = bx_lr_instruction();
+	flush_icache_range(fn_addr, fn_addr + 8);
+
+	fn_addr = ((uintptr_t)&__aeabi_idiv) & ~1;
+	((u32 *)fn_addr)[0] = sdiv_instruction();
+	((u32 *)fn_addr)[1] = bx_lr_instruction();
+	flush_icache_range(fn_addr, fn_addr + 8);
+}
+
+#else
+static inline void patch_aeabi_idiv(void) { }
+#endif
+
 static void __init cpuid_init_hwcaps(void)
 {
 	int block;
@@ -642,6 +711,7 @@
 	elf_hwcap = list->elf_hwcap;
 
 	cpuid_init_hwcaps();
+	patch_aeabi_idiv();
 
 #ifndef CONFIG_ARM_THUMB
 	elf_hwcap &= ~(HWCAP_THUMB | HWCAP_IDIVT);
@@ -956,8 +1026,8 @@
 	strlcpy(cmd_line, boot_command_line, COMMAND_LINE_SIZE);
 	*cmdline_p = cmd_line;
 
-	if (IS_ENABLED(CONFIG_FIX_EARLYCON_MEM))
-		early_fixmap_init();
+	early_fixmap_init();
+	early_ioremap_init();
 
 	parse_early_param();
 
@@ -965,9 +1035,12 @@
 	early_paging_init(mdesc);
 #endif
 	setup_dma_zone(mdesc);
+	efi_init();
 	sanity_check_meminfo();
 	arm_memblock_init(mdesc);
 
+	early_ioremap_reset();
+
 	paging_init(mdesc);
 	request_standard_resources(mdesc);
 
diff --git a/arch/arm/kernel/smccc-call.S b/arch/arm/kernel/smccc-call.S
new file mode 100644
index 0000000..2e48b67
--- /dev/null
+++ b/arch/arm/kernel/smccc-call.S
@@ -0,0 +1,62 @@
+/*
+ * Copyright (c) 2015, Linaro Limited
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+#include <linux/linkage.h>
+
+#include <asm/opcodes-sec.h>
+#include <asm/opcodes-virt.h>
+#include <asm/unwind.h>
+
+	/*
+	 * Wrap c macros in asm macros to delay expansion until after the
+	 * SMCCC asm macro is expanded.
+	 */
+	.macro SMCCC_SMC
+	__SMC(0)
+	.endm
+
+	.macro SMCCC_HVC
+	__HVC(0)
+	.endm
+
+	.macro SMCCC instr
+UNWIND(	.fnstart)
+	mov	r12, sp
+	push	{r4-r7}
+UNWIND(	.save	{r4-r7})
+	ldm	r12, {r4-r7}
+	\instr
+	pop	{r4-r7}
+	ldr	r12, [sp, #(4 * 4)]
+	stm	r12, {r0-r3}
+	bx	lr
+UNWIND(	.fnend)
+	.endm
+
+/*
+ * void smccc_smc(unsigned long a0, unsigned long a1, unsigned long a2,
+ *		  unsigned long a3, unsigned long a4, unsigned long a5,
+ *		  unsigned long a6, unsigned long a7, struct arm_smccc_res *res)
+ */
+ENTRY(arm_smccc_smc)
+	SMCCC SMCCC_SMC
+ENDPROC(arm_smccc_smc)
+
+/*
+ * void smccc_hvc(unsigned long a0, unsigned long a1, unsigned long a2,
+ *		  unsigned long a3, unsigned long a4, unsigned long a5,
+ *		  unsigned long a6, unsigned long a7, struct arm_smccc_res *res)
+ */
+ENTRY(arm_smccc_hvc)
+	SMCCC SMCCC_HVC
+ENDPROC(arm_smccc_hvc)
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index b263613..37312f6 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -69,11 +69,15 @@
 	IPI_TIMER,
 	IPI_RESCHEDULE,
 	IPI_CALL_FUNC,
-	IPI_CALL_FUNC_SINGLE,
 	IPI_CPU_STOP,
 	IPI_IRQ_WORK,
 	IPI_COMPLETION,
-	IPI_CPU_BACKTRACE = 15,
+	IPI_CPU_BACKTRACE,
+	/*
+	 * SGI8-15 can be reserved by secure firmware, and thus may
+	 * not be usable by the kernel. Please keep the above limited
+	 * to at most 8 entries.
+	 */
 };
 
 static DECLARE_COMPLETION(cpu_running);
@@ -475,7 +479,6 @@
 	S(IPI_TIMER, "Timer broadcast interrupts"),
 	S(IPI_RESCHEDULE, "Rescheduling interrupts"),
 	S(IPI_CALL_FUNC, "Function call interrupts"),
-	S(IPI_CALL_FUNC_SINGLE, "Single function call interrupts"),
 	S(IPI_CPU_STOP, "CPU stop interrupts"),
 	S(IPI_IRQ_WORK, "IRQ work interrupts"),
 	S(IPI_COMPLETION, "completion interrupts"),
@@ -525,7 +528,7 @@
 
 void arch_send_call_function_single_ipi(int cpu)
 {
-	smp_cross_call(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE);
+	smp_cross_call(cpumask_of(cpu), IPI_CALL_FUNC);
 }
 
 #ifdef CONFIG_IRQ_WORK
@@ -620,12 +623,6 @@
 		irq_exit();
 		break;
 
-	case IPI_CALL_FUNC_SINGLE:
-		irq_enter();
-		generic_smp_call_function_single_interrupt();
-		irq_exit();
-		break;
-
 	case IPI_CPU_STOP:
 		irq_enter();
 		ipi_cpu_stop(cpu);
diff --git a/arch/arm/kernel/vdso.c b/arch/arm/kernel/vdso.c
index 54a5aea..994e971 100644
--- a/arch/arm/kernel/vdso.c
+++ b/arch/arm/kernel/vdso.c
@@ -224,7 +224,7 @@
 				       VM_READ | VM_MAYREAD,
 				       &vdso_data_mapping);
 
-	return IS_ERR(vma) ? PTR_ERR(vma) : 0;
+	return PTR_ERR_OR_ZERO(vma);
 }
 
 /* assumes mmap_sem is write-locked */
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index e06fd29..dda1959 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -44,6 +44,7 @@
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_coproc.h>
 #include <asm/kvm_psci.h>
+#include <asm/sections.h>
 
 #ifdef REQUIRES_VIRT
 __asm__(".arch_extension	virt");
@@ -58,9 +59,12 @@
 
 /* The VMID used in the VTTBR */
 static atomic64_t kvm_vmid_gen = ATOMIC64_INIT(1);
-static u8 kvm_next_vmid;
+static u32 kvm_next_vmid;
+static unsigned int kvm_vmid_bits __read_mostly;
 static DEFINE_SPINLOCK(kvm_vmid_lock);
 
+static bool vgic_present;
+
 static void kvm_arm_set_running_vcpu(struct kvm_vcpu *vcpu)
 {
 	BUG_ON(preemptible());
@@ -132,7 +136,8 @@
 	kvm->arch.vmid_gen = 0;
 
 	/* The maximum number of VCPUs is limited by the host's GIC model */
-	kvm->arch.max_vcpus = kvm_vgic_get_max_vcpus();
+	kvm->arch.max_vcpus = vgic_present ?
+				kvm_vgic_get_max_vcpus() : KVM_MAX_VCPUS;
 
 	return ret;
 out_free_stage2_pgd:
@@ -172,6 +177,8 @@
 	int r;
 	switch (ext) {
 	case KVM_CAP_IRQCHIP:
+		r = vgic_present;
+		break;
 	case KVM_CAP_IOEVENTFD:
 	case KVM_CAP_DEVICE_CTRL:
 	case KVM_CAP_USER_MEMORY:
@@ -433,11 +440,12 @@
 	kvm->arch.vmid_gen = atomic64_read(&kvm_vmid_gen);
 	kvm->arch.vmid = kvm_next_vmid;
 	kvm_next_vmid++;
+	kvm_next_vmid &= (1 << kvm_vmid_bits) - 1;
 
 	/* update vttbr to be used with the new vmid */
 	pgd_phys = virt_to_phys(kvm_get_hwpgd(kvm));
 	BUG_ON(pgd_phys & ~VTTBR_BADDR_MASK);
-	vmid = ((u64)(kvm->arch.vmid) << VTTBR_VMID_SHIFT) & VTTBR_VMID_MASK;
+	vmid = ((u64)(kvm->arch.vmid) << VTTBR_VMID_SHIFT) & VTTBR_VMID_MASK(kvm_vmid_bits);
 	kvm->arch.vttbr = pgd_phys | vmid;
 
 	spin_unlock(&kvm_vmid_lock);
@@ -603,6 +611,7 @@
 		ret = kvm_call_hyp(__kvm_vcpu_run, vcpu);
 
 		vcpu->mode = OUTSIDE_GUEST_MODE;
+		vcpu->stat.exits++;
 		/*
 		 * Back from guest
 		 *************************************************************/
@@ -913,6 +922,8 @@
 
 	switch (dev_id) {
 	case KVM_ARM_DEVICE_VGIC_V2:
+		if (!vgic_present)
+			return -ENXIO;
 		return kvm_vgic_addr(kvm, type, &dev_addr->addr, true);
 	default:
 		return -ENODEV;
@@ -927,6 +938,8 @@
 
 	switch (ioctl) {
 	case KVM_CREATE_IRQCHIP: {
+		if (!vgic_present)
+			return -ENXIO;
 		return kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2);
 	}
 	case KVM_ARM_SET_DEVICE_ADDR: {
@@ -1067,6 +1080,12 @@
 		goto out_free_mappings;
 	}
 
+	err = create_hyp_mappings(__start_rodata, __end_rodata);
+	if (err) {
+		kvm_err("Cannot map rodata section\n");
+		goto out_free_mappings;
+	}
+
 	/*
 	 * Map the Hyp stack pages
 	 */
@@ -1111,8 +1130,17 @@
 	 * Init HYP view of VGIC
 	 */
 	err = kvm_vgic_hyp_init();
-	if (err)
+	switch (err) {
+	case 0:
+		vgic_present = true;
+		break;
+	case -ENODEV:
+	case -ENXIO:
+		vgic_present = false;
+		break;
+	default:
 		goto out_free_context;
+	}
 
 	/*
 	 * Init HYP architected timer support
@@ -1127,6 +1155,10 @@
 
 	kvm_perf_init();
 
+	/* set size of VMID supported by CPU */
+	kvm_vmid_bits = kvm_get_vmid_bits();
+	kvm_info("%d-bit VMID\n", kvm_vmid_bits);
+
 	kvm_info("Hyp mode initialized successfully\n");
 
 	return 0;
diff --git a/arch/arm/kvm/emulate.c b/arch/arm/kvm/emulate.c
index d6c0052..dc99159 100644
--- a/arch/arm/kvm/emulate.c
+++ b/arch/arm/kvm/emulate.c
@@ -275,6 +275,40 @@
 		return vbar;
 }
 
+/*
+ * Switch to an exception mode, updating both CPSR and SPSR. Follow
+ * the logic described in AArch32.EnterMode() from the ARMv8 ARM.
+ */
+static void kvm_update_psr(struct kvm_vcpu *vcpu, unsigned long mode)
+{
+	unsigned long cpsr = *vcpu_cpsr(vcpu);
+	u32 sctlr = vcpu->arch.cp15[c1_SCTLR];
+
+	*vcpu_cpsr(vcpu) = (cpsr & ~MODE_MASK) | mode;
+
+	switch (mode) {
+	case FIQ_MODE:
+		*vcpu_cpsr(vcpu) |= PSR_F_BIT;
+		/* Fall through */
+	case ABT_MODE:
+	case IRQ_MODE:
+		*vcpu_cpsr(vcpu) |= PSR_A_BIT;
+		/* Fall through */
+	default:
+		*vcpu_cpsr(vcpu) |= PSR_I_BIT;
+	}
+
+	*vcpu_cpsr(vcpu) &= ~(PSR_IT_MASK | PSR_J_BIT | PSR_E_BIT | PSR_T_BIT);
+
+	if (sctlr & SCTLR_TE)
+		*vcpu_cpsr(vcpu) |= PSR_T_BIT;
+	if (sctlr & SCTLR_EE)
+		*vcpu_cpsr(vcpu) |= PSR_E_BIT;
+
+	/* Note: These now point to the mode banked copies */
+	*vcpu_spsr(vcpu) = cpsr;
+}
+
 /**
  * kvm_inject_undefined - inject an undefined exception into the guest
  * @vcpu: The VCPU to receive the undefined exception
@@ -286,29 +320,13 @@
  */
 void kvm_inject_undefined(struct kvm_vcpu *vcpu)
 {
-	unsigned long new_lr_value;
-	unsigned long new_spsr_value;
 	unsigned long cpsr = *vcpu_cpsr(vcpu);
-	u32 sctlr = vcpu->arch.cp15[c1_SCTLR];
 	bool is_thumb = (cpsr & PSR_T_BIT);
 	u32 vect_offset = 4;
 	u32 return_offset = (is_thumb) ? 2 : 4;
 
-	new_spsr_value = cpsr;
-	new_lr_value = *vcpu_pc(vcpu) - return_offset;
-
-	*vcpu_cpsr(vcpu) = (cpsr & ~MODE_MASK) | UND_MODE;
-	*vcpu_cpsr(vcpu) |= PSR_I_BIT;
-	*vcpu_cpsr(vcpu) &= ~(PSR_IT_MASK | PSR_J_BIT | PSR_E_BIT | PSR_T_BIT);
-
-	if (sctlr & SCTLR_TE)
-		*vcpu_cpsr(vcpu) |= PSR_T_BIT;
-	if (sctlr & SCTLR_EE)
-		*vcpu_cpsr(vcpu) |= PSR_E_BIT;
-
-	/* Note: These now point to UND banked copies */
-	*vcpu_spsr(vcpu) = cpsr;
-	*vcpu_reg(vcpu, 14) = new_lr_value;
+	kvm_update_psr(vcpu, UND_MODE);
+	*vcpu_reg(vcpu, 14) = *vcpu_pc(vcpu) - return_offset;
 
 	/* Branch to exception vector */
 	*vcpu_pc(vcpu) = exc_vector_base(vcpu) + vect_offset;
@@ -320,30 +338,14 @@
  */
 static void inject_abt(struct kvm_vcpu *vcpu, bool is_pabt, unsigned long addr)
 {
-	unsigned long new_lr_value;
-	unsigned long new_spsr_value;
 	unsigned long cpsr = *vcpu_cpsr(vcpu);
-	u32 sctlr = vcpu->arch.cp15[c1_SCTLR];
 	bool is_thumb = (cpsr & PSR_T_BIT);
 	u32 vect_offset;
 	u32 return_offset = (is_thumb) ? 4 : 0;
 	bool is_lpae;
 
-	new_spsr_value = cpsr;
-	new_lr_value = *vcpu_pc(vcpu) + return_offset;
-
-	*vcpu_cpsr(vcpu) = (cpsr & ~MODE_MASK) | ABT_MODE;
-	*vcpu_cpsr(vcpu) |= PSR_I_BIT | PSR_A_BIT;
-	*vcpu_cpsr(vcpu) &= ~(PSR_IT_MASK | PSR_J_BIT | PSR_E_BIT | PSR_T_BIT);
-
-	if (sctlr & SCTLR_TE)
-		*vcpu_cpsr(vcpu) |= PSR_T_BIT;
-	if (sctlr & SCTLR_EE)
-		*vcpu_cpsr(vcpu) |= PSR_E_BIT;
-
-	/* Note: These now point to ABT banked copies */
-	*vcpu_spsr(vcpu) = cpsr;
-	*vcpu_reg(vcpu, 14) = new_lr_value;
+	kvm_update_psr(vcpu, ABT_MODE);
+	*vcpu_reg(vcpu, 14) = *vcpu_pc(vcpu) + return_offset;
 
 	if (is_pabt)
 		vect_offset = 12;
diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c
index 96e935b..5fa69d7 100644
--- a/arch/arm/kvm/guest.c
+++ b/arch/arm/kvm/guest.c
@@ -33,6 +33,12 @@
 #define VCPU_STAT(x) { #x, offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU }
 
 struct kvm_stats_debugfs_item debugfs_entries[] = {
+	VCPU_STAT(hvc_exit_stat),
+	VCPU_STAT(wfe_exit_stat),
+	VCPU_STAT(wfi_exit_stat),
+	VCPU_STAT(mmio_exit_user),
+	VCPU_STAT(mmio_exit_kernel),
+	VCPU_STAT(exits),
 	{ NULL }
 };
 
diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c
index 95f12b2..3ede90d 100644
--- a/arch/arm/kvm/handle_exit.c
+++ b/arch/arm/kvm/handle_exit.c
@@ -42,6 +42,7 @@
 
 	trace_kvm_hvc(*vcpu_pc(vcpu), *vcpu_reg(vcpu, 0),
 		      kvm_vcpu_hvc_get_imm(vcpu));
+	vcpu->stat.hvc_exit_stat++;
 
 	ret = kvm_psci_call(vcpu);
 	if (ret < 0) {
@@ -89,9 +90,11 @@
 {
 	if (kvm_vcpu_get_hsr(vcpu) & HSR_WFI_IS_WFE) {
 		trace_kvm_wfx(*vcpu_pc(vcpu), true);
+		vcpu->stat.wfe_exit_stat++;
 		kvm_vcpu_on_spin(vcpu);
 	} else {
 		trace_kvm_wfx(*vcpu_pc(vcpu), false);
+		vcpu->stat.wfi_exit_stat++;
 		kvm_vcpu_block(vcpu);
 	}
 
diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c
index 3a10c9f..7f33b20 100644
--- a/arch/arm/kvm/mmio.c
+++ b/arch/arm/kvm/mmio.c
@@ -210,8 +210,11 @@
 
 	if (!ret) {
 		/* We handled the access successfully in the kernel. */
+		vcpu->stat.mmio_exit_kernel++;
 		kvm_handle_mmio_return(vcpu, run);
 		return 1;
+	} else {
+		vcpu->stat.mmio_exit_user++;
 	}
 
 	run->exit_reason	= KVM_EXIT_MMIO;
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 61d96a6..22f7fa0 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -656,9 +656,9 @@
  * kvm_alloc_stage2_pgd - allocate level-1 table for stage-2 translation.
  * @kvm:	The KVM struct pointer for the VM.
  *
- * Allocates the 1st level table only of size defined by S2_PGD_ORDER (can
- * support either full 40-bit input addresses or limited to 32-bit input
- * addresses). Clears the allocated pages.
+ * Allocates only the stage-2 HW PGD level table(s) (can support either full
+ * 40-bit input addresses or limited to 32-bit input addresses). Clears the
+ * allocated pages.
  *
  * Note we don't need locking here as this is only called when the VM is
  * created, which can only be done once.
diff --git a/arch/arm/lib/lib1funcs.S b/arch/arm/lib/lib1funcs.S
index af2267f..9397b2e 100644
--- a/arch/arm/lib/lib1funcs.S
+++ b/arch/arm/lib/lib1funcs.S
@@ -205,6 +205,10 @@
 .endm
 
 
+#ifdef CONFIG_ARM_PATCH_IDIV
+	.align	3
+#endif
+
 ENTRY(__udivsi3)
 ENTRY(__aeabi_uidiv)
 UNWIND(.fnstart)
@@ -253,6 +257,10 @@
 UNWIND(.fnend)
 ENDPROC(__umodsi3)
 
+#ifdef CONFIG_ARM_PATCH_IDIV
+	.align 3
+#endif
+
 ENTRY(__divsi3)
 ENTRY(__aeabi_idiv)
 UNWIND(.fnstart)
diff --git a/arch/arm/mach-davinci/board-da850-evm.c b/arch/arm/mach-davinci/board-da850-evm.c
index 1ed545c..9cc7b81 100644
--- a/arch/arm/mach-davinci/board-da850-evm.c
+++ b/arch/arm/mach-davinci/board-da850-evm.c
@@ -49,8 +49,8 @@
 #include <asm/mach/arch.h>
 #include <asm/system_info.h>
 
-#include <media/tvp514x.h>
-#include <media/adv7343.h>
+#include <media/i2c/tvp514x.h>
+#include <media/i2c/adv7343.h>
 
 #define DA850_EVM_PHY_ID		"davinci_mdio-0:00"
 #define DA850_LCD_PWR_PIN		GPIO_TO_PIN(2, 8)
diff --git a/arch/arm/mach-davinci/board-dm355-evm.c b/arch/arm/mach-davinci/board-dm355-evm.c
index b46b4d2..c71dd998 100644
--- a/arch/arm/mach-davinci/board-dm355-evm.c
+++ b/arch/arm/mach-davinci/board-dm355-evm.c
@@ -19,7 +19,7 @@
 #include <linux/gpio.h>
 #include <linux/clk.h>
 #include <linux/videodev2.h>
-#include <media/tvp514x.h>
+#include <media/i2c/tvp514x.h>
 #include <linux/spi/spi.h>
 #include <linux/spi/eeprom.h>
 #include <linux/platform_data/gpio-davinci.h>
diff --git a/arch/arm/mach-davinci/board-dm365-evm.c b/arch/arm/mach-davinci/board-dm365-evm.c
index a756003..f073518 100644
--- a/arch/arm/mach-davinci/board-dm365-evm.c
+++ b/arch/arm/mach-davinci/board-dm365-evm.c
@@ -40,8 +40,8 @@
 #include <linux/platform_data/mtd-davinci.h>
 #include <linux/platform_data/keyscan-davinci.h>
 
-#include <media/ths7303.h>
-#include <media/tvp514x.h>
+#include <media/i2c/ths7303.h>
+#include <media/i2c/tvp514x.h>
 
 #include "davinci.h"
 
diff --git a/arch/arm/mach-davinci/board-dm644x-evm.c b/arch/arm/mach-davinci/board-dm644x-evm.c
index bbdd2d6..7a20507 100644
--- a/arch/arm/mach-davinci/board-dm644x-evm.c
+++ b/arch/arm/mach-davinci/board-dm644x-evm.c
@@ -26,7 +26,7 @@
 #include <linux/v4l2-dv-timings.h>
 #include <linux/export.h>
 
-#include <media/tvp514x.h>
+#include <media/i2c/tvp514x.h>
 
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
diff --git a/arch/arm/mach-davinci/board-dm646x-evm.c b/arch/arm/mach-davinci/board-dm646x-evm.c
index 846a84d..ee6ab7e 100644
--- a/arch/arm/mach-davinci/board-dm646x-evm.c
+++ b/arch/arm/mach-davinci/board-dm646x-evm.c
@@ -25,8 +25,8 @@
 #include <linux/platform_data/at24.h>
 #include <linux/i2c/pcf857x.h>
 
-#include <media/tvp514x.h>
-#include <media/adv7343.h>
+#include <media/i2c/tvp514x.h>
+#include <media/i2c/adv7343.h>
 
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/nand.h>
diff --git a/arch/arm/mach-exynos/Kconfig b/arch/arm/mach-exynos/Kconfig
index 3a10f1a..ff10539 100644
--- a/arch/arm/mach-exynos/Kconfig
+++ b/arch/arm/mach-exynos/Kconfig
@@ -27,6 +27,7 @@
 	select SRAM
 	select THERMAL
 	select MFD_SYSCON
+	select CLKSRC_EXYNOS_MCT
 	help
 	  Support for SAMSUNG EXYNOS SoCs (EXYNOS4/5)
 
diff --git a/arch/arm/mach-imx/devices/devices-common.h b/arch/arm/mach-imx/devices/devices-common.h
index 67f7fb1..09cebd8 100644
--- a/arch/arm/mach-imx/devices/devices-common.h
+++ b/arch/arm/mach-imx/devices/devices-common.h
@@ -177,7 +177,7 @@
 		const struct imxuart_platform_data *pdata);
 
 #include <linux/platform_data/video-mx3fb.h>
-#include <linux/platform_data/camera-mx3.h>
+#include <linux/platform_data/media/camera-mx3.h>
 struct imx_ipu_core_data {
 	resource_size_t iobase;
 	resource_size_t synirq;
@@ -192,7 +192,7 @@
 		const struct imx_ipu_core_data *data,
 		struct mx3fb_platform_data *pdata);
 
-#include <linux/platform_data/camera-mx2.h>
+#include <linux/platform_data/media/camera-mx2.h>
 struct imx_mx2_camera_data {
 	const char *devid;
 	resource_size_t iobasecsi;
diff --git a/arch/arm/mach-omap1/include/mach/camera.h b/arch/arm/mach-omap1/include/mach/camera.h
index 847d00f..caa6c0d6 100644
--- a/arch/arm/mach-omap1/include/mach/camera.h
+++ b/arch/arm/mach-omap1/include/mach/camera.h
@@ -1,7 +1,7 @@
 #ifndef __ASM_ARCH_CAMERA_H_
 #define __ASM_ARCH_CAMERA_H_
 
-#include <media/omap1_camera.h>
+#include <linux/platform_data/media/omap1_camera.h>
 
 void omap1_camera_init(void *);
 
diff --git a/arch/arm/mach-omap2/board-generic.c b/arch/arm/mach-omap2/board-generic.c
index 04a56cc..8098272 100644
--- a/arch/arm/mach-omap2/board-generic.c
+++ b/arch/arm/mach-omap2/board-generic.c
@@ -16,6 +16,7 @@
 #include <linux/of_platform.h>
 #include <linux/irqdomain.h>
 
+#include <asm/setup.h>
 #include <asm/mach/arch.h>
 
 #include "common.h"
@@ -76,8 +77,17 @@
 	NULL,
 };
 
+/* Legacy userspace on Nokia N900 needs ATAGS exported in /proc/atags,
+ * save them while the data is still not overwritten
+ */
+static void __init rx51_reserve(void)
+{
+	save_atags((const struct tag *)(PAGE_OFFSET + 0x100));
+	omap_reserve();
+}
+
 DT_MACHINE_START(OMAP3_N900_DT, "Nokia RX-51 board")
-	.reserve	= omap_reserve,
+	.reserve	= rx51_reserve,
 	.map_io		= omap3_map_io,
 	.init_early	= omap3430_init_early,
 	.init_machine	= omap_generic_init,
diff --git a/arch/arm/mach-omap2/board-rx51-peripherals.c b/arch/arm/mach-omap2/board-rx51-peripherals.c
index 14edcd7..0a0567f 100644
--- a/arch/arm/mach-omap2/board-rx51-peripherals.c
+++ b/arch/arm/mach-omap2/board-rx51-peripherals.c
@@ -39,7 +39,7 @@
 
 #include <sound/tlv320aic3x.h>
 #include <sound/tpa6130a2-plat.h>
-#include <media/si4713.h>
+#include <linux/platform_data/media/si4713.h>
 #include <linux/platform_data/leds-lp55xx.h>
 
 #include <linux/platform_data/tsl2563.h>
@@ -48,7 +48,7 @@
 #include <video/omap-panel-data.h>
 
 #if defined(CONFIG_IR_RX51) || defined(CONFIG_IR_RX51_MODULE)
-#include <media/ir-rx51.h>
+#include <linux/platform_data/media/ir-rx51.h>
 #endif
 
 #include "mux.h"
diff --git a/arch/arm/mach-omap2/gpmc-onenand.c b/arch/arm/mach-omap2/gpmc-onenand.c
index 17a6f75..7b76ce0 100644
--- a/arch/arm/mach-omap2/gpmc-onenand.c
+++ b/arch/arm/mach-omap2/gpmc-onenand.c
@@ -149,8 +149,8 @@
 		freq = 104;
 		break;
 	default:
-		freq = 54;
-		break;
+		pr_err("onenand rate not detected, bad GPMC async timings?\n");
+		freq = 0;
 	}
 
 	return freq;
@@ -271,6 +271,11 @@
 	struct gpmc_timings t;
 	int ret;
 
+	/*
+	 * Note that we need to keep sync_write set for the call to
+	 * omap2_onenand_set_async_mode() to work to detect the onenand
+	 * supported clock rate for the sync timings.
+	 */
 	if (gpmc_onenand_data->of_node) {
 		gpmc_read_settings_dt(gpmc_onenand_data->of_node,
 				      &onenand_async);
@@ -281,12 +286,9 @@
 			else
 				gpmc_onenand_data->flags |= ONENAND_SYNC_READ;
 			onenand_async.sync_read = false;
-			onenand_async.sync_write = false;
 		}
 	}
 
-	omap2_onenand_set_async_mode(onenand_base);
-
 	omap2_onenand_calc_async_timings(&t);
 
 	ret = gpmc_cs_program_settings(gpmc_onenand_data->cs, &onenand_async);
@@ -310,6 +312,8 @@
 	if (!freq) {
 		/* Very first call freq is not known */
 		freq = omap2_onenand_get_freq(gpmc_onenand_data, onenand_base);
+		if (!freq)
+			return -ENODEV;
 		set_onenand_cfg(onenand_base);
 	}
 
diff --git a/arch/arm/mach-pxa/devices.c b/arch/arm/mach-pxa/devices.c
index 2a6e0ae..d1211a4 100644
--- a/arch/arm/mach-pxa/devices.c
+++ b/arch/arm/mach-pxa/devices.c
@@ -14,7 +14,7 @@
 #include <mach/irqs.h>
 #include <linux/platform_data/usb-ohci-pxa27x.h>
 #include <linux/platform_data/keypad-pxa27x.h>
-#include <linux/platform_data/camera-pxa.h>
+#include <linux/platform_data/media/camera-pxa.h>
 #include <mach/audio.h>
 #include <mach/hardware.h>
 #include <linux/platform_data/mmp_dma.h>
diff --git a/arch/arm/mach-pxa/em-x270.c b/arch/arm/mach-pxa/em-x270.c
index 9d7072b..8b1f89e 100644
--- a/arch/arm/mach-pxa/em-x270.c
+++ b/arch/arm/mach-pxa/em-x270.c
@@ -46,7 +46,7 @@
 #include <linux/platform_data/usb-ohci-pxa27x.h>
 #include <linux/platform_data/mmc-pxamci.h>
 #include <linux/platform_data/keypad-pxa27x.h>
-#include <linux/platform_data/camera-pxa.h>
+#include <linux/platform_data/media/camera-pxa.h>
 
 #include "generic.h"
 #include "devices.h"
diff --git a/arch/arm/mach-pxa/ezx.c b/arch/arm/mach-pxa/ezx.c
index 7c0d561..cd62240 100644
--- a/arch/arm/mach-pxa/ezx.c
+++ b/arch/arm/mach-pxa/ezx.c
@@ -34,7 +34,7 @@
 #include <linux/platform_data/usb-ohci-pxa27x.h>
 #include <mach/hardware.h>
 #include <linux/platform_data/keypad-pxa27x.h>
-#include <linux/platform_data/camera-pxa.h>
+#include <linux/platform_data/media/camera-pxa.h>
 
 #include "devices.h"
 #include "generic.h"
diff --git a/arch/arm/mach-pxa/mioa701.c b/arch/arm/mach-pxa/mioa701.c
index 3b52b1a..ccfd2b6 100644
--- a/arch/arm/mach-pxa/mioa701.c
+++ b/arch/arm/mach-pxa/mioa701.c
@@ -54,7 +54,7 @@
 #include <linux/platform_data/mmc-pxamci.h>
 #include <mach/udc.h>
 #include <mach/pxa27x-udc.h>
-#include <linux/platform_data/camera-pxa.h>
+#include <linux/platform_data/media/camera-pxa.h>
 #include <mach/audio.h>
 #include <mach/smemc.h>
 #include <media/soc_camera.h>
diff --git a/arch/arm/mach-pxa/palmtreo.c b/arch/arm/mach-pxa/palmtreo.c
index d8b937c..2dc5606 100644
--- a/arch/arm/mach-pxa/palmtreo.c
+++ b/arch/arm/mach-pxa/palmtreo.c
@@ -43,7 +43,7 @@
 #include <linux/platform_data/usb-ohci-pxa27x.h>
 #include <mach/pxa2xx-regs.h>
 #include <linux/platform_data/asoc-palm27x.h>
-#include <linux/platform_data/camera-pxa.h>
+#include <linux/platform_data/media/camera-pxa.h>
 #include <mach/palm27x.h>
 
 #include <sound/pxa2xx-lib.h>
diff --git a/arch/arm/mach-pxa/palmz72.c b/arch/arm/mach-pxa/palmz72.c
index 1a35ddf..e3df17a 100644
--- a/arch/arm/mach-pxa/palmz72.c
+++ b/arch/arm/mach-pxa/palmz72.c
@@ -49,7 +49,7 @@
 #include <mach/palm27x.h>
 
 #include <mach/pm.h>
-#include <linux/platform_data/camera-pxa.h>
+#include <linux/platform_data/media/camera-pxa.h>
 
 #include <media/soc_camera.h>
 
diff --git a/arch/arm/mach-pxa/pcm990-baseboard.c b/arch/arm/mach-pxa/pcm990-baseboard.c
index b71c96f..8459239 100644
--- a/arch/arm/mach-pxa/pcm990-baseboard.c
+++ b/arch/arm/mach-pxa/pcm990-baseboard.c
@@ -27,10 +27,10 @@
 #include <linux/pwm.h>
 #include <linux/pwm_backlight.h>
 
-#include <media/mt9v022.h>
+#include <media/i2c/mt9v022.h>
 #include <media/soc_camera.h>
 
-#include <linux/platform_data/camera-pxa.h>
+#include <linux/platform_data/media/camera-pxa.h>
 #include <asm/mach/map.h>
 #include <mach/pxa27x.h>
 #include <mach/audio.h>
diff --git a/arch/arm/mach-sti/Kconfig b/arch/arm/mach-sti/Kconfig
index 125865d..12dd1dc 100644
--- a/arch/arm/mach-sti/Kconfig
+++ b/arch/arm/mach-sti/Kconfig
@@ -3,6 +3,7 @@
 	select ARM_GIC
 	select ST_IRQCHIP
 	select ARM_GLOBAL_TIMER
+	select CLKSRC_ST_LPC
 	select PINCTRL
 	select PINCTRL_ST
 	select MFD_SYSCON
diff --git a/arch/arm/mach-ux500/Kconfig b/arch/arm/mach-ux500/Kconfig
index c9ac19b..5eacdd6 100644
--- a/arch/arm/mach-ux500/Kconfig
+++ b/arch/arm/mach-ux500/Kconfig
@@ -32,6 +32,7 @@
 	select PINCTRL_AB8540
 	select REGULATOR
 	select REGULATOR_DB8500_PRCMU
+	select CLKSRC_DBX500_PRCMU
 	select PM_GENERIC_DOMAINS if PM
 
 config MACH_MOP500
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index 493692d..9f9d542 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -790,7 +790,7 @@
 };
 
 static int __init __l2c_init(const struct l2c_init_data *data,
-			     u32 aux_val, u32 aux_mask, u32 cache_id)
+			     u32 aux_val, u32 aux_mask, u32 cache_id, bool nosync)
 {
 	struct outer_cache_fns fns;
 	unsigned way_size_bits, ways;
@@ -866,6 +866,10 @@
 	fns.configure = outer_cache.configure;
 	if (data->fixup)
 		data->fixup(l2x0_base, cache_id, &fns);
+	if (nosync) {
+		pr_info("L2C: disabling outer sync\n");
+		fns.sync = NULL;
+	}
 
 	/*
 	 * Check if l2x0 controller is already enabled.  If we are booting
@@ -925,7 +929,7 @@
 	if (data->save)
 		data->save(l2x0_base);
 
-	__l2c_init(data, aux_val, aux_mask, cache_id);
+	__l2c_init(data, aux_val, aux_mask, cache_id, false);
 }
 
 #ifdef CONFIG_OF
@@ -1060,6 +1064,18 @@
 		val |= (dirty - 1) << L2X0_AUX_CTRL_DIRTY_LATENCY_SHIFT;
 	}
 
+	if (of_property_read_bool(np, "arm,parity-enable")) {
+		mask &= ~L2C_AUX_CTRL_PARITY_ENABLE;
+		val |= L2C_AUX_CTRL_PARITY_ENABLE;
+	} else if (of_property_read_bool(np, "arm,parity-disable")) {
+		mask &= ~L2C_AUX_CTRL_PARITY_ENABLE;
+	}
+
+	if (of_property_read_bool(np, "arm,shared-override")) {
+		mask &= ~L2C_AUX_CTRL_SHARED_OVERRIDE;
+		val |= L2C_AUX_CTRL_SHARED_OVERRIDE;
+	}
+
 	ret = l2x0_cache_size_of_parse(np, aux_val, aux_mask, &assoc, SZ_256K);
 	if (ret)
 		return;
@@ -1176,6 +1192,14 @@
 		*aux_mask &= ~L2C_AUX_CTRL_SHARED_OVERRIDE;
 	}
 
+	if (of_property_read_bool(np, "arm,parity-enable")) {
+		*aux_val |= L2C_AUX_CTRL_PARITY_ENABLE;
+		*aux_mask &= ~L2C_AUX_CTRL_PARITY_ENABLE;
+	} else if (of_property_read_bool(np, "arm,parity-disable")) {
+		*aux_val &= ~L2C_AUX_CTRL_PARITY_ENABLE;
+		*aux_mask &= ~L2C_AUX_CTRL_PARITY_ENABLE;
+	}
+
 	prefetch = l2x0_saved_regs.prefetch_ctrl;
 
 	ret = of_property_read_u32(np, "arm,double-linefill", &val);
@@ -1704,6 +1728,7 @@
 	struct resource res;
 	u32 cache_id, old_aux;
 	u32 cache_level = 2;
+	bool nosync = false;
 
 	np = of_find_matching_node(NULL, l2x0_ids);
 	if (!np)
@@ -1742,6 +1767,8 @@
 	if (cache_level != 2)
 		pr_err("L2C: device tree specifies invalid cache level\n");
 
+	nosync = of_property_read_bool(np, "arm,outer-sync-disable");
+
 	/* Read back current (default) hardware configuration */
 	if (data->save)
 		data->save(l2x0_base);
@@ -1756,6 +1783,6 @@
 	else
 		cache_id = readl_relaxed(l2x0_base + L2X0_CACHE_ID);
 
-	return __l2c_init(data, aux_val, aux_mask, cache_id);
+	return __l2c_init(data, aux_val, aux_mask, cache_id, nosync);
 }
 #endif
diff --git a/arch/arm/mm/cache-uniphier.c b/arch/arm/mm/cache-uniphier.c
index 0502ba1..a6fa7b7 100644
--- a/arch/arm/mm/cache-uniphier.c
+++ b/arch/arm/mm/cache-uniphier.c
@@ -377,17 +377,6 @@
 	{ /* sentinel */ }
 };
 
-static struct device_node * __init uniphier_cache_get_next_level_node(
-							struct device_node *np)
-{
-	u32 phandle;
-
-	if (of_property_read_u32(np, "next-level-cache", &phandle))
-		return NULL;
-
-	return of_find_node_by_phandle(phandle);
-}
-
 static int __init __uniphier_cache_init(struct device_node *np,
 					unsigned int *cache_level)
 {
@@ -491,7 +480,7 @@
 	 * next level cache fails because we want to continue with available
 	 * cache levels.
 	 */
-	next_np = uniphier_cache_get_next_level_node(np);
+	next_np = of_find_next_cache_node(np);
 	if (next_np) {
 		(*cache_level)++;
 		ret = __uniphier_cache_init(next_np, cache_level);
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 7f8cd1b..49bd081 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -192,7 +192,7 @@
 #ifdef CONFIG_HAVE_ARCH_PFN_VALID
 int pfn_valid(unsigned long pfn)
 {
-	return memblock_is_memory(__pfn_to_phys(pfn));
+	return memblock_is_map_memory(__pfn_to_phys(pfn));
 }
 EXPORT_SYMBOL(pfn_valid);
 #endif
@@ -433,6 +433,9 @@
 		if (end <= max_low)
 			continue;
 
+		if (memblock_is_nomap(mem))
+			continue;
+
 		/* Truncate partial highmem entries */
 		if (start < max_low)
 			start = max_low;
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index 0c81056..66a978d 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -30,6 +30,7 @@
 #include <asm/cp15.h>
 #include <asm/cputype.h>
 #include <asm/cacheflush.h>
+#include <asm/early_ioremap.h>
 #include <asm/mmu_context.h>
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
@@ -469,3 +470,11 @@
 }
 EXPORT_SYMBOL_GPL(pci_ioremap_io);
 #endif
+
+/*
+ * Must be called after early_fixmap_init
+ */
+void __init early_ioremap_init(void)
+{
+	early_ioremap_setup();
+}
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 4867f5d..a87f6cc 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -390,7 +390,7 @@
 	 * The early fixmap range spans multiple pmds, for which
 	 * we are not prepared:
 	 */
-	BUILD_BUG_ON((__fix_to_virt(__end_of_permanent_fixed_addresses) >> PMD_SHIFT)
+	BUILD_BUG_ON((__fix_to_virt(__end_of_early_ioremap_region) >> PMD_SHIFT)
 		     != FIXADDR_TOP >> PMD_SHIFT);
 
 	pmd = fixmap_pmd(FIXADDR_TOP);
@@ -572,7 +572,7 @@
 	 * in the Short-descriptor translation table format descriptors.
 	 */
 	if (cpu_arch == CPU_ARCH_ARMv7 &&
-		(read_cpuid_ext(CPUID_EXT_MMFR0) & 0xF) == 4) {
+		(read_cpuid_ext(CPUID_EXT_MMFR0) & 0xF) >= 4) {
 		user_pmd_table |= PMD_PXNTABLE;
 	}
 #endif
@@ -724,30 +724,49 @@
 	return early_alloc_aligned(sz, sz);
 }
 
-static pte_t * __init early_pte_alloc(pmd_t *pmd, unsigned long addr, unsigned long prot)
+static void *__init late_alloc(unsigned long sz)
+{
+	void *ptr = (void *)__get_free_pages(PGALLOC_GFP, get_order(sz));
+
+	BUG_ON(!ptr);
+	return ptr;
+}
+
+static pte_t * __init pte_alloc(pmd_t *pmd, unsigned long addr,
+				unsigned long prot,
+				void *(*alloc)(unsigned long sz))
 {
 	if (pmd_none(*pmd)) {
-		pte_t *pte = early_alloc(PTE_HWTABLE_OFF + PTE_HWTABLE_SIZE);
+		pte_t *pte = alloc(PTE_HWTABLE_OFF + PTE_HWTABLE_SIZE);
 		__pmd_populate(pmd, __pa(pte), prot);
 	}
 	BUG_ON(pmd_bad(*pmd));
 	return pte_offset_kernel(pmd, addr);
 }
 
+static pte_t * __init early_pte_alloc(pmd_t *pmd, unsigned long addr,
+				      unsigned long prot)
+{
+	return pte_alloc(pmd, addr, prot, early_alloc);
+}
+
 static void __init alloc_init_pte(pmd_t *pmd, unsigned long addr,
 				  unsigned long end, unsigned long pfn,
-				  const struct mem_type *type)
+				  const struct mem_type *type,
+				  void *(*alloc)(unsigned long sz),
+				  bool ng)
 {
-	pte_t *pte = early_pte_alloc(pmd, addr, type->prot_l1);
+	pte_t *pte = pte_alloc(pmd, addr, type->prot_l1, alloc);
 	do {
-		set_pte_ext(pte, pfn_pte(pfn, __pgprot(type->prot_pte)), 0);
+		set_pte_ext(pte, pfn_pte(pfn, __pgprot(type->prot_pte)),
+			    ng ? PTE_EXT_NG : 0);
 		pfn++;
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 }
 
 static void __init __map_init_section(pmd_t *pmd, unsigned long addr,
 			unsigned long end, phys_addr_t phys,
-			const struct mem_type *type)
+			const struct mem_type *type, bool ng)
 {
 	pmd_t *p = pmd;
 
@@ -765,7 +784,7 @@
 		pmd++;
 #endif
 	do {
-		*pmd = __pmd(phys | type->prot_sect);
+		*pmd = __pmd(phys | type->prot_sect | (ng ? PMD_SECT_nG : 0));
 		phys += SECTION_SIZE;
 	} while (pmd++, addr += SECTION_SIZE, addr != end);
 
@@ -774,7 +793,8 @@
 
 static void __init alloc_init_pmd(pud_t *pud, unsigned long addr,
 				      unsigned long end, phys_addr_t phys,
-				      const struct mem_type *type)
+				      const struct mem_type *type,
+				      void *(*alloc)(unsigned long sz), bool ng)
 {
 	pmd_t *pmd = pmd_offset(pud, addr);
 	unsigned long next;
@@ -792,10 +812,10 @@
 		 */
 		if (type->prot_sect &&
 				((addr | next | phys) & ~SECTION_MASK) == 0) {
-			__map_init_section(pmd, addr, next, phys, type);
+			__map_init_section(pmd, addr, next, phys, type, ng);
 		} else {
 			alloc_init_pte(pmd, addr, next,
-						__phys_to_pfn(phys), type);
+				       __phys_to_pfn(phys), type, alloc, ng);
 		}
 
 		phys += next - addr;
@@ -805,21 +825,24 @@
 
 static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr,
 				  unsigned long end, phys_addr_t phys,
-				  const struct mem_type *type)
+				  const struct mem_type *type,
+				  void *(*alloc)(unsigned long sz), bool ng)
 {
 	pud_t *pud = pud_offset(pgd, addr);
 	unsigned long next;
 
 	do {
 		next = pud_addr_end(addr, end);
-		alloc_init_pmd(pud, addr, next, phys, type);
+		alloc_init_pmd(pud, addr, next, phys, type, alloc, ng);
 		phys += next - addr;
 	} while (pud++, addr = next, addr != end);
 }
 
 #ifndef CONFIG_ARM_LPAE
-static void __init create_36bit_mapping(struct map_desc *md,
-					const struct mem_type *type)
+static void __init create_36bit_mapping(struct mm_struct *mm,
+					struct map_desc *md,
+					const struct mem_type *type,
+					bool ng)
 {
 	unsigned long addr, length, end;
 	phys_addr_t phys;
@@ -859,7 +882,7 @@
 	 */
 	phys |= (((md->pfn >> (32 - PAGE_SHIFT)) & 0xF) << 20);
 
-	pgd = pgd_offset_k(addr);
+	pgd = pgd_offset(mm, addr);
 	end = addr + length;
 	do {
 		pud_t *pud = pud_offset(pgd, addr);
@@ -867,7 +890,8 @@
 		int i;
 
 		for (i = 0; i < 16; i++)
-			*pmd++ = __pmd(phys | type->prot_sect | PMD_SECT_SUPER);
+			*pmd++ = __pmd(phys | type->prot_sect | PMD_SECT_SUPER |
+				       (ng ? PMD_SECT_nG : 0));
 
 		addr += SUPERSECTION_SIZE;
 		phys += SUPERSECTION_SIZE;
@@ -876,33 +900,15 @@
 }
 #endif	/* !CONFIG_ARM_LPAE */
 
-/*
- * Create the page directory entries and any necessary
- * page tables for the mapping specified by `md'.  We
- * are able to cope here with varying sizes and address
- * offsets, and we take full advantage of sections and
- * supersections.
- */
-static void __init create_mapping(struct map_desc *md)
+static void __init __create_mapping(struct mm_struct *mm, struct map_desc *md,
+				    void *(*alloc)(unsigned long sz),
+				    bool ng)
 {
 	unsigned long addr, length, end;
 	phys_addr_t phys;
 	const struct mem_type *type;
 	pgd_t *pgd;
 
-	if (md->virtual != vectors_base() && md->virtual < TASK_SIZE) {
-		pr_warn("BUG: not creating mapping for 0x%08llx at 0x%08lx in user region\n",
-			(long long)__pfn_to_phys((u64)md->pfn), md->virtual);
-		return;
-	}
-
-	if ((md->type == MT_DEVICE || md->type == MT_ROM) &&
-	    md->virtual >= PAGE_OFFSET && md->virtual < FIXADDR_START &&
-	    (md->virtual < VMALLOC_START || md->virtual >= VMALLOC_END)) {
-		pr_warn("BUG: mapping for 0x%08llx at 0x%08lx out of vmalloc space\n",
-			(long long)__pfn_to_phys((u64)md->pfn), md->virtual);
-	}
-
 	type = &mem_types[md->type];
 
 #ifndef CONFIG_ARM_LPAE
@@ -910,7 +916,7 @@
 	 * Catch 36-bit addresses
 	 */
 	if (md->pfn >= 0x100000) {
-		create_36bit_mapping(md, type);
+		create_36bit_mapping(mm, md, type, ng);
 		return;
 	}
 #endif
@@ -925,12 +931,12 @@
 		return;
 	}
 
-	pgd = pgd_offset_k(addr);
+	pgd = pgd_offset(mm, addr);
 	end = addr + length;
 	do {
 		unsigned long next = pgd_addr_end(addr, end);
 
-		alloc_init_pud(pgd, addr, next, phys, type);
+		alloc_init_pud(pgd, addr, next, phys, type, alloc, ng);
 
 		phys += next - addr;
 		addr = next;
@@ -938,6 +944,43 @@
 }
 
 /*
+ * Create the page directory entries and any necessary
+ * page tables for the mapping specified by `md'.  We
+ * are able to cope here with varying sizes and address
+ * offsets, and we take full advantage of sections and
+ * supersections.
+ */
+static void __init create_mapping(struct map_desc *md)
+{
+	if (md->virtual != vectors_base() && md->virtual < TASK_SIZE) {
+		pr_warn("BUG: not creating mapping for 0x%08llx at 0x%08lx in user region\n",
+			(long long)__pfn_to_phys((u64)md->pfn), md->virtual);
+		return;
+	}
+
+	if ((md->type == MT_DEVICE || md->type == MT_ROM) &&
+	    md->virtual >= PAGE_OFFSET && md->virtual < FIXADDR_START &&
+	    (md->virtual < VMALLOC_START || md->virtual >= VMALLOC_END)) {
+		pr_warn("BUG: mapping for 0x%08llx at 0x%08lx out of vmalloc space\n",
+			(long long)__pfn_to_phys((u64)md->pfn), md->virtual);
+	}
+
+	__create_mapping(&init_mm, md, early_alloc, false);
+}
+
+void __init create_mapping_late(struct mm_struct *mm, struct map_desc *md,
+				bool ng)
+{
+#ifdef CONFIG_ARM_LPAE
+	pud_t *pud = pud_alloc(mm, pgd_offset(mm, md->virtual), md->virtual);
+	if (WARN_ON(!pud))
+		return;
+	pmd_alloc(mm, pud, 0);
+#endif
+	__create_mapping(mm, md, late_alloc, ng);
+}
+
+/*
  * Create the architecture specific mappings
  */
 void __init iotable_init(struct map_desc *io_desc, int nr)
@@ -1392,6 +1435,9 @@
 		phys_addr_t end = start + reg->size;
 		struct map_desc map;
 
+		if (memblock_is_nomap(reg))
+			continue;
+
 		if (end > arm_lowmem_limit)
 			end = arm_lowmem_limit;
 		if (start >= end)
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 8e1ea43..0f92d57 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -274,10 +274,12 @@
 __v7_b15mp_setup:
 __v7_ca17mp_setup:
 	mov	r10, #0
-1:	adr	r12, __v7_setup_stack		@ the local stack
-	stmia	r12, {r0-r5, lr}		@ v7_invalidate_l1 touches r0-r6
+1:	adr	r0, __v7_setup_stack_ptr
+	ldr	r12, [r0]
+	add	r12, r12, r0			@ the local stack
+	stmia	r12, {r1-r6, lr}		@ v7_invalidate_l1 touches r0-r6
 	bl      v7_invalidate_l1
-	ldmia	r12, {r0-r5, lr}
+	ldmia	r12, {r1-r6, lr}
 #ifdef CONFIG_SMP
 	ALT_SMP(mrc	p15, 0, r0, c1, c0, 1)
 	ALT_UP(mov	r0, #(1 << 6))		@ fake it for UP
@@ -415,10 +417,12 @@
 #endif /* CONFIG_CPU_PJ4B */
 
 __v7_setup:
-	adr	r12, __v7_setup_stack		@ the local stack
-	stmia	r12, {r0-r5, lr}		@ v7_invalidate_l1 touches r0-r6
+	adr	r0, __v7_setup_stack_ptr
+	ldr	r12, [r0]
+	add	r12, r12, r0			@ the local stack
+	stmia	r12, {r1-r6, lr}		@ v7_invalidate_l1 touches r0-r6
 	bl      v7_invalidate_l1
-	ldmia	r12, {r0-r5, lr}
+	ldmia	r12, {r1-r6, lr}
 
 __v7_setup_cont:
 	and	r0, r9, #0xff000000		@ ARM?
@@ -480,11 +484,16 @@
 	orr	r0, r0, r6			@ set them
  THUMB(	orr	r0, r0, #1 << 30	)	@ Thumb exceptions
 	ret	lr				@ return to head.S:__ret
-ENDPROC(__v7_setup)
 
 	.align	2
+__v7_setup_stack_ptr:
+	.word	__v7_setup_stack - .
+ENDPROC(__v7_setup)
+
+	.bss
+	.align	2
 __v7_setup_stack:
-	.space	4 * 7				@ 12 registers
+	.space	4 * 7				@ 7 registers
 
 	__INITDATA
 
diff --git a/arch/arm/mm/proc-v7m.S b/arch/arm/mm/proc-v7m.S
index 67d9209077..7229d8d 100644
--- a/arch/arm/mm/proc-v7m.S
+++ b/arch/arm/mm/proc-v7m.S
@@ -12,6 +12,7 @@
  */
 #include <linux/linkage.h>
 #include <asm/assembler.h>
+#include <asm/memory.h>
 #include <asm/v7m.h>
 #include "proc-macros.S"
 
@@ -97,19 +98,19 @@
 	mov	r5, #0x00800000
 	str	r5, [r0, V7M_SCB_SHPR3]	@ set PendSV priority
 
-	@ SVC to run the kernel in this mode
+	@ SVC to switch to handler mode. Notice that this requires sp to
+	@ point to writeable memory because the processor saves
+	@ some registers to the stack.
 	badr	r1, 1f
 	ldr	r5, [r12, #11 * 4]	@ read the SVC vector entry
 	str	r1, [r12, #11 * 4]	@ write the temporary SVC vector entry
 	mov	r6, lr			@ save LR
-	mov	r7, sp			@ save SP
-	ldr	sp, =__v7m_setup_stack_top
+	ldr	sp, =init_thread_union + THREAD_START_SP
 	cpsie	i
 	svc	#0
 1:	cpsid	i
 	str	r5, [r12, #11 * 4]	@ restore the original SVC vector entry
 	mov	lr, r6			@ restore LR
-	mov	sp, r7			@ restore SP
 
 	@ Special-purpose control register
 	mov	r1, #1
@@ -123,11 +124,6 @@
 	ret	lr
 ENDPROC(__v7m_setup)
 
-	.align 2
-__v7m_setup_stack:
-	.space	4 * 8				@ 8 registers
-__v7m_setup_stack_top:
-
 	define_processor_functions v7m, dabort=nommu_early_abort, pabort=legacy_pabort, nommu=1
 
 	.section ".rodata"
diff --git a/arch/arm/plat-samsung/devs.c b/arch/arm/plat-samsung/devs.c
index 8207462..74ef889 100644
--- a/arch/arm/plat-samsung/devs.c
+++ b/arch/arm/plat-samsung/devs.c
@@ -36,7 +36,7 @@
 #include <linux/platform_data/s3c-hsotg.h>
 #include <linux/platform_data/dma-s3c24xx.h>
 
-#include <media/s5p_hdmi.h>
+#include <linux/platform_data/media/s5p_hdmi.h>
 
 #include <asm/irq.h>
 #include <asm/mach/arch.h>
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index fc7ea52..75cd734 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -12,6 +12,7 @@
 #include <xen/page.h>
 #include <xen/interface/sched.h>
 #include <xen/xen-ops.h>
+#include <asm/paravirt.h>
 #include <asm/xen/hypervisor.h>
 #include <asm/xen/hypercall.h>
 #include <asm/system_misc.h>
@@ -25,6 +26,10 @@
 #include <linux/cpufreq.h>
 #include <linux/cpu.h>
 #include <linux/console.h>
+#include <linux/pvclock_gtod.h>
+#include <linux/time64.h>
+#include <linux/timekeeping.h>
+#include <linux/timekeeper_internal.h>
 
 #include <linux/mm.h>
 
@@ -79,6 +84,83 @@
 }
 EXPORT_SYMBOL_GPL(xen_unmap_domain_gfn_range);
 
+static unsigned long long xen_stolen_accounting(int cpu)
+{
+	struct vcpu_runstate_info state;
+
+	BUG_ON(cpu != smp_processor_id());
+
+	xen_get_runstate_snapshot(&state);
+
+	WARN_ON(state.state != RUNSTATE_running);
+
+	return state.time[RUNSTATE_runnable] + state.time[RUNSTATE_offline];
+}
+
+static void xen_read_wallclock(struct timespec64 *ts)
+{
+	u32 version;
+	struct timespec64 now, ts_monotonic;
+	struct shared_info *s = HYPERVISOR_shared_info;
+	struct pvclock_wall_clock *wall_clock = &(s->wc);
+
+	/* get wallclock at system boot */
+	do {
+		version = wall_clock->version;
+		rmb();		/* fetch version before time */
+		now.tv_sec  = ((uint64_t)wall_clock->sec_hi << 32) | wall_clock->sec;
+		now.tv_nsec = wall_clock->nsec;
+		rmb();		/* fetch time before checking version */
+	} while ((wall_clock->version & 1) || (version != wall_clock->version));
+
+	/* time since system boot */
+	ktime_get_ts64(&ts_monotonic);
+	*ts = timespec64_add(now, ts_monotonic);
+}
+
+static int xen_pvclock_gtod_notify(struct notifier_block *nb,
+				   unsigned long was_set, void *priv)
+{
+	/* Protected by the calling core code serialization */
+	static struct timespec64 next_sync;
+
+	struct xen_platform_op op;
+	struct timespec64 now, system_time;
+	struct timekeeper *tk = priv;
+
+	now.tv_sec = tk->xtime_sec;
+	now.tv_nsec = (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift);
+	system_time = timespec64_add(now, tk->wall_to_monotonic);
+
+	/*
+	 * We only take the expensive HV call when the clock was set
+	 * or when the 11 minutes RTC synchronization time elapsed.
+	 */
+	if (!was_set && timespec64_compare(&now, &next_sync) < 0)
+		return NOTIFY_OK;
+
+	op.cmd = XENPF_settime64;
+	op.u.settime64.mbz = 0;
+	op.u.settime64.secs = now.tv_sec;
+	op.u.settime64.nsecs = now.tv_nsec;
+	op.u.settime64.system_time = timespec64_to_ns(&system_time);
+	(void)HYPERVISOR_platform_op(&op);
+
+	/*
+	 * Move the next drift compensation time 11 minutes
+	 * ahead. That's emulating the sync_cmos_clock() update for
+	 * the hardware RTC.
+	 */
+	next_sync = now;
+	next_sync.tv_sec += 11 * 60;
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block xen_pvclock_gtod_notifier = {
+	.notifier_call = xen_pvclock_gtod_notify,
+};
+
 static void xen_percpu_init(void)
 {
 	struct vcpu_register_vcpu_info info;
@@ -104,6 +186,8 @@
 	BUG_ON(err);
 	per_cpu(xen_vcpu, cpu) = vcpup;
 
+	xen_setup_runstate_info(cpu);
+
 after_register_vcpu_info:
 	enable_percpu_irq(xen_events_irq, 0);
 	put_cpu();
@@ -271,6 +355,11 @@
 
 	register_cpu_notifier(&xen_cpu_notifier);
 
+	pv_time_ops.steal_clock = xen_stolen_accounting;
+	static_key_slow_inc(&paravirt_steal_enabled);
+	if (xen_initial_domain())
+		pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier);
+
 	return 0;
 }
 early_initcall(xen_guest_init);
@@ -282,6 +371,11 @@
 
 	pm_power_off = xen_power_off;
 	arm_pm_restart = xen_restart;
+	if (!xen_initial_domain()) {
+		struct timespec64 ts;
+		xen_read_wallclock(&ts);
+		do_settimeofday64(&ts);
+	}
 
 	return 0;
 }
@@ -307,5 +401,6 @@
 EXPORT_SYMBOL_GPL(HYPERVISOR_physdev_op);
 EXPORT_SYMBOL_GPL(HYPERVISOR_vcpu_op);
 EXPORT_SYMBOL_GPL(HYPERVISOR_tmem_op);
+EXPORT_SYMBOL_GPL(HYPERVISOR_platform_op);
 EXPORT_SYMBOL_GPL(HYPERVISOR_multicall);
 EXPORT_SYMBOL_GPL(privcmd_call);
diff --git a/arch/arm/xen/hypercall.S b/arch/arm/xen/hypercall.S
index 10fd99c..9a36f4f 100644
--- a/arch/arm/xen/hypercall.S
+++ b/arch/arm/xen/hypercall.S
@@ -89,6 +89,7 @@
 HYPERCALL2(physdev_op);
 HYPERCALL3(vcpu_op);
 HYPERCALL1(tmem_op);
+HYPERCALL1(platform_op_raw);
 HYPERCALL2(multicall);
 
 ENTRY(privcmd_call)
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 871f217..d6ebffd 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -70,6 +70,7 @@
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_GENERIC_DMA_COHERENT
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS
+	select HAVE_IRQ_TIME_ACCOUNTING
 	select HAVE_MEMBLOCK
 	select HAVE_PATA_PLATFORM
 	select HAVE_PERF_EVENTS
@@ -92,6 +93,7 @@
 	select SPARSE_IRQ
 	select SYSCTL_EXCEPTION_TRACE
 	select HAVE_CONTEXT_TRACKING
+	select HAVE_ARM_SMCCC
 	help
 	  ARM 64-bit (AArch64) Linux support.
 
@@ -529,9 +531,6 @@
 config SYS_SUPPORTS_HUGETLBFS
 	def_bool y
 
-config ARCH_WANT_GENERAL_HUGETLB
-	def_bool y
-
 config ARCH_WANT_HUGE_PMD_SHARE
 	def_bool y if ARM64_4K_PAGES || (ARM64_16K_PAGES && !ARM64_VA_BITS_36)
 
@@ -556,6 +555,25 @@
 	  and the task is only allowed to execute a few safe syscalls
 	  defined by each seccomp mode.
 
+config PARAVIRT
+	bool "Enable paravirtualization code"
+	help
+	  This changes the kernel so it can modify itself when it is run
+	  under a hypervisor, potentially improving performance significantly
+	  over full virtualization.
+
+config PARAVIRT_TIME_ACCOUNTING
+	bool "Paravirtual steal time accounting"
+	select PARAVIRT
+	default n
+	help
+	  Select this option to enable fine granularity task steal time
+	  accounting. Time spent executing other tasks in parallel with
+	  the current vCPU is discounted from the vCPU power. To account for
+	  that, there can be a small performance impact.
+
+	  If in doubt, say N here.
+
 config XEN_DOM0
 	def_bool y
 	depends on XEN
@@ -564,6 +582,7 @@
 	bool "Xen guest support on ARM64"
 	depends on ARM64 && OF
 	select SWIOTLB_XEN
+	select PARAVIRT
 	help
 	  Say Y if you want to run Linux in a Virtual Machine on Xen on ARM64.
 
diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h
index d56ec07..e4962f0 100644
--- a/arch/arm64/include/asm/alternative.h
+++ b/arch/arm64/include/asm/alternative.h
@@ -19,7 +19,6 @@
 
 void __init apply_alternatives_all(void);
 void apply_alternatives(void *start, size_t length);
-void free_alternatives_memory(void);
 
 #define ALTINSTR_ENTRY(feature)						      \
 	" .word 661b - .\n"				/* label           */ \
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 12eff92..bb7b727 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -193,6 +193,17 @@
 	str	\src, [\tmp, :lo12:\sym]
 	.endm
 
+	/*
+	 * @sym: The name of the per-cpu variable
+	 * @reg: Result of per_cpu(sym, smp_processor_id())
+	 * @tmp: scratch register
+	 */
+	.macro this_cpu_ptr, sym, reg, tmp
+	adr_l	\reg, \sym
+	mrs	\tmp, tpidr_el1
+	add	\reg, \reg, \tmp
+	.endm
+
 /*
  * Annotate a function as position independent, i.e., safe to be called before
  * the kernel virtual mapping is activated.
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index 54efeda..7fc294c 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -68,6 +68,7 @@
 extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end);
 extern void flush_icache_range(unsigned long start, unsigned long end);
 extern void __flush_dcache_area(void *addr, size_t len);
+extern void __clean_dcache_area_pou(void *addr, size_t len);
 extern long __flush_cache_user_range(unsigned long start, unsigned long end);
 
 static inline void flush_cache_mm(struct mm_struct *mm)
diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h
index 9ea611e..510c7b4 100644
--- a/arch/arm64/include/asm/cmpxchg.h
+++ b/arch/arm64/include/asm/cmpxchg.h
@@ -19,7 +19,6 @@
 #define __ASM_CMPXCHG_H
 
 #include <linux/bug.h>
-#include <linux/mmdebug.h>
 
 #include <asm/atomic.h>
 #include <asm/barrier.h>
diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h
index ef57220..8e88a69 100644
--- a/arch/arm64/include/asm/efi.h
+++ b/arch/arm64/include/asm/efi.h
@@ -2,7 +2,9 @@
 #define _ASM_EFI_H
 
 #include <asm/io.h>
+#include <asm/mmu_context.h>
 #include <asm/neon.h>
+#include <asm/tlbflush.h>
 
 #ifdef CONFIG_EFI
 extern void efi_init(void);
@@ -10,6 +12,8 @@
 #define efi_init()
 #endif
 
+int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md);
+
 #define efi_call_virt(f, ...)						\
 ({									\
 	efi_##f##_t *__f;						\
@@ -63,6 +67,11 @@
  *   Services are enabled and the EFI_RUNTIME_SERVICES bit set.
  */
 
+static inline void efi_set_pgd(struct mm_struct *mm)
+{
+	switch_mm(NULL, mm, NULL);
+}
+
 void efi_virtmap_load(void);
 void efi_virtmap_unload(void);
 
diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h
index c5534fa..3c60f37 100644
--- a/arch/arm64/include/asm/ftrace.h
+++ b/arch/arm64/include/asm/ftrace.h
@@ -28,6 +28,8 @@
 
 extern unsigned long ftrace_graph_call;
 
+extern void return_to_handler(void);
+
 static inline unsigned long ftrace_call_adjust(unsigned long addr)
 {
 	/*
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index bb4052e..bbc1e35 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -26,36 +26,7 @@
 	return *ptep;
 }
 
-static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-				   pte_t *ptep, pte_t pte)
-{
-	set_pte_at(mm, addr, ptep, pte);
-}
 
-static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
-					 unsigned long addr, pte_t *ptep)
-{
-	ptep_clear_flush(vma, addr, ptep);
-}
-
-static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
-					   unsigned long addr, pte_t *ptep)
-{
-	ptep_set_wrprotect(mm, addr, ptep);
-}
-
-static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-					    unsigned long addr, pte_t *ptep)
-{
-	return ptep_get_and_clear(mm, addr, ptep);
-}
-
-static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
-					     unsigned long addr, pte_t *ptep,
-					     pte_t pte, int dirty)
-{
-	return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
-}
 
 static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
 					  unsigned long addr, unsigned long end,
@@ -97,4 +68,19 @@
 	clear_bit(PG_dcache_clean, &page->flags);
 }
 
+extern pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
+				struct page *page, int writable);
+#define arch_make_huge_pte arch_make_huge_pte
+extern void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+			    pte_t *ptep, pte_t pte);
+extern int huge_ptep_set_access_flags(struct vm_area_struct *vma,
+				      unsigned long addr, pte_t *ptep,
+				      pte_t pte, int dirty);
+extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+				     unsigned long addr, pte_t *ptep);
+extern void huge_ptep_set_wrprotect(struct mm_struct *mm,
+				    unsigned long addr, pte_t *ptep);
+extern void huge_ptep_clear_flush(struct vm_area_struct *vma,
+				  unsigned long addr, pte_t *ptep);
+
 #endif /* __ASM_HUGETLB_H */
diff --git a/arch/arm64/include/asm/irq.h b/arch/arm64/include/asm/irq.h
index 8e8d306..b77197d 100644
--- a/arch/arm64/include/asm/irq.h
+++ b/arch/arm64/include/asm/irq.h
@@ -1,10 +1,45 @@
 #ifndef __ASM_IRQ_H
 #define __ASM_IRQ_H
 
+#define IRQ_STACK_SIZE			THREAD_SIZE
+#define IRQ_STACK_START_SP		THREAD_START_SP
+
+#ifndef __ASSEMBLER__
+
+#include <linux/percpu.h>
+
 #include <asm-generic/irq.h>
+#include <asm/thread_info.h>
 
 struct pt_regs;
 
+DECLARE_PER_CPU(unsigned long [IRQ_STACK_SIZE/sizeof(long)], irq_stack);
+
+/*
+ * The highest address on the stack, and the first to be used. Used to
+ * find the dummy-stack frame put down by el?_irq() in entry.S, which
+ * is structured as follows:
+ *
+ *       ------------
+ *       |          |  <- irq_stack_ptr
+ *   top ------------
+ *       |   x19    | <- irq_stack_ptr - 0x08
+ *       ------------
+ *       |   x29    | <- irq_stack_ptr - 0x10
+ *       ------------
+ *
+ * where x19 holds a copy of the task stack pointer where the struct pt_regs
+ * from kernel_entry can be found.
+ *
+ */
+#define IRQ_STACK_PTR(cpu) ((unsigned long)per_cpu(irq_stack, cpu) + IRQ_STACK_START_SP)
+
+/*
+ * The offset from irq_stack_ptr where entry.S will store the original
+ * stack pointer. Used by unwind_frame() and dump_backtrace().
+ */
+#define IRQ_STACK_TO_TASK_STACK(ptr) (*((unsigned long *)((ptr) - 0x08)))
+
 extern void set_handle_irq(void (*handle_irq)(struct pt_regs *));
 
 static inline int nr_legacy_irqs(void)
@@ -12,4 +47,14 @@
 	return 0;
 }
 
+static inline bool on_irq_stack(unsigned long sp, int cpu)
+{
+	/* variable names the same as kernel/stacktrace.c */
+	unsigned long low = (unsigned long)per_cpu(irq_stack, cpu);
+	unsigned long high = low + IRQ_STACK_START_SP;
+
+	return (low <= sp && sp <= high);
+}
+
+#endif /* !__ASSEMBLER__ */
 #endif
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 5e6857b..738a95f 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -125,6 +125,7 @@
 #define VTCR_EL2_SL0_LVL1	(1 << 6)
 #define VTCR_EL2_T0SZ_MASK	0x3f
 #define VTCR_EL2_T0SZ_40B	24
+#define VTCR_EL2_VS		19
 
 /*
  * We configure the Stage-2 page tables to always restrict the IPA space to be
@@ -169,7 +170,7 @@
 #define VTTBR_BADDR_SHIFT (VTTBR_X - 1)
 #define VTTBR_BADDR_MASK  (((UL(1) << (PHYS_MASK_SHIFT - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
 #define VTTBR_VMID_SHIFT  (UL(48))
-#define VTTBR_VMID_MASK	  (UL(0xFF) << VTTBR_VMID_SHIFT)
+#define VTTBR_VMID_MASK(size) (_AT(u64, (1 << size) - 1) << VTTBR_VMID_SHIFT)
 
 /* Hyp System Trap Register */
 #define HSTR_EL2_T(x)	(1 << x)
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 5e37710..52b777b 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -20,82 +20,6 @@
 
 #include <asm/virt.h>
 
-/*
- * 0 is reserved as an invalid value.
- * Order *must* be kept in sync with the hyp switch code.
- */
-#define	MPIDR_EL1	1	/* MultiProcessor Affinity Register */
-#define	CSSELR_EL1	2	/* Cache Size Selection Register */
-#define	SCTLR_EL1	3	/* System Control Register */
-#define	ACTLR_EL1	4	/* Auxiliary Control Register */
-#define	CPACR_EL1	5	/* Coprocessor Access Control */
-#define	TTBR0_EL1	6	/* Translation Table Base Register 0 */
-#define	TTBR1_EL1	7	/* Translation Table Base Register 1 */
-#define	TCR_EL1		8	/* Translation Control Register */
-#define	ESR_EL1		9	/* Exception Syndrome Register */
-#define	AFSR0_EL1	10	/* Auxilary Fault Status Register 0 */
-#define	AFSR1_EL1	11	/* Auxilary Fault Status Register 1 */
-#define	FAR_EL1		12	/* Fault Address Register */
-#define	MAIR_EL1	13	/* Memory Attribute Indirection Register */
-#define	VBAR_EL1	14	/* Vector Base Address Register */
-#define	CONTEXTIDR_EL1	15	/* Context ID Register */
-#define	TPIDR_EL0	16	/* Thread ID, User R/W */
-#define	TPIDRRO_EL0	17	/* Thread ID, User R/O */
-#define	TPIDR_EL1	18	/* Thread ID, Privileged */
-#define	AMAIR_EL1	19	/* Aux Memory Attribute Indirection Register */
-#define	CNTKCTL_EL1	20	/* Timer Control Register (EL1) */
-#define	PAR_EL1		21	/* Physical Address Register */
-#define MDSCR_EL1	22	/* Monitor Debug System Control Register */
-#define MDCCINT_EL1	23	/* Monitor Debug Comms Channel Interrupt Enable Reg */
-
-/* 32bit specific registers. Keep them at the end of the range */
-#define	DACR32_EL2	24	/* Domain Access Control Register */
-#define	IFSR32_EL2	25	/* Instruction Fault Status Register */
-#define	FPEXC32_EL2	26	/* Floating-Point Exception Control Register */
-#define	DBGVCR32_EL2	27	/* Debug Vector Catch Register */
-#define	NR_SYS_REGS	28
-
-/* 32bit mapping */
-#define c0_MPIDR	(MPIDR_EL1 * 2)	/* MultiProcessor ID Register */
-#define c0_CSSELR	(CSSELR_EL1 * 2)/* Cache Size Selection Register */
-#define c1_SCTLR	(SCTLR_EL1 * 2)	/* System Control Register */
-#define c1_ACTLR	(ACTLR_EL1 * 2)	/* Auxiliary Control Register */
-#define c1_CPACR	(CPACR_EL1 * 2)	/* Coprocessor Access Control */
-#define c2_TTBR0	(TTBR0_EL1 * 2)	/* Translation Table Base Register 0 */
-#define c2_TTBR0_high	(c2_TTBR0 + 1)	/* TTBR0 top 32 bits */
-#define c2_TTBR1	(TTBR1_EL1 * 2)	/* Translation Table Base Register 1 */
-#define c2_TTBR1_high	(c2_TTBR1 + 1)	/* TTBR1 top 32 bits */
-#define c2_TTBCR	(TCR_EL1 * 2)	/* Translation Table Base Control R. */
-#define c3_DACR		(DACR32_EL2 * 2)/* Domain Access Control Register */
-#define c5_DFSR		(ESR_EL1 * 2)	/* Data Fault Status Register */
-#define c5_IFSR		(IFSR32_EL2 * 2)/* Instruction Fault Status Register */
-#define c5_ADFSR	(AFSR0_EL1 * 2)	/* Auxiliary Data Fault Status R */
-#define c5_AIFSR	(AFSR1_EL1 * 2)	/* Auxiliary Instr Fault Status R */
-#define c6_DFAR		(FAR_EL1 * 2)	/* Data Fault Address Register */
-#define c6_IFAR		(c6_DFAR + 1)	/* Instruction Fault Address Register */
-#define c7_PAR		(PAR_EL1 * 2)	/* Physical Address Register */
-#define c7_PAR_high	(c7_PAR + 1)	/* PAR top 32 bits */
-#define c10_PRRR	(MAIR_EL1 * 2)	/* Primary Region Remap Register */
-#define c10_NMRR	(c10_PRRR + 1)	/* Normal Memory Remap Register */
-#define c12_VBAR	(VBAR_EL1 * 2)	/* Vector Base Address Register */
-#define c13_CID		(CONTEXTIDR_EL1 * 2)	/* Context ID Register */
-#define c13_TID_URW	(TPIDR_EL0 * 2)	/* Thread ID, User R/W */
-#define c13_TID_URO	(TPIDRRO_EL0 * 2)/* Thread ID, User R/O */
-#define c13_TID_PRIV	(TPIDR_EL1 * 2)	/* Thread ID, Privileged */
-#define c10_AMAIR0	(AMAIR_EL1 * 2)	/* Aux Memory Attr Indirection Reg */
-#define c10_AMAIR1	(c10_AMAIR0 + 1)/* Aux Memory Attr Indirection Reg */
-#define c14_CNTKCTL	(CNTKCTL_EL1 * 2) /* Timer Control Register (PL1) */
-
-#define cp14_DBGDSCRext	(MDSCR_EL1 * 2)
-#define cp14_DBGBCR0	(DBGBCR0_EL1 * 2)
-#define cp14_DBGBVR0	(DBGBVR0_EL1 * 2)
-#define cp14_DBGBXVR0	(cp14_DBGBVR0 + 1)
-#define cp14_DBGWCR0	(DBGWCR0_EL1 * 2)
-#define cp14_DBGWVR0	(DBGWVR0_EL1 * 2)
-#define cp14_DBGDCCINT	(MDCCINT_EL1 * 2)
-
-#define NR_COPRO_REGS	(NR_SYS_REGS * 2)
-
 #define ARM_EXCEPTION_IRQ	  0
 #define ARM_EXCEPTION_TRAP	  1
 
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 25a4021..3066328 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -26,7 +26,6 @@
 
 #include <asm/esr.h>
 #include <asm/kvm_arm.h>
-#include <asm/kvm_asm.h>
 #include <asm/kvm_mmio.h>
 #include <asm/ptrace.h>
 #include <asm/cputype.h>
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index a35ce72..689d4c9 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -25,7 +25,6 @@
 #include <linux/types.h>
 #include <linux/kvm_types.h>
 #include <asm/kvm.h>
-#include <asm/kvm_asm.h>
 #include <asm/kvm_mmio.h>
 
 #define __KVM_HAVE_ARCH_INTC_INITIALIZED
@@ -85,6 +84,86 @@
 	u64 hpfar_el2;		/* Hyp IPA Fault Address Register */
 };
 
+/*
+ * 0 is reserved as an invalid value.
+ * Order should be kept in sync with the save/restore code.
+ */
+enum vcpu_sysreg {
+	__INVALID_SYSREG__,
+	MPIDR_EL1,	/* MultiProcessor Affinity Register */
+	CSSELR_EL1,	/* Cache Size Selection Register */
+	SCTLR_EL1,	/* System Control Register */
+	ACTLR_EL1,	/* Auxiliary Control Register */
+	CPACR_EL1,	/* Coprocessor Access Control */
+	TTBR0_EL1,	/* Translation Table Base Register 0 */
+	TTBR1_EL1,	/* Translation Table Base Register 1 */
+	TCR_EL1,	/* Translation Control Register */
+	ESR_EL1,	/* Exception Syndrome Register */
+	AFSR0_EL1,	/* Auxilary Fault Status Register 0 */
+	AFSR1_EL1,	/* Auxilary Fault Status Register 1 */
+	FAR_EL1,	/* Fault Address Register */
+	MAIR_EL1,	/* Memory Attribute Indirection Register */
+	VBAR_EL1,	/* Vector Base Address Register */
+	CONTEXTIDR_EL1,	/* Context ID Register */
+	TPIDR_EL0,	/* Thread ID, User R/W */
+	TPIDRRO_EL0,	/* Thread ID, User R/O */
+	TPIDR_EL1,	/* Thread ID, Privileged */
+	AMAIR_EL1,	/* Aux Memory Attribute Indirection Register */
+	CNTKCTL_EL1,	/* Timer Control Register (EL1) */
+	PAR_EL1,	/* Physical Address Register */
+	MDSCR_EL1,	/* Monitor Debug System Control Register */
+	MDCCINT_EL1,	/* Monitor Debug Comms Channel Interrupt Enable Reg */
+
+	/* 32bit specific registers. Keep them at the end of the range */
+	DACR32_EL2,	/* Domain Access Control Register */
+	IFSR32_EL2,	/* Instruction Fault Status Register */
+	FPEXC32_EL2,	/* Floating-Point Exception Control Register */
+	DBGVCR32_EL2,	/* Debug Vector Catch Register */
+
+	NR_SYS_REGS	/* Nothing after this line! */
+};
+
+/* 32bit mapping */
+#define c0_MPIDR	(MPIDR_EL1 * 2)	/* MultiProcessor ID Register */
+#define c0_CSSELR	(CSSELR_EL1 * 2)/* Cache Size Selection Register */
+#define c1_SCTLR	(SCTLR_EL1 * 2)	/* System Control Register */
+#define c1_ACTLR	(ACTLR_EL1 * 2)	/* Auxiliary Control Register */
+#define c1_CPACR	(CPACR_EL1 * 2)	/* Coprocessor Access Control */
+#define c2_TTBR0	(TTBR0_EL1 * 2)	/* Translation Table Base Register 0 */
+#define c2_TTBR0_high	(c2_TTBR0 + 1)	/* TTBR0 top 32 bits */
+#define c2_TTBR1	(TTBR1_EL1 * 2)	/* Translation Table Base Register 1 */
+#define c2_TTBR1_high	(c2_TTBR1 + 1)	/* TTBR1 top 32 bits */
+#define c2_TTBCR	(TCR_EL1 * 2)	/* Translation Table Base Control R. */
+#define c3_DACR		(DACR32_EL2 * 2)/* Domain Access Control Register */
+#define c5_DFSR		(ESR_EL1 * 2)	/* Data Fault Status Register */
+#define c5_IFSR		(IFSR32_EL2 * 2)/* Instruction Fault Status Register */
+#define c5_ADFSR	(AFSR0_EL1 * 2)	/* Auxiliary Data Fault Status R */
+#define c5_AIFSR	(AFSR1_EL1 * 2)	/* Auxiliary Instr Fault Status R */
+#define c6_DFAR		(FAR_EL1 * 2)	/* Data Fault Address Register */
+#define c6_IFAR		(c6_DFAR + 1)	/* Instruction Fault Address Register */
+#define c7_PAR		(PAR_EL1 * 2)	/* Physical Address Register */
+#define c7_PAR_high	(c7_PAR + 1)	/* PAR top 32 bits */
+#define c10_PRRR	(MAIR_EL1 * 2)	/* Primary Region Remap Register */
+#define c10_NMRR	(c10_PRRR + 1)	/* Normal Memory Remap Register */
+#define c12_VBAR	(VBAR_EL1 * 2)	/* Vector Base Address Register */
+#define c13_CID		(CONTEXTIDR_EL1 * 2)	/* Context ID Register */
+#define c13_TID_URW	(TPIDR_EL0 * 2)	/* Thread ID, User R/W */
+#define c13_TID_URO	(TPIDRRO_EL0 * 2)/* Thread ID, User R/O */
+#define c13_TID_PRIV	(TPIDR_EL1 * 2)	/* Thread ID, Privileged */
+#define c10_AMAIR0	(AMAIR_EL1 * 2)	/* Aux Memory Attr Indirection Reg */
+#define c10_AMAIR1	(c10_AMAIR0 + 1)/* Aux Memory Attr Indirection Reg */
+#define c14_CNTKCTL	(CNTKCTL_EL1 * 2) /* Timer Control Register (PL1) */
+
+#define cp14_DBGDSCRext	(MDSCR_EL1 * 2)
+#define cp14_DBGBCR0	(DBGBCR0_EL1 * 2)
+#define cp14_DBGBVR0	(DBGBVR0_EL1 * 2)
+#define cp14_DBGBXVR0	(cp14_DBGBVR0 + 1)
+#define cp14_DBGWCR0	(DBGWCR0_EL1 * 2)
+#define cp14_DBGWVR0	(DBGWVR0_EL1 * 2)
+#define cp14_DBGDCCINT	(MDCCINT_EL1 * 2)
+
+#define NR_COPRO_REGS	(NR_SYS_REGS * 2)
+
 struct kvm_cpu_context {
 	struct kvm_regs	gp_regs;
 	union {
@@ -197,6 +276,12 @@
 	u32 halt_successful_poll;
 	u32 halt_attempted_poll;
 	u32 halt_wakeup;
+	u32 hvc_exit_stat;
+	u64 wfe_exit_stat;
+	u64 wfi_exit_stat;
+	u64 mmio_exit_user;
+	u64 mmio_exit_kernel;
+	u64 exits;
 };
 
 int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init);
diff --git a/arch/arm64/include/asm/kvm_mmio.h b/arch/arm64/include/asm/kvm_mmio.h
index 889c908..fe612a9 100644
--- a/arch/arm64/include/asm/kvm_mmio.h
+++ b/arch/arm64/include/asm/kvm_mmio.h
@@ -19,7 +19,6 @@
 #define __ARM64_KVM_MMIO_H__
 
 #include <linux/kvm_host.h>
-#include <asm/kvm_asm.h>
 #include <asm/kvm_arm.h>
 
 /*
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 61505676..0bf8b43 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -20,6 +20,7 @@
 
 #include <asm/page.h>
 #include <asm/memory.h>
+#include <asm/cpufeature.h>
 
 /*
  * As we only have the TTBR0_EL2 register, we cannot express
@@ -158,7 +159,6 @@
 #define PTRS_PER_S2_PGD_SHIFT	(KVM_PHYS_SHIFT - PGDIR_SHIFT)
 #endif
 #define PTRS_PER_S2_PGD		(1 << PTRS_PER_S2_PGD_SHIFT)
-#define S2_PGD_ORDER		get_order(PTRS_PER_S2_PGD * sizeof(pgd_t))
 
 #define kvm_pgd_index(addr)	(((addr) >> PGDIR_SHIFT) & (PTRS_PER_S2_PGD - 1))
 
@@ -302,5 +302,12 @@
 	merged_hyp_pgd[idmap_idx] = __pgd(__pa(boot_hyp_pgd) | PMD_TYPE_TABLE);
 }
 
+static inline unsigned int kvm_get_vmid_bits(void)
+{
+	int reg = read_system_reg(SYS_ID_AA64MMFR1_EL1);
+
+	return (cpuid_feature_extract_field(reg, ID_AA64MMFR1_VMIDBITS_SHIFT) == 2) ? 16 : 8;
+}
+
 #endif /* __ASSEMBLY__ */
 #endif /* __ARM64_KVM_MMU_H__ */
diff --git a/arch/arm64/include/asm/paravirt.h b/arch/arm64/include/asm/paravirt.h
new file mode 100644
index 0000000..fd5f428
--- /dev/null
+++ b/arch/arm64/include/asm/paravirt.h
@@ -0,0 +1,20 @@
+#ifndef _ASM_ARM64_PARAVIRT_H
+#define _ASM_ARM64_PARAVIRT_H
+
+#ifdef CONFIG_PARAVIRT
+struct static_key;
+extern struct static_key paravirt_steal_enabled;
+extern struct static_key paravirt_steal_rq_enabled;
+
+struct pv_time_ops {
+	unsigned long long (*steal_clock)(int cpu);
+};
+extern struct pv_time_ops pv_time_ops;
+
+static inline u64 paravirt_steal_clock(int cpu)
+{
+	return pv_time_ops.steal_clock(cpu);
+}
+#endif
+
+#endif
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index d6739e8..5c25b83 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -90,7 +90,23 @@
 /*
  * Contiguous page definitions.
  */
-#define CONT_PTES		(_AC(1, UL) << CONT_SHIFT)
+#ifdef CONFIG_ARM64_64K_PAGES
+#define CONT_PTE_SHIFT		5
+#define CONT_PMD_SHIFT		5
+#elif defined(CONFIG_ARM64_16K_PAGES)
+#define CONT_PTE_SHIFT		7
+#define CONT_PMD_SHIFT		5
+#else
+#define CONT_PTE_SHIFT		4
+#define CONT_PMD_SHIFT		4
+#endif
+
+#define CONT_PTES		(1 << CONT_PTE_SHIFT)
+#define CONT_PTE_SIZE		(CONT_PTES * PAGE_SIZE)
+#define CONT_PTE_MASK		(~(CONT_PTE_SIZE - 1))
+#define CONT_PMDS		(1 << CONT_PMD_SHIFT)
+#define CONT_PMD_SIZE		(CONT_PMDS * PMD_SIZE)
+#define CONT_PMD_MASK		(~(CONT_PMD_SIZE - 1))
 /* the the numerical offset of the PTE within a range of CONT_PTES */
 #define CONT_RANGE_OFFSET(addr) (((addr)>>PAGE_SHIFT)&(CONT_PTES-1))
 
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 63f52b5..69d2e2f 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -167,6 +167,16 @@
 	((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER))
 #define pte_valid_not_user(pte) \
 	((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID)
+#define pte_valid_young(pte) \
+	((pte_val(pte) & (PTE_VALID | PTE_AF)) == (PTE_VALID | PTE_AF))
+
+/*
+ * Could the pte be present in the TLB? We must check mm_tlb_flush_pending
+ * so that we don't erroneously return false for pages that have been
+ * remapped as PROT_NONE but are yet to be flushed from the TLB.
+ */
+#define pte_accessible(mm, pte)	\
+	(mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid_young(pte))
 
 static inline pte_t clear_pte_bit(pte_t pte, pgprot_t prot)
 {
@@ -217,7 +227,8 @@
 
 static inline pte_t pte_mkcont(pte_t pte)
 {
-	return set_pte_bit(pte, __pgprot(PTE_CONT));
+	pte = set_pte_bit(pte, __pgprot(PTE_CONT));
+	return set_pte_bit(pte, __pgprot(PTE_TYPE_PAGE));
 }
 
 static inline pte_t pte_mknoncont(pte_t pte)
@@ -225,6 +236,11 @@
 	return clear_pte_bit(pte, __pgprot(PTE_CONT));
 }
 
+static inline pmd_t pmd_mkcont(pmd_t pmd)
+{
+	return __pmd(pmd_val(pmd) | PMD_SECT_CONT);
+}
+
 static inline void set_pte(pte_t *ptep, pte_t pte)
 {
 	*ptep = pte;
@@ -298,7 +314,7 @@
 /*
  * Hugetlb definitions.
  */
-#define HUGE_MAX_HSTATE		2
+#define HUGE_MAX_HSTATE		4
 #define HPAGE_SHIFT		PMD_SHIFT
 #define HPAGE_SIZE		(_AC(1, UL) << HPAGE_SHIFT)
 #define HPAGE_MASK		(~(HPAGE_SIZE - 1))
@@ -664,7 +680,8 @@
 
 #include <asm-generic/pgtable.h>
 
-#define pgtable_cache_init() do { } while (0)
+void pgd_cache_init(void);
+#define pgtable_cache_init	pgd_cache_init
 
 /*
  * On AArch64, the cache coherency is handled via the set_pte_at() function.
diff --git a/arch/arm64/include/asm/shmparam.h b/arch/arm64/include/asm/shmparam.h
index 4df608a..e368a55 100644
--- a/arch/arm64/include/asm/shmparam.h
+++ b/arch/arm64/include/asm/shmparam.h
@@ -21,7 +21,7 @@
  * alignment value. Since we don't have aliasing D-caches, the rest of
  * the time we can safely use PAGE_SIZE.
  */
-#define COMPAT_SHMLBA	0x4000
+#define COMPAT_SHMLBA	(4 * PAGE_SIZE)
 
 #include <asm-generic/shmparam.h>
 
diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h
index c85e96d..fc9682b 100644
--- a/arch/arm64/include/asm/spinlock.h
+++ b/arch/arm64/include/asm/spinlock.h
@@ -26,9 +26,28 @@
  * The memory barriers are implicit with the load-acquire and store-release
  * instructions.
  */
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
+{
+	unsigned int tmp;
+	arch_spinlock_t lockval;
 
-#define arch_spin_unlock_wait(lock) \
-	do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0)
+	asm volatile(
+"	sevl\n"
+"1:	wfe\n"
+"2:	ldaxr	%w0, %2\n"
+"	eor	%w1, %w0, %w0, ror #16\n"
+"	cbnz	%w1, 1b\n"
+	ARM64_LSE_ATOMIC_INSN(
+	/* LL/SC */
+"	stxr	%w1, %w0, %2\n"
+"	cbnz	%w1, 2b\n", /* Serialise against any concurrent lockers */
+	/* LSE atomics */
+"	nop\n"
+"	nop\n")
+	: "=&r" (lockval), "=&r" (tmp), "+Q" (*lock)
+	:
+	: "memory");
+}
 
 #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
 
diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h
index 7318f6d..801a16db 100644
--- a/arch/arm64/include/asm/stacktrace.h
+++ b/arch/arm64/include/asm/stacktrace.h
@@ -16,14 +16,19 @@
 #ifndef __ASM_STACKTRACE_H
 #define __ASM_STACKTRACE_H
 
+struct task_struct;
+
 struct stackframe {
 	unsigned long fp;
 	unsigned long sp;
 	unsigned long pc;
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	unsigned int graph;
+#endif
 };
 
-extern int unwind_frame(struct stackframe *frame);
-extern void walk_stackframe(struct stackframe *frame,
+extern int unwind_frame(struct task_struct *tsk, struct stackframe *frame);
+extern void walk_stackframe(struct task_struct *tsk, struct stackframe *frame,
 			    int (*fn)(struct stackframe *, void *), void *data);
 
 #endif	/* __ASM_STACKTRACE_H */
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index d48ab5b..4aeebec 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -20,6 +20,8 @@
 #ifndef __ASM_SYSREG_H
 #define __ASM_SYSREG_H
 
+#include <linux/stringify.h>
+
 #include <asm/opcodes.h>
 
 /*
@@ -208,6 +210,8 @@
 
 #else
 
+#include <linux/types.h>
+
 asm(
 "	.irp	num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30\n"
 "	.equ	__reg_num_x\\num, \\num\n"
@@ -232,6 +236,23 @@
 	val |= set;
 	asm volatile("msr sctlr_el1, %0" : : "r" (val));
 }
+
+/*
+ * Unlike read_cpuid, calls to read_sysreg are never expected to be
+ * optimized away or replaced with synthetic values.
+ */
+#define read_sysreg(r) ({					\
+	u64 __val;						\
+	asm volatile("mrs %0, " __stringify(r) : "=r" (__val));	\
+	__val;							\
+})
+
+#define write_sysreg(v, r) do {					\
+	u64 __val = (u64)v;					\
+	asm volatile("msr " __stringify(r) ", %0"		\
+		     : : "r" (__val));				\
+} while (0)
+
 #endif
 
 #endif	/* __ASM_SYSREG_H */
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 90c7ff2..abd64bd 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -73,10 +73,16 @@
  */
 static inline struct thread_info *current_thread_info(void) __attribute_const__;
 
+/*
+ * struct thread_info can be accessed directly via sp_el0.
+ */
 static inline struct thread_info *current_thread_info(void)
 {
-	return (struct thread_info *)
-		(current_stack_pointer & ~(THREAD_SIZE - 1));
+	unsigned long sp_el0;
+
+	asm ("mrs %0, sp_el0" : "=r" (sp_el0));
+
+	return (struct thread_info *)sp_el0;
 }
 
 #define thread_saved_pc(tsk)	\
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 474691f..83cd7e6 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -14,10 +14,10 @@
 arm64-obj-y		:= debug-monitors.o entry.o irq.o fpsimd.o		\
 			   entry-fpsimd.o process.o ptrace.o setup.o signal.o	\
 			   sys.o stacktrace.o time.o traps.o io.o vdso.o	\
-			   hyp-stub.o psci.o psci-call.o cpu_ops.o insn.o	\
+			   hyp-stub.o psci.o cpu_ops.o insn.o	\
 			   return_address.o cpuinfo.o cpu_errata.o		\
 			   cpufeature.o alternative.o cacheinfo.o		\
-			   smp.o smp_spin_table.o topology.o
+			   smp.o smp_spin_table.o topology.o smccc-call.o
 
 extra-$(CONFIG_EFI)			:= efi-entry.o
 
@@ -41,6 +41,7 @@
 arm64-obj-$(CONFIG_PCI)			+= pci.o
 arm64-obj-$(CONFIG_ARMV8_DEPRECATED)	+= armv8_deprecated.o
 arm64-obj-$(CONFIG_ACPI)		+= acpi.o
+arm64-obj-$(CONFIG_PARAVIRT)		+= paravirt.o
 
 obj-y					+= $(arm64-obj-y) vdso/
 obj-m					+= $(arm64-obj-m)
diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c
index ab9db0e..d2ee1b2 100644
--- a/arch/arm64/kernel/alternative.c
+++ b/arch/arm64/kernel/alternative.c
@@ -158,9 +158,3 @@
 
 	__apply_alternatives(&region);
 }
-
-void free_alternatives_memory(void)
-{
-	free_reserved_area(__alt_instructions, __alt_instructions_end,
-			   0, "alternatives");
-}
diff --git a/arch/arm64/kernel/arm64ksyms.c b/arch/arm64/kernel/arm64ksyms.c
index 3b6d8cc..678f30b0 100644
--- a/arch/arm64/kernel/arm64ksyms.c
+++ b/arch/arm64/kernel/arm64ksyms.c
@@ -26,6 +26,7 @@
 #include <linux/syscalls.h>
 #include <linux/uaccess.h>
 #include <linux/io.h>
+#include <linux/arm-smccc.h>
 
 #include <asm/checksum.h>
 
@@ -68,3 +69,7 @@
 #ifdef CONFIG_FUNCTION_TRACER
 EXPORT_SYMBOL(_mcount);
 #endif
+
+	/* arm-smccc */
+EXPORT_SYMBOL(arm_smccc_smc);
+EXPORT_SYMBOL(arm_smccc_hvc);
diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c
index 937f5e58..3e01207 100644
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -62,7 +62,7 @@
 };
 
 static LIST_HEAD(insn_emulation);
-static int nr_insn_emulated;
+static int nr_insn_emulated __initdata;
 static DEFINE_RAW_SPINLOCK(insn_emulation_lock);
 
 static void register_emulation_hooks(struct insn_emulation_ops *ops)
@@ -173,7 +173,7 @@
 	return ret;
 }
 
-static void register_insn_emulation(struct insn_emulation_ops *ops)
+static void __init register_insn_emulation(struct insn_emulation_ops *ops)
 {
 	unsigned long flags;
 	struct insn_emulation *insn;
@@ -237,7 +237,7 @@
 	{ }
 };
 
-static void register_insn_emulation_sysctl(struct ctl_table *table)
+static void __init register_insn_emulation_sysctl(struct ctl_table *table)
 {
 	unsigned long flags;
 	int i = 0;
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 25de8b2..fffa4ac6 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -28,6 +28,7 @@
 #include <asm/suspend.h>
 #include <asm/vdso_datapage.h>
 #include <linux/kbuild.h>
+#include <linux/arm-smccc.h>
 
 int main(void)
 {
@@ -108,49 +109,11 @@
   DEFINE(CPU_GP_REGS,		offsetof(struct kvm_cpu_context, gp_regs));
   DEFINE(CPU_USER_PT_REGS,	offsetof(struct kvm_regs, regs));
   DEFINE(CPU_FP_REGS,		offsetof(struct kvm_regs, fp_regs));
-  DEFINE(CPU_SP_EL1,		offsetof(struct kvm_regs, sp_el1));
-  DEFINE(CPU_ELR_EL1,		offsetof(struct kvm_regs, elr_el1));
-  DEFINE(CPU_SPSR,		offsetof(struct kvm_regs, spsr));
-  DEFINE(CPU_SYSREGS,		offsetof(struct kvm_cpu_context, sys_regs));
+  DEFINE(VCPU_FPEXC32_EL2,	offsetof(struct kvm_vcpu, arch.ctxt.sys_regs[FPEXC32_EL2]));
   DEFINE(VCPU_ESR_EL2,		offsetof(struct kvm_vcpu, arch.fault.esr_el2));
   DEFINE(VCPU_FAR_EL2,		offsetof(struct kvm_vcpu, arch.fault.far_el2));
   DEFINE(VCPU_HPFAR_EL2,	offsetof(struct kvm_vcpu, arch.fault.hpfar_el2));
-  DEFINE(VCPU_DEBUG_FLAGS,	offsetof(struct kvm_vcpu, arch.debug_flags));
-  DEFINE(VCPU_DEBUG_PTR,	offsetof(struct kvm_vcpu, arch.debug_ptr));
-  DEFINE(DEBUG_BCR, 		offsetof(struct kvm_guest_debug_arch, dbg_bcr));
-  DEFINE(DEBUG_BVR, 		offsetof(struct kvm_guest_debug_arch, dbg_bvr));
-  DEFINE(DEBUG_WCR, 		offsetof(struct kvm_guest_debug_arch, dbg_wcr));
-  DEFINE(DEBUG_WVR, 		offsetof(struct kvm_guest_debug_arch, dbg_wvr));
-  DEFINE(VCPU_HCR_EL2,		offsetof(struct kvm_vcpu, arch.hcr_el2));
-  DEFINE(VCPU_MDCR_EL2,	offsetof(struct kvm_vcpu, arch.mdcr_el2));
-  DEFINE(VCPU_IRQ_LINES,	offsetof(struct kvm_vcpu, arch.irq_lines));
   DEFINE(VCPU_HOST_CONTEXT,	offsetof(struct kvm_vcpu, arch.host_cpu_context));
-  DEFINE(VCPU_HOST_DEBUG_STATE, offsetof(struct kvm_vcpu, arch.host_debug_state));
-  DEFINE(VCPU_TIMER_CNTV_CTL,	offsetof(struct kvm_vcpu, arch.timer_cpu.cntv_ctl));
-  DEFINE(VCPU_TIMER_CNTV_CVAL,	offsetof(struct kvm_vcpu, arch.timer_cpu.cntv_cval));
-  DEFINE(KVM_TIMER_CNTVOFF,	offsetof(struct kvm, arch.timer.cntvoff));
-  DEFINE(KVM_TIMER_ENABLED,	offsetof(struct kvm, arch.timer.enabled));
-  DEFINE(VCPU_KVM,		offsetof(struct kvm_vcpu, kvm));
-  DEFINE(VCPU_VGIC_CPU,		offsetof(struct kvm_vcpu, arch.vgic_cpu));
-  DEFINE(VGIC_V2_CPU_HCR,	offsetof(struct vgic_cpu, vgic_v2.vgic_hcr));
-  DEFINE(VGIC_V2_CPU_VMCR,	offsetof(struct vgic_cpu, vgic_v2.vgic_vmcr));
-  DEFINE(VGIC_V2_CPU_MISR,	offsetof(struct vgic_cpu, vgic_v2.vgic_misr));
-  DEFINE(VGIC_V2_CPU_EISR,	offsetof(struct vgic_cpu, vgic_v2.vgic_eisr));
-  DEFINE(VGIC_V2_CPU_ELRSR,	offsetof(struct vgic_cpu, vgic_v2.vgic_elrsr));
-  DEFINE(VGIC_V2_CPU_APR,	offsetof(struct vgic_cpu, vgic_v2.vgic_apr));
-  DEFINE(VGIC_V2_CPU_LR,	offsetof(struct vgic_cpu, vgic_v2.vgic_lr));
-  DEFINE(VGIC_V3_CPU_SRE,	offsetof(struct vgic_cpu, vgic_v3.vgic_sre));
-  DEFINE(VGIC_V3_CPU_HCR,	offsetof(struct vgic_cpu, vgic_v3.vgic_hcr));
-  DEFINE(VGIC_V3_CPU_VMCR,	offsetof(struct vgic_cpu, vgic_v3.vgic_vmcr));
-  DEFINE(VGIC_V3_CPU_MISR,	offsetof(struct vgic_cpu, vgic_v3.vgic_misr));
-  DEFINE(VGIC_V3_CPU_EISR,	offsetof(struct vgic_cpu, vgic_v3.vgic_eisr));
-  DEFINE(VGIC_V3_CPU_ELRSR,	offsetof(struct vgic_cpu, vgic_v3.vgic_elrsr));
-  DEFINE(VGIC_V3_CPU_AP0R,	offsetof(struct vgic_cpu, vgic_v3.vgic_ap0r));
-  DEFINE(VGIC_V3_CPU_AP1R,	offsetof(struct vgic_cpu, vgic_v3.vgic_ap1r));
-  DEFINE(VGIC_V3_CPU_LR,	offsetof(struct vgic_cpu, vgic_v3.vgic_lr));
-  DEFINE(VGIC_CPU_NR_LR,	offsetof(struct vgic_cpu, nr_lr));
-  DEFINE(KVM_VTTBR,		offsetof(struct kvm, arch.vttbr));
-  DEFINE(KVM_VGIC_VCTRL,	offsetof(struct kvm, arch.vgic.vctrl_base));
 #endif
 #ifdef CONFIG_CPU_PM
   DEFINE(CPU_SUSPEND_SZ,	sizeof(struct cpu_suspend_ctx));
@@ -161,5 +124,7 @@
   DEFINE(SLEEP_SAVE_SP_PHYS,	offsetof(struct sleep_save_sp, save_ptr_stash_phys));
   DEFINE(SLEEP_SAVE_SP_VIRT,	offsetof(struct sleep_save_sp, save_ptr_stash));
 #endif
+  DEFINE(ARM_SMCCC_RES_X0_OFFS,	offsetof(struct arm_smccc_res, a0));
+  DEFINE(ARM_SMCCC_RES_X2_OFFS,	offsetof(struct arm_smccc_res, a2));
   return 0;
 }
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 0669c63..5c90aa4 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -684,7 +684,7 @@
 	{},
 };
 
-static void cap_set_hwcap(const struct arm64_cpu_capabilities *cap)
+static void __init cap_set_hwcap(const struct arm64_cpu_capabilities *cap)
 {
 	switch (cap->hwcap_type) {
 	case CAP_HWCAP:
@@ -729,7 +729,7 @@
 	return rc;
 }
 
-static void setup_cpu_hwcaps(void)
+static void __init setup_cpu_hwcaps(void)
 {
 	int i;
 	const struct arm64_cpu_capabilities *hwcaps = arm64_hwcaps;
@@ -758,7 +758,8 @@
  * Run through the enabled capabilities and enable() it on all active
  * CPUs
  */
-static void enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps)
+static void __init
+enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps)
 {
 	int i;
 
@@ -897,7 +898,7 @@
 
 #endif	/* CONFIG_HOTPLUG_CPU */
 
-static void setup_feature_capabilities(void)
+static void __init setup_feature_capabilities(void)
 {
 	update_cpu_capabilities(arm64_features, "detected feature:");
 	enable_cpu_capabilities(arm64_features);
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index 4eeb171..b6abc85 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -11,317 +11,34 @@
  *
  */
 
-#include <linux/atomic.h>
 #include <linux/dmi.h>
 #include <linux/efi.h>
-#include <linux/export.h>
-#include <linux/memblock.h>
-#include <linux/mm_types.h>
-#include <linux/bootmem.h>
-#include <linux/of.h>
-#include <linux/of_fdt.h>
-#include <linux/preempt.h>
-#include <linux/rbtree.h>
-#include <linux/rwsem.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/spinlock.h>
+#include <linux/init.h>
 
-#include <asm/cacheflush.h>
 #include <asm/efi.h>
-#include <asm/tlbflush.h>
-#include <asm/mmu_context.h>
-#include <asm/mmu.h>
-#include <asm/pgtable.h>
 
-struct efi_memory_map memmap;
-
-static u64 efi_system_table;
-
-static pgd_t efi_pgd[PTRS_PER_PGD] __page_aligned_bss;
-
-static struct mm_struct efi_mm = {
-	.mm_rb			= RB_ROOT,
-	.pgd			= efi_pgd,
-	.mm_users		= ATOMIC_INIT(2),
-	.mm_count		= ATOMIC_INIT(1),
-	.mmap_sem		= __RWSEM_INITIALIZER(efi_mm.mmap_sem),
-	.page_table_lock	= __SPIN_LOCK_UNLOCKED(efi_mm.page_table_lock),
-	.mmlist			= LIST_HEAD_INIT(efi_mm.mmlist),
-};
-
-static int __init is_normal_ram(efi_memory_desc_t *md)
+int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md)
 {
-	if (md->attribute & EFI_MEMORY_WB)
-		return 1;
-	return 0;
-}
-
-/*
- * Translate a EFI virtual address into a physical address: this is necessary,
- * as some data members of the EFI system table are virtually remapped after
- * SetVirtualAddressMap() has been called.
- */
-static phys_addr_t efi_to_phys(unsigned long addr)
-{
-	efi_memory_desc_t *md;
-
-	for_each_efi_memory_desc(&memmap, md) {
-		if (!(md->attribute & EFI_MEMORY_RUNTIME))
-			continue;
-		if (md->virt_addr == 0)
-			/* no virtual mapping has been installed by the stub */
-			break;
-		if (md->virt_addr <= addr &&
-		    (addr - md->virt_addr) < (md->num_pages << EFI_PAGE_SHIFT))
-			return md->phys_addr + addr - md->virt_addr;
-	}
-	return addr;
-}
-
-static int __init uefi_init(void)
-{
-	efi_char16_t *c16;
-	void *config_tables;
-	u64 table_size;
-	char vendor[100] = "unknown";
-	int i, retval;
-
-	efi.systab = early_memremap(efi_system_table,
-				    sizeof(efi_system_table_t));
-	if (efi.systab == NULL) {
-		pr_warn("Unable to map EFI system table.\n");
-		return -ENOMEM;
-	}
-
-	set_bit(EFI_BOOT, &efi.flags);
-	set_bit(EFI_64BIT, &efi.flags);
+	pteval_t prot_val;
 
 	/*
-	 * Verify the EFI Table
+	 * Only regions of type EFI_RUNTIME_SERVICES_CODE need to be
+	 * executable, everything else can be mapped with the XN bits
+	 * set.
 	 */
-	if (efi.systab->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) {
-		pr_err("System table signature incorrect\n");
-		retval = -EINVAL;
-		goto out;
-	}
-	if ((efi.systab->hdr.revision >> 16) < 2)
-		pr_warn("Warning: EFI system table version %d.%02d, expected 2.00 or greater\n",
-			efi.systab->hdr.revision >> 16,
-			efi.systab->hdr.revision & 0xffff);
+	if ((md->attribute & EFI_MEMORY_WB) == 0)
+		prot_val = PROT_DEVICE_nGnRE;
+	else if (md->type == EFI_RUNTIME_SERVICES_CODE ||
+		 !PAGE_ALIGNED(md->phys_addr))
+		prot_val = pgprot_val(PAGE_KERNEL_EXEC);
+	else
+		prot_val = pgprot_val(PAGE_KERNEL);
 
-	/* Show what we know for posterity */
-	c16 = early_memremap(efi_to_phys(efi.systab->fw_vendor),
-			     sizeof(vendor) * sizeof(efi_char16_t));
-	if (c16) {
-		for (i = 0; i < (int) sizeof(vendor) - 1 && *c16; ++i)
-			vendor[i] = c16[i];
-		vendor[i] = '\0';
-		early_memunmap(c16, sizeof(vendor) * sizeof(efi_char16_t));
-	}
-
-	pr_info("EFI v%u.%.02u by %s\n",
-		efi.systab->hdr.revision >> 16,
-		efi.systab->hdr.revision & 0xffff, vendor);
-
-	table_size = sizeof(efi_config_table_64_t) * efi.systab->nr_tables;
-	config_tables = early_memremap(efi_to_phys(efi.systab->tables),
-				       table_size);
-	if (config_tables == NULL) {
-		pr_warn("Unable to map EFI config table array.\n");
-		retval = -ENOMEM;
-		goto out;
-	}
-	retval = efi_config_parse_tables(config_tables, efi.systab->nr_tables,
-					 sizeof(efi_config_table_64_t), NULL);
-
-	early_memunmap(config_tables, table_size);
-out:
-	early_memunmap(efi.systab,  sizeof(efi_system_table_t));
-	return retval;
-}
-
-/*
- * Return true for RAM regions we want to permanently reserve.
- */
-static __init int is_reserve_region(efi_memory_desc_t *md)
-{
-	switch (md->type) {
-	case EFI_LOADER_CODE:
-	case EFI_LOADER_DATA:
-	case EFI_BOOT_SERVICES_CODE:
-	case EFI_BOOT_SERVICES_DATA:
-	case EFI_CONVENTIONAL_MEMORY:
-	case EFI_PERSISTENT_MEMORY:
-		return 0;
-	default:
-		break;
-	}
-	return is_normal_ram(md);
-}
-
-static __init void reserve_regions(void)
-{
-	efi_memory_desc_t *md;
-	u64 paddr, npages, size;
-
-	if (efi_enabled(EFI_DBG))
-		pr_info("Processing EFI memory map:\n");
-
-	for_each_efi_memory_desc(&memmap, md) {
-		paddr = md->phys_addr;
-		npages = md->num_pages;
-
-		if (efi_enabled(EFI_DBG)) {
-			char buf[64];
-
-			pr_info("  0x%012llx-0x%012llx %s",
-				paddr, paddr + (npages << EFI_PAGE_SHIFT) - 1,
-				efi_md_typeattr_format(buf, sizeof(buf), md));
-		}
-
-		memrange_efi_to_native(&paddr, &npages);
-		size = npages << PAGE_SHIFT;
-
-		if (is_normal_ram(md))
-			early_init_dt_add_memory_arch(paddr, size);
-
-		if (is_reserve_region(md)) {
-			memblock_reserve(paddr, size);
-			if (efi_enabled(EFI_DBG))
-				pr_cont("*");
-		}
-
-		if (efi_enabled(EFI_DBG))
-			pr_cont("\n");
-	}
-
-	set_bit(EFI_MEMMAP, &efi.flags);
-}
-
-void __init efi_init(void)
-{
-	struct efi_fdt_params params;
-
-	/* Grab UEFI information placed in FDT by stub */
-	if (!efi_get_fdt_params(&params))
-		return;
-
-	efi_system_table = params.system_table;
-
-	memblock_reserve(params.mmap & PAGE_MASK,
-			 PAGE_ALIGN(params.mmap_size + (params.mmap & ~PAGE_MASK)));
-	memmap.phys_map = params.mmap;
-	memmap.map = early_memremap(params.mmap, params.mmap_size);
-	if (memmap.map == NULL) {
-		/*
-		* If we are booting via UEFI, the UEFI memory map is the only
-		* description of memory we have, so there is little point in
-		* proceeding if we cannot access it.
-		*/
-		panic("Unable to map EFI memory map.\n");
-	}
-	memmap.map_end = memmap.map + params.mmap_size;
-	memmap.desc_size = params.desc_size;
-	memmap.desc_version = params.desc_ver;
-
-	if (uefi_init() < 0)
-		return;
-
-	reserve_regions();
-	early_memunmap(memmap.map, params.mmap_size);
-}
-
-static bool __init efi_virtmap_init(void)
-{
-	efi_memory_desc_t *md;
-
-	init_new_context(NULL, &efi_mm);
-
-	for_each_efi_memory_desc(&memmap, md) {
-		pgprot_t prot;
-
-		if (!(md->attribute & EFI_MEMORY_RUNTIME))
-			continue;
-		if (md->virt_addr == 0)
-			return false;
-
-		pr_info("  EFI remap 0x%016llx => %p\n",
-			md->phys_addr, (void *)md->virt_addr);
-
-		/*
-		 * Only regions of type EFI_RUNTIME_SERVICES_CODE need to be
-		 * executable, everything else can be mapped with the XN bits
-		 * set.
-		 */
-		if (!is_normal_ram(md))
-			prot = __pgprot(PROT_DEVICE_nGnRE);
-		else if (md->type == EFI_RUNTIME_SERVICES_CODE ||
-			 !PAGE_ALIGNED(md->phys_addr))
-			prot = PAGE_KERNEL_EXEC;
-		else
-			prot = PAGE_KERNEL;
-
-		create_pgd_mapping(&efi_mm, md->phys_addr, md->virt_addr,
-				   md->num_pages << EFI_PAGE_SHIFT, 
-				   __pgprot(pgprot_val(prot) | PTE_NG));
-	}
-	return true;
-}
-
-/*
- * Enable the UEFI Runtime Services if all prerequisites are in place, i.e.,
- * non-early mapping of the UEFI system table and virtual mappings for all
- * EFI_MEMORY_RUNTIME regions.
- */
-static int __init arm64_enable_runtime_services(void)
-{
-	u64 mapsize;
-
-	if (!efi_enabled(EFI_BOOT)) {
-		pr_info("EFI services will not be available.\n");
-		return 0;
-	}
-
-	if (efi_runtime_disabled()) {
-		pr_info("EFI runtime services will be disabled.\n");
-		return 0;
-	}
-
-	pr_info("Remapping and enabling EFI services.\n");
-
-	mapsize = memmap.map_end - memmap.map;
-	memmap.map = (__force void *)ioremap_cache(memmap.phys_map,
-						   mapsize);
-	if (!memmap.map) {
-		pr_err("Failed to remap EFI memory map\n");
-		return -ENOMEM;
-	}
-	memmap.map_end = memmap.map + mapsize;
-	efi.memmap = &memmap;
-
-	efi.systab = (__force void *)ioremap_cache(efi_system_table,
-						   sizeof(efi_system_table_t));
-	if (!efi.systab) {
-		pr_err("Failed to remap EFI System Table\n");
-		return -ENOMEM;
-	}
-	set_bit(EFI_SYSTEM_TABLES, &efi.flags);
-
-	if (!efi_virtmap_init()) {
-		pr_err("No UEFI virtual mapping was installed -- runtime services will not be available\n");
-		return -ENOMEM;
-	}
-
-	/* Set up runtime services function pointers */
-	efi_native_runtime_setup();
-	set_bit(EFI_RUNTIME_SERVICES, &efi.flags);
-
-	efi.runtime_version = efi.systab->hdr.revision;
-
+	create_pgd_mapping(mm, md->phys_addr, md->virt_addr,
+			   md->num_pages << EFI_PAGE_SHIFT,
+			   __pgprot(prot_val | PTE_NG));
 	return 0;
 }
-early_initcall(arm64_enable_runtime_services);
 
 static int __init arm64_dmi_init(void)
 {
@@ -337,23 +54,6 @@
 }
 core_initcall(arm64_dmi_init);
 
-static void efi_set_pgd(struct mm_struct *mm)
-{
-	switch_mm(NULL, mm, NULL);
-}
-
-void efi_virtmap_load(void)
-{
-	preempt_disable();
-	efi_set_pgd(&efi_mm);
-}
-
-void efi_virtmap_unload(void)
-{
-	efi_set_pgd(current->active_mm);
-	preempt_enable();
-}
-
 /*
  * UpdateCapsule() depends on the system being shutdown via
  * ResetSystem().
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 7ed3d75..1f7f5a2 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -27,6 +27,7 @@
 #include <asm/cpufeature.h>
 #include <asm/errno.h>
 #include <asm/esr.h>
+#include <asm/irq.h>
 #include <asm/thread_info.h>
 #include <asm/unistd.h>
 
@@ -88,9 +89,12 @@
 
 	.if	\el == 0
 	mrs	x21, sp_el0
-	get_thread_info tsk			// Ensure MDSCR_EL1.SS is clear,
+	mov	tsk, sp
+	and	tsk, tsk, #~(THREAD_SIZE - 1)	// Ensure MDSCR_EL1.SS is clear,
 	ldr	x19, [tsk, #TI_FLAGS]		// since we can unmask debug
 	disable_step_tsk x19, x20		// exceptions when scheduling.
+
+	mov	x29, xzr			// fp pointed to user-space
 	.else
 	add	x21, sp, #S_FRAME_SIZE
 	.endif
@@ -108,6 +112,13 @@
 	.endif
 
 	/*
+	 * Set sp_el0 to current thread_info.
+	 */
+	.if	\el == 0
+	msr	sp_el0, tsk
+	.endif
+
+	/*
 	 * Registers that may be useful after this macro is invoked:
 	 *
 	 * x21 - aborted SP
@@ -164,8 +175,44 @@
 	.endm
 
 	.macro	get_thread_info, rd
-	mov	\rd, sp
-	and	\rd, \rd, #~(THREAD_SIZE - 1)	// top of stack
+	mrs	\rd, sp_el0
+	.endm
+
+	.macro	irq_stack_entry
+	mov	x19, sp			// preserve the original sp
+
+	/*
+	 * Compare sp with the current thread_info, if the top
+	 * ~(THREAD_SIZE - 1) bits match, we are on a task stack, and
+	 * should switch to the irq stack.
+	 */
+	and	x25, x19, #~(THREAD_SIZE - 1)
+	cmp	x25, tsk
+	b.ne	9998f
+
+	this_cpu_ptr irq_stack, x25, x26
+	mov	x26, #IRQ_STACK_START_SP
+	add	x26, x25, x26
+
+	/* switch to the irq stack */
+	mov	sp, x26
+
+	/*
+	 * Add a dummy stack frame, this non-standard format is fixed up
+	 * by unwind_frame()
+	 */
+	stp     x29, x19, [sp, #-16]!
+	mov	x29, sp
+
+9998:
+	.endm
+
+	/*
+	 * x19 should be preserved between irq_stack_entry and
+	 * irq_stack_exit.
+	 */
+	.macro	irq_stack_exit
+	mov	sp, x19
 	.endm
 
 /*
@@ -183,10 +230,11 @@
  * Interrupt handling.
  */
 	.macro	irq_handler
-	adrp	x1, handle_arch_irq
-	ldr	x1, [x1, #:lo12:handle_arch_irq]
+	ldr_l	x1, handle_arch_irq
 	mov	x0, sp
+	irq_stack_entry
 	blr	x1
+	irq_stack_exit
 	.endm
 
 	.text
@@ -358,10 +406,10 @@
 	bl	trace_hardirqs_off
 #endif
 
+	get_thread_info tsk
 	irq_handler
 
 #ifdef CONFIG_PREEMPT
-	get_thread_info tsk
 	ldr	w24, [tsk, #TI_PREEMPT]		// get preempt count
 	cbnz	w24, 1f				// preempt count != 0
 	ldr	x0, [tsk, #TI_FLAGS]		// get flags
@@ -599,6 +647,8 @@
 	ldp	x29, x9, [x8], #16
 	ldr	lr, [x8]
 	mov	sp, x9
+	and	x9, x9, #~(THREAD_SIZE - 1)
+	msr	sp_el0, x9
 	ret
 ENDPROC(cpu_switch_to)
 
@@ -626,14 +676,14 @@
 work_pending:
 	tbnz	x1, #TIF_NEED_RESCHED, work_resched
 	/* TIF_SIGPENDING, TIF_NOTIFY_RESUME or TIF_FOREIGN_FPSTATE case */
-	ldr	x2, [sp, #S_PSTATE]
 	mov	x0, sp				// 'regs'
-	tst	x2, #PSR_MODE_MASK		// user mode regs?
-	b.ne	no_work_pending			// returning to kernel
 	enable_irq				// enable interrupts for do_notify_resume()
 	bl	do_notify_resume
 	b	ret_to_user
 work_resched:
+#ifdef CONFIG_TRACE_IRQFLAGS
+	bl	trace_hardirqs_off		// the IRQs are off here, inform the tracing code
+#endif
 	bl	schedule
 
 /*
@@ -645,7 +695,6 @@
 	and	x2, x1, #_TIF_WORK_MASK
 	cbnz	x2, work_pending
 	enable_step_tsk x1, x2
-no_work_pending:
 	kernel_exit 0
 ENDPROC(ret_to_user)
 
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 4c46c54..acc1afd 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -289,7 +289,7 @@
 	.notifier_call = fpsimd_cpu_pm_notifier,
 };
 
-static void fpsimd_pm_init(void)
+static void __init fpsimd_pm_init(void)
 {
 	cpu_pm_register_notifier(&fpsimd_cpu_pm_notifier_block);
 }
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index c851be7..ebecf9a 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -29,12 +29,11 @@
 
 	/*
 	 * Note:
-	 * Due to modules and __init, code can disappear and change,
-	 * we need to protect against faulting as well as code changing.
-	 * We do this by aarch64_insn_*() which use the probe_kernel_*().
-	 *
-	 * No lock is held here because all the modifications are run
-	 * through stop_machine().
+	 * We are paranoid about modifying text, as if a bug were to happen, it
+	 * could cause us to read or write to someplace that could cause harm.
+	 * Carefully read and modify the code with aarch64_insn_*() which uses
+	 * probe_kernel_*(), and make sure what we read is what we expected it
+	 * to be before modifying it.
 	 */
 	if (validate) {
 		if (aarch64_insn_read((void *)pc, &replaced))
@@ -93,6 +92,11 @@
 	return ftrace_modify_code(pc, old, new, true);
 }
 
+void arch_ftrace_update_code(int command)
+{
+	ftrace_modify_all_code(command);
+}
+
 int __init ftrace_dyn_arch_init(void)
 {
 	return 0;
@@ -125,23 +129,20 @@
 	 * on other archs. It's unlikely on AArch64.
 	 */
 	old = *parent;
-	*parent = return_hooker;
 
 	trace.func = self_addr;
 	trace.depth = current->curr_ret_stack + 1;
 
 	/* Only trace if the calling function expects to */
-	if (!ftrace_graph_entry(&trace)) {
-		*parent = old;
+	if (!ftrace_graph_entry(&trace))
 		return;
-	}
 
 	err = ftrace_push_return_trace(old, self_addr, &trace.depth,
 				       frame_pointer);
-	if (err == -EBUSY) {
-		*parent = old;
+	if (err == -EBUSY)
 		return;
-	}
+	else
+		*parent = return_hooker;
 }
 
 #ifdef CONFIG_DYNAMIC_FTRACE
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 23cfc08..ffe9c2b6 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -415,15 +415,17 @@
  */
 	.set	initial_sp, init_thread_union + THREAD_START_SP
 __mmap_switched:
-	adr_l	x6, __bss_start
-	adr_l	x7, __bss_stop
+	// Clear BSS
+	adr_l	x0, __bss_start
+	mov	x1, xzr
+	adr_l	x2, __bss_stop
+	sub	x2, x2, x0
+	bl	__pi_memset
 
-1:	cmp	x6, x7
-	b.hs	2f
-	str	xzr, [x6], #8			// Clear BSS
-	b	1b
-2:
 	adr_l	sp, initial_sp, x4
+	mov	x4, sp
+	and	x4, x4, #~(THREAD_SIZE - 1)
+	msr	sp_el0, x4			// Save thread_info
 	str_l	x21, __fdt_pointer, x5		// Save FDT pointer
 	str_l	x24, memstart_addr, x6		// Save PHYS_OFFSET
 	mov	x29, #0
@@ -606,6 +608,8 @@
 ENTRY(__secondary_switched)
 	ldr	x0, [x21]			// get secondary_data.stack
 	mov	sp, x0
+	and	x0, x0, #~(THREAD_SIZE - 1)
+	msr	sp_el0, x0			// save thread_info
 	mov	x29, #0
 	b	secondary_start_kernel
 ENDPROC(__secondary_switched)
diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c
index 9f17ec0..2386b26 100644
--- a/arch/arm64/kernel/irq.c
+++ b/arch/arm64/kernel/irq.c
@@ -30,6 +30,9 @@
 
 unsigned long irq_err_count;
 
+/* irq stack only needs to be 16 byte aligned - not IRQ_STACK_SIZE aligned. */
+DEFINE_PER_CPU(unsigned long [IRQ_STACK_SIZE/sizeof(long)], irq_stack) __aligned(16);
+
 int arch_show_interrupts(struct seq_file *p, int prec)
 {
 	show_ipi_list(p, prec);
diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c
index f4bc779e..93e9702 100644
--- a/arch/arm64/kernel/module.c
+++ b/arch/arm64/kernel/module.c
@@ -30,9 +30,6 @@
 #include <asm/insn.h>
 #include <asm/sections.h>
 
-#define	AARCH64_INSN_IMM_MOVNZ		AARCH64_INSN_IMM_MAX
-#define	AARCH64_INSN_IMM_MOVK		AARCH64_INSN_IMM_16
-
 void *module_alloc(unsigned long size)
 {
 	void *p;
@@ -75,15 +72,18 @@
 
 static int reloc_data(enum aarch64_reloc_op op, void *place, u64 val, int len)
 {
-	u64 imm_mask = (1 << len) - 1;
 	s64 sval = do_reloc(op, place, val);
 
 	switch (len) {
 	case 16:
 		*(s16 *)place = sval;
+		if (sval < S16_MIN || sval > U16_MAX)
+			return -ERANGE;
 		break;
 	case 32:
 		*(s32 *)place = sval;
+		if (sval < S32_MIN || sval > U32_MAX)
+			return -ERANGE;
 		break;
 	case 64:
 		*(s64 *)place = sval;
@@ -92,34 +92,23 @@
 		pr_err("Invalid length (%d) for data relocation\n", len);
 		return 0;
 	}
-
-	/*
-	 * Extract the upper value bits (including the sign bit) and
-	 * shift them to bit 0.
-	 */
-	sval = (s64)(sval & ~(imm_mask >> 1)) >> (len - 1);
-
-	/*
-	 * Overflow has occurred if the value is not representable in
-	 * len bits (i.e the bottom len bits are not sign-extended and
-	 * the top bits are not all zero).
-	 */
-	if ((u64)(sval + 1) > 2)
-		return -ERANGE;
-
 	return 0;
 }
 
+enum aarch64_insn_movw_imm_type {
+	AARCH64_INSN_IMM_MOVNZ,
+	AARCH64_INSN_IMM_MOVKZ,
+};
+
 static int reloc_insn_movw(enum aarch64_reloc_op op, void *place, u64 val,
-			   int lsb, enum aarch64_insn_imm_type imm_type)
+			   int lsb, enum aarch64_insn_movw_imm_type imm_type)
 {
-	u64 imm, limit = 0;
+	u64 imm;
 	s64 sval;
 	u32 insn = le32_to_cpu(*(u32 *)place);
 
 	sval = do_reloc(op, place, val);
-	sval >>= lsb;
-	imm = sval & 0xffff;
+	imm = sval >> lsb;
 
 	if (imm_type == AARCH64_INSN_IMM_MOVNZ) {
 		/*
@@ -128,7 +117,7 @@
 		 * immediate is less than zero.
 		 */
 		insn &= ~(3 << 29);
-		if ((s64)imm >= 0) {
+		if (sval >= 0) {
 			/* >=0: Set the instruction to MOVZ (opcode 10b). */
 			insn |= 2 << 29;
 		} else {
@@ -140,29 +129,13 @@
 			 */
 			imm = ~imm;
 		}
-		imm_type = AARCH64_INSN_IMM_MOVK;
 	}
 
 	/* Update the instruction with the new encoding. */
-	insn = aarch64_insn_encode_immediate(imm_type, insn, imm);
+	insn = aarch64_insn_encode_immediate(AARCH64_INSN_IMM_16, insn, imm);
 	*(u32 *)place = cpu_to_le32(insn);
 
-	/* Shift out the immediate field. */
-	sval >>= 16;
-
-	/*
-	 * For unsigned immediates, the overflow check is straightforward.
-	 * For signed immediates, the sign bit is actually the bit past the
-	 * most significant bit of the field.
-	 * The AARCH64_INSN_IMM_16 immediate type is unsigned.
-	 */
-	if (imm_type != AARCH64_INSN_IMM_16) {
-		sval++;
-		limit++;
-	}
-
-	/* Check the upper bits depending on the sign of the immediate. */
-	if ((u64)sval > limit)
+	if (imm > U16_MAX)
 		return -ERANGE;
 
 	return 0;
@@ -267,25 +240,25 @@
 			overflow_check = false;
 		case R_AARCH64_MOVW_UABS_G0:
 			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 0,
-					      AARCH64_INSN_IMM_16);
+					      AARCH64_INSN_IMM_MOVKZ);
 			break;
 		case R_AARCH64_MOVW_UABS_G1_NC:
 			overflow_check = false;
 		case R_AARCH64_MOVW_UABS_G1:
 			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 16,
-					      AARCH64_INSN_IMM_16);
+					      AARCH64_INSN_IMM_MOVKZ);
 			break;
 		case R_AARCH64_MOVW_UABS_G2_NC:
 			overflow_check = false;
 		case R_AARCH64_MOVW_UABS_G2:
 			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 32,
-					      AARCH64_INSN_IMM_16);
+					      AARCH64_INSN_IMM_MOVKZ);
 			break;
 		case R_AARCH64_MOVW_UABS_G3:
 			/* We're using the top bits so we can't overflow. */
 			overflow_check = false;
 			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 48,
-					      AARCH64_INSN_IMM_16);
+					      AARCH64_INSN_IMM_MOVKZ);
 			break;
 		case R_AARCH64_MOVW_SABS_G0:
 			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 0,
@@ -302,7 +275,7 @@
 		case R_AARCH64_MOVW_PREL_G0_NC:
 			overflow_check = false;
 			ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 0,
-					      AARCH64_INSN_IMM_MOVK);
+					      AARCH64_INSN_IMM_MOVKZ);
 			break;
 		case R_AARCH64_MOVW_PREL_G0:
 			ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 0,
@@ -311,7 +284,7 @@
 		case R_AARCH64_MOVW_PREL_G1_NC:
 			overflow_check = false;
 			ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 16,
-					      AARCH64_INSN_IMM_MOVK);
+					      AARCH64_INSN_IMM_MOVKZ);
 			break;
 		case R_AARCH64_MOVW_PREL_G1:
 			ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 16,
@@ -320,7 +293,7 @@
 		case R_AARCH64_MOVW_PREL_G2_NC:
 			overflow_check = false;
 			ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 32,
-					      AARCH64_INSN_IMM_MOVK);
+					      AARCH64_INSN_IMM_MOVKZ);
 			break;
 		case R_AARCH64_MOVW_PREL_G2:
 			ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 32,
diff --git a/arch/arm64/kernel/paravirt.c b/arch/arm64/kernel/paravirt.c
new file mode 100644
index 0000000..53f371e
--- /dev/null
+++ b/arch/arm64/kernel/paravirt.c
@@ -0,0 +1,25 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Copyright (C) 2013 Citrix Systems
+ *
+ * Author: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
+ */
+
+#include <linux/export.h>
+#include <linux/jump_label.h>
+#include <linux/types.h>
+#include <asm/paravirt.h>
+
+struct static_key paravirt_steal_enabled;
+struct static_key paravirt_steal_rq_enabled;
+
+struct pv_time_ops pv_time_ops;
+EXPORT_SYMBOL_GPL(pv_time_ops);
diff --git a/arch/arm64/kernel/perf_callchain.c b/arch/arm64/kernel/perf_callchain.c
index 3aa7483..ff46654 100644
--- a/arch/arm64/kernel/perf_callchain.c
+++ b/arch/arm64/kernel/perf_callchain.c
@@ -164,8 +164,11 @@
 	frame.fp = regs->regs[29];
 	frame.sp = regs->sp;
 	frame.pc = regs->pc;
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	frame.graph = current->curr_ret_stack;
+#endif
 
-	walk_stackframe(&frame, callchain_trace, entry);
+	walk_stackframe(current, &frame, callchain_trace, entry);
 }
 
 unsigned long perf_instruction_pointer(struct pt_regs *regs)
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 5b1897e..f7ab14c 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -29,60 +29,74 @@
  * ARMv8 PMUv3 Performance Events handling code.
  * Common event types.
  */
-enum armv8_pmuv3_perf_types {
-	/* Required events. */
-	ARMV8_PMUV3_PERFCTR_PMNC_SW_INCR			= 0x00,
-	ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL			= 0x03,
-	ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS			= 0x04,
-	ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED			= 0x10,
-	ARMV8_PMUV3_PERFCTR_CLOCK_CYCLES			= 0x11,
-	ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED			= 0x12,
 
-	/* At least one of the following is required. */
-	ARMV8_PMUV3_PERFCTR_INSTR_EXECUTED			= 0x08,
-	ARMV8_PMUV3_PERFCTR_OP_SPEC				= 0x1B,
+/* Required events. */
+#define ARMV8_PMUV3_PERFCTR_PMNC_SW_INCR			0x00
+#define ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL			0x03
+#define ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS			0x04
+#define ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED			0x10
+#define ARMV8_PMUV3_PERFCTR_CLOCK_CYCLES			0x11
+#define ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED			0x12
 
-	/* Common architectural events. */
-	ARMV8_PMUV3_PERFCTR_MEM_READ				= 0x06,
-	ARMV8_PMUV3_PERFCTR_MEM_WRITE				= 0x07,
-	ARMV8_PMUV3_PERFCTR_EXC_TAKEN				= 0x09,
-	ARMV8_PMUV3_PERFCTR_EXC_EXECUTED			= 0x0A,
-	ARMV8_PMUV3_PERFCTR_CID_WRITE				= 0x0B,
-	ARMV8_PMUV3_PERFCTR_PC_WRITE				= 0x0C,
-	ARMV8_PMUV3_PERFCTR_PC_IMM_BRANCH			= 0x0D,
-	ARMV8_PMUV3_PERFCTR_PC_PROC_RETURN			= 0x0E,
-	ARMV8_PMUV3_PERFCTR_MEM_UNALIGNED_ACCESS		= 0x0F,
-	ARMV8_PMUV3_PERFCTR_TTBR_WRITE				= 0x1C,
+/* At least one of the following is required. */
+#define ARMV8_PMUV3_PERFCTR_INSTR_EXECUTED			0x08
+#define ARMV8_PMUV3_PERFCTR_OP_SPEC				0x1B
 
-	/* Common microarchitectural events. */
-	ARMV8_PMUV3_PERFCTR_L1_ICACHE_REFILL			= 0x01,
-	ARMV8_PMUV3_PERFCTR_ITLB_REFILL				= 0x02,
-	ARMV8_PMUV3_PERFCTR_DTLB_REFILL				= 0x05,
-	ARMV8_PMUV3_PERFCTR_MEM_ACCESS				= 0x13,
-	ARMV8_PMUV3_PERFCTR_L1_ICACHE_ACCESS			= 0x14,
-	ARMV8_PMUV3_PERFCTR_L1_DCACHE_WB			= 0x15,
-	ARMV8_PMUV3_PERFCTR_L2_CACHE_ACCESS			= 0x16,
-	ARMV8_PMUV3_PERFCTR_L2_CACHE_REFILL			= 0x17,
-	ARMV8_PMUV3_PERFCTR_L2_CACHE_WB				= 0x18,
-	ARMV8_PMUV3_PERFCTR_BUS_ACCESS				= 0x19,
-	ARMV8_PMUV3_PERFCTR_MEM_ERROR				= 0x1A,
-	ARMV8_PMUV3_PERFCTR_BUS_CYCLES				= 0x1D,
-};
+/* Common architectural events. */
+#define ARMV8_PMUV3_PERFCTR_MEM_READ				0x06
+#define ARMV8_PMUV3_PERFCTR_MEM_WRITE				0x07
+#define ARMV8_PMUV3_PERFCTR_EXC_TAKEN				0x09
+#define ARMV8_PMUV3_PERFCTR_EXC_EXECUTED			0x0A
+#define ARMV8_PMUV3_PERFCTR_CID_WRITE				0x0B
+#define ARMV8_PMUV3_PERFCTR_PC_WRITE				0x0C
+#define ARMV8_PMUV3_PERFCTR_PC_IMM_BRANCH			0x0D
+#define ARMV8_PMUV3_PERFCTR_PC_PROC_RETURN			0x0E
+#define ARMV8_PMUV3_PERFCTR_MEM_UNALIGNED_ACCESS		0x0F
+#define ARMV8_PMUV3_PERFCTR_TTBR_WRITE				0x1C
+#define ARMV8_PMUV3_PERFCTR_CHAIN				0x1E
+#define ARMV8_PMUV3_PERFCTR_BR_RETIRED				0x21
+
+/* Common microarchitectural events. */
+#define ARMV8_PMUV3_PERFCTR_L1_ICACHE_REFILL			0x01
+#define ARMV8_PMUV3_PERFCTR_ITLB_REFILL				0x02
+#define ARMV8_PMUV3_PERFCTR_DTLB_REFILL				0x05
+#define ARMV8_PMUV3_PERFCTR_MEM_ACCESS				0x13
+#define ARMV8_PMUV3_PERFCTR_L1_ICACHE_ACCESS			0x14
+#define ARMV8_PMUV3_PERFCTR_L1_DCACHE_WB			0x15
+#define ARMV8_PMUV3_PERFCTR_L2_CACHE_ACCESS			0x16
+#define ARMV8_PMUV3_PERFCTR_L2_CACHE_REFILL			0x17
+#define ARMV8_PMUV3_PERFCTR_L2_CACHE_WB				0x18
+#define ARMV8_PMUV3_PERFCTR_BUS_ACCESS				0x19
+#define ARMV8_PMUV3_PERFCTR_MEM_ERROR				0x1A
+#define ARMV8_PMUV3_PERFCTR_BUS_CYCLES				0x1D
+#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_ALLOCATE			0x1F
+#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_ALLOCATE			0x20
+#define ARMV8_PMUV3_PERFCTR_BR_MIS_PRED_RETIRED			0x22
+#define ARMV8_PMUV3_PERFCTR_STALL_FRONTEND			0x23
+#define ARMV8_PMUV3_PERFCTR_STALL_BACKEND			0x24
+#define ARMV8_PMUV3_PERFCTR_L1D_TLB				0x25
+#define ARMV8_PMUV3_PERFCTR_L1I_TLB				0x26
+#define ARMV8_PMUV3_PERFCTR_L2I_CACHE				0x27
+#define ARMV8_PMUV3_PERFCTR_L2I_CACHE_REFILL			0x28
+#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_ALLOCATE			0x29
+#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_REFILL			0x2A
+#define ARMV8_PMUV3_PERFCTR_L3D_CACHE				0x2B
+#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_WB			0x2C
+#define ARMV8_PMUV3_PERFCTR_L2D_TLB_REFILL			0x2D
+#define ARMV8_PMUV3_PERFCTR_L21_TLB_REFILL			0x2E
+#define ARMV8_PMUV3_PERFCTR_L2D_TLB				0x2F
+#define ARMV8_PMUV3_PERFCTR_L21_TLB				0x30
 
 /* ARMv8 Cortex-A53 specific event types. */
-enum armv8_a53_pmu_perf_types {
-	ARMV8_A53_PERFCTR_PREFETCH_LINEFILL			= 0xC2,
-};
+#define ARMV8_A53_PERFCTR_PREFETCH_LINEFILL			0xC2
 
-/* ARMv8 Cortex-A57 specific event types. */
-enum armv8_a57_perf_types {
-	ARMV8_A57_PERFCTR_L1_DCACHE_ACCESS_LD			= 0x40,
-	ARMV8_A57_PERFCTR_L1_DCACHE_ACCESS_ST			= 0x41,
-	ARMV8_A57_PERFCTR_L1_DCACHE_REFILL_LD			= 0x42,
-	ARMV8_A57_PERFCTR_L1_DCACHE_REFILL_ST			= 0x43,
-	ARMV8_A57_PERFCTR_DTLB_REFILL_LD			= 0x4c,
-	ARMV8_A57_PERFCTR_DTLB_REFILL_ST			= 0x4d,
-};
+/* ARMv8 Cortex-A57 and Cortex-A72 specific event types. */
+#define ARMV8_A57_PERFCTR_L1_DCACHE_ACCESS_LD			0x40
+#define ARMV8_A57_PERFCTR_L1_DCACHE_ACCESS_ST			0x41
+#define ARMV8_A57_PERFCTR_L1_DCACHE_REFILL_LD			0x42
+#define ARMV8_A57_PERFCTR_L1_DCACHE_REFILL_ST			0x43
+#define ARMV8_A57_PERFCTR_DTLB_REFILL_LD			0x4c
+#define ARMV8_A57_PERFCTR_DTLB_REFILL_ST			0x4d
 
 /* PMUv3 HW events mapping. */
 static const unsigned armv8_pmuv3_perf_map[PERF_COUNT_HW_MAX] = {
@@ -106,6 +120,7 @@
 	[PERF_COUNT_HW_BUS_CYCLES]		= ARMV8_PMUV3_PERFCTR_BUS_CYCLES,
 };
 
+/* ARM Cortex-A57 and Cortex-A72 events mapping. */
 static const unsigned armv8_a57_perf_map[PERF_COUNT_HW_MAX] = {
 	PERF_MAP_ALL_UNSUPPORTED,
 	[PERF_COUNT_HW_CPU_CYCLES]		= ARMV8_PMUV3_PERFCTR_CLOCK_CYCLES,
@@ -178,6 +193,137 @@
 	[C(BPU)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
 };
 
+#define ARMV8_EVENT_ATTR_RESOLVE(m) #m
+#define ARMV8_EVENT_ATTR(name, config) \
+	PMU_EVENT_ATTR_STRING(name, armv8_event_attr_##name, \
+			      "event=" ARMV8_EVENT_ATTR_RESOLVE(config))
+
+ARMV8_EVENT_ATTR(sw_incr, ARMV8_PMUV3_PERFCTR_PMNC_SW_INCR);
+ARMV8_EVENT_ATTR(l1i_cache_refill, ARMV8_PMUV3_PERFCTR_L1_ICACHE_REFILL);
+ARMV8_EVENT_ATTR(l1i_tlb_refill, ARMV8_PMUV3_PERFCTR_ITLB_REFILL);
+ARMV8_EVENT_ATTR(l1d_cache_refill, ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL);
+ARMV8_EVENT_ATTR(l1d_cache, ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS);
+ARMV8_EVENT_ATTR(l1d_tlb_refill, ARMV8_PMUV3_PERFCTR_DTLB_REFILL);
+ARMV8_EVENT_ATTR(ld_retired, ARMV8_PMUV3_PERFCTR_MEM_READ);
+ARMV8_EVENT_ATTR(st_retired, ARMV8_PMUV3_PERFCTR_MEM_WRITE);
+ARMV8_EVENT_ATTR(inst_retired, ARMV8_PMUV3_PERFCTR_INSTR_EXECUTED);
+ARMV8_EVENT_ATTR(exc_taken, ARMV8_PMUV3_PERFCTR_EXC_TAKEN);
+ARMV8_EVENT_ATTR(exc_return, ARMV8_PMUV3_PERFCTR_EXC_EXECUTED);
+ARMV8_EVENT_ATTR(cid_write_retired, ARMV8_PMUV3_PERFCTR_CID_WRITE);
+ARMV8_EVENT_ATTR(pc_write_retired, ARMV8_PMUV3_PERFCTR_PC_WRITE);
+ARMV8_EVENT_ATTR(br_immed_retired, ARMV8_PMUV3_PERFCTR_PC_IMM_BRANCH);
+ARMV8_EVENT_ATTR(br_return_retired, ARMV8_PMUV3_PERFCTR_PC_PROC_RETURN);
+ARMV8_EVENT_ATTR(unaligned_ldst_retired, ARMV8_PMUV3_PERFCTR_MEM_UNALIGNED_ACCESS);
+ARMV8_EVENT_ATTR(br_mis_pred, ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED);
+ARMV8_EVENT_ATTR(cpu_cycles, ARMV8_PMUV3_PERFCTR_CLOCK_CYCLES);
+ARMV8_EVENT_ATTR(br_pred, ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED);
+ARMV8_EVENT_ATTR(mem_access, ARMV8_PMUV3_PERFCTR_MEM_ACCESS);
+ARMV8_EVENT_ATTR(l1i_cache, ARMV8_PMUV3_PERFCTR_L1_ICACHE_ACCESS);
+ARMV8_EVENT_ATTR(l1d_cache_wb, ARMV8_PMUV3_PERFCTR_L1_DCACHE_WB);
+ARMV8_EVENT_ATTR(l2d_cache, ARMV8_PMUV3_PERFCTR_L2_CACHE_ACCESS);
+ARMV8_EVENT_ATTR(l2d_cache_refill, ARMV8_PMUV3_PERFCTR_L2_CACHE_REFILL);
+ARMV8_EVENT_ATTR(l2d_cache_wb, ARMV8_PMUV3_PERFCTR_L2_CACHE_WB);
+ARMV8_EVENT_ATTR(bus_access, ARMV8_PMUV3_PERFCTR_BUS_ACCESS);
+ARMV8_EVENT_ATTR(memory_error, ARMV8_PMUV3_PERFCTR_MEM_ERROR);
+ARMV8_EVENT_ATTR(inst_spec, ARMV8_PMUV3_PERFCTR_OP_SPEC);
+ARMV8_EVENT_ATTR(ttbr_write_retired, ARMV8_PMUV3_PERFCTR_TTBR_WRITE);
+ARMV8_EVENT_ATTR(bus_cycles, ARMV8_PMUV3_PERFCTR_BUS_CYCLES);
+ARMV8_EVENT_ATTR(chain, ARMV8_PMUV3_PERFCTR_CHAIN);
+ARMV8_EVENT_ATTR(l1d_cache_allocate, ARMV8_PMUV3_PERFCTR_L1D_CACHE_ALLOCATE);
+ARMV8_EVENT_ATTR(l2d_cache_allocate, ARMV8_PMUV3_PERFCTR_L2D_CACHE_ALLOCATE);
+ARMV8_EVENT_ATTR(br_retired, ARMV8_PMUV3_PERFCTR_BR_RETIRED);
+ARMV8_EVENT_ATTR(br_mis_pred_retired, ARMV8_PMUV3_PERFCTR_BR_MIS_PRED_RETIRED);
+ARMV8_EVENT_ATTR(stall_frontend, ARMV8_PMUV3_PERFCTR_STALL_FRONTEND);
+ARMV8_EVENT_ATTR(stall_backend, ARMV8_PMUV3_PERFCTR_STALL_BACKEND);
+ARMV8_EVENT_ATTR(l1d_tlb, ARMV8_PMUV3_PERFCTR_L1D_TLB);
+ARMV8_EVENT_ATTR(l1i_tlb, ARMV8_PMUV3_PERFCTR_L1I_TLB);
+ARMV8_EVENT_ATTR(l2i_cache, ARMV8_PMUV3_PERFCTR_L2I_CACHE);
+ARMV8_EVENT_ATTR(l2i_cache_refill, ARMV8_PMUV3_PERFCTR_L2I_CACHE_REFILL);
+ARMV8_EVENT_ATTR(l3d_cache_allocate, ARMV8_PMUV3_PERFCTR_L3D_CACHE_ALLOCATE);
+ARMV8_EVENT_ATTR(l3d_cache_refill, ARMV8_PMUV3_PERFCTR_L3D_CACHE_REFILL);
+ARMV8_EVENT_ATTR(l3d_cache, ARMV8_PMUV3_PERFCTR_L3D_CACHE);
+ARMV8_EVENT_ATTR(l3d_cache_wb, ARMV8_PMUV3_PERFCTR_L3D_CACHE_WB);
+ARMV8_EVENT_ATTR(l2d_tlb_refill, ARMV8_PMUV3_PERFCTR_L2D_TLB_REFILL);
+ARMV8_EVENT_ATTR(l21_tlb_refill, ARMV8_PMUV3_PERFCTR_L21_TLB_REFILL);
+ARMV8_EVENT_ATTR(l2d_tlb, ARMV8_PMUV3_PERFCTR_L2D_TLB);
+ARMV8_EVENT_ATTR(l21_tlb, ARMV8_PMUV3_PERFCTR_L21_TLB);
+
+static struct attribute *armv8_pmuv3_event_attrs[] = {
+	&armv8_event_attr_sw_incr.attr.attr,
+	&armv8_event_attr_l1i_cache_refill.attr.attr,
+	&armv8_event_attr_l1i_tlb_refill.attr.attr,
+	&armv8_event_attr_l1d_cache_refill.attr.attr,
+	&armv8_event_attr_l1d_cache.attr.attr,
+	&armv8_event_attr_l1d_tlb_refill.attr.attr,
+	&armv8_event_attr_ld_retired.attr.attr,
+	&armv8_event_attr_st_retired.attr.attr,
+	&armv8_event_attr_inst_retired.attr.attr,
+	&armv8_event_attr_exc_taken.attr.attr,
+	&armv8_event_attr_exc_return.attr.attr,
+	&armv8_event_attr_cid_write_retired.attr.attr,
+	&armv8_event_attr_pc_write_retired.attr.attr,
+	&armv8_event_attr_br_immed_retired.attr.attr,
+	&armv8_event_attr_br_return_retired.attr.attr,
+	&armv8_event_attr_unaligned_ldst_retired.attr.attr,
+	&armv8_event_attr_br_mis_pred.attr.attr,
+	&armv8_event_attr_cpu_cycles.attr.attr,
+	&armv8_event_attr_br_pred.attr.attr,
+	&armv8_event_attr_mem_access.attr.attr,
+	&armv8_event_attr_l1i_cache.attr.attr,
+	&armv8_event_attr_l1d_cache_wb.attr.attr,
+	&armv8_event_attr_l2d_cache.attr.attr,
+	&armv8_event_attr_l2d_cache_refill.attr.attr,
+	&armv8_event_attr_l2d_cache_wb.attr.attr,
+	&armv8_event_attr_bus_access.attr.attr,
+	&armv8_event_attr_memory_error.attr.attr,
+	&armv8_event_attr_inst_spec.attr.attr,
+	&armv8_event_attr_ttbr_write_retired.attr.attr,
+	&armv8_event_attr_bus_cycles.attr.attr,
+	&armv8_event_attr_chain.attr.attr,
+	&armv8_event_attr_l1d_cache_allocate.attr.attr,
+	&armv8_event_attr_l2d_cache_allocate.attr.attr,
+	&armv8_event_attr_br_retired.attr.attr,
+	&armv8_event_attr_br_mis_pred_retired.attr.attr,
+	&armv8_event_attr_stall_frontend.attr.attr,
+	&armv8_event_attr_stall_backend.attr.attr,
+	&armv8_event_attr_l1d_tlb.attr.attr,
+	&armv8_event_attr_l1i_tlb.attr.attr,
+	&armv8_event_attr_l2i_cache.attr.attr,
+	&armv8_event_attr_l2i_cache_refill.attr.attr,
+	&armv8_event_attr_l3d_cache_allocate.attr.attr,
+	&armv8_event_attr_l3d_cache_refill.attr.attr,
+	&armv8_event_attr_l3d_cache.attr.attr,
+	&armv8_event_attr_l3d_cache_wb.attr.attr,
+	&armv8_event_attr_l2d_tlb_refill.attr.attr,
+	&armv8_event_attr_l21_tlb_refill.attr.attr,
+	&armv8_event_attr_l2d_tlb.attr.attr,
+	&armv8_event_attr_l21_tlb.attr.attr,
+	NULL,
+};
+
+static struct attribute_group armv8_pmuv3_events_attr_group = {
+	.name = "events",
+	.attrs = armv8_pmuv3_event_attrs,
+};
+
+PMU_FORMAT_ATTR(event, "config:0-9");
+
+static struct attribute *armv8_pmuv3_format_attrs[] = {
+	&format_attr_event.attr,
+	NULL,
+};
+
+static struct attribute_group armv8_pmuv3_format_attr_group = {
+	.name = "format",
+	.attrs = armv8_pmuv3_format_attrs,
+};
+
+static const struct attribute_group *armv8_pmuv3_attr_groups[] = {
+	&armv8_pmuv3_events_attr_group,
+	&armv8_pmuv3_format_attr_group,
+	NULL,
+};
+
 
 /*
  * Perf Events' indices
@@ -574,9 +720,6 @@
 
 	/* Initialize & Reset PMNC: C and P bits. */
 	armv8pmu_pmcr_write(ARMV8_PMCR_P | ARMV8_PMCR_C);
-
-	/* Disable access from userspace. */
-	asm volatile("msr pmuserenr_el0, %0" :: "r" (0));
 }
 
 static int armv8_pmuv3_map_event(struct perf_event *event)
@@ -646,6 +789,7 @@
 	armv8_pmu_init(cpu_pmu);
 	cpu_pmu->name			= "armv8_cortex_a53";
 	cpu_pmu->map_event		= armv8_a53_map_event;
+	cpu_pmu->pmu.attr_groups	= armv8_pmuv3_attr_groups;
 	return armv8pmu_probe_num_events(cpu_pmu);
 }
 
@@ -654,6 +798,16 @@
 	armv8_pmu_init(cpu_pmu);
 	cpu_pmu->name			= "armv8_cortex_a57";
 	cpu_pmu->map_event		= armv8_a57_map_event;
+	cpu_pmu->pmu.attr_groups	= armv8_pmuv3_attr_groups;
+	return armv8pmu_probe_num_events(cpu_pmu);
+}
+
+static int armv8_a72_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	armv8_pmu_init(cpu_pmu);
+	cpu_pmu->name			= "armv8_cortex_a72";
+	cpu_pmu->map_event		= armv8_a57_map_event;
+	cpu_pmu->pmu.attr_groups	= armv8_pmuv3_attr_groups;
 	return armv8pmu_probe_num_events(cpu_pmu);
 }
 
@@ -661,6 +815,7 @@
 	{.compatible = "arm,armv8-pmuv3",	.data = armv8_pmuv3_init},
 	{.compatible = "arm,cortex-a53-pmu",	.data = armv8_a53_pmu_init},
 	{.compatible = "arm,cortex-a57-pmu",	.data = armv8_a57_pmu_init},
+	{.compatible = "arm,cortex-a72-pmu",	.data = armv8_a72_pmu_init},
 	{},
 };
 
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index f75b540..88d742b 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -344,11 +344,14 @@
 	frame.fp = thread_saved_fp(p);
 	frame.sp = thread_saved_sp(p);
 	frame.pc = thread_saved_pc(p);
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	frame.graph = p->curr_ret_stack;
+#endif
 	stack_page = (unsigned long)task_stack_page(p);
 	do {
 		if (frame.sp < stack_page ||
 		    frame.sp >= stack_page + THREAD_SIZE ||
-		    unwind_frame(&frame))
+		    unwind_frame(p, &frame))
 			return 0;
 		if (!in_sched_functions(frame.pc))
 			return frame.pc;
diff --git a/arch/arm64/kernel/psci-call.S b/arch/arm64/kernel/psci-call.S
deleted file mode 100644
index cf83e61..0000000
--- a/arch/arm64/kernel/psci-call.S
+++ /dev/null
@@ -1,28 +0,0 @@
-/*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * Copyright (C) 2015 ARM Limited
- *
- * Author: Will Deacon <will.deacon@arm.com>
- */
-
-#include <linux/linkage.h>
-
-/* int __invoke_psci_fn_hvc(u64 function_id, u64 arg0, u64 arg1, u64 arg2) */
-ENTRY(__invoke_psci_fn_hvc)
-	hvc	#0
-	ret
-ENDPROC(__invoke_psci_fn_hvc)
-
-/* int __invoke_psci_fn_smc(u64 function_id, u64 arg0, u64 arg1, u64 arg2) */
-ENTRY(__invoke_psci_fn_smc)
-	smc	#0
-	ret
-ENDPROC(__invoke_psci_fn_smc)
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 1971f49..ff7f132 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -58,6 +58,12 @@
  */
 void ptrace_disable(struct task_struct *child)
 {
+	/*
+	 * This would be better off in core code, but PTRACE_DETACH has
+	 * grown its fair share of arch-specific worts and changing it
+	 * is likely to cause regressions on obscure architectures.
+	 */
+	user_disable_single_step(child);
 }
 
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
diff --git a/arch/arm64/kernel/return_address.c b/arch/arm64/kernel/return_address.c
index 6c4fd28..1718706 100644
--- a/arch/arm64/kernel/return_address.c
+++ b/arch/arm64/kernel/return_address.c
@@ -43,8 +43,11 @@
 	frame.fp = (unsigned long)__builtin_frame_address(0);
 	frame.sp = current_stack_pointer;
 	frame.pc = (unsigned long)return_address; /* dummy */
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	frame.graph = current->curr_ret_stack;
+#endif
 
-	walk_stackframe(&frame, save_return_addr, &data);
+	walk_stackframe(current, &frame, save_return_addr, &data);
 
 	if (!data.level)
 		return data.addr;
diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S
index f586f7c..e33fe33 100644
--- a/arch/arm64/kernel/sleep.S
+++ b/arch/arm64/kernel/sleep.S
@@ -173,6 +173,9 @@
 	/* load physical address of identity map page table in x1 */
 	adrp	x1, idmap_pg_dir
 	mov	sp, x2
+	/* save thread_info */
+	and	x2, x2, #~(THREAD_SIZE - 1)
+	msr	sp_el0, x2
 	/*
 	 * cpu_do_resume expects x0 to contain context physical address
 	 * pointer and x1 to contain physical address of 1:1 page tables
diff --git a/arch/arm64/kernel/smccc-call.S b/arch/arm64/kernel/smccc-call.S
new file mode 100644
index 0000000..ae0496f
--- /dev/null
+++ b/arch/arm64/kernel/smccc-call.S
@@ -0,0 +1,43 @@
+/*
+ * Copyright (c) 2015, Linaro Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License Version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+#include <linux/linkage.h>
+#include <asm/asm-offsets.h>
+
+	.macro SMCCC instr
+	.cfi_startproc
+	\instr	#0
+	ldr	x4, [sp]
+	stp	x0, x1, [x4, #ARM_SMCCC_RES_X0_OFFS]
+	stp	x2, x3, [x4, #ARM_SMCCC_RES_X2_OFFS]
+	ret
+	.cfi_endproc
+	.endm
+
+/*
+ * void arm_smccc_smc(unsigned long a0, unsigned long a1, unsigned long a2,
+ *		  unsigned long a3, unsigned long a4, unsigned long a5,
+ *		  unsigned long a6, unsigned long a7, struct arm_smccc_res *res)
+ */
+ENTRY(arm_smccc_smc)
+	SMCCC	smc
+ENDPROC(arm_smccc_smc)
+
+/*
+ * void arm_smccc_hvc(unsigned long a0, unsigned long a1, unsigned long a2,
+ *		  unsigned long a3, unsigned long a4, unsigned long a5,
+ *		  unsigned long a6, unsigned long a7, struct arm_smccc_res *res)
+ */
+ENTRY(arm_smccc_hvc)
+	SMCCC	hvc
+ENDPROC(arm_smccc_hvc)
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index ccb6078..4fad978 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -17,9 +17,11 @@
  */
 #include <linux/kernel.h>
 #include <linux/export.h>
+#include <linux/ftrace.h>
 #include <linux/sched.h>
 #include <linux/stacktrace.h>
 
+#include <asm/irq.h>
 #include <asm/stacktrace.h>
 
 /*
@@ -35,25 +37,83 @@
  *	ldp	x29, x30, [sp]
  *	add	sp, sp, #0x10
  */
-int notrace unwind_frame(struct stackframe *frame)
+int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame)
 {
 	unsigned long high, low;
 	unsigned long fp = frame->fp;
+	unsigned long irq_stack_ptr;
+
+	/*
+	 * Use raw_smp_processor_id() to avoid false-positives from
+	 * CONFIG_DEBUG_PREEMPT. get_wchan() calls unwind_frame() on sleeping
+	 * task stacks, we can be pre-empted in this case, so
+	 * {raw_,}smp_processor_id() may give us the wrong value. Sleeping
+	 * tasks can't ever be on an interrupt stack, so regardless of cpu,
+	 * the checks will always fail.
+	 */
+	irq_stack_ptr = IRQ_STACK_PTR(raw_smp_processor_id());
 
 	low  = frame->sp;
-	high = ALIGN(low, THREAD_SIZE);
+	/* irq stacks are not THREAD_SIZE aligned */
+	if (on_irq_stack(frame->sp, raw_smp_processor_id()))
+		high = irq_stack_ptr;
+	else
+		high = ALIGN(low, THREAD_SIZE) - 0x20;
 
-	if (fp < low || fp > high - 0x18 || fp & 0xf)
+	if (fp < low || fp > high || fp & 0xf)
 		return -EINVAL;
 
 	frame->sp = fp + 0x10;
 	frame->fp = *(unsigned long *)(fp);
 	frame->pc = *(unsigned long *)(fp + 8);
 
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	if (tsk && tsk->ret_stack &&
+			(frame->pc == (unsigned long)return_to_handler)) {
+		/*
+		 * This is a case where function graph tracer has
+		 * modified a return address (LR) in a stack frame
+		 * to hook a function return.
+		 * So replace it to an original value.
+		 */
+		frame->pc = tsk->ret_stack[frame->graph--].ret;
+	}
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+	/*
+	 * Check whether we are going to walk through from interrupt stack
+	 * to task stack.
+	 * If we reach the end of the stack - and its an interrupt stack,
+	 * unpack the dummy frame to find the original elr.
+	 *
+	 * Check the frame->fp we read from the bottom of the irq_stack,
+	 * and the original task stack pointer are both in current->stack.
+	 */
+	if (frame->sp == irq_stack_ptr) {
+		struct pt_regs *irq_args;
+		unsigned long orig_sp = IRQ_STACK_TO_TASK_STACK(irq_stack_ptr);
+
+		if (object_is_on_stack((void *)orig_sp) &&
+		   object_is_on_stack((void *)frame->fp)) {
+			frame->sp = orig_sp;
+
+			/* orig_sp is the saved pt_regs, find the elr */
+			irq_args = (struct pt_regs *)orig_sp;
+			frame->pc = irq_args->pc;
+		} else {
+			/*
+			 * This frame has a non-standard format, and we
+			 * didn't fix it, because the data looked wrong.
+			 * Refuse to output this frame.
+			 */
+			return -EINVAL;
+		}
+	}
+
 	return 0;
 }
 
-void notrace walk_stackframe(struct stackframe *frame,
+void notrace walk_stackframe(struct task_struct *tsk, struct stackframe *frame,
 		     int (*fn)(struct stackframe *, void *), void *data)
 {
 	while (1) {
@@ -61,7 +121,7 @@
 
 		if (fn(frame, data))
 			break;
-		ret = unwind_frame(frame);
+		ret = unwind_frame(tsk, frame);
 		if (ret < 0)
 			break;
 	}
@@ -112,8 +172,11 @@
 		frame.sp = current_stack_pointer;
 		frame.pc = (unsigned long)save_stack_trace_tsk;
 	}
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	frame.graph = tsk->curr_ret_stack;
+#endif
 
-	walk_stackframe(&frame, save_trace, &data);
+	walk_stackframe(tsk, &frame, save_trace, &data);
 	if (trace->nr_entries < trace->max_entries)
 		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
diff --git a/arch/arm64/kernel/time.c b/arch/arm64/kernel/time.c
index 13339b6..5977969 100644
--- a/arch/arm64/kernel/time.c
+++ b/arch/arm64/kernel/time.c
@@ -52,8 +52,11 @@
 	frame.fp = regs->regs[29];
 	frame.sp = regs->sp;
 	frame.pc = regs->pc;
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	frame.graph = -1; /* no task info */
+#endif
 	do {
-		int ret = unwind_frame(&frame);
+		int ret = unwind_frame(NULL, &frame);
 		if (ret < 0)
 			return 0;
 	} while (in_lock_functions(frame.pc));
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index e9b9b53..cbedd72 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -146,17 +146,15 @@
 static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
 {
 	struct stackframe frame;
+	unsigned long irq_stack_ptr = IRQ_STACK_PTR(smp_processor_id());
+	int skip;
 
 	pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk);
 
 	if (!tsk)
 		tsk = current;
 
-	if (regs) {
-		frame.fp = regs->regs[29];
-		frame.sp = regs->sp;
-		frame.pc = regs->pc;
-	} else if (tsk == current) {
+	if (tsk == current) {
 		frame.fp = (unsigned long)__builtin_frame_address(0);
 		frame.sp = current_stack_pointer;
 		frame.pc = (unsigned long)dump_backtrace;
@@ -168,21 +166,49 @@
 		frame.sp = thread_saved_sp(tsk);
 		frame.pc = thread_saved_pc(tsk);
 	}
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	frame.graph = tsk->curr_ret_stack;
+#endif
 
-	pr_emerg("Call trace:\n");
+	skip = !!regs;
+	printk("Call trace:\n");
 	while (1) {
 		unsigned long where = frame.pc;
 		unsigned long stack;
 		int ret;
 
-		dump_backtrace_entry(where);
-		ret = unwind_frame(&frame);
+		/* skip until specified stack frame */
+		if (!skip) {
+			dump_backtrace_entry(where);
+		} else if (frame.fp == regs->regs[29]) {
+			skip = 0;
+			/*
+			 * Mostly, this is the case where this function is
+			 * called in panic/abort. As exception handler's
+			 * stack frame does not contain the corresponding pc
+			 * at which an exception has taken place, use regs->pc
+			 * instead.
+			 */
+			dump_backtrace_entry(regs->pc);
+		}
+		ret = unwind_frame(tsk, &frame);
 		if (ret < 0)
 			break;
 		stack = frame.sp;
-		if (in_exception_text(where))
+		if (in_exception_text(where)) {
+			/*
+			 * If we switched to the irq_stack before calling this
+			 * exception handler, then the pt_regs will be on the
+			 * task stack. The easiest way to tell is if the large
+			 * pt_regs would overlap with the end of the irq_stack.
+			 */
+			if (stack < irq_stack_ptr &&
+			    (stack + sizeof(struct pt_regs)) > irq_stack_ptr)
+				stack = IRQ_STACK_TO_TASK_STACK(irq_stack_ptr);
+
 			dump_mem("", "Exception stack", stack,
 				 stack + sizeof(struct pt_regs), false);
+		}
 	}
 }
 
@@ -456,22 +482,22 @@
 
 void __pte_error(const char *file, int line, unsigned long val)
 {
-	pr_crit("%s:%d: bad pte %016lx.\n", file, line, val);
+	pr_err("%s:%d: bad pte %016lx.\n", file, line, val);
 }
 
 void __pmd_error(const char *file, int line, unsigned long val)
 {
-	pr_crit("%s:%d: bad pmd %016lx.\n", file, line, val);
+	pr_err("%s:%d: bad pmd %016lx.\n", file, line, val);
 }
 
 void __pud_error(const char *file, int line, unsigned long val)
 {
-	pr_crit("%s:%d: bad pud %016lx.\n", file, line, val);
+	pr_err("%s:%d: bad pud %016lx.\n", file, line, val);
 }
 
 void __pgd_error(const char *file, int line, unsigned long val)
 {
-	pr_crit("%s:%d: bad pgd %016lx.\n", file, line, val);
+	pr_err("%s:%d: bad pgd %016lx.\n", file, line, val);
 }
 
 /* GENERIC_BUG traps */
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 71426a78..e3928f57 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -113,7 +113,6 @@
 		*(.got)			/* Global offset table		*/
 	}
 
-	ALIGN_DEBUG_RO
 	RO_DATA(PAGE_SIZE)
 	EXCEPTION_TABLE(8)
 	NOTES
@@ -128,7 +127,6 @@
 		ARM_EXIT_KEEP(EXIT_TEXT)
 	}
 
-	ALIGN_DEBUG_RO_MIN(16)
 	.init.data : {
 		INIT_DATA
 		INIT_SETUP(16)
@@ -143,9 +141,6 @@
 
 	PERCPU_SECTION(L1_CACHE_BYTES)
 
-	. = ALIGN(PAGE_SIZE);
-	__init_end = .;
-
 	. = ALIGN(4);
 	.altinstructions : {
 		__alt_instructions = .;
@@ -157,6 +152,8 @@
 	}
 
 	. = ALIGN(PAGE_SIZE);
+	__init_end = .;
+
 	_data = .;
 	_sdata = .;
 	RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index 1949fe5..caee9ee 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -10,6 +10,7 @@
 ARM=../../../arch/arm/kvm
 
 obj-$(CONFIG_KVM_ARM_HOST) += kvm.o
+obj-$(CONFIG_KVM_ARM_HOST) += hyp/
 
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o $(KVM)/vfio.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(ARM)/arm.o $(ARM)/mmu.o $(ARM)/mmio.o
@@ -22,8 +23,6 @@
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v2.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v2-emul.o
-kvm-$(CONFIG_KVM_ARM_HOST) += vgic-v2-switch.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v3.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v3-emul.o
-kvm-$(CONFIG_KVM_ARM_HOST) += vgic-v3-switch.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/arch_timer.o
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index d250160..fcb7788 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -28,13 +28,21 @@
 #include <asm/cputype.h>
 #include <asm/uaccess.h>
 #include <asm/kvm.h>
-#include <asm/kvm_asm.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_coproc.h>
 
 #include "trace.h"
 
+#define VM_STAT(x) { #x, offsetof(struct kvm, stat.x), KVM_STAT_VM }
+#define VCPU_STAT(x) { #x, offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU }
+
 struct kvm_stats_debugfs_item debugfs_entries[] = {
+	VCPU_STAT(hvc_exit_stat),
+	VCPU_STAT(wfe_exit_stat),
+	VCPU_STAT(wfi_exit_stat),
+	VCPU_STAT(mmio_exit_user),
+	VCPU_STAT(mmio_exit_kernel),
+	VCPU_STAT(exits),
 	{ NULL }
 };
 
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 15f0477..eba89e4 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -23,6 +23,7 @@
 #include <linux/kvm_host.h>
 
 #include <asm/esr.h>
+#include <asm/kvm_asm.h>
 #include <asm/kvm_coproc.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_mmu.h>
@@ -39,6 +40,7 @@
 
 	trace_kvm_hvc_arm64(*vcpu_pc(vcpu), vcpu_get_reg(vcpu, 0),
 			    kvm_vcpu_hvc_get_imm(vcpu));
+	vcpu->stat.hvc_exit_stat++;
 
 	ret = kvm_psci_call(vcpu);
 	if (ret < 0) {
@@ -71,9 +73,11 @@
 {
 	if (kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WFx_ISS_WFE) {
 		trace_kvm_wfx_arm64(*vcpu_pc(vcpu), true);
+		vcpu->stat.wfe_exit_stat++;
 		kvm_vcpu_on_spin(vcpu);
 	} else {
 		trace_kvm_wfx_arm64(*vcpu_pc(vcpu), false);
+		vcpu->stat.wfi_exit_stat++;
 		kvm_vcpu_block(vcpu);
 	}
 
diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S
index 178ba22..3e568dc 100644
--- a/arch/arm64/kvm/hyp-init.S
+++ b/arch/arm64/kvm/hyp-init.S
@@ -94,6 +94,15 @@
 	 */
 	mrs	x5, ID_AA64MMFR0_EL1
 	bfi	x4, x5, #16, #3
+	/*
+	 * Read the VMIDBits bits from ID_AA64MMFR1_EL1 and set the VS bit in
+	 * VTCR_EL2.
+	 */
+	mrs	x5, ID_AA64MMFR1_EL1
+	ubfx	x5, x5, #5, #1
+	lsl	x5, x5, #VTCR_EL2_VS
+	orr	x4, x4, x5
+
 	msr	vtcr_el2, x4
 
 	mrs	x4, mair_el1
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index 86c2898..0ccdcbb 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -17,910 +17,7 @@
 
 #include <linux/linkage.h>
 
-#include <asm/alternative.h>
-#include <asm/asm-offsets.h>
 #include <asm/assembler.h>
-#include <asm/cpufeature.h>
-#include <asm/debug-monitors.h>
-#include <asm/esr.h>
-#include <asm/fpsimdmacros.h>
-#include <asm/kvm.h>
-#include <asm/kvm_arm.h>
-#include <asm/kvm_asm.h>
-#include <asm/kvm_mmu.h>
-#include <asm/memory.h>
-
-#define CPU_GP_REG_OFFSET(x)	(CPU_GP_REGS + x)
-#define CPU_XREG_OFFSET(x)	CPU_GP_REG_OFFSET(CPU_USER_PT_REGS + 8*x)
-#define CPU_SPSR_OFFSET(x)	CPU_GP_REG_OFFSET(CPU_SPSR + 8*x)
-#define CPU_SYSREG_OFFSET(x)	(CPU_SYSREGS + 8*x)
-
-	.text
-	.pushsection	.hyp.text, "ax"
-	.align	PAGE_SHIFT
-
-.macro save_common_regs
-	// x2: base address for cpu context
-	// x3: tmp register
-
-	add	x3, x2, #CPU_XREG_OFFSET(19)
-	stp	x19, x20, [x3]
-	stp	x21, x22, [x3, #16]
-	stp	x23, x24, [x3, #32]
-	stp	x25, x26, [x3, #48]
-	stp	x27, x28, [x3, #64]
-	stp	x29, lr, [x3, #80]
-
-	mrs	x19, sp_el0
-	mrs	x20, elr_el2		// pc before entering el2
-	mrs	x21, spsr_el2		// pstate before entering el2
-
-	stp	x19, x20, [x3, #96]
-	str	x21, [x3, #112]
-
-	mrs	x22, sp_el1
-	mrs	x23, elr_el1
-	mrs	x24, spsr_el1
-
-	str	x22, [x2, #CPU_GP_REG_OFFSET(CPU_SP_EL1)]
-	str	x23, [x2, #CPU_GP_REG_OFFSET(CPU_ELR_EL1)]
-	str	x24, [x2, #CPU_SPSR_OFFSET(KVM_SPSR_EL1)]
-.endm
-
-.macro restore_common_regs
-	// x2: base address for cpu context
-	// x3: tmp register
-
-	ldr	x22, [x2, #CPU_GP_REG_OFFSET(CPU_SP_EL1)]
-	ldr	x23, [x2, #CPU_GP_REG_OFFSET(CPU_ELR_EL1)]
-	ldr	x24, [x2, #CPU_SPSR_OFFSET(KVM_SPSR_EL1)]
-
-	msr	sp_el1, x22
-	msr	elr_el1, x23
-	msr	spsr_el1, x24
-
-	add	x3, x2, #CPU_XREG_OFFSET(31)    // SP_EL0
-	ldp	x19, x20, [x3]
-	ldr	x21, [x3, #16]
-
-	msr	sp_el0, x19
-	msr	elr_el2, x20 		// pc on return from el2
-	msr	spsr_el2, x21 		// pstate on return from el2
-
-	add	x3, x2, #CPU_XREG_OFFSET(19)
-	ldp	x19, x20, [x3]
-	ldp	x21, x22, [x3, #16]
-	ldp	x23, x24, [x3, #32]
-	ldp	x25, x26, [x3, #48]
-	ldp	x27, x28, [x3, #64]
-	ldp	x29, lr, [x3, #80]
-.endm
-
-.macro save_host_regs
-	save_common_regs
-.endm
-
-.macro restore_host_regs
-	restore_common_regs
-.endm
-
-.macro save_fpsimd
-	// x2: cpu context address
-	// x3, x4: tmp regs
-	add	x3, x2, #CPU_GP_REG_OFFSET(CPU_FP_REGS)
-	fpsimd_save x3, 4
-.endm
-
-.macro restore_fpsimd
-	// x2: cpu context address
-	// x3, x4: tmp regs
-	add	x3, x2, #CPU_GP_REG_OFFSET(CPU_FP_REGS)
-	fpsimd_restore x3, 4
-.endm
-
-.macro save_guest_regs
-	// x0 is the vcpu address
-	// x1 is the return code, do not corrupt!
-	// x2 is the cpu context
-	// x3 is a tmp register
-	// Guest's x0-x3 are on the stack
-
-	// Compute base to save registers
-	add	x3, x2, #CPU_XREG_OFFSET(4)
-	stp	x4, x5, [x3]
-	stp	x6, x7, [x3, #16]
-	stp	x8, x9, [x3, #32]
-	stp	x10, x11, [x3, #48]
-	stp	x12, x13, [x3, #64]
-	stp	x14, x15, [x3, #80]
-	stp	x16, x17, [x3, #96]
-	str	x18, [x3, #112]
-
-	pop	x6, x7			// x2, x3
-	pop	x4, x5			// x0, x1
-
-	add	x3, x2, #CPU_XREG_OFFSET(0)
-	stp	x4, x5, [x3]
-	stp	x6, x7, [x3, #16]
-
-	save_common_regs
-.endm
-
-.macro restore_guest_regs
-	// x0 is the vcpu address.
-	// x2 is the cpu context
-	// x3 is a tmp register
-
-	// Prepare x0-x3 for later restore
-	add	x3, x2, #CPU_XREG_OFFSET(0)
-	ldp	x4, x5, [x3]
-	ldp	x6, x7, [x3, #16]
-	push	x4, x5		// Push x0-x3 on the stack
-	push	x6, x7
-
-	// x4-x18
-	ldp	x4, x5, [x3, #32]
-	ldp	x6, x7, [x3, #48]
-	ldp	x8, x9, [x3, #64]
-	ldp	x10, x11, [x3, #80]
-	ldp	x12, x13, [x3, #96]
-	ldp	x14, x15, [x3, #112]
-	ldp	x16, x17, [x3, #128]
-	ldr	x18, [x3, #144]
-
-	// x19-x29, lr, sp*, elr*, spsr*
-	restore_common_regs
-
-	// Last bits of the 64bit state
-	pop	x2, x3
-	pop	x0, x1
-
-	// Do not touch any register after this!
-.endm
-
-/*
- * Macros to perform system register save/restore.
- *
- * Ordering here is absolutely critical, and must be kept consistent
- * in {save,restore}_sysregs, {save,restore}_guest_32bit_state,
- * and in kvm_asm.h.
- *
- * In other words, don't touch any of these unless you know what
- * you are doing.
- */
-.macro save_sysregs
-	// x2: base address for cpu context
-	// x3: tmp register
-
-	add	x3, x2, #CPU_SYSREG_OFFSET(MPIDR_EL1)
-
-	mrs	x4,	vmpidr_el2
-	mrs	x5,	csselr_el1
-	mrs	x6,	sctlr_el1
-	mrs	x7,	actlr_el1
-	mrs	x8,	cpacr_el1
-	mrs	x9,	ttbr0_el1
-	mrs	x10,	ttbr1_el1
-	mrs	x11,	tcr_el1
-	mrs	x12,	esr_el1
-	mrs	x13, 	afsr0_el1
-	mrs	x14,	afsr1_el1
-	mrs	x15,	far_el1
-	mrs	x16,	mair_el1
-	mrs	x17,	vbar_el1
-	mrs	x18,	contextidr_el1
-	mrs	x19,	tpidr_el0
-	mrs	x20,	tpidrro_el0
-	mrs	x21,	tpidr_el1
-	mrs	x22, 	amair_el1
-	mrs	x23, 	cntkctl_el1
-	mrs	x24,	par_el1
-	mrs	x25,	mdscr_el1
-
-	stp	x4, x5, [x3]
-	stp	x6, x7, [x3, #16]
-	stp	x8, x9, [x3, #32]
-	stp	x10, x11, [x3, #48]
-	stp	x12, x13, [x3, #64]
-	stp	x14, x15, [x3, #80]
-	stp	x16, x17, [x3, #96]
-	stp	x18, x19, [x3, #112]
-	stp	x20, x21, [x3, #128]
-	stp	x22, x23, [x3, #144]
-	stp	x24, x25, [x3, #160]
-.endm
-
-.macro save_debug type
-	// x4: pointer to register set
-	// x5: number of registers to skip
-	// x6..x22 trashed
-
-	adr	x22, 1f
-	add	x22, x22, x5, lsl #2
-	br	x22
-1:
-	mrs	x21, \type\()15_el1
-	mrs	x20, \type\()14_el1
-	mrs	x19, \type\()13_el1
-	mrs	x18, \type\()12_el1
-	mrs	x17, \type\()11_el1
-	mrs	x16, \type\()10_el1
-	mrs	x15, \type\()9_el1
-	mrs	x14, \type\()8_el1
-	mrs	x13, \type\()7_el1
-	mrs	x12, \type\()6_el1
-	mrs	x11, \type\()5_el1
-	mrs	x10, \type\()4_el1
-	mrs	x9, \type\()3_el1
-	mrs	x8, \type\()2_el1
-	mrs	x7, \type\()1_el1
-	mrs	x6, \type\()0_el1
-
-	adr	x22, 1f
-	add	x22, x22, x5, lsl #2
-	br	x22
-1:
-	str	x21, [x4, #(15 * 8)]
-	str	x20, [x4, #(14 * 8)]
-	str	x19, [x4, #(13 * 8)]
-	str	x18, [x4, #(12 * 8)]
-	str	x17, [x4, #(11 * 8)]
-	str	x16, [x4, #(10 * 8)]
-	str	x15, [x4, #(9 * 8)]
-	str	x14, [x4, #(8 * 8)]
-	str	x13, [x4, #(7 * 8)]
-	str	x12, [x4, #(6 * 8)]
-	str	x11, [x4, #(5 * 8)]
-	str	x10, [x4, #(4 * 8)]
-	str	x9, [x4, #(3 * 8)]
-	str	x8, [x4, #(2 * 8)]
-	str	x7, [x4, #(1 * 8)]
-	str	x6, [x4, #(0 * 8)]
-.endm
-
-.macro restore_sysregs
-	// x2: base address for cpu context
-	// x3: tmp register
-
-	add	x3, x2, #CPU_SYSREG_OFFSET(MPIDR_EL1)
-
-	ldp	x4, x5, [x3]
-	ldp	x6, x7, [x3, #16]
-	ldp	x8, x9, [x3, #32]
-	ldp	x10, x11, [x3, #48]
-	ldp	x12, x13, [x3, #64]
-	ldp	x14, x15, [x3, #80]
-	ldp	x16, x17, [x3, #96]
-	ldp	x18, x19, [x3, #112]
-	ldp	x20, x21, [x3, #128]
-	ldp	x22, x23, [x3, #144]
-	ldp	x24, x25, [x3, #160]
-
-	msr	vmpidr_el2,	x4
-	msr	csselr_el1,	x5
-	msr	sctlr_el1,	x6
-	msr	actlr_el1,	x7
-	msr	cpacr_el1,	x8
-	msr	ttbr0_el1,	x9
-	msr	ttbr1_el1,	x10
-	msr	tcr_el1,	x11
-	msr	esr_el1,	x12
-	msr	afsr0_el1,	x13
-	msr	afsr1_el1,	x14
-	msr	far_el1,	x15
-	msr	mair_el1,	x16
-	msr	vbar_el1,	x17
-	msr	contextidr_el1,	x18
-	msr	tpidr_el0,	x19
-	msr	tpidrro_el0,	x20
-	msr	tpidr_el1,	x21
-	msr	amair_el1,	x22
-	msr	cntkctl_el1,	x23
-	msr	par_el1,	x24
-	msr	mdscr_el1,	x25
-.endm
-
-.macro restore_debug type
-	// x4: pointer to register set
-	// x5: number of registers to skip
-	// x6..x22 trashed
-
-	adr	x22, 1f
-	add	x22, x22, x5, lsl #2
-	br	x22
-1:
-	ldr	x21, [x4, #(15 * 8)]
-	ldr	x20, [x4, #(14 * 8)]
-	ldr	x19, [x4, #(13 * 8)]
-	ldr	x18, [x4, #(12 * 8)]
-	ldr	x17, [x4, #(11 * 8)]
-	ldr	x16, [x4, #(10 * 8)]
-	ldr	x15, [x4, #(9 * 8)]
-	ldr	x14, [x4, #(8 * 8)]
-	ldr	x13, [x4, #(7 * 8)]
-	ldr	x12, [x4, #(6 * 8)]
-	ldr	x11, [x4, #(5 * 8)]
-	ldr	x10, [x4, #(4 * 8)]
-	ldr	x9, [x4, #(3 * 8)]
-	ldr	x8, [x4, #(2 * 8)]
-	ldr	x7, [x4, #(1 * 8)]
-	ldr	x6, [x4, #(0 * 8)]
-
-	adr	x22, 1f
-	add	x22, x22, x5, lsl #2
-	br	x22
-1:
-	msr	\type\()15_el1, x21
-	msr	\type\()14_el1, x20
-	msr	\type\()13_el1, x19
-	msr	\type\()12_el1, x18
-	msr	\type\()11_el1, x17
-	msr	\type\()10_el1, x16
-	msr	\type\()9_el1, x15
-	msr	\type\()8_el1, x14
-	msr	\type\()7_el1, x13
-	msr	\type\()6_el1, x12
-	msr	\type\()5_el1, x11
-	msr	\type\()4_el1, x10
-	msr	\type\()3_el1, x9
-	msr	\type\()2_el1, x8
-	msr	\type\()1_el1, x7
-	msr	\type\()0_el1, x6
-.endm
-
-.macro skip_32bit_state tmp, target
-	// Skip 32bit state if not needed
-	mrs	\tmp, hcr_el2
-	tbnz	\tmp, #HCR_RW_SHIFT, \target
-.endm
-
-.macro skip_tee_state tmp, target
-	// Skip ThumbEE state if not needed
-	mrs	\tmp, id_pfr0_el1
-	tbz	\tmp, #12, \target
-.endm
-
-.macro skip_debug_state tmp, target
-	ldr	\tmp, [x0, #VCPU_DEBUG_FLAGS]
-	tbz	\tmp, #KVM_ARM64_DEBUG_DIRTY_SHIFT, \target
-.endm
-
-/*
- * Branch to target if CPTR_EL2.TFP bit is set (VFP/SIMD trapping enabled)
- */
-.macro skip_fpsimd_state tmp, target
-	mrs	\tmp, cptr_el2
-	tbnz	\tmp, #CPTR_EL2_TFP_SHIFT, \target
-.endm
-
-.macro compute_debug_state target
-	// Compute debug state: If any of KDE, MDE or KVM_ARM64_DEBUG_DIRTY
-	// is set, we do a full save/restore cycle and disable trapping.
-	add	x25, x0, #VCPU_CONTEXT
-
-	// Check the state of MDSCR_EL1
-	ldr	x25, [x25, #CPU_SYSREG_OFFSET(MDSCR_EL1)]
-	and	x26, x25, #DBG_MDSCR_KDE
-	and	x25, x25, #DBG_MDSCR_MDE
-	adds	xzr, x25, x26
-	b.eq	9998f		// Nothing to see there
-
-	// If any interesting bits was set, we must set the flag
-	mov	x26, #KVM_ARM64_DEBUG_DIRTY
-	str	x26, [x0, #VCPU_DEBUG_FLAGS]
-	b	9999f		// Don't skip restore
-
-9998:
-	// Otherwise load the flags from memory in case we recently
-	// trapped
-	skip_debug_state x25, \target
-9999:
-.endm
-
-.macro save_guest_32bit_state
-	skip_32bit_state x3, 1f
-
-	add	x3, x2, #CPU_SPSR_OFFSET(KVM_SPSR_ABT)
-	mrs	x4, spsr_abt
-	mrs	x5, spsr_und
-	mrs	x6, spsr_irq
-	mrs	x7, spsr_fiq
-	stp	x4, x5, [x3]
-	stp	x6, x7, [x3, #16]
-
-	add	x3, x2, #CPU_SYSREG_OFFSET(DACR32_EL2)
-	mrs	x4, dacr32_el2
-	mrs	x5, ifsr32_el2
-	stp	x4, x5, [x3]
-
-	skip_fpsimd_state x8, 2f
-	mrs	x6, fpexc32_el2
-	str	x6, [x3, #16]
-2:
-	skip_debug_state x8, 1f
-	mrs	x7, dbgvcr32_el2
-	str	x7, [x3, #24]
-1:
-.endm
-
-.macro restore_guest_32bit_state
-	skip_32bit_state x3, 1f
-
-	add	x3, x2, #CPU_SPSR_OFFSET(KVM_SPSR_ABT)
-	ldp	x4, x5, [x3]
-	ldp	x6, x7, [x3, #16]
-	msr	spsr_abt, x4
-	msr	spsr_und, x5
-	msr	spsr_irq, x6
-	msr	spsr_fiq, x7
-
-	add	x3, x2, #CPU_SYSREG_OFFSET(DACR32_EL2)
-	ldp	x4, x5, [x3]
-	msr	dacr32_el2, x4
-	msr	ifsr32_el2, x5
-
-	skip_debug_state x8, 1f
-	ldr	x7, [x3, #24]
-	msr	dbgvcr32_el2, x7
-1:
-.endm
-
-.macro activate_traps
-	ldr     x2, [x0, #VCPU_HCR_EL2]
-
-	/*
-	 * We are about to set CPTR_EL2.TFP to trap all floating point
-	 * register accesses to EL2, however, the ARM ARM clearly states that
-	 * traps are only taken to EL2 if the operation would not otherwise
-	 * trap to EL1.  Therefore, always make sure that for 32-bit guests,
-	 * we set FPEXC.EN to prevent traps to EL1, when setting the TFP bit.
-	 */
-	tbnz	x2, #HCR_RW_SHIFT, 99f // open code skip_32bit_state
-	mov	x3, #(1 << 30)
-	msr	fpexc32_el2, x3
-	isb
-99:
-	msr     hcr_el2, x2
-	mov	x2, #CPTR_EL2_TTA
-	orr     x2, x2, #CPTR_EL2_TFP
-	msr	cptr_el2, x2
-
-	mov	x2, #(1 << 15)	// Trap CP15 Cr=15
-	msr	hstr_el2, x2
-
-	// Monitor Debug Config - see kvm_arm_setup_debug()
-	ldr	x2, [x0, #VCPU_MDCR_EL2]
-	msr	mdcr_el2, x2
-.endm
-
-.macro deactivate_traps
-	mov	x2, #HCR_RW
-	msr	hcr_el2, x2
-	msr	hstr_el2, xzr
-
-	mrs	x2, mdcr_el2
-	and	x2, x2, #MDCR_EL2_HPMN_MASK
-	msr	mdcr_el2, x2
-.endm
-
-.macro activate_vm
-	ldr	x1, [x0, #VCPU_KVM]
-	kern_hyp_va	x1
-	ldr	x2, [x1, #KVM_VTTBR]
-	msr	vttbr_el2, x2
-.endm
-
-.macro deactivate_vm
-	msr	vttbr_el2, xzr
-.endm
-
-/*
- * Call into the vgic backend for state saving
- */
-.macro save_vgic_state
-alternative_if_not ARM64_HAS_SYSREG_GIC_CPUIF
-	bl	__save_vgic_v2_state
-alternative_else
-	bl	__save_vgic_v3_state
-alternative_endif
-	mrs	x24, hcr_el2
-	mov	x25, #HCR_INT_OVERRIDE
-	neg	x25, x25
-	and	x24, x24, x25
-	msr	hcr_el2, x24
-.endm
-
-/*
- * Call into the vgic backend for state restoring
- */
-.macro restore_vgic_state
-	mrs	x24, hcr_el2
-	ldr	x25, [x0, #VCPU_IRQ_LINES]
-	orr	x24, x24, #HCR_INT_OVERRIDE
-	orr	x24, x24, x25
-	msr	hcr_el2, x24
-alternative_if_not ARM64_HAS_SYSREG_GIC_CPUIF
-	bl	__restore_vgic_v2_state
-alternative_else
-	bl	__restore_vgic_v3_state
-alternative_endif
-.endm
-
-.macro save_timer_state
-	// x0: vcpu pointer
-	ldr	x2, [x0, #VCPU_KVM]
-	kern_hyp_va x2
-	ldr	w3, [x2, #KVM_TIMER_ENABLED]
-	cbz	w3, 1f
-
-	mrs	x3, cntv_ctl_el0
-	and	x3, x3, #3
-	str	w3, [x0, #VCPU_TIMER_CNTV_CTL]
-
-	isb
-
-	mrs	x3, cntv_cval_el0
-	str	x3, [x0, #VCPU_TIMER_CNTV_CVAL]
-
-1:
-	// Disable the virtual timer
-	msr	cntv_ctl_el0, xzr
-
-	// Allow physical timer/counter access for the host
-	mrs	x2, cnthctl_el2
-	orr	x2, x2, #3
-	msr	cnthctl_el2, x2
-
-	// Clear cntvoff for the host
-	msr	cntvoff_el2, xzr
-.endm
-
-.macro restore_timer_state
-	// x0: vcpu pointer
-	// Disallow physical timer access for the guest
-	// Physical counter access is allowed
-	mrs	x2, cnthctl_el2
-	orr	x2, x2, #1
-	bic	x2, x2, #2
-	msr	cnthctl_el2, x2
-
-	ldr	x2, [x0, #VCPU_KVM]
-	kern_hyp_va x2
-	ldr	w3, [x2, #KVM_TIMER_ENABLED]
-	cbz	w3, 1f
-
-	ldr	x3, [x2, #KVM_TIMER_CNTVOFF]
-	msr	cntvoff_el2, x3
-	ldr	x2, [x0, #VCPU_TIMER_CNTV_CVAL]
-	msr	cntv_cval_el0, x2
-	isb
-
-	ldr	w2, [x0, #VCPU_TIMER_CNTV_CTL]
-	and	x2, x2, #3
-	msr	cntv_ctl_el0, x2
-1:
-.endm
-
-__save_sysregs:
-	save_sysregs
-	ret
-
-__restore_sysregs:
-	restore_sysregs
-	ret
-
-/* Save debug state */
-__save_debug:
-	// x2: ptr to CPU context
-	// x3: ptr to debug reg struct
-	// x4/x5/x6-22/x24-26: trashed
-
-	mrs	x26, id_aa64dfr0_el1
-	ubfx	x24, x26, #12, #4	// Extract BRPs
-	ubfx	x25, x26, #20, #4	// Extract WRPs
-	mov	w26, #15
-	sub	w24, w26, w24		// How many BPs to skip
-	sub	w25, w26, w25		// How many WPs to skip
-
-	mov	x5, x24
-	add	x4, x3, #DEBUG_BCR
-	save_debug dbgbcr
-	add	x4, x3, #DEBUG_BVR
-	save_debug dbgbvr
-
-	mov	x5, x25
-	add	x4, x3, #DEBUG_WCR
-	save_debug dbgwcr
-	add	x4, x3, #DEBUG_WVR
-	save_debug dbgwvr
-
-	mrs	x21, mdccint_el1
-	str	x21, [x2, #CPU_SYSREG_OFFSET(MDCCINT_EL1)]
-	ret
-
-/* Restore debug state */
-__restore_debug:
-	// x2: ptr to CPU context
-	// x3: ptr to debug reg struct
-	// x4/x5/x6-22/x24-26: trashed
-
-	mrs	x26, id_aa64dfr0_el1
-	ubfx	x24, x26, #12, #4	// Extract BRPs
-	ubfx	x25, x26, #20, #4	// Extract WRPs
-	mov	w26, #15
-	sub	w24, w26, w24		// How many BPs to skip
-	sub	w25, w26, w25		// How many WPs to skip
-
-	mov	x5, x24
-	add	x4, x3, #DEBUG_BCR
-	restore_debug dbgbcr
-	add	x4, x3, #DEBUG_BVR
-	restore_debug dbgbvr
-
-	mov	x5, x25
-	add	x4, x3, #DEBUG_WCR
-	restore_debug dbgwcr
-	add	x4, x3, #DEBUG_WVR
-	restore_debug dbgwvr
-
-	ldr	x21, [x2, #CPU_SYSREG_OFFSET(MDCCINT_EL1)]
-	msr	mdccint_el1, x21
-
-	ret
-
-__save_fpsimd:
-	skip_fpsimd_state x3, 1f
-	save_fpsimd
-1:	ret
-
-__restore_fpsimd:
-	skip_fpsimd_state x3, 1f
-	restore_fpsimd
-1:	ret
-
-switch_to_guest_fpsimd:
-	push	x4, lr
-
-	mrs	x2, cptr_el2
-	bic	x2, x2, #CPTR_EL2_TFP
-	msr	cptr_el2, x2
-	isb
-
-	mrs	x0, tpidr_el2
-
-	ldr	x2, [x0, #VCPU_HOST_CONTEXT]
-	kern_hyp_va x2
-	bl __save_fpsimd
-
-	add	x2, x0, #VCPU_CONTEXT
-	bl __restore_fpsimd
-
-	skip_32bit_state x3, 1f
-	ldr	x4, [x2, #CPU_SYSREG_OFFSET(FPEXC32_EL2)]
-	msr	fpexc32_el2, x4
-1:
-	pop	x4, lr
-	pop	x2, x3
-	pop	x0, x1
-
-	eret
-
-/*
- * u64 __kvm_vcpu_run(struct kvm_vcpu *vcpu);
- *
- * This is the world switch. The first half of the function
- * deals with entering the guest, and anything from __kvm_vcpu_return
- * to the end of the function deals with reentering the host.
- * On the enter path, only x0 (vcpu pointer) must be preserved until
- * the last moment. On the exit path, x0 (vcpu pointer) and x1 (exception
- * code) must both be preserved until the epilogue.
- * In both cases, x2 points to the CPU context we're saving/restoring from/to.
- */
-ENTRY(__kvm_vcpu_run)
-	kern_hyp_va	x0
-	msr	tpidr_el2, x0	// Save the vcpu register
-
-	// Host context
-	ldr	x2, [x0, #VCPU_HOST_CONTEXT]
-	kern_hyp_va x2
-
-	save_host_regs
-	bl __save_sysregs
-
-	compute_debug_state 1f
-	add	x3, x0, #VCPU_HOST_DEBUG_STATE
-	bl	__save_debug
-1:
-	activate_traps
-	activate_vm
-
-	restore_vgic_state
-	restore_timer_state
-
-	// Guest context
-	add	x2, x0, #VCPU_CONTEXT
-
-	// We must restore the 32-bit state before the sysregs, thanks
-	// to Cortex-A57 erratum #852523.
-	restore_guest_32bit_state
-	bl __restore_sysregs
-
-	skip_debug_state x3, 1f
-	ldr	x3, [x0, #VCPU_DEBUG_PTR]
-	kern_hyp_va x3
-	bl	__restore_debug
-1:
-	restore_guest_regs
-
-	// That's it, no more messing around.
-	eret
-
-__kvm_vcpu_return:
-	// Assume x0 is the vcpu pointer, x1 the return code
-	// Guest's x0-x3 are on the stack
-
-	// Guest context
-	add	x2, x0, #VCPU_CONTEXT
-
-	save_guest_regs
-	bl __save_fpsimd
-	bl __save_sysregs
-
-	skip_debug_state x3, 1f
-	ldr	x3, [x0, #VCPU_DEBUG_PTR]
-	kern_hyp_va x3
-	bl	__save_debug
-1:
-	save_guest_32bit_state
-
-	save_timer_state
-	save_vgic_state
-
-	deactivate_traps
-	deactivate_vm
-
-	// Host context
-	ldr	x2, [x0, #VCPU_HOST_CONTEXT]
-	kern_hyp_va x2
-
-	bl __restore_sysregs
-	bl __restore_fpsimd
-	/* Clear FPSIMD and Trace trapping */
-	msr     cptr_el2, xzr
-
-	skip_debug_state x3, 1f
-	// Clear the dirty flag for the next run, as all the state has
-	// already been saved. Note that we nuke the whole 64bit word.
-	// If we ever add more flags, we'll have to be more careful...
-	str	xzr, [x0, #VCPU_DEBUG_FLAGS]
-	add	x3, x0, #VCPU_HOST_DEBUG_STATE
-	bl	__restore_debug
-1:
-	restore_host_regs
-
-	mov	x0, x1
-	ret
-END(__kvm_vcpu_run)
-
-// void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
-ENTRY(__kvm_tlb_flush_vmid_ipa)
-	dsb	ishst
-
-	kern_hyp_va	x0
-	ldr	x2, [x0, #KVM_VTTBR]
-	msr	vttbr_el2, x2
-	isb
-
-	/*
-	 * We could do so much better if we had the VA as well.
-	 * Instead, we invalidate Stage-2 for this IPA, and the
-	 * whole of Stage-1. Weep...
-	 */
-	lsr	x1, x1, #12
-	tlbi	ipas2e1is, x1
-	/*
-	 * We have to ensure completion of the invalidation at Stage-2,
-	 * since a table walk on another CPU could refill a TLB with a
-	 * complete (S1 + S2) walk based on the old Stage-2 mapping if
-	 * the Stage-1 invalidation happened first.
-	 */
-	dsb	ish
-	tlbi	vmalle1is
-	dsb	ish
-	isb
-
-	msr	vttbr_el2, xzr
-	ret
-ENDPROC(__kvm_tlb_flush_vmid_ipa)
-
-/**
- * void __kvm_tlb_flush_vmid(struct kvm *kvm) - Flush per-VMID TLBs
- * @struct kvm *kvm - pointer to kvm structure
- *
- * Invalidates all Stage 1 and 2 TLB entries for current VMID.
- */
-ENTRY(__kvm_tlb_flush_vmid)
-	dsb     ishst
-
-	kern_hyp_va     x0
-	ldr     x2, [x0, #KVM_VTTBR]
-	msr     vttbr_el2, x2
-	isb
-
-	tlbi    vmalls12e1is
-	dsb     ish
-	isb
-
-	msr     vttbr_el2, xzr
-	ret
-ENDPROC(__kvm_tlb_flush_vmid)
-
-ENTRY(__kvm_flush_vm_context)
-	dsb	ishst
-	tlbi	alle1is
-	ic	ialluis
-	dsb	ish
-	ret
-ENDPROC(__kvm_flush_vm_context)
-
-__kvm_hyp_panic:
-	// Stash PAR_EL1 before corrupting it in __restore_sysregs
-	mrs	x0, par_el1
-	push	x0, xzr
-
-	// Guess the context by looking at VTTBR:
-	// If zero, then we're already a host.
-	// Otherwise restore a minimal host context before panicing.
-	mrs	x0, vttbr_el2
-	cbz	x0, 1f
-
-	mrs	x0, tpidr_el2
-
-	deactivate_traps
-	deactivate_vm
-
-	ldr	x2, [x0, #VCPU_HOST_CONTEXT]
-	kern_hyp_va x2
-
-	bl __restore_sysregs
-
-	/*
-	 * Make sure we have a valid host stack, and don't leave junk in the
-	 * frame pointer that will give us a misleading host stack unwinding.
-	 */
-	ldr	x22, [x2, #CPU_GP_REG_OFFSET(CPU_SP_EL1)]
-	msr	sp_el1, x22
-	mov	x29, xzr
-
-1:	adr	x0, __hyp_panic_str
-	adr	x1, 2f
-	ldp	x2, x3, [x1]
-	sub	x0, x0, x2
-	add	x0, x0, x3
-	mrs	x1, spsr_el2
-	mrs	x2, elr_el2
-	mrs	x3, esr_el2
-	mrs	x4, far_el2
-	mrs	x5, hpfar_el2
-	pop	x6, xzr		// active context PAR_EL1
-	mrs	x7, tpidr_el2
-
-	mov	lr, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT |\
-		      PSR_MODE_EL1h)
-	msr	spsr_el2, lr
-	ldr	lr, =panic
-	msr	elr_el2, lr
-	eret
-
-	.align	3
-2:	.quad	HYP_PAGE_OFFSET
-	.quad	PAGE_OFFSET
-ENDPROC(__kvm_hyp_panic)
-
-__hyp_panic_str:
-	.ascii	"HYP panic:\nPS:%08x PC:%016x ESR:%08x\nFAR:%016x HPFAR:%016x PAR:%016x\nVCPU:%p\n\0"
-
-	.align	2
 
 /*
  * u64 kvm_call_hyp(void *hypfn, ...);
@@ -934,7 +31,7 @@
  * passed as x0, x1, and x2 (a maximum of 3 arguments in addition to the
  * function pointer can be passed).  The function being called must be mapped
  * in Hyp mode (see init_hyp_mode in arch/arm/kvm/arm.c).  Return values are
- * passed in r0 and r1.
+ * passed in x0.
  *
  * A function pointer with a value of 0 has a special meaning, and is
  * used to implement __hyp_get_vectors in the same way as in
@@ -944,179 +41,3 @@
 	hvc	#0
 	ret
 ENDPROC(kvm_call_hyp)
-
-.macro invalid_vector	label, target
-	.align	2
-\label:
-	b \target
-ENDPROC(\label)
-.endm
-
-	/* None of these should ever happen */
-	invalid_vector	el2t_sync_invalid, __kvm_hyp_panic
-	invalid_vector	el2t_irq_invalid, __kvm_hyp_panic
-	invalid_vector	el2t_fiq_invalid, __kvm_hyp_panic
-	invalid_vector	el2t_error_invalid, __kvm_hyp_panic
-	invalid_vector	el2h_sync_invalid, __kvm_hyp_panic
-	invalid_vector	el2h_irq_invalid, __kvm_hyp_panic
-	invalid_vector	el2h_fiq_invalid, __kvm_hyp_panic
-	invalid_vector	el2h_error_invalid, __kvm_hyp_panic
-	invalid_vector	el1_sync_invalid, __kvm_hyp_panic
-	invalid_vector	el1_irq_invalid, __kvm_hyp_panic
-	invalid_vector	el1_fiq_invalid, __kvm_hyp_panic
-	invalid_vector	el1_error_invalid, __kvm_hyp_panic
-
-el1_sync:					// Guest trapped into EL2
-	push	x0, x1
-	push	x2, x3
-
-	mrs	x1, esr_el2
-	lsr	x2, x1, #ESR_ELx_EC_SHIFT
-
-	cmp	x2, #ESR_ELx_EC_HVC64
-	b.ne	el1_trap
-
-	mrs	x3, vttbr_el2			// If vttbr is valid, the 64bit guest
-	cbnz	x3, el1_trap			// called HVC
-
-	/* Here, we're pretty sure the host called HVC. */
-	pop	x2, x3
-	pop	x0, x1
-
-	/* Check for __hyp_get_vectors */
-	cbnz	x0, 1f
-	mrs	x0, vbar_el2
-	b	2f
-
-1:	push	lr, xzr
-
-	/*
-	 * Compute the function address in EL2, and shuffle the parameters.
-	 */
-	kern_hyp_va	x0
-	mov	lr, x0
-	mov	x0, x1
-	mov	x1, x2
-	mov	x2, x3
-	blr	lr
-
-	pop	lr, xzr
-2:	eret
-
-el1_trap:
-	/*
-	 * x1: ESR
-	 * x2: ESR_EC
-	 */
-
-	/* Guest accessed VFP/SIMD registers, save host, restore Guest */
-	cmp	x2, #ESR_ELx_EC_FP_ASIMD
-	b.eq	switch_to_guest_fpsimd
-
-	cmp	x2, #ESR_ELx_EC_DABT_LOW
-	mov	x0, #ESR_ELx_EC_IABT_LOW
-	ccmp	x2, x0, #4, ne
-	b.ne	1f		// Not an abort we care about
-
-	/* This is an abort. Check for permission fault */
-alternative_if_not ARM64_WORKAROUND_834220
-	and	x2, x1, #ESR_ELx_FSC_TYPE
-	cmp	x2, #FSC_PERM
-	b.ne	1f		// Not a permission fault
-alternative_else
-	nop			// Use the permission fault path to
-	nop			// check for a valid S1 translation,
-	nop			// regardless of the ESR value.
-alternative_endif
-
-	/*
-	 * Check for Stage-1 page table walk, which is guaranteed
-	 * to give a valid HPFAR_EL2.
-	 */
-	tbnz	x1, #7, 1f	// S1PTW is set
-
-	/* Preserve PAR_EL1 */
-	mrs	x3, par_el1
-	push	x3, xzr
-
-	/*
-	 * Permission fault, HPFAR_EL2 is invalid.
-	 * Resolve the IPA the hard way using the guest VA.
-	 * Stage-1 translation already validated the memory access rights.
-	 * As such, we can use the EL1 translation regime, and don't have
-	 * to distinguish between EL0 and EL1 access.
-	 */
-	mrs	x2, far_el2
-	at	s1e1r, x2
-	isb
-
-	/* Read result */
-	mrs	x3, par_el1
-	pop	x0, xzr			// Restore PAR_EL1 from the stack
-	msr	par_el1, x0
-	tbnz	x3, #0, 3f		// Bail out if we failed the translation
-	ubfx	x3, x3, #12, #36	// Extract IPA
-	lsl	x3, x3, #4		// and present it like HPFAR
-	b	2f
-
-1:	mrs	x3, hpfar_el2
-	mrs	x2, far_el2
-
-2:	mrs	x0, tpidr_el2
-	str	w1, [x0, #VCPU_ESR_EL2]
-	str	x2, [x0, #VCPU_FAR_EL2]
-	str	x3, [x0, #VCPU_HPFAR_EL2]
-
-	mov	x1, #ARM_EXCEPTION_TRAP
-	b	__kvm_vcpu_return
-
-	/*
-	 * Translation failed. Just return to the guest and
-	 * let it fault again. Another CPU is probably playing
-	 * behind our back.
-	 */
-3:	pop	x2, x3
-	pop	x0, x1
-
-	eret
-
-el1_irq:
-	push	x0, x1
-	push	x2, x3
-	mrs	x0, tpidr_el2
-	mov	x1, #ARM_EXCEPTION_IRQ
-	b	__kvm_vcpu_return
-
-	.ltorg
-
-	.align 11
-
-ENTRY(__kvm_hyp_vector)
-	ventry	el2t_sync_invalid		// Synchronous EL2t
-	ventry	el2t_irq_invalid		// IRQ EL2t
-	ventry	el2t_fiq_invalid		// FIQ EL2t
-	ventry	el2t_error_invalid		// Error EL2t
-
-	ventry	el2h_sync_invalid		// Synchronous EL2h
-	ventry	el2h_irq_invalid		// IRQ EL2h
-	ventry	el2h_fiq_invalid		// FIQ EL2h
-	ventry	el2h_error_invalid		// Error EL2h
-
-	ventry	el1_sync			// Synchronous 64-bit EL1
-	ventry	el1_irq				// IRQ 64-bit EL1
-	ventry	el1_fiq_invalid			// FIQ 64-bit EL1
-	ventry	el1_error_invalid		// Error 64-bit EL1
-
-	ventry	el1_sync			// Synchronous 32-bit EL1
-	ventry	el1_irq				// IRQ 32-bit EL1
-	ventry	el1_fiq_invalid			// FIQ 32-bit EL1
-	ventry	el1_error_invalid		// Error 32-bit EL1
-ENDPROC(__kvm_hyp_vector)
-
-
-ENTRY(__kvm_get_mdcr_el2)
-	mrs	x0, mdcr_el2
-	ret
-ENDPROC(__kvm_get_mdcr_el2)
-
-	.popsection
diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile
new file mode 100644
index 0000000..826032b
--- /dev/null
+++ b/arch/arm64/kvm/hyp/Makefile
@@ -0,0 +1,14 @@
+#
+# Makefile for Kernel-based Virtual Machine module, HYP part
+#
+
+obj-$(CONFIG_KVM_ARM_HOST) += vgic-v2-sr.o
+obj-$(CONFIG_KVM_ARM_HOST) += vgic-v3-sr.o
+obj-$(CONFIG_KVM_ARM_HOST) += timer-sr.o
+obj-$(CONFIG_KVM_ARM_HOST) += sysreg-sr.o
+obj-$(CONFIG_KVM_ARM_HOST) += debug-sr.o
+obj-$(CONFIG_KVM_ARM_HOST) += entry.o
+obj-$(CONFIG_KVM_ARM_HOST) += switch.o
+obj-$(CONFIG_KVM_ARM_HOST) += fpsimd.o
+obj-$(CONFIG_KVM_ARM_HOST) += tlb.o
+obj-$(CONFIG_KVM_ARM_HOST) += hyp-entry.o
diff --git a/arch/arm64/kvm/hyp/debug-sr.c b/arch/arm64/kvm/hyp/debug-sr.c
new file mode 100644
index 0000000..c9c1e97
--- /dev/null
+++ b/arch/arm64/kvm/hyp/debug-sr.c
@@ -0,0 +1,140 @@
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/compiler.h>
+#include <linux/kvm_host.h>
+
+#include <asm/kvm_asm.h>
+#include <asm/kvm_mmu.h>
+
+#include "hyp.h"
+
+#define read_debug(r,n)		read_sysreg(r##n##_el1)
+#define write_debug(v,r,n)	write_sysreg(v, r##n##_el1)
+
+#define save_debug(ptr,reg,nr)						\
+	switch (nr) {							\
+	case 15:	ptr[15] = read_debug(reg, 15);			\
+	case 14:	ptr[14] = read_debug(reg, 14);			\
+	case 13:	ptr[13] = read_debug(reg, 13);			\
+	case 12:	ptr[12] = read_debug(reg, 12);			\
+	case 11:	ptr[11] = read_debug(reg, 11);			\
+	case 10:	ptr[10] = read_debug(reg, 10);			\
+	case 9:		ptr[9] = read_debug(reg, 9);			\
+	case 8:		ptr[8] = read_debug(reg, 8);			\
+	case 7:		ptr[7] = read_debug(reg, 7);			\
+	case 6:		ptr[6] = read_debug(reg, 6);			\
+	case 5:		ptr[5] = read_debug(reg, 5);			\
+	case 4:		ptr[4] = read_debug(reg, 4);			\
+	case 3:		ptr[3] = read_debug(reg, 3);			\
+	case 2:		ptr[2] = read_debug(reg, 2);			\
+	case 1:		ptr[1] = read_debug(reg, 1);			\
+	default:	ptr[0] = read_debug(reg, 0);			\
+	}
+
+#define restore_debug(ptr,reg,nr)					\
+	switch (nr) {							\
+	case 15:	write_debug(ptr[15], reg, 15);			\
+	case 14:	write_debug(ptr[14], reg, 14);			\
+	case 13:	write_debug(ptr[13], reg, 13);			\
+	case 12:	write_debug(ptr[12], reg, 12);			\
+	case 11:	write_debug(ptr[11], reg, 11);			\
+	case 10:	write_debug(ptr[10], reg, 10);			\
+	case 9:		write_debug(ptr[9], reg, 9);			\
+	case 8:		write_debug(ptr[8], reg, 8);			\
+	case 7:		write_debug(ptr[7], reg, 7);			\
+	case 6:		write_debug(ptr[6], reg, 6);			\
+	case 5:		write_debug(ptr[5], reg, 5);			\
+	case 4:		write_debug(ptr[4], reg, 4);			\
+	case 3:		write_debug(ptr[3], reg, 3);			\
+	case 2:		write_debug(ptr[2], reg, 2);			\
+	case 1:		write_debug(ptr[1], reg, 1);			\
+	default:	write_debug(ptr[0], reg, 0);			\
+	}
+
+void __hyp_text __debug_save_state(struct kvm_vcpu *vcpu,
+				   struct kvm_guest_debug_arch *dbg,
+				   struct kvm_cpu_context *ctxt)
+{
+	u64 aa64dfr0;
+	int brps, wrps;
+
+	if (!(vcpu->arch.debug_flags & KVM_ARM64_DEBUG_DIRTY))
+		return;
+
+	aa64dfr0 = read_sysreg(id_aa64dfr0_el1);
+	brps = (aa64dfr0 >> 12) & 0xf;
+	wrps = (aa64dfr0 >> 20) & 0xf;
+
+	save_debug(dbg->dbg_bcr, dbgbcr, brps);
+	save_debug(dbg->dbg_bvr, dbgbvr, brps);
+	save_debug(dbg->dbg_wcr, dbgwcr, wrps);
+	save_debug(dbg->dbg_wvr, dbgwvr, wrps);
+
+	ctxt->sys_regs[MDCCINT_EL1] = read_sysreg(mdccint_el1);
+}
+
+void __hyp_text __debug_restore_state(struct kvm_vcpu *vcpu,
+				      struct kvm_guest_debug_arch *dbg,
+				      struct kvm_cpu_context *ctxt)
+{
+	u64 aa64dfr0;
+	int brps, wrps;
+
+	if (!(vcpu->arch.debug_flags & KVM_ARM64_DEBUG_DIRTY))
+		return;
+
+	aa64dfr0 = read_sysreg(id_aa64dfr0_el1);
+
+	brps = (aa64dfr0 >> 12) & 0xf;
+	wrps = (aa64dfr0 >> 20) & 0xf;
+
+	restore_debug(dbg->dbg_bcr, dbgbcr, brps);
+	restore_debug(dbg->dbg_bvr, dbgbvr, brps);
+	restore_debug(dbg->dbg_wcr, dbgwcr, wrps);
+	restore_debug(dbg->dbg_wvr, dbgwvr, wrps);
+
+	write_sysreg(ctxt->sys_regs[MDCCINT_EL1], mdccint_el1);
+}
+
+void __hyp_text __debug_cond_save_host_state(struct kvm_vcpu *vcpu)
+{
+	/* If any of KDE, MDE or KVM_ARM64_DEBUG_DIRTY is set, perform
+	 * a full save/restore cycle. */
+	if ((vcpu->arch.ctxt.sys_regs[MDSCR_EL1] & DBG_MDSCR_KDE) ||
+	    (vcpu->arch.ctxt.sys_regs[MDSCR_EL1] & DBG_MDSCR_MDE))
+		vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
+
+	__debug_save_state(vcpu, &vcpu->arch.host_debug_state,
+			   kern_hyp_va(vcpu->arch.host_cpu_context));
+}
+
+void __hyp_text __debug_cond_restore_host_state(struct kvm_vcpu *vcpu)
+{
+	__debug_restore_state(vcpu, &vcpu->arch.host_debug_state,
+			      kern_hyp_va(vcpu->arch.host_cpu_context));
+
+	if (vcpu->arch.debug_flags & KVM_ARM64_DEBUG_DIRTY)
+		vcpu->arch.debug_flags &= ~KVM_ARM64_DEBUG_DIRTY;
+}
+
+static u32 __hyp_text __debug_read_mdcr_el2(void)
+{
+	return read_sysreg(mdcr_el2);
+}
+
+__alias(__debug_read_mdcr_el2) u32 __kvm_get_mdcr_el2(void);
diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S
new file mode 100644
index 0000000..fd0fbe9
--- /dev/null
+++ b/arch/arm64/kvm/hyp/entry.S
@@ -0,0 +1,160 @@
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/linkage.h>
+
+#include <asm/asm-offsets.h>
+#include <asm/assembler.h>
+#include <asm/fpsimdmacros.h>
+#include <asm/kvm.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_mmu.h>
+
+#define CPU_GP_REG_OFFSET(x)	(CPU_GP_REGS + x)
+#define CPU_XREG_OFFSET(x)	CPU_GP_REG_OFFSET(CPU_USER_PT_REGS + 8*x)
+
+	.text
+	.pushsection	.hyp.text, "ax"
+
+.macro save_callee_saved_regs ctxt
+	stp	x19, x20, [\ctxt, #CPU_XREG_OFFSET(19)]
+	stp	x21, x22, [\ctxt, #CPU_XREG_OFFSET(21)]
+	stp	x23, x24, [\ctxt, #CPU_XREG_OFFSET(23)]
+	stp	x25, x26, [\ctxt, #CPU_XREG_OFFSET(25)]
+	stp	x27, x28, [\ctxt, #CPU_XREG_OFFSET(27)]
+	stp	x29, lr,  [\ctxt, #CPU_XREG_OFFSET(29)]
+.endm
+
+.macro restore_callee_saved_regs ctxt
+	ldp	x19, x20, [\ctxt, #CPU_XREG_OFFSET(19)]
+	ldp	x21, x22, [\ctxt, #CPU_XREG_OFFSET(21)]
+	ldp	x23, x24, [\ctxt, #CPU_XREG_OFFSET(23)]
+	ldp	x25, x26, [\ctxt, #CPU_XREG_OFFSET(25)]
+	ldp	x27, x28, [\ctxt, #CPU_XREG_OFFSET(27)]
+	ldp	x29, lr,  [\ctxt, #CPU_XREG_OFFSET(29)]
+.endm
+
+/*
+ * u64 __guest_enter(struct kvm_vcpu *vcpu,
+ *		     struct kvm_cpu_context *host_ctxt);
+ */
+ENTRY(__guest_enter)
+	// x0: vcpu
+	// x1: host/guest context
+	// x2-x18: clobbered by macros
+
+	// Store the host regs
+	save_callee_saved_regs x1
+
+	// Preserve vcpu & host_ctxt for use at exit time
+	stp	x0, x1, [sp, #-16]!
+
+	add	x1, x0, #VCPU_CONTEXT
+
+	// Prepare x0-x1 for later restore by pushing them onto the stack
+	ldp	x2, x3, [x1, #CPU_XREG_OFFSET(0)]
+	stp	x2, x3, [sp, #-16]!
+
+	// x2-x18
+	ldp	x2, x3,   [x1, #CPU_XREG_OFFSET(2)]
+	ldp	x4, x5,   [x1, #CPU_XREG_OFFSET(4)]
+	ldp	x6, x7,   [x1, #CPU_XREG_OFFSET(6)]
+	ldp	x8, x9,   [x1, #CPU_XREG_OFFSET(8)]
+	ldp	x10, x11, [x1, #CPU_XREG_OFFSET(10)]
+	ldp	x12, x13, [x1, #CPU_XREG_OFFSET(12)]
+	ldp	x14, x15, [x1, #CPU_XREG_OFFSET(14)]
+	ldp	x16, x17, [x1, #CPU_XREG_OFFSET(16)]
+	ldr	x18,      [x1, #CPU_XREG_OFFSET(18)]
+
+	// x19-x29, lr
+	restore_callee_saved_regs x1
+
+	// Last bits of the 64bit state
+	ldp	x0, x1, [sp], #16
+
+	// Do not touch any register after this!
+	eret
+ENDPROC(__guest_enter)
+
+ENTRY(__guest_exit)
+	// x0: vcpu
+	// x1: return code
+	// x2-x3: free
+	// x4-x29,lr: vcpu regs
+	// vcpu x0-x3 on the stack
+
+	add	x2, x0, #VCPU_CONTEXT
+
+	stp	x4, x5,   [x2, #CPU_XREG_OFFSET(4)]
+	stp	x6, x7,   [x2, #CPU_XREG_OFFSET(6)]
+	stp	x8, x9,   [x2, #CPU_XREG_OFFSET(8)]
+	stp	x10, x11, [x2, #CPU_XREG_OFFSET(10)]
+	stp	x12, x13, [x2, #CPU_XREG_OFFSET(12)]
+	stp	x14, x15, [x2, #CPU_XREG_OFFSET(14)]
+	stp	x16, x17, [x2, #CPU_XREG_OFFSET(16)]
+	str	x18,      [x2, #CPU_XREG_OFFSET(18)]
+
+	ldp	x6, x7, [sp], #16	// x2, x3
+	ldp	x4, x5, [sp], #16	// x0, x1
+
+	stp	x4, x5, [x2, #CPU_XREG_OFFSET(0)]
+	stp	x6, x7, [x2, #CPU_XREG_OFFSET(2)]
+
+	save_callee_saved_regs x2
+
+	// Restore vcpu & host_ctxt from the stack
+	// (preserving return code in x1)
+	ldp	x0, x2, [sp], #16
+	// Now restore the host regs
+	restore_callee_saved_regs x2
+
+	mov	x0, x1
+	ret
+ENDPROC(__guest_exit)
+
+ENTRY(__fpsimd_guest_restore)
+	stp	x4, lr, [sp, #-16]!
+
+	mrs	x2, cptr_el2
+	bic	x2, x2, #CPTR_EL2_TFP
+	msr	cptr_el2, x2
+	isb
+
+	mrs	x3, tpidr_el2
+
+	ldr	x0, [x3, #VCPU_HOST_CONTEXT]
+	kern_hyp_va x0
+	add	x0, x0, #CPU_GP_REG_OFFSET(CPU_FP_REGS)
+	bl	__fpsimd_save_state
+
+	add	x2, x3, #VCPU_CONTEXT
+	add	x0, x2, #CPU_GP_REG_OFFSET(CPU_FP_REGS)
+	bl	__fpsimd_restore_state
+
+	// Skip restoring fpexc32 for AArch64 guests
+	mrs	x1, hcr_el2
+	tbnz	x1, #HCR_RW_SHIFT, 1f
+	ldr	x4, [x3, #VCPU_FPEXC32_EL2]
+	msr	fpexc32_el2, x4
+1:
+	ldp	x4, lr, [sp], #16
+	ldp	x2, x3, [sp], #16
+	ldp	x0, x1, [sp], #16
+
+	eret
+ENDPROC(__fpsimd_guest_restore)
diff --git a/arch/arm64/kvm/hyp/fpsimd.S b/arch/arm64/kvm/hyp/fpsimd.S
new file mode 100644
index 0000000..da3f22c
--- /dev/null
+++ b/arch/arm64/kvm/hyp/fpsimd.S
@@ -0,0 +1,33 @@
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/linkage.h>
+
+#include <asm/fpsimdmacros.h>
+
+	.text
+	.pushsection	.hyp.text, "ax"
+
+ENTRY(__fpsimd_save_state)
+	fpsimd_save	x0, 1
+	ret
+ENDPROC(__fpsimd_save_state)
+
+ENTRY(__fpsimd_restore_state)
+	fpsimd_restore	x0, 1
+	ret
+ENDPROC(__fpsimd_restore_state)
diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
new file mode 100644
index 0000000..93e8d983
--- /dev/null
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -0,0 +1,212 @@
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/linkage.h>
+
+#include <asm/alternative.h>
+#include <asm/assembler.h>
+#include <asm/asm-offsets.h>
+#include <asm/cpufeature.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_mmu.h>
+
+	.text
+	.pushsection	.hyp.text, "ax"
+
+.macro	save_x0_to_x3
+	stp	x0, x1, [sp, #-16]!
+	stp	x2, x3, [sp, #-16]!
+.endm
+
+.macro	restore_x0_to_x3
+	ldp	x2, x3, [sp], #16
+	ldp	x0, x1, [sp], #16
+.endm
+
+el1_sync:				// Guest trapped into EL2
+	save_x0_to_x3
+
+	mrs	x1, esr_el2
+	lsr	x2, x1, #ESR_ELx_EC_SHIFT
+
+	cmp	x2, #ESR_ELx_EC_HVC64
+	b.ne	el1_trap
+
+	mrs	x3, vttbr_el2		// If vttbr is valid, the 64bit guest
+	cbnz	x3, el1_trap		// called HVC
+
+	/* Here, we're pretty sure the host called HVC. */
+	restore_x0_to_x3
+
+	/* Check for __hyp_get_vectors */
+	cbnz	x0, 1f
+	mrs	x0, vbar_el2
+	b	2f
+
+1:	stp	lr, xzr, [sp, #-16]!
+
+	/*
+	 * Compute the function address in EL2, and shuffle the parameters.
+	 */
+	kern_hyp_va	x0
+	mov	lr, x0
+	mov	x0, x1
+	mov	x1, x2
+	mov	x2, x3
+	blr	lr
+
+	ldp	lr, xzr, [sp], #16
+2:	eret
+
+el1_trap:
+	/*
+	 * x1: ESR
+	 * x2: ESR_EC
+	 */
+
+	/* Guest accessed VFP/SIMD registers, save host, restore Guest */
+	cmp	x2, #ESR_ELx_EC_FP_ASIMD
+	b.eq	__fpsimd_guest_restore
+
+	cmp	x2, #ESR_ELx_EC_DABT_LOW
+	mov	x0, #ESR_ELx_EC_IABT_LOW
+	ccmp	x2, x0, #4, ne
+	b.ne	1f		// Not an abort we care about
+
+	/* This is an abort. Check for permission fault */
+alternative_if_not ARM64_WORKAROUND_834220
+	and	x2, x1, #ESR_ELx_FSC_TYPE
+	cmp	x2, #FSC_PERM
+	b.ne	1f		// Not a permission fault
+alternative_else
+	nop			// Use the permission fault path to
+	nop			// check for a valid S1 translation,
+	nop			// regardless of the ESR value.
+alternative_endif
+
+	/*
+	 * Check for Stage-1 page table walk, which is guaranteed
+	 * to give a valid HPFAR_EL2.
+	 */
+	tbnz	x1, #7, 1f	// S1PTW is set
+
+	/* Preserve PAR_EL1 */
+	mrs	x3, par_el1
+	stp	x3, xzr, [sp, #-16]!
+
+	/*
+	 * Permission fault, HPFAR_EL2 is invalid.
+	 * Resolve the IPA the hard way using the guest VA.
+	 * Stage-1 translation already validated the memory access rights.
+	 * As such, we can use the EL1 translation regime, and don't have
+	 * to distinguish between EL0 and EL1 access.
+	 */
+	mrs	x2, far_el2
+	at	s1e1r, x2
+	isb
+
+	/* Read result */
+	mrs	x3, par_el1
+	ldp	x0, xzr, [sp], #16	// Restore PAR_EL1 from the stack
+	msr	par_el1, x0
+	tbnz	x3, #0, 3f		// Bail out if we failed the translation
+	ubfx	x3, x3, #12, #36	// Extract IPA
+	lsl	x3, x3, #4		// and present it like HPFAR
+	b	2f
+
+1:	mrs	x3, hpfar_el2
+	mrs	x2, far_el2
+
+2:	mrs	x0, tpidr_el2
+	str	w1, [x0, #VCPU_ESR_EL2]
+	str	x2, [x0, #VCPU_FAR_EL2]
+	str	x3, [x0, #VCPU_HPFAR_EL2]
+
+	mov	x1, #ARM_EXCEPTION_TRAP
+	b	__guest_exit
+
+	/*
+	 * Translation failed. Just return to the guest and
+	 * let it fault again. Another CPU is probably playing
+	 * behind our back.
+	 */
+3:	restore_x0_to_x3
+
+	eret
+
+el1_irq:
+	save_x0_to_x3
+	mrs	x0, tpidr_el2
+	mov	x1, #ARM_EXCEPTION_IRQ
+	b	__guest_exit
+
+ENTRY(__hyp_do_panic)
+	mov	lr, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT |\
+		      PSR_MODE_EL1h)
+	msr	spsr_el2, lr
+	ldr	lr, =panic
+	msr	elr_el2, lr
+	eret
+ENDPROC(__hyp_do_panic)
+
+.macro invalid_vector	label, target = __hyp_panic
+	.align	2
+\label:
+	b \target
+ENDPROC(\label)
+.endm
+
+	/* None of these should ever happen */
+	invalid_vector	el2t_sync_invalid
+	invalid_vector	el2t_irq_invalid
+	invalid_vector	el2t_fiq_invalid
+	invalid_vector	el2t_error_invalid
+	invalid_vector	el2h_sync_invalid
+	invalid_vector	el2h_irq_invalid
+	invalid_vector	el2h_fiq_invalid
+	invalid_vector	el2h_error_invalid
+	invalid_vector	el1_sync_invalid
+	invalid_vector	el1_irq_invalid
+	invalid_vector	el1_fiq_invalid
+	invalid_vector	el1_error_invalid
+
+	.ltorg
+
+	.align 11
+
+ENTRY(__kvm_hyp_vector)
+	ventry	el2t_sync_invalid		// Synchronous EL2t
+	ventry	el2t_irq_invalid		// IRQ EL2t
+	ventry	el2t_fiq_invalid		// FIQ EL2t
+	ventry	el2t_error_invalid		// Error EL2t
+
+	ventry	el2h_sync_invalid		// Synchronous EL2h
+	ventry	el2h_irq_invalid		// IRQ EL2h
+	ventry	el2h_fiq_invalid		// FIQ EL2h
+	ventry	el2h_error_invalid		// Error EL2h
+
+	ventry	el1_sync			// Synchronous 64-bit EL1
+	ventry	el1_irq				// IRQ 64-bit EL1
+	ventry	el1_fiq_invalid			// FIQ 64-bit EL1
+	ventry	el1_error_invalid		// Error 64-bit EL1
+
+	ventry	el1_sync			// Synchronous 32-bit EL1
+	ventry	el1_irq				// IRQ 32-bit EL1
+	ventry	el1_fiq_invalid			// FIQ 32-bit EL1
+	ventry	el1_error_invalid		// Error 32-bit EL1
+ENDPROC(__kvm_hyp_vector)
diff --git a/arch/arm64/kvm/hyp/hyp.h b/arch/arm64/kvm/hyp/hyp.h
new file mode 100644
index 0000000..fb27517
--- /dev/null
+++ b/arch/arm64/kvm/hyp/hyp.h
@@ -0,0 +1,90 @@
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ARM64_KVM_HYP_H__
+#define __ARM64_KVM_HYP_H__
+
+#include <linux/compiler.h>
+#include <linux/kvm_host.h>
+#include <asm/kvm_mmu.h>
+#include <asm/sysreg.h>
+
+#define __hyp_text __section(.hyp.text) notrace
+
+#define kern_hyp_va(v) (typeof(v))((unsigned long)(v) & HYP_PAGE_OFFSET_MASK)
+#define hyp_kern_va(v) (typeof(v))((unsigned long)(v) - HYP_PAGE_OFFSET \
+						      + PAGE_OFFSET)
+
+/**
+ * hyp_alternate_select - Generates patchable code sequences that are
+ * used to switch between two implementations of a function, depending
+ * on the availability of a feature.
+ *
+ * @fname: a symbol name that will be defined as a function returning a
+ * function pointer whose type will match @orig and @alt
+ * @orig: A pointer to the default function, as returned by @fname when
+ * @cond doesn't hold
+ * @alt: A pointer to the alternate function, as returned by @fname
+ * when @cond holds
+ * @cond: a CPU feature (as described in asm/cpufeature.h)
+ */
+#define hyp_alternate_select(fname, orig, alt, cond)			\
+typeof(orig) * __hyp_text fname(void)					\
+{									\
+	typeof(alt) *val = orig;					\
+	asm volatile(ALTERNATIVE("nop		\n",			\
+				 "mov	%0, %1	\n",			\
+				 cond)					\
+		     : "+r" (val) : "r" (alt));				\
+	return val;							\
+}
+
+void __vgic_v2_save_state(struct kvm_vcpu *vcpu);
+void __vgic_v2_restore_state(struct kvm_vcpu *vcpu);
+
+void __vgic_v3_save_state(struct kvm_vcpu *vcpu);
+void __vgic_v3_restore_state(struct kvm_vcpu *vcpu);
+
+void __timer_save_state(struct kvm_vcpu *vcpu);
+void __timer_restore_state(struct kvm_vcpu *vcpu);
+
+void __sysreg_save_state(struct kvm_cpu_context *ctxt);
+void __sysreg_restore_state(struct kvm_cpu_context *ctxt);
+void __sysreg32_save_state(struct kvm_vcpu *vcpu);
+void __sysreg32_restore_state(struct kvm_vcpu *vcpu);
+
+void __debug_save_state(struct kvm_vcpu *vcpu,
+			struct kvm_guest_debug_arch *dbg,
+			struct kvm_cpu_context *ctxt);
+void __debug_restore_state(struct kvm_vcpu *vcpu,
+			   struct kvm_guest_debug_arch *dbg,
+			   struct kvm_cpu_context *ctxt);
+void __debug_cond_save_host_state(struct kvm_vcpu *vcpu);
+void __debug_cond_restore_host_state(struct kvm_vcpu *vcpu);
+
+void __fpsimd_save_state(struct user_fpsimd_state *fp_regs);
+void __fpsimd_restore_state(struct user_fpsimd_state *fp_regs);
+static inline bool __fpsimd_enabled(void)
+{
+	return !(read_sysreg(cptr_el2) & CPTR_EL2_TFP);
+}
+
+u64 __guest_enter(struct kvm_vcpu *vcpu, struct kvm_cpu_context *host_ctxt);
+void __noreturn __hyp_do_panic(unsigned long, ...);
+
+#endif /* __ARM64_KVM_HYP_H__ */
+
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
new file mode 100644
index 0000000..ca8f5a5
--- /dev/null
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -0,0 +1,175 @@
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "hyp.h"
+
+static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu)
+{
+	u64 val;
+
+	/*
+	 * We are about to set CPTR_EL2.TFP to trap all floating point
+	 * register accesses to EL2, however, the ARM ARM clearly states that
+	 * traps are only taken to EL2 if the operation would not otherwise
+	 * trap to EL1.  Therefore, always make sure that for 32-bit guests,
+	 * we set FPEXC.EN to prevent traps to EL1, when setting the TFP bit.
+	 */
+	val = vcpu->arch.hcr_el2;
+	if (!(val & HCR_RW)) {
+		write_sysreg(1 << 30, fpexc32_el2);
+		isb();
+	}
+	write_sysreg(val, hcr_el2);
+	/* Trap on AArch32 cp15 c15 accesses (EL1 or EL0) */
+	write_sysreg(1 << 15, hstr_el2);
+	write_sysreg(CPTR_EL2_TTA | CPTR_EL2_TFP, cptr_el2);
+	write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
+}
+
+static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu)
+{
+	write_sysreg(HCR_RW, hcr_el2);
+	write_sysreg(0, hstr_el2);
+	write_sysreg(read_sysreg(mdcr_el2) & MDCR_EL2_HPMN_MASK, mdcr_el2);
+	write_sysreg(0, cptr_el2);
+}
+
+static void __hyp_text __activate_vm(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = kern_hyp_va(vcpu->kvm);
+	write_sysreg(kvm->arch.vttbr, vttbr_el2);
+}
+
+static void __hyp_text __deactivate_vm(struct kvm_vcpu *vcpu)
+{
+	write_sysreg(0, vttbr_el2);
+}
+
+static hyp_alternate_select(__vgic_call_save_state,
+			    __vgic_v2_save_state, __vgic_v3_save_state,
+			    ARM64_HAS_SYSREG_GIC_CPUIF);
+
+static hyp_alternate_select(__vgic_call_restore_state,
+			    __vgic_v2_restore_state, __vgic_v3_restore_state,
+			    ARM64_HAS_SYSREG_GIC_CPUIF);
+
+static void __hyp_text __vgic_save_state(struct kvm_vcpu *vcpu)
+{
+	__vgic_call_save_state()(vcpu);
+	write_sysreg(read_sysreg(hcr_el2) & ~HCR_INT_OVERRIDE, hcr_el2);
+}
+
+static void __hyp_text __vgic_restore_state(struct kvm_vcpu *vcpu)
+{
+	u64 val;
+
+	val = read_sysreg(hcr_el2);
+	val |= 	HCR_INT_OVERRIDE;
+	val |= vcpu->arch.irq_lines;
+	write_sysreg(val, hcr_el2);
+
+	__vgic_call_restore_state()(vcpu);
+}
+
+static int __hyp_text __guest_run(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpu_context *host_ctxt;
+	struct kvm_cpu_context *guest_ctxt;
+	bool fp_enabled;
+	u64 exit_code;
+
+	vcpu = kern_hyp_va(vcpu);
+	write_sysreg(vcpu, tpidr_el2);
+
+	host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context);
+	guest_ctxt = &vcpu->arch.ctxt;
+
+	__sysreg_save_state(host_ctxt);
+	__debug_cond_save_host_state(vcpu);
+
+	__activate_traps(vcpu);
+	__activate_vm(vcpu);
+
+	__vgic_restore_state(vcpu);
+	__timer_restore_state(vcpu);
+
+	/*
+	 * We must restore the 32-bit state before the sysregs, thanks
+	 * to Cortex-A57 erratum #852523.
+	 */
+	__sysreg32_restore_state(vcpu);
+	__sysreg_restore_state(guest_ctxt);
+	__debug_restore_state(vcpu, kern_hyp_va(vcpu->arch.debug_ptr), guest_ctxt);
+
+	/* Jump in the fire! */
+	exit_code = __guest_enter(vcpu, host_ctxt);
+	/* And we're baaack! */
+
+	fp_enabled = __fpsimd_enabled();
+
+	__sysreg_save_state(guest_ctxt);
+	__sysreg32_save_state(vcpu);
+	__timer_save_state(vcpu);
+	__vgic_save_state(vcpu);
+
+	__deactivate_traps(vcpu);
+	__deactivate_vm(vcpu);
+
+	__sysreg_restore_state(host_ctxt);
+
+	if (fp_enabled) {
+		__fpsimd_save_state(&guest_ctxt->gp_regs.fp_regs);
+		__fpsimd_restore_state(&host_ctxt->gp_regs.fp_regs);
+	}
+
+	__debug_save_state(vcpu, kern_hyp_va(vcpu->arch.debug_ptr), guest_ctxt);
+	__debug_cond_restore_host_state(vcpu);
+
+	return exit_code;
+}
+
+__alias(__guest_run) int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
+
+static const char __hyp_panic_string[] = "HYP panic:\nPS:%08llx PC:%016llx ESR:%08llx\nFAR:%016llx HPFAR:%016llx PAR:%016llx\nVCPU:%p\n";
+
+void __hyp_text __noreturn __hyp_panic(void)
+{
+	unsigned long str_va = (unsigned long)__hyp_panic_string;
+	u64 spsr = read_sysreg(spsr_el2);
+	u64 elr = read_sysreg(elr_el2);
+	u64 par = read_sysreg(par_el1);
+
+	if (read_sysreg(vttbr_el2)) {
+		struct kvm_vcpu *vcpu;
+		struct kvm_cpu_context *host_ctxt;
+
+		vcpu = (struct kvm_vcpu *)read_sysreg(tpidr_el2);
+		host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context);
+		__deactivate_traps(vcpu);
+		__deactivate_vm(vcpu);
+		__sysreg_restore_state(host_ctxt);
+	}
+
+	/* Call panic for real */
+	__hyp_do_panic(hyp_kern_va(str_va),
+		       spsr,  elr,
+		       read_sysreg(esr_el2),   read_sysreg(far_el2),
+		       read_sysreg(hpfar_el2), par,
+		       (void *)read_sysreg(tpidr_el2));
+
+	unreachable();
+}
diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c
new file mode 100644
index 0000000..42563098
--- /dev/null
+++ b/arch/arm64/kvm/hyp/sysreg-sr.c
@@ -0,0 +1,138 @@
+/*
+ * Copyright (C) 2012-2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/compiler.h>
+#include <linux/kvm_host.h>
+
+#include <asm/kvm_asm.h>
+#include <asm/kvm_mmu.h>
+
+#include "hyp.h"
+
+/* ctxt is already in the HYP VA space */
+void __hyp_text __sysreg_save_state(struct kvm_cpu_context *ctxt)
+{
+	ctxt->sys_regs[MPIDR_EL1]	= read_sysreg(vmpidr_el2);
+	ctxt->sys_regs[CSSELR_EL1]	= read_sysreg(csselr_el1);
+	ctxt->sys_regs[SCTLR_EL1]	= read_sysreg(sctlr_el1);
+	ctxt->sys_regs[ACTLR_EL1]	= read_sysreg(actlr_el1);
+	ctxt->sys_regs[CPACR_EL1]	= read_sysreg(cpacr_el1);
+	ctxt->sys_regs[TTBR0_EL1]	= read_sysreg(ttbr0_el1);
+	ctxt->sys_regs[TTBR1_EL1]	= read_sysreg(ttbr1_el1);
+	ctxt->sys_regs[TCR_EL1]		= read_sysreg(tcr_el1);
+	ctxt->sys_regs[ESR_EL1]		= read_sysreg(esr_el1);
+	ctxt->sys_regs[AFSR0_EL1]	= read_sysreg(afsr0_el1);
+	ctxt->sys_regs[AFSR1_EL1]	= read_sysreg(afsr1_el1);
+	ctxt->sys_regs[FAR_EL1]		= read_sysreg(far_el1);
+	ctxt->sys_regs[MAIR_EL1]	= read_sysreg(mair_el1);
+	ctxt->sys_regs[VBAR_EL1]	= read_sysreg(vbar_el1);
+	ctxt->sys_regs[CONTEXTIDR_EL1]	= read_sysreg(contextidr_el1);
+	ctxt->sys_regs[TPIDR_EL0]	= read_sysreg(tpidr_el0);
+	ctxt->sys_regs[TPIDRRO_EL0]	= read_sysreg(tpidrro_el0);
+	ctxt->sys_regs[TPIDR_EL1]	= read_sysreg(tpidr_el1);
+	ctxt->sys_regs[AMAIR_EL1]	= read_sysreg(amair_el1);
+	ctxt->sys_regs[CNTKCTL_EL1]	= read_sysreg(cntkctl_el1);
+	ctxt->sys_regs[PAR_EL1]		= read_sysreg(par_el1);
+	ctxt->sys_regs[MDSCR_EL1]	= read_sysreg(mdscr_el1);
+
+	ctxt->gp_regs.regs.sp		= read_sysreg(sp_el0);
+	ctxt->gp_regs.regs.pc		= read_sysreg(elr_el2);
+	ctxt->gp_regs.regs.pstate	= read_sysreg(spsr_el2);
+	ctxt->gp_regs.sp_el1		= read_sysreg(sp_el1);
+	ctxt->gp_regs.elr_el1		= read_sysreg(elr_el1);
+	ctxt->gp_regs.spsr[KVM_SPSR_EL1]= read_sysreg(spsr_el1);
+}
+
+void __hyp_text __sysreg_restore_state(struct kvm_cpu_context *ctxt)
+{
+	write_sysreg(ctxt->sys_regs[MPIDR_EL1],	  vmpidr_el2);
+	write_sysreg(ctxt->sys_regs[CSSELR_EL1],  csselr_el1);
+	write_sysreg(ctxt->sys_regs[SCTLR_EL1],	  sctlr_el1);
+	write_sysreg(ctxt->sys_regs[ACTLR_EL1],	  actlr_el1);
+	write_sysreg(ctxt->sys_regs[CPACR_EL1],	  cpacr_el1);
+	write_sysreg(ctxt->sys_regs[TTBR0_EL1],	  ttbr0_el1);
+	write_sysreg(ctxt->sys_regs[TTBR1_EL1],	  ttbr1_el1);
+	write_sysreg(ctxt->sys_regs[TCR_EL1],	  tcr_el1);
+	write_sysreg(ctxt->sys_regs[ESR_EL1],	  esr_el1);
+	write_sysreg(ctxt->sys_regs[AFSR0_EL1],	  afsr0_el1);
+	write_sysreg(ctxt->sys_regs[AFSR1_EL1],	  afsr1_el1);
+	write_sysreg(ctxt->sys_regs[FAR_EL1],	  far_el1);
+	write_sysreg(ctxt->sys_regs[MAIR_EL1],	  mair_el1);
+	write_sysreg(ctxt->sys_regs[VBAR_EL1],	  vbar_el1);
+	write_sysreg(ctxt->sys_regs[CONTEXTIDR_EL1], contextidr_el1);
+	write_sysreg(ctxt->sys_regs[TPIDR_EL0],	  tpidr_el0);
+	write_sysreg(ctxt->sys_regs[TPIDRRO_EL0], tpidrro_el0);
+	write_sysreg(ctxt->sys_regs[TPIDR_EL1],	  tpidr_el1);
+	write_sysreg(ctxt->sys_regs[AMAIR_EL1],	  amair_el1);
+	write_sysreg(ctxt->sys_regs[CNTKCTL_EL1], cntkctl_el1);
+	write_sysreg(ctxt->sys_regs[PAR_EL1],	  par_el1);
+	write_sysreg(ctxt->sys_regs[MDSCR_EL1],	  mdscr_el1);
+
+	write_sysreg(ctxt->gp_regs.regs.sp,	sp_el0);
+	write_sysreg(ctxt->gp_regs.regs.pc,	elr_el2);
+	write_sysreg(ctxt->gp_regs.regs.pstate,	spsr_el2);
+	write_sysreg(ctxt->gp_regs.sp_el1,	sp_el1);
+	write_sysreg(ctxt->gp_regs.elr_el1,	elr_el1);
+	write_sysreg(ctxt->gp_regs.spsr[KVM_SPSR_EL1], spsr_el1);
+}
+
+void __hyp_text __sysreg32_save_state(struct kvm_vcpu *vcpu)
+{
+	u64 *spsr, *sysreg;
+
+	if (read_sysreg(hcr_el2) & HCR_RW)
+		return;
+
+	spsr = vcpu->arch.ctxt.gp_regs.spsr;
+	sysreg = vcpu->arch.ctxt.sys_regs;
+
+	spsr[KVM_SPSR_ABT] = read_sysreg(spsr_abt);
+	spsr[KVM_SPSR_UND] = read_sysreg(spsr_und);
+	spsr[KVM_SPSR_IRQ] = read_sysreg(spsr_irq);
+	spsr[KVM_SPSR_FIQ] = read_sysreg(spsr_fiq);
+
+	sysreg[DACR32_EL2] = read_sysreg(dacr32_el2);
+	sysreg[IFSR32_EL2] = read_sysreg(ifsr32_el2);
+
+	if (__fpsimd_enabled())
+		sysreg[FPEXC32_EL2] = read_sysreg(fpexc32_el2);
+
+	if (vcpu->arch.debug_flags & KVM_ARM64_DEBUG_DIRTY)
+		sysreg[DBGVCR32_EL2] = read_sysreg(dbgvcr32_el2);
+}
+
+void __hyp_text __sysreg32_restore_state(struct kvm_vcpu *vcpu)
+{
+	u64 *spsr, *sysreg;
+
+	if (read_sysreg(hcr_el2) & HCR_RW)
+		return;
+
+	spsr = vcpu->arch.ctxt.gp_regs.spsr;
+	sysreg = vcpu->arch.ctxt.sys_regs;
+
+	write_sysreg(spsr[KVM_SPSR_ABT], spsr_abt);
+	write_sysreg(spsr[KVM_SPSR_UND], spsr_und);
+	write_sysreg(spsr[KVM_SPSR_IRQ], spsr_irq);
+	write_sysreg(spsr[KVM_SPSR_FIQ], spsr_fiq);
+
+	write_sysreg(sysreg[DACR32_EL2], dacr32_el2);
+	write_sysreg(sysreg[IFSR32_EL2], ifsr32_el2);
+
+	if (vcpu->arch.debug_flags & KVM_ARM64_DEBUG_DIRTY)
+		write_sysreg(sysreg[DBGVCR32_EL2], dbgvcr32_el2);
+}
diff --git a/arch/arm64/kvm/hyp/timer-sr.c b/arch/arm64/kvm/hyp/timer-sr.c
new file mode 100644
index 0000000..1051e5d
--- /dev/null
+++ b/arch/arm64/kvm/hyp/timer-sr.c
@@ -0,0 +1,71 @@
+/*
+ * Copyright (C) 2012-2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <clocksource/arm_arch_timer.h>
+#include <linux/compiler.h>
+#include <linux/kvm_host.h>
+
+#include <asm/kvm_mmu.h>
+
+#include "hyp.h"
+
+/* vcpu is already in the HYP VA space */
+void __hyp_text __timer_save_state(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = kern_hyp_va(vcpu->kvm);
+	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
+	u64 val;
+
+	if (kvm->arch.timer.enabled) {
+		timer->cntv_ctl = read_sysreg(cntv_ctl_el0);
+		timer->cntv_cval = read_sysreg(cntv_cval_el0);
+	}
+
+	/* Disable the virtual timer */
+	write_sysreg(0, cntv_ctl_el0);
+
+	/* Allow physical timer/counter access for the host */
+	val = read_sysreg(cnthctl_el2);
+	val |= CNTHCTL_EL1PCTEN | CNTHCTL_EL1PCEN;
+	write_sysreg(val, cnthctl_el2);
+
+	/* Clear cntvoff for the host */
+	write_sysreg(0, cntvoff_el2);
+}
+
+void __hyp_text __timer_restore_state(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = kern_hyp_va(vcpu->kvm);
+	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
+	u64 val;
+
+	/*
+	 * Disallow physical timer access for the guest
+	 * Physical counter access is allowed
+	 */
+	val = read_sysreg(cnthctl_el2);
+	val &= ~CNTHCTL_EL1PCEN;
+	val |= CNTHCTL_EL1PCTEN;
+	write_sysreg(val, cnthctl_el2);
+
+	if (kvm->arch.timer.enabled) {
+		write_sysreg(kvm->arch.timer.cntvoff, cntvoff_el2);
+		write_sysreg(timer->cntv_cval, cntv_cval_el0);
+		isb();
+		write_sysreg(timer->cntv_ctl, cntv_ctl_el0);
+	}
+}
diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c
new file mode 100644
index 0000000..2a7e0d8
--- /dev/null
+++ b/arch/arm64/kvm/hyp/tlb.c
@@ -0,0 +1,80 @@
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "hyp.h"
+
+static void __hyp_text __tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
+{
+	dsb(ishst);
+
+	/* Switch to requested VMID */
+	kvm = kern_hyp_va(kvm);
+	write_sysreg(kvm->arch.vttbr, vttbr_el2);
+	isb();
+
+	/*
+	 * We could do so much better if we had the VA as well.
+	 * Instead, we invalidate Stage-2 for this IPA, and the
+	 * whole of Stage-1. Weep...
+	 */
+	ipa >>= 12;
+	asm volatile("tlbi ipas2e1is, %0" : : "r" (ipa));
+
+	/*
+	 * We have to ensure completion of the invalidation at Stage-2,
+	 * since a table walk on another CPU could refill a TLB with a
+	 * complete (S1 + S2) walk based on the old Stage-2 mapping if
+	 * the Stage-1 invalidation happened first.
+	 */
+	dsb(ish);
+	asm volatile("tlbi vmalle1is" : : );
+	dsb(ish);
+	isb();
+
+	write_sysreg(0, vttbr_el2);
+}
+
+__alias(__tlb_flush_vmid_ipa) void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm,
+							    phys_addr_t ipa);
+
+static void __hyp_text __tlb_flush_vmid(struct kvm *kvm)
+{
+	dsb(ishst);
+
+	/* Switch to requested VMID */
+	kvm = kern_hyp_va(kvm);
+	write_sysreg(kvm->arch.vttbr, vttbr_el2);
+	isb();
+
+	asm volatile("tlbi vmalls12e1is" : : );
+	dsb(ish);
+	isb();
+
+	write_sysreg(0, vttbr_el2);
+}
+
+__alias(__tlb_flush_vmid) void __kvm_tlb_flush_vmid(struct kvm *kvm);
+
+static void __hyp_text __tlb_flush_vm_context(void)
+{
+	dsb(ishst);
+	asm volatile("tlbi alle1is	\n"
+		     "ic ialluis	  ": : );
+	dsb(ish);
+}
+
+__alias(__tlb_flush_vm_context) void __kvm_flush_vm_context(void);
diff --git a/arch/arm64/kvm/hyp/vgic-v2-sr.c b/arch/arm64/kvm/hyp/vgic-v2-sr.c
new file mode 100644
index 0000000..e717612
--- /dev/null
+++ b/arch/arm64/kvm/hyp/vgic-v2-sr.c
@@ -0,0 +1,84 @@
+/*
+ * Copyright (C) 2012-2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/compiler.h>
+#include <linux/irqchip/arm-gic.h>
+#include <linux/kvm_host.h>
+
+#include <asm/kvm_mmu.h>
+
+#include "hyp.h"
+
+/* vcpu is already in the HYP VA space */
+void __hyp_text __vgic_v2_save_state(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = kern_hyp_va(vcpu->kvm);
+	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
+	struct vgic_dist *vgic = &kvm->arch.vgic;
+	void __iomem *base = kern_hyp_va(vgic->vctrl_base);
+	u32 eisr0, eisr1, elrsr0, elrsr1;
+	int i, nr_lr;
+
+	if (!base)
+		return;
+
+	nr_lr = vcpu->arch.vgic_cpu.nr_lr;
+	cpu_if->vgic_vmcr = readl_relaxed(base + GICH_VMCR);
+	cpu_if->vgic_misr = readl_relaxed(base + GICH_MISR);
+	eisr0  = readl_relaxed(base + GICH_EISR0);
+	elrsr0 = readl_relaxed(base + GICH_ELRSR0);
+	if (unlikely(nr_lr > 32)) {
+		eisr1  = readl_relaxed(base + GICH_EISR1);
+		elrsr1 = readl_relaxed(base + GICH_ELRSR1);
+	} else {
+		eisr1 = elrsr1 = 0;
+	}
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	cpu_if->vgic_eisr  = ((u64)eisr0 << 32) | eisr1;
+	cpu_if->vgic_elrsr = ((u64)elrsr0 << 32) | elrsr1;
+#else
+	cpu_if->vgic_eisr  = ((u64)eisr1 << 32) | eisr0;
+	cpu_if->vgic_elrsr = ((u64)elrsr1 << 32) | elrsr0;
+#endif
+	cpu_if->vgic_apr    = readl_relaxed(base + GICH_APR);
+
+	writel_relaxed(0, base + GICH_HCR);
+
+	for (i = 0; i < nr_lr; i++)
+		cpu_if->vgic_lr[i] = readl_relaxed(base + GICH_LR0 + (i * 4));
+}
+
+/* vcpu is already in the HYP VA space */
+void __hyp_text __vgic_v2_restore_state(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = kern_hyp_va(vcpu->kvm);
+	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
+	struct vgic_dist *vgic = &kvm->arch.vgic;
+	void __iomem *base = kern_hyp_va(vgic->vctrl_base);
+	int i, nr_lr;
+
+	if (!base)
+		return;
+
+	writel_relaxed(cpu_if->vgic_hcr, base + GICH_HCR);
+	writel_relaxed(cpu_if->vgic_vmcr, base + GICH_VMCR);
+	writel_relaxed(cpu_if->vgic_apr, base + GICH_APR);
+
+	nr_lr = vcpu->arch.vgic_cpu.nr_lr;
+	for (i = 0; i < nr_lr; i++)
+		writel_relaxed(cpu_if->vgic_lr[i], base + GICH_LR0 + (i * 4));
+}
diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c
new file mode 100644
index 0000000..9142e08
--- /dev/null
+++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c
@@ -0,0 +1,228 @@
+/*
+ * Copyright (C) 2012-2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/compiler.h>
+#include <linux/irqchip/arm-gic-v3.h>
+#include <linux/kvm_host.h>
+
+#include <asm/kvm_mmu.h>
+
+#include "hyp.h"
+
+#define vtr_to_max_lr_idx(v)		((v) & 0xf)
+#define vtr_to_nr_pri_bits(v)		(((u32)(v) >> 29) + 1)
+
+#define read_gicreg(r)							\
+	({								\
+		u64 reg;						\
+		asm volatile("mrs_s %0, " __stringify(r) : "=r" (reg));	\
+		reg;							\
+	})
+
+#define write_gicreg(v,r)						\
+	do {								\
+		u64 __val = (v);					\
+		asm volatile("msr_s " __stringify(r) ", %0" : : "r" (__val));\
+	} while (0)
+
+/* vcpu is already in the HYP VA space */
+void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu)
+{
+	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
+	u64 val;
+	u32 max_lr_idx, nr_pri_bits;
+
+	/*
+	 * Make sure stores to the GIC via the memory mapped interface
+	 * are now visible to the system register interface.
+	 */
+	dsb(st);
+
+	cpu_if->vgic_vmcr  = read_gicreg(ICH_VMCR_EL2);
+	cpu_if->vgic_misr  = read_gicreg(ICH_MISR_EL2);
+	cpu_if->vgic_eisr  = read_gicreg(ICH_EISR_EL2);
+	cpu_if->vgic_elrsr = read_gicreg(ICH_ELSR_EL2);
+
+	write_gicreg(0, ICH_HCR_EL2);
+	val = read_gicreg(ICH_VTR_EL2);
+	max_lr_idx = vtr_to_max_lr_idx(val);
+	nr_pri_bits = vtr_to_nr_pri_bits(val);
+
+	switch (max_lr_idx) {
+	case 15:
+		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(15)] = read_gicreg(ICH_LR15_EL2);
+	case 14:
+		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(14)] = read_gicreg(ICH_LR14_EL2);
+	case 13:
+		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(13)] = read_gicreg(ICH_LR13_EL2);
+	case 12:
+		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(12)] = read_gicreg(ICH_LR12_EL2);
+	case 11:
+		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(11)] = read_gicreg(ICH_LR11_EL2);
+	case 10:
+		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(10)] = read_gicreg(ICH_LR10_EL2);
+	case 9:
+		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(9)] = read_gicreg(ICH_LR9_EL2);
+	case 8:
+		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(8)] = read_gicreg(ICH_LR8_EL2);
+	case 7:
+		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(7)] = read_gicreg(ICH_LR7_EL2);
+	case 6:
+		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(6)] = read_gicreg(ICH_LR6_EL2);
+	case 5:
+		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(5)] = read_gicreg(ICH_LR5_EL2);
+	case 4:
+		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(4)] = read_gicreg(ICH_LR4_EL2);
+	case 3:
+		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(3)] = read_gicreg(ICH_LR3_EL2);
+	case 2:
+		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(2)] = read_gicreg(ICH_LR2_EL2);
+	case 1:
+		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(1)] = read_gicreg(ICH_LR1_EL2);
+	case 0:
+		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(0)] = read_gicreg(ICH_LR0_EL2);
+	}
+
+	switch (nr_pri_bits) {
+	case 7:
+		cpu_if->vgic_ap0r[3] = read_gicreg(ICH_AP0R3_EL2);
+		cpu_if->vgic_ap0r[2] = read_gicreg(ICH_AP0R2_EL2);
+	case 6:
+		cpu_if->vgic_ap0r[1] = read_gicreg(ICH_AP0R1_EL2);
+	default:
+		cpu_if->vgic_ap0r[0] = read_gicreg(ICH_AP0R0_EL2);
+	}
+
+	switch (nr_pri_bits) {
+	case 7:
+		cpu_if->vgic_ap1r[3] = read_gicreg(ICH_AP1R3_EL2);
+		cpu_if->vgic_ap1r[2] = read_gicreg(ICH_AP1R2_EL2);
+	case 6:
+		cpu_if->vgic_ap1r[1] = read_gicreg(ICH_AP1R1_EL2);
+	default:
+		cpu_if->vgic_ap1r[0] = read_gicreg(ICH_AP1R0_EL2);
+	}
+
+	val = read_gicreg(ICC_SRE_EL2);
+	write_gicreg(val | ICC_SRE_EL2_ENABLE, ICC_SRE_EL2);
+	isb(); /* Make sure ENABLE is set at EL2 before setting SRE at EL1 */
+	write_gicreg(1, ICC_SRE_EL1);
+}
+
+void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
+{
+	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
+	u64 val;
+	u32 max_lr_idx, nr_pri_bits;
+
+	/*
+	 * VFIQEn is RES1 if ICC_SRE_EL1.SRE is 1. This causes a
+	 * Group0 interrupt (as generated in GICv2 mode) to be
+	 * delivered as a FIQ to the guest, with potentially fatal
+	 * consequences. So we must make sure that ICC_SRE_EL1 has
+	 * been actually programmed with the value we want before
+	 * starting to mess with the rest of the GIC.
+	 */
+	write_gicreg(cpu_if->vgic_sre, ICC_SRE_EL1);
+	isb();
+
+	write_gicreg(cpu_if->vgic_hcr, ICH_HCR_EL2);
+	write_gicreg(cpu_if->vgic_vmcr, ICH_VMCR_EL2);
+
+	val = read_gicreg(ICH_VTR_EL2);
+	max_lr_idx = vtr_to_max_lr_idx(val);
+	nr_pri_bits = vtr_to_nr_pri_bits(val);
+
+	switch (nr_pri_bits) {
+	case 7:
+		 write_gicreg(cpu_if->vgic_ap1r[3], ICH_AP1R3_EL2);
+		 write_gicreg(cpu_if->vgic_ap1r[2], ICH_AP1R2_EL2);
+	case 6:
+		 write_gicreg(cpu_if->vgic_ap1r[1], ICH_AP1R1_EL2);
+	default:
+		 write_gicreg(cpu_if->vgic_ap1r[0], ICH_AP1R0_EL2);
+	}	 	                           
+		 	                           
+	switch (nr_pri_bits) {
+	case 7:
+		 write_gicreg(cpu_if->vgic_ap0r[3], ICH_AP0R3_EL2);
+		 write_gicreg(cpu_if->vgic_ap0r[2], ICH_AP0R2_EL2);
+	case 6:
+		 write_gicreg(cpu_if->vgic_ap0r[1], ICH_AP0R1_EL2);
+	default:
+		 write_gicreg(cpu_if->vgic_ap0r[0], ICH_AP0R0_EL2);
+	}
+
+	switch (max_lr_idx) {
+	case 15:
+		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(15)], ICH_LR15_EL2);
+	case 14:
+		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(14)], ICH_LR14_EL2);
+	case 13:
+		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(13)], ICH_LR13_EL2);
+	case 12:
+		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(12)], ICH_LR12_EL2);
+	case 11:
+		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(11)], ICH_LR11_EL2);
+	case 10:
+		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(10)], ICH_LR10_EL2);
+	case 9:
+		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(9)], ICH_LR9_EL2);
+	case 8:
+		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(8)], ICH_LR8_EL2);
+	case 7:
+		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(7)], ICH_LR7_EL2);
+	case 6:
+		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(6)], ICH_LR6_EL2);
+	case 5:
+		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(5)], ICH_LR5_EL2);
+	case 4:
+		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(4)], ICH_LR4_EL2);
+	case 3:
+		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(3)], ICH_LR3_EL2);
+	case 2:
+		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(2)], ICH_LR2_EL2);
+	case 1:
+		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(1)], ICH_LR1_EL2);
+	case 0:
+		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(0)], ICH_LR0_EL2);
+	}
+
+	/*
+	 * Ensures that the above will have reached the
+	 * (re)distributors. This ensure the guest will read the
+	 * correct values from the memory-mapped interface.
+	 */
+	isb();
+	dsb(sy);
+
+	/*
+	 * Prevent the guest from touching the GIC system registers if
+	 * SRE isn't enabled for GICv3 emulation.
+	 */
+	if (!cpu_if->vgic_sre) {
+		write_gicreg(read_gicreg(ICC_SRE_EL2) & ~ICC_SRE_EL2_ENABLE,
+			     ICC_SRE_EL2);
+	}
+}
+
+static u64 __hyp_text __vgic_v3_read_ich_vtr_el2(void)
+{
+	return read_gicreg(ICH_VTR_EL2);
+}
+
+__alias(__vgic_v3_read_ich_vtr_el2) u64 __vgic_v3_get_ich_vtr_el2(void);
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index d2650e8..eec3598b 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -29,6 +29,7 @@
 #include <asm/debug-monitors.h>
 #include <asm/esr.h>
 #include <asm/kvm_arm.h>
+#include <asm/kvm_asm.h>
 #include <asm/kvm_coproc.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_host.h>
@@ -219,9 +220,9 @@
  * All writes will set the KVM_ARM64_DEBUG_DIRTY flag to ensure the
  * hyp.S code switches between host and guest values in future.
  */
-static inline void reg_to_dbg(struct kvm_vcpu *vcpu,
-			      struct sys_reg_params *p,
-			      u64 *dbg_reg)
+static void reg_to_dbg(struct kvm_vcpu *vcpu,
+		       struct sys_reg_params *p,
+		       u64 *dbg_reg)
 {
 	u64 val = p->regval;
 
@@ -234,18 +235,18 @@
 	vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
 }
 
-static inline void dbg_to_reg(struct kvm_vcpu *vcpu,
-			      struct sys_reg_params *p,
-			      u64 *dbg_reg)
+static void dbg_to_reg(struct kvm_vcpu *vcpu,
+		       struct sys_reg_params *p,
+		       u64 *dbg_reg)
 {
 	p->regval = *dbg_reg;
 	if (p->is_32bit)
 		p->regval &= 0xffffffffUL;
 }
 
-static inline bool trap_bvr(struct kvm_vcpu *vcpu,
-			    struct sys_reg_params *p,
-			    const struct sys_reg_desc *rd)
+static bool trap_bvr(struct kvm_vcpu *vcpu,
+		     struct sys_reg_params *p,
+		     const struct sys_reg_desc *rd)
 {
 	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg];
 
@@ -279,15 +280,15 @@
 	return 0;
 }
 
-static inline void reset_bvr(struct kvm_vcpu *vcpu,
-			     const struct sys_reg_desc *rd)
+static void reset_bvr(struct kvm_vcpu *vcpu,
+		      const struct sys_reg_desc *rd)
 {
 	vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg] = rd->val;
 }
 
-static inline bool trap_bcr(struct kvm_vcpu *vcpu,
-			    struct sys_reg_params *p,
-			    const struct sys_reg_desc *rd)
+static bool trap_bcr(struct kvm_vcpu *vcpu,
+		     struct sys_reg_params *p,
+		     const struct sys_reg_desc *rd)
 {
 	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg];
 
@@ -322,15 +323,15 @@
 	return 0;
 }
 
-static inline void reset_bcr(struct kvm_vcpu *vcpu,
-			     const struct sys_reg_desc *rd)
+static void reset_bcr(struct kvm_vcpu *vcpu,
+		      const struct sys_reg_desc *rd)
 {
 	vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg] = rd->val;
 }
 
-static inline bool trap_wvr(struct kvm_vcpu *vcpu,
-			    struct sys_reg_params *p,
-			    const struct sys_reg_desc *rd)
+static bool trap_wvr(struct kvm_vcpu *vcpu,
+		     struct sys_reg_params *p,
+		     const struct sys_reg_desc *rd)
 {
 	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg];
 
@@ -365,15 +366,15 @@
 	return 0;
 }
 
-static inline void reset_wvr(struct kvm_vcpu *vcpu,
-			     const struct sys_reg_desc *rd)
+static void reset_wvr(struct kvm_vcpu *vcpu,
+		      const struct sys_reg_desc *rd)
 {
 	vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg] = rd->val;
 }
 
-static inline bool trap_wcr(struct kvm_vcpu *vcpu,
-			    struct sys_reg_params *p,
-			    const struct sys_reg_desc *rd)
+static bool trap_wcr(struct kvm_vcpu *vcpu,
+		     struct sys_reg_params *p,
+		     const struct sys_reg_desc *rd)
 {
 	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg];
 
@@ -407,8 +408,8 @@
 	return 0;
 }
 
-static inline void reset_wcr(struct kvm_vcpu *vcpu,
-			     const struct sys_reg_desc *rd)
+static void reset_wcr(struct kvm_vcpu *vcpu,
+		      const struct sys_reg_desc *rd)
 {
 	vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg] = rd->val;
 }
@@ -722,9 +723,9 @@
  * system is in.
  */
 
-static inline bool trap_xvr(struct kvm_vcpu *vcpu,
-			    struct sys_reg_params *p,
-			    const struct sys_reg_desc *rd)
+static bool trap_xvr(struct kvm_vcpu *vcpu,
+		     struct sys_reg_params *p,
+		     const struct sys_reg_desc *rd)
 {
 	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg];
 
diff --git a/arch/arm64/kvm/vgic-v2-switch.S b/arch/arm64/kvm/vgic-v2-switch.S
deleted file mode 100644
index 3f00071..0000000
--- a/arch/arm64/kvm/vgic-v2-switch.S
+++ /dev/null
@@ -1,134 +0,0 @@
-/*
- * Copyright (C) 2012,2013 - ARM Ltd
- * Author: Marc Zyngier <marc.zyngier@arm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include <linux/linkage.h>
-#include <linux/irqchip/arm-gic.h>
-
-#include <asm/assembler.h>
-#include <asm/memory.h>
-#include <asm/asm-offsets.h>
-#include <asm/kvm.h>
-#include <asm/kvm_asm.h>
-#include <asm/kvm_arm.h>
-#include <asm/kvm_mmu.h>
-
-	.text
-	.pushsection	.hyp.text, "ax"
-
-/*
- * Save the VGIC CPU state into memory
- * x0: Register pointing to VCPU struct
- * Do not corrupt x1!!!
- */
-ENTRY(__save_vgic_v2_state)
-__save_vgic_v2_state:
-	/* Get VGIC VCTRL base into x2 */
-	ldr	x2, [x0, #VCPU_KVM]
-	kern_hyp_va	x2
-	ldr	x2, [x2, #KVM_VGIC_VCTRL]
-	kern_hyp_va	x2
-	cbz	x2, 2f		// disabled
-
-	/* Compute the address of struct vgic_cpu */
-	add	x3, x0, #VCPU_VGIC_CPU
-
-	/* Save all interesting registers */
-	ldr	w5, [x2, #GICH_VMCR]
-	ldr	w6, [x2, #GICH_MISR]
-	ldr	w7, [x2, #GICH_EISR0]
-	ldr	w8, [x2, #GICH_EISR1]
-	ldr	w9, [x2, #GICH_ELRSR0]
-	ldr	w10, [x2, #GICH_ELRSR1]
-	ldr	w11, [x2, #GICH_APR]
-CPU_BE(	rev	w5,  w5  )
-CPU_BE(	rev	w6,  w6  )
-CPU_BE(	rev	w7,  w7  )
-CPU_BE(	rev	w8,  w8  )
-CPU_BE(	rev	w9,  w9  )
-CPU_BE(	rev	w10, w10 )
-CPU_BE(	rev	w11, w11 )
-
-	str	w5, [x3, #VGIC_V2_CPU_VMCR]
-	str	w6, [x3, #VGIC_V2_CPU_MISR]
-CPU_LE(	str	w7, [x3, #VGIC_V2_CPU_EISR] )
-CPU_LE(	str	w8, [x3, #(VGIC_V2_CPU_EISR + 4)] )
-CPU_LE(	str	w9, [x3, #VGIC_V2_CPU_ELRSR] )
-CPU_LE(	str	w10, [x3, #(VGIC_V2_CPU_ELRSR + 4)] )
-CPU_BE(	str	w7, [x3, #(VGIC_V2_CPU_EISR + 4)] )
-CPU_BE(	str	w8, [x3, #VGIC_V2_CPU_EISR] )
-CPU_BE(	str	w9, [x3, #(VGIC_V2_CPU_ELRSR + 4)] )
-CPU_BE(	str	w10, [x3, #VGIC_V2_CPU_ELRSR] )
-	str	w11, [x3, #VGIC_V2_CPU_APR]
-
-	/* Clear GICH_HCR */
-	str	wzr, [x2, #GICH_HCR]
-
-	/* Save list registers */
-	add	x2, x2, #GICH_LR0
-	ldr	w4, [x3, #VGIC_CPU_NR_LR]
-	add	x3, x3, #VGIC_V2_CPU_LR
-1:	ldr	w5, [x2], #4
-CPU_BE(	rev	w5, w5 )
-	str	w5, [x3], #4
-	sub	w4, w4, #1
-	cbnz	w4, 1b
-2:
-	ret
-ENDPROC(__save_vgic_v2_state)
-
-/*
- * Restore the VGIC CPU state from memory
- * x0: Register pointing to VCPU struct
- */
-ENTRY(__restore_vgic_v2_state)
-__restore_vgic_v2_state:
-	/* Get VGIC VCTRL base into x2 */
-	ldr	x2, [x0, #VCPU_KVM]
-	kern_hyp_va	x2
-	ldr	x2, [x2, #KVM_VGIC_VCTRL]
-	kern_hyp_va	x2
-	cbz	x2, 2f		// disabled
-
-	/* Compute the address of struct vgic_cpu */
-	add	x3, x0, #VCPU_VGIC_CPU
-
-	/* We only restore a minimal set of registers */
-	ldr	w4, [x3, #VGIC_V2_CPU_HCR]
-	ldr	w5, [x3, #VGIC_V2_CPU_VMCR]
-	ldr	w6, [x3, #VGIC_V2_CPU_APR]
-CPU_BE(	rev	w4, w4 )
-CPU_BE(	rev	w5, w5 )
-CPU_BE(	rev	w6, w6 )
-
-	str	w4, [x2, #GICH_HCR]
-	str	w5, [x2, #GICH_VMCR]
-	str	w6, [x2, #GICH_APR]
-
-	/* Restore list registers */
-	add	x2, x2, #GICH_LR0
-	ldr	w4, [x3, #VGIC_CPU_NR_LR]
-	add	x3, x3, #VGIC_V2_CPU_LR
-1:	ldr	w5, [x3], #4
-CPU_BE(	rev	w5, w5 )
-	str	w5, [x2], #4
-	sub	w4, w4, #1
-	cbnz	w4, 1b
-2:
-	ret
-ENDPROC(__restore_vgic_v2_state)
-
-	.popsection
diff --git a/arch/arm64/kvm/vgic-v3-switch.S b/arch/arm64/kvm/vgic-v3-switch.S
deleted file mode 100644
index 3c20730..0000000
--- a/arch/arm64/kvm/vgic-v3-switch.S
+++ /dev/null
@@ -1,269 +0,0 @@
-/*
- * Copyright (C) 2012,2013 - ARM Ltd
- * Author: Marc Zyngier <marc.zyngier@arm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include <linux/linkage.h>
-#include <linux/irqchip/arm-gic-v3.h>
-
-#include <asm/assembler.h>
-#include <asm/memory.h>
-#include <asm/asm-offsets.h>
-#include <asm/kvm.h>
-#include <asm/kvm_asm.h>
-#include <asm/kvm_arm.h>
-
-	.text
-	.pushsection	.hyp.text, "ax"
-
-/*
- * We store LRs in reverse order to let the CPU deal with streaming
- * access. Use this macro to make it look saner...
- */
-#define LR_OFFSET(n)	(VGIC_V3_CPU_LR + (15 - n) * 8)
-
-/*
- * Save the VGIC CPU state into memory
- * x0: Register pointing to VCPU struct
- * Do not corrupt x1!!!
- */
-.macro	save_vgic_v3_state
-	// Compute the address of struct vgic_cpu
-	add	x3, x0, #VCPU_VGIC_CPU
-
-	// Make sure stores to the GIC via the memory mapped interface
-	// are now visible to the system register interface
-	dsb	st
-
-	// Save all interesting registers
-	mrs_s	x5, ICH_VMCR_EL2
-	mrs_s	x6, ICH_MISR_EL2
-	mrs_s	x7, ICH_EISR_EL2
-	mrs_s	x8, ICH_ELSR_EL2
-
-	str	w5, [x3, #VGIC_V3_CPU_VMCR]
-	str	w6, [x3, #VGIC_V3_CPU_MISR]
-	str	w7, [x3, #VGIC_V3_CPU_EISR]
-	str	w8, [x3, #VGIC_V3_CPU_ELRSR]
-
-	msr_s	ICH_HCR_EL2, xzr
-
-	mrs_s	x21, ICH_VTR_EL2
-	mvn	w22, w21
-	ubfiz	w23, w22, 2, 4	// w23 = (15 - ListRegs) * 4
-
-	adr	x24, 1f
-	add	x24, x24, x23
-	br	x24
-
-1:
-	mrs_s	x20, ICH_LR15_EL2
-	mrs_s	x19, ICH_LR14_EL2
-	mrs_s	x18, ICH_LR13_EL2
-	mrs_s	x17, ICH_LR12_EL2
-	mrs_s	x16, ICH_LR11_EL2
-	mrs_s	x15, ICH_LR10_EL2
-	mrs_s	x14, ICH_LR9_EL2
-	mrs_s	x13, ICH_LR8_EL2
-	mrs_s	x12, ICH_LR7_EL2
-	mrs_s	x11, ICH_LR6_EL2
-	mrs_s	x10, ICH_LR5_EL2
-	mrs_s	x9, ICH_LR4_EL2
-	mrs_s	x8, ICH_LR3_EL2
-	mrs_s	x7, ICH_LR2_EL2
-	mrs_s	x6, ICH_LR1_EL2
-	mrs_s	x5, ICH_LR0_EL2
-
-	adr	x24, 1f
-	add	x24, x24, x23
-	br	x24
-
-1:
-	str	x20, [x3, #LR_OFFSET(15)]
-	str	x19, [x3, #LR_OFFSET(14)]
-	str	x18, [x3, #LR_OFFSET(13)]
-	str	x17, [x3, #LR_OFFSET(12)]
-	str	x16, [x3, #LR_OFFSET(11)]
-	str	x15, [x3, #LR_OFFSET(10)]
-	str	x14, [x3, #LR_OFFSET(9)]
-	str	x13, [x3, #LR_OFFSET(8)]
-	str	x12, [x3, #LR_OFFSET(7)]
-	str	x11, [x3, #LR_OFFSET(6)]
-	str	x10, [x3, #LR_OFFSET(5)]
-	str	x9, [x3, #LR_OFFSET(4)]
-	str	x8, [x3, #LR_OFFSET(3)]
-	str	x7, [x3, #LR_OFFSET(2)]
-	str	x6, [x3, #LR_OFFSET(1)]
-	str	x5, [x3, #LR_OFFSET(0)]
-
-	tbnz	w21, #29, 6f	// 6 bits
-	tbz	w21, #30, 5f	// 5 bits
-				// 7 bits
-	mrs_s	x20, ICH_AP0R3_EL2
-	str	w20, [x3, #(VGIC_V3_CPU_AP0R + 3*4)]
-	mrs_s	x19, ICH_AP0R2_EL2
-	str	w19, [x3, #(VGIC_V3_CPU_AP0R + 2*4)]
-6:	mrs_s	x18, ICH_AP0R1_EL2
-	str	w18, [x3, #(VGIC_V3_CPU_AP0R + 1*4)]
-5:	mrs_s	x17, ICH_AP0R0_EL2
-	str	w17, [x3, #VGIC_V3_CPU_AP0R]
-
-	tbnz	w21, #29, 6f	// 6 bits
-	tbz	w21, #30, 5f	// 5 bits
-				// 7 bits
-	mrs_s	x20, ICH_AP1R3_EL2
-	str	w20, [x3, #(VGIC_V3_CPU_AP1R + 3*4)]
-	mrs_s	x19, ICH_AP1R2_EL2
-	str	w19, [x3, #(VGIC_V3_CPU_AP1R + 2*4)]
-6:	mrs_s	x18, ICH_AP1R1_EL2
-	str	w18, [x3, #(VGIC_V3_CPU_AP1R + 1*4)]
-5:	mrs_s	x17, ICH_AP1R0_EL2
-	str	w17, [x3, #VGIC_V3_CPU_AP1R]
-
-	// Restore SRE_EL1 access and re-enable SRE at EL1.
-	mrs_s	x5, ICC_SRE_EL2
-	orr	x5, x5, #ICC_SRE_EL2_ENABLE
-	msr_s	ICC_SRE_EL2, x5
-	isb
-	mov	x5, #1
-	msr_s	ICC_SRE_EL1, x5
-.endm
-
-/*
- * Restore the VGIC CPU state from memory
- * x0: Register pointing to VCPU struct
- */
-.macro	restore_vgic_v3_state
-	// Compute the address of struct vgic_cpu
-	add	x3, x0, #VCPU_VGIC_CPU
-
-	// Restore all interesting registers
-	ldr	w4, [x3, #VGIC_V3_CPU_HCR]
-	ldr	w5, [x3, #VGIC_V3_CPU_VMCR]
-	ldr	w25, [x3, #VGIC_V3_CPU_SRE]
-
-	msr_s	ICC_SRE_EL1, x25
-
-	// make sure SRE is valid before writing the other registers
-	isb
-
-	msr_s	ICH_HCR_EL2, x4
-	msr_s	ICH_VMCR_EL2, x5
-
-	mrs_s	x21, ICH_VTR_EL2
-
-	tbnz	w21, #29, 6f	// 6 bits
-	tbz	w21, #30, 5f	// 5 bits
-				// 7 bits
-	ldr	w20, [x3, #(VGIC_V3_CPU_AP1R + 3*4)]
-	msr_s	ICH_AP1R3_EL2, x20
-	ldr	w19, [x3, #(VGIC_V3_CPU_AP1R + 2*4)]
-	msr_s	ICH_AP1R2_EL2, x19
-6:	ldr	w18, [x3, #(VGIC_V3_CPU_AP1R + 1*4)]
-	msr_s	ICH_AP1R1_EL2, x18
-5:	ldr	w17, [x3, #VGIC_V3_CPU_AP1R]
-	msr_s	ICH_AP1R0_EL2, x17
-
-	tbnz	w21, #29, 6f	// 6 bits
-	tbz	w21, #30, 5f	// 5 bits
-				// 7 bits
-	ldr	w20, [x3, #(VGIC_V3_CPU_AP0R + 3*4)]
-	msr_s	ICH_AP0R3_EL2, x20
-	ldr	w19, [x3, #(VGIC_V3_CPU_AP0R + 2*4)]
-	msr_s	ICH_AP0R2_EL2, x19
-6:	ldr	w18, [x3, #(VGIC_V3_CPU_AP0R + 1*4)]
-	msr_s	ICH_AP0R1_EL2, x18
-5:	ldr	w17, [x3, #VGIC_V3_CPU_AP0R]
-	msr_s	ICH_AP0R0_EL2, x17
-
-	and	w22, w21, #0xf
-	mvn	w22, w21
-	ubfiz	w23, w22, 2, 4	// w23 = (15 - ListRegs) * 4
-
-	adr	x24, 1f
-	add	x24, x24, x23
-	br	x24
-
-1:
-	ldr	x20, [x3, #LR_OFFSET(15)]
-	ldr	x19, [x3, #LR_OFFSET(14)]
-	ldr	x18, [x3, #LR_OFFSET(13)]
-	ldr	x17, [x3, #LR_OFFSET(12)]
-	ldr	x16, [x3, #LR_OFFSET(11)]
-	ldr	x15, [x3, #LR_OFFSET(10)]
-	ldr	x14, [x3, #LR_OFFSET(9)]
-	ldr	x13, [x3, #LR_OFFSET(8)]
-	ldr	x12, [x3, #LR_OFFSET(7)]
-	ldr	x11, [x3, #LR_OFFSET(6)]
-	ldr	x10, [x3, #LR_OFFSET(5)]
-	ldr	x9, [x3, #LR_OFFSET(4)]
-	ldr	x8, [x3, #LR_OFFSET(3)]
-	ldr	x7, [x3, #LR_OFFSET(2)]
-	ldr	x6, [x3, #LR_OFFSET(1)]
-	ldr	x5, [x3, #LR_OFFSET(0)]
-
-	adr	x24, 1f
-	add	x24, x24, x23
-	br	x24
-
-1:
-	msr_s	ICH_LR15_EL2, x20
-	msr_s	ICH_LR14_EL2, x19
-	msr_s	ICH_LR13_EL2, x18
-	msr_s	ICH_LR12_EL2, x17
-	msr_s	ICH_LR11_EL2, x16
-	msr_s	ICH_LR10_EL2, x15
-	msr_s	ICH_LR9_EL2,  x14
-	msr_s	ICH_LR8_EL2,  x13
-	msr_s	ICH_LR7_EL2,  x12
-	msr_s	ICH_LR6_EL2,  x11
-	msr_s	ICH_LR5_EL2,  x10
-	msr_s	ICH_LR4_EL2,   x9
-	msr_s	ICH_LR3_EL2,   x8
-	msr_s	ICH_LR2_EL2,   x7
-	msr_s	ICH_LR1_EL2,   x6
-	msr_s	ICH_LR0_EL2,   x5
-
-	// Ensure that the above will have reached the
-	// (re)distributors. This ensure the guest will read
-	// the correct values from the memory-mapped interface.
-	isb
-	dsb	sy
-
-	// Prevent the guest from touching the GIC system registers
-	// if SRE isn't enabled for GICv3 emulation
-	cbnz	x25, 1f
-	mrs_s	x5, ICC_SRE_EL2
-	and	x5, x5, #~ICC_SRE_EL2_ENABLE
-	msr_s	ICC_SRE_EL2, x5
-1:
-.endm
-
-ENTRY(__save_vgic_v3_state)
-	save_vgic_v3_state
-	ret
-ENDPROC(__save_vgic_v3_state)
-
-ENTRY(__restore_vgic_v3_state)
-	restore_vgic_v3_state
-	ret
-ENDPROC(__restore_vgic_v3_state)
-
-ENTRY(__vgic_v3_get_ich_vtr_el2)
-	mrs_s	x0, ICH_VTR_EL2
-	ret
-ENDPROC(__vgic_v3_get_ich_vtr_el2)
-
-	.popsection
diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
index cfa44a6..6df0706 100644
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -81,26 +81,32 @@
 /*
  *	__flush_dcache_area(kaddr, size)
  *
- *	Ensure that the data held in the page kaddr is written back to the
- *	page in question.
+ *	Ensure that any D-cache lines for the interval [kaddr, kaddr+size)
+ *	are cleaned and invalidated to the PoC.
  *
  *	- kaddr   - kernel address
  *	- size    - size in question
  */
 ENTRY(__flush_dcache_area)
-	dcache_line_size x2, x3
-	add	x1, x0, x1
-	sub	x3, x2, #1
-	bic	x0, x0, x3
-1:	dc	civac, x0			// clean & invalidate D line / unified line
-	add	x0, x0, x2
-	cmp	x0, x1
-	b.lo	1b
-	dsb	sy
+	dcache_by_line_op civac, sy, x0, x1, x2, x3
 	ret
 ENDPIPROC(__flush_dcache_area)
 
 /*
+ *	__clean_dcache_area_pou(kaddr, size)
+ *
+ * 	Ensure that any D-cache lines for the interval [kaddr, kaddr+size)
+ * 	are cleaned to the PoU.
+ *
+ *	- kaddr   - kernel address
+ *	- size    - size in question
+ */
+ENTRY(__clean_dcache_area_pou)
+	dcache_by_line_op cvau, ish, x0, x1, x2, x3
+	ret
+ENDPROC(__clean_dcache_area_pou)
+
+/*
  *	__inval_cache_range(start, end)
  *	- start   - start address of region
  *	- end     - end address of region
diff --git a/arch/arm64/mm/copypage.c b/arch/arm64/mm/copypage.c
index 13bbc3be..22e4cb4 100644
--- a/arch/arm64/mm/copypage.c
+++ b/arch/arm64/mm/copypage.c
@@ -24,8 +24,9 @@
 
 void __cpu_copy_user_page(void *kto, const void *kfrom, unsigned long vaddr)
 {
+	struct page *page = virt_to_page(kto);
 	copy_page(kto, kfrom);
-	__flush_dcache_area(kto, PAGE_SIZE);
+	flush_dcache_page(page);
 }
 EXPORT_SYMBOL_GPL(__cpu_copy_user_page);
 
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 7963aa4..331c4ca 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -40,7 +40,7 @@
 static struct gen_pool *atomic_pool;
 
 #define DEFAULT_DMA_COHERENT_POOL_SIZE  SZ_256K
-static size_t atomic_pool_size = DEFAULT_DMA_COHERENT_POOL_SIZE;
+static size_t atomic_pool_size __initdata = DEFAULT_DMA_COHERENT_POOL_SIZE;
 
 static int __init early_coherent_pool(char *p)
 {
@@ -896,7 +896,7 @@
 	return 0;
 }
 
-static int register_iommu_dma_ops_notifier(struct bus_type *bus)
+static int __init register_iommu_dma_ops_notifier(struct bus_type *bus)
 {
 	struct notifier_block *nb = kzalloc(sizeof(*nb), GFP_KERNEL);
 	int ret;
diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index c26b804..46649d6 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -34,19 +34,24 @@
 		__flush_icache_all();
 }
 
+static void sync_icache_aliases(void *kaddr, unsigned long len)
+{
+	unsigned long addr = (unsigned long)kaddr;
+
+	if (icache_is_aliasing()) {
+		__clean_dcache_area_pou(kaddr, len);
+		__flush_icache_all();
+	} else {
+		flush_icache_range(addr, addr + len);
+	}
+}
+
 static void flush_ptrace_access(struct vm_area_struct *vma, struct page *page,
 				unsigned long uaddr, void *kaddr,
 				unsigned long len)
 {
-	if (vma->vm_flags & VM_EXEC) {
-		unsigned long addr = (unsigned long)kaddr;
-		if (icache_is_aliasing()) {
-			__flush_dcache_area(kaddr, len);
-			__flush_icache_all();
-		} else {
-			flush_icache_range(addr, addr + len);
-		}
-	}
+	if (vma->vm_flags & VM_EXEC)
+		sync_icache_aliases(kaddr, len);
 }
 
 /*
@@ -74,13 +79,11 @@
 	if (!page_mapping(page))
 		return;
 
-	if (!test_and_set_bit(PG_dcache_clean, &page->flags)) {
-		__flush_dcache_area(page_address(page),
-				PAGE_SIZE << compound_order(page));
+	if (!test_and_set_bit(PG_dcache_clean, &page->flags))
+		sync_icache_aliases(page_address(page),
+				    PAGE_SIZE << compound_order(page));
+	else if (icache_is_aivivt())
 		__flush_icache_all();
-	} else if (icache_is_aivivt()) {
-		__flush_icache_all();
-	}
 }
 
 /*
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 383b03f..82d607c 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -41,17 +41,289 @@
 #endif
 }
 
+static int find_num_contig(struct mm_struct *mm, unsigned long addr,
+			   pte_t *ptep, pte_t pte, size_t *pgsize)
+{
+	pgd_t *pgd = pgd_offset(mm, addr);
+	pud_t *pud;
+	pmd_t *pmd;
+
+	*pgsize = PAGE_SIZE;
+	if (!pte_cont(pte))
+		return 1;
+	if (!pgd_present(*pgd)) {
+		VM_BUG_ON(!pgd_present(*pgd));
+		return 1;
+	}
+	pud = pud_offset(pgd, addr);
+	if (!pud_present(*pud)) {
+		VM_BUG_ON(!pud_present(*pud));
+		return 1;
+	}
+	pmd = pmd_offset(pud, addr);
+	if (!pmd_present(*pmd)) {
+		VM_BUG_ON(!pmd_present(*pmd));
+		return 1;
+	}
+	if ((pte_t *)pmd == ptep) {
+		*pgsize = PMD_SIZE;
+		return CONT_PMDS;
+	}
+	return CONT_PTES;
+}
+
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+			    pte_t *ptep, pte_t pte)
+{
+	size_t pgsize;
+	int i;
+	int ncontig = find_num_contig(mm, addr, ptep, pte, &pgsize);
+	unsigned long pfn;
+	pgprot_t hugeprot;
+
+	if (ncontig == 1) {
+		set_pte_at(mm, addr, ptep, pte);
+		return;
+	}
+
+	pfn = pte_pfn(pte);
+	hugeprot = __pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^ pte_val(pte));
+	for (i = 0; i < ncontig; i++) {
+		pr_debug("%s: set pte %p to 0x%llx\n", __func__, ptep,
+			 pte_val(pfn_pte(pfn, hugeprot)));
+		set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot));
+		ptep++;
+		pfn += pgsize >> PAGE_SHIFT;
+		addr += pgsize;
+	}
+}
+
+pte_t *huge_pte_alloc(struct mm_struct *mm,
+		      unsigned long addr, unsigned long sz)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pte_t *pte = NULL;
+
+	pr_debug("%s: addr:0x%lx sz:0x%lx\n", __func__, addr, sz);
+	pgd = pgd_offset(mm, addr);
+	pud = pud_alloc(mm, pgd, addr);
+	if (!pud)
+		return NULL;
+
+	if (sz == PUD_SIZE) {
+		pte = (pte_t *)pud;
+	} else if (sz == (PAGE_SIZE * CONT_PTES)) {
+		pmd_t *pmd = pmd_alloc(mm, pud, addr);
+
+		WARN_ON(addr & (sz - 1));
+		/*
+		 * Note that if this code were ever ported to the
+		 * 32-bit arm platform then it will cause trouble in
+		 * the case where CONFIG_HIGHPTE is set, since there
+		 * will be no pte_unmap() to correspond with this
+		 * pte_alloc_map().
+		 */
+		pte = pte_alloc_map(mm, NULL, pmd, addr);
+	} else if (sz == PMD_SIZE) {
+		if (IS_ENABLED(CONFIG_ARCH_WANT_HUGE_PMD_SHARE) &&
+		    pud_none(*pud))
+			pte = huge_pmd_share(mm, addr, pud);
+		else
+			pte = (pte_t *)pmd_alloc(mm, pud, addr);
+	} else if (sz == (PMD_SIZE * CONT_PMDS)) {
+		pmd_t *pmd;
+
+		pmd = pmd_alloc(mm, pud, addr);
+		WARN_ON(addr & (sz - 1));
+		return (pte_t *)pmd;
+	}
+
+	pr_debug("%s: addr:0x%lx sz:0x%lx ret pte=%p/0x%llx\n", __func__, addr,
+	       sz, pte, pte_val(*pte));
+	return pte;
+}
+
+pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd = NULL;
+	pte_t *pte = NULL;
+
+	pgd = pgd_offset(mm, addr);
+	pr_debug("%s: addr:0x%lx pgd:%p\n", __func__, addr, pgd);
+	if (!pgd_present(*pgd))
+		return NULL;
+	pud = pud_offset(pgd, addr);
+	if (!pud_present(*pud))
+		return NULL;
+
+	if (pud_huge(*pud))
+		return (pte_t *)pud;
+	pmd = pmd_offset(pud, addr);
+	if (!pmd_present(*pmd))
+		return NULL;
+
+	if (pte_cont(pmd_pte(*pmd))) {
+		pmd = pmd_offset(
+			pud, (addr & CONT_PMD_MASK));
+		return (pte_t *)pmd;
+	}
+	if (pmd_huge(*pmd))
+		return (pte_t *)pmd;
+	pte = pte_offset_kernel(pmd, addr);
+	if (pte_present(*pte) && pte_cont(*pte)) {
+		pte = pte_offset_kernel(
+			pmd, (addr & CONT_PTE_MASK));
+		return pte;
+	}
+	return NULL;
+}
+
+pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
+			 struct page *page, int writable)
+{
+	size_t pagesize = huge_page_size(hstate_vma(vma));
+
+	if (pagesize == CONT_PTE_SIZE) {
+		entry = pte_mkcont(entry);
+	} else if (pagesize == CONT_PMD_SIZE) {
+		entry = pmd_pte(pmd_mkcont(pte_pmd(entry)));
+	} else if (pagesize != PUD_SIZE && pagesize != PMD_SIZE) {
+		pr_warn("%s: unrecognized huge page size 0x%lx\n",
+			__func__, pagesize);
+	}
+	return entry;
+}
+
+pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+			      unsigned long addr, pte_t *ptep)
+{
+	pte_t pte;
+
+	if (pte_cont(*ptep)) {
+		int ncontig, i;
+		size_t pgsize;
+		pte_t *cpte;
+		bool is_dirty = false;
+
+		cpte = huge_pte_offset(mm, addr);
+		ncontig = find_num_contig(mm, addr, cpte, *cpte, &pgsize);
+		/* save the 1st pte to return */
+		pte = ptep_get_and_clear(mm, addr, cpte);
+		for (i = 1; i < ncontig; ++i) {
+			/*
+			 * If HW_AFDBM is enabled, then the HW could
+			 * turn on the dirty bit for any of the page
+			 * in the set, so check them all.
+			 */
+			++cpte;
+			if (pte_dirty(ptep_get_and_clear(mm, addr, cpte)))
+				is_dirty = true;
+		}
+		if (is_dirty)
+			return pte_mkdirty(pte);
+		else
+			return pte;
+	} else {
+		return ptep_get_and_clear(mm, addr, ptep);
+	}
+}
+
+int huge_ptep_set_access_flags(struct vm_area_struct *vma,
+			       unsigned long addr, pte_t *ptep,
+			       pte_t pte, int dirty)
+{
+	pte_t *cpte;
+
+	if (pte_cont(pte)) {
+		int ncontig, i, changed = 0;
+		size_t pgsize = 0;
+		unsigned long pfn = pte_pfn(pte);
+		/* Select all bits except the pfn */
+		pgprot_t hugeprot =
+			__pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^
+				 pte_val(pte));
+
+		cpte = huge_pte_offset(vma->vm_mm, addr);
+		pfn = pte_pfn(*cpte);
+		ncontig = find_num_contig(vma->vm_mm, addr, cpte,
+					  *cpte, &pgsize);
+		for (i = 0; i < ncontig; ++i, ++cpte) {
+			changed = ptep_set_access_flags(vma, addr, cpte,
+							pfn_pte(pfn,
+								hugeprot),
+							dirty);
+			pfn += pgsize >> PAGE_SHIFT;
+		}
+		return changed;
+	} else {
+		return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
+	}
+}
+
+void huge_ptep_set_wrprotect(struct mm_struct *mm,
+			     unsigned long addr, pte_t *ptep)
+{
+	if (pte_cont(*ptep)) {
+		int ncontig, i;
+		pte_t *cpte;
+		size_t pgsize = 0;
+
+		cpte = huge_pte_offset(mm, addr);
+		ncontig = find_num_contig(mm, addr, cpte, *cpte, &pgsize);
+		for (i = 0; i < ncontig; ++i, ++cpte)
+			ptep_set_wrprotect(mm, addr, cpte);
+	} else {
+		ptep_set_wrprotect(mm, addr, ptep);
+	}
+}
+
+void huge_ptep_clear_flush(struct vm_area_struct *vma,
+			   unsigned long addr, pte_t *ptep)
+{
+	if (pte_cont(*ptep)) {
+		int ncontig, i;
+		pte_t *cpte;
+		size_t pgsize = 0;
+
+		cpte = huge_pte_offset(vma->vm_mm, addr);
+		ncontig = find_num_contig(vma->vm_mm, addr, cpte,
+					  *cpte, &pgsize);
+		for (i = 0; i < ncontig; ++i, ++cpte)
+			ptep_clear_flush(vma, addr, cpte);
+	} else {
+		ptep_clear_flush(vma, addr, ptep);
+	}
+}
+
 static __init int setup_hugepagesz(char *opt)
 {
 	unsigned long ps = memparse(opt, &opt);
+
 	if (ps == PMD_SIZE) {
 		hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT);
 	} else if (ps == PUD_SIZE) {
 		hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
+	} else if (ps == (PAGE_SIZE * CONT_PTES)) {
+		hugetlb_add_hstate(CONT_PTE_SHIFT);
+	} else if (ps == (PMD_SIZE * CONT_PMDS)) {
+		hugetlb_add_hstate((PMD_SHIFT + CONT_PMD_SHIFT) - PAGE_SHIFT);
 	} else {
-		pr_err("hugepagesz: Unsupported page size %lu M\n", ps >> 20);
+		pr_err("hugepagesz: Unsupported page size %lu K\n", ps >> 10);
 		return 0;
 	}
 	return 1;
 }
 __setup("hugepagesz=", setup_hugepagesz);
+
+#ifdef CONFIG_ARM64_64K_PAGES
+static __init int add_default_hugepagesz(void)
+{
+	if (size_to_hstate(CONT_PTES * PAGE_SIZE) == NULL)
+		hugetlb_add_hstate(CONT_PMD_SHIFT);
+	return 0;
+}
+arch_initcall(add_default_hugepagesz);
+#endif
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 17bf39a..f3b061e 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -71,7 +71,7 @@
  * currently assumes that for memory starting above 4G, 32-bit devices will
  * use a DMA offset.
  */
-static phys_addr_t max_zone_dma_phys(void)
+static phys_addr_t __init max_zone_dma_phys(void)
 {
 	phys_addr_t offset = memblock_start_of_DRAM() & GENMASK_ULL(63, 32);
 	return min(offset + (1ULL << 32), memblock_end_of_DRAM());
@@ -120,17 +120,17 @@
 #ifdef CONFIG_HAVE_ARCH_PFN_VALID
 int pfn_valid(unsigned long pfn)
 {
-	return memblock_is_memory(pfn << PAGE_SHIFT);
+	return memblock_is_map_memory(pfn << PAGE_SHIFT);
 }
 EXPORT_SYMBOL(pfn_valid);
 #endif
 
 #ifndef CONFIG_SPARSEMEM
-static void arm64_memory_present(void)
+static void __init arm64_memory_present(void)
 {
 }
 #else
-static void arm64_memory_present(void)
+static void __init arm64_memory_present(void)
 {
 	struct memblock_region *reg;
 
@@ -360,7 +360,6 @@
 {
 	fixup_init();
 	free_initmem_default(0);
-	free_alternatives_memory();
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 873e363..58faeaa 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -251,6 +251,14 @@
 {
 	unsigned long addr, length, end, next;
 
+	/*
+	 * If the virtual and physical address don't have the same offset
+	 * within a page, we cannot map the region as the caller expects.
+	 */
+	if (WARN_ON((phys ^ virt) & ~PAGE_MASK))
+		return;
+
+	phys &= PAGE_MASK;
 	addr = virt & PAGE_MASK;
 	length = PAGE_ALIGN(size + (virt & ~PAGE_MASK));
 
@@ -280,7 +288,7 @@
 			&phys, virt);
 		return;
 	}
-	__create_mapping(&init_mm, pgd_offset_k(virt & PAGE_MASK), phys, virt,
+	__create_mapping(&init_mm, pgd_offset_k(virt), phys, virt,
 			 size, prot, early_alloc);
 }
 
@@ -301,7 +309,7 @@
 		return;
 	}
 
-	return __create_mapping(&init_mm, pgd_offset_k(virt & PAGE_MASK),
+	return __create_mapping(&init_mm, pgd_offset_k(virt),
 				phys, virt, size, prot, late_alloc);
 }
 
@@ -372,6 +380,8 @@
 
 		if (start >= end)
 			break;
+		if (memblock_is_nomap(reg))
+			continue;
 
 		if (ARM64_SWAPPER_USES_SECTION_MAPS) {
 			/*
@@ -456,6 +466,9 @@
 
 	empty_zero_page = virt_to_page(zero_page);
 
+	/* Ensure the zero page is visible to the page table walker */
+	dsb(ishst);
+
 	/*
 	 * TTBR0 is only used for the identity mapping at this stage. Make it
 	 * point to zero page to avoid speculatively fetching new entries.
diff --git a/arch/arm64/mm/pgd.c b/arch/arm64/mm/pgd.c
index cb3ba1b..ae11d4e 100644
--- a/arch/arm64/mm/pgd.c
+++ b/arch/arm64/mm/pgd.c
@@ -46,14 +46,14 @@
 		kmem_cache_free(pgd_cache, pgd);
 }
 
-static int __init pgd_cache_init(void)
+void __init pgd_cache_init(void)
 {
+	if (PGD_SIZE == PAGE_SIZE)
+		return;
+
 	/*
 	 * Naturally aligned pgds required by the architecture.
 	 */
-	if (PGD_SIZE != PAGE_SIZE)
-		pgd_cache = kmem_cache_create("pgd_cache", PGD_SIZE, PGD_SIZE,
-					      SLAB_PANIC, NULL);
-	return 0;
+	pgd_cache = kmem_cache_create("pgd_cache", PGD_SIZE, PGD_SIZE,
+				      SLAB_PANIC, NULL);
 }
-core_initcall(pgd_cache_init);
diff --git a/arch/arm64/mm/proc-macros.S b/arch/arm64/mm/proc-macros.S
index 4c4d93c..146bd99 100644
--- a/arch/arm64/mm/proc-macros.S
+++ b/arch/arm64/mm/proc-macros.S
@@ -62,3 +62,25 @@
 	bfi	\valreg, \tmpreg, #TCR_T0SZ_OFFSET, #TCR_TxSZ_WIDTH
 #endif
 	.endm
+
+/*
+ * Macro to perform a data cache maintenance for the interval
+ * [kaddr, kaddr + size)
+ *
+ * 	op:		operation passed to dc instruction
+ * 	domain:		domain used in dsb instruciton
+ * 	kaddr:		starting virtual address of the region
+ * 	size:		size of the region
+ * 	Corrupts: 	kaddr, size, tmp1, tmp2
+ */
+	.macro dcache_by_line_op op, domain, kaddr, size, tmp1, tmp2
+	dcache_line_size \tmp1, \tmp2
+	add	\size, \kaddr, \size
+	sub	\tmp2, \tmp1, #1
+	bic	\kaddr, \kaddr, \tmp2
+9998:	dc	\op, \kaddr
+	add	\kaddr, \kaddr, \tmp1
+	cmp	\kaddr, \size
+	b.lo	9998b
+	dsb	\domain
+	.endm
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index cacecc4..a3d867e 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -117,6 +117,7 @@
 	 */
 	ubfx	x11, x11, #1, #1
 	msr	oslar_el1, x11
+	msr	pmuserenr_el0, xzr		// Disable PMU access from EL0
 	mov	x0, x12
 	dsb	nsh		// Make sure local tlb invalidation completed
 	isb
@@ -139,8 +140,6 @@
 	ret
 ENDPROC(cpu_do_switch_mm)
 
-	.section ".text.init", #alloc, #execinstr
-
 /*
  *	__cpu_setup
  *
@@ -155,6 +154,7 @@
 	msr	cpacr_el1, x0			// Enable FP/ASIMD
 	mov	x0, #1 << 12			// Reset mdscr_el1 and disable
 	msr	mdscr_el1, x0			// access to the DCC from EL0
+	msr	pmuserenr_el0, xzr		// Disable PMU access from EL0
 	/*
 	 * Memory region attributes for LPAE:
 	 *
diff --git a/arch/arm64/xen/hypercall.S b/arch/arm64/xen/hypercall.S
index 8bbe940..70df80e 100644
--- a/arch/arm64/xen/hypercall.S
+++ b/arch/arm64/xen/hypercall.S
@@ -80,6 +80,7 @@
 HYPERCALL2(physdev_op);
 HYPERCALL3(vcpu_op);
 HYPERCALL1(tmem_op);
+HYPERCALL1(platform_op_raw);
 HYPERCALL2(multicall);
 
 ENTRY(privcmd_call)
diff --git a/arch/blackfin/include/asm/cmpxchg.h b/arch/blackfin/include/asm/cmpxchg.h
index c05868c..2539288 100644
--- a/arch/blackfin/include/asm/cmpxchg.h
+++ b/arch/blackfin/include/asm/cmpxchg.h
@@ -128,6 +128,5 @@
 #endif /* !CONFIG_SMP */
 
 #define xchg(ptr, x) ((__typeof__(*(ptr)))__xchg((unsigned long)(x), (ptr), sizeof(*(ptr))))
-#define tas(ptr) ((void)xchg((ptr), 1))
 
 #endif /* __ARCH_BLACKFIN_CMPXCHG__ */
diff --git a/arch/blackfin/include/asm/uaccess.h b/arch/blackfin/include/asm/uaccess.h
index 90612a7..12f5d68 100644
--- a/arch/blackfin/include/asm/uaccess.h
+++ b/arch/blackfin/include/asm/uaccess.h
@@ -168,12 +168,6 @@
 #define __copy_to_user_inatomic __copy_to_user
 #define __copy_from_user_inatomic __copy_from_user
 
-#define copy_to_user_ret(to, from, n, retval) ({ if (copy_to_user(to, from, n))\
-				                 return retval; })
-
-#define copy_from_user_ret(to, from, n, retval) ({ if (copy_from_user(to, from, n))\
-                                                   return retval; })
-
 static inline unsigned long __must_check
 copy_from_user(void *to, const void __user *from, unsigned long n)
 {
diff --git a/arch/blackfin/mach-bf561/boards/ezkit.c b/arch/blackfin/mach-bf561/boards/ezkit.c
index 2de71e8..f35525b 100644
--- a/arch/blackfin/mach-bf561/boards/ezkit.c
+++ b/arch/blackfin/mach-bf561/boards/ezkit.c
@@ -443,7 +443,7 @@
 };
 
 #if IS_ENABLED(CONFIG_VIDEO_ADV7183)
-#include <media/adv7183.h>
+#include <media/i2c/adv7183.h>
 static struct v4l2_input adv7183_inputs[] = {
 	{
 		.index = 0,
diff --git a/arch/blackfin/mach-bf609/boards/ezkit.c b/arch/blackfin/mach-bf609/boards/ezkit.c
index 2c61fc0..c7928d8 100644
--- a/arch/blackfin/mach-bf609/boards/ezkit.c
+++ b/arch/blackfin/mach-bf609/boards/ezkit.c
@@ -933,7 +933,7 @@
 #endif
 
 #if IS_ENABLED(CONFIG_VIDEO_ADV7842)
-#include <media/adv7842.h>
+#include <media/i2c/adv7842.h>
 
 static struct v4l2_input adv7842_inputs[] = {
 	{
@@ -1084,7 +1084,7 @@
 };
 
 #if IS_ENABLED(CONFIG_VIDEO_ADV7511)
-#include <media/adv7511.h>
+#include <media/i2c/adv7511.h>
 
 static struct v4l2_output adv7511_outputs[] = {
 	{
@@ -1125,7 +1125,7 @@
 #endif
 
 #if IS_ENABLED(CONFIG_VIDEO_ADV7343)
-#include <media/adv7343.h>
+#include <media/i2c/adv7343.h>
 
 static struct v4l2_output adv7343_outputs[] = {
 	{
diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild
index 945544e..64465e7 100644
--- a/arch/c6x/include/asm/Kbuild
+++ b/arch/c6x/include/asm/Kbuild
@@ -4,6 +4,7 @@
 generic-y += barrier.h
 generic-y += bitsperlong.h
 generic-y += bugs.h
+generic-y += clkdev.h
 generic-y += cputime.h
 generic-y += current.h
 generic-y += device.h
diff --git a/arch/c6x/include/asm/clkdev.h b/arch/c6x/include/asm/clkdev.h
deleted file mode 100644
index 76a070b..0000000
--- a/arch/c6x/include/asm/clkdev.h
+++ /dev/null
@@ -1,22 +0,0 @@
-#ifndef _ASM_CLKDEV_H
-#define _ASM_CLKDEV_H
-
-#include <linux/slab.h>
-
-struct clk;
-
-static inline int __clk_get(struct clk *clk)
-{
-	return 1;
-}
-
-static inline void __clk_put(struct clk *clk)
-{
-}
-
-static inline struct clk_lookup_alloc *__clkdev_alloc(size_t size)
-{
-	return kzalloc(size, GFP_KERNEL);
-}
-
-#endif /* _ASM_CLKDEV_H */
diff --git a/arch/c6x/include/asm/cmpxchg.h b/arch/c6x/include/asm/cmpxchg.h
index b27c8ce..93d0a5a 100644
--- a/arch/c6x/include/asm/cmpxchg.h
+++ b/arch/c6x/include/asm/cmpxchg.h
@@ -47,8 +47,6 @@
 #define xchg(ptr, x) \
 	((__typeof__(*(ptr)))__xchg((unsigned int)(x), (void *) (ptr), \
 				    sizeof(*(ptr))))
-#define tas(ptr)    xchg((ptr), 1)
-
 
 #include <asm-generic/cmpxchg-local.h>
 
diff --git a/arch/frv/include/asm/cmpxchg.h b/arch/frv/include/asm/cmpxchg.h
index 5b04dd0..a899765 100644
--- a/arch/frv/include/asm/cmpxchg.h
+++ b/arch/frv/include/asm/cmpxchg.h
@@ -69,8 +69,6 @@
 
 #endif
 
-#define tas(ptr) (xchg((ptr), 1))
-
 /*****************************************************************************/
 /*
  * compare and conditionally exchange value with memory
diff --git a/arch/h8300/Kconfig b/arch/h8300/Kconfig
index dd3ac75..2e20333 100644
--- a/arch/h8300/Kconfig
+++ b/arch/h8300/Kconfig
@@ -17,6 +17,7 @@
 	select HAVE_MEMBLOCK
 	select HAVE_DMA_ATTRS
 	select CLKSRC_OF
+	select H8300_TMR8
 
 config RWSEM_GENERIC_SPINLOCK
 	def_bool y
diff --git a/arch/h8300/include/asm/io.h b/arch/h8300/include/asm/io.h
index bb837cd..f0e14f3 100644
--- a/arch/h8300/include/asm/io.h
+++ b/arch/h8300/include/asm/io.h
@@ -3,40 +3,45 @@
 
 #ifdef __KERNEL__
 
-#include <asm-generic/io.h>
-
 /* H8/300 internal I/O functions */
-static inline unsigned char ctrl_inb(unsigned long addr)
+
+#define __raw_readb __raw_readb
+static inline u8 __raw_readb(const volatile void __iomem *addr)
 {
-	return *(volatile unsigned char *)addr;
+	return *(volatile u8 *)addr;
 }
 
-static inline unsigned short ctrl_inw(unsigned long addr)
+#define __raw_readw __raw_readw
+static inline u16 __raw_readw(const volatile void __iomem *addr)
 {
-	return *(volatile unsigned short *)addr;
+	return *(volatile u16 *)addr;
 }
 
-static inline unsigned long ctrl_inl(unsigned long addr)
+#define __raw_readl __raw_readl
+static inline u32  __raw_readl(const volatile void __iomem *addr)
 {
-	return *(volatile unsigned long *)addr;
+	return *(volatile u32 *)addr;
 }
 
-static inline void ctrl_outb(unsigned char b, unsigned long addr)
+#define __raw_writeb __raw_writeb
+static inline void __raw_writeb(u8 b, const volatile void __iomem *addr)
 {
-	*(volatile unsigned char *)addr = b;
+	*(volatile u8 *)addr = b;
 }
 
-static inline void ctrl_outw(unsigned short b, unsigned long addr)
+#define __raw_writew __raw_writew
+static inline void __raw_writew(u16 b, const volatile void __iomem *addr)
 {
-	*(volatile unsigned short *)addr = b;
+	*(volatile u16 *)addr = b;
 }
 
-static inline void ctrl_outl(unsigned long b, unsigned long addr)
+#define __raw_writel __raw_writel
+static inline void __raw_writel(u32 b, const volatile void __iomem *addr)
 {
-	*(volatile unsigned long *)addr = b;
+	*(volatile u32 *)addr = b;
 }
 
-static inline void ctrl_bclr(int b, unsigned char *addr)
+static inline void ctrl_bclr(int b, void __iomem *addr)
 {
 	if (__builtin_constant_p(b))
 		__asm__("bclr %1,%0" : "+WU"(*addr): "i"(b));
@@ -44,7 +49,7 @@
 		__asm__("bclr %w1,%0" : "+WU"(*addr): "r"(b));
 }
 
-static inline void ctrl_bset(int b, unsigned char *addr)
+static inline void ctrl_bset(int b, void __iomem *addr)
 {
 	if (__builtin_constant_p(b))
 		__asm__("bset %1,%0" : "+WU"(*addr): "i"(b));
@@ -52,6 +57,8 @@
 		__asm__("bset %w1,%0" : "+WU"(*addr): "r"(b));
 }
 
+#include <asm-generic/io.h>
+
 #endif /* __KERNEL__ */
 
 #endif /* _H8300_IO_H */
diff --git a/arch/h8300/kernel/setup.c b/arch/h8300/kernel/setup.c
index c772abe..e4985df 100644
--- a/arch/h8300/kernel/setup.c
+++ b/arch/h8300/kernel/setup.c
@@ -207,14 +207,14 @@
 #define get_wait(base, addr) ({		\
 	int baddr;			\
 	baddr = ((addr) / 0x200000 * 2);			     \
-	w *= (ctrl_inw((unsigned long)(base) + 2) & (3 << baddr)) + 1;	\
+	w *= (readw((base) + 2) & (3 << baddr)) + 1;		     \
 	})
 #endif
 #if defined(CONFIG_CPU_H8S)
 #define get_wait(base, addr) ({		\
 	int baddr;			\
 	baddr = ((addr) / 0x200000 * 16);			     \
-	w *= (ctrl_inl((unsigned long)(base) + 2) & (7 << baddr)) + 1;	\
+	w *= (readl((base) + 2) & (7 << baddr)) + 1;	\
 	})
 #endif
 
@@ -228,8 +228,8 @@
 
 	bsc = of_find_compatible_node(NULL, NULL, "renesas,h8300-bsc");
 	base = of_iomap(bsc, 0);
-	w = (ctrl_inb((unsigned long)base + 0) & bit)?2:1;
-	if (ctrl_inb((unsigned long)base + 1) & bit)
+	w = (readb(base + 0) & bit)?2:1;
+	if (readb(base + 1) & bit)
 		w *= get_wait(base, addr);
 	else
 		w *= 2;
diff --git a/arch/ia64/include/asm/barrier.h b/arch/ia64/include/asm/barrier.h
index df896a1..209c4b8 100644
--- a/arch/ia64/include/asm/barrier.h
+++ b/arch/ia64/include/asm/barrier.h
@@ -77,7 +77,7 @@
 	___p1;								\
 })
 
-#define smp_store_mb(var, value)	do { WRITE_ONCE(var, value); mb(); } while (0)
+#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); smp_mb(); } while (0)
 
 /*
  * The group barrier in front of the rsm & ssm are necessary to ensure
diff --git a/arch/ia64/include/asm/percpu.h b/arch/ia64/include/asm/percpu.h
index 0ec484d..b929579 100644
--- a/arch/ia64/include/asm/percpu.h
+++ b/arch/ia64/include/asm/percpu.h
@@ -6,8 +6,6 @@
  *	David Mosberger-Tang <davidm@hpl.hp.com>
  */
 
-#define PERCPU_ENOUGH_ROOM PERCPU_PAGE_SIZE
-
 #ifdef __ASSEMBLY__
 # define THIS_CPU(var)	(var)  /* use this to mark accesses to per-CPU variables... */
 #else /* !__ASSEMBLY__ */
diff --git a/arch/m68k/atari/config.c b/arch/m68k/atari/config.c
index 192b00f..cbd5991 100644
--- a/arch/m68k/atari/config.c
+++ b/arch/m68k/atari/config.c
@@ -858,7 +858,7 @@
 };
 #endif /* CONFIG_ATARI_ETHERNEC */
 
-#ifdef CONFIG_ATARI_SCSI
+#if IS_ENABLED(CONFIG_ATARI_SCSI)
 static const struct resource atari_scsi_st_rsrc[] __initconst = {
 	{
 		.flags = IORESOURCE_IRQ,
@@ -910,7 +910,7 @@
 	}
 #endif
 
-#ifdef CONFIG_ATARI_SCSI
+#if IS_ENABLED(CONFIG_ATARI_SCSI)
 	if (ATARIHW_PRESENT(ST_SCSI))
 		platform_device_register_simple("atari_scsi", -1,
 			atari_scsi_st_rsrc, ARRAY_SIZE(atari_scsi_st_rsrc));
diff --git a/arch/m68k/coldfire/gpio.c b/arch/m68k/coldfire/gpio.c
index e7e4286..37a83e2 100644
--- a/arch/m68k/coldfire/gpio.c
+++ b/arch/m68k/coldfire/gpio.c
@@ -121,7 +121,7 @@
 
 static int mcfgpio_get_value(struct gpio_chip *chip, unsigned offset)
 {
-	return __mcfgpio_get_value(offset);
+	return !!__mcfgpio_get_value(offset);
 }
 
 static int mcfgpio_direction_output(struct gpio_chip *chip, unsigned offset,
diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index 5b4ec54..fc96e81 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -276,6 +276,7 @@
 CONFIG_NET_MPLS_GSO=m
 CONFIG_MPLS_ROUTING=m
 CONFIG_MPLS_IPTUNNEL=m
+CONFIG_NET_L3_MASTER_DEV=y
 # CONFIG_WIRELESS is not set
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -532,11 +533,13 @@
 CONFIG_NLS_MAC_ROMANIAN=m
 CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
+# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_ASYNC_RAID6_TEST=m
 CONFIG_TEST_HEXDUMP=m
 CONFIG_TEST_STRING_HELPERS=m
 CONFIG_TEST_KSTRTOX=m
+CONFIG_TEST_PRINTF=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_LKM=m
 CONFIG_TEST_USER_COPY=m
@@ -559,6 +562,7 @@
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
+CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index 6e5198e..05c904f 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -274,6 +274,7 @@
 CONFIG_NET_MPLS_GSO=m
 CONFIG_MPLS_ROUTING=m
 CONFIG_MPLS_IPTUNNEL=m
+CONFIG_NET_L3_MASTER_DEV=y
 # CONFIG_WIRELESS is not set
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -372,6 +373,7 @@
 # CONFIG_MOUSE_PS2 is not set
 CONFIG_MOUSE_SERIAL=m
 CONFIG_SERIO=m
+CONFIG_USERIO=m
 # CONFIG_LEGACY_PTYS is not set
 # CONFIG_DEVKMEM is not set
 # CONFIG_HW_RANDOM is not set
@@ -490,11 +492,13 @@
 CONFIG_NLS_MAC_ROMANIAN=m
 CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
+# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_ASYNC_RAID6_TEST=m
 CONFIG_TEST_HEXDUMP=m
 CONFIG_TEST_STRING_HELPERS=m
 CONFIG_TEST_KSTRTOX=m
+CONFIG_TEST_PRINTF=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_LKM=m
 CONFIG_TEST_USER_COPY=m
@@ -517,6 +521,7 @@
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
+CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index f75600b..d572b73 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -274,6 +274,7 @@
 CONFIG_NET_MPLS_GSO=m
 CONFIG_MPLS_ROUTING=m
 CONFIG_MPLS_IPTUNNEL=m
+CONFIG_NET_L3_MASTER_DEV=y
 # CONFIG_WIRELESS is not set
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -512,11 +513,13 @@
 CONFIG_NLS_MAC_ROMANIAN=m
 CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
+# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_ASYNC_RAID6_TEST=m
 CONFIG_TEST_HEXDUMP=m
 CONFIG_TEST_STRING_HELPERS=m
 CONFIG_TEST_KSTRTOX=m
+CONFIG_TEST_PRINTF=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_LKM=m
 CONFIG_TEST_USER_COPY=m
@@ -539,6 +542,7 @@
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
+CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index a42d91c..11a30c6 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -272,6 +272,7 @@
 CONFIG_NET_MPLS_GSO=m
 CONFIG_MPLS_ROUTING=m
 CONFIG_MPLS_IPTUNNEL=m
+CONFIG_NET_L3_MASTER_DEV=y
 # CONFIG_WIRELESS is not set
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -483,11 +484,13 @@
 CONFIG_NLS_MAC_ROMANIAN=m
 CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
+# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_ASYNC_RAID6_TEST=m
 CONFIG_TEST_HEXDUMP=m
 CONFIG_TEST_STRING_HELPERS=m
 CONFIG_TEST_KSTRTOX=m
+CONFIG_TEST_PRINTF=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_LKM=m
 CONFIG_TEST_USER_COPY=m
@@ -510,6 +513,7 @@
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
+CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index 77f4a11..6630a51 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -274,6 +274,7 @@
 CONFIG_NET_MPLS_GSO=m
 CONFIG_MPLS_ROUTING=m
 CONFIG_MPLS_IPTUNNEL=m
+CONFIG_NET_L3_MASTER_DEV=y
 # CONFIG_WIRELESS is not set
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -375,6 +376,7 @@
 CONFIG_INPUT_MISC=y
 CONFIG_HP_SDC_RTC=m
 CONFIG_SERIO_SERPORT=m
+CONFIG_USERIO=m
 # CONFIG_LEGACY_PTYS is not set
 # CONFIG_DEVKMEM is not set
 # CONFIG_HW_RANDOM is not set
@@ -492,11 +494,13 @@
 CONFIG_NLS_MAC_ROMANIAN=m
 CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
+# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_ASYNC_RAID6_TEST=m
 CONFIG_TEST_HEXDUMP=m
 CONFIG_TEST_STRING_HELPERS=m
 CONFIG_TEST_KSTRTOX=m
+CONFIG_TEST_PRINTF=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_LKM=m
 CONFIG_TEST_USER_COPY=m
@@ -519,6 +523,7 @@
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
+CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index 5a329f7..1d90b71 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -276,6 +276,7 @@
 CONFIG_NET_MPLS_GSO=m
 CONFIG_MPLS_ROUTING=m
 CONFIG_MPLS_IPTUNNEL=m
+CONFIG_NET_L3_MASTER_DEV=y
 # CONFIG_WIRELESS is not set
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -394,6 +395,7 @@
 CONFIG_INPUT_MISC=y
 CONFIG_INPUT_M68K_BEEP=m
 CONFIG_SERIO=m
+CONFIG_USERIO=m
 # CONFIG_LEGACY_PTYS is not set
 # CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_PMACZILOG=y
@@ -514,11 +516,13 @@
 CONFIG_NLS_MAC_ROMANIAN=m
 CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
+# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_ASYNC_RAID6_TEST=m
 CONFIG_TEST_HEXDUMP=m
 CONFIG_TEST_STRING_HELPERS=m
 CONFIG_TEST_KSTRTOX=m
+CONFIG_TEST_PRINTF=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_LKM=m
 CONFIG_TEST_USER_COPY=m
@@ -541,6 +545,7 @@
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
+CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index 83c80d2..1fd21c1 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -286,6 +286,7 @@
 CONFIG_NET_MPLS_GSO=m
 CONFIG_MPLS_ROUTING=m
 CONFIG_MPLS_IPTUNNEL=m
+CONFIG_NET_L3_MASTER_DEV=y
 # CONFIG_WIRELESS is not set
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -449,6 +450,7 @@
 CONFIG_INPUT_M68K_BEEP=m
 CONFIG_HP_SDC_RTC=m
 CONFIG_SERIO_Q40KBD=y
+CONFIG_USERIO=m
 # CONFIG_LEGACY_PTYS is not set
 # CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_PMACZILOG=y
@@ -594,11 +596,13 @@
 CONFIG_NLS_MAC_ROMANIAN=m
 CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
+# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_ASYNC_RAID6_TEST=m
 CONFIG_TEST_HEXDUMP=m
 CONFIG_TEST_STRING_HELPERS=m
 CONFIG_TEST_KSTRTOX=m
+CONFIG_TEST_PRINTF=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_LKM=m
 CONFIG_TEST_USER_COPY=m
@@ -621,6 +625,7 @@
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
+CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index 6cb42c3b..74e10f7 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -271,6 +271,7 @@
 CONFIG_NET_MPLS_GSO=m
 CONFIG_MPLS_ROUTING=m
 CONFIG_MPLS_IPTUNNEL=m
+CONFIG_NET_L3_MASTER_DEV=y
 # CONFIG_WIRELESS is not set
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -483,11 +484,13 @@
 CONFIG_NLS_MAC_ROMANIAN=m
 CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
+# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_ASYNC_RAID6_TEST=m
 CONFIG_TEST_HEXDUMP=m
 CONFIG_TEST_STRING_HELPERS=m
 CONFIG_TEST_KSTRTOX=m
+CONFIG_TEST_PRINTF=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_LKM=m
 CONFIG_TEST_USER_COPY=m
@@ -510,6 +513,7 @@
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
+CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index c7508c3..7034e71 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -272,6 +272,7 @@
 CONFIG_NET_MPLS_GSO=m
 CONFIG_MPLS_ROUTING=m
 CONFIG_MPLS_IPTUNNEL=m
+CONFIG_NET_L3_MASTER_DEV=y
 # CONFIG_WIRELESS is not set
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -483,11 +484,13 @@
 CONFIG_NLS_MAC_ROMANIAN=m
 CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
+# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_ASYNC_RAID6_TEST=m
 CONFIG_TEST_HEXDUMP=m
 CONFIG_TEST_STRING_HELPERS=m
 CONFIG_TEST_KSTRTOX=m
+CONFIG_TEST_PRINTF=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_LKM=m
 CONFIG_TEST_USER_COPY=m
@@ -510,6 +513,7 @@
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
+CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index 64b7166..f7deb5f 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -272,6 +272,7 @@
 CONFIG_NET_MPLS_GSO=m
 CONFIG_MPLS_ROUTING=m
 CONFIG_MPLS_IPTUNNEL=m
+CONFIG_NET_L3_MASTER_DEV=y
 # CONFIG_WIRELESS is not set
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -385,6 +386,7 @@
 CONFIG_INPUT_MISC=y
 CONFIG_INPUT_M68K_BEEP=m
 CONFIG_SERIO_Q40KBD=y
+CONFIG_USERIO=m
 # CONFIG_LEGACY_PTYS is not set
 # CONFIG_DEVKMEM is not set
 CONFIG_PRINTER=m
@@ -505,11 +507,13 @@
 CONFIG_NLS_MAC_ROMANIAN=m
 CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
+# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_ASYNC_RAID6_TEST=m
 CONFIG_TEST_HEXDUMP=m
 CONFIG_TEST_STRING_HELPERS=m
 CONFIG_TEST_KSTRTOX=m
+CONFIG_TEST_PRINTF=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_LKM=m
 CONFIG_TEST_USER_COPY=m
@@ -532,6 +536,7 @@
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
+CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index 9a4cab7..0ce79eb 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -269,6 +269,7 @@
 CONFIG_NET_MPLS_GSO=m
 CONFIG_MPLS_ROUTING=m
 CONFIG_MPLS_IPTUNNEL=m
+CONFIG_NET_L3_MASTER_DEV=y
 # CONFIG_WIRELESS is not set
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -369,6 +370,7 @@
 CONFIG_KEYBOARD_SUNKBD=y
 # CONFIG_MOUSE_PS2 is not set
 CONFIG_MOUSE_SERIAL=m
+CONFIG_USERIO=m
 # CONFIG_LEGACY_PTYS is not set
 # CONFIG_DEVKMEM is not set
 # CONFIG_HW_RANDOM is not set
@@ -484,11 +486,13 @@
 CONFIG_NLS_MAC_ROMANIAN=m
 CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
+# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_ASYNC_RAID6_TEST=m
 CONFIG_TEST_HEXDUMP=m
 CONFIG_TEST_STRING_HELPERS=m
 CONFIG_TEST_KSTRTOX=m
+CONFIG_TEST_PRINTF=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_LKM=m
 CONFIG_TEST_USER_COPY=m
@@ -510,6 +514,7 @@
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
+CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index 1a2eaac..4cb787e4 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -269,6 +269,7 @@
 CONFIG_NET_MPLS_GSO=m
 CONFIG_MPLS_ROUTING=m
 CONFIG_MPLS_IPTUNNEL=m
+CONFIG_NET_L3_MASTER_DEV=y
 # CONFIG_WIRELESS is not set
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -369,6 +370,7 @@
 CONFIG_KEYBOARD_SUNKBD=y
 # CONFIG_MOUSE_PS2 is not set
 CONFIG_MOUSE_SERIAL=m
+CONFIG_USERIO=m
 # CONFIG_LEGACY_PTYS is not set
 # CONFIG_DEVKMEM is not set
 # CONFIG_HW_RANDOM is not set
@@ -484,11 +486,13 @@
 CONFIG_NLS_MAC_ROMANIAN=m
 CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
+# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_ASYNC_RAID6_TEST=m
 CONFIG_TEST_HEXDUMP=m
 CONFIG_TEST_STRING_HELPERS=m
 CONFIG_TEST_KSTRTOX=m
+CONFIG_TEST_PRINTF=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_LKM=m
 CONFIG_TEST_USER_COPY=m
@@ -511,6 +515,7 @@
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
+CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
diff --git a/arch/m68k/include/asm/mac_psc.h b/arch/m68k/include/asm/mac_psc.h
index e5c0d71..9233051 100644
--- a/arch/m68k/include/asm/mac_psc.h
+++ b/arch/m68k/include/asm/mac_psc.h
@@ -209,7 +209,6 @@
 #ifndef __ASSEMBLY__
 
 extern volatile __u8 *psc;
-extern int psc_present;
 
 extern void psc_register_interrupts(void);
 extern void psc_irq_enable(int);
diff --git a/arch/m68k/include/asm/page.h b/arch/m68k/include/asm/page.h
index 38b024a..430d4d5 100644
--- a/arch/m68k/include/asm/page.h
+++ b/arch/m68k/include/asm/page.h
@@ -48,6 +48,9 @@
 #include <asm/page_no.h>
 #endif
 
+#define __phys_to_pfn(paddr)	((unsigned long)((paddr) >> PAGE_SHIFT))
+#define __pfn_to_phys(pfn)	PFN_PHYS(pfn)
+
 #define VM_DATA_DEFAULT_FLAGS	(VM_READ | VM_WRITE | VM_EXEC | \
 				 VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
 
diff --git a/arch/m68k/include/asm/uaccess_no.h b/arch/m68k/include/asm/uaccess_no.h
index 68bbe9b..1bdf152 100644
--- a/arch/m68k/include/asm/uaccess_no.h
+++ b/arch/m68k/include/asm/uaccess_no.h
@@ -135,10 +135,6 @@
 #define __copy_to_user_inatomic __copy_to_user
 #define __copy_from_user_inatomic __copy_from_user
 
-#define copy_to_user_ret(to,from,n,retval) ({ if (copy_to_user(to,from,n)) return retval; })
-
-#define copy_from_user_ret(to,from,n,retval) ({ if (copy_from_user(to,from,n)) return retval; })
-
 /*
  * Copy a null terminated string from userspace.
  */
diff --git a/arch/m68k/mac/macints.c b/arch/m68k/mac/macints.c
index 5c1a6b2..9f98c08 100644
--- a/arch/m68k/mac/macints.c
+++ b/arch/m68k/mac/macints.c
@@ -174,7 +174,7 @@
 		oss_register_interrupts();
 	else
 		via_register_interrupts();
-	if (psc_present)
+	if (psc)
 		psc_register_interrupts();
 	if (baboon_present)
 		baboon_register_interrupts();
@@ -212,7 +212,7 @@
 	case 4:
 	case 5:
 	case 6:
-		if (psc_present)
+		if (psc)
 			psc_irq_enable(irq);
 		else if (oss_present)
 			oss_irq_enable(irq);
@@ -242,7 +242,7 @@
 	case 4:
 	case 5:
 	case 6:
-		if (psc_present)
+		if (psc)
 			psc_irq_disable(irq);
 		else if (oss_present)
 			oss_irq_disable(irq);
diff --git a/arch/m68k/mac/psc.c b/arch/m68k/mac/psc.c
index 2290c0c..cb2b1a3 100644
--- a/arch/m68k/mac/psc.c
+++ b/arch/m68k/mac/psc.c
@@ -27,7 +27,6 @@
 
 #define DEBUG_PSC
 
-int psc_present;
 volatile __u8 *psc;
 EXPORT_SYMBOL_GPL(psc);
 
@@ -39,7 +38,9 @@
 {
 	int	i;
 
-	if (!psc_present) return;
+	if (!psc)
+		return;
+
 	for (i = 0x30 ; i < 0x70 ; i += 0x10) {
 		printk("PSC #%d:  IFR = 0x%02X IER = 0x%02X\n",
 			i >> 4,
@@ -81,7 +82,6 @@
 	 && macintosh_config->ident != MAC_MODEL_Q840)
 	{
 		psc = NULL;
-		psc_present = 0;
 		return;
 	}
 
@@ -91,7 +91,6 @@
 	 */
 
 	psc = (void *) PSC_BASE;
-	psc_present = 1;
 
 	printk("PSC detected at %p\n", psc);
 
diff --git a/arch/m68k/sun3/config.c b/arch/m68k/sun3/config.c
index 2a5f43a..71884bf 100644
--- a/arch/m68k/sun3/config.c
+++ b/arch/m68k/sun3/config.c
@@ -171,7 +171,7 @@
         intersil_clear();
 }
 
-#ifdef CONFIG_SUN3_SCSI
+#if IS_ENABLED(CONFIG_SUN3_SCSI)
 
 static const struct resource sun3_scsi_vme_rsrc[] __initconst = {
 	{
diff --git a/arch/mips/boot/dts/brcm/bcm6328.dtsi b/arch/mips/boot/dts/brcm/bcm6328.dtsi
index 41891c1..d52ce3d 100644
--- a/arch/mips/boot/dts/brcm/bcm6328.dtsi
+++ b/arch/mips/boot/dts/brcm/bcm6328.dtsi
@@ -73,7 +73,6 @@
 		timer: timer@10000040 {
 			compatible = "syscon";
 			reg = <0x10000040 0x2c>;
-			little-endian;
 		};
 
 		reboot {
diff --git a/arch/mips/boot/dts/brcm/bcm7125.dtsi b/arch/mips/boot/dts/brcm/bcm7125.dtsi
index 1a7efa8..4fc7ece 100644
--- a/arch/mips/boot/dts/brcm/bcm7125.dtsi
+++ b/arch/mips/boot/dts/brcm/bcm7125.dtsi
@@ -98,7 +98,6 @@
 		sun_top_ctrl: syscon@404000 {
 			compatible = "brcm,bcm7125-sun-top-ctrl", "syscon";
 			reg = <0x404000 0x60c>;
-			little-endian;
 		};
 
 		reboot {
diff --git a/arch/mips/boot/dts/brcm/bcm7346.dtsi b/arch/mips/boot/dts/brcm/bcm7346.dtsi
index d4bf52c..a3039bb 100644
--- a/arch/mips/boot/dts/brcm/bcm7346.dtsi
+++ b/arch/mips/boot/dts/brcm/bcm7346.dtsi
@@ -118,7 +118,6 @@
 		sun_top_ctrl: syscon@404000 {
 			compatible = "brcm,bcm7346-sun-top-ctrl", "syscon";
 			reg = <0x404000 0x51c>;
-			little-endian;
 		};
 
 		reboot {
diff --git a/arch/mips/boot/dts/brcm/bcm7358.dtsi b/arch/mips/boot/dts/brcm/bcm7358.dtsi
index 8e25016..4274ff4 100644
--- a/arch/mips/boot/dts/brcm/bcm7358.dtsi
+++ b/arch/mips/boot/dts/brcm/bcm7358.dtsi
@@ -112,7 +112,6 @@
 		sun_top_ctrl: syscon@404000 {
 			compatible = "brcm,bcm7358-sun-top-ctrl", "syscon";
 			reg = <0x404000 0x51c>;
-			little-endian;
 		};
 
 		reboot {
diff --git a/arch/mips/boot/dts/brcm/bcm7360.dtsi b/arch/mips/boot/dts/brcm/bcm7360.dtsi
index 7e5f7604..0dcc9163 100644
--- a/arch/mips/boot/dts/brcm/bcm7360.dtsi
+++ b/arch/mips/boot/dts/brcm/bcm7360.dtsi
@@ -112,7 +112,6 @@
 		sun_top_ctrl: syscon@404000 {
 			compatible = "brcm,bcm7360-sun-top-ctrl", "syscon";
 			reg = <0x404000 0x51c>;
-			little-endian;
 		};
 
 		reboot {
diff --git a/arch/mips/boot/dts/brcm/bcm7362.dtsi b/arch/mips/boot/dts/brcm/bcm7362.dtsi
index c739ea7..2f3f9fc 100644
--- a/arch/mips/boot/dts/brcm/bcm7362.dtsi
+++ b/arch/mips/boot/dts/brcm/bcm7362.dtsi
@@ -118,7 +118,6 @@
 		sun_top_ctrl: syscon@404000 {
 			compatible = "brcm,bcm7362-sun-top-ctrl", "syscon";
 			reg = <0x404000 0x51c>;
-			little-endian;
 		};
 
 		reboot {
diff --git a/arch/mips/boot/dts/brcm/bcm7420.dtsi b/arch/mips/boot/dts/brcm/bcm7420.dtsi
index 5f55d0a..bee221b 100644
--- a/arch/mips/boot/dts/brcm/bcm7420.dtsi
+++ b/arch/mips/boot/dts/brcm/bcm7420.dtsi
@@ -99,7 +99,6 @@
 		sun_top_ctrl: syscon@404000 {
 			compatible = "brcm,bcm7420-sun-top-ctrl", "syscon";
 			reg = <0x404000 0x60c>;
-			little-endian;
 		};
 
 		reboot {
diff --git a/arch/mips/boot/dts/brcm/bcm7425.dtsi b/arch/mips/boot/dts/brcm/bcm7425.dtsi
index e24d41a..571f30f 100644
--- a/arch/mips/boot/dts/brcm/bcm7425.dtsi
+++ b/arch/mips/boot/dts/brcm/bcm7425.dtsi
@@ -100,7 +100,6 @@
 		sun_top_ctrl: syscon@404000 {
 			compatible = "brcm,bcm7425-sun-top-ctrl", "syscon";
 			reg = <0x404000 0x51c>;
-			little-endian;
 		};
 
 		reboot {
diff --git a/arch/mips/boot/dts/brcm/bcm7435.dtsi b/arch/mips/boot/dts/brcm/bcm7435.dtsi
index 8b9432c..614ee21 100644
--- a/arch/mips/boot/dts/brcm/bcm7435.dtsi
+++ b/arch/mips/boot/dts/brcm/bcm7435.dtsi
@@ -114,7 +114,6 @@
 		sun_top_ctrl: syscon@404000 {
 			compatible = "brcm,bcm7425-sun-top-ctrl", "syscon";
 			reg = <0x404000 0x51c>;
-			little-endian;
 		};
 
 		reboot {
diff --git a/arch/mips/lasat/picvue_proc.c b/arch/mips/lasat/picvue_proc.c
index 2bcd839..b420958 100644
--- a/arch/mips/lasat/picvue_proc.c
+++ b/arch/mips/lasat/picvue_proc.c
@@ -22,7 +22,6 @@
 static DEFINE_MUTEX(pvc_mutex);
 static char pvc_lines[PVC_NLINES][PVC_LINELEN+1];
 static int pvc_linedata[PVC_NLINES];
-static struct proc_dir_entry *pvc_display_dir;
 static char *pvc_linename[PVC_NLINES] = {"line1", "line2"};
 #define DISPLAY_DIR_NAME "display"
 static int scroll_dir, scroll_interval;
@@ -169,22 +168,17 @@
 
 static void pvc_proc_cleanup(void)
 {
-	int i;
-	for (i = 0; i < PVC_NLINES; i++)
-		remove_proc_entry(pvc_linename[i], pvc_display_dir);
-	remove_proc_entry("scroll", pvc_display_dir);
-	remove_proc_entry(DISPLAY_DIR_NAME, NULL);
-
+	remove_proc_subtree(DISPLAY_DIR_NAME, NULL);
 	del_timer_sync(&timer);
 }
 
 static int __init pvc_proc_init(void)
 {
-	struct proc_dir_entry *proc_entry;
+	struct proc_dir_entry *dir, *proc_entry;
 	int i;
 
-	pvc_display_dir = proc_mkdir(DISPLAY_DIR_NAME, NULL);
-	if (pvc_display_dir == NULL)
+	dir = proc_mkdir(DISPLAY_DIR_NAME, NULL);
+	if (dir == NULL)
 		goto error;
 
 	for (i = 0; i < PVC_NLINES; i++) {
@@ -192,12 +186,12 @@
 		pvc_linedata[i] = i;
 	}
 	for (i = 0; i < PVC_NLINES; i++) {
-		proc_entry = proc_create_data(pvc_linename[i], 0644, pvc_display_dir,
+		proc_entry = proc_create_data(pvc_linename[i], 0644, dir,
 					&pvc_line_proc_fops, &pvc_linedata[i]);
 		if (proc_entry == NULL)
 			goto error;
 	}
-	proc_entry = proc_create("scroll", 0644, pvc_display_dir,
+	proc_entry = proc_create("scroll", 0644, dir,
 				 &pvc_scroll_proc_fops);
 	if (proc_entry == NULL)
 		goto error;
diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile
index 1456890..ee3617c 100644
--- a/arch/mips/vdso/Makefile
+++ b/arch/mips/vdso/Makefile
@@ -26,7 +26,7 @@
 # the comments on that file.
 #
 ifndef CONFIG_CPU_MIPSR6
-  ifeq ($(call ld-ifversion, -lt, 22500000, y),y)
+  ifeq ($(call ld-ifversion, -lt, 225000000, y),y)
     $(warning MIPS VDSO requires binutils >= 2.25)
     obj-vdso-y := $(filter-out gettimeofday.o, $(obj-vdso-y))
     ccflags-vdso += -DDISABLE_MIPS_VDSO
diff --git a/arch/mn10300/include/asm/uaccess.h b/arch/mn10300/include/asm/uaccess.h
index 5372787..20f7bf6 100644
--- a/arch/mn10300/include/asm/uaccess.h
+++ b/arch/mn10300/include/asm/uaccess.h
@@ -110,21 +110,6 @@
 #define __put_user(x, ptr) __put_user_nocheck((x), (ptr), sizeof(*(ptr)))
 #define __get_user(x, ptr) __get_user_nocheck((x), (ptr), sizeof(*(ptr)))
 
-/*
- * The "xxx_ret" versions return constant specified in third argument, if
- * something bad happens. These macros can be optimized for the
- * case of just returning from the function xxx_ret is used.
- */
-
-#define put_user_ret(x, ptr, ret) \
-	({ if (put_user((x), (ptr)))	return (ret); })
-#define get_user_ret(x, ptr, ret) \
-	({ if (get_user((x), (ptr)))	return (ret); })
-#define __put_user_ret(x, ptr, ret) \
-	({ if (__put_user((x), (ptr)))	return (ret); })
-#define __get_user_ret(x, ptr, ret) \
-	({ if (__get_user((x), (ptr)))	return (ret); })
-
 struct __large_struct { unsigned long buf[100]; };
 #define __m(x) (*(struct __large_struct *)(x))
 
diff --git a/arch/powerpc/include/asm/barrier.h b/arch/powerpc/include/asm/barrier.h
index 0eca6ef..a7af5fb 100644
--- a/arch/powerpc/include/asm/barrier.h
+++ b/arch/powerpc/include/asm/barrier.h
@@ -34,7 +34,7 @@
 #define rmb()  __asm__ __volatile__ ("sync" : : : "memory")
 #define wmb()  __asm__ __volatile__ ("sync" : : : "memory")
 
-#define smp_store_mb(var, value)	do { WRITE_ONCE(var, value); mb(); } while (0)
+#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); smp_mb(); } while (0)
 
 #ifdef __SUBARCH_HAS_LWSYNC
 #    define SMPWMB      LWSYNC
diff --git a/arch/powerpc/include/asm/icswx.h b/arch/powerpc/include/asm/icswx.h
index 9f8402b..27e588f 100644
--- a/arch/powerpc/include/asm/icswx.h
+++ b/arch/powerpc/include/asm/icswx.h
@@ -164,6 +164,7 @@
 #define ICSWX_INITIATED		(0x8)
 #define ICSWX_BUSY		(0x4)
 #define ICSWX_REJECTED		(0x2)
+#define ICSWX_XERS0		(0x1)	/* undefined or set from XERSO. */
 
 static inline int icswx(__be32 ccw, struct coprocessor_request_block *crb)
 {
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index cfa758c..271fefb 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -50,6 +50,10 @@
 #define KVM_NR_IRQCHIPS          1
 #define KVM_IRQCHIP_NUM_PINS     256
 
+/* PPC-specific vcpu->requests bit members */
+#define KVM_REQ_WATCHDOG           8
+#define KVM_REQ_EPR_EXIT           9
+
 #include <linux/mmu_notifier.h>
 
 #define KVM_ARCH_WANT_MMU_NOTIFIER
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index 2a8ebae..b7c20f0 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -274,21 +274,6 @@
 	__gu_err;						\
 })
 
-#ifndef __powerpc64__
-#define __get_user64_nocheck(x, ptr, size)			\
-({								\
-	long __gu_err;						\
-	long long __gu_val;					\
-	__typeof__(*(ptr)) __user *__gu_addr = (ptr);	\
-	__chk_user_ptr(ptr);					\
-	if (!is_kernel_addr((unsigned long)__gu_addr))		\
-		might_fault();					\
-	__get_user_size(__gu_val, __gu_addr, (size), __gu_err);	\
-	(x) = (__force __typeof__(*(ptr)))__gu_val;			\
-	__gu_err;						\
-})
-#endif /* __powerpc64__ */
-
 #define __get_user_check(x, ptr, size)					\
 ({									\
 	long __gu_err = -EFAULT;					\
diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c
index 32e2652..0cab9e8 100644
--- a/arch/powerpc/kernel/nvram_64.c
+++ b/arch/powerpc/kernel/nvram_64.c
@@ -27,6 +27,7 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/kmsg_dump.h>
+#include <linux/pagemap.h>
 #include <linux/pstore.h>
 #include <linux/zlib.h>
 #include <asm/uaccess.h>
@@ -733,24 +734,10 @@
 
 static loff_t dev_nvram_llseek(struct file *file, loff_t offset, int origin)
 {
-	int size;
-
 	if (ppc_md.nvram_size == NULL)
 		return -ENODEV;
-	size = ppc_md.nvram_size();
-
-	switch (origin) {
-	case 1:
-		offset += file->f_pos;
-		break;
-	case 2:
-		offset += size;
-		break;
-	}
-	if (offset < 0)
-		return -EINVAL;
-	file->f_pos = offset;
-	return file->f_pos;
+	return generic_file_llseek_size(file, offset, origin, MAX_LFS_FILESIZE,
+					ppc_md.nvram_size());
 }
 
 
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index a7352b5..6b35269 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -314,16 +314,10 @@
 
 static struct kvm_vcpu *kvmppc_find_vcpu(struct kvm *kvm, int id)
 {
-	int r;
-	struct kvm_vcpu *v, *ret = NULL;
+	struct kvm_vcpu *ret;
 
 	mutex_lock(&kvm->lock);
-	kvm_for_each_vcpu(r, v, kvm) {
-		if (v->vcpu_id == id) {
-			ret = v;
-			break;
-		}
-	}
+	ret = kvm_get_vcpu_by_id(kvm, id);
 	mutex_unlock(&kvm->lock);
 	return ret;
 }
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 64891b0..70fb08d 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -512,7 +512,7 @@
 	put_page(hpage);
 }
 
-static int kvmppc_visible_gpa(struct kvm_vcpu *vcpu, gpa_t gpa)
+static bool kvmppc_visible_gpa(struct kvm_vcpu *vcpu, gpa_t gpa)
 {
 	ulong mp_pa = vcpu->arch.magic_page_pa;
 
@@ -521,7 +521,7 @@
 
 	gpa &= ~0xFFFULL;
 	if (unlikely(mp_pa) && unlikely((mp_pa & KVM_PAM) == (gpa & KVM_PAM))) {
-		return 1;
+		return true;
 	}
 
 	return kvm_is_visible_gfn(vcpu->kvm, gpa >> PAGE_SHIFT);
diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c
index 610f472..a1ac80b 100644
--- a/arch/powerpc/sysdev/fsl_pci.c
+++ b/arch/powerpc/sysdev/fsl_pci.c
@@ -21,10 +21,12 @@
 #include <linux/pci.h>
 #include <linux/delay.h>
 #include <linux/string.h>
+#include <linux/fsl/edac.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/memblock.h>
 #include <linux/log2.h>
+#include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/suspend.h>
 #include <linux/syscore_ops.h>
@@ -1255,6 +1257,25 @@
 #endif
 }
 
+static int add_err_dev(struct platform_device *pdev)
+{
+	struct platform_device *errdev;
+	struct mpc85xx_edac_pci_plat_data pd = {
+		.of_node = pdev->dev.of_node
+	};
+
+	errdev = platform_device_register_resndata(&pdev->dev,
+						   "mpc85xx-pci-edac",
+						   PLATFORM_DEVID_AUTO,
+						   pdev->resource,
+						   pdev->num_resources,
+						   &pd, sizeof(pd));
+	if (IS_ERR(errdev))
+		return PTR_ERR(errdev);
+
+	return 0;
+}
+
 static int fsl_pci_probe(struct platform_device *pdev)
 {
 	struct device_node *node;
@@ -1262,8 +1283,13 @@
 
 	node = pdev->dev.of_node;
 	ret = fsl_add_bridge(pdev, fsl_pci_primary == node);
+	if (ret)
+		return ret;
 
-	mpc85xx_pci_err_probe(pdev);
+	ret = add_err_dev(pdev);
+	if (ret)
+		dev_err(&pdev->dev, "couldn't register error device: %d\n",
+			ret);
 
 	return 0;
 }
diff --git a/arch/powerpc/sysdev/fsl_pci.h b/arch/powerpc/sysdev/fsl_pci.h
index c1cec77..1515885 100644
--- a/arch/powerpc/sysdev/fsl_pci.h
+++ b/arch/powerpc/sysdev/fsl_pci.h
@@ -130,15 +130,6 @@
 static inline void fsl_pci_assign_primary(void) {}
 #endif
 
-#ifdef CONFIG_EDAC_MPC85XX
-int mpc85xx_pci_err_probe(struct platform_device *op);
-#else
-static inline int mpc85xx_pci_err_probe(struct platform_device *op)
-{
-	return -ENOTSUPP;
-}
-#endif
-
 #ifdef CONFIG_FSL_PCI
 extern int fsl_pci_mcheck_exception(struct pt_regs *);
 #else
diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h
index d68e11e..7ffd0b1 100644
--- a/arch/s390/include/asm/barrier.h
+++ b/arch/s390/include/asm/barrier.h
@@ -36,7 +36,7 @@
 #define smp_mb__before_atomic()		smp_mb()
 #define smp_mb__after_atomic()		smp_mb()
 
-#define smp_store_mb(var, value)		do { WRITE_ONCE(var, value); mb(); } while (0)
+#define smp_store_mb(var, value)	do { WRITE_ONCE(var, value); smp_mb(); } while (0)
 
 #define smp_store_release(p, v)						\
 do {									\
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index bab6739..08e34a5 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -104,6 +104,9 @@
 #define HWCAP_S390_TE		1024
 #define HWCAP_S390_VXRS		2048
 
+/* Internal bits, not exposed via elf */
+#define HWCAP_INT_SIE		1UL
+
 /*
  * These are used to set parameters in the core dumps.
  */
@@ -169,6 +172,10 @@
 extern unsigned long elf_hwcap;
 #define ELF_HWCAP (elf_hwcap)
 
+/* Internal hardware capabilities, not exposed via elf */
+
+extern unsigned long int_hwcap;
+
 /* This yields a string that ld.so will use to load implementation
    specific libraries for optimization.  This is more specific in
    intent than poking at uname or /proc/cpuinfo.
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index efaac2c..6742414 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -25,7 +25,9 @@
 #include <asm/fpu/api.h>
 #include <asm/isc.h>
 
-#define KVM_MAX_VCPUS 64
+#define KVM_S390_BSCA_CPU_SLOTS 64
+#define KVM_S390_ESCA_CPU_SLOTS 248
+#define KVM_MAX_VCPUS KVM_S390_ESCA_CPU_SLOTS
 #define KVM_USER_MEM_SLOTS 32
 
 /*
@@ -37,12 +39,41 @@
 #define KVM_IRQCHIP_NUM_PINS 4096
 #define KVM_HALT_POLL_NS_DEFAULT 0
 
+/* s390-specific vcpu->requests bit members */
+#define KVM_REQ_ENABLE_IBS         8
+#define KVM_REQ_DISABLE_IBS        9
+
 #define SIGP_CTRL_C		0x80
 #define SIGP_CTRL_SCN_MASK	0x3f
 
-struct sca_entry {
+union bsca_sigp_ctrl {
+	__u8 value;
+	struct {
+		__u8 c : 1;
+		__u8 r : 1;
+		__u8 scn : 6;
+	};
+} __packed;
+
+union esca_sigp_ctrl {
+	__u16 value;
+	struct {
+		__u8 c : 1;
+		__u8 reserved: 7;
+		__u8 scn;
+	};
+} __packed;
+
+struct esca_entry {
+	union esca_sigp_ctrl sigp_ctrl;
+	__u16   reserved1[3];
+	__u64   sda;
+	__u64   reserved2[6];
+} __packed;
+
+struct bsca_entry {
 	__u8	reserved0;
-	__u8	sigp_ctrl;
+	union bsca_sigp_ctrl	sigp_ctrl;
 	__u16	reserved[3];
 	__u64	sda;
 	__u64	reserved2[2];
@@ -57,14 +88,22 @@
 	};
 };
 
-struct sca_block {
+struct bsca_block {
 	union ipte_control ipte_control;
 	__u64	reserved[5];
 	__u64	mcn;
 	__u64	reserved2;
-	struct sca_entry cpu[64];
+	struct bsca_entry cpu[KVM_S390_BSCA_CPU_SLOTS];
 } __attribute__((packed));
 
+struct esca_block {
+	union ipte_control ipte_control;
+	__u64   reserved1[7];
+	__u64   mcn[4];
+	__u64   reserved2[20];
+	struct esca_entry cpu[KVM_S390_ESCA_CPU_SLOTS];
+} __packed;
+
 #define CPUSTAT_STOPPED    0x80000000
 #define CPUSTAT_WAIT       0x10000000
 #define CPUSTAT_ECALL_PEND 0x08000000
@@ -182,7 +221,8 @@
 	__u64	pp;			/* 0x01de */
 	__u8	reserved1e6[2];		/* 0x01e6 */
 	__u64	itdba;			/* 0x01e8 */
-	__u8	reserved1f0[16];	/* 0x01f0 */
+	__u64   riccbd;			/* 0x01f0 */
+	__u8    reserved1f8[8];		/* 0x01f8 */
 } __attribute__((packed));
 
 struct kvm_s390_itdb {
@@ -585,11 +625,14 @@
 };
 
 struct kvm_arch{
-	struct sca_block *sca;
+	void *sca;
+	int use_esca;
+	rwlock_t sca_lock;
 	debug_info_t *dbf;
 	struct kvm_s390_float_interrupt float_int;
 	struct kvm_device *flic;
 	struct gmap *gmap;
+	unsigned long mem_limit;
 	int css_support;
 	int use_irqchip;
 	int use_cmma;
diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h
index 821dde5..dea883f 100644
--- a/arch/s390/include/asm/sclp.h
+++ b/arch/s390/include/asm/sclp.h
@@ -29,7 +29,10 @@
 
 struct sclp_core_entry {
 	u8 core_id;
-	u8 reserved0[2];
+	u8 reserved0;
+	u8 : 4;
+	u8 sief2 : 1;
+	u8 : 3;
 	u8 : 3;
 	u8 siif : 1;
 	u8 sigpif : 1;
@@ -53,6 +56,9 @@
 	unsigned char has_sigpif : 1;
 	unsigned char has_core_type : 1;
 	unsigned char has_sprp : 1;
+	unsigned char has_hvs : 1;
+	unsigned char has_esca : 1;
+	unsigned char has_sief2 : 1;
 	unsigned int ibc;
 	unsigned int mtid;
 	unsigned int mtid_cp;
diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h
index ef1a5fc..fe84bd5 100644
--- a/arch/s390/include/uapi/asm/kvm.h
+++ b/arch/s390/include/uapi/asm/kvm.h
@@ -66,6 +66,8 @@
 #define KVM_S390_VM_MEM_CLR_CMMA	1
 #define KVM_S390_VM_MEM_LIMIT_SIZE	2
 
+#define KVM_S390_NO_MEM_LIMIT		U64_MAX
+
 /* kvm attributes for KVM_S390_VM_TOD */
 #define KVM_S390_VM_TOD_LOW		0
 #define KVM_S390_VM_TOD_HIGH		1
@@ -151,6 +153,7 @@
 #define KVM_SYNC_ARCH0  (1UL << 4)
 #define KVM_SYNC_PFAULT (1UL << 5)
 #define KVM_SYNC_VRS    (1UL << 6)
+#define KVM_SYNC_RICCB  (1UL << 7)
 /* definition of registers in kvm_run */
 struct kvm_sync_regs {
 	__u64 prefix;	/* prefix register */
@@ -168,6 +171,8 @@
 	__u64 vrs[32][2];	/* vector registers */
 	__u8  reserved[512];	/* for future vector expansion */
 	__u32 fpc;	/* only valid with vector registers */
+	__u8 padding[52];	/* riccb needs to be 64byte aligned */
+	__u8 riccb[64];		/* runtime instrumentation controls block */
 };
 
 #define KVM_REG_S390_TODPR	(KVM_REG_S390 | KVM_REG_SIZE_U32 | 0x1)
diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c
index 7ce00e7..647128d 100644
--- a/arch/s390/kernel/processor.c
+++ b/arch/s390/kernel/processor.c
@@ -61,6 +61,9 @@
 		"esan3", "zarch", "stfle", "msa", "ldisp", "eimm", "dfp",
 		"edat", "etf3eh", "highgprs", "te", "vx"
 	};
+	static const char * const int_hwcap_str[] = {
+		"sie"
+	};
 	unsigned long n = (unsigned long) v - 1;
 	int i;
 
@@ -75,6 +78,9 @@
 		for (i = 0; i < ARRAY_SIZE(hwcap_str); i++)
 			if (hwcap_str[i] && (elf_hwcap & (1UL << i)))
 				seq_printf(m, "%s ", hwcap_str[i]);
+		for (i = 0; i < ARRAY_SIZE(int_hwcap_str); i++)
+			if (int_hwcap_str[i] && (int_hwcap & (1UL << i)))
+				seq_printf(m, "%s ", int_hwcap_str[i]);
 		seq_puts(m, "\n");
 		show_cacheinfo(m);
 	}
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index c837bca..dc83ae6 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -80,6 +80,8 @@
 unsigned long elf_hwcap __read_mostly = 0;
 char elf_platform[ELF_PLATFORM_SIZE];
 
+unsigned long int_hwcap = 0;
+
 int __initdata memory_end_set;
 unsigned long __initdata memory_end;
 unsigned long __initdata max_physmem_end;
@@ -793,6 +795,13 @@
 		strcpy(elf_platform, "z13");
 		break;
 	}
+
+	/*
+	 * Virtualization support HWCAP_INT_SIE is bit 0.
+	 */
+	if (sclp.has_sief2)
+		int_hwcap |= HWCAP_INT_SIE;
+
 	return 0;
 }
 arch_initcall(setup_hwcaps);
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index 5fbfb88..05f7de9 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -155,10 +155,8 @@
 
 static int __diag_time_slice_end_directed(struct kvm_vcpu *vcpu)
 {
-	struct kvm *kvm = vcpu->kvm;
 	struct kvm_vcpu *tcpu;
 	int tid;
-	int i;
 
 	tid = vcpu->run->s.regs.gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4];
 	vcpu->stat.diagnose_9c++;
@@ -167,12 +165,9 @@
 	if (tid == vcpu->vcpu_id)
 		return 0;
 
-	kvm_for_each_vcpu(i, tcpu, kvm)
-		if (tcpu->vcpu_id == tid) {
-			kvm_vcpu_yield_to(tcpu);
-			break;
-		}
-
+	tcpu = kvm_get_vcpu_by_id(vcpu->kvm, tid);
+	if (tcpu)
+		kvm_vcpu_yield_to(tcpu);
 	return 0;
 }
 
diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index a7559f7..d30db40 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -259,10 +259,14 @@
 
 int ipte_lock_held(struct kvm_vcpu *vcpu)
 {
-	union ipte_control *ic = &vcpu->kvm->arch.sca->ipte_control;
+	if (vcpu->arch.sie_block->eca & 1) {
+		int rc;
 
-	if (vcpu->arch.sie_block->eca & 1)
-		return ic->kh != 0;
+		read_lock(&vcpu->kvm->arch.sca_lock);
+		rc = kvm_s390_get_ipte_control(vcpu->kvm)->kh != 0;
+		read_unlock(&vcpu->kvm->arch.sca_lock);
+		return rc;
+	}
 	return vcpu->kvm->arch.ipte_lock_count != 0;
 }
 
@@ -274,16 +278,20 @@
 	vcpu->kvm->arch.ipte_lock_count++;
 	if (vcpu->kvm->arch.ipte_lock_count > 1)
 		goto out;
-	ic = &vcpu->kvm->arch.sca->ipte_control;
+retry:
+	read_lock(&vcpu->kvm->arch.sca_lock);
+	ic = kvm_s390_get_ipte_control(vcpu->kvm);
 	do {
 		old = READ_ONCE(*ic);
-		while (old.k) {
+		if (old.k) {
+			read_unlock(&vcpu->kvm->arch.sca_lock);
 			cond_resched();
-			old = READ_ONCE(*ic);
+			goto retry;
 		}
 		new = old;
 		new.k = 1;
 	} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
+	read_unlock(&vcpu->kvm->arch.sca_lock);
 out:
 	mutex_unlock(&vcpu->kvm->arch.ipte_mutex);
 }
@@ -296,12 +304,14 @@
 	vcpu->kvm->arch.ipte_lock_count--;
 	if (vcpu->kvm->arch.ipte_lock_count)
 		goto out;
-	ic = &vcpu->kvm->arch.sca->ipte_control;
+	read_lock(&vcpu->kvm->arch.sca_lock);
+	ic = kvm_s390_get_ipte_control(vcpu->kvm);
 	do {
 		old = READ_ONCE(*ic);
 		new = old;
 		new.k = 0;
 	} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
+	read_unlock(&vcpu->kvm->arch.sca_lock);
 	wake_up(&vcpu->kvm->arch.ipte_wq);
 out:
 	mutex_unlock(&vcpu->kvm->arch.ipte_mutex);
@@ -311,24 +321,29 @@
 {
 	union ipte_control old, new, *ic;
 
-	ic = &vcpu->kvm->arch.sca->ipte_control;
+retry:
+	read_lock(&vcpu->kvm->arch.sca_lock);
+	ic = kvm_s390_get_ipte_control(vcpu->kvm);
 	do {
 		old = READ_ONCE(*ic);
-		while (old.kg) {
+		if (old.kg) {
+			read_unlock(&vcpu->kvm->arch.sca_lock);
 			cond_resched();
-			old = READ_ONCE(*ic);
+			goto retry;
 		}
 		new = old;
 		new.k = 1;
 		new.kh++;
 	} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
+	read_unlock(&vcpu->kvm->arch.sca_lock);
 }
 
 static void ipte_unlock_siif(struct kvm_vcpu *vcpu)
 {
 	union ipte_control old, new, *ic;
 
-	ic = &vcpu->kvm->arch.sca->ipte_control;
+	read_lock(&vcpu->kvm->arch.sca_lock);
+	ic = kvm_s390_get_ipte_control(vcpu->kvm);
 	do {
 		old = READ_ONCE(*ic);
 		new = old;
@@ -336,6 +351,7 @@
 		if (!new.kh)
 			new.k = 0;
 	} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
+	read_unlock(&vcpu->kvm->arch.sca_lock);
 	if (!new.kh)
 		wake_up(&vcpu->kvm->arch.ipte_wq);
 }
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index b4a5aa1..d53c107 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -54,9 +54,6 @@
 static int handle_noop(struct kvm_vcpu *vcpu)
 {
 	switch (vcpu->arch.sie_block->icptcode) {
-	case 0x0:
-		vcpu->stat.exit_null++;
-		break;
 	case 0x10:
 		vcpu->stat.exit_external_request++;
 		break;
@@ -338,8 +335,10 @@
 
 int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu)
 {
+	if (kvm_is_ucontrol(vcpu->kvm))
+		return -EOPNOTSUPP;
+
 	switch (vcpu->arch.sie_block->icptcode) {
-	case 0x00:
 	case 0x10:
 	case 0x18:
 		return handle_noop(vcpu);
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 6a75352..62ec925 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -34,6 +34,106 @@
 #define PFAULT_DONE 0x0680
 #define VIRTIO_PARAM 0x0d00
 
+/* handle external calls via sigp interpretation facility */
+static int sca_ext_call_pending(struct kvm_vcpu *vcpu, int *src_id)
+{
+	int c, scn;
+
+	if (!(atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_ECALL_PEND))
+		return 0;
+
+	read_lock(&vcpu->kvm->arch.sca_lock);
+	if (vcpu->kvm->arch.use_esca) {
+		struct esca_block *sca = vcpu->kvm->arch.sca;
+		union esca_sigp_ctrl sigp_ctrl =
+			sca->cpu[vcpu->vcpu_id].sigp_ctrl;
+
+		c = sigp_ctrl.c;
+		scn = sigp_ctrl.scn;
+	} else {
+		struct bsca_block *sca = vcpu->kvm->arch.sca;
+		union bsca_sigp_ctrl sigp_ctrl =
+			sca->cpu[vcpu->vcpu_id].sigp_ctrl;
+
+		c = sigp_ctrl.c;
+		scn = sigp_ctrl.scn;
+	}
+	read_unlock(&vcpu->kvm->arch.sca_lock);
+
+	if (src_id)
+		*src_id = scn;
+
+	return c;
+}
+
+static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id)
+{
+	int expect, rc;
+
+	read_lock(&vcpu->kvm->arch.sca_lock);
+	if (vcpu->kvm->arch.use_esca) {
+		struct esca_block *sca = vcpu->kvm->arch.sca;
+		union esca_sigp_ctrl *sigp_ctrl =
+			&(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
+		union esca_sigp_ctrl new_val = {0}, old_val = *sigp_ctrl;
+
+		new_val.scn = src_id;
+		new_val.c = 1;
+		old_val.c = 0;
+
+		expect = old_val.value;
+		rc = cmpxchg(&sigp_ctrl->value, old_val.value, new_val.value);
+	} else {
+		struct bsca_block *sca = vcpu->kvm->arch.sca;
+		union bsca_sigp_ctrl *sigp_ctrl =
+			&(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
+		union bsca_sigp_ctrl new_val = {0}, old_val = *sigp_ctrl;
+
+		new_val.scn = src_id;
+		new_val.c = 1;
+		old_val.c = 0;
+
+		expect = old_val.value;
+		rc = cmpxchg(&sigp_ctrl->value, old_val.value, new_val.value);
+	}
+	read_unlock(&vcpu->kvm->arch.sca_lock);
+
+	if (rc != expect) {
+		/* another external call is pending */
+		return -EBUSY;
+	}
+	atomic_or(CPUSTAT_ECALL_PEND, &vcpu->arch.sie_block->cpuflags);
+	return 0;
+}
+
+static void sca_clear_ext_call(struct kvm_vcpu *vcpu)
+{
+	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+	int rc, expect;
+
+	atomic_andnot(CPUSTAT_ECALL_PEND, li->cpuflags);
+	read_lock(&vcpu->kvm->arch.sca_lock);
+	if (vcpu->kvm->arch.use_esca) {
+		struct esca_block *sca = vcpu->kvm->arch.sca;
+		union esca_sigp_ctrl *sigp_ctrl =
+			&(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
+		union esca_sigp_ctrl old = *sigp_ctrl;
+
+		expect = old.value;
+		rc = cmpxchg(&sigp_ctrl->value, old.value, 0);
+	} else {
+		struct bsca_block *sca = vcpu->kvm->arch.sca;
+		union bsca_sigp_ctrl *sigp_ctrl =
+			&(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
+		union bsca_sigp_ctrl old = *sigp_ctrl;
+
+		expect = old.value;
+		rc = cmpxchg(&sigp_ctrl->value, old.value, 0);
+	}
+	read_unlock(&vcpu->kvm->arch.sca_lock);
+	WARN_ON(rc != expect); /* cannot clear? */
+}
+
 int psw_extint_disabled(struct kvm_vcpu *vcpu)
 {
 	return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_EXT);
@@ -792,13 +892,11 @@
 int kvm_s390_ext_call_pending(struct kvm_vcpu *vcpu)
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
-	uint8_t sigp_ctrl = vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl;
 
 	if (!sclp.has_sigpif)
 		return test_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs);
 
-	return (sigp_ctrl & SIGP_CTRL_C) &&
-	       (atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_ECALL_PEND);
+	return sca_ext_call_pending(vcpu, NULL);
 }
 
 int kvm_s390_vcpu_has_irq(struct kvm_vcpu *vcpu, int exclude_stop)
@@ -909,9 +1007,7 @@
 	memset(&li->irq, 0, sizeof(li->irq));
 	spin_unlock(&li->lock);
 
-	/* clear pending external calls set by sigp interpretation facility */
-	atomic_andnot(CPUSTAT_ECALL_PEND, li->cpuflags);
-	vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl = 0;
+	sca_clear_ext_call(vcpu);
 }
 
 int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
@@ -1003,21 +1099,6 @@
 	return 0;
 }
 
-static int __inject_extcall_sigpif(struct kvm_vcpu *vcpu, uint16_t src_id)
-{
-	unsigned char new_val, old_val;
-	uint8_t *sigp_ctrl = &vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl;
-
-	new_val = SIGP_CTRL_C | (src_id & SIGP_CTRL_SCN_MASK);
-	old_val = *sigp_ctrl & ~SIGP_CTRL_C;
-	if (cmpxchg(sigp_ctrl, old_val, new_val) != old_val) {
-		/* another external call is pending */
-		return -EBUSY;
-	}
-	atomic_or(CPUSTAT_ECALL_PEND, &vcpu->arch.sie_block->cpuflags);
-	return 0;
-}
-
 static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
@@ -1034,7 +1115,7 @@
 		return -EINVAL;
 
 	if (sclp.has_sigpif)
-		return __inject_extcall_sigpif(vcpu, src_id);
+		return sca_inject_ext_call(vcpu, src_id);
 
 	if (test_and_set_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs))
 		return -EBUSY;
@@ -2203,7 +2284,7 @@
 
 int kvm_s390_get_irq_state(struct kvm_vcpu *vcpu, __u8 __user *buf, int len)
 {
-	uint8_t sigp_ctrl = vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl;
+	int scn;
 	unsigned long sigp_emerg_pending[BITS_TO_LONGS(KVM_MAX_VCPUS)];
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 	unsigned long pending_irqs;
@@ -2243,14 +2324,12 @@
 		}
 	}
 
-	if ((sigp_ctrl & SIGP_CTRL_C) &&
-	    (atomic_read(&vcpu->arch.sie_block->cpuflags) &
-	     CPUSTAT_ECALL_PEND)) {
+	if (sca_ext_call_pending(vcpu, &scn)) {
 		if (n + sizeof(irq) > len)
 			return -ENOBUFS;
 		memset(&irq, 0, sizeof(irq));
 		irq.type = KVM_S390_INT_EXTERNAL_CALL;
-		irq.u.extcall.code = sigp_ctrl & SIGP_CTRL_SCN_MASK;
+		irq.u.extcall.code = scn;
 		if (copy_to_user(&buf[n], &irq, sizeof(irq)))
 			return -EFAULT;
 		n += sizeof(irq);
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 8465892..5927c61 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -246,7 +246,8 @@
 		break;
 	case KVM_CAP_NR_VCPUS:
 	case KVM_CAP_MAX_VCPUS:
-		r = KVM_MAX_VCPUS;
+		r = sclp.has_esca ? KVM_S390_ESCA_CPU_SLOTS
+				  : KVM_S390_BSCA_CPU_SLOTS;
 		break;
 	case KVM_CAP_NR_MEMSLOTS:
 		r = KVM_USER_MEM_SLOTS;
@@ -257,6 +258,9 @@
 	case KVM_CAP_S390_VECTOR_REGISTERS:
 		r = MACHINE_HAS_VX;
 		break;
+	case KVM_CAP_S390_RI:
+		r = test_facility(64);
+		break;
 	default:
 		r = 0;
 	}
@@ -283,6 +287,8 @@
 }
 
 /* Section: vm related */
+static void sca_del_vcpu(struct kvm_vcpu *vcpu);
+
 /*
  * Get (and clear) the dirty memory log for a memory slot.
  */
@@ -355,6 +361,20 @@
 		VM_EVENT(kvm, 3, "ENABLE: CAP_S390_VECTOR_REGISTERS %s",
 			 r ? "(not available)" : "(success)");
 		break;
+	case KVM_CAP_S390_RI:
+		r = -EINVAL;
+		mutex_lock(&kvm->lock);
+		if (atomic_read(&kvm->online_vcpus)) {
+			r = -EBUSY;
+		} else if (test_facility(64)) {
+			set_kvm_facility(kvm->arch.model.fac->mask, 64);
+			set_kvm_facility(kvm->arch.model.fac->list, 64);
+			r = 0;
+		}
+		mutex_unlock(&kvm->lock);
+		VM_EVENT(kvm, 3, "ENABLE: CAP_S390_RI %s",
+			 r ? "(not available)" : "(success)");
+		break;
 	case KVM_CAP_S390_USER_STSI:
 		VM_EVENT(kvm, 3, "%s", "ENABLE: CAP_S390_USER_STSI");
 		kvm->arch.user_stsi = 1;
@@ -375,8 +395,8 @@
 	case KVM_S390_VM_MEM_LIMIT_SIZE:
 		ret = 0;
 		VM_EVENT(kvm, 3, "QUERY: max guest memory: %lu bytes",
-			 kvm->arch.gmap->asce_end);
-		if (put_user(kvm->arch.gmap->asce_end, (u64 __user *)attr->addr))
+			 kvm->arch.mem_limit);
+		if (put_user(kvm->arch.mem_limit, (u64 __user *)attr->addr))
 			ret = -EFAULT;
 		break;
 	default:
@@ -428,9 +448,17 @@
 		if (get_user(new_limit, (u64 __user *)attr->addr))
 			return -EFAULT;
 
-		if (new_limit > kvm->arch.gmap->asce_end)
+		if (kvm->arch.mem_limit != KVM_S390_NO_MEM_LIMIT &&
+		    new_limit > kvm->arch.mem_limit)
 			return -E2BIG;
 
+		if (!new_limit)
+			return -EINVAL;
+
+		/* gmap_alloc takes last usable address */
+		if (new_limit != KVM_S390_NO_MEM_LIMIT)
+			new_limit -= 1;
+
 		ret = -EBUSY;
 		mutex_lock(&kvm->lock);
 		if (atomic_read(&kvm->online_vcpus) == 0) {
@@ -447,7 +475,9 @@
 			}
 		}
 		mutex_unlock(&kvm->lock);
-		VM_EVENT(kvm, 3, "SET: max guest memory: %lu bytes", new_limit);
+		VM_EVENT(kvm, 3, "SET: max guest address: %lu", new_limit);
+		VM_EVENT(kvm, 3, "New guest asce: 0x%pK",
+			 (void *) kvm->arch.gmap->asce);
 		break;
 	}
 	default:
@@ -1024,7 +1054,7 @@
 	u8 config[128];
 	int cc;
 
-	if (test_facility(2) && test_facility(12)) {
+	if (test_facility(12)) {
 		cc = kvm_s390_query_ap_config(config);
 
 		if (cc)
@@ -1075,6 +1105,15 @@
 	return 0;
 }
 
+static void sca_dispose(struct kvm *kvm)
+{
+	if (kvm->arch.use_esca)
+		free_pages_exact(kvm->arch.sca, sizeof(struct esca_block));
+	else
+		free_page((unsigned long)(kvm->arch.sca));
+	kvm->arch.sca = NULL;
+}
+
 int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
 	int i, rc;
@@ -1098,14 +1137,17 @@
 
 	rc = -ENOMEM;
 
-	kvm->arch.sca = (struct sca_block *) get_zeroed_page(GFP_KERNEL);
+	kvm->arch.use_esca = 0; /* start with basic SCA */
+	rwlock_init(&kvm->arch.sca_lock);
+	kvm->arch.sca = (struct bsca_block *) get_zeroed_page(GFP_KERNEL);
 	if (!kvm->arch.sca)
 		goto out_err;
 	spin_lock(&kvm_lock);
 	sca_offset += 16;
-	if (sca_offset + sizeof(struct sca_block) > PAGE_SIZE)
+	if (sca_offset + sizeof(struct bsca_block) > PAGE_SIZE)
 		sca_offset = 0;
-	kvm->arch.sca = (struct sca_block *) ((char *) kvm->arch.sca + sca_offset);
+	kvm->arch.sca = (struct bsca_block *)
+			((char *) kvm->arch.sca + sca_offset);
 	spin_unlock(&kvm_lock);
 
 	sprintf(debug_name, "kvm-%u", current->pid);
@@ -1157,8 +1199,14 @@
 
 	if (type & KVM_VM_S390_UCONTROL) {
 		kvm->arch.gmap = NULL;
+		kvm->arch.mem_limit = KVM_S390_NO_MEM_LIMIT;
 	} else {
-		kvm->arch.gmap = gmap_alloc(current->mm, (1UL << 44) - 1);
+		if (sclp.hamax == U64_MAX)
+			kvm->arch.mem_limit = TASK_MAX_SIZE;
+		else
+			kvm->arch.mem_limit = min_t(unsigned long, TASK_MAX_SIZE,
+						    sclp.hamax + 1);
+		kvm->arch.gmap = gmap_alloc(current->mm, kvm->arch.mem_limit - 1);
 		if (!kvm->arch.gmap)
 			goto out_err;
 		kvm->arch.gmap->private = kvm;
@@ -1170,14 +1218,14 @@
 	kvm->arch.epoch = 0;
 
 	spin_lock_init(&kvm->arch.start_stop_lock);
-	KVM_EVENT(3, "vm 0x%p created by pid %u", kvm, current->pid);
+	KVM_EVENT(3, "vm 0x%pK created by pid %u", kvm, current->pid);
 
 	return 0;
 out_err:
 	kfree(kvm->arch.crypto.crycb);
 	free_page((unsigned long)kvm->arch.model.fac);
 	debug_unregister(kvm->arch.dbf);
-	free_page((unsigned long)(kvm->arch.sca));
+	sca_dispose(kvm);
 	KVM_EVENT(3, "creation of vm failed: %d", rc);
 	return rc;
 }
@@ -1188,14 +1236,8 @@
 	trace_kvm_s390_destroy_vcpu(vcpu->vcpu_id);
 	kvm_s390_clear_local_irqs(vcpu);
 	kvm_clear_async_pf_completion_queue(vcpu);
-	if (!kvm_is_ucontrol(vcpu->kvm)) {
-		clear_bit(63 - vcpu->vcpu_id,
-			  (unsigned long *) &vcpu->kvm->arch.sca->mcn);
-		if (vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda ==
-		    (__u64) vcpu->arch.sie_block)
-			vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda = 0;
-	}
-	smp_mb();
+	if (!kvm_is_ucontrol(vcpu->kvm))
+		sca_del_vcpu(vcpu);
 
 	if (kvm_is_ucontrol(vcpu->kvm))
 		gmap_free(vcpu->arch.gmap);
@@ -1228,14 +1270,14 @@
 {
 	kvm_free_vcpus(kvm);
 	free_page((unsigned long)kvm->arch.model.fac);
-	free_page((unsigned long)(kvm->arch.sca));
+	sca_dispose(kvm);
 	debug_unregister(kvm->arch.dbf);
 	kfree(kvm->arch.crypto.crycb);
 	if (!kvm_is_ucontrol(kvm))
 		gmap_free(kvm->arch.gmap);
 	kvm_s390_destroy_adapters(kvm);
 	kvm_s390_clear_float_irqs(kvm);
-	KVM_EVENT(3, "vm 0x%p destroyed", kvm);
+	KVM_EVENT(3, "vm 0x%pK destroyed", kvm);
 }
 
 /* Section: vcpu related */
@@ -1249,6 +1291,117 @@
 	return 0;
 }
 
+static void sca_del_vcpu(struct kvm_vcpu *vcpu)
+{
+	read_lock(&vcpu->kvm->arch.sca_lock);
+	if (vcpu->kvm->arch.use_esca) {
+		struct esca_block *sca = vcpu->kvm->arch.sca;
+
+		clear_bit_inv(vcpu->vcpu_id, (unsigned long *) sca->mcn);
+		sca->cpu[vcpu->vcpu_id].sda = 0;
+	} else {
+		struct bsca_block *sca = vcpu->kvm->arch.sca;
+
+		clear_bit_inv(vcpu->vcpu_id, (unsigned long *) &sca->mcn);
+		sca->cpu[vcpu->vcpu_id].sda = 0;
+	}
+	read_unlock(&vcpu->kvm->arch.sca_lock);
+}
+
+static void sca_add_vcpu(struct kvm_vcpu *vcpu)
+{
+	read_lock(&vcpu->kvm->arch.sca_lock);
+	if (vcpu->kvm->arch.use_esca) {
+		struct esca_block *sca = vcpu->kvm->arch.sca;
+
+		sca->cpu[vcpu->vcpu_id].sda = (__u64) vcpu->arch.sie_block;
+		vcpu->arch.sie_block->scaoh = (__u32)(((__u64)sca) >> 32);
+		vcpu->arch.sie_block->scaol = (__u32)(__u64)sca & ~0x3fU;
+		vcpu->arch.sie_block->ecb2 |= 0x04U;
+		set_bit_inv(vcpu->vcpu_id, (unsigned long *) sca->mcn);
+	} else {
+		struct bsca_block *sca = vcpu->kvm->arch.sca;
+
+		sca->cpu[vcpu->vcpu_id].sda = (__u64) vcpu->arch.sie_block;
+		vcpu->arch.sie_block->scaoh = (__u32)(((__u64)sca) >> 32);
+		vcpu->arch.sie_block->scaol = (__u32)(__u64)sca;
+		set_bit_inv(vcpu->vcpu_id, (unsigned long *) &sca->mcn);
+	}
+	read_unlock(&vcpu->kvm->arch.sca_lock);
+}
+
+/* Basic SCA to Extended SCA data copy routines */
+static inline void sca_copy_entry(struct esca_entry *d, struct bsca_entry *s)
+{
+	d->sda = s->sda;
+	d->sigp_ctrl.c = s->sigp_ctrl.c;
+	d->sigp_ctrl.scn = s->sigp_ctrl.scn;
+}
+
+static void sca_copy_b_to_e(struct esca_block *d, struct bsca_block *s)
+{
+	int i;
+
+	d->ipte_control = s->ipte_control;
+	d->mcn[0] = s->mcn;
+	for (i = 0; i < KVM_S390_BSCA_CPU_SLOTS; i++)
+		sca_copy_entry(&d->cpu[i], &s->cpu[i]);
+}
+
+static int sca_switch_to_extended(struct kvm *kvm)
+{
+	struct bsca_block *old_sca = kvm->arch.sca;
+	struct esca_block *new_sca;
+	struct kvm_vcpu *vcpu;
+	unsigned int vcpu_idx;
+	u32 scaol, scaoh;
+
+	new_sca = alloc_pages_exact(sizeof(*new_sca), GFP_KERNEL|__GFP_ZERO);
+	if (!new_sca)
+		return -ENOMEM;
+
+	scaoh = (u32)((u64)(new_sca) >> 32);
+	scaol = (u32)(u64)(new_sca) & ~0x3fU;
+
+	kvm_s390_vcpu_block_all(kvm);
+	write_lock(&kvm->arch.sca_lock);
+
+	sca_copy_b_to_e(new_sca, old_sca);
+
+	kvm_for_each_vcpu(vcpu_idx, vcpu, kvm) {
+		vcpu->arch.sie_block->scaoh = scaoh;
+		vcpu->arch.sie_block->scaol = scaol;
+		vcpu->arch.sie_block->ecb2 |= 0x04U;
+	}
+	kvm->arch.sca = new_sca;
+	kvm->arch.use_esca = 1;
+
+	write_unlock(&kvm->arch.sca_lock);
+	kvm_s390_vcpu_unblock_all(kvm);
+
+	free_page((unsigned long)old_sca);
+
+	VM_EVENT(kvm, 2, "Switched to ESCA (0x%pK -> 0x%pK)",
+		 old_sca, kvm->arch.sca);
+	return 0;
+}
+
+static int sca_can_add_vcpu(struct kvm *kvm, unsigned int id)
+{
+	int rc;
+
+	if (id < KVM_S390_BSCA_CPU_SLOTS)
+		return true;
+	if (!sclp.has_esca)
+		return false;
+
+	mutex_lock(&kvm->lock);
+	rc = kvm->arch.use_esca ? 0 : sca_switch_to_extended(kvm);
+	mutex_unlock(&kvm->lock);
+
+	return rc == 0 && id < KVM_S390_ESCA_CPU_SLOTS;
+}
+
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
@@ -1259,6 +1412,8 @@
 				    KVM_SYNC_CRS |
 				    KVM_SYNC_ARCH0 |
 				    KVM_SYNC_PFAULT;
+	if (test_kvm_facility(vcpu->kvm, 64))
+		vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB;
 	if (test_kvm_facility(vcpu->kvm, 129))
 		vcpu->run->kvm_valid_regs |= KVM_SYNC_VRS;
 
@@ -1369,8 +1524,11 @@
 	vcpu->arch.sie_block->epoch = vcpu->kvm->arch.epoch;
 	preempt_enable();
 	mutex_unlock(&vcpu->kvm->lock);
-	if (!kvm_is_ucontrol(vcpu->kvm))
+	if (!kvm_is_ucontrol(vcpu->kvm)) {
 		vcpu->arch.gmap = vcpu->kvm->arch.gmap;
+		sca_add_vcpu(vcpu);
+	}
+
 }
 
 static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu)
@@ -1439,10 +1597,13 @@
 		vcpu->arch.sie_block->eca |= 1;
 	if (sclp.has_sigpif)
 		vcpu->arch.sie_block->eca |= 0x10000000U;
+	if (test_kvm_facility(vcpu->kvm, 64))
+		vcpu->arch.sie_block->ecb3 |= 0x01;
 	if (test_kvm_facility(vcpu->kvm, 129)) {
 		vcpu->arch.sie_block->eca |= 0x00020000;
 		vcpu->arch.sie_block->ecd |= 0x20000000;
 	}
+	vcpu->arch.sie_block->riccbd = (unsigned long) &vcpu->run->s.regs.riccb;
 	vcpu->arch.sie_block->ictl |= ICTL_ISKE | ICTL_SSKE | ICTL_RRBE;
 
 	if (vcpu->kvm->arch.use_cmma) {
@@ -1465,7 +1626,7 @@
 	struct sie_page *sie_page;
 	int rc = -EINVAL;
 
-	if (id >= KVM_MAX_VCPUS)
+	if (!kvm_is_ucontrol(kvm) && !sca_can_add_vcpu(kvm, id))
 		goto out;
 
 	rc = -ENOMEM;
@@ -1482,20 +1643,6 @@
 	vcpu->arch.sie_block->itdba = (unsigned long) &sie_page->itdb;
 
 	vcpu->arch.sie_block->icpua = id;
-	if (!kvm_is_ucontrol(kvm)) {
-		if (!kvm->arch.sca) {
-			WARN_ON_ONCE(1);
-			goto out_free_cpu;
-		}
-		if (!kvm->arch.sca->cpu[id].sda)
-			kvm->arch.sca->cpu[id].sda =
-				(__u64) vcpu->arch.sie_block;
-		vcpu->arch.sie_block->scaoh =
-			(__u32)(((__u64)kvm->arch.sca) >> 32);
-		vcpu->arch.sie_block->scaol = (__u32)(__u64)kvm->arch.sca;
-		set_bit(63 - id, (unsigned long *) &kvm->arch.sca->mcn);
-	}
-
 	spin_lock_init(&vcpu->arch.local_int.lock);
 	vcpu->arch.local_int.float_int = &kvm->arch.float_int;
 	vcpu->arch.local_int.wq = &vcpu->wq;
@@ -1509,15 +1656,13 @@
 	 */
 	vcpu->arch.guest_fpregs.fprs = kzalloc(sizeof(freg_t) * __NUM_FPRS,
 					       GFP_KERNEL);
-	if (!vcpu->arch.guest_fpregs.fprs) {
-		rc = -ENOMEM;
+	if (!vcpu->arch.guest_fpregs.fprs)
 		goto out_free_sie_block;
-	}
 
 	rc = kvm_vcpu_init(vcpu, kvm, id);
 	if (rc)
 		goto out_free_sie_block;
-	VM_EVENT(kvm, 3, "create cpu %d at %p, sie block at %p", id, vcpu,
+	VM_EVENT(kvm, 3, "create cpu %d at 0x%pK, sie block at 0x%pK", id, vcpu,
 		 vcpu->arch.sie_block);
 	trace_kvm_s390_create_vcpu(id, vcpu, vcpu->arch.sie_block);
 
@@ -2013,7 +2158,8 @@
 	 */
 	kvm_check_async_pf_completion(vcpu);
 
-	memcpy(&vcpu->arch.sie_block->gg14, &vcpu->run->s.regs.gprs[14], 16);
+	vcpu->arch.sie_block->gg14 = vcpu->run->s.regs.gprs[14];
+	vcpu->arch.sie_block->gg15 = vcpu->run->s.regs.gprs[15];
 
 	if (need_resched())
 		schedule();
@@ -2071,8 +2217,6 @@
 
 static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
 {
-	int rc = -1;
-
 	VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
 		   vcpu->arch.sie_block->icptcode);
 	trace_kvm_s390_sie_exit(vcpu, vcpu->arch.sie_block->icptcode);
@@ -2080,40 +2224,36 @@
 	if (guestdbg_enabled(vcpu))
 		kvm_s390_restore_guest_per_regs(vcpu);
 
-	if (exit_reason >= 0) {
-		rc = 0;
+	vcpu->run->s.regs.gprs[14] = vcpu->arch.sie_block->gg14;
+	vcpu->run->s.regs.gprs[15] = vcpu->arch.sie_block->gg15;
+
+	if (vcpu->arch.sie_block->icptcode > 0) {
+		int rc = kvm_handle_sie_intercept(vcpu);
+
+		if (rc != -EOPNOTSUPP)
+			return rc;
+		vcpu->run->exit_reason = KVM_EXIT_S390_SIEIC;
+		vcpu->run->s390_sieic.icptcode = vcpu->arch.sie_block->icptcode;
+		vcpu->run->s390_sieic.ipa = vcpu->arch.sie_block->ipa;
+		vcpu->run->s390_sieic.ipb = vcpu->arch.sie_block->ipb;
+		return -EREMOTE;
+	} else if (exit_reason != -EFAULT) {
+		vcpu->stat.exit_null++;
+		return 0;
 	} else if (kvm_is_ucontrol(vcpu->kvm)) {
 		vcpu->run->exit_reason = KVM_EXIT_S390_UCONTROL;
 		vcpu->run->s390_ucontrol.trans_exc_code =
 						current->thread.gmap_addr;
 		vcpu->run->s390_ucontrol.pgm_code = 0x10;
-		rc = -EREMOTE;
-
+		return -EREMOTE;
 	} else if (current->thread.gmap_pfault) {
 		trace_kvm_s390_major_guest_pfault(vcpu);
 		current->thread.gmap_pfault = 0;
-		if (kvm_arch_setup_async_pf(vcpu)) {
-			rc = 0;
-		} else {
-			gpa_t gpa = current->thread.gmap_addr;
-			rc = kvm_arch_fault_in_page(vcpu, gpa, 1);
-		}
+		if (kvm_arch_setup_async_pf(vcpu))
+			return 0;
+		return kvm_arch_fault_in_page(vcpu, current->thread.gmap_addr, 1);
 	}
-
-	if (rc == -1)
-		rc = vcpu_post_run_fault_in_sie(vcpu);
-
-	memcpy(&vcpu->run->s.regs.gprs[14], &vcpu->arch.sie_block->gg14, 16);
-
-	if (rc == 0) {
-		if (kvm_is_ucontrol(vcpu->kvm))
-			/* Don't exit for host interrupts. */
-			rc = vcpu->arch.sie_block->icptcode ? -EOPNOTSUPP : 0;
-		else
-			rc = kvm_handle_sie_intercept(vcpu);
-	}
-
-	return rc;
+	return vcpu_post_run_fault_in_sie(vcpu);
 }
 
 static int __vcpu_run(struct kvm_vcpu *vcpu)
@@ -2233,18 +2373,8 @@
 		rc = 0;
 	}
 
-	if (rc == -EOPNOTSUPP) {
-		/* intercept cannot be handled in-kernel, prepare kvm-run */
-		kvm_run->exit_reason         = KVM_EXIT_S390_SIEIC;
-		kvm_run->s390_sieic.icptcode = vcpu->arch.sie_block->icptcode;
-		kvm_run->s390_sieic.ipa      = vcpu->arch.sie_block->ipa;
-		kvm_run->s390_sieic.ipb      = vcpu->arch.sie_block->ipb;
-		rc = 0;
-	}
-
 	if (rc == -EREMOTE) {
-		/* intercept was handled, but userspace support is needed
-		 * kvm_run has been prepared by the handler */
+		/* userspace support is needed, kvm_run has been prepared */
 		rc = 0;
 	}
 
@@ -2736,6 +2866,9 @@
 	if (mem->memory_size & 0xffffful)
 		return -EINVAL;
 
+	if (mem->guest_phys_addr + mem->memory_size > kvm->arch.mem_limit)
+		return -EINVAL;
+
 	return 0;
 }
 
@@ -2767,6 +2900,11 @@
 
 static int __init kvm_s390_init(void)
 {
+	if (!sclp.has_sief2) {
+		pr_info("SIE not available\n");
+		return -ENODEV;
+	}
+
 	return kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
 }
 
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 1e70e00..df1abad 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -340,4 +340,11 @@
 void kvm_s390_prepare_debug_exit(struct kvm_vcpu *vcpu);
 void kvm_s390_handle_per_event(struct kvm_vcpu *vcpu);
 
+/* support for Basic/Extended SCA handling */
+static inline union ipte_control *kvm_s390_get_ipte_control(struct kvm *kvm)
+{
+	struct bsca_block *sca = kvm->arch.sca; /* SCA version doesn't matter */
+
+	return &sca->ipte_control;
+}
 #endif
diff --git a/arch/s390/kvm/trace-s390.h b/arch/s390/kvm/trace-s390.h
index cc1d6c6..396485b 100644
--- a/arch/s390/kvm/trace-s390.h
+++ b/arch/s390/kvm/trace-s390.h
@@ -55,8 +55,8 @@
 		    __entry->sie_block = sie_block;
 		    ),
 
-	    TP_printk("create cpu %d at %p, sie block at %p", __entry->id,
-		      __entry->vcpu, __entry->sie_block)
+	    TP_printk("create cpu %d at 0x%pK, sie block at 0x%pK",
+		      __entry->id, __entry->vcpu, __entry->sie_block)
 	);
 
 TRACE_EVENT(kvm_s390_destroy_vcpu,
@@ -254,7 +254,7 @@
 		    __entry->kvm = kvm;
 		    ),
 
-	    TP_printk("enabling channel I/O support (kvm @ %p)\n",
+	    TP_printk("enabling channel I/O support (kvm @ %pK)\n",
 		      __entry->kvm)
 	);
 
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 54ef3bc..63b03989 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -133,7 +133,7 @@
 /**
  * gmap_alloc - allocate a guest address space
  * @mm: pointer to the parent mm_struct
- * @limit: maximum size of the gmap address space
+ * @limit: maximum address of the gmap address space
  *
  * Returns a guest address space structure.
  */
@@ -402,7 +402,7 @@
 	if ((from | to | len) & (PMD_SIZE - 1))
 		return -EINVAL;
 	if (len == 0 || from + len < from || to + len < to ||
-	    from + len > TASK_MAX_SIZE || to + len > gmap->asce_end)
+	    from + len - 1 > TASK_MAX_SIZE || to + len - 1 > gmap->asce_end)
 		return -EINVAL;
 
 	flush = 0;
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index d348f2c..32da0a6 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -366,8 +366,7 @@
 	pa = page_to_phys(page);
 	memset((void *) pa, 0, size);
 
-	map = s390_dma_map_pages(dev, page, pa % PAGE_SIZE,
-				 size, DMA_BIDIRECTIONAL, NULL);
+	map = s390_dma_map_pages(dev, page, 0, size, DMA_BIDIRECTIONAL, NULL);
 	if (dma_mapping_error(dev, map)) {
 		free_pages(pa, get_order(size));
 		return NULL;
diff --git a/arch/sh/boards/mach-ap325rxa/setup.c b/arch/sh/boards/mach-ap325rxa/setup.c
index cbd2a9f..62c3b81 100644
--- a/arch/sh/boards/mach-ap325rxa/setup.c
+++ b/arch/sh/boards/mach-ap325rxa/setup.c
@@ -27,10 +27,10 @@
 #include <linux/gpio.h>
 #include <linux/videodev2.h>
 #include <linux/sh_intc.h>
-#include <media/ov772x.h>
+#include <media/i2c/ov772x.h>
 #include <media/soc_camera.h>
-#include <media/soc_camera_platform.h>
-#include <media/sh_mobile_ceu.h>
+#include <linux/platform_data/media/soc_camera_platform.h>
+#include <media/drv-intf/sh_mobile_ceu.h>
 #include <video/sh_mobile_lcdc.h>
 #include <asm/io.h>
 #include <asm/clock.h>
diff --git a/arch/sh/boards/mach-ecovec24/setup.c b/arch/sh/boards/mach-ecovec24/setup.c
index d531791..a9c0c07 100644
--- a/arch/sh/boards/mach-ecovec24/setup.c
+++ b/arch/sh/boards/mach-ecovec24/setup.c
@@ -38,10 +38,10 @@
 #include <video/sh_mobile_lcdc.h>
 #include <sound/sh_fsi.h>
 #include <sound/simple_card.h>
-#include <media/sh_mobile_ceu.h>
+#include <media/drv-intf/sh_mobile_ceu.h>
 #include <media/soc_camera.h>
-#include <media/tw9910.h>
-#include <media/mt9t112.h>
+#include <media/i2c/tw9910.h>
+#include <media/i2c/mt9t112.h>
 #include <asm/heartbeat.h>
 #include <asm/clock.h>
 #include <asm/suspend.h>
@@ -900,8 +900,8 @@
 	.resource       = irda_resources,
 };
 
-#include <media/ak881x.h>
-#include <media/sh_vou.h>
+#include <media/i2c/ak881x.h>
+#include <media/drv-intf/sh_vou.h>
 
 static struct ak881x_pdata ak881x_pdata = {
 	.flags = AK881X_IF_MODE_SLAVE,
diff --git a/arch/sh/boards/mach-kfr2r09/setup.c b/arch/sh/boards/mach-kfr2r09/setup.c
index 7d997ce..6bd9230 100644
--- a/arch/sh/boards/mach-kfr2r09/setup.c
+++ b/arch/sh/boards/mach-kfr2r09/setup.c
@@ -27,9 +27,9 @@
 #include <linux/usb/r8a66597.h>
 #include <linux/videodev2.h>
 #include <linux/sh_intc.h>
-#include <media/rj54n1cb0c.h>
+#include <media/i2c/rj54n1cb0c.h>
 #include <media/soc_camera.h>
-#include <media/sh_mobile_ceu.h>
+#include <media/drv-intf/sh_mobile_ceu.h>
 #include <video/sh_mobile_lcdc.h>
 #include <asm/suspend.h>
 #include <asm/clock.h>
diff --git a/arch/sh/boards/mach-migor/setup.c b/arch/sh/boards/mach-migor/setup.c
index 29b7c0d..8f237a5 100644
--- a/arch/sh/boards/mach-migor/setup.c
+++ b/arch/sh/boards/mach-migor/setup.c
@@ -27,10 +27,10 @@
 #include <linux/videodev2.h>
 #include <linux/sh_intc.h>
 #include <video/sh_mobile_lcdc.h>
-#include <media/sh_mobile_ceu.h>
-#include <media/ov772x.h>
+#include <media/drv-intf/sh_mobile_ceu.h>
+#include <media/i2c/ov772x.h>
 #include <media/soc_camera.h>
-#include <media/tw9910.h>
+#include <media/i2c/tw9910.h>
 #include <asm/clock.h>
 #include <asm/machvec.h>
 #include <asm/io.h>
diff --git a/arch/sh/boards/mach-se/7724/setup.c b/arch/sh/boards/mach-se/7724/setup.c
index 4f6635a..e0e1df1 100644
--- a/arch/sh/boards/mach-se/7724/setup.c
+++ b/arch/sh/boards/mach-se/7724/setup.c
@@ -30,7 +30,7 @@
 #include <linux/sh_intc.h>
 #include <linux/videodev2.h>
 #include <video/sh_mobile_lcdc.h>
-#include <media/sh_mobile_ceu.h>
+#include <media/drv-intf/sh_mobile_ceu.h>
 #include <sound/sh_fsi.h>
 #include <sound/simple_card.h>
 #include <asm/io.h>
@@ -534,8 +534,8 @@
 	.resource       = irda_resources,
 };
 
-#include <media/ak881x.h>
-#include <media/sh_vou.h>
+#include <media/i2c/ak881x.h>
+#include <media/drv-intf/sh_vou.h>
 
 static struct ak881x_pdata ak881x_pdata = {
 	.flags = AK881X_IF_MODE_SLAVE,
diff --git a/arch/sparc/include/asm/uaccess_32.h b/arch/sparc/include/asm/uaccess_32.h
index 64ee103..57aca27 100644
--- a/arch/sparc/include/asm/uaccess_32.h
+++ b/arch/sparc/include/asm/uaccess_32.h
@@ -205,31 +205,6 @@
 	__gu_ret; \
 })
 
-#define __get_user_check_ret(x, addr, size, type, retval) ({ \
-	register unsigned long __gu_val __asm__ ("l1"); \
-	if (__access_ok(addr, size)) { \
-		switch (size) { \
-		case 1: \
-			__get_user_asm_ret(__gu_val, ub, addr, retval); \
-			break; \
-		case 2: \
-			__get_user_asm_ret(__gu_val, uh, addr, retval); \
-			break; \
-		case 4: \
-			__get_user_asm_ret(__gu_val, , addr, retval); \
-			break; \
-		case 8: \
-			__get_user_asm_ret(__gu_val, d, addr, retval); \
-			break; \
-		default: \
-			if (__get_user_bad()) \
-				return retval; \
-		} \
-		x = (__force type) __gu_val; \
-	} else \
-		return retval; \
-})
-
 #define __get_user_nocheck(x, addr, size, type) ({			\
 	register int __gu_ret;						\
 	register unsigned long __gu_val;				\
@@ -247,20 +222,6 @@
 	__gu_ret;							\
 })
 
-#define __get_user_nocheck_ret(x, addr, size, type, retval) ({		\
-	register unsigned long __gu_val __asm__ ("l1");			\
-	switch (size) {							\
-	case 1: __get_user_asm_ret(__gu_val, ub, addr, retval); break;	\
-	case 2: __get_user_asm_ret(__gu_val, uh, addr, retval); break;	\
-	case 4: __get_user_asm_ret(__gu_val, , addr, retval);  break;	\
-	case 8: __get_user_asm_ret(__gu_val, d, addr, retval); break;	\
-	default:							\
-		if (__get_user_bad())					\
-			return retval;					\
-	}								\
-	x = (__force type) __gu_val;					\
-})
-
 #define __get_user_asm(x, size, addr, ret)				\
 __asm__ __volatile__(							\
 		"/* Get user asm, inline. */\n"				\
@@ -281,32 +242,6 @@
 	       : "=&r" (ret), "=&r" (x) : "m" (*__m(addr)),		\
 		 "i" (-EFAULT))
 
-#define __get_user_asm_ret(x, size, addr, retval)			\
-if (__builtin_constant_p(retval) && retval == -EFAULT)			\
-	__asm__ __volatile__(						\
-			"/* Get user asm ret, inline. */\n"		\
-		"1:\t"	"ld"#size " %1, %0\n\n\t"			\
-			".section __ex_table,#alloc\n\t"		\
-			".align	4\n\t"					\
-			".word	1b,__ret_efault\n\n\t"			\
-			".previous\n\t"					\
-		       : "=&r" (x) : "m" (*__m(addr)));			\
-else									\
-	__asm__ __volatile__(						\
-			"/* Get user asm ret, inline. */\n"		\
-		"1:\t"	"ld"#size " %1, %0\n\n\t"			\
-			".section .fixup,#alloc,#execinstr\n\t"		\
-			".align	4\n"					\
-		"3:\n\t"						\
-			"ret\n\t"					\
-			" restore %%g0, %2, %%o0\n\n\t"			\
-			".previous\n\t"					\
-			".section __ex_table,#alloc\n\t"		\
-			".align	4\n\t"					\
-			".word	1b, 3b\n\n\t"				\
-			".previous\n\t"					\
-		       : "=&r" (x) : "m" (*__m(addr)), "i" (retval))
-
 int __get_user_bad(void);
 
 unsigned long __copy_user(void __user *to, const void __user *from, unsigned long size);
diff --git a/arch/sparc/include/asm/uaccess_64.h b/arch/sparc/include/asm/uaccess_64.h
index ea6e9a2..e9a51d6 100644
--- a/arch/sparc/include/asm/uaccess_64.h
+++ b/arch/sparc/include/asm/uaccess_64.h
@@ -179,20 +179,6 @@
 	 __gu_ret;							     \
 })
 
-#define __get_user_nocheck_ret(data, addr, size, type, retval) ({	\
-	register unsigned long __gu_val __asm__ ("l1");			\
-	switch (size) {							\
-	case 1: __get_user_asm_ret(__gu_val, ub, addr, retval); break;	\
-	case 2: __get_user_asm_ret(__gu_val, uh, addr, retval); break;	\
-	case 4: __get_user_asm_ret(__gu_val, uw, addr, retval); break;	\
-	case 8: __get_user_asm_ret(__gu_val, x, addr, retval); break;	\
-	default:							\
-		if (__get_user_bad())					\
-			return retval;					\
-	}								\
-	data = (__force type) __gu_val;					\
-})
-
 #define __get_user_asm(x, size, addr, ret)				\
 __asm__ __volatile__(							\
 		"/* Get user asm, inline. */\n"				\
@@ -214,32 +200,6 @@
 	       : "=r" (ret), "=r" (x) : "r" (__m(addr)),		\
 		 "i" (-EFAULT))
 
-#define __get_user_asm_ret(x, size, addr, retval)			\
-if (__builtin_constant_p(retval) && retval == -EFAULT)			\
-	__asm__ __volatile__(						\
-		"/* Get user asm ret, inline. */\n"			\
-	"1:\t"	"ld"#size "a [%1] %%asi, %0\n\n\t"			\
-		".section __ex_table,\"a\"\n\t"				\
-		".align	4\n\t"						\
-		".word	1b,__ret_efault\n\n\t"				\
-		".previous\n\t"						\
-	       : "=r" (x) : "r" (__m(addr)));				\
-else									\
-	__asm__ __volatile__(						\
-		"/* Get user asm ret, inline. */\n"			\
-	"1:\t"	"ld"#size "a [%1] %%asi, %0\n\n\t"			\
-		".section .fixup,#alloc,#execinstr\n\t"			\
-		".align	4\n"						\
-	"3:\n\t"							\
-		"ret\n\t"						\
-		" restore %%g0, %2, %%o0\n\n\t"				\
-		".previous\n\t"						\
-		".section __ex_table,\"a\"\n\t"				\
-		".align	4\n\t"						\
-		".word	1b, 3b\n\n\t"					\
-		".previous\n\t"						\
-	       : "=r" (x) : "r" (__m(addr)), "i" (retval))
-
 int __get_user_bad(void);
 
 unsigned long __must_check ___copy_from_user(void *to,
diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c
index 6f80936..1122886 100644
--- a/arch/sparc/kernel/mdesc.c
+++ b/arch/sparc/kernel/mdesc.c
@@ -1033,25 +1033,9 @@
 
 static loff_t mdesc_llseek(struct file *file, loff_t offset, int whence)
 {
-	struct mdesc_handle *hp;
+	struct mdesc_handle *hp = file->private_data;
 
-	switch (whence) {
-	case SEEK_CUR:
-		offset += file->f_pos;
-		break;
-	case SEEK_SET:
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	hp = file->private_data;
-	if (offset > hp->handle_size)
-		return -EINVAL;
-	else
-		file->f_pos = offset;
-
-	return offset;
+	return no_seek_end_llseek_size(file, offset, whence, hp->handle_size);
 }
 
 /* mdesc_close() - /dev/mdesc is being closed, release the reference to
diff --git a/arch/tile/include/asm/cmpxchg.h b/arch/tile/include/asm/cmpxchg.h
index 0ccda3c..25d5899 100644
--- a/arch/tile/include/asm/cmpxchg.h
+++ b/arch/tile/include/asm/cmpxchg.h
@@ -127,8 +127,6 @@
 
 #endif
 
-#define tas(ptr) xchg((ptr), 1)
-
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_TILE_CMPXCHG_H */
diff --git a/arch/um/Kconfig.common b/arch/um/Kconfig.common
index d195a87..cc00134 100644
--- a/arch/um/Kconfig.common
+++ b/arch/um/Kconfig.common
@@ -2,6 +2,7 @@
 	bool
 	default y
 	select HAVE_ARCH_AUDITSYSCALL
+	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_UID16
 	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select GENERIC_IRQ_SHOW
diff --git a/arch/um/Kconfig.um b/arch/um/Kconfig.um
index 28a9885..4b2ed58 100644
--- a/arch/um/Kconfig.um
+++ b/arch/um/Kconfig.um
@@ -104,3 +104,19 @@
 	int
 	default 3 if 3_LEVEL_PGTABLES
 	default 2
+
+config SECCOMP
+	def_bool y
+	prompt "Enable seccomp to safely compute untrusted bytecode"
+	---help---
+	  This kernel feature is useful for number crunching applications
+	  that may need to compute untrusted bytecode during their
+	  execution. By using pipes or other transports made available to
+	  the process as file descriptors supporting the read/write
+	  syscalls, it's possible to isolate those applications in
+	  their own address space using seccomp. Once seccomp is
+	  enabled via prctl(PR_SET_SECCOMP), it cannot be disabled
+	  and the task is only allowed to execute a few safe syscalls
+	  defined by each seccomp mode.
+
+	  If unsure, say Y.
diff --git a/arch/um/drivers/hostaudio_kern.c b/arch/um/drivers/hostaudio_kern.c
index f6b911c..3a4b587 100644
--- a/arch/um/drivers/hostaudio_kern.c
+++ b/arch/um/drivers/hostaudio_kern.c
@@ -105,13 +105,9 @@
 	printk(KERN_DEBUG "hostaudio: write called, count = %d\n", count);
 #endif
 
-	kbuf = kmalloc(count, GFP_KERNEL);
-	if (kbuf == NULL)
-		return -ENOMEM;
-
-	err = -EFAULT;
-	if (copy_from_user(kbuf, buffer, count))
-		goto out;
+	kbuf = memdup_user(buffer, count);
+	if (IS_ERR(kbuf))
+		return PTR_ERR(kbuf);
 
 	err = os_write_file(state->fd, kbuf, count);
 	if (err < 0)
diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c
index 29880c9..b821b13 100644
--- a/arch/um/drivers/mconsole_kern.c
+++ b/arch/um/drivers/mconsole_kern.c
@@ -748,19 +748,11 @@
 {
 	char *buf;
 
-	buf = kmalloc(count + 1, GFP_KERNEL);
-	if (buf == NULL)
-		return -ENOMEM;
-
-	if (copy_from_user(buf, buffer, count)) {
-		count = -EFAULT;
-		goto out;
-	}
-
-	buf[count] = '\0';
+	buf = memdup_user_nul(buffer, count);
+	if (IS_ERR(buf))
+		return PTR_ERR(buf);
 
 	mconsole_notify(notify_socket, MCONSOLE_USER_NOTIFY, buf, count);
- out:
 	kfree(buf);
 	return count;
 }
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index e8ab93c..39ba207 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -535,11 +535,7 @@
 {
 	int err;
 
-	err = os_seek_file(fd, offset);
-	if (err < 0)
-		return err;
-
-	err = os_read_file(fd, buf, len);
+	err = os_pread_file(fd, buf, len, offset);
 	if (err < 0)
 		return err;
 
@@ -1377,14 +1373,8 @@
 	if(req->cow_offset == -1)
 		return 0;
 
-	n = os_seek_file(req->fds[1], req->cow_offset);
-	if(n < 0){
-		printk("do_io - bitmap lseek failed : err = %d\n", -n);
-		return 1;
-	}
-
-	n = os_write_file(req->fds[1], &req->bitmap_words,
-			  sizeof(req->bitmap_words));
+	n = os_pwrite_file(req->fds[1], &req->bitmap_words,
+			  sizeof(req->bitmap_words), req->cow_offset);
 	if(n != sizeof(req->bitmap_words)){
 		printk("do_io - bitmap update failed, err = %d fd = %d\n", -n,
 		       req->fds[1]);
@@ -1399,7 +1389,6 @@
 	char *buf;
 	unsigned long len;
 	int n, nsectors, start, end, bit;
-	int err;
 	__u64 off;
 
 	if (req->op == UBD_FLUSH) {
@@ -1428,18 +1417,12 @@
 		len = (end - start) * req->sectorsize;
 		buf = &req->buffer[start * req->sectorsize];
 
-		err = os_seek_file(req->fds[bit], off);
-		if(err < 0){
-			printk("do_io - lseek failed : err = %d\n", -err);
-			req->error = 1;
-			return;
-		}
 		if(req->op == UBD_READ){
 			n = 0;
 			do {
 				buf = &buf[n];
 				len -= n;
-				n = os_read_file(req->fds[bit], buf, len);
+				n = os_pread_file(req->fds[bit], buf, len, off);
 				if (n < 0) {
 					printk("do_io - read failed, err = %d "
 					       "fd = %d\n", -n, req->fds[bit]);
@@ -1449,7 +1432,7 @@
 			} while((n < len) && (n != 0));
 			if (n < len) memset(&buf[n], 0, len - n);
 		} else {
-			n = os_write_file(req->fds[bit], buf, len);
+			n = os_pwrite_file(req->fds[bit], buf, len, off);
 			if(n != len){
 				printk("do_io - write failed err = %d "
 				       "fd = %d\n", -n, req->fds[bit]);
diff --git a/arch/um/include/asm/hardirq.h b/arch/um/include/asm/hardirq.h
new file mode 100644
index 0000000..756f0778
--- /dev/null
+++ b/arch/um/include/asm/hardirq.h
@@ -0,0 +1,23 @@
+#ifndef __ASM_UM_HARDIRQ_H
+#define __ASM_UM_HARDIRQ_H
+
+#include <linux/cache.h>
+#include <linux/threads.h>
+
+typedef struct {
+	unsigned int __softirq_pending;
+} ____cacheline_aligned irq_cpustat_t;
+
+#include <linux/irq_cpustat.h>	/* Standard mappings for irq_cpustat_t above */
+#include <linux/irq.h>
+
+#ifndef ack_bad_irq
+static inline void ack_bad_irq(unsigned int irq)
+{
+	printk(KERN_CRIT "unexpected IRQ trap at vector %02x\n", irq);
+}
+#endif
+
+#define __ARCH_IRQ_EXIT_IRQS_DISABLED 1
+
+#endif /* __ASM_UM_HARDIRQ_H */
diff --git a/arch/um/include/asm/syscall-generic.h b/arch/um/include/asm/syscall-generic.h
new file mode 100644
index 0000000..9fb9cf8
--- /dev/null
+++ b/arch/um/include/asm/syscall-generic.h
@@ -0,0 +1,138 @@
+/*
+ * Access to user system call parameters and results
+ *
+ * See asm-generic/syscall.h for function descriptions.
+ *
+ * Copyright (C) 2015 Mickaël Salaün <mic@digikod.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __UM_SYSCALL_GENERIC_H
+#define __UM_SYSCALL_GENERIC_H
+
+#include <asm/ptrace.h>
+#include <linux/err.h>
+#include <linux/sched.h>
+#include <sysdep/ptrace.h>
+
+static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs)
+{
+
+	return PT_REGS_SYSCALL_NR(regs);
+}
+
+static inline void syscall_rollback(struct task_struct *task,
+				    struct pt_regs *regs)
+{
+	/* do nothing */
+}
+
+static inline long syscall_get_error(struct task_struct *task,
+				     struct pt_regs *regs)
+{
+	const long error = regs_return_value(regs);
+
+	return IS_ERR_VALUE(error) ? error : 0;
+}
+
+static inline long syscall_get_return_value(struct task_struct *task,
+					    struct pt_regs *regs)
+{
+	return regs_return_value(regs);
+}
+
+static inline void syscall_set_return_value(struct task_struct *task,
+					    struct pt_regs *regs,
+					    int error, long val)
+{
+	PT_REGS_SET_SYSCALL_RETURN(regs, (long) error ?: val);
+}
+
+static inline void syscall_get_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 unsigned int i, unsigned int n,
+					 unsigned long *args)
+{
+	const struct uml_pt_regs *r = &regs->regs;
+
+	switch (i) {
+	case 0:
+		if (!n--)
+			break;
+		*args++ = UPT_SYSCALL_ARG1(r);
+	case 1:
+		if (!n--)
+			break;
+		*args++ = UPT_SYSCALL_ARG2(r);
+	case 2:
+		if (!n--)
+			break;
+		*args++ = UPT_SYSCALL_ARG3(r);
+	case 3:
+		if (!n--)
+			break;
+		*args++ = UPT_SYSCALL_ARG4(r);
+	case 4:
+		if (!n--)
+			break;
+		*args++ = UPT_SYSCALL_ARG5(r);
+	case 5:
+		if (!n--)
+			break;
+		*args++ = UPT_SYSCALL_ARG6(r);
+	case 6:
+		if (!n--)
+			break;
+	default:
+		BUG();
+		break;
+	}
+}
+
+static inline void syscall_set_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 unsigned int i, unsigned int n,
+					 const unsigned long *args)
+{
+	struct uml_pt_regs *r = &regs->regs;
+
+	switch (i) {
+	case 0:
+		if (!n--)
+			break;
+		UPT_SYSCALL_ARG1(r) = *args++;
+	case 1:
+		if (!n--)
+			break;
+		UPT_SYSCALL_ARG2(r) = *args++;
+	case 2:
+		if (!n--)
+			break;
+		UPT_SYSCALL_ARG3(r) = *args++;
+	case 3:
+		if (!n--)
+			break;
+		UPT_SYSCALL_ARG4(r) = *args++;
+	case 4:
+		if (!n--)
+			break;
+		UPT_SYSCALL_ARG5(r) = *args++;
+	case 5:
+		if (!n--)
+			break;
+		UPT_SYSCALL_ARG6(r) = *args++;
+	case 6:
+		if (!n--)
+			break;
+	default:
+		BUG();
+		break;
+	}
+}
+
+/* See arch/x86/um/asm/syscall.h for syscall_get_arch() definition. */
+
+#endif	/* __UM_SYSCALL_GENERIC_H */
diff --git a/arch/um/include/asm/thread_info.h b/arch/um/include/asm/thread_info.h
index 53968aa..053baff 100644
--- a/arch/um/include/asm/thread_info.h
+++ b/arch/um/include/asm/thread_info.h
@@ -62,11 +62,13 @@
 #define TIF_SYSCALL_AUDIT	6
 #define TIF_RESTORE_SIGMASK	7
 #define TIF_NOTIFY_RESUME	8
+#define TIF_SECCOMP		9	/* secure computing */
 
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
 #define _TIF_MEMDIE		(1 << TIF_MEMDIE)
 #define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
+#define _TIF_SECCOMP		(1 << TIF_SECCOMP)
 
 #endif
diff --git a/arch/um/include/shared/os.h b/arch/um/include/shared/os.h
index 868e6c3..de5d572 100644
--- a/arch/um/include/shared/os.h
+++ b/arch/um/include/shared/os.h
@@ -146,6 +146,8 @@
 extern int os_write_file(int fd, const void *buf, int count);
 extern int os_sync_file(int fd);
 extern int os_file_size(const char *file, unsigned long long *size_out);
+extern int os_pread_file(int fd, void *buf, int len, unsigned long long offset);
+extern int os_pwrite_file(int fd, const void *buf, int count, unsigned long long offset);
 extern int os_file_modtime(const char *file, unsigned long *modtime);
 extern int os_pipe(int *fd, int stream, int close_on_exec);
 extern int os_set_fd_async(int fd);
@@ -282,7 +284,6 @@
 				 void *arg);
 extern void halt_skas(void);
 extern void reboot_skas(void);
-extern int get_syscall(struct uml_pt_regs *regs);
 
 /* irq.c */
 extern int os_waiting_for_events(struct irq_fd *active_fds);
diff --git a/arch/um/kernel/skas/syscall.c b/arch/um/kernel/skas/syscall.c
index 1683b8e..48b0dcb 100644
--- a/arch/um/kernel/skas/syscall.c
+++ b/arch/um/kernel/skas/syscall.c
@@ -5,31 +5,38 @@
 
 #include <linux/kernel.h>
 #include <linux/ptrace.h>
+#include <linux/seccomp.h>
 #include <kern_util.h>
 #include <sysdep/ptrace.h>
+#include <sysdep/ptrace_user.h>
 #include <sysdep/syscalls.h>
-#include <os.h>
 
 void handle_syscall(struct uml_pt_regs *r)
 {
 	struct pt_regs *regs = container_of(r, struct pt_regs, regs);
-	long result;
 	int syscall;
 
-	if (syscall_trace_enter(regs)) {
-		result = -ENOSYS;
+	/* Initialize the syscall number and default return value. */
+	UPT_SYSCALL_NR(r) = PT_SYSCALL_NR(r->gp);
+	PT_REGS_SET_SYSCALL_RETURN(regs, -ENOSYS);
+
+	/* Do the secure computing check first; failures should be fast. */
+	if (secure_computing() == -1)
+		return;
+
+	if (syscall_trace_enter(regs))
 		goto out;
-	}
 
-	syscall = get_syscall(r);
+	/* Update the syscall number after orig_ax has potentially been updated
+	 * with ptrace.
+	 */
+	UPT_SYSCALL_NR(r) = PT_SYSCALL_NR(r->gp);
+	syscall = UPT_SYSCALL_NR(r);
 
-	if ((syscall > __NR_syscall_max) || syscall < 0)
-		result = -ENOSYS;
-	else
-		result = EXECUTE_SYSCALL(syscall, regs);
+	if (syscall >= 0 && syscall <= __NR_syscall_max)
+		PT_REGS_SET_SYSCALL_RETURN(regs,
+				EXECUTE_SYSCALL(syscall, regs));
 
 out:
-	PT_REGS_SET_SYSCALL_RETURN(regs, result);
-
 	syscall_trace_leave(regs);
 }
diff --git a/arch/um/os-Linux/file.c b/arch/um/os-Linux/file.c
index 26e0164..2db18cb 100644
--- a/arch/um/os-Linux/file.c
+++ b/arch/um/os-Linux/file.c
@@ -264,6 +264,15 @@
 	return n;
 }
 
+int os_pread_file(int fd, void *buf, int len, unsigned long long offset)
+{
+	int n = pread(fd, buf, len, offset);
+
+	if (n < 0)
+		return -errno;
+	return n;
+}
+
 int os_write_file(int fd, const void *buf, int len)
 {
 	int n = write(fd, (void *) buf, len);
@@ -282,6 +291,16 @@
 	return n;
 }
 
+int os_pwrite_file(int fd, const void *buf, int len, unsigned long long offset)
+{
+	int n = pwrite(fd, (void *) buf, len, offset);
+
+	if (n < 0)
+		return -errno;
+	return n;
+}
+
+
 int os_file_size(const char *file, unsigned long long *size_out)
 {
 	struct uml_stat buf;
diff --git a/arch/um/os-Linux/mem.c b/arch/um/os-Linux/mem.c
index 897e9ad..8b17676 100644
--- a/arch/um/os-Linux/mem.c
+++ b/arch/um/os-Linux/mem.c
@@ -106,6 +106,17 @@
 		}
 	}
 
+#ifdef O_TMPFILE
+	fd = open(tempdir, O_CLOEXEC | O_RDWR | O_EXCL | O_TMPFILE, 0700);
+	/*
+	 * If the running system does not support O_TMPFILE flag then retry
+	 * without it.
+	 */
+	if (fd != -1 || (errno != EINVAL && errno != EISDIR &&
+			errno != EOPNOTSUPP))
+		return fd;
+#endif
+
 	tempname = malloc(strlen(tempdir) + strlen(template) + 1);
 	if (tempname == NULL)
 		return -1;
@@ -142,12 +153,6 @@
 	if (fd < 0)
 		exit(1);
 
-	err = fchmod(fd, 0777);
-	if (err < 0) {
-		perror("fchmod");
-		exit(1);
-	}
-
 	/*
 	 * Seek to len - 1 because writing a character there will
 	 * increase the file size by one byte, to the desired length.
diff --git a/arch/um/os-Linux/signal.c b/arch/um/os-Linux/signal.c
index c211153..7801666 100644
--- a/arch/um/os-Linux/signal.c
+++ b/arch/um/os-Linux/signal.c
@@ -62,6 +62,7 @@
 
 static int signals_enabled;
 static unsigned int signals_pending;
+static unsigned int signals_active = 0;
 
 void sig_handler(int sig, struct siginfo *si, mcontext_t *mc)
 {
@@ -101,7 +102,12 @@
 
 	block_signals();
 
+	signals_active |= SIGALRM_MASK;
+
 	timer_real_alarm_handler(mc);
+
+	signals_active &= ~SIGALRM_MASK;
+
 	set_signals(enabled);
 }
 
@@ -286,8 +292,16 @@
 		if (save_pending & SIGIO_MASK)
 			sig_handler_common(SIGIO, NULL, NULL);
 
-		if (save_pending & SIGALRM_MASK)
+		/* Do not reenter the handler */
+
+		if ((save_pending & SIGALRM_MASK) && (!(signals_active & SIGALRM_MASK)))
 			timer_real_alarm_handler(NULL);
+
+		/* Rerun the loop only if there is still pending SIGIO and not in TIMER handler */
+
+		if (!(signals_pending & SIGIO_MASK) && (signals_active & SIGALRM_MASK))
+			return;
+
 	}
 }
 
diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c
index b856c66..23025d6 100644
--- a/arch/um/os-Linux/skas/process.c
+++ b/arch/um/os-Linux/skas/process.c
@@ -172,13 +172,6 @@
 	handle_syscall(regs);
 }
 
-int get_syscall(struct uml_pt_regs *regs)
-{
-	UPT_SYSCALL_NR(regs) = PT_SYSCALL_NR(regs->gp);
-
-	return UPT_SYSCALL_NR(regs);
-}
-
 extern char __syscall_stub_start[];
 
 static int userspace_tramp(void *stack)
diff --git a/arch/um/os-Linux/start_up.c b/arch/um/os-Linux/start_up.c
index 47f1ff0..22a358e 100644
--- a/arch/um/os-Linux/start_up.c
+++ b/arch/um/os-Linux/start_up.c
@@ -94,6 +94,8 @@
 {
 	int pid, n, status;
 
+	fflush(stdout);
+
 	pid = fork();
 	if (pid == 0)
 		ptrace_child();
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index db3622f..258965d 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -349,6 +349,17 @@
 
 	  If in doubt, say Y.
 
+config X86_FAST_FEATURE_TESTS
+	bool "Fast CPU feature tests" if EMBEDDED
+	default y
+	---help---
+	  Some fast-paths in the kernel depend on the capabilities of the CPU.
+	  Say Y here for the kernel to patch in the appropriate code at runtime
+	  based on the capabilities of the CPU. The infrastructure for patching
+	  code at runtime takes up some additional space; space-constrained
+	  embedded systems may wish to say N here to produce smaller, slightly
+	  slower code.
+
 config X86_X2APIC
 	bool "Support x2apic"
 	depends on X86_LOCAL_APIC && X86_64 && (IRQ_REMAP || HYPERVISOR_GUEST)
@@ -687,6 +698,14 @@
 
 	  If you are unsure how to answer this question, answer Y.
 
+config QUEUED_LOCK_STAT
+	bool "Paravirt queued spinlock statistics"
+	depends on PARAVIRT_SPINLOCKS && DEBUG_FS && QUEUED_SPINLOCKS
+	---help---
+	  Enable the collection of statistical data on the slowpath
+	  behavior of paravirtualized queued spinlocks and report
+	  them on debugfs.
+
 source "arch/x86/xen/Kconfig"
 
 config KVM_GUEST
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 137dfa9..110253c 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -69,7 +69,7 @@
 	def_bool n
 
 config X86_PTDUMP
-	bool "Export kernel pagetable layout to userspace via debugfs"
+	tristate "Export kernel pagetable layout to userspace via debugfs"
 	depends on DEBUG_KERNEL
 	select DEBUG_FS
 	select X86_PTDUMP_CORE
diff --git a/arch/x86/crypto/chacha20_glue.c b/arch/x86/crypto/chacha20_glue.c
index 722bace..8baaff5 100644
--- a/arch/x86/crypto/chacha20_glue.c
+++ b/arch/x86/crypto/chacha20_glue.c
@@ -125,7 +125,7 @@
 
 static int __init chacha20_simd_mod_init(void)
 {
-	if (!cpu_has_ssse3)
+	if (!boot_cpu_has(X86_FEATURE_SSSE3))
 		return -ENODEV;
 
 #ifdef CONFIG_AS_AVX2
diff --git a/arch/x86/crypto/crc32c-intel_glue.c b/arch/x86/crypto/crc32c-intel_glue.c
index 81a595d7..0e98716 100644
--- a/arch/x86/crypto/crc32c-intel_glue.c
+++ b/arch/x86/crypto/crc32c-intel_glue.c
@@ -257,7 +257,7 @@
 	if (!x86_match_cpu(crc32c_cpu_id))
 		return -ENODEV;
 #ifdef CONFIG_X86_64
-	if (cpu_has_pclmulqdq) {
+	if (boot_cpu_has(X86_FEATURE_PCLMULQDQ)) {
 		alg.update = crc32c_pcl_intel_update;
 		alg.finup = crc32c_pcl_intel_finup;
 		alg.digest = crc32c_pcl_intel_digest;
diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c
index 440df0c..a69321a 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_glue.c
+++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c
@@ -219,6 +219,29 @@
 	}
 }
 
+static int ghash_async_import(struct ahash_request *req, const void *in)
+{
+	struct ahash_request *cryptd_req = ahash_request_ctx(req);
+	struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
+	struct ghash_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	ghash_async_init(req);
+	memcpy(dctx, in, sizeof(*dctx));
+	return 0;
+
+}
+
+static int ghash_async_export(struct ahash_request *req, void *out)
+{
+	struct ahash_request *cryptd_req = ahash_request_ctx(req);
+	struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
+	struct ghash_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	memcpy(out, dctx, sizeof(*dctx));
+	return 0;
+
+}
+
 static int ghash_async_digest(struct ahash_request *req)
 {
 	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
@@ -288,8 +311,11 @@
 	.final		= ghash_async_final,
 	.setkey		= ghash_async_setkey,
 	.digest		= ghash_async_digest,
+	.export		= ghash_async_export,
+	.import		= ghash_async_import,
 	.halg = {
 		.digestsize	= GHASH_DIGEST_SIZE,
+		.statesize = sizeof(struct ghash_desc_ctx),
 		.base = {
 			.cra_name		= "ghash",
 			.cra_driver_name	= "ghash-clmulni",
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index 3c71dd9..e32206e 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -1,3 +1,5 @@
+#include <linux/jump_label.h>
+
 /*
 
  x86 function call convention, 64-bit:
@@ -232,3 +234,16 @@
 
 #endif /* CONFIG_X86_64 */
 
+/*
+ * This does 'call enter_from_user_mode' unless we can avoid it based on
+ * kernel config or using the static jump infrastructure.
+ */
+.macro CALL_enter_from_user_mode
+#ifdef CONFIG_CONTEXT_TRACKING
+#ifdef HAVE_JUMP_LABEL
+	STATIC_JUMP_IF_FALSE .Lafter_call_\@, context_tracking_enabled, def=0
+#endif
+	call enter_from_user_mode
+.Lafter_call_\@:
+#endif
+.endm
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index a89fdbc..0366374 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -421,7 +421,7 @@
 	regs->ip = landing_pad;
 
 	/*
-	 * Fetch ECX from where the vDSO stashed it.
+	 * Fetch EBP from where the vDSO stashed it.
 	 *
 	 * WARNING: We are in CONTEXT_USER and RCU isn't paying attention!
 	 */
@@ -432,10 +432,10 @@
 		 * Micro-optimization: the pointer we're following is explicitly
 		 * 32 bits, so it can't be out of range.
 		 */
-		__get_user(*(u32 *)&regs->cx,
+		__get_user(*(u32 *)&regs->bp,
 			    (u32 __user __force *)(unsigned long)(u32)regs->sp)
 #else
-		get_user(*(u32 *)&regs->cx,
+		get_user(*(u32 *)&regs->bp,
 			 (u32 __user __force *)(unsigned long)(u32)regs->sp)
 #endif
 		) {
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 3eb572e..77d8c51 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -292,7 +292,7 @@
 	movl	TSS_sysenter_sp0(%esp), %esp
 sysenter_past_esp:
 	pushl	$__USER_DS		/* pt_regs->ss */
-	pushl	%ecx			/* pt_regs->cx */
+	pushl	%ebp			/* pt_regs->sp (stashed in bp) */
 	pushfl				/* pt_regs->flags (except IF = 0) */
 	orl	$X86_EFLAGS_IF, (%esp)	/* Fix IF */
 	pushl	$__USER_CS		/* pt_regs->cs */
@@ -308,8 +308,9 @@
 
 	movl	%esp, %eax
 	call	do_fast_syscall_32
-	testl	%eax, %eax
-	jz	.Lsyscall_32_done
+	/* XEN PV guests always use IRET path */
+	ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \
+		    "jmp .Lsyscall_32_done", X86_FEATURE_XENPV
 
 /* Opportunistic SYSEXIT */
 	TRACE_IRQS_ON			/* User mode traces as IRQs on. */
@@ -328,7 +329,8 @@
 	 * Return back to the vDSO, which will pop ecx and edx.
 	 * Don't bother with DS and ES (they already contain __USER_DS).
 	 */
-	ENABLE_INTERRUPTS_SYSEXIT
+	sti
+	sysexit
 
 .pushsection .fixup, "ax"
 2:	movl	$0, PT_FS(%esp)
@@ -551,11 +553,6 @@
 	iret
 	_ASM_EXTABLE(native_iret, iret_exc)
 END(native_iret)
-
-ENTRY(native_irq_enable_sysexit)
-	sti
-	sysexit
-END(native_irq_enable_sysexit)
 #endif
 
 ENTRY(overflow)
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index a55697d..9d34d3c 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -520,9 +520,7 @@
 	 */
 	TRACE_IRQS_OFF
 
-#ifdef CONFIG_CONTEXT_TRACKING
-	call enter_from_user_mode
-#endif
+	CALL_enter_from_user_mode
 
 1:
 	/*
@@ -1066,9 +1064,7 @@
 	 * (which can take locks).
 	 */
 	TRACE_IRQS_OFF
-#ifdef CONFIG_CONTEXT_TRACKING
-	call enter_from_user_mode
-#endif
+	CALL_enter_from_user_mode
 	ret
 
 .Lerror_entry_done:
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index c320183..ff1c6d6 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -18,13 +18,6 @@
 
 	.section .entry.text, "ax"
 
-#ifdef CONFIG_PARAVIRT
-ENTRY(native_usergs_sysret32)
-	swapgs
-	sysretl
-ENDPROC(native_usergs_sysret32)
-#endif
-
 /*
  * 32-bit SYSENTER instruction entry.
  *
@@ -63,7 +56,7 @@
 
 	/* Construct struct pt_regs on stack */
 	pushq	$__USER32_DS		/* pt_regs->ss */
-	pushq	%rcx			/* pt_regs->sp */
+	pushq	%rbp			/* pt_regs->sp (stashed in bp) */
 
 	/*
 	 * Push flags.  This is nasty.  First, interrupts are currently
@@ -82,14 +75,14 @@
 	pushq	%rdi			/* pt_regs->di */
 	pushq	%rsi			/* pt_regs->si */
 	pushq	%rdx			/* pt_regs->dx */
-	pushq	%rcx			/* pt_regs->cx (will be overwritten) */
+	pushq	%rcx			/* pt_regs->cx */
 	pushq	$-ENOSYS		/* pt_regs->ax */
 	pushq   %r8                     /* pt_regs->r8  = 0 */
 	pushq   %r8                     /* pt_regs->r9  = 0 */
 	pushq   %r8                     /* pt_regs->r10 = 0 */
 	pushq   %r8                     /* pt_regs->r11 = 0 */
 	pushq   %rbx                    /* pt_regs->rbx */
-	pushq   %rbp                    /* pt_regs->rbp */
+	pushq   %rbp                    /* pt_regs->rbp (will be overwritten) */
 	pushq   %r8                     /* pt_regs->r12 = 0 */
 	pushq   %r8                     /* pt_regs->r13 = 0 */
 	pushq   %r8                     /* pt_regs->r14 = 0 */
@@ -103,15 +96,15 @@
 	 * This needs to happen before enabling interrupts so that
 	 * we don't get preempted with NT set.
 	 *
-	 * NB.: sysenter_fix_flags is a label with the code under it moved
+	 * NB.: .Lsysenter_fix_flags is a label with the code under it moved
 	 * out-of-line as an optimization: NT is unlikely to be set in the
 	 * majority of the cases and instead of polluting the I$ unnecessarily,
 	 * we're keeping that code behind a branch which will predict as
 	 * not-taken and therefore its instructions won't be fetched.
 	 */
 	testl	$X86_EFLAGS_NT, EFLAGS(%rsp)
-	jnz	sysenter_fix_flags
-sysenter_flags_fixed:
+	jnz	.Lsysenter_fix_flags
+.Lsysenter_flags_fixed:
 
 	/*
 	 * User mode is traced as though IRQs are on, and SYSENTER
@@ -121,14 +114,15 @@
 
 	movq	%rsp, %rdi
 	call	do_fast_syscall_32
-	testl	%eax, %eax
-	jz	.Lsyscall_32_done
+	/* XEN PV guests always use IRET path */
+	ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \
+		    "jmp .Lsyscall_32_done", X86_FEATURE_XENPV
 	jmp	sysret32_from_system_call
 
-sysenter_fix_flags:
+.Lsysenter_fix_flags:
 	pushq	$X86_EFLAGS_FIXED
 	popfq
-	jmp	sysenter_flags_fixed
+	jmp	.Lsysenter_flags_fixed
 ENDPROC(entry_SYSENTER_compat)
 
 /*
@@ -178,7 +172,7 @@
 	pushq	%rdi			/* pt_regs->di */
 	pushq	%rsi			/* pt_regs->si */
 	pushq	%rdx			/* pt_regs->dx */
-	pushq	%rcx			/* pt_regs->cx (will be overwritten) */
+	pushq	%rbp			/* pt_regs->cx (stashed in bp) */
 	pushq	$-ENOSYS		/* pt_regs->ax */
 	xorq    %r8,%r8
 	pushq   %r8                     /* pt_regs->r8  = 0 */
@@ -186,7 +180,7 @@
 	pushq   %r8                     /* pt_regs->r10 = 0 */
 	pushq   %r8                     /* pt_regs->r11 = 0 */
 	pushq   %rbx                    /* pt_regs->rbx */
-	pushq   %rbp                    /* pt_regs->rbp */
+	pushq   %rbp                    /* pt_regs->rbp (will be overwritten) */
 	pushq   %r8                     /* pt_regs->r12 = 0 */
 	pushq   %r8                     /* pt_regs->r13 = 0 */
 	pushq   %r8                     /* pt_regs->r14 = 0 */
@@ -200,8 +194,9 @@
 
 	movq	%rsp, %rdi
 	call	do_fast_syscall_32
-	testl	%eax, %eax
-	jz	.Lsyscall_32_done
+	/* XEN PV guests always use IRET path */
+	ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \
+		    "jmp .Lsyscall_32_done", X86_FEATURE_XENPV
 
 	/* Opportunistic SYSRET */
 sysret32_from_system_call:
@@ -236,7 +231,8 @@
 	xorq	%r9, %r9
 	xorq	%r10, %r10
 	movq	RSP-ORIG_RAX(%rsp), %rsp
-        USERGS_SYSRET32
+	swapgs
+	sysretl
 END(entry_SYSCALL_compat)
 
 /*
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index f17705e..cb713df 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -383,3 +383,4 @@
 374	i386	userfaultfd		sys_userfaultfd
 375	i386	membarrier		sys_membarrier
 376	i386	mlock2			sys_mlock2
+377	i386	copy_file_range		sys_copy_file_range
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 314a90b..dc1040a 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -332,6 +332,7 @@
 323	common	userfaultfd		sys_userfaultfd
 324	common	membarrier		sys_membarrier
 325	common	mlock2			sys_mlock2
+326	common	copy_file_range		sys_copy_file_range
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
index ca94fa6..8602f06 100644
--- a/arch/x86/entry/vdso/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vclock_gettime.c
@@ -17,8 +17,10 @@
 #include <asm/vvar.h>
 #include <asm/unistd.h>
 #include <asm/msr.h>
+#include <asm/pvclock.h>
 #include <linux/math64.h>
 #include <linux/time.h>
+#include <linux/kernel.h>
 
 #define gtod (&VVAR(vsyscall_gtod_data))
 
@@ -36,12 +38,12 @@
 }
 #endif
 
-#ifndef BUILD_VDSO32
+#ifdef CONFIG_PARAVIRT_CLOCK
+extern u8 pvclock_page
+	__attribute__((visibility("hidden")));
+#endif
 
-#include <linux/kernel.h>
-#include <asm/vsyscall.h>
-#include <asm/fixmap.h>
-#include <asm/pvclock.h>
+#ifndef BUILD_VDSO32
 
 notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
 {
@@ -60,75 +62,6 @@
 	return ret;
 }
 
-#ifdef CONFIG_PARAVIRT_CLOCK
-
-static notrace const struct pvclock_vsyscall_time_info *get_pvti(int cpu)
-{
-	const struct pvclock_vsyscall_time_info *pvti_base;
-	int idx = cpu / (PAGE_SIZE/PVTI_SIZE);
-	int offset = cpu % (PAGE_SIZE/PVTI_SIZE);
-
-	BUG_ON(PVCLOCK_FIXMAP_BEGIN + idx > PVCLOCK_FIXMAP_END);
-
-	pvti_base = (struct pvclock_vsyscall_time_info *)
-		    __fix_to_virt(PVCLOCK_FIXMAP_BEGIN+idx);
-
-	return &pvti_base[offset];
-}
-
-static notrace cycle_t vread_pvclock(int *mode)
-{
-	const struct pvclock_vsyscall_time_info *pvti;
-	cycle_t ret;
-	u64 last;
-	u32 version;
-	u8 flags;
-	unsigned cpu, cpu1;
-
-
-	/*
-	 * Note: hypervisor must guarantee that:
-	 * 1. cpu ID number maps 1:1 to per-CPU pvclock time info.
-	 * 2. that per-CPU pvclock time info is updated if the
-	 *    underlying CPU changes.
-	 * 3. that version is increased whenever underlying CPU
-	 *    changes.
-	 *
-	 */
-	do {
-		cpu = __getcpu() & VGETCPU_CPU_MASK;
-		/* TODO: We can put vcpu id into higher bits of pvti.version.
-		 * This will save a couple of cycles by getting rid of
-		 * __getcpu() calls (Gleb).
-		 */
-
-		pvti = get_pvti(cpu);
-
-		version = __pvclock_read_cycles(&pvti->pvti, &ret, &flags);
-
-		/*
-		 * Test we're still on the cpu as well as the version.
-		 * We could have been migrated just after the first
-		 * vgetcpu but before fetching the version, so we
-		 * wouldn't notice a version change.
-		 */
-		cpu1 = __getcpu() & VGETCPU_CPU_MASK;
-	} while (unlikely(cpu != cpu1 ||
-			  (pvti->pvti.version & 1) ||
-			  pvti->pvti.version != version));
-
-	if (unlikely(!(flags & PVCLOCK_TSC_STABLE_BIT)))
-		*mode = VCLOCK_NONE;
-
-	/* refer to tsc.c read_tsc() comment for rationale */
-	last = gtod->cycle_last;
-
-	if (likely(ret >= last))
-		return ret;
-
-	return last;
-}
-#endif
 
 #else
 
@@ -162,15 +95,77 @@
 	return ret;
 }
 
+#endif
+
 #ifdef CONFIG_PARAVIRT_CLOCK
+static notrace const struct pvclock_vsyscall_time_info *get_pvti0(void)
+{
+	return (const struct pvclock_vsyscall_time_info *)&pvclock_page;
+}
 
 static notrace cycle_t vread_pvclock(int *mode)
 {
-	*mode = VCLOCK_NONE;
-	return 0;
-}
-#endif
+	const struct pvclock_vcpu_time_info *pvti = &get_pvti0()->pvti;
+	cycle_t ret;
+	u64 tsc, pvti_tsc;
+	u64 last, delta, pvti_system_time;
+	u32 version, pvti_tsc_to_system_mul, pvti_tsc_shift;
 
+	/*
+	 * Note: The kernel and hypervisor must guarantee that cpu ID
+	 * number maps 1:1 to per-CPU pvclock time info.
+	 *
+	 * Because the hypervisor is entirely unaware of guest userspace
+	 * preemption, it cannot guarantee that per-CPU pvclock time
+	 * info is updated if the underlying CPU changes or that that
+	 * version is increased whenever underlying CPU changes.
+	 *
+	 * On KVM, we are guaranteed that pvti updates for any vCPU are
+	 * atomic as seen by *all* vCPUs.  This is an even stronger
+	 * guarantee than we get with a normal seqlock.
+	 *
+	 * On Xen, we don't appear to have that guarantee, but Xen still
+	 * supplies a valid seqlock using the version field.
+
+	 * We only do pvclock vdso timing at all if
+	 * PVCLOCK_TSC_STABLE_BIT is set, and we interpret that bit to
+	 * mean that all vCPUs have matching pvti and that the TSC is
+	 * synced, so we can just look at vCPU 0's pvti.
+	 */
+
+	if (unlikely(!(pvti->flags & PVCLOCK_TSC_STABLE_BIT))) {
+		*mode = VCLOCK_NONE;
+		return 0;
+	}
+
+	do {
+		version = pvti->version;
+
+		smp_rmb();
+
+		tsc = rdtsc_ordered();
+		pvti_tsc_to_system_mul = pvti->tsc_to_system_mul;
+		pvti_tsc_shift = pvti->tsc_shift;
+		pvti_system_time = pvti->system_time;
+		pvti_tsc = pvti->tsc_timestamp;
+
+		/* Make sure that the version double-check is last. */
+		smp_rmb();
+	} while (unlikely((version & 1) || version != pvti->version));
+
+	delta = tsc - pvti_tsc;
+	ret = pvti_system_time +
+		pvclock_scale_delta(delta, pvti_tsc_to_system_mul,
+				    pvti_tsc_shift);
+
+	/* refer to vread_tsc() comment for rationale */
+	last = gtod->cycle_last;
+
+	if (likely(ret >= last))
+		return ret;
+
+	return last;
+}
 #endif
 
 notrace static cycle_t vread_tsc(void)
diff --git a/arch/x86/entry/vdso/vdso-layout.lds.S b/arch/x86/entry/vdso/vdso-layout.lds.S
index de2c921..4158acc 100644
--- a/arch/x86/entry/vdso/vdso-layout.lds.S
+++ b/arch/x86/entry/vdso/vdso-layout.lds.S
@@ -25,7 +25,7 @@
 	 * segment.
 	 */
 
-	vvar_start = . - 2 * PAGE_SIZE;
+	vvar_start = . - 3 * PAGE_SIZE;
 	vvar_page = vvar_start;
 
 	/* Place all vvars at the offsets in asm/vvar.h. */
@@ -36,6 +36,7 @@
 #undef EMIT_VVAR
 
 	hpet_page = vvar_start + PAGE_SIZE;
+	pvclock_page = vvar_start + 2 * PAGE_SIZE;
 
 	. = SIZEOF_HEADERS;
 
diff --git a/arch/x86/entry/vdso/vdso2c.c b/arch/x86/entry/vdso/vdso2c.c
index 785d992..491020b 100644
--- a/arch/x86/entry/vdso/vdso2c.c
+++ b/arch/x86/entry/vdso/vdso2c.c
@@ -73,6 +73,7 @@
 	sym_vvar_start,
 	sym_vvar_page,
 	sym_hpet_page,
+	sym_pvclock_page,
 	sym_VDSO_FAKE_SECTION_TABLE_START,
 	sym_VDSO_FAKE_SECTION_TABLE_END,
 };
@@ -80,6 +81,7 @@
 const int special_pages[] = {
 	sym_vvar_page,
 	sym_hpet_page,
+	sym_pvclock_page,
 };
 
 struct vdso_sym {
@@ -91,6 +93,7 @@
 	[sym_vvar_start] = {"vvar_start", true},
 	[sym_vvar_page] = {"vvar_page", true},
 	[sym_hpet_page] = {"hpet_page", true},
+	[sym_pvclock_page] = {"pvclock_page", true},
 	[sym_VDSO_FAKE_SECTION_TABLE_START] = {
 		"VDSO_FAKE_SECTION_TABLE_START", false
 	},
diff --git a/arch/x86/entry/vdso/vdso32/system_call.S b/arch/x86/entry/vdso/vdso32/system_call.S
index 93bd845..3a1d929 100644
--- a/arch/x86/entry/vdso/vdso32/system_call.S
+++ b/arch/x86/entry/vdso/vdso32/system_call.S
@@ -1,5 +1,5 @@
 /*
- * Code for the vDSO.  This version uses the old int $0x80 method.
+ * AT_SYSINFO entry point
 */
 
 #include <asm/dwarf2.h>
@@ -21,35 +21,67 @@
 	/*
 	 * Reshuffle regs so that all of any of the entry instructions
 	 * will preserve enough state.
+	 *
+	 * A really nice entry sequence would be:
+	 *  pushl %edx
+	 *  pushl %ecx
+	 *  movl  %esp, %ecx
+	 *
+	 * Unfortunately, naughty Android versions between July and December
+	 * 2015 actually hardcode the traditional Linux SYSENTER entry
+	 * sequence.  That is severely broken for a number of reasons (ask
+	 * anyone with an AMD CPU, for example).  Nonetheless, we try to keep
+	 * it working approximately as well as it ever worked.
+	 *
+	 * This link may eludicate some of the history:
+	 *   https://android-review.googlesource.com/#/q/Iac3295376d61ef83e713ac9b528f3b50aa780cd7
+	 * personally, I find it hard to understand what's going on there.
+	 *
+	 * Note to future user developers: DO NOT USE SYSENTER IN YOUR CODE.
+	 * Execute an indirect call to the address in the AT_SYSINFO auxv
+	 * entry.  That is the ONLY correct way to make a fast 32-bit system
+	 * call on Linux.  (Open-coding int $0x80 is also fine, but it's
+	 * slow.)
 	 */
-	pushl	%edx
-	CFI_ADJUST_CFA_OFFSET	4
-	CFI_REL_OFFSET		edx, 0
 	pushl	%ecx
 	CFI_ADJUST_CFA_OFFSET	4
 	CFI_REL_OFFSET		ecx, 0
-	movl	%esp, %ecx
+	pushl	%edx
+	CFI_ADJUST_CFA_OFFSET	4
+	CFI_REL_OFFSET		edx, 0
+	pushl	%ebp
+	CFI_ADJUST_CFA_OFFSET	4
+	CFI_REL_OFFSET		ebp, 0
+
+	#define SYSENTER_SEQUENCE	"movl %esp, %ebp; sysenter"
+	#define SYSCALL_SEQUENCE	"movl %ecx, %ebp; syscall"
 
 #ifdef CONFIG_X86_64
 	/* If SYSENTER (Intel) or SYSCALL32 (AMD) is available, use it. */
-	ALTERNATIVE_2 "", "sysenter", X86_FEATURE_SYSENTER32, \
-	                  "syscall",  X86_FEATURE_SYSCALL32
+	ALTERNATIVE_2 "", SYSENTER_SEQUENCE, X86_FEATURE_SYSENTER32, \
+	                  SYSCALL_SEQUENCE,  X86_FEATURE_SYSCALL32
 #else
-	ALTERNATIVE "", "sysenter", X86_FEATURE_SEP
+	ALTERNATIVE "", SYSENTER_SEQUENCE, X86_FEATURE_SEP
 #endif
 
 	/* Enter using int $0x80 */
-	movl	(%esp), %ecx
 	int	$0x80
 GLOBAL(int80_landing_pad)
 
-	/* Restore ECX and EDX in case they were clobbered. */
-	popl	%ecx
-	CFI_RESTORE		ecx
+	/*
+	 * Restore EDX and ECX in case they were clobbered.  EBP is not
+	 * clobbered (the kernel restores it), but it's cleaner and
+	 * probably faster to pop it than to adjust ESP using addl.
+	 */
+	popl	%ebp
+	CFI_RESTORE		ebp
 	CFI_ADJUST_CFA_OFFSET	-4
 	popl	%edx
 	CFI_RESTORE		edx
 	CFI_ADJUST_CFA_OFFSET	-4
+	popl	%ecx
+	CFI_RESTORE		ecx
+	CFI_ADJUST_CFA_OFFSET	-4
 	ret
 	CFI_ENDPROC
 
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 64df471..b8f69e2 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -12,6 +12,7 @@
 #include <linux/random.h>
 #include <linux/elf.h>
 #include <linux/cpu.h>
+#include <asm/pvclock.h>
 #include <asm/vgtod.h>
 #include <asm/proto.h>
 #include <asm/vdso.h>
@@ -100,6 +101,7 @@
 		.name = "[vvar]",
 		.pages = no_pages,
 	};
+	struct pvclock_vsyscall_time_info *pvti;
 
 	if (calculate_addr) {
 		addr = vdso_addr(current->mm->start_stack,
@@ -169,6 +171,18 @@
 	}
 #endif
 
+	pvti = pvclock_pvti_cpu0_va();
+	if (pvti && image->sym_pvclock_page) {
+		ret = remap_pfn_range(vma,
+				      text_start + image->sym_pvclock_page,
+				      __pa(pvti) >> PAGE_SHIFT,
+				      PAGE_SIZE,
+				      PAGE_READONLY);
+
+		if (ret)
+			goto up_fail;
+	}
+
 up_fail:
 	if (ret)
 		current->mm->context.vdso = NULL;
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index a30316b..c80f6b6 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -23,6 +23,11 @@
 #define APIC_VERBOSE 1
 #define APIC_DEBUG   2
 
+/* Macros for apic_extnmi which controls external NMI masking */
+#define APIC_EXTNMI_BSP		0 /* Default */
+#define APIC_EXTNMI_ALL		1
+#define APIC_EXTNMI_NONE	2
+
 /*
  * Define the default level of output to be very little
  * This can be turned up by using apic=verbose for more
@@ -303,6 +308,7 @@
 				      unsigned int *apicid);
 
 	/* ipi */
+	void (*send_IPI)(int cpu, int vector);
 	void (*send_IPI_mask)(const struct cpumask *mask, int vector);
 	void (*send_IPI_mask_allbutself)(const struct cpumask *mask,
 					 int vector);
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index ae5fb83..3e86742 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -3,7 +3,6 @@
 
 #include <linux/compiler.h>
 #include <linux/types.h>
-#include <asm/processor.h>
 #include <asm/alternative.h>
 #include <asm/cmpxchg.h>
 #include <asm/rmwcc.h>
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index a11c30b..a984111 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -3,7 +3,6 @@
 
 #include <linux/compiler.h>
 #include <linux/types.h>
-#include <asm/processor.h>
 //#include <asm/cmpxchg.h>
 
 /* An 64bit atomic type */
diff --git a/arch/x86/include/asm/calgary.h b/arch/x86/include/asm/calgary.h
index 0d467b3..a8303eb 100644
--- a/arch/x86/include/asm/calgary.h
+++ b/arch/x86/include/asm/calgary.h
@@ -31,7 +31,7 @@
 #include <asm/types.h>
 
 struct iommu_table {
-	struct cal_chipset_ops *chip_ops; /* chipset specific funcs */
+	const struct cal_chipset_ops *chip_ops; /* chipset specific funcs */
 	unsigned long  it_base;      /* mapped address of tce table */
 	unsigned long  it_hint;      /* Hint for next alloc */
 	unsigned long *it_map;       /* A simple allocation bitmap for now */
diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h
index f7e1429..e4959d0 100644
--- a/arch/x86/include/asm/cmpxchg_32.h
+++ b/arch/x86/include/asm/cmpxchg_32.h
@@ -109,6 +109,6 @@
 
 #endif
 
-#define system_has_cmpxchg_double() cpu_has_cx8
+#define system_has_cmpxchg_double() boot_cpu_has(X86_FEATURE_CX8)
 
 #endif /* _ASM_X86_CMPXCHG_32_H */
diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h
index 1af9469..caa23a3 100644
--- a/arch/x86/include/asm/cmpxchg_64.h
+++ b/arch/x86/include/asm/cmpxchg_64.h
@@ -18,6 +18,6 @@
 	cmpxchg_local((ptr), (o), (n));					\
 })
 
-#define system_has_cmpxchg_double() cpu_has_cx16
+#define system_has_cmpxchg_double() boot_cpu_has(X86_FEATURE_CX16)
 
 #endif /* _ASM_X86_CMPXCHG_64_H */
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index bf2caa1..678637a 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -36,4 +36,7 @@
 
 int mwait_usable(const struct cpuinfo_x86 *);
 
+unsigned int x86_family(unsigned int sig);
+unsigned int x86_model(unsigned int sig);
+unsigned int x86_stepping(unsigned int sig);
 #endif /* _ASM_X86_CPU_H */
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index e4f8010..7ad8c94 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -12,7 +12,7 @@
 #include <asm/disabled-features.h>
 #endif
 
-#define NCAPINTS	14	/* N 32-bit words worth of info */
+#define NCAPINTS	16	/* N 32-bit words worth of info */
 #define NBUGINTS	1	/* N 32-bit bug flags */
 
 /*
@@ -181,22 +181,17 @@
 
 /*
  * Auxiliary flags: Linux defined - For features scattered in various
- * CPUID levels like 0x6, 0xA etc, word 7
+ * CPUID levels like 0x6, 0xA etc, word 7.
+ *
+ * Reuse free bits when adding new feature flags!
  */
-#define X86_FEATURE_IDA		( 7*32+ 0) /* Intel Dynamic Acceleration */
-#define X86_FEATURE_ARAT	( 7*32+ 1) /* Always Running APIC Timer */
+
 #define X86_FEATURE_CPB		( 7*32+ 2) /* AMD Core Performance Boost */
 #define X86_FEATURE_EPB		( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
-#define X86_FEATURE_PLN		( 7*32+ 5) /* Intel Power Limit Notification */
-#define X86_FEATURE_PTS		( 7*32+ 6) /* Intel Package Thermal Status */
-#define X86_FEATURE_DTHERM	( 7*32+ 7) /* Digital Thermal Sensor */
+
 #define X86_FEATURE_HW_PSTATE	( 7*32+ 8) /* AMD HW-PState */
 #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
-#define X86_FEATURE_HWP		( 7*32+ 10) /* "hwp" Intel HWP */
-#define X86_FEATURE_HWP_NOTIFY	( 7*32+ 11) /* Intel HWP_NOTIFY */
-#define X86_FEATURE_HWP_ACT_WINDOW ( 7*32+ 12) /* Intel HWP_ACT_WINDOW */
-#define X86_FEATURE_HWP_EPP	( 7*32+13) /* Intel HWP_EPP */
-#define X86_FEATURE_HWP_PKG_REQ ( 7*32+14) /* Intel HWP_PKG_REQ */
+
 #define X86_FEATURE_INTEL_PT	( 7*32+15) /* Intel Processor Trace */
 
 /* Virtualization flags: Linux defined, word 8 */
@@ -205,17 +200,9 @@
 #define X86_FEATURE_FLEXPRIORITY ( 8*32+ 2) /* Intel FlexPriority */
 #define X86_FEATURE_EPT         ( 8*32+ 3) /* Intel Extended Page Table */
 #define X86_FEATURE_VPID        ( 8*32+ 4) /* Intel Virtual Processor ID */
-#define X86_FEATURE_NPT		( 8*32+ 5) /* AMD Nested Page Table support */
-#define X86_FEATURE_LBRV	( 8*32+ 6) /* AMD LBR Virtualization support */
-#define X86_FEATURE_SVML	( 8*32+ 7) /* "svm_lock" AMD SVM locking MSR */
-#define X86_FEATURE_NRIPS	( 8*32+ 8) /* "nrip_save" AMD SVM next_rip save */
-#define X86_FEATURE_TSCRATEMSR  ( 8*32+ 9) /* "tsc_scale" AMD TSC scaling support */
-#define X86_FEATURE_VMCBCLEAN   ( 8*32+10) /* "vmcb_clean" AMD VMCB clean bits support */
-#define X86_FEATURE_FLUSHBYASID ( 8*32+11) /* AMD flush-by-ASID support */
-#define X86_FEATURE_DECODEASSISTS ( 8*32+12) /* AMD Decode Assists support */
-#define X86_FEATURE_PAUSEFILTER ( 8*32+13) /* AMD filtered pause intercept */
-#define X86_FEATURE_PFTHRESHOLD ( 8*32+14) /* AMD pause filter threshold */
+
 #define X86_FEATURE_VMMCALL     ( 8*32+15) /* Prefer vmmcall to vmcall */
+#define X86_FEATURE_XENPV       ( 8*32+16) /* "" Xen paravirtual guest */
 
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */
@@ -258,6 +245,30 @@
 /* AMD-defined CPU features, CPUID level 0x80000008 (ebx), word 13 */
 #define X86_FEATURE_CLZERO	(13*32+0) /* CLZERO instruction */
 
+/* Thermal and Power Management Leaf, CPUID level 0x00000006 (eax), word 14 */
+#define X86_FEATURE_DTHERM	(14*32+ 0) /* Digital Thermal Sensor */
+#define X86_FEATURE_IDA		(14*32+ 1) /* Intel Dynamic Acceleration */
+#define X86_FEATURE_ARAT	(14*32+ 2) /* Always Running APIC Timer */
+#define X86_FEATURE_PLN		(14*32+ 4) /* Intel Power Limit Notification */
+#define X86_FEATURE_PTS		(14*32+ 6) /* Intel Package Thermal Status */
+#define X86_FEATURE_HWP		(14*32+ 7) /* Intel Hardware P-states */
+#define X86_FEATURE_HWP_NOTIFY	(14*32+ 8) /* HWP Notification */
+#define X86_FEATURE_HWP_ACT_WINDOW (14*32+ 9) /* HWP Activity Window */
+#define X86_FEATURE_HWP_EPP	(14*32+10) /* HWP Energy Perf. Preference */
+#define X86_FEATURE_HWP_PKG_REQ (14*32+11) /* HWP Package Level Request */
+
+/* AMD SVM Feature Identification, CPUID level 0x8000000a (edx), word 15 */
+#define X86_FEATURE_NPT		(15*32+ 0) /* Nested Page Table support */
+#define X86_FEATURE_LBRV	(15*32+ 1) /* LBR Virtualization support */
+#define X86_FEATURE_SVML	(15*32+ 2) /* "svm_lock" SVM locking MSR */
+#define X86_FEATURE_NRIPS	(15*32+ 3) /* "nrip_save" SVM next_rip save */
+#define X86_FEATURE_TSCRATEMSR  (15*32+ 4) /* "tsc_scale" TSC scaling support */
+#define X86_FEATURE_VMCBCLEAN   (15*32+ 5) /* "vmcb_clean" VMCB clean bits support */
+#define X86_FEATURE_FLUSHBYASID (15*32+ 6) /* flush-by-ASID support */
+#define X86_FEATURE_DECODEASSISTS (15*32+ 7) /* Decode Assists support */
+#define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */
+#define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */
+
 /*
  * BUG word(s)
  */
@@ -278,6 +289,26 @@
 #include <asm/asm.h>
 #include <linux/bitops.h>
 
+enum cpuid_leafs
+{
+	CPUID_1_EDX		= 0,
+	CPUID_8000_0001_EDX,
+	CPUID_8086_0001_EDX,
+	CPUID_LNX_1,
+	CPUID_1_ECX,
+	CPUID_C000_0001_EDX,
+	CPUID_8000_0001_ECX,
+	CPUID_LNX_2,
+	CPUID_LNX_3,
+	CPUID_7_0_EBX,
+	CPUID_D_1_EAX,
+	CPUID_F_0_EDX,
+	CPUID_F_1_EDX,
+	CPUID_8000_0008_EBX,
+	CPUID_6_EAX,
+	CPUID_8000_000A_EDX,
+};
+
 #ifdef CONFIG_X86_FEATURE_NAMES
 extern const char * const x86_cap_flags[NCAPINTS*32];
 extern const char * const x86_power_flags[32];
@@ -355,60 +386,31 @@
 } while (0)
 
 #define cpu_has_fpu		boot_cpu_has(X86_FEATURE_FPU)
-#define cpu_has_de		boot_cpu_has(X86_FEATURE_DE)
 #define cpu_has_pse		boot_cpu_has(X86_FEATURE_PSE)
 #define cpu_has_tsc		boot_cpu_has(X86_FEATURE_TSC)
 #define cpu_has_pge		boot_cpu_has(X86_FEATURE_PGE)
 #define cpu_has_apic		boot_cpu_has(X86_FEATURE_APIC)
-#define cpu_has_sep		boot_cpu_has(X86_FEATURE_SEP)
-#define cpu_has_mtrr		boot_cpu_has(X86_FEATURE_MTRR)
-#define cpu_has_mmx		boot_cpu_has(X86_FEATURE_MMX)
 #define cpu_has_fxsr		boot_cpu_has(X86_FEATURE_FXSR)
 #define cpu_has_xmm		boot_cpu_has(X86_FEATURE_XMM)
 #define cpu_has_xmm2		boot_cpu_has(X86_FEATURE_XMM2)
-#define cpu_has_xmm3		boot_cpu_has(X86_FEATURE_XMM3)
-#define cpu_has_ssse3		boot_cpu_has(X86_FEATURE_SSSE3)
 #define cpu_has_aes		boot_cpu_has(X86_FEATURE_AES)
 #define cpu_has_avx		boot_cpu_has(X86_FEATURE_AVX)
 #define cpu_has_avx2		boot_cpu_has(X86_FEATURE_AVX2)
-#define cpu_has_ht		boot_cpu_has(X86_FEATURE_HT)
-#define cpu_has_nx		boot_cpu_has(X86_FEATURE_NX)
-#define cpu_has_xstore		boot_cpu_has(X86_FEATURE_XSTORE)
-#define cpu_has_xstore_enabled	boot_cpu_has(X86_FEATURE_XSTORE_EN)
-#define cpu_has_xcrypt		boot_cpu_has(X86_FEATURE_XCRYPT)
-#define cpu_has_xcrypt_enabled	boot_cpu_has(X86_FEATURE_XCRYPT_EN)
-#define cpu_has_ace2		boot_cpu_has(X86_FEATURE_ACE2)
-#define cpu_has_ace2_enabled	boot_cpu_has(X86_FEATURE_ACE2_EN)
-#define cpu_has_phe		boot_cpu_has(X86_FEATURE_PHE)
-#define cpu_has_phe_enabled	boot_cpu_has(X86_FEATURE_PHE_EN)
-#define cpu_has_pmm		boot_cpu_has(X86_FEATURE_PMM)
-#define cpu_has_pmm_enabled	boot_cpu_has(X86_FEATURE_PMM_EN)
-#define cpu_has_ds		boot_cpu_has(X86_FEATURE_DS)
-#define cpu_has_pebs		boot_cpu_has(X86_FEATURE_PEBS)
 #define cpu_has_clflush		boot_cpu_has(X86_FEATURE_CLFLUSH)
-#define cpu_has_bts		boot_cpu_has(X86_FEATURE_BTS)
 #define cpu_has_gbpages		boot_cpu_has(X86_FEATURE_GBPAGES)
 #define cpu_has_arch_perfmon	boot_cpu_has(X86_FEATURE_ARCH_PERFMON)
 #define cpu_has_pat		boot_cpu_has(X86_FEATURE_PAT)
-#define cpu_has_xmm4_1		boot_cpu_has(X86_FEATURE_XMM4_1)
-#define cpu_has_xmm4_2		boot_cpu_has(X86_FEATURE_XMM4_2)
 #define cpu_has_x2apic		boot_cpu_has(X86_FEATURE_X2APIC)
 #define cpu_has_xsave		boot_cpu_has(X86_FEATURE_XSAVE)
-#define cpu_has_xsaveopt	boot_cpu_has(X86_FEATURE_XSAVEOPT)
 #define cpu_has_xsaves		boot_cpu_has(X86_FEATURE_XSAVES)
 #define cpu_has_osxsave		boot_cpu_has(X86_FEATURE_OSXSAVE)
 #define cpu_has_hypervisor	boot_cpu_has(X86_FEATURE_HYPERVISOR)
-#define cpu_has_pclmulqdq	boot_cpu_has(X86_FEATURE_PCLMULQDQ)
-#define cpu_has_perfctr_core	boot_cpu_has(X86_FEATURE_PERFCTR_CORE)
-#define cpu_has_perfctr_nb	boot_cpu_has(X86_FEATURE_PERFCTR_NB)
-#define cpu_has_perfctr_l2	boot_cpu_has(X86_FEATURE_PERFCTR_L2)
-#define cpu_has_cx8		boot_cpu_has(X86_FEATURE_CX8)
-#define cpu_has_cx16		boot_cpu_has(X86_FEATURE_CX16)
-#define cpu_has_eager_fpu	boot_cpu_has(X86_FEATURE_EAGER_FPU)
-#define cpu_has_topoext		boot_cpu_has(X86_FEATURE_TOPOEXT)
-#define cpu_has_bpext		boot_cpu_has(X86_FEATURE_BPEXT)
+/*
+ * Do not add any more of those clumsy macros - use static_cpu_has_safe() for
+ * fast paths and boot_cpu_has() otherwise!
+ */
 
-#if __GNUC__ >= 4
+#if __GNUC__ >= 4 && defined(CONFIG_X86_FAST_FEATURE_TESTS)
 extern void warn_pre_alternatives(void);
 extern bool __static_cpu_has_safe(u16 bit);
 
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index f80d700..6d7d0e5 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -19,7 +19,6 @@
 #include <asm/acpi.h>
 #include <asm/apicdef.h>
 #include <asm/page.h>
-#include <asm/pvclock.h>
 #ifdef CONFIG_X86_32
 #include <linux/threads.h>
 #include <asm/kmap_types.h>
@@ -72,10 +71,6 @@
 #ifdef CONFIG_X86_VSYSCALL_EMULATION
 	VSYSCALL_PAGE = (FIXADDR_TOP - VSYSCALL_ADDR) >> PAGE_SHIFT,
 #endif
-#ifdef CONFIG_PARAVIRT_CLOCK
-	PVCLOCK_FIXMAP_BEGIN,
-	PVCLOCK_FIXMAP_END = PVCLOCK_FIXMAP_BEGIN+PVCLOCK_VSYSCALL_NR_PAGES-1,
-#endif
 #endif
 	FIX_DBGP_BASE,
 	FIX_EARLYCON_MEM_BASE,
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 3c3550c..eadcdd5 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -224,18 +224,67 @@
 #define XRSTOR		".byte " REX_PREFIX "0x0f,0xae,0x2f"
 #define XRSTORS		".byte " REX_PREFIX "0x0f,0xc7,0x1f"
 
-/* xstate instruction fault handler: */
-#define xstate_fault(__err)		\
-					\
-	".section .fixup,\"ax\"\n"	\
-					\
-	"3:  movl $-2,%[_err]\n"	\
-	"    jmp  2b\n"			\
-					\
-	".previous\n"			\
-					\
-	_ASM_EXTABLE(1b, 3b)		\
-	: [_err] "=r" (__err)
+#define XSTATE_OP(op, st, lmask, hmask, err)				\
+	asm volatile("1:" op "\n\t"					\
+		     "xor %[err], %[err]\n"				\
+		     "2:\n\t"						\
+		     ".pushsection .fixup,\"ax\"\n\t"			\
+		     "3: movl $-2,%[err]\n\t"				\
+		     "jmp 2b\n\t"					\
+		     ".popsection\n\t"					\
+		     _ASM_EXTABLE(1b, 3b)				\
+		     : [err] "=r" (err)					\
+		     : "D" (st), "m" (*st), "a" (lmask), "d" (hmask)	\
+		     : "memory")
+
+/*
+ * If XSAVES is enabled, it replaces XSAVEOPT because it supports a compact
+ * format and supervisor states in addition to modified optimization in
+ * XSAVEOPT.
+ *
+ * Otherwise, if XSAVEOPT is enabled, XSAVEOPT replaces XSAVE because XSAVEOPT
+ * supports modified optimization which is not supported by XSAVE.
+ *
+ * We use XSAVE as a fallback.
+ *
+ * The 661 label is defined in the ALTERNATIVE* macros as the address of the
+ * original instruction which gets replaced. We need to use it here as the
+ * address of the instruction where we might get an exception at.
+ */
+#define XSTATE_XSAVE(st, lmask, hmask, err)				\
+	asm volatile(ALTERNATIVE_2(XSAVE,				\
+				   XSAVEOPT, X86_FEATURE_XSAVEOPT,	\
+				   XSAVES,   X86_FEATURE_XSAVES)	\
+		     "\n"						\
+		     "xor %[err], %[err]\n"				\
+		     "3:\n"						\
+		     ".pushsection .fixup,\"ax\"\n"			\
+		     "4: movl $-2, %[err]\n"				\
+		     "jmp 3b\n"						\
+		     ".popsection\n"					\
+		     _ASM_EXTABLE(661b, 4b)				\
+		     : [err] "=r" (err)					\
+		     : "D" (st), "m" (*st), "a" (lmask), "d" (hmask)	\
+		     : "memory")
+
+/*
+ * Use XRSTORS to restore context if it is enabled. XRSTORS supports compact
+ * XSAVE area format.
+ */
+#define XSTATE_XRESTORE(st, lmask, hmask, err)				\
+	asm volatile(ALTERNATIVE(XRSTOR,				\
+				 XRSTORS, X86_FEATURE_XSAVES)		\
+		     "\n"						\
+		     "xor %[err], %[err]\n"				\
+		     "3:\n"						\
+		     ".pushsection .fixup,\"ax\"\n"			\
+		     "4: movl $-2, %[err]\n"				\
+		     "jmp 3b\n"						\
+		     ".popsection\n"					\
+		     _ASM_EXTABLE(661b, 4b)				\
+		     : [err] "=r" (err)					\
+		     : "D" (st), "m" (*st), "a" (lmask), "d" (hmask)	\
+		     : "memory")
 
 /*
  * This function is called only during boot time when x86 caps are not set
@@ -246,22 +295,14 @@
 	u64 mask = -1;
 	u32 lmask = mask;
 	u32 hmask = mask >> 32;
-	int err = 0;
+	int err;
 
 	WARN_ON(system_state != SYSTEM_BOOTING);
 
-	if (boot_cpu_has(X86_FEATURE_XSAVES))
-		asm volatile("1:"XSAVES"\n\t"
-			"2:\n\t"
-			     xstate_fault(err)
-			: "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err)
-			: "memory");
+	if (static_cpu_has_safe(X86_FEATURE_XSAVES))
+		XSTATE_OP(XSAVES, xstate, lmask, hmask, err);
 	else
-		asm volatile("1:"XSAVE"\n\t"
-			"2:\n\t"
-			     xstate_fault(err)
-			: "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err)
-			: "memory");
+		XSTATE_OP(XSAVE, xstate, lmask, hmask, err);
 
 	/* We should never fault when copying to a kernel buffer: */
 	WARN_ON_FPU(err);
@@ -276,22 +317,14 @@
 	u64 mask = -1;
 	u32 lmask = mask;
 	u32 hmask = mask >> 32;
-	int err = 0;
+	int err;
 
 	WARN_ON(system_state != SYSTEM_BOOTING);
 
-	if (boot_cpu_has(X86_FEATURE_XSAVES))
-		asm volatile("1:"XRSTORS"\n\t"
-			"2:\n\t"
-			     xstate_fault(err)
-			: "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err)
-			: "memory");
+	if (static_cpu_has_safe(X86_FEATURE_XSAVES))
+		XSTATE_OP(XRSTORS, xstate, lmask, hmask, err);
 	else
-		asm volatile("1:"XRSTOR"\n\t"
-			"2:\n\t"
-			     xstate_fault(err)
-			: "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err)
-			: "memory");
+		XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
 
 	/* We should never fault when copying from a kernel buffer: */
 	WARN_ON_FPU(err);
@@ -305,33 +338,11 @@
 	u64 mask = -1;
 	u32 lmask = mask;
 	u32 hmask = mask >> 32;
-	int err = 0;
+	int err;
 
 	WARN_ON(!alternatives_patched);
 
-	/*
-	 * If xsaves is enabled, xsaves replaces xsaveopt because
-	 * it supports compact format and supervisor states in addition to
-	 * modified optimization in xsaveopt.
-	 *
-	 * Otherwise, if xsaveopt is enabled, xsaveopt replaces xsave
-	 * because xsaveopt supports modified optimization which is not
-	 * supported by xsave.
-	 *
-	 * If none of xsaves and xsaveopt is enabled, use xsave.
-	 */
-	alternative_input_2(
-		"1:"XSAVE,
-		XSAVEOPT,
-		X86_FEATURE_XSAVEOPT,
-		XSAVES,
-		X86_FEATURE_XSAVES,
-		[xstate] "D" (xstate), "a" (lmask), "d" (hmask) :
-		"memory");
-	asm volatile("2:\n\t"
-		     xstate_fault(err)
-		     : "0" (err)
-		     : "memory");
+	XSTATE_XSAVE(xstate, lmask, hmask, err);
 
 	/* We should never fault when copying to a kernel buffer: */
 	WARN_ON_FPU(err);
@@ -344,23 +355,9 @@
 {
 	u32 lmask = mask;
 	u32 hmask = mask >> 32;
-	int err = 0;
+	int err;
 
-	/*
-	 * Use xrstors to restore context if it is enabled. xrstors supports
-	 * compacted format of xsave area which is not supported by xrstor.
-	 */
-	alternative_input(
-		"1: " XRSTOR,
-		XRSTORS,
-		X86_FEATURE_XSAVES,
-		"D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask)
-		: "memory");
-
-	asm volatile("2:\n"
-		     xstate_fault(err)
-		     : "0" (err)
-		     : "memory");
+	XSTATE_XRESTORE(xstate, lmask, hmask, err);
 
 	/* We should never fault when copying from a kernel buffer: */
 	WARN_ON_FPU(err);
@@ -388,12 +385,10 @@
 	if (unlikely(err))
 		return -EFAULT;
 
-	__asm__ __volatile__(ASM_STAC "\n"
-			     "1:"XSAVE"\n"
-			     "2: " ASM_CLAC "\n"
-			     xstate_fault(err)
-			     : "D" (buf), "a" (-1), "d" (-1), "0" (err)
-			     : "memory");
+	stac();
+	XSTATE_OP(XSAVE, buf, -1, -1, err);
+	clac();
+
 	return err;
 }
 
@@ -405,14 +400,12 @@
 	struct xregs_state *xstate = ((__force struct xregs_state *)buf);
 	u32 lmask = mask;
 	u32 hmask = mask >> 32;
-	int err = 0;
+	int err;
 
-	__asm__ __volatile__(ASM_STAC "\n"
-			     "1:"XRSTOR"\n"
-			     "2: " ASM_CLAC "\n"
-			     xstate_fault(err)
-			     : "D" (xstate), "a" (lmask), "d" (hmask), "0" (err)
-			     : "memory");	/* memory required? */
+	stac();
+	XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
+	clac();
+
 	return err;
 }
 
diff --git a/arch/x86/include/asm/intel_pt.h b/arch/x86/include/asm/intel_pt.h
new file mode 100644
index 0000000..e1a4117
--- /dev/null
+++ b/arch/x86/include/asm/intel_pt.h
@@ -0,0 +1,10 @@
+#ifndef _ASM_X86_INTEL_PT_H
+#define _ASM_X86_INTEL_PT_H
+
+#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL)
+void cpu_emergency_stop_pt(void);
+#else
+static inline void cpu_emergency_stop_pt(void) {}
+#endif
+
+#endif /* _ASM_X86_INTEL_PT_H */
diff --git a/arch/x86/include/asm/ipi.h b/arch/x86/include/asm/ipi.h
index 615fa90..cfc9a0d 100644
--- a/arch/x86/include/asm/ipi.h
+++ b/arch/x86/include/asm/ipi.h
@@ -119,6 +119,8 @@
 	native_apic_mem_write(APIC_ICR, cfg);
 }
 
+extern void default_send_IPI_single(int cpu, int vector);
+extern void default_send_IPI_single_phys(int cpu, int vector);
 extern void default_send_IPI_mask_sequence_phys(const struct cpumask *mask,
 						 int vector);
 extern void default_send_IPI_mask_allbutself_phys(const struct cpumask *mask,
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
index 5daeca3..adc54c1 100644
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -1,12 +1,18 @@
 #ifndef _ASM_X86_JUMP_LABEL_H
 #define _ASM_X86_JUMP_LABEL_H
 
-#ifndef __ASSEMBLY__
-
-#include <linux/stringify.h>
-#include <linux/types.h>
-#include <asm/nops.h>
-#include <asm/asm.h>
+#ifndef HAVE_JUMP_LABEL
+/*
+ * For better or for worse, if jump labels (the gcc extension) are missing,
+ * then the entire static branch patching infrastructure is compiled out.
+ * If that happens, the code in here will malfunction.  Raise a compiler
+ * error instead.
+ *
+ * In theory, jump labels and the static branch patching infrastructure
+ * could be decoupled to fix this.
+ */
+#error asm/jump_label.h included on a non-jump-label kernel
+#endif
 
 #define JUMP_LABEL_NOP_SIZE 5
 
@@ -16,6 +22,14 @@
 # define STATIC_KEY_INIT_NOP GENERIC_NOP5_ATOMIC
 #endif
 
+#include <asm/asm.h>
+#include <asm/nops.h>
+
+#ifndef __ASSEMBLY__
+
+#include <linux/stringify.h>
+#include <linux/types.h>
+
 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
 	asm_volatile_goto("1:"
@@ -59,5 +73,40 @@
 	jump_label_t key;
 };
 
-#endif  /* __ASSEMBLY__ */
+#else	/* __ASSEMBLY__ */
+
+.macro STATIC_JUMP_IF_TRUE target, key, def
+.Lstatic_jump_\@:
+	.if \def
+	/* Equivalent to "jmp.d32 \target" */
+	.byte		0xe9
+	.long		\target - .Lstatic_jump_after_\@
+.Lstatic_jump_after_\@:
+	.else
+	.byte		STATIC_KEY_INIT_NOP
+	.endif
+	.pushsection __jump_table, "aw"
+	_ASM_ALIGN
+	_ASM_PTR	.Lstatic_jump_\@, \target, \key
+	.popsection
+.endm
+
+.macro STATIC_JUMP_IF_FALSE target, key, def
+.Lstatic_jump_\@:
+	.if \def
+	.byte		STATIC_KEY_INIT_NOP
+	.else
+	/* Equivalent to "jmp.d32 \target" */
+	.byte		0xe9
+	.long		\target - .Lstatic_jump_after_\@
+.Lstatic_jump_after_\@:
+	.endif
+	.pushsection __jump_table, "aw"
+	_ASM_ALIGN
+	_ASM_PTR	.Lstatic_jump_\@, \target, \key + 1
+	.popsection
+.endm
+
+#endif	/* __ASSEMBLY__ */
+
 #endif
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 30cfd64..44adbb8 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -25,6 +25,7 @@
 #include <linux/pvclock_gtod.h>
 #include <linux/clocksource.h>
 #include <linux/irqbypass.h>
+#include <linux/hyperv.h>
 
 #include <asm/pvclock-abi.h>
 #include <asm/desc.h>
@@ -45,6 +46,31 @@
 
 #define KVM_IRQCHIP_NUM_PINS  KVM_IOAPIC_NUM_PINS
 
+/* x86-specific vcpu->requests bit members */
+#define KVM_REQ_MIGRATE_TIMER      8
+#define KVM_REQ_REPORT_TPR_ACCESS  9
+#define KVM_REQ_TRIPLE_FAULT      10
+#define KVM_REQ_MMU_SYNC          11
+#define KVM_REQ_CLOCK_UPDATE      12
+#define KVM_REQ_DEACTIVATE_FPU    13
+#define KVM_REQ_EVENT             14
+#define KVM_REQ_APF_HALT          15
+#define KVM_REQ_STEAL_UPDATE      16
+#define KVM_REQ_NMI               17
+#define KVM_REQ_PMU               18
+#define KVM_REQ_PMI               19
+#define KVM_REQ_SMI               20
+#define KVM_REQ_MASTERCLOCK_UPDATE 21
+#define KVM_REQ_MCLOCK_INPROGRESS 22
+#define KVM_REQ_SCAN_IOAPIC       23
+#define KVM_REQ_GLOBAL_CLOCK_UPDATE 24
+#define KVM_REQ_APIC_PAGE_RELOAD  25
+#define KVM_REQ_HV_CRASH          26
+#define KVM_REQ_IOAPIC_EOI_EXIT   27
+#define KVM_REQ_HV_RESET          28
+#define KVM_REQ_HV_EXIT           29
+#define KVM_REQ_HV_STIMER         30
+
 #define CR0_RESERVED_BITS                                               \
 	(~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \
 			  | X86_CR0_ET | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM \
@@ -213,6 +239,10 @@
 	};
 };
 
+struct kvm_rmap_head {
+	unsigned long val;
+};
+
 struct kvm_mmu_page {
 	struct list_head link;
 	struct hlist_node hash_link;
@@ -230,7 +260,7 @@
 	bool unsync;
 	int root_count;          /* Currently serving as active root */
 	unsigned int unsync_children;
-	unsigned long parent_ptes;	/* Reverse mapping for parent_pte */
+	struct kvm_rmap_head parent_ptes; /* rmap pointers to parent sptes */
 
 	/* The page is obsolete if mmu_valid_gen != kvm->arch.mmu_valid_gen.  */
 	unsigned long mmu_valid_gen;
@@ -374,10 +404,38 @@
 	struct list_head head;
 };
 
+/* Hyper-V SynIC timer */
+struct kvm_vcpu_hv_stimer {
+	struct hrtimer timer;
+	int index;
+	u64 config;
+	u64 count;
+	u64 exp_time;
+	struct hv_message msg;
+	bool msg_pending;
+};
+
+/* Hyper-V synthetic interrupt controller (SynIC)*/
+struct kvm_vcpu_hv_synic {
+	u64 version;
+	u64 control;
+	u64 msg_page;
+	u64 evt_page;
+	atomic64_t sint[HV_SYNIC_SINT_COUNT];
+	atomic_t sint_to_gsi[HV_SYNIC_SINT_COUNT];
+	DECLARE_BITMAP(auto_eoi_bitmap, 256);
+	DECLARE_BITMAP(vec_bitmap, 256);
+	bool active;
+};
+
 /* Hyper-V per vcpu emulation context */
 struct kvm_vcpu_hv {
 	u64 hv_vapic;
 	s64 runtime_offset;
+	struct kvm_vcpu_hv_synic synic;
+	struct kvm_hyperv_exit exit;
+	struct kvm_vcpu_hv_stimer stimer[HV_SYNIC_STIMER_COUNT];
+	DECLARE_BITMAP(stimer_pending_bitmap, HV_SYNIC_STIMER_COUNT);
 };
 
 struct kvm_vcpu_arch {
@@ -400,7 +458,8 @@
 	u64 efer;
 	u64 apic_base;
 	struct kvm_lapic *apic;    /* kernel irqchip context */
-	u64 eoi_exit_bitmap[4];
+	bool apicv_active;
+	DECLARE_BITMAP(ioapic_handled_vectors, 256);
 	unsigned long apic_attention;
 	int32_t apic_arb_prio;
 	int mp_state;
@@ -589,7 +648,7 @@
 };
 
 struct kvm_arch_memory_slot {
-	unsigned long *rmap[KVM_NR_PAGE_SIZES];
+	struct kvm_rmap_head *rmap[KVM_NR_PAGE_SIZES];
 	struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1];
 };
 
@@ -831,10 +890,11 @@
 	void (*enable_nmi_window)(struct kvm_vcpu *vcpu);
 	void (*enable_irq_window)(struct kvm_vcpu *vcpu);
 	void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr);
-	int (*cpu_uses_apicv)(struct kvm_vcpu *vcpu);
+	bool (*get_enable_apicv)(void);
+	void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu);
 	void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr);
 	void (*hwapic_isr_update)(struct kvm *kvm, int isr);
-	void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu);
+	void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
 	void (*set_virtual_x2apic_mode)(struct kvm_vcpu *vcpu, bool set);
 	void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu, hpa_t hpa);
 	void (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector);
@@ -1086,6 +1146,8 @@
 gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva,
 				struct x86_exception *exception);
 
+void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu);
+
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);
 
 int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code,
@@ -1231,6 +1293,9 @@
 unsigned long kvm_get_linear_rip(struct kvm_vcpu *vcpu);
 bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip);
 
+void kvm_make_mclock_inprogress_request(struct kvm *kvm);
+void kvm_make_scan_ioapic_request(struct kvm *kvm);
+
 void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
 				     struct kvm_async_pf *work);
 void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index 34e62b1..1e1b07a 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -1,6 +1,7 @@
 #ifndef _ASM_X86_MICROCODE_H
 #define _ASM_X86_MICROCODE_H
 
+#include <asm/cpu.h>
 #include <linux/earlycpio.h>
 
 #define native_rdmsr(msr, val1, val2)			\
@@ -95,14 +96,14 @@
 
 /*
  * In early loading microcode phase on BSP, boot_cpu_data is not set up yet.
- * x86_vendor() gets vendor id for BSP.
+ * x86_cpuid_vendor() gets vendor id for BSP.
  *
  * In 32 bit AP case, accessing boot_cpu_data needs linear address. To simplify
- * coding, we still use x86_vendor() to get vendor id for AP.
+ * coding, we still use x86_cpuid_vendor() to get vendor id for AP.
  *
- * x86_vendor() gets vendor information directly from CPUID.
+ * x86_cpuid_vendor() gets vendor information directly from CPUID.
  */
-static inline int x86_vendor(void)
+static inline int x86_cpuid_vendor(void)
 {
 	u32 eax = 0x00000000;
 	u32 ebx, ecx = 0, edx;
@@ -118,40 +119,14 @@
 	return X86_VENDOR_UNKNOWN;
 }
 
-static inline unsigned int __x86_family(unsigned int sig)
-{
-	unsigned int x86;
-
-	x86 = (sig >> 8) & 0xf;
-
-	if (x86 == 0xf)
-		x86 += (sig >> 20) & 0xff;
-
-	return x86;
-}
-
-static inline unsigned int x86_family(void)
+static inline unsigned int x86_cpuid_family(void)
 {
 	u32 eax = 0x00000001;
 	u32 ebx, ecx = 0, edx;
 
 	native_cpuid(&eax, &ebx, &ecx, &edx);
 
-	return __x86_family(eax);
-}
-
-static inline unsigned int x86_model(unsigned int sig)
-{
-	unsigned int x86, model;
-
-	x86 = __x86_family(sig);
-
-	model = (sig >> 4) & 0xf;
-
-	if (x86 == 0x6 || x86 == 0xf)
-		model += ((sig >> 16) & 0xf) << 4;
-
-	return model;
+	return x86_family(eax);
 }
 
 #ifdef CONFIG_MICROCODE
diff --git a/arch/x86/include/asm/msi.h b/arch/x86/include/asm/msi.h
index 93724cc..eb4b09b 100644
--- a/arch/x86/include/asm/msi.h
+++ b/arch/x86/include/asm/msi.h
@@ -1,7 +1,13 @@
 #ifndef _ASM_X86_MSI_H
 #define _ASM_X86_MSI_H
 #include <asm/hw_irq.h>
+#include <asm/irqdomain.h>
 
 typedef struct irq_alloc_info msi_alloc_info_t;
 
+int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec,
+		    msi_alloc_info_t *arg);
+
+void pci_msi_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc);
+
 #endif /* _ASM_X86_MSI_H */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 690b402..b05402e 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -321,6 +321,7 @@
 #define MSR_F15H_PERF_CTR		0xc0010201
 #define MSR_F15H_NB_PERF_CTL		0xc0010240
 #define MSR_F15H_NB_PERF_CTR		0xc0010241
+#define MSR_F15H_IC_CFG			0xc0011021
 
 /* Fam 10h MSRs */
 #define MSR_FAM10H_MMIO_CONF_BASE	0xc0010058
diff --git a/arch/x86/include/asm/msr-trace.h b/arch/x86/include/asm/msr-trace.h
new file mode 100644
index 0000000..7567225
--- /dev/null
+++ b/arch/x86/include/asm/msr-trace.h
@@ -0,0 +1,57 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM msr
+
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE msr-trace
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH asm/
+
+#if !defined(_TRACE_MSR_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_MSR_H
+
+#include <linux/tracepoint.h>
+
+/*
+ * Tracing for x86 model specific registers. Directly maps to the
+ * RDMSR/WRMSR instructions.
+ */
+
+DECLARE_EVENT_CLASS(msr_trace_class,
+	    TP_PROTO(unsigned msr, u64 val, int failed),
+	    TP_ARGS(msr, val, failed),
+	    TP_STRUCT__entry(
+		    __field(	unsigned,	msr )
+		    __field(    u64,		val )
+		    __field(    int,		failed )
+	    ),
+	    TP_fast_assign(
+		    __entry->msr = msr;
+		    __entry->val = val;
+		    __entry->failed = failed;
+	    ),
+	    TP_printk("%x, value %llx%s",
+		      __entry->msr,
+		      __entry->val,
+		      __entry->failed ? " #GP" : "")
+);
+
+DEFINE_EVENT(msr_trace_class, read_msr,
+	     TP_PROTO(unsigned msr, u64 val, int failed),
+	     TP_ARGS(msr, val, failed)
+);
+
+DEFINE_EVENT(msr_trace_class, write_msr,
+	     TP_PROTO(unsigned msr, u64 val, int failed),
+	     TP_ARGS(msr, val, failed)
+);
+
+DEFINE_EVENT(msr_trace_class, rdpmc,
+	     TP_PROTO(unsigned msr, u64 val, int failed),
+	     TP_ARGS(msr, val, failed)
+);
+
+#endif /* _TRACE_MSR_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 77d8b28..93fb7c1 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -32,6 +32,16 @@
 	int err;
 };
 
+struct saved_msr {
+	bool valid;
+	struct msr_info info;
+};
+
+struct saved_msrs {
+	unsigned int num;
+	struct saved_msr *array;
+};
+
 static inline unsigned long long native_read_tscp(unsigned int *aux)
 {
 	unsigned long low, high;
@@ -57,11 +67,34 @@
 #define EAX_EDX_RET(val, low, high)	"=A" (val)
 #endif
 
+#ifdef CONFIG_TRACEPOINTS
+/*
+ * Be very careful with includes. This header is prone to include loops.
+ */
+#include <asm/atomic.h>
+#include <linux/tracepoint-defs.h>
+
+extern struct tracepoint __tracepoint_read_msr;
+extern struct tracepoint __tracepoint_write_msr;
+extern struct tracepoint __tracepoint_rdpmc;
+#define msr_tracepoint_active(t) static_key_false(&(t).key)
+extern void do_trace_write_msr(unsigned msr, u64 val, int failed);
+extern void do_trace_read_msr(unsigned msr, u64 val, int failed);
+extern void do_trace_rdpmc(unsigned msr, u64 val, int failed);
+#else
+#define msr_tracepoint_active(t) false
+static inline void do_trace_write_msr(unsigned msr, u64 val, int failed) {}
+static inline void do_trace_read_msr(unsigned msr, u64 val, int failed) {}
+static inline void do_trace_rdpmc(unsigned msr, u64 val, int failed) {}
+#endif
+
 static inline unsigned long long native_read_msr(unsigned int msr)
 {
 	DECLARE_ARGS(val, low, high);
 
 	asm volatile("rdmsr" : EAX_EDX_RET(val, low, high) : "c" (msr));
+	if (msr_tracepoint_active(__tracepoint_read_msr))
+		do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), 0);
 	return EAX_EDX_VAL(val, low, high);
 }
 
@@ -78,6 +111,8 @@
 		     _ASM_EXTABLE(2b, 3b)
 		     : [err] "=r" (*err), EAX_EDX_RET(val, low, high)
 		     : "c" (msr), [fault] "i" (-EIO));
+	if (msr_tracepoint_active(__tracepoint_read_msr))
+		do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), *err);
 	return EAX_EDX_VAL(val, low, high);
 }
 
@@ -85,6 +120,8 @@
 				    unsigned low, unsigned high)
 {
 	asm volatile("wrmsr" : : "c" (msr), "a"(low), "d" (high) : "memory");
+	if (msr_tracepoint_active(__tracepoint_read_msr))
+		do_trace_write_msr(msr, ((u64)high << 32 | low), 0);
 }
 
 /* Can be uninlined because referenced by paravirt */
@@ -102,6 +139,8 @@
 		     : "c" (msr), "0" (low), "d" (high),
 		       [fault] "i" (-EIO)
 		     : "memory");
+	if (msr_tracepoint_active(__tracepoint_read_msr))
+		do_trace_write_msr(msr, ((u64)high << 32 | low), err);
 	return err;
 }
 
@@ -160,6 +199,8 @@
 	DECLARE_ARGS(val, low, high);
 
 	asm volatile("rdpmc" : EAX_EDX_RET(val, low, high) : "c" (counter));
+	if (msr_tracepoint_active(__tracepoint_rdpmc))
+		do_trace_rdpmc(counter, EAX_EDX_VAL(val, low, high), 0);
 	return EAX_EDX_VAL(val, low, high);
 }
 
@@ -190,7 +231,7 @@
 
 static inline void wrmsrl(unsigned msr, u64 val)
 {
-	native_write_msr(msr, (u32)val, (u32)(val >> 32));
+	native_write_msr(msr, (u32)(val & 0xffffffffULL), (u32)(val >> 32));
 }
 
 /* wrmsr with exception handling */
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index cc071c6..7bd0099 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -5,9 +5,9 @@
 #include <linux/types.h>
 
 /* PAGE_SHIFT determines the page size */
-#define PAGE_SHIFT	12
-#define PAGE_SIZE	(_AC(1,UL) << PAGE_SHIFT)
-#define PAGE_MASK	(~(PAGE_SIZE-1))
+#define PAGE_SHIFT		12
+#define PAGE_SIZE		(_AC(1,UL) << PAGE_SHIFT)
+#define PAGE_MASK		(~(PAGE_SIZE-1))
 
 #define PMD_PAGE_SIZE		(_AC(1, UL) << PMD_SHIFT)
 #define PMD_PAGE_MASK		(~(PMD_PAGE_SIZE-1))
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 10d0596..f619250 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -19,6 +19,12 @@
 	return pv_info.paravirt_enabled;
 }
 
+static inline int paravirt_has_feature(unsigned int feature)
+{
+	WARN_ON_ONCE(!pv_info.paravirt_enabled);
+	return (pv_info.features & feature);
+}
+
 static inline void load_sp0(struct tss_struct *tss,
 			     struct thread_struct *thread)
 {
@@ -285,15 +291,6 @@
 #endif
 }
 
-#ifdef CONFIG_SMP
-static inline void startup_ipi_hook(int phys_apicid, unsigned long start_eip,
-				    unsigned long start_esp)
-{
-	PVOP_VCALL3(pv_apic_ops.startup_ipi_hook,
-		    phys_apicid, start_eip, start_esp);
-}
-#endif
-
 static inline void paravirt_activate_mm(struct mm_struct *prev,
 					struct mm_struct *next)
 {
@@ -375,23 +372,6 @@
 {
 	PVOP_VCALL3(pv_mmu_ops.pte_update, mm, addr, ptep);
 }
-static inline void pmd_update(struct mm_struct *mm, unsigned long addr,
-			      pmd_t *pmdp)
-{
-	PVOP_VCALL3(pv_mmu_ops.pmd_update, mm, addr, pmdp);
-}
-
-static inline void pte_update_defer(struct mm_struct *mm, unsigned long addr,
-				    pte_t *ptep)
-{
-	PVOP_VCALL3(pv_mmu_ops.pte_update_defer, mm, addr, ptep);
-}
-
-static inline void pmd_update_defer(struct mm_struct *mm, unsigned long addr,
-				    pmd_t *pmdp)
-{
-	PVOP_VCALL3(pv_mmu_ops.pmd_update_defer, mm, addr, pmdp);
-}
 
 static inline pte_t __pte(pteval_t val)
 {
@@ -922,23 +902,11 @@
 		  call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_enable);	\
 		  PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
 
-#define USERGS_SYSRET32							\
-	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret32),	\
-		  CLBR_NONE,						\
-		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret32))
-
 #ifdef CONFIG_X86_32
 #define GET_CR0_INTO_EAX				\
 	push %ecx; push %edx;				\
 	call PARA_INDIRECT(pv_cpu_ops+PV_CPU_read_cr0);	\
 	pop %edx; pop %ecx
-
-#define ENABLE_INTERRUPTS_SYSEXIT					\
-	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_irq_enable_sysexit),	\
-		  CLBR_NONE,						\
-		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_irq_enable_sysexit))
-
-
 #else	/* !CONFIG_X86_32 */
 
 /*
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 31247b5..77db561 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -70,9 +70,14 @@
 #endif
 
 	int paravirt_enabled;
+	unsigned int features;	  /* valid only if paravirt_enabled is set */
 	const char *name;
 };
 
+#define paravirt_has(x) paravirt_has_feature(PV_SUPPORTED_##x)
+/* Supported features */
+#define PV_SUPPORTED_RTC        (1<<0)
+
 struct pv_init_ops {
 	/*
 	 * Patch may replace one of the defined code sequences with
@@ -157,15 +162,6 @@
 
 	u64 (*read_pmc)(int counter);
 
-#ifdef CONFIG_X86_32
-	/*
-	 * Atomically enable interrupts and return to userspace.  This
-	 * is only used in 32-bit kernels.  64-bit kernels use
-	 * usergs_sysret32 instead.
-	 */
-	void (*irq_enable_sysexit)(void);
-#endif
-
 	/*
 	 * Switch to usermode gs and return to 64-bit usermode using
 	 * sysret.  Only used in 64-bit kernels to return to 64-bit
@@ -174,14 +170,6 @@
 	 */
 	void (*usergs_sysret64)(void);
 
-	/*
-	 * Switch to usermode gs and return to 32-bit usermode using
-	 * sysret.  Used to return to 32-on-64 compat processes.
-	 * Other usermode register state, including %esp, must already
-	 * be restored.
-	 */
-	void (*usergs_sysret32)(void);
-
 	/* Normal iret.  Jump to this with the standard iret stack
 	   frame set up. */
 	void (*iret)(void);
@@ -215,14 +203,6 @@
 #endif
 };
 
-struct pv_apic_ops {
-#ifdef CONFIG_X86_LOCAL_APIC
-	void (*startup_ipi_hook)(int phys_apicid,
-				 unsigned long start_eip,
-				 unsigned long start_esp);
-#endif
-};
-
 struct pv_mmu_ops {
 	unsigned long (*read_cr2)(void);
 	void (*write_cr2)(unsigned long);
@@ -274,12 +254,6 @@
 			   pmd_t *pmdp, pmd_t pmdval);
 	void (*pte_update)(struct mm_struct *mm, unsigned long addr,
 			   pte_t *ptep);
-	void (*pte_update_defer)(struct mm_struct *mm,
-				 unsigned long addr, pte_t *ptep);
-	void (*pmd_update)(struct mm_struct *mm, unsigned long addr,
-			   pmd_t *pmdp);
-	void (*pmd_update_defer)(struct mm_struct *mm,
-				 unsigned long addr, pmd_t *pmdp);
 
 	pte_t (*ptep_modify_prot_start)(struct mm_struct *mm, unsigned long addr,
 					pte_t *ptep);
@@ -354,7 +328,6 @@
 	struct pv_time_ops pv_time_ops;
 	struct pv_cpu_ops pv_cpu_ops;
 	struct pv_irq_ops pv_irq_ops;
-	struct pv_apic_ops pv_apic_ops;
 	struct pv_mmu_ops pv_mmu_ops;
 	struct pv_lock_ops pv_lock_ops;
 };
@@ -364,7 +337,6 @@
 extern struct pv_time_ops pv_time_ops;
 extern struct pv_cpu_ops pv_cpu_ops;
 extern struct pv_irq_ops pv_irq_ops;
-extern struct pv_apic_ops pv_apic_ops;
 extern struct pv_mmu_ops pv_mmu_ops;
 extern struct pv_lock_ops pv_lock_ops;
 
@@ -402,10 +374,8 @@
 	__visible extern const char start_##ops##_##name[], end_##ops##_##name[];	\
 	asm(NATIVE_LABEL("start_", ops, name) code NATIVE_LABEL("end_", ops, name))
 
-unsigned paravirt_patch_nop(void);
 unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len);
 unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len);
-unsigned paravirt_patch_ignore(unsigned len);
 unsigned paravirt_patch_call(void *insnbuf,
 			     const void *target, u16 tgt_clobbers,
 			     unsigned long addr, u16 site_clobbers,
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 6ec0c8b..d3eee66 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -69,9 +69,6 @@
 #define pmd_clear(pmd)			native_pmd_clear(pmd)
 
 #define pte_update(mm, addr, ptep)              do { } while (0)
-#define pte_update_defer(mm, addr, ptep)        do { } while (0)
-#define pmd_update(mm, addr, ptep)              do { } while (0)
-#define pmd_update_defer(mm, addr, ptep)        do { } while (0)
 
 #define pgd_val(x)	native_pgd_val(x)
 #define __pgd(x)	native_make_pgd(x)
@@ -731,14 +728,9 @@
  * updates should either be sets, clears, or set_pte_atomic for P->P
  * transitions, which means this hook should only be called for user PTEs.
  * This hook implies a P->P protection or access change has taken place, which
- * requires a subsequent TLB flush.  The notification can optionally be delayed
- * until the TLB flush event by using the pte_update_defer form of the
- * interface, but care must be taken to assure that the flush happens while
- * still holding the same page table lock so that the shadow and primary pages
- * do not become out of sync on SMP.
+ * requires a subsequent TLB flush.
  */
 #define pte_update(mm, addr, ptep)		do { } while (0)
-#define pte_update_defer(mm, addr, ptep)	do { } while (0)
 #endif
 
 /*
@@ -830,9 +822,7 @@
 static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr,
 				       pmd_t *pmdp)
 {
-	pmd_t pmd = native_pmdp_get_and_clear(pmdp);
-	pmd_update(mm, addr, pmdp);
-	return pmd;
+	return native_pmdp_get_and_clear(pmdp);
 }
 
 #define __HAVE_ARCH_PMDP_SET_WRPROTECT
@@ -840,7 +830,6 @@
 				      unsigned long addr, pmd_t *pmdp)
 {
 	clear_bit(_PAGE_BIT_RW, (unsigned long *)pmdp);
-	pmd_update(mm, addr, pmdp);
 }
 
 /*
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 67522256..2d5a50c 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -472,6 +472,7 @@
 #else
 #define __cpuid			native_cpuid
 #define paravirt_enabled()	0
+#define paravirt_has(x) 	0
 
 static inline void load_sp0(struct tss_struct *tss,
 			    struct thread_struct *thread)
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index 7a6bed5c..fdcc040 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -4,6 +4,15 @@
 #include <linux/clocksource.h>
 #include <asm/pvclock-abi.h>
 
+#ifdef CONFIG_KVM_GUEST
+extern struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void);
+#else
+static inline struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void)
+{
+	return NULL;
+}
+#endif
+
 /* some helper functions for xen and kvm pv clock sources */
 cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src);
 u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src);
@@ -91,10 +100,5 @@
 } __attribute__((__aligned__(SMP_CACHE_BYTES)));
 
 #define PVTI_SIZE sizeof(struct pvclock_vsyscall_time_info)
-#define PVCLOCK_VSYSCALL_NR_PAGES (((NR_CPUS-1)/(PAGE_SIZE/PVTI_SIZE))+1)
-
-int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i,
-				 int size);
-struct pvclock_vcpu_time_info *pvclock_get_vsyscall_time_info(int cpu);
 
 #endif /* _ASM_X86_PVCLOCK_H */
diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h
index b002e71..9f92c18 100644
--- a/arch/x86/include/asm/qspinlock_paravirt.h
+++ b/arch/x86/include/asm/qspinlock_paravirt.h
@@ -1,6 +1,65 @@
 #ifndef __ASM_QSPINLOCK_PARAVIRT_H
 #define __ASM_QSPINLOCK_PARAVIRT_H
 
+/*
+ * For x86-64, PV_CALLEE_SAVE_REGS_THUNK() saves and restores 8 64-bit
+ * registers. For i386, however, only 1 32-bit register needs to be saved
+ * and restored. So an optimized version of __pv_queued_spin_unlock() is
+ * hand-coded for 64-bit, but it isn't worthwhile to do it for 32-bit.
+ */
+#ifdef CONFIG_64BIT
+
+PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock_slowpath);
+#define __pv_queued_spin_unlock	__pv_queued_spin_unlock
+#define PV_UNLOCK		"__raw_callee_save___pv_queued_spin_unlock"
+#define PV_UNLOCK_SLOWPATH	"__raw_callee_save___pv_queued_spin_unlock_slowpath"
+
+/*
+ * Optimized assembly version of __raw_callee_save___pv_queued_spin_unlock
+ * which combines the registers saving trunk and the body of the following
+ * C code:
+ *
+ * void __pv_queued_spin_unlock(struct qspinlock *lock)
+ * {
+ *	struct __qspinlock *l = (void *)lock;
+ *	u8 lockval = cmpxchg(&l->locked, _Q_LOCKED_VAL, 0);
+ *
+ *	if (likely(lockval == _Q_LOCKED_VAL))
+ *		return;
+ *	pv_queued_spin_unlock_slowpath(lock, lockval);
+ * }
+ *
+ * For x86-64,
+ *   rdi = lock              (first argument)
+ *   rsi = lockval           (second argument)
+ *   rdx = internal variable (set to 0)
+ */
+asm    (".pushsection .text;"
+	".globl " PV_UNLOCK ";"
+	".align 4,0x90;"
+	PV_UNLOCK ": "
+	"push  %rdx;"
+	"mov   $0x1,%eax;"
+	"xor   %edx,%edx;"
+	"lock cmpxchg %dl,(%rdi);"
+	"cmp   $0x1,%al;"
+	"jne   .slowpath;"
+	"pop   %rdx;"
+	"ret;"
+	".slowpath: "
+	"push   %rsi;"
+	"movzbl %al,%esi;"
+	"call " PV_UNLOCK_SLOWPATH ";"
+	"pop    %rsi;"
+	"pop    %rdx;"
+	"ret;"
+	".size " PV_UNLOCK ", .-" PV_UNLOCK ";"
+	".popsection");
+
+#else /* CONFIG_64BIT */
+
+extern void __pv_queued_spin_unlock(struct qspinlock *lock);
 PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock);
 
+#endif /* CONFIG_64BIT */
 #endif
diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h
index a82c4f1..2cb1cc2 100644
--- a/arch/x86/include/asm/reboot.h
+++ b/arch/x86/include/asm/reboot.h
@@ -25,5 +25,6 @@
 
 typedef void (*nmi_shootdown_cb)(int, struct pt_regs*);
 void nmi_shootdown_cpus(nmi_shootdown_cb callback);
+void run_crash_ipi_callback(struct pt_regs *regs);
 
 #endif /* _ASM_X86_REBOOT_H */
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 222a6a3..dfcf072 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -21,15 +21,6 @@
 extern int smp_num_siblings;
 extern unsigned int num_processors;
 
-static inline bool cpu_has_ht_siblings(void)
-{
-	bool has_siblings = false;
-#ifdef CONFIG_SMP
-	has_siblings = cpu_has_ht && smp_num_siblings > 1;
-#endif
-	return has_siblings;
-}
-
 DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map);
 DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_map);
 /* cpus sharing the last level cache: */
@@ -74,9 +65,6 @@
 extern void set_cpu_sibling_map(int cpu);
 
 #ifdef CONFIG_SMP
-#ifndef CONFIG_PARAVIRT
-#define startup_ipi_hook(phys_apicid, start_eip, start_esp) do { } while (0)
-#endif
 extern struct smp_ops smp_ops;
 
 static inline void smp_send_stop(void)
diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h
index d1793f0..8e9dbe7 100644
--- a/arch/x86/include/asm/suspend_32.h
+++ b/arch/x86/include/asm/suspend_32.h
@@ -15,6 +15,7 @@
 	unsigned long cr0, cr2, cr3, cr4;
 	u64 misc_enable;
 	bool misc_enable_saved;
+	struct saved_msrs saved_msrs;
 	struct desc_ptr gdt_desc;
 	struct desc_ptr idt;
 	u16 ldt;
diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h
index 7ebf0eb..6136a18 100644
--- a/arch/x86/include/asm/suspend_64.h
+++ b/arch/x86/include/asm/suspend_64.h
@@ -24,6 +24,7 @@
 	unsigned long cr0, cr2, cr3, cr4, cr8;
 	u64 misc_enable;
 	bool misc_enable_saved;
+	struct saved_msrs saved_msrs;
 	unsigned long efer;
 	u16 gdt_pad; /* Unused */
 	struct desc_ptr gdt_desc;
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 09b1b0a..660458a 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -745,5 +745,14 @@
 #undef __copy_from_user_overflow
 #undef __copy_to_user_overflow
 
+/*
+ * We rely on the nested NMI work to allow atomic faults from the NMI path; the
+ * nested NMI paths are careful to preserve CR2.
+ *
+ * Caller must use pagefault_enable/disable, or run in interrupt context,
+ * and also do a uaccess_ok() check
+ */
+#define __copy_from_user_nmi __copy_from_user_inatomic
+
 #endif /* _ASM_X86_UACCESS_H */
 
diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h
index 756de91..deabaf9 100644
--- a/arch/x86/include/asm/vdso.h
+++ b/arch/x86/include/asm/vdso.h
@@ -22,6 +22,7 @@
 
 	long sym_vvar_page;
 	long sym_hpet_page;
+	long sym_pvclock_page;
 	long sym_VDSO32_NOTE_MASK;
 	long sym___kernel_sigreturn;
 	long sym___kernel_rt_sigreturn;
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index cd0fc0c..1ae89a2 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -82,13 +82,11 @@
  * struct x86_init_timers - platform specific timer setup
  * @setup_perpcu_clockev:	set up the per cpu clock event device for the
  *				boot cpu
- * @tsc_pre_init:		platform function called before TSC init
  * @timer_init:			initialize the platform timer (default PIT/HPET)
  * @wallclock_init:		init the wallclock device
  */
 struct x86_init_timers {
 	void (*setup_percpu_clockev)(void);
-	void (*tsc_pre_init)(void);
 	void (*timer_init)(void);
 	void (*wallclock_init)(void);
 };
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 4c20dd3..3bcdcc8 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -310,10 +310,10 @@
 }
 
 static inline int
-HYPERVISOR_dom0_op(struct xen_platform_op *platform_op)
+HYPERVISOR_platform_op(struct xen_platform_op *op)
 {
-	platform_op->interface_version = XENPF_INTERFACE_VERSION;
-	return _hypercall1(int, dom0_op, platform_op);
+	op->interface_version = XENPF_INTERFACE_VERSION;
+	return _hypercall1(int, platform_op, op);
 }
 
 static inline int
diff --git a/arch/x86/include/asm/xor_32.h b/arch/x86/include/asm/xor_32.h
index 5a08bc8..c54beb4 100644
--- a/arch/x86/include/asm/xor_32.h
+++ b/arch/x86/include/asm/xor_32.h
@@ -553,7 +553,7 @@
 	if (cpu_has_xmm) {				\
 		xor_speed(&xor_block_pIII_sse);		\
 		xor_speed(&xor_block_sse_pf64);		\
-	} else if (cpu_has_mmx) {			\
+	} else if (boot_cpu_has(X86_FEATURE_MMX)) {	\
 		xor_speed(&xor_block_pII_mmx);		\
 		xor_speed(&xor_block_p5_mmx);		\
 	} else {					\
diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h
index 040d408..7956412 100644
--- a/arch/x86/include/uapi/asm/hyperv.h
+++ b/arch/x86/include/uapi/asm/hyperv.h
@@ -269,4 +269,96 @@
 #define HV_SYNIC_SINT_AUTO_EOI		(1ULL << 17)
 #define HV_SYNIC_SINT_VECTOR_MASK	(0xFF)
 
+#define HV_SYNIC_STIMER_COUNT		(4)
+
+/* Define synthetic interrupt controller message constants. */
+#define HV_MESSAGE_SIZE			(256)
+#define HV_MESSAGE_PAYLOAD_BYTE_COUNT	(240)
+#define HV_MESSAGE_PAYLOAD_QWORD_COUNT	(30)
+
+/* Define hypervisor message types. */
+enum hv_message_type {
+	HVMSG_NONE			= 0x00000000,
+
+	/* Memory access messages. */
+	HVMSG_UNMAPPED_GPA		= 0x80000000,
+	HVMSG_GPA_INTERCEPT		= 0x80000001,
+
+	/* Timer notification messages. */
+	HVMSG_TIMER_EXPIRED			= 0x80000010,
+
+	/* Error messages. */
+	HVMSG_INVALID_VP_REGISTER_VALUE	= 0x80000020,
+	HVMSG_UNRECOVERABLE_EXCEPTION	= 0x80000021,
+	HVMSG_UNSUPPORTED_FEATURE		= 0x80000022,
+
+	/* Trace buffer complete messages. */
+	HVMSG_EVENTLOG_BUFFERCOMPLETE	= 0x80000040,
+
+	/* Platform-specific processor intercept messages. */
+	HVMSG_X64_IOPORT_INTERCEPT		= 0x80010000,
+	HVMSG_X64_MSR_INTERCEPT		= 0x80010001,
+	HVMSG_X64_CPUID_INTERCEPT		= 0x80010002,
+	HVMSG_X64_EXCEPTION_INTERCEPT	= 0x80010003,
+	HVMSG_X64_APIC_EOI			= 0x80010004,
+	HVMSG_X64_LEGACY_FP_ERROR		= 0x80010005
+};
+
+/* Define synthetic interrupt controller message flags. */
+union hv_message_flags {
+	__u8 asu8;
+	struct {
+		__u8 msg_pending:1;
+		__u8 reserved:7;
+	};
+};
+
+/* Define port identifier type. */
+union hv_port_id {
+	__u32 asu32;
+	struct {
+		__u32 id:24;
+		__u32 reserved:8;
+	} u;
+};
+
+/* Define synthetic interrupt controller message header. */
+struct hv_message_header {
+	__u32 message_type;
+	__u8 payload_size;
+	union hv_message_flags message_flags;
+	__u8 reserved[2];
+	union {
+		__u64 sender;
+		union hv_port_id port;
+	};
+};
+
+/* Define synthetic interrupt controller message format. */
+struct hv_message {
+	struct hv_message_header header;
+	union {
+		__u64 payload[HV_MESSAGE_PAYLOAD_QWORD_COUNT];
+	} u;
+};
+
+/* Define the synthetic interrupt message page layout. */
+struct hv_message_page {
+	struct hv_message sint_message[HV_SYNIC_SINT_COUNT];
+};
+
+/* Define timer message payload structure. */
+struct hv_timer_message_payload {
+	__u32 timer_index;
+	__u32 reserved;
+	__u64 expiration_time;	/* When the timer expired */
+	__u64 delivery_time;	/* When the message was delivered */
+};
+
+#define HV_STIMER_ENABLE		(1ULL << 0)
+#define HV_STIMER_PERIODIC		(1ULL << 1)
+#define HV_STIMER_LAZY			(1ULL << 2)
+#define HV_STIMER_AUTOENABLE		(1ULL << 3)
+#define HV_STIMER_SINT(config)		(__u8)(((config) >> 16) & 0x0F)
+
 #endif
diff --git a/arch/x86/include/uapi/asm/mce.h b/arch/x86/include/uapi/asm/mce.h
index 03429da..2184943 100644
--- a/arch/x86/include/uapi/asm/mce.h
+++ b/arch/x86/include/uapi/asm/mce.h
@@ -16,7 +16,7 @@
 	__u8  cpuvendor;	/* cpu vendor as encoded in system.h */
 	__u8  inject_flags;	/* software inject flags */
 	__u8  severity;
-	__u8  usable_addr;
+	__u8  pad;
 	__u32 cpuid;	/* CPUID 1 EAX */
 	__u8  cs;		/* code segment */
 	__u8  bank;	/* machine check bank */
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 2f69e3b1..8a5cdda 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -82,6 +82,12 @@
 static unsigned int disabled_cpu_apicid __read_mostly = BAD_APICID;
 
 /*
+ * This variable controls which CPUs receive external NMIs.  By default,
+ * external NMIs are delivered only to the BSP.
+ */
+static int apic_extnmi = APIC_EXTNMI_BSP;
+
+/*
  * Map cpu index to physical APIC ID
  */
 DEFINE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid, BAD_APICID);
@@ -1161,6 +1167,8 @@
 	value = APIC_DM_NMI;
 	if (!lapic_is_integrated())		/* 82489DX */
 		value |= APIC_LVT_LEVEL_TRIGGER;
+	if (apic_extnmi == APIC_EXTNMI_NONE)
+		value |= APIC_LVT_MASKED;
 	apic_write(APIC_LVT1, value);
 }
 
@@ -1378,9 +1386,11 @@
 	apic_write(APIC_LVT0, value);
 
 	/*
-	 * only the BP should see the LINT1 NMI signal, obviously.
+	 * Only the BSP sees the LINT1 NMI signal by default. This can be
+	 * modified by apic_extnmi= boot option.
 	 */
-	if (!cpu)
+	if ((!cpu && apic_extnmi != APIC_EXTNMI_NONE) ||
+	    apic_extnmi == APIC_EXTNMI_ALL)
 		value = APIC_DM_NMI;
 	else
 		value = APIC_DM_NMI | APIC_LVT_MASKED;
@@ -2270,6 +2280,7 @@
 	unsigned int apic_tmict;
 	unsigned int apic_tdcr;
 	unsigned int apic_thmr;
+	unsigned int apic_cmci;
 } apic_pm_state;
 
 static int lapic_suspend(void)
@@ -2299,6 +2310,10 @@
 	if (maxlvt >= 5)
 		apic_pm_state.apic_thmr = apic_read(APIC_LVTTHMR);
 #endif
+#ifdef CONFIG_X86_MCE_INTEL
+	if (maxlvt >= 6)
+		apic_pm_state.apic_cmci = apic_read(APIC_LVTCMCI);
+#endif
 
 	local_irq_save(flags);
 	disable_local_APIC();
@@ -2355,10 +2370,14 @@
 	apic_write(APIC_SPIV, apic_pm_state.apic_spiv);
 	apic_write(APIC_LVT0, apic_pm_state.apic_lvt0);
 	apic_write(APIC_LVT1, apic_pm_state.apic_lvt1);
-#if defined(CONFIG_X86_MCE_INTEL)
+#ifdef CONFIG_X86_THERMAL_VECTOR
 	if (maxlvt >= 5)
 		apic_write(APIC_LVTTHMR, apic_pm_state.apic_thmr);
 #endif
+#ifdef CONFIG_X86_MCE_INTEL
+	if (maxlvt >= 6)
+		apic_write(APIC_LVTCMCI, apic_pm_state.apic_cmci);
+#endif
 	if (maxlvt >= 4)
 		apic_write(APIC_LVTPC, apic_pm_state.apic_lvtpc);
 	apic_write(APIC_LVTT, apic_pm_state.apic_lvtt);
@@ -2548,3 +2567,23 @@
 	return 0;
 }
 early_param("disable_cpu_apicid", apic_set_disabled_cpu_apicid);
+
+static int __init apic_set_extnmi(char *arg)
+{
+	if (!arg)
+		return -EINVAL;
+
+	if (!strncmp("all", arg, 3))
+		apic_extnmi = APIC_EXTNMI_ALL;
+	else if (!strncmp("none", arg, 4))
+		apic_extnmi = APIC_EXTNMI_NONE;
+	else if (!strncmp("bsp", arg, 3))
+		apic_extnmi = APIC_EXTNMI_BSP;
+	else {
+		pr_warn("Unknown external NMI delivery mode `%s' ignored\n", arg);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+early_param("apic_extnmi", apic_set_extnmi);
diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c
index f92ab36..9968f30 100644
--- a/arch/x86/kernel/apic/apic_flat_64.c
+++ b/arch/x86/kernel/apic/apic_flat_64.c
@@ -185,6 +185,7 @@
 
 	.cpu_mask_to_apicid_and		= flat_cpu_mask_to_apicid_and,
 
+	.send_IPI			= default_send_IPI_single,
 	.send_IPI_mask			= flat_send_IPI_mask,
 	.send_IPI_mask_allbutself	= flat_send_IPI_mask_allbutself,
 	.send_IPI_allbutself		= flat_send_IPI_allbutself,
@@ -230,17 +231,6 @@
 	return 0;
 }
 
-static void physflat_send_IPI_mask(const struct cpumask *cpumask, int vector)
-{
-	default_send_IPI_mask_sequence_phys(cpumask, vector);
-}
-
-static void physflat_send_IPI_mask_allbutself(const struct cpumask *cpumask,
-					      int vector)
-{
-	default_send_IPI_mask_allbutself_phys(cpumask, vector);
-}
-
 static void physflat_send_IPI_allbutself(int vector)
 {
 	default_send_IPI_mask_allbutself_phys(cpu_online_mask, vector);
@@ -248,7 +238,7 @@
 
 static void physflat_send_IPI_all(int vector)
 {
-	physflat_send_IPI_mask(cpu_online_mask, vector);
+	default_send_IPI_mask_sequence_phys(cpu_online_mask, vector);
 }
 
 static int physflat_probe(void)
@@ -292,8 +282,9 @@
 
 	.cpu_mask_to_apicid_and		= default_cpu_mask_to_apicid_and,
 
-	.send_IPI_mask			= physflat_send_IPI_mask,
-	.send_IPI_mask_allbutself	= physflat_send_IPI_mask_allbutself,
+	.send_IPI			= default_send_IPI_single_phys,
+	.send_IPI_mask			= default_send_IPI_mask_sequence_phys,
+	.send_IPI_mask_allbutself	= default_send_IPI_mask_allbutself_phys,
 	.send_IPI_allbutself		= physflat_send_IPI_allbutself,
 	.send_IPI_all			= physflat_send_IPI_all,
 	.send_IPI_self			= apic_send_IPI_self,
diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c
index 0d96749..331a7a0 100644
--- a/arch/x86/kernel/apic/apic_noop.c
+++ b/arch/x86/kernel/apic/apic_noop.c
@@ -30,6 +30,7 @@
 #include <asm/e820.h>
 
 static void noop_init_apic_ldr(void) { }
+static void noop_send_IPI(int cpu, int vector) { }
 static void noop_send_IPI_mask(const struct cpumask *cpumask, int vector) { }
 static void noop_send_IPI_mask_allbutself(const struct cpumask *cpumask, int vector) { }
 static void noop_send_IPI_allbutself(int vector) { }
@@ -144,6 +145,7 @@
 
 	.cpu_mask_to_apicid_and		= flat_cpu_mask_to_apicid_and,
 
+	.send_IPI			= noop_send_IPI,
 	.send_IPI_mask			= noop_send_IPI_mask,
 	.send_IPI_mask_allbutself	= noop_send_IPI_mask_allbutself,
 	.send_IPI_allbutself		= noop_send_IPI_allbutself,
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index 38dd5ef..c80c02c 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -193,20 +193,17 @@
 	case 1:
 		init_extra_mapping_uc(NUMACHIP_LCSR_BASE, NUMACHIP_LCSR_SIZE);
 		numachip_apic_icr_write = numachip1_apic_icr_write;
-		x86_init.pci.arch_init = pci_numachip_init;
 		break;
 	case 2:
 		init_extra_mapping_uc(NUMACHIP2_LCSR_BASE, NUMACHIP2_LCSR_SIZE);
 		numachip_apic_icr_write = numachip2_apic_icr_write;
-
-		/* Use MCFG config cycles rather than locked CF8 cycles */
-		raw_pci_ops = &pci_mmcfg;
 		break;
 	default:
 		return 0;
 	}
 
 	x86_cpuinit.fixup_cpu_id = fixup_cpu_id;
+	x86_init.pci.arch_init = pci_numachip_init;
 
 	return 0;
 }
@@ -276,6 +273,7 @@
 
 	.cpu_mask_to_apicid_and		= default_cpu_mask_to_apicid_and,
 
+	.send_IPI			= numachip_send_IPI_one,
 	.send_IPI_mask			= numachip_send_IPI_mask,
 	.send_IPI_mask_allbutself	= numachip_send_IPI_mask_allbutself,
 	.send_IPI_allbutself		= numachip_send_IPI_allbutself,
@@ -327,6 +325,7 @@
 
 	.cpu_mask_to_apicid_and		= default_cpu_mask_to_apicid_and,
 
+	.send_IPI			= numachip_send_IPI_one,
 	.send_IPI_mask			= numachip_send_IPI_mask,
 	.send_IPI_mask_allbutself	= numachip_send_IPI_mask_allbutself,
 	.send_IPI_allbutself		= numachip_send_IPI_allbutself,
diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c
index 971cf88..cf9bd896 100644
--- a/arch/x86/kernel/apic/bigsmp_32.c
+++ b/arch/x86/kernel/apic/bigsmp_32.c
@@ -96,11 +96,6 @@
 	return cpuid_apic >> index_msb;
 }
 
-static inline void bigsmp_send_IPI_mask(const struct cpumask *mask, int vector)
-{
-	default_send_IPI_mask_sequence_phys(mask, vector);
-}
-
 static void bigsmp_send_IPI_allbutself(int vector)
 {
 	default_send_IPI_mask_allbutself_phys(cpu_online_mask, vector);
@@ -108,7 +103,7 @@
 
 static void bigsmp_send_IPI_all(int vector)
 {
-	bigsmp_send_IPI_mask(cpu_online_mask, vector);
+	default_send_IPI_mask_sequence_phys(cpu_online_mask, vector);
 }
 
 static int dmi_bigsmp; /* can be set by dmi scanners */
@@ -180,7 +175,8 @@
 
 	.cpu_mask_to_apicid_and		= default_cpu_mask_to_apicid_and,
 
-	.send_IPI_mask			= bigsmp_send_IPI_mask,
+	.send_IPI			= default_send_IPI_single_phys,
+	.send_IPI_mask			= default_send_IPI_mask_sequence_phys,
 	.send_IPI_mask_allbutself	= NULL,
 	.send_IPI_allbutself		= bigsmp_send_IPI_allbutself,
 	.send_IPI_all			= bigsmp_send_IPI_all,
diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c
index 6207156..eb45fc9 100644
--- a/arch/x86/kernel/apic/ipi.c
+++ b/arch/x86/kernel/apic/ipi.c
@@ -18,6 +18,16 @@
 #include <asm/proto.h>
 #include <asm/ipi.h>
 
+void default_send_IPI_single_phys(int cpu, int vector)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	__default_send_IPI_dest_field(per_cpu(x86_cpu_to_apicid, cpu),
+				      vector, APIC_DEST_PHYSICAL);
+	local_irq_restore(flags);
+}
+
 void default_send_IPI_mask_sequence_phys(const struct cpumask *mask, int vector)
 {
 	unsigned long query_cpu;
@@ -55,6 +65,14 @@
 	local_irq_restore(flags);
 }
 
+/*
+ * Helper function for APICs which insist on cpumasks
+ */
+void default_send_IPI_single(int cpu, int vector)
+{
+	apic->send_IPI_mask(cpumask_of(cpu), vector);
+}
+
 #ifdef CONFIG_X86_32
 
 void default_send_IPI_mask_sequence_logical(const struct cpumask *mask,
diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
index 5f1feb6..ade2532 100644
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -96,8 +96,8 @@
 	return arg->msi_hwirq;
 }
 
-static int pci_msi_prepare(struct irq_domain *domain, struct device *dev,
-			   int nvec, msi_alloc_info_t *arg)
+int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec,
+		    msi_alloc_info_t *arg)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct msi_desc *desc = first_pci_msi_entry(pdev);
@@ -113,11 +113,13 @@
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(pci_msi_prepare);
 
-static void pci_msi_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc)
+void pci_msi_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc)
 {
 	arg->msi_hwirq = pci_msi_domain_calc_hwirq(arg->msi_dev, desc);
 }
+EXPORT_SYMBOL_GPL(pci_msi_set_desc);
 
 static struct msi_domain_ops pci_msi_domain_ops = {
 	.get_hwirq	= pci_msi_get_hwirq,
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index 7694ae6..f316e34 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -105,6 +105,7 @@
 
 	.cpu_mask_to_apicid_and		= flat_cpu_mask_to_apicid_and,
 
+	.send_IPI			= default_send_IPI_single,
 	.send_IPI_mask			= default_send_IPI_mask_logical,
 	.send_IPI_mask_allbutself	= default_send_IPI_mask_allbutself_logical,
 	.send_IPI_allbutself		= default_send_IPI_allbutself,
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 861bc59..908cb37 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -29,6 +29,7 @@
 };
 
 struct irq_domain *x86_vector_domain;
+EXPORT_SYMBOL_GPL(x86_vector_domain);
 static DEFINE_RAW_SPINLOCK(vector_lock);
 static cpumask_var_t vector_cpumask;
 static struct irq_chip lapic_controller;
@@ -66,6 +67,7 @@
 
 	return data ? &data->cfg : NULL;
 }
+EXPORT_SYMBOL_GPL(irqd_cfg);
 
 struct irq_cfg *irq_cfg(unsigned int irq)
 {
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index cc8311c4..aca8b75 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -23,6 +23,14 @@
 	return per_cpu(x86_cpu_to_logical_apicid, cpu) >> 16;
 }
 
+static void x2apic_send_IPI(int cpu, int vector)
+{
+	u32 dest = per_cpu(x86_cpu_to_logical_apicid, cpu);
+
+	x2apic_wrmsr_fence();
+	__x2apic_send_IPI_dest(dest, vector, APIC_DEST_LOGICAL);
+}
+
 static void
 __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest)
 {
@@ -266,6 +274,7 @@
 
 	.cpu_mask_to_apicid_and		= x2apic_cpu_mask_to_apicid_and,
 
+	.send_IPI			= x2apic_send_IPI,
 	.send_IPI_mask			= x2apic_send_IPI_mask,
 	.send_IPI_mask_allbutself	= x2apic_send_IPI_mask_allbutself,
 	.send_IPI_allbutself		= x2apic_send_IPI_allbutself,
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index 662e915..a1242e2 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -36,6 +36,14 @@
 	return x2apic_enabled() && (x2apic_phys || x2apic_fadt_phys());
 }
 
+static void x2apic_send_IPI(int cpu, int vector)
+{
+	u32 dest = per_cpu(x86_cpu_to_apicid, cpu);
+
+	x2apic_wrmsr_fence();
+	__x2apic_send_IPI_dest(dest, vector, APIC_DEST_PHYSICAL);
+}
+
 static void
 __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest)
 {
@@ -122,6 +130,7 @@
 
 	.cpu_mask_to_apicid_and		= default_cpu_mask_to_apicid_and,
 
+	.send_IPI			= x2apic_send_IPI,
 	.send_IPI_mask			= x2apic_send_IPI_mask,
 	.send_IPI_mask_allbutself	= x2apic_send_IPI_mask_allbutself,
 	.send_IPI_allbutself		= x2apic_send_IPI_allbutself,
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 4a13946..d760c6b 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -406,6 +406,7 @@
 
 	.cpu_mask_to_apicid_and		= uv_cpu_mask_to_apicid_and,
 
+	.send_IPI			= uv_send_IPI_one,
 	.send_IPI_mask			= uv_send_IPI_mask,
 	.send_IPI_mask_allbutself	= uv_send_IPI_mask_allbutself,
 	.send_IPI_allbutself		= uv_send_IPI_allbutself,
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 439df97..84a7524 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -65,9 +65,6 @@
 	OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable);
 	OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable);
 	OFFSET(PV_CPU_iret, pv_cpu_ops, iret);
-#ifdef CONFIG_X86_32
-	OFFSET(PV_CPU_irq_enable_sysexit, pv_cpu_ops, irq_enable_sysexit);
-#endif
 	OFFSET(PV_CPU_read_cr0, pv_cpu_ops, read_cr0);
 	OFFSET(PV_MMU_read_cr2, pv_mmu_ops, read_cr2);
 #endif
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index d8f42f9..f2edafb 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -23,7 +23,6 @@
 {
 #ifdef CONFIG_PARAVIRT
 	OFFSET(PV_IRQ_adjust_exception_frame, pv_irq_ops, adjust_exception_frame);
-	OFFSET(PV_CPU_usergs_sysret32, pv_cpu_ops, usergs_sysret32);
 	OFFSET(PV_CPU_usergs_sysret64, pv_cpu_ops, usergs_sysret64);
 	OFFSET(PV_CPU_swapgs, pv_cpu_ops, swapgs);
 	BLANK();
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index a8816b3..e678dde 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -304,7 +304,7 @@
 	int cpu = smp_processor_id();
 
 	/* get information required for multi-node processors */
-	if (cpu_has_topoext) {
+	if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
 		u32 eax, ebx, ecx, edx;
 
 		cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
@@ -678,9 +678,9 @@
 	 * Disable it on the affected CPUs.
 	 */
 	if ((c->x86_model >= 0x02) && (c->x86_model < 0x20)) {
-		if (!rdmsrl_safe(0xc0011021, &value) && !(value & 0x1E)) {
+		if (!rdmsrl_safe(MSR_F15H_IC_CFG, &value) && !(value & 0x1E)) {
 			value |= 0x1E;
-			wrmsrl_safe(0xc0011021, value);
+			wrmsrl_safe(MSR_F15H_IC_CFG, value);
 		}
 	}
 }
@@ -922,7 +922,7 @@
 
 void set_dr_addr_mask(unsigned long mask, int dr)
 {
-	if (!cpu_has_bpext)
+	if (!boot_cpu_has(X86_FEATURE_BPEXT))
 		return;
 
 	switch (dr) {
diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index d8fba5c..ae20be6 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -43,7 +43,7 @@
 		/* store Centaur Extended Feature Flags as
 		 * word 5 of the CPU capability bit array
 		 */
-		c->x86_capability[5] = cpuid_edx(0xC0000001);
+		c->x86_capability[CPUID_C000_0001_EDX] = cpuid_edx(0xC0000001);
 	}
 #ifdef CONFIG_X86_32
 	/* Cyrix III family needs CX8 & PGE explicitly enabled. */
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index c2b7522..37830de 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -581,14 +581,9 @@
 		u32 junk, tfms, cap0, misc;
 
 		cpuid(0x00000001, &tfms, &misc, &junk, &cap0);
-		c->x86 = (tfms >> 8) & 0xf;
-		c->x86_model = (tfms >> 4) & 0xf;
-		c->x86_mask = tfms & 0xf;
-
-		if (c->x86 == 0xf)
-			c->x86 += (tfms >> 20) & 0xff;
-		if (c->x86 >= 0x6)
-			c->x86_model += ((tfms >> 16) & 0xf) << 4;
+		c->x86		= x86_family(tfms);
+		c->x86_model	= x86_model(tfms);
+		c->x86_mask	= x86_stepping(tfms);
 
 		if (cap0 & (1<<19)) {
 			c->x86_clflush_size = ((misc >> 8) & 0xff) * 8;
@@ -599,50 +594,47 @@
 
 void get_cpu_cap(struct cpuinfo_x86 *c)
 {
-	u32 tfms, xlvl;
-	u32 ebx;
+	u32 eax, ebx, ecx, edx;
 
 	/* Intel-defined flags: level 0x00000001 */
 	if (c->cpuid_level >= 0x00000001) {
-		u32 capability, excap;
+		cpuid(0x00000001, &eax, &ebx, &ecx, &edx);
 
-		cpuid(0x00000001, &tfms, &ebx, &excap, &capability);
-		c->x86_capability[0] = capability;
-		c->x86_capability[4] = excap;
+		c->x86_capability[CPUID_1_ECX] = ecx;
+		c->x86_capability[CPUID_1_EDX] = edx;
 	}
 
 	/* Additional Intel-defined flags: level 0x00000007 */
 	if (c->cpuid_level >= 0x00000007) {
-		u32 eax, ebx, ecx, edx;
-
 		cpuid_count(0x00000007, 0, &eax, &ebx, &ecx, &edx);
 
-		c->x86_capability[9] = ebx;
+		c->x86_capability[CPUID_7_0_EBX] = ebx;
+
+		c->x86_capability[CPUID_6_EAX] = cpuid_eax(0x00000006);
 	}
 
 	/* Extended state features: level 0x0000000d */
 	if (c->cpuid_level >= 0x0000000d) {
-		u32 eax, ebx, ecx, edx;
-
 		cpuid_count(0x0000000d, 1, &eax, &ebx, &ecx, &edx);
 
-		c->x86_capability[10] = eax;
+		c->x86_capability[CPUID_D_1_EAX] = eax;
 	}
 
 	/* Additional Intel-defined flags: level 0x0000000F */
 	if (c->cpuid_level >= 0x0000000F) {
-		u32 eax, ebx, ecx, edx;
 
 		/* QoS sub-leaf, EAX=0Fh, ECX=0 */
 		cpuid_count(0x0000000F, 0, &eax, &ebx, &ecx, &edx);
-		c->x86_capability[11] = edx;
+		c->x86_capability[CPUID_F_0_EDX] = edx;
+
 		if (cpu_has(c, X86_FEATURE_CQM_LLC)) {
 			/* will be overridden if occupancy monitoring exists */
 			c->x86_cache_max_rmid = ebx;
 
 			/* QoS sub-leaf, EAX=0Fh, ECX=1 */
 			cpuid_count(0x0000000F, 1, &eax, &ebx, &ecx, &edx);
-			c->x86_capability[12] = edx;
+			c->x86_capability[CPUID_F_1_EDX] = edx;
+
 			if (cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC)) {
 				c->x86_cache_max_rmid = ecx;
 				c->x86_cache_occ_scale = ebx;
@@ -654,22 +646,24 @@
 	}
 
 	/* AMD-defined flags: level 0x80000001 */
-	xlvl = cpuid_eax(0x80000000);
-	c->extended_cpuid_level = xlvl;
+	eax = cpuid_eax(0x80000000);
+	c->extended_cpuid_level = eax;
 
-	if ((xlvl & 0xffff0000) == 0x80000000) {
-		if (xlvl >= 0x80000001) {
-			c->x86_capability[1] = cpuid_edx(0x80000001);
-			c->x86_capability[6] = cpuid_ecx(0x80000001);
+	if ((eax & 0xffff0000) == 0x80000000) {
+		if (eax >= 0x80000001) {
+			cpuid(0x80000001, &eax, &ebx, &ecx, &edx);
+
+			c->x86_capability[CPUID_8000_0001_ECX] = ecx;
+			c->x86_capability[CPUID_8000_0001_EDX] = edx;
 		}
 	}
 
 	if (c->extended_cpuid_level >= 0x80000008) {
-		u32 eax = cpuid_eax(0x80000008);
+		cpuid(0x80000008, &eax, &ebx, &ecx, &edx);
 
 		c->x86_virt_bits = (eax >> 8) & 0xff;
 		c->x86_phys_bits = eax & 0xff;
-		c->x86_capability[13] = cpuid_ebx(0x80000008);
+		c->x86_capability[CPUID_8000_0008_EBX] = ebx;
 	}
 #ifdef CONFIG_X86_32
 	else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36))
@@ -679,6 +673,9 @@
 	if (c->extended_cpuid_level >= 0x80000007)
 		c->x86_power = cpuid_edx(0x80000007);
 
+	if (c->extended_cpuid_level >= 0x8000000a)
+		c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a);
+
 	init_scattered_cpuid_features(c);
 }
 
@@ -1185,7 +1182,7 @@
 	 * They both write to the same internal register. STAR allows to
 	 * set CS/DS but only a 32bit target. LSTAR sets the 64bit rip.
 	 */
-	wrmsrl(MSR_STAR,  ((u64)__USER32_CS)<<48  | ((u64)__KERNEL_CS)<<32);
+	wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS);
 	wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64);
 
 #ifdef CONFIG_IA32_EMULATION
@@ -1443,7 +1440,9 @@
 
 	printk(KERN_INFO "Initializing CPU#%d\n", cpu);
 
-	if (cpu_feature_enabled(X86_FEATURE_VME) || cpu_has_tsc || cpu_has_de)
+	if (cpu_feature_enabled(X86_FEATURE_VME) ||
+	    cpu_has_tsc ||
+	    boot_cpu_has(X86_FEATURE_DE))
 		cr4_clear_bits(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE);
 
 	load_current_idt();
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 209ac1e..565648b 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -445,7 +445,8 @@
 
 	if (cpu_has_xmm2)
 		set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
-	if (cpu_has_ds) {
+
+	if (boot_cpu_has(X86_FEATURE_DS)) {
 		unsigned int l1;
 		rdmsr(MSR_IA32_MISC_ENABLE, l1, l2);
 		if (!(l1 & (1<<11)))
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index e38d338..0b6c523 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -591,7 +591,7 @@
 	unsigned		edx;
 
 	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
-		if (cpu_has_topoext)
+		if (boot_cpu_has(X86_FEATURE_TOPOEXT))
 			cpuid_count(0x8000001d, index, &eax.full,
 				    &ebx.full, &ecx.full, &edx);
 		else
@@ -637,7 +637,7 @@
 void init_amd_cacheinfo(struct cpuinfo_x86 *c)
 {
 
-	if (cpu_has_topoext) {
+	if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
 		num_cache_leaves = find_num_cache_leaves(c);
 	} else if (c->extended_cpuid_level >= 0x80000006) {
 		if (cpuid_edx(0x80000006) & 0xf000)
@@ -809,7 +809,7 @@
 	struct cacheinfo *this_leaf;
 	int i, sibling;
 
-	if (cpu_has_topoext) {
+	if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
 		unsigned int apicid, nshared, first, last;
 
 		this_leaf = this_cpu_ci->info_list + index;
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index c5b0d56..a006f4c 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -114,7 +114,6 @@
 static struct irq_work mce_irq_work;
 
 static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs);
-static int mce_usable_address(struct mce *m);
 
 /*
  * CPU/chipset specific EDAC code can register a notifier call here to print
@@ -475,6 +474,28 @@
 	irq_work_queue(&mce_irq_work);
 }
 
+/*
+ * Check if the address reported by the CPU is in a format we can parse.
+ * It would be possible to add code for most other cases, but all would
+ * be somewhat complicated (e.g. segment offset would require an instruction
+ * parser). So only support physical addresses up to page granuality for now.
+ */
+static int mce_usable_address(struct mce *m)
+{
+	if (!(m->status & MCI_STATUS_MISCV) || !(m->status & MCI_STATUS_ADDRV))
+		return 0;
+
+	/* Checks after this one are Intel-specific: */
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+		return 1;
+
+	if (MCI_MISC_ADDR_LSB(m->misc) > PAGE_SHIFT)
+		return 0;
+	if (MCI_MISC_ADDR_MODE(m->misc) != MCI_MISC_ADDR_PHYS)
+		return 0;
+	return 1;
+}
+
 static int srao_decode_notifier(struct notifier_block *nb, unsigned long val,
 				void *data)
 {
@@ -484,7 +505,7 @@
 	if (!mce)
 		return NOTIFY_DONE;
 
-	if (mce->usable_addr && (mce->severity == MCE_AO_SEVERITY)) {
+	if (mce_usable_address(mce) && (mce->severity == MCE_AO_SEVERITY)) {
 		pfn = mce->addr >> PAGE_SHIFT;
 		memory_failure(pfn, MCE_VECTOR, 0);
 	}
@@ -522,10 +543,10 @@
 	struct cpuinfo_x86 *c = &boot_cpu_data;
 
 	if (c->x86_vendor == X86_VENDOR_AMD) {
-		/*
-		 * coming soon
-		 */
-		return false;
+		/* ErrCodeExt[20:16] */
+		u8 xec = (m->status >> 16) & 0x1f;
+
+		return (xec == 0x0 || xec == 0x8);
 	} else if (c->x86_vendor == X86_VENDOR_INTEL) {
 		/*
 		 * Intel SDM Volume 3B - 15.9.2 Compound Error Codes
@@ -567,7 +588,7 @@
  */
 bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 {
-	bool error_logged = false;
+	bool error_seen = false;
 	struct mce m;
 	int severity;
 	int i;
@@ -601,6 +622,8 @@
 		    (m.status & (mca_cfg.ser ? MCI_STATUS_S : MCI_STATUS_UC)))
 			continue;
 
+		error_seen = true;
+
 		mce_read_aux(&m, i);
 
 		if (!(flags & MCP_TIMESTAMP))
@@ -608,27 +631,24 @@
 
 		severity = mce_severity(&m, mca_cfg.tolerant, NULL, false);
 
-		/*
-		 * In the cases where we don't have a valid address after all,
-		 * do not add it into the ring buffer.
-		 */
-		if (severity == MCE_DEFERRED_SEVERITY && memory_error(&m)) {
-			if (m.status & MCI_STATUS_ADDRV) {
+		if (severity == MCE_DEFERRED_SEVERITY && memory_error(&m))
+			if (m.status & MCI_STATUS_ADDRV)
 				m.severity = severity;
-				m.usable_addr = mce_usable_address(&m);
-
-				if (!mce_gen_pool_add(&m))
-					mce_schedule_work();
-			}
-		}
 
 		/*
 		 * Don't get the IP here because it's unlikely to
 		 * have anything to do with the actual error location.
 		 */
-		if (!(flags & MCP_DONTLOG) && !mca_cfg.dont_log_ce) {
-			error_logged = true;
+		if (!(flags & MCP_DONTLOG) && !mca_cfg.dont_log_ce)
 			mce_log(&m);
+		else if (mce_usable_address(&m)) {
+			/*
+			 * Although we skipped logging this, we still want
+			 * to take action. Add to the pool so the registered
+			 * notifiers will see it.
+			 */
+			if (!mce_gen_pool_add(&m))
+				mce_schedule_work();
 		}
 
 		/*
@@ -644,7 +664,7 @@
 
 	sync_core();
 
-	return error_logged;
+	return error_seen;
 }
 EXPORT_SYMBOL_GPL(machine_check_poll);
 
@@ -931,23 +951,6 @@
 	return ret;
 }
 
-/*
- * Check if the address reported by the CPU is in a format we can parse.
- * It would be possible to add code for most other cases, but all would
- * be somewhat complicated (e.g. segment offset would require an instruction
- * parser). So only support physical addresses up to page granuality for now.
- */
-static int mce_usable_address(struct mce *m)
-{
-	if (!(m->status & MCI_STATUS_MISCV) || !(m->status & MCI_STATUS_ADDRV))
-		return 0;
-	if (MCI_MISC_ADDR_LSB(m->misc) > PAGE_SHIFT)
-		return 0;
-	if (MCI_MISC_ADDR_MODE(m->misc) != MCI_MISC_ADDR_PHYS)
-		return 0;
-	return 1;
-}
-
 static void mce_clear_state(unsigned long *toclear)
 {
 	int i;
@@ -999,6 +1002,17 @@
 	int flags = MF_ACTION_REQUIRED;
 	int lmce = 0;
 
+	/* If this CPU is offline, just bail out. */
+	if (cpu_is_offline(smp_processor_id())) {
+		u64 mcgstatus;
+
+		mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS);
+		if (mcgstatus & MCG_STATUS_RIPV) {
+			mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
+			return;
+		}
+	}
+
 	ist_enter(regs);
 
 	this_cpu_inc(mce_exception_count);
@@ -1089,7 +1103,6 @@
 
 		/* assuming valid severity level != 0 */
 		m.severity = severity;
-		m.usable_addr = mce_usable_address(&m);
 
 		mce_log(&m);
 
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index b3e94ef..faec712 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -129,8 +129,8 @@
 	if (!have_cpuid_p())
 		return;
 
-	vendor = x86_vendor();
-	family = x86_family();
+	vendor = x86_cpuid_vendor();
+	family = x86_cpuid_family();
 
 	switch (vendor) {
 	case X86_VENDOR_INTEL:
@@ -165,8 +165,8 @@
 	if (!have_cpuid_p())
 		return;
 
-	vendor = x86_vendor();
-	family = x86_family();
+	vendor = x86_cpuid_vendor();
+	family = x86_cpuid_family();
 
 	switch (vendor) {
 	case X86_VENDOR_INTEL:
@@ -206,8 +206,8 @@
 {
 	int vendor, family;
 
-	vendor = x86_vendor();
-	family = x86_family();
+	vendor = x86_cpuid_vendor();
+	family = x86_cpuid_family();
 
 	switch (vendor) {
 	case X86_VENDOR_INTEL:
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index ce47402..ee81c54 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -145,10 +145,10 @@
 	int ext_sigcount, i;
 	struct extended_signature *ext_sig;
 
-	fam   = __x86_family(sig);
+	fam   = x86_family(sig);
 	model = x86_model(sig);
 
-	fam_ucode   = __x86_family(mc_header->sig);
+	fam_ucode   = x86_family(mc_header->sig);
 	model_ucode = x86_model(mc_header->sig);
 
 	if (fam == fam_ucode && model == model_ucode)
@@ -163,7 +163,7 @@
 	ext_sigcount = ext_header->count;
 
 	for (i = 0; i < ext_sigcount; i++) {
-		fam_ucode   = __x86_family(ext_sig->sig);
+		fam_ucode   = x86_family(ext_sig->sig);
 		model_ucode = x86_model(ext_sig->sig);
 
 		if (fam == fam_ucode && model == model_ucode)
@@ -365,7 +365,7 @@
 	native_cpuid(&eax, &ebx, &ecx, &edx);
 	csig.sig = eax;
 
-	family = __x86_family(csig.sig);
+	family = x86_family(csig.sig);
 	model  = x86_model(csig.sig);
 
 	if ((model >= 5) || (family > 6)) {
@@ -521,16 +521,12 @@
 {
 #ifdef CONFIG_X86_64
 	unsigned int eax = 0x00000001, ebx, ecx = 0, edx;
-	unsigned int family, model, stepping;
 	char name[30];
 
 	native_cpuid(&eax, &ebx, &ecx, &edx);
 
-	family   = __x86_family(eax);
-	model    = x86_model(eax);
-	stepping = eax & 0xf;
-
-	sprintf(name, "intel-ucode/%02x-%02x-%02x", family, model, stepping);
+	sprintf(name, "intel-ucode/%02x-%02x-%02x",
+		      x86_family(eax), x86_model(eax), x86_stepping(eax));
 
 	return get_builtin_firmware(cp, name);
 #else
diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c
index 70d7c93..0d98503 100644
--- a/arch/x86/kernel/cpu/mtrr/cleanup.c
+++ b/arch/x86/kernel/cpu/mtrr/cleanup.c
@@ -593,9 +593,16 @@
 		      unsigned long x_remove_base,
 		      unsigned long x_remove_size, int i)
 {
-	static struct range range_new[RANGE_NUM];
+	/*
+	 * range_new should really be an automatic variable, but
+	 * putting 4096 bytes on the stack is frowned upon, to put it
+	 * mildly. It is safe to make it a static __initdata variable,
+	 * since mtrr_calc_range_state is only called during init and
+	 * there's no way it will call itself recursively.
+	 */
+	static struct range range_new[RANGE_NUM] __initdata;
 	unsigned long range_sums_new;
-	static int nr_range_new;
+	int nr_range_new;
 	int num_reg;
 
 	/* Convert ranges to var ranges state: */
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 3b533cf..c870af1 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -349,7 +349,7 @@
 
 void mtrr_save_fixed_ranges(void *info)
 {
-	if (cpu_has_mtrr)
+	if (boot_cpu_has(X86_FEATURE_MTRR))
 		get_fixed_ranges(mtrr_state.fixed_ranges);
 }
 
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index f891b47..5c3d149 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -682,7 +682,7 @@
 
 	phys_addr = 32;
 
-	if (cpu_has_mtrr) {
+	if (boot_cpu_has(X86_FEATURE_MTRR)) {
 		mtrr_if = &generic_mtrr_ops;
 		size_or_mask = SIZE_OR_MASK_BITS(36);
 		size_and_mask = 0x00f00000;
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 2bf79d7..1b443db 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -482,6 +482,9 @@
 			/* Support for IP fixup */
 			if (x86_pmu.lbr_nr || x86_pmu.intel_cap.pebs_format >= 2)
 				precise++;
+
+			if (x86_pmu.pebs_prec_dist)
+				precise++;
 		}
 
 		if (event->attr.precise_ip > precise)
@@ -1531,6 +1534,7 @@
 {
 	struct device_attribute *d;
 	struct perf_pmu_events_attr *pmu_attr;
+	int offset = 0;
 	int i, j;
 
 	for (i = 0; attrs[i]; i++) {
@@ -1539,7 +1543,7 @@
 		/* str trumps id */
 		if (pmu_attr->event_str)
 			continue;
-		if (x86_pmu.event_map(i))
+		if (x86_pmu.event_map(i + offset))
 			continue;
 
 		for (j = i; attrs[j]; j++)
@@ -1547,6 +1551,14 @@
 
 		/* Check the shifted attr. */
 		i--;
+
+		/*
+		 * event_map() is index based, the attrs array is organized
+		 * by increasing event index. If we shift the events, then
+		 * we need to compensate for the event_map(), otherwise
+		 * we are looking up the wrong event in the map
+		 */
+		offset++;
 	}
 }
 
@@ -2250,12 +2262,19 @@
 	ss_base = get_segment_base(regs->ss);
 
 	fp = compat_ptr(ss_base + regs->bp);
+	pagefault_disable();
 	while (entry->nr < PERF_MAX_STACK_DEPTH) {
 		unsigned long bytes;
 		frame.next_frame     = 0;
 		frame.return_address = 0;
 
-		bytes = copy_from_user_nmi(&frame, fp, sizeof(frame));
+		if (!access_ok(VERIFY_READ, fp, 8))
+			break;
+
+		bytes = __copy_from_user_nmi(&frame.next_frame, fp, 4);
+		if (bytes != 0)
+			break;
+		bytes = __copy_from_user_nmi(&frame.return_address, fp+4, 4);
 		if (bytes != 0)
 			break;
 
@@ -2265,6 +2284,7 @@
 		perf_callchain_store(entry, cs_base + frame.return_address);
 		fp = compat_ptr(ss_base + frame.next_frame);
 	}
+	pagefault_enable();
 	return 1;
 }
 #else
@@ -2302,12 +2322,19 @@
 	if (perf_callchain_user32(regs, entry))
 		return;
 
+	pagefault_disable();
 	while (entry->nr < PERF_MAX_STACK_DEPTH) {
 		unsigned long bytes;
 		frame.next_frame	     = NULL;
 		frame.return_address = 0;
 
-		bytes = copy_from_user_nmi(&frame, fp, sizeof(frame));
+		if (!access_ok(VERIFY_READ, fp, 16))
+			break;
+
+		bytes = __copy_from_user_nmi(&frame.next_frame, fp, 8);
+		if (bytes != 0)
+			break;
+		bytes = __copy_from_user_nmi(&frame.return_address, fp+8, 8);
 		if (bytes != 0)
 			break;
 
@@ -2315,8 +2342,9 @@
 			break;
 
 		perf_callchain_store(entry, frame.return_address);
-		fp = frame.next_frame;
+		fp = (void __user *)frame.next_frame;
 	}
+	pagefault_enable();
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index d0e35eb..7bb61e3 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -14,17 +14,7 @@
 
 #include <linux/perf_event.h>
 
-#if 0
-#undef wrmsrl
-#define wrmsrl(msr, val) 						\
-do {									\
-	unsigned int _msr = (msr);					\
-	u64 _val = (val);						\
-	trace_printk("wrmsrl(%x, %Lx)\n", (unsigned int)(_msr),		\
-			(unsigned long long)(_val));			\
-	native_write_msr((_msr), (u32)(_val), (u32)(_val >> 32));	\
-} while (0)
-#endif
+/* To enable MSR tracing please use the generic trace points. */
 
 /*
  *          |   NHM/WSM    |      SNB     |
@@ -318,6 +308,10 @@
 #define INTEL_UEVENT_CONSTRAINT(c, n)	\
 	EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK)
 
+/* Constraint on specific umask bit only + event */
+#define INTEL_UBIT_EVENT_CONSTRAINT(c, n)	\
+	EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT|(c))
+
 /* Like UEVENT_CONSTRAINT, but match flags too */
 #define INTEL_FLAGS_UEVENT_CONSTRAINT(c, n)	\
 	EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS)
@@ -589,7 +583,8 @@
 			bts_active	:1,
 			pebs		:1,
 			pebs_active	:1,
-			pebs_broken	:1;
+			pebs_broken	:1,
+			pebs_prec_dist	:1;
 	int		pebs_record_size;
 	void		(*drain_pebs)(struct pt_regs *regs);
 	struct event_constraint *pebs_constraints;
@@ -907,6 +902,8 @@
 
 void intel_pmu_lbr_init_skl(void);
 
+void intel_pmu_lbr_init_knl(void);
+
 int intel_pmu_setup_lbr_filter(struct perf_event *event);
 
 void intel_pt_interrupt(void);
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 1cee5d2..5861053 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -18,7 +18,7 @@
 		[ C(RESULT_MISS)   ] = 0x0141, /* Data Cache Misses          */
 	},
 	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0142, /* Data Cache Refills :system */
+		[ C(RESULT_ACCESS) ] = 0,
 		[ C(RESULT_MISS)   ] = 0,
 	},
 	[ C(OP_PREFETCH) ] = {
@@ -160,7 +160,7 @@
 	if (offset)
 		return offset;
 
-	if (!cpu_has_perfctr_core)
+	if (!boot_cpu_has(X86_FEATURE_PERFCTR_CORE))
 		offset = index;
 	else
 		offset = index << 1;
@@ -652,7 +652,7 @@
 
 static int __init amd_core_pmu_init(void)
 {
-	if (!cpu_has_perfctr_core)
+	if (!boot_cpu_has(X86_FEATURE_PERFCTR_CORE))
 		return 0;
 
 	switch (boot_cpu_data.x86) {
diff --git a/arch/x86/kernel/cpu/perf_event_amd_uncore.c b/arch/x86/kernel/cpu/perf_event_amd_uncore.c
index cc6cedb..4974274 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_uncore.c
@@ -523,10 +523,10 @@
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
 		goto fail_nodev;
 
-	if (!cpu_has_topoext)
+	if (!boot_cpu_has(X86_FEATURE_TOPOEXT))
 		goto fail_nodev;
 
-	if (cpu_has_perfctr_nb) {
+	if (boot_cpu_has(X86_FEATURE_PERFCTR_NB)) {
 		amd_uncore_nb = alloc_percpu(struct amd_uncore *);
 		if (!amd_uncore_nb) {
 			ret = -ENOMEM;
@@ -540,7 +540,7 @@
 		ret = 0;
 	}
 
-	if (cpu_has_perfctr_l2) {
+	if (boot_cpu_has(X86_FEATURE_PERFCTR_L2)) {
 		amd_uncore_l2 = alloc_percpu(struct amd_uncore *);
 		if (!amd_uncore_l2) {
 			ret = -ENOMEM;
@@ -583,10 +583,11 @@
 
 	/* amd_uncore_nb/l2 should have been freed by cleanup_cpu_online */
 	amd_uncore_nb = amd_uncore_l2 = NULL;
-	if (cpu_has_perfctr_l2)
+
+	if (boot_cpu_has(X86_FEATURE_PERFCTR_L2))
 		perf_pmu_unregister(&amd_l2_pmu);
 fail_l2:
-	if (cpu_has_perfctr_nb)
+	if (boot_cpu_has(X86_FEATURE_PERFCTR_NB))
 		perf_pmu_unregister(&amd_nb_pmu);
 	if (amd_uncore_l2)
 		free_percpu(amd_uncore_l2);
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index e2a4300..a667078 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -185,6 +185,14 @@
 	EVENT_CONSTRAINT_END
 };
 
+static struct extra_reg intel_knl_extra_regs[] __read_mostly = {
+	INTEL_UEVENT_EXTRA_REG(0x01b7,
+			       MSR_OFFCORE_RSP_0, 0x7f9ffbffffull, RSP_0),
+	INTEL_UEVENT_EXTRA_REG(0x02b7,
+			       MSR_OFFCORE_RSP_1, 0x3f9ffbffffull, RSP_1),
+	EVENT_EXTRA_END
+};
+
 static struct extra_reg intel_snb_extra_regs[] __read_mostly = {
 	/* must define OFFCORE_RSP_X first, see intel_fixup_er() */
 	INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0),
@@ -255,7 +263,7 @@
 	FIXED_EVENT_CONSTRAINT(0x003c, 1),	/* CPU_CLK_UNHALTED.CORE */
 	FIXED_EVENT_CONSTRAINT(0x0300, 2),	/* CPU_CLK_UNHALTED.REF */
 	INTEL_UEVENT_CONSTRAINT(0x148, 0x4),	/* L1D_PEND_MISS.PENDING */
-	INTEL_UEVENT_CONSTRAINT(0x8a3, 0x4),	/* CYCLE_ACTIVITY.CYCLES_L1D_MISS */
+	INTEL_UBIT_EVENT_CONSTRAINT(0x8a3, 0x4),	/* CYCLE_ACTIVITY.CYCLES_L1D_MISS */
 	EVENT_CONSTRAINT_END
 };
 
@@ -1457,6 +1465,42 @@
  },
 };
 
+#define KNL_OT_L2_HITE		BIT_ULL(19) /* Other Tile L2 Hit */
+#define KNL_OT_L2_HITF		BIT_ULL(20) /* Other Tile L2 Hit */
+#define KNL_MCDRAM_LOCAL	BIT_ULL(21)
+#define KNL_MCDRAM_FAR		BIT_ULL(22)
+#define KNL_DDR_LOCAL		BIT_ULL(23)
+#define KNL_DDR_FAR		BIT_ULL(24)
+#define KNL_DRAM_ANY		(KNL_MCDRAM_LOCAL | KNL_MCDRAM_FAR | \
+				    KNL_DDR_LOCAL | KNL_DDR_FAR)
+#define KNL_L2_READ		SLM_DMND_READ
+#define KNL_L2_WRITE		SLM_DMND_WRITE
+#define KNL_L2_PREFETCH		SLM_DMND_PREFETCH
+#define KNL_L2_ACCESS		SLM_LLC_ACCESS
+#define KNL_L2_MISS		(KNL_OT_L2_HITE | KNL_OT_L2_HITF | \
+				   KNL_DRAM_ANY | SNB_SNP_ANY | \
+						  SNB_NON_DRAM)
+
+static __initconst const u64 knl_hw_cache_extra_regs
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	[C(LL)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)] = KNL_L2_READ | KNL_L2_ACCESS,
+			[C(RESULT_MISS)]   = 0,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)] = KNL_L2_WRITE | KNL_L2_ACCESS,
+			[C(RESULT_MISS)]   = KNL_L2_WRITE | KNL_L2_MISS,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)] = KNL_L2_PREFETCH | KNL_L2_ACCESS,
+			[C(RESULT_MISS)]   = KNL_L2_PREFETCH | KNL_L2_MISS,
+		},
+	},
+};
+
 /*
  * Use from PMIs where the LBRs are already disabled.
  */
@@ -2475,6 +2519,44 @@
 	}
 }
 
+static void intel_pebs_aliases_precdist(struct perf_event *event)
+{
+	if ((event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) {
+		/*
+		 * Use an alternative encoding for CPU_CLK_UNHALTED.THREAD_P
+		 * (0x003c) so that we can use it with PEBS.
+		 *
+		 * The regular CPU_CLK_UNHALTED.THREAD_P event (0x003c) isn't
+		 * PEBS capable. However we can use INST_RETIRED.PREC_DIST
+		 * (0x01c0), which is a PEBS capable event, to get the same
+		 * count.
+		 *
+		 * The PREC_DIST event has special support to minimize sample
+		 * shadowing effects. One drawback is that it can be
+		 * only programmed on counter 1, but that seems like an
+		 * acceptable trade off.
+		 */
+		u64 alt_config = X86_CONFIG(.event=0xc0, .umask=0x01, .inv=1, .cmask=16);
+
+		alt_config |= (event->hw.config & ~X86_RAW_EVENT_MASK);
+		event->hw.config = alt_config;
+	}
+}
+
+static void intel_pebs_aliases_ivb(struct perf_event *event)
+{
+	if (event->attr.precise_ip < 3)
+		return intel_pebs_aliases_snb(event);
+	return intel_pebs_aliases_precdist(event);
+}
+
+static void intel_pebs_aliases_skl(struct perf_event *event)
+{
+	if (event->attr.precise_ip < 3)
+		return intel_pebs_aliases_core2(event);
+	return intel_pebs_aliases_precdist(event);
+}
+
 static unsigned long intel_pmu_free_running_flags(struct perf_event *event)
 {
 	unsigned long flags = x86_pmu.free_running_flags;
@@ -3332,6 +3414,7 @@
 
 		x86_pmu.event_constraints = intel_gen_event_constraints;
 		x86_pmu.pebs_constraints = intel_atom_pebs_event_constraints;
+		x86_pmu.pebs_aliases = intel_pebs_aliases_core2;
 		pr_cont("Atom events, ");
 		break;
 
@@ -3431,7 +3514,8 @@
 
 		x86_pmu.event_constraints = intel_ivb_event_constraints;
 		x86_pmu.pebs_constraints = intel_ivb_pebs_event_constraints;
-		x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
+		x86_pmu.pebs_aliases = intel_pebs_aliases_ivb;
+		x86_pmu.pebs_prec_dist = true;
 		if (boot_cpu_data.x86_model == 62)
 			x86_pmu.extra_regs = intel_snbep_extra_regs;
 		else
@@ -3464,7 +3548,8 @@
 		x86_pmu.event_constraints = intel_hsw_event_constraints;
 		x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints;
 		x86_pmu.extra_regs = intel_snbep_extra_regs;
-		x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
+		x86_pmu.pebs_aliases = intel_pebs_aliases_ivb;
+		x86_pmu.pebs_prec_dist = true;
 		/* all extra regs are per-cpu when HT is on */
 		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
 		x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
@@ -3499,7 +3584,8 @@
 		x86_pmu.event_constraints = intel_bdw_event_constraints;
 		x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints;
 		x86_pmu.extra_regs = intel_snbep_extra_regs;
-		x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
+		x86_pmu.pebs_aliases = intel_pebs_aliases_ivb;
+		x86_pmu.pebs_prec_dist = true;
 		/* all extra regs are per-cpu when HT is on */
 		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
 		x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
@@ -3511,6 +3597,24 @@
 		pr_cont("Broadwell events, ");
 		break;
 
+	case 87: /* Knights Landing Xeon Phi */
+		memcpy(hw_cache_event_ids,
+		       slm_hw_cache_event_ids, sizeof(hw_cache_event_ids));
+		memcpy(hw_cache_extra_regs,
+		       knl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
+		intel_pmu_lbr_init_knl();
+
+		x86_pmu.event_constraints = intel_slm_event_constraints;
+		x86_pmu.pebs_constraints = intel_slm_pebs_event_constraints;
+		x86_pmu.extra_regs = intel_knl_extra_regs;
+
+		/* all extra regs are per-cpu when HT is on */
+		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+		x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
+
+		pr_cont("Knights Landing events, ");
+		break;
+
 	case 78: /* 14nm Skylake Mobile */
 	case 94: /* 14nm Skylake Desktop */
 		x86_pmu.late_ack = true;
@@ -3521,7 +3625,8 @@
 		x86_pmu.event_constraints = intel_skl_event_constraints;
 		x86_pmu.pebs_constraints = intel_skl_pebs_event_constraints;
 		x86_pmu.extra_regs = intel_skl_extra_regs;
-		x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
+		x86_pmu.pebs_aliases = intel_pebs_aliases_skl;
+		x86_pmu.pebs_prec_dist = true;
 		/* all extra regs are per-cpu when HT is on */
 		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
 		x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 5db1c77..10602f0 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -620,6 +620,8 @@
 	INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1),    /* MEM_LOAD_RETIRED.* */
 	/* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */
 	INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x01),
+	/* Allow all events as PEBS with no flags */
+	INTEL_ALL_EVENT_CONSTRAINT(0, 0x1),
 	EVENT_CONSTRAINT_END
 };
 
@@ -686,6 +688,8 @@
 	INTEL_PST_CONSTRAINT(0x02cd, 0x8),    /* MEM_TRANS_RETIRED.PRECISE_STORES */
 	/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
 	INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
+	/* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */
+	INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2),
 	INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf),    /* MEM_UOP_RETIRED.* */
 	INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf),    /* MEM_LOAD_UOPS_RETIRED.* */
 	INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf),    /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
@@ -700,6 +704,8 @@
 	INTEL_PLD_CONSTRAINT(0x01cd, 0xf),    /* MEM_TRANS_RETIRED.* */
 	/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
 	INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
+	/* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */
+	INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2),
 	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */
 	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(0x11d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */
 	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */
@@ -718,9 +724,10 @@
 
 struct event_constraint intel_skl_pebs_event_constraints[] = {
 	INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x2),	/* INST_RETIRED.PREC_DIST */
-	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */
-	/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
-	INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
+	/* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */
+	INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2),
+	/* INST_RETIRED.TOTAL_CYCLES_PS (inv=1, cmask=16) (cycles:p). */
+	INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x0f),
 	INTEL_PLD_CONSTRAINT(0x1cd, 0xf),		      /* MEM_TRANS_RETIRED.* */
 	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */
 	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */
@@ -1101,6 +1108,13 @@
 	void *at;
 	u64 pebs_status;
 
+	/*
+	 * fmt0 does not have a status bitfield (does not use
+	 * perf_record_nhm format)
+	 */
+	if (x86_pmu.intel_cap.pebs_format < 1)
+		return base;
+
 	if (base == NULL)
 		return NULL;
 
@@ -1186,7 +1200,7 @@
 	if (!event->attr.precise_ip)
 		return;
 
-	n = (top - at) / x86_pmu.pebs_record_size;
+	n = top - at;
 	if (n <= 0)
 		return;
 
@@ -1230,12 +1244,21 @@
 		pebs_status = p->status & cpuc->pebs_enabled;
 		pebs_status &= (1ULL << x86_pmu.max_pebs_events) - 1;
 
+		/*
+		 * On some CPUs the PEBS status can be zero when PEBS is
+		 * racing with clearing of GLOBAL_STATUS.
+		 *
+		 * Normally we would drop that record, but in the
+		 * case when there is only a single active PEBS event
+		 * we can assume it's for that event.
+		 */
+		if (!pebs_status && cpuc->pebs_enabled &&
+			!(cpuc->pebs_enabled & (cpuc->pebs_enabled-1)))
+			pebs_status = cpuc->pebs_enabled;
+
 		bit = find_first_bit((unsigned long *)&pebs_status,
 					x86_pmu.max_pebs_events);
-		if (WARN(bit >= x86_pmu.max_pebs_events,
-			 "PEBS record without PEBS event! status=%Lx pebs_enabled=%Lx active_mask=%Lx",
-			 (unsigned long long)p->status, (unsigned long long)cpuc->pebs_enabled,
-			 *(unsigned long long *)cpuc->active_mask))
+		if (bit >= x86_pmu.max_pebs_events)
 			continue;
 
 		/*
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 659f01e..653f88d 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -42,6 +42,13 @@
 #define LBR_FAR_BIT		8 /* do not capture far branches */
 #define LBR_CALL_STACK_BIT	9 /* enable call stack */
 
+/*
+ * Following bit only exists in Linux; we mask it out before writing it to
+ * the actual MSR. But it helps the constraint perf code to understand
+ * that this is a separate configuration.
+ */
+#define LBR_NO_INFO_BIT	       63 /* don't read LBR_INFO. */
+
 #define LBR_KERNEL	(1 << LBR_KERNEL_BIT)
 #define LBR_USER	(1 << LBR_USER_BIT)
 #define LBR_JCC		(1 << LBR_JCC_BIT)
@@ -52,6 +59,7 @@
 #define LBR_IND_JMP	(1 << LBR_IND_JMP_BIT)
 #define LBR_FAR		(1 << LBR_FAR_BIT)
 #define LBR_CALL_STACK	(1 << LBR_CALL_STACK_BIT)
+#define LBR_NO_INFO	(1ULL << LBR_NO_INFO_BIT)
 
 #define LBR_PLM (LBR_KERNEL | LBR_USER)
 
@@ -152,8 +160,8 @@
 	 * did not change.
 	 */
 	if (cpuc->lbr_sel)
-		lbr_select = cpuc->lbr_sel->config;
-	if (!pmi)
+		lbr_select = cpuc->lbr_sel->config & x86_pmu.lbr_sel_mask;
+	if (!pmi && cpuc->lbr_sel)
 		wrmsrl(MSR_LBR_SELECT, lbr_select);
 
 	rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
@@ -422,6 +430,7 @@
  */
 static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 {
+	bool need_info = false;
 	unsigned long mask = x86_pmu.lbr_nr - 1;
 	int lbr_format = x86_pmu.intel_cap.lbr_format;
 	u64 tos = intel_pmu_lbr_tos();
@@ -429,8 +438,11 @@
 	int out = 0;
 	int num = x86_pmu.lbr_nr;
 
-	if (cpuc->lbr_sel->config & LBR_CALL_STACK)
-		num = tos;
+	if (cpuc->lbr_sel) {
+		need_info = !(cpuc->lbr_sel->config & LBR_NO_INFO);
+		if (cpuc->lbr_sel->config & LBR_CALL_STACK)
+			num = tos;
+	}
 
 	for (i = 0; i < num; i++) {
 		unsigned long lbr_idx = (tos - i) & mask;
@@ -442,7 +454,7 @@
 		rdmsrl(x86_pmu.lbr_from + lbr_idx, from);
 		rdmsrl(x86_pmu.lbr_to   + lbr_idx, to);
 
-		if (lbr_format == LBR_FORMAT_INFO) {
+		if (lbr_format == LBR_FORMAT_INFO && need_info) {
 			u64 info;
 
 			rdmsrl(MSR_LBR_INFO_0 + lbr_idx, info);
@@ -590,6 +602,7 @@
 		if (v != LBR_IGN)
 			mask |= v;
 	}
+
 	reg = &event->hw.branch_reg;
 	reg->idx = EXTRA_REG_LBR;
 
@@ -600,6 +613,11 @@
 	 */
 	reg->config = mask ^ x86_pmu.lbr_sel_mask;
 
+	if ((br_type & PERF_SAMPLE_BRANCH_NO_CYCLES) &&
+	    (br_type & PERF_SAMPLE_BRANCH_NO_FLAGS) &&
+	    (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO))
+		reg->config |= LBR_NO_INFO;
+
 	return 0;
 }
 
@@ -1028,3 +1046,17 @@
 	 */
 	pr_cont("8-deep LBR, ");
 }
+
+/* Knights Landing */
+void intel_pmu_lbr_init_knl(void)
+{
+	x86_pmu.lbr_nr	   = 8;
+	x86_pmu.lbr_tos    = MSR_LBR_TOS;
+	x86_pmu.lbr_from   = MSR_LBR_NHM_FROM;
+	x86_pmu.lbr_to     = MSR_LBR_NHM_TO;
+
+	x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
+	x86_pmu.lbr_sel_map  = snb_lbr_sel_map;
+
+	pr_cont("8-deep LBR, ");
+}
diff --git a/arch/x86/kernel/cpu/perf_event_intel_pt.c b/arch/x86/kernel/cpu/perf_event_intel_pt.c
index 868e119..c0bbd10 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_pt.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_pt.c
@@ -27,6 +27,7 @@
 #include <asm/perf_event.h>
 #include <asm/insn.h>
 #include <asm/io.h>
+#include <asm/intel_pt.h>
 
 #include "perf_event.h"
 #include "intel_pt.h"
@@ -1122,6 +1123,14 @@
 	return 0;
 }
 
+void cpu_emergency_stop_pt(void)
+{
+	struct pt *pt = this_cpu_ptr(&pt_ctx);
+
+	if (pt->handle.event)
+		pt_event_stop(pt->handle.event, PERF_EF_UPDATE);
+}
+
 static __init int pt_init(void)
 {
 	int ret, cpu, prior_warn = 0;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index ed446bd..24a351a 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -63,7 +63,7 @@
 #define INTEL_RAPL_PP1		0x4	/* pseudo-encoding */
 
 #define NR_RAPL_DOMAINS         0x4
-static const char *rapl_domain_names[NR_RAPL_DOMAINS] __initconst = {
+static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = {
 	"pp0-core",
 	"package",
 	"dram",
@@ -109,11 +109,11 @@
 
 #define RAPL_CNTR_WIDTH 32 /* 32-bit rapl counters */
 
-#define RAPL_EVENT_ATTR_STR(_name, v, str)				\
-static struct perf_pmu_events_attr event_attr_##v = {			\
-	.attr		= __ATTR(_name, 0444, rapl_sysfs_show, NULL),	\
-	.id		= 0,						\
-	.event_str	= str,						\
+#define RAPL_EVENT_ATTR_STR(_name, v, str)					\
+static struct perf_pmu_events_attr event_attr_##v = {				\
+	.attr		= __ATTR(_name, 0444, perf_event_sysfs_show, NULL),	\
+	.id		= 0,							\
+	.event_str	= str,							\
 };
 
 struct rapl_pmu {
@@ -405,19 +405,6 @@
 	.attrs = rapl_pmu_attrs,
 };
 
-static ssize_t rapl_sysfs_show(struct device *dev,
-			       struct device_attribute *attr,
-			       char *page)
-{
-	struct perf_pmu_events_attr *pmu_attr = \
-		container_of(attr, struct perf_pmu_events_attr, attr);
-
-	if (pmu_attr->event_str)
-		return sprintf(page, "%s", pmu_attr->event_str);
-
-	return 0;
-}
-
 RAPL_EVENT_ATTR_STR(energy-cores, rapl_cores, "event=0x01");
 RAPL_EVENT_ATTR_STR(energy-pkg  ,   rapl_pkg, "event=0x02");
 RAPL_EVENT_ATTR_STR(energy-ram  ,   rapl_ram, "event=0x03");
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 61215a6..f97f807 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -884,6 +884,15 @@
 	 * each box has a different function id.
 	 */
 	pmu = &type->pmus[UNCORE_PCI_DEV_IDX(id->driver_data)];
+	/* Knights Landing uses a common PCI device ID for multiple instances of
+	 * an uncore PMU device type. There is only one entry per device type in
+	 * the knl_uncore_pci_ids table inspite of multiple devices present for
+	 * some device types. Hence PCI device idx would be 0 for all devices.
+	 * So increment pmu pointer to point to an unused array element.
+	 */
+	if (boot_cpu_data.x86_model == 87)
+		while (pmu->func_id >= 0)
+			pmu++;
 	if (pmu->func_id < 0)
 		pmu->func_id = pdev->devfn;
 	else
@@ -966,6 +975,7 @@
 	case 63: /* Haswell-EP */
 		ret = hswep_uncore_pci_init();
 		break;
+	case 79: /* BDX-EP */
 	case 86: /* BDX-DE */
 		ret = bdx_uncore_pci_init();
 		break;
@@ -982,6 +992,9 @@
 	case 61: /* Broadwell */
 		ret = bdw_uncore_pci_init();
 		break;
+	case 87: /* Knights Landing */
+		ret = knl_uncore_pci_init();
+		break;
 	default:
 		return 0;
 	}
@@ -1287,9 +1300,13 @@
 	case 63: /* Haswell-EP */
 		hswep_uncore_cpu_init();
 		break;
+	case 79: /* BDX-EP */
 	case 86: /* BDX-DE */
 		bdx_uncore_cpu_init();
 		break;
+	case 87: /* Knights Landing */
+		knl_uncore_cpu_init();
+		break;
 	default:
 		return 0;
 	}
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index 2f0a4a9..07aa2d6 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -338,6 +338,7 @@
 int bdw_uncore_pci_init(void);
 void snb_uncore_cpu_init(void);
 void nhm_uncore_cpu_init(void);
+int snb_pci2phy_map_init(int devid);
 
 /* perf_event_intel_uncore_snbep.c */
 int snbep_uncore_pci_init(void);
@@ -348,6 +349,8 @@
 void hswep_uncore_cpu_init(void);
 int bdx_uncore_pci_init(void);
 void bdx_uncore_cpu_init(void);
+int knl_uncore_pci_init(void);
+void knl_uncore_cpu_init(void);
 
 /* perf_event_intel_uncore_nhmex.c */
 void nhmex_uncore_cpu_init(void);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
index 8452561..0b93482 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
@@ -417,7 +417,7 @@
 	}
 }
 
-static int snb_pci2phy_map_init(int devid)
+int snb_pci2phy_map_init(int devid)
 {
 	struct pci_dev *dev = NULL;
 	struct pci2phy_map *map;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
index f0f4fcb..33acb88 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
@@ -209,31 +209,98 @@
 #define HSWEP_PCU_MSR_PMON_BOX_CTL		0x710
 #define HSWEP_PCU_MSR_PMON_BOX_FILTER		0x715
 
+/* KNL Ubox */
+#define KNL_U_MSR_PMON_RAW_EVENT_MASK \
+					(SNBEP_U_MSR_PMON_RAW_EVENT_MASK | \
+						SNBEP_CBO_PMON_CTL_TID_EN)
+/* KNL CHA */
+#define KNL_CHA_MSR_OFFSET			0xc
+#define KNL_CHA_MSR_PMON_CTL_QOR		(1 << 16)
+#define KNL_CHA_MSR_PMON_RAW_EVENT_MASK \
+					(SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK | \
+					 KNL_CHA_MSR_PMON_CTL_QOR)
+#define KNL_CHA_MSR_PMON_BOX_FILTER_TID		0x1ff
+#define KNL_CHA_MSR_PMON_BOX_FILTER_STATE	(7 << 18)
+#define KNL_CHA_MSR_PMON_BOX_FILTER_OP		(0xfffffe2aULL << 32)
+
+/* KNL EDC/MC UCLK */
+#define KNL_UCLK_MSR_PMON_CTR0_LOW		0x400
+#define KNL_UCLK_MSR_PMON_CTL0			0x420
+#define KNL_UCLK_MSR_PMON_BOX_CTL		0x430
+#define KNL_UCLK_MSR_PMON_UCLK_FIXED_LOW	0x44c
+#define KNL_UCLK_MSR_PMON_UCLK_FIXED_CTL	0x454
+#define KNL_PMON_FIXED_CTL_EN			0x1
+
+/* KNL EDC */
+#define KNL_EDC0_ECLK_MSR_PMON_CTR0_LOW		0xa00
+#define KNL_EDC0_ECLK_MSR_PMON_CTL0		0xa20
+#define KNL_EDC0_ECLK_MSR_PMON_BOX_CTL		0xa30
+#define KNL_EDC0_ECLK_MSR_PMON_ECLK_FIXED_LOW	0xa3c
+#define KNL_EDC0_ECLK_MSR_PMON_ECLK_FIXED_CTL	0xa44
+
+/* KNL MC */
+#define KNL_MC0_CH0_MSR_PMON_CTR0_LOW		0xb00
+#define KNL_MC0_CH0_MSR_PMON_CTL0		0xb20
+#define KNL_MC0_CH0_MSR_PMON_BOX_CTL		0xb30
+#define KNL_MC0_CH0_MSR_PMON_FIXED_LOW		0xb3c
+#define KNL_MC0_CH0_MSR_PMON_FIXED_CTL		0xb44
+
+/* KNL IRP */
+#define KNL_IRP_PCI_PMON_BOX_CTL		0xf0
+#define KNL_IRP_PCI_PMON_RAW_EVENT_MASK		(SNBEP_PMON_RAW_EVENT_MASK | \
+						 KNL_CHA_MSR_PMON_CTL_QOR)
+/* KNL PCU */
+#define KNL_PCU_PMON_CTL_EV_SEL_MASK		0x0000007f
+#define KNL_PCU_PMON_CTL_USE_OCC_CTR		(1 << 7)
+#define KNL_PCU_MSR_PMON_CTL_TRESH_MASK		0x3f000000
+#define KNL_PCU_MSR_PMON_RAW_EVENT_MASK	\
+				(KNL_PCU_PMON_CTL_EV_SEL_MASK | \
+				 KNL_PCU_PMON_CTL_USE_OCC_CTR | \
+				 SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \
+				 SNBEP_PMON_CTL_EDGE_DET | \
+				 SNBEP_CBO_PMON_CTL_TID_EN | \
+				 SNBEP_PMON_CTL_EV_SEL_EXT | \
+				 SNBEP_PMON_CTL_INVERT | \
+				 KNL_PCU_MSR_PMON_CTL_TRESH_MASK | \
+				 SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \
+				 SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET)
 
 DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7");
+DEFINE_UNCORE_FORMAT_ATTR(event2, event, "config:0-6");
 DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21");
+DEFINE_UNCORE_FORMAT_ATTR(use_occ_ctr, use_occ_ctr, "config:7");
 DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15");
+DEFINE_UNCORE_FORMAT_ATTR(qor, qor, "config:16");
 DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18");
 DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19");
 DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23");
 DEFINE_UNCORE_FORMAT_ATTR(thresh8, thresh, "config:24-31");
+DEFINE_UNCORE_FORMAT_ATTR(thresh6, thresh, "config:24-29");
 DEFINE_UNCORE_FORMAT_ATTR(thresh5, thresh, "config:24-28");
 DEFINE_UNCORE_FORMAT_ATTR(occ_sel, occ_sel, "config:14-15");
 DEFINE_UNCORE_FORMAT_ATTR(occ_invert, occ_invert, "config:30");
 DEFINE_UNCORE_FORMAT_ATTR(occ_edge, occ_edge, "config:14-51");
+DEFINE_UNCORE_FORMAT_ATTR(occ_edge_det, occ_edge_det, "config:31");
 DEFINE_UNCORE_FORMAT_ATTR(filter_tid, filter_tid, "config1:0-4");
 DEFINE_UNCORE_FORMAT_ATTR(filter_tid2, filter_tid, "config1:0");
 DEFINE_UNCORE_FORMAT_ATTR(filter_tid3, filter_tid, "config1:0-5");
+DEFINE_UNCORE_FORMAT_ATTR(filter_tid4, filter_tid, "config1:0-8");
 DEFINE_UNCORE_FORMAT_ATTR(filter_cid, filter_cid, "config1:5");
 DEFINE_UNCORE_FORMAT_ATTR(filter_link, filter_link, "config1:5-8");
 DEFINE_UNCORE_FORMAT_ATTR(filter_link2, filter_link, "config1:6-8");
+DEFINE_UNCORE_FORMAT_ATTR(filter_link3, filter_link, "config1:12");
 DEFINE_UNCORE_FORMAT_ATTR(filter_nid, filter_nid, "config1:10-17");
 DEFINE_UNCORE_FORMAT_ATTR(filter_nid2, filter_nid, "config1:32-47");
 DEFINE_UNCORE_FORMAT_ATTR(filter_state, filter_state, "config1:18-22");
 DEFINE_UNCORE_FORMAT_ATTR(filter_state2, filter_state, "config1:17-22");
 DEFINE_UNCORE_FORMAT_ATTR(filter_state3, filter_state, "config1:17-23");
+DEFINE_UNCORE_FORMAT_ATTR(filter_state4, filter_state, "config1:18-20");
+DEFINE_UNCORE_FORMAT_ATTR(filter_local, filter_local, "config1:33");
+DEFINE_UNCORE_FORMAT_ATTR(filter_all_op, filter_all_op, "config1:35");
+DEFINE_UNCORE_FORMAT_ATTR(filter_nnm, filter_nnm, "config1:37");
 DEFINE_UNCORE_FORMAT_ATTR(filter_opc, filter_opc, "config1:23-31");
 DEFINE_UNCORE_FORMAT_ATTR(filter_opc2, filter_opc, "config1:52-60");
+DEFINE_UNCORE_FORMAT_ATTR(filter_opc3, filter_opc, "config1:41-60");
 DEFINE_UNCORE_FORMAT_ATTR(filter_nc, filter_nc, "config1:62");
 DEFINE_UNCORE_FORMAT_ATTR(filter_c6, filter_c6, "config1:61");
 DEFINE_UNCORE_FORMAT_ATTR(filter_isoc, filter_isoc, "config1:63");
@@ -315,8 +382,9 @@
 static void snbep_uncore_pci_init_box(struct intel_uncore_box *box)
 {
 	struct pci_dev *pdev = box->pci_dev;
+	int box_ctl = uncore_pci_box_ctl(box);
 
-	pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, SNBEP_PMON_BOX_CTL_INT);
+	pci_write_config_dword(pdev, box_ctl, SNBEP_PMON_BOX_CTL_INT);
 }
 
 static void snbep_uncore_msr_disable_box(struct intel_uncore_box *box)
@@ -1728,6 +1796,419 @@
 }
 /* end of IvyTown uncore support */
 
+/* KNL uncore support */
+static struct attribute *knl_uncore_ubox_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_tid_en.attr,
+	&format_attr_inv.attr,
+	&format_attr_thresh5.attr,
+	NULL,
+};
+
+static struct attribute_group knl_uncore_ubox_format_group = {
+	.name = "format",
+	.attrs = knl_uncore_ubox_formats_attr,
+};
+
+static struct intel_uncore_type knl_uncore_ubox = {
+	.name			= "ubox",
+	.num_counters		= 2,
+	.num_boxes		= 1,
+	.perf_ctr_bits		= 48,
+	.fixed_ctr_bits		= 48,
+	.perf_ctr		= HSWEP_U_MSR_PMON_CTR0,
+	.event_ctl		= HSWEP_U_MSR_PMON_CTL0,
+	.event_mask		= KNL_U_MSR_PMON_RAW_EVENT_MASK,
+	.fixed_ctr		= HSWEP_U_MSR_PMON_UCLK_FIXED_CTR,
+	.fixed_ctl		= HSWEP_U_MSR_PMON_UCLK_FIXED_CTL,
+	.ops			= &snbep_uncore_msr_ops,
+	.format_group		= &knl_uncore_ubox_format_group,
+};
+
+static struct attribute *knl_uncore_cha_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_qor.attr,
+	&format_attr_edge.attr,
+	&format_attr_tid_en.attr,
+	&format_attr_inv.attr,
+	&format_attr_thresh8.attr,
+	&format_attr_filter_tid4.attr,
+	&format_attr_filter_link3.attr,
+	&format_attr_filter_state4.attr,
+	&format_attr_filter_local.attr,
+	&format_attr_filter_all_op.attr,
+	&format_attr_filter_nnm.attr,
+	&format_attr_filter_opc3.attr,
+	&format_attr_filter_nc.attr,
+	&format_attr_filter_isoc.attr,
+	NULL,
+};
+
+static struct attribute_group knl_uncore_cha_format_group = {
+	.name = "format",
+	.attrs = knl_uncore_cha_formats_attr,
+};
+
+static struct event_constraint knl_uncore_cha_constraints[] = {
+	UNCORE_EVENT_CONSTRAINT(0x11, 0x1),
+	UNCORE_EVENT_CONSTRAINT(0x1f, 0x1),
+	UNCORE_EVENT_CONSTRAINT(0x36, 0x1),
+	EVENT_CONSTRAINT_END
+};
+
+static struct extra_reg knl_uncore_cha_extra_regs[] = {
+	SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN,
+				  SNBEP_CBO_PMON_CTL_TID_EN, 0x1),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x3d, 0xff, 0x2),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x35, 0xff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x36, 0xff, 0x4),
+	EVENT_EXTRA_END
+};
+
+static u64 knl_cha_filter_mask(int fields)
+{
+	u64 mask = 0;
+
+	if (fields & 0x1)
+		mask |= KNL_CHA_MSR_PMON_BOX_FILTER_TID;
+	if (fields & 0x2)
+		mask |= KNL_CHA_MSR_PMON_BOX_FILTER_STATE;
+	if (fields & 0x4)
+		mask |= KNL_CHA_MSR_PMON_BOX_FILTER_OP;
+	return mask;
+}
+
+static struct event_constraint *
+knl_cha_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+	return __snbep_cbox_get_constraint(box, event, knl_cha_filter_mask);
+}
+
+static int knl_cha_hw_config(struct intel_uncore_box *box,
+			     struct perf_event *event)
+{
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct extra_reg *er;
+	int idx = 0;
+
+	for (er = knl_uncore_cha_extra_regs; er->msr; er++) {
+		if (er->event != (event->hw.config & er->config_mask))
+			continue;
+		idx |= er->idx;
+	}
+
+	if (idx) {
+		reg1->reg = HSWEP_C0_MSR_PMON_BOX_FILTER0 +
+			    KNL_CHA_MSR_OFFSET * box->pmu->pmu_idx;
+		reg1->config = event->attr.config1 & knl_cha_filter_mask(idx);
+		reg1->idx = idx;
+	}
+	return 0;
+}
+
+static void hswep_cbox_enable_event(struct intel_uncore_box *box,
+				    struct perf_event *event);
+
+static struct intel_uncore_ops knl_uncore_cha_ops = {
+	.init_box		= snbep_uncore_msr_init_box,
+	.disable_box		= snbep_uncore_msr_disable_box,
+	.enable_box		= snbep_uncore_msr_enable_box,
+	.disable_event		= snbep_uncore_msr_disable_event,
+	.enable_event		= hswep_cbox_enable_event,
+	.read_counter		= uncore_msr_read_counter,
+	.hw_config		= knl_cha_hw_config,
+	.get_constraint		= knl_cha_get_constraint,
+	.put_constraint		= snbep_cbox_put_constraint,
+};
+
+static struct intel_uncore_type knl_uncore_cha = {
+	.name			= "cha",
+	.num_counters		= 4,
+	.num_boxes		= 38,
+	.perf_ctr_bits		= 48,
+	.event_ctl		= HSWEP_C0_MSR_PMON_CTL0,
+	.perf_ctr		= HSWEP_C0_MSR_PMON_CTR0,
+	.event_mask		= KNL_CHA_MSR_PMON_RAW_EVENT_MASK,
+	.box_ctl		= HSWEP_C0_MSR_PMON_BOX_CTL,
+	.msr_offset		= KNL_CHA_MSR_OFFSET,
+	.num_shared_regs	= 1,
+	.constraints		= knl_uncore_cha_constraints,
+	.ops			= &knl_uncore_cha_ops,
+	.format_group		= &knl_uncore_cha_format_group,
+};
+
+static struct attribute *knl_uncore_pcu_formats_attr[] = {
+	&format_attr_event2.attr,
+	&format_attr_use_occ_ctr.attr,
+	&format_attr_occ_sel.attr,
+	&format_attr_edge.attr,
+	&format_attr_tid_en.attr,
+	&format_attr_inv.attr,
+	&format_attr_thresh6.attr,
+	&format_attr_occ_invert.attr,
+	&format_attr_occ_edge_det.attr,
+	NULL,
+};
+
+static struct attribute_group knl_uncore_pcu_format_group = {
+	.name = "format",
+	.attrs = knl_uncore_pcu_formats_attr,
+};
+
+static struct intel_uncore_type knl_uncore_pcu = {
+	.name			= "pcu",
+	.num_counters		= 4,
+	.num_boxes		= 1,
+	.perf_ctr_bits		= 48,
+	.perf_ctr		= HSWEP_PCU_MSR_PMON_CTR0,
+	.event_ctl		= HSWEP_PCU_MSR_PMON_CTL0,
+	.event_mask		= KNL_PCU_MSR_PMON_RAW_EVENT_MASK,
+	.box_ctl		= HSWEP_PCU_MSR_PMON_BOX_CTL,
+	.ops			= &snbep_uncore_msr_ops,
+	.format_group		= &knl_uncore_pcu_format_group,
+};
+
+static struct intel_uncore_type *knl_msr_uncores[] = {
+	&knl_uncore_ubox,
+	&knl_uncore_cha,
+	&knl_uncore_pcu,
+	NULL,
+};
+
+void knl_uncore_cpu_init(void)
+{
+	uncore_msr_uncores = knl_msr_uncores;
+}
+
+static void knl_uncore_imc_enable_box(struct intel_uncore_box *box)
+{
+	struct pci_dev *pdev = box->pci_dev;
+	int box_ctl = uncore_pci_box_ctl(box);
+
+	pci_write_config_dword(pdev, box_ctl, 0);
+}
+
+static void knl_uncore_imc_enable_event(struct intel_uncore_box *box,
+					struct perf_event *event)
+{
+	struct pci_dev *pdev = box->pci_dev;
+	struct hw_perf_event *hwc = &event->hw;
+
+	if ((event->attr.config & SNBEP_PMON_CTL_EV_SEL_MASK)
+							== UNCORE_FIXED_EVENT)
+		pci_write_config_dword(pdev, hwc->config_base,
+				       hwc->config | KNL_PMON_FIXED_CTL_EN);
+	else
+		pci_write_config_dword(pdev, hwc->config_base,
+				       hwc->config | SNBEP_PMON_CTL_EN);
+}
+
+static struct intel_uncore_ops knl_uncore_imc_ops = {
+	.init_box	= snbep_uncore_pci_init_box,
+	.disable_box	= snbep_uncore_pci_disable_box,
+	.enable_box	= knl_uncore_imc_enable_box,
+	.read_counter	= snbep_uncore_pci_read_counter,
+	.enable_event	= knl_uncore_imc_enable_event,
+	.disable_event	= snbep_uncore_pci_disable_event,
+};
+
+static struct intel_uncore_type knl_uncore_imc_uclk = {
+	.name			= "imc_uclk",
+	.num_counters		= 4,
+	.num_boxes		= 2,
+	.perf_ctr_bits		= 48,
+	.fixed_ctr_bits		= 48,
+	.perf_ctr		= KNL_UCLK_MSR_PMON_CTR0_LOW,
+	.event_ctl		= KNL_UCLK_MSR_PMON_CTL0,
+	.event_mask		= SNBEP_PMON_RAW_EVENT_MASK,
+	.fixed_ctr		= KNL_UCLK_MSR_PMON_UCLK_FIXED_LOW,
+	.fixed_ctl		= KNL_UCLK_MSR_PMON_UCLK_FIXED_CTL,
+	.box_ctl		= KNL_UCLK_MSR_PMON_BOX_CTL,
+	.ops			= &knl_uncore_imc_ops,
+	.format_group		= &snbep_uncore_format_group,
+};
+
+static struct intel_uncore_type knl_uncore_imc_dclk = {
+	.name			= "imc",
+	.num_counters		= 4,
+	.num_boxes		= 6,
+	.perf_ctr_bits		= 48,
+	.fixed_ctr_bits		= 48,
+	.perf_ctr		= KNL_MC0_CH0_MSR_PMON_CTR0_LOW,
+	.event_ctl		= KNL_MC0_CH0_MSR_PMON_CTL0,
+	.event_mask		= SNBEP_PMON_RAW_EVENT_MASK,
+	.fixed_ctr		= KNL_MC0_CH0_MSR_PMON_FIXED_LOW,
+	.fixed_ctl		= KNL_MC0_CH0_MSR_PMON_FIXED_CTL,
+	.box_ctl		= KNL_MC0_CH0_MSR_PMON_BOX_CTL,
+	.ops			= &knl_uncore_imc_ops,
+	.format_group		= &snbep_uncore_format_group,
+};
+
+static struct intel_uncore_type knl_uncore_edc_uclk = {
+	.name			= "edc_uclk",
+	.num_counters		= 4,
+	.num_boxes		= 8,
+	.perf_ctr_bits		= 48,
+	.fixed_ctr_bits		= 48,
+	.perf_ctr		= KNL_UCLK_MSR_PMON_CTR0_LOW,
+	.event_ctl		= KNL_UCLK_MSR_PMON_CTL0,
+	.event_mask		= SNBEP_PMON_RAW_EVENT_MASK,
+	.fixed_ctr		= KNL_UCLK_MSR_PMON_UCLK_FIXED_LOW,
+	.fixed_ctl		= KNL_UCLK_MSR_PMON_UCLK_FIXED_CTL,
+	.box_ctl		= KNL_UCLK_MSR_PMON_BOX_CTL,
+	.ops			= &knl_uncore_imc_ops,
+	.format_group		= &snbep_uncore_format_group,
+};
+
+static struct intel_uncore_type knl_uncore_edc_eclk = {
+	.name			= "edc_eclk",
+	.num_counters		= 4,
+	.num_boxes		= 8,
+	.perf_ctr_bits		= 48,
+	.fixed_ctr_bits		= 48,
+	.perf_ctr		= KNL_EDC0_ECLK_MSR_PMON_CTR0_LOW,
+	.event_ctl		= KNL_EDC0_ECLK_MSR_PMON_CTL0,
+	.event_mask		= SNBEP_PMON_RAW_EVENT_MASK,
+	.fixed_ctr		= KNL_EDC0_ECLK_MSR_PMON_ECLK_FIXED_LOW,
+	.fixed_ctl		= KNL_EDC0_ECLK_MSR_PMON_ECLK_FIXED_CTL,
+	.box_ctl		= KNL_EDC0_ECLK_MSR_PMON_BOX_CTL,
+	.ops			= &knl_uncore_imc_ops,
+	.format_group		= &snbep_uncore_format_group,
+};
+
+static struct event_constraint knl_uncore_m2pcie_constraints[] = {
+	UNCORE_EVENT_CONSTRAINT(0x23, 0x3),
+	EVENT_CONSTRAINT_END
+};
+
+static struct intel_uncore_type knl_uncore_m2pcie = {
+	.name		= "m2pcie",
+	.num_counters   = 4,
+	.num_boxes	= 1,
+	.perf_ctr_bits	= 48,
+	.constraints	= knl_uncore_m2pcie_constraints,
+	SNBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+static struct attribute *knl_uncore_irp_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_qor.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_thresh8.attr,
+	NULL,
+};
+
+static struct attribute_group knl_uncore_irp_format_group = {
+	.name = "format",
+	.attrs = knl_uncore_irp_formats_attr,
+};
+
+static struct intel_uncore_type knl_uncore_irp = {
+	.name			= "irp",
+	.num_counters		= 2,
+	.num_boxes		= 1,
+	.perf_ctr_bits		= 48,
+	.perf_ctr		= SNBEP_PCI_PMON_CTR0,
+	.event_ctl		= SNBEP_PCI_PMON_CTL0,
+	.event_mask		= KNL_IRP_PCI_PMON_RAW_EVENT_MASK,
+	.box_ctl		= KNL_IRP_PCI_PMON_BOX_CTL,
+	.ops			= &snbep_uncore_pci_ops,
+	.format_group		= &knl_uncore_irp_format_group,
+};
+
+enum {
+	KNL_PCI_UNCORE_MC_UCLK,
+	KNL_PCI_UNCORE_MC_DCLK,
+	KNL_PCI_UNCORE_EDC_UCLK,
+	KNL_PCI_UNCORE_EDC_ECLK,
+	KNL_PCI_UNCORE_M2PCIE,
+	KNL_PCI_UNCORE_IRP,
+};
+
+static struct intel_uncore_type *knl_pci_uncores[] = {
+	[KNL_PCI_UNCORE_MC_UCLK]	= &knl_uncore_imc_uclk,
+	[KNL_PCI_UNCORE_MC_DCLK]	= &knl_uncore_imc_dclk,
+	[KNL_PCI_UNCORE_EDC_UCLK]	= &knl_uncore_edc_uclk,
+	[KNL_PCI_UNCORE_EDC_ECLK]	= &knl_uncore_edc_eclk,
+	[KNL_PCI_UNCORE_M2PCIE]		= &knl_uncore_m2pcie,
+	[KNL_PCI_UNCORE_IRP]		= &knl_uncore_irp,
+	NULL,
+};
+
+/*
+ * KNL uses a common PCI device ID for multiple instances of an Uncore PMU
+ * device type. prior to KNL, each instance of a PMU device type had a unique
+ * device ID.
+ *
+ *	PCI Device ID	Uncore PMU Devices
+ *	----------------------------------
+ *	0x7841		MC0 UClk, MC1 UClk
+ *	0x7843		MC0 DClk CH 0, MC0 DClk CH 1, MC0 DClk CH 2,
+ *			MC1 DClk CH 0, MC1 DClk CH 1, MC1 DClk CH 2
+ *	0x7833		EDC0 UClk, EDC1 UClk, EDC2 UClk, EDC3 UClk,
+ *			EDC4 UClk, EDC5 UClk, EDC6 UClk, EDC7 UClk
+ *	0x7835		EDC0 EClk, EDC1 EClk, EDC2 EClk, EDC3 EClk,
+ *			EDC4 EClk, EDC5 EClk, EDC6 EClk, EDC7 EClk
+ *	0x7817		M2PCIe
+ *	0x7814		IRP
+*/
+
+static const struct pci_device_id knl_uncore_pci_ids[] = {
+	{ /* MC UClk */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7841),
+		.driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_MC_UCLK, 0),
+	},
+	{ /* MC DClk Channel */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7843),
+		.driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_MC_DCLK, 0),
+	},
+	{ /* EDC UClk */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7833),
+		.driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_EDC_UCLK, 0),
+	},
+	{ /* EDC EClk */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7835),
+		.driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_EDC_ECLK, 0),
+	},
+	{ /* M2PCIe */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7817),
+		.driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_M2PCIE, 0),
+	},
+	{ /* IRP */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7814),
+		.driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_IRP, 0),
+	},
+	{ /* end: all zeroes */ }
+};
+
+static struct pci_driver knl_uncore_pci_driver = {
+	.name		= "knl_uncore",
+	.id_table	= knl_uncore_pci_ids,
+};
+
+int knl_uncore_pci_init(void)
+{
+	int ret;
+
+	/* All KNL PCI based PMON units are on the same PCI bus except IRP */
+	ret = snb_pci2phy_map_init(0x7814); /* IRP */
+	if (ret)
+		return ret;
+	ret = snb_pci2phy_map_init(0x7817); /* M2PCIe */
+	if (ret)
+		return ret;
+	uncore_pci_uncores = knl_pci_uncores;
+	uncore_pci_driver = &knl_uncore_pci_driver;
+	return 0;
+}
+
+/* end of KNL uncore support */
+
 /* Haswell-EP uncore support */
 static struct attribute *hswep_uncore_ubox_formats_attr[] = {
 	&format_attr_event.attr,
@@ -2338,7 +2819,7 @@
 }
 /* end of Haswell-EP uncore support */
 
-/* BDX-DE uncore support */
+/* BDX uncore support */
 
 static struct intel_uncore_type bdx_uncore_ubox = {
 	.name			= "ubox",
@@ -2360,13 +2841,14 @@
 	UNCORE_EVENT_CONSTRAINT(0x09, 0x3),
 	UNCORE_EVENT_CONSTRAINT(0x11, 0x1),
 	UNCORE_EVENT_CONSTRAINT(0x36, 0x1),
+	UNCORE_EVENT_CONSTRAINT(0x3e, 0x1),
 	EVENT_CONSTRAINT_END
 };
 
 static struct intel_uncore_type bdx_uncore_cbox = {
 	.name			= "cbox",
 	.num_counters		= 4,
-	.num_boxes		= 8,
+	.num_boxes		= 24,
 	.perf_ctr_bits		= 48,
 	.event_ctl		= HSWEP_C0_MSR_PMON_CTL0,
 	.perf_ctr		= HSWEP_C0_MSR_PMON_CTR0,
@@ -2379,9 +2861,24 @@
 	.format_group		= &hswep_uncore_cbox_format_group,
 };
 
+static struct intel_uncore_type bdx_uncore_sbox = {
+	.name			= "sbox",
+	.num_counters		= 4,
+	.num_boxes		= 4,
+	.perf_ctr_bits		= 48,
+	.event_ctl		= HSWEP_S0_MSR_PMON_CTL0,
+	.perf_ctr		= HSWEP_S0_MSR_PMON_CTR0,
+	.event_mask		= HSWEP_S_MSR_PMON_RAW_EVENT_MASK,
+	.box_ctl		= HSWEP_S0_MSR_PMON_BOX_CTL,
+	.msr_offset		= HSWEP_SBOX_MSR_OFFSET,
+	.ops			= &hswep_uncore_sbox_msr_ops,
+	.format_group		= &hswep_uncore_sbox_format_group,
+};
+
 static struct intel_uncore_type *bdx_msr_uncores[] = {
 	&bdx_uncore_ubox,
 	&bdx_uncore_cbox,
+	&bdx_uncore_sbox,
 	&hswep_uncore_pcu,
 	NULL,
 };
@@ -2396,7 +2893,7 @@
 static struct intel_uncore_type bdx_uncore_ha = {
 	.name		= "ha",
 	.num_counters   = 4,
-	.num_boxes	= 1,
+	.num_boxes	= 2,
 	.perf_ctr_bits	= 48,
 	SNBEP_UNCORE_PCI_COMMON_INIT(),
 };
@@ -2404,7 +2901,7 @@
 static struct intel_uncore_type bdx_uncore_imc = {
 	.name		= "imc",
 	.num_counters   = 5,
-	.num_boxes	= 2,
+	.num_boxes	= 8,
 	.perf_ctr_bits	= 48,
 	.fixed_ctr_bits	= 48,
 	.fixed_ctr	= SNBEP_MC_CHy_PCI_PMON_FIXED_CTR,
@@ -2424,6 +2921,19 @@
 	.format_group		= &snbep_uncore_format_group,
 };
 
+static struct intel_uncore_type bdx_uncore_qpi = {
+	.name			= "qpi",
+	.num_counters		= 4,
+	.num_boxes		= 3,
+	.perf_ctr_bits		= 48,
+	.perf_ctr		= SNBEP_PCI_PMON_CTR0,
+	.event_ctl		= SNBEP_PCI_PMON_CTL0,
+	.event_mask		= SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK,
+	.box_ctl		= SNBEP_PCI_PMON_BOX_CTL,
+	.num_shared_regs	= 1,
+	.ops			= &snbep_uncore_qpi_ops,
+	.format_group		= &snbep_uncore_qpi_format_group,
+};
 
 static struct event_constraint bdx_uncore_r2pcie_constraints[] = {
 	UNCORE_EVENT_CONSTRAINT(0x10, 0x3),
@@ -2432,6 +2942,8 @@
 	UNCORE_EVENT_CONSTRAINT(0x23, 0x1),
 	UNCORE_EVENT_CONSTRAINT(0x25, 0x1),
 	UNCORE_EVENT_CONSTRAINT(0x26, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x28, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x2c, 0x3),
 	UNCORE_EVENT_CONSTRAINT(0x2d, 0x3),
 	EVENT_CONSTRAINT_END
 };
@@ -2445,18 +2957,65 @@
 	SNBEP_UNCORE_PCI_COMMON_INIT(),
 };
 
+static struct event_constraint bdx_uncore_r3qpi_constraints[] = {
+	UNCORE_EVENT_CONSTRAINT(0x01, 0x7),
+	UNCORE_EVENT_CONSTRAINT(0x07, 0x7),
+	UNCORE_EVENT_CONSTRAINT(0x08, 0x7),
+	UNCORE_EVENT_CONSTRAINT(0x09, 0x7),
+	UNCORE_EVENT_CONSTRAINT(0x0a, 0x7),
+	UNCORE_EVENT_CONSTRAINT(0x0e, 0x7),
+	UNCORE_EVENT_CONSTRAINT(0x10, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x11, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x13, 0x1),
+	UNCORE_EVENT_CONSTRAINT(0x14, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x15, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x1f, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x20, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x21, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x22, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x23, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x25, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x26, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x28, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x29, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x2c, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x2d, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x2e, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x2f, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x33, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x34, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x36, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x37, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x38, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x39, 0x3),
+	EVENT_CONSTRAINT_END
+};
+
+static struct intel_uncore_type bdx_uncore_r3qpi = {
+	.name		= "r3qpi",
+	.num_counters   = 3,
+	.num_boxes	= 3,
+	.perf_ctr_bits	= 48,
+	.constraints	= bdx_uncore_r3qpi_constraints,
+	SNBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
 enum {
 	BDX_PCI_UNCORE_HA,
 	BDX_PCI_UNCORE_IMC,
 	BDX_PCI_UNCORE_IRP,
+	BDX_PCI_UNCORE_QPI,
 	BDX_PCI_UNCORE_R2PCIE,
+	BDX_PCI_UNCORE_R3QPI,
 };
 
 static struct intel_uncore_type *bdx_pci_uncores[] = {
 	[BDX_PCI_UNCORE_HA]	= &bdx_uncore_ha,
 	[BDX_PCI_UNCORE_IMC]	= &bdx_uncore_imc,
 	[BDX_PCI_UNCORE_IRP]	= &bdx_uncore_irp,
+	[BDX_PCI_UNCORE_QPI]	= &bdx_uncore_qpi,
 	[BDX_PCI_UNCORE_R2PCIE]	= &bdx_uncore_r2pcie,
+	[BDX_PCI_UNCORE_R3QPI]	= &bdx_uncore_r3qpi,
 	NULL,
 };
 
@@ -2465,6 +3024,10 @@
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f30),
 		.driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_HA, 0),
 	},
+	{ /* Home Agent 1 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f38),
+		.driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_HA, 1),
+	},
 	{ /* MC0 Channel 0 */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fb0),
 		.driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 0),
@@ -2473,14 +3036,74 @@
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fb1),
 		.driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 1),
 	},
+	{ /* MC0 Channel 2 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fb4),
+		.driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 2),
+	},
+	{ /* MC0 Channel 3 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fb5),
+		.driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 3),
+	},
+	{ /* MC1 Channel 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fd0),
+		.driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 4),
+	},
+	{ /* MC1 Channel 1 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fd1),
+		.driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 5),
+	},
+	{ /* MC1 Channel 2 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fd4),
+		.driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 6),
+	},
+	{ /* MC1 Channel 3 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fd5),
+		.driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 7),
+	},
 	{ /* IRP */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f39),
 		.driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IRP, 0),
 	},
+	{ /* QPI0 Port 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f32),
+		.driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_QPI, 0),
+	},
+	{ /* QPI0 Port 1 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f33),
+		.driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_QPI, 1),
+	},
+	{ /* QPI1 Port 2 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f3a),
+		.driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_QPI, 2),
+	},
 	{ /* R2PCIe */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f34),
 		.driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_R2PCIE, 0),
 	},
+	{ /* R3QPI0 Link 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f36),
+		.driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_R3QPI, 0),
+	},
+	{ /* R3QPI0 Link 1 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f37),
+		.driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_R3QPI, 1),
+	},
+	{ /* R3QPI1 Link 2 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f3e),
+		.driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_R3QPI, 2),
+	},
+	{ /* QPI Port 0 filter  */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f86),
+		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 0),
+	},
+	{ /* QPI Port 1 filter  */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f96),
+		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 1),
+	},
+	{ /* QPI Port 2 filter  */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f46),
+		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 2),
+	},
 	{ /* end: all zeroes */ }
 };
 
@@ -2500,4 +3123,4 @@
 	return 0;
 }
 
-/* end of BDX-DE uncore support */
+/* end of BDX uncore support */
diff --git a/arch/x86/kernel/cpu/rdrand.c b/arch/x86/kernel/cpu/rdrand.c
index 136ac74..819d949 100644
--- a/arch/x86/kernel/cpu/rdrand.c
+++ b/arch/x86/kernel/cpu/rdrand.c
@@ -33,28 +33,27 @@
 __setup("nordrand", x86_rdrand_setup);
 
 /*
- * Force a reseed cycle; we are architecturally guaranteed a reseed
- * after no more than 512 128-bit chunks of random data.  This also
- * acts as a test of the CPU capability.
+ * RDRAND has Built-In-Self-Test (BIST) that runs on every invocation.
+ * Run the instruction a few times as a sanity check.
+ * If it fails, it is simple to disable RDRAND here.
  */
-#define RESEED_LOOP ((512*128)/sizeof(unsigned long))
+#define SANITY_CHECK_LOOPS 8
 
 void x86_init_rdrand(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_ARCH_RANDOM
 	unsigned long tmp;
-	int i, count, ok;
+	int i;
 
 	if (!cpu_has(c, X86_FEATURE_RDRAND))
-		return;		/* Nothing to do */
+		return;
 
-	for (count = i = 0; i < RESEED_LOOP; i++) {
-		ok = rdrand_long(&tmp);
-		if (ok)
-			count++;
+	for (i = 0; i < SANITY_CHECK_LOOPS; i++) {
+		if (!rdrand_long(&tmp)) {
+			clear_cpu_cap(c, X86_FEATURE_RDRAND);
+			printk_once(KERN_WARNING "rdrand: disabled\n");
+			return;
+		}
 	}
-
-	if (count != RESEED_LOOP)
-		clear_cpu_cap(c, X86_FEATURE_RDRAND);
 #endif
 }
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 608fb26..8cb57df 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -31,32 +31,12 @@
 	const struct cpuid_bit *cb;
 
 	static const struct cpuid_bit cpuid_bits[] = {
-		{ X86_FEATURE_DTHERM,		CR_EAX, 0, 0x00000006, 0 },
-		{ X86_FEATURE_IDA,		CR_EAX, 1, 0x00000006, 0 },
-		{ X86_FEATURE_ARAT,		CR_EAX, 2, 0x00000006, 0 },
-		{ X86_FEATURE_PLN,		CR_EAX, 4, 0x00000006, 0 },
-		{ X86_FEATURE_PTS,		CR_EAX, 6, 0x00000006, 0 },
-		{ X86_FEATURE_HWP,		CR_EAX, 7, 0x00000006, 0 },
-		{ X86_FEATURE_HWP_NOTIFY,	CR_EAX, 8, 0x00000006, 0 },
-		{ X86_FEATURE_HWP_ACT_WINDOW,	CR_EAX, 9, 0x00000006, 0 },
-		{ X86_FEATURE_HWP_EPP,		CR_EAX,10, 0x00000006, 0 },
-		{ X86_FEATURE_HWP_PKG_REQ,	CR_EAX,11, 0x00000006, 0 },
 		{ X86_FEATURE_INTEL_PT,		CR_EBX,25, 0x00000007, 0 },
 		{ X86_FEATURE_APERFMPERF,	CR_ECX, 0, 0x00000006, 0 },
 		{ X86_FEATURE_EPB,		CR_ECX, 3, 0x00000006, 0 },
 		{ X86_FEATURE_HW_PSTATE,	CR_EDX, 7, 0x80000007, 0 },
 		{ X86_FEATURE_CPB,		CR_EDX, 9, 0x80000007, 0 },
 		{ X86_FEATURE_PROC_FEEDBACK,	CR_EDX,11, 0x80000007, 0 },
-		{ X86_FEATURE_NPT,		CR_EDX, 0, 0x8000000a, 0 },
-		{ X86_FEATURE_LBRV,		CR_EDX, 1, 0x8000000a, 0 },
-		{ X86_FEATURE_SVML,		CR_EDX, 2, 0x8000000a, 0 },
-		{ X86_FEATURE_NRIPS,		CR_EDX, 3, 0x8000000a, 0 },
-		{ X86_FEATURE_TSCRATEMSR,	CR_EDX, 4, 0x8000000a, 0 },
-		{ X86_FEATURE_VMCBCLEAN,	CR_EDX, 5, 0x8000000a, 0 },
-		{ X86_FEATURE_FLUSHBYASID,	CR_EDX, 6, 0x8000000a, 0 },
-		{ X86_FEATURE_DECODEASSISTS,	CR_EDX, 7, 0x8000000a, 0 },
-		{ X86_FEATURE_PAUSEFILTER,	CR_EDX,10, 0x8000000a, 0 },
-		{ X86_FEATURE_PFTHRESHOLD,	CR_EDX,12, 0x8000000a, 0 },
 		{ 0, 0, 0, 0, 0 }
 	};
 
diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c
index 3fa0e5a..252da7a 100644
--- a/arch/x86/kernel/cpu/transmeta.c
+++ b/arch/x86/kernel/cpu/transmeta.c
@@ -12,7 +12,7 @@
 	xlvl = cpuid_eax(0x80860000);
 	if ((xlvl & 0xffff0000) == 0x80860000) {
 		if (xlvl >= 0x80860001)
-			c->x86_capability[2] = cpuid_edx(0x80860001);
+			c->x86_capability[CPUID_8086_0001_EDX] = cpuid_edx(0x80860001);
 	}
 }
 
@@ -82,7 +82,7 @@
 	/* Unhide possibly hidden capability flags */
 	rdmsr(0x80860004, cap_mask, uk);
 	wrmsr(0x80860004, ~0, uk);
-	c->x86_capability[0] = cpuid_edx(0x00000001);
+	c->x86_capability[CPUID_1_EDX] = cpuid_edx(0x00000001);
 	wrmsr(0x80860004, cap_mask, uk);
 
 	/* All Transmeta CPUs have a constant TSC */
diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c
index bd3507d..2836de39 100644
--- a/arch/x86/kernel/cpuid.c
+++ b/arch/x86/kernel/cpuid.c
@@ -58,28 +58,6 @@
 		    &cmd->eax, &cmd->ebx, &cmd->ecx, &cmd->edx);
 }
 
-static loff_t cpuid_seek(struct file *file, loff_t offset, int orig)
-{
-	loff_t ret;
-	struct inode *inode = file->f_mapping->host;
-
-	mutex_lock(&inode->i_mutex);
-	switch (orig) {
-	case 0:
-		file->f_pos = offset;
-		ret = file->f_pos;
-		break;
-	case 1:
-		file->f_pos += offset;
-		ret = file->f_pos;
-		break;
-	default:
-		ret = -EINVAL;
-	}
-	mutex_unlock(&inode->i_mutex);
-	return ret;
-}
-
 static ssize_t cpuid_read(struct file *file, char __user *buf,
 			  size_t count, loff_t *ppos)
 {
@@ -132,7 +110,7 @@
  */
 static const struct file_operations cpuid_fops = {
 	.owner = THIS_MODULE,
-	.llseek = cpuid_seek,
+	.llseek = no_seek_end_llseek,
 	.read = cpuid_read,
 	.open = cpuid_open,
 };
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 2c1910f..58f3431 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -35,6 +35,7 @@
 #include <asm/cpu.h>
 #include <asm/reboot.h>
 #include <asm/virtext.h>
+#include <asm/intel_pt.h>
 
 /* Alignment required for elf header segment */
 #define ELF_CORE_HEADER_ALIGN   4096
@@ -125,6 +126,11 @@
 	cpu_emergency_vmxoff();
 	cpu_emergency_svm_disable();
 
+	/*
+	 * Disable Intel PT to stop its logging
+	 */
+	cpu_emergency_stop_pt();
+
 	disable_local_APIC();
 }
 
@@ -169,6 +175,11 @@
 	cpu_emergency_vmxoff();
 	cpu_emergency_svm_disable();
 
+	/*
+	 * Disable Intel PT to stop its logging
+	 */
+	cpu_emergency_stop_pt();
+
 #ifdef CONFIG_X86_IO_APIC
 	/* Prevent crash_kexec() from deadlocking on ioapic_lock. */
 	ioapic_zap_locks();
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index be39b5f..7b2978a 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -12,7 +12,7 @@
  */
 static void fpu__init_cpu_ctx_switch(void)
 {
-	if (!cpu_has_eager_fpu)
+	if (!boot_cpu_has(X86_FEATURE_EAGER_FPU))
 		stts();
 	else
 		clts();
@@ -143,9 +143,18 @@
 unsigned int xstate_size;
 EXPORT_SYMBOL_GPL(xstate_size);
 
-/* Enforce that 'MEMBER' is the last field of 'TYPE': */
+/* Get alignment of the TYPE. */
+#define TYPE_ALIGN(TYPE) offsetof(struct { char x; TYPE test; }, test)
+
+/*
+ * Enforce that 'MEMBER' is the last field of 'TYPE'.
+ *
+ * Align the computed size with alignment of the TYPE,
+ * because that's how C aligns structs.
+ */
 #define CHECK_MEMBER_AT_END_OF(TYPE, MEMBER) \
-	BUILD_BUG_ON(sizeof(TYPE) != offsetofend(TYPE, MEMBER))
+	BUILD_BUG_ON(sizeof(TYPE) != ALIGN(offsetofend(TYPE, MEMBER), \
+					   TYPE_ALIGN(TYPE)))
 
 /*
  * We append the 'struct fpu' to the task_struct:
@@ -188,7 +197,7 @@
  */
 static void __init fpu__init_system_xstate_size_legacy(void)
 {
-	static int on_boot_cpu = 1;
+	static int on_boot_cpu __initdata = 1;
 
 	WARN_ON_FPU(!on_boot_cpu);
 	on_boot_cpu = 0;
@@ -278,7 +287,7 @@
  */
 static void __init fpu__init_system_ctx_switch(void)
 {
-	static bool on_boot_cpu = 1;
+	static bool on_boot_cpu __initdata = 1;
 
 	WARN_ON_FPU(!on_boot_cpu);
 	on_boot_cpu = 0;
@@ -287,7 +296,7 @@
 	current_thread_info()->status = 0;
 
 	/* Auto enable eagerfpu for xsaveopt */
-	if (cpu_has_xsaveopt && eagerfpu != DISABLE)
+	if (boot_cpu_has(X86_FEATURE_XSAVEOPT) && eagerfpu != DISABLE)
 		eagerfpu = ENABLE;
 
 	if (xfeatures_mask & XFEATURE_MASK_EAGER) {
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 70fc312..40f1002 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -297,7 +297,7 @@
  */
 static void __init setup_init_fpu_buf(void)
 {
-	static int on_boot_cpu = 1;
+	static int on_boot_cpu __initdata = 1;
 
 	WARN_ON_FPU(!on_boot_cpu);
 	on_boot_cpu = 0;
@@ -608,7 +608,7 @@
 void __init fpu__init_system_xstate(void)
 {
 	unsigned int eax, ebx, ecx, edx;
-	static int on_boot_cpu = 1;
+	static int on_boot_cpu __initdata = 1;
 	int err;
 
 	WARN_ON_FPU(!on_boot_cpu);
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index 50a3fad..2bcfb5f 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -300,6 +300,10 @@
 			return -EINVAL;
 		if (bp->attr.bp_addr & (bp->attr.bp_len - 1))
 			return -EINVAL;
+
+		if (!boot_cpu_has(X86_FEATURE_BPEXT))
+			return -EOPNOTSUPP;
+
 		/*
 		 * It's impossible to use a range breakpoint to fake out
 		 * user vs kernel detection because bp_len - 1 can't
@@ -307,8 +311,6 @@
 		 * breakpoints, then we'll have to check for kprobe-blacklisted
 		 * addresses anywhere in the range.
 		 */
-		if (!cpu_has_bpext)
-			return -EOPNOTSUPP;
 		info->mask = bp->attr.bp_len - 1;
 		info->len = X86_BREAKPOINT_LEN_1;
 	}
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 2bd81e3..72cef58 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -45,6 +45,11 @@
 static struct pvclock_vsyscall_time_info *hv_clock;
 static struct pvclock_wall_clock wall_clock;
 
+struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void)
+{
+	return hv_clock;
+}
+
 /*
  * The wallclock is the time of day when we booted. Since then, some time may
  * have elapsed since the hypervisor wrote the data. So we try to account for
@@ -305,7 +310,6 @@
 {
 #ifdef CONFIG_X86_64
 	int cpu;
-	int ret;
 	u8 flags;
 	struct pvclock_vcpu_time_info *vcpu_time;
 	unsigned int size;
@@ -325,11 +329,6 @@
 		return 1;
 	}
 
-	if ((ret = pvclock_init_vsyscall(hv_clock, size))) {
-		put_cpu();
-		return ret;
-	}
-
 	put_cpu();
 
 	kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK;
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index 113e707..64f9616 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -45,28 +45,6 @@
 
 static struct class *msr_class;
 
-static loff_t msr_seek(struct file *file, loff_t offset, int orig)
-{
-	loff_t ret;
-	struct inode *inode = file_inode(file);
-
-	mutex_lock(&inode->i_mutex);
-	switch (orig) {
-	case SEEK_SET:
-		file->f_pos = offset;
-		ret = file->f_pos;
-		break;
-	case SEEK_CUR:
-		file->f_pos += offset;
-		ret = file->f_pos;
-		break;
-	default:
-		ret = -EINVAL;
-	}
-	mutex_unlock(&inode->i_mutex);
-	return ret;
-}
-
 static ssize_t msr_read(struct file *file, char __user *buf,
 			size_t count, loff_t *ppos)
 {
@@ -194,7 +172,7 @@
  */
 static const struct file_operations msr_fops = {
 	.owner = THIS_MODULE,
-	.llseek = msr_seek,
+	.llseek = no_seek_end_llseek,
 	.read = msr_read,
 	.write = msr_write,
 	.open = msr_open,
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 697f90d..8a2cdd7 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -29,6 +29,7 @@
 #include <asm/mach_traps.h>
 #include <asm/nmi.h>
 #include <asm/x86_init.h>
+#include <asm/reboot.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/nmi.h>
@@ -231,7 +232,7 @@
 #endif
 
 	if (panic_on_unrecovered_nmi)
-		panic("NMI: Not continuing");
+		nmi_panic(regs, "NMI: Not continuing");
 
 	pr_emerg("Dazed and confused, but trying to continue\n");
 
@@ -255,8 +256,16 @@
 		 reason, smp_processor_id());
 	show_regs(regs);
 
-	if (panic_on_io_nmi)
-		panic("NMI IOCK error: Not continuing");
+	if (panic_on_io_nmi) {
+		nmi_panic(regs, "NMI IOCK error: Not continuing");
+
+		/*
+		 * If we end up here, it means we have received an NMI while
+		 * processing panic(). Simply return without delaying and
+		 * re-enabling NMIs.
+		 */
+		return;
+	}
 
 	/* Re-enable the IOCK line, wait for a few seconds */
 	reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_IOCHK;
@@ -297,7 +306,7 @@
 
 	pr_emerg("Do you have a strange power saving mode enabled?\n");
 	if (unknown_nmi_panic || panic_on_unrecovered_nmi)
-		panic("NMI: Not continuing");
+		nmi_panic(regs, "NMI: Not continuing");
 
 	pr_emerg("Dazed and confused, but trying to continue\n");
 }
@@ -348,8 +357,19 @@
 		return;
 	}
 
-	/* Non-CPU-specific NMI: NMI sources can be processed on any CPU */
-	raw_spin_lock(&nmi_reason_lock);
+	/*
+	 * Non-CPU-specific NMI: NMI sources can be processed on any CPU.
+	 *
+	 * Another CPU may be processing panic routines while holding
+	 * nmi_reason_lock. Check if the CPU issued the IPI for crash dumping,
+	 * and if so, call its callback directly.  If there is no CPU preparing
+	 * crash dump, we simply loop here.
+	 */
+	while (!raw_spin_trylock(&nmi_reason_lock)) {
+		run_crash_ipi_callback(regs);
+		cpu_relax();
+	}
+
 	reason = x86_platform.get_nmi_reason();
 
 	if (reason & NMI_REASON_MASK) {
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index c2130ae..f08ac28 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -74,16 +74,6 @@
 /* Undefined instruction for dealing with missing ops pointers. */
 static const unsigned char ud2a[] = { 0x0f, 0x0b };
 
-unsigned paravirt_patch_nop(void)
-{
-	return 0;
-}
-
-unsigned paravirt_patch_ignore(unsigned len)
-{
-	return len;
-}
-
 struct branch {
 	unsigned char opcode;
 	u32 delta;
@@ -133,7 +123,6 @@
 		.pv_time_ops = pv_time_ops,
 		.pv_cpu_ops = pv_cpu_ops,
 		.pv_irq_ops = pv_irq_ops,
-		.pv_apic_ops = pv_apic_ops,
 		.pv_mmu_ops = pv_mmu_ops,
 #ifdef CONFIG_PARAVIRT_SPINLOCKS
 		.pv_lock_ops = pv_lock_ops,
@@ -152,8 +141,7 @@
 		/* If there's no function, patch it with a ud2a (BUG) */
 		ret = paravirt_patch_insns(insnbuf, len, ud2a, ud2a+sizeof(ud2a));
 	else if (opfunc == _paravirt_nop)
-		/* If the operation is a nop, then nop the callsite */
-		ret = paravirt_patch_nop();
+		ret = 0;
 
 	/* identity functions just return their single argument */
 	else if (opfunc == _paravirt_ident_32)
@@ -162,10 +150,6 @@
 		ret = paravirt_patch_ident_64(insnbuf, len);
 
 	else if (type == PARAVIRT_PATCH(pv_cpu_ops.iret) ||
-#ifdef CONFIG_X86_32
-		 type == PARAVIRT_PATCH(pv_cpu_ops.irq_enable_sysexit) ||
-#endif
-		 type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret32) ||
 		 type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret64))
 		/* If operation requires a jmp, then jmp */
 		ret = paravirt_patch_jmp(insnbuf, opfunc, addr, len);
@@ -220,8 +204,6 @@
 
 /* These are in entry.S */
 extern void native_iret(void);
-extern void native_irq_enable_sysexit(void);
-extern void native_usergs_sysret32(void);
 extern void native_usergs_sysret64(void);
 
 static struct resource reserve_ioports = {
@@ -379,13 +361,7 @@
 
 	.load_sp0 = native_load_sp0,
 
-#if defined(CONFIG_X86_32)
-	.irq_enable_sysexit = native_irq_enable_sysexit,
-#endif
 #ifdef CONFIG_X86_64
-#ifdef CONFIG_IA32_EMULATION
-	.usergs_sysret32 = native_usergs_sysret32,
-#endif
 	.usergs_sysret64 = native_usergs_sysret64,
 #endif
 	.iret = native_iret,
@@ -403,12 +379,6 @@
 NOKPROBE_SYMBOL(native_set_debugreg);
 NOKPROBE_SYMBOL(native_load_idt);
 
-struct pv_apic_ops pv_apic_ops = {
-#ifdef CONFIG_X86_LOCAL_APIC
-	.startup_ipi_hook = paravirt_nop,
-#endif
-};
-
 #if defined(CONFIG_X86_32) && !defined(CONFIG_X86_PAE)
 /* 32-bit pagetable entries */
 #define PTE_IDENT	__PV_IS_CALLEE_SAVE(_paravirt_ident_32)
@@ -444,9 +414,6 @@
 	.set_pmd = native_set_pmd,
 	.set_pmd_at = native_set_pmd_at,
 	.pte_update = paravirt_nop,
-	.pte_update_defer = paravirt_nop,
-	.pmd_update = paravirt_nop,
-	.pmd_update_defer = paravirt_nop,
 
 	.ptep_modify_prot_start = __ptep_modify_prot_start,
 	.ptep_modify_prot_commit = __ptep_modify_prot_commit,
@@ -492,6 +459,5 @@
 EXPORT_SYMBOL_GPL(pv_time_ops);
 EXPORT_SYMBOL    (pv_cpu_ops);
 EXPORT_SYMBOL    (pv_mmu_ops);
-EXPORT_SYMBOL_GPL(pv_apic_ops);
 EXPORT_SYMBOL_GPL(pv_info);
 EXPORT_SYMBOL    (pv_irq_ops);
diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c
index c89f50a76..158dc06 100644
--- a/arch/x86/kernel/paravirt_patch_32.c
+++ b/arch/x86/kernel/paravirt_patch_32.c
@@ -5,7 +5,6 @@
 DEF_NATIVE(pv_irq_ops, restore_fl, "push %eax; popf");
 DEF_NATIVE(pv_irq_ops, save_fl, "pushf; pop %eax");
 DEF_NATIVE(pv_cpu_ops, iret, "iret");
-DEF_NATIVE(pv_cpu_ops, irq_enable_sysexit, "sti; sysexit");
 DEF_NATIVE(pv_mmu_ops, read_cr2, "mov %cr2, %eax");
 DEF_NATIVE(pv_mmu_ops, write_cr3, "mov %eax, %cr3");
 DEF_NATIVE(pv_mmu_ops, read_cr3, "mov %cr3, %eax");
@@ -46,7 +45,6 @@
 		PATCH_SITE(pv_irq_ops, restore_fl);
 		PATCH_SITE(pv_irq_ops, save_fl);
 		PATCH_SITE(pv_cpu_ops, iret);
-		PATCH_SITE(pv_cpu_ops, irq_enable_sysexit);
 		PATCH_SITE(pv_mmu_ops, read_cr2);
 		PATCH_SITE(pv_mmu_ops, read_cr3);
 		PATCH_SITE(pv_mmu_ops, write_cr3);
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index 8aa0558..e70087a 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -13,9 +13,7 @@
 DEF_NATIVE(pv_cpu_ops, clts, "clts");
 DEF_NATIVE(pv_cpu_ops, wbinvd, "wbinvd");
 
-DEF_NATIVE(pv_cpu_ops, irq_enable_sysexit, "swapgs; sti; sysexit");
 DEF_NATIVE(pv_cpu_ops, usergs_sysret64, "swapgs; sysretq");
-DEF_NATIVE(pv_cpu_ops, usergs_sysret32, "swapgs; sysretl");
 DEF_NATIVE(pv_cpu_ops, swapgs, "swapgs");
 
 DEF_NATIVE(, mov32, "mov %edi, %eax");
@@ -55,7 +53,6 @@
 		PATCH_SITE(pv_irq_ops, save_fl);
 		PATCH_SITE(pv_irq_ops, irq_enable);
 		PATCH_SITE(pv_irq_ops, irq_disable);
-		PATCH_SITE(pv_cpu_ops, usergs_sysret32);
 		PATCH_SITE(pv_cpu_ops, usergs_sysret64);
 		PATCH_SITE(pv_cpu_ops, swapgs);
 		PATCH_SITE(pv_mmu_ops, read_cr2);
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index 0497f71..833b1d3 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -180,13 +180,13 @@
 static void calgary_init_bitmap_from_tce_table(struct iommu_table *tbl);
 static void get_tce_space_from_tar(void);
 
-static struct cal_chipset_ops calgary_chip_ops = {
+static const struct cal_chipset_ops calgary_chip_ops = {
 	.handle_quirks = calgary_handle_quirks,
 	.tce_cache_blast = calgary_tce_cache_blast,
 	.dump_error_regs = calgary_dump_error_regs
 };
 
-static struct cal_chipset_ops calioc2_chip_ops = {
+static const struct cal_chipset_ops calioc2_chip_ops = {
 	.handle_quirks = calioc2_handle_quirks,
 	.tce_cache_blast = calioc2_tce_cache_blast,
 	.dump_error_regs = calioc2_dump_error_regs
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index adf0392..7c577a1 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -88,7 +88,7 @@
 {
 	/* don't initialize swiotlb if iommu=off (no_iommu=1) */
 #ifdef CONFIG_X86_64
-	if (!no_iommu && max_pfn > MAX_DMA32_PFN)
+	if (!no_iommu && max_possible_pfn > MAX_DMA32_PFN)
 		swiotlb = 1;
 #endif
 	return swiotlb;
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index e835d26..b9d99e0 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -125,7 +125,7 @@
 		if (dead_task->mm->context.ldt) {
 			pr_warn("WARNING: dead process %s still has LDT? <%p/%d>\n",
 				dead_task->comm,
-				dead_task->mm->context.ldt,
+				dead_task->mm->context.ldt->entries,
 				dead_task->mm->context.ldt->size);
 			BUG();
 		}
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 558f50e..32e9d9c 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -124,21 +124,6 @@
 	return NULL;
 }
 
-static const int arg_offs_table[] = {
-#ifdef CONFIG_X86_32
-	[0] = offsetof(struct pt_regs, ax),
-	[1] = offsetof(struct pt_regs, dx),
-	[2] = offsetof(struct pt_regs, cx)
-#else /* CONFIG_X86_64 */
-	[0] = offsetof(struct pt_regs, di),
-	[1] = offsetof(struct pt_regs, si),
-	[2] = offsetof(struct pt_regs, dx),
-	[3] = offsetof(struct pt_regs, cx),
-	[4] = offsetof(struct pt_regs, r8),
-	[5] = offsetof(struct pt_regs, r9)
-#endif
-};
-
 /*
  * does not yet catch signals sent when the child dies.
  * in exit.c or in signal.c.
diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c
index 2f355d2..99bfc02 100644
--- a/arch/x86/kernel/pvclock.c
+++ b/arch/x86/kernel/pvclock.c
@@ -140,27 +140,3 @@
 
 	set_normalized_timespec(ts, now.tv_sec, now.tv_nsec);
 }
-
-#ifdef CONFIG_X86_64
-/*
- * Initialize the generic pvclock vsyscall state.  This will allocate
- * a/some page(s) for the per-vcpu pvclock information, set up a
- * fixmap mapping for the page(s)
- */
-
-int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i,
-				 int size)
-{
-	int idx;
-
-	WARN_ON (size != PVCLOCK_VSYSCALL_NR_PAGES*PAGE_SIZE);
-
-	for (idx = 0; idx <= (PVCLOCK_FIXMAP_END-PVCLOCK_FIXMAP_BEGIN); idx++) {
-		__set_fixmap(PVCLOCK_FIXMAP_BEGIN + idx,
-			     __pa(i) + (idx*PAGE_SIZE),
-			     PAGE_KERNEL_VVAR);
-	}
-
-	return 0;
-}
-#endif
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 02693dd..d64889a 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -718,6 +718,7 @@
 static nmi_shootdown_cb shootdown_callback;
 
 static atomic_t waiting_for_crash_ipi;
+static int crash_ipi_issued;
 
 static int crash_nmi_callback(unsigned int val, struct pt_regs *regs)
 {
@@ -780,6 +781,9 @@
 
 	smp_send_nmi_allbutself();
 
+	/* Kick CPUs looping in NMI context. */
+	WRITE_ONCE(crash_ipi_issued, 1);
+
 	msecs = 1000; /* Wait at most a second for the other cpus to stop */
 	while ((atomic_read(&waiting_for_crash_ipi) > 0) && msecs) {
 		mdelay(1);
@@ -788,9 +792,35 @@
 
 	/* Leave the nmi callback set */
 }
+
+/*
+ * Check if the crash dumping IPI got issued and if so, call its callback
+ * directly. This function is used when we have already been in NMI handler.
+ * It doesn't return.
+ */
+void run_crash_ipi_callback(struct pt_regs *regs)
+{
+	if (crash_ipi_issued)
+		crash_nmi_callback(0, regs);
+}
+
+/* Override the weak function in kernel/panic.c */
+void nmi_panic_self_stop(struct pt_regs *regs)
+{
+	while (1) {
+		/* If no CPU is preparing crash dump, we simply loop here. */
+		run_crash_ipi_callback(regs);
+		cpu_relax();
+	}
+}
+
 #else /* !CONFIG_SMP */
 void nmi_shootdown_cpus(nmi_shootdown_cb callback)
 {
 	/* No other CPUs to shoot down */
 }
+
+void run_crash_ipi_callback(struct pt_regs *regs)
+{
+}
 #endif
diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c
index cd96852..4af8d06 100644
--- a/arch/x86/kernel/rtc.c
+++ b/arch/x86/kernel/rtc.c
@@ -200,6 +200,9 @@
 	}
 #endif
 
+	if (paravirt_enabled() && !paravirt_has(RTC))
+		return -ENODEV;
+
 	platform_device_register(&rtc_device);
 	dev_info(&rtc_device.dev,
 		 "registered platform RTC device (no PNP device found)\n");
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index d2bbe34..d3d80e6 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1048,6 +1048,8 @@
 	if (mtrr_trim_uncached_memory(max_pfn))
 		max_pfn = e820_end_of_ram_pfn();
 
+	max_possible_pfn = max_pfn;
+
 #ifdef CONFIG_X86_32
 	/* max_low_pfn get updated here */
 	find_low_pfn_range();
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 12c8286..658777c 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -125,12 +125,12 @@
 		WARN_ON(1);
 		return;
 	}
-	apic->send_IPI_mask(cpumask_of(cpu), RESCHEDULE_VECTOR);
+	apic->send_IPI(cpu, RESCHEDULE_VECTOR);
 }
 
 void native_send_call_func_single_ipi(int cpu)
 {
-	apic->send_IPI_mask(cpumask_of(cpu), CALL_FUNCTION_SINGLE_VECTOR);
+	apic->send_IPI(cpu, CALL_FUNCTION_SINGLE_VECTOR);
 }
 
 void native_send_call_func_ipi(const struct cpumask *mask)
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index fbabe4f..24d57f7 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -304,7 +304,7 @@
 
 static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 {
-	if (cpu_has_topoext) {
+	if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
 		int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
 
 		if (c->phys_proc_id == o->phys_proc_id &&
@@ -630,13 +630,6 @@
 		num_starts = 0;
 
 	/*
-	 * Paravirt / VMI wants a startup IPI hook here to set up the
-	 * target processor state.
-	 */
-	startup_ipi_hook(phys_apicid, (unsigned long) start_secondary,
-			 stack_start);
-
-	/*
 	 * Run STARTUP IPI loop.
 	 */
 	pr_debug("#startup loops: %d\n", num_starts);
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index c7c4d9c..3d743da 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -1185,8 +1185,6 @@
 	u64 lpj;
 	int cpu;
 
-	x86_init.timers.tsc_pre_init();
-
 	if (!cpu_has_tsc) {
 		setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
 		return;
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index 5246193..483231e 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -357,8 +357,10 @@
 	tss = &per_cpu(cpu_tss, get_cpu());
 	/* make room for real-mode segments */
 	tsk->thread.sp0 += 16;
-	if (cpu_has_sep)
+
+	if (static_cpu_has_safe(X86_FEATURE_SEP))
 		tsk->thread.sysenter_cs = 0;
+
 	load_sp0(tss, &tsk->thread);
 	put_cpu();
 
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 3839628..dad5fe9 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -68,7 +68,6 @@
 
 	.timers = {
 		.setup_percpu_clockev	= setup_boot_APIC_clock,
-		.tsc_pre_init		= x86_init_noop,
 		.timer_init		= hpet_time_init,
 		.wallclock_init		= x86_init_noop,
 	},
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index 3f5c48d..c8eda14 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -2,6 +2,7 @@
 #define ARCH_X86_KVM_CPUID_H
 
 #include "x86.h"
+#include <asm/cpu.h>
 
 int kvm_update_cpuid(struct kvm_vcpu *vcpu);
 struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
@@ -178,4 +179,37 @@
 }
 #undef BIT_NRIPS
 
+static inline int guest_cpuid_family(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 0x1, 0);
+	if (!best)
+		return -1;
+
+	return x86_family(best->eax);
+}
+
+static inline int guest_cpuid_model(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 0x1, 0);
+	if (!best)
+		return -1;
+
+	return x86_model(best->eax);
+}
+
+static inline int guest_cpuid_stepping(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 0x1, 0);
+	if (!best)
+		return -1;
+
+	return x86_stepping(best->eax);
+}
+
 #endif
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 62cf8c9..c58ba67 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -23,13 +23,665 @@
 
 #include "x86.h"
 #include "lapic.h"
+#include "ioapic.h"
 #include "hyperv.h"
 
 #include <linux/kvm_host.h>
+#include <linux/highmem.h>
+#include <asm/apicdef.h>
 #include <trace/events/kvm.h>
 
 #include "trace.h"
 
+static inline u64 synic_read_sint(struct kvm_vcpu_hv_synic *synic, int sint)
+{
+	return atomic64_read(&synic->sint[sint]);
+}
+
+static inline int synic_get_sint_vector(u64 sint_value)
+{
+	if (sint_value & HV_SYNIC_SINT_MASKED)
+		return -1;
+	return sint_value & HV_SYNIC_SINT_VECTOR_MASK;
+}
+
+static bool synic_has_vector_connected(struct kvm_vcpu_hv_synic *synic,
+				      int vector)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(synic->sint); i++) {
+		if (synic_get_sint_vector(synic_read_sint(synic, i)) == vector)
+			return true;
+	}
+	return false;
+}
+
+static bool synic_has_vector_auto_eoi(struct kvm_vcpu_hv_synic *synic,
+				     int vector)
+{
+	int i;
+	u64 sint_value;
+
+	for (i = 0; i < ARRAY_SIZE(synic->sint); i++) {
+		sint_value = synic_read_sint(synic, i);
+		if (synic_get_sint_vector(sint_value) == vector &&
+		    sint_value & HV_SYNIC_SINT_AUTO_EOI)
+			return true;
+	}
+	return false;
+}
+
+static int synic_set_sint(struct kvm_vcpu_hv_synic *synic, int sint,
+			  u64 data, bool host)
+{
+	int vector;
+
+	vector = data & HV_SYNIC_SINT_VECTOR_MASK;
+	if (vector < 16 && !host)
+		return 1;
+	/*
+	 * Guest may configure multiple SINTs to use the same vector, so
+	 * we maintain a bitmap of vectors handled by synic, and a
+	 * bitmap of vectors with auto-eoi behavior.  The bitmaps are
+	 * updated here, and atomically queried on fast paths.
+	 */
+
+	atomic64_set(&synic->sint[sint], data);
+
+	if (synic_has_vector_connected(synic, vector))
+		__set_bit(vector, synic->vec_bitmap);
+	else
+		__clear_bit(vector, synic->vec_bitmap);
+
+	if (synic_has_vector_auto_eoi(synic, vector))
+		__set_bit(vector, synic->auto_eoi_bitmap);
+	else
+		__clear_bit(vector, synic->auto_eoi_bitmap);
+
+	/* Load SynIC vectors into EOI exit bitmap */
+	kvm_make_request(KVM_REQ_SCAN_IOAPIC, synic_to_vcpu(synic));
+	return 0;
+}
+
+static struct kvm_vcpu_hv_synic *synic_get(struct kvm *kvm, u32 vcpu_id)
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_vcpu_hv_synic *synic;
+
+	if (vcpu_id >= atomic_read(&kvm->online_vcpus))
+		return NULL;
+	vcpu = kvm_get_vcpu(kvm, vcpu_id);
+	if (!vcpu)
+		return NULL;
+	synic = vcpu_to_synic(vcpu);
+	return (synic->active) ? synic : NULL;
+}
+
+static void synic_clear_sint_msg_pending(struct kvm_vcpu_hv_synic *synic,
+					u32 sint)
+{
+	struct kvm_vcpu *vcpu = synic_to_vcpu(synic);
+	struct page *page;
+	gpa_t gpa;
+	struct hv_message *msg;
+	struct hv_message_page *msg_page;
+
+	gpa = synic->msg_page & PAGE_MASK;
+	page = kvm_vcpu_gfn_to_page(vcpu, gpa >> PAGE_SHIFT);
+	if (is_error_page(page)) {
+		vcpu_err(vcpu, "Hyper-V SynIC can't get msg page, gpa 0x%llx\n",
+			 gpa);
+		return;
+	}
+	msg_page = kmap_atomic(page);
+
+	msg = &msg_page->sint_message[sint];
+	msg->header.message_flags.msg_pending = 0;
+
+	kunmap_atomic(msg_page);
+	kvm_release_page_dirty(page);
+	kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT);
+}
+
+static void kvm_hv_notify_acked_sint(struct kvm_vcpu *vcpu, u32 sint)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_vcpu_hv_synic *synic = vcpu_to_synic(vcpu);
+	struct kvm_vcpu_hv *hv_vcpu = vcpu_to_hv_vcpu(vcpu);
+	struct kvm_vcpu_hv_stimer *stimer;
+	int gsi, idx, stimers_pending;
+
+	trace_kvm_hv_notify_acked_sint(vcpu->vcpu_id, sint);
+
+	if (synic->msg_page & HV_SYNIC_SIMP_ENABLE)
+		synic_clear_sint_msg_pending(synic, sint);
+
+	/* Try to deliver pending Hyper-V SynIC timers messages */
+	stimers_pending = 0;
+	for (idx = 0; idx < ARRAY_SIZE(hv_vcpu->stimer); idx++) {
+		stimer = &hv_vcpu->stimer[idx];
+		if (stimer->msg_pending &&
+		    (stimer->config & HV_STIMER_ENABLE) &&
+		    HV_STIMER_SINT(stimer->config) == sint) {
+			set_bit(stimer->index,
+				hv_vcpu->stimer_pending_bitmap);
+			stimers_pending++;
+		}
+	}
+	if (stimers_pending)
+		kvm_make_request(KVM_REQ_HV_STIMER, vcpu);
+
+	idx = srcu_read_lock(&kvm->irq_srcu);
+	gsi = atomic_read(&synic->sint_to_gsi[sint]);
+	if (gsi != -1)
+		kvm_notify_acked_gsi(kvm, gsi);
+	srcu_read_unlock(&kvm->irq_srcu, idx);
+}
+
+static void synic_exit(struct kvm_vcpu_hv_synic *synic, u32 msr)
+{
+	struct kvm_vcpu *vcpu = synic_to_vcpu(synic);
+	struct kvm_vcpu_hv *hv_vcpu = &vcpu->arch.hyperv;
+
+	hv_vcpu->exit.type = KVM_EXIT_HYPERV_SYNIC;
+	hv_vcpu->exit.u.synic.msr = msr;
+	hv_vcpu->exit.u.synic.control = synic->control;
+	hv_vcpu->exit.u.synic.evt_page = synic->evt_page;
+	hv_vcpu->exit.u.synic.msg_page = synic->msg_page;
+
+	kvm_make_request(KVM_REQ_HV_EXIT, vcpu);
+}
+
+static int synic_set_msr(struct kvm_vcpu_hv_synic *synic,
+			 u32 msr, u64 data, bool host)
+{
+	struct kvm_vcpu *vcpu = synic_to_vcpu(synic);
+	int ret;
+
+	if (!synic->active)
+		return 1;
+
+	trace_kvm_hv_synic_set_msr(vcpu->vcpu_id, msr, data, host);
+
+	ret = 0;
+	switch (msr) {
+	case HV_X64_MSR_SCONTROL:
+		synic->control = data;
+		if (!host)
+			synic_exit(synic, msr);
+		break;
+	case HV_X64_MSR_SVERSION:
+		if (!host) {
+			ret = 1;
+			break;
+		}
+		synic->version = data;
+		break;
+	case HV_X64_MSR_SIEFP:
+		if (data & HV_SYNIC_SIEFP_ENABLE)
+			if (kvm_clear_guest(vcpu->kvm,
+					    data & PAGE_MASK, PAGE_SIZE)) {
+				ret = 1;
+				break;
+			}
+		synic->evt_page = data;
+		if (!host)
+			synic_exit(synic, msr);
+		break;
+	case HV_X64_MSR_SIMP:
+		if (data & HV_SYNIC_SIMP_ENABLE)
+			if (kvm_clear_guest(vcpu->kvm,
+					    data & PAGE_MASK, PAGE_SIZE)) {
+				ret = 1;
+				break;
+			}
+		synic->msg_page = data;
+		if (!host)
+			synic_exit(synic, msr);
+		break;
+	case HV_X64_MSR_EOM: {
+		int i;
+
+		for (i = 0; i < ARRAY_SIZE(synic->sint); i++)
+			kvm_hv_notify_acked_sint(vcpu, i);
+		break;
+	}
+	case HV_X64_MSR_SINT0 ... HV_X64_MSR_SINT15:
+		ret = synic_set_sint(synic, msr - HV_X64_MSR_SINT0, data, host);
+		break;
+	default:
+		ret = 1;
+		break;
+	}
+	return ret;
+}
+
+static int synic_get_msr(struct kvm_vcpu_hv_synic *synic, u32 msr, u64 *pdata)
+{
+	int ret;
+
+	if (!synic->active)
+		return 1;
+
+	ret = 0;
+	switch (msr) {
+	case HV_X64_MSR_SCONTROL:
+		*pdata = synic->control;
+		break;
+	case HV_X64_MSR_SVERSION:
+		*pdata = synic->version;
+		break;
+	case HV_X64_MSR_SIEFP:
+		*pdata = synic->evt_page;
+		break;
+	case HV_X64_MSR_SIMP:
+		*pdata = synic->msg_page;
+		break;
+	case HV_X64_MSR_EOM:
+		*pdata = 0;
+		break;
+	case HV_X64_MSR_SINT0 ... HV_X64_MSR_SINT15:
+		*pdata = atomic64_read(&synic->sint[msr - HV_X64_MSR_SINT0]);
+		break;
+	default:
+		ret = 1;
+		break;
+	}
+	return ret;
+}
+
+int synic_set_irq(struct kvm_vcpu_hv_synic *synic, u32 sint)
+{
+	struct kvm_vcpu *vcpu = synic_to_vcpu(synic);
+	struct kvm_lapic_irq irq;
+	int ret, vector;
+
+	if (sint >= ARRAY_SIZE(synic->sint))
+		return -EINVAL;
+
+	vector = synic_get_sint_vector(synic_read_sint(synic, sint));
+	if (vector < 0)
+		return -ENOENT;
+
+	memset(&irq, 0, sizeof(irq));
+	irq.dest_id = kvm_apic_id(vcpu->arch.apic);
+	irq.dest_mode = APIC_DEST_PHYSICAL;
+	irq.delivery_mode = APIC_DM_FIXED;
+	irq.vector = vector;
+	irq.level = 1;
+
+	ret = kvm_irq_delivery_to_apic(vcpu->kvm, NULL, &irq, NULL);
+	trace_kvm_hv_synic_set_irq(vcpu->vcpu_id, sint, irq.vector, ret);
+	return ret;
+}
+
+int kvm_hv_synic_set_irq(struct kvm *kvm, u32 vcpu_id, u32 sint)
+{
+	struct kvm_vcpu_hv_synic *synic;
+
+	synic = synic_get(kvm, vcpu_id);
+	if (!synic)
+		return -EINVAL;
+
+	return synic_set_irq(synic, sint);
+}
+
+void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector)
+{
+	struct kvm_vcpu_hv_synic *synic = vcpu_to_synic(vcpu);
+	int i;
+
+	trace_kvm_hv_synic_send_eoi(vcpu->vcpu_id, vector);
+
+	for (i = 0; i < ARRAY_SIZE(synic->sint); i++)
+		if (synic_get_sint_vector(synic_read_sint(synic, i)) == vector)
+			kvm_hv_notify_acked_sint(vcpu, i);
+}
+
+static int kvm_hv_set_sint_gsi(struct kvm *kvm, u32 vcpu_id, u32 sint, int gsi)
+{
+	struct kvm_vcpu_hv_synic *synic;
+
+	synic = synic_get(kvm, vcpu_id);
+	if (!synic)
+		return -EINVAL;
+
+	if (sint >= ARRAY_SIZE(synic->sint_to_gsi))
+		return -EINVAL;
+
+	atomic_set(&synic->sint_to_gsi[sint], gsi);
+	return 0;
+}
+
+void kvm_hv_irq_routing_update(struct kvm *kvm)
+{
+	struct kvm_irq_routing_table *irq_rt;
+	struct kvm_kernel_irq_routing_entry *e;
+	u32 gsi;
+
+	irq_rt = srcu_dereference_check(kvm->irq_routing, &kvm->irq_srcu,
+					lockdep_is_held(&kvm->irq_lock));
+
+	for (gsi = 0; gsi < irq_rt->nr_rt_entries; gsi++) {
+		hlist_for_each_entry(e, &irq_rt->map[gsi], link) {
+			if (e->type == KVM_IRQ_ROUTING_HV_SINT)
+				kvm_hv_set_sint_gsi(kvm, e->hv_sint.vcpu,
+						    e->hv_sint.sint, gsi);
+		}
+	}
+}
+
+static void synic_init(struct kvm_vcpu_hv_synic *synic)
+{
+	int i;
+
+	memset(synic, 0, sizeof(*synic));
+	synic->version = HV_SYNIC_VERSION_1;
+	for (i = 0; i < ARRAY_SIZE(synic->sint); i++) {
+		atomic64_set(&synic->sint[i], HV_SYNIC_SINT_MASKED);
+		atomic_set(&synic->sint_to_gsi[i], -1);
+	}
+}
+
+static u64 get_time_ref_counter(struct kvm *kvm)
+{
+	return div_u64(get_kernel_ns() + kvm->arch.kvmclock_offset, 100);
+}
+
+static void stimer_mark_pending(struct kvm_vcpu_hv_stimer *stimer,
+				bool vcpu_kick)
+{
+	struct kvm_vcpu *vcpu = stimer_to_vcpu(stimer);
+
+	set_bit(stimer->index,
+		vcpu_to_hv_vcpu(vcpu)->stimer_pending_bitmap);
+	kvm_make_request(KVM_REQ_HV_STIMER, vcpu);
+	if (vcpu_kick)
+		kvm_vcpu_kick(vcpu);
+}
+
+static void stimer_cleanup(struct kvm_vcpu_hv_stimer *stimer)
+{
+	struct kvm_vcpu *vcpu = stimer_to_vcpu(stimer);
+
+	trace_kvm_hv_stimer_cleanup(stimer_to_vcpu(stimer)->vcpu_id,
+				    stimer->index);
+
+	hrtimer_cancel(&stimer->timer);
+	clear_bit(stimer->index,
+		  vcpu_to_hv_vcpu(vcpu)->stimer_pending_bitmap);
+	stimer->msg_pending = false;
+	stimer->exp_time = 0;
+}
+
+static enum hrtimer_restart stimer_timer_callback(struct hrtimer *timer)
+{
+	struct kvm_vcpu_hv_stimer *stimer;
+
+	stimer = container_of(timer, struct kvm_vcpu_hv_stimer, timer);
+	trace_kvm_hv_stimer_callback(stimer_to_vcpu(stimer)->vcpu_id,
+				     stimer->index);
+	stimer_mark_pending(stimer, true);
+
+	return HRTIMER_NORESTART;
+}
+
+/*
+ * stimer_start() assumptions:
+ * a) stimer->count is not equal to 0
+ * b) stimer->config has HV_STIMER_ENABLE flag
+ */
+static int stimer_start(struct kvm_vcpu_hv_stimer *stimer)
+{
+	u64 time_now;
+	ktime_t ktime_now;
+
+	time_now = get_time_ref_counter(stimer_to_vcpu(stimer)->kvm);
+	ktime_now = ktime_get();
+
+	if (stimer->config & HV_STIMER_PERIODIC) {
+		if (stimer->exp_time) {
+			if (time_now >= stimer->exp_time) {
+				u64 remainder;
+
+				div64_u64_rem(time_now - stimer->exp_time,
+					      stimer->count, &remainder);
+				stimer->exp_time =
+					time_now + (stimer->count - remainder);
+			}
+		} else
+			stimer->exp_time = time_now + stimer->count;
+
+		trace_kvm_hv_stimer_start_periodic(
+					stimer_to_vcpu(stimer)->vcpu_id,
+					stimer->index,
+					time_now, stimer->exp_time);
+
+		hrtimer_start(&stimer->timer,
+			      ktime_add_ns(ktime_now,
+					   100 * (stimer->exp_time - time_now)),
+			      HRTIMER_MODE_ABS);
+		return 0;
+	}
+	stimer->exp_time = stimer->count;
+	if (time_now >= stimer->count) {
+		/*
+		 * Expire timer according to Hypervisor Top-Level Functional
+		 * specification v4(15.3.1):
+		 * "If a one shot is enabled and the specified count is in
+		 * the past, it will expire immediately."
+		 */
+		stimer_mark_pending(stimer, false);
+		return 0;
+	}
+
+	trace_kvm_hv_stimer_start_one_shot(stimer_to_vcpu(stimer)->vcpu_id,
+					   stimer->index,
+					   time_now, stimer->count);
+
+	hrtimer_start(&stimer->timer,
+		      ktime_add_ns(ktime_now, 100 * (stimer->count - time_now)),
+		      HRTIMER_MODE_ABS);
+	return 0;
+}
+
+static int stimer_set_config(struct kvm_vcpu_hv_stimer *stimer, u64 config,
+			     bool host)
+{
+	trace_kvm_hv_stimer_set_config(stimer_to_vcpu(stimer)->vcpu_id,
+				       stimer->index, config, host);
+
+	stimer_cleanup(stimer);
+	if ((stimer->config & HV_STIMER_ENABLE) && HV_STIMER_SINT(config) == 0)
+		config &= ~HV_STIMER_ENABLE;
+	stimer->config = config;
+	stimer_mark_pending(stimer, false);
+	return 0;
+}
+
+static int stimer_set_count(struct kvm_vcpu_hv_stimer *stimer, u64 count,
+			    bool host)
+{
+	trace_kvm_hv_stimer_set_count(stimer_to_vcpu(stimer)->vcpu_id,
+				      stimer->index, count, host);
+
+	stimer_cleanup(stimer);
+	stimer->count = count;
+	if (stimer->count == 0)
+		stimer->config &= ~HV_STIMER_ENABLE;
+	else if (stimer->config & HV_STIMER_AUTOENABLE)
+		stimer->config |= HV_STIMER_ENABLE;
+	stimer_mark_pending(stimer, false);
+	return 0;
+}
+
+static int stimer_get_config(struct kvm_vcpu_hv_stimer *stimer, u64 *pconfig)
+{
+	*pconfig = stimer->config;
+	return 0;
+}
+
+static int stimer_get_count(struct kvm_vcpu_hv_stimer *stimer, u64 *pcount)
+{
+	*pcount = stimer->count;
+	return 0;
+}
+
+static int synic_deliver_msg(struct kvm_vcpu_hv_synic *synic, u32 sint,
+			     struct hv_message *src_msg)
+{
+	struct kvm_vcpu *vcpu = synic_to_vcpu(synic);
+	struct page *page;
+	gpa_t gpa;
+	struct hv_message *dst_msg;
+	int r;
+	struct hv_message_page *msg_page;
+
+	if (!(synic->msg_page & HV_SYNIC_SIMP_ENABLE))
+		return -ENOENT;
+
+	gpa = synic->msg_page & PAGE_MASK;
+	page = kvm_vcpu_gfn_to_page(vcpu, gpa >> PAGE_SHIFT);
+	if (is_error_page(page))
+		return -EFAULT;
+
+	msg_page = kmap_atomic(page);
+	dst_msg = &msg_page->sint_message[sint];
+	if (sync_cmpxchg(&dst_msg->header.message_type, HVMSG_NONE,
+			 src_msg->header.message_type) != HVMSG_NONE) {
+		dst_msg->header.message_flags.msg_pending = 1;
+		r = -EAGAIN;
+	} else {
+		memcpy(&dst_msg->u.payload, &src_msg->u.payload,
+		       src_msg->header.payload_size);
+		dst_msg->header.message_type = src_msg->header.message_type;
+		dst_msg->header.payload_size = src_msg->header.payload_size;
+		r = synic_set_irq(synic, sint);
+		if (r >= 1)
+			r = 0;
+		else if (r == 0)
+			r = -EFAULT;
+	}
+	kunmap_atomic(msg_page);
+	kvm_release_page_dirty(page);
+	kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT);
+	return r;
+}
+
+static int stimer_send_msg(struct kvm_vcpu_hv_stimer *stimer)
+{
+	struct kvm_vcpu *vcpu = stimer_to_vcpu(stimer);
+	struct hv_message *msg = &stimer->msg;
+	struct hv_timer_message_payload *payload =
+			(struct hv_timer_message_payload *)&msg->u.payload;
+
+	payload->expiration_time = stimer->exp_time;
+	payload->delivery_time = get_time_ref_counter(vcpu->kvm);
+	return synic_deliver_msg(vcpu_to_synic(vcpu),
+				 HV_STIMER_SINT(stimer->config), msg);
+}
+
+static void stimer_expiration(struct kvm_vcpu_hv_stimer *stimer)
+{
+	int r;
+
+	stimer->msg_pending = true;
+	r = stimer_send_msg(stimer);
+	trace_kvm_hv_stimer_expiration(stimer_to_vcpu(stimer)->vcpu_id,
+				       stimer->index, r);
+	if (!r) {
+		stimer->msg_pending = false;
+		if (!(stimer->config & HV_STIMER_PERIODIC))
+			stimer->config &= ~HV_STIMER_ENABLE;
+	}
+}
+
+void kvm_hv_process_stimers(struct kvm_vcpu *vcpu)
+{
+	struct kvm_vcpu_hv *hv_vcpu = vcpu_to_hv_vcpu(vcpu);
+	struct kvm_vcpu_hv_stimer *stimer;
+	u64 time_now, exp_time;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(hv_vcpu->stimer); i++)
+		if (test_and_clear_bit(i, hv_vcpu->stimer_pending_bitmap)) {
+			stimer = &hv_vcpu->stimer[i];
+			if (stimer->config & HV_STIMER_ENABLE) {
+				exp_time = stimer->exp_time;
+
+				if (exp_time) {
+					time_now =
+						get_time_ref_counter(vcpu->kvm);
+					if (time_now >= exp_time)
+						stimer_expiration(stimer);
+				}
+
+				if ((stimer->config & HV_STIMER_ENABLE) &&
+				    stimer->count)
+					stimer_start(stimer);
+				else
+					stimer_cleanup(stimer);
+			}
+		}
+}
+
+void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu)
+{
+	struct kvm_vcpu_hv *hv_vcpu = vcpu_to_hv_vcpu(vcpu);
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(hv_vcpu->stimer); i++)
+		stimer_cleanup(&hv_vcpu->stimer[i]);
+}
+
+static void stimer_prepare_msg(struct kvm_vcpu_hv_stimer *stimer)
+{
+	struct hv_message *msg = &stimer->msg;
+	struct hv_timer_message_payload *payload =
+			(struct hv_timer_message_payload *)&msg->u.payload;
+
+	memset(&msg->header, 0, sizeof(msg->header));
+	msg->header.message_type = HVMSG_TIMER_EXPIRED;
+	msg->header.payload_size = sizeof(*payload);
+
+	payload->timer_index = stimer->index;
+	payload->expiration_time = 0;
+	payload->delivery_time = 0;
+}
+
+static void stimer_init(struct kvm_vcpu_hv_stimer *stimer, int timer_index)
+{
+	memset(stimer, 0, sizeof(*stimer));
+	stimer->index = timer_index;
+	hrtimer_init(&stimer->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+	stimer->timer.function = stimer_timer_callback;
+	stimer_prepare_msg(stimer);
+}
+
+void kvm_hv_vcpu_init(struct kvm_vcpu *vcpu)
+{
+	struct kvm_vcpu_hv *hv_vcpu = vcpu_to_hv_vcpu(vcpu);
+	int i;
+
+	synic_init(&hv_vcpu->synic);
+
+	bitmap_zero(hv_vcpu->stimer_pending_bitmap, HV_SYNIC_STIMER_COUNT);
+	for (i = 0; i < ARRAY_SIZE(hv_vcpu->stimer); i++)
+		stimer_init(&hv_vcpu->stimer[i], i);
+}
+
+int kvm_hv_activate_synic(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * Hyper-V SynIC auto EOI SINT's are
+	 * not compatible with APICV, so deactivate APICV
+	 */
+	kvm_vcpu_deactivate_apicv(vcpu);
+	vcpu_to_synic(vcpu)->active = true;
+	return 0;
+}
+
 static bool kvm_hv_msr_partition_wide(u32 msr)
 {
 	bool r = false;
@@ -226,6 +878,31 @@
 			return 1;
 		hv->runtime_offset = data - current_task_runtime_100ns();
 		break;
+	case HV_X64_MSR_SCONTROL:
+	case HV_X64_MSR_SVERSION:
+	case HV_X64_MSR_SIEFP:
+	case HV_X64_MSR_SIMP:
+	case HV_X64_MSR_EOM:
+	case HV_X64_MSR_SINT0 ... HV_X64_MSR_SINT15:
+		return synic_set_msr(vcpu_to_synic(vcpu), msr, data, host);
+	case HV_X64_MSR_STIMER0_CONFIG:
+	case HV_X64_MSR_STIMER1_CONFIG:
+	case HV_X64_MSR_STIMER2_CONFIG:
+	case HV_X64_MSR_STIMER3_CONFIG: {
+		int timer_index = (msr - HV_X64_MSR_STIMER0_CONFIG)/2;
+
+		return stimer_set_config(vcpu_to_stimer(vcpu, timer_index),
+					 data, host);
+	}
+	case HV_X64_MSR_STIMER0_COUNT:
+	case HV_X64_MSR_STIMER1_COUNT:
+	case HV_X64_MSR_STIMER2_COUNT:
+	case HV_X64_MSR_STIMER3_COUNT: {
+		int timer_index = (msr - HV_X64_MSR_STIMER0_COUNT)/2;
+
+		return stimer_set_count(vcpu_to_stimer(vcpu, timer_index),
+					data, host);
+	}
 	default:
 		vcpu_unimpl(vcpu, "Hyper-V uhandled wrmsr: 0x%x data 0x%llx\n",
 			    msr, data);
@@ -248,11 +925,9 @@
 	case HV_X64_MSR_HYPERCALL:
 		data = hv->hv_hypercall;
 		break;
-	case HV_X64_MSR_TIME_REF_COUNT: {
-		data =
-		     div_u64(get_kernel_ns() + kvm->arch.kvmclock_offset, 100);
+	case HV_X64_MSR_TIME_REF_COUNT:
+		data = get_time_ref_counter(kvm);
 		break;
-	}
 	case HV_X64_MSR_REFERENCE_TSC:
 		data = hv->hv_tsc_page;
 		break;
@@ -304,6 +979,31 @@
 	case HV_X64_MSR_VP_RUNTIME:
 		data = current_task_runtime_100ns() + hv->runtime_offset;
 		break;
+	case HV_X64_MSR_SCONTROL:
+	case HV_X64_MSR_SVERSION:
+	case HV_X64_MSR_SIEFP:
+	case HV_X64_MSR_SIMP:
+	case HV_X64_MSR_EOM:
+	case HV_X64_MSR_SINT0 ... HV_X64_MSR_SINT15:
+		return synic_get_msr(vcpu_to_synic(vcpu), msr, pdata);
+	case HV_X64_MSR_STIMER0_CONFIG:
+	case HV_X64_MSR_STIMER1_CONFIG:
+	case HV_X64_MSR_STIMER2_CONFIG:
+	case HV_X64_MSR_STIMER3_CONFIG: {
+		int timer_index = (msr - HV_X64_MSR_STIMER0_CONFIG)/2;
+
+		return stimer_get_config(vcpu_to_stimer(vcpu, timer_index),
+					 pdata);
+	}
+	case HV_X64_MSR_STIMER0_COUNT:
+	case HV_X64_MSR_STIMER1_COUNT:
+	case HV_X64_MSR_STIMER2_COUNT:
+	case HV_X64_MSR_STIMER3_COUNT: {
+		int timer_index = (msr - HV_X64_MSR_STIMER0_COUNT)/2;
+
+		return stimer_get_count(vcpu_to_stimer(vcpu, timer_index),
+					pdata);
+	}
 	default:
 		vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
 		return 1;
diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h
index c7bce55..60eccd4 100644
--- a/arch/x86/kvm/hyperv.h
+++ b/arch/x86/kvm/hyperv.h
@@ -24,9 +24,64 @@
 #ifndef __ARCH_X86_KVM_HYPERV_H__
 #define __ARCH_X86_KVM_HYPERV_H__
 
+static inline struct kvm_vcpu_hv *vcpu_to_hv_vcpu(struct kvm_vcpu *vcpu)
+{
+	return &vcpu->arch.hyperv;
+}
+
+static inline struct kvm_vcpu *hv_vcpu_to_vcpu(struct kvm_vcpu_hv *hv_vcpu)
+{
+	struct kvm_vcpu_arch *arch;
+
+	arch = container_of(hv_vcpu, struct kvm_vcpu_arch, hyperv);
+	return container_of(arch, struct kvm_vcpu, arch);
+}
+
+static inline struct kvm_vcpu_hv_synic *vcpu_to_synic(struct kvm_vcpu *vcpu)
+{
+	return &vcpu->arch.hyperv.synic;
+}
+
+static inline struct kvm_vcpu *synic_to_vcpu(struct kvm_vcpu_hv_synic *synic)
+{
+	return hv_vcpu_to_vcpu(container_of(synic, struct kvm_vcpu_hv, synic));
+}
+
 int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host);
 int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata);
+
 bool kvm_hv_hypercall_enabled(struct kvm *kvm);
 int kvm_hv_hypercall(struct kvm_vcpu *vcpu);
 
+void kvm_hv_irq_routing_update(struct kvm *kvm);
+int kvm_hv_synic_set_irq(struct kvm *kvm, u32 vcpu_id, u32 sint);
+void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector);
+int kvm_hv_activate_synic(struct kvm_vcpu *vcpu);
+
+void kvm_hv_vcpu_init(struct kvm_vcpu *vcpu);
+void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu);
+
+static inline struct kvm_vcpu_hv_stimer *vcpu_to_stimer(struct kvm_vcpu *vcpu,
+							int timer_index)
+{
+	return &vcpu_to_hv_vcpu(vcpu)->stimer[timer_index];
+}
+
+static inline struct kvm_vcpu *stimer_to_vcpu(struct kvm_vcpu_hv_stimer *stimer)
+{
+	struct kvm_vcpu_hv *hv_vcpu;
+
+	hv_vcpu = container_of(stimer - stimer->index, struct kvm_vcpu_hv,
+			       stimer[0]);
+	return hv_vcpu_to_vcpu(hv_vcpu);
+}
+
+static inline bool kvm_hv_has_stimer_pending(struct kvm_vcpu *vcpu)
+{
+	return !bitmap_empty(vcpu->arch.hyperv.stimer_pending_bitmap,
+			     HV_SYNIC_STIMER_COUNT);
+}
+
+void kvm_hv_process_stimers(struct kvm_vcpu *vcpu);
+
 #endif
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 08116ff..b0ea42b 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -420,6 +420,7 @@
 	u8 saved_mode;
 	if (hpet_legacy_start) {
 		/* save existing mode for later reenablement */
+		WARN_ON(channel != 0);
 		saved_mode = kvm->arch.vpit->pit_state.channels[0].mode;
 		kvm->arch.vpit->pit_state.channels[0].mode = 0xff; /* disable timer */
 		pit_load_count(kvm, channel, val);
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index 88d0a92..1facfd6 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -233,7 +233,7 @@
 }
 
 
-void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
+void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, ulong *ioapic_handled_vectors)
 {
 	struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic;
 	union kvm_ioapic_redirect_entry *e;
@@ -250,7 +250,7 @@
 			    (e->fields.trig_mode == IOAPIC_EDGE_TRIG &&
 			     kvm_apic_pending_eoi(vcpu, e->fields.vector)))
 				__set_bit(e->fields.vector,
-					(unsigned long *)eoi_exit_bitmap);
+					  ioapic_handled_vectors);
 		}
 	}
 	spin_unlock(&ioapic->lock);
diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h
index 084617d..2d16dc2 100644
--- a/arch/x86/kvm/ioapic.h
+++ b/arch/x86/kvm/ioapic.h
@@ -121,7 +121,8 @@
 		struct kvm_lapic_irq *irq, unsigned long *dest_map);
 int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state);
 int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state);
-void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
-void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
-
+void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu,
+			   ulong *ioapic_handled_vectors);
+void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu,
+			    ulong *ioapic_handled_vectors);
 #endif
diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index 097060e..3982b47 100644
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c
@@ -76,7 +76,7 @@
 	if (kvm_cpu_has_extint(v))
 		return 1;
 
-	if (kvm_vcpu_apic_vid_enabled(v))
+	if (kvm_vcpu_apicv_active(v))
 		return 0;
 
 	return kvm_apic_has_interrupt(v) != -1; /* LAPIC */
diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
index 84b96d3..8fc89ef 100644
--- a/arch/x86/kvm/irq_comm.c
+++ b/arch/x86/kvm/irq_comm.c
@@ -33,6 +33,8 @@
 
 #include "lapic.h"
 
+#include "hyperv.h"
+
 static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e,
 			   struct kvm *kvm, int irq_source_id, int level,
 			   bool line_status)
@@ -219,6 +221,16 @@
 	srcu_read_unlock(&kvm->irq_srcu, idx);
 }
 
+static int kvm_hv_set_sint(struct kvm_kernel_irq_routing_entry *e,
+		    struct kvm *kvm, int irq_source_id, int level,
+		    bool line_status)
+{
+	if (!level)
+		return -1;
+
+	return kvm_hv_synic_set_irq(kvm, e->hv_sint.vcpu, e->hv_sint.sint);
+}
+
 int kvm_set_routing_entry(struct kvm_kernel_irq_routing_entry *e,
 			  const struct kvm_irq_routing_entry *ue)
 {
@@ -257,6 +269,11 @@
 		e->msi.address_hi = ue->u.msi.address_hi;
 		e->msi.data = ue->u.msi.data;
 		break;
+	case KVM_IRQ_ROUTING_HV_SINT:
+		e->set = kvm_hv_set_sint;
+		e->hv_sint.vcpu = ue->u.hv_sint.vcpu;
+		e->hv_sint.sint = ue->u.hv_sint.sint;
+		break;
 	default:
 		goto out;
 	}
@@ -332,14 +349,15 @@
 	return kvm_set_irq_routing(kvm, empty_routing, 0, 0);
 }
 
-void kvm_arch_irq_routing_update(struct kvm *kvm)
+void kvm_arch_post_irq_routing_update(struct kvm *kvm)
 {
 	if (ioapic_in_kernel(kvm) || !irqchip_in_kernel(kvm))
 		return;
 	kvm_make_scan_ioapic_request(kvm);
 }
 
-void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
+void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu,
+			    ulong *ioapic_handled_vectors)
 {
 	struct kvm *kvm = vcpu->kvm;
 	struct kvm_kernel_irq_routing_entry *entry;
@@ -369,9 +387,26 @@
 				u32 vector = entry->msi.data & 0xff;
 
 				__set_bit(vector,
-					  (unsigned long *) eoi_exit_bitmap);
+					  ioapic_handled_vectors);
 			}
 		}
 	}
 	srcu_read_unlock(&kvm->irq_srcu, idx);
 }
+
+int kvm_arch_set_irq(struct kvm_kernel_irq_routing_entry *irq, struct kvm *kvm,
+		     int irq_source_id, int level, bool line_status)
+{
+	switch (irq->type) {
+	case KVM_IRQ_ROUTING_HV_SINT:
+		return kvm_hv_set_sint(irq, kvm, irq_source_id, level,
+				       line_status);
+	default:
+		return -EWOULDBLOCK;
+	}
+}
+
+void kvm_arch_irq_routing_update(struct kvm *kvm)
+{
+	kvm_hv_irq_routing_update(kvm);
+}
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 4d30b86..36591fa 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -41,6 +41,7 @@
 #include "trace.h"
 #include "x86.h"
 #include "cpuid.h"
+#include "hyperv.h"
 
 #ifndef CONFIG_X86_64
 #define mod_64(x, y) ((x) - (y) * div64_u64(x, y))
@@ -128,11 +129,6 @@
 	(LVT_MASK | APIC_MODE_MASK | APIC_INPUT_POLARITY | \
 	 APIC_LVT_REMOTE_IRR | APIC_LVT_LEVEL_TRIGGER)
 
-static inline int kvm_apic_id(struct kvm_lapic *apic)
-{
-	return (kvm_apic_get_reg(apic, APIC_ID) >> 24) & 0xff;
-}
-
 /* The logical map is definitely wrong if we have multiple
  * modes at the same time.  (Physical map is always right.)
  */
@@ -379,7 +375,8 @@
 	if (!apic->irr_pending)
 		return -1;
 
-	kvm_x86_ops->sync_pir_to_irr(apic->vcpu);
+	if (apic->vcpu->arch.apicv_active)
+		kvm_x86_ops->sync_pir_to_irr(apic->vcpu);
 	result = apic_search_irr(apic);
 	ASSERT(result == -1 || result >= 16);
 
@@ -392,7 +389,7 @@
 
 	vcpu = apic->vcpu;
 
-	if (unlikely(kvm_vcpu_apic_vid_enabled(vcpu))) {
+	if (unlikely(vcpu->arch.apicv_active)) {
 		/* try to update RVI */
 		apic_clear_vector(vec, apic->regs + APIC_IRR);
 		kvm_make_request(KVM_REQ_EVENT, vcpu);
@@ -418,7 +415,7 @@
 	 * because the processor can modify ISR under the hood.  Instead
 	 * just set SVI.
 	 */
-	if (unlikely(kvm_x86_ops->hwapic_isr_update))
+	if (unlikely(vcpu->arch.apicv_active))
 		kvm_x86_ops->hwapic_isr_update(vcpu->kvm, vec);
 	else {
 		++apic->isr_count;
@@ -466,7 +463,7 @@
 	 * on the other hand isr_count and highest_isr_cache are unused
 	 * and must be left alone.
 	 */
-	if (unlikely(kvm_x86_ops->hwapic_isr_update))
+	if (unlikely(vcpu->arch.apicv_active))
 		kvm_x86_ops->hwapic_isr_update(vcpu->kvm,
 					       apic_find_highest_isr(apic));
 	else {
@@ -852,7 +849,7 @@
 				apic_clear_vector(vector, apic->regs + APIC_TMR);
 		}
 
-		if (kvm_x86_ops->deliver_posted_interrupt)
+		if (vcpu->arch.apicv_active)
 			kvm_x86_ops->deliver_posted_interrupt(vcpu, vector);
 		else {
 			apic_set_irr(vector, apic);
@@ -932,7 +929,7 @@
 
 static bool kvm_ioapic_handles_vector(struct kvm_lapic *apic, int vector)
 {
-	return test_bit(vector, (ulong *)apic->vcpu->arch.eoi_exit_bitmap);
+	return test_bit(vector, apic->vcpu->arch.ioapic_handled_vectors);
 }
 
 static void kvm_ioapic_send_eoi(struct kvm_lapic *apic, int vector)
@@ -974,6 +971,9 @@
 	apic_clear_isr(vector, apic);
 	apic_update_ppr(apic);
 
+	if (test_bit(vector, vcpu_to_synic(apic->vcpu)->vec_bitmap))
+		kvm_hv_synic_send_eoi(apic->vcpu, vector);
+
 	kvm_ioapic_send_eoi(apic, vector);
 	kvm_make_request(KVM_REQ_EVENT, apic->vcpu);
 	return vector;
@@ -1225,7 +1225,7 @@
 		int vec = reg & APIC_VECTOR_MASK;
 		void *bitmap = apic->regs + APIC_ISR;
 
-		if (kvm_x86_ops->deliver_posted_interrupt)
+		if (vcpu->arch.apicv_active)
 			bitmap = apic->regs + APIC_IRR;
 
 		if (apic_test_vector(vec, bitmap))
@@ -1693,8 +1693,8 @@
 		apic_set_reg(apic, APIC_ISR + 0x10 * i, 0);
 		apic_set_reg(apic, APIC_TMR + 0x10 * i, 0);
 	}
-	apic->irr_pending = kvm_vcpu_apic_vid_enabled(vcpu);
-	apic->isr_count = kvm_x86_ops->hwapic_isr_update ? 1 : 0;
+	apic->irr_pending = vcpu->arch.apicv_active;
+	apic->isr_count = vcpu->arch.apicv_active ? 1 : 0;
 	apic->highest_isr_cache = -1;
 	update_divide_count(apic);
 	atomic_set(&apic->lapic_timer.pending, 0);
@@ -1883,6 +1883,12 @@
 	apic_set_isr(vector, apic);
 	apic_update_ppr(apic);
 	apic_clear_irr(vector, apic);
+
+	if (test_bit(vector, vcpu_to_synic(vcpu)->auto_eoi_bitmap)) {
+		apic_clear_isr(vector, apic);
+		apic_update_ppr(apic);
+	}
+
 	return vector;
 }
 
@@ -1906,15 +1912,15 @@
 	update_divide_count(apic);
 	start_apic_timer(apic);
 	apic->irr_pending = true;
-	apic->isr_count = kvm_x86_ops->hwapic_isr_update ?
+	apic->isr_count = vcpu->arch.apicv_active ?
 				1 : count_vectors(apic->regs + APIC_ISR);
 	apic->highest_isr_cache = -1;
-	if (kvm_x86_ops->hwapic_irr_update)
+	if (vcpu->arch.apicv_active) {
 		kvm_x86_ops->hwapic_irr_update(vcpu,
 				apic_find_highest_irr(apic));
-	if (unlikely(kvm_x86_ops->hwapic_isr_update))
 		kvm_x86_ops->hwapic_isr_update(vcpu->kvm,
 				apic_find_highest_isr(apic));
+	}
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
 	if (ioapic_in_kernel(vcpu->kvm))
 		kvm_rtc_eoi_tracking_restore_one(vcpu);
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index fde8e35d..41bdb35 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -143,9 +143,9 @@
 	return apic->vcpu->arch.apic_base & X2APIC_ENABLE;
 }
 
-static inline bool kvm_vcpu_apic_vid_enabled(struct kvm_vcpu *vcpu)
+static inline bool kvm_vcpu_apicv_active(struct kvm_vcpu *vcpu)
 {
-	return kvm_x86_ops->cpu_uses_apicv(vcpu);
+	return vcpu->arch.apic && vcpu->arch.apicv_active;
 }
 
 static inline bool kvm_apic_has_events(struct kvm_vcpu *vcpu)
@@ -164,6 +164,11 @@
 	return kvm_vcpu_has_lapic(vcpu) && test_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
 }
 
+static inline int kvm_apic_id(struct kvm_lapic *apic)
+{
+	return (kvm_apic_get_reg(apic, APIC_ID) >> 24) & 0xff;
+}
+
 bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector);
 
 void wait_lapic_expire(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index e7c2c14..420a5ca 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -311,11 +311,6 @@
 	return pte & PT_PAGE_SIZE_MASK;
 }
 
-static int is_rmap_spte(u64 pte)
-{
-	return is_shadow_present_pte(pte);
-}
-
 static int is_last_spte(u64 pte, int level)
 {
 	if (level == PT_PAGE_TABLE_LEVEL)
@@ -540,7 +535,7 @@
 	u64 old_spte = *sptep;
 	bool ret = false;
 
-	WARN_ON(!is_rmap_spte(new_spte));
+	WARN_ON(!is_shadow_present_pte(new_spte));
 
 	if (!is_shadow_present_pte(old_spte)) {
 		mmu_spte_set(sptep, new_spte);
@@ -595,7 +590,7 @@
 	else
 		old_spte = __update_clear_spte_slow(sptep, 0ull);
 
-	if (!is_rmap_spte(old_spte))
+	if (!is_shadow_present_pte(old_spte))
 		return 0;
 
 	pfn = spte_to_pfn(old_spte);
@@ -909,36 +904,35 @@
 }
 
 /*
- * Pte mapping structures:
+ * About rmap_head encoding:
  *
- * If pte_list bit zero is zero, then pte_list point to the spte.
- *
- * If pte_list bit zero is one, (then pte_list & ~1) points to a struct
+ * If the bit zero of rmap_head->val is clear, then it points to the only spte
+ * in this rmap chain. Otherwise, (rmap_head->val & ~1) points to a struct
  * pte_list_desc containing more mappings.
- *
- * Returns the number of pte entries before the spte was added or zero if
- * the spte was not added.
- *
+ */
+
+/*
+ * Returns the number of pointers in the rmap chain, not counting the new one.
  */
 static int pte_list_add(struct kvm_vcpu *vcpu, u64 *spte,
-			unsigned long *pte_list)
+			struct kvm_rmap_head *rmap_head)
 {
 	struct pte_list_desc *desc;
 	int i, count = 0;
 
-	if (!*pte_list) {
+	if (!rmap_head->val) {
 		rmap_printk("pte_list_add: %p %llx 0->1\n", spte, *spte);
-		*pte_list = (unsigned long)spte;
-	} else if (!(*pte_list & 1)) {
+		rmap_head->val = (unsigned long)spte;
+	} else if (!(rmap_head->val & 1)) {
 		rmap_printk("pte_list_add: %p %llx 1->many\n", spte, *spte);
 		desc = mmu_alloc_pte_list_desc(vcpu);
-		desc->sptes[0] = (u64 *)*pte_list;
+		desc->sptes[0] = (u64 *)rmap_head->val;
 		desc->sptes[1] = spte;
-		*pte_list = (unsigned long)desc | 1;
+		rmap_head->val = (unsigned long)desc | 1;
 		++count;
 	} else {
 		rmap_printk("pte_list_add: %p %llx many->many\n", spte, *spte);
-		desc = (struct pte_list_desc *)(*pte_list & ~1ul);
+		desc = (struct pte_list_desc *)(rmap_head->val & ~1ul);
 		while (desc->sptes[PTE_LIST_EXT-1] && desc->more) {
 			desc = desc->more;
 			count += PTE_LIST_EXT;
@@ -955,8 +949,9 @@
 }
 
 static void
-pte_list_desc_remove_entry(unsigned long *pte_list, struct pte_list_desc *desc,
-			   int i, struct pte_list_desc *prev_desc)
+pte_list_desc_remove_entry(struct kvm_rmap_head *rmap_head,
+			   struct pte_list_desc *desc, int i,
+			   struct pte_list_desc *prev_desc)
 {
 	int j;
 
@@ -967,43 +962,43 @@
 	if (j != 0)
 		return;
 	if (!prev_desc && !desc->more)
-		*pte_list = (unsigned long)desc->sptes[0];
+		rmap_head->val = (unsigned long)desc->sptes[0];
 	else
 		if (prev_desc)
 			prev_desc->more = desc->more;
 		else
-			*pte_list = (unsigned long)desc->more | 1;
+			rmap_head->val = (unsigned long)desc->more | 1;
 	mmu_free_pte_list_desc(desc);
 }
 
-static void pte_list_remove(u64 *spte, unsigned long *pte_list)
+static void pte_list_remove(u64 *spte, struct kvm_rmap_head *rmap_head)
 {
 	struct pte_list_desc *desc;
 	struct pte_list_desc *prev_desc;
 	int i;
 
-	if (!*pte_list) {
+	if (!rmap_head->val) {
 		printk(KERN_ERR "pte_list_remove: %p 0->BUG\n", spte);
 		BUG();
-	} else if (!(*pte_list & 1)) {
+	} else if (!(rmap_head->val & 1)) {
 		rmap_printk("pte_list_remove:  %p 1->0\n", spte);
-		if ((u64 *)*pte_list != spte) {
+		if ((u64 *)rmap_head->val != spte) {
 			printk(KERN_ERR "pte_list_remove:  %p 1->BUG\n", spte);
 			BUG();
 		}
-		*pte_list = 0;
+		rmap_head->val = 0;
 	} else {
 		rmap_printk("pte_list_remove:  %p many->many\n", spte);
-		desc = (struct pte_list_desc *)(*pte_list & ~1ul);
+		desc = (struct pte_list_desc *)(rmap_head->val & ~1ul);
 		prev_desc = NULL;
 		while (desc) {
-			for (i = 0; i < PTE_LIST_EXT && desc->sptes[i]; ++i)
+			for (i = 0; i < PTE_LIST_EXT && desc->sptes[i]; ++i) {
 				if (desc->sptes[i] == spte) {
-					pte_list_desc_remove_entry(pte_list,
-							       desc, i,
-							       prev_desc);
+					pte_list_desc_remove_entry(rmap_head,
+							desc, i, prev_desc);
 					return;
 				}
+			}
 			prev_desc = desc;
 			desc = desc->more;
 		}
@@ -1012,28 +1007,8 @@
 	}
 }
 
-typedef void (*pte_list_walk_fn) (u64 *spte);
-static void pte_list_walk(unsigned long *pte_list, pte_list_walk_fn fn)
-{
-	struct pte_list_desc *desc;
-	int i;
-
-	if (!*pte_list)
-		return;
-
-	if (!(*pte_list & 1))
-		return fn((u64 *)*pte_list);
-
-	desc = (struct pte_list_desc *)(*pte_list & ~1ul);
-	while (desc) {
-		for (i = 0; i < PTE_LIST_EXT && desc->sptes[i]; ++i)
-			fn(desc->sptes[i]);
-		desc = desc->more;
-	}
-}
-
-static unsigned long *__gfn_to_rmap(gfn_t gfn, int level,
-				    struct kvm_memory_slot *slot)
+static struct kvm_rmap_head *__gfn_to_rmap(gfn_t gfn, int level,
+					   struct kvm_memory_slot *slot)
 {
 	unsigned long idx;
 
@@ -1041,10 +1016,8 @@
 	return &slot->arch.rmap[level - PT_PAGE_TABLE_LEVEL][idx];
 }
 
-/*
- * Take gfn and return the reverse mapping to it.
- */
-static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, struct kvm_mmu_page *sp)
+static struct kvm_rmap_head *gfn_to_rmap(struct kvm *kvm, gfn_t gfn,
+					 struct kvm_mmu_page *sp)
 {
 	struct kvm_memslots *slots;
 	struct kvm_memory_slot *slot;
@@ -1065,24 +1038,24 @@
 static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
 {
 	struct kvm_mmu_page *sp;
-	unsigned long *rmapp;
+	struct kvm_rmap_head *rmap_head;
 
 	sp = page_header(__pa(spte));
 	kvm_mmu_page_set_gfn(sp, spte - sp->spt, gfn);
-	rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp);
-	return pte_list_add(vcpu, spte, rmapp);
+	rmap_head = gfn_to_rmap(vcpu->kvm, gfn, sp);
+	return pte_list_add(vcpu, spte, rmap_head);
 }
 
 static void rmap_remove(struct kvm *kvm, u64 *spte)
 {
 	struct kvm_mmu_page *sp;
 	gfn_t gfn;
-	unsigned long *rmapp;
+	struct kvm_rmap_head *rmap_head;
 
 	sp = page_header(__pa(spte));
 	gfn = kvm_mmu_page_get_gfn(sp, spte - sp->spt);
-	rmapp = gfn_to_rmap(kvm, gfn, sp);
-	pte_list_remove(spte, rmapp);
+	rmap_head = gfn_to_rmap(kvm, gfn, sp);
+	pte_list_remove(spte, rmap_head);
 }
 
 /*
@@ -1102,19 +1075,26 @@
  *
  * Returns sptep if found, NULL otherwise.
  */
-static u64 *rmap_get_first(unsigned long rmap, struct rmap_iterator *iter)
+static u64 *rmap_get_first(struct kvm_rmap_head *rmap_head,
+			   struct rmap_iterator *iter)
 {
-	if (!rmap)
+	u64 *sptep;
+
+	if (!rmap_head->val)
 		return NULL;
 
-	if (!(rmap & 1)) {
+	if (!(rmap_head->val & 1)) {
 		iter->desc = NULL;
-		return (u64 *)rmap;
+		sptep = (u64 *)rmap_head->val;
+		goto out;
 	}
 
-	iter->desc = (struct pte_list_desc *)(rmap & ~1ul);
+	iter->desc = (struct pte_list_desc *)(rmap_head->val & ~1ul);
 	iter->pos = 0;
-	return iter->desc->sptes[iter->pos];
+	sptep = iter->desc->sptes[iter->pos];
+out:
+	BUG_ON(!is_shadow_present_pte(*sptep));
+	return sptep;
 }
 
 /*
@@ -1124,14 +1104,14 @@
  */
 static u64 *rmap_get_next(struct rmap_iterator *iter)
 {
+	u64 *sptep;
+
 	if (iter->desc) {
 		if (iter->pos < PTE_LIST_EXT - 1) {
-			u64 *sptep;
-
 			++iter->pos;
 			sptep = iter->desc->sptes[iter->pos];
 			if (sptep)
-				return sptep;
+				goto out;
 		}
 
 		iter->desc = iter->desc->more;
@@ -1139,17 +1119,20 @@
 		if (iter->desc) {
 			iter->pos = 0;
 			/* desc->sptes[0] cannot be NULL */
-			return iter->desc->sptes[iter->pos];
+			sptep = iter->desc->sptes[iter->pos];
+			goto out;
 		}
 	}
 
 	return NULL;
+out:
+	BUG_ON(!is_shadow_present_pte(*sptep));
+	return sptep;
 }
 
-#define for_each_rmap_spte(_rmap_, _iter_, _spte_)			    \
-	   for (_spte_ = rmap_get_first(*_rmap_, _iter_);		    \
-		_spte_ && ({BUG_ON(!is_shadow_present_pte(*_spte_)); 1;});  \
-			_spte_ = rmap_get_next(_iter_))
+#define for_each_rmap_spte(_rmap_head_, _iter_, _spte_)			\
+	for (_spte_ = rmap_get_first(_rmap_head_, _iter_);		\
+	     _spte_; _spte_ = rmap_get_next(_iter_))
 
 static void drop_spte(struct kvm *kvm, u64 *sptep)
 {
@@ -1207,14 +1190,15 @@
 	return mmu_spte_update(sptep, spte);
 }
 
-static bool __rmap_write_protect(struct kvm *kvm, unsigned long *rmapp,
+static bool __rmap_write_protect(struct kvm *kvm,
+				 struct kvm_rmap_head *rmap_head,
 				 bool pt_protect)
 {
 	u64 *sptep;
 	struct rmap_iterator iter;
 	bool flush = false;
 
-	for_each_rmap_spte(rmapp, &iter, sptep)
+	for_each_rmap_spte(rmap_head, &iter, sptep)
 		flush |= spte_write_protect(kvm, sptep, pt_protect);
 
 	return flush;
@@ -1231,13 +1215,13 @@
 	return mmu_spte_update(sptep, spte);
 }
 
-static bool __rmap_clear_dirty(struct kvm *kvm, unsigned long *rmapp)
+static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head)
 {
 	u64 *sptep;
 	struct rmap_iterator iter;
 	bool flush = false;
 
-	for_each_rmap_spte(rmapp, &iter, sptep)
+	for_each_rmap_spte(rmap_head, &iter, sptep)
 		flush |= spte_clear_dirty(kvm, sptep);
 
 	return flush;
@@ -1254,13 +1238,13 @@
 	return mmu_spte_update(sptep, spte);
 }
 
-static bool __rmap_set_dirty(struct kvm *kvm, unsigned long *rmapp)
+static bool __rmap_set_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head)
 {
 	u64 *sptep;
 	struct rmap_iterator iter;
 	bool flush = false;
 
-	for_each_rmap_spte(rmapp, &iter, sptep)
+	for_each_rmap_spte(rmap_head, &iter, sptep)
 		flush |= spte_set_dirty(kvm, sptep);
 
 	return flush;
@@ -1280,12 +1264,12 @@
 				     struct kvm_memory_slot *slot,
 				     gfn_t gfn_offset, unsigned long mask)
 {
-	unsigned long *rmapp;
+	struct kvm_rmap_head *rmap_head;
 
 	while (mask) {
-		rmapp = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask),
-				      PT_PAGE_TABLE_LEVEL, slot);
-		__rmap_write_protect(kvm, rmapp, false);
+		rmap_head = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask),
+					  PT_PAGE_TABLE_LEVEL, slot);
+		__rmap_write_protect(kvm, rmap_head, false);
 
 		/* clear the first set bit */
 		mask &= mask - 1;
@@ -1305,12 +1289,12 @@
 				     struct kvm_memory_slot *slot,
 				     gfn_t gfn_offset, unsigned long mask)
 {
-	unsigned long *rmapp;
+	struct kvm_rmap_head *rmap_head;
 
 	while (mask) {
-		rmapp = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask),
-				      PT_PAGE_TABLE_LEVEL, slot);
-		__rmap_clear_dirty(kvm, rmapp);
+		rmap_head = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask),
+					  PT_PAGE_TABLE_LEVEL, slot);
+		__rmap_clear_dirty(kvm, rmap_head);
 
 		/* clear the first set bit */
 		mask &= mask - 1;
@@ -1342,28 +1326,27 @@
 static bool rmap_write_protect(struct kvm_vcpu *vcpu, u64 gfn)
 {
 	struct kvm_memory_slot *slot;
-	unsigned long *rmapp;
+	struct kvm_rmap_head *rmap_head;
 	int i;
 	bool write_protected = false;
 
 	slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
 
 	for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
-		rmapp = __gfn_to_rmap(gfn, i, slot);
-		write_protected |= __rmap_write_protect(vcpu->kvm, rmapp, true);
+		rmap_head = __gfn_to_rmap(gfn, i, slot);
+		write_protected |= __rmap_write_protect(vcpu->kvm, rmap_head, true);
 	}
 
 	return write_protected;
 }
 
-static bool kvm_zap_rmapp(struct kvm *kvm, unsigned long *rmapp)
+static bool kvm_zap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head)
 {
 	u64 *sptep;
 	struct rmap_iterator iter;
 	bool flush = false;
 
-	while ((sptep = rmap_get_first(*rmapp, &iter))) {
-		BUG_ON(!(*sptep & PT_PRESENT_MASK));
+	while ((sptep = rmap_get_first(rmap_head, &iter))) {
 		rmap_printk("%s: spte %p %llx.\n", __func__, sptep, *sptep);
 
 		drop_spte(kvm, sptep);
@@ -1373,14 +1356,14 @@
 	return flush;
 }
 
-static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
+static int kvm_unmap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
 			   struct kvm_memory_slot *slot, gfn_t gfn, int level,
 			   unsigned long data)
 {
-	return kvm_zap_rmapp(kvm, rmapp);
+	return kvm_zap_rmapp(kvm, rmap_head);
 }
 
-static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp,
+static int kvm_set_pte_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
 			     struct kvm_memory_slot *slot, gfn_t gfn, int level,
 			     unsigned long data)
 {
@@ -1395,7 +1378,7 @@
 	new_pfn = pte_pfn(*ptep);
 
 restart:
-	for_each_rmap_spte(rmapp, &iter, sptep) {
+	for_each_rmap_spte(rmap_head, &iter, sptep) {
 		rmap_printk("kvm_set_pte_rmapp: spte %p %llx gfn %llx (%d)\n",
 			     sptep, *sptep, gfn, level);
 
@@ -1433,11 +1416,11 @@
 
 	/* output fields. */
 	gfn_t gfn;
-	unsigned long *rmap;
+	struct kvm_rmap_head *rmap;
 	int level;
 
 	/* private field. */
-	unsigned long *end_rmap;
+	struct kvm_rmap_head *end_rmap;
 };
 
 static void
@@ -1496,7 +1479,7 @@
 				unsigned long end,
 				unsigned long data,
 				int (*handler)(struct kvm *kvm,
-					       unsigned long *rmapp,
+					       struct kvm_rmap_head *rmap_head,
 					       struct kvm_memory_slot *slot,
 					       gfn_t gfn,
 					       int level,
@@ -1540,7 +1523,8 @@
 
 static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
 			  unsigned long data,
-			  int (*handler)(struct kvm *kvm, unsigned long *rmapp,
+			  int (*handler)(struct kvm *kvm,
+					 struct kvm_rmap_head *rmap_head,
 					 struct kvm_memory_slot *slot,
 					 gfn_t gfn, int level,
 					 unsigned long data))
@@ -1563,7 +1547,7 @@
 	kvm_handle_hva(kvm, hva, (unsigned long)&pte, kvm_set_pte_rmapp);
 }
 
-static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
+static int kvm_age_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
 			 struct kvm_memory_slot *slot, gfn_t gfn, int level,
 			 unsigned long data)
 {
@@ -1573,18 +1557,19 @@
 
 	BUG_ON(!shadow_accessed_mask);
 
-	for_each_rmap_spte(rmapp, &iter, sptep)
+	for_each_rmap_spte(rmap_head, &iter, sptep) {
 		if (*sptep & shadow_accessed_mask) {
 			young = 1;
 			clear_bit((ffs(shadow_accessed_mask) - 1),
 				 (unsigned long *)sptep);
 		}
+	}
 
 	trace_kvm_age_page(gfn, level, slot, young);
 	return young;
 }
 
-static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
+static int kvm_test_age_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
 			      struct kvm_memory_slot *slot, gfn_t gfn,
 			      int level, unsigned long data)
 {
@@ -1600,11 +1585,12 @@
 	if (!shadow_accessed_mask)
 		goto out;
 
-	for_each_rmap_spte(rmapp, &iter, sptep)
+	for_each_rmap_spte(rmap_head, &iter, sptep) {
 		if (*sptep & shadow_accessed_mask) {
 			young = 1;
 			break;
 		}
+	}
 out:
 	return young;
 }
@@ -1613,14 +1599,14 @@
 
 static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
 {
-	unsigned long *rmapp;
+	struct kvm_rmap_head *rmap_head;
 	struct kvm_mmu_page *sp;
 
 	sp = page_header(__pa(spte));
 
-	rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp);
+	rmap_head = gfn_to_rmap(vcpu->kvm, gfn, sp);
 
-	kvm_unmap_rmapp(vcpu->kvm, rmapp, NULL, gfn, sp->role.level, 0);
+	kvm_unmap_rmapp(vcpu->kvm, rmap_head, NULL, gfn, sp->role.level, 0);
 	kvm_flush_remote_tlbs(vcpu->kvm);
 }
 
@@ -1720,8 +1706,7 @@
 	mmu_spte_clear_no_track(parent_pte);
 }
 
-static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu,
-					       u64 *parent_pte, int direct)
+static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, int direct)
 {
 	struct kvm_mmu_page *sp;
 
@@ -1737,8 +1722,6 @@
 	 * this feature. See the comments in kvm_zap_obsolete_pages().
 	 */
 	list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages);
-	sp->parent_ptes = 0;
-	mmu_page_add_parent_pte(vcpu, sp, parent_pte);
 	kvm_mod_used_mmu_pages(vcpu->kvm, +1);
 	return sp;
 }
@@ -1746,7 +1729,12 @@
 static void mark_unsync(u64 *spte);
 static void kvm_mmu_mark_parents_unsync(struct kvm_mmu_page *sp)
 {
-	pte_list_walk(&sp->parent_ptes, mark_unsync);
+	u64 *sptep;
+	struct rmap_iterator iter;
+
+	for_each_rmap_spte(&sp->parent_ptes, &iter, sptep) {
+		mark_unsync(sptep);
+	}
 }
 
 static void mark_unsync(u64 *spte)
@@ -1806,6 +1794,13 @@
 	return (pvec->nr == KVM_PAGE_ARRAY_NR);
 }
 
+static inline void clear_unsync_child_bit(struct kvm_mmu_page *sp, int idx)
+{
+	--sp->unsync_children;
+	WARN_ON((int)sp->unsync_children < 0);
+	__clear_bit(idx, sp->unsync_child_bitmap);
+}
+
 static int __mmu_unsync_walk(struct kvm_mmu_page *sp,
 			   struct kvm_mmu_pages *pvec)
 {
@@ -1815,8 +1810,10 @@
 		struct kvm_mmu_page *child;
 		u64 ent = sp->spt[i];
 
-		if (!is_shadow_present_pte(ent) || is_large_pte(ent))
-			goto clear_child_bitmap;
+		if (!is_shadow_present_pte(ent) || is_large_pte(ent)) {
+			clear_unsync_child_bit(sp, i);
+			continue;
+		}
 
 		child = page_header(ent & PT64_BASE_ADDR_MASK);
 
@@ -1825,28 +1822,21 @@
 				return -ENOSPC;
 
 			ret = __mmu_unsync_walk(child, pvec);
-			if (!ret)
-				goto clear_child_bitmap;
-			else if (ret > 0)
+			if (!ret) {
+				clear_unsync_child_bit(sp, i);
+				continue;
+			} else if (ret > 0) {
 				nr_unsync_leaf += ret;
-			else
+			} else
 				return ret;
 		} else if (child->unsync) {
 			nr_unsync_leaf++;
 			if (mmu_pages_add(pvec, child, i))
 				return -ENOSPC;
 		} else
-			 goto clear_child_bitmap;
-
-		continue;
-
-clear_child_bitmap:
-		__clear_bit(i, sp->unsync_child_bitmap);
-		sp->unsync_children--;
-		WARN_ON((int)sp->unsync_children < 0);
+			clear_unsync_child_bit(sp, i);
 	}
 
-
 	return nr_unsync_leaf;
 }
 
@@ -2009,9 +1999,7 @@
 		if (!sp)
 			return;
 
-		--sp->unsync_children;
-		WARN_ON((int)sp->unsync_children < 0);
-		__clear_bit(idx, sp->unsync_child_bitmap);
+		clear_unsync_child_bit(sp, idx);
 		level++;
 	} while (level < PT64_ROOT_LEVEL-1 && !sp->unsync_children);
 }
@@ -2053,14 +2041,6 @@
 	}
 }
 
-static void init_shadow_page_table(struct kvm_mmu_page *sp)
-{
-	int i;
-
-	for (i = 0; i < PT64_ENT_PER_PAGE; ++i)
-		sp->spt[i] = 0ull;
-}
-
 static void __clear_sp_write_flooding_count(struct kvm_mmu_page *sp)
 {
 	sp->write_flooding_count = 0;
@@ -2083,8 +2063,7 @@
 					     gva_t gaddr,
 					     unsigned level,
 					     int direct,
-					     unsigned access,
-					     u64 *parent_pte)
+					     unsigned access)
 {
 	union kvm_mmu_page_role role;
 	unsigned quadrant;
@@ -2116,21 +2095,18 @@
 		if (sp->unsync && kvm_sync_page_transient(vcpu, sp))
 			break;
 
-		mmu_page_add_parent_pte(vcpu, sp, parent_pte);
-		if (sp->unsync_children) {
+		if (sp->unsync_children)
 			kvm_make_request(KVM_REQ_MMU_SYNC, vcpu);
-			kvm_mmu_mark_parents_unsync(sp);
-		} else if (sp->unsync)
-			kvm_mmu_mark_parents_unsync(sp);
 
 		__clear_sp_write_flooding_count(sp);
 		trace_kvm_mmu_get_page(sp, false);
 		return sp;
 	}
+
 	++vcpu->kvm->stat.mmu_cache_miss;
-	sp = kvm_mmu_alloc_page(vcpu, parent_pte, direct);
-	if (!sp)
-		return sp;
+
+	sp = kvm_mmu_alloc_page(vcpu, direct);
+
 	sp->gfn = gfn;
 	sp->role = role;
 	hlist_add_head(&sp->hash_link,
@@ -2144,7 +2120,7 @@
 		account_shadowed(vcpu->kvm, sp);
 	}
 	sp->mmu_valid_gen = vcpu->kvm->arch.mmu_valid_gen;
-	init_shadow_page_table(sp);
+	clear_page(sp->spt);
 	trace_kvm_mmu_get_page(sp, true);
 	return sp;
 }
@@ -2198,7 +2174,8 @@
 	return __shadow_walk_next(iterator, *iterator->sptep);
 }
 
-static void link_shadow_page(u64 *sptep, struct kvm_mmu_page *sp, bool accessed)
+static void link_shadow_page(struct kvm_vcpu *vcpu, u64 *sptep,
+			     struct kvm_mmu_page *sp)
 {
 	u64 spte;
 
@@ -2206,12 +2183,14 @@
 			VMX_EPT_WRITABLE_MASK != PT_WRITABLE_MASK);
 
 	spte = __pa(sp->spt) | PT_PRESENT_MASK | PT_WRITABLE_MASK |
-	       shadow_user_mask | shadow_x_mask;
-
-	if (accessed)
-		spte |= shadow_accessed_mask;
+	       shadow_user_mask | shadow_x_mask | shadow_accessed_mask;
 
 	mmu_spte_set(sptep, spte);
+
+	mmu_page_add_parent_pte(vcpu, sp, sptep);
+
+	if (sp->unsync_children || sp->unsync)
+		mark_unsync(sptep);
 }
 
 static void validate_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep,
@@ -2270,17 +2249,12 @@
 		mmu_page_zap_pte(kvm, sp, sp->spt + i);
 }
 
-static void kvm_mmu_put_page(struct kvm_mmu_page *sp, u64 *parent_pte)
-{
-	mmu_page_remove_parent_pte(sp, parent_pte);
-}
-
 static void kvm_mmu_unlink_parents(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
 	u64 *sptep;
 	struct rmap_iterator iter;
 
-	while ((sptep = rmap_get_first(sp->parent_ptes, &iter)))
+	while ((sptep = rmap_get_first(&sp->parent_ptes, &iter)))
 		drop_parent_pte(sp, sptep);
 }
 
@@ -2564,18 +2538,18 @@
 	return ret;
 }
 
-static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
-			 unsigned pte_access, int write_fault, int *emulate,
-			 int level, gfn_t gfn, pfn_t pfn, bool speculative,
-			 bool host_writable)
+static bool mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access,
+			 int write_fault, int level, gfn_t gfn, pfn_t pfn,
+			 bool speculative, bool host_writable)
 {
 	int was_rmapped = 0;
 	int rmap_count;
+	bool emulate = false;
 
 	pgprintk("%s: spte %llx write_fault %d gfn %llx\n", __func__,
 		 *sptep, write_fault, gfn);
 
-	if (is_rmap_spte(*sptep)) {
+	if (is_shadow_present_pte(*sptep)) {
 		/*
 		 * If we overwrite a PTE page pointer with a 2MB PMD, unlink
 		 * the parent of the now unreachable PTE.
@@ -2600,12 +2574,12 @@
 	if (set_spte(vcpu, sptep, pte_access, level, gfn, pfn, speculative,
 	      true, host_writable)) {
 		if (write_fault)
-			*emulate = 1;
+			emulate = true;
 		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 	}
 
-	if (unlikely(is_mmio_spte(*sptep) && emulate))
-		*emulate = 1;
+	if (unlikely(is_mmio_spte(*sptep)))
+		emulate = true;
 
 	pgprintk("%s: setting spte %llx\n", __func__, *sptep);
 	pgprintk("instantiating %s PTE (%s) at %llx (%llx) addr %p\n",
@@ -2624,6 +2598,8 @@
 	}
 
 	kvm_release_pfn_clean(pfn);
+
+	return emulate;
 }
 
 static pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn,
@@ -2658,9 +2634,8 @@
 		return -1;
 
 	for (i = 0; i < ret; i++, gfn++, start++)
-		mmu_set_spte(vcpu, start, access, 0, NULL,
-			     sp->role.level, gfn, page_to_pfn(pages[i]),
-			     true, true);
+		mmu_set_spte(vcpu, start, access, 0, sp->role.level, gfn,
+			     page_to_pfn(pages[i]), true, true);
 
 	return 0;
 }
@@ -2708,9 +2683,8 @@
 	__direct_pte_prefetch(vcpu, sp, sptep);
 }
 
-static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
-			int map_writable, int level, gfn_t gfn, pfn_t pfn,
-			bool prefault)
+static int __direct_map(struct kvm_vcpu *vcpu, int write, int map_writable,
+			int level, gfn_t gfn, pfn_t pfn, bool prefault)
 {
 	struct kvm_shadow_walk_iterator iterator;
 	struct kvm_mmu_page *sp;
@@ -2722,9 +2696,9 @@
 
 	for_each_shadow_entry(vcpu, (u64)gfn << PAGE_SHIFT, iterator) {
 		if (iterator.level == level) {
-			mmu_set_spte(vcpu, iterator.sptep, ACC_ALL,
-				     write, &emulate, level, gfn, pfn,
-				     prefault, map_writable);
+			emulate = mmu_set_spte(vcpu, iterator.sptep, ACC_ALL,
+					       write, level, gfn, pfn, prefault,
+					       map_writable);
 			direct_pte_prefetch(vcpu, iterator.sptep);
 			++vcpu->stat.pf_fixed;
 			break;
@@ -2737,10 +2711,9 @@
 			base_addr &= PT64_LVL_ADDR_MASK(iterator.level);
 			pseudo_gfn = base_addr >> PAGE_SHIFT;
 			sp = kvm_mmu_get_page(vcpu, pseudo_gfn, iterator.addr,
-					      iterator.level - 1,
-					      1, ACC_ALL, iterator.sptep);
+					      iterator.level - 1, 1, ACC_ALL);
 
-			link_shadow_page(iterator.sptep, sp, true);
+			link_shadow_page(vcpu, iterator.sptep, sp);
 		}
 	}
 	return emulate;
@@ -2919,7 +2892,7 @@
 	 * If the mapping has been changed, let the vcpu fault on the
 	 * same address again.
 	 */
-	if (!is_rmap_spte(spte)) {
+	if (!is_shadow_present_pte(spte)) {
 		ret = true;
 		goto exit;
 	}
@@ -3018,11 +2991,9 @@
 	make_mmu_pages_available(vcpu);
 	if (likely(!force_pt_level))
 		transparent_hugepage_adjust(vcpu, &gfn, &pfn, &level);
-	r = __direct_map(vcpu, v, write, map_writable, level, gfn, pfn,
-			 prefault);
+	r = __direct_map(vcpu, write, map_writable, level, gfn, pfn, prefault);
 	spin_unlock(&vcpu->kvm->mmu_lock);
 
-
 	return r;
 
 out_unlock:
@@ -3097,8 +3068,7 @@
 	if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_LEVEL) {
 		spin_lock(&vcpu->kvm->mmu_lock);
 		make_mmu_pages_available(vcpu);
-		sp = kvm_mmu_get_page(vcpu, 0, 0, PT64_ROOT_LEVEL,
-				      1, ACC_ALL, NULL);
+		sp = kvm_mmu_get_page(vcpu, 0, 0, PT64_ROOT_LEVEL, 1, ACC_ALL);
 		++sp->root_count;
 		spin_unlock(&vcpu->kvm->mmu_lock);
 		vcpu->arch.mmu.root_hpa = __pa(sp->spt);
@@ -3110,9 +3080,7 @@
 			spin_lock(&vcpu->kvm->mmu_lock);
 			make_mmu_pages_available(vcpu);
 			sp = kvm_mmu_get_page(vcpu, i << (30 - PAGE_SHIFT),
-					      i << 30,
-					      PT32_ROOT_LEVEL, 1, ACC_ALL,
-					      NULL);
+					i << 30, PT32_ROOT_LEVEL, 1, ACC_ALL);
 			root = __pa(sp->spt);
 			++sp->root_count;
 			spin_unlock(&vcpu->kvm->mmu_lock);
@@ -3149,7 +3117,7 @@
 		spin_lock(&vcpu->kvm->mmu_lock);
 		make_mmu_pages_available(vcpu);
 		sp = kvm_mmu_get_page(vcpu, root_gfn, 0, PT64_ROOT_LEVEL,
-				      0, ACC_ALL, NULL);
+				      0, ACC_ALL);
 		root = __pa(sp->spt);
 		++sp->root_count;
 		spin_unlock(&vcpu->kvm->mmu_lock);
@@ -3182,9 +3150,8 @@
 		}
 		spin_lock(&vcpu->kvm->mmu_lock);
 		make_mmu_pages_available(vcpu);
-		sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30,
-				      PT32_ROOT_LEVEL, 0,
-				      ACC_ALL, NULL);
+		sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30, PT32_ROOT_LEVEL,
+				      0, ACC_ALL);
 		root = __pa(sp->spt);
 		++sp->root_count;
 		spin_unlock(&vcpu->kvm->mmu_lock);
@@ -3531,8 +3498,7 @@
 	make_mmu_pages_available(vcpu);
 	if (likely(!force_pt_level))
 		transparent_hugepage_adjust(vcpu, &gfn, &pfn, &level);
-	r = __direct_map(vcpu, gpa, write, map_writable,
-			 level, gfn, pfn, prefault);
+	r = __direct_map(vcpu, write, map_writable, level, gfn, pfn, prefault);
 	spin_unlock(&vcpu->kvm->mmu_lock);
 
 	return r;
@@ -4058,10 +4024,12 @@
 	g_context->inject_page_fault = kvm_inject_page_fault;
 
 	/*
-	 * Note that arch.mmu.gva_to_gpa translates l2_gva to l1_gpa. The
-	 * translation of l2_gpa to l1_gpa addresses is done using the
-	 * arch.nested_mmu.gva_to_gpa function. Basically the gva_to_gpa
-	 * functions between mmu and nested_mmu are swapped.
+	 * Note that arch.mmu.gva_to_gpa translates l2_gpa to l1_gpa using
+	 * L1's nested page tables (e.g. EPT12). The nested translation
+	 * of l2_gva to l1_gpa is done by arch.nested_mmu.gva_to_gpa using
+	 * L2's page tables as the first level of translation and L1's
+	 * nested page tables as the second level of translation. Basically
+	 * the gva_to_gpa functions between mmu and nested_mmu are swapped.
 	 */
 	if (!is_paging(vcpu)) {
 		g_context->nx = false;
@@ -4495,7 +4463,7 @@
 }
 
 /* The return value indicates if tlb flush on all vcpus is needed. */
-typedef bool (*slot_level_handler) (struct kvm *kvm, unsigned long *rmap);
+typedef bool (*slot_level_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_head);
 
 /* The caller should hold mmu-lock before calling this function. */
 static bool
@@ -4589,9 +4557,10 @@
 	spin_unlock(&kvm->mmu_lock);
 }
 
-static bool slot_rmap_write_protect(struct kvm *kvm, unsigned long *rmapp)
+static bool slot_rmap_write_protect(struct kvm *kvm,
+				    struct kvm_rmap_head *rmap_head)
 {
-	return __rmap_write_protect(kvm, rmapp, false);
+	return __rmap_write_protect(kvm, rmap_head, false);
 }
 
 void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
@@ -4627,7 +4596,7 @@
 }
 
 static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm,
-		unsigned long *rmapp)
+					 struct kvm_rmap_head *rmap_head)
 {
 	u64 *sptep;
 	struct rmap_iterator iter;
@@ -4636,7 +4605,7 @@
 	struct kvm_mmu_page *sp;
 
 restart:
-	for_each_rmap_spte(rmapp, &iter, sptep) {
+	for_each_rmap_spte(rmap_head, &iter, sptep) {
 		sp = page_header(__pa(sptep));
 		pfn = spte_to_pfn(*sptep);
 
diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c
index 03d518e..1cee3ec 100644
--- a/arch/x86/kvm/mmu_audit.c
+++ b/arch/x86/kvm/mmu_audit.c
@@ -129,7 +129,7 @@
 static void inspect_spte_has_rmap(struct kvm *kvm, u64 *sptep)
 {
 	static DEFINE_RATELIMIT_STATE(ratelimit_state, 5 * HZ, 10);
-	unsigned long *rmapp;
+	struct kvm_rmap_head *rmap_head;
 	struct kvm_mmu_page *rev_sp;
 	struct kvm_memslots *slots;
 	struct kvm_memory_slot *slot;
@@ -150,8 +150,8 @@
 		return;
 	}
 
-	rmapp = __gfn_to_rmap(gfn, rev_sp->role.level, slot);
-	if (!*rmapp) {
+	rmap_head = __gfn_to_rmap(gfn, rev_sp->role.level, slot);
+	if (!rmap_head->val) {
 		if (!__ratelimit(&ratelimit_state))
 			return;
 		audit_printk(kvm, "no rmap for writable spte %llx\n",
@@ -183,7 +183,7 @@
 		return;
 
 	for (i = 0; i < PT64_ENT_PER_PAGE; ++i) {
-		if (!is_rmap_spte(sp->spt[i]))
+		if (!is_shadow_present_pte(sp->spt[i]))
 			continue;
 
 		inspect_spte_has_rmap(kvm, sp->spt + i);
@@ -192,7 +192,7 @@
 
 static void audit_write_protection(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
-	unsigned long *rmapp;
+	struct kvm_rmap_head *rmap_head;
 	u64 *sptep;
 	struct rmap_iterator iter;
 	struct kvm_memslots *slots;
@@ -203,13 +203,14 @@
 
 	slots = kvm_memslots_for_spte_role(kvm, sp->role);
 	slot = __gfn_to_memslot(slots, sp->gfn);
-	rmapp = __gfn_to_rmap(sp->gfn, PT_PAGE_TABLE_LEVEL, slot);
+	rmap_head = __gfn_to_rmap(sp->gfn, PT_PAGE_TABLE_LEVEL, slot);
 
-	for_each_rmap_spte(rmapp, &iter, sptep)
+	for_each_rmap_spte(rmap_head, &iter, sptep) {
 		if (is_writable_pte(*sptep))
 			audit_printk(kvm, "shadow page has writable "
 				     "mappings: gfn %llx role %x\n",
 				     sp->gfn, sp->role.word);
+	}
 }
 
 static void audit_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 3058a22..91e939b 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -475,8 +475,8 @@
 	 * we call mmu_set_spte() with host_writable = true because
 	 * pte_prefetch_gfn_to_pfn always gets a writable pfn.
 	 */
-	mmu_set_spte(vcpu, spte, pte_access, 0, NULL, PT_PAGE_TABLE_LEVEL,
-		     gfn, pfn, true, true);
+	mmu_set_spte(vcpu, spte, pte_access, 0, PT_PAGE_TABLE_LEVEL, gfn, pfn,
+		     true, true);
 
 	return true;
 }
@@ -556,7 +556,7 @@
 	struct kvm_mmu_page *sp = NULL;
 	struct kvm_shadow_walk_iterator it;
 	unsigned direct_access, access = gw->pt_access;
-	int top_level, emulate = 0;
+	int top_level, emulate;
 
 	direct_access = gw->pte_access;
 
@@ -587,7 +587,7 @@
 		if (!is_shadow_present_pte(*it.sptep)) {
 			table_gfn = gw->table_gfn[it.level - 2];
 			sp = kvm_mmu_get_page(vcpu, table_gfn, addr, it.level-1,
-					      false, access, it.sptep);
+					      false, access);
 		}
 
 		/*
@@ -598,7 +598,7 @@
 			goto out_gpte_changed;
 
 		if (sp)
-			link_shadow_page(it.sptep, sp, PT_GUEST_ACCESSED_MASK);
+			link_shadow_page(vcpu, it.sptep, sp);
 	}
 
 	for (;
@@ -617,20 +617,18 @@
 		direct_gfn = gw->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1);
 
 		sp = kvm_mmu_get_page(vcpu, direct_gfn, addr, it.level-1,
-				      true, direct_access, it.sptep);
-		link_shadow_page(it.sptep, sp, PT_GUEST_ACCESSED_MASK);
+				      true, direct_access);
+		link_shadow_page(vcpu, it.sptep, sp);
 	}
 
 	clear_sp_write_flooding_count(it.sptep);
-	mmu_set_spte(vcpu, it.sptep, gw->pte_access, write_fault, &emulate,
-		     it.level, gw->gfn, pfn, prefault, map_writable);
+	emulate = mmu_set_spte(vcpu, it.sptep, gw->pte_access, write_fault,
+			       it.level, gw->gfn, pfn, prefault, map_writable);
 	FNAME(pte_prefetch)(vcpu, gw, it.sptep);
 
 	return emulate;
 
 out_gpte_changed:
-	if (sp)
-		kvm_mmu_put_page(sp, it.sptep);
 	kvm_release_pfn_clean(pfn);
 	return 0;
 }
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 899c40f..c13a64b 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -86,6 +86,7 @@
 	MSR_FS_BASE,
 #endif
 	MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
+	MSR_TSC_AUX,
 };
 
 #define NR_HOST_SAVE_USER_MSRS ARRAY_SIZE(host_save_user_msrs)
@@ -135,6 +136,7 @@
 	uint64_t asid_generation;
 	uint64_t sysenter_esp;
 	uint64_t sysenter_eip;
+	uint64_t tsc_aux;
 
 	u64 next_rip;
 
@@ -1238,6 +1240,9 @@
 			wrmsrl(MSR_AMD64_TSC_RATIO, tsc_ratio);
 		}
 	}
+	/* This assumes that the kernel never uses MSR_TSC_AUX */
+	if (static_cpu_has(X86_FEATURE_RDTSCP))
+		wrmsrl(MSR_TSC_AUX, svm->tsc_aux);
 }
 
 static void svm_vcpu_put(struct kvm_vcpu *vcpu)
@@ -3024,6 +3029,11 @@
 	case MSR_IA32_SYSENTER_ESP:
 		msr_info->data = svm->sysenter_esp;
 		break;
+	case MSR_TSC_AUX:
+		if (!boot_cpu_has(X86_FEATURE_RDTSCP))
+			return 1;
+		msr_info->data = svm->tsc_aux;
+		break;
 	/*
 	 * Nobody will change the following 5 values in the VMCB so we can
 	 * safely return them on rdmsr. They will always be 0 until LBRV is
@@ -3053,6 +3063,23 @@
 	case MSR_IA32_UCODE_REV:
 		msr_info->data = 0x01000065;
 		break;
+	case MSR_F15H_IC_CFG: {
+
+		int family, model;
+
+		family = guest_cpuid_family(vcpu);
+		model  = guest_cpuid_model(vcpu);
+
+		if (family < 0 || model < 0)
+			return kvm_get_msr_common(vcpu, msr_info);
+
+		msr_info->data = 0;
+
+		if (family == 0x15 &&
+		    (model >= 0x2 && model < 0x20))
+			msr_info->data = 0x1E;
+		}
+		break;
 	default:
 		return kvm_get_msr_common(vcpu, msr_info);
 	}
@@ -3145,6 +3172,18 @@
 		svm->sysenter_esp = data;
 		svm->vmcb->save.sysenter_esp = data;
 		break;
+	case MSR_TSC_AUX:
+		if (!boot_cpu_has(X86_FEATURE_RDTSCP))
+			return 1;
+
+		/*
+		 * This is rare, so we update the MSR here instead of using
+		 * direct_access_msrs.  Doing that would require a rdmsr in
+		 * svm_vcpu_put.
+		 */
+		svm->tsc_aux = data;
+		wrmsrl(MSR_TSC_AUX, svm->tsc_aux);
+		break;
 	case MSR_IA32_DEBUGCTLMSR:
 		if (!boot_cpu_has(X86_FEATURE_LBRV)) {
 			vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTL 0x%llx, nop\n",
@@ -3561,12 +3600,16 @@
 	return;
 }
 
-static int svm_cpu_uses_apicv(struct kvm_vcpu *vcpu)
+static bool svm_get_enable_apicv(void)
 {
-	return 0;
+	return false;
 }
 
-static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu)
+static void svm_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu)
+{
+}
+
+static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
 {
 	return;
 }
@@ -4037,7 +4080,7 @@
 
 static bool svm_rdtscp_supported(void)
 {
-	return false;
+	return boot_cpu_has(X86_FEATURE_RDTSCP);
 }
 
 static bool svm_invpcid_supported(void)
@@ -4328,7 +4371,8 @@
 	.enable_irq_window = enable_irq_window,
 	.update_cr8_intercept = update_cr8_intercept,
 	.set_virtual_x2apic_mode = svm_set_virtual_x2apic_mode,
-	.cpu_uses_apicv = svm_cpu_uses_apicv,
+	.get_enable_apicv = svm_get_enable_apicv,
+	.refresh_apicv_exec_ctrl = svm_refresh_apicv_exec_ctrl,
 	.load_eoi_exitmap = svm_load_eoi_exitmap,
 	.sync_pir_to_irr = svm_sync_pir_to_irr,
 
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 1203025..ad9f6a2 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -268,7 +268,7 @@
 #define kvm_trace_sym_exc						\
 	EXS(DE), EXS(DB), EXS(BP), EXS(OF), EXS(BR), EXS(UD), EXS(NM),	\
 	EXS(DF), EXS(TS), EXS(NP), EXS(SS), EXS(GP), EXS(PF),		\
-	EXS(MF), EXS(MC)
+	EXS(MF), EXS(AC), EXS(MC)
 
 /*
  * Tracepoint for kvm interrupt injection:
@@ -1025,6 +1025,269 @@
 		  __entry->pi_desc_addr)
 );
 
+/*
+ * Tracepoint for kvm_hv_notify_acked_sint.
+ */
+TRACE_EVENT(kvm_hv_notify_acked_sint,
+	TP_PROTO(int vcpu_id, u32 sint),
+	TP_ARGS(vcpu_id, sint),
+
+	TP_STRUCT__entry(
+		__field(int, vcpu_id)
+		__field(u32, sint)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_id = vcpu_id;
+		__entry->sint = sint;
+	),
+
+	TP_printk("vcpu_id %d sint %u", __entry->vcpu_id, __entry->sint)
+);
+
+/*
+ * Tracepoint for synic_set_irq.
+ */
+TRACE_EVENT(kvm_hv_synic_set_irq,
+	TP_PROTO(int vcpu_id, u32 sint, int vector, int ret),
+	TP_ARGS(vcpu_id, sint, vector, ret),
+
+	TP_STRUCT__entry(
+		__field(int, vcpu_id)
+		__field(u32, sint)
+		__field(int, vector)
+		__field(int, ret)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_id = vcpu_id;
+		__entry->sint = sint;
+		__entry->vector = vector;
+		__entry->ret = ret;
+	),
+
+	TP_printk("vcpu_id %d sint %u vector %d ret %d",
+		  __entry->vcpu_id, __entry->sint, __entry->vector,
+		  __entry->ret)
+);
+
+/*
+ * Tracepoint for kvm_hv_synic_send_eoi.
+ */
+TRACE_EVENT(kvm_hv_synic_send_eoi,
+	TP_PROTO(int vcpu_id, int vector),
+	TP_ARGS(vcpu_id, vector),
+
+	TP_STRUCT__entry(
+		__field(int, vcpu_id)
+		__field(u32, sint)
+		__field(int, vector)
+		__field(int, ret)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_id = vcpu_id;
+		__entry->vector	= vector;
+	),
+
+	TP_printk("vcpu_id %d vector %d", __entry->vcpu_id, __entry->vector)
+);
+
+/*
+ * Tracepoint for synic_set_msr.
+ */
+TRACE_EVENT(kvm_hv_synic_set_msr,
+	TP_PROTO(int vcpu_id, u32 msr, u64 data, bool host),
+	TP_ARGS(vcpu_id, msr, data, host),
+
+	TP_STRUCT__entry(
+		__field(int, vcpu_id)
+		__field(u32, msr)
+		__field(u64, data)
+		__field(bool, host)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_id = vcpu_id;
+		__entry->msr = msr;
+		__entry->data = data;
+		__entry->host = host
+	),
+
+	TP_printk("vcpu_id %d msr 0x%x data 0x%llx host %d",
+		  __entry->vcpu_id, __entry->msr, __entry->data, __entry->host)
+);
+
+/*
+ * Tracepoint for stimer_set_config.
+ */
+TRACE_EVENT(kvm_hv_stimer_set_config,
+	TP_PROTO(int vcpu_id, int timer_index, u64 config, bool host),
+	TP_ARGS(vcpu_id, timer_index, config, host),
+
+	TP_STRUCT__entry(
+		__field(int, vcpu_id)
+		__field(int, timer_index)
+		__field(u64, config)
+		__field(bool, host)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_id = vcpu_id;
+		__entry->timer_index = timer_index;
+		__entry->config = config;
+		__entry->host = host;
+	),
+
+	TP_printk("vcpu_id %d timer %d config 0x%llx host %d",
+		  __entry->vcpu_id, __entry->timer_index, __entry->config,
+		  __entry->host)
+);
+
+/*
+ * Tracepoint for stimer_set_count.
+ */
+TRACE_EVENT(kvm_hv_stimer_set_count,
+	TP_PROTO(int vcpu_id, int timer_index, u64 count, bool host),
+	TP_ARGS(vcpu_id, timer_index, count, host),
+
+	TP_STRUCT__entry(
+		__field(int, vcpu_id)
+		__field(int, timer_index)
+		__field(u64, count)
+		__field(bool, host)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_id = vcpu_id;
+		__entry->timer_index = timer_index;
+		__entry->count = count;
+		__entry->host = host;
+	),
+
+	TP_printk("vcpu_id %d timer %d count %llu host %d",
+		  __entry->vcpu_id, __entry->timer_index, __entry->count,
+		  __entry->host)
+);
+
+/*
+ * Tracepoint for stimer_start(periodic timer case).
+ */
+TRACE_EVENT(kvm_hv_stimer_start_periodic,
+	TP_PROTO(int vcpu_id, int timer_index, u64 time_now, u64 exp_time),
+	TP_ARGS(vcpu_id, timer_index, time_now, exp_time),
+
+	TP_STRUCT__entry(
+		__field(int, vcpu_id)
+		__field(int, timer_index)
+		__field(u64, time_now)
+		__field(u64, exp_time)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_id = vcpu_id;
+		__entry->timer_index = timer_index;
+		__entry->time_now = time_now;
+		__entry->exp_time = exp_time;
+	),
+
+	TP_printk("vcpu_id %d timer %d time_now %llu exp_time %llu",
+		  __entry->vcpu_id, __entry->timer_index, __entry->time_now,
+		  __entry->exp_time)
+);
+
+/*
+ * Tracepoint for stimer_start(one-shot timer case).
+ */
+TRACE_EVENT(kvm_hv_stimer_start_one_shot,
+	TP_PROTO(int vcpu_id, int timer_index, u64 time_now, u64 count),
+	TP_ARGS(vcpu_id, timer_index, time_now, count),
+
+	TP_STRUCT__entry(
+		__field(int, vcpu_id)
+		__field(int, timer_index)
+		__field(u64, time_now)
+		__field(u64, count)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_id = vcpu_id;
+		__entry->timer_index = timer_index;
+		__entry->time_now = time_now;
+		__entry->count = count;
+	),
+
+	TP_printk("vcpu_id %d timer %d time_now %llu count %llu",
+		  __entry->vcpu_id, __entry->timer_index, __entry->time_now,
+		  __entry->count)
+);
+
+/*
+ * Tracepoint for stimer_timer_callback.
+ */
+TRACE_EVENT(kvm_hv_stimer_callback,
+	TP_PROTO(int vcpu_id, int timer_index),
+	TP_ARGS(vcpu_id, timer_index),
+
+	TP_STRUCT__entry(
+		__field(int, vcpu_id)
+		__field(int, timer_index)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_id = vcpu_id;
+		__entry->timer_index = timer_index;
+	),
+
+	TP_printk("vcpu_id %d timer %d",
+		  __entry->vcpu_id, __entry->timer_index)
+);
+
+/*
+ * Tracepoint for stimer_expiration.
+ */
+TRACE_EVENT(kvm_hv_stimer_expiration,
+	TP_PROTO(int vcpu_id, int timer_index, int msg_send_result),
+	TP_ARGS(vcpu_id, timer_index, msg_send_result),
+
+	TP_STRUCT__entry(
+		__field(int, vcpu_id)
+		__field(int, timer_index)
+		__field(int, msg_send_result)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_id = vcpu_id;
+		__entry->timer_index = timer_index;
+		__entry->msg_send_result = msg_send_result;
+	),
+
+	TP_printk("vcpu_id %d timer %d msg send result %d",
+		  __entry->vcpu_id, __entry->timer_index,
+		  __entry->msg_send_result)
+);
+
+/*
+ * Tracepoint for stimer_cleanup.
+ */
+TRACE_EVENT(kvm_hv_stimer_cleanup,
+	TP_PROTO(int vcpu_id, int timer_index),
+	TP_ARGS(vcpu_id, timer_index),
+
+	TP_STRUCT__entry(
+		__field(int, vcpu_id)
+		__field(int, timer_index)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_id = vcpu_id;
+		__entry->timer_index = timer_index;
+	),
+
+	TP_printk("vcpu_id %d timer %d",
+		  __entry->vcpu_id, __entry->timer_index)
+);
+
 #endif /* _TRACE_KVM_H */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 44976a5..04d61d4 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -19,6 +19,7 @@
 #include "irq.h"
 #include "mmu.h"
 #include "cpuid.h"
+#include "lapic.h"
 
 #include <linux/kvm_host.h>
 #include <linux/module.h>
@@ -862,7 +863,6 @@
 static void kvm_cpu_vmxoff(void);
 static bool vmx_mpx_supported(void);
 static bool vmx_xsaves_supported(void);
-static int vmx_cpu_uses_apicv(struct kvm_vcpu *vcpu);
 static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr);
 static void vmx_set_segment(struct kvm_vcpu *vcpu,
 			    struct kvm_segment *var, int seg);
@@ -870,7 +870,6 @@
 			    struct kvm_segment *var, int seg);
 static bool guest_state_valid(struct kvm_vcpu *vcpu);
 static u32 vmx_segment_access_rights(struct kvm_segment *var);
-static void vmx_sync_pir_to_irr_dummy(struct kvm_vcpu *vcpu);
 static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx);
 static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx);
 static int alloc_identity_pagetable(struct kvm *kvm);
@@ -1448,7 +1447,51 @@
 	}
 }
 
-static __always_inline unsigned long vmcs_readl(unsigned long field)
+static __always_inline void vmcs_check16(unsigned long field)
+{
+        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2000,
+			 "16-bit accessor invalid for 64-bit field");
+        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2001,
+			 "16-bit accessor invalid for 64-bit high field");
+        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x4000,
+			 "16-bit accessor invalid for 32-bit high field");
+        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x6000,
+			 "16-bit accessor invalid for natural width field");
+}
+
+static __always_inline void vmcs_check32(unsigned long field)
+{
+        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0,
+			 "32-bit accessor invalid for 16-bit field");
+        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x6000,
+			 "32-bit accessor invalid for natural width field");
+}
+
+static __always_inline void vmcs_check64(unsigned long field)
+{
+        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0,
+			 "64-bit accessor invalid for 16-bit field");
+        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2001,
+			 "64-bit accessor invalid for 64-bit high field");
+        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x4000,
+			 "64-bit accessor invalid for 32-bit field");
+        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x6000,
+			 "64-bit accessor invalid for natural width field");
+}
+
+static __always_inline void vmcs_checkl(unsigned long field)
+{
+        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0,
+			 "Natural width accessor invalid for 16-bit field");
+        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2000,
+			 "Natural width accessor invalid for 64-bit field");
+        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2001,
+			 "Natural width accessor invalid for 64-bit high field");
+        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x4000,
+			 "Natural width accessor invalid for 32-bit field");
+}
+
+static __always_inline unsigned long __vmcs_readl(unsigned long field)
 {
 	unsigned long value;
 
@@ -1459,23 +1502,32 @@
 
 static __always_inline u16 vmcs_read16(unsigned long field)
 {
-	return vmcs_readl(field);
+	vmcs_check16(field);
+	return __vmcs_readl(field);
 }
 
 static __always_inline u32 vmcs_read32(unsigned long field)
 {
-	return vmcs_readl(field);
+	vmcs_check32(field);
+	return __vmcs_readl(field);
 }
 
 static __always_inline u64 vmcs_read64(unsigned long field)
 {
+	vmcs_check64(field);
 #ifdef CONFIG_X86_64
-	return vmcs_readl(field);
+	return __vmcs_readl(field);
 #else
-	return vmcs_readl(field) | ((u64)vmcs_readl(field+1) << 32);
+	return __vmcs_readl(field) | ((u64)__vmcs_readl(field+1) << 32);
 #endif
 }
 
+static __always_inline unsigned long vmcs_readl(unsigned long field)
+{
+	vmcs_checkl(field);
+	return __vmcs_readl(field);
+}
+
 static noinline void vmwrite_error(unsigned long field, unsigned long value)
 {
 	printk(KERN_ERR "vmwrite error: reg %lx value %lx (err %d)\n",
@@ -1483,7 +1535,7 @@
 	dump_stack();
 }
 
-static void vmcs_writel(unsigned long field, unsigned long value)
+static __always_inline void __vmcs_writel(unsigned long field, unsigned long value)
 {
 	u8 error;
 
@@ -1493,33 +1545,46 @@
 		vmwrite_error(field, value);
 }
 
-static void vmcs_write16(unsigned long field, u16 value)
+static __always_inline void vmcs_write16(unsigned long field, u16 value)
 {
-	vmcs_writel(field, value);
+	vmcs_check16(field);
+	__vmcs_writel(field, value);
 }
 
-static void vmcs_write32(unsigned long field, u32 value)
+static __always_inline void vmcs_write32(unsigned long field, u32 value)
 {
-	vmcs_writel(field, value);
+	vmcs_check32(field);
+	__vmcs_writel(field, value);
 }
 
-static void vmcs_write64(unsigned long field, u64 value)
+static __always_inline void vmcs_write64(unsigned long field, u64 value)
 {
-	vmcs_writel(field, value);
+	vmcs_check64(field);
+	__vmcs_writel(field, value);
 #ifndef CONFIG_X86_64
 	asm volatile ("");
-	vmcs_writel(field+1, value >> 32);
+	__vmcs_writel(field+1, value >> 32);
 #endif
 }
 
-static void vmcs_clear_bits(unsigned long field, u32 mask)
+static __always_inline void vmcs_writel(unsigned long field, unsigned long value)
 {
-	vmcs_writel(field, vmcs_readl(field) & ~mask);
+	vmcs_checkl(field);
+	__vmcs_writel(field, value);
 }
 
-static void vmcs_set_bits(unsigned long field, u32 mask)
+static __always_inline void vmcs_clear_bits(unsigned long field, u32 mask)
 {
-	vmcs_writel(field, vmcs_readl(field) | mask);
+        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x2000,
+			 "vmcs_clear_bits does not support 64-bit fields");
+	__vmcs_writel(field, __vmcs_readl(field) & ~mask);
+}
+
+static __always_inline void vmcs_set_bits(unsigned long field, u32 mask)
+{
+        BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x2000,
+			 "vmcs_set_bits does not support 64-bit fields");
+	__vmcs_writel(field, __vmcs_readl(field) | mask);
 }
 
 static inline void vm_entry_controls_init(struct vcpu_vmx *vmx, u32 val)
@@ -2498,7 +2563,7 @@
 	vmx->nested.nested_vmx_pinbased_ctls_high |=
 		PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR |
 		PIN_BASED_VMX_PREEMPTION_TIMER;
-	if (vmx_cpu_uses_apicv(&vmx->vcpu))
+	if (kvm_vcpu_apicv_active(&vmx->vcpu))
 		vmx->nested.nested_vmx_pinbased_ctls_high |=
 			PIN_BASED_POSTED_INTR;
 
@@ -4462,9 +4527,9 @@
 			msr, MSR_TYPE_W);
 }
 
-static int vmx_cpu_uses_apicv(struct kvm_vcpu *vcpu)
+static bool vmx_get_enable_apicv(void)
 {
-	return enable_apicv && lapic_in_kernel(vcpu);
+	return enable_apicv;
 }
 
 static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
@@ -4586,11 +4651,6 @@
 	kvm_apic_update_irr(vcpu, vmx->pi_desc.pir);
 }
 
-static void vmx_sync_pir_to_irr_dummy(struct kvm_vcpu *vcpu)
-{
-	return;
-}
-
 /*
  * Set up the vmcs's constant host-state fields, i.e., host-state fields that
  * will not change in the lifetime of the guest.
@@ -4660,11 +4720,18 @@
 {
 	u32 pin_based_exec_ctrl = vmcs_config.pin_based_exec_ctrl;
 
-	if (!vmx_cpu_uses_apicv(&vmx->vcpu))
+	if (!kvm_vcpu_apicv_active(&vmx->vcpu))
 		pin_based_exec_ctrl &= ~PIN_BASED_POSTED_INTR;
 	return pin_based_exec_ctrl;
 }
 
+static void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, vmx_pin_based_exec_ctrl(vmx));
+}
+
 static u32 vmx_exec_control(struct vcpu_vmx *vmx)
 {
 	u32 exec_control = vmcs_config.cpu_based_exec_ctrl;
@@ -4703,7 +4770,7 @@
 		exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST;
 	if (!ple_gap)
 		exec_control &= ~SECONDARY_EXEC_PAUSE_LOOP_EXITING;
-	if (!vmx_cpu_uses_apicv(&vmx->vcpu))
+	if (!kvm_vcpu_apicv_active(&vmx->vcpu))
 		exec_control &= ~(SECONDARY_EXEC_APIC_REGISTER_VIRT |
 				  SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY);
 	exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
@@ -4767,7 +4834,7 @@
 		vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
 				vmx_secondary_exec_control(vmx));
 
-	if (vmx_cpu_uses_apicv(&vmx->vcpu)) {
+	if (kvm_vcpu_apicv_active(&vmx->vcpu)) {
 		vmcs_write64(EOI_EXIT_BITMAP0, 0);
 		vmcs_write64(EOI_EXIT_BITMAP1, 0);
 		vmcs_write64(EOI_EXIT_BITMAP2, 0);
@@ -4775,7 +4842,7 @@
 
 		vmcs_write16(GUEST_INTR_STATUS, 0);
 
-		vmcs_write64(POSTED_INTR_NV, POSTED_INTR_VECTOR);
+		vmcs_write16(POSTED_INTR_NV, POSTED_INTR_VECTOR);
 		vmcs_write64(POSTED_INTR_DESC_ADDR, __pa((&vmx->pi_desc)));
 	}
 
@@ -4867,7 +4934,7 @@
 
 	seg_setup(VCPU_SREG_CS);
 	vmcs_write16(GUEST_CS_SELECTOR, 0xf000);
-	vmcs_write32(GUEST_CS_BASE, 0xffff0000);
+	vmcs_writel(GUEST_CS_BASE, 0xffff0000ul);
 
 	seg_setup(VCPU_SREG_DS);
 	seg_setup(VCPU_SREG_ES);
@@ -4903,7 +4970,7 @@
 
 	vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE);
 	vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, 0);
-	vmcs_write32(GUEST_PENDING_DBG_EXCEPTIONS, 0);
+	vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, 0);
 
 	setup_msrs(vmx);
 
@@ -4919,7 +4986,7 @@
 
 	kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu);
 
-	if (vmx_cpu_uses_apicv(vcpu))
+	if (kvm_vcpu_apicv_active(vcpu))
 		memset(&vmx->pi_desc, 0, sizeof(struct pi_desc));
 
 	if (vmx->vpid != 0)
@@ -6203,15 +6270,6 @@
 		kvm_tsc_scaling_ratio_frac_bits = 48;
 	}
 
-	if (enable_apicv)
-		kvm_x86_ops->update_cr8_intercept = NULL;
-	else {
-		kvm_x86_ops->hwapic_irr_update = NULL;
-		kvm_x86_ops->hwapic_isr_update = NULL;
-		kvm_x86_ops->deliver_posted_interrupt = NULL;
-		kvm_x86_ops->sync_pir_to_irr = vmx_sync_pir_to_irr_dummy;
-	}
-
 	vmx_disable_intercept_for_msr(MSR_FS_BASE, false);
 	vmx_disable_intercept_for_msr(MSR_GS_BASE, false);
 	vmx_disable_intercept_for_msr(MSR_KERNEL_GS_BASE, true);
@@ -7901,7 +7959,7 @@
 	u32 pin_based_exec_ctrl = vmcs_read32(PIN_BASED_VM_EXEC_CONTROL);
 	u32 secondary_exec_control = 0;
 	unsigned long cr4 = vmcs_readl(GUEST_CR4);
-	u64 efer = vmcs_readl(GUEST_IA32_EFER);
+	u64 efer = vmcs_read64(GUEST_IA32_EFER);
 	int i, n;
 
 	if (cpu_has_secondary_exec_ctrls())
@@ -7917,10 +7975,10 @@
 	if ((secondary_exec_control & SECONDARY_EXEC_ENABLE_EPT) &&
 	    (cr4 & X86_CR4_PAE) && !(efer & EFER_LMA))
 	{
-		pr_err("PDPTR0 = 0x%016lx  PDPTR1 = 0x%016lx\n",
-		       vmcs_readl(GUEST_PDPTR0), vmcs_readl(GUEST_PDPTR1));
-		pr_err("PDPTR2 = 0x%016lx  PDPTR3 = 0x%016lx\n",
-		       vmcs_readl(GUEST_PDPTR2), vmcs_readl(GUEST_PDPTR3));
+		pr_err("PDPTR0 = 0x%016llx  PDPTR1 = 0x%016llx\n",
+		       vmcs_read64(GUEST_PDPTR0), vmcs_read64(GUEST_PDPTR1));
+		pr_err("PDPTR2 = 0x%016llx  PDPTR3 = 0x%016llx\n",
+		       vmcs_read64(GUEST_PDPTR2), vmcs_read64(GUEST_PDPTR3));
 	}
 	pr_err("RSP = 0x%016lx  RIP = 0x%016lx\n",
 	       vmcs_readl(GUEST_RSP), vmcs_readl(GUEST_RIP));
@@ -7941,16 +7999,16 @@
 	vmx_dump_sel("TR:  ", GUEST_TR_SELECTOR);
 	if ((vmexit_ctl & (VM_EXIT_SAVE_IA32_PAT | VM_EXIT_SAVE_IA32_EFER)) ||
 	    (vmentry_ctl & (VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_LOAD_IA32_EFER)))
-		pr_err("EFER =     0x%016llx  PAT = 0x%016lx\n",
-		       efer, vmcs_readl(GUEST_IA32_PAT));
-	pr_err("DebugCtl = 0x%016lx  DebugExceptions = 0x%016lx\n",
-	       vmcs_readl(GUEST_IA32_DEBUGCTL),
+		pr_err("EFER =     0x%016llx  PAT = 0x%016llx\n",
+		       efer, vmcs_read64(GUEST_IA32_PAT));
+	pr_err("DebugCtl = 0x%016llx  DebugExceptions = 0x%016lx\n",
+	       vmcs_read64(GUEST_IA32_DEBUGCTL),
 	       vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS));
 	if (vmentry_ctl & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL)
-		pr_err("PerfGlobCtl = 0x%016lx\n",
-		       vmcs_readl(GUEST_IA32_PERF_GLOBAL_CTRL));
+		pr_err("PerfGlobCtl = 0x%016llx\n",
+		       vmcs_read64(GUEST_IA32_PERF_GLOBAL_CTRL));
 	if (vmentry_ctl & VM_ENTRY_LOAD_BNDCFGS)
-		pr_err("BndCfgS = 0x%016lx\n", vmcs_readl(GUEST_BNDCFGS));
+		pr_err("BndCfgS = 0x%016llx\n", vmcs_read64(GUEST_BNDCFGS));
 	pr_err("Interruptibility = %08x  ActivityState = %08x\n",
 	       vmcs_read32(GUEST_INTERRUPTIBILITY_INFO),
 	       vmcs_read32(GUEST_ACTIVITY_STATE));
@@ -7979,11 +8037,12 @@
 	       vmcs_read32(HOST_IA32_SYSENTER_CS),
 	       vmcs_readl(HOST_IA32_SYSENTER_EIP));
 	if (vmexit_ctl & (VM_EXIT_LOAD_IA32_PAT | VM_EXIT_LOAD_IA32_EFER))
-		pr_err("EFER = 0x%016lx  PAT = 0x%016lx\n",
-		       vmcs_readl(HOST_IA32_EFER), vmcs_readl(HOST_IA32_PAT));
+		pr_err("EFER = 0x%016llx  PAT = 0x%016llx\n",
+		       vmcs_read64(HOST_IA32_EFER),
+		       vmcs_read64(HOST_IA32_PAT));
 	if (vmexit_ctl & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL)
-		pr_err("PerfGlobCtl = 0x%016lx\n",
-		       vmcs_readl(HOST_IA32_PERF_GLOBAL_CTRL));
+		pr_err("PerfGlobCtl = 0x%016llx\n",
+		       vmcs_read64(HOST_IA32_PERF_GLOBAL_CTRL));
 
 	pr_err("*** Control State ***\n");
 	pr_err("PinBased=%08x CPUBased=%08x SecondaryExec=%08x\n",
@@ -8006,16 +8065,16 @@
 	pr_err("IDTVectoring: info=%08x errcode=%08x\n",
 	       vmcs_read32(IDT_VECTORING_INFO_FIELD),
 	       vmcs_read32(IDT_VECTORING_ERROR_CODE));
-	pr_err("TSC Offset = 0x%016lx\n", vmcs_readl(TSC_OFFSET));
+	pr_err("TSC Offset = 0x%016llx\n", vmcs_read64(TSC_OFFSET));
 	if (secondary_exec_control & SECONDARY_EXEC_TSC_SCALING)
-		pr_err("TSC Multiplier = 0x%016lx\n",
-		       vmcs_readl(TSC_MULTIPLIER));
+		pr_err("TSC Multiplier = 0x%016llx\n",
+		       vmcs_read64(TSC_MULTIPLIER));
 	if (cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW)
 		pr_err("TPR Threshold = 0x%02x\n", vmcs_read32(TPR_THRESHOLD));
 	if (pin_based_exec_ctrl & PIN_BASED_POSTED_INTR)
 		pr_err("PostedIntrVec = 0x%02x\n", vmcs_read16(POSTED_INTR_NV));
 	if ((secondary_exec_control & SECONDARY_EXEC_ENABLE_EPT))
-		pr_err("EPT pointer = 0x%016lx\n", vmcs_readl(EPT_POINTER));
+		pr_err("EPT pointer = 0x%016llx\n", vmcs_read64(EPT_POINTER));
 	n = vmcs_read32(CR3_TARGET_COUNT);
 	for (i = 0; i + 1 < n; i += 4)
 		pr_err("CR3 target%u=%016lx target%u=%016lx\n",
@@ -8154,7 +8213,7 @@
 	 * apicv
 	 */
 	if (!cpu_has_vmx_virtualize_x2apic_mode() ||
-				!vmx_cpu_uses_apicv(vcpu))
+				!kvm_vcpu_apicv_active(vcpu))
 		return;
 
 	if (!cpu_need_tpr_shadow(vcpu))
@@ -8259,10 +8318,9 @@
 	}
 }
 
-static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu)
+static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
 {
-	u64 *eoi_exit_bitmap = vcpu->arch.eoi_exit_bitmap;
-	if (!vmx_cpu_uses_apicv(vcpu))
+	if (!kvm_vcpu_apicv_active(vcpu))
 		return;
 
 	vmcs_write64(EOI_EXIT_BITMAP0, eoi_exit_bitmap[0]);
@@ -8932,7 +8990,8 @@
 			best->ebx &= ~bit(X86_FEATURE_INVPCID);
 	}
 
-	vmcs_set_secondary_exec_control(secondary_exec_ctl);
+	if (cpu_has_secondary_exec_ctrls())
+		vmcs_set_secondary_exec_control(secondary_exec_ctl);
 
 	if (static_cpu_has(X86_FEATURE_PCOMMIT) && nested) {
 		if (guest_cpuid_has_pcommit(vcpu))
@@ -9508,7 +9567,7 @@
 		 */
 		vmx->nested.posted_intr_nv = vmcs12->posted_intr_nv;
 		vmx->nested.pi_pending = false;
-		vmcs_write64(POSTED_INTR_NV, POSTED_INTR_VECTOR);
+		vmcs_write16(POSTED_INTR_NV, POSTED_INTR_VECTOR);
 		vmcs_write64(POSTED_INTR_DESC_ADDR,
 			page_to_phys(vmx->nested.pi_desc_page) +
 			(unsigned long)(vmcs12->posted_intr_desc_addr &
@@ -10169,7 +10228,7 @@
 	 * Additionally, restore L2's PDPTR to vmcs12.
 	 */
 	if (enable_ept) {
-		vmcs12->guest_cr3 = vmcs_read64(GUEST_CR3);
+		vmcs12->guest_cr3 = vmcs_readl(GUEST_CR3);
 		vmcs12->guest_pdptr0 = vmcs_read64(GUEST_PDPTR0);
 		vmcs12->guest_pdptr1 = vmcs_read64(GUEST_PDPTR1);
 		vmcs12->guest_pdptr2 = vmcs_read64(GUEST_PDPTR2);
@@ -10805,7 +10864,8 @@
 	.update_cr8_intercept = update_cr8_intercept,
 	.set_virtual_x2apic_mode = vmx_set_virtual_x2apic_mode,
 	.set_apic_access_page_addr = vmx_set_apic_access_page_addr,
-	.cpu_uses_apicv = vmx_cpu_uses_apicv,
+	.get_enable_apicv = vmx_get_enable_apicv,
+	.refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl,
 	.load_eoi_exitmap = vmx_load_eoi_exitmap,
 	.hwapic_irr_update = vmx_hwapic_irr_update,
 	.hwapic_isr_update = vmx_hwapic_isr_update,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 7ffc224..f53f5b1 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -951,7 +951,7 @@
 	MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR,
 #endif
 	MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA,
-	MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS
+	MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS, MSR_TSC_AUX,
 };
 
 static unsigned num_msrs_to_save;
@@ -966,6 +966,8 @@
 	HV_X64_MSR_RESET,
 	HV_X64_MSR_VP_INDEX,
 	HV_X64_MSR_VP_RUNTIME,
+	HV_X64_MSR_SCONTROL,
+	HV_X64_MSR_STIMER0_CONFIG,
 	HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME,
 	MSR_KVM_PV_EOI_EN,
 
@@ -1167,7 +1169,8 @@
 
 	++version;
 
-	kvm_write_guest(kvm, wall_clock, &version, sizeof(version));
+	if (kvm_write_guest(kvm, wall_clock, &version, sizeof(version)))
+		return;
 
 	/*
 	 * The guest calculates current wall clock time by adding
@@ -1683,6 +1686,11 @@
 #endif
 }
 
+void kvm_make_mclock_inprogress_request(struct kvm *kvm)
+{
+	kvm_make_all_cpus_request(kvm, KVM_REQ_MCLOCK_INPROGRESS);
+}
+
 static void kvm_gen_update_masterclock(struct kvm *kvm)
 {
 #ifdef CONFIG_X86_64
@@ -2198,6 +2206,7 @@
 	case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
 	case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
 	case HV_X64_MSR_CRASH_CTL:
+	case HV_X64_MSR_STIMER0_CONFIG ... HV_X64_MSR_STIMER3_COUNT:
 		return kvm_hv_set_msr_common(vcpu, msr, data,
 					     msr_info->host_initiated);
 	case MSR_IA32_BBL_CR_CTL3:
@@ -2402,6 +2411,7 @@
 	case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
 	case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
 	case HV_X64_MSR_CRASH_CTL:
+	case HV_X64_MSR_STIMER0_CONFIG ... HV_X64_MSR_STIMER3_COUNT:
 		return kvm_hv_get_msr_common(vcpu,
 					     msr_info->index, &msr_info->data);
 		break;
@@ -2541,6 +2551,7 @@
 	case KVM_CAP_HYPERV:
 	case KVM_CAP_HYPERV_VAPIC:
 	case KVM_CAP_HYPERV_SPIN:
+	case KVM_CAP_HYPERV_SYNIC:
 	case KVM_CAP_PCI_SEGMENT:
 	case KVM_CAP_DEBUGREGS:
 	case KVM_CAP_X86_ROBUST_SINGLESTEP:
@@ -2693,6 +2704,11 @@
 	return kvm_arch_has_noncoherent_dma(vcpu->kvm);
 }
 
+static inline void kvm_migrate_timers(struct kvm_vcpu *vcpu)
+{
+	set_bit(KVM_REQ_MIGRATE_TIMER, &vcpu->requests);
+}
+
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	/* Address WBINVD may be executed by guest */
@@ -2748,7 +2764,9 @@
 static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu,
 				    struct kvm_lapic_state *s)
 {
-	kvm_x86_ops->sync_pir_to_irr(vcpu);
+	if (vcpu->arch.apicv_active)
+		kvm_x86_ops->sync_pir_to_irr(vcpu);
+
 	memcpy(s->regs, vcpu->arch.apic->regs, sizeof *s);
 
 	return 0;
@@ -3191,6 +3209,20 @@
 	return 0;
 }
 
+static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
+				     struct kvm_enable_cap *cap)
+{
+	if (cap->flags)
+		return -EINVAL;
+
+	switch (cap->cap) {
+	case KVM_CAP_HYPERV_SYNIC:
+		return kvm_hv_activate_synic(vcpu);
+	default:
+		return -EINVAL;
+	}
+}
+
 long kvm_arch_vcpu_ioctl(struct file *filp,
 			 unsigned int ioctl, unsigned long arg)
 {
@@ -3455,6 +3487,15 @@
 		r = kvm_set_guest_paused(vcpu);
 		goto out;
 	}
+	case KVM_ENABLE_CAP: {
+		struct kvm_enable_cap cap;
+
+		r = -EFAULT;
+		if (copy_from_user(&cap, argp, sizeof(cap)))
+			goto out;
+		r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap);
+		break;
+	}
 	default:
 		r = -EINVAL;
 	}
@@ -3606,7 +3647,8 @@
 	       sizeof(kvm->arch.vpit->pit_state.channels));
 	kvm->arch.vpit->pit_state.flags = ps->flags;
 	for (i = 0; i < 3; i++)
-		kvm_pit_load_count(kvm, i, kvm->arch.vpit->pit_state.channels[i].count, start);
+		kvm_pit_load_count(kvm, i, kvm->arch.vpit->pit_state.channels[i].count,
+				   start && i == 0);
 	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
 	return 0;
 }
@@ -4005,16 +4047,17 @@
 
 		/*
 		 * Even MSRs that are valid in the host may not be exposed
-		 * to the guests in some cases.  We could work around this
-		 * in VMX with the generic MSR save/load machinery, but it
-		 * is not really worthwhile since it will really only
-		 * happen with nested virtualization.
+		 * to the guests in some cases.
 		 */
 		switch (msrs_to_save[i]) {
 		case MSR_IA32_BNDCFGS:
 			if (!kvm_x86_ops->mpx_supported())
 				continue;
 			break;
+		case MSR_TSC_AUX:
+			if (!kvm_x86_ops->rdtscp_supported())
+				continue;
+			break;
 		default:
 			break;
 		}
@@ -5871,6 +5914,12 @@
 	kvm_irq_delivery_to_apic(kvm, NULL, &lapic_irq, NULL);
 }
 
+void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.apicv_active = false;
+	kvm_x86_ops->refresh_apicv_exec_ctrl(vcpu);
+}
+
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 {
 	unsigned long nr, a0, a1, a2, a3, ret;
@@ -5964,6 +6013,9 @@
 	if (!vcpu->arch.apic)
 		return;
 
+	if (vcpu->arch.apicv_active)
+		return;
+
 	if (!vcpu->arch.apic->vapic_addr)
 		max_irr = kvm_lapic_find_highest_irr(vcpu);
 	else
@@ -6300,20 +6352,30 @@
 	kvm_mmu_reset_context(vcpu);
 }
 
+void kvm_make_scan_ioapic_request(struct kvm *kvm)
+{
+	kvm_make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC);
+}
+
 static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
 {
+	u64 eoi_exit_bitmap[4];
+
 	if (!kvm_apic_hw_enabled(vcpu->arch.apic))
 		return;
 
-	memset(vcpu->arch.eoi_exit_bitmap, 0, 256 / 8);
+	bitmap_zero(vcpu->arch.ioapic_handled_vectors, 256);
 
 	if (irqchip_split(vcpu->kvm))
-		kvm_scan_ioapic_routes(vcpu, vcpu->arch.eoi_exit_bitmap);
+		kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors);
 	else {
-		kvm_x86_ops->sync_pir_to_irr(vcpu);
-		kvm_ioapic_scan_entry(vcpu, vcpu->arch.eoi_exit_bitmap);
+		if (vcpu->arch.apicv_active)
+			kvm_x86_ops->sync_pir_to_irr(vcpu);
+		kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors);
 	}
-	kvm_x86_ops->load_eoi_exitmap(vcpu);
+	bitmap_or((ulong *)eoi_exit_bitmap, vcpu->arch.ioapic_handled_vectors,
+		  vcpu_to_synic(vcpu)->vec_bitmap, 256);
+	kvm_x86_ops->load_eoi_exitmap(vcpu, eoi_exit_bitmap);
 }
 
 static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu)
@@ -6421,7 +6483,7 @@
 		if (kvm_check_request(KVM_REQ_IOAPIC_EOI_EXIT, vcpu)) {
 			BUG_ON(vcpu->arch.pending_ioapic_eoi > 255);
 			if (test_bit(vcpu->arch.pending_ioapic_eoi,
-				     (void *) vcpu->arch.eoi_exit_bitmap)) {
+				     vcpu->arch.ioapic_handled_vectors)) {
 				vcpu->run->exit_reason = KVM_EXIT_IOAPIC_EOI;
 				vcpu->run->eoi.vector =
 						vcpu->arch.pending_ioapic_eoi;
@@ -6445,6 +6507,20 @@
 			r = 0;
 			goto out;
 		}
+		if (kvm_check_request(KVM_REQ_HV_EXIT, vcpu)) {
+			vcpu->run->exit_reason = KVM_EXIT_HYPERV;
+			vcpu->run->hyperv = vcpu->arch.hyperv.exit;
+			r = 0;
+			goto out;
+		}
+
+		/*
+		 * KVM_REQ_HV_STIMER has to be processed after
+		 * KVM_REQ_CLOCK_UPDATE, because Hyper-V SynIC timers
+		 * depend on the guest clock being up-to-date
+		 */
+		if (kvm_check_request(KVM_REQ_HV_STIMER, vcpu))
+			kvm_hv_process_stimers(vcpu);
 	}
 
 	/*
@@ -6456,7 +6532,7 @@
 		 * Update architecture specific hints for APIC
 		 * virtual interrupt delivery.
 		 */
-		if (kvm_x86_ops->hwapic_irr_update)
+		if (vcpu->arch.apicv_active)
 			kvm_x86_ops->hwapic_irr_update(vcpu,
 				kvm_lapic_find_highest_irr(vcpu));
 	}
@@ -7527,6 +7603,7 @@
 	BUG_ON(vcpu->kvm == NULL);
 	kvm = vcpu->kvm;
 
+	vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv();
 	vcpu->arch.pv.pv_unhalted = false;
 	vcpu->arch.emulate_ctxt.ops = &emulate_ops;
 	if (!irqchip_in_kernel(kvm) || kvm_vcpu_is_reset_bsp(vcpu))
@@ -7584,6 +7661,8 @@
 
 	vcpu->arch.pending_external_vector = -1;
 
+	kvm_hv_vcpu_init(vcpu);
+
 	return 0;
 
 fail_free_mce_banks:
@@ -7602,6 +7681,7 @@
 {
 	int idx;
 
+	kvm_hv_vcpu_uninit(vcpu);
 	kvm_pmu_destroy(vcpu);
 	kfree(vcpu->arch.mce_banks);
 	kvm_free_lapic(vcpu);
@@ -7996,6 +8076,9 @@
 	    kvm_cpu_has_interrupt(vcpu))
 		return true;
 
+	if (kvm_hv_has_stimer_pending(vcpu))
+		return true;
+
 	return false;
 }
 
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index a0d09f6..4ba229a 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -1414,6 +1414,7 @@
 	pv_info.kernel_rpl = 1;
 	/* Everyone except Xen runs with this set. */
 	pv_info.shared_kernel_pmd = 1;
+	pv_info.features = 0;
 
 	/*
 	 * We set up all the lguest overrides for sensitive operations.  These
@@ -1472,7 +1473,6 @@
 	pv_mmu_ops.lazy_mode.leave = lguest_leave_lazy_mmu_mode;
 	pv_mmu_ops.lazy_mode.flush = paravirt_flush_lazy_mmu;
 	pv_mmu_ops.pte_update = lguest_pte_update;
-	pv_mmu_ops.pte_update_defer = lguest_pte_update;
 
 #ifdef CONFIG_X86_LOCAL_APIC
 	/* APIC read/write intercepts */
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index f258788..a501fa2 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -16,7 +16,7 @@
 
 obj-$(CONFIG_SMP) += msr-smp.o cache-smp.o
 
-lib-y := delay.o misc.o cmdline.o
+lib-y := delay.o misc.o cmdline.o cpu.o
 lib-y += usercopy_$(BITS).o usercopy.o getuser.o putuser.o
 lib-y += memcpy_$(BITS).o
 lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
diff --git a/arch/x86/lib/cpu.c b/arch/x86/lib/cpu.c
new file mode 100644
index 0000000..aa417a9
--- /dev/null
+++ b/arch/x86/lib/cpu.c
@@ -0,0 +1,35 @@
+#include <linux/module.h>
+
+unsigned int x86_family(unsigned int sig)
+{
+	unsigned int x86;
+
+	x86 = (sig >> 8) & 0xf;
+
+	if (x86 == 0xf)
+		x86 += (sig >> 20) & 0xff;
+
+	return x86;
+}
+EXPORT_SYMBOL_GPL(x86_family);
+
+unsigned int x86_model(unsigned int sig)
+{
+	unsigned int fam, model;
+
+	 fam = x86_family(sig);
+
+	model = (sig >> 4) & 0xf;
+
+	if (fam >= 0x6)
+		model += ((sig >> 16) & 0xf) << 4;
+
+	return model;
+}
+EXPORT_SYMBOL_GPL(x86_model);
+
+unsigned int x86_stepping(unsigned int sig)
+{
+	return sig & 0xf;
+}
+EXPORT_SYMBOL_GPL(x86_stepping);
diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c
index 4362373..004c861 100644
--- a/arch/x86/lib/msr.c
+++ b/arch/x86/lib/msr.c
@@ -1,6 +1,8 @@
 #include <linux/module.h>
 #include <linux/preempt.h>
 #include <asm/msr.h>
+#define CREATE_TRACE_POINTS
+#include <asm/msr-trace.h>
 
 struct msr *msrs_alloc(void)
 {
@@ -108,3 +110,27 @@
 {
 	return __flip_bit(msr, bit, false);
 }
+
+#ifdef CONFIG_TRACEPOINTS
+void do_trace_write_msr(unsigned msr, u64 val, int failed)
+{
+	trace_write_msr(msr, val, failed);
+}
+EXPORT_SYMBOL(do_trace_write_msr);
+EXPORT_TRACEPOINT_SYMBOL(write_msr);
+
+void do_trace_read_msr(unsigned msr, u64 val, int failed)
+{
+	trace_read_msr(msr, val, failed);
+}
+EXPORT_SYMBOL(do_trace_read_msr);
+EXPORT_TRACEPOINT_SYMBOL(read_msr);
+
+void do_trace_rdpmc(unsigned counter, u64 val, int failed)
+{
+	trace_rdpmc(counter, val, failed);
+}
+EXPORT_SYMBOL(do_trace_rdpmc);
+EXPORT_TRACEPOINT_SYMBOL(rdpmc);
+
+#endif
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 65c47fd..f9d38a4 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -15,6 +15,7 @@
 
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
 obj-$(CONFIG_X86_PTDUMP_CORE)	+= dump_pagetables.o
+obj-$(CONFIG_X86_PTDUMP)	+= debug_pagetables.o
 
 obj-$(CONFIG_HIGHMEM)		+= highmem_32.o
 
diff --git a/arch/x86/mm/debug_pagetables.c b/arch/x86/mm/debug_pagetables.c
new file mode 100644
index 0000000..bfcffdf
--- /dev/null
+++ b/arch/x86/mm/debug_pagetables.c
@@ -0,0 +1,46 @@
+#include <linux/debugfs.h>
+#include <linux/module.h>
+#include <linux/seq_file.h>
+#include <asm/pgtable.h>
+
+static int ptdump_show(struct seq_file *m, void *v)
+{
+	ptdump_walk_pgd_level(m, NULL);
+	return 0;
+}
+
+static int ptdump_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, ptdump_show, NULL);
+}
+
+static const struct file_operations ptdump_fops = {
+	.owner		= THIS_MODULE,
+	.open		= ptdump_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static struct dentry *pe;
+
+static int __init pt_dump_debug_init(void)
+{
+	pe = debugfs_create_file("kernel_page_tables", S_IRUSR, NULL, NULL,
+				 &ptdump_fops);
+	if (!pe)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void __exit pt_dump_debug_exit(void)
+{
+	debugfs_remove_recursive(pe);
+}
+
+module_init(pt_dump_debug_init);
+module_exit(pt_dump_debug_exit);
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Arjan van de Ven <arjan@linux.intel.com>");
+MODULE_DESCRIPTION("Kernel debugging helper that dumps pagetables");
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index 0f1c6fc..4a6f1d9 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -426,38 +426,15 @@
 {
 	ptdump_walk_pgd_level_core(m, pgd, false);
 }
+EXPORT_SYMBOL_GPL(ptdump_walk_pgd_level);
 
 void ptdump_walk_pgd_level_checkwx(void)
 {
 	ptdump_walk_pgd_level_core(NULL, NULL, true);
 }
 
-#ifdef CONFIG_X86_PTDUMP
-static int ptdump_show(struct seq_file *m, void *v)
+static int __init pt_dump_init(void)
 {
-	ptdump_walk_pgd_level(m, NULL);
-	return 0;
-}
-
-static int ptdump_open(struct inode *inode, struct file *filp)
-{
-	return single_open(filp, ptdump_show, NULL);
-}
-
-static const struct file_operations ptdump_fops = {
-	.open		= ptdump_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-#endif
-
-static int pt_dump_init(void)
-{
-#ifdef CONFIG_X86_PTDUMP
-	struct dentry *pe;
-#endif
-
 #ifdef CONFIG_X86_32
 	/* Not a compile-time constant on x86-32 */
 	address_markers[VMALLOC_START_NR].start_address = VMALLOC_START;
@@ -468,13 +445,6 @@
 	address_markers[FIXADDR_START_NR].start_address = FIXADDR_START;
 #endif
 
-#ifdef CONFIG_X86_PTDUMP
-	pe = debugfs_create_file("kernel_page_tables", 0600, NULL, NULL,
-				 &ptdump_fops);
-	if (!pe)
-		return -ENOMEM;
-#endif
-
 	return 0;
 }
 
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index b9c78f3..0d8d53d 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -194,8 +194,8 @@
 	 * Check if the request spans more than any BAR in the iomem resource
 	 * tree.
 	 */
-	WARN_ONCE(iomem_map_sanity_check(unaligned_phys_addr, unaligned_size),
-		  KERN_INFO "Info: mapping multiple BARs. Your kernel is fine.");
+	if (iomem_map_sanity_check(unaligned_phys_addr, unaligned_size))
+		pr_warn("caller %pS mapping multiple BARs\n", caller);
 
 	return ret_addr;
 err_free_area:
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index a3137a4..6000ad7 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -129,14 +129,16 @@
  */
 void clflush_cache_range(void *vaddr, unsigned int size)
 {
-	unsigned long clflush_mask = boot_cpu_data.x86_clflush_size - 1;
+	const unsigned long clflush_size = boot_cpu_data.x86_clflush_size;
+	void *p = (void *)((unsigned long)vaddr & ~(clflush_size - 1));
 	void *vend = vaddr + size;
-	void *p;
+
+	if (p >= vend)
+		return;
 
 	mb();
 
-	for (p = (void *)((unsigned long)vaddr & ~clflush_mask);
-	     p < vend; p += boot_cpu_data.x86_clflush_size)
+	for (; p < vend; p += clflush_size)
 		clflushopt(p);
 
 	mb();
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 188e3e0..031782e 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -586,7 +586,7 @@
 	entry = rbt_memtype_erase(start, end);
 	spin_unlock(&memtype_lock);
 
-	if (!entry) {
+	if (IS_ERR(entry)) {
 		pr_info("x86/PAT: %s:%d freeing invalid memtype [mem %#010Lx-%#010Lx]\n",
 			current->comm, current->pid, start, end - 1);
 		return -EINVAL;
@@ -992,6 +992,16 @@
 	vma->vm_flags &= ~VM_PAT;
 }
 
+/*
+ * untrack_pfn_moved is called, while mremapping a pfnmap for a new region,
+ * with the old vma after its pfnmap page table has been removed.  The new
+ * vma has a new pfnmap to the same pfn & cache type with VM_PAT set.
+ */
+void untrack_pfn_moved(struct vm_area_struct *vma)
+{
+	vma->vm_flags &= ~VM_PAT;
+}
+
 pgprot_t pgprot_writecombine(pgprot_t prot)
 {
 	return __pgprot(pgprot_val(prot) |
diff --git a/arch/x86/mm/pat_rbtree.c b/arch/x86/mm/pat_rbtree.c
index 6393108..2f77022 100644
--- a/arch/x86/mm/pat_rbtree.c
+++ b/arch/x86/mm/pat_rbtree.c
@@ -98,8 +98,13 @@
 	return last_lower; /* Returns NULL if there is no overlap */
 }
 
-static struct memtype *memtype_rb_exact_match(struct rb_root *root,
-				u64 start, u64 end)
+enum {
+	MEMTYPE_EXACT_MATCH	= 0,
+	MEMTYPE_END_MATCH	= 1
+};
+
+static struct memtype *memtype_rb_match(struct rb_root *root,
+				u64 start, u64 end, int match_type)
 {
 	struct memtype *match;
 
@@ -107,7 +112,12 @@
 	while (match != NULL && match->start < end) {
 		struct rb_node *node;
 
-		if (match->start == start && match->end == end)
+		if ((match_type == MEMTYPE_EXACT_MATCH) &&
+		    (match->start == start) && (match->end == end))
+			return match;
+
+		if ((match_type == MEMTYPE_END_MATCH) &&
+		    (match->start < start) && (match->end == end))
 			return match;
 
 		node = rb_next(&match->rb);
@@ -117,7 +127,7 @@
 			match = NULL;
 	}
 
-	return NULL; /* Returns NULL if there is no exact match */
+	return NULL; /* Returns NULL if there is no match */
 }
 
 static int memtype_rb_check_conflict(struct rb_root *root,
@@ -210,12 +220,36 @@
 {
 	struct memtype *data;
 
-	data = memtype_rb_exact_match(&memtype_rbroot, start, end);
-	if (!data)
-		goto out;
+	/*
+	 * Since the memtype_rbroot tree allows overlapping ranges,
+	 * rbt_memtype_erase() checks with EXACT_MATCH first, i.e. free
+	 * a whole node for the munmap case.  If no such entry is found,
+	 * it then checks with END_MATCH, i.e. shrink the size of a node
+	 * from the end for the mremap case.
+	 */
+	data = memtype_rb_match(&memtype_rbroot, start, end,
+				MEMTYPE_EXACT_MATCH);
+	if (!data) {
+		data = memtype_rb_match(&memtype_rbroot, start, end,
+					MEMTYPE_END_MATCH);
+		if (!data)
+			return ERR_PTR(-EINVAL);
+	}
 
-	rb_erase_augmented(&data->rb, &memtype_rbroot, &memtype_rb_augment_cb);
-out:
+	if (data->start == start) {
+		/* munmap: erase this node */
+		rb_erase_augmented(&data->rb, &memtype_rbroot,
+					&memtype_rb_augment_cb);
+	} else {
+		/* mremap: update the end value of this node */
+		rb_erase_augmented(&data->rb, &memtype_rbroot,
+					&memtype_rb_augment_cb);
+		data->end = start;
+		data->subtree_max_end = data->end;
+		memtype_rb_insert(&memtype_rbroot, data);
+		return NULL;
+	}
+
 	return data;
 }
 
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index fb0a9dd..ee9c2e3 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -414,7 +414,7 @@
 
 	if (changed && dirty) {
 		*ptep = entry;
-		pte_update_defer(vma->vm_mm, address, ptep);
+		pte_update(vma->vm_mm, address, ptep);
 	}
 
 	return changed;
@@ -431,7 +431,6 @@
 
 	if (changed && dirty) {
 		*pmdp = entry;
-		pmd_update_defer(vma->vm_mm, address, pmdp);
 		/*
 		 * We had a write-protection fault here and changed the pmd
 		 * to to more permissive. No need to flush the TLB for that,
@@ -469,9 +468,6 @@
 		ret = test_and_clear_bit(_PAGE_BIT_ACCESSED,
 					 (unsigned long *)pmdp);
 
-	if (ret)
-		pmd_update(vma->vm_mm, addr, pmdp);
-
 	return ret;
 }
 #endif
@@ -518,7 +514,6 @@
 	set = !test_and_set_bit(_PAGE_BIT_SPLITTING,
 				(unsigned long *)pmdp);
 	if (set) {
-		pmd_update(vma->vm_mm, address, pmdp);
 		/* need tlb flush only to serialize against gup-fast */
 		flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
 	}
diff --git a/arch/x86/mm/setup_nx.c b/arch/x86/mm/setup_nx.c
index 90555bf..92e2eac 100644
--- a/arch/x86/mm/setup_nx.c
+++ b/arch/x86/mm/setup_nx.c
@@ -31,7 +31,7 @@
 
 void x86_configure_nx(void)
 {
-	if (cpu_has_nx && !disable_nx)
+	if (boot_cpu_has(X86_FEATURE_NX) && !disable_nx)
 		__supported_pte_mask |= _PAGE_NX;
 	else
 		__supported_pte_mask &= ~_PAGE_NX;
@@ -39,7 +39,7 @@
 
 void __init x86_report_nx(void)
 {
-	if (!cpu_has_nx) {
+	if (!boot_cpu_has(X86_FEATURE_NX)) {
 		printk(KERN_NOTICE "Notice: NX (Execute Disable) protection "
 		       "missing in CPU!\n");
 	} else {
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index c2aea63..b5f8218 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -203,6 +203,8 @@
 		pr_warn("SRAT: Failed to mark hotplug range [mem %#010Lx-%#010Lx] in memblock\n",
 			(unsigned long long)start, (unsigned long long)end - 1);
 
+	max_possible_pfn = max(max_possible_pfn, PFN_UP(end - 1));
+
 	return 0;
 out_err_bad_srat:
 	bad_srat();
diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c
index 327f21c..8dd8005 100644
--- a/arch/x86/platform/uv/uv_nmi.c
+++ b/arch/x86/platform/uv/uv_nmi.c
@@ -28,6 +28,7 @@
 #include <linux/nmi.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
+#include <linux/clocksource.h>
 
 #include <asm/apic.h>
 #include <asm/current.h>
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 9ab5279..d5f6499 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -23,6 +23,7 @@
 #include <asm/debugreg.h>
 #include <asm/cpu.h>
 #include <asm/mmu_context.h>
+#include <linux/dmi.h>
 
 #ifdef CONFIG_X86_32
 __visible unsigned long saved_context_ebx;
@@ -32,6 +33,29 @@
 #endif
 struct saved_context saved_context;
 
+static void msr_save_context(struct saved_context *ctxt)
+{
+	struct saved_msr *msr = ctxt->saved_msrs.array;
+	struct saved_msr *end = msr + ctxt->saved_msrs.num;
+
+	while (msr < end) {
+		msr->valid = !rdmsrl_safe(msr->info.msr_no, &msr->info.reg.q);
+		msr++;
+	}
+}
+
+static void msr_restore_context(struct saved_context *ctxt)
+{
+	struct saved_msr *msr = ctxt->saved_msrs.array;
+	struct saved_msr *end = msr + ctxt->saved_msrs.num;
+
+	while (msr < end) {
+		if (msr->valid)
+			wrmsrl(msr->info.msr_no, msr->info.reg.q);
+		msr++;
+	}
+}
+
 /**
  *	__save_processor_state - save CPU registers before creating a
  *		hibernation image and before restoring the memory state from it
@@ -111,6 +135,7 @@
 #endif
 	ctxt->misc_enable_saved = !rdmsrl_safe(MSR_IA32_MISC_ENABLE,
 					       &ctxt->misc_enable);
+	msr_save_context(ctxt);
 }
 
 /* Needed by apm.c */
@@ -229,6 +254,7 @@
 	x86_platform.restore_sched_clock_state();
 	mtrr_bp_restore();
 	perf_restore_debug_store();
+	msr_restore_context(ctxt);
 }
 
 /* Needed by apm.c */
@@ -320,3 +346,69 @@
 }
 
 core_initcall(bsp_pm_check_init);
+
+static int msr_init_context(const u32 *msr_id, const int total_num)
+{
+	int i = 0;
+	struct saved_msr *msr_array;
+
+	if (saved_context.saved_msrs.array || saved_context.saved_msrs.num > 0) {
+		pr_err("x86/pm: MSR quirk already applied, please check your DMI match table.\n");
+		return -EINVAL;
+	}
+
+	msr_array = kmalloc_array(total_num, sizeof(struct saved_msr), GFP_KERNEL);
+	if (!msr_array) {
+		pr_err("x86/pm: Can not allocate memory to save/restore MSRs during suspend.\n");
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < total_num; i++) {
+		msr_array[i].info.msr_no	= msr_id[i];
+		msr_array[i].valid		= false;
+		msr_array[i].info.reg.q		= 0;
+	}
+	saved_context.saved_msrs.num	= total_num;
+	saved_context.saved_msrs.array	= msr_array;
+
+	return 0;
+}
+
+/*
+ * The following section is a quirk framework for problematic BIOSen:
+ * Sometimes MSRs are modified by the BIOSen after suspended to
+ * RAM, this might cause unexpected behavior after wakeup.
+ * Thus we save/restore these specified MSRs across suspend/resume
+ * in order to work around it.
+ *
+ * For any further problematic BIOSen/platforms,
+ * please add your own function similar to msr_initialize_bdw.
+ */
+static int msr_initialize_bdw(const struct dmi_system_id *d)
+{
+	/* Add any extra MSR ids into this array. */
+	u32 bdw_msr_id[] = { MSR_IA32_THERM_CONTROL };
+
+	pr_info("x86/pm: %s detected, MSR saving is needed during suspending.\n", d->ident);
+	return msr_init_context(bdw_msr_id, ARRAY_SIZE(bdw_msr_id));
+}
+
+static struct dmi_system_id msr_save_dmi_table[] = {
+	{
+	 .callback = msr_initialize_bdw,
+	 .ident = "BROADWELL BDX_EP",
+	 .matches = {
+		DMI_MATCH(DMI_PRODUCT_NAME, "GRANTLEY"),
+		DMI_MATCH(DMI_PRODUCT_VERSION, "E63448-400"),
+		},
+	},
+	{}
+};
+
+static int pm_check_save_msr(void)
+{
+	dmi_check_system(msr_save_dmi_table);
+	return 0;
+}
+
+device_initcall(pm_check_save_msr);
diff --git a/arch/x86/um/Makefile b/arch/x86/um/Makefile
index a8fecc2..3ee2bb6 100644
--- a/arch/x86/um/Makefile
+++ b/arch/x86/um/Makefile
@@ -17,7 +17,7 @@
 ifeq ($(CONFIG_X86_32),y)
 
 obj-y += checksum_32.o
-obj-$(CONFIG_BINFMT_ELF) += elfcore.o
+obj-$(CONFIG_ELF_CORE) += elfcore.o
 
 subarch-y = ../lib/string_32.o ../lib/atomic64_32.o ../lib/atomic64_cx8_32.o
 subarch-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += ../lib/rwsem.o
diff --git a/arch/x86/um/asm/syscall.h b/arch/x86/um/asm/syscall.h
index 81d6562..11ab90d 100644
--- a/arch/x86/um/asm/syscall.h
+++ b/arch/x86/um/asm/syscall.h
@@ -1,6 +1,7 @@
 #ifndef __UM_ASM_SYSCALL_H
 #define __UM_ASM_SYSCALL_H
 
+#include <asm/syscall-generic.h>
 #include <uapi/linux/audit.h>
 
 typedef asmlinkage long (*sys_call_ptr_t)(unsigned long, unsigned long,
diff --git a/arch/x86/um/ptrace_32.c b/arch/x86/um/ptrace_32.c
index a29756f2..47c78d5 100644
--- a/arch/x86/um/ptrace_32.c
+++ b/arch/x86/um/ptrace_32.c
@@ -68,6 +68,7 @@
 	[EFL] = HOST_EFLAGS,
 	[UESP] = HOST_SP,
 	[SS] = HOST_SS,
+	[ORIG_EAX] = HOST_ORIG_AX,
 };
 
 int putreg(struct task_struct *child, int regno, unsigned long value)
@@ -83,6 +84,7 @@
 	case EAX:
 	case EIP:
 	case UESP:
+	case ORIG_EAX:
 		break;
 	case FS:
 		if (value && (value & 3) != 3)
@@ -108,9 +110,6 @@
 		value &= FLAG_MASK;
 		child->thread.regs.regs.gp[HOST_EFLAGS] |= value;
 		return 0;
-	case ORIG_EAX:
-		child->thread.regs.regs.syscall = value;
-		return 0;
 	default :
 		panic("Bad register in putreg() : %d\n", regno);
 	}
@@ -143,8 +142,6 @@
 
 	regno >>= 2;
 	switch (regno) {
-	case ORIG_EAX:
-		return child->thread.regs.regs.syscall;
 	case FS:
 	case GS:
 	case DS:
@@ -163,6 +160,7 @@
 	case EDI:
 	case EBP:
 	case EFL:
+	case ORIG_EAX:
 		break;
 	default:
 		panic("Bad register in getreg() : %d\n", regno);
diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c
index acda713..abf4901 100644
--- a/arch/x86/xen/apic.c
+++ b/arch/x86/xen/apic.c
@@ -64,7 +64,7 @@
 	if (reg != APIC_ID)
 		return 0;
 
-	ret = HYPERVISOR_dom0_op(&op);
+	ret = HYPERVISOR_platform_op(&op);
 	if (ret)
 		return 0;
 
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 5774800..d09e4c9 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -415,7 +415,7 @@
 
 	set_xen_guest_handle(op.u.set_pminfo.pdc, buf);
 
-	if ((HYPERVISOR_dom0_op(&op) == 0) &&
+	if ((HYPERVISOR_platform_op(&op) == 0) &&
 	    (buf[2] & (ACPI_PDC_C_C1_FFH | ACPI_PDC_C_C2C3_FFH))) {
 		cpuid_leaf5_ecx_val = cx;
 		cpuid_leaf5_edx_val = dx;
@@ -1192,7 +1192,7 @@
 #ifdef CONFIG_X86_64
 	.extra_user_64bit_cs = FLAT_USER_CS64,
 #endif
-
+	.features = 0,
 	.name = "Xen",
 };
 
@@ -1229,10 +1229,7 @@
 
 	.iret = xen_iret,
 #ifdef CONFIG_X86_64
-	.usergs_sysret32 = xen_sysret32,
 	.usergs_sysret64 = xen_sysret64,
-#else
-	.irq_enable_sysexit = xen_sysexit,
 #endif
 
 	.load_tr_desc = paravirt_nop,
@@ -1265,12 +1262,6 @@
 	.end_context_switch = xen_end_context_switch,
 };
 
-static const struct pv_apic_ops xen_apic_ops __initconst = {
-#ifdef CONFIG_X86_LOCAL_APIC
-	.startup_ipi_hook = paravirt_nop,
-#endif
-};
-
 static void xen_reboot(int reason)
 {
 	struct sched_shutdown r = { .reason = reason };
@@ -1374,7 +1365,7 @@
 		info->params.length = sizeof(info->params);
 		set_xen_guest_handle(op.u.firmware_info.u.disk_info.edd_params,
 				     &info->params);
-		ret = HYPERVISOR_dom0_op(&op);
+		ret = HYPERVISOR_platform_op(&op);
 		if (ret)
 			break;
 
@@ -1392,7 +1383,7 @@
 	op.u.firmware_info.type = XEN_FW_DISK_MBR_SIGNATURE;
 	for (nr = 0; nr < EDD_MBR_SIG_MAX; nr++) {
 		op.u.firmware_info.index = nr;
-		ret = HYPERVISOR_dom0_op(&op);
+		ret = HYPERVISOR_platform_op(&op);
 		if (ret)
 			break;
 		mbr_signature[nr] = op.u.firmware_info.u.disk_mbr_signature.mbr_signature;
@@ -1535,8 +1526,9 @@
 
 	/* Install Xen paravirt ops */
 	pv_info = xen_info;
+	if (xen_initial_domain())
+		pv_info.features |= PV_SUPPORTED_RTC;
 	pv_init_ops = xen_init_ops;
-	pv_apic_ops = xen_apic_ops;
 	if (!xen_pvh_domain()) {
 		pv_cpu_ops = xen_cpu_ops;
 
@@ -1698,7 +1690,7 @@
 		xen_start_info->console.domU.mfn = 0;
 		xen_start_info->console.domU.evtchn = 0;
 
-		if (HYPERVISOR_dom0_op(&op) == 0)
+		if (HYPERVISOR_platform_op(&op) == 0)
 			boot_params.kbd_status = op.u.firmware_info.u.kbd_shift_flags;
 
 		/* Make sure ACS will be enabled */
@@ -1886,8 +1878,10 @@
 
 static void xen_set_cpu_features(struct cpuinfo_x86 *c)
 {
-	if (xen_pv_domain())
+	if (xen_pv_domain()) {
 		clear_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS);
+		set_cpu_cap(c, X86_FEATURE_XENPV);
+	}
 }
 
 const struct hypervisor_x86 x86_hyper_xen = {
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index cb5e266..c913ca4 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -2436,7 +2436,6 @@
 	.flush_tlb_others = xen_flush_tlb_others,
 
 	.pte_update = paravirt_nop,
-	.pte_update_defer = paravirt_nop,
 
 	.pgd_alloc = xen_pgd_alloc,
 	.pgd_free = xen_pgd_free,
diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
index df0c405..7f664c4 100644
--- a/arch/x86/xen/suspend.c
+++ b/arch/x86/xen/suspend.c
@@ -34,7 +34,8 @@
 {
 #ifdef CONFIG_XEN_PVHVM
 	int cpu;
-	xen_hvm_init_shared_info();
+	if (!suspend_cancelled)
+	    xen_hvm_init_shared_info();
 	xen_callback_vector();
 	xen_unplug_emulated_devices();
 	if (xen_feature(XENFEAT_hvm_safe_pvclock)) {
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index f1ba6a0..a0a4e55 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -16,6 +16,7 @@
 #include <linux/gfp.h>
 #include <linux/slab.h>
 #include <linux/pvclock_gtod.h>
+#include <linux/timekeeper_internal.h>
 
 #include <asm/pvclock.h>
 #include <asm/xen/hypervisor.h>
@@ -32,86 +33,12 @@
 #define TIMER_SLOP	100000
 #define NS_PER_TICK	(1000000000LL / HZ)
 
-/* runstate info updated by Xen */
-static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate);
-
 /* snapshots of runstate info */
 static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate_snapshot);
 
 /* unused ns of stolen time */
 static DEFINE_PER_CPU(u64, xen_residual_stolen);
 
-/* return an consistent snapshot of 64-bit time/counter value */
-static u64 get64(const u64 *p)
-{
-	u64 ret;
-
-	if (BITS_PER_LONG < 64) {
-		u32 *p32 = (u32 *)p;
-		u32 h, l;
-
-		/*
-		 * Read high then low, and then make sure high is
-		 * still the same; this will only loop if low wraps
-		 * and carries into high.
-		 * XXX some clean way to make this endian-proof?
-		 */
-		do {
-			h = p32[1];
-			barrier();
-			l = p32[0];
-			barrier();
-		} while (p32[1] != h);
-
-		ret = (((u64)h) << 32) | l;
-	} else
-		ret = *p;
-
-	return ret;
-}
-
-/*
- * Runstate accounting
- */
-static void get_runstate_snapshot(struct vcpu_runstate_info *res)
-{
-	u64 state_time;
-	struct vcpu_runstate_info *state;
-
-	BUG_ON(preemptible());
-
-	state = this_cpu_ptr(&xen_runstate);
-
-	/*
-	 * The runstate info is always updated by the hypervisor on
-	 * the current CPU, so there's no need to use anything
-	 * stronger than a compiler barrier when fetching it.
-	 */
-	do {
-		state_time = get64(&state->state_entry_time);
-		barrier();
-		*res = *state;
-		barrier();
-	} while (get64(&state->state_entry_time) != state_time);
-}
-
-/* return true when a vcpu could run but has no real cpu to run on */
-bool xen_vcpu_stolen(int vcpu)
-{
-	return per_cpu(xen_runstate, vcpu).state == RUNSTATE_runnable;
-}
-
-void xen_setup_runstate_info(int cpu)
-{
-	struct vcpu_register_runstate_memory_area area;
-
-	area.addr.v = &per_cpu(xen_runstate, cpu);
-
-	if (HYPERVISOR_vcpu_op(VCPUOP_register_runstate_memory_area,
-			       cpu, &area))
-		BUG();
-}
-
 static void do_stolen_accounting(void)
 {
 	struct vcpu_runstate_info state;
@@ -119,7 +46,7 @@
 	s64 runnable, offline, stolen;
 	cputime_t ticks;
 
-	get_runstate_snapshot(&state);
+	xen_get_runstate_snapshot(&state);
 
 	WARN_ON(state.state != RUNSTATE_running);
 
@@ -194,26 +121,46 @@
 				   unsigned long was_set, void *priv)
 {
 	/* Protected by the calling core code serialization */
-	static struct timespec next_sync;
+	static struct timespec64 next_sync;
 
 	struct xen_platform_op op;
-	struct timespec now;
+	struct timespec64 now;
+	struct timekeeper *tk = priv;
+	static bool settime64_supported = true;
+	int ret;
 
-	now = __current_kernel_time();
+	now.tv_sec = tk->xtime_sec;
+	now.tv_nsec = (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift);
 
 	/*
 	 * We only take the expensive HV call when the clock was set
 	 * or when the 11 minutes RTC synchronization time elapsed.
 	 */
-	if (!was_set && timespec_compare(&now, &next_sync) < 0)
+	if (!was_set && timespec64_compare(&now, &next_sync) < 0)
 		return NOTIFY_OK;
 
-	op.cmd = XENPF_settime;
-	op.u.settime.secs = now.tv_sec;
-	op.u.settime.nsecs = now.tv_nsec;
-	op.u.settime.system_time = xen_clocksource_read();
+again:
+	if (settime64_supported) {
+		op.cmd = XENPF_settime64;
+		op.u.settime64.mbz = 0;
+		op.u.settime64.secs = now.tv_sec;
+		op.u.settime64.nsecs = now.tv_nsec;
+		op.u.settime64.system_time = xen_clocksource_read();
+	} else {
+		op.cmd = XENPF_settime32;
+		op.u.settime32.secs = now.tv_sec;
+		op.u.settime32.nsecs = now.tv_nsec;
+		op.u.settime32.system_time = xen_clocksource_read();
+	}
 
-	(void)HYPERVISOR_dom0_op(&op);
+	ret = HYPERVISOR_platform_op(&op);
+
+	if (ret == -ENOSYS && settime64_supported) {
+		settime64_supported = false;
+		goto again;
+	}
+	if (ret < 0)
+		return NOTIFY_BAD;
 
 	/*
 	 * Move the next drift compensation time 11 minutes
diff --git a/arch/x86/xen/xen-asm_32.S b/arch/x86/xen/xen-asm_32.S
index fd92a64..feb6d40 100644
--- a/arch/x86/xen/xen-asm_32.S
+++ b/arch/x86/xen/xen-asm_32.S
@@ -35,20 +35,6 @@
 	ret
 
 /*
- * We can't use sysexit directly, because we're not running in ring0.
- * But we can easily fake it up using iret.  Assuming xen_sysexit is
- * jumped to with a standard stack frame, we can just strip it back to
- * a standard iret frame and use iret.
- */
-ENTRY(xen_sysexit)
-	movl PT_EAX(%esp), %eax			/* Shouldn't be necessary? */
-	orl $X86_EFLAGS_IF, PT_EFLAGS(%esp)
-	lea PT_EIP(%esp), %esp
-
-	jmp xen_iret
-ENDPROC(xen_sysexit)
-
-/*
  * This is run where a normal iret would be run, with the same stack setup:
  *	8: eflags
  *	4: cs
diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S
index f22667a..cc8acc4 100644
--- a/arch/x86/xen/xen-asm_64.S
+++ b/arch/x86/xen/xen-asm_64.S
@@ -68,25 +68,6 @@
 ENDPATCH(xen_sysret64)
 RELOC(xen_sysret64, 1b+1)
 
-ENTRY(xen_sysret32)
-	/*
-	 * We're already on the usermode stack at this point, but
-	 * still with the kernel gs, so we can easily switch back
-	 */
-	movq %rsp, PER_CPU_VAR(rsp_scratch)
-	movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
-
-	pushq $__USER32_DS
-	pushq PER_CPU_VAR(rsp_scratch)
-	pushq %r11
-	pushq $__USER32_CS
-	pushq %rcx
-
-	pushq $0
-1:	jmp hypercall_iret
-ENDPATCH(xen_sysret32)
-RELOC(xen_sysret32, 1b+1)
-
 /*
  * Xen handles syscall callbacks much like ordinary exceptions, which
  * means we have:
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 1399423..4140b07 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -139,9 +139,6 @@
 
 /* These are not functions, and cannot be called normally */
 __visible void xen_iret(void);
-#ifdef CONFIG_X86_32
-__visible void xen_sysexit(void);
-#endif
 __visible void xen_sysret32(void);
 __visible void xen_sysret64(void);
 __visible void xen_adjust_exception_frame(void);
diff --git a/arch/xtensa/platforms/iss/simdisk.c b/arch/xtensa/platforms/iss/simdisk.c
index 3c3ace2..f58a4e6 100644
--- a/arch/xtensa/platforms/iss/simdisk.c
+++ b/arch/xtensa/platforms/iss/simdisk.c
@@ -227,16 +227,12 @@
 static ssize_t proc_write_simdisk(struct file *file, const char __user *buf,
 			size_t count, loff_t *ppos)
 {
-	char *tmp = kmalloc(count + 1, GFP_KERNEL);
+	char *tmp = memdup_user_nul(buf, count);
 	struct simdisk *dev = PDE_DATA(file_inode(file));
 	int err;
 
-	if (tmp == NULL)
-		return -ENOMEM;
-	if (copy_from_user(tmp, buf, count)) {
-		err = -EFAULT;
-		goto out_free;
-	}
+	if (IS_ERR(tmp))
+		return PTR_ERR(tmp);
 
 	err = simdisk_detach(dev);
 	if (err != 0)
@@ -244,8 +240,6 @@
 
 	if (count > 0 && tmp[count - 1] == '\n')
 		tmp[count - 1] = 0;
-	else
-		tmp[count] = 0;
 
 	if (tmp[0])
 		err = simdisk_attach(dev, tmp);
diff --git a/block/blk-merge.c b/block/blk-merge.c
index e73846a..e01405a 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -81,7 +81,7 @@
 	struct bio *new = NULL;
 
 	bio_for_each_segment(bv, bio, iter) {
-		if (sectors + (bv.bv_len >> 9) > blk_max_size_offset(q, bio->bi_iter.bi_sector))
+		if (sectors + (bv.bv_len >> 9) > queue_max_sectors(q))
 			goto split;
 
 		/*
diff --git a/crypto/Makefile b/crypto/Makefile
index f7aba92..2acdbbd 100644
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -40,6 +40,7 @@
 rsa_generic-y += rsaprivkey-asn1.o
 rsa_generic-y += rsa.o
 rsa_generic-y += rsa_helper.o
+rsa_generic-y += rsa-pkcs1pad.o
 obj-$(CONFIG_CRYPTO_RSA) += rsa_generic.o
 
 cryptomgr-y := algboss.o testmgr.o
diff --git a/crypto/akcipher.c b/crypto/akcipher.c
index 120ec04..def301e 100644
--- a/crypto/akcipher.c
+++ b/crypto/akcipher.c
@@ -21,6 +21,7 @@
 #include <linux/cryptouser.h>
 #include <net/netlink.h>
 #include <crypto/akcipher.h>
+#include <crypto/internal/akcipher.h>
 #include "internal.h"
 
 #ifdef CONFIG_NET
@@ -75,9 +76,17 @@
 	return 0;
 }
 
+static void crypto_akcipher_free_instance(struct crypto_instance *inst)
+{
+	struct akcipher_instance *akcipher = akcipher_instance(inst);
+
+	akcipher->free(akcipher);
+}
+
 static const struct crypto_type crypto_akcipher_type = {
 	.extsize = crypto_alg_extsize,
 	.init_tfm = crypto_akcipher_init_tfm,
+	.free = crypto_akcipher_free_instance,
 #ifdef CONFIG_PROC_FS
 	.show = crypto_akcipher_show,
 #endif
@@ -88,6 +97,14 @@
 	.tfmsize = offsetof(struct crypto_akcipher, base),
 };
 
+int crypto_grab_akcipher(struct crypto_akcipher_spawn *spawn, const char *name,
+			 u32 type, u32 mask)
+{
+	spawn->base.frontend = &crypto_akcipher_type;
+	return crypto_grab_spawn(&spawn->base, name, type, mask);
+}
+EXPORT_SYMBOL_GPL(crypto_grab_akcipher);
+
 struct crypto_akcipher *crypto_alloc_akcipher(const char *alg_name, u32 type,
 					      u32 mask)
 {
@@ -95,13 +112,20 @@
 }
 EXPORT_SYMBOL_GPL(crypto_alloc_akcipher);
 
-int crypto_register_akcipher(struct akcipher_alg *alg)
+static void akcipher_prepare_alg(struct akcipher_alg *alg)
 {
 	struct crypto_alg *base = &alg->base;
 
 	base->cra_type = &crypto_akcipher_type;
 	base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK;
 	base->cra_flags |= CRYPTO_ALG_TYPE_AKCIPHER;
+}
+
+int crypto_register_akcipher(struct akcipher_alg *alg)
+{
+	struct crypto_alg *base = &alg->base;
+
+	akcipher_prepare_alg(alg);
 	return crypto_register_alg(base);
 }
 EXPORT_SYMBOL_GPL(crypto_register_akcipher);
@@ -112,5 +136,13 @@
 }
 EXPORT_SYMBOL_GPL(crypto_unregister_akcipher);
 
+int akcipher_register_instance(struct crypto_template *tmpl,
+			       struct akcipher_instance *inst)
+{
+	akcipher_prepare_alg(&inst->alg);
+	return crypto_register_instance(tmpl, akcipher_crypto_instance(inst));
+}
+EXPORT_SYMBOL_GPL(akcipher_register_instance);
+
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Generic public key cipher type");
diff --git a/crypto/algapi.c b/crypto/algapi.c
index 59bf491..7be76aa 100644
--- a/crypto/algapi.c
+++ b/crypto/algapi.c
@@ -93,16 +93,15 @@
 {
 	struct crypto_spawn *spawn, *n;
 
-	if (list_empty(stack))
+	spawn = list_first_entry_or_null(stack, struct crypto_spawn, list);
+	if (!spawn)
 		return NULL;
 
-	spawn = list_first_entry(stack, struct crypto_spawn, list);
-	n = list_entry(spawn->list.next, struct crypto_spawn, list);
+	n = list_next_entry(spawn, list);
 
 	if (spawn->alg && &n->list != stack && !n->alg)
 		n->alg = (n->list.next == stack) ? alg :
-			 &list_entry(n->list.next, struct crypto_spawn,
-				     list)->inst->alg;
+			 &list_next_entry(n, list)->inst->alg;
 
 	list_move(&spawn->list, secondary_spawns);
 
diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c
index 23525c2..147069c 100644
--- a/crypto/algif_aead.c
+++ b/crypto/algif_aead.c
@@ -213,7 +213,7 @@
 	}
 
 	while (size) {
-		unsigned long len = size;
+		size_t len = size;
 		struct scatterlist *sg = NULL;
 
 		/* use the existing memory in an allocated page */
@@ -247,7 +247,7 @@
 		/* allocate a new page */
 		len = min_t(unsigned long, size, aead_sndbuf(sk));
 		while (len) {
-			int plen = 0;
+			size_t plen = 0;
 
 			if (sgl->cur >= ALG_MAX_PAGES) {
 				aead_put_sgl(sk);
@@ -256,7 +256,7 @@
 			}
 
 			sg = sgl->sg + sgl->cur;
-			plen = min_t(int, len, PAGE_SIZE);
+			plen = min_t(size_t, len, PAGE_SIZE);
 
 			sg_assign_page(sg, alloc_page(GFP_KERNEL));
 			err = -ENOMEM;
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index 5e20ca1..eaa9f9b 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -40,7 +40,7 @@
 	struct af_alg_completion completion;
 
 	atomic_t inflight;
-	unsigned used;
+	size_t used;
 
 	unsigned int len;
 	bool more;
@@ -153,7 +153,7 @@
 	return 0;
 }
 
-static void skcipher_pull_sgl(struct sock *sk, int used, int put)
+static void skcipher_pull_sgl(struct sock *sk, size_t used, int put)
 {
 	struct alg_sock *ask = alg_sk(sk);
 	struct skcipher_ctx *ctx = ask->private;
@@ -167,7 +167,7 @@
 		sg = sgl->sg;
 
 		for (i = 0; i < sgl->cur; i++) {
-			int plen = min_t(int, used, sg[i].length);
+			size_t plen = min_t(size_t, used, sg[i].length);
 
 			if (!sg_page(sg + i))
 				continue;
@@ -348,7 +348,7 @@
 	while (size) {
 		struct scatterlist *sg;
 		unsigned long len = size;
-		int plen;
+		size_t plen;
 
 		if (ctx->merge) {
 			sgl = list_entry(ctx->tsgl.prev,
@@ -390,7 +390,7 @@
 		sg_unmark_end(sg + sgl->cur);
 		do {
 			i = sgl->cur;
-			plen = min_t(int, len, PAGE_SIZE);
+			plen = min_t(size_t, len, PAGE_SIZE);
 
 			sg_assign_page(sg + i, alloc_page(GFP_KERNEL));
 			err = -ENOMEM;
diff --git a/crypto/asymmetric_keys/signature.c b/crypto/asymmetric_keys/signature.c
index 9441240..004d5fc 100644
--- a/crypto/asymmetric_keys/signature.c
+++ b/crypto/asymmetric_keys/signature.c
@@ -13,7 +13,7 @@
 
 #define pr_fmt(fmt) "SIG: "fmt
 #include <keys/asymmetric-subtype.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/err.h>
 #include <crypto/public_key.h>
 #include "asymmetric_keys.h"
diff --git a/crypto/async_tx/async_memcpy.c b/crypto/async_tx/async_memcpy.c
index f8c0b8d..88bc8e6 100644
--- a/crypto/async_tx/async_memcpy.c
+++ b/crypto/async_tx/async_memcpy.c
@@ -53,7 +53,7 @@
 	struct dmaengine_unmap_data *unmap = NULL;
 
 	if (device)
-		unmap = dmaengine_get_unmap_data(device->dev, 2, GFP_NOIO);
+		unmap = dmaengine_get_unmap_data(device->dev, 2, GFP_NOWAIT);
 
 	if (unmap && is_dma_copy_aligned(device, src_offset, dest_offset, len)) {
 		unsigned long dma_prep_flags = 0;
diff --git a/crypto/async_tx/async_pq.c b/crypto/async_tx/async_pq.c
index 5d355e0..c0748bb 100644
--- a/crypto/async_tx/async_pq.c
+++ b/crypto/async_tx/async_pq.c
@@ -188,7 +188,7 @@
 	BUG_ON(disks > 255 || !(P(blocks, disks) || Q(blocks, disks)));
 
 	if (device)
-		unmap = dmaengine_get_unmap_data(device->dev, disks, GFP_NOIO);
+		unmap = dmaengine_get_unmap_data(device->dev, disks, GFP_NOWAIT);
 
 	/* XORing P/Q is only implemented in software */
 	if (unmap && !(submit->flags & ASYNC_TX_PQ_XOR_DST) &&
@@ -307,7 +307,7 @@
 	BUG_ON(disks < 4);
 
 	if (device)
-		unmap = dmaengine_get_unmap_data(device->dev, disks, GFP_NOIO);
+		unmap = dmaengine_get_unmap_data(device->dev, disks, GFP_NOWAIT);
 
 	if (unmap && disks <= dma_maxpq(device, 0) &&
 	    is_dma_pq_aligned(device, offset, 0, len)) {
diff --git a/crypto/async_tx/async_raid6_recov.c b/crypto/async_tx/async_raid6_recov.c
index 934a849..8fab627 100644
--- a/crypto/async_tx/async_raid6_recov.c
+++ b/crypto/async_tx/async_raid6_recov.c
@@ -41,7 +41,7 @@
 	u8 *a, *b, *c;
 
 	if (dma)
-		unmap = dmaengine_get_unmap_data(dma->dev, 3, GFP_NOIO);
+		unmap = dmaengine_get_unmap_data(dma->dev, 3, GFP_NOWAIT);
 
 	if (unmap) {
 		struct device *dev = dma->dev;
@@ -105,7 +105,7 @@
 	u8 *d, *s;
 
 	if (dma)
-		unmap = dmaengine_get_unmap_data(dma->dev, 3, GFP_NOIO);
+		unmap = dmaengine_get_unmap_data(dma->dev, 3, GFP_NOWAIT);
 
 	if (unmap) {
 		dma_addr_t dma_dest[2];
diff --git a/crypto/async_tx/async_xor.c b/crypto/async_tx/async_xor.c
index e1bce26..da75777 100644
--- a/crypto/async_tx/async_xor.c
+++ b/crypto/async_tx/async_xor.c
@@ -182,7 +182,7 @@
 	BUG_ON(src_cnt <= 1);
 
 	if (device)
-		unmap = dmaengine_get_unmap_data(device->dev, src_cnt+1, GFP_NOIO);
+		unmap = dmaengine_get_unmap_data(device->dev, src_cnt+1, GFP_NOWAIT);
 
 	if (unmap && is_dma_xor_aligned(device, offset, 0, len)) {
 		struct dma_async_tx_descriptor *tx;
@@ -278,7 +278,7 @@
 	BUG_ON(src_cnt <= 1);
 
 	if (device)
-		unmap = dmaengine_get_unmap_data(device->dev, src_cnt, GFP_NOIO);
+		unmap = dmaengine_get_unmap_data(device->dev, src_cnt, GFP_NOWAIT);
 
 	if (unmap && src_cnt <= device->max_xor &&
 	    is_dma_xor_aligned(device, offset, 0, len)) {
diff --git a/crypto/chacha20poly1305.c b/crypto/chacha20poly1305.c
index 99c3cce..7b6b935 100644
--- a/crypto/chacha20poly1305.c
+++ b/crypto/chacha20poly1305.c
@@ -130,6 +130,9 @@
 	struct scatterlist *src, *dst;
 	int err;
 
+	if (rctx->cryptlen == 0)
+		goto skip;
+
 	chacha_iv(creq->iv, req, 1);
 
 	sg_init_table(rctx->src, 2);
@@ -150,6 +153,7 @@
 	if (err)
 		return err;
 
+skip:
 	return poly_verify_tag(req);
 }
 
@@ -415,6 +419,9 @@
 	struct scatterlist *src, *dst;
 	int err;
 
+	if (req->cryptlen == 0)
+		goto skip;
+
 	chacha_iv(creq->iv, req, 1);
 
 	sg_init_table(rctx->src, 2);
@@ -435,6 +442,7 @@
 	if (err)
 		return err;
 
+skip:
 	return poly_genkey(req);
 }
 
diff --git a/crypto/cryptd.c b/crypto/cryptd.c
index c81861b..7921251 100644
--- a/crypto/cryptd.c
+++ b/crypto/cryptd.c
@@ -637,6 +637,7 @@
 	inst->alg.halg.base.cra_flags = type;
 
 	inst->alg.halg.digestsize = salg->digestsize;
+	inst->alg.halg.statesize = salg->statesize;
 	inst->alg.halg.base.cra_ctxsize = sizeof(struct cryptd_hash_ctx);
 
 	inst->alg.halg.base.cra_init = cryptd_hash_init_tfm;
@@ -887,8 +888,7 @@
 	if (snprintf(cryptd_alg_name, CRYPTO_MAX_ALG_NAME,
 		     "cryptd(%s)", alg_name) >= CRYPTO_MAX_ALG_NAME)
 		return ERR_PTR(-EINVAL);
-	type &= ~(CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_GENIV);
-	type |= CRYPTO_ALG_TYPE_BLKCIPHER;
+	type = crypto_skcipher_type(type);
 	mask &= ~CRYPTO_ALG_TYPE_MASK;
 	mask |= (CRYPTO_ALG_GENIV | CRYPTO_ALG_TYPE_BLKCIPHER_MASK);
 	tfm = crypto_alloc_base(cryptd_alg_name, type, mask);
diff --git a/crypto/drbg.c b/crypto/drbg.c
index a7c2314..ab6ef1d 100644
--- a/crypto/drbg.c
+++ b/crypto/drbg.c
@@ -626,7 +626,7 @@
 	return len;
 }
 
-static struct drbg_state_ops drbg_ctr_ops = {
+static const struct drbg_state_ops drbg_ctr_ops = {
 	.update		= drbg_ctr_update,
 	.generate	= drbg_ctr_generate,
 	.crypto_init	= drbg_init_sym_kernel,
@@ -752,7 +752,7 @@
 	return len;
 }
 
-static struct drbg_state_ops drbg_hmac_ops = {
+static const struct drbg_state_ops drbg_hmac_ops = {
 	.update		= drbg_hmac_update,
 	.generate	= drbg_hmac_generate,
 	.crypto_init	= drbg_init_hash_kernel,
@@ -1032,7 +1032,7 @@
  * scratchpad usage: as update and generate are used isolated, both
  * can use the scratchpad
  */
-static struct drbg_state_ops drbg_hash_ops = {
+static const struct drbg_state_ops drbg_hash_ops = {
 	.update		= drbg_hash_update,
 	.generate	= drbg_hash_generate,
 	.crypto_init	= drbg_init_hash_kernel,
diff --git a/crypto/mcryptd.c b/crypto/mcryptd.c
index fe5b495a..f78d4fc 100644
--- a/crypto/mcryptd.c
+++ b/crypto/mcryptd.c
@@ -128,13 +128,9 @@
 	flist = per_cpu_ptr(mcryptd_flist, smp_processor_id());
 	while (single_task_running()) {
 		mutex_lock(&flist->lock);
-		if (list_empty(&flist->list)) {
-			mutex_unlock(&flist->lock);
-			return;
-		}
-		cstate = list_entry(flist->list.next,
+		cstate = list_first_entry_or_null(&flist->list,
 				struct mcryptd_alg_cstate, flush_list);
-		if (!cstate->flusher_engaged) {
+		if (!cstate || !cstate->flusher_engaged) {
 			mutex_unlock(&flist->lock);
 			return;
 		}
diff --git a/crypto/md5.c b/crypto/md5.c
index 33d17e9..2355a7c 100644
--- a/crypto/md5.c
+++ b/crypto/md5.c
@@ -24,6 +24,12 @@
 #include <linux/cryptohash.h>
 #include <asm/byteorder.h>
 
+const u8 md5_zero_message_hash[MD5_DIGEST_SIZE] = {
+	0xd4, 0x1d, 0x8c, 0xd9, 0x8f, 0x00, 0xb2, 0x04,
+	0xe9, 0x80, 0x09, 0x98, 0xec, 0xf8, 0x42, 0x7e,
+};
+EXPORT_SYMBOL_GPL(md5_zero_message_hash);
+
 /* XXX: this stuff can be optimized */
 static inline void le32_to_cpu_array(u32 *buf, unsigned int words)
 {
diff --git a/crypto/rsa-pkcs1pad.c b/crypto/rsa-pkcs1pad.c
new file mode 100644
index 0000000..50f5c97
--- /dev/null
+++ b/crypto/rsa-pkcs1pad.c
@@ -0,0 +1,628 @@
+/*
+ * RSA padding templates.
+ *
+ * Copyright (c) 2015  Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#include <crypto/algapi.h>
+#include <crypto/akcipher.h>
+#include <crypto/internal/akcipher.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/random.h>
+
+struct pkcs1pad_ctx {
+	struct crypto_akcipher *child;
+
+	unsigned int key_size;
+};
+
+struct pkcs1pad_request {
+	struct akcipher_request child_req;
+
+	struct scatterlist in_sg[3], out_sg[2];
+	uint8_t *in_buf, *out_buf;
+};
+
+static int pkcs1pad_set_pub_key(struct crypto_akcipher *tfm, const void *key,
+		unsigned int keylen)
+{
+	struct pkcs1pad_ctx *ctx = akcipher_tfm_ctx(tfm);
+	int err, size;
+
+	err = crypto_akcipher_set_pub_key(ctx->child, key, keylen);
+
+	if (!err) {
+		/* Find out new modulus size from rsa implementation */
+		size = crypto_akcipher_maxsize(ctx->child);
+
+		ctx->key_size = size > 0 ? size : 0;
+		if (size <= 0)
+			err = size;
+	}
+
+	return err;
+}
+
+static int pkcs1pad_set_priv_key(struct crypto_akcipher *tfm, const void *key,
+		unsigned int keylen)
+{
+	struct pkcs1pad_ctx *ctx = akcipher_tfm_ctx(tfm);
+	int err, size;
+
+	err = crypto_akcipher_set_priv_key(ctx->child, key, keylen);
+
+	if (!err) {
+		/* Find out new modulus size from rsa implementation */
+		size = crypto_akcipher_maxsize(ctx->child);
+
+		ctx->key_size = size > 0 ? size : 0;
+		if (size <= 0)
+			err = size;
+	}
+
+	return err;
+}
+
+static int pkcs1pad_get_max_size(struct crypto_akcipher *tfm)
+{
+	struct pkcs1pad_ctx *ctx = akcipher_tfm_ctx(tfm);
+
+	/*
+	 * The maximum destination buffer size for the encrypt/sign operations
+	 * will be the same as for RSA, even though it's smaller for
+	 * decrypt/verify.
+	 */
+
+	return ctx->key_size ?: -EINVAL;
+}
+
+static void pkcs1pad_sg_set_buf(struct scatterlist *sg, void *buf, size_t len,
+		struct scatterlist *next)
+{
+	int nsegs = next ? 1 : 0;
+
+	if (offset_in_page(buf) + len <= PAGE_SIZE) {
+		nsegs += 1;
+		sg_init_table(sg, nsegs);
+		sg_set_buf(sg, buf, len);
+	} else {
+		nsegs += 2;
+		sg_init_table(sg, nsegs);
+		sg_set_buf(sg + 0, buf, PAGE_SIZE - offset_in_page(buf));
+		sg_set_buf(sg + 1, buf + PAGE_SIZE - offset_in_page(buf),
+				offset_in_page(buf) + len - PAGE_SIZE);
+	}
+
+	if (next)
+		sg_chain(sg, nsegs, next);
+}
+
+static int pkcs1pad_encrypt_sign_complete(struct akcipher_request *req, int err)
+{
+	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+	struct pkcs1pad_ctx *ctx = akcipher_tfm_ctx(tfm);
+	struct pkcs1pad_request *req_ctx = akcipher_request_ctx(req);
+	size_t pad_len = ctx->key_size - req_ctx->child_req.dst_len;
+	size_t chunk_len, pad_left;
+	struct sg_mapping_iter miter;
+
+	if (!err) {
+		if (pad_len) {
+			sg_miter_start(&miter, req->dst,
+					sg_nents_for_len(req->dst, pad_len),
+					SG_MITER_ATOMIC | SG_MITER_TO_SG);
+
+			pad_left = pad_len;
+			while (pad_left) {
+				sg_miter_next(&miter);
+
+				chunk_len = min(miter.length, pad_left);
+				memset(miter.addr, 0, chunk_len);
+				pad_left -= chunk_len;
+			}
+
+			sg_miter_stop(&miter);
+		}
+
+		sg_pcopy_from_buffer(req->dst,
+				sg_nents_for_len(req->dst, ctx->key_size),
+				req_ctx->out_buf, req_ctx->child_req.dst_len,
+				pad_len);
+	}
+	req->dst_len = ctx->key_size;
+
+	kfree(req_ctx->in_buf);
+	kzfree(req_ctx->out_buf);
+
+	return err;
+}
+
+static void pkcs1pad_encrypt_sign_complete_cb(
+		struct crypto_async_request *child_async_req, int err)
+{
+	struct akcipher_request *req = child_async_req->data;
+	struct crypto_async_request async_req;
+
+	if (err == -EINPROGRESS)
+		return;
+
+	async_req.data = req->base.data;
+	async_req.tfm = crypto_akcipher_tfm(crypto_akcipher_reqtfm(req));
+	async_req.flags = child_async_req->flags;
+	req->base.complete(&async_req,
+			pkcs1pad_encrypt_sign_complete(req, err));
+}
+
+static int pkcs1pad_encrypt(struct akcipher_request *req)
+{
+	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+	struct pkcs1pad_ctx *ctx = akcipher_tfm_ctx(tfm);
+	struct pkcs1pad_request *req_ctx = akcipher_request_ctx(req);
+	int err;
+	unsigned int i, ps_end;
+
+	if (!ctx->key_size)
+		return -EINVAL;
+
+	if (req->src_len > ctx->key_size - 11)
+		return -EOVERFLOW;
+
+	if (req->dst_len < ctx->key_size) {
+		req->dst_len = ctx->key_size;
+		return -EOVERFLOW;
+	}
+
+	if (ctx->key_size > PAGE_SIZE)
+		return -ENOTSUPP;
+
+	/*
+	 * Replace both input and output to add the padding in the input and
+	 * the potential missing leading zeros in the output.
+	 */
+	req_ctx->child_req.src = req_ctx->in_sg;
+	req_ctx->child_req.src_len = ctx->key_size - 1;
+	req_ctx->child_req.dst = req_ctx->out_sg;
+	req_ctx->child_req.dst_len = ctx->key_size;
+
+	req_ctx->in_buf = kmalloc(ctx->key_size - 1 - req->src_len,
+			(req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
+			GFP_KERNEL : GFP_ATOMIC);
+	if (!req_ctx->in_buf)
+		return -ENOMEM;
+
+	ps_end = ctx->key_size - req->src_len - 2;
+	req_ctx->in_buf[0] = 0x02;
+	for (i = 1; i < ps_end; i++)
+		req_ctx->in_buf[i] = 1 + prandom_u32_max(255);
+	req_ctx->in_buf[ps_end] = 0x00;
+
+	pkcs1pad_sg_set_buf(req_ctx->in_sg, req_ctx->in_buf,
+			ctx->key_size - 1 - req->src_len, req->src);
+
+	req_ctx->out_buf = kmalloc(ctx->key_size,
+			(req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
+			GFP_KERNEL : GFP_ATOMIC);
+	if (!req_ctx->out_buf) {
+		kfree(req_ctx->in_buf);
+		return -ENOMEM;
+	}
+
+	pkcs1pad_sg_set_buf(req_ctx->out_sg, req_ctx->out_buf,
+			ctx->key_size, NULL);
+
+	akcipher_request_set_tfm(&req_ctx->child_req, ctx->child);
+	akcipher_request_set_callback(&req_ctx->child_req, req->base.flags,
+			pkcs1pad_encrypt_sign_complete_cb, req);
+
+	err = crypto_akcipher_encrypt(&req_ctx->child_req);
+	if (err != -EINPROGRESS &&
+			(err != -EBUSY ||
+			 !(req->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG)))
+		return pkcs1pad_encrypt_sign_complete(req, err);
+
+	return err;
+}
+
+static int pkcs1pad_decrypt_complete(struct akcipher_request *req, int err)
+{
+	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+	struct pkcs1pad_ctx *ctx = akcipher_tfm_ctx(tfm);
+	struct pkcs1pad_request *req_ctx = akcipher_request_ctx(req);
+	unsigned int pos;
+
+	if (err == -EOVERFLOW)
+		/* Decrypted value had no leading 0 byte */
+		err = -EINVAL;
+
+	if (err)
+		goto done;
+
+	if (req_ctx->child_req.dst_len != ctx->key_size - 1) {
+		err = -EINVAL;
+		goto done;
+	}
+
+	if (req_ctx->out_buf[0] != 0x02) {
+		err = -EINVAL;
+		goto done;
+	}
+	for (pos = 1; pos < req_ctx->child_req.dst_len; pos++)
+		if (req_ctx->out_buf[pos] == 0x00)
+			break;
+	if (pos < 9 || pos == req_ctx->child_req.dst_len) {
+		err = -EINVAL;
+		goto done;
+	}
+	pos++;
+
+	if (req->dst_len < req_ctx->child_req.dst_len - pos)
+		err = -EOVERFLOW;
+	req->dst_len = req_ctx->child_req.dst_len - pos;
+
+	if (!err)
+		sg_copy_from_buffer(req->dst,
+				sg_nents_for_len(req->dst, req->dst_len),
+				req_ctx->out_buf + pos, req->dst_len);
+
+done:
+	kzfree(req_ctx->out_buf);
+
+	return err;
+}
+
+static void pkcs1pad_decrypt_complete_cb(
+		struct crypto_async_request *child_async_req, int err)
+{
+	struct akcipher_request *req = child_async_req->data;
+	struct crypto_async_request async_req;
+
+	if (err == -EINPROGRESS)
+		return;
+
+	async_req.data = req->base.data;
+	async_req.tfm = crypto_akcipher_tfm(crypto_akcipher_reqtfm(req));
+	async_req.flags = child_async_req->flags;
+	req->base.complete(&async_req, pkcs1pad_decrypt_complete(req, err));
+}
+
+static int pkcs1pad_decrypt(struct akcipher_request *req)
+{
+	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+	struct pkcs1pad_ctx *ctx = akcipher_tfm_ctx(tfm);
+	struct pkcs1pad_request *req_ctx = akcipher_request_ctx(req);
+	int err;
+
+	if (!ctx->key_size || req->src_len != ctx->key_size)
+		return -EINVAL;
+
+	if (ctx->key_size > PAGE_SIZE)
+		return -ENOTSUPP;
+
+	/* Reuse input buffer, output to a new buffer */
+	req_ctx->child_req.src = req->src;
+	req_ctx->child_req.src_len = req->src_len;
+	req_ctx->child_req.dst = req_ctx->out_sg;
+	req_ctx->child_req.dst_len = ctx->key_size - 1;
+
+	req_ctx->out_buf = kmalloc(ctx->key_size - 1,
+			(req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
+			GFP_KERNEL : GFP_ATOMIC);
+	if (!req_ctx->out_buf)
+		return -ENOMEM;
+
+	pkcs1pad_sg_set_buf(req_ctx->out_sg, req_ctx->out_buf,
+			ctx->key_size - 1, NULL);
+
+	akcipher_request_set_tfm(&req_ctx->child_req, ctx->child);
+	akcipher_request_set_callback(&req_ctx->child_req, req->base.flags,
+			pkcs1pad_decrypt_complete_cb, req);
+
+	err = crypto_akcipher_decrypt(&req_ctx->child_req);
+	if (err != -EINPROGRESS &&
+			(err != -EBUSY ||
+			 !(req->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG)))
+		return pkcs1pad_decrypt_complete(req, err);
+
+	return err;
+}
+
+static int pkcs1pad_sign(struct akcipher_request *req)
+{
+	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+	struct pkcs1pad_ctx *ctx = akcipher_tfm_ctx(tfm);
+	struct pkcs1pad_request *req_ctx = akcipher_request_ctx(req);
+	int err;
+	unsigned int ps_end;
+
+	if (!ctx->key_size)
+		return -EINVAL;
+
+	if (req->src_len > ctx->key_size - 11)
+		return -EOVERFLOW;
+
+	if (req->dst_len < ctx->key_size) {
+		req->dst_len = ctx->key_size;
+		return -EOVERFLOW;
+	}
+
+	if (ctx->key_size > PAGE_SIZE)
+		return -ENOTSUPP;
+
+	/*
+	 * Replace both input and output to add the padding in the input and
+	 * the potential missing leading zeros in the output.
+	 */
+	req_ctx->child_req.src = req_ctx->in_sg;
+	req_ctx->child_req.src_len = ctx->key_size - 1;
+	req_ctx->child_req.dst = req_ctx->out_sg;
+	req_ctx->child_req.dst_len = ctx->key_size;
+
+	req_ctx->in_buf = kmalloc(ctx->key_size - 1 - req->src_len,
+			(req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
+			GFP_KERNEL : GFP_ATOMIC);
+	if (!req_ctx->in_buf)
+		return -ENOMEM;
+
+	ps_end = ctx->key_size - req->src_len - 2;
+	req_ctx->in_buf[0] = 0x01;
+	memset(req_ctx->in_buf + 1, 0xff, ps_end - 1);
+	req_ctx->in_buf[ps_end] = 0x00;
+
+	pkcs1pad_sg_set_buf(req_ctx->in_sg, req_ctx->in_buf,
+			ctx->key_size - 1 - req->src_len, req->src);
+
+	req_ctx->out_buf = kmalloc(ctx->key_size,
+			(req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
+			GFP_KERNEL : GFP_ATOMIC);
+	if (!req_ctx->out_buf) {
+		kfree(req_ctx->in_buf);
+		return -ENOMEM;
+	}
+
+	pkcs1pad_sg_set_buf(req_ctx->out_sg, req_ctx->out_buf,
+			ctx->key_size, NULL);
+
+	akcipher_request_set_tfm(&req_ctx->child_req, ctx->child);
+	akcipher_request_set_callback(&req_ctx->child_req, req->base.flags,
+			pkcs1pad_encrypt_sign_complete_cb, req);
+
+	err = crypto_akcipher_sign(&req_ctx->child_req);
+	if (err != -EINPROGRESS &&
+			(err != -EBUSY ||
+			 !(req->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG)))
+		return pkcs1pad_encrypt_sign_complete(req, err);
+
+	return err;
+}
+
+static int pkcs1pad_verify_complete(struct akcipher_request *req, int err)
+{
+	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+	struct pkcs1pad_ctx *ctx = akcipher_tfm_ctx(tfm);
+	struct pkcs1pad_request *req_ctx = akcipher_request_ctx(req);
+	unsigned int pos;
+
+	if (err == -EOVERFLOW)
+		/* Decrypted value had no leading 0 byte */
+		err = -EINVAL;
+
+	if (err)
+		goto done;
+
+	if (req_ctx->child_req.dst_len != ctx->key_size - 1) {
+		err = -EINVAL;
+		goto done;
+	}
+
+	if (req_ctx->out_buf[0] != 0x01) {
+		err = -EINVAL;
+		goto done;
+	}
+	for (pos = 1; pos < req_ctx->child_req.dst_len; pos++)
+		if (req_ctx->out_buf[pos] != 0xff)
+			break;
+	if (pos < 9 || pos == req_ctx->child_req.dst_len ||
+			req_ctx->out_buf[pos] != 0x00) {
+		err = -EINVAL;
+		goto done;
+	}
+	pos++;
+
+	if (req->dst_len < req_ctx->child_req.dst_len - pos)
+		err = -EOVERFLOW;
+	req->dst_len = req_ctx->child_req.dst_len - pos;
+
+	if (!err)
+		sg_copy_from_buffer(req->dst,
+				sg_nents_for_len(req->dst, req->dst_len),
+				req_ctx->out_buf + pos, req->dst_len);
+
+done:
+	kzfree(req_ctx->out_buf);
+
+	return err;
+}
+
+static void pkcs1pad_verify_complete_cb(
+		struct crypto_async_request *child_async_req, int err)
+{
+	struct akcipher_request *req = child_async_req->data;
+	struct crypto_async_request async_req;
+
+	if (err == -EINPROGRESS)
+		return;
+
+	async_req.data = req->base.data;
+	async_req.tfm = crypto_akcipher_tfm(crypto_akcipher_reqtfm(req));
+	async_req.flags = child_async_req->flags;
+	req->base.complete(&async_req, pkcs1pad_verify_complete(req, err));
+}
+
+/*
+ * The verify operation is here for completeness similar to the verification
+ * defined in RFC2313 section 10.2 except that block type 0 is not accepted,
+ * as in RFC2437.  RFC2437 section 9.2 doesn't define any operation to
+ * retrieve the DigestInfo from a signature, instead the user is expected
+ * to call the sign operation to generate the expected signature and compare
+ * signatures instead of the message-digests.
+ */
+static int pkcs1pad_verify(struct akcipher_request *req)
+{
+	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+	struct pkcs1pad_ctx *ctx = akcipher_tfm_ctx(tfm);
+	struct pkcs1pad_request *req_ctx = akcipher_request_ctx(req);
+	int err;
+
+	if (!ctx->key_size || req->src_len != ctx->key_size)
+		return -EINVAL;
+
+	if (ctx->key_size > PAGE_SIZE)
+		return -ENOTSUPP;
+
+	/* Reuse input buffer, output to a new buffer */
+	req_ctx->child_req.src = req->src;
+	req_ctx->child_req.src_len = req->src_len;
+	req_ctx->child_req.dst = req_ctx->out_sg;
+	req_ctx->child_req.dst_len = ctx->key_size - 1;
+
+	req_ctx->out_buf = kmalloc(ctx->key_size - 1,
+			(req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
+			GFP_KERNEL : GFP_ATOMIC);
+	if (!req_ctx->out_buf)
+		return -ENOMEM;
+
+	pkcs1pad_sg_set_buf(req_ctx->out_sg, req_ctx->out_buf,
+			ctx->key_size - 1, NULL);
+
+	akcipher_request_set_tfm(&req_ctx->child_req, ctx->child);
+	akcipher_request_set_callback(&req_ctx->child_req, req->base.flags,
+			pkcs1pad_verify_complete_cb, req);
+
+	err = crypto_akcipher_verify(&req_ctx->child_req);
+	if (err != -EINPROGRESS &&
+			(err != -EBUSY ||
+			 !(req->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG)))
+		return pkcs1pad_verify_complete(req, err);
+
+	return err;
+}
+
+static int pkcs1pad_init_tfm(struct crypto_akcipher *tfm)
+{
+	struct akcipher_instance *inst = akcipher_alg_instance(tfm);
+	struct pkcs1pad_ctx *ctx = akcipher_tfm_ctx(tfm);
+	struct crypto_akcipher *child_tfm;
+
+	child_tfm = crypto_spawn_akcipher(akcipher_instance_ctx(inst));
+	if (IS_ERR(child_tfm))
+		return PTR_ERR(child_tfm);
+
+	ctx->child = child_tfm;
+
+	return 0;
+}
+
+static void pkcs1pad_exit_tfm(struct crypto_akcipher *tfm)
+{
+	struct pkcs1pad_ctx *ctx = akcipher_tfm_ctx(tfm);
+
+	crypto_free_akcipher(ctx->child);
+}
+
+static void pkcs1pad_free(struct akcipher_instance *inst)
+{
+	struct crypto_akcipher_spawn *spawn = akcipher_instance_ctx(inst);
+
+	crypto_drop_akcipher(spawn);
+
+	kfree(inst);
+}
+
+static int pkcs1pad_create(struct crypto_template *tmpl, struct rtattr **tb)
+{
+	struct crypto_attr_type *algt;
+	struct akcipher_instance *inst;
+	struct crypto_akcipher_spawn *spawn;
+	struct akcipher_alg *rsa_alg;
+	const char *rsa_alg_name;
+	int err;
+
+	algt = crypto_get_attr_type(tb);
+	if (IS_ERR(algt))
+		return PTR_ERR(algt);
+
+	if ((algt->type ^ CRYPTO_ALG_TYPE_AKCIPHER) & algt->mask)
+		return -EINVAL;
+
+	rsa_alg_name = crypto_attr_alg_name(tb[1]);
+	if (IS_ERR(rsa_alg_name))
+		return PTR_ERR(rsa_alg_name);
+
+	inst = kzalloc(sizeof(*inst) + sizeof(*spawn), GFP_KERNEL);
+	if (!inst)
+		return -ENOMEM;
+
+	spawn = akcipher_instance_ctx(inst);
+	crypto_set_spawn(&spawn->base, akcipher_crypto_instance(inst));
+	err = crypto_grab_akcipher(spawn, rsa_alg_name, 0,
+			crypto_requires_sync(algt->type, algt->mask));
+	if (err)
+		goto out_free_inst;
+
+	rsa_alg = crypto_spawn_akcipher_alg(spawn);
+
+	err = -ENAMETOOLONG;
+	if (snprintf(inst->alg.base.cra_name,
+				CRYPTO_MAX_ALG_NAME, "pkcs1pad(%s)",
+				rsa_alg->base.cra_name) >=
+			CRYPTO_MAX_ALG_NAME ||
+			snprintf(inst->alg.base.cra_driver_name,
+				CRYPTO_MAX_ALG_NAME, "pkcs1pad(%s)",
+				rsa_alg->base.cra_driver_name) >=
+			CRYPTO_MAX_ALG_NAME)
+		goto out_drop_alg;
+
+	inst->alg.base.cra_flags = rsa_alg->base.cra_flags & CRYPTO_ALG_ASYNC;
+	inst->alg.base.cra_priority = rsa_alg->base.cra_priority;
+	inst->alg.base.cra_ctxsize = sizeof(struct pkcs1pad_ctx);
+
+	inst->alg.init = pkcs1pad_init_tfm;
+	inst->alg.exit = pkcs1pad_exit_tfm;
+
+	inst->alg.encrypt = pkcs1pad_encrypt;
+	inst->alg.decrypt = pkcs1pad_decrypt;
+	inst->alg.sign = pkcs1pad_sign;
+	inst->alg.verify = pkcs1pad_verify;
+	inst->alg.set_pub_key = pkcs1pad_set_pub_key;
+	inst->alg.set_priv_key = pkcs1pad_set_priv_key;
+	inst->alg.max_size = pkcs1pad_get_max_size;
+	inst->alg.reqsize = sizeof(struct pkcs1pad_request) + rsa_alg->reqsize;
+
+	inst->free = pkcs1pad_free;
+
+	err = akcipher_register_instance(tmpl, inst);
+	if (err)
+		goto out_drop_alg;
+
+	return 0;
+
+out_drop_alg:
+	crypto_drop_akcipher(spawn);
+out_free_inst:
+	kfree(inst);
+	return err;
+}
+
+struct crypto_template rsa_pkcs1pad_tmpl = {
+	.name = "pkcs1pad",
+	.create = pkcs1pad_create,
+	.module = THIS_MODULE,
+};
diff --git a/crypto/rsa.c b/crypto/rsa.c
index 1093e04..77d737f 100644
--- a/crypto/rsa.c
+++ b/crypto/rsa.c
@@ -13,6 +13,7 @@
 #include <crypto/internal/rsa.h>
 #include <crypto/internal/akcipher.h>
 #include <crypto/akcipher.h>
+#include <crypto/algapi.h>
 
 /*
  * RSAEP function [RFC3447 sec 5.1.1]
@@ -91,12 +92,6 @@
 		goto err_free_c;
 	}
 
-	if (req->dst_len < mpi_get_size(pkey->n)) {
-		req->dst_len = mpi_get_size(pkey->n);
-		ret = -EOVERFLOW;
-		goto err_free_c;
-	}
-
 	ret = -ENOMEM;
 	m = mpi_read_raw_from_sgl(req->src, req->src_len);
 	if (!m)
@@ -136,12 +131,6 @@
 		goto err_free_m;
 	}
 
-	if (req->dst_len < mpi_get_size(pkey->n)) {
-		req->dst_len = mpi_get_size(pkey->n);
-		ret = -EOVERFLOW;
-		goto err_free_m;
-	}
-
 	ret = -ENOMEM;
 	c = mpi_read_raw_from_sgl(req->src, req->src_len);
 	if (!c)
@@ -180,12 +169,6 @@
 		goto err_free_s;
 	}
 
-	if (req->dst_len < mpi_get_size(pkey->n)) {
-		req->dst_len = mpi_get_size(pkey->n);
-		ret = -EOVERFLOW;
-		goto err_free_s;
-	}
-
 	ret = -ENOMEM;
 	m = mpi_read_raw_from_sgl(req->src, req->src_len);
 	if (!m)
@@ -225,12 +208,6 @@
 		goto err_free_m;
 	}
 
-	if (req->dst_len < mpi_get_size(pkey->n)) {
-		req->dst_len = mpi_get_size(pkey->n);
-		ret = -EOVERFLOW;
-		goto err_free_m;
-	}
-
 	ret = -ENOMEM;
 	s = mpi_read_raw_from_sgl(req->src, req->src_len);
 	if (!s) {
@@ -339,11 +316,24 @@
 
 static int rsa_init(void)
 {
-	return crypto_register_akcipher(&rsa);
+	int err;
+
+	err = crypto_register_akcipher(&rsa);
+	if (err)
+		return err;
+
+	err = crypto_register_template(&rsa_pkcs1pad_tmpl);
+	if (err) {
+		crypto_unregister_akcipher(&rsa);
+		return err;
+	}
+
+	return 0;
 }
 
 static void rsa_exit(void)
 {
+	crypto_unregister_template(&rsa_pkcs1pad_tmpl);
 	crypto_unregister_akcipher(&rsa);
 }
 
diff --git a/crypto/sha1_generic.c b/crypto/sha1_generic.c
index 39e3acc..6877cbb 100644
--- a/crypto/sha1_generic.c
+++ b/crypto/sha1_generic.c
@@ -26,6 +26,13 @@
 #include <crypto/sha1_base.h>
 #include <asm/byteorder.h>
 
+const u8 sha1_zero_message_hash[SHA1_DIGEST_SIZE] = {
+	0xda, 0x39, 0xa3, 0xee, 0x5e, 0x6b, 0x4b, 0x0d,
+	0x32, 0x55, 0xbf, 0xef, 0x95, 0x60, 0x18, 0x90,
+	0xaf, 0xd8, 0x07, 0x09
+};
+EXPORT_SYMBOL_GPL(sha1_zero_message_hash);
+
 static void sha1_generic_block_fn(struct sha1_state *sst, u8 const *src,
 				  int blocks)
 {
diff --git a/crypto/sha256_generic.c b/crypto/sha256_generic.c
index 7843116..8f9c47e 100644
--- a/crypto/sha256_generic.c
+++ b/crypto/sha256_generic.c
@@ -27,6 +27,22 @@
 #include <asm/byteorder.h>
 #include <asm/unaligned.h>
 
+const u8 sha224_zero_message_hash[SHA224_DIGEST_SIZE] = {
+	0xd1, 0x4a, 0x02, 0x8c, 0x2a, 0x3a, 0x2b, 0xc9, 0x47,
+	0x61, 0x02, 0xbb, 0x28, 0x82, 0x34, 0xc4, 0x15, 0xa2,
+	0xb0, 0x1f, 0x82, 0x8e, 0xa6, 0x2a, 0xc5, 0xb3, 0xe4,
+	0x2f
+};
+EXPORT_SYMBOL_GPL(sha224_zero_message_hash);
+
+const u8 sha256_zero_message_hash[SHA256_DIGEST_SIZE] = {
+	0xe3, 0xb0, 0xc4, 0x42, 0x98, 0xfc, 0x1c, 0x14,
+	0x9a, 0xfb, 0xf4, 0xc8, 0x99, 0x6f, 0xb9, 0x24,
+	0x27, 0xae, 0x41, 0xe4, 0x64, 0x9b, 0x93, 0x4c,
+	0xa4, 0x95, 0x99, 0x1b, 0x78, 0x52, 0xb8, 0x55
+};
+EXPORT_SYMBOL_GPL(sha256_zero_message_hash);
+
 static inline u32 Ch(u32 x, u32 y, u32 z)
 {
 	return z ^ (x & (y ^ z));
diff --git a/crypto/tcrypt.c b/crypto/tcrypt.c
index 46a4a75..270bc4b 100644
--- a/crypto/tcrypt.c
+++ b/crypto/tcrypt.c
@@ -1789,7 +1789,7 @@
 		test_aead_speed("rfc4106(gcm(aes))", ENCRYPT, sec,
 				NULL, 0, 16, 16, aead_speed_template_20);
 		test_aead_speed("gcm(aes)", ENCRYPT, sec,
-				NULL, 0, 16, 8, aead_speed_template_20);
+				NULL, 0, 16, 8, speed_template_16_24_32);
 		break;
 
 	case 212:
diff --git a/drivers/acpi/device_sysfs.c b/drivers/acpi/device_sysfs.c
index 707cf62..b9afb47 100644
--- a/drivers/acpi/device_sysfs.c
+++ b/drivers/acpi/device_sysfs.c
@@ -104,7 +104,7 @@
 
 		init_completion(&dn->kobj_done);
 		ret = kobject_init_and_add(&dn->kobj, &acpi_data_node_ktype,
-					   kobj, dn->name);
+					   kobj, "%s", dn->name);
 		if (ret)
 			acpi_handle_err(dn->handle, "Failed to expose (%d)\n", ret);
 		else
diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig
index 6aaa3f8..861643ea 100644
--- a/drivers/ata/Kconfig
+++ b/drivers/ata/Kconfig
@@ -100,7 +100,7 @@
 
 config AHCI_BRCMSTB
 	tristate "Broadcom STB AHCI SATA support"
-	depends on ARCH_BRCMSTB
+	depends on ARCH_BRCMSTB || BMIPS_GENERIC
 	help
 	  This option enables support for the AHCI SATA3 controller found on
 	  STB SoC's.
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index cdfbcc5..594fcab 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -1306,15 +1306,13 @@
 #endif
 
 /*
- * ahci_init_msix() only implements single MSI-X support, not multiple
- * MSI-X per-port interrupts. This is needed for host controllers that only
- * have MSI-X support implemented, but no MSI or intx.
+ * ahci_init_msix() - optionally enable per-port MSI-X otherwise defer
+ * to single msi.
  */
 static int ahci_init_msix(struct pci_dev *pdev, unsigned int n_ports,
-			  struct ahci_host_priv *hpriv)
+			  struct ahci_host_priv *hpriv, unsigned long flags)
 {
-	int rc, nvec;
-	struct msix_entry entry = {};
+	int nvec, i, rc;
 
 	/* Do not init MSI-X if MSI is disabled for the device */
 	if (hpriv->flags & AHCI_HFLAG_NO_MSI)
@@ -1324,22 +1322,39 @@
 	if (nvec < 0)
 		return nvec;
 
-	if (!nvec) {
+	/*
+	 * Proper MSI-X implementations will have a vector per-port.
+	 * Barring that, we prefer single-MSI over single-MSIX.  If this
+	 * check fails (not enough MSI-X vectors for all ports) we will
+	 * be called again with the flag clear iff ahci_init_msi()
+	 * fails.
+	 */
+	if (flags & AHCI_HFLAG_MULTI_MSIX) {
+		if (nvec < n_ports)
+			return -ENODEV;
+		nvec = n_ports;
+	} else if (nvec) {
+		nvec = 1;
+	} else {
+		/*
+		 * Emit dev_err() since this was the non-legacy irq
+		 * method of last resort.
+		 */
 		rc = -ENODEV;
 		goto fail;
 	}
 
-	/*
-	 * There can be more than one vector (e.g. for error detection or
-	 * hdd hotplug). Only the first vector (entry.entry = 0) is used.
-	 */
-	rc = pci_enable_msix_exact(pdev, &entry, 1);
+	for (i = 0; i < nvec; i++)
+		hpriv->msix[i].entry = i;
+	rc = pci_enable_msix_exact(pdev, hpriv->msix, nvec);
 	if (rc < 0)
 		goto fail;
 
-	hpriv->irq = entry.vector;
+	if (nvec > 1)
+		hpriv->flags |= AHCI_HFLAG_MULTI_MSIX;
+	hpriv->irq = hpriv->msix[0].vector; /* for single msi-x */
 
-	return 1;
+	return nvec;
 fail:
 	dev_err(&pdev->dev,
 		"failed to enable MSI-X with error %d, # of vectors: %d\n",
@@ -1403,20 +1418,25 @@
 {
 	int nvec;
 
+	/*
+	 * Try to enable per-port MSI-X.  If the host is not capable
+	 * fall back to single MSI before finally attempting single
+	 * MSI-X.
+	 */
+	nvec = ahci_init_msix(pdev, n_ports, hpriv, AHCI_HFLAG_MULTI_MSIX);
+	if (nvec >= 0)
+		return nvec;
+
 	nvec = ahci_init_msi(pdev, n_ports, hpriv);
 	if (nvec >= 0)
 		return nvec;
 
-	/*
-	 * Currently, MSI-X support only implements single IRQ mode and
-	 * exists for controllers which can't do other types of IRQ. Only
-	 * set it up if MSI fails.
-	 */
-	nvec = ahci_init_msix(pdev, n_ports, hpriv);
+	/* try single-msix */
+	nvec = ahci_init_msix(pdev, n_ports, hpriv, 0);
 	if (nvec >= 0)
 		return nvec;
 
-	/* lagacy intx interrupts */
+	/* legacy intx interrupts */
 	pci_intx(pdev, 1);
 	hpriv->irq = pdev->irq;
 
@@ -1578,7 +1598,10 @@
 	if (!host)
 		return -ENOMEM;
 	host->private_data = hpriv;
-
+	hpriv->msix = devm_kzalloc(&pdev->dev,
+			sizeof(struct msix_entry) * n_ports, GFP_KERNEL);
+	if (!hpriv->msix)
+		return -ENOMEM;
 	ahci_init_interrupts(pdev, n_ports, hpriv);
 
 	if (!(hpriv->cap & HOST_CAP_SSS) || ahci_ignore_sss)
diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h
index 45586c1..a4faa43 100644
--- a/drivers/ata/ahci.h
+++ b/drivers/ata/ahci.h
@@ -35,6 +35,7 @@
 #ifndef _AHCI_H
 #define _AHCI_H
 
+#include <linux/pci.h>
 #include <linux/clk.h>
 #include <linux/libata.h>
 #include <linux/phy/phy.h>
@@ -237,11 +238,18 @@
 	AHCI_HFLAG_DELAY_ENGINE		= (1 << 15), /* do not start engine on
 						        port start (wait until
 						        error-handling stage) */
-	AHCI_HFLAG_MULTI_MSI		= (1 << 16), /* multiple PCI MSIs */
 	AHCI_HFLAG_NO_DEVSLP		= (1 << 17), /* no device sleep */
 	AHCI_HFLAG_NO_FBS		= (1 << 18), /* no FBS */
 	AHCI_HFLAG_EDGE_IRQ		= (1 << 19), /* HOST_IRQ_STAT behaves as
 							Edge Triggered */
+#ifdef CONFIG_PCI_MSI
+	AHCI_HFLAG_MULTI_MSI		= (1 << 20), /* multiple PCI MSIs */
+	AHCI_HFLAG_MULTI_MSIX		= (1 << 21), /* per-port MSI-X */
+#else
+	/* compile out MSI infrastructure */
+	AHCI_HFLAG_MULTI_MSI		= 0,
+	AHCI_HFLAG_MULTI_MSIX		= 0,
+#endif
 
 	/* ap->flags bits */
 
@@ -308,7 +316,6 @@
 	unsigned int		ncq_saw_d2h:1;
 	unsigned int		ncq_saw_dmas:1;
 	unsigned int		ncq_saw_sdb:1;
-	atomic_t		intr_status;	/* interrupts to handle */
 	spinlock_t		lock;		/* protects parent ata_port */
 	u32 			intr_mask;	/* interrupts to enable */
 	bool			fbs_supported;	/* set iff FBS is supported */
@@ -343,6 +350,7 @@
 	 * the PHY position in this array.
 	 */
 	struct phy		**phys;
+	struct msix_entry	*msix;		/* Optional MSI-X support */
 	unsigned		nports;		/* Number of ports */
 	void			*plat_data;	/* Other platform data */
 	unsigned int		irq;		/* interrupt line */
@@ -354,6 +362,21 @@
 	void			(*start_engine)(struct ata_port *ap);
 };
 
+#ifdef CONFIG_PCI_MSI
+static inline int ahci_irq_vector(struct ahci_host_priv *hpriv, int port)
+{
+	if (hpriv->flags & AHCI_HFLAG_MULTI_MSIX)
+		return hpriv->msix[port].vector;
+	else
+		return hpriv->irq + port;
+}
+#else
+static inline int ahci_irq_vector(struct ahci_host_priv *hpriv, int port)
+{
+	return hpriv->irq;
+}
+#endif
+
 extern int ahci_ignore_sss;
 
 extern struct device_attribute *ahci_shost_attrs[];
diff --git a/drivers/ata/ahci_brcmstb.c b/drivers/ata/ahci_brcmstb.c
index 14b7305..b36cae2 100644
--- a/drivers/ata/ahci_brcmstb.c
+++ b/drivers/ata/ahci_brcmstb.c
@@ -52,8 +52,10 @@
   #define SATA_TOP_CTRL_2_PHY_GLOBAL_RESET		BIT(14)
  #define SATA_TOP_CTRL_PHY_OFFS				0x8
  #define SATA_TOP_MAX_PHYS				2
-#define SATA_TOP_CTRL_SATA_TP_OUT			0x1c
-#define SATA_TOP_CTRL_CLIENT_INIT_CTRL			0x20
+
+#define SATA_FIRST_PORT_CTRL				0x700
+#define SATA_NEXT_PORT_CTRL_OFFSET			0x80
+#define SATA_PORT_PCTRL6(reg_base)			(reg_base + 0x18)
 
 /* On big-endian MIPS, buses are reversed to big endian, so switch them back */
 #if defined(CONFIG_MIPS) && defined(__BIG_ENDIAN)
@@ -69,14 +71,21 @@
 	(DATA_ENDIAN << DMADESC_ENDIAN_SHIFT) |		\
 	(MMIO_ENDIAN << MMIO_ENDIAN_SHIFT))
 
+enum brcm_ahci_quirks {
+	BRCM_AHCI_QUIRK_NO_NCQ		= BIT(0),
+	BRCM_AHCI_QUIRK_SKIP_PHY_ENABLE	= BIT(1),
+};
+
 struct brcm_ahci_priv {
 	struct device *dev;
 	void __iomem *top_ctrl;
 	u32 port_mask;
+	u32 quirks;
 };
 
 static const struct ata_port_info ahci_brcm_port_info = {
-	.flags		= AHCI_FLAG_COMMON,
+	.flags		= AHCI_FLAG_COMMON | ATA_FLAG_NO_DIPM,
+	.link_flags	= ATA_LFLAG_NO_DB_DELAY,
 	.pio_mask	= ATA_PIO4,
 	.udma_mask	= ATA_UDMA6,
 	.port_ops	= &ahci_platform_ops,
@@ -107,6 +116,34 @@
 		writel_relaxed(val, addr);
 }
 
+static void brcm_sata_alpm_init(struct ahci_host_priv *hpriv)
+{
+	struct brcm_ahci_priv *priv = hpriv->plat_data;
+	u32 bus_ctrl, port_ctrl, host_caps;
+	int i;
+
+	/* Enable support for ALPM */
+	bus_ctrl = brcm_sata_readreg(priv->top_ctrl +
+				     SATA_TOP_CTRL_BUS_CTRL);
+	brcm_sata_writereg(bus_ctrl | OVERRIDE_HWINIT,
+			   priv->top_ctrl + SATA_TOP_CTRL_BUS_CTRL);
+	host_caps = readl(hpriv->mmio + HOST_CAP);
+	writel(host_caps | HOST_CAP_ALPM, hpriv->mmio);
+	brcm_sata_writereg(bus_ctrl, priv->top_ctrl + SATA_TOP_CTRL_BUS_CTRL);
+
+	/*
+	 * Adjust timeout to allow PLL sufficient time to lock while waking
+	 * up from slumber mode.
+	 */
+	for (i = 0, port_ctrl = SATA_FIRST_PORT_CTRL;
+	     i < SATA_TOP_MAX_PHYS;
+	     i++, port_ctrl += SATA_NEXT_PORT_CTRL_OFFSET) {
+		if (priv->port_mask & BIT(i))
+			writel(0xff1003fc,
+			       hpriv->mmio + SATA_PORT_PCTRL6(port_ctrl));
+	}
+}
+
 static void brcm_sata_phy_enable(struct brcm_ahci_priv *priv, int port)
 {
 	void __iomem *phyctrl = priv->top_ctrl + SATA_TOP_CTRL_PHY_CTRL +
@@ -114,6 +151,9 @@
 	void __iomem *p;
 	u32 reg;
 
+	if (priv->quirks & BRCM_AHCI_QUIRK_SKIP_PHY_ENABLE)
+		return;
+
 	/* clear PHY_DEFAULT_POWER_STATE */
 	p = phyctrl + SATA_TOP_CTRL_PHY_CTRL_1;
 	reg = brcm_sata_readreg(p);
@@ -143,6 +183,9 @@
 	void __iomem *p;
 	u32 reg;
 
+	if (priv->quirks & BRCM_AHCI_QUIRK_SKIP_PHY_ENABLE)
+		return;
+
 	/* power-off the PHY digital logic */
 	p = phyctrl + SATA_TOP_CTRL_PHY_CTRL_2;
 	reg = brcm_sata_readreg(p);
@@ -230,6 +273,7 @@
 
 	brcm_sata_init(priv);
 	brcm_sata_phys_enable(priv);
+	brcm_sata_alpm_init(hpriv);
 	return ahci_platform_resume(dev);
 }
 #endif
@@ -256,6 +300,11 @@
 	if (IS_ERR(priv->top_ctrl))
 		return PTR_ERR(priv->top_ctrl);
 
+	if (of_device_is_compatible(dev->of_node, "brcm,bcm7425-ahci")) {
+		priv->quirks |= BRCM_AHCI_QUIRK_NO_NCQ;
+		priv->quirks |= BRCM_AHCI_QUIRK_SKIP_PHY_ENABLE;
+	}
+
 	brcm_sata_init(priv);
 
 	priv->port_mask = brcm_ahci_get_portmask(pdev, priv);
@@ -269,10 +318,15 @@
 		return PTR_ERR(hpriv);
 	hpriv->plat_data = priv;
 
+	brcm_sata_alpm_init(hpriv);
+
 	ret = ahci_platform_enable_resources(hpriv);
 	if (ret)
 		return ret;
 
+	if (priv->quirks & BRCM_AHCI_QUIRK_NO_NCQ)
+		hpriv->flags |= AHCI_HFLAG_NO_NCQ;
+
 	ret = ahci_platform_init_host(pdev, hpriv, &ahci_brcm_port_info,
 				      &ahci_platform_sht);
 	if (ret)
@@ -300,6 +354,7 @@
 }
 
 static const struct of_device_id ahci_of_match[] = {
+	{.compatible = "brcm,bcm7425-ahci"},
 	{.compatible = "brcm,bcm7445-ahci"},
 	{},
 };
diff --git a/drivers/ata/ahci_qoriq.c b/drivers/ata/ahci_qoriq.c
index d0f9de9..7bdee9b 100644
--- a/drivers/ata/ahci_qoriq.c
+++ b/drivers/ata/ahci_qoriq.c
@@ -34,14 +34,20 @@
 
 /* port register default value */
 #define AHCI_PORT_PHY_1_CFG	0xa003fffe
-#define AHCI_PORT_PHY_2_CFG	0x28183411
-#define AHCI_PORT_PHY_3_CFG	0x0e081004
-#define AHCI_PORT_PHY_4_CFG	0x00480811
-#define AHCI_PORT_PHY_5_CFG	0x192c96a4
-#define AHCI_PORT_TRANS_CFG	0x08000025
+#define AHCI_PORT_TRANS_CFG	0x08000029
+
+/* for ls1021a */
+#define LS1021A_PORT_PHY2	0x28183414
+#define LS1021A_PORT_PHY3	0x0e080e06
+#define LS1021A_PORT_PHY4	0x064a080b
+#define LS1021A_PORT_PHY5	0x2aa86470
 
 #define SATA_ECC_DISABLE	0x00020000
 
+/* for ls1043a */
+#define LS1043A_PORT_PHY2	0x28184d1f
+#define LS1043A_PORT_PHY3	0x0e081509
+
 enum ahci_qoriq_type {
 	AHCI_LS1021A,
 	AHCI_LS1043A,
@@ -151,16 +157,23 @@
 	case AHCI_LS1021A:
 		writel(SATA_ECC_DISABLE, qpriv->ecc_addr);
 		writel(AHCI_PORT_PHY_1_CFG, reg_base + PORT_PHY1);
-		writel(AHCI_PORT_PHY_2_CFG, reg_base + PORT_PHY2);
-		writel(AHCI_PORT_PHY_3_CFG, reg_base + PORT_PHY3);
-		writel(AHCI_PORT_PHY_4_CFG, reg_base + PORT_PHY4);
-		writel(AHCI_PORT_PHY_5_CFG, reg_base + PORT_PHY5);
+		writel(LS1021A_PORT_PHY2, reg_base + PORT_PHY2);
+		writel(LS1021A_PORT_PHY3, reg_base + PORT_PHY3);
+		writel(LS1021A_PORT_PHY4, reg_base + PORT_PHY4);
+		writel(LS1021A_PORT_PHY5, reg_base + PORT_PHY5);
 		writel(AHCI_PORT_TRANS_CFG, reg_base + PORT_TRANS);
 		break;
 
 	case AHCI_LS1043A:
+		writel(AHCI_PORT_PHY_1_CFG, reg_base + PORT_PHY1);
+		writel(LS1043A_PORT_PHY2, reg_base + PORT_PHY2);
+		writel(LS1043A_PORT_PHY3, reg_base + PORT_PHY3);
+		writel(AHCI_PORT_TRANS_CFG, reg_base + PORT_TRANS);
+		break;
+
 	case AHCI_LS2080A:
 		writel(AHCI_PORT_PHY_1_CFG, reg_base + PORT_PHY1);
+		writel(AHCI_PORT_TRANS_CFG, reg_base + PORT_TRANS);
 		break;
 	}
 
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index 4665512..d61740e 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -43,6 +43,7 @@
 #include <scsi/scsi_host.h>
 #include <scsi/scsi_cmnd.h>
 #include <linux/libata.h>
+#include <linux/pci.h>
 #include "ahci.h"
 #include "libata.h"
 
@@ -1804,29 +1805,10 @@
 	ahci_handle_port_interrupt(ap, port_mmio, status);
 }
 
-static irqreturn_t ahci_port_thread_fn(int irq, void *dev_instance)
-{
-	struct ata_port *ap = dev_instance;
-	struct ahci_port_priv *pp = ap->private_data;
-	void __iomem *port_mmio = ahci_port_base(ap);
-	u32 status;
-
-	status = atomic_xchg(&pp->intr_status, 0);
-	if (!status)
-		return IRQ_NONE;
-
-	spin_lock_bh(ap->lock);
-	ahci_handle_port_interrupt(ap, port_mmio, status);
-	spin_unlock_bh(ap->lock);
-
-	return IRQ_HANDLED;
-}
-
-static irqreturn_t ahci_multi_irqs_intr(int irq, void *dev_instance)
+static irqreturn_t ahci_multi_irqs_intr_hard(int irq, void *dev_instance)
 {
 	struct ata_port *ap = dev_instance;
 	void __iomem *port_mmio = ahci_port_base(ap);
-	struct ahci_port_priv *pp = ap->private_data;
 	u32 status;
 
 	VPRINTK("ENTER\n");
@@ -1834,11 +1816,13 @@
 	status = readl(port_mmio + PORT_IRQ_STAT);
 	writel(status, port_mmio + PORT_IRQ_STAT);
 
-	atomic_or(status, &pp->intr_status);
+	spin_lock(ap->lock);
+	ahci_handle_port_interrupt(ap, port_mmio, status);
+	spin_unlock(ap->lock);
 
 	VPRINTK("EXIT\n");
 
-	return IRQ_WAKE_THREAD;
+	return IRQ_HANDLED;
 }
 
 static u32 ahci_handle_port_intr(struct ata_host *host, u32 irq_masked)
@@ -2479,9 +2463,10 @@
 }
 EXPORT_SYMBOL_GPL(ahci_set_em_messages);
 
-static int ahci_host_activate_multi_irqs(struct ata_host *host, int irq,
+static int ahci_host_activate_multi_irqs(struct ata_host *host,
 					 struct scsi_host_template *sht)
 {
+	struct ahci_host_priv *hpriv = host->private_data;
 	int i, rc;
 
 	rc = ata_host_start(host);
@@ -2493,6 +2478,7 @@
 	 */
 	for (i = 0; i < host->n_ports; i++) {
 		struct ahci_port_priv *pp = host->ports[i]->private_data;
+		int irq = ahci_irq_vector(hpriv, i);
 
 		/* Do not receive interrupts sent by dummy ports */
 		if (!pp) {
@@ -2500,14 +2486,14 @@
 			continue;
 		}
 
-		rc = devm_request_threaded_irq(host->dev, irq + i,
-					       ahci_multi_irqs_intr,
-					       ahci_port_thread_fn, 0,
-					       pp->irq_desc, host->ports[i]);
+		rc = devm_request_irq(host->dev, irq, ahci_multi_irqs_intr_hard,
+				0, pp->irq_desc, host->ports[i]);
+
 		if (rc)
 			return rc;
-		ata_port_desc(host->ports[i], "irq %d", irq + i);
+		ata_port_desc(host->ports[i], "irq %d", irq);
 	}
+
 	return ata_host_register(host, sht);
 }
 
@@ -2528,8 +2514,8 @@
 	int irq = hpriv->irq;
 	int rc;
 
-	if (hpriv->flags & AHCI_HFLAG_MULTI_MSI)
-		rc = ahci_host_activate_multi_irqs(host, irq, sht);
+	if (hpriv->flags & (AHCI_HFLAG_MULTI_MSI | AHCI_HFLAG_MULTI_MSIX))
+		rc = ahci_host_activate_multi_irqs(host, sht);
 	else if (hpriv->flags & AHCI_HFLAG_EDGE_IRQ)
 		rc = ata_host_activate(host, irq, ahci_single_edge_irq_intr,
 				       IRQF_SHARED, sht);
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index b79cb10..cbb7471 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -50,6 +50,7 @@
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/timer.h>
+#include <linux/time.h>
 #include <linux/interrupt.h>
 #include <linux/completion.h>
 #include <linux/suspend.h>
@@ -3597,7 +3598,8 @@
 		 * immediately after resuming.  Delay 200ms before
 		 * debouncing.
 		 */
-		ata_msleep(link->ap, 200);
+		if (!(link->flags & ATA_LFLAG_NO_DB_DELAY))
+			ata_msleep(link->ap, 200);
 
 		/* is SControl restored correctly? */
 		if ((rc = sata_scr_read(link, SCR_CONTROL, &scontrol)))
@@ -6223,6 +6225,7 @@
 		      struct scsi_host_template *sht)
 {
 	int i, rc;
+	char *irq_desc;
 
 	rc = ata_host_start(host);
 	if (rc)
@@ -6234,8 +6237,14 @@
 		return ata_host_register(host, sht);
 	}
 
+	irq_desc = devm_kasprintf(host->dev, GFP_KERNEL, "%s[%s]",
+				  dev_driver_string(host->dev),
+				  dev_name(host->dev));
+	if (!irq_desc)
+		return -ENOMEM;
+
 	rc = devm_request_irq(host->dev, irq, irq_handler, irq_flags,
-			      dev_name(host->dev), host);
+			      irq_desc, host);
 	if (rc)
 		return rc;
 
@@ -6697,7 +6706,12 @@
 	if (owns_eh)
 		ata_eh_release(ap);
 
-	msleep(msecs);
+	if (msecs < 20) {
+		unsigned long usecs = msecs * USEC_PER_MSEC;
+		usleep_range(usecs, usecs + 50);
+	} else {
+		msleep(msecs);
+	}
 
 	if (owns_eh)
 		ata_eh_acquire(ap);
diff --git a/drivers/ata/sata_rcar.c b/drivers/ata/sata_rcar.c
index 8804127..f72d601 100644
--- a/drivers/ata/sata_rcar.c
+++ b/drivers/ata/sata_rcar.c
@@ -854,17 +854,14 @@
 		.compatible = "renesas,sata-r8a7793",
 		.data = (void *)RCAR_GEN2_SATA
 	},
+	{
+		.compatible = "renesas,sata-r8a7795",
+		.data = (void *)RCAR_GEN2_SATA
+	},
 	{ },
 };
 MODULE_DEVICE_TABLE(of, sata_rcar_match);
 
-static const struct platform_device_id sata_rcar_id_table[] = {
-	{ "sata_rcar", RCAR_GEN1_SATA }, /* Deprecated by "sata-r8a7779" */
-	{ "sata-r8a7779", RCAR_GEN1_SATA },
-	{ },
-};
-MODULE_DEVICE_TABLE(platform, sata_rcar_id_table);
-
 static int sata_rcar_probe(struct platform_device *pdev)
 {
 	const struct of_device_id *of_id;
@@ -884,11 +881,10 @@
 		return -ENOMEM;
 
 	of_id = of_match_device(sata_rcar_match, &pdev->dev);
-	if (of_id)
-		priv->type = (enum sata_rcar_type)of_id->data;
-	else
-		priv->type = platform_get_device_id(pdev)->driver_data;
+	if (!of_id)
+		return -ENODEV;
 
+	priv->type = (enum sata_rcar_type)of_id->data;
 	priv->clk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(priv->clk)) {
 		dev_err(&pdev->dev, "failed to get access to sata clock\n");
@@ -1018,7 +1014,6 @@
 static struct platform_driver sata_rcar_driver = {
 	.probe		= sata_rcar_probe,
 	.remove		= sata_rcar_remove,
-	.id_table	= sata_rcar_id_table,
 	.driver = {
 		.name		= DRV_NAME,
 		.of_match_table	= sata_rcar_match,
diff --git a/drivers/ata/sata_sx4.c b/drivers/ata/sata_sx4.c
index fab504f..48301cb 100644
--- a/drivers/ata/sata_sx4.c
+++ b/drivers/ata/sata_sx4.c
@@ -1396,6 +1396,8 @@
 		addr = 0;
 		length = size * 1024 * 1024;
 		buf = kzalloc(ECC_ERASE_BUF_SZ, GFP_KERNEL);
+		if (!buf)
+			return 1;
 		while (addr < length) {
 			pdc20621_put_to_dimm(host, buf, addr,
 					     ECC_ERASE_BUF_SZ);
diff --git a/drivers/base/component.c b/drivers/base/component.c
index f748430..89f5cf68 100644
--- a/drivers/base/component.c
+++ b/drivers/base/component.c
@@ -18,18 +18,24 @@
 #include <linux/mutex.h>
 #include <linux/slab.h>
 
+struct component;
+
+struct component_match_array {
+	void *data;
+	int (*compare)(struct device *, void *);
+	void (*release)(struct device *, void *);
+	struct component *component;
+	bool duplicate;
+};
+
 struct component_match {
 	size_t alloc;
 	size_t num;
-	struct {
-		void *data;
-		int (*fn)(struct device *, void *);
-	} compare[0];
+	struct component_match_array *compare;
 };
 
 struct master {
 	struct list_head node;
-	struct list_head components;
 	bool bound;
 
 	const struct component_master_ops *ops;
@@ -39,7 +45,6 @@
 
 struct component {
 	struct list_head node;
-	struct list_head master_node;
 	struct master *master;
 	bool bound;
 
@@ -63,48 +68,21 @@
 	return NULL;
 }
 
-/* Attach an unattached component to a master. */
-static void component_attach_master(struct master *master, struct component *c)
-{
-	c->master = master;
-
-	list_add_tail(&c->master_node, &master->components);
-}
-
-/* Detach a component from a master. */
-static void component_detach_master(struct master *master, struct component *c)
-{
-	list_del(&c->master_node);
-
-	c->master = NULL;
-}
-
-/*
- * Add a component to a master, finding the component via the compare
- * function and compare data.  This is safe to call for duplicate matches
- * and will not result in the same component being added multiple times.
- */
-int component_master_add_child(struct master *master,
+static struct component *find_component(struct master *master,
 	int (*compare)(struct device *, void *), void *compare_data)
 {
 	struct component *c;
-	int ret = -ENXIO;
 
 	list_for_each_entry(c, &component_list, node) {
 		if (c->master && c->master != master)
 			continue;
 
-		if (compare(c->dev, compare_data)) {
-			if (!c->master)
-				component_attach_master(master, c);
-			ret = 0;
-			break;
-		}
+		if (compare(c->dev, compare_data))
+			return c;
 	}
 
-	return ret;
+	return NULL;
 }
-EXPORT_SYMBOL_GPL(component_master_add_child);
 
 static int find_components(struct master *master)
 {
@@ -112,39 +90,44 @@
 	size_t i;
 	int ret = 0;
 
-	if (!match) {
-		/*
-		 * Search the list of components, looking for components that
-		 * belong to this master, and attach them to the master.
-		 */
-		return master->ops->add_components(master->dev, master);
-	}
-
 	/*
 	 * Scan the array of match functions and attach
 	 * any components which are found to this master.
 	 */
 	for (i = 0; i < match->num; i++) {
-		ret = component_master_add_child(master,
-						 match->compare[i].fn,
-						 match->compare[i].data);
-		if (ret)
+		struct component_match_array *mc = &match->compare[i];
+		struct component *c;
+
+		dev_dbg(master->dev, "Looking for component %zu\n", i);
+
+		if (match->compare[i].component)
+			continue;
+
+		c = find_component(master, mc->compare, mc->data);
+		if (!c) {
+			ret = -ENXIO;
 			break;
+		}
+
+		dev_dbg(master->dev, "found component %s, duplicate %u\n", dev_name(c->dev), !!c->master);
+
+		/* Attach this component to the master */
+		match->compare[i].duplicate = !!c->master;
+		match->compare[i].component = c;
+		c->master = master;
 	}
 	return ret;
 }
 
-/* Detach all attached components from this master */
-static void master_remove_components(struct master *master)
+/* Detach component from associated master */
+static void remove_component(struct master *master, struct component *c)
 {
-	while (!list_empty(&master->components)) {
-		struct component *c = list_first_entry(&master->components,
-					struct component, master_node);
+	size_t i;
 
-		WARN_ON(c->master != master);
-
-		component_detach_master(master, c);
-	}
+	/* Detach the component from this master. */
+	for (i = 0; i < master->match->num; i++)
+		if (master->match->compare[i].component == c)
+			master->match->compare[i].component = NULL;
 }
 
 /*
@@ -159,44 +142,32 @@
 {
 	int ret;
 
-	if (master->bound)
-		return 0;
+	dev_dbg(master->dev, "trying to bring up master\n");
 
-	/*
-	 * Search the list of components, looking for components that
-	 * belong to this master, and attach them to the master.
-	 */
 	if (find_components(master)) {
-		/* Failed to find all components */
-		ret = 0;
-		goto out;
+		dev_dbg(master->dev, "master has incomplete components\n");
+		return 0;
 	}
 
 	if (component && component->master != master) {
-		ret = 0;
-		goto out;
+		dev_dbg(master->dev, "master is not for this component (%s)\n",
+			dev_name(component->dev));
+		return 0;
 	}
 
-	if (!devres_open_group(master->dev, NULL, GFP_KERNEL)) {
-		ret = -ENOMEM;
-		goto out;
-	}
+	if (!devres_open_group(master->dev, NULL, GFP_KERNEL))
+		return -ENOMEM;
 
 	/* Found all components */
 	ret = master->ops->bind(master->dev);
 	if (ret < 0) {
 		devres_release_group(master->dev, NULL);
 		dev_info(master->dev, "master bind failed: %d\n", ret);
-		goto out;
+		return ret;
 	}
 
 	master->bound = true;
 	return 1;
-
-out:
-	master_remove_components(master);
-
-	return ret;
 }
 
 static int try_to_bring_up_masters(struct component *component)
@@ -205,9 +176,11 @@
 	int ret = 0;
 
 	list_for_each_entry(m, &masters, node) {
-		ret = try_to_bring_up_master(m, component);
-		if (ret != 0)
-			break;
+		if (!m->bound) {
+			ret = try_to_bring_up_master(m, component);
+			if (ret != 0)
+				break;
+		}
 	}
 
 	return ret;
@@ -220,45 +193,57 @@
 		devres_release_group(master->dev, NULL);
 		master->bound = false;
 	}
-
-	master_remove_components(master);
 }
 
-static size_t component_match_size(size_t num)
+static void component_match_release(struct device *master,
+	struct component_match *match)
 {
-	return offsetof(struct component_match, compare[num]);
+	unsigned int i;
+
+	for (i = 0; i < match->num; i++) {
+		struct component_match_array *mc = &match->compare[i];
+
+		if (mc->release)
+			mc->release(master, mc->data);
+	}
 }
 
-static struct component_match *component_match_realloc(struct device *dev,
+static void devm_component_match_release(struct device *dev, void *res)
+{
+	component_match_release(dev, res);
+}
+
+static int component_match_realloc(struct device *dev,
 	struct component_match *match, size_t num)
 {
-	struct component_match *new;
+	struct component_match_array *new;
 
-	if (match && match->alloc == num)
-		return match;
+	if (match->alloc == num)
+		return 0;
 
-	new = devm_kmalloc(dev, component_match_size(num), GFP_KERNEL);
+	new = devm_kmalloc_array(dev, num, sizeof(*new), GFP_KERNEL);
 	if (!new)
-		return ERR_PTR(-ENOMEM);
+		return -ENOMEM;
 
-	if (match) {
-		memcpy(new, match, component_match_size(min(match->num, num)));
-		devm_kfree(dev, match);
-	} else {
-		new->num = 0;
+	if (match->compare) {
+		memcpy(new, match->compare, sizeof(*new) *
+					    min(match->num, num));
+		devm_kfree(dev, match->compare);
 	}
+	match->compare = new;
+	match->alloc = num;
 
-	new->alloc = num;
-
-	return new;
+	return 0;
 }
 
 /*
- * Add a component to be matched.
+ * Add a component to be matched, with a release function.
  *
  * The match array is first created or extended if necessary.
  */
-void component_match_add(struct device *dev, struct component_match **matchptr,
+void component_match_add_release(struct device *master,
+	struct component_match **matchptr,
+	void (*release)(struct device *, void *),
 	int (*compare)(struct device *, void *), void *compare_data)
 {
 	struct component_match *match = *matchptr;
@@ -266,22 +251,37 @@
 	if (IS_ERR(match))
 		return;
 
-	if (!match || match->num == match->alloc) {
-		size_t new_size = match ? match->alloc + 16 : 15;
+	if (!match) {
+		match = devres_alloc(devm_component_match_release,
+				     sizeof(*match), GFP_KERNEL);
+		if (!match) {
+			*matchptr = ERR_PTR(-ENOMEM);
+			return;
+		}
 
-		match = component_match_realloc(dev, match, new_size);
+		devres_add(master, match);
 
 		*matchptr = match;
-
-		if (IS_ERR(match))
-			return;
 	}
 
-	match->compare[match->num].fn = compare;
+	if (match->num == match->alloc) {
+		size_t new_size = match ? match->alloc + 16 : 15;
+		int ret;
+
+		ret = component_match_realloc(master, match, new_size);
+		if (ret) {
+			*matchptr = ERR_PTR(ret);
+			return;
+		}
+	}
+
+	match->compare[match->num].compare = compare;
+	match->compare[match->num].release = release;
 	match->compare[match->num].data = compare_data;
+	match->compare[match->num].component = NULL;
 	match->num++;
 }
-EXPORT_SYMBOL(component_match_add);
+EXPORT_SYMBOL(component_match_add_release);
 
 int component_master_add_with_match(struct device *dev,
 	const struct component_master_ops *ops,
@@ -290,15 +290,10 @@
 	struct master *master;
 	int ret;
 
-	if (ops->add_components && match)
-		return -EINVAL;
-
-	if (match) {
-		/* Reallocate the match array for its true size */
-		match = component_match_realloc(dev, match, match->num);
-		if (IS_ERR(match))
-			return PTR_ERR(match);
-	}
+	/* Reallocate the match array for its true size */
+	ret = component_match_realloc(dev, match, match->num);
+	if (ret)
+		return ret;
 
 	master = kzalloc(sizeof(*master), GFP_KERNEL);
 	if (!master)
@@ -307,7 +302,6 @@
 	master->dev = dev;
 	master->ops = ops;
 	master->match = match;
-	INIT_LIST_HEAD(&master->components);
 
 	/* Add to the list of available masters. */
 	mutex_lock(&component_mutex);
@@ -326,24 +320,28 @@
 }
 EXPORT_SYMBOL_GPL(component_master_add_with_match);
 
-int component_master_add(struct device *dev,
-	const struct component_master_ops *ops)
-{
-	return component_master_add_with_match(dev, ops, NULL);
-}
-EXPORT_SYMBOL_GPL(component_master_add);
-
 void component_master_del(struct device *dev,
 	const struct component_master_ops *ops)
 {
 	struct master *master;
+	int i;
 
 	mutex_lock(&component_mutex);
 	master = __master_find(dev, ops);
 	if (master) {
+		struct component_match *match = master->match;
+
 		take_down_master(master);
 
 		list_del(&master->node);
+
+		if (match) {
+			for (i = 0; i < match->num; i++) {
+				struct component *c = match->compare[i].component;
+				if (c)
+					c->master = NULL;
+			}
+		}
 		kfree(master);
 	}
 	mutex_unlock(&component_mutex);
@@ -366,6 +364,7 @@
 {
 	struct master *master;
 	struct component *c;
+	size_t i;
 
 	WARN_ON(!mutex_is_locked(&component_mutex));
 
@@ -373,8 +372,12 @@
 	if (!master)
 		return;
 
-	list_for_each_entry_reverse(c, &master->components, master_node)
-		component_unbind(c, master, data);
+	/* Unbind components in reverse order */
+	for (i = master->match->num; i--; )
+		if (!master->match->compare[i].duplicate) {
+			c = master->match->compare[i].component;
+			component_unbind(c, master, data);
+		}
 }
 EXPORT_SYMBOL_GPL(component_unbind_all);
 
@@ -434,6 +437,7 @@
 {
 	struct master *master;
 	struct component *c;
+	size_t i;
 	int ret = 0;
 
 	WARN_ON(!mutex_is_locked(&component_mutex));
@@ -442,16 +446,21 @@
 	if (!master)
 		return -EINVAL;
 
-	list_for_each_entry(c, &master->components, master_node) {
-		ret = component_bind(c, master, data);
-		if (ret)
-			break;
-	}
+	/* Bind components in match order */
+	for (i = 0; i < master->match->num; i++)
+		if (!master->match->compare[i].duplicate) {
+			c = master->match->compare[i].component;
+			ret = component_bind(c, master, data);
+			if (ret)
+				break;
+		}
 
 	if (ret != 0) {
-		list_for_each_entry_continue_reverse(c, &master->components,
-						     master_node)
-			component_unbind(c, master, data);
+		for (; i--; )
+			if (!master->match->compare[i].duplicate) {
+				c = master->match->compare[i].component;
+				component_unbind(c, master, data);
+			}
 	}
 
 	return ret;
@@ -499,8 +508,10 @@
 			break;
 		}
 
-	if (component && component->master)
+	if (component && component->master) {
 		take_down_master(component->master);
+		remove_component(component->master, component);
+	}
 
 	mutex_unlock(&component_mutex);
 
diff --git a/drivers/base/platform-msi.c b/drivers/base/platform-msi.c
index 5df4575..47c43386 100644
--- a/drivers/base/platform-msi.c
+++ b/drivers/base/platform-msi.c
@@ -24,13 +24,17 @@
 #include <linux/msi.h>
 #include <linux/slab.h>
 
-#define DEV_ID_SHIFT	24
+#define DEV_ID_SHIFT	21
+#define MAX_DEV_MSIS	(1 << (32 - DEV_ID_SHIFT))
 
 /*
  * Internal data structure containing a (made up, but unique) devid
  * and the callback to write the MSI message.
  */
 struct platform_msi_priv_data {
+	struct device		*dev;
+	void 			*host_data;
+	msi_alloc_info_t	arg;
 	irq_write_msi_msg_t	write_msg;
 	int			devid;
 };
@@ -110,39 +114,49 @@
 		chip->irq_write_msi_msg = platform_msi_write_msg;
 }
 
-static void platform_msi_free_descs(struct device *dev)
+static void platform_msi_free_descs(struct device *dev, int base, int nvec)
 {
 	struct msi_desc *desc, *tmp;
 
 	list_for_each_entry_safe(desc, tmp, dev_to_msi_list(dev), list) {
-		list_del(&desc->list);
-		free_msi_entry(desc);
+		if (desc->platform.msi_index >= base &&
+		    desc->platform.msi_index < (base + nvec)) {
+			list_del(&desc->list);
+			free_msi_entry(desc);
+		}
 	}
 }
 
-static int platform_msi_alloc_descs(struct device *dev, int nvec,
-				    struct platform_msi_priv_data *data)
+static int platform_msi_alloc_descs_with_irq(struct device *dev, int virq,
+					     int nvec,
+					     struct platform_msi_priv_data *data)
 
 {
-	int i;
+	struct msi_desc *desc;
+	int i, base = 0;
+
+	if (!list_empty(dev_to_msi_list(dev))) {
+		desc = list_last_entry(dev_to_msi_list(dev),
+				       struct msi_desc, list);
+		base = desc->platform.msi_index + 1;
+	}
 
 	for (i = 0; i < nvec; i++) {
-		struct msi_desc *desc;
-
 		desc = alloc_msi_entry(dev);
 		if (!desc)
 			break;
 
 		desc->platform.msi_priv_data = data;
-		desc->platform.msi_index = i;
+		desc->platform.msi_index = base + i;
 		desc->nvec_used = 1;
+		desc->irq = virq ? virq + i : 0;
 
 		list_add_tail(&desc->list, dev_to_msi_list(dev));
 	}
 
 	if (i != nvec) {
 		/* Clean up the mess */
-		platform_msi_free_descs(dev);
+		platform_msi_free_descs(dev, base, nvec);
 
 		return -ENOMEM;
 	}
@@ -150,6 +164,13 @@
 	return 0;
 }
 
+static int platform_msi_alloc_descs(struct device *dev, int nvec,
+				    struct platform_msi_priv_data *data)
+
+{
+	return platform_msi_alloc_descs_with_irq(dev, 0, nvec, data);
+}
+
 /**
  * platform_msi_create_irq_domain - Create a platform MSI interrupt domain
  * @fwnode:		Optional fwnode of the interrupt controller
@@ -180,6 +201,53 @@
 	return domain;
 }
 
+static struct platform_msi_priv_data *
+platform_msi_alloc_priv_data(struct device *dev, unsigned int nvec,
+			     irq_write_msi_msg_t write_msi_msg)
+{
+	struct platform_msi_priv_data *datap;
+	/*
+	 * Limit the number of interrupts to 256 per device. Should we
+	 * need to bump this up, DEV_ID_SHIFT should be adjusted
+	 * accordingly (which would impact the max number of MSI
+	 * capable devices).
+	 */
+	if (!dev->msi_domain || !write_msi_msg || !nvec || nvec > MAX_DEV_MSIS)
+		return ERR_PTR(-EINVAL);
+
+	if (dev->msi_domain->bus_token != DOMAIN_BUS_PLATFORM_MSI) {
+		dev_err(dev, "Incompatible msi_domain, giving up\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	/* Already had a helping of MSI? Greed... */
+	if (!list_empty(dev_to_msi_list(dev)))
+		return ERR_PTR(-EBUSY);
+
+	datap = kzalloc(sizeof(*datap), GFP_KERNEL);
+	if (!datap)
+		return ERR_PTR(-ENOMEM);
+
+	datap->devid = ida_simple_get(&platform_msi_devid_ida,
+				      0, 1 << DEV_ID_SHIFT, GFP_KERNEL);
+	if (datap->devid < 0) {
+		int err = datap->devid;
+		kfree(datap);
+		return ERR_PTR(err);
+	}
+
+	datap->write_msg = write_msi_msg;
+	datap->dev = dev;
+
+	return datap;
+}
+
+static void platform_msi_free_priv_data(struct platform_msi_priv_data *data)
+{
+	ida_simple_remove(&platform_msi_devid_ida, data->devid);
+	kfree(data);
+}
+
 /**
  * platform_msi_domain_alloc_irqs - Allocate MSI interrupts for @dev
  * @dev:		The device for which to allocate interrupts
@@ -195,41 +263,13 @@
 	struct platform_msi_priv_data *priv_data;
 	int err;
 
-	/*
-	 * Limit the number of interrupts to 256 per device. Should we
-	 * need to bump this up, DEV_ID_SHIFT should be adjusted
-	 * accordingly (which would impact the max number of MSI
-	 * capable devices).
-	 */
-	if (!dev->msi_domain || !write_msi_msg || !nvec ||
-	    nvec > (1 << (32 - DEV_ID_SHIFT)))
-		return -EINVAL;
-
-	if (dev->msi_domain->bus_token != DOMAIN_BUS_PLATFORM_MSI) {
-		dev_err(dev, "Incompatible msi_domain, giving up\n");
-		return -EINVAL;
-	}
-
-	/* Already had a helping of MSI? Greed... */
-	if (!list_empty(dev_to_msi_list(dev)))
-		return -EBUSY;
-
-	priv_data = kzalloc(sizeof(*priv_data), GFP_KERNEL);
-	if (!priv_data)
-		return -ENOMEM;
-
-	priv_data->devid = ida_simple_get(&platform_msi_devid_ida,
-					  0, 1 << DEV_ID_SHIFT, GFP_KERNEL);
-	if (priv_data->devid < 0) {
-		err = priv_data->devid;
-		goto out_free_data;
-	}
-
-	priv_data->write_msg = write_msi_msg;
+	priv_data = platform_msi_alloc_priv_data(dev, nvec, write_msi_msg);
+	if (IS_ERR(priv_data))
+		return PTR_ERR(priv_data);
 
 	err = platform_msi_alloc_descs(dev, nvec, priv_data);
 	if (err)
-		goto out_free_id;
+		goto out_free_priv_data;
 
 	err = msi_domain_alloc_irqs(dev->msi_domain, dev, nvec);
 	if (err)
@@ -238,11 +278,9 @@
 	return 0;
 
 out_free_desc:
-	platform_msi_free_descs(dev);
-out_free_id:
-	ida_simple_remove(&platform_msi_devid_ida, priv_data->devid);
-out_free_data:
-	kfree(priv_data);
+	platform_msi_free_descs(dev, 0, nvec);
+out_free_priv_data:
+	platform_msi_free_priv_data(priv_data);
 
 	return err;
 }
@@ -253,18 +291,126 @@
  */
 void platform_msi_domain_free_irqs(struct device *dev)
 {
-	struct msi_desc *desc;
+	if (!list_empty(dev_to_msi_list(dev))) {
+		struct msi_desc *desc;
 
-	desc = first_msi_entry(dev);
-	if (desc) {
-		struct platform_msi_priv_data *data;
-
-		data = desc->platform.msi_priv_data;
-
-		ida_simple_remove(&platform_msi_devid_ida, data->devid);
-		kfree(data);
+		desc = first_msi_entry(dev);
+		platform_msi_free_priv_data(desc->platform.msi_priv_data);
 	}
 
 	msi_domain_free_irqs(dev->msi_domain, dev);
-	platform_msi_free_descs(dev);
+	platform_msi_free_descs(dev, 0, MAX_DEV_MSIS);
+}
+
+/**
+ * platform_msi_get_host_data - Query the private data associated with
+ *                              a platform-msi domain
+ * @domain:	The platform-msi domain
+ *
+ * Returns the private data provided when calling
+ * platform_msi_create_device_domain.
+ */
+void *platform_msi_get_host_data(struct irq_domain *domain)
+{
+	struct platform_msi_priv_data *data = domain->host_data;
+	return data->host_data;
+}
+
+/**
+ * platform_msi_create_device_domain - Create a platform-msi domain
+ *
+ * @dev:		The device generating the MSIs
+ * @nvec:		The number of MSIs that need to be allocated
+ * @write_msi_msg:	Callback to write an interrupt message for @dev
+ * @ops:		The hierarchy domain operations to use
+ * @host_data:		Private data associated to this domain
+ *
+ * Returns an irqdomain for @nvec interrupts
+ */
+struct irq_domain *
+platform_msi_create_device_domain(struct device *dev,
+				  unsigned int nvec,
+				  irq_write_msi_msg_t write_msi_msg,
+				  const struct irq_domain_ops *ops,
+				  void *host_data)
+{
+	struct platform_msi_priv_data *data;
+	struct irq_domain *domain;
+	int err;
+
+	data = platform_msi_alloc_priv_data(dev, nvec, write_msi_msg);
+	if (IS_ERR(data))
+		return NULL;
+
+	data->host_data = host_data;
+	domain = irq_domain_create_hierarchy(dev->msi_domain, 0, nvec,
+					     of_node_to_fwnode(dev->of_node),
+					     ops, data);
+	if (!domain)
+		goto free_priv;
+
+	err = msi_domain_prepare_irqs(domain->parent, dev, nvec, &data->arg);
+	if (err)
+		goto free_domain;
+
+	return domain;
+
+free_domain:
+	irq_domain_remove(domain);
+free_priv:
+	platform_msi_free_priv_data(data);
+	return NULL;
+}
+
+/**
+ * platform_msi_domain_free - Free interrupts associated with a platform-msi
+ *                            domain
+ *
+ * @domain:	The platform-msi domain
+ * @virq:	The base irq from which to perform the free operation
+ * @nvec:	How many interrupts to free from @virq
+ */
+void platform_msi_domain_free(struct irq_domain *domain, unsigned int virq,
+			      unsigned int nvec)
+{
+	struct platform_msi_priv_data *data = domain->host_data;
+	struct msi_desc *desc;
+	for_each_msi_entry(desc, data->dev) {
+		if (WARN_ON(!desc->irq || desc->nvec_used != 1))
+			return;
+		if (!(desc->irq >= virq && desc->irq < (virq + nvec)))
+			continue;
+
+		irq_domain_free_irqs_common(domain, desc->irq, 1);
+	}
+}
+
+/**
+ * platform_msi_domain_alloc - Allocate interrupts associated with
+ *			       a platform-msi domain
+ *
+ * @domain:	The platform-msi domain
+ * @virq:	The base irq from which to perform the allocate operation
+ * @nvec:	How many interrupts to free from @virq
+ *
+ * Return 0 on success, or an error code on failure. Must be called
+ * with irq_domain_mutex held (which can only be done as part of a
+ * top-level interrupt allocation).
+ */
+int platform_msi_domain_alloc(struct irq_domain *domain, unsigned int virq,
+			      unsigned int nr_irqs)
+{
+	struct platform_msi_priv_data *data = domain->host_data;
+	int err;
+
+	err = platform_msi_alloc_descs_with_irq(data->dev, virq, nr_irqs, data);
+	if (err)
+		return err;
+
+	err = msi_domain_populate_irqs(domain->parent, data->dev,
+				       virq, nr_irqs, &data->arg);
+	if (err)
+		platform_msi_domain_free(domain, virq, nr_irqs);
+
+	return err;
 }
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index 1dd6d3b..73e3994 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -117,6 +117,26 @@
 EXPORT_SYMBOL_GPL(platform_get_irq);
 
 /**
+ * platform_irq_count - Count the number of IRQs a platform device uses
+ * @dev: platform device
+ *
+ * Return: Number of IRQs a platform device uses or EPROBE_DEFER
+ */
+int platform_irq_count(struct platform_device *dev)
+{
+	int ret, nr = 0;
+
+	while ((ret = platform_get_irq(dev, nr)) >= 0)
+		nr++;
+
+	if (ret == -EPROBE_DEFER)
+		return ret;
+
+	return nr;
+}
+EXPORT_SYMBOL_GPL(platform_irq_count);
+
+/**
  * platform_get_resource_byname - get a resource for a device by name
  * @dev: platform device
  * @type: resource type
diff --git a/drivers/base/regmap/regcache-flat.c b/drivers/base/regmap/regcache-flat.c
index 0246f44..686c9e0 100644
--- a/drivers/base/regmap/regcache-flat.c
+++ b/drivers/base/regmap/regcache-flat.c
@@ -21,7 +21,7 @@
 	int i;
 	unsigned int *cache;
 
-	map->cache = kzalloc(sizeof(unsigned int) * (map->max_register + 1),
+	map->cache = kcalloc(map->max_register + 1, sizeof(unsigned int),
 			     GFP_KERNEL);
 	if (!map->cache)
 		return -ENOMEM;
diff --git a/drivers/base/regmap/regcache-lzo.c b/drivers/base/regmap/regcache-lzo.c
index 736e0d3..6f77d73 100644
--- a/drivers/base/regmap/regcache-lzo.c
+++ b/drivers/base/regmap/regcache-lzo.c
@@ -139,7 +139,7 @@
 	ret = 0;
 
 	blkcount = regcache_lzo_block_count(map);
-	map->cache = kzalloc(blkcount * sizeof *lzo_blocks,
+	map->cache = kcalloc(blkcount, sizeof(*lzo_blocks),
 			     GFP_KERNEL);
 	if (!map->cache)
 		return -ENOMEM;
@@ -152,8 +152,8 @@
 	 * that register.
 	 */
 	bmp_size = map->num_reg_defaults_raw;
-	sync_bmp = kmalloc(BITS_TO_LONGS(bmp_size) * sizeof(long),
-			   GFP_KERNEL);
+	sync_bmp = kmalloc_array(BITS_TO_LONGS(bmp_size), sizeof(long),
+				 GFP_KERNEL);
 	if (!sync_bmp) {
 		ret = -ENOMEM;
 		goto err;
diff --git a/drivers/base/regmap/regcache-rbtree.c b/drivers/base/regmap/regcache-rbtree.c
index 56486d9..aa56af8 100644
--- a/drivers/base/regmap/regcache-rbtree.c
+++ b/drivers/base/regmap/regcache-rbtree.c
@@ -361,13 +361,14 @@
 		rbnode->base_reg = reg;
 	}
 
-	rbnode->block = kmalloc(rbnode->blklen * map->cache_word_size,
-				GFP_KERNEL);
+	rbnode->block = kmalloc_array(rbnode->blklen, map->cache_word_size,
+				      GFP_KERNEL);
 	if (!rbnode->block)
 		goto err_free;
 
-	rbnode->cache_present = kzalloc(BITS_TO_LONGS(rbnode->blklen) *
-		sizeof(*rbnode->cache_present), GFP_KERNEL);
+	rbnode->cache_present = kcalloc(BITS_TO_LONGS(rbnode->blklen),
+					sizeof(*rbnode->cache_present),
+					GFP_KERNEL);
 	if (!rbnode->cache_present)
 		goto err_free_block;
 
@@ -413,8 +414,8 @@
 		max = reg + max_dist;
 
 		/* look for an adjacent register to the one we are about to add */
-		for (node = rb_first(&rbtree_ctx->root); node;
-		     node = rb_next(node)) {
+		node = rbtree_ctx->root.rb_node;
+		while (node) {
 			rbnode_tmp = rb_entry(node, struct regcache_rbtree_node,
 					      node);
 
@@ -425,6 +426,11 @@
 				new_base_reg = min(reg, base_reg);
 				new_top_reg = max(reg, top_reg);
 			} else {
+				if (max < base_reg)
+					node = node->rb_left;
+				else
+					node = node->rb_right;
+
 				continue;
 			}
 
diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c
index 4c07802..348be3a 100644
--- a/drivers/base/regmap/regcache.c
+++ b/drivers/base/regmap/regcache.c
@@ -100,15 +100,25 @@
 	int i;
 	void *tmp_buf;
 
-	for (i = 0; i < config->num_reg_defaults; i++)
-		if (config->reg_defaults[i].reg % map->reg_stride)
-			return -EINVAL;
-
 	if (map->cache_type == REGCACHE_NONE) {
+		if (config->reg_defaults || config->num_reg_defaults_raw)
+			dev_warn(map->dev,
+				 "No cache used with register defaults set!\n");
+
 		map->cache_bypass = true;
 		return 0;
 	}
 
+	if (config->reg_defaults && !config->num_reg_defaults) {
+		dev_err(map->dev,
+			 "Register defaults are set without the number!\n");
+		return -EINVAL;
+	}
+
+	for (i = 0; i < config->num_reg_defaults; i++)
+		if (config->reg_defaults[i].reg % map->reg_stride)
+			return -EINVAL;
+
 	for (i = 0; i < ARRAY_SIZE(cache_types); i++)
 		if (cache_types[i]->type == map->cache_type)
 			break;
@@ -138,8 +148,6 @@
 	 * a copy of it.
 	 */
 	if (config->reg_defaults) {
-		if (!map->num_reg_defaults)
-			return -EINVAL;
 		tmp_buf = kmemdup(config->reg_defaults, map->num_reg_defaults *
 				  sizeof(struct reg_default), GFP_KERNEL);
 		if (!tmp_buf)
@@ -535,19 +543,30 @@
 	switch (map->cache_word_size) {
 	case 1: {
 		u8 *cache = base;
+
 		cache[idx] = val;
 		break;
 	}
 	case 2: {
 		u16 *cache = base;
+
 		cache[idx] = val;
 		break;
 	}
 	case 4: {
 		u32 *cache = base;
+
 		cache[idx] = val;
 		break;
 	}
+#ifdef CONFIG_64BIT
+	case 8: {
+		u64 *cache = base;
+
+		cache[idx] = val;
+		break;
+	}
+#endif
 	default:
 		BUG();
 	}
@@ -568,16 +587,26 @@
 	switch (map->cache_word_size) {
 	case 1: {
 		const u8 *cache = base;
+
 		return cache[idx];
 	}
 	case 2: {
 		const u16 *cache = base;
+
 		return cache[idx];
 	}
 	case 4: {
 		const u32 *cache = base;
+
 		return cache[idx];
 	}
+#ifdef CONFIG_64BIT
+	case 8: {
+		const u64 *cache = base;
+
+		return cache[idx];
+	}
+#endif
 	default:
 		BUG();
 	}
diff --git a/drivers/base/regmap/regmap-debugfs.c b/drivers/base/regmap/regmap-debugfs.c
index 3f0a7e2..1ee3d40 100644
--- a/drivers/base/regmap/regmap-debugfs.c
+++ b/drivers/base/regmap/regmap-debugfs.c
@@ -397,72 +397,39 @@
 	.llseek = default_llseek,
 };
 
-static ssize_t regmap_access_read_file(struct file *file,
-				       char __user *user_buf, size_t count,
-				       loff_t *ppos)
+static int regmap_access_show(struct seq_file *s, void *ignored)
 {
-	int reg_len, tot_len;
-	size_t buf_pos = 0;
-	loff_t p = 0;
-	ssize_t ret;
-	int i;
-	struct regmap *map = file->private_data;
-	char *buf;
+	struct regmap *map = s->private;
+	int i, reg_len;
 
-	if (*ppos < 0 || !count)
-		return -EINVAL;
-
-	buf = kmalloc(count, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-
-	/* Calculate the length of a fixed format  */
 	reg_len = regmap_calc_reg_len(map->max_register);
-	tot_len = reg_len + 10; /* ': R W V P\n' */
 
 	for (i = 0; i <= map->max_register; i += map->reg_stride) {
 		/* Ignore registers which are neither readable nor writable */
 		if (!regmap_readable(map, i) && !regmap_writeable(map, i))
 			continue;
 
-		/* If we're in the region the user is trying to read */
-		if (p >= *ppos) {
-			/* ...but not beyond it */
-			if (buf_pos + tot_len + 1 >= count)
-				break;
-
-			/* Format the register */
-			snprintf(buf + buf_pos, count - buf_pos,
-				 "%.*x: %c %c %c %c\n",
-				 reg_len, i,
-				 regmap_readable(map, i) ? 'y' : 'n',
-				 regmap_writeable(map, i) ? 'y' : 'n',
-				 regmap_volatile(map, i) ? 'y' : 'n',
-				 regmap_precious(map, i) ? 'y' : 'n');
-
-			buf_pos += tot_len;
-		}
-		p += tot_len;
+		/* Format the register */
+		seq_printf(s, "%.*x: %c %c %c %c\n", reg_len, i,
+			   regmap_readable(map, i) ? 'y' : 'n',
+			   regmap_writeable(map, i) ? 'y' : 'n',
+			   regmap_volatile(map, i) ? 'y' : 'n',
+			   regmap_precious(map, i) ? 'y' : 'n');
 	}
 
-	ret = buf_pos;
+	return 0;
+}
 
-	if (copy_to_user(user_buf, buf, buf_pos)) {
-		ret = -EFAULT;
-		goto out;
-	}
-
-	*ppos += buf_pos;
-
-out:
-	kfree(buf);
-	return ret;
+static int access_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, regmap_access_show, inode->i_private);
 }
 
 static const struct file_operations regmap_access_fops = {
-	.open = simple_open,
-	.read = regmap_access_read_file,
-	.llseek = default_llseek,
+	.open		= access_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
 };
 
 static ssize_t regmap_cache_only_write_file(struct file *file,
diff --git a/drivers/base/regmap/regmap-irq.c b/drivers/base/regmap/regmap-irq.c
index 8d16db5..9b0d202 100644
--- a/drivers/base/regmap/regmap-irq.c
+++ b/drivers/base/regmap/regmap-irq.c
@@ -39,8 +39,11 @@
 	unsigned int *mask_buf;
 	unsigned int *mask_buf_def;
 	unsigned int *wake_buf;
+	unsigned int *type_buf;
+	unsigned int *type_buf_def;
 
 	unsigned int irq_reg_stride;
+	unsigned int type_reg_stride;
 };
 
 static inline const
@@ -144,6 +147,22 @@
 		}
 	}
 
+	for (i = 0; i < d->chip->num_type_reg; i++) {
+		if (!d->type_buf_def[i])
+			continue;
+		reg = d->chip->type_base +
+			(i * map->reg_stride * d->type_reg_stride);
+		if (d->chip->type_invert)
+			ret = regmap_update_bits(d->map, reg,
+				d->type_buf_def[i], ~d->type_buf[i]);
+		else
+			ret = regmap_update_bits(d->map, reg,
+				d->type_buf_def[i], d->type_buf[i]);
+		if (ret != 0)
+			dev_err(d->map->dev, "Failed to sync type in %x\n",
+				reg);
+	}
+
 	if (d->chip->runtime_pm)
 		pm_runtime_put(map->dev);
 
@@ -178,6 +197,38 @@
 	d->mask_buf[irq_data->reg_offset / map->reg_stride] |= irq_data->mask;
 }
 
+static int regmap_irq_set_type(struct irq_data *data, unsigned int type)
+{
+	struct regmap_irq_chip_data *d = irq_data_get_irq_chip_data(data);
+	struct regmap *map = d->map;
+	const struct regmap_irq *irq_data = irq_to_regmap_irq(d, data->hwirq);
+	int reg = irq_data->type_reg_offset / map->reg_stride;
+
+	if (!(irq_data->type_rising_mask | irq_data->type_falling_mask))
+		return 0;
+
+	d->type_buf[reg] &= ~(irq_data->type_falling_mask |
+					irq_data->type_rising_mask);
+	switch (type) {
+	case IRQ_TYPE_EDGE_FALLING:
+		d->type_buf[reg] |= irq_data->type_falling_mask;
+		break;
+
+	case IRQ_TYPE_EDGE_RISING:
+		d->type_buf[reg] |= irq_data->type_rising_mask;
+		break;
+
+	case IRQ_TYPE_EDGE_BOTH:
+		d->type_buf[reg] |= (irq_data->type_falling_mask |
+					irq_data->type_rising_mask);
+		break;
+
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
 static int regmap_irq_set_wake(struct irq_data *data, unsigned int on)
 {
 	struct regmap_irq_chip_data *d = irq_data_get_irq_chip_data(data);
@@ -204,6 +255,7 @@
 	.irq_bus_sync_unlock	= regmap_irq_sync_unlock,
 	.irq_disable		= regmap_irq_disable,
 	.irq_enable		= regmap_irq_enable,
+	.irq_set_type		= regmap_irq_set_type,
 	.irq_set_wake		= regmap_irq_set_wake,
 };
 
@@ -386,28 +438,40 @@
 	if (!d)
 		return -ENOMEM;
 
-	d->status_buf = kzalloc(sizeof(unsigned int) * chip->num_regs,
+	d->status_buf = kcalloc(chip->num_regs, sizeof(unsigned int),
 				GFP_KERNEL);
 	if (!d->status_buf)
 		goto err_alloc;
 
-	d->mask_buf = kzalloc(sizeof(unsigned int) * chip->num_regs,
+	d->mask_buf = kcalloc(chip->num_regs, sizeof(unsigned int),
 			      GFP_KERNEL);
 	if (!d->mask_buf)
 		goto err_alloc;
 
-	d->mask_buf_def = kzalloc(sizeof(unsigned int) * chip->num_regs,
+	d->mask_buf_def = kcalloc(chip->num_regs, sizeof(unsigned int),
 				  GFP_KERNEL);
 	if (!d->mask_buf_def)
 		goto err_alloc;
 
 	if (chip->wake_base) {
-		d->wake_buf = kzalloc(sizeof(unsigned int) * chip->num_regs,
+		d->wake_buf = kcalloc(chip->num_regs, sizeof(unsigned int),
 				      GFP_KERNEL);
 		if (!d->wake_buf)
 			goto err_alloc;
 	}
 
+	if (chip->num_type_reg) {
+		d->type_buf_def = kcalloc(chip->num_type_reg,
+					sizeof(unsigned int), GFP_KERNEL);
+		if (!d->type_buf_def)
+			goto err_alloc;
+
+		d->type_buf = kcalloc(chip->num_type_reg, sizeof(unsigned int),
+				      GFP_KERNEL);
+		if (!d->type_buf)
+			goto err_alloc;
+	}
+
 	d->irq_chip = regmap_irq_chip;
 	d->irq_chip.name = chip->name;
 	d->irq = irq;
@@ -420,10 +484,16 @@
 	else
 		d->irq_reg_stride = 1;
 
+	if (chip->type_reg_stride)
+		d->type_reg_stride = chip->type_reg_stride;
+	else
+		d->type_reg_stride = 1;
+
 	if (!map->use_single_read && map->reg_stride == 1 &&
 	    d->irq_reg_stride == 1) {
-		d->status_reg_buf = kmalloc(map->format.val_bytes *
-					    chip->num_regs, GFP_KERNEL);
+		d->status_reg_buf = kmalloc_array(chip->num_regs,
+						  map->format.val_bytes,
+						  GFP_KERNEL);
 		if (!d->status_reg_buf)
 			goto err_alloc;
 	}
@@ -511,6 +581,33 @@
 		}
 	}
 
+	if (chip->num_type_reg) {
+		for (i = 0; i < chip->num_irqs; i++) {
+			reg = chip->irqs[i].type_reg_offset / map->reg_stride;
+			d->type_buf_def[reg] |= chip->irqs[i].type_rising_mask |
+					chip->irqs[i].type_falling_mask;
+		}
+		for (i = 0; i < chip->num_type_reg; ++i) {
+			if (!d->type_buf_def[i])
+				continue;
+
+			reg = chip->type_base +
+				(i * map->reg_stride * d->type_reg_stride);
+			if (chip->type_invert)
+				ret = regmap_update_bits(map, reg,
+					d->type_buf_def[i], 0xFF);
+			else
+				ret = regmap_update_bits(map, reg,
+					d->type_buf_def[i], 0x0);
+			if (ret != 0) {
+				dev_err(map->dev,
+					"Failed to set type in 0x%x: %x\n",
+					reg, ret);
+				goto err_alloc;
+			}
+		}
+	}
+
 	if (irq_base)
 		d->domain = irq_domain_add_legacy(map->dev->of_node,
 						  chip->num_irqs, irq_base, 0,
@@ -541,6 +638,8 @@
 err_domain:
 	/* Should really dispose of the domain but... */
 err_alloc:
+	kfree(d->type_buf);
+	kfree(d->type_buf_def);
 	kfree(d->wake_buf);
 	kfree(d->mask_buf_def);
 	kfree(d->mask_buf);
@@ -564,6 +663,8 @@
 
 	free_irq(irq, d);
 	irq_domain_remove(d->domain);
+	kfree(d->type_buf);
+	kfree(d->type_buf_def);
 	kfree(d->wake_buf);
 	kfree(d->mask_buf_def);
 	kfree(d->mask_buf);
diff --git a/drivers/base/regmap/regmap-mmio.c b/drivers/base/regmap/regmap-mmio.c
index 426a57e..8812bfb 100644
--- a/drivers/base/regmap/regmap-mmio.c
+++ b/drivers/base/regmap/regmap-mmio.c
@@ -61,6 +61,33 @@
 	}
 }
 
+static int regmap_mmio_get_min_stride(size_t val_bits)
+{
+	int min_stride;
+
+	switch (val_bits) {
+	case 8:
+		/* The core treats 0 as 1 */
+		min_stride = 0;
+		return 0;
+	case 16:
+		min_stride = 2;
+		break;
+	case 32:
+		min_stride = 4;
+		break;
+#ifdef CONFIG_64BIT
+	case 64:
+		min_stride = 8;
+		break;
+#endif
+	default:
+		return -EINVAL;
+	}
+
+	return min_stride;
+}
+
 static inline void regmap_mmio_count_check(size_t count, u32 offset)
 {
 	BUG_ON(count <= offset);
@@ -106,17 +133,17 @@
 	while (val_size) {
 		switch (ctx->val_bytes) {
 		case 1:
-			writeb(*(u8 *)val, ctx->regs + offset);
+			__raw_writeb(*(u8 *)val, ctx->regs + offset);
 			break;
 		case 2:
-			writew(*(u16 *)val, ctx->regs + offset);
+			__raw_writew(*(u16 *)val, ctx->regs + offset);
 			break;
 		case 4:
-			writel(*(u32 *)val, ctx->regs + offset);
+			__raw_writel(*(u32 *)val, ctx->regs + offset);
 			break;
 #ifdef CONFIG_64BIT
 		case 8:
-			writeq(*(u64 *)val, ctx->regs + offset);
+			__raw_writeq(*(u64 *)val, ctx->regs + offset);
 			break;
 #endif
 		default:
@@ -166,17 +193,17 @@
 	while (val_size) {
 		switch (ctx->val_bytes) {
 		case 1:
-			*(u8 *)val = readb(ctx->regs + offset);
+			*(u8 *)val = __raw_readb(ctx->regs + offset);
 			break;
 		case 2:
-			*(u16 *)val = readw(ctx->regs + offset);
+			*(u16 *)val = __raw_readw(ctx->regs + offset);
 			break;
 		case 4:
-			*(u32 *)val = readl(ctx->regs + offset);
+			*(u32 *)val = __raw_readl(ctx->regs + offset);
 			break;
 #ifdef CONFIG_64BIT
 		case 8:
-			*(u64 *)val = readq(ctx->regs + offset);
+			*(u64 *)val = __raw_readq(ctx->regs + offset);
 			break;
 #endif
 		default:
@@ -231,26 +258,9 @@
 	if (config->pad_bits)
 		return ERR_PTR(-EINVAL);
 
-	switch (config->val_bits) {
-	case 8:
-		/* The core treats 0 as 1 */
-		min_stride = 0;
-		break;
-	case 16:
-		min_stride = 2;
-		break;
-	case 32:
-		min_stride = 4;
-		break;
-#ifdef CONFIG_64BIT
-	case 64:
-		min_stride = 8;
-		break;
-#endif
-		break;
-	default:
-		return ERR_PTR(-EINVAL);
-	}
+	min_stride = regmap_mmio_get_min_stride(config->val_bits);
+	if (min_stride < 0)
+		return ERR_PTR(min_stride);
 
 	if (config->reg_stride < min_stride)
 		return ERR_PTR(-EINVAL);
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index 4ac63c0..ee54e84 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -245,6 +245,28 @@
 	*(u32 *)buf = val << shift;
 }
 
+#ifdef CONFIG_64BIT
+static void regmap_format_64_be(void *buf, unsigned int val, unsigned int shift)
+{
+	__be64 *b = buf;
+
+	b[0] = cpu_to_be64((u64)val << shift);
+}
+
+static void regmap_format_64_le(void *buf, unsigned int val, unsigned int shift)
+{
+	__le64 *b = buf;
+
+	b[0] = cpu_to_le64((u64)val << shift);
+}
+
+static void regmap_format_64_native(void *buf, unsigned int val,
+				    unsigned int shift)
+{
+	*(u64 *)buf = (u64)val << shift;
+}
+#endif
+
 static void regmap_parse_inplace_noop(void *buf)
 {
 }
@@ -332,6 +354,41 @@
 	return *(u32 *)buf;
 }
 
+#ifdef CONFIG_64BIT
+static unsigned int regmap_parse_64_be(const void *buf)
+{
+	const __be64 *b = buf;
+
+	return be64_to_cpu(b[0]);
+}
+
+static unsigned int regmap_parse_64_le(const void *buf)
+{
+	const __le64 *b = buf;
+
+	return le64_to_cpu(b[0]);
+}
+
+static void regmap_parse_64_be_inplace(void *buf)
+{
+	__be64 *b = buf;
+
+	b[0] = be64_to_cpu(b[0]);
+}
+
+static void regmap_parse_64_le_inplace(void *buf)
+{
+	__le64 *b = buf;
+
+	b[0] = le64_to_cpu(b[0]);
+}
+
+static unsigned int regmap_parse_64_native(const void *buf)
+{
+	return *(u64 *)buf;
+}
+#endif
+
 static void regmap_lock_mutex(void *__map)
 {
 	struct regmap *map = __map;
@@ -712,6 +769,21 @@
 		}
 		break;
 
+#ifdef CONFIG_64BIT
+	case 64:
+		switch (reg_endian) {
+		case REGMAP_ENDIAN_BIG:
+			map->format.format_reg = regmap_format_64_be;
+			break;
+		case REGMAP_ENDIAN_NATIVE:
+			map->format.format_reg = regmap_format_64_native;
+			break;
+		default:
+			goto err_map;
+		}
+		break;
+#endif
+
 	default:
 		goto err_map;
 	}
@@ -771,6 +843,28 @@
 			goto err_map;
 		}
 		break;
+#ifdef CONFIG_64BIT
+	case 64:
+		switch (val_endian) {
+		case REGMAP_ENDIAN_BIG:
+			map->format.format_val = regmap_format_64_be;
+			map->format.parse_val = regmap_parse_64_be;
+			map->format.parse_inplace = regmap_parse_64_be_inplace;
+			break;
+		case REGMAP_ENDIAN_LITTLE:
+			map->format.format_val = regmap_format_64_le;
+			map->format.parse_val = regmap_parse_64_le;
+			map->format.parse_inplace = regmap_parse_64_le_inplace;
+			break;
+		case REGMAP_ENDIAN_NATIVE:
+			map->format.format_val = regmap_format_64_native;
+			map->format.parse_val = regmap_parse_64_native;
+			break;
+		default:
+			goto err_map;
+		}
+		break;
+#endif
 	}
 
 	if (map->format.format_write) {
@@ -1513,7 +1607,7 @@
 {
 	int ret;
 
-	if (reg % map->reg_stride)
+	if (!IS_ALIGNED(reg, map->reg_stride))
 		return -EINVAL;
 
 	map->lock(map->lock_arg);
@@ -1540,7 +1634,7 @@
 {
 	int ret;
 
-	if (reg % map->reg_stride)
+	if (!IS_ALIGNED(reg, map->reg_stride))
 		return -EINVAL;
 
 	map->lock(map->lock_arg);
@@ -1714,7 +1808,7 @@
 
 	if (map->bus && !map->format.parse_inplace)
 		return -EINVAL;
-	if (reg % map->reg_stride)
+	if (!IS_ALIGNED(reg, map->reg_stride))
 		return -EINVAL;
 
 	/*
@@ -1983,7 +2077,7 @@
 			int reg = regs[i].reg;
 			if (!map->writeable_reg(map->dev, reg))
 				return -EINVAL;
-			if (reg % map->reg_stride)
+			if (!IS_ALIGNED(reg, map->reg_stride))
 				return -EINVAL;
 		}
 
@@ -2133,7 +2227,7 @@
 
 	if (val_len % map->format.val_bytes)
 		return -EINVAL;
-	if (reg % map->reg_stride)
+	if (!IS_ALIGNED(reg, map->reg_stride))
 		return -EINVAL;
 
 	map->lock(map->lock_arg);
@@ -2260,7 +2354,7 @@
 {
 	int ret;
 
-	if (reg % map->reg_stride)
+	if (!IS_ALIGNED(reg, map->reg_stride))
 		return -EINVAL;
 
 	map->lock(map->lock_arg);
@@ -2296,7 +2390,7 @@
 		return -EINVAL;
 	if (val_len % map->format.val_bytes)
 		return -EINVAL;
-	if (reg % map->reg_stride)
+	if (!IS_ALIGNED(reg, map->reg_stride))
 		return -EINVAL;
 	if (val_count == 0)
 		return -EINVAL;
@@ -2414,7 +2508,7 @@
 	size_t val_bytes = map->format.val_bytes;
 	bool vol = regmap_volatile_range(map, reg, val_count);
 
-	if (reg % map->reg_stride)
+	if (!IS_ALIGNED(reg, map->reg_stride))
 		return -EINVAL;
 
 	if (map->bus && map->format.parse_inplace && (vol || map->cache_type == REGCACHE_NONE)) {
@@ -2488,11 +2582,19 @@
 				 * we assume that the values are native
 				 * endian.
 				 */
+#ifdef CONFIG_64BIT
+				u64 *u64 = val;
+#endif
 				u32 *u32 = val;
 				u16 *u16 = val;
 				u8 *u8 = val;
 
 				switch (map->format.val_bytes) {
+#ifdef CONFIG_64BIT
+				case 8:
+					u64[i] = ival;
+					break;
+#endif
 				case 4:
 					u32[i] = ival;
 					break;
diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c
index 0422c47..b38bd06 100644
--- a/drivers/block/cciss.c
+++ b/drivers/block/cciss.c
@@ -514,14 +514,9 @@
 	if (!buf || length > PAGE_SIZE - 1)
 		return -EINVAL;
 
-	buffer = (char *)__get_free_page(GFP_KERNEL);
-	if (!buffer)
-		return -ENOMEM;
-
-	err = -EFAULT;
-	if (copy_from_user(buffer, buf, length))
-		goto out;
-	buffer[length] = '\0';
+	buffer = memdup_user_nul(buf, length);
+	if (IS_ERR(buffer))
+		return PTR_ERR(buffer);
 
 #ifdef CONFIG_CISS_SCSI_TAPE
 	if (strncmp(ENGAGE_SCSI, buffer, sizeof ENGAGE_SCSI - 1) == 0) {
@@ -537,8 +532,7 @@
 	/* might be nice to have "disengage" too, but it's not
 	   safely possible. (only 1 module use count, lock issues.) */
 
-out:
-	free_page((unsigned long)buffer);
+	kfree(buffer);
 	return err;
 }
 
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index 3457ac8..34997d8 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -2029,13 +2029,10 @@
 	}
 
 	if (taskout) {
-		outbuf = kzalloc(taskout, GFP_KERNEL);
-		if (outbuf == NULL) {
-			err = -ENOMEM;
-			goto abort;
-		}
-		if (copy_from_user(outbuf, buf + outtotal, taskout)) {
-			err = -EFAULT;
+		outbuf = memdup_user(buf + outtotal, taskout);
+		if (IS_ERR(outbuf)) {
+			err = PTR_ERR(outbuf);
+			outbuf = NULL;
 			goto abort;
 		}
 		outbuf_dma = pci_map_single(dd->pdev,
@@ -2050,14 +2047,10 @@
 	}
 
 	if (taskin) {
-		inbuf = kzalloc(taskin, GFP_KERNEL);
-		if (inbuf == NULL) {
-			err = -ENOMEM;
-			goto abort;
-		}
-
-		if (copy_from_user(inbuf, buf + intotal, taskin)) {
-			err = -EFAULT;
+		inbuf = memdup_user(buf + intotal, taskin);
+		if (IS_ERR(inbuf)) {
+			err = PTR_ERR(inbuf);
+			inbuf = NULL;
 			goto abort;
 		}
 		inbuf_dma = pci_map_single(dd->pdev,
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 93b3f99..e4c5cc1 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -827,6 +827,7 @@
 {
 	.owner =	THIS_MODULE,
 	.ioctl =	nbd_ioctl,
+	.compat_ioctl =	nbd_ioctl,
 };
 
 #if IS_ENABLED(CONFIG_DEBUG_FS)
diff --git a/drivers/block/rsxx/core.c b/drivers/block/rsxx/core.c
index d8b2488..34997df 100644
--- a/drivers/block/rsxx/core.c
+++ b/drivers/block/rsxx/core.c
@@ -203,14 +203,11 @@
 	char *buf;
 	ssize_t st;
 
-	buf = kzalloc(cnt, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
+	buf = memdup_user(ubuf, cnt);
+	if (IS_ERR(buf))
+		return PTR_ERR(buf);
 
-	st = copy_from_user(buf, ubuf, cnt);
-	if (!st)
-		st = rsxx_creg_write(card, CREG_ADD_CRAM + (u32)*ppos, cnt,
-				     buf, 1);
+	st = rsxx_creg_write(card, CREG_ADD_CRAM + (u32)*ppos, cnt, buf, 1);
 	kfree(buf);
 	if (st)
 		return st;
diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c
index c206ccd..1b257ea 100644
--- a/drivers/cdrom/cdrom.c
+++ b/drivers/cdrom/cdrom.c
@@ -3186,15 +3186,11 @@
 	if (!CDROM_CAN(CDC_DVD))
 		return -ENOSYS;
 
-	s = kmalloc(size, GFP_KERNEL);
-	if (!s)
-		return -ENOMEM;
+	s = memdup_user(arg, size);
+	if (IS_ERR(s))
+		return PTR_ERR(s);
 
 	cd_dbg(CD_DO_IOCTL, "entering DVD_READ_STRUCT\n");
-	if (copy_from_user(s, arg, size)) {
-		kfree(s);
-		return -EFAULT;
-	}
 
 	ret = dvd_read_struct(cdi, s, cgc);
 	if (ret)
diff --git a/drivers/char/generic_nvram.c b/drivers/char/generic_nvram.c
index 6c4f4b5..073db95 100644
--- a/drivers/char/generic_nvram.c
+++ b/drivers/char/generic_nvram.c
@@ -20,6 +20,7 @@
 #include <linux/fcntl.h>
 #include <linux/init.h>
 #include <linux/mutex.h>
+#include <linux/pagemap.h>
 #include <asm/uaccess.h>
 #include <asm/nvram.h>
 #ifdef CONFIG_PPC_PMAC
@@ -33,24 +34,8 @@
 
 static loff_t nvram_llseek(struct file *file, loff_t offset, int origin)
 {
-	switch (origin) {
-	case 0:
-		break;
-	case 1:
-		offset += file->f_pos;
-		break;
-	case 2:
-		offset += nvram_len;
-		break;
-	default:
-		offset = -1;
-	}
-	if (offset < 0)
-		return -EINVAL;
-
-	file->f_pos = offset;
-
-	return file->f_pos;
+	return generic_file_llseek_size(file, offset, origin,
+					MAX_LFS_FILESIZE, nvram_len);
 }
 
 static ssize_t read_nvram(struct file *file, char __user *buf,
diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c
index 6f497aa..9203f2d 100644
--- a/drivers/char/hw_random/core.c
+++ b/drivers/char/hw_random/core.c
@@ -238,7 +238,10 @@
 			goto out;
 		}
 
-		mutex_lock(&reading_mutex);
+		if (mutex_lock_interruptible(&reading_mutex)) {
+			err = -ERESTARTSYS;
+			goto out_put;
+		}
 		if (!data_avail) {
 			bytes_read = rng_get_data(rng, rng_buffer,
 				rng_buffer_size(),
@@ -288,6 +291,7 @@
 
 out_unlock_reading:
 	mutex_unlock(&reading_mutex);
+out_put:
 	put_rng(rng);
 	goto out;
 }
diff --git a/drivers/char/hw_random/omap3-rom-rng.c b/drivers/char/hw_random/omap3-rom-rng.c
index a405cdc..8da14f1 100644
--- a/drivers/char/hw_random/omap3-rom-rng.c
+++ b/drivers/char/hw_random/omap3-rom-rng.c
@@ -17,7 +17,7 @@
 #include <linux/init.h>
 #include <linux/random.h>
 #include <linux/hw_random.h>
-#include <linux/timer.h>
+#include <linux/workqueue.h>
 #include <linux/clk.h>
 #include <linux/err.h>
 #include <linux/platform_device.h>
@@ -29,11 +29,11 @@
 /* param1: ptr, param2: count, param3: flag */
 static u32 (*omap3_rom_rng_call)(u32, u32, u32);
 
-static struct timer_list idle_timer;
+static struct delayed_work idle_work;
 static int rng_idle;
 static struct clk *rng_clk;
 
-static void omap3_rom_rng_idle(unsigned long data)
+static void omap3_rom_rng_idle(struct work_struct *work)
 {
 	int r;
 
@@ -51,7 +51,7 @@
 	u32 r;
 	u32 ptr;
 
-	del_timer_sync(&idle_timer);
+	cancel_delayed_work_sync(&idle_work);
 	if (rng_idle) {
 		clk_prepare_enable(rng_clk);
 		r = omap3_rom_rng_call(0, 0, RNG_GEN_PRNG_HW_INIT);
@@ -65,7 +65,7 @@
 
 	ptr = virt_to_phys(buf);
 	r = omap3_rom_rng_call(ptr, count, RNG_GEN_HW);
-	mod_timer(&idle_timer, jiffies + msecs_to_jiffies(500));
+	schedule_delayed_work(&idle_work, msecs_to_jiffies(500));
 	if (r != 0)
 		return -EINVAL;
 	return 0;
@@ -102,7 +102,7 @@
 		return -EINVAL;
 	}
 
-	setup_timer(&idle_timer, omap3_rom_rng_idle, 0);
+	INIT_DELAYED_WORK(&idle_work, omap3_rom_rng_idle);
 	rng_clk = devm_clk_get(&pdev->dev, "ick");
 	if (IS_ERR(rng_clk)) {
 		pr_err("unable to get RNG clock\n");
@@ -118,6 +118,7 @@
 
 static int omap3_rom_rng_remove(struct platform_device *pdev)
 {
+	cancel_delayed_work_sync(&idle_work);
 	hwrng_unregister(&omap3_rom_rng_ops);
 	clk_disable_unprepare(rng_clk);
 	return 0;
diff --git a/drivers/char/hw_random/via-rng.c b/drivers/char/hw_random/via-rng.c
index 0c98a9d..44ce806 100644
--- a/drivers/char/hw_random/via-rng.c
+++ b/drivers/char/hw_random/via-rng.c
@@ -140,7 +140,7 @@
 	 * RNG configuration like it used to be the case in this
 	 * register */
 	if ((c->x86 == 6) && (c->x86_model >= 0x0f)) {
-		if (!cpu_has_xstore_enabled) {
+		if (!boot_cpu_has(X86_FEATURE_XSTORE_EN)) {
 			pr_err(PFX "can't enable hardware RNG "
 				"if XSTORE is not enabled\n");
 			return -ENODEV;
@@ -200,8 +200,9 @@
 {
 	int err;
 
-	if (!cpu_has_xstore)
+	if (!boot_cpu_has(X86_FEATURE_XSTORE))
 		return -ENODEV;
+
 	pr_info("VIA RNG detected\n");
 	err = hwrng_register(&via_rng);
 	if (err) {
diff --git a/drivers/char/mbcs.c b/drivers/char/mbcs.c
index e5d3e3f..67d4264 100644
--- a/drivers/char/mbcs.c
+++ b/drivers/char/mbcs.c
@@ -26,6 +26,7 @@
 #include <linux/uio.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
+#include <linux/pagemap.h>
 #include <asm/io.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
@@ -451,31 +452,8 @@
 
 static loff_t mbcs_sram_llseek(struct file * filp, loff_t off, int whence)
 {
-	loff_t newpos;
-
-	switch (whence) {
-	case SEEK_SET:
-		newpos = off;
-		break;
-
-	case SEEK_CUR:
-		newpos = filp->f_pos + off;
-		break;
-
-	case SEEK_END:
-		newpos = MBCS_SRAM_SIZE + off;
-		break;
-
-	default:		/* can't happen */
-		return -EINVAL;
-	}
-
-	if (newpos < 0)
-		return -EINVAL;
-
-	filp->f_pos = newpos;
-
-	return newpos;
+	return generic_file_llseek_size(filp, off, whence, MAX_LFS_FILESIZE,
+					MBCS_SRAM_SIZE);
 }
 
 static uint64_t mbcs_pioaddr(struct mbcs_soft *soft, uint64_t offset)
diff --git a/drivers/char/nvram.c b/drivers/char/nvram.c
index 97c2d8d..0129232 100644
--- a/drivers/char/nvram.c
+++ b/drivers/char/nvram.c
@@ -110,6 +110,7 @@
 #include <linux/io.h>
 #include <linux/uaccess.h>
 #include <linux/mutex.h>
+#include <linux/pagemap.h>
 
 
 static DEFINE_MUTEX(nvram_mutex);
@@ -213,21 +214,8 @@
 
 static loff_t nvram_llseek(struct file *file, loff_t offset, int origin)
 {
-	switch (origin) {
-	case 0:
-		/* nothing to do */
-		break;
-	case 1:
-		offset += file->f_pos;
-		break;
-	case 2:
-		offset += NVRAM_BYTES;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	return (offset >= 0) ? (file->f_pos = offset) : -EINVAL;
+	return generic_file_llseek_size(file, offset, origin, MAX_LFS_FILESIZE,
+					NVRAM_BYTES);
 }
 
 static ssize_t nvram_read(struct file *file, char __user *buf,
diff --git a/drivers/char/nwflash.c b/drivers/char/nwflash.c
index e371480..dbe598d 100644
--- a/drivers/char/nwflash.c
+++ b/drivers/char/nwflash.c
@@ -277,36 +277,7 @@
 		printk(KERN_DEBUG "flash_llseek: offset=0x%X, orig=0x%X.\n",
 		       (unsigned int) offset, orig);
 
-	switch (orig) {
-	case 0:
-		if (offset < 0) {
-			ret = -EINVAL;
-			break;
-		}
-
-		if ((unsigned int) offset > gbFlashSize) {
-			ret = -EINVAL;
-			break;
-		}
-
-		file->f_pos = (unsigned int) offset;
-		ret = file->f_pos;
-		break;
-	case 1:
-		if ((file->f_pos + offset) > gbFlashSize) {
-			ret = -EINVAL;
-			break;
-		}
-		if ((file->f_pos + offset) < 0) {
-			ret = -EINVAL;
-			break;
-		}
-		file->f_pos += offset;
-		ret = file->f_pos;
-		break;
-	default:
-		ret = -EINVAL;
-	}
+	ret = no_seek_end_llseek_size(file, offset, orig, gbFlashSize);
 	mutex_unlock(&flash_mutex);
 	return ret;
 }
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 2eb5f0e..b251013 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -28,10 +28,16 @@
 	bool
 
 config DIGICOLOR_TIMER
-	bool
+	bool "Digicolor timer driver" if COMPILE_TEST
+	depends on GENERIC_CLOCKEVENTS
+	help
+	  Enables the support for the digicolor timer driver.
 
 config DW_APB_TIMER
-	bool
+	bool "DW APB timer driver" if COMPILE_TEST
+	depends on GENERIC_CLOCKEVENTS
+	help
+	  Enables the support for the dw_apb timer.
 
 config DW_APB_TIMER_OF
 	bool
@@ -39,47 +45,77 @@
 	select CLKSRC_OF
 
 config ROCKCHIP_TIMER
-	bool
+	bool "Rockchip timer driver" if COMPILE_TEST
+	depends on ARM || ARM64
 	select CLKSRC_OF
+	help
+	  Enables the support for the rockchip timer driver.
 
 config ARMADA_370_XP_TIMER
-	bool
+	bool "Armada 370 and XP timer driver" if COMPILE_TEST
+	depends on ARM
 	select CLKSRC_OF
+	help
+	  Enables the support for the Armada 370 and XP timer driver.
 
 config MESON6_TIMER
-	bool
+	bool "Meson6 timer driver" if COMPILE_TEST
+	depends on GENERIC_CLOCKEVENTS
 	select CLKSRC_MMIO
+	help
+	  Enables the support for the Meson6 timer driver.
 
 config ORION_TIMER
+	bool "Orion timer driver" if COMPILE_TEST
+	depends on ARM
 	select CLKSRC_OF
 	select CLKSRC_MMIO
-	bool
+	help
+	  Enables the support for the Orion timer driver
 
 config SUN4I_TIMER
+	bool "Sun4i timer driver" if COMPILE_TEST
+	depends on GENERIC_CLOCKEVENTS
 	select CLKSRC_MMIO
-	bool
+	help
+	  Enables support for the Sun4i timer.
 
 config SUN5I_HSTIMER
+	bool "Sun5i timer driver" if COMPILE_TEST
 	select CLKSRC_MMIO
-	bool
+	depends on COMMON_CLK
+	help
+	  Enables support the Sun5i timer.
 
 config TEGRA_TIMER
-	bool
+	bool "Tegra timer driver" if COMPILE_TEST
+	depends on ARM
+	help
+	  Enables support for the Tegra driver.
 
 config VT8500_TIMER
-	bool
+	bool "VT8500 timer driver" if COMPILE_TEST
+	depends on GENERIC_CLOCKEVENTS
+	help
+	  Enables support for the VT8500 driver.
 
 config CADENCE_TTC_TIMER
-	bool
+	bool "Cadence TTC timer driver" if COMPILE_TEST
+	depends on COMMON_CLK
+	help
+	  Enables support for the cadence ttc driver.
 
 config ASM9260_TIMER
-	bool
+	bool "ASM9260 timer driver" if COMPILE_TEST
+	depends on GENERIC_CLOCKEVENTS
 	select CLKSRC_MMIO
 	select CLKSRC_OF
+	help
+	  Enables support for the ASM9260 timer.
 
 config CLKSRC_NOMADIK_MTU
-	bool
-	depends on (ARCH_NOMADIK || ARCH_U8500)
+	bool "Nomakdik clocksource driver" if COMPILE_TEST
+	depends on ARM
 	select CLKSRC_MMIO
 	help
 	  Support for Multi Timer Unit. MTU provides access
@@ -93,9 +129,8 @@
 	  Use the Multi Timer Unit as the sched_clock.
 
 config CLKSRC_DBX500_PRCMU
-	bool "Clocksource PRCMU Timer"
-	depends on UX500_SOC_DB8500
-	default y
+	bool "Clocksource PRCMU Timer" if COMPILE_TEST
+	depends on GENERIC_CLOCKEVENTS
 	help
 	  Use the always on PRCMU Timer as clocksource
 
@@ -116,13 +151,18 @@
 	  event device.
 
 config CLKSRC_LPC32XX
-	bool
+	bool "Clocksource for LPC32XX" if COMPILE_TEST
+	depends on GENERIC_CLOCKEVENTS
 	select CLKSRC_MMIO
 	select CLKSRC_OF
+	help
+	  Support for the LPC32XX clocksource.
 
 config CLKSRC_PISTACHIO
-	bool
+	bool "Clocksource for Pistachio SoC" if COMPILE_TEST
 	select CLKSRC_OF
+	help
+	  Enables the clocksource for the Pistachio SoC.
 
 config CLKSRC_TI_32K
 	bool "Texas Instruments 32.768 Hz Clocksource" if COMPILE_TEST
@@ -199,13 +239,14 @@
 	  This option enables support for the Meta per-thread timers.
 
 config CLKSRC_EXYNOS_MCT
-	def_bool y if ARCH_EXYNOS
-	depends on !ARM64
+	bool "Exynos multi core timer driver" if COMPILE_TEST
+	depends on ARM
 	help
 	  Support for Multi Core Timer controller on Exynos SoCs.
 
 config CLKSRC_SAMSUNG_PWM
-	bool
+	bool "PWM timer drvier for Samsung S3C, S5P" if COMPILE_TEST
+	depends on GENERIC_CLOCKEVENTS
 	help
 	  This is a new clocksource driver for the PWM timer found in
 	  Samsung S3C, S5P and Exynos SoCs, replacing an earlier driver
@@ -213,7 +254,8 @@
 	  needed only on systems that do not have the Exynos MCT available.
 
 config FSL_FTM_TIMER
-	bool
+	bool "Freescale FlexTimer Module driver" if COMPILE_TEST
+	depends on GENERIC_CLOCKEVENTS
 	help
 	  Support for Freescale FlexTimer Module (FTM) timer.
 
@@ -226,9 +268,12 @@
         bool
 
 config MTK_TIMER
+	bool "Mediatek timer driver" if COMPILE_TEST
+	depends on GENERIC_CLOCKEVENTS
 	select CLKSRC_OF
 	select CLKSRC_MMIO
-	bool
+	help
+	  Support for Mediatek timer driver.
 
 config SYS_SUPPORTS_SH_MTU2
         bool
@@ -279,7 +324,12 @@
 	  such as EMEV2 from former NEC Electronics.
 
 config CLKSRC_QCOM
-	bool
+	bool "Qualcomm MSM timer" if COMPILE_TEST
+	depends on ARM
+	select CLKSRC_OF
+	help
+	  This enables the clocksource and the per CPU clockevent driver for the
+	  Qualcomm SoCs.
 
 config CLKSRC_VERSATILE
 	bool "ARM Versatile (Express) reference platforms clock source"
@@ -298,21 +348,40 @@
 	select CLKSRC_OF
 
 config CLKSRC_TANGO_XTAL
-	bool
+	bool "Clocksource for Tango SoC" if COMPILE_TEST
+	depends on ARM
 	select CLKSRC_OF
+	select CLKSRC_MMIO
+	help
+	  This enables the clocksource for Tango SoC
 
 config CLKSRC_PXA
-	def_bool y if ARCH_PXA || ARCH_SA1100
-	select CLKSRC_OF if OF
+	bool "Clocksource for PXA or SA-11x0 platform" if COMPILE_TEST
+	depends on GENERIC_CLOCKEVENTS
+	select CLKSRC_MMIO
 	help
 	  This enables OST0 support available on PXA and SA-11x0
 	  platforms.
 
+config H8300_TMR8
+        bool "Clockevent timer for the H8300 platform" if COMPILE_TEST
+        depends on GENERIC_CLOCKEVENTS
+	help
+	  This enables the 8 bits timer for the H8300 platform.
+
 config H8300_TMR16
-        bool
+        bool "Clockevent timer for the H83069 platform" if COMPILE_TEST
+        depends on GENERIC_CLOCKEVENTS
+	help
+	  This enables the 16 bits timer for the H8300 platform with the
+	  H83069 cpu.
 
 config H8300_TPU
-        bool
+        bool "Clocksource for the H8300 platform" if COMPILE_TEST
+        depends on GENERIC_CLOCKEVENTS
+	help
+	  This enables the clocksource for the H8300 platform with the
+	  H8S2678 cpu.
 
 config CLKSRC_IMX_GPT
 	bool "Clocksource using i.MX GPT" if COMPILE_TEST
@@ -320,8 +389,7 @@
 	select CLKSRC_MMIO
 
 config CLKSRC_ST_LPC
-	bool
-	depends on ARCH_STI
+	bool "Low power clocksource found in the LPC" if COMPILE_TEST
 	select CLKSRC_OF if OF
 	help
 	  Enable this option to use the Low Power controller timer
diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile
index 56bd16e..dc2b899 100644
--- a/drivers/clocksource/Makefile
+++ b/drivers/clocksource/Makefile
@@ -60,7 +60,7 @@
 obj-$(CONFIG_CLKSRC_TANGO_XTAL)		+= tango_xtal.o
 obj-$(CONFIG_CLKSRC_IMX_GPT)		+= timer-imx-gpt.o
 obj-$(CONFIG_ASM9260_TIMER)		+= asm9260_timer.o
-obj-$(CONFIG_H8300)			+= h8300_timer8.o
+obj-$(CONFIG_H8300_TMR8)		+= h8300_timer8.o
 obj-$(CONFIG_H8300_TMR16)		+= h8300_timer16.o
 obj-$(CONFIG_H8300_TPU)			+= h8300_tpu.o
 obj-$(CONFIG_CLKSRC_ST_LPC)		+= clksrc_st_lpc.o
diff --git a/drivers/clocksource/acpi_pm.c b/drivers/clocksource/acpi_pm.c
index 6eab889..28037d0 100644
--- a/drivers/clocksource/acpi_pm.c
+++ b/drivers/clocksource/acpi_pm.c
@@ -109,10 +109,8 @@
 
 	/* the bug has been fixed in PIIX4M */
 	if (dev->revision < 3) {
-		printk(KERN_WARNING "* Found PM-Timer Bug on the chipset."
-		       " Due to workarounds for a bug,\n"
-		       "* this clock source is slow. Consider trying"
-		       " other clock sources\n");
+		pr_warn("* Found PM-Timer Bug on the chipset. Due to workarounds for a bug,\n"
+			"* this clock source is slow. Consider trying other clock sources\n");
 
 		acpi_pm_need_workaround();
 	}
@@ -125,12 +123,9 @@
 	if (acpi_pm_good)
 		return;
 
-	printk(KERN_WARNING "* The chipset may have PM-Timer Bug. Due to"
-	       " workarounds for a bug,\n"
-	       "* this clock source is slow. If you are sure your timer"
-	       " does not have\n"
-	       "* this bug, please use \"acpi_pm_good\" to disable the"
-	       " workaround\n");
+	pr_warn("* The chipset may have PM-Timer Bug. Due to workarounds for a bug,\n"
+		"* this clock source is slow. If you are sure your timer does not have\n"
+		"* this bug, please use \"acpi_pm_good\" to disable the workaround\n");
 
 	acpi_pm_need_workaround();
 }
@@ -162,8 +157,7 @@
 	/* Check that the PMTMR delta is within 5% of what we expect */
 	if (delta < (PMTMR_EXPECTED_RATE * 19) / 20 ||
 	    delta > (PMTMR_EXPECTED_RATE * 21) / 20) {
-		printk(KERN_INFO "PM-Timer running at invalid rate: %lu%% "
-			"of normal - aborting.\n",
+		pr_info("PM-Timer running at invalid rate: %lu%% of normal - aborting.\n",
 			100UL * delta / PMTMR_EXPECTED_RATE);
 		return -1;
 	}
@@ -199,15 +193,14 @@
 				break;
 			if ((value2 < value1) && ((value2) < 0xFFF))
 				break;
-			printk(KERN_INFO "PM-Timer had inconsistent results:"
-			       " %#llx, %#llx - aborting.\n",
-			       value1, value2);
+			pr_info("PM-Timer had inconsistent results: %#llx, %#llx - aborting.\n",
+				value1, value2);
 			pmtmr_ioport = 0;
 			return -EINVAL;
 		}
 		if (i == ACPI_PM_READ_CHECKS) {
-			printk(KERN_INFO "PM-Timer failed consistency check "
-			       " (%#llx) - aborting.\n", value1);
+			pr_info("PM-Timer failed consistency check  (%#llx) - aborting.\n",
+				value1);
 			pmtmr_ioport = 0;
 			return -ENODEV;
 		}
diff --git a/drivers/clocksource/arm_global_timer.c b/drivers/clocksource/arm_global_timer.c
index a2cb6fa..d189d8c 100644
--- a/drivers/clocksource/arm_global_timer.c
+++ b/drivers/clocksource/arm_global_timer.c
@@ -99,17 +99,17 @@
 
 	counter += delta;
 	ctrl = GT_CONTROL_TIMER_ENABLE;
-	writel(ctrl, gt_base + GT_CONTROL);
-	writel(lower_32_bits(counter), gt_base + GT_COMP0);
-	writel(upper_32_bits(counter), gt_base + GT_COMP1);
+	writel_relaxed(ctrl, gt_base + GT_CONTROL);
+	writel_relaxed(lower_32_bits(counter), gt_base + GT_COMP0);
+	writel_relaxed(upper_32_bits(counter), gt_base + GT_COMP1);
 
 	if (periodic) {
-		writel(delta, gt_base + GT_AUTO_INC);
+		writel_relaxed(delta, gt_base + GT_AUTO_INC);
 		ctrl |= GT_CONTROL_AUTO_INC;
 	}
 
 	ctrl |= GT_CONTROL_COMP_ENABLE | GT_CONTROL_IRQ_ENABLE;
-	writel(ctrl, gt_base + GT_CONTROL);
+	writel_relaxed(ctrl, gt_base + GT_CONTROL);
 }
 
 static int gt_clockevent_shutdown(struct clock_event_device *evt)
@@ -195,12 +195,23 @@
 	return gt_counter_read();
 }
 
+static void gt_resume(struct clocksource *cs)
+{
+	unsigned long ctrl;
+
+	ctrl = readl(gt_base + GT_CONTROL);
+	if (!(ctrl & GT_CONTROL_TIMER_ENABLE))
+		/* re-enable timer on resume */
+		writel(GT_CONTROL_TIMER_ENABLE, gt_base + GT_CONTROL);
+}
+
 static struct clocksource gt_clocksource = {
 	.name	= "arm_global_timer",
 	.rating	= 300,
 	.read	= gt_clocksource_read,
 	.mask	= CLOCKSOURCE_MASK(64),
 	.flags	= CLOCK_SOURCE_IS_CONTINUOUS,
+	.resume = gt_resume,
 };
 
 #ifdef CONFIG_CLKSRC_ARM_GLOBAL_TIMER_SCHED_CLOCK
diff --git a/drivers/clocksource/dw_apb_timer.c b/drivers/clocksource/dw_apb_timer.c
index c76c750..6334526 100644
--- a/drivers/clocksource/dw_apb_timer.c
+++ b/drivers/clocksource/dw_apb_timer.c
@@ -49,20 +49,31 @@
 	return container_of(cs, struct dw_apb_clocksource, cs);
 }
 
-static unsigned long apbt_readl(struct dw_apb_timer *timer, unsigned long offs)
+static inline u32 apbt_readl(struct dw_apb_timer *timer, unsigned long offs)
 {
 	return readl(timer->base + offs);
 }
 
-static void apbt_writel(struct dw_apb_timer *timer, unsigned long val,
-		 unsigned long offs)
+static inline void apbt_writel(struct dw_apb_timer *timer, u32 val,
+			unsigned long offs)
 {
 	writel(val, timer->base + offs);
 }
 
+static inline u32 apbt_readl_relaxed(struct dw_apb_timer *timer, unsigned long offs)
+{
+	return readl_relaxed(timer->base + offs);
+}
+
+static inline void apbt_writel_relaxed(struct dw_apb_timer *timer, u32 val,
+			unsigned long offs)
+{
+	writel_relaxed(val, timer->base + offs);
+}
+
 static void apbt_disable_int(struct dw_apb_timer *timer)
 {
-	unsigned long ctrl = apbt_readl(timer, APBTMR_N_CONTROL);
+	u32 ctrl = apbt_readl(timer, APBTMR_N_CONTROL);
 
 	ctrl |= APBTMR_CONTROL_INT;
 	apbt_writel(timer, ctrl, APBTMR_N_CONTROL);
@@ -81,7 +92,7 @@
 
 static void apbt_eoi(struct dw_apb_timer *timer)
 {
-	apbt_readl(timer, APBTMR_N_EOI);
+	apbt_readl_relaxed(timer, APBTMR_N_EOI);
 }
 
 static irqreturn_t dw_apb_clockevent_irq(int irq, void *data)
@@ -103,7 +114,7 @@
 
 static void apbt_enable_int(struct dw_apb_timer *timer)
 {
-	unsigned long ctrl = apbt_readl(timer, APBTMR_N_CONTROL);
+	u32 ctrl = apbt_readl(timer, APBTMR_N_CONTROL);
 	/* clear pending intr */
 	apbt_readl(timer, APBTMR_N_EOI);
 	ctrl &= ~APBTMR_CONTROL_INT;
@@ -113,7 +124,7 @@
 static int apbt_shutdown(struct clock_event_device *evt)
 {
 	struct dw_apb_clock_event_device *dw_ced = ced_to_dw_apb_ced(evt);
-	unsigned long ctrl;
+	u32 ctrl;
 
 	pr_debug("%s CPU %d state=shutdown\n", __func__,
 		 cpumask_first(evt->cpumask));
@@ -127,7 +138,7 @@
 static int apbt_set_oneshot(struct clock_event_device *evt)
 {
 	struct dw_apb_clock_event_device *dw_ced = ced_to_dw_apb_ced(evt);
-	unsigned long ctrl;
+	u32 ctrl;
 
 	pr_debug("%s CPU %d state=oneshot\n", __func__,
 		 cpumask_first(evt->cpumask));
@@ -160,7 +171,7 @@
 {
 	struct dw_apb_clock_event_device *dw_ced = ced_to_dw_apb_ced(evt);
 	unsigned long period = DIV_ROUND_UP(dw_ced->timer.freq, HZ);
-	unsigned long ctrl;
+	u32 ctrl;
 
 	pr_debug("%s CPU %d state=periodic\n", __func__,
 		 cpumask_first(evt->cpumask));
@@ -196,17 +207,17 @@
 static int apbt_next_event(unsigned long delta,
 			   struct clock_event_device *evt)
 {
-	unsigned long ctrl;
+	u32 ctrl;
 	struct dw_apb_clock_event_device *dw_ced = ced_to_dw_apb_ced(evt);
 
 	/* Disable timer */
-	ctrl = apbt_readl(&dw_ced->timer, APBTMR_N_CONTROL);
+	ctrl = apbt_readl_relaxed(&dw_ced->timer, APBTMR_N_CONTROL);
 	ctrl &= ~APBTMR_CONTROL_ENABLE;
-	apbt_writel(&dw_ced->timer, ctrl, APBTMR_N_CONTROL);
+	apbt_writel_relaxed(&dw_ced->timer, ctrl, APBTMR_N_CONTROL);
 	/* write new count */
-	apbt_writel(&dw_ced->timer, delta, APBTMR_N_LOAD_COUNT);
+	apbt_writel_relaxed(&dw_ced->timer, delta, APBTMR_N_LOAD_COUNT);
 	ctrl |= APBTMR_CONTROL_ENABLE;
-	apbt_writel(&dw_ced->timer, ctrl, APBTMR_N_CONTROL);
+	apbt_writel_relaxed(&dw_ced->timer, ctrl, APBTMR_N_CONTROL);
 
 	return 0;
 }
@@ -323,7 +334,7 @@
 	 * start count down from 0xffff_ffff. this is done by toggling the
 	 * enable bit then load initial load count to ~0.
 	 */
-	unsigned long ctrl = apbt_readl(&dw_cs->timer, APBTMR_N_CONTROL);
+	u32 ctrl = apbt_readl(&dw_cs->timer, APBTMR_N_CONTROL);
 
 	ctrl &= ~APBTMR_CONTROL_ENABLE;
 	apbt_writel(&dw_cs->timer, ctrl, APBTMR_N_CONTROL);
@@ -338,11 +349,12 @@
 
 static cycle_t __apbt_read_clocksource(struct clocksource *cs)
 {
-	unsigned long current_count;
+	u32 current_count;
 	struct dw_apb_clocksource *dw_cs =
 		clocksource_to_dw_apb_clocksource(cs);
 
-	current_count = apbt_readl(&dw_cs->timer, APBTMR_N_CURRENT_VALUE);
+	current_count = apbt_readl_relaxed(&dw_cs->timer,
+					APBTMR_N_CURRENT_VALUE);
 
 	return (cycle_t)~current_count;
 }
diff --git a/drivers/clocksource/dw_apb_timer_of.c b/drivers/clocksource/dw_apb_timer_of.c
index a19a3f61..860843c 100644
--- a/drivers/clocksource/dw_apb_timer_of.c
+++ b/drivers/clocksource/dw_apb_timer_of.c
@@ -16,6 +16,7 @@
  * You should have received a copy of the GNU General Public License
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
+#include <linux/delay.h>
 #include <linux/dw_apb_timer.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
@@ -130,6 +131,17 @@
 	sched_clock_register(read_sched_clock, 32, sched_rate);
 }
 
+#ifdef CONFIG_ARM
+static unsigned long dw_apb_delay_timer_read(void)
+{
+	return ~readl_relaxed(sched_io_base);
+}
+
+static struct delay_timer dw_apb_delay_timer = {
+	.read_current_timer	= dw_apb_delay_timer_read,
+};
+#endif
+
 static int num_called;
 static void __init dw_apb_timer_init(struct device_node *timer)
 {
@@ -142,6 +154,10 @@
 		pr_debug("%s: found clocksource timer\n", __func__);
 		add_clocksource(timer);
 		init_sched_clock();
+#ifdef CONFIG_ARM
+		dw_apb_delay_timer.freq = sched_rate;
+		register_current_timer_delay(&dw_apb_delay_timer);
+#endif
 		break;
 	default:
 		break;
diff --git a/drivers/clocksource/h8300_timer16.c b/drivers/clocksource/h8300_timer16.c
index 0e076c6..75c4407 100644
--- a/drivers/clocksource/h8300_timer16.c
+++ b/drivers/clocksource/h8300_timer16.c
@@ -4,85 +4,56 @@
  *  Copyright 2015 Yoshinori Sato <ysato@users.sourcefoge.jp>
  */
 
-#include <linux/errno.h>
-#include <linux/kernel.h>
-#include <linux/param.h>
-#include <linux/string.h>
-#include <linux/slab.h>
 #include <linux/interrupt.h>
 #include <linux/init.h>
-#include <linux/platform_device.h>
 #include <linux/clocksource.h>
-#include <linux/module.h>
 #include <linux/clk.h>
 #include <linux/io.h>
 #include <linux/of.h>
-
-#include <asm/segment.h>
-#include <asm/irq.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
 
 #define TSTR	0
-#define TSNC	1
-#define TMDR	2
-#define TOLR	3
-#define TISRA	4
-#define TISRB	5
 #define TISRC	6
 
 #define TCR	0
-#define TIOR	1
 #define TCNT	2
-#define GRA	4
-#define GRB	6
 
-#define FLAG_REPROGRAM (1 << 0)
-#define FLAG_SKIPEVENT (1 << 1)
-#define FLAG_IRQCONTEXT (1 << 2)
-#define FLAG_STARTED (1 << 3)
-
-#define ONESHOT  0
-#define PERIODIC 1
-
-#define RELATIVE 0
-#define ABSOLUTE 1
+#define bset(b, a) iowrite8(ioread8(a) | (1 << (b)), (a))
+#define bclr(b, a) iowrite8(ioread8(a) & ~(1 << (b)), (a))
 
 struct timer16_priv {
-	struct platform_device *pdev;
 	struct clocksource cs;
-	struct irqaction irqaction;
 	unsigned long total_cycles;
-	unsigned long mapbase;
-	unsigned long mapcommon;
-	unsigned long flags;
-	unsigned short gra;
+	void __iomem *mapbase;
+	void __iomem *mapcommon;
 	unsigned short cs_enabled;
 	unsigned char enb;
-	unsigned char imfa;
-	unsigned char imiea;
 	unsigned char ovf;
-	raw_spinlock_t lock;
-	struct clk *clk;
+	unsigned char ovie;
 };
 
 static unsigned long timer16_get_counter(struct timer16_priv *p)
 {
-	unsigned long v1, v2, v3;
-	int o1, o2;
+	unsigned short v1, v2, v3;
+	unsigned char  o1, o2;
 
-	o1 = ctrl_inb(p->mapcommon + TISRC) & p->ovf;
+	o1 = ioread8(p->mapcommon + TISRC) & p->ovf;
 
 	/* Make sure the timer value is stable. Stolen from acpi_pm.c */
 	do {
 		o2 = o1;
-		v1 = ctrl_inw(p->mapbase + TCNT);
-		v2 = ctrl_inw(p->mapbase + TCNT);
-		v3 = ctrl_inw(p->mapbase + TCNT);
-		o1 = ctrl_inb(p->mapcommon + TISRC) & p->ovf;
+		v1 = ioread16be(p->mapbase + TCNT);
+		v2 = ioread16be(p->mapbase + TCNT);
+		v3 = ioread16be(p->mapbase + TCNT);
+		o1 = ioread8(p->mapcommon + TISRC) & p->ovf;
 	} while (unlikely((o1 != o2) || (v1 > v2 && v1 < v3)
 			  || (v2 > v3 && v2 < v1) || (v3 > v1 && v3 < v2)));
 
-	v2 |= 0x10000;
-	return v2;
+	if (likely(!o1))
+		return v2;
+	else
+		return v2 + 0x10000;
 }
 
 
@@ -90,8 +61,7 @@
 {
 	struct timer16_priv *p = (struct timer16_priv *)dev_id;
 
-	ctrl_outb(ctrl_inb(p->mapcommon + TISRA) & ~p->imfa,
-		  p->mapcommon + TISRA);
+	bclr(p->ovf, p->mapcommon + TISRC);
 	p->total_cycles += 0x10000;
 
 	return IRQ_HANDLED;
@@ -105,13 +75,10 @@
 static cycle_t timer16_clocksource_read(struct clocksource *cs)
 {
 	struct timer16_priv *p = cs_to_priv(cs);
-	unsigned long flags, raw;
-	unsigned long value;
+	unsigned long raw, value;
 
-	raw_spin_lock_irqsave(&p->lock, flags);
 	value = p->total_cycles;
 	raw = timer16_get_counter(p);
-	raw_spin_unlock_irqrestore(&p->lock, flags);
 
 	return value + raw;
 }
@@ -123,10 +90,10 @@
 	WARN_ON(p->cs_enabled);
 
 	p->total_cycles = 0;
-	ctrl_outw(0x0000, p->mapbase + TCNT);
-	ctrl_outb(0x83, p->mapbase + TCR);
-	ctrl_outb(ctrl_inb(p->mapcommon + TSTR) | p->enb,
-		  p->mapcommon + TSTR);
+	iowrite16be(0x0000, p->mapbase + TCNT);
+	iowrite8(0x83, p->mapbase + TCR);
+	bset(p->ovie, p->mapcommon + TISRC);
+	bset(p->enb, p->mapcommon + TSTR);
 
 	p->cs_enabled = true;
 	return 0;
@@ -138,116 +105,83 @@
 
 	WARN_ON(!p->cs_enabled);
 
-	ctrl_outb(ctrl_inb(p->mapcommon + TSTR) & ~p->enb,
-		  p->mapcommon + TSTR);
+	bclr(p->ovie, p->mapcommon + TISRC);
+	bclr(p->enb, p->mapcommon + TSTR);
 
 	p->cs_enabled = false;
 }
 
+static struct timer16_priv timer16_priv = {
+	.cs = {
+		.name = "h8300_16timer",
+		.rating = 200,
+		.read = timer16_clocksource_read,
+		.enable = timer16_enable,
+		.disable = timer16_disable,
+		.mask = CLOCKSOURCE_MASK(sizeof(unsigned long) * 8),
+		.flags = CLOCK_SOURCE_IS_CONTINUOUS,
+	},
+};
+
 #define REG_CH   0
 #define REG_COMM 1
 
-static int timer16_setup(struct timer16_priv *p, struct platform_device *pdev)
+static void __init h8300_16timer_init(struct device_node *node)
 {
-	struct resource *res[2];
+	void __iomem *base[2];
 	int ret, irq;
 	unsigned int ch;
+	struct clk *clk;
 
-	p->pdev = pdev;
-
-	res[REG_CH] = platform_get_resource(p->pdev,
-					    IORESOURCE_MEM, REG_CH);
-	res[REG_COMM] = platform_get_resource(p->pdev,
-					      IORESOURCE_MEM, REG_COMM);
-	if (!res[REG_CH] || !res[REG_COMM]) {
-		dev_err(&p->pdev->dev, "failed to get I/O memory\n");
-		return -ENXIO;
-	}
-	irq = platform_get_irq(p->pdev, 0);
-	if (irq < 0) {
-		dev_err(&p->pdev->dev, "failed to get irq\n");
-		return irq;
+	clk = of_clk_get(node, 0);
+	if (IS_ERR(clk)) {
+		pr_err("failed to get clock for clocksource\n");
+		return;
 	}
 
-	p->clk = clk_get(&p->pdev->dev, "fck");
-	if (IS_ERR(p->clk)) {
-		dev_err(&p->pdev->dev, "can't get clk\n");
-		return PTR_ERR(p->clk);
+	base[REG_CH] = of_iomap(node, 0);
+	if (!base[REG_CH]) {
+		pr_err("failed to map registers for clocksource\n");
+		goto free_clk;
 	}
-	of_property_read_u32(p->pdev->dev.of_node, "renesas,channel", &ch);
 
-	p->pdev = pdev;
-	p->mapbase = res[REG_CH]->start;
-	p->mapcommon = res[REG_COMM]->start;
-	p->enb = 1 << ch;
-	p->imfa = 1 << ch;
-	p->imiea = 1 << (4 + ch);
-	p->cs.name = pdev->name;
-	p->cs.rating = 200;
-	p->cs.read = timer16_clocksource_read;
-	p->cs.enable = timer16_enable;
-	p->cs.disable = timer16_disable;
-	p->cs.mask = CLOCKSOURCE_MASK(sizeof(unsigned long) * 8);
-	p->cs.flags = CLOCK_SOURCE_IS_CONTINUOUS;
+	base[REG_COMM] = of_iomap(node, 1);
+	if (!base[REG_COMM]) {
+		pr_err("failed to map registers for clocksource\n");
+		goto unmap_ch;
+	}
+
+	irq = irq_of_parse_and_map(node, 0);
+	if (!irq) {
+		pr_err("failed to get irq for clockevent\n");
+		goto unmap_comm;
+	}
+
+	of_property_read_u32(node, "renesas,channel", &ch);
+
+	timer16_priv.mapbase = base[REG_CH];
+	timer16_priv.mapcommon = base[REG_COMM];
+	timer16_priv.enb = ch;
+	timer16_priv.ovf = ch;
+	timer16_priv.ovie = 4 + ch;
 
 	ret = request_irq(irq, timer16_interrupt,
-			  IRQF_TIMER, pdev->name, p);
+			  IRQF_TIMER, timer16_priv.cs.name, &timer16_priv);
 	if (ret < 0) {
-		dev_err(&p->pdev->dev, "failed to request irq %d\n", irq);
-		return ret;
+		pr_err("failed to request irq %d of clocksource\n", irq);
+		goto unmap_comm;
 	}
 
-	clocksource_register_hz(&p->cs, clk_get_rate(p->clk) / 8);
+	clocksource_register_hz(&timer16_priv.cs,
+				clk_get_rate(clk) / 8);
+	return;
 
-	return 0;
+unmap_comm:
+	iounmap(base[REG_COMM]);
+unmap_ch:
+	iounmap(base[REG_CH]);
+free_clk:
+	clk_put(clk);
 }
 
-static int timer16_probe(struct platform_device *pdev)
-{
-	struct timer16_priv *p = platform_get_drvdata(pdev);
-
-	if (p) {
-		dev_info(&pdev->dev, "kept as earlytimer\n");
-		return 0;
-	}
-
-	p = devm_kzalloc(&pdev->dev, sizeof(*p), GFP_KERNEL);
-	if (!p)
-		return -ENOMEM;
-
-	return timer16_setup(p, pdev);
-}
-
-static int timer16_remove(struct platform_device *pdev)
-{
-	return -EBUSY;
-}
-
-static const struct of_device_id timer16_of_table[] = {
-	{ .compatible = "renesas,16bit-timer" },
-	{ }
-};
-static struct platform_driver timer16_driver = {
-	.probe		= timer16_probe,
-	.remove		= timer16_remove,
-	.driver		= {
-		.name	= "h8300h-16timer",
-		.of_match_table = of_match_ptr(timer16_of_table),
-	}
-};
-
-static int __init timer16_init(void)
-{
-	return platform_driver_register(&timer16_driver);
-}
-
-static void __exit timer16_exit(void)
-{
-	platform_driver_unregister(&timer16_driver);
-}
-
-subsys_initcall(timer16_init);
-module_exit(timer16_exit);
-MODULE_AUTHOR("Yoshinori Sato");
-MODULE_DESCRIPTION("H8/300H 16bit Timer Driver");
-MODULE_LICENSE("GPL v2");
+CLOCKSOURCE_OF_DECLARE(h8300_16bit, "renesas,16bit-timer", h8300_16timer_init);
diff --git a/drivers/clocksource/h8300_timer8.c b/drivers/clocksource/h8300_timer8.c
index 44375d8..c151941 100644
--- a/drivers/clocksource/h8300_timer8.c
+++ b/drivers/clocksource/h8300_timer8.c
@@ -8,19 +8,15 @@
  */
 
 #include <linux/errno.h>
-#include <linux/sched.h>
 #include <linux/kernel.h>
 #include <linux/interrupt.h>
 #include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/slab.h>
 #include <linux/clockchips.h>
-#include <linux/module.h>
 #include <linux/clk.h>
 #include <linux/io.h>
 #include <linux/of.h>
-
-#include <asm/irq.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
 
 #define _8TCR	0
 #define _8TCSR	2
@@ -28,126 +24,74 @@
 #define TCORB	6
 #define _8TCNT	8
 
-#define FLAG_REPROGRAM (1 << 0)
-#define FLAG_SKIPEVENT (1 << 1)
-#define FLAG_IRQCONTEXT (1 << 2)
+#define CMIEA	6
+#define CMFA	6
+
 #define FLAG_STARTED (1 << 3)
 
-#define ONESHOT  0
-#define PERIODIC 1
+#define SCALE 64
 
-#define RELATIVE 0
-#define ABSOLUTE 1
+#define bset(b, a) iowrite8(ioread8(a) | (1 << (b)), (a))
+#define bclr(b, a) iowrite8(ioread8(a) & ~(1 << (b)), (a))
 
 struct timer8_priv {
-	struct platform_device *pdev;
 	struct clock_event_device ced;
-	struct irqaction irqaction;
-	unsigned long mapbase;
-	raw_spinlock_t lock;
+	void __iomem *mapbase;
 	unsigned long flags;
 	unsigned int rate;
-	unsigned int tcora;
-	struct clk *pclk;
 };
 
-static unsigned long timer8_get_counter(struct timer8_priv *p)
-{
-	unsigned long v1, v2, v3;
-	int o1, o2;
-
-	o1 = ctrl_inb(p->mapbase + _8TCSR) & 0x20;
-
-	/* Make sure the timer value is stable. Stolen from acpi_pm.c */
-	do {
-		o2 = o1;
-		v1 = ctrl_inw(p->mapbase + _8TCNT);
-		v2 = ctrl_inw(p->mapbase + _8TCNT);
-		v3 = ctrl_inw(p->mapbase + _8TCNT);
-		o1 = ctrl_inb(p->mapbase + _8TCSR) & 0x20;
-	} while (unlikely((o1 != o2) || (v1 > v2 && v1 < v3)
-			  || (v2 > v3 && v2 < v1) || (v3 > v1 && v3 < v2)));
-
-	v2 |= o1 << 10;
-	return v2;
-}
-
 static irqreturn_t timer8_interrupt(int irq, void *dev_id)
 {
 	struct timer8_priv *p = dev_id;
 
-	ctrl_outb(ctrl_inb(p->mapbase + _8TCSR) & ~0x40,
-		  p->mapbase + _8TCSR);
-	p->flags |= FLAG_IRQCONTEXT;
-	ctrl_outw(p->tcora, p->mapbase + TCORA);
-	if (!(p->flags & FLAG_SKIPEVENT)) {
-		if (clockevent_state_oneshot(&p->ced))
-			ctrl_outw(0x0000, p->mapbase + _8TCR);
-		p->ced.event_handler(&p->ced);
-	}
-	p->flags &= ~(FLAG_SKIPEVENT | FLAG_IRQCONTEXT);
+	if (clockevent_state_oneshot(&p->ced))
+		iowrite16be(0x0000, p->mapbase + _8TCR);
+
+	p->ced.event_handler(&p->ced);
+
+	bclr(CMFA, p->mapbase + _8TCSR);
 
 	return IRQ_HANDLED;
 }
 
 static void timer8_set_next(struct timer8_priv *p, unsigned long delta)
 {
-	unsigned long flags;
-	unsigned long now;
-
-	raw_spin_lock_irqsave(&p->lock, flags);
 	if (delta >= 0x10000)
-		dev_warn(&p->pdev->dev, "delta out of range\n");
-	now = timer8_get_counter(p);
-	p->tcora = delta;
-	ctrl_outb(ctrl_inb(p->mapbase + _8TCR) | 0x40, p->mapbase + _8TCR);
-	if (delta > now)
-		ctrl_outw(delta, p->mapbase + TCORA);
-	else
-		ctrl_outw(now + 1, p->mapbase + TCORA);
-
-	raw_spin_unlock_irqrestore(&p->lock, flags);
+		pr_warn("delta out of range\n");
+	bclr(CMIEA, p->mapbase + _8TCR);
+	iowrite16be(delta, p->mapbase + TCORA);
+	iowrite16be(0x0000, p->mapbase + _8TCNT);
+	bclr(CMFA, p->mapbase + _8TCSR);
+	bset(CMIEA, p->mapbase + _8TCR);
 }
 
 static int timer8_enable(struct timer8_priv *p)
 {
-	p->rate = clk_get_rate(p->pclk) / 64;
-	ctrl_outw(0xffff, p->mapbase + TCORA);
-	ctrl_outw(0x0000, p->mapbase + _8TCNT);
-	ctrl_outw(0x0c02, p->mapbase + _8TCR);
+	iowrite16be(0xffff, p->mapbase + TCORA);
+	iowrite16be(0x0000, p->mapbase + _8TCNT);
+	iowrite16be(0x0c02, p->mapbase + _8TCR);
 
 	return 0;
 }
 
 static int timer8_start(struct timer8_priv *p)
 {
-	int ret = 0;
-	unsigned long flags;
+	int ret;
 
-	raw_spin_lock_irqsave(&p->lock, flags);
+	if ((p->flags & FLAG_STARTED))
+		return 0;
 
-	if (!(p->flags & FLAG_STARTED))
-		ret = timer8_enable(p);
-
-	if (ret)
-		goto out;
-	p->flags |= FLAG_STARTED;
-
- out:
-	raw_spin_unlock_irqrestore(&p->lock, flags);
+	ret = timer8_enable(p);
+	if (!ret)
+		p->flags |= FLAG_STARTED;
 
 	return ret;
 }
 
 static void timer8_stop(struct timer8_priv *p)
 {
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&p->lock, flags);
-
-	ctrl_outw(0x0000, p->mapbase + _8TCR);
-
-	raw_spin_unlock_irqrestore(&p->lock, flags);
+	iowrite16be(0x0000, p->mapbase + _8TCR);
 }
 
 static inline struct timer8_priv *ced_to_priv(struct clock_event_device *ced)
@@ -155,7 +99,7 @@
 	return container_of(ced, struct timer8_priv, ced);
 }
 
-static void timer8_clock_event_start(struct timer8_priv *p, int periodic)
+static void timer8_clock_event_start(struct timer8_priv *p, unsigned long delta)
 {
 	struct clock_event_device *ced = &p->ced;
 
@@ -166,7 +110,7 @@
 	ced->max_delta_ns = clockevent_delta2ns(0xffff, ced);
 	ced->min_delta_ns = clockevent_delta2ns(0x0001, ced);
 
-	timer8_set_next(p, periodic?(p->rate + HZ/2) / HZ:0x10000);
+	timer8_set_next(p, delta);
 }
 
 static int timer8_clock_event_shutdown(struct clock_event_device *ced)
@@ -179,9 +123,9 @@
 {
 	struct timer8_priv *p = ced_to_priv(ced);
 
-	dev_info(&p->pdev->dev, "used for periodic clock events\n");
+	pr_info("%s: used for periodic clock events\n", ced->name);
 	timer8_stop(p);
-	timer8_clock_event_start(p, PERIODIC);
+	timer8_clock_event_start(p, (p->rate + HZ/2) / HZ);
 
 	return 0;
 }
@@ -190,9 +134,9 @@
 {
 	struct timer8_priv *p = ced_to_priv(ced);
 
-	dev_info(&p->pdev->dev, "used for oneshot clock events\n");
+	pr_info("%s: used for oneshot clock events\n", ced->name);
 	timer8_stop(p);
-	timer8_clock_event_start(p, ONESHOT);
+	timer8_clock_event_start(p, 0x10000);
 
 	return 0;
 }
@@ -208,110 +152,64 @@
 	return 0;
 }
 
-static int timer8_setup(struct timer8_priv *p,
-			struct platform_device *pdev)
+static struct timer8_priv timer8_priv = {
+	.ced = {
+		.name = "h8300_8timer",
+		.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
+		.rating = 200,
+		.set_next_event = timer8_clock_event_next,
+		.set_state_shutdown = timer8_clock_event_shutdown,
+		.set_state_periodic = timer8_clock_event_periodic,
+		.set_state_oneshot = timer8_clock_event_oneshot,
+	},
+};
+
+static void __init h8300_8timer_init(struct device_node *node)
 {
-	struct resource *res;
+	void __iomem *base;
 	int irq;
-	int ret;
+	struct clk *clk;
 
-	p->pdev = pdev;
-
-	res = platform_get_resource(p->pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(&p->pdev->dev, "failed to get I/O memory\n");
-		return -ENXIO;
+	clk = of_clk_get(node, 0);
+	if (IS_ERR(clk)) {
+		pr_err("failed to get clock for clockevent\n");
+		return;
 	}
 
-	irq = platform_get_irq(p->pdev, 0);
-	if (irq < 0) {
-		dev_err(&p->pdev->dev, "failed to get irq\n");
-		return -ENXIO;
+	base = of_iomap(node, 0);
+	if (!base) {
+		pr_err("failed to map registers for clockevent\n");
+		goto free_clk;
 	}
 
-	p->mapbase = res->start;
-
-	p->irqaction.name = dev_name(&p->pdev->dev);
-	p->irqaction.handler = timer8_interrupt;
-	p->irqaction.dev_id = p;
-	p->irqaction.flags = IRQF_TIMER;
-
-	p->pclk = clk_get(&p->pdev->dev, "fck");
-	if (IS_ERR(p->pclk)) {
-		dev_err(&p->pdev->dev, "can't get clk\n");
-		return PTR_ERR(p->pclk);
+	irq = irq_of_parse_and_map(node, 0);
+	if (!irq) {
+		pr_err("failed to get irq for clockevent\n");
+		goto unmap_reg;
 	}
 
-	p->ced.name = pdev->name;
-	p->ced.features = CLOCK_EVT_FEAT_PERIODIC |
-		CLOCK_EVT_FEAT_ONESHOT;
-	p->ced.rating = 200;
-	p->ced.cpumask = cpumask_of(0);
-	p->ced.set_next_event = timer8_clock_event_next;
-	p->ced.set_state_shutdown = timer8_clock_event_shutdown;
-	p->ced.set_state_periodic = timer8_clock_event_periodic;
-	p->ced.set_state_oneshot = timer8_clock_event_oneshot;
+	timer8_priv.mapbase = base;
 
-	ret = setup_irq(irq, &p->irqaction);
-	if (ret < 0) {
-		dev_err(&p->pdev->dev,
-			"failed to request irq %d\n", irq);
-		return ret;
+	timer8_priv.rate = clk_get_rate(clk) / SCALE;
+	if (!timer8_priv.rate) {
+		pr_err("Failed to get rate for the clocksource\n");
+		goto unmap_reg;
 	}
-	clockevents_register_device(&p->ced);
-	platform_set_drvdata(pdev, p);
 
-	return 0;
+	if (request_irq(irq, timer8_interrupt, IRQF_TIMER,
+			timer8_priv.ced.name, &timer8_priv) < 0) {
+		pr_err("failed to request irq %d for clockevent\n", irq);
+		goto unmap_reg;
+	}
+
+	clockevents_config_and_register(&timer8_priv.ced,
+					timer8_priv.rate, 1, 0x0000ffff);
+
+	return;
+unmap_reg:
+	iounmap(base);
+free_clk:
+	clk_put(clk);
 }
 
-static int timer8_probe(struct platform_device *pdev)
-{
-	struct timer8_priv *p = platform_get_drvdata(pdev);
-
-	if (p) {
-		dev_info(&pdev->dev, "kept as earlytimer\n");
-		return 0;
-	}
-
-	p = devm_kzalloc(&pdev->dev, sizeof(*p), GFP_KERNEL);
-	if (!p)
-		return -ENOMEM;
-
-	return timer8_setup(p, pdev);
-}
-
-static int timer8_remove(struct platform_device *pdev)
-{
-	return -EBUSY;
-}
-
-static const struct of_device_id timer8_of_table[] __maybe_unused = {
-	{ .compatible = "renesas,8bit-timer" },
-	{ }
-};
-
-MODULE_DEVICE_TABLE(of, timer8_of_table);
-static struct platform_driver timer8_driver = {
-	.probe		= timer8_probe,
-	.remove		= timer8_remove,
-	.driver		= {
-		.name	= "h8300-8timer",
-		.of_match_table = of_match_ptr(timer8_of_table),
-	}
-};
-
-static int __init timer8_init(void)
-{
-	return platform_driver_register(&timer8_driver);
-}
-
-static void __exit timer8_exit(void)
-{
-	platform_driver_unregister(&timer8_driver);
-}
-
-subsys_initcall(timer8_init);
-module_exit(timer8_exit);
-MODULE_AUTHOR("Yoshinori Sato");
-MODULE_DESCRIPTION("H8/300 8bit Timer Driver");
-MODULE_LICENSE("GPL v2");
+CLOCKSOURCE_OF_DECLARE(h8300_8bit, "renesas,8bit-timer", h8300_8timer_init);
diff --git a/drivers/clocksource/h8300_tpu.c b/drivers/clocksource/h8300_tpu.c
index 5487410..d4c1a28 100644
--- a/drivers/clocksource/h8300_tpu.c
+++ b/drivers/clocksource/h8300_tpu.c
@@ -1,42 +1,30 @@
 /*
- *  H8/300 TPU Driver
+ *  H8S TPU Driver
  *
  *  Copyright 2015 Yoshinori Sato <ysato@users.sourcefoge.jp>
  *
  */
 
 #include <linux/errno.h>
-#include <linux/sched.h>
 #include <linux/kernel.h>
-#include <linux/interrupt.h>
 #include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/slab.h>
 #include <linux/clocksource.h>
-#include <linux/module.h>
 #include <linux/clk.h>
 #include <linux/io.h>
 #include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
 
-#include <asm/irq.h>
+#define TCR	0x0
+#define TSR	0x5
+#define TCNT	0x6
 
-#define TCR	0
-#define TMDR	1
-#define TIOR	2
-#define TER	4
-#define TSR	5
-#define TCNT	6
-#define TGRA	8
-#define TGRB	10
-#define TGRC	12
-#define TGRD	14
+#define TCFV	0x10
 
 struct tpu_priv {
-	struct platform_device *pdev;
 	struct clocksource cs;
-	struct clk *clk;
-	unsigned long mapbase1;
-	unsigned long mapbase2;
+	void __iomem *mapbase1;
+	void __iomem *mapbase2;
 	raw_spinlock_t lock;
 	unsigned int cs_enabled;
 };
@@ -45,8 +33,8 @@
 {
 	unsigned long tcnt;
 
-	tcnt = ctrl_inw(p->mapbase1 + TCNT) << 16;
-	tcnt |= ctrl_inw(p->mapbase2 + TCNT);
+	tcnt = ioread16be(p->mapbase1 + TCNT) << 16;
+	tcnt |= ioread16be(p->mapbase2 + TCNT);
 	return tcnt;
 }
 
@@ -55,7 +43,7 @@
 	unsigned long v1, v2, v3;
 	int o1, o2;
 
-	o1 = ctrl_inb(p->mapbase1 + TSR) & 0x10;
+	o1 = ioread8(p->mapbase1 + TSR) & TCFV;
 
 	/* Make sure the timer value is stable. Stolen from acpi_pm.c */
 	do {
@@ -63,7 +51,7 @@
 		v1 = read_tcnt32(p);
 		v2 = read_tcnt32(p);
 		v3 = read_tcnt32(p);
-		o1 = ctrl_inb(p->mapbase1 + TSR) & 0x10;
+		o1 = ioread8(p->mapbase1 + TSR) & TCFV;
 	} while (unlikely((o1 != o2) || (v1 > v2 && v1 < v3)
 			  || (v2 > v3 && v2 < v1) || (v3 > v1 && v3 < v2)));
 
@@ -96,10 +84,10 @@
 
 	WARN_ON(p->cs_enabled);
 
-	ctrl_outw(0, p->mapbase1 + TCNT);
-	ctrl_outw(0, p->mapbase2 + TCNT);
-	ctrl_outb(0x0f, p->mapbase1 + TCR);
-	ctrl_outb(0x03, p->mapbase2 + TCR);
+	iowrite16be(0, p->mapbase1 + TCNT);
+	iowrite16be(0, p->mapbase2 + TCNT);
+	iowrite8(0x0f, p->mapbase1 + TCR);
+	iowrite8(0x03, p->mapbase2 + TCR);
 
 	p->cs_enabled = true;
 	return 0;
@@ -111,96 +99,59 @@
 
 	WARN_ON(!p->cs_enabled);
 
-	ctrl_outb(0, p->mapbase1 + TCR);
-	ctrl_outb(0, p->mapbase2 + TCR);
+	iowrite8(0, p->mapbase1 + TCR);
+	iowrite8(0, p->mapbase2 + TCR);
 	p->cs_enabled = false;
 }
 
+static struct tpu_priv tpu_priv = {
+	.cs = {
+		.name = "H8S_TPU",
+		.rating = 200,
+		.read = tpu_clocksource_read,
+		.enable = tpu_clocksource_enable,
+		.disable = tpu_clocksource_disable,
+		.mask = CLOCKSOURCE_MASK(sizeof(unsigned long) * 8),
+		.flags = CLOCK_SOURCE_IS_CONTINUOUS,
+	},
+};
+
 #define CH_L 0
 #define CH_H 1
 
-static int __init tpu_setup(struct tpu_priv *p, struct platform_device *pdev)
+static void __init h8300_tpu_init(struct device_node *node)
 {
-	struct resource *res[2];
+	void __iomem *base[2];
+	struct clk *clk;
 
-	p->pdev = pdev;
-
-	res[CH_L] = platform_get_resource(p->pdev, IORESOURCE_MEM, CH_L);
-	res[CH_H] = platform_get_resource(p->pdev, IORESOURCE_MEM, CH_H);
-	if (!res[CH_L] || !res[CH_H]) {
-		dev_err(&p->pdev->dev, "failed to get I/O memory\n");
-		return -ENXIO;
+	clk = of_clk_get(node, 0);
+	if (IS_ERR(clk)) {
+		pr_err("failed to get clock for clocksource\n");
+		return;
 	}
 
-	p->clk = clk_get(&p->pdev->dev, "fck");
-	if (IS_ERR(p->clk)) {
-		dev_err(&p->pdev->dev, "can't get clk\n");
-		return PTR_ERR(p->clk);
+	base[CH_L] = of_iomap(node, CH_L);
+	if (!base[CH_L]) {
+		pr_err("failed to map registers for clocksource\n");
+		goto free_clk;
+	}
+	base[CH_H] = of_iomap(node, CH_H);
+	if (!base[CH_H]) {
+		pr_err("failed to map registers for clocksource\n");
+		goto unmap_L;
 	}
 
-	p->mapbase1 = res[CH_L]->start;
-	p->mapbase2 = res[CH_H]->start;
+	tpu_priv.mapbase1 = base[CH_L];
+	tpu_priv.mapbase2 = base[CH_H];
 
-	p->cs.name = pdev->name;
-	p->cs.rating = 200;
-	p->cs.read = tpu_clocksource_read;
-	p->cs.enable = tpu_clocksource_enable;
-	p->cs.disable = tpu_clocksource_disable;
-	p->cs.mask = CLOCKSOURCE_MASK(sizeof(unsigned long) * 8);
-	p->cs.flags = CLOCK_SOURCE_IS_CONTINUOUS;
-	clocksource_register_hz(&p->cs, clk_get_rate(p->clk) / 64);
-	platform_set_drvdata(pdev, p);
+	clocksource_register_hz(&tpu_priv.cs, clk_get_rate(clk) / 64);
 
-	return 0;
+	return;
+
+unmap_L:
+	iounmap(base[CH_H]);
+free_clk:
+	clk_put(clk);
 }
 
-static int tpu_probe(struct platform_device *pdev)
-{
-	struct tpu_priv *p = platform_get_drvdata(pdev);
-
-	if (p) {
-		dev_info(&pdev->dev, "kept as earlytimer\n");
-		return 0;
-	}
-
-	p = devm_kzalloc(&pdev->dev, sizeof(*p), GFP_KERNEL);
-	if (!p)
-		return -ENOMEM;
-
-	return tpu_setup(p, pdev);
-}
-
-static int tpu_remove(struct platform_device *pdev)
-{
-	return -EBUSY;
-}
-
-static const struct of_device_id tpu_of_table[] = {
-	{ .compatible = "renesas,tpu" },
-	{ }
-};
-
-static struct platform_driver tpu_driver = {
-	.probe		= tpu_probe,
-	.remove		= tpu_remove,
-	.driver		= {
-		.name	= "h8s-tpu",
-		.of_match_table = of_match_ptr(tpu_of_table),
-	}
-};
-
-static int __init tpu_init(void)
-{
-	return platform_driver_register(&tpu_driver);
-}
-
-static void __exit tpu_exit(void)
-{
-	platform_driver_unregister(&tpu_driver);
-}
-
-subsys_initcall(tpu_init);
-module_exit(tpu_exit);
-MODULE_AUTHOR("Yoshinori Sato");
-MODULE_DESCRIPTION("H8S Timer Pulse Unit Driver");
-MODULE_LICENSE("GPL v2");
+CLOCKSOURCE_OF_DECLARE(h8300_tpu, "renesas,tpu", h8300_tpu_init);
diff --git a/drivers/clocksource/mtk_timer.c b/drivers/clocksource/mtk_timer.c
index fbfc746..d67bc35 100644
--- a/drivers/clocksource/mtk_timer.c
+++ b/drivers/clocksource/mtk_timer.c
@@ -16,6 +16,8 @@
  * GNU General Public License for more details.
  */
 
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
 #include <linux/clk.h>
 #include <linux/clockchips.h>
 #include <linux/interrupt.h>
@@ -187,10 +189,8 @@
 	struct clk *clk;
 
 	evt = kzalloc(sizeof(*evt), GFP_KERNEL);
-	if (!evt) {
-		pr_warn("Can't allocate mtk clock event driver struct");
+	if (!evt)
 		return;
-	}
 
 	evt->dev.name = "mtk_tick";
 	evt->dev.rating = 300;
@@ -204,31 +204,31 @@
 
 	evt->gpt_base = of_io_request_and_map(node, 0, "mtk-timer");
 	if (IS_ERR(evt->gpt_base)) {
-		pr_warn("Can't get resource\n");
-		return;
+		pr_err("Can't get resource\n");
+		goto err_kzalloc;
 	}
 
 	evt->dev.irq = irq_of_parse_and_map(node, 0);
 	if (evt->dev.irq <= 0) {
-		pr_warn("Can't parse IRQ");
+		pr_err("Can't parse IRQ\n");
 		goto err_mem;
 	}
 
 	clk = of_clk_get(node, 0);
 	if (IS_ERR(clk)) {
-		pr_warn("Can't get timer clock");
+		pr_err("Can't get timer clock\n");
 		goto err_irq;
 	}
 
 	if (clk_prepare_enable(clk)) {
-		pr_warn("Can't prepare clock");
+		pr_err("Can't prepare clock\n");
 		goto err_clk_put;
 	}
 	rate = clk_get_rate(clk);
 
 	if (request_irq(evt->dev.irq, mtk_timer_interrupt,
 			IRQF_TIMER | IRQF_IRQPOLL, "mtk_timer", evt)) {
-		pr_warn("failed to setup irq %d\n", evt->dev.irq);
+		pr_err("failed to setup irq %d\n", evt->dev.irq);
 		goto err_clk_disable;
 	}
 
@@ -260,5 +260,7 @@
 	iounmap(evt->gpt_base);
 	of_address_to_resource(node, 0, &res);
 	release_mem_region(res.start, resource_size(&res));
+err_kzalloc:
+	kfree(evt);
 }
 CLOCKSOURCE_OF_DECLARE(mtk_mt6577, "mediatek,mt6577-timer", mtk_timer_init);
diff --git a/drivers/clocksource/rockchip_timer.c b/drivers/clocksource/rockchip_timer.c
index d3c1742..8c77a52 100644
--- a/drivers/clocksource/rockchip_timer.c
+++ b/drivers/clocksource/rockchip_timer.c
@@ -17,16 +17,16 @@
 
 #define TIMER_NAME "rk_timer"
 
-#define TIMER_LOAD_COUNT0 0x00
-#define TIMER_LOAD_COUNT1 0x04
-#define TIMER_CONTROL_REG 0x10
-#define TIMER_INT_STATUS 0x18
+#define TIMER_LOAD_COUNT0	0x00
+#define TIMER_LOAD_COUNT1	0x04
+#define TIMER_CONTROL_REG	0x10
+#define TIMER_INT_STATUS	0x18
 
-#define TIMER_DISABLE 0x0
-#define TIMER_ENABLE 0x1
-#define TIMER_MODE_FREE_RUNNING (0 << 1)
-#define TIMER_MODE_USER_DEFINED_COUNT (1 << 1)
-#define TIMER_INT_UNMASK (1 << 2)
+#define TIMER_DISABLE		0x0
+#define TIMER_ENABLE		0x1
+#define TIMER_MODE_FREE_RUNNING			(0 << 1)
+#define TIMER_MODE_USER_DEFINED_COUNT		(1 << 1)
+#define TIMER_INT_UNMASK			(1 << 2)
 
 struct bc_timer {
 	struct clock_event_device ce;
@@ -49,14 +49,12 @@
 static inline void rk_timer_disable(struct clock_event_device *ce)
 {
 	writel_relaxed(TIMER_DISABLE, rk_base(ce) + TIMER_CONTROL_REG);
-	dsb();
 }
 
 static inline void rk_timer_enable(struct clock_event_device *ce, u32 flags)
 {
 	writel_relaxed(TIMER_ENABLE | TIMER_INT_UNMASK | flags,
 		       rk_base(ce) + TIMER_CONTROL_REG);
-	dsb();
 }
 
 static void rk_timer_update_counter(unsigned long cycles,
@@ -64,13 +62,11 @@
 {
 	writel_relaxed(cycles, rk_base(ce) + TIMER_LOAD_COUNT0);
 	writel_relaxed(0, rk_base(ce) + TIMER_LOAD_COUNT1);
-	dsb();
 }
 
 static void rk_timer_interrupt_clear(struct clock_event_device *ce)
 {
 	writel_relaxed(1, rk_base(ce) + TIMER_INT_STATUS);
-	dsb();
 }
 
 static inline int rk_timer_set_next_event(unsigned long cycles,
@@ -173,4 +169,5 @@
 
 	clockevents_config_and_register(ce, bc_timer.freq, 1, UINT_MAX);
 }
+
 CLOCKSOURCE_OF_DECLARE(rk_timer, "rockchip,rk3288-timer", rk_timer_init);
diff --git a/drivers/clocksource/tango_xtal.c b/drivers/clocksource/tango_xtal.c
index d297b30..2bcecaf 100644
--- a/drivers/clocksource/tango_xtal.c
+++ b/drivers/clocksource/tango_xtal.c
@@ -19,19 +19,6 @@
 	return read_xtal_counter();
 }
 
-static cycle_t read_clocksource(struct clocksource *cs)
-{
-	return read_xtal_counter();
-}
-
-static struct clocksource tango_xtal = {
-	.name	= "tango-xtal",
-	.rating	= 350,
-	.read	= read_clocksource,
-	.mask	= CLOCKSOURCE_MASK(32),
-	.flags	= CLOCK_SOURCE_IS_CONTINUOUS,
-};
-
 static void __init tango_clocksource_init(struct device_node *np)
 {
 	struct clk *clk;
@@ -53,8 +40,9 @@
 	delay_timer.freq = xtal_freq;
 	delay_timer.read_current_timer = read_xtal_counter;
 
-	ret = clocksource_register_hz(&tango_xtal, xtal_freq);
-	if (ret != 0) {
+	ret = clocksource_mmio_init(xtal_in_cnt, "tango-xtal", xtal_freq, 350,
+				    32, clocksource_mmio_readl_up);
+	if (!ret) {
 		pr_err("%s: registration failed\n", np->full_name);
 		return;
 	}
diff --git a/drivers/clocksource/tegra20_timer.c b/drivers/clocksource/tegra20_timer.c
index 6ebda11..38333ab 100644
--- a/drivers/clocksource/tegra20_timer.c
+++ b/drivers/clocksource/tegra20_timer.c
@@ -96,7 +96,8 @@
 	.name			= "timer0",
 	.rating			= 300,
 	.features		= CLOCK_EVT_FEAT_ONESHOT |
-				  CLOCK_EVT_FEAT_PERIODIC,
+				  CLOCK_EVT_FEAT_PERIODIC |
+				  CLOCK_EVT_FEAT_DYNIRQ,
 	.set_next_event		= tegra_timer_set_next_event,
 	.set_state_shutdown	= tegra_timer_shutdown,
 	.set_state_periodic	= tegra_timer_set_periodic,
diff --git a/drivers/clocksource/time-lpc32xx.c b/drivers/clocksource/time-lpc32xx.c
index a1c06a2..1316876 100644
--- a/drivers/clocksource/time-lpc32xx.c
+++ b/drivers/clocksource/time-lpc32xx.c
@@ -125,7 +125,7 @@
 
 	clk = of_clk_get_by_name(np, "timerclk");
 	if (IS_ERR(clk)) {
-		pr_err("clock get failed (%lu)\n", PTR_ERR(clk));
+		pr_err("clock get failed (%ld)\n", PTR_ERR(clk));
 		return PTR_ERR(clk);
 	}
 
@@ -184,7 +184,7 @@
 
 	clk = of_clk_get_by_name(np, "timerclk");
 	if (IS_ERR(clk)) {
-		pr_err("clock get failed (%lu)\n", PTR_ERR(clk));
+		pr_err("clock get failed (%ld)\n", PTR_ERR(clk));
 		return PTR_ERR(clk);
 	}
 
diff --git a/drivers/clocksource/time-pistachio.c b/drivers/clocksource/time-pistachio.c
index bba6799..3269d9e 100644
--- a/drivers/clocksource/time-pistachio.c
+++ b/drivers/clocksource/time-pistachio.c
@@ -84,7 +84,7 @@
 	counter = gpt_readl(pcs->base, TIMER_CURRENT_VALUE, 0);
 	raw_spin_unlock_irqrestore(&pcs->lock, flags);
 
-	return ~(cycle_t)counter;
+	return (cycle_t)~counter;
 }
 
 static u64 notrace pistachio_read_sched_clock(void)
diff --git a/drivers/clocksource/timer-sun5i.c b/drivers/clocksource/timer-sun5i.c
index bca9573..24c83f9 100644
--- a/drivers/clocksource/timer-sun5i.c
+++ b/drivers/clocksource/timer-sun5i.c
@@ -152,13 +152,6 @@
 	return IRQ_HANDLED;
 }
 
-static cycle_t sun5i_clksrc_read(struct clocksource *clksrc)
-{
-	struct sun5i_timer_clksrc *cs = to_sun5i_timer_clksrc(clksrc);
-
-	return ~readl(cs->timer.base + TIMER_CNTVAL_LO_REG(1));
-}
-
 static int sun5i_rate_cb_clksrc(struct notifier_block *nb,
 				unsigned long event, void *data)
 {
@@ -217,13 +210,8 @@
 	writel(TIMER_CTL_ENABLE | TIMER_CTL_RELOAD,
 	       base + TIMER_CTL_REG(1));
 
-	cs->clksrc.name = node->name;
-	cs->clksrc.rating = 340;
-	cs->clksrc.read = sun5i_clksrc_read;
-	cs->clksrc.mask = CLOCKSOURCE_MASK(32);
-	cs->clksrc.flags = CLOCK_SOURCE_IS_CONTINUOUS;
-
-	ret = clocksource_register_hz(&cs->clksrc, rate);
+	ret = clocksource_mmio_init(base + TIMER_CNTVAL_LO_REG(1), node->name,
+				    rate, 340, 32, clocksource_mmio_readl_down);
 	if (ret) {
 		pr_err("Couldn't register clock source.\n");
 		goto err_remove_notifier;
diff --git a/drivers/clocksource/vt8500_timer.c b/drivers/clocksource/vt8500_timer.c
index a92e94b..de49805 100644
--- a/drivers/clocksource/vt8500_timer.c
+++ b/drivers/clocksource/vt8500_timer.c
@@ -30,7 +30,6 @@
 #include <linux/clocksource.h>
 #include <linux/clockchips.h>
 #include <linux/delay.h>
-#include <asm/mach/time.h>
 
 #include <linux/of.h>
 #include <linux/of_address.h>
diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index 2569e04..3dd69df9 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -194,6 +194,9 @@
        select CRYPTO_DES
        select CRYPTO_BLKCIPHER
        select CRYPTO_HASH
+       select CRYPTO_MD5
+       select CRYPTO_SHA1
+       select CRYPTO_SHA256
        depends on SPARC64
        help
 	  Each core of a Niagara2 processor contains a Stream
@@ -378,10 +381,10 @@
 
 config CRYPTO_DEV_ATMEL_AES
 	tristate "Support for Atmel AES hw accelerator"
-	depends on ARCH_AT91
+	depends on AT_XDMAC || AT_HDMAC || COMPILE_TEST
 	select CRYPTO_AES
+	select CRYPTO_AEAD
 	select CRYPTO_BLKCIPHER
-	select AT_HDMAC
 	help
 	  Some Atmel processors have AES hw accelerator.
 	  Select this if you want to use the Atmel module for
@@ -498,4 +501,15 @@
 	  To compile this driver as a module, choose M here: the module
 	  will be called sun4i-ss.
 
+config CRYPTO_DEV_ROCKCHIP
+	tristate "Rockchip's Cryptographic Engine driver"
+	depends on OF && ARCH_ROCKCHIP
+	select CRYPTO_AES
+	select CRYPTO_DES
+	select CRYPTO_BLKCIPHER
+
+	help
+	  This driver interfaces with the hardware crypto accelerator.
+	  Supporting cbc/ecb chainmode, and aes/des/des3_ede cipher mode.
+
 endif # CRYPTO_HW
diff --git a/drivers/crypto/Makefile b/drivers/crypto/Makefile
index c3ced6fb..713de9d 100644
--- a/drivers/crypto/Makefile
+++ b/drivers/crypto/Makefile
@@ -29,3 +29,4 @@
 obj-$(CONFIG_CRYPTO_DEV_QCE) += qce/
 obj-$(CONFIG_CRYPTO_DEV_VMX) += vmx/
 obj-$(CONFIG_CRYPTO_DEV_SUN4I_SS) += sunxi-ss/
+obj-$(CONFIG_CRYPTO_DEV_ROCKCHIP) += rockchip/
diff --git a/drivers/crypto/amcc/crypto4xx_core.c b/drivers/crypto/amcc/crypto4xx_core.c
index 58a630e..62134c8 100644
--- a/drivers/crypto/amcc/crypto4xx_core.c
+++ b/drivers/crypto/amcc/crypto4xx_core.c
@@ -781,6 +781,10 @@
 
 	/* figure how many gd is needed */
 	num_gd = sg_nents_for_len(src, datalen);
+	if ((int)num_gd < 0) {
+		dev_err(dev->core_dev->device, "Invalid number of src SG.\n");
+		return -EINVAL;
+	}
 	if (num_gd == 1)
 		num_gd = 0;
 
diff --git a/drivers/crypto/atmel-aes-regs.h b/drivers/crypto/atmel-aes-regs.h
index 2786bb1..6c2951b 100644
--- a/drivers/crypto/atmel-aes-regs.h
+++ b/drivers/crypto/atmel-aes-regs.h
@@ -9,6 +9,7 @@
 #define	AES_MR			0x04
 #define AES_MR_CYPHER_DEC		(0 << 0)
 #define AES_MR_CYPHER_ENC		(1 << 0)
+#define AES_MR_GTAGEN			(1 << 1)
 #define	AES_MR_DUALBUFF			(1 << 3)
 #define AES_MR_PROCDLY_MASK		(0xF << 4)
 #define AES_MR_PROCDLY_OFFSET	4
@@ -26,6 +27,7 @@
 #define AES_MR_OPMOD_OFB		(0x2 << 12)
 #define AES_MR_OPMOD_CFB		(0x3 << 12)
 #define AES_MR_OPMOD_CTR		(0x4 << 12)
+#define AES_MR_OPMOD_GCM		(0x5 << 12)
 #define AES_MR_LOD				(0x1 << 15)
 #define AES_MR_CFBS_MASK		(0x7 << 16)
 #define AES_MR_CFBS_128b		(0x0 << 16)
@@ -44,6 +46,7 @@
 #define	AES_ISR		0x1C
 #define AES_INT_DATARDY		(1 << 0)
 #define AES_INT_URAD		(1 << 8)
+#define AES_INT_TAGRDY		(1 << 16)
 #define AES_ISR_URAT_MASK	(0xF << 12)
 #define AES_ISR_URAT_IDR_WR_PROC	(0x0 << 12)
 #define AES_ISR_URAT_ODR_RD_PROC	(0x1 << 12)
@@ -57,6 +60,13 @@
 #define AES_ODATAR(x)	(0x50 + ((x) * 0x04))
 #define AES_IVR(x)		(0x60 + ((x) * 0x04))
 
+#define AES_AADLENR	0x70
+#define AES_CLENR	0x74
+#define AES_GHASHR(x)	(0x78 + ((x) * 0x04))
+#define AES_TAGR(x)	(0x88 + ((x) * 0x04))
+#define AES_CTRR	0x98
+#define AES_GCMHR(x)	(0x9c + ((x) * 0x04))
+
 #define AES_HW_VERSION	0xFC
 
 #endif /* __ATMEL_AES_REGS_H__ */
diff --git a/drivers/crypto/atmel-aes.c b/drivers/crypto/atmel-aes.c
index fb16d81..5621612 100644
--- a/drivers/crypto/atmel-aes.c
+++ b/drivers/crypto/atmel-aes.c
@@ -33,68 +33,118 @@
 #include <linux/of_device.h>
 #include <linux/delay.h>
 #include <linux/crypto.h>
-#include <linux/cryptohash.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/algapi.h>
 #include <crypto/aes.h>
-#include <crypto/hash.h>
-#include <crypto/internal/hash.h>
+#include <crypto/internal/aead.h>
 #include <linux/platform_data/crypto-atmel.h>
 #include <dt-bindings/dma/at91.h>
 #include "atmel-aes-regs.h"
 
+#define ATMEL_AES_PRIORITY	300
+
+#define ATMEL_AES_BUFFER_ORDER	2
+#define ATMEL_AES_BUFFER_SIZE	(PAGE_SIZE << ATMEL_AES_BUFFER_ORDER)
+
 #define CFB8_BLOCK_SIZE		1
 #define CFB16_BLOCK_SIZE	2
 #define CFB32_BLOCK_SIZE	4
 #define CFB64_BLOCK_SIZE	8
 
-/* AES flags */
-#define AES_FLAGS_MODE_MASK	0x03ff
-#define AES_FLAGS_ENCRYPT	BIT(0)
-#define AES_FLAGS_CBC		BIT(1)
-#define AES_FLAGS_CFB		BIT(2)
-#define AES_FLAGS_CFB8		BIT(3)
-#define AES_FLAGS_CFB16		BIT(4)
-#define AES_FLAGS_CFB32		BIT(5)
-#define AES_FLAGS_CFB64		BIT(6)
-#define AES_FLAGS_CFB128	BIT(7)
-#define AES_FLAGS_OFB		BIT(8)
-#define AES_FLAGS_CTR		BIT(9)
+#define SIZE_IN_WORDS(x)	((x) >> 2)
 
-#define AES_FLAGS_INIT		BIT(16)
-#define AES_FLAGS_DMA		BIT(17)
-#define AES_FLAGS_BUSY		BIT(18)
-#define AES_FLAGS_FAST		BIT(19)
+/* AES flags */
+/* Reserve bits [18:16] [14:12] [1:0] for mode (same as for AES_MR) */
+#define AES_FLAGS_ENCRYPT	AES_MR_CYPHER_ENC
+#define AES_FLAGS_GTAGEN	AES_MR_GTAGEN
+#define AES_FLAGS_OPMODE_MASK	(AES_MR_OPMOD_MASK | AES_MR_CFBS_MASK)
+#define AES_FLAGS_ECB		AES_MR_OPMOD_ECB
+#define AES_FLAGS_CBC		AES_MR_OPMOD_CBC
+#define AES_FLAGS_OFB		AES_MR_OPMOD_OFB
+#define AES_FLAGS_CFB128	(AES_MR_OPMOD_CFB | AES_MR_CFBS_128b)
+#define AES_FLAGS_CFB64		(AES_MR_OPMOD_CFB | AES_MR_CFBS_64b)
+#define AES_FLAGS_CFB32		(AES_MR_OPMOD_CFB | AES_MR_CFBS_32b)
+#define AES_FLAGS_CFB16		(AES_MR_OPMOD_CFB | AES_MR_CFBS_16b)
+#define AES_FLAGS_CFB8		(AES_MR_OPMOD_CFB | AES_MR_CFBS_8b)
+#define AES_FLAGS_CTR		AES_MR_OPMOD_CTR
+#define AES_FLAGS_GCM		AES_MR_OPMOD_GCM
+
+#define AES_FLAGS_MODE_MASK	(AES_FLAGS_OPMODE_MASK |	\
+				 AES_FLAGS_ENCRYPT |		\
+				 AES_FLAGS_GTAGEN)
+
+#define AES_FLAGS_INIT		BIT(2)
+#define AES_FLAGS_BUSY		BIT(3)
+#define AES_FLAGS_DUMP_REG	BIT(4)
+
+#define AES_FLAGS_PERSISTENT	(AES_FLAGS_INIT | AES_FLAGS_BUSY)
 
 #define ATMEL_AES_QUEUE_LENGTH	50
 
-#define ATMEL_AES_DMA_THRESHOLD		16
+#define ATMEL_AES_DMA_THRESHOLD		256
 
 
 struct atmel_aes_caps {
-	bool	has_dualbuff;
-	bool	has_cfb64;
-	u32		max_burst_size;
+	bool			has_dualbuff;
+	bool			has_cfb64;
+	bool			has_ctr32;
+	bool			has_gcm;
+	u32			max_burst_size;
 };
 
 struct atmel_aes_dev;
 
+
+typedef int (*atmel_aes_fn_t)(struct atmel_aes_dev *);
+
+
+struct atmel_aes_base_ctx {
+	struct atmel_aes_dev	*dd;
+	atmel_aes_fn_t		start;
+	int			keylen;
+	u32			key[AES_KEYSIZE_256 / sizeof(u32)];
+	u16			block_size;
+};
+
 struct atmel_aes_ctx {
-	struct atmel_aes_dev *dd;
+	struct atmel_aes_base_ctx	base;
+};
 
-	int		keylen;
-	u32		key[AES_KEYSIZE_256 / sizeof(u32)];
+struct atmel_aes_ctr_ctx {
+	struct atmel_aes_base_ctx	base;
 
-	u16		block_size;
+	u32			iv[AES_BLOCK_SIZE / sizeof(u32)];
+	size_t			offset;
+	struct scatterlist	src[2];
+	struct scatterlist	dst[2];
+};
+
+struct atmel_aes_gcm_ctx {
+	struct atmel_aes_base_ctx	base;
+
+	struct scatterlist	src[2];
+	struct scatterlist	dst[2];
+
+	u32			j0[AES_BLOCK_SIZE / sizeof(u32)];
+	u32			tag[AES_BLOCK_SIZE / sizeof(u32)];
+	u32			ghash[AES_BLOCK_SIZE / sizeof(u32)];
+	size_t			textlen;
+
+	const u32		*ghash_in;
+	u32			*ghash_out;
+	atmel_aes_fn_t		ghash_resume;
 };
 
 struct atmel_aes_reqctx {
-	unsigned long mode;
+	unsigned long		mode;
 };
 
 struct atmel_aes_dma {
-	struct dma_chan			*chan;
-	struct dma_slave_config dma_conf;
+	struct dma_chan		*chan;
+	struct scatterlist	*sg;
+	int			nents;
+	unsigned int		remainder;
+	unsigned int		sg_len;
 };
 
 struct atmel_aes_dev {
@@ -102,13 +152,18 @@
 	unsigned long		phys_base;
 	void __iomem		*io_base;
 
-	struct atmel_aes_ctx	*ctx;
+	struct crypto_async_request	*areq;
+	struct atmel_aes_base_ctx	*ctx;
+
+	bool			is_async;
+	atmel_aes_fn_t		resume;
+	atmel_aes_fn_t		cpu_transfer_complete;
+
 	struct device		*dev;
 	struct clk		*iclk;
-	int	irq;
+	int			irq;
 
 	unsigned long		flags;
-	int	err;
 
 	spinlock_t		lock;
 	struct crypto_queue	queue;
@@ -116,33 +171,21 @@
 	struct tasklet_struct	done_task;
 	struct tasklet_struct	queue_task;
 
-	struct ablkcipher_request	*req;
-	size_t	total;
+	size_t			total;
+	size_t			datalen;
+	u32			*data;
 
-	struct scatterlist	*in_sg;
-	unsigned int		nb_in_sg;
-	size_t				in_offset;
-	struct scatterlist	*out_sg;
-	unsigned int		nb_out_sg;
-	size_t				out_offset;
+	struct atmel_aes_dma	src;
+	struct atmel_aes_dma	dst;
 
-	size_t	bufcnt;
-	size_t	buflen;
-	size_t	dma_size;
-
-	void	*buf_in;
-	int		dma_in;
-	dma_addr_t	dma_addr_in;
-	struct atmel_aes_dma	dma_lch_in;
-
-	void	*buf_out;
-	int		dma_out;
-	dma_addr_t	dma_addr_out;
-	struct atmel_aes_dma	dma_lch_out;
+	size_t			buflen;
+	void			*buf;
+	struct scatterlist	aligned_sg;
+	struct scatterlist	*real_dst;
 
 	struct atmel_aes_caps	caps;
 
-	u32	hw_version;
+	u32			hw_version;
 };
 
 struct atmel_aes_drv {
@@ -155,71 +198,128 @@
 	.lock = __SPIN_LOCK_UNLOCKED(atmel_aes.lock),
 };
 
-static int atmel_aes_sg_length(struct ablkcipher_request *req,
-			struct scatterlist *sg)
+#ifdef VERBOSE_DEBUG
+static const char *atmel_aes_reg_name(u32 offset, char *tmp, size_t sz)
 {
-	unsigned int total = req->nbytes;
-	int sg_nb;
-	unsigned int len;
-	struct scatterlist *sg_list;
+	switch (offset) {
+	case AES_CR:
+		return "CR";
 
-	sg_nb = 0;
-	sg_list = sg;
-	total = req->nbytes;
+	case AES_MR:
+		return "MR";
 
-	while (total) {
-		len = min(sg_list->length, total);
+	case AES_ISR:
+		return "ISR";
 
-		sg_nb++;
-		total -= len;
+	case AES_IMR:
+		return "IMR";
 
-		sg_list = sg_next(sg_list);
-		if (!sg_list)
-			total = 0;
+	case AES_IER:
+		return "IER";
+
+	case AES_IDR:
+		return "IDR";
+
+	case AES_KEYWR(0):
+	case AES_KEYWR(1):
+	case AES_KEYWR(2):
+	case AES_KEYWR(3):
+	case AES_KEYWR(4):
+	case AES_KEYWR(5):
+	case AES_KEYWR(6):
+	case AES_KEYWR(7):
+		snprintf(tmp, sz, "KEYWR[%u]", (offset - AES_KEYWR(0)) >> 2);
+		break;
+
+	case AES_IDATAR(0):
+	case AES_IDATAR(1):
+	case AES_IDATAR(2):
+	case AES_IDATAR(3):
+		snprintf(tmp, sz, "IDATAR[%u]", (offset - AES_IDATAR(0)) >> 2);
+		break;
+
+	case AES_ODATAR(0):
+	case AES_ODATAR(1):
+	case AES_ODATAR(2):
+	case AES_ODATAR(3):
+		snprintf(tmp, sz, "ODATAR[%u]", (offset - AES_ODATAR(0)) >> 2);
+		break;
+
+	case AES_IVR(0):
+	case AES_IVR(1):
+	case AES_IVR(2):
+	case AES_IVR(3):
+		snprintf(tmp, sz, "IVR[%u]", (offset - AES_IVR(0)) >> 2);
+		break;
+
+	case AES_AADLENR:
+		return "AADLENR";
+
+	case AES_CLENR:
+		return "CLENR";
+
+	case AES_GHASHR(0):
+	case AES_GHASHR(1):
+	case AES_GHASHR(2):
+	case AES_GHASHR(3):
+		snprintf(tmp, sz, "GHASHR[%u]", (offset - AES_GHASHR(0)) >> 2);
+		break;
+
+	case AES_TAGR(0):
+	case AES_TAGR(1):
+	case AES_TAGR(2):
+	case AES_TAGR(3):
+		snprintf(tmp, sz, "TAGR[%u]", (offset - AES_TAGR(0)) >> 2);
+		break;
+
+	case AES_CTRR:
+		return "CTRR";
+
+	case AES_GCMHR(0):
+	case AES_GCMHR(1):
+	case AES_GCMHR(2):
+	case AES_GCMHR(3):
+		snprintf(tmp, sz, "GCMHR[%u]", (offset - AES_GCMHR(0)) >> 2);
+
+	default:
+		snprintf(tmp, sz, "0x%02x", offset);
+		break;
 	}
 
-	return sg_nb;
+	return tmp;
 }
+#endif /* VERBOSE_DEBUG */
 
-static int atmel_aes_sg_copy(struct scatterlist **sg, size_t *offset,
-			void *buf, size_t buflen, size_t total, int out)
-{
-	unsigned int count, off = 0;
-
-	while (buflen && total) {
-		count = min((*sg)->length - *offset, total);
-		count = min(count, buflen);
-
-		if (!count)
-			return off;
-
-		scatterwalk_map_and_copy(buf + off, *sg, *offset, count, out);
-
-		off += count;
-		buflen -= count;
-		*offset += count;
-		total -= count;
-
-		if (*offset == (*sg)->length) {
-			*sg = sg_next(*sg);
-			if (*sg)
-				*offset = 0;
-			else
-				total = 0;
-		}
-	}
-
-	return off;
-}
+/* Shared functions */
 
 static inline u32 atmel_aes_read(struct atmel_aes_dev *dd, u32 offset)
 {
-	return readl_relaxed(dd->io_base + offset);
+	u32 value = readl_relaxed(dd->io_base + offset);
+
+#ifdef VERBOSE_DEBUG
+	if (dd->flags & AES_FLAGS_DUMP_REG) {
+		char tmp[16];
+
+		dev_vdbg(dd->dev, "read 0x%08x from %s\n", value,
+			 atmel_aes_reg_name(offset, tmp, sizeof(tmp)));
+	}
+#endif /* VERBOSE_DEBUG */
+
+	return value;
 }
 
 static inline void atmel_aes_write(struct atmel_aes_dev *dd,
 					u32 offset, u32 value)
 {
+#ifdef VERBOSE_DEBUG
+	if (dd->flags & AES_FLAGS_DUMP_REG) {
+		char tmp[16];
+
+		dev_vdbg(dd->dev, "write 0x%08x into %s\n", value,
+			 atmel_aes_reg_name(offset, tmp));
+	}
+#endif /* VERBOSE_DEBUG */
+
 	writel_relaxed(value, dd->io_base + offset);
 }
 
@@ -231,13 +331,50 @@
 }
 
 static void atmel_aes_write_n(struct atmel_aes_dev *dd, u32 offset,
-					u32 *value, int count)
+			      const u32 *value, int count)
 {
 	for (; count--; value++, offset += 4)
 		atmel_aes_write(dd, offset, *value);
 }
 
-static struct atmel_aes_dev *atmel_aes_find_dev(struct atmel_aes_ctx *ctx)
+static inline void atmel_aes_read_block(struct atmel_aes_dev *dd, u32 offset,
+					u32 *value)
+{
+	atmel_aes_read_n(dd, offset, value, SIZE_IN_WORDS(AES_BLOCK_SIZE));
+}
+
+static inline void atmel_aes_write_block(struct atmel_aes_dev *dd, u32 offset,
+					 const u32 *value)
+{
+	atmel_aes_write_n(dd, offset, value, SIZE_IN_WORDS(AES_BLOCK_SIZE));
+}
+
+static inline int atmel_aes_wait_for_data_ready(struct atmel_aes_dev *dd,
+						atmel_aes_fn_t resume)
+{
+	u32 isr = atmel_aes_read(dd, AES_ISR);
+
+	if (unlikely(isr & AES_INT_DATARDY))
+		return resume(dd);
+
+	dd->resume = resume;
+	atmel_aes_write(dd, AES_IER, AES_INT_DATARDY);
+	return -EINPROGRESS;
+}
+
+static inline size_t atmel_aes_padlen(size_t len, size_t block_size)
+{
+	len &= block_size - 1;
+	return len ? block_size - len : 0;
+}
+
+static inline struct aead_request *
+aead_request_cast(struct crypto_async_request *req)
+{
+	return container_of(req, struct aead_request, base);
+}
+
+static struct atmel_aes_dev *atmel_aes_find_dev(struct atmel_aes_base_ctx *ctx)
 {
 	struct atmel_aes_dev *aes_dd = NULL;
 	struct atmel_aes_dev *tmp;
@@ -270,7 +407,6 @@
 		atmel_aes_write(dd, AES_CR, AES_CR_SWRST);
 		atmel_aes_write(dd, AES_MR, 0xE << AES_MR_CKEY_OFFSET);
 		dd->flags |= AES_FLAGS_INIT;
-		dd->err = 0;
 	}
 
 	return 0;
@@ -281,227 +417,51 @@
 	return atmel_aes_read(dd, AES_HW_VERSION) & 0x00000fff;
 }
 
-static void atmel_aes_hw_version_init(struct atmel_aes_dev *dd)
+static int atmel_aes_hw_version_init(struct atmel_aes_dev *dd)
 {
-	atmel_aes_hw_init(dd);
+	int err;
+
+	err = atmel_aes_hw_init(dd);
+	if (err)
+		return err;
 
 	dd->hw_version = atmel_aes_get_version(dd);
 
-	dev_info(dd->dev,
-			"version: 0x%x\n", dd->hw_version);
+	dev_info(dd->dev, "version: 0x%x\n", dd->hw_version);
 
 	clk_disable_unprepare(dd->iclk);
+	return 0;
 }
 
-static void atmel_aes_finish_req(struct atmel_aes_dev *dd, int err)
+static inline void atmel_aes_set_mode(struct atmel_aes_dev *dd,
+				      const struct atmel_aes_reqctx *rctx)
 {
-	struct ablkcipher_request *req = dd->req;
+	/* Clear all but persistent flags and set request flags. */
+	dd->flags = (dd->flags & AES_FLAGS_PERSISTENT) | rctx->mode;
+}
 
+static inline bool atmel_aes_is_encrypt(const struct atmel_aes_dev *dd)
+{
+	return (dd->flags & AES_FLAGS_ENCRYPT);
+}
+
+static inline int atmel_aes_complete(struct atmel_aes_dev *dd, int err)
+{
 	clk_disable_unprepare(dd->iclk);
 	dd->flags &= ~AES_FLAGS_BUSY;
 
-	req->base.complete(&req->base, err);
-}
+	if (dd->is_async)
+		dd->areq->complete(dd->areq, err);
 
-static void atmel_aes_dma_callback(void *data)
-{
-	struct atmel_aes_dev *dd = data;
-
-	/* dma_lch_out - completed */
-	tasklet_schedule(&dd->done_task);
-}
-
-static int atmel_aes_crypt_dma(struct atmel_aes_dev *dd,
-		dma_addr_t dma_addr_in, dma_addr_t dma_addr_out, int length)
-{
-	struct scatterlist sg[2];
-	struct dma_async_tx_descriptor	*in_desc, *out_desc;
-
-	dd->dma_size = length;
-
-	dma_sync_single_for_device(dd->dev, dma_addr_in, length,
-				   DMA_TO_DEVICE);
-	dma_sync_single_for_device(dd->dev, dma_addr_out, length,
-				   DMA_FROM_DEVICE);
-
-	if (dd->flags & AES_FLAGS_CFB8) {
-		dd->dma_lch_in.dma_conf.dst_addr_width =
-			DMA_SLAVE_BUSWIDTH_1_BYTE;
-		dd->dma_lch_out.dma_conf.src_addr_width =
-			DMA_SLAVE_BUSWIDTH_1_BYTE;
-	} else if (dd->flags & AES_FLAGS_CFB16) {
-		dd->dma_lch_in.dma_conf.dst_addr_width =
-			DMA_SLAVE_BUSWIDTH_2_BYTES;
-		dd->dma_lch_out.dma_conf.src_addr_width =
-			DMA_SLAVE_BUSWIDTH_2_BYTES;
-	} else {
-		dd->dma_lch_in.dma_conf.dst_addr_width =
-			DMA_SLAVE_BUSWIDTH_4_BYTES;
-		dd->dma_lch_out.dma_conf.src_addr_width =
-			DMA_SLAVE_BUSWIDTH_4_BYTES;
-	}
-
-	if (dd->flags & (AES_FLAGS_CFB8 | AES_FLAGS_CFB16 |
-			AES_FLAGS_CFB32 | AES_FLAGS_CFB64)) {
-		dd->dma_lch_in.dma_conf.src_maxburst = 1;
-		dd->dma_lch_in.dma_conf.dst_maxburst = 1;
-		dd->dma_lch_out.dma_conf.src_maxburst = 1;
-		dd->dma_lch_out.dma_conf.dst_maxburst = 1;
-	} else {
-		dd->dma_lch_in.dma_conf.src_maxburst = dd->caps.max_burst_size;
-		dd->dma_lch_in.dma_conf.dst_maxburst = dd->caps.max_burst_size;
-		dd->dma_lch_out.dma_conf.src_maxburst = dd->caps.max_burst_size;
-		dd->dma_lch_out.dma_conf.dst_maxburst = dd->caps.max_burst_size;
-	}
-
-	dmaengine_slave_config(dd->dma_lch_in.chan, &dd->dma_lch_in.dma_conf);
-	dmaengine_slave_config(dd->dma_lch_out.chan, &dd->dma_lch_out.dma_conf);
-
-	dd->flags |= AES_FLAGS_DMA;
-
-	sg_init_table(&sg[0], 1);
-	sg_dma_address(&sg[0]) = dma_addr_in;
-	sg_dma_len(&sg[0]) = length;
-
-	sg_init_table(&sg[1], 1);
-	sg_dma_address(&sg[1]) = dma_addr_out;
-	sg_dma_len(&sg[1]) = length;
-
-	in_desc = dmaengine_prep_slave_sg(dd->dma_lch_in.chan, &sg[0],
-				1, DMA_MEM_TO_DEV,
-				DMA_PREP_INTERRUPT  |  DMA_CTRL_ACK);
-	if (!in_desc)
-		return -EINVAL;
-
-	out_desc = dmaengine_prep_slave_sg(dd->dma_lch_out.chan, &sg[1],
-				1, DMA_DEV_TO_MEM,
-				DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
-	if (!out_desc)
-		return -EINVAL;
-
-	out_desc->callback = atmel_aes_dma_callback;
-	out_desc->callback_param = dd;
-
-	dmaengine_submit(out_desc);
-	dma_async_issue_pending(dd->dma_lch_out.chan);
-
-	dmaengine_submit(in_desc);
-	dma_async_issue_pending(dd->dma_lch_in.chan);
-
-	return 0;
-}
-
-static int atmel_aes_crypt_cpu_start(struct atmel_aes_dev *dd)
-{
-	dd->flags &= ~AES_FLAGS_DMA;
-
-	dma_sync_single_for_cpu(dd->dev, dd->dma_addr_in,
-				dd->dma_size, DMA_TO_DEVICE);
-	dma_sync_single_for_cpu(dd->dev, dd->dma_addr_out,
-				dd->dma_size, DMA_FROM_DEVICE);
-
-	/* use cache buffers */
-	dd->nb_in_sg = atmel_aes_sg_length(dd->req, dd->in_sg);
-	if (!dd->nb_in_sg)
-		return -EINVAL;
-
-	dd->nb_out_sg = atmel_aes_sg_length(dd->req, dd->out_sg);
-	if (!dd->nb_out_sg)
-		return -EINVAL;
-
-	dd->bufcnt = sg_copy_to_buffer(dd->in_sg, dd->nb_in_sg,
-					dd->buf_in, dd->total);
-
-	if (!dd->bufcnt)
-		return -EINVAL;
-
-	dd->total -= dd->bufcnt;
-
-	atmel_aes_write(dd, AES_IER, AES_INT_DATARDY);
-	atmel_aes_write_n(dd, AES_IDATAR(0), (u32 *) dd->buf_in,
-				dd->bufcnt >> 2);
-
-	return 0;
-}
-
-static int atmel_aes_crypt_dma_start(struct atmel_aes_dev *dd)
-{
-	int err, fast = 0, in, out;
-	size_t count;
-	dma_addr_t addr_in, addr_out;
-
-	if ((!dd->in_offset) && (!dd->out_offset)) {
-		/* check for alignment */
-		in = IS_ALIGNED((u32)dd->in_sg->offset, sizeof(u32)) &&
-			IS_ALIGNED(dd->in_sg->length, dd->ctx->block_size);
-		out = IS_ALIGNED((u32)dd->out_sg->offset, sizeof(u32)) &&
-			IS_ALIGNED(dd->out_sg->length, dd->ctx->block_size);
-		fast = in && out;
-
-		if (sg_dma_len(dd->in_sg) != sg_dma_len(dd->out_sg))
-			fast = 0;
-	}
-
-
-	if (fast)  {
-		count = min(dd->total, sg_dma_len(dd->in_sg));
-		count = min(count, sg_dma_len(dd->out_sg));
-
-		err = dma_map_sg(dd->dev, dd->in_sg, 1, DMA_TO_DEVICE);
-		if (!err) {
-			dev_err(dd->dev, "dma_map_sg() error\n");
-			return -EINVAL;
-		}
-
-		err = dma_map_sg(dd->dev, dd->out_sg, 1,
-				DMA_FROM_DEVICE);
-		if (!err) {
-			dev_err(dd->dev, "dma_map_sg() error\n");
-			dma_unmap_sg(dd->dev, dd->in_sg, 1,
-				DMA_TO_DEVICE);
-			return -EINVAL;
-		}
-
-		addr_in = sg_dma_address(dd->in_sg);
-		addr_out = sg_dma_address(dd->out_sg);
-
-		dd->flags |= AES_FLAGS_FAST;
-
-	} else {
-		dma_sync_single_for_cpu(dd->dev, dd->dma_addr_in,
-					dd->dma_size, DMA_TO_DEVICE);
-
-		/* use cache buffers */
-		count = atmel_aes_sg_copy(&dd->in_sg, &dd->in_offset,
-				dd->buf_in, dd->buflen, dd->total, 0);
-
-		addr_in = dd->dma_addr_in;
-		addr_out = dd->dma_addr_out;
-
-		dd->flags &= ~AES_FLAGS_FAST;
-	}
-
-	dd->total -= count;
-
-	err = atmel_aes_crypt_dma(dd, addr_in, addr_out, count);
-
-	if (err && (dd->flags & AES_FLAGS_FAST)) {
-		dma_unmap_sg(dd->dev, dd->in_sg, 1, DMA_TO_DEVICE);
-		dma_unmap_sg(dd->dev, dd->out_sg, 1, DMA_TO_DEVICE);
-	}
+	tasklet_schedule(&dd->queue_task);
 
 	return err;
 }
 
-static int atmel_aes_write_ctrl(struct atmel_aes_dev *dd)
+static void atmel_aes_write_ctrl(struct atmel_aes_dev *dd, bool use_dma,
+				 const u32 *iv)
 {
-	int err;
-	u32 valcr = 0, valmr = 0;
-
-	err = atmel_aes_hw_init(dd);
-
-	if (err)
-		return err;
+	u32 valmr = 0;
 
 	/* MR register must be set before IV registers */
 	if (dd->ctx->keylen == AES_KEYSIZE_128)
@@ -511,32 +471,9 @@
 	else
 		valmr |= AES_MR_KEYSIZE_256;
 
-	if (dd->flags & AES_FLAGS_CBC) {
-		valmr |= AES_MR_OPMOD_CBC;
-	} else if (dd->flags & AES_FLAGS_CFB) {
-		valmr |= AES_MR_OPMOD_CFB;
-		if (dd->flags & AES_FLAGS_CFB8)
-			valmr |= AES_MR_CFBS_8b;
-		else if (dd->flags & AES_FLAGS_CFB16)
-			valmr |= AES_MR_CFBS_16b;
-		else if (dd->flags & AES_FLAGS_CFB32)
-			valmr |= AES_MR_CFBS_32b;
-		else if (dd->flags & AES_FLAGS_CFB64)
-			valmr |= AES_MR_CFBS_64b;
-		else if (dd->flags & AES_FLAGS_CFB128)
-			valmr |= AES_MR_CFBS_128b;
-	} else if (dd->flags & AES_FLAGS_OFB) {
-		valmr |= AES_MR_OPMOD_OFB;
-	} else if (dd->flags & AES_FLAGS_CTR) {
-		valmr |= AES_MR_OPMOD_CTR;
-	} else {
-		valmr |= AES_MR_OPMOD_ECB;
-	}
+	valmr |= dd->flags & AES_FLAGS_MODE_MASK;
 
-	if (dd->flags & AES_FLAGS_ENCRYPT)
-		valmr |= AES_MR_CYPHER_ENC;
-
-	if (dd->total > ATMEL_AES_DMA_THRESHOLD) {
+	if (use_dma) {
 		valmr |= AES_MR_SMOD_IDATAR0;
 		if (dd->caps.has_dualbuff)
 			valmr |= AES_MR_DUALBUFF;
@@ -544,289 +481,579 @@
 		valmr |= AES_MR_SMOD_AUTO;
 	}
 
-	atmel_aes_write(dd, AES_CR, valcr);
 	atmel_aes_write(dd, AES_MR, valmr);
 
 	atmel_aes_write_n(dd, AES_KEYWR(0), dd->ctx->key,
-						dd->ctx->keylen >> 2);
+			  SIZE_IN_WORDS(dd->ctx->keylen));
 
-	if (((dd->flags & AES_FLAGS_CBC) || (dd->flags & AES_FLAGS_CFB) ||
-	   (dd->flags & AES_FLAGS_OFB) || (dd->flags & AES_FLAGS_CTR)) &&
-	   dd->req->info) {
-		atmel_aes_write_n(dd, AES_IVR(0), dd->req->info, 4);
+	if (iv && (valmr & AES_MR_OPMOD_MASK) != AES_MR_OPMOD_ECB)
+		atmel_aes_write_block(dd, AES_IVR(0), iv);
+}
+
+
+/* CPU transfer */
+
+static int atmel_aes_cpu_transfer(struct atmel_aes_dev *dd)
+{
+	int err = 0;
+	u32 isr;
+
+	for (;;) {
+		atmel_aes_read_block(dd, AES_ODATAR(0), dd->data);
+		dd->data += 4;
+		dd->datalen -= AES_BLOCK_SIZE;
+
+		if (dd->datalen < AES_BLOCK_SIZE)
+			break;
+
+		atmel_aes_write_block(dd, AES_IDATAR(0), dd->data);
+
+		isr = atmel_aes_read(dd, AES_ISR);
+		if (!(isr & AES_INT_DATARDY)) {
+			dd->resume = atmel_aes_cpu_transfer;
+			atmel_aes_write(dd, AES_IER, AES_INT_DATARDY);
+			return -EINPROGRESS;
+		}
+	}
+
+	if (!sg_copy_from_buffer(dd->real_dst, sg_nents(dd->real_dst),
+				 dd->buf, dd->total))
+		err = -EINVAL;
+
+	if (err)
+		return atmel_aes_complete(dd, err);
+
+	return dd->cpu_transfer_complete(dd);
+}
+
+static int atmel_aes_cpu_start(struct atmel_aes_dev *dd,
+			       struct scatterlist *src,
+			       struct scatterlist *dst,
+			       size_t len,
+			       atmel_aes_fn_t resume)
+{
+	size_t padlen = atmel_aes_padlen(len, AES_BLOCK_SIZE);
+
+	if (unlikely(len == 0))
+		return -EINVAL;
+
+	sg_copy_to_buffer(src, sg_nents(src), dd->buf, len);
+
+	dd->total = len;
+	dd->real_dst = dst;
+	dd->cpu_transfer_complete = resume;
+	dd->datalen = len + padlen;
+	dd->data = (u32 *)dd->buf;
+	atmel_aes_write_block(dd, AES_IDATAR(0), dd->data);
+	return atmel_aes_wait_for_data_ready(dd, atmel_aes_cpu_transfer);
+}
+
+
+/* DMA transfer */
+
+static void atmel_aes_dma_callback(void *data);
+
+static bool atmel_aes_check_aligned(struct atmel_aes_dev *dd,
+				    struct scatterlist *sg,
+				    size_t len,
+				    struct atmel_aes_dma *dma)
+{
+	int nents;
+
+	if (!IS_ALIGNED(len, dd->ctx->block_size))
+		return false;
+
+	for (nents = 0; sg; sg = sg_next(sg), ++nents) {
+		if (!IS_ALIGNED(sg->offset, sizeof(u32)))
+			return false;
+
+		if (len <= sg->length) {
+			if (!IS_ALIGNED(len, dd->ctx->block_size))
+				return false;
+
+			dma->nents = nents+1;
+			dma->remainder = sg->length - len;
+			sg->length = len;
+			return true;
+		}
+
+		if (!IS_ALIGNED(sg->length, dd->ctx->block_size))
+			return false;
+
+		len -= sg->length;
+	}
+
+	return false;
+}
+
+static inline void atmel_aes_restore_sg(const struct atmel_aes_dma *dma)
+{
+	struct scatterlist *sg = dma->sg;
+	int nents = dma->nents;
+
+	if (!dma->remainder)
+		return;
+
+	while (--nents > 0 && sg)
+		sg = sg_next(sg);
+
+	if (!sg)
+		return;
+
+	sg->length += dma->remainder;
+}
+
+static int atmel_aes_map(struct atmel_aes_dev *dd,
+			 struct scatterlist *src,
+			 struct scatterlist *dst,
+			 size_t len)
+{
+	bool src_aligned, dst_aligned;
+	size_t padlen;
+
+	dd->total = len;
+	dd->src.sg = src;
+	dd->dst.sg = dst;
+	dd->real_dst = dst;
+
+	src_aligned = atmel_aes_check_aligned(dd, src, len, &dd->src);
+	if (src == dst)
+		dst_aligned = src_aligned;
+	else
+		dst_aligned = atmel_aes_check_aligned(dd, dst, len, &dd->dst);
+	if (!src_aligned || !dst_aligned) {
+		padlen = atmel_aes_padlen(len, dd->ctx->block_size);
+
+		if (dd->buflen < len + padlen)
+			return -ENOMEM;
+
+		if (!src_aligned) {
+			sg_copy_to_buffer(src, sg_nents(src), dd->buf, len);
+			dd->src.sg = &dd->aligned_sg;
+			dd->src.nents = 1;
+			dd->src.remainder = 0;
+		}
+
+		if (!dst_aligned) {
+			dd->dst.sg = &dd->aligned_sg;
+			dd->dst.nents = 1;
+			dd->dst.remainder = 0;
+		}
+
+		sg_init_table(&dd->aligned_sg, 1);
+		sg_set_buf(&dd->aligned_sg, dd->buf, len + padlen);
+	}
+
+	if (dd->src.sg == dd->dst.sg) {
+		dd->src.sg_len = dma_map_sg(dd->dev, dd->src.sg, dd->src.nents,
+					    DMA_BIDIRECTIONAL);
+		dd->dst.sg_len = dd->src.sg_len;
+		if (!dd->src.sg_len)
+			return -EFAULT;
+	} else {
+		dd->src.sg_len = dma_map_sg(dd->dev, dd->src.sg, dd->src.nents,
+					    DMA_TO_DEVICE);
+		if (!dd->src.sg_len)
+			return -EFAULT;
+
+		dd->dst.sg_len = dma_map_sg(dd->dev, dd->dst.sg, dd->dst.nents,
+					    DMA_FROM_DEVICE);
+		if (!dd->dst.sg_len) {
+			dma_unmap_sg(dd->dev, dd->src.sg, dd->src.nents,
+				     DMA_TO_DEVICE);
+			return -EFAULT;
+		}
 	}
 
 	return 0;
 }
 
-static int atmel_aes_handle_queue(struct atmel_aes_dev *dd,
-			       struct ablkcipher_request *req)
+static void atmel_aes_unmap(struct atmel_aes_dev *dd)
 {
-	struct crypto_async_request *async_req, *backlog;
-	struct atmel_aes_ctx *ctx;
-	struct atmel_aes_reqctx *rctx;
+	if (dd->src.sg == dd->dst.sg) {
+		dma_unmap_sg(dd->dev, dd->src.sg, dd->src.nents,
+			     DMA_BIDIRECTIONAL);
+
+		if (dd->src.sg != &dd->aligned_sg)
+			atmel_aes_restore_sg(&dd->src);
+	} else {
+		dma_unmap_sg(dd->dev, dd->dst.sg, dd->dst.nents,
+			     DMA_FROM_DEVICE);
+
+		if (dd->dst.sg != &dd->aligned_sg)
+			atmel_aes_restore_sg(&dd->dst);
+
+		dma_unmap_sg(dd->dev, dd->src.sg, dd->src.nents,
+			     DMA_TO_DEVICE);
+
+		if (dd->src.sg != &dd->aligned_sg)
+			atmel_aes_restore_sg(&dd->src);
+	}
+
+	if (dd->dst.sg == &dd->aligned_sg)
+		sg_copy_from_buffer(dd->real_dst, sg_nents(dd->real_dst),
+				    dd->buf, dd->total);
+}
+
+static int atmel_aes_dma_transfer_start(struct atmel_aes_dev *dd,
+					enum dma_slave_buswidth addr_width,
+					enum dma_transfer_direction dir,
+					u32 maxburst)
+{
+	struct dma_async_tx_descriptor *desc;
+	struct dma_slave_config config;
+	dma_async_tx_callback callback;
+	struct atmel_aes_dma *dma;
+	int err;
+
+	memset(&config, 0, sizeof(config));
+	config.direction = dir;
+	config.src_addr_width = addr_width;
+	config.dst_addr_width = addr_width;
+	config.src_maxburst = maxburst;
+	config.dst_maxburst = maxburst;
+
+	switch (dir) {
+	case DMA_MEM_TO_DEV:
+		dma = &dd->src;
+		callback = NULL;
+		config.dst_addr = dd->phys_base + AES_IDATAR(0);
+		break;
+
+	case DMA_DEV_TO_MEM:
+		dma = &dd->dst;
+		callback = atmel_aes_dma_callback;
+		config.src_addr = dd->phys_base + AES_ODATAR(0);
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	err = dmaengine_slave_config(dma->chan, &config);
+	if (err)
+		return err;
+
+	desc = dmaengine_prep_slave_sg(dma->chan, dma->sg, dma->sg_len, dir,
+				       DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+	if (!desc)
+		return -ENOMEM;
+
+	desc->callback = callback;
+	desc->callback_param = dd;
+	dmaengine_submit(desc);
+	dma_async_issue_pending(dma->chan);
+
+	return 0;
+}
+
+static void atmel_aes_dma_transfer_stop(struct atmel_aes_dev *dd,
+					enum dma_transfer_direction dir)
+{
+	struct atmel_aes_dma *dma;
+
+	switch (dir) {
+	case DMA_MEM_TO_DEV:
+		dma = &dd->src;
+		break;
+
+	case DMA_DEV_TO_MEM:
+		dma = &dd->dst;
+		break;
+
+	default:
+		return;
+	}
+
+	dmaengine_terminate_all(dma->chan);
+}
+
+static int atmel_aes_dma_start(struct atmel_aes_dev *dd,
+			       struct scatterlist *src,
+			       struct scatterlist *dst,
+			       size_t len,
+			       atmel_aes_fn_t resume)
+{
+	enum dma_slave_buswidth addr_width;
+	u32 maxburst;
+	int err;
+
+	switch (dd->ctx->block_size) {
+	case CFB8_BLOCK_SIZE:
+		addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE;
+		maxburst = 1;
+		break;
+
+	case CFB16_BLOCK_SIZE:
+		addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
+		maxburst = 1;
+		break;
+
+	case CFB32_BLOCK_SIZE:
+	case CFB64_BLOCK_SIZE:
+		addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+		maxburst = 1;
+		break;
+
+	case AES_BLOCK_SIZE:
+		addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+		maxburst = dd->caps.max_burst_size;
+		break;
+
+	default:
+		err = -EINVAL;
+		goto exit;
+	}
+
+	err = atmel_aes_map(dd, src, dst, len);
+	if (err)
+		goto exit;
+
+	dd->resume = resume;
+
+	/* Set output DMA transfer first */
+	err = atmel_aes_dma_transfer_start(dd, addr_width, DMA_DEV_TO_MEM,
+					   maxburst);
+	if (err)
+		goto unmap;
+
+	/* Then set input DMA transfer */
+	err = atmel_aes_dma_transfer_start(dd, addr_width, DMA_MEM_TO_DEV,
+					   maxburst);
+	if (err)
+		goto output_transfer_stop;
+
+	return -EINPROGRESS;
+
+output_transfer_stop:
+	atmel_aes_dma_transfer_stop(dd, DMA_DEV_TO_MEM);
+unmap:
+	atmel_aes_unmap(dd);
+exit:
+	return atmel_aes_complete(dd, err);
+}
+
+static void atmel_aes_dma_stop(struct atmel_aes_dev *dd)
+{
+	atmel_aes_dma_transfer_stop(dd, DMA_MEM_TO_DEV);
+	atmel_aes_dma_transfer_stop(dd, DMA_DEV_TO_MEM);
+	atmel_aes_unmap(dd);
+}
+
+static void atmel_aes_dma_callback(void *data)
+{
+	struct atmel_aes_dev *dd = data;
+
+	atmel_aes_dma_stop(dd);
+	dd->is_async = true;
+	(void)dd->resume(dd);
+}
+
+static int atmel_aes_handle_queue(struct atmel_aes_dev *dd,
+				  struct crypto_async_request *new_areq)
+{
+	struct crypto_async_request *areq, *backlog;
+	struct atmel_aes_base_ctx *ctx;
 	unsigned long flags;
 	int err, ret = 0;
 
 	spin_lock_irqsave(&dd->lock, flags);
-	if (req)
-		ret = ablkcipher_enqueue_request(&dd->queue, req);
+	if (new_areq)
+		ret = crypto_enqueue_request(&dd->queue, new_areq);
 	if (dd->flags & AES_FLAGS_BUSY) {
 		spin_unlock_irqrestore(&dd->lock, flags);
 		return ret;
 	}
 	backlog = crypto_get_backlog(&dd->queue);
-	async_req = crypto_dequeue_request(&dd->queue);
-	if (async_req)
+	areq = crypto_dequeue_request(&dd->queue);
+	if (areq)
 		dd->flags |= AES_FLAGS_BUSY;
 	spin_unlock_irqrestore(&dd->lock, flags);
 
-	if (!async_req)
+	if (!areq)
 		return ret;
 
 	if (backlog)
 		backlog->complete(backlog, -EINPROGRESS);
 
-	req = ablkcipher_request_cast(async_req);
+	ctx = crypto_tfm_ctx(areq->tfm);
 
-	/* assign new request to device */
-	dd->req = req;
-	dd->total = req->nbytes;
-	dd->in_offset = 0;
-	dd->in_sg = req->src;
-	dd->out_offset = 0;
-	dd->out_sg = req->dst;
-
-	rctx = ablkcipher_request_ctx(req);
-	ctx = crypto_ablkcipher_ctx(crypto_ablkcipher_reqtfm(req));
-	rctx->mode &= AES_FLAGS_MODE_MASK;
-	dd->flags = (dd->flags & ~AES_FLAGS_MODE_MASK) | rctx->mode;
+	dd->areq = areq;
 	dd->ctx = ctx;
-	ctx->dd = dd;
+	dd->is_async = (areq != new_areq);
 
-	err = atmel_aes_write_ctrl(dd);
-	if (!err) {
-		if (dd->total > ATMEL_AES_DMA_THRESHOLD)
-			err = atmel_aes_crypt_dma_start(dd);
-		else
-			err = atmel_aes_crypt_cpu_start(dd);
-	}
-	if (err) {
-		/* aes_task will not finish it, so do it here */
-		atmel_aes_finish_req(dd, err);
-		tasklet_schedule(&dd->queue_task);
-	}
-
-	return ret;
+	err = ctx->start(dd);
+	return (dd->is_async) ? ret : err;
 }
 
-static int atmel_aes_crypt_dma_stop(struct atmel_aes_dev *dd)
+
+/* AES async block ciphers */
+
+static int atmel_aes_transfer_complete(struct atmel_aes_dev *dd)
 {
-	int err = -EINVAL;
-	size_t count;
+	return atmel_aes_complete(dd, 0);
+}
 
-	if (dd->flags & AES_FLAGS_DMA) {
-		err = 0;
-		if  (dd->flags & AES_FLAGS_FAST) {
-			dma_unmap_sg(dd->dev, dd->out_sg, 1, DMA_FROM_DEVICE);
-			dma_unmap_sg(dd->dev, dd->in_sg, 1, DMA_TO_DEVICE);
-		} else {
-			dma_sync_single_for_cpu(dd->dev, dd->dma_addr_out,
-				dd->dma_size, DMA_FROM_DEVICE);
+static int atmel_aes_start(struct atmel_aes_dev *dd)
+{
+	struct ablkcipher_request *req = ablkcipher_request_cast(dd->areq);
+	struct atmel_aes_reqctx *rctx = ablkcipher_request_ctx(req);
+	bool use_dma = (req->nbytes >= ATMEL_AES_DMA_THRESHOLD ||
+			dd->ctx->block_size != AES_BLOCK_SIZE);
+	int err;
 
-			/* copy data */
-			count = atmel_aes_sg_copy(&dd->out_sg, &dd->out_offset,
-				dd->buf_out, dd->buflen, dd->dma_size, 1);
-			if (count != dd->dma_size) {
-				err = -EINVAL;
-				pr_err("not all data converted: %u\n", count);
-			}
+	atmel_aes_set_mode(dd, rctx);
+
+	err = atmel_aes_hw_init(dd);
+	if (err)
+		return atmel_aes_complete(dd, err);
+
+	atmel_aes_write_ctrl(dd, use_dma, req->info);
+	if (use_dma)
+		return atmel_aes_dma_start(dd, req->src, req->dst, req->nbytes,
+					   atmel_aes_transfer_complete);
+
+	return atmel_aes_cpu_start(dd, req->src, req->dst, req->nbytes,
+				   atmel_aes_transfer_complete);
+}
+
+static inline struct atmel_aes_ctr_ctx *
+atmel_aes_ctr_ctx_cast(struct atmel_aes_base_ctx *ctx)
+{
+	return container_of(ctx, struct atmel_aes_ctr_ctx, base);
+}
+
+static int atmel_aes_ctr_transfer(struct atmel_aes_dev *dd)
+{
+	struct atmel_aes_ctr_ctx *ctx = atmel_aes_ctr_ctx_cast(dd->ctx);
+	struct ablkcipher_request *req = ablkcipher_request_cast(dd->areq);
+	struct scatterlist *src, *dst;
+	u32 ctr, blocks;
+	size_t datalen;
+	bool use_dma, fragmented = false;
+
+	/* Check for transfer completion. */
+	ctx->offset += dd->total;
+	if (ctx->offset >= req->nbytes)
+		return atmel_aes_transfer_complete(dd);
+
+	/* Compute data length. */
+	datalen = req->nbytes - ctx->offset;
+	blocks = DIV_ROUND_UP(datalen, AES_BLOCK_SIZE);
+	ctr = be32_to_cpu(ctx->iv[3]);
+	if (dd->caps.has_ctr32) {
+		/* Check 32bit counter overflow. */
+		u32 start = ctr;
+		u32 end = start + blocks - 1;
+
+		if (end < start) {
+			ctr |= 0xffffffff;
+			datalen = AES_BLOCK_SIZE * -start;
+			fragmented = true;
+		}
+	} else {
+		/* Check 16bit counter overflow. */
+		u16 start = ctr & 0xffff;
+		u16 end = start + (u16)blocks - 1;
+
+		if (blocks >> 16 || end < start) {
+			ctr |= 0xffff;
+			datalen = AES_BLOCK_SIZE * (0x10000-start);
+			fragmented = true;
 		}
 	}
+	use_dma = (datalen >= ATMEL_AES_DMA_THRESHOLD);
 
-	return err;
+	/* Jump to offset. */
+	src = scatterwalk_ffwd(ctx->src, req->src, ctx->offset);
+	dst = ((req->src == req->dst) ? src :
+	       scatterwalk_ffwd(ctx->dst, req->dst, ctx->offset));
+
+	/* Configure hardware. */
+	atmel_aes_write_ctrl(dd, use_dma, ctx->iv);
+	if (unlikely(fragmented)) {
+		/*
+		 * Increment the counter manually to cope with the hardware
+		 * counter overflow.
+		 */
+		ctx->iv[3] = cpu_to_be32(ctr);
+		crypto_inc((u8 *)ctx->iv, AES_BLOCK_SIZE);
+	}
+
+	if (use_dma)
+		return atmel_aes_dma_start(dd, src, dst, datalen,
+					   atmel_aes_ctr_transfer);
+
+	return atmel_aes_cpu_start(dd, src, dst, datalen,
+				   atmel_aes_ctr_transfer);
 }
 
-
-static int atmel_aes_buff_init(struct atmel_aes_dev *dd)
+static int atmel_aes_ctr_start(struct atmel_aes_dev *dd)
 {
-	int err = -ENOMEM;
+	struct atmel_aes_ctr_ctx *ctx = atmel_aes_ctr_ctx_cast(dd->ctx);
+	struct ablkcipher_request *req = ablkcipher_request_cast(dd->areq);
+	struct atmel_aes_reqctx *rctx = ablkcipher_request_ctx(req);
+	int err;
 
-	dd->buf_in = (void *)__get_free_pages(GFP_KERNEL, 0);
-	dd->buf_out = (void *)__get_free_pages(GFP_KERNEL, 0);
-	dd->buflen = PAGE_SIZE;
-	dd->buflen &= ~(AES_BLOCK_SIZE - 1);
+	atmel_aes_set_mode(dd, rctx);
 
-	if (!dd->buf_in || !dd->buf_out) {
-		dev_err(dd->dev, "unable to alloc pages.\n");
-		goto err_alloc;
-	}
-
-	/* MAP here */
-	dd->dma_addr_in = dma_map_single(dd->dev, dd->buf_in,
-					dd->buflen, DMA_TO_DEVICE);
-	if (dma_mapping_error(dd->dev, dd->dma_addr_in)) {
-		dev_err(dd->dev, "dma %d bytes error\n", dd->buflen);
-		err = -EINVAL;
-		goto err_map_in;
-	}
-
-	dd->dma_addr_out = dma_map_single(dd->dev, dd->buf_out,
-					dd->buflen, DMA_FROM_DEVICE);
-	if (dma_mapping_error(dd->dev, dd->dma_addr_out)) {
-		dev_err(dd->dev, "dma %d bytes error\n", dd->buflen);
-		err = -EINVAL;
-		goto err_map_out;
-	}
-
-	return 0;
-
-err_map_out:
-	dma_unmap_single(dd->dev, dd->dma_addr_in, dd->buflen,
-		DMA_TO_DEVICE);
-err_map_in:
-err_alloc:
-	free_page((unsigned long)dd->buf_out);
-	free_page((unsigned long)dd->buf_in);
+	err = atmel_aes_hw_init(dd);
 	if (err)
-		pr_err("error: %d\n", err);
-	return err;
-}
+		return atmel_aes_complete(dd, err);
 
-static void atmel_aes_buff_cleanup(struct atmel_aes_dev *dd)
-{
-	dma_unmap_single(dd->dev, dd->dma_addr_out, dd->buflen,
-			 DMA_FROM_DEVICE);
-	dma_unmap_single(dd->dev, dd->dma_addr_in, dd->buflen,
-		DMA_TO_DEVICE);
-	free_page((unsigned long)dd->buf_out);
-	free_page((unsigned long)dd->buf_in);
+	memcpy(ctx->iv, req->info, AES_BLOCK_SIZE);
+	ctx->offset = 0;
+	dd->total = 0;
+	return atmel_aes_ctr_transfer(dd);
 }
 
 static int atmel_aes_crypt(struct ablkcipher_request *req, unsigned long mode)
 {
-	struct atmel_aes_ctx *ctx = crypto_ablkcipher_ctx(
-			crypto_ablkcipher_reqtfm(req));
-	struct atmel_aes_reqctx *rctx = ablkcipher_request_ctx(req);
+	struct atmel_aes_base_ctx *ctx;
+	struct atmel_aes_reqctx *rctx;
 	struct atmel_aes_dev *dd;
 
-	if (mode & AES_FLAGS_CFB8) {
-		if (!IS_ALIGNED(req->nbytes, CFB8_BLOCK_SIZE)) {
-			pr_err("request size is not exact amount of CFB8 blocks\n");
-			return -EINVAL;
-		}
+	ctx = crypto_ablkcipher_ctx(crypto_ablkcipher_reqtfm(req));
+	switch (mode & AES_FLAGS_OPMODE_MASK) {
+	case AES_FLAGS_CFB8:
 		ctx->block_size = CFB8_BLOCK_SIZE;
-	} else if (mode & AES_FLAGS_CFB16) {
-		if (!IS_ALIGNED(req->nbytes, CFB16_BLOCK_SIZE)) {
-			pr_err("request size is not exact amount of CFB16 blocks\n");
-			return -EINVAL;
-		}
+		break;
+
+	case AES_FLAGS_CFB16:
 		ctx->block_size = CFB16_BLOCK_SIZE;
-	} else if (mode & AES_FLAGS_CFB32) {
-		if (!IS_ALIGNED(req->nbytes, CFB32_BLOCK_SIZE)) {
-			pr_err("request size is not exact amount of CFB32 blocks\n");
-			return -EINVAL;
-		}
+		break;
+
+	case AES_FLAGS_CFB32:
 		ctx->block_size = CFB32_BLOCK_SIZE;
-	} else if (mode & AES_FLAGS_CFB64) {
-		if (!IS_ALIGNED(req->nbytes, CFB64_BLOCK_SIZE)) {
-			pr_err("request size is not exact amount of CFB64 blocks\n");
-			return -EINVAL;
-		}
+		break;
+
+	case AES_FLAGS_CFB64:
 		ctx->block_size = CFB64_BLOCK_SIZE;
-	} else {
-		if (!IS_ALIGNED(req->nbytes, AES_BLOCK_SIZE)) {
-			pr_err("request size is not exact amount of AES blocks\n");
-			return -EINVAL;
-		}
+		break;
+
+	default:
 		ctx->block_size = AES_BLOCK_SIZE;
+		break;
 	}
 
 	dd = atmel_aes_find_dev(ctx);
 	if (!dd)
 		return -ENODEV;
 
+	rctx = ablkcipher_request_ctx(req);
 	rctx->mode = mode;
 
-	return atmel_aes_handle_queue(dd, req);
-}
-
-static bool atmel_aes_filter(struct dma_chan *chan, void *slave)
-{
-	struct at_dma_slave	*sl = slave;
-
-	if (sl && sl->dma_dev == chan->device->dev) {
-		chan->private = sl;
-		return true;
-	} else {
-		return false;
-	}
-}
-
-static int atmel_aes_dma_init(struct atmel_aes_dev *dd,
-	struct crypto_platform_data *pdata)
-{
-	int err = -ENOMEM;
-	dma_cap_mask_t mask;
-
-	dma_cap_zero(mask);
-	dma_cap_set(DMA_SLAVE, mask);
-
-	/* Try to grab 2 DMA channels */
-	dd->dma_lch_in.chan = dma_request_slave_channel_compat(mask,
-			atmel_aes_filter, &pdata->dma_slave->rxdata, dd->dev, "tx");
-	if (!dd->dma_lch_in.chan)
-		goto err_dma_in;
-
-	dd->dma_lch_in.dma_conf.direction = DMA_MEM_TO_DEV;
-	dd->dma_lch_in.dma_conf.dst_addr = dd->phys_base +
-		AES_IDATAR(0);
-	dd->dma_lch_in.dma_conf.src_maxburst = dd->caps.max_burst_size;
-	dd->dma_lch_in.dma_conf.src_addr_width =
-		DMA_SLAVE_BUSWIDTH_4_BYTES;
-	dd->dma_lch_in.dma_conf.dst_maxburst = dd->caps.max_burst_size;
-	dd->dma_lch_in.dma_conf.dst_addr_width =
-		DMA_SLAVE_BUSWIDTH_4_BYTES;
-	dd->dma_lch_in.dma_conf.device_fc = false;
-
-	dd->dma_lch_out.chan = dma_request_slave_channel_compat(mask,
-			atmel_aes_filter, &pdata->dma_slave->txdata, dd->dev, "rx");
-	if (!dd->dma_lch_out.chan)
-		goto err_dma_out;
-
-	dd->dma_lch_out.dma_conf.direction = DMA_DEV_TO_MEM;
-	dd->dma_lch_out.dma_conf.src_addr = dd->phys_base +
-		AES_ODATAR(0);
-	dd->dma_lch_out.dma_conf.src_maxburst = dd->caps.max_burst_size;
-	dd->dma_lch_out.dma_conf.src_addr_width =
-		DMA_SLAVE_BUSWIDTH_4_BYTES;
-	dd->dma_lch_out.dma_conf.dst_maxburst = dd->caps.max_burst_size;
-	dd->dma_lch_out.dma_conf.dst_addr_width =
-		DMA_SLAVE_BUSWIDTH_4_BYTES;
-	dd->dma_lch_out.dma_conf.device_fc = false;
-
-	return 0;
-
-err_dma_out:
-	dma_release_channel(dd->dma_lch_in.chan);
-err_dma_in:
-	dev_warn(dd->dev, "no DMA channel available\n");
-	return err;
-}
-
-static void atmel_aes_dma_cleanup(struct atmel_aes_dev *dd)
-{
-	dma_release_channel(dd->dma_lch_in.chan);
-	dma_release_channel(dd->dma_lch_out.chan);
+	return atmel_aes_handle_queue(dd, &req->base);
 }
 
 static int atmel_aes_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
 			   unsigned int keylen)
 {
-	struct atmel_aes_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	struct atmel_aes_base_ctx *ctx = crypto_ablkcipher_ctx(tfm);
 
-	if (keylen != AES_KEYSIZE_128 && keylen != AES_KEYSIZE_192 &&
-		   keylen != AES_KEYSIZE_256) {
+	if (keylen != AES_KEYSIZE_128 &&
+	    keylen != AES_KEYSIZE_192 &&
+	    keylen != AES_KEYSIZE_256) {
 		crypto_ablkcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
 		return -EINVAL;
 	}
@@ -839,115 +1066,110 @@
 
 static int atmel_aes_ecb_encrypt(struct ablkcipher_request *req)
 {
-	return atmel_aes_crypt(req,
-		AES_FLAGS_ENCRYPT);
+	return atmel_aes_crypt(req, AES_FLAGS_ECB | AES_FLAGS_ENCRYPT);
 }
 
 static int atmel_aes_ecb_decrypt(struct ablkcipher_request *req)
 {
-	return atmel_aes_crypt(req,
-		0);
+	return atmel_aes_crypt(req, AES_FLAGS_ECB);
 }
 
 static int atmel_aes_cbc_encrypt(struct ablkcipher_request *req)
 {
-	return atmel_aes_crypt(req,
-		AES_FLAGS_ENCRYPT | AES_FLAGS_CBC);
+	return atmel_aes_crypt(req, AES_FLAGS_CBC | AES_FLAGS_ENCRYPT);
 }
 
 static int atmel_aes_cbc_decrypt(struct ablkcipher_request *req)
 {
-	return atmel_aes_crypt(req,
-		AES_FLAGS_CBC);
+	return atmel_aes_crypt(req, AES_FLAGS_CBC);
 }
 
 static int atmel_aes_ofb_encrypt(struct ablkcipher_request *req)
 {
-	return atmel_aes_crypt(req,
-		AES_FLAGS_ENCRYPT | AES_FLAGS_OFB);
+	return atmel_aes_crypt(req, AES_FLAGS_OFB | AES_FLAGS_ENCRYPT);
 }
 
 static int atmel_aes_ofb_decrypt(struct ablkcipher_request *req)
 {
-	return atmel_aes_crypt(req,
-		AES_FLAGS_OFB);
+	return atmel_aes_crypt(req, AES_FLAGS_OFB);
 }
 
 static int atmel_aes_cfb_encrypt(struct ablkcipher_request *req)
 {
-	return atmel_aes_crypt(req,
-		AES_FLAGS_ENCRYPT | AES_FLAGS_CFB | AES_FLAGS_CFB128);
+	return atmel_aes_crypt(req, AES_FLAGS_CFB128 | AES_FLAGS_ENCRYPT);
 }
 
 static int atmel_aes_cfb_decrypt(struct ablkcipher_request *req)
 {
-	return atmel_aes_crypt(req,
-		AES_FLAGS_CFB | AES_FLAGS_CFB128);
+	return atmel_aes_crypt(req, AES_FLAGS_CFB128);
 }
 
 static int atmel_aes_cfb64_encrypt(struct ablkcipher_request *req)
 {
-	return atmel_aes_crypt(req,
-		AES_FLAGS_ENCRYPT | AES_FLAGS_CFB | AES_FLAGS_CFB64);
+	return atmel_aes_crypt(req, AES_FLAGS_CFB64 | AES_FLAGS_ENCRYPT);
 }
 
 static int atmel_aes_cfb64_decrypt(struct ablkcipher_request *req)
 {
-	return atmel_aes_crypt(req,
-		AES_FLAGS_CFB | AES_FLAGS_CFB64);
+	return atmel_aes_crypt(req, AES_FLAGS_CFB64);
 }
 
 static int atmel_aes_cfb32_encrypt(struct ablkcipher_request *req)
 {
-	return atmel_aes_crypt(req,
-		AES_FLAGS_ENCRYPT | AES_FLAGS_CFB | AES_FLAGS_CFB32);
+	return atmel_aes_crypt(req, AES_FLAGS_CFB32 | AES_FLAGS_ENCRYPT);
 }
 
 static int atmel_aes_cfb32_decrypt(struct ablkcipher_request *req)
 {
-	return atmel_aes_crypt(req,
-		AES_FLAGS_CFB | AES_FLAGS_CFB32);
+	return atmel_aes_crypt(req, AES_FLAGS_CFB32);
 }
 
 static int atmel_aes_cfb16_encrypt(struct ablkcipher_request *req)
 {
-	return atmel_aes_crypt(req,
-		AES_FLAGS_ENCRYPT | AES_FLAGS_CFB | AES_FLAGS_CFB16);
+	return atmel_aes_crypt(req, AES_FLAGS_CFB16 | AES_FLAGS_ENCRYPT);
 }
 
 static int atmel_aes_cfb16_decrypt(struct ablkcipher_request *req)
 {
-	return atmel_aes_crypt(req,
-		AES_FLAGS_CFB | AES_FLAGS_CFB16);
+	return atmel_aes_crypt(req, AES_FLAGS_CFB16);
 }
 
 static int atmel_aes_cfb8_encrypt(struct ablkcipher_request *req)
 {
-	return atmel_aes_crypt(req,
-		AES_FLAGS_ENCRYPT |	AES_FLAGS_CFB | AES_FLAGS_CFB8);
+	return atmel_aes_crypt(req, AES_FLAGS_CFB8 | AES_FLAGS_ENCRYPT);
 }
 
 static int atmel_aes_cfb8_decrypt(struct ablkcipher_request *req)
 {
-	return atmel_aes_crypt(req,
-		AES_FLAGS_CFB | AES_FLAGS_CFB8);
+	return atmel_aes_crypt(req, AES_FLAGS_CFB8);
 }
 
 static int atmel_aes_ctr_encrypt(struct ablkcipher_request *req)
 {
-	return atmel_aes_crypt(req,
-		AES_FLAGS_ENCRYPT | AES_FLAGS_CTR);
+	return atmel_aes_crypt(req, AES_FLAGS_CTR | AES_FLAGS_ENCRYPT);
 }
 
 static int atmel_aes_ctr_decrypt(struct ablkcipher_request *req)
 {
-	return atmel_aes_crypt(req,
-		AES_FLAGS_CTR);
+	return atmel_aes_crypt(req, AES_FLAGS_CTR);
 }
 
 static int atmel_aes_cra_init(struct crypto_tfm *tfm)
 {
+	struct atmel_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+
 	tfm->crt_ablkcipher.reqsize = sizeof(struct atmel_aes_reqctx);
+	ctx->base.start = atmel_aes_start;
+
+	return 0;
+}
+
+static int atmel_aes_ctr_cra_init(struct crypto_tfm *tfm)
+{
+	struct atmel_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	tfm->crt_ablkcipher.reqsize = sizeof(struct atmel_aes_reqctx);
+	ctx->base.start = atmel_aes_ctr_start;
 
 	return 0;
 }
@@ -960,7 +1182,7 @@
 {
 	.cra_name		= "ecb(aes)",
 	.cra_driver_name	= "atmel-ecb-aes",
-	.cra_priority		= 100,
+	.cra_priority		= ATMEL_AES_PRIORITY,
 	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
 	.cra_blocksize		= AES_BLOCK_SIZE,
 	.cra_ctxsize		= sizeof(struct atmel_aes_ctx),
@@ -980,7 +1202,7 @@
 {
 	.cra_name		= "cbc(aes)",
 	.cra_driver_name	= "atmel-cbc-aes",
-	.cra_priority		= 100,
+	.cra_priority		= ATMEL_AES_PRIORITY,
 	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
 	.cra_blocksize		= AES_BLOCK_SIZE,
 	.cra_ctxsize		= sizeof(struct atmel_aes_ctx),
@@ -1001,7 +1223,7 @@
 {
 	.cra_name		= "ofb(aes)",
 	.cra_driver_name	= "atmel-ofb-aes",
-	.cra_priority		= 100,
+	.cra_priority		= ATMEL_AES_PRIORITY,
 	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
 	.cra_blocksize		= AES_BLOCK_SIZE,
 	.cra_ctxsize		= sizeof(struct atmel_aes_ctx),
@@ -1022,7 +1244,7 @@
 {
 	.cra_name		= "cfb(aes)",
 	.cra_driver_name	= "atmel-cfb-aes",
-	.cra_priority		= 100,
+	.cra_priority		= ATMEL_AES_PRIORITY,
 	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
 	.cra_blocksize		= AES_BLOCK_SIZE,
 	.cra_ctxsize		= sizeof(struct atmel_aes_ctx),
@@ -1043,7 +1265,7 @@
 {
 	.cra_name		= "cfb32(aes)",
 	.cra_driver_name	= "atmel-cfb32-aes",
-	.cra_priority		= 100,
+	.cra_priority		= ATMEL_AES_PRIORITY,
 	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
 	.cra_blocksize		= CFB32_BLOCK_SIZE,
 	.cra_ctxsize		= sizeof(struct atmel_aes_ctx),
@@ -1064,7 +1286,7 @@
 {
 	.cra_name		= "cfb16(aes)",
 	.cra_driver_name	= "atmel-cfb16-aes",
-	.cra_priority		= 100,
+	.cra_priority		= ATMEL_AES_PRIORITY,
 	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
 	.cra_blocksize		= CFB16_BLOCK_SIZE,
 	.cra_ctxsize		= sizeof(struct atmel_aes_ctx),
@@ -1085,7 +1307,7 @@
 {
 	.cra_name		= "cfb8(aes)",
 	.cra_driver_name	= "atmel-cfb8-aes",
-	.cra_priority		= 100,
+	.cra_priority		= ATMEL_AES_PRIORITY,
 	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
 	.cra_blocksize		= CFB8_BLOCK_SIZE,
 	.cra_ctxsize		= sizeof(struct atmel_aes_ctx),
@@ -1106,14 +1328,14 @@
 {
 	.cra_name		= "ctr(aes)",
 	.cra_driver_name	= "atmel-ctr-aes",
-	.cra_priority		= 100,
+	.cra_priority		= ATMEL_AES_PRIORITY,
 	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= AES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct atmel_aes_ctx),
+	.cra_blocksize		= 1,
+	.cra_ctxsize		= sizeof(struct atmel_aes_ctr_ctx),
 	.cra_alignmask		= 0xf,
 	.cra_type		= &crypto_ablkcipher_type,
 	.cra_module		= THIS_MODULE,
-	.cra_init		= atmel_aes_cra_init,
+	.cra_init		= atmel_aes_ctr_cra_init,
 	.cra_exit		= atmel_aes_cra_exit,
 	.cra_u.ablkcipher = {
 		.min_keysize	= AES_MIN_KEY_SIZE,
@@ -1129,7 +1351,7 @@
 static struct crypto_alg aes_cfb64_alg = {
 	.cra_name		= "cfb64(aes)",
 	.cra_driver_name	= "atmel-cfb64-aes",
-	.cra_priority		= 100,
+	.cra_priority		= ATMEL_AES_PRIORITY,
 	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
 	.cra_blocksize		= CFB64_BLOCK_SIZE,
 	.cra_ctxsize		= sizeof(struct atmel_aes_ctx),
@@ -1148,6 +1370,481 @@
 	}
 };
 
+
+/* gcm aead functions */
+
+static int atmel_aes_gcm_ghash(struct atmel_aes_dev *dd,
+			       const u32 *data, size_t datalen,
+			       const u32 *ghash_in, u32 *ghash_out,
+			       atmel_aes_fn_t resume);
+static int atmel_aes_gcm_ghash_init(struct atmel_aes_dev *dd);
+static int atmel_aes_gcm_ghash_finalize(struct atmel_aes_dev *dd);
+
+static int atmel_aes_gcm_start(struct atmel_aes_dev *dd);
+static int atmel_aes_gcm_process(struct atmel_aes_dev *dd);
+static int atmel_aes_gcm_length(struct atmel_aes_dev *dd);
+static int atmel_aes_gcm_data(struct atmel_aes_dev *dd);
+static int atmel_aes_gcm_tag_init(struct atmel_aes_dev *dd);
+static int atmel_aes_gcm_tag(struct atmel_aes_dev *dd);
+static int atmel_aes_gcm_finalize(struct atmel_aes_dev *dd);
+
+static inline struct atmel_aes_gcm_ctx *
+atmel_aes_gcm_ctx_cast(struct atmel_aes_base_ctx *ctx)
+{
+	return container_of(ctx, struct atmel_aes_gcm_ctx, base);
+}
+
+static int atmel_aes_gcm_ghash(struct atmel_aes_dev *dd,
+			       const u32 *data, size_t datalen,
+			       const u32 *ghash_in, u32 *ghash_out,
+			       atmel_aes_fn_t resume)
+{
+	struct atmel_aes_gcm_ctx *ctx = atmel_aes_gcm_ctx_cast(dd->ctx);
+
+	dd->data = (u32 *)data;
+	dd->datalen = datalen;
+	ctx->ghash_in = ghash_in;
+	ctx->ghash_out = ghash_out;
+	ctx->ghash_resume = resume;
+
+	atmel_aes_write_ctrl(dd, false, NULL);
+	return atmel_aes_wait_for_data_ready(dd, atmel_aes_gcm_ghash_init);
+}
+
+static int atmel_aes_gcm_ghash_init(struct atmel_aes_dev *dd)
+{
+	struct atmel_aes_gcm_ctx *ctx = atmel_aes_gcm_ctx_cast(dd->ctx);
+
+	/* Set the data length. */
+	atmel_aes_write(dd, AES_AADLENR, dd->total);
+	atmel_aes_write(dd, AES_CLENR, 0);
+
+	/* If needed, overwrite the GCM Intermediate Hash Word Registers */
+	if (ctx->ghash_in)
+		atmel_aes_write_block(dd, AES_GHASHR(0), ctx->ghash_in);
+
+	return atmel_aes_gcm_ghash_finalize(dd);
+}
+
+static int atmel_aes_gcm_ghash_finalize(struct atmel_aes_dev *dd)
+{
+	struct atmel_aes_gcm_ctx *ctx = atmel_aes_gcm_ctx_cast(dd->ctx);
+	u32 isr;
+
+	/* Write data into the Input Data Registers. */
+	while (dd->datalen > 0) {
+		atmel_aes_write_block(dd, AES_IDATAR(0), dd->data);
+		dd->data += 4;
+		dd->datalen -= AES_BLOCK_SIZE;
+
+		isr = atmel_aes_read(dd, AES_ISR);
+		if (!(isr & AES_INT_DATARDY)) {
+			dd->resume = atmel_aes_gcm_ghash_finalize;
+			atmel_aes_write(dd, AES_IER, AES_INT_DATARDY);
+			return -EINPROGRESS;
+		}
+	}
+
+	/* Read the computed hash from GHASHRx. */
+	atmel_aes_read_block(dd, AES_GHASHR(0), ctx->ghash_out);
+
+	return ctx->ghash_resume(dd);
+}
+
+
+static int atmel_aes_gcm_start(struct atmel_aes_dev *dd)
+{
+	struct atmel_aes_gcm_ctx *ctx = atmel_aes_gcm_ctx_cast(dd->ctx);
+	struct aead_request *req = aead_request_cast(dd->areq);
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct atmel_aes_reqctx *rctx = aead_request_ctx(req);
+	size_t ivsize = crypto_aead_ivsize(tfm);
+	size_t datalen, padlen;
+	const void *iv = req->iv;
+	u8 *data = dd->buf;
+	int err;
+
+	atmel_aes_set_mode(dd, rctx);
+
+	err = atmel_aes_hw_init(dd);
+	if (err)
+		return atmel_aes_complete(dd, err);
+
+	if (likely(ivsize == 12)) {
+		memcpy(ctx->j0, iv, ivsize);
+		ctx->j0[3] = cpu_to_be32(1);
+		return atmel_aes_gcm_process(dd);
+	}
+
+	padlen = atmel_aes_padlen(ivsize, AES_BLOCK_SIZE);
+	datalen = ivsize + padlen + AES_BLOCK_SIZE;
+	if (datalen > dd->buflen)
+		return atmel_aes_complete(dd, -EINVAL);
+
+	memcpy(data, iv, ivsize);
+	memset(data + ivsize, 0, padlen + sizeof(u64));
+	((u64 *)(data + datalen))[-1] = cpu_to_be64(ivsize * 8);
+
+	return atmel_aes_gcm_ghash(dd, (const u32 *)data, datalen,
+				   NULL, ctx->j0, atmel_aes_gcm_process);
+}
+
+static int atmel_aes_gcm_process(struct atmel_aes_dev *dd)
+{
+	struct atmel_aes_gcm_ctx *ctx = atmel_aes_gcm_ctx_cast(dd->ctx);
+	struct aead_request *req = aead_request_cast(dd->areq);
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	bool enc = atmel_aes_is_encrypt(dd);
+	u32 authsize;
+
+	/* Compute text length. */
+	authsize = crypto_aead_authsize(tfm);
+	ctx->textlen = req->cryptlen - (enc ? 0 : authsize);
+
+	/*
+	 * According to tcrypt test suite, the GCM Automatic Tag Generation
+	 * fails when both the message and its associated data are empty.
+	 */
+	if (likely(req->assoclen != 0 || ctx->textlen != 0))
+		dd->flags |= AES_FLAGS_GTAGEN;
+
+	atmel_aes_write_ctrl(dd, false, NULL);
+	return atmel_aes_wait_for_data_ready(dd, atmel_aes_gcm_length);
+}
+
+static int atmel_aes_gcm_length(struct atmel_aes_dev *dd)
+{
+	struct atmel_aes_gcm_ctx *ctx = atmel_aes_gcm_ctx_cast(dd->ctx);
+	struct aead_request *req = aead_request_cast(dd->areq);
+	u32 j0_lsw, *j0 = ctx->j0;
+	size_t padlen;
+
+	/* Write incr32(J0) into IV. */
+	j0_lsw = j0[3];
+	j0[3] = cpu_to_be32(be32_to_cpu(j0[3]) + 1);
+	atmel_aes_write_block(dd, AES_IVR(0), j0);
+	j0[3] = j0_lsw;
+
+	/* Set aad and text lengths. */
+	atmel_aes_write(dd, AES_AADLENR, req->assoclen);
+	atmel_aes_write(dd, AES_CLENR, ctx->textlen);
+
+	/* Check whether AAD are present. */
+	if (unlikely(req->assoclen == 0)) {
+		dd->datalen = 0;
+		return atmel_aes_gcm_data(dd);
+	}
+
+	/* Copy assoc data and add padding. */
+	padlen = atmel_aes_padlen(req->assoclen, AES_BLOCK_SIZE);
+	if (unlikely(req->assoclen + padlen > dd->buflen))
+		return atmel_aes_complete(dd, -EINVAL);
+	sg_copy_to_buffer(req->src, sg_nents(req->src), dd->buf, req->assoclen);
+
+	/* Write assoc data into the Input Data register. */
+	dd->data = (u32 *)dd->buf;
+	dd->datalen = req->assoclen + padlen;
+	return atmel_aes_gcm_data(dd);
+}
+
+static int atmel_aes_gcm_data(struct atmel_aes_dev *dd)
+{
+	struct atmel_aes_gcm_ctx *ctx = atmel_aes_gcm_ctx_cast(dd->ctx);
+	struct aead_request *req = aead_request_cast(dd->areq);
+	bool use_dma = (ctx->textlen >= ATMEL_AES_DMA_THRESHOLD);
+	struct scatterlist *src, *dst;
+	u32 isr, mr;
+
+	/* Write AAD first. */
+	while (dd->datalen > 0) {
+		atmel_aes_write_block(dd, AES_IDATAR(0), dd->data);
+		dd->data += 4;
+		dd->datalen -= AES_BLOCK_SIZE;
+
+		isr = atmel_aes_read(dd, AES_ISR);
+		if (!(isr & AES_INT_DATARDY)) {
+			dd->resume = atmel_aes_gcm_data;
+			atmel_aes_write(dd, AES_IER, AES_INT_DATARDY);
+			return -EINPROGRESS;
+		}
+	}
+
+	/* GMAC only. */
+	if (unlikely(ctx->textlen == 0))
+		return atmel_aes_gcm_tag_init(dd);
+
+	/* Prepare src and dst scatter lists to transfer cipher/plain texts */
+	src = scatterwalk_ffwd(ctx->src, req->src, req->assoclen);
+	dst = ((req->src == req->dst) ? src :
+	       scatterwalk_ffwd(ctx->dst, req->dst, req->assoclen));
+
+	if (use_dma) {
+		/* Update the Mode Register for DMA transfers. */
+		mr = atmel_aes_read(dd, AES_MR);
+		mr &= ~(AES_MR_SMOD_MASK | AES_MR_DUALBUFF);
+		mr |= AES_MR_SMOD_IDATAR0;
+		if (dd->caps.has_dualbuff)
+			mr |= AES_MR_DUALBUFF;
+		atmel_aes_write(dd, AES_MR, mr);
+
+		return atmel_aes_dma_start(dd, src, dst, ctx->textlen,
+					   atmel_aes_gcm_tag_init);
+	}
+
+	return atmel_aes_cpu_start(dd, src, dst, ctx->textlen,
+				   atmel_aes_gcm_tag_init);
+}
+
+static int atmel_aes_gcm_tag_init(struct atmel_aes_dev *dd)
+{
+	struct atmel_aes_gcm_ctx *ctx = atmel_aes_gcm_ctx_cast(dd->ctx);
+	struct aead_request *req = aead_request_cast(dd->areq);
+	u64 *data = dd->buf;
+
+	if (likely(dd->flags & AES_FLAGS_GTAGEN)) {
+		if (!(atmel_aes_read(dd, AES_ISR) & AES_INT_TAGRDY)) {
+			dd->resume = atmel_aes_gcm_tag_init;
+			atmel_aes_write(dd, AES_IER, AES_INT_TAGRDY);
+			return -EINPROGRESS;
+		}
+
+		return atmel_aes_gcm_finalize(dd);
+	}
+
+	/* Read the GCM Intermediate Hash Word Registers. */
+	atmel_aes_read_block(dd, AES_GHASHR(0), ctx->ghash);
+
+	data[0] = cpu_to_be64(req->assoclen * 8);
+	data[1] = cpu_to_be64(ctx->textlen * 8);
+
+	return atmel_aes_gcm_ghash(dd, (const u32 *)data, AES_BLOCK_SIZE,
+				   ctx->ghash, ctx->ghash, atmel_aes_gcm_tag);
+}
+
+static int atmel_aes_gcm_tag(struct atmel_aes_dev *dd)
+{
+	struct atmel_aes_gcm_ctx *ctx = atmel_aes_gcm_ctx_cast(dd->ctx);
+	unsigned long flags;
+
+	/*
+	 * Change mode to CTR to complete the tag generation.
+	 * Use J0 as Initialization Vector.
+	 */
+	flags = dd->flags;
+	dd->flags &= ~(AES_FLAGS_OPMODE_MASK | AES_FLAGS_GTAGEN);
+	dd->flags |= AES_FLAGS_CTR;
+	atmel_aes_write_ctrl(dd, false, ctx->j0);
+	dd->flags = flags;
+
+	atmel_aes_write_block(dd, AES_IDATAR(0), ctx->ghash);
+	return atmel_aes_wait_for_data_ready(dd, atmel_aes_gcm_finalize);
+}
+
+static int atmel_aes_gcm_finalize(struct atmel_aes_dev *dd)
+{
+	struct atmel_aes_gcm_ctx *ctx = atmel_aes_gcm_ctx_cast(dd->ctx);
+	struct aead_request *req = aead_request_cast(dd->areq);
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	bool enc = atmel_aes_is_encrypt(dd);
+	u32 offset, authsize, itag[4], *otag = ctx->tag;
+	int err;
+
+	/* Read the computed tag. */
+	if (likely(dd->flags & AES_FLAGS_GTAGEN))
+		atmel_aes_read_block(dd, AES_TAGR(0), ctx->tag);
+	else
+		atmel_aes_read_block(dd, AES_ODATAR(0), ctx->tag);
+
+	offset = req->assoclen + ctx->textlen;
+	authsize = crypto_aead_authsize(tfm);
+	if (enc) {
+		scatterwalk_map_and_copy(otag, req->dst, offset, authsize, 1);
+		err = 0;
+	} else {
+		scatterwalk_map_and_copy(itag, req->src, offset, authsize, 0);
+		err = crypto_memneq(itag, otag, authsize) ? -EBADMSG : 0;
+	}
+
+	return atmel_aes_complete(dd, err);
+}
+
+static int atmel_aes_gcm_crypt(struct aead_request *req,
+			       unsigned long mode)
+{
+	struct atmel_aes_base_ctx *ctx;
+	struct atmel_aes_reqctx *rctx;
+	struct atmel_aes_dev *dd;
+
+	ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
+	ctx->block_size = AES_BLOCK_SIZE;
+
+	dd = atmel_aes_find_dev(ctx);
+	if (!dd)
+		return -ENODEV;
+
+	rctx = aead_request_ctx(req);
+	rctx->mode = AES_FLAGS_GCM | mode;
+
+	return atmel_aes_handle_queue(dd, &req->base);
+}
+
+static int atmel_aes_gcm_setkey(struct crypto_aead *tfm, const u8 *key,
+				unsigned int keylen)
+{
+	struct atmel_aes_base_ctx *ctx = crypto_aead_ctx(tfm);
+
+	if (keylen != AES_KEYSIZE_256 &&
+	    keylen != AES_KEYSIZE_192 &&
+	    keylen != AES_KEYSIZE_128) {
+		crypto_aead_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	memcpy(ctx->key, key, keylen);
+	ctx->keylen = keylen;
+
+	return 0;
+}
+
+static int atmel_aes_gcm_setauthsize(struct crypto_aead *tfm,
+				     unsigned int authsize)
+{
+	/* Same as crypto_gcm_authsize() from crypto/gcm.c */
+	switch (authsize) {
+	case 4:
+	case 8:
+	case 12:
+	case 13:
+	case 14:
+	case 15:
+	case 16:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int atmel_aes_gcm_encrypt(struct aead_request *req)
+{
+	return atmel_aes_gcm_crypt(req, AES_FLAGS_ENCRYPT);
+}
+
+static int atmel_aes_gcm_decrypt(struct aead_request *req)
+{
+	return atmel_aes_gcm_crypt(req, 0);
+}
+
+static int atmel_aes_gcm_init(struct crypto_aead *tfm)
+{
+	struct atmel_aes_gcm_ctx *ctx = crypto_aead_ctx(tfm);
+
+	crypto_aead_set_reqsize(tfm, sizeof(struct atmel_aes_reqctx));
+	ctx->base.start = atmel_aes_gcm_start;
+
+	return 0;
+}
+
+static void atmel_aes_gcm_exit(struct crypto_aead *tfm)
+{
+
+}
+
+static struct aead_alg aes_gcm_alg = {
+	.setkey		= atmel_aes_gcm_setkey,
+	.setauthsize	= atmel_aes_gcm_setauthsize,
+	.encrypt	= atmel_aes_gcm_encrypt,
+	.decrypt	= atmel_aes_gcm_decrypt,
+	.init		= atmel_aes_gcm_init,
+	.exit		= atmel_aes_gcm_exit,
+	.ivsize		= 12,
+	.maxauthsize	= AES_BLOCK_SIZE,
+
+	.base = {
+		.cra_name		= "gcm(aes)",
+		.cra_driver_name	= "atmel-gcm-aes",
+		.cra_priority		= ATMEL_AES_PRIORITY,
+		.cra_flags		= CRYPTO_ALG_ASYNC,
+		.cra_blocksize		= 1,
+		.cra_ctxsize		= sizeof(struct atmel_aes_gcm_ctx),
+		.cra_alignmask		= 0xf,
+		.cra_module		= THIS_MODULE,
+	},
+};
+
+
+/* Probe functions */
+
+static int atmel_aes_buff_init(struct atmel_aes_dev *dd)
+{
+	dd->buf = (void *)__get_free_pages(GFP_KERNEL, ATMEL_AES_BUFFER_ORDER);
+	dd->buflen = ATMEL_AES_BUFFER_SIZE;
+	dd->buflen &= ~(AES_BLOCK_SIZE - 1);
+
+	if (!dd->buf) {
+		dev_err(dd->dev, "unable to alloc pages.\n");
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void atmel_aes_buff_cleanup(struct atmel_aes_dev *dd)
+{
+	free_page((unsigned long)dd->buf);
+}
+
+static bool atmel_aes_filter(struct dma_chan *chan, void *slave)
+{
+	struct at_dma_slave	*sl = slave;
+
+	if (sl && sl->dma_dev == chan->device->dev) {
+		chan->private = sl;
+		return true;
+	} else {
+		return false;
+	}
+}
+
+static int atmel_aes_dma_init(struct atmel_aes_dev *dd,
+			      struct crypto_platform_data *pdata)
+{
+	struct at_dma_slave *slave;
+	int err = -ENOMEM;
+	dma_cap_mask_t mask;
+
+	dma_cap_zero(mask);
+	dma_cap_set(DMA_SLAVE, mask);
+
+	/* Try to grab 2 DMA channels */
+	slave = &pdata->dma_slave->rxdata;
+	dd->src.chan = dma_request_slave_channel_compat(mask, atmel_aes_filter,
+							slave, dd->dev, "tx");
+	if (!dd->src.chan)
+		goto err_dma_in;
+
+	slave = &pdata->dma_slave->txdata;
+	dd->dst.chan = dma_request_slave_channel_compat(mask, atmel_aes_filter,
+							slave, dd->dev, "rx");
+	if (!dd->dst.chan)
+		goto err_dma_out;
+
+	return 0;
+
+err_dma_out:
+	dma_release_channel(dd->src.chan);
+err_dma_in:
+	dev_warn(dd->dev, "no DMA channel available\n");
+	return err;
+}
+
+static void atmel_aes_dma_cleanup(struct atmel_aes_dev *dd)
+{
+	dma_release_channel(dd->dst.chan);
+	dma_release_channel(dd->src.chan);
+}
+
 static void atmel_aes_queue_task(unsigned long data)
 {
 	struct atmel_aes_dev *dd = (struct atmel_aes_dev *)data;
@@ -1157,42 +1854,10 @@
 
 static void atmel_aes_done_task(unsigned long data)
 {
-	struct atmel_aes_dev *dd = (struct atmel_aes_dev *) data;
-	int err;
+	struct atmel_aes_dev *dd = (struct atmel_aes_dev *)data;
 
-	if (!(dd->flags & AES_FLAGS_DMA)) {
-		atmel_aes_read_n(dd, AES_ODATAR(0), (u32 *) dd->buf_out,
-				dd->bufcnt >> 2);
-
-		if (sg_copy_from_buffer(dd->out_sg, dd->nb_out_sg,
-			dd->buf_out, dd->bufcnt))
-			err = 0;
-		else
-			err = -EINVAL;
-
-		goto cpu_end;
-	}
-
-	err = atmel_aes_crypt_dma_stop(dd);
-
-	err = dd->err ? : err;
-
-	if (dd->total && !err) {
-		if (dd->flags & AES_FLAGS_FAST) {
-			dd->in_sg = sg_next(dd->in_sg);
-			dd->out_sg = sg_next(dd->out_sg);
-			if (!dd->in_sg || !dd->out_sg)
-				err = -EINVAL;
-		}
-		if (!err)
-			err = atmel_aes_crypt_dma_start(dd);
-		if (!err)
-			return; /* DMA started. Not fininishing. */
-	}
-
-cpu_end:
-	atmel_aes_finish_req(dd, err);
-	atmel_aes_handle_queue(dd, NULL);
+	dd->is_async = true;
+	(void)dd->resume(dd);
 }
 
 static irqreturn_t atmel_aes_irq(int irq, void *dev_id)
@@ -1217,10 +1882,14 @@
 {
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(aes_algs); i++)
-		crypto_unregister_alg(&aes_algs[i]);
+	if (dd->caps.has_gcm)
+		crypto_unregister_aead(&aes_gcm_alg);
+
 	if (dd->caps.has_cfb64)
 		crypto_unregister_alg(&aes_cfb64_alg);
+
+	for (i = 0; i < ARRAY_SIZE(aes_algs); i++)
+		crypto_unregister_alg(&aes_algs[i]);
 }
 
 static int atmel_aes_register_algs(struct atmel_aes_dev *dd)
@@ -1239,8 +1908,16 @@
 			goto err_aes_cfb64_alg;
 	}
 
+	if (dd->caps.has_gcm) {
+		err = crypto_register_aead(&aes_gcm_alg);
+		if (err)
+			goto err_aes_gcm_alg;
+	}
+
 	return 0;
 
+err_aes_gcm_alg:
+	crypto_unregister_alg(&aes_cfb64_alg);
 err_aes_cfb64_alg:
 	i = ARRAY_SIZE(aes_algs);
 err_aes_algs:
@@ -1254,13 +1931,24 @@
 {
 	dd->caps.has_dualbuff = 0;
 	dd->caps.has_cfb64 = 0;
+	dd->caps.has_ctr32 = 0;
+	dd->caps.has_gcm = 0;
 	dd->caps.max_burst_size = 1;
 
 	/* keep only major version number */
 	switch (dd->hw_version & 0xff0) {
+	case 0x500:
+		dd->caps.has_dualbuff = 1;
+		dd->caps.has_cfb64 = 1;
+		dd->caps.has_ctr32 = 1;
+		dd->caps.has_gcm = 1;
+		dd->caps.max_burst_size = 4;
+		break;
 	case 0x200:
 		dd->caps.has_dualbuff = 1;
 		dd->caps.has_cfb64 = 1;
+		dd->caps.has_ctr32 = 1;
+		dd->caps.has_gcm = 1;
 		dd->caps.max_burst_size = 4;
 		break;
 	case 0x130:
@@ -1402,7 +2090,9 @@
 		goto res_err;
 	}
 
-	atmel_aes_hw_version_init(aes_dd);
+	err = atmel_aes_hw_version_init(aes_dd);
+	if (err)
+		goto res_err;
 
 	atmel_aes_get_cap(aes_dd);
 
@@ -1423,8 +2113,8 @@
 		goto err_algs;
 
 	dev_info(dev, "Atmel AES - Using %s, %s for DMA transfers\n",
-			dma_chan_name(aes_dd->dma_lch_in.chan),
-			dma_chan_name(aes_dd->dma_lch_out.chan));
+			dma_chan_name(aes_dd->src.chan),
+			dma_chan_name(aes_dd->dst.chan));
 
 	return 0;
 
@@ -1462,6 +2152,7 @@
 	tasklet_kill(&aes_dd->queue_task);
 
 	atmel_aes_dma_cleanup(aes_dd);
+	atmel_aes_buff_cleanup(aes_dd);
 
 	return 0;
 }
diff --git a/drivers/crypto/atmel-sha.c b/drivers/crypto/atmel-sha.c
index 660d8c0..20de861 100644
--- a/drivers/crypto/atmel-sha.c
+++ b/drivers/crypto/atmel-sha.c
@@ -755,7 +755,6 @@
 {
 	struct atmel_sha_reqctx *ctx = ahash_request_ctx(req);
 	struct atmel_sha_dev *dd = ctx->dd;
-	int err = 0;
 
 	if (ctx->digcnt[0] || ctx->digcnt[1])
 		atmel_sha_copy_ready_hash(req);
@@ -763,7 +762,7 @@
 	dev_dbg(dd->dev, "digcnt: 0x%llx 0x%llx, bufcnt: %d\n", ctx->digcnt[1],
 		ctx->digcnt[0], ctx->bufcnt);
 
-	return err;
+	return 0;
 }
 
 static void atmel_sha_finish_req(struct ahash_request *req, int err)
diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c
index 49106ea..5845d4a 100644
--- a/drivers/crypto/caam/caamhash.c
+++ b/drivers/crypto/caam/caamhash.c
@@ -803,6 +803,10 @@
 	if (to_hash) {
 		src_nents = sg_nents_for_len(req->src,
 					     req->nbytes - (*next_buflen));
+		if (src_nents < 0) {
+			dev_err(jrdev, "Invalid number of src SG.\n");
+			return src_nents;
+		}
 		sec4_sg_src_index = 1 + (*buflen ? 1 : 0);
 		sec4_sg_bytes = (sec4_sg_src_index + src_nents) *
 				 sizeof(struct sec4_sg_entry);
@@ -1002,6 +1006,10 @@
 	int sh_len;
 
 	src_nents = sg_nents_for_len(req->src, req->nbytes);
+	if (src_nents < 0) {
+		dev_err(jrdev, "Invalid number of src SG.\n");
+		return src_nents;
+	}
 	sec4_sg_src_index = 1 + (buflen ? 1 : 0);
 	sec4_sg_bytes = (sec4_sg_src_index + src_nents) *
 			 sizeof(struct sec4_sg_entry);
@@ -1086,6 +1094,10 @@
 	int sh_len;
 
 	src_nents = sg_count(req->src, req->nbytes);
+	if (src_nents < 0) {
+		dev_err(jrdev, "Invalid number of src SG.\n");
+		return src_nents;
+	}
 	dma_map_sg(jrdev, req->src, src_nents ? : 1, DMA_TO_DEVICE);
 	sec4_sg_bytes = src_nents * sizeof(struct sec4_sg_entry);
 
@@ -1234,6 +1246,10 @@
 	if (to_hash) {
 		src_nents = sg_nents_for_len(req->src,
 					     req->nbytes - (*next_buflen));
+		if (src_nents < 0) {
+			dev_err(jrdev, "Invalid number of src SG.\n");
+			return src_nents;
+		}
 		sec4_sg_bytes = (1 + src_nents) *
 				sizeof(struct sec4_sg_entry);
 
@@ -1342,6 +1358,10 @@
 	int ret = 0;
 
 	src_nents = sg_nents_for_len(req->src, req->nbytes);
+	if (src_nents < 0) {
+		dev_err(jrdev, "Invalid number of src SG.\n");
+		return src_nents;
+	}
 	sec4_sg_src_index = 2;
 	sec4_sg_bytes = (sec4_sg_src_index + src_nents) *
 			 sizeof(struct sec4_sg_entry);
@@ -1430,6 +1450,10 @@
 
 	if (to_hash) {
 		src_nents = sg_count(req->src, req->nbytes - (*next_buflen));
+		if (src_nents < 0) {
+			dev_err(jrdev, "Invalid number of src SG.\n");
+			return src_nents;
+		}
 		dma_map_sg(jrdev, req->src, src_nents ? : 1, DMA_TO_DEVICE);
 		sec4_sg_bytes = src_nents * sizeof(struct sec4_sg_entry);
 
@@ -1572,7 +1596,7 @@
 		len = state->buflen_1;
 	} else {
 		buf = state->buf_0;
-		len = state->buflen_1;
+		len = state->buflen_0;
 	}
 
 	memcpy(export->buf, buf, len);
diff --git a/drivers/crypto/ccp/Kconfig b/drivers/crypto/ccp/Kconfig
index 3cd8481..6e37845 100644
--- a/drivers/crypto/ccp/Kconfig
+++ b/drivers/crypto/ccp/Kconfig
@@ -3,6 +3,8 @@
 	depends on CRYPTO_DEV_CCP
 	default m
 	select HW_RANDOM
+	select CRYPTO_SHA1
+	select CRYPTO_SHA256
 	help
 	  Provides the interface to use the AMD Cryptographic Coprocessor
 	  which can be used to offload encryption operations such as SHA,
diff --git a/drivers/crypto/ccp/ccp-ops.c b/drivers/crypto/ccp/ccp-ops.c
index c6e883b2..6613aee 100644
--- a/drivers/crypto/ccp/ccp-ops.c
+++ b/drivers/crypto/ccp/ccp-ops.c
@@ -152,32 +152,6 @@
 	cpu_to_be32(SHA256_H6), cpu_to_be32(SHA256_H7),
 };
 
-/* The CCP cannot perform zero-length sha operations so the caller
- * is required to buffer data for the final operation.  However, a
- * sha operation for a message with a total length of zero is valid
- * so known values are required to supply the result.
- */
-static const u8 ccp_sha1_zero[CCP_SHA_CTXSIZE] = {
-	0xda, 0x39, 0xa3, 0xee, 0x5e, 0x6b, 0x4b, 0x0d,
-	0x32, 0x55, 0xbf, 0xef, 0x95, 0x60, 0x18, 0x90,
-	0xaf, 0xd8, 0x07, 0x09, 0x00, 0x00, 0x00, 0x00,
-	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-};
-
-static const u8 ccp_sha224_zero[CCP_SHA_CTXSIZE] = {
-	0xd1, 0x4a, 0x02, 0x8c, 0x2a, 0x3a, 0x2b, 0xc9,
-	0x47, 0x61, 0x02, 0xbb, 0x28, 0x82, 0x34, 0xc4,
-	0x15, 0xa2, 0xb0, 0x1f, 0x82, 0x8e, 0xa6, 0x2a,
-	0xc5, 0xb3, 0xe4, 0x2f, 0x00, 0x00, 0x00, 0x00,
-};
-
-static const u8 ccp_sha256_zero[CCP_SHA_CTXSIZE] = {
-	0xe3, 0xb0, 0xc4, 0x42, 0x98, 0xfc, 0x1c, 0x14,
-	0x9a, 0xfb, 0xf4, 0xc8, 0x99, 0x6f, 0xb9, 0x24,
-	0x27, 0xae, 0x41, 0xe4, 0x64, 0x9b, 0x93, 0x4c,
-	0xa4, 0x95, 0x99, 0x1b, 0x78, 0x52, 0xb8, 0x55,
-};
-
 static u32 ccp_addr_lo(struct ccp_dma_info *info)
 {
 	return lower_32_bits(info->address + info->offset);
@@ -1391,18 +1365,21 @@
 		if (sha->msg_bits)
 			return -EINVAL;
 
-		/* A sha operation for a message with a total length of zero,
-		 * return known result.
+		/* The CCP cannot perform zero-length sha operations so the
+		 * caller is required to buffer data for the final operation.
+		 * However, a sha operation for a message with a total length
+		 * of zero is valid so known values are required to supply
+		 * the result.
 		 */
 		switch (sha->type) {
 		case CCP_SHA_TYPE_1:
-			sha_zero = ccp_sha1_zero;
+			sha_zero = sha1_zero_message_hash;
 			break;
 		case CCP_SHA_TYPE_224:
-			sha_zero = ccp_sha224_zero;
+			sha_zero = sha224_zero_message_hash;
 			break;
 		case CCP_SHA_TYPE_256:
-			sha_zero = ccp_sha256_zero;
+			sha_zero = sha256_zero_message_hash;
 			break;
 		default:
 			return -EINVAL;
diff --git a/drivers/crypto/ccp/ccp-pci.c b/drivers/crypto/ccp/ccp-pci.c
index 6ade02f..7690467 100644
--- a/drivers/crypto/ccp/ccp-pci.c
+++ b/drivers/crypto/ccp/ccp-pci.c
@@ -44,7 +44,7 @@
 {
 	struct ccp_pci *ccp_pci = ccp->dev_specific;
 	struct device *dev = ccp->dev;
-	struct pci_dev *pdev = container_of(dev, struct pci_dev, dev);
+	struct pci_dev *pdev = to_pci_dev(dev);
 	struct msix_entry msix_entry[MSIX_VECTORS];
 	unsigned int name_len = sizeof(ccp_pci->msix[0].name) - 1;
 	int v, ret;
@@ -86,7 +86,7 @@
 static int ccp_get_msi_irq(struct ccp_device *ccp)
 {
 	struct device *dev = ccp->dev;
-	struct pci_dev *pdev = container_of(dev, struct pci_dev, dev);
+	struct pci_dev *pdev = to_pci_dev(dev);
 	int ret;
 
 	ret = pci_enable_msi(pdev);
@@ -133,7 +133,7 @@
 {
 	struct ccp_pci *ccp_pci = ccp->dev_specific;
 	struct device *dev = ccp->dev;
-	struct pci_dev *pdev = container_of(dev, struct pci_dev, dev);
+	struct pci_dev *pdev = to_pci_dev(dev);
 
 	if (ccp_pci->msix_count) {
 		while (ccp_pci->msix_count--)
@@ -149,7 +149,7 @@
 static int ccp_find_mmio_area(struct ccp_device *ccp)
 {
 	struct device *dev = ccp->dev;
-	struct pci_dev *pdev = container_of(dev, struct pci_dev, dev);
+	struct pci_dev *pdev = to_pci_dev(dev);
 	resource_size_t io_len;
 	unsigned long io_flags;
 
diff --git a/drivers/crypto/ccp/ccp-platform.c b/drivers/crypto/ccp/ccp-platform.c
index 01b50cb..66dd7c9 100644
--- a/drivers/crypto/ccp/ccp-platform.c
+++ b/drivers/crypto/ccp/ccp-platform.c
@@ -35,8 +35,7 @@
 static int ccp_get_irq(struct ccp_device *ccp)
 {
 	struct device *dev = ccp->dev;
-	struct platform_device *pdev = container_of(dev,
-					struct platform_device, dev);
+	struct platform_device *pdev = to_platform_device(dev);
 	int ret;
 
 	ret = platform_get_irq(pdev, 0);
@@ -78,8 +77,7 @@
 static struct resource *ccp_find_mmio_area(struct ccp_device *ccp)
 {
 	struct device *dev = ccp->dev;
-	struct platform_device *pdev = container_of(dev,
-					struct platform_device, dev);
+	struct platform_device *pdev = to_platform_device(dev);
 	struct resource *ior;
 
 	ior = platform_get_resource(pdev, IORESOURCE_MEM, 0);
diff --git a/drivers/crypto/hifn_795x.c b/drivers/crypto/hifn_795x.c
index ca5c71a..eee2c7e 100644
--- a/drivers/crypto/hifn_795x.c
+++ b/drivers/crypto/hifn_795x.c
@@ -11,10 +11,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #include <linux/kernel.h>
@@ -36,14 +32,6 @@
 #include <crypto/algapi.h>
 #include <crypto/des.h>
 
-//#define HIFN_DEBUG
-
-#ifdef HIFN_DEBUG
-#define dprintk(f, a...) 	printk(f, ##a)
-#else
-#define dprintk(f, a...)	do {} while (0)
-#endif
-
 static char hifn_pll_ref[sizeof("extNNN")] = "ext";
 module_param_string(hifn_pll_ref, hifn_pll_ref, sizeof(hifn_pll_ref), 0444);
 MODULE_PARM_DESC(hifn_pll_ref,
@@ -79,12 +67,12 @@
 
 /* DMA registres */
 
-#define HIFN_DMA_CRA 			0x0C	/* DMA Command Ring Address */
-#define HIFN_DMA_SDRA 			0x1C	/* DMA Source Data Ring Address */
+#define HIFN_DMA_CRA			0x0C	/* DMA Command Ring Address */
+#define HIFN_DMA_SDRA			0x1C	/* DMA Source Data Ring Address */
 #define HIFN_DMA_RRA			0x2C	/* DMA Result Ring Address */
 #define HIFN_DMA_DDRA			0x3C	/* DMA Destination Data Ring Address */
 #define HIFN_DMA_STCTL			0x40	/* DMA Status and Control */
-#define HIFN_DMA_INTREN 		0x44	/* DMA Interrupt Enable */
+#define HIFN_DMA_INTREN			0x44	/* DMA Interrupt Enable */
 #define HIFN_DMA_CFG1			0x48	/* DMA Configuration #1 */
 #define HIFN_DMA_CFG2			0x6C	/* DMA Configuration #2 */
 #define HIFN_CHIP_ID			0x98	/* Chip ID */
@@ -358,10 +346,10 @@
 #define HIFN_NAMESIZE			32
 #define HIFN_MAX_RESULT_ORDER		5
 
-#define	HIFN_D_CMD_RSIZE		24*1
-#define	HIFN_D_SRC_RSIZE		80*1
-#define	HIFN_D_DST_RSIZE		80*1
-#define	HIFN_D_RES_RSIZE		24*1
+#define	HIFN_D_CMD_RSIZE		(24 * 1)
+#define	HIFN_D_SRC_RSIZE		(80 * 1)
+#define	HIFN_D_DST_RSIZE		(80 * 1)
+#define	HIFN_D_RES_RSIZE		(24 * 1)
 
 #define HIFN_D_DST_DALIGN		4
 
@@ -386,17 +374,16 @@
 #define	HIFN_MAX_RESULT			(8 + 4 + 4 + 20 + 4)
 #define HIFN_USED_RESULT		12
 
-struct hifn_desc
-{
+struct hifn_desc {
 	volatile __le32		l;
 	volatile __le32		p;
 };
 
 struct hifn_dma {
-	struct hifn_desc	cmdr[HIFN_D_CMD_RSIZE+1];
-	struct hifn_desc	srcr[HIFN_D_SRC_RSIZE+1];
-	struct hifn_desc	dstr[HIFN_D_DST_RSIZE+1];
-	struct hifn_desc	resr[HIFN_D_RES_RSIZE+1];
+	struct hifn_desc	cmdr[HIFN_D_CMD_RSIZE + 1];
+	struct hifn_desc	srcr[HIFN_D_SRC_RSIZE + 1];
+	struct hifn_desc	dstr[HIFN_D_DST_RSIZE + 1];
+	struct hifn_desc	resr[HIFN_D_RES_RSIZE + 1];
 
 	u8			command_bufs[HIFN_D_CMD_RSIZE][HIFN_MAX_COMMAND];
 	u8			result_bufs[HIFN_D_CMD_RSIZE][HIFN_MAX_RESULT];
@@ -410,16 +397,15 @@
 	int			cmdk, srck, dstk, resk;
 };
 
-#define HIFN_FLAG_CMD_BUSY	(1<<0)
-#define HIFN_FLAG_SRC_BUSY	(1<<1)
-#define HIFN_FLAG_DST_BUSY	(1<<2)
-#define HIFN_FLAG_RES_BUSY	(1<<3)
-#define HIFN_FLAG_OLD_KEY	(1<<4)
+#define HIFN_FLAG_CMD_BUSY	(1 << 0)
+#define HIFN_FLAG_SRC_BUSY	(1 << 1)
+#define HIFN_FLAG_DST_BUSY	(1 << 2)
+#define HIFN_FLAG_RES_BUSY	(1 << 3)
+#define HIFN_FLAG_OLD_KEY	(1 << 4)
 
 #define HIFN_DEFAULT_ACTIVE_NUM	5
 
-struct hifn_device
-{
+struct hifn_device {
 	char			name[HIFN_NAMESIZE];
 
 	int			irq;
@@ -432,7 +418,7 @@
 
 	u32			dmareg;
 
-	void 			*sa[HIFN_D_RES_RSIZE];
+	void			*sa[HIFN_D_RES_RSIZE];
 
 	spinlock_t		lock;
 
@@ -447,7 +433,7 @@
 
 	struct tasklet_struct	tasklet;
 
-	struct crypto_queue 	queue;
+	struct crypto_queue	queue;
 	struct list_head	alg_list;
 
 	unsigned int		pk_clk_freq;
@@ -468,8 +454,7 @@
 #define	HIFN_D_JUMP			0x40000000
 #define	HIFN_D_VALID			0x80000000
 
-struct hifn_base_command
-{
+struct hifn_base_command {
 	volatile __le16		masks;
 	volatile __le16		session_num;
 	volatile __le16		total_source_count;
@@ -491,12 +476,11 @@
 /*
  * Structure to help build up the command data structure.
  */
-struct hifn_crypt_command
-{
-	volatile __le16 		masks;
-	volatile __le16 		header_skip;
-	volatile __le16 		source_count;
-	volatile __le16 		reserved;
+struct hifn_crypt_command {
+	volatile __le16		masks;
+	volatile __le16		header_skip;
+	volatile __le16		source_count;
+	volatile __le16		reserved;
 };
 
 #define	HIFN_CRYPT_CMD_ALG_MASK		0x0003		/* algorithm: */
@@ -522,12 +506,11 @@
 /*
  * Structure to help build up the command data structure.
  */
-struct hifn_mac_command
-{
-	volatile __le16 	masks;
-	volatile __le16 	header_skip;
-	volatile __le16 	source_count;
-	volatile __le16 	reserved;
+struct hifn_mac_command {
+	volatile __le16	masks;
+	volatile __le16	header_skip;
+	volatile __le16	source_count;
+	volatile __le16	reserved;
 };
 
 #define	HIFN_MAC_CMD_ALG_MASK		0x0001
@@ -551,12 +534,11 @@
 #define	HIFN_MAC_CMD_POS_IPSEC		0x0200
 #define	HIFN_MAC_CMD_NEW_KEY		0x0800
 
-struct hifn_comp_command
-{
-	volatile __le16 	masks;
-	volatile __le16 	header_skip;
-	volatile __le16 	source_count;
-	volatile __le16 	reserved;
+struct hifn_comp_command {
+	volatile __le16		masks;
+	volatile __le16		header_skip;
+	volatile __le16		source_count;
+	volatile __le16		reserved;
 };
 
 #define	HIFN_COMP_CMD_SRCLEN_M		0xc000
@@ -570,12 +552,11 @@
 #define	HIFN_COMP_CMD_ALG_MPPC		0x0001	/*   MPPC */
 #define	HIFN_COMP_CMD_ALG_LZS		0x0000	/*   LZS */
 
-struct hifn_base_result
-{
-	volatile __le16 	flags;
-	volatile __le16 	session;
-	volatile __le16 	src_cnt;		/* 15:0 of source count */
-	volatile __le16 	dst_cnt;		/* 15:0 of dest count */
+struct hifn_base_result {
+	volatile __le16		flags;
+	volatile __le16		session;
+	volatile __le16		src_cnt;		/* 15:0 of source count */
+	volatile __le16		dst_cnt;		/* 15:0 of dest count */
 };
 
 #define	HIFN_BASE_RES_DSTOVERRUN	0x0200	/* destination overrun */
@@ -584,8 +565,7 @@
 #define	HIFN_BASE_RES_DSTLEN_M		0x3000	/* 17:16 of dest count */
 #define	HIFN_BASE_RES_DSTLEN_S		12
 
-struct hifn_comp_result
-{
+struct hifn_comp_result {
 	volatile __le16		flags;
 	volatile __le16		crc;
 };
@@ -596,18 +576,16 @@
 #define	HIFN_COMP_RES_ENDMARKER		0x0002	/* LZS: end marker seen */
 #define	HIFN_COMP_RES_SRC_NOTZERO	0x0001	/* source expired */
 
-struct hifn_mac_result
-{
-	volatile __le16 	flags;
-	volatile __le16 	reserved;
+struct hifn_mac_result {
+	volatile __le16		flags;
+	volatile __le16		reserved;
 	/* followed by 0, 6, 8, or 10 u16's of the MAC, then crypt */
 };
 
 #define	HIFN_MAC_RES_MISCOMPARE		0x0002	/* compare failed */
 #define	HIFN_MAC_RES_SRC_NOTZERO	0x0001	/* source expired */
 
-struct hifn_crypt_result
-{
+struct hifn_crypt_result {
 	volatile __le16		flags;
 	volatile __le16		reserved;
 };
@@ -622,11 +600,10 @@
 #define	HIFN_POLL_SCALAR	0x0
 #endif
 
-#define	HIFN_MAX_SEGLEN 	0xffff		/* maximum dma segment len */
+#define	HIFN_MAX_SEGLEN		0xffff		/* maximum dma segment len */
 #define	HIFN_MAX_DMALEN		0x3ffff		/* maximum dma length */
 
-struct hifn_crypto_alg
-{
+struct hifn_crypto_alg {
 	struct list_head	entry;
 	struct crypto_alg	alg;
 	struct hifn_device	*dev;
@@ -634,24 +611,21 @@
 
 #define ASYNC_SCATTERLIST_CACHE	16
 
-#define ASYNC_FLAGS_MISALIGNED	(1<<0)
+#define ASYNC_FLAGS_MISALIGNED	(1 << 0)
 
-struct hifn_cipher_walk
-{
+struct hifn_cipher_walk {
 	struct scatterlist	cache[ASYNC_SCATTERLIST_CACHE];
 	u32			flags;
 	int			num;
 };
 
-struct hifn_context
-{
+struct hifn_context {
 	u8			key[HIFN_MAX_CRYPT_KEY_LENGTH];
 	struct hifn_device	*dev;
 	unsigned int		keysize;
 };
 
-struct hifn_request_context
-{
+struct hifn_request_context {
 	u8			*iv;
 	unsigned int		ivsize;
 	u8			op, type, mode, unused;
@@ -693,7 +667,7 @@
 	int i;
 	u32 ret;
 
-	for (i=10000; i > 0; --i) {
+	for (i = 10000; i > 0; --i) {
 		ret = hifn_read_0(dev, HIFN_0_PUCTRL);
 		if (!(ret & HIFN_PUCTRL_RESET))
 			break;
@@ -702,7 +676,7 @@
 	}
 
 	if (!i)
-		dprintk("%s: Failed to reset PUC unit.\n", dev->name);
+		dev_err(&dev->pdev->dev, "Failed to reset PUC unit.\n");
 }
 
 static void hifn_reset_puc(struct hifn_device *dev)
@@ -749,13 +723,12 @@
 	hifn_reset_puc(dev);
 }
 
-static u32 hifn_next_signature(u_int32_t a, u_int cnt)
+static u32 hifn_next_signature(u32 a, u_int cnt)
 {
 	int i;
 	u32 v;
 
 	for (i = 0; i < cnt; i++) {
-
 		/* get the parity */
 		v = a & 0x80080125;
 		v ^= v >> 16;
@@ -846,33 +819,28 @@
 	hifn_write_1(dev, HIFN_1_PUB_RESET, hifn_read_1(dev, HIFN_1_PUB_RESET) |
 			HIFN_PUBRST_RESET);
 
-	for (i=100; i > 0; --i) {
+	for (i = 100; i > 0; --i) {
 		mdelay(1);
 
 		if ((hifn_read_1(dev, HIFN_1_PUB_RESET) & HIFN_PUBRST_RESET) == 0)
 			break;
 	}
 
-	if (!i)
-		dprintk("Chip %s: Failed to initialise public key engine.\n",
-				dev->name);
-	else {
+	if (!i) {
+		dev_err(&dev->pdev->dev, "Failed to initialise public key engine.\n");
+	} else {
 		hifn_write_1(dev, HIFN_1_PUB_IEN, HIFN_PUBIEN_DONE);
 		dev->dmareg |= HIFN_DMAIER_PUBDONE;
 		hifn_write_1(dev, HIFN_1_DMA_IER, dev->dmareg);
 
-		dprintk("Chip %s: Public key engine has been successfully "
-				"initialised.\n", dev->name);
+		dev_dbg(&dev->pdev->dev, "Public key engine has been successfully initialised.\n");
 	}
 
-	/*
-	 * Enable RNG engine.
-	 */
+	/* Enable RNG engine. */
 
 	hifn_write_1(dev, HIFN_1_RNG_CONFIG,
 			hifn_read_1(dev, HIFN_1_RNG_CONFIG) | HIFN_RNGCFG_ENA);
-	dprintk("Chip %s: RNG engine has been successfully initialised.\n",
-			dev->name);
+	dev_dbg(&dev->pdev->dev, "RNG engine has been successfully initialised.\n");
 
 #ifdef CONFIG_CRYPTO_DEV_HIFN_795X_RNG
 	/* First value must be discarded */
@@ -896,8 +864,8 @@
 		}
 	}
 
-	if (offtbl == NULL) {
-		dprintk("Chip %s: Unknown card!\n", dev->name);
+	if (!offtbl) {
+		dev_err(&dev->pdev->dev, "Unknown card!\n");
 		return -ENODEV;
 	}
 
@@ -912,7 +880,7 @@
 	hifn_write_1(dev, HIFN_1_UNLOCK_SECRET2, 0);
 	mdelay(1);
 
-	for (i=0; i<12; ++i) {
+	for (i = 0; i < 12; ++i) {
 		addr = hifn_next_signature(addr, offtbl[i] + 0x101);
 		hifn_write_1(dev, HIFN_1_UNLOCK_SECRET2, addr);
 
@@ -920,7 +888,7 @@
 	}
 	hifn_write_1(dev, HIFN_1_DMA_CNFG, dmacfg);
 
-	dprintk("Chip %s: %s.\n", dev->name, pci_name(dev->pdev));
+	dev_dbg(&dev->pdev->dev, "%s %s.\n", dev->name, pci_name(dev->pdev));
 
 	return 0;
 }
@@ -931,16 +899,14 @@
 	u32 dptr = dev->desc_dma;
 	int i;
 
-	for (i=0; i<HIFN_D_CMD_RSIZE; ++i)
+	for (i = 0; i < HIFN_D_CMD_RSIZE; ++i)
 		dma->cmdr[i].p = __cpu_to_le32(dptr +
 				offsetof(struct hifn_dma, command_bufs[i][0]));
-	for (i=0; i<HIFN_D_RES_RSIZE; ++i)
+	for (i = 0; i < HIFN_D_RES_RSIZE; ++i)
 		dma->resr[i].p = __cpu_to_le32(dptr +
 				offsetof(struct hifn_dma, result_bufs[i][0]));
 
-	/*
-	 * Setup LAST descriptors.
-	 */
+	/* Setup LAST descriptors. */
 	dma->cmdr[HIFN_D_CMD_RSIZE].p = __cpu_to_le32(dptr +
 			offsetof(struct hifn_dma, cmdr[0]));
 	dma->srcr[HIFN_D_SRC_RSIZE].p = __cpu_to_le32(dptr +
@@ -960,7 +926,7 @@
  * to calculate the optimal multiplier. For PCI we assume 66MHz, since that
  * allows us to operate without the risk of overclocking the chip. If it
  * actually uses 33MHz, the chip will operate at half the speed, this can be
- * overriden by specifying the frequency as module parameter (pci33).
+ * overridden by specifying the frequency as module parameter (pci33).
  *
  * Unfortunately the PCI clock is not very suitable since the HIFN needs a
  * stable clock and the PCI clock frequency may vary, so the default is the
@@ -984,9 +950,8 @@
 		freq = simple_strtoul(hifn_pll_ref + 3, NULL, 10);
 	else {
 		freq = 66;
-		printk(KERN_INFO "hifn795x: assuming %uMHz clock speed, "
-				 "override with hifn_pll_ref=%.3s<frequency>\n",
-		       freq, hifn_pll_ref);
+		dev_info(&dev->pdev->dev, "assuming %uMHz clock speed, override with hifn_pll_ref=%.3s<frequency>\n",
+			 freq, hifn_pll_ref);
 	}
 
 	m = HIFN_PLL_FCK_MAX / freq;
@@ -1174,17 +1139,17 @@
 
 	mask = 0;
 	switch (rctx->op) {
-		case ACRYPTO_OP_DECRYPT:
-			mask = HIFN_BASE_CMD_CRYPT | HIFN_BASE_CMD_DECODE;
-			break;
-		case ACRYPTO_OP_ENCRYPT:
-			mask = HIFN_BASE_CMD_CRYPT;
-			break;
-		case ACRYPTO_OP_HMAC:
-			mask = HIFN_BASE_CMD_MAC;
-			break;
-		default:
-			goto err_out;
+	case ACRYPTO_OP_DECRYPT:
+		mask = HIFN_BASE_CMD_CRYPT | HIFN_BASE_CMD_DECODE;
+		break;
+	case ACRYPTO_OP_ENCRYPT:
+		mask = HIFN_BASE_CMD_CRYPT;
+		break;
+	case ACRYPTO_OP_HMAC:
+		mask = HIFN_BASE_CMD_MAC;
+		break;
+	default:
+		goto err_out;
 	}
 
 	buf_pos += hifn_setup_base_command(dev, buf_pos, nbytes,
@@ -1199,53 +1164,53 @@
 			md |= HIFN_CRYPT_CMD_NEW_IV;
 
 		switch (rctx->mode) {
-			case ACRYPTO_MODE_ECB:
-				md |= HIFN_CRYPT_CMD_MODE_ECB;
-				break;
-			case ACRYPTO_MODE_CBC:
-				md |= HIFN_CRYPT_CMD_MODE_CBC;
-				break;
-			case ACRYPTO_MODE_CFB:
-				md |= HIFN_CRYPT_CMD_MODE_CFB;
-				break;
-			case ACRYPTO_MODE_OFB:
-				md |= HIFN_CRYPT_CMD_MODE_OFB;
-				break;
-			default:
-				goto err_out;
+		case ACRYPTO_MODE_ECB:
+			md |= HIFN_CRYPT_CMD_MODE_ECB;
+			break;
+		case ACRYPTO_MODE_CBC:
+			md |= HIFN_CRYPT_CMD_MODE_CBC;
+			break;
+		case ACRYPTO_MODE_CFB:
+			md |= HIFN_CRYPT_CMD_MODE_CFB;
+			break;
+		case ACRYPTO_MODE_OFB:
+			md |= HIFN_CRYPT_CMD_MODE_OFB;
+			break;
+		default:
+			goto err_out;
 		}
 
 		switch (rctx->type) {
-			case ACRYPTO_TYPE_AES_128:
-				if (ctx->keysize != 16)
-					goto err_out;
-				md |= HIFN_CRYPT_CMD_KSZ_128 |
-					HIFN_CRYPT_CMD_ALG_AES;
-				break;
-			case ACRYPTO_TYPE_AES_192:
-				if (ctx->keysize != 24)
-					goto err_out;
-				md |= HIFN_CRYPT_CMD_KSZ_192 |
-					HIFN_CRYPT_CMD_ALG_AES;
-				break;
-			case ACRYPTO_TYPE_AES_256:
-				if (ctx->keysize != 32)
-					goto err_out;
-				md |= HIFN_CRYPT_CMD_KSZ_256 |
-					HIFN_CRYPT_CMD_ALG_AES;
-				break;
-			case ACRYPTO_TYPE_3DES:
-				if (ctx->keysize != 24)
-					goto err_out;
-				md |= HIFN_CRYPT_CMD_ALG_3DES;
-				break;
-			case ACRYPTO_TYPE_DES:
-				if (ctx->keysize != 8)
-					goto err_out;
-				md |= HIFN_CRYPT_CMD_ALG_DES;
-				break;
-			default:
+		case ACRYPTO_TYPE_AES_128:
+			if (ctx->keysize != 16)
 				goto err_out;
+			md |= HIFN_CRYPT_CMD_KSZ_128 |
+				HIFN_CRYPT_CMD_ALG_AES;
+			break;
+		case ACRYPTO_TYPE_AES_192:
+			if (ctx->keysize != 24)
+				goto err_out;
+			md |= HIFN_CRYPT_CMD_KSZ_192 |
+				HIFN_CRYPT_CMD_ALG_AES;
+			break;
+		case ACRYPTO_TYPE_AES_256:
+			if (ctx->keysize != 32)
+				goto err_out;
+			md |= HIFN_CRYPT_CMD_KSZ_256 |
+				HIFN_CRYPT_CMD_ALG_AES;
+			break;
+		case ACRYPTO_TYPE_3DES:
+			if (ctx->keysize != 24)
+				goto err_out;
+			md |= HIFN_CRYPT_CMD_ALG_3DES;
+			break;
+		case ACRYPTO_TYPE_DES:
+			if (ctx->keysize != 8)
+				goto err_out;
+			md |= HIFN_CRYPT_CMD_ALG_DES;
+			break;
+		default:
+			goto err_out;
 		}
 
 		buf_pos += hifn_setup_crypto_command(dev, buf_pos,
@@ -1265,8 +1230,9 @@
 			HIFN_D_VALID | HIFN_D_LAST |
 			HIFN_D_MASKDONEIRQ | HIFN_D_JUMP);
 		dma->cmdi = 0;
-	} else
-		dma->cmdr[dma->cmdi-1].l |= __cpu_to_le32(HIFN_D_VALID);
+	} else {
+		dma->cmdr[dma->cmdi - 1].l |= __cpu_to_le32(HIFN_D_VALID);
+	}
 
 	if (!(dev->flags & HIFN_FLAG_CMD_BUSY)) {
 		hifn_write_1(dev, HIFN_1_DMA_CSR, HIFN_DMACSR_C_CTRL_ENA);
@@ -1424,7 +1390,7 @@
 	sg_init_table(w->cache, num);
 
 	w->num = 0;
-	for (i=0; i<num; ++i) {
+	for (i = 0; i < num; ++i) {
 		struct page *page = alloc_page(gfp_flags);
 		struct scatterlist *s;
 
@@ -1444,7 +1410,7 @@
 {
 	int i;
 
-	for (i=0; i<w->num; ++i) {
+	for (i = 0; i < w->num; ++i) {
 		struct scatterlist *s = &w->cache[i];
 
 		__free_page(sg_page(s));
@@ -1471,8 +1437,8 @@
 		drest -= copy;
 		nbytes -= copy;
 
-		dprintk("%s: copy: %u, size: %u, drest: %u, nbytes: %u.\n",
-				__func__, copy, size, drest, nbytes);
+		pr_debug("%s: copy: %u, size: %u, drest: %u, nbytes: %u.\n",
+			 __func__, copy, size, drest, nbytes);
 
 		dst++;
 		idx++;
@@ -1499,8 +1465,8 @@
 
 		dst = &req->dst[idx];
 
-		dprintk("\n%s: dlen: %u, doff: %u, offset: %u, nbytes: %u.\n",
-			__func__, dst->length, dst->offset, offset, nbytes);
+		pr_debug("\n%s: dlen: %u, doff: %u, offset: %u, nbytes: %u.\n",
+			 __func__, dst->length, dst->offset, offset, nbytes);
 
 		if (!IS_ALIGNED(dst->offset, HIFN_D_DST_DALIGN) ||
 		    !IS_ALIGNED(dst->length, HIFN_D_DST_DALIGN) ||
@@ -1525,10 +1491,10 @@
 				 * to put there additional blocksized chunk,
 				 * so we mark that page as containing only
 				 * blocksize aligned chunks:
-				 * 	t->length = (slen & ~(HIFN_D_DST_DALIGN - 1));
+				 *	t->length = (slen & ~(HIFN_D_DST_DALIGN - 1));
 				 * and increase number of bytes to be processed
 				 * in next chunk:
-				 * 	nbytes += diff;
+				 *	nbytes += diff;
 				 */
 				nbytes += diff;
 
@@ -1536,14 +1502,13 @@
 				 * Temporary of course...
 				 * Kick author if you will catch this one.
 				 */
-				printk(KERN_ERR "%s: dlen: %u, nbytes: %u,"
-					"slen: %u, offset: %u.\n",
-					__func__, dlen, nbytes, slen, offset);
-				printk(KERN_ERR "%s: please contact author to fix this "
-					"issue, generally you should not catch "
-					"this path under any condition but who "
-					"knows how did you use crypto code.\n"
-					"Thank you.\n",	__func__);
+				pr_err("%s: dlen: %u, nbytes: %u, slen: %u, offset: %u.\n",
+				       __func__, dlen, nbytes, slen, offset);
+				pr_err("%s: please contact author to fix this "
+				       "issue, generally you should not catch "
+				       "this path under any condition but who "
+				       "knows how did you use crypto code.\n"
+				       "Thank you.\n",	__func__);
 				BUG();
 			} else {
 				copy += diff + nbytes;
@@ -1630,70 +1595,16 @@
 	spin_unlock_irqrestore(&dev->lock, flags);
 err_out_exit:
 	if (err) {
-		printk("%s: iv: %p [%d], key: %p [%d], mode: %u, op: %u, "
-				"type: %u, err: %d.\n",
-			dev->name, rctx->iv, rctx->ivsize,
-			ctx->key, ctx->keysize,
-			rctx->mode, rctx->op, rctx->type, err);
+		dev_info(&dev->pdev->dev, "iv: %p [%d], key: %p [%d], mode: %u, op: %u, "
+			 "type: %u, err: %d.\n",
+			 rctx->iv, rctx->ivsize,
+			 ctx->key, ctx->keysize,
+			 rctx->mode, rctx->op, rctx->type, err);
 	}
 
 	return err;
 }
 
-static int hifn_test(struct hifn_device *dev, int encdec, u8 snum)
-{
-	int n, err;
-	u8 src[16];
-	struct hifn_context ctx;
-	struct hifn_request_context rctx;
-	u8 fips_aes_ecb_from_zero[16] = {
-		0x66, 0xE9, 0x4B, 0xD4,
-		0xEF, 0x8A, 0x2C, 0x3B,
-		0x88, 0x4C, 0xFA, 0x59,
-		0xCA, 0x34, 0x2B, 0x2E};
-	struct scatterlist sg;
-
-	memset(src, 0, sizeof(src));
-	memset(ctx.key, 0, sizeof(ctx.key));
-
-	ctx.dev = dev;
-	ctx.keysize = 16;
-	rctx.ivsize = 0;
-	rctx.iv = NULL;
-	rctx.op = (encdec)?ACRYPTO_OP_ENCRYPT:ACRYPTO_OP_DECRYPT;
-	rctx.mode = ACRYPTO_MODE_ECB;
-	rctx.type = ACRYPTO_TYPE_AES_128;
-	rctx.walk.cache[0].length = 0;
-
-	sg_init_one(&sg, &src, sizeof(src));
-
-	err = hifn_setup_dma(dev, &ctx, &rctx, &sg, &sg, sizeof(src), NULL);
-	if (err)
-		goto err_out;
-
-	dev->started = 0;
-	msleep(200);
-
-	dprintk("%s: decoded: ", dev->name);
-	for (n=0; n<sizeof(src); ++n)
-		dprintk("%02x ", src[n]);
-	dprintk("\n");
-	dprintk("%s: FIPS   : ", dev->name);
-	for (n=0; n<sizeof(fips_aes_ecb_from_zero); ++n)
-		dprintk("%02x ", fips_aes_ecb_from_zero[n]);
-	dprintk("\n");
-
-	if (!memcmp(src, fips_aes_ecb_from_zero, sizeof(fips_aes_ecb_from_zero))) {
-		printk(KERN_INFO "%s: AES 128 ECB test has been successfully "
-				"passed.\n", dev->name);
-		return 0;
-	}
-
-err_out:
-	printk(KERN_INFO "%s: AES 128 ECB test has been failed.\n", dev->name);
-	return -1;
-}
-
 static int hifn_start_device(struct hifn_device *dev)
 {
 	int err;
@@ -1739,8 +1650,8 @@
 		saddr += copy;
 		offset = 0;
 
-		dprintk("%s: copy: %u, size: %u, srest: %u, nbytes: %u.\n",
-				__func__, copy, size, srest, nbytes);
+		pr_debug("%s: copy: %u, size: %u, srest: %u, nbytes: %u.\n",
+			 __func__, copy, size, srest, nbytes);
 
 		dst++;
 		idx++;
@@ -1760,7 +1671,8 @@
 	dev->sa[i] = NULL;
 	dev->started--;
 	if (dev->started < 0)
-		printk("%s: started: %d.\n", __func__, dev->started);
+		dev_info(&dev->pdev->dev, "%s: started: %d.\n", __func__,
+			 dev->started);
 	spin_unlock_irqrestore(&dev->lock, flags);
 	BUG_ON(dev->started < 0);
 }
@@ -1779,7 +1691,7 @@
 			t = &rctx->walk.cache[idx];
 			dst = &req->dst[idx];
 
-			dprintk("\n%s: sg_page(t): %p, t->length: %u, "
+			pr_debug("\n%s: sg_page(t): %p, t->length: %u, "
 				"sg_page(dst): %p, dst->length: %u, "
 				"nbytes: %u.\n",
 				__func__, sg_page(t), t->length,
@@ -1815,9 +1727,8 @@
 	struct hifn_dma *dma = (struct hifn_dma *)dev->desc_virt;
 	int i, u;
 
-	dprintk("%s: ring cleanup 1: i: %d.%d.%d.%d, u: %d.%d.%d.%d, "
+	dev_dbg(&dev->pdev->dev, "ring cleanup 1: i: %d.%d.%d.%d, u: %d.%d.%d.%d, "
 			"k: %d.%d.%d.%d.\n",
-			dev->name,
 			dma->cmdi, dma->srci, dma->dsti, dma->resi,
 			dma->cmdu, dma->srcu, dma->dstu, dma->resu,
 			dma->cmdk, dma->srck, dma->dstk, dma->resk);
@@ -1870,9 +1781,8 @@
 	}
 	dma->dstk = i; dma->dstu = u;
 
-	dprintk("%s: ring cleanup 2: i: %d.%d.%d.%d, u: %d.%d.%d.%d, "
+	dev_dbg(&dev->pdev->dev, "ring cleanup 2: i: %d.%d.%d.%d, u: %d.%d.%d.%d, "
 			"k: %d.%d.%d.%d.\n",
-			dev->name,
 			dma->cmdi, dma->srci, dma->dsti, dma->resi,
 			dma->cmdu, dma->srcu, dma->dstu, dma->resu,
 			dma->cmdk, dma->srck, dma->dstk, dma->resk);
@@ -1921,21 +1831,22 @@
 			int i;
 			struct hifn_dma *dma = (struct hifn_dma *)dev->desc_virt;
 
-			printk("%s: r: %08x, active: %d, started: %d, "
-				"success: %lu: qlen: %u/%u, reset: %d.\n",
-				dev->name, r, dev->active, dev->started,
-				dev->success, dev->queue.qlen, dev->queue.max_qlen,
-				reset);
+			dev_info(&dev->pdev->dev,
+				 "r: %08x, active: %d, started: %d, "
+				 "success: %lu: qlen: %u/%u, reset: %d.\n",
+				 r, dev->active, dev->started,
+				 dev->success, dev->queue.qlen, dev->queue.max_qlen,
+				 reset);
 
-			printk("%s: res: ", __func__);
-			for (i=0; i<HIFN_D_RES_RSIZE; ++i) {
-				printk("%x.%p ", dma->resr[i].l, dev->sa[i]);
+			dev_info(&dev->pdev->dev, "%s: res: ", __func__);
+			for (i = 0; i < HIFN_D_RES_RSIZE; ++i) {
+				pr_info("%x.%p ", dma->resr[i].l, dev->sa[i]);
 				if (dev->sa[i]) {
 					hifn_process_ready(dev->sa[i], -ENODEV);
 					hifn_complete_sa(dev, i);
 				}
 			}
-			printk("\n");
+			pr_info("\n");
 
 			hifn_reset_dma(dev, 1);
 			hifn_stop_device(dev);
@@ -1957,9 +1868,9 @@
 
 	dmacsr = hifn_read_1(dev, HIFN_1_DMA_CSR);
 
-	dprintk("%s: 1 dmacsr: %08x, dmareg: %08x, res: %08x [%d], "
+	dev_dbg(&dev->pdev->dev, "1 dmacsr: %08x, dmareg: %08x, res: %08x [%d], "
 			"i: %d.%d.%d.%d, u: %d.%d.%d.%d.\n",
-		dev->name, dmacsr, dev->dmareg, dmacsr & dev->dmareg, dma->cmdi,
+		dmacsr, dev->dmareg, dmacsr & dev->dmareg, dma->cmdi,
 		dma->cmdi, dma->srci, dma->dsti, dma->resi,
 		dma->cmdu, dma->srcu, dma->dstu, dma->resu);
 
@@ -1978,9 +1889,9 @@
 	if (restart) {
 		u32 puisr = hifn_read_0(dev, HIFN_0_PUISR);
 
-		printk(KERN_WARNING "%s: overflow: r: %d, d: %d, puisr: %08x, d: %u.\n",
-			dev->name, !!(dmacsr & HIFN_DMACSR_R_OVER),
-			!!(dmacsr & HIFN_DMACSR_D_OVER),
+		dev_warn(&dev->pdev->dev, "overflow: r: %d, d: %d, puisr: %08x, d: %u.\n",
+			 !!(dmacsr & HIFN_DMACSR_R_OVER),
+			 !!(dmacsr & HIFN_DMACSR_D_OVER),
 			puisr, !!(puisr & HIFN_PUISR_DSTOVER));
 		if (!!(puisr & HIFN_PUISR_DSTOVER))
 			hifn_write_0(dev, HIFN_0_PUISR, HIFN_PUISR_DSTOVER);
@@ -1991,18 +1902,18 @@
 	restart = dmacsr & (HIFN_DMACSR_C_ABORT | HIFN_DMACSR_S_ABORT |
 			HIFN_DMACSR_D_ABORT | HIFN_DMACSR_R_ABORT);
 	if (restart) {
-		printk(KERN_WARNING "%s: abort: c: %d, s: %d, d: %d, r: %d.\n",
-			dev->name, !!(dmacsr & HIFN_DMACSR_C_ABORT),
-			!!(dmacsr & HIFN_DMACSR_S_ABORT),
-			!!(dmacsr & HIFN_DMACSR_D_ABORT),
-			!!(dmacsr & HIFN_DMACSR_R_ABORT));
+		dev_warn(&dev->pdev->dev, "abort: c: %d, s: %d, d: %d, r: %d.\n",
+			 !!(dmacsr & HIFN_DMACSR_C_ABORT),
+			 !!(dmacsr & HIFN_DMACSR_S_ABORT),
+			 !!(dmacsr & HIFN_DMACSR_D_ABORT),
+			 !!(dmacsr & HIFN_DMACSR_R_ABORT));
 		hifn_reset_dma(dev, 1);
 		hifn_init_dma(dev);
 		hifn_init_registers(dev);
 	}
 
 	if ((dmacsr & HIFN_DMACSR_C_WAIT) && (dma->cmdu == 0)) {
-		dprintk("%s: wait on command.\n", dev->name);
+		dev_dbg(&dev->pdev->dev, "wait on command.\n");
 		dev->dmareg &= ~(HIFN_DMAIER_C_WAIT);
 		hifn_write_1(dev, HIFN_1_DMA_IER, dev->dmareg);
 	}
@@ -2020,19 +1931,19 @@
 	struct hifn_dma *dma = (struct hifn_dma *)dev->desc_virt;
 	int i;
 
-	for (i=0; i<HIFN_D_RES_RSIZE; ++i) {
+	for (i = 0; i < HIFN_D_RES_RSIZE; ++i) {
 		struct hifn_desc *d = &dma->resr[i];
 
 		if (dev->sa[i]) {
 			hifn_process_ready(dev->sa[i],
-				(d->l & __cpu_to_le32(HIFN_D_VALID))?-ENODEV:0);
+				(d->l & __cpu_to_le32(HIFN_D_VALID)) ? -ENODEV : 0);
 			hifn_complete_sa(dev, i);
 		}
 	}
 
 	spin_lock_irqsave(&dev->lock, flags);
 	while ((async_req = crypto_dequeue_request(&dev->queue))) {
-		req = container_of(async_req, struct ablkcipher_request, base);
+		req = ablkcipher_request_cast(async_req);
 		spin_unlock_irqrestore(&dev->lock, flags);
 
 		hifn_process_ready(req, -ENODEV);
@@ -2057,7 +1968,7 @@
 	if (len == HIFN_DES_KEY_LENGTH) {
 		u32 tmp[DES_EXPKEY_WORDS];
 		int ret = des_ekey(tmp, key);
-		
+
 		if (unlikely(ret == 0) && (tfm->crt_flags & CRYPTO_TFM_REQ_WEAK_KEY)) {
 			tfm->crt_flags |= CRYPTO_TFM_RES_WEAK_KEY;
 			return -EINVAL;
@@ -2151,7 +2062,7 @@
 		if (backlog)
 			backlog->complete(backlog, -EINPROGRESS);
 
-		req = container_of(async_req, struct ablkcipher_request, base);
+		req = ablkcipher_request_cast(async_req);
 
 		err = hifn_handle_req(req);
 		if (err)
@@ -2298,9 +2209,7 @@
 			ACRYPTO_TYPE_3DES, ACRYPTO_MODE_OFB);
 }
 
-/*
- * 3DES decryption functions.
- */
+/* 3DES decryption functions. */
 static inline int hifn_decrypt_3des_ecb(struct ablkcipher_request *req)
 {
 	return hifn_setup_crypto(req, ACRYPTO_OP_DECRYPT,
@@ -2322,8 +2231,7 @@
 			ACRYPTO_TYPE_3DES, ACRYPTO_MODE_OFB);
 }
 
-struct hifn_alg_template
-{
+struct hifn_alg_template {
 	char name[CRYPTO_MAX_ALG_NAME];
 	char drv_name[CRYPTO_MAX_ALG_NAME];
 	unsigned int bsize;
@@ -2483,7 +2391,7 @@
 	struct hifn_crypto_alg *alg;
 	int err;
 
-	alg = kzalloc(sizeof(struct hifn_crypto_alg), GFP_KERNEL);
+	alg = kzalloc(sizeof(*alg), GFP_KERNEL);
 	if (!alg)
 		return -ENOMEM;
 
@@ -2530,7 +2438,7 @@
 {
 	int i, err;
 
-	for (i=0; i<ARRAY_SIZE(hifn_alg_templates); ++i) {
+	for (i = 0; i < ARRAY_SIZE(hifn_alg_templates); ++i) {
 		err = hifn_alg_alloc(dev, &hifn_alg_templates[i]);
 		if (err)
 			goto err_out_exit;
@@ -2575,7 +2483,7 @@
 		goto err_out_disable_pci_device;
 
 	snprintf(name, sizeof(name), "hifn%d",
-			atomic_inc_return(&hifn_dev_number)-1);
+			atomic_inc_return(&hifn_dev_number) - 1);
 
 	err = pci_request_regions(pdev, name);
 	if (err)
@@ -2584,8 +2492,7 @@
 	if (pci_resource_len(pdev, 0) < HIFN_BAR0_SIZE ||
 	    pci_resource_len(pdev, 1) < HIFN_BAR1_SIZE ||
 	    pci_resource_len(pdev, 2) < HIFN_BAR2_SIZE) {
-		dprintk("%s: Broken hardware - I/O regions are too small.\n",
-				pci_name(pdev));
+		dev_err(&pdev->dev, "Broken hardware - I/O regions are too small.\n");
 		err = -ENODEV;
 		goto err_out_free_regions;
 	}
@@ -2602,7 +2509,7 @@
 	snprintf(dev->name, sizeof(dev->name), "%s", name);
 	spin_lock_init(&dev->lock);
 
-	for (i=0; i<3; ++i) {
+	for (i = 0; i < 3; ++i) {
 		unsigned long addr, size;
 
 		addr = pci_resource_start(pdev, i);
@@ -2618,7 +2525,7 @@
 	dev->desc_virt = pci_zalloc_consistent(pdev, sizeof(struct hifn_dma),
 					       &dev->desc_dma);
 	if (!dev->desc_virt) {
-		dprintk("Failed to allocate descriptor rings.\n");
+		dev_err(&pdev->dev, "Failed to allocate descriptor rings.\n");
 		err = -ENOMEM;
 		goto err_out_unmap_bars;
 	}
@@ -2626,7 +2533,7 @@
 	dev->pdev = pdev;
 	dev->irq = pdev->irq;
 
-	for (i=0; i<HIFN_D_RES_RSIZE; ++i)
+	for (i = 0; i < HIFN_D_RES_RSIZE; ++i)
 		dev->sa[i] = NULL;
 
 	pci_set_drvdata(pdev, dev);
@@ -2637,7 +2544,8 @@
 
 	err = request_irq(dev->irq, hifn_interrupt, IRQF_SHARED, dev->name, dev);
 	if (err) {
-		dprintk("Failed to request IRQ%d: err: %d.\n", dev->irq, err);
+		dev_err(&pdev->dev, "Failed to request IRQ%d: err: %d.\n",
+			dev->irq, err);
 		dev->irq = 0;
 		goto err_out_free_desc;
 	}
@@ -2646,10 +2554,6 @@
 	if (err)
 		goto err_out_free_irq;
 
-	err = hifn_test(dev, 1, 0);
-	if (err)
-		goto err_out_stop_device;
-
 	err = hifn_register_rng(dev);
 	if (err)
 		goto err_out_stop_device;
@@ -2661,9 +2565,9 @@
 	INIT_DELAYED_WORK(&dev->work, hifn_work);
 	schedule_delayed_work(&dev->work, HZ);
 
-	dprintk("HIFN crypto accelerator card at %s has been "
-			"successfully registered as %s.\n",
-			pci_name(pdev), dev->name);
+	dev_dbg(&pdev->dev, "HIFN crypto accelerator card at %s has been "
+		"successfully registered as %s.\n",
+		pci_name(pdev), dev->name);
 
 	return 0;
 
@@ -2680,7 +2584,7 @@
 			dev->desc_virt, dev->desc_dma);
 
 err_out_unmap_bars:
-	for (i=0; i<3; ++i)
+	for (i = 0; i < 3; ++i)
 		if (dev->bar[i])
 			iounmap(dev->bar[i]);
 
@@ -2715,7 +2619,7 @@
 
 		pci_free_consistent(pdev, sizeof(struct hifn_dma),
 				dev->desc_virt, dev->desc_dma);
-		for (i=0; i<3; ++i)
+		for (i = 0; i < 3; ++i)
 			if (dev->bar[i])
 				iounmap(dev->bar[i]);
 
@@ -2750,8 +2654,7 @@
 
 	if (strncmp(hifn_pll_ref, "ext", 3) &&
 	    strncmp(hifn_pll_ref, "pci", 3)) {
-		printk(KERN_ERR "hifn795x: invalid hifn_pll_ref clock, "
-				"must be pci or ext");
+		pr_err("hifn795x: invalid hifn_pll_ref clock, must be pci or ext");
 		return -EINVAL;
 	}
 
@@ -2763,22 +2666,21 @@
 	if (hifn_pll_ref[3] != '\0') {
 		freq = simple_strtoul(hifn_pll_ref + 3, NULL, 10);
 		if (freq < 20 || freq > 100) {
-			printk(KERN_ERR "hifn795x: invalid hifn_pll_ref "
-					"frequency, must be in the range "
-					"of 20-100");
+			pr_err("hifn795x: invalid hifn_pll_ref frequency, must"
+			       "be in the range of 20-100");
 			return -EINVAL;
 		}
 	}
 
 	err = pci_register_driver(&hifn_pci_driver);
 	if (err < 0) {
-		dprintk("Failed to register PCI driver for %s device.\n",
-				hifn_pci_driver.name);
+		pr_err("Failed to register PCI driver for %s device.\n",
+		       hifn_pci_driver.name);
 		return -ENODEV;
 	}
 
-	printk(KERN_INFO "Driver for HIFN 795x crypto accelerator chip "
-			"has been successfully registered.\n");
+	pr_info("Driver for HIFN 795x crypto accelerator chip "
+		"has been successfully registered.\n");
 
 	return 0;
 }
@@ -2787,8 +2689,8 @@
 {
 	pci_unregister_driver(&hifn_pci_driver);
 
-	printk(KERN_INFO "Driver for HIFN 795x crypto accelerator chip "
-			"has been successfully unregistered.\n");
+	pr_info("Driver for HIFN 795x crypto accelerator chip "
+		"has been successfully unregistered.\n");
 }
 
 module_init(hifn_init);
diff --git a/drivers/crypto/ixp4xx_crypto.c b/drivers/crypto/ixp4xx_crypto.c
index 8f27903..e52496a 100644
--- a/drivers/crypto/ixp4xx_crypto.c
+++ b/drivers/crypto/ixp4xx_crypto.c
@@ -510,10 +510,8 @@
 	printk(KERN_ERR "%s not responding\n", npe_name(npe_c));
 	ret = -EIO;
 err:
-	if (ctx_pool)
-		dma_pool_destroy(ctx_pool);
-	if (buffer_pool)
-		dma_pool_destroy(buffer_pool);
+	dma_pool_destroy(ctx_pool);
+	dma_pool_destroy(buffer_pool);
 	npe_release(npe_c);
 	return ret;
 }
diff --git a/drivers/crypto/marvell/cipher.c b/drivers/crypto/marvell/cipher.c
index 6edae64b..dcf1fce 100644
--- a/drivers/crypto/marvell/cipher.c
+++ b/drivers/crypto/marvell/cipher.c
@@ -401,7 +401,15 @@
 		return -EINVAL;
 
 	creq->src_nents = sg_nents_for_len(req->src, req->nbytes);
+	if (creq->src_nents < 0) {
+		dev_err(cesa_dev->dev, "Invalid number of src SG");
+		return creq->src_nents;
+	}
 	creq->dst_nents = sg_nents_for_len(req->dst, req->nbytes);
+	if (creq->dst_nents < 0) {
+		dev_err(cesa_dev->dev, "Invalid number of dst SG");
+		return creq->dst_nents;
+	}
 
 	mv_cesa_update_op_cfg(tmpl, CESA_SA_DESC_CFG_OP_CRYPT_ONLY,
 			      CESA_SA_DESC_CFG_OP_MSK);
diff --git a/drivers/crypto/marvell/hash.c b/drivers/crypto/marvell/hash.c
index 6ec55b4..683cca9 100644
--- a/drivers/crypto/marvell/hash.c
+++ b/drivers/crypto/marvell/hash.c
@@ -712,6 +712,10 @@
 		creq->req.base.type = CESA_STD_REQ;
 
 	creq->src_nents = sg_nents_for_len(req->src, req->nbytes);
+	if (creq->src_nents < 0) {
+		dev_err(cesa_dev->dev, "Invalid number of src SG");
+		return creq->src_nents;
+	}
 
 	ret = mv_cesa_ahash_cache_req(req, cached);
 	if (ret)
diff --git a/drivers/crypto/n2_core.c b/drivers/crypto/n2_core.c
index 5450880..b85a7a7 100644
--- a/drivers/crypto/n2_core.c
+++ b/drivers/crypto/n2_core.c
@@ -241,7 +241,7 @@
 
 struct n2_ahash_alg {
 	struct list_head	entry;
-	const char		*hash_zero;
+	const u8		*hash_zero;
 	const u32		*hash_init;
 	u8			hw_op_hashsz;
 	u8			digest_size;
@@ -1267,7 +1267,7 @@
 
 struct n2_hash_tmpl {
 	const char	*name;
-	const char	*hash_zero;
+	const u8	*hash_zero;
 	const u32	*hash_init;
 	u8		hw_op_hashsz;
 	u8		digest_size;
@@ -1276,40 +1276,19 @@
 	u8		hmac_type;
 };
 
-static const char md5_zero[MD5_DIGEST_SIZE] = {
-	0xd4, 0x1d, 0x8c, 0xd9, 0x8f, 0x00, 0xb2, 0x04,
-	0xe9, 0x80, 0x09, 0x98, 0xec, 0xf8, 0x42, 0x7e,
-};
 static const u32 md5_init[MD5_HASH_WORDS] = {
 	cpu_to_le32(MD5_H0),
 	cpu_to_le32(MD5_H1),
 	cpu_to_le32(MD5_H2),
 	cpu_to_le32(MD5_H3),
 };
-static const char sha1_zero[SHA1_DIGEST_SIZE] = {
-	0xda, 0x39, 0xa3, 0xee, 0x5e, 0x6b, 0x4b, 0x0d, 0x32,
-	0x55, 0xbf, 0xef, 0x95, 0x60, 0x18, 0x90, 0xaf, 0xd8,
-	0x07, 0x09
-};
 static const u32 sha1_init[SHA1_DIGEST_SIZE / 4] = {
 	SHA1_H0, SHA1_H1, SHA1_H2, SHA1_H3, SHA1_H4,
 };
-static const char sha256_zero[SHA256_DIGEST_SIZE] = {
-	0xe3, 0xb0, 0xc4, 0x42, 0x98, 0xfc, 0x1c, 0x14, 0x9a,
-	0xfb, 0xf4, 0xc8, 0x99, 0x6f, 0xb9, 0x24, 0x27, 0xae,
-	0x41, 0xe4, 0x64, 0x9b, 0x93, 0x4c, 0xa4, 0x95, 0x99,
-	0x1b, 0x78, 0x52, 0xb8, 0x55
-};
 static const u32 sha256_init[SHA256_DIGEST_SIZE / 4] = {
 	SHA256_H0, SHA256_H1, SHA256_H2, SHA256_H3,
 	SHA256_H4, SHA256_H5, SHA256_H6, SHA256_H7,
 };
-static const char sha224_zero[SHA224_DIGEST_SIZE] = {
-	0xd1, 0x4a, 0x02, 0x8c, 0x2a, 0x3a, 0x2b, 0xc9, 0x47,
-	0x61, 0x02, 0xbb, 0x28, 0x82, 0x34, 0xc4, 0x15, 0xa2,
-	0xb0, 0x1f, 0x82, 0x8e, 0xa6, 0x2a, 0xc5, 0xb3, 0xe4,
-	0x2f
-};
 static const u32 sha224_init[SHA256_DIGEST_SIZE / 4] = {
 	SHA224_H0, SHA224_H1, SHA224_H2, SHA224_H3,
 	SHA224_H4, SHA224_H5, SHA224_H6, SHA224_H7,
@@ -1317,7 +1296,7 @@
 
 static const struct n2_hash_tmpl hash_tmpls[] = {
 	{ .name		= "md5",
-	  .hash_zero	= md5_zero,
+	  .hash_zero	= md5_zero_message_hash,
 	  .hash_init	= md5_init,
 	  .auth_type	= AUTH_TYPE_MD5,
 	  .hmac_type	= AUTH_TYPE_HMAC_MD5,
@@ -1325,7 +1304,7 @@
 	  .digest_size	= MD5_DIGEST_SIZE,
 	  .block_size	= MD5_HMAC_BLOCK_SIZE },
 	{ .name		= "sha1",
-	  .hash_zero	= sha1_zero,
+	  .hash_zero	= sha1_zero_message_hash,
 	  .hash_init	= sha1_init,
 	  .auth_type	= AUTH_TYPE_SHA1,
 	  .hmac_type	= AUTH_TYPE_HMAC_SHA1,
@@ -1333,7 +1312,7 @@
 	  .digest_size	= SHA1_DIGEST_SIZE,
 	  .block_size	= SHA1_BLOCK_SIZE },
 	{ .name		= "sha256",
-	  .hash_zero	= sha256_zero,
+	  .hash_zero	= sha256_zero_message_hash,
 	  .hash_init	= sha256_init,
 	  .auth_type	= AUTH_TYPE_SHA256,
 	  .hmac_type	= AUTH_TYPE_HMAC_SHA256,
@@ -1341,7 +1320,7 @@
 	  .digest_size	= SHA256_DIGEST_SIZE,
 	  .block_size	= SHA256_BLOCK_SIZE },
 	{ .name		= "sha224",
-	  .hash_zero	= sha224_zero,
+	  .hash_zero	= sha224_zero_message_hash,
 	  .hash_init	= sha224_init,
 	  .auth_type	= AUTH_TYPE_SHA256,
 	  .hmac_type	= AUTH_TYPE_RESERVED,
@@ -2243,22 +2222,19 @@
 	.remove		=	n2_mau_remove,
 };
 
+static struct platform_driver * const drivers[] = {
+	&n2_crypto_driver,
+	&n2_mau_driver,
+};
+
 static int __init n2_init(void)
 {
-	int err = platform_driver_register(&n2_crypto_driver);
-
-	if (!err) {
-		err = platform_driver_register(&n2_mau_driver);
-		if (err)
-			platform_driver_unregister(&n2_crypto_driver);
-	}
-	return err;
+	return platform_register_drivers(drivers, ARRAY_SIZE(drivers));
 }
 
 static void __exit n2_exit(void)
 {
-	platform_driver_unregister(&n2_mau_driver);
-	platform_driver_unregister(&n2_crypto_driver);
+	platform_unregister_drivers(drivers, ARRAY_SIZE(drivers));
 }
 
 module_init(n2_init);
diff --git a/drivers/crypto/nx/nx-842-powernv.c b/drivers/crypto/nx/nx-842-powernv.c
index 9ef51fa..1710f80 100644
--- a/drivers/crypto/nx/nx-842-powernv.c
+++ b/drivers/crypto/nx/nx-842-powernv.c
@@ -442,6 +442,14 @@
 			     (unsigned int)ccw,
 			     (unsigned int)be32_to_cpu(crb->ccw));
 
+	/*
+	 * NX842 coprocessor sets 3rd bit in CR register with XER[S0].
+	 * XER[S0] is the integer summary overflow bit which is nothing
+	 * to do NX. Since this bit can be set with other return values,
+	 * mask this bit.
+	 */
+	ret &= ~ICSWX_XERS0;
+
 	switch (ret) {
 	case ICSWX_INITIATED:
 		ret = wait_for_csb(wmem, csb);
@@ -454,10 +462,6 @@
 		pr_err_ratelimited("ICSWX rejected\n");
 		ret = -EPROTO;
 		break;
-	default:
-		pr_err_ratelimited("Invalid ICSWX return code %x\n", ret);
-		ret = -EPROTO;
-		break;
 	}
 
 	if (!ret)
@@ -525,7 +529,6 @@
 static int __init nx842_powernv_probe(struct device_node *dn)
 {
 	struct nx842_coproc *coproc;
-	struct property *ct_prop, *ci_prop;
 	unsigned int ct, ci;
 	int chip_id;
 
@@ -534,18 +537,16 @@
 		pr_err("ibm,chip-id missing\n");
 		return -EINVAL;
 	}
-	ct_prop = of_find_property(dn, "ibm,842-coprocessor-type", NULL);
-	if (!ct_prop) {
+
+	if (of_property_read_u32(dn, "ibm,842-coprocessor-type", &ct)) {
 		pr_err("ibm,842-coprocessor-type missing\n");
 		return -EINVAL;
 	}
-	ct = be32_to_cpu(*(unsigned int *)ct_prop->value);
-	ci_prop = of_find_property(dn, "ibm,842-coprocessor-instance", NULL);
-	if (!ci_prop) {
+
+	if (of_property_read_u32(dn, "ibm,842-coprocessor-instance", &ci)) {
 		pr_err("ibm,842-coprocessor-instance missing\n");
 		return -EINVAL;
 	}
-	ci = be32_to_cpu(*(unsigned int *)ci_prop->value);
 
 	coproc = kmalloc(sizeof(*coproc), GFP_KERNEL);
 	if (!coproc)
diff --git a/drivers/crypto/omap-aes.c b/drivers/crypto/omap-aes.c
index eba2314..dd355bd 100644
--- a/drivers/crypto/omap-aes.c
+++ b/drivers/crypto/omap-aes.c
@@ -539,8 +539,6 @@
 
 static int omap_aes_crypt_dma_stop(struct omap_aes_dev *dd)
 {
-	int err = 0;
-
 	pr_debug("total: %d\n", dd->total);
 
 	omap_aes_dma_stop(dd);
@@ -548,7 +546,7 @@
 	dmaengine_terminate_all(dd->dma_lch_in);
 	dmaengine_terminate_all(dd->dma_lch_out);
 
-	return err;
+	return 0;
 }
 
 static int omap_aes_check_aligned(struct scatterlist *sg, int total)
diff --git a/drivers/crypto/omap-des.c b/drivers/crypto/omap-des.c
index 0a70e46..dd7b93f 100644
--- a/drivers/crypto/omap-des.c
+++ b/drivers/crypto/omap-des.c
@@ -527,8 +527,6 @@
 
 static int omap_des_crypt_dma_stop(struct omap_des_dev *dd)
 {
-	int err = 0;
-
 	pr_debug("total: %d\n", dd->total);
 
 	omap_des_dma_stop(dd);
@@ -536,7 +534,7 @@
 	dmaengine_terminate_all(dd->dma_lch_in);
 	dmaengine_terminate_all(dd->dma_lch_out);
 
-	return err;
+	return 0;
 }
 
 static int omap_des_copy_needed(struct scatterlist *sg)
@@ -1086,6 +1084,7 @@
 	dd->phys_base = res->start;
 
 	pm_runtime_enable(dev);
+	pm_runtime_irq_safe(dev);
 	err = pm_runtime_get_sync(dev);
 	if (err < 0) {
 		pm_runtime_put_noidle(dev);
diff --git a/drivers/crypto/padlock-aes.c b/drivers/crypto/padlock-aes.c
index da2d677..441e86b 100644
--- a/drivers/crypto/padlock-aes.c
+++ b/drivers/crypto/padlock-aes.c
@@ -238,7 +238,7 @@
 	/* Padlock in ECB mode fetches at least ecb_fetch_bytes of data.
 	 * We could avoid some copying here but it's probably not worth it.
 	 */
-	if (unlikely(((unsigned long)in & ~PAGE_MASK) + ecb_fetch_bytes > PAGE_SIZE)) {
+	if (unlikely(offset_in_page(in) + ecb_fetch_bytes > PAGE_SIZE)) {
 		ecb_crypt_copy(in, out, key, cword, count);
 		return;
 	}
@@ -250,7 +250,7 @@
 			    u8 *iv, struct cword *cword, int count)
 {
 	/* Padlock in CBC mode fetches at least cbc_fetch_bytes of data. */
-	if (unlikely(((unsigned long)in & ~PAGE_MASK) + cbc_fetch_bytes > PAGE_SIZE))
+	if (unlikely(offset_in_page(in) + cbc_fetch_bytes > PAGE_SIZE))
 		return cbc_crypt_copy(in, out, key, iv, cword, count);
 
 	return rep_xcrypt_cbc(in, out, key, iv, cword, count);
@@ -515,7 +515,7 @@
 	if (!x86_match_cpu(padlock_cpu_id))
 		return -ENODEV;
 
-	if (!cpu_has_xcrypt_enabled) {
+	if (!boot_cpu_has(X86_FEATURE_XCRYPT_EN)) {
 		printk(KERN_NOTICE PFX "VIA PadLock detected, but not enabled. Hmm, strange...\n");
 		return -ENODEV;
 	}
diff --git a/drivers/crypto/padlock-sha.c b/drivers/crypto/padlock-sha.c
index 4e154c9..8c5f906 100644
--- a/drivers/crypto/padlock-sha.c
+++ b/drivers/crypto/padlock-sha.c
@@ -540,7 +540,7 @@
 	struct shash_alg *sha1;
 	struct shash_alg *sha256;
 
-	if (!x86_match_cpu(padlock_sha_ids) || !cpu_has_phe_enabled)
+	if (!x86_match_cpu(padlock_sha_ids) || !boot_cpu_has(X86_FEATURE_PHE_EN))
 		return -ENODEV;
 
 	/* Register the newly added algorithm module if on *
diff --git a/drivers/crypto/picoxcell_crypto.c b/drivers/crypto/picoxcell_crypto.c
index 615da96..3b1c7ec 100644
--- a/drivers/crypto/picoxcell_crypto.c
+++ b/drivers/crypto/picoxcell_crypto.c
@@ -272,12 +272,6 @@
 	return indx;
 }
 
-/* Count the number of scatterlist entries in a scatterlist. */
-static inline int sg_count(struct scatterlist *sg_list, int nbytes)
-{
-	return sg_nents_for_len(sg_list, nbytes);
-}
-
 static inline void ddt_set(struct spacc_ddt *ddt, dma_addr_t phys, size_t len)
 {
 	ddt->p = phys;
@@ -295,12 +289,17 @@
 					 enum dma_data_direction dir,
 					 dma_addr_t *ddt_phys)
 {
-	unsigned nents, mapped_ents;
+	unsigned mapped_ents;
 	struct scatterlist *cur;
 	struct spacc_ddt *ddt;
 	int i;
+	int nents;
 
-	nents = sg_count(payload, nbytes);
+	nents = sg_nents_for_len(payload, nbytes);
+	if (nents < 0) {
+		dev_err(engine->dev, "Invalid numbers of SG.\n");
+		return NULL;
+	}
 	mapped_ents = dma_map_sg(engine->dev, payload, nents, dir);
 
 	if (mapped_ents + 1 > MAX_DDT_LEN)
@@ -328,7 +327,7 @@
 	struct spacc_engine *engine = req->engine;
 	struct spacc_ddt *src_ddt, *dst_ddt;
 	unsigned total;
-	unsigned int src_nents, dst_nents;
+	int src_nents, dst_nents;
 	struct scatterlist *cur;
 	int i, dst_ents, src_ents;
 
@@ -336,13 +335,21 @@
 	if (req->is_encrypt)
 		total += crypto_aead_authsize(aead);
 
-	src_nents = sg_count(areq->src, total);
+	src_nents = sg_nents_for_len(areq->src, total);
+	if (src_nents < 0) {
+		dev_err(engine->dev, "Invalid numbers of src SG.\n");
+		return src_nents;
+	}
 	if (src_nents + 1 > MAX_DDT_LEN)
 		return -E2BIG;
 
 	dst_nents = 0;
 	if (areq->src != areq->dst) {
-		dst_nents = sg_count(areq->dst, total);
+		dst_nents = sg_nents_for_len(areq->dst, total);
+		if (dst_nents < 0) {
+			dev_err(engine->dev, "Invalid numbers of dst SG.\n");
+			return dst_nents;
+		}
 		if (src_nents + 1 > MAX_DDT_LEN)
 			return -E2BIG;
 	}
@@ -422,13 +429,22 @@
 			 (req->is_encrypt ? crypto_aead_authsize(aead) : 0);
 	struct spacc_aead_ctx *aead_ctx = crypto_aead_ctx(aead);
 	struct spacc_engine *engine = aead_ctx->generic.engine;
-	unsigned nents = sg_count(areq->src, total);
+	int nents = sg_nents_for_len(areq->src, total);
+
+	/* sg_nents_for_len should not fail since it works when mapping sg */
+	if (unlikely(nents < 0)) {
+		dev_err(engine->dev, "Invalid numbers of src SG.\n");
+		return;
+	}
 
 	if (areq->src != areq->dst) {
 		dma_unmap_sg(engine->dev, areq->src, nents, DMA_TO_DEVICE);
-		dma_unmap_sg(engine->dev, areq->dst,
-			     sg_count(areq->dst, total),
-			     DMA_FROM_DEVICE);
+		nents = sg_nents_for_len(areq->dst, total);
+		if (unlikely(nents < 0)) {
+			dev_err(engine->dev, "Invalid numbers of dst SG.\n");
+			return;
+		}
+		dma_unmap_sg(engine->dev, areq->dst, nents, DMA_FROM_DEVICE);
 	} else
 		dma_unmap_sg(engine->dev, areq->src, nents, DMA_BIDIRECTIONAL);
 
@@ -440,7 +456,12 @@
 			   dma_addr_t ddt_addr, struct scatterlist *payload,
 			   unsigned nbytes, enum dma_data_direction dir)
 {
-	unsigned nents = sg_count(payload, nbytes);
+	int nents = sg_nents_for_len(payload, nbytes);
+
+	if (nents < 0) {
+		dev_err(req->engine->dev, "Invalid numbers of SG.\n");
+		return;
+	}
 
 	dma_unmap_sg(req->engine->dev, payload, nents, dir);
 	dma_pool_free(req->engine->req_pool, ddt, ddt_addr);
@@ -835,8 +856,7 @@
 
 static void spacc_ablk_complete(struct spacc_req *req)
 {
-	struct ablkcipher_request *ablk_req =
-		container_of(req->req, struct ablkcipher_request, base);
+	struct ablkcipher_request *ablk_req = ablkcipher_request_cast(req->req);
 
 	if (ablk_req->src != ablk_req->dst) {
 		spacc_free_ddt(req, req->src_ddt, req->src_addr, ablk_req->src,
diff --git a/drivers/crypto/qat/Kconfig b/drivers/crypto/qat/Kconfig
index eefccf7..85b44e5 100644
--- a/drivers/crypto/qat/Kconfig
+++ b/drivers/crypto/qat/Kconfig
@@ -22,6 +22,28 @@
 	  To compile this as a module, choose M here: the module
 	  will be called qat_dh895xcc.
 
+config CRYPTO_DEV_QAT_C3XXX
+	tristate "Support for Intel(R) C3XXX"
+	depends on X86 && PCI
+	select CRYPTO_DEV_QAT
+	help
+	  Support for Intel(R) C3xxx with Intel(R) QuickAssist Technology
+	  for accelerating crypto and compression workloads.
+
+	  To compile this as a module, choose M here: the module
+	  will be called qat_c3xxx.
+
+config CRYPTO_DEV_QAT_C62X
+	tristate "Support for Intel(R) C62X"
+	depends on X86 && PCI
+	select CRYPTO_DEV_QAT
+	help
+	  Support for Intel(R) C62x with Intel(R) QuickAssist Technology
+	  for accelerating crypto and compression workloads.
+
+	  To compile this as a module, choose M here: the module
+	  will be called qat_c62x.
+
 config CRYPTO_DEV_QAT_DH895xCCVF
 	tristate "Support for Intel(R) DH895xCC Virtual Function"
 	depends on X86 && PCI
@@ -34,3 +56,27 @@
 
 	  To compile this as a module, choose M here: the module
 	  will be called qat_dh895xccvf.
+
+config CRYPTO_DEV_QAT_C3XXXVF
+	tristate "Support for Intel(R) C3XXX Virtual Function"
+	depends on X86 && PCI
+	select PCI_IOV
+	select CRYPTO_DEV_QAT
+	help
+	  Support for Intel(R) C3xxx with Intel(R) QuickAssist Technology
+	  Virtual Function for accelerating crypto and compression workloads.
+
+	  To compile this as a module, choose M here: the module
+	  will be called qat_c3xxxvf.
+
+config CRYPTO_DEV_QAT_C62XVF
+	tristate "Support for Intel(R) C62X Virtual Function"
+	depends on X86 && PCI
+	select PCI_IOV
+	select CRYPTO_DEV_QAT
+	help
+	  Support for Intel(R) C62x with Intel(R) QuickAssist Technology
+	  Virtual Function for accelerating crypto and compression workloads.
+
+	  To compile this as a module, choose M here: the module
+	  will be called qat_c62xvf.
diff --git a/drivers/crypto/qat/Makefile b/drivers/crypto/qat/Makefile
index a3ce0b7..8265106 100644
--- a/drivers/crypto/qat/Makefile
+++ b/drivers/crypto/qat/Makefile
@@ -1,3 +1,7 @@
 obj-$(CONFIG_CRYPTO_DEV_QAT) += qat_common/
 obj-$(CONFIG_CRYPTO_DEV_QAT_DH895xCC) += qat_dh895xcc/
+obj-$(CONFIG_CRYPTO_DEV_QAT_C3XXX) += qat_c3xxx/
+obj-$(CONFIG_CRYPTO_DEV_QAT_C62X) += qat_c62x/
 obj-$(CONFIG_CRYPTO_DEV_QAT_DH895xCCVF) += qat_dh895xccvf/
+obj-$(CONFIG_CRYPTO_DEV_QAT_C3XXXVF) += qat_c3xxxvf/
+obj-$(CONFIG_CRYPTO_DEV_QAT_C62XVF) += qat_c62xvf/
diff --git a/drivers/crypto/qat/qat_c3xxx/Makefile b/drivers/crypto/qat/qat_c3xxx/Makefile
new file mode 100644
index 0000000..8f5fd48
--- /dev/null
+++ b/drivers/crypto/qat/qat_c3xxx/Makefile
@@ -0,0 +1,3 @@
+ccflags-y := -I$(src)/../qat_common
+obj-$(CONFIG_CRYPTO_DEV_QAT_C3XXX) += qat_c3xxx.o
+qat_c3xxx-objs := adf_drv.o adf_c3xxx_hw_data.o
diff --git a/drivers/crypto/qat/qat_c3xxx/adf_c3xxx_hw_data.c b/drivers/crypto/qat/qat_c3xxx/adf_c3xxx_hw_data.c
new file mode 100644
index 0000000..c5bd5a9
--- /dev/null
+++ b/drivers/crypto/qat/qat_c3xxx/adf_c3xxx_hw_data.c
@@ -0,0 +1,238 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+	* Redistributions of source code must retain the above copyright
+	  notice, this list of conditions and the following disclaimer.
+	* Redistributions in binary form must reproduce the above copyright
+	  notice, this list of conditions and the following disclaimer in
+	  the documentation and/or other materials provided with the
+	  distribution.
+	* Neither the name of Intel Corporation nor the names of its
+	  contributors may be used to endorse or promote products derived
+	  from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#include <adf_accel_devices.h>
+#include <adf_common_drv.h>
+#include <adf_pf2vf_msg.h>
+#include "adf_c3xxx_hw_data.h"
+
+/* Worker thread to service arbiter mappings based on dev SKUs */
+static const u32 thrd_to_arb_map_6_me_sku[] = {
+	0x12222AAA, 0x11222AAA, 0x12222AAA,
+	0x11222AAA, 0x12222AAA, 0x11222AAA
+};
+
+static struct adf_hw_device_class c3xxx_class = {
+	.name = ADF_C3XXX_DEVICE_NAME,
+	.type = DEV_C3XXX,
+	.instances = 0
+};
+
+static u32 get_accel_mask(u32 fuse)
+{
+	return (~fuse) >> ADF_C3XXX_ACCELERATORS_REG_OFFSET &
+		ADF_C3XXX_ACCELERATORS_MASK;
+}
+
+static u32 get_ae_mask(u32 fuse)
+{
+	return (~fuse) & ADF_C3XXX_ACCELENGINES_MASK;
+}
+
+static u32 get_num_accels(struct adf_hw_device_data *self)
+{
+	u32 i, ctr = 0;
+
+	if (!self || !self->accel_mask)
+		return 0;
+
+	for (i = 0; i < ADF_C3XXX_MAX_ACCELERATORS; i++) {
+		if (self->accel_mask & (1 << i))
+			ctr++;
+	}
+	return ctr;
+}
+
+static u32 get_num_aes(struct adf_hw_device_data *self)
+{
+	u32 i, ctr = 0;
+
+	if (!self || !self->ae_mask)
+		return 0;
+
+	for (i = 0; i < ADF_C3XXX_MAX_ACCELENGINES; i++) {
+		if (self->ae_mask & (1 << i))
+			ctr++;
+	}
+	return ctr;
+}
+
+static u32 get_misc_bar_id(struct adf_hw_device_data *self)
+{
+	return ADF_C3XXX_PMISC_BAR;
+}
+
+static u32 get_etr_bar_id(struct adf_hw_device_data *self)
+{
+	return ADF_C3XXX_ETR_BAR;
+}
+
+static u32 get_sram_bar_id(struct adf_hw_device_data *self)
+{
+	return 0;
+}
+
+static enum dev_sku_info get_sku(struct adf_hw_device_data *self)
+{
+	int aes = get_num_aes(self);
+
+	if (aes == 6)
+		return DEV_SKU_4;
+
+	return DEV_SKU_UNKNOWN;
+}
+
+static void adf_get_arbiter_mapping(struct adf_accel_dev *accel_dev,
+				    u32 const **arb_map_config)
+{
+	switch (accel_dev->accel_pci_dev.sku) {
+	case DEV_SKU_4:
+		*arb_map_config = thrd_to_arb_map_6_me_sku;
+		break;
+	default:
+		dev_err(&GET_DEV(accel_dev),
+			"The configuration doesn't match any SKU");
+		*arb_map_config = NULL;
+	}
+}
+
+static u32 get_pf2vf_offset(u32 i)
+{
+	return ADF_C3XXX_PF2VF_OFFSET(i);
+}
+
+static u32 get_vintmsk_offset(u32 i)
+{
+	return ADF_C3XXX_VINTMSK_OFFSET(i);
+}
+
+static void adf_enable_error_correction(struct adf_accel_dev *accel_dev)
+{
+	struct adf_hw_device_data *hw_device = accel_dev->hw_device;
+	struct adf_bar *misc_bar = &GET_BARS(accel_dev)[ADF_C3XXX_PMISC_BAR];
+	void __iomem *csr = misc_bar->virt_addr;
+	unsigned int val, i;
+
+	/* Enable Accel Engine error detection & correction */
+	for (i = 0; i < hw_device->get_num_aes(hw_device); i++) {
+		val = ADF_CSR_RD(csr, ADF_C3XXX_AE_CTX_ENABLES(i));
+		val |= ADF_C3XXX_ENABLE_AE_ECC_ERR;
+		ADF_CSR_WR(csr, ADF_C3XXX_AE_CTX_ENABLES(i), val);
+		val = ADF_CSR_RD(csr, ADF_C3XXX_AE_MISC_CONTROL(i));
+		val |= ADF_C3XXX_ENABLE_AE_ECC_PARITY_CORR;
+		ADF_CSR_WR(csr, ADF_C3XXX_AE_MISC_CONTROL(i), val);
+	}
+
+	/* Enable shared memory error detection & correction */
+	for (i = 0; i < hw_device->get_num_accels(hw_device); i++) {
+		val = ADF_CSR_RD(csr, ADF_C3XXX_UERRSSMSH(i));
+		val |= ADF_C3XXX_ERRSSMSH_EN;
+		ADF_CSR_WR(csr, ADF_C3XXX_UERRSSMSH(i), val);
+		val = ADF_CSR_RD(csr, ADF_C3XXX_CERRSSMSH(i));
+		val |= ADF_C3XXX_ERRSSMSH_EN;
+		ADF_CSR_WR(csr, ADF_C3XXX_CERRSSMSH(i), val);
+	}
+}
+
+static void adf_enable_ints(struct adf_accel_dev *accel_dev)
+{
+	void __iomem *addr;
+
+	addr = (&GET_BARS(accel_dev)[ADF_C3XXX_PMISC_BAR])->virt_addr;
+
+	/* Enable bundle and misc interrupts */
+	ADF_CSR_WR(addr, ADF_C3XXX_SMIAPF0_MASK_OFFSET,
+		   ADF_C3XXX_SMIA0_MASK);
+	ADF_CSR_WR(addr, ADF_C3XXX_SMIAPF1_MASK_OFFSET,
+		   ADF_C3XXX_SMIA1_MASK);
+}
+
+static int adf_pf_enable_vf2pf_comms(struct adf_accel_dev *accel_dev)
+{
+	return 0;
+}
+
+void adf_init_hw_data_c3xxx(struct adf_hw_device_data *hw_data)
+{
+	hw_data->dev_class = &c3xxx_class;
+	hw_data->instance_id = c3xxx_class.instances++;
+	hw_data->num_banks = ADF_C3XXX_ETR_MAX_BANKS;
+	hw_data->num_accel = ADF_C3XXX_MAX_ACCELERATORS;
+	hw_data->num_logical_accel = 1;
+	hw_data->num_engines = ADF_C3XXX_MAX_ACCELENGINES;
+	hw_data->tx_rx_gap = ADF_C3XXX_RX_RINGS_OFFSET;
+	hw_data->tx_rings_mask = ADF_C3XXX_TX_RINGS_MASK;
+	hw_data->alloc_irq = adf_isr_resource_alloc;
+	hw_data->free_irq = adf_isr_resource_free;
+	hw_data->enable_error_correction = adf_enable_error_correction;
+	hw_data->get_accel_mask = get_accel_mask;
+	hw_data->get_ae_mask = get_ae_mask;
+	hw_data->get_num_accels = get_num_accels;
+	hw_data->get_num_aes = get_num_aes;
+	hw_data->get_sram_bar_id = get_sram_bar_id;
+	hw_data->get_etr_bar_id = get_etr_bar_id;
+	hw_data->get_misc_bar_id = get_misc_bar_id;
+	hw_data->get_pf2vf_offset = get_pf2vf_offset;
+	hw_data->get_vintmsk_offset = get_vintmsk_offset;
+	hw_data->get_sku = get_sku;
+	hw_data->fw_name = ADF_C3XXX_FW;
+	hw_data->fw_mmp_name = ADF_C3XXX_MMP;
+	hw_data->init_admin_comms = adf_init_admin_comms;
+	hw_data->exit_admin_comms = adf_exit_admin_comms;
+	hw_data->disable_iov = adf_disable_sriov;
+	hw_data->send_admin_init = adf_send_admin_init;
+	hw_data->init_arb = adf_init_arb;
+	hw_data->exit_arb = adf_exit_arb;
+	hw_data->get_arb_mapping = adf_get_arbiter_mapping;
+	hw_data->enable_ints = adf_enable_ints;
+	hw_data->enable_vf2pf_comms = adf_pf_enable_vf2pf_comms;
+	hw_data->min_iov_compat_ver = ADF_PFVF_COMPATIBILITY_VERSION;
+}
+
+void adf_clean_hw_data_c3xxx(struct adf_hw_device_data *hw_data)
+{
+	hw_data->dev_class->instances--;
+}
diff --git a/drivers/crypto/qat/qat_dh895xcc/adf_drv.h b/drivers/crypto/qat/qat_c3xxx/adf_c3xxx_hw_data.h
similarity index 60%
copy from drivers/crypto/qat/qat_dh895xcc/adf_drv.h
copy to drivers/crypto/qat/qat_c3xxx/adf_c3xxx_hw_data.h
index 85ff245..2f2681d 100644
--- a/drivers/crypto/qat/qat_dh895xcc/adf_drv.h
+++ b/drivers/crypto/qat/qat_c3xxx/adf_c3xxx_hw_data.h
@@ -44,15 +44,40 @@
   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */
-#ifndef ADF_DH895x_DRV_H_
-#define ADF_DH895x_DRV_H_
-#include <adf_accel_devices.h>
-#include <adf_transport.h>
+#ifndef ADF_C3XXX_HW_DATA_H_
+#define ADF_C3XXX_HW_DATA_H_
 
-void adf_init_hw_data_dh895xcc(struct adf_hw_device_data *hw_data);
-void adf_clean_hw_data_dh895xcc(struct adf_hw_device_data *hw_data);
-int adf_isr_resource_alloc(struct adf_accel_dev *accel_dev);
-void adf_isr_resource_free(struct adf_accel_dev *accel_dev);
-void adf_get_arbiter_mapping(struct adf_accel_dev *accel_dev,
-			     uint32_t const **arb_map_config);
+/* PCIe configuration space */
+#define ADF_C3XXX_PMISC_BAR 0
+#define ADF_C3XXX_ETR_BAR 1
+#define ADF_C3XXX_RX_RINGS_OFFSET 8
+#define ADF_C3XXX_TX_RINGS_MASK 0xFF
+#define ADF_C3XXX_MAX_ACCELERATORS 3
+#define ADF_C3XXX_MAX_ACCELENGINES 6
+#define ADF_C3XXX_ACCELERATORS_REG_OFFSET 16
+#define ADF_C3XXX_ACCELERATORS_MASK 0x3
+#define ADF_C3XXX_ACCELENGINES_MASK 0x3F
+#define ADF_C3XXX_ETR_MAX_BANKS 16
+#define ADF_C3XXX_SMIAPF0_MASK_OFFSET (0x3A000 + 0x28)
+#define ADF_C3XXX_SMIAPF1_MASK_OFFSET (0x3A000 + 0x30)
+#define ADF_C3XXX_SMIA0_MASK 0xFFFF
+#define ADF_C3XXX_SMIA1_MASK 0x1
+/* Error detection and correction */
+#define ADF_C3XXX_AE_CTX_ENABLES(i) (i * 0x1000 + 0x20818)
+#define ADF_C3XXX_AE_MISC_CONTROL(i) (i * 0x1000 + 0x20960)
+#define ADF_C3XXX_ENABLE_AE_ECC_ERR BIT(28)
+#define ADF_C3XXX_ENABLE_AE_ECC_PARITY_CORR (BIT(24) | BIT(12))
+#define ADF_C3XXX_UERRSSMSH(i) (i * 0x4000 + 0x18)
+#define ADF_C3XXX_CERRSSMSH(i) (i * 0x4000 + 0x10)
+#define ADF_C3XXX_ERRSSMSH_EN BIT(3)
+
+#define ADF_C3XXX_PF2VF_OFFSET(i)	(0x3A000 + 0x280 + ((i) * 0x04))
+#define ADF_C3XXX_VINTMSK_OFFSET(i)	(0x3A000 + 0x200 + ((i) * 0x04))
+
+/* Firmware Binary */
+#define ADF_C3XXX_FW "qat_c3xxx.bin"
+#define ADF_C3XXX_MMP "qat_c3xxx_mmp.bin"
+
+void adf_init_hw_data_c3xxx(struct adf_hw_device_data *hw_data);
+void adf_clean_hw_data_c3xxx(struct adf_hw_device_data *hw_data);
 #endif
diff --git a/drivers/crypto/qat/qat_c3xxx/adf_drv.c b/drivers/crypto/qat/qat_c3xxx/adf_drv.c
new file mode 100644
index 0000000..e13bd08
--- /dev/null
+++ b/drivers/crypto/qat/qat_c3xxx/adf_drv.c
@@ -0,0 +1,335 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/fs.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <linux/platform_device.h>
+#include <linux/workqueue.h>
+#include <linux/io.h>
+#include <adf_accel_devices.h>
+#include <adf_common_drv.h>
+#include <adf_cfg.h>
+#include "adf_c3xxx_hw_data.h"
+
+#define ADF_SYSTEM_DEVICE(device_id) \
+	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, device_id)}
+
+static const struct pci_device_id adf_pci_tbl[] = {
+	ADF_SYSTEM_DEVICE(ADF_C3XXX_PCI_DEVICE_ID),
+	{0,}
+};
+MODULE_DEVICE_TABLE(pci, adf_pci_tbl);
+
+static int adf_probe(struct pci_dev *dev, const struct pci_device_id *ent);
+static void adf_remove(struct pci_dev *dev);
+
+static struct pci_driver adf_driver = {
+	.id_table = adf_pci_tbl,
+	.name = ADF_C3XXX_DEVICE_NAME,
+	.probe = adf_probe,
+	.remove = adf_remove,
+	.sriov_configure = adf_sriov_configure,
+};
+
+static void adf_cleanup_pci_dev(struct adf_accel_dev *accel_dev)
+{
+	pci_release_regions(accel_dev->accel_pci_dev.pci_dev);
+	pci_disable_device(accel_dev->accel_pci_dev.pci_dev);
+}
+
+static void adf_cleanup_accel(struct adf_accel_dev *accel_dev)
+{
+	struct adf_accel_pci *accel_pci_dev = &accel_dev->accel_pci_dev;
+	int i;
+
+	for (i = 0; i < ADF_PCI_MAX_BARS; i++) {
+		struct adf_bar *bar = &accel_pci_dev->pci_bars[i];
+
+		if (bar->virt_addr)
+			pci_iounmap(accel_pci_dev->pci_dev, bar->virt_addr);
+	}
+
+	if (accel_dev->hw_device) {
+		switch (accel_pci_dev->pci_dev->device) {
+		case ADF_C3XXX_PCI_DEVICE_ID:
+			adf_clean_hw_data_c3xxx(accel_dev->hw_device);
+			break;
+		default:
+			break;
+		}
+		kfree(accel_dev->hw_device);
+		accel_dev->hw_device = NULL;
+	}
+	adf_cfg_dev_remove(accel_dev);
+	debugfs_remove(accel_dev->debugfs_dir);
+	adf_devmgr_rm_dev(accel_dev, NULL);
+}
+
+static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
+{
+	struct adf_accel_dev *accel_dev;
+	struct adf_accel_pci *accel_pci_dev;
+	struct adf_hw_device_data *hw_data;
+	char name[ADF_DEVICE_NAME_LENGTH];
+	unsigned int i, bar_nr;
+	int ret, bar_mask;
+
+	switch (ent->device) {
+	case ADF_C3XXX_PCI_DEVICE_ID:
+		break;
+	default:
+		dev_err(&pdev->dev, "Invalid device 0x%x.\n", ent->device);
+		return -ENODEV;
+	}
+
+	if (num_possible_nodes() > 1 && dev_to_node(&pdev->dev) < 0) {
+		/* If the accelerator is connected to a node with no memory
+		 * there is no point in using the accelerator since the remote
+		 * memory transaction will be very slow. */
+		dev_err(&pdev->dev, "Invalid NUMA configuration.\n");
+		return -EINVAL;
+	}
+
+	accel_dev = kzalloc_node(sizeof(*accel_dev), GFP_KERNEL,
+				 dev_to_node(&pdev->dev));
+	if (!accel_dev)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&accel_dev->crypto_list);
+	accel_pci_dev = &accel_dev->accel_pci_dev;
+	accel_pci_dev->pci_dev = pdev;
+
+	/* Add accel device to accel table.
+	 * This should be called before adf_cleanup_accel is called */
+	if (adf_devmgr_add_dev(accel_dev, NULL)) {
+		dev_err(&pdev->dev, "Failed to add new accelerator device.\n");
+		kfree(accel_dev);
+		return -EFAULT;
+	}
+
+	accel_dev->owner = THIS_MODULE;
+	/* Allocate and configure device configuration structure */
+	hw_data = kzalloc_node(sizeof(*hw_data), GFP_KERNEL,
+			       dev_to_node(&pdev->dev));
+	if (!hw_data) {
+		ret = -ENOMEM;
+		goto out_err;
+	}
+
+	accel_dev->hw_device = hw_data;
+	adf_init_hw_data_c3xxx(accel_dev->hw_device);
+	pci_read_config_byte(pdev, PCI_REVISION_ID, &accel_pci_dev->revid);
+	pci_read_config_dword(pdev, ADF_DEVICE_FUSECTL_OFFSET,
+			      &hw_data->fuses);
+
+	/* Get Accelerators and Accelerators Engines masks */
+	hw_data->accel_mask = hw_data->get_accel_mask(hw_data->fuses);
+	hw_data->ae_mask = hw_data->get_ae_mask(hw_data->fuses);
+	accel_pci_dev->sku = hw_data->get_sku(hw_data);
+	/* If the device has no acceleration engines then ignore it. */
+	if (!hw_data->accel_mask || !hw_data->ae_mask ||
+	    ((~hw_data->ae_mask) & 0x01)) {
+		dev_err(&pdev->dev, "No acceleration units found");
+		ret = -EFAULT;
+		goto out_err;
+	}
+
+	/* Create dev top level debugfs entry */
+	snprintf(name, sizeof(name), "%s%s_%02x:%02d.%02d",
+		 ADF_DEVICE_NAME_PREFIX, hw_data->dev_class->name,
+		 pdev->bus->number, PCI_SLOT(pdev->devfn),
+		 PCI_FUNC(pdev->devfn));
+
+	accel_dev->debugfs_dir = debugfs_create_dir(name, NULL);
+	if (!accel_dev->debugfs_dir) {
+		dev_err(&pdev->dev, "Could not create debugfs dir %s\n", name);
+		ret = -EINVAL;
+		goto out_err;
+	}
+
+	/* Create device configuration table */
+	ret = adf_cfg_dev_add(accel_dev);
+	if (ret)
+		goto out_err;
+
+	/* enable PCI device */
+	if (pci_enable_device(pdev)) {
+		ret = -EFAULT;
+		goto out_err;
+	}
+
+	/* set dma identifier */
+	if (pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) {
+		if ((pci_set_dma_mask(pdev, DMA_BIT_MASK(32)))) {
+			dev_err(&pdev->dev, "No usable DMA configuration\n");
+			ret = -EFAULT;
+			goto out_err_disable;
+		} else {
+			pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
+		}
+
+	} else {
+		pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
+	}
+
+	if (pci_request_regions(pdev, ADF_C3XXX_DEVICE_NAME)) {
+		ret = -EFAULT;
+		goto out_err_disable;
+	}
+
+	/* Read accelerator capabilities mask */
+	pci_read_config_dword(pdev, ADF_DEVICE_LEGFUSE_OFFSET,
+			      &hw_data->accel_capabilities_mask);
+
+	/* Find and map all the device's BARS */
+	i = 0;
+	bar_mask = pci_select_bars(pdev, IORESOURCE_MEM);
+	for_each_set_bit(bar_nr, (const unsigned long *)&bar_mask,
+			 ADF_PCI_MAX_BARS * 2) {
+		struct adf_bar *bar = &accel_pci_dev->pci_bars[i++];
+
+		bar->base_addr = pci_resource_start(pdev, bar_nr);
+		if (!bar->base_addr)
+			break;
+		bar->size = pci_resource_len(pdev, bar_nr);
+		bar->virt_addr = pci_iomap(accel_pci_dev->pci_dev, bar_nr, 0);
+		if (!bar->virt_addr) {
+			dev_err(&pdev->dev, "Failed to map BAR %d\n", bar_nr);
+			ret = -EFAULT;
+			goto out_err_free_reg;
+		}
+	}
+	pci_set_master(pdev);
+
+	if (adf_enable_aer(accel_dev, &adf_driver)) {
+		dev_err(&pdev->dev, "Failed to enable aer\n");
+		ret = -EFAULT;
+		goto out_err_free_reg;
+	}
+
+	if (pci_save_state(pdev)) {
+		dev_err(&pdev->dev, "Failed to save pci state\n");
+		ret = -ENOMEM;
+		goto out_err_free_reg;
+	}
+
+	ret = qat_crypto_dev_config(accel_dev);
+	if (ret)
+		goto out_err_free_reg;
+
+	ret = adf_dev_init(accel_dev);
+	if (ret)
+		goto out_err_dev_shutdown;
+
+	ret = adf_dev_start(accel_dev);
+	if (ret)
+		goto out_err_dev_stop;
+
+	return ret;
+
+out_err_dev_stop:
+	adf_dev_stop(accel_dev);
+out_err_dev_shutdown:
+	adf_dev_shutdown(accel_dev);
+out_err_free_reg:
+	pci_release_regions(accel_pci_dev->pci_dev);
+out_err_disable:
+	pci_disable_device(accel_pci_dev->pci_dev);
+out_err:
+	adf_cleanup_accel(accel_dev);
+	kfree(accel_dev);
+	return ret;
+}
+
+static void adf_remove(struct pci_dev *pdev)
+{
+	struct adf_accel_dev *accel_dev = adf_devmgr_pci_to_accel_dev(pdev);
+
+	if (!accel_dev) {
+		pr_err("QAT: Driver removal failed\n");
+		return;
+	}
+	if (adf_dev_stop(accel_dev))
+		dev_err(&GET_DEV(accel_dev), "Failed to stop QAT accel dev\n");
+
+	adf_dev_shutdown(accel_dev);
+	adf_disable_aer(accel_dev);
+	adf_cleanup_accel(accel_dev);
+	adf_cleanup_pci_dev(accel_dev);
+	kfree(accel_dev);
+}
+
+static int __init adfdrv_init(void)
+{
+	request_module("intel_qat");
+
+	if (pci_register_driver(&adf_driver)) {
+		pr_err("QAT: Driver initialization failed\n");
+		return -EFAULT;
+	}
+	return 0;
+}
+
+static void __exit adfdrv_release(void)
+{
+	pci_unregister_driver(&adf_driver);
+}
+
+module_init(adfdrv_init);
+module_exit(adfdrv_release);
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_AUTHOR("Intel");
+MODULE_DESCRIPTION("Intel(R) QuickAssist Technology");
+MODULE_VERSION(ADF_DRV_VERSION);
diff --git a/drivers/crypto/qat/qat_c3xxxvf/Makefile b/drivers/crypto/qat/qat_c3xxxvf/Makefile
new file mode 100644
index 0000000..16d178e
--- /dev/null
+++ b/drivers/crypto/qat/qat_c3xxxvf/Makefile
@@ -0,0 +1,3 @@
+ccflags-y := -I$(src)/../qat_common
+obj-$(CONFIG_CRYPTO_DEV_QAT_C3XXXVF) += qat_c3xxxvf.o
+qat_c3xxxvf-objs := adf_drv.o adf_c3xxxvf_hw_data.o
diff --git a/drivers/crypto/qat/qat_c3xxxvf/adf_c3xxxvf_hw_data.c b/drivers/crypto/qat/qat_c3xxxvf/adf_c3xxxvf_hw_data.c
new file mode 100644
index 0000000..1af321c
--- /dev/null
+++ b/drivers/crypto/qat/qat_c3xxxvf/adf_c3xxxvf_hw_data.c
@@ -0,0 +1,173 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2015 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2015 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#include <adf_accel_devices.h>
+#include <adf_pf2vf_msg.h>
+#include <adf_common_drv.h>
+#include "adf_c3xxxvf_hw_data.h"
+
+static struct adf_hw_device_class c3xxxiov_class = {
+	.name = ADF_C3XXXVF_DEVICE_NAME,
+	.type = DEV_C3XXXVF,
+	.instances = 0
+};
+
+static u32 get_accel_mask(u32 fuse)
+{
+	return ADF_C3XXXIOV_ACCELERATORS_MASK;
+}
+
+static u32 get_ae_mask(u32 fuse)
+{
+	return ADF_C3XXXIOV_ACCELENGINES_MASK;
+}
+
+static u32 get_num_accels(struct adf_hw_device_data *self)
+{
+	return ADF_C3XXXIOV_MAX_ACCELERATORS;
+}
+
+static u32 get_num_aes(struct adf_hw_device_data *self)
+{
+	return ADF_C3XXXIOV_MAX_ACCELENGINES;
+}
+
+static u32 get_misc_bar_id(struct adf_hw_device_data *self)
+{
+	return ADF_C3XXXIOV_PMISC_BAR;
+}
+
+static u32 get_etr_bar_id(struct adf_hw_device_data *self)
+{
+	return ADF_C3XXXIOV_ETR_BAR;
+}
+
+static enum dev_sku_info get_sku(struct adf_hw_device_data *self)
+{
+	return DEV_SKU_VF;
+}
+
+static u32 get_pf2vf_offset(u32 i)
+{
+	return ADF_C3XXXIOV_PF2VF_OFFSET;
+}
+
+static u32 get_vintmsk_offset(u32 i)
+{
+	return ADF_C3XXXIOV_VINTMSK_OFFSET;
+}
+
+static int adf_vf_int_noop(struct adf_accel_dev *accel_dev)
+{
+	return 0;
+}
+
+static void adf_vf_void_noop(struct adf_accel_dev *accel_dev)
+{
+}
+
+static int adf_vf2pf_init(struct adf_accel_dev *accel_dev)
+{
+	u32 msg = (ADF_VF2PF_MSGORIGIN_SYSTEM |
+		(ADF_VF2PF_MSGTYPE_INIT << ADF_VF2PF_MSGTYPE_SHIFT));
+
+	if (adf_iov_putmsg(accel_dev, msg, 0)) {
+		dev_err(&GET_DEV(accel_dev),
+			"Failed to send Init event to PF\n");
+		return -EFAULT;
+	}
+	return 0;
+}
+
+static void adf_vf2pf_shutdown(struct adf_accel_dev *accel_dev)
+{
+	u32 msg = (ADF_VF2PF_MSGORIGIN_SYSTEM |
+	    (ADF_VF2PF_MSGTYPE_SHUTDOWN << ADF_VF2PF_MSGTYPE_SHIFT));
+
+	if (adf_iov_putmsg(accel_dev, msg, 0))
+		dev_err(&GET_DEV(accel_dev),
+			"Failed to send Shutdown event to PF\n");
+}
+
+void adf_init_hw_data_c3xxxiov(struct adf_hw_device_data *hw_data)
+{
+	hw_data->dev_class = &c3xxxiov_class;
+	hw_data->num_banks = ADF_C3XXXIOV_ETR_MAX_BANKS;
+	hw_data->num_accel = ADF_C3XXXIOV_MAX_ACCELERATORS;
+	hw_data->num_logical_accel = 1;
+	hw_data->num_engines = ADF_C3XXXIOV_MAX_ACCELENGINES;
+	hw_data->tx_rx_gap = ADF_C3XXXIOV_RX_RINGS_OFFSET;
+	hw_data->tx_rings_mask = ADF_C3XXXIOV_TX_RINGS_MASK;
+	hw_data->alloc_irq = adf_vf_isr_resource_alloc;
+	hw_data->free_irq = adf_vf_isr_resource_free;
+	hw_data->enable_error_correction = adf_vf_void_noop;
+	hw_data->init_admin_comms = adf_vf_int_noop;
+	hw_data->exit_admin_comms = adf_vf_void_noop;
+	hw_data->send_admin_init = adf_vf2pf_init;
+	hw_data->init_arb = adf_vf_int_noop;
+	hw_data->exit_arb = adf_vf_void_noop;
+	hw_data->disable_iov = adf_vf2pf_shutdown;
+	hw_data->get_accel_mask = get_accel_mask;
+	hw_data->get_ae_mask = get_ae_mask;
+	hw_data->get_num_accels = get_num_accels;
+	hw_data->get_num_aes = get_num_aes;
+	hw_data->get_etr_bar_id = get_etr_bar_id;
+	hw_data->get_misc_bar_id = get_misc_bar_id;
+	hw_data->get_pf2vf_offset = get_pf2vf_offset;
+	hw_data->get_vintmsk_offset = get_vintmsk_offset;
+	hw_data->get_sku = get_sku;
+	hw_data->enable_ints = adf_vf_void_noop;
+	hw_data->enable_vf2pf_comms = adf_enable_vf2pf_comms;
+	hw_data->min_iov_compat_ver = ADF_PFVF_COMPATIBILITY_VERSION;
+	hw_data->dev_class->instances++;
+	adf_devmgr_update_class_index(hw_data);
+}
+
+void adf_clean_hw_data_c3xxxiov(struct adf_hw_device_data *hw_data)
+{
+	hw_data->dev_class->instances--;
+	adf_devmgr_update_class_index(hw_data);
+}
diff --git a/drivers/crypto/qat/qat_dh895xcc/adf_drv.h b/drivers/crypto/qat/qat_c3xxxvf/adf_c3xxxvf_hw_data.h
similarity index 75%
rename from drivers/crypto/qat/qat_dh895xcc/adf_drv.h
rename to drivers/crypto/qat/qat_c3xxxvf/adf_c3xxxvf_hw_data.h
index 85ff245..934f216 100644
--- a/drivers/crypto/qat/qat_dh895xcc/adf_drv.h
+++ b/drivers/crypto/qat/qat_c3xxxvf/adf_c3xxxvf_hw_data.h
@@ -3,7 +3,7 @@
   redistributing this file, you may do so under either license.
 
   GPL LICENSE SUMMARY
-  Copyright(c) 2014 Intel Corporation.
+  Copyright(c) 2015 Intel Corporation.
   This program is free software; you can redistribute it and/or modify
   it under the terms of version 2 of the GNU General Public License as
   published by the Free Software Foundation.
@@ -17,7 +17,7 @@
   qat-linux@intel.com
 
   BSD LICENSE
-  Copyright(c) 2014 Intel Corporation.
+  Copyright(c) 2015 Intel Corporation.
   Redistribution and use in source and binary forms, with or without
   modification, are permitted provided that the following conditions
   are met:
@@ -44,15 +44,21 @@
   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */
-#ifndef ADF_DH895x_DRV_H_
-#define ADF_DH895x_DRV_H_
-#include <adf_accel_devices.h>
-#include <adf_transport.h>
+#ifndef ADF_C3XXXVF_HW_DATA_H_
+#define ADF_C3XXXVF_HW_DATA_H_
 
-void adf_init_hw_data_dh895xcc(struct adf_hw_device_data *hw_data);
-void adf_clean_hw_data_dh895xcc(struct adf_hw_device_data *hw_data);
-int adf_isr_resource_alloc(struct adf_accel_dev *accel_dev);
-void adf_isr_resource_free(struct adf_accel_dev *accel_dev);
-void adf_get_arbiter_mapping(struct adf_accel_dev *accel_dev,
-			     uint32_t const **arb_map_config);
+#define ADF_C3XXXIOV_PMISC_BAR 1
+#define ADF_C3XXXIOV_ACCELERATORS_MASK 0x1
+#define ADF_C3XXXIOV_ACCELENGINES_MASK 0x1
+#define ADF_C3XXXIOV_MAX_ACCELERATORS 1
+#define ADF_C3XXXIOV_MAX_ACCELENGINES 1
+#define ADF_C3XXXIOV_RX_RINGS_OFFSET 8
+#define ADF_C3XXXIOV_TX_RINGS_MASK 0xFF
+#define ADF_C3XXXIOV_ETR_BAR 0
+#define ADF_C3XXXIOV_ETR_MAX_BANKS 1
+#define ADF_C3XXXIOV_PF2VF_OFFSET	0x200
+#define ADF_C3XXXIOV_VINTMSK_OFFSET	0x208
+
+void adf_init_hw_data_c3xxxiov(struct adf_hw_device_data *hw_data);
+void adf_clean_hw_data_c3xxxiov(struct adf_hw_device_data *hw_data);
 #endif
diff --git a/drivers/crypto/qat/qat_c3xxxvf/adf_drv.c b/drivers/crypto/qat/qat_c3xxxvf/adf_drv.c
new file mode 100644
index 0000000..1ac4ae9
--- /dev/null
+++ b/drivers/crypto/qat/qat_c3xxxvf/adf_drv.c
@@ -0,0 +1,305 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/fs.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <linux/platform_device.h>
+#include <linux/workqueue.h>
+#include <linux/io.h>
+#include <adf_accel_devices.h>
+#include <adf_common_drv.h>
+#include <adf_cfg.h>
+#include "adf_c3xxxvf_hw_data.h"
+
+#define ADF_SYSTEM_DEVICE(device_id) \
+	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, device_id)}
+
+static const struct pci_device_id adf_pci_tbl[] = {
+	ADF_SYSTEM_DEVICE(ADF_C3XXXIOV_PCI_DEVICE_ID),
+	{0,}
+};
+MODULE_DEVICE_TABLE(pci, adf_pci_tbl);
+
+static int adf_probe(struct pci_dev *dev, const struct pci_device_id *ent);
+static void adf_remove(struct pci_dev *dev);
+
+static struct pci_driver adf_driver = {
+	.id_table = adf_pci_tbl,
+	.name = ADF_C3XXXVF_DEVICE_NAME,
+	.probe = adf_probe,
+	.remove = adf_remove,
+};
+
+static void adf_cleanup_pci_dev(struct adf_accel_dev *accel_dev)
+{
+	pci_release_regions(accel_dev->accel_pci_dev.pci_dev);
+	pci_disable_device(accel_dev->accel_pci_dev.pci_dev);
+}
+
+static void adf_cleanup_accel(struct adf_accel_dev *accel_dev)
+{
+	struct adf_accel_pci *accel_pci_dev = &accel_dev->accel_pci_dev;
+	struct adf_accel_dev *pf;
+	int i;
+
+	for (i = 0; i < ADF_PCI_MAX_BARS; i++) {
+		struct adf_bar *bar = &accel_pci_dev->pci_bars[i];
+
+		if (bar->virt_addr)
+			pci_iounmap(accel_pci_dev->pci_dev, bar->virt_addr);
+	}
+
+	if (accel_dev->hw_device) {
+		switch (accel_pci_dev->pci_dev->device) {
+		case ADF_C3XXXIOV_PCI_DEVICE_ID:
+			adf_clean_hw_data_c3xxxiov(accel_dev->hw_device);
+			break;
+		default:
+			break;
+		}
+		kfree(accel_dev->hw_device);
+		accel_dev->hw_device = NULL;
+	}
+	adf_cfg_dev_remove(accel_dev);
+	debugfs_remove(accel_dev->debugfs_dir);
+	pf = adf_devmgr_pci_to_accel_dev(accel_pci_dev->pci_dev->physfn);
+	adf_devmgr_rm_dev(accel_dev, pf);
+}
+
+static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
+{
+	struct adf_accel_dev *accel_dev;
+	struct adf_accel_dev *pf;
+	struct adf_accel_pci *accel_pci_dev;
+	struct adf_hw_device_data *hw_data;
+	char name[ADF_DEVICE_NAME_LENGTH];
+	unsigned int i, bar_nr;
+	int ret, bar_mask;
+
+	switch (ent->device) {
+	case ADF_C3XXXIOV_PCI_DEVICE_ID:
+		break;
+	default:
+		dev_err(&pdev->dev, "Invalid device 0x%x.\n", ent->device);
+		return -ENODEV;
+	}
+
+	accel_dev = kzalloc_node(sizeof(*accel_dev), GFP_KERNEL,
+				 dev_to_node(&pdev->dev));
+	if (!accel_dev)
+		return -ENOMEM;
+
+	accel_dev->is_vf = true;
+	pf = adf_devmgr_pci_to_accel_dev(pdev->physfn);
+	accel_pci_dev = &accel_dev->accel_pci_dev;
+	accel_pci_dev->pci_dev = pdev;
+
+	/* Add accel device to accel table */
+	if (adf_devmgr_add_dev(accel_dev, pf)) {
+		dev_err(&pdev->dev, "Failed to add new accelerator device.\n");
+		kfree(accel_dev);
+		return -EFAULT;
+	}
+	INIT_LIST_HEAD(&accel_dev->crypto_list);
+
+	accel_dev->owner = THIS_MODULE;
+	/* Allocate and configure device configuration structure */
+	hw_data = kzalloc_node(sizeof(*hw_data), GFP_KERNEL,
+			       dev_to_node(&pdev->dev));
+	if (!hw_data) {
+		ret = -ENOMEM;
+		goto out_err;
+	}
+	accel_dev->hw_device = hw_data;
+	adf_init_hw_data_c3xxxiov(accel_dev->hw_device);
+
+	/* Get Accelerators and Accelerators Engines masks */
+	hw_data->accel_mask = hw_data->get_accel_mask(hw_data->fuses);
+	hw_data->ae_mask = hw_data->get_ae_mask(hw_data->fuses);
+	accel_pci_dev->sku = hw_data->get_sku(hw_data);
+
+	/* Create dev top level debugfs entry */
+	snprintf(name, sizeof(name), "%s%s_%02x:%02d.%02d",
+		 ADF_DEVICE_NAME_PREFIX, hw_data->dev_class->name,
+		 pdev->bus->number, PCI_SLOT(pdev->devfn),
+		 PCI_FUNC(pdev->devfn));
+
+	accel_dev->debugfs_dir = debugfs_create_dir(name, NULL);
+	if (!accel_dev->debugfs_dir) {
+		dev_err(&pdev->dev, "Could not create debugfs dir %s\n", name);
+		ret = -EINVAL;
+		goto out_err;
+	}
+
+	/* Create device configuration table */
+	ret = adf_cfg_dev_add(accel_dev);
+	if (ret)
+		goto out_err;
+
+	/* enable PCI device */
+	if (pci_enable_device(pdev)) {
+		ret = -EFAULT;
+		goto out_err;
+	}
+
+	/* set dma identifier */
+	if (pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) {
+		if ((pci_set_dma_mask(pdev, DMA_BIT_MASK(32)))) {
+			dev_err(&pdev->dev, "No usable DMA configuration\n");
+			ret = -EFAULT;
+			goto out_err_disable;
+		} else {
+			pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
+		}
+
+	} else {
+		pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
+	}
+
+	if (pci_request_regions(pdev, ADF_C3XXXVF_DEVICE_NAME)) {
+		ret = -EFAULT;
+		goto out_err_disable;
+	}
+
+	/* Find and map all the device's BARS */
+	i = 0;
+	bar_mask = pci_select_bars(pdev, IORESOURCE_MEM);
+	for_each_set_bit(bar_nr, (const unsigned long *)&bar_mask,
+			 ADF_PCI_MAX_BARS * 2) {
+		struct adf_bar *bar = &accel_pci_dev->pci_bars[i++];
+
+		bar->base_addr = pci_resource_start(pdev, bar_nr);
+		if (!bar->base_addr)
+			break;
+		bar->size = pci_resource_len(pdev, bar_nr);
+		bar->virt_addr = pci_iomap(accel_pci_dev->pci_dev, bar_nr, 0);
+		if (!bar->virt_addr) {
+			dev_err(&pdev->dev, "Failed to map BAR %d\n", bar_nr);
+			ret = -EFAULT;
+			goto out_err_free_reg;
+		}
+	}
+	pci_set_master(pdev);
+	/* Completion for VF2PF request/response message exchange */
+	init_completion(&accel_dev->vf.iov_msg_completion);
+
+	ret = qat_crypto_dev_config(accel_dev);
+	if (ret)
+		goto out_err_free_reg;
+
+	ret = adf_dev_init(accel_dev);
+	if (ret)
+		goto out_err_dev_shutdown;
+
+	ret = adf_dev_start(accel_dev);
+	if (ret)
+		goto out_err_dev_stop;
+
+	return ret;
+
+out_err_dev_stop:
+	adf_dev_stop(accel_dev);
+out_err_dev_shutdown:
+	adf_dev_shutdown(accel_dev);
+out_err_free_reg:
+	pci_release_regions(accel_pci_dev->pci_dev);
+out_err_disable:
+	pci_disable_device(accel_pci_dev->pci_dev);
+out_err:
+	adf_cleanup_accel(accel_dev);
+	kfree(accel_dev);
+	return ret;
+}
+
+static void adf_remove(struct pci_dev *pdev)
+{
+	struct adf_accel_dev *accel_dev = adf_devmgr_pci_to_accel_dev(pdev);
+
+	if (!accel_dev) {
+		pr_err("QAT: Driver removal failed\n");
+		return;
+	}
+	if (adf_dev_stop(accel_dev))
+		dev_err(&GET_DEV(accel_dev), "Failed to stop QAT accel dev\n");
+
+	adf_dev_shutdown(accel_dev);
+	adf_cleanup_accel(accel_dev);
+	adf_cleanup_pci_dev(accel_dev);
+	kfree(accel_dev);
+}
+
+static int __init adfdrv_init(void)
+{
+	request_module("intel_qat");
+
+	if (pci_register_driver(&adf_driver)) {
+		pr_err("QAT: Driver initialization failed\n");
+		return -EFAULT;
+	}
+	return 0;
+}
+
+static void __exit adfdrv_release(void)
+{
+	pci_unregister_driver(&adf_driver);
+	adf_clean_vf_map(true);
+}
+
+module_init(adfdrv_init);
+module_exit(adfdrv_release);
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_AUTHOR("Intel");
+MODULE_DESCRIPTION("Intel(R) QuickAssist Technology");
+MODULE_VERSION(ADF_DRV_VERSION);
diff --git a/drivers/crypto/qat/qat_c62x/Makefile b/drivers/crypto/qat/qat_c62x/Makefile
new file mode 100644
index 0000000..bd75ace
--- /dev/null
+++ b/drivers/crypto/qat/qat_c62x/Makefile
@@ -0,0 +1,3 @@
+ccflags-y := -I$(src)/../qat_common
+obj-$(CONFIG_CRYPTO_DEV_QAT_C62X) += qat_c62x.o
+qat_c62x-objs := adf_drv.o adf_c62x_hw_data.o
diff --git a/drivers/crypto/qat/qat_c62x/adf_c62x_hw_data.c b/drivers/crypto/qat/qat_c62x/adf_c62x_hw_data.c
new file mode 100644
index 0000000..879e04c
--- /dev/null
+++ b/drivers/crypto/qat/qat_c62x/adf_c62x_hw_data.c
@@ -0,0 +1,248 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+	* Redistributions of source code must retain the above copyright
+	  notice, this list of conditions and the following disclaimer.
+	* Redistributions in binary form must reproduce the above copyright
+	  notice, this list of conditions and the following disclaimer in
+	  the documentation and/or other materials provided with the
+	  distribution.
+	* Neither the name of Intel Corporation nor the names of its
+	  contributors may be used to endorse or promote products derived
+	  from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#include <adf_accel_devices.h>
+#include <adf_common_drv.h>
+#include <adf_pf2vf_msg.h>
+#include "adf_c62x_hw_data.h"
+
+/* Worker thread to service arbiter mappings based on dev SKUs */
+static const u32 thrd_to_arb_map_8_me_sku[] = {
+	0x12222AAA, 0x11222AAA, 0x12222AAA, 0x11222AAA, 0x12222AAA,
+	0x11222AAA, 0x12222AAA, 0x11222AAA, 0, 0
+};
+
+static const u32 thrd_to_arb_map_10_me_sku[] = {
+	0x12222AAA, 0x11222AAA, 0x12222AAA, 0x11222AAA, 0x12222AAA,
+	0x11222AAA, 0x12222AAA, 0x11222AAA, 0x12222AAA, 0x11222AAA
+};
+
+static struct adf_hw_device_class c62x_class = {
+	.name = ADF_C62X_DEVICE_NAME,
+	.type = DEV_C62X,
+	.instances = 0
+};
+
+static u32 get_accel_mask(u32 fuse)
+{
+	return (~fuse) >> ADF_C62X_ACCELERATORS_REG_OFFSET &
+			  ADF_C62X_ACCELERATORS_MASK;
+}
+
+static u32 get_ae_mask(u32 fuse)
+{
+	return (~fuse) & ADF_C62X_ACCELENGINES_MASK;
+}
+
+static u32 get_num_accels(struct adf_hw_device_data *self)
+{
+	u32 i, ctr = 0;
+
+	if (!self || !self->accel_mask)
+		return 0;
+
+	for (i = 0; i < ADF_C62X_MAX_ACCELERATORS; i++) {
+		if (self->accel_mask & (1 << i))
+			ctr++;
+	}
+	return ctr;
+}
+
+static u32 get_num_aes(struct adf_hw_device_data *self)
+{
+	u32 i, ctr = 0;
+
+	if (!self || !self->ae_mask)
+		return 0;
+
+	for (i = 0; i < ADF_C62X_MAX_ACCELENGINES; i++) {
+		if (self->ae_mask & (1 << i))
+			ctr++;
+	}
+	return ctr;
+}
+
+static u32 get_misc_bar_id(struct adf_hw_device_data *self)
+{
+	return ADF_C62X_PMISC_BAR;
+}
+
+static u32 get_etr_bar_id(struct adf_hw_device_data *self)
+{
+	return ADF_C62X_ETR_BAR;
+}
+
+static u32 get_sram_bar_id(struct adf_hw_device_data *self)
+{
+	return ADF_C62X_SRAM_BAR;
+}
+
+static enum dev_sku_info get_sku(struct adf_hw_device_data *self)
+{
+	int aes = get_num_aes(self);
+
+	if (aes == 8)
+		return DEV_SKU_2;
+	else if (aes == 10)
+		return DEV_SKU_4;
+
+	return DEV_SKU_UNKNOWN;
+}
+
+static void adf_get_arbiter_mapping(struct adf_accel_dev *accel_dev,
+				    u32 const **arb_map_config)
+{
+	switch (accel_dev->accel_pci_dev.sku) {
+	case DEV_SKU_2:
+		*arb_map_config = thrd_to_arb_map_8_me_sku;
+		break;
+	case DEV_SKU_4:
+		*arb_map_config = thrd_to_arb_map_10_me_sku;
+		break;
+	default:
+		dev_err(&GET_DEV(accel_dev),
+			"The configuration doesn't match any SKU");
+		*arb_map_config = NULL;
+	}
+}
+
+static u32 get_pf2vf_offset(u32 i)
+{
+	return ADF_C62X_PF2VF_OFFSET(i);
+}
+
+static u32 get_vintmsk_offset(u32 i)
+{
+	return ADF_C62X_VINTMSK_OFFSET(i);
+}
+
+static void adf_enable_error_correction(struct adf_accel_dev *accel_dev)
+{
+	struct adf_hw_device_data *hw_device = accel_dev->hw_device;
+	struct adf_bar *misc_bar = &GET_BARS(accel_dev)[ADF_C62X_PMISC_BAR];
+	void __iomem *csr = misc_bar->virt_addr;
+	unsigned int val, i;
+
+	/* Enable Accel Engine error detection & correction */
+	for (i = 0; i < hw_device->get_num_aes(hw_device); i++) {
+		val = ADF_CSR_RD(csr, ADF_C62X_AE_CTX_ENABLES(i));
+		val |= ADF_C62X_ENABLE_AE_ECC_ERR;
+		ADF_CSR_WR(csr, ADF_C62X_AE_CTX_ENABLES(i), val);
+		val = ADF_CSR_RD(csr, ADF_C62X_AE_MISC_CONTROL(i));
+		val |= ADF_C62X_ENABLE_AE_ECC_PARITY_CORR;
+		ADF_CSR_WR(csr, ADF_C62X_AE_MISC_CONTROL(i), val);
+	}
+
+	/* Enable shared memory error detection & correction */
+	for (i = 0; i < hw_device->get_num_accels(hw_device); i++) {
+		val = ADF_CSR_RD(csr, ADF_C62X_UERRSSMSH(i));
+		val |= ADF_C62X_ERRSSMSH_EN;
+		ADF_CSR_WR(csr, ADF_C62X_UERRSSMSH(i), val);
+		val = ADF_CSR_RD(csr, ADF_C62X_CERRSSMSH(i));
+		val |= ADF_C62X_ERRSSMSH_EN;
+		ADF_CSR_WR(csr, ADF_C62X_CERRSSMSH(i), val);
+	}
+}
+
+static void adf_enable_ints(struct adf_accel_dev *accel_dev)
+{
+	void __iomem *addr;
+
+	addr = (&GET_BARS(accel_dev)[ADF_C62X_PMISC_BAR])->virt_addr;
+
+	/* Enable bundle and misc interrupts */
+	ADF_CSR_WR(addr, ADF_C62X_SMIAPF0_MASK_OFFSET,
+		   ADF_C62X_SMIA0_MASK);
+	ADF_CSR_WR(addr, ADF_C62X_SMIAPF1_MASK_OFFSET,
+		   ADF_C62X_SMIA1_MASK);
+}
+
+static int adf_pf_enable_vf2pf_comms(struct adf_accel_dev *accel_dev)
+{
+	return 0;
+}
+
+void adf_init_hw_data_c62x(struct adf_hw_device_data *hw_data)
+{
+	hw_data->dev_class = &c62x_class;
+	hw_data->instance_id = c62x_class.instances++;
+	hw_data->num_banks = ADF_C62X_ETR_MAX_BANKS;
+	hw_data->num_accel = ADF_C62X_MAX_ACCELERATORS;
+	hw_data->num_logical_accel = 1;
+	hw_data->num_engines = ADF_C62X_MAX_ACCELENGINES;
+	hw_data->tx_rx_gap = ADF_C62X_RX_RINGS_OFFSET;
+	hw_data->tx_rings_mask = ADF_C62X_TX_RINGS_MASK;
+	hw_data->alloc_irq = adf_isr_resource_alloc;
+	hw_data->free_irq = adf_isr_resource_free;
+	hw_data->enable_error_correction = adf_enable_error_correction;
+	hw_data->get_accel_mask = get_accel_mask;
+	hw_data->get_ae_mask = get_ae_mask;
+	hw_data->get_num_accels = get_num_accels;
+	hw_data->get_num_aes = get_num_aes;
+	hw_data->get_sram_bar_id = get_sram_bar_id;
+	hw_data->get_etr_bar_id = get_etr_bar_id;
+	hw_data->get_misc_bar_id = get_misc_bar_id;
+	hw_data->get_pf2vf_offset = get_pf2vf_offset;
+	hw_data->get_vintmsk_offset = get_vintmsk_offset;
+	hw_data->get_sku = get_sku;
+	hw_data->fw_name = ADF_C62X_FW;
+	hw_data->fw_mmp_name = ADF_C62X_MMP;
+	hw_data->init_admin_comms = adf_init_admin_comms;
+	hw_data->exit_admin_comms = adf_exit_admin_comms;
+	hw_data->disable_iov = adf_disable_sriov;
+	hw_data->send_admin_init = adf_send_admin_init;
+	hw_data->init_arb = adf_init_arb;
+	hw_data->exit_arb = adf_exit_arb;
+	hw_data->get_arb_mapping = adf_get_arbiter_mapping;
+	hw_data->enable_ints = adf_enable_ints;
+	hw_data->enable_vf2pf_comms = adf_pf_enable_vf2pf_comms;
+	hw_data->min_iov_compat_ver = ADF_PFVF_COMPATIBILITY_VERSION;
+}
+
+void adf_clean_hw_data_c62x(struct adf_hw_device_data *hw_data)
+{
+	hw_data->dev_class->instances--;
+}
diff --git a/drivers/crypto/qat/qat_dh895xcc/adf_drv.h b/drivers/crypto/qat/qat_c62x/adf_c62x_hw_data.h
similarity index 60%
copy from drivers/crypto/qat/qat_dh895xcc/adf_drv.h
copy to drivers/crypto/qat/qat_c62x/adf_c62x_hw_data.h
index 85ff245..17a8a32 100644
--- a/drivers/crypto/qat/qat_dh895xcc/adf_drv.h
+++ b/drivers/crypto/qat/qat_c62x/adf_c62x_hw_data.h
@@ -44,15 +44,41 @@
   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */
-#ifndef ADF_DH895x_DRV_H_
-#define ADF_DH895x_DRV_H_
-#include <adf_accel_devices.h>
-#include <adf_transport.h>
+#ifndef ADF_C62X_HW_DATA_H_
+#define ADF_C62X_HW_DATA_H_
 
-void adf_init_hw_data_dh895xcc(struct adf_hw_device_data *hw_data);
-void adf_clean_hw_data_dh895xcc(struct adf_hw_device_data *hw_data);
-int adf_isr_resource_alloc(struct adf_accel_dev *accel_dev);
-void adf_isr_resource_free(struct adf_accel_dev *accel_dev);
-void adf_get_arbiter_mapping(struct adf_accel_dev *accel_dev,
-			     uint32_t const **arb_map_config);
+/* PCIe configuration space */
+#define ADF_C62X_SRAM_BAR 0
+#define ADF_C62X_PMISC_BAR 1
+#define ADF_C62X_ETR_BAR 2
+#define ADF_C62X_RX_RINGS_OFFSET 8
+#define ADF_C62X_TX_RINGS_MASK 0xFF
+#define ADF_C62X_MAX_ACCELERATORS 5
+#define ADF_C62X_MAX_ACCELENGINES 10
+#define ADF_C62X_ACCELERATORS_REG_OFFSET 16
+#define ADF_C62X_ACCELERATORS_MASK 0x1F
+#define ADF_C62X_ACCELENGINES_MASK 0x3FF
+#define ADF_C62X_ETR_MAX_BANKS 16
+#define ADF_C62X_SMIAPF0_MASK_OFFSET (0x3A000 + 0x28)
+#define ADF_C62X_SMIAPF1_MASK_OFFSET (0x3A000 + 0x30)
+#define ADF_C62X_SMIA0_MASK 0xFFFF
+#define ADF_C62X_SMIA1_MASK 0x1
+/* Error detection and correction */
+#define ADF_C62X_AE_CTX_ENABLES(i) (i * 0x1000 + 0x20818)
+#define ADF_C62X_AE_MISC_CONTROL(i) (i * 0x1000 + 0x20960)
+#define ADF_C62X_ENABLE_AE_ECC_ERR BIT(28)
+#define ADF_C62X_ENABLE_AE_ECC_PARITY_CORR (BIT(24) | BIT(12))
+#define ADF_C62X_UERRSSMSH(i) (i * 0x4000 + 0x18)
+#define ADF_C62X_CERRSSMSH(i) (i * 0x4000 + 0x10)
+#define ADF_C62X_ERRSSMSH_EN BIT(3)
+
+#define ADF_C62X_PF2VF_OFFSET(i)	(0x3A000 + 0x280 + ((i) * 0x04))
+#define ADF_C62X_VINTMSK_OFFSET(i)	(0x3A000 + 0x200 + ((i) * 0x04))
+
+/* Firmware Binary */
+#define ADF_C62X_FW "qat_c62x.bin"
+#define ADF_C62X_MMP "qat_c62x_mmp.bin"
+
+void adf_init_hw_data_c62x(struct adf_hw_device_data *hw_data);
+void adf_clean_hw_data_c62x(struct adf_hw_device_data *hw_data);
 #endif
diff --git a/drivers/crypto/qat/qat_c62x/adf_drv.c b/drivers/crypto/qat/qat_c62x/adf_drv.c
new file mode 100644
index 0000000..512c565
--- /dev/null
+++ b/drivers/crypto/qat/qat_c62x/adf_drv.c
@@ -0,0 +1,335 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/fs.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <linux/platform_device.h>
+#include <linux/workqueue.h>
+#include <linux/io.h>
+#include <adf_accel_devices.h>
+#include <adf_common_drv.h>
+#include <adf_cfg.h>
+#include "adf_c62x_hw_data.h"
+
+#define ADF_SYSTEM_DEVICE(device_id) \
+	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, device_id)}
+
+static const struct pci_device_id adf_pci_tbl[] = {
+	ADF_SYSTEM_DEVICE(ADF_C62X_PCI_DEVICE_ID),
+	{0,}
+};
+MODULE_DEVICE_TABLE(pci, adf_pci_tbl);
+
+static int adf_probe(struct pci_dev *dev, const struct pci_device_id *ent);
+static void adf_remove(struct pci_dev *dev);
+
+static struct pci_driver adf_driver = {
+	.id_table = adf_pci_tbl,
+	.name = ADF_C62X_DEVICE_NAME,
+	.probe = adf_probe,
+	.remove = adf_remove,
+	.sriov_configure = adf_sriov_configure,
+};
+
+static void adf_cleanup_pci_dev(struct adf_accel_dev *accel_dev)
+{
+	pci_release_regions(accel_dev->accel_pci_dev.pci_dev);
+	pci_disable_device(accel_dev->accel_pci_dev.pci_dev);
+}
+
+static void adf_cleanup_accel(struct adf_accel_dev *accel_dev)
+{
+	struct adf_accel_pci *accel_pci_dev = &accel_dev->accel_pci_dev;
+	int i;
+
+	for (i = 0; i < ADF_PCI_MAX_BARS; i++) {
+		struct adf_bar *bar = &accel_pci_dev->pci_bars[i];
+
+		if (bar->virt_addr)
+			pci_iounmap(accel_pci_dev->pci_dev, bar->virt_addr);
+	}
+
+	if (accel_dev->hw_device) {
+		switch (accel_pci_dev->pci_dev->device) {
+		case ADF_C62X_PCI_DEVICE_ID:
+			adf_clean_hw_data_c62x(accel_dev->hw_device);
+			break;
+		default:
+			break;
+		}
+		kfree(accel_dev->hw_device);
+		accel_dev->hw_device = NULL;
+	}
+	adf_cfg_dev_remove(accel_dev);
+	debugfs_remove(accel_dev->debugfs_dir);
+	adf_devmgr_rm_dev(accel_dev, NULL);
+}
+
+static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
+{
+	struct adf_accel_dev *accel_dev;
+	struct adf_accel_pci *accel_pci_dev;
+	struct adf_hw_device_data *hw_data;
+	char name[ADF_DEVICE_NAME_LENGTH];
+	unsigned int i, bar_nr;
+	int ret, bar_mask;
+
+	switch (ent->device) {
+	case ADF_C62X_PCI_DEVICE_ID:
+		break;
+	default:
+		dev_err(&pdev->dev, "Invalid device 0x%x.\n", ent->device);
+		return -ENODEV;
+	}
+
+	if (num_possible_nodes() > 1 && dev_to_node(&pdev->dev) < 0) {
+		/* If the accelerator is connected to a node with no memory
+		 * there is no point in using the accelerator since the remote
+		 * memory transaction will be very slow. */
+		dev_err(&pdev->dev, "Invalid NUMA configuration.\n");
+		return -EINVAL;
+	}
+
+	accel_dev = kzalloc_node(sizeof(*accel_dev), GFP_KERNEL,
+				 dev_to_node(&pdev->dev));
+	if (!accel_dev)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&accel_dev->crypto_list);
+	accel_pci_dev = &accel_dev->accel_pci_dev;
+	accel_pci_dev->pci_dev = pdev;
+
+	/* Add accel device to accel table.
+	 * This should be called before adf_cleanup_accel is called */
+	if (adf_devmgr_add_dev(accel_dev, NULL)) {
+		dev_err(&pdev->dev, "Failed to add new accelerator device.\n");
+		kfree(accel_dev);
+		return -EFAULT;
+	}
+
+	accel_dev->owner = THIS_MODULE;
+	/* Allocate and configure device configuration structure */
+	hw_data = kzalloc_node(sizeof(*hw_data), GFP_KERNEL,
+			       dev_to_node(&pdev->dev));
+	if (!hw_data) {
+		ret = -ENOMEM;
+		goto out_err;
+	}
+
+	accel_dev->hw_device = hw_data;
+	adf_init_hw_data_c62x(accel_dev->hw_device);
+	pci_read_config_byte(pdev, PCI_REVISION_ID, &accel_pci_dev->revid);
+	pci_read_config_dword(pdev, ADF_DEVICE_FUSECTL_OFFSET,
+			      &hw_data->fuses);
+
+	/* Get Accelerators and Accelerators Engines masks */
+	hw_data->accel_mask = hw_data->get_accel_mask(hw_data->fuses);
+	hw_data->ae_mask = hw_data->get_ae_mask(hw_data->fuses);
+	accel_pci_dev->sku = hw_data->get_sku(hw_data);
+	/* If the device has no acceleration engines then ignore it. */
+	if (!hw_data->accel_mask || !hw_data->ae_mask ||
+	    ((~hw_data->ae_mask) & 0x01)) {
+		dev_err(&pdev->dev, "No acceleration units found");
+		ret = -EFAULT;
+		goto out_err;
+	}
+
+	/* Create dev top level debugfs entry */
+	snprintf(name, sizeof(name), "%s%s_%02x:%02d.%02d",
+		 ADF_DEVICE_NAME_PREFIX, hw_data->dev_class->name,
+		 pdev->bus->number, PCI_SLOT(pdev->devfn),
+		 PCI_FUNC(pdev->devfn));
+
+	accel_dev->debugfs_dir = debugfs_create_dir(name, NULL);
+	if (!accel_dev->debugfs_dir) {
+		dev_err(&pdev->dev, "Could not create debugfs dir %s\n", name);
+		ret = -EINVAL;
+		goto out_err;
+	}
+
+	/* Create device configuration table */
+	ret = adf_cfg_dev_add(accel_dev);
+	if (ret)
+		goto out_err;
+
+	/* enable PCI device */
+	if (pci_enable_device(pdev)) {
+		ret = -EFAULT;
+		goto out_err;
+	}
+
+	/* set dma identifier */
+	if (pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) {
+		if ((pci_set_dma_mask(pdev, DMA_BIT_MASK(32)))) {
+			dev_err(&pdev->dev, "No usable DMA configuration\n");
+			ret = -EFAULT;
+			goto out_err_disable;
+		} else {
+			pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
+		}
+
+	} else {
+		pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
+	}
+
+	if (pci_request_regions(pdev, ADF_C62X_DEVICE_NAME)) {
+		ret = -EFAULT;
+		goto out_err_disable;
+	}
+
+	/* Read accelerator capabilities mask */
+	pci_read_config_dword(pdev, ADF_DEVICE_LEGFUSE_OFFSET,
+			      &hw_data->accel_capabilities_mask);
+
+	/* Find and map all the device's BARS */
+	i = 0;
+	bar_mask = pci_select_bars(pdev, IORESOURCE_MEM);
+	for_each_set_bit(bar_nr, (const unsigned long *)&bar_mask,
+			 ADF_PCI_MAX_BARS * 2) {
+		struct adf_bar *bar = &accel_pci_dev->pci_bars[i++];
+
+		bar->base_addr = pci_resource_start(pdev, bar_nr);
+		if (!bar->base_addr)
+			break;
+		bar->size = pci_resource_len(pdev, bar_nr);
+		bar->virt_addr = pci_iomap(accel_pci_dev->pci_dev, bar_nr, 0);
+		if (!bar->virt_addr) {
+			dev_err(&pdev->dev, "Failed to map BAR %d\n", bar_nr);
+			ret = -EFAULT;
+			goto out_err_free_reg;
+		}
+	}
+	pci_set_master(pdev);
+
+	if (adf_enable_aer(accel_dev, &adf_driver)) {
+		dev_err(&pdev->dev, "Failed to enable aer\n");
+		ret = -EFAULT;
+		goto out_err_free_reg;
+	}
+
+	if (pci_save_state(pdev)) {
+		dev_err(&pdev->dev, "Failed to save pci state\n");
+		ret = -ENOMEM;
+		goto out_err_free_reg;
+	}
+
+	ret = qat_crypto_dev_config(accel_dev);
+	if (ret)
+		goto out_err_free_reg;
+
+	ret = adf_dev_init(accel_dev);
+	if (ret)
+		goto out_err_dev_shutdown;
+
+	ret = adf_dev_start(accel_dev);
+	if (ret)
+		goto out_err_dev_stop;
+
+	return ret;
+
+out_err_dev_stop:
+	adf_dev_stop(accel_dev);
+out_err_dev_shutdown:
+	adf_dev_shutdown(accel_dev);
+out_err_free_reg:
+	pci_release_regions(accel_pci_dev->pci_dev);
+out_err_disable:
+	pci_disable_device(accel_pci_dev->pci_dev);
+out_err:
+	adf_cleanup_accel(accel_dev);
+	kfree(accel_dev);
+	return ret;
+}
+
+static void adf_remove(struct pci_dev *pdev)
+{
+	struct adf_accel_dev *accel_dev = adf_devmgr_pci_to_accel_dev(pdev);
+
+	if (!accel_dev) {
+		pr_err("QAT: Driver removal failed\n");
+		return;
+	}
+	if (adf_dev_stop(accel_dev))
+		dev_err(&GET_DEV(accel_dev), "Failed to stop QAT accel dev\n");
+
+	adf_dev_shutdown(accel_dev);
+	adf_disable_aer(accel_dev);
+	adf_cleanup_accel(accel_dev);
+	adf_cleanup_pci_dev(accel_dev);
+	kfree(accel_dev);
+}
+
+static int __init adfdrv_init(void)
+{
+	request_module("intel_qat");
+
+	if (pci_register_driver(&adf_driver)) {
+		pr_err("QAT: Driver initialization failed\n");
+		return -EFAULT;
+	}
+	return 0;
+}
+
+static void __exit adfdrv_release(void)
+{
+	pci_unregister_driver(&adf_driver);
+}
+
+module_init(adfdrv_init);
+module_exit(adfdrv_release);
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_AUTHOR("Intel");
+MODULE_DESCRIPTION("Intel(R) QuickAssist Technology");
+MODULE_VERSION(ADF_DRV_VERSION);
diff --git a/drivers/crypto/qat/qat_c62xvf/Makefile b/drivers/crypto/qat/qat_c62xvf/Makefile
new file mode 100644
index 0000000..ecd708c
--- /dev/null
+++ b/drivers/crypto/qat/qat_c62xvf/Makefile
@@ -0,0 +1,3 @@
+ccflags-y := -I$(src)/../qat_common
+obj-$(CONFIG_CRYPTO_DEV_QAT_C62XVF) += qat_c62xvf.o
+qat_c62xvf-objs := adf_drv.o adf_c62xvf_hw_data.o
diff --git a/drivers/crypto/qat/qat_c62xvf/adf_c62xvf_hw_data.c b/drivers/crypto/qat/qat_c62xvf/adf_c62xvf_hw_data.c
new file mode 100644
index 0000000..baf4b509
--- /dev/null
+++ b/drivers/crypto/qat/qat_c62xvf/adf_c62xvf_hw_data.c
@@ -0,0 +1,173 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2015 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2015 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#include <adf_accel_devices.h>
+#include <adf_pf2vf_msg.h>
+#include <adf_common_drv.h>
+#include "adf_c62xvf_hw_data.h"
+
+static struct adf_hw_device_class c62xiov_class = {
+	.name = ADF_C62XVF_DEVICE_NAME,
+	.type = DEV_C62XVF,
+	.instances = 0
+};
+
+static u32 get_accel_mask(u32 fuse)
+{
+	return ADF_C62XIOV_ACCELERATORS_MASK;
+}
+
+static u32 get_ae_mask(u32 fuse)
+{
+	return ADF_C62XIOV_ACCELENGINES_MASK;
+}
+
+static u32 get_num_accels(struct adf_hw_device_data *self)
+{
+	return ADF_C62XIOV_MAX_ACCELERATORS;
+}
+
+static u32 get_num_aes(struct adf_hw_device_data *self)
+{
+	return ADF_C62XIOV_MAX_ACCELENGINES;
+}
+
+static u32 get_misc_bar_id(struct adf_hw_device_data *self)
+{
+	return ADF_C62XIOV_PMISC_BAR;
+}
+
+static u32 get_etr_bar_id(struct adf_hw_device_data *self)
+{
+	return ADF_C62XIOV_ETR_BAR;
+}
+
+static enum dev_sku_info get_sku(struct adf_hw_device_data *self)
+{
+	return DEV_SKU_VF;
+}
+
+static u32 get_pf2vf_offset(u32 i)
+{
+	return ADF_C62XIOV_PF2VF_OFFSET;
+}
+
+static u32 get_vintmsk_offset(u32 i)
+{
+	return ADF_C62XIOV_VINTMSK_OFFSET;
+}
+
+static int adf_vf_int_noop(struct adf_accel_dev *accel_dev)
+{
+	return 0;
+}
+
+static void adf_vf_void_noop(struct adf_accel_dev *accel_dev)
+{
+}
+
+static int adf_vf2pf_init(struct adf_accel_dev *accel_dev)
+{
+	u32 msg = (ADF_VF2PF_MSGORIGIN_SYSTEM |
+		(ADF_VF2PF_MSGTYPE_INIT << ADF_VF2PF_MSGTYPE_SHIFT));
+
+	if (adf_iov_putmsg(accel_dev, msg, 0)) {
+		dev_err(&GET_DEV(accel_dev),
+			"Failed to send Init event to PF\n");
+		return -EFAULT;
+	}
+	return 0;
+}
+
+static void adf_vf2pf_shutdown(struct adf_accel_dev *accel_dev)
+{
+	u32 msg = (ADF_VF2PF_MSGORIGIN_SYSTEM |
+	    (ADF_VF2PF_MSGTYPE_SHUTDOWN << ADF_VF2PF_MSGTYPE_SHIFT));
+
+	if (adf_iov_putmsg(accel_dev, msg, 0))
+		dev_err(&GET_DEV(accel_dev),
+			"Failed to send Shutdown event to PF\n");
+}
+
+void adf_init_hw_data_c62xiov(struct adf_hw_device_data *hw_data)
+{
+	hw_data->dev_class = &c62xiov_class;
+	hw_data->num_banks = ADF_C62XIOV_ETR_MAX_BANKS;
+	hw_data->num_accel = ADF_C62XIOV_MAX_ACCELERATORS;
+	hw_data->num_logical_accel = 1;
+	hw_data->num_engines = ADF_C62XIOV_MAX_ACCELENGINES;
+	hw_data->tx_rx_gap = ADF_C62XIOV_RX_RINGS_OFFSET;
+	hw_data->tx_rings_mask = ADF_C62XIOV_TX_RINGS_MASK;
+	hw_data->alloc_irq = adf_vf_isr_resource_alloc;
+	hw_data->free_irq = adf_vf_isr_resource_free;
+	hw_data->enable_error_correction = adf_vf_void_noop;
+	hw_data->init_admin_comms = adf_vf_int_noop;
+	hw_data->exit_admin_comms = adf_vf_void_noop;
+	hw_data->send_admin_init = adf_vf2pf_init;
+	hw_data->init_arb = adf_vf_int_noop;
+	hw_data->exit_arb = adf_vf_void_noop;
+	hw_data->disable_iov = adf_vf2pf_shutdown;
+	hw_data->get_accel_mask = get_accel_mask;
+	hw_data->get_ae_mask = get_ae_mask;
+	hw_data->get_num_accels = get_num_accels;
+	hw_data->get_num_aes = get_num_aes;
+	hw_data->get_etr_bar_id = get_etr_bar_id;
+	hw_data->get_misc_bar_id = get_misc_bar_id;
+	hw_data->get_pf2vf_offset = get_pf2vf_offset;
+	hw_data->get_vintmsk_offset = get_vintmsk_offset;
+	hw_data->get_sku = get_sku;
+	hw_data->enable_ints = adf_vf_void_noop;
+	hw_data->enable_vf2pf_comms = adf_enable_vf2pf_comms;
+	hw_data->min_iov_compat_ver = ADF_PFVF_COMPATIBILITY_VERSION;
+	hw_data->dev_class->instances++;
+	adf_devmgr_update_class_index(hw_data);
+}
+
+void adf_clean_hw_data_c62xiov(struct adf_hw_device_data *hw_data)
+{
+	hw_data->dev_class->instances--;
+	adf_devmgr_update_class_index(hw_data);
+}
diff --git a/drivers/crypto/qat/qat_dh895xcc/adf_drv.h b/drivers/crypto/qat/qat_c62xvf/adf_c62xvf_hw_data.h
similarity index 75%
copy from drivers/crypto/qat/qat_dh895xcc/adf_drv.h
copy to drivers/crypto/qat/qat_c62xvf/adf_c62xvf_hw_data.h
index 85ff245..a28d83e 100644
--- a/drivers/crypto/qat/qat_dh895xcc/adf_drv.h
+++ b/drivers/crypto/qat/qat_c62xvf/adf_c62xvf_hw_data.h
@@ -3,7 +3,7 @@
   redistributing this file, you may do so under either license.
 
   GPL LICENSE SUMMARY
-  Copyright(c) 2014 Intel Corporation.
+  Copyright(c) 2015 Intel Corporation.
   This program is free software; you can redistribute it and/or modify
   it under the terms of version 2 of the GNU General Public License as
   published by the Free Software Foundation.
@@ -17,7 +17,7 @@
   qat-linux@intel.com
 
   BSD LICENSE
-  Copyright(c) 2014 Intel Corporation.
+  Copyright(c) 2015 Intel Corporation.
   Redistribution and use in source and binary forms, with or without
   modification, are permitted provided that the following conditions
   are met:
@@ -44,15 +44,21 @@
   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */
-#ifndef ADF_DH895x_DRV_H_
-#define ADF_DH895x_DRV_H_
-#include <adf_accel_devices.h>
-#include <adf_transport.h>
+#ifndef ADF_C62XVF_HW_DATA_H_
+#define ADF_C62XVF_HW_DATA_H_
 
-void adf_init_hw_data_dh895xcc(struct adf_hw_device_data *hw_data);
-void adf_clean_hw_data_dh895xcc(struct adf_hw_device_data *hw_data);
-int adf_isr_resource_alloc(struct adf_accel_dev *accel_dev);
-void adf_isr_resource_free(struct adf_accel_dev *accel_dev);
-void adf_get_arbiter_mapping(struct adf_accel_dev *accel_dev,
-			     uint32_t const **arb_map_config);
+#define ADF_C62XIOV_PMISC_BAR 1
+#define ADF_C62XIOV_ACCELERATORS_MASK 0x1
+#define ADF_C62XIOV_ACCELENGINES_MASK 0x1
+#define ADF_C62XIOV_MAX_ACCELERATORS 1
+#define ADF_C62XIOV_MAX_ACCELENGINES 1
+#define ADF_C62XIOV_RX_RINGS_OFFSET 8
+#define ADF_C62XIOV_TX_RINGS_MASK 0xFF
+#define ADF_C62XIOV_ETR_BAR 0
+#define ADF_C62XIOV_ETR_MAX_BANKS 1
+#define ADF_C62XIOV_PF2VF_OFFSET	0x200
+#define ADF_C62XIOV_VINTMSK_OFFSET	0x208
+
+void adf_init_hw_data_c62xiov(struct adf_hw_device_data *hw_data);
+void adf_clean_hw_data_c62xiov(struct adf_hw_device_data *hw_data);
 #endif
diff --git a/drivers/crypto/qat/qat_c62xvf/adf_drv.c b/drivers/crypto/qat/qat_c62xvf/adf_drv.c
new file mode 100644
index 0000000..d2e4b92
--- /dev/null
+++ b/drivers/crypto/qat/qat_c62xvf/adf_drv.c
@@ -0,0 +1,305 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/fs.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <linux/platform_device.h>
+#include <linux/workqueue.h>
+#include <linux/io.h>
+#include <adf_accel_devices.h>
+#include <adf_common_drv.h>
+#include <adf_cfg.h>
+#include "adf_c62xvf_hw_data.h"
+
+#define ADF_SYSTEM_DEVICE(device_id) \
+	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, device_id)}
+
+static const struct pci_device_id adf_pci_tbl[] = {
+	ADF_SYSTEM_DEVICE(ADF_C62XIOV_PCI_DEVICE_ID),
+	{0,}
+};
+MODULE_DEVICE_TABLE(pci, adf_pci_tbl);
+
+static int adf_probe(struct pci_dev *dev, const struct pci_device_id *ent);
+static void adf_remove(struct pci_dev *dev);
+
+static struct pci_driver adf_driver = {
+	.id_table = adf_pci_tbl,
+	.name = ADF_C62XVF_DEVICE_NAME,
+	.probe = adf_probe,
+	.remove = adf_remove,
+};
+
+static void adf_cleanup_pci_dev(struct adf_accel_dev *accel_dev)
+{
+	pci_release_regions(accel_dev->accel_pci_dev.pci_dev);
+	pci_disable_device(accel_dev->accel_pci_dev.pci_dev);
+}
+
+static void adf_cleanup_accel(struct adf_accel_dev *accel_dev)
+{
+	struct adf_accel_pci *accel_pci_dev = &accel_dev->accel_pci_dev;
+	struct adf_accel_dev *pf;
+	int i;
+
+	for (i = 0; i < ADF_PCI_MAX_BARS; i++) {
+		struct adf_bar *bar = &accel_pci_dev->pci_bars[i];
+
+		if (bar->virt_addr)
+			pci_iounmap(accel_pci_dev->pci_dev, bar->virt_addr);
+	}
+
+	if (accel_dev->hw_device) {
+		switch (accel_pci_dev->pci_dev->device) {
+		case ADF_C62XIOV_PCI_DEVICE_ID:
+			adf_clean_hw_data_c62xiov(accel_dev->hw_device);
+			break;
+		default:
+			break;
+		}
+		kfree(accel_dev->hw_device);
+		accel_dev->hw_device = NULL;
+	}
+	adf_cfg_dev_remove(accel_dev);
+	debugfs_remove(accel_dev->debugfs_dir);
+	pf = adf_devmgr_pci_to_accel_dev(accel_pci_dev->pci_dev->physfn);
+	adf_devmgr_rm_dev(accel_dev, pf);
+}
+
+static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
+{
+	struct adf_accel_dev *accel_dev;
+	struct adf_accel_dev *pf;
+	struct adf_accel_pci *accel_pci_dev;
+	struct adf_hw_device_data *hw_data;
+	char name[ADF_DEVICE_NAME_LENGTH];
+	unsigned int i, bar_nr;
+	int ret, bar_mask;
+
+	switch (ent->device) {
+	case ADF_C62XIOV_PCI_DEVICE_ID:
+		break;
+	default:
+		dev_err(&pdev->dev, "Invalid device 0x%x.\n", ent->device);
+		return -ENODEV;
+	}
+
+	accel_dev = kzalloc_node(sizeof(*accel_dev), GFP_KERNEL,
+				 dev_to_node(&pdev->dev));
+	if (!accel_dev)
+		return -ENOMEM;
+
+	accel_dev->is_vf = true;
+	pf = adf_devmgr_pci_to_accel_dev(pdev->physfn);
+	accel_pci_dev = &accel_dev->accel_pci_dev;
+	accel_pci_dev->pci_dev = pdev;
+
+	/* Add accel device to accel table */
+	if (adf_devmgr_add_dev(accel_dev, pf)) {
+		dev_err(&pdev->dev, "Failed to add new accelerator device.\n");
+		kfree(accel_dev);
+		return -EFAULT;
+	}
+	INIT_LIST_HEAD(&accel_dev->crypto_list);
+
+	accel_dev->owner = THIS_MODULE;
+	/* Allocate and configure device configuration structure */
+	hw_data = kzalloc_node(sizeof(*hw_data), GFP_KERNEL,
+			       dev_to_node(&pdev->dev));
+	if (!hw_data) {
+		ret = -ENOMEM;
+		goto out_err;
+	}
+	accel_dev->hw_device = hw_data;
+	adf_init_hw_data_c62xiov(accel_dev->hw_device);
+
+	/* Get Accelerators and Accelerators Engines masks */
+	hw_data->accel_mask = hw_data->get_accel_mask(hw_data->fuses);
+	hw_data->ae_mask = hw_data->get_ae_mask(hw_data->fuses);
+	accel_pci_dev->sku = hw_data->get_sku(hw_data);
+
+	/* Create dev top level debugfs entry */
+	snprintf(name, sizeof(name), "%s%s_%02x:%02d.%02d",
+		 ADF_DEVICE_NAME_PREFIX, hw_data->dev_class->name,
+		 pdev->bus->number, PCI_SLOT(pdev->devfn),
+		 PCI_FUNC(pdev->devfn));
+
+	accel_dev->debugfs_dir = debugfs_create_dir(name, NULL);
+	if (!accel_dev->debugfs_dir) {
+		dev_err(&pdev->dev, "Could not create debugfs dir %s\n", name);
+		ret = -EINVAL;
+		goto out_err;
+	}
+
+	/* Create device configuration table */
+	ret = adf_cfg_dev_add(accel_dev);
+	if (ret)
+		goto out_err;
+
+	/* enable PCI device */
+	if (pci_enable_device(pdev)) {
+		ret = -EFAULT;
+		goto out_err;
+	}
+
+	/* set dma identifier */
+	if (pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) {
+		if ((pci_set_dma_mask(pdev, DMA_BIT_MASK(32)))) {
+			dev_err(&pdev->dev, "No usable DMA configuration\n");
+			ret = -EFAULT;
+			goto out_err_disable;
+		} else {
+			pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
+		}
+
+	} else {
+		pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
+	}
+
+	if (pci_request_regions(pdev, ADF_C62XVF_DEVICE_NAME)) {
+		ret = -EFAULT;
+		goto out_err_disable;
+	}
+
+	/* Find and map all the device's BARS */
+	i = 0;
+	bar_mask = pci_select_bars(pdev, IORESOURCE_MEM);
+	for_each_set_bit(bar_nr, (const unsigned long *)&bar_mask,
+			 ADF_PCI_MAX_BARS * 2) {
+		struct adf_bar *bar = &accel_pci_dev->pci_bars[i++];
+
+		bar->base_addr = pci_resource_start(pdev, bar_nr);
+		if (!bar->base_addr)
+			break;
+		bar->size = pci_resource_len(pdev, bar_nr);
+		bar->virt_addr = pci_iomap(accel_pci_dev->pci_dev, bar_nr, 0);
+		if (!bar->virt_addr) {
+			dev_err(&pdev->dev, "Failed to map BAR %d\n", bar_nr);
+			ret = -EFAULT;
+			goto out_err_free_reg;
+		}
+	}
+	pci_set_master(pdev);
+	/* Completion for VF2PF request/response message exchange */
+	init_completion(&accel_dev->vf.iov_msg_completion);
+
+	ret = qat_crypto_dev_config(accel_dev);
+	if (ret)
+		goto out_err_free_reg;
+
+	ret = adf_dev_init(accel_dev);
+	if (ret)
+		goto out_err_dev_shutdown;
+
+	ret = adf_dev_start(accel_dev);
+	if (ret)
+		goto out_err_dev_stop;
+
+	return ret;
+
+out_err_dev_stop:
+	adf_dev_stop(accel_dev);
+out_err_dev_shutdown:
+	adf_dev_shutdown(accel_dev);
+out_err_free_reg:
+	pci_release_regions(accel_pci_dev->pci_dev);
+out_err_disable:
+	pci_disable_device(accel_pci_dev->pci_dev);
+out_err:
+	adf_cleanup_accel(accel_dev);
+	kfree(accel_dev);
+	return ret;
+}
+
+static void adf_remove(struct pci_dev *pdev)
+{
+	struct adf_accel_dev *accel_dev = adf_devmgr_pci_to_accel_dev(pdev);
+
+	if (!accel_dev) {
+		pr_err("QAT: Driver removal failed\n");
+		return;
+	}
+	if (adf_dev_stop(accel_dev))
+		dev_err(&GET_DEV(accel_dev), "Failed to stop QAT accel dev\n");
+
+	adf_dev_shutdown(accel_dev);
+	adf_cleanup_accel(accel_dev);
+	adf_cleanup_pci_dev(accel_dev);
+	kfree(accel_dev);
+}
+
+static int __init adfdrv_init(void)
+{
+	request_module("intel_qat");
+
+	if (pci_register_driver(&adf_driver)) {
+		pr_err("QAT: Driver initialization failed\n");
+		return -EFAULT;
+	}
+	return 0;
+}
+
+static void __exit adfdrv_release(void)
+{
+	pci_unregister_driver(&adf_driver);
+	adf_clean_vf_map(true);
+}
+
+module_init(adfdrv_init);
+module_exit(adfdrv_release);
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_AUTHOR("Intel");
+MODULE_DESCRIPTION("Intel(R) QuickAssist Technology");
+MODULE_VERSION(ADF_DRV_VERSION);
diff --git a/drivers/crypto/qat/qat_common/Makefile b/drivers/crypto/qat/qat_common/Makefile
index 9e9e196..29c7c53 100644
--- a/drivers/crypto/qat/qat_common/Makefile
+++ b/drivers/crypto/qat/qat_common/Makefile
@@ -4,10 +4,12 @@
 			      $(obj)/qat_rsaprivkey-asn1.h
 
 clean-files += qat_rsapubkey-asn1.c qat_rsapubkey-asn1.h
-clean-files += qat_rsaprivkey-asn1.c qat_rsapvivkey-asn1.h
+clean-files += qat_rsaprivkey-asn1.c qat_rsaprivkey-asn1.h
 
 obj-$(CONFIG_CRYPTO_DEV_QAT) += intel_qat.o
 intel_qat-objs := adf_cfg.o \
+	adf_isr.o \
+	adf_vf_isr.o \
 	adf_ctl_drv.o \
 	adf_dev_mgr.o \
 	adf_init.o \
diff --git a/drivers/crypto/qat/qat_common/adf_accel_devices.h b/drivers/crypto/qat/qat_common/adf_accel_devices.h
index ca853d5..f96d427 100644
--- a/drivers/crypto/qat/qat_common/adf_accel_devices.h
+++ b/drivers/crypto/qat/qat_common/adf_accel_devices.h
@@ -55,8 +55,20 @@
 
 #define ADF_DH895XCC_DEVICE_NAME "dh895xcc"
 #define ADF_DH895XCCVF_DEVICE_NAME "dh895xccvf"
+#define ADF_C62X_DEVICE_NAME "c62x"
+#define ADF_C62XVF_DEVICE_NAME "c62xvf"
+#define ADF_C3XXX_DEVICE_NAME "c3xxx"
+#define ADF_C3XXXVF_DEVICE_NAME "c3xxxvf"
 #define ADF_DH895XCC_PCI_DEVICE_ID 0x435
 #define ADF_DH895XCCIOV_PCI_DEVICE_ID 0x443
+#define ADF_C62X_PCI_DEVICE_ID 0x37c8
+#define ADF_C62XIOV_PCI_DEVICE_ID 0x37c9
+#define ADF_C3XXX_PCI_DEVICE_ID 0x19e2
+#define ADF_C3XXXIOV_PCI_DEVICE_ID 0x19e3
+#define ADF_ERRSOU3 (0x3A000 + 0x0C)
+#define ADF_ERRSOU5 (0x3A000 + 0xD8)
+#define ADF_DEVICE_FUSECTL_OFFSET 0x40
+#define ADF_DEVICE_LEGFUSE_OFFSET 0x4C
 #define ADF_PCI_MAX_BARS 3
 #define ADF_DEVICE_NAME_LENGTH 32
 #define ADF_ETR_MAX_RINGS_PER_BANK 16
@@ -168,11 +180,11 @@
 	const char *fw_mmp_name;
 	uint32_t fuses;
 	uint32_t accel_capabilities_mask;
+	uint32_t instance_id;
 	uint16_t accel_mask;
 	uint16_t ae_mask;
 	uint16_t tx_rings_mask;
 	uint8_t tx_rx_gap;
-	uint8_t instance_id;
 	uint8_t num_banks;
 	uint8_t num_accel;
 	uint8_t num_logical_accel;
@@ -239,6 +251,6 @@
 		} vf;
 	};
 	bool is_vf;
-	uint8_t accel_id;
+	u32 accel_id;
 } __packed;
 #endif
diff --git a/drivers/crypto/qat/qat_common/adf_accel_engine.c b/drivers/crypto/qat/qat_common/adf_accel_engine.c
index 20b08bd..a42fc42 100644
--- a/drivers/crypto/qat/qat_common/adf_accel_engine.c
+++ b/drivers/crypto/qat/qat_common/adf_accel_engine.c
@@ -78,9 +78,12 @@
 	uof_addr = (void *)loader_data->uof_fw->data;
 	mmp_size = loader_data->mmp_fw->size;
 	mmp_addr = (void *)loader_data->mmp_fw->data;
-	qat_uclo_wr_mimage(loader_data->fw_loader, mmp_addr, mmp_size);
-	if (qat_uclo_map_uof_obj(loader_data->fw_loader, uof_addr, uof_size)) {
-		dev_err(&GET_DEV(accel_dev), "Failed to map UOF\n");
+	if (qat_uclo_wr_mimage(loader_data->fw_loader, mmp_addr, mmp_size)) {
+		dev_err(&GET_DEV(accel_dev), "Failed to load MMP\n");
+		goto out_err;
+	}
+	if (qat_uclo_map_obj(loader_data->fw_loader, uof_addr, uof_size)) {
+		dev_err(&GET_DEV(accel_dev), "Failed to map FW\n");
 		goto out_err;
 	}
 	if (qat_uclo_wr_all_uimage(loader_data->fw_loader)) {
diff --git a/drivers/crypto/qat/qat_common/adf_admin.c b/drivers/crypto/qat/qat_common/adf_admin.c
index 147d755..eb557f6 100644
--- a/drivers/crypto/qat/qat_common/adf_admin.c
+++ b/drivers/crypto/qat/qat_common/adf_admin.c
@@ -51,6 +51,7 @@
 #include <linux/pci.h>
 #include <linux/dma-mapping.h>
 #include "adf_accel_devices.h"
+#include "adf_common_drv.h"
 #include "icp_qat_fw_init_admin.h"
 
 /* Admin Messages Registers */
@@ -234,7 +235,8 @@
 	struct adf_bar *pmisc =
 		&GET_BARS(accel_dev)[hw_data->get_misc_bar_id(hw_data)];
 	void __iomem *csr = pmisc->virt_addr;
-	void __iomem *mailbox = csr + ADF_DH895XCC_MAILBOX_BASE_OFFSET;
+	void __iomem *mailbox = (void __iomem *)((uintptr_t)csr +
+				 ADF_DH895XCC_MAILBOX_BASE_OFFSET);
 	u64 reg_val;
 
 	admin = kzalloc_node(sizeof(*accel_dev->admin), GFP_KERNEL,
diff --git a/drivers/crypto/qat/qat_common/adf_aer.c b/drivers/crypto/qat/qat_common/adf_aer.c
index 0a5ca0b..e78a1d7 100644
--- a/drivers/crypto/qat/qat_common/adf_aer.c
+++ b/drivers/crypto/qat/qat_common/adf_aer.c
@@ -82,7 +82,7 @@
 	struct work_struct reset_work;
 };
 
-static void adf_dev_restore(struct adf_accel_dev *accel_dev)
+void adf_dev_restore(struct adf_accel_dev *accel_dev)
 {
 	struct pci_dev *pdev = accel_to_pci_dev(accel_dev);
 	struct pci_dev *parent = pdev->bus->self;
@@ -197,7 +197,7 @@
 	dev_info(&pdev->dev, "Device is up and runnig\n");
 }
 
-static struct pci_error_handlers adf_err_handler = {
+static const struct pci_error_handlers adf_err_handler = {
 	.error_detected = adf_error_detected,
 	.slot_reset = adf_slot_reset,
 	.resume = adf_resume,
diff --git a/drivers/crypto/qat/qat_common/adf_cfg_common.h b/drivers/crypto/qat/qat_common/adf_cfg_common.h
index c697fb1..8c4f657 100644
--- a/drivers/crypto/qat/qat_common/adf_cfg_common.h
+++ b/drivers/crypto/qat/qat_common/adf_cfg_common.h
@@ -72,12 +72,16 @@
 	DEV_UNKNOWN = 0,
 	DEV_DH895XCC,
 	DEV_DH895XCCVF,
+	DEV_C62X,
+	DEV_C62XVF,
+	DEV_C3XXX,
+	DEV_C3XXXVF
 };
 
 struct adf_dev_status_info {
 	enum adf_device_type type;
-	uint8_t accel_id;
-	uint8_t instance_id;
+	u32 accel_id;
+	u32 instance_id;
 	uint8_t num_ae;
 	uint8_t num_accel;
 	uint8_t num_logical_accel;
diff --git a/drivers/crypto/qat/qat_common/adf_common_drv.h b/drivers/crypto/qat/qat_common/adf_common_drv.h
index 3f76bd4..0e82ce3 100644
--- a/drivers/crypto/qat/qat_common/adf_common_drv.h
+++ b/drivers/crypto/qat/qat_common/adf_common_drv.h
@@ -54,7 +54,7 @@
 #include "icp_qat_hal.h"
 
 #define ADF_MAJOR_VERSION	0
-#define ADF_MINOR_VERSION	2
+#define ADF_MINOR_VERSION	6
 #define ADF_BUILD_VERSION	0
 #define ADF_DRV_VERSION		__stringify(ADF_MAJOR_VERSION) "." \
 				__stringify(ADF_MINOR_VERSION) "." \
@@ -106,8 +106,6 @@
 int adf_dev_stop(struct adf_accel_dev *accel_dev);
 void adf_dev_shutdown(struct adf_accel_dev *accel_dev);
 
-void adf_enable_pf2vf_interrupts(struct adf_accel_dev *accel_dev);
-void adf_disable_pf2vf_interrupts(struct adf_accel_dev *accel_dev);
 int adf_iov_putmsg(struct adf_accel_dev *accel_dev, u32 msg, u8 vf_nr);
 void adf_pf2vf_notify_restarting(struct adf_accel_dev *accel_dev);
 int adf_enable_vf2pf_comms(struct adf_accel_dev *accel_dev);
@@ -143,6 +141,7 @@
 
 int adf_enable_aer(struct adf_accel_dev *accel_dev, struct pci_driver *adf);
 void adf_disable_aer(struct adf_accel_dev *accel_dev);
+void adf_dev_restore(struct adf_accel_dev *accel_dev);
 int adf_init_aer(void);
 void adf_exit_aer(void);
 int adf_init_admin_comms(struct adf_accel_dev *accel_dev);
@@ -159,6 +158,7 @@
 void adf_cleanup_etr_data(struct adf_accel_dev *accel_dev);
 int qat_crypto_register(void);
 int qat_crypto_unregister(void);
+int qat_crypto_dev_config(struct adf_accel_dev *accel_dev);
 struct qat_crypto_instance *qat_crypto_get_instance_node(int node);
 void qat_crypto_put_instance(struct qat_crypto_instance *inst);
 void qat_alg_callback(void *resp);
@@ -168,6 +168,11 @@
 int qat_asym_algs_register(void);
 void qat_asym_algs_unregister(void);
 
+int adf_isr_resource_alloc(struct adf_accel_dev *accel_dev);
+void adf_isr_resource_free(struct adf_accel_dev *accel_dev);
+int adf_vf_isr_resource_alloc(struct adf_accel_dev *accel_dev);
+void adf_vf_isr_resource_free(struct adf_accel_dev *accel_dev);
+
 int qat_hal_init(struct adf_accel_dev *accel_dev);
 void qat_hal_deinit(struct icp_qat_fw_loader_handle *handle);
 void qat_hal_start(struct icp_qat_fw_loader_handle *handle, unsigned char ae,
@@ -178,6 +183,8 @@
 int qat_hal_clr_reset(struct icp_qat_fw_loader_handle *handle);
 void qat_hal_set_live_ctx(struct icp_qat_fw_loader_handle *handle,
 			  unsigned char ae, unsigned int ctx_mask);
+int qat_hal_check_ae_active(struct icp_qat_fw_loader_handle *handle,
+			    unsigned int ae);
 int qat_hal_set_ae_lm_mode(struct icp_qat_fw_loader_handle *handle,
 			   unsigned char ae, enum icp_qat_uof_regtype lm_type,
 			   unsigned char mode);
@@ -216,10 +223,10 @@
 		  unsigned char ae, unsigned short lm_addr, unsigned int value);
 int qat_uclo_wr_all_uimage(struct icp_qat_fw_loader_handle *handle);
 void qat_uclo_del_uof_obj(struct icp_qat_fw_loader_handle *handle);
-int qat_uclo_map_uof_obj(struct icp_qat_fw_loader_handle *handle,
-			 void *addr_ptr, int mem_size);
-void qat_uclo_wr_mimage(struct icp_qat_fw_loader_handle *handle,
-			void *addr_ptr, int mem_size);
+int qat_uclo_wr_mimage(struct icp_qat_fw_loader_handle *handle, void *addr_ptr,
+		       int mem_size);
+int qat_uclo_map_obj(struct icp_qat_fw_loader_handle *handle,
+		     void *addr_ptr, int mem_size);
 #if defined(CONFIG_PCI_IOV)
 int adf_sriov_configure(struct pci_dev *pdev, int numvfs);
 void adf_disable_sriov(struct adf_accel_dev *accel_dev);
@@ -227,6 +234,8 @@
 				  uint32_t vf_mask);
 void adf_enable_vf2pf_interrupts(struct adf_accel_dev *accel_dev,
 				 uint32_t vf_mask);
+void adf_enable_pf2vf_interrupts(struct adf_accel_dev *accel_dev);
+void adf_disable_pf2vf_interrupts(struct adf_accel_dev *accel_dev);
 #else
 static inline int adf_sriov_configure(struct pci_dev *pdev, int numvfs)
 {
@@ -236,5 +245,13 @@
 static inline void adf_disable_sriov(struct adf_accel_dev *accel_dev)
 {
 }
+
+static inline void adf_enable_pf2vf_interrupts(struct adf_accel_dev *accel_dev)
+{
+}
+
+static inline void adf_disable_pf2vf_interrupts(struct adf_accel_dev *accel_dev)
+{
+}
 #endif
 #endif
diff --git a/drivers/crypto/qat/qat_common/adf_ctl_drv.c b/drivers/crypto/qat/qat_common/adf_ctl_drv.c
index 473d36d..5c897e6 100644
--- a/drivers/crypto/qat/qat_common/adf_ctl_drv.c
+++ b/drivers/crypto/qat/qat_common/adf_ctl_drv.c
@@ -255,12 +255,9 @@
 
 static int adf_ctl_is_device_in_use(int id)
 {
-	struct list_head *itr, *head = adf_devmgr_get_head();
+	struct adf_accel_dev *dev;
 
-	list_for_each(itr, head) {
-		struct adf_accel_dev *dev =
-				list_entry(itr, struct adf_accel_dev, list);
-
+	list_for_each_entry(dev, adf_devmgr_get_head(), list) {
 		if (id == dev->accel_id || id == ADF_CFG_ALL_DEVICES) {
 			if (adf_devmgr_in_reset(dev) || adf_dev_in_use(dev)) {
 				dev_info(&GET_DEV(dev),
@@ -275,12 +272,10 @@
 
 static int adf_ctl_stop_devices(uint32_t id)
 {
-	struct list_head *itr, *head = adf_devmgr_get_head();
+	struct adf_accel_dev *accel_dev;
 	int ret = 0;
 
-	list_for_each(itr, head) {
-		struct adf_accel_dev *accel_dev =
-				list_entry(itr, struct adf_accel_dev, list);
+	list_for_each_entry_reverse(accel_dev, adf_devmgr_get_head(), list) {
 		if (id == accel_dev->accel_id || id == ADF_CFG_ALL_DEVICES) {
 			if (!adf_dev_started(accel_dev))
 				continue;
@@ -342,12 +337,10 @@
 	if (ret)
 		return ret;
 
+	ret = -ENODEV;
 	accel_dev = adf_devmgr_get_dev_by_id(ctl_data->device_id);
-	if (!accel_dev) {
-		pr_err("QAT: Device %d not found\n", ctl_data->device_id);
-		ret = -ENODEV;
+	if (!accel_dev)
 		goto out;
-	}
 
 	if (!adf_dev_started(accel_dev)) {
 		dev_info(&GET_DEV(accel_dev),
diff --git a/drivers/crypto/qat/qat_common/adf_dev_mgr.c b/drivers/crypto/qat/qat_common/adf_dev_mgr.c
index 8dfdb8f..b3ebb25 100644
--- a/drivers/crypto/qat/qat_common/adf_dev_mgr.c
+++ b/drivers/crypto/qat/qat_common/adf_dev_mgr.c
@@ -53,6 +53,7 @@
 static LIST_HEAD(vfs_table);
 static DEFINE_MUTEX(table_lock);
 static uint32_t num_devices;
+static u8 id_map[ADF_MAX_DEVICES];
 
 struct vf_id_map {
 	u32 bdf;
@@ -116,8 +117,10 @@
 	mutex_lock(&table_lock);
 	list_for_each_safe(ptr, tmp, &vfs_table) {
 		map = list_entry(ptr, struct vf_id_map, list);
-		if (map->bdf != -1)
+		if (map->bdf != -1) {
+			id_map[map->id] = 0;
 			num_devices--;
+		}
 
 		if (vf && map->bdf == -1)
 			continue;
@@ -154,6 +157,19 @@
 }
 EXPORT_SYMBOL_GPL(adf_devmgr_update_class_index);
 
+static unsigned int adf_find_free_id(void)
+{
+	unsigned int i;
+
+	for (i = 0; i < ADF_MAX_DEVICES; i++) {
+		if (!id_map[i]) {
+			id_map[i] = 1;
+			return i;
+		}
+	}
+	return ADF_MAX_DEVICES + 1;
+}
+
 /**
  * adf_devmgr_add_dev() - Add accel_dev to the acceleration framework
  * @accel_dev:  Pointer to acceleration device.
@@ -194,8 +210,12 @@
 		}
 
 		list_add_tail(&accel_dev->list, &accel_table);
-		accel_dev->accel_id = num_devices++;
-
+		accel_dev->accel_id = adf_find_free_id();
+		if (accel_dev->accel_id > ADF_MAX_DEVICES) {
+			ret = -EFAULT;
+			goto unlock;
+		}
+		num_devices++;
 		map = kzalloc(sizeof(*map), GFP_KERNEL);
 		if (!map) {
 			ret = -ENOMEM;
@@ -236,8 +256,13 @@
 			ret = -ENOMEM;
 			goto unlock;
 		}
-
-		accel_dev->accel_id = num_devices++;
+		accel_dev->accel_id = adf_find_free_id();
+		if (accel_dev->accel_id > ADF_MAX_DEVICES) {
+			kfree(map);
+			ret = -EFAULT;
+			goto unlock;
+		}
+		num_devices++;
 		list_add_tail(&accel_dev->list, &accel_table);
 		map->bdf = adf_get_vf_num(accel_dev);
 		map->id = accel_dev->accel_id;
@@ -271,6 +296,7 @@
 {
 	mutex_lock(&table_lock);
 	if (!accel_dev->is_vf || (accel_dev->is_vf && !pf)) {
+		id_map[accel_dev->accel_id] = 0;
 		num_devices--;
 	} else if (accel_dev->is_vf && pf) {
 		struct vf_id_map *map, *next;
diff --git a/drivers/crypto/qat/qat_common/adf_hw_arbiter.c b/drivers/crypto/qat/qat_common/adf_hw_arbiter.c
index 6849422..f267d9e 100644
--- a/drivers/crypto/qat/qat_common/adf_hw_arbiter.c
+++ b/drivers/crypto/qat/qat_common/adf_hw_arbiter.c
@@ -45,6 +45,7 @@
   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */
 #include "adf_accel_devices.h"
+#include "adf_common_drv.h"
 #include "adf_transport_internal.h"
 
 #define ADF_ARB_NUM 4
@@ -124,19 +125,12 @@
 }
 EXPORT_SYMBOL_GPL(adf_init_arb);
 
-/**
- * adf_update_ring_arb() - update ring arbitration rgister
- * @accel_dev:  Pointer to ring data.
- *
- * Function enables or disables rings for/from arbitration.
- */
 void adf_update_ring_arb(struct adf_etr_ring_data *ring)
 {
 	WRITE_CSR_ARB_RINGSRVARBEN(ring->bank->csr_addr,
 				   ring->bank->bank_number,
 				   ring->bank->ring_mask & 0xFF);
 }
-EXPORT_SYMBOL_GPL(adf_update_ring_arb);
 
 void adf_exit_arb(struct adf_accel_dev *accel_dev)
 {
diff --git a/drivers/crypto/qat/qat_common/adf_init.c b/drivers/crypto/qat/qat_common/adf_init.c
index d873eee..ef5575e 100644
--- a/drivers/crypto/qat/qat_common/adf_init.c
+++ b/drivers/crypto/qat/qat_common/adf_init.c
@@ -62,15 +62,6 @@
 	mutex_unlock(&service_lock);
 }
 
-/**
- * adf_service_register() - Register acceleration service in the accel framework
- * @service:    Pointer to the service
- *
- * Function adds the acceleration service to the acceleration framework.
- * To be used by QAT device specific drivers.
- *
- * Return: 0 on success, error code otherwise.
- */
 int adf_service_register(struct service_hndl *service)
 {
 	service->init_status = 0;
@@ -78,7 +69,6 @@
 	adf_service_add(service);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(adf_service_register);
 
 static void adf_service_remove(struct service_hndl *service)
 {
@@ -87,15 +77,6 @@
 	mutex_unlock(&service_lock);
 }
 
-/**
- * adf_service_unregister() - Unregister acceleration service from the framework
- * @service:    Pointer to the service
- *
- * Function remove the acceleration service from the acceleration framework.
- * To be used by QAT device specific drivers.
- *
- * Return: 0 on success, error code otherwise.
- */
 int adf_service_unregister(struct service_hndl *service)
 {
 	if (service->init_status || service->start_status) {
@@ -105,7 +86,6 @@
 	adf_service_remove(service);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(adf_service_unregister);
 
 /**
  * adf_dev_init() - Init data structures and services for the given accel device
@@ -366,6 +346,7 @@
 
 	hw_data->disable_iov(accel_dev);
 	adf_cleanup_etr_data(accel_dev);
+	adf_dev_restore(accel_dev);
 }
 EXPORT_SYMBOL_GPL(adf_dev_shutdown);
 
diff --git a/drivers/crypto/qat/qat_dh895xcc/adf_isr.c b/drivers/crypto/qat/qat_common/adf_isr.c
similarity index 90%
rename from drivers/crypto/qat/qat_dh895xcc/adf_isr.c
rename to drivers/crypto/qat/qat_common/adf_isr.c
index 5570f78..b81f79a 100644
--- a/drivers/crypto/qat/qat_dh895xcc/adf_isr.c
+++ b/drivers/crypto/qat/qat_common/adf_isr.c
@@ -51,15 +51,13 @@
 #include <linux/slab.h>
 #include <linux/errno.h>
 #include <linux/interrupt.h>
-#include <adf_accel_devices.h>
-#include <adf_common_drv.h>
-#include <adf_cfg.h>
-#include <adf_cfg_strings.h>
-#include <adf_cfg_common.h>
-#include <adf_transport_access_macros.h>
-#include <adf_transport_internal.h>
-#include "adf_drv.h"
-#include "adf_dh895xcc_hw_data.h"
+#include "adf_accel_devices.h"
+#include "adf_common_drv.h"
+#include "adf_cfg.h"
+#include "adf_cfg_strings.h"
+#include "adf_cfg_common.h"
+#include "adf_transport_access_macros.h"
+#include "adf_transport_internal.h"
 
 static int adf_enable_msix(struct adf_accel_dev *accel_dev)
 {
@@ -109,14 +107,16 @@
 #ifdef CONFIG_PCI_IOV
 	/* If SR-IOV is enabled (vf_info is non-NULL), check for VF->PF ints */
 	if (accel_dev->pf.vf_info) {
-		void __iomem *pmisc_bar_addr =
-		    (&GET_BARS(accel_dev)[ADF_DH895XCC_PMISC_BAR])->virt_addr;
+		struct adf_hw_device_data *hw_data = accel_dev->hw_device;
+		struct adf_bar *pmisc =
+			&GET_BARS(accel_dev)[hw_data->get_misc_bar_id(hw_data)];
+		void __iomem *pmisc_bar_addr = pmisc->virt_addr;
 		u32 vf_mask;
 
 		/* Get the interrupt sources triggered by VFs */
-		vf_mask = ((ADF_CSR_RD(pmisc_bar_addr, ADF_DH895XCC_ERRSOU5) &
+		vf_mask = ((ADF_CSR_RD(pmisc_bar_addr, ADF_ERRSOU5) &
 			    0x0000FFFF) << 16) |
-			  ((ADF_CSR_RD(pmisc_bar_addr, ADF_DH895XCC_ERRSOU3) &
+			  ((ADF_CSR_RD(pmisc_bar_addr, ADF_ERRSOU3) &
 			    0x01FFFE00) >> 9);
 
 		if (vf_mask) {
@@ -301,6 +301,12 @@
 	}
 }
 
+/**
+ * adf_vf_isr_resource_free() - Free IRQ for acceleration device
+ * @accel_dev:  Pointer to acceleration device.
+ *
+ * Function frees interrupts for acceleration device.
+ */
 void adf_isr_resource_free(struct adf_accel_dev *accel_dev)
 {
 	adf_free_irqs(accel_dev);
@@ -308,7 +314,16 @@
 	adf_disable_msix(&accel_dev->accel_pci_dev);
 	adf_isr_free_msix_entry_table(accel_dev);
 }
+EXPORT_SYMBOL_GPL(adf_isr_resource_free);
 
+/**
+ * adf_vf_isr_resource_alloc() - Allocate IRQ for acceleration device
+ * @accel_dev:  Pointer to acceleration device.
+ *
+ * Function allocates interrupts for acceleration device.
+ *
+ * Return: 0 on success, error code otherwise.
+ */
 int adf_isr_resource_alloc(struct adf_accel_dev *accel_dev)
 {
 	int ret;
@@ -330,3 +345,4 @@
 	adf_isr_resource_free(accel_dev);
 	return -EFAULT;
 }
+EXPORT_SYMBOL_GPL(adf_isr_resource_alloc);
diff --git a/drivers/crypto/qat/qat_common/adf_pf2vf_msg.c b/drivers/crypto/qat/qat_common/adf_pf2vf_msg.c
index 5fdbad8..b3875fd 100644
--- a/drivers/crypto/qat/qat_common/adf_pf2vf_msg.c
+++ b/drivers/crypto/qat/qat_common/adf_pf2vf_msg.c
@@ -45,8 +45,6 @@
   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */
 
-#include <linux/pci.h>
-#include <linux/mutex.h>
 #include <linux/delay.h>
 #include "adf_accel_devices.h"
 #include "adf_common_drv.h"
@@ -58,12 +56,6 @@
 #define ADF_DH895XCC_ERRMSK5	(ADF_DH895XCC_EP_OFFSET + 0xDC)
 #define ADF_DH895XCC_ERRMSK5_VF2PF_U_MASK(vf_mask) (vf_mask >> 16)
 
-/**
- * adf_enable_pf2vf_interrupts() - Enable PF to VF interrupts
- * @accel_dev:  Pointer to acceleration device.
- *
- * Function enables PF to VF interrupts
- */
 void adf_enable_pf2vf_interrupts(struct adf_accel_dev *accel_dev)
 {
 	struct adf_accel_pci *pci_info = &accel_dev->accel_pci_dev;
@@ -73,14 +65,7 @@
 
 	ADF_CSR_WR(pmisc_bar_addr, hw_data->get_vintmsk_offset(0), 0x0);
 }
-EXPORT_SYMBOL_GPL(adf_enable_pf2vf_interrupts);
 
-/**
- * adf_disable_pf2vf_interrupts() - Disable PF to VF interrupts
- * @accel_dev:  Pointer to acceleration device.
- *
- * Function disables PF to VF interrupts
- */
 void adf_disable_pf2vf_interrupts(struct adf_accel_dev *accel_dev)
 {
 	struct adf_accel_pci *pci_info = &accel_dev->accel_pci_dev;
@@ -90,7 +75,6 @@
 
 	ADF_CSR_WR(pmisc_bar_addr, hw_data->get_vintmsk_offset(0), 0x2);
 }
-EXPORT_SYMBOL_GPL(adf_disable_pf2vf_interrupts);
 
 void adf_enable_vf2pf_interrupts(struct adf_accel_dev *accel_dev,
 				 u32 vf_mask)
@@ -116,12 +100,6 @@
 	}
 }
 
-/**
- * adf_disable_pf2vf_interrupts() - Disable VF to PF interrupts
- * @accel_dev:  Pointer to acceleration device.
- *
- * Function disables VF to PF interrupts
- */
 void adf_disable_vf2pf_interrupts(struct adf_accel_dev *accel_dev, u32 vf_mask)
 {
 	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
@@ -144,7 +122,6 @@
 		ADF_CSR_WR(pmisc_addr, ADF_DH895XCC_ERRMSK5, reg);
 	}
 }
-EXPORT_SYMBOL_GPL(adf_disable_vf2pf_interrupts);
 
 static int __adf_iov_putmsg(struct adf_accel_dev *accel_dev, u32 msg, u8 vf_nr)
 {
diff --git a/drivers/crypto/qat/qat_common/adf_transport.c b/drivers/crypto/qat/qat_common/adf_transport.c
index 3865ae8..57d2622 100644
--- a/drivers/crypto/qat/qat_common/adf_transport.c
+++ b/drivers/crypto/qat/qat_common/adf_transport.c
@@ -122,7 +122,7 @@
 		return -EAGAIN;
 	}
 	spin_lock_bh(&ring->lock);
-	memcpy(ring->base_addr + ring->tail, msg,
+	memcpy((void *)((uintptr_t)ring->base_addr + ring->tail), msg,
 	       ADF_MSG_SIZE_TO_BYTES(ring->msg_size));
 
 	ring->tail = adf_modulo(ring->tail +
@@ -137,23 +137,22 @@
 static int adf_handle_response(struct adf_etr_ring_data *ring)
 {
 	uint32_t msg_counter = 0;
-	uint32_t *msg = (uint32_t *)(ring->base_addr + ring->head);
+	uint32_t *msg = (uint32_t *)((uintptr_t)ring->base_addr + ring->head);
 
 	while (*msg != ADF_RING_EMPTY_SIG) {
 		ring->callback((uint32_t *)msg);
+		atomic_dec(ring->inflights);
 		*msg = ADF_RING_EMPTY_SIG;
 		ring->head = adf_modulo(ring->head +
 					ADF_MSG_SIZE_TO_BYTES(ring->msg_size),
 					ADF_RING_SIZE_MODULO(ring->ring_size));
 		msg_counter++;
-		msg = (uint32_t *)(ring->base_addr + ring->head);
+		msg = (uint32_t *)((uintptr_t)ring->base_addr + ring->head);
 	}
-	if (msg_counter > 0) {
+	if (msg_counter > 0)
 		WRITE_CSR_RING_HEAD(ring->bank->csr_addr,
 				    ring->bank->bank_number,
 				    ring->ring_number, ring->head);
-		atomic_sub(msg_counter, ring->inflights);
-	}
 	return 0;
 }
 
@@ -342,27 +341,15 @@
 	}
 }
 
-/**
- * adf_response_handler() - Bottom half handler response handler
- * @bank_addr:  Address of a ring bank for with the BH was scheduled.
- *
- * Function is the bottom half handler for the response from acceleration
- * device. There is one handler for every ring bank. Function checks all
- * communication rings in the bank.
- * To be used by QAT device specific drivers.
- *
- * Return: void
- */
-void adf_response_handler(unsigned long bank_addr)
+void adf_response_handler(uintptr_t bank_addr)
 {
 	struct adf_etr_bank_data *bank = (void *)bank_addr;
 
-	/* Handle all the responses nad reenable IRQs */
+	/* Handle all the responses and reenable IRQs */
 	adf_ring_response_handler(bank);
 	WRITE_CSR_INT_FLAG_AND_COL(bank->csr_addr, bank->bank_number,
 				   bank->irq_mask);
 }
-EXPORT_SYMBOL_GPL(adf_response_handler);
 
 static inline int adf_get_cfg_int(struct adf_accel_dev *accel_dev,
 				  const char *section, const char *format,
@@ -447,6 +434,7 @@
 		goto err;
 	}
 
+	WRITE_CSR_INT_FLAG(csr_addr, bank_num, ADF_BANK_INT_FLAG_CLEAR_MASK);
 	WRITE_CSR_INT_SRCSEL(csr_addr, bank_num);
 	return 0;
 err:
diff --git a/drivers/crypto/qat/qat_common/adf_transport_access_macros.h b/drivers/crypto/qat/qat_common/adf_transport_access_macros.h
index 6ad7e4e..80e02a2 100644
--- a/drivers/crypto/qat/qat_common/adf_transport_access_macros.h
+++ b/drivers/crypto/qat/qat_common/adf_transport_access_macros.h
@@ -50,12 +50,14 @@
 #include "adf_accel_devices.h"
 #define ADF_BANK_INT_SRC_SEL_MASK_0 0x4444444CUL
 #define ADF_BANK_INT_SRC_SEL_MASK_X 0x44444444UL
+#define ADF_BANK_INT_FLAG_CLEAR_MASK 0xFFFF
 #define ADF_RING_CSR_RING_CONFIG 0x000
 #define ADF_RING_CSR_RING_LBASE 0x040
 #define ADF_RING_CSR_RING_UBASE 0x080
 #define ADF_RING_CSR_RING_HEAD 0x0C0
 #define ADF_RING_CSR_RING_TAIL 0x100
 #define ADF_RING_CSR_E_STAT 0x14C
+#define ADF_RING_CSR_INT_FLAG	0x170
 #define ADF_RING_CSR_INT_SRCSEL 0x174
 #define ADF_RING_CSR_INT_SRCSEL_2 0x178
 #define ADF_RING_CSR_INT_COL_EN 0x17C
@@ -144,6 +146,9 @@
 #define WRITE_CSR_RING_TAIL(csr_base_addr, bank, ring, value) \
 	ADF_CSR_WR(csr_base_addr, (ADF_RING_BUNDLE_SIZE * bank) + \
 		ADF_RING_CSR_RING_TAIL + (ring << 2), value)
+#define WRITE_CSR_INT_FLAG(csr_base_addr, bank, value) \
+	ADF_CSR_WR(csr_base_addr, (ADF_RING_BUNDLE_SIZE * (bank)) + \
+			ADF_RING_CSR_INT_FLAG, value)
 #define WRITE_CSR_INT_SRCSEL(csr_base_addr, bank) \
 do { \
 	ADF_CSR_WR(csr_base_addr, (ADF_RING_BUNDLE_SIZE * bank) + \
diff --git a/drivers/crypto/qat/qat_common/adf_transport_internal.h b/drivers/crypto/qat/qat_common/adf_transport_internal.h
index a486962..bb88336 100644
--- a/drivers/crypto/qat/qat_common/adf_transport_internal.h
+++ b/drivers/crypto/qat/qat_common/adf_transport_internal.h
@@ -91,7 +91,7 @@
 	struct dentry *debug;
 };
 
-void adf_response_handler(unsigned long bank_addr);
+void adf_response_handler(uintptr_t bank_addr);
 #ifdef CONFIG_DEBUG_FS
 #include <linux/debugfs.h>
 int adf_bank_debugfs_add(struct adf_etr_bank_data *bank);
diff --git a/drivers/crypto/qat/qat_dh895xccvf/adf_isr.c b/drivers/crypto/qat/qat_common/adf_vf_isr.c
similarity index 81%
rename from drivers/crypto/qat/qat_dh895xccvf/adf_isr.c
rename to drivers/crypto/qat/qat_common/adf_vf_isr.c
index 87c5d8a..09427b3 100644
--- a/drivers/crypto/qat/qat_dh895xccvf/adf_isr.c
+++ b/drivers/crypto/qat/qat_common/adf_vf_isr.c
@@ -51,16 +51,18 @@
 #include <linux/slab.h>
 #include <linux/errno.h>
 #include <linux/interrupt.h>
-#include <adf_accel_devices.h>
-#include <adf_common_drv.h>
-#include <adf_cfg.h>
-#include <adf_cfg_strings.h>
-#include <adf_cfg_common.h>
-#include <adf_transport_access_macros.h>
-#include <adf_transport_internal.h>
-#include <adf_pf2vf_msg.h>
-#include "adf_drv.h"
-#include "adf_dh895xccvf_hw_data.h"
+#include "adf_accel_devices.h"
+#include "adf_common_drv.h"
+#include "adf_cfg.h"
+#include "adf_cfg_strings.h"
+#include "adf_cfg_common.h"
+#include "adf_transport_access_macros.h"
+#include "adf_transport_internal.h"
+#include "adf_pf2vf_msg.h"
+
+#define ADF_VINTSOU_OFFSET	0x204
+#define ADF_VINTSOU_BUN		BIT(0)
+#define ADF_VINTSOU_PF2VF	BIT(1)
 
 static int adf_enable_msi(struct adf_accel_dev *accel_dev)
 {
@@ -91,12 +93,14 @@
 static void adf_pf2vf_bh_handler(void *data)
 {
 	struct adf_accel_dev *accel_dev = data;
-	void __iomem *pmisc_bar_addr =
-		(&GET_BARS(accel_dev)[ADF_DH895XCCIOV_PMISC_BAR])->virt_addr;
+	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
+	struct adf_bar *pmisc =
+			&GET_BARS(accel_dev)[hw_data->get_misc_bar_id(hw_data)];
+	void __iomem *pmisc_bar_addr = pmisc->virt_addr;
 	u32 msg;
 
 	/* Read the message from PF */
-	msg = ADF_CSR_RD(pmisc_bar_addr, ADF_DH895XCCIOV_PF2VF_OFFSET);
+	msg = ADF_CSR_RD(pmisc_bar_addr, hw_data->get_pf2vf_offset(0));
 
 	if (!(msg & ADF_PF2VF_MSGORIGIN_SYSTEM))
 		/* Ignore legacy non-system (non-kernel) PF2VF messages */
@@ -124,8 +128,8 @@
 	}
 
 	/* To ack, clear the PF2VFINT bit */
-	msg &= ~ADF_DH895XCC_PF2VF_PF2VFINT;
-	ADF_CSR_WR(pmisc_bar_addr, ADF_DH895XCCIOV_PF2VF_OFFSET, msg);
+	msg &= ~BIT(0);
+	ADF_CSR_WR(pmisc_bar_addr, hw_data->get_pf2vf_offset(0), msg);
 
 	/* Re-enable PF2VF interrupts */
 	adf_enable_pf2vf_interrupts(accel_dev);
@@ -155,15 +159,17 @@
 static irqreturn_t adf_isr(int irq, void *privdata)
 {
 	struct adf_accel_dev *accel_dev = privdata;
-	void __iomem *pmisc_bar_addr =
-		(&GET_BARS(accel_dev)[ADF_DH895XCCIOV_PMISC_BAR])->virt_addr;
+	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
+	struct adf_bar *pmisc =
+			&GET_BARS(accel_dev)[hw_data->get_misc_bar_id(hw_data)];
+	void __iomem *pmisc_bar_addr = pmisc->virt_addr;
 	u32 v_int;
 
 	/* Read VF INT source CSR to determine the source of VF interrupt */
-	v_int = ADF_CSR_RD(pmisc_bar_addr, ADF_DH895XCCIOV_VINTSOU_OFFSET);
+	v_int = ADF_CSR_RD(pmisc_bar_addr, ADF_VINTSOU_OFFSET);
 
 	/* Check for PF2VF interrupt */
-	if (v_int & ADF_DH895XCC_VINTSOU_PF2VF) {
+	if (v_int & ADF_VINTSOU_PF2VF) {
 		/* Disable PF to VF interrupt */
 		adf_disable_pf2vf_interrupts(accel_dev);
 
@@ -173,7 +179,7 @@
 	}
 
 	/* Check bundle interrupt */
-	if (v_int & ADF_DH895XCC_VINTSOU_BUN) {
+	if (v_int & ADF_VINTSOU_BUN) {
 		struct adf_etr_data *etr_data = accel_dev->transport;
 		struct adf_etr_bank_data *bank = &etr_data->banks[0];
 
@@ -226,6 +232,12 @@
 	tasklet_kill(&priv_data->banks[0].resp_handler);
 }
 
+/**
+ * adf_vf_isr_resource_free() - Free IRQ for acceleration device
+ * @accel_dev:  Pointer to acceleration device.
+ *
+ * Function frees interrupts for acceleration device virtual function.
+ */
 void adf_vf_isr_resource_free(struct adf_accel_dev *accel_dev)
 {
 	struct pci_dev *pdev = accel_to_pci_dev(accel_dev);
@@ -236,7 +248,16 @@
 	adf_cleanup_pf2vf_bh(accel_dev);
 	adf_disable_msi(accel_dev);
 }
+EXPORT_SYMBOL_GPL(adf_vf_isr_resource_free);
 
+/**
+ * adf_vf_isr_resource_alloc() - Allocate IRQ for acceleration device
+ * @accel_dev:  Pointer to acceleration device.
+ *
+ * Function allocates interrupts for acceleration device virtual function.
+ *
+ * Return: 0 on success, error code otherwise.
+ */
 int adf_vf_isr_resource_alloc(struct adf_accel_dev *accel_dev)
 {
 	if (adf_enable_msi(accel_dev))
@@ -256,3 +277,4 @@
 	adf_vf_isr_resource_free(accel_dev);
 	return -EFAULT;
 }
+EXPORT_SYMBOL_GPL(adf_vf_isr_resource_alloc);
diff --git a/drivers/crypto/qat/qat_common/icp_qat_fw_loader_handle.h b/drivers/crypto/qat/qat_common/icp_qat_fw_loader_handle.h
index 5e1aa40..2ffef3e 100644
--- a/drivers/crypto/qat/qat_common/icp_qat_fw_loader_handle.h
+++ b/drivers/crypto/qat/qat_common/icp_qat_fw_loader_handle.h
@@ -68,11 +68,21 @@
 
 struct icp_qat_fw_loader_handle {
 	struct icp_qat_fw_loader_hal_handle *hal_handle;
+	struct pci_dev *pci_dev;
 	void *obj_handle;
+	void *sobj_handle;
+	bool fw_auth;
 	void __iomem *hal_sram_addr_v;
 	void __iomem *hal_cap_g_ctl_csr_addr_v;
 	void __iomem *hal_cap_ae_xfer_csr_addr_v;
 	void __iomem *hal_cap_ae_local_csr_addr_v;
 	void __iomem *hal_ep_csr_addr_v;
 };
+
+struct icp_firml_dram_desc {
+	void __iomem *dram_base_addr;
+	void *dram_base_addr_v;
+	dma_addr_t dram_bus_addr;
+	u64 dram_size;
+};
 #endif
diff --git a/drivers/crypto/qat/qat_common/icp_qat_hal.h b/drivers/crypto/qat/qat_common/icp_qat_hal.h
index 85b6d241..7187917 100644
--- a/drivers/crypto/qat/qat_common/icp_qat_hal.h
+++ b/drivers/crypto/qat/qat_common/icp_qat_hal.h
@@ -81,6 +81,31 @@
 	LOCAL_CSR_STATUS = 0x180,
 };
 
+enum fcu_csr {
+	FCU_CONTROL           = 0x8c0,
+	FCU_STATUS            = 0x8c4,
+	FCU_STATUS1           = 0x8c8,
+	FCU_DRAM_ADDR_LO      = 0x8cc,
+	FCU_DRAM_ADDR_HI      = 0x8d0,
+	FCU_RAMBASE_ADDR_HI   = 0x8d4,
+	FCU_RAMBASE_ADDR_LO   = 0x8d8
+};
+
+enum fcu_cmd {
+	FCU_CTRL_CMD_NOOP  = 0,
+	FCU_CTRL_CMD_AUTH  = 1,
+	FCU_CTRL_CMD_LOAD  = 2,
+	FCU_CTRL_CMD_START = 3
+};
+
+enum fcu_sts {
+	FCU_STS_NO_STS    = 0,
+	FCU_STS_VERI_DONE = 1,
+	FCU_STS_LOAD_DONE = 2,
+	FCU_STS_VERI_FAIL = 3,
+	FCU_STS_LOAD_FAIL = 4,
+	FCU_STS_BUSY      = 5
+};
 #define UA_ECS                      (0x1 << 31)
 #define ACS_ABO_BITPOS              31
 #define ACS_ACNO                    0x7
@@ -98,6 +123,13 @@
 #define LCS_STATUS          (0x1)
 #define MMC_SHARE_CS_BITPOS         2
 #define GLOBAL_CSR                0xA00
+#define FCU_CTRL_AE_POS     0x8
+#define FCU_AUTH_STS_MASK   0x7
+#define FCU_STS_DONE_POS    0x9
+#define FCU_STS_AUTHFWLD_POS 0X8
+#define FCU_LOADED_AE_POS   0x16
+#define FW_AUTH_WAIT_PERIOD 10
+#define FW_AUTH_MAX_RETRY   300
 
 #define SET_CAP_CSR(handle, csr, val) \
 	ADF_CSR_WR(handle->hal_cap_g_ctl_csr_addr_v, csr, val)
@@ -106,14 +138,14 @@
 #define SET_GLB_CSR(handle, csr, val) SET_CAP_CSR(handle, csr + GLOBAL_CSR, val)
 #define GET_GLB_CSR(handle, csr) GET_CAP_CSR(handle, GLOBAL_CSR + csr)
 #define AE_CSR(handle, ae) \
-	(handle->hal_cap_ae_local_csr_addr_v + \
+	((char __iomem *)handle->hal_cap_ae_local_csr_addr_v + \
 	((ae & handle->hal_handle->ae_mask) << 12))
 #define AE_CSR_ADDR(handle, ae, csr) (AE_CSR(handle, ae) + (0x3ff & csr))
 #define SET_AE_CSR(handle, ae, csr, val) \
 	ADF_CSR_WR(AE_CSR_ADDR(handle, ae, csr), 0, val)
 #define GET_AE_CSR(handle, ae, csr) ADF_CSR_RD(AE_CSR_ADDR(handle, ae, csr), 0)
 #define AE_XFER(handle, ae) \
-	(handle->hal_cap_ae_xfer_csr_addr_v + \
+	((char __iomem *)handle->hal_cap_ae_xfer_csr_addr_v + \
 	((ae & handle->hal_handle->ae_mask) << 12))
 #define AE_XFER_ADDR(handle, ae, reg) (AE_XFER(handle, ae) + \
 	((reg & 0xff) << 2))
@@ -121,5 +153,4 @@
 	ADF_CSR_WR(AE_XFER_ADDR(handle, ae, reg), 0, val)
 #define SRAM_WRITE(handle, addr, val) \
 	ADF_CSR_WR(handle->hal_sram_addr_v, addr, val)
-#define SRAM_READ(handle, addr) ADF_CSR_RD(handle->hal_sram_addr_v, addr)
 #endif
diff --git a/drivers/crypto/qat/qat_common/icp_qat_uclo.h b/drivers/crypto/qat/qat_common/icp_qat_uclo.h
index 2132a8c..d97db99 100644
--- a/drivers/crypto/qat/qat_common/icp_qat_uclo.h
+++ b/drivers/crypto/qat/qat_common/icp_qat_uclo.h
@@ -47,32 +47,55 @@
 #ifndef __ICP_QAT_UCLO_H__
 #define __ICP_QAT_UCLO_H__
 
-#define ICP_QAT_AC_C_CPU_TYPE     0x00400000
+#define ICP_QAT_AC_895XCC_DEV_TYPE 0x00400000
+#define ICP_QAT_AC_C62X_DEV_TYPE   0x01000000
+#define ICP_QAT_AC_C3XXX_DEV_TYPE  0x02000000
 #define ICP_QAT_UCLO_MAX_AE       12
 #define ICP_QAT_UCLO_MAX_CTX      8
 #define ICP_QAT_UCLO_MAX_UIMAGE   (ICP_QAT_UCLO_MAX_AE * ICP_QAT_UCLO_MAX_CTX)
 #define ICP_QAT_UCLO_MAX_USTORE   0x4000
 #define ICP_QAT_UCLO_MAX_XFER_REG 128
 #define ICP_QAT_UCLO_MAX_GPR_REG  128
-#define ICP_QAT_UCLO_MAX_NN_REG   128
 #define ICP_QAT_UCLO_MAX_LMEM_REG 1024
 #define ICP_QAT_UCLO_AE_ALL_CTX   0xff
 #define ICP_QAT_UOF_OBJID_LEN     8
 #define ICP_QAT_UOF_FID 0xc6c2
 #define ICP_QAT_UOF_MAJVER 0x4
 #define ICP_QAT_UOF_MINVER 0x11
-#define ICP_QAT_UOF_NN_MODE_NOTCARE   0xff
 #define ICP_QAT_UOF_OBJS        "UOF_OBJS"
 #define ICP_QAT_UOF_STRT        "UOF_STRT"
-#define ICP_QAT_UOF_GTID        "UOF_GTID"
 #define ICP_QAT_UOF_IMAG        "UOF_IMAG"
 #define ICP_QAT_UOF_IMEM        "UOF_IMEM"
-#define ICP_QAT_UOF_MSEG        "UOF_MSEG"
 #define ICP_QAT_UOF_LOCAL_SCOPE     1
 #define ICP_QAT_UOF_INIT_EXPR               0
 #define ICP_QAT_UOF_INIT_REG                1
 #define ICP_QAT_UOF_INIT_REG_CTX            2
 #define ICP_QAT_UOF_INIT_EXPR_ENDIAN_SWAP   3
+#define ICP_QAT_SUOF_OBJ_ID_LEN             8
+#define ICP_QAT_SUOF_FID  0x53554f46
+#define ICP_QAT_SUOF_MAJVER 0x0
+#define ICP_QAT_SUOF_MINVER 0x1
+#define ICP_QAT_SIMG_AE_INIT_SEQ_LEN    (50 * sizeof(unsigned long long))
+#define ICP_QAT_SIMG_AE_INSTS_LEN       (0x4000 * sizeof(unsigned long long))
+#define ICP_QAT_CSS_FWSK_MODULUS_LEN    256
+#define ICP_QAT_CSS_FWSK_EXPONENT_LEN   4
+#define ICP_QAT_CSS_FWSK_PAD_LEN        252
+#define ICP_QAT_CSS_FWSK_PUB_LEN   (ICP_QAT_CSS_FWSK_MODULUS_LEN + \
+				    ICP_QAT_CSS_FWSK_EXPONENT_LEN + \
+				    ICP_QAT_CSS_FWSK_PAD_LEN)
+#define ICP_QAT_CSS_SIGNATURE_LEN   256
+#define ICP_QAT_CSS_AE_IMG_LEN     (sizeof(struct icp_qat_simg_ae_mode) + \
+				    ICP_QAT_SIMG_AE_INIT_SEQ_LEN +         \
+				    ICP_QAT_SIMG_AE_INSTS_LEN)
+#define ICP_QAT_CSS_AE_SIMG_LEN    (sizeof(struct icp_qat_css_hdr) + \
+				    ICP_QAT_CSS_FWSK_PUB_LEN + \
+				    ICP_QAT_CSS_SIGNATURE_LEN + \
+				    ICP_QAT_CSS_AE_IMG_LEN)
+#define ICP_QAT_AE_IMG_OFFSET	   (sizeof(struct icp_qat_css_hdr) + \
+				    ICP_QAT_CSS_FWSK_MODULUS_LEN + \
+				    ICP_QAT_CSS_FWSK_EXPONENT_LEN + \
+				    ICP_QAT_CSS_SIGNATURE_LEN)
+#define ICP_QAT_CSS_MAX_IMAGE_LEN   0x40000
 
 #define ICP_QAT_CTX_MODE(ae_mode) ((ae_mode) & 0xf)
 #define ICP_QAT_NN_MODE(ae_mode) (((ae_mode) >> 0x4) & 0xf)
@@ -112,6 +135,11 @@
 	ICP_NEIGH_REL,
 };
 
+enum icp_qat_css_fwtype {
+	CSS_AE_FIRMWARE = 0,
+	CSS_MMP_FIRMWARE = 1
+};
+
 struct icp_qat_uclo_page {
 	struct icp_qat_uclo_encap_page *encap_page;
 	struct icp_qat_uclo_region *region;
@@ -235,7 +263,7 @@
 };
 
 struct icp_qat_uof_objhdr {
-	unsigned int cpu_type;
+	unsigned int ac_dev_type;
 	unsigned short min_cpu_ver;
 	unsigned short max_cpu_ver;
 	short max_chunks;
@@ -326,7 +354,7 @@
 	unsigned int img_name;
 	unsigned int ae_assigned;
 	unsigned int ctx_assigned;
-	unsigned int cpu_type;
+	unsigned int ac_dev_type;
 	unsigned int entry_address;
 	unsigned int fill_pattern[2];
 	unsigned int reloadable_size;
@@ -374,4 +402,127 @@
 	unsigned int size;
 	struct icp_qat_uof_batch_init *next;
 };
+
+struct icp_qat_suof_img_hdr {
+	char          *simg_buf;
+	unsigned long simg_len;
+	char          *css_header;
+	char          *css_key;
+	char          *css_signature;
+	char          *css_simg;
+	unsigned long simg_size;
+	unsigned int  ae_num;
+	unsigned int  ae_mask;
+	unsigned int  fw_type;
+	unsigned long simg_name;
+	unsigned long appmeta_data;
+};
+
+struct icp_qat_suof_img_tbl {
+	unsigned int num_simgs;
+	struct icp_qat_suof_img_hdr *simg_hdr;
+};
+
+struct icp_qat_suof_handle {
+	unsigned int  file_id;
+	unsigned int  check_sum;
+	char          min_ver;
+	char          maj_ver;
+	char          fw_type;
+	char          *suof_buf;
+	unsigned int  suof_size;
+	char          *sym_str;
+	unsigned int  sym_size;
+	struct icp_qat_suof_img_tbl img_table;
+};
+
+struct icp_qat_fw_auth_desc {
+	unsigned int   img_len;
+	unsigned int   reserved;
+	unsigned int   css_hdr_high;
+	unsigned int   css_hdr_low;
+	unsigned int   img_high;
+	unsigned int   img_low;
+	unsigned int   signature_high;
+	unsigned int   signature_low;
+	unsigned int   fwsk_pub_high;
+	unsigned int   fwsk_pub_low;
+	unsigned int   img_ae_mode_data_high;
+	unsigned int   img_ae_mode_data_low;
+	unsigned int   img_ae_init_data_high;
+	unsigned int   img_ae_init_data_low;
+	unsigned int   img_ae_insts_high;
+	unsigned int   img_ae_insts_low;
+};
+
+struct icp_qat_auth_chunk {
+	struct icp_qat_fw_auth_desc fw_auth_desc;
+	u64 chunk_size;
+	u64 chunk_bus_addr;
+};
+
+struct icp_qat_css_hdr {
+	unsigned int module_type;
+	unsigned int header_len;
+	unsigned int header_ver;
+	unsigned int module_id;
+	unsigned int module_vendor;
+	unsigned int date;
+	unsigned int size;
+	unsigned int key_size;
+	unsigned int module_size;
+	unsigned int exponent_size;
+	unsigned int fw_type;
+	unsigned int reserved[21];
+};
+
+struct icp_qat_simg_ae_mode {
+	unsigned int     file_id;
+	unsigned short   maj_ver;
+	unsigned short   min_ver;
+	unsigned int     dev_type;
+	unsigned short   devmax_ver;
+	unsigned short   devmin_ver;
+	unsigned int     ae_mask;
+	unsigned int     ctx_enables;
+	char             fw_type;
+	char             ctx_mode;
+	char             nn_mode;
+	char             lm0_mode;
+	char             lm1_mode;
+	char             scs_mode;
+	char             lm2_mode;
+	char             lm3_mode;
+	char             tindex_mode;
+	unsigned char    reserved[7];
+	char             simg_name[256];
+	char             appmeta_data[256];
+};
+
+struct icp_qat_suof_filehdr {
+	unsigned int     file_id;
+	unsigned int     check_sum;
+	char             min_ver;
+	char             maj_ver;
+	char             fw_type;
+	char             reserved;
+	unsigned short   max_chunks;
+	unsigned short   num_chunks;
+};
+
+struct icp_qat_suof_chunk_hdr {
+	char chunk_id[ICP_QAT_SUOF_OBJ_ID_LEN];
+	u64 offset;
+	u64 size;
+};
+
+struct icp_qat_suof_strtable {
+	unsigned int tab_length;
+	unsigned int strings;
+};
+
+struct icp_qat_suof_objhdr {
+	unsigned int img_length;
+	unsigned int reserved;
+};
 #endif
diff --git a/drivers/crypto/qat/qat_common/qat_crypto.c b/drivers/crypto/qat/qat_common/qat_crypto.c
index 9cab154..3852d31 100644
--- a/drivers/crypto/qat/qat_common/qat_crypto.c
+++ b/drivers/crypto/qat/qat_common/qat_crypto.c
@@ -49,6 +49,7 @@
 #include "adf_accel_devices.h"
 #include "adf_common_drv.h"
 #include "adf_transport.h"
+#include "adf_transport_access_macros.h"
 #include "adf_cfg.h"
 #include "adf_cfg_strings.h"
 #include "qat_crypto.h"
@@ -66,13 +67,10 @@
 
 static int qat_crypto_free_instances(struct adf_accel_dev *accel_dev)
 {
-	struct qat_crypto_instance *inst;
-	struct list_head *list_ptr, *tmp;
+	struct qat_crypto_instance *inst, *tmp;
 	int i;
 
-	list_for_each_safe(list_ptr, tmp, &accel_dev->crypto_list) {
-		inst = list_entry(list_ptr, struct qat_crypto_instance, list);
-
+	list_for_each_entry_safe(inst, tmp, &accel_dev->crypto_list, list) {
 		for (i = 0; i < atomic_read(&inst->refctr); i++)
 			qat_crypto_put_instance(inst);
 
@@ -88,7 +86,7 @@
 		if (inst->pke_rx)
 			adf_remove_ring(inst->pke_rx);
 
-		list_del(list_ptr);
+		list_del(&inst->list);
 		kfree(inst);
 	}
 	return 0;
@@ -96,17 +94,13 @@
 
 struct qat_crypto_instance *qat_crypto_get_instance_node(int node)
 {
-	struct adf_accel_dev *accel_dev = NULL;
-	struct qat_crypto_instance *inst = NULL;
-	struct list_head *itr;
+	struct adf_accel_dev *accel_dev = NULL, *tmp_dev;
+	struct qat_crypto_instance *inst = NULL, *tmp_inst;
 	unsigned long best = ~0;
 
-	list_for_each(itr, adf_devmgr_get_head()) {
-		struct adf_accel_dev *tmp_dev;
+	list_for_each_entry(tmp_dev, adf_devmgr_get_head(), list) {
 		unsigned long ctr;
 
-		tmp_dev = list_entry(itr, struct adf_accel_dev, list);
-
 		if ((node == dev_to_node(&GET_DEV(tmp_dev)) ||
 		     dev_to_node(&GET_DEV(tmp_dev)) < 0) &&
 		    adf_dev_started(tmp_dev) &&
@@ -118,19 +112,16 @@
 			}
 		}
 	}
-	if (!accel_dev)
+
+	if (!accel_dev) {
 		pr_info("QAT: Could not find a device on node %d\n", node);
-
-	/* Get any started device */
-	list_for_each(itr, adf_devmgr_get_head()) {
-		struct adf_accel_dev *tmp_dev;
-
-		tmp_dev = list_entry(itr, struct adf_accel_dev, list);
-
-		if (adf_dev_started(tmp_dev) &&
-		    !list_empty(&tmp_dev->crypto_list)) {
-			accel_dev = tmp_dev;
-			break;
+		/* Get any started device */
+		list_for_each_entry(tmp_dev, adf_devmgr_get_head(), list) {
+			if (adf_dev_started(tmp_dev) &&
+			    !list_empty(&tmp_dev->crypto_list)) {
+				accel_dev = tmp_dev;
+				break;
+			}
 		}
 	}
 
@@ -138,11 +129,9 @@
 		return NULL;
 
 	best = ~0;
-	list_for_each(itr, &accel_dev->crypto_list) {
-		struct qat_crypto_instance *tmp_inst;
+	list_for_each_entry(tmp_inst, &accel_dev->crypto_list, list) {
 		unsigned long ctr;
 
-		tmp_inst = list_entry(itr, struct qat_crypto_instance, list);
 		ctr = atomic_read(&tmp_inst->refctr);
 		if (best > ctr) {
 			inst = tmp_inst;
@@ -159,6 +148,97 @@
 	return inst;
 }
 
+/**
+ * qat_crypto_dev_config() - create dev config required to create crypto inst.
+ *
+ * @accel_dev: Pointer to acceleration device.
+ *
+ * Function creates device configuration required to create crypto instances
+ *
+ * Return: 0 on success, error code otherwise.
+ */
+int qat_crypto_dev_config(struct adf_accel_dev *accel_dev)
+{
+	int cpus = num_online_cpus();
+	int banks = GET_MAX_BANKS(accel_dev);
+	int instances = min(cpus, banks);
+	char key[ADF_CFG_MAX_KEY_LEN_IN_BYTES];
+	int i;
+	unsigned long val;
+
+	if (adf_cfg_section_add(accel_dev, ADF_KERNEL_SEC))
+		goto err;
+	if (adf_cfg_section_add(accel_dev, "Accelerator0"))
+		goto err;
+	for (i = 0; i < instances; i++) {
+		val = i;
+		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_BANK_NUM, i);
+		if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+						key, (void *)&val, ADF_DEC))
+			goto err;
+
+		snprintf(key, sizeof(key), ADF_CY "%d" ADF_ETRMGR_CORE_AFFINITY,
+			 i);
+		if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+						key, (void *)&val, ADF_DEC))
+			goto err;
+
+		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_ASYM_SIZE, i);
+		val = 128;
+		if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+						key, (void *)&val, ADF_DEC))
+			goto err;
+
+		val = 512;
+		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_SYM_SIZE, i);
+		if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+						key, (void *)&val, ADF_DEC))
+			goto err;
+
+		val = 0;
+		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_ASYM_TX, i);
+		if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+						key, (void *)&val, ADF_DEC))
+			goto err;
+
+		val = 2;
+		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_SYM_TX, i);
+		if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+						key, (void *)&val, ADF_DEC))
+			goto err;
+
+		val = 8;
+		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_ASYM_RX, i);
+		if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+						key, (void *)&val, ADF_DEC))
+			goto err;
+
+		val = 10;
+		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_SYM_RX, i);
+		if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+						key, (void *)&val, ADF_DEC))
+			goto err;
+
+		val = ADF_COALESCING_DEF_TIME;
+		snprintf(key, sizeof(key), ADF_ETRMGR_COALESCE_TIMER_FORMAT, i);
+		if (adf_cfg_add_key_value_param(accel_dev, "Accelerator0",
+						key, (void *)&val, ADF_DEC))
+			goto err;
+	}
+
+	val = i;
+	if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+					ADF_NUM_CY, (void *)&val, ADF_DEC))
+		goto err;
+
+	set_bit(ADF_STATUS_CONFIGURED, &accel_dev->status);
+	return 0;
+err:
+	dev_err(&GET_DEV(accel_dev), "Failed to start QAT accel dev\n");
+	return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(qat_crypto_dev_config);
+
 static int qat_crypto_create_instances(struct adf_accel_dev *accel_dev)
 {
 	int i;
diff --git a/drivers/crypto/qat/qat_common/qat_hal.c b/drivers/crypto/qat/qat_common/qat_hal.c
index 380e761..0ac0ba8 100644
--- a/drivers/crypto/qat/qat_common/qat_hal.c
+++ b/drivers/crypto/qat/qat_common/qat_hal.c
@@ -45,21 +45,22 @@
   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */
 #include <linux/slab.h>
+#include <linux/delay.h>
 
 #include "adf_accel_devices.h"
 #include "adf_common_drv.h"
 #include "icp_qat_hal.h"
 #include "icp_qat_uclo.h"
 
-#define BAD_REGADDR               0xffff
-#define MAX_RETRY_TIMES           10000
-#define INIT_CTX_ARB_VALUE        0x0
+#define BAD_REGADDR	       0xffff
+#define MAX_RETRY_TIMES	   10000
+#define INIT_CTX_ARB_VALUE	0x0
 #define INIT_CTX_ENABLE_VALUE     0x0
-#define INIT_PC_VALUE             0x0
+#define INIT_PC_VALUE	     0x0
 #define INIT_WAKEUP_EVENTS_VALUE  0x1
 #define INIT_SIG_EVENTS_VALUE     0x1
 #define INIT_CCENABLE_VALUE       0x2000
-#define RST_CSR_QAT_LSB           20
+#define RST_CSR_QAT_LSB	   20
 #define RST_CSR_AE_LSB		  0
 #define MC_TIMESTAMP_ENABLE       (0x1 << 7)
 
@@ -185,7 +186,7 @@
 		if (elapsed_cycles >= 8 && !(csr & (1 << ACS_ABO_BITPOS)))
 			return 0;
 	}
-	if (!times) {
+	if (times < 0) {
 		pr_err("QAT: wait_num_cycles time out\n");
 		return -EFAULT;
 	}
@@ -391,9 +392,6 @@
 	unsigned int times = MAX_RETRY_TIMES;
 
 	for (ae = 0; ae < handle->hal_handle->ae_max_num; ae++) {
-		if (!(handle->hal_handle->ae_mask & (1 << ae)))
-			continue;
-
 		qat_hal_rd_ae_csr(handle, ae, PROFILE_COUNT,
 				  (unsigned int *)&base_cnt);
 		base_cnt &= 0xffff;
@@ -413,6 +411,20 @@
 	return 0;
 }
 
+int qat_hal_check_ae_active(struct icp_qat_fw_loader_handle *handle,
+			    unsigned int ae)
+{
+	unsigned int enable = 0, active = 0;
+
+	qat_hal_rd_ae_csr(handle, ae, CTX_ENABLES, &enable);
+	qat_hal_rd_ae_csr(handle, ae, ACTIVE_CTX_STATUS, &active);
+	if ((enable & (0xff << CE_ENABLE_BITPOS)) ||
+	    (active & (1 << ACS_ABO_BITPOS)))
+		return 1;
+	else
+		return 0;
+}
+
 static void qat_hal_reset_timestamp(struct icp_qat_fw_loader_handle *handle)
 {
 	unsigned int misc_ctl;
@@ -425,8 +437,6 @@
 			    (~MC_TIMESTAMP_ENABLE));
 
 	for (ae = 0; ae < handle->hal_handle->ae_max_num; ae++) {
-		if (!(handle->hal_handle->ae_mask & (1 << ae)))
-			continue;
 		qat_hal_wr_ae_csr(handle, ae, TIMESTAMP_LOW, 0);
 		qat_hal_wr_ae_csr(handle, ae, TIMESTAMP_HIGH, 0);
 	}
@@ -440,8 +450,9 @@
 #define ESRAM_AUTO_INIT_CSR_OFFSET 0xC1C
 static int qat_hal_init_esram(struct icp_qat_fw_loader_handle *handle)
 {
-	void __iomem *csr_addr = handle->hal_ep_csr_addr_v +
-				 ESRAM_AUTO_INIT_CSR_OFFSET;
+	void __iomem *csr_addr =
+			(void __iomem *)((uintptr_t)handle->hal_ep_csr_addr_v +
+			ESRAM_AUTO_INIT_CSR_OFFSET);
 	unsigned int csr_val, times = 30;
 
 	csr_val = ADF_CSR_RD(csr_addr, 0);
@@ -493,8 +504,6 @@
 
 	/* Set undefined power-up/reset states to reasonable default values */
 	for (ae = 0; ae < handle->hal_handle->ae_max_num; ae++) {
-		if (!(handle->hal_handle->ae_mask & (1 << ae)))
-			continue;
 		qat_hal_wr_ae_csr(handle, ae, CTX_ENABLES,
 				  INIT_CTX_ENABLE_VALUE);
 		qat_hal_wr_indr_csr(handle, ae, ICP_QAT_UCLO_AE_ALL_CTX,
@@ -598,25 +607,31 @@
 	qat_hal_wr_ae_csr(handle, ae, CTX_ENABLES, ctx);
 }
 
-static int qat_hal_clear_gpr(struct icp_qat_fw_loader_handle *handle)
+static void qat_hal_clear_xfer(struct icp_qat_fw_loader_handle *handle)
 {
 	unsigned char ae;
-	unsigned int ctx_mask = ICP_QAT_UCLO_AE_ALL_CTX;
-	int times = MAX_RETRY_TIMES;
-	unsigned int csr_val = 0;
 	unsigned short reg;
-	unsigned int savctx = 0;
-	int ret = 0;
 
 	for (ae = 0; ae < handle->hal_handle->ae_max_num; ae++) {
-		if (!(handle->hal_handle->ae_mask & (1 << ae)))
-			continue;
 		for (reg = 0; reg < ICP_QAT_UCLO_MAX_GPR_REG; reg++) {
 			qat_hal_init_rd_xfer(handle, ae, 0, ICP_SR_RD_ABS,
 					     reg, 0);
 			qat_hal_init_rd_xfer(handle, ae, 0, ICP_DR_RD_ABS,
 					     reg, 0);
 		}
+	}
+}
+
+static int qat_hal_clear_gpr(struct icp_qat_fw_loader_handle *handle)
+{
+	unsigned char ae;
+	unsigned int ctx_mask = ICP_QAT_UCLO_AE_ALL_CTX;
+	int times = MAX_RETRY_TIMES;
+	unsigned int csr_val = 0;
+	unsigned int savctx = 0;
+	int ret = 0;
+
+	for (ae = 0; ae < handle->hal_handle->ae_max_num; ae++) {
 		qat_hal_rd_ae_csr(handle, ae, AE_MISC_CONTROL, &csr_val);
 		csr_val &= ~(1 << MMC_SHARE_CS_BITPOS);
 		qat_hal_wr_ae_csr(handle, ae, AE_MISC_CONTROL, csr_val);
@@ -638,8 +653,6 @@
 		qat_hal_enable_ctx(handle, ae, ctx_mask);
 	}
 	for (ae = 0; ae < handle->hal_handle->ae_max_num; ae++) {
-		if (!(handle->hal_handle->ae_mask & (1 << ae)))
-			continue;
 		/* wait for AE to finish */
 		do {
 			ret = qat_hal_wait_cycles(handle, ae, 20, 1);
@@ -667,10 +680,10 @@
 	return 0;
 }
 
-#define ICP_DH895XCC_AE_OFFSET      0x20000
-#define ICP_DH895XCC_CAP_OFFSET     (ICP_DH895XCC_AE_OFFSET + 0x10000)
+#define ICP_QAT_AE_OFFSET	0x20000
+#define ICP_QAT_CAP_OFFSET       (ICP_QAT_AE_OFFSET + 0x10000)
 #define LOCAL_TO_XFER_REG_OFFSET    0x800
-#define ICP_DH895XCC_EP_OFFSET      0x3a000
+#define ICP_QAT_EP_OFFSET	0x3a000
 int qat_hal_init(struct adf_accel_dev *accel_dev)
 {
 	unsigned char ae;
@@ -687,15 +700,22 @@
 	if (!handle)
 		return -ENOMEM;
 
-	handle->hal_cap_g_ctl_csr_addr_v = misc_bar->virt_addr +
-						ICP_DH895XCC_CAP_OFFSET;
-	handle->hal_cap_ae_xfer_csr_addr_v = misc_bar->virt_addr +
-						ICP_DH895XCC_AE_OFFSET;
-	handle->hal_ep_csr_addr_v = misc_bar->virt_addr +
-				    ICP_DH895XCC_EP_OFFSET;
-	handle->hal_cap_ae_local_csr_addr_v =
-		handle->hal_cap_ae_xfer_csr_addr_v + LOCAL_TO_XFER_REG_OFFSET;
 	handle->hal_sram_addr_v = sram_bar->virt_addr;
+	handle->hal_cap_g_ctl_csr_addr_v =
+		(void __iomem *)((uintptr_t)misc_bar->virt_addr +
+				 ICP_QAT_CAP_OFFSET);
+	handle->hal_cap_ae_xfer_csr_addr_v =
+		(void __iomem *)((uintptr_t)misc_bar->virt_addr +
+				 ICP_QAT_AE_OFFSET);
+	handle->hal_ep_csr_addr_v =
+		(void __iomem *)((uintptr_t)misc_bar->virt_addr +
+				 ICP_QAT_EP_OFFSET);
+	handle->hal_cap_ae_local_csr_addr_v =
+		(void __iomem *)((uintptr_t)handle->hal_cap_ae_xfer_csr_addr_v +
+				 LOCAL_TO_XFER_REG_OFFSET);
+	handle->pci_dev = pci_info->pci_dev;
+	handle->fw_auth = (handle->pci_dev->device ==
+			   ADF_DH895XCC_PCI_DEVICE_ID) ? false : true;
 	handle->hal_handle = kzalloc(sizeof(*handle->hal_handle), GFP_KERNEL);
 	if (!handle->hal_handle)
 		goto out_hal_handle;
@@ -723,14 +743,16 @@
 		dev_err(&GET_DEV(accel_dev), "qat_hal_clr_reset error\n");
 		goto out_err;
 	}
-	if (qat_hal_clear_gpr(handle))
-		goto out_err;
+	qat_hal_clear_xfer(handle);
+	if (!handle->fw_auth) {
+		if (qat_hal_clear_gpr(handle))
+			goto out_err;
+	}
+
 	/* Set SIGNATURE_ENABLE[0] to 0x1 in order to enable ALU_OUT csr */
 	for (ae = 0; ae < handle->hal_handle->ae_max_num; ae++) {
 		unsigned int csr_val = 0;
 
-		if (!(hw_data->ae_mask & (1 << ae)))
-			continue;
 		qat_hal_rd_ae_csr(handle, ae, SIGNATURE_ENABLE, &csr_val);
 		csr_val |= 0x1;
 		qat_hal_wr_ae_csr(handle, ae, SIGNATURE_ENABLE, csr_val);
@@ -756,15 +778,31 @@
 void qat_hal_start(struct icp_qat_fw_loader_handle *handle, unsigned char ae,
 		   unsigned int ctx_mask)
 {
-	qat_hal_put_wakeup_event(handle, ae, (~ctx_mask) &
+	int retry = 0;
+	unsigned int fcu_sts = 0;
+
+	if (handle->fw_auth) {
+		SET_CAP_CSR(handle, FCU_CONTROL, FCU_CTRL_CMD_START);
+		do {
+			msleep(FW_AUTH_WAIT_PERIOD);
+			fcu_sts = GET_CAP_CSR(handle, FCU_STATUS);
+			if (((fcu_sts >> FCU_STS_DONE_POS) & 0x1))
+				return;
+		} while (retry++ < FW_AUTH_MAX_RETRY);
+		pr_err("QAT: start error (AE 0x%x FCU_STS = 0x%x)\n", ae,
+		       fcu_sts);
+	} else {
+		qat_hal_put_wakeup_event(handle, ae, (~ctx_mask) &
 				 ICP_QAT_UCLO_AE_ALL_CTX, 0x10000);
-	qat_hal_enable_ctx(handle, ae, ctx_mask);
+		qat_hal_enable_ctx(handle, ae, ctx_mask);
+	}
 }
 
 void qat_hal_stop(struct icp_qat_fw_loader_handle *handle, unsigned char ae,
 		  unsigned int ctx_mask)
 {
-	qat_hal_disable_ctx(handle, ae, ctx_mask);
+	if (!handle->fw_auth)
+		qat_hal_disable_ctx(handle, ae, ctx_mask);
 }
 
 void qat_hal_set_pc(struct icp_qat_fw_loader_handle *handle,
diff --git a/drivers/crypto/qat/qat_common/qat_uclo.c b/drivers/crypto/qat/qat_common/qat_uclo.c
index c48f181..25d15f1 100644
--- a/drivers/crypto/qat/qat_common/qat_uclo.c
+++ b/drivers/crypto/qat/qat_common/qat_uclo.c
@@ -47,7 +47,7 @@
 #include <linux/slab.h>
 #include <linux/ctype.h>
 #include <linux/kernel.h>
-
+#include <linux/delay.h>
 #include "adf_accel_devices.h"
 #include "adf_common_drv.h"
 #include "icp_qat_uclo.h"
@@ -119,10 +119,10 @@
 {
 	if ((!str_table->table_len) || (str_offset > str_table->table_len))
 		return NULL;
-	return (char *)(((unsigned long)(str_table->strings)) + str_offset);
+	return (char *)(((uintptr_t)(str_table->strings)) + str_offset);
 }
 
-static int qat_uclo_check_format(struct icp_qat_uof_filehdr *hdr)
+static int qat_uclo_check_uof_format(struct icp_qat_uof_filehdr *hdr)
 {
 	int maj = hdr->maj_ver & 0xff;
 	int min = hdr->min_ver & 0xff;
@@ -139,6 +139,31 @@
 	return 0;
 }
 
+static int qat_uclo_check_suof_format(struct icp_qat_suof_filehdr *suof_hdr)
+{
+	int maj = suof_hdr->maj_ver & 0xff;
+	int min = suof_hdr->min_ver & 0xff;
+
+	if (suof_hdr->file_id != ICP_QAT_SUOF_FID) {
+		pr_err("QAT: invalid header 0x%x\n", suof_hdr->file_id);
+		return -EINVAL;
+	}
+	if (suof_hdr->fw_type != 0) {
+		pr_err("QAT: unsupported firmware type\n");
+		return -EINVAL;
+	}
+	if (suof_hdr->num_chunks <= 0x1) {
+		pr_err("QAT: SUOF chunk amount is incorrect\n");
+		return -EINVAL;
+	}
+	if (maj != ICP_QAT_SUOF_MAJVER || min != ICP_QAT_SUOF_MINVER) {
+		pr_err("QAT: bad SUOF version, major 0x%x, minor 0x%x\n",
+		       maj, min);
+		return -EINVAL;
+	}
+	return 0;
+}
+
 static void qat_uclo_wr_sram_by_words(struct icp_qat_fw_loader_handle *handle,
 				      unsigned int addr, unsigned int *val,
 				      unsigned int num_in_bytes)
@@ -275,7 +300,7 @@
 	unsigned int i, flag = 0;
 
 	mem_val_attr =
-		(struct icp_qat_uof_memvar_attr *)((unsigned long)init_mem +
+		(struct icp_qat_uof_memvar_attr *)((uintptr_t)init_mem +
 		sizeof(struct icp_qat_uof_initmem));
 
 	init_header = *init_tab_base;
@@ -425,8 +450,8 @@
 			if (qat_uclo_init_ae_memory(handle, initmem))
 				return -EINVAL;
 		}
-		initmem = (struct icp_qat_uof_initmem *)((unsigned long)(
-			(unsigned long)initmem +
+		initmem = (struct icp_qat_uof_initmem *)((uintptr_t)(
+			(uintptr_t)initmem +
 			sizeof(struct icp_qat_uof_initmem)) +
 			(sizeof(struct icp_qat_uof_memvar_attr) *
 			initmem->val_attr_num));
@@ -454,7 +479,7 @@
 	int i;
 	struct icp_qat_uof_chunkhdr *chunk_hdr =
 	    (struct icp_qat_uof_chunkhdr *)
-	    ((unsigned long)obj_hdr + sizeof(struct icp_qat_uof_objhdr));
+	    ((uintptr_t)obj_hdr + sizeof(struct icp_qat_uof_objhdr));
 
 	for (i = 0; i < obj_hdr->num_chunks; i++) {
 		if ((cur < (void *)&chunk_hdr[i]) &&
@@ -596,7 +621,7 @@
 	page->uwblock = (struct icp_qat_uclo_encap_uwblock *)uwblock;
 	for (i = 0; i < uword_block_tab->entry_num; i++)
 		page->uwblock[i].micro_words =
-		(unsigned long)encap_uof_obj->beg_uof + uwblock[i].uword_offset;
+		(uintptr_t)encap_uof_obj->beg_uof + uwblock[i].uword_offset;
 }
 
 static int qat_uclo_map_uimage(struct icp_qat_uclo_objhandle *obj_handle,
@@ -697,7 +722,7 @@
 		memcpy(&str_table->table_len, obj_hdr->file_buff +
 		       chunk_hdr->offset, sizeof(str_table->table_len));
 		hdr_size = (char *)&str_table->strings - (char *)str_table;
-		str_table->strings = (unsigned long)obj_hdr->file_buff +
+		str_table->strings = (uintptr_t)obj_hdr->file_buff +
 					chunk_hdr->offset + hdr_size;
 		return str_table;
 	}
@@ -721,13 +746,31 @@
 	}
 }
 
+static unsigned int
+qat_uclo_get_dev_type(struct icp_qat_fw_loader_handle *handle)
+{
+	switch (handle->pci_dev->device) {
+	case ADF_DH895XCC_PCI_DEVICE_ID:
+		return ICP_QAT_AC_895XCC_DEV_TYPE;
+	case ADF_C62X_PCI_DEVICE_ID:
+		return ICP_QAT_AC_C62X_DEV_TYPE;
+	case ADF_C3XXX_PCI_DEVICE_ID:
+		return ICP_QAT_AC_C3XXX_DEV_TYPE;
+	default:
+		pr_err("QAT: unsupported device 0x%x\n",
+		       handle->pci_dev->device);
+		return 0;
+	}
+}
+
 static int qat_uclo_check_uof_compat(struct icp_qat_uclo_objhandle *obj_handle)
 {
 	unsigned int maj_ver, prod_type = obj_handle->prod_type;
 
-	if (!(prod_type & obj_handle->encap_uof_obj.obj_hdr->cpu_type)) {
-		pr_err("QAT: UOF type 0x%x not match with cur platform 0x%x\n",
-		       obj_handle->encap_uof_obj.obj_hdr->cpu_type, prod_type);
+	if (!(prod_type & obj_handle->encap_uof_obj.obj_hdr->ac_dev_type)) {
+		pr_err("QAT: UOF type 0x%x doesn't match with platform 0x%x\n",
+		       obj_handle->encap_uof_obj.obj_hdr->ac_dev_type,
+		       prod_type);
 		return -EINVAL;
 	}
 	maj_ver = obj_handle->prod_rev & 0xff;
@@ -932,7 +975,7 @@
 	obj_handle->encap_uof_obj.obj_hdr = (struct icp_qat_uof_objhdr *)
 					     obj_handle->obj_hdr->file_buff;
 	obj_handle->uword_in_bytes = 6;
-	obj_handle->prod_type = ICP_QAT_AC_C_CPU_TYPE;
+	obj_handle->prod_type = qat_uclo_get_dev_type(handle);
 	obj_handle->prod_rev = PID_MAJOR_REV |
 			(PID_MINOR_REV & handle->hal_handle->revision_id);
 	if (qat_uclo_check_uof_compat(obj_handle)) {
@@ -969,23 +1012,435 @@
 	return -EFAULT;
 }
 
-void qat_uclo_wr_mimage(struct icp_qat_fw_loader_handle *handle,
-			void *addr_ptr, int mem_size)
+static int qat_uclo_map_suof_file_hdr(struct icp_qat_fw_loader_handle *handle,
+				      struct icp_qat_suof_filehdr *suof_ptr,
+				      int suof_size)
 {
-	qat_uclo_wr_sram_by_words(handle, 0, addr_ptr, ALIGN(mem_size, 4));
+	unsigned int check_sum = 0;
+	unsigned int min_ver_offset = 0;
+	struct icp_qat_suof_handle *suof_handle = handle->sobj_handle;
+
+	suof_handle->file_id = ICP_QAT_SUOF_FID;
+	suof_handle->suof_buf = (char *)suof_ptr;
+	suof_handle->suof_size = suof_size;
+	min_ver_offset = suof_size - offsetof(struct icp_qat_suof_filehdr,
+					      min_ver);
+	check_sum = qat_uclo_calc_str_checksum((char *)&suof_ptr->min_ver,
+					       min_ver_offset);
+	if (check_sum != suof_ptr->check_sum) {
+		pr_err("QAT: incorrect SUOF checksum\n");
+		return -EINVAL;
+	}
+	suof_handle->check_sum = suof_ptr->check_sum;
+	suof_handle->min_ver = suof_ptr->min_ver;
+	suof_handle->maj_ver = suof_ptr->maj_ver;
+	suof_handle->fw_type = suof_ptr->fw_type;
+	return 0;
 }
 
-int qat_uclo_map_uof_obj(struct icp_qat_fw_loader_handle *handle,
-			 void *addr_ptr, int mem_size)
+static void qat_uclo_map_simg(struct icp_qat_suof_handle *suof_handle,
+			      struct icp_qat_suof_img_hdr *suof_img_hdr,
+			      struct icp_qat_suof_chunk_hdr *suof_chunk_hdr)
+{
+	struct icp_qat_simg_ae_mode *ae_mode;
+	struct icp_qat_suof_objhdr *suof_objhdr;
+
+	suof_img_hdr->simg_buf  = (suof_handle->suof_buf +
+				   suof_chunk_hdr->offset +
+				   sizeof(*suof_objhdr));
+	suof_img_hdr->simg_len = ((struct icp_qat_suof_objhdr *)(uintptr_t)
+				  (suof_handle->suof_buf +
+				   suof_chunk_hdr->offset))->img_length;
+
+	suof_img_hdr->css_header = suof_img_hdr->simg_buf;
+	suof_img_hdr->css_key = (suof_img_hdr->css_header +
+				 sizeof(struct icp_qat_css_hdr));
+	suof_img_hdr->css_signature = suof_img_hdr->css_key +
+				      ICP_QAT_CSS_FWSK_MODULUS_LEN +
+				      ICP_QAT_CSS_FWSK_EXPONENT_LEN;
+	suof_img_hdr->css_simg = suof_img_hdr->css_signature +
+				 ICP_QAT_CSS_SIGNATURE_LEN;
+
+	ae_mode = (struct icp_qat_simg_ae_mode *)(suof_img_hdr->css_simg);
+	suof_img_hdr->ae_mask = ae_mode->ae_mask;
+	suof_img_hdr->simg_name = (unsigned long)&ae_mode->simg_name;
+	suof_img_hdr->appmeta_data = (unsigned long)&ae_mode->appmeta_data;
+	suof_img_hdr->fw_type = ae_mode->fw_type;
+}
+
+static void
+qat_uclo_map_suof_symobjs(struct icp_qat_suof_handle *suof_handle,
+			  struct icp_qat_suof_chunk_hdr *suof_chunk_hdr)
+{
+	char **sym_str = (char **)&suof_handle->sym_str;
+	unsigned int *sym_size = &suof_handle->sym_size;
+	struct icp_qat_suof_strtable *str_table_obj;
+
+	*sym_size = *(unsigned int *)(uintptr_t)
+		   (suof_chunk_hdr->offset + suof_handle->suof_buf);
+	*sym_str = (char *)(uintptr_t)
+		   (suof_handle->suof_buf + suof_chunk_hdr->offset +
+		   sizeof(str_table_obj->tab_length));
+}
+
+static int qat_uclo_check_simg_compat(struct icp_qat_fw_loader_handle *handle,
+				      struct icp_qat_suof_img_hdr *img_hdr)
+{
+	struct icp_qat_simg_ae_mode *img_ae_mode = NULL;
+	unsigned int prod_rev, maj_ver, prod_type;
+
+	prod_type = qat_uclo_get_dev_type(handle);
+	img_ae_mode = (struct icp_qat_simg_ae_mode *)img_hdr->css_simg;
+	prod_rev = PID_MAJOR_REV |
+			 (PID_MINOR_REV & handle->hal_handle->revision_id);
+	if (img_ae_mode->dev_type != prod_type) {
+		pr_err("QAT: incompatible product type %x\n",
+		       img_ae_mode->dev_type);
+		return -EINVAL;
+	}
+	maj_ver = prod_rev & 0xff;
+	if ((maj_ver > img_ae_mode->devmax_ver) ||
+	    (maj_ver < img_ae_mode->devmin_ver)) {
+		pr_err("QAT: incompatible device majver 0x%x\n", maj_ver);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static void qat_uclo_del_suof(struct icp_qat_fw_loader_handle *handle)
+{
+	struct icp_qat_suof_handle *sobj_handle = handle->sobj_handle;
+
+	kfree(sobj_handle->img_table.simg_hdr);
+	sobj_handle->img_table.simg_hdr = NULL;
+	kfree(handle->sobj_handle);
+	handle->sobj_handle = NULL;
+}
+
+static void qat_uclo_tail_img(struct icp_qat_suof_img_hdr *suof_img_hdr,
+			      unsigned int img_id, unsigned int num_simgs)
+{
+	struct icp_qat_suof_img_hdr img_header;
+
+	if (img_id != num_simgs - 1) {
+		memcpy(&img_header, &suof_img_hdr[num_simgs - 1],
+		       sizeof(*suof_img_hdr));
+		memcpy(&suof_img_hdr[num_simgs - 1], &suof_img_hdr[img_id],
+		       sizeof(*suof_img_hdr));
+		memcpy(&suof_img_hdr[img_id], &img_header,
+		       sizeof(*suof_img_hdr));
+	}
+}
+
+static int qat_uclo_map_suof(struct icp_qat_fw_loader_handle *handle,
+			     struct icp_qat_suof_filehdr *suof_ptr,
+			     int suof_size)
+{
+	struct icp_qat_suof_handle *suof_handle = handle->sobj_handle;
+	struct icp_qat_suof_chunk_hdr *suof_chunk_hdr = NULL;
+	struct icp_qat_suof_img_hdr *suof_img_hdr = NULL;
+	int ret = 0, ae0_img = ICP_QAT_UCLO_MAX_AE;
+	unsigned int i = 0;
+	struct icp_qat_suof_img_hdr img_header;
+
+	if (!suof_ptr || (suof_size == 0)) {
+		pr_err("QAT: input parameter SUOF pointer/size is NULL\n");
+		return -EINVAL;
+	}
+	if (qat_uclo_check_suof_format(suof_ptr))
+		return -EINVAL;
+	ret = qat_uclo_map_suof_file_hdr(handle, suof_ptr, suof_size);
+	if (ret)
+		return ret;
+	suof_chunk_hdr = (struct icp_qat_suof_chunk_hdr *)
+			 ((uintptr_t)suof_ptr + sizeof(*suof_ptr));
+
+	qat_uclo_map_suof_symobjs(suof_handle, suof_chunk_hdr);
+	suof_handle->img_table.num_simgs = suof_ptr->num_chunks - 1;
+
+	if (suof_handle->img_table.num_simgs != 0) {
+		suof_img_hdr = kzalloc(suof_handle->img_table.num_simgs *
+				       sizeof(img_header), GFP_KERNEL);
+		if (!suof_img_hdr)
+			return -ENOMEM;
+		suof_handle->img_table.simg_hdr = suof_img_hdr;
+	}
+
+	for (i = 0; i < suof_handle->img_table.num_simgs; i++) {
+		qat_uclo_map_simg(handle->sobj_handle, &suof_img_hdr[i],
+				  &suof_chunk_hdr[1 + i]);
+		ret = qat_uclo_check_simg_compat(handle,
+						 &suof_img_hdr[i]);
+		if (ret)
+			return ret;
+		if ((suof_img_hdr[i].ae_mask & 0x1) != 0)
+			ae0_img = i;
+	}
+	qat_uclo_tail_img(suof_img_hdr, ae0_img,
+			  suof_handle->img_table.num_simgs);
+	return 0;
+}
+
+#define ADD_ADDR(high, low)  ((((uint64_t)high) << 32) + low)
+#define BITS_IN_DWORD 32
+
+static int qat_uclo_auth_fw(struct icp_qat_fw_loader_handle *handle,
+			    struct icp_qat_fw_auth_desc *desc)
+{
+	unsigned int fcu_sts, retry = 0;
+	u64 bus_addr;
+
+	bus_addr = ADD_ADDR(desc->css_hdr_high, desc->css_hdr_low)
+			   - sizeof(struct icp_qat_auth_chunk);
+	SET_CAP_CSR(handle, FCU_DRAM_ADDR_HI, (bus_addr >> BITS_IN_DWORD));
+	SET_CAP_CSR(handle, FCU_DRAM_ADDR_LO, bus_addr);
+	SET_CAP_CSR(handle, FCU_CONTROL, FCU_CTRL_CMD_AUTH);
+
+	do {
+		msleep(FW_AUTH_WAIT_PERIOD);
+		fcu_sts = GET_CAP_CSR(handle, FCU_STATUS);
+		if ((fcu_sts & FCU_AUTH_STS_MASK) == FCU_STS_VERI_FAIL)
+			goto auth_fail;
+		if (((fcu_sts >> FCU_STS_AUTHFWLD_POS) & 0x1))
+			if ((fcu_sts & FCU_AUTH_STS_MASK) == FCU_STS_VERI_DONE)
+				return 0;
+	} while (retry++ < FW_AUTH_MAX_RETRY);
+auth_fail:
+	pr_err("QAT: authentication error (FCU_STATUS = 0x%x),retry = %d\n",
+	       fcu_sts & FCU_AUTH_STS_MASK, retry);
+	return -EINVAL;
+}
+
+static int qat_uclo_simg_alloc(struct icp_qat_fw_loader_handle *handle,
+			       struct icp_firml_dram_desc *dram_desc,
+			       unsigned int size)
+{
+	void *vptr;
+	dma_addr_t ptr;
+
+	vptr = dma_alloc_coherent(&handle->pci_dev->dev,
+				  size, &ptr, GFP_KERNEL);
+	if (!vptr)
+		return -ENOMEM;
+	dram_desc->dram_base_addr_v = vptr;
+	dram_desc->dram_bus_addr = ptr;
+	dram_desc->dram_size = size;
+	return 0;
+}
+
+static void qat_uclo_simg_free(struct icp_qat_fw_loader_handle *handle,
+			       struct icp_firml_dram_desc *dram_desc)
+{
+	dma_free_coherent(&handle->pci_dev->dev,
+			  (size_t)(dram_desc->dram_size),
+			  (dram_desc->dram_base_addr_v),
+			  dram_desc->dram_bus_addr);
+	memset(dram_desc, 0, sizeof(*dram_desc));
+}
+
+static void qat_uclo_ummap_auth_fw(struct icp_qat_fw_loader_handle *handle,
+				   struct icp_qat_fw_auth_desc **desc)
+{
+	struct icp_firml_dram_desc dram_desc;
+
+	dram_desc.dram_base_addr_v = *desc;
+	dram_desc.dram_bus_addr = ((struct icp_qat_auth_chunk *)
+				   (*desc))->chunk_bus_addr;
+	dram_desc.dram_size = ((struct icp_qat_auth_chunk *)
+			       (*desc))->chunk_size;
+	qat_uclo_simg_free(handle, &dram_desc);
+}
+
+static int qat_uclo_map_auth_fw(struct icp_qat_fw_loader_handle *handle,
+				char *image, unsigned int size,
+				struct icp_qat_fw_auth_desc **desc)
+{
+	struct icp_qat_css_hdr *css_hdr = (struct icp_qat_css_hdr *)image;
+	struct icp_qat_fw_auth_desc *auth_desc;
+	struct icp_qat_auth_chunk *auth_chunk;
+	u64 virt_addr,  bus_addr, virt_base;
+	unsigned int length, simg_offset = sizeof(*auth_chunk);
+	struct icp_firml_dram_desc img_desc;
+
+	if (size > (ICP_QAT_AE_IMG_OFFSET + ICP_QAT_CSS_MAX_IMAGE_LEN)) {
+		pr_err("QAT: error, input image size overflow %d\n", size);
+		return -EINVAL;
+	}
+	length = (css_hdr->fw_type == CSS_AE_FIRMWARE) ?
+		 ICP_QAT_CSS_AE_SIMG_LEN + simg_offset :
+		 size + ICP_QAT_CSS_FWSK_PAD_LEN + simg_offset;
+	if (qat_uclo_simg_alloc(handle, &img_desc, length)) {
+		pr_err("QAT: error, allocate continuous dram fail\n");
+		return -ENOMEM;
+	}
+
+	auth_chunk = img_desc.dram_base_addr_v;
+	auth_chunk->chunk_size = img_desc.dram_size;
+	auth_chunk->chunk_bus_addr = img_desc.dram_bus_addr;
+	virt_base = (uintptr_t)img_desc.dram_base_addr_v + simg_offset;
+	bus_addr  = img_desc.dram_bus_addr + simg_offset;
+	auth_desc = img_desc.dram_base_addr_v;
+	auth_desc->css_hdr_high = (unsigned int)(bus_addr >> BITS_IN_DWORD);
+	auth_desc->css_hdr_low = (unsigned int)bus_addr;
+	virt_addr = virt_base;
+
+	memcpy((void *)(uintptr_t)virt_addr, image, sizeof(*css_hdr));
+	/* pub key */
+	bus_addr = ADD_ADDR(auth_desc->css_hdr_high, auth_desc->css_hdr_low) +
+			   sizeof(*css_hdr);
+	virt_addr = virt_addr + sizeof(*css_hdr);
+
+	auth_desc->fwsk_pub_high = (unsigned int)(bus_addr >> BITS_IN_DWORD);
+	auth_desc->fwsk_pub_low = (unsigned int)bus_addr;
+
+	memcpy((void *)(uintptr_t)virt_addr,
+	       (void *)(image + sizeof(*css_hdr)),
+	       ICP_QAT_CSS_FWSK_MODULUS_LEN);
+	/* padding */
+	memset((void *)(uintptr_t)(virt_addr + ICP_QAT_CSS_FWSK_MODULUS_LEN),
+	       0, ICP_QAT_CSS_FWSK_PAD_LEN);
+
+	/* exponent */
+	memcpy((void *)(uintptr_t)(virt_addr + ICP_QAT_CSS_FWSK_MODULUS_LEN +
+	       ICP_QAT_CSS_FWSK_PAD_LEN),
+	       (void *)(image + sizeof(*css_hdr) +
+			ICP_QAT_CSS_FWSK_MODULUS_LEN),
+	       sizeof(unsigned int));
+
+	/* signature */
+	bus_addr = ADD_ADDR(auth_desc->fwsk_pub_high,
+			    auth_desc->fwsk_pub_low) +
+		   ICP_QAT_CSS_FWSK_PUB_LEN;
+	virt_addr = virt_addr + ICP_QAT_CSS_FWSK_PUB_LEN;
+	auth_desc->signature_high = (unsigned int)(bus_addr >> BITS_IN_DWORD);
+	auth_desc->signature_low = (unsigned int)bus_addr;
+
+	memcpy((void *)(uintptr_t)virt_addr,
+	       (void *)(image + sizeof(*css_hdr) +
+	       ICP_QAT_CSS_FWSK_MODULUS_LEN +
+	       ICP_QAT_CSS_FWSK_EXPONENT_LEN),
+	       ICP_QAT_CSS_SIGNATURE_LEN);
+
+	bus_addr = ADD_ADDR(auth_desc->signature_high,
+			    auth_desc->signature_low) +
+		   ICP_QAT_CSS_SIGNATURE_LEN;
+	virt_addr += ICP_QAT_CSS_SIGNATURE_LEN;
+
+	auth_desc->img_high = (unsigned int)(bus_addr >> BITS_IN_DWORD);
+	auth_desc->img_low = (unsigned int)bus_addr;
+	auth_desc->img_len = size - ICP_QAT_AE_IMG_OFFSET;
+	memcpy((void *)(uintptr_t)virt_addr,
+	       (void *)(image + ICP_QAT_AE_IMG_OFFSET),
+	       auth_desc->img_len);
+	virt_addr = virt_base;
+	/* AE firmware */
+	if (((struct icp_qat_css_hdr *)(uintptr_t)virt_addr)->fw_type ==
+	    CSS_AE_FIRMWARE) {
+		auth_desc->img_ae_mode_data_high = auth_desc->img_high;
+		auth_desc->img_ae_mode_data_low = auth_desc->img_low;
+		bus_addr = ADD_ADDR(auth_desc->img_ae_mode_data_high,
+				    auth_desc->img_ae_mode_data_low) +
+			   sizeof(struct icp_qat_simg_ae_mode);
+
+		auth_desc->img_ae_init_data_high = (unsigned int)
+						 (bus_addr >> BITS_IN_DWORD);
+		auth_desc->img_ae_init_data_low = (unsigned int)bus_addr;
+		bus_addr += ICP_QAT_SIMG_AE_INIT_SEQ_LEN;
+		auth_desc->img_ae_insts_high = (unsigned int)
+					     (bus_addr >> BITS_IN_DWORD);
+		auth_desc->img_ae_insts_low = (unsigned int)bus_addr;
+	} else {
+		auth_desc->img_ae_insts_high = auth_desc->img_high;
+		auth_desc->img_ae_insts_low = auth_desc->img_low;
+	}
+	*desc = auth_desc;
+	return 0;
+}
+
+static int qat_uclo_load_fw(struct icp_qat_fw_loader_handle *handle,
+			    struct icp_qat_fw_auth_desc *desc)
+{
+	unsigned int i;
+	unsigned int fcu_sts;
+	struct icp_qat_simg_ae_mode *virt_addr;
+	unsigned int fcu_loaded_ae_pos = FCU_LOADED_AE_POS;
+
+	virt_addr = (void *)((uintptr_t)desc +
+		     sizeof(struct icp_qat_auth_chunk) +
+		     sizeof(struct icp_qat_css_hdr) +
+		     ICP_QAT_CSS_FWSK_PUB_LEN +
+		     ICP_QAT_CSS_SIGNATURE_LEN);
+	for (i = 0; i < handle->hal_handle->ae_max_num; i++) {
+		int retry = 0;
+
+		if (!((virt_addr->ae_mask >> i) & 0x1))
+			continue;
+		if (qat_hal_check_ae_active(handle, i)) {
+			pr_err("QAT: AE %d is active\n", i);
+			return -EINVAL;
+		}
+		SET_CAP_CSR(handle, FCU_CONTROL,
+			    (FCU_CTRL_CMD_LOAD | (i << FCU_CTRL_AE_POS)));
+
+		do {
+			msleep(FW_AUTH_WAIT_PERIOD);
+			fcu_sts = GET_CAP_CSR(handle, FCU_STATUS);
+			if (((fcu_sts & FCU_AUTH_STS_MASK) ==
+			    FCU_STS_LOAD_DONE) &&
+			    ((fcu_sts >> fcu_loaded_ae_pos) & (1 << i)))
+				break;
+		} while (retry++ < FW_AUTH_MAX_RETRY);
+		if (retry > FW_AUTH_MAX_RETRY) {
+			pr_err("QAT: firmware load failed timeout %x\n", retry);
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
+
+static int qat_uclo_map_suof_obj(struct icp_qat_fw_loader_handle *handle,
+				 void *addr_ptr, int mem_size)
+{
+	struct icp_qat_suof_handle *suof_handle;
+
+	suof_handle = kzalloc(sizeof(*suof_handle), GFP_KERNEL);
+	if (!suof_handle)
+		return -ENOMEM;
+	handle->sobj_handle = suof_handle;
+	if (qat_uclo_map_suof(handle, addr_ptr, mem_size)) {
+		qat_uclo_del_suof(handle);
+		pr_err("QAT: map SUOF failed\n");
+		return -EINVAL;
+	}
+	return 0;
+}
+
+int qat_uclo_wr_mimage(struct icp_qat_fw_loader_handle *handle,
+		       void *addr_ptr, int mem_size)
+{
+	struct icp_qat_fw_auth_desc *desc = NULL;
+	int status = 0;
+
+	if (handle->fw_auth) {
+		if (!qat_uclo_map_auth_fw(handle, addr_ptr, mem_size, &desc))
+			status = qat_uclo_auth_fw(handle, desc);
+		qat_uclo_ummap_auth_fw(handle, &desc);
+	} else {
+		if (handle->pci_dev->device == ADF_C3XXX_PCI_DEVICE_ID) {
+			pr_err("QAT: C3XXX doesn't support unsigned MMP\n");
+			return -EINVAL;
+		}
+		qat_uclo_wr_sram_by_words(handle, 0, addr_ptr, mem_size);
+	}
+	return status;
+}
+
+static int qat_uclo_map_uof_obj(struct icp_qat_fw_loader_handle *handle,
+				void *addr_ptr, int mem_size)
 {
 	struct icp_qat_uof_filehdr *filehdr;
 	struct icp_qat_uclo_objhandle *objhdl;
 
-	BUILD_BUG_ON(ICP_QAT_UCLO_MAX_AE >=
-		     (sizeof(handle->hal_handle->ae_mask) * 8));
-
-	if (!handle || !addr_ptr || mem_size < 24)
-		return -EINVAL;
 	objhdl = kzalloc(sizeof(*objhdl), GFP_KERNEL);
 	if (!objhdl)
 		return -ENOMEM;
@@ -993,7 +1448,7 @@
 	if (!objhdl->obj_buf)
 		goto out_objbuf_err;
 	filehdr = (struct icp_qat_uof_filehdr *)objhdl->obj_buf;
-	if (qat_uclo_check_format(filehdr))
+	if (qat_uclo_check_uof_format(filehdr))
 		goto out_objhdr_err;
 	objhdl->obj_hdr = qat_uclo_map_chunk((char *)objhdl->obj_buf, filehdr,
 					     ICP_QAT_UOF_OBJS);
@@ -1016,11 +1471,27 @@
 	return -ENOMEM;
 }
 
+int qat_uclo_map_obj(struct icp_qat_fw_loader_handle *handle,
+		     void *addr_ptr, int mem_size)
+{
+	BUILD_BUG_ON(ICP_QAT_UCLO_MAX_AE >=
+		     (sizeof(handle->hal_handle->ae_mask) * 8));
+
+	if (!handle || !addr_ptr || mem_size < 24)
+		return -EINVAL;
+
+	return (handle->fw_auth) ?
+			qat_uclo_map_suof_obj(handle, addr_ptr, mem_size) :
+			qat_uclo_map_uof_obj(handle, addr_ptr, mem_size);
+}
+
 void qat_uclo_del_uof_obj(struct icp_qat_fw_loader_handle *handle)
 {
 	struct icp_qat_uclo_objhandle *obj_handle = handle->obj_handle;
 	unsigned int a;
 
+	if (handle->sobj_handle)
+		qat_uclo_del_suof(handle);
 	if (!obj_handle)
 		return;
 
@@ -1055,7 +1526,7 @@
 		    encap_page->uwblock[i].words_num - 1) {
 			raddr -= encap_page->uwblock[i].start_addr;
 			raddr *= obj_handle->uword_in_bytes;
-			memcpy(&uwrd, (void *)(((unsigned long)
+			memcpy(&uwrd, (void *)(((uintptr_t)
 			       encap_page->uwblock[i].micro_words) + raddr),
 			       obj_handle->uword_in_bytes);
 			uwrd = uwrd & 0xbffffffffffull;
@@ -1147,7 +1618,33 @@
 	}
 }
 
-int qat_uclo_wr_all_uimage(struct icp_qat_fw_loader_handle *handle)
+static int qat_uclo_wr_suof_img(struct icp_qat_fw_loader_handle *handle)
+{
+	unsigned int i;
+	struct icp_qat_fw_auth_desc *desc = NULL;
+	struct icp_qat_suof_handle *sobj_handle = handle->sobj_handle;
+	struct icp_qat_suof_img_hdr *simg_hdr = sobj_handle->img_table.simg_hdr;
+
+	for (i = 0; i < sobj_handle->img_table.num_simgs; i++) {
+		if (qat_uclo_map_auth_fw(handle,
+					 (char *)simg_hdr[i].simg_buf,
+					 (unsigned int)
+					 (simg_hdr[i].simg_len),
+					 &desc))
+			goto wr_err;
+		if (qat_uclo_auth_fw(handle, desc))
+			goto wr_err;
+		if (qat_uclo_load_fw(handle, desc))
+			goto wr_err;
+		qat_uclo_ummap_auth_fw(handle, &desc);
+	}
+	return 0;
+wr_err:
+	qat_uclo_ummap_auth_fw(handle, &desc);
+	return -EINVAL;
+}
+
+static int qat_uclo_wr_uof_img(struct icp_qat_fw_loader_handle *handle)
 {
 	struct icp_qat_uclo_objhandle *obj_handle = handle->obj_handle;
 	unsigned int i;
@@ -1164,3 +1661,9 @@
 	}
 	return 0;
 }
+
+int qat_uclo_wr_all_uimage(struct icp_qat_fw_loader_handle *handle)
+{
+	return (handle->fw_auth) ? qat_uclo_wr_suof_img(handle) :
+				   qat_uclo_wr_uof_img(handle);
+}
diff --git a/drivers/crypto/qat/qat_dh895xcc/Makefile b/drivers/crypto/qat/qat_dh895xcc/Makefile
index 8c79c54..180a00e 100644
--- a/drivers/crypto/qat/qat_dh895xcc/Makefile
+++ b/drivers/crypto/qat/qat_dh895xcc/Makefile
@@ -1,5 +1,3 @@
 ccflags-y := -I$(src)/../qat_common
 obj-$(CONFIG_CRYPTO_DEV_QAT_DH895xCC) += qat_dh895xcc.o
-qat_dh895xcc-objs := adf_drv.o \
-		adf_isr.o \
-		adf_dh895xcc_hw_data.o
+qat_dh895xcc-objs := adf_drv.o adf_dh895xcc_hw_data.o
diff --git a/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c b/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c
index ff54257..6e1d5e1 100644
--- a/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c
+++ b/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c
@@ -48,7 +48,6 @@
 #include <adf_pf2vf_msg.h>
 #include <adf_common_drv.h>
 #include "adf_dh895xcc_hw_data.h"
-#include "adf_drv.h"
 
 /* Worker thread to service arbiter mappings based on dev SKUs */
 static const uint32_t thrd_to_arb_map_sku4[] = {
@@ -143,8 +142,8 @@
 	return DEV_SKU_UNKNOWN;
 }
 
-void adf_get_arbiter_mapping(struct adf_accel_dev *accel_dev,
-			     uint32_t const **arb_map_config)
+static void adf_get_arbiter_mapping(struct adf_accel_dev *accel_dev,
+				    u32 const **arb_map_config)
 {
 	switch (accel_dev->accel_pci_dev.sku) {
 	case DEV_SKU_1:
diff --git a/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.h b/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.h
index 88dffb2..092f735 100644
--- a/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.h
+++ b/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.h
@@ -53,7 +53,6 @@
 #define ADF_DH895XCC_ETR_BAR 2
 #define ADF_DH895XCC_RX_RINGS_OFFSET 8
 #define ADF_DH895XCC_TX_RINGS_MASK 0xFF
-#define ADF_DH895XCC_FUSECTL_OFFSET 0x40
 #define ADF_DH895XCC_FUSECTL_SKU_MASK 0x300000
 #define ADF_DH895XCC_FUSECTL_SKU_SHIFT 20
 #define ADF_DH895XCC_FUSECTL_SKU_1 0x0
@@ -65,7 +64,6 @@
 #define ADF_DH895XCC_ACCELERATORS_REG_OFFSET 13
 #define ADF_DH895XCC_ACCELERATORS_MASK 0x3F
 #define ADF_DH895XCC_ACCELENGINES_MASK 0xFFF
-#define ADF_DH895XCC_LEGFUSE_OFFSET 0x4C
 #define ADF_DH895XCC_ETR_MAX_BANKS 32
 #define ADF_DH895XCC_SMIAPF0_MASK_OFFSET (0x3A000 + 0x28)
 #define ADF_DH895XCC_SMIAPF1_MASK_OFFSET (0x3A000 + 0x30)
@@ -80,11 +78,12 @@
 #define ADF_DH895XCC_CERRSSMSH(i) (i * 0x4000 + 0x10)
 #define ADF_DH895XCC_ERRSSMSH_EN BIT(3)
 
-#define ADF_DH895XCC_ERRSOU3	(0x3A000 + 0x00C)
-#define ADF_DH895XCC_ERRSOU5	(0x3A000 + 0x0D8)
 #define ADF_DH895XCC_PF2VF_OFFSET(i)	(0x3A000 + 0x280 + ((i) * 0x04))
 #define ADF_DH895XCC_VINTMSK_OFFSET(i)	(0x3A000 + 0x200 + ((i) * 0x04))
 /* FW names */
 #define ADF_DH895XCC_FW "qat_895xcc.bin"
-#define ADF_DH895XCC_MMP "qat_mmp.bin"
+#define ADF_DH895XCC_MMP "qat_895xcc_mmp.bin"
+
+void adf_init_hw_data_dh895xcc(struct adf_hw_device_data *hw_data);
+void adf_clean_hw_data_dh895xcc(struct adf_hw_device_data *hw_data);
 #endif
diff --git a/drivers/crypto/qat/qat_dh895xcc/adf_drv.c b/drivers/crypto/qat/qat_dh895xcc/adf_drv.c
index f8dd14f..a8c4b92 100644
--- a/drivers/crypto/qat/qat_dh895xcc/adf_drv.c
+++ b/drivers/crypto/qat/qat_dh895xcc/adf_drv.c
@@ -60,11 +60,7 @@
 #include <adf_accel_devices.h>
 #include <adf_common_drv.h>
 #include <adf_cfg.h>
-#include <adf_transport_access_macros.h>
 #include "adf_dh895xcc_hw_data.h"
-#include "adf_drv.h"
-
-static const char adf_driver_name[] = ADF_DH895XCC_DEVICE_NAME;
 
 #define ADF_SYSTEM_DEVICE(device_id) \
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, device_id)}
@@ -80,7 +76,7 @@
 
 static struct pci_driver adf_driver = {
 	.id_table = adf_pci_tbl,
-	.name = adf_driver_name,
+	.name = ADF_DH895XCC_DEVICE_NAME,
 	.probe = adf_probe,
 	.remove = adf_remove,
 	.sriov_configure = adf_sriov_configure,
@@ -120,87 +116,6 @@
 	adf_devmgr_rm_dev(accel_dev, NULL);
 }
 
-static int adf_dev_configure(struct adf_accel_dev *accel_dev)
-{
-	int cpus = num_online_cpus();
-	int banks = GET_MAX_BANKS(accel_dev);
-	int instances = min(cpus, banks);
-	char key[ADF_CFG_MAX_KEY_LEN_IN_BYTES];
-	int i;
-	unsigned long val;
-
-	if (adf_cfg_section_add(accel_dev, ADF_KERNEL_SEC))
-		goto err;
-	if (adf_cfg_section_add(accel_dev, "Accelerator0"))
-		goto err;
-	for (i = 0; i < instances; i++) {
-		val = i;
-		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_BANK_NUM, i);
-		if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
-						key, (void *)&val, ADF_DEC))
-			goto err;
-
-		snprintf(key, sizeof(key), ADF_CY "%d" ADF_ETRMGR_CORE_AFFINITY,
-			 i);
-		if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
-						key, (void *)&val, ADF_DEC))
-			goto err;
-
-		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_ASYM_SIZE, i);
-		val = 128;
-		if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
-						key, (void *)&val, ADF_DEC))
-			goto err;
-
-		val = 512;
-		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_SYM_SIZE, i);
-		if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
-						key, (void *)&val, ADF_DEC))
-			goto err;
-
-		val = 0;
-		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_ASYM_TX, i);
-		if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
-						key, (void *)&val, ADF_DEC))
-			goto err;
-
-		val = 2;
-		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_SYM_TX, i);
-		if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
-						key, (void *)&val, ADF_DEC))
-			goto err;
-
-		val = 8;
-		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_ASYM_RX, i);
-		if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
-						key, (void *)&val, ADF_DEC))
-			goto err;
-
-		val = 10;
-		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_SYM_RX, i);
-		if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
-						key, (void *)&val, ADF_DEC))
-			goto err;
-
-		val = ADF_COALESCING_DEF_TIME;
-		snprintf(key, sizeof(key), ADF_ETRMGR_COALESCE_TIMER_FORMAT, i);
-		if (adf_cfg_add_key_value_param(accel_dev, "Accelerator0",
-						key, (void *)&val, ADF_DEC))
-			goto err;
-	}
-
-	val = i;
-	if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
-					ADF_NUM_CY, (void *)&val, ADF_DEC))
-		goto err;
-
-	set_bit(ADF_STATUS_CONFIGURED, &accel_dev->status);
-	return 0;
-err:
-	dev_err(&GET_DEV(accel_dev), "Failed to start QAT accel dev\n");
-	return -EINVAL;
-}
-
 static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	struct adf_accel_dev *accel_dev;
@@ -253,15 +168,9 @@
 	}
 
 	accel_dev->hw_device = hw_data;
-	switch (ent->device) {
-	case ADF_DH895XCC_PCI_DEVICE_ID:
-		adf_init_hw_data_dh895xcc(accel_dev->hw_device);
-		break;
-	default:
-		return -ENODEV;
-	}
+	adf_init_hw_data_dh895xcc(accel_dev->hw_device);
 	pci_read_config_byte(pdev, PCI_REVISION_ID, &accel_pci_dev->revid);
-	pci_read_config_dword(pdev, ADF_DH895XCC_FUSECTL_OFFSET,
+	pci_read_config_dword(pdev, ADF_DEVICE_FUSECTL_OFFSET,
 			      &hw_data->fuses);
 
 	/* Get Accelerators and Accelerators Engines masks */
@@ -316,13 +225,13 @@
 		pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
 	}
 
-	if (pci_request_regions(pdev, adf_driver_name)) {
+	if (pci_request_regions(pdev, ADF_DH895XCC_DEVICE_NAME)) {
 		ret = -EFAULT;
 		goto out_err_disable;
 	}
 
 	/* Read accelerator capabilities mask */
-	pci_read_config_dword(pdev, ADF_DH895XCC_LEGFUSE_OFFSET,
+	pci_read_config_dword(pdev, ADF_DEVICE_LEGFUSE_OFFSET,
 			      &hw_data->accel_capabilities_mask);
 
 	/* Find and map all the device's BARS */
@@ -357,7 +266,7 @@
 		goto out_err_free_reg;
 	}
 
-	ret = adf_dev_configure(accel_dev);
+	ret = qat_crypto_dev_config(accel_dev);
 	if (ret)
 		goto out_err_free_reg;
 
diff --git a/drivers/crypto/qat/qat_dh895xccvf/Makefile b/drivers/crypto/qat/qat_dh895xccvf/Makefile
index 85399fc..5c3ccf8 100644
--- a/drivers/crypto/qat/qat_dh895xccvf/Makefile
+++ b/drivers/crypto/qat/qat_dh895xccvf/Makefile
@@ -1,5 +1,3 @@
 ccflags-y := -I$(src)/../qat_common
 obj-$(CONFIG_CRYPTO_DEV_QAT_DH895xCCVF) += qat_dh895xccvf.o
-qat_dh895xccvf-objs := adf_drv.o \
-		adf_isr.o \
-		adf_dh895xccvf_hw_data.o
+qat_dh895xccvf-objs := adf_drv.o adf_dh895xccvf_hw_data.o
diff --git a/drivers/crypto/qat/qat_dh895xccvf/adf_dh895xccvf_hw_data.c b/drivers/crypto/qat/qat_dh895xccvf/adf_dh895xccvf_hw_data.c
index a9a27ef..dc04ab6 100644
--- a/drivers/crypto/qat/qat_dh895xccvf/adf_dh895xccvf_hw_data.c
+++ b/drivers/crypto/qat/qat_dh895xccvf/adf_dh895xccvf_hw_data.c
@@ -48,7 +48,6 @@
 #include <adf_pf2vf_msg.h>
 #include <adf_common_drv.h>
 #include "adf_dh895xccvf_hw_data.h"
-#include "adf_drv.h"
 
 static struct adf_hw_device_class dh895xcciov_class = {
 	.name = ADF_DH895XCCVF_DEVICE_NAME,
@@ -136,7 +135,6 @@
 void adf_init_hw_data_dh895xcciov(struct adf_hw_device_data *hw_data)
 {
 	hw_data->dev_class = &dh895xcciov_class;
-	hw_data->instance_id = dh895xcciov_class.instances++;
 	hw_data->num_banks = ADF_DH895XCCIOV_ETR_MAX_BANKS;
 	hw_data->num_accel = ADF_DH895XCCIOV_MAX_ACCELERATORS;
 	hw_data->num_logical_accel = 1;
@@ -164,9 +162,12 @@
 	hw_data->enable_ints = adf_vf_void_noop;
 	hw_data->enable_vf2pf_comms = adf_enable_vf2pf_comms;
 	hw_data->min_iov_compat_ver = ADF_PFVF_COMPATIBILITY_VERSION;
+	hw_data->dev_class->instances++;
+	adf_devmgr_update_class_index(hw_data);
 }
 
 void adf_clean_hw_data_dh895xcciov(struct adf_hw_device_data *hw_data)
 {
 	hw_data->dev_class->instances--;
+	adf_devmgr_update_class_index(hw_data);
 }
diff --git a/drivers/crypto/qat/qat_dh895xccvf/adf_dh895xccvf_hw_data.h b/drivers/crypto/qat/qat_dh895xccvf/adf_dh895xccvf_hw_data.h
index 8f6babf..6ddc19b 100644
--- a/drivers/crypto/qat/qat_dh895xccvf/adf_dh895xccvf_hw_data.h
+++ b/drivers/crypto/qat/qat_dh895xccvf/adf_dh895xccvf_hw_data.h
@@ -56,13 +56,9 @@
 #define ADF_DH895XCCIOV_TX_RINGS_MASK 0xFF
 #define ADF_DH895XCCIOV_ETR_BAR 0
 #define ADF_DH895XCCIOV_ETR_MAX_BANKS 1
-
 #define ADF_DH895XCCIOV_PF2VF_OFFSET	0x200
-#define ADF_DH895XCC_PF2VF_PF2VFINT	BIT(0)
-
-#define ADF_DH895XCCIOV_VINTSOU_OFFSET	0x204
-#define ADF_DH895XCC_VINTSOU_BUN	BIT(0)
-#define ADF_DH895XCC_VINTSOU_PF2VF	BIT(1)
-
 #define ADF_DH895XCCIOV_VINTMSK_OFFSET	0x208
+
+void adf_init_hw_data_dh895xcciov(struct adf_hw_device_data *hw_data);
+void adf_clean_hw_data_dh895xcciov(struct adf_hw_device_data *hw_data);
 #endif
diff --git a/drivers/crypto/qat/qat_dh895xccvf/adf_drv.c b/drivers/crypto/qat/qat_dh895xccvf/adf_drv.c
index 789426f..f8cc4bf 100644
--- a/drivers/crypto/qat/qat_dh895xccvf/adf_drv.c
+++ b/drivers/crypto/qat/qat_dh895xccvf/adf_drv.c
@@ -60,11 +60,7 @@
 #include <adf_accel_devices.h>
 #include <adf_common_drv.h>
 #include <adf_cfg.h>
-#include <adf_transport_access_macros.h>
 #include "adf_dh895xccvf_hw_data.h"
-#include "adf_drv.h"
-
-static const char adf_driver_name[] = ADF_DH895XCCVF_DEVICE_NAME;
 
 #define ADF_SYSTEM_DEVICE(device_id) \
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, device_id)}
@@ -80,7 +76,7 @@
 
 static struct pci_driver adf_driver = {
 	.id_table = adf_pci_tbl,
-	.name = adf_driver_name,
+	.name = ADF_DH895XCCVF_DEVICE_NAME,
 	.probe = adf_probe,
 	.remove = adf_remove,
 };
@@ -121,83 +117,6 @@
 	adf_devmgr_rm_dev(accel_dev, pf);
 }
 
-static int adf_dev_configure(struct adf_accel_dev *accel_dev)
-{
-	char key[ADF_CFG_MAX_KEY_LEN_IN_BYTES];
-	unsigned long val, bank = 0;
-
-	if (adf_cfg_section_add(accel_dev, ADF_KERNEL_SEC))
-		goto err;
-	if (adf_cfg_section_add(accel_dev, "Accelerator0"))
-		goto err;
-
-	snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_BANK_NUM, 0);
-	if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC, key,
-					(void *)&bank, ADF_DEC))
-		goto err;
-
-	val = bank;
-	snprintf(key, sizeof(key), ADF_CY "%d" ADF_ETRMGR_CORE_AFFINITY, 0);
-	if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC, key,
-					(void *)&val, ADF_DEC))
-		goto err;
-
-	snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_ASYM_SIZE, 0);
-
-	val = 128;
-	if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC, key,
-					(void *)&val, ADF_DEC))
-		goto err;
-
-	val = 512;
-	snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_SYM_SIZE, 0);
-	if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
-					key, (void *)&val, ADF_DEC))
-		goto err;
-
-	val = 0;
-	snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_ASYM_TX, 0);
-	if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
-					key, (void *)&val, ADF_DEC))
-		goto err;
-
-	val = 2;
-	snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_SYM_TX, 0);
-	if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
-					key, (void *)&val, ADF_DEC))
-		goto err;
-
-	val = 8;
-	snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_ASYM_RX, 0);
-	if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
-					key, (void *)&val, ADF_DEC))
-		goto err;
-
-	val = 10;
-	snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_SYM_RX, 0);
-	if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
-					key, (void *)&val, ADF_DEC))
-			goto err;
-
-	val = ADF_COALESCING_DEF_TIME;
-	snprintf(key, sizeof(key), ADF_ETRMGR_COALESCE_TIMER_FORMAT,
-		 (int)bank);
-	if (adf_cfg_add_key_value_param(accel_dev, "Accelerator0",
-					key, (void *)&val, ADF_DEC))
-		goto err;
-
-	val = 1;
-	if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
-					ADF_NUM_CY, (void *)&val, ADF_DEC))
-		goto err;
-
-	set_bit(ADF_STATUS_CONFIGURED, &accel_dev->status);
-	return 0;
-err:
-	dev_err(&GET_DEV(accel_dev), "Failed to configure QAT accel dev\n");
-	return -EINVAL;
-}
-
 static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	struct adf_accel_dev *accel_dev;
@@ -243,14 +162,7 @@
 		goto out_err;
 	}
 	accel_dev->hw_device = hw_data;
-	switch (ent->device) {
-	case ADF_DH895XCCIOV_PCI_DEVICE_ID:
-		adf_init_hw_data_dh895xcciov(accel_dev->hw_device);
-		break;
-	default:
-		ret = -ENODEV;
-		goto out_err;
-	}
+	adf_init_hw_data_dh895xcciov(accel_dev->hw_device);
 
 	/* Get Accelerators and Accelerators Engines masks */
 	hw_data->accel_mask = hw_data->get_accel_mask(hw_data->fuses);
@@ -295,7 +207,7 @@
 		pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
 	}
 
-	if (pci_request_regions(pdev, adf_driver_name)) {
+	if (pci_request_regions(pdev, ADF_DH895XCCVF_DEVICE_NAME)) {
 		ret = -EFAULT;
 		goto out_err_disable;
 	}
@@ -322,7 +234,7 @@
 	/* Completion for VF2PF request/response message exchange */
 	init_completion(&accel_dev->vf.iov_msg_completion);
 
-	ret = adf_dev_configure(accel_dev);
+	ret = qat_crypto_dev_config(accel_dev);
 	if (ret)
 		goto out_err_free_reg;
 
diff --git a/drivers/crypto/qat/qat_dh895xccvf/adf_drv.h b/drivers/crypto/qat/qat_dh895xccvf/adf_drv.h
deleted file mode 100644
index e270e4a..0000000
--- a/drivers/crypto/qat/qat_dh895xccvf/adf_drv.h
+++ /dev/null
@@ -1,57 +0,0 @@
-/*
-  This file is provided under a dual BSD/GPLv2 license.  When using or
-  redistributing this file, you may do so under either license.
-
-  GPL LICENSE SUMMARY
-  Copyright(c) 2014 Intel Corporation.
-  This program is free software; you can redistribute it and/or modify
-  it under the terms of version 2 of the GNU General Public License as
-  published by the Free Software Foundation.
-
-  This program is distributed in the hope that it will be useful, but
-  WITHOUT ANY WARRANTY; without even the implied warranty of
-  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
-  General Public License for more details.
-
-  Contact Information:
-  qat-linux@intel.com
-
-  BSD LICENSE
-  Copyright(c) 2014 Intel Corporation.
-  Redistribution and use in source and binary forms, with or without
-  modification, are permitted provided that the following conditions
-  are met:
-
-    * Redistributions of source code must retain the above copyright
-      notice, this list of conditions and the following disclaimer.
-    * Redistributions in binary form must reproduce the above copyright
-      notice, this list of conditions and the following disclaimer in
-      the documentation and/or other materials provided with the
-      distribution.
-    * Neither the name of Intel Corporation nor the names of its
-      contributors may be used to endorse or promote products derived
-      from this software without specific prior written permission.
-
-  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
-  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
-  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
-  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
-  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
-  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
-  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
-  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
-  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
-  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
-  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-*/
-#ifndef ADF_DH895xVF_DRV_H_
-#define ADF_DH895xVF_DRV_H_
-#include <adf_accel_devices.h>
-#include <adf_transport.h>
-
-void adf_init_hw_data_dh895xcciov(struct adf_hw_device_data *hw_data);
-void adf_clean_hw_data_dh895xcciov(struct adf_hw_device_data *hw_data);
-int adf_vf_isr_resource_alloc(struct adf_accel_dev *accel_dev);
-void adf_vf_isr_resource_free(struct adf_accel_dev *accel_dev);
-void adf_update_ring_arb_enable(struct adf_etr_ring_data *ring);
-#endif
diff --git a/drivers/crypto/qce/ablkcipher.c b/drivers/crypto/qce/ablkcipher.c
index 2c0d63d..dbcbbe2 100644
--- a/drivers/crypto/qce/ablkcipher.c
+++ b/drivers/crypto/qce/ablkcipher.c
@@ -83,6 +83,14 @@
 		rctx->dst_nents = sg_nents_for_len(req->dst, req->nbytes);
 	else
 		rctx->dst_nents = rctx->src_nents;
+	if (rctx->src_nents < 0) {
+		dev_err(qce->dev, "Invalid numbers of src SG.\n");
+		return rctx->src_nents;
+	}
+	if (rctx->dst_nents < 0) {
+		dev_err(qce->dev, "Invalid numbers of dst SG.\n");
+		return -rctx->dst_nents;
+	}
 
 	rctx->dst_nents += 1;
 
diff --git a/drivers/crypto/qce/sha.c b/drivers/crypto/qce/sha.c
index 0c9973e..47e114a 100644
--- a/drivers/crypto/qce/sha.c
+++ b/drivers/crypto/qce/sha.c
@@ -92,6 +92,11 @@
 	}
 
 	rctx->src_nents = sg_nents_for_len(req->src, req->nbytes);
+	if (rctx->src_nents < 0) {
+		dev_err(qce->dev, "Invalid numbers of src SG.\n");
+		return rctx->src_nents;
+	}
+
 	ret = dma_map_sg(qce->dev, req->src, rctx->src_nents, DMA_TO_DEVICE);
 	if (ret < 0)
 		return ret;
diff --git a/drivers/crypto/rockchip/Makefile b/drivers/crypto/rockchip/Makefile
new file mode 100644
index 0000000..7051c6c
--- /dev/null
+++ b/drivers/crypto/rockchip/Makefile
@@ -0,0 +1,3 @@
+obj-$(CONFIG_CRYPTO_DEV_ROCKCHIP) += rk_crypto.o
+rk_crypto-objs := rk3288_crypto.o \
+		  rk3288_crypto_ablkcipher.o \
diff --git a/drivers/crypto/rockchip/rk3288_crypto.c b/drivers/crypto/rockchip/rk3288_crypto.c
new file mode 100644
index 0000000..da9c73d
--- /dev/null
+++ b/drivers/crypto/rockchip/rk3288_crypto.c
@@ -0,0 +1,394 @@
+/*
+ * Crypto acceleration support for Rockchip RK3288
+ *
+ * Copyright (c) 2015, Fuzhou Rockchip Electronics Co., Ltd
+ *
+ * Author: Zain Wang <zain.wang@rock-chips.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * Some ideas are from marvell-cesa.c and s5p-sss.c driver.
+ */
+
+#include "rk3288_crypto.h"
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/of.h>
+#include <linux/clk.h>
+#include <linux/crypto.h>
+#include <linux/reset.h>
+
+static int rk_crypto_enable_clk(struct rk_crypto_info *dev)
+{
+	int err;
+
+	err = clk_prepare_enable(dev->sclk);
+	if (err) {
+		dev_err(dev->dev, "[%s:%d], Couldn't enable clock sclk\n",
+			__func__, __LINE__);
+		goto err_return;
+	}
+	err = clk_prepare_enable(dev->aclk);
+	if (err) {
+		dev_err(dev->dev, "[%s:%d], Couldn't enable clock aclk\n",
+			__func__, __LINE__);
+		goto err_aclk;
+	}
+	err = clk_prepare_enable(dev->hclk);
+	if (err) {
+		dev_err(dev->dev, "[%s:%d], Couldn't enable clock hclk\n",
+			__func__, __LINE__);
+		goto err_hclk;
+	}
+	err = clk_prepare_enable(dev->dmaclk);
+	if (err) {
+		dev_err(dev->dev, "[%s:%d], Couldn't enable clock dmaclk\n",
+			__func__, __LINE__);
+		goto err_dmaclk;
+	}
+	return err;
+err_dmaclk:
+	clk_disable_unprepare(dev->hclk);
+err_hclk:
+	clk_disable_unprepare(dev->aclk);
+err_aclk:
+	clk_disable_unprepare(dev->sclk);
+err_return:
+	return err;
+}
+
+static void rk_crypto_disable_clk(struct rk_crypto_info *dev)
+{
+	clk_disable_unprepare(dev->dmaclk);
+	clk_disable_unprepare(dev->hclk);
+	clk_disable_unprepare(dev->aclk);
+	clk_disable_unprepare(dev->sclk);
+}
+
+static int check_alignment(struct scatterlist *sg_src,
+			   struct scatterlist *sg_dst,
+			   int align_mask)
+{
+	int in, out, align;
+
+	in = IS_ALIGNED((uint32_t)sg_src->offset, 4) &&
+	     IS_ALIGNED((uint32_t)sg_src->length, align_mask);
+	if (!sg_dst)
+		return in;
+	out = IS_ALIGNED((uint32_t)sg_dst->offset, 4) &&
+	      IS_ALIGNED((uint32_t)sg_dst->length, align_mask);
+	align = in && out;
+
+	return (align && (sg_src->length == sg_dst->length));
+}
+
+static int rk_load_data(struct rk_crypto_info *dev,
+			struct scatterlist *sg_src,
+			struct scatterlist *sg_dst)
+{
+	unsigned int count;
+
+	dev->aligned = dev->aligned ?
+		check_alignment(sg_src, sg_dst, dev->align_size) :
+		dev->aligned;
+	if (dev->aligned) {
+		count = min(dev->left_bytes, sg_src->length);
+		dev->left_bytes -= count;
+
+		if (!dma_map_sg(dev->dev, sg_src, 1, DMA_TO_DEVICE)) {
+			dev_err(dev->dev, "[%s:%d] dma_map_sg(src)  error\n",
+				__func__, __LINE__);
+			return -EINVAL;
+		}
+		dev->addr_in = sg_dma_address(sg_src);
+
+		if (sg_dst) {
+			if (!dma_map_sg(dev->dev, sg_dst, 1, DMA_FROM_DEVICE)) {
+				dev_err(dev->dev,
+					"[%s:%d] dma_map_sg(dst)  error\n",
+					__func__, __LINE__);
+				dma_unmap_sg(dev->dev, sg_src, 1,
+					     DMA_TO_DEVICE);
+				return -EINVAL;
+			}
+			dev->addr_out = sg_dma_address(sg_dst);
+		}
+	} else {
+		count = (dev->left_bytes > PAGE_SIZE) ?
+			PAGE_SIZE : dev->left_bytes;
+
+		if (!sg_pcopy_to_buffer(dev->first, dev->nents,
+					dev->addr_vir, count,
+					dev->total - dev->left_bytes)) {
+			dev_err(dev->dev, "[%s:%d] pcopy err\n",
+				__func__, __LINE__);
+			return -EINVAL;
+		}
+		dev->left_bytes -= count;
+		sg_init_one(&dev->sg_tmp, dev->addr_vir, count);
+		if (!dma_map_sg(dev->dev, &dev->sg_tmp, 1, DMA_TO_DEVICE)) {
+			dev_err(dev->dev, "[%s:%d] dma_map_sg(sg_tmp)  error\n",
+				__func__, __LINE__);
+			return -ENOMEM;
+		}
+		dev->addr_in = sg_dma_address(&dev->sg_tmp);
+
+		if (sg_dst) {
+			if (!dma_map_sg(dev->dev, &dev->sg_tmp, 1,
+					DMA_FROM_DEVICE)) {
+				dev_err(dev->dev,
+					"[%s:%d] dma_map_sg(sg_tmp)  error\n",
+					__func__, __LINE__);
+				dma_unmap_sg(dev->dev, &dev->sg_tmp, 1,
+					     DMA_TO_DEVICE);
+				return -ENOMEM;
+			}
+			dev->addr_out = sg_dma_address(&dev->sg_tmp);
+		}
+	}
+	dev->count = count;
+	return 0;
+}
+
+static void rk_unload_data(struct rk_crypto_info *dev)
+{
+	struct scatterlist *sg_in, *sg_out;
+
+	sg_in = dev->aligned ? dev->sg_src : &dev->sg_tmp;
+	dma_unmap_sg(dev->dev, sg_in, 1, DMA_TO_DEVICE);
+
+	if (dev->sg_dst) {
+		sg_out = dev->aligned ? dev->sg_dst : &dev->sg_tmp;
+		dma_unmap_sg(dev->dev, sg_out, 1, DMA_FROM_DEVICE);
+	}
+}
+
+static irqreturn_t rk_crypto_irq_handle(int irq, void *dev_id)
+{
+	struct rk_crypto_info *dev  = platform_get_drvdata(dev_id);
+	u32 interrupt_status;
+	int err = 0;
+
+	spin_lock(&dev->lock);
+	interrupt_status = CRYPTO_READ(dev, RK_CRYPTO_INTSTS);
+	CRYPTO_WRITE(dev, RK_CRYPTO_INTSTS, interrupt_status);
+	if (interrupt_status & 0x0a) {
+		dev_warn(dev->dev, "DMA Error\n");
+		err = -EFAULT;
+	} else if (interrupt_status & 0x05) {
+		err = dev->update(dev);
+	}
+	if (err)
+		dev->complete(dev, err);
+	spin_unlock(&dev->lock);
+	return IRQ_HANDLED;
+}
+
+static void rk_crypto_tasklet_cb(unsigned long data)
+{
+	struct rk_crypto_info *dev = (struct rk_crypto_info *)data;
+	struct crypto_async_request *async_req, *backlog;
+	unsigned long flags;
+	int err = 0;
+
+	spin_lock_irqsave(&dev->lock, flags);
+	backlog   = crypto_get_backlog(&dev->queue);
+	async_req = crypto_dequeue_request(&dev->queue);
+	spin_unlock_irqrestore(&dev->lock, flags);
+	if (!async_req) {
+		dev_err(dev->dev, "async_req is NULL !!\n");
+		return;
+	}
+	if (backlog) {
+		backlog->complete(backlog, -EINPROGRESS);
+		backlog = NULL;
+	}
+
+	if (crypto_tfm_alg_type(async_req->tfm) == CRYPTO_ALG_TYPE_ABLKCIPHER)
+		dev->ablk_req = ablkcipher_request_cast(async_req);
+	err = dev->start(dev);
+	if (err)
+		dev->complete(dev, err);
+}
+
+static struct rk_crypto_tmp *rk_cipher_algs[] = {
+	&rk_ecb_aes_alg,
+	&rk_cbc_aes_alg,
+	&rk_ecb_des_alg,
+	&rk_cbc_des_alg,
+	&rk_ecb_des3_ede_alg,
+	&rk_cbc_des3_ede_alg,
+};
+
+static int rk_crypto_register(struct rk_crypto_info *crypto_info)
+{
+	unsigned int i, k;
+	int err = 0;
+
+	for (i = 0; i < ARRAY_SIZE(rk_cipher_algs); i++) {
+		rk_cipher_algs[i]->dev = crypto_info;
+		err = crypto_register_alg(&rk_cipher_algs[i]->alg);
+		if (err)
+			goto err_cipher_algs;
+	}
+	return 0;
+
+err_cipher_algs:
+	for (k = 0; k < i; k++)
+		crypto_unregister_alg(&rk_cipher_algs[k]->alg);
+	return err;
+}
+
+static void rk_crypto_unregister(void)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(rk_cipher_algs); i++)
+		crypto_unregister_alg(&rk_cipher_algs[i]->alg);
+}
+
+static void rk_crypto_action(void *data)
+{
+	struct rk_crypto_info *crypto_info = data;
+
+	reset_control_assert(crypto_info->rst);
+}
+
+static const struct of_device_id crypto_of_id_table[] = {
+	{ .compatible = "rockchip,rk3288-crypto" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, crypto_of_id_table);
+
+static int rk_crypto_probe(struct platform_device *pdev)
+{
+	struct resource *res;
+	struct device *dev = &pdev->dev;
+	struct rk_crypto_info *crypto_info;
+	int err = 0;
+
+	crypto_info = devm_kzalloc(&pdev->dev,
+				   sizeof(*crypto_info), GFP_KERNEL);
+	if (!crypto_info) {
+		err = -ENOMEM;
+		goto err_crypto;
+	}
+
+	crypto_info->rst = devm_reset_control_get(dev, "crypto-rst");
+	if (IS_ERR(crypto_info->rst)) {
+		err = PTR_ERR(crypto_info->rst);
+		goto err_crypto;
+	}
+
+	reset_control_assert(crypto_info->rst);
+	usleep_range(10, 20);
+	reset_control_deassert(crypto_info->rst);
+
+	err = devm_add_action(dev, rk_crypto_action, crypto_info);
+	if (err) {
+		reset_control_assert(crypto_info->rst);
+		goto err_crypto;
+	}
+
+	spin_lock_init(&crypto_info->lock);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	crypto_info->reg = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(crypto_info->reg)) {
+		err = PTR_ERR(crypto_info->reg);
+		goto err_crypto;
+	}
+
+	crypto_info->aclk = devm_clk_get(&pdev->dev, "aclk");
+	if (IS_ERR(crypto_info->aclk)) {
+		err = PTR_ERR(crypto_info->aclk);
+		goto err_crypto;
+	}
+
+	crypto_info->hclk = devm_clk_get(&pdev->dev, "hclk");
+	if (IS_ERR(crypto_info->hclk)) {
+		err = PTR_ERR(crypto_info->hclk);
+		goto err_crypto;
+	}
+
+	crypto_info->sclk = devm_clk_get(&pdev->dev, "sclk");
+	if (IS_ERR(crypto_info->sclk)) {
+		err = PTR_ERR(crypto_info->sclk);
+		goto err_crypto;
+	}
+
+	crypto_info->dmaclk = devm_clk_get(&pdev->dev, "apb_pclk");
+	if (IS_ERR(crypto_info->dmaclk)) {
+		err = PTR_ERR(crypto_info->dmaclk);
+		goto err_crypto;
+	}
+
+	crypto_info->irq = platform_get_irq(pdev, 0);
+	if (crypto_info->irq < 0) {
+		dev_warn(crypto_info->dev,
+			 "control Interrupt is not available.\n");
+		err = crypto_info->irq;
+		goto err_crypto;
+	}
+
+	err = devm_request_irq(&pdev->dev, crypto_info->irq,
+			       rk_crypto_irq_handle, IRQF_SHARED,
+			       "rk-crypto", pdev);
+
+	if (err) {
+		dev_err(crypto_info->dev, "irq request failed.\n");
+		goto err_crypto;
+	}
+
+	crypto_info->dev = &pdev->dev;
+	platform_set_drvdata(pdev, crypto_info);
+
+	tasklet_init(&crypto_info->crypto_tasklet,
+		     rk_crypto_tasklet_cb, (unsigned long)crypto_info);
+	crypto_init_queue(&crypto_info->queue, 50);
+
+	crypto_info->enable_clk = rk_crypto_enable_clk;
+	crypto_info->disable_clk = rk_crypto_disable_clk;
+	crypto_info->load_data = rk_load_data;
+	crypto_info->unload_data = rk_unload_data;
+
+	err = rk_crypto_register(crypto_info);
+	if (err) {
+		dev_err(dev, "err in register alg");
+		goto err_register_alg;
+	}
+
+	dev_info(dev, "Crypto Accelerator successfully registered\n");
+	return 0;
+
+err_register_alg:
+	tasklet_kill(&crypto_info->crypto_tasklet);
+err_crypto:
+	return err;
+}
+
+static int rk_crypto_remove(struct platform_device *pdev)
+{
+	struct rk_crypto_info *crypto_tmp = platform_get_drvdata(pdev);
+
+	rk_crypto_unregister();
+	tasklet_kill(&crypto_tmp->crypto_tasklet);
+	return 0;
+}
+
+static struct platform_driver crypto_driver = {
+	.probe		= rk_crypto_probe,
+	.remove		= rk_crypto_remove,
+	.driver		= {
+		.name	= "rk3288-crypto",
+		.of_match_table	= crypto_of_id_table,
+	},
+};
+
+module_platform_driver(crypto_driver);
+
+MODULE_AUTHOR("Zain Wang <zain.wang@rock-chips.com>");
+MODULE_DESCRIPTION("Support for Rockchip's cryptographic engine");
+MODULE_LICENSE("GPL");
diff --git a/drivers/crypto/rockchip/rk3288_crypto.h b/drivers/crypto/rockchip/rk3288_crypto.h
new file mode 100644
index 0000000..e499c2c
--- /dev/null
+++ b/drivers/crypto/rockchip/rk3288_crypto.h
@@ -0,0 +1,216 @@
+#ifndef __RK3288_CRYPTO_H__
+#define __RK3288_CRYPTO_H__
+
+#include <crypto/aes.h>
+#include <crypto/des.h>
+#include <crypto/algapi.h>
+#include <linux/interrupt.h>
+#include <linux/delay.h>
+
+#define _SBF(v, f)			((v) << (f))
+
+/* Crypto control registers*/
+#define RK_CRYPTO_INTSTS		0x0000
+#define RK_CRYPTO_PKA_DONE_INT		BIT(5)
+#define RK_CRYPTO_HASH_DONE_INT		BIT(4)
+#define RK_CRYPTO_HRDMA_ERR_INT		BIT(3)
+#define RK_CRYPTO_HRDMA_DONE_INT	BIT(2)
+#define RK_CRYPTO_BCDMA_ERR_INT		BIT(1)
+#define RK_CRYPTO_BCDMA_DONE_INT	BIT(0)
+
+#define RK_CRYPTO_INTENA		0x0004
+#define RK_CRYPTO_PKA_DONE_ENA		BIT(5)
+#define RK_CRYPTO_HASH_DONE_ENA		BIT(4)
+#define RK_CRYPTO_HRDMA_ERR_ENA		BIT(3)
+#define RK_CRYPTO_HRDMA_DONE_ENA	BIT(2)
+#define RK_CRYPTO_BCDMA_ERR_ENA		BIT(1)
+#define RK_CRYPTO_BCDMA_DONE_ENA	BIT(0)
+
+#define RK_CRYPTO_CTRL			0x0008
+#define RK_CRYPTO_WRITE_MASK		_SBF(0xFFFF, 16)
+#define RK_CRYPTO_TRNG_FLUSH		BIT(9)
+#define RK_CRYPTO_TRNG_START		BIT(8)
+#define RK_CRYPTO_PKA_FLUSH		BIT(7)
+#define RK_CRYPTO_HASH_FLUSH		BIT(6)
+#define RK_CRYPTO_BLOCK_FLUSH		BIT(5)
+#define RK_CRYPTO_PKA_START		BIT(4)
+#define RK_CRYPTO_HASH_START		BIT(3)
+#define RK_CRYPTO_BLOCK_START		BIT(2)
+#define RK_CRYPTO_TDES_START		BIT(1)
+#define RK_CRYPTO_AES_START		BIT(0)
+
+#define RK_CRYPTO_CONF			0x000c
+/* HASH Receive DMA Address Mode:   fix | increment */
+#define RK_CRYPTO_HR_ADDR_MODE		BIT(8)
+/* Block Transmit DMA Address Mode: fix | increment */
+#define RK_CRYPTO_BT_ADDR_MODE		BIT(7)
+/* Block Receive DMA Address Mode:  fix | increment */
+#define RK_CRYPTO_BR_ADDR_MODE		BIT(6)
+#define RK_CRYPTO_BYTESWAP_HRFIFO	BIT(5)
+#define RK_CRYPTO_BYTESWAP_BTFIFO	BIT(4)
+#define RK_CRYPTO_BYTESWAP_BRFIFO	BIT(3)
+/* AES = 0 OR DES = 1 */
+#define RK_CRYPTO_DESSEL				BIT(2)
+#define RK_CYYPTO_HASHINSEL_INDEPENDENT_SOURCE		_SBF(0x00, 0)
+#define RK_CYYPTO_HASHINSEL_BLOCK_CIPHER_INPUT		_SBF(0x01, 0)
+#define RK_CYYPTO_HASHINSEL_BLOCK_CIPHER_OUTPUT		_SBF(0x02, 0)
+
+/* Block Receiving DMA Start Address Register */
+#define RK_CRYPTO_BRDMAS		0x0010
+/* Block Transmitting DMA Start Address Register */
+#define RK_CRYPTO_BTDMAS		0x0014
+/* Block Receiving DMA Length Register */
+#define RK_CRYPTO_BRDMAL		0x0018
+/* Hash Receiving DMA Start Address Register */
+#define RK_CRYPTO_HRDMAS		0x001c
+/* Hash Receiving DMA Length Register */
+#define RK_CRYPTO_HRDMAL		0x0020
+
+/* AES registers */
+#define RK_CRYPTO_AES_CTRL			  0x0080
+#define RK_CRYPTO_AES_BYTESWAP_CNT	BIT(11)
+#define RK_CRYPTO_AES_BYTESWAP_KEY	BIT(10)
+#define RK_CRYPTO_AES_BYTESWAP_IV	BIT(9)
+#define RK_CRYPTO_AES_BYTESWAP_DO	BIT(8)
+#define RK_CRYPTO_AES_BYTESWAP_DI	BIT(7)
+#define RK_CRYPTO_AES_KEY_CHANGE	BIT(6)
+#define RK_CRYPTO_AES_ECB_MODE		_SBF(0x00, 4)
+#define RK_CRYPTO_AES_CBC_MODE		_SBF(0x01, 4)
+#define RK_CRYPTO_AES_CTR_MODE		_SBF(0x02, 4)
+#define RK_CRYPTO_AES_128BIT_key	_SBF(0x00, 2)
+#define RK_CRYPTO_AES_192BIT_key	_SBF(0x01, 2)
+#define RK_CRYPTO_AES_256BIT_key	_SBF(0x02, 2)
+/* Slave = 0 / fifo = 1 */
+#define RK_CRYPTO_AES_FIFO_MODE		BIT(1)
+/* Encryption = 0 , Decryption = 1 */
+#define RK_CRYPTO_AES_DEC		BIT(0)
+
+#define RK_CRYPTO_AES_STS		0x0084
+#define RK_CRYPTO_AES_DONE		BIT(0)
+
+/* AES Input Data 0-3 Register */
+#define RK_CRYPTO_AES_DIN_0		0x0088
+#define RK_CRYPTO_AES_DIN_1		0x008c
+#define RK_CRYPTO_AES_DIN_2		0x0090
+#define RK_CRYPTO_AES_DIN_3		0x0094
+
+/* AES output Data 0-3 Register */
+#define RK_CRYPTO_AES_DOUT_0		0x0098
+#define RK_CRYPTO_AES_DOUT_1		0x009c
+#define RK_CRYPTO_AES_DOUT_2		0x00a0
+#define RK_CRYPTO_AES_DOUT_3		0x00a4
+
+/* AES IV Data 0-3 Register */
+#define RK_CRYPTO_AES_IV_0		0x00a8
+#define RK_CRYPTO_AES_IV_1		0x00ac
+#define RK_CRYPTO_AES_IV_2		0x00b0
+#define RK_CRYPTO_AES_IV_3		0x00b4
+
+/* AES Key Data 0-3 Register */
+#define RK_CRYPTO_AES_KEY_0		0x00b8
+#define RK_CRYPTO_AES_KEY_1		0x00bc
+#define RK_CRYPTO_AES_KEY_2		0x00c0
+#define RK_CRYPTO_AES_KEY_3		0x00c4
+#define RK_CRYPTO_AES_KEY_4		0x00c8
+#define RK_CRYPTO_AES_KEY_5		0x00cc
+#define RK_CRYPTO_AES_KEY_6		0x00d0
+#define RK_CRYPTO_AES_KEY_7		0x00d4
+
+/* des/tdes */
+#define RK_CRYPTO_TDES_CTRL		0x0100
+#define RK_CRYPTO_TDES_BYTESWAP_KEY	BIT(8)
+#define RK_CRYPTO_TDES_BYTESWAP_IV	BIT(7)
+#define RK_CRYPTO_TDES_BYTESWAP_DO	BIT(6)
+#define RK_CRYPTO_TDES_BYTESWAP_DI	BIT(5)
+/* 0: ECB, 1: CBC */
+#define RK_CRYPTO_TDES_CHAINMODE_CBC	BIT(4)
+/* TDES Key Mode, 0 : EDE, 1 : EEE */
+#define RK_CRYPTO_TDES_EEE		BIT(3)
+/* 0: DES, 1:TDES */
+#define RK_CRYPTO_TDES_SELECT		BIT(2)
+/* 0: Slave, 1:Fifo */
+#define RK_CRYPTO_TDES_FIFO_MODE	BIT(1)
+/* Encryption = 0 , Decryption = 1 */
+#define RK_CRYPTO_TDES_DEC		BIT(0)
+
+#define RK_CRYPTO_TDES_STS		0x0104
+#define RK_CRYPTO_TDES_DONE		BIT(0)
+
+#define RK_CRYPTO_TDES_DIN_0		0x0108
+#define RK_CRYPTO_TDES_DIN_1		0x010c
+#define RK_CRYPTO_TDES_DOUT_0		0x0110
+#define RK_CRYPTO_TDES_DOUT_1		0x0114
+#define RK_CRYPTO_TDES_IV_0		0x0118
+#define RK_CRYPTO_TDES_IV_1		0x011c
+#define RK_CRYPTO_TDES_KEY1_0		0x0120
+#define RK_CRYPTO_TDES_KEY1_1		0x0124
+#define RK_CRYPTO_TDES_KEY2_0		0x0128
+#define RK_CRYPTO_TDES_KEY2_1		0x012c
+#define RK_CRYPTO_TDES_KEY3_0		0x0130
+#define RK_CRYPTO_TDES_KEY3_1		0x0134
+
+#define CRYPTO_READ(dev, offset)		  \
+		readl_relaxed(((dev)->reg + (offset)))
+#define CRYPTO_WRITE(dev, offset, val)	  \
+		writel_relaxed((val), ((dev)->reg + (offset)))
+
+struct rk_crypto_info {
+	struct device			*dev;
+	struct clk			*aclk;
+	struct clk			*hclk;
+	struct clk			*sclk;
+	struct clk			*dmaclk;
+	struct reset_control		*rst;
+	void __iomem			*reg;
+	int				irq;
+	struct crypto_queue		queue;
+	struct tasklet_struct		crypto_tasklet;
+	struct ablkcipher_request	*ablk_req;
+	/* device lock */
+	spinlock_t			lock;
+
+	/* the public variable */
+	struct scatterlist		*sg_src;
+	struct scatterlist		*sg_dst;
+	struct scatterlist		sg_tmp;
+	struct scatterlist		*first;
+	unsigned int			left_bytes;
+	void				*addr_vir;
+	int				aligned;
+	int				align_size;
+	size_t				nents;
+	unsigned int			total;
+	unsigned int			count;
+	u32				mode;
+	dma_addr_t			addr_in;
+	dma_addr_t			addr_out;
+	int (*start)(struct rk_crypto_info *dev);
+	int (*update)(struct rk_crypto_info *dev);
+	void (*complete)(struct rk_crypto_info *dev, int err);
+	int (*enable_clk)(struct rk_crypto_info *dev);
+	void (*disable_clk)(struct rk_crypto_info *dev);
+	int (*load_data)(struct rk_crypto_info *dev,
+			 struct scatterlist *sg_src,
+			 struct scatterlist *sg_dst);
+	void (*unload_data)(struct rk_crypto_info *dev);
+};
+
+/* the private variable of cipher */
+struct rk_cipher_ctx {
+	struct rk_crypto_info		*dev;
+	unsigned int			keylen;
+};
+
+struct rk_crypto_tmp {
+	struct rk_crypto_info *dev;
+	struct crypto_alg alg;
+};
+
+extern struct rk_crypto_tmp rk_ecb_aes_alg;
+extern struct rk_crypto_tmp rk_cbc_aes_alg;
+extern struct rk_crypto_tmp rk_ecb_des_alg;
+extern struct rk_crypto_tmp rk_cbc_des_alg;
+extern struct rk_crypto_tmp rk_ecb_des3_ede_alg;
+extern struct rk_crypto_tmp rk_cbc_des3_ede_alg;
+
+#endif
diff --git a/drivers/crypto/rockchip/rk3288_crypto_ablkcipher.c b/drivers/crypto/rockchip/rk3288_crypto_ablkcipher.c
new file mode 100644
index 0000000..d98b681
--- /dev/null
+++ b/drivers/crypto/rockchip/rk3288_crypto_ablkcipher.c
@@ -0,0 +1,505 @@
+/*
+ * Crypto acceleration support for Rockchip RK3288
+ *
+ * Copyright (c) 2015, Fuzhou Rockchip Electronics Co., Ltd
+ *
+ * Author: Zain Wang <zain.wang@rock-chips.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * Some ideas are from marvell-cesa.c and s5p-sss.c driver.
+ */
+#include "rk3288_crypto.h"
+
+#define RK_CRYPTO_DEC			BIT(0)
+
+static void rk_crypto_complete(struct rk_crypto_info *dev, int err)
+{
+	if (dev->ablk_req->base.complete)
+		dev->ablk_req->base.complete(&dev->ablk_req->base, err);
+}
+
+static int rk_handle_req(struct rk_crypto_info *dev,
+			 struct ablkcipher_request *req)
+{
+	unsigned long flags;
+	int err;
+
+	if (!IS_ALIGNED(req->nbytes, dev->align_size))
+		return -EINVAL;
+
+	dev->left_bytes = req->nbytes;
+	dev->total = req->nbytes;
+	dev->sg_src = req->src;
+	dev->first = req->src;
+	dev->nents = sg_nents(req->src);
+	dev->sg_dst = req->dst;
+	dev->aligned = 1;
+	dev->ablk_req = req;
+
+	spin_lock_irqsave(&dev->lock, flags);
+	err = ablkcipher_enqueue_request(&dev->queue, req);
+	spin_unlock_irqrestore(&dev->lock, flags);
+	tasklet_schedule(&dev->crypto_tasklet);
+	return err;
+}
+
+static int rk_aes_setkey(struct crypto_ablkcipher *cipher,
+			 const u8 *key, unsigned int keylen)
+{
+	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(cipher);
+	struct rk_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	if (keylen != AES_KEYSIZE_128 && keylen != AES_KEYSIZE_192 &&
+	    keylen != AES_KEYSIZE_256) {
+		crypto_ablkcipher_set_flags(cipher, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+	ctx->keylen = keylen;
+	memcpy_toio(ctx->dev->reg + RK_CRYPTO_AES_KEY_0, key, keylen);
+	return 0;
+}
+
+static int rk_tdes_setkey(struct crypto_ablkcipher *cipher,
+			  const u8 *key, unsigned int keylen)
+{
+	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(cipher);
+	struct rk_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+	u32 tmp[DES_EXPKEY_WORDS];
+
+	if (keylen != DES_KEY_SIZE && keylen != DES3_EDE_KEY_SIZE) {
+		crypto_ablkcipher_set_flags(cipher, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	if (keylen == DES_KEY_SIZE) {
+		if (!des_ekey(tmp, key) &&
+		    (tfm->crt_flags & CRYPTO_TFM_REQ_WEAK_KEY)) {
+			tfm->crt_flags |= CRYPTO_TFM_RES_WEAK_KEY;
+			return -EINVAL;
+		}
+	}
+
+	ctx->keylen = keylen;
+	memcpy_toio(ctx->dev->reg + RK_CRYPTO_TDES_KEY1_0, key, keylen);
+	return 0;
+}
+
+static int rk_aes_ecb_encrypt(struct ablkcipher_request *req)
+{
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+	struct rk_cipher_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	struct rk_crypto_info *dev = ctx->dev;
+
+	dev->mode = RK_CRYPTO_AES_ECB_MODE;
+	return rk_handle_req(dev, req);
+}
+
+static int rk_aes_ecb_decrypt(struct ablkcipher_request *req)
+{
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+	struct rk_cipher_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	struct rk_crypto_info *dev = ctx->dev;
+
+	dev->mode = RK_CRYPTO_AES_ECB_MODE | RK_CRYPTO_DEC;
+	return rk_handle_req(dev, req);
+}
+
+static int rk_aes_cbc_encrypt(struct ablkcipher_request *req)
+{
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+	struct rk_cipher_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	struct rk_crypto_info *dev = ctx->dev;
+
+	dev->mode = RK_CRYPTO_AES_CBC_MODE;
+	return rk_handle_req(dev, req);
+}
+
+static int rk_aes_cbc_decrypt(struct ablkcipher_request *req)
+{
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+	struct rk_cipher_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	struct rk_crypto_info *dev = ctx->dev;
+
+	dev->mode = RK_CRYPTO_AES_CBC_MODE | RK_CRYPTO_DEC;
+	return rk_handle_req(dev, req);
+}
+
+static int rk_des_ecb_encrypt(struct ablkcipher_request *req)
+{
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+	struct rk_cipher_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	struct rk_crypto_info *dev = ctx->dev;
+
+	dev->mode = 0;
+	return rk_handle_req(dev, req);
+}
+
+static int rk_des_ecb_decrypt(struct ablkcipher_request *req)
+{
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+	struct rk_cipher_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	struct rk_crypto_info *dev = ctx->dev;
+
+	dev->mode = RK_CRYPTO_DEC;
+	return rk_handle_req(dev, req);
+}
+
+static int rk_des_cbc_encrypt(struct ablkcipher_request *req)
+{
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+	struct rk_cipher_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	struct rk_crypto_info *dev = ctx->dev;
+
+	dev->mode = RK_CRYPTO_TDES_CHAINMODE_CBC;
+	return rk_handle_req(dev, req);
+}
+
+static int rk_des_cbc_decrypt(struct ablkcipher_request *req)
+{
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+	struct rk_cipher_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	struct rk_crypto_info *dev = ctx->dev;
+
+	dev->mode = RK_CRYPTO_TDES_CHAINMODE_CBC | RK_CRYPTO_DEC;
+	return rk_handle_req(dev, req);
+}
+
+static int rk_des3_ede_ecb_encrypt(struct ablkcipher_request *req)
+{
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+	struct rk_cipher_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	struct rk_crypto_info *dev = ctx->dev;
+
+	dev->mode = RK_CRYPTO_TDES_SELECT;
+	return rk_handle_req(dev, req);
+}
+
+static int rk_des3_ede_ecb_decrypt(struct ablkcipher_request *req)
+{
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+	struct rk_cipher_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	struct rk_crypto_info *dev = ctx->dev;
+
+	dev->mode = RK_CRYPTO_TDES_SELECT | RK_CRYPTO_DEC;
+	return rk_handle_req(dev, req);
+}
+
+static int rk_des3_ede_cbc_encrypt(struct ablkcipher_request *req)
+{
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+	struct rk_cipher_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	struct rk_crypto_info *dev = ctx->dev;
+
+	dev->mode = RK_CRYPTO_TDES_SELECT | RK_CRYPTO_TDES_CHAINMODE_CBC;
+	return rk_handle_req(dev, req);
+}
+
+static int rk_des3_ede_cbc_decrypt(struct ablkcipher_request *req)
+{
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+	struct rk_cipher_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	struct rk_crypto_info *dev = ctx->dev;
+
+	dev->mode = RK_CRYPTO_TDES_SELECT | RK_CRYPTO_TDES_CHAINMODE_CBC |
+		    RK_CRYPTO_DEC;
+	return rk_handle_req(dev, req);
+}
+
+static void rk_ablk_hw_init(struct rk_crypto_info *dev)
+{
+	struct crypto_ablkcipher *cipher =
+		crypto_ablkcipher_reqtfm(dev->ablk_req);
+	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(cipher);
+	struct rk_cipher_ctx *ctx = crypto_ablkcipher_ctx(cipher);
+	u32 ivsize, block, conf_reg = 0;
+
+	block = crypto_tfm_alg_blocksize(tfm);
+	ivsize = crypto_ablkcipher_ivsize(cipher);
+
+	if (block == DES_BLOCK_SIZE) {
+		dev->mode |= RK_CRYPTO_TDES_FIFO_MODE |
+			     RK_CRYPTO_TDES_BYTESWAP_KEY |
+			     RK_CRYPTO_TDES_BYTESWAP_IV;
+		CRYPTO_WRITE(dev, RK_CRYPTO_TDES_CTRL, dev->mode);
+		memcpy_toio(dev->reg + RK_CRYPTO_TDES_IV_0,
+			    dev->ablk_req->info, ivsize);
+		conf_reg = RK_CRYPTO_DESSEL;
+	} else {
+		dev->mode |= RK_CRYPTO_AES_FIFO_MODE |
+			     RK_CRYPTO_AES_KEY_CHANGE |
+			     RK_CRYPTO_AES_BYTESWAP_KEY |
+			     RK_CRYPTO_AES_BYTESWAP_IV;
+		if (ctx->keylen == AES_KEYSIZE_192)
+			dev->mode |= RK_CRYPTO_AES_192BIT_key;
+		else if (ctx->keylen == AES_KEYSIZE_256)
+			dev->mode |= RK_CRYPTO_AES_256BIT_key;
+		CRYPTO_WRITE(dev, RK_CRYPTO_AES_CTRL, dev->mode);
+		memcpy_toio(dev->reg + RK_CRYPTO_AES_IV_0,
+			    dev->ablk_req->info, ivsize);
+	}
+	conf_reg |= RK_CRYPTO_BYTESWAP_BTFIFO |
+		    RK_CRYPTO_BYTESWAP_BRFIFO;
+	CRYPTO_WRITE(dev, RK_CRYPTO_CONF, conf_reg);
+	CRYPTO_WRITE(dev, RK_CRYPTO_INTENA,
+		     RK_CRYPTO_BCDMA_ERR_ENA | RK_CRYPTO_BCDMA_DONE_ENA);
+}
+
+static void crypto_dma_start(struct rk_crypto_info *dev)
+{
+	CRYPTO_WRITE(dev, RK_CRYPTO_BRDMAS, dev->addr_in);
+	CRYPTO_WRITE(dev, RK_CRYPTO_BRDMAL, dev->count / 4);
+	CRYPTO_WRITE(dev, RK_CRYPTO_BTDMAS, dev->addr_out);
+	CRYPTO_WRITE(dev, RK_CRYPTO_CTRL, RK_CRYPTO_BLOCK_START |
+		     _SBF(RK_CRYPTO_BLOCK_START, 16));
+}
+
+static int rk_set_data_start(struct rk_crypto_info *dev)
+{
+	int err;
+
+	err = dev->load_data(dev, dev->sg_src, dev->sg_dst);
+	if (!err)
+		crypto_dma_start(dev);
+	return err;
+}
+
+static int rk_ablk_start(struct rk_crypto_info *dev)
+{
+	unsigned long flags;
+	int err;
+
+	spin_lock_irqsave(&dev->lock, flags);
+	rk_ablk_hw_init(dev);
+	err = rk_set_data_start(dev);
+	spin_unlock_irqrestore(&dev->lock, flags);
+	return err;
+}
+
+static void rk_iv_copyback(struct rk_crypto_info *dev)
+{
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(dev->ablk_req);
+	u32 ivsize = crypto_ablkcipher_ivsize(tfm);
+
+	if (ivsize == DES_BLOCK_SIZE)
+		memcpy_fromio(dev->ablk_req->info,
+			      dev->reg + RK_CRYPTO_TDES_IV_0, ivsize);
+	else if (ivsize == AES_BLOCK_SIZE)
+		memcpy_fromio(dev->ablk_req->info,
+			      dev->reg + RK_CRYPTO_AES_IV_0, ivsize);
+}
+
+/* return:
+ *	true	some err was occurred
+ *	fault	no err, continue
+ */
+static int rk_ablk_rx(struct rk_crypto_info *dev)
+{
+	int err = 0;
+
+	dev->unload_data(dev);
+	if (!dev->aligned) {
+		if (!sg_pcopy_from_buffer(dev->ablk_req->dst, dev->nents,
+					  dev->addr_vir, dev->count,
+					  dev->total - dev->left_bytes -
+					  dev->count)) {
+			err = -EINVAL;
+			goto out_rx;
+		}
+	}
+	if (dev->left_bytes) {
+		if (dev->aligned) {
+			if (sg_is_last(dev->sg_src)) {
+				dev_err(dev->dev, "[%s:%d] Lack of data\n",
+					__func__, __LINE__);
+				err = -ENOMEM;
+				goto out_rx;
+			}
+			dev->sg_src = sg_next(dev->sg_src);
+			dev->sg_dst = sg_next(dev->sg_dst);
+		}
+		err = rk_set_data_start(dev);
+	} else {
+		rk_iv_copyback(dev);
+		/* here show the calculation is over without any err */
+		dev->complete(dev, 0);
+	}
+out_rx:
+	return err;
+}
+
+static int rk_ablk_cra_init(struct crypto_tfm *tfm)
+{
+	struct rk_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct crypto_alg *alg = tfm->__crt_alg;
+	struct rk_crypto_tmp *algt;
+
+	algt = container_of(alg, struct rk_crypto_tmp, alg);
+
+	ctx->dev = algt->dev;
+	ctx->dev->align_size = crypto_tfm_alg_alignmask(tfm) + 1;
+	ctx->dev->start = rk_ablk_start;
+	ctx->dev->update = rk_ablk_rx;
+	ctx->dev->complete = rk_crypto_complete;
+	ctx->dev->addr_vir = (char *)__get_free_page(GFP_KERNEL);
+
+	return ctx->dev->addr_vir ? ctx->dev->enable_clk(ctx->dev) : -ENOMEM;
+}
+
+static void rk_ablk_cra_exit(struct crypto_tfm *tfm)
+{
+	struct rk_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	free_page((unsigned long)ctx->dev->addr_vir);
+	ctx->dev->disable_clk(ctx->dev);
+}
+
+struct rk_crypto_tmp rk_ecb_aes_alg = {
+	.alg = {
+		.cra_name		= "ecb(aes)",
+		.cra_driver_name	= "ecb-aes-rk",
+		.cra_priority		= 300,
+		.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
+					  CRYPTO_ALG_ASYNC,
+		.cra_blocksize		= AES_BLOCK_SIZE,
+		.cra_ctxsize		= sizeof(struct rk_cipher_ctx),
+		.cra_alignmask		= 0x0f,
+		.cra_type		= &crypto_ablkcipher_type,
+		.cra_module		= THIS_MODULE,
+		.cra_init		= rk_ablk_cra_init,
+		.cra_exit		= rk_ablk_cra_exit,
+		.cra_u.ablkcipher	= {
+			.min_keysize	= AES_MIN_KEY_SIZE,
+			.max_keysize	= AES_MAX_KEY_SIZE,
+			.setkey		= rk_aes_setkey,
+			.encrypt	= rk_aes_ecb_encrypt,
+			.decrypt	= rk_aes_ecb_decrypt,
+		}
+	}
+};
+
+struct rk_crypto_tmp rk_cbc_aes_alg = {
+	.alg = {
+		.cra_name		= "cbc(aes)",
+		.cra_driver_name	= "cbc-aes-rk",
+		.cra_priority		= 300,
+		.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
+					  CRYPTO_ALG_ASYNC,
+		.cra_blocksize		= AES_BLOCK_SIZE,
+		.cra_ctxsize		= sizeof(struct rk_cipher_ctx),
+		.cra_alignmask		= 0x0f,
+		.cra_type		= &crypto_ablkcipher_type,
+		.cra_module		= THIS_MODULE,
+		.cra_init		= rk_ablk_cra_init,
+		.cra_exit		= rk_ablk_cra_exit,
+		.cra_u.ablkcipher	= {
+			.min_keysize	= AES_MIN_KEY_SIZE,
+			.max_keysize	= AES_MAX_KEY_SIZE,
+			.ivsize		= AES_BLOCK_SIZE,
+			.setkey		= rk_aes_setkey,
+			.encrypt	= rk_aes_cbc_encrypt,
+			.decrypt	= rk_aes_cbc_decrypt,
+		}
+	}
+};
+
+struct rk_crypto_tmp rk_ecb_des_alg = {
+	.alg = {
+		.cra_name		= "ecb(des)",
+		.cra_driver_name	= "ecb-des-rk",
+		.cra_priority		= 300,
+		.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
+					  CRYPTO_ALG_ASYNC,
+		.cra_blocksize		= DES_BLOCK_SIZE,
+		.cra_ctxsize		= sizeof(struct rk_cipher_ctx),
+		.cra_alignmask		= 0x07,
+		.cra_type		= &crypto_ablkcipher_type,
+		.cra_module		= THIS_MODULE,
+		.cra_init		= rk_ablk_cra_init,
+		.cra_exit		= rk_ablk_cra_exit,
+		.cra_u.ablkcipher	= {
+			.min_keysize	= DES_KEY_SIZE,
+			.max_keysize	= DES_KEY_SIZE,
+			.setkey		= rk_tdes_setkey,
+			.encrypt	= rk_des_ecb_encrypt,
+			.decrypt	= rk_des_ecb_decrypt,
+		}
+	}
+};
+
+struct rk_crypto_tmp rk_cbc_des_alg = {
+	.alg = {
+		.cra_name		= "cbc(des)",
+		.cra_driver_name	= "cbc-des-rk",
+		.cra_priority		= 300,
+		.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
+					  CRYPTO_ALG_ASYNC,
+		.cra_blocksize		= DES_BLOCK_SIZE,
+		.cra_ctxsize		= sizeof(struct rk_cipher_ctx),
+		.cra_alignmask		= 0x07,
+		.cra_type		= &crypto_ablkcipher_type,
+		.cra_module		= THIS_MODULE,
+		.cra_init		= rk_ablk_cra_init,
+		.cra_exit		= rk_ablk_cra_exit,
+		.cra_u.ablkcipher	= {
+			.min_keysize	= DES_KEY_SIZE,
+			.max_keysize	= DES_KEY_SIZE,
+			.ivsize		= DES_BLOCK_SIZE,
+			.setkey		= rk_tdes_setkey,
+			.encrypt	= rk_des_cbc_encrypt,
+			.decrypt	= rk_des_cbc_decrypt,
+		}
+	}
+};
+
+struct rk_crypto_tmp rk_ecb_des3_ede_alg = {
+	.alg = {
+		.cra_name		= "ecb(des3_ede)",
+		.cra_driver_name	= "ecb-des3-ede-rk",
+		.cra_priority		= 300,
+		.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
+					  CRYPTO_ALG_ASYNC,
+		.cra_blocksize		= DES_BLOCK_SIZE,
+		.cra_ctxsize		= sizeof(struct rk_cipher_ctx),
+		.cra_alignmask		= 0x07,
+		.cra_type		= &crypto_ablkcipher_type,
+		.cra_module		= THIS_MODULE,
+		.cra_init		= rk_ablk_cra_init,
+		.cra_exit		= rk_ablk_cra_exit,
+		.cra_u.ablkcipher	= {
+			.min_keysize	= DES3_EDE_KEY_SIZE,
+			.max_keysize	= DES3_EDE_KEY_SIZE,
+			.ivsize		= DES_BLOCK_SIZE,
+			.setkey		= rk_tdes_setkey,
+			.encrypt	= rk_des3_ede_ecb_encrypt,
+			.decrypt	= rk_des3_ede_ecb_decrypt,
+		}
+	}
+};
+
+struct rk_crypto_tmp rk_cbc_des3_ede_alg = {
+	.alg = {
+		.cra_name		= "cbc(des3_ede)",
+		.cra_driver_name	= "cbc-des3-ede-rk",
+		.cra_priority		= 300,
+		.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER |
+					  CRYPTO_ALG_ASYNC,
+		.cra_blocksize		= DES_BLOCK_SIZE,
+		.cra_ctxsize		= sizeof(struct rk_cipher_ctx),
+		.cra_alignmask		= 0x07,
+		.cra_type		= &crypto_ablkcipher_type,
+		.cra_module		= THIS_MODULE,
+		.cra_init		= rk_ablk_cra_init,
+		.cra_exit		= rk_ablk_cra_exit,
+		.cra_u.ablkcipher	= {
+			.min_keysize	= DES3_EDE_KEY_SIZE,
+			.max_keysize	= DES3_EDE_KEY_SIZE,
+			.ivsize		= DES_BLOCK_SIZE,
+			.setkey		= rk_tdes_setkey,
+			.encrypt	= rk_des3_ede_cbc_encrypt,
+			.decrypt	= rk_des3_ede_cbc_decrypt,
+		}
+	}
+};
diff --git a/drivers/crypto/sahara.c b/drivers/crypto/sahara.c
index f68c24a..6c4f91c 100644
--- a/drivers/crypto/sahara.c
+++ b/drivers/crypto/sahara.c
@@ -130,18 +130,18 @@
 #define SAHARA_REG_IDAR		0x20
 
 struct sahara_hw_desc {
-	u32		hdr;
-	u32		len1;
-	dma_addr_t	p1;
-	u32		len2;
-	dma_addr_t	p2;
-	dma_addr_t	next;
+	u32	hdr;
+	u32	len1;
+	u32	p1;
+	u32	len2;
+	u32	p2;
+	u32	next;
 };
 
 struct sahara_hw_link {
-	u32		len;
-	dma_addr_t	p;
-	dma_addr_t	next;
+	u32	len;
+	u32	p;
+	u32	next;
 };
 
 struct sahara_ctx {
@@ -228,9 +228,9 @@
 
 	size_t			total;
 	struct scatterlist	*in_sg;
-	unsigned int		nb_in_sg;
+	int		nb_in_sg;
 	struct scatterlist	*out_sg;
-	unsigned int		nb_out_sg;
+	int		nb_out_sg;
 
 	u32			error;
 };
@@ -416,8 +416,8 @@
 		return;
 
 	for (i = 0; i < SAHARA_MAX_HW_DESC; i++) {
-		dev_dbg(dev->device, "Descriptor (%d) (0x%08x):\n",
-			i, dev->hw_phys_desc[i]);
+		dev_dbg(dev->device, "Descriptor (%d) (%pad):\n",
+			i, &dev->hw_phys_desc[i]);
 		dev_dbg(dev->device, "\thdr = 0x%08x\n", dev->hw_desc[i]->hdr);
 		dev_dbg(dev->device, "\tlen1 = %u\n", dev->hw_desc[i]->len1);
 		dev_dbg(dev->device, "\tp1 = 0x%08x\n", dev->hw_desc[i]->p1);
@@ -437,8 +437,8 @@
 		return;
 
 	for (i = 0; i < SAHARA_MAX_HW_LINK; i++) {
-		dev_dbg(dev->device, "Link (%d) (0x%08x):\n",
-			i, dev->hw_phys_link[i]);
+		dev_dbg(dev->device, "Link (%d) (%pad):\n",
+			i, &dev->hw_phys_link[i]);
 		dev_dbg(dev->device, "\tlen = %u\n", dev->hw_link[i]->len);
 		dev_dbg(dev->device, "\tp = 0x%08x\n", dev->hw_link[i]->p);
 		dev_dbg(dev->device, "\tnext = 0x%08x\n",
@@ -477,7 +477,15 @@
 	}
 
 	dev->nb_in_sg = sg_nents_for_len(dev->in_sg, dev->total);
+	if (dev->nb_in_sg < 0) {
+		dev_err(dev->device, "Invalid numbers of src SG.\n");
+		return dev->nb_in_sg;
+	}
 	dev->nb_out_sg = sg_nents_for_len(dev->out_sg, dev->total);
+	if (dev->nb_out_sg < 0) {
+		dev_err(dev->device, "Invalid numbers of dst SG.\n");
+		return dev->nb_out_sg;
+	}
 	if ((dev->nb_in_sg + dev->nb_out_sg) > SAHARA_MAX_HW_LINK) {
 		dev_err(dev->device, "not enough hw links (%d)\n",
 			dev->nb_in_sg + dev->nb_out_sg);
@@ -793,6 +801,10 @@
 	dev->in_sg = rctx->in_sg;
 
 	dev->nb_in_sg = sg_nents_for_len(dev->in_sg, rctx->total);
+	if (dev->nb_in_sg < 0) {
+		dev_err(dev->device, "Invalid numbers of src SG.\n");
+		return dev->nb_in_sg;
+	}
 	if ((dev->nb_in_sg) > SAHARA_MAX_HW_LINK) {
 		dev_err(dev->device, "not enough hw links (%d)\n",
 			dev->nb_in_sg + dev->nb_out_sg);
diff --git a/drivers/crypto/sunxi-ss/sun4i-ss-core.c b/drivers/crypto/sunxi-ss/sun4i-ss-core.c
index eab6fe2..107cd2a 100644
--- a/drivers/crypto/sunxi-ss/sun4i-ss-core.c
+++ b/drivers/crypto/sunxi-ss/sun4i-ss-core.c
@@ -39,6 +39,7 @@
 		.import = sun4i_hash_import_md5,
 		.halg = {
 			.digestsize = MD5_DIGEST_SIZE,
+			.statesize = sizeof(struct md5_state),
 			.base = {
 				.cra_name = "md5",
 				.cra_driver_name = "md5-sun4i-ss",
@@ -66,6 +67,7 @@
 		.import = sun4i_hash_import_sha1,
 		.halg = {
 			.digestsize = SHA1_DIGEST_SIZE,
+			.statesize = sizeof(struct sha1_state),
 			.base = {
 				.cra_name = "sha1",
 				.cra_driver_name = "sha1-sun4i-ss",
diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c
index b6f9f42..a0d4a08 100644
--- a/drivers/crypto/talitos.c
+++ b/drivers/crypto/talitos.c
@@ -1216,6 +1216,7 @@
 	struct talitos_private *priv = dev_get_drvdata(dev);
 	bool is_sec1 = has_ftr_sec1(priv);
 	int max_len = is_sec1 ? TALITOS1_MAX_DATA_LEN : TALITOS2_MAX_DATA_LEN;
+	void *err;
 
 	if (cryptlen + authsize > max_len) {
 		dev_err(dev, "length exceeds h/w max limit\n");
@@ -1228,14 +1229,29 @@
 	if (!dst || dst == src) {
 		src_nents = sg_nents_for_len(src,
 					     assoclen + cryptlen + authsize);
+		if (src_nents < 0) {
+			dev_err(dev, "Invalid number of src SG.\n");
+			err = ERR_PTR(-EINVAL);
+			goto error_sg;
+		}
 		src_nents = (src_nents == 1) ? 0 : src_nents;
 		dst_nents = dst ? src_nents : 0;
 	} else { /* dst && dst != src*/
 		src_nents = sg_nents_for_len(src, assoclen + cryptlen +
 						 (encrypt ? 0 : authsize));
+		if (src_nents < 0) {
+			dev_err(dev, "Invalid number of src SG.\n");
+			err = ERR_PTR(-EINVAL);
+			goto error_sg;
+		}
 		src_nents = (src_nents == 1) ? 0 : src_nents;
 		dst_nents = sg_nents_for_len(dst, assoclen + cryptlen +
 						 (encrypt ? authsize : 0));
+		if (dst_nents < 0) {
+			dev_err(dev, "Invalid number of dst SG.\n");
+			err = ERR_PTR(-EINVAL);
+			goto error_sg;
+		}
 		dst_nents = (dst_nents == 1) ? 0 : dst_nents;
 	}
 
@@ -1260,11 +1276,9 @@
 
 	edesc = kmalloc(alloc_len, GFP_DMA | flags);
 	if (!edesc) {
-		if (iv_dma)
-			dma_unmap_single(dev, iv_dma, ivsize, DMA_TO_DEVICE);
-
 		dev_err(dev, "could not allocate edescriptor\n");
-		return ERR_PTR(-ENOMEM);
+		err = ERR_PTR(-ENOMEM);
+		goto error_sg;
 	}
 
 	edesc->src_nents = src_nents;
@@ -1277,6 +1291,10 @@
 						     DMA_BIDIRECTIONAL);
 
 	return edesc;
+error_sg:
+	if (iv_dma)
+		dma_unmap_single(dev, iv_dma, ivsize, DMA_TO_DEVICE);
+	return err;
 }
 
 static struct talitos_edesc *aead_edesc_alloc(struct aead_request *areq, u8 *iv,
@@ -1830,11 +1848,16 @@
 	unsigned int nbytes_to_hash;
 	unsigned int to_hash_later;
 	unsigned int nsg;
+	int nents;
 
 	if (!req_ctx->last && (nbytes + req_ctx->nbuf <= blocksize)) {
 		/* Buffer up to one whole block */
-		sg_copy_to_buffer(areq->src,
-				  sg_nents_for_len(areq->src, nbytes),
+		nents = sg_nents_for_len(areq->src, nbytes);
+		if (nents < 0) {
+			dev_err(ctx->dev, "Invalid number of src SG.\n");
+			return nents;
+		}
+		sg_copy_to_buffer(areq->src, nents,
 				  req_ctx->buf + req_ctx->nbuf, nbytes);
 		req_ctx->nbuf += nbytes;
 		return 0;
@@ -1867,7 +1890,11 @@
 		req_ctx->psrc = areq->src;
 
 	if (to_hash_later) {
-		int nents = sg_nents_for_len(areq->src, nbytes);
+		nents = sg_nents_for_len(areq->src, nbytes);
+		if (nents < 0) {
+			dev_err(ctx->dev, "Invalid number of src SG.\n");
+			return nents;
+		}
 		sg_pcopy_to_buffer(areq->src, nents,
 				      req_ctx->bufnext,
 				      to_hash_later,
@@ -2297,6 +2324,22 @@
 	/* ABLKCIPHER algorithms. */
 	{	.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
 		.alg.crypto = {
+			.cra_name = "ecb(aes)",
+			.cra_driver_name = "ecb-aes-talitos",
+			.cra_blocksize = AES_BLOCK_SIZE,
+			.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
+				     CRYPTO_ALG_ASYNC,
+			.cra_ablkcipher = {
+				.min_keysize = AES_MIN_KEY_SIZE,
+				.max_keysize = AES_MAX_KEY_SIZE,
+				.ivsize = AES_BLOCK_SIZE,
+			}
+		},
+		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
+				     DESC_HDR_SEL0_AESU,
+	},
+	{	.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
+		.alg.crypto = {
 			.cra_name = "cbc(aes)",
 			.cra_driver_name = "cbc-aes-talitos",
 			.cra_blocksize = AES_BLOCK_SIZE,
@@ -2314,6 +2357,73 @@
 	},
 	{	.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
 		.alg.crypto = {
+			.cra_name = "ctr(aes)",
+			.cra_driver_name = "ctr-aes-talitos",
+			.cra_blocksize = AES_BLOCK_SIZE,
+			.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
+				     CRYPTO_ALG_ASYNC,
+			.cra_ablkcipher = {
+				.min_keysize = AES_MIN_KEY_SIZE,
+				.max_keysize = AES_MAX_KEY_SIZE,
+				.ivsize = AES_BLOCK_SIZE,
+			}
+		},
+		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
+				     DESC_HDR_SEL0_AESU |
+				     DESC_HDR_MODE0_AESU_CTR,
+	},
+	{	.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
+		.alg.crypto = {
+			.cra_name = "ecb(des)",
+			.cra_driver_name = "ecb-des-talitos",
+			.cra_blocksize = DES_BLOCK_SIZE,
+			.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
+				     CRYPTO_ALG_ASYNC,
+			.cra_ablkcipher = {
+				.min_keysize = DES_KEY_SIZE,
+				.max_keysize = DES_KEY_SIZE,
+				.ivsize = DES_BLOCK_SIZE,
+			}
+		},
+		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
+				     DESC_HDR_SEL0_DEU,
+	},
+	{	.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
+		.alg.crypto = {
+			.cra_name = "cbc(des)",
+			.cra_driver_name = "cbc-des-talitos",
+			.cra_blocksize = DES_BLOCK_SIZE,
+			.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
+				     CRYPTO_ALG_ASYNC,
+			.cra_ablkcipher = {
+				.min_keysize = DES_KEY_SIZE,
+				.max_keysize = DES_KEY_SIZE,
+				.ivsize = DES_BLOCK_SIZE,
+			}
+		},
+		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
+				     DESC_HDR_SEL0_DEU |
+				     DESC_HDR_MODE0_DEU_CBC,
+	},
+	{	.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
+		.alg.crypto = {
+			.cra_name = "ecb(des3_ede)",
+			.cra_driver_name = "ecb-3des-talitos",
+			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
+				     CRYPTO_ALG_ASYNC,
+			.cra_ablkcipher = {
+				.min_keysize = DES3_EDE_KEY_SIZE,
+				.max_keysize = DES3_EDE_KEY_SIZE,
+				.ivsize = DES3_EDE_BLOCK_SIZE,
+			}
+		},
+		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
+				     DESC_HDR_SEL0_DEU |
+				     DESC_HDR_MODE0_DEU_3DES,
+	},
+	{	.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
+		.alg.crypto = {
 			.cra_name = "cbc(des3_ede)",
 			.cra_driver_name = "cbc-3des-talitos",
 			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
diff --git a/drivers/crypto/talitos.h b/drivers/crypto/talitos.h
index 0090f32..8dd8f40 100644
--- a/drivers/crypto/talitos.h
+++ b/drivers/crypto/talitos.h
@@ -345,6 +345,7 @@
 /* primary execution unit mode (MODE0) and derivatives */
 #define	DESC_HDR_MODE0_ENCRYPT		cpu_to_be32(0x00100000)
 #define	DESC_HDR_MODE0_AESU_CBC		cpu_to_be32(0x00200000)
+#define	DESC_HDR_MODE0_AESU_CTR		cpu_to_be32(0x00600000)
 #define	DESC_HDR_MODE0_DEU_CBC		cpu_to_be32(0x00400000)
 #define	DESC_HDR_MODE0_DEU_3DES		cpu_to_be32(0x00200000)
 #define	DESC_HDR_MODE0_MDEU_CONT	cpu_to_be32(0x08000000)
diff --git a/drivers/crypto/ux500/Kconfig b/drivers/crypto/ux500/Kconfig
index 3079644..0e338bf 100644
--- a/drivers/crypto/ux500/Kconfig
+++ b/drivers/crypto/ux500/Kconfig
@@ -18,6 +18,8 @@
         tristate "UX500 crypto driver for HASH block"
         depends on CRYPTO_DEV_UX500
         select CRYPTO_HASH
+	select CRYPTO_SHA1
+	select CRYPTO_SHA256
         help
           This selects the hash driver for the UX500_HASH hardware.
           Depends on UX500/STM DMA if running in DMA mode.
diff --git a/drivers/crypto/ux500/hash/hash_core.c b/drivers/crypto/ux500/hash/hash_core.c
index f47d112..d6fdc58 100644
--- a/drivers/crypto/ux500/hash/hash_core.c
+++ b/drivers/crypto/ux500/hash/hash_core.c
@@ -41,22 +41,6 @@
 module_param(hash_mode, int, 0);
 MODULE_PARM_DESC(hash_mode, "CPU or DMA mode. CPU = 0 (default), DMA = 1");
 
-/**
- * Pre-calculated empty message digests.
- */
-static const u8 zero_message_hash_sha1[SHA1_DIGEST_SIZE] = {
-	0xda, 0x39, 0xa3, 0xee, 0x5e, 0x6b, 0x4b, 0x0d,
-	0x32, 0x55, 0xbf, 0xef, 0x95, 0x60, 0x18, 0x90,
-	0xaf, 0xd8, 0x07, 0x09
-};
-
-static const u8 zero_message_hash_sha256[SHA256_DIGEST_SIZE] = {
-	0xe3, 0xb0, 0xc4, 0x42, 0x98, 0xfc, 0x1c, 0x14,
-	0x9a, 0xfb, 0xf4, 0xc8, 0x99, 0x6f, 0xb9, 0x24,
-	0x27, 0xae, 0x41, 0xe4, 0x64, 0x9b, 0x93, 0x4c,
-	0xa4, 0x95, 0x99, 0x1b, 0x78, 0x52, 0xb8, 0x55
-};
-
 /* HMAC-SHA1, no key */
 static const u8 zero_message_hmac_sha1[SHA1_DIGEST_SIZE] = {
 	0xfb, 0xdb, 0x1d, 0x1b, 0x18, 0xaa, 0x6c, 0x08,
@@ -242,13 +226,13 @@
 
 	if (HASH_OPER_MODE_HASH == ctx->config.oper_mode) {
 		if (HASH_ALGO_SHA1 == ctx->config.algorithm) {
-			memcpy(zero_hash, &zero_message_hash_sha1[0],
+			memcpy(zero_hash, &sha1_zero_message_hash[0],
 			       SHA1_DIGEST_SIZE);
 			*zero_hash_size = SHA1_DIGEST_SIZE;
 			*zero_digest = true;
 		} else if (HASH_ALGO_SHA256 ==
 				ctx->config.algorithm) {
-			memcpy(zero_hash, &zero_message_hash_sha256[0],
+			memcpy(zero_hash, &sha256_zero_message_hash[0],
 			       SHA256_DIGEST_SIZE);
 			*zero_hash_size = SHA256_DIGEST_SIZE;
 			*zero_digest = true;
diff --git a/drivers/crypto/vmx/aes_cbc.c b/drivers/crypto/vmx/aes_cbc.c
index 0b8fe2e..78a9786 100644
--- a/drivers/crypto/vmx/aes_cbc.c
+++ b/drivers/crypto/vmx/aes_cbc.c
@@ -191,7 +191,7 @@
 	.cra_init = p8_aes_cbc_init,
 	.cra_exit = p8_aes_cbc_exit,
 	.cra_blkcipher = {
-			  .ivsize = 0,
+			  .ivsize = AES_BLOCK_SIZE,
 			  .min_keysize = AES_MIN_KEY_SIZE,
 			  .max_keysize = AES_MAX_KEY_SIZE,
 			  .setkey = p8_aes_cbc_setkey,
diff --git a/drivers/crypto/vmx/aes_ctr.c b/drivers/crypto/vmx/aes_ctr.c
index ee1306c..1febc4f 100644
--- a/drivers/crypto/vmx/aes_ctr.c
+++ b/drivers/crypto/vmx/aes_ctr.c
@@ -175,7 +175,7 @@
 	.cra_init = p8_aes_ctr_init,
 	.cra_exit = p8_aes_ctr_exit,
 	.cra_blkcipher = {
-			  .ivsize = 0,
+			  .ivsize = AES_BLOCK_SIZE,
 			  .min_keysize = AES_MIN_KEY_SIZE,
 			  .max_keysize = AES_MAX_KEY_SIZE,
 			  .setkey = p8_aes_ctr_setkey,
diff --git a/drivers/dma/mic_x100_dma.c b/drivers/dma/mic_x100_dma.c
index cddfa8d..068e920 100644
--- a/drivers/dma/mic_x100_dma.c
+++ b/drivers/dma/mic_x100_dma.c
@@ -317,7 +317,6 @@
 	struct mic_dma_chan *mic_ch = to_mic_dma_chan(ch);
 	struct device *dev = mic_dma_ch_to_device(mic_ch);
 	int result;
-	struct dma_async_tx_descriptor *tx = NULL;
 
 	if (!len && !flags)
 		return NULL;
@@ -325,13 +324,10 @@
 	spin_lock(&mic_ch->prep_lock);
 	result = mic_dma_do_dma(mic_ch, flags, dma_src, dma_dest, len);
 	if (result >= 0)
-		tx = allocate_tx(mic_ch);
-
-	if (!tx)
-		dev_err(dev, "Error enqueueing dma, error=%d\n", result);
-
+		return allocate_tx(mic_ch);
+	dev_err(dev, "Error enqueueing dma, error=%d\n", result);
 	spin_unlock(&mic_ch->prep_lock);
-	return tx;
+	return NULL;
 }
 
 static struct dma_async_tx_descriptor *
@@ -339,14 +335,13 @@
 {
 	struct mic_dma_chan *mic_ch = to_mic_dma_chan(ch);
 	int ret;
-	struct dma_async_tx_descriptor *tx = NULL;
 
 	spin_lock(&mic_ch->prep_lock);
 	ret = mic_dma_do_dma(mic_ch, flags, 0, 0, 0);
 	if (!ret)
-		tx = allocate_tx(mic_ch);
+		return allocate_tx(mic_ch);
 	spin_unlock(&mic_ch->prep_lock);
-	return tx;
+	return NULL;
 }
 
 /* Return the status of the transaction */
diff --git a/drivers/dma/xgene-dma.c b/drivers/dma/xgene-dma.c
index 9dfa2b0..9cb93c5 100644
--- a/drivers/dma/xgene-dma.c
+++ b/drivers/dma/xgene-dma.c
@@ -29,6 +29,7 @@
 #include <linux/dmapool.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
+#include <linux/irq.h>
 #include <linux/module.h>
 #include <linux/of_device.h>
 
@@ -1610,6 +1611,7 @@
 	/* Register DMA channel rx irq */
 	for (i = 0; i < XGENE_DMA_MAX_CHANNEL; i++) {
 		chan = &pdma->chan[i];
+		irq_set_status_flags(chan->rx_irq, IRQ_DISABLE_UNLAZY);
 		ret = devm_request_irq(chan->dev, chan->rx_irq,
 				       xgene_dma_chan_ring_isr,
 				       0, chan->name, chan);
@@ -1620,6 +1622,7 @@
 
 			for (j = 0; j < i; j++) {
 				chan = &pdma->chan[i];
+				irq_clear_status_flags(chan->rx_irq, IRQ_DISABLE_UNLAZY);
 				devm_free_irq(chan->dev, chan->rx_irq, chan);
 			}
 
@@ -1640,6 +1643,7 @@
 
 	for (i = 0; i < XGENE_DMA_MAX_CHANNEL; i++) {
 		chan = &pdma->chan[i];
+		irq_clear_status_flags(chan->rx_irq, IRQ_DISABLE_UNLAZY);
 		devm_free_irq(chan->dev, chan->rx_irq, chan);
 	}
 }
diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile
index dbf53e0..be163e2 100644
--- a/drivers/edac/Makefile
+++ b/drivers/edac/Makefile
@@ -10,7 +10,7 @@
 obj-$(CONFIG_EDAC_MM_EDAC)		+= edac_core.o
 
 edac_core-y	:= edac_mc.o edac_device.o edac_mc_sysfs.o
-edac_core-y	+= edac_module.o edac_device_sysfs.o
+edac_core-y	+= edac_module.o edac_device_sysfs.o wq.o
 
 edac_core-$(CONFIG_EDAC_DEBUG)		+= debugfs.o
 
diff --git a/drivers/edac/edac_device.c b/drivers/edac/edac_device.c
index 592af5f..a979003 100644
--- a/drivers/edac/edac_device.c
+++ b/drivers/edac/edac_device.c
@@ -390,11 +390,9 @@
 	 * between integral seconds
 	 */
 	if (edac_dev->poll_msec == 1000)
-		queue_delayed_work(edac_workqueue, &edac_dev->work,
-				round_jiffies_relative(edac_dev->delay));
+		edac_queue_work(&edac_dev->work, round_jiffies_relative(edac_dev->delay));
 	else
-		queue_delayed_work(edac_workqueue, &edac_dev->work,
-				edac_dev->delay);
+		edac_queue_work(&edac_dev->work, edac_dev->delay);
 }
 
 /*
@@ -402,8 +400,8 @@
  *	initialize a workq item for this edac_device instance
  *	passing in the new delay period in msec
  */
-void edac_device_workq_setup(struct edac_device_ctl_info *edac_dev,
-				unsigned msec)
+static void edac_device_workq_setup(struct edac_device_ctl_info *edac_dev,
+				    unsigned msec)
 {
 	edac_dbg(0, "\n");
 
@@ -422,29 +420,23 @@
 	 * to fire together on the 1 second exactly
 	 */
 	if (edac_dev->poll_msec == 1000)
-		queue_delayed_work(edac_workqueue, &edac_dev->work,
-				round_jiffies_relative(edac_dev->delay));
+		edac_queue_work(&edac_dev->work, round_jiffies_relative(edac_dev->delay));
 	else
-		queue_delayed_work(edac_workqueue, &edac_dev->work,
-				edac_dev->delay);
+		edac_queue_work(&edac_dev->work, edac_dev->delay);
 }
 
 /*
  * edac_device_workq_teardown
  *	stop the workq processing on this edac_dev
  */
-void edac_device_workq_teardown(struct edac_device_ctl_info *edac_dev)
+static void edac_device_workq_teardown(struct edac_device_ctl_info *edac_dev)
 {
-	int status;
-
 	if (!edac_dev->edac_check)
 		return;
 
-	status = cancel_delayed_work(&edac_dev->work);
-	if (status == 0) {
-		/* workq instance might be running, wait for it */
-		flush_workqueue(edac_workqueue);
-	}
+	edac_dev->op_state = OP_OFFLINE;
+
+	edac_stop_work(&edac_dev->work);
 }
 
 /*
@@ -457,16 +449,15 @@
 void edac_device_reset_delay_period(struct edac_device_ctl_info *edac_dev,
 					unsigned long value)
 {
-	/* cancel the current workq request, without the mutex lock */
-	edac_device_workq_teardown(edac_dev);
+	unsigned long jiffs = msecs_to_jiffies(value);
 
-	/* acquire the mutex before doing the workq setup */
-	mutex_lock(&device_ctls_mutex);
+	if (value == 1000)
+		jiffs = round_jiffies_relative(value);
 
-	/* restart the workq request, with new delay value */
-	edac_device_workq_setup(edac_dev, value);
+	edac_dev->poll_msec = value;
+	edac_dev->delay	    = jiffs;
 
-	mutex_unlock(&device_ctls_mutex);
+	edac_mod_work(&edac_dev->work, jiffs);
 }
 
 /*
diff --git a/drivers/edac/edac_device_sysfs.c b/drivers/edac/edac_device_sysfs.c
index fb68a06..93da1a4 100644
--- a/drivers/edac/edac_device_sysfs.c
+++ b/drivers/edac/edac_device_sysfs.c
@@ -237,11 +237,6 @@
 
 	/* get the /sys/devices/system/edac reference */
 	edac_subsys = edac_get_sysfs_subsys();
-	if (edac_subsys == NULL) {
-		edac_dbg(1, "no edac_subsys error\n");
-		err = -ENODEV;
-		goto err_out;
-	}
 
 	/* Point to the 'edac_subsys' this instance 'reports' to */
 	edac_dev->edac_subsys = edac_subsys;
@@ -256,7 +251,7 @@
 
 	if (!try_module_get(edac_dev->owner)) {
 		err = -ENODEV;
-		goto err_mod_get;
+		goto err_out;
 	}
 
 	/* register */
@@ -282,9 +277,6 @@
 err_kobj_reg:
 	module_put(edac_dev->owner);
 
-err_mod_get:
-	edac_put_sysfs_subsys();
-
 err_out:
 	return err;
 }
@@ -306,7 +298,6 @@
 	 *   b) 'kfree' the memory
 	 */
 	kobject_put(&dev->kobj);
-	edac_put_sysfs_subsys();
 }
 
 /* edac_dev -> instance information */
diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c
index 77ecd6a..8adfc16 100644
--- a/drivers/edac/edac_mc.c
+++ b/drivers/edac/edac_mc.c
@@ -548,8 +548,7 @@
 	mutex_unlock(&mem_ctls_mutex);
 
 	/* Reschedule */
-	queue_delayed_work(edac_workqueue, &mci->work,
-			msecs_to_jiffies(edac_mc_get_poll_msec()));
+	edac_queue_work(&mci->work, msecs_to_jiffies(edac_mc_get_poll_msec()));
 }
 
 /*
@@ -561,8 +560,7 @@
  *
  *		called with the mem_ctls_mutex held
  */
-static void edac_mc_workq_setup(struct mem_ctl_info *mci, unsigned msec,
-				bool init)
+static void edac_mc_workq_setup(struct mem_ctl_info *mci, unsigned msec)
 {
 	edac_dbg(0, "\n");
 
@@ -570,10 +568,9 @@
 	if (mci->op_state != OP_RUNNING_POLL)
 		return;
 
-	if (init)
-		INIT_DELAYED_WORK(&mci->work, edac_mc_workq_function);
+	INIT_DELAYED_WORK(&mci->work, edac_mc_workq_function);
 
-	mod_delayed_work(edac_workqueue, &mci->work, msecs_to_jiffies(msec));
+	edac_queue_work(&mci->work, msecs_to_jiffies(msec));
 }
 
 /*
@@ -586,18 +583,9 @@
  */
 static void edac_mc_workq_teardown(struct mem_ctl_info *mci)
 {
-	int status;
+	mci->op_state = OP_OFFLINE;
 
-	if (mci->op_state != OP_RUNNING_POLL)
-		return;
-
-	status = cancel_delayed_work(&mci->work);
-	if (status == 0) {
-		edac_dbg(0, "not canceled, flush the queue\n");
-
-		/* workq instance might be running, wait for it */
-		flush_workqueue(edac_workqueue);
-	}
+	edac_stop_work(&mci->work);
 }
 
 /*
@@ -616,9 +604,8 @@
 	list_for_each(item, &mc_devices) {
 		mci = list_entry(item, struct mem_ctl_info, link);
 
-		edac_mc_workq_setup(mci, value, false);
+		edac_mod_work(&mci->work, value);
 	}
-
 	mutex_unlock(&mem_ctls_mutex);
 }
 
@@ -789,7 +776,7 @@
 		/* This instance is NOW RUNNING */
 		mci->op_state = OP_RUNNING_POLL;
 
-		edac_mc_workq_setup(mci, edac_mc_get_poll_msec(), true);
+		edac_mc_workq_setup(mci, edac_mc_get_poll_msec());
 	} else {
 		mci->op_state = OP_RUNNING_INTERRUPT;
 	}
diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c
index a75acea..26e65ab 100644
--- a/drivers/edac/edac_mc_sysfs.c
+++ b/drivers/edac/edac_mc_sysfs.c
@@ -880,21 +880,26 @@
 int edac_create_sysfs_mci_device(struct mem_ctl_info *mci,
 				 const struct attribute_group **groups)
 {
+	char *name;
 	int i, err;
 
 	/*
 	 * The memory controller needs its own bus, in order to avoid
 	 * namespace conflicts at /sys/bus/edac.
 	 */
-	mci->bus->name = kasprintf(GFP_KERNEL, "mc%d", mci->mc_idx);
-	if (!mci->bus->name)
+	name = kasprintf(GFP_KERNEL, "mc%d", mci->mc_idx);
+	if (!name)
 		return -ENOMEM;
 
+	mci->bus->name = name;
+
 	edac_dbg(0, "creating bus %s\n", mci->bus->name);
 
 	err = bus_register(mci->bus);
-	if (err < 0)
-		goto fail_free_name;
+	if (err < 0) {
+		kfree(name);
+		return err;
+	}
 
 	/* get the /sys/devices/system/edac subsys reference */
 	mci->dev.type = &mci_attr_type;
@@ -961,8 +966,8 @@
 	device_unregister(&mci->dev);
 fail_unregister_bus:
 	bus_unregister(mci->bus);
-fail_free_name:
-	kfree(mci->bus->name);
+	kfree(name);
+
 	return err;
 }
 
@@ -993,10 +998,12 @@
 
 void edac_unregister_sysfs(struct mem_ctl_info *mci)
 {
+	const char *name = mci->bus->name;
+
 	edac_dbg(1, "Unregistering device %s\n", dev_name(&mci->dev));
 	device_unregister(&mci->dev);
 	bus_unregister(mci->bus);
-	kfree(mci->bus->name);
+	kfree(name);
 }
 
 static void mc_attr_release(struct device *dev)
@@ -1018,24 +1025,15 @@
  */
 int __init edac_mc_sysfs_init(void)
 {
-	struct bus_type *edac_subsys;
 	int err;
 
-	/* get the /sys/devices/system/edac subsys reference */
-	edac_subsys = edac_get_sysfs_subsys();
-	if (edac_subsys == NULL) {
-		edac_dbg(1, "no edac_subsys\n");
-		err = -EINVAL;
-		goto out;
-	}
-
 	mci_pdev = kzalloc(sizeof(*mci_pdev), GFP_KERNEL);
 	if (!mci_pdev) {
 		err = -ENOMEM;
-		goto out_put_sysfs;
+		goto out;
 	}
 
-	mci_pdev->bus = edac_subsys;
+	mci_pdev->bus = edac_get_sysfs_subsys();
 	mci_pdev->type = &mc_attr_type;
 	device_initialize(mci_pdev);
 	dev_set_name(mci_pdev, "mc");
@@ -1050,8 +1048,6 @@
 
  out_dev_free:
 	kfree(mci_pdev);
- out_put_sysfs:
-	edac_put_sysfs_subsys();
  out:
 	return err;
 }
@@ -1059,5 +1055,4 @@
 void edac_mc_sysfs_exit(void)
 {
 	device_unregister(mci_pdev);
-	edac_put_sysfs_subsys();
 }
diff --git a/drivers/edac/edac_module.c b/drivers/edac/edac_module.c
index 9cb082a..5f8543b 100644
--- a/drivers/edac/edac_module.c
+++ b/drivers/edac/edac_module.c
@@ -43,9 +43,6 @@
 MODULE_PARM_DESC(edac_debug_level, "EDAC debug level: [0-4], default: 2");
 #endif
 
-/* scope is to module level only */
-struct workqueue_struct *edac_workqueue;
-
 /*
  * edac_op_state_to_string()
  */
@@ -66,31 +63,37 @@
 }
 
 /*
- * edac_workqueue_setup
- *	initialize the edac work queue for polling operations
+ * sysfs object: /sys/devices/system/edac
+ *	need to export to other files
  */
-static int edac_workqueue_setup(void)
+static struct bus_type edac_subsys = {
+	.name = "edac",
+	.dev_name = "edac",
+};
+
+static int edac_subsys_init(void)
 {
-	edac_workqueue = create_singlethread_workqueue("edac-poller");
-	if (edac_workqueue == NULL)
-		return -ENODEV;
-	else
-		return 0;
+	int err;
+
+	/* create the /sys/devices/system/edac directory */
+	err = subsys_system_register(&edac_subsys, NULL);
+	if (err)
+		printk(KERN_ERR "Error registering toplevel EDAC sysfs dir\n");
+
+	return err;
 }
 
-/*
- * edac_workqueue_teardown
- *	teardown the edac workqueue
- */
-static void edac_workqueue_teardown(void)
+static void edac_subsys_exit(void)
 {
-	if (edac_workqueue) {
-		flush_workqueue(edac_workqueue);
-		destroy_workqueue(edac_workqueue);
-		edac_workqueue = NULL;
-	}
+	bus_unregister(&edac_subsys);
 }
 
+/* return pointer to the 'edac' node in sysfs */
+struct bus_type *edac_get_sysfs_subsys(void)
+{
+	return &edac_subsys;
+}
+EXPORT_SYMBOL_GPL(edac_get_sysfs_subsys);
 /*
  * edac_init
  *      module initialization entry point
@@ -101,6 +104,10 @@
 
 	edac_printk(KERN_INFO, EDAC_MC, EDAC_VERSION "\n");
 
+	err = edac_subsys_init();
+	if (err)
+		return err;
+
 	/*
 	 * Harvest and clear any boot/initialization PCI parity errors
 	 *
@@ -129,6 +136,8 @@
 	edac_mc_sysfs_exit();
 
 err_sysfs:
+	edac_subsys_exit();
+
 	return err;
 }
 
@@ -144,6 +153,7 @@
 	edac_workqueue_teardown();
 	edac_mc_sysfs_exit();
 	edac_debugfs_exit();
+	edac_subsys_exit();
 }
 
 /*
diff --git a/drivers/edac/edac_module.h b/drivers/edac/edac_module.h
index b95a48f..cfaacb9 100644
--- a/drivers/edac/edac_module.h
+++ b/drivers/edac/edac_module.h
@@ -47,10 +47,12 @@
 extern void edac_device_remove_sysfs(struct edac_device_ctl_info *edac_dev);
 
 /* edac core workqueue: single CPU mode */
-extern struct workqueue_struct *edac_workqueue;
-extern void edac_device_workq_setup(struct edac_device_ctl_info *edac_dev,
-				    unsigned msec);
-extern void edac_device_workq_teardown(struct edac_device_ctl_info *edac_dev);
+int edac_workqueue_setup(void);
+void edac_workqueue_teardown(void);
+bool edac_queue_work(struct delayed_work *work, unsigned long delay);
+bool edac_stop_work(struct delayed_work *work);
+bool edac_mod_work(struct delayed_work *work, unsigned long delay);
+
 extern void edac_device_reset_delay_period(struct edac_device_ctl_info
 					   *edac_dev, unsigned long value);
 extern void edac_mc_reset_delay_period(unsigned long value);
diff --git a/drivers/edac/edac_pci.c b/drivers/edac/edac_pci.c
index 2cf44b4d..9968538 100644
--- a/drivers/edac/edac_pci.c
+++ b/drivers/edac/edac_pci.c
@@ -178,41 +178,6 @@
 	INIT_LIST_HEAD(&pci->link);
 }
 
-#if 0
-/* Older code, but might use in the future */
-
-/*
- * edac_pci_find()
- * 	Search for an edac_pci_ctl_info structure whose index is 'idx'
- *
- * If found, return a pointer to the structure
- * Else return NULL.
- *
- * Caller must hold pci_ctls_mutex.
- */
-struct edac_pci_ctl_info *edac_pci_find(int idx)
-{
-	struct list_head *item;
-	struct edac_pci_ctl_info *pci;
-
-	/* Iterage over list, looking for exact match of ID */
-	list_for_each(item, &edac_pci_list) {
-		pci = list_entry(item, struct edac_pci_ctl_info, link);
-
-		if (pci->pci_idx >= idx) {
-			if (pci->pci_idx == idx)
-				return pci;
-
-			/* not on list, so terminate early */
-			break;
-		}
-	}
-
-	return NULL;
-}
-EXPORT_SYMBOL_GPL(edac_pci_find);
-#endif
-
 /*
  * edac_pci_workq_function()
  *
@@ -244,7 +209,7 @@
 			delay = msecs_to_jiffies(msec);
 
 		/* Reschedule only if we are in POLL mode */
-		queue_delayed_work(edac_workqueue, &pci->work, delay);
+		edac_queue_work(&pci->work, delay);
 	}
 
 	mutex_unlock(&edac_pci_ctls_mutex);
@@ -264,8 +229,8 @@
 	edac_dbg(0, "\n");
 
 	INIT_DELAYED_WORK(&pci->work, edac_pci_workq_function);
-	queue_delayed_work(edac_workqueue, &pci->work,
-			msecs_to_jiffies(edac_pci_get_poll_msec()));
+
+	edac_queue_work(&pci->work, msecs_to_jiffies(edac_pci_get_poll_msec()));
 }
 
 /*
@@ -274,39 +239,14 @@
  */
 static void edac_pci_workq_teardown(struct edac_pci_ctl_info *pci)
 {
-	int status;
-
 	edac_dbg(0, "\n");
 
-	status = cancel_delayed_work(&pci->work);
-	if (status == 0)
-		flush_workqueue(edac_workqueue);
+	pci->op_state = OP_OFFLINE;
+
+	edac_stop_work(&pci->work);
 }
 
 /*
- * edac_pci_reset_delay_period
- *
- *	called with a new period value for the workq period
- *	a) stop current workq timer
- *	b) restart workq timer with new value
- */
-void edac_pci_reset_delay_period(struct edac_pci_ctl_info *pci,
-				 unsigned long value)
-{
-	edac_dbg(0, "\n");
-
-	edac_pci_workq_teardown(pci);
-
-	/* need to lock for the setup */
-	mutex_lock(&edac_pci_ctls_mutex);
-
-	edac_pci_workq_setup(pci, value);
-
-	mutex_unlock(&edac_pci_ctls_mutex);
-}
-EXPORT_SYMBOL_GPL(edac_pci_reset_delay_period);
-
-/*
  * edac_pci_alloc_index: Allocate a unique PCI index number
  *
  * Return:
diff --git a/drivers/edac/edac_pci_sysfs.c b/drivers/edac/edac_pci_sysfs.c
index 24d877f..6e3428b 100644
--- a/drivers/edac/edac_pci_sysfs.c
+++ b/drivers/edac/edac_pci_sysfs.c
@@ -331,10 +331,7 @@
 };
 
 /**
- * edac_pci_main_kobj_setup()
- *
- *	setup the sysfs for EDAC PCI attributes
- *	assumes edac_subsys has already been initialized
+ * edac_pci_main_kobj_setup: Setup the sysfs for EDAC PCI attributes.
  */
 static int edac_pci_main_kobj_setup(void)
 {
@@ -351,11 +348,6 @@
 	 * controls and attributes
 	 */
 	edac_subsys = edac_get_sysfs_subsys();
-	if (edac_subsys == NULL) {
-		edac_dbg(1, "no edac_subsys\n");
-		err = -ENODEV;
-		goto decrement_count_fail;
-	}
 
 	/* Bump the reference count on this module to ensure the
 	 * modules isn't unloaded until we deconstruct the top
@@ -364,7 +356,7 @@
 	if (!try_module_get(THIS_MODULE)) {
 		edac_dbg(1, "try_module_get() failed\n");
 		err = -ENODEV;
-		goto mod_get_fail;
+		goto decrement_count_fail;
 	}
 
 	edac_pci_top_main_kobj = kzalloc(sizeof(struct kobject), GFP_KERNEL);
@@ -399,9 +391,6 @@
 kzalloc_fail:
 	module_put(THIS_MODULE);
 
-mod_get_fail:
-	edac_put_sysfs_subsys();
-
 decrement_count_fail:
 	/* if are on this error exit, nothing to tear down */
 	atomic_dec(&edac_pci_sysfs_refcount);
@@ -426,7 +415,6 @@
 	if (atomic_dec_return(&edac_pci_sysfs_refcount) == 0) {
 		edac_dbg(0, "called kobject_put on main kobj\n");
 		kobject_put(edac_pci_top_main_kobj);
-		edac_put_sysfs_subsys();
 	}
 }
 
diff --git a/drivers/edac/edac_stub.c b/drivers/edac/edac_stub.c
index ff07aae..952e411 100644
--- a/drivers/edac/edac_stub.c
+++ b/drivers/edac/edac_stub.c
@@ -26,8 +26,6 @@
 int edac_err_assert = 0;
 EXPORT_SYMBOL_GPL(edac_err_assert);
 
-static atomic_t edac_subsys_valid = ATOMIC_INIT(0);
-
 int edac_report_status = EDAC_REPORTING_ENABLED;
 EXPORT_SYMBOL_GPL(edac_report_status);
 
@@ -68,42 +66,3 @@
 	edac_err_assert++;
 }
 EXPORT_SYMBOL_GPL(edac_atomic_assert_error);
-
-/*
- * sysfs object: /sys/devices/system/edac
- *	need to export to other files
- */
-struct bus_type edac_subsys = {
-	.name = "edac",
-	.dev_name = "edac",
-};
-EXPORT_SYMBOL_GPL(edac_subsys);
-
-/* return pointer to the 'edac' node in sysfs */
-struct bus_type *edac_get_sysfs_subsys(void)
-{
-	int err = 0;
-
-	if (atomic_read(&edac_subsys_valid))
-		goto out;
-
-	/* create the /sys/devices/system/edac directory */
-	err = subsys_system_register(&edac_subsys, NULL);
-	if (err) {
-		printk(KERN_ERR "Error registering toplevel EDAC sysfs dir\n");
-		return NULL;
-	}
-
-out:
-	atomic_inc(&edac_subsys_valid);
-	return &edac_subsys;
-}
-EXPORT_SYMBOL_GPL(edac_get_sysfs_subsys);
-
-void edac_put_sysfs_subsys(void)
-{
-	/* last user unregisters it */
-	if (atomic_dec_and_test(&edac_subsys_valid))
-		bus_unregister(&edac_subsys);
-}
-EXPORT_SYMBOL_GPL(edac_put_sysfs_subsys);
diff --git a/drivers/edac/i5100_edac.c b/drivers/edac/i5100_edac.c
index 4091777..c655162 100644
--- a/drivers/edac/i5100_edac.c
+++ b/drivers/edac/i5100_edac.c
@@ -575,9 +575,7 @@
 
 static void i5100_refresh_scrubbing(struct work_struct *work)
 {
-	struct delayed_work *i5100_scrubbing = container_of(work,
-							    struct delayed_work,
-							    work);
+	struct delayed_work *i5100_scrubbing = to_delayed_work(work);
 	struct i5100_priv *priv = container_of(i5100_scrubbing,
 					       struct i5100_priv,
 					       i5100_scrubbing);
diff --git a/drivers/edac/mpc85xx_edac.c b/drivers/edac/mpc85xx_edac.c
index 23ef8e9..b7139c1 100644
--- a/drivers/edac/mpc85xx_edac.c
+++ b/drivers/edac/mpc85xx_edac.c
@@ -20,6 +20,7 @@
 #include <linux/edac.h>
 #include <linux/smp.h>
 #include <linux/gfp.h>
+#include <linux/fsl/edac.h>
 
 #include <linux/of_platform.h>
 #include <linux/of_device.h>
@@ -238,10 +239,12 @@
 	return IRQ_HANDLED;
 }
 
-int mpc85xx_pci_err_probe(struct platform_device *op)
+static int mpc85xx_pci_err_probe(struct platform_device *op)
 {
 	struct edac_pci_ctl_info *pci;
 	struct mpc85xx_pci_pdata *pdata;
+	struct mpc85xx_edac_pci_plat_data *plat_data;
+	struct device_node *of_node;
 	struct resource r;
 	int res = 0;
 
@@ -266,7 +269,15 @@
 	pdata->name = "mpc85xx_pci_err";
 	pdata->irq = NO_IRQ;
 
-	if (mpc85xx_pcie_find_capability(op->dev.of_node) > 0)
+	plat_data = op->dev.platform_data;
+	if (!plat_data) {
+		dev_err(&op->dev, "no platform data");
+		res = -ENXIO;
+		goto err;
+	}
+	of_node = plat_data->of_node;
+
+	if (mpc85xx_pcie_find_capability(of_node) > 0)
 		pdata->is_pcie = true;
 
 	dev_set_drvdata(&op->dev, pci);
@@ -284,7 +295,7 @@
 
 	pdata->edac_idx = edac_pci_idx++;
 
-	res = of_address_to_resource(op->dev.of_node, 0, &r);
+	res = of_address_to_resource(of_node, 0, &r);
 	if (res) {
 		printk(KERN_ERR "%s: Unable to get resource for "
 		       "PCI err regs\n", __func__);
@@ -339,7 +350,7 @@
 	}
 
 	if (edac_op_state == EDAC_OPSTATE_INT) {
-		pdata->irq = irq_of_parse_and_map(op->dev.of_node, 0);
+		pdata->irq = irq_of_parse_and_map(of_node, 0);
 		res = devm_request_irq(&op->dev, pdata->irq,
 				       mpc85xx_pci_isr,
 				       IRQF_SHARED,
@@ -386,8 +397,22 @@
 	devres_release_group(&op->dev, mpc85xx_pci_err_probe);
 	return res;
 }
-EXPORT_SYMBOL(mpc85xx_pci_err_probe);
 
+static const struct platform_device_id mpc85xx_pci_err_match[] = {
+	{
+		.name = "mpc85xx-pci-edac"
+	},
+	{}
+};
+
+static struct platform_driver mpc85xx_pci_err_driver = {
+	.probe = mpc85xx_pci_err_probe,
+	.id_table = mpc85xx_pci_err_match,
+	.driver = {
+		.name = "mpc85xx_pci_err",
+		.suppress_bind_attrs = true,
+	},
+};
 #endif				/* CONFIG_PCI */
 
 /**************************** L2 Err device ***************************/
@@ -1208,6 +1233,14 @@
 }
 #endif
 
+static struct platform_driver * const drivers[] = {
+	&mpc85xx_mc_err_driver,
+	&mpc85xx_l2_err_driver,
+#ifdef CONFIG_PCI
+	&mpc85xx_pci_err_driver,
+#endif
+};
+
 static int __init mpc85xx_mc_init(void)
 {
 	int res = 0;
@@ -1226,13 +1259,9 @@
 		break;
 	}
 
-	res = platform_driver_register(&mpc85xx_mc_err_driver);
+	res = platform_register_drivers(drivers, ARRAY_SIZE(drivers));
 	if (res)
-		printk(KERN_WARNING EDAC_MOD_STR "MC fails to register\n");
-
-	res = platform_driver_register(&mpc85xx_l2_err_driver);
-	if (res)
-		printk(KERN_WARNING EDAC_MOD_STR "L2 fails to register\n");
+		printk(KERN_WARNING EDAC_MOD_STR "drivers fail to register\n");
 
 #ifdef CONFIG_FSL_SOC_BOOKE
 	pvr = mfspr(SPRN_PVR);
@@ -1270,8 +1299,7 @@
 		on_each_cpu(mpc85xx_mc_restore_hid1, NULL, 0);
 	}
 #endif
-	platform_driver_unregister(&mpc85xx_l2_err_driver);
-	platform_driver_unregister(&mpc85xx_mc_err_driver);
+	platform_unregister_drivers(drivers, ARRAY_SIZE(drivers));
 }
 
 module_exit(mpc85xx_mc_exit);
diff --git a/drivers/edac/mv64x60_edac.c b/drivers/edac/mv64x60_edac.c
index 0574e1b..6c54127 100644
--- a/drivers/edac/mv64x60_edac.c
+++ b/drivers/edac/mv64x60_edac.c
@@ -847,6 +847,15 @@
 	}
 };
 
+static struct platform_driver * const drivers[] = {
+	&mv64x60_mc_err_driver,
+	&mv64x60_cpu_err_driver,
+	&mv64x60_sram_err_driver,
+#ifdef CONFIG_PCI
+	&mv64x60_pci_err_driver,
+#endif
+};
+
 static int __init mv64x60_edac_init(void)
 {
 	int ret = 0;
@@ -863,39 +872,13 @@
 		break;
 	}
 
-	ret = platform_driver_register(&mv64x60_mc_err_driver);
-	if (ret)
-		printk(KERN_WARNING EDAC_MOD_STR "MC err failed to register\n");
-
-	ret = platform_driver_register(&mv64x60_cpu_err_driver);
-	if (ret)
-		printk(KERN_WARNING EDAC_MOD_STR
-			"CPU err failed to register\n");
-
-	ret = platform_driver_register(&mv64x60_sram_err_driver);
-	if (ret)
-		printk(KERN_WARNING EDAC_MOD_STR
-			"SRAM err failed to register\n");
-
-#ifdef CONFIG_PCI
-	ret = platform_driver_register(&mv64x60_pci_err_driver);
-	if (ret)
-		printk(KERN_WARNING EDAC_MOD_STR
-			"PCI err failed to register\n");
-#endif
-
-	return ret;
+	return platform_register_drivers(drivers, ARRAY_SIZE(drivers));
 }
 module_init(mv64x60_edac_init);
 
 static void __exit mv64x60_edac_exit(void)
 {
-#ifdef CONFIG_PCI
-	platform_driver_unregister(&mv64x60_pci_err_driver);
-#endif
-	platform_driver_unregister(&mv64x60_sram_err_driver);
-	platform_driver_unregister(&mv64x60_cpu_err_driver);
-	platform_driver_unregister(&mv64x60_mc_err_driver);
+	platform_unregister_drivers(drivers, ARRAY_SIZE(drivers));
 }
 module_exit(mv64x60_edac_exit);
 
diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index 429309c..e438ee5 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -65,15 +65,20 @@
 	0xd8, 0xe0, 0xe8, 0xf0, 0xf8,
 };
 
-#define SAD_LIMIT(reg)		((GET_BITFIELD(reg, 6, 25) << 26) | 0x3ffffff)
-#define DRAM_ATTR(reg)		GET_BITFIELD(reg, 2,  3)
-#define INTERLEAVE_MODE(reg)	GET_BITFIELD(reg, 1,  1)
+static const u32 knl_dram_rule[] = {
+	0x60, 0x68, 0x70, 0x78, 0x80, /* 0-4 */
+	0x88, 0x90, 0x98, 0xa0, 0xa8, /* 5-9 */
+	0xb0, 0xb8, 0xc0, 0xc8, 0xd0, /* 10-14 */
+	0xd8, 0xe0, 0xe8, 0xf0, 0xf8, /* 15-19 */
+	0x100, 0x108, 0x110, 0x118,   /* 20-23 */
+};
+
 #define DRAM_RULE_ENABLE(reg)	GET_BITFIELD(reg, 0,  0)
 #define A7MODE(reg)		GET_BITFIELD(reg, 26, 26)
 
-static char *get_dram_attr(u32 reg)
+static char *show_dram_attr(u32 attr)
 {
-	switch(DRAM_ATTR(reg)) {
+	switch (attr) {
 		case 0:
 			return "DRAM";
 		case 1:
@@ -97,6 +102,14 @@
 	0xdc, 0xe4, 0xec, 0xf4, 0xfc,
 };
 
+static const u32 knl_interleave_list[] = {
+	0x64, 0x6c, 0x74, 0x7c, 0x84, /* 0-4 */
+	0x8c, 0x94, 0x9c, 0xa4, 0xac, /* 5-9 */
+	0xb4, 0xbc, 0xc4, 0xcc, 0xd4, /* 10-14 */
+	0xdc, 0xe4, 0xec, 0xf4, 0xfc, /* 15-19 */
+	0x104, 0x10c, 0x114, 0x11c,   /* 20-23 */
+};
+
 struct interleave_pkg {
 	unsigned char start;
 	unsigned char end;
@@ -134,10 +147,13 @@
 /* Devices 12 Function 7 */
 
 #define TOLM		0x80
-#define	TOHM		0x84
+#define TOHM		0x84
 #define HASWELL_TOLM	0xd0
 #define HASWELL_TOHM_0	0xd4
 #define HASWELL_TOHM_1	0xd8
+#define KNL_TOLM	0xd0
+#define KNL_TOHM_0	0xd4
+#define KNL_TOHM_1	0xd8
 
 #define GET_TOLM(reg)		((GET_BITFIELD(reg, 0,  3) << 28) | 0x3ffffff)
 #define GET_TOHM(reg)		((GET_BITFIELD(reg, 0, 20) << 25) | 0x3ffffff)
@@ -148,6 +164,8 @@
 
 #define SOURCE_ID(reg)		GET_BITFIELD(reg, 9, 11)
 
+#define SOURCE_ID_KNL(reg)	GET_BITFIELD(reg, 12, 14)
+
 #define SAD_CONTROL	0xf4
 
 /* Device 14 function 0 */
@@ -170,6 +188,7 @@
 /* Device 15, function 0 */
 
 #define MCMTR			0x7c
+#define KNL_MCMTR		0x624
 
 #define IS_ECC_ENABLED(mcmtr)		GET_BITFIELD(mcmtr, 2, 2)
 #define IS_LOCKSTEP_ENABLED(mcmtr)	GET_BITFIELD(mcmtr, 1, 1)
@@ -186,6 +205,8 @@
 	0x80, 0x84, 0x88,
 };
 
+static const int knl_mtr_reg = 0xb60;
+
 #define RANK_DISABLE(mtr)		GET_BITFIELD(mtr, 16, 19)
 #define IS_DIMM_PRESENT(mtr)		GET_BITFIELD(mtr, 14, 14)
 #define RANK_CNT_BITS(mtr)		GET_BITFIELD(mtr, 12, 13)
@@ -256,6 +277,9 @@
 
 #define NUM_CHANNELS		8	/* 2MC per socket, four chan per MC */
 #define MAX_DIMMS		3	/* Max DIMMS per channel */
+#define KNL_MAX_CHAS		38	/* KNL max num. of Cache Home Agents */
+#define KNL_MAX_CHANNELS	6	/* KNL max num. of PCI channels */
+#define KNL_MAX_EDCS		8	/* Embedded DRAM controllers */
 #define CHANNEL_UNSPECIFIED	0xf	/* Intel IA32 SDM 15-14 */
 
 enum type {
@@ -263,6 +287,7 @@
 	IVY_BRIDGE,
 	HASWELL,
 	BROADWELL,
+	KNIGHTS_LANDING,
 };
 
 struct sbridge_pvt;
@@ -273,6 +298,10 @@
 	u64		(*get_tolm)(struct sbridge_pvt *pvt);
 	u64		(*get_tohm)(struct sbridge_pvt *pvt);
 	u64		(*rir_limit)(u32 reg);
+	u64		(*sad_limit)(u32 reg);
+	u32		(*interleave_mode)(u32 reg);
+	char*		(*show_interleave_mode)(u32 reg);
+	u32		(*dram_attr)(u32 reg);
 	const u32	*dram_rule;
 	const u32	*interleave_list;
 	const struct interleave_pkg *interleave_pkg;
@@ -308,6 +337,16 @@
 	struct mem_ctl_info	*mci;
 };
 
+struct knl_pvt {
+	struct pci_dev          *pci_cha[KNL_MAX_CHAS];
+	struct pci_dev          *pci_channel[KNL_MAX_CHANNELS];
+	struct pci_dev          *pci_mc0;
+	struct pci_dev          *pci_mc1;
+	struct pci_dev          *pci_mc0_misc;
+	struct pci_dev          *pci_mc1_misc;
+	struct pci_dev          *pci_mc_info; /* tolm, tohm */
+};
+
 struct sbridge_pvt {
 	struct pci_dev		*pci_ta, *pci_ddrio, *pci_ras;
 	struct pci_dev		*pci_sad0, *pci_sad1;
@@ -336,6 +375,7 @@
 
 	/* Memory description */
 	u64			tolm, tohm;
+	struct knl_pvt knl;
 };
 
 #define PCI_DESCR(device_id, opt)	\
@@ -509,6 +549,50 @@
 	{0,}			/* 0 terminated list. */
 };
 
+/* Knight's Landing Support */
+/*
+ * KNL's memory channels are swizzled between memory controllers.
+ * MC0 is mapped to CH3,5,6 and MC1 is mapped to CH0,1,2
+ */
+#define knl_channel_remap(channel) ((channel + 3) % 6)
+
+/* Memory controller, TAD tables, error injection - 2-8-0, 2-9-0 (2 of these) */
+#define PCI_DEVICE_ID_INTEL_KNL_IMC_MC       0x7840
+/* DRAM channel stuff; bank addrs, dimmmtr, etc.. 2-8-2 - 2-9-4 (6 of these) */
+#define PCI_DEVICE_ID_INTEL_KNL_IMC_CHANNEL  0x7843
+/* kdrwdbu TAD limits/offsets, MCMTR - 2-10-1, 2-11-1 (2 of these) */
+#define PCI_DEVICE_ID_INTEL_KNL_IMC_TA       0x7844
+/* CHA broadcast registers, dram rules - 1-29-0 (1 of these) */
+#define PCI_DEVICE_ID_INTEL_KNL_IMC_SAD0     0x782a
+/* SAD target - 1-29-1 (1 of these) */
+#define PCI_DEVICE_ID_INTEL_KNL_IMC_SAD1     0x782b
+/* Caching / Home Agent */
+#define PCI_DEVICE_ID_INTEL_KNL_IMC_CHA      0x782c
+/* Device with TOLM and TOHM, 0-5-0 (1 of these) */
+#define PCI_DEVICE_ID_INTEL_KNL_IMC_TOLHM    0x7810
+
+/*
+ * KNL differs from SB, IB, and Haswell in that it has multiple
+ * instances of the same device with the same device ID, so we handle that
+ * by creating as many copies in the table as we expect to find.
+ * (Like device ID must be grouped together.)
+ */
+
+static const struct pci_id_descr pci_dev_descr_knl[] = {
+	[0]         = { PCI_DESCR(PCI_DEVICE_ID_INTEL_KNL_IMC_SAD0, 0) },
+	[1]         = { PCI_DESCR(PCI_DEVICE_ID_INTEL_KNL_IMC_SAD1, 0) },
+	[2 ... 3]   = { PCI_DESCR(PCI_DEVICE_ID_INTEL_KNL_IMC_MC, 0)},
+	[4 ... 41]  = { PCI_DESCR(PCI_DEVICE_ID_INTEL_KNL_IMC_CHA, 0) },
+	[42 ... 47] = { PCI_DESCR(PCI_DEVICE_ID_INTEL_KNL_IMC_CHANNEL, 0) },
+	[48]        = { PCI_DESCR(PCI_DEVICE_ID_INTEL_KNL_IMC_TA, 0) },
+	[49]        = { PCI_DESCR(PCI_DEVICE_ID_INTEL_KNL_IMC_TOLHM, 0) },
+};
+
+static const struct pci_id_table pci_dev_descr_knl_table[] = {
+	PCI_ID_TABLE_ENTRY(pci_dev_descr_knl),
+	{0,}
+};
+
 /*
  * Broadwell support
  *
@@ -585,6 +669,7 @@
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TA)},
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0)},
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0)},
+	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KNL_IMC_SAD0)},
 	{0,}			/* 0 terminated list. */
 };
 
@@ -598,7 +683,7 @@
 	int ranks = (1 << RANK_CNT_BITS(mtr));
 	int max = 4;
 
-	if (type == HASWELL || type == BROADWELL)
+	if (type == HASWELL || type == BROADWELL || type == KNIGHTS_LANDING)
 		max = 8;
 
 	if (ranks > max) {
@@ -636,10 +721,19 @@
 	return 1 << cols;
 }
 
-static struct sbridge_dev *get_sbridge_dev(u8 bus)
+static struct sbridge_dev *get_sbridge_dev(u8 bus, int multi_bus)
 {
 	struct sbridge_dev *sbridge_dev;
 
+	/*
+	 * If we have devices scattered across several busses that pertain
+	 * to the same memory controller, we'll lump them all together.
+	 */
+	if (multi_bus) {
+		return list_first_entry_or_null(&sbridge_edac_list,
+				struct sbridge_dev, list);
+	}
+
 	list_for_each_entry(sbridge_dev, &sbridge_edac_list, list) {
 		if (sbridge_dev->bus == bus)
 			return sbridge_dev;
@@ -718,6 +812,67 @@
 	return ((u64)GET_BITFIELD(reg,  1, 10) << 29) | 0x1fffffff;
 }
 
+static u64 sad_limit(u32 reg)
+{
+	return (GET_BITFIELD(reg, 6, 25) << 26) | 0x3ffffff;
+}
+
+static u32 interleave_mode(u32 reg)
+{
+	return GET_BITFIELD(reg, 1, 1);
+}
+
+char *show_interleave_mode(u32 reg)
+{
+	return interleave_mode(reg) ? "8:6" : "[8:6]XOR[18:16]";
+}
+
+static u32 dram_attr(u32 reg)
+{
+	return GET_BITFIELD(reg, 2, 3);
+}
+
+static u64 knl_sad_limit(u32 reg)
+{
+	return (GET_BITFIELD(reg, 7, 26) << 26) | 0x3ffffff;
+}
+
+static u32 knl_interleave_mode(u32 reg)
+{
+	return GET_BITFIELD(reg, 1, 2);
+}
+
+static char *knl_show_interleave_mode(u32 reg)
+{
+	char *s;
+
+	switch (knl_interleave_mode(reg)) {
+	case 0:
+		s = "use address bits [8:6]";
+		break;
+	case 1:
+		s = "use address bits [10:8]";
+		break;
+	case 2:
+		s = "use address bits [14:12]";
+		break;
+	case 3:
+		s = "use address bits [32:30]";
+		break;
+	default:
+		WARN_ON(1);
+		break;
+	}
+
+	return s;
+}
+
+static u32 dram_attr_knl(u32 reg)
+{
+	return GET_BITFIELD(reg, 3, 4);
+}
+
+
 static enum mem_type get_memory_type(struct sbridge_pvt *pvt)
 {
 	u32 reg;
@@ -769,6 +924,12 @@
 	return mtype;
 }
 
+static enum dev_type knl_get_width(struct sbridge_pvt *pvt, u32 mtr)
+{
+	/* for KNL value is fixed */
+	return DEV_X16;
+}
+
 static enum dev_type sbridge_get_width(struct sbridge_pvt *pvt, u32 mtr)
 {
 	/* there's no way to figure out */
@@ -812,6 +973,12 @@
 	return __ibridge_get_width(GET_BITFIELD(mtr, 8, 9));
 }
 
+static enum mem_type knl_get_memory_type(struct sbridge_pvt *pvt)
+{
+	/* DDR4 RDIMMS and LRDIMMS are supported */
+	return MEM_RDDR4;
+}
+
 static u8 get_node_id(struct sbridge_pvt *pvt)
 {
 	u32 reg;
@@ -827,6 +994,15 @@
 	return GET_BITFIELD(reg, 0, 3);
 }
 
+static u8 knl_get_node_id(struct sbridge_pvt *pvt)
+{
+	u32 reg;
+
+	pci_read_config_dword(pvt->pci_sad1, SAD_CONTROL, &reg);
+	return GET_BITFIELD(reg, 0, 2);
+}
+
+
 static u64 haswell_get_tolm(struct sbridge_pvt *pvt)
 {
 	u32 reg;
@@ -848,6 +1024,26 @@
 	return rc | 0x1ffffff;
 }
 
+static u64 knl_get_tolm(struct sbridge_pvt *pvt)
+{
+	u32 reg;
+
+	pci_read_config_dword(pvt->knl.pci_mc_info, KNL_TOLM, &reg);
+	return (GET_BITFIELD(reg, 26, 31) << 26) | 0x3ffffff;
+}
+
+static u64 knl_get_tohm(struct sbridge_pvt *pvt)
+{
+	u64 rc;
+	u32 reg_lo, reg_hi;
+
+	pci_read_config_dword(pvt->knl.pci_mc_info, KNL_TOHM_0, &reg_lo);
+	pci_read_config_dword(pvt->knl.pci_mc_info, KNL_TOHM_1, &reg_hi);
+	rc = ((u64)reg_hi << 32) | reg_lo;
+	return rc | 0x3ffffff;
+}
+
+
 static u64 haswell_rir_limit(u32 reg)
 {
 	return (((u64)GET_BITFIELD(reg,  1, 11) + 1) << 29) - 1;
@@ -905,11 +1101,22 @@
 	case BROADWELL:
 		id = PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TA;
 		break;
+	case KNIGHTS_LANDING:
+		/*
+		 * KNL doesn't group things by bus the same way
+		 * SB/IB/Haswell does.
+		 */
+		id = PCI_DEVICE_ID_INTEL_KNL_IMC_TA;
+		break;
 	default:
 		return -ENODEV;
 	}
 
-	pdev = get_pdev_same_bus(bus, id);
+	if (type != KNIGHTS_LANDING)
+		pdev = get_pdev_same_bus(bus, id);
+	else
+		pdev = pci_get_device(PCI_VENDOR_ID_INTEL, id, 0);
+
 	if (!pdev) {
 		sbridge_printk(KERN_ERR, "Couldn't find PCI device "
 					"%04x:%04x! on bus %02d\n",
@@ -917,7 +1124,8 @@
 		return -ENODEV;
 	}
 
-	pci_read_config_dword(pdev, MCMTR, &mcmtr);
+	pci_read_config_dword(pdev,
+			type == KNIGHTS_LANDING ? KNL_MCMTR : MCMTR, &mcmtr);
 	if (!IS_ECC_ENABLED(mcmtr)) {
 		sbridge_printk(KERN_ERR, "ECC is disabled. Aborting\n");
 		return -ENODEV;
@@ -925,6 +1133,476 @@
 	return 0;
 }
 
+/* Low bits of TAD limit, and some metadata. */
+static const u32 knl_tad_dram_limit_lo[] = {
+	0x400, 0x500, 0x600, 0x700,
+	0x800, 0x900, 0xa00, 0xb00,
+};
+
+/* Low bits of TAD offset. */
+static const u32 knl_tad_dram_offset_lo[] = {
+	0x404, 0x504, 0x604, 0x704,
+	0x804, 0x904, 0xa04, 0xb04,
+};
+
+/* High 16 bits of TAD limit and offset. */
+static const u32 knl_tad_dram_hi[] = {
+	0x408, 0x508, 0x608, 0x708,
+	0x808, 0x908, 0xa08, 0xb08,
+};
+
+/* Number of ways a tad entry is interleaved. */
+static const u32 knl_tad_ways[] = {
+	8, 6, 4, 3, 2, 1,
+};
+
+/*
+ * Retrieve the n'th Target Address Decode table entry
+ * from the memory controller's TAD table.
+ *
+ * @pvt:	driver private data
+ * @entry:	which entry you want to retrieve
+ * @mc:		which memory controller (0 or 1)
+ * @offset:	output tad range offset
+ * @limit:	output address of first byte above tad range
+ * @ways:	output number of interleave ways
+ *
+ * The offset value has curious semantics.  It's a sort of running total
+ * of the sizes of all the memory regions that aren't mapped in this
+ * tad table.
+ */
+static int knl_get_tad(const struct sbridge_pvt *pvt,
+		const int entry,
+		const int mc,
+		u64 *offset,
+		u64 *limit,
+		int *ways)
+{
+	u32 reg_limit_lo, reg_offset_lo, reg_hi;
+	struct pci_dev *pci_mc;
+	int way_id;
+
+	switch (mc) {
+	case 0:
+		pci_mc = pvt->knl.pci_mc0;
+		break;
+	case 1:
+		pci_mc = pvt->knl.pci_mc1;
+		break;
+	default:
+		WARN_ON(1);
+		return -EINVAL;
+	}
+
+	pci_read_config_dword(pci_mc,
+			knl_tad_dram_limit_lo[entry], &reg_limit_lo);
+	pci_read_config_dword(pci_mc,
+			knl_tad_dram_offset_lo[entry], &reg_offset_lo);
+	pci_read_config_dword(pci_mc,
+			knl_tad_dram_hi[entry], &reg_hi);
+
+	/* Is this TAD entry enabled? */
+	if (!GET_BITFIELD(reg_limit_lo, 0, 0))
+		return -ENODEV;
+
+	way_id = GET_BITFIELD(reg_limit_lo, 3, 5);
+
+	if (way_id < ARRAY_SIZE(knl_tad_ways)) {
+		*ways = knl_tad_ways[way_id];
+	} else {
+		*ways = 0;
+		sbridge_printk(KERN_ERR,
+				"Unexpected value %d in mc_tad_limit_lo wayness field\n",
+				way_id);
+		return -ENODEV;
+	}
+
+	/*
+	 * The least significant 6 bits of base and limit are truncated.
+	 * For limit, we fill the missing bits with 1s.
+	 */
+	*offset = ((u64) GET_BITFIELD(reg_offset_lo, 6, 31) << 6) |
+				((u64) GET_BITFIELD(reg_hi, 0,  15) << 32);
+	*limit = ((u64) GET_BITFIELD(reg_limit_lo,  6, 31) << 6) | 63 |
+				((u64) GET_BITFIELD(reg_hi, 16, 31) << 32);
+
+	return 0;
+}
+
+/* Determine which memory controller is responsible for a given channel. */
+static int knl_channel_mc(int channel)
+{
+	WARN_ON(channel < 0 || channel >= 6);
+
+	return channel < 3 ? 1 : 0;
+}
+
+/*
+ * Get the Nth entry from EDC_ROUTE_TABLE register.
+ * (This is the per-tile mapping of logical interleave targets to
+ *  physical EDC modules.)
+ *
+ * entry 0: 0:2
+ *       1: 3:5
+ *       2: 6:8
+ *       3: 9:11
+ *       4: 12:14
+ *       5: 15:17
+ *       6: 18:20
+ *       7: 21:23
+ * reserved: 24:31
+ */
+static u32 knl_get_edc_route(int entry, u32 reg)
+{
+	WARN_ON(entry >= KNL_MAX_EDCS);
+	return GET_BITFIELD(reg, entry*3, (entry*3)+2);
+}
+
+/*
+ * Get the Nth entry from MC_ROUTE_TABLE register.
+ * (This is the per-tile mapping of logical interleave targets to
+ *  physical DRAM channels modules.)
+ *
+ * entry 0: mc 0:2   channel 18:19
+ *       1: mc 3:5   channel 20:21
+ *       2: mc 6:8   channel 22:23
+ *       3: mc 9:11  channel 24:25
+ *       4: mc 12:14 channel 26:27
+ *       5: mc 15:17 channel 28:29
+ * reserved: 30:31
+ *
+ * Though we have 3 bits to identify the MC, we should only see
+ * the values 0 or 1.
+ */
+
+static u32 knl_get_mc_route(int entry, u32 reg)
+{
+	int mc, chan;
+
+	WARN_ON(entry >= KNL_MAX_CHANNELS);
+
+	mc = GET_BITFIELD(reg, entry*3, (entry*3)+2);
+	chan = GET_BITFIELD(reg, (entry*2) + 18, (entry*2) + 18 + 1);
+
+	return knl_channel_remap(mc*3 + chan);
+}
+
+/*
+ * Render the EDC_ROUTE register in human-readable form.
+ * Output string s should be at least KNL_MAX_EDCS*2 bytes.
+ */
+static void knl_show_edc_route(u32 reg, char *s)
+{
+	int i;
+
+	for (i = 0; i < KNL_MAX_EDCS; i++) {
+		s[i*2] = knl_get_edc_route(i, reg) + '0';
+		s[i*2+1] = '-';
+	}
+
+	s[KNL_MAX_EDCS*2 - 1] = '\0';
+}
+
+/*
+ * Render the MC_ROUTE register in human-readable form.
+ * Output string s should be at least KNL_MAX_CHANNELS*2 bytes.
+ */
+static void knl_show_mc_route(u32 reg, char *s)
+{
+	int i;
+
+	for (i = 0; i < KNL_MAX_CHANNELS; i++) {
+		s[i*2] = knl_get_mc_route(i, reg) + '0';
+		s[i*2+1] = '-';
+	}
+
+	s[KNL_MAX_CHANNELS*2 - 1] = '\0';
+}
+
+#define KNL_EDC_ROUTE 0xb8
+#define KNL_MC_ROUTE 0xb4
+
+/* Is this dram rule backed by regular DRAM in flat mode? */
+#define KNL_EDRAM(reg) GET_BITFIELD(reg, 29, 29)
+
+/* Is this dram rule cached? */
+#define KNL_CACHEABLE(reg) GET_BITFIELD(reg, 28, 28)
+
+/* Is this rule backed by edc ? */
+#define KNL_EDRAM_ONLY(reg) GET_BITFIELD(reg, 29, 29)
+
+/* Is this rule backed by DRAM, cacheable in EDRAM? */
+#define KNL_CACHEABLE(reg) GET_BITFIELD(reg, 28, 28)
+
+/* Is this rule mod3? */
+#define KNL_MOD3(reg) GET_BITFIELD(reg, 27, 27)
+
+/*
+ * Figure out how big our RAM modules are.
+ *
+ * The DIMMMTR register in KNL doesn't tell us the size of the DIMMs, so we
+ * have to figure this out from the SAD rules, interleave lists, route tables,
+ * and TAD rules.
+ *
+ * SAD rules can have holes in them (e.g. the 3G-4G hole), so we have to
+ * inspect the TAD rules to figure out how large the SAD regions really are.
+ *
+ * When we know the real size of a SAD region and how many ways it's
+ * interleaved, we know the individual contribution of each channel to
+ * TAD is size/ways.
+ *
+ * Finally, we have to check whether each channel participates in each SAD
+ * region.
+ *
+ * Fortunately, KNL only supports one DIMM per channel, so once we know how
+ * much memory the channel uses, we know the DIMM is at least that large.
+ * (The BIOS might possibly choose not to map all available memory, in which
+ * case we will underreport the size of the DIMM.)
+ *
+ * In theory, we could try to determine the EDC sizes as well, but that would
+ * only work in flat mode, not in cache mode.
+ *
+ * @mc_sizes: Output sizes of channels (must have space for KNL_MAX_CHANNELS
+ *            elements)
+ */
+static int knl_get_dimm_capacity(struct sbridge_pvt *pvt, u64 *mc_sizes)
+{
+	u64 sad_base, sad_size, sad_limit = 0;
+	u64 tad_base, tad_size, tad_limit, tad_deadspace, tad_livespace;
+	int sad_rule = 0;
+	int tad_rule = 0;
+	int intrlv_ways, tad_ways;
+	u32 first_pkg, pkg;
+	int i;
+	u64 sad_actual_size[2]; /* sad size accounting for holes, per mc */
+	u32 dram_rule, interleave_reg;
+	u32 mc_route_reg[KNL_MAX_CHAS];
+	u32 edc_route_reg[KNL_MAX_CHAS];
+	int edram_only;
+	char edc_route_string[KNL_MAX_EDCS*2];
+	char mc_route_string[KNL_MAX_CHANNELS*2];
+	int cur_reg_start;
+	int mc;
+	int channel;
+	int way;
+	int participants[KNL_MAX_CHANNELS];
+	int participant_count = 0;
+
+	for (i = 0; i < KNL_MAX_CHANNELS; i++)
+		mc_sizes[i] = 0;
+
+	/* Read the EDC route table in each CHA. */
+	cur_reg_start = 0;
+	for (i = 0; i < KNL_MAX_CHAS; i++) {
+		pci_read_config_dword(pvt->knl.pci_cha[i],
+				KNL_EDC_ROUTE, &edc_route_reg[i]);
+
+		if (i > 0 && edc_route_reg[i] != edc_route_reg[i-1]) {
+			knl_show_edc_route(edc_route_reg[i-1],
+					edc_route_string);
+			if (cur_reg_start == i-1)
+				edac_dbg(0, "edc route table for CHA %d: %s\n",
+					cur_reg_start, edc_route_string);
+			else
+				edac_dbg(0, "edc route table for CHA %d-%d: %s\n",
+					cur_reg_start, i-1, edc_route_string);
+			cur_reg_start = i;
+		}
+	}
+	knl_show_edc_route(edc_route_reg[i-1], edc_route_string);
+	if (cur_reg_start == i-1)
+		edac_dbg(0, "edc route table for CHA %d: %s\n",
+			cur_reg_start, edc_route_string);
+	else
+		edac_dbg(0, "edc route table for CHA %d-%d: %s\n",
+			cur_reg_start, i-1, edc_route_string);
+
+	/* Read the MC route table in each CHA. */
+	cur_reg_start = 0;
+	for (i = 0; i < KNL_MAX_CHAS; i++) {
+		pci_read_config_dword(pvt->knl.pci_cha[i],
+			KNL_MC_ROUTE, &mc_route_reg[i]);
+
+		if (i > 0 && mc_route_reg[i] != mc_route_reg[i-1]) {
+			knl_show_mc_route(mc_route_reg[i-1], mc_route_string);
+			if (cur_reg_start == i-1)
+				edac_dbg(0, "mc route table for CHA %d: %s\n",
+					cur_reg_start, mc_route_string);
+			else
+				edac_dbg(0, "mc route table for CHA %d-%d: %s\n",
+					cur_reg_start, i-1, mc_route_string);
+			cur_reg_start = i;
+		}
+	}
+	knl_show_mc_route(mc_route_reg[i-1], mc_route_string);
+	if (cur_reg_start == i-1)
+		edac_dbg(0, "mc route table for CHA %d: %s\n",
+			cur_reg_start, mc_route_string);
+	else
+		edac_dbg(0, "mc route table for CHA %d-%d: %s\n",
+			cur_reg_start, i-1, mc_route_string);
+
+	/* Process DRAM rules */
+	for (sad_rule = 0; sad_rule < pvt->info.max_sad; sad_rule++) {
+		/* previous limit becomes the new base */
+		sad_base = sad_limit;
+
+		pci_read_config_dword(pvt->pci_sad0,
+			pvt->info.dram_rule[sad_rule], &dram_rule);
+
+		if (!DRAM_RULE_ENABLE(dram_rule))
+			break;
+
+		edram_only = KNL_EDRAM_ONLY(dram_rule);
+
+		sad_limit = pvt->info.sad_limit(dram_rule)+1;
+		sad_size = sad_limit - sad_base;
+
+		pci_read_config_dword(pvt->pci_sad0,
+			pvt->info.interleave_list[sad_rule], &interleave_reg);
+
+		/*
+		 * Find out how many ways this dram rule is interleaved.
+		 * We stop when we see the first channel again.
+		 */
+		first_pkg = sad_pkg(pvt->info.interleave_pkg,
+						interleave_reg, 0);
+		for (intrlv_ways = 1; intrlv_ways < 8; intrlv_ways++) {
+			pkg = sad_pkg(pvt->info.interleave_pkg,
+						interleave_reg, intrlv_ways);
+
+			if ((pkg & 0x8) == 0) {
+				/*
+				 * 0 bit means memory is non-local,
+				 * which KNL doesn't support
+				 */
+				edac_dbg(0, "Unexpected interleave target %d\n",
+					pkg);
+				return -1;
+			}
+
+			if (pkg == first_pkg)
+				break;
+		}
+		if (KNL_MOD3(dram_rule))
+			intrlv_ways *= 3;
+
+		edac_dbg(3, "dram rule %d (base 0x%llx, limit 0x%llx), %d way interleave%s\n",
+			sad_rule,
+			sad_base,
+			sad_limit,
+			intrlv_ways,
+			edram_only ? ", EDRAM" : "");
+
+		/*
+		 * Find out how big the SAD region really is by iterating
+		 * over TAD tables (SAD regions may contain holes).
+		 * Each memory controller might have a different TAD table, so
+		 * we have to look at both.
+		 *
+		 * Livespace is the memory that's mapped in this TAD table,
+		 * deadspace is the holes (this could be the MMIO hole, or it
+		 * could be memory that's mapped by the other TAD table but
+		 * not this one).
+		 */
+		for (mc = 0; mc < 2; mc++) {
+			sad_actual_size[mc] = 0;
+			tad_livespace = 0;
+			for (tad_rule = 0;
+					tad_rule < ARRAY_SIZE(
+						knl_tad_dram_limit_lo);
+					tad_rule++) {
+				if (knl_get_tad(pvt,
+						tad_rule,
+						mc,
+						&tad_deadspace,
+						&tad_limit,
+						&tad_ways))
+					break;
+
+				tad_size = (tad_limit+1) -
+					(tad_livespace + tad_deadspace);
+				tad_livespace += tad_size;
+				tad_base = (tad_limit+1) - tad_size;
+
+				if (tad_base < sad_base) {
+					if (tad_limit > sad_base)
+						edac_dbg(0, "TAD region overlaps lower SAD boundary -- TAD tables may be configured incorrectly.\n");
+				} else if (tad_base < sad_limit) {
+					if (tad_limit+1 > sad_limit) {
+						edac_dbg(0, "TAD region overlaps upper SAD boundary -- TAD tables may be configured incorrectly.\n");
+					} else {
+						/* TAD region is completely inside SAD region */
+						edac_dbg(3, "TAD region %d 0x%llx - 0x%llx (%lld bytes) table%d\n",
+							tad_rule, tad_base,
+							tad_limit, tad_size,
+							mc);
+						sad_actual_size[mc] += tad_size;
+					}
+				}
+				tad_base = tad_limit+1;
+			}
+		}
+
+		for (mc = 0; mc < 2; mc++) {
+			edac_dbg(3, " total TAD DRAM footprint in table%d : 0x%llx (%lld bytes)\n",
+				mc, sad_actual_size[mc], sad_actual_size[mc]);
+		}
+
+		/* Ignore EDRAM rule */
+		if (edram_only)
+			continue;
+
+		/* Figure out which channels participate in interleave. */
+		for (channel = 0; channel < KNL_MAX_CHANNELS; channel++)
+			participants[channel] = 0;
+
+		/* For each channel, does at least one CHA have
+		 * this channel mapped to the given target?
+		 */
+		for (channel = 0; channel < KNL_MAX_CHANNELS; channel++) {
+			for (way = 0; way < intrlv_ways; way++) {
+				int target;
+				int cha;
+
+				if (KNL_MOD3(dram_rule))
+					target = way;
+				else
+					target = 0x7 & sad_pkg(
+				pvt->info.interleave_pkg, interleave_reg, way);
+
+				for (cha = 0; cha < KNL_MAX_CHAS; cha++) {
+					if (knl_get_mc_route(target,
+						mc_route_reg[cha]) == channel
+						&& participants[channel]) {
+						participant_count++;
+						participants[channel] = 1;
+						break;
+					}
+				}
+			}
+		}
+
+		if (participant_count != intrlv_ways)
+			edac_dbg(0, "participant_count (%d) != interleave_ways (%d): DIMM size may be incorrect\n",
+				participant_count, intrlv_ways);
+
+		for (channel = 0; channel < KNL_MAX_CHANNELS; channel++) {
+			mc = knl_channel_mc(channel);
+			if (participants[channel]) {
+				edac_dbg(4, "mc channel %d contributes %lld bytes via sad entry %d\n",
+					channel,
+					sad_actual_size[mc]/intrlv_ways,
+					sad_rule);
+				mc_sizes[channel] +=
+					sad_actual_size[mc]/intrlv_ways;
+			}
+		}
+	}
+
+	return 0;
+}
+
 static int get_dimm_config(struct mem_ctl_info *mci)
 {
 	struct sbridge_pvt *pvt = mci->pvt_info;
@@ -934,13 +1612,20 @@
 	u32 reg;
 	enum edac_type mode;
 	enum mem_type mtype;
+	int channels = pvt->info.type == KNIGHTS_LANDING ?
+		KNL_MAX_CHANNELS : NUM_CHANNELS;
+	u64 knl_mc_sizes[KNL_MAX_CHANNELS];
 
-	if (pvt->info.type == HASWELL || pvt->info.type == BROADWELL)
+	if (pvt->info.type == HASWELL || pvt->info.type == BROADWELL ||
+			pvt->info.type == KNIGHTS_LANDING)
 		pci_read_config_dword(pvt->pci_sad1, SAD_TARGET, &reg);
 	else
 		pci_read_config_dword(pvt->pci_br0, SAD_TARGET, &reg);
 
-	pvt->sbridge_dev->source_id = SOURCE_ID(reg);
+	if (pvt->info.type == KNIGHTS_LANDING)
+		pvt->sbridge_dev->source_id = SOURCE_ID_KNL(reg);
+	else
+		pvt->sbridge_dev->source_id = SOURCE_ID(reg);
 
 	pvt->sbridge_dev->node_id = pvt->info.get_node_id(pvt);
 	edac_dbg(0, "mc#%d: Node ID: %d, source ID: %d\n",
@@ -948,31 +1633,42 @@
 		 pvt->sbridge_dev->node_id,
 		 pvt->sbridge_dev->source_id);
 
-	pci_read_config_dword(pvt->pci_ras, RASENABLES, &reg);
-	if (IS_MIRROR_ENABLED(reg)) {
-		edac_dbg(0, "Memory mirror is enabled\n");
-		pvt->is_mirrored = true;
-	} else {
-		edac_dbg(0, "Memory mirror is disabled\n");
-		pvt->is_mirrored = false;
-	}
-
-	pci_read_config_dword(pvt->pci_ta, MCMTR, &pvt->info.mcmtr);
-	if (IS_LOCKSTEP_ENABLED(pvt->info.mcmtr)) {
-		edac_dbg(0, "Lockstep is enabled\n");
-		mode = EDAC_S8ECD8ED;
-		pvt->is_lockstep = true;
-	} else {
-		edac_dbg(0, "Lockstep is disabled\n");
+	/* KNL doesn't support mirroring or lockstep,
+	 * and is always closed page
+	 */
+	if (pvt->info.type == KNIGHTS_LANDING) {
 		mode = EDAC_S4ECD4ED;
-		pvt->is_lockstep = false;
-	}
-	if (IS_CLOSE_PG(pvt->info.mcmtr)) {
-		edac_dbg(0, "address map is on closed page mode\n");
-		pvt->is_close_pg = true;
+		pvt->is_mirrored = false;
+
+		if (knl_get_dimm_capacity(pvt, knl_mc_sizes) != 0)
+			return -1;
 	} else {
-		edac_dbg(0, "address map is on open page mode\n");
-		pvt->is_close_pg = false;
+		pci_read_config_dword(pvt->pci_ras, RASENABLES, &reg);
+		if (IS_MIRROR_ENABLED(reg)) {
+			edac_dbg(0, "Memory mirror is enabled\n");
+			pvt->is_mirrored = true;
+		} else {
+			edac_dbg(0, "Memory mirror is disabled\n");
+			pvt->is_mirrored = false;
+		}
+
+		pci_read_config_dword(pvt->pci_ta, MCMTR, &pvt->info.mcmtr);
+		if (IS_LOCKSTEP_ENABLED(pvt->info.mcmtr)) {
+			edac_dbg(0, "Lockstep is enabled\n");
+			mode = EDAC_S8ECD8ED;
+			pvt->is_lockstep = true;
+		} else {
+			edac_dbg(0, "Lockstep is disabled\n");
+			mode = EDAC_S4ECD4ED;
+			pvt->is_lockstep = false;
+		}
+		if (IS_CLOSE_PG(pvt->info.mcmtr)) {
+			edac_dbg(0, "address map is on closed page mode\n");
+			pvt->is_close_pg = true;
+		} else {
+			edac_dbg(0, "address map is on open page mode\n");
+			pvt->is_close_pg = false;
+		}
 	}
 
 	mtype = pvt->info.get_memory_type(pvt);
@@ -988,23 +1684,46 @@
 	else
 		banks = 8;
 
-	for (i = 0; i < NUM_CHANNELS; i++) {
+	for (i = 0; i < channels; i++) {
 		u32 mtr;
 
-		if (!pvt->pci_tad[i])
-			continue;
-		for (j = 0; j < ARRAY_SIZE(mtr_regs); j++) {
+		int max_dimms_per_channel;
+
+		if (pvt->info.type == KNIGHTS_LANDING) {
+			max_dimms_per_channel = 1;
+			if (!pvt->knl.pci_channel[i])
+				continue;
+		} else {
+			max_dimms_per_channel = ARRAY_SIZE(mtr_regs);
+			if (!pvt->pci_tad[i])
+				continue;
+		}
+
+		for (j = 0; j < max_dimms_per_channel; j++) {
 			dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, mci->n_layers,
 				       i, j, 0);
-			pci_read_config_dword(pvt->pci_tad[i],
-					      mtr_regs[j], &mtr);
+			if (pvt->info.type == KNIGHTS_LANDING) {
+				pci_read_config_dword(pvt->knl.pci_channel[i],
+					knl_mtr_reg, &mtr);
+			} else {
+				pci_read_config_dword(pvt->pci_tad[i],
+					mtr_regs[j], &mtr);
+			}
 			edac_dbg(4, "Channel #%d  MTR%d = %x\n", i, j, mtr);
 			if (IS_DIMM_PRESENT(mtr)) {
 				pvt->channel[i].dimms++;
 
 				ranks = numrank(pvt->info.type, mtr);
-				rows = numrow(mtr);
-				cols = numcol(mtr);
+
+				if (pvt->info.type == KNIGHTS_LANDING) {
+					/* For DDR4, this is fixed. */
+					cols = 1 << 10;
+					rows = knl_mc_sizes[i] /
+						((u64) cols * ranks * banks * 8);
+				} else {
+					rows = numrow(mtr);
+					cols = numcol(mtr);
+				}
 
 				size = ((u64)rows * cols * banks * ranks) >> (20 - 3);
 				npages = MiB_TO_PAGES(size);
@@ -1069,7 +1788,7 @@
 		/* SAD_LIMIT Address range is 45:26 */
 		pci_read_config_dword(pvt->pci_sad0, pvt->info.dram_rule[n_sads],
 				      &reg);
-		limit = SAD_LIMIT(reg);
+		limit = pvt->info.sad_limit(reg);
 
 		if (!DRAM_RULE_ENABLE(reg))
 			continue;
@@ -1081,10 +1800,10 @@
 		gb = div_u64_rem(tmp_mb, 1024, &mb);
 		edac_dbg(0, "SAD#%d %s up to %u.%03u GB (0x%016Lx) Interleave: %s reg=0x%08x\n",
 			 n_sads,
-			 get_dram_attr(reg),
+			 show_dram_attr(pvt->info.dram_attr(reg)),
 			 gb, (mb*1000)/1024,
 			 ((u64)tmp_mb) << 20L,
-			 INTERLEAVE_MODE(reg) ? "8:6" : "[8:6]XOR[18:16]",
+			 pvt->info.show_interleave_mode(reg),
 			 reg);
 		prv = limit;
 
@@ -1101,6 +1820,9 @@
 		}
 	}
 
+	if (pvt->info.type == KNIGHTS_LANDING)
+		return;
+
 	/*
 	 * Step 3) Get TAD range
 	 */
@@ -1248,7 +1970,7 @@
 		if (!DRAM_RULE_ENABLE(reg))
 			continue;
 
-		limit = SAD_LIMIT(reg);
+		limit = pvt->info.sad_limit(reg);
 		if (limit <= prv) {
 			sprintf(msg, "Can't discover the memory socket");
 			return -EINVAL;
@@ -1262,8 +1984,8 @@
 		return -EINVAL;
 	}
 	dram_rule = reg;
-	*area_type = get_dram_attr(dram_rule);
-	interleave_mode = INTERLEAVE_MODE(dram_rule);
+	*area_type = show_dram_attr(pvt->info.dram_attr(dram_rule));
+	interleave_mode = pvt->info.interleave_mode(dram_rule);
 
 	pci_read_config_dword(pvt->pci_sad0, pvt->info.interleave_list[n_sads],
 			      &reg);
@@ -1567,7 +2289,8 @@
 static int sbridge_get_onedevice(struct pci_dev **prev,
 				 u8 *num_mc,
 				 const struct pci_id_table *table,
-				 const unsigned devno)
+				 const unsigned devno,
+				 const int multi_bus)
 {
 	struct sbridge_dev *sbridge_dev;
 	const struct pci_id_descr *dev_descr = &table->descr[devno];
@@ -1603,7 +2326,7 @@
 	}
 	bus = pdev->bus->number;
 
-	sbridge_dev = get_sbridge_dev(bus);
+	sbridge_dev = get_sbridge_dev(bus, multi_bus);
 	if (!sbridge_dev) {
 		sbridge_dev = alloc_sbridge_dev(bus, table);
 		if (!sbridge_dev) {
@@ -1652,21 +2375,32 @@
  * @num_mc: pointer to the memory controllers count, to be incremented in case
  *	    of success.
  * @table: model specific table
+ * @allow_dups: allow for multiple devices to exist with the same device id
+ *              (as implemented, this isn't expected to work correctly in the
+ *              multi-socket case).
+ * @multi_bus: don't assume devices on different buses belong to different
+ *             memory controllers.
  *
  * returns 0 in case of success or error code
  */
-static int sbridge_get_all_devices(u8 *num_mc,
-				   const struct pci_id_table *table)
+static int sbridge_get_all_devices_full(u8 *num_mc,
+					const struct pci_id_table *table,
+					int allow_dups,
+					int multi_bus)
 {
 	int i, rc;
 	struct pci_dev *pdev = NULL;
 
 	while (table && table->descr) {
 		for (i = 0; i < table->n_devs; i++) {
-			pdev = NULL;
+			if (!allow_dups || i == 0 ||
+					table->descr[i].dev_id !=
+						table->descr[i-1].dev_id) {
+				pdev = NULL;
+			}
 			do {
 				rc = sbridge_get_onedevice(&pdev, num_mc,
-							   table, i);
+							   table, i, multi_bus);
 				if (rc < 0) {
 					if (i == 0) {
 						i = table->n_devs;
@@ -1675,7 +2409,7 @@
 					sbridge_put_all_devices();
 					return -ENODEV;
 				}
-			} while (pdev);
+			} while (pdev && !allow_dups);
 		}
 		table++;
 	}
@@ -1683,6 +2417,11 @@
 	return 0;
 }
 
+#define sbridge_get_all_devices(num_mc, table) \
+		sbridge_get_all_devices_full(num_mc, table, 0, 0)
+#define sbridge_get_all_devices_knl(num_mc, table) \
+		sbridge_get_all_devices_full(num_mc, table, 1, 1)
+
 static int sbridge_mci_bind_devs(struct mem_ctl_info *mci,
 				 struct sbridge_dev *sbridge_dev)
 {
@@ -2038,6 +2777,131 @@
 	return -ENODEV;
 }
 
+static int knl_mci_bind_devs(struct mem_ctl_info *mci,
+			struct sbridge_dev *sbridge_dev)
+{
+	struct sbridge_pvt *pvt = mci->pvt_info;
+	struct pci_dev *pdev;
+	int dev, func;
+
+	int i;
+	int devidx;
+
+	for (i = 0; i < sbridge_dev->n_devs; i++) {
+		pdev = sbridge_dev->pdev[i];
+		if (!pdev)
+			continue;
+
+		/* Extract PCI device and function. */
+		dev = (pdev->devfn >> 3) & 0x1f;
+		func = pdev->devfn & 0x7;
+
+		switch (pdev->device) {
+		case PCI_DEVICE_ID_INTEL_KNL_IMC_MC:
+			if (dev == 8)
+				pvt->knl.pci_mc0 = pdev;
+			else if (dev == 9)
+				pvt->knl.pci_mc1 = pdev;
+			else {
+				sbridge_printk(KERN_ERR,
+					"Memory controller in unexpected place! (dev %d, fn %d)\n",
+					dev, func);
+				continue;
+			}
+			break;
+
+		case PCI_DEVICE_ID_INTEL_KNL_IMC_SAD0:
+			pvt->pci_sad0 = pdev;
+			break;
+
+		case PCI_DEVICE_ID_INTEL_KNL_IMC_SAD1:
+			pvt->pci_sad1 = pdev;
+			break;
+
+		case PCI_DEVICE_ID_INTEL_KNL_IMC_CHA:
+			/* There are one of these per tile, and range from
+			 * 1.14.0 to 1.18.5.
+			 */
+			devidx = ((dev-14)*8)+func;
+
+			if (devidx < 0 || devidx >= KNL_MAX_CHAS) {
+				sbridge_printk(KERN_ERR,
+					"Caching and Home Agent in unexpected place! (dev %d, fn %d)\n",
+					dev, func);
+				continue;
+			}
+
+			WARN_ON(pvt->knl.pci_cha[devidx] != NULL);
+
+			pvt->knl.pci_cha[devidx] = pdev;
+			break;
+
+		case PCI_DEVICE_ID_INTEL_KNL_IMC_CHANNEL:
+			devidx = -1;
+
+			/*
+			 *  MC0 channels 0-2 are device 9 function 2-4,
+			 *  MC1 channels 3-5 are device 8 function 2-4.
+			 */
+
+			if (dev == 9)
+				devidx = func-2;
+			else if (dev == 8)
+				devidx = 3 + (func-2);
+
+			if (devidx < 0 || devidx >= KNL_MAX_CHANNELS) {
+				sbridge_printk(KERN_ERR,
+					"DRAM Channel Registers in unexpected place! (dev %d, fn %d)\n",
+					dev, func);
+				continue;
+			}
+
+			WARN_ON(pvt->knl.pci_channel[devidx] != NULL);
+			pvt->knl.pci_channel[devidx] = pdev;
+			break;
+
+		case PCI_DEVICE_ID_INTEL_KNL_IMC_TOLHM:
+			pvt->knl.pci_mc_info = pdev;
+			break;
+
+		case PCI_DEVICE_ID_INTEL_KNL_IMC_TA:
+			pvt->pci_ta = pdev;
+			break;
+
+		default:
+			sbridge_printk(KERN_ERR, "Unexpected device %d\n",
+				pdev->device);
+			break;
+		}
+	}
+
+	if (!pvt->knl.pci_mc0  || !pvt->knl.pci_mc1 ||
+	    !pvt->pci_sad0     || !pvt->pci_sad1    ||
+	    !pvt->pci_ta) {
+		goto enodev;
+	}
+
+	for (i = 0; i < KNL_MAX_CHANNELS; i++) {
+		if (!pvt->knl.pci_channel[i]) {
+			sbridge_printk(KERN_ERR, "Missing channel %d\n", i);
+			goto enodev;
+		}
+	}
+
+	for (i = 0; i < KNL_MAX_CHAS; i++) {
+		if (!pvt->knl.pci_cha[i]) {
+			sbridge_printk(KERN_ERR, "Missing CHA %d\n", i);
+			goto enodev;
+		}
+	}
+
+	return 0;
+
+enodev:
+	sbridge_printk(KERN_ERR, "Some needed devices are missing\n");
+	return -ENODEV;
+}
+
 /****************************************************************************
 			Error check routines
  ****************************************************************************/
@@ -2127,8 +2991,36 @@
 	if (!GET_BITFIELD(m->status, 58, 58))
 		return;
 
-	rc = get_memory_error_data(mci, m->addr, &socket, &ha,
-				   &channel_mask, &rank, &area_type, msg);
+	if (pvt->info.type == KNIGHTS_LANDING) {
+		if (channel == 14) {
+			edac_dbg(0, "%s%s err_code:%04x:%04x EDRAM bank %d\n",
+				overflow ? " OVERFLOW" : "",
+				(uncorrected_error && recoverable)
+				? " recoverable" : "",
+				mscod, errcode,
+				m->bank);
+		} else {
+			char A = *("A");
+
+			channel = knl_channel_remap(channel);
+			channel_mask = 1 << channel;
+			snprintf(msg, sizeof(msg),
+				"%s%s err_code:%04x:%04x channel:%d (DIMM_%c)",
+				overflow ? " OVERFLOW" : "",
+				(uncorrected_error && recoverable)
+				? " recoverable" : " ",
+				mscod, errcode, channel, A + channel);
+			edac_mc_handle_error(tp_event, mci, core_err_cnt,
+				m->addr >> PAGE_SHIFT, m->addr & ~PAGE_MASK, 0,
+				channel, 0, -1,
+				optype, msg);
+		}
+		return;
+	} else {
+		rc = get_memory_error_data(mci, m->addr, &socket, &ha,
+				&channel_mask, &rank, &area_type, msg);
+	}
+
 	if (rc < 0)
 		goto err_parsing;
 	new_mci = get_mci_for_node_id(socket);
@@ -2359,10 +3251,11 @@
 
 	/* allocate a new MC control structure */
 	layers[0].type = EDAC_MC_LAYER_CHANNEL;
-	layers[0].size = NUM_CHANNELS;
+	layers[0].size = type == KNIGHTS_LANDING ?
+		KNL_MAX_CHANNELS : NUM_CHANNELS;
 	layers[0].is_virt_csrow = false;
 	layers[1].type = EDAC_MC_LAYER_SLOT;
-	layers[1].size = MAX_DIMMS;
+	layers[1].size = type == KNIGHTS_LANDING ? 1 : MAX_DIMMS;
 	layers[1].is_virt_csrow = true;
 	mci = edac_mc_alloc(sbridge_dev->mc, ARRAY_SIZE(layers), layers,
 			    sizeof(*pvt));
@@ -2380,7 +3273,8 @@
 	pvt->sbridge_dev = sbridge_dev;
 	sbridge_dev->mci = mci;
 
-	mci->mtype_cap = MEM_FLAG_DDR3;
+	mci->mtype_cap = type == KNIGHTS_LANDING ?
+		MEM_FLAG_DDR4 : MEM_FLAG_DDR3;
 	mci->edac_ctl_cap = EDAC_FLAG_NONE;
 	mci->edac_cap = EDAC_FLAG_NONE;
 	mci->mod_name = "sbridge_edac.c";
@@ -2401,6 +3295,10 @@
 		pvt->info.get_memory_type = get_memory_type;
 		pvt->info.get_node_id = get_node_id;
 		pvt->info.rir_limit = rir_limit;
+		pvt->info.sad_limit = sad_limit;
+		pvt->info.interleave_mode = interleave_mode;
+		pvt->info.show_interleave_mode = show_interleave_mode;
+		pvt->info.dram_attr = dram_attr;
 		pvt->info.max_sad = ARRAY_SIZE(ibridge_dram_rule);
 		pvt->info.interleave_list = ibridge_interleave_list;
 		pvt->info.max_interleave = ARRAY_SIZE(ibridge_interleave_list);
@@ -2421,6 +3319,10 @@
 		pvt->info.get_memory_type = get_memory_type;
 		pvt->info.get_node_id = get_node_id;
 		pvt->info.rir_limit = rir_limit;
+		pvt->info.sad_limit = sad_limit;
+		pvt->info.interleave_mode = interleave_mode;
+		pvt->info.show_interleave_mode = show_interleave_mode;
+		pvt->info.dram_attr = dram_attr;
 		pvt->info.max_sad = ARRAY_SIZE(sbridge_dram_rule);
 		pvt->info.interleave_list = sbridge_interleave_list;
 		pvt->info.max_interleave = ARRAY_SIZE(sbridge_interleave_list);
@@ -2441,6 +3343,10 @@
 		pvt->info.get_memory_type = haswell_get_memory_type;
 		pvt->info.get_node_id = haswell_get_node_id;
 		pvt->info.rir_limit = haswell_rir_limit;
+		pvt->info.sad_limit = sad_limit;
+		pvt->info.interleave_mode = interleave_mode;
+		pvt->info.show_interleave_mode = show_interleave_mode;
+		pvt->info.dram_attr = dram_attr;
 		pvt->info.max_sad = ARRAY_SIZE(ibridge_dram_rule);
 		pvt->info.interleave_list = ibridge_interleave_list;
 		pvt->info.max_interleave = ARRAY_SIZE(ibridge_interleave_list);
@@ -2461,6 +3367,10 @@
 		pvt->info.get_memory_type = haswell_get_memory_type;
 		pvt->info.get_node_id = haswell_get_node_id;
 		pvt->info.rir_limit = haswell_rir_limit;
+		pvt->info.sad_limit = sad_limit;
+		pvt->info.interleave_mode = interleave_mode;
+		pvt->info.show_interleave_mode = show_interleave_mode;
+		pvt->info.dram_attr = dram_attr;
 		pvt->info.max_sad = ARRAY_SIZE(ibridge_dram_rule);
 		pvt->info.interleave_list = ibridge_interleave_list;
 		pvt->info.max_interleave = ARRAY_SIZE(ibridge_interleave_list);
@@ -2473,6 +3383,30 @@
 		if (unlikely(rc < 0))
 			goto fail0;
 		break;
+	case KNIGHTS_LANDING:
+		/* pvt->info.rankcfgr == ??? */
+		pvt->info.get_tolm = knl_get_tolm;
+		pvt->info.get_tohm = knl_get_tohm;
+		pvt->info.dram_rule = knl_dram_rule;
+		pvt->info.get_memory_type = knl_get_memory_type;
+		pvt->info.get_node_id = knl_get_node_id;
+		pvt->info.rir_limit = NULL;
+		pvt->info.sad_limit = knl_sad_limit;
+		pvt->info.interleave_mode = knl_interleave_mode;
+		pvt->info.show_interleave_mode = knl_show_interleave_mode;
+		pvt->info.dram_attr = dram_attr_knl;
+		pvt->info.max_sad = ARRAY_SIZE(knl_dram_rule);
+		pvt->info.interleave_list = knl_interleave_list;
+		pvt->info.max_interleave = ARRAY_SIZE(knl_interleave_list);
+		pvt->info.interleave_pkg = ibridge_interleave_pkg;
+		pvt->info.get_width = knl_get_width;
+		mci->ctl_name = kasprintf(GFP_KERNEL,
+			"Knights Landing Socket#%d", mci->mc_idx);
+
+		rc = knl_mci_bind_devs(mci, sbridge_dev);
+		if (unlikely(rc < 0))
+			goto fail0;
+		break;
 	}
 
 	/* Get dimm basic config and the memory layout */
@@ -2527,20 +3461,29 @@
 
 	switch (pdev->device) {
 	case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TA:
-		rc = sbridge_get_all_devices(&num_mc, pci_dev_descr_ibridge_table);
+		rc = sbridge_get_all_devices(&num_mc,
+					pci_dev_descr_ibridge_table);
 		type = IVY_BRIDGE;
 		break;
 	case PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_HA0:
-		rc = sbridge_get_all_devices(&num_mc, pci_dev_descr_sbridge_table);
+		rc = sbridge_get_all_devices(&num_mc,
+					pci_dev_descr_sbridge_table);
 		type = SANDY_BRIDGE;
 		break;
 	case PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0:
-		rc = sbridge_get_all_devices(&num_mc, pci_dev_descr_haswell_table);
+		rc = sbridge_get_all_devices(&num_mc,
+					pci_dev_descr_haswell_table);
 		type = HASWELL;
 		break;
 	case PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0:
-		rc = sbridge_get_all_devices(&num_mc, pci_dev_descr_broadwell_table);
+		rc = sbridge_get_all_devices(&num_mc,
+					pci_dev_descr_broadwell_table);
 		type = BROADWELL;
+	    break;
+	case PCI_DEVICE_ID_INTEL_KNL_IMC_SAD0:
+		rc = sbridge_get_all_devices_knl(&num_mc,
+					pci_dev_descr_knl_table);
+		type = KNIGHTS_LANDING;
 		break;
 	}
 	if (unlikely(rc < 0)) {
diff --git a/drivers/edac/wq.c b/drivers/edac/wq.c
new file mode 100644
index 0000000..1b8c07e
--- /dev/null
+++ b/drivers/edac/wq.c
@@ -0,0 +1,42 @@
+#include "edac_module.h"
+
+static struct workqueue_struct *wq;
+
+bool edac_queue_work(struct delayed_work *work, unsigned long delay)
+{
+	return queue_delayed_work(wq, work, delay);
+}
+EXPORT_SYMBOL_GPL(edac_queue_work);
+
+bool edac_mod_work(struct delayed_work *work, unsigned long delay)
+{
+	return mod_delayed_work(wq, work, delay);
+}
+EXPORT_SYMBOL_GPL(edac_mod_work);
+
+bool edac_stop_work(struct delayed_work *work)
+{
+	bool ret;
+
+	ret = cancel_delayed_work_sync(work);
+	flush_workqueue(wq);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(edac_stop_work);
+
+int edac_workqueue_setup(void)
+{
+	wq = create_singlethread_workqueue("edac-poller");
+	if (!wq)
+		return -ENODEV;
+	else
+		return 0;
+}
+
+void edac_workqueue_teardown(void)
+{
+	flush_workqueue(wq);
+	destroy_workqueue(wq);
+	wq = NULL;
+}
diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig
index cf478fe..49a3a11 100644
--- a/drivers/firmware/Kconfig
+++ b/drivers/firmware/Kconfig
@@ -173,6 +173,9 @@
 	def_bool y
 	depends on QCOM_SCM && ARM64
 
+config HAVE_ARM_SMCCC
+	bool
+
 source "drivers/firmware/broadcom/Kconfig"
 source "drivers/firmware/google/Kconfig"
 source "drivers/firmware/efi/Kconfig"
diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c
index ac1ce4a..0e08e66 100644
--- a/drivers/firmware/dmi_scan.c
+++ b/drivers/firmware/dmi_scan.c
@@ -521,6 +521,7 @@
 			dmi_ver = smbios_ver;
 		else
 			dmi_ver = (buf[14] & 0xF0) << 4 | (buf[14] & 0x0F);
+		dmi_ver <<= 8;
 		dmi_num = get_unaligned_le16(buf + 12);
 		dmi_len = get_unaligned_le16(buf + 6);
 		dmi_base = get_unaligned_le32(buf + 8);
@@ -528,15 +529,14 @@
 		if (dmi_walk_early(dmi_decode) == 0) {
 			if (smbios_ver) {
 				pr_info("SMBIOS %d.%d present.\n",
-				       dmi_ver >> 8, dmi_ver & 0xFF);
+					dmi_ver >> 16, (dmi_ver >> 8) & 0xFF);
 			} else {
 				smbios_entry_point_size = 15;
 				memcpy(smbios_entry_point, buf,
 				       smbios_entry_point_size);
 				pr_info("Legacy DMI %d.%d present.\n",
-				       dmi_ver >> 8, dmi_ver & 0xFF);
+					dmi_ver >> 16, (dmi_ver >> 8) & 0xFF);
 			}
-			dmi_ver <<= 8;
 			dmi_format_ids(dmi_ids_string, sizeof(dmi_ids_string));
 			printk(KERN_DEBUG "DMI: %s\n", dmi_ids_string);
 			return 0;
diff --git a/drivers/firmware/efi/Makefile b/drivers/firmware/efi/Makefile
index ec379a4..62e654f 100644
--- a/drivers/firmware/efi/Makefile
+++ b/drivers/firmware/efi/Makefile
@@ -18,3 +18,7 @@
 obj-$(CONFIG_EFI_RUNTIME_WRAPPERS)	+= runtime-wrappers.o
 obj-$(CONFIG_EFI_STUB)			+= libstub/
 obj-$(CONFIG_EFI_FAKE_MEMMAP)		+= fake_mem.o
+
+arm-obj-$(CONFIG_EFI)			:= arm-init.o arm-runtime.o
+obj-$(CONFIG_ARM)			+= $(arm-obj-y)
+obj-$(CONFIG_ARM64)			+= $(arm-obj-y)
diff --git a/drivers/firmware/efi/arm-init.c b/drivers/firmware/efi/arm-init.c
new file mode 100644
index 0000000..9e15d57
--- /dev/null
+++ b/drivers/firmware/efi/arm-init.c
@@ -0,0 +1,209 @@
+/*
+ * Extensible Firmware Interface
+ *
+ * Based on Extensible Firmware Interface Specification version 2.4
+ *
+ * Copyright (C) 2013 - 2015 Linaro Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/efi.h>
+#include <linux/init.h>
+#include <linux/memblock.h>
+#include <linux/mm_types.h>
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+
+#include <asm/efi.h>
+
+struct efi_memory_map memmap;
+
+u64 efi_system_table;
+
+static int __init is_normal_ram(efi_memory_desc_t *md)
+{
+	if (md->attribute & EFI_MEMORY_WB)
+		return 1;
+	return 0;
+}
+
+/*
+ * Translate a EFI virtual address into a physical address: this is necessary,
+ * as some data members of the EFI system table are virtually remapped after
+ * SetVirtualAddressMap() has been called.
+ */
+static phys_addr_t efi_to_phys(unsigned long addr)
+{
+	efi_memory_desc_t *md;
+
+	for_each_efi_memory_desc(&memmap, md) {
+		if (!(md->attribute & EFI_MEMORY_RUNTIME))
+			continue;
+		if (md->virt_addr == 0)
+			/* no virtual mapping has been installed by the stub */
+			break;
+		if (md->virt_addr <= addr &&
+		    (addr - md->virt_addr) < (md->num_pages << EFI_PAGE_SHIFT))
+			return md->phys_addr + addr - md->virt_addr;
+	}
+	return addr;
+}
+
+static int __init uefi_init(void)
+{
+	efi_char16_t *c16;
+	void *config_tables;
+	size_t table_size;
+	char vendor[100] = "unknown";
+	int i, retval;
+
+	efi.systab = early_memremap(efi_system_table,
+				    sizeof(efi_system_table_t));
+	if (efi.systab == NULL) {
+		pr_warn("Unable to map EFI system table.\n");
+		return -ENOMEM;
+	}
+
+	set_bit(EFI_BOOT, &efi.flags);
+	if (IS_ENABLED(CONFIG_64BIT))
+		set_bit(EFI_64BIT, &efi.flags);
+
+	/*
+	 * Verify the EFI Table
+	 */
+	if (efi.systab->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) {
+		pr_err("System table signature incorrect\n");
+		retval = -EINVAL;
+		goto out;
+	}
+	if ((efi.systab->hdr.revision >> 16) < 2)
+		pr_warn("Warning: EFI system table version %d.%02d, expected 2.00 or greater\n",
+			efi.systab->hdr.revision >> 16,
+			efi.systab->hdr.revision & 0xffff);
+
+	/* Show what we know for posterity */
+	c16 = early_memremap(efi_to_phys(efi.systab->fw_vendor),
+			     sizeof(vendor) * sizeof(efi_char16_t));
+	if (c16) {
+		for (i = 0; i < (int) sizeof(vendor) - 1 && *c16; ++i)
+			vendor[i] = c16[i];
+		vendor[i] = '\0';
+		early_memunmap(c16, sizeof(vendor) * sizeof(efi_char16_t));
+	}
+
+	pr_info("EFI v%u.%.02u by %s\n",
+		efi.systab->hdr.revision >> 16,
+		efi.systab->hdr.revision & 0xffff, vendor);
+
+	table_size = sizeof(efi_config_table_64_t) * efi.systab->nr_tables;
+	config_tables = early_memremap(efi_to_phys(efi.systab->tables),
+				       table_size);
+	if (config_tables == NULL) {
+		pr_warn("Unable to map EFI config table array.\n");
+		retval = -ENOMEM;
+		goto out;
+	}
+	retval = efi_config_parse_tables(config_tables, efi.systab->nr_tables,
+					 sizeof(efi_config_table_t), NULL);
+
+	early_memunmap(config_tables, table_size);
+out:
+	early_memunmap(efi.systab,  sizeof(efi_system_table_t));
+	return retval;
+}
+
+/*
+ * Return true for RAM regions we want to permanently reserve.
+ */
+static __init int is_reserve_region(efi_memory_desc_t *md)
+{
+	switch (md->type) {
+	case EFI_LOADER_CODE:
+	case EFI_LOADER_DATA:
+	case EFI_BOOT_SERVICES_CODE:
+	case EFI_BOOT_SERVICES_DATA:
+	case EFI_CONVENTIONAL_MEMORY:
+	case EFI_PERSISTENT_MEMORY:
+		return 0;
+	default:
+		break;
+	}
+	return is_normal_ram(md);
+}
+
+static __init void reserve_regions(void)
+{
+	efi_memory_desc_t *md;
+	u64 paddr, npages, size;
+
+	if (efi_enabled(EFI_DBG))
+		pr_info("Processing EFI memory map:\n");
+
+	for_each_efi_memory_desc(&memmap, md) {
+		paddr = md->phys_addr;
+		npages = md->num_pages;
+
+		if (efi_enabled(EFI_DBG)) {
+			char buf[64];
+
+			pr_info("  0x%012llx-0x%012llx %s",
+				paddr, paddr + (npages << EFI_PAGE_SHIFT) - 1,
+				efi_md_typeattr_format(buf, sizeof(buf), md));
+		}
+
+		memrange_efi_to_native(&paddr, &npages);
+		size = npages << PAGE_SHIFT;
+
+		if (is_normal_ram(md))
+			early_init_dt_add_memory_arch(paddr, size);
+
+		if (is_reserve_region(md)) {
+			memblock_mark_nomap(paddr, size);
+			if (efi_enabled(EFI_DBG))
+				pr_cont("*");
+		}
+
+		if (efi_enabled(EFI_DBG))
+			pr_cont("\n");
+	}
+
+	set_bit(EFI_MEMMAP, &efi.flags);
+}
+
+void __init efi_init(void)
+{
+	struct efi_fdt_params params;
+
+	/* Grab UEFI information placed in FDT by stub */
+	if (!efi_get_fdt_params(&params))
+		return;
+
+	efi_system_table = params.system_table;
+
+	memmap.phys_map = params.mmap;
+	memmap.map = early_memremap(params.mmap, params.mmap_size);
+	if (memmap.map == NULL) {
+		/*
+		* If we are booting via UEFI, the UEFI memory map is the only
+		* description of memory we have, so there is little point in
+		* proceeding if we cannot access it.
+		*/
+		panic("Unable to map EFI memory map.\n");
+	}
+	memmap.map_end = memmap.map + params.mmap_size;
+	memmap.desc_size = params.desc_size;
+	memmap.desc_version = params.desc_ver;
+
+	if (uefi_init() < 0)
+		return;
+
+	reserve_regions();
+	early_memunmap(memmap.map, params.mmap_size);
+	memblock_mark_nomap(params.mmap & PAGE_MASK,
+			    PAGE_ALIGN(params.mmap_size +
+				       (params.mmap & ~PAGE_MASK)));
+}
diff --git a/drivers/firmware/efi/arm-runtime.c b/drivers/firmware/efi/arm-runtime.c
new file mode 100644
index 0000000..6ae21e4
--- /dev/null
+++ b/drivers/firmware/efi/arm-runtime.c
@@ -0,0 +1,135 @@
+/*
+ * Extensible Firmware Interface
+ *
+ * Based on Extensible Firmware Interface Specification version 2.4
+ *
+ * Copyright (C) 2013, 2014 Linaro Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/efi.h>
+#include <linux/io.h>
+#include <linux/memblock.h>
+#include <linux/mm_types.h>
+#include <linux/preempt.h>
+#include <linux/rbtree.h>
+#include <linux/rwsem.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+
+#include <asm/cacheflush.h>
+#include <asm/efi.h>
+#include <asm/mmu.h>
+#include <asm/pgalloc.h>
+#include <asm/pgtable.h>
+
+extern u64 efi_system_table;
+
+static struct mm_struct efi_mm = {
+	.mm_rb			= RB_ROOT,
+	.mm_users		= ATOMIC_INIT(2),
+	.mm_count		= ATOMIC_INIT(1),
+	.mmap_sem		= __RWSEM_INITIALIZER(efi_mm.mmap_sem),
+	.page_table_lock	= __SPIN_LOCK_UNLOCKED(efi_mm.page_table_lock),
+	.mmlist			= LIST_HEAD_INIT(efi_mm.mmlist),
+};
+
+static bool __init efi_virtmap_init(void)
+{
+	efi_memory_desc_t *md;
+
+	efi_mm.pgd = pgd_alloc(&efi_mm);
+	init_new_context(NULL, &efi_mm);
+
+	for_each_efi_memory_desc(&memmap, md) {
+		phys_addr_t phys = md->phys_addr;
+		int ret;
+
+		if (!(md->attribute & EFI_MEMORY_RUNTIME))
+			continue;
+		if (md->virt_addr == 0)
+			return false;
+
+		ret = efi_create_mapping(&efi_mm, md);
+		if  (!ret) {
+			pr_info("  EFI remap %pa => %p\n",
+				&phys, (void *)(unsigned long)md->virt_addr);
+		} else {
+			pr_warn("  EFI remap %pa: failed to create mapping (%d)\n",
+				&phys, ret);
+			return false;
+		}
+	}
+	return true;
+}
+
+/*
+ * Enable the UEFI Runtime Services if all prerequisites are in place, i.e.,
+ * non-early mapping of the UEFI system table and virtual mappings for all
+ * EFI_MEMORY_RUNTIME regions.
+ */
+static int __init arm_enable_runtime_services(void)
+{
+	u64 mapsize;
+
+	if (!efi_enabled(EFI_BOOT)) {
+		pr_info("EFI services will not be available.\n");
+		return 0;
+	}
+
+	if (efi_runtime_disabled()) {
+		pr_info("EFI runtime services will be disabled.\n");
+		return 0;
+	}
+
+	pr_info("Remapping and enabling EFI services.\n");
+
+	mapsize = memmap.map_end - memmap.map;
+	memmap.map = (__force void *)ioremap_cache(memmap.phys_map,
+						   mapsize);
+	if (!memmap.map) {
+		pr_err("Failed to remap EFI memory map\n");
+		return -ENOMEM;
+	}
+	memmap.map_end = memmap.map + mapsize;
+	efi.memmap = &memmap;
+
+	efi.systab = (__force void *)ioremap_cache(efi_system_table,
+						   sizeof(efi_system_table_t));
+	if (!efi.systab) {
+		pr_err("Failed to remap EFI System Table\n");
+		return -ENOMEM;
+	}
+	set_bit(EFI_SYSTEM_TABLES, &efi.flags);
+
+	if (!efi_virtmap_init()) {
+		pr_err("No UEFI virtual mapping was installed -- runtime services will not be available\n");
+		return -ENOMEM;
+	}
+
+	/* Set up runtime services function pointers */
+	efi_native_runtime_setup();
+	set_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+
+	efi.runtime_version = efi.systab->hdr.revision;
+
+	return 0;
+}
+early_initcall(arm_enable_runtime_services);
+
+void efi_virtmap_load(void)
+{
+	preempt_disable();
+	efi_set_pgd(&efi_mm);
+}
+
+void efi_virtmap_unload(void)
+{
+	efi_set_pgd(current->active_mm);
+	preempt_enable();
+}
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 027ca21..cffa89b 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -25,6 +25,8 @@
 #include <linux/io.h>
 #include <linux/platform_device.h>
 
+#include <asm/efi.h>
+
 struct efi __read_mostly efi = {
 	.mps			= EFI_INVALID_TABLE_ADDR,
 	.acpi			= EFI_INVALID_TABLE_ADDR,
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index 3c0467d..9c12e18 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -8,7 +8,7 @@
 cflags-$(CONFIG_X86_64)		:= -mcmodel=small
 cflags-$(CONFIG_X86)		+= -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2 \
 				   -fPIC -fno-strict-aliasing -mno-red-zone \
-				   -mno-mmx -mno-sse -DDISABLE_BRANCH_PROFILING
+				   -mno-mmx -mno-sse
 
 cflags-$(CONFIG_ARM64)		:= $(subst -pg,,$(KBUILD_CFLAGS))
 cflags-$(CONFIG_ARM)		:= $(subst -pg,,$(KBUILD_CFLAGS)) \
@@ -16,7 +16,7 @@
 
 cflags-$(CONFIG_EFI_ARMSTUB)	+= -I$(srctree)/scripts/dtc/libfdt
 
-KBUILD_CFLAGS			:= $(cflags-y) \
+KBUILD_CFLAGS			:= $(cflags-y) -DDISABLE_BRANCH_PROFILING \
 				   $(call cc-option,-ffreestanding) \
 				   $(call cc-option,-fno-stack-protector)
 
@@ -34,6 +34,7 @@
 lib-$(CONFIG_EFI_ARMSTUB)	+= arm-stub.o fdt.o string.o \
 				   $(patsubst %.c,lib-%.o,$(arm-deps))
 
+lib-$(CONFIG_ARM)		+= arm32-stub.o
 lib-$(CONFIG_ARM64)		+= arm64-stub.o
 CFLAGS_arm64-stub.o 		:= -DTEXT_OFFSET=$(TEXT_OFFSET)
 
@@ -67,3 +68,11 @@
 		     $(OBJDUMP) -r $@ | grep $(STUBCOPY_RELOC-y)	\
 		     && (echo >&2 "$@: absolute symbol references not allowed in the EFI stub"; \
 			 rm -f $@; /bin/false); else /bin/false; fi
+
+#
+# ARM discards the .data section because it disallows r/w data in the
+# decompressor. So move our .data to .data.efistub, which is preserved
+# explicitly by the decompressor linker script.
+#
+STUBCOPY_FLAGS-$(CONFIG_ARM)	+= --rename-section .data=.data.efistub
+STUBCOPY_RELOC-$(CONFIG_ARM)	:= R_ARM_ABS
diff --git a/drivers/firmware/efi/libstub/arm-stub.c b/drivers/firmware/efi/libstub/arm-stub.c
index 950c87f..3397902 100644
--- a/drivers/firmware/efi/libstub/arm-stub.c
+++ b/drivers/firmware/efi/libstub/arm-stub.c
@@ -303,8 +303,10 @@
  * The value chosen is the largest non-zero power of 2 suitable for this purpose
  * both on 32-bit and 64-bit ARM CPUs, to maximize the likelihood that it can
  * be mapped efficiently.
+ * Since 32-bit ARM could potentially execute with a 1G/3G user/kernel split,
+ * map everything below 1 GB.
  */
-#define EFI_RT_VIRTUAL_BASE	0x40000000
+#define EFI_RT_VIRTUAL_BASE	SZ_512M
 
 static int cmp_mem_desc(const void *l, const void *r)
 {
diff --git a/drivers/firmware/efi/libstub/arm32-stub.c b/drivers/firmware/efi/libstub/arm32-stub.c
new file mode 100644
index 0000000..495ebd6
--- /dev/null
+++ b/drivers/firmware/efi/libstub/arm32-stub.c
@@ -0,0 +1,85 @@
+/*
+ * Copyright (C) 2013 Linaro Ltd;  <roy.franz@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+#include <linux/efi.h>
+#include <asm/efi.h>
+
+efi_status_t handle_kernel_image(efi_system_table_t *sys_table,
+				 unsigned long *image_addr,
+				 unsigned long *image_size,
+				 unsigned long *reserve_addr,
+				 unsigned long *reserve_size,
+				 unsigned long dram_base,
+				 efi_loaded_image_t *image)
+{
+	unsigned long nr_pages;
+	efi_status_t status;
+	/* Use alloc_addr to tranlsate between types */
+	efi_physical_addr_t alloc_addr;
+
+	/*
+	 * Verify that the DRAM base address is compatible with the ARM
+	 * boot protocol, which determines the base of DRAM by masking
+	 * off the low 27 bits of the address at which the zImage is
+	 * loaded. These assumptions are made by the decompressor,
+	 * before any memory map is available.
+	 */
+	dram_base = round_up(dram_base, SZ_128M);
+
+	/*
+	 * Reserve memory for the uncompressed kernel image. This is
+	 * all that prevents any future allocations from conflicting
+	 * with the kernel. Since we can't tell from the compressed
+	 * image how much DRAM the kernel actually uses (due to BSS
+	 * size uncertainty) we allocate the maximum possible size.
+	 * Do this very early, as prints can cause memory allocations
+	 * that may conflict with this.
+	 */
+	alloc_addr = dram_base;
+	*reserve_size = MAX_UNCOMP_KERNEL_SIZE;
+	nr_pages = round_up(*reserve_size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
+	status = sys_table->boottime->allocate_pages(EFI_ALLOCATE_ADDRESS,
+						     EFI_LOADER_DATA,
+						     nr_pages, &alloc_addr);
+	if (status != EFI_SUCCESS) {
+		*reserve_size = 0;
+		pr_efi_err(sys_table, "Unable to allocate memory for uncompressed kernel.\n");
+		return status;
+	}
+	*reserve_addr = alloc_addr;
+
+	/*
+	 * Relocate the zImage, so that it appears in the lowest 128 MB
+	 * memory window.
+	 */
+	*image_size = image->image_size;
+	status = efi_relocate_kernel(sys_table, image_addr, *image_size,
+				     *image_size,
+				     dram_base + MAX_UNCOMP_KERNEL_SIZE, 0);
+	if (status != EFI_SUCCESS) {
+		pr_efi_err(sys_table, "Failed to relocate kernel.\n");
+		efi_free(sys_table, *reserve_size, *reserve_addr);
+		*reserve_size = 0;
+		return status;
+	}
+
+	/*
+	 * Check to see if we were able to allocate memory low enough
+	 * in memory. The kernel determines the base of DRAM from the
+	 * address at which the zImage is loaded.
+	 */
+	if (*image_addr + *image_size > dram_base + ZIMAGE_OFFSET_LIMIT) {
+		pr_efi_err(sys_table, "Failed to relocate kernel, no low memory available.\n");
+		efi_free(sys_table, *reserve_size, *reserve_addr);
+		*reserve_size = 0;
+		efi_free(sys_table, *image_size, *image_addr);
+		*image_size = 0;
+		return EFI_LOAD_ERROR;
+	}
+	return EFI_SUCCESS;
+}
diff --git a/drivers/firmware/psci.c b/drivers/firmware/psci.c
index d24f35d..f25cd79 100644
--- a/drivers/firmware/psci.c
+++ b/drivers/firmware/psci.c
@@ -13,6 +13,7 @@
 
 #define pr_fmt(fmt) "psci: " fmt
 
+#include <linux/arm-smccc.h>
 #include <linux/errno.h>
 #include <linux/linkage.h>
 #include <linux/of.h>
@@ -58,8 +59,6 @@
 
 typedef unsigned long (psci_fn)(unsigned long, unsigned long,
 				unsigned long, unsigned long);
-asmlinkage psci_fn __invoke_psci_fn_hvc;
-asmlinkage psci_fn __invoke_psci_fn_smc;
 static psci_fn *invoke_psci_fn;
 
 enum psci_function {
@@ -107,6 +106,26 @@
 	return !(state & ~valid_mask);
 }
 
+static unsigned long __invoke_psci_fn_hvc(unsigned long function_id,
+			unsigned long arg0, unsigned long arg1,
+			unsigned long arg2)
+{
+	struct arm_smccc_res res;
+
+	arm_smccc_hvc(function_id, arg0, arg1, arg2, 0, 0, 0, 0, &res);
+	return res.a0;
+}
+
+static unsigned long __invoke_psci_fn_smc(unsigned long function_id,
+			unsigned long arg0, unsigned long arg1,
+			unsigned long arg2)
+{
+	struct arm_smccc_res res;
+
+	arm_smccc_smc(function_id, arg0, arg1, arg2, 0, 0, 0, 0, &res);
+	return res.a0;
+}
+
 static int psci_to_linux_errno(int errno)
 {
 	switch (errno) {
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index c6a1b4c..d321222 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -559,19 +559,10 @@
 
 	/* this is the actual buffer to work with */
 
-	args_buff = kmalloc(args->buf_size_in_bytes -
-					sizeof(*args), GFP_KERNEL);
-	if (args_buff == NULL)
-		return -ENOMEM;
-
-	status = copy_from_user(args_buff, cmd_from_user,
+	args_buff = memdup_user(args_buff,
 				args->buf_size_in_bytes - sizeof(*args));
-
-	if (status != 0) {
-		pr_debug("Failed to copy address watch user data\n");
-		kfree(args_buff);
-		return -EINVAL;
-	}
+	if (IS_ERR(args_buff))
+		return PTR_ERR(args_buff);
 
 	aw_info.process = p;
 
@@ -677,22 +668,12 @@
 	if (cmd_from_user == NULL)
 		return -EINVAL;
 
-	/* this is the actual buffer to work with */
+	/* copy the entire buffer from user */
 
-	args_buff = kmalloc(args->buf_size_in_bytes - sizeof(*args),
-			GFP_KERNEL);
-
-	if (args_buff == NULL)
-		return -ENOMEM;
-
-	/* Now copy the entire buffer from user */
-	status = copy_from_user(args_buff, cmd_from_user,
+	args_buff = memdup_user(cmd_from_user,
 				args->buf_size_in_bytes - sizeof(*args));
-	if (status != 0) {
-		pr_debug("Failed to copy wave control user data\n");
-		kfree(args_buff);
-		return -EINVAL;
-	}
+	if (IS_ERR(args_buff))
+		return PTR_ERR(args_buff);
 
 	/* move ptr to the start of the "pay-load" area */
 	wac_info.process = p;
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv40.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv40.c
index ffa902e..05a8954 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv40.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv40.c
@@ -156,6 +156,7 @@
 		return -ENOMEM;
 	nvkm_object_ctor(&nv40_gr_chan, oclass, &chan->object);
 	chan->gr = gr;
+	chan->fifo = fifoch;
 	*pobject = &chan->object;
 
 	spin_lock_irqsave(&chan->gr->base.engine.lock, flags);
diff --git a/drivers/gpu/ipu-v3/ipu-cpmem.c b/drivers/gpu/ipu-v3/ipu-cpmem.c
index 63eb16b..883a314 100644
--- a/drivers/gpu/ipu-v3/ipu-cpmem.c
+++ b/drivers/gpu/ipu-v3/ipu-cpmem.c
@@ -161,7 +161,7 @@
  * The DRM pixel formats and IPU internal representation are ordered the other
  * way around, with the first named component ordered at the most significant
  * bits. Further, V4L2 formats are not well defined:
- *     http://linuxtv.org/downloads/v4l-dvb-apis/packed-rgb.html
+ *     https://linuxtv.org/downloads/v4l-dvb-apis/packed-rgb.html
  * We choose the interpretation which matches GStreamer behavior.
  */
 static int v4l2_pix_fmt_to_drm_fourcc(u32 pixelformat)
diff --git a/drivers/gpu/vga/vgaarb.c b/drivers/gpu/vga/vgaarb.c
index 9abcaa5..f17cb04 100644
--- a/drivers/gpu/vga/vgaarb.c
+++ b/drivers/gpu/vga/vgaarb.c
@@ -1163,12 +1163,8 @@
 
 static unsigned int vga_arb_fpoll(struct file *file, poll_table *wait)
 {
-	struct vga_arb_private *priv = file->private_data;
-
 	pr_debug("%s\n", __func__);
 
-	if (priv == NULL)
-		return -ENODEV;
 	poll_wait(file, &vga_wait_queue, wait);
 	return POLLIN;
 }
@@ -1209,9 +1205,6 @@
 
 	pr_debug("%s\n", __func__);
 
-	if (priv == NULL)
-		return -ENODEV;
-
 	spin_lock_irqsave(&vga_user_lock, flags);
 	list_del(&priv->list);
 	for (i = 0; i < MAX_USER_CARDS; i++) {
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index 3782636..678663e 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -63,10 +63,6 @@
 /* Define version of the synthetic interrupt controller. */
 #define HV_SYNIC_VERSION		(1)
 
-/* Define synthetic interrupt controller message constants. */
-#define HV_MESSAGE_SIZE			(256)
-#define HV_MESSAGE_PAYLOAD_BYTE_COUNT	(240)
-#define HV_MESSAGE_PAYLOAD_QWORD_COUNT	(30)
 #define HV_ANY_VP			(0xFFFFFFFF)
 
 /* Define synthetic interrupt controller flag constants. */
@@ -74,48 +70,9 @@
 #define HV_EVENT_FLAGS_BYTE_COUNT	(256)
 #define HV_EVENT_FLAGS_DWORD_COUNT	(256 / sizeof(u32))
 
-/* Define hypervisor message types. */
-enum hv_message_type {
-	HVMSG_NONE			= 0x00000000,
-
-	/* Memory access messages. */
-	HVMSG_UNMAPPED_GPA		= 0x80000000,
-	HVMSG_GPA_INTERCEPT		= 0x80000001,
-
-	/* Timer notification messages. */
-	HVMSG_TIMER_EXPIRED			= 0x80000010,
-
-	/* Error messages. */
-	HVMSG_INVALID_VP_REGISTER_VALUE	= 0x80000020,
-	HVMSG_UNRECOVERABLE_EXCEPTION	= 0x80000021,
-	HVMSG_UNSUPPORTED_FEATURE		= 0x80000022,
-
-	/* Trace buffer complete messages. */
-	HVMSG_EVENTLOG_BUFFERCOMPLETE	= 0x80000040,
-
-	/* Platform-specific processor intercept messages. */
-	HVMSG_X64_IOPORT_INTERCEPT		= 0x80010000,
-	HVMSG_X64_MSR_INTERCEPT		= 0x80010001,
-	HVMSG_X64_CPUID_INTERCEPT		= 0x80010002,
-	HVMSG_X64_EXCEPTION_INTERCEPT	= 0x80010003,
-	HVMSG_X64_APIC_EOI			= 0x80010004,
-	HVMSG_X64_LEGACY_FP_ERROR		= 0x80010005
-};
-
-#define HV_SYNIC_STIMER_COUNT		(4)
-
 /* Define invalid partition identifier. */
 #define HV_PARTITION_ID_INVALID		((u64)0x0)
 
-/* Define port identifier type. */
-union hv_port_id {
-	u32 asu32;
-	struct {
-		u32 id:24;
-		u32 reserved:8;
-	} u ;
-};
-
 /* Define port type. */
 enum hv_port_type {
 	HVPORT_MSG	= 1,
@@ -163,27 +120,6 @@
 	};
 };
 
-/* Define synthetic interrupt controller message flags. */
-union hv_message_flags {
-	u8 asu8;
-	struct {
-		u8 msg_pending:1;
-		u8 reserved:7;
-	};
-};
-
-/* Define synthetic interrupt controller message header. */
-struct hv_message_header {
-	enum hv_message_type message_type;
-	u8 payload_size;
-	union hv_message_flags message_flags;
-	u8 reserved[2];
-	union {
-		u64 sender;
-		union hv_port_id port;
-	};
-};
-
 /*
  * Timer configuration register.
  */
@@ -200,31 +136,9 @@
 	};
 };
 
-
-/* Define timer message payload structure. */
-struct hv_timer_message_payload {
-	u32 timer_index;
-	u32 reserved;
-	u64 expiration_time;	/* When the timer expired */
-	u64 delivery_time;	/* When the message was delivered */
-};
-
-/* Define synthetic interrupt controller message format. */
-struct hv_message {
-	struct hv_message_header header;
-	union {
-		u64 payload[HV_MESSAGE_PAYLOAD_QWORD_COUNT];
-	} u ;
-};
-
 /* Define the number of message buffers associated with each port. */
 #define HV_PORT_MESSAGE_BUFFER_COUNT	(16)
 
-/* Define the synthetic interrupt message page layout. */
-struct hv_message_page {
-	struct hv_message sint_message[HV_SYNIC_SINT_COUNT];
-};
-
 /* Define the synthetic interrupt controller event flags format. */
 union hv_synic_event_flags {
 	u8 flags8[HV_EVENT_FLAGS_BYTE_COUNT];
@@ -347,7 +261,7 @@
 struct hv_input_post_message {
 	union hv_connection_id connectionid;
 	u32 reserved;
-	enum hv_message_type message_type;
+	u32 message_type;
 	u32 payload_size;
 	u64 payload[HV_MESSAGE_PAYLOAD_QWORD_COUNT];
 };
diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index 80a73bf..60fb80b 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -859,16 +859,6 @@
 	  This driver can also be built as a module.  If so, the module
 	  will be called max31790.
 
-config SENSORS_HTU21
-	tristate "Measurement Specialties HTU21D humidity/temperature sensors"
-	depends on I2C
-	help
-	  If you say yes here you get support for the Measurement Specialties
-	  HTU21D humidity and temperature sensors.
-
-	  This driver can also be built as a module.  If so, the module
-	  will be called htu21.
-
 config SENSORS_MCP3021
 	tristate "Microchip MCP3021 and compatibles"
 	depends on I2C
diff --git a/drivers/hwmon/Makefile b/drivers/hwmon/Makefile
index 12a3239..30c94df 100644
--- a/drivers/hwmon/Makefile
+++ b/drivers/hwmon/Makefile
@@ -68,7 +68,6 @@
 obj-$(CONFIG_SENSORS_GL520SM)	+= gl520sm.o
 obj-$(CONFIG_SENSORS_GPIO_FAN)	+= gpio-fan.o
 obj-$(CONFIG_SENSORS_HIH6130)	+= hih6130.o
-obj-$(CONFIG_SENSORS_HTU21)	+= htu21.o
 obj-$(CONFIG_SENSORS_ULTRA45)	+= ultra45_env.o
 obj-$(CONFIG_SENSORS_I5500)	+= i5500_temp.o
 obj-$(CONFIG_SENSORS_I5K_AMB)	+= i5k_amb.o
diff --git a/drivers/hwmon/fam15h_power.c b/drivers/hwmon/fam15h_power.c
index 5f7067d..f77eb971 100644
--- a/drivers/hwmon/fam15h_power.c
+++ b/drivers/hwmon/fam15h_power.c
@@ -47,6 +47,8 @@
 
 #define MSR_F15H_CU_MAX_PWR_ACCUMULATOR	0xc001007b
 
+#define PCI_DEVICE_ID_AMD_15H_M70H_NB_F4 0x15b4
+
 struct fam15h_power_data {
 	struct pci_dev *pdev;
 	unsigned int tdp_to_watts;
@@ -124,7 +126,7 @@
 
 	if (c->x86 == 0x15 &&
 	    (c->x86_model <= 0xf ||
-	     (c->x86_model >= 0x60 && c->x86_model <= 0x6f)))
+	     (c->x86_model >= 0x60 && c->x86_model <= 0x7f)))
 		n += 1;
 
 	fam15h_power_attrs = devm_kcalloc(&pdev->dev, n,
@@ -138,7 +140,7 @@
 	fam15h_power_attrs[n++] = &dev_attr_power1_crit.attr;
 	if (c->x86 == 0x15 &&
 	    (c->x86_model <= 0xf ||
-	     (c->x86_model >= 0x60 && c->x86_model <= 0x6f)))
+	     (c->x86_model >= 0x60 && c->x86_model <= 0x7f)))
 		fam15h_power_attrs[n++] = &dev_attr_power1_input.attr;
 
 	data->group.attrs = fam15h_power_attrs;
@@ -296,6 +298,7 @@
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_15H_NB_F4) },
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_15H_M30H_NB_F4) },
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_15H_M60H_NB_F4) },
+	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_15H_M70H_NB_F4) },
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_16H_NB_F4) },
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F4) },
 	{}
diff --git a/drivers/hwmon/htu21.c b/drivers/hwmon/htu21.c
deleted file mode 100644
index 4c3bbb7..0000000
--- a/drivers/hwmon/htu21.c
+++ /dev/null
@@ -1,174 +0,0 @@
-/*
- * Measurement Specialties HTU21D humidity and temperature sensor driver
- *
- * Copyright (C) 2013 William Markezana <william.markezana@meas-spec.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- */
-
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/slab.h>
-#include <linux/i2c.h>
-#include <linux/hwmon.h>
-#include <linux/hwmon-sysfs.h>
-#include <linux/err.h>
-#include <linux/mutex.h>
-#include <linux/device.h>
-#include <linux/jiffies.h>
-
-/* HTU21 Commands */
-#define HTU21_T_MEASUREMENT_HM	0xE3
-#define HTU21_RH_MEASUREMENT_HM	0xE5
-
-struct htu21 {
-	struct i2c_client *client;
-	struct mutex lock;
-	bool valid;
-	unsigned long last_update;
-	int temperature;
-	int humidity;
-};
-
-static inline int htu21_temp_ticks_to_millicelsius(int ticks)
-{
-	ticks &= ~0x0003; /* clear status bits */
-	/*
-	 * Formula T = -46.85 + 175.72 * ST / 2^16 from datasheet p14,
-	 * optimized for integer fixed point (3 digits) arithmetic
-	 */
-	return ((21965 * ticks) >> 13) - 46850;
-}
-
-static inline int htu21_rh_ticks_to_per_cent_mille(int ticks)
-{
-	ticks &= ~0x0003; /* clear status bits */
-	/*
-	 * Formula RH = -6 + 125 * SRH / 2^16 from datasheet p14,
-	 * optimized for integer fixed point (3 digits) arithmetic
-	 */
-	return ((15625 * ticks) >> 13) - 6000;
-}
-
-static int htu21_update_measurements(struct device *dev)
-{
-	struct htu21 *htu21 = dev_get_drvdata(dev);
-	struct i2c_client *client = htu21->client;
-	int ret = 0;
-
-	mutex_lock(&htu21->lock);
-
-	if (time_after(jiffies, htu21->last_update + HZ / 2) ||
-	    !htu21->valid) {
-		ret = i2c_smbus_read_word_swapped(client,
-						  HTU21_T_MEASUREMENT_HM);
-		if (ret < 0)
-			goto out;
-		htu21->temperature = htu21_temp_ticks_to_millicelsius(ret);
-		ret = i2c_smbus_read_word_swapped(client,
-						  HTU21_RH_MEASUREMENT_HM);
-		if (ret < 0)
-			goto out;
-		htu21->humidity = htu21_rh_ticks_to_per_cent_mille(ret);
-		htu21->last_update = jiffies;
-		htu21->valid = true;
-	}
-out:
-	mutex_unlock(&htu21->lock);
-
-	return ret >= 0 ? 0 : ret;
-}
-
-static ssize_t htu21_show_temperature(struct device *dev,
-				      struct device_attribute *attr, char *buf)
-{
-	struct htu21 *htu21 = dev_get_drvdata(dev);
-	int ret;
-
-	ret = htu21_update_measurements(dev);
-	if (ret < 0)
-		return ret;
-	return sprintf(buf, "%d\n", htu21->temperature);
-}
-
-static ssize_t htu21_show_humidity(struct device *dev,
-				   struct device_attribute *attr, char *buf)
-{
-	struct htu21 *htu21 = dev_get_drvdata(dev);
-	int ret;
-
-	ret = htu21_update_measurements(dev);
-	if (ret < 0)
-		return ret;
-	return sprintf(buf, "%d\n", htu21->humidity);
-}
-
-static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO,
-			  htu21_show_temperature, NULL, 0);
-static SENSOR_DEVICE_ATTR(humidity1_input, S_IRUGO,
-			  htu21_show_humidity, NULL, 0);
-
-static struct attribute *htu21_attrs[] = {
-	&sensor_dev_attr_temp1_input.dev_attr.attr,
-	&sensor_dev_attr_humidity1_input.dev_attr.attr,
-	NULL
-};
-
-ATTRIBUTE_GROUPS(htu21);
-
-static int htu21_probe(struct i2c_client *client,
-		       const struct i2c_device_id *id)
-{
-	struct device *dev = &client->dev;
-	struct htu21 *htu21;
-	struct device *hwmon_dev;
-
-	if (!i2c_check_functionality(client->adapter,
-				     I2C_FUNC_SMBUS_READ_WORD_DATA)) {
-		dev_err(&client->dev,
-			"adapter does not support SMBus word transactions\n");
-		return -ENODEV;
-	}
-
-	htu21 = devm_kzalloc(dev, sizeof(*htu21), GFP_KERNEL);
-	if (!htu21)
-		return -ENOMEM;
-
-	htu21->client = client;
-	mutex_init(&htu21->lock);
-
-	hwmon_dev = devm_hwmon_device_register_with_groups(dev, client->name,
-							   htu21,
-							   htu21_groups);
-	return PTR_ERR_OR_ZERO(hwmon_dev);
-}
-
-static const struct i2c_device_id htu21_id[] = {
-	{ "htu21", 0 },
-	{ }
-};
-MODULE_DEVICE_TABLE(i2c, htu21_id);
-
-static struct i2c_driver htu21_driver = {
-	.class = I2C_CLASS_HWMON,
-	.driver = {
-		.name	= "htu21",
-	},
-	.probe       = htu21_probe,
-	.id_table    = htu21_id,
-};
-
-module_i2c_driver(htu21_driver);
-
-MODULE_AUTHOR("William Markezana <william.markezana@meas-spec.com>");
-MODULE_DESCRIPTION("MEAS HTU21D humidity and temperature sensor driver");
-MODULE_LICENSE("GPL");
diff --git a/drivers/hwmon/ibmaem.c b/drivers/hwmon/ibmaem.c
index 7a8a6fb..1f64378 100644
--- a/drivers/hwmon/ibmaem.c
+++ b/drivers/hwmon/ibmaem.c
@@ -920,8 +920,8 @@
 
 /* Discover sensors on an AEM device */
 static int aem_register_sensors(struct aem_data *data,
-				struct aem_ro_sensor_template *ro,
-				struct aem_rw_sensor_template *rw)
+				const struct aem_ro_sensor_template *ro,
+				const struct aem_rw_sensor_template *rw)
 {
 	struct device *dev = &data->pdev->dev;
 	struct sensor_device_attribute *sensors = data->sensors;
@@ -1020,19 +1020,19 @@
 /* Sensor probe functions */
 
 /* Description of AEM1 sensors */
-static struct aem_ro_sensor_template aem1_ro_sensors[] = {
+static const struct aem_ro_sensor_template aem1_ro_sensors[] = {
 {"energy1_input",  aem_show_energy, 0},
 {"power1_average", aem_show_power,  0},
 {NULL,		   NULL,	    0},
 };
 
-static struct aem_rw_sensor_template aem1_rw_sensors[] = {
+static const struct aem_rw_sensor_template aem1_rw_sensors[] = {
 {"power1_average_interval", aem_show_power_period, aem_set_power_period, 0},
 {NULL,			    NULL,                  NULL,                 0},
 };
 
 /* Description of AEM2 sensors */
-static struct aem_ro_sensor_template aem2_ro_sensors[] = {
+static const struct aem_ro_sensor_template aem2_ro_sensors[] = {
 {"energy1_input",	  aem_show_energy,	0},
 {"energy2_input",	  aem_show_energy,	1},
 {"power1_average",	  aem_show_power,	0},
@@ -1050,7 +1050,7 @@
 {NULL,                    NULL,                 0},
 };
 
-static struct aem_rw_sensor_template aem2_rw_sensors[] = {
+static const struct aem_rw_sensor_template aem2_rw_sensors[] = {
 {"power1_average_interval", aem_show_power_period, aem_set_power_period, 0},
 {"power2_average_interval", aem_show_power_period, aem_set_power_period, 1},
 {NULL,			    NULL,                  NULL,                 0},
diff --git a/drivers/hwmon/nct6683.c b/drivers/hwmon/nct6683.c
index 37f0170..559c596 100644
--- a/drivers/hwmon/nct6683.c
+++ b/drivers/hwmon/nct6683.c
@@ -29,7 +29,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/acpi.h>
-#include <linux/dmi.h>
+#include <linux/delay.h>
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/io.h>
@@ -45,7 +45,7 @@
 
 static bool force;
 module_param(force, bool, 0);
-MODULE_PARM_DESC(force, "Set to one to enable detection on non-Intel boards");
+MODULE_PARM_DESC(force, "Set to one to enable support for unknown vendors");
 
 static const char * const nct6683_device_names[] = {
 	"nct6683",
@@ -141,6 +141,7 @@
 #define NCT6683_REG_MON(x)		(0x100 + (x) * 2)
 #define NCT6683_REG_FAN_RPM(x)		(0x140 + (x) * 2)
 #define NCT6683_REG_PWM(x)		(0x160 + (x))
+#define NCT6683_REG_PWM_WRITE(x)	(0xa28 + (x))
 
 #define NCT6683_REG_MON_STS(x)		(0x174 + (x))
 #define NCT6683_REG_IDLE(x)		(0x178 + (x))
@@ -165,8 +166,13 @@
 
 #define NCT6683_REG_FAN_MIN(x)		(0x3b8 + (x) * 2)	/* 16 bit */
 
+#define NCT6683_REG_FAN_CFG_CTRL	0xa01
+#define NCT6683_FAN_CFG_REQ		0x80
+#define NCT6683_FAN_CFG_DONE		0x40
+
 #define NCT6683_REG_CUSTOMER_ID		0x602
 #define NCT6683_CUSTOMER_ID_INTEL	0x805
+#define NCT6683_CUSTOMER_ID_MITAC	0xa0e
 
 #define NCT6683_REG_BUILD_YEAR		0x604
 #define NCT6683_REG_BUILD_MONTH		0x605
@@ -394,7 +400,8 @@
 };
 
 static struct attribute_group *
-nct6683_create_attr_group(struct device *dev, struct sensor_template_group *tg,
+nct6683_create_attr_group(struct device *dev,
+			  const struct sensor_template_group *tg,
 			  int repeat)
 {
 	struct sensor_device_attribute_2 *a2;
@@ -559,6 +566,7 @@
 			break;
 		}
 		break;
+	case NCT6683_CUSTOMER_ID_MITAC:
 	default:
 		switch (nr) {
 		default:
@@ -703,7 +711,7 @@
 	NULL
 };
 
-static struct sensor_template_group nct6683_in_template_group = {
+static const struct sensor_template_group nct6683_in_template_group = {
 	.templates = nct6683_attributes_in_template,
 	.is_visible = nct6683_in_is_visible,
 };
@@ -774,7 +782,7 @@
 	NULL
 };
 
-static struct sensor_template_group nct6683_fan_template_group = {
+static const struct sensor_template_group nct6683_fan_template_group = {
 	.templates = nct6683_attributes_fan_template,
 	.is_visible = nct6683_fan_is_visible,
 	.base = 1,
@@ -902,7 +910,7 @@
 	NULL
 };
 
-static struct sensor_template_group nct6683_temp_template_group = {
+static const struct sensor_template_group nct6683_temp_template_group = {
 	.templates = nct6683_attributes_temp_template,
 	.is_visible = nct6683_temp_is_visible,
 	.base = 1,
@@ -918,7 +926,29 @@
 	return sprintf(buf, "%d\n", data->pwm[index]);
 }
 
-SENSOR_TEMPLATE(pwm, "pwm%d", S_IRUGO, show_pwm, NULL, 0);
+static ssize_t
+store_pwm(struct device *dev, struct device_attribute *attr, const char *buf,
+	  size_t count)
+{
+	struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr);
+	struct nct6683_data *data = dev_get_drvdata(dev);
+	int index = sattr->index;
+	unsigned long val;
+
+	if (kstrtoul(buf, 10, &val) || val > 255)
+		return -EINVAL;
+
+	mutex_lock(&data->update_lock);
+	nct6683_write(data, NCT6683_REG_FAN_CFG_CTRL, NCT6683_FAN_CFG_REQ);
+	usleep_range(1000, 2000);
+	nct6683_write(data, NCT6683_REG_PWM_WRITE(index), val);
+	nct6683_write(data, NCT6683_REG_FAN_CFG_CTRL, NCT6683_FAN_CFG_DONE);
+	mutex_unlock(&data->update_lock);
+
+	return count;
+}
+
+SENSOR_TEMPLATE(pwm, "pwm%d", S_IRUGO, show_pwm, store_pwm, 0);
 
 static umode_t nct6683_pwm_is_visible(struct kobject *kobj,
 				      struct attribute *attr, int index)
@@ -930,6 +960,10 @@
 	if (!(data->have_pwm & (1 << pwm)))
 		return 0;
 
+	/* Only update pwm values for Mitac boards */
+	if (data->customer_id == NCT6683_CUSTOMER_ID_MITAC)
+		return attr->mode | S_IWUSR;
+
 	return attr->mode;
 }
 
@@ -938,7 +972,7 @@
 	NULL
 };
 
-static struct sensor_template_group nct6683_pwm_template_group = {
+static const struct sensor_template_group nct6683_pwm_template_group = {
 	.templates = nct6683_attributes_pwm_template,
 	.is_visible = nct6683_pwm_is_visible,
 	.base = 1,
@@ -1170,6 +1204,7 @@
 	struct device *hwmon_dev;
 	struct resource *res;
 	int groups = 0;
+	char build[16];
 
 	res = platform_get_resource(pdev, IORESOURCE_IO, 0);
 	if (!devm_request_region(dev, res->start, IOREGION_LENGTH, DRVNAME))
@@ -1187,6 +1222,17 @@
 
 	data->customer_id = nct6683_read16(data, NCT6683_REG_CUSTOMER_ID);
 
+	/* By default only instantiate driver if the customer ID is known */
+	switch (data->customer_id) {
+	case NCT6683_CUSTOMER_ID_INTEL:
+		break;
+	case NCT6683_CUSTOMER_ID_MITAC:
+		break;
+	default:
+		if (!force)
+			return -ENODEV;
+	}
+
 	nct6683_init_device(data);
 	nct6683_setup_fans(data);
 	nct6683_setup_sensors(data);
@@ -1230,13 +1276,22 @@
 	}
 	data->groups[groups++] = &nct6683_group_other;
 
-	dev_info(dev, "%s EC firmware version %d.%d build %02x/%02x/%02x\n",
+	if (data->customer_id == NCT6683_CUSTOMER_ID_INTEL)
+		scnprintf(build, sizeof(build), "%02x/%02x/%02x",
+			  nct6683_read(data, NCT6683_REG_BUILD_MONTH),
+			  nct6683_read(data, NCT6683_REG_BUILD_DAY),
+			  nct6683_read(data, NCT6683_REG_BUILD_YEAR));
+	else
+		scnprintf(build, sizeof(build), "%02d/%02d/%02d",
+			  nct6683_read(data, NCT6683_REG_BUILD_MONTH),
+			  nct6683_read(data, NCT6683_REG_BUILD_DAY),
+			  nct6683_read(data, NCT6683_REG_BUILD_YEAR));
+
+	dev_info(dev, "%s EC firmware version %d.%d build %s\n",
 		 nct6683_chip_names[data->kind],
 		 nct6683_read(data, NCT6683_REG_VERSION_HI),
 		 nct6683_read(data, NCT6683_REG_VERSION_LO),
-		 nct6683_read(data, NCT6683_REG_BUILD_MONTH),
-		 nct6683_read(data, NCT6683_REG_BUILD_DAY),
-		 nct6683_read(data, NCT6683_REG_BUILD_YEAR));
+		 build);
 
 	hwmon_dev = devm_hwmon_device_register_with_groups(dev,
 			nct6683_device_names[data->kind], data, data->groups);
@@ -1292,20 +1347,10 @@
 
 static int __init nct6683_find(int sioaddr, struct nct6683_sio_data *sio_data)
 {
-	const char *board_vendor;
 	int addr;
 	u16 val;
 	int err;
 
-	/*
-	 * Only run on Intel boards unless the 'force' module parameter is set
-	 */
-	if (!force) {
-		board_vendor = dmi_get_system_info(DMI_BOARD_VENDOR);
-		if (!board_vendor || strcmp(board_vendor, "Intel Corporation"))
-			return -ENODEV;
-	}
-
 	err = superio_enter(sioaddr);
 	if (err)
 		return err;
diff --git a/drivers/hwmon/nct6775.c b/drivers/hwmon/nct6775.c
index d7ebdf8..d087a8e 100644
--- a/drivers/hwmon/nct6775.c
+++ b/drivers/hwmon/nct6775.c
@@ -1045,7 +1045,8 @@
 };
 
 static struct attribute_group *
-nct6775_create_attr_group(struct device *dev, struct sensor_template_group *tg,
+nct6775_create_attr_group(struct device *dev,
+			  const struct sensor_template_group *tg,
 			  int repeat)
 {
 	struct attribute_group *group;
@@ -1827,7 +1828,7 @@
 	NULL
 };
 
-static struct sensor_template_group nct6775_in_template_group = {
+static const struct sensor_template_group nct6775_in_template_group = {
 	.templates = nct6775_attributes_in_template,
 	.is_visible = nct6775_in_is_visible,
 };
@@ -2046,7 +2047,7 @@
 	NULL
 };
 
-static struct sensor_template_group nct6775_fan_template_group = {
+static const struct sensor_template_group nct6775_fan_template_group = {
 	.templates = nct6775_attributes_fan_template,
 	.is_visible = nct6775_fan_is_visible,
 	.base = 1,
@@ -2255,7 +2256,7 @@
 	NULL
 };
 
-static struct sensor_template_group nct6775_temp_template_group = {
+static const struct sensor_template_group nct6775_temp_template_group = {
 	.templates = nct6775_attributes_temp_template,
 	.is_visible = nct6775_temp_is_visible,
 	.base = 1,
@@ -3117,7 +3118,7 @@
 	NULL
 };
 
-static struct sensor_template_group nct6775_pwm_template_group = {
+static const struct sensor_template_group nct6775_pwm_template_group = {
 	.templates = nct6775_attributes_pwm_template,
 	.is_visible = nct6775_pwm_is_visible,
 	.base = 1,
diff --git a/drivers/hwmon/pmbus/Kconfig b/drivers/hwmon/pmbus/Kconfig
index df6ebb2b..7e5cc3d 100644
--- a/drivers/hwmon/pmbus/Kconfig
+++ b/drivers/hwmon/pmbus/Kconfig
@@ -65,6 +65,16 @@
 	  If you say yes here you get regulator support for Linear
 	  Technology LTC2974, LTC2977, LTC2978, LTC3880, LTC3883, and LTM4676.
 
+config SENSORS_LTC3815
+	tristate "Linear Technologies LTC3815"
+	default n
+	help
+	  If you say yes here you get hardware monitoring support for Linear
+	  Technology LTC3815.
+
+	  This driver can also be built as a module. If so, the module will
+	  be called ltc3815.
+
 config SENSORS_MAX16064
 	tristate "Maxim MAX16064"
 	default n
diff --git a/drivers/hwmon/pmbus/Makefile b/drivers/hwmon/pmbus/Makefile
index bce046d..5621320 100644
--- a/drivers/hwmon/pmbus/Makefile
+++ b/drivers/hwmon/pmbus/Makefile
@@ -7,6 +7,7 @@
 obj-$(CONFIG_SENSORS_ADM1275)	+= adm1275.o
 obj-$(CONFIG_SENSORS_LM25066)	+= lm25066.o
 obj-$(CONFIG_SENSORS_LTC2978)	+= ltc2978.o
+obj-$(CONFIG_SENSORS_LTC3815)	+= ltc3815.o
 obj-$(CONFIG_SENSORS_MAX16064)	+= max16064.o
 obj-$(CONFIG_SENSORS_MAX20751)	+= max20751.o
 obj-$(CONFIG_SENSORS_MAX34440)	+= max34440.o
diff --git a/drivers/hwmon/pmbus/ltc3815.c b/drivers/hwmon/pmbus/ltc3815.c
new file mode 100644
index 0000000..bb32e62
--- /dev/null
+++ b/drivers/hwmon/pmbus/ltc3815.c
@@ -0,0 +1,215 @@
+/*
+ * Hardware monitoring driver for LTC3815
+ *
+ * Copyright (c) 2015 Linear Technology
+ * Copyright (c) 2015 Guenter Roeck
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/err.h>
+#include <linux/i2c.h>
+#include <linux/init.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include "pmbus.h"
+
+#define LTC3815_MFR_IOUT_PEAK	0xd7
+#define LTC3815_MFR_VOUT_PEAK	0xdd
+#define LTC3815_MFR_VIN_PEAK	0xde
+#define LTC3815_MFR_TEMP_PEAK	0xdf
+#define LTC3815_MFR_IIN_PEAK	0xe1
+#define LTC3815_MFR_SPECIAL_ID	0xe7
+
+#define LTC3815_ID		0x8000
+#define LTC3815_ID_MASK		0xff00
+
+static int ltc3815_read_byte_data(struct i2c_client *client, int page, int reg)
+{
+	int ret;
+
+	switch (reg) {
+	case PMBUS_VOUT_MODE:
+		/*
+		 * The chip returns 0x3e, suggesting VID mode with manufacturer
+		 * specific VID codes. Since the output voltage is reported
+		 * with a LSB of 0.5mV, override and report direct mode with
+		 * appropriate coefficients.
+		 */
+		ret = 0x40;
+		break;
+	default:
+		ret = -ENODATA;
+		break;
+	}
+	return ret;
+}
+
+static int ltc3815_write_byte(struct i2c_client *client, int page, u8 reg)
+{
+	int ret;
+
+	switch (reg) {
+	case PMBUS_CLEAR_FAULTS:
+		/*
+		 * LTC3815 does not support the CLEAR_FAULTS command.
+		 * Emulate it by clearing the status register.
+		 */
+		ret = pmbus_read_word_data(client, 0, PMBUS_STATUS_WORD);
+		if (ret > 0) {
+			pmbus_write_word_data(client, 0, PMBUS_STATUS_WORD,
+					      ret);
+			ret = 0;
+		}
+		break;
+	default:
+		ret = -ENODATA;
+		break;
+	}
+	return ret;
+}
+
+static int ltc3815_read_word_data(struct i2c_client *client, int page, int reg)
+{
+	int ret;
+
+	switch (reg) {
+	case PMBUS_VIRT_READ_VIN_MAX:
+		ret = pmbus_read_word_data(client, page, LTC3815_MFR_VIN_PEAK);
+		break;
+	case PMBUS_VIRT_READ_VOUT_MAX:
+		ret = pmbus_read_word_data(client, page, LTC3815_MFR_VOUT_PEAK);
+		break;
+	case PMBUS_VIRT_READ_TEMP_MAX:
+		ret = pmbus_read_word_data(client, page, LTC3815_MFR_TEMP_PEAK);
+		break;
+	case PMBUS_VIRT_READ_IOUT_MAX:
+		ret = pmbus_read_word_data(client, page, LTC3815_MFR_IOUT_PEAK);
+		break;
+	case PMBUS_VIRT_READ_IIN_MAX:
+		ret = pmbus_read_word_data(client, page, LTC3815_MFR_IIN_PEAK);
+		break;
+	case PMBUS_VIRT_RESET_VOUT_HISTORY:
+	case PMBUS_VIRT_RESET_VIN_HISTORY:
+	case PMBUS_VIRT_RESET_TEMP_HISTORY:
+	case PMBUS_VIRT_RESET_IOUT_HISTORY:
+	case PMBUS_VIRT_RESET_IIN_HISTORY:
+		ret = 0;
+		break;
+	default:
+		ret = -ENODATA;
+		break;
+	}
+	return ret;
+}
+
+static int ltc3815_write_word_data(struct i2c_client *client, int page,
+				   int reg, u16 word)
+{
+	int ret;
+
+	switch (reg) {
+	case PMBUS_VIRT_RESET_IIN_HISTORY:
+		ret = pmbus_write_word_data(client, page,
+					    LTC3815_MFR_IIN_PEAK, 0);
+		break;
+	case PMBUS_VIRT_RESET_IOUT_HISTORY:
+		ret = pmbus_write_word_data(client, page,
+					    LTC3815_MFR_IOUT_PEAK, 0);
+		break;
+	case PMBUS_VIRT_RESET_VOUT_HISTORY:
+		ret = pmbus_write_word_data(client, page,
+					    LTC3815_MFR_VOUT_PEAK, 0);
+		break;
+	case PMBUS_VIRT_RESET_VIN_HISTORY:
+		ret = pmbus_write_word_data(client, page,
+					    LTC3815_MFR_VIN_PEAK, 0);
+		break;
+	case PMBUS_VIRT_RESET_TEMP_HISTORY:
+		ret = pmbus_write_word_data(client, page,
+					    LTC3815_MFR_TEMP_PEAK, 0);
+		break;
+	default:
+		ret = -ENODATA;
+		break;
+	}
+	return ret;
+}
+
+static const struct i2c_device_id ltc3815_id[] = {
+	{"ltc3815", 0},
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, ltc3815_id);
+
+static struct pmbus_driver_info ltc3815_info = {
+	.pages = 1,
+	.format[PSC_VOLTAGE_IN] = direct,
+	.format[PSC_VOLTAGE_OUT] = direct,
+	.format[PSC_CURRENT_IN] = direct,
+	.format[PSC_CURRENT_OUT] = direct,
+	.format[PSC_TEMPERATURE] = direct,
+	.m[PSC_VOLTAGE_IN] = 250,
+	.b[PSC_VOLTAGE_IN] = 0,
+	.R[PSC_VOLTAGE_IN] = 0,
+	.m[PSC_VOLTAGE_OUT] = 2,
+	.b[PSC_VOLTAGE_OUT] = 0,
+	.R[PSC_VOLTAGE_OUT] = 3,
+	.m[PSC_CURRENT_IN] = 1,
+	.b[PSC_CURRENT_IN] = 0,
+	.R[PSC_CURRENT_IN] = 2,
+	.m[PSC_CURRENT_OUT] = 1,
+	.b[PSC_CURRENT_OUT] = 0,
+	.R[PSC_CURRENT_OUT] = 2,
+	.m[PSC_TEMPERATURE] = 1,
+	.b[PSC_TEMPERATURE] = 0,
+	.R[PSC_TEMPERATURE] = 0,
+	.func[0] = PMBUS_HAVE_VIN | PMBUS_HAVE_IIN | PMBUS_HAVE_VOUT |
+		PMBUS_HAVE_IOUT | PMBUS_HAVE_TEMP,
+	.read_byte_data = ltc3815_read_byte_data,
+	.read_word_data = ltc3815_read_word_data,
+	.write_byte = ltc3815_write_byte,
+	.write_word_data = ltc3815_write_word_data,
+};
+
+static int ltc3815_probe(struct i2c_client *client,
+			 const struct i2c_device_id *id)
+{
+	int chip_id;
+
+	if (!i2c_check_functionality(client->adapter,
+				     I2C_FUNC_SMBUS_READ_WORD_DATA))
+		return -ENODEV;
+
+	chip_id = i2c_smbus_read_word_data(client, LTC3815_MFR_SPECIAL_ID);
+	if (chip_id < 0)
+		return chip_id;
+	if ((chip_id & LTC3815_ID_MASK) != LTC3815_ID)
+		return -ENODEV;
+
+	return pmbus_do_probe(client, id, &ltc3815_info);
+}
+
+static struct i2c_driver ltc3815_driver = {
+	.driver = {
+		   .name = "ltc3815",
+		   },
+	.probe = ltc3815_probe,
+	.remove = pmbus_do_remove,
+	.id_table = ltc3815_id,
+};
+
+module_i2c_driver(ltc3815_driver);
+
+MODULE_AUTHOR("Guenter Roeck");
+MODULE_DESCRIPTION("PMBus driver for LTC3815");
+MODULE_LICENSE("GPL");
diff --git a/drivers/input/touchscreen/sur40.c b/drivers/input/touchscreen/sur40.c
index d214f22..b6c4d03 100644
--- a/drivers/input/touchscreen/sur40.c
+++ b/drivers/input/touchscreen/sur40.c
@@ -444,7 +444,7 @@
 		goto err_poll;
 
 	/* mark as finished */
-	v4l2_get_timestamp(&new_buf->vb.timestamp);
+	new_buf->vb.vb2_buf.timestamp = ktime_get_ns();
 	new_buf->vb.sequence = sur40->sequence++;
 	new_buf->vb.field = V4L2_FIELD_NONE;
 	vb2_buffer_done(&new_buf->vb.vb2_buf, VB2_BUF_STATE_DONE);
@@ -644,22 +644,21 @@
  * minimum number: many DMA engines need a minimum of 2 buffers in the
  * queue and you need to have another available for userspace processing.
  */
-static int sur40_queue_setup(struct vb2_queue *q, const void *parg,
+static int sur40_queue_setup(struct vb2_queue *q,
 		       unsigned int *nbuffers, unsigned int *nplanes,
 		       unsigned int sizes[], void *alloc_ctxs[])
 {
-	const struct v4l2_format *fmt = parg;
 	struct sur40_state *sur40 = vb2_get_drv_priv(q);
 
 	if (q->num_buffers + *nbuffers < 3)
 		*nbuffers = 3 - q->num_buffers;
+	alloc_ctxs[0] = sur40->alloc_ctx;
 
-	if (fmt && fmt->fmt.pix.sizeimage < sur40_video_format.sizeimage)
-		return -EINVAL;
+	if (*nplanes)
+		return sizes[0] < sur40_video_format.sizeimage ? -EINVAL : 0;
 
 	*nplanes = 1;
-	sizes[0] = fmt ? fmt->fmt.pix.sizeimage : sur40_video_format.sizeimage;
-	alloc_ctxs[0] = sur40->alloc_ctx;
+	sizes[0] = sur40_video_format.sizeimage;
 
 	return 0;
 }
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 3a20db4..72d6182 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -21,10 +21,13 @@
 
 #include <linux/device.h>
 #include <linux/dma-iommu.h>
+#include <linux/gfp.h>
 #include <linux/huge_mm.h>
 #include <linux/iommu.h>
 #include <linux/iova.h>
 #include <linux/mm.h>
+#include <linux/scatterlist.h>
+#include <linux/vmalloc.h>
 
 int iommu_dma_init(void)
 {
@@ -191,6 +194,7 @@
 {
 	struct page **pages;
 	unsigned int i = 0, array_size = count * sizeof(*pages);
+	unsigned int order = MAX_ORDER;
 
 	if (array_size <= PAGE_SIZE)
 		pages = kzalloc(array_size, GFP_KERNEL);
@@ -204,14 +208,15 @@
 
 	while (count) {
 		struct page *page = NULL;
-		int j, order = __fls(count);
+		int j;
 
 		/*
 		 * Higher-order allocations are a convenience rather
 		 * than a necessity, hence using __GFP_NORETRY until
 		 * falling back to single-page allocations.
 		 */
-		for (order = min(order, MAX_ORDER); order > 0; order--) {
+		for (order = min_t(unsigned int, order, __fls(count));
+		     order > 0; order--) {
 			page = alloc_pages(gfp | __GFP_NORETRY, order);
 			if (!page)
 				continue;
@@ -453,7 +458,7 @@
 		size_t s_offset = iova_offset(iovad, s->offset);
 		size_t s_length = s->length;
 
-		sg_dma_address(s) = s->offset;
+		sg_dma_address(s) = s_offset;
 		sg_dma_len(s) = s_length;
 		s->offset -= s_offset;
 		s_length = iova_align(iovad, s_length + s_offset);
diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c
index 1fae188..c12ba45 100644
--- a/drivers/iommu/intel_irq_remapping.c
+++ b/drivers/iommu/intel_irq_remapping.c
@@ -753,7 +753,7 @@
 		 * should have X86_FEATURE_CX16 support, this has been confirmed
 		 * with Intel hardware guys.
 		 */
-		if ( cpu_has_cx16 )
+		if (boot_cpu_has(X86_FEATURE_CX16))
 			intel_irq_remap_ops.capability |= 1 << IRQ_POSTING_CAP;
 
 		for_each_iommu(iommu, drhd)
diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
index 8cf605fa..dfb868e 100644
--- a/drivers/iommu/ipmmu-vmsa.c
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -295,7 +295,7 @@
 
 static int ipmmu_domain_init_context(struct ipmmu_vmsa_domain *domain)
 {
-	phys_addr_t ttbr;
+	u64 ttbr;
 
 	/*
 	 * Allocate the page table operations.
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index 4d7294e..11fc2a2 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -8,6 +8,11 @@
 	select IRQ_DOMAIN_HIERARCHY
 	select MULTI_IRQ_HANDLER
 
+config ARM_GIC_MAX_NR
+	int
+	default 2 if ARCH_REALVIEW
+	default 1
+
 config ARM_GIC_V2M
 	bool
 	depends on ARM_GIC
@@ -27,6 +32,14 @@
 	bool
 	select PCI_MSI_IRQ_DOMAIN
 
+config HISILICON_IRQ_MBIGEN
+	bool "Support mbigen interrupt controller"
+	default n
+	depends on ARM_GIC_V3 && ARM_GIC_V3_ITS && GENERIC_MSI_IRQ_DOMAIN
+	help
+	 Enable the mbigen interrupt controller used on
+	 Hisilicon platform.
+
 config ARM_NVIC
 	bool
 	select IRQ_DOMAIN
@@ -138,6 +151,12 @@
 	select IRQ_DOMAIN
 	select GENERIC_IRQ_CHIP
 
+config TS4800_IRQ
+	tristate "TS-4800 IRQ controller"
+	select IRQ_DOMAIN
+	help
+	  Support for the TS-4800 FPGA IRQ controller
+
 config VERSATILE_FPGA_IRQ
 	bool
 	select IRQ_DOMAIN
diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile
index 177f78f..d4c2e4e 100644
--- a/drivers/irqchip/Makefile
+++ b/drivers/irqchip/Makefile
@@ -21,9 +21,11 @@
 obj-$(CONFIG_ARCH_SUNXI)		+= irq-sunxi-nmi.o
 obj-$(CONFIG_ARCH_SPEAR3XX)		+= spear-shirq.o
 obj-$(CONFIG_ARM_GIC)			+= irq-gic.o irq-gic-common.o
+obj-$(CONFIG_REALVIEW_DT)		+= irq-gic-realview.o
 obj-$(CONFIG_ARM_GIC_V2M)		+= irq-gic-v2m.o
 obj-$(CONFIG_ARM_GIC_V3)		+= irq-gic-v3.o irq-gic-common.o
 obj-$(CONFIG_ARM_GIC_V3_ITS)		+= irq-gic-v3-its.o irq-gic-v3-its-pci-msi.o irq-gic-v3-its-platform-msi.o
+obj-$(CONFIG_HISILICON_IRQ_MBIGEN)	+= irq-mbigen.o
 obj-$(CONFIG_ARM_NVIC)			+= irq-nvic.o
 obj-$(CONFIG_ARM_VIC)			+= irq-vic.o
 obj-$(CONFIG_ATMEL_AIC_IRQ)		+= irq-atmel-aic-common.o irq-atmel-aic.o
@@ -39,6 +41,7 @@
 obj-$(CONFIG_ARCH_VT8500)		+= irq-vt8500.o
 obj-$(CONFIG_ST_IRQCHIP)		+= irq-st.o
 obj-$(CONFIG_TB10X_IRQC)		+= irq-tb10x.o
+obj-$(CONFIG_TS4800_IRQ)		+= irq-ts4800.o
 obj-$(CONFIG_XTENSA)			+= irq-xtensa-pic.o
 obj-$(CONFIG_XTENSA_MX)			+= irq-xtensa-mx.o
 obj-$(CONFIG_IRQ_CROSSBAR)		+= irq-crossbar.o
diff --git a/drivers/irqchip/irq-bcm2836.c b/drivers/irqchip/irq-bcm2836.c
index f687082..963065a 100644
--- a/drivers/irqchip/irq-bcm2836.c
+++ b/drivers/irqchip/irq-bcm2836.c
@@ -21,6 +21,9 @@
 #include <linux/irqdomain.h>
 #include <asm/exception.h>
 
+#define LOCAL_CONTROL			0x000
+#define LOCAL_PRESCALER			0x008
+
 /*
  * The low 2 bits identify the CPU that the GPU IRQ goes to, and the
  * next 2 bits identify the CPU that the GPU FIQ goes to.
@@ -50,14 +53,16 @@
 /* Same status bits as above, but for FIQ. */
 #define LOCAL_FIQ_PENDING0		0x070
 /*
- * Mailbox0 write-to-set bits.  There are 16 mailboxes, 4 per CPU, and
+ * Mailbox write-to-set bits.  There are 16 mailboxes, 4 per CPU, and
  * these bits are organized by mailbox number and then CPU number.  We
  * use mailbox 0 for IPIs.  The mailbox's interrupt is raised while
  * any bit is set.
  */
 #define LOCAL_MAILBOX0_SET0		0x080
-/* Mailbox0 write-to-clear bits. */
+#define LOCAL_MAILBOX3_SET0		0x08c
+/* Mailbox write-to-clear bits. */
 #define LOCAL_MAILBOX0_CLR0		0x0c0
+#define LOCAL_MAILBOX3_CLR0		0x0cc
 
 #define LOCAL_IRQ_CNTPSIRQ	0
 #define LOCAL_IRQ_CNTPNSIRQ	1
@@ -162,7 +167,7 @@
 	u32 stat;
 
 	stat = readl_relaxed(intc.base + LOCAL_IRQ_PENDING0 + 4 * cpu);
-	if (stat & 0x10) {
+	if (stat & BIT(LOCAL_IRQ_MAILBOX0)) {
 #ifdef CONFIG_SMP
 		void __iomem *mailbox0 = (intc.base +
 					  LOCAL_MAILBOX0_CLR0 + 16 * cpu);
@@ -172,7 +177,7 @@
 		writel(1 << ipi, mailbox0);
 		handle_IPI(ipi, regs);
 #endif
-	} else {
+	} else if (stat) {
 		u32 hwirq = ffs(stat) - 1;
 
 		handle_IRQ(irq_linear_revmap(intc.domain, hwirq), regs);
@@ -217,6 +222,24 @@
 	.notifier_call = bcm2836_arm_irqchip_cpu_notify,
 	.priority = 100,
 };
+
+int __init bcm2836_smp_boot_secondary(unsigned int cpu,
+				      struct task_struct *idle)
+{
+	unsigned long secondary_startup_phys =
+		(unsigned long)virt_to_phys((void *)secondary_startup);
+
+	dsb();
+	writel(secondary_startup_phys,
+	       intc.base + LOCAL_MAILBOX3_SET0 + 16 * cpu);
+
+	return 0;
+}
+
+static const struct smp_operations bcm2836_smp_ops __initconst = {
+	.smp_boot_secondary	= bcm2836_smp_boot_secondary,
+};
+
 #endif
 
 static const struct irq_domain_ops bcm2836_arm_irqchip_intc_ops = {
@@ -234,9 +257,31 @@
 	register_cpu_notifier(&bcm2836_arm_irqchip_cpu_notifier);
 
 	set_smp_cross_call(bcm2836_arm_irqchip_send_ipi);
+	smp_set_ops(&bcm2836_smp_ops);
 #endif
 }
 
+/*
+ * The LOCAL_IRQ_CNT* timer firings are based off of the external
+ * oscillator with some scaling.  The firmware sets up CNTFRQ to
+ * report 19.2Mhz, but doesn't set up the scaling registers.
+ */
+static void bcm2835_init_local_timer_frequency(void)
+{
+	/*
+	 * Set the timer to source from the 19.2Mhz crystal clock (bit
+	 * 8 unset), and only increment by 1 instead of 2 (bit 9
+	 * unset).
+	 */
+	writel(0, intc.base + LOCAL_CONTROL);
+
+	/*
+	 * Set the timer prescaler to 1:1 (timer freq = input freq *
+	 * 2**31 / prescaler)
+	 */
+	writel(0x80000000, intc.base + LOCAL_PRESCALER);
+}
+
 static int __init bcm2836_arm_irqchip_l1_intc_of_init(struct device_node *node,
 						      struct device_node *parent)
 {
@@ -246,6 +291,8 @@
 			node->full_name);
 	}
 
+	bcm2835_init_local_timer_frequency();
+
 	intc.domain = irq_domain_add_linear(node, LAST_IRQ + 1,
 					    &bcm2836_arm_irqchip_intc_ops,
 					    NULL);
diff --git a/drivers/irqchip/irq-gic-realview.c b/drivers/irqchip/irq-gic-realview.c
new file mode 100644
index 0000000..aa46eb2
--- /dev/null
+++ b/drivers/irqchip/irq-gic-realview.c
@@ -0,0 +1,43 @@
+/*
+ * Special GIC quirks for the ARM RealView
+ * Copyright (C) 2015 Linus Walleij
+ */
+#include <linux/of.h>
+#include <linux/regmap.h>
+#include <linux/mfd/syscon.h>
+#include <linux/bitops.h>
+#include <linux/irqchip.h>
+#include <linux/irqchip/arm-gic.h>
+
+#define REALVIEW_SYS_LOCK_OFFSET	0x20
+#define REALVIEW_PB11MP_SYS_PLD_CTRL1	0x74
+#define VERSATILE_LOCK_VAL		0xA05F
+#define PLD_INTMODE_MASK		BIT(22)|BIT(23)|BIT(24)
+#define PLD_INTMODE_LEGACY		0x0
+#define PLD_INTMODE_NEW_DCC		BIT(22)
+#define PLD_INTMODE_NEW_NO_DCC		BIT(23)
+#define PLD_INTMODE_FIQ_ENABLE		BIT(24)
+
+static int __init
+realview_gic_of_init(struct device_node *node, struct device_node *parent)
+{
+	static struct regmap *map;
+
+	/* The PB11MPCore GIC needs to be configured in the syscon */
+	map = syscon_regmap_lookup_by_compatible("arm,realview-pb11mp-syscon");
+	if (!IS_ERR(map)) {
+		/* new irq mode with no DCC */
+		regmap_write(map, REALVIEW_SYS_LOCK_OFFSET,
+			     VERSATILE_LOCK_VAL);
+		regmap_update_bits(map, REALVIEW_PB11MP_SYS_PLD_CTRL1,
+				   PLD_INTMODE_NEW_NO_DCC,
+				   PLD_INTMODE_MASK);
+		regmap_write(map, REALVIEW_SYS_LOCK_OFFSET, 0x0000);
+		pr_info("TC11MP GIC: set up interrupt controller to NEW mode, no DCC\n");
+	} else {
+		pr_err("TC11MP GIC setup: could not find syscon\n");
+		return -ENXIO;
+	}
+	return gic_of_init(node, parent);
+}
+IRQCHIP_DECLARE(armtc11mp_gic, "arm,tc11mp-gic", realview_gic_of_init);
diff --git a/drivers/irqchip/irq-gic-v2m.c b/drivers/irqchip/irq-gic-v2m.c
index 87f8d10..c779f83 100644
--- a/drivers/irqchip/irq-gic-v2m.c
+++ b/drivers/irqchip/irq-gic-v2m.c
@@ -15,9 +15,11 @@
 
 #define pr_fmt(fmt) "GICv2m: " fmt
 
+#include <linux/acpi.h>
 #include <linux/irq.h>
 #include <linux/irqdomain.h>
 #include <linux/kernel.h>
+#include <linux/msi.h>
 #include <linux/of_address.h>
 #include <linux/of_pci.h>
 #include <linux/slab.h>
@@ -55,7 +57,7 @@
 
 struct v2m_data {
 	struct list_head entry;
-	struct device_node *node;
+	struct fwnode_handle *fwnode;
 	struct resource res;	/* GICv2m resource */
 	void __iomem *base;	/* GICv2m virt address */
 	u32 spi_start;		/* The SPI number that MSIs start */
@@ -138,6 +140,11 @@
 		fwspec.param[0] = 0;
 		fwspec.param[1] = hwirq - 32;
 		fwspec.param[2] = IRQ_TYPE_EDGE_RISING;
+	} else if (is_fwnode_irqchip(domain->parent->fwnode)) {
+		fwspec.fwnode = domain->parent->fwnode;
+		fwspec.param_count = 2;
+		fwspec.param[0] = hwirq;
+		fwspec.param[1] = IRQ_TYPE_EDGE_RISING;
 	} else {
 		return -EINVAL;
 	}
@@ -254,7 +261,9 @@
 		list_del(&v2m->entry);
 		kfree(v2m->bm);
 		iounmap(v2m->base);
-		of_node_put(v2m->node);
+		of_node_put(to_of_node(v2m->fwnode));
+		if (is_fwnode_irqchip(v2m->fwnode))
+			irq_domain_free_fwnode(v2m->fwnode);
 		kfree(v2m);
 	}
 }
@@ -268,7 +277,7 @@
 	if (!v2m)
 		return 0;
 
-	inner_domain = irq_domain_create_tree(of_node_to_fwnode(v2m->node),
+	inner_domain = irq_domain_create_tree(v2m->fwnode,
 					      &gicv2m_domain_ops, v2m);
 	if (!inner_domain) {
 		pr_err("Failed to create GICv2m domain\n");
@@ -277,10 +286,10 @@
 
 	inner_domain->bus_token = DOMAIN_BUS_NEXUS;
 	inner_domain->parent = parent;
-	pci_domain = pci_msi_create_irq_domain(of_node_to_fwnode(v2m->node),
+	pci_domain = pci_msi_create_irq_domain(v2m->fwnode,
 					       &gicv2m_msi_domain_info,
 					       inner_domain);
-	plat_domain = platform_msi_create_irq_domain(of_node_to_fwnode(v2m->node),
+	plat_domain = platform_msi_create_irq_domain(v2m->fwnode,
 						     &gicv2m_pmsi_domain_info,
 						     inner_domain);
 	if (!pci_domain || !plat_domain) {
@@ -296,8 +305,9 @@
 	return 0;
 }
 
-static int __init gicv2m_init_one(struct device_node *node,
-				  struct irq_domain *parent)
+static int __init gicv2m_init_one(struct fwnode_handle *fwnode,
+				  u32 spi_start, u32 nr_spis,
+				  struct resource *res)
 {
 	int ret;
 	struct v2m_data *v2m;
@@ -309,13 +319,9 @@
 	}
 
 	INIT_LIST_HEAD(&v2m->entry);
-	v2m->node = node;
+	v2m->fwnode = fwnode;
 
-	ret = of_address_to_resource(node, 0, &v2m->res);
-	if (ret) {
-		pr_err("Failed to allocate v2m resource.\n");
-		goto err_free_v2m;
-	}
+	memcpy(&v2m->res, res, sizeof(struct resource));
 
 	v2m->base = ioremap(v2m->res.start, resource_size(&v2m->res));
 	if (!v2m->base) {
@@ -324,10 +330,9 @@
 		goto err_free_v2m;
 	}
 
-	if (!of_property_read_u32(node, "arm,msi-base-spi", &v2m->spi_start) &&
-	    !of_property_read_u32(node, "arm,msi-num-spis", &v2m->nr_spis)) {
-		pr_info("Overriding V2M MSI_TYPER (base:%u, num:%u)\n",
-			v2m->spi_start, v2m->nr_spis);
+	if (spi_start && nr_spis) {
+		v2m->spi_start = spi_start;
+		v2m->nr_spis = nr_spis;
 	} else {
 		u32 typer = readl_relaxed(v2m->base + V2M_MSI_TYPER);
 
@@ -359,10 +364,9 @@
 	}
 
 	list_add_tail(&v2m->entry, &v2m_nodes);
-	pr_info("Node %s: range[%#lx:%#lx], SPI[%d:%d]\n", node->name,
-		(unsigned long)v2m->res.start, (unsigned long)v2m->res.end,
-		v2m->spi_start, (v2m->spi_start + v2m->nr_spis));
 
+	pr_info("range%pR, SPI[%d:%d]\n", res,
+		v2m->spi_start, (v2m->spi_start + v2m->nr_spis - 1));
 	return 0;
 
 err_iounmap:
@@ -377,19 +381,36 @@
 	{},
 };
 
-int __init gicv2m_of_init(struct device_node *node, struct irq_domain *parent)
+static int __init gicv2m_of_init(struct fwnode_handle *parent_handle,
+				 struct irq_domain *parent)
 {
 	int ret = 0;
+	struct device_node *node = to_of_node(parent_handle);
 	struct device_node *child;
 
 	for (child = of_find_matching_node(node, gicv2m_device_id); child;
 	     child = of_find_matching_node(child, gicv2m_device_id)) {
+		u32 spi_start = 0, nr_spis = 0;
+		struct resource res;
+
 		if (!of_find_property(child, "msi-controller", NULL))
 			continue;
 
-		ret = gicv2m_init_one(child, parent);
+		ret = of_address_to_resource(child, 0, &res);
 		if (ret) {
-			of_node_put(node);
+			pr_err("Failed to allocate v2m resource.\n");
+			break;
+		}
+
+		if (!of_property_read_u32(child, "arm,msi-base-spi",
+					  &spi_start) &&
+		    !of_property_read_u32(child, "arm,msi-num-spis", &nr_spis))
+			pr_info("DT overriding V2M MSI_TYPER (base:%u, num:%u)\n",
+				spi_start, nr_spis);
+
+		ret = gicv2m_init_one(&child->fwnode, spi_start, nr_spis, &res);
+		if (ret) {
+			of_node_put(child);
 			break;
 		}
 	}
@@ -400,3 +421,101 @@
 		gicv2m_teardown();
 	return ret;
 }
+
+#ifdef CONFIG_ACPI
+static int acpi_num_msi;
+
+static struct fwnode_handle *gicv2m_get_fwnode(struct device *dev)
+{
+	struct v2m_data *data;
+
+	if (WARN_ON(acpi_num_msi <= 0))
+		return NULL;
+
+	/* We only return the fwnode of the first MSI frame. */
+	data = list_first_entry_or_null(&v2m_nodes, struct v2m_data, entry);
+	if (!data)
+		return NULL;
+
+	return data->fwnode;
+}
+
+static int __init
+acpi_parse_madt_msi(struct acpi_subtable_header *header,
+		    const unsigned long end)
+{
+	int ret;
+	struct resource res;
+	u32 spi_start = 0, nr_spis = 0;
+	struct acpi_madt_generic_msi_frame *m;
+	struct fwnode_handle *fwnode;
+
+	m = (struct acpi_madt_generic_msi_frame *)header;
+	if (BAD_MADT_ENTRY(m, end))
+		return -EINVAL;
+
+	res.start = m->base_address;
+	res.end = m->base_address + SZ_4K - 1;
+	res.flags = IORESOURCE_MEM;
+
+	if (m->flags & ACPI_MADT_OVERRIDE_SPI_VALUES) {
+		spi_start = m->spi_base;
+		nr_spis = m->spi_count;
+
+		pr_info("ACPI overriding V2M MSI_TYPER (base:%u, num:%u)\n",
+			spi_start, nr_spis);
+	}
+
+	fwnode = irq_domain_alloc_fwnode((void *)m->base_address);
+	if (!fwnode) {
+		pr_err("Unable to allocate GICv2m domain token\n");
+		return -EINVAL;
+	}
+
+	ret = gicv2m_init_one(fwnode, spi_start, nr_spis, &res);
+	if (ret)
+		irq_domain_free_fwnode(fwnode);
+
+	return ret;
+}
+
+static int __init gicv2m_acpi_init(struct irq_domain *parent)
+{
+	int ret;
+
+	if (acpi_num_msi > 0)
+		return 0;
+
+	acpi_num_msi = acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_MSI_FRAME,
+				      acpi_parse_madt_msi, 0);
+
+	if (acpi_num_msi <= 0)
+		goto err_out;
+
+	ret = gicv2m_allocate_domains(parent);
+	if (ret)
+		goto err_out;
+
+	pci_msi_register_fwnode_provider(&gicv2m_get_fwnode);
+
+	return 0;
+
+err_out:
+	gicv2m_teardown();
+	return -EINVAL;
+}
+#else /* CONFIG_ACPI */
+static int __init gicv2m_acpi_init(struct irq_domain *parent)
+{
+	return -EINVAL;
+}
+#endif /* CONFIG_ACPI */
+
+int __init gicv2m_init(struct fwnode_handle *parent_handle,
+		       struct irq_domain *parent)
+{
+	if (is_of_node(parent_handle))
+		return gicv2m_of_init(parent_handle, parent);
+
+	return gicv2m_acpi_init(parent);
+}
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index abf2ffa..911758c 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -69,6 +69,7 @@
 };
 
 struct gic_chip_data {
+	struct irq_chip chip;
 	union gic_base dist_base;
 	union gic_base cpu_base;
 #ifdef CONFIG_CPU_PM
@@ -99,11 +100,7 @@
 
 static struct static_key supports_deactivate = STATIC_KEY_INIT_TRUE;
 
-#ifndef MAX_GIC_NR
-#define MAX_GIC_NR	1
-#endif
-
-static struct gic_chip_data gic_data[MAX_GIC_NR] __read_mostly;
+static struct gic_chip_data gic_data[CONFIG_ARM_GIC_MAX_NR] __read_mostly;
 
 #ifdef CONFIG_GIC_NON_BANKED
 static void __iomem *gic_get_percpu_base(union gic_base *base)
@@ -336,7 +333,7 @@
 		irqstat = readl_relaxed(cpu_base + GIC_CPU_INTACK);
 		irqnr = irqstat & GICC_IAR_INT_ID_MASK;
 
-		if (likely(irqnr > 15 && irqnr < 1021)) {
+		if (likely(irqnr > 15 && irqnr < 1020)) {
 			if (static_key_true(&supports_deactivate))
 				writel_relaxed(irqstat, cpu_base + GIC_CPU_EOI);
 			handle_domain_irq(gic->domain, irqnr, regs);
@@ -383,7 +380,6 @@
 }
 
 static struct irq_chip gic_chip = {
-	.name			= "GIC",
 	.irq_mask		= gic_mask_irq,
 	.irq_unmask		= gic_unmask_irq,
 	.irq_eoi		= gic_eoi_irq,
@@ -417,8 +413,7 @@
 
 void __init gic_cascade_irq(unsigned int gic_nr, unsigned int irq)
 {
-	if (gic_nr >= MAX_GIC_NR)
-		BUG();
+	BUG_ON(gic_nr >= CONFIG_ARM_GIC_MAX_NR);
 	irq_set_chained_handler_and_data(irq, gic_handle_cascade_irq,
 					 &gic_data[gic_nr]);
 }
@@ -524,7 +519,7 @@
 	void __iomem *cpu_base;
 	u32 val = 0;
 
-	if (gic_nr >= MAX_GIC_NR)
+	if (gic_nr >= CONFIG_ARM_GIC_MAX_NR)
 		return -EINVAL;
 
 	cpu_base = gic_data_cpu_base(&gic_data[gic_nr]);
@@ -548,8 +543,7 @@
 	void __iomem *dist_base;
 	int i;
 
-	if (gic_nr >= MAX_GIC_NR)
-		BUG();
+	BUG_ON(gic_nr >= CONFIG_ARM_GIC_MAX_NR);
 
 	gic_irqs = gic_data[gic_nr].gic_irqs;
 	dist_base = gic_data_dist_base(&gic_data[gic_nr]);
@@ -587,8 +581,7 @@
 	unsigned int i;
 	void __iomem *dist_base;
 
-	if (gic_nr >= MAX_GIC_NR)
-		BUG();
+	BUG_ON(gic_nr >= CONFIG_ARM_GIC_MAX_NR);
 
 	gic_irqs = gic_data[gic_nr].gic_irqs;
 	dist_base = gic_data_dist_base(&gic_data[gic_nr]);
@@ -634,8 +627,7 @@
 	void __iomem *dist_base;
 	void __iomem *cpu_base;
 
-	if (gic_nr >= MAX_GIC_NR)
-		BUG();
+	BUG_ON(gic_nr >= CONFIG_ARM_GIC_MAX_NR);
 
 	dist_base = gic_data_dist_base(&gic_data[gic_nr]);
 	cpu_base = gic_data_cpu_base(&gic_data[gic_nr]);
@@ -664,8 +656,7 @@
 	void __iomem *dist_base;
 	void __iomem *cpu_base;
 
-	if (gic_nr >= MAX_GIC_NR)
-		BUG();
+	BUG_ON(gic_nr >= CONFIG_ARM_GIC_MAX_NR);
 
 	dist_base = gic_data_dist_base(&gic_data[gic_nr]);
 	cpu_base = gic_data_cpu_base(&gic_data[gic_nr]);
@@ -703,7 +694,7 @@
 {
 	int i;
 
-	for (i = 0; i < MAX_GIC_NR; i++) {
+	for (i = 0; i < CONFIG_ARM_GIC_MAX_NR; i++) {
 #ifdef CONFIG_GIC_NON_BANKED
 		/* Skip over unused GICs */
 		if (!gic_data[i].get_base)
@@ -835,8 +826,7 @@
 	int i, ror_val, cpu = smp_processor_id();
 	u32 val, cur_target_mask, active_mask;
 
-	if (gic_nr >= MAX_GIC_NR)
-		BUG();
+	BUG_ON(gic_nr >= CONFIG_ARM_GIC_MAX_NR);
 
 	dist_base = gic_data_dist_base(&gic_data[gic_nr]);
 	if (!dist_base)
@@ -925,20 +915,15 @@
 static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq,
 				irq_hw_number_t hw)
 {
-	struct irq_chip *chip = &gic_chip;
-
-	if (static_key_true(&supports_deactivate)) {
-		if (d->host_data == (void *)&gic_data[0])
-			chip = &gic_eoimode1_chip;
-	}
+	struct gic_chip_data *gic = d->host_data;
 
 	if (hw < 32) {
 		irq_set_percpu_devid(irq);
-		irq_domain_set_info(d, irq, hw, chip, d->host_data,
+		irq_domain_set_info(d, irq, hw, &gic->chip, d->host_data,
 				    handle_percpu_devid_irq, NULL, NULL);
 		irq_set_status_flags(irq, IRQ_NOAUTOEN);
 	} else {
-		irq_domain_set_info(d, irq, hw, chip, d->host_data,
+		irq_domain_set_info(d, irq, hw, &gic->chip, d->host_data,
 				    handle_fasteoi_irq, NULL, NULL);
 		irq_set_probe(irq);
 	}
@@ -972,7 +957,7 @@
 		return 0;
 	}
 
-	if (fwspec->fwnode->type == FWNODE_IRQCHIP) {
+	if (is_fwnode_irqchip(fwspec->fwnode)) {
 		if(fwspec->param_count != 2)
 			return -EINVAL;
 
@@ -1040,11 +1025,20 @@
 	struct gic_chip_data *gic;
 	int gic_irqs, irq_base, i;
 
-	BUG_ON(gic_nr >= MAX_GIC_NR);
+	BUG_ON(gic_nr >= CONFIG_ARM_GIC_MAX_NR);
 
 	gic_check_cpu_features();
 
 	gic = &gic_data[gic_nr];
+
+	/* Initialize irq_chip */
+	if (static_key_true(&supports_deactivate) && gic_nr == 0) {
+		gic->chip = gic_eoimode1_chip;
+	} else {
+		gic->chip = gic_chip;
+		gic->chip.name = kasprintf(GFP_KERNEL, "GIC-%d", gic_nr);
+	}
+
 #ifdef CONFIG_GIC_NON_BANKED
 	if (percpu_offset) { /* Frankein-GIC without banked registers... */
 		unsigned int cpu;
@@ -1196,7 +1190,7 @@
 	return true;
 }
 
-static int __init
+int __init
 gic_of_init(struct device_node *node, struct device_node *parent)
 {
 	void __iomem *cpu_base;
@@ -1234,7 +1228,7 @@
 	}
 
 	if (IS_ENABLED(CONFIG_ARM_GIC_V2M))
-		gicv2m_of_init(node, gic_data[gic_cnt].domain);
+		gicv2m_init(&node->fwnode, gic_data[gic_cnt].domain);
 
 	gic_cnt++;
 	return 0;
@@ -1359,6 +1353,10 @@
 	__gic_init_bases(0, -1, dist_base, cpu_base, 0, domain_handle);
 
 	acpi_set_irq_model(ACPI_IRQ_MODEL_GIC, domain_handle);
+
+	if (IS_ENABLED(CONFIG_ARM_GIC_V2M))
+		gicv2m_init(NULL, gic_data[0].domain);
+
 	return 0;
 }
 IRQCHIP_ACPI_DECLARE(gic_v2, ACPI_MADT_TYPE_GENERIC_DISTRIBUTOR,
diff --git a/drivers/irqchip/irq-mbigen.c b/drivers/irqchip/irq-mbigen.c
new file mode 100644
index 0000000..4dd3eb8
--- /dev/null
+++ b/drivers/irqchip/irq-mbigen.c
@@ -0,0 +1,297 @@
+/*
+ * Copyright (C) 2015 Hisilicon Limited, All Rights Reserved.
+ * Author: Jun Ma <majun258@huawei.com>
+ * Author: Yun Wu <wuyun.wu@huawei.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/irqchip.h>
+#include <linux/module.h>
+#include <linux/msi.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+/* Interrupt numbers per mbigen node supported */
+#define IRQS_PER_MBIGEN_NODE		128
+
+/* 64 irqs (Pin0-pin63) are reserved for each mbigen chip */
+#define RESERVED_IRQ_PER_MBIGEN_CHIP	64
+
+/* The maximum IRQ pin number of mbigen chip(start from 0) */
+#define MAXIMUM_IRQ_PIN_NUM		1407
+
+/**
+ * In mbigen vector register
+ * bit[21:12]:	event id value
+ * bit[11:0]:	device id
+ */
+#define IRQ_EVENT_ID_SHIFT		12
+#define IRQ_EVENT_ID_MASK		0x3ff
+
+/* register range of each mbigen node */
+#define MBIGEN_NODE_OFFSET		0x1000
+
+/* offset of vector register in mbigen node */
+#define REG_MBIGEN_VEC_OFFSET		0x200
+
+/**
+ * offset of clear register in mbigen node
+ * This register is used to clear the status
+ * of interrupt
+ */
+#define REG_MBIGEN_CLEAR_OFFSET		0xa000
+
+/**
+ * offset of interrupt type register
+ * This register is used to configure interrupt
+ * trigger type
+ */
+#define REG_MBIGEN_TYPE_OFFSET		0x0
+
+/**
+ * struct mbigen_device - holds the information of mbigen device.
+ *
+ * @pdev:		pointer to the platform device structure of mbigen chip.
+ * @base:		mapped address of this mbigen chip.
+ */
+struct mbigen_device {
+	struct platform_device	*pdev;
+	void __iomem		*base;
+};
+
+static inline unsigned int get_mbigen_vec_reg(irq_hw_number_t hwirq)
+{
+	unsigned int nid, pin;
+
+	hwirq -= RESERVED_IRQ_PER_MBIGEN_CHIP;
+	nid = hwirq / IRQS_PER_MBIGEN_NODE + 1;
+	pin = hwirq % IRQS_PER_MBIGEN_NODE;
+
+	return pin * 4 + nid * MBIGEN_NODE_OFFSET
+			+ REG_MBIGEN_VEC_OFFSET;
+}
+
+static inline void get_mbigen_type_reg(irq_hw_number_t hwirq,
+					u32 *mask, u32 *addr)
+{
+	unsigned int nid, irq_ofst, ofst;
+
+	hwirq -= RESERVED_IRQ_PER_MBIGEN_CHIP;
+	nid = hwirq / IRQS_PER_MBIGEN_NODE + 1;
+	irq_ofst = hwirq % IRQS_PER_MBIGEN_NODE;
+
+	*mask = 1 << (irq_ofst % 32);
+	ofst = irq_ofst / 32 * 4;
+
+	*addr = ofst + nid * MBIGEN_NODE_OFFSET
+		+ REG_MBIGEN_TYPE_OFFSET;
+}
+
+static inline void get_mbigen_clear_reg(irq_hw_number_t hwirq,
+					u32 *mask, u32 *addr)
+{
+	unsigned int ofst;
+
+	hwirq -= RESERVED_IRQ_PER_MBIGEN_CHIP;
+	ofst = hwirq / 32 * 4;
+
+	*mask = 1 << (hwirq % 32);
+	*addr = ofst + REG_MBIGEN_CLEAR_OFFSET;
+}
+
+static void mbigen_eoi_irq(struct irq_data *data)
+{
+	void __iomem *base = data->chip_data;
+	u32 mask, addr;
+
+	get_mbigen_clear_reg(data->hwirq, &mask, &addr);
+
+	writel_relaxed(mask, base + addr);
+
+	irq_chip_eoi_parent(data);
+}
+
+static int mbigen_set_type(struct irq_data *data, unsigned int type)
+{
+	void __iomem *base = data->chip_data;
+	u32 mask, addr, val;
+
+	if (type != IRQ_TYPE_LEVEL_HIGH && type != IRQ_TYPE_EDGE_RISING)
+		return -EINVAL;
+
+	get_mbigen_type_reg(data->hwirq, &mask, &addr);
+
+	val = readl_relaxed(base + addr);
+
+	if (type == IRQ_TYPE_LEVEL_HIGH)
+		val |= mask;
+	else
+		val &= ~mask;
+
+	writel_relaxed(val, base + addr);
+
+	return 0;
+}
+
+static struct irq_chip mbigen_irq_chip = {
+	.name =			"mbigen-v2",
+	.irq_mask =		irq_chip_mask_parent,
+	.irq_unmask =		irq_chip_unmask_parent,
+	.irq_eoi =		mbigen_eoi_irq,
+	.irq_set_type =		mbigen_set_type,
+	.irq_set_affinity =	irq_chip_set_affinity_parent,
+};
+
+static void mbigen_write_msg(struct msi_desc *desc, struct msi_msg *msg)
+{
+	struct irq_data *d = irq_get_irq_data(desc->irq);
+	void __iomem *base = d->chip_data;
+	u32 val;
+
+	base += get_mbigen_vec_reg(d->hwirq);
+	val = readl_relaxed(base);
+
+	val &= ~(IRQ_EVENT_ID_MASK << IRQ_EVENT_ID_SHIFT);
+	val |= (msg->data << IRQ_EVENT_ID_SHIFT);
+
+	/* The address of doorbell is encoded in mbigen register by default
+	 * So,we don't need to program the doorbell address at here
+	 */
+	writel_relaxed(val, base);
+}
+
+static int mbigen_domain_translate(struct irq_domain *d,
+				    struct irq_fwspec *fwspec,
+				    unsigned long *hwirq,
+				    unsigned int *type)
+{
+	if (is_of_node(fwspec->fwnode)) {
+		if (fwspec->param_count != 2)
+			return -EINVAL;
+
+		if ((fwspec->param[0] > MAXIMUM_IRQ_PIN_NUM) ||
+			(fwspec->param[0] < RESERVED_IRQ_PER_MBIGEN_CHIP))
+			return -EINVAL;
+		else
+			*hwirq = fwspec->param[0];
+
+		/* If there is no valid irq type, just use the default type */
+		if ((fwspec->param[1] == IRQ_TYPE_EDGE_RISING) ||
+			(fwspec->param[1] == IRQ_TYPE_LEVEL_HIGH))
+			*type = fwspec->param[1];
+		else
+			return -EINVAL;
+
+		return 0;
+	}
+	return -EINVAL;
+}
+
+static int mbigen_irq_domain_alloc(struct irq_domain *domain,
+					unsigned int virq,
+					unsigned int nr_irqs,
+					void *args)
+{
+	struct irq_fwspec *fwspec = args;
+	irq_hw_number_t hwirq;
+	unsigned int type;
+	struct mbigen_device *mgn_chip;
+	int i, err;
+
+	err = mbigen_domain_translate(domain, fwspec, &hwirq, &type);
+	if (err)
+		return err;
+
+	err = platform_msi_domain_alloc(domain, virq, nr_irqs);
+	if (err)
+		return err;
+
+	mgn_chip = platform_msi_get_host_data(domain);
+
+	for (i = 0; i < nr_irqs; i++)
+		irq_domain_set_hwirq_and_chip(domain, virq + i, hwirq + i,
+				      &mbigen_irq_chip, mgn_chip->base);
+
+	return 0;
+}
+
+static struct irq_domain_ops mbigen_domain_ops = {
+	.translate	= mbigen_domain_translate,
+	.alloc		= mbigen_irq_domain_alloc,
+	.free		= irq_domain_free_irqs_common,
+};
+
+static int mbigen_device_probe(struct platform_device *pdev)
+{
+	struct mbigen_device *mgn_chip;
+	struct resource *res;
+	struct irq_domain *domain;
+	u32 num_pins;
+
+	mgn_chip = devm_kzalloc(&pdev->dev, sizeof(*mgn_chip), GFP_KERNEL);
+	if (!mgn_chip)
+		return -ENOMEM;
+
+	mgn_chip->pdev = pdev;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	mgn_chip->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(mgn_chip->base))
+		return PTR_ERR(mgn_chip->base);
+
+	if (of_property_read_u32(pdev->dev.of_node, "num-pins", &num_pins) < 0) {
+		dev_err(&pdev->dev, "No num-pins property\n");
+		return -EINVAL;
+	}
+
+	domain = platform_msi_create_device_domain(&pdev->dev, num_pins,
+							mbigen_write_msg,
+							&mbigen_domain_ops,
+							mgn_chip);
+
+	if (!domain)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, mgn_chip);
+
+	dev_info(&pdev->dev, "Allocated %d MSIs\n", num_pins);
+
+	return 0;
+}
+
+static const struct of_device_id mbigen_of_match[] = {
+	{ .compatible = "hisilicon,mbigen-v2" },
+	{ /* END */ }
+};
+MODULE_DEVICE_TABLE(of, mbigen_of_match);
+
+static struct platform_driver mbigen_platform_driver = {
+	.driver = {
+		.name		= "Hisilicon MBIGEN-V2",
+		.owner		= THIS_MODULE,
+		.of_match_table	= mbigen_of_match,
+	},
+	.probe			= mbigen_device_probe,
+};
+
+module_platform_driver(mbigen_platform_driver);
+
+MODULE_AUTHOR("Jun Ma <majun258@huawei.com>");
+MODULE_AUTHOR("Yun Wu <wuyun.wu@huawei.com>");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Hisilicon MBI Generator driver");
diff --git a/drivers/irqchip/irq-omap-intc.c b/drivers/irqchip/irq-omap-intc.c
index 8587d0f..9d1bcfc 100644
--- a/drivers/irqchip/irq-omap-intc.c
+++ b/drivers/irqchip/irq-omap-intc.c
@@ -47,6 +47,7 @@
 #define INTC_ILR0		0x0100
 
 #define ACTIVEIRQ_MASK		0x7f	/* omap2/3 active interrupt bits */
+#define SPURIOUSIRQ_MASK	(0x1ffffff << 7)
 #define INTCPS_NR_ILR_REGS	128
 #define INTCPS_NR_MIR_REGS	4
 
@@ -207,7 +208,6 @@
 		ct = gc->chip_types;
 
 		ct->type = IRQ_TYPE_LEVEL_MASK;
-		ct->handler = handle_level_irq;
 
 		ct->chip.irq_ack = omap_mask_ack_irq;
 		ct->chip.irq_mask = irq_gc_mask_disable_reg;
@@ -330,11 +330,35 @@
 static asmlinkage void __exception_irq_entry
 omap_intc_handle_irq(struct pt_regs *regs)
 {
+	extern unsigned long irq_err_count;
 	u32 irqnr;
 
 	irqnr = intc_readl(INTC_SIR);
+
+	/*
+	 * A spurious IRQ can result if interrupt that triggered the
+	 * sorting is no longer active during the sorting (10 INTC
+	 * functional clock cycles after interrupt assertion). Or a
+	 * change in interrupt mask affected the result during sorting
+	 * time. There is no special handling required except ignoring
+	 * the SIR register value just read and retrying.
+	 * See section 6.2.5 of AM335x TRM Literature Number: SPRUH73K
+	 *
+	 * Many a times, a spurious interrupt situation has been fixed
+	 * by adding a flush for the posted write acking the IRQ in
+	 * the device driver. Typically, this is going be the device
+	 * driver whose interrupt was handled just before the spurious
+	 * IRQ occurred. Pay attention to those device drivers if you
+	 * run into hitting the spurious IRQ condition below.
+	 */
+	if (unlikely((irqnr & SPURIOUSIRQ_MASK) == SPURIOUSIRQ_MASK)) {
+		pr_err_once("%s: spurious irq!\n", __func__);
+		irq_err_count++;
+		omap_ack_irq(NULL);
+		return;
+	}
+
 	irqnr &= ACTIVEIRQ_MASK;
-	WARN_ONCE(!irqnr, "Spurious IRQ ?\n");
 	handle_domain_irq(domain, irqnr, regs);
 }
 
diff --git a/drivers/irqchip/irq-renesas-h8300h.c b/drivers/irqchip/irq-renesas-h8300h.c
index 6fd30d5..c378768 100644
--- a/drivers/irqchip/irq-renesas-h8300h.c
+++ b/drivers/irqchip/irq-renesas-h8300h.c
@@ -21,9 +21,9 @@
 	10, 10, 10, 10,  9,  9,  9,  9,
 };
 
-static void *intc_baseaddr;
+static void __iomem *intc_baseaddr;
 
-#define IPR ((unsigned long)intc_baseaddr + 6)
+#define IPR (intc_baseaddr + 6)
 
 static void h8300h_disable_irq(struct irq_data *data)
 {
@@ -81,8 +81,8 @@
 	BUG_ON(!intc_baseaddr);
 
 	/* All interrupt priority low */
-	ctrl_outb(0x00, IPR + 0);
-	ctrl_outb(0x00, IPR + 1);
+	writeb(0x00, IPR + 0);
+	writeb(0x00, IPR + 1);
 
 	domain = irq_domain_add_linear(intc, NR_IRQS, &irq_ops, NULL);
 	BUG_ON(!domain);
diff --git a/drivers/irqchip/irq-renesas-intc-irqpin.c b/drivers/irqchip/irq-renesas-intc-irqpin.c
index c325806..713177d 100644
--- a/drivers/irqchip/irq-renesas-intc-irqpin.c
+++ b/drivers/irqchip/irq-renesas-intc-irqpin.c
@@ -31,7 +31,6 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/of_device.h>
-#include <linux/platform_data/irq-renesas-intc-irqpin.h>
 #include <linux/pm_runtime.h>
 
 #define INTC_IRQPIN_MAX 8 /* maximum 8 interrupts per driver instance */
@@ -75,18 +74,20 @@
 struct intc_irqpin_priv {
 	struct intc_irqpin_iomem iomem[INTC_IRQPIN_REG_NR];
 	struct intc_irqpin_irq irq[INTC_IRQPIN_MAX];
-	struct renesas_intc_irqpin_config config;
-	unsigned int number_of_irqs;
+	unsigned int sense_bitfield_width;
 	struct platform_device *pdev;
 	struct irq_chip irq_chip;
 	struct irq_domain *irq_domain;
 	struct clk *clk;
-	bool shared_irqs;
+	unsigned shared_irqs:1;
+	unsigned needs_clk:1;
 	u8 shared_irq_mask;
 };
 
-struct intc_irqpin_irlm_config {
+struct intc_irqpin_config {
 	unsigned int irlm_bit;
+	unsigned needs_irlm:1;
+	unsigned needs_clk:1;
 };
 
 static unsigned long intc_irqpin_read32(void __iomem *iomem)
@@ -171,7 +172,7 @@
 static int intc_irqpin_set_sense(struct intc_irqpin_priv *p, int irq, int value)
 {
 	/* The SENSE register is assumed to be 32-bit. */
-	int bitfield_width = p->config.sense_bitfield_width;
+	int bitfield_width = p->sense_bitfield_width;
 	int shift = 32 - (irq + 1) * bitfield_width;
 
 	dev_dbg(&p->pdev->dev, "sense irq = %d, mode = %d\n", irq, value);
@@ -361,8 +362,15 @@
 	.xlate  = irq_domain_xlate_twocell,
 };
 
-static const struct intc_irqpin_irlm_config intc_irqpin_irlm_r8a777x = {
+static const struct intc_irqpin_config intc_irqpin_irlm_r8a777x = {
 	.irlm_bit = 23, /* ICR0.IRLM0 */
+	.needs_irlm = 1,
+	.needs_clk = 0,
+};
+
+static const struct intc_irqpin_config intc_irqpin_rmobile = {
+	.needs_irlm = 0,
+	.needs_clk = 1,
 };
 
 static const struct of_device_id intc_irqpin_dt_ids[] = {
@@ -371,14 +379,18 @@
 	  .data = &intc_irqpin_irlm_r8a777x },
 	{ .compatible = "renesas,intc-irqpin-r8a7779",
 	  .data = &intc_irqpin_irlm_r8a777x },
+	{ .compatible = "renesas,intc-irqpin-r8a7740",
+	  .data = &intc_irqpin_rmobile },
+	{ .compatible = "renesas,intc-irqpin-sh73a0",
+	  .data = &intc_irqpin_rmobile },
 	{},
 };
 MODULE_DEVICE_TABLE(of, intc_irqpin_dt_ids);
 
 static int intc_irqpin_probe(struct platform_device *pdev)
 {
+	const struct intc_irqpin_config *config = NULL;
 	struct device *dev = &pdev->dev;
-	struct renesas_intc_irqpin_config *pdata = dev->platform_data;
 	const struct of_device_id *of_id;
 	struct intc_irqpin_priv *p;
 	struct intc_irqpin_iomem *i;
@@ -388,6 +400,8 @@
 	void (*enable_fn)(struct irq_data *d);
 	void (*disable_fn)(struct irq_data *d);
 	const char *name = dev_name(dev);
+	bool control_parent;
+	unsigned int nirqs;
 	int ref_irq;
 	int ret;
 	int k;
@@ -399,23 +413,28 @@
 	}
 
 	/* deal with driver instance configuration */
-	if (pdata) {
-		memcpy(&p->config, pdata, sizeof(*pdata));
-	} else {
-		of_property_read_u32(dev->of_node, "sense-bitfield-width",
-				     &p->config.sense_bitfield_width);
-		p->config.control_parent = of_property_read_bool(dev->of_node,
-								 "control-parent");
-	}
-	if (!p->config.sense_bitfield_width)
-		p->config.sense_bitfield_width = 4; /* default to 4 bits */
+	of_property_read_u32(dev->of_node, "sense-bitfield-width",
+			     &p->sense_bitfield_width);
+	control_parent = of_property_read_bool(dev->of_node, "control-parent");
+	if (!p->sense_bitfield_width)
+		p->sense_bitfield_width = 4; /* default to 4 bits */
 
 	p->pdev = pdev;
 	platform_set_drvdata(pdev, p);
 
+	of_id = of_match_device(intc_irqpin_dt_ids, dev);
+	if (of_id && of_id->data) {
+		config = of_id->data;
+		p->needs_clk = config->needs_clk;
+	}
+
 	p->clk = devm_clk_get(dev, NULL);
 	if (IS_ERR(p->clk)) {
-		dev_warn(dev, "unable to get clock\n");
+		if (p->needs_clk) {
+			dev_err(dev, "unable to get clock\n");
+			ret = PTR_ERR(p->clk);
+			goto err0;
+		}
 		p->clk = NULL;
 	}
 
@@ -443,8 +462,8 @@
 		p->irq[k].requested_irq = irq->start;
 	}
 
-	p->number_of_irqs = k;
-	if (p->number_of_irqs < 1) {
+	nirqs = k;
+	if (nirqs < 1) {
 		dev_err(dev, "not enough IRQ resources\n");
 		ret = -EINVAL;
 		goto err0;
@@ -485,20 +504,16 @@
 	}
 
 	/* configure "individual IRQ mode" where needed */
-	of_id = of_match_device(intc_irqpin_dt_ids, dev);
-	if (of_id && of_id->data) {
-		const struct intc_irqpin_irlm_config *irlm_config = of_id->data;
-
+	if (config && config->needs_irlm) {
 		if (io[INTC_IRQPIN_REG_IRLM])
 			intc_irqpin_read_modify_write(p, INTC_IRQPIN_REG_IRLM,
-						      irlm_config->irlm_bit,
-						      1, 1);
+						      config->irlm_bit, 1, 1);
 		else
 			dev_warn(dev, "unable to select IRLM mode\n");
 	}
 
 	/* mask all interrupts using priority */
-	for (k = 0; k < p->number_of_irqs; k++)
+	for (k = 0; k < nirqs; k++)
 		intc_irqpin_mask_unmask_prio(p, k, 1);
 
 	/* clear all pending interrupts */
@@ -506,16 +521,16 @@
 
 	/* scan for shared interrupt lines */
 	ref_irq = p->irq[0].requested_irq;
-	p->shared_irqs = true;
-	for (k = 1; k < p->number_of_irqs; k++) {
+	p->shared_irqs = 1;
+	for (k = 1; k < nirqs; k++) {
 		if (ref_irq != p->irq[k].requested_irq) {
-			p->shared_irqs = false;
+			p->shared_irqs = 0;
 			break;
 		}
 	}
 
 	/* use more severe masking method if requested */
-	if (p->config.control_parent) {
+	if (control_parent) {
 		enable_fn = intc_irqpin_irq_enable_force;
 		disable_fn = intc_irqpin_irq_disable_force;
 	} else if (!p->shared_irqs) {
@@ -534,9 +549,7 @@
 	irq_chip->irq_set_wake = intc_irqpin_irq_set_wake;
 	irq_chip->flags	= IRQCHIP_MASK_ON_SUSPEND;
 
-	p->irq_domain = irq_domain_add_simple(dev->of_node,
-					      p->number_of_irqs,
-					      p->config.irq_base,
+	p->irq_domain = irq_domain_add_simple(dev->of_node, nirqs, 0,
 					      &intc_irqpin_irq_domain_ops, p);
 	if (!p->irq_domain) {
 		ret = -ENXIO;
@@ -555,7 +568,7 @@
 		}
 	} else {
 		/* request interrupts one by one */
-		for (k = 0; k < p->number_of_irqs; k++) {
+		for (k = 0; k < nirqs; k++) {
 			if (devm_request_irq(dev, p->irq[k].requested_irq,
 					     intc_irqpin_irq_handler, 0, name,
 					     &p->irq[k])) {
@@ -567,17 +580,10 @@
 	}
 
 	/* unmask all interrupts on prio level */
-	for (k = 0; k < p->number_of_irqs; k++)
+	for (k = 0; k < nirqs; k++)
 		intc_irqpin_mask_unmask_prio(p, k, 0);
 
-	dev_info(dev, "driving %d irqs\n", p->number_of_irqs);
-
-	/* warn in case of mismatch if irq base is specified */
-	if (p->config.irq_base) {
-		if (p->config.irq_base != p->irq[0].domain_irq)
-			dev_warn(dev, "irq base mismatch (%d/%d)\n",
-				 p->config.irq_base, p->irq[0].domain_irq);
-	}
+	dev_info(dev, "driving %d irqs\n", nirqs);
 
 	return 0;
 
diff --git a/drivers/irqchip/irq-sunxi-nmi.c b/drivers/irqchip/irq-sunxi-nmi.c
index 4ef1780..0820f67 100644
--- a/drivers/irqchip/irq-sunxi-nmi.c
+++ b/drivers/irqchip/irq-sunxi-nmi.c
@@ -50,6 +50,12 @@
 	.enable	= 0x34,
 };
 
+static struct sunxi_sc_nmi_reg_offs sun9i_reg_offs = {
+	.ctrl	= 0x00,
+	.pend	= 0x08,
+	.enable	= 0x04,
+};
+
 static inline void sunxi_sc_nmi_write(struct irq_chip_generic *gc, u32 off,
 				      u32 val)
 {
@@ -207,3 +213,10 @@
 	return sunxi_sc_nmi_irq_init(node, &sun7i_reg_offs);
 }
 IRQCHIP_DECLARE(sun7i_sc_nmi, "allwinner,sun7i-a20-sc-nmi", sun7i_sc_nmi_irq_init);
+
+static int __init sun9i_nmi_irq_init(struct device_node *node,
+				     struct device_node *parent)
+{
+	return sunxi_sc_nmi_irq_init(node, &sun9i_reg_offs);
+}
+IRQCHIP_DECLARE(sun9i_nmi, "allwinner,sun9i-a80-nmi", sun9i_nmi_irq_init);
diff --git a/drivers/irqchip/irq-ts4800.c b/drivers/irqchip/irq-ts4800.c
new file mode 100644
index 0000000..4192bdc
--- /dev/null
+++ b/drivers/irqchip/irq-ts4800.c
@@ -0,0 +1,163 @@
+/*
+ * Multiplexed-IRQs driver for TS-4800's FPGA
+ *
+ * Copyright (c) 2015 - Savoir-faire Linux
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/irqchip.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/irqdomain.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/platform_device.h>
+
+#define IRQ_MASK        0x4
+#define IRQ_STATUS      0x8
+
+struct ts4800_irq_data {
+	void __iomem            *base;
+	struct irq_domain       *domain;
+	struct irq_chip         irq_chip;
+};
+
+static void ts4800_irq_mask(struct irq_data *d)
+{
+	struct ts4800_irq_data *data = irq_data_get_irq_chip_data(d);
+	u16 reg = readw(data->base + IRQ_MASK);
+	u16 mask = 1 << d->hwirq;
+
+	writew(reg | mask, data->base + IRQ_MASK);
+}
+
+static void ts4800_irq_unmask(struct irq_data *d)
+{
+	struct ts4800_irq_data *data = irq_data_get_irq_chip_data(d);
+	u16 reg = readw(data->base + IRQ_MASK);
+	u16 mask = 1 << d->hwirq;
+
+	writew(reg & ~mask, data->base + IRQ_MASK);
+}
+
+static int ts4800_irqdomain_map(struct irq_domain *d, unsigned int irq,
+				irq_hw_number_t hwirq)
+{
+	struct ts4800_irq_data *data = d->host_data;
+
+	irq_set_chip_and_handler(irq, &data->irq_chip, handle_simple_irq);
+	irq_set_chip_data(irq, data);
+	irq_set_noprobe(irq);
+
+	return 0;
+}
+
+struct irq_domain_ops ts4800_ic_ops = {
+	.map = ts4800_irqdomain_map,
+	.xlate = irq_domain_xlate_onecell,
+};
+
+static void ts4800_ic_chained_handle_irq(struct irq_desc *desc)
+{
+	struct ts4800_irq_data *data = irq_desc_get_handler_data(desc);
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	u16 status = readw(data->base + IRQ_STATUS);
+
+	chained_irq_enter(chip, desc);
+
+	if (unlikely(status == 0)) {
+		handle_bad_irq(desc);
+		goto out;
+	}
+
+	do {
+		unsigned int bit = __ffs(status);
+		int irq = irq_find_mapping(data->domain, bit);
+
+		status &= ~(1 << bit);
+		generic_handle_irq(irq);
+	} while (status);
+
+out:
+	chained_irq_exit(chip, desc);
+}
+
+static int ts4800_ic_probe(struct platform_device *pdev)
+{
+	struct device_node *node = pdev->dev.of_node;
+	struct ts4800_irq_data *data;
+	struct irq_chip *irq_chip;
+	struct resource *res;
+	int parent_irq;
+
+	data = devm_kzalloc(&pdev->dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	data->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(data->base))
+		return PTR_ERR(data->base);
+
+	writew(0xFFFF, data->base + IRQ_MASK);
+
+	parent_irq = irq_of_parse_and_map(node, 0);
+	if (!parent_irq) {
+		dev_err(&pdev->dev, "failed to get parent IRQ\n");
+		return -EINVAL;
+	}
+
+	irq_chip = &data->irq_chip;
+	irq_chip->name = dev_name(&pdev->dev);
+	irq_chip->irq_mask = ts4800_irq_mask;
+	irq_chip->irq_unmask = ts4800_irq_unmask;
+
+	data->domain = irq_domain_add_linear(node, 8, &ts4800_ic_ops, data);
+	if (!data->domain) {
+		dev_err(&pdev->dev, "cannot add IRQ domain\n");
+		return -ENOMEM;
+	}
+
+	irq_set_chained_handler_and_data(parent_irq,
+					 ts4800_ic_chained_handle_irq, data);
+
+	platform_set_drvdata(pdev, data);
+
+	return 0;
+}
+
+static int ts4800_ic_remove(struct platform_device *pdev)
+{
+	struct ts4800_irq_data *data = platform_get_drvdata(pdev);
+
+	irq_domain_remove(data->domain);
+
+	return 0;
+}
+
+static const struct of_device_id ts4800_ic_of_match[] = {
+	{ .compatible = "technologic,ts4800-irqc", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, ts4800_ic_of_match);
+
+static struct platform_driver ts4800_ic_driver = {
+	.probe  = ts4800_ic_probe,
+	.remove = ts4800_ic_remove,
+	.driver = {
+		.name = "ts4800-irqc",
+		.of_match_table = ts4800_ic_of_match,
+	},
+};
+module_platform_driver(ts4800_ic_driver);
+
+MODULE_AUTHOR("Damien Riegel <damien.riegel@savoirfairelinux.com>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:ts4800_irqc");
diff --git a/drivers/irqchip/irq-zevio.c b/drivers/irqchip/irq-zevio.c
index 4c48fa8..cb9d8ec 100644
--- a/drivers/irqchip/irq-zevio.c
+++ b/drivers/irqchip/irq-zevio.c
@@ -43,8 +43,7 @@
 static void zevio_irq_ack(struct irq_data *irqd)
 {
 	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(irqd);
-	struct irq_chip_regs *regs =
-		&container_of(irqd->chip, struct irq_chip_type, chip)->regs;
+	struct irq_chip_regs *regs = &irq_data_get_chip_type(irqd)->regs;
 
 	readl(gc->reg_base + regs->ack);
 }
diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig
index b1ab8bd..7f940c2 100644
--- a/drivers/leds/Kconfig
+++ b/drivers/leds/Kconfig
@@ -52,6 +52,7 @@
 config LEDS_BCM6328
 	tristate "LED Support for Broadcom BCM6328"
 	depends on LEDS_CLASS
+	depends on HAS_IOMEM
 	depends on OF
 	help
 	  This option enables support for LEDs connected to the BCM6328
@@ -60,6 +61,7 @@
 config LEDS_BCM6358
 	tristate "LED Support for Broadcom BCM6358"
 	depends on LEDS_CLASS
+	depends on HAS_IOMEM
 	depends on OF
 	help
 	  This option enables support for LEDs connected to the BCM6358
diff --git a/drivers/leds/led-class-flash.c b/drivers/leds/led-class-flash.c
index 3b25734..cf39827 100644
--- a/drivers/leds/led-class-flash.c
+++ b/drivers/leds/led-class-flash.c
@@ -108,7 +108,7 @@
 	if (ret)
 		goto unlock;
 
-	if (state < 0 || state > 1) {
+	if (state > 1) {
 		ret = -EINVAL;
 		goto unlock;
 	}
@@ -298,7 +298,7 @@
 	led_cdev = &fled_cdev->led_cdev;
 
 	if (led_cdev->flags & LED_DEV_CAP_FLASH) {
-		if (!led_cdev->brightness_set_sync)
+		if (!led_cdev->brightness_set_blocking)
 			return -EINVAL;
 
 		ops = fled_cdev->ops;
@@ -316,10 +316,6 @@
 	if (ret < 0)
 		return ret;
 
-	/* Setting a torch brightness needs to have immediate effect */
-	led_cdev->flags &= ~SET_BRIGHTNESS_ASYNC;
-	led_cdev->flags |= SET_BRIGHTNESS_SYNC;
-
 	return 0;
 }
 EXPORT_SYMBOL_GPL(led_classdev_flash_register);
diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c
index 7385f98..14139c33 100644
--- a/drivers/leds/led-class.c
+++ b/drivers/leds/led-class.c
@@ -109,7 +109,7 @@
 void led_classdev_suspend(struct led_classdev *led_cdev)
 {
 	led_cdev->flags |= LED_SUSPENDED;
-	led_cdev->brightness_set(led_cdev, 0);
+	led_set_brightness_nopm(led_cdev, 0);
 }
 EXPORT_SYMBOL_GPL(led_classdev_suspend);
 
@@ -119,7 +119,7 @@
  */
 void led_classdev_resume(struct led_classdev *led_cdev)
 {
-	led_cdev->brightness_set(led_cdev, led_cdev->brightness);
+	led_set_brightness_nopm(led_cdev, led_cdev->brightness);
 
 	if (led_cdev->flash_resume)
 		led_cdev->flash_resume(led_cdev);
@@ -215,8 +215,6 @@
 	if (!led_cdev->max_brightness)
 		led_cdev->max_brightness = LED_FULL;
 
-	led_cdev->flags |= SET_BRIGHTNESS_ASYNC;
-
 	led_update_brightness(led_cdev);
 
 	led_init_core(led_cdev);
@@ -247,12 +245,13 @@
 	up_write(&led_cdev->trigger_lock);
 #endif
 
-	cancel_work_sync(&led_cdev->set_brightness_work);
-
 	/* Stop blinking */
 	led_stop_software_blink(led_cdev);
+
 	led_set_brightness(led_cdev, LED_OFF);
 
+	flush_work(&led_cdev->set_brightness_work);
+
 	device_unregister(led_cdev->dev);
 
 	down_write(&leds_list_lock);
diff --git a/drivers/leds/led-core.c b/drivers/leds/led-core.c
index c1c3af0..19e1e60d 100644
--- a/drivers/leds/led-core.c
+++ b/drivers/leds/led-core.c
@@ -32,7 +32,7 @@
 	unsigned long delay;
 
 	if (!led_cdev->blink_delay_on || !led_cdev->blink_delay_off) {
-		led_set_brightness_async(led_cdev, LED_OFF);
+		led_set_brightness_nosleep(led_cdev, LED_OFF);
 		return;
 	}
 
@@ -44,23 +44,23 @@
 	brightness = led_get_brightness(led_cdev);
 	if (!brightness) {
 		/* Time to switch the LED on. */
-		if (led_cdev->delayed_set_value) {
-			led_cdev->blink_brightness =
-					led_cdev->delayed_set_value;
-			led_cdev->delayed_set_value = 0;
-		}
 		brightness = led_cdev->blink_brightness;
 		delay = led_cdev->blink_delay_on;
 	} else {
 		/* Store the current brightness value to be able
 		 * to restore it when the delay_off period is over.
+		 * Do it only if there is no pending blink brightness
+		 * change, to avoid overwriting the new value.
 		 */
-		led_cdev->blink_brightness = brightness;
+		if (!(led_cdev->flags & LED_BLINK_BRIGHTNESS_CHANGE))
+			led_cdev->blink_brightness = brightness;
+		else
+			led_cdev->flags &= ~LED_BLINK_BRIGHTNESS_CHANGE;
 		brightness = LED_OFF;
 		delay = led_cdev->blink_delay_off;
 	}
 
-	led_set_brightness_async(led_cdev, brightness);
+	led_set_brightness_nosleep(led_cdev, brightness);
 
 	/* Return in next iteration if led is in one-shot mode and we are in
 	 * the final blink state so that the led is toggled each delay_on +
@@ -83,10 +83,24 @@
 {
 	struct led_classdev *led_cdev =
 		container_of(ws, struct led_classdev, set_brightness_work);
+	int ret = 0;
 
-	led_stop_software_blink(led_cdev);
+	if (led_cdev->flags & LED_BLINK_DISABLE) {
+		led_cdev->delayed_set_value = LED_OFF;
+		led_stop_software_blink(led_cdev);
+		led_cdev->flags &= ~LED_BLINK_DISABLE;
+	}
 
-	led_set_brightness_async(led_cdev, led_cdev->delayed_set_value);
+	if (led_cdev->brightness_set)
+		led_cdev->brightness_set(led_cdev, led_cdev->delayed_set_value);
+	else if (led_cdev->brightness_set_blocking)
+		ret = led_cdev->brightness_set_blocking(led_cdev,
+						led_cdev->delayed_set_value);
+	else
+		ret = -ENOTSUPP;
+	if (ret < 0)
+		dev_err(led_cdev->dev,
+			"Setting an LED's brightness failed (%d)\n", ret);
 }
 
 static void led_set_software_blink(struct led_classdev *led_cdev,
@@ -106,13 +120,14 @@
 
 	/* never on - just set to off */
 	if (!delay_on) {
-		led_set_brightness_async(led_cdev, LED_OFF);
+		led_set_brightness_nosleep(led_cdev, LED_OFF);
 		return;
 	}
 
 	/* never off - just set to brightness */
 	if (!delay_off) {
-		led_set_brightness_async(led_cdev, led_cdev->blink_brightness);
+		led_set_brightness_nosleep(led_cdev,
+					   led_cdev->blink_brightness);
 		return;
 	}
 
@@ -156,7 +171,7 @@
 
 	led_blink_setup(led_cdev, delay_on, delay_off);
 }
-EXPORT_SYMBOL(led_blink_set);
+EXPORT_SYMBOL_GPL(led_blink_set);
 
 void led_blink_set_oneshot(struct led_classdev *led_cdev,
 			   unsigned long *delay_on,
@@ -177,7 +192,7 @@
 
 	led_blink_setup(led_cdev, delay_on, delay_off);
 }
-EXPORT_SYMBOL(led_blink_set_oneshot);
+EXPORT_SYMBOL_GPL(led_blink_set_oneshot);
 
 void led_stop_software_blink(struct led_classdev *led_cdev)
 {
@@ -190,29 +205,74 @@
 void led_set_brightness(struct led_classdev *led_cdev,
 			enum led_brightness brightness)
 {
-	int ret = 0;
-
-	/* delay brightness if soft-blink is active */
+	/*
+	 * In case blinking is on delay brightness setting
+	 * until the next timer tick.
+	 */
 	if (led_cdev->blink_delay_on || led_cdev->blink_delay_off) {
-		led_cdev->delayed_set_value = brightness;
-		if (brightness == LED_OFF)
+		/*
+		 * If we need to disable soft blinking delegate this to the
+		 * work queue task to avoid problems in case we are called
+		 * from hard irq context.
+		 */
+		if (brightness == LED_OFF) {
+			led_cdev->flags |= LED_BLINK_DISABLE;
 			schedule_work(&led_cdev->set_brightness_work);
+		} else {
+			led_cdev->flags |= LED_BLINK_BRIGHTNESS_CHANGE;
+			led_cdev->blink_brightness = brightness;
+		}
 		return;
 	}
 
-	if (led_cdev->flags & SET_BRIGHTNESS_ASYNC) {
-		led_set_brightness_async(led_cdev, brightness);
-		return;
-	} else if (led_cdev->flags & SET_BRIGHTNESS_SYNC)
-		ret = led_set_brightness_sync(led_cdev, brightness);
-	else
-		ret = -EINVAL;
-
-	if (ret < 0)
-		dev_dbg(led_cdev->dev, "Setting LED brightness failed (%d)\n",
-			ret);
+	led_set_brightness_nosleep(led_cdev, brightness);
 }
-EXPORT_SYMBOL(led_set_brightness);
+EXPORT_SYMBOL_GPL(led_set_brightness);
+
+void led_set_brightness_nopm(struct led_classdev *led_cdev,
+			      enum led_brightness value)
+{
+	/* Use brightness_set op if available, it is guaranteed not to sleep */
+	if (led_cdev->brightness_set) {
+		led_cdev->brightness_set(led_cdev, value);
+		return;
+	}
+
+	/* If brightness setting can sleep, delegate it to a work queue task */
+	led_cdev->delayed_set_value = value;
+	schedule_work(&led_cdev->set_brightness_work);
+}
+EXPORT_SYMBOL_GPL(led_set_brightness_nopm);
+
+void led_set_brightness_nosleep(struct led_classdev *led_cdev,
+				enum led_brightness value)
+{
+	led_cdev->brightness = min(value, led_cdev->max_brightness);
+
+	if (led_cdev->flags & LED_SUSPENDED)
+		return;
+
+	led_set_brightness_nopm(led_cdev, led_cdev->brightness);
+}
+EXPORT_SYMBOL_GPL(led_set_brightness_nosleep);
+
+int led_set_brightness_sync(struct led_classdev *led_cdev,
+			    enum led_brightness value)
+{
+	if (led_cdev->blink_delay_on || led_cdev->blink_delay_off)
+		return -EBUSY;
+
+	led_cdev->brightness = min(value, led_cdev->max_brightness);
+
+	if (led_cdev->flags & LED_SUSPENDED)
+		return 0;
+
+	if (led_cdev->brightness_set_blocking)
+		return led_cdev->brightness_set_blocking(led_cdev,
+							 led_cdev->brightness);
+	return -ENOTSUPP;
+}
+EXPORT_SYMBOL_GPL(led_set_brightness_sync);
 
 int led_update_brightness(struct led_classdev *led_cdev)
 {
@@ -228,7 +288,7 @@
 
 	return ret;
 }
-EXPORT_SYMBOL(led_update_brightness);
+EXPORT_SYMBOL_GPL(led_update_brightness);
 
 /* Caller must ensure led_cdev->led_access held */
 void led_sysfs_disable(struct led_classdev *led_cdev)
diff --git a/drivers/leds/led-triggers.c b/drivers/leds/led-triggers.c
index e8b1120..e1e9334 100644
--- a/drivers/leds/led-triggers.c
+++ b/drivers/leds/led-triggers.c
@@ -249,6 +249,34 @@
 }
 EXPORT_SYMBOL_GPL(led_trigger_unregister);
 
+static void devm_led_trigger_release(struct device *dev, void *res)
+{
+	led_trigger_unregister(*(struct led_trigger **)res);
+}
+
+int devm_led_trigger_register(struct device *dev,
+			      struct led_trigger *trig)
+{
+	struct led_trigger **dr;
+	int rc;
+
+	dr = devres_alloc(devm_led_trigger_release, sizeof(*dr),
+			  GFP_KERNEL);
+	if (!dr)
+		return -ENOMEM;
+
+	*dr = trig;
+
+	rc = led_trigger_register(trig);
+	if (rc)
+		devres_free(dr);
+	else
+		devres_add(dev, dr);
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(devm_led_trigger_register);
+
 /* Simple LED Tigger Interface */
 
 void led_trigger_event(struct led_trigger *trig,
diff --git a/drivers/leds/leds-88pm860x.c b/drivers/leds/leds-88pm860x.c
index 7870840..1ad4d03 100644
--- a/drivers/leds/leds-88pm860x.c
+++ b/drivers/leds/leds-88pm860x.c
@@ -16,7 +16,6 @@
 #include <linux/i2c.h>
 #include <linux/leds.h>
 #include <linux/slab.h>
-#include <linux/workqueue.h>
 #include <linux/mfd/88pm860x.h>
 #include <linux/module.h>
 
@@ -33,7 +32,6 @@
 struct pm860x_led {
 	struct led_classdev cdev;
 	struct i2c_client *i2c;
-	struct work_struct work;
 	struct pm860x_chip *chip;
 	struct mutex lock;
 	char name[MFD_NAME_SIZE];
@@ -69,17 +67,18 @@
 	return ret;
 }
 
-static void pm860x_led_work(struct work_struct *work)
+static int pm860x_led_set(struct led_classdev *cdev,
+			   enum led_brightness value)
 {
-
-	struct pm860x_led *led;
+	struct pm860x_led *led = container_of(cdev, struct pm860x_led, cdev);
 	struct pm860x_chip *chip;
 	unsigned char buf[3];
 	int ret;
 
-	led = container_of(work, struct pm860x_led, work);
 	chip = led->chip;
 	mutex_lock(&led->lock);
+	led->brightness = value >> 3;
+
 	if ((led->current_brightness == 0) && led->brightness) {
 		led_power_set(chip, led->port, 1);
 		if (led->iset) {
@@ -112,15 +111,8 @@
 	dev_dbg(chip->dev, "Update LED. (reg:%d, brightness:%d)\n",
 		led->reg_control, led->brightness);
 	mutex_unlock(&led->lock);
-}
 
-static void pm860x_led_set(struct led_classdev *cdev,
-			   enum led_brightness value)
-{
-	struct pm860x_led *data = container_of(cdev, struct pm860x_led, cdev);
-
-	data->brightness = value >> 3;
-	schedule_work(&data->work);
+	return 0;
 }
 
 #ifdef CONFIG_OF
@@ -213,9 +205,8 @@
 
 	data->current_brightness = 0;
 	data->cdev.name = data->name;
-	data->cdev.brightness_set = pm860x_led_set;
+	data->cdev.brightness_set_blocking = pm860x_led_set;
 	mutex_init(&data->lock);
-	INIT_WORK(&data->work, pm860x_led_work);
 
 	ret = led_classdev_register(chip->dev, &data->cdev);
 	if (ret < 0) {
diff --git a/drivers/leds/leds-aat1290.c b/drivers/leds/leds-aat1290.c
index ac77d36..def3cf9 100644
--- a/drivers/leds/leds-aat1290.c
+++ b/drivers/leds/leds-aat1290.c
@@ -20,7 +20,6 @@
 #include <linux/pinctrl/consumer.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
-#include <linux/workqueue.h>
 #include <media/v4l2-flash-led-class.h>
 
 #define AAT1290_MOVIE_MODE_CURRENT_ADDR	17
@@ -82,8 +81,6 @@
 
 	/* brightness cache */
 	unsigned int torch_brightness;
-	/* assures led-triggers compatibility */
-	struct work_struct work_brightness_set;
 };
 
 static struct aat1290_led *fled_cdev_to_led(
@@ -92,6 +89,12 @@
 	return container_of(fled_cdev, struct aat1290_led, fled_cdev);
 }
 
+static struct led_classdev_flash *led_cdev_to_fled_cdev(
+				struct led_classdev *led_cdev)
+{
+	return container_of(led_cdev, struct led_classdev_flash, led_cdev);
+}
+
 static void aat1290_as2cwire_write(struct aat1290_led *led, int addr, int value)
 {
 	int i;
@@ -134,9 +137,14 @@
 							flash_tm_reg);
 }
 
-static void aat1290_brightness_set(struct aat1290_led *led,
+/* LED subsystem callbacks */
+
+static int aat1290_led_brightness_set(struct led_classdev *led_cdev,
 					enum led_brightness brightness)
 {
+	struct led_classdev_flash *fled_cdev = led_cdev_to_fled_cdev(led_cdev);
+	struct aat1290_led *led = fled_cdev_to_led(fled_cdev);
+
 	mutex_lock(&led->lock);
 
 	if (brightness == 0) {
@@ -158,35 +166,6 @@
 	}
 
 	mutex_unlock(&led->lock);
-}
-
-/* LED subsystem callbacks */
-
-static void aat1290_brightness_set_work(struct work_struct *work)
-{
-	struct aat1290_led *led =
-		container_of(work, struct aat1290_led, work_brightness_set);
-
-	aat1290_brightness_set(led, led->torch_brightness);
-}
-
-static void aat1290_led_brightness_set(struct led_classdev *led_cdev,
-					enum led_brightness brightness)
-{
-	struct led_classdev_flash *fled_cdev = lcdev_to_flcdev(led_cdev);
-	struct aat1290_led *led = fled_cdev_to_led(fled_cdev);
-
-	led->torch_brightness = brightness;
-	schedule_work(&led->work_brightness_set);
-}
-
-static int aat1290_led_brightness_set_sync(struct led_classdev *led_cdev,
-					enum led_brightness brightness)
-{
-	struct led_classdev_flash *fled_cdev = lcdev_to_flcdev(led_cdev);
-	struct aat1290_led *led = fled_cdev_to_led(fled_cdev);
-
-	aat1290_brightness_set(led, brightness);
 
 	return 0;
 }
@@ -296,7 +275,7 @@
 	if (ret < 0) {
 		dev_err(dev,
 			"flash-max-microamp DT property missing\n");
-		return ret;
+		goto err_parse_dt;
 	}
 
 	ret = of_property_read_u32(child_node, "flash-max-timeout-us",
@@ -304,13 +283,14 @@
 	if (ret < 0) {
 		dev_err(dev,
 			"flash-max-timeout-us DT property missing\n");
-		return ret;
+		goto err_parse_dt;
 	}
 
-	of_node_put(child_node);
-
 	*sub_node = child_node;
 
+err_parse_dt:
+	of_node_put(child_node);
+
 	return ret;
 }
 
@@ -509,11 +489,9 @@
 	mutex_init(&led->lock);
 
 	/* Initialize LED Flash class device */
-	led_cdev->brightness_set = aat1290_led_brightness_set;
-	led_cdev->brightness_set_sync = aat1290_led_brightness_set_sync;
+	led_cdev->brightness_set_blocking = aat1290_led_brightness_set;
 	led_cdev->max_brightness = led_cfg.max_brightness;
 	led_cdev->flags |= LED_DEV_CAP_FLASH;
-	INIT_WORK(&led->work_brightness_set, aat1290_brightness_set_work);
 
 	aat1290_init_flash_timeout(led, &led_cfg);
 
@@ -548,7 +526,6 @@
 
 	v4l2_flash_release(led->v4l2_flash);
 	led_classdev_flash_unregister(&led->fled_cdev);
-	cancel_work_sync(&led->work_brightness_set);
 
 	mutex_destroy(&led->lock);
 
diff --git a/drivers/leds/leds-adp5520.c b/drivers/leds/leds-adp5520.c
index 07e66ca..853b2d3 100644
--- a/drivers/leds/leds-adp5520.c
+++ b/drivers/leds/leds-adp5520.c
@@ -17,34 +17,24 @@
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
 #include <linux/leds.h>
-#include <linux/workqueue.h>
 #include <linux/mfd/adp5520.h>
 #include <linux/slab.h>
 
 struct adp5520_led {
 	struct led_classdev	cdev;
-	struct work_struct	work;
 	struct device		*master;
-	enum led_brightness	new_brightness;
 	int			id;
 	int			flags;
 };
 
-static void adp5520_led_work(struct work_struct *work)
-{
-	struct adp5520_led *led = container_of(work, struct adp5520_led, work);
-	adp5520_write(led->master, ADP5520_LED1_CURRENT + led->id - 1,
-			 led->new_brightness >> 2);
-}
-
-static void adp5520_led_set(struct led_classdev *led_cdev,
+static int adp5520_led_set(struct led_classdev *led_cdev,
 			   enum led_brightness value)
 {
 	struct adp5520_led *led;
 
 	led = container_of(led_cdev, struct adp5520_led, cdev);
-	led->new_brightness = value;
-	schedule_work(&led->work);
+	return adp5520_write(led->master, ADP5520_LED1_CURRENT + led->id - 1,
+			 value >> 2);
 }
 
 static int adp5520_led_setup(struct adp5520_led *led)
@@ -135,7 +125,7 @@
 
 		led_dat->cdev.name = cur_led->name;
 		led_dat->cdev.default_trigger = cur_led->default_trigger;
-		led_dat->cdev.brightness_set = adp5520_led_set;
+		led_dat->cdev.brightness_set_blocking = adp5520_led_set;
 		led_dat->cdev.brightness = LED_OFF;
 
 		if (cur_led->flags & ADP5520_FLAG_LED_MASK)
@@ -146,9 +136,6 @@
 		led_dat->id = led_dat->flags & ADP5520_FLAG_LED_MASK;
 
 		led_dat->master = pdev->dev.parent;
-		led_dat->new_brightness = LED_OFF;
-
-		INIT_WORK(&led_dat->work, adp5520_led_work);
 
 		ret = led_classdev_register(led_dat->master, &led_dat->cdev);
 		if (ret) {
@@ -170,10 +157,8 @@
 
 err:
 	if (i > 0) {
-		for (i = i - 1; i >= 0; i--) {
+		for (i = i - 1; i >= 0; i--)
 			led_classdev_unregister(&led[i].cdev);
-			cancel_work_sync(&led[i].work);
-		}
 	}
 
 	return ret;
@@ -192,7 +177,6 @@
 
 	for (i = 0; i < pdata->num_leds; i++) {
 		led_classdev_unregister(&led[i].cdev);
-		cancel_work_sync(&led[i].work);
 	}
 
 	return 0;
diff --git a/drivers/leds/leds-bcm6328.c b/drivers/leds/leds-bcm6328.c
index c7ea5c6..1548259 100644
--- a/drivers/leds/leds-bcm6328.c
+++ b/drivers/leds/leds-bcm6328.c
@@ -42,16 +42,16 @@
 #define BCM6328_LED_SHIFT_TEST		BIT(30)
 #define BCM6328_LED_TEST		BIT(31)
 #define BCM6328_INIT_MASK		(BCM6328_SERIAL_LED_EN | \
-					 BCM6328_SERIAL_LED_MUX  | \
+					 BCM6328_SERIAL_LED_MUX | \
 					 BCM6328_SERIAL_LED_CLK_NPOL | \
 					 BCM6328_SERIAL_LED_DATA_PPOL | \
 					 BCM6328_SERIAL_LED_SHIFT_DIR)
 
 #define BCM6328_LED_MODE_MASK		3
-#define BCM6328_LED_MODE_OFF		0
+#define BCM6328_LED_MODE_ON		0
 #define BCM6328_LED_MODE_FAST		1
 #define BCM6328_LED_MODE_BLINK		2
-#define BCM6328_LED_MODE_ON		3
+#define BCM6328_LED_MODE_OFF		3
 #define BCM6328_LED_SHIFT(X)		((X) << 1)
 
 /**
@@ -76,12 +76,20 @@
 
 static void bcm6328_led_write(void __iomem *reg, unsigned long data)
 {
+#ifdef CONFIG_CPU_BIG_ENDIAN
 	iowrite32be(data, reg);
+#else
+	writel(data, reg);
+#endif
 }
 
 static unsigned long bcm6328_led_read(void __iomem *reg)
 {
+#ifdef CONFIG_CPU_BIG_ENDIAN
 	return ioread32be(reg);
+#else
+	return readl(reg);
+#endif
 }
 
 /**
@@ -126,34 +134,45 @@
 	*(led->blink_leds) &= ~BIT(led->pin);
 	if ((led->active_low && value == LED_OFF) ||
 	    (!led->active_low && value != LED_OFF))
-		bcm6328_led_mode(led, BCM6328_LED_MODE_OFF);
-	else
 		bcm6328_led_mode(led, BCM6328_LED_MODE_ON);
+	else
+		bcm6328_led_mode(led, BCM6328_LED_MODE_OFF);
 	spin_unlock_irqrestore(led->lock, flags);
 }
 
+static unsigned long bcm6328_blink_delay(unsigned long delay)
+{
+	unsigned long bcm6328_delay;
+
+	bcm6328_delay = delay + BCM6328_LED_INTERVAL_MS / 2;
+	bcm6328_delay = bcm6328_delay / BCM6328_LED_INTERVAL_MS;
+	if (bcm6328_delay == 0)
+		bcm6328_delay = 1;
+
+	return bcm6328_delay;
+}
+
 static int bcm6328_blink_set(struct led_classdev *led_cdev,
 			     unsigned long *delay_on, unsigned long *delay_off)
 {
 	struct bcm6328_led *led =
 		container_of(led_cdev, struct bcm6328_led, cdev);
 	unsigned long delay, flags;
+	int rc;
 
 	if (!*delay_on)
 		*delay_on = BCM6328_LED_DEF_DELAY;
 	if (!*delay_off)
 		*delay_off = BCM6328_LED_DEF_DELAY;
 
-	if (*delay_on != *delay_off) {
+	delay = bcm6328_blink_delay(*delay_on);
+	if (delay != bcm6328_blink_delay(*delay_off)) {
 		dev_dbg(led_cdev->dev,
 			"fallback to soft blinking (delay_on != delay_off)\n");
 		return -EINVAL;
 	}
 
-	delay = *delay_on / BCM6328_LED_INTERVAL_MS;
-	if (delay == 0)
-		delay = 1;
-	else if (delay > BCM6328_LED_INTV_MASK) {
+	if (delay > BCM6328_LED_INTV_MASK) {
 		dev_dbg(led_cdev->dev,
 			"fallback to soft blinking (delay > %ums)\n",
 			BCM6328_LED_INTV_MASK * BCM6328_LED_INTERVAL_MS);
@@ -175,16 +194,15 @@
 		bcm6328_led_write(led->mem + BCM6328_REG_INIT, val);
 
 		bcm6328_led_mode(led, BCM6328_LED_MODE_BLINK);
-
-		spin_unlock_irqrestore(led->lock, flags);
+		rc = 0;
 	} else {
-		spin_unlock_irqrestore(led->lock, flags);
 		dev_dbg(led_cdev->dev,
 			"fallback to soft blinking (delay already set)\n");
-		return -EINVAL;
+		rc = -EINVAL;
 	}
+	spin_unlock_irqrestore(led->lock, flags);
 
-	return 0;
+	return rc;
 }
 
 static int bcm6328_hwled(struct device *dev, struct device_node *nc, u32 reg,
@@ -264,7 +282,6 @@
 		       unsigned long *blink_leds, unsigned long *blink_delay)
 {
 	struct bcm6328_led *led;
-	unsigned long flags;
 	const char *state;
 	int rc;
 
@@ -286,7 +303,6 @@
 						    "linux,default-trigger",
 						    NULL);
 
-	spin_lock_irqsave(lock, flags);
 	if (!of_property_read_string(nc, "default-state", &state)) {
 		if (!strcmp(state, "on")) {
 			led->cdev.brightness = LED_FULL;
@@ -303,8 +319,8 @@
 			val = bcm6328_led_read(mode) >>
 			      BCM6328_LED_SHIFT(shift % 16);
 			val &= BCM6328_LED_MODE_MASK;
-			if ((led->active_low && val == BCM6328_LED_MODE_ON) ||
-			    (!led->active_low && val == BCM6328_LED_MODE_OFF))
+			if ((led->active_low && val == BCM6328_LED_MODE_OFF) ||
+			    (!led->active_low && val == BCM6328_LED_MODE_ON))
 				led->cdev.brightness = LED_FULL;
 			else
 				led->cdev.brightness = LED_OFF;
@@ -315,12 +331,7 @@
 		led->cdev.brightness = LED_OFF;
 	}
 
-	if ((led->active_low && led->cdev.brightness == LED_FULL) ||
-	    (!led->active_low && led->cdev.brightness == LED_OFF))
-		bcm6328_led_mode(led, BCM6328_LED_MODE_ON);
-	else
-		bcm6328_led_mode(led, BCM6328_LED_MODE_OFF);
-	spin_unlock_irqrestore(lock, flags);
+	bcm6328_led_set(&led->cdev, led->cdev.brightness);
 
 	led->cdev.brightness_set = bcm6328_led_set;
 	led->cdev.blink_set = bcm6328_blink_set;
@@ -341,7 +352,7 @@
 	struct device_node *child;
 	struct resource *mem_r;
 	void __iomem *mem;
-	spinlock_t *lock;
+	spinlock_t *lock; /* memory lock */
 	unsigned long val, *blink_leds, *blink_delay;
 
 	mem_r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
diff --git a/drivers/leds/leds-bcm6358.c b/drivers/leds/leds-bcm6358.c
index 82b4ee1..b2cc066 100644
--- a/drivers/leds/leds-bcm6358.c
+++ b/drivers/leds/leds-bcm6358.c
@@ -49,12 +49,20 @@
 
 static void bcm6358_led_write(void __iomem *reg, unsigned long data)
 {
+#ifdef CONFIG_CPU_BIG_ENDIAN
 	iowrite32be(data, reg);
+#else
+	writel(data, reg);
+#endif
 }
 
 static unsigned long bcm6358_led_read(void __iomem *reg)
 {
+#ifdef CONFIG_CPU_BIG_ENDIAN
 	return ioread32be(reg);
+#else
+	return readl(reg);
+#endif
 }
 
 static unsigned long bcm6358_led_busy(void __iomem *mem)
@@ -68,12 +76,15 @@
 	return val;
 }
 
-static void bcm6358_led_mode(struct bcm6358_led *led, unsigned long value)
+static void bcm6358_led_set(struct led_classdev *led_cdev,
+			    enum led_brightness value)
 {
-	unsigned long val;
+	struct bcm6358_led *led =
+		container_of(led_cdev, struct bcm6358_led, cdev);
+	unsigned long flags, val;
 
+	spin_lock_irqsave(led->lock, flags);
 	bcm6358_led_busy(led->mem);
-
 	val = bcm6358_led_read(led->mem + BCM6358_REG_MODE);
 	if ((led->active_low && value == LED_OFF) ||
 	    (!led->active_low && value != LED_OFF))
@@ -81,17 +92,6 @@
 	else
 		val &= ~(BIT(led->pin));
 	bcm6358_led_write(led->mem + BCM6358_REG_MODE, val);
-}
-
-static void bcm6358_led_set(struct led_classdev *led_cdev,
-			    enum led_brightness value)
-{
-	struct bcm6358_led *led =
-		container_of(led_cdev, struct bcm6358_led, cdev);
-	unsigned long flags;
-
-	spin_lock_irqsave(led->lock, flags);
-	bcm6358_led_mode(led, value);
 	spin_unlock_irqrestore(led->lock, flags);
 }
 
@@ -99,7 +99,6 @@
 		       void __iomem *mem, spinlock_t *lock)
 {
 	struct bcm6358_led *led;
-	unsigned long flags;
 	const char *state;
 	int rc;
 
@@ -119,15 +118,11 @@
 						    "linux,default-trigger",
 						    NULL);
 
-	spin_lock_irqsave(lock, flags);
 	if (!of_property_read_string(nc, "default-state", &state)) {
 		if (!strcmp(state, "on")) {
 			led->cdev.brightness = LED_FULL;
 		} else if (!strcmp(state, "keep")) {
 			unsigned long val;
-
-			bcm6358_led_busy(led->mem);
-
 			val = bcm6358_led_read(led->mem + BCM6358_REG_MODE);
 			val &= BIT(led->pin);
 			if ((led->active_low && !val) ||
@@ -141,8 +136,8 @@
 	} else {
 		led->cdev.brightness = LED_OFF;
 	}
-	bcm6358_led_mode(led, led->cdev.brightness);
-	spin_unlock_irqrestore(lock, flags);
+
+	bcm6358_led_set(&led->cdev, led->cdev.brightness);
 
 	led->cdev.brightness_set = bcm6358_led_set;
 
diff --git a/drivers/leds/leds-bd2802.c b/drivers/leds/leds-bd2802.c
index 6078c15..6b4de76 100644
--- a/drivers/leds/leds-bd2802.c
+++ b/drivers/leds/leds-bd2802.c
@@ -72,7 +72,6 @@
 	struct bd2802_led_platform_data	*pdata;
 	struct i2c_client		*client;
 	struct rw_semaphore		rwsem;
-	struct work_struct		work;
 
 	struct led_state		led[2];
 
@@ -518,29 +517,22 @@
 	&bd2802_rgb_current_attr,
 };
 
-static void bd2802_led_work(struct work_struct *work)
-{
-	struct bd2802_led *led = container_of(work, struct bd2802_led, work);
-
-	if (led->state)
-		bd2802_turn_on(led, led->led_id, led->color, led->state);
-	else
-		bd2802_turn_off(led, led->led_id, led->color);
-}
-
 #define BD2802_CONTROL_RGBS(name, id, clr)				\
-static void bd2802_set_##name##_brightness(struct led_classdev *led_cdev,\
+static int bd2802_set_##name##_brightness(struct led_classdev *led_cdev,\
 					enum led_brightness value)	\
 {									\
 	struct bd2802_led *led =					\
 		container_of(led_cdev, struct bd2802_led, cdev_##name);	\
 	led->led_id = id;						\
 	led->color = clr;						\
-	if (value == LED_OFF)						\
+	if (value == LED_OFF) {						\
 		led->state = BD2802_OFF;				\
-	else								\
+		bd2802_turn_off(led, led->led_id, led->color);		\
+	} else {							\
 		led->state = BD2802_ON;					\
-	schedule_work(&led->work);					\
+		bd2802_turn_on(led, led->led_id, led->color, BD2802_ON);\
+	}								\
+	return 0;							\
 }									\
 static int bd2802_set_##name##_blink(struct led_classdev *led_cdev,	\
 		unsigned long *delay_on, unsigned long *delay_off)	\
@@ -552,7 +544,7 @@
 	led->led_id = id;						\
 	led->color = clr;						\
 	led->state = BD2802_BLINK;					\
-	schedule_work(&led->work);					\
+	bd2802_turn_on(led, led->led_id, led->color, BD2802_BLINK);	\
 	return 0;							\
 }
 
@@ -567,11 +559,9 @@
 {
 	int ret;
 
-	INIT_WORK(&led->work, bd2802_led_work);
-
 	led->cdev_led1r.name = "led1_R";
 	led->cdev_led1r.brightness = LED_OFF;
-	led->cdev_led1r.brightness_set = bd2802_set_led1r_brightness;
+	led->cdev_led1r.brightness_set_blocking = bd2802_set_led1r_brightness;
 	led->cdev_led1r.blink_set = bd2802_set_led1r_blink;
 
 	ret = led_classdev_register(&led->client->dev, &led->cdev_led1r);
@@ -583,7 +573,7 @@
 
 	led->cdev_led1g.name = "led1_G";
 	led->cdev_led1g.brightness = LED_OFF;
-	led->cdev_led1g.brightness_set = bd2802_set_led1g_brightness;
+	led->cdev_led1g.brightness_set_blocking = bd2802_set_led1g_brightness;
 	led->cdev_led1g.blink_set = bd2802_set_led1g_blink;
 
 	ret = led_classdev_register(&led->client->dev, &led->cdev_led1g);
@@ -595,7 +585,7 @@
 
 	led->cdev_led1b.name = "led1_B";
 	led->cdev_led1b.brightness = LED_OFF;
-	led->cdev_led1b.brightness_set = bd2802_set_led1b_brightness;
+	led->cdev_led1b.brightness_set_blocking = bd2802_set_led1b_brightness;
 	led->cdev_led1b.blink_set = bd2802_set_led1b_blink;
 
 	ret = led_classdev_register(&led->client->dev, &led->cdev_led1b);
@@ -607,7 +597,7 @@
 
 	led->cdev_led2r.name = "led2_R";
 	led->cdev_led2r.brightness = LED_OFF;
-	led->cdev_led2r.brightness_set = bd2802_set_led2r_brightness;
+	led->cdev_led2r.brightness_set_blocking = bd2802_set_led2r_brightness;
 	led->cdev_led2r.blink_set = bd2802_set_led2r_blink;
 
 	ret = led_classdev_register(&led->client->dev, &led->cdev_led2r);
@@ -619,7 +609,7 @@
 
 	led->cdev_led2g.name = "led2_G";
 	led->cdev_led2g.brightness = LED_OFF;
-	led->cdev_led2g.brightness_set = bd2802_set_led2g_brightness;
+	led->cdev_led2g.brightness_set_blocking = bd2802_set_led2g_brightness;
 	led->cdev_led2g.blink_set = bd2802_set_led2g_blink;
 
 	ret = led_classdev_register(&led->client->dev, &led->cdev_led2g);
@@ -631,7 +621,7 @@
 
 	led->cdev_led2b.name = "led2_B";
 	led->cdev_led2b.brightness = LED_OFF;
-	led->cdev_led2b.brightness_set = bd2802_set_led2b_brightness;
+	led->cdev_led2b.brightness_set_blocking = bd2802_set_led2b_brightness;
 	led->cdev_led2b.blink_set = bd2802_set_led2b_blink;
 	led->cdev_led2b.flags |= LED_CORE_SUSPENDRESUME;
 
@@ -661,7 +651,6 @@
 
 static void bd2802_unregister_led_classdev(struct bd2802_led *led)
 {
-	cancel_work_sync(&led->work);
 	led_classdev_unregister(&led->cdev_led2b);
 	led_classdev_unregister(&led->cdev_led2g);
 	led_classdev_unregister(&led->cdev_led2r);
diff --git a/drivers/leds/leds-blinkm.c b/drivers/leds/leds-blinkm.c
index d0452b0..617fe97 100644
--- a/drivers/leds/leds-blinkm.c
+++ b/drivers/leds/leds-blinkm.c
@@ -39,16 +39,9 @@
 	struct i2c_client *i2c_client;
 	struct led_classdev led_cdev;
 	int id;
-	atomic_t active;
-};
-
-struct blinkm_work {
-	struct blinkm_led *blinkm_led;
-	struct work_struct work;
 };
 
 #define cdev_to_blmled(c)          container_of(c, struct blinkm_led, led_cdev)
-#define work_to_blmwork(c)         container_of(c, struct blinkm_work, work)
 
 struct blinkm_data {
 	struct i2c_client *i2c_client;
@@ -439,65 +432,30 @@
 	return 0;
 }
 
-static void led_work(struct work_struct *work)
-{
-	int ret;
-	struct blinkm_led *led;
-	struct blinkm_data *data;
-	struct blinkm_work *blm_work = work_to_blmwork(work);
-
-	led = blm_work->blinkm_led;
-	data = i2c_get_clientdata(led->i2c_client);
-	ret = blinkm_transfer_hw(led->i2c_client, BLM_GO_RGB);
-	atomic_dec(&led->active);
-	dev_dbg(&led->i2c_client->dev,
-			"# DONE # next_red = %d, next_green = %d,"
-			" next_blue = %d, active = %d\n",
-			data->next_red, data->next_green,
-			data->next_blue, atomic_read(&led->active));
-	kfree(blm_work);
-}
-
 static int blinkm_led_common_set(struct led_classdev *led_cdev,
 				 enum led_brightness value, int color)
 {
 	/* led_brightness is 0, 127 or 255 - we just use it here as-is */
 	struct blinkm_led *led = cdev_to_blmled(led_cdev);
 	struct blinkm_data *data = i2c_get_clientdata(led->i2c_client);
-	struct blinkm_work *bl_work;
 
 	switch (color) {
 	case RED:
 		/* bail out if there's no change */
 		if (data->next_red == (u8) value)
 			return 0;
-		/* we assume a quite fast sequence here ([off]->on->off)
-		 * think of network led trigger - we cannot blink that fast, so
-		 * in case we already have a off->on->off transition queued up,
-		 * we refuse to queue up more.
-		 * Revisit: fast-changing brightness. */
-		if (atomic_read(&led->active) > 1)
-			return 0;
 		data->next_red = (u8) value;
 		break;
 	case GREEN:
 		/* bail out if there's no change */
 		if (data->next_green == (u8) value)
 			return 0;
-		/* we assume a quite fast sequence here ([off]->on->off)
-		 * Revisit: fast-changing brightness. */
-		if (atomic_read(&led->active) > 1)
-			return 0;
 		data->next_green = (u8) value;
 		break;
 	case BLUE:
 		/* bail out if there's no change */
 		if (data->next_blue == (u8) value)
 			return 0;
-		/* we assume a quite fast sequence here ([off]->on->off)
-		 * Revisit: fast-changing brightness. */
-		if (atomic_read(&led->active) > 1)
-			return 0;
 		data->next_blue = (u8) value;
 		break;
 
@@ -506,42 +464,31 @@
 		return -EINVAL;
 	}
 
-	bl_work = kzalloc(sizeof(*bl_work), GFP_ATOMIC);
-	if (!bl_work)
-		return -ENOMEM;
-
-	atomic_inc(&led->active);
+	blinkm_transfer_hw(led->i2c_client, BLM_GO_RGB);
 	dev_dbg(&led->i2c_client->dev,
-			"#TO_SCHED# next_red = %d, next_green = %d,"
-			" next_blue = %d, active = %d\n",
+			"# DONE # next_red = %d, next_green = %d,"
+			" next_blue = %d\n",
 			data->next_red, data->next_green,
-			data->next_blue, atomic_read(&led->active));
-
-	/* a fresh work _item_ for each change */
-	bl_work->blinkm_led = led;
-	INIT_WORK(&bl_work->work, led_work);
-	/* queue work in own queue for easy sync on exit*/
-	schedule_work(&bl_work->work);
-
+			data->next_blue);
 	return 0;
 }
 
-static void blinkm_led_red_set(struct led_classdev *led_cdev,
+static int blinkm_led_red_set(struct led_classdev *led_cdev,
 			       enum led_brightness value)
 {
-	blinkm_led_common_set(led_cdev, value, RED);
+	return blinkm_led_common_set(led_cdev, value, RED);
 }
 
-static void blinkm_led_green_set(struct led_classdev *led_cdev,
+static int blinkm_led_green_set(struct led_classdev *led_cdev,
 				 enum led_brightness value)
 {
-	blinkm_led_common_set(led_cdev, value, GREEN);
+	return blinkm_led_common_set(led_cdev, value, GREEN);
 }
 
-static void blinkm_led_blue_set(struct led_classdev *led_cdev,
+static int blinkm_led_blue_set(struct led_classdev *led_cdev,
 				enum led_brightness value)
 {
-	blinkm_led_common_set(led_cdev, value, BLUE);
+	return blinkm_led_common_set(led_cdev, value, BLUE);
 }
 
 static void blinkm_init_hw(struct i2c_client *client)
@@ -669,7 +616,6 @@
 		led[i]->id = i;
 		led[i]->led_cdev.max_brightness = 255;
 		led[i]->led_cdev.flags = LED_CORE_SUSPENDRESUME;
-		atomic_set(&led[i]->active, 0);
 		switch (i) {
 		case RED:
 			snprintf(blinkm_led_name, sizeof(blinkm_led_name),
@@ -677,7 +623,8 @@
 					 client->adapter->nr,
 					 client->addr);
 			led[i]->led_cdev.name = blinkm_led_name;
-			led[i]->led_cdev.brightness_set = blinkm_led_red_set;
+			led[i]->led_cdev.brightness_set_blocking =
+							blinkm_led_red_set;
 			err = led_classdev_register(&client->dev,
 						    &led[i]->led_cdev);
 			if (err < 0) {
@@ -693,7 +640,8 @@
 					 client->adapter->nr,
 					 client->addr);
 			led[i]->led_cdev.name = blinkm_led_name;
-			led[i]->led_cdev.brightness_set = blinkm_led_green_set;
+			led[i]->led_cdev.brightness_set_blocking =
+							blinkm_led_green_set;
 			err = led_classdev_register(&client->dev,
 						    &led[i]->led_cdev);
 			if (err < 0) {
@@ -709,7 +657,8 @@
 					 client->adapter->nr,
 					 client->addr);
 			led[i]->led_cdev.name = blinkm_led_name;
-			led[i]->led_cdev.brightness_set = blinkm_led_blue_set;
+			led[i]->led_cdev.brightness_set_blocking =
+							blinkm_led_blue_set;
 			err = led_classdev_register(&client->dev,
 						    &led[i]->led_cdev);
 			if (err < 0) {
@@ -746,10 +695,8 @@
 	int i;
 
 	/* make sure no workqueue entries are pending */
-	for (i = 0; i < 3; i++) {
-		flush_scheduled_work();
+	for (i = 0; i < 3; i++)
 		led_classdev_unregister(&data->blinkm_leds[i].led_cdev);
-	}
 
 	/* reset rgb */
 	data->next_red = 0x00;
diff --git a/drivers/leds/leds-da903x.c b/drivers/leds/leds-da903x.c
index 952ba96e..4752a2b 100644
--- a/drivers/leds/leds-da903x.c
+++ b/drivers/leds/leds-da903x.c
@@ -16,7 +16,6 @@
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
 #include <linux/leds.h>
-#include <linux/workqueue.h>
 #include <linux/mfd/da903x.h>
 #include <linux/slab.h>
 
@@ -33,9 +32,7 @@
 
 struct da903x_led {
 	struct led_classdev	cdev;
-	struct work_struct	work;
 	struct device		*master;
-	enum led_brightness	new_brightness;
 	int			id;
 	int			flags;
 };
@@ -43,11 +40,13 @@
 #define DA9030_LED_OFFSET(id)	((id) - DA9030_ID_LED_1)
 #define DA9034_LED_OFFSET(id)	((id) - DA9034_ID_LED_1)
 
-static void da903x_led_work(struct work_struct *work)
+static int da903x_led_set(struct led_classdev *led_cdev,
+			   enum led_brightness value)
 {
-	struct da903x_led *led = container_of(work, struct da903x_led, work);
+	struct da903x_led *led =
+			container_of(led_cdev, struct da903x_led, cdev);
 	uint8_t val;
-	int offset;
+	int offset, ret = -EINVAL;
 
 	switch (led->id) {
 	case DA9030_ID_LED_1:
@@ -57,37 +56,31 @@
 	case DA9030_ID_LED_PC:
 		offset = DA9030_LED_OFFSET(led->id);
 		val = led->flags & ~0x87;
-		val |= (led->new_brightness) ? 0x80 : 0; /* EN bit */
-		val |= (0x7 - (led->new_brightness >> 5)) & 0x7; /* PWM<2:0> */
-		da903x_write(led->master, DA9030_LED1_CONTROL + offset, val);
+		val |= value ? 0x80 : 0; /* EN bit */
+		val |= (0x7 - (value >> 5)) & 0x7; /* PWM<2:0> */
+		ret = da903x_write(led->master, DA9030_LED1_CONTROL + offset,
+				   val);
 		break;
 	case DA9030_ID_VIBRA:
 		val = led->flags & ~0x80;
-		val |= (led->new_brightness) ? 0x80 : 0; /* EN bit */
-		da903x_write(led->master, DA9030_MISC_CONTROL_A, val);
+		val |= value ? 0x80 : 0; /* EN bit */
+		ret = da903x_write(led->master, DA9030_MISC_CONTROL_A, val);
 		break;
 	case DA9034_ID_LED_1:
 	case DA9034_ID_LED_2:
 		offset = DA9034_LED_OFFSET(led->id);
-		val = (led->new_brightness * 0x5f / LED_FULL) & 0x7f;
+		val = (value * 0x5f / LED_FULL) & 0x7f;
 		val |= (led->flags & DA9034_LED_RAMP) ? 0x80 : 0;
-		da903x_write(led->master, DA9034_LED1_CONTROL + offset, val);
+		ret = da903x_write(led->master, DA9034_LED1_CONTROL + offset,
+				   val);
 		break;
 	case DA9034_ID_VIBRA:
-		val = led->new_brightness & 0xfe;
-		da903x_write(led->master, DA9034_VIBRA, val);
+		val = value & 0xfe;
+		ret = da903x_write(led->master, DA9034_VIBRA, val);
 		break;
 	}
-}
 
-static void da903x_led_set(struct led_classdev *led_cdev,
-			   enum led_brightness value)
-{
-	struct da903x_led *led;
-
-	led = container_of(led_cdev, struct da903x_led, cdev);
-	led->new_brightness = value;
-	schedule_work(&led->work);
+	return ret;
 }
 
 static int da903x_led_probe(struct platform_device *pdev)
@@ -113,15 +106,12 @@
 
 	led->cdev.name = pdata->name;
 	led->cdev.default_trigger = pdata->default_trigger;
-	led->cdev.brightness_set = da903x_led_set;
+	led->cdev.brightness_set_blocking = da903x_led_set;
 	led->cdev.brightness = LED_OFF;
 
 	led->id = id;
 	led->flags = pdata->flags;
 	led->master = pdev->dev.parent;
-	led->new_brightness = LED_OFF;
-
-	INIT_WORK(&led->work, da903x_led_work);
 
 	ret = led_classdev_register(led->master, &led->cdev);
 	if (ret) {
diff --git a/drivers/leds/leds-da9052.c b/drivers/leds/leds-da9052.c
index 28291b6..f8c7d82 100644
--- a/drivers/leds/leds-da9052.c
+++ b/drivers/leds/leds-da9052.c
@@ -16,7 +16,6 @@
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
 #include <linux/leds.h>
-#include <linux/workqueue.h>
 #include <linux/slab.h>
 
 #include <linux/mfd/da9052/reg.h>
@@ -32,11 +31,9 @@
 
 struct da9052_led {
 	struct led_classdev cdev;
-	struct work_struct work;
 	struct da9052 *da9052;
 	unsigned char led_index;
 	unsigned char id;
-	int brightness;
 };
 
 static unsigned char led_reg[] = {
@@ -44,12 +41,13 @@
 	DA9052_LED_CONT_5_REG,
 };
 
-static int da9052_set_led_brightness(struct da9052_led *led)
+static int da9052_set_led_brightness(struct da9052_led *led,
+				     enum led_brightness brightness)
 {
 	u8 val;
 	int error;
 
-	val = (led->brightness & 0x7f) | DA9052_LED_CONT_DIM;
+	val = (brightness & 0x7f) | DA9052_LED_CONT_DIM;
 
 	error = da9052_reg_write(led->da9052, led_reg[led->led_index], val);
 	if (error < 0)
@@ -58,21 +56,13 @@
 	return error;
 }
 
-static void da9052_led_work(struct work_struct *work)
-{
-	struct da9052_led *led = container_of(work, struct da9052_led, work);
-
-	da9052_set_led_brightness(led);
-}
-
-static void da9052_led_set(struct led_classdev *led_cdev,
+static int da9052_led_set(struct led_classdev *led_cdev,
 			   enum led_brightness value)
 {
-	struct da9052_led *led;
+	struct da9052_led *led =
+			container_of(led_cdev, struct da9052_led, cdev);
 
-	led = container_of(led_cdev, struct da9052_led, cdev);
-	led->brightness = value;
-	schedule_work(&led->work);
+	return da9052_set_led_brightness(led, value);
 }
 
 static int da9052_configure_leds(struct da9052 *da9052)
@@ -133,13 +123,11 @@
 
 	for (i = 0; i < pled->num_leds; i++) {
 		led[i].cdev.name = pled->leds[i].name;
-		led[i].cdev.brightness_set = da9052_led_set;
+		led[i].cdev.brightness_set_blocking = da9052_led_set;
 		led[i].cdev.brightness = LED_OFF;
 		led[i].cdev.max_brightness = DA9052_MAX_BRIGHTNESS;
-		led[i].brightness = LED_OFF;
 		led[i].led_index = pled->leds[i].flags;
 		led[i].da9052 = dev_get_drvdata(pdev->dev.parent);
-		INIT_WORK(&led[i].work, da9052_led_work);
 
 		error = led_classdev_register(pdev->dev.parent, &led[i].cdev);
 		if (error) {
@@ -148,7 +136,8 @@
 			goto err_register;
 		}
 
-		error = da9052_set_led_brightness(&led[i]);
+		error = da9052_set_led_brightness(&led[i],
+						  led[i].cdev.brightness);
 		if (error) {
 			dev_err(&pdev->dev, "Unable to init led %d\n",
 				led[i].led_index);
@@ -166,10 +155,8 @@
 	return 0;
 
 err_register:
-	for (i = i - 1; i >= 0; i--) {
+	for (i = i - 1; i >= 0; i--)
 		led_classdev_unregister(&led[i].cdev);
-		cancel_work_sync(&led[i].work);
-	}
 err:
 	return error;
 }
@@ -187,10 +174,8 @@
 	pled = pdata->pled;
 
 	for (i = 0; i < pled->num_leds; i++) {
-		led[i].brightness = 0;
-		da9052_set_led_brightness(&led[i]);
+		da9052_set_led_brightness(&led[i], LED_OFF);
 		led_classdev_unregister(&led[i].cdev);
-		cancel_work_sync(&led[i].work);
 	}
 
 	return 0;
diff --git a/drivers/leds/leds-dac124s085.c b/drivers/leds/leds-dac124s085.c
index 3141596..5a5a86d 100644
--- a/drivers/leds/leds-dac124s085.c
+++ b/drivers/leds/leds-dac124s085.c
@@ -13,20 +13,15 @@
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
-#include <linux/spinlock.h>
-#include <linux/workqueue.h>
 #include <linux/spi/spi.h>
 
 struct dac124s085_led {
 	struct led_classdev	ldev;
 	struct spi_device	*spi;
 	int			id;
-	int			brightness;
 	char			name[sizeof("dac124s085-3")];
 
 	struct mutex		mutex;
-	struct work_struct	work;
-	spinlock_t		lock;
 };
 
 struct dac124s085 {
@@ -38,29 +33,21 @@
 #define ALL_WRITE_UPDATE	(2 << 12)
 #define POWER_DOWN_OUTPUT	(3 << 12)
 
-static void dac124s085_led_work(struct work_struct *work)
-{
-	struct dac124s085_led *led = container_of(work, struct dac124s085_led,
-						  work);
-	u16 word;
-
-	mutex_lock(&led->mutex);
-	word = cpu_to_le16(((led->id) << 14) | REG_WRITE_UPDATE |
-			   (led->brightness & 0xfff));
-	spi_write(led->spi, (const u8 *)&word, sizeof(word));
-	mutex_unlock(&led->mutex);
-}
-
-static void dac124s085_set_brightness(struct led_classdev *ldev,
+static int dac124s085_set_brightness(struct led_classdev *ldev,
 				      enum led_brightness brightness)
 {
 	struct dac124s085_led *led = container_of(ldev, struct dac124s085_led,
 						  ldev);
+	u16 word;
+	int ret;
 
-	spin_lock(&led->lock);
-	led->brightness = brightness;
-	schedule_work(&led->work);
-	spin_unlock(&led->lock);
+	mutex_lock(&led->mutex);
+	word = cpu_to_le16(((led->id) << 14) | REG_WRITE_UPDATE |
+			   (brightness & 0xfff));
+	ret = spi_write(led->spi, (const u8 *)&word, sizeof(word));
+	mutex_unlock(&led->mutex);
+
+	return ret;
 }
 
 static int dac124s085_probe(struct spi_device *spi)
@@ -78,16 +65,13 @@
 	for (i = 0; i < ARRAY_SIZE(dac->leds); i++) {
 		led		= dac->leds + i;
 		led->id		= i;
-		led->brightness	= LED_OFF;
 		led->spi	= spi;
 		snprintf(led->name, sizeof(led->name), "dac124s085-%d", i);
-		spin_lock_init(&led->lock);
-		INIT_WORK(&led->work, dac124s085_led_work);
 		mutex_init(&led->mutex);
 		led->ldev.name = led->name;
 		led->ldev.brightness = LED_OFF;
 		led->ldev.max_brightness = 0xfff;
-		led->ldev.brightness_set = dac124s085_set_brightness;
+		led->ldev.brightness_set_blocking = dac124s085_set_brightness;
 		ret = led_classdev_register(&spi->dev, &led->ldev);
 		if (ret < 0)
 			goto eledcr;
@@ -109,10 +93,8 @@
 	struct dac124s085	*dac = spi_get_drvdata(spi);
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(dac->leds); i++) {
+	for (i = 0; i < ARRAY_SIZE(dac->leds); i++)
 		led_classdev_unregister(&dac->leds[i].ldev);
-		cancel_work_sync(&dac->leds[i].work);
-	}
 
 	return 0;
 }
diff --git a/drivers/leds/leds-gpio.c b/drivers/leds/leds-gpio.c
index 5db4515..7bc5328 100644
--- a/drivers/leds/leds-gpio.c
+++ b/drivers/leds/leds-gpio.c
@@ -20,32 +20,16 @@
 #include <linux/platform_device.h>
 #include <linux/property.h>
 #include <linux/slab.h>
-#include <linux/workqueue.h>
 
 struct gpio_led_data {
 	struct led_classdev cdev;
 	struct gpio_desc *gpiod;
-	struct work_struct work;
-	u8 new_level;
 	u8 can_sleep;
 	u8 blinking;
 	int (*platform_gpio_blink_set)(struct gpio_desc *desc, int state,
 			unsigned long *delay_on, unsigned long *delay_off);
 };
 
-static void gpio_led_work(struct work_struct *work)
-{
-	struct gpio_led_data *led_dat =
-		container_of(work, struct gpio_led_data, work);
-
-	if (led_dat->blinking) {
-		led_dat->platform_gpio_blink_set(led_dat->gpiod,
-					led_dat->new_level, NULL, NULL);
-		led_dat->blinking = 0;
-	} else
-		gpiod_set_value_cansleep(led_dat->gpiod, led_dat->new_level);
-}
-
 static void gpio_led_set(struct led_classdev *led_cdev,
 	enum led_brightness value)
 {
@@ -58,23 +42,25 @@
 	else
 		level = 1;
 
-	/* Setting GPIOs with I2C/etc requires a task context, and we don't
-	 * seem to have a reliable way to know if we're already in one; so
-	 * let's just assume the worst.
-	 */
-	if (led_dat->can_sleep) {
-		led_dat->new_level = level;
-		schedule_work(&led_dat->work);
+	if (led_dat->blinking) {
+		led_dat->platform_gpio_blink_set(led_dat->gpiod, level,
+						 NULL, NULL);
+		led_dat->blinking = 0;
 	} else {
-		if (led_dat->blinking) {
-			led_dat->platform_gpio_blink_set(led_dat->gpiod, level,
-							 NULL, NULL);
-			led_dat->blinking = 0;
-		} else
+		if (led_dat->can_sleep)
+			gpiod_set_value_cansleep(led_dat->gpiod, level);
+		else
 			gpiod_set_value(led_dat->gpiod, level);
 	}
 }
 
+static int gpio_led_set_blocking(struct led_classdev *led_cdev,
+	enum led_brightness value)
+{
+	gpio_led_set(led_cdev, value);
+	return 0;
+}
+
 static int gpio_blink_set(struct led_classdev *led_cdev,
 	unsigned long *delay_on, unsigned long *delay_off)
 {
@@ -125,12 +111,15 @@
 	led_dat->cdev.name = template->name;
 	led_dat->cdev.default_trigger = template->default_trigger;
 	led_dat->can_sleep = gpiod_cansleep(led_dat->gpiod);
+	if (!led_dat->can_sleep)
+		led_dat->cdev.brightness_set = gpio_led_set;
+	else
+		led_dat->cdev.brightness_set_blocking = gpio_led_set_blocking;
 	led_dat->blinking = 0;
 	if (blink_set) {
 		led_dat->platform_gpio_blink_set = blink_set;
 		led_dat->cdev.blink_set = gpio_blink_set;
 	}
-	led_dat->cdev.brightness_set = gpio_led_set;
 	if (template->default_state == LEDS_GPIO_DEFSTATE_KEEP)
 		state = !!gpiod_get_value_cansleep(led_dat->gpiod);
 	else
@@ -143,17 +132,9 @@
 	if (ret < 0)
 		return ret;
 
-	INIT_WORK(&led_dat->work, gpio_led_work);
-
 	return led_classdev_register(parent, &led_dat->cdev);
 }
 
-static void delete_gpio_led(struct gpio_led_data *led)
-{
-	led_classdev_unregister(&led->cdev);
-	cancel_work_sync(&led->work);
-}
-
 struct gpio_leds_priv {
 	int num_leds;
 	struct gpio_led_data leds[];
@@ -233,7 +214,7 @@
 
 err:
 	for (count = priv->num_leds - 1; count >= 0; count--)
-		delete_gpio_led(&priv->leds[count]);
+		led_classdev_unregister(&priv->leds[count].cdev);
 	return ERR_PTR(ret);
 }
 
@@ -265,7 +246,8 @@
 			if (ret < 0) {
 				/* On failure: unwind the led creations */
 				for (i = i - 1; i >= 0; i--)
-					delete_gpio_led(&priv->leds[i]);
+					led_classdev_unregister(
+							&priv->leds[i].cdev);
 				return ret;
 			}
 		}
@@ -286,7 +268,7 @@
 	int i;
 
 	for (i = 0; i < priv->num_leds; i++)
-		delete_gpio_led(&priv->leds[i]);
+		led_classdev_unregister(&priv->leds[i].cdev);
 
 	return 0;
 }
diff --git a/drivers/leds/leds-ipaq-micro.c b/drivers/leds/leds-ipaq-micro.c
index fa262b6..02f1733 100644
--- a/drivers/leds/leds-ipaq-micro.c
+++ b/drivers/leds/leds-ipaq-micro.c
@@ -20,7 +20,7 @@
 #define LED_AUTOSTOP (1 << 5) /* LED ON/OFF auto stop set 0:disable, 1:enable */
 #define LED_ALWAYS   (1 << 6) /* LED Interrupt Mask 0:No mask, 1:mask         */
 
-static void micro_leds_brightness_set(struct led_classdev *led_cdev,
+static int micro_leds_brightness_set(struct led_classdev *led_cdev,
 				      enum led_brightness value)
 {
 	struct ipaq_micro *micro = dev_get_drvdata(led_cdev->dev->parent->parent);
@@ -50,7 +50,7 @@
 		msg.tx_data[2] = 1;
 		msg.tx_data[3] = 0; /* Duty cycle 256 */
 	}
-	ipaq_micro_tx_msg_sync(micro, &msg);
+	return ipaq_micro_tx_msg_sync(micro, &msg);
 }
 
 /* Maximum duty cycle in ms 256/10 sec = 25600 ms */
@@ -102,7 +102,7 @@
 
 static struct led_classdev micro_led = {
 	.name			= "led-ipaq-micro",
-	.brightness_set		= micro_leds_brightness_set,
+	.brightness_set_blocking = micro_leds_brightness_set,
 	.blink_set		= micro_leds_blink_set,
 	.flags			= LED_CORE_SUSPENDRESUME,
 };
diff --git a/drivers/leds/leds-ktd2692.c b/drivers/leds/leds-ktd2692.c
index feca07b..bf23ba1 100644
--- a/drivers/leds/leds-ktd2692.c
+++ b/drivers/leds/leds-ktd2692.c
@@ -18,7 +18,6 @@
 #include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/regulator/consumer.h>
-#include <linux/workqueue.h>
 
 /* Value related the movie mode */
 #define KTD2692_MOVIE_MODE_CURRENT_LEVELS	16
@@ -82,7 +81,6 @@
 	/* secures access to the device */
 	struct mutex lock;
 	struct regulator *regulator;
-	struct work_struct work_brightness_set;
 
 	struct gpio_desc *aux_gpio;
 	struct gpio_desc *ctrl_gpio;
@@ -158,9 +156,12 @@
 	ktd2692_expresswire_end(led);
 }
 
-static void ktd2692_brightness_set(struct ktd2692_context *led,
-				   enum led_brightness brightness)
+static int ktd2692_led_brightness_set(struct led_classdev *led_cdev,
+				       enum led_brightness brightness)
 {
+	struct led_classdev_flash *fled_cdev = lcdev_to_flcdev(led_cdev);
+	struct ktd2692_context *led = fled_cdev_to_led(fled_cdev);
+
 	mutex_lock(&led->lock);
 
 	if (brightness == LED_OFF) {
@@ -174,33 +175,6 @@
 
 	ktd2692_expresswire_write(led, led->mode | KTD2692_REG_MODE_BASE);
 	mutex_unlock(&led->lock);
-}
-
-static void ktd2692_brightness_set_work(struct work_struct *work)
-{
-	struct ktd2692_context *led =
-		container_of(work, struct ktd2692_context, work_brightness_set);
-
-	ktd2692_brightness_set(led, led->torch_brightness);
-}
-
-static void ktd2692_led_brightness_set(struct led_classdev *led_cdev,
-				       enum led_brightness brightness)
-{
-	struct led_classdev_flash *fled_cdev = lcdev_to_flcdev(led_cdev);
-	struct ktd2692_context *led = fled_cdev_to_led(fled_cdev);
-
-	led->torch_brightness = brightness;
-	schedule_work(&led->work_brightness_set);
-}
-
-static int ktd2692_led_brightness_set_sync(struct led_classdev *led_cdev,
-					   enum led_brightness brightness)
-{
-	struct led_classdev_flash *fled_cdev = lcdev_to_flcdev(led_cdev);
-	struct ktd2692_context *led = fled_cdev_to_led(fled_cdev);
-
-	ktd2692_brightness_set(led, brightness);
 
 	return 0;
 }
@@ -332,21 +306,24 @@
 				   &cfg->movie_max_microamp);
 	if (ret) {
 		dev_err(dev, "failed to parse led-max-microamp\n");
-		return ret;
+		goto err_parse_dt;
 	}
 
 	ret = of_property_read_u32(child_node, "flash-max-microamp",
 				   &cfg->flash_max_microamp);
 	if (ret) {
 		dev_err(dev, "failed to parse flash-max-microamp\n");
-		return ret;
+		goto err_parse_dt;
 	}
 
 	ret = of_property_read_u32(child_node, "flash-max-timeout-us",
 				   &cfg->flash_max_timeout);
-	if (ret)
+	if (ret) {
 		dev_err(dev, "failed to parse flash-max-timeout-us\n");
+		goto err_parse_dt;
+	}
 
+err_parse_dt:
 	of_node_put(child_node);
 	return ret;
 }
@@ -381,12 +358,10 @@
 	fled_cdev->ops = &flash_ops;
 
 	led_cdev->max_brightness = led_cfg.max_brightness;
-	led_cdev->brightness_set = ktd2692_led_brightness_set;
-	led_cdev->brightness_set_sync = ktd2692_led_brightness_set_sync;
+	led_cdev->brightness_set_blocking = ktd2692_led_brightness_set;
 	led_cdev->flags |= LED_CORE_SUSPENDRESUME | LED_DEV_CAP_FLASH;
 
 	mutex_init(&led->lock);
-	INIT_WORK(&led->work_brightness_set, ktd2692_brightness_set_work);
 
 	platform_set_drvdata(pdev, led);
 
@@ -408,7 +383,6 @@
 	int ret;
 
 	led_classdev_flash_unregister(&led->fled_cdev);
-	cancel_work_sync(&led->work_brightness_set);
 
 	if (led->regulator) {
 		ret = regulator_disable(led->regulator);
diff --git a/drivers/leds/leds-lm3533.c b/drivers/leds/leds-lm3533.c
index 6e2e020..196dcb5 100644
--- a/drivers/leds/leds-lm3533.c
+++ b/drivers/leds/leds-lm3533.c
@@ -17,7 +17,6 @@
 #include <linux/mutex.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
-#include <linux/workqueue.h>
 
 #include <linux/mfd/lm3533.h>
 
@@ -53,9 +52,6 @@
 
 	struct mutex mutex;
 	unsigned long flags;
-
-	struct work_struct work;
-	u8 new_brightness;
 };
 
 
@@ -123,27 +119,17 @@
 	return ret;
 }
 
-static void lm3533_led_work(struct work_struct *work)
-{
-	struct lm3533_led *led = container_of(work, struct lm3533_led, work);
-
-	dev_dbg(led->cdev.dev, "%s - %u\n", __func__, led->new_brightness);
-
-	if (led->new_brightness == 0)
-		lm3533_led_pattern_enable(led, 0);	/* disable blink */
-
-	lm3533_ctrlbank_set_brightness(&led->cb, led->new_brightness);
-}
-
-static void lm3533_led_set(struct led_classdev *cdev,
+static int lm3533_led_set(struct led_classdev *cdev,
 						enum led_brightness value)
 {
 	struct lm3533_led *led = to_lm3533_led(cdev);
 
 	dev_dbg(led->cdev.dev, "%s - %d\n", __func__, value);
 
-	led->new_brightness = value;
-	schedule_work(&led->work);
+	if (value == 0)
+		lm3533_led_pattern_enable(led, 0);	/* disable blink */
+
+	return lm3533_ctrlbank_set_brightness(&led->cb, value);
 }
 
 static enum led_brightness lm3533_led_get(struct led_classdev *cdev)
@@ -693,7 +679,7 @@
 	led->lm3533 = lm3533;
 	led->cdev.name = pdata->name;
 	led->cdev.default_trigger = pdata->default_trigger;
-	led->cdev.brightness_set = lm3533_led_set;
+	led->cdev.brightness_set_blocking = lm3533_led_set;
 	led->cdev.brightness_get = lm3533_led_get;
 	led->cdev.blink_set = lm3533_led_blink_set;
 	led->cdev.brightness = LED_OFF;
@@ -701,7 +687,6 @@
 	led->id = pdev->id;
 
 	mutex_init(&led->mutex);
-	INIT_WORK(&led->work, lm3533_led_work);
 
 	/* The class framework makes a callback to get brightness during
 	 * registration so use parent device (for error reporting) until
@@ -733,7 +718,6 @@
 
 err_unregister:
 	led_classdev_unregister(&led->cdev);
-	flush_work(&led->work);
 
 	return ret;
 }
@@ -746,7 +730,6 @@
 
 	lm3533_ctrlbank_disable(&led->cb);
 	led_classdev_unregister(&led->cdev);
-	flush_work(&led->work);
 
 	return 0;
 }
@@ -760,7 +743,6 @@
 
 	lm3533_ctrlbank_disable(&led->cb);
 	lm3533_led_set(&led->cdev, LED_OFF);		/* disable blink */
-	flush_work(&led->work);
 }
 
 static struct platform_driver lm3533_led_driver = {
diff --git a/drivers/leds/leds-lm355x.c b/drivers/leds/leds-lm355x.c
index 48872997..6cb94f9 100644
--- a/drivers/leds/leds-lm355x.c
+++ b/drivers/leds/leds-lm355x.c
@@ -16,7 +16,6 @@
 #include <linux/platform_device.h>
 #include <linux/fs.h>
 #include <linux/regmap.h>
-#include <linux/workqueue.h>
 #include <linux/platform_data/leds-lm355x.h>
 
 enum lm355x_type {
@@ -59,14 +58,6 @@
 	struct led_classdev cdev_torch;
 	struct led_classdev cdev_indicator;
 
-	struct work_struct work_flash;
-	struct work_struct work_torch;
-	struct work_struct work_indicator;
-
-	u8 br_flash;
-	u8 br_torch;
-	u8 br_indicator;
-
 	struct lm355x_platform_data *pdata;
 	struct regmap *regmap;
 	struct mutex lock;
@@ -204,7 +195,7 @@
 }
 
 /* chip control */
-static void lm355x_control(struct lm355x_chip_data *chip,
+static int lm355x_control(struct lm355x_chip_data *chip,
 			   u8 brightness, enum lm355x_mode opmode)
 {
 	int ret;
@@ -301,7 +292,7 @@
 	case MODE_SHDN:
 		break;
 	default:
-		return;
+		return -EINVAL;
 	}
 	/* operation mode control */
 	ret = regmap_update_bits(chip->regmap, preg[REG_OPMODE].regno,
@@ -309,73 +300,55 @@
 				 opmode << preg[REG_OPMODE].shift);
 	if (ret < 0)
 		goto out;
-	return;
+	return ret;
 out:
 	dev_err(chip->dev, "%s:i2c access fail to register\n", __func__);
-	return;
+	return ret;
 }
 
 /* torch */
-static void lm355x_deferred_torch_brightness_set(struct work_struct *work)
-{
-	struct lm355x_chip_data *chip =
-	    container_of(work, struct lm355x_chip_data, work_torch);
 
-	mutex_lock(&chip->lock);
-	lm355x_control(chip, chip->br_torch, MODE_TORCH);
-	mutex_unlock(&chip->lock);
-}
-
-static void lm355x_torch_brightness_set(struct led_classdev *cdev,
+static int lm355x_torch_brightness_set(struct led_classdev *cdev,
 					enum led_brightness brightness)
 {
 	struct lm355x_chip_data *chip =
 	    container_of(cdev, struct lm355x_chip_data, cdev_torch);
+	int ret;
 
-	chip->br_torch = brightness;
-	schedule_work(&chip->work_torch);
+	mutex_lock(&chip->lock);
+	ret = lm355x_control(chip, brightness, MODE_TORCH);
+	mutex_unlock(&chip->lock);
+	return ret;
 }
 
 /* flash */
-static void lm355x_deferred_strobe_brightness_set(struct work_struct *work)
-{
-	struct lm355x_chip_data *chip =
-	    container_of(work, struct lm355x_chip_data, work_flash);
 
-	mutex_lock(&chip->lock);
-	lm355x_control(chip, chip->br_flash, MODE_FLASH);
-	mutex_unlock(&chip->lock);
-}
-
-static void lm355x_strobe_brightness_set(struct led_classdev *cdev,
+static int lm355x_strobe_brightness_set(struct led_classdev *cdev,
 					 enum led_brightness brightness)
 {
 	struct lm355x_chip_data *chip =
 	    container_of(cdev, struct lm355x_chip_data, cdev_flash);
+	int ret;
 
-	chip->br_flash = brightness;
-	schedule_work(&chip->work_flash);
+	mutex_lock(&chip->lock);
+	ret = lm355x_control(chip, brightness, MODE_FLASH);
+	mutex_unlock(&chip->lock);
+	return ret;
 }
 
 /* indicator */
-static void lm355x_deferred_indicator_brightness_set(struct work_struct *work)
-{
-	struct lm355x_chip_data *chip =
-	    container_of(work, struct lm355x_chip_data, work_indicator);
 
-	mutex_lock(&chip->lock);
-	lm355x_control(chip, chip->br_indicator, MODE_INDIC);
-	mutex_unlock(&chip->lock);
-}
-
-static void lm355x_indicator_brightness_set(struct led_classdev *cdev,
+static int lm355x_indicator_brightness_set(struct led_classdev *cdev,
 					    enum led_brightness brightness)
 {
 	struct lm355x_chip_data *chip =
 	    container_of(cdev, struct lm355x_chip_data, cdev_indicator);
+	int ret;
 
-	chip->br_indicator = brightness;
-	schedule_work(&chip->work_indicator);
+	mutex_lock(&chip->lock);
+	ret = lm355x_control(chip, brightness, MODE_INDIC);
+	mutex_unlock(&chip->lock);
+	return ret;
 }
 
 /* indicator pattern only for lm3556*/
@@ -479,34 +452,31 @@
 		goto err_out;
 
 	/* flash */
-	INIT_WORK(&chip->work_flash, lm355x_deferred_strobe_brightness_set);
 	chip->cdev_flash.name = "flash";
 	chip->cdev_flash.max_brightness = 16;
-	chip->cdev_flash.brightness_set = lm355x_strobe_brightness_set;
+	chip->cdev_flash.brightness_set_blocking = lm355x_strobe_brightness_set;
 	chip->cdev_flash.default_trigger = "flash";
 	err = led_classdev_register((struct device *)
 				    &client->dev, &chip->cdev_flash);
 	if (err < 0)
 		goto err_out;
 	/* torch */
-	INIT_WORK(&chip->work_torch, lm355x_deferred_torch_brightness_set);
 	chip->cdev_torch.name = "torch";
 	chip->cdev_torch.max_brightness = 8;
-	chip->cdev_torch.brightness_set = lm355x_torch_brightness_set;
+	chip->cdev_torch.brightness_set_blocking = lm355x_torch_brightness_set;
 	chip->cdev_torch.default_trigger = "torch";
 	err = led_classdev_register((struct device *)
 				    &client->dev, &chip->cdev_torch);
 	if (err < 0)
 		goto err_create_torch_file;
 	/* indicator */
-	INIT_WORK(&chip->work_indicator,
-		  lm355x_deferred_indicator_brightness_set);
 	chip->cdev_indicator.name = "indicator";
 	if (id->driver_data == CHIP_LM3554)
 		chip->cdev_indicator.max_brightness = 4;
 	else
 		chip->cdev_indicator.max_brightness = 8;
-	chip->cdev_indicator.brightness_set = lm355x_indicator_brightness_set;
+	chip->cdev_indicator.brightness_set_blocking =
+					lm355x_indicator_brightness_set;
 	/* indicator pattern control only for LM3556 */
 	if (id->driver_data == CHIP_LM3556)
 		chip->cdev_indicator.groups = lm355x_indicator_groups;
@@ -534,11 +504,8 @@
 
 	regmap_write(chip->regmap, preg[REG_OPMODE].regno, 0);
 	led_classdev_unregister(&chip->cdev_indicator);
-	flush_work(&chip->work_indicator);
 	led_classdev_unregister(&chip->cdev_torch);
-	flush_work(&chip->work_torch);
 	led_classdev_unregister(&chip->cdev_flash);
-	flush_work(&chip->work_flash);
 	dev_info(&client->dev, "%s is removed\n", lm355x_name[chip->type]);
 
 	return 0;
diff --git a/drivers/leds/leds-lm3642.c b/drivers/leds/leds-lm3642.c
index 02ebe34..cada084 100644
--- a/drivers/leds/leds-lm3642.c
+++ b/drivers/leds/leds-lm3642.c
@@ -15,7 +15,6 @@
 #include <linux/platform_device.h>
 #include <linux/fs.h>
 #include <linux/regmap.h>
-#include <linux/workqueue.h>
 #include <linux/platform_data/leds-lm3642.h>
 
 #define	REG_FILT_TIME			(0x0)
@@ -73,10 +72,6 @@
 	struct led_classdev cdev_torch;
 	struct led_classdev cdev_indicator;
 
-	struct work_struct work_flash;
-	struct work_struct work_torch;
-	struct work_struct work_indicator;
-
 	u8 br_flash;
 	u8 br_torch;
 	u8 br_indicator;
@@ -209,24 +204,18 @@
 
 static DEVICE_ATTR(torch_pin, S_IWUSR, NULL, lm3642_torch_pin_store);
 
-static void lm3642_deferred_torch_brightness_set(struct work_struct *work)
-{
-	struct lm3642_chip_data *chip =
-	    container_of(work, struct lm3642_chip_data, work_torch);
-
-	mutex_lock(&chip->lock);
-	lm3642_control(chip, chip->br_torch, MODES_TORCH);
-	mutex_unlock(&chip->lock);
-}
-
-static void lm3642_torch_brightness_set(struct led_classdev *cdev,
+static int lm3642_torch_brightness_set(struct led_classdev *cdev,
 					enum led_brightness brightness)
 {
 	struct lm3642_chip_data *chip =
 	    container_of(cdev, struct lm3642_chip_data, cdev_torch);
+	int ret;
 
+	mutex_lock(&chip->lock);
 	chip->br_torch = brightness;
-	schedule_work(&chip->work_torch);
+	ret = lm3642_control(chip, chip->br_torch, MODES_TORCH);
+	mutex_unlock(&chip->lock);
+	return ret;
 }
 
 /* flash */
@@ -266,45 +255,33 @@
 
 static DEVICE_ATTR(strobe_pin, S_IWUSR, NULL, lm3642_strobe_pin_store);
 
-static void lm3642_deferred_strobe_brightness_set(struct work_struct *work)
-{
-	struct lm3642_chip_data *chip =
-	    container_of(work, struct lm3642_chip_data, work_flash);
-
-	mutex_lock(&chip->lock);
-	lm3642_control(chip, chip->br_flash, MODES_FLASH);
-	mutex_unlock(&chip->lock);
-}
-
-static void lm3642_strobe_brightness_set(struct led_classdev *cdev,
+static int lm3642_strobe_brightness_set(struct led_classdev *cdev,
 					 enum led_brightness brightness)
 {
 	struct lm3642_chip_data *chip =
 	    container_of(cdev, struct lm3642_chip_data, cdev_flash);
+	int ret;
 
+	mutex_lock(&chip->lock);
 	chip->br_flash = brightness;
-	schedule_work(&chip->work_flash);
+	ret = lm3642_control(chip, chip->br_flash, MODES_FLASH);
+	mutex_unlock(&chip->lock);
+	return ret;
 }
 
 /* indicator */
-static void lm3642_deferred_indicator_brightness_set(struct work_struct *work)
-{
-	struct lm3642_chip_data *chip =
-	    container_of(work, struct lm3642_chip_data, work_indicator);
-
-	mutex_lock(&chip->lock);
-	lm3642_control(chip, chip->br_indicator, MODES_INDIC);
-	mutex_unlock(&chip->lock);
-}
-
-static void lm3642_indicator_brightness_set(struct led_classdev *cdev,
+static int lm3642_indicator_brightness_set(struct led_classdev *cdev,
 					    enum led_brightness brightness)
 {
 	struct lm3642_chip_data *chip =
 	    container_of(cdev, struct lm3642_chip_data, cdev_indicator);
+	int ret;
 
+	mutex_lock(&chip->lock);
 	chip->br_indicator = brightness;
-	schedule_work(&chip->work_indicator);
+	ret = lm3642_control(chip, chip->br_indicator, MODES_INDIC);
+	mutex_unlock(&chip->lock);
+	return ret;
 }
 
 static const struct regmap_config lm3642_regmap = {
@@ -371,10 +348,9 @@
 		goto err_out;
 
 	/* flash */
-	INIT_WORK(&chip->work_flash, lm3642_deferred_strobe_brightness_set);
 	chip->cdev_flash.name = "flash";
 	chip->cdev_flash.max_brightness = 16;
-	chip->cdev_flash.brightness_set = lm3642_strobe_brightness_set;
+	chip->cdev_flash.brightness_set_blocking = lm3642_strobe_brightness_set;
 	chip->cdev_flash.default_trigger = "flash";
 	chip->cdev_flash.groups = lm3642_flash_groups,
 	err = led_classdev_register((struct device *)
@@ -385,10 +361,9 @@
 	}
 
 	/* torch */
-	INIT_WORK(&chip->work_torch, lm3642_deferred_torch_brightness_set);
 	chip->cdev_torch.name = "torch";
 	chip->cdev_torch.max_brightness = 8;
-	chip->cdev_torch.brightness_set = lm3642_torch_brightness_set;
+	chip->cdev_torch.brightness_set_blocking = lm3642_torch_brightness_set;
 	chip->cdev_torch.default_trigger = "torch";
 	chip->cdev_torch.groups = lm3642_torch_groups,
 	err = led_classdev_register((struct device *)
@@ -399,11 +374,10 @@
 	}
 
 	/* indicator */
-	INIT_WORK(&chip->work_indicator,
-		  lm3642_deferred_indicator_brightness_set);
 	chip->cdev_indicator.name = "indicator";
 	chip->cdev_indicator.max_brightness = 8;
-	chip->cdev_indicator.brightness_set = lm3642_indicator_brightness_set;
+	chip->cdev_indicator.brightness_set_blocking =
+						lm3642_indicator_brightness_set;
 	err = led_classdev_register((struct device *)
 				    &client->dev, &chip->cdev_indicator);
 	if (err < 0) {
@@ -427,11 +401,8 @@
 	struct lm3642_chip_data *chip = i2c_get_clientdata(client);
 
 	led_classdev_unregister(&chip->cdev_indicator);
-	flush_work(&chip->work_indicator);
 	led_classdev_unregister(&chip->cdev_torch);
-	flush_work(&chip->work_torch);
 	led_classdev_unregister(&chip->cdev_flash);
-	flush_work(&chip->work_flash);
 	regmap_write(chip->regmap, REG_ENABLE, 0);
 	return 0;
 }
diff --git a/drivers/leds/leds-lp3944.c b/drivers/leds/leds-lp3944.c
index 53144fb..6c758ae 100644
--- a/drivers/leds/leds-lp3944.c
+++ b/drivers/leds/leds-lp3944.c
@@ -31,7 +31,6 @@
 #include <linux/slab.h>
 #include <linux/leds.h>
 #include <linux/mutex.h>
-#include <linux/workqueue.h>
 #include <linux/leds-lp3944.h>
 
 /* Read Only Registers */
@@ -68,10 +67,8 @@
 struct lp3944_led_data {
 	u8 id;
 	enum lp3944_type type;
-	enum lp3944_status status;
 	struct led_classdev ldev;
 	struct i2c_client *client;
-	struct work_struct work;
 };
 
 struct lp3944_data {
@@ -275,13 +272,12 @@
 	dev_dbg(&led->client->dev, "%s: OK hardware accelerated blink!\n",
 		__func__);
 
-	led->status = LP3944_LED_STATUS_DIM0;
-	schedule_work(&led->work);
+	lp3944_led_set(led, LP3944_LED_STATUS_DIM0);
 
 	return 0;
 }
 
-static void lp3944_led_set_brightness(struct led_classdev *led_cdev,
+static int lp3944_led_set_brightness(struct led_classdev *led_cdev,
 				      enum led_brightness brightness)
 {
 	struct lp3944_led_data *led = ldev_to_led(led_cdev);
@@ -289,16 +285,7 @@
 	dev_dbg(&led->client->dev, "%s: %s, %d\n",
 		__func__, led_cdev->name, brightness);
 
-	led->status = !!brightness;
-	schedule_work(&led->work);
-}
-
-static void lp3944_led_work(struct work_struct *work)
-{
-	struct lp3944_led_data *led;
-
-	led = container_of(work, struct lp3944_led_data, work);
-	lp3944_led_set(led, led->status);
+	return lp3944_led_set(led, !!brightness);
 }
 
 static int lp3944_configure(struct i2c_client *client,
@@ -318,14 +305,13 @@
 		case LP3944_LED_TYPE_LED:
 		case LP3944_LED_TYPE_LED_INVERTED:
 			led->type = pled->type;
-			led->status = pled->status;
 			led->ldev.name = pled->name;
 			led->ldev.max_brightness = 1;
-			led->ldev.brightness_set = lp3944_led_set_brightness;
+			led->ldev.brightness_set_blocking =
+						lp3944_led_set_brightness;
 			led->ldev.blink_set = lp3944_led_set_blink;
 			led->ldev.flags = LED_CORE_SUSPENDRESUME;
 
-			INIT_WORK(&led->work, lp3944_led_work);
 			err = led_classdev_register(&client->dev, &led->ldev);
 			if (err < 0) {
 				dev_err(&client->dev,
@@ -336,14 +322,14 @@
 
 			/* to expose the default value to userspace */
 			led->ldev.brightness =
-					(enum led_brightness) led->status;
+					(enum led_brightness) pled->status;
 
 			/* Set the default led status */
-			err = lp3944_led_set(led, led->status);
+			err = lp3944_led_set(led, pled->status);
 			if (err < 0) {
 				dev_err(&client->dev,
 					"%s couldn't set STATUS %d\n",
-					led->ldev.name, led->status);
+					led->ldev.name, pled->status);
 				goto exit;
 			}
 			break;
@@ -364,7 +350,6 @@
 			case LP3944_LED_TYPE_LED:
 			case LP3944_LED_TYPE_LED_INVERTED:
 				led_classdev_unregister(&data->leds[i].ldev);
-				cancel_work_sync(&data->leds[i].work);
 				break;
 
 			case LP3944_LED_TYPE_NONE:
@@ -424,7 +409,6 @@
 		case LP3944_LED_TYPE_LED:
 		case LP3944_LED_TYPE_LED_INVERTED:
 			led_classdev_unregister(&data->leds[i].ldev);
-			cancel_work_sync(&data->leds[i].work);
 			break;
 
 		case LP3944_LED_TYPE_NONE:
diff --git a/drivers/leds/leds-lp5521.c b/drivers/leds/leds-lp5521.c
index 63a9254..549b315 100644
--- a/drivers/leds/leds-lp5521.c
+++ b/drivers/leds/leds-lp5521.c
@@ -362,16 +362,17 @@
 	return 0;
 }
 
-static void lp5521_led_brightness_work(struct work_struct *work)
+static int lp5521_led_brightness(struct lp55xx_led *led)
 {
-	struct lp55xx_led *led = container_of(work, struct lp55xx_led,
-					      brightness_work);
 	struct lp55xx_chip *chip = led->chip;
+	int ret;
 
 	mutex_lock(&chip->lock);
-	lp55xx_write(chip, LP5521_REG_LED_PWM_BASE + led->chan_nr,
+	ret = lp55xx_write(chip, LP5521_REG_LED_PWM_BASE + led->chan_nr,
 		led->brightness);
 	mutex_unlock(&chip->lock);
+
+	return ret;
 }
 
 static ssize_t show_engine_mode(struct device *dev,
@@ -501,7 +502,7 @@
 	},
 	.max_channel  = LP5521_MAX_LEDS,
 	.post_init_device   = lp5521_post_init_device,
-	.brightness_work_fn = lp5521_led_brightness_work,
+	.brightness_fn      = lp5521_led_brightness,
 	.set_led_current    = lp5521_set_led_current,
 	.firmware_cb        = lp5521_firmware_loaded,
 	.run_engine         = lp5521_run_engine,
diff --git a/drivers/leds/leds-lp5523.c b/drivers/leds/leds-lp5523.c
index 1d0187f..c5b30f0 100644
--- a/drivers/leds/leds-lp5523.c
+++ b/drivers/leds/leds-lp5523.c
@@ -802,16 +802,16 @@
 	return ret;
 }
 
-static void lp5523_led_brightness_work(struct work_struct *work)
+static int lp5523_led_brightness(struct lp55xx_led *led)
 {
-	struct lp55xx_led *led = container_of(work, struct lp55xx_led,
-					      brightness_work);
 	struct lp55xx_chip *chip = led->chip;
+	int ret;
 
 	mutex_lock(&chip->lock);
-	lp55xx_write(chip, LP5523_REG_LED_PWM_BASE + led->chan_nr,
+	ret = lp55xx_write(chip, LP5523_REG_LED_PWM_BASE + led->chan_nr,
 		     led->brightness);
 	mutex_unlock(&chip->lock);
+	return ret;
 }
 
 static LP55XX_DEV_ATTR_RW(engine1_mode, show_engine1_mode, store_engine1_mode);
@@ -867,7 +867,7 @@
 	},
 	.max_channel  = LP5523_MAX_LEDS,
 	.post_init_device   = lp5523_post_init_device,
-	.brightness_work_fn = lp5523_led_brightness_work,
+	.brightness_fn      = lp5523_led_brightness,
 	.set_led_current    = lp5523_set_led_current,
 	.firmware_cb        = lp5523_firmware_loaded,
 	.run_engine         = lp5523_run_engine,
diff --git a/drivers/leds/leds-lp5562.c b/drivers/leds/leds-lp5562.c
index 0360c59..b753338 100644
--- a/drivers/leds/leds-lp5562.c
+++ b/drivers/leds/leds-lp5562.c
@@ -311,10 +311,8 @@
 	return 0;
 }
 
-static void lp5562_led_brightness_work(struct work_struct *work)
+static int lp5562_led_brightness(struct lp55xx_led *led)
 {
-	struct lp55xx_led *led = container_of(work, struct lp55xx_led,
-					      brightness_work);
 	struct lp55xx_chip *chip = led->chip;
 	u8 addr[] = {
 		LP5562_REG_R_PWM,
@@ -322,10 +320,13 @@
 		LP5562_REG_B_PWM,
 		LP5562_REG_W_PWM,
 	};
+	int ret;
 
 	mutex_lock(&chip->lock);
-	lp55xx_write(chip, addr[led->chan_nr], led->brightness);
+	ret = lp55xx_write(chip, addr[led->chan_nr], led->brightness);
 	mutex_unlock(&chip->lock);
+
+	return ret;
 }
 
 static void lp5562_write_program_memory(struct lp55xx_chip *chip,
@@ -503,7 +504,7 @@
 	},
 	.post_init_device   = lp5562_post_init_device,
 	.set_led_current    = lp5562_set_led_current,
-	.brightness_work_fn = lp5562_led_brightness_work,
+	.brightness_fn      = lp5562_led_brightness,
 	.run_engine         = lp5562_run_engine,
 	.firmware_cb        = lp5562_firmware_loaded,
 	.dev_attr_group     = &lp5562_group,
diff --git a/drivers/leds/leds-lp55xx-common.c b/drivers/leds/leds-lp55xx-common.c
index 59b7683..5377f22 100644
--- a/drivers/leds/leds-lp55xx-common.c
+++ b/drivers/leds/leds-lp55xx-common.c
@@ -134,13 +134,14 @@
 };
 ATTRIBUTE_GROUPS(lp55xx_led);
 
-static void lp55xx_set_brightness(struct led_classdev *cdev,
+static int lp55xx_set_brightness(struct led_classdev *cdev,
 			     enum led_brightness brightness)
 {
 	struct lp55xx_led *led = cdev_to_lp55xx_led(cdev);
+	struct lp55xx_device_config *cfg = led->chip->cfg;
 
 	led->brightness = (u8)brightness;
-	schedule_work(&led->brightness_work);
+	return cfg->brightness_fn(led);
 }
 
 static int lp55xx_init_led(struct lp55xx_led *led,
@@ -172,7 +173,7 @@
 		return -EINVAL;
 	}
 
-	led->cdev.brightness_set = lp55xx_set_brightness;
+	led->cdev.brightness_set_blocking = lp55xx_set_brightness;
 	led->cdev.groups = lp55xx_led_groups;
 
 	if (pdata->led_config[chan].name) {
@@ -464,7 +465,7 @@
 	int ret;
 	int i;
 
-	if (!cfg->brightness_work_fn) {
+	if (!cfg->brightness_fn) {
 		dev_err(&chip->cl->dev, "empty brightness configuration\n");
 		return -EINVAL;
 	}
@@ -481,8 +482,6 @@
 		if (ret)
 			goto err_init_led;
 
-		INIT_WORK(&each->brightness_work, cfg->brightness_work_fn);
-
 		chip->num_leds++;
 		each->chip = chip;
 
@@ -507,7 +506,6 @@
 	for (i = 0; i < chip->num_leds; i++) {
 		each = led + i;
 		led_classdev_unregister(&each->cdev);
-		flush_work(&each->brightness_work);
 	}
 }
 EXPORT_SYMBOL_GPL(lp55xx_unregister_leds);
diff --git a/drivers/leds/leds-lp55xx-common.h b/drivers/leds/leds-lp55xx-common.h
index c7f1e61..abf1fb5 100644
--- a/drivers/leds/leds-lp55xx-common.h
+++ b/drivers/leds/leds-lp55xx-common.h
@@ -95,7 +95,7 @@
  * @enable             : Chip specific enable command
  * @max_channel        : Maximum number of channels
  * @post_init_device   : Chip specific initialization code
- * @brightness_work_fn : Brightness work function
+ * @brightness_fn      : Brightness function
  * @set_led_current    : LED current set function
  * @firmware_cb        : Call function when the firmware is loaded
  * @run_engine         : Run internal engine for pattern
@@ -110,7 +110,7 @@
 	int (*post_init_device) (struct lp55xx_chip *chip);
 
 	/* access brightness register */
-	void (*brightness_work_fn)(struct work_struct *work);
+	int (*brightness_fn)(struct lp55xx_led *led);
 
 	/* current setting function */
 	void (*set_led_current) (struct lp55xx_led *led, u8 led_current);
@@ -164,7 +164,6 @@
  * @cdev            : LED class device
  * @led_current     : Current setting at each led channel
  * @max_current     : Maximun current at each led channel
- * @brightness_work : Workqueue for brightness control
  * @brightness      : Brightness value
  * @chip            : The lp55xx chip data
  */
@@ -173,7 +172,6 @@
 	struct led_classdev cdev;
 	u8 led_current;
 	u8 max_current;
-	struct work_struct brightness_work;
 	u8 brightness;
 	struct lp55xx_chip *chip;
 };
diff --git a/drivers/leds/leds-lp8501.c b/drivers/leds/leds-lp8501.c
index 3f54f6f..3f9675b 100644
--- a/drivers/leds/leds-lp8501.c
+++ b/drivers/leds/leds-lp8501.c
@@ -272,16 +272,17 @@
 	lp8501_update_program_memory(chip, fw->data, fw->size);
 }
 
-static void lp8501_led_brightness_work(struct work_struct *work)
+static int lp8501_led_brightness(struct lp55xx_led *led)
 {
-	struct lp55xx_led *led = container_of(work, struct lp55xx_led,
-					      brightness_work);
 	struct lp55xx_chip *chip = led->chip;
+	int ret;
 
 	mutex_lock(&chip->lock);
-	lp55xx_write(chip, LP8501_REG_LED_PWM_BASE + led->chan_nr,
+	ret = lp55xx_write(chip, LP8501_REG_LED_PWM_BASE + led->chan_nr,
 		     led->brightness);
 	mutex_unlock(&chip->lock);
+
+	return ret;
 }
 
 /* Chip specific configurations */
@@ -296,7 +297,7 @@
 	},
 	.max_channel  = LP8501_MAX_LEDS,
 	.post_init_device   = lp8501_post_init_device,
-	.brightness_work_fn = lp8501_led_brightness_work,
+	.brightness_fn      = lp8501_led_brightness,
 	.set_led_current    = lp8501_set_led_current,
 	.firmware_cb        = lp8501_firmware_loaded,
 	.run_engine         = lp8501_run_engine,
diff --git a/drivers/leds/leds-lp8788.c b/drivers/leds/leds-lp8788.c
index 3409f03..0eee38f 100644
--- a/drivers/leds/leds-lp8788.c
+++ b/drivers/leds/leds-lp8788.c
@@ -26,10 +26,8 @@
 struct lp8788_led {
 	struct lp8788 *lp;
 	struct mutex lock;
-	struct work_struct work;
 	struct led_classdev led_dev;
 	enum lp8788_isink_number isink_num;
-	enum led_brightness brightness;
 	int on;
 };
 
@@ -76,24 +74,29 @@
 	return lp8788_update_bits(led->lp, addr, mask, val);
 }
 
-static void lp8788_led_enable(struct lp8788_led *led,
+static int lp8788_led_enable(struct lp8788_led *led,
 			enum lp8788_isink_number num, int on)
 {
+	int ret;
+
 	u8 mask = 1 << num;
 	u8 val = on << num;
 
-	if (lp8788_update_bits(led->lp, LP8788_ISINK_CTRL, mask, val))
-		return;
+	ret = lp8788_update_bits(led->lp, LP8788_ISINK_CTRL, mask, val);
+	if (ret == 0)
+		led->on = on;
 
-	led->on = on;
+	return ret;
 }
 
-static void lp8788_led_work(struct work_struct *work)
+static int lp8788_brightness_set(struct led_classdev *led_cdev,
+				enum led_brightness val)
 {
-	struct lp8788_led *led = container_of(work, struct lp8788_led, work);
+	struct lp8788_led *led =
+			container_of(led_cdev, struct lp8788_led, led_dev);
+
 	enum lp8788_isink_number num = led->isink_num;
-	int enable;
-	u8 val = led->brightness;
+	int enable, ret;
 
 	mutex_lock(&led->lock);
 
@@ -101,28 +104,21 @@
 	case LP8788_ISINK_1:
 	case LP8788_ISINK_2:
 	case LP8788_ISINK_3:
-		lp8788_write_byte(led->lp, lp8788_pwm_addr[num], val);
+		ret = lp8788_write_byte(led->lp, lp8788_pwm_addr[num], val);
+		if (ret < 0)
+			goto unlock;
 		break;
 	default:
 		mutex_unlock(&led->lock);
-		return;
+		return -EINVAL;
 	}
 
 	enable = (val > 0) ? 1 : 0;
 	if (enable != led->on)
-		lp8788_led_enable(led, num, enable);
-
+		ret = lp8788_led_enable(led, num, enable);
+unlock:
 	mutex_unlock(&led->lock);
-}
-
-static void lp8788_brightness_set(struct led_classdev *led_cdev,
-				enum led_brightness brt_val)
-{
-	struct lp8788_led *led =
-			container_of(led_cdev, struct lp8788_led, led_dev);
-
-	led->brightness = brt_val;
-	schedule_work(&led->work);
+	return ret;
 }
 
 static int lp8788_led_probe(struct platform_device *pdev)
@@ -139,7 +135,7 @@
 
 	led->lp = lp;
 	led->led_dev.max_brightness = MAX_BRIGHTNESS;
-	led->led_dev.brightness_set = lp8788_brightness_set;
+	led->led_dev.brightness_set_blocking = lp8788_brightness_set;
 
 	led_pdata = lp->pdata ? lp->pdata->led_pdata : NULL;
 
@@ -149,7 +145,6 @@
 		led->led_dev.name = led_pdata->name;
 
 	mutex_init(&led->lock);
-	INIT_WORK(&led->work, lp8788_led_work);
 
 	platform_set_drvdata(pdev, led);
 
@@ -173,7 +168,6 @@
 	struct lp8788_led *led = platform_get_drvdata(pdev);
 
 	led_classdev_unregister(&led->led_dev);
-	flush_work(&led->work);
 
 	return 0;
 }
diff --git a/drivers/leds/leds-lp8860.c b/drivers/leds/leds-lp8860.c
index 79f0843..3e70775 100644
--- a/drivers/leds/leds-lp8860.c
+++ b/drivers/leds/leds-lp8860.c
@@ -91,26 +91,22 @@
 /**
  * struct lp8860_led -
  * @lock - Lock for reading/writing the device
- * @work - Work item used to off load the brightness register writes
  * @client - Pointer to the I2C client
  * @led_dev - led class device pointer
  * @regmap - Devices register map
  * @eeprom_regmap - EEPROM register map
  * @enable_gpio - VDDIO/EN gpio to enable communication interface
  * @regulator - LED supply regulator pointer
- * @brightness - Current brightness value requested
  * @label - LED label
 **/
 struct lp8860_led {
 	struct mutex lock;
-	struct work_struct work;
 	struct i2c_client *client;
 	struct led_classdev led_dev;
 	struct regmap *regmap;
 	struct regmap *eeprom_regmap;
 	struct gpio_desc *enable_gpio;
 	struct regulator *regulator;
-	enum led_brightness brightness;
 	const char *label;
 };
 
@@ -212,11 +208,13 @@
 	return ret;
 }
 
-static void lp8860_led_brightness_work(struct work_struct *work)
+static int lp8860_brightness_set(struct led_classdev *led_cdev,
+				enum led_brightness brt_val)
 {
-	struct lp8860_led *led = container_of(work, struct lp8860_led, work);
+	struct lp8860_led *led =
+			container_of(led_cdev, struct lp8860_led, led_dev);
+	int disp_brightness = brt_val * 255;
 	int ret;
-	int disp_brightness = led->brightness * 255;
 
 	mutex_lock(&led->lock);
 
@@ -241,16 +239,7 @@
 	}
 out:
 	mutex_unlock(&led->lock);
-}
-
-static void lp8860_brightness_set(struct led_classdev *led_cdev,
-				enum led_brightness brt_val)
-{
-	struct lp8860_led *led =
-			container_of(led_cdev, struct lp8860_led, led_dev);
-
-	led->brightness = brt_val;
-	schedule_work(&led->work);
+	return ret;
 }
 
 static int lp8860_init(struct lp8860_led *led)
@@ -406,10 +395,9 @@
 	led->client = client;
 	led->led_dev.name = led->label;
 	led->led_dev.max_brightness = LED_FULL;
-	led->led_dev.brightness_set = lp8860_brightness_set;
+	led->led_dev.brightness_set_blocking = lp8860_brightness_set;
 
 	mutex_init(&led->lock);
-	INIT_WORK(&led->work, lp8860_led_brightness_work);
 
 	i2c_set_clientdata(client, led);
 
@@ -448,7 +436,6 @@
 	int ret;
 
 	led_classdev_unregister(&led->led_dev);
-	cancel_work_sync(&led->work);
 
 	if (led->enable_gpio)
 		gpiod_direction_output(led->enable_gpio, 0);
diff --git a/drivers/leds/leds-lt3593.c b/drivers/leds/leds-lt3593.c
index 9f41124..a7ff510 100644
--- a/drivers/leds/leds-lt3593.c
+++ b/drivers/leds/leds-lt3593.c
@@ -19,7 +19,6 @@
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
 #include <linux/leds.h>
-#include <linux/workqueue.h>
 #include <linux/delay.h>
 #include <linux/gpio.h>
 #include <linux/slab.h>
@@ -28,15 +27,14 @@
 struct lt3593_led_data {
 	struct led_classdev cdev;
 	unsigned gpio;
-	struct work_struct work;
-	u8 new_level;
 };
 
-static void lt3593_led_work(struct work_struct *work)
+static int lt3593_led_set(struct led_classdev *led_cdev,
+			   enum led_brightness value)
 {
-	int pulses;
 	struct lt3593_led_data *led_dat =
-		container_of(work, struct lt3593_led_data, work);
+		container_of(led_cdev, struct lt3593_led_data, cdev);
+	int pulses;
 
 	/*
 	 * The LT3593 resets its internal current level register to the maximum
@@ -47,18 +45,18 @@
 	 * applied is to the output driver.
 	 */
 
-	if (led_dat->new_level == 0) {
+	if (value == 0) {
 		gpio_set_value_cansleep(led_dat->gpio, 0);
-		return;
+		return 0;
 	}
 
-	pulses = 32 - (led_dat->new_level * 32) / 255;
+	pulses = 32 - (value * 32) / 255;
 
 	if (pulses == 0) {
 		gpio_set_value_cansleep(led_dat->gpio, 0);
 		mdelay(1);
 		gpio_set_value_cansleep(led_dat->gpio, 1);
-		return;
+		return 0;
 	}
 
 	gpio_set_value_cansleep(led_dat->gpio, 1);
@@ -69,16 +67,8 @@
 		gpio_set_value_cansleep(led_dat->gpio, 1);
 		udelay(1);
 	}
-}
 
-static void lt3593_led_set(struct led_classdev *led_cdev,
-	enum led_brightness value)
-{
-	struct lt3593_led_data *led_dat =
-		container_of(led_cdev, struct lt3593_led_data, cdev);
-
-	led_dat->new_level = value;
-	schedule_work(&led_dat->work);
+	return 0;
 }
 
 static int create_lt3593_led(const struct gpio_led *template,
@@ -97,7 +87,7 @@
 	led_dat->cdev.default_trigger = template->default_trigger;
 	led_dat->gpio = template->gpio;
 
-	led_dat->cdev.brightness_set = lt3593_led_set;
+	led_dat->cdev.brightness_set_blocking = lt3593_led_set;
 
 	state = (template->default_state == LEDS_GPIO_DEFSTATE_ON);
 	led_dat->cdev.brightness = state ? LED_FULL : LED_OFF;
@@ -111,8 +101,6 @@
 	if (ret < 0)
 		return ret;
 
-	INIT_WORK(&led_dat->work, lt3593_led_work);
-
 	ret = led_classdev_register(parent, &led_dat->cdev);
 	if (ret < 0)
 		return ret;
@@ -129,7 +117,6 @@
 		return;
 
 	led_classdev_unregister(&led->cdev);
-	cancel_work_sync(&led->work);
 }
 
 static int lt3593_led_probe(struct platform_device *pdev)
diff --git a/drivers/leds/leds-max77693.c b/drivers/leds/leds-max77693.c
index afbb140..1eb58ef 100644
--- a/drivers/leds/leds-max77693.c
+++ b/drivers/leds/leds-max77693.c
@@ -20,7 +20,6 @@
 #include <linux/platform_device.h>
 #include <linux/regmap.h>
 #include <linux/slab.h>
-#include <linux/workqueue.h>
 #include <media/v4l2-flash-led-class.h>
 
 #define MODE_OFF		0
@@ -62,8 +61,6 @@
 	int fled_id;
 	/* corresponding LED Flash class device */
 	struct led_classdev_flash fled_cdev;
-	/* assures led-triggers compatibility */
-	struct work_struct work_brightness_set;
 	/* V4L2 Flash device */
 	struct v4l2_flash *v4l2_flash;
 
@@ -463,10 +460,14 @@
 	return max77693_set_mode_reg(led, MODE_OFF);
 }
 
-static int __max77693_led_brightness_set(struct max77693_led_device *led,
-					int fled_id, enum led_brightness value)
+/* LED subsystem callbacks */
+static int max77693_led_brightness_set(struct led_classdev *led_cdev,
+					enum led_brightness value)
 {
-	int ret;
+	struct led_classdev_flash *fled_cdev = lcdev_to_flcdev(led_cdev);
+	struct max77693_sub_led *sub_led = flcdev_to_sub_led(fled_cdev);
+	struct max77693_led_device *led = sub_led_to_led(sub_led);
+	int fled_id = sub_led->fled_id, ret;
 
 	mutex_lock(&led->lock);
 
@@ -494,45 +495,10 @@
 			ret);
 unlock:
 	mutex_unlock(&led->lock);
+
 	return ret;
 }
 
-static void max77693_led_brightness_set_work(
-					struct work_struct *work)
-{
-	struct max77693_sub_led *sub_led =
-			container_of(work, struct max77693_sub_led,
-					work_brightness_set);
-	struct max77693_led_device *led = sub_led_to_led(sub_led);
-
-	__max77693_led_brightness_set(led, sub_led->fled_id,
-				sub_led->torch_brightness);
-}
-
-/* LED subsystem callbacks */
-
-static int max77693_led_brightness_set_sync(
-				struct led_classdev *led_cdev,
-				enum led_brightness value)
-{
-	struct led_classdev_flash *fled_cdev = lcdev_to_flcdev(led_cdev);
-	struct max77693_sub_led *sub_led = flcdev_to_sub_led(fled_cdev);
-	struct max77693_led_device *led = sub_led_to_led(sub_led);
-
-	return __max77693_led_brightness_set(led, sub_led->fled_id, value);
-}
-
-static void max77693_led_brightness_set(
-				struct led_classdev *led_cdev,
-				enum led_brightness value)
-{
-	struct led_classdev_flash *fled_cdev = lcdev_to_flcdev(led_cdev);
-	struct max77693_sub_led *sub_led = flcdev_to_sub_led(fled_cdev);
-
-	sub_led->torch_brightness = value;
-	schedule_work(&sub_led->work_brightness_set);
-}
-
 static int max77693_led_flash_brightness_set(
 				struct led_classdev_flash *fled_cdev,
 				u32 brightness)
@@ -682,6 +648,7 @@
 		if (sub_nodes[fled_id]) {
 			dev_err(dev,
 				"Conflicting \"led-sources\" DT properties\n");
+			of_node_put(child_node);
 			return -EINVAL;
 		}
 
@@ -931,16 +898,13 @@
 
 	led_cdev->name = led_cfg->label[fled_id];
 
-	led_cdev->brightness_set = max77693_led_brightness_set;
-	led_cdev->brightness_set_sync = max77693_led_brightness_set_sync;
+	led_cdev->brightness_set_blocking = max77693_led_brightness_set;
 	led_cdev->max_brightness = (led->iout_joint ?
 					led_cfg->iout_torch_max[FLED1] +
 					led_cfg->iout_torch_max[FLED2] :
 					led_cfg->iout_torch_max[fled_id]) /
 				   TORCH_IOUT_STEP;
 	led_cdev->flags |= LED_DEV_CAP_FLASH;
-	INIT_WORK(&sub_led->work_brightness_set,
-			max77693_led_brightness_set_work);
 
 	max77693_init_flash_settings(sub_led, led_cfg);
 
@@ -1062,13 +1026,11 @@
 	if (led->iout_joint || max77693_fled_used(led, FLED1)) {
 		v4l2_flash_release(sub_leds[FLED1].v4l2_flash);
 		led_classdev_flash_unregister(&sub_leds[FLED1].fled_cdev);
-		cancel_work_sync(&sub_leds[FLED1].work_brightness_set);
 	}
 
 	if (!led->iout_joint && max77693_fled_used(led, FLED2)) {
 		v4l2_flash_release(sub_leds[FLED2].v4l2_flash);
 		led_classdev_flash_unregister(&sub_leds[FLED2].fled_cdev);
-		cancel_work_sync(&sub_leds[FLED2].work_brightness_set);
 	}
 
 	mutex_destroy(&led->lock);
diff --git a/drivers/leds/leds-max8997.c b/drivers/leds/leds-max8997.c
index c592aa5..01b45906 100644
--- a/drivers/leds/leds-max8997.c
+++ b/drivers/leds/leds-max8997.c
@@ -13,7 +13,6 @@
 #include <linux/module.h>
 #include <linux/err.h>
 #include <linux/slab.h>
-#include <linux/workqueue.h>
 #include <linux/leds.h>
 #include <linux/mfd/max8997.h>
 #include <linux/mfd/max8997-private.h>
diff --git a/drivers/leds/leds-mc13783.c b/drivers/leds/leds-mc13783.c
index e2b847f..a2e4c17 100644
--- a/drivers/leds/leds-mc13783.c
+++ b/drivers/leds/leds-mc13783.c
@@ -20,7 +20,6 @@
 #include <linux/platform_device.h>
 #include <linux/leds.h>
 #include <linux/of.h>
-#include <linux/workqueue.h>
 #include <linux/mfd/mc13xxx.h>
 
 struct mc13xxx_led_devtype {
@@ -32,8 +31,6 @@
 
 struct mc13xxx_led {
 	struct led_classdev	cdev;
-	struct work_struct	work;
-	enum led_brightness	new_brightness;
 	int			id;
 	struct mc13xxx_leds	*leds;
 };
@@ -55,9 +52,11 @@
 	return 0x3f;
 }
 
-static void mc13xxx_led_work(struct work_struct *work)
+static int mc13xxx_led_set(struct led_classdev *led_cdev,
+			    enum led_brightness value)
 {
-	struct mc13xxx_led *led = container_of(work, struct mc13xxx_led, work);
+	struct mc13xxx_led *led =
+		container_of(led_cdev, struct mc13xxx_led, cdev);
 	struct mc13xxx_leds *leds = led->leds;
 	unsigned int reg, bank, off, shift;
 
@@ -105,19 +104,9 @@
 		BUG();
 	}
 
-	mc13xxx_reg_rmw(leds->master, leds->devtype->ledctrl_base + reg,
+	return mc13xxx_reg_rmw(leds->master, leds->devtype->ledctrl_base + reg,
 			mc13xxx_max_brightness(led->id) << shift,
-			led->new_brightness << shift);
-}
-
-static void mc13xxx_led_set(struct led_classdev *led_cdev,
-			    enum led_brightness value)
-{
-	struct mc13xxx_led *led =
-		container_of(led_cdev, struct mc13xxx_led, cdev);
-
-	led->new_brightness = value;
-	schedule_work(&led->work);
+			value << shift);
 }
 
 #ifdef CONFIG_OF
@@ -257,11 +246,9 @@
 		leds->led[i].cdev.name = name;
 		leds->led[i].cdev.default_trigger = trig;
 		leds->led[i].cdev.flags = LED_CORE_SUSPENDRESUME;
-		leds->led[i].cdev.brightness_set = mc13xxx_led_set;
+		leds->led[i].cdev.brightness_set_blocking = mc13xxx_led_set;
 		leds->led[i].cdev.max_brightness = mc13xxx_max_brightness(id);
 
-		INIT_WORK(&leds->led[i].work, mc13xxx_led_work);
-
 		ret = led_classdev_register(dev->parent, &leds->led[i].cdev);
 		if (ret) {
 			dev_err(dev, "Failed to register LED %i\n", id);
@@ -270,10 +257,8 @@
 	}
 
 	if (ret)
-		while (--i >= 0) {
+		while (--i >= 0)
 			led_classdev_unregister(&leds->led[i].cdev);
-			cancel_work_sync(&leds->led[i].work);
-		}
 
 	return ret;
 }
@@ -283,10 +268,8 @@
 	struct mc13xxx_leds *leds = platform_get_drvdata(pdev);
 	int i;
 
-	for (i = 0; i < leds->num_leds; i++) {
+	for (i = 0; i < leds->num_leds; i++)
 		led_classdev_unregister(&leds->led[i].cdev);
-		cancel_work_sync(&leds->led[i].work);
-	}
 
 	return 0;
 }
diff --git a/drivers/leds/leds-ns2.c b/drivers/leds/leds-ns2.c
index a95a612..506b75b 100644
--- a/drivers/leds/leds-ns2.c
+++ b/drivers/leds/leds-ns2.c
@@ -45,24 +45,12 @@
 	unsigned		cmd;
 	unsigned		slow;
 	bool			can_sleep;
-	int			mode_index;
 	unsigned char		sata; /* True when SATA mode active. */
 	rwlock_t		rw_lock; /* Lock GPIOs. */
-	struct work_struct	work;
 	int			num_modes;
 	struct ns2_led_modval	*modval;
 };
 
-static void ns2_led_work(struct work_struct *work)
-{
-	struct ns2_led_data *led_dat =
-		container_of(work, struct ns2_led_data, work);
-	int i = led_dat->mode_index;
-
-	gpio_set_value_cansleep(led_dat->cmd, led_dat->modval[i].cmd_level);
-	gpio_set_value_cansleep(led_dat->slow, led_dat->modval[i].slow_level);
-}
-
 static int ns2_led_get_mode(struct ns2_led_data *led_dat,
 			    enum ns2_led_modes *mode)
 {
@@ -112,8 +100,8 @@
 		goto exit_unlock;
 	}
 
-	led_dat->mode_index = i;
-	schedule_work(&led_dat->work);
+	gpio_set_value_cansleep(led_dat->cmd, led_dat->modval[i].cmd_level);
+	gpio_set_value_cansleep(led_dat->slow, led_dat->modval[i].slow_level);
 
 exit_unlock:
 	write_unlock_irqrestore(&led_dat->rw_lock, flags);
@@ -136,6 +124,13 @@
 	ns2_led_set_mode(led_dat, mode);
 }
 
+static int ns2_led_set_blocking(struct led_classdev *led_cdev,
+			enum led_brightness value)
+{
+	ns2_led_set(led_cdev, value);
+	return 0;
+}
+
 static ssize_t ns2_led_sata_store(struct device *dev,
 				  struct device_attribute *attr,
 				  const char *buff, size_t count)
@@ -219,13 +214,16 @@
 	led_dat->cdev.name = template->name;
 	led_dat->cdev.default_trigger = template->default_trigger;
 	led_dat->cdev.blink_set = NULL;
-	led_dat->cdev.brightness_set = ns2_led_set;
 	led_dat->cdev.flags |= LED_CORE_SUSPENDRESUME;
 	led_dat->cdev.groups = ns2_led_groups;
 	led_dat->cmd = template->cmd;
 	led_dat->slow = template->slow;
 	led_dat->can_sleep = gpio_cansleep(led_dat->cmd) |
 				gpio_cansleep(led_dat->slow);
+	if (led_dat->can_sleep)
+		led_dat->cdev.brightness_set_blocking = ns2_led_set_blocking;
+	else
+		led_dat->cdev.brightness_set = ns2_led_set;
 	led_dat->modval = template->modval;
 	led_dat->num_modes = template->num_modes;
 
@@ -238,8 +236,6 @@
 	led_dat->cdev.brightness =
 		(mode == NS_V2_LED_OFF) ? LED_OFF : LED_FULL;
 
-	INIT_WORK(&led_dat->work, ns2_led_work);
-
 	ret = led_classdev_register(&pdev->dev, &led_dat->cdev);
 	if (ret < 0)
 		return ret;
@@ -250,7 +246,6 @@
 static void delete_ns2_led(struct ns2_led_data *led_dat)
 {
 	led_classdev_unregister(&led_dat->cdev);
-	cancel_work_sync(&led_dat->work);
 }
 
 #ifdef CONFIG_OF_GPIO
diff --git a/drivers/leds/leds-pca9532.c b/drivers/leds/leds-pca9532.c
index 5a6363d..17c63ec 100644
--- a/drivers/leds/leds-pca9532.c
+++ b/drivers/leds/leds-pca9532.c
@@ -158,7 +158,7 @@
 	mutex_unlock(&data->update_lock);
 }
 
-static void pca9532_set_brightness(struct led_classdev *led_cdev,
+static int pca9532_set_brightness(struct led_classdev *led_cdev,
 	enum led_brightness value)
 {
 	int err = 0;
@@ -172,9 +172,12 @@
 		led->state = PCA9532_PWM0; /* Thecus: hardcode one pwm */
 		err = pca9532_calcpwm(led->client, 0, 0, value);
 		if (err)
-			return; /* XXX: led api doesn't allow error code? */
+			return err;
 	}
-	schedule_work(&led->work);
+	if (led->state == PCA9532_PWM0)
+		pca9532_setpwm(led->client, 0);
+	pca9532_setled(led);
+	return err;
 }
 
 static int pca9532_set_blink(struct led_classdev *led_cdev,
@@ -198,7 +201,10 @@
 	err = pca9532_calcpwm(client, 0, psc, led_cdev->brightness);
 	if (err)
 		return err;
-	schedule_work(&led->work);
+	if (led->state == PCA9532_PWM0)
+		pca9532_setpwm(led->client, 0);
+	pca9532_setled(led);
+
 	return 0;
 }
 
@@ -233,15 +239,6 @@
 	mutex_unlock(&data->update_lock);
 }
 
-static void pca9532_led_work(struct work_struct *work)
-{
-	struct pca9532_led *led;
-	led = container_of(work, struct pca9532_led, work);
-	if (led->state == PCA9532_PWM0)
-		pca9532_setpwm(led->client, 0);
-	pca9532_setled(led);
-}
-
 #ifdef CONFIG_LEDS_PCA9532_GPIO
 static int pca9532_gpio_request_pin(struct gpio_chip *gc, unsigned offset)
 {
@@ -307,7 +304,6 @@
 			break;
 		case PCA9532_TYPE_LED:
 			led_classdev_unregister(&data->leds[i].ldev);
-			cancel_work_sync(&data->leds[i].work);
 			break;
 		case PCA9532_TYPE_N2100_BEEP:
 			if (data->idev != NULL) {
@@ -359,9 +355,9 @@
 			led->name = pled->name;
 			led->ldev.name = led->name;
 			led->ldev.brightness = LED_OFF;
-			led->ldev.brightness_set = pca9532_set_brightness;
+			led->ldev.brightness_set_blocking =
+						pca9532_set_brightness;
 			led->ldev.blink_set = pca9532_set_blink;
-			INIT_WORK(&led->work, pca9532_led_work);
 			err = led_classdev_register(&client->dev, &led->ldev);
 			if (err < 0) {
 				dev_err(&client->dev,
diff --git a/drivers/leds/leds-pca955x.c b/drivers/leds/leds-pca955x.c
index b775e1e..840401a 100644
--- a/drivers/leds/leds-pca955x.c
+++ b/drivers/leds/leds-pca955x.c
@@ -47,7 +47,6 @@
 #include <linux/leds.h>
 #include <linux/err.h>
 #include <linux/i2c.h>
-#include <linux/workqueue.h>
 #include <linux/slab.h>
 
 /* LED select registers determine the source that drives LED outputs */
@@ -110,8 +109,6 @@
 
 struct pca955x_led {
 	struct pca955x	*pca955x;
-	struct work_struct	work;
-	enum led_brightness	brightness;
 	struct led_classdev	led_cdev;
 	int			led_num;	/* 0 .. 15 potentially */
 	char			name[32];
@@ -193,7 +190,8 @@
 		pca95xx_num_input_regs(pca955x->chipdef->bits) + 4 + n);
 }
 
-static void pca955x_led_work(struct work_struct *work)
+static int pca955x_led_set(struct led_classdev *led_cdev,
+			    enum led_brightness value)
 {
 	struct pca955x_led *pca955x_led;
 	struct pca955x *pca955x;
@@ -201,7 +199,7 @@
 	int chip_ls;	/* which LSx to use (0-3 potentially) */
 	int ls_led;	/* which set of bits within LSx to use (0-3) */
 
-	pca955x_led = container_of(work, struct pca955x_led, work);
+	pca955x_led = container_of(led_cdev, struct pca955x_led, led_cdev);
 	pca955x = pca955x_led->pca955x;
 
 	chip_ls = pca955x_led->led_num / 4;
@@ -211,7 +209,7 @@
 
 	ls = pca955x_read_ls(pca955x->client, chip_ls);
 
-	switch (pca955x_led->brightness) {
+	switch (value) {
 	case LED_FULL:
 		ls = pca955x_ledsel(ls, ls_led, PCA955X_LS_LED_ON);
 		break;
@@ -230,7 +228,7 @@
 		 * just turning off for all other values.
 		 */
 		pca955x_write_pwm(pca955x->client, 1,
-				255 - pca955x_led->brightness);
+				255 - value);
 		ls = pca955x_ledsel(ls, ls_led, PCA955X_LS_BLINK1);
 		break;
 	}
@@ -238,21 +236,8 @@
 	pca955x_write_ls(pca955x->client, chip_ls, ls);
 
 	mutex_unlock(&pca955x->lock);
-}
 
-static void pca955x_led_set(struct led_classdev *led_cdev, enum led_brightness value)
-{
-	struct pca955x_led *pca955x;
-
-	pca955x = container_of(led_cdev, struct pca955x_led, led_cdev);
-
-	pca955x->brightness = value;
-
-	/*
-	 * Must use workqueue for the actual I/O since I2C operations
-	 * can sleep.
-	 */
-	schedule_work(&pca955x->work);
+	return 0;
 }
 
 static int pca955x_probe(struct i2c_client *client,
@@ -328,9 +313,7 @@
 		}
 
 		pca955x_led->led_cdev.name = pca955x_led->name;
-		pca955x_led->led_cdev.brightness_set = pca955x_led_set;
-
-		INIT_WORK(&pca955x_led->work, pca955x_led_work);
+		pca955x_led->led_cdev.brightness_set_blocking = pca955x_led_set;
 
 		err = led_classdev_register(&client->dev,
 					&pca955x_led->led_cdev);
@@ -355,10 +338,8 @@
 	return 0;
 
 exit:
-	while (i--) {
+	while (i--)
 		led_classdev_unregister(&pca955x->leds[i].led_cdev);
-		cancel_work_sync(&pca955x->leds[i].work);
-	}
 
 	return err;
 }
@@ -368,10 +349,8 @@
 	struct pca955x *pca955x = i2c_get_clientdata(client);
 	int i;
 
-	for (i = 0; i < pca955x->chipdef->bits; i++) {
+	for (i = 0; i < pca955x->chipdef->bits; i++)
 		led_classdev_unregister(&pca955x->leds[i].led_cdev);
-		cancel_work_sync(&pca955x->leds[i].work);
-	}
 
 	return 0;
 }
diff --git a/drivers/leds/leds-pca963x.c b/drivers/leds/leds-pca963x.c
index 41f269f..407eba1 100644
--- a/drivers/leds/leds-pca963x.c
+++ b/drivers/leds/leds-pca963x.c
@@ -32,7 +32,6 @@
 #include <linux/leds.h>
 #include <linux/err.h>
 #include <linux/i2c.h>
-#include <linux/workqueue.h>
 #include <linux/slab.h>
 #include <linux/of.h>
 #include <linux/platform_data/leds-pca963x.h>
@@ -96,11 +95,6 @@
 };
 MODULE_DEVICE_TABLE(i2c, pca963x_id);
 
-enum pca963x_cmd {
-	BRIGHTNESS_SET,
-	BLINK_SET,
-};
-
 struct pca963x_led;
 
 struct pca963x {
@@ -112,47 +106,52 @@
 
 struct pca963x_led {
 	struct pca963x *chip;
-	struct work_struct work;
-	enum led_brightness brightness;
 	struct led_classdev led_cdev;
 	int led_num; /* 0 .. 15 potentially */
-	enum pca963x_cmd cmd;
 	char name[32];
 	u8 gdc;
 	u8 gfrq;
 };
 
-static void pca963x_brightness_work(struct pca963x_led *pca963x)
+static int pca963x_brightness(struct pca963x_led *pca963x,
+			       enum led_brightness brightness)
 {
 	u8 ledout_addr = pca963x->chip->chipdef->ledout_base
 		+ (pca963x->led_num / 4);
 	u8 ledout;
 	int shift = 2 * (pca963x->led_num % 4);
 	u8 mask = 0x3 << shift;
+	int ret;
 
 	mutex_lock(&pca963x->chip->mutex);
 	ledout = i2c_smbus_read_byte_data(pca963x->chip->client, ledout_addr);
-	switch (pca963x->brightness) {
+	switch (brightness) {
 	case LED_FULL:
-		i2c_smbus_write_byte_data(pca963x->chip->client, ledout_addr,
+		ret = i2c_smbus_write_byte_data(pca963x->chip->client,
+			ledout_addr,
 			(ledout & ~mask) | (PCA963X_LED_ON << shift));
 		break;
 	case LED_OFF:
-		i2c_smbus_write_byte_data(pca963x->chip->client, ledout_addr,
-			ledout & ~mask);
+		ret = i2c_smbus_write_byte_data(pca963x->chip->client,
+			ledout_addr, ledout & ~mask);
 		break;
 	default:
-		i2c_smbus_write_byte_data(pca963x->chip->client,
+		ret = i2c_smbus_write_byte_data(pca963x->chip->client,
 			PCA963X_PWM_BASE + pca963x->led_num,
-			pca963x->brightness);
-		i2c_smbus_write_byte_data(pca963x->chip->client, ledout_addr,
+			brightness);
+		if (ret < 0)
+			goto unlock;
+		ret = i2c_smbus_write_byte_data(pca963x->chip->client,
+			ledout_addr,
 			(ledout & ~mask) | (PCA963X_LED_PWM << shift));
 		break;
 	}
+unlock:
 	mutex_unlock(&pca963x->chip->mutex);
+	return ret;
 }
 
-static void pca963x_blink_work(struct pca963x_led *pca963x)
+static void pca963x_blink(struct pca963x_led *pca963x)
 {
 	u8 ledout_addr = pca963x->chip->chipdef->ledout_base +
 		(pca963x->led_num / 4);
@@ -180,36 +179,14 @@
 	mutex_unlock(&pca963x->chip->mutex);
 }
 
-static void pca963x_work(struct work_struct *work)
-{
-	struct pca963x_led *pca963x = container_of(work,
-		struct pca963x_led, work);
-
-	switch (pca963x->cmd) {
-	case BRIGHTNESS_SET:
-		pca963x_brightness_work(pca963x);
-		break;
-	case BLINK_SET:
-		pca963x_blink_work(pca963x);
-		break;
-	}
-}
-
-static void pca963x_led_set(struct led_classdev *led_cdev,
+static int pca963x_led_set(struct led_classdev *led_cdev,
 	enum led_brightness value)
 {
 	struct pca963x_led *pca963x;
 
 	pca963x = container_of(led_cdev, struct pca963x_led, led_cdev);
 
-	pca963x->cmd = BRIGHTNESS_SET;
-	pca963x->brightness = value;
-
-	/*
-	 * Must use workqueue for the actual I/O since I2C operations
-	 * can sleep.
-	 */
-	schedule_work(&pca963x->work);
+	return pca963x_brightness(pca963x, value);
 }
 
 static int pca963x_blink_set(struct led_classdev *led_cdev,
@@ -254,15 +231,10 @@
 	 */
 	gfrq = (period * 24 / 1000) - 1;
 
-	pca963x->cmd = BLINK_SET;
 	pca963x->gdc = gdc;
 	pca963x->gfrq = gfrq;
 
-	/*
-	 * Must use workqueue for the actual I/O since I2C operations
-	 * can sleep.
-	 */
-	schedule_work(&pca963x->work);
+	pca963x_blink(pca963x);
 
 	*delay_on = time_on;
 	*delay_off = time_off;
@@ -409,13 +381,11 @@
 				 client->addr, i);
 
 		pca963x[i].led_cdev.name = pca963x[i].name;
-		pca963x[i].led_cdev.brightness_set = pca963x_led_set;
+		pca963x[i].led_cdev.brightness_set_blocking = pca963x_led_set;
 
 		if (pdata && pdata->blink_type == PCA963X_HW_BLINK)
 			pca963x[i].led_cdev.blink_set = pca963x_blink_set;
 
-		INIT_WORK(&pca963x[i].work, pca963x_work);
-
 		err = led_classdev_register(&client->dev, &pca963x[i].led_cdev);
 		if (err < 0)
 			goto exit;
@@ -435,10 +405,8 @@
 	return 0;
 
 exit:
-	while (i--) {
+	while (i--)
 		led_classdev_unregister(&pca963x[i].led_cdev);
-		cancel_work_sync(&pca963x[i].work);
-	}
 
 	return err;
 }
@@ -448,10 +416,8 @@
 	struct pca963x *pca963x = i2c_get_clientdata(client);
 	int i;
 
-	for (i = 0; i < pca963x->chipdef->n_leds; i++) {
+	for (i = 0; i < pca963x->chipdef->n_leds; i++)
 		led_classdev_unregister(&pca963x->leds[i].led_cdev);
-		cancel_work_sync(&pca963x->leds[i].work);
-	}
 
 	return 0;
 }
diff --git a/drivers/leds/leds-powernv.c b/drivers/leds/leds-powernv.c
index 1e75e1f..dfb8bd3 100644
--- a/drivers/leds/leds-powernv.c
+++ b/drivers/leds/leds-powernv.c
@@ -77,7 +77,7 @@
  * This function is called from work queue task context when ever it gets
  * scheduled. This function can sleep at opal_async_wait_response call.
  */
-static void powernv_led_set(struct powernv_led_data *powernv_led,
+static int powernv_led_set(struct powernv_led_data *powernv_led,
 			    enum led_brightness value)
 {
 	int rc, token;
@@ -99,7 +99,7 @@
 		if (token != -ERESTARTSYS)
 			dev_err(dev, "%s: Couldn't get OPAL async token\n",
 				__func__);
-		return;
+		return token;
 	}
 
 	rc = opal_leds_set_ind(token, powernv_led->loc_code,
@@ -125,6 +125,7 @@
 
 out_token:
 	opal_async_release_token(token);
+	return rc;
 }
 
 /*
@@ -173,20 +174,23 @@
  * LED classdev 'brightness_get' function. This schedules work
  * to update LED state.
  */
-static void powernv_brightness_set(struct led_classdev *led_cdev,
+static int powernv_brightness_set(struct led_classdev *led_cdev,
 				   enum led_brightness value)
 {
 	struct powernv_led_data *powernv_led =
 		container_of(led_cdev, struct powernv_led_data, cdev);
 	struct powernv_led_common *powernv_led_common = powernv_led->common;
+	int rc;
 
 	/* Do not modify LED in unload path */
 	if (powernv_led_common->led_disabled)
-		return;
+		return 0;
 
 	mutex_lock(&powernv_led_common->lock);
-	powernv_led_set(powernv_led, value);
+	rc = powernv_led_set(powernv_led, value);
 	mutex_unlock(&powernv_led_common->lock);
+
+	return rc;
 }
 
 /* LED classdev 'brightness_get' function */
@@ -227,7 +231,7 @@
 		return -ENOMEM;
 	}
 
-	powernv_led->cdev.brightness_set = powernv_brightness_set;
+	powernv_led->cdev.brightness_set_blocking = powernv_brightness_set;
 	powernv_led->cdev.brightness_get = powernv_brightness_get;
 	powernv_led->cdev.brightness = LED_OFF;
 	powernv_led->cdev.max_brightness = LED_FULL;
@@ -256,8 +260,6 @@
 
 	for_each_child_of_node(led_node, np) {
 		p = of_find_property(np, "led-types", NULL);
-		if (!p)
-			continue;
 
 		while ((cur = of_prop_next_string(p, cur)) != NULL) {
 			powernv_led = devm_kzalloc(dev, sizeof(*powernv_led),
diff --git a/drivers/leds/leds-pwm.c b/drivers/leds/leds-pwm.c
index 1d07e3e..4783bac 100644
--- a/drivers/leds/leds-pwm.c
+++ b/drivers/leds/leds-pwm.c
@@ -22,12 +22,10 @@
 #include <linux/pwm.h>
 #include <linux/leds_pwm.h>
 #include <linux/slab.h>
-#include <linux/workqueue.h>
 
 struct led_pwm_data {
 	struct led_classdev	cdev;
 	struct pwm_device	*pwm;
-	struct work_struct	work;
 	unsigned int		active_low;
 	unsigned int		period;
 	int			duty;
@@ -51,14 +49,6 @@
 		pwm_enable(led_dat->pwm);
 }
 
-static void led_pwm_work(struct work_struct *work)
-{
-	struct led_pwm_data *led_dat =
-		container_of(work, struct led_pwm_data, work);
-
-	__led_pwm_set(led_dat);
-}
-
 static void led_pwm_set(struct led_classdev *led_cdev,
 	enum led_brightness brightness)
 {
@@ -75,10 +65,14 @@
 
 	led_dat->duty = duty;
 
-	if (led_dat->can_sleep)
-		schedule_work(&led_dat->work);
-	else
-		__led_pwm_set(led_dat);
+	__led_pwm_set(led_dat);
+}
+
+static int led_pwm_set_blocking(struct led_classdev *led_cdev,
+	enum led_brightness brightness)
+{
+	led_pwm_set(led_cdev, brightness);
+	return 0;
 }
 
 static inline size_t sizeof_pwm_leds_priv(int num_leds)
@@ -89,11 +83,8 @@
 
 static void led_pwm_cleanup(struct led_pwm_priv *priv)
 {
-	while (priv->num_leds--) {
+	while (priv->num_leds--)
 		led_classdev_unregister(&priv->leds[priv->num_leds].cdev);
-		if (priv->leds[priv->num_leds].can_sleep)
-			cancel_work_sync(&priv->leds[priv->num_leds].work);
-	}
 }
 
 static int led_pwm_add(struct device *dev, struct led_pwm_priv *priv,
@@ -105,7 +96,6 @@
 	led_data->active_low = led->active_low;
 	led_data->cdev.name = led->name;
 	led_data->cdev.default_trigger = led->default_trigger;
-	led_data->cdev.brightness_set = led_pwm_set;
 	led_data->cdev.brightness = LED_OFF;
 	led_data->cdev.max_brightness = led->max_brightness;
 	led_data->cdev.flags = LED_CORE_SUSPENDRESUME;
@@ -122,8 +112,10 @@
 	}
 
 	led_data->can_sleep = pwm_can_sleep(led_data->pwm);
-	if (led_data->can_sleep)
-		INIT_WORK(&led_data->work, led_pwm_work);
+	if (!led_data->can_sleep)
+		led_data->cdev.brightness_set = led_pwm_set;
+	else
+		led_data->cdev.brightness_set_blocking = led_pwm_set_blocking;
 
 	led_data->period = pwm_get_period(led_data->pwm);
 	if (!led_data->period && (led->pwm_period_ns > 0))
@@ -132,6 +124,7 @@
 	ret = led_classdev_register(dev, &led_data->cdev);
 	if (ret == 0) {
 		priv->num_leds++;
+		led_pwm_set(&led_data->cdev, led_data->cdev.brightness);
 	} else {
 		dev_err(dev, "failed to register PWM led for %s: %d\n",
 			led->name, ret);
@@ -236,6 +229,6 @@
 module_platform_driver(led_pwm_driver);
 
 MODULE_AUTHOR("Luotao Fu <l.fu@pengutronix.de>");
-MODULE_DESCRIPTION("PWM LED driver for PXA");
-MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("generic PWM LED driver");
+MODULE_LICENSE("GPL v2");
 MODULE_ALIAS("platform:leds-pwm");
diff --git a/drivers/leds/leds-regulator.c b/drivers/leds/leds-regulator.c
index ffc2139..acf77ca 100644
--- a/drivers/leds/leds-regulator.c
+++ b/drivers/leds/leds-regulator.c
@@ -14,7 +14,6 @@
 #include <linux/module.h>
 #include <linux/err.h>
 #include <linux/slab.h>
-#include <linux/workqueue.h>
 #include <linux/leds.h>
 #include <linux/leds-regulator.h>
 #include <linux/platform_device.h>
@@ -25,10 +24,8 @@
 
 struct regulator_led {
 	struct led_classdev cdev;
-	enum led_brightness value;
 	int enabled;
 	struct mutex mutex;
-	struct work_struct work;
 
 	struct regulator *vcc;
 };
@@ -94,22 +91,24 @@
 	led->enabled = 0;
 }
 
-static void regulator_led_set_value(struct regulator_led *led)
+static int regulator_led_brightness_set(struct led_classdev *led_cdev,
+					 enum led_brightness value)
 {
+	struct regulator_led *led = to_regulator_led(led_cdev);
 	int voltage;
-	int ret;
+	int ret = 0;
 
 	mutex_lock(&led->mutex);
 
-	if (led->value == LED_OFF) {
+	if (value == LED_OFF) {
 		regulator_led_disable(led);
 		goto out;
 	}
 
 	if (led->cdev.max_brightness > 1) {
-		voltage = led_regulator_get_voltage(led->vcc, led->value);
+		voltage = led_regulator_get_voltage(led->vcc, value);
 		dev_dbg(led->cdev.dev, "brightness: %d voltage: %d\n",
-				led->value, voltage);
+				value, voltage);
 
 		ret = regulator_set_voltage(led->vcc, voltage, voltage);
 		if (ret != 0)
@@ -121,23 +120,7 @@
 
 out:
 	mutex_unlock(&led->mutex);
-}
-
-static void led_work(struct work_struct *work)
-{
-	struct regulator_led *led;
-
-	led = container_of(work, struct regulator_led, work);
-	regulator_led_set_value(led);
-}
-
-static void regulator_led_brightness_set(struct led_classdev *led_cdev,
-			   enum led_brightness value)
-{
-	struct regulator_led *led = to_regulator_led(led_cdev);
-
-	led->value = value;
-	schedule_work(&led->work);
+	return ret;
 }
 
 static int regulator_led_probe(struct platform_device *pdev)
@@ -169,9 +152,8 @@
 				pdata->brightness);
 		return -EINVAL;
 	}
-	led->value = pdata->brightness;
 
-	led->cdev.brightness_set = regulator_led_brightness_set;
+	led->cdev.brightness_set_blocking = regulator_led_brightness_set;
 	led->cdev.name = pdata->name;
 	led->cdev.flags |= LED_CORE_SUSPENDRESUME;
 	led->vcc = vcc;
@@ -181,21 +163,18 @@
 		led->enabled = 1;
 
 	mutex_init(&led->mutex);
-	INIT_WORK(&led->work, led_work);
 
 	platform_set_drvdata(pdev, led);
 
 	ret = led_classdev_register(&pdev->dev, &led->cdev);
-	if (ret < 0) {
-		cancel_work_sync(&led->work);
+	if (ret < 0)
 		return ret;
-	}
 
 	/* to expose the default value to userspace */
-	led->cdev.brightness = led->value;
+	led->cdev.brightness = pdata->brightness;
 
 	/* Set the default led status */
-	regulator_led_set_value(led);
+	regulator_led_brightness_set(&led->cdev, led->cdev.brightness);
 
 	return 0;
 }
@@ -205,7 +184,6 @@
 	struct regulator_led *led = platform_get_drvdata(pdev);
 
 	led_classdev_unregister(&led->cdev);
-	cancel_work_sync(&led->work);
 	regulator_led_disable(led);
 	return 0;
 }
diff --git a/drivers/leds/leds-sunfire.c b/drivers/leds/leds-sunfire.c
index c2553c54..7c09db8 100644
--- a/drivers/leds/leds-sunfire.c
+++ b/drivers/leds/leds-sunfire.c
@@ -234,28 +234,19 @@
 	},
 };
 
+static struct platform_driver * const drivers[] = {
+	&sunfire_clockboard_led_driver,
+	&sunfire_fhc_led_driver,
+};
+
 static int __init sunfire_leds_init(void)
 {
-	int err = platform_driver_register(&sunfire_clockboard_led_driver);
-
-	if (err) {
-		pr_err("Could not register clock board LED driver\n");
-		return err;
-	}
-
-	err = platform_driver_register(&sunfire_fhc_led_driver);
-	if (err) {
-		pr_err("Could not register FHC LED driver\n");
-		platform_driver_unregister(&sunfire_clockboard_led_driver);
-	}
-
-	return err;
+	return platform_register_drivers(drivers, ARRAY_SIZE(drivers));
 }
 
 static void __exit sunfire_leds_exit(void)
 {
-	platform_driver_unregister(&sunfire_clockboard_led_driver);
-	platform_driver_unregister(&sunfire_fhc_led_driver);
+	platform_unregister_drivers(drivers, ARRAY_SIZE(drivers));
 }
 
 module_init(sunfire_leds_init);
diff --git a/drivers/leds/leds-syscon.c b/drivers/leds/leds-syscon.c
index b88900d..3be40f7 100644
--- a/drivers/leds/leds-syscon.c
+++ b/drivers/leds/leds-syscon.c
@@ -20,7 +20,7 @@
  * MA 02111-1307 USA
  */
 #include <linux/io.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/of_device.h>
 #include <linux/of_address.h>
 #include <linux/platform_device.h>
@@ -139,29 +139,17 @@
 	return 0;
 }
 
-static int syscon_led_remove(struct platform_device *pdev)
-{
-	struct syscon_led *sled = platform_get_drvdata(pdev);
-
-	led_classdev_unregister(&sled->cdev);
-	/* Turn it off */
-	regmap_update_bits(sled->map, sled->offset, sled->mask, 0);
-	return 0;
-}
-
 static const struct of_device_id of_syscon_leds_match[] = {
 	{ .compatible = "register-bit-led", },
 	{},
 };
 
-MODULE_DEVICE_TABLE(of, of_syscon_leds_match);
-
 static struct platform_driver syscon_led_driver = {
 	.probe		= syscon_led_probe,
-	.remove		= syscon_led_remove,
 	.driver		= {
 		.name	= "leds-syscon",
 		.of_match_table = of_syscon_leds_match,
+		.suppress_bind_attrs = true,
 	},
 };
-module_platform_driver(syscon_led_driver);
+builtin_platform_driver(syscon_led_driver);
diff --git a/drivers/leds/leds-tlc591xx.c b/drivers/leds/leds-tlc591xx.c
index b806eca..30453164 100644
--- a/drivers/leds/leds-tlc591xx.c
+++ b/drivers/leds/leds-tlc591xx.c
@@ -14,7 +14,6 @@
 #include <linux/of_device.h>
 #include <linux/regmap.h>
 #include <linux/slab.h>
-#include <linux/workqueue.h>
 
 #define TLC591XX_MAX_LEDS	16
 
@@ -42,13 +41,11 @@
 #define LEDOUT_MASK		0x3
 
 #define ldev_to_led(c)		container_of(c, struct tlc591xx_led, ldev)
-#define work_to_led(work)	container_of(work, struct tlc591xx_led, work)
 
 struct tlc591xx_led {
 	bool active;
 	unsigned int led_no;
 	struct led_classdev ldev;
-	struct work_struct work;
 	struct tlc591xx_priv *priv;
 };
 
@@ -110,12 +107,12 @@
 	return regmap_write(priv->regmap, pwm, brightness);
 }
 
-static void
-tlc591xx_led_work(struct work_struct *work)
+static int
+tlc591xx_brightness_set(struct led_classdev *led_cdev,
+			enum led_brightness brightness)
 {
-	struct tlc591xx_led *led = work_to_led(work);
+	struct tlc591xx_led *led = ldev_to_led(led_cdev);
 	struct tlc591xx_priv *priv = led->priv;
-	enum led_brightness brightness = led->ldev.brightness;
 	int err;
 
 	switch (brightness) {
@@ -131,18 +128,7 @@
 			err = tlc591xx_set_pwm(priv, led, brightness);
 	}
 
-	if (err)
-		dev_err(led->ldev.dev, "Failed setting brightness\n");
-}
-
-static void
-tlc591xx_brightness_set(struct led_classdev *led_cdev,
-			enum led_brightness brightness)
-{
-	struct tlc591xx_led *led = ldev_to_led(led_cdev);
-
-	led->ldev.brightness = brightness;
-	schedule_work(&led->work);
+	return err;
 }
 
 static void
@@ -151,10 +137,8 @@
 	int i = j;
 
 	while (--i >= 0) {
-		if (priv->leds[i].active) {
+		if (priv->leds[i].active)
 			led_classdev_unregister(&priv->leds[i].ldev);
-			cancel_work_sync(&priv->leds[i].work);
-		}
 	}
 }
 
@@ -175,9 +159,8 @@
 
 		led->priv = priv;
 		led->led_no = i;
-		led->ldev.brightness_set = tlc591xx_brightness_set;
+		led->ldev.brightness_set_blocking = tlc591xx_brightness_set;
 		led->ldev.max_brightness = LED_FULL;
-		INIT_WORK(&led->work, tlc591xx_led_work);
 		err = led_classdev_register(dev, &led->ldev);
 		if (err < 0) {
 			dev_err(dev, "couldn't register LED %s\n",
diff --git a/drivers/leds/leds-wm831x-status.c b/drivers/leds/leds-wm831x-status.c
index 56027ef..64a2226 100644
--- a/drivers/leds/leds-wm831x-status.c
+++ b/drivers/leds/leds-wm831x-status.c
@@ -23,7 +23,6 @@
 struct wm831x_status {
 	struct led_classdev cdev;
 	struct wm831x *wm831x;
-	struct work_struct work;
 	struct mutex mutex;
 
 	spinlock_t value_lock;
@@ -40,10 +39,8 @@
 #define to_wm831x_status(led_cdev) \
 	container_of(led_cdev, struct wm831x_status, cdev)
 
-static void wm831x_status_work(struct work_struct *work)
+static void wm831x_status_set(struct wm831x_status *led)
 {
-	struct wm831x_status *led = container_of(work, struct wm831x_status,
-						 work);
 	unsigned long flags;
 
 	mutex_lock(&led->mutex);
@@ -70,8 +67,8 @@
 	mutex_unlock(&led->mutex);
 }
 
-static void wm831x_status_set(struct led_classdev *led_cdev,
-			   enum led_brightness value)
+static int wm831x_status_brightness_set(struct led_classdev *led_cdev,
+					 enum led_brightness value)
 {
 	struct wm831x_status *led = to_wm831x_status(led_cdev);
 	unsigned long flags;
@@ -80,8 +77,10 @@
 	led->brightness = value;
 	if (value == LED_OFF)
 		led->blink = 0;
-	schedule_work(&led->work);
 	spin_unlock_irqrestore(&led->value_lock, flags);
+	wm831x_status_set(led);
+
+	return 0;
 }
 
 static int wm831x_status_blink_set(struct led_classdev *led_cdev,
@@ -147,11 +146,8 @@
 	else
 		led->blink = 0;
 
-	/* Always update; if we fail turn off blinking since we expect
-	 * a software fallback. */
-	schedule_work(&led->work);
-
 	spin_unlock_irqrestore(&led->value_lock, flags);
+	wm831x_status_set(led);
 
 	return ret;
 }
@@ -206,11 +202,9 @@
 	for (i = 0; i < ARRAY_SIZE(led_src_texts); i++) {
 		if (!strcmp(name, led_src_texts[i])) {
 			mutex_lock(&led->mutex);
-
 			led->src = i;
-			schedule_work(&led->work);
-
 			mutex_unlock(&led->mutex);
+			wm831x_status_set(led);
 		}
 	}
 
@@ -262,7 +256,6 @@
 		pdata.name = dev_name(&pdev->dev);
 
 	mutex_init(&drvdata->mutex);
-	INIT_WORK(&drvdata->work, wm831x_status_work);
 	spin_lock_init(&drvdata->value_lock);
 
 	/* We cache the configuration register and read startup values
@@ -287,7 +280,7 @@
 
 	drvdata->cdev.name = pdata.name;
 	drvdata->cdev.default_trigger = pdata.default_trigger;
-	drvdata->cdev.brightness_set = wm831x_status_set;
+	drvdata->cdev.brightness_set_blocking = wm831x_status_brightness_set;
 	drvdata->cdev.blink_set = wm831x_status_blink_set;
 	drvdata->cdev.groups = wm831x_status_groups;
 
diff --git a/drivers/leds/leds-wm8350.c b/drivers/leds/leds-wm8350.c
index 0d12183..e1e4e9d 100644
--- a/drivers/leds/leds-wm8350.c
+++ b/drivers/leds/leds-wm8350.c
@@ -89,40 +89,42 @@
 #define to_wm8350_led(led_cdev) \
 	container_of(led_cdev, struct wm8350_led, cdev)
 
-static void wm8350_led_enable(struct wm8350_led *led)
+static int wm8350_led_enable(struct wm8350_led *led)
 {
-	int ret;
+	int ret = 0;
 
 	if (led->enabled)
-		return;
+		return ret;
 
 	ret = regulator_enable(led->isink);
 	if (ret != 0) {
 		dev_err(led->cdev.dev, "Failed to enable ISINK: %d\n", ret);
-		return;
+		return ret;
 	}
 
 	ret = regulator_enable(led->dcdc);
 	if (ret != 0) {
 		dev_err(led->cdev.dev, "Failed to enable DCDC: %d\n", ret);
 		regulator_disable(led->isink);
-		return;
+		return ret;
 	}
 
 	led->enabled = 1;
+
+	return ret;
 }
 
-static void wm8350_led_disable(struct wm8350_led *led)
+static int wm8350_led_disable(struct wm8350_led *led)
 {
-	int ret;
+	int ret = 0;
 
 	if (!led->enabled)
-		return;
+		return ret;
 
 	ret = regulator_disable(led->dcdc);
 	if (ret != 0) {
 		dev_err(led->cdev.dev, "Failed to disable DCDC: %d\n", ret);
-		return;
+		return ret;
 	}
 
 	ret = regulator_disable(led->isink);
@@ -132,27 +134,29 @@
 		if (ret != 0)
 			dev_err(led->cdev.dev, "Failed to reenable DCDC: %d\n",
 				ret);
-		return;
+		return ret;
 	}
 
 	led->enabled = 0;
+
+	return ret;
 }
 
-static void led_work(struct work_struct *work)
+static int wm8350_led_set(struct led_classdev *led_cdev,
+			   enum led_brightness value)
 {
-	struct wm8350_led *led = container_of(work, struct wm8350_led, work);
+	struct wm8350_led *led = to_wm8350_led(led_cdev);
+	unsigned long flags;
 	int ret;
 	int uA;
-	unsigned long flags;
 
-	mutex_lock(&led->mutex);
+	led->value = value;
 
 	spin_lock_irqsave(&led->value_lock, flags);
 
 	if (led->value == LED_OFF) {
 		spin_unlock_irqrestore(&led->value_lock, flags);
-		wm8350_led_disable(led);
-		goto out;
+		return wm8350_led_disable(led);
 	}
 
 	/* This scales linearly into the index of valid current
@@ -166,36 +170,21 @@
 
 	ret = regulator_set_current_limit(led->isink, isink_cur[uA],
 					  isink_cur[uA]);
-	if (ret != 0)
+	if (ret != 0) {
 		dev_err(led->cdev.dev, "Failed to set %duA: %d\n",
 			isink_cur[uA], ret);
+		return ret;
+	}
 
-	wm8350_led_enable(led);
-
-out:
-	mutex_unlock(&led->mutex);
-}
-
-static void wm8350_led_set(struct led_classdev *led_cdev,
-			   enum led_brightness value)
-{
-	struct wm8350_led *led = to_wm8350_led(led_cdev);
-	unsigned long flags;
-
-	spin_lock_irqsave(&led->value_lock, flags);
-	led->value = value;
-	schedule_work(&led->work);
-	spin_unlock_irqrestore(&led->value_lock, flags);
+	return wm8350_led_enable(led);
 }
 
 static void wm8350_led_shutdown(struct platform_device *pdev)
 {
 	struct wm8350_led *led = platform_get_drvdata(pdev);
 
-	mutex_lock(&led->mutex);
 	led->value = LED_OFF;
 	wm8350_led_disable(led);
-	mutex_unlock(&led->mutex);
 }
 
 static int wm8350_led_probe(struct platform_device *pdev)
@@ -232,7 +221,7 @@
 	if (led == NULL)
 		return -ENOMEM;
 
-	led->cdev.brightness_set = wm8350_led_set;
+	led->cdev.brightness_set_blocking = wm8350_led_set;
 	led->cdev.default_trigger = pdata->default_trigger;
 	led->cdev.name = pdata->name;
 	led->cdev.flags |= LED_CORE_SUSPENDRESUME;
@@ -251,8 +240,6 @@
 			 pdata->max_uA);
 
 	spin_lock_init(&led->value_lock);
-	mutex_init(&led->mutex);
-	INIT_WORK(&led->work, led_work);
 	led->value = LED_OFF;
 	platform_set_drvdata(pdev, led);
 
@@ -264,7 +251,6 @@
 	struct wm8350_led *led = platform_get_drvdata(pdev);
 
 	led_classdev_unregister(&led->cdev);
-	flush_work(&led->work);
 	wm8350_led_disable(led);
 	return 0;
 }
diff --git a/drivers/leds/leds.h b/drivers/leds/leds.h
index 4238fbc..db3f20d 100644
--- a/drivers/leds/leds.h
+++ b/drivers/leds/leds.h
@@ -16,29 +16,6 @@
 #include <linux/rwsem.h>
 #include <linux/leds.h>
 
-static inline void led_set_brightness_async(struct led_classdev *led_cdev,
-					enum led_brightness value)
-{
-	value = min(value, led_cdev->max_brightness);
-	led_cdev->brightness = value;
-
-	if (!(led_cdev->flags & LED_SUSPENDED))
-		led_cdev->brightness_set(led_cdev, value);
-}
-
-static inline int led_set_brightness_sync(struct led_classdev *led_cdev,
-					enum led_brightness value)
-{
-	int ret = 0;
-
-	led_cdev->brightness = min(value, led_cdev->max_brightness);
-
-	if (!(led_cdev->flags & LED_SUSPENDED))
-		ret = led_cdev->brightness_set_sync(led_cdev,
-						led_cdev->brightness);
-	return ret;
-}
-
 static inline int led_get_brightness(struct led_classdev *led_cdev)
 {
 	return led_cdev->brightness;
@@ -46,6 +23,10 @@
 
 void led_init_core(struct led_classdev *led_cdev);
 void led_stop_software_blink(struct led_classdev *led_cdev);
+void led_set_brightness_nopm(struct led_classdev *led_cdev,
+				enum led_brightness value);
+void led_set_brightness_nosleep(struct led_classdev *led_cdev,
+				enum led_brightness value);
 
 extern struct rw_semaphore leds_list_lock;
 extern struct list_head leds_list;
diff --git a/drivers/leds/trigger/ledtrig-backlight.c b/drivers/leds/trigger/ledtrig-backlight.c
index 59eca17..1ca1f16 100644
--- a/drivers/leds/trigger/ledtrig-backlight.c
+++ b/drivers/leds/trigger/ledtrig-backlight.c
@@ -51,9 +51,9 @@
 
 	if ((n->old_status == UNBLANK) ^ n->invert) {
 		n->brightness = led->brightness;
-		led_set_brightness_async(led, LED_OFF);
+		led_set_brightness_nosleep(led, LED_OFF);
 	} else {
-		led_set_brightness_async(led, n->brightness);
+		led_set_brightness_nosleep(led, n->brightness);
 	}
 
 	n->old_status = new_status;
@@ -89,9 +89,9 @@
 
 	/* After inverting, we need to update the LED. */
 	if ((n->old_status == BLANK) ^ n->invert)
-		led_set_brightness_async(led, LED_OFF);
+		led_set_brightness_nosleep(led, LED_OFF);
 	else
-		led_set_brightness_async(led, n->brightness);
+		led_set_brightness_nosleep(led, n->brightness);
 
 	return num;
 }
diff --git a/drivers/leds/trigger/ledtrig-cpu.c b/drivers/leds/trigger/ledtrig-cpu.c
index aec0f02..938467f 100644
--- a/drivers/leds/trigger/ledtrig-cpu.c
+++ b/drivers/leds/trigger/ledtrig-cpu.c
@@ -19,7 +19,6 @@
  *
  */
 
-#include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/slab.h>
@@ -140,27 +139,4 @@
 
 	return 0;
 }
-module_init(ledtrig_cpu_init);
-
-static void __exit ledtrig_cpu_exit(void)
-{
-	int cpu;
-
-	unregister_cpu_notifier(&ledtrig_cpu_nb);
-
-	for_each_possible_cpu(cpu) {
-		struct led_trigger_cpu *trig = &per_cpu(cpu_trig, cpu);
-
-		led_trigger_unregister_simple(trig->_trig);
-		trig->_trig = NULL;
-		memset(trig->name, 0, MAX_NAME_LEN);
-	}
-
-	unregister_syscore_ops(&ledtrig_cpu_syscore_ops);
-}
-module_exit(ledtrig_cpu_exit);
-
-MODULE_AUTHOR("Linus Walleij <linus.walleij@linaro.org>");
-MODULE_AUTHOR("Bryan Wu <bryan.wu@canonical.com>");
-MODULE_DESCRIPTION("CPU LED trigger");
-MODULE_LICENSE("GPL");
+device_initcall(ledtrig_cpu_init);
diff --git a/drivers/leds/trigger/ledtrig-default-on.c b/drivers/leds/trigger/ledtrig-default-on.c
index 6f38f88..ff455cb 100644
--- a/drivers/leds/trigger/ledtrig-default-on.c
+++ b/drivers/leds/trigger/ledtrig-default-on.c
@@ -19,7 +19,7 @@
 
 static void defon_trig_activate(struct led_classdev *led_cdev)
 {
-	led_set_brightness_async(led_cdev, led_cdev->max_brightness);
+	led_set_brightness_nosleep(led_cdev, led_cdev->max_brightness);
 }
 
 static struct led_trigger defon_led_trigger = {
diff --git a/drivers/leds/trigger/ledtrig-gpio.c b/drivers/leds/trigger/ledtrig-gpio.c
index 4cc7040..51288a4 100644
--- a/drivers/leds/trigger/ledtrig-gpio.c
+++ b/drivers/leds/trigger/ledtrig-gpio.c
@@ -54,12 +54,12 @@
 
 	if (tmp) {
 		if (gpio_data->desired_brightness)
-			led_set_brightness_async(gpio_data->led,
+			led_set_brightness_nosleep(gpio_data->led,
 					   gpio_data->desired_brightness);
 		else
-			led_set_brightness_async(gpio_data->led, LED_FULL);
+			led_set_brightness_nosleep(gpio_data->led, LED_FULL);
 	} else {
-		led_set_brightness_async(gpio_data->led, LED_OFF);
+		led_set_brightness_nosleep(gpio_data->led, LED_OFF);
 	}
 }
 
diff --git a/drivers/leds/trigger/ledtrig-heartbeat.c b/drivers/leds/trigger/ledtrig-heartbeat.c
index 8622ce6..410c39c 100644
--- a/drivers/leds/trigger/ledtrig-heartbeat.c
+++ b/drivers/leds/trigger/ledtrig-heartbeat.c
@@ -38,7 +38,7 @@
 	unsigned long delay = 0;
 
 	if (unlikely(panic_heartbeats)) {
-		led_set_brightness(led_cdev, LED_OFF);
+		led_set_brightness_nosleep(led_cdev, LED_OFF);
 		return;
 	}
 
@@ -81,7 +81,7 @@
 		break;
 	}
 
-	led_set_brightness_async(led_cdev, brightness);
+	led_set_brightness_nosleep(led_cdev, brightness);
 	mod_timer(&heartbeat_data->timer, jiffies + delay);
 }
 
diff --git a/drivers/leds/trigger/ledtrig-ide-disk.c b/drivers/leds/trigger/ledtrig-ide-disk.c
index 2cd7c0c..c02a3ac 100644
--- a/drivers/leds/trigger/ledtrig-ide-disk.c
+++ b/drivers/leds/trigger/ledtrig-ide-disk.c
@@ -11,7 +11,6 @@
  *
  */
 
-#include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/leds.h>
@@ -33,15 +32,4 @@
 	led_trigger_register_simple("ide-disk", &ledtrig_ide);
 	return 0;
 }
-
-static void __exit ledtrig_ide_exit(void)
-{
-	led_trigger_unregister_simple(ledtrig_ide);
-}
-
-module_init(ledtrig_ide_init);
-module_exit(ledtrig_ide_exit);
-
-MODULE_AUTHOR("Richard Purdie <rpurdie@openedhand.com>");
-MODULE_DESCRIPTION("LED IDE Disk Activity Trigger");
-MODULE_LICENSE("GPL");
+device_initcall(ledtrig_ide_init);
diff --git a/drivers/leds/trigger/ledtrig-oneshot.c b/drivers/leds/trigger/ledtrig-oneshot.c
index fbd02cd..b8ea9f0 100644
--- a/drivers/leds/trigger/ledtrig-oneshot.c
+++ b/drivers/leds/trigger/ledtrig-oneshot.c
@@ -63,9 +63,9 @@
 	oneshot_data->invert = !!state;
 
 	if (oneshot_data->invert)
-		led_set_brightness_async(led_cdev, LED_FULL);
+		led_set_brightness_nosleep(led_cdev, LED_FULL);
 	else
-		led_set_brightness_async(led_cdev, LED_OFF);
+		led_set_brightness_nosleep(led_cdev, LED_OFF);
 
 	return size;
 }
@@ -201,4 +201,4 @@
 
 MODULE_AUTHOR("Fabio Baltieri <fabio.baltieri@gmail.com>");
 MODULE_DESCRIPTION("One-shot LED trigger");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/leds/trigger/ledtrig-transient.c b/drivers/leds/trigger/ledtrig-transient.c
index 3c34de4..7e6011b 100644
--- a/drivers/leds/trigger/ledtrig-transient.c
+++ b/drivers/leds/trigger/ledtrig-transient.c
@@ -41,7 +41,7 @@
 	struct transient_trig_data *transient_data = led_cdev->trigger_data;
 
 	transient_data->activate = 0;
-	led_set_brightness_async(led_cdev, transient_data->restore_state);
+	led_set_brightness_nosleep(led_cdev, transient_data->restore_state);
 }
 
 static ssize_t transient_activate_show(struct device *dev,
@@ -72,7 +72,7 @@
 	if (state == 0 && transient_data->activate == 1) {
 		del_timer(&transient_data->timer);
 		transient_data->activate = state;
-		led_set_brightness_async(led_cdev,
+		led_set_brightness_nosleep(led_cdev,
 					transient_data->restore_state);
 		return size;
 	}
@@ -81,11 +81,11 @@
 	if (state == 1 && transient_data->activate == 0 &&
 	    transient_data->duration != 0) {
 		transient_data->activate = state;
-		led_set_brightness_async(led_cdev, transient_data->state);
+		led_set_brightness_nosleep(led_cdev, transient_data->state);
 		transient_data->restore_state =
 		    (transient_data->state == LED_FULL) ? LED_OFF : LED_FULL;
 		mod_timer(&transient_data->timer,
-			  jiffies + transient_data->duration);
+			  jiffies + msecs_to_jiffies(transient_data->duration));
 	}
 
 	/* state == 0 && transient_data->activate == 0
@@ -204,7 +204,7 @@
 
 	if (led_cdev->activated) {
 		del_timer_sync(&transient_data->timer);
-		led_set_brightness_async(led_cdev,
+		led_set_brightness_nosleep(led_cdev,
 					transient_data->restore_state);
 		device_remove_file(led_cdev->dev, &dev_attr_activate);
 		device_remove_file(led_cdev->dev, &dev_attr_duration);
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index 7913fdc..0a2e727 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -240,6 +240,15 @@
 	 as a cache, holding recently-read blocks in memory and performing
 	 delayed writes.
 
+config DM_DEBUG_BLOCK_STACK_TRACING
+       bool "Keep stack trace of persistent data block lock holders"
+       depends on STACKTRACE_SUPPORT && DM_BUFIO
+       select STACKTRACE
+       ---help---
+	 Enable this for messages that may help debug problems with the
+	 block manager locking used by thin provisioning and caching.
+
+	 If unsure, say N.
 config DM_BIO_PRISON
        tristate
        depends on BLK_DEV_DM
@@ -458,6 +467,18 @@
 
 	  If unsure, say N.
 
+config DM_VERITY_FEC
+	bool "Verity forward error correction support"
+	depends on DM_VERITY
+	select REED_SOLOMON
+	select REED_SOLOMON_DEC8
+	---help---
+	  Add forward error correction support to dm-verity. This option
+	  makes it possible to use pre-generated error correction data to
+	  recover from corrupted blocks.
+
+	  If unsure, say N.
+
 config DM_SWITCH
 	tristate "Switch target support (EXPERIMENTAL)"
 	depends on BLK_DEV_DM
diff --git a/drivers/md/Makefile b/drivers/md/Makefile
index f34979cd..62a6576 100644
--- a/drivers/md/Makefile
+++ b/drivers/md/Makefile
@@ -16,6 +16,7 @@
 dm-cache-smq-y   += dm-cache-policy-smq.o
 dm-cache-cleaner-y += dm-cache-policy-cleaner.o
 dm-era-y	+= dm-era-target.o
+dm-verity-y	+= dm-verity-target.o
 md-mod-y	+= md.o bitmap.o
 raid456-y	+= raid5.o raid5-cache.o
 
@@ -63,3 +64,7 @@
 ifeq ($(CONFIG_DM_UEVENT),y)
 dm-mod-objs			+= dm-uevent.o
 endif
+
+ifeq ($(CONFIG_DM_VERITY_FEC),y)
+dm-verity-objs			+= dm-verity-fec.o
+endif
diff --git a/drivers/md/bcache/util.c b/drivers/md/bcache/util.c
index db3ae4c..dde6172 100644
--- a/drivers/md/bcache/util.c
+++ b/drivers/md/bcache/util.c
@@ -230,7 +230,7 @@
 	BUG_ON(!bio->bi_iter.bi_size);
 	BUG_ON(bio->bi_vcnt);
 
-	bv->bv_offset = base ? ((unsigned long) base) % PAGE_SIZE : 0;
+	bv->bv_offset = base ? offset_in_page(base) : 0;
 	goto start;
 
 	for (; size; bio->bi_vcnt++, bv++) {
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 2dd3308..cd77216 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -16,6 +16,7 @@
 #include <linux/shrinker.h>
 #include <linux/module.h>
 #include <linux/rbtree.h>
+#include <linux/stacktrace.h>
 
 #define DM_MSG_PREFIX "bufio"
 
@@ -149,6 +150,11 @@
 	struct list_head write_list;
 	struct bio bio;
 	struct bio_vec bio_vec[DM_BUFIO_INLINE_VECS];
+#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
+#define MAX_STACK 10
+	struct stack_trace stack_trace;
+	unsigned long stack_entries[MAX_STACK];
+#endif
 };
 
 /*----------------------------------------------------------------*/
@@ -253,6 +259,17 @@
  */
 static DEFINE_MUTEX(dm_bufio_clients_lock);
 
+#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
+static void buffer_record_stack(struct dm_buffer *b)
+{
+	b->stack_trace.nr_entries = 0;
+	b->stack_trace.max_entries = MAX_STACK;
+	b->stack_trace.entries = b->stack_entries;
+	b->stack_trace.skip = 2;
+	save_stack_trace(&b->stack_trace);
+}
+#endif
+
 /*----------------------------------------------------------------
  * A red/black tree acts as an index for all the buffers.
  *--------------------------------------------------------------*/
@@ -454,6 +471,9 @@
 
 	adjust_total_allocated(b->data_mode, (long)c->block_size);
 
+#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
+	memset(&b->stack_trace, 0, sizeof(b->stack_trace));
+#endif
 	return b;
 }
 
@@ -630,7 +650,7 @@
 	do {
 		if (!bio_add_page(&b->bio, virt_to_page(ptr),
 				  len < PAGE_SIZE ? len : PAGE_SIZE,
-				  virt_to_phys(ptr) & (PAGE_SIZE - 1))) {
+				  offset_in_page(ptr))) {
 			BUG_ON(b->c->block_size <= PAGE_SIZE);
 			use_dmio(b, rw, block, end_io);
 			return;
@@ -1063,12 +1083,16 @@
 
 	dm_bufio_lock(c);
 	b = __bufio_new(c, block, nf, &need_submit, &write_list);
+#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
+	if (b && b->hold_count == 1)
+		buffer_record_stack(b);
+#endif
 	dm_bufio_unlock(c);
 
 	__flush_write_list(&write_list);
 
 	if (!b)
-		return b;
+		return NULL;
 
 	if (need_submit)
 		submit_io(b, READ, b->block, read_endio);
@@ -1462,6 +1486,7 @@
 {
 	struct dm_buffer *b;
 	int i;
+	bool warned = false;
 
 	BUG_ON(dm_bufio_in_request());
 
@@ -1476,9 +1501,21 @@
 		__free_buffer_wake(b);
 
 	for (i = 0; i < LIST_SIZE; i++)
-		list_for_each_entry(b, &c->lru[i], lru_list)
+		list_for_each_entry(b, &c->lru[i], lru_list) {
+			WARN_ON(!warned);
+			warned = true;
 			DMERR("leaked buffer %llx, hold count %u, list %d",
 			      (unsigned long long)b->block, b->hold_count, i);
+#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
+			print_stack_trace(&b->stack_trace, 1);
+			b->hold_count = 0; /* mark unclaimed to avoid BUG_ON below */
+#endif
+		}
+
+#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
+	while ((b = __get_unclaimed_buffer(c)))
+		__free_buffer_wake(b);
+#endif
 
 	for (i = 0; i < LIST_SIZE; i++)
 		BUG_ON(!list_empty(&c->lru[i]));
@@ -1891,8 +1928,7 @@
 		bug = 1;
 	}
 
-	if (bug)
-		BUG();
+	BUG_ON(bug);
 }
 
 module_init(dm_bufio_init)
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index 2fd4c82..5780acc 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -118,14 +118,12 @@
  */
 struct dm_hook_info {
 	bio_end_io_t *bi_end_io;
-	void *bi_private;
 };
 
 static void dm_hook_bio(struct dm_hook_info *h, struct bio *bio,
 			bio_end_io_t *bi_end_io, void *bi_private)
 {
 	h->bi_end_io = bio->bi_end_io;
-	h->bi_private = bio->bi_private;
 
 	bio->bi_end_io = bi_end_io;
 	bio->bi_private = bi_private;
@@ -134,7 +132,6 @@
 static void dm_unhook_bio(struct dm_hook_info *h, struct bio *bio)
 {
 	bio->bi_end_io = h->bi_end_io;
-	bio->bi_private = h->bi_private;
 }
 
 /*----------------------------------------------------------------*/
diff --git a/drivers/md/dm-exception-store.h b/drivers/md/dm-exception-store.h
index fae34e7..12b5216 100644
--- a/drivers/md/dm-exception-store.h
+++ b/drivers/md/dm-exception-store.h
@@ -69,7 +69,7 @@
 	 * Update the metadata with this exception.
 	 */
 	void (*commit_exception) (struct dm_exception_store *store,
-				  struct dm_exception *e,
+				  struct dm_exception *e, int valid,
 				  void (*callback) (void *, int success),
 				  void *callback_context);
 
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index 81c5e1a..06d426e 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -246,7 +246,7 @@
 {
 	dp->get_page = vm_get_page;
 	dp->next_page = vm_next_page;
-	dp->context_u = ((unsigned long) data) & (PAGE_SIZE - 1);
+	dp->context_u = offset_in_page(data);
 	dp->context_ptr = data;
 }
 
@@ -271,7 +271,7 @@
 {
 	dp->get_page = km_get_page;
 	dp->next_page = km_next_page;
-	dp->context_u = ((unsigned long) data) & (PAGE_SIZE - 1);
+	dp->context_u = offset_in_page(data);
 	dp->context_ptr = data;
 }
 
diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c
index 3164b8b..4d39093 100644
--- a/drivers/md/dm-snap-persistent.c
+++ b/drivers/md/dm-snap-persistent.c
@@ -695,7 +695,7 @@
 }
 
 static void persistent_commit_exception(struct dm_exception_store *store,
-					struct dm_exception *e,
+					struct dm_exception *e, int valid,
 					void (*callback) (void *, int success),
 					void *callback_context)
 {
@@ -704,6 +704,9 @@
 	struct core_exception ce;
 	struct commit_callback *cb;
 
+	if (!valid)
+		ps->valid = 0;
+
 	ce.old_chunk = e->old_chunk;
 	ce.new_chunk = e->new_chunk;
 	write_exception(ps, ps->current_committed++, &ce);
diff --git a/drivers/md/dm-snap-transient.c b/drivers/md/dm-snap-transient.c
index 9b7c8c8..4d50a12 100644
--- a/drivers/md/dm-snap-transient.c
+++ b/drivers/md/dm-snap-transient.c
@@ -52,12 +52,12 @@
 }
 
 static void transient_commit_exception(struct dm_exception_store *store,
-				       struct dm_exception *e,
+				       struct dm_exception *e, int valid,
 				       void (*callback) (void *, int success),
 				       void *callback_context)
 {
 	/* Just succeed */
-	callback(callback_context, 1);
+	callback(callback_context, valid);
 }
 
 static void transient_usage(struct dm_exception_store *store,
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index c06b74e..376638608 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -207,7 +207,6 @@
 	 */
 	struct bio *full_bio;
 	bio_end_io_t *full_bio_end_io;
-	void *full_bio_private;
 };
 
 /*
@@ -1438,8 +1437,9 @@
 	dm_table_event(s->ti->table);
 }
 
-static void pending_complete(struct dm_snap_pending_exception *pe, int success)
+static void pending_complete(void *context, int success)
 {
+	struct dm_snap_pending_exception *pe = context;
 	struct dm_exception *e;
 	struct dm_snapshot *s = pe->snap;
 	struct bio *origin_bios = NULL;
@@ -1485,10 +1485,8 @@
 	snapshot_bios = bio_list_get(&pe->snapshot_bios);
 	origin_bios = bio_list_get(&pe->origin_bios);
 	full_bio = pe->full_bio;
-	if (full_bio) {
+	if (full_bio)
 		full_bio->bi_end_io = pe->full_bio_end_io;
-		full_bio->bi_private = pe->full_bio_private;
-	}
 	increment_pending_exceptions_done_count();
 
 	up_write(&s->lock);
@@ -1509,24 +1507,13 @@
 	free_pending_exception(pe);
 }
 
-static void commit_callback(void *context, int success)
-{
-	struct dm_snap_pending_exception *pe = context;
-
-	pending_complete(pe, success);
-}
-
 static void complete_exception(struct dm_snap_pending_exception *pe)
 {
 	struct dm_snapshot *s = pe->snap;
 
-	if (unlikely(pe->copy_error))
-		pending_complete(pe, 0);
-
-	else
-		/* Update the metadata if we are persistent */
-		s->store->type->commit_exception(s->store, &pe->e,
-						 commit_callback, pe);
+	/* Update the metadata if we are persistent */
+	s->store->type->commit_exception(s->store, &pe->e, !pe->copy_error,
+					 pending_complete, pe);
 }
 
 /*
@@ -1605,7 +1592,6 @@
 
 	pe->full_bio = bio;
 	pe->full_bio_end_io = bio->bi_end_io;
-	pe->full_bio_private = bio->bi_private;
 
 	callback_data = dm_kcopyd_prepare_callback(s->kcopyd_client,
 						   copy_callback, pe);
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index c219a05..f962d64 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -1395,8 +1395,21 @@
 	return td->snapshotted_time > time;
 }
 
-int dm_thin_find_block(struct dm_thin_device *td, dm_block_t block,
-		       int can_issue_io, struct dm_thin_lookup_result *result)
+static void unpack_lookup_result(struct dm_thin_device *td, __le64 value,
+				 struct dm_thin_lookup_result *result)
+{
+	uint64_t block_time = 0;
+	dm_block_t exception_block;
+	uint32_t exception_time;
+
+	block_time = le64_to_cpu(value);
+	unpack_block_time(block_time, &exception_block, &exception_time);
+	result->block = exception_block;
+	result->shared = __snapshotted_since(td, exception_time);
+}
+
+static int __find_block(struct dm_thin_device *td, dm_block_t block,
+			int can_issue_io, struct dm_thin_lookup_result *result)
 {
 	int r;
 	__le64 value;
@@ -1404,39 +1417,56 @@
 	dm_block_t keys[2] = { td->id, block };
 	struct dm_btree_info *info;
 
-	down_read(&pmd->root_lock);
-	if (pmd->fail_io) {
-		up_read(&pmd->root_lock);
-		return -EINVAL;
-	}
-
 	if (can_issue_io) {
 		info = &pmd->info;
 	} else
 		info = &pmd->nb_info;
 
 	r = dm_btree_lookup(info, pmd->root, keys, &value);
-	if (!r) {
-		uint64_t block_time = 0;
-		dm_block_t exception_block;
-		uint32_t exception_time;
+	if (!r)
+		unpack_lookup_result(td, value, result);
 
-		block_time = le64_to_cpu(value);
-		unpack_block_time(block_time, &exception_block,
-				  &exception_time);
-		result->block = exception_block;
-		result->shared = __snapshotted_since(td, exception_time);
+	return r;
+}
+
+int dm_thin_find_block(struct dm_thin_device *td, dm_block_t block,
+		       int can_issue_io, struct dm_thin_lookup_result *result)
+{
+	int r;
+	struct dm_pool_metadata *pmd = td->pmd;
+
+	down_read(&pmd->root_lock);
+	if (pmd->fail_io) {
+		up_read(&pmd->root_lock);
+		return -EINVAL;
 	}
 
+	r = __find_block(td, block, can_issue_io, result);
+
 	up_read(&pmd->root_lock);
 	return r;
 }
 
-/* FIXME: write a more efficient one in btree */
-int dm_thin_find_mapped_range(struct dm_thin_device *td,
-			      dm_block_t begin, dm_block_t end,
-			      dm_block_t *thin_begin, dm_block_t *thin_end,
-			      dm_block_t *pool_begin, bool *maybe_shared)
+static int __find_next_mapped_block(struct dm_thin_device *td, dm_block_t block,
+					  dm_block_t *vblock,
+					  struct dm_thin_lookup_result *result)
+{
+	int r;
+	__le64 value;
+	struct dm_pool_metadata *pmd = td->pmd;
+	dm_block_t keys[2] = { td->id, block };
+
+	r = dm_btree_lookup_next(&pmd->info, pmd->root, keys, vblock, &value);
+	if (!r)
+		unpack_lookup_result(td, value, result);
+
+	return r;
+}
+
+static int __find_mapped_range(struct dm_thin_device *td,
+			       dm_block_t begin, dm_block_t end,
+			       dm_block_t *thin_begin, dm_block_t *thin_end,
+			       dm_block_t *pool_begin, bool *maybe_shared)
 {
 	int r;
 	dm_block_t pool_end;
@@ -1445,21 +1475,11 @@
 	if (end < begin)
 		return -ENODATA;
 
-	/*
-	 * Find first mapped block.
-	 */
-	while (begin < end) {
-		r = dm_thin_find_block(td, begin, true, &lookup);
-		if (r) {
-			if (r != -ENODATA)
-				return r;
-		} else
-			break;
+	r = __find_next_mapped_block(td, begin, &begin, &lookup);
+	if (r)
+		return r;
 
-		begin++;
-	}
-
-	if (begin == end)
+	if (begin >= end)
 		return -ENODATA;
 
 	*thin_begin = begin;
@@ -1469,7 +1489,7 @@
 	begin++;
 	pool_end = *pool_begin + 1;
 	while (begin != end) {
-		r = dm_thin_find_block(td, begin, true, &lookup);
+		r = __find_block(td, begin, true, &lookup);
 		if (r) {
 			if (r == -ENODATA)
 				break;
@@ -1489,6 +1509,24 @@
 	return 0;
 }
 
+int dm_thin_find_mapped_range(struct dm_thin_device *td,
+			      dm_block_t begin, dm_block_t end,
+			      dm_block_t *thin_begin, dm_block_t *thin_end,
+			      dm_block_t *pool_begin, bool *maybe_shared)
+{
+	int r = -EINVAL;
+	struct dm_pool_metadata *pmd = td->pmd;
+
+	down_read(&pmd->root_lock);
+	if (!pmd->fail_io) {
+		r = __find_mapped_range(td, begin, end, thin_begin, thin_end,
+					pool_begin, maybe_shared);
+	}
+	up_read(&pmd->root_lock);
+
+	return r;
+}
+
 static int __insert(struct dm_thin_device *td, dm_block_t block,
 		    dm_block_t data_block)
 {
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 63903a5..72d91f4 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -3453,8 +3453,8 @@
 	struct pool_c *pt = ti->private;
 	struct pool *pool = pt->pool;
 
-	cancel_delayed_work(&pool->waker);
-	cancel_delayed_work(&pool->no_space_timeout);
+	cancel_delayed_work_sync(&pool->waker);
+	cancel_delayed_work_sync(&pool->no_space_timeout);
 	flush_workqueue(pool->wq);
 	(void) commit(pool);
 }
@@ -3886,7 +3886,7 @@
 	.name = "thin-pool",
 	.features = DM_TARGET_SINGLETON | DM_TARGET_ALWAYS_WRITEABLE |
 		    DM_TARGET_IMMUTABLE,
-	.version = {1, 16, 0},
+	.version = {1, 17, 0},
 	.module = THIS_MODULE,
 	.ctr = pool_ctr,
 	.dtr = pool_dtr,
@@ -4260,7 +4260,7 @@
 
 static struct target_type thin_target = {
 	.name = "thin",
-	.version = {1, 16, 0},
+	.version = {1, 17, 0},
 	.module	= THIS_MODULE,
 	.ctr = thin_ctr,
 	.dtr = thin_dtr,
diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c
new file mode 100644
index 0000000..1cc10c4
--- /dev/null
+++ b/drivers/md/dm-verity-fec.c
@@ -0,0 +1,818 @@
+/*
+ * Copyright (C) 2015 Google, Inc.
+ *
+ * Author: Sami Tolvanen <samitolvanen@google.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#include "dm-verity-fec.h"
+#include <linux/math64.h>
+
+#define DM_MSG_PREFIX	"verity-fec"
+
+/*
+ * If error correction has been configured, returns true.
+ */
+bool verity_fec_is_enabled(struct dm_verity *v)
+{
+	return v->fec && v->fec->dev;
+}
+
+/*
+ * Return a pointer to dm_verity_fec_io after dm_verity_io and its variable
+ * length fields.
+ */
+static inline struct dm_verity_fec_io *fec_io(struct dm_verity_io *io)
+{
+	return (struct dm_verity_fec_io *) verity_io_digest_end(io->v, io);
+}
+
+/*
+ * Return an interleaved offset for a byte in RS block.
+ */
+static inline u64 fec_interleave(struct dm_verity *v, u64 offset)
+{
+	u32 mod;
+
+	mod = do_div(offset, v->fec->rsn);
+	return offset + mod * (v->fec->rounds << v->data_dev_block_bits);
+}
+
+/*
+ * Decode an RS block using Reed-Solomon.
+ */
+static int fec_decode_rs8(struct dm_verity *v, struct dm_verity_fec_io *fio,
+			  u8 *data, u8 *fec, int neras)
+{
+	int i;
+	uint16_t par[DM_VERITY_FEC_RSM - DM_VERITY_FEC_MIN_RSN];
+
+	for (i = 0; i < v->fec->roots; i++)
+		par[i] = fec[i];
+
+	return decode_rs8(fio->rs, data, par, v->fec->rsn, NULL, neras,
+			  fio->erasures, 0, NULL);
+}
+
+/*
+ * Read error-correcting codes for the requested RS block. Returns a pointer
+ * to the data block. Caller is responsible for releasing buf.
+ */
+static u8 *fec_read_parity(struct dm_verity *v, u64 rsb, int index,
+			   unsigned *offset, struct dm_buffer **buf)
+{
+	u64 position, block;
+	u8 *res;
+
+	position = (index + rsb) * v->fec->roots;
+	block = position >> v->data_dev_block_bits;
+	*offset = (unsigned)(position - (block << v->data_dev_block_bits));
+
+	res = dm_bufio_read(v->fec->bufio, v->fec->start + block, buf);
+	if (unlikely(IS_ERR(res))) {
+		DMERR("%s: FEC %llu: parity read failed (block %llu): %ld",
+		      v->data_dev->name, (unsigned long long)rsb,
+		      (unsigned long long)(v->fec->start + block),
+		      PTR_ERR(res));
+		*buf = NULL;
+	}
+
+	return res;
+}
+
+/* Loop over each preallocated buffer slot. */
+#define fec_for_each_prealloc_buffer(__i) \
+	for (__i = 0; __i < DM_VERITY_FEC_BUF_PREALLOC; __i++)
+
+/* Loop over each extra buffer slot. */
+#define fec_for_each_extra_buffer(io, __i) \
+	for (__i = DM_VERITY_FEC_BUF_PREALLOC; __i < DM_VERITY_FEC_BUF_MAX; __i++)
+
+/* Loop over each allocated buffer. */
+#define fec_for_each_buffer(io, __i) \
+	for (__i = 0; __i < (io)->nbufs; __i++)
+
+/* Loop over each RS block in each allocated buffer. */
+#define fec_for_each_buffer_rs_block(io, __i, __j) \
+	fec_for_each_buffer(io, __i) \
+		for (__j = 0; __j < 1 << DM_VERITY_FEC_BUF_RS_BITS; __j++)
+
+/*
+ * Return a pointer to the current RS block when called inside
+ * fec_for_each_buffer_rs_block.
+ */
+static inline u8 *fec_buffer_rs_block(struct dm_verity *v,
+				      struct dm_verity_fec_io *fio,
+				      unsigned i, unsigned j)
+{
+	return &fio->bufs[i][j * v->fec->rsn];
+}
+
+/*
+ * Return an index to the current RS block when called inside
+ * fec_for_each_buffer_rs_block.
+ */
+static inline unsigned fec_buffer_rs_index(unsigned i, unsigned j)
+{
+	return (i << DM_VERITY_FEC_BUF_RS_BITS) + j;
+}
+
+/*
+ * Decode all RS blocks from buffers and copy corrected bytes into fio->output
+ * starting from block_offset.
+ */
+static int fec_decode_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio,
+			   u64 rsb, int byte_index, unsigned block_offset,
+			   int neras)
+{
+	int r, corrected = 0, res;
+	struct dm_buffer *buf;
+	unsigned n, i, offset;
+	u8 *par, *block;
+
+	par = fec_read_parity(v, rsb, block_offset, &offset, &buf);
+	if (IS_ERR(par))
+		return PTR_ERR(par);
+
+	/*
+	 * Decode the RS blocks we have in bufs. Each RS block results in
+	 * one corrected target byte and consumes fec->roots parity bytes.
+	 */
+	fec_for_each_buffer_rs_block(fio, n, i) {
+		block = fec_buffer_rs_block(v, fio, n, i);
+		res = fec_decode_rs8(v, fio, block, &par[offset], neras);
+		if (res < 0) {
+			dm_bufio_release(buf);
+
+			r = res;
+			goto error;
+		}
+
+		corrected += res;
+		fio->output[block_offset] = block[byte_index];
+
+		block_offset++;
+		if (block_offset >= 1 << v->data_dev_block_bits)
+			goto done;
+
+		/* read the next block when we run out of parity bytes */
+		offset += v->fec->roots;
+		if (offset >= 1 << v->data_dev_block_bits) {
+			dm_bufio_release(buf);
+
+			par = fec_read_parity(v, rsb, block_offset, &offset, &buf);
+			if (unlikely(IS_ERR(par)))
+				return PTR_ERR(par);
+		}
+	}
+done:
+	r = corrected;
+error:
+	if (r < 0 && neras)
+		DMERR_LIMIT("%s: FEC %llu: failed to correct: %d",
+			    v->data_dev->name, (unsigned long long)rsb, r);
+	else if (r > 0)
+		DMWARN_LIMIT("%s: FEC %llu: corrected %d errors",
+			     v->data_dev->name, (unsigned long long)rsb, r);
+
+	return r;
+}
+
+/*
+ * Locate data block erasures using verity hashes.
+ */
+static int fec_is_erasure(struct dm_verity *v, struct dm_verity_io *io,
+			  u8 *want_digest, u8 *data)
+{
+	if (unlikely(verity_hash(v, verity_io_hash_desc(v, io),
+				 data, 1 << v->data_dev_block_bits,
+				 verity_io_real_digest(v, io))))
+		return 0;
+
+	return memcmp(verity_io_real_digest(v, io), want_digest,
+		      v->digest_size) != 0;
+}
+
+/*
+ * Read data blocks that are part of the RS block and deinterleave as much as
+ * fits into buffers. Check for erasure locations if @neras is non-NULL.
+ */
+static int fec_read_bufs(struct dm_verity *v, struct dm_verity_io *io,
+			 u64 rsb, u64 target, unsigned block_offset,
+			 int *neras)
+{
+	bool is_zero;
+	int i, j, target_index = -1;
+	struct dm_buffer *buf;
+	struct dm_bufio_client *bufio;
+	struct dm_verity_fec_io *fio = fec_io(io);
+	u64 block, ileaved;
+	u8 *bbuf, *rs_block;
+	u8 want_digest[v->digest_size];
+	unsigned n, k;
+
+	if (neras)
+		*neras = 0;
+
+	/*
+	 * read each of the rsn data blocks that are part of the RS block, and
+	 * interleave contents to available bufs
+	 */
+	for (i = 0; i < v->fec->rsn; i++) {
+		ileaved = fec_interleave(v, rsb * v->fec->rsn + i);
+
+		/*
+		 * target is the data block we want to correct, target_index is
+		 * the index of this block within the rsn RS blocks
+		 */
+		if (ileaved == target)
+			target_index = i;
+
+		block = ileaved >> v->data_dev_block_bits;
+		bufio = v->fec->data_bufio;
+
+		if (block >= v->data_blocks) {
+			block -= v->data_blocks;
+
+			/*
+			 * blocks outside the area were assumed to contain
+			 * zeros when encoding data was generated
+			 */
+			if (unlikely(block >= v->fec->hash_blocks))
+				continue;
+
+			block += v->hash_start;
+			bufio = v->bufio;
+		}
+
+		bbuf = dm_bufio_read(bufio, block, &buf);
+		if (unlikely(IS_ERR(bbuf))) {
+			DMWARN_LIMIT("%s: FEC %llu: read failed (%llu): %ld",
+				     v->data_dev->name,
+				     (unsigned long long)rsb,
+				     (unsigned long long)block, PTR_ERR(bbuf));
+
+			/* assume the block is corrupted */
+			if (neras && *neras <= v->fec->roots)
+				fio->erasures[(*neras)++] = i;
+
+			continue;
+		}
+
+		/* locate erasures if the block is on the data device */
+		if (bufio == v->fec->data_bufio &&
+		    verity_hash_for_block(v, io, block, want_digest,
+					  &is_zero) == 0) {
+			/* skip known zero blocks entirely */
+			if (is_zero)
+				continue;
+
+			/*
+			 * skip if we have already found the theoretical
+			 * maximum number (i.e. fec->roots) of erasures
+			 */
+			if (neras && *neras <= v->fec->roots &&
+			    fec_is_erasure(v, io, want_digest, bbuf))
+				fio->erasures[(*neras)++] = i;
+		}
+
+		/*
+		 * deinterleave and copy the bytes that fit into bufs,
+		 * starting from block_offset
+		 */
+		fec_for_each_buffer_rs_block(fio, n, j) {
+			k = fec_buffer_rs_index(n, j) + block_offset;
+
+			if (k >= 1 << v->data_dev_block_bits)
+				goto done;
+
+			rs_block = fec_buffer_rs_block(v, fio, n, j);
+			rs_block[i] = bbuf[k];
+		}
+done:
+		dm_bufio_release(buf);
+	}
+
+	return target_index;
+}
+
+/*
+ * Allocate RS control structure and FEC buffers from preallocated mempools,
+ * and attempt to allocate as many extra buffers as available.
+ */
+static int fec_alloc_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio)
+{
+	unsigned n;
+
+	if (!fio->rs) {
+		fio->rs = mempool_alloc(v->fec->rs_pool, 0);
+		if (unlikely(!fio->rs)) {
+			DMERR("failed to allocate RS");
+			return -ENOMEM;
+		}
+	}
+
+	fec_for_each_prealloc_buffer(n) {
+		if (fio->bufs[n])
+			continue;
+
+		fio->bufs[n] = mempool_alloc(v->fec->prealloc_pool, GFP_NOIO);
+		if (unlikely(!fio->bufs[n])) {
+			DMERR("failed to allocate FEC buffer");
+			return -ENOMEM;
+		}
+	}
+
+	/* try to allocate the maximum number of buffers */
+	fec_for_each_extra_buffer(fio, n) {
+		if (fio->bufs[n])
+			continue;
+
+		fio->bufs[n] = mempool_alloc(v->fec->extra_pool, GFP_NOIO);
+		/* we can manage with even one buffer if necessary */
+		if (unlikely(!fio->bufs[n]))
+			break;
+	}
+	fio->nbufs = n;
+
+	if (!fio->output) {
+		fio->output = mempool_alloc(v->fec->output_pool, GFP_NOIO);
+
+		if (!fio->output) {
+			DMERR("failed to allocate FEC page");
+			return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * Initialize buffers and clear erasures. fec_read_bufs() assumes buffers are
+ * zeroed before deinterleaving.
+ */
+static void fec_init_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio)
+{
+	unsigned n;
+
+	fec_for_each_buffer(fio, n)
+		memset(fio->bufs[n], 0, v->fec->rsn << DM_VERITY_FEC_BUF_RS_BITS);
+
+	memset(fio->erasures, 0, sizeof(fio->erasures));
+}
+
+/*
+ * Decode all RS blocks in a single data block and return the target block
+ * (indicated by @offset) in fio->output. If @use_erasures is non-zero, uses
+ * hashes to locate erasures.
+ */
+static int fec_decode_rsb(struct dm_verity *v, struct dm_verity_io *io,
+			  struct dm_verity_fec_io *fio, u64 rsb, u64 offset,
+			  bool use_erasures)
+{
+	int r, neras = 0;
+	unsigned pos;
+
+	r = fec_alloc_bufs(v, fio);
+	if (unlikely(r < 0))
+		return r;
+
+	for (pos = 0; pos < 1 << v->data_dev_block_bits; ) {
+		fec_init_bufs(v, fio);
+
+		r = fec_read_bufs(v, io, rsb, offset, pos,
+				  use_erasures ? &neras : NULL);
+		if (unlikely(r < 0))
+			return r;
+
+		r = fec_decode_bufs(v, fio, rsb, r, pos, neras);
+		if (r < 0)
+			return r;
+
+		pos += fio->nbufs << DM_VERITY_FEC_BUF_RS_BITS;
+	}
+
+	/* Always re-validate the corrected block against the expected hash */
+	r = verity_hash(v, verity_io_hash_desc(v, io), fio->output,
+			1 << v->data_dev_block_bits,
+			verity_io_real_digest(v, io));
+	if (unlikely(r < 0))
+		return r;
+
+	if (memcmp(verity_io_real_digest(v, io), verity_io_want_digest(v, io),
+		   v->digest_size)) {
+		DMERR_LIMIT("%s: FEC %llu: failed to correct (%d erasures)",
+			    v->data_dev->name, (unsigned long long)rsb, neras);
+		return -EILSEQ;
+	}
+
+	return 0;
+}
+
+static int fec_bv_copy(struct dm_verity *v, struct dm_verity_io *io, u8 *data,
+		       size_t len)
+{
+	struct dm_verity_fec_io *fio = fec_io(io);
+
+	memcpy(data, &fio->output[fio->output_pos], len);
+	fio->output_pos += len;
+
+	return 0;
+}
+
+/*
+ * Correct errors in a block. Copies corrected block to dest if non-NULL,
+ * otherwise to a bio_vec starting from iter.
+ */
+int verity_fec_decode(struct dm_verity *v, struct dm_verity_io *io,
+		      enum verity_block_type type, sector_t block, u8 *dest,
+		      struct bvec_iter *iter)
+{
+	int r;
+	struct dm_verity_fec_io *fio = fec_io(io);
+	u64 offset, res, rsb;
+
+	if (!verity_fec_is_enabled(v))
+		return -EOPNOTSUPP;
+
+	if (type == DM_VERITY_BLOCK_TYPE_METADATA)
+		block += v->data_blocks;
+
+	/*
+	 * For RS(M, N), the continuous FEC data is divided into blocks of N
+	 * bytes. Since block size may not be divisible by N, the last block
+	 * is zero padded when decoding.
+	 *
+	 * Each byte of the block is covered by a different RS(M, N) code,
+	 * and each code is interleaved over N blocks to make it less likely
+	 * that bursty corruption will leave us in unrecoverable state.
+	 */
+
+	offset = block << v->data_dev_block_bits;
+
+	res = offset;
+	div64_u64(res, v->fec->rounds << v->data_dev_block_bits);
+
+	/*
+	 * The base RS block we can feed to the interleaver to find out all
+	 * blocks required for decoding.
+	 */
+	rsb = offset - res * (v->fec->rounds << v->data_dev_block_bits);
+
+	/*
+	 * Locating erasures is slow, so attempt to recover the block without
+	 * them first. Do a second attempt with erasures if the corruption is
+	 * bad enough.
+	 */
+	r = fec_decode_rsb(v, io, fio, rsb, offset, false);
+	if (r < 0) {
+		r = fec_decode_rsb(v, io, fio, rsb, offset, true);
+		if (r < 0)
+			return r;
+	}
+
+	if (dest)
+		memcpy(dest, fio->output, 1 << v->data_dev_block_bits);
+	else if (iter) {
+		fio->output_pos = 0;
+		r = verity_for_bv_block(v, io, iter, fec_bv_copy);
+	}
+
+	return r;
+}
+
+/*
+ * Clean up per-bio data.
+ */
+void verity_fec_finish_io(struct dm_verity_io *io)
+{
+	unsigned n;
+	struct dm_verity_fec *f = io->v->fec;
+	struct dm_verity_fec_io *fio = fec_io(io);
+
+	if (!verity_fec_is_enabled(io->v))
+		return;
+
+	mempool_free(fio->rs, f->rs_pool);
+
+	fec_for_each_prealloc_buffer(n)
+		mempool_free(fio->bufs[n], f->prealloc_pool);
+
+	fec_for_each_extra_buffer(fio, n)
+		mempool_free(fio->bufs[n], f->extra_pool);
+
+	mempool_free(fio->output, f->output_pool);
+}
+
+/*
+ * Initialize per-bio data.
+ */
+void verity_fec_init_io(struct dm_verity_io *io)
+{
+	struct dm_verity_fec_io *fio = fec_io(io);
+
+	if (!verity_fec_is_enabled(io->v))
+		return;
+
+	fio->rs = NULL;
+	memset(fio->bufs, 0, sizeof(fio->bufs));
+	fio->nbufs = 0;
+	fio->output = NULL;
+}
+
+/*
+ * Append feature arguments and values to the status table.
+ */
+unsigned verity_fec_status_table(struct dm_verity *v, unsigned sz,
+				 char *result, unsigned maxlen)
+{
+	if (!verity_fec_is_enabled(v))
+		return sz;
+
+	DMEMIT(" " DM_VERITY_OPT_FEC_DEV " %s "
+	       DM_VERITY_OPT_FEC_BLOCKS " %llu "
+	       DM_VERITY_OPT_FEC_START " %llu "
+	       DM_VERITY_OPT_FEC_ROOTS " %d",
+	       v->fec->dev->name,
+	       (unsigned long long)v->fec->blocks,
+	       (unsigned long long)v->fec->start,
+	       v->fec->roots);
+
+	return sz;
+}
+
+void verity_fec_dtr(struct dm_verity *v)
+{
+	struct dm_verity_fec *f = v->fec;
+
+	if (!verity_fec_is_enabled(v))
+		goto out;
+
+	mempool_destroy(f->rs_pool);
+	mempool_destroy(f->prealloc_pool);
+	mempool_destroy(f->extra_pool);
+	kmem_cache_destroy(f->cache);
+
+	if (f->data_bufio)
+		dm_bufio_client_destroy(f->data_bufio);
+	if (f->bufio)
+		dm_bufio_client_destroy(f->bufio);
+
+	if (f->dev)
+		dm_put_device(v->ti, f->dev);
+out:
+	kfree(f);
+	v->fec = NULL;
+}
+
+static void *fec_rs_alloc(gfp_t gfp_mask, void *pool_data)
+{
+	struct dm_verity *v = (struct dm_verity *)pool_data;
+
+	return init_rs(8, 0x11d, 0, 1, v->fec->roots);
+}
+
+static void fec_rs_free(void *element, void *pool_data)
+{
+	struct rs_control *rs = (struct rs_control *)element;
+
+	if (rs)
+		free_rs(rs);
+}
+
+bool verity_is_fec_opt_arg(const char *arg_name)
+{
+	return (!strcasecmp(arg_name, DM_VERITY_OPT_FEC_DEV) ||
+		!strcasecmp(arg_name, DM_VERITY_OPT_FEC_BLOCKS) ||
+		!strcasecmp(arg_name, DM_VERITY_OPT_FEC_START) ||
+		!strcasecmp(arg_name, DM_VERITY_OPT_FEC_ROOTS));
+}
+
+int verity_fec_parse_opt_args(struct dm_arg_set *as, struct dm_verity *v,
+			      unsigned *argc, const char *arg_name)
+{
+	int r;
+	struct dm_target *ti = v->ti;
+	const char *arg_value;
+	unsigned long long num_ll;
+	unsigned char num_c;
+	char dummy;
+
+	if (!*argc) {
+		ti->error = "FEC feature arguments require a value";
+		return -EINVAL;
+	}
+
+	arg_value = dm_shift_arg(as);
+	(*argc)--;
+
+	if (!strcasecmp(arg_name, DM_VERITY_OPT_FEC_DEV)) {
+		r = dm_get_device(ti, arg_value, FMODE_READ, &v->fec->dev);
+		if (r) {
+			ti->error = "FEC device lookup failed";
+			return r;
+		}
+
+	} else if (!strcasecmp(arg_name, DM_VERITY_OPT_FEC_BLOCKS)) {
+		if (sscanf(arg_value, "%llu%c", &num_ll, &dummy) != 1 ||
+		    ((sector_t)(num_ll << (v->data_dev_block_bits - SECTOR_SHIFT))
+		     >> (v->data_dev_block_bits - SECTOR_SHIFT) != num_ll)) {
+			ti->error = "Invalid " DM_VERITY_OPT_FEC_BLOCKS;
+			return -EINVAL;
+		}
+		v->fec->blocks = num_ll;
+
+	} else if (!strcasecmp(arg_name, DM_VERITY_OPT_FEC_START)) {
+		if (sscanf(arg_value, "%llu%c", &num_ll, &dummy) != 1 ||
+		    ((sector_t)(num_ll << (v->data_dev_block_bits - SECTOR_SHIFT)) >>
+		     (v->data_dev_block_bits - SECTOR_SHIFT) != num_ll)) {
+			ti->error = "Invalid " DM_VERITY_OPT_FEC_START;
+			return -EINVAL;
+		}
+		v->fec->start = num_ll;
+
+	} else if (!strcasecmp(arg_name, DM_VERITY_OPT_FEC_ROOTS)) {
+		if (sscanf(arg_value, "%hhu%c", &num_c, &dummy) != 1 || !num_c ||
+		    num_c < (DM_VERITY_FEC_RSM - DM_VERITY_FEC_MAX_RSN) ||
+		    num_c > (DM_VERITY_FEC_RSM - DM_VERITY_FEC_MIN_RSN)) {
+			ti->error = "Invalid " DM_VERITY_OPT_FEC_ROOTS;
+			return -EINVAL;
+		}
+		v->fec->roots = num_c;
+
+	} else {
+		ti->error = "Unrecognized verity FEC feature request";
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/*
+ * Allocate dm_verity_fec for v->fec. Must be called before verity_fec_ctr.
+ */
+int verity_fec_ctr_alloc(struct dm_verity *v)
+{
+	struct dm_verity_fec *f;
+
+	f = kzalloc(sizeof(struct dm_verity_fec), GFP_KERNEL);
+	if (!f) {
+		v->ti->error = "Cannot allocate FEC structure";
+		return -ENOMEM;
+	}
+	v->fec = f;
+
+	return 0;
+}
+
+/*
+ * Validate arguments and preallocate memory. Must be called after arguments
+ * have been parsed using verity_fec_parse_opt_args.
+ */
+int verity_fec_ctr(struct dm_verity *v)
+{
+	struct dm_verity_fec *f = v->fec;
+	struct dm_target *ti = v->ti;
+	u64 hash_blocks;
+
+	if (!verity_fec_is_enabled(v)) {
+		verity_fec_dtr(v);
+		return 0;
+	}
+
+	/*
+	 * FEC is computed over data blocks, possible metadata, and
+	 * hash blocks. In other words, FEC covers total of fec_blocks
+	 * blocks consisting of the following:
+	 *
+	 *  data blocks | hash blocks | metadata (optional)
+	 *
+	 * We allow metadata after hash blocks to support a use case
+	 * where all data is stored on the same device and FEC covers
+	 * the entire area.
+	 *
+	 * If metadata is included, we require it to be available on the
+	 * hash device after the hash blocks.
+	 */
+
+	hash_blocks = v->hash_blocks - v->hash_start;
+
+	/*
+	 * Require matching block sizes for data and hash devices for
+	 * simplicity.
+	 */
+	if (v->data_dev_block_bits != v->hash_dev_block_bits) {
+		ti->error = "Block sizes must match to use FEC";
+		return -EINVAL;
+	}
+
+	if (!f->roots) {
+		ti->error = "Missing " DM_VERITY_OPT_FEC_ROOTS;
+		return -EINVAL;
+	}
+	f->rsn = DM_VERITY_FEC_RSM - f->roots;
+
+	if (!f->blocks) {
+		ti->error = "Missing " DM_VERITY_OPT_FEC_BLOCKS;
+		return -EINVAL;
+	}
+
+	f->rounds = f->blocks;
+	if (sector_div(f->rounds, f->rsn))
+		f->rounds++;
+
+	/*
+	 * Due to optional metadata, f->blocks can be larger than
+	 * data_blocks and hash_blocks combined.
+	 */
+	if (f->blocks < v->data_blocks + hash_blocks || !f->rounds) {
+		ti->error = "Invalid " DM_VERITY_OPT_FEC_BLOCKS;
+		return -EINVAL;
+	}
+
+	/*
+	 * Metadata is accessed through the hash device, so we require
+	 * it to be large enough.
+	 */
+	f->hash_blocks = f->blocks - v->data_blocks;
+	if (dm_bufio_get_device_size(v->bufio) < f->hash_blocks) {
+		ti->error = "Hash device is too small for "
+			DM_VERITY_OPT_FEC_BLOCKS;
+		return -E2BIG;
+	}
+
+	f->bufio = dm_bufio_client_create(f->dev->bdev,
+					  1 << v->data_dev_block_bits,
+					  1, 0, NULL, NULL);
+	if (IS_ERR(f->bufio)) {
+		ti->error = "Cannot initialize FEC bufio client";
+		return PTR_ERR(f->bufio);
+	}
+
+	if (dm_bufio_get_device_size(f->bufio) <
+	    ((f->start + f->rounds * f->roots) >> v->data_dev_block_bits)) {
+		ti->error = "FEC device is too small";
+		return -E2BIG;
+	}
+
+	f->data_bufio = dm_bufio_client_create(v->data_dev->bdev,
+					       1 << v->data_dev_block_bits,
+					       1, 0, NULL, NULL);
+	if (IS_ERR(f->data_bufio)) {
+		ti->error = "Cannot initialize FEC data bufio client";
+		return PTR_ERR(f->data_bufio);
+	}
+
+	if (dm_bufio_get_device_size(f->data_bufio) < v->data_blocks) {
+		ti->error = "Data device is too small";
+		return -E2BIG;
+	}
+
+	/* Preallocate an rs_control structure for each worker thread */
+	f->rs_pool = mempool_create(num_online_cpus(), fec_rs_alloc,
+				    fec_rs_free, (void *) v);
+	if (!f->rs_pool) {
+		ti->error = "Cannot allocate RS pool";
+		return -ENOMEM;
+	}
+
+	f->cache = kmem_cache_create("dm_verity_fec_buffers",
+				     f->rsn << DM_VERITY_FEC_BUF_RS_BITS,
+				     0, 0, NULL);
+	if (!f->cache) {
+		ti->error = "Cannot create FEC buffer cache";
+		return -ENOMEM;
+	}
+
+	/* Preallocate DM_VERITY_FEC_BUF_PREALLOC buffers for each thread */
+	f->prealloc_pool = mempool_create_slab_pool(num_online_cpus() *
+						    DM_VERITY_FEC_BUF_PREALLOC,
+						    f->cache);
+	if (!f->prealloc_pool) {
+		ti->error = "Cannot allocate FEC buffer prealloc pool";
+		return -ENOMEM;
+	}
+
+	f->extra_pool = mempool_create_slab_pool(0, f->cache);
+	if (!f->extra_pool) {
+		ti->error = "Cannot allocate FEC buffer extra pool";
+		return -ENOMEM;
+	}
+
+	/* Preallocate an output buffer for each thread */
+	f->output_pool = mempool_create_kmalloc_pool(num_online_cpus(),
+						     1 << v->data_dev_block_bits);
+	if (!f->output_pool) {
+		ti->error = "Cannot allocate FEC output pool";
+		return -ENOMEM;
+	}
+
+	/* Reserve space for our per-bio data */
+	ti->per_bio_data_size += sizeof(struct dm_verity_fec_io);
+
+	return 0;
+}
diff --git a/drivers/md/dm-verity-fec.h b/drivers/md/dm-verity-fec.h
new file mode 100644
index 0000000..7fa0298
--- /dev/null
+++ b/drivers/md/dm-verity-fec.h
@@ -0,0 +1,152 @@
+/*
+ * Copyright (C) 2015 Google, Inc.
+ *
+ * Author: Sami Tolvanen <samitolvanen@google.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#ifndef DM_VERITY_FEC_H
+#define DM_VERITY_FEC_H
+
+#include "dm-verity.h"
+#include <linux/rslib.h>
+
+/* Reed-Solomon(M, N) parameters */
+#define DM_VERITY_FEC_RSM		255
+#define DM_VERITY_FEC_MAX_RSN		253
+#define DM_VERITY_FEC_MIN_RSN		231	/* ~10% space overhead */
+
+/* buffers for deinterleaving and decoding */
+#define DM_VERITY_FEC_BUF_PREALLOC	1	/* buffers to preallocate */
+#define DM_VERITY_FEC_BUF_RS_BITS	4	/* 1 << RS blocks per buffer */
+/* we need buffers for at most 1 << block size RS blocks */
+#define DM_VERITY_FEC_BUF_MAX \
+	(1 << (PAGE_SHIFT - DM_VERITY_FEC_BUF_RS_BITS))
+
+#define DM_VERITY_OPT_FEC_DEV		"use_fec_from_device"
+#define DM_VERITY_OPT_FEC_BLOCKS	"fec_blocks"
+#define DM_VERITY_OPT_FEC_START		"fec_start"
+#define DM_VERITY_OPT_FEC_ROOTS		"fec_roots"
+
+/* configuration */
+struct dm_verity_fec {
+	struct dm_dev *dev;	/* parity data device */
+	struct dm_bufio_client *data_bufio;	/* for data dev access */
+	struct dm_bufio_client *bufio;		/* for parity data access */
+	sector_t start;		/* parity data start in blocks */
+	sector_t blocks;	/* number of blocks covered */
+	sector_t rounds;	/* number of interleaving rounds */
+	sector_t hash_blocks;	/* blocks covered after v->hash_start */
+	unsigned char roots;	/* number of parity bytes, M-N of RS(M, N) */
+	unsigned char rsn;	/* N of RS(M, N) */
+	mempool_t *rs_pool;	/* mempool for fio->rs */
+	mempool_t *prealloc_pool;	/* mempool for preallocated buffers */
+	mempool_t *extra_pool;	/* mempool for extra buffers */
+	mempool_t *output_pool;	/* mempool for output */
+	struct kmem_cache *cache;	/* cache for buffers */
+};
+
+/* per-bio data */
+struct dm_verity_fec_io {
+	struct rs_control *rs;	/* Reed-Solomon state */
+	int erasures[DM_VERITY_FEC_MAX_RSN];	/* erasures for decode_rs8 */
+	u8 *bufs[DM_VERITY_FEC_BUF_MAX];	/* bufs for deinterleaving */
+	unsigned nbufs;		/* number of buffers allocated */
+	u8 *output;		/* buffer for corrected output */
+	size_t output_pos;
+};
+
+#ifdef CONFIG_DM_VERITY_FEC
+
+/* each feature parameter requires a value */
+#define DM_VERITY_OPTS_FEC	8
+
+extern bool verity_fec_is_enabled(struct dm_verity *v);
+
+extern int verity_fec_decode(struct dm_verity *v, struct dm_verity_io *io,
+			     enum verity_block_type type, sector_t block,
+			     u8 *dest, struct bvec_iter *iter);
+
+extern unsigned verity_fec_status_table(struct dm_verity *v, unsigned sz,
+					char *result, unsigned maxlen);
+
+extern void verity_fec_finish_io(struct dm_verity_io *io);
+extern void verity_fec_init_io(struct dm_verity_io *io);
+
+extern bool verity_is_fec_opt_arg(const char *arg_name);
+extern int verity_fec_parse_opt_args(struct dm_arg_set *as,
+				     struct dm_verity *v, unsigned *argc,
+				     const char *arg_name);
+
+extern void verity_fec_dtr(struct dm_verity *v);
+
+extern int verity_fec_ctr_alloc(struct dm_verity *v);
+extern int verity_fec_ctr(struct dm_verity *v);
+
+#else /* !CONFIG_DM_VERITY_FEC */
+
+#define DM_VERITY_OPTS_FEC	0
+
+static inline bool verity_fec_is_enabled(struct dm_verity *v)
+{
+	return false;
+}
+
+static inline int verity_fec_decode(struct dm_verity *v,
+				    struct dm_verity_io *io,
+				    enum verity_block_type type,
+				    sector_t block, u8 *dest,
+				    struct bvec_iter *iter)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline unsigned verity_fec_status_table(struct dm_verity *v,
+					       unsigned sz, char *result,
+					       unsigned maxlen)
+{
+	return sz;
+}
+
+static inline void verity_fec_finish_io(struct dm_verity_io *io)
+{
+}
+
+static inline void verity_fec_init_io(struct dm_verity_io *io)
+{
+}
+
+static inline bool verity_is_fec_opt_arg(const char *arg_name)
+{
+	return false;
+}
+
+static inline int verity_fec_parse_opt_args(struct dm_arg_set *as,
+					    struct dm_verity *v,
+					    unsigned *argc,
+					    const char *arg_name)
+{
+	return -EINVAL;
+}
+
+static inline void verity_fec_dtr(struct dm_verity *v)
+{
+}
+
+static inline int verity_fec_ctr_alloc(struct dm_verity *v)
+{
+	return 0;
+}
+
+static inline int verity_fec_ctr(struct dm_verity *v)
+{
+	return 0;
+}
+
+#endif /* CONFIG_DM_VERITY_FEC */
+
+#endif /* DM_VERITY_FEC_H */
diff --git a/drivers/md/dm-verity.c b/drivers/md/dm-verity-target.c
similarity index 69%
rename from drivers/md/dm-verity.c
rename to drivers/md/dm-verity-target.c
index ccf4188..5c5d30c 100644
--- a/drivers/md/dm-verity.c
+++ b/drivers/md/dm-verity-target.c
@@ -14,12 +14,11 @@
  * access behavior.
  */
 
-#include "dm-bufio.h"
+#include "dm-verity.h"
+#include "dm-verity-fec.h"
 
 #include <linux/module.h>
-#include <linux/device-mapper.h>
 #include <linux/reboot.h>
-#include <crypto/hash.h>
 
 #define DM_MSG_PREFIX			"verity"
 
@@ -28,83 +27,18 @@
 
 #define DM_VERITY_DEFAULT_PREFETCH_SIZE	262144
 
-#define DM_VERITY_MAX_LEVELS		63
 #define DM_VERITY_MAX_CORRUPTED_ERRS	100
 
 #define DM_VERITY_OPT_LOGGING		"ignore_corruption"
 #define DM_VERITY_OPT_RESTART		"restart_on_corruption"
+#define DM_VERITY_OPT_IGN_ZEROES	"ignore_zero_blocks"
+
+#define DM_VERITY_OPTS_MAX		(2 + DM_VERITY_OPTS_FEC)
 
 static unsigned dm_verity_prefetch_cluster = DM_VERITY_DEFAULT_PREFETCH_SIZE;
 
 module_param_named(prefetch_cluster, dm_verity_prefetch_cluster, uint, S_IRUGO | S_IWUSR);
 
-enum verity_mode {
-	DM_VERITY_MODE_EIO,
-	DM_VERITY_MODE_LOGGING,
-	DM_VERITY_MODE_RESTART
-};
-
-enum verity_block_type {
-	DM_VERITY_BLOCK_TYPE_DATA,
-	DM_VERITY_BLOCK_TYPE_METADATA
-};
-
-struct dm_verity {
-	struct dm_dev *data_dev;
-	struct dm_dev *hash_dev;
-	struct dm_target *ti;
-	struct dm_bufio_client *bufio;
-	char *alg_name;
-	struct crypto_shash *tfm;
-	u8 *root_digest;	/* digest of the root block */
-	u8 *salt;		/* salt: its size is salt_size */
-	unsigned salt_size;
-	sector_t data_start;	/* data offset in 512-byte sectors */
-	sector_t hash_start;	/* hash start in blocks */
-	sector_t data_blocks;	/* the number of data blocks */
-	sector_t hash_blocks;	/* the number of hash blocks */
-	unsigned char data_dev_block_bits;	/* log2(data blocksize) */
-	unsigned char hash_dev_block_bits;	/* log2(hash blocksize) */
-	unsigned char hash_per_block_bits;	/* log2(hashes in hash block) */
-	unsigned char levels;	/* the number of tree levels */
-	unsigned char version;
-	unsigned digest_size;	/* digest size for the current hash algorithm */
-	unsigned shash_descsize;/* the size of temporary space for crypto */
-	int hash_failed;	/* set to 1 if hash of any block failed */
-	enum verity_mode mode;	/* mode for handling verification errors */
-	unsigned corrupted_errs;/* Number of errors for corrupted blocks */
-
-	struct workqueue_struct *verify_wq;
-
-	/* starting blocks for each tree level. 0 is the lowest level. */
-	sector_t hash_level_block[DM_VERITY_MAX_LEVELS];
-};
-
-struct dm_verity_io {
-	struct dm_verity *v;
-
-	/* original values of bio->bi_end_io and bio->bi_private */
-	bio_end_io_t *orig_bi_end_io;
-	void *orig_bi_private;
-
-	sector_t block;
-	unsigned n_blocks;
-
-	struct bvec_iter iter;
-
-	struct work_struct work;
-
-	/*
-	 * Three variably-size fields follow this struct:
-	 *
-	 * u8 hash_desc[v->shash_descsize];
-	 * u8 real_digest[v->digest_size];
-	 * u8 want_digest[v->digest_size];
-	 *
-	 * To access them use: io_hash_desc(), io_real_digest() and io_want_digest().
-	 */
-};
-
 struct dm_verity_prefetch_work {
 	struct work_struct work;
 	struct dm_verity *v;
@@ -112,21 +46,6 @@
 	unsigned n_blocks;
 };
 
-static struct shash_desc *io_hash_desc(struct dm_verity *v, struct dm_verity_io *io)
-{
-	return (struct shash_desc *)(io + 1);
-}
-
-static u8 *io_real_digest(struct dm_verity *v, struct dm_verity_io *io)
-{
-	return (u8 *)(io + 1) + v->shash_descsize;
-}
-
-static u8 *io_want_digest(struct dm_verity *v, struct dm_verity_io *io)
-{
-	return (u8 *)(io + 1) + v->shash_descsize + v->digest_size;
-}
-
 /*
  * Auxiliary structure appended to each dm-bufio buffer. If the value
  * hash_verified is nonzero, hash of the block has been verified.
@@ -173,6 +92,84 @@
 	return block >> (level * v->hash_per_block_bits);
 }
 
+/*
+ * Wrapper for crypto_shash_init, which handles verity salting.
+ */
+static int verity_hash_init(struct dm_verity *v, struct shash_desc *desc)
+{
+	int r;
+
+	desc->tfm = v->tfm;
+	desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+
+	r = crypto_shash_init(desc);
+
+	if (unlikely(r < 0)) {
+		DMERR("crypto_shash_init failed: %d", r);
+		return r;
+	}
+
+	if (likely(v->version >= 1)) {
+		r = crypto_shash_update(desc, v->salt, v->salt_size);
+
+		if (unlikely(r < 0)) {
+			DMERR("crypto_shash_update failed: %d", r);
+			return r;
+		}
+	}
+
+	return 0;
+}
+
+static int verity_hash_update(struct dm_verity *v, struct shash_desc *desc,
+			      const u8 *data, size_t len)
+{
+	int r = crypto_shash_update(desc, data, len);
+
+	if (unlikely(r < 0))
+		DMERR("crypto_shash_update failed: %d", r);
+
+	return r;
+}
+
+static int verity_hash_final(struct dm_verity *v, struct shash_desc *desc,
+			     u8 *digest)
+{
+	int r;
+
+	if (unlikely(!v->version)) {
+		r = crypto_shash_update(desc, v->salt, v->salt_size);
+
+		if (r < 0) {
+			DMERR("crypto_shash_update failed: %d", r);
+			return r;
+		}
+	}
+
+	r = crypto_shash_final(desc, digest);
+
+	if (unlikely(r < 0))
+		DMERR("crypto_shash_final failed: %d", r);
+
+	return r;
+}
+
+int verity_hash(struct dm_verity *v, struct shash_desc *desc,
+		const u8 *data, size_t len, u8 *digest)
+{
+	int r;
+
+	r = verity_hash_init(v, desc);
+	if (unlikely(r < 0))
+		return r;
+
+	r = verity_hash_update(v, desc, data, len);
+	if (unlikely(r < 0))
+		return r;
+
+	return verity_hash_final(v, desc, digest);
+}
+
 static void verity_hash_at_level(struct dm_verity *v, sector_t block, int level,
 				 sector_t *hash_block, unsigned *offset)
 {
@@ -246,17 +243,17 @@
  * Verify hash of a metadata block pertaining to the specified data block
  * ("block" argument) at a specified level ("level" argument).
  *
- * On successful return, io_want_digest(v, io) contains the hash value for
- * a lower tree level or for the data block (if we're at the lowest leve).
+ * On successful return, verity_io_want_digest(v, io) contains the hash value
+ * for a lower tree level or for the data block (if we're at the lowest level).
  *
  * If "skip_unverified" is true, unverified buffer is skipped and 1 is returned.
  * If "skip_unverified" is false, unverified buffer is hashed and verified
- * against current value of io_want_digest(v, io).
+ * against current value of verity_io_want_digest(v, io).
  */
-static int verity_verify_level(struct dm_verity_io *io, sector_t block,
-			       int level, bool skip_unverified)
+static int verity_verify_level(struct dm_verity *v, struct dm_verity_io *io,
+			       sector_t block, int level, bool skip_unverified,
+			       u8 *want_digest)
 {
-	struct dm_verity *v = io->v;
 	struct dm_buffer *buf;
 	struct buffer_aux *aux;
 	u8 *data;
@@ -273,172 +270,185 @@
 	aux = dm_bufio_get_aux_data(buf);
 
 	if (!aux->hash_verified) {
-		struct shash_desc *desc;
-		u8 *result;
-
 		if (skip_unverified) {
 			r = 1;
 			goto release_ret_r;
 		}
 
-		desc = io_hash_desc(v, io);
-		desc->tfm = v->tfm;
-		desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
-		r = crypto_shash_init(desc);
-		if (r < 0) {
-			DMERR("crypto_shash_init failed: %d", r);
+		r = verity_hash(v, verity_io_hash_desc(v, io),
+				data, 1 << v->hash_dev_block_bits,
+				verity_io_real_digest(v, io));
+		if (unlikely(r < 0))
 			goto release_ret_r;
-		}
 
-		if (likely(v->version >= 1)) {
-			r = crypto_shash_update(desc, v->salt, v->salt_size);
-			if (r < 0) {
-				DMERR("crypto_shash_update failed: %d", r);
-				goto release_ret_r;
-			}
-		}
-
-		r = crypto_shash_update(desc, data, 1 << v->hash_dev_block_bits);
-		if (r < 0) {
-			DMERR("crypto_shash_update failed: %d", r);
-			goto release_ret_r;
-		}
-
-		if (!v->version) {
-			r = crypto_shash_update(desc, v->salt, v->salt_size);
-			if (r < 0) {
-				DMERR("crypto_shash_update failed: %d", r);
-				goto release_ret_r;
-			}
-		}
-
-		result = io_real_digest(v, io);
-		r = crypto_shash_final(desc, result);
-		if (r < 0) {
-			DMERR("crypto_shash_final failed: %d", r);
-			goto release_ret_r;
-		}
-		if (unlikely(memcmp(result, io_want_digest(v, io), v->digest_size))) {
-			if (verity_handle_err(v, DM_VERITY_BLOCK_TYPE_METADATA,
-					      hash_block)) {
-				r = -EIO;
-				goto release_ret_r;
-			}
-		} else
+		if (likely(memcmp(verity_io_real_digest(v, io), want_digest,
+				  v->digest_size) == 0))
 			aux->hash_verified = 1;
+		else if (verity_fec_decode(v, io,
+					   DM_VERITY_BLOCK_TYPE_METADATA,
+					   hash_block, data, NULL) == 0)
+			aux->hash_verified = 1;
+		else if (verity_handle_err(v,
+					   DM_VERITY_BLOCK_TYPE_METADATA,
+					   hash_block)) {
+			r = -EIO;
+			goto release_ret_r;
+		}
 	}
 
 	data += offset;
-
-	memcpy(io_want_digest(v, io), data, v->digest_size);
-
-	dm_bufio_release(buf);
-	return 0;
+	memcpy(want_digest, data, v->digest_size);
+	r = 0;
 
 release_ret_r:
 	dm_bufio_release(buf);
+	return r;
+}
+
+/*
+ * Find a hash for a given block, write it to digest and verify the integrity
+ * of the hash tree if necessary.
+ */
+int verity_hash_for_block(struct dm_verity *v, struct dm_verity_io *io,
+			  sector_t block, u8 *digest, bool *is_zero)
+{
+	int r = 0, i;
+
+	if (likely(v->levels)) {
+		/*
+		 * First, we try to get the requested hash for
+		 * the current block. If the hash block itself is
+		 * verified, zero is returned. If it isn't, this
+		 * function returns 1 and we fall back to whole
+		 * chain verification.
+		 */
+		r = verity_verify_level(v, io, block, 0, true, digest);
+		if (likely(r <= 0))
+			goto out;
+	}
+
+	memcpy(digest, v->root_digest, v->digest_size);
+
+	for (i = v->levels - 1; i >= 0; i--) {
+		r = verity_verify_level(v, io, block, i, false, digest);
+		if (unlikely(r))
+			goto out;
+	}
+out:
+	if (!r && v->zero_digest)
+		*is_zero = !memcmp(v->zero_digest, digest, v->digest_size);
+	else
+		*is_zero = false;
 
 	return r;
 }
 
 /*
+ * Calls function process for 1 << v->data_dev_block_bits bytes in the bio_vec
+ * starting from iter.
+ */
+int verity_for_bv_block(struct dm_verity *v, struct dm_verity_io *io,
+			struct bvec_iter *iter,
+			int (*process)(struct dm_verity *v,
+				       struct dm_verity_io *io, u8 *data,
+				       size_t len))
+{
+	unsigned todo = 1 << v->data_dev_block_bits;
+	struct bio *bio = dm_bio_from_per_bio_data(io, v->ti->per_bio_data_size);
+
+	do {
+		int r;
+		u8 *page;
+		unsigned len;
+		struct bio_vec bv = bio_iter_iovec(bio, *iter);
+
+		page = kmap_atomic(bv.bv_page);
+		len = bv.bv_len;
+
+		if (likely(len >= todo))
+			len = todo;
+
+		r = process(v, io, page + bv.bv_offset, len);
+		kunmap_atomic(page);
+
+		if (r < 0)
+			return r;
+
+		bio_advance_iter(bio, iter, len);
+		todo -= len;
+	} while (todo);
+
+	return 0;
+}
+
+static int verity_bv_hash_update(struct dm_verity *v, struct dm_verity_io *io,
+				 u8 *data, size_t len)
+{
+	return verity_hash_update(v, verity_io_hash_desc(v, io), data, len);
+}
+
+static int verity_bv_zero(struct dm_verity *v, struct dm_verity_io *io,
+			  u8 *data, size_t len)
+{
+	memset(data, 0, len);
+	return 0;
+}
+
+/*
  * Verify one "dm_verity_io" structure.
  */
 static int verity_verify_io(struct dm_verity_io *io)
 {
+	bool is_zero;
 	struct dm_verity *v = io->v;
-	struct bio *bio = dm_bio_from_per_bio_data(io,
-						   v->ti->per_bio_data_size);
+	struct bvec_iter start;
 	unsigned b;
-	int i;
 
 	for (b = 0; b < io->n_blocks; b++) {
-		struct shash_desc *desc;
-		u8 *result;
 		int r;
-		unsigned todo;
+		struct shash_desc *desc = verity_io_hash_desc(v, io);
 
-		if (likely(v->levels)) {
+		r = verity_hash_for_block(v, io, io->block + b,
+					  verity_io_want_digest(v, io),
+					  &is_zero);
+		if (unlikely(r < 0))
+			return r;
+
+		if (is_zero) {
 			/*
-			 * First, we try to get the requested hash for
-			 * the current block. If the hash block itself is
-			 * verified, zero is returned. If it isn't, this
-			 * function returns 0 and we fall back to whole
-			 * chain verification.
+			 * If we expect a zero block, don't validate, just
+			 * return zeros.
 			 */
-			int r = verity_verify_level(io, io->block + b, 0, true);
-			if (likely(!r))
-				goto test_block_hash;
-			if (r < 0)
+			r = verity_for_bv_block(v, io, &io->iter,
+						verity_bv_zero);
+			if (unlikely(r < 0))
 				return r;
+
+			continue;
 		}
 
-		memcpy(io_want_digest(v, io), v->root_digest, v->digest_size);
-
-		for (i = v->levels - 1; i >= 0; i--) {
-			int r = verity_verify_level(io, io->block + b, i, false);
-			if (unlikely(r))
-				return r;
-		}
-
-test_block_hash:
-		desc = io_hash_desc(v, io);
-		desc->tfm = v->tfm;
-		desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
-		r = crypto_shash_init(desc);
-		if (r < 0) {
-			DMERR("crypto_shash_init failed: %d", r);
+		r = verity_hash_init(v, desc);
+		if (unlikely(r < 0))
 			return r;
-		}
 
-		if (likely(v->version >= 1)) {
-			r = crypto_shash_update(desc, v->salt, v->salt_size);
-			if (r < 0) {
-				DMERR("crypto_shash_update failed: %d", r);
-				return r;
-			}
-		}
-		todo = 1 << v->data_dev_block_bits;
-		do {
-			u8 *page;
-			unsigned len;
-			struct bio_vec bv = bio_iter_iovec(bio, io->iter);
-
-			page = kmap_atomic(bv.bv_page);
-			len = bv.bv_len;
-			if (likely(len >= todo))
-				len = todo;
-			r = crypto_shash_update(desc, page + bv.bv_offset, len);
-			kunmap_atomic(page);
-
-			if (r < 0) {
-				DMERR("crypto_shash_update failed: %d", r);
-				return r;
-			}
-
-			bio_advance_iter(bio, &io->iter, len);
-			todo -= len;
-		} while (todo);
-
-		if (!v->version) {
-			r = crypto_shash_update(desc, v->salt, v->salt_size);
-			if (r < 0) {
-				DMERR("crypto_shash_update failed: %d", r);
-				return r;
-			}
-		}
-
-		result = io_real_digest(v, io);
-		r = crypto_shash_final(desc, result);
-		if (r < 0) {
-			DMERR("crypto_shash_final failed: %d", r);
+		start = io->iter;
+		r = verity_for_bv_block(v, io, &io->iter, verity_bv_hash_update);
+		if (unlikely(r < 0))
 			return r;
-		}
-		if (unlikely(memcmp(result, io_want_digest(v, io), v->digest_size))) {
-			if (verity_handle_err(v, DM_VERITY_BLOCK_TYPE_DATA,
-					      io->block + b))
-				return -EIO;
-		}
+
+		r = verity_hash_final(v, desc, verity_io_real_digest(v, io));
+		if (unlikely(r < 0))
+			return r;
+
+		if (likely(memcmp(verity_io_real_digest(v, io),
+				  verity_io_want_digest(v, io), v->digest_size) == 0))
+			continue;
+		else if (verity_fec_decode(v, io, DM_VERITY_BLOCK_TYPE_DATA,
+					   io->block + b, NULL, &start) == 0)
+			continue;
+		else if (verity_handle_err(v, DM_VERITY_BLOCK_TYPE_DATA,
+					   io->block + b))
+			return -EIO;
 	}
 
 	return 0;
@@ -453,9 +463,10 @@
 	struct bio *bio = dm_bio_from_per_bio_data(io, v->ti->per_bio_data_size);
 
 	bio->bi_end_io = io->orig_bi_end_io;
-	bio->bi_private = io->orig_bi_private;
 	bio->bi_error = error;
 
+	verity_fec_finish_io(io);
+
 	bio_endio(bio);
 }
 
@@ -470,7 +481,7 @@
 {
 	struct dm_verity_io *io = bio->bi_private;
 
-	if (bio->bi_error) {
+	if (bio->bi_error && !verity_fec_is_enabled(io->v)) {
 		verity_finish_io(io, bio->bi_error);
 		return;
 	}
@@ -566,7 +577,6 @@
 	io = dm_per_bio_data(bio, ti->per_bio_data_size);
 	io->v = v;
 	io->orig_bi_end_io = bio->bi_end_io;
-	io->orig_bi_private = bio->bi_private;
 	io->block = bio->bi_iter.bi_sector >> (v->data_dev_block_bits - SECTOR_SHIFT);
 	io->n_blocks = bio->bi_iter.bi_size >> v->data_dev_block_bits;
 
@@ -574,6 +584,8 @@
 	bio->bi_private = io;
 	io->iter = bio->bi_iter;
 
+	verity_fec_init_io(io);
+
 	verity_submit_prefetch(v, io);
 
 	generic_make_request(bio);
@@ -588,6 +600,7 @@
 			  unsigned status_flags, char *result, unsigned maxlen)
 {
 	struct dm_verity *v = ti->private;
+	unsigned args = 0;
 	unsigned sz = 0;
 	unsigned x;
 
@@ -614,8 +627,17 @@
 		else
 			for (x = 0; x < v->salt_size; x++)
 				DMEMIT("%02x", v->salt[x]);
+		if (v->mode != DM_VERITY_MODE_EIO)
+			args++;
+		if (verity_fec_is_enabled(v))
+			args += DM_VERITY_OPTS_FEC;
+		if (v->zero_digest)
+			args++;
+		if (!args)
+			return;
+		DMEMIT(" %u", args);
 		if (v->mode != DM_VERITY_MODE_EIO) {
-			DMEMIT(" 1 ");
+			DMEMIT(" ");
 			switch (v->mode) {
 			case DM_VERITY_MODE_LOGGING:
 				DMEMIT(DM_VERITY_OPT_LOGGING);
@@ -627,6 +649,9 @@
 				BUG();
 			}
 		}
+		if (v->zero_digest)
+			DMEMIT(" " DM_VERITY_OPT_IGN_ZEROES);
+		sz = verity_fec_status_table(v, sz, result, maxlen);
 		break;
 	}
 }
@@ -677,6 +702,7 @@
 
 	kfree(v->salt);
 	kfree(v->root_digest);
+	kfree(v->zero_digest);
 
 	if (v->tfm)
 		crypto_free_shash(v->tfm);
@@ -689,9 +715,94 @@
 	if (v->data_dev)
 		dm_put_device(ti, v->data_dev);
 
+	verity_fec_dtr(v);
+
 	kfree(v);
 }
 
+static int verity_alloc_zero_digest(struct dm_verity *v)
+{
+	int r = -ENOMEM;
+	struct shash_desc *desc;
+	u8 *zero_data;
+
+	v->zero_digest = kmalloc(v->digest_size, GFP_KERNEL);
+
+	if (!v->zero_digest)
+		return r;
+
+	desc = kmalloc(v->shash_descsize, GFP_KERNEL);
+
+	if (!desc)
+		return r; /* verity_dtr will free zero_digest */
+
+	zero_data = kzalloc(1 << v->data_dev_block_bits, GFP_KERNEL);
+
+	if (!zero_data)
+		goto out;
+
+	r = verity_hash(v, desc, zero_data, 1 << v->data_dev_block_bits,
+			v->zero_digest);
+
+out:
+	kfree(desc);
+	kfree(zero_data);
+
+	return r;
+}
+
+static int verity_parse_opt_args(struct dm_arg_set *as, struct dm_verity *v)
+{
+	int r;
+	unsigned argc;
+	struct dm_target *ti = v->ti;
+	const char *arg_name;
+
+	static struct dm_arg _args[] = {
+		{0, DM_VERITY_OPTS_MAX, "Invalid number of feature args"},
+	};
+
+	r = dm_read_arg_group(_args, as, &argc, &ti->error);
+	if (r)
+		return -EINVAL;
+
+	if (!argc)
+		return 0;
+
+	do {
+		arg_name = dm_shift_arg(as);
+		argc--;
+
+		if (!strcasecmp(arg_name, DM_VERITY_OPT_LOGGING)) {
+			v->mode = DM_VERITY_MODE_LOGGING;
+			continue;
+
+		} else if (!strcasecmp(arg_name, DM_VERITY_OPT_RESTART)) {
+			v->mode = DM_VERITY_MODE_RESTART;
+			continue;
+
+		} else if (!strcasecmp(arg_name, DM_VERITY_OPT_IGN_ZEROES)) {
+			r = verity_alloc_zero_digest(v);
+			if (r) {
+				ti->error = "Cannot allocate zero digest";
+				return r;
+			}
+			continue;
+
+		} else if (verity_is_fec_opt_arg(arg_name)) {
+			r = verity_fec_parse_opt_args(as, v, &argc, arg_name);
+			if (r)
+				return r;
+			continue;
+		}
+
+		ti->error = "Unrecognized verity feature request";
+		return -EINVAL;
+	} while (argc && !r);
+
+	return r;
+}
+
 /*
  * Target parameters:
  *	<version>	The current format is version 1.
@@ -710,18 +821,13 @@
 {
 	struct dm_verity *v;
 	struct dm_arg_set as;
-	const char *opt_string;
-	unsigned int num, opt_params;
+	unsigned int num;
 	unsigned long long num_ll;
 	int r;
 	int i;
 	sector_t hash_position;
 	char dummy;
 
-	static struct dm_arg _args[] = {
-		{0, 1, "Invalid number of feature args"},
-	};
-
 	v = kzalloc(sizeof(struct dm_verity), GFP_KERNEL);
 	if (!v) {
 		ti->error = "Cannot allocate verity structure";
@@ -730,6 +836,10 @@
 	ti->private = v;
 	v->ti = ti;
 
+	r = verity_fec_ctr_alloc(v);
+	if (r)
+		goto bad;
+
 	if ((dm_table_get_mode(ti->table) & ~FMODE_READ)) {
 		ti->error = "Device must be readonly";
 		r = -EINVAL;
@@ -866,29 +976,9 @@
 		as.argc = argc;
 		as.argv = argv;
 
-		r = dm_read_arg_group(_args, &as, &opt_params, &ti->error);
-		if (r)
+		r = verity_parse_opt_args(&as, v);
+		if (r < 0)
 			goto bad;
-
-		while (opt_params) {
-			opt_params--;
-			opt_string = dm_shift_arg(&as);
-			if (!opt_string) {
-				ti->error = "Not enough feature arguments";
-				r = -EINVAL;
-				goto bad;
-			}
-
-			if (!strcasecmp(opt_string, DM_VERITY_OPT_LOGGING))
-				v->mode = DM_VERITY_MODE_LOGGING;
-			else if (!strcasecmp(opt_string, DM_VERITY_OPT_RESTART))
-				v->mode = DM_VERITY_MODE_RESTART;
-			else {
-				ti->error = "Invalid feature arguments";
-				r = -EINVAL;
-				goto bad;
-			}
-		}
 	}
 
 	v->hash_per_block_bits =
@@ -938,8 +1028,6 @@
 		goto bad;
 	}
 
-	ti->per_bio_data_size = roundup(sizeof(struct dm_verity_io) + v->shash_descsize + v->digest_size * 2, __alignof__(struct dm_verity_io));
-
 	/* WQ_UNBOUND greatly improves performance when running on ramdisk */
 	v->verify_wq = alloc_workqueue("kverityd", WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM | WQ_UNBOUND, num_online_cpus());
 	if (!v->verify_wq) {
@@ -948,6 +1036,16 @@
 		goto bad;
 	}
 
+	ti->per_bio_data_size = sizeof(struct dm_verity_io) +
+				v->shash_descsize + v->digest_size * 2;
+
+	r = verity_fec_ctr(v);
+	if (r)
+		goto bad;
+
+	ti->per_bio_data_size = roundup(ti->per_bio_data_size,
+					__alignof__(struct dm_verity_io));
+
 	return 0;
 
 bad:
@@ -958,7 +1056,7 @@
 
 static struct target_type verity_target = {
 	.name		= "verity",
-	.version	= {1, 2, 0},
+	.version	= {1, 3, 0},
 	.module		= THIS_MODULE,
 	.ctr		= verity_ctr,
 	.dtr		= verity_dtr,
diff --git a/drivers/md/dm-verity.h b/drivers/md/dm-verity.h
new file mode 100644
index 0000000..fb419f4
--- /dev/null
+++ b/drivers/md/dm-verity.h
@@ -0,0 +1,129 @@
+/*
+ * Copyright (C) 2012 Red Hat, Inc.
+ * Copyright (C) 2015 Google, Inc.
+ *
+ * Author: Mikulas Patocka <mpatocka@redhat.com>
+ *
+ * Based on Chromium dm-verity driver (C) 2011 The Chromium OS Authors
+ *
+ * This file is released under the GPLv2.
+ */
+
+#ifndef DM_VERITY_H
+#define DM_VERITY_H
+
+#include "dm-bufio.h"
+#include <linux/device-mapper.h>
+#include <crypto/hash.h>
+
+#define DM_VERITY_MAX_LEVELS		63
+
+enum verity_mode {
+	DM_VERITY_MODE_EIO,
+	DM_VERITY_MODE_LOGGING,
+	DM_VERITY_MODE_RESTART
+};
+
+enum verity_block_type {
+	DM_VERITY_BLOCK_TYPE_DATA,
+	DM_VERITY_BLOCK_TYPE_METADATA
+};
+
+struct dm_verity_fec;
+
+struct dm_verity {
+	struct dm_dev *data_dev;
+	struct dm_dev *hash_dev;
+	struct dm_target *ti;
+	struct dm_bufio_client *bufio;
+	char *alg_name;
+	struct crypto_shash *tfm;
+	u8 *root_digest;	/* digest of the root block */
+	u8 *salt;		/* salt: its size is salt_size */
+	u8 *zero_digest;	/* digest for a zero block */
+	unsigned salt_size;
+	sector_t data_start;	/* data offset in 512-byte sectors */
+	sector_t hash_start;	/* hash start in blocks */
+	sector_t data_blocks;	/* the number of data blocks */
+	sector_t hash_blocks;	/* the number of hash blocks */
+	unsigned char data_dev_block_bits;	/* log2(data blocksize) */
+	unsigned char hash_dev_block_bits;	/* log2(hash blocksize) */
+	unsigned char hash_per_block_bits;	/* log2(hashes in hash block) */
+	unsigned char levels;	/* the number of tree levels */
+	unsigned char version;
+	unsigned digest_size;	/* digest size for the current hash algorithm */
+	unsigned shash_descsize;/* the size of temporary space for crypto */
+	int hash_failed;	/* set to 1 if hash of any block failed */
+	enum verity_mode mode;	/* mode for handling verification errors */
+	unsigned corrupted_errs;/* Number of errors for corrupted blocks */
+
+	struct workqueue_struct *verify_wq;
+
+	/* starting blocks for each tree level. 0 is the lowest level. */
+	sector_t hash_level_block[DM_VERITY_MAX_LEVELS];
+
+	struct dm_verity_fec *fec;	/* forward error correction */
+};
+
+struct dm_verity_io {
+	struct dm_verity *v;
+
+	/* original value of bio->bi_end_io */
+	bio_end_io_t *orig_bi_end_io;
+
+	sector_t block;
+	unsigned n_blocks;
+
+	struct bvec_iter iter;
+
+	struct work_struct work;
+
+	/*
+	 * Three variably-size fields follow this struct:
+	 *
+	 * u8 hash_desc[v->shash_descsize];
+	 * u8 real_digest[v->digest_size];
+	 * u8 want_digest[v->digest_size];
+	 *
+	 * To access them use: verity_io_hash_desc(), verity_io_real_digest()
+	 * and verity_io_want_digest().
+	 */
+};
+
+static inline struct shash_desc *verity_io_hash_desc(struct dm_verity *v,
+						     struct dm_verity_io *io)
+{
+	return (struct shash_desc *)(io + 1);
+}
+
+static inline u8 *verity_io_real_digest(struct dm_verity *v,
+					struct dm_verity_io *io)
+{
+	return (u8 *)(io + 1) + v->shash_descsize;
+}
+
+static inline u8 *verity_io_want_digest(struct dm_verity *v,
+					struct dm_verity_io *io)
+{
+	return (u8 *)(io + 1) + v->shash_descsize + v->digest_size;
+}
+
+static inline u8 *verity_io_digest_end(struct dm_verity *v,
+				       struct dm_verity_io *io)
+{
+	return verity_io_want_digest(v, io) + v->digest_size;
+}
+
+extern int verity_for_bv_block(struct dm_verity *v, struct dm_verity_io *io,
+			       struct bvec_iter *iter,
+			       int (*process)(struct dm_verity *v,
+					      struct dm_verity_io *io,
+					      u8 *data, size_t len));
+
+extern int verity_hash(struct dm_verity *v, struct shash_desc *desc,
+		       const u8 *data, size_t len, u8 *digest);
+
+extern int verity_hash_for_block(struct dm_verity *v, struct dm_verity_io *io,
+				 sector_t block, u8 *digest, bool *is_zero);
+
+#endif /* DM_VERITY_H */
diff --git a/drivers/md/persistent-data/Kconfig b/drivers/md/persistent-data/Kconfig
index 78c74bb..a53cbc9 100644
--- a/drivers/md/persistent-data/Kconfig
+++ b/drivers/md/persistent-data/Kconfig
@@ -7,12 +7,3 @@
 	 Library providing immutable on-disk data structure support for
 	 device-mapper targets such as the thin provisioning target.
 
-config DM_DEBUG_BLOCK_STACK_TRACING
-       bool "Keep stack trace of persistent data block lock holders"
-       depends on STACKTRACE_SUPPORT && DM_PERSISTENT_DATA
-       select STACKTRACE
-       ---help---
-	 Enable this for messages that may help debug problems with the
-	 block manager locking used by thin provisioning and caching.
-
-	 If unsure, say N.
diff --git a/drivers/md/persistent-data/dm-block-manager.c b/drivers/md/persistent-data/dm-block-manager.c
index f2393ba..1e33dd5 100644
--- a/drivers/md/persistent-data/dm-block-manager.c
+++ b/drivers/md/persistent-data/dm-block-manager.c
@@ -97,10 +97,6 @@
 static int __check_holder(struct block_lock *lock)
 {
 	unsigned i;
-#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
-	static struct stack_trace t;
-	static stack_entries entries;
-#endif
 
 	for (i = 0; i < MAX_HOLDERS; i++) {
 		if (lock->holders[i] == current) {
@@ -110,12 +106,7 @@
 			print_stack_trace(lock->traces + i, 4);
 
 			DMERR("subsequent acquisition attempted here:");
-			t.nr_entries = 0;
-			t.max_entries = MAX_STACK;
-			t.entries = entries;
-			t.skip = 3;
-			save_stack_trace(&t);
-			print_stack_trace(&t, 4);
+			dump_stack();
 #endif
 			return -EINVAL;
 		}
diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c
index b1ced58..ea3d3b6 100644
--- a/drivers/md/persistent-data/dm-btree.c
+++ b/drivers/md/persistent-data/dm-btree.c
@@ -754,12 +754,19 @@
 	return 0;
 }
 
+static bool need_insert(struct btree_node *node, uint64_t *keys,
+			unsigned level, unsigned index)
+{
+        return ((index >= le32_to_cpu(node->header.nr_entries)) ||
+		(le64_to_cpu(node->keys[index]) != keys[level]));
+}
+
 static int insert(struct dm_btree_info *info, dm_block_t root,
 		  uint64_t *keys, void *value, dm_block_t *new_root,
 		  int *inserted)
 		  __dm_written_to_disk(value)
 {
-	int r, need_insert;
+	int r;
 	unsigned level, index = -1, last_level = info->levels - 1;
 	dm_block_t block = root;
 	struct shadow_spine spine;
@@ -775,10 +782,8 @@
 			goto bad;
 
 		n = dm_block_data(shadow_current(&spine));
-		need_insert = ((index >= le32_to_cpu(n->header.nr_entries)) ||
-			       (le64_to_cpu(n->keys[index]) != keys[level]));
 
-		if (need_insert) {
+		if (need_insert(n, keys, level, index)) {
 			dm_block_t new_tree;
 			__le64 new_le;
 
@@ -805,10 +810,8 @@
 		goto bad;
 
 	n = dm_block_data(shadow_current(&spine));
-	need_insert = ((index >= le32_to_cpu(n->header.nr_entries)) ||
-		       (le64_to_cpu(n->keys[index]) != keys[level]));
 
-	if (need_insert) {
+	if (need_insert(n, keys, level, index)) {
 		if (inserted)
 			*inserted = 1;
 
diff --git a/drivers/md/persistent-data/dm-space-map-metadata.c b/drivers/md/persistent-data/dm-space-map-metadata.c
index fca6dbc..7e44005 100644
--- a/drivers/md/persistent-data/dm-space-map-metadata.c
+++ b/drivers/md/persistent-data/dm-space-map-metadata.c
@@ -152,12 +152,9 @@
 
 static int brb_pop(struct bop_ring_buffer *brb)
 {
-	struct block_op *bop;
-
 	if (brb_empty(brb))
 		return -ENODATA;
 
-	bop = brb->bops + brb->begin;
 	brb->begin = brb_next(brb, brb->begin);
 
 	return 0;
diff --git a/drivers/media/Kconfig b/drivers/media/Kconfig
index 3ef3d6c..9264ea7 100644
--- a/drivers/media/Kconfig
+++ b/drivers/media/Kconfig
@@ -9,7 +9,7 @@
 	  If you want to use Webcams, Video grabber devices and/or TV devices
 	  enable this option and other options below.
 	  Additional info and docs are available on the web at
-	  <http://linuxtv.org>
+	  <https://linuxtv.org>
 
 if MEDIA_SUPPORT
 
@@ -51,7 +51,7 @@
 	  Enable AM/FM radio support.
 
 	  Additional info and docs are available on the web at
-	  <http://linuxtv.org>
+	  <https://linuxtv.org>
 
 	  Say Y when you have a board with radio support.
 
diff --git a/drivers/media/common/cx2341x.c b/drivers/media/common/cx2341x.c
index c07b9db..5e4afa0 100644
--- a/drivers/media/common/cx2341x.c
+++ b/drivers/media/common/cx2341x.c
@@ -27,7 +27,7 @@
 #include <linux/videodev2.h>
 
 #include <media/tuner.h>
-#include <media/cx2341x.h>
+#include <media/drv-intf/cx2341x.h>
 #include <media/v4l2-common.h>
 
 MODULE_DESCRIPTION("cx23415/6/8 driver");
diff --git a/drivers/media/common/saa7146/saa7146_core.c b/drivers/media/common/saa7146/saa7146_core.c
index 1ff9f53..9f7c5b0 100644
--- a/drivers/media/common/saa7146/saa7146_core.c
+++ b/drivers/media/common/saa7146/saa7146_core.c
@@ -20,7 +20,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#include <media/saa7146.h>
+#include <media/drv-intf/saa7146.h>
 #include <linux/module.h>
 
 static int saa7146_num;
diff --git a/drivers/media/common/saa7146/saa7146_fops.c b/drivers/media/common/saa7146/saa7146_fops.c
index df1e8c9..930d2c9 100644
--- a/drivers/media/common/saa7146/saa7146_fops.c
+++ b/drivers/media/common/saa7146/saa7146_fops.c
@@ -1,6 +1,6 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#include <media/saa7146_vv.h>
+#include <media/drv-intf/saa7146_vv.h>
 #include <linux/module.h>
 
 /****************************************************************************/
diff --git a/drivers/media/common/saa7146/saa7146_hlp.c b/drivers/media/common/saa7146/saa7146_hlp.c
index 3dc6a83..6ebcbc6 100644
--- a/drivers/media/common/saa7146/saa7146_hlp.c
+++ b/drivers/media/common/saa7146/saa7146_hlp.c
@@ -2,7 +2,7 @@
 
 #include <linux/kernel.h>
 #include <linux/export.h>
-#include <media/saa7146_vv.h>
+#include <media/drv-intf/saa7146_vv.h>
 
 static void calculate_output_format_register(struct saa7146_dev* saa, u32 palette, u32* clip_format)
 {
diff --git a/drivers/media/common/saa7146/saa7146_i2c.c b/drivers/media/common/saa7146/saa7146_i2c.c
index 2202719..239a2db 100644
--- a/drivers/media/common/saa7146/saa7146_i2c.c
+++ b/drivers/media/common/saa7146/saa7146_i2c.c
@@ -1,6 +1,6 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#include <media/saa7146_vv.h>
+#include <media/drv-intf/saa7146_vv.h>
 
 static u32 saa7146_i2c_func(struct i2c_adapter *adapter)
 {
diff --git a/drivers/media/common/saa7146/saa7146_vbi.c b/drivers/media/common/saa7146/saa7146_vbi.c
index 2da9957..4923751 100644
--- a/drivers/media/common/saa7146/saa7146_vbi.c
+++ b/drivers/media/common/saa7146/saa7146_vbi.c
@@ -1,4 +1,4 @@
-#include <media/saa7146_vv.h>
+#include <media/drv-intf/saa7146_vv.h>
 
 static int vbi_pixel_to_capture = 720 * 2;
 
diff --git a/drivers/media/common/saa7146/saa7146_video.c b/drivers/media/common/saa7146/saa7146_video.c
index 3077949..d5837be 100644
--- a/drivers/media/common/saa7146/saa7146_video.c
+++ b/drivers/media/common/saa7146/saa7146_video.c
@@ -1,6 +1,6 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#include <media/saa7146_vv.h>
+#include <media/drv-intf/saa7146_vv.h>
 #include <media/v4l2-event.h>
 #include <media/v4l2-ctrls.h>
 #include <linux/module.h>
diff --git a/drivers/media/common/siano/smsir.h b/drivers/media/common/siano/smsir.h
index fc8b792..d9abd96 100644
--- a/drivers/media/common/siano/smsir.h
+++ b/drivers/media/common/siano/smsir.h
@@ -30,8 +30,6 @@
 #include <linux/input.h>
 #include <media/rc-core.h>
 
-#define IR_DEFAULT_TIMEOUT		100
-
 struct smscore_device_t;
 
 struct ir_t {
diff --git a/drivers/media/dvb-core/demux.h b/drivers/media/dvb-core/demux.h
index ccc1f43..6d3b95b 100644
--- a/drivers/media/dvb-core/demux.h
+++ b/drivers/media/dvb-core/demux.h
@@ -32,6 +32,49 @@
 #include <linux/time.h>
 #include <linux/dvb/dmx.h>
 
+/**
+ * DOC: Digital TV Demux
+ *
+ * The Kernel Digital TV Demux kABI defines a driver-internal interface for
+ * registering low-level, hardware specific driver to a hardware independent
+ * demux layer. It is only of interest for Digital TV device driver writers.
+ * The header file for this kABI is named demux.h and located in
+ * drivers/media/dvb-core.
+ *
+ * The demux kABI should be implemented for each demux in the system. It is
+ * used to select the TS source of a demux and to manage the demux resources.
+ * When the demux client allocates a resource via the demux kABI, it receives
+ * a pointer to the kABI of that resource.
+ *
+ * Each demux receives its TS input from a DVB front-end or from memory, as
+ * set via this demux kABI. In a system with more than one front-end, the kABI
+ * can be used to select one of the DVB front-ends as a TS source for a demux,
+ * unless this is fixed in the HW platform.
+ *
+ * The demux kABI only controls front-ends regarding to their connections with
+ * demuxes; the kABI used to set the other front-end parameters, such as
+ * tuning, are devined via the Digital TV Frontend kABI.
+ *
+ * The functions that implement the abstract interface demux should be defined
+ * static or module private and registered to the Demux core for external
+ * access. It is not necessary to implement every function in the struct
+ * &dmx_demux. For example, a demux interface might support Section filtering,
+ * but not PES filtering. The kABI client is expected to check the value of any
+ * function pointer before calling the function: the value of NULL means
+ * that the function is not available.
+ *
+ * Whenever the functions of the demux API modify shared data, the
+ * possibilities of lost update and race condition problems should be
+ * addressed, e.g. by protecting parts of code with mutexes.
+ *
+ * Note that functions called from a bottom half context must not sleep.
+ * Even a simple memory allocation without using %GFP_ATOMIC can result in a
+ * kernel thread being put to sleep if swapping is needed. For example, the
+ * Linux Kernel calls the functions of a network device interface from a
+ * bottom half context. Thus, if a demux kABI function is called from network
+ * device code, the function must not sleep.
+ */
+
 /*
  * Common definitions
  */
@@ -187,8 +230,28 @@
 	int (*stop_filtering)(struct dmx_section_feed *feed);
 };
 
-/*
- * Callback functions
+/**
+ * DOC: Demux Callback
+ *
+ * This kernel-space API comprises the callback functions that deliver filtered
+ * data to the demux client. Unlike the other DVB kABIs, these functions are
+ * provided by the client and called from the demux code.
+ *
+ * The function pointers of this abstract interface are not packed into a
+ * structure as in the other demux APIs, because the callback functions are
+ * registered and used independent of each other. As an example, it is possible
+ * for the API client to provide several callback functions for receiving TS
+ * packets and no callbacks for PES packets or sections.
+ *
+ * The functions that implement the callback API need not be re-entrant: when
+ * a demux driver calls one of these functions, the driver is not allowed to
+ * call the function again before the original call returns. If a callback is
+ * triggered by a hardware interrupt, it is recommended to use the Linux
+ * bottom half mechanism or start a tasklet instead of making the callback
+ * function call directly from a hardware interrupt.
+ *
+ * This mechanism is implemented by dmx_ts_cb() and dmx_section_cb()
+ * callbacks.
  */
 
 /**
diff --git a/drivers/media/dvb-core/dvb-usb-ids.h b/drivers/media/dvb-core/dvb-usb-ids.h
index 0a46580..1c1c298 100644
--- a/drivers/media/dvb-core/dvb-usb-ids.h
+++ b/drivers/media/dvb-core/dvb-usb-ids.h
@@ -389,4 +389,5 @@
 #define USB_PID_PCTV_2002E_SE                           0x025d
 #define USB_PID_SVEON_STV27                             0xd3af
 #define USB_PID_TURBOX_DTT_2000                         0xd3a4
+#define USB_PID_WINTV_SOLOHD                            0x0264
 #endif
diff --git a/drivers/media/dvb-core/dvb_frontend.c b/drivers/media/dvb-core/dvb_frontend.c
index c38ef1a..b64f337 100644
--- a/drivers/media/dvb-core/dvb_frontend.c
+++ b/drivers/media/dvb-core/dvb_frontend.c
@@ -891,21 +891,21 @@
 }
 
 /*
- * Sleep until gettimeofday() > waketime + add_usec
- * This needs to be as precise as possible, but as the delay is
- * usually between 2ms and 32ms, it is done using a scheduled msleep
- * followed by usleep (normally a busy-wait loop) for the remainder
+ * Sleep for the amount of time given by add_usec parameter
+ *
+ * This needs to be as precise as possible, as it affects the detection of
+ * the dish tone command at the satellite subsystem. The precision is improved
+ * by using a scheduled msleep followed by udelay for the remainder.
  */
 void dvb_frontend_sleep_until(ktime_t *waketime, u32 add_usec)
 {
-	s32 delta, newdelta;
+	s32 delta;
 
-	ktime_add_us(*waketime, add_usec);
+	*waketime = ktime_add_us(*waketime, add_usec);
 	delta = ktime_us_delta(ktime_get_real(), *waketime);
 	if (delta > 2500) {
 		msleep((delta - 1500) / 1000);
-		newdelta = ktime_us_delta(ktime_get_real(), *waketime);
-		delta = (newdelta > delta) ? 0 : newdelta;
+		delta = ktime_us_delta(ktime_get_real(), *waketime);
 	}
 	if (delta > 0)
 		udelay(delta);
@@ -2313,9 +2313,9 @@
 		dev_dbg(fe->dvb->device, "%s: current delivery system on cache: %d, V3 type: %d\n",
 				 __func__, c->delivery_system, fe->ops.info.type);
 
-		/* Force the CAN_INVERSION_AUTO bit on. If the frontend doesn't
-		 * do it, it is done for it. */
-		info->caps |= FE_CAN_INVERSION_AUTO;
+		/* Set CAN_INVERSION_AUTO bit on in other than oneshot mode */
+		if (!(fepriv->tune_mode_flags & FE_TUNE_MODE_ONESHOT))
+			info->caps |= FE_CAN_INVERSION_AUTO;
 		err = 0;
 		break;
 	}
@@ -2710,6 +2710,11 @@
 	else if (fe->ops.tuner_ops.init)
 		ret = fe->ops.tuner_ops.init(fe);
 
+	if (fe->ops.set_tone && fepriv->tone != -1)
+		fe->ops.set_tone(fe, fepriv->tone);
+	if (fe->ops.set_voltage && fepriv->voltage != -1)
+		fe->ops.set_voltage(fe, fepriv->voltage);
+
 	fe->exit = DVB_FE_NO_EXIT;
 	fepriv->state = FESTATE_RETUNE;
 	dvb_frontend_wakeup(fe);
diff --git a/drivers/media/dvb-core/dvb_frontend.h b/drivers/media/dvb-core/dvb_frontend.h
index 97661b2..458bcce 100644
--- a/drivers/media/dvb-core/dvb_frontend.h
+++ b/drivers/media/dvb-core/dvb_frontend.h
@@ -42,6 +42,29 @@
 
 #include "dvbdev.h"
 
+/**
+ * DOC: Digital TV Frontend
+ *
+ * The Digital TV Frontend kABI defines a driver-internal interface for
+ * registering low-level, hardware specific driver to a hardware independent
+ * frontend layer. It is only of interest for Digital TV device driver writers.
+ * The header file for this API is named dvb_frontend.h and located in
+ * drivers/media/dvb-core.
+ *
+ * Before using the Digital TV frontend core, the bridge driver should attach
+ * the frontend demod, tuner and SEC devices and call dvb_register_frontend(),
+ * in order to register the new frontend at the subsystem. At device
+ * detach/removal, the bridge driver should call dvb_unregister_frontend() to
+ * remove the frontend from the core and then dvb_frontend_detach() to free the
+ * memory allocated by the frontend drivers.
+ *
+ * The drivers should also call dvb_frontend_suspend() as part of their
+ * handler for the &device_driver.suspend(), and dvb_frontend_resume() as
+ * part of their handler for &device_driver.resume().
+ *
+ * A few other optional functions are provided to handle some special cases.
+ */
+
 /*
  * Maximum number of Delivery systems per frontend. It
  * should be smaller or equal to 32
@@ -112,16 +135,6 @@
 	u64 std;
 };
 
-enum tuner_param {
-	DVBFE_TUNER_FREQUENCY		= (1 <<  0),
-	DVBFE_TUNER_TUNERSTEP		= (1 <<  1),
-	DVBFE_TUNER_IFFREQ		= (1 <<  2),
-	DVBFE_TUNER_BANDWIDTH		= (1 <<  3),
-	DVBFE_TUNER_REFCLOCK		= (1 <<  4),
-	DVBFE_TUNER_IQSENSE		= (1 <<  5),
-	DVBFE_TUNER_DUMMY		= (1 << 31)
-};
-
 /**
  * enum dvbfe_algo - defines the algorithm used to tune into a channel
  *
@@ -152,15 +165,6 @@
 	DVBFE_ALGO_RECOVERY		= (1 << 31)
 };
 
-struct tuner_state {
-	u32 frequency;
-	u32 tunerstep;
-	u32 ifreq;
-	u32 bandwidth;
-	u32 iqsense;
-	u32 refclock;
-};
-
 /**
  * enum dvbfe_search - search callback possible return status
  *
@@ -209,12 +213,12 @@
  *			are stored at @dvb_frontend.dtv_property_cache;. The
  *			tuner demod can change the parameters to reflect the
  *			changes needed for the channel to be tuned, and
- *			update statistics.
+ *			update statistics. This is the recommended way to set
+ *			the tuner parameters and should be used on newer
+ *			drivers.
  * @set_analog_params:	callback function used to tune into an analog TV
  *			channel on hybrid tuners. It passes @analog_parameters;
  *			to the driver.
- * @calc_regs:		callback function used to pass register data settings
- *			for simple tuners.
  * @set_config:		callback function used to send some tuner-specific
  *			parameters.
  * @get_frequency:	get the actual tuned frequency
@@ -227,16 +231,10 @@
  *			via DVBv5 API (@dvb_frontend.dtv_property_cache;).
  * @get_afc:		Used only by analog TV core. Reports the frequency
  *			drift due to AFC.
- * @set_frequency:	Set a new frequency. Please notice that using
- *			set_params is preferred.
- * @set_bandwidth:	Set a new frequency. Please notice that using
- *			set_params is preferred.
- * @set_state:		callback function used on some legacy drivers that
- * 			don't implement set_params in order to set properties.
- * 			Shouldn't be used on new drivers.
- * @get_state:		callback function used to get properties by some
- * 			legacy drivers that don't implement set_params.
- * 			Shouldn't be used on new drivers.
+ * @calc_regs:		callback function used to pass register data settings
+ *			for simple tuners.  Shouldn't be used on newer drivers.
+ * @set_frequency:	Set a new frequency. Shouldn't be used on newer drivers.
+ * @set_bandwidth:	Set a new frequency. Shouldn't be used on newer drivers.
  *
  * NOTE: frequencies used on get_frequency and set_frequency are in Hz for
  * terrestrial/cable or kHz for satellite.
@@ -252,14 +250,10 @@
 	int (*suspend)(struct dvb_frontend *fe);
 	int (*resume)(struct dvb_frontend *fe);
 
-	/** This is for simple PLLs - set all parameters in one go. */
+	/* This is the recomended way to set the tuner */
 	int (*set_params)(struct dvb_frontend *fe);
 	int (*set_analog_params)(struct dvb_frontend *fe, struct analog_parameters *p);
 
-	/** This is support for demods like the mt352 - fills out the supplied buffer with what to write. */
-	int (*calc_regs)(struct dvb_frontend *fe, u8 *buf, int buf_len);
-
-	/** This is to allow setting tuner-specific configs */
 	int (*set_config)(struct dvb_frontend *fe, void *priv_cfg);
 
 	int (*get_frequency)(struct dvb_frontend *fe, u32 *frequency);
@@ -272,17 +266,23 @@
 	int (*get_rf_strength)(struct dvb_frontend *fe, u16 *strength);
 	int (*get_afc)(struct dvb_frontend *fe, s32 *afc);
 
-	/** These are provided separately from set_params in order to facilitate silicon
-	 * tuners which require sophisticated tuning loops, controlling each parameter separately. */
-	int (*set_frequency)(struct dvb_frontend *fe, u32 frequency);
-	int (*set_bandwidth)(struct dvb_frontend *fe, u32 bandwidth);
+	/*
+	 * This is support for demods like the mt352 - fills out the supplied
+	 * buffer with what to write.
+	 *
+	 * Don't use on newer drivers.
+	 */
+	int (*calc_regs)(struct dvb_frontend *fe, u8 *buf, int buf_len);
 
 	/*
-	 * These are provided separately from set_params in order to facilitate silicon
-	 * tuners which require sophisticated tuning loops, controlling each parameter separately.
+	 * These are provided separately from set_params in order to
+	 * facilitate silicon tuners which require sophisticated tuning loops,
+	 * controlling each parameter separately.
+	 *
+	 * Don't use on newer drivers.
 	 */
-	int (*set_state)(struct dvb_frontend *fe, enum tuner_param param, struct tuner_state *state);
-	int (*get_state)(struct dvb_frontend *fe, enum tuner_param param, struct tuner_state *state);
+	int (*set_frequency)(struct dvb_frontend *fe, u32 frequency);
+	int (*set_bandwidth)(struct dvb_frontend *fe, u32 bandwidth);
 };
 
 /**
@@ -404,6 +404,11 @@
  *			FE_ENABLE_HIGH_LNB_VOLTAGE ioctl (only Satellite).
  * @dishnetwork_send_legacy_command: callback function to implement the
  *			FE_DISHNETWORK_SEND_LEGACY_CMD ioctl (only Satellite).
+ *			Drivers should not use this, except when the DVB
+ *			core emulation fails to provide proper support (e.g.
+ *			if set_voltage() takes more than 8ms to work), and
+ *			when backward compatibility with this legacy API is
+ *			required.
  * @i2c_gate_ctrl:	controls the I2C gate. Newer drivers should use I2C
  *			mux support instead.
  * @ts_bus_ctrl:	callback function used to take control of the TS bus.
@@ -466,7 +471,8 @@
 	int (*ts_bus_ctrl)(struct dvb_frontend* fe, int acquire);
 	int (*set_lna)(struct dvb_frontend *);
 
-	/* These callbacks are for devices that implement their own
+	/*
+	 * These callbacks are for devices that implement their own
 	 * tuning algorithms, rather than a simple swzigzag
 	 */
 	enum dvbfe_search (*search)(struct dvb_frontend *fe);
@@ -682,17 +688,126 @@
 	unsigned int exit;
 };
 
-extern int dvb_register_frontend(struct dvb_adapter *dvb,
+/**
+ * dvb_register_frontend() - Registers a DVB frontend at the adapter
+ *
+ * @dvb: pointer to the dvb adapter
+ * @fe: pointer to the frontend struct
+ *
+ * Allocate and initialize the private data needed by the frontend core to
+ * manage the frontend and calls dvb_register_device() to register a new
+ * frontend. It also cleans the property cache that stores the frontend
+ * parameters and selects the first available delivery system.
+ */
+int dvb_register_frontend(struct dvb_adapter *dvb,
 				 struct dvb_frontend *fe);
 
-extern int dvb_unregister_frontend(struct dvb_frontend *fe);
+/**
+ * dvb_unregister_frontend() - Unregisters a DVB frontend
+ *
+ * @fe: pointer to the frontend struct
+ *
+ * Stops the frontend kthread, calls dvb_unregister_device() and frees the
+ * private frontend data allocated by dvb_register_frontend().
+ *
+ * NOTE: This function doesn't frees the memory allocated by the demod,
+ * by the SEC driver and by the tuner. In order to free it, an explicit call to
+ * dvb_frontend_detach() is needed, after calling this function.
+ */
+int dvb_unregister_frontend(struct dvb_frontend *fe);
 
-extern void dvb_frontend_detach(struct dvb_frontend *fe);
+/**
+ * dvb_frontend_detach() - Detaches and frees frontend specific data
+ *
+ * @fe: pointer to the frontend struct
+ *
+ * This function should be called after dvb_unregister_frontend(). It
+ * calls the SEC, tuner and demod release functions:
+ * &dvb_frontend_ops.release_sec, &dvb_frontend_ops.tuner_ops.release,
+ * &dvb_frontend_ops.analog_ops.release and &dvb_frontend_ops.release.
+ *
+ * If the driver is compiled with CONFIG_MEDIA_ATTACH, it also decreases
+ * the module reference count, needed to allow userspace to remove the
+ * previously used DVB frontend modules.
+ */
+void dvb_frontend_detach(struct dvb_frontend *fe);
 
-extern void dvb_frontend_reinitialise(struct dvb_frontend *fe);
-extern int dvb_frontend_suspend(struct dvb_frontend *fe);
-extern int dvb_frontend_resume(struct dvb_frontend *fe);
+/**
+ * dvb_frontend_suspend() - Suspends a Digital TV frontend
+ *
+ * @fe: pointer to the frontend struct
+ *
+ * This function prepares a Digital TV frontend to suspend.
+ *
+ * In order to prepare the tuner to suspend, if
+ * &dvb_frontend_ops.tuner_ops.suspend() is available, it calls it. Otherwise,
+ * it will call &dvb_frontend_ops.tuner_ops.sleep(), if available.
+ *
+ * It will also call &dvb_frontend_ops.sleep() to put the demod to suspend.
+ *
+ * The drivers should also call dvb_frontend_suspend() as part of their
+ * handler for the &device_driver.suspend().
+ */
+int dvb_frontend_suspend(struct dvb_frontend *fe);
 
-extern void dvb_frontend_sleep_until(ktime_t *waketime, u32 add_usec);
+/**
+ * dvb_frontend_resume() - Resumes a Digital TV frontend
+ *
+ * @fe: pointer to the frontend struct
+ *
+ * This function resumes the usual operation of the tuner after resume.
+ *
+ * In order to resume the frontend, it calls the demod &dvb_frontend_ops.init().
+ *
+ * If &dvb_frontend_ops.tuner_ops.resume() is available, It, it calls it.
+ * Otherwise,t will call &dvb_frontend_ops.tuner_ops.init(), if available.
+ *
+ * Once tuner and demods are resumed, it will enforce that the SEC voltage and
+ * tone are restored to their previous values and wake up the frontend's
+ * kthread in order to retune the frontend.
+ *
+ * The drivers should also call dvb_frontend_resume() as part of their
+ * handler for the &device_driver.resume().
+ */
+int dvb_frontend_resume(struct dvb_frontend *fe);
+
+/**
+ * dvb_frontend_reinitialise() - forces a reinitialisation at the frontend
+ *
+ * @fe: pointer to the frontend struct
+ *
+ * Calls &dvb_frontend_ops.init() and &dvb_frontend_ops.tuner_ops.init(),
+ * and resets SEC tone and voltage (for Satellite systems).
+ *
+ * NOTE: Currently, this function is used only by one driver (budget-av).
+ * It seems to be due to address some special issue with that specific
+ * frontend.
+ */
+void dvb_frontend_reinitialise(struct dvb_frontend *fe);
+
+/**
+ * dvb_frontend_sleep_until() - Sleep for the amount of time given by
+ *                      add_usec parameter
+ *
+ * @waketime: pointer to a struct ktime_t
+ * @add_usec: time to sleep, in microseconds
+ *
+ * This function is used to measure the time required for the
+ * %FE_DISHNETWORK_SEND_LEGACY_CMD ioctl to work. It needs to be as precise
+ * as possible, as it affects the detection of the dish tone command at the
+ * satellite subsystem.
+ *
+ * Its used internally by the DVB frontend core, in order to emulate
+ * %FE_DISHNETWORK_SEND_LEGACY_CMD using the &dvb_frontend_ops.set_voltage()
+ * callback.
+ *
+ * NOTE: it should not be used at the drivers, as the emulation for the
+ * legacy callback is provided by the Kernel. The only situation where this
+ * should be at the drivers is when there are some bugs at the hardware that
+ * would prevent the core emulation to work. On such cases, the driver would
+ * be writing a &dvb_frontend_ops.dishnetwork_send_legacy_command() and
+ * calling this function directly.
+ */
+void dvb_frontend_sleep_until(ktime_t *waketime, u32 add_usec);
 
 #endif
diff --git a/drivers/media/dvb-frontends/Kconfig b/drivers/media/dvb-frontends/Kconfig
index 292c947..310e4b8 100644
--- a/drivers/media/dvb-frontends/Kconfig
+++ b/drivers/media/dvb-frontends/Kconfig
@@ -264,7 +264,7 @@
 config DVB_TDA10071
 	tristate "NXP TDA10071"
 	depends on DVB_CORE && I2C
-	select REGMAP
+	select REGMAP_I2C
 	default m if !MEDIA_SUBDRV_AUTOSELECT
 	help
 	  Say Y when you want to support this frontend.
diff --git a/drivers/media/dvb-frontends/au8522_common.c b/drivers/media/dvb-frontends/au8522_common.c
index 3559ff2..f135126 100644
--- a/drivers/media/dvb-frontends/au8522_common.c
+++ b/drivers/media/dvb-frontends/au8522_common.c
@@ -44,7 +44,7 @@
 	int ret;
 	u8 buf[] = { (reg >> 8) | 0x80, reg & 0xff, data };
 
-	struct i2c_msg msg = { .addr = state->config->demod_address,
+	struct i2c_msg msg = { .addr = state->config.demod_address,
 			       .flags = 0, .buf = buf, .len = 3 };
 
 	ret = i2c_transfer(state->i2c, &msg, 1);
@@ -64,9 +64,9 @@
 	u8 b1[] = { 0 };
 
 	struct i2c_msg msg[] = {
-		{ .addr = state->config->demod_address, .flags = 0,
+		{ .addr = state->config.demod_address, .flags = 0,
 		  .buf = b0, .len = 2 },
-		{ .addr = state->config->demod_address, .flags = I2C_M_RD,
+		{ .addr = state->config.demod_address, .flags = I2C_M_RD,
 		  .buf = b1, .len = 1 } };
 
 	ret = i2c_transfer(state->i2c, msg, 2);
@@ -140,7 +140,7 @@
 
 static int au8522_led_gpio_enable(struct au8522_state *state, int onoff)
 {
-	struct au8522_led_config *led_config = state->config->led_cfg;
+	struct au8522_led_config *led_config = state->config.led_cfg;
 	u8 val;
 
 	/* bail out if we can't control an LED */
@@ -170,7 +170,7 @@
  */
 int au8522_led_ctrl(struct au8522_state *state, int led)
 {
-	struct au8522_led_config *led_config = state->config->led_cfg;
+	struct au8522_led_config *led_config = state->config.led_cfg;
 	int i, ret = 0;
 
 	/* bail out if we can't control an LED */
diff --git a/drivers/media/dvb-frontends/au8522_decoder.c b/drivers/media/dvb-frontends/au8522_decoder.c
index 28d7dc2..c8f13d8 100644
--- a/drivers/media/dvb-frontends/au8522_decoder.c
+++ b/drivers/media/dvb-frontends/au8522_decoder.c
@@ -730,7 +730,6 @@
 	struct v4l2_ctrl_handler *hdl;
 	struct v4l2_subdev *sd;
 	int instance;
-	struct au8522_config *demod_config;
 
 	/* Check if the adapter supports the needed features */
 	if (!i2c_check_functionality(client->adapter,
@@ -754,15 +753,7 @@
 		break;
 	}
 
-	demod_config = kzalloc(sizeof(struct au8522_config), GFP_KERNEL);
-	if (demod_config == NULL) {
-		if (instance == 1)
-			kfree(state);
-		return -ENOMEM;
-	}
-	demod_config->demod_address = 0x8e >> 1;
-
-	state->config = demod_config;
+	state->config.demod_address = 0x8e >> 1;
 	state->i2c = client->adapter;
 
 	sd = &state->sd;
@@ -784,8 +775,7 @@
 		int err = hdl->error;
 
 		v4l2_ctrl_handler_free(hdl);
-		kfree(demod_config);
-		kfree(state);
+		au8522_release_state(state);
 		return err;
 	}
 
diff --git a/drivers/media/dvb-frontends/au8522_dig.c b/drivers/media/dvb-frontends/au8522_dig.c
index f956f13..6c1e976 100644
--- a/drivers/media/dvb-frontends/au8522_dig.c
+++ b/drivers/media/dvb-frontends/au8522_dig.c
@@ -566,7 +566,7 @@
 			au8522_writereg(state,
 				VSB_mod_tab[i].reg,
 				VSB_mod_tab[i].data);
-		au8522_set_if(fe, state->config->vsb_if);
+		au8522_set_if(fe, state->config.vsb_if);
 		break;
 	case QAM_64:
 		dprintk("%s() QAM 64\n", __func__);
@@ -574,7 +574,7 @@
 			au8522_writereg(state,
 				QAM64_mod_tab[i].reg,
 				QAM64_mod_tab[i].data);
-		au8522_set_if(fe, state->config->qam_if);
+		au8522_set_if(fe, state->config.qam_if);
 		break;
 	case QAM_256:
 		if (zv_mode) {
@@ -583,7 +583,7 @@
 				au8522_writereg(state,
 					QAM256_mod_tab_zv_mode[i].reg,
 					QAM256_mod_tab_zv_mode[i].data);
-			au8522_set_if(fe, state->config->qam_if);
+			au8522_set_if(fe, state->config.qam_if);
 			msleep(100);
 			au8522_writereg(state, 0x821a, 0x00);
 		} else {
@@ -592,7 +592,7 @@
 				au8522_writereg(state,
 					QAM256_mod_tab[i].reg,
 					QAM256_mod_tab[i].data);
-			au8522_set_if(fe, state->config->qam_if);
+			au8522_set_if(fe, state->config.qam_if);
 		}
 		break;
 	default:
@@ -666,7 +666,7 @@
 			*status |= FE_HAS_LOCK | FE_HAS_SYNC;
 	}
 
-	switch (state->config->status_mode) {
+	switch (state->config.status_mode) {
 	case AU8522_DEMODLOCKING:
 		dprintk("%s() DEMODLOCKING\n", __func__);
 		if (*status & FE_HAS_VITERBI)
@@ -704,7 +704,7 @@
 
 static int au8522_led_status(struct au8522_state *state, const u16 *snr)
 {
-	struct au8522_led_config *led_config = state->config->led_cfg;
+	struct au8522_led_config *led_config = state->config.led_cfg;
 	int led;
 	u16 strong;
 
@@ -758,7 +758,7 @@
 					    au8522_readreg(state, 0x4311),
 					    snr);
 
-	if (state->config->led_cfg)
+	if (state->config.led_cfg)
 		au8522_led_status(state, snr);
 
 	return ret;
@@ -866,7 +866,7 @@
 	}
 
 	/* setup the state */
-	state->config = config;
+	state->config = *config;
 	state->i2c = i2c;
 	state->operational_mode = AU8522_DIGITAL_MODE;
 
diff --git a/drivers/media/dvb-frontends/au8522_priv.h b/drivers/media/dvb-frontends/au8522_priv.h
index 951b384..ee330c6 100644
--- a/drivers/media/dvb-frontends/au8522_priv.h
+++ b/drivers/media/dvb-frontends/au8522_priv.h
@@ -50,7 +50,7 @@
 	struct list_head hybrid_tuner_instance_list;
 
 	/* configuration settings */
-	const struct au8522_config *config;
+	struct au8522_config config;
 
 	struct dvb_frontend frontend;
 
diff --git a/drivers/media/dvb-frontends/bsbe1-d01a.h b/drivers/media/dvb-frontends/bsbe1-d01a.h
index 7ed3c42..baaf89e 100644
--- a/drivers/media/dvb-frontends/bsbe1-d01a.h
+++ b/drivers/media/dvb-frontends/bsbe1-d01a.h
@@ -21,7 +21,7 @@
  * Or, point your browser to http://www.gnu.org/copyleft/gpl.html
  *
  *
- * the project's page is at http://www.linuxtv.org
+ * the project's page is at https://linuxtv.org
  */
 
 #ifndef BSBE1_D01A_H
diff --git a/drivers/media/dvb-frontends/bsbe1.h b/drivers/media/dvb-frontends/bsbe1.h
index 53e4d0d..4ad7661 100644
--- a/drivers/media/dvb-frontends/bsbe1.h
+++ b/drivers/media/dvb-frontends/bsbe1.h
@@ -19,7 +19,7 @@
  * Or, point your browser to http://www.gnu.org/copyleft/gpl.html
  *
  *
- * the project's page is at http://www.linuxtv.org
+ * the project's page is at https://linuxtv.org
  */
 
 #ifndef BSBE1_H
diff --git a/drivers/media/dvb-frontends/bsru6.h b/drivers/media/dvb-frontends/bsru6.h
index c2a578e..275c178 100644
--- a/drivers/media/dvb-frontends/bsru6.h
+++ b/drivers/media/dvb-frontends/bsru6.h
@@ -19,7 +19,7 @@
  * Or, point your browser to http://www.gnu.org/copyleft/gpl.html
  *
  *
- * the project's page is at http://www.linuxtv.org
+ * the project's page is at https://linuxtv.org
  */
 
 #ifndef BSRU6_H
diff --git a/drivers/media/dvb-frontends/isl6405.c b/drivers/media/dvb-frontends/isl6405.c
index b46450a..6913cd6 100644
--- a/drivers/media/dvb-frontends/isl6405.c
+++ b/drivers/media/dvb-frontends/isl6405.c
@@ -22,7 +22,7 @@
  * Or, point your browser to http://www.gnu.org/copyleft/gpl.html
  *
  *
- * the project's page is at http://www.linuxtv.org
+ * the project's page is at https://linuxtv.org
  */
 #include <linux/delay.h>
 #include <linux/errno.h>
diff --git a/drivers/media/dvb-frontends/isl6405.h b/drivers/media/dvb-frontends/isl6405.h
index 3c148b8..4a23d3b 100644
--- a/drivers/media/dvb-frontends/isl6405.h
+++ b/drivers/media/dvb-frontends/isl6405.h
@@ -22,7 +22,7 @@
  * Or, point your browser to http://www.gnu.org/copyleft/gpl.html
  *
  *
- * the project's page is at http://www.linuxtv.org
+ * the project's page is at https://linuxtv.org
  */
 
 #ifndef _ISL6405_H
diff --git a/drivers/media/dvb-frontends/isl6421.c b/drivers/media/dvb-frontends/isl6421.c
index 3a4d460..0b6d383 100644
--- a/drivers/media/dvb-frontends/isl6421.c
+++ b/drivers/media/dvb-frontends/isl6421.c
@@ -22,7 +22,7 @@
  * Or, point your browser to http://www.gnu.org/copyleft/gpl.html
  *
  *
- * the project's page is at http://www.linuxtv.org
+ * the project's page is at https://linuxtv.org
  */
 #include <linux/delay.h>
 #include <linux/errno.h>
diff --git a/drivers/media/dvb-frontends/isl6421.h b/drivers/media/dvb-frontends/isl6421.h
index 3273597..00f9874 100644
--- a/drivers/media/dvb-frontends/isl6421.h
+++ b/drivers/media/dvb-frontends/isl6421.h
@@ -22,7 +22,7 @@
  * Or, point your browser to http://www.gnu.org/copyleft/gpl.html
  *
  *
- * the project's page is at http://www.linuxtv.org
+ * the project's page is at https://linuxtv.org
  */
 
 #ifndef _ISL6421_H
diff --git a/drivers/media/dvb-frontends/lnbp21.c b/drivers/media/dvb-frontends/lnbp21.c
index 4aca0fb..6261460 100644
--- a/drivers/media/dvb-frontends/lnbp21.c
+++ b/drivers/media/dvb-frontends/lnbp21.c
@@ -22,7 +22,7 @@
  * Or, point your browser to http://www.gnu.org/copyleft/gpl.html
  *
  *
- * the project's page is at http://www.linuxtv.org
+ * the project's page is at https://linuxtv.org
  */
 #include <linux/delay.h>
 #include <linux/errno.h>
diff --git a/drivers/media/dvb-frontends/lnbp21.h b/drivers/media/dvb-frontends/lnbp21.h
index a9b530d..cd9101f 100644
--- a/drivers/media/dvb-frontends/lnbp21.h
+++ b/drivers/media/dvb-frontends/lnbp21.h
@@ -21,7 +21,7 @@
  * Or, point your browser to http://www.gnu.org/copyleft/gpl.html
  *
  *
- * the project's page is at http://www.linuxtv.org
+ * the project's page is at https://linuxtv.org
  */
 
 #ifndef _LNBP21_H
diff --git a/drivers/media/dvb-frontends/lnbp22.c b/drivers/media/dvb-frontends/lnbp22.c
index d7ca0fd..5c5fd04 100644
--- a/drivers/media/dvb-frontends/lnbp22.c
+++ b/drivers/media/dvb-frontends/lnbp22.c
@@ -22,7 +22,7 @@
  * Or, point your browser to http://www.gnu.org/copyleft/gpl.html
  *
  *
- * the project's page is at http://www.linuxtv.org
+ * the project's page is at https://linuxtv.org
  */
 #include <linux/delay.h>
 #include <linux/errno.h>
diff --git a/drivers/media/dvb-frontends/lnbp22.h b/drivers/media/dvb-frontends/lnbp22.h
index 6281483..5d01d92 100644
--- a/drivers/media/dvb-frontends/lnbp22.h
+++ b/drivers/media/dvb-frontends/lnbp22.h
@@ -22,7 +22,7 @@
  * Or, point your browser to http://www.gnu.org/copyleft/gpl.html
  *
  *
- * the project's page is at http://www.linuxtv.org
+ * the project's page is at https://linuxtv.org
  */
 
 #ifndef _LNBP22_H
diff --git a/drivers/media/dvb-frontends/rtl2832.c b/drivers/media/dvb-frontends/rtl2832.c
index 78b87b2..10f2119 100644
--- a/drivers/media/dvb-frontends/rtl2832.c
+++ b/drivers/media/dvb-frontends/rtl2832.c
@@ -976,7 +976,8 @@
 
 	ret = __i2c_transfer(client->adapter, msg, 2);
 	if (ret != 2) {
-		dev_warn(&client->dev, "i2c reg read failed %d\n", ret);
+		dev_warn(&client->dev, "i2c reg read failed %d reg %02x\n",
+			 ret, *(u8 *)reg_buf);
 		if (ret >= 0)
 			ret = -EREMOTEIO;
 		return ret;
@@ -999,7 +1000,8 @@
 
 	ret = __i2c_transfer(client->adapter, msg, 1);
 	if (ret != 1) {
-		dev_warn(&client->dev, "i2c reg write failed %d\n", ret);
+		dev_warn(&client->dev, "i2c reg write failed %d reg %02x\n",
+			 ret, *(u8 *)data);
 		if (ret >= 0)
 			ret = -EREMOTEIO;
 		return ret;
@@ -1028,7 +1030,8 @@
 
 	ret = __i2c_transfer(client->adapter, msg, 1);
 	if (ret != 1) {
-		dev_warn(&client->dev, "i2c reg write failed %d\n", ret);
+		dev_warn(&client->dev, "i2c reg write failed %d reg %02x\n",
+			 ret, *(u8 const *)reg);
 		if (ret >= 0)
 			ret = -EREMOTEIO;
 		return ret;
@@ -1097,18 +1100,6 @@
 	if (ret)
 		goto err;
 
-	ret = rtl2832_bulk_write(client, 0x022, "\x01", 1);
-	if (ret)
-		goto err;
-
-	ret = rtl2832_bulk_write(client, 0x026, "\x1f", 1);
-	if (ret)
-		goto err;
-
-	ret = rtl2832_bulk_write(client, 0x027, "\xff", 1);
-	if (ret)
-		goto err;
-
 	ret = rtl2832_bulk_write(client, 0x192, "\x7f\xf7\xff", 3);
 	if (ret)
 		goto err;
diff --git a/drivers/media/dvb-frontends/rtl2832_sdr.c b/drivers/media/dvb-frontends/rtl2832_sdr.c
index dcd8d94..b860f02 100644
--- a/drivers/media/dvb-frontends/rtl2832_sdr.c
+++ b/drivers/media/dvb-frontends/rtl2832_sdr.c
@@ -310,7 +310,7 @@
 		len = rtl2832_sdr_convert_stream(dev, ptr, urb->transfer_buffer,
 				urb->actual_length);
 		vb2_set_plane_payload(&fbuf->vb.vb2_buf, 0, len);
-		v4l2_get_timestamp(&fbuf->vb.timestamp);
+		fbuf->vb.vb2_buf.timestamp = ktime_get_ns();
 		fbuf->vb.sequence = dev->sequence++;
 		vb2_buffer_done(&fbuf->vb.vb2_buf, VB2_BUF_STATE_DONE);
 	}
@@ -490,7 +490,7 @@
 
 /* Videobuf2 operations */
 static int rtl2832_sdr_queue_setup(struct vb2_queue *vq,
-		const void *parg, unsigned int *nbuffers,
+		unsigned int *nbuffers,
 		unsigned int *nplanes, unsigned int sizes[], void *alloc_ctxs[])
 {
 	struct rtl2832_sdr_dev *dev = vb2_get_drv_priv(vq);
diff --git a/drivers/media/dvb-frontends/si2165.c b/drivers/media/dvb-frontends/si2165.c
index 7c2eeee..1cf6e52 100644
--- a/drivers/media/dvb-frontends/si2165.c
+++ b/drivers/media/dvb-frontends/si2165.c
@@ -1,21 +1,21 @@
 /*
-    Driver for Silicon Labs Si2161 DVB-T and Si2165 DVB-C/-T Demodulator
-
-    Copyright (C) 2013-2014 Matthias Schwarzott <zzam@gentoo.org>
-
-    This program is free software; you can redistribute it and/or modify
-    it under the terms of the GNU General Public License as published by
-    the Free Software Foundation; either version 2 of the License, or
-    (at your option) any later version.
-
-    This program is distributed in the hope that it will be useful,
-    but WITHOUT ANY WARRANTY; without even the implied warranty of
-    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-    GNU General Public License for more details.
-
-    References:
-    http://www.silabs.com/Support%20Documents/TechnicalDocs/Si2165-short.pdf
-*/
+ *  Driver for Silicon Labs Si2161 DVB-T and Si2165 DVB-C/-T Demodulator
+ *
+ *  Copyright (C) 2013-2014 Matthias Schwarzott <zzam@gentoo.org>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  References:
+ *  http://www.silabs.com/Support%20Documents/TechnicalDocs/Si2165-short.pdf
+ */
 
 #include <linux/delay.h>
 #include <linux/errno.h>
@@ -31,16 +31,18 @@
 #include "si2165_priv.h"
 #include "si2165.h"
 
-/* Hauppauge WinTV-HVR-930C-HD B130 / PCTV QuatroStick 521e 1113xx
- * uses 16 MHz xtal */
-
-/* Hauppauge WinTV-HVR-930C-HD B131 / PCTV QuatroStick 522e 1114xx
- * uses 24 MHz clock provided by tuner */
+/*
+ * Hauppauge WinTV-HVR-930C-HD B130 / PCTV QuatroStick 521e 1113xx
+ * uses 16 MHz xtal
+ *
+ * Hauppauge WinTV-HVR-930C-HD B131 / PCTV QuatroStick 522e 1114xx
+ * uses 24 MHz clock provided by tuner
+ */
 
 struct si2165_state {
 	struct i2c_adapter *i2c;
 
-	struct dvb_frontend frontend;
+	struct dvb_frontend fe;
 
 	struct si2165_config config;
 
@@ -241,6 +243,27 @@
 	return ret;
 }
 
+#define REG16(reg, val) { (reg), (val) & 0xff }, { (reg)+1, (val)>>8 & 0xff }
+struct si2165_reg_value_pair {
+	u16 reg;
+	u8 val;
+};
+
+static int si2165_write_reg_list(struct si2165_state *state,
+				 const struct si2165_reg_value_pair *regs,
+				 int count)
+{
+	int i;
+	int ret;
+
+	for (i = 0; i < count; i++) {
+		ret = si2165_writereg8(state, regs[i].reg, regs[i].val);
+		if (ret < 0)
+			return ret;
+	}
+	return 0;
+}
+
 static int si2165_get_tune_settings(struct dvb_frontend *fe,
 				    struct dvb_frontend_tune_settings *s)
 {
@@ -258,8 +281,10 @@
 	u8 divl = 12;
 	u8 buf[4];
 
-	/* hardcoded values can be deleted if calculation is verified
-	 * or it yields the same values as the windows driver */
+	/*
+	 * hardcoded values can be deleted if calculation is verified
+	 * or it yields the same values as the windows driver
+	 */
 	switch (ref_freq_Hz) {
 	case 16000000u:
 		divn = 56;
@@ -274,8 +299,10 @@
 		if (ref_freq_Hz > 16000000u)
 			divr = 2;
 
-		/* now select divn and divp such that
-		 * fvco is in 1624..1824 MHz */
+		/*
+		 * now select divn and divp such that
+		 * fvco is in 1624..1824 MHz
+		 */
 		if (1624000000u * divr > ref_freq_Hz * 2u * 63u)
 			divp = 4;
 
@@ -341,10 +368,12 @@
 	if (len % 4 != 0)
 		return -EINVAL;
 
-	deb_fw_load("si2165_upload_firmware_block called with len=0x%x offset=0x%x blockcount=0x%x\n",
+	deb_fw_load(
+		"si2165_upload_firmware_block called with len=0x%x offset=0x%x blockcount=0x%x\n",
 				len, offset, block_count);
 	while (offset+12 <= len && cur_block < block_count) {
-		deb_fw_load("si2165_upload_firmware_block in while len=0x%x offset=0x%x cur_block=0x%x blockcount=0x%x\n",
+		deb_fw_load(
+			"si2165_upload_firmware_block in while len=0x%x offset=0x%x cur_block=0x%x blockcount=0x%x\n",
 					len, offset, cur_block, block_count);
 		wordcount = data[offset];
 		if (wordcount < 1 || data[offset+1] ||
@@ -383,7 +412,8 @@
 		cur_block++;
 	}
 
-	deb_fw_load("si2165_upload_firmware_block after while len=0x%x offset=0x%x cur_block=0x%x blockcount=0x%x\n",
+	deb_fw_load(
+		"si2165_upload_firmware_block after while len=0x%x offset=0x%x cur_block=0x%x blockcount=0x%x\n",
 				len, offset, cur_block, block_count);
 
 	if (poffset)
@@ -633,7 +663,7 @@
 		goto error;
 
 	/* ber_pkt */
-	ret = si2165_writereg16(state, 0x0470 , 0x7530);
+	ret = si2165_writereg16(state, 0x0470, 0x7530);
 	if (ret < 0)
 		goto error;
 
@@ -660,22 +690,19 @@
 			goto error;
 	}
 
-	/* write adc values after each reset*/
-	ret = si2165_writereg8(state, 0x012a, 0x46);
+	/* ts output config */
+	ret = si2165_writereg8(state, 0x04e4, 0x20);
 	if (ret < 0)
-		goto error;
-	ret = si2165_writereg8(state, 0x012c, 0x00);
+		return ret;
+	ret = si2165_writereg16(state, 0x04ef, 0x00fe);
 	if (ret < 0)
-		goto error;
-	ret = si2165_writereg8(state, 0x012e, 0x0a);
+		return ret;
+	ret = si2165_writereg24(state, 0x04f4, 0x555555);
 	if (ret < 0)
-		goto error;
-	ret = si2165_writereg8(state, 0x012f, 0xff);
+		return ret;
+	ret = si2165_writereg8(state, 0x04e5, 0x01);
 	if (ret < 0)
-		goto error;
-	ret = si2165_writereg8(state, 0x0123, 0x70);
-	if (ret < 0)
-		goto error;
+		return ret;
 
 	return 0;
 error:
@@ -733,16 +760,26 @@
 	do_div(oversamp, dvb_rate);
 	reg_value = oversamp & 0x3fffffff;
 
-	/* oversamp, usbdump contained 0x03100000; */
+	dprintk("%s: Write oversamp=%#x\n", __func__, reg_value);
 	return si2165_writereg32(state, 0x00e4, reg_value);
 }
 
-static int si2165_set_if_freq_shift(struct si2165_state *state, u32 IF)
+static int si2165_set_if_freq_shift(struct si2165_state *state)
 {
+	struct dvb_frontend *fe = &state->fe;
 	u64 if_freq_shift;
 	s32 reg_value = 0;
 	u32 fe_clk = si2165_get_fe_clk(state);
+	u32 IF = 0;
 
+	if (!fe->ops.tuner_ops.get_if_frequency) {
+		dev_err(&state->i2c->dev,
+			"%s: Error: get_if_frequency() not defined at tuner. Can't work without it!\n",
+			KBUILD_MODNAME);
+		return -EINVAL;
+	}
+
+	fe->ops.tuner_ops.get_if_frequency(fe, &IF);
 	if_freq_shift = IF;
 	if_freq_shift <<= 29;
 
@@ -758,25 +795,39 @@
 	return si2165_writereg32(state, 0x00e8, reg_value);
 }
 
-static int si2165_set_parameters(struct dvb_frontend *fe)
+static const struct si2165_reg_value_pair dvbt_regs[] = {
+	/* standard = DVB-T */
+	{ 0x00ec, 0x01 },
+	{ 0x08f8, 0x00 },
+	/* impulsive_noise_remover */
+	{ 0x031c, 0x01 },
+	{ 0x00cb, 0x00 },
+	/* agc2 */
+	{ 0x016e, 0x41 },
+	{ 0x016c, 0x0e },
+	{ 0x016d, 0x10 },
+	/* agc */
+	{ 0x015b, 0x03 },
+	{ 0x0150, 0x78 },
+	/* agc */
+	{ 0x01a0, 0x78 },
+	{ 0x01c8, 0x68 },
+	/* freq_sync_range */
+	REG16(0x030c, 0x0064),
+	/* gp_reg0 */
+	{ 0x0387, 0x00 }
+};
+
+static int si2165_set_frontend_dvbt(struct dvb_frontend *fe)
 {
 	int ret;
 	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
 	struct si2165_state *state = fe->demodulator_priv;
-	u8 val[3];
-	u32 IF;
 	u32 dvb_rate = 0;
 	u16 bw10k;
 
 	dprintk("%s: called\n", __func__);
 
-	if (!fe->ops.tuner_ops.get_if_frequency) {
-		dev_err(&state->i2c->dev,
-			"%s: Error: get_if_frequency() not defined at tuner. Can't work without it!\n",
-			KBUILD_MODNAME);
-		return -EINVAL;
-	}
-
 	if (!state->has_dvbt)
 		return -EINVAL;
 
@@ -788,34 +839,10 @@
 		bw10k = 800;
 	}
 
-	/* standard = DVB-T */
-	ret = si2165_writereg8(state, 0x00ec, 0x01);
-	if (ret < 0)
-		return ret;
 	ret = si2165_adjust_pll_divl(state, 12);
 	if (ret < 0)
 		return ret;
 
-	fe->ops.tuner_ops.get_if_frequency(fe, &IF);
-	ret = si2165_set_if_freq_shift(state, IF);
-	if (ret < 0)
-		return ret;
-	ret = si2165_writereg8(state, 0x08f8, 0x00);
-	if (ret < 0)
-		return ret;
-	/* ts output config */
-	ret = si2165_writereg8(state, 0x04e4, 0x20);
-	if (ret < 0)
-		return ret;
-	ret = si2165_writereg16(state, 0x04ef, 0x00fe);
-	if (ret < 0)
-		return ret;
-	ret = si2165_writereg24(state, 0x04f4, 0x555555);
-	if (ret < 0)
-		return ret;
-	ret = si2165_writereg8(state, 0x04e5, 0x01);
-	if (ret < 0)
-		return ret;
 	/* bandwidth in 10KHz steps */
 	ret = si2165_writereg16(state, 0x0308, bw10k);
 	if (ret < 0)
@@ -823,48 +850,115 @@
 	ret = si2165_set_oversamp(state, dvb_rate);
 	if (ret < 0)
 		return ret;
-	/* impulsive_noise_remover */
-	ret = si2165_writereg8(state, 0x031c, 0x01);
+
+	ret = si2165_write_reg_list(state, dvbt_regs, ARRAY_SIZE(dvbt_regs));
 	if (ret < 0)
 		return ret;
-	ret = si2165_writereg8(state, 0x00cb, 0x00);
-	if (ret < 0)
-		return ret;
+
+	return 0;
+}
+
+static const struct si2165_reg_value_pair dvbc_regs[] = {
+	/* standard = DVB-C */
+	{ 0x00ec, 0x05 },
+	{ 0x08f8, 0x00 },
+
 	/* agc2 */
-	ret = si2165_writereg8(state, 0x016e, 0x41);
-	if (ret < 0)
-		return ret;
-	ret = si2165_writereg8(state, 0x016c, 0x0e);
-	if (ret < 0)
-		return ret;
-	ret = si2165_writereg8(state, 0x016d, 0x10);
-	if (ret < 0)
-		return ret;
+	{ 0x016e, 0x50 },
+	{ 0x016c, 0x0e },
+	{ 0x016d, 0x10 },
 	/* agc */
-	ret = si2165_writereg8(state, 0x015b, 0x03);
-	if (ret < 0)
-		return ret;
-	ret = si2165_writereg8(state, 0x0150, 0x78);
-	if (ret < 0)
-		return ret;
+	{ 0x015b, 0x03 },
+	{ 0x0150, 0x68 },
 	/* agc */
-	ret = si2165_writereg8(state, 0x01a0, 0x78);
+	{ 0x01a0, 0x68 },
+	{ 0x01c8, 0x50 },
+
+	{ 0x0278, 0x0d },
+
+	{ 0x023a, 0x05 },
+	{ 0x0261, 0x09 },
+	REG16(0x0350, 0x3e80),
+	{ 0x02f4, 0x00 },
+
+	{ 0x00cb, 0x01 },
+	REG16(0x024c, 0x0000),
+	REG16(0x027c, 0x0000),
+	{ 0x0232, 0x03 },
+	{ 0x02f4, 0x0b },
+	{ 0x018b, 0x00 },
+};
+
+static int si2165_set_frontend_dvbc(struct dvb_frontend *fe)
+{
+	struct si2165_state *state = fe->demodulator_priv;
+	int ret;
+	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
+	const u32 dvb_rate = p->symbol_rate;
+	const u32 bw_hz = p->bandwidth_hz;
+
+	if (!state->has_dvbc)
+		return -EINVAL;
+
+	if (dvb_rate == 0)
+		return -EINVAL;
+
+	ret = si2165_adjust_pll_divl(state, 14);
 	if (ret < 0)
 		return ret;
-	ret = si2165_writereg8(state, 0x01c8, 0x68);
+
+	/* Oversampling */
+	ret = si2165_set_oversamp(state, dvb_rate);
 	if (ret < 0)
 		return ret;
-	/* freq_sync_range */
-	ret = si2165_writereg16(state, 0x030c, 0x0064);
+
+	ret = si2165_writereg32(state, 0x00c4, bw_hz);
 	if (ret < 0)
 		return ret;
-	/* gp_reg0 */
-	ret = si2165_readreg8(state, 0x0387, val);
+
+	ret = si2165_write_reg_list(state, dvbc_regs, ARRAY_SIZE(dvbc_regs));
 	if (ret < 0)
 		return ret;
-	ret = si2165_writereg8(state, 0x0387, 0x00);
+
+	return 0;
+}
+
+static const struct si2165_reg_value_pair agc_rewrite[] = {
+	{ 0x012a, 0x46 },
+	{ 0x012c, 0x00 },
+	{ 0x012e, 0x0a },
+	{ 0x012f, 0xff },
+	{ 0x0123, 0x70 }
+};
+
+static int si2165_set_frontend(struct dvb_frontend *fe)
+{
+	struct si2165_state *state = fe->demodulator_priv;
+	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
+	u32 delsys = p->delivery_system;
+	int ret;
+	u8 val[3];
+
+	/* initial setting of if freq shift */
+	ret = si2165_set_if_freq_shift(state);
 	if (ret < 0)
 		return ret;
+
+	switch (delsys) {
+	case SYS_DVBT:
+		ret = si2165_set_frontend_dvbt(fe);
+		if (ret < 0)
+			return ret;
+		break;
+	case SYS_DVBC_ANNEX_A:
+		ret = si2165_set_frontend_dvbc(fe);
+		if (ret < 0)
+			return ret;
+		break;
+	default:
+		return -EINVAL;
+	}
+
 	/* dsp_addr_jump */
 	ret = si2165_writereg32(state, 0x0348, 0xf4000000);
 	if (ret < 0)
@@ -874,8 +968,7 @@
 		fe->ops.tuner_ops.set_params(fe);
 
 	/* recalc if_freq_shift if IF might has changed */
-	fe->ops.tuner_ops.get_if_frequency(fe, &IF);
-	ret = si2165_set_if_freq_shift(state, IF);
+	ret = si2165_set_if_freq_shift(state);
 	if (ret < 0)
 		return ret;
 
@@ -886,6 +979,7 @@
 	ret = si2165_writereg8(state, 0x0341, 0x00);
 	if (ret < 0)
 		return ret;
+
 	/* reset all */
 	ret = si2165_writereg8(state, 0x00c0, 0x00);
 	if (ret < 0)
@@ -894,6 +988,13 @@
 	ret = si2165_writereg32(state, 0x0384, 0x00000000);
 	if (ret < 0)
 		return ret;
+
+	/* write adc values after each reset*/
+	ret = si2165_write_reg_list(state, agc_rewrite,
+				    ARRAY_SIZE(agc_rewrite));
+	if (ret < 0)
+		return ret;
+
 	/* start_synchro */
 	ret = si2165_writereg8(state, 0x02e0, 0x01);
 	if (ret < 0)
@@ -917,7 +1018,12 @@
 static struct dvb_frontend_ops si2165_ops = {
 	.info = {
 		.name = "Silicon Labs ",
-		.caps =	FE_CAN_FEC_1_2 |
+		 /* For DVB-C */
+		.symbol_rate_min = 1000000,
+		.symbol_rate_max = 7200000,
+		/* For DVB-T */
+		.frequency_stepsize = 166667,
+		.caps = FE_CAN_FEC_1_2 |
 			FE_CAN_FEC_2_3 |
 			FE_CAN_FEC_3_4 |
 			FE_CAN_FEC_5_6 |
@@ -930,7 +1036,6 @@
 			FE_CAN_QAM_128 |
 			FE_CAN_QAM_256 |
 			FE_CAN_QAM_AUTO |
-			FE_CAN_TRANSMISSION_MODE_AUTO |
 			FE_CAN_GUARD_INTERVAL_AUTO |
 			FE_CAN_HIERARCHY_AUTO |
 			FE_CAN_MUTE_TS |
@@ -943,7 +1048,7 @@
 	.init = si2165_init,
 	.sleep = si2165_sleep,
 
-	.set_frontend      = si2165_set_parameters,
+	.set_frontend      = si2165_set_frontend,
 	.read_status       = si2165_read_status,
 
 	.release = si2165_release,
@@ -979,9 +1084,9 @@
 	}
 
 	/* create dvb_frontend */
-	memcpy(&state->frontend.ops, &si2165_ops,
+	memcpy(&state->fe.ops, &si2165_ops,
 		sizeof(struct dvb_frontend_ops));
-	state->frontend.demodulator_priv = state;
+	state->fe.demodulator_priv = state;
 
 	/* powerup */
 	io_ret = si2165_writereg8(state, 0x0000, state->config.chip_mode);
@@ -1033,20 +1138,22 @@
 		KBUILD_MODNAME, chip_name, rev_char, state->chip_type,
 		state->chip_revcode);
 
-	strlcat(state->frontend.ops.info.name, chip_name,
-			sizeof(state->frontend.ops.info.name));
+	strlcat(state->fe.ops.info.name, chip_name,
+			sizeof(state->fe.ops.info.name));
 
 	n = 0;
 	if (state->has_dvbt) {
-		state->frontend.ops.delsys[n++] = SYS_DVBT;
-		strlcat(state->frontend.ops.info.name, " DVB-T",
-			sizeof(state->frontend.ops.info.name));
+		state->fe.ops.delsys[n++] = SYS_DVBT;
+		strlcat(state->fe.ops.info.name, " DVB-T",
+			sizeof(state->fe.ops.info.name));
 	}
-	if (state->has_dvbc)
-		dev_warn(&state->i2c->dev, "%s: DVB-C is not yet supported.\n",
-		       KBUILD_MODNAME);
+	if (state->has_dvbc) {
+		state->fe.ops.delsys[n++] = SYS_DVBC_ANNEX_A;
+		strlcat(state->fe.ops.info.name, " DVB-C",
+			sizeof(state->fe.ops.info.name));
+	}
 
-	return &state->frontend;
+	return &state->fe;
 
 error:
 	kfree(state);
diff --git a/drivers/media/dvb-frontends/stb6100.c b/drivers/media/dvb-frontends/stb6100.c
index 4ef8a5c..c978c80 100644
--- a/drivers/media/dvb-frontends/stb6100.c
+++ b/drivers/media/dvb-frontends/stb6100.c
@@ -252,6 +252,7 @@
 {
 	int rc;
 	u8 f;
+	u32 bw;
 	struct stb6100_state *state = fe->tuner_priv;
 
 	rc = stb6100_read_reg(state, STB6100_F);
@@ -259,9 +260,9 @@
 		return rc;
 	f = rc & STB6100_F_F;
 
-	state->status.bandwidth = (f + 5) * 2000;	/* x2 for ZIF	*/
+	bw = (f + 5) * 2000;	/* x2 for ZIF	*/
 
-	*bandwidth = state->bandwidth = state->status.bandwidth * 1000;
+	*bandwidth = state->bandwidth = bw * 1000;
 	dprintk(verbose, FE_DEBUG, 1, "bandwidth = %u Hz", state->bandwidth);
 	return 0;
 }
@@ -495,68 +496,28 @@
 static int stb6100_init(struct dvb_frontend *fe)
 {
 	struct stb6100_state *state = fe->tuner_priv;
-	struct tuner_state *status = &state->status;
+	int refclk = 27000000; /* Hz */
 
-	status->tunerstep	= 125000;
-	status->ifreq		= 0;
-	status->refclock	= 27000000;	/* Hz	*/
-	status->iqsense		= 1;
-	status->bandwidth	= 36000;	/* kHz	*/
-	state->bandwidth	= status->bandwidth * 1000;	/* Hz	*/
-	state->reference	= status->refclock / 1000;	/* kHz	*/
+	/*
+	 * iqsense = 1
+	 * tunerstep = 125000
+	 */
+	state->bandwidth        = 36000000;		/* Hz	*/
+	state->reference	= refclk / 1000;	/* kHz	*/
 
 	/* Set default bandwidth. Modified, PN 13-May-10	*/
 	return 0;
 }
 
-static int stb6100_get_state(struct dvb_frontend *fe,
-			     enum tuner_param param,
-			     struct tuner_state *state)
+static int stb6100_set_params(struct dvb_frontend *fe)
 {
-	switch (param) {
-	case DVBFE_TUNER_FREQUENCY:
-		stb6100_get_frequency(fe, &state->frequency);
-		break;
-	case DVBFE_TUNER_TUNERSTEP:
-		break;
-	case DVBFE_TUNER_IFFREQ:
-		break;
-	case DVBFE_TUNER_BANDWIDTH:
-		stb6100_get_bandwidth(fe, &state->bandwidth);
-		break;
-	case DVBFE_TUNER_REFCLOCK:
-		break;
-	default:
-		break;
-	}
+	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 
-	return 0;
-}
+	if (c->frequency > 0)
+		stb6100_set_frequency(fe, c->frequency);
 
-static int stb6100_set_state(struct dvb_frontend *fe,
-			     enum tuner_param param,
-			     struct tuner_state *state)
-{
-	struct stb6100_state *tstate = fe->tuner_priv;
-
-	switch (param) {
-	case DVBFE_TUNER_FREQUENCY:
-		stb6100_set_frequency(fe, state->frequency);
-		tstate->frequency = state->frequency;
-		break;
-	case DVBFE_TUNER_TUNERSTEP:
-		break;
-	case DVBFE_TUNER_IFFREQ:
-		break;
-	case DVBFE_TUNER_BANDWIDTH:
-		stb6100_set_bandwidth(fe, state->bandwidth);
-		tstate->bandwidth = state->bandwidth;
-		break;
-	case DVBFE_TUNER_REFCLOCK:
-		break;
-	default:
-		break;
-	}
+	if (c->bandwidth_hz > 0)
+		stb6100_set_bandwidth(fe, c->bandwidth_hz);
 
 	return 0;
 }
@@ -572,8 +533,9 @@
 	.init		= stb6100_init,
 	.sleep          = stb6100_sleep,
 	.get_status	= stb6100_get_status,
-	.get_state	= stb6100_get_state,
-	.set_state	= stb6100_set_state,
+	.set_params	= stb6100_set_params,
+	.get_frequency  = stb6100_get_frequency,
+	.get_bandwidth  = stb6100_get_bandwidth,
 	.release	= stb6100_release
 };
 
diff --git a/drivers/media/dvb-frontends/stb6100.h b/drivers/media/dvb-frontends/stb6100.h
index 218c818..f7b468b 100644
--- a/drivers/media/dvb-frontends/stb6100.h
+++ b/drivers/media/dvb-frontends/stb6100.h
@@ -86,7 +86,6 @@
 	const struct stb6100_config	*config;
 	struct dvb_tuner_ops		ops;
 	struct dvb_frontend		*frontend;
-	struct tuner_state		status;
 
 	u32 frequency;
 	u32 srate;
diff --git a/drivers/media/dvb-frontends/stb6100_cfg.h b/drivers/media/dvb-frontends/stb6100_cfg.h
index 6edc153..2ef67aa 100644
--- a/drivers/media/dvb-frontends/stb6100_cfg.h
+++ b/drivers/media/dvb-frontends/stb6100_cfg.h
@@ -19,20 +19,21 @@
 	Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 */
 
+#include <linux/dvb/frontend.h>
+#include "dvb_frontend.h"
+
 static int stb6100_get_frequency(struct dvb_frontend *fe, u32 *frequency)
 {
 	struct dvb_frontend_ops	*frontend_ops = &fe->ops;
 	struct dvb_tuner_ops	*tuner_ops = &frontend_ops->tuner_ops;
-	struct tuner_state	t_state;
 	int err = 0;
 
-	if (tuner_ops->get_state) {
-		err = tuner_ops->get_state(fe, DVBFE_TUNER_FREQUENCY, &t_state);
+	if (tuner_ops->get_frequency) {
+		err = tuner_ops->get_frequency(fe, frequency);
 		if (err < 0) {
 			printk("%s: Invalid parameter\n", __func__);
 			return err;
 		}
-		*frequency = t_state.frequency;
 	}
 	return 0;
 }
@@ -41,13 +42,16 @@
 {
 	struct dvb_frontend_ops	*frontend_ops = &fe->ops;
 	struct dvb_tuner_ops	*tuner_ops = &frontend_ops->tuner_ops;
-	struct tuner_state	t_state;
+	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
+	u32 bw = c->bandwidth_hz;
 	int err = 0;
 
-	t_state.frequency = frequency;
+	c->frequency = frequency;
+	c->bandwidth_hz = 0;		/* Don't adjust the bandwidth */
 
-	if (tuner_ops->set_state) {
-		err = tuner_ops->set_state(fe, DVBFE_TUNER_FREQUENCY, &t_state);
+	if (tuner_ops->set_params) {
+		err = tuner_ops->set_params(fe);
+		c->bandwidth_hz = bw;
 		if (err < 0) {
 			printk("%s: Invalid parameter\n", __func__);
 			return err;
@@ -60,16 +64,14 @@
 {
 	struct dvb_frontend_ops	*frontend_ops = &fe->ops;
 	struct dvb_tuner_ops	*tuner_ops = &frontend_ops->tuner_ops;
-	struct tuner_state	t_state;
 	int err = 0;
 
-	if (tuner_ops->get_state) {
-		err = tuner_ops->get_state(fe, DVBFE_TUNER_BANDWIDTH, &t_state);
+	if (tuner_ops->get_bandwidth) {
+		err = tuner_ops->get_bandwidth(fe, bandwidth);
 		if (err < 0) {
 			printk("%s: Invalid parameter\n", __func__);
 			return err;
 		}
-		*bandwidth = t_state.bandwidth;
 	}
 	return 0;
 }
@@ -78,13 +80,16 @@
 {
 	struct dvb_frontend_ops	*frontend_ops = &fe->ops;
 	struct dvb_tuner_ops	*tuner_ops = &frontend_ops->tuner_ops;
-	struct tuner_state	t_state;
+	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
+	u32 freq = c->frequency;
 	int err = 0;
 
-	t_state.bandwidth = bandwidth;
+	c->bandwidth_hz = bandwidth;
+	c->frequency = 0;		/* Don't adjust the frequency */
 
-	if (tuner_ops->set_state) {
-		err = tuner_ops->set_state(fe, DVBFE_TUNER_BANDWIDTH, &t_state);
+	if (tuner_ops->set_params) {
+		err = tuner_ops->set_params(fe);
+		c->frequency = freq;
 		if (err < 0) {
 			printk("%s: Invalid parameter\n", __func__);
 			return err;
diff --git a/drivers/media/dvb-frontends/stb6100_proc.h b/drivers/media/dvb-frontends/stb6100_proc.h
index bd8a0ec..50ffa21 100644
--- a/drivers/media/dvb-frontends/stb6100_proc.h
+++ b/drivers/media/dvb-frontends/stb6100_proc.h
@@ -17,27 +17,27 @@
 	Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 */
 
+#include <linux/dvb/frontend.h>
+#include "dvb_frontend.h"
+
 static int stb6100_get_freq(struct dvb_frontend *fe, u32 *frequency)
 {
 	struct dvb_frontend_ops	*frontend_ops = &fe->ops;
 	struct dvb_tuner_ops	*tuner_ops = &frontend_ops->tuner_ops;
-	struct tuner_state	state;
 	int err = 0;
 
-	if (tuner_ops->get_state) {
+	if (tuner_ops->get_frequency) {
 		if (frontend_ops->i2c_gate_ctrl)
 			frontend_ops->i2c_gate_ctrl(fe, 1);
 
-		err = tuner_ops->get_state(fe, DVBFE_TUNER_FREQUENCY, &state);
+		err = tuner_ops->get_frequency(fe, frequency);
 		if (err < 0) {
-			printk(KERN_ERR "%s: Invalid parameter\n", __func__);
+			printk("%s: Invalid parameter\n", __func__);
 			return err;
 		}
 
 		if (frontend_ops->i2c_gate_ctrl)
 			frontend_ops->i2c_gate_ctrl(fe, 0);
-
-		*frequency = state.frequency;
 	}
 
 	return 0;
@@ -47,18 +47,21 @@
 {
 	struct dvb_frontend_ops	*frontend_ops = &fe->ops;
 	struct dvb_tuner_ops	*tuner_ops = &frontend_ops->tuner_ops;
-	struct tuner_state	state;
+	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
+	u32 bw = c->bandwidth_hz;
 	int err = 0;
 
-	state.frequency = frequency;
+	c->frequency = frequency;
+	c->bandwidth_hz = 0;		/* Don't adjust the bandwidth */
 
-	if (tuner_ops->set_state) {
+	if (tuner_ops->set_params) {
 		if (frontend_ops->i2c_gate_ctrl)
 			frontend_ops->i2c_gate_ctrl(fe, 1);
 
-		err = tuner_ops->set_state(fe, DVBFE_TUNER_FREQUENCY, &state);
+		err = tuner_ops->set_params(fe);
+		c->bandwidth_hz = bw;
 		if (err < 0) {
-			printk(KERN_ERR "%s: Invalid parameter\n", __func__);
+			printk("%s: Invalid parameter\n", __func__);
 			return err;
 		}
 
@@ -74,14 +77,13 @@
 {
 	struct dvb_frontend_ops	*frontend_ops = &fe->ops;
 	struct dvb_tuner_ops	*tuner_ops = &frontend_ops->tuner_ops;
-	struct tuner_state	state;
 	int err = 0;
 
-	if (tuner_ops->get_state) {
+	if (tuner_ops->get_bandwidth) {
 		if (frontend_ops->i2c_gate_ctrl)
 			frontend_ops->i2c_gate_ctrl(fe, 1);
 
-		err = tuner_ops->get_state(fe, DVBFE_TUNER_BANDWIDTH, &state);
+		err = tuner_ops->get_bandwidth(fe, bandwidth);
 		if (err < 0) {
 			printk(KERN_ERR "%s: Invalid parameter\n", __func__);
 			return err;
@@ -89,8 +91,6 @@
 
 		if (frontend_ops->i2c_gate_ctrl)
 			frontend_ops->i2c_gate_ctrl(fe, 0);
-
-		*bandwidth = state.bandwidth;
 	}
 
 	return 0;
@@ -100,16 +100,19 @@
 {
 	struct dvb_frontend_ops	*frontend_ops = &fe->ops;
 	struct dvb_tuner_ops	*tuner_ops = &frontend_ops->tuner_ops;
-	struct tuner_state	state;
+	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
+	u32 freq = c->frequency;
 	int err = 0;
 
-	state.bandwidth = bandwidth;
+	c->bandwidth_hz = bandwidth;
+	c->frequency = 0;		/* Don't adjust the frequency */
 
-	if (tuner_ops->set_state) {
+	if (tuner_ops->set_params) {
 		if (frontend_ops->i2c_gate_ctrl)
 			frontend_ops->i2c_gate_ctrl(fe, 1);
 
-		err = tuner_ops->set_state(fe, DVBFE_TUNER_BANDWIDTH, &state);
+		err = tuner_ops->set_params(fe);
+		c->frequency = freq;
 		if (err < 0) {
 			printk(KERN_ERR "%s: Invalid parameter\n", __func__);
 			return err;
diff --git a/drivers/media/dvb-frontends/tda665x.c b/drivers/media/dvb-frontends/tda665x.c
index 63cc123..82f8cc5 100644
--- a/drivers/media/dvb-frontends/tda665x.c
+++ b/drivers/media/dvb-frontends/tda665x.c
@@ -66,26 +66,13 @@
 	return err;
 }
 
-static int tda665x_get_state(struct dvb_frontend *fe,
-			     enum tuner_param param,
-			     struct tuner_state *tstate)
+static int tda665x_get_frequency(struct dvb_frontend *fe, u32 *frequency)
 {
 	struct tda665x_state *state = fe->tuner_priv;
-	int err = 0;
 
-	switch (param) {
-	case DVBFE_TUNER_FREQUENCY:
-		tstate->frequency = state->frequency;
-		break;
-	case DVBFE_TUNER_BANDWIDTH:
-		break;
-	default:
-		printk(KERN_ERR "%s: Unknown parameter (param=%d)\n", __func__, param);
-		err = -EINVAL;
-		break;
-	}
+	*frequency = state->frequency;
 
-	return err;
+	return 0;
 }
 
 static int tda665x_get_status(struct dvb_frontend *fe, u32 *status)
@@ -111,9 +98,8 @@
 	return err;
 }
 
-static int tda665x_set_state(struct dvb_frontend *fe,
-			     enum tuner_param param,
-			     struct tuner_state *tstate)
+static int tda665x_set_frequency(struct dvb_frontend *fe,
+				 u32 new_frequency)
 {
 	struct tda665x_state *state = fe->tuner_priv;
 	const struct tda665x_config *config = state->config;
@@ -121,88 +107,96 @@
 	u8 buf[4];
 	int err = 0;
 
-	if (param & DVBFE_TUNER_FREQUENCY) {
-
-		frequency = tstate->frequency;
-		if ((frequency < config->frequency_max) || (frequency > config->frequency_min)) {
-			printk(KERN_ERR "%s: Frequency beyond limits, frequency=%d\n", __func__, frequency);
-			return -EINVAL;
-		}
-
-		frequency += config->frequency_offst;
-		frequency *= config->ref_multiplier;
-		frequency += config->ref_divider >> 1;
-		frequency /= config->ref_divider;
-
-		buf[0] = (u8) ((frequency & 0x7f00) >> 8);
-		buf[1] = (u8) (frequency & 0x00ff) >> 0;
-		buf[2] = 0x80 | 0x40 | 0x02;
-		buf[3] = 0x00;
-
-		/* restore frequency */
-		frequency = tstate->frequency;
-
-		if (frequency < 153000000) {
-			/* VHF-L */
-			buf[3] |= 0x01; /* fc, Low Band, 47 - 153 MHz */
-			if (frequency < 68000000)
-				buf[3] |= 0x40; /* 83uA */
-			if (frequency < 1040000000)
-				buf[3] |= 0x60; /* 122uA */
-			if (frequency < 1250000000)
-				buf[3] |= 0x80; /* 163uA */
-			else
-				buf[3] |= 0xa0; /* 254uA */
-		} else if (frequency < 438000000) {
-			/* VHF-H */
-			buf[3] |= 0x02; /* fc, Mid Band, 153 - 438 MHz */
-			if (frequency < 230000000)
-				buf[3] |= 0x40;
-			if (frequency < 300000000)
-				buf[3] |= 0x60;
-			else
-				buf[3] |= 0x80;
-		} else {
-			/* UHF */
-			buf[3] |= 0x04; /* fc, High Band, 438 - 862 MHz */
-			if (frequency < 470000000)
-				buf[3] |= 0x60;
-			if (frequency < 526000000)
-				buf[3] |= 0x80;
-			else
-				buf[3] |= 0xa0;
-		}
-
-		/* Set params */
-		err = tda665x_write(state, buf, 5);
-		if (err < 0)
-			goto exit;
-
-		/* sleep for some time */
-		printk(KERN_DEBUG "%s: Waiting to Phase LOCK\n", __func__);
-		msleep(20);
-		/* check status */
-		err = tda665x_get_status(fe, &status);
-		if (err < 0)
-			goto exit;
-
-		if (status == 1) {
-			printk(KERN_DEBUG "%s: Tuner Phase locked: status=%d\n", __func__, status);
-			state->frequency = frequency; /* cache successful state */
-		} else {
-			printk(KERN_ERR "%s: No Phase lock: status=%d\n", __func__, status);
-		}
-	} else {
-		printk(KERN_ERR "%s: Unknown parameter (param=%d)\n", __func__, param);
+	if ((new_frequency < config->frequency_max)
+	    || (new_frequency > config->frequency_min)) {
+		printk(KERN_ERR "%s: Frequency beyond limits, frequency=%d\n",
+		       __func__, new_frequency);
 		return -EINVAL;
 	}
 
+	frequency = new_frequency;
+
+	frequency += config->frequency_offst;
+	frequency *= config->ref_multiplier;
+	frequency += config->ref_divider >> 1;
+	frequency /= config->ref_divider;
+
+	buf[0] = (u8) ((frequency & 0x7f00) >> 8);
+	buf[1] = (u8) (frequency & 0x00ff) >> 0;
+	buf[2] = 0x80 | 0x40 | 0x02;
+	buf[3] = 0x00;
+
+	/* restore frequency */
+	frequency = new_frequency;
+
+	if (frequency < 153000000) {
+		/* VHF-L */
+		buf[3] |= 0x01; /* fc, Low Band, 47 - 153 MHz */
+		if (frequency < 68000000)
+			buf[3] |= 0x40; /* 83uA */
+		if (frequency < 1040000000)
+			buf[3] |= 0x60; /* 122uA */
+		if (frequency < 1250000000)
+			buf[3] |= 0x80; /* 163uA */
+		else
+			buf[3] |= 0xa0; /* 254uA */
+	} else if (frequency < 438000000) {
+		/* VHF-H */
+		buf[3] |= 0x02; /* fc, Mid Band, 153 - 438 MHz */
+		if (frequency < 230000000)
+			buf[3] |= 0x40;
+		if (frequency < 300000000)
+			buf[3] |= 0x60;
+		else
+			buf[3] |= 0x80;
+	} else {
+		/* UHF */
+		buf[3] |= 0x04; /* fc, High Band, 438 - 862 MHz */
+		if (frequency < 470000000)
+			buf[3] |= 0x60;
+		if (frequency < 526000000)
+			buf[3] |= 0x80;
+		else
+			buf[3] |= 0xa0;
+	}
+
+	/* Set params */
+	err = tda665x_write(state, buf, 5);
+	if (err < 0)
+		goto exit;
+
+	/* sleep for some time */
+	printk(KERN_DEBUG "%s: Waiting to Phase LOCK\n", __func__);
+	msleep(20);
+	/* check status */
+	err = tda665x_get_status(fe, &status);
+	if (err < 0)
+		goto exit;
+
+	if (status == 1) {
+		printk(KERN_DEBUG "%s: Tuner Phase locked: status=%d\n",
+		       __func__, status);
+		state->frequency = frequency; /* cache successful state */
+	} else {
+		printk(KERN_ERR "%s: No Phase lock: status=%d\n",
+		       __func__, status);
+	}
+
 	return 0;
 exit:
 	printk(KERN_ERR "%s: I/O Error\n", __func__);
 	return err;
 }
 
+static int tda665x_set_params(struct dvb_frontend *fe)
+{
+	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
+
+	tda665x_set_frequency(fe, c->frequency);
+
+	return 0;
+}
+
 static int tda665x_release(struct dvb_frontend *fe)
 {
 	struct tda665x_state *state = fe->tuner_priv;
@@ -213,10 +207,9 @@
 }
 
 static struct dvb_tuner_ops tda665x_ops = {
-
-	.set_state	= tda665x_set_state,
-	.get_state	= tda665x_get_state,
 	.get_status	= tda665x_get_status,
+	.set_params	= tda665x_set_params,
+	.get_frequency	= tda665x_get_frequency,
 	.release	= tda665x_release
 };
 
diff --git a/drivers/media/dvb-frontends/tda8261.c b/drivers/media/dvb-frontends/tda8261.c
index 19c4888..3285b1b 100644
--- a/drivers/media/dvb-frontends/tda8261.c
+++ b/drivers/media/dvb-frontends/tda8261.c
@@ -83,88 +83,71 @@
 static const u32 div_tab[] = { 2000, 1000,  500,  250,  125 }; /* kHz */
 static const u8  ref_div[] = { 0x00, 0x01, 0x02, 0x05, 0x07 };
 
-static int tda8261_get_state(struct dvb_frontend *fe,
-			     enum tuner_param param,
-			     struct tuner_state *tstate)
+static int tda8261_get_frequency(struct dvb_frontend *fe, u32 *frequency)
 {
 	struct tda8261_state *state = fe->tuner_priv;
-	int err = 0;
 
-	switch (param) {
-	case DVBFE_TUNER_FREQUENCY:
-		tstate->frequency = state->frequency;
-		break;
-	case DVBFE_TUNER_BANDWIDTH:
-		tstate->bandwidth = 40000000; /* FIXME! need to calculate Bandwidth */
-		break;
-	default:
-		pr_err("%s: Unknown parameter (param=%d)\n", __func__, param);
-		err = -EINVAL;
-		break;
-	}
+	*frequency = state->frequency;
 
-	return err;
+	return 0;
 }
 
-static int tda8261_set_state(struct dvb_frontend *fe,
-			     enum tuner_param param,
-			     struct tuner_state *tstate)
+static int tda8261_set_params(struct dvb_frontend *fe)
 {
+	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	struct tda8261_state *state = fe->tuner_priv;
 	const struct tda8261_config *config = state->config;
 	u32 frequency, N, status = 0;
 	u8 buf[4];
 	int err = 0;
 
-	if (param & DVBFE_TUNER_FREQUENCY) {
-		/**
-		 * N = Max VCO Frequency / Channel Spacing
-		 * Max VCO Frequency = VCO frequency + (channel spacing - 1)
-		 * (to account for half channel spacing on either side)
-		 */
-		frequency = tstate->frequency;
-		if ((frequency < 950000) || (frequency > 2150000)) {
-			pr_warn("%s: Frequency beyond limits, frequency=%d\n", __func__, frequency);
-			return -EINVAL;
-		}
-		N = (frequency + (div_tab[config->step_size] - 1)) / div_tab[config->step_size];
-		pr_debug("%s: Step size=%d, Divider=%d, PG=0x%02x (%d)\n",
-			__func__, config->step_size, div_tab[config->step_size], N, N);
-
-		buf[0] = (N >> 8) & 0xff;
-		buf[1] = N & 0xff;
-		buf[2] = (0x01 << 7) | ((ref_div[config->step_size] & 0x07) << 1);
-
-		if (frequency < 1450000)
-			buf[3] = 0x00;
-		else if (frequency < 2000000)
-			buf[3] = 0x40;
-		else if (frequency < 2150000)
-			buf[3] = 0x80;
-
-		/* Set params */
-		if ((err = tda8261_write(state, buf)) < 0) {
-			pr_err("%s: I/O Error\n", __func__);
-			return err;
-		}
-		/* sleep for some time */
-		pr_debug("%s: Waiting to Phase LOCK\n", __func__);
-		msleep(20);
-		/* check status */
-		if ((err = tda8261_get_status(fe, &status)) < 0) {
-			pr_err("%s: I/O Error\n", __func__);
-			return err;
-		}
-		if (status == 1) {
-			pr_debug("%s: Tuner Phase locked: status=%d\n", __func__, status);
-			state->frequency = frequency; /* cache successful state */
-		} else {
-			pr_debug("%s: No Phase lock: status=%d\n", __func__, status);
-		}
-	} else {
-		pr_err("%s: Unknown parameter (param=%d)\n", __func__, param);
+	/*
+	 * N = Max VCO Frequency / Channel Spacing
+	 * Max VCO Frequency = VCO frequency + (channel spacing - 1)
+	 * (to account for half channel spacing on either side)
+	 */
+	frequency = c->frequency;
+	if ((frequency < 950000) || (frequency > 2150000)) {
+		pr_warn("%s: Frequency beyond limits, frequency=%d\n",
+			__func__, frequency);
 		return -EINVAL;
 	}
+	N = (frequency + (div_tab[config->step_size] - 1)) / div_tab[config->step_size];
+	pr_debug("%s: Step size=%d, Divider=%d, PG=0x%02x (%d)\n",
+		__func__, config->step_size, div_tab[config->step_size], N, N);
+
+	buf[0] = (N >> 8) & 0xff;
+	buf[1] = N & 0xff;
+	buf[2] = (0x01 << 7) | ((ref_div[config->step_size] & 0x07) << 1);
+
+	if (frequency < 1450000)
+		buf[3] = 0x00;
+	else if (frequency < 2000000)
+		buf[3] = 0x40;
+	else if (frequency < 2150000)
+		buf[3] = 0x80;
+
+	/* Set params */
+	err = tda8261_write(state, buf);
+	if (err < 0) {
+		pr_err("%s: I/O Error\n", __func__);
+		return err;
+	}
+	/* sleep for some time */
+	pr_debug("%s: Waiting to Phase LOCK\n", __func__);
+	msleep(20);
+	/* check status */
+	if ((err = tda8261_get_status(fe, &status)) < 0) {
+		pr_err("%s: I/O Error\n", __func__);
+		return err;
+	}
+	if (status == 1) {
+		pr_debug("%s: Tuner Phase locked: status=%d\n", __func__,
+			 status);
+		state->frequency = frequency; /* cache successful state */
+	} else {
+		pr_debug("%s: No Phase lock: status=%d\n", __func__, status);
+	}
 
 	return 0;
 }
@@ -182,14 +165,13 @@
 
 	.info = {
 		.name		= "TDA8261",
-//		.tuner_name	= NULL,
 		.frequency_min	=  950000,
 		.frequency_max	= 2150000,
 		.frequency_step = 0
 	},
 
-	.set_state	= tda8261_set_state,
-	.get_state	= tda8261_get_state,
+	.set_params	= tda8261_set_params,
+	.get_frequency	= tda8261_get_frequency,
 	.get_status	= tda8261_get_status,
 	.release	= tda8261_release
 };
@@ -210,10 +192,7 @@
 	fe->ops.tuner_ops	= tda8261_ops;
 
 	fe->ops.tuner_ops.info.frequency_step = div_tab[config->step_size];
-//	fe->ops.tuner_ops.tuner_name	 = &config->buf;
 
-//	printk("%s: Attaching %s TDA8261 8PSK/QPSK tuner\n",
-//		__func__, fe->ops.tuner_ops.tuner_name);
 	pr_info("%s: Attaching TDA8261 8PSK/QPSK tuner\n", __func__);
 
 	return fe;
diff --git a/drivers/media/dvb-frontends/tda8261_cfg.h b/drivers/media/dvb-frontends/tda8261_cfg.h
index 04a19e1..fe527ff 100644
--- a/drivers/media/dvb-frontends/tda8261_cfg.h
+++ b/drivers/media/dvb-frontends/tda8261_cfg.h
@@ -21,17 +21,15 @@
 {
 	struct dvb_frontend_ops	*frontend_ops = &fe->ops;
 	struct dvb_tuner_ops	*tuner_ops = &frontend_ops->tuner_ops;
-	struct tuner_state	t_state;
 	int err = 0;
 
-	if (tuner_ops->get_state) {
-		err = tuner_ops->get_state(fe, DVBFE_TUNER_FREQUENCY, &t_state);
+	if (tuner_ops->get_frequency) {
+		err = tuner_ops->get_frequency(fe, frequency);
 		if (err < 0) {
-			printk("%s: Invalid parameter\n", __func__);
+			pr_err("%s: Invalid parameter\n", __func__);
 			return err;
 		}
-		*frequency = t_state.frequency;
-		printk("%s: Frequency=%d\n", __func__, t_state.frequency);
+		pr_debug("%s: Frequency=%d\n", __func__, *frequency);
 	}
 	return 0;
 }
@@ -40,37 +38,24 @@
 {
 	struct dvb_frontend_ops	*frontend_ops = &fe->ops;
 	struct dvb_tuner_ops	*tuner_ops = &frontend_ops->tuner_ops;
-	struct tuner_state	t_state;
+	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	int err = 0;
 
-	t_state.frequency = frequency;
-
-	if (tuner_ops->set_state) {
-		err = tuner_ops->set_state(fe, DVBFE_TUNER_FREQUENCY, &t_state);
+	if (tuner_ops->set_params) {
+		err = tuner_ops->set_params(fe);
 		if (err < 0) {
-			printk("%s: Invalid parameter\n", __func__);
+			pr_err("%s: Invalid parameter\n", __func__);
 			return err;
 		}
 	}
-	printk("%s: Frequency=%d\n", __func__, t_state.frequency);
+	pr_debug("%s: Frequency=%d\n", __func__, c->frequency);
 	return 0;
 }
 
 static int tda8261_get_bandwidth(struct dvb_frontend *fe, u32 *bandwidth)
 {
-	struct dvb_frontend_ops	*frontend_ops = &fe->ops;
-	struct dvb_tuner_ops	*tuner_ops = &frontend_ops->tuner_ops;
-	struct tuner_state	t_state;
-	int err = 0;
+	/* FIXME! need to calculate Bandwidth */
+	*bandwidth = 40000000;
 
-	if (tuner_ops->get_state) {
-		err = tuner_ops->get_state(fe, DVBFE_TUNER_BANDWIDTH, &t_state);
-		if (err < 0) {
-			printk("%s: Invalid parameter\n", __func__);
-			return err;
-		}
-		*bandwidth = t_state.bandwidth;
-		printk("%s: Bandwidth=%d\n", __func__, t_state.bandwidth);
-	}
 	return 0;
 }
diff --git a/drivers/media/dvb-frontends/tdhd1.h b/drivers/media/dvb-frontends/tdhd1.h
index 1775098..2b9e873 100644
--- a/drivers/media/dvb-frontends/tdhd1.h
+++ b/drivers/media/dvb-frontends/tdhd1.h
@@ -20,7 +20,7 @@
  * Or, point your browser to http://www.gnu.org/copyleft/gpl.html
  *
  *
- * The project's page is at http://www.linuxtv.org
+ * The project's page is at https://linuxtv.org
  */
 
 #ifndef TDHD1_H
diff --git a/drivers/media/i2c/Kconfig b/drivers/media/i2c/Kconfig
index 521bbf1..993dc50 100644
--- a/drivers/media/i2c/Kconfig
+++ b/drivers/media/i2c/Kconfig
@@ -83,6 +83,16 @@
 	  To compile this driver as a module, choose M here: the
 	  module will be called msp3400.
 
+config VIDEO_CS3308
+	tristate "Cirrus Logic CS3308 audio ADC"
+	depends on VIDEO_V4L2 && I2C
+	---help---
+	  Support for the Cirrus Logic CS3308 High Performance 8-Channel
+	  Analog Volume Control
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called cs3308.
+
 config VIDEO_CS5345
 	tristate "Cirrus Logic CS5345 audio ADC"
 	depends on VIDEO_V4L2 && I2C
diff --git a/drivers/media/i2c/Makefile b/drivers/media/i2c/Makefile
index 07db257..94f2c99 100644
--- a/drivers/media/i2c/Makefile
+++ b/drivers/media/i2c/Makefile
@@ -43,6 +43,7 @@
 obj-$(CONFIG_VIDEO_TW2804) += tw2804.o
 obj-$(CONFIG_VIDEO_TW9903) += tw9903.o
 obj-$(CONFIG_VIDEO_TW9906) += tw9906.o
+obj-$(CONFIG_VIDEO_CS3308) += cs3308.o
 obj-$(CONFIG_VIDEO_CS5345) += cs5345.o
 obj-$(CONFIG_VIDEO_CS53L32A) += cs53l32a.o
 obj-$(CONFIG_VIDEO_M52790) += m52790.o
diff --git a/drivers/media/i2c/ad9389b.c b/drivers/media/i2c/ad9389b.c
index 69094ab..0494a78 100644
--- a/drivers/media/i2c/ad9389b.c
+++ b/drivers/media/i2c/ad9389b.c
@@ -35,7 +35,7 @@
 #include <media/v4l2-common.h>
 #include <media/v4l2-dv-timings.h>
 #include <media/v4l2-ctrls.h>
-#include <media/ad9389b.h>
+#include <media/i2c/ad9389b.h>
 
 static int debug;
 module_param(debug, int, 0644);
diff --git a/drivers/media/i2c/adp1653.c b/drivers/media/i2c/adp1653.c
index 5dd3977..f00745b 100644
--- a/drivers/media/i2c/adp1653.c
+++ b/drivers/media/i2c/adp1653.c
@@ -37,7 +37,7 @@
 #include <linux/slab.h>
 #include <linux/of.h>
 #include <linux/gpio/consumer.h>
-#include <media/adp1653.h>
+#include <media/i2c/adp1653.h>
 #include <media/v4l2-device.h>
 
 #define TIMEOUT_MAX		820000
diff --git a/drivers/media/i2c/adv7180.c b/drivers/media/i2c/adv7180.c
index f82c8aa..3c3c4bf 100644
--- a/drivers/media/i2c/adv7180.c
+++ b/drivers/media/i2c/adv7180.c
@@ -1112,7 +1112,7 @@
 	mutex_lock(&state->mutex);
 
 	adv7180_write(state, ADV7180_REG_PWR_MAN, ADV7180_PWR_MAN_RES);
-	usleep_range(2000, 10000);
+	usleep_range(5000, 10000);
 
 	ret = state->chip_info->init(state);
 	if (ret)
diff --git a/drivers/media/i2c/adv7183.c b/drivers/media/i2c/adv7183.c
index e2dd161..2bec737 100644
--- a/drivers/media/i2c/adv7183.c
+++ b/drivers/media/i2c/adv7183.c
@@ -27,7 +27,7 @@
 #include <linux/types.h>
 #include <linux/videodev2.h>
 
-#include <media/adv7183.h>
+#include <media/i2c/adv7183.h>
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-device.h>
 
diff --git a/drivers/media/i2c/adv7343.c b/drivers/media/i2c/adv7343.c
index f89d0af..11f9029 100644
--- a/drivers/media/i2c/adv7343.c
+++ b/drivers/media/i2c/adv7343.c
@@ -28,7 +28,7 @@
 #include <linux/of.h>
 #include <linux/of_graph.h>
 
-#include <media/adv7343.h>
+#include <media/i2c/adv7343.h>
 #include <media/v4l2-async.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-ctrls.h>
diff --git a/drivers/media/i2c/adv7393.c b/drivers/media/i2c/adv7393.c
index 0215f95..76d9874 100644
--- a/drivers/media/i2c/adv7393.c
+++ b/drivers/media/i2c/adv7393.c
@@ -31,7 +31,7 @@
 #include <linux/videodev2.h>
 #include <linux/uaccess.h>
 
-#include <media/adv7393.h>
+#include <media/i2c/adv7393.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-ctrls.h>
 
diff --git a/drivers/media/i2c/adv7511.c b/drivers/media/i2c/adv7511.c
index e4900df..eeb2cd8 100644
--- a/drivers/media/i2c/adv7511.c
+++ b/drivers/media/i2c/adv7511.c
@@ -32,7 +32,7 @@
 #include <media/v4l2-common.h>
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-dv-timings.h>
-#include <media/adv7511.h>
+#include <media/i2c/adv7511.h>
 
 static int debug;
 module_param(debug, int, 0644);
@@ -1116,7 +1116,7 @@
 	adv7511_wr_and_or(sd, 0x55, 0x9f, y << 5);
 	adv7511_wr_and_or(sd, 0x56, 0x3f, c << 6);
 	adv7511_wr_and_or(sd, 0x57, 0x83, (ec << 4) | (q << 2));
-	adv7511_wr_and_or(sd, 0x59, 0x0f, yq << 4);
+	adv7511_wr_and_or(sd, 0x59, 0x3f, yq << 6);
 	adv7511_wr_and_or(sd, 0x4a, 0xff, 1);
 
 	return 0;
diff --git a/drivers/media/i2c/adv7604.c b/drivers/media/i2c/adv7604.c
index 5631ec0..7452862 100644
--- a/drivers/media/i2c/adv7604.c
+++ b/drivers/media/i2c/adv7604.c
@@ -39,7 +39,7 @@
 #include <linux/workqueue.h>
 #include <linux/regmap.h>
 
-#include <media/adv7604.h>
+#include <media/i2c/adv7604.h>
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-event.h>
@@ -905,7 +905,7 @@
 
 	for (i = 0; predef_vid_timings[i].timings.bt.width; i++) {
 		if (!v4l2_match_dv_timings(timings, &predef_vid_timings[i].timings,
-					is_digital_input(sd) ? 250000 : 1000000))
+				is_digital_input(sd) ? 250000 : 1000000, false))
 			continue;
 		io_write(sd, 0x00, predef_vid_timings[i].vid_std); /* video std */
 		io_write(sd, 0x01, (predef_vid_timings[i].v_freq << 4) +
@@ -1479,7 +1479,7 @@
 
 	for (i = 0; adv76xx_timings[i].bt.width; i++) {
 		if (v4l2_match_dv_timings(timings, &adv76xx_timings[i],
-					is_digital_input(sd) ? 250000 : 1000000)) {
+				is_digital_input(sd) ? 250000 : 1000000, false)) {
 			*timings = adv76xx_timings[i];
 			break;
 		}
@@ -1644,7 +1644,7 @@
 	if (!timings)
 		return -EINVAL;
 
-	if (v4l2_match_dv_timings(&state->timings, timings, 0)) {
+	if (v4l2_match_dv_timings(&state->timings, timings, 0, false)) {
 		v4l2_dbg(1, debug, sd, "%s: no change\n", __func__);
 		return 0;
 	}
diff --git a/drivers/media/i2c/adv7842.c b/drivers/media/i2c/adv7842.c
index b7269b8..69378e4 100644
--- a/drivers/media/i2c/adv7842.c
+++ b/drivers/media/i2c/adv7842.c
@@ -43,7 +43,7 @@
 #include <media/v4l2-event.h>
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-dv-timings.h>
-#include <media/adv7842.h>
+#include <media/i2c/adv7842.h>
 
 static int debug;
 module_param(debug, int, 0644);
@@ -155,7 +155,7 @@
 	int i;
 
 	for (i = 0; adv7842_timings_exceptions[i].bt.width; i++)
-		if (v4l2_match_dv_timings(t, adv7842_timings_exceptions + i, 0))
+		if (v4l2_match_dv_timings(t, adv7842_timings_exceptions + i, 0, false))
 			return false;
 	return true;
 }
@@ -1008,7 +1008,7 @@
 
 	for (i = 0; predef_vid_timings[i].timings.bt.width; i++) {
 		if (!v4l2_match_dv_timings(timings, &predef_vid_timings[i].timings,
-					  is_digital_input(sd) ? 250000 : 1000000))
+				  is_digital_input(sd) ? 250000 : 1000000, false))
 			continue;
 		/* video std */
 		io_write(sd, 0x00, predef_vid_timings[i].vid_std);
@@ -1659,7 +1659,7 @@
 	if (state->mode == ADV7842_MODE_SDP)
 		return -ENODATA;
 
-	if (v4l2_match_dv_timings(&state->timings, timings, 0)) {
+	if (v4l2_match_dv_timings(&state->timings, timings, 0, false)) {
 		v4l2_dbg(1, debug, sd, "%s: no change\n", __func__);
 		return 0;
 	}
diff --git a/drivers/media/i2c/ak881x.c b/drivers/media/i2c/ak881x.c
index d3b965e..d9f2b6b 100644
--- a/drivers/media/i2c/ak881x.c
+++ b/drivers/media/i2c/ak881x.c
@@ -15,7 +15,7 @@
 #include <linux/videodev2.h>
 #include <linux/module.h>
 
-#include <media/ak881x.h>
+#include <media/i2c/ak881x.h>
 #include <media/v4l2-common.h>
 #include <media/v4l2-device.h>
 
diff --git a/drivers/media/i2c/as3645a.c b/drivers/media/i2c/as3645a.c
index 301084b..29a2e70 100644
--- a/drivers/media/i2c/as3645a.c
+++ b/drivers/media/i2c/as3645a.c
@@ -31,7 +31,7 @@
 #include <linux/mutex.h>
 #include <linux/slab.h>
 
-#include <media/as3645a.h>
+#include <media/i2c/as3645a.h>
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-device.h>
 
diff --git a/drivers/media/i2c/bt819.c b/drivers/media/i2c/bt819.c
index e00e310..7907bcf 100644
--- a/drivers/media/i2c/bt819.c
+++ b/drivers/media/i2c/bt819.c
@@ -37,7 +37,7 @@
 #include <linux/slab.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-ctrls.h>
-#include <media/bt819.h>
+#include <media/i2c/bt819.h>
 
 MODULE_DESCRIPTION("Brooktree-819 video decoder driver");
 MODULE_AUTHOR("Mike Bernson & Dave Perks");
diff --git a/drivers/media/i2c/cs3308.c b/drivers/media/i2c/cs3308.c
new file mode 100644
index 0000000..d28b4f3
--- /dev/null
+++ b/drivers/media/i2c/cs3308.c
@@ -0,0 +1,138 @@
+/*
+ * Cirrus Logic cs3308 8-Channel Analog Volume Control
+ *
+ * Copyright (C) 2010 Devin Heitmueller <dheitmueller@kernellabs.com>
+ * Copyright (C) 2012 Steven Toth <stoth@kernellabs.com>
+ *
+ * Derived from cs5345.c Copyright (C) 2007 Hans Verkuil
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/i2c.h>
+#include <linux/slab.h>
+#include <linux/videodev2.h>
+#include <media/v4l2-device.h>
+
+MODULE_DESCRIPTION("i2c device driver for cs3308 8-channel volume control");
+MODULE_AUTHOR("Devin Heitmueller");
+MODULE_LICENSE("GPL");
+
+static inline int cs3308_write(struct v4l2_subdev *sd, u8 reg, u8 value)
+{
+	struct i2c_client *client = v4l2_get_subdevdata(sd);
+
+	return i2c_smbus_write_byte_data(client, reg, value);
+}
+
+static inline int cs3308_read(struct v4l2_subdev *sd, u8 reg)
+{
+	struct i2c_client *client = v4l2_get_subdevdata(sd);
+
+	return i2c_smbus_read_byte_data(client, reg);
+}
+
+#ifdef CONFIG_VIDEO_ADV_DEBUG
+static int cs3308_g_register(struct v4l2_subdev *sd, struct v4l2_dbg_register *reg)
+{
+	reg->val = cs3308_read(sd, reg->reg & 0xffff);
+	reg->size = 1;
+	return 0;
+}
+
+static int cs3308_s_register(struct v4l2_subdev *sd, const struct v4l2_dbg_register *reg)
+{
+	cs3308_write(sd, reg->reg & 0xffff, reg->val & 0xff);
+	return 0;
+}
+#endif
+
+/* ----------------------------------------------------------------------- */
+
+static const struct v4l2_subdev_core_ops cs3308_core_ops = {
+#ifdef CONFIG_VIDEO_ADV_DEBUG
+	.g_register = cs3308_g_register,
+	.s_register = cs3308_s_register,
+#endif
+};
+
+static const struct v4l2_subdev_ops cs3308_ops = {
+	.core = &cs3308_core_ops,
+};
+
+/* ----------------------------------------------------------------------- */
+
+static int cs3308_probe(struct i2c_client *client,
+			const struct i2c_device_id *id)
+{
+	struct v4l2_subdev *sd;
+	unsigned i;
+
+	/* Check if the adapter supports the needed features */
+	if (!i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_BYTE_DATA))
+		return -EIO;
+
+	if ((i2c_smbus_read_byte_data(client, 0x1c) & 0xf0) != 0xe0)
+		return -ENODEV;
+
+	v4l_info(client, "chip found @ 0x%x (%s)\n",
+		 client->addr << 1, client->adapter->name);
+
+	sd = kzalloc(sizeof(struct v4l2_subdev), GFP_KERNEL);
+	if (sd == NULL)
+		return -ENOMEM;
+
+	v4l2_i2c_subdev_init(sd, client, &cs3308_ops);
+
+	/* Set some reasonable defaults */
+	cs3308_write(sd, 0x0d, 0x00); /* Power up all channels */
+	cs3308_write(sd, 0x0e, 0x00); /* Master Power */
+	cs3308_write(sd, 0x0b, 0x00); /* Device Configuration */
+	/* Set volume for each channel */
+	for (i = 1; i <= 8; i++)
+		cs3308_write(sd, i, 0xd2);
+	cs3308_write(sd, 0x0a, 0x00); /* Unmute all channels */
+	return 0;
+}
+
+/* ----------------------------------------------------------------------- */
+
+static int cs3308_remove(struct i2c_client *client)
+{
+	struct v4l2_subdev *sd = i2c_get_clientdata(client);
+
+	v4l2_device_unregister_subdev(sd);
+	kfree(sd);
+	return 0;
+}
+
+/* ----------------------------------------------------------------------- */
+
+static const struct i2c_device_id cs3308_id[] = {
+	{ "cs3308", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, cs3308_id);
+
+static struct i2c_driver cs3308_driver = {
+	.driver = {
+		.owner  = THIS_MODULE,
+		.name   = "cs3308",
+	},
+	.probe          = cs3308_probe,
+	.remove         = cs3308_remove,
+	.id_table       = cs3308_id,
+};
+
+module_i2c_driver(cs3308_driver);
diff --git a/drivers/media/i2c/cx25840/cx25840-audio.c b/drivers/media/i2c/cx25840/cx25840-audio.c
index 34b96c7..baf3d9c 100644
--- a/drivers/media/i2c/cx25840/cx25840-audio.c
+++ b/drivers/media/i2c/cx25840/cx25840-audio.c
@@ -19,7 +19,7 @@
 #include <linux/videodev2.h>
 #include <linux/i2c.h>
 #include <media/v4l2-common.h>
-#include <media/cx25840.h>
+#include <media/drv-intf/cx25840.h>
 
 #include "cx25840-core.h"
 
diff --git a/drivers/media/i2c/cx25840/cx25840-core.c b/drivers/media/i2c/cx25840/cx25840-core.c
index fe6eb78..f2e2c34 100644
--- a/drivers/media/i2c/cx25840/cx25840-core.c
+++ b/drivers/media/i2c/cx25840/cx25840-core.c
@@ -45,7 +45,7 @@
 #include <linux/delay.h>
 #include <linux/math64.h>
 #include <media/v4l2-common.h>
-#include <media/cx25840.h>
+#include <media/drv-intf/cx25840.h>
 
 #include "cx25840-core.h"
 
@@ -559,7 +559,10 @@
 	cx25840_write4(client, 0x414, 0x00107d12);
 
 	/* Chroma */
-	cx25840_write4(client, 0x420, 0x3d008282);
+	if (is_cx23888(state))
+		cx25840_write4(client, 0x418, 0x1d008282);
+	else
+		cx25840_write4(client, 0x420, 0x3d008282);
 
 	/*
 	 * Aux PLL
@@ -666,14 +669,17 @@
 	cx25840_write4(client, 0x404, 0x0010253e);
 
 	/* CC on  - Undocumented Register */
-	cx25840_write(client, 0x42f, 0x66);
+	cx25840_write(client, state->vbi_regs_offset + 0x42f, 0x66);
 
 	/* HVR-1250 / HVR1850 DIF related */
 	/* Power everything up */
 	cx25840_write4(client, 0x130, 0x0);
 
 	/* Undocumented */
-	cx25840_write4(client, 0x478, 0x6628021F);
+	if (is_cx23888(state))
+		cx25840_write4(client, 0x454, 0x6628021F);
+	else
+		cx25840_write4(client, 0x478, 0x6628021F);
 
 	/* AFE_CLK_OUT_CTRL - Select the clock output source as output */
 	cx25840_write4(client, 0x144, 0x5);
@@ -1106,31 +1112,15 @@
 			cx25840_write4(client, 0x410, 0xffff0dbf);
 			cx25840_write4(client, 0x414, 0x00137d03);
 
-			/* on the 887, 0x418 is HSCALE_CTRL, on the 888 it is 
-			   CHROMA_CTRL */
-			if (is_cx23888(state))
-				cx25840_write4(client, 0x418, 0x01008080);
-			else
-				cx25840_write4(client, 0x418, 0x01000000);
+			cx25840_write4(client, state->vbi_regs_offset + 0x42c, 0x42600000);
+			cx25840_write4(client, state->vbi_regs_offset + 0x430, 0x0000039b);
+			cx25840_write4(client, state->vbi_regs_offset + 0x438, 0x00000000);
 
-			cx25840_write4(client, 0x41c, 0x00000000);
-
-			/* on the 887, 0x420 is CHROMA_CTRL, on the 888 it is 
-			   CRUSH_CTRL */
-			if (is_cx23888(state))
-				cx25840_write4(client, 0x420, 0x001c3e0f);
-			else
-				cx25840_write4(client, 0x420, 0x001c8282);
-
-			cx25840_write4(client, 0x42c, 0x42600000);
-			cx25840_write4(client, 0x430, 0x0000039b);
-			cx25840_write4(client, 0x438, 0x00000000);
-
-			cx25840_write4(client, 0x440, 0xF8E3E824);
-			cx25840_write4(client, 0x444, 0x401040dc);
-			cx25840_write4(client, 0x448, 0xcd3f02a0);
-			cx25840_write4(client, 0x44c, 0x161f1000);
-			cx25840_write4(client, 0x450, 0x00000802);
+			cx25840_write4(client, state->vbi_regs_offset + 0x440, 0xF8E3E824);
+			cx25840_write4(client, state->vbi_regs_offset + 0x444, 0x401040dc);
+			cx25840_write4(client, state->vbi_regs_offset + 0x448, 0xcd3f02a0);
+			cx25840_write4(client, state->vbi_regs_offset + 0x44c, 0x161f1000);
+			cx25840_write4(client, state->vbi_regs_offset + 0x450, 0x00000802);
 
 			cx25840_write4(client, 0x91c, 0x01000000);
 			cx25840_write4(client, 0x8e0, 0x03063870);
@@ -1400,8 +1390,14 @@
 
 	Vlines = fmt->height + (is_50Hz ? 4 : 7);
 
+	/*
+	 * We keep 1 margin for the Vsrc < Vlines check since the
+	 * cx23888 reports a Vsrc of 486 instead of 487 for the NTSC
+	 * height. Without that margin the cx23885 fails in this
+	 * check.
+	 */
 	if ((fmt->width * 16 < Hsrc) || (Hsrc < fmt->width) ||
-			(Vlines * 8 < Vsrc) || (Vsrc < Vlines)) {
+			(Vlines * 8 < Vsrc) || (Vsrc + 1 < Vlines)) {
 		v4l_err(client, "%dx%d is not a valid size!\n",
 				fmt->width, fmt->height);
 		return -ERANGE;
@@ -1426,14 +1422,20 @@
 			fmt->width, fmt->height, HSC, VSC);
 
 	/* HSCALE=HSC */
-	cx25840_write(client, 0x418, HSC & 0xff);
-	cx25840_write(client, 0x419, (HSC >> 8) & 0xff);
-	cx25840_write(client, 0x41a, HSC >> 16);
-	/* VSCALE=VSC */
-	cx25840_write(client, 0x41c, VSC & 0xff);
-	cx25840_write(client, 0x41d, VSC >> 8);
-	/* VS_INTRLACE=1 VFILT=filter */
-	cx25840_write(client, 0x41e, 0x8 | filter);
+	if (is_cx23888(state)) {
+		cx25840_write4(client, 0x434, HSC | (1 << 24));
+		/* VSCALE=VSC VS_INTRLACE=1 VFILT=filter */
+		cx25840_write4(client, 0x438, VSC | (1 << 19) | (filter << 16));
+	} else {
+		cx25840_write(client, 0x418, HSC & 0xff);
+		cx25840_write(client, 0x419, (HSC >> 8) & 0xff);
+		cx25840_write(client, 0x41a, HSC >> 16);
+		/* VSCALE=VSC */
+		cx25840_write(client, 0x41c, VSC & 0xff);
+		cx25840_write(client, 0x41d, VSC >> 8);
+		/* VS_INTRLACE=1 VFILT=filter */
+		cx25840_write(client, 0x41e, 0x8 | filter);
+	}
 	return 0;
 }
 
@@ -1714,26 +1716,27 @@
 
 	v4l_dbg(1, cx25840_debug, client, "%s video output\n",
 			enable ? "enable" : "disable");
+
+	/*
+	 * It's not clear what should be done for these devices.
+	 * The original code used the same addresses as for the cx25840, but
+	 * those addresses do something else entirely on the cx2388x and
+	 * cx231xx. Since it never did anything in the first place, just do
+	 * nothing.
+	 */
+	if (is_cx2388x(state) || is_cx231xx(state))
+		return 0;
+
 	if (enable) {
-		if (is_cx2388x(state) || is_cx231xx(state)) {
-			v = cx25840_read(client, 0x421) | 0x0b;
-			cx25840_write(client, 0x421, v);
-		} else {
-			v = cx25840_read(client, 0x115) | 0x0c;
-			cx25840_write(client, 0x115, v);
-			v = cx25840_read(client, 0x116) | 0x04;
-			cx25840_write(client, 0x116, v);
-		}
+		v = cx25840_read(client, 0x115) | 0x0c;
+		cx25840_write(client, 0x115, v);
+		v = cx25840_read(client, 0x116) | 0x04;
+		cx25840_write(client, 0x116, v);
 	} else {
-		if (is_cx2388x(state) || is_cx231xx(state)) {
-			v = cx25840_read(client, 0x421) & ~(0x0b);
-			cx25840_write(client, 0x421, v);
-		} else {
-			v = cx25840_read(client, 0x115) & ~(0x0c);
-			cx25840_write(client, 0x115, v);
-			v = cx25840_read(client, 0x116) & ~(0x04);
-			cx25840_write(client, 0x116, v);
-		}
+		v = cx25840_read(client, 0x115) & ~(0x0c);
+		cx25840_write(client, 0x115, v);
+		v = cx25840_read(client, 0x116) & ~(0x04);
+		cx25840_write(client, 0x116, v);
 	}
 	return 0;
 }
@@ -4974,7 +4977,7 @@
 	cx25840_write4(client, 0x4b4, 0x20524030);
 	cx25840_write4(client, 0x47c, 0x010a8263);
 
-	if (std & V4L2_STD_NTSC) {
+	if (std & V4L2_STD_525_60) {
 		v4l_dbg(1, cx25840_debug, client, "%s() Selecting NTSC",
 			__func__);
 
@@ -5264,6 +5267,8 @@
 	state->vbi_line_offset = 8;
 	state->id = id;
 	state->rev = device_id;
+	state->vbi_regs_offset = id == CX23888_AV ? 0x500 - 0x424 : 0;
+	state->std = V4L2_STD_NTSC_M;
 	v4l2_ctrl_handler_init(&state->hdl, 9);
 	v4l2_ctrl_new_std(&state->hdl, &cx25840_ctrl_ops,
 			V4L2_CID_BRIGHTNESS, 0, 255, 1, 128);
diff --git a/drivers/media/i2c/cx25840/cx25840-core.h b/drivers/media/i2c/cx25840/cx25840-core.h
index fdea48c..254ef45 100644
--- a/drivers/media/i2c/cx25840/cx25840-core.h
+++ b/drivers/media/i2c/cx25840/cx25840-core.h
@@ -69,6 +69,7 @@
 	enum cx25840_model id;
 	u32 rev;
 	int is_initialized;
+	unsigned vbi_regs_offset;
 	wait_queue_head_t fw_wait;    /* wake up when the fw load is finished */
 	struct work_struct fw_work;   /* work entry for fw load */
 	struct cx25840_ir_state *ir_state;
diff --git a/drivers/media/i2c/cx25840/cx25840-firmware.c b/drivers/media/i2c/cx25840/cx25840-firmware.c
index 9bbb31a..37e05292 100644
--- a/drivers/media/i2c/cx25840/cx25840-firmware.c
+++ b/drivers/media/i2c/cx25840/cx25840-firmware.c
@@ -19,7 +19,7 @@
 #include <linux/i2c.h>
 #include <linux/firmware.h>
 #include <media/v4l2-common.h>
-#include <media/cx25840.h>
+#include <media/drv-intf/cx25840.h>
 
 #include "cx25840-core.h"
 
diff --git a/drivers/media/i2c/cx25840/cx25840-ir.c b/drivers/media/i2c/cx25840/cx25840-ir.c
index 4cf8f18..4b78201 100644
--- a/drivers/media/i2c/cx25840/cx25840-ir.c
+++ b/drivers/media/i2c/cx25840/cx25840-ir.c
@@ -24,7 +24,7 @@
 #include <linux/slab.h>
 #include <linux/kfifo.h>
 #include <linux/module.h>
-#include <media/cx25840.h>
+#include <media/drv-intf/cx25840.h>
 #include <media/rc-core.h>
 
 #include "cx25840-core.h"
diff --git a/drivers/media/i2c/cx25840/cx25840-vbi.c b/drivers/media/i2c/cx25840/cx25840-vbi.c
index c39e91d..0470bb6 100644
--- a/drivers/media/i2c/cx25840/cx25840-vbi.c
+++ b/drivers/media/i2c/cx25840/cx25840-vbi.c
@@ -19,7 +19,7 @@
 #include <linux/videodev2.h>
 #include <linux/i2c.h>
 #include <media/v4l2-common.h>
-#include <media/cx25840.h>
+#include <media/drv-intf/cx25840.h>
 
 #include "cx25840-core.h"
 
@@ -104,7 +104,8 @@
 
 	if (is_pal) {
 		for (i = 7; i <= 23; i++) {
-			u8 v = cx25840_read(client, 0x424 + i - 7);
+			u8 v = cx25840_read(client,
+				 state->vbi_regs_offset + 0x424 + i - 7);
 
 			svbi->service_lines[0][i] = lcr2vbi[v >> 4];
 			svbi->service_lines[1][i] = lcr2vbi[v & 0xf];
@@ -113,7 +114,8 @@
 		}
 	} else {
 		for (i = 10; i <= 21; i++) {
-			u8 v = cx25840_read(client, 0x424 + i - 10);
+			u8 v = cx25840_read(client,
+				state->vbi_regs_offset + 0x424 + i - 10);
 
 			svbi->service_lines[0][i] = lcr2vbi[v >> 4];
 			svbi->service_lines[1][i] = lcr2vbi[v & 0xf];
@@ -135,7 +137,10 @@
 	cx25840_std_setup(client);
 
 	/* VBI Offset */
-	cx25840_write(client, 0x47f, vbi_offset);
+	if (is_cx23888(state))
+		cx25840_write(client, 0x54f, vbi_offset);
+	else
+		cx25840_write(client, 0x47f, vbi_offset);
 	cx25840_write(client, 0x404, 0x2e);
 	return 0;
 }
@@ -158,7 +163,10 @@
 	/* Sliced VBI */
 	cx25840_write(client, 0x404, 0x32);	/* Ancillary data */
 	cx25840_write(client, 0x406, 0x13);
-	cx25840_write(client, 0x47f, vbi_offset);
+	if (is_cx23888(state))
+		cx25840_write(client, 0x54f, vbi_offset);
+	else
+		cx25840_write(client, 0x47f, vbi_offset);
 
 	if (is_pal) {
 		for (i = 0; i <= 6; i++)
@@ -194,17 +202,23 @@
 	}
 
 	if (is_pal) {
-		for (x = 1, i = 0x424; i <= 0x434; i++, x++)
+		for (x = 1, i = state->vbi_regs_offset + 0x424;
+		     i <= state->vbi_regs_offset + 0x434; i++, x++)
 			cx25840_write(client, i, lcr[6 + x]);
 	} else {
-		for (x = 1, i = 0x424; i <= 0x430; i++, x++)
+		for (x = 1, i = state->vbi_regs_offset + 0x424;
+		     i <= state->vbi_regs_offset + 0x430; i++, x++)
 			cx25840_write(client, i, lcr[9 + x]);
-		for (i = 0x431; i <= 0x434; i++)
+		for (i = state->vbi_regs_offset + 0x431;
+		     i <= state->vbi_regs_offset + 0x434; i++)
 			cx25840_write(client, i, 0);
 	}
 
-	cx25840_write(client, 0x43c, 0x16);
-	cx25840_write(client, 0x474, is_pal ? 0x2a : 0x22);
+	cx25840_write(client, state->vbi_regs_offset + 0x43c, 0x16);
+	if (is_cx23888(state))
+		cx25840_write(client, 0x428, is_pal ? 0x2a : 0x22);
+	else
+		cx25840_write(client, 0x474, is_pal ? 0x2a : 0x22);
 	return 0;
 }
 
diff --git a/drivers/media/i2c/ir-kbd-i2c.c b/drivers/media/i2c/ir-kbd-i2c.c
index 728d2cc..8304919 100644
--- a/drivers/media/i2c/ir-kbd-i2c.c
+++ b/drivers/media/i2c/ir-kbd-i2c.c
@@ -47,7 +47,7 @@
 #include <linux/workqueue.h>
 
 #include <media/rc-core.h>
-#include <media/ir-kbd-i2c.h>
+#include <media/i2c/ir-kbd-i2c.h>
 
 /* ----------------------------------------------------------------------- */
 /* insmod parameters                                                       */
diff --git a/drivers/media/i2c/lm3560.c b/drivers/media/i2c/lm3560.c
index d9ece4b..19ecb88 100644
--- a/drivers/media/i2c/lm3560.c
+++ b/drivers/media/i2c/lm3560.c
@@ -24,7 +24,7 @@
 #include <linux/mutex.h>
 #include <linux/regmap.h>
 #include <linux/videodev2.h>
-#include <media/lm3560.h>
+#include <media/i2c/lm3560.h>
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-device.h>
 
diff --git a/drivers/media/i2c/lm3646.c b/drivers/media/i2c/lm3646.c
index 626fb46..7fbe6ff 100644
--- a/drivers/media/i2c/lm3646.c
+++ b/drivers/media/i2c/lm3646.c
@@ -18,7 +18,7 @@
 #include <linux/slab.h>
 #include <linux/regmap.h>
 #include <linux/videodev2.h>
-#include <media/lm3646.h>
+#include <media/i2c/lm3646.h>
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-device.h>
 
diff --git a/drivers/media/i2c/m52790.c b/drivers/media/i2c/m52790.c
index 77eb07e..81171d8 100644
--- a/drivers/media/i2c/m52790.c
+++ b/drivers/media/i2c/m52790.c
@@ -27,7 +27,7 @@
 #include <asm/uaccess.h>
 #include <linux/i2c.h>
 #include <linux/videodev2.h>
-#include <media/m52790.h>
+#include <media/i2c/m52790.h>
 #include <media/v4l2-device.h>
 
 MODULE_DESCRIPTION("i2c device driver for m52790 A/V switch");
diff --git a/drivers/media/i2c/m5mols/m5mols_capture.c b/drivers/media/i2c/m5mols/m5mols_capture.c
index 1a03d02..a0cd6dc 100644
--- a/drivers/media/i2c/m5mols/m5mols_capture.c
+++ b/drivers/media/i2c/m5mols/m5mols_capture.c
@@ -25,8 +25,8 @@
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-subdev.h>
-#include <media/m5mols.h>
-#include <media/exynos-fimc.h>
+#include <media/i2c/m5mols.h>
+#include <media/drv-intf/exynos-fimc.h>
 
 #include "m5mols.h"
 #include "m5mols_reg.h"
diff --git a/drivers/media/i2c/m5mols/m5mols_core.c b/drivers/media/i2c/m5mols/m5mols_core.c
index 6404c0d..f899393 100644
--- a/drivers/media/i2c/m5mols/m5mols_core.c
+++ b/drivers/media/i2c/m5mols/m5mols_core.c
@@ -25,7 +25,7 @@
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-subdev.h>
-#include <media/m5mols.h>
+#include <media/i2c/m5mols.h>
 
 #include "m5mols.h"
 #include "m5mols_reg.h"
diff --git a/drivers/media/i2c/msp3400-driver.c b/drivers/media/i2c/msp3400-driver.c
index bdb9400..a84561d 100644
--- a/drivers/media/i2c/msp3400-driver.c
+++ b/drivers/media/i2c/msp3400-driver.c
@@ -56,8 +56,8 @@
 #include <linux/videodev2.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-ioctl.h>
-#include <media/msp3400.h>
-#include <media/tvaudio.h>
+#include <media/drv-intf/msp3400.h>
+#include <media/i2c/tvaudio.h>
 #include "msp3400-driver.h"
 
 /* ---------------------------------------------------------------------- */
diff --git a/drivers/media/i2c/msp3400-driver.h b/drivers/media/i2c/msp3400-driver.h
index fbe5e07..6cae213 100644
--- a/drivers/media/i2c/msp3400-driver.h
+++ b/drivers/media/i2c/msp3400-driver.h
@@ -4,7 +4,7 @@
 #ifndef MSP3400_DRIVER_H
 #define MSP3400_DRIVER_H
 
-#include <media/msp3400.h>
+#include <media/drv-intf/msp3400.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-ctrls.h>
 
diff --git a/drivers/media/i2c/msp3400-kthreads.c b/drivers/media/i2c/msp3400-kthreads.c
index f8b5171..1712080 100644
--- a/drivers/media/i2c/msp3400-kthreads.c
+++ b/drivers/media/i2c/msp3400-kthreads.c
@@ -26,7 +26,7 @@
 #include <linux/freezer.h>
 #include <linux/videodev2.h>
 #include <media/v4l2-common.h>
-#include <media/msp3400.h>
+#include <media/drv-intf/msp3400.h>
 #include <linux/kthread.h>
 #include <linux/suspend.h>
 #include "msp3400-driver.h"
diff --git a/drivers/media/i2c/mt9m032.c b/drivers/media/i2c/mt9m032.c
index c7747bd0..101cb26 100644
--- a/drivers/media/i2c/mt9m032.c
+++ b/drivers/media/i2c/mt9m032.c
@@ -31,7 +31,7 @@
 #include <linux/v4l2-mediabus.h>
 
 #include <media/media-entity.h>
-#include <media/mt9m032.h>
+#include <media/i2c/mt9m032.h>
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-subdev.h>
@@ -671,7 +671,7 @@
 	return 0;
 }
 
-static struct v4l2_ctrl_ops mt9m032_ctrl_ops = {
+static const struct v4l2_ctrl_ops mt9m032_ctrl_ops = {
 	.s_ctrl = mt9m032_set_ctrl,
 	.try_ctrl = mt9m032_try_ctrl,
 };
diff --git a/drivers/media/i2c/mt9p031.c b/drivers/media/i2c/mt9p031.c
index 0db15f5..a3da0e9 100644
--- a/drivers/media/i2c/mt9p031.c
+++ b/drivers/media/i2c/mt9p031.c
@@ -26,7 +26,7 @@
 #include <linux/slab.h>
 #include <linux/videodev2.h>
 
-#include <media/mt9p031.h>
+#include <media/i2c/mt9p031.h>
 #include <media/v4l2-async.h>
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-device.h>
@@ -817,7 +817,7 @@
 	return 0;
 }
 
-static struct v4l2_ctrl_ops mt9p031_ctrl_ops = {
+static const struct v4l2_ctrl_ops mt9p031_ctrl_ops = {
 	.s_ctrl = mt9p031_s_ctrl,
 };
 
diff --git a/drivers/media/i2c/mt9t001.c b/drivers/media/i2c/mt9t001.c
index 8ae99f7..b28fdff 100644
--- a/drivers/media/i2c/mt9t001.c
+++ b/drivers/media/i2c/mt9t001.c
@@ -21,7 +21,7 @@
 #include <linux/videodev2.h>
 #include <linux/v4l2-mediabus.h>
 
-#include <media/mt9t001.h>
+#include <media/i2c/mt9t001.h>
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-subdev.h>
@@ -626,7 +626,7 @@
 	return 0;
 }
 
-static struct v4l2_ctrl_ops mt9t001_ctrl_ops = {
+static const struct v4l2_ctrl_ops mt9t001_ctrl_ops = {
 	.s_ctrl = mt9t001_s_ctrl,
 };
 
diff --git a/drivers/media/i2c/mt9v011.c b/drivers/media/i2c/mt9v011.c
index a4a5c39..b9fea11 100644
--- a/drivers/media/i2c/mt9v011.c
+++ b/drivers/media/i2c/mt9v011.c
@@ -13,7 +13,7 @@
 #include <asm/div64.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-ctrls.h>
-#include <media/mt9v011.h>
+#include <media/i2c/mt9v011.h>
 
 MODULE_DESCRIPTION("Micron mt9v011 sensor driver");
 MODULE_AUTHOR("Mauro Carvalho Chehab");
@@ -454,7 +454,7 @@
 	return 0;
 }
 
-static struct v4l2_ctrl_ops mt9v011_ctrl_ops = {
+static const struct v4l2_ctrl_ops mt9v011_ctrl_ops = {
 	.s_ctrl = mt9v011_s_ctrl,
 };
 
diff --git a/drivers/media/i2c/mt9v032.c b/drivers/media/i2c/mt9v032.c
index a68ce94..1dbbd23 100644
--- a/drivers/media/i2c/mt9v032.c
+++ b/drivers/media/i2c/mt9v032.c
@@ -25,7 +25,7 @@
 #include <linux/v4l2-mediabus.h>
 #include <linux/module.h>
 
-#include <media/mt9v032.h>
+#include <media/i2c/mt9v032.h>
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-of.h>
@@ -703,7 +703,7 @@
 	return 0;
 }
 
-static struct v4l2_ctrl_ops mt9v032_ctrl_ops = {
+static const struct v4l2_ctrl_ops mt9v032_ctrl_ops = {
 	.s_ctrl = mt9v032_s_ctrl,
 };
 
diff --git a/drivers/media/i2c/noon010pc30.c b/drivers/media/i2c/noon010pc30.c
index f197b6c..69e4f30 100644
--- a/drivers/media/i2c/noon010pc30.c
+++ b/drivers/media/i2c/noon010pc30.c
@@ -18,7 +18,7 @@
 #include <linux/i2c.h>
 #include <linux/slab.h>
 #include <linux/regulator/consumer.h>
-#include <media/noon010pc30.h>
+#include <media/i2c/noon010pc30.h>
 #include <linux/videodev2.h>
 #include <linux/module.h>
 #include <media/v4l2-ctrls.h>
diff --git a/drivers/media/i2c/ov2659.c b/drivers/media/i2c/ov2659.c
index 49109f4..82c7ac1 100644
--- a/drivers/media/i2c/ov2659.c
+++ b/drivers/media/i2c/ov2659.c
@@ -37,7 +37,7 @@
 #include <linux/videodev2.h>
 
 #include <media/media-entity.h>
-#include <media/ov2659.h>
+#include <media/i2c/ov2659.h>
 #include <media/v4l2-common.h>
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-device.h>
@@ -1249,7 +1249,7 @@
 	return 0;
 }
 
-static struct v4l2_ctrl_ops ov2659_ctrl_ops = {
+static const struct v4l2_ctrl_ops ov2659_ctrl_ops = {
 	.s_ctrl = ov2659_s_ctrl,
 };
 
diff --git a/drivers/media/i2c/ov7670.c b/drivers/media/i2c/ov7670.c
index e1b5dc8..56cfb5c 100644
--- a/drivers/media/i2c/ov7670.c
+++ b/drivers/media/i2c/ov7670.c
@@ -20,7 +20,7 @@
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-mediabus.h>
 #include <media/v4l2-image-sizes.h>
-#include <media/ov7670.h>
+#include <media/i2c/ov7670.h>
 
 MODULE_AUTHOR("Jonathan Corbet <corbet@lwn.net>");
 MODULE_DESCRIPTION("A low-level driver for OmniVision ov7670 sensors");
diff --git a/drivers/media/i2c/ov9650.c b/drivers/media/i2c/ov9650.c
index 1ee6a55..9fe9006 100644
--- a/drivers/media/i2c/ov9650.c
+++ b/drivers/media/i2c/ov9650.c
@@ -29,7 +29,7 @@
 #include <media/v4l2-image-sizes.h>
 #include <media/v4l2-subdev.h>
 #include <media/v4l2-mediabus.h>
-#include <media/ov9650.h>
+#include <media/i2c/ov9650.h>
 
 static int debug;
 module_param(debug, int, 0644);
diff --git a/drivers/media/i2c/s5c73m3/s5c73m3-core.c b/drivers/media/i2c/s5c73m3/s5c73m3-core.c
index 51b2601..25f5e79 100644
--- a/drivers/media/i2c/s5c73m3/s5c73m3-core.c
+++ b/drivers/media/i2c/s5c73m3/s5c73m3-core.c
@@ -34,7 +34,7 @@
 #include <media/v4l2-device.h>
 #include <media/v4l2-subdev.h>
 #include <media/v4l2-mediabus.h>
-#include <media/s5c73m3.h>
+#include <media/i2c/s5c73m3.h>
 #include <media/v4l2-of.h>
 
 #include "s5c73m3.h"
diff --git a/drivers/media/i2c/s5c73m3/s5c73m3-ctrls.c b/drivers/media/i2c/s5c73m3/s5c73m3-ctrls.c
index 8001cde..0a06033 100644
--- a/drivers/media/i2c/s5c73m3/s5c73m3-ctrls.c
+++ b/drivers/media/i2c/s5c73m3/s5c73m3-ctrls.c
@@ -32,7 +32,7 @@
 #include <media/v4l2-device.h>
 #include <media/v4l2-subdev.h>
 #include <media/v4l2-mediabus.h>
-#include <media/s5c73m3.h>
+#include <media/i2c/s5c73m3.h>
 
 #include "s5c73m3.h"
 
diff --git a/drivers/media/i2c/s5c73m3/s5c73m3-spi.c b/drivers/media/i2c/s5c73m3/s5c73m3-spi.c
index 72ef9f9..7d65b36 100644
--- a/drivers/media/i2c/s5c73m3/s5c73m3-spi.c
+++ b/drivers/media/i2c/s5c73m3/s5c73m3-spi.c
@@ -37,6 +37,7 @@
 	SPI_DIR_RX,
 	SPI_DIR_TX
 };
+MODULE_DEVICE_TABLE(of, s5c73m3_spi_ids);
 
 static int spi_xmit(struct spi_device *spi_dev, void *addr, const int len,
 							enum spi_direction dir)
diff --git a/drivers/media/i2c/s5c73m3/s5c73m3.h b/drivers/media/i2c/s5c73m3/s5c73m3.h
index 13aed59..653f68e 100644
--- a/drivers/media/i2c/s5c73m3/s5c73m3.h
+++ b/drivers/media/i2c/s5c73m3/s5c73m3.h
@@ -23,7 +23,7 @@
 #include <media/v4l2-common.h>
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-subdev.h>
-#include <media/s5c73m3.h>
+#include <media/i2c/s5c73m3.h>
 
 #define DRIVER_NAME			"S5C73M3"
 
diff --git a/drivers/media/i2c/s5k4ecgx.c b/drivers/media/i2c/s5k4ecgx.c
index 9708423..6757aca 100644
--- a/drivers/media/i2c/s5k4ecgx.c
+++ b/drivers/media/i2c/s5k4ecgx.c
@@ -27,7 +27,7 @@
 #include <asm/unaligned.h>
 
 #include <media/media-entity.h>
-#include <media/s5k4ecgx.h>
+#include <media/i2c/s5k4ecgx.h>
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-mediabus.h>
diff --git a/drivers/media/i2c/s5k6aa.c b/drivers/media/i2c/s5k6aa.c
index d0ad6a2..60aaff7 100644
--- a/drivers/media/i2c/s5k6aa.c
+++ b/drivers/media/i2c/s5k6aa.c
@@ -28,7 +28,7 @@
 #include <media/v4l2-device.h>
 #include <media/v4l2-subdev.h>
 #include <media/v4l2-mediabus.h>
-#include <media/s5k6aa.h>
+#include <media/i2c/s5k6aa.h>
 
 static int debug;
 module_param(debug, int, 0644);
diff --git a/drivers/media/i2c/saa6588.c b/drivers/media/i2c/saa6588.c
index 37e65f6..89e458c 100644
--- a/drivers/media/i2c/saa6588.c
+++ b/drivers/media/i2c/saa6588.c
@@ -31,7 +31,7 @@
 #include <linux/wait.h>
 #include <asm/uaccess.h>
 
-#include <media/saa6588.h>
+#include <media/i2c/saa6588.h>
 #include <media/v4l2-device.h>
 
 
diff --git a/drivers/media/i2c/saa7115.c b/drivers/media/i2c/saa7115.c
index 91e7522..24d2b76 100644
--- a/drivers/media/i2c/saa7115.c
+++ b/drivers/media/i2c/saa7115.c
@@ -46,7 +46,7 @@
 #include <linux/videodev2.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-ctrls.h>
-#include <media/saa7115.h>
+#include <media/i2c/saa7115.h>
 #include <asm/div64.h>
 
 #define VRES_60HZ	(480+16)
diff --git a/drivers/media/i2c/saa7127.c b/drivers/media/i2c/saa7127.c
index a43d96d..8d94dcb 100644
--- a/drivers/media/i2c/saa7127.c
+++ b/drivers/media/i2c/saa7127.c
@@ -54,7 +54,7 @@
 #include <linux/i2c.h>
 #include <linux/videodev2.h>
 #include <media/v4l2-device.h>
-#include <media/saa7127.h>
+#include <media/i2c/saa7127.h>
 
 static int debug;
 static int test_image;
diff --git a/drivers/media/i2c/smiapp/smiapp.h b/drivers/media/i2c/smiapp/smiapp.h
index ed010a8..f6af0cc 100644
--- a/drivers/media/i2c/smiapp/smiapp.h
+++ b/drivers/media/i2c/smiapp/smiapp.h
@@ -22,7 +22,7 @@
 #include <linux/mutex.h>
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-subdev.h>
-#include <media/smiapp.h>
+#include <media/i2c/smiapp.h>
 
 #include "smiapp-pll.h"
 #include "smiapp-reg.h"
diff --git a/drivers/media/i2c/soc_camera/mt9m001.c b/drivers/media/i2c/soc_camera/mt9m001.c
index 4fbdd1e..2e14e52 100644
--- a/drivers/media/i2c/soc_camera/mt9m001.c
+++ b/drivers/media/i2c/soc_camera/mt9m001.c
@@ -15,7 +15,7 @@
 #include <linux/module.h>
 
 #include <media/soc_camera.h>
-#include <media/soc_mediabus.h>
+#include <media/drv-intf/soc_mediabus.h>
 #include <media/v4l2-clk.h>
 #include <media/v4l2-subdev.h>
 #include <media/v4l2-ctrls.h>
diff --git a/drivers/media/i2c/soc_camera/mt9t112.c b/drivers/media/i2c/soc_camera/mt9t112.c
index 2f35d31..6a1b2a9 100644
--- a/drivers/media/i2c/soc_camera/mt9t112.c
+++ b/drivers/media/i2c/soc_camera/mt9t112.c
@@ -25,7 +25,7 @@
 #include <linux/v4l2-mediabus.h>
 #include <linux/videodev2.h>
 
-#include <media/mt9t112.h>
+#include <media/i2c/mt9t112.h>
 #include <media/soc_camera.h>
 #include <media/v4l2-clk.h>
 #include <media/v4l2-common.h>
diff --git a/drivers/media/i2c/soc_camera/mt9v022.c b/drivers/media/i2c/soc_camera/mt9v022.c
index f313774..c2ba1fb 100644
--- a/drivers/media/i2c/soc_camera/mt9v022.c
+++ b/drivers/media/i2c/soc_camera/mt9v022.c
@@ -15,9 +15,9 @@
 #include <linux/log2.h>
 #include <linux/module.h>
 
-#include <media/mt9v022.h>
+#include <media/i2c/mt9v022.h>
 #include <media/soc_camera.h>
-#include <media/soc_mediabus.h>
+#include <media/drv-intf/soc_mediabus.h>
 #include <media/v4l2-subdev.h>
 #include <media/v4l2-clk.h>
 #include <media/v4l2-ctrls.h>
diff --git a/drivers/media/i2c/soc_camera/ov772x.c b/drivers/media/i2c/soc_camera/ov772x.c
index f150a8b..a43410c 100644
--- a/drivers/media/i2c/soc_camera/ov772x.c
+++ b/drivers/media/i2c/soc_camera/ov772x.c
@@ -24,7 +24,7 @@
 #include <linux/v4l2-mediabus.h>
 #include <linux/videodev2.h>
 
-#include <media/ov772x.h>
+#include <media/i2c/ov772x.h>
 #include <media/soc_camera.h>
 #include <media/v4l2-clk.h>
 #include <media/v4l2-ctrls.h>
diff --git a/drivers/media/i2c/soc_camera/rj54n1cb0c.c b/drivers/media/i2c/soc_camera/rj54n1cb0c.c
index c769cf6..aa7bfbb 100644
--- a/drivers/media/i2c/soc_camera/rj54n1cb0c.c
+++ b/drivers/media/i2c/soc_camera/rj54n1cb0c.c
@@ -15,7 +15,7 @@
 #include <linux/videodev2.h>
 #include <linux/module.h>
 
-#include <media/rj54n1cb0c.h>
+#include <media/i2c/rj54n1cb0c.h>
 #include <media/soc_camera.h>
 #include <media/v4l2-clk.h>
 #include <media/v4l2-subdev.h>
diff --git a/drivers/media/i2c/soc_camera/tw9910.c b/drivers/media/i2c/soc_camera/tw9910.c
index e939c24..06aff81 100644
--- a/drivers/media/i2c/soc_camera/tw9910.c
+++ b/drivers/media/i2c/soc_camera/tw9910.c
@@ -26,7 +26,7 @@
 #include <linux/videodev2.h>
 
 #include <media/soc_camera.h>
-#include <media/tw9910.h>
+#include <media/i2c/tw9910.h>
 #include <media/v4l2-clk.h>
 #include <media/v4l2-subdev.h>
 
diff --git a/drivers/media/i2c/sr030pc30.c b/drivers/media/i2c/sr030pc30.c
index b04c09d..0bf031b 100644
--- a/drivers/media/i2c/sr030pc30.c
+++ b/drivers/media/i2c/sr030pc30.c
@@ -24,7 +24,7 @@
 #include <media/v4l2-subdev.h>
 #include <media/v4l2-mediabus.h>
 #include <media/v4l2-ctrls.h>
-#include <media/sr030pc30.h>
+#include <media/i2c/sr030pc30.h>
 
 static int debug;
 module_param(debug, int, 0644);
diff --git a/drivers/media/i2c/tc358743.c b/drivers/media/i2c/tc358743.c
index 9ef5baa..77b8011 100644
--- a/drivers/media/i2c/tc358743.c
+++ b/drivers/media/i2c/tc358743.c
@@ -42,7 +42,7 @@
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-event.h>
 #include <media/v4l2-of.h>
-#include <media/tc358743.h>
+#include <media/i2c/tc358743.h>
 
 #include "tc358743_regs.h"
 
@@ -862,7 +862,7 @@
 		v4l2_dbg(1, debug, sd, "%s: Format changed. No signal\n",
 				__func__);
 	} else {
-		if (!v4l2_match_dv_timings(&state->timings, &timings, 0))
+		if (!v4l2_match_dv_timings(&state->timings, &timings, 0, false))
 			enable_stream(sd, false);
 
 		v4l2_print_dv_timings(sd->name,
@@ -1366,7 +1366,7 @@
 		v4l2_print_dv_timings(sd->name, "tc358743_s_dv_timings: ",
 				timings, false);
 
-	if (v4l2_match_dv_timings(&state->timings, timings, 0)) {
+	if (v4l2_match_dv_timings(&state->timings, timings, 0, false)) {
 		v4l2_dbg(1, debug, sd, "%s: no change\n", __func__);
 		return 0;
 	}
diff --git a/drivers/media/i2c/ths7303.c b/drivers/media/i2c/ths7303.c
index bda3a65..5bbfcab 100644
--- a/drivers/media/i2c/ths7303.c
+++ b/drivers/media/i2c/ths7303.c
@@ -25,7 +25,7 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 
-#include <media/ths7303.h>
+#include <media/i2c/ths7303.h>
 #include <media/v4l2-device.h>
 
 #define THS7303_CHANNEL_1	1
diff --git a/drivers/media/i2c/tvaudio.c b/drivers/media/i2c/tvaudio.c
index 2a8114a..fece2a4 100644
--- a/drivers/media/i2c/tvaudio.c
+++ b/drivers/media/i2c/tvaudio.c
@@ -36,7 +36,7 @@
 #include <linux/kthread.h>
 #include <linux/freezer.h>
 
-#include <media/tvaudio.h>
+#include <media/i2c/tvaudio.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-ctrls.h>
 
diff --git a/drivers/media/i2c/tvp514x.c b/drivers/media/i2c/tvp514x.c
index a93985a..b5dba5b 100644
--- a/drivers/media/i2c/tvp514x.c
+++ b/drivers/media/i2c/tvp514x.c
@@ -44,7 +44,7 @@
 #include <media/v4l2-mediabus.h>
 #include <media/v4l2-of.h>
 #include <media/v4l2-ctrls.h>
-#include <media/tvp514x.h>
+#include <media/i2c/tvp514x.h>
 #include <media/media-entity.h>
 
 #include "tvp514x_regs.h"
diff --git a/drivers/media/i2c/tvp5150.c b/drivers/media/i2c/tvp5150.c
index 3c5fb25..6c3769d 100644
--- a/drivers/media/i2c/tvp5150.c
+++ b/drivers/media/i2c/tvp5150.c
@@ -12,7 +12,7 @@
 #include <linux/module.h>
 #include <media/v4l2-async.h>
 #include <media/v4l2-device.h>
-#include <media/tvp5150.h>
+#include <media/i2c/tvp5150.h>
 #include <media/v4l2-ctrls.h>
 
 #include "tvp5150_reg.h"
diff --git a/drivers/media/i2c/tvp7002.c b/drivers/media/i2c/tvp7002.c
index f617d8b..772a304 100644
--- a/drivers/media/i2c/tvp7002.c
+++ b/drivers/media/i2c/tvp7002.c
@@ -32,7 +32,7 @@
 #include <linux/of.h>
 #include <linux/of_graph.h>
 #include <linux/v4l2-dv-timings.h>
-#include <media/tvp7002.h>
+#include <media/i2c/tvp7002.h>
 #include <media/v4l2-async.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-common.h>
diff --git a/drivers/media/i2c/uda1342.c b/drivers/media/i2c/uda1342.c
index 081786d..8e17a83 100644
--- a/drivers/media/i2c/uda1342.c
+++ b/drivers/media/i2c/uda1342.c
@@ -20,7 +20,7 @@
 #include <linux/i2c.h>
 #include <linux/videodev2.h>
 #include <media/v4l2-device.h>
-#include <media/uda1342.h>
+#include <media/i2c/uda1342.h>
 #include <linux/slab.h>
 
 static int write_reg(struct i2c_client *client, int reg, int value)
diff --git a/drivers/media/i2c/upd64031a.c b/drivers/media/i2c/upd64031a.c
index 2c0f955..c03567e 100644
--- a/drivers/media/i2c/upd64031a.c
+++ b/drivers/media/i2c/upd64031a.c
@@ -27,7 +27,7 @@
 #include <linux/videodev2.h>
 #include <linux/slab.h>
 #include <media/v4l2-device.h>
-#include <media/upd64031a.h>
+#include <media/i2c/upd64031a.h>
 
 /* --------------------- read registers functions define -------------------- */
 
diff --git a/drivers/media/i2c/upd64083.c b/drivers/media/i2c/upd64083.c
index f2057a4..77f122f 100644
--- a/drivers/media/i2c/upd64083.c
+++ b/drivers/media/i2c/upd64083.c
@@ -27,7 +27,7 @@
 #include <linux/videodev2.h>
 #include <linux/slab.h>
 #include <media/v4l2-device.h>
-#include <media/upd64083.h>
+#include <media/i2c/upd64083.h>
 
 MODULE_DESCRIPTION("uPD64083 driver");
 MODULE_AUTHOR("T. Adachi, Takeru KOMORIYA, Hans Verkuil");
diff --git a/drivers/media/i2c/wm8775.c b/drivers/media/i2c/wm8775.c
index d33d2cd6..6e00f14 100644
--- a/drivers/media/i2c/wm8775.c
+++ b/drivers/media/i2c/wm8775.c
@@ -34,7 +34,7 @@
 #include <linux/videodev2.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-ctrls.h>
-#include <media/wm8775.h>
+#include <media/i2c/wm8775.h>
 
 MODULE_DESCRIPTION("wm8775 driver");
 MODULE_AUTHOR("Ulf Eklund, Hans Verkuil");
diff --git a/drivers/media/pci/bt8xx/bttv-cards.c b/drivers/media/pci/bt8xx/bttv-cards.c
index 4654fb6..8a17cc0 100644
--- a/drivers/media/pci/bt8xx/bttv-cards.c
+++ b/drivers/media/pci/bt8xx/bttv-cards.c
@@ -41,7 +41,7 @@
 
 #include "bttvp.h"
 #include <media/v4l2-common.h>
-#include <media/tvaudio.h>
+#include <media/i2c/tvaudio.h>
 #include "bttv-audio-hook.h"
 
 /* fwd decl */
@@ -3808,7 +3808,7 @@
 		gpio_inout(mask, (1 << gpio.clk) | (1 << gpio.wren));
 }
 
-static struct snd_tea575x_ops bttv_tea_ops = {
+static const struct snd_tea575x_ops bttv_tea_ops = {
 	.set_pins = bttv_tea575x_set_pins,
 	.get_pins = bttv_tea575x_get_pins,
 	.set_direction = bttv_tea575x_set_direction,
diff --git a/drivers/media/pci/bt8xx/bttv-driver.c b/drivers/media/pci/bt8xx/bttv-driver.c
index 15a4ebc..9400e99 100644
--- a/drivers/media/pci/bt8xx/bttv-driver.c
+++ b/drivers/media/pci/bt8xx/bttv-driver.c
@@ -50,15 +50,15 @@
 #include <media/v4l2-common.h>
 #include <media/v4l2-ioctl.h>
 #include <media/v4l2-event.h>
-#include <media/tvaudio.h>
-#include <media/msp3400.h>
+#include <media/i2c/tvaudio.h>
+#include <media/drv-intf/msp3400.h>
 
 #include <linux/dma-mapping.h>
 
 #include <asm/io.h>
 #include <asm/byteorder.h>
 
-#include <media/saa6588.h>
+#include <media/i2c/saa6588.h>
 
 #define BTTV_VERSION "0.9.19"
 
diff --git a/drivers/media/pci/bt8xx/bttvp.h b/drivers/media/pci/bt8xx/bttvp.h
index 31bf79d..b1e0023 100644
--- a/drivers/media/pci/bt8xx/bttvp.h
+++ b/drivers/media/pci/bt8xx/bttvp.h
@@ -41,8 +41,8 @@
 #include <media/videobuf-dma-sg.h>
 #include <media/tveeprom.h>
 #include <media/rc-core.h>
-#include <media/ir-kbd-i2c.h>
-#include <media/tea575x.h>
+#include <media/i2c/ir-kbd-i2c.h>
+#include <media/drv-intf/tea575x.h>
 
 #include "bt848.h"
 #include "bttv.h"
diff --git a/drivers/media/pci/cobalt/cobalt-driver.c b/drivers/media/pci/cobalt/cobalt-driver.c
index 8fed61e..8d6f04f 100644
--- a/drivers/media/pci/cobalt/cobalt-driver.c
+++ b/drivers/media/pci/cobalt/cobalt-driver.c
@@ -21,9 +21,9 @@
  */
 
 #include <linux/delay.h>
-#include <media/adv7604.h>
-#include <media/adv7842.h>
-#include <media/adv7511.h>
+#include <media/i2c/adv7604.h>
+#include <media/i2c/adv7842.h>
+#include <media/i2c/adv7511.h>
 #include <media/v4l2-event.h>
 #include <media/v4l2-ctrls.h>
 
diff --git a/drivers/media/pci/cobalt/cobalt-irq.c b/drivers/media/pci/cobalt/cobalt-irq.c
index 3de26d0..b190d4f 100644
--- a/drivers/media/pci/cobalt/cobalt-irq.c
+++ b/drivers/media/pci/cobalt/cobalt-irq.c
@@ -18,7 +18,7 @@
  *  SOFTWARE.
  */
 
-#include <media/adv7604.h>
+#include <media/i2c/adv7604.h>
 
 #include "cobalt-driver.h"
 #include "cobalt-irq.h"
@@ -134,7 +134,7 @@
 		skip = true;
 		s->skip_first_frames--;
 	}
-	v4l2_get_timestamp(&cb->vb.timestamp);
+	cb->vb.vb2_buf.timestamp = ktime_get_ns();
 	/* TODO: the sequence number should be read from the FPGA so we
 	   also know about dropped frames. */
 	cb->vb.sequence = s->sequence++;
diff --git a/drivers/media/pci/cobalt/cobalt-v4l2.c b/drivers/media/pci/cobalt/cobalt-v4l2.c
index ff46e42..c0ba458 100644
--- a/drivers/media/pci/cobalt/cobalt-v4l2.c
+++ b/drivers/media/pci/cobalt/cobalt-v4l2.c
@@ -29,8 +29,8 @@
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-event.h>
 #include <media/v4l2-dv-timings.h>
-#include <media/adv7604.h>
-#include <media/adv7842.h>
+#include <media/i2c/adv7604.h>
+#include <media/i2c/adv7842.h>
 
 #include "cobalt-alsa.h"
 #include "cobalt-cpld.h"
@@ -43,11 +43,10 @@
 
 /* vb2 DMA streaming ops */
 
-static int cobalt_queue_setup(struct vb2_queue *q, const void *parg,
+static int cobalt_queue_setup(struct vb2_queue *q,
 			unsigned int *num_buffers, unsigned int *num_planes,
 			unsigned int sizes[], void *alloc_ctxs[])
 {
-	const struct v4l2_format *fmt = parg;
 	struct cobalt_stream *s = q->drv_priv;
 	unsigned size = s->stride * s->height;
 
@@ -55,14 +54,11 @@
 		*num_buffers = 3;
 	if (*num_buffers > NR_BUFS)
 		*num_buffers = NR_BUFS;
-	*num_planes = 1;
-	if (fmt) {
-		if (fmt->fmt.pix.sizeimage < size)
-			return -EINVAL;
-		size = fmt->fmt.pix.sizeimage;
-	}
-	sizes[0] = size;
 	alloc_ctxs[0] = s->cobalt->alloc_ctx;
+	if (*num_planes)
+		return sizes[0] < size ? -EINVAL : 0;
+	*num_planes = 1;
+	sizes[0] = size;
 	return 0;
 }
 
@@ -649,7 +645,7 @@
 		return 0;
 	}
 
-	if (v4l2_match_dv_timings(timings, &s->timings, 0))
+	if (v4l2_match_dv_timings(timings, &s->timings, 0, false))
 		return 0;
 
 	if (vb2_is_busy(&s->q))
diff --git a/drivers/media/pci/cx18/cx18-cards.c b/drivers/media/pci/cx18/cx18-cards.c
index c07c849..5e01ea4 100644
--- a/drivers/media/pci/cx18/cx18-cards.c
+++ b/drivers/media/pci/cx18/cx18-cards.c
@@ -26,7 +26,7 @@
 #include "cx18-cards.h"
 #include "cx18-av-core.h"
 #include "cx18-i2c.h"
-#include <media/cs5345.h>
+#include <media/i2c/cs5345.h>
 
 #define V4L2_STD_PAL_SECAM (V4L2_STD_PAL|V4L2_STD_SECAM)
 
diff --git a/drivers/media/pci/cx18/cx18-controls.c b/drivers/media/pci/cx18/cx18-controls.c
index 71227a1..adb5a8c 100644
--- a/drivers/media/pci/cx18/cx18-controls.c
+++ b/drivers/media/pci/cx18/cx18-controls.c
@@ -126,7 +126,7 @@
 	return 0;
 }
 
-struct cx2341x_handler_ops cx18_cxhdl_ops = {
+const struct cx2341x_handler_ops cx18_cxhdl_ops = {
 	.s_audio_mode = cx18_s_audio_mode,
 	.s_audio_sampling_freq = cx18_s_audio_sampling_freq,
 	.s_video_encoding = cx18_s_video_encoding,
diff --git a/drivers/media/pci/cx18/cx18-controls.h b/drivers/media/pci/cx18/cx18-controls.h
index cb5dfc7..3267948 100644
--- a/drivers/media/pci/cx18/cx18-controls.h
+++ b/drivers/media/pci/cx18/cx18-controls.h
@@ -21,4 +21,4 @@
  *  02111-1307  USA
  */
 
-extern struct cx2341x_handler_ops cx18_cxhdl_ops;
+extern const struct cx2341x_handler_ops cx18_cxhdl_ops;
diff --git a/drivers/media/pci/cx18/cx18-driver.h b/drivers/media/pci/cx18/cx18-driver.h
index b15beed..7e31f2a 100644
--- a/drivers/media/pci/cx18/cx18-driver.h
+++ b/drivers/media/pci/cx18/cx18-driver.h
@@ -49,7 +49,7 @@
 #include <media/v4l2-device.h>
 #include <media/v4l2-fh.h>
 #include <media/tuner.h>
-#include <media/ir-kbd-i2c.h>
+#include <media/i2c/ir-kbd-i2c.h>
 #include "cx18-mailbox.h"
 #include "cx18-av-core.h"
 #include "cx23418.h"
diff --git a/drivers/media/pci/cx18/cx18-ioctl.c b/drivers/media/pci/cx18/cx18-ioctl.c
index 55525af..eeb741c 100644
--- a/drivers/media/pci/cx18/cx18-ioctl.c
+++ b/drivers/media/pci/cx18/cx18-ioctl.c
@@ -453,8 +453,8 @@
 
 	if (cropcap->type != V4L2_BUF_TYPE_VIDEO_CAPTURE)
 		return -EINVAL;
-	cropcap->pixelaspect.numerator = cx->is_50hz ? 59 : 10;
-	cropcap->pixelaspect.denominator = cx->is_50hz ? 54 : 11;
+	cropcap->pixelaspect.numerator = cx->is_50hz ? 54 : 11;
+	cropcap->pixelaspect.denominator = cx->is_50hz ? 59 : 10;
 	return 0;
 }
 
diff --git a/drivers/media/pci/cx18/cx23418.h b/drivers/media/pci/cx18/cx23418.h
index 767a8d2..67ffe65 100644
--- a/drivers/media/pci/cx18/cx23418.h
+++ b/drivers/media/pci/cx18/cx23418.h
@@ -22,7 +22,7 @@
 #ifndef CX23418_H
 #define CX23418_H
 
-#include <media/cx2341x.h>
+#include <media/drv-intf/cx2341x.h>
 
 #define MGR_CMD_MASK            		0x40000000
 /* The MSB of the command code indicates that this is the completion of a
diff --git a/drivers/media/pci/cx23885/Kconfig b/drivers/media/pci/cx23885/Kconfig
index 2e1b88c..3435bba 100644
--- a/drivers/media/pci/cx23885/Kconfig
+++ b/drivers/media/pci/cx23885/Kconfig
@@ -10,6 +10,7 @@
 	select VIDEOBUF2_DMA_SG
 	select VIDEO_CX25840
 	select VIDEO_CX2341X
+	select VIDEO_CS3308
 	select DVB_DIB7000P if MEDIA_SUBDRV_AUTOSELECT
 	select DVB_DRXK if MEDIA_SUBDRV_AUTOSELECT
 	select DVB_S5H1409 if MEDIA_SUBDRV_AUTOSELECT
diff --git a/drivers/media/pci/cx23885/cx23885-417.c b/drivers/media/pci/cx23885/cx23885-417.c
index 88a3afb..bd33387 100644
--- a/drivers/media/pci/cx23885/cx23885-417.c
+++ b/drivers/media/pci/cx23885/cx23885-417.c
@@ -30,7 +30,7 @@
 #include <linux/slab.h>
 #include <media/v4l2-common.h>
 #include <media/v4l2-ioctl.h>
-#include <media/cx2341x.h>
+#include <media/drv-intf/cx2341x.h>
 
 #include "cx23885.h"
 #include "cx23885-ioctl.h"
@@ -1138,7 +1138,7 @@
 
 /* ------------------------------------------------------------------ */
 
-static int queue_setup(struct vb2_queue *q, const void *parg,
+static int queue_setup(struct vb2_queue *q,
 			   unsigned int *num_buffers, unsigned int *num_planes,
 			   unsigned int sizes[], void *alloc_ctxs[])
 {
diff --git a/drivers/media/pci/cx23885/cx23885-cards.c b/drivers/media/pci/cx23885/cx23885-cards.c
index f384f29..310ee76 100644
--- a/drivers/media/pci/cx23885/cx23885-cards.c
+++ b/drivers/media/pci/cx23885/cx23885-cards.c
@@ -19,7 +19,7 @@
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/delay.h>
-#include <media/cx25840.h>
+#include <media/drv-intf/cx25840.h>
 #include <linux/firmware.h>
 #include <misc/altera.h>
 
@@ -715,6 +715,56 @@
 		.portb		= CX23885_MPEG_DVB,
 		.portc		= CX23885_MPEG_DVB,
 	},
+	[CX23885_BOARD_VIEWCAST_260E] = {
+		.name		= "ViewCast 260e",
+		.porta		= CX23885_ANALOG_VIDEO,
+		.force_bff	= 1,
+		.input          = {{
+			.type   = CX23885_VMUX_COMPOSITE1,
+			.vmux   = CX25840_VIN6_CH1,
+			.amux   = CX25840_AUDIO7,
+		}, {
+			.type   = CX23885_VMUX_SVIDEO,
+			.vmux   = CX25840_VIN7_CH3 |
+					CX25840_VIN5_CH1 |
+					CX25840_SVIDEO_ON,
+			.amux   = CX25840_AUDIO7,
+		}, {
+			.type   = CX23885_VMUX_COMPONENT,
+			.vmux   = CX25840_VIN7_CH3 |
+					CX25840_VIN6_CH2 |
+					CX25840_VIN5_CH1 |
+					CX25840_COMPONENT_ON,
+			.amux   = CX25840_AUDIO7,
+		} },
+	},
+	[CX23885_BOARD_VIEWCAST_460E] = {
+		.name		= "ViewCast 460e",
+		.porta		= CX23885_ANALOG_VIDEO,
+		.force_bff	= 1,
+		.input          = {{
+			.type   = CX23885_VMUX_COMPOSITE1,
+			.vmux   = CX25840_VIN4_CH1,
+			.amux   = CX25840_AUDIO7,
+		}, {
+			.type   = CX23885_VMUX_SVIDEO,
+			.vmux   = CX25840_VIN7_CH3 |
+					CX25840_VIN6_CH1 |
+					CX25840_SVIDEO_ON,
+			.amux   = CX25840_AUDIO7,
+		}, {
+			.type   = CX23885_VMUX_COMPONENT,
+			.vmux   = CX25840_VIN7_CH3 |
+					CX25840_VIN6_CH1 |
+					CX25840_VIN5_CH2 |
+					CX25840_COMPONENT_ON,
+			.amux   = CX25840_AUDIO7,
+		}, {
+			.type   = CX23885_VMUX_COMPOSITE2,
+			.vmux   = CX25840_VIN6_CH1,
+			.amux   = CX25840_AUDIO7,
+		} },
+	},
 };
 const unsigned int cx23885_bcount = ARRAY_SIZE(cx23885_boards);
 
@@ -1002,6 +1052,14 @@
 		.subvendor = 0x0070,
 		.subdevice = 0xf038,
 		.card      = CX23885_BOARD_HAUPPAUGE_HVR5525,
+	}, {
+		.subvendor = 0x1576,
+		.subdevice = 0x0260,
+		.card      = CX23885_BOARD_VIEWCAST_260E,
+	}, {
+		.subvendor = 0x1576,
+		.subdevice = 0x0460,
+		.card      = CX23885_BOARD_VIEWCAST_460E,
 	},
 };
 const unsigned int cx23885_idcount = ARRAY_SIZE(cx23885_subids);
@@ -1034,6 +1092,28 @@
 		       dev->name, i, cx23885_boards[i].name);
 }
 
+static void viewcast_eeprom(struct cx23885_dev *dev, u8 *eeprom_data)
+{
+	u32 sn;
+
+	/* The serial number record begins with tag 0x59 */
+	if (*(eeprom_data + 0x00) != 0x59) {
+		pr_info("%s() eeprom records are undefined, no serial number\n",
+			__func__);
+		return;
+	}
+
+	sn =	(*(eeprom_data + 0x06) << 24) |
+		(*(eeprom_data + 0x05) << 16) |
+		(*(eeprom_data + 0x04) << 8) |
+		(*(eeprom_data + 0x03));
+
+	pr_info("%s: card '%s' sn# MM%d\n",
+		dev->name,
+		cx23885_boards[dev->board].name,
+		sn);
+}
+
 static void hauppauge_eeprom(struct cx23885_dev *dev, u8 *eeprom_data)
 {
 	struct tveeprom tv;
@@ -1671,6 +1751,12 @@
 		cx23885_gpio_set(dev, GPIO_8 | GPIO_9);
 		msleep(100);
 		break;
+	case CX23885_BOARD_VIEWCAST_260E:
+	case CX23885_BOARD_VIEWCAST_460E:
+		/* For documentation purposes, it's worth noting that this
+		 * card does not have any GPIO's connected to subcomponents.
+		 */
+		break;
 	}
 }
 
@@ -1917,6 +2003,14 @@
 		if (dev->i2c_bus[0].i2c_rc == 0)
 			hauppauge_eeprom(dev, eeprom+0xc0);
 		break;
+	case CX23885_BOARD_VIEWCAST_260E:
+	case CX23885_BOARD_VIEWCAST_460E:
+		dev->i2c_bus[1].i2c_client.addr = 0xa0 >> 1;
+		tveeprom_read(&dev->i2c_bus[1].i2c_client,
+			      eeprom, sizeof(eeprom));
+		if (dev->i2c_bus[0].i2c_rc == 0)
+			viewcast_eeprom(dev, eeprom);
+		break;
 	}
 
 	switch (dev->board) {
@@ -2120,6 +2214,8 @@
 	case CX23885_BOARD_DVBSKY_S950:
 	case CX23885_BOARD_DVBSKY_S952:
 	case CX23885_BOARD_DVBSKY_T982:
+	case CX23885_BOARD_VIEWCAST_260E:
+	case CX23885_BOARD_VIEWCAST_460E:
 		dev->sd_cx25840 = v4l2_i2c_new_subdev(&dev->v4l2_dev,
 				&dev->i2c_bus[2].i2c_adap,
 				"cx25840", 0x88 >> 1, NULL);
@@ -2130,6 +2226,24 @@
 		break;
 	}
 
+	switch (dev->board) {
+	case CX23885_BOARD_VIEWCAST_260E:
+		v4l2_i2c_new_subdev(&dev->v4l2_dev,
+				&dev->i2c_bus[0].i2c_adap,
+				"cs3308", 0x82 >> 1, NULL);
+		break;
+	case CX23885_BOARD_VIEWCAST_460E:
+		/* This cs3308 controls the audio from the breakout cable */
+		v4l2_i2c_new_subdev(&dev->v4l2_dev,
+				&dev->i2c_bus[0].i2c_adap,
+				"cs3308", 0x80 >> 1, NULL);
+		/* This cs3308 controls the audio from the onboard header */
+		v4l2_i2c_new_subdev(&dev->v4l2_dev,
+				&dev->i2c_bus[0].i2c_adap,
+				"cs3308", 0x82 >> 1, NULL);
+		break;
+	}
+
 	/* AUX-PLL 27MHz CLK */
 	switch (dev->board) {
 	case CX23885_BOARD_NETUP_DUAL_DVBS2_CI:
diff --git a/drivers/media/pci/cx23885/cx23885-core.c b/drivers/media/pci/cx23885/cx23885-core.c
index e8f8472..813c217 100644
--- a/drivers/media/pci/cx23885/cx23885-core.c
+++ b/drivers/media/pci/cx23885/cx23885-core.c
@@ -427,7 +427,7 @@
 	buf = list_entry(q->active.next,
 			 struct cx23885_buffer, queue);
 
-	v4l2_get_timestamp(&buf->vb.timestamp);
+	buf->vb.vb2_buf.timestamp = ktime_get_ns();
 	buf->vb.sequence = q->count++;
 	dprintk(1, "[%p/%d] wakeup reg=%d buf=%d\n", buf,
 		buf->vb.vb2_buf.index,
@@ -968,6 +968,16 @@
 	call_all(dev, core, s_power, 0);
 	cx23885_ir_init(dev);
 
+	if (dev->board == CX23885_BOARD_VIEWCAST_460E) {
+		/*
+		 * GPIOs 9/8 are input detection bits for the breakout video
+		 * (gpio 8) and audio (gpio 9) cables. When they're attached,
+		 * this gpios are pulled high. Make sure these GPIOs are marked
+		 * as inputs.
+		 */
+		cx23885_gpio_enable(dev, 0x300, 0);
+	}
+
 	if (cx23885_boards[dev->board].porta == CX23885_ANALOG_VIDEO) {
 		if (cx23885_video_register(dev) < 0) {
 			printk(KERN_ERR "%s() Failed to register analog "
diff --git a/drivers/media/pci/cx23885/cx23885-dvb.c b/drivers/media/pci/cx23885/cx23885-dvb.c
index c4307ad..80319bb 100644
--- a/drivers/media/pci/cx23885/cx23885-dvb.c
+++ b/drivers/media/pci/cx23885/cx23885-dvb.c
@@ -92,7 +92,7 @@
 
 /* ------------------------------------------------------------------ */
 
-static int queue_setup(struct vb2_queue *q, const void *parg,
+static int queue_setup(struct vb2_queue *q,
 			   unsigned int *num_buffers, unsigned int *num_planes,
 			   unsigned int sizes[], void *alloc_ctxs[])
 {
@@ -2168,11 +2168,12 @@
 		}
 		port->i2c_client_tuner = client_tuner;
 		break;
-	case CX23885_BOARD_HAUPPAUGE_HVR5525:
-		switch (port->nr) {
+	case CX23885_BOARD_HAUPPAUGE_HVR5525: {
 		struct m88rs6000t_config m88rs6000t_config;
 		struct a8293_platform_data a8293_pdata = {};
 
+		switch (port->nr) {
+
 		/* port b - satellite */
 		case 1:
 			/* attach frontend */
@@ -2267,6 +2268,7 @@
 			break;
 		}
 		break;
+	}
 	default:
 		printk(KERN_INFO "%s: The frontend of your DVB/ATSC card "
 			" isn't supported yet\n",
diff --git a/drivers/media/pci/cx23885/cx23885-i2c.c b/drivers/media/pci/cx23885/cx23885-i2c.c
index 1135ea3..ae061b3 100644
--- a/drivers/media/pci/cx23885/cx23885-i2c.c
+++ b/drivers/media/pci/cx23885/cx23885-i2c.c
@@ -279,6 +279,8 @@
 	[0x10 >> 1] = "tda10048",
 	[0x12 >> 1] = "dib7000pc",
 	[0x1c >> 1] = "lgdt3303",
+	[0x80 >> 1] = "cs3308",
+	[0x82 >> 1] = "cs3308",
 	[0x86 >> 1] = "tda9887",
 	[0x32 >> 1] = "cx24227",
 	[0x88 >> 1] = "cx25837",
diff --git a/drivers/media/pci/cx23885/cx23885-input.c b/drivers/media/pci/cx23885/cx23885-input.c
index 088799c..64328d0 100644
--- a/drivers/media/pci/cx23885/cx23885-input.c
+++ b/drivers/media/pci/cx23885/cx23885-input.c
@@ -268,7 +268,7 @@
 	struct rc_dev *rc;
 	char *rc_map;
 	enum rc_driver_type driver_type;
-	unsigned long allowed_protos;
+	u64 allowed_protos;
 
 	int ret;
 
diff --git a/drivers/media/pci/cx23885/cx23885-vbi.c b/drivers/media/pci/cx23885/cx23885-vbi.c
index cf3cb13..39750eb 100644
--- a/drivers/media/pci/cx23885/cx23885-vbi.c
+++ b/drivers/media/pci/cx23885/cx23885-vbi.c
@@ -83,7 +83,7 @@
 	if (status & VID_BC_MSK_VBI_RISCI1) {
 		dprintk(1, "%s() VID_BC_MSK_VBI_RISCI1\n", __func__);
 		spin_lock(&dev->slock);
-		count = cx_read(VID_A_GPCNT);
+		count = cx_read(VBI_A_GPCNT);
 		cx23885_video_wakeup(dev, &dev->vbiq, count);
 		spin_unlock(&dev->slock);
 		handled++;
@@ -103,7 +103,6 @@
 				VBI_LINE_LENGTH, buf->risc.dma);
 
 	/* reset counter */
-	cx_write(VID_A_GPCNT_CTL, 3);
 	cx_write(VID_A_VBI_CTRL, 3);
 	cx_write(VBI_A_GPCNT_CTL, 3);
 	q->count = 0;
@@ -121,7 +120,7 @@
 
 /* ------------------------------------------------------------------ */
 
-static int queue_setup(struct vb2_queue *q, const void *parg,
+static int queue_setup(struct vb2_queue *q,
 			   unsigned int *num_buffers, unsigned int *num_planes,
 			   unsigned int sizes[], void *alloc_ctxs[])
 {
diff --git a/drivers/media/pci/cx23885/cx23885-video.c b/drivers/media/pci/cx23885/cx23885-video.c
index 71a80e2..e1d7d08 100644
--- a/drivers/media/pci/cx23885/cx23885-video.c
+++ b/drivers/media/pci/cx23885/cx23885-video.c
@@ -35,7 +35,7 @@
 #include "cx23885-ioctl.h"
 #include "tuner-xc2028.h"
 
-#include <media/cx25840.h>
+#include <media/drv-intf/cx25840.h>
 
 MODULE_DESCRIPTION("v4l2 driver module for cx23885 based TV cards");
 MODULE_AUTHOR("Steven Toth <stoth@linuxtv.org>");
@@ -105,7 +105,7 @@
 			struct cx23885_buffer, queue);
 
 	buf->vb.sequence = q->count++;
-	v4l2_get_timestamp(&buf->vb.timestamp);
+	buf->vb.vb2_buf.timestamp = ktime_get_ns();
 	dprintk(2, "[%p/%d] wakeup reg=%d buf=%d\n", buf,
 			buf->vb.vb2_buf.index, count, q->count);
 	list_del(&buf->queue);
@@ -114,11 +114,19 @@
 
 int cx23885_set_tvnorm(struct cx23885_dev *dev, v4l2_std_id norm)
 {
+	struct v4l2_subdev_format format = {
+		.which = V4L2_SUBDEV_FORMAT_ACTIVE,
+		.format.code = MEDIA_BUS_FMT_FIXED,
+	};
+
 	dprintk(1, "%s(norm = 0x%08x) name: [%s]\n",
 		__func__,
 		(unsigned int)norm,
 		v4l2_norm_to_name(norm));
 
+	if (dev->tvnorm == norm)
+		return 0;
+
 	if (dev->tvnorm != norm) {
 		if (vb2_is_busy(&dev->vb2_vidq) || vb2_is_busy(&dev->vb2_vbiq) ||
 		    vb2_is_busy(&dev->vb2_mpegq))
@@ -126,9 +134,17 @@
 	}
 
 	dev->tvnorm = norm;
+	dev->width = 720;
+	dev->height = norm_maxh(norm);
+	dev->field = V4L2_FIELD_INTERLACED;
 
 	call_all(dev, video, s_std, norm);
 
+	format.format.width = dev->width;
+	format.format.height = dev->height;
+	format.format.field = dev->field;
+	call_all(dev, pad, set_fmt, NULL, &format);
+
 	return 0;
 }
 
@@ -247,7 +263,9 @@
 		(dev->board == CX23885_BOARD_HAUPPAUGE_HVR1255_22111) ||
 		(dev->board == CX23885_BOARD_HAUPPAUGE_HVR1850) ||
 		(dev->board == CX23885_BOARD_MYGICA_X8507) ||
-		(dev->board == CX23885_BOARD_AVERMEDIA_HC81R)) {
+		(dev->board == CX23885_BOARD_AVERMEDIA_HC81R) ||
+		(dev->board == CX23885_BOARD_VIEWCAST_260E) ||
+		(dev->board == CX23885_BOARD_VIEWCAST_460E)) {
 		/* Configure audio routing */
 		v4l2_subdev_call(dev->sd_cx25840, audio, s_routing,
 			INPUT(input)->amux, 0, 0);
@@ -315,7 +333,7 @@
 	return 0;
 }
 
-static int queue_setup(struct vb2_queue *q, const void *parg,
+static int queue_setup(struct vb2_queue *q,
 			   unsigned int *num_buffers, unsigned int *num_planes,
 			   unsigned int sizes[], void *alloc_ctxs[])
 {
@@ -545,7 +563,7 @@
 		return -EINVAL;
 
 	field = f->fmt.pix.field;
-	maxw  = norm_maxw(dev->tvnorm);
+	maxw  = 720;
 	maxh  = norm_maxh(dev->tvnorm);
 
 	if (V4L2_FIELD_ANY == field) {
@@ -648,6 +666,26 @@
 	return 0;
 }
 
+static int vidioc_cropcap(struct file *file, void *priv,
+			  struct v4l2_cropcap *cc)
+{
+	struct cx23885_dev *dev = video_drvdata(file);
+	bool is_50hz = dev->tvnorm & V4L2_STD_625_50;
+
+	if (cc->type != V4L2_BUF_TYPE_VIDEO_CAPTURE)
+		return -EINVAL;
+
+	cc->bounds.left = 0;
+	cc->bounds.top = 0;
+	cc->bounds.width = 720;
+	cc->bounds.height = norm_maxh(dev->tvnorm);
+	cc->defrect = cc->bounds;
+	cc->pixelaspect.numerator = is_50hz ? 54 : 11;
+	cc->pixelaspect.denominator = is_50hz ? 59 : 10;
+
+	return 0;
+}
+
 static int vidioc_g_std(struct file *file, void *priv, v4l2_std_id *id)
 {
 	struct cx23885_dev *dev = video_drvdata(file);
@@ -1082,6 +1120,7 @@
 	.vidioc_dqbuf         = vb2_ioctl_dqbuf,
 	.vidioc_streamon      = vb2_ioctl_streamon,
 	.vidioc_streamoff     = vb2_ioctl_streamoff,
+	.vidioc_cropcap       = vidioc_cropcap,
 	.vidioc_s_std         = vidioc_s_std,
 	.vidioc_g_std         = vidioc_g_std,
 	.vidioc_enum_input    = vidioc_enum_input,
diff --git a/drivers/media/pci/cx23885/cx23885.h b/drivers/media/pci/cx23885/cx23885.h
index c5ba083..b1a5409 100644
--- a/drivers/media/pci/cx23885/cx23885.h
+++ b/drivers/media/pci/cx23885/cx23885.h
@@ -30,7 +30,7 @@
 #include <media/rc-core.h>
 
 #include "cx23885-reg.h"
-#include "media/cx2341x.h"
+#include "media/drv-intf/cx2341x.h"
 
 #include <linux/mutex.h>
 
@@ -101,6 +101,8 @@
 #define CX23885_BOARD_DVBSKY_T982              51
 #define CX23885_BOARD_HAUPPAUGE_HVR5525        52
 #define CX23885_BOARD_HAUPPAUGE_STARBURST      53
+#define CX23885_BOARD_VIEWCAST_260E            54
+#define CX23885_BOARD_VIEWCAST_460E            55
 
 #define GPIO_0 0x00000001
 #define GPIO_1 0x00000002
@@ -627,11 +629,6 @@
 /* ----------------------------------------------------------- */
 /* tv norms                                                    */
 
-static inline unsigned int norm_maxw(v4l2_std_id norm)
-{
-	return (norm & V4L2_STD_525_60) ? 720 : 768;
-}
-
 static inline unsigned int norm_maxh(v4l2_std_id norm)
 {
 	return (norm & V4L2_STD_525_60) ? 480 : 576;
diff --git a/drivers/media/pci/cx25821/cx25821-video.c b/drivers/media/pci/cx25821/cx25821-video.c
index 26e3e29..c48bba9 100644
--- a/drivers/media/pci/cx25821/cx25821-video.c
+++ b/drivers/media/pci/cx25821/cx25821-video.c
@@ -130,7 +130,7 @@
 			buf = list_entry(dmaq->active.next,
 					 struct cx25821_buffer, queue);
 
-			v4l2_get_timestamp(&buf->vb.timestamp);
+			buf->vb.vb2_buf.timestamp = ktime_get_ns();
 			buf->vb.sequence = dmaq->count++;
 			list_del(&buf->queue);
 			vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_DONE);
@@ -141,20 +141,20 @@
 	return handled;
 }
 
-static int cx25821_queue_setup(struct vb2_queue *q, const void *parg,
+static int cx25821_queue_setup(struct vb2_queue *q,
 			   unsigned int *num_buffers, unsigned int *num_planes,
 			   unsigned int sizes[], void *alloc_ctxs[])
 {
-	const struct v4l2_format *fmt = parg;
 	struct cx25821_channel *chan = q->drv_priv;
 	unsigned size = (chan->fmt->depth * chan->width * chan->height) >> 3;
 
-	if (fmt && fmt->fmt.pix.sizeimage < size)
-		return -EINVAL;
+	alloc_ctxs[0] = chan->dev->alloc_ctx;
+
+	if (*num_planes)
+		return sizes[0] < size ? -EINVAL : 0;
 
 	*num_planes = 1;
-	sizes[0] = fmt ? fmt->fmt.pix.sizeimage : size;
-	alloc_ctxs[0] = chan->dev->alloc_ctx;
+	sizes[0] = size;
 	return 0;
 }
 
diff --git a/drivers/media/pci/cx88/cx88-alsa.c b/drivers/media/pci/cx88/cx88-alsa.c
index 1b5268f..e158a1d 100644
--- a/drivers/media/pci/cx88/cx88-alsa.c
+++ b/drivers/media/pci/cx88/cx88-alsa.c
@@ -40,7 +40,7 @@
 #include <sound/control.h>
 #include <sound/initval.h>
 #include <sound/tlv.h>
-#include <media/wm8775.h>
+#include <media/i2c/wm8775.h>
 
 #include "cx88.h"
 #include "cx88-reg.h"
diff --git a/drivers/media/pci/cx88/cx88-blackbird.c b/drivers/media/pci/cx88/cx88-blackbird.c
index 8b88913..3233d45 100644
--- a/drivers/media/pci/cx88/cx88-blackbird.c
+++ b/drivers/media/pci/cx88/cx88-blackbird.c
@@ -36,7 +36,7 @@
 #include <media/v4l2-common.h>
 #include <media/v4l2-ioctl.h>
 #include <media/v4l2-event.h>
-#include <media/cx2341x.h>
+#include <media/drv-intf/cx2341x.h>
 
 #include "cx88.h"
 
@@ -637,7 +637,7 @@
 
 /* ------------------------------------------------------------------ */
 
-static int queue_setup(struct vb2_queue *q, const void *parg,
+static int queue_setup(struct vb2_queue *q,
 			   unsigned int *num_buffers, unsigned int *num_planes,
 			   unsigned int sizes[], void *alloc_ctxs[])
 {
diff --git a/drivers/media/pci/cx88/cx88-core.c b/drivers/media/pci/cx88/cx88-core.c
index 9a43c78..46fe8c1 100644
--- a/drivers/media/pci/cx88/cx88-core.c
+++ b/drivers/media/pci/cx88/cx88-core.c
@@ -518,7 +518,7 @@
 
 	buf = list_entry(q->active.next,
 			 struct cx88_buffer, list);
-	v4l2_get_timestamp(&buf->vb.timestamp);
+	buf->vb.vb2_buf.timestamp = ktime_get_ns();
 	buf->vb.field = core->field;
 	buf->vb.sequence = q->count++;
 	list_del(&buf->list);
diff --git a/drivers/media/pci/cx88/cx88-dvb.c b/drivers/media/pci/cx88/cx88-dvb.c
index f048350..afb2075 100644
--- a/drivers/media/pci/cx88/cx88-dvb.c
+++ b/drivers/media/pci/cx88/cx88-dvb.c
@@ -82,7 +82,7 @@
 
 /* ------------------------------------------------------------------ */
 
-static int queue_setup(struct vb2_queue *q, const void *parg,
+static int queue_setup(struct vb2_queue *q,
 			   unsigned int *num_buffers, unsigned int *num_planes,
 			   unsigned int sizes[], void *alloc_ctxs[])
 {
diff --git a/drivers/media/pci/cx88/cx88-vbi.c b/drivers/media/pci/cx88/cx88-vbi.c
index 007a5ee..ccc646d 100644
--- a/drivers/media/pci/cx88/cx88-vbi.c
+++ b/drivers/media/pci/cx88/cx88-vbi.c
@@ -107,7 +107,7 @@
 
 /* ------------------------------------------------------------------ */
 
-static int queue_setup(struct vb2_queue *q, const void *parg,
+static int queue_setup(struct vb2_queue *q,
 			   unsigned int *num_buffers, unsigned int *num_planes,
 			   unsigned int sizes[], void *alloc_ctxs[])
 {
diff --git a/drivers/media/pci/cx88/cx88-video.c b/drivers/media/pci/cx88/cx88-video.c
index aef9acf..5f331df 100644
--- a/drivers/media/pci/cx88/cx88-video.c
+++ b/drivers/media/pci/cx88/cx88-video.c
@@ -41,7 +41,7 @@
 #include <media/v4l2-common.h>
 #include <media/v4l2-ioctl.h>
 #include <media/v4l2-event.h>
-#include <media/wm8775.h>
+#include <media/i2c/wm8775.h>
 
 MODULE_DESCRIPTION("v4l2 driver module for cx2388x based TV cards");
 MODULE_AUTHOR("Gerd Knorr <kraxel@bytesex.org> [SuSE Labs]");
@@ -429,7 +429,7 @@
 
 /* ------------------------------------------------------------------ */
 
-static int queue_setup(struct vb2_queue *q, const void *parg,
+static int queue_setup(struct vb2_queue *q,
 			   unsigned int *num_buffers, unsigned int *num_planes,
 			   unsigned int sizes[], void *alloc_ctxs[])
 {
diff --git a/drivers/media/pci/cx88/cx88.h b/drivers/media/pci/cx88/cx88.h
index 2996eb3..78f817e 100644
--- a/drivers/media/pci/cx88/cx88.h
+++ b/drivers/media/pci/cx88/cx88.h
@@ -30,10 +30,10 @@
 #include <media/tuner.h>
 #include <media/tveeprom.h>
 #include <media/videobuf2-dma-sg.h>
-#include <media/cx2341x.h>
+#include <media/drv-intf/cx2341x.h>
 #include <media/videobuf2-dvb.h>
-#include <media/ir-kbd-i2c.h>
-#include <media/wm8775.h>
+#include <media/i2c/ir-kbd-i2c.h>
+#include <media/i2c/wm8775.h>
 
 #include "cx88-reg.h"
 #include "tuner-xc2028.h"
diff --git a/drivers/media/pci/ddbridge/ddbridge-core.c b/drivers/media/pci/ddbridge/ddbridge-core.c
index 0ac2dd3..fba5b40 100644
--- a/drivers/media/pci/ddbridge/ddbridge-core.c
+++ b/drivers/media/pci/ddbridge/ddbridge-core.c
@@ -81,13 +81,13 @@
 static int ddb_i2c_cmd(struct ddb_i2c *i2c, u32 adr, u32 cmd)
 {
 	struct ddb *dev = i2c->dev;
-	int stat;
+	long stat;
 	u32 val;
 
 	i2c->done = 0;
 	ddbwritel((adr << 9) | cmd, i2c->regs + I2C_COMMAND);
 	stat = wait_event_timeout(i2c->wq, i2c->done == 1, HZ);
-	if (stat <= 0) {
+	if (stat == 0) {
 		printk(KERN_ERR "I2C timeout\n");
 		{ /* MSI debugging*/
 			u32 istat = ddbreadl(INTERRUPT_STATUS);
diff --git a/drivers/media/pci/dm1105/dm1105.c b/drivers/media/pci/dm1105/dm1105.c
index 88915fb..5dd5047 100644
--- a/drivers/media/pci/dm1105/dm1105.c
+++ b/drivers/media/pci/dm1105/dm1105.c
@@ -1206,7 +1206,6 @@
 	i2c_del_adapter(&dev->i2c_adap);
 
 	dm1105_hw_exit(dev);
-	synchronize_irq(pdev->irq);
 	free_irq(pdev->irq, dev);
 	pci_iounmap(pdev, dev->io_mem);
 	pci_release_regions(pdev);
diff --git a/drivers/media/pci/dt3155/dt3155.c b/drivers/media/pci/dt3155/dt3155.c
index d84abde..568c0c8 100644
--- a/drivers/media/pci/dt3155/dt3155.c
+++ b/drivers/media/pci/dt3155/dt3155.c
@@ -131,22 +131,21 @@
 }
 
 static int
-dt3155_queue_setup(struct vb2_queue *vq, const void *parg,
+dt3155_queue_setup(struct vb2_queue *vq,
 		unsigned int *nbuffers, unsigned int *num_planes,
 		unsigned int sizes[], void *alloc_ctxs[])
 
 {
-	const struct v4l2_format *fmt = parg;
 	struct dt3155_priv *pd = vb2_get_drv_priv(vq);
 	unsigned size = pd->width * pd->height;
 
 	if (vq->num_buffers + *nbuffers < 2)
 		*nbuffers = 2 - vq->num_buffers;
-	if (fmt && fmt->fmt.pix.sizeimage < size)
-		return -EINVAL;
-	*num_planes = 1;
-	sizes[0] = fmt ? fmt->fmt.pix.sizeimage : size;
 	alloc_ctxs[0] = pd->alloc_ctx;
+	if (*num_planes)
+		return sizes[0] < size ? -EINVAL : 0;
+	*num_planes = 1;
+	sizes[0] = size;
 	return 0;
 }
 
@@ -271,7 +270,7 @@
 
 	spin_lock(&ipd->lock);
 	if (ipd->curr_buf && !list_empty(&ipd->dmaq)) {
-		v4l2_get_timestamp(&ipd->curr_buf->timestamp);
+		ipd->curr_buf->vb2_buf.timestamp = ktime_get_ns();
 		ipd->curr_buf->sequence = ipd->sequence++;
 		ipd->curr_buf->field = V4L2_FIELD_NONE;
 		vb2_buffer_done(&ipd->curr_buf->vb2_buf, VB2_BUF_STATE_DONE);
diff --git a/drivers/media/pci/ivtv/ivtv-cards.c b/drivers/media/pci/ivtv/ivtv-cards.c
index 145e474..410d97b 100644
--- a/drivers/media/pci/ivtv/ivtv-cards.c
+++ b/drivers/media/pci/ivtv/ivtv-cards.c
@@ -22,12 +22,12 @@
 #include "ivtv-cards.h"
 #include "ivtv-i2c.h"
 
-#include <media/msp3400.h>
-#include <media/m52790.h>
-#include <media/wm8775.h>
-#include <media/cs53l32a.h>
-#include <media/cx25840.h>
-#include <media/upd64031a.h>
+#include <media/drv-intf/msp3400.h>
+#include <media/i2c/m52790.h>
+#include <media/i2c/wm8775.h>
+#include <media/i2c/cs53l32a.h>
+#include <media/drv-intf/cx25840.h>
+#include <media/i2c/upd64031a.h>
 
 #define MSP_TUNER  MSP_INPUT(MSP_IN_SCART1, MSP_IN_TUNER1, \
 				MSP_DSP_IN_TUNER, MSP_DSP_IN_TUNER)
diff --git a/drivers/media/pci/ivtv/ivtv-controls.c b/drivers/media/pci/ivtv/ivtv-controls.c
index 8a55ccb..9666ca0 100644
--- a/drivers/media/pci/ivtv/ivtv-controls.c
+++ b/drivers/media/pci/ivtv/ivtv-controls.c
@@ -96,7 +96,7 @@
 	return 0;
 }
 
-struct cx2341x_handler_ops ivtv_cxhdl_ops = {
+const struct cx2341x_handler_ops ivtv_cxhdl_ops = {
 	.s_audio_mode = ivtv_s_audio_mode,
 	.s_audio_sampling_freq = ivtv_s_audio_sampling_freq,
 	.s_video_encoding = ivtv_s_video_encoding,
diff --git a/drivers/media/pci/ivtv/ivtv-controls.h b/drivers/media/pci/ivtv/ivtv-controls.h
index 3999e63..ea397ba 100644
--- a/drivers/media/pci/ivtv/ivtv-controls.h
+++ b/drivers/media/pci/ivtv/ivtv-controls.h
@@ -21,7 +21,7 @@
 #ifndef IVTV_CONTROLS_H
 #define IVTV_CONTROLS_H
 
-extern struct cx2341x_handler_ops ivtv_cxhdl_ops;
+extern const struct cx2341x_handler_ops ivtv_cxhdl_ops;
 extern const struct v4l2_ctrl_ops ivtv_hdl_out_ops;
 int ivtv_g_pts_frame(struct ivtv *itv, s64 *pts, s64 *frame);
 
diff --git a/drivers/media/pci/ivtv/ivtv-driver.c b/drivers/media/pci/ivtv/ivtv-driver.c
index c2e60b4..374033a 100644
--- a/drivers/media/pci/ivtv/ivtv-driver.c
+++ b/drivers/media/pci/ivtv/ivtv-driver.c
@@ -57,7 +57,7 @@
 #include "ivtv-gpio.h"
 #include <linux/dma-mapping.h>
 #include <media/tveeprom.h>
-#include <media/saa7115.h>
+#include <media/i2c/saa7115.h>
 #include "tuner-xc2028.h"
 
 /* If you have already X v4l cards, then set this to X. This way
@@ -826,7 +826,7 @@
 				IVTV_CARD_INPUT_VID_TUNER)
 			break;
 	}
-	if (i == itv->nof_inputs)
+	if (i >= itv->nof_inputs)
 		i = 0;
 	itv->active_input = i;
 	itv->audio_input = itv->card->video_inputs[i].audio_index;
diff --git a/drivers/media/pci/ivtv/ivtv-driver.h b/drivers/media/pci/ivtv/ivtv-driver.h
index ee0ef6e..6c08dae 100644
--- a/drivers/media/pci/ivtv/ivtv-driver.h
+++ b/drivers/media/pci/ivtv/ivtv-driver.h
@@ -64,8 +64,8 @@
 #include <media/v4l2-device.h>
 #include <media/v4l2-fh.h>
 #include <media/tuner.h>
-#include <media/cx2341x.h>
-#include <media/ir-kbd-i2c.h>
+#include <media/drv-intf/cx2341x.h>
+#include <media/i2c/ir-kbd-i2c.h>
 
 #include <linux/ivtv.h>
 
diff --git a/drivers/media/pci/ivtv/ivtv-fileops.c b/drivers/media/pci/ivtv/ivtv-fileops.c
index 605d280..c9bd018 100644
--- a/drivers/media/pci/ivtv/ivtv-fileops.c
+++ b/drivers/media/pci/ivtv/ivtv-fileops.c
@@ -34,7 +34,7 @@
 #include "ivtv-cards.h"
 #include "ivtv-firmware.h"
 #include <media/v4l2-event.h>
-#include <media/saa7115.h>
+#include <media/i2c/saa7115.h>
 
 /* This function tries to claim the stream for a specific file descriptor.
    If no one else is using this stream then the stream is claimed and
diff --git a/drivers/media/pci/ivtv/ivtv-firmware.c b/drivers/media/pci/ivtv/ivtv-firmware.c
index 4b0e758..5b3095f 100644
--- a/drivers/media/pci/ivtv/ivtv-firmware.c
+++ b/drivers/media/pci/ivtv/ivtv-firmware.c
@@ -26,7 +26,7 @@
 #include "ivtv-ioctl.h"
 #include "ivtv-cards.h"
 #include <linux/firmware.h>
-#include <media/saa7127.h>
+#include <media/i2c/saa7127.h>
 
 #define IVTV_MASK_SPU_ENABLE 		0xFFFFFFFE
 #define IVTV_MASK_VPU_ENABLE15 		0xFFFFFFF6
diff --git a/drivers/media/pci/ivtv/ivtv-i2c.c b/drivers/media/pci/ivtv/ivtv-i2c.c
index 1a41ba5..bccbf2d 100644
--- a/drivers/media/pci/ivtv/ivtv-i2c.c
+++ b/drivers/media/pci/ivtv/ivtv-i2c.c
@@ -63,7 +63,7 @@
 #include "ivtv-cards.h"
 #include "ivtv-gpio.h"
 #include "ivtv-i2c.h"
-#include <media/cx25840.h>
+#include <media/drv-intf/cx25840.h>
 
 /* i2c implementation for cx23415/6 chip, ivtv project.
  * Author: Kevin Thayer (nufan_wfk at yahoo.com)
diff --git a/drivers/media/pci/ivtv/ivtv-ioctl.c b/drivers/media/pci/ivtv/ivtv-ioctl.c
index 9a21c17..2dc4b20 100644
--- a/drivers/media/pci/ivtv/ivtv-ioctl.c
+++ b/drivers/media/pci/ivtv/ivtv-ioctl.c
@@ -32,7 +32,7 @@
 #include "ivtv-gpio.h"
 #include "ivtv-controls.h"
 #include "ivtv-cards.h"
-#include <media/saa7127.h>
+#include <media/i2c/saa7127.h>
 #include <media/tveeprom.h>
 #include <media/v4l2-event.h>
 #include <linux/dvb/audio.h>
@@ -831,11 +831,11 @@
 	struct ivtv *itv = id->itv;
 
 	if (cropcap->type == V4L2_BUF_TYPE_VIDEO_CAPTURE) {
-		cropcap->pixelaspect.numerator = itv->is_50hz ? 59 : 10;
-		cropcap->pixelaspect.denominator = itv->is_50hz ? 54 : 11;
+		cropcap->pixelaspect.numerator = itv->is_50hz ? 54 : 11;
+		cropcap->pixelaspect.denominator = itv->is_50hz ? 59 : 10;
 	} else if (cropcap->type == V4L2_BUF_TYPE_VIDEO_OUTPUT) {
-		cropcap->pixelaspect.numerator = itv->is_out_50hz ? 59 : 10;
-		cropcap->pixelaspect.denominator = itv->is_out_50hz ? 54 : 11;
+		cropcap->pixelaspect.numerator = itv->is_out_50hz ? 54 : 11;
+		cropcap->pixelaspect.denominator = itv->is_out_50hz ? 59 : 10;
 	} else {
 		return -EINVAL;
 	}
diff --git a/drivers/media/pci/ivtv/ivtv-routing.c b/drivers/media/pci/ivtv/ivtv-routing.c
index 8898c56..0c168f2 100644
--- a/drivers/media/pci/ivtv/ivtv-routing.c
+++ b/drivers/media/pci/ivtv/ivtv-routing.c
@@ -24,10 +24,10 @@
 #include "ivtv-gpio.h"
 #include "ivtv-routing.h"
 
-#include <media/msp3400.h>
-#include <media/m52790.h>
-#include <media/upd64031a.h>
-#include <media/upd64083.h>
+#include <media/drv-intf/msp3400.h>
+#include <media/i2c/m52790.h>
+#include <media/i2c/upd64031a.h>
+#include <media/i2c/upd64083.h>
 
 /* Selects the audio input and output according to the current
    settings. */
diff --git a/drivers/media/pci/netup_unidvb/netup_unidvb_core.c b/drivers/media/pci/netup_unidvb/netup_unidvb_core.c
index 3fdbd81..81e1a5e 100644
--- a/drivers/media/pci/netup_unidvb/netup_unidvb_core.c
+++ b/drivers/media/pci/netup_unidvb/netup_unidvb_core.c
@@ -277,7 +277,6 @@
 }
 
 static int netup_unidvb_queue_setup(struct vb2_queue *vq,
-				    const void *parg,
 				    unsigned int *nbuffers,
 				    unsigned int *nplanes,
 				    unsigned int sizes[],
@@ -580,7 +579,7 @@
 			dev_dbg(&ndev->pci_dev->dev,
 				"%s(): buffer %p done, size %d\n",
 				__func__, buf, buf->size);
-			v4l2_get_timestamp(&buf->vb.timestamp);
+			buf->vb.vb2_buf.timestamp = ktime_get_ns();
 			vb2_set_plane_payload(&buf->vb.vb2_buf, 0, buf->size);
 			vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_DONE);
 		}
diff --git a/drivers/media/pci/saa7134/saa7134-core.c b/drivers/media/pci/saa7134/saa7134-core.c
index f720cea..e227b02 100644
--- a/drivers/media/pci/saa7134/saa7134-core.c
+++ b/drivers/media/pci/saa7134/saa7134-core.c
@@ -309,7 +309,7 @@
 	core_dbg("buffer_finish %p\n", q->curr);
 
 	/* finish current buffer */
-	v4l2_get_timestamp(&q->curr->vb2.timestamp);
+	q->curr->vb2.vb2_buf.timestamp = ktime_get_ns();
 	q->curr->vb2.sequence = q->seq_nr++;
 	vb2_buffer_done(&q->curr->vb2.vb2_buf, state);
 	q->curr = NULL;
diff --git a/drivers/media/pci/saa7134/saa7134-ts.c b/drivers/media/pci/saa7134/saa7134-ts.c
index 7fb5ee7..0584a2a 100644
--- a/drivers/media/pci/saa7134/saa7134-ts.c
+++ b/drivers/media/pci/saa7134/saa7134-ts.c
@@ -116,7 +116,7 @@
 }
 EXPORT_SYMBOL_GPL(saa7134_ts_buffer_prepare);
 
-int saa7134_ts_queue_setup(struct vb2_queue *q, const void *parg,
+int saa7134_ts_queue_setup(struct vb2_queue *q,
 			   unsigned int *nbuffers, unsigned int *nplanes,
 			   unsigned int sizes[], void *alloc_ctxs[])
 {
diff --git a/drivers/media/pci/saa7134/saa7134-vbi.c b/drivers/media/pci/saa7134/saa7134-vbi.c
index 6271b0e..e76da37 100644
--- a/drivers/media/pci/saa7134/saa7134-vbi.c
+++ b/drivers/media/pci/saa7134/saa7134-vbi.c
@@ -138,7 +138,7 @@
 				    saa7134_buffer_startpage(buf));
 }
 
-static int queue_setup(struct vb2_queue *q, const void *parg,
+static int queue_setup(struct vb2_queue *q,
 			   unsigned int *nbuffers, unsigned int *nplanes,
 			   unsigned int sizes[], void *alloc_ctxs[])
 {
diff --git a/drivers/media/pci/saa7134/saa7134-video.c b/drivers/media/pci/saa7134/saa7134-video.c
index 518086c..a63c136 100644
--- a/drivers/media/pci/saa7134/saa7134-video.c
+++ b/drivers/media/pci/saa7134/saa7134-video.c
@@ -32,7 +32,7 @@
 
 #include <media/v4l2-common.h>
 #include <media/v4l2-event.h>
-#include <media/saa6588.h>
+#include <media/i2c/saa6588.h>
 
 /* ------------------------------------------------------------------ */
 
@@ -904,7 +904,7 @@
 				    saa7134_buffer_startpage(buf));
 }
 
-static int queue_setup(struct vb2_queue *q, const void *parg,
+static int queue_setup(struct vb2_queue *q,
 			   unsigned int *nbuffers, unsigned int *nplanes,
 			   unsigned int sizes[], void *alloc_ctxs[])
 {
diff --git a/drivers/media/pci/saa7134/saa7134.h b/drivers/media/pci/saa7134/saa7134.h
index 6b6d234..5938bc7 100644
--- a/drivers/media/pci/saa7134/saa7134.h
+++ b/drivers/media/pci/saa7134/saa7134.h
@@ -42,7 +42,7 @@
 #include <media/v4l2-ctrls.h>
 #include <media/tuner.h>
 #include <media/rc-core.h>
-#include <media/ir-kbd-i2c.h>
+#include <media/i2c/ir-kbd-i2c.h>
 #include <media/videobuf2-dma-sg.h>
 #include <sound/core.h>
 #include <sound/pcm.h>
@@ -820,7 +820,7 @@
 
 int saa7134_ts_buffer_init(struct vb2_buffer *vb2);
 int saa7134_ts_buffer_prepare(struct vb2_buffer *vb2);
-int saa7134_ts_queue_setup(struct vb2_queue *q, const void *parg,
+int saa7134_ts_queue_setup(struct vb2_queue *q,
 			   unsigned int *nbuffers, unsigned int *nplanes,
 			   unsigned int sizes[], void *alloc_ctxs[]);
 int saa7134_ts_start_streaming(struct vb2_queue *vq, unsigned int count);
diff --git a/drivers/media/pci/saa7146/hexium_gemini.c b/drivers/media/pci/saa7146/hexium_gemini.c
index 03cbcd2..c889ec9 100644
--- a/drivers/media/pci/saa7146/hexium_gemini.c
+++ b/drivers/media/pci/saa7146/hexium_gemini.c
@@ -25,7 +25,7 @@
 
 #define DEBUG_VARIABLE debug
 
-#include <media/saa7146_vv.h>
+#include <media/drv-intf/saa7146_vv.h>
 #include <linux/module.h>
 
 static int debug;
diff --git a/drivers/media/pci/saa7146/hexium_orion.c b/drivers/media/pci/saa7146/hexium_orion.c
index 15f0d66..c306a92 100644
--- a/drivers/media/pci/saa7146/hexium_orion.c
+++ b/drivers/media/pci/saa7146/hexium_orion.c
@@ -25,7 +25,7 @@
 
 #define DEBUG_VARIABLE debug
 
-#include <media/saa7146_vv.h>
+#include <media/drv-intf/saa7146_vv.h>
 #include <linux/module.h>
 
 static int debug;
diff --git a/drivers/media/pci/saa7146/mxb.c b/drivers/media/pci/saa7146/mxb.c
index 0ca1e07..504d788 100644
--- a/drivers/media/pci/saa7146/mxb.c
+++ b/drivers/media/pci/saa7146/mxb.c
@@ -25,10 +25,10 @@
 
 #define DEBUG_VARIABLE debug
 
-#include <media/saa7146_vv.h>
+#include <media/drv-intf/saa7146_vv.h>
 #include <media/tuner.h>
 #include <media/v4l2-common.h>
-#include <media/saa7115.h>
+#include <media/i2c/saa7115.h>
 #include <linux/module.h>
 
 #include "tea6415c.h"
diff --git a/drivers/media/pci/solo6x10/solo6x10-v4l2-enc.c b/drivers/media/pci/solo6x10/solo6x10-v4l2-enc.c
index 4432fd6..67a14c4 100644
--- a/drivers/media/pci/solo6x10/solo6x10-v4l2-enc.c
+++ b/drivers/media/pci/solo6x10/solo6x10-v4l2-enc.c
@@ -531,8 +531,7 @@
 
 	if (!ret) {
 		vbuf->sequence = solo_enc->sequence++;
-		vbuf->timestamp.tv_sec = vop_sec(vh);
-		vbuf->timestamp.tv_usec = vop_usec(vh);
+		vb->timestamp = ktime_get_ns();
 
 		/* Check for motion flags */
 		if (solo_is_motion_on(solo_enc) && enc_buf->motion) {
@@ -663,7 +662,6 @@
 }
 
 static int solo_enc_queue_setup(struct vb2_queue *q,
-				const void *parg,
 				unsigned int *num_buffers,
 				unsigned int *num_planes, unsigned int sizes[],
 				void *alloc_ctxs[])
diff --git a/drivers/media/pci/solo6x10/solo6x10-v4l2.c b/drivers/media/pci/solo6x10/solo6x10-v4l2.c
index f7ce493..721ff53 100644
--- a/drivers/media/pci/solo6x10/solo6x10-v4l2.c
+++ b/drivers/media/pci/solo6x10/solo6x10-v4l2.c
@@ -225,7 +225,7 @@
 		vb2_set_plane_payload(vb, 0,
 			solo_vlines(solo_dev) * solo_bytesperline(solo_dev));
 		vbuf->sequence = solo_dev->sequence++;
-		v4l2_get_timestamp(&vbuf->timestamp);
+		vb->timestamp = ktime_get_ns();
 	}
 
 	vb2_buffer_done(vb, error ? VB2_BUF_STATE_ERROR : VB2_BUF_STATE_DONE);
@@ -313,7 +313,7 @@
 	solo_dev->kthread = NULL;
 }
 
-static int solo_queue_setup(struct vb2_queue *q, const void *parg,
+static int solo_queue_setup(struct vb2_queue *q,
 			   unsigned int *num_buffers, unsigned int *num_planes,
 			   unsigned int sizes[], void *alloc_ctxs[])
 {
diff --git a/drivers/media/pci/sta2x11/sta2x11_vip.c b/drivers/media/pci/sta2x11/sta2x11_vip.c
index 6367b45..753411c 100644
--- a/drivers/media/pci/sta2x11/sta2x11_vip.c
+++ b/drivers/media/pci/sta2x11/sta2x11_vip.c
@@ -265,7 +265,7 @@
 
 
 /* Videobuf2 Operations */
-static int queue_setup(struct vb2_queue *vq, const void *parg,
+static int queue_setup(struct vb2_queue *vq,
 		       unsigned int *nbuffers, unsigned int *nplanes,
 		       unsigned int sizes[], void *alloc_ctxs[])
 {
@@ -817,7 +817,7 @@
 		/* Disable acquisition */
 		reg_write(vip, DVP_CTL, reg_read(vip, DVP_CTL) & ~DVP_CTL_ENA);
 		/* Remove the active buffer from the list */
-		v4l2_get_timestamp(&vip->active->vb.timestamp);
+		vip->active->vb.vb2_buf.timestamp = ktime_get_ns();
 		vip->active->vb.sequence = vip->sequence++;
 		vb2_buffer_done(&vip->active->vb.vb2_buf, VB2_BUF_STATE_DONE);
 	}
diff --git a/drivers/media/pci/ttpci/av7110.c b/drivers/media/pci/ttpci/av7110.c
index f893649..5e18b67 100644
--- a/drivers/media/pci/ttpci/av7110.c
+++ b/drivers/media/pci/ttpci/av7110.c
@@ -26,7 +26,7 @@
  * Or, point your browser to http://www.gnu.org/copyleft/gpl.html
  *
  *
- * the project's page is at http://www.linuxtv.org/ 
+ * the project's page is at https://linuxtv.org
  */
 
 
@@ -1537,7 +1537,7 @@
 			printk(KERN_ERR "dvb-ttpci: usually this should be in "
 			       "/usr/lib/hotplug/firmware or /lib/firmware\n");
 			printk(KERN_ERR "dvb-ttpci: and can be downloaded from"
-			       " http://www.linuxtv.org/download/dvb/firmware/\n");
+			       " https://linuxtv.org/download/dvb/firmware/\n");
 		} else
 			printk(KERN_ERR "dvb-ttpci: cannot request firmware"
 			       " (error %i)\n", ret);
@@ -2314,7 +2314,7 @@
 /* Budgetpatch note:
  * Original hardware design by Roberto Deza:
  * There is a DVB_Wiki at
- * http://www.linuxtv.org/
+ * https://linuxtv.org
  *
  * New software triggering design by Emard that works on
  * original Roberto Deza's hardware:
diff --git a/drivers/media/pci/ttpci/av7110.h b/drivers/media/pci/ttpci/av7110.h
index 3a55927..3707ccd 100644
--- a/drivers/media/pci/ttpci/av7110.h
+++ b/drivers/media/pci/ttpci/av7110.h
@@ -32,7 +32,7 @@
 #include "stv0297.h"
 #include "l64781.h"
 
-#include <media/saa7146_vv.h>
+#include <media/drv-intf/saa7146_vv.h>
 
 
 #define ANALOG_TUNER_VES1820 1
diff --git a/drivers/media/pci/ttpci/av7110_av.c b/drivers/media/pci/ttpci/av7110_av.c
index 9ed1ec7..6fc748e 100644
--- a/drivers/media/pci/ttpci/av7110_av.c
+++ b/drivers/media/pci/ttpci/av7110_av.c
@@ -25,7 +25,7 @@
  * Or, point your browser to http://www.gnu.org/copyleft/gpl.html
  *
  *
- * the project's page is at http://www.linuxtv.org/ 
+ * the project's page is at https://linuxtv.org
  */
 
 #include <linux/types.h>
@@ -280,9 +280,11 @@
 }
 
 
-int av7110_set_volume(struct av7110 *av7110, int volleft, int volright)
+int av7110_set_volume(struct av7110 *av7110, unsigned int volleft,
+		      unsigned int volright)
 {
-	int err, vol, val, balance = 0;
+	unsigned int vol, val, balance = 0;
+	int err;
 
 	dprintk(2, "av7110:%p, \n", av7110);
 
@@ -1043,6 +1045,9 @@
 
 	dprintk(2, "av7110:%p, \n", av7110);
 
+	if (len == 0)
+		return 0;
+
 	if (!(av7110->playing & RP_VIDEO)) {
 		if (av7110_av_start_play(av7110, RP_VIDEO) < 0)
 			return -EBUSY;
diff --git a/drivers/media/pci/ttpci/av7110_av.h b/drivers/media/pci/ttpci/av7110_av.h
index 5f02ef8..f52276f 100644
--- a/drivers/media/pci/ttpci/av7110_av.h
+++ b/drivers/media/pci/ttpci/av7110_av.h
@@ -10,7 +10,8 @@
 extern int av7110_pes_play(void *dest, struct dvb_ringbuffer *buf, int dlen);
 extern int av7110_write_to_decoder(struct dvb_demux_feed *feed, const u8 *buf, size_t len);
 
-extern int av7110_set_volume(struct av7110 *av7110, int volleft, int volright);
+extern int av7110_set_volume(struct av7110 *av7110, unsigned int volleft,
+			     unsigned int volright);
 extern int av7110_av_stop(struct av7110 *av7110, int av);
 extern int av7110_av_start_record(struct av7110 *av7110, int av,
 			  struct dvb_demux_feed *dvbdmxfeed);
diff --git a/drivers/media/pci/ttpci/av7110_ca.c b/drivers/media/pci/ttpci/av7110_ca.c
index a6079b9..bc4c65f 100644
--- a/drivers/media/pci/ttpci/av7110_ca.c
+++ b/drivers/media/pci/ttpci/av7110_ca.c
@@ -25,7 +25,7 @@
  * Or, point your browser to http://www.gnu.org/copyleft/gpl.html
  *
  *
- * the project's page is at http://www.linuxtv.org/ 
+ * the project's page is at https://linuxtv.org
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/media/pci/ttpci/av7110_hw.c b/drivers/media/pci/ttpci/av7110_hw.c
index 300bd3c..0583d56 100644
--- a/drivers/media/pci/ttpci/av7110_hw.c
+++ b/drivers/media/pci/ttpci/av7110_hw.c
@@ -22,7 +22,7 @@
  * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  * Or, point your browser to http://www.gnu.org/copyleft/gpl.html
  *
- * the project's page is at http://www.linuxtv.org/
+ * the project's page is at https://linuxtv.org
  */
 
 /* for debugging ARM communication: */
diff --git a/drivers/media/pci/ttpci/av7110_v4l.c b/drivers/media/pci/ttpci/av7110_v4l.c
index 6c4076a..479aff0 100644
--- a/drivers/media/pci/ttpci/av7110_v4l.c
+++ b/drivers/media/pci/ttpci/av7110_v4l.c
@@ -22,7 +22,7 @@
  * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  * Or, point your browser to http://www.gnu.org/copyleft/gpl.html
  *
- * the project's page is at http://www.linuxtv.org/ 
+ * the project's page is at https://linuxtv.org
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
diff --git a/drivers/media/pci/ttpci/budget-av.c b/drivers/media/pci/ttpci/budget-av.c
index 3e469d4..6f0d016 100644
--- a/drivers/media/pci/ttpci/budget-av.c
+++ b/drivers/media/pci/ttpci/budget-av.c
@@ -30,7 +30,7 @@
  * Or, point your browser to http://www.gnu.org/copyleft/gpl.html
  *
  *
- * the project's page is at http://www.linuxtv.org/ 
+ * the project's page is at https://linuxtv.org
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -46,7 +46,7 @@
 #include "tda1004x.h"
 #include "tua6100.h"
 #include "dvb-pll.h"
-#include <media/saa7146_vv.h>
+#include <media/drv-intf/saa7146_vv.h>
 #include <linux/module.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
diff --git a/drivers/media/pci/ttpci/budget-ci.c b/drivers/media/pci/ttpci/budget-ci.c
index 1feeeff..7b27af4 100644
--- a/drivers/media/pci/ttpci/budget-ci.c
+++ b/drivers/media/pci/ttpci/budget-ci.c
@@ -26,7 +26,7 @@
  * Or, point your browser to http://www.gnu.org/copyleft/gpl.html
  *
  *
- * the project's page is at http://www.linuxtv.org/
+ * the project's page is at https://linuxtv.org
  */
 
 #include <linux/module.h>
diff --git a/drivers/media/pci/ttpci/budget-core.c b/drivers/media/pci/ttpci/budget-core.c
index e9674b4..6d42dcf 100644
--- a/drivers/media/pci/ttpci/budget-core.c
+++ b/drivers/media/pci/ttpci/budget-core.c
@@ -31,7 +31,7 @@
  * Or, point your browser to http://www.gnu.org/copyleft/gpl.html
  *
  *
- * the project's page is at http://www.linuxtv.org/ 
+ * the project's page is at https://linuxtv.org
  */
 
 
diff --git a/drivers/media/pci/ttpci/budget-patch.c b/drivers/media/pci/ttpci/budget-patch.c
index b5b6596..591dbdf 100644
--- a/drivers/media/pci/ttpci/budget-patch.c
+++ b/drivers/media/pci/ttpci/budget-patch.c
@@ -27,7 +27,7 @@
  * Or, point your browser to http://www.gnu.org/copyleft/gpl.html
  *
  *
- * the project's page is at http://www.linuxtv.org/ 
+ * the project's page is at https://linuxtv.org
  */
 
 #include "av7110.h"
diff --git a/drivers/media/pci/ttpci/budget.c b/drivers/media/pci/ttpci/budget.c
index 99972be..de54310 100644
--- a/drivers/media/pci/ttpci/budget.c
+++ b/drivers/media/pci/ttpci/budget.c
@@ -31,7 +31,7 @@
  * Or, point your browser to http://www.gnu.org/copyleft/gpl.html
  *
  *
- * the project's page is at http://www.linuxtv.org/ 
+ * the project's page is at https://linuxtv.org
  */
 
 #include "budget.h"
diff --git a/drivers/media/pci/ttpci/budget.h b/drivers/media/pci/ttpci/budget.h
index 1ccbe1a..655eef5 100644
--- a/drivers/media/pci/ttpci/budget.h
+++ b/drivers/media/pci/ttpci/budget.h
@@ -13,7 +13,7 @@
 #include <linux/module.h>
 #include <linux/mutex.h>
 
-#include <media/saa7146.h>
+#include <media/drv-intf/saa7146.h>
 
 extern int budget_debug;
 
diff --git a/drivers/media/pci/tw68/tw68-video.c b/drivers/media/pci/tw68/tw68-video.c
index 46642ef..07116a8 100644
--- a/drivers/media/pci/tw68/tw68-video.c
+++ b/drivers/media/pci/tw68/tw68-video.c
@@ -376,28 +376,28 @@
 /* ------------------------------------------------------------- */
 /* vb2 queue operations                                          */
 
-static int tw68_queue_setup(struct vb2_queue *q, const void *parg,
+static int tw68_queue_setup(struct vb2_queue *q,
 			   unsigned int *num_buffers, unsigned int *num_planes,
 			   unsigned int sizes[], void *alloc_ctxs[])
 {
-	const struct v4l2_format *fmt = parg;
 	struct tw68_dev *dev = vb2_get_drv_priv(q);
 	unsigned tot_bufs = q->num_buffers + *num_buffers;
+	unsigned size = (dev->fmt->depth * dev->width * dev->height) >> 3;
 
-	sizes[0] = (dev->fmt->depth * dev->width * dev->height) >> 3;
+	if (tot_bufs < 2)
+		tot_bufs = 2;
+	tot_bufs = tw68_buffer_count(size, tot_bufs);
+	*num_buffers = tot_bufs - q->num_buffers;
 	alloc_ctxs[0] = dev->alloc_ctx;
 	/*
-	 * We allow create_bufs, but only if the sizeimage is the same as the
+	 * We allow create_bufs, but only if the sizeimage is >= as the
 	 * current sizeimage. The tw68_buffer_count calculation becomes quite
 	 * difficult otherwise.
 	 */
-	if (fmt && fmt->fmt.pix.sizeimage < sizes[0])
-		return -EINVAL;
+	if (*num_planes)
+		return sizes[0] < size ? -EINVAL : 0;
 	*num_planes = 1;
-	if (tot_bufs < 2)
-		tot_bufs = 2;
-	tot_bufs = tw68_buffer_count(sizes[0], tot_bufs);
-	*num_buffers = tot_bufs - q->num_buffers;
+	sizes[0] = size;
 
 	return 0;
 }
@@ -1016,7 +1016,7 @@
 		buf = list_entry(dev->active.next, struct tw68_buf, list);
 		list_del(&buf->list);
 		spin_unlock(&dev->slock);
-		v4l2_get_timestamp(&buf->vb.timestamp);
+		buf->vb.vb2_buf.timestamp = ktime_get_ns();
 		buf->vb.field = dev->field;
 		buf->vb.sequence = dev->seqnr++;
 		vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_DONE);
diff --git a/drivers/media/pci/zoran/zoran_card.c b/drivers/media/pci/zoran/zoran_card.c
index 1136d92..9d2697f 100644
--- a/drivers/media/pci/zoran/zoran_card.c
+++ b/drivers/media/pci/zoran/zoran_card.c
@@ -50,7 +50,7 @@
 #include <linux/mutex.h>
 #include <linux/io.h>
 #include <media/v4l2-common.h>
-#include <media/bt819.h>
+#include <media/i2c/bt819.h>
 
 #include "videocodec.h"
 #include "zoran.h"
diff --git a/drivers/media/platform/Kconfig b/drivers/media/platform/Kconfig
index ccbc974..0c53805 100644
--- a/drivers/media/platform/Kconfig
+++ b/drivers/media/platform/Kconfig
@@ -38,7 +38,7 @@
 	depends on MEDIA_CAMERA_SUPPORT
 	depends on VIDEO_DEV && I2C && HAS_DMA
 	depends on ARCH_SHMOBILE || COMPILE_TEST
-	select VIDEOBUF_DMA_CONTIG
+	select VIDEOBUF2_DMA_CONTIG
 	help
 	  Support for the Video Output Unit (VOU) on SuperH SoCs.
 
diff --git a/drivers/media/platform/am437x/am437x-vpfe.c b/drivers/media/platform/am437x/am437x-vpfe.c
index f0480d6..de32e3a 100644
--- a/drivers/media/platform/am437x/am437x-vpfe.c
+++ b/drivers/media/platform/am437x/am437x-vpfe.c
@@ -1281,7 +1281,7 @@
  */
 static inline void vpfe_process_buffer_complete(struct vpfe_device *vpfe)
 {
-	v4l2_get_timestamp(&vpfe->cur_frm->vb.timestamp);
+	vpfe->cur_frm->vb.vb2_buf.timestamp = ktime_get_ns();
 	vpfe->cur_frm->vb.field = vpfe->fmt.fmt.pix.field;
 	vpfe->cur_frm->vb.sequence = vpfe->sequence++;
 	vb2_buffer_done(&vpfe->cur_frm->vb.vb2_buf, VB2_BUF_STATE_DONE);
@@ -1898,7 +1898,6 @@
 /*
  * vpfe_queue_setup - Callback function for buffer setup.
  * @vq: vb2_queue ptr
- * @fmt: v4l2 format
  * @nbuffers: ptr to number of buffers requested by application
  * @nplanes:: contains number of distinct video planes needed to hold a frame
  * @sizes[]: contains the size (in bytes) of each plane.
@@ -1908,22 +1907,24 @@
  * the buffer count and buffer size
  */
 static int vpfe_queue_setup(struct vb2_queue *vq,
-			    const void *parg,
 			    unsigned int *nbuffers, unsigned int *nplanes,
 			    unsigned int sizes[], void *alloc_ctxs[])
 {
-	const struct v4l2_format *fmt = parg;
 	struct vpfe_device *vpfe = vb2_get_drv_priv(vq);
-
-	if (fmt && fmt->fmt.pix.sizeimage < vpfe->fmt.fmt.pix.sizeimage)
-		return -EINVAL;
+	unsigned size = vpfe->fmt.fmt.pix.sizeimage;
 
 	if (vq->num_buffers + *nbuffers < 3)
 		*nbuffers = 3 - vq->num_buffers;
+	alloc_ctxs[0] = vpfe->alloc_ctx;
+
+	if (*nplanes) {
+		if (sizes[0] < size)
+			return -EINVAL;
+		size = sizes[0];
+	}
 
 	*nplanes = 1;
-	sizes[0] = fmt ? fmt->fmt.pix.sizeimage : vpfe->fmt.fmt.pix.sizeimage;
-	alloc_ctxs[0] = vpfe->alloc_ctx;
+	sizes[0] = size;
 
 	vpfe_dbg(1, vpfe,
 		"nbuffers=%d, size=%u\n", *nbuffers, sizes[0]);
diff --git a/drivers/media/platform/blackfin/bfin_capture.c b/drivers/media/platform/blackfin/bfin_capture.c
index 7764b9c..d0092da 100644
--- a/drivers/media/platform/blackfin/bfin_capture.c
+++ b/drivers/media/platform/blackfin/bfin_capture.c
@@ -202,22 +202,20 @@
 }
 
 static int bcap_queue_setup(struct vb2_queue *vq,
-				const void *parg,
 				unsigned int *nbuffers, unsigned int *nplanes,
 				unsigned int sizes[], void *alloc_ctxs[])
 {
-	const struct v4l2_format *fmt = parg;
 	struct bcap_device *bcap_dev = vb2_get_drv_priv(vq);
 
-	if (fmt && fmt->fmt.pix.sizeimage < bcap_dev->fmt.sizeimage)
-		return -EINVAL;
-
 	if (vq->num_buffers + *nbuffers < 2)
 		*nbuffers = 2;
+	alloc_ctxs[0] = bcap_dev->alloc_ctx;
+
+	if (*nplanes)
+		return sizes[0] < bcap_dev->fmt.sizeimage ? -EINVAL : 0;
 
 	*nplanes = 1;
-	sizes[0] = fmt ? fmt->fmt.pix.sizeimage : bcap_dev->fmt.sizeimage;
-	alloc_ctxs[0] = bcap_dev->alloc_ctx;
+	sizes[0] = bcap_dev->fmt.sizeimage;
 
 	return 0;
 }
@@ -406,7 +404,7 @@
 	spin_lock(&bcap_dev->lock);
 
 	if (!list_empty(&bcap_dev->dma_queue)) {
-		v4l2_get_timestamp(&vbuf->timestamp);
+		vb->timestamp = ktime_get_ns();
 		if (ppi->err) {
 			vb2_buffer_done(vb, VB2_BUF_STATE_ERROR);
 			ppi->err = false;
diff --git a/drivers/media/platform/coda/coda-bit.c b/drivers/media/platform/coda/coda-bit.c
index 654e964..7d28899 100644
--- a/drivers/media/platform/coda/coda-bit.c
+++ b/drivers/media/platform/coda/coda-bit.c
@@ -246,7 +246,7 @@
 
 		/* Drop frames that do not start/end with a SOI/EOI markers */
 		if (ctx->codec->src_fourcc == V4L2_PIX_FMT_JPEG &&
-		    !coda_jpeg_check_buffer(ctx, src_buf)) {
+		    !coda_jpeg_check_buffer(ctx, &src_buf->vb2_buf)) {
 			v4l2_err(&ctx->dev->v4l2_dev,
 				 "dropping invalid JPEG frame %d\n",
 				 ctx->qsequence);
@@ -279,7 +279,7 @@
 			if (meta) {
 				meta->sequence = src_buf->sequence;
 				meta->timecode = src_buf->timecode;
-				meta->timestamp = src_buf->timestamp;
+				meta->timestamp = src_buf->vb2_buf.timestamp;
 				meta->start = start;
 				meta->end = ctx->bitstream_fifo.kfifo.in &
 					    ctx->bitstream_fifo.kfifo.mask;
@@ -1364,7 +1364,7 @@
 		dst_buf->flags &= ~V4L2_BUF_FLAG_KEYFRAME;
 	}
 
-	dst_buf->timestamp = src_buf->timestamp;
+	dst_buf->vb2_buf.timestamp = src_buf->vb2_buf.timestamp;
 	dst_buf->flags &= ~V4L2_BUF_FLAG_TSTAMP_SRC_MASK;
 	dst_buf->flags |=
 		src_buf->flags & V4L2_BUF_FLAG_TSTAMP_SRC_MASK;
@@ -2040,7 +2040,7 @@
 		dst_buf->flags |= ctx->frame_types[ctx->display_idx];
 		meta = &ctx->frame_metas[ctx->display_idx];
 		dst_buf->timecode = meta->timecode;
-		dst_buf->timestamp = meta->timestamp;
+		dst_buf->vb2_buf.timestamp = meta->timestamp;
 
 		trace_coda_dec_rot_done(ctx, dst_buf, meta);
 
diff --git a/drivers/media/platform/coda/coda-common.c b/drivers/media/platform/coda/coda-common.c
index 15516a6e..2d782ce 100644
--- a/drivers/media/platform/coda/coda-common.c
+++ b/drivers/media/platform/coda/coda-common.c
@@ -28,7 +28,7 @@
 #include <linux/slab.h>
 #include <linux/videodev2.h>
 #include <linux/of.h>
-#include <linux/platform_data/coda.h>
+#include <linux/platform_data/media/coda.h>
 #include <linux/reset.h>
 
 #include <media/v4l2-ctrls.h>
@@ -131,6 +131,7 @@
 	CODA_CODEC(CODA7_MODE_ENCODE_MP4,  V4L2_PIX_FMT_YUV420, V4L2_PIX_FMT_MPEG4,  1280, 720),
 	CODA_CODEC(CODA7_MODE_ENCODE_MJPG, V4L2_PIX_FMT_YUV420, V4L2_PIX_FMT_JPEG,   8192, 8192),
 	CODA_CODEC(CODA7_MODE_DECODE_H264, V4L2_PIX_FMT_H264,   V4L2_PIX_FMT_YUV420, 1920, 1088),
+	CODA_CODEC(CODA7_MODE_DECODE_MP2,  V4L2_PIX_FMT_MPEG2,  V4L2_PIX_FMT_YUV420, 1920, 1088),
 	CODA_CODEC(CODA7_MODE_DECODE_MP4,  V4L2_PIX_FMT_MPEG4,  V4L2_PIX_FMT_YUV420, 1920, 1088),
 	CODA_CODEC(CODA7_MODE_DECODE_MJPG, V4L2_PIX_FMT_JPEG,   V4L2_PIX_FMT_YUV420, 8192, 8192),
 };
@@ -139,6 +140,7 @@
 	CODA_CODEC(CODA9_MODE_ENCODE_H264, V4L2_PIX_FMT_YUV420, V4L2_PIX_FMT_H264,   1920, 1088),
 	CODA_CODEC(CODA9_MODE_ENCODE_MP4,  V4L2_PIX_FMT_YUV420, V4L2_PIX_FMT_MPEG4,  1920, 1088),
 	CODA_CODEC(CODA9_MODE_DECODE_H264, V4L2_PIX_FMT_H264,   V4L2_PIX_FMT_YUV420, 1920, 1088),
+	CODA_CODEC(CODA9_MODE_DECODE_MP2,  V4L2_PIX_FMT_MPEG2,  V4L2_PIX_FMT_YUV420, 1920, 1088),
 	CODA_CODEC(CODA9_MODE_DECODE_MP4,  V4L2_PIX_FMT_MPEG4,  V4L2_PIX_FMT_YUV420, 1920, 1088),
 };
 
@@ -187,6 +189,7 @@
 	.ops = &coda_bit_decode_ops,
 	.src_formats = {
 		V4L2_PIX_FMT_H264,
+		V4L2_PIX_FMT_MPEG2,
 		V4L2_PIX_FMT_MPEG4,
 	},
 	.dst_formats = {
@@ -293,7 +296,8 @@
 		*max_h = h;
 }
 
-const struct coda_video_device *to_coda_video_device(struct video_device *vdev)
+static const struct coda_video_device *to_coda_video_device(struct video_device
+							    *vdev)
 {
 	struct coda_dev *dev = video_get_drvdata(vdev);
 	unsigned int i = vdev - dev->vfd;
@@ -469,6 +473,7 @@
 		/* fallthrough */
 	case V4L2_PIX_FMT_H264:
 	case V4L2_PIX_FMT_MPEG4:
+	case V4L2_PIX_FMT_MPEG2:
 		f->fmt.pix.bytesperline = 0;
 		f->fmt.pix.sizeimage = coda_estimate_sizeimage(ctx,
 							f->fmt.pix.sizeimage,
@@ -920,6 +925,7 @@
 	.vidioc_expbuf		= v4l2_m2m_ioctl_expbuf,
 	.vidioc_dqbuf		= v4l2_m2m_ioctl_dqbuf,
 	.vidioc_create_bufs	= v4l2_m2m_ioctl_create_bufs,
+	.vidioc_prepare_buf	= v4l2_m2m_ioctl_prepare_buf,
 
 	.vidioc_streamon	= v4l2_m2m_ioctl_streamon,
 	.vidioc_streamoff	= v4l2_m2m_ioctl_streamoff,
@@ -1131,7 +1137,7 @@
 /*
  * Queue operations
  */
-static int coda_queue_setup(struct vb2_queue *vq, const void *parg,
+static int coda_queue_setup(struct vb2_queue *vq,
 				unsigned int *nbuffers, unsigned int *nplanes,
 				unsigned int sizes[], void *alloc_ctxs[])
 {
@@ -1250,6 +1256,9 @@
 	struct vb2_v4l2_buffer *buf;
 	int ret = 0;
 
+	if (count < 1)
+		return -EINVAL;
+
 	q_data_src = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT);
 	if (q->type == V4L2_BUF_TYPE_VIDEO_OUTPUT) {
 		if (ctx->inst_type == CODA_INST_DECODER && ctx->use_bit) {
@@ -1262,20 +1271,10 @@
 				ret = -EINVAL;
 				goto err;
 			}
-		} else {
-			if (count < 1) {
-				ret = -EINVAL;
-				goto err;
-			}
 		}
 
 		ctx->streamon_out = 1;
 	} else {
-		if (count < 1) {
-			ret = -EINVAL;
-			goto err;
-		}
-
 		ctx->streamon_cap = 1;
 	}
 
diff --git a/drivers/media/platform/coda/coda-jpeg.c b/drivers/media/platform/coda/coda-jpeg.c
index 96cd42a..9f899a6 100644
--- a/drivers/media/platform/coda/coda-jpeg.c
+++ b/drivers/media/platform/coda/coda-jpeg.c
@@ -178,14 +178,28 @@
 	return 0;
 }
 
-bool coda_jpeg_check_buffer(struct coda_ctx *ctx, struct vb2_v4l2_buffer *vb)
+bool coda_jpeg_check_buffer(struct coda_ctx *ctx, struct vb2_buffer *vb)
 {
-	void *vaddr = vb2_plane_vaddr(&vb->vb2_buf, 0);
-	u16 soi = be16_to_cpup((__be16 *)vaddr);
-	u16 eoi = be16_to_cpup((__be16 *)(vaddr +
-			  vb2_get_plane_payload(&vb->vb2_buf, 0) - 2));
+	void *vaddr = vb2_plane_vaddr(vb, 0);
+	u16 soi, eoi;
+	int len, i;
 
-	return soi == SOI_MARKER && eoi == EOI_MARKER;
+	soi = be16_to_cpup((__be16 *)vaddr);
+	if (soi != SOI_MARKER)
+		return false;
+
+	len = vb2_get_plane_payload(vb, 0);
+	vaddr += len - 2;
+	for (i = 0; i < 32; i++) {
+		eoi = be16_to_cpup((__be16 *)(vaddr - i));
+		if (eoi == EOI_MARKER) {
+			if (i > 0)
+				vb2_set_plane_payload(vb, 0, len - i);
+			return true;
+		}
+	}
+
+	return false;
 }
 
 /*
diff --git a/drivers/media/platform/coda/coda.h b/drivers/media/platform/coda/coda.h
index 96532b0..d08e984 100644
--- a/drivers/media/platform/coda/coda.h
+++ b/drivers/media/platform/coda/coda.h
@@ -138,7 +138,7 @@
 	struct list_head	list;
 	u32			sequence;
 	struct v4l2_timecode	timecode;
-	struct timeval		timestamp;
+	u64			timestamp;
 	u32			start;
 	u32			end;
 };
@@ -289,7 +289,7 @@
 
 int coda_h264_padding(int size, char *p);
 
-bool coda_jpeg_check_buffer(struct coda_ctx *ctx, struct vb2_v4l2_buffer *vb);
+bool coda_jpeg_check_buffer(struct coda_ctx *ctx, struct vb2_buffer *vb);
 int coda_jpeg_write_tables(struct coda_ctx *ctx);
 void coda_set_jpeg_compression_quality(struct coda_ctx *ctx, int quality);
 
diff --git a/drivers/media/platform/davinci/Kconfig b/drivers/media/platform/davinci/Kconfig
index 469e9d2..554e710 100644
--- a/drivers/media/platform/davinci/Kconfig
+++ b/drivers/media/platform/davinci/Kconfig
@@ -3,6 +3,7 @@
 	depends on VIDEO_V4L2
 	depends on ARCH_DAVINCI || COMPILE_TEST
 	depends on HAS_DMA
+	depends on I2C
 	select VIDEOBUF2_DMA_CONTIG
 	select VIDEO_ADV7343 if MEDIA_SUBDRV_AUTOSELECT
 	select VIDEO_THS7303 if MEDIA_SUBDRV_AUTOSELECT
@@ -19,6 +20,7 @@
 	depends on VIDEO_V4L2
 	depends on ARCH_DAVINCI || COMPILE_TEST
 	depends on HAS_DMA
+	depends on I2C
 	select VIDEOBUF2_DMA_CONTIG
 	help
 	  Enables Davinci VPIF module used for capture devices.
@@ -33,6 +35,7 @@
 	depends on VIDEO_V4L2
 	depends on ARCH_DAVINCI || COMPILE_TEST
 	depends on HAS_DMA
+	depends on I2C
 	select VIDEOBUF_DMA_CONTIG
 	help
 	   Enables DaVinci CCD hw module. DaVinci CCDC hw interfaces
@@ -49,6 +52,7 @@
 	depends on VIDEO_V4L2
 	depends on ARCH_DAVINCI || COMPILE_TEST
 	depends on HAS_DMA
+	depends on I2C
 	select VIDEOBUF_DMA_CONTIG
 	help
 	   Enables DM355 CCD hw module. DM355 CCDC hw interfaces
@@ -64,6 +68,7 @@
 	tristate "TI DM365 ISIF video capture driver"
 	depends on VIDEO_V4L2 && ARCH_DAVINCI
 	depends on HAS_DMA
+	depends on I2C
 	select VIDEOBUF_DMA_CONTIG
 	help
 	   Enables ISIF hw module. This is the hardware module for
@@ -77,6 +82,7 @@
 	tristate "TI DaVinci VPBE V4L2-Display driver"
 	depends on VIDEO_V4L2 && ARCH_DAVINCI
 	depends on HAS_DMA
+	depends on I2C
 	select VIDEOBUF2_DMA_CONTIG
 	help
 	    Enables Davinci VPBE module used for display devices.
diff --git a/drivers/media/platform/davinci/vpbe_display.c b/drivers/media/platform/davinci/vpbe_display.c
index 6d91422..0abcdfe 100644
--- a/drivers/media/platform/davinci/vpbe_display.c
+++ b/drivers/media/platform/davinci/vpbe_display.c
@@ -74,7 +74,7 @@
 	if (layer->cur_frm == layer->next_frm)
 		return;
 
-	v4l2_get_timestamp(&layer->cur_frm->vb.timestamp);
+	layer->cur_frm->vb.vb2_buf.timestamp = ktime_get_ns();
 	vb2_buffer_done(&layer->cur_frm->vb.vb2_buf, VB2_BUF_STATE_DONE);
 	/* Make cur_frm pointing to next_frm */
 	layer->cur_frm = layer->next_frm;
@@ -228,28 +228,27 @@
  * This function allocates memory for the buffers
  */
 static int
-vpbe_buffer_queue_setup(struct vb2_queue *vq, const void *parg,
+vpbe_buffer_queue_setup(struct vb2_queue *vq,
 			unsigned int *nbuffers, unsigned int *nplanes,
 			unsigned int sizes[], void *alloc_ctxs[])
 
 {
-	const struct v4l2_format *fmt = parg;
 	/* Get the file handle object and layer object */
 	struct vpbe_layer *layer = vb2_get_drv_priv(vq);
 	struct vpbe_device *vpbe_dev = layer->disp_dev->vpbe_dev;
 
 	v4l2_dbg(1, debug, &vpbe_dev->v4l2_dev, "vpbe_buffer_setup\n");
 
-	if (fmt && fmt->fmt.pix.sizeimage < layer->pix_fmt.sizeimage)
-		return -EINVAL;
-
 	/* Store number of buffers allocated in numbuffer member */
 	if (vq->num_buffers + *nbuffers < VPBE_DEFAULT_NUM_BUFS)
 		*nbuffers = VPBE_DEFAULT_NUM_BUFS - vq->num_buffers;
+	alloc_ctxs[0] = layer->alloc_ctx;
+
+	if (*nplanes)
+		return sizes[0] < layer->pix_fmt.sizeimage ? -EINVAL : 0;
 
 	*nplanes = 1;
-	sizes[0] = fmt ? fmt->fmt.pix.sizeimage : layer->pix_fmt.sizeimage;
-	alloc_ctxs[0] = layer->alloc_ctx;
+	sizes[0] = layer->pix_fmt.sizeimage;
 
 	return 0;
 }
diff --git a/drivers/media/platform/davinci/vpif_capture.c b/drivers/media/platform/davinci/vpif_capture.c
index c1e573b..08f7028 100644
--- a/drivers/media/platform/davinci/vpif_capture.c
+++ b/drivers/media/platform/davinci/vpif_capture.c
@@ -104,7 +104,6 @@
 /**
  * vpif_buffer_queue_setup : Callback function for buffer setup.
  * @vq: vb2_queue ptr
- * @fmt: v4l2 format
  * @nbuffers: ptr to number of buffers requested by application
  * @nplanes:: contains number of distinct video planes needed to hold a frame
  * @sizes[]: contains the size (in bytes) of each plane.
@@ -114,26 +113,26 @@
  * the buffer count and buffer size
  */
 static int vpif_buffer_queue_setup(struct vb2_queue *vq,
-				const void *parg,
 				unsigned int *nbuffers, unsigned int *nplanes,
 				unsigned int sizes[], void *alloc_ctxs[])
 {
-	const struct v4l2_format *fmt = parg;
 	struct channel_obj *ch = vb2_get_drv_priv(vq);
-	struct common_obj *common;
-
-	common = &ch->common[VPIF_VIDEO_INDEX];
+	struct common_obj *common = &ch->common[VPIF_VIDEO_INDEX];
+	unsigned size = common->fmt.fmt.pix.sizeimage;
 
 	vpif_dbg(2, debug, "vpif_buffer_setup\n");
 
-	if (fmt && fmt->fmt.pix.sizeimage < common->fmt.fmt.pix.sizeimage)
-		return -EINVAL;
+	if (*nplanes) {
+		if (sizes[0] < size)
+			return -EINVAL;
+		size = sizes[0];
+	}
 
 	if (vq->num_buffers + *nbuffers < 3)
 		*nbuffers = 3 - vq->num_buffers;
 
 	*nplanes = 1;
-	sizes[0] = fmt ? fmt->fmt.pix.sizeimage : common->fmt.fmt.pix.sizeimage;
+	sizes[0] = size;
 	alloc_ctxs[0] = common->alloc_ctx;
 
 	/* Calculate the offset for Y and C data in the buffer */
@@ -331,7 +330,7 @@
  */
 static void vpif_process_buffer_complete(struct common_obj *common)
 {
-	v4l2_get_timestamp(&common->cur_frm->vb.timestamp);
+	common->cur_frm->vb.vb2_buf.timestamp = ktime_get_ns();
 	vb2_buffer_done(&common->cur_frm->vb.vb2_buf, VB2_BUF_STATE_DONE);
 	/* Make curFrm pointing to nextFrm */
 	common->cur_frm = common->next_frm;
diff --git a/drivers/media/platform/davinci/vpif_display.c b/drivers/media/platform/davinci/vpif_display.c
index fd27803..f40755c 100644
--- a/drivers/media/platform/davinci/vpif_display.c
+++ b/drivers/media/platform/davinci/vpif_display.c
@@ -99,7 +99,6 @@
 /**
  * vpif_buffer_queue_setup : Callback function for buffer setup.
  * @vq: vb2_queue ptr
- * @fmt: v4l2 format
  * @nbuffers: ptr to number of buffers requested by application
  * @nplanes:: contains number of distinct video planes needed to hold a frame
  * @sizes[]: contains the size (in bytes) of each plane.
@@ -109,22 +108,24 @@
  * the buffer count and buffer size
  */
 static int vpif_buffer_queue_setup(struct vb2_queue *vq,
-				const void *parg,
 				unsigned int *nbuffers, unsigned int *nplanes,
 				unsigned int sizes[], void *alloc_ctxs[])
 {
-	const struct v4l2_format *fmt = parg;
 	struct channel_obj *ch = vb2_get_drv_priv(vq);
 	struct common_obj *common = &ch->common[VPIF_VIDEO_INDEX];
+	unsigned size = common->fmt.fmt.pix.sizeimage;
 
-	if (fmt && fmt->fmt.pix.sizeimage < common->fmt.fmt.pix.sizeimage)
-		return -EINVAL;
+	if (*nplanes) {
+		if (sizes[0] < size)
+			return -EINVAL;
+		size = sizes[0];
+	}
 
 	if (vq->num_buffers + *nbuffers < 3)
 		*nbuffers = 3 - vq->num_buffers;
 
 	*nplanes = 1;
-	sizes[0] = fmt ? fmt->fmt.pix.sizeimage : common->fmt.fmt.pix.sizeimage;
+	sizes[0] = size;
 	alloc_ctxs[0] = common->alloc_ctx;
 
 	/* Calculate the offset for Y and C data  in the buffer */
@@ -330,7 +331,7 @@
 		/* one frame is displayed If next frame is
 		 *  available, release cur_frm and move on */
 		/* Copy frame display time */
-		v4l2_get_timestamp(&common->cur_frm->vb.timestamp);
+		common->cur_frm->vb.vb2_buf.timestamp = ktime_get_ns();
 		/* Change status of the cur_frm */
 		vb2_buffer_done(&common->cur_frm->vb.vb2_buf,
 					VB2_BUF_STATE_DONE);
@@ -386,8 +387,8 @@
 			if (!channel_first_int[i][channel_id]) {
 				/* Mark status of the cur_frm to
 				 * done and unlock semaphore on it */
-				v4l2_get_timestamp(
-					&common->cur_frm->vb.timestamp);
+				common->cur_frm->vb.vb2_buf.timestamp =
+						ktime_get_ns();
 				vb2_buffer_done(&common->cur_frm->vb.vb2_buf,
 						VB2_BUF_STATE_DONE);
 				/* Make cur_frm pointing to next_frm */
diff --git a/drivers/media/platform/exynos-gsc/gsc-m2m.c b/drivers/media/platform/exynos-gsc/gsc-m2m.c
index d82e717..93782f1 100644
--- a/drivers/media/platform/exynos-gsc/gsc-m2m.c
+++ b/drivers/media/platform/exynos-gsc/gsc-m2m.c
@@ -86,7 +86,7 @@
 	dst_vb = v4l2_m2m_dst_buf_remove(ctx->m2m_ctx);
 
 	if (src_vb && dst_vb) {
-		dst_vb->timestamp = src_vb->timestamp;
+		dst_vb->vb2_buf.timestamp = src_vb->vb2_buf.timestamp;
 		dst_vb->timecode = src_vb->timecode;
 		dst_vb->flags &= ~V4L2_BUF_FLAG_TSTAMP_SRC_MASK;
 		dst_vb->flags |=
@@ -125,7 +125,7 @@
 	if (ret)
 		return ret;
 
-	dst_vb->timestamp = src_vb->timestamp;
+	dst_vb->vb2_buf.timestamp = src_vb->vb2_buf.timestamp;
 
 	return 0;
 }
@@ -212,7 +212,6 @@
 }
 
 static int gsc_m2m_queue_setup(struct vb2_queue *vq,
-			const void *parg,
 			unsigned int *num_buffers, unsigned int *num_planes,
 			unsigned int sizes[], void *allocators[])
 {
diff --git a/drivers/media/platform/exynos4-is/common.c b/drivers/media/platform/exynos4-is/common.c
index 0eb34ec..b6716c5 100644
--- a/drivers/media/platform/exynos4-is/common.c
+++ b/drivers/media/platform/exynos4-is/common.c
@@ -10,7 +10,7 @@
  */
 
 #include <linux/module.h>
-#include <media/exynos-fimc.h>
+#include <media/drv-intf/exynos-fimc.h>
 #include "common.h"
 
 /* Called with the media graph mutex held or entity->stream_count > 0. */
diff --git a/drivers/media/platform/exynos4-is/fimc-capture.c b/drivers/media/platform/exynos4-is/fimc-capture.c
index 99e5732..0d549a6 100644
--- a/drivers/media/platform/exynos4-is/fimc-capture.c
+++ b/drivers/media/platform/exynos4-is/fimc-capture.c
@@ -193,7 +193,7 @@
 	    test_bit(ST_CAPT_RUN, &fimc->state) && deq_buf) {
 		v_buf = fimc_active_queue_pop(cap);
 
-		v4l2_get_timestamp(&v_buf->vb.timestamp);
+		v_buf->vb.vb2_buf.timestamp = ktime_get_ns();
 		v_buf->vb.sequence = cap->frame_count++;
 
 		vb2_buffer_done(&v_buf->vb.vb2_buf, VB2_BUF_STATE_DONE);
@@ -338,37 +338,36 @@
 
 }
 
-static int queue_setup(struct vb2_queue *vq, const void *parg,
+static int queue_setup(struct vb2_queue *vq,
 		       unsigned int *num_buffers, unsigned int *num_planes,
 		       unsigned int sizes[], void *allocators[])
 {
-	const struct v4l2_format *pfmt = parg;
-	const struct v4l2_pix_format_mplane *pixm = NULL;
 	struct fimc_ctx *ctx = vq->drv_priv;
 	struct fimc_frame *frame = &ctx->d_frame;
 	struct fimc_fmt *fmt = frame->fmt;
-	unsigned long wh;
+	unsigned long wh = frame->f_width * frame->f_height;
 	int i;
 
-	if (pfmt) {
-		pixm = &pfmt->fmt.pix_mp;
-		fmt = fimc_find_format(&pixm->pixelformat, NULL,
-				       FMT_FLAGS_CAM | FMT_FLAGS_M2M, -1);
-		wh = pixm->width * pixm->height;
-	} else {
-		wh = frame->f_width * frame->f_height;
-	}
-
 	if (fmt == NULL)
 		return -EINVAL;
 
+	if (*num_planes) {
+		if (*num_planes != fmt->memplanes)
+			return -EINVAL;
+		for (i = 0; i < *num_planes; i++) {
+			if (sizes[i] < (wh * fmt->depth[i]) / 8)
+				return -EINVAL;
+			allocators[i] = ctx->fimc_dev->alloc_ctx;
+		}
+		return 0;
+	}
+
 	*num_planes = fmt->memplanes;
 
 	for (i = 0; i < fmt->memplanes; i++) {
 		unsigned int size = (wh * fmt->depth[i]) / 8;
-		if (pixm)
-			sizes[i] = max(size, pixm->plane_fmt[i].sizeimage);
-		else if (fimc_fmt_is_user_defined(fmt->color))
+
+		if (fimc_fmt_is_user_defined(fmt->color))
 			sizes[i] = frame->payload[i];
 		else
 			sizes[i] = max_t(u32, size, frame->payload[i]);
diff --git a/drivers/media/platform/exynos4-is/fimc-core.h b/drivers/media/platform/exynos4-is/fimc-core.h
index d336fa2..6b74354 100644
--- a/drivers/media/platform/exynos4-is/fimc-core.h
+++ b/drivers/media/platform/exynos4-is/fimc-core.h
@@ -27,7 +27,7 @@
 #include <media/v4l2-device.h>
 #include <media/v4l2-mem2mem.h>
 #include <media/v4l2-mediabus.h>
-#include <media/exynos-fimc.h>
+#include <media/drv-intf/exynos-fimc.h>
 
 #define dbg(fmt, args...) \
 	pr_debug("%s:%d: " fmt "\n", __func__, __LINE__, ##args)
diff --git a/drivers/media/platform/exynos4-is/fimc-isp-video.c b/drivers/media/platform/exynos4-is/fimc-isp-video.c
index 6e66484..0dd22ec 100644
--- a/drivers/media/platform/exynos4-is/fimc-isp-video.c
+++ b/drivers/media/platform/exynos4-is/fimc-isp-video.c
@@ -30,7 +30,7 @@
 #include <media/v4l2-ioctl.h>
 #include <media/videobuf2-v4l2.h>
 #include <media/videobuf2-dma-contig.h>
-#include <media/exynos-fimc.h>
+#include <media/drv-intf/exynos-fimc.h>
 
 #include "common.h"
 #include "media-dev.h"
@@ -39,39 +39,36 @@
 #include "fimc-is-param.h"
 
 static int isp_video_capture_queue_setup(struct vb2_queue *vq,
-			const void *parg,
 			unsigned int *num_buffers, unsigned int *num_planes,
 			unsigned int sizes[], void *allocators[])
 {
-	const struct v4l2_format *pfmt = parg;
 	struct fimc_isp *isp = vb2_get_drv_priv(vq);
 	struct v4l2_pix_format_mplane *vid_fmt = &isp->video_capture.pixfmt;
-	const struct v4l2_pix_format_mplane *pixm = NULL;
-	const struct fimc_fmt *fmt;
+	const struct fimc_fmt *fmt = isp->video_capture.format;
 	unsigned int wh, i;
 
-	if (pfmt) {
-		pixm = &pfmt->fmt.pix_mp;
-		fmt = fimc_isp_find_format(&pixm->pixelformat, NULL, -1);
-		wh = pixm->width * pixm->height;
-	} else {
-		fmt = isp->video_capture.format;
-		wh = vid_fmt->width * vid_fmt->height;
-	}
+	wh = vid_fmt->width * vid_fmt->height;
 
 	if (fmt == NULL)
 		return -EINVAL;
 
 	*num_buffers = clamp_t(u32, *num_buffers, FIMC_ISP_REQ_BUFS_MIN,
 						FIMC_ISP_REQ_BUFS_MAX);
+	if (*num_planes) {
+		if (*num_planes != fmt->memplanes)
+			return -EINVAL;
+		for (i = 0; i < *num_planes; i++) {
+			if (sizes[i] < (wh * fmt->depth[i]) / 8)
+				return -EINVAL;
+			allocators[i] = isp->alloc_ctx;
+		}
+		return 0;
+	}
+
 	*num_planes = fmt->memplanes;
 
 	for (i = 0; i < fmt->memplanes; i++) {
-		unsigned int size = (wh * fmt->depth[i]) / 8;
-		if (pixm)
-			sizes[i] = max(size, pixm->plane_fmt[i].sizeimage);
-		else
-			sizes[i] = size;
+		sizes[i] = (wh * fmt->depth[i]) / 8;
 		allocators[i] = isp->alloc_ctx;
 	}
 
@@ -254,7 +251,7 @@
 	buf_index = (is->i2h_cmd.args[1] - 1) % video->buf_count;
 	vbuf = &video->buffers[buf_index]->vb;
 
-	v4l2_get_timestamp(&vbuf->timestamp);
+	vbuf->vb2_buf.timestamp = ktime_get_ns();
 	vb2_buffer_done(&vbuf->vb2_buf, VB2_BUF_STATE_DONE);
 
 	video->buf_mask &= ~BIT(buf_index);
diff --git a/drivers/media/platform/exynos4-is/fimc-isp.h b/drivers/media/platform/exynos4-is/fimc-isp.h
index c2d25df..e0686b5 100644
--- a/drivers/media/platform/exynos4-is/fimc-isp.h
+++ b/drivers/media/platform/exynos4-is/fimc-isp.h
@@ -24,7 +24,7 @@
 #include <media/videobuf2-v4l2.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-mediabus.h>
-#include <media/exynos-fimc.h>
+#include <media/drv-intf/exynos-fimc.h>
 
 extern int fimc_isp_debug;
 
diff --git a/drivers/media/platform/exynos4-is/fimc-lite-reg.c b/drivers/media/platform/exynos4-is/fimc-lite-reg.c
index 0477716..f0acc550 100644
--- a/drivers/media/platform/exynos4-is/fimc-lite-reg.c
+++ b/drivers/media/platform/exynos4-is/fimc-lite-reg.c
@@ -12,7 +12,7 @@
 #include <linux/bitops.h>
 #include <linux/delay.h>
 #include <linux/io.h>
-#include <media/exynos-fimc.h>
+#include <media/drv-intf/exynos-fimc.h>
 
 #include "fimc-lite-reg.h"
 #include "fimc-lite.h"
diff --git a/drivers/media/platform/exynos4-is/fimc-lite.c b/drivers/media/platform/exynos4-is/fimc-lite.c
index 60660c3..639ee71 100644
--- a/drivers/media/platform/exynos4-is/fimc-lite.c
+++ b/drivers/media/platform/exynos4-is/fimc-lite.c
@@ -30,7 +30,7 @@
 #include <media/v4l2-mem2mem.h>
 #include <media/videobuf2-v4l2.h>
 #include <media/videobuf2-dma-contig.h>
-#include <media/exynos-fimc.h>
+#include <media/drv-intf/exynos-fimc.h>
 
 #include "common.h"
 #include "fimc-core.h"
@@ -292,7 +292,7 @@
 	    test_bit(ST_FLITE_RUN, &fimc->state) &&
 	    !list_empty(&fimc->active_buf_q)) {
 		vbuf = fimc_lite_active_queue_pop(fimc);
-		v4l2_get_timestamp(&vbuf->vb.timestamp);
+		vbuf->vb.vb2_buf.timestamp = ktime_get_ns();
 		vbuf->vb.sequence = fimc->frame_count++;
 		flite_hw_mask_dma_buffer(fimc, vbuf->index);
 		vb2_buffer_done(&vbuf->vb.vb2_buf, VB2_BUF_STATE_DONE);
@@ -355,37 +355,34 @@
 	fimc_lite_stop_capture(fimc, false);
 }
 
-static int queue_setup(struct vb2_queue *vq, const void *parg,
+static int queue_setup(struct vb2_queue *vq,
 		       unsigned int *num_buffers, unsigned int *num_planes,
 		       unsigned int sizes[], void *allocators[])
 {
-	const struct v4l2_format *pfmt = parg;
-	const struct v4l2_pix_format_mplane *pixm = NULL;
 	struct fimc_lite *fimc = vq->drv_priv;
 	struct flite_frame *frame = &fimc->out_frame;
 	const struct fimc_fmt *fmt = frame->fmt;
-	unsigned long wh;
+	unsigned long wh = frame->f_width * frame->f_height;
 	int i;
 
-	if (pfmt) {
-		pixm = &pfmt->fmt.pix_mp;
-		fmt = fimc_lite_find_format(&pixm->pixelformat, NULL, 0, -1);
-		wh = pixm->width * pixm->height;
-	} else {
-		wh = frame->f_width * frame->f_height;
-	}
-
 	if (fmt == NULL)
 		return -EINVAL;
 
+	if (*num_planes) {
+		if (*num_planes != fmt->memplanes)
+			return -EINVAL;
+		for (i = 0; i < *num_planes; i++) {
+			if (sizes[i] < (wh * fmt->depth[i]) / 8)
+				return -EINVAL;
+			allocators[i] = fimc->alloc_ctx;
+		}
+		return 0;
+	}
+
 	*num_planes = fmt->memplanes;
 
 	for (i = 0; i < fmt->memplanes; i++) {
-		unsigned int size = (wh * fmt->depth[i]) / 8;
-		if (pixm)
-			sizes[i] = max(size, pixm->plane_fmt[i].sizeimage);
-		else
-			sizes[i] = size;
+		sizes[i] = (wh * fmt->depth[i]) / 8;
 		allocators[i] = fimc->alloc_ctx;
 	}
 
diff --git a/drivers/media/platform/exynos4-is/fimc-lite.h b/drivers/media/platform/exynos4-is/fimc-lite.h
index b302305..11690d5 100644
--- a/drivers/media/platform/exynos4-is/fimc-lite.h
+++ b/drivers/media/platform/exynos4-is/fimc-lite.h
@@ -23,7 +23,7 @@
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-mediabus.h>
-#include <media/exynos-fimc.h>
+#include <media/drv-intf/exynos-fimc.h>
 
 #define FIMC_LITE_DRV_NAME	"exynos-fimc-lite"
 #define FLITE_CLK_NAME		"flite"
diff --git a/drivers/media/platform/exynos4-is/fimc-m2m.c b/drivers/media/platform/exynos4-is/fimc-m2m.c
index 4d1d64a4..5aa857c 100644
--- a/drivers/media/platform/exynos4-is/fimc-m2m.c
+++ b/drivers/media/platform/exynos4-is/fimc-m2m.c
@@ -132,7 +132,7 @@
 	if (ret)
 		goto dma_unlock;
 
-	dst_vb->timestamp = src_vb->timestamp;
+	dst_vb->vb2_buf.timestamp = src_vb->vb2_buf.timestamp;
 	dst_vb->flags &= ~V4L2_BUF_FLAG_TSTAMP_SRC_MASK;
 	dst_vb->flags |=
 		src_vb->flags & V4L2_BUF_FLAG_TSTAMP_SRC_MASK;
@@ -176,7 +176,7 @@
 	fimc_m2m_shutdown(priv);
 }
 
-static int fimc_queue_setup(struct vb2_queue *vq, const void *parg,
+static int fimc_queue_setup(struct vb2_queue *vq,
 			    unsigned int *num_buffers, unsigned int *num_planes,
 			    unsigned int sizes[], void *allocators[])
 {
diff --git a/drivers/media/platform/exynos4-is/fimc-reg.c b/drivers/media/platform/exynos4-is/fimc-reg.c
index df0cbcb..0806724 100644
--- a/drivers/media/platform/exynos4-is/fimc-reg.c
+++ b/drivers/media/platform/exynos4-is/fimc-reg.c
@@ -13,7 +13,7 @@
 #include <linux/io.h>
 #include <linux/regmap.h>
 
-#include <media/exynos-fimc.h>
+#include <media/drv-intf/exynos-fimc.h>
 #include "media-dev.h"
 
 #include "fimc-reg.h"
diff --git a/drivers/media/platform/exynos4-is/media-dev.c b/drivers/media/platform/exynos4-is/media-dev.c
index 4f5586a..9481ce3 100644
--- a/drivers/media/platform/exynos4-is/media-dev.c
+++ b/drivers/media/platform/exynos4-is/media-dev.c
@@ -31,7 +31,7 @@
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-of.h>
 #include <media/media-device.h>
-#include <media/exynos-fimc.h>
+#include <media/drv-intf/exynos-fimc.h>
 
 #include "media-dev.h"
 #include "fimc-core.h"
diff --git a/drivers/media/platform/exynos4-is/media-dev.h b/drivers/media/platform/exynos4-is/media-dev.h
index 0321454..93a96126 100644
--- a/drivers/media/platform/exynos4-is/media-dev.h
+++ b/drivers/media/platform/exynos4-is/media-dev.h
@@ -19,7 +19,7 @@
 #include <media/media-entity.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-subdev.h>
-#include <media/exynos-fimc.h>
+#include <media/drv-intf/exynos-fimc.h>
 
 #include "fimc-core.h"
 #include "fimc-lite.h"
diff --git a/drivers/media/platform/exynos4-is/mipi-csis.c b/drivers/media/platform/exynos4-is/mipi-csis.c
index 4b85105..ff5dabf 100644
--- a/drivers/media/platform/exynos4-is/mipi-csis.c
+++ b/drivers/media/platform/exynos4-is/mipi-csis.c
@@ -29,7 +29,7 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/videodev2.h>
-#include <media/exynos-fimc.h>
+#include <media/drv-intf/exynos-fimc.h>
 #include <media/v4l2-of.h>
 #include <media/v4l2-subdev.h>
 
diff --git a/drivers/media/platform/m2m-deinterlace.c b/drivers/media/platform/m2m-deinterlace.c
index 29973f9..7383818 100644
--- a/drivers/media/platform/m2m-deinterlace.c
+++ b/drivers/media/platform/m2m-deinterlace.c
@@ -207,7 +207,7 @@
 	src_vb = v4l2_m2m_src_buf_remove(curr_ctx->m2m_ctx);
 	dst_vb = v4l2_m2m_dst_buf_remove(curr_ctx->m2m_ctx);
 
-	dst_vb->timestamp = src_vb->timestamp;
+	dst_vb->vb2_buf.timestamp = src_vb->vb2_buf.timestamp;
 	dst_vb->flags &= ~V4L2_BUF_FLAG_TSTAMP_SRC_MASK;
 	dst_vb->flags |=
 		src_vb->flags & V4L2_BUF_FLAG_TSTAMP_SRC_MASK;
@@ -798,7 +798,6 @@
 };
 
 static int deinterlace_queue_setup(struct vb2_queue *vq,
-				const void *parg,
 				unsigned int *nbuffers, unsigned int *nplanes,
 				unsigned int sizes[], void *alloc_ctxs[])
 {
diff --git a/drivers/media/platform/marvell-ccic/mcam-core.c b/drivers/media/platform/marvell-ccic/mcam-core.c
index aa2b440..9b878de 100644
--- a/drivers/media/platform/marvell-ccic/mcam-core.c
+++ b/drivers/media/platform/marvell-ccic/mcam-core.c
@@ -25,7 +25,7 @@
 #include <media/v4l2-ioctl.h>
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-event.h>
-#include <media/ov7670.h>
+#include <media/i2c/ov7670.h>
 #include <media/videobuf2-vmalloc.h>
 #include <media/videobuf2-dma-contig.h>
 #include <media/videobuf2-dma-sg.h>
@@ -226,7 +226,7 @@
 	vbuf->vb2_buf.planes[0].bytesused = cam->pix_format.sizeimage;
 	vbuf->sequence = cam->buf_seq[frame];
 	vbuf->field = V4L2_FIELD_NONE;
-	v4l2_get_timestamp(&vbuf->timestamp);
+	vbuf->vb2_buf.timestamp = ktime_get_ns();
 	vb2_set_plane_payload(&vbuf->vb2_buf, 0, cam->pix_format.sizeimage);
 	vb2_buffer_done(&vbuf->vb2_buf, VB2_BUF_STATE_DONE);
 }
@@ -1049,24 +1049,25 @@
  */
 
 static int mcam_vb_queue_setup(struct vb2_queue *vq,
-		const void *parg, unsigned int *nbufs,
+		unsigned int *nbufs,
 		unsigned int *num_planes, unsigned int sizes[],
 		void *alloc_ctxs[])
 {
-	const struct v4l2_format *fmt = parg;
 	struct mcam_camera *cam = vb2_get_drv_priv(vq);
 	int minbufs = (cam->buffer_mode == B_DMA_contig) ? 3 : 2;
+	unsigned size = cam->pix_format.sizeimage;
 
-	if (fmt && fmt->fmt.pix.sizeimage < cam->pix_format.sizeimage)
-		return -EINVAL;
-	sizes[0] = fmt ? fmt->fmt.pix.sizeimage : cam->pix_format.sizeimage;
-	*num_planes = 1; /* Someday we have to support planar formats... */
 	if (*nbufs < minbufs)
 		*nbufs = minbufs;
 	if (cam->buffer_mode == B_DMA_contig)
 		alloc_ctxs[0] = cam->vb_alloc_ctx;
 	else if (cam->buffer_mode == B_DMA_sg)
 		alloc_ctxs[0] = cam->vb_alloc_ctx_sg;
+
+	if (*num_planes)
+		return sizes[0] < size ? -EINVAL : 0;
+	sizes[0] = size;
+	*num_planes = 1; /* Someday we have to support planar formats... */
 	return 0;
 }
 
diff --git a/drivers/media/platform/marvell-ccic/mmp-driver.c b/drivers/media/platform/marvell-ccic/mmp-driver.c
index b5f165a..816f4b6 100644
--- a/drivers/media/platform/marvell-ccic/mmp-driver.c
+++ b/drivers/media/platform/marvell-ccic/mmp-driver.c
@@ -18,7 +18,7 @@
 #include <linux/slab.h>
 #include <linux/videodev2.h>
 #include <media/v4l2-device.h>
-#include <media/mmp-camera.h>
+#include <linux/platform_data/media/mmp-camera.h>
 #include <linux/device.h>
 #include <linux/platform_device.h>
 #include <linux/gpio.h>
diff --git a/drivers/media/platform/mx2_emmaprp.c b/drivers/media/platform/mx2_emmaprp.c
index 03a1b60..3c4012d 100644
--- a/drivers/media/platform/mx2_emmaprp.c
+++ b/drivers/media/platform/mx2_emmaprp.c
@@ -375,7 +375,7 @@
 			src_vb = v4l2_m2m_src_buf_remove(curr_ctx->m2m_ctx);
 			dst_vb = v4l2_m2m_dst_buf_remove(curr_ctx->m2m_ctx);
 
-			dst_vb->timestamp = src_vb->timestamp;
+			dst_vb->vb2_buf.timestamp = src_vb->vb2_buf.timestamp;
 			dst_vb->flags &=
 				~V4L2_BUF_FLAG_TSTAMP_SRC_MASK;
 			dst_vb->flags |=
@@ -689,7 +689,6 @@
  * Queue operations
  */
 static int emmaprp_queue_setup(struct vb2_queue *vq,
-				const void *parg,
 				unsigned int *nbuffers, unsigned int *nplanes,
 				unsigned int sizes[], void *alloc_ctxs[])
 {
diff --git a/drivers/media/platform/omap/omap_vout_vrfb.c b/drivers/media/platform/omap/omap_vout_vrfb.c
index c6e2527..b8638e4 100644
--- a/drivers/media/platform/omap/omap_vout_vrfb.c
+++ b/drivers/media/platform/omap/omap_vout_vrfb.c
@@ -79,10 +79,12 @@
 	int j;
 
 	for (j = 0; j < VRFB_NUM_BUFS; j++) {
-		omap_vout_free_buffer(vout->smsshado_virt_addr[j],
-				vout->smsshado_size);
-		vout->smsshado_virt_addr[j] = 0;
-		vout->smsshado_phy_addr[j] = 0;
+		if (vout->smsshado_virt_addr[j]) {
+			omap_vout_free_buffer(vout->smsshado_virt_addr[j],
+					      vout->smsshado_size);
+			vout->smsshado_virt_addr[j] = 0;
+			vout->smsshado_phy_addr[j] = 0;
+		}
 	}
 }
 
diff --git a/drivers/media/platform/omap3isp/ispvideo.c b/drivers/media/platform/omap3isp/ispvideo.c
index f4f5916..ecadca3 100644
--- a/drivers/media/platform/omap3isp/ispvideo.c
+++ b/drivers/media/platform/omap3isp/ispvideo.c
@@ -320,7 +320,6 @@
  */
 
 static int isp_video_queue_setup(struct vb2_queue *queue,
-				 const void *parg,
 				 unsigned int *count, unsigned int *num_planes,
 				 unsigned int sizes[], void *alloc_ctxs[])
 {
@@ -467,7 +466,7 @@
 	list_del(&buf->irqlist);
 	spin_unlock_irqrestore(&video->irqlock, flags);
 
-	v4l2_get_timestamp(&buf->vb.timestamp);
+	buf->vb.vb2_buf.timestamp = ktime_get_ns();
 
 	/* Do frame number propagation only if this is the output video node.
 	 * Frame number either comes from the CSI receivers or it gets
diff --git a/drivers/media/platform/rcar_jpu.c b/drivers/media/platform/rcar_jpu.c
index f8e3e83..485f525 100644
--- a/drivers/media/platform/rcar_jpu.c
+++ b/drivers/media/platform/rcar_jpu.c
@@ -1015,28 +1015,33 @@
  * ============================================================================
  */
 static int jpu_queue_setup(struct vb2_queue *vq,
-			   const void *parg,
 			   unsigned int *nbuffers, unsigned int *nplanes,
 			   unsigned int sizes[], void *alloc_ctxs[])
 {
-	const struct v4l2_format *fmt = parg;
 	struct jpu_ctx *ctx = vb2_get_drv_priv(vq);
 	struct jpu_q_data *q_data;
 	unsigned int i;
 
 	q_data = jpu_get_q_data(ctx, vq->type);
 
+	if (*nplanes) {
+		if (*nplanes != q_data->format.num_planes)
+			return -EINVAL;
+
+		for (i = 0; i < *nplanes; i++) {
+			unsigned int q_size = q_data->format.plane_fmt[i].sizeimage;
+
+			if (sizes[i] < q_size)
+				return -EINVAL;
+			alloc_ctxs[i] = ctx->jpu->alloc_ctx;
+		}
+		return 0;
+	}
+
 	*nplanes = q_data->format.num_planes;
 
 	for (i = 0; i < *nplanes; i++) {
-		unsigned int q_size = q_data->format.plane_fmt[i].sizeimage;
-		unsigned int f_size = fmt ?
-			fmt->fmt.pix_mp.plane_fmt[i].sizeimage : 0;
-
-		if (fmt && f_size < q_size)
-			return -EINVAL;
-
-		sizes[i] = fmt ? f_size : q_size;
+		sizes[i] = q_data->format.plane_fmt[i].sizeimage;
 		alloc_ctxs[i] = ctx->jpu->alloc_ctx;
 	}
 
@@ -1300,17 +1305,17 @@
 	struct jpu *jpu = video_drvdata(file);
 	struct jpu_ctx *ctx = fh_to_ctx(file->private_data);
 
-	mutex_lock(&jpu->mutex);
-	if (--jpu->ref_count == 0)
-		clk_disable_unprepare(jpu->clk);
-	mutex_unlock(&jpu->mutex);
-
 	v4l2_m2m_ctx_release(ctx->fh.m2m_ctx);
 	v4l2_ctrl_handler_free(&ctx->ctrl_handler);
 	v4l2_fh_del(&ctx->fh);
 	v4l2_fh_exit(&ctx->fh);
 	kfree(ctx);
 
+	mutex_lock(&jpu->mutex);
+	if (--jpu->ref_count == 0)
+		clk_disable_unprepare(jpu->clk);
+	mutex_unlock(&jpu->mutex);
+
 	return 0;
 }
 
@@ -1560,12 +1565,9 @@
 		}
 
 		dst_buf->field = src_buf->field;
-		dst_buf->timestamp = src_buf->timestamp;
+		dst_buf->vb2_buf.timestamp = src_buf->vb2_buf.timestamp;
 		if (src_buf->flags & V4L2_BUF_FLAG_TIMECODE)
 			dst_buf->timecode = src_buf->timecode;
-		dst_buf->flags &= ~V4L2_BUF_FLAG_TSTAMP_SRC_MASK;
-		dst_buf->flags |= src_buf->flags &
-					V4L2_BUF_FLAG_TSTAMP_SRC_MASK;
 		dst_buf->flags = src_buf->flags &
 			(V4L2_BUF_FLAG_TIMECODE | V4L2_BUF_FLAG_KEYFRAME |
 			 V4L2_BUF_FLAG_PFRAME | V4L2_BUF_FLAG_BFRAME |
diff --git a/drivers/media/platform/s3c-camif/camif-capture.c b/drivers/media/platform/s3c-camif/camif-capture.c
index 537b858..ec3abbe 100644
--- a/drivers/media/platform/s3c-camif/camif-capture.c
+++ b/drivers/media/platform/s3c-camif/camif-capture.c
@@ -338,7 +338,7 @@
 
 		if (!WARN_ON(vbuf == NULL)) {
 			/* Dequeue a filled buffer */
-			v4l2_get_timestamp(&vbuf->vb.timestamp);
+			vbuf->vb.vb2_buf.timestamp = ktime_get_ns();
 			vbuf->vb.sequence = vp->frame_sequence++;
 			vb2_buffer_done(&vbuf->vb.vb2_buf, VB2_BUF_STATE_DONE);
 
@@ -435,38 +435,27 @@
 	camif_stop_capture(vp);
 }
 
-static int queue_setup(struct vb2_queue *vq, const void *parg,
+static int queue_setup(struct vb2_queue *vq,
 		       unsigned int *num_buffers, unsigned int *num_planes,
 		       unsigned int sizes[], void *allocators[])
 {
-	const struct v4l2_format *pfmt = parg;
-	const struct v4l2_pix_format *pix = NULL;
 	struct camif_vp *vp = vb2_get_drv_priv(vq);
 	struct camif_dev *camif = vp->camif;
 	struct camif_frame *frame = &vp->out_frame;
-	const struct camif_fmt *fmt;
+	const struct camif_fmt *fmt = vp->out_fmt;
 	unsigned int size;
 
-	if (pfmt) {
-		pix = &pfmt->fmt.pix;
-		fmt = s3c_camif_find_format(vp, &pix->pixelformat, -1);
-		if (fmt == NULL)
-			return -EINVAL;
-		size = (pix->width * pix->height * fmt->depth) / 8;
-	} else {
-		fmt = vp->out_fmt;
-		if (fmt == NULL)
-			return -EINVAL;
-		size = (frame->f_width * frame->f_height * fmt->depth) / 8;
-	}
+	if (fmt == NULL)
+		return -EINVAL;
+
+	size = (frame->f_width * frame->f_height * fmt->depth) / 8;
+	allocators[0] = camif->alloc_ctx;
+
+	if (*num_planes)
+		return sizes[0] < size ? -EINVAL : 0;
 
 	*num_planes = 1;
-
-	if (pix)
-		sizes[0] = max(size, pix->sizeimage);
-	else
-		sizes[0] = size;
-	allocators[0] = camif->alloc_ctx;
+	sizes[0] = size;
 
 	pr_debug("size: %u\n", sizes[0]);
 	return 0;
diff --git a/drivers/media/platform/s3c-camif/camif-core.h b/drivers/media/platform/s3c-camif/camif-core.h
index adaf196..57cbc3d 100644
--- a/drivers/media/platform/s3c-camif/camif-core.h
+++ b/drivers/media/platform/s3c-camif/camif-core.h
@@ -26,7 +26,7 @@
 #include <media/v4l2-device.h>
 #include <media/v4l2-mediabus.h>
 #include <media/videobuf2-v4l2.h>
-#include <media/s3c_camif.h>
+#include <media/drv-intf/s3c_camif.h>
 
 #define S3C_CAMIF_DRIVER_NAME	"s3c-camif"
 #define CAMIF_REQ_BUFS_MIN	3
diff --git a/drivers/media/platform/s3c-camif/camif-regs.h b/drivers/media/platform/s3c-camif/camif-regs.h
index af2d472..5ad36c1 100644
--- a/drivers/media/platform/s3c-camif/camif-regs.h
+++ b/drivers/media/platform/s3c-camif/camif-regs.h
@@ -13,7 +13,7 @@
 #define CAMIF_REGS_H_
 
 #include "camif-core.h"
-#include <media/s3c_camif.h>
+#include <media/drv-intf/s3c_camif.h>
 
 /*
  * The id argument indicates the processing path:
diff --git a/drivers/media/platform/s5p-g2d/g2d.c b/drivers/media/platform/s5p-g2d/g2d.c
index e1936d9..74bd46c 100644
--- a/drivers/media/platform/s5p-g2d/g2d.c
+++ b/drivers/media/platform/s5p-g2d/g2d.c
@@ -101,7 +101,7 @@
 	}
 }
 
-static int g2d_queue_setup(struct vb2_queue *vq, const void *parg,
+static int g2d_queue_setup(struct vb2_queue *vq,
 			   unsigned int *nbuffers, unsigned int *nplanes,
 			   unsigned int sizes[], void *alloc_ctxs[])
 {
@@ -552,7 +552,7 @@
 	BUG_ON(dst == NULL);
 
 	dst->timecode = src->timecode;
-	dst->timestamp = src->timestamp;
+	dst->vb2_buf.timestamp = src->vb2_buf.timestamp;
 	dst->flags &= ~V4L2_BUF_FLAG_TSTAMP_SRC_MASK;
 	dst->flags |=
 		src->flags & V4L2_BUF_FLAG_TSTAMP_SRC_MASK;
diff --git a/drivers/media/platform/s5p-jpeg/jpeg-core.c b/drivers/media/platform/s5p-jpeg/jpeg-core.c
index 4a608cb..c3b13a63 100644
--- a/drivers/media/platform/s5p-jpeg/jpeg-core.c
+++ b/drivers/media/platform/s5p-jpeg/jpeg-core.c
@@ -2430,7 +2430,6 @@
  */
 
 static int s5p_jpeg_queue_setup(struct vb2_queue *vq,
-			   const void *parg,
 			   unsigned int *nbuffers, unsigned int *nplanes,
 			   unsigned int sizes[], void *alloc_ctxs[])
 {
@@ -2621,7 +2620,7 @@
 	}
 
 	dst_buf->timecode = src_buf->timecode;
-	dst_buf->timestamp = src_buf->timestamp;
+	dst_buf->vb2_buf.timestamp = src_buf->vb2_buf.timestamp;
 	dst_buf->flags &= ~V4L2_BUF_FLAG_TSTAMP_SRC_MASK;
 	dst_buf->flags |=
 		src_buf->flags & V4L2_BUF_FLAG_TSTAMP_SRC_MASK;
@@ -2752,7 +2751,7 @@
 	dst_buf = v4l2_m2m_dst_buf_remove(curr_ctx->fh.m2m_ctx);
 
 	dst_buf->timecode = src_buf->timecode;
-	dst_buf->timestamp = src_buf->timestamp;
+	dst_buf->vb2_buf.timestamp = src_buf->vb2_buf.timestamp;
 
 	v4l2_m2m_buf_done(src_buf, state);
 	if (curr_ctx->mode == S5P_JPEG_ENCODE)
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc.c b/drivers/media/platform/s5p-mfc/s5p_mfc.c
index 3ffe2ec..927ab49 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc.c
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc.c
@@ -85,6 +85,26 @@
 	spin_unlock_irqrestore(&dev->condlock, flags);
 }
 
+int s5p_mfc_get_new_ctx(struct s5p_mfc_dev *dev)
+{
+	unsigned long flags;
+	int ctx;
+
+	spin_lock_irqsave(&dev->condlock, flags);
+	ctx = dev->curr_ctx;
+	do {
+		ctx = (ctx + 1) % MFC_NUM_CONTEXTS;
+		if (ctx == dev->curr_ctx) {
+			if (!test_bit(ctx, &dev->ctx_work_bits))
+				ctx = -EAGAIN;
+			break;
+		}
+	} while (!test_bit(ctx, &dev->ctx_work_bits));
+	spin_unlock_irqrestore(&dev->condlock, flags);
+
+	return ctx;
+}
+
 /* Wake up context wait_queue */
 static void wake_up_ctx(struct s5p_mfc_ctx *ctx, unsigned int reason,
 			unsigned int err)
@@ -105,6 +125,20 @@
 	wake_up(&dev->queue);
 }
 
+void s5p_mfc_cleanup_queue(struct list_head *lh, struct vb2_queue *vq)
+{
+	struct s5p_mfc_buf *b;
+	int i;
+
+	while (!list_empty(lh)) {
+		b = list_entry(lh->next, struct s5p_mfc_buf, list);
+		for (i = 0; i < b->b->vb2_buf.num_planes; i++)
+			vb2_set_plane_payload(&b->b->vb2_buf, i, 0);
+		vb2_buffer_done(&b->b->vb2_buf, VB2_BUF_STATE_ERROR);
+		list_del(&b->list);
+	}
+}
+
 static void s5p_mfc_watchdog(unsigned long arg)
 {
 	struct s5p_mfc_dev *dev = (struct s5p_mfc_dev *)arg;
@@ -150,10 +184,8 @@
 		if (!ctx)
 			continue;
 		ctx->state = MFCINST_ERROR;
-		s5p_mfc_hw_call_void(dev->mfc_ops, cleanup_queue,
-						&ctx->dst_queue, &ctx->vq_dst);
-		s5p_mfc_hw_call_void(dev->mfc_ops, cleanup_queue,
-						&ctx->src_queue, &ctx->vq_src);
+		s5p_mfc_cleanup_queue(&ctx->dst_queue, &ctx->vq_dst);
+		s5p_mfc_cleanup_queue(&ctx->src_queue, &ctx->vq_src);
 		clear_work_bit(ctx);
 		wake_up_ctx(ctx, S5P_MFC_R2H_CMD_ERR_RET, 0);
 	}
@@ -233,8 +265,8 @@
 				== dec_y_addr) {
 			dst_buf->b->timecode =
 						src_buf->b->timecode;
-			dst_buf->b->timestamp =
-						src_buf->b->timestamp;
+			dst_buf->b->vb2_buf.timestamp =
+						src_buf->b->vb2_buf.timestamp;
 			dst_buf->b->flags &=
 				~V4L2_BUF_FLAG_TSTAMP_SRC_MASK;
 			dst_buf->b->flags |=
@@ -327,7 +359,6 @@
 	unsigned int dst_frame_status;
 	unsigned int dec_frame_status;
 	struct s5p_mfc_buf *src_buf;
-	unsigned long flags;
 	unsigned int res_change;
 
 	dst_frame_status = s5p_mfc_hw_call(dev->mfc_ops, get_dspl_status, dev)
@@ -343,17 +374,16 @@
 	if (res_change == S5P_FIMV_RES_INCREASE ||
 		res_change == S5P_FIMV_RES_DECREASE) {
 		ctx->state = MFCINST_RES_CHANGE_INIT;
-		s5p_mfc_hw_call_void(dev->mfc_ops, clear_int_flags, dev);
+		s5p_mfc_hw_call(dev->mfc_ops, clear_int_flags, dev);
 		wake_up_ctx(ctx, reason, err);
 		WARN_ON(test_and_clear_bit(0, &dev->hw_lock) == 0);
 		s5p_mfc_clock_off();
-		s5p_mfc_hw_call_void(dev->mfc_ops, try_run, dev);
+		s5p_mfc_hw_call(dev->mfc_ops, try_run, dev);
 		return;
 	}
 	if (ctx->dpb_flush_flag)
 		ctx->dpb_flush_flag = 0;
 
-	spin_lock_irqsave(&dev->irqlock, flags);
 	/* All frames remaining in the buffer have been extracted  */
 	if (dst_frame_status == S5P_FIMV_DEC_STATUS_DECODING_EMPTY) {
 		if (ctx->state == MFCINST_RES_CHANGE_FLUSH) {
@@ -413,11 +443,10 @@
 		}
 	}
 leave_handle_frame:
-	spin_unlock_irqrestore(&dev->irqlock, flags);
 	if ((ctx->src_queue_cnt == 0 && ctx->state != MFCINST_FINISHING)
 				    || ctx->dst_queue_cnt < ctx->pb_count)
 		clear_work_bit(ctx);
-	s5p_mfc_hw_call_void(dev->mfc_ops, clear_int_flags, dev);
+	s5p_mfc_hw_call(dev->mfc_ops, clear_int_flags, dev);
 	wake_up_ctx(ctx, reason, err);
 	WARN_ON(test_and_clear_bit(0, &dev->hw_lock) == 0);
 	s5p_mfc_clock_off();
@@ -425,15 +454,13 @@
 	if (test_bit(0, &dev->enter_suspend))
 		wake_up_dev(dev, reason, err);
 	else
-		s5p_mfc_hw_call_void(dev->mfc_ops, try_run, dev);
+		s5p_mfc_hw_call(dev->mfc_ops, try_run, dev);
 }
 
 /* Error handling for interrupt */
 static void s5p_mfc_handle_error(struct s5p_mfc_dev *dev,
 		struct s5p_mfc_ctx *ctx, unsigned int reason, unsigned int err)
 {
-	unsigned long flags;
-
 	mfc_err("Interrupt Error: %08x\n", err);
 
 	if (ctx != NULL) {
@@ -450,13 +477,9 @@
 			clear_work_bit(ctx);
 			ctx->state = MFCINST_ERROR;
 			/* Mark all dst buffers as having an error */
-			spin_lock_irqsave(&dev->irqlock, flags);
-			s5p_mfc_hw_call_void(dev->mfc_ops, cleanup_queue,
-						&ctx->dst_queue, &ctx->vq_dst);
+			s5p_mfc_cleanup_queue(&ctx->dst_queue, &ctx->vq_dst);
 			/* Mark all src buffers as having an error */
-			s5p_mfc_hw_call_void(dev->mfc_ops, cleanup_queue,
-						&ctx->src_queue, &ctx->vq_src);
-			spin_unlock_irqrestore(&dev->irqlock, flags);
+			s5p_mfc_cleanup_queue(&ctx->src_queue, &ctx->vq_src);
 			wake_up_ctx(ctx, reason, err);
 			break;
 		default:
@@ -467,7 +490,7 @@
 		}
 	}
 	WARN_ON(test_and_clear_bit(0, &dev->hw_lock) == 0);
-	s5p_mfc_hw_call_void(dev->mfc_ops, clear_int_flags, dev);
+	s5p_mfc_hw_call(dev->mfc_ops, clear_int_flags, dev);
 	s5p_mfc_clock_off();
 	wake_up_dev(dev, reason, err);
 	return;
@@ -491,7 +514,7 @@
 		ctx->img_height = s5p_mfc_hw_call(dev->mfc_ops, get_img_height,
 				dev);
 
-		s5p_mfc_hw_call_void(dev->mfc_ops, dec_calc_dpb_size, ctx);
+		s5p_mfc_hw_call(dev->mfc_ops, dec_calc_dpb_size, ctx);
 
 		ctx->pb_count = s5p_mfc_hw_call(dev->mfc_ops, get_dpb_count,
 				dev);
@@ -518,11 +541,11 @@
 			ctx->head_processed = 1;
 		}
 	}
-	s5p_mfc_hw_call_void(dev->mfc_ops, clear_int_flags, dev);
+	s5p_mfc_hw_call(dev->mfc_ops, clear_int_flags, dev);
 	clear_work_bit(ctx);
 	WARN_ON(test_and_clear_bit(0, &dev->hw_lock) == 0);
 	s5p_mfc_clock_off();
-	s5p_mfc_hw_call_void(dev->mfc_ops, try_run, dev);
+	s5p_mfc_hw_call(dev->mfc_ops, try_run, dev);
 	wake_up_ctx(ctx, reason, err);
 }
 
@@ -532,12 +555,11 @@
 {
 	struct s5p_mfc_buf *src_buf;
 	struct s5p_mfc_dev *dev;
-	unsigned long flags;
 
 	if (ctx == NULL)
 		return;
 	dev = ctx->dev;
-	s5p_mfc_hw_call_void(dev->mfc_ops, clear_int_flags, dev);
+	s5p_mfc_hw_call(dev->mfc_ops, clear_int_flags, dev);
 	ctx->int_type = reason;
 	ctx->int_err = err;
 	ctx->int_cond = 1;
@@ -545,7 +567,6 @@
 	if (err == 0) {
 		ctx->state = MFCINST_RUNNING;
 		if (!ctx->dpb_flush_flag && ctx->head_processed) {
-			spin_lock_irqsave(&dev->irqlock, flags);
 			if (!list_empty(&ctx->src_queue)) {
 				src_buf = list_entry(ctx->src_queue.next,
 					     struct s5p_mfc_buf, list);
@@ -554,7 +575,6 @@
 				vb2_buffer_done(&src_buf->b->vb2_buf,
 						VB2_BUF_STATE_DONE);
 			}
-			spin_unlock_irqrestore(&dev->irqlock, flags);
 		} else {
 			ctx->dpb_flush_flag = 0;
 		}
@@ -563,7 +583,7 @@
 		s5p_mfc_clock_off();
 
 		wake_up(&ctx->queue);
-		s5p_mfc_hw_call_void(dev->mfc_ops, try_run, dev);
+		s5p_mfc_hw_call(dev->mfc_ops, try_run, dev);
 	} else {
 		WARN_ON(test_and_clear_bit(0, &dev->hw_lock) == 0);
 
@@ -582,7 +602,6 @@
 
 	ctx->state = MFCINST_FINISHED;
 
-	spin_lock(&dev->irqlock);
 	if (!list_empty(&ctx->dst_queue)) {
 		mb_entry = list_entry(ctx->dst_queue.next, struct s5p_mfc_buf,
 									list);
@@ -591,7 +610,6 @@
 		vb2_set_plane_payload(&mb_entry->b->vb2_buf, 0, 0);
 		vb2_buffer_done(&mb_entry->b->vb2_buf, VB2_BUF_STATE_DONE);
 	}
-	spin_unlock(&dev->irqlock);
 
 	clear_work_bit(ctx);
 
@@ -599,7 +617,7 @@
 
 	s5p_mfc_clock_off();
 	wake_up(&ctx->queue);
-	s5p_mfc_hw_call_void(dev->mfc_ops, try_run, dev);
+	s5p_mfc_hw_call(dev->mfc_ops, try_run, dev);
 }
 
 /* Interrupt processing */
@@ -613,6 +631,7 @@
 	mfc_debug_enter();
 	/* Reset the timeout watchdog */
 	atomic_set(&dev->watchdog_cnt, 0);
+	spin_lock(&dev->irqlock);
 	ctx = dev->ctx[dev->curr_ctx];
 	/* Get the reason of interrupt and the error code */
 	reason = s5p_mfc_hw_call(dev->mfc_ops, get_int_reason, dev);
@@ -639,15 +658,15 @@
 
 			if (ctx->state == MFCINST_FINISHING &&
 						list_empty(&ctx->ref_queue)) {
-				s5p_mfc_hw_call_void(dev->mfc_ops, clear_int_flags, dev);
+				s5p_mfc_hw_call(dev->mfc_ops, clear_int_flags, dev);
 				s5p_mfc_handle_stream_complete(ctx);
 				break;
 			}
-			s5p_mfc_hw_call_void(dev->mfc_ops, clear_int_flags, dev);
+			s5p_mfc_hw_call(dev->mfc_ops, clear_int_flags, dev);
 			wake_up_ctx(ctx, reason, err);
 			WARN_ON(test_and_clear_bit(0, &dev->hw_lock) == 0);
 			s5p_mfc_clock_off();
-			s5p_mfc_hw_call_void(dev->mfc_ops, try_run, dev);
+			s5p_mfc_hw_call(dev->mfc_ops, try_run, dev);
 		} else {
 			s5p_mfc_handle_frame(ctx, reason, err);
 		}
@@ -677,7 +696,7 @@
 	case S5P_MFC_R2H_CMD_WAKEUP_RET:
 		if (ctx)
 			clear_work_bit(ctx);
-		s5p_mfc_hw_call_void(dev->mfc_ops, clear_int_flags, dev);
+		s5p_mfc_hw_call(dev->mfc_ops, clear_int_flags, dev);
 		wake_up_dev(dev, reason, err);
 		clear_bit(0, &dev->hw_lock);
 		clear_bit(0, &dev->enter_suspend);
@@ -688,7 +707,7 @@
 		break;
 
 	case S5P_MFC_R2H_CMD_COMPLETE_SEQ_RET:
-		s5p_mfc_hw_call_void(dev->mfc_ops, clear_int_flags, dev);
+		s5p_mfc_hw_call(dev->mfc_ops, clear_int_flags, dev);
 		ctx->int_type = reason;
 		ctx->int_err = err;
 		s5p_mfc_handle_stream_complete(ctx);
@@ -702,12 +721,13 @@
 
 	default:
 		mfc_debug(2, "Unknown int reason\n");
-		s5p_mfc_hw_call_void(dev->mfc_ops, clear_int_flags, dev);
+		s5p_mfc_hw_call(dev->mfc_ops, clear_int_flags, dev);
 	}
+	spin_unlock(&dev->irqlock);
 	mfc_debug_leave();
 	return IRQ_HANDLED;
 irq_cleanup_hw:
-	s5p_mfc_hw_call_void(dev->mfc_ops, clear_int_flags, dev);
+	s5p_mfc_hw_call(dev->mfc_ops, clear_int_flags, dev);
 	ctx->int_type = reason;
 	ctx->int_err = err;
 	ctx->int_cond = 1;
@@ -716,7 +736,8 @@
 
 	s5p_mfc_clock_off();
 
-	s5p_mfc_hw_call_void(dev->mfc_ops, try_run, dev);
+	s5p_mfc_hw_call(dev->mfc_ops, try_run, dev);
+	spin_unlock(&dev->irqlock);
 	mfc_debug(2, "Exit via irq_cleanup_hw\n");
 	return IRQ_HANDLED;
 }
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_common.h b/drivers/media/platform/s5p-mfc/s5p_mfc_common.h
index d1a3f9b..9eb2481e 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc_common.h
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc_common.h
@@ -308,7 +308,7 @@
 	struct s5p_mfc_pm	pm;
 	struct s5p_mfc_variant	*variant;
 	int num_inst;
-	spinlock_t irqlock;	/* lock when operating on videobuf2 queues */
+	spinlock_t irqlock;	/* lock when operating on context */
 	spinlock_t condlock;	/* lock when changing/checking if a context is
 					ready to be processed */
 	struct mutex mfc_mutex; /* video_device lock */
@@ -653,7 +653,7 @@
 		unsigned int bits;
 	} slice_size;
 
-	struct s5p_mfc_codec_ops *c_ops;
+	const struct s5p_mfc_codec_ops *c_ops;
 
 	struct v4l2_ctrl *ctrls[MFC_MAX_CTRLS];
 	struct v4l2_ctrl_handler ctrl_handler;
@@ -694,13 +694,7 @@
 
 /* Macro for making hardware specific calls */
 #define s5p_mfc_hw_call(f, op, args...) \
-	((f && f->op) ? f->op(args) : -ENODEV)
-
-#define s5p_mfc_hw_call_void(f, op, args...) \
-do { \
-	if (f && f->op) \
-		f->op(args); \
-} while (0)
+	((f && f->op) ? f->op(args) : (typeof(f->op(args)))(-ENODEV))
 
 #define fh_to_ctx(__fh) container_of(__fh, struct s5p_mfc_ctx, fh)
 #define ctrl_to_ctx(__ctrl) \
@@ -710,6 +704,8 @@
 void set_work_bit(struct s5p_mfc_ctx *ctx);
 void clear_work_bit_irqsave(struct s5p_mfc_ctx *ctx);
 void set_work_bit_irqsave(struct s5p_mfc_ctx *ctx);
+int s5p_mfc_get_new_ctx(struct s5p_mfc_dev *dev);
+void s5p_mfc_cleanup_queue(struct list_head *lh, struct vb2_queue *vq);
 
 #define HAS_PORTNUM(dev)	(dev ? (dev->variant ? \
 				(dev->variant->port_num ? 1 : 0) : 0) : 0)
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_ctrl.c b/drivers/media/platform/s5p-mfc/s5p_mfc_ctrl.c
index 40d8a03..cc88871 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc_ctrl.c
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc_ctrl.c
@@ -319,7 +319,7 @@
 	s5p_mfc_clock_on();
 
 	s5p_mfc_reset(dev);
-	s5p_mfc_hw_call_void(dev->mfc_ops, release_dev_context_buffer, dev);
+	s5p_mfc_hw_call(dev->mfc_ops, release_dev_context_buffer, dev);
 
 	s5p_mfc_clock_off();
 }
@@ -468,7 +468,7 @@
 	}
 
 	set_work_bit_irqsave(ctx);
-	s5p_mfc_hw_call_void(dev->mfc_ops, try_run, dev);
+	s5p_mfc_hw_call(dev->mfc_ops, try_run, dev);
 	if (s5p_mfc_wait_for_done_ctx(ctx,
 		S5P_MFC_R2H_CMD_OPEN_INSTANCE_RET, 0)) {
 		/* Error or timeout */
@@ -482,9 +482,9 @@
 
 err_free_desc_buf:
 	if (ctx->type == MFCINST_DECODER)
-		s5p_mfc_hw_call_void(dev->mfc_ops, release_dec_desc_buffer, ctx);
+		s5p_mfc_hw_call(dev->mfc_ops, release_dec_desc_buffer, ctx);
 err_free_inst_buf:
-	s5p_mfc_hw_call_void(dev->mfc_ops, release_instance_buffer, ctx);
+	s5p_mfc_hw_call(dev->mfc_ops, release_instance_buffer, ctx);
 err:
 	return ret;
 }
@@ -493,17 +493,17 @@
 {
 	ctx->state = MFCINST_RETURN_INST;
 	set_work_bit_irqsave(ctx);
-	s5p_mfc_hw_call_void(dev->mfc_ops, try_run, dev);
+	s5p_mfc_hw_call(dev->mfc_ops, try_run, dev);
 	/* Wait until instance is returned or timeout occurred */
 	if (s5p_mfc_wait_for_done_ctx(ctx,
 				S5P_MFC_R2H_CMD_CLOSE_INSTANCE_RET, 0))
 		mfc_err("Err returning instance\n");
 
 	/* Free resources */
-	s5p_mfc_hw_call_void(dev->mfc_ops, release_codec_buffers, ctx);
-	s5p_mfc_hw_call_void(dev->mfc_ops, release_instance_buffer, ctx);
+	s5p_mfc_hw_call(dev->mfc_ops, release_codec_buffers, ctx);
+	s5p_mfc_hw_call(dev->mfc_ops, release_instance_buffer, ctx);
 	if (ctx->type == MFCINST_DECODER)
-		s5p_mfc_hw_call_void(dev->mfc_ops, release_dec_desc_buffer, ctx);
+		s5p_mfc_hw_call(dev->mfc_ops, release_dec_desc_buffer, ctx);
 
 	ctx->inst_no = MFC_NO_INSTANCE_SET;
 	ctx->state = MFCINST_FREE;
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_dec.c b/drivers/media/platform/s5p-mfc/s5p_mfc_dec.c
index 8c5060a..f2d6376 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc_dec.c
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc_dec.c
@@ -252,7 +252,7 @@
 	return 0;
 }
 
-static struct s5p_mfc_codec_ops decoder_codec_ops = {
+static const struct s5p_mfc_codec_ops decoder_codec_ops = {
 	.pre_seq_start		= NULL,
 	.post_seq_start		= NULL,
 	.pre_frame_start	= NULL,
@@ -523,7 +523,7 @@
 		ret = vb2_reqbufs(&ctx->vq_dst, reqbufs);
 		if (ret)
 			goto out;
-		s5p_mfc_hw_call_void(dev->mfc_ops, release_codec_buffers, ctx);
+		s5p_mfc_hw_call(dev->mfc_ops, release_codec_buffers, ctx);
 		ctx->dst_bufs_cnt = 0;
 	} else if (ctx->capture_state == QUEUE_FREE) {
 		WARN_ON(ctx->dst_bufs_cnt != 0);
@@ -551,7 +551,7 @@
 
 		if (s5p_mfc_ctx_ready(ctx))
 			set_work_bit_irqsave(ctx);
-		s5p_mfc_hw_call_void(dev->mfc_ops, try_run, dev);
+		s5p_mfc_hw_call(dev->mfc_ops, try_run, dev);
 		s5p_mfc_wait_for_done_ctx(ctx, S5P_MFC_R2H_CMD_INIT_BUFFERS_RET,
 					  0);
 	} else {
@@ -831,7 +831,7 @@
 			if (s5p_mfc_ctx_ready(ctx))
 				set_work_bit_irqsave(ctx);
 			spin_unlock_irqrestore(&dev->irqlock, flags);
-			s5p_mfc_hw_call_void(dev->mfc_ops, try_run, dev);
+			s5p_mfc_hw_call(dev->mfc_ops, try_run, dev);
 		} else {
 			mfc_err("EOS: marking last buffer of stream");
 			buf = list_entry(ctx->src_queue.prev,
@@ -888,7 +888,7 @@
 };
 
 static int s5p_mfc_queue_setup(struct vb2_queue *vq,
-			const void *parg, unsigned int *buf_count,
+			unsigned int *buf_count,
 			unsigned int *plane_count, unsigned int psize[],
 			void *allocators[])
 {
@@ -1012,7 +1012,7 @@
 	/* If context is ready then dev = work->data;schedule it to run */
 	if (s5p_mfc_ctx_ready(ctx))
 		set_work_bit_irqsave(ctx);
-	s5p_mfc_hw_call_void(dev->mfc_ops, try_run, dev);
+	s5p_mfc_hw_call(dev->mfc_ops, try_run, dev);
 	return 0;
 }
 
@@ -1023,42 +1023,41 @@
 	struct s5p_mfc_dev *dev = ctx->dev;
 	int aborted = 0;
 
+	spin_lock_irqsave(&dev->irqlock, flags);
 	if ((ctx->state == MFCINST_FINISHING ||
 		ctx->state ==  MFCINST_RUNNING) &&
 		dev->curr_ctx == ctx->num && dev->hw_lock) {
 		ctx->state = MFCINST_ABORT;
+		spin_unlock_irqrestore(&dev->irqlock, flags);
 		s5p_mfc_wait_for_done_ctx(ctx,
 					S5P_MFC_R2H_CMD_FRAME_DONE_RET, 0);
 		aborted = 1;
+		spin_lock_irqsave(&dev->irqlock, flags);
 	}
 	if (q->type == V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE) {
-		spin_lock_irqsave(&dev->irqlock, flags);
-		s5p_mfc_hw_call_void(dev->mfc_ops, cleanup_queue,
-						&ctx->dst_queue, &ctx->vq_dst);
+		s5p_mfc_cleanup_queue(&ctx->dst_queue, &ctx->vq_dst);
 		INIT_LIST_HEAD(&ctx->dst_queue);
 		ctx->dst_queue_cnt = 0;
 		ctx->dpb_flush_flag = 1;
 		ctx->dec_dst_flag = 0;
-		spin_unlock_irqrestore(&dev->irqlock, flags);
 		if (IS_MFCV6_PLUS(dev) && (ctx->state == MFCINST_RUNNING)) {
 			ctx->state = MFCINST_FLUSH;
 			set_work_bit_irqsave(ctx);
-			s5p_mfc_hw_call_void(dev->mfc_ops, try_run, dev);
+			s5p_mfc_hw_call(dev->mfc_ops, try_run, dev);
+			spin_unlock_irqrestore(&dev->irqlock, flags);
 			if (s5p_mfc_wait_for_done_ctx(ctx,
 				S5P_MFC_R2H_CMD_DPB_FLUSH_RET, 0))
 				mfc_err("Err flushing buffers\n");
+			spin_lock_irqsave(&dev->irqlock, flags);
 		}
-	}
-	if (q->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE) {
-		spin_lock_irqsave(&dev->irqlock, flags);
-		s5p_mfc_hw_call_void(dev->mfc_ops, cleanup_queue,
-						&ctx->src_queue, &ctx->vq_src);
+	} else if (q->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE) {
+		s5p_mfc_cleanup_queue(&ctx->src_queue, &ctx->vq_src);
 		INIT_LIST_HEAD(&ctx->src_queue);
 		ctx->src_queue_cnt = 0;
-		spin_unlock_irqrestore(&dev->irqlock, flags);
 	}
 	if (aborted)
 		ctx->state = MFCINST_RUNNING;
+	spin_unlock_irqrestore(&dev->irqlock, flags);
 }
 
 
@@ -1091,7 +1090,7 @@
 	}
 	if (s5p_mfc_ctx_ready(ctx))
 		set_work_bit_irqsave(ctx);
-	s5p_mfc_hw_call_void(dev->mfc_ops, try_run, dev);
+	s5p_mfc_hw_call(dev->mfc_ops, try_run, dev);
 }
 
 static struct vb2_ops s5p_mfc_dec_qops = {
@@ -1104,7 +1103,7 @@
 	.buf_queue		= s5p_mfc_buf_queue,
 };
 
-struct s5p_mfc_codec_ops *get_dec_codec_ops(void)
+const struct s5p_mfc_codec_ops *get_dec_codec_ops(void)
 {
 	return &decoder_codec_ops;
 }
@@ -1119,7 +1118,7 @@
 	return &s5p_mfc_dec_ioctl_ops;
 }
 
-#define IS_MFC51_PRIV(x) ((V4L2_CTRL_ID2CLASS(x) == V4L2_CTRL_CLASS_MPEG) \
+#define IS_MFC51_PRIV(x) ((V4L2_CTRL_ID2WHICH(x) == V4L2_CTRL_CLASS_MPEG) \
 						&& V4L2_CTRL_DRIVER_PRIV(x))
 
 int s5p_mfc_dec_ctrls_setup(struct s5p_mfc_ctx *ctx)
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_dec.h b/drivers/media/platform/s5p-mfc/s5p_mfc_dec.h
index d06a7ca..886628b 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc_dec.h
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc_dec.h
@@ -13,7 +13,7 @@
 #ifndef S5P_MFC_DEC_H_
 #define S5P_MFC_DEC_H_
 
-struct s5p_mfc_codec_ops *get_dec_codec_ops(void);
+const struct s5p_mfc_codec_ops *get_dec_codec_ops(void);
 struct vb2_ops *get_dec_queue_ops(void);
 const struct v4l2_ioctl_ops *get_dec_v4l2_ioctl_ops(void);
 struct s5p_mfc_fmt *get_dec_def_fmt(bool src);
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_enc.c b/drivers/media/platform/s5p-mfc/s5p_mfc_enc.c
index 5c678ec..0434f02 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc_enc.c
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc_enc.c
@@ -769,15 +769,12 @@
 	struct s5p_mfc_buf *dst_mb;
 	unsigned long dst_addr;
 	unsigned int dst_size;
-	unsigned long flags;
 
-	spin_lock_irqsave(&dev->irqlock, flags);
 	dst_mb = list_entry(ctx->dst_queue.next, struct s5p_mfc_buf, list);
 	dst_addr = vb2_dma_contig_plane_dma_addr(&dst_mb->b->vb2_buf, 0);
 	dst_size = vb2_plane_size(&dst_mb->b->vb2_buf, 0);
-	s5p_mfc_hw_call_void(dev->mfc_ops, set_enc_stream_buffer, ctx, dst_addr,
+	s5p_mfc_hw_call(dev->mfc_ops, set_enc_stream_buffer, ctx, dst_addr,
 			dst_size);
-	spin_unlock_irqrestore(&dev->irqlock, flags);
 	return 0;
 }
 
@@ -786,11 +783,9 @@
 	struct s5p_mfc_dev *dev = ctx->dev;
 	struct s5p_mfc_enc_params *p = &ctx->enc_params;
 	struct s5p_mfc_buf *dst_mb;
-	unsigned long flags;
 	unsigned int enc_pb_count;
 
 	if (p->seq_hdr_mode == V4L2_MPEG_VIDEO_HEADER_MODE_SEPARATE) {
-		spin_lock_irqsave(&dev->irqlock, flags);
 		if (!list_empty(&ctx->dst_queue)) {
 			dst_mb = list_entry(ctx->dst_queue.next,
 					struct s5p_mfc_buf, list);
@@ -802,14 +797,13 @@
 			vb2_buffer_done(&dst_mb->b->vb2_buf,
 					VB2_BUF_STATE_DONE);
 		}
-		spin_unlock_irqrestore(&dev->irqlock, flags);
 	}
 
 	if (!IS_MFCV6_PLUS(dev)) {
 		ctx->state = MFCINST_RUNNING;
 		if (s5p_mfc_ctx_ready(ctx))
 			set_work_bit_irqsave(ctx);
-		s5p_mfc_hw_call_void(dev->mfc_ops, try_run, dev);
+		s5p_mfc_hw_call(dev->mfc_ops, try_run, dev);
 	} else {
 		enc_pb_count = s5p_mfc_hw_call(dev->mfc_ops,
 				get_enc_dpb_count, dev);
@@ -826,25 +820,20 @@
 	struct s5p_mfc_dev *dev = ctx->dev;
 	struct s5p_mfc_buf *dst_mb;
 	struct s5p_mfc_buf *src_mb;
-	unsigned long flags;
 	unsigned long src_y_addr, src_c_addr, dst_addr;
 	unsigned int dst_size;
 
-	spin_lock_irqsave(&dev->irqlock, flags);
 	src_mb = list_entry(ctx->src_queue.next, struct s5p_mfc_buf, list);
 	src_y_addr = vb2_dma_contig_plane_dma_addr(&src_mb->b->vb2_buf, 0);
 	src_c_addr = vb2_dma_contig_plane_dma_addr(&src_mb->b->vb2_buf, 1);
-	s5p_mfc_hw_call_void(dev->mfc_ops, set_enc_frame_buffer, ctx,
+	s5p_mfc_hw_call(dev->mfc_ops, set_enc_frame_buffer, ctx,
 							src_y_addr, src_c_addr);
-	spin_unlock_irqrestore(&dev->irqlock, flags);
 
-	spin_lock_irqsave(&dev->irqlock, flags);
 	dst_mb = list_entry(ctx->dst_queue.next, struct s5p_mfc_buf, list);
 	dst_addr = vb2_dma_contig_plane_dma_addr(&dst_mb->b->vb2_buf, 0);
 	dst_size = vb2_plane_size(&dst_mb->b->vb2_buf, 0);
-	s5p_mfc_hw_call_void(dev->mfc_ops, set_enc_stream_buffer, ctx, dst_addr,
+	s5p_mfc_hw_call(dev->mfc_ops, set_enc_stream_buffer, ctx, dst_addr,
 			dst_size);
-	spin_unlock_irqrestore(&dev->irqlock, flags);
 
 	return 0;
 }
@@ -857,7 +846,6 @@
 	unsigned long mb_y_addr, mb_c_addr;
 	int slice_type;
 	unsigned int strm_size;
-	unsigned long flags;
 
 	slice_type = s5p_mfc_hw_call(dev->mfc_ops, get_enc_slice_type, dev);
 	strm_size = s5p_mfc_hw_call(dev->mfc_ops, get_enc_strm_size, dev);
@@ -865,9 +853,8 @@
 	mfc_debug(2, "Encoded stream size: %d\n", strm_size);
 	mfc_debug(2, "Display order: %d\n",
 		  mfc_read(dev, S5P_FIMV_ENC_SI_PIC_CNT));
-	spin_lock_irqsave(&dev->irqlock, flags);
 	if (slice_type >= 0) {
-		s5p_mfc_hw_call_void(dev->mfc_ops, get_enc_frame_buffer, ctx,
+		s5p_mfc_hw_call(dev->mfc_ops, get_enc_frame_buffer, ctx,
 				&enc_y_addr, &enc_c_addr);
 		list_for_each_entry(mb_entry, &ctx->src_queue, list) {
 			mb_y_addr = vb2_dma_contig_plane_dma_addr(
@@ -929,14 +916,13 @@
 		vb2_set_plane_payload(&mb_entry->b->vb2_buf, 0, strm_size);
 		vb2_buffer_done(&mb_entry->b->vb2_buf, VB2_BUF_STATE_DONE);
 	}
-	spin_unlock_irqrestore(&dev->irqlock, flags);
 	if ((ctx->src_queue_cnt == 0) || (ctx->dst_queue_cnt == 0))
 		clear_work_bit(ctx);
 
 	return 0;
 }
 
-static struct s5p_mfc_codec_ops encoder_codec_ops = {
+static const struct s5p_mfc_codec_ops encoder_codec_ops = {
 	.pre_seq_start		= enc_pre_seq_start,
 	.post_seq_start		= enc_post_seq_start,
 	.pre_frame_start	= enc_pre_frame_start,
@@ -1120,7 +1106,7 @@
 			pix_fmt_mp->width, pix_fmt_mp->height,
 			ctx->img_width, ctx->img_height);
 
-		s5p_mfc_hw_call_void(dev->mfc_ops, enc_calc_src_size, ctx);
+		s5p_mfc_hw_call(dev->mfc_ops, enc_calc_src_size, ctx);
 		pix_fmt_mp->plane_fmt[0].sizeimage = ctx->luma_size;
 		pix_fmt_mp->plane_fmt[0].bytesperline = ctx->buf_width;
 		pix_fmt_mp->plane_fmt[1].sizeimage = ctx->chroma_size;
@@ -1178,7 +1164,7 @@
 		if (reqbufs->count == 0) {
 			mfc_debug(2, "Freeing buffers\n");
 			ret = vb2_reqbufs(&ctx->vq_src, reqbufs);
-			s5p_mfc_hw_call_void(dev->mfc_ops, release_codec_buffers,
+			s5p_mfc_hw_call(dev->mfc_ops, release_codec_buffers,
 					ctx);
 			ctx->output_state = QUEUE_FREE;
 			return ret;
@@ -1741,7 +1727,7 @@
 			if (s5p_mfc_ctx_ready(ctx))
 				set_work_bit_irqsave(ctx);
 			spin_unlock_irqrestore(&dev->irqlock, flags);
-			s5p_mfc_hw_call_void(dev->mfc_ops, try_run, dev);
+			s5p_mfc_hw_call(dev->mfc_ops, try_run, dev);
 		} else {
 			mfc_debug(2, "EOS: marking last buffer of stream\n");
 			buf = list_entry(ctx->src_queue.prev,
@@ -1818,7 +1804,6 @@
 }
 
 static int s5p_mfc_queue_setup(struct vb2_queue *vq,
-			const void *parg,
 			unsigned int *buf_count, unsigned int *plane_count,
 			unsigned int psize[], void *allocators[])
 {
@@ -1969,7 +1954,7 @@
 	/* If context is ready then dev = work->data;schedule it to run */
 	if (s5p_mfc_ctx_ready(ctx))
 		set_work_bit_irqsave(ctx);
-	s5p_mfc_hw_call_void(dev->mfc_ops, try_run, dev);
+	s5p_mfc_hw_call(dev->mfc_ops, try_run, dev);
 
 	return 0;
 }
@@ -1990,15 +1975,13 @@
 	ctx->state = MFCINST_FINISHED;
 	spin_lock_irqsave(&dev->irqlock, flags);
 	if (q->type == V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE) {
-		s5p_mfc_hw_call_void(dev->mfc_ops, cleanup_queue,
-						&ctx->dst_queue, &ctx->vq_dst);
+		s5p_mfc_cleanup_queue(&ctx->dst_queue, &ctx->vq_dst);
 		INIT_LIST_HEAD(&ctx->dst_queue);
 		ctx->dst_queue_cnt = 0;
 	}
 	if (q->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE) {
 		cleanup_ref_queue(ctx);
-		s5p_mfc_hw_call_void(dev->mfc_ops, cleanup_queue, &ctx->src_queue,
-				&ctx->vq_src);
+		s5p_mfc_cleanup_queue(&ctx->src_queue, &ctx->vq_src);
 		INIT_LIST_HEAD(&ctx->src_queue);
 		ctx->src_queue_cnt = 0;
 	}
@@ -2038,7 +2021,7 @@
 	}
 	if (s5p_mfc_ctx_ready(ctx))
 		set_work_bit_irqsave(ctx);
-	s5p_mfc_hw_call_void(dev->mfc_ops, try_run, dev);
+	s5p_mfc_hw_call(dev->mfc_ops, try_run, dev);
 }
 
 static struct vb2_ops s5p_mfc_enc_qops = {
@@ -2052,7 +2035,7 @@
 	.buf_queue		= s5p_mfc_buf_queue,
 };
 
-struct s5p_mfc_codec_ops *get_enc_codec_ops(void)
+const struct s5p_mfc_codec_ops *get_enc_codec_ops(void)
 {
 	return &encoder_codec_ops;
 }
@@ -2067,7 +2050,7 @@
 	return &s5p_mfc_enc_ioctl_ops;
 }
 
-#define IS_MFC51_PRIV(x) ((V4L2_CTRL_ID2CLASS(x) == V4L2_CTRL_CLASS_MPEG) \
+#define IS_MFC51_PRIV(x) ((V4L2_CTRL_ID2WHICH(x) == V4L2_CTRL_CLASS_MPEG) \
 						&& V4L2_CTRL_DRIVER_PRIV(x))
 
 int s5p_mfc_enc_ctrls_setup(struct s5p_mfc_ctx *ctx)
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_enc.h b/drivers/media/platform/s5p-mfc/s5p_mfc_enc.h
index 5118d46b..d0d42f8 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc_enc.h
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc_enc.h
@@ -13,7 +13,7 @@
 #ifndef S5P_MFC_ENC_H_
 #define S5P_MFC_ENC_H_
 
-struct s5p_mfc_codec_ops *get_enc_codec_ops(void);
+const struct s5p_mfc_codec_ops *get_enc_codec_ops(void);
 struct vb2_ops *get_enc_queue_ops(void);
 const struct v4l2_ioctl_ops *get_enc_v4l2_ioctl_ops(void);
 struct s5p_mfc_fmt *get_enc_def_fmt(bool src);
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_opr.h b/drivers/media/platform/s5p-mfc/s5p_mfc_opr.h
index 77a08b1..b6ac417 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc_opr.h
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc_opr.h
@@ -20,254 +20,254 @@
 struct s5p_mfc_regs {
 
 	/* codec common registers */
-	volatile void __iomem *risc_on;
-	volatile void __iomem *risc2host_int;
-	volatile void __iomem *host2risc_int;
-	volatile void __iomem *risc_base_address;
-	volatile void __iomem *mfc_reset;
-	volatile void __iomem *host2risc_command;
-	volatile void __iomem *risc2host_command;
-	volatile void __iomem *mfc_bus_reset_ctrl;
-	volatile void __iomem *firmware_version;
-	volatile void __iomem *instance_id;
-	volatile void __iomem *codec_type;
-	volatile void __iomem *context_mem_addr;
-	volatile void __iomem *context_mem_size;
-	volatile void __iomem *pixel_format;
-	volatile void __iomem *metadata_enable;
-	volatile void __iomem *mfc_version;
-	volatile void __iomem *dbg_info_enable;
-	volatile void __iomem *dbg_buffer_addr;
-	volatile void __iomem *dbg_buffer_size;
-	volatile void __iomem *hed_control;
-	volatile void __iomem *mfc_timeout_value;
-	volatile void __iomem *hed_shared_mem_addr;
-	volatile void __iomem *dis_shared_mem_addr;/* only v7 */
-	volatile void __iomem *ret_instance_id;
-	volatile void __iomem *error_code;
-	volatile void __iomem *dbg_buffer_output_size;
-	volatile void __iomem *metadata_status;
-	volatile void __iomem *metadata_addr_mb_info;
-	volatile void __iomem *metadata_size_mb_info;
-	volatile void __iomem *dbg_info_stage_counter;
+	void __iomem *risc_on;
+	void __iomem *risc2host_int;
+	void __iomem *host2risc_int;
+	void __iomem *risc_base_address;
+	void __iomem *mfc_reset;
+	void __iomem *host2risc_command;
+	void __iomem *risc2host_command;
+	void __iomem *mfc_bus_reset_ctrl;
+	void __iomem *firmware_version;
+	void __iomem *instance_id;
+	void __iomem *codec_type;
+	void __iomem *context_mem_addr;
+	void __iomem *context_mem_size;
+	void __iomem *pixel_format;
+	void __iomem *metadata_enable;
+	void __iomem *mfc_version;
+	void __iomem *dbg_info_enable;
+	void __iomem *dbg_buffer_addr;
+	void __iomem *dbg_buffer_size;
+	void __iomem *hed_control;
+	void __iomem *mfc_timeout_value;
+	void __iomem *hed_shared_mem_addr;
+	void __iomem *dis_shared_mem_addr;/* only v7 */
+	void __iomem *ret_instance_id;
+	void __iomem *error_code;
+	void __iomem *dbg_buffer_output_size;
+	void __iomem *metadata_status;
+	void __iomem *metadata_addr_mb_info;
+	void __iomem *metadata_size_mb_info;
+	void __iomem *dbg_info_stage_counter;
 
 	/* decoder registers */
-	volatile void __iomem *d_crc_ctrl;
-	volatile void __iomem *d_dec_options;
-	volatile void __iomem *d_display_delay;
-	volatile void __iomem *d_set_frame_width;
-	volatile void __iomem *d_set_frame_height;
-	volatile void __iomem *d_sei_enable;
-	volatile void __iomem *d_min_num_dpb;
-	volatile void __iomem *d_min_first_plane_dpb_size;
-	volatile void __iomem *d_min_second_plane_dpb_size;
-	volatile void __iomem *d_min_third_plane_dpb_size;/* only v8 */
-	volatile void __iomem *d_min_num_mv;
-	volatile void __iomem *d_mvc_num_views;
-	volatile void __iomem *d_min_num_dis;/* only v7 */
-	volatile void __iomem *d_min_first_dis_size;/* only v7 */
-	volatile void __iomem *d_min_second_dis_size;/* only v7 */
-	volatile void __iomem *d_min_third_dis_size;/* only v7 */
-	volatile void __iomem *d_post_filter_luma_dpb0;/*  v7 and v8 */
-	volatile void __iomem *d_post_filter_luma_dpb1;/* v7 and v8 */
-	volatile void __iomem *d_post_filter_luma_dpb2;/* only v7 */
-	volatile void __iomem *d_post_filter_chroma_dpb0;/* v7 and v8 */
-	volatile void __iomem *d_post_filter_chroma_dpb1;/* v7 and v8 */
-	volatile void __iomem *d_post_filter_chroma_dpb2;/* only v7 */
-	volatile void __iomem *d_num_dpb;
-	volatile void __iomem *d_num_mv;
-	volatile void __iomem *d_init_buffer_options;
-	volatile void __iomem *d_first_plane_dpb_stride_size;/* only v8 */
-	volatile void __iomem *d_second_plane_dpb_stride_size;/* only v8 */
-	volatile void __iomem *d_third_plane_dpb_stride_size;/* only v8 */
-	volatile void __iomem *d_first_plane_dpb_size;
-	volatile void __iomem *d_second_plane_dpb_size;
-	volatile void __iomem *d_third_plane_dpb_size;/* only v8 */
-	volatile void __iomem *d_mv_buffer_size;
-	volatile void __iomem *d_first_plane_dpb;
-	volatile void __iomem *d_second_plane_dpb;
-	volatile void __iomem *d_third_plane_dpb;
-	volatile void __iomem *d_mv_buffer;
-	volatile void __iomem *d_scratch_buffer_addr;
-	volatile void __iomem *d_scratch_buffer_size;
-	volatile void __iomem *d_metadata_buffer_addr;
-	volatile void __iomem *d_metadata_buffer_size;
-	volatile void __iomem *d_nal_start_options;/* v7 and v8 */
-	volatile void __iomem *d_cpb_buffer_addr;
-	volatile void __iomem *d_cpb_buffer_size;
-	volatile void __iomem *d_available_dpb_flag_upper;
-	volatile void __iomem *d_available_dpb_flag_lower;
-	volatile void __iomem *d_cpb_buffer_offset;
-	volatile void __iomem *d_slice_if_enable;
-	volatile void __iomem *d_picture_tag;
-	volatile void __iomem *d_stream_data_size;
-	volatile void __iomem *d_dynamic_dpb_flag_upper;/* v7 and v8 */
-	volatile void __iomem *d_dynamic_dpb_flag_lower;/* v7 and v8 */
-	volatile void __iomem *d_display_frame_width;
-	volatile void __iomem *d_display_frame_height;
-	volatile void __iomem *d_display_status;
-	volatile void __iomem *d_display_first_plane_addr;
-	volatile void __iomem *d_display_second_plane_addr;
-	volatile void __iomem *d_display_third_plane_addr;/* only v8 */
-	volatile void __iomem *d_display_frame_type;
-	volatile void __iomem *d_display_crop_info1;
-	volatile void __iomem *d_display_crop_info2;
-	volatile void __iomem *d_display_picture_profile;
-	volatile void __iomem *d_display_luma_crc;/* v7 and v8 */
-	volatile void __iomem *d_display_chroma0_crc;/* v7 and v8 */
-	volatile void __iomem *d_display_chroma1_crc;/* only v8 */
-	volatile void __iomem *d_display_luma_crc_top;/* only v6 */
-	volatile void __iomem *d_display_chroma_crc_top;/* only v6 */
-	volatile void __iomem *d_display_luma_crc_bot;/* only v6 */
-	volatile void __iomem *d_display_chroma_crc_bot;/* only v6 */
-	volatile void __iomem *d_display_aspect_ratio;
-	volatile void __iomem *d_display_extended_ar;
-	volatile void __iomem *d_decoded_frame_width;
-	volatile void __iomem *d_decoded_frame_height;
-	volatile void __iomem *d_decoded_status;
-	volatile void __iomem *d_decoded_first_plane_addr;
-	volatile void __iomem *d_decoded_second_plane_addr;
-	volatile void __iomem *d_decoded_third_plane_addr;/* only v8 */
-	volatile void __iomem *d_decoded_frame_type;
-	volatile void __iomem *d_decoded_crop_info1;
-	volatile void __iomem *d_decoded_crop_info2;
-	volatile void __iomem *d_decoded_picture_profile;
-	volatile void __iomem *d_decoded_nal_size;
-	volatile void __iomem *d_decoded_luma_crc;
-	volatile void __iomem *d_decoded_chroma0_crc;
-	volatile void __iomem *d_decoded_chroma1_crc;/* only v8 */
-	volatile void __iomem *d_ret_picture_tag_top;
-	volatile void __iomem *d_ret_picture_tag_bot;
-	volatile void __iomem *d_ret_picture_time_top;
-	volatile void __iomem *d_ret_picture_time_bot;
-	volatile void __iomem *d_chroma_format;
-	volatile void __iomem *d_vc1_info;/* v7 and v8 */
-	volatile void __iomem *d_mpeg4_info;
-	volatile void __iomem *d_h264_info;
-	volatile void __iomem *d_metadata_addr_concealed_mb;
-	volatile void __iomem *d_metadata_size_concealed_mb;
-	volatile void __iomem *d_metadata_addr_vc1_param;
-	volatile void __iomem *d_metadata_size_vc1_param;
-	volatile void __iomem *d_metadata_addr_sei_nal;
-	volatile void __iomem *d_metadata_size_sei_nal;
-	volatile void __iomem *d_metadata_addr_vui;
-	volatile void __iomem *d_metadata_size_vui;
-	volatile void __iomem *d_metadata_addr_mvcvui;/* v7 and v8 */
-	volatile void __iomem *d_metadata_size_mvcvui;/* v7 and v8 */
-	volatile void __iomem *d_mvc_view_id;
-	volatile void __iomem *d_frame_pack_sei_avail;
-	volatile void __iomem *d_frame_pack_arrgment_id;
-	volatile void __iomem *d_frame_pack_sei_info;
-	volatile void __iomem *d_frame_pack_grid_pos;
-	volatile void __iomem *d_display_recovery_sei_info;/* v7 and v8 */
-	volatile void __iomem *d_decoded_recovery_sei_info;/* v7 and v8 */
-	volatile void __iomem *d_display_first_addr;/* only v7 */
-	volatile void __iomem *d_display_second_addr;/* only v7 */
-	volatile void __iomem *d_display_third_addr;/* only v7 */
-	volatile void __iomem *d_decoded_first_addr;/* only v7 */
-	volatile void __iomem *d_decoded_second_addr;/* only v7 */
-	volatile void __iomem *d_decoded_third_addr;/* only v7 */
-	volatile void __iomem *d_used_dpb_flag_upper;/* v7 and v8 */
-	volatile void __iomem *d_used_dpb_flag_lower;/* v7 and v8 */
+	void __iomem *d_crc_ctrl;
+	void __iomem *d_dec_options;
+	void __iomem *d_display_delay;
+	void __iomem *d_set_frame_width;
+	void __iomem *d_set_frame_height;
+	void __iomem *d_sei_enable;
+	void __iomem *d_min_num_dpb;
+	void __iomem *d_min_first_plane_dpb_size;
+	void __iomem *d_min_second_plane_dpb_size;
+	void __iomem *d_min_third_plane_dpb_size;/* only v8 */
+	void __iomem *d_min_num_mv;
+	void __iomem *d_mvc_num_views;
+	void __iomem *d_min_num_dis;/* only v7 */
+	void __iomem *d_min_first_dis_size;/* only v7 */
+	void __iomem *d_min_second_dis_size;/* only v7 */
+	void __iomem *d_min_third_dis_size;/* only v7 */
+	void __iomem *d_post_filter_luma_dpb0;/*  v7 and v8 */
+	void __iomem *d_post_filter_luma_dpb1;/* v7 and v8 */
+	void __iomem *d_post_filter_luma_dpb2;/* only v7 */
+	void __iomem *d_post_filter_chroma_dpb0;/* v7 and v8 */
+	void __iomem *d_post_filter_chroma_dpb1;/* v7 and v8 */
+	void __iomem *d_post_filter_chroma_dpb2;/* only v7 */
+	void __iomem *d_num_dpb;
+	void __iomem *d_num_mv;
+	void __iomem *d_init_buffer_options;
+	void __iomem *d_first_plane_dpb_stride_size;/* only v8 */
+	void __iomem *d_second_plane_dpb_stride_size;/* only v8 */
+	void __iomem *d_third_plane_dpb_stride_size;/* only v8 */
+	void __iomem *d_first_plane_dpb_size;
+	void __iomem *d_second_plane_dpb_size;
+	void __iomem *d_third_plane_dpb_size;/* only v8 */
+	void __iomem *d_mv_buffer_size;
+	void __iomem *d_first_plane_dpb;
+	void __iomem *d_second_plane_dpb;
+	void __iomem *d_third_plane_dpb;
+	void __iomem *d_mv_buffer;
+	void __iomem *d_scratch_buffer_addr;
+	void __iomem *d_scratch_buffer_size;
+	void __iomem *d_metadata_buffer_addr;
+	void __iomem *d_metadata_buffer_size;
+	void __iomem *d_nal_start_options;/* v7 and v8 */
+	void __iomem *d_cpb_buffer_addr;
+	void __iomem *d_cpb_buffer_size;
+	void __iomem *d_available_dpb_flag_upper;
+	void __iomem *d_available_dpb_flag_lower;
+	void __iomem *d_cpb_buffer_offset;
+	void __iomem *d_slice_if_enable;
+	void __iomem *d_picture_tag;
+	void __iomem *d_stream_data_size;
+	void __iomem *d_dynamic_dpb_flag_upper;/* v7 and v8 */
+	void __iomem *d_dynamic_dpb_flag_lower;/* v7 and v8 */
+	void __iomem *d_display_frame_width;
+	void __iomem *d_display_frame_height;
+	void __iomem *d_display_status;
+	void __iomem *d_display_first_plane_addr;
+	void __iomem *d_display_second_plane_addr;
+	void __iomem *d_display_third_plane_addr;/* only v8 */
+	void __iomem *d_display_frame_type;
+	void __iomem *d_display_crop_info1;
+	void __iomem *d_display_crop_info2;
+	void __iomem *d_display_picture_profile;
+	void __iomem *d_display_luma_crc;/* v7 and v8 */
+	void __iomem *d_display_chroma0_crc;/* v7 and v8 */
+	void __iomem *d_display_chroma1_crc;/* only v8 */
+	void __iomem *d_display_luma_crc_top;/* only v6 */
+	void __iomem *d_display_chroma_crc_top;/* only v6 */
+	void __iomem *d_display_luma_crc_bot;/* only v6 */
+	void __iomem *d_display_chroma_crc_bot;/* only v6 */
+	void __iomem *d_display_aspect_ratio;
+	void __iomem *d_display_extended_ar;
+	void __iomem *d_decoded_frame_width;
+	void __iomem *d_decoded_frame_height;
+	void __iomem *d_decoded_status;
+	void __iomem *d_decoded_first_plane_addr;
+	void __iomem *d_decoded_second_plane_addr;
+	void __iomem *d_decoded_third_plane_addr;/* only v8 */
+	void __iomem *d_decoded_frame_type;
+	void __iomem *d_decoded_crop_info1;
+	void __iomem *d_decoded_crop_info2;
+	void __iomem *d_decoded_picture_profile;
+	void __iomem *d_decoded_nal_size;
+	void __iomem *d_decoded_luma_crc;
+	void __iomem *d_decoded_chroma0_crc;
+	void __iomem *d_decoded_chroma1_crc;/* only v8 */
+	void __iomem *d_ret_picture_tag_top;
+	void __iomem *d_ret_picture_tag_bot;
+	void __iomem *d_ret_picture_time_top;
+	void __iomem *d_ret_picture_time_bot;
+	void __iomem *d_chroma_format;
+	void __iomem *d_vc1_info;/* v7 and v8 */
+	void __iomem *d_mpeg4_info;
+	void __iomem *d_h264_info;
+	void __iomem *d_metadata_addr_concealed_mb;
+	void __iomem *d_metadata_size_concealed_mb;
+	void __iomem *d_metadata_addr_vc1_param;
+	void __iomem *d_metadata_size_vc1_param;
+	void __iomem *d_metadata_addr_sei_nal;
+	void __iomem *d_metadata_size_sei_nal;
+	void __iomem *d_metadata_addr_vui;
+	void __iomem *d_metadata_size_vui;
+	void __iomem *d_metadata_addr_mvcvui;/* v7 and v8 */
+	void __iomem *d_metadata_size_mvcvui;/* v7 and v8 */
+	void __iomem *d_mvc_view_id;
+	void __iomem *d_frame_pack_sei_avail;
+	void __iomem *d_frame_pack_arrgment_id;
+	void __iomem *d_frame_pack_sei_info;
+	void __iomem *d_frame_pack_grid_pos;
+	void __iomem *d_display_recovery_sei_info;/* v7 and v8 */
+	void __iomem *d_decoded_recovery_sei_info;/* v7 and v8 */
+	void __iomem *d_display_first_addr;/* only v7 */
+	void __iomem *d_display_second_addr;/* only v7 */
+	void __iomem *d_display_third_addr;/* only v7 */
+	void __iomem *d_decoded_first_addr;/* only v7 */
+	void __iomem *d_decoded_second_addr;/* only v7 */
+	void __iomem *d_decoded_third_addr;/* only v7 */
+	void __iomem *d_used_dpb_flag_upper;/* v7 and v8 */
+	void __iomem *d_used_dpb_flag_lower;/* v7 and v8 */
 
 	/* encoder registers */
-	volatile void __iomem *e_frame_width;
-	volatile void __iomem *e_frame_height;
-	volatile void __iomem *e_cropped_frame_width;
-	volatile void __iomem *e_cropped_frame_height;
-	volatile void __iomem *e_frame_crop_offset;
-	volatile void __iomem *e_enc_options;
-	volatile void __iomem *e_picture_profile;
-	volatile void __iomem *e_vbv_buffer_size;
-	volatile void __iomem *e_vbv_init_delay;
-	volatile void __iomem *e_fixed_picture_qp;
-	volatile void __iomem *e_rc_config;
-	volatile void __iomem *e_rc_qp_bound;
-	volatile void __iomem *e_rc_qp_bound_pb;/* v7 and v8 */
-	volatile void __iomem *e_rc_mode;
-	volatile void __iomem *e_mb_rc_config;
-	volatile void __iomem *e_padding_ctrl;
-	volatile void __iomem *e_air_threshold;
-	volatile void __iomem *e_mv_hor_range;
-	volatile void __iomem *e_mv_ver_range;
-	volatile void __iomem *e_num_dpb;
-	volatile void __iomem *e_luma_dpb;
-	volatile void __iomem *e_chroma_dpb;
-	volatile void __iomem *e_me_buffer;
-	volatile void __iomem *e_scratch_buffer_addr;
-	volatile void __iomem *e_scratch_buffer_size;
-	volatile void __iomem *e_tmv_buffer0;
-	volatile void __iomem *e_tmv_buffer1;
-	volatile void __iomem *e_ir_buffer_addr;/* v7 and v8 */
-	volatile void __iomem *e_source_first_plane_addr;
-	volatile void __iomem *e_source_second_plane_addr;
-	volatile void __iomem *e_source_third_plane_addr;/* v7 and v8 */
-	volatile void __iomem *e_source_first_plane_stride;/* v7 and v8 */
-	volatile void __iomem *e_source_second_plane_stride;/* v7 and v8 */
-	volatile void __iomem *e_source_third_plane_stride;/* v7 and v8 */
-	volatile void __iomem *e_stream_buffer_addr;
-	volatile void __iomem *e_stream_buffer_size;
-	volatile void __iomem *e_roi_buffer_addr;
-	volatile void __iomem *e_param_change;
-	volatile void __iomem *e_ir_size;
-	volatile void __iomem *e_gop_config;
-	volatile void __iomem *e_mslice_mode;
-	volatile void __iomem *e_mslice_size_mb;
-	volatile void __iomem *e_mslice_size_bits;
-	volatile void __iomem *e_frame_insertion;
-	volatile void __iomem *e_rc_frame_rate;
-	volatile void __iomem *e_rc_bit_rate;
-	volatile void __iomem *e_rc_roi_ctrl;
-	volatile void __iomem *e_picture_tag;
-	volatile void __iomem *e_bit_count_enable;
-	volatile void __iomem *e_max_bit_count;
-	volatile void __iomem *e_min_bit_count;
-	volatile void __iomem *e_metadata_buffer_addr;
-	volatile void __iomem *e_metadata_buffer_size;
-	volatile void __iomem *e_encoded_source_first_plane_addr;
-	volatile void __iomem *e_encoded_source_second_plane_addr;
-	volatile void __iomem *e_encoded_source_third_plane_addr;/* v7 and v8 */
-	volatile void __iomem *e_stream_size;
-	volatile void __iomem *e_slice_type;
-	volatile void __iomem *e_picture_count;
-	volatile void __iomem *e_ret_picture_tag;
-	volatile void __iomem *e_stream_buffer_write_pointer; /*  only v6 */
-	volatile void __iomem *e_recon_luma_dpb_addr;
-	volatile void __iomem *e_recon_chroma_dpb_addr;
-	volatile void __iomem *e_metadata_addr_enc_slice;
-	volatile void __iomem *e_metadata_size_enc_slice;
-	volatile void __iomem *e_mpeg4_options;
-	volatile void __iomem *e_mpeg4_hec_period;
-	volatile void __iomem *e_aspect_ratio;
-	volatile void __iomem *e_extended_sar;
-	volatile void __iomem *e_h264_options;
-	volatile void __iomem *e_h264_options_2;/* v7 and v8 */
-	volatile void __iomem *e_h264_lf_alpha_offset;
-	volatile void __iomem *e_h264_lf_beta_offset;
-	volatile void __iomem *e_h264_i_period;
-	volatile void __iomem *e_h264_fmo_slice_grp_map_type;
-	volatile void __iomem *e_h264_fmo_num_slice_grp_minus1;
-	volatile void __iomem *e_h264_fmo_slice_grp_change_dir;
-	volatile void __iomem *e_h264_fmo_slice_grp_change_rate_minus1;
-	volatile void __iomem *e_h264_fmo_run_length_minus1_0;
-	volatile void __iomem *e_h264_aso_slice_order_0;
-	volatile void __iomem *e_h264_chroma_qp_offset;
-	volatile void __iomem *e_h264_num_t_layer;
-	volatile void __iomem *e_h264_hierarchical_qp_layer0;
-	volatile void __iomem *e_h264_frame_packing_sei_info;
-	volatile void __iomem *e_h264_nal_control;/* v7 and v8 */
-	volatile void __iomem *e_mvc_frame_qp_view1;
-	volatile void __iomem *e_mvc_rc_bit_rate_view1;
-	volatile void __iomem *e_mvc_rc_qbound_view1;
-	volatile void __iomem *e_mvc_rc_mode_view1;
-	volatile void __iomem *e_mvc_inter_view_prediction_on;
-	volatile void __iomem *e_vp8_options;/* v7 and v8 */
-	volatile void __iomem *e_vp8_filter_options;/* v7 and v8 */
-	volatile void __iomem *e_vp8_golden_frame_option;/* v7 and v8 */
-	volatile void __iomem *e_vp8_num_t_layer;/* v7 and v8 */
-	volatile void __iomem *e_vp8_hierarchical_qp_layer0;/* v7 and v8 */
-	volatile void __iomem *e_vp8_hierarchical_qp_layer1;/* v7 and v8 */
-	volatile void __iomem *e_vp8_hierarchical_qp_layer2;/* v7 and v8 */
+	void __iomem *e_frame_width;
+	void __iomem *e_frame_height;
+	void __iomem *e_cropped_frame_width;
+	void __iomem *e_cropped_frame_height;
+	void __iomem *e_frame_crop_offset;
+	void __iomem *e_enc_options;
+	void __iomem *e_picture_profile;
+	void __iomem *e_vbv_buffer_size;
+	void __iomem *e_vbv_init_delay;
+	void __iomem *e_fixed_picture_qp;
+	void __iomem *e_rc_config;
+	void __iomem *e_rc_qp_bound;
+	void __iomem *e_rc_qp_bound_pb;/* v7 and v8 */
+	void __iomem *e_rc_mode;
+	void __iomem *e_mb_rc_config;
+	void __iomem *e_padding_ctrl;
+	void __iomem *e_air_threshold;
+	void __iomem *e_mv_hor_range;
+	void __iomem *e_mv_ver_range;
+	void __iomem *e_num_dpb;
+	void __iomem *e_luma_dpb;
+	void __iomem *e_chroma_dpb;
+	void __iomem *e_me_buffer;
+	void __iomem *e_scratch_buffer_addr;
+	void __iomem *e_scratch_buffer_size;
+	void __iomem *e_tmv_buffer0;
+	void __iomem *e_tmv_buffer1;
+	void __iomem *e_ir_buffer_addr;/* v7 and v8 */
+	void __iomem *e_source_first_plane_addr;
+	void __iomem *e_source_second_plane_addr;
+	void __iomem *e_source_third_plane_addr;/* v7 and v8 */
+	void __iomem *e_source_first_plane_stride;/* v7 and v8 */
+	void __iomem *e_source_second_plane_stride;/* v7 and v8 */
+	void __iomem *e_source_third_plane_stride;/* v7 and v8 */
+	void __iomem *e_stream_buffer_addr;
+	void __iomem *e_stream_buffer_size;
+	void __iomem *e_roi_buffer_addr;
+	void __iomem *e_param_change;
+	void __iomem *e_ir_size;
+	void __iomem *e_gop_config;
+	void __iomem *e_mslice_mode;
+	void __iomem *e_mslice_size_mb;
+	void __iomem *e_mslice_size_bits;
+	void __iomem *e_frame_insertion;
+	void __iomem *e_rc_frame_rate;
+	void __iomem *e_rc_bit_rate;
+	void __iomem *e_rc_roi_ctrl;
+	void __iomem *e_picture_tag;
+	void __iomem *e_bit_count_enable;
+	void __iomem *e_max_bit_count;
+	void __iomem *e_min_bit_count;
+	void __iomem *e_metadata_buffer_addr;
+	void __iomem *e_metadata_buffer_size;
+	void __iomem *e_encoded_source_first_plane_addr;
+	void __iomem *e_encoded_source_second_plane_addr;
+	void __iomem *e_encoded_source_third_plane_addr;/* v7 and v8 */
+	void __iomem *e_stream_size;
+	void __iomem *e_slice_type;
+	void __iomem *e_picture_count;
+	void __iomem *e_ret_picture_tag;
+	void __iomem *e_stream_buffer_write_pointer; /*  only v6 */
+	void __iomem *e_recon_luma_dpb_addr;
+	void __iomem *e_recon_chroma_dpb_addr;
+	void __iomem *e_metadata_addr_enc_slice;
+	void __iomem *e_metadata_size_enc_slice;
+	void __iomem *e_mpeg4_options;
+	void __iomem *e_mpeg4_hec_period;
+	void __iomem *e_aspect_ratio;
+	void __iomem *e_extended_sar;
+	void __iomem *e_h264_options;
+	void __iomem *e_h264_options_2;/* v7 and v8 */
+	void __iomem *e_h264_lf_alpha_offset;
+	void __iomem *e_h264_lf_beta_offset;
+	void __iomem *e_h264_i_period;
+	void __iomem *e_h264_fmo_slice_grp_map_type;
+	void __iomem *e_h264_fmo_num_slice_grp_minus1;
+	void __iomem *e_h264_fmo_slice_grp_change_dir;
+	void __iomem *e_h264_fmo_slice_grp_change_rate_minus1;
+	void __iomem *e_h264_fmo_run_length_minus1_0;
+	void __iomem *e_h264_aso_slice_order_0;
+	void __iomem *e_h264_chroma_qp_offset;
+	void __iomem *e_h264_num_t_layer;
+	void __iomem *e_h264_hierarchical_qp_layer0;
+	void __iomem *e_h264_frame_packing_sei_info;
+	void __iomem *e_h264_nal_control;/* v7 and v8 */
+	void __iomem *e_mvc_frame_qp_view1;
+	void __iomem *e_mvc_rc_bit_rate_view1;
+	void __iomem *e_mvc_rc_qbound_view1;
+	void __iomem *e_mvc_rc_mode_view1;
+	void __iomem *e_mvc_inter_view_prediction_on;
+	void __iomem *e_vp8_options;/* v7 and v8 */
+	void __iomem *e_vp8_filter_options;/* v7 and v8 */
+	void __iomem *e_vp8_golden_frame_option;/* v7 and v8 */
+	void __iomem *e_vp8_num_t_layer;/* v7 and v8 */
+	void __iomem *e_vp8_hierarchical_qp_layer0;/* v7 and v8 */
+	void __iomem *e_vp8_hierarchical_qp_layer1;/* v7 and v8 */
+	void __iomem *e_vp8_hierarchical_qp_layer2;/* v7 and v8 */
 };
 
 struct s5p_mfc_hw_ops {
@@ -281,28 +281,14 @@
 	void (*release_dev_context_buffer)(struct s5p_mfc_dev *dev);
 	void (*dec_calc_dpb_size)(struct s5p_mfc_ctx *ctx);
 	void (*enc_calc_src_size)(struct s5p_mfc_ctx *ctx);
-	int (*set_dec_stream_buffer)(struct s5p_mfc_ctx *ctx,
-			int buf_addr, unsigned int start_num_byte,
-			unsigned int buf_size);
-	int (*set_dec_frame_buffer)(struct s5p_mfc_ctx *ctx);
 	int (*set_enc_stream_buffer)(struct s5p_mfc_ctx *ctx,
 			unsigned long addr, unsigned int size);
 	void (*set_enc_frame_buffer)(struct s5p_mfc_ctx *ctx,
 			unsigned long y_addr, unsigned long c_addr);
 	void (*get_enc_frame_buffer)(struct s5p_mfc_ctx *ctx,
 			unsigned long *y_addr, unsigned long *c_addr);
-	int (*set_enc_ref_buffer)(struct s5p_mfc_ctx *ctx);
-	int (*init_decode)(struct s5p_mfc_ctx *ctx);
-	int (*init_encode)(struct s5p_mfc_ctx *ctx);
-	int (*encode_one_frame)(struct s5p_mfc_ctx *ctx);
 	void (*try_run)(struct s5p_mfc_dev *dev);
-	void (*cleanup_queue)(struct list_head *lh,
-			struct vb2_queue *vq);
 	void (*clear_int_flags)(struct s5p_mfc_dev *dev);
-	void (*write_info)(struct s5p_mfc_ctx *ctx, unsigned int data,
-			unsigned int ofs);
-	unsigned int (*read_info)(struct s5p_mfc_ctx *ctx,
-			unsigned long ofs);
 	int (*get_dspl_y_adr)(struct s5p_mfc_dev *dev);
 	int (*get_dec_y_adr)(struct s5p_mfc_dev *dev);
 	int (*get_dspl_status)(struct s5p_mfc_dev *dev);
@@ -313,7 +299,6 @@
 	int (*get_int_reason)(struct s5p_mfc_dev *dev);
 	int (*get_int_err)(struct s5p_mfc_dev *dev);
 	int (*err_dec)(unsigned int err);
-	int (*err_dspl)(unsigned int err);
 	int (*get_img_width)(struct s5p_mfc_dev *dev);
 	int (*get_img_height)(struct s5p_mfc_dev *dev);
 	int (*get_dpb_count)(struct s5p_mfc_dev *dev);
@@ -322,10 +307,6 @@
 	int (*get_enc_strm_size)(struct s5p_mfc_dev *dev);
 	int (*get_enc_slice_type)(struct s5p_mfc_dev *dev);
 	int (*get_enc_dpb_count)(struct s5p_mfc_dev *dev);
-	int (*get_enc_pic_count)(struct s5p_mfc_dev *dev);
-	int (*get_sei_avail_status)(struct s5p_mfc_ctx *ctx);
-	int (*get_mvc_num_views)(struct s5p_mfc_dev *dev);
-	int (*get_mvc_view_id)(struct s5p_mfc_dev *dev);
 	unsigned int (*get_pic_type_top)(struct s5p_mfc_ctx *ctx);
 	unsigned int (*get_pic_type_bot)(struct s5p_mfc_ctx *ctx);
 	unsigned int (*get_crop_info_h)(struct s5p_mfc_ctx *ctx);
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_opr_v5.c b/drivers/media/platform/s5p-mfc/s5p_mfc_opr_v5.c
index 873c933..81e1e4c 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc_opr_v5.c
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc_opr_v5.c
@@ -1153,27 +1153,6 @@
 	return 0;
 }
 
-static int s5p_mfc_get_new_ctx(struct s5p_mfc_dev *dev)
-{
-	unsigned long flags;
-	int new_ctx;
-	int cnt;
-
-	spin_lock_irqsave(&dev->condlock, flags);
-	new_ctx = (dev->curr_ctx + 1) % MFC_NUM_CONTEXTS;
-	cnt = 0;
-	while (!test_bit(new_ctx, &dev->ctx_work_bits)) {
-		new_ctx = (new_ctx + 1) % MFC_NUM_CONTEXTS;
-		if (++cnt > MFC_NUM_CONTEXTS) {
-			/* No contexts to run */
-			spin_unlock_irqrestore(&dev->condlock, flags);
-			return -EAGAIN;
-		}
-	}
-	spin_unlock_irqrestore(&dev->condlock, flags);
-	return new_ctx;
-}
-
 static void s5p_mfc_run_res_change(struct s5p_mfc_ctx *ctx)
 {
 	struct s5p_mfc_dev *dev = ctx->dev;
@@ -1187,7 +1166,6 @@
 {
 	struct s5p_mfc_dev *dev = ctx->dev;
 	struct s5p_mfc_buf *temp_vb;
-	unsigned long flags;
 
 	if (ctx->state == MFCINST_FINISHING) {
 		last_frame = MFC_DEC_LAST_FRAME;
@@ -1197,11 +1175,9 @@
 		return 0;
 	}
 
-	spin_lock_irqsave(&dev->irqlock, flags);
 	/* Frames are being decoded */
 	if (list_empty(&ctx->src_queue)) {
 		mfc_debug(2, "No src buffers\n");
-		spin_unlock_irqrestore(&dev->irqlock, flags);
 		return -EAGAIN;
 	}
 	/* Get the next source buffer */
@@ -1210,7 +1186,6 @@
 	s5p_mfc_set_dec_stream_buffer_v5(ctx,
 		vb2_dma_contig_plane_dma_addr(&temp_vb->b->vb2_buf, 0),
 		ctx->consumed_stream, temp_vb->b->vb2_buf.planes[0].bytesused);
-	spin_unlock_irqrestore(&dev->irqlock, flags);
 	dev->curr_ctx = ctx->num;
 	if (temp_vb->b->vb2_buf.planes[0].bytesused == 0) {
 		last_frame = MFC_DEC_LAST_FRAME;
@@ -1224,21 +1199,17 @@
 static int s5p_mfc_run_enc_frame(struct s5p_mfc_ctx *ctx)
 {
 	struct s5p_mfc_dev *dev = ctx->dev;
-	unsigned long flags;
 	struct s5p_mfc_buf *dst_mb;
 	struct s5p_mfc_buf *src_mb;
 	unsigned long src_y_addr, src_c_addr, dst_addr;
 	unsigned int dst_size;
 
-	spin_lock_irqsave(&dev->irqlock, flags);
 	if (list_empty(&ctx->src_queue) && ctx->state != MFCINST_FINISHING) {
 		mfc_debug(2, "no src buffers\n");
-		spin_unlock_irqrestore(&dev->irqlock, flags);
 		return -EAGAIN;
 	}
 	if (list_empty(&ctx->dst_queue)) {
 		mfc_debug(2, "no dst buffers\n");
-		spin_unlock_irqrestore(&dev->irqlock, flags);
 		return -EAGAIN;
 	}
 	if (list_empty(&ctx->src_queue)) {
@@ -1270,7 +1241,6 @@
 	dst_addr = vb2_dma_contig_plane_dma_addr(&dst_mb->b->vb2_buf, 0);
 	dst_size = vb2_plane_size(&dst_mb->b->vb2_buf, 0);
 	s5p_mfc_set_enc_stream_buffer_v5(ctx, dst_addr, dst_size);
-	spin_unlock_irqrestore(&dev->irqlock, flags);
 	dev->curr_ctx = ctx->num;
 	mfc_debug(2, "encoding buffer with index=%d state=%d\n",
 		  src_mb ? src_mb->b->vb2_buf.index : -1, ctx->state);
@@ -1281,11 +1251,9 @@
 static void s5p_mfc_run_init_dec(struct s5p_mfc_ctx *ctx)
 {
 	struct s5p_mfc_dev *dev = ctx->dev;
-	unsigned long flags;
 	struct s5p_mfc_buf *temp_vb;
 
 	/* Initializing decoding - parsing header */
-	spin_lock_irqsave(&dev->irqlock, flags);
 	mfc_debug(2, "Preparing to init decoding\n");
 	temp_vb = list_entry(ctx->src_queue.next, struct s5p_mfc_buf, list);
 	s5p_mfc_set_dec_desc_buffer(ctx);
@@ -1294,7 +1262,6 @@
 	s5p_mfc_set_dec_stream_buffer_v5(ctx,
 			vb2_dma_contig_plane_dma_addr(&temp_vb->b->vb2_buf, 0),
 			0, temp_vb->b->vb2_buf.planes[0].bytesused);
-	spin_unlock_irqrestore(&dev->irqlock, flags);
 	dev->curr_ctx = ctx->num;
 	s5p_mfc_init_decode_v5(ctx);
 }
@@ -1302,18 +1269,15 @@
 static void s5p_mfc_run_init_enc(struct s5p_mfc_ctx *ctx)
 {
 	struct s5p_mfc_dev *dev = ctx->dev;
-	unsigned long flags;
 	struct s5p_mfc_buf *dst_mb;
 	unsigned long dst_addr;
 	unsigned int dst_size;
 
 	s5p_mfc_set_enc_ref_buffer_v5(ctx);
-	spin_lock_irqsave(&dev->irqlock, flags);
 	dst_mb = list_entry(ctx->dst_queue.next, struct s5p_mfc_buf, list);
 	dst_addr = vb2_dma_contig_plane_dma_addr(&dst_mb->b->vb2_buf, 0);
 	dst_size = vb2_plane_size(&dst_mb->b->vb2_buf, 0);
 	s5p_mfc_set_enc_stream_buffer_v5(ctx, dst_addr, dst_size);
-	spin_unlock_irqrestore(&dev->irqlock, flags);
 	dev->curr_ctx = ctx->num;
 	s5p_mfc_init_encode_v5(ctx);
 }
@@ -1321,7 +1285,6 @@
 static int s5p_mfc_run_init_dec_buffers(struct s5p_mfc_ctx *ctx)
 {
 	struct s5p_mfc_dev *dev = ctx->dev;
-	unsigned long flags;
 	struct s5p_mfc_buf *temp_vb;
 	int ret;
 
@@ -1335,11 +1298,9 @@
 			"before starting processing\n");
 		return -EAGAIN;
 	}
-	spin_lock_irqsave(&dev->irqlock, flags);
 	if (list_empty(&ctx->src_queue)) {
 		mfc_err("Header has been deallocated in the middle of"
 			" initialization\n");
-		spin_unlock_irqrestore(&dev->irqlock, flags);
 		return -EIO;
 	}
 	temp_vb = list_entry(ctx->src_queue.next, struct s5p_mfc_buf, list);
@@ -1348,7 +1309,6 @@
 	s5p_mfc_set_dec_stream_buffer_v5(ctx,
 			vb2_dma_contig_plane_dma_addr(&temp_vb->b->vb2_buf, 0),
 			0, temp_vb->b->vb2_buf.planes[0].bytesused);
-	spin_unlock_irqrestore(&dev->irqlock, flags);
 	dev->curr_ctx = ctx->num;
 	ret = s5p_mfc_set_dec_frame_buffer_v5(ctx);
 	if (ret) {
@@ -1472,21 +1432,6 @@
 	}
 }
 
-
-static void s5p_mfc_cleanup_queue_v5(struct list_head *lh, struct vb2_queue *vq)
-{
-	struct s5p_mfc_buf *b;
-	int i;
-
-	while (!list_empty(lh)) {
-		b = list_entry(lh->next, struct s5p_mfc_buf, list);
-		for (i = 0; i < b->b->vb2_buf.num_planes; i++)
-			vb2_set_plane_payload(&b->b->vb2_buf, i, 0);
-		vb2_buffer_done(&b->b->vb2_buf, VB2_BUF_STATE_ERROR);
-		list_del(&b->list);
-	}
-}
-
 static void s5p_mfc_clear_int_flags_v5(struct s5p_mfc_dev *dev)
 {
 	mfc_write(dev, 0, S5P_FIMV_RISC_HOST_INT);
@@ -1590,11 +1535,6 @@
 	return (err & S5P_FIMV_ERR_DEC_MASK) >> S5P_FIMV_ERR_DEC_SHIFT;
 }
 
-static int s5p_mfc_err_dspl_v5(unsigned int err)
-{
-	return (err & S5P_FIMV_ERR_DSPL_MASK) >> S5P_FIMV_ERR_DSPL_SHIFT;
-}
-
 static int s5p_mfc_get_img_width_v5(struct s5p_mfc_dev *dev)
 {
 	return mfc_read(dev, S5P_FIMV_SI_HRESOL);
@@ -1636,26 +1576,6 @@
 	return -1;
 }
 
-static int s5p_mfc_get_enc_pic_count_v5(struct s5p_mfc_dev *dev)
-{
-	return mfc_read(dev, S5P_FIMV_ENC_SI_PIC_CNT);
-}
-
-static int s5p_mfc_get_sei_avail_status_v5(struct s5p_mfc_ctx *ctx)
-{
-	return s5p_mfc_read_info_v5(ctx, FRAME_PACK_SEI_AVAIL);
-}
-
-static int s5p_mfc_get_mvc_num_views_v5(struct s5p_mfc_dev *dev)
-{
-	return -1;
-}
-
-static int s5p_mfc_get_mvc_view_id_v5(struct s5p_mfc_dev *dev)
-{
-	return -1;
-}
-
 static unsigned int s5p_mfc_get_pic_type_top_v5(struct s5p_mfc_ctx *ctx)
 {
 	return s5p_mfc_read_info_v5(ctx, PIC_TIME_TOP);
@@ -1688,20 +1608,11 @@
 	.release_dev_context_buffer = s5p_mfc_release_dev_context_buffer_v5,
 	.dec_calc_dpb_size = s5p_mfc_dec_calc_dpb_size_v5,
 	.enc_calc_src_size = s5p_mfc_enc_calc_src_size_v5,
-	.set_dec_stream_buffer = s5p_mfc_set_dec_stream_buffer_v5,
-	.set_dec_frame_buffer = s5p_mfc_set_dec_frame_buffer_v5,
 	.set_enc_stream_buffer = s5p_mfc_set_enc_stream_buffer_v5,
 	.set_enc_frame_buffer = s5p_mfc_set_enc_frame_buffer_v5,
 	.get_enc_frame_buffer = s5p_mfc_get_enc_frame_buffer_v5,
-	.set_enc_ref_buffer = s5p_mfc_set_enc_ref_buffer_v5,
-	.init_decode = s5p_mfc_init_decode_v5,
-	.init_encode = s5p_mfc_init_encode_v5,
-	.encode_one_frame = s5p_mfc_encode_one_frame_v5,
 	.try_run = s5p_mfc_try_run_v5,
-	.cleanup_queue = s5p_mfc_cleanup_queue_v5,
 	.clear_int_flags = s5p_mfc_clear_int_flags_v5,
-	.write_info = s5p_mfc_write_info_v5,
-	.read_info = s5p_mfc_read_info_v5,
 	.get_dspl_y_adr = s5p_mfc_get_dspl_y_adr_v5,
 	.get_dec_y_adr = s5p_mfc_get_dec_y_adr_v5,
 	.get_dspl_status = s5p_mfc_get_dspl_status_v5,
@@ -1712,7 +1623,6 @@
 	.get_int_reason = s5p_mfc_get_int_reason_v5,
 	.get_int_err = s5p_mfc_get_int_err_v5,
 	.err_dec = s5p_mfc_err_dec_v5,
-	.err_dspl = s5p_mfc_err_dspl_v5,
 	.get_img_width = s5p_mfc_get_img_width_v5,
 	.get_img_height = s5p_mfc_get_img_height_v5,
 	.get_dpb_count = s5p_mfc_get_dpb_count_v5,
@@ -1721,10 +1631,6 @@
 	.get_enc_strm_size = s5p_mfc_get_enc_strm_size_v5,
 	.get_enc_slice_type = s5p_mfc_get_enc_slice_type_v5,
 	.get_enc_dpb_count = s5p_mfc_get_enc_dpb_count_v5,
-	.get_enc_pic_count = s5p_mfc_get_enc_pic_count_v5,
-	.get_sei_avail_status = s5p_mfc_get_sei_avail_status_v5,
-	.get_mvc_num_views = s5p_mfc_get_mvc_num_views_v5,
-	.get_mvc_view_id = s5p_mfc_get_mvc_view_id_v5,
 	.get_pic_type_top = s5p_mfc_get_pic_type_top_v5,
 	.get_pic_type_bot = s5p_mfc_get_pic_type_bot_v5,
 	.get_crop_info_h = s5p_mfc_get_crop_info_h_v5,
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_opr_v6.c b/drivers/media/platform/s5p-mfc/s5p_mfc_opr_v6.c
index b958453..d6f207e 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc_opr_v6.c
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc_opr_v6.c
@@ -505,7 +505,7 @@
 	}
 
 	writel(ctx->inst_no, mfc_regs->instance_id);
-	s5p_mfc_hw_call_void(dev->mfc_cmds, cmd_host2risc, dev,
+	s5p_mfc_hw_call(dev->mfc_cmds, cmd_host2risc, dev,
 			S5P_FIMV_CH_INIT_BUFS_V6, NULL);
 
 	mfc_debug(2, "After setting buffers.\n");
@@ -603,7 +603,7 @@
 	}
 
 	writel(ctx->inst_no, mfc_regs->instance_id);
-	s5p_mfc_hw_call_void(dev->mfc_cmds, cmd_host2risc, dev,
+	s5p_mfc_hw_call(dev->mfc_cmds, cmd_host2risc, dev,
 			S5P_FIMV_CH_INIT_BUFS_V6, NULL);
 
 	mfc_debug_leave();
@@ -1378,7 +1378,7 @@
 	writel(ctx->sei_fp_parse & 0x1, mfc_regs->d_sei_enable);
 
 	writel(ctx->inst_no, mfc_regs->instance_id);
-	s5p_mfc_hw_call_void(dev->mfc_cmds, cmd_host2risc, dev,
+	s5p_mfc_hw_call(dev->mfc_cmds, cmd_host2risc, dev,
 			S5P_FIMV_CH_SEQ_HEADER_V6, NULL);
 
 	mfc_debug_leave();
@@ -1393,7 +1393,7 @@
 	if (flush) {
 		dev->curr_ctx = ctx->num;
 		writel(ctx->inst_no, mfc_regs->instance_id);
-		s5p_mfc_hw_call_void(dev->mfc_cmds, cmd_host2risc, dev,
+		s5p_mfc_hw_call(dev->mfc_cmds, cmd_host2risc, dev,
 				S5P_FIMV_H2R_CMD_FLUSH_V6, NULL);
 	}
 }
@@ -1413,11 +1413,11 @@
 	 * is the last frame or not. */
 	switch (last_frame) {
 	case 0:
-		s5p_mfc_hw_call_void(dev->mfc_cmds, cmd_host2risc, dev,
+		s5p_mfc_hw_call(dev->mfc_cmds, cmd_host2risc, dev,
 				S5P_FIMV_CH_FRAME_START_V6, NULL);
 		break;
 	case 1:
-		s5p_mfc_hw_call_void(dev->mfc_cmds, cmd_host2risc, dev,
+		s5p_mfc_hw_call(dev->mfc_cmds, cmd_host2risc, dev,
 				S5P_FIMV_CH_LAST_FRAME_V6, NULL);
 		break;
 	default:
@@ -1455,7 +1455,7 @@
 	}
 
 	writel(ctx->inst_no, mfc_regs->instance_id);
-	s5p_mfc_hw_call_void(dev->mfc_cmds, cmd_host2risc, dev,
+	s5p_mfc_hw_call(dev->mfc_cmds, cmd_host2risc, dev,
 			S5P_FIMV_CH_SEQ_HEADER_V6, NULL);
 
 	return 0;
@@ -1500,37 +1500,13 @@
 		cmd = S5P_FIMV_CH_LAST_FRAME_V6;
 
 	writel(ctx->inst_no, mfc_regs->instance_id);
-	s5p_mfc_hw_call_void(dev->mfc_cmds, cmd_host2risc, dev, cmd, NULL);
+	s5p_mfc_hw_call(dev->mfc_cmds, cmd_host2risc, dev, cmd, NULL);
 
 	mfc_debug(2, "--\n");
 
 	return 0;
 }
 
-static inline int s5p_mfc_get_new_ctx(struct s5p_mfc_dev *dev)
-{
-	unsigned long flags;
-	int new_ctx;
-	int cnt;
-
-	spin_lock_irqsave(&dev->condlock, flags);
-	mfc_debug(2, "Previous context: %d (bits %08lx)\n", dev->curr_ctx,
-							dev->ctx_work_bits);
-	new_ctx = (dev->curr_ctx + 1) % MFC_NUM_CONTEXTS;
-	cnt = 0;
-	while (!test_bit(new_ctx, &dev->ctx_work_bits)) {
-		new_ctx = (new_ctx + 1) % MFC_NUM_CONTEXTS;
-		cnt++;
-		if (cnt > MFC_NUM_CONTEXTS) {
-			/* No contexts to run */
-			spin_unlock_irqrestore(&dev->condlock, flags);
-			return -EAGAIN;
-		}
-	}
-	spin_unlock_irqrestore(&dev->condlock, flags);
-	return new_ctx;
-}
-
 static inline void s5p_mfc_run_dec_last_frames(struct s5p_mfc_ctx *ctx)
 {
 	struct s5p_mfc_dev *dev = ctx->dev;
@@ -1544,7 +1520,6 @@
 {
 	struct s5p_mfc_dev *dev = ctx->dev;
 	struct s5p_mfc_buf *temp_vb;
-	unsigned long flags;
 	int last_frame = 0;
 
 	if (ctx->state == MFCINST_FINISHING) {
@@ -1556,11 +1531,9 @@
 		return 0;
 	}
 
-	spin_lock_irqsave(&dev->irqlock, flags);
 	/* Frames are being decoded */
 	if (list_empty(&ctx->src_queue)) {
 		mfc_debug(2, "No src buffers.\n");
-		spin_unlock_irqrestore(&dev->irqlock, flags);
 		return -EAGAIN;
 	}
 	/* Get the next source buffer */
@@ -1570,7 +1543,6 @@
 		vb2_dma_contig_plane_dma_addr(&temp_vb->b->vb2_buf, 0),
 			ctx->consumed_stream,
 			temp_vb->b->vb2_buf.planes[0].bytesused);
-	spin_unlock_irqrestore(&dev->irqlock, flags);
 
 	dev->curr_ctx = ctx->num;
 	if (temp_vb->b->vb2_buf.planes[0].bytesused == 0) {
@@ -1586,7 +1558,6 @@
 static inline int s5p_mfc_run_enc_frame(struct s5p_mfc_ctx *ctx)
 {
 	struct s5p_mfc_dev *dev = ctx->dev;
-	unsigned long flags;
 	struct s5p_mfc_buf *dst_mb;
 	struct s5p_mfc_buf *src_mb;
 	unsigned long src_y_addr, src_c_addr, dst_addr;
@@ -1595,17 +1566,13 @@
 	*/
 	unsigned int dst_size;
 
-	spin_lock_irqsave(&dev->irqlock, flags);
-
 	if (list_empty(&ctx->src_queue) && ctx->state != MFCINST_FINISHING) {
 		mfc_debug(2, "no src buffers.\n");
-		spin_unlock_irqrestore(&dev->irqlock, flags);
 		return -EAGAIN;
 	}
 
 	if (list_empty(&ctx->dst_queue)) {
 		mfc_debug(2, "no dst buffers.\n");
-		spin_unlock_irqrestore(&dev->irqlock, flags);
 		return -EAGAIN;
 	}
 
@@ -1639,8 +1606,6 @@
 
 	s5p_mfc_set_enc_stream_buffer_v6(ctx, dst_addr, dst_size);
 
-	spin_unlock_irqrestore(&dev->irqlock, flags);
-
 	dev->curr_ctx = ctx->num;
 	s5p_mfc_encode_one_frame_v6(ctx);
 
@@ -1650,18 +1615,15 @@
 static inline void s5p_mfc_run_init_dec(struct s5p_mfc_ctx *ctx)
 {
 	struct s5p_mfc_dev *dev = ctx->dev;
-	unsigned long flags;
 	struct s5p_mfc_buf *temp_vb;
 
 	/* Initializing decoding - parsing header */
-	spin_lock_irqsave(&dev->irqlock, flags);
 	mfc_debug(2, "Preparing to init decoding.\n");
 	temp_vb = list_entry(ctx->src_queue.next, struct s5p_mfc_buf, list);
 	mfc_debug(2, "Header size: %d\n", temp_vb->b->vb2_buf.planes[0].bytesused);
 	s5p_mfc_set_dec_stream_buffer_v6(ctx,
 		vb2_dma_contig_plane_dma_addr(&temp_vb->b->vb2_buf, 0), 0,
 			temp_vb->b->vb2_buf.planes[0].bytesused);
-	spin_unlock_irqrestore(&dev->irqlock, flags);
 	dev->curr_ctx = ctx->num;
 	s5p_mfc_init_decode_v6(ctx);
 }
@@ -1669,18 +1631,14 @@
 static inline void s5p_mfc_run_init_enc(struct s5p_mfc_ctx *ctx)
 {
 	struct s5p_mfc_dev *dev = ctx->dev;
-	unsigned long flags;
 	struct s5p_mfc_buf *dst_mb;
 	unsigned long dst_addr;
 	unsigned int dst_size;
 
-	spin_lock_irqsave(&dev->irqlock, flags);
-
 	dst_mb = list_entry(ctx->dst_queue.next, struct s5p_mfc_buf, list);
 	dst_addr = vb2_dma_contig_plane_dma_addr(&dst_mb->b->vb2_buf, 0);
 	dst_size = vb2_plane_size(&dst_mb->b->vb2_buf, 0);
 	s5p_mfc_set_enc_stream_buffer_v6(ctx, dst_addr, dst_size);
-	spin_unlock_irqrestore(&dev->irqlock, flags);
 	dev->curr_ctx = ctx->num;
 	s5p_mfc_init_encode_v6(ctx);
 }
@@ -1846,21 +1804,6 @@
 	}
 }
 
-
-static void s5p_mfc_cleanup_queue_v6(struct list_head *lh, struct vb2_queue *vq)
-{
-	struct s5p_mfc_buf *b;
-	int i;
-
-	while (!list_empty(lh)) {
-		b = list_entry(lh->next, struct s5p_mfc_buf, list);
-		for (i = 0; i < b->b->vb2_buf.num_planes; i++)
-			vb2_set_plane_payload(&b->b->vb2_buf, i, 0);
-		vb2_buffer_done(&b->b->vb2_buf, VB2_BUF_STATE_ERROR);
-		list_del(&b->list);
-	}
-}
-
 static void s5p_mfc_clear_int_flags_v6(struct s5p_mfc_dev *dev)
 {
 	const struct s5p_mfc_regs *mfc_regs = dev->mfc_regs;
@@ -1868,14 +1811,6 @@
 	writel(0, mfc_regs->risc2host_int);
 }
 
-static void s5p_mfc_write_info_v6(struct s5p_mfc_ctx *ctx, unsigned int data,
-		unsigned int ofs)
-{
-	s5p_mfc_clock_on();
-	writel(data, (void __iomem *)((unsigned long)ofs));
-	s5p_mfc_clock_off();
-}
-
 static unsigned int
 s5p_mfc_read_info_v6(struct s5p_mfc_ctx *ctx, unsigned long ofs)
 {
@@ -1942,11 +1877,6 @@
 	return (err & S5P_FIMV_ERR_DEC_MASK_V6) >> S5P_FIMV_ERR_DEC_SHIFT_V6;
 }
 
-static int s5p_mfc_err_dspl_v6(unsigned int err)
-{
-	return (err & S5P_FIMV_ERR_DSPL_MASK_V6) >> S5P_FIMV_ERR_DSPL_SHIFT_V6;
-}
-
 static int s5p_mfc_get_img_width_v6(struct s5p_mfc_dev *dev)
 {
 	return readl(dev->mfc_regs->d_display_frame_width);
@@ -1987,27 +1917,6 @@
 	return readl(dev->mfc_regs->e_slice_type);
 }
 
-static int s5p_mfc_get_enc_pic_count_v6(struct s5p_mfc_dev *dev)
-{
-	return readl(dev->mfc_regs->e_picture_count);
-}
-
-static int s5p_mfc_get_sei_avail_status_v6(struct s5p_mfc_ctx *ctx)
-{
-	struct s5p_mfc_dev *dev = ctx->dev;
-	return readl(dev->mfc_regs->d_frame_pack_sei_avail);
-}
-
-static int s5p_mfc_get_mvc_num_views_v6(struct s5p_mfc_dev *dev)
-{
-	return readl(dev->mfc_regs->d_mvc_num_views);
-}
-
-static int s5p_mfc_get_mvc_view_id_v6(struct s5p_mfc_dev *dev)
-{
-	return readl(dev->mfc_regs->d_mvc_view_id);
-}
-
 static unsigned int s5p_mfc_get_pic_type_top_v6(struct s5p_mfc_ctx *ctx)
 {
 	return s5p_mfc_read_info_v6(ctx,
@@ -2282,20 +2191,11 @@
 		s5p_mfc_release_dev_context_buffer_v6,
 	.dec_calc_dpb_size = s5p_mfc_dec_calc_dpb_size_v6,
 	.enc_calc_src_size = s5p_mfc_enc_calc_src_size_v6,
-	.set_dec_stream_buffer = s5p_mfc_set_dec_stream_buffer_v6,
-	.set_dec_frame_buffer = s5p_mfc_set_dec_frame_buffer_v6,
 	.set_enc_stream_buffer = s5p_mfc_set_enc_stream_buffer_v6,
 	.set_enc_frame_buffer = s5p_mfc_set_enc_frame_buffer_v6,
 	.get_enc_frame_buffer = s5p_mfc_get_enc_frame_buffer_v6,
-	.set_enc_ref_buffer = s5p_mfc_set_enc_ref_buffer_v6,
-	.init_decode = s5p_mfc_init_decode_v6,
-	.init_encode = s5p_mfc_init_encode_v6,
-	.encode_one_frame = s5p_mfc_encode_one_frame_v6,
 	.try_run = s5p_mfc_try_run_v6,
-	.cleanup_queue = s5p_mfc_cleanup_queue_v6,
 	.clear_int_flags = s5p_mfc_clear_int_flags_v6,
-	.write_info = s5p_mfc_write_info_v6,
-	.read_info = s5p_mfc_read_info_v6,
 	.get_dspl_y_adr = s5p_mfc_get_dspl_y_adr_v6,
 	.get_dec_y_adr = s5p_mfc_get_dec_y_adr_v6,
 	.get_dspl_status = s5p_mfc_get_dspl_status_v6,
@@ -2306,7 +2206,6 @@
 	.get_int_reason = s5p_mfc_get_int_reason_v6,
 	.get_int_err = s5p_mfc_get_int_err_v6,
 	.err_dec = s5p_mfc_err_dec_v6,
-	.err_dspl = s5p_mfc_err_dspl_v6,
 	.get_img_width = s5p_mfc_get_img_width_v6,
 	.get_img_height = s5p_mfc_get_img_height_v6,
 	.get_dpb_count = s5p_mfc_get_dpb_count_v6,
@@ -2315,10 +2214,6 @@
 	.get_enc_strm_size = s5p_mfc_get_enc_strm_size_v6,
 	.get_enc_slice_type = s5p_mfc_get_enc_slice_type_v6,
 	.get_enc_dpb_count = s5p_mfc_get_enc_dpb_count_v6,
-	.get_enc_pic_count = s5p_mfc_get_enc_pic_count_v6,
-	.get_sei_avail_status = s5p_mfc_get_sei_avail_status_v6,
-	.get_mvc_num_views = s5p_mfc_get_mvc_num_views_v6,
-	.get_mvc_view_id = s5p_mfc_get_mvc_view_id_v6,
 	.get_pic_type_top = s5p_mfc_get_pic_type_top_v6,
 	.get_pic_type_bot = s5p_mfc_get_pic_type_bot_v6,
 	.get_crop_info_h = s5p_mfc_get_crop_info_h_v6,
diff --git a/drivers/media/platform/s5p-tv/hdmi_drv.c b/drivers/media/platform/s5p-tv/hdmi_drv.c
index 7994075..e71b13e 100644
--- a/drivers/media/platform/s5p-tv/hdmi_drv.c
+++ b/drivers/media/platform/s5p-tv/hdmi_drv.c
@@ -33,7 +33,7 @@
 #include <linux/regulator/consumer.h>
 #include <linux/v4l2-dv-timings.h>
 
-#include <media/s5p_hdmi.h>
+#include <linux/platform_data/media/s5p_hdmi.h>
 #include <media/v4l2-common.h>
 #include <media/v4l2-dev.h>
 #include <media/v4l2-device.h>
@@ -627,7 +627,7 @@
 
 	for (i = 0; i < ARRAY_SIZE(hdmi_timings); i++)
 		if (v4l2_match_dv_timings(&hdmi_timings[i].dv_timings,
-					timings, 0))
+					timings, 0, false))
 			break;
 	if (i == ARRAY_SIZE(hdmi_timings)) {
 		dev_err(dev, "timings not supported\n");
diff --git a/drivers/media/platform/s5p-tv/mixer_video.c b/drivers/media/platform/s5p-tv/mixer_video.c
index dc1c679..d9e7f03 100644
--- a/drivers/media/platform/s5p-tv/mixer_video.c
+++ b/drivers/media/platform/s5p-tv/mixer_video.c
@@ -881,7 +881,7 @@
 	.unlocked_ioctl = video_ioctl2,
 };
 
-static int queue_setup(struct vb2_queue *vq, const void *parg,
+static int queue_setup(struct vb2_queue *vq,
 	unsigned int *nbuffers, unsigned int *nplanes, unsigned int sizes[],
 	void *alloc_ctxs[])
 {
diff --git a/drivers/media/platform/s5p-tv/sii9234_drv.c b/drivers/media/platform/s5p-tv/sii9234_drv.c
index 8d17131..0a97f9a 100644
--- a/drivers/media/platform/s5p-tv/sii9234_drv.c
+++ b/drivers/media/platform/s5p-tv/sii9234_drv.c
@@ -23,7 +23,7 @@
 #include <linux/regulator/machine.h>
 #include <linux/slab.h>
 
-#include <media/sii9234.h>
+#include <linux/platform_data/media/sii9234.h>
 #include <media/v4l2-subdev.h>
 
 MODULE_AUTHOR("Tomasz Stanislawski <t.stanislaws@samsung.com>");
diff --git a/drivers/media/platform/sh_veu.c b/drivers/media/platform/sh_veu.c
index d6ab33e..82b5d69 100644
--- a/drivers/media/platform/sh_veu.c
+++ b/drivers/media/platform/sh_veu.c
@@ -865,32 +865,14 @@
 		/* ========== Queue operations ========== */
 
 static int sh_veu_queue_setup(struct vb2_queue *vq,
-			      const void *parg,
 			      unsigned int *nbuffers, unsigned int *nplanes,
 			      unsigned int sizes[], void *alloc_ctxs[])
 {
-	const struct v4l2_format *f = parg;
 	struct sh_veu_dev *veu = vb2_get_drv_priv(vq);
-	struct sh_veu_vfmt *vfmt;
-	unsigned int size, count = *nbuffers;
-
-	if (f) {
-		const struct v4l2_pix_format *pix = &f->fmt.pix;
-		const struct sh_veu_format *fmt = sh_veu_find_fmt(f);
-		struct v4l2_format ftmp = *f;
-
-		if (fmt->fourcc != pix->pixelformat)
-			return -EINVAL;
-		sh_veu_try_fmt(&ftmp, fmt);
-		if (ftmp.fmt.pix.width != pix->width ||
-		    ftmp.fmt.pix.height != pix->height)
-			return -EINVAL;
-		size = pix->bytesperline ? pix->bytesperline * pix->height * fmt->depth / fmt->ydepth :
-			pix->width * pix->height * fmt->depth / fmt->ydepth;
-	} else {
-		vfmt = sh_veu_get_vfmt(veu, vq->type);
-		size = vfmt->bytesperline * vfmt->frame.height * vfmt->fmt->depth / vfmt->fmt->ydepth;
-	}
+	struct sh_veu_vfmt *vfmt = sh_veu_get_vfmt(veu, vq->type);
+	unsigned int count = *nbuffers;
+	unsigned int size = vfmt->bytesperline * vfmt->frame.height *
+		vfmt->fmt->depth / vfmt->fmt->ydepth;
 
 	if (count < 2)
 		*nbuffers = count = 2;
@@ -900,6 +882,11 @@
 		*nbuffers = count;
 	}
 
+	if (*nplanes) {
+		alloc_ctxs[0] = veu->alloc_ctx;
+		return sizes[0] < size ? -EINVAL : 0;
+	}
+
 	*nplanes = 1;
 	sizes[0] = size;
 	alloc_ctxs[0] = veu->alloc_ctx;
@@ -1107,7 +1094,7 @@
 	if (!src || !dst)
 		return IRQ_NONE;
 
-	dst->timestamp = src->timestamp;
+	dst->vb2_buf.timestamp = src->vb2_buf.timestamp;
 	dst->flags &= ~V4L2_BUF_FLAG_TSTAMP_SRC_MASK;
 	dst->flags |=
 		src->flags & V4L2_BUF_FLAG_TSTAMP_SRC_MASK;
diff --git a/drivers/media/platform/sh_vou.c b/drivers/media/platform/sh_vou.c
index 2231f89..1157404 100644
--- a/drivers/media/platform/sh_vou.c
+++ b/drivers/media/platform/sh_vou.c
@@ -22,7 +22,7 @@
 #include <linux/videodev2.h>
 #include <linux/module.h>
 
-#include <media/sh_vou.h>
+#include <media/drv-intf/sh_vou.h>
 #include <media/v4l2-common.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-ioctl.h>
@@ -243,22 +243,21 @@
 }
 
 /* Locking: caller holds fop_lock mutex */
-static int sh_vou_queue_setup(struct vb2_queue *vq, const void *parg,
+static int sh_vou_queue_setup(struct vb2_queue *vq,
 		       unsigned int *nbuffers, unsigned int *nplanes,
 		       unsigned int sizes[], void *alloc_ctxs[])
 {
-	const struct v4l2_format *fmt = parg;
 	struct sh_vou_device *vou_dev = vb2_get_drv_priv(vq);
 	struct v4l2_pix_format *pix = &vou_dev->pix;
 	int bytes_per_line = vou_fmt[vou_dev->pix_idx].bpp * pix->width / 8;
 
 	dev_dbg(vou_dev->v4l2_dev.dev, "%s()\n", __func__);
 
-	if (fmt && fmt->fmt.pix.sizeimage < pix->height * bytes_per_line)
-		return -EINVAL;
-	*nplanes = 1;
-	sizes[0] = fmt ? fmt->fmt.pix.sizeimage : pix->height * bytes_per_line;
 	alloc_ctxs[0] = vou_dev->alloc_ctx;
+	if (*nplanes)
+		return sizes[0] < pix->height * bytes_per_line ? -EINVAL : 0;
+	*nplanes = 1;
+	sizes[0] = pix->height * bytes_per_line;
 	return 0;
 }
 
@@ -1071,7 +1070,7 @@
 
 	list_del(&vb->list);
 
-	v4l2_get_timestamp(&vb->vb.timestamp);
+	vb->vb.vb2_buf.timestamp = ktime_get_ns();
 	vb->vb.sequence = vou_dev->sequence++;
 	vb->vb.field = V4L2_FIELD_INTERLACED;
 	vb2_buffer_done(&vb->vb.vb2_buf, VB2_BUF_STATE_DONE);
diff --git a/drivers/media/platform/soc_camera/atmel-isi.c b/drivers/media/platform/soc_camera/atmel-isi.c
index 454f68f..c398b28 100644
--- a/drivers/media/platform/soc_camera/atmel-isi.c
+++ b/drivers/media/platform/soc_camera/atmel-isi.c
@@ -24,7 +24,7 @@
 #include <linux/slab.h>
 
 #include <media/soc_camera.h>
-#include <media/soc_mediabus.h>
+#include <media/drv-intf/soc_mediabus.h>
 #include <media/v4l2-of.h>
 #include <media/videobuf2-dma-contig.h>
 
@@ -79,6 +79,7 @@
 	dma_addr_t			fb_descriptors_phys;
 	struct				list_head dma_desc_head;
 	struct isi_dma_desc		dma_desc[MAX_BUFFER_NUM];
+	bool				enable_preview_path;
 
 	struct completion		complete;
 	/* ISI peripherial clock */
@@ -103,13 +104,55 @@
 	return readl(isi->regs + reg);
 }
 
-static void configure_geometry(struct atmel_isi *isi, u32 width,
-			u32 height, u32 code)
+static u32 setup_cfg2_yuv_swap(struct atmel_isi *isi,
+		const struct soc_camera_format_xlate *xlate)
 {
-	u32 cfg2;
+	if (xlate->host_fmt->fourcc == V4L2_PIX_FMT_YUYV) {
+		/* all convert to YUYV */
+		switch (xlate->code) {
+		case MEDIA_BUS_FMT_VYUY8_2X8:
+			return ISI_CFG2_YCC_SWAP_MODE_3;
+		case MEDIA_BUS_FMT_UYVY8_2X8:
+			return ISI_CFG2_YCC_SWAP_MODE_2;
+		case MEDIA_BUS_FMT_YVYU8_2X8:
+			return ISI_CFG2_YCC_SWAP_MODE_1;
+		}
+	} else if (xlate->host_fmt->fourcc == V4L2_PIX_FMT_RGB565) {
+		/*
+		 * Preview path is enabled, it will convert UYVY to RGB format.
+		 * But if sensor output format is not UYVY, we need to set
+		 * YCC_SWAP_MODE to convert it as UYVY.
+		 */
+		switch (xlate->code) {
+		case MEDIA_BUS_FMT_VYUY8_2X8:
+			return ISI_CFG2_YCC_SWAP_MODE_1;
+		case MEDIA_BUS_FMT_YUYV8_2X8:
+			return ISI_CFG2_YCC_SWAP_MODE_2;
+		case MEDIA_BUS_FMT_YVYU8_2X8:
+			return ISI_CFG2_YCC_SWAP_MODE_3;
+		}
+	}
+
+	/*
+	 * By default, no swap for the codec path of Atmel ISI. So codec
+	 * output is same as sensor's output.
+	 * For instance, if sensor's output is YUYV, then codec outputs YUYV.
+	 * And if sensor's output is UYVY, then codec outputs UYVY.
+	 */
+	return ISI_CFG2_YCC_SWAP_DEFAULT;
+}
+
+static void configure_geometry(struct atmel_isi *isi, u32 width,
+		u32 height, const struct soc_camera_format_xlate *xlate)
+{
+	u32 cfg2, psize;
+	u32 fourcc = xlate->host_fmt->fourcc;
+
+	isi->enable_preview_path = fourcc == V4L2_PIX_FMT_RGB565 ||
+				   fourcc == V4L2_PIX_FMT_RGB32;
 
 	/* According to sensor's output format to set cfg2 */
-	switch (code) {
+	switch (xlate->code) {
 	default:
 	/* Grey */
 	case MEDIA_BUS_FMT_Y8_1X8:
@@ -117,16 +160,11 @@
 		break;
 	/* YUV */
 	case MEDIA_BUS_FMT_VYUY8_2X8:
-		cfg2 = ISI_CFG2_YCC_SWAP_MODE_3 | ISI_CFG2_COL_SPACE_YCbCr;
-		break;
 	case MEDIA_BUS_FMT_UYVY8_2X8:
-		cfg2 = ISI_CFG2_YCC_SWAP_MODE_2 | ISI_CFG2_COL_SPACE_YCbCr;
-		break;
 	case MEDIA_BUS_FMT_YVYU8_2X8:
-		cfg2 = ISI_CFG2_YCC_SWAP_MODE_1 | ISI_CFG2_COL_SPACE_YCbCr;
-		break;
 	case MEDIA_BUS_FMT_YUYV8_2X8:
-		cfg2 = ISI_CFG2_YCC_SWAP_DEFAULT | ISI_CFG2_COL_SPACE_YCbCr;
+		cfg2 = ISI_CFG2_COL_SPACE_YCbCr |
+				setup_cfg2_yuv_swap(isi, xlate);
 		break;
 	/* RGB, TODO */
 	}
@@ -139,6 +177,16 @@
 	cfg2 |= ((height - 1) << ISI_CFG2_IM_VSIZE_OFFSET)
 			& ISI_CFG2_IM_VSIZE_MASK;
 	isi_writel(isi, ISI_CFG2, cfg2);
+
+	/* No down sampling, preview size equal to sensor output size */
+	psize = ((width - 1) << ISI_PSIZE_PREV_HSIZE_OFFSET) &
+		ISI_PSIZE_PREV_HSIZE_MASK;
+	psize |= ((height - 1) << ISI_PSIZE_PREV_VSIZE_OFFSET) &
+		ISI_PSIZE_PREV_VSIZE_MASK;
+	isi_writel(isi, ISI_PSIZE, psize);
+	isi_writel(isi, ISI_PDECF, ISI_PDECF_NO_SAMPLING);
+
+	return;
 }
 
 static bool is_supported(struct soc_camera_device *icd,
@@ -151,8 +199,9 @@
 	case V4L2_PIX_FMT_UYVY:
 	case V4L2_PIX_FMT_YVYU:
 	case V4L2_PIX_FMT_VYUY:
+	/* RGB */
+	case V4L2_PIX_FMT_RGB565:
 		return true;
-	/* RGB, TODO */
 	default:
 		return false;
 	}
@@ -165,7 +214,7 @@
 		struct frame_buffer *buf = isi->active;
 
 		list_del_init(&buf->list);
-		v4l2_get_timestamp(&vbuf->timestamp);
+		vbuf->vb2_buf.timestamp = ktime_get_ns();
 		vbuf->sequence = isi->sequence++;
 		vb2_buffer_done(&vbuf->vb2_buf, VB2_BUF_STATE_DONE);
 	}
@@ -176,11 +225,19 @@
 		/* start next dma frame. */
 		isi->active = list_entry(isi->video_buffer_list.next,
 					struct frame_buffer, list);
-		isi_writel(isi, ISI_DMA_C_DSCR,
-			(u32)isi->active->p_dma_desc->fbd_phys);
-		isi_writel(isi, ISI_DMA_C_CTRL,
-			ISI_DMA_CTRL_FETCH | ISI_DMA_CTRL_DONE);
-		isi_writel(isi, ISI_DMA_CHER, ISI_DMA_CHSR_C_CH);
+		if (!isi->enable_preview_path) {
+			isi_writel(isi, ISI_DMA_C_DSCR,
+				(u32)isi->active->p_dma_desc->fbd_phys);
+			isi_writel(isi, ISI_DMA_C_CTRL,
+				ISI_DMA_CTRL_FETCH | ISI_DMA_CTRL_DONE);
+			isi_writel(isi, ISI_DMA_CHER, ISI_DMA_CHSR_C_CH);
+		} else {
+			isi_writel(isi, ISI_DMA_P_DSCR,
+				(u32)isi->active->p_dma_desc->fbd_phys);
+			isi_writel(isi, ISI_DMA_P_CTRL,
+				ISI_DMA_CTRL_FETCH | ISI_DMA_CTRL_DONE);
+			isi_writel(isi, ISI_DMA_CHER, ISI_DMA_CHSR_P_CH);
+		}
 	}
 	return IRQ_HANDLED;
 }
@@ -207,7 +264,8 @@
 		isi_writel(isi, ISI_INTDIS, ISI_CTRL_DIS);
 		ret = IRQ_HANDLED;
 	} else {
-		if (likely(pending & ISI_SR_CXFR_DONE))
+		if (likely(pending & ISI_SR_CXFR_DONE) ||
+				likely(pending & ISI_SR_PXFR_DONE))
 			ret = atmel_isi_handle_streaming(isi);
 	}
 
@@ -245,7 +303,7 @@
 /* ------------------------------------------------------------------
 	Videobuf operations
    ------------------------------------------------------------------*/
-static int queue_setup(struct vb2_queue *vq, const void *parg,
+static int queue_setup(struct vb2_queue *vq,
 				unsigned int *nbuffers, unsigned int *nplanes,
 				unsigned int sizes[], void *alloc_ctxs[])
 {
@@ -352,21 +410,35 @@
 			ISI_SR_CXFR_DONE | ISI_SR_PXFR_DONE);
 
 	/* Check if already in a frame */
-	if (isi_readl(isi, ISI_STATUS) & ISI_CTRL_CDC) {
-		dev_err(isi->soc_host.icd->parent, "Already in frame handling.\n");
-		return;
-	}
+	if (!isi->enable_preview_path) {
+		if (isi_readl(isi, ISI_STATUS) & ISI_CTRL_CDC) {
+			dev_err(isi->soc_host.icd->parent, "Already in frame handling.\n");
+			return;
+		}
 
-	isi_writel(isi, ISI_DMA_C_DSCR, (u32)buffer->p_dma_desc->fbd_phys);
-	isi_writel(isi, ISI_DMA_C_CTRL, ISI_DMA_CTRL_FETCH | ISI_DMA_CTRL_DONE);
-	isi_writel(isi, ISI_DMA_CHER, ISI_DMA_CHSR_C_CH);
+		isi_writel(isi, ISI_DMA_C_DSCR,
+				(u32)buffer->p_dma_desc->fbd_phys);
+		isi_writel(isi, ISI_DMA_C_CTRL,
+				ISI_DMA_CTRL_FETCH | ISI_DMA_CTRL_DONE);
+		isi_writel(isi, ISI_DMA_CHER, ISI_DMA_CHSR_C_CH);
+	} else {
+		isi_writel(isi, ISI_DMA_P_DSCR,
+				(u32)buffer->p_dma_desc->fbd_phys);
+		isi_writel(isi, ISI_DMA_P_CTRL,
+				ISI_DMA_CTRL_FETCH | ISI_DMA_CTRL_DONE);
+		isi_writel(isi, ISI_DMA_CHER, ISI_DMA_CHSR_P_CH);
+	}
 
 	cfg1 &= ~ISI_CFG1_FRATE_DIV_MASK;
 	/* Enable linked list */
 	cfg1 |= isi->pdata.frate | ISI_CFG1_DISCR;
 
-	/* Enable codec path and ISI */
-	ctrl = ISI_CTRL_CDC | ISI_CTRL_EN;
+	/* Enable ISI */
+	ctrl = ISI_CTRL_EN;
+
+	if (!isi->enable_preview_path)
+		ctrl |= ISI_CTRL_CDC;
+
 	isi_writel(isi, ISI_CTRL, ctrl);
 	isi_writel(isi, ISI_CFG1, cfg1);
 }
@@ -411,7 +483,7 @@
 	isi_writel(isi, ISI_INTDIS, (u32)~0UL);
 
 	configure_geometry(isi, icd->user_width, icd->user_height,
-				icd->current_fmt->code);
+				icd->current_fmt);
 
 	spin_lock_irq(&isi->lock);
 	/* Clear any pending interrupt */
@@ -443,15 +515,17 @@
 	}
 	spin_unlock_irq(&isi->lock);
 
-	timeout = jiffies + FRAME_INTERVAL_MILLI_SEC * HZ;
-	/* Wait until the end of the current frame. */
-	while ((isi_readl(isi, ISI_STATUS) & ISI_CTRL_CDC) &&
-			time_before(jiffies, timeout))
-		msleep(1);
+	if (!isi->enable_preview_path) {
+		timeout = jiffies + FRAME_INTERVAL_MILLI_SEC * HZ;
+		/* Wait until the end of the current frame. */
+		while ((isi_readl(isi, ISI_STATUS) & ISI_CTRL_CDC) &&
+				time_before(jiffies, timeout))
+			msleep(1);
 
-	if (time_after(jiffies, timeout))
-		dev_err(icd->parent,
-			"Timeout waiting for finishing codec request\n");
+		if (time_after(jiffies, timeout))
+			dev_err(icd->parent,
+				"Timeout waiting for finishing codec request\n");
+	}
 
 	/* Disable interrupts */
 	isi_writel(isi, ISI_INTDIS,
@@ -617,6 +691,14 @@
 		.order			= SOC_MBUS_ORDER_LE,
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
+	{
+		.fourcc			= V4L2_PIX_FMT_RGB565,
+		.name			= "RGB565",
+		.bits_per_sample	= 8,
+		.packing		= SOC_MBUS_PACKING_2X8_PADHI,
+		.order			= SOC_MBUS_ORDER_LE,
+		.layout			= SOC_MBUS_LAYOUT_PACKED,
+	},
 };
 
 /* This will be corrected as we get more formats */
@@ -673,7 +755,7 @@
 				  struct soc_camera_format_xlate *xlate)
 {
 	struct v4l2_subdev *sd = soc_camera_to_subdev(icd);
-	int formats = 0, ret;
+	int formats = 0, ret, i, n;
 	/* sensor format */
 	struct v4l2_subdev_mbus_code_enum code = {
 		.which = V4L2_SUBDEV_FORMAT_ACTIVE,
@@ -707,11 +789,11 @@
 	case MEDIA_BUS_FMT_VYUY8_2X8:
 	case MEDIA_BUS_FMT_YUYV8_2X8:
 	case MEDIA_BUS_FMT_YVYU8_2X8:
-		formats++;
-		if (xlate) {
-			xlate->host_fmt	= &isi_camera_formats[0];
+		n = ARRAY_SIZE(isi_camera_formats);
+		formats += n;
+		for (i = 0; xlate && i < n; i++, xlate++) {
+			xlate->host_fmt	= &isi_camera_formats[i];
 			xlate->code	= code.code;
-			xlate++;
 			dev_dbg(icd->parent, "Providing format %s using code %d\n",
 				isi_camera_formats[0].name, code.code);
 		}
diff --git a/drivers/media/platform/soc_camera/atmel-isi.h b/drivers/media/platform/soc_camera/atmel-isi.h
index 5acc771..0acb32a 100644
--- a/drivers/media/platform/soc_camera/atmel-isi.h
+++ b/drivers/media/platform/soc_camera/atmel-isi.h
@@ -79,6 +79,16 @@
 #define ISI_CFG2_IM_VSIZE_MASK		(0x7FF << ISI_CFG2_IM_VSIZE_OFFSET)
 #define ISI_CFG2_IM_HSIZE_MASK		(0x7FF << ISI_CFG2_IM_HSIZE_OFFSET)
 
+/* Bitfields in PSIZE */
+#define ISI_PSIZE_PREV_VSIZE_OFFSET	0
+#define ISI_PSIZE_PREV_HSIZE_OFFSET	16
+#define ISI_PSIZE_PREV_VSIZE_MASK	(0x3FF << ISI_PSIZE_PREV_VSIZE_OFFSET)
+#define ISI_PSIZE_PREV_HSIZE_MASK	(0x3FF << ISI_PSIZE_PREV_HSIZE_OFFSET)
+
+/* Bitfields in PDECF */
+#define ISI_PDECF_DEC_FACTOR_MASK	(0xFF << 0)
+#define	ISI_PDECF_NO_SAMPLING		(16)
+
 /* Bitfields in CTRL */
 /* Also using in SR(ISI_V2) */
 #define ISI_CTRL_EN				(1 << 0)
diff --git a/drivers/media/platform/soc_camera/mx2_camera.c b/drivers/media/platform/soc_camera/mx2_camera.c
index 1f28d21..48dd5b7 100644
--- a/drivers/media/platform/soc_camera/mx2_camera.c
+++ b/drivers/media/platform/soc_camera/mx2_camera.c
@@ -35,11 +35,11 @@
 #include <media/videobuf2-v4l2.h>
 #include <media/videobuf2-dma-contig.h>
 #include <media/soc_camera.h>
-#include <media/soc_mediabus.h>
+#include <media/drv-intf/soc_mediabus.h>
 
 #include <linux/videodev2.h>
 
-#include <linux/platform_data/camera-mx2.h>
+#include <linux/platform_data/media/camera-mx2.h>
 
 #include <asm/dma.h>
 
@@ -469,21 +469,15 @@
  *  Videobuf operations
  */
 static int mx2_videobuf_setup(struct vb2_queue *vq,
-			const void *parg,
 			unsigned int *count, unsigned int *num_planes,
 			unsigned int sizes[], void *alloc_ctxs[])
 {
-	const struct v4l2_format *fmt = parg;
 	struct soc_camera_device *icd = soc_camera_from_vb2q(vq);
 	struct soc_camera_host *ici = to_soc_camera_host(icd->parent);
 	struct mx2_camera_dev *pcdev = ici->priv;
 
 	dev_dbg(icd->parent, "count=%d, size=%d\n", *count, sizes[0]);
 
-	/* TODO: support for VIDIOC_CREATE_BUFS not ready */
-	if (fmt != NULL)
-		return -ENOTTY;
-
 	alloc_ctxs[0] = pcdev->alloc_ctx;
 
 	sizes[0] = icd->sizeimage;
@@ -1351,7 +1345,7 @@
 				vb2_get_plane_payload(vb, 0));
 
 		list_del_init(&buf->internal.queue);
-		v4l2_get_timestamp(&vbuf->timestamp);
+		vb->timestamp = ktime_get_ns();
 		vbuf->sequence = pcdev->frame_count;
 		if (err)
 			vb2_buffer_done(vb, VB2_BUF_STATE_ERROR);
diff --git a/drivers/media/platform/soc_camera/mx3_camera.c b/drivers/media/platform/soc_camera/mx3_camera.c
index 49c3a25..169ed11 100644
--- a/drivers/media/platform/soc_camera/mx3_camera.c
+++ b/drivers/media/platform/soc_camera/mx3_camera.c
@@ -23,9 +23,9 @@
 #include <media/v4l2-dev.h>
 #include <media/videobuf2-dma-contig.h>
 #include <media/soc_camera.h>
-#include <media/soc_mediabus.h>
+#include <media/drv-intf/soc_mediabus.h>
 
-#include <linux/platform_data/camera-mx3.h>
+#include <linux/platform_data/media/camera-mx3.h>
 #include <linux/platform_data/dma-imx.h>
 
 #define MX3_CAM_DRV_NAME "mx3-camera"
@@ -155,7 +155,7 @@
 		struct mx3_camera_buffer *buf = to_mx3_vb(vb);
 
 		list_del_init(&buf->queue);
-		v4l2_get_timestamp(&vb->timestamp);
+		vb->vb2_buf.timestamp = ktime_get_ns();
 		vb->field = mx3_cam->field;
 		vb->sequence = mx3_cam->sequence++;
 		vb2_buffer_done(&vb->vb2_buf, VB2_BUF_STATE_DONE);
@@ -185,11 +185,9 @@
  * Calculate the __buffer__ (not data) size and number of buffers.
  */
 static int mx3_videobuf_setup(struct vb2_queue *vq,
-			const void *parg,
 			unsigned int *count, unsigned int *num_planes,
 			unsigned int sizes[], void *alloc_ctxs[])
 {
-	const struct v4l2_format *fmt = parg;
 	struct soc_camera_device *icd = soc_camera_from_vb2q(vq);
 	struct soc_camera_host *ici = to_soc_camera_host(icd->parent);
 	struct mx3_camera_dev *mx3_cam = ici->priv;
@@ -197,33 +195,6 @@
 	if (!mx3_cam->idmac_channel[0])
 		return -EINVAL;
 
-	if (fmt) {
-		const struct soc_camera_format_xlate *xlate = soc_camera_xlate_by_fourcc(icd,
-								fmt->fmt.pix.pixelformat);
-		unsigned int bytes_per_line;
-		int ret;
-
-		if (!xlate)
-			return -EINVAL;
-
-		ret = soc_mbus_bytes_per_line(fmt->fmt.pix.width,
-					      xlate->host_fmt);
-		if (ret < 0)
-			return ret;
-
-		bytes_per_line = max_t(u32, fmt->fmt.pix.bytesperline, ret);
-
-		ret = soc_mbus_image_size(xlate->host_fmt, bytes_per_line,
-					  fmt->fmt.pix.height);
-		if (ret < 0)
-			return ret;
-
-		sizes[0] = max_t(u32, fmt->fmt.pix.sizeimage, ret);
-	} else {
-		/* Called from VIDIOC_REQBUFS or in compatibility mode */
-		sizes[0] = icd->sizeimage;
-	}
-
 	alloc_ctxs[0] = mx3_cam->alloc_ctx;
 
 	if (!vq->num_buffers)
@@ -232,9 +203,14 @@
 	if (!*count)
 		*count = 2;
 
+	/* Called from VIDIOC_REQBUFS or in compatibility mode */
+	if (!*num_planes)
+		sizes[0] = icd->sizeimage;
+	else if (sizes[0] < icd->sizeimage)
+		return -EINVAL;
+
 	/* If *num_planes != 0, we have already verified *count. */
-	if (!*num_planes &&
-	    sizes[0] * *count + mx3_cam->buf_total > MAX_VIDEO_MEM * 1024 * 1024)
+	if (sizes[0] * *count + mx3_cam->buf_total > MAX_VIDEO_MEM * 1024 * 1024)
 		*count = (MAX_VIDEO_MEM * 1024 * 1024 - mx3_cam->buf_total) /
 			sizes[0];
 
diff --git a/drivers/media/platform/soc_camera/omap1_camera.c b/drivers/media/platform/soc_camera/omap1_camera.c
index ba8dcd1..bd721e3 100644
--- a/drivers/media/platform/soc_camera/omap1_camera.c
+++ b/drivers/media/platform/soc_camera/omap1_camera.c
@@ -28,9 +28,9 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 
-#include <media/omap1_camera.h>
+#include <linux/platform_data/media/omap1_camera.h>
 #include <media/soc_camera.h>
-#include <media/soc_mediabus.h>
+#include <media/drv-intf/soc_mediabus.h>
 #include <media/videobuf-dma-contig.h>
 #include <media/videobuf-dma-sg.h>
 
diff --git a/drivers/media/platform/soc_camera/pxa_camera.c b/drivers/media/platform/soc_camera/pxa_camera.c
index fcb942d..415f3bd 100644
--- a/drivers/media/platform/soc_camera/pxa_camera.c
+++ b/drivers/media/platform/soc_camera/pxa_camera.c
@@ -33,13 +33,13 @@
 #include <media/v4l2-dev.h>
 #include <media/videobuf-dma-sg.h>
 #include <media/soc_camera.h>
-#include <media/soc_mediabus.h>
+#include <media/drv-intf/soc_mediabus.h>
 #include <media/v4l2-of.h>
 
 #include <linux/videodev2.h>
 
 #include <mach/dma.h>
-#include <linux/platform_data/camera-pxa.h>
+#include <linux/platform_data/media/camera-pxa.h>
 
 #define PXA_CAM_VERSION "0.0.6"
 #define PXA_CAM_DRV_NAME "pxa27x-camera"
diff --git a/drivers/media/platform/soc_camera/rcar_vin.c b/drivers/media/platform/soc_camera/rcar_vin.c
index efe57b2..b7fd695 100644
--- a/drivers/media/platform/soc_camera/rcar_vin.c
+++ b/drivers/media/platform/soc_camera/rcar_vin.c
@@ -21,14 +21,13 @@
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
-#include <linux/platform_data/camera-rcar.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/slab.h>
 #include <linux/videodev2.h>
 
 #include <media/soc_camera.h>
-#include <media/soc_mediabus.h>
+#include <media/drv-intf/soc_mediabus.h>
 #include <media/v4l2-common.h>
 #include <media/v4l2-dev.h>
 #include <media/v4l2-device.h>
@@ -138,6 +137,11 @@
 
 #define TIMEOUT_MS		100
 
+#define RCAR_VIN_HSYNC_ACTIVE_LOW	(1 << 0)
+#define RCAR_VIN_VSYNC_ACTIVE_LOW	(1 << 1)
+#define RCAR_VIN_BT601			(1 << 2)
+#define RCAR_VIN_BT656			(1 << 3)
+
 enum chip_id {
 	RCAR_GEN2,
 	RCAR_H1,
@@ -527,46 +531,14 @@
  * required
  */
 static int rcar_vin_videobuf_setup(struct vb2_queue *vq,
-				   const void *parg,
 				   unsigned int *count,
 				   unsigned int *num_planes,
 				   unsigned int sizes[], void *alloc_ctxs[])
 {
-	const struct v4l2_format *fmt = parg;
 	struct soc_camera_device *icd = soc_camera_from_vb2q(vq);
 	struct soc_camera_host *ici = to_soc_camera_host(icd->parent);
 	struct rcar_vin_priv *priv = ici->priv;
 
-	if (fmt) {
-		const struct soc_camera_format_xlate *xlate;
-		unsigned int bytes_per_line;
-		int ret;
-
-		if (fmt->fmt.pix.sizeimage < icd->sizeimage)
-			return -EINVAL;
-
-		xlate = soc_camera_xlate_by_fourcc(icd,
-						   fmt->fmt.pix.pixelformat);
-		if (!xlate)
-			return -EINVAL;
-		ret = soc_mbus_bytes_per_line(fmt->fmt.pix.width,
-					      xlate->host_fmt);
-		if (ret < 0)
-			return ret;
-
-		bytes_per_line = max_t(u32, fmt->fmt.pix.bytesperline, ret);
-
-		ret = soc_mbus_image_size(xlate->host_fmt, bytes_per_line,
-					  fmt->fmt.pix.height);
-		if (ret < 0)
-			return ret;
-
-		sizes[0] = max_t(u32, fmt->fmt.pix.sizeimage, ret);
-	} else {
-		/* Called from VIDIOC_REQBUFS or in compatibility mode */
-		sizes[0] = icd->sizeimage;
-	}
-
 	alloc_ctxs[0] = priv->alloc_ctx;
 
 	if (!vq->num_buffers)
@@ -576,14 +548,18 @@
 		*count = 2;
 	priv->vb_count = *count;
 
-	*num_planes = 1;
-
 	/* Number of hardware slots */
 	if (is_continuous_transfer(priv))
 		priv->nr_hw_slots = MAX_BUFFER_NUM;
 	else
 		priv->nr_hw_slots = 1;
 
+	if (*num_planes)
+		return sizes[0] < icd->sizeimage ? -EINVAL : 0;
+
+	sizes[0] = icd->sizeimage;
+	*num_planes = 1;
+
 	dev_dbg(icd->parent, "count=%d, size=%u\n", *count, sizes[0]);
 
 	return 0;
@@ -912,7 +888,7 @@
 
 		priv->queue_buf[slot]->field = priv->field;
 		priv->queue_buf[slot]->sequence = priv->sequence++;
-		v4l2_get_timestamp(&priv->queue_buf[slot]->timestamp);
+		priv->queue_buf[slot]->vb2_buf.timestamp = ktime_get_ns();
 		vb2_buffer_done(&priv->queue_buf[slot]->vb2_buf,
 				VB2_BUF_STATE_DONE);
 		priv->queue_buf[slot] = NULL;
@@ -1853,64 +1829,44 @@
 MODULE_DEVICE_TABLE(of, rcar_vin_of_table);
 #endif
 
-static struct platform_device_id rcar_vin_id_table[] = {
-	{ "r8a7779-vin",  RCAR_H1 },
-	{ "r8a7778-vin",  RCAR_M1 },
-	{ "uPD35004-vin", RCAR_E1 },
-	{},
-};
-MODULE_DEVICE_TABLE(platform, rcar_vin_id_table);
-
 static int rcar_vin_probe(struct platform_device *pdev)
 {
 	const struct of_device_id *match = NULL;
 	struct rcar_vin_priv *priv;
+	struct v4l2_of_endpoint ep;
+	struct device_node *np;
 	struct resource *mem;
-	struct rcar_vin_platform_data *pdata;
 	unsigned int pdata_flags;
 	int irq, ret;
 
-	if (pdev->dev.of_node) {
-		struct v4l2_of_endpoint ep;
-		struct device_node *np;
+	match = of_match_device(of_match_ptr(rcar_vin_of_table), &pdev->dev);
 
-		match = of_match_device(of_match_ptr(rcar_vin_of_table),
-					&pdev->dev);
-
-		np = of_graph_get_next_endpoint(pdev->dev.of_node, NULL);
-		if (!np) {
-			dev_err(&pdev->dev, "could not find endpoint\n");
-			return -EINVAL;
-		}
-
-		ret = v4l2_of_parse_endpoint(np, &ep);
-		if (ret) {
-			dev_err(&pdev->dev, "could not parse endpoint\n");
-			return ret;
-		}
-
-		if (ep.bus_type == V4L2_MBUS_BT656)
-			pdata_flags = RCAR_VIN_BT656;
-		else {
-			pdata_flags = 0;
-			if (ep.bus.parallel.flags & V4L2_MBUS_HSYNC_ACTIVE_LOW)
-				pdata_flags |= RCAR_VIN_HSYNC_ACTIVE_LOW;
-			if (ep.bus.parallel.flags & V4L2_MBUS_VSYNC_ACTIVE_LOW)
-				pdata_flags |= RCAR_VIN_VSYNC_ACTIVE_LOW;
-		}
-
-		of_node_put(np);
-
-		dev_dbg(&pdev->dev, "pdata_flags = %08x\n", pdata_flags);
-	} else {
-		pdata = pdev->dev.platform_data;
-		if (!pdata || !pdata->flags) {
-			dev_err(&pdev->dev, "platform data not set\n");
-			return -EINVAL;
-		}
-		pdata_flags = pdata->flags;
+	np = of_graph_get_next_endpoint(pdev->dev.of_node, NULL);
+	if (!np) {
+		dev_err(&pdev->dev, "could not find endpoint\n");
+		return -EINVAL;
 	}
 
+	ret = v4l2_of_parse_endpoint(np, &ep);
+	if (ret) {
+		dev_err(&pdev->dev, "could not parse endpoint\n");
+		return ret;
+	}
+
+	if (ep.bus_type == V4L2_MBUS_BT656)
+		pdata_flags = RCAR_VIN_BT656;
+	else {
+		pdata_flags = 0;
+		if (ep.bus.parallel.flags & V4L2_MBUS_HSYNC_ACTIVE_LOW)
+			pdata_flags |= RCAR_VIN_HSYNC_ACTIVE_LOW;
+		if (ep.bus.parallel.flags & V4L2_MBUS_VSYNC_ACTIVE_LOW)
+			pdata_flags |= RCAR_VIN_VSYNC_ACTIVE_LOW;
+	}
+
+	of_node_put(np);
+
+	dev_dbg(&pdev->dev, "pdata_flags = %08x\n", pdata_flags);
+
 	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (mem == NULL)
 		return -EINVAL;
@@ -1992,7 +1948,6 @@
 		.name		= DRV_NAME,
 		.of_match_table	= of_match_ptr(rcar_vin_of_table),
 	},
-	.id_table	= rcar_vin_id_table,
 };
 
 module_platform_driver(rcar_vin_driver);
diff --git a/drivers/media/platform/soc_camera/sh_mobile_ceu_camera.c b/drivers/media/platform/soc_camera/sh_mobile_ceu_camera.c
index 67a669d..90c87f2 100644
--- a/drivers/media/platform/soc_camera/sh_mobile_ceu_camera.c
+++ b/drivers/media/platform/soc_camera/sh_mobile_ceu_camera.c
@@ -40,11 +40,11 @@
 #include <media/v4l2-common.h>
 #include <media/v4l2-dev.h>
 #include <media/soc_camera.h>
-#include <media/sh_mobile_ceu.h>
-#include <media/sh_mobile_csi2.h>
+#include <media/drv-intf/sh_mobile_ceu.h>
+#include <media/drv-intf/sh_mobile_csi2.h>
 #include <media/videobuf2-dma-contig.h>
 #include <media/v4l2-mediabus.h>
-#include <media/soc_mediabus.h>
+#include <media/drv-intf/soc_mediabus.h>
 
 #include "soc_scale_crop.h"
 
@@ -210,43 +210,14 @@
  *		  for the current frame format if required
  */
 static int sh_mobile_ceu_videobuf_setup(struct vb2_queue *vq,
-			const void *parg,
 			unsigned int *count, unsigned int *num_planes,
 			unsigned int sizes[], void *alloc_ctxs[])
 {
-	const struct v4l2_format *fmt = parg;
 	struct soc_camera_device *icd = container_of(vq,
 			struct soc_camera_device, vb2_vidq);
 	struct soc_camera_host *ici = to_soc_camera_host(icd->parent);
 	struct sh_mobile_ceu_dev *pcdev = ici->priv;
 
-	if (fmt) {
-		const struct soc_camera_format_xlate *xlate = soc_camera_xlate_by_fourcc(icd,
-								fmt->fmt.pix.pixelformat);
-		unsigned int bytes_per_line;
-		int ret;
-
-		if (!xlate)
-			return -EINVAL;
-
-		ret = soc_mbus_bytes_per_line(fmt->fmt.pix.width,
-					      xlate->host_fmt);
-		if (ret < 0)
-			return ret;
-
-		bytes_per_line = max_t(u32, fmt->fmt.pix.bytesperline, ret);
-
-		ret = soc_mbus_image_size(xlate->host_fmt, bytes_per_line,
-					  fmt->fmt.pix.height);
-		if (ret < 0)
-			return ret;
-
-		sizes[0] = max_t(u32, fmt->fmt.pix.sizeimage, ret);
-	} else {
-		/* Called from VIDIOC_REQBUFS or in compatibility mode */
-		sizes[0] = icd->sizeimage;
-	}
-
 	alloc_ctxs[0] = pcdev->alloc_ctx;
 
 	if (!vq->num_buffers)
@@ -255,8 +226,14 @@
 	if (!*count)
 		*count = 2;
 
+	/* Called from VIDIOC_REQBUFS or in compatibility mode */
+	if (!*num_planes)
+		sizes[0] = icd->sizeimage;
+	else if (sizes[0] < icd->sizeimage)
+		return -EINVAL;
+
 	/* If *num_planes != 0, we have already verified *count. */
-	if (pcdev->video_limit && !*num_planes) {
+	if (pcdev->video_limit) {
 		size_t size = PAGE_ALIGN(sizes[0]) * *count;
 
 		if (size + pcdev->buf_total > pcdev->video_limit)
@@ -533,7 +510,7 @@
 		pcdev->active = NULL;
 
 	ret = sh_mobile_ceu_capture(pcdev);
-	v4l2_get_timestamp(&vbuf->timestamp);
+	vbuf->vb2_buf.timestamp = ktime_get_ns();
 	if (!ret) {
 		vbuf->field = pcdev->field;
 		vbuf->sequence = pcdev->sequence++;
diff --git a/drivers/media/platform/soc_camera/sh_mobile_csi2.c b/drivers/media/platform/soc_camera/sh_mobile_csi2.c
index 12d3626..09b1836 100644
--- a/drivers/media/platform/soc_camera/sh_mobile_csi2.c
+++ b/drivers/media/platform/soc_camera/sh_mobile_csi2.c
@@ -18,10 +18,10 @@
 #include <linux/videodev2.h>
 #include <linux/module.h>
 
-#include <media/sh_mobile_ceu.h>
-#include <media/sh_mobile_csi2.h>
+#include <media/drv-intf/sh_mobile_ceu.h>
+#include <media/drv-intf/sh_mobile_csi2.h>
 #include <media/soc_camera.h>
-#include <media/soc_mediabus.h>
+#include <media/drv-intf/soc_mediabus.h>
 #include <media/v4l2-common.h>
 #include <media/v4l2-dev.h>
 #include <media/v4l2-device.h>
diff --git a/drivers/media/platform/soc_camera/soc_camera.c b/drivers/media/platform/soc_camera/soc_camera.c
index dc98122..cc84c6d 100644
--- a/drivers/media/platform/soc_camera/soc_camera.c
+++ b/drivers/media/platform/soc_camera/soc_camera.c
@@ -30,7 +30,7 @@
 #include <linux/vmalloc.h>
 
 #include <media/soc_camera.h>
-#include <media/soc_mediabus.h>
+#include <media/drv-intf/soc_mediabus.h>
 #include <media/v4l2-async.h>
 #include <media/v4l2-clk.h>
 #include <media/v4l2-common.h>
@@ -1360,7 +1360,7 @@
 	struct soc_camera_host_desc *shd = &sdesc->host_desc;
 	struct i2c_adapter *adap;
 	struct v4l2_subdev *subdev;
-	char clk_name[V4L2_SUBDEV_NAME_SIZE];
+	char clk_name[V4L2_CLK_NAME_SIZE];
 	int ret;
 
 	/* First find out how we link the main client */
@@ -1391,8 +1391,8 @@
 	ssdd->sd_pdata.regulators = NULL;
 	shd->board_info->platform_data = ssdd;
 
-	snprintf(clk_name, sizeof(clk_name), "%d-%04x",
-		 shd->i2c_adapter_id, shd->board_info->addr);
+	v4l2_clk_name_i2c(clk_name, sizeof(clk_name),
+			  shd->i2c_adapter_id, shd->board_info->addr);
 
 	icd->clk = v4l2_clk_register(&soc_camera_clk_ops, clk_name, icd);
 	if (IS_ERR(icd->clk)) {
@@ -1526,7 +1526,7 @@
 	struct soc_camera_async_client *sasc;
 	struct soc_camera_device *icd;
 	struct soc_camera_desc sdesc = {.host_desc.bus_id = ici->nr,};
-	char clk_name[V4L2_SUBDEV_NAME_SIZE];
+	char clk_name[V4L2_CLK_NAME_SIZE];
 	unsigned int i;
 	int ret;
 
@@ -1572,8 +1572,9 @@
 	icd->sasc = sasc;
 	icd->parent = ici->v4l2_dev.dev;
 
-	snprintf(clk_name, sizeof(clk_name), "%d-%04x",
-		 sasd->asd.match.i2c.adapter_id, sasd->asd.match.i2c.address);
+	v4l2_clk_name_i2c(clk_name, sizeof(clk_name),
+			  sasd->asd.match.i2c.adapter_id,
+			  sasd->asd.match.i2c.address);
 
 	icd->clk = v4l2_clk_register(&soc_camera_clk_ops, clk_name, icd);
 	if (IS_ERR(icd->clk)) {
@@ -1631,7 +1632,7 @@
 	struct soc_camera_async_client *sasc;
 	struct soc_of_info *info;
 	struct i2c_client *client;
-	char clk_name[V4L2_SUBDEV_NAME_SIZE + 32];
+	char clk_name[V4L2_CLK_NAME_SIZE];
 	int ret;
 
 	/* allocate a new subdev and add match info to it */
@@ -1674,11 +1675,11 @@
 	client = of_find_i2c_device_by_node(remote);
 
 	if (client)
-		snprintf(clk_name, sizeof(clk_name), "%d-%04x",
-			 client->adapter->nr, client->addr);
+		v4l2_clk_name_i2c(clk_name, sizeof(clk_name),
+				  client->adapter->nr, client->addr);
 	else
-		snprintf(clk_name, sizeof(clk_name), "of-%s",
-			 of_node_full_name(remote));
+		v4l2_clk_name_of(clk_name, sizeof(clk_name),
+				 of_node_full_name(remote));
 
 	icd->clk = v4l2_clk_register(&soc_camera_clk_ops, clk_name, icd);
 	if (IS_ERR(icd->clk)) {
diff --git a/drivers/media/platform/soc_camera/soc_camera_platform.c b/drivers/media/platform/soc_camera/soc_camera_platform.c
index cc8eb07..a51d2a4 100644
--- a/drivers/media/platform/soc_camera/soc_camera_platform.c
+++ b/drivers/media/platform/soc_camera/soc_camera_platform.c
@@ -18,7 +18,7 @@
 #include <linux/videodev2.h>
 #include <media/v4l2-subdev.h>
 #include <media/soc_camera.h>
-#include <media/soc_camera_platform.h>
+#include <linux/platform_data/media/soc_camera_platform.h>
 
 struct soc_camera_platform_priv {
 	struct v4l2_subdev subdev;
diff --git a/drivers/media/platform/soc_camera/soc_mediabus.c b/drivers/media/platform/soc_camera/soc_mediabus.c
index 1dbcd42..e3e665e 100644
--- a/drivers/media/platform/soc_camera/soc_mediabus.c
+++ b/drivers/media/platform/soc_camera/soc_mediabus.c
@@ -13,7 +13,7 @@
 
 #include <media/v4l2-device.h>
 #include <media/v4l2-mediabus.h>
-#include <media/soc_mediabus.h>
+#include <media/drv-intf/soc_mediabus.h>
 
 static const struct soc_mbus_lookup mbus_fmt[] = {
 {
diff --git a/drivers/media/platform/sti/bdisp/bdisp-v4l2.c b/drivers/media/platform/sti/bdisp/bdisp-v4l2.c
index a0d267e..d12a419 100644
--- a/drivers/media/platform/sti/bdisp/bdisp-v4l2.c
+++ b/drivers/media/platform/sti/bdisp/bdisp-v4l2.c
@@ -191,7 +191,7 @@
 	dst_vb = v4l2_m2m_dst_buf_remove(ctx->fh.m2m_ctx);
 
 	if (src_vb && dst_vb) {
-		dst_vb->timestamp = src_vb->timestamp;
+		dst_vb->vb2_buf.timestamp = src_vb->vb2_buf.timestamp;
 		dst_vb->timecode = src_vb->timecode;
 		dst_vb->flags &= ~V4L2_BUF_FLAG_TSTAMP_SRC_MASK;
 		dst_vb->flags |= src_vb->flags &
@@ -297,7 +297,7 @@
 	if (ret)
 		return ret;
 
-	dst_vb->timestamp = src_vb->timestamp;
+	dst_vb->vb2_buf.timestamp = src_vb->vb2_buf.timestamp;
 
 	return 0;
 }
@@ -438,11 +438,9 @@
 }
 
 static int bdisp_queue_setup(struct vb2_queue *vq,
-			     const void *parg,
 			     unsigned int *nb_buf, unsigned int *nb_planes,
 			     unsigned int sizes[], void *allocators[])
 {
-	const struct v4l2_format *fmt = parg;
 	struct bdisp_ctx *ctx = vb2_get_drv_priv(vq);
 	struct bdisp_frame *frame = ctx_get_frame(ctx, vq->type);
 
@@ -455,13 +453,13 @@
 		dev_err(ctx->bdisp_dev->dev, "Invalid format\n");
 		return -EINVAL;
 	}
+	allocators[0] = ctx->bdisp_dev->alloc_ctx;
 
-	if (fmt && fmt->fmt.pix.sizeimage < frame->sizeimage)
-		return -EINVAL;
+	if (*nb_planes)
+		return sizes[0] < frame->sizeimage ? -EINVAL : 0;
 
 	*nb_planes = 1;
-	sizes[0] = fmt ? fmt->fmt.pix.sizeimage : frame->sizeimage;
-	allocators[0] = ctx->bdisp_dev->alloc_ctx;
+	sizes[0] = frame->sizeimage;
 
 	return 0;
 }
diff --git a/drivers/media/platform/sti/c8sectpfe/c8sectpfe-common.c b/drivers/media/platform/sti/c8sectpfe/c8sectpfe-common.c
index 95223ab..2dfbe8a 100644
--- a/drivers/media/platform/sti/c8sectpfe/c8sectpfe-common.c
+++ b/drivers/media/platform/sti/c8sectpfe/c8sectpfe-common.c
@@ -209,18 +209,18 @@
 
 		tsin = fei->channel_data[n];
 
-		if (tsin && tsin->frontend) {
-			dvb_unregister_frontend(tsin->frontend);
-			dvb_frontend_detach(tsin->frontend);
-		}
+		if (tsin) {
+			if (tsin->frontend) {
+				dvb_unregister_frontend(tsin->frontend);
+				dvb_frontend_detach(tsin->frontend);
+			}
 
-		if (tsin && tsin->i2c_adapter)
 			i2c_put_adapter(tsin->i2c_adapter);
 
-		if (tsin && tsin->i2c_client) {
-			if (tsin->i2c_client->dev.driver->owner)
+			if (tsin->i2c_client) {
 				module_put(tsin->i2c_client->dev.driver->owner);
-			i2c_unregister_device(tsin->i2c_client);
+				i2c_unregister_device(tsin->i2c_client);
+			}
 		}
 	}
 
diff --git a/drivers/media/platform/sti/c8sectpfe/c8sectpfe-core.c b/drivers/media/platform/sti/c8sectpfe/c8sectpfe-core.c
index 8490a65..78e3cb9 100644
--- a/drivers/media/platform/sti/c8sectpfe/c8sectpfe-core.c
+++ b/drivers/media/platform/sti/c8sectpfe/c8sectpfe-core.c
@@ -823,7 +823,7 @@
 		}
 		of_node_put(i2c_bus);
 
-		tsin->rst_gpio = of_get_named_gpio(child, "rst-gpio", 0);
+		tsin->rst_gpio = of_get_named_gpio(child, "reset-gpios", 0);
 
 		ret = gpio_is_valid(tsin->rst_gpio);
 		if (!ret) {
diff --git a/drivers/media/platform/ti-vpe/vpe.c b/drivers/media/platform/ti-vpe/vpe.c
index de24eff..1fa00c2 100644
--- a/drivers/media/platform/ti-vpe/vpe.c
+++ b/drivers/media/platform/ti-vpe/vpe.c
@@ -1288,7 +1288,7 @@
 	d_vb = ctx->dst_vb;
 
 	d_vb->flags = s_vb->flags;
-	d_vb->timestamp = s_vb->timestamp;
+	d_vb->vb2_buf.timestamp = s_vb->vb2_buf.timestamp;
 
 	if (s_vb->flags & V4L2_BUF_FLAG_TIMECODE)
 		d_vb->timecode = s_vb->timecode;
@@ -1796,7 +1796,6 @@
  * Queue operations
  */
 static int vpe_queue_setup(struct vb2_queue *vq,
-			   const void *parg,
 			   unsigned int *nbuffers, unsigned int *nplanes,
 			   unsigned int sizes[], void *alloc_ctxs[])
 {
diff --git a/drivers/media/platform/timblogiw.c b/drivers/media/platform/timblogiw.c
index 5820e45..113c9f3 100644
--- a/drivers/media/platform/timblogiw.c
+++ b/drivers/media/platform/timblogiw.c
@@ -31,7 +31,7 @@
 #include <media/v4l2-ioctl.h>
 #include <media/v4l2-device.h>
 #include <media/videobuf-dma-contig.h>
-#include <media/timb_video.h>
+#include <linux/platform_data/media/timb_video.h>
 
 #define DRIVER_NAME			"timb-video"
 
diff --git a/drivers/media/platform/via-camera.c b/drivers/media/platform/via-camera.c
index 32e4ff4..1254f7e 100644
--- a/drivers/media/platform/via-camera.c
+++ b/drivers/media/platform/via-camera.c
@@ -19,7 +19,7 @@
 #include <media/v4l2-ioctl.h>
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-image-sizes.h>
-#include <media/ov7670.h>
+#include <media/i2c/ov7670.h>
 #include <media/videobuf-dma-sg.h>
 #include <linux/delay.h>
 #include <linux/dma-mapping.h>
diff --git a/drivers/media/platform/vim2m.c b/drivers/media/platform/vim2m.c
index e18fb9f..418113c 100644
--- a/drivers/media/platform/vim2m.c
+++ b/drivers/media/platform/vim2m.c
@@ -235,7 +235,7 @@
 	out_vb->sequence =
 		get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE)->sequence++;
 	in_vb->sequence = q_data->sequence++;
-	out_vb->timestamp = in_vb->timestamp;
+	out_vb->vb2_buf.timestamp = in_vb->vb2_buf.timestamp;
 
 	if (in_vb->flags & V4L2_BUF_FLAG_TIMECODE)
 		out_vb->timecode = in_vb->timecode;
@@ -710,11 +710,9 @@
  */
 
 static int vim2m_queue_setup(struct vb2_queue *vq,
-				const void *parg,
 				unsigned int *nbuffers, unsigned int *nplanes,
 				unsigned int sizes[], void *alloc_ctxs[])
 {
-	const struct v4l2_format *fmt = parg;
 	struct vim2m_ctx *ctx = vb2_get_drv_priv(vq);
 	struct vim2m_q_data *q_data;
 	unsigned int size, count = *nbuffers;
@@ -723,17 +721,14 @@
 
 	size = q_data->width * q_data->height * q_data->fmt->depth >> 3;
 
-	if (fmt) {
-		if (fmt->fmt.pix.sizeimage < size)
-			return -EINVAL;
-		size = fmt->fmt.pix.sizeimage;
-	}
-
 	while (size * count > MEM2MEM_VID_MEM_LIMIT)
 		(count)--;
+	*nbuffers = count;
+
+	if (*nplanes)
+		return sizes[0] < size ? -EINVAL : 0;
 
 	*nplanes = 1;
-	*nbuffers = count;
 	sizes[0] = size;
 
 	/*
diff --git a/drivers/media/platform/vivid/vivid-core.h b/drivers/media/platform/vivid/vivid-core.h
index 55b304a..751c1ba 100644
--- a/drivers/media/platform/vivid/vivid-core.h
+++ b/drivers/media/platform/vivid/vivid-core.h
@@ -264,6 +264,7 @@
 	bool				vflip;
 	bool				vbi_cap_interlaced;
 	bool				loop_video;
+	bool				reduced_fps;
 
 	/* Framebuffer */
 	unsigned long			video_pbase;
@@ -285,7 +286,7 @@
 	bool				dqbuf_error;
 	bool				seq_wrap;
 	bool				time_wrap;
-	__kernel_time_t			time_wrap_offset;
+	u64				time_wrap_offset;
 	unsigned			perc_dropped_buffers;
 	enum vivid_signal_mode		std_signal_mode;
 	unsigned			query_std_last;
diff --git a/drivers/media/platform/vivid/vivid-ctrls.c b/drivers/media/platform/vivid/vivid-ctrls.c
index f41ac0b..b98089c 100644
--- a/drivers/media/platform/vivid/vivid-ctrls.c
+++ b/drivers/media/platform/vivid/vivid-ctrls.c
@@ -78,6 +78,7 @@
 #define VIVID_CID_TIME_WRAP		(VIVID_CID_VIVID_BASE + 39)
 #define VIVID_CID_MAX_EDID_BLOCKS	(VIVID_CID_VIVID_BASE + 40)
 #define VIVID_CID_PERCENTAGE_FILL	(VIVID_CID_VIVID_BASE + 41)
+#define VIVID_CID_REDUCED_FPS		(VIVID_CID_VIVID_BASE + 42)
 
 #define VIVID_CID_STD_SIGNAL_MODE	(VIVID_CID_VIVID_BASE + 60)
 #define VIVID_CID_STANDARD		(VIVID_CID_VIVID_BASE + 61)
@@ -424,6 +425,10 @@
 		dev->sensor_vflip = ctrl->val;
 		tpg_s_vflip(&dev->tpg, dev->sensor_vflip ^ dev->vflip);
 		break;
+	case VIVID_CID_REDUCED_FPS:
+		dev->reduced_fps = ctrl->val;
+		vivid_update_format_cap(dev, true);
+		break;
 	case VIVID_CID_HAS_CROP_CAP:
 		dev->has_crop_cap = ctrl->val;
 		vivid_update_format_cap(dev, true);
@@ -601,6 +606,15 @@
 	.step = 1,
 };
 
+static const struct v4l2_ctrl_config vivid_ctrl_reduced_fps = {
+	.ops = &vivid_vid_cap_ctrl_ops,
+	.id = VIVID_CID_REDUCED_FPS,
+	.name = "Reduced Framerate",
+	.type = V4L2_CTRL_TYPE_BOOLEAN,
+	.max = 1,
+	.step = 1,
+};
+
 static const struct v4l2_ctrl_config vivid_ctrl_has_crop_cap = {
 	.ops = &vivid_vid_cap_ctrl_ops,
 	.id = VIVID_CID_HAS_CROP_CAP,
@@ -940,7 +954,7 @@
 static int vivid_streaming_s_ctrl(struct v4l2_ctrl *ctrl)
 {
 	struct vivid_dev *dev = container_of(ctrl->handler, struct vivid_dev, ctrl_hdl_streaming);
-	struct timeval tv;
+	u64 rem;
 
 	switch (ctrl->id) {
 	case VIVID_CID_DQBUF_ERROR:
@@ -979,8 +993,16 @@
 			dev->time_wrap_offset = 0;
 			break;
 		}
-		v4l2_get_timestamp(&tv);
-		dev->time_wrap_offset = -tv.tv_sec - 16;
+		/*
+		 * We want to set the time 16 seconds before the 32 bit tv_sec
+		 * value of struct timeval would wrap around. So first we
+		 * calculate ktime_get_ns() % ((1 << 32) * NSEC_PER_SEC), and
+		 * then we set the offset to ((1 << 32) - 16) * NSEC_PER_SEC).
+		 */
+		div64_u64_rem(ktime_get_ns(),
+			0x100000000ULL * NSEC_PER_SEC, &rem);
+		dev->time_wrap_offset =
+			(0x100000000ULL - 16) * NSEC_PER_SEC - rem;
 		break;
 	}
 	return 0;
@@ -1340,11 +1362,13 @@
 	v4l2_ctrl_handler_init(hdl_vid_cap, 55);
 	v4l2_ctrl_new_custom(hdl_vid_cap, &vivid_ctrl_class, NULL);
 	v4l2_ctrl_handler_init(hdl_vid_out, 26);
-	v4l2_ctrl_new_custom(hdl_vid_out, &vivid_ctrl_class, NULL);
+	if (!no_error_inj)
+		v4l2_ctrl_new_custom(hdl_vid_out, &vivid_ctrl_class, NULL);
 	v4l2_ctrl_handler_init(hdl_vbi_cap, 21);
 	v4l2_ctrl_new_custom(hdl_vbi_cap, &vivid_ctrl_class, NULL);
 	v4l2_ctrl_handler_init(hdl_vbi_out, 19);
-	v4l2_ctrl_new_custom(hdl_vbi_out, &vivid_ctrl_class, NULL);
+	if (!no_error_inj)
+		v4l2_ctrl_new_custom(hdl_vbi_out, &vivid_ctrl_class, NULL);
 	v4l2_ctrl_handler_init(hdl_radio_rx, 17);
 	v4l2_ctrl_new_custom(hdl_radio_rx, &vivid_ctrl_class, NULL);
 	v4l2_ctrl_handler_init(hdl_radio_tx, 17);
@@ -1414,6 +1438,7 @@
 		v4l2_ctrl_new_custom(hdl_vid_cap, &vivid_ctrl_vflip, NULL);
 		v4l2_ctrl_new_custom(hdl_vid_cap, &vivid_ctrl_insert_sav, NULL);
 		v4l2_ctrl_new_custom(hdl_vid_cap, &vivid_ctrl_insert_eav, NULL);
+		v4l2_ctrl_new_custom(hdl_vid_cap, &vivid_ctrl_reduced_fps, NULL);
 		if (show_ccs_cap) {
 			dev->ctrl_has_crop_cap = v4l2_ctrl_new_custom(hdl_vid_cap,
 				&vivid_ctrl_has_crop_cap, NULL);
diff --git a/drivers/media/platform/vivid/vivid-kthread-cap.c b/drivers/media/platform/vivid/vivid-kthread-cap.c
index 83cc6d3..9034281 100644
--- a/drivers/media/platform/vivid/vivid-kthread-cap.c
+++ b/drivers/media/platform/vivid/vivid-kthread-cap.c
@@ -441,7 +441,7 @@
 	 * "Start of Exposure".
 	 */
 	if (dev->tstamp_src_is_soe)
-		v4l2_get_timestamp(&buf->vb.timestamp);
+		buf->vb.vb2_buf.timestamp = ktime_get_ns();
 	if (dev->field_cap == V4L2_FIELD_ALTERNATE) {
 		/*
 		 * 60 Hz standards start with the bottom field, 50 Hz standards
@@ -558,8 +558,8 @@
 	 * the timestamp now.
 	 */
 	if (!dev->tstamp_src_is_soe)
-		v4l2_get_timestamp(&buf->vb.timestamp);
-	buf->vb.timestamp.tv_sec += dev->time_wrap_offset;
+		buf->vb.vb2_buf.timestamp = ktime_get_ns();
+	buf->vb.vb2_buf.timestamp += dev->time_wrap_offset;
 }
 
 /*
diff --git a/drivers/media/platform/vivid/vivid-kthread-out.c b/drivers/media/platform/vivid/vivid-kthread-out.c
index c2c46dc..98eed58 100644
--- a/drivers/media/platform/vivid/vivid-kthread-out.c
+++ b/drivers/media/platform/vivid/vivid-kthread-out.c
@@ -95,8 +95,8 @@
 			 */
 			vid_out_buf->vb.sequence /= 2;
 		}
-		v4l2_get_timestamp(&vid_out_buf->vb.timestamp);
-		vid_out_buf->vb.timestamp.tv_sec += dev->time_wrap_offset;
+		vid_out_buf->vb.vb2_buf.timestamp =
+			ktime_get_ns() + dev->time_wrap_offset;
 		vb2_buffer_done(&vid_out_buf->vb.vb2_buf, dev->dqbuf_error ?
 				VB2_BUF_STATE_ERROR : VB2_BUF_STATE_DONE);
 		dprintk(dev, 2, "vid_out buffer %d done\n",
@@ -108,8 +108,8 @@
 			vivid_sliced_vbi_out_process(dev, vbi_out_buf);
 
 		vbi_out_buf->vb.sequence = dev->vbi_out_seq_count;
-		v4l2_get_timestamp(&vbi_out_buf->vb.timestamp);
-		vbi_out_buf->vb.timestamp.tv_sec += dev->time_wrap_offset;
+		vbi_out_buf->vb.vb2_buf.timestamp =
+			ktime_get_ns() + dev->time_wrap_offset;
 		vb2_buffer_done(&vbi_out_buf->vb.vb2_buf, dev->dqbuf_error ?
 				VB2_BUF_STATE_ERROR : VB2_BUF_STATE_DONE);
 		dprintk(dev, 2, "vbi_out buffer %d done\n",
diff --git a/drivers/media/platform/vivid/vivid-sdr-cap.c b/drivers/media/platform/vivid/vivid-sdr-cap.c
index 082c401..3d1604cb 100644
--- a/drivers/media/platform/vivid/vivid-sdr-cap.c
+++ b/drivers/media/platform/vivid/vivid-sdr-cap.c
@@ -117,8 +117,8 @@
 	if (sdr_cap_buf) {
 		sdr_cap_buf->vb.sequence = dev->sdr_cap_seq_count;
 		vivid_sdr_cap_process(dev, sdr_cap_buf);
-		v4l2_get_timestamp(&sdr_cap_buf->vb.timestamp);
-		sdr_cap_buf->vb.timestamp.tv_sec += dev->time_wrap_offset;
+		sdr_cap_buf->vb.vb2_buf.timestamp =
+			ktime_get_ns() + dev->time_wrap_offset;
 		vb2_buffer_done(&sdr_cap_buf->vb.vb2_buf, dev->dqbuf_error ?
 				VB2_BUF_STATE_ERROR : VB2_BUF_STATE_DONE);
 		dev->dqbuf_error = false;
@@ -213,7 +213,7 @@
 	return 0;
 }
 
-static int sdr_cap_queue_setup(struct vb2_queue *vq, const void *parg,
+static int sdr_cap_queue_setup(struct vb2_queue *vq,
 		       unsigned *nbuffers, unsigned *nplanes,
 		       unsigned sizes[], void *alloc_ctxs[])
 {
diff --git a/drivers/media/platform/vivid/vivid-vbi-cap.c b/drivers/media/platform/vivid/vivid-vbi-cap.c
index e903d02..cda45a5 100644
--- a/drivers/media/platform/vivid/vivid-vbi-cap.c
+++ b/drivers/media/platform/vivid/vivid-vbi-cap.c
@@ -108,8 +108,7 @@
 	if (!VIVID_INVALID_SIGNAL(dev->std_signal_mode))
 		vivid_vbi_gen_raw(&dev->vbi_gen, &vbi, vbuf);
 
-	v4l2_get_timestamp(&buf->vb.timestamp);
-	buf->vb.timestamp.tv_sec += dev->time_wrap_offset;
+	buf->vb.vb2_buf.timestamp = ktime_get_ns() + dev->time_wrap_offset;
 }
 
 
@@ -133,11 +132,10 @@
 			vbuf[i] = dev->vbi_gen.data[i];
 	}
 
-	v4l2_get_timestamp(&buf->vb.timestamp);
-	buf->vb.timestamp.tv_sec += dev->time_wrap_offset;
+	buf->vb.vb2_buf.timestamp = ktime_get_ns() + dev->time_wrap_offset;
 }
 
-static int vbi_cap_queue_setup(struct vb2_queue *vq, const void *parg,
+static int vbi_cap_queue_setup(struct vb2_queue *vq,
 		       unsigned *nbuffers, unsigned *nplanes,
 		       unsigned sizes[], void *alloc_ctxs[])
 {
diff --git a/drivers/media/platform/vivid/vivid-vbi-out.c b/drivers/media/platform/vivid/vivid-vbi-out.c
index 75c5709..3c5a469 100644
--- a/drivers/media/platform/vivid/vivid-vbi-out.c
+++ b/drivers/media/platform/vivid/vivid-vbi-out.c
@@ -27,7 +27,7 @@
 #include "vivid-vbi-out.h"
 #include "vivid-vbi-cap.h"
 
-static int vbi_out_queue_setup(struct vb2_queue *vq, const void *parg,
+static int vbi_out_queue_setup(struct vb2_queue *vq,
 		       unsigned *nbuffers, unsigned *nplanes,
 		       unsigned sizes[], void *alloc_ctxs[])
 {
diff --git a/drivers/media/platform/vivid/vivid-vid-cap.c b/drivers/media/platform/vivid/vivid-vid-cap.c
index ef54123..b84f081 100644
--- a/drivers/media/platform/vivid/vivid-vid-cap.c
+++ b/drivers/media/platform/vivid/vivid-vid-cap.c
@@ -95,11 +95,10 @@
 	VIVID_WEBCAM_SIZES
 };
 
-static int vid_cap_queue_setup(struct vb2_queue *vq, const void *parg,
+static int vid_cap_queue_setup(struct vb2_queue *vq,
 		       unsigned *nbuffers, unsigned *nplanes,
 		       unsigned sizes[], void *alloc_ctxs[])
 {
-	const struct v4l2_format *fmt = parg;
 	struct vivid_dev *dev = vb2_get_drv_priv(vq);
 	unsigned buffers = tpg_g_buffers(&dev->tpg);
 	unsigned h = dev->fmt_cap_rect.height;
@@ -122,27 +121,16 @@
 		dev->queue_setup_error = false;
 		return -EINVAL;
 	}
-	if (fmt) {
-		const struct v4l2_pix_format_mplane *mp;
-		struct v4l2_format mp_fmt;
-		const struct vivid_fmt *vfmt;
-
-		if (!V4L2_TYPE_IS_MULTIPLANAR(fmt->type)) {
-			fmt_sp2mp(fmt, &mp_fmt);
-			fmt = &mp_fmt;
-		}
-		mp = &fmt->fmt.pix_mp;
+	if (*nplanes) {
 		/*
-		 * Check if the number of planes in the specified format match
+		 * Check if the number of requested planes match
 		 * the number of buffers in the current format. You can't mix that.
 		 */
-		if (mp->num_planes != buffers)
+		if (*nplanes != buffers)
 			return -EINVAL;
-		vfmt = vivid_get_format(dev, mp->pixelformat);
 		for (p = 0; p < buffers; p++) {
-			sizes[p] = mp->plane_fmt[p].sizeimage;
 			if (sizes[p] < tpg_g_line_width(&dev->tpg, p) * h +
-							vfmt->data_offset[p])
+						dev->fmt_cap->data_offset[p])
 				return -EINVAL;
 		}
 	} else {
@@ -405,6 +393,7 @@
 {
 	struct v4l2_bt_timings *bt = &dev->dv_timings_cap.bt;
 	unsigned size;
+	u64 pixelclock;
 
 	switch (dev->input_type[dev->input]) {
 	case WEBCAM:
@@ -434,8 +423,15 @@
 		dev->src_rect.width = bt->width;
 		dev->src_rect.height = bt->height;
 		size = V4L2_DV_BT_FRAME_WIDTH(bt) * V4L2_DV_BT_FRAME_HEIGHT(bt);
+		if (dev->reduced_fps && can_reduce_fps(bt)) {
+			pixelclock = div_u64(bt->pixelclock * 1000, 1001);
+			bt->flags |= V4L2_DV_FL_REDUCED_FPS;
+		} else {
+			pixelclock = bt->pixelclock;
+			bt->flags &= ~V4L2_DV_FL_REDUCED_FPS;
+		}
 		dev->timeperframe_vid_cap = (struct v4l2_fract) {
-			size / 100, (u32)bt->pixelclock / 100
+			size / 100, (u32)pixelclock / 100
 		};
 		if (bt->interlaced)
 			dev->field_cap = V4L2_FIELD_ALTERNATE;
@@ -1662,7 +1658,7 @@
 	    !valid_cvt_gtf_timings(timings))
 		return -EINVAL;
 
-	if (v4l2_match_dv_timings(timings, &dev->dv_timings_cap, 0))
+	if (v4l2_match_dv_timings(timings, &dev->dv_timings_cap, 0, false))
 		return 0;
 	if (vb2_is_busy(&dev->vb_vid_cap_q))
 		return -EBUSY;
diff --git a/drivers/media/platform/vivid/vivid-vid-out.c b/drivers/media/platform/vivid/vivid-vid-out.c
index b77acb6..64e4d66 100644
--- a/drivers/media/platform/vivid/vivid-vid-out.c
+++ b/drivers/media/platform/vivid/vivid-vid-out.c
@@ -31,11 +31,10 @@
 #include "vivid-kthread-out.h"
 #include "vivid-vid-out.h"
 
-static int vid_out_queue_setup(struct vb2_queue *vq, const void *parg,
+static int vid_out_queue_setup(struct vb2_queue *vq,
 		       unsigned *nbuffers, unsigned *nplanes,
 		       unsigned sizes[], void *alloc_ctxs[])
 {
-	const struct v4l2_format *fmt = parg;
 	struct vivid_dev *dev = vb2_get_drv_priv(vq);
 	const struct vivid_fmt *vfmt = dev->fmt_out;
 	unsigned planes = vfmt->buffers;
@@ -64,26 +63,16 @@
 		return -EINVAL;
 	}
 
-	if (fmt) {
-		const struct v4l2_pix_format_mplane *mp;
-		struct v4l2_format mp_fmt;
-
-		if (!V4L2_TYPE_IS_MULTIPLANAR(fmt->type)) {
-			fmt_sp2mp(fmt, &mp_fmt);
-			fmt = &mp_fmt;
-		}
-		mp = &fmt->fmt.pix_mp;
+	if (*nplanes) {
 		/*
-		 * Check if the number of planes in the specified format match
+		 * Check if the number of requested planes match
 		 * the number of planes in the current format. You can't mix that.
 		 */
-		if (mp->num_planes != planes)
+		if (*nplanes != planes)
 			return -EINVAL;
-		sizes[0] = mp->plane_fmt[0].sizeimage;
 		if (sizes[0] < size)
 			return -EINVAL;
 		for (p = 1; p < planes; p++) {
-			sizes[p] = mp->plane_fmt[p].sizeimage;
 			if (sizes[p] < dev->bytesperline_out[p] * h)
 				return -EINVAL;
 		}
@@ -224,6 +213,7 @@
 {
 	struct v4l2_bt_timings *bt = &dev->dv_timings_out.bt;
 	unsigned size, p;
+	u64 pixelclock;
 
 	switch (dev->output_type[dev->output]) {
 	case SVID:
@@ -245,8 +235,14 @@
 		dev->sink_rect.width = bt->width;
 		dev->sink_rect.height = bt->height;
 		size = V4L2_DV_BT_FRAME_WIDTH(bt) * V4L2_DV_BT_FRAME_HEIGHT(bt);
+
+		if (can_reduce_fps(bt) && (bt->flags & V4L2_DV_FL_REDUCED_FPS))
+			pixelclock = div_u64(bt->pixelclock * 1000, 1001);
+		else
+			pixelclock = bt->pixelclock;
+
 		dev->timeperframe_vid_out = (struct v4l2_fract) {
-			size / 100, (u32)bt->pixelclock / 100
+			size / 100, (u32)pixelclock / 100
 		};
 		if (bt->interlaced)
 			dev->field_out = V4L2_FIELD_ALTERNATE;
@@ -1149,7 +1145,7 @@
 				0, NULL, NULL) &&
 	    !valid_cvt_gtf_timings(timings))
 		return -EINVAL;
-	if (v4l2_match_dv_timings(timings, &dev->dv_timings_out, 0))
+	if (v4l2_match_dv_timings(timings, &dev->dv_timings_out, 0, true))
 		return 0;
 	if (vb2_is_busy(&dev->vb_vid_out_q))
 		return -EBUSY;
diff --git a/drivers/media/platform/vsp1/vsp1_video.c b/drivers/media/platform/vsp1/vsp1_video.c
index 5ce88e1..45eb65f 100644
--- a/drivers/media/platform/vsp1/vsp1_video.c
+++ b/drivers/media/platform/vsp1/vsp1_video.c
@@ -274,35 +274,6 @@
 	return 0;
 }
 
-static bool
-vsp1_video_format_adjust(struct vsp1_video *video,
-			 const struct v4l2_pix_format_mplane *format,
-			 struct v4l2_pix_format_mplane *adjust)
-{
-	unsigned int i;
-
-	*adjust = *format;
-	__vsp1_video_try_format(video, adjust, NULL);
-
-	if (format->width != adjust->width ||
-	    format->height != adjust->height ||
-	    format->pixelformat != adjust->pixelformat ||
-	    format->num_planes != adjust->num_planes)
-		return false;
-
-	for (i = 0; i < format->num_planes; ++i) {
-		if (format->plane_fmt[i].bytesperline !=
-		    adjust->plane_fmt[i].bytesperline)
-			return false;
-
-		adjust->plane_fmt[i].sizeimage =
-			max(adjust->plane_fmt[i].sizeimage,
-			    format->plane_fmt[i].sizeimage);
-	}
-
-	return true;
-}
-
 /* -----------------------------------------------------------------------------
  * Pipeline Management
  */
@@ -611,7 +582,7 @@
 	spin_unlock_irqrestore(&video->irqlock, flags);
 
 	done->buf.sequence = video->sequence++;
-	v4l2_get_timestamp(&done->buf.timestamp);
+	done->buf.vb2_buf.timestamp = ktime_get_ns();
 	for (i = 0; i < done->buf.vb2_buf.num_planes; ++i)
 		vb2_set_plane_payload(&done->buf.vb2_buf, i, done->length[i]);
 	vb2_buffer_done(&done->buf.vb2_buf, VB2_BUF_STATE_DONE);
@@ -787,26 +758,24 @@
  */
 
 static int
-vsp1_video_queue_setup(struct vb2_queue *vq, const void *parg,
+vsp1_video_queue_setup(struct vb2_queue *vq,
 		     unsigned int *nbuffers, unsigned int *nplanes,
 		     unsigned int sizes[], void *alloc_ctxs[])
 {
-	const struct v4l2_format *fmt = parg;
 	struct vsp1_video *video = vb2_get_drv_priv(vq);
-	const struct v4l2_pix_format_mplane *format;
-	struct v4l2_pix_format_mplane pix_mp;
+	const struct v4l2_pix_format_mplane *format = &video->format;
 	unsigned int i;
 
-	if (fmt) {
-		/* Make sure the format is valid and adjust the sizeimage field
-		 * if needed.
-		 */
-		if (!vsp1_video_format_adjust(video, &fmt->fmt.pix_mp, &pix_mp))
+	if (*nplanes) {
+		if (*nplanes != format->num_planes)
 			return -EINVAL;
 
-		format = &pix_mp;
-	} else {
-		format = &video->format;
+		for (i = 0; i < *nplanes; i++) {
+			if (sizes[i] < format->plane_fmt[i].sizeimage)
+				return -EINVAL;
+			alloc_ctxs[i] = video->alloc_ctx;
+		}
+		return 0;
 	}
 
 	*nplanes = format->num_planes;
diff --git a/drivers/media/platform/xilinx/xilinx-dma.c b/drivers/media/platform/xilinx/xilinx-dma.c
index d11cc70..722758f 100644
--- a/drivers/media/platform/xilinx/xilinx-dma.c
+++ b/drivers/media/platform/xilinx/xilinx-dma.c
@@ -303,27 +303,25 @@
 
 	buf->buf.field = V4L2_FIELD_NONE;
 	buf->buf.sequence = dma->sequence++;
-	v4l2_get_timestamp(&buf->buf.timestamp);
+	buf->buf.vb2_buf.timestamp = ktime_get_ns();
 	vb2_set_plane_payload(&buf->buf.vb2_buf, 0, dma->format.sizeimage);
 	vb2_buffer_done(&buf->buf.vb2_buf, VB2_BUF_STATE_DONE);
 }
 
 static int
-xvip_dma_queue_setup(struct vb2_queue *vq, const void *parg,
+xvip_dma_queue_setup(struct vb2_queue *vq,
 		     unsigned int *nbuffers, unsigned int *nplanes,
 		     unsigned int sizes[], void *alloc_ctxs[])
 {
-	const struct v4l2_format *fmt = parg;
 	struct xvip_dma *dma = vb2_get_drv_priv(vq);
 
+	alloc_ctxs[0] = dma->alloc_ctx;
 	/* Make sure the image size is large enough. */
-	if (fmt && fmt->fmt.pix.sizeimage < dma->format.sizeimage)
-		return -EINVAL;
+	if (*nplanes)
+		return sizes[0] < dma->format.sizeimage ? -EINVAL : 0;
 
 	*nplanes = 1;
-
-	sizes[0] = fmt ? fmt->fmt.pix.sizeimage : dma->format.sizeimage;
-	alloc_ctxs[0] = dma->alloc_ctx;
+	sizes[0] = dma->format.sizeimage;
 
 	return 0;
 }
diff --git a/drivers/media/platform/xilinx/xilinx-tpg.c b/drivers/media/platform/xilinx/xilinx-tpg.c
index b5f7d5e..8bd7e37 100644
--- a/drivers/media/platform/xilinx/xilinx-tpg.c
+++ b/drivers/media/platform/xilinx/xilinx-tpg.c
@@ -731,6 +731,7 @@
 		format = xvip_of_get_format(port);
 		if (IS_ERR(format)) {
 			dev_err(dev, "invalid format in DT");
+			of_node_put(port);
 			return PTR_ERR(format);
 		}
 
@@ -739,6 +740,7 @@
 			xtpg->vip_format = format;
 		} else if (xtpg->vip_format != format) {
 			dev_err(dev, "in/out format mismatch in DT");
+			of_node_put(port);
 			return -EINVAL;
 		}
 
diff --git a/drivers/media/platform/xilinx/xilinx-vipp.c b/drivers/media/platform/xilinx/xilinx-vipp.c
index 7b7cb9c..b9bf24f 100644
--- a/drivers/media/platform/xilinx/xilinx-vipp.c
+++ b/drivers/media/platform/xilinx/xilinx-vipp.c
@@ -476,8 +476,10 @@
 
 	for_each_child_of_node(ports, port) {
 		ret = xvip_graph_dma_init_one(xdev, port);
-		if (ret < 0)
+		if (ret < 0) {
+			of_node_put(port);
 			return ret;
+		}
 	}
 
 	return 0;
diff --git a/drivers/media/radio/radio-maxiradio.c b/drivers/media/radio/radio-maxiradio.c
index 5236035..70fd8e8 100644
--- a/drivers/media/radio/radio-maxiradio.c
+++ b/drivers/media/radio/radio-maxiradio.c
@@ -42,7 +42,7 @@
 #include <linux/videodev2.h>
 #include <linux/io.h>
 #include <linux/slab.h>
-#include <media/tea575x.h>
+#include <media/drv-intf/tea575x.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-ioctl.h>
 #include <media/v4l2-fh.h>
@@ -108,7 +108,7 @@
 {
 }
 
-static struct snd_tea575x_ops maxiradio_tea_ops = {
+static const struct snd_tea575x_ops maxiradio_tea_ops = {
 	.set_pins = maxiradio_tea575x_set_pins,
 	.get_pins = maxiradio_tea575x_get_pins,
 	.set_direction = maxiradio_tea575x_set_direction,
diff --git a/drivers/media/radio/radio-sf16fmr2.c b/drivers/media/radio/radio-sf16fmr2.c
index b8d61cb..dc81d42 100644
--- a/drivers/media/radio/radio-sf16fmr2.c
+++ b/drivers/media/radio/radio-sf16fmr2.c
@@ -14,7 +14,7 @@
 #include <linux/io.h>		/* outb, outb_p			*/
 #include <linux/isa.h>
 #include <linux/pnp.h>
-#include <media/tea575x.h>
+#include <media/drv-intf/tea575x.h>
 
 MODULE_AUTHOR("Ondrej Zary");
 MODULE_DESCRIPTION("MediaForte SF16-FMR2 and SF16-FMD2 FM radio card driver");
@@ -82,7 +82,7 @@
 {
 }
 
-static struct snd_tea575x_ops fmr2_tea_ops = {
+static const struct snd_tea575x_ops fmr2_tea_ops = {
 	.set_pins = fmr2_tea575x_set_pins,
 	.get_pins = fmr2_tea575x_get_pins,
 	.set_direction = fmr2_tea575x_set_direction,
diff --git a/drivers/media/radio/radio-shark.c b/drivers/media/radio/radio-shark.c
index 050b3bb..85667a95 100644
--- a/drivers/media/radio/radio-shark.c
+++ b/drivers/media/radio/radio-shark.c
@@ -33,7 +33,7 @@
 #include <linux/usb.h>
 #include <linux/workqueue.h>
 #include <media/v4l2-device.h>
-#include <media/tea575x.h>
+#include <media/drv-intf/tea575x.h>
 
 #if defined(CONFIG_LEDS_CLASS) || \
     (defined(CONFIG_LEDS_CLASS_MODULE) && defined(CONFIG_RADIO_SHARK_MODULE))
@@ -150,7 +150,7 @@
 	return val;
 }
 
-static struct snd_tea575x_ops shark_tea_ops = {
+static const struct snd_tea575x_ops shark_tea_ops = {
 	.write_val = shark_write_val,
 	.read_val  = shark_read_val,
 };
diff --git a/drivers/media/radio/radio-shark2.c b/drivers/media/radio/radio-shark2.c
index 8654e0d..0e65a85 100644
--- a/drivers/media/radio/radio-shark2.c
+++ b/drivers/media/radio/radio-shark2.c
@@ -137,7 +137,7 @@
 	return 0;
 }
 
-static struct radio_tea5777_ops shark_tea_ops = {
+static const struct radio_tea5777_ops shark_tea_ops = {
 	.write_reg = shark_write_reg,
 	.read_reg  = shark_read_reg,
 };
diff --git a/drivers/media/radio/radio-si476x.c b/drivers/media/radio/radio-si476x.c
index 9cbb8cd..859f0c0 100644
--- a/drivers/media/radio/radio-si476x.c
+++ b/drivers/media/radio/radio-si476x.c
@@ -31,7 +31,7 @@
 #include <media/v4l2-event.h>
 #include <media/v4l2-device.h>
 
-#include <media/si476x.h>
+#include <media/drv-intf/si476x.h>
 #include <linux/mfd/si476x-core.h>
 
 #define FM_FREQ_RANGE_LOW   64000000
diff --git a/drivers/media/radio/radio-tea5777.h b/drivers/media/radio/radio-tea5777.h
index 4ea43a9..4bd9425 100644
--- a/drivers/media/radio/radio-tea5777.h
+++ b/drivers/media/radio/radio-tea5777.h
@@ -76,7 +76,7 @@
 	u32 read_reg;
 	u64 write_reg;
 	struct mutex mutex;
-	struct radio_tea5777_ops *ops;
+	const struct radio_tea5777_ops *ops;
 	void *private_data;
 	u8 card[32];
 	u8 bus_info[32];
diff --git a/drivers/media/radio/radio-timb.c b/drivers/media/radio/radio-timb.c
index 04baafe..a82eb96 100644
--- a/drivers/media/radio/radio-timb.c
+++ b/drivers/media/radio/radio-timb.c
@@ -26,7 +26,7 @@
 #include <linux/slab.h>
 #include <linux/i2c.h>
 #include <linux/module.h>
-#include <media/timb_radio.h>
+#include <linux/platform_data/media/timb_radio.h>
 
 #define DRIVER_NAME "timb-radio"
 
diff --git a/drivers/media/radio/si4713/radio-usb-si4713.c b/drivers/media/radio/si4713/radio-usb-si4713.c
index a77319d..5146be2 100644
--- a/drivers/media/radio/si4713/radio-usb-si4713.c
+++ b/drivers/media/radio/si4713/radio-usb-si4713.c
@@ -31,7 +31,7 @@
 #include <media/v4l2-device.h>
 #include <media/v4l2-ioctl.h>
 #include <media/v4l2-event.h>
-#include <media/si4713.h>
+#include <linux/platform_data/media/si4713.h>
 
 #include "si4713.h"
 
diff --git a/drivers/media/radio/si4713/si4713.h b/drivers/media/radio/si4713/si4713.h
index 8a376e1..29d0e1f 100644
--- a/drivers/media/radio/si4713/si4713.h
+++ b/drivers/media/radio/si4713/si4713.h
@@ -20,7 +20,7 @@
 #include <linux/gpio/consumer.h>
 #include <media/v4l2-subdev.h>
 #include <media/v4l2-ctrls.h>
-#include <media/si4713.h>
+#include <linux/platform_data/media/si4713.h>
 
 #define SI4713_PRODUCT_NUMBER		0x0D
 
diff --git a/drivers/media/radio/tea575x.c b/drivers/media/radio/tea575x.c
index 43d1ea5..3e08475 100644
--- a/drivers/media/radio/tea575x.c
+++ b/drivers/media/radio/tea575x.c
@@ -31,7 +31,7 @@
 #include <media/v4l2-fh.h>
 #include <media/v4l2-ioctl.h>
 #include <media/v4l2-event.h>
-#include <media/tea575x.h>
+#include <media/drv-intf/tea575x.h>
 
 MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
 MODULE_DESCRIPTION("Routines for control of TEA5757/5759 Philips AM/FM radio tuner chips");
diff --git a/drivers/media/rc/Kconfig b/drivers/media/rc/Kconfig
index b6e1311..bd4d685 100644
--- a/drivers/media/rc/Kconfig
+++ b/drivers/media/rc/Kconfig
@@ -101,7 +101,8 @@
 
 	---help---
 	   Enable this option if you have an infrared remote control which
-	   uses the Sharp protocol, and you need software decoding support.
+	   uses the Sharp protocol (Sharp, Denon), and you need software
+	   decoding support.
 
 config IR_MCE_KBD_DECODER
 	tristate "Enable IR raw decoder for the MCE keyboard/mouse protocol"
diff --git a/drivers/media/rc/gpio-ir-recv.c b/drivers/media/rc/gpio-ir-recv.c
index 7dbc9ca..5b63b1f 100644
--- a/drivers/media/rc/gpio-ir-recv.c
+++ b/drivers/media/rc/gpio-ir-recv.c
@@ -21,7 +21,7 @@
 #include <linux/platform_device.h>
 #include <linux/irq.h>
 #include <media/rc-core.h>
-#include <media/gpio-ir-recv.h>
+#include <linux/platform_data/media/gpio-ir-recv.h>
 
 #define GPIO_IR_DRIVER_NAME	"gpio-rc-recv"
 #define GPIO_IR_DEVICE_NAME	"gpio_ir_recv"
@@ -30,6 +30,7 @@
 	struct rc_dev *rcdev;
 	int gpio_nr;
 	bool active_low;
+	struct timer_list flush_timer;
 };
 
 #ifdef CONFIG_OF
@@ -93,12 +94,26 @@
 	if (rc < 0)
 		goto err_get_value;
 
+	mod_timer(&gpio_dev->flush_timer,
+		  jiffies + nsecs_to_jiffies(gpio_dev->rcdev->timeout));
+
 	ir_raw_event_handle(gpio_dev->rcdev);
 
 err_get_value:
 	return IRQ_HANDLED;
 }
 
+static void flush_timer(unsigned long arg)
+{
+	struct gpio_rc_dev *gpio_dev = (struct gpio_rc_dev *)arg;
+	DEFINE_IR_RAW_EVENT(ev);
+
+	ev.timeout = true;
+	ev.duration = gpio_dev->rcdev->timeout;
+	ir_raw_event_store(gpio_dev->rcdev, &ev);
+	ir_raw_event_handle(gpio_dev->rcdev);
+}
+
 static int gpio_ir_recv_probe(struct platform_device *pdev)
 {
 	struct gpio_rc_dev *gpio_dev;
@@ -144,6 +159,9 @@
 	rcdev->input_id.version = 0x0100;
 	rcdev->dev.parent = &pdev->dev;
 	rcdev->driver_name = GPIO_IR_DRIVER_NAME;
+	rcdev->min_timeout = 0;
+	rcdev->timeout = IR_DEFAULT_TIMEOUT;
+	rcdev->max_timeout = 10 * IR_DEFAULT_TIMEOUT;
 	if (pdata->allowed_protos)
 		rcdev->allowed_protocols = pdata->allowed_protos;
 	else
@@ -154,6 +172,9 @@
 	gpio_dev->gpio_nr = pdata->gpio_nr;
 	gpio_dev->active_low = pdata->active_low;
 
+	setup_timer(&gpio_dev->flush_timer, flush_timer,
+		    (unsigned long)gpio_dev);
+
 	rc = gpio_request(pdata->gpio_nr, "gpio-ir-recv");
 	if (rc < 0)
 		goto err_gpio_request;
@@ -196,6 +217,7 @@
 	struct gpio_rc_dev *gpio_dev = platform_get_drvdata(pdev);
 
 	free_irq(gpio_to_irq(gpio_dev->gpio_nr), gpio_dev);
+	del_timer_sync(&gpio_dev->flush_timer);
 	rc_unregister_device(gpio_dev->rcdev);
 	gpio_free(gpio_dev->gpio_nr);
 	kfree(gpio_dev);
diff --git a/drivers/media/rc/ir-jvc-decoder.c b/drivers/media/rc/ir-jvc-decoder.c
index 30bcf18..182402f 100644
--- a/drivers/media/rc/ir-jvc-decoder.c
+++ b/drivers/media/rc/ir-jvc-decoder.c
@@ -47,9 +47,6 @@
 {
 	struct jvc_dec *data = &dev->raw->jvc;
 
-	if (!(dev->enabled_protocols & RC_BIT_JVC))
-		return 0;
-
 	if (!is_timing_event(ev)) {
 		if (ev.reset)
 			data->state = STATE_INACTIVE;
diff --git a/drivers/media/rc/ir-lirc-codec.c b/drivers/media/rc/ir-lirc-codec.c
index a32659f..5effc65 100644
--- a/drivers/media/rc/ir-lirc-codec.c
+++ b/drivers/media/rc/ir-lirc-codec.c
@@ -415,6 +415,7 @@
 
 	lirc_unregister_driver(lirc->drv->minor);
 	lirc_buffer_free(lirc->drv->rbuf);
+	kfree(lirc->drv->rbuf);
 	kfree(lirc->drv);
 
 	return 0;
diff --git a/drivers/media/rc/ir-mce_kbd-decoder.c b/drivers/media/rc/ir-mce_kbd-decoder.c
index 9f3c9b5..d809862 100644
--- a/drivers/media/rc/ir-mce_kbd-decoder.c
+++ b/drivers/media/rc/ir-mce_kbd-decoder.c
@@ -216,9 +216,6 @@
 	u32 scancode;
 	unsigned long delay;
 
-	if (!(dev->enabled_protocols & RC_BIT_MCE_KBD))
-		return 0;
-
 	if (!is_timing_event(ev)) {
 		if (ev.reset)
 			data->state = STATE_INACTIVE;
diff --git a/drivers/media/rc/ir-nec-decoder.c b/drivers/media/rc/ir-nec-decoder.c
index 7b81fec..bea0d1e 100644
--- a/drivers/media/rc/ir-nec-decoder.c
+++ b/drivers/media/rc/ir-nec-decoder.c
@@ -52,9 +52,6 @@
 	u8 address, not_address, command, not_command;
 	bool send_32bits = false;
 
-	if (!(dev->enabled_protocols & RC_BIT_NEC))
-		return 0;
-
 	if (!is_timing_event(ev)) {
 		if (ev.reset)
 			data->state = STATE_INACTIVE;
diff --git a/drivers/media/rc/ir-rc5-decoder.c b/drivers/media/rc/ir-rc5-decoder.c
index 84fa6e9..6ffe776 100644
--- a/drivers/media/rc/ir-rc5-decoder.c
+++ b/drivers/media/rc/ir-rc5-decoder.c
@@ -53,9 +53,6 @@
 	u32 scancode;
 	enum rc_type protocol;
 
-	if (!(dev->enabled_protocols & (RC_BIT_RC5 | RC_BIT_RC5X | RC_BIT_RC5_SZ)))
-		return 0;
-
 	if (!is_timing_event(ev)) {
 		if (ev.reset)
 			data->state = STATE_INACTIVE;
diff --git a/drivers/media/rc/ir-rc6-decoder.c b/drivers/media/rc/ir-rc6-decoder.c
index d16bc67..e0e2ede 100644
--- a/drivers/media/rc/ir-rc6-decoder.c
+++ b/drivers/media/rc/ir-rc6-decoder.c
@@ -90,11 +90,6 @@
 	u8 toggle;
 	enum rc_type protocol;
 
-	if (!(dev->enabled_protocols &
-	      (RC_BIT_RC6_0 | RC_BIT_RC6_6A_20 | RC_BIT_RC6_6A_24 |
-	       RC_BIT_RC6_6A_32 | RC_BIT_RC6_MCE)))
-		return 0;
-
 	if (!is_timing_event(ev)) {
 		if (ev.reset)
 			data->state = STATE_INACTIVE;
diff --git a/drivers/media/rc/ir-rx51.c b/drivers/media/rc/ir-rx51.c
index b1e19a2..4e1711a 100644
--- a/drivers/media/rc/ir-rx51.c
+++ b/drivers/media/rc/ir-rx51.c
@@ -31,7 +31,7 @@
 
 #include <media/lirc.h>
 #include <media/lirc_dev.h>
-#include <media/ir-rx51.h>
+#include <linux/platform_data/media/ir-rx51.h>
 
 #define LIRC_RX51_DRIVER_FEATURES (LIRC_CAN_SET_SEND_DUTY_CYCLE |	\
 				   LIRC_CAN_SET_SEND_CARRIER |		\
diff --git a/drivers/media/rc/ir-sanyo-decoder.c b/drivers/media/rc/ir-sanyo-decoder.c
index ad1dc6a..7331e5e7 100644
--- a/drivers/media/rc/ir-sanyo-decoder.c
+++ b/drivers/media/rc/ir-sanyo-decoder.c
@@ -58,9 +58,6 @@
 	u32 scancode;
 	u8 address, command, not_command;
 
-	if (!(dev->enabled_protocols & RC_BIT_SANYO))
-		return 0;
-
 	if (!is_timing_event(ev)) {
 		if (ev.reset) {
 			IR_dprintk(1, "SANYO event reset received. reset to state 0\n");
diff --git a/drivers/media/rc/ir-sharp-decoder.c b/drivers/media/rc/ir-sharp-decoder.c
index b7acdba..317677f 100644
--- a/drivers/media/rc/ir-sharp-decoder.c
+++ b/drivers/media/rc/ir-sharp-decoder.c
@@ -48,9 +48,6 @@
 	struct sharp_dec *data = &dev->raw->sharp;
 	u32 msg, echo, address, command, scancode;
 
-	if (!(dev->enabled_protocols & RC_BIT_SHARP))
-		return 0;
-
 	if (!is_timing_event(ev)) {
 		if (ev.reset)
 			data->state = STATE_INACTIVE;
@@ -118,7 +115,9 @@
 
 		if (data->count == SHARP_NBITS) {
 			/* exp,chk bits should be 1,0 */
-			if ((data->bits & 0x3) != 0x2)
+			if ((data->bits & 0x3) != 0x2 &&
+			/* DENON variant, both chk bits 0 */
+			    (data->bits & 0x3) != 0x0)
 				break;
 			data->state = STATE_ECHO_SPACE;
 		} else {
diff --git a/drivers/media/rc/ir-sony-decoder.c b/drivers/media/rc/ir-sony-decoder.c
index 58ef06f..baa972c 100644
--- a/drivers/media/rc/ir-sony-decoder.c
+++ b/drivers/media/rc/ir-sony-decoder.c
@@ -46,10 +46,6 @@
 	u32 scancode;
 	u8 device, subdevice, function;
 
-	if (!(dev->enabled_protocols &
-	      (RC_BIT_SONY12 | RC_BIT_SONY15 | RC_BIT_SONY20)))
-		return 0;
-
 	if (!is_timing_event(ev)) {
 		if (ev.reset)
 			data->state = STATE_INACTIVE;
diff --git a/drivers/media/rc/ir-xmp-decoder.c b/drivers/media/rc/ir-xmp-decoder.c
index 1017d48..1859619 100644
--- a/drivers/media/rc/ir-xmp-decoder.c
+++ b/drivers/media/rc/ir-xmp-decoder.c
@@ -43,9 +43,6 @@
 {
 	struct xmp_dec *data = &dev->raw->xmp;
 
-	if (!(dev->enabled_protocols & RC_BIT_XMP))
-		return 0;
-
 	if (!is_timing_event(ev)) {
 		if (ev.reset)
 			data->state = STATE_INACTIVE;
diff --git a/drivers/media/rc/nuvoton-cir.c b/drivers/media/rc/nuvoton-cir.c
index 85af7a8..18adf58 100644
--- a/drivers/media/rc/nuvoton-cir.c
+++ b/drivers/media/rc/nuvoton-cir.c
@@ -39,6 +39,18 @@
 
 #include "nuvoton-cir.h"
 
+static const struct nvt_chip nvt_chips[] = {
+	{ "w83667hg", NVT_W83667HG },
+	{ "NCT6775F", NVT_6775F },
+	{ "NCT6776F", NVT_6776F },
+	{ "NCT6779D", NVT_6779D },
+};
+
+static inline bool is_w83667hg(struct nvt_dev *nvt)
+{
+	return nvt->chip_ver == NVT_W83667HG;
+}
+
 /* write val to config reg */
 static inline void nvt_cr_write(struct nvt_dev *nvt, u8 val, u8 reg)
 {
@@ -224,74 +236,60 @@
 	pr_cont("\n");
 }
 
-/* detect hardware features */
-static int nvt_hw_detect(struct nvt_dev *nvt)
+static inline const char *nvt_find_chip(struct nvt_dev *nvt, int id)
 {
-	unsigned long flags;
-	u8 chip_major, chip_minor;
-	char chip_id[12];
-	bool chip_unknown = false;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(nvt_chips); i++)
+		if ((id & SIO_ID_MASK) == nvt_chips[i].chip_ver) {
+			nvt->chip_ver = nvt_chips[i].chip_ver;
+			return nvt_chips[i].name;
+		}
+
+	return NULL;
+}
+
+
+/* detect hardware features */
+static void nvt_hw_detect(struct nvt_dev *nvt)
+{
+	const char *chip_name;
+	int chip_id;
 
 	nvt_efm_enable(nvt);
 
 	/* Check if we're wired for the alternate EFER setup */
-	chip_major = nvt_cr_read(nvt, CR_CHIP_ID_HI);
-	if (chip_major == 0xff) {
+	nvt->chip_major = nvt_cr_read(nvt, CR_CHIP_ID_HI);
+	if (nvt->chip_major == 0xff) {
 		nvt->cr_efir = CR_EFIR2;
 		nvt->cr_efdr = CR_EFDR2;
 		nvt_efm_enable(nvt);
-		chip_major = nvt_cr_read(nvt, CR_CHIP_ID_HI);
+		nvt->chip_major = nvt_cr_read(nvt, CR_CHIP_ID_HI);
 	}
 
-	chip_minor = nvt_cr_read(nvt, CR_CHIP_ID_LO);
+	nvt->chip_minor = nvt_cr_read(nvt, CR_CHIP_ID_LO);
 
-	/* these are the known working chip revisions... */
-	switch (chip_major) {
-	case CHIP_ID_HIGH_667:
-		strcpy(chip_id, "w83667hg\0");
-		if (chip_minor != CHIP_ID_LOW_667)
-			chip_unknown = true;
-		break;
-	case CHIP_ID_HIGH_677B:
-		strcpy(chip_id, "w83677hg\0");
-		if (chip_minor != CHIP_ID_LOW_677B2 &&
-		    chip_minor != CHIP_ID_LOW_677B3)
-			chip_unknown = true;
-		break;
-	case CHIP_ID_HIGH_677C:
-		strcpy(chip_id, "w83677hg-c\0");
-		if (chip_minor != CHIP_ID_LOW_677C)
-			chip_unknown = true;
-		break;
-	default:
-		strcpy(chip_id, "w836x7hg\0");
-		chip_unknown = true;
-		break;
-	}
+	chip_id = nvt->chip_major << 8 | nvt->chip_minor;
+	chip_name = nvt_find_chip(nvt, chip_id);
 
 	/* warn, but still let the driver load, if we don't know this chip */
-	if (chip_unknown)
-		nvt_pr(KERN_WARNING, "%s: unknown chip, id: 0x%02x 0x%02x, "
-		       "it may not work...", chip_id, chip_major, chip_minor);
+	if (!chip_name)
+		dev_warn(&nvt->pdev->dev,
+			 "unknown chip, id: 0x%02x 0x%02x, it may not work...",
+			 nvt->chip_major, nvt->chip_minor);
 	else
-		nvt_dbg("%s: chip id: 0x%02x 0x%02x",
-			chip_id, chip_major, chip_minor);
+		dev_info(&nvt->pdev->dev,
+			 "found %s or compatible: chip id: 0x%02x 0x%02x",
+			 chip_name, nvt->chip_major, nvt->chip_minor);
 
 	nvt_efm_disable(nvt);
-
-	spin_lock_irqsave(&nvt->nvt_lock, flags);
-	nvt->chip_major = chip_major;
-	nvt->chip_minor = chip_minor;
-	spin_unlock_irqrestore(&nvt->nvt_lock, flags);
-
-	return 0;
 }
 
 static void nvt_cir_ldev_init(struct nvt_dev *nvt)
 {
 	u8 val, psreg, psmask, psval;
 
-	if (nvt->chip_major == CHIP_ID_HIGH_667) {
+	if (is_w83667hg(nvt)) {
 		psreg = CR_MULTIFUNC_PIN_SEL;
 		psmask = MULTIFUNC_PIN_SEL_MASK;
 		psval = MULTIFUNC_ENABLE_CIR | MULTIFUNC_ENABLE_CIRWB;
@@ -485,8 +483,9 @@
 	duration *= SAMPLE_PERIOD;
 
 	if (!count || !duration) {
-		nvt_pr(KERN_NOTICE, "Unable to determine carrier! (c:%u, d:%u)",
-		       count, duration);
+		dev_notice(&nvt->pdev->dev,
+			   "Unable to determine carrier! (c:%u, d:%u)",
+			   count, duration);
 		return 0;
 	}
 
@@ -661,7 +660,7 @@
 
 static void nvt_handle_rx_fifo_overrun(struct nvt_dev *nvt)
 {
-	nvt_pr(KERN_WARNING, "RX FIFO overrun detected, flushing data!");
+	dev_warn(&nvt->pdev->dev, "RX FIFO overrun detected, flushing data!");
 
 	nvt->pkts = 0;
 	nvt_clear_cir_fifo(nvt);
@@ -719,7 +718,7 @@
 
 static void nvt_cir_log_irqs(u8 status, u8 iren)
 {
-	nvt_pr(KERN_INFO, "IRQ 0x%02x (IREN 0x%02x) :%s%s%s%s%s%s%s%s%s",
+	nvt_dbg("IRQ 0x%02x (IREN 0x%02x) :%s%s%s%s%s%s%s%s%s",
 		status, iren,
 		status & CIR_IRSTS_RDR	? " RDR"	: "",
 		status & CIR_IRSTS_RTR	? " RTR"	: "",
@@ -779,7 +778,7 @@
 	if (!status) {
 		nvt_dbg_verbose("%s exiting, IRSTS 0x0", __func__);
 		nvt_cir_reg_write(nvt, 0xff, CIR_IRSTS);
-		return IRQ_RETVAL(IRQ_NONE);
+		return IRQ_NONE;
 	}
 
 	/* ack/clear all irq flags we've got */
@@ -790,11 +789,10 @@
 	iren = nvt_cir_reg_read(nvt, CIR_IREN);
 	if (!iren) {
 		nvt_dbg_verbose("%s exiting, CIR not enabled", __func__);
-		return IRQ_RETVAL(IRQ_NONE);
+		return IRQ_NONE;
 	}
 
-	if (debug)
-		nvt_cir_log_irqs(status, iren);
+	nvt_cir_log_irqs(status, iren);
 
 	if (status & CIR_IRSTS_RTR) {
 		/* FIXME: add code for study/learn mode */
@@ -853,7 +851,7 @@
 	}
 
 	nvt_dbg_verbose("%s done", __func__);
-	return IRQ_RETVAL(IRQ_HANDLED);
+	return IRQ_HANDLED;
 }
 
 /* Interrupt service routine for CIR Wake */
@@ -867,7 +865,7 @@
 
 	status = nvt_cir_wake_reg_read(nvt, CIR_WAKE_IRSTS);
 	if (!status)
-		return IRQ_RETVAL(IRQ_NONE);
+		return IRQ_NONE;
 
 	if (status & CIR_WAKE_IRSTS_IR_PENDING)
 		nvt_clear_cir_wake_fifo(nvt);
@@ -879,7 +877,7 @@
 	iren = nvt_cir_wake_reg_read(nvt, CIR_WAKE_IREN);
 	if (!iren) {
 		nvt_dbg_wake("%s exiting, wake not enabled", __func__);
-		return IRQ_RETVAL(IRQ_HANDLED);
+		return IRQ_HANDLED;
 	}
 
 	if ((status & CIR_WAKE_IRSTS_PE) &&
@@ -896,7 +894,7 @@
 	}
 
 	nvt_dbg_wake("%s done", __func__);
-	return IRQ_RETVAL(IRQ_HANDLED);
+	return IRQ_HANDLED;
 }
 
 static void nvt_enable_cir(struct nvt_dev *nvt)
@@ -974,7 +972,7 @@
 	struct rc_dev *rdev;
 	int ret = -ENOMEM;
 
-	nvt = kzalloc(sizeof(struct nvt_dev), GFP_KERNEL);
+	nvt = devm_kzalloc(&pdev->dev, sizeof(struct nvt_dev), GFP_KERNEL);
 	if (!nvt)
 		return ret;
 
@@ -1026,9 +1024,7 @@
 
 	init_waitqueue_head(&nvt->tx.queue);
 
-	ret = nvt_hw_detect(nvt);
-	if (ret)
-		goto exit_free_dev_rdev;
+	nvt_hw_detect(nvt);
 
 	/* Initialize CIR & CIR Wake Logical Devices */
 	nvt_efm_enable(nvt);
@@ -1074,25 +1070,26 @@
 
 	ret = -EBUSY;
 	/* now claim resources */
-	if (!request_region(nvt->cir_addr,
+	if (!devm_request_region(&pdev->dev, nvt->cir_addr,
 			    CIR_IOREG_LENGTH, NVT_DRIVER_NAME))
 		goto exit_unregister_device;
 
-	if (request_irq(nvt->cir_irq, nvt_cir_isr, IRQF_SHARED,
-			NVT_DRIVER_NAME, (void *)nvt))
-		goto exit_release_cir_addr;
+	if (devm_request_irq(&pdev->dev, nvt->cir_irq, nvt_cir_isr,
+			     IRQF_SHARED, NVT_DRIVER_NAME, (void *)nvt))
+		goto exit_unregister_device;
 
-	if (!request_region(nvt->cir_wake_addr,
+	if (!devm_request_region(&pdev->dev, nvt->cir_wake_addr,
 			    CIR_IOREG_LENGTH, NVT_DRIVER_NAME))
-		goto exit_free_irq;
+		goto exit_unregister_device;
 
-	if (request_irq(nvt->cir_wake_irq, nvt_cir_wake_isr, IRQF_SHARED,
-			NVT_DRIVER_NAME, (void *)nvt))
-		goto exit_release_cir_wake_addr;
+	if (devm_request_irq(&pdev->dev, nvt->cir_wake_irq,
+			     nvt_cir_wake_isr, IRQF_SHARED,
+			     NVT_DRIVER_NAME, (void *)nvt))
+		goto exit_unregister_device;
 
 	device_init_wakeup(&pdev->dev, true);
 
-	nvt_pr(KERN_NOTICE, "driver has been successfully loaded\n");
+	dev_notice(&pdev->dev, "driver has been successfully loaded\n");
 	if (debug) {
 		cir_dump_regs(nvt);
 		cir_wake_dump_regs(nvt);
@@ -1100,18 +1097,11 @@
 
 	return 0;
 
-exit_release_cir_wake_addr:
-	release_region(nvt->cir_wake_addr, CIR_IOREG_LENGTH);
-exit_free_irq:
-	free_irq(nvt->cir_irq, nvt);
-exit_release_cir_addr:
-	release_region(nvt->cir_addr, CIR_IOREG_LENGTH);
 exit_unregister_device:
 	rc_unregister_device(rdev);
 	rdev = NULL;
 exit_free_dev_rdev:
 	rc_free_device(rdev);
-	kfree(nvt);
 
 	return ret;
 }
@@ -1129,15 +1119,7 @@
 	nvt_enable_wake(nvt);
 	spin_unlock_irqrestore(&nvt->nvt_lock, flags);
 
-	/* free resources */
-	free_irq(nvt->cir_irq, nvt);
-	free_irq(nvt->cir_wake_irq, nvt);
-	release_region(nvt->cir_addr, CIR_IOREG_LENGTH);
-	release_region(nvt->cir_wake_addr, CIR_IOREG_LENGTH);
-
 	rc_unregister_device(nvt->rdev);
-
-	kfree(nvt);
 }
 
 static int nvt_suspend(struct pnp_dev *pdev, pm_message_t state)
diff --git a/drivers/media/rc/nuvoton-cir.h b/drivers/media/rc/nuvoton-cir.h
index e1cf23c..0ad15d34 100644
--- a/drivers/media/rc/nuvoton-cir.h
+++ b/drivers/media/rc/nuvoton-cir.h
@@ -35,9 +35,6 @@
 static int debug;
 
 
-#define nvt_pr(level, text, ...) \
-	printk(level KBUILD_MODNAME ": " text, ## __VA_ARGS__)
-
 #define nvt_dbg(text, ...) \
 	if (debug) \
 		printk(KERN_DEBUG \
@@ -64,6 +61,21 @@
 #define TX_BUF_LEN 256
 #define RX_BUF_LEN 32
 
+#define SIO_ID_MASK 0xfff0
+
+enum nvt_chip_ver {
+	NVT_UNKNOWN	= 0,
+	NVT_W83667HG	= 0xa510,
+	NVT_6775F	= 0xb470,
+	NVT_6776F	= 0xc330,
+	NVT_6779D	= 0xc560
+};
+
+struct nvt_chip {
+	const char *name;
+	enum nvt_chip_ver chip_ver;
+};
+
 struct nvt_dev {
 	struct pnp_dev *pdev;
 	struct rc_dev *rdev;
@@ -93,6 +105,7 @@
 	int cir_irq;
 	int cir_wake_irq;
 
+	enum nvt_chip_ver chip_ver;
 	/* hardware id */
 	u8 chip_major;
 	u8 chip_minor;
@@ -326,15 +339,6 @@
 #define EFER_EFM_ENABLE		0x87
 #define EFER_EFM_DISABLE	0xaa
 
-/* Chip IDs found in CR_CHIP_ID_{HI,LO} */
-#define CHIP_ID_HIGH_667	0xa5
-#define CHIP_ID_HIGH_677B	0xb4
-#define CHIP_ID_HIGH_677C	0xc3
-#define CHIP_ID_LOW_667		0x13
-#define CHIP_ID_LOW_677B2	0x72
-#define CHIP_ID_LOW_677B3	0x73
-#define CHIP_ID_LOW_677C	0x33
-
 /* Config regs we need to care about */
 #define CR_SOFTWARE_RESET	0x02
 #define CR_LOGICAL_DEV_SEL	0x07
diff --git a/drivers/media/rc/rc-core-priv.h b/drivers/media/rc/rc-core-priv.h
index b68d4f76..7359f3d 100644
--- a/drivers/media/rc/rc-core-priv.h
+++ b/drivers/media/rc/rc-core-priv.h
@@ -167,75 +167,4 @@
  * loads the compiled decoders for their usage with IR raw events
  */
 
-/* from ir-nec-decoder.c */
-#ifdef CONFIG_IR_NEC_DECODER_MODULE
-#define load_nec_decode()	request_module_nowait("ir-nec-decoder")
-#else
-static inline void load_nec_decode(void) { }
-#endif
-
-/* from ir-rc5-decoder.c */
-#ifdef CONFIG_IR_RC5_DECODER_MODULE
-#define load_rc5_decode()	request_module_nowait("ir-rc5-decoder")
-#else
-static inline void load_rc5_decode(void) { }
-#endif
-
-/* from ir-rc6-decoder.c */
-#ifdef CONFIG_IR_RC6_DECODER_MODULE
-#define load_rc6_decode()	request_module_nowait("ir-rc6-decoder")
-#else
-static inline void load_rc6_decode(void) { }
-#endif
-
-/* from ir-jvc-decoder.c */
-#ifdef CONFIG_IR_JVC_DECODER_MODULE
-#define load_jvc_decode()	request_module_nowait("ir-jvc-decoder")
-#else
-static inline void load_jvc_decode(void) { }
-#endif
-
-/* from ir-sony-decoder.c */
-#ifdef CONFIG_IR_SONY_DECODER_MODULE
-#define load_sony_decode()	request_module_nowait("ir-sony-decoder")
-#else
-static inline void load_sony_decode(void) { }
-#endif
-
-/* from ir-sanyo-decoder.c */
-#ifdef CONFIG_IR_SANYO_DECODER_MODULE
-#define load_sanyo_decode()	request_module_nowait("ir-sanyo-decoder")
-#else
-static inline void load_sanyo_decode(void) { }
-#endif
-
-/* from ir-sharp-decoder.c */
-#ifdef CONFIG_IR_SHARP_DECODER_MODULE
-#define load_sharp_decode()	request_module_nowait("ir-sharp-decoder")
-#else
-static inline void load_sharp_decode(void) { }
-#endif
-
-/* from ir-mce_kbd-decoder.c */
-#ifdef CONFIG_IR_MCE_KBD_DECODER_MODULE
-#define load_mce_kbd_decode()	request_module_nowait("ir-mce_kbd-decoder")
-#else
-static inline void load_mce_kbd_decode(void) { }
-#endif
-
-/* from ir-lirc-codec.c */
-#ifdef CONFIG_IR_LIRC_CODEC_MODULE
-#define load_lirc_codec()	request_module_nowait("ir-lirc-codec")
-#else
-static inline void load_lirc_codec(void) { }
-#endif
-
-/* from ir-xmp-decoder.c */
-#ifdef CONFIG_IR_XMP_DECODER_MODULE
-#define load_xmp_decode()      request_module_nowait("ir-xmp-decoder")
-#else
-static inline void load_xmp_decode(void) { }
-#endif
-
-
 #endif /* _RC_CORE_PRIV */
diff --git a/drivers/media/rc/rc-ir-raw.c b/drivers/media/rc/rc-ir-raw.c
index ad26052..c69807f 100644
--- a/drivers/media/rc/rc-ir-raw.c
+++ b/drivers/media/rc/rc-ir-raw.c
@@ -59,7 +59,9 @@
 
 		mutex_lock(&ir_raw_handler_lock);
 		list_for_each_entry(handler, &ir_raw_handler_list, list)
-			handler->decode(raw->dev, ev);
+			if (raw->dev->enabled_protocols & handler->protocols ||
+			    !handler->protocols)
+				handler->decode(raw->dev, ev);
 		raw->prev_ev = ev;
 		mutex_unlock(&ir_raw_handler_lock);
 	}
@@ -246,6 +248,14 @@
 	return 0;
 }
 
+static void ir_raw_disable_protocols(struct rc_dev *dev, u64 protocols)
+{
+	mutex_lock(&dev->lock);
+	dev->enabled_protocols &= ~protocols;
+	dev->enabled_wakeup_protocols &= ~protocols;
+	mutex_unlock(&dev->lock);
+}
+
 /*
  * Used to (un)register raw event clients
  */
@@ -337,33 +347,16 @@
 void ir_raw_handler_unregister(struct ir_raw_handler *ir_raw_handler)
 {
 	struct ir_raw_event_ctrl *raw;
+	u64 protocols = ir_raw_handler->protocols;
 
 	mutex_lock(&ir_raw_handler_lock);
 	list_del(&ir_raw_handler->list);
-	if (ir_raw_handler->raw_unregister)
-		list_for_each_entry(raw, &ir_raw_client_list, list)
+	list_for_each_entry(raw, &ir_raw_client_list, list) {
+		ir_raw_disable_protocols(raw->dev, protocols);
+		if (ir_raw_handler->raw_unregister)
 			ir_raw_handler->raw_unregister(raw->dev);
-	available_protocols &= ~ir_raw_handler->protocols;
+	}
+	available_protocols &= ~protocols;
 	mutex_unlock(&ir_raw_handler_lock);
 }
 EXPORT_SYMBOL(ir_raw_handler_unregister);
-
-void ir_raw_init(void)
-{
-	/* Load the decoder modules */
-
-	load_nec_decode();
-	load_rc5_decode();
-	load_rc6_decode();
-	load_jvc_decode();
-	load_sony_decode();
-	load_sanyo_decode();
-	load_sharp_decode();
-	load_mce_kbd_decode();
-	load_lirc_codec();
-	load_xmp_decode();
-
-	/* If needed, we may later add some init code. In this case,
-	   it is needed to change the CONFIG_MODULE test at rc-core.h
-	 */
-}
diff --git a/drivers/media/rc/rc-main.c b/drivers/media/rc/rc-main.c
index 3f0f71a..1042fa3 100644
--- a/drivers/media/rc/rc-main.c
+++ b/drivers/media/rc/rc-main.c
@@ -61,7 +61,7 @@
 	struct rc_map_list *map;
 
 	map = seek_rc_map(name);
-#ifdef MODULE
+#ifdef CONFIG_MODULES
 	if (!map) {
 		int rc = request_module("%s", name);
 		if (rc < 0) {
@@ -777,30 +777,31 @@
  * used by the sysfs protocols file. Note that the order
  * of the entries is relevant.
  */
-static struct {
+static const struct {
 	u64	type;
-	char	*name;
+	const char	*name;
+	const char	*module_name;
 } proto_names[] = {
-	{ RC_BIT_NONE,		"none"		},
-	{ RC_BIT_OTHER,		"other"		},
-	{ RC_BIT_UNKNOWN,	"unknown"	},
+	{ RC_BIT_NONE,		"none",		NULL			},
+	{ RC_BIT_OTHER,		"other",	NULL			},
+	{ RC_BIT_UNKNOWN,	"unknown",	NULL			},
 	{ RC_BIT_RC5 |
-	  RC_BIT_RC5X,		"rc-5"		},
-	{ RC_BIT_NEC,		"nec"		},
+	  RC_BIT_RC5X,		"rc-5",		"ir-rc5-decoder"	},
+	{ RC_BIT_NEC,		"nec",		"ir-nec-decoder"	},
 	{ RC_BIT_RC6_0 |
 	  RC_BIT_RC6_6A_20 |
 	  RC_BIT_RC6_6A_24 |
 	  RC_BIT_RC6_6A_32 |
-	  RC_BIT_RC6_MCE,	"rc-6"		},
-	{ RC_BIT_JVC,		"jvc"		},
+	  RC_BIT_RC6_MCE,	"rc-6",		"ir-rc6-decoder"	},
+	{ RC_BIT_JVC,		"jvc",		"ir-jvc-decoder"	},
 	{ RC_BIT_SONY12 |
 	  RC_BIT_SONY15 |
-	  RC_BIT_SONY20,	"sony"		},
-	{ RC_BIT_RC5_SZ,	"rc-5-sz"	},
-	{ RC_BIT_SANYO,		"sanyo"		},
-	{ RC_BIT_SHARP,		"sharp"		},
-	{ RC_BIT_MCE_KBD,	"mce_kbd"	},
-	{ RC_BIT_XMP,		"xmp"		},
+	  RC_BIT_SONY20,	"sony",		"ir-sony-decoder"	},
+	{ RC_BIT_RC5_SZ,	"rc-5-sz",	"ir-rc5-decoder"	},
+	{ RC_BIT_SANYO,		"sanyo",	"ir-sanyo-decoder"	},
+	{ RC_BIT_SHARP,		"sharp",	"ir-sharp-decoder"	},
+	{ RC_BIT_MCE_KBD,	"mce_kbd",	"ir-mce_kbd-decoder"	},
+	{ RC_BIT_XMP,		"xmp",		"ir-xmp-decoder"	},
 };
 
 /**
@@ -979,6 +980,48 @@
 	return count;
 }
 
+static void ir_raw_load_modules(u64 *protocols)
+
+{
+	u64 available;
+	int i, ret;
+
+	for (i = 0; i < ARRAY_SIZE(proto_names); i++) {
+		if (proto_names[i].type == RC_BIT_NONE ||
+		    proto_names[i].type & (RC_BIT_OTHER | RC_BIT_UNKNOWN))
+			continue;
+
+		available = ir_raw_get_allowed_protocols();
+		if (!(*protocols & proto_names[i].type & ~available))
+			continue;
+
+		if (!proto_names[i].module_name) {
+			pr_err("Can't enable IR protocol %s\n",
+			       proto_names[i].name);
+			*protocols &= ~proto_names[i].type;
+			continue;
+		}
+
+		ret = request_module("%s", proto_names[i].module_name);
+		if (ret < 0) {
+			pr_err("Couldn't load IR protocol module %s\n",
+			       proto_names[i].module_name);
+			*protocols &= ~proto_names[i].type;
+			continue;
+		}
+		msleep(20);
+		available = ir_raw_get_allowed_protocols();
+		if (!(*protocols & proto_names[i].type & ~available))
+			continue;
+
+		pr_err("Loaded IR protocol module %s, \
+		       but protocol %s still not available\n",
+		       proto_names[i].module_name,
+		       proto_names[i].name);
+		*protocols &= ~proto_names[i].type;
+	}
+}
+
 /**
  * store_protocols() - changes the current/wakeup IR protocol(s)
  * @device:	the device descriptor
@@ -1045,6 +1088,9 @@
 		goto out;
 	}
 
+	if (dev->driver_type == RC_DRIVER_IR_RAW)
+		ir_raw_load_modules(&new_protocols);
+
 	if (new_protocols != old_protocols) {
 		*current_protocols = new_protocols;
 		IR_dprintk(1, "Protocols changed to 0x%llx\n",
@@ -1420,17 +1466,13 @@
 	dev->input_dev->rep[REP_PERIOD] = 125;
 
 	path = kobject_get_path(&dev->dev.kobj, GFP_KERNEL);
-	printk(KERN_INFO "%s: %s as %s\n",
-		dev_name(&dev->dev),
-		dev->input_name ? dev->input_name : "Unspecified device",
-		path ? path : "N/A");
+	dev_info(&dev->dev, "%s as %s\n",
+		dev->input_name ?: "Unspecified device", path ?: "N/A");
 	kfree(path);
 
 	if (dev->driver_type == RC_DRIVER_IR_RAW) {
-		/* Load raw decoders, if they aren't already */
 		if (!raw_init) {
-			IR_dprintk(1, "Loading raw decoders\n");
-			ir_raw_init();
+			request_module_nowait("ir-lirc-codec");
 			raw_init = true;
 		}
 		/* calls ir_register_device so unlock mutex here*/
diff --git a/drivers/media/rc/st_rc.c b/drivers/media/rc/st_rc.c
index 37d0401..1fa0c9d 100644
--- a/drivers/media/rc/st_rc.c
+++ b/drivers/media/rc/st_rc.c
@@ -16,6 +16,7 @@
 #include <linux/reset.h>
 #include <media/rc-core.h>
 #include <linux/pinctrl/consumer.h>
+#include <linux/pm_wakeirq.h>
 
 struct st_rc_device {
 	struct device			*dev;
@@ -190,6 +191,9 @@
 static int st_rc_remove(struct platform_device *pdev)
 {
 	struct st_rc_device *rc_dev = platform_get_drvdata(pdev);
+
+	dev_pm_clear_wake_irq(&pdev->dev);
+	device_init_wakeup(&pdev->dev, false);
 	clk_disable_unprepare(rc_dev->sys_clock);
 	rc_unregister_device(rc_dev->rdev);
 	return 0;
@@ -298,22 +302,22 @@
 	rdev->map_name = RC_MAP_LIRC;
 	rdev->input_name = "ST Remote Control Receiver";
 
-	/* enable wake via this device */
-	device_set_wakeup_capable(dev, true);
-	device_set_wakeup_enable(dev, true);
-
 	ret = rc_register_device(rdev);
 	if (ret < 0)
 		goto clkerr;
 
 	rc_dev->rdev = rdev;
 	if (devm_request_irq(dev, rc_dev->irq, st_rc_rx_interrupt,
-			IRQF_NO_SUSPEND, IR_ST_NAME, rc_dev) < 0) {
+			     0, IR_ST_NAME, rc_dev) < 0) {
 		dev_err(dev, "IRQ %d register failed\n", rc_dev->irq);
 		ret = -EINVAL;
 		goto rcerr;
 	}
 
+	/* enable wake via this device */
+	device_init_wakeup(dev, true);
+	dev_pm_set_wake_irq(dev, rc_dev->irq);
+
 	/**
 	 * for LIRC_MODE_MODE2 or LIRC_MODE_PULSE or LIRC_MODE_RAW
 	 * lircd expects a long space first before a signal train to sync.
diff --git a/drivers/media/rc/streamzap.c b/drivers/media/rc/streamzap.c
index 5a17cb8..815243c 100644
--- a/drivers/media/rc/streamzap.c
+++ b/drivers/media/rc/streamzap.c
@@ -34,6 +34,7 @@
 #include <linux/device.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/ktime.h>
 #include <linux/usb.h>
 #include <linux/usb/input.h>
 #include <media/rc-core.h>
@@ -96,8 +97,8 @@
 	/* sum of signal lengths received since signal start */
 	unsigned long		sum;
 	/* start time of signal; necessary for gap tracking */
-	struct timeval		signal_last;
-	struct timeval		signal_start;
+	ktime_t			signal_last;
+	ktime_t			signal_start;
 	bool			timeout_enabled;
 
 	char			name[128];
@@ -136,20 +137,18 @@
 	DEFINE_IR_RAW_EVENT(rawir);
 
 	if (sz->idle) {
-		long deltv;
+		int delta;
 
 		sz->signal_last = sz->signal_start;
-		do_gettimeofday(&sz->signal_start);
+		sz->signal_start = ktime_get_real();
 
-		deltv = sz->signal_start.tv_sec - sz->signal_last.tv_sec;
+		delta = ktime_us_delta(sz->signal_start, sz->signal_last);
 		rawir.pulse = false;
-		if (deltv > 15) {
+		if (delta > (15 * USEC_PER_SEC)) {
 			/* really long time */
 			rawir.duration = IR_MAX_DURATION;
 		} else {
-			rawir.duration = (int)(deltv * 1000000 +
-				sz->signal_start.tv_usec -
-				sz->signal_last.tv_usec);
+			rawir.duration = delta;
 			rawir.duration -= sz->sum;
 			rawir.duration = US_TO_NS(rawir.duration);
 			rawir.duration = (rawir.duration > IR_MAX_DURATION) ?
@@ -428,7 +427,7 @@
 	sz->max_timeout = US_TO_NS(SZ_TIMEOUT * SZ_RESOLUTION);
 	#endif
 
-	do_gettimeofday(&sz->signal_start);
+	sz->signal_start = ktime_get_real();
 
 	/* Complete final initialisations */
 	usb_fill_int_urb(sz->urb_in, usbdev, pipe, sz->buf_in,
diff --git a/drivers/media/rc/sunxi-cir.c b/drivers/media/rc/sunxi-cir.c
index 7830aef..40f7768 100644
--- a/drivers/media/rc/sunxi-cir.c
+++ b/drivers/media/rc/sunxi-cir.c
@@ -153,6 +153,8 @@
 	if (!ir)
 		return -ENOMEM;
 
+	spin_lock_init(&ir->ir_lock);
+
 	if (of_device_is_compatible(dn, "allwinner,sun5i-a13-ir"))
 		ir->fifo_size = 64;
 	else
diff --git a/drivers/media/tuners/max2165.c b/drivers/media/tuners/max2165.c
index 95ed46f..353b178 100644
--- a/drivers/media/tuners/max2165.c
+++ b/drivers/media/tuners/max2165.c
@@ -385,7 +385,7 @@
 	.info = {
 		.name           = "Maxim MAX2165",
 		.frequency_min  = 470000000,
-		.frequency_max  = 780000000,
+		.frequency_max  = 862000000,
 		.frequency_step =     50000,
 	},
 
diff --git a/drivers/media/tuners/mt2063.c b/drivers/media/tuners/mt2063.c
index 9e9c5eb..6457ac9 100644
--- a/drivers/media/tuners/mt2063.c
+++ b/drivers/media/tuners/mt2063.c
@@ -225,7 +225,6 @@
 	const struct mt2063_config *config;
 	struct dvb_tuner_ops ops;
 	struct dvb_frontend *frontend;
-	struct tuner_state status;
 
 	u32 frequency;
 	u32 srate;
diff --git a/drivers/media/tuners/si2157.c b/drivers/media/tuners/si2157.c
index ce157ed..0e1ca2b 100644
--- a/drivers/media/tuners/si2157.c
+++ b/drivers/media/tuners/si2157.c
@@ -168,6 +168,7 @@
 		len = fw->data[fw->size - remaining];
 		if (len > SI2157_ARGLEN) {
 			dev_err(&client->dev, "Bad firmware length\n");
+			ret = -EINVAL;
 			goto err_release_firmware;
 		}
 		memcpy(cmd.args, &fw->data[(fw->size - remaining) + 1], len);
diff --git a/drivers/media/usb/airspy/airspy.c b/drivers/media/usb/airspy/airspy.c
index 565a593..0d4ac59 100644
--- a/drivers/media/usb/airspy/airspy.c
+++ b/drivers/media/usb/airspy/airspy.c
@@ -316,7 +316,7 @@
 		len = airspy_convert_stream(s, ptr, urb->transfer_buffer,
 				urb->actual_length);
 		vb2_set_plane_payload(&fbuf->vb.vb2_buf, 0, len);
-		v4l2_get_timestamp(&fbuf->vb.timestamp);
+		fbuf->vb.vb2_buf.timestamp = ktime_get_ns();
 		fbuf->vb.sequence = s->sequence++;
 		vb2_buffer_done(&fbuf->vb.vb2_buf, VB2_BUF_STATE_DONE);
 	}
@@ -488,7 +488,7 @@
 
 /* Videobuf2 operations */
 static int airspy_queue_setup(struct vb2_queue *vq,
-		const void *parg, unsigned int *nbuffers,
+		unsigned int *nbuffers,
 		unsigned int *nplanes, unsigned int sizes[], void *alloc_ctxs[])
 {
 	struct airspy *s = vb2_get_drv_priv(vq);
diff --git a/drivers/media/usb/as102/as102_fw.c b/drivers/media/usb/as102/as102_fw.c
index 07d08c4..5a28ce3 100644
--- a/drivers/media/usb/as102/as102_fw.c
+++ b/drivers/media/usb/as102/as102_fw.c
@@ -198,6 +198,7 @@
 	pr_info("%s: firmware: %s loaded with success\n",
 		DRIVER_NAME, fw1);
 	release_firmware(firmware);
+	firmware = NULL;
 
 	/* wait for boot to complete */
 	mdelay(100);
diff --git a/drivers/media/usb/au0828/au0828-vbi.c b/drivers/media/usb/au0828/au0828-vbi.c
index 130c8b4..b4efc10 100644
--- a/drivers/media/usb/au0828/au0828-vbi.c
+++ b/drivers/media/usb/au0828/au0828-vbi.c
@@ -30,23 +30,17 @@
 
 /* ------------------------------------------------------------------ */
 
-static int vbi_queue_setup(struct vb2_queue *vq, const void *parg,
+static int vbi_queue_setup(struct vb2_queue *vq,
 			   unsigned int *nbuffers, unsigned int *nplanes,
 			   unsigned int sizes[], void *alloc_ctxs[])
 {
-	const struct v4l2_format *fmt = parg;
 	struct au0828_dev *dev = vb2_get_drv_priv(vq);
-	unsigned long img_size = dev->vbi_width * dev->vbi_height * 2;
-	unsigned long size;
+	unsigned long size = dev->vbi_width * dev->vbi_height * 2;
 
-	size = fmt ? (fmt->fmt.vbi.samples_per_line *
-		(fmt->fmt.vbi.count[0] + fmt->fmt.vbi.count[1])) : img_size;
-	if (size < img_size)
-		return -EINVAL;
-
+	if (*nplanes)
+		return sizes[0] < size ? -EINVAL : 0;
 	*nplanes = 1;
 	sizes[0] = size;
-
 	return 0;
 }
 
diff --git a/drivers/media/usb/au0828/au0828-video.c b/drivers/media/usb/au0828/au0828-video.c
index 45c622e..0a725a1 100644
--- a/drivers/media/usb/au0828/au0828-video.c
+++ b/drivers/media/usb/au0828/au0828-video.c
@@ -314,7 +314,7 @@
 		vb->sequence = dev->vbi_frame_count++;
 
 	vb->field = V4L2_FIELD_INTERLACED;
-	v4l2_get_timestamp(&vb->timestamp);
+	vb->vb2_buf.timestamp = ktime_get_ns();
 	vb2_buffer_done(&vb->vb2_buf, VB2_BUF_STATE_DONE);
 }
 
@@ -638,19 +638,15 @@
 	return rc;
 }
 
-static int queue_setup(struct vb2_queue *vq, const void *parg,
+static int queue_setup(struct vb2_queue *vq,
 		       unsigned int *nbuffers, unsigned int *nplanes,
 		       unsigned int sizes[], void *alloc_ctxs[])
 {
-	const struct v4l2_format *fmt = parg;
 	struct au0828_dev *dev = vb2_get_drv_priv(vq);
-	unsigned long img_size = dev->height * dev->bytesperline;
-	unsigned long size;
+	unsigned long size = dev->height * dev->bytesperline;
 
-	size = fmt ? fmt->fmt.pix.sizeimage : img_size;
-	if (size < img_size)
-		return -EINVAL;
-
+	if (*nplanes)
+		return sizes[0] < size ? -EINVAL : 0;
 	*nplanes = 1;
 	sizes[0] = size;
 
diff --git a/drivers/media/usb/cpia2/cpia2_usb.c b/drivers/media/usb/cpia2/cpia2_usb.c
index 351a78a..c1aa1ab2 100644
--- a/drivers/media/usb/cpia2/cpia2_usb.c
+++ b/drivers/media/usb/cpia2/cpia2_usb.c
@@ -890,8 +890,7 @@
 		DBG("Wakeup waiting processes\n");
 		cam->curbuff->status = FRAME_READY;
 		cam->curbuff->length = 0;
-		if (waitqueue_active(&cam->wq_stream))
-			wake_up_interruptible(&cam->wq_stream);
+		wake_up_interruptible(&cam->wq_stream);
 	}
 
 	DBG("Releasing interface\n");
diff --git a/drivers/media/usb/cx231xx/cx231xx-417.c b/drivers/media/usb/cx231xx/cx231xx-417.c
index 47a98a2..48643b9 100644
--- a/drivers/media/usb/cx231xx/cx231xx-417.c
+++ b/drivers/media/usb/cx231xx/cx231xx-417.c
@@ -37,7 +37,7 @@
 #include <media/v4l2-common.h>
 #include <media/v4l2-ioctl.h>
 #include <media/v4l2-event.h>
-#include <media/cx2341x.h>
+#include <media/drv-intf/cx2341x.h>
 #include <media/tuner.h>
 
 #define CX231xx_FIRM_IMAGE_SIZE 376836
@@ -1492,6 +1492,27 @@
 
 /* ------------------------------------------------------------------ */
 
+static int vidioc_cropcap(struct file *file, void *priv,
+			  struct v4l2_cropcap *cc)
+{
+	struct cx231xx_fh *fh = priv;
+	struct cx231xx *dev = fh->dev;
+	bool is_50hz = dev->encodernorm.id & V4L2_STD_625_50;
+
+	if (cc->type != V4L2_BUF_TYPE_VIDEO_CAPTURE)
+		return -EINVAL;
+
+	cc->bounds.left = 0;
+	cc->bounds.top = 0;
+	cc->bounds.width = dev->ts1.width;
+	cc->bounds.height = dev->ts1.height;
+	cc->defrect = cc->bounds;
+	cc->pixelaspect.numerator = is_50hz ? 54 : 11;
+	cc->pixelaspect.denominator = is_50hz ? 59 : 10;
+
+	return 0;
+}
+
 static int vidioc_g_std(struct file *file, void *fh0, v4l2_std_id *norm)
 {
 	struct cx231xx_fh  *fh  = file->private_data;
@@ -1834,6 +1855,7 @@
 	.vidioc_g_input		 = cx231xx_g_input,
 	.vidioc_s_input		 = cx231xx_s_input,
 	.vidioc_s_ctrl		 = vidioc_s_ctrl,
+	.vidioc_cropcap		 = vidioc_cropcap,
 	.vidioc_querycap	 = cx231xx_querycap,
 	.vidioc_enum_fmt_vid_cap = vidioc_enum_fmt_vid_cap,
 	.vidioc_g_fmt_vid_cap	 = vidioc_g_fmt_vid_cap,
@@ -1901,7 +1923,7 @@
 	return 0;
 }
 
-static struct cx2341x_handler_ops cx231xx_ops = {
+static const struct cx2341x_handler_ops cx231xx_ops = {
 	/* needed for the video clock freq */
 	.s_audio_sampling_freq = cx231xx_s_audio_sampling_freq,
 	/* needed for setting up the video resolution */
diff --git a/drivers/media/usb/cx231xx/cx231xx-cards.c b/drivers/media/usb/cx231xx/cx231xx-cards.c
index 4a117a5..89dc695 100644
--- a/drivers/media/usb/cx231xx/cx231xx-cards.c
+++ b/drivers/media/usb/cx231xx/cx231xx-cards.c
@@ -30,7 +30,7 @@
 #include <media/tveeprom.h>
 #include <media/v4l2-common.h>
 
-#include <media/cx25840.h>
+#include <media/drv-intf/cx25840.h>
 #include "dvb-usb-ids.h"
 #include "xc5000.h"
 #include "tda18271.h"
@@ -352,7 +352,7 @@
 		.agc_analog_digital_select_gpio = 0x0c,
 		.gpio_pin_status_mask = 0x4001000,
 		.tuner_i2c_master = I2C_1_MUX_1,
-		.demod_i2c_master = I2C_2,
+		.demod_i2c_master = I2C_1_MUX_1,
 		.has_dvb = 1,
 		.demod_addr = 0x0e,
 		.norm = V4L2_STD_NTSC,
@@ -713,7 +713,7 @@
 		.agc_analog_digital_select_gpio = 0x0c,
 		.gpio_pin_status_mask = 0x4001000,
 		.tuner_i2c_master = I2C_1_MUX_3,
-		.demod_i2c_master = I2C_2,
+		.demod_i2c_master = I2C_1_MUX_3,
 		.has_dvb = 1,
 		.demod_addr = 0x0e,
 		.norm = V4L2_STD_PAL,
@@ -752,7 +752,7 @@
 		.agc_analog_digital_select_gpio = 0x0c,
 		.gpio_pin_status_mask = 0x4001000,
 		.tuner_i2c_master = I2C_1_MUX_3,
-		.demod_i2c_master = I2C_2,
+		.demod_i2c_master = I2C_1_MUX_3,
 		.has_dvb = 1,
 		.demod_addr = 0x0e,
 		.norm = V4L2_STD_PAL,
@@ -791,7 +791,7 @@
 		.agc_analog_digital_select_gpio = 0x0c,
 		.gpio_pin_status_mask = 0x4001000,
 		.tuner_i2c_master = I2C_1_MUX_3,
-		.demod_i2c_master = I2C_2,
+		.demod_i2c_master = I2C_1_MUX_3,
 		.has_dvb = 1,
 		.demod_addr = 0x0e,
 		.norm = V4L2_STD_NTSC,
diff --git a/drivers/media/usb/cx231xx/cx231xx-core.c b/drivers/media/usb/cx231xx/cx231xx-core.c
index a2fd49b..f497888 100644
--- a/drivers/media/usb/cx231xx/cx231xx-core.c
+++ b/drivers/media/usb/cx231xx/cx231xx-core.c
@@ -914,6 +914,7 @@
  */
 void cx231xx_uninit_bulk(struct cx231xx *dev)
 {
+	struct cx231xx_dmaqueue *dma_q = &dev->video_mode.vidq;
 	struct urb *urb;
 	int i;
 
@@ -931,7 +932,7 @@
 			if (dev->video_mode.bulk_ctl.transfer_buffer[i]) {
 				usb_free_coherent(dev->udev,
 						urb->transfer_buffer_length,
-						dev->video_mode.isoc_ctl.
+						dev->video_mode.bulk_ctl.
 						transfer_buffer[i],
 						urb->transfer_dma);
 			}
@@ -943,10 +944,12 @@
 
 	kfree(dev->video_mode.bulk_ctl.urb);
 	kfree(dev->video_mode.bulk_ctl.transfer_buffer);
+	kfree(dma_q->p_left_data);
 
 	dev->video_mode.bulk_ctl.urb = NULL;
 	dev->video_mode.bulk_ctl.transfer_buffer = NULL;
 	dev->video_mode.bulk_ctl.num_bufs = 0;
+	dma_q->p_left_data = NULL;
 
 	if (dev->mode_tv == 0)
 		cx231xx_capture_start(dev, 0, Raw_Video);
@@ -1196,6 +1199,16 @@
 				  sb_size, cx231xx_bulk_irq_callback, dma_q);
 	}
 
+	/* clear halt */
+	rc = usb_clear_halt(dev->udev, dev->video_mode.bulk_ctl.urb[0]->pipe);
+	if (rc < 0) {
+		dev_err(dev->dev,
+			"failed to clear USB bulk endpoint stall/halt condition (error=%i)\n",
+			rc);
+		cx231xx_uninit_bulk(dev);
+		return rc;
+	}
+
 	init_waitqueue_head(&dma_q->wq);
 
 	/* submit urbs and enables IRQ */
diff --git a/drivers/media/usb/cx231xx/cx231xx-dvb.c b/drivers/media/usb/cx231xx/cx231xx-dvb.c
index 66ee161..e3594b9 100644
--- a/drivers/media/usb/cx231xx/cx231xx-dvb.c
+++ b/drivers/media/usb/cx231xx/cx231xx-dvb.c
@@ -725,7 +725,7 @@
 
 		dev->dvb->frontend = dvb_attach(lgdt3305_attach,
 						&hcw_lgdt3305_config,
-						tuner_i2c);
+						demod_i2c);
 
 		if (dev->dvb->frontend == NULL) {
 			dev_err(dev->dev,
@@ -746,7 +746,7 @@
 
 		dev->dvb->frontend = dvb_attach(si2165_attach,
 			&hauppauge_930C_HD_1113xx_si2165_config,
-			tuner_i2c
+			demod_i2c
 			);
 
 		if (dev->dvb->frontend == NULL) {
@@ -779,7 +779,7 @@
 
 		dev->dvb->frontend = dvb_attach(si2165_attach,
 			&pctv_quatro_stick_1114xx_si2165_config,
-			tuner_i2c
+			demod_i2c
 			);
 
 		if (dev->dvb->frontend == NULL) {
@@ -835,7 +835,7 @@
 
 		dev->dvb->frontend = dvb_attach(lgdt3306a_attach,
 			&hauppauge_955q_lgdt3306a_config,
-			tuner_i2c
+			demod_i2c
 			);
 
 		if (dev->dvb->frontend == NULL) {
diff --git a/drivers/media/usb/cx231xx/cx231xx-vbi.c b/drivers/media/usb/cx231xx/cx231xx-vbi.c
index a08014d..15bb573 100644
--- a/drivers/media/usb/cx231xx/cx231xx-vbi.c
+++ b/drivers/media/usb/cx231xx/cx231xx-vbi.c
@@ -32,7 +32,7 @@
 
 #include <media/v4l2-common.h>
 #include <media/v4l2-ioctl.h>
-#include <media/msp3400.h>
+#include <media/drv-intf/msp3400.h>
 #include <media/tuner.h>
 
 #include "cx231xx-vbi.h"
diff --git a/drivers/media/usb/cx231xx/cx231xx-video.c b/drivers/media/usb/cx231xx/cx231xx-video.c
index d0d8f08..a70850f 100644
--- a/drivers/media/usb/cx231xx/cx231xx-video.c
+++ b/drivers/media/usb/cx231xx/cx231xx-video.c
@@ -36,7 +36,7 @@
 #include <media/v4l2-common.h>
 #include <media/v4l2-ioctl.h>
 #include <media/v4l2-event.h>
-#include <media/msp3400.h>
+#include <media/drv-intf/msp3400.h>
 #include <media/tuner.h>
 
 #include "dvb_frontend.h"
@@ -1444,6 +1444,7 @@
 {
 	struct cx231xx_fh *fh = priv;
 	struct cx231xx *dev = fh->dev;
+	bool is_50hz = dev->norm & V4L2_STD_625_50;
 
 	if (cc->type != V4L2_BUF_TYPE_VIDEO_CAPTURE)
 		return -EINVAL;
@@ -1453,8 +1454,8 @@
 	cc->bounds.width = dev->width;
 	cc->bounds.height = dev->height;
 	cc->defrect = cc->bounds;
-	cc->pixelaspect.numerator = 54;	/* 4:3 FIXME: remove magic numbers */
-	cc->pixelaspect.denominator = 59;
+	cc->pixelaspect.numerator = is_50hz ? 54 : 11;
+	cc->pixelaspect.denominator = is_50hz ? 59 : 10;
 
 	return 0;
 }
diff --git a/drivers/media/usb/cx231xx/cx231xx.h b/drivers/media/usb/cx231xx/cx231xx.h
index 54790fb..ec6d3f5 100644
--- a/drivers/media/usb/cx231xx/cx231xx.h
+++ b/drivers/media/usb/cx231xx/cx231xx.h
@@ -30,14 +30,14 @@
 #include <linux/mutex.h>
 #include <linux/usb.h>
 
-#include <media/cx2341x.h>
+#include <media/drv-intf/cx2341x.h>
 
 #include <media/videobuf-vmalloc.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-fh.h>
 #include <media/rc-core.h>
-#include <media/ir-kbd-i2c.h>
+#include <media/i2c/ir-kbd-i2c.h>
 #include <media/videobuf-dvb.h>
 
 #include "cx231xx-reg.h"
diff --git a/drivers/media/usb/dvb-usb-v2/Kconfig b/drivers/media/usb/dvb-usb-v2/Kconfig
index 9facc92..3dc8ef0 100644
--- a/drivers/media/usb/dvb-usb-v2/Kconfig
+++ b/drivers/media/usb/dvb-usb-v2/Kconfig
@@ -9,7 +9,7 @@
 	  <file:Documentation/dvb/README.dvb-usb>.
 
 	  For a complete list of supported USB devices see the LinuxTV DVB Wiki:
-	  <http://www.linuxtv.org/wiki/index.php/DVB_USB>
+	  <https://linuxtv.org/wiki/index.php/DVB_USB>
 
 	  Say Y if you own a USB DVB device.
 
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.c b/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.c
index ea37536..84f6de6 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.c
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.c
@@ -35,7 +35,7 @@
 struct mxl111sf_demod_state {
 	struct mxl111sf_state *mxl_state;
 
-	struct mxl111sf_demod_config *cfg;
+	const struct mxl111sf_demod_config *cfg;
 
 	struct dvb_frontend fe;
 };
@@ -579,7 +579,7 @@
 };
 
 struct dvb_frontend *mxl111sf_demod_attach(struct mxl111sf_state *mxl_state,
-					   struct mxl111sf_demod_config *cfg)
+				   const struct mxl111sf_demod_config *cfg)
 {
 	struct mxl111sf_demod_state *state = NULL;
 
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.h b/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.h
index 0bd83e5..7065aca 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.h
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.h
@@ -35,11 +35,11 @@
 #if IS_ENABLED(CONFIG_DVB_USB_MXL111SF)
 extern
 struct dvb_frontend *mxl111sf_demod_attach(struct mxl111sf_state *mxl_state,
-					   struct mxl111sf_demod_config *cfg);
+				   const struct mxl111sf_demod_config *cfg);
 #else
 static inline
 struct dvb_frontend *mxl111sf_demod_attach(struct mxl111sf_state *mxl_state,
-					   struct mxl111sf_demod_config *cfg)
+				   const struct mxl111sf_demod_config *cfg)
 {
 	printk(KERN_WARNING "%s: driver disabled by Kconfig\n", __func__);
 	return NULL;
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf.c b/drivers/media/usb/dvb-usb-v2/mxl111sf.c
index bec12b0..1710f90 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf.c
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf.c
@@ -288,9 +288,9 @@
 	err = mxl1x1sf_set_device_mode(state, adap_state->device_mode);
 
 	mxl_fail(err);
-	mxl111sf_enable_usb_output(state);
+	err = mxl111sf_enable_usb_output(state);
 	mxl_fail(err);
-	mxl1x1sf_top_master_ctrl(state, 1);
+	err = mxl1x1sf_top_master_ctrl(state, 1);
 	mxl_fail(err);
 
 	if ((MXL111SF_GPIO_MOD_DVBT != adap_state->gpio_mode) &&
@@ -731,7 +731,7 @@
 	return ret;
 }
 
-static struct mxl111sf_demod_config mxl_demod_config = {
+static const struct mxl111sf_demod_config mxl_demod_config = {
 	.read_reg        = mxl111sf_read_reg,
 	.write_reg       = mxl111sf_write_reg,
 	.program_regs    = mxl111sf_ctrl_program_regs,
diff --git a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
index 5a503a6..eb5787a 100644
--- a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
+++ b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
@@ -181,11 +181,17 @@
 			goto err_mutex_unlock;
 		} else if (msg[0].addr == 0x10) {
 			/* method 1 - integrated demod */
-			req.value = (msg[0].buf[0] << 8) | (msg[0].addr << 1);
-			req.index = CMD_DEMOD_RD | dev->page;
-			req.size = msg[1].len;
-			req.data = &msg[1].buf[0];
-			ret = rtl28xxu_ctrl_msg(d, &req);
+			if (msg[0].buf[0] == 0x00) {
+				/* return demod page from driver cache */
+				msg[1].buf[0] = dev->page;
+				ret = 0;
+			} else {
+				req.value = (msg[0].buf[0] << 8) | (msg[0].addr << 1);
+				req.index = CMD_DEMOD_RD | dev->page;
+				req.size = msg[1].len;
+				req.data = &msg[1].buf[0];
+				ret = rtl28xxu_ctrl_msg(d, &req);
+			}
 		} else if (msg[0].len < 2) {
 			/* method 2 - old I2C */
 			req.value = (msg[0].buf[0] << 8) | (msg[0].addr << 1);
diff --git a/drivers/media/usb/dvb-usb/Kconfig b/drivers/media/usb/dvb-usb/Kconfig
index 128eee6..f03b0b7 100644
--- a/drivers/media/usb/dvb-usb/Kconfig
+++ b/drivers/media/usb/dvb-usb/Kconfig
@@ -9,7 +9,7 @@
 	  <file:Documentation/dvb/README.dvb-usb>.
 
 	  For a complete list of supported USB devices see the LinuxTV DVB Wiki:
-	  <http://www.linuxtv.org/wiki/index.php/DVB_USB>
+	  <https://linuxtv.org/wiki/index.php/DVB_USB>
 
 	  Say Y if you own a USB DVB device.
 
diff --git a/drivers/media/usb/em28xx/em28xx-camera.c b/drivers/media/usb/em28xx/em28xx-camera.c
index ed0b3a8..b58acd3 100644
--- a/drivers/media/usb/em28xx/em28xx-camera.c
+++ b/drivers/media/usb/em28xx/em28xx-camera.c
@@ -21,7 +21,7 @@
 
 #include <linux/i2c.h>
 #include <media/soc_camera.h>
-#include <media/mt9v011.h>
+#include <media/i2c/mt9v011.h>
 #include <media/v4l2-clk.h>
 #include <media/v4l2-common.h>
 
@@ -322,7 +322,7 @@
 
 int em28xx_init_camera(struct em28xx *dev)
 {
-	char clk_name[V4L2_SUBDEV_NAME_SIZE];
+	char clk_name[V4L2_CLK_NAME_SIZE];
 	struct i2c_client *client = &dev->i2c_client[dev->def_i2c_bus];
 	struct i2c_adapter *adap = &dev->i2c_adap[dev->def_i2c_bus];
 	struct em28xx_v4l2 *v4l2 = dev->v4l2;
diff --git a/drivers/media/usb/em28xx/em28xx-cards.c b/drivers/media/usb/em28xx/em28xx-cards.c
index 3940046..a1b6ef5 100644
--- a/drivers/media/usb/em28xx/em28xx-cards.c
+++ b/drivers/media/usb/em28xx/em28xx-cards.c
@@ -30,10 +30,10 @@
 #include <linux/i2c.h>
 #include <linux/usb.h>
 #include <media/tuner.h>
-#include <media/msp3400.h>
-#include <media/saa7115.h>
-#include <media/tvp5150.h>
-#include <media/tvaudio.h>
+#include <media/drv-intf/msp3400.h>
+#include <media/i2c/saa7115.h>
+#include <media/i2c/tvp5150.h>
+#include <media/i2c/tvaudio.h>
 #include <media/i2c-addr.h>
 #include <media/tveeprom.h>
 #include <media/v4l2-common.h>
@@ -1051,8 +1051,12 @@
 	},
 	[EM2870_BOARD_TERRATEC_XS_MT2060] = {
 		.name         = "Terratec Cinergy T XS (MT2060)",
-		.valid        = EM28XX_BOARD_NOT_VALIDATED,
+		.xclk         = EM28XX_XCLK_IR_RC5_MODE |
+				EM28XX_XCLK_FREQUENCY_12MHZ,
+		.i2c_speed    = EM28XX_I2C_CLK_WAIT_ENABLE,
 		.tuner_type   = TUNER_ABSENT, /* MT2060 */
+		.has_dvb      = 1,
+		.tuner_gpio   = default_tuner_gpio,
 	},
 	[EM2870_BOARD_KWORLD_350U] = {
 		.name         = "Kworld 350 U DVB-T",
@@ -2368,7 +2372,7 @@
 	{ USB_DEVICE(0x0ccd, 0x0042),
 			.driver_info = EM2882_BOARD_TERRATEC_HYBRID_XS },
 	{ USB_DEVICE(0x0ccd, 0x0043),
-			.driver_info = EM2870_BOARD_TERRATEC_XS },
+			.driver_info = EM2870_BOARD_TERRATEC_XS_MT2060 },
 	{ USB_DEVICE(0x0ccd, 0x008e),	/* Cinergy HTC USB XS Rev. 1 */
 			.driver_info = EM2884_BOARD_TERRATEC_HTC_USB_XS },
 	{ USB_DEVICE(0x0ccd, 0x00ac),	/* Cinergy HTC USB XS Rev. 2 */
@@ -2471,6 +2475,8 @@
 			.driver_info = EM28178_BOARD_PCTV_461E },
 	{ USB_DEVICE(0x2013, 0x025f),
 			.driver_info = EM28178_BOARD_PCTV_292E },
+	{ USB_DEVICE(0x2040, 0x0264), /* Hauppauge WinTV-soloHD */
+			.driver_info = EM28178_BOARD_PCTV_292E },
 	{ USB_DEVICE(0x0413, 0x6f07),
 			.driver_info = EM2861_BOARD_LEADTEK_VC100 },
 	{ USB_DEVICE(0xeb1a, 0x8179),
diff --git a/drivers/media/usb/em28xx/em28xx-dvb.c b/drivers/media/usb/em28xx/em28xx-dvb.c
index 357be76..bf5c244 100644
--- a/drivers/media/usb/em28xx/em28xx-dvb.c
+++ b/drivers/media/usb/em28xx/em28xx-dvb.c
@@ -38,6 +38,7 @@
 #include "lgdt3305.h"
 #include "zl10353.h"
 #include "s5h1409.h"
+#include "mt2060.h"
 #include "mt352.h"
 #include "mt352_priv.h" /* FIXME */
 #include "tda1002x.h"
@@ -815,6 +816,10 @@
 	.parallel_ts = 1,
 };
 
+static struct mt2060_config em28xx_mt2060_config = {
+	.i2c_address = 0x60,
+};
+
 static struct qt1010_config em28xx_qt1010_config = {
 	.i2c_address = 0x62
 };
@@ -1142,6 +1147,16 @@
 			goto out_free;
 		}
 		break;
+	case EM2870_BOARD_TERRATEC_XS_MT2060:
+		dvb->fe[0] = dvb_attach(zl10353_attach,
+						&em28xx_zl10353_no_i2c_gate_dev,
+						&dev->i2c_adap[dev->def_i2c_bus]);
+		if (dvb->fe[0] != NULL) {
+			dvb_attach(mt2060_attach, dvb->fe[0],
+					&dev->i2c_adap[dev->def_i2c_bus],
+					&em28xx_mt2060_config, 1220);
+		}
+		break;
 	case EM2870_BOARD_KWORLD_355U:
 		dvb->fe[0] = dvb_attach(zl10353_attach,
 					   &em28xx_zl10353_no_i2c_gate_dev,
diff --git a/drivers/media/usb/em28xx/em28xx-vbi.c b/drivers/media/usb/em28xx/em28xx-vbi.c
index e23c285..fe94c92 100644
--- a/drivers/media/usb/em28xx/em28xx-vbi.c
+++ b/drivers/media/usb/em28xx/em28xx-vbi.c
@@ -31,26 +31,22 @@
 
 /* ------------------------------------------------------------------ */
 
-static int vbi_queue_setup(struct vb2_queue *vq, const void *parg,
+static int vbi_queue_setup(struct vb2_queue *vq,
 			   unsigned int *nbuffers, unsigned int *nplanes,
 			   unsigned int sizes[], void *alloc_ctxs[])
 {
-	const struct v4l2_format *fmt = parg;
 	struct em28xx *dev = vb2_get_drv_priv(vq);
 	struct em28xx_v4l2 *v4l2 = dev->v4l2;
-	unsigned long size;
+	unsigned long size = v4l2->vbi_width * v4l2->vbi_height * 2;
 
-	if (fmt)
-		size = fmt->fmt.pix.sizeimage;
-	else
-		size = v4l2->vbi_width * v4l2->vbi_height * 2;
-
-	if (0 == *nbuffers)
-		*nbuffers = 32;
 	if (*nbuffers < 2)
 		*nbuffers = 2;
-	if (*nbuffers > 32)
-		*nbuffers = 32;
+
+	if (*nplanes) {
+		if (sizes[0] < size)
+			return -EINVAL;
+		size = sizes[0];
+	}
 
 	*nplanes = 1;
 	sizes[0] = size;
diff --git a/drivers/media/usb/em28xx/em28xx-video.c b/drivers/media/usb/em28xx/em28xx-video.c
index 6a3cf34..0e86ff4 100644
--- a/drivers/media/usb/em28xx/em28xx-video.c
+++ b/drivers/media/usb/em28xx/em28xx-video.c
@@ -43,7 +43,7 @@
 #include <media/v4l2-ioctl.h>
 #include <media/v4l2-event.h>
 #include <media/v4l2-clk.h>
-#include <media/msp3400.h>
+#include <media/drv-intf/msp3400.h>
 #include <media/tuner.h>
 
 #define DRIVER_AUTHOR "Ludovico Cavedon <cavedon@sssup.it>, " \
@@ -438,7 +438,7 @@
 		buf->vb.field = V4L2_FIELD_NONE;
 	else
 		buf->vb.field = V4L2_FIELD_INTERLACED;
-	v4l2_get_timestamp(&buf->vb.timestamp);
+	buf->vb.vb2_buf.timestamp = ktime_get_ns();
 
 	vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_DONE);
 }
@@ -871,30 +871,19 @@
 	Videobuf2 operations
    ------------------------------------------------------------------*/
 
-static int queue_setup(struct vb2_queue *vq, const void *parg,
+static int queue_setup(struct vb2_queue *vq,
 		       unsigned int *nbuffers, unsigned int *nplanes,
 		       unsigned int sizes[], void *alloc_ctxs[])
 {
-	const struct v4l2_format *fmt = parg;
 	struct em28xx *dev = vb2_get_drv_priv(vq);
 	struct em28xx_v4l2 *v4l2 = dev->v4l2;
-	unsigned long size;
-
-	if (fmt)
-		size = fmt->fmt.pix.sizeimage;
-	else
-		size =
+	unsigned long size =
 		    (v4l2->width * v4l2->height * v4l2->format->depth + 7) >> 3;
 
-	if (size == 0)
-		return -EINVAL;
-
-	if (0 == *nbuffers)
-		*nbuffers = 32;
-
+	if (*nplanes)
+		return sizes[0] < size ? -EINVAL : 0;
 	*nplanes = 1;
 	sizes[0] = size;
-
 	return 0;
 }
 
diff --git a/drivers/media/usb/em28xx/em28xx.h b/drivers/media/usb/em28xx/em28xx.h
index 76bf8ba..8ff066c 100644
--- a/drivers/media/usb/em28xx/em28xx.h
+++ b/drivers/media/usb/em28xx/em28xx.h
@@ -40,7 +40,7 @@
 #include <media/v4l2-device.h>
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-fh.h>
-#include <media/ir-kbd-i2c.h>
+#include <media/i2c/ir-kbd-i2c.h>
 #include <media/rc-core.h>
 #include "tuner-xc2028.h"
 #include "xc5000.h"
diff --git a/drivers/media/usb/go7007/go7007-driver.c b/drivers/media/usb/go7007/go7007-driver.c
index ae1cfa7..05b1126 100644
--- a/drivers/media/usb/go7007/go7007-driver.c
+++ b/drivers/media/usb/go7007/go7007-driver.c
@@ -466,7 +466,7 @@
 	else
 		go7007_set_motion_regions(go, vb, 0);
 
-	v4l2_get_timestamp(&vb->vb.timestamp);
+	vb->vb.vb2_buf.timestamp = ktime_get_ns();
 	vb_tmp = vb;
 	spin_lock(&go->spinlock);
 	list_del(&vb->list);
diff --git a/drivers/media/usb/go7007/go7007-usb.c b/drivers/media/usb/go7007/go7007-usb.c
index 4857c46..3dbf14c 100644
--- a/drivers/media/usb/go7007/go7007-usb.c
+++ b/drivers/media/usb/go7007/go7007-usb.c
@@ -23,9 +23,9 @@
 #include <linux/usb.h>
 #include <linux/i2c.h>
 #include <asm/byteorder.h>
-#include <media/saa7115.h>
+#include <media/i2c/saa7115.h>
 #include <media/tuner.h>
-#include <media/uda1342.h>
+#include <media/i2c/uda1342.h>
 
 #include "go7007-priv.h"
 
@@ -1289,7 +1289,7 @@
 
 	/* Allocate the URBs and buffers for receiving the audio stream */
 	if ((board->flags & GO7007_USB_EZUSB) &&
-	    (board->flags & GO7007_BOARD_HAS_AUDIO)) {
+	    (board->main_info.flags & GO7007_BOARD_HAS_AUDIO)) {
 		for (i = 0; i < 8; ++i) {
 			usb->audio_urbs[i] = usb_alloc_urb(0, GFP_KERNEL);
 			if (usb->audio_urbs[i] == NULL)
diff --git a/drivers/media/usb/go7007/go7007-v4l2.c b/drivers/media/usb/go7007/go7007-v4l2.c
index f3d187d..358c1c1 100644
--- a/drivers/media/usb/go7007/go7007-v4l2.c
+++ b/drivers/media/usb/go7007/go7007-v4l2.c
@@ -30,7 +30,7 @@
 #include <media/v4l2-subdev.h>
 #include <media/v4l2-event.h>
 #include <media/videobuf2-vmalloc.h>
-#include <media/saa7115.h>
+#include <media/i2c/saa7115.h>
 
 #include "go7007-priv.h"
 
@@ -369,7 +369,6 @@
 }
 
 static int go7007_queue_setup(struct vb2_queue *q,
-		const void *parg,
 		unsigned int *num_buffers, unsigned int *num_planes,
 		unsigned int sizes[], void *alloc_ctxs[])
 {
diff --git a/drivers/media/usb/gspca/ov534.c b/drivers/media/usb/gspca/ov534.c
index 146071b..bfff1d1 100644
--- a/drivers/media/usb/gspca/ov534.c
+++ b/drivers/media/usb/gspca/ov534.c
@@ -1491,8 +1491,13 @@
 	struct v4l2_fract *tpf = &cp->timeperframe;
 	struct sd *sd = (struct sd *) gspca_dev;
 
-	/* Set requested framerate */
-	sd->frame_rate = tpf->denominator / tpf->numerator;
+	if (tpf->numerator == 0 || tpf->denominator == 0)
+		/* Set default framerate */
+		sd->frame_rate = 30;
+	else
+		/* Set requested framerate */
+		sd->frame_rate = tpf->denominator / tpf->numerator;
+
 	if (gspca_dev->streaming)
 		set_frame_rate(gspca_dev);
 
diff --git a/drivers/media/usb/gspca/topro.c b/drivers/media/usb/gspca/topro.c
index c70ff40..c028a5c 100644
--- a/drivers/media/usb/gspca/topro.c
+++ b/drivers/media/usb/gspca/topro.c
@@ -4802,7 +4802,11 @@
 	struct v4l2_fract *tpf = &cp->timeperframe;
 	int fr, i;
 
-	sd->framerate = tpf->denominator / tpf->numerator;
+	if (tpf->numerator == 0 || tpf->denominator == 0)
+		sd->framerate = 30;
+	else
+		sd->framerate = tpf->denominator / tpf->numerator;
+
 	if (gspca_dev->streaming)
 		setframerate(gspca_dev, v4l2_ctrl_g_ctrl(gspca_dev->exposure));
 
diff --git a/drivers/media/usb/hackrf/hackrf.c b/drivers/media/usb/hackrf/hackrf.c
index 0fe5cb2..9e700ca 100644
--- a/drivers/media/usb/hackrf/hackrf.c
+++ b/drivers/media/usb/hackrf/hackrf.c
@@ -526,7 +526,7 @@
 		    urb->transfer_buffer, len);
 	vb2_set_plane_payload(&buffer->vb.vb2_buf, 0, len);
 	buffer->vb.sequence = dev->sequence++;
-	v4l2_get_timestamp(&buffer->vb.timestamp);
+	buffer->vb.vb2_buf.timestamp = ktime_get_ns();
 	vb2_buffer_done(&buffer->vb.vb2_buf, VB2_BUF_STATE_DONE);
 exit_usb_submit_urb:
 	usb_submit_urb(urb, GFP_ATOMIC);
@@ -571,7 +571,7 @@
 			   vb2_plane_vaddr(&buffer->vb.vb2_buf, 0), len);
 	urb->actual_length = len;
 	buffer->vb.sequence = dev->sequence++;
-	v4l2_get_timestamp(&buffer->vb.timestamp);
+	buffer->vb.vb2_buf.timestamp = ktime_get_ns();
 	vb2_buffer_done(&buffer->vb.vb2_buf, VB2_BUF_STATE_DONE);
 exit_usb_submit_urb:
 	usb_submit_urb(urb, GFP_ATOMIC);
@@ -759,7 +759,7 @@
 }
 
 static int hackrf_queue_setup(struct vb2_queue *vq,
-		const void *parg, unsigned int *nbuffers,
+		unsigned int *nbuffers,
 		unsigned int *nplanes, unsigned int sizes[], void *alloc_ctxs[])
 {
 	struct hackrf_dev *dev = vb2_get_drv_priv(vq);
diff --git a/drivers/media/usb/hdpvr/hdpvr-video.c b/drivers/media/usb/hdpvr/hdpvr-video.c
index d8d8c0f..7dee22d 100644
--- a/drivers/media/usb/hdpvr/hdpvr-video.c
+++ b/drivers/media/usb/hdpvr/hdpvr-video.c
@@ -642,7 +642,7 @@
 	if (dev->status != STATUS_IDLE)
 		return -EBUSY;
 	for (i = 0; i < ARRAY_SIZE(hdpvr_dv_timings); i++)
-		if (v4l2_match_dv_timings(timings, hdpvr_dv_timings + i, 0))
+		if (v4l2_match_dv_timings(timings, hdpvr_dv_timings + i, 0, false))
 			break;
 	if (i == ARRAY_SIZE(hdpvr_dv_timings))
 		return -EINVAL;
diff --git a/drivers/media/usb/hdpvr/hdpvr.h b/drivers/media/usb/hdpvr/hdpvr.h
index a319430..78e8154 100644
--- a/drivers/media/usb/hdpvr/hdpvr.h
+++ b/drivers/media/usb/hdpvr/hdpvr.h
@@ -17,7 +17,7 @@
 
 #include <media/v4l2-device.h>
 #include <media/v4l2-ctrls.h>
-#include <media/ir-kbd-i2c.h>
+#include <media/i2c/ir-kbd-i2c.h>
 
 #define HDPVR_MAX 8
 #define HDPVR_I2C_MAX_SIZE 128
diff --git a/drivers/media/usb/msi2500/msi2500.c b/drivers/media/usb/msi2500/msi2500.c
index e06a21a..c104315 100644
--- a/drivers/media/usb/msi2500/msi2500.c
+++ b/drivers/media/usb/msi2500/msi2500.c
@@ -616,7 +616,6 @@
 
 /* Videobuf2 operations */
 static int msi2500_queue_setup(struct vb2_queue *vq,
-			       const void *parg,
 			       unsigned int *nbuffers,
 			       unsigned int *nplanes, unsigned int sizes[],
 			       void *alloc_ctxs[])
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-audio.c b/drivers/media/usb/pvrusb2/pvrusb2-audio.c
index 45276c6..5f953d8 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-audio.c
+++ b/drivers/media/usb/pvrusb2/pvrusb2-audio.c
@@ -23,7 +23,7 @@
 #include "pvrusb2-hdw-internal.h"
 #include "pvrusb2-debug.h"
 #include <linux/videodev2.h>
-#include <media/msp3400.h>
+#include <media/drv-intf/msp3400.h>
 #include <media/v4l2-common.h>
 
 
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-cx2584x-v4l.c b/drivers/media/usb/pvrusb2/pvrusb2-cx2584x-v4l.c
index 1a81aa7..7d675fa 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-cx2584x-v4l.c
+++ b/drivers/media/usb/pvrusb2/pvrusb2-cx2584x-v4l.c
@@ -32,7 +32,7 @@
 
 #include "pvrusb2-hdw-internal.h"
 #include "pvrusb2-debug.h"
-#include <media/cx25840.h>
+#include <media/drv-intf/cx25840.h>
 #include <linux/videodev2.h>
 #include <media/v4l2-common.h>
 #include <linux/errno.h>
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-hdw-internal.h b/drivers/media/usb/pvrusb2/pvrusb2-hdw-internal.h
index 1f9c028..60141b1 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-hdw-internal.h
+++ b/drivers/media/usb/pvrusb2/pvrusb2-hdw-internal.h
@@ -39,8 +39,8 @@
 #include "pvrusb2-hdw.h"
 #include "pvrusb2-io.h"
 #include <media/v4l2-device.h>
-#include <media/cx2341x.h>
-#include <media/ir-kbd-i2c.h>
+#include <media/drv-intf/cx2341x.h>
+#include <media/i2c/ir-kbd-i2c.h>
 #include "pvrusb2-devattr.h"
 
 /* Legal values for PVR2_CID_HSM */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-i2c-core.c b/drivers/media/usb/pvrusb2/pvrusb2-i2c-core.c
index 4baa9d6..14321d0 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-i2c-core.c
+++ b/drivers/media/usb/pvrusb2/pvrusb2-i2c-core.c
@@ -20,7 +20,7 @@
 
 #include <linux/i2c.h>
 #include <linux/module.h>
-#include <media/ir-kbd-i2c.h>
+#include <media/i2c/ir-kbd-i2c.h>
 #include "pvrusb2-i2c-core.h"
 #include "pvrusb2-hdw-internal.h"
 #include "pvrusb2-debug.h"
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-v4l2.c b/drivers/media/usb/pvrusb2/pvrusb2-v4l2.c
index 1c5f85b..81f788b 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-v4l2.c
+++ b/drivers/media/usb/pvrusb2/pvrusb2-v4l2.c
@@ -628,6 +628,7 @@
 	struct pvr2_v4l2_fh *fh = file->private_data;
 	struct pvr2_hdw *hdw = fh->channel.mc_head->hdw;
 	struct v4l2_ext_control *ctrl;
+	struct pvr2_ctrl *cptr;
 	unsigned int idx;
 	int val;
 	int ret;
@@ -635,8 +636,15 @@
 	ret = 0;
 	for (idx = 0; idx < ctls->count; idx++) {
 		ctrl = ctls->controls + idx;
-		ret = pvr2_ctrl_get_value(
-				pvr2_hdw_get_ctrl_v4l(hdw, ctrl->id), &val);
+		cptr = pvr2_hdw_get_ctrl_v4l(hdw, ctrl->id);
+		if (cptr) {
+			if (ctls->which == V4L2_CTRL_WHICH_DEF_VAL)
+				pvr2_ctrl_get_def(cptr, &val);
+			else
+				ret = pvr2_ctrl_get_value(cptr, &val);
+		} else
+			ret = -EINVAL;
+
 		if (ret) {
 			ctls->error_idx = idx;
 			return ret;
@@ -658,6 +666,10 @@
 	unsigned int idx;
 	int ret;
 
+	/* Default value cannot be changed */
+	if (ctls->which == V4L2_CTRL_WHICH_DEF_VAL)
+		return -EINVAL;
+
 	ret = 0;
 	for (idx = 0; idx < ctls->count; idx++) {
 		ctrl = ctls->controls + idx;
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-video-v4l.c b/drivers/media/usb/pvrusb2/pvrusb2-video-v4l.c
index 139b397..105123a 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-video-v4l.c
+++ b/drivers/media/usb/pvrusb2/pvrusb2-video-v4l.c
@@ -35,7 +35,7 @@
 #include "pvrusb2-debug.h"
 #include <linux/videodev2.h>
 #include <media/v4l2-common.h>
-#include <media/saa7115.h>
+#include <media/i2c/saa7115.h>
 #include <linux/errno.h>
 
 struct routing_scheme {
diff --git a/drivers/media/usb/pwc/pwc-if.c b/drivers/media/usb/pwc/pwc-if.c
index b79c36fd..086cf1c 100644
--- a/drivers/media/usb/pwc/pwc-if.c
+++ b/drivers/media/usb/pwc/pwc-if.c
@@ -316,8 +316,7 @@
 			struct pwc_frame_buf *fbuf = pdev->fill_buf;
 
 			if (pdev->vsync == 1) {
-				v4l2_get_timestamp(
-					&fbuf->vb.timestamp);
+				fbuf->vb.vb2_buf.timestamp = ktime_get_ns();
 				pdev->vsync = 2;
 			}
 
@@ -571,7 +570,7 @@
 /***************************************************************************/
 /* Videobuf2 operations */
 
-static int queue_setup(struct vb2_queue *vq, const void *parg,
+static int queue_setup(struct vb2_queue *vq,
 				unsigned int *nbuffers, unsigned int *nplanes,
 				unsigned int sizes[], void *alloc_ctxs[])
 {
diff --git a/drivers/media/usb/s2255/s2255drv.c b/drivers/media/usb/s2255/s2255drv.c
index e7acb12..9acdaa3 100644
--- a/drivers/media/usb/s2255/s2255drv.c
+++ b/drivers/media/usb/s2255/s2255drv.c
@@ -574,7 +574,7 @@
 	buf = list_entry(vc->buf_list.next,
 			 struct s2255_buffer, list);
 	list_del(&buf->list);
-	v4l2_get_timestamp(&buf->vb.timestamp);
+	buf->vb.vb2_buf.timestamp = ktime_get_ns();
 	buf->vb.field = vc->field;
 	buf->vb.sequence = vc->frame_count;
 	spin_unlock_irqrestore(&vc->qlock, flags);
@@ -660,7 +660,7 @@
    Videobuf operations
    ------------------------------------------------------------------*/
 
-static int queue_setup(struct vb2_queue *vq, const void *parg,
+static int queue_setup(struct vb2_queue *vq,
 		       unsigned int *nbuffers, unsigned int *nplanes,
 		       unsigned int sizes[], void *alloc_ctxs[])
 {
diff --git a/drivers/media/usb/stk1160/stk1160-core.c b/drivers/media/usb/stk1160/stk1160-core.c
index 1b6836f..bc02947 100644
--- a/drivers/media/usb/stk1160/stk1160-core.c
+++ b/drivers/media/usb/stk1160/stk1160-core.c
@@ -34,7 +34,7 @@
 #include <linux/usb.h>
 #include <linux/mm.h>
 #include <linux/vmalloc.h>
-#include <media/saa7115.h>
+#include <media/i2c/saa7115.h>
 
 #include "stk1160.h"
 #include "stk1160-reg.h"
diff --git a/drivers/media/usb/stk1160/stk1160-v4l.c b/drivers/media/usb/stk1160/stk1160-v4l.c
index 0bd34f1..77131fd 100644
--- a/drivers/media/usb/stk1160/stk1160-v4l.c
+++ b/drivers/media/usb/stk1160/stk1160-v4l.c
@@ -33,7 +33,7 @@
 #include <media/v4l2-event.h>
 #include <media/videobuf2-vmalloc.h>
 
-#include <media/saa7115.h>
+#include <media/i2c/saa7115.h>
 
 #include "stk1160.h"
 #include "stk1160-reg.h"
@@ -664,7 +664,7 @@
 /*
  * Videobuf2 operations
  */
-static int queue_setup(struct vb2_queue *vq, const void *parg,
+static int queue_setup(struct vb2_queue *vq,
 				unsigned int *nbuffers, unsigned int *nplanes,
 				unsigned int sizes[], void *alloc_ctxs[])
 {
diff --git a/drivers/media/usb/stk1160/stk1160-video.c b/drivers/media/usb/stk1160/stk1160-video.c
index 75654e6..46191d5 100644
--- a/drivers/media/usb/stk1160/stk1160-video.c
+++ b/drivers/media/usb/stk1160/stk1160-video.c
@@ -99,7 +99,7 @@
 	buf->vb.sequence = dev->sequence++;
 	buf->vb.field = V4L2_FIELD_INTERLACED;
 	buf->vb.vb2_buf.planes[0].bytesused = buf->bytesused;
-	v4l2_get_timestamp(&buf->vb.timestamp);
+	buf->vb.vb2_buf.timestamp = ktime_get_ns();
 
 	vb2_set_plane_payload(&buf->vb.vb2_buf, 0, buf->bytesused);
 	vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_DONE);
diff --git a/drivers/media/usb/tm6000/tm6000-cards.c b/drivers/media/usb/tm6000/tm6000-cards.c
index 2e8c3af..8902ee3 100644
--- a/drivers/media/usb/tm6000/tm6000-cards.c
+++ b/drivers/media/usb/tm6000/tm6000-cards.c
@@ -26,7 +26,7 @@
 #include <linux/slab.h>
 #include <media/v4l2-common.h>
 #include <media/tuner.h>
-#include <media/tvaudio.h>
+#include <media/i2c/tvaudio.h>
 #include <media/i2c-addr.h>
 #include <media/rc-map.h>
 
diff --git a/drivers/media/usb/ttusb-dec/ttusb_dec.c b/drivers/media/usb/ttusb-dec/ttusb_dec.c
index a5de46f..4e36e24 100644
--- a/drivers/media/usb/ttusb-dec/ttusb_dec.c
+++ b/drivers/media/usb/ttusb-dec/ttusb_dec.c
@@ -1606,7 +1606,7 @@
 	return ttusb_dec_send_command(dec, command, param_length, params, result_length, cmd_result);
 }
 
-static struct ttusbdecfe_config fe_config = {
+static const struct ttusbdecfe_config fe_config = {
 	.send_command = fe_send_command
 };
 
diff --git a/drivers/media/usb/usbtv/usbtv-video.c b/drivers/media/usb/usbtv/usbtv-video.c
index e645c9d..4ebb339 100644
--- a/drivers/media/usb/usbtv/usbtv-video.c
+++ b/drivers/media/usb/usbtv/usbtv-video.c
@@ -322,7 +322,7 @@
 
 		buf->vb.field = V4L2_FIELD_INTERLACED;
 		buf->vb.sequence = usbtv->sequence++;
-		v4l2_get_timestamp(&buf->vb.timestamp);
+		buf->vb.vb2_buf.timestamp = ktime_get_ns();
 		vb2_set_plane_payload(&buf->vb.vb2_buf, 0, size);
 		vb2_buffer_done(&buf->vb.vb2_buf, state);
 		list_del(&buf->list);
@@ -599,19 +599,18 @@
 };
 
 static int usbtv_queue_setup(struct vb2_queue *vq,
-	const void *parg, unsigned int *nbuffers,
+	unsigned int *nbuffers,
 	unsigned int *nplanes, unsigned int sizes[], void *alloc_ctxs[])
 {
-	const struct v4l2_format *fmt = parg;
 	struct usbtv *usbtv = vb2_get_drv_priv(vq);
 	unsigned size = USBTV_CHUNK * usbtv->n_chunks * 2 * sizeof(u32);
 
 	if (vq->num_buffers + *nbuffers < 2)
 		*nbuffers = 2 - vq->num_buffers;
+	if (*nplanes)
+		return sizes[0] < size ? -EINVAL : 0;
 	*nplanes = 1;
-	if (fmt && fmt->fmt.pix.sizeimage < size)
-		return -EINVAL;
-	sizes[0] = fmt ? fmt->fmt.pix.sizeimage : size;
+	sizes[0] = size;
 
 	return 0;
 }
diff --git a/drivers/media/usb/usbvision/usbvision-core.c b/drivers/media/usb/usbvision/usbvision-core.c
index dc3b4d5..1ea04e7 100644
--- a/drivers/media/usb/usbvision/usbvision-core.c
+++ b/drivers/media/usb/usbvision/usbvision-core.c
@@ -37,7 +37,7 @@
 #include <linux/videodev2.h>
 #include <linux/i2c.h>
 
-#include <media/saa7115.h>
+#include <media/i2c/saa7115.h>
 #include <media/v4l2-common.h>
 #include <media/tuner.h>
 
diff --git a/drivers/media/usb/usbvision/usbvision-video.c b/drivers/media/usb/usbvision/usbvision-video.c
index b693206..de9ff3b 100644
--- a/drivers/media/usb/usbvision/usbvision-video.c
+++ b/drivers/media/usb/usbvision/usbvision-video.c
@@ -59,7 +59,7 @@
 #include <linux/videodev2.h>
 #include <linux/i2c.h>
 
-#include <media/saa7115.h>
+#include <media/i2c/saa7115.h>
 #include <media/v4l2-common.h>
 #include <media/v4l2-ioctl.h>
 #include <media/v4l2-event.h>
@@ -1461,11 +1461,32 @@
 	printk(KERN_INFO "%s: %s found\n", __func__,
 				usbvision_device_data[model].model_string);
 
+	/*
+	 * this is a security check.
+	 * an exploit using an incorrect bInterfaceNumber is known
+	 */
+	if (ifnum >= USB_MAXINTERFACES || !dev->actconfig->interface[ifnum])
+		return -ENODEV;
+
 	if (usbvision_device_data[model].interface >= 0)
 		interface = &dev->actconfig->interface[usbvision_device_data[model].interface]->altsetting[0];
-	else
+	else if (ifnum < dev->actconfig->desc.bNumInterfaces)
 		interface = &dev->actconfig->interface[ifnum]->altsetting[0];
+	else {
+		dev_err(&intf->dev, "interface %d is invalid, max is %d\n",
+		    ifnum, dev->actconfig->desc.bNumInterfaces - 1);
+		ret = -ENODEV;
+		goto err_usb;
+	}
+
+	if (interface->desc.bNumEndpoints < 2) {
+		dev_err(&intf->dev, "interface %d has %d endpoints, but must"
+		    " have minimum 2\n", ifnum, interface->desc.bNumEndpoints);
+		ret = -ENODEV;
+		goto err_usb;
+	}
 	endpoint = &interface->endpoint[1].desc;
+
 	if (!usb_endpoint_xfer_isoc(endpoint)) {
 		dev_err(&intf->dev, "%s: interface %d. has non-ISO endpoint!\n",
 		    __func__, ifnum);
diff --git a/drivers/media/usb/uvc/uvc_ctrl.c b/drivers/media/usb/uvc/uvc_ctrl.c
index 3e59b28..c2ee6e3 100644
--- a/drivers/media/usb/uvc/uvc_ctrl.c
+++ b/drivers/media/usb/uvc/uvc_ctrl.c
@@ -227,7 +227,8 @@
 		.size		= 4,
 		.flags		= UVC_CTRL_FLAG_SET_CUR
 				| UVC_CTRL_FLAG_GET_RANGE
-				| UVC_CTRL_FLAG_RESTORE,
+				| UVC_CTRL_FLAG_RESTORE
+				| UVC_CTRL_FLAG_AUTO_UPDATE,
 	},
 	{
 		.entity		= UVC_GUID_UVC_CAMERA,
diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c
index d11fd6a..39abbaf 100644
--- a/drivers/media/usb/uvc/uvc_driver.c
+++ b/drivers/media/usb/uvc/uvc_driver.c
@@ -2540,7 +2540,8 @@
 	  .bInterfaceProtocol	= 0,
 	  .driver_info		= UVC_QUIRK_FORCE_Y8 },
 	/* Generic USB Video Class */
-	{ USB_INTERFACE_INFO(USB_CLASS_VIDEO, 1, 0) },
+	{ USB_INTERFACE_INFO(USB_CLASS_VIDEO, 1, UVC_PC_PROTOCOL_UNDEFINED) },
+	{ USB_INTERFACE_INFO(USB_CLASS_VIDEO, 1, UVC_PC_PROTOCOL_15) },
 	{}
 };
 
diff --git a/drivers/media/usb/uvc/uvc_queue.c b/drivers/media/usb/uvc/uvc_queue.c
index cfb868a..5439472 100644
--- a/drivers/media/usb/uvc/uvc_queue.c
+++ b/drivers/media/usb/uvc/uvc_queue.c
@@ -69,23 +69,19 @@
  * videobuf2 queue operations
  */
 
-static int uvc_queue_setup(struct vb2_queue *vq, const void *parg,
+static int uvc_queue_setup(struct vb2_queue *vq,
 			   unsigned int *nbuffers, unsigned int *nplanes,
 			   unsigned int sizes[], void *alloc_ctxs[])
 {
-	const struct v4l2_format *fmt = parg;
 	struct uvc_video_queue *queue = vb2_get_drv_priv(vq);
 	struct uvc_streaming *stream = uvc_queue_to_stream(queue);
+	unsigned size = stream->ctrl.dwMaxVideoFrameSize;
 
 	/* Make sure the image size is large enough. */
-	if (fmt && fmt->fmt.pix.sizeimage < stream->ctrl.dwMaxVideoFrameSize)
-		return -EINVAL;
-
+	if (*nplanes)
+		return sizes[0] < size ? -EINVAL : 0;
 	*nplanes = 1;
-
-	sizes[0] = fmt ? fmt->fmt.pix.sizeimage
-		 : stream->ctrl.dwMaxVideoFrameSize;
-
+	sizes[0] = size;
 	return 0;
 }
 
diff --git a/drivers/media/usb/uvc/uvc_v4l2.c b/drivers/media/usb/uvc/uvc_v4l2.c
index 2764f43..d7723ce 100644
--- a/drivers/media/usb/uvc/uvc_v4l2.c
+++ b/drivers/media/usb/uvc/uvc_v4l2.c
@@ -983,6 +983,22 @@
 	unsigned int i;
 	int ret;
 
+	if (ctrls->which == V4L2_CTRL_WHICH_DEF_VAL) {
+		for (i = 0; i < ctrls->count; ++ctrl, ++i) {
+			struct v4l2_queryctrl qc = { .id = ctrl->id };
+
+			ret = uvc_query_v4l2_ctrl(chain, &qc);
+			if (ret < 0) {
+				ctrls->error_idx = i;
+				return ret;
+			}
+
+			ctrl->value = qc.default_value;
+		}
+
+		return 0;
+	}
+
 	ret = uvc_ctrl_begin(chain);
 	if (ret < 0)
 		return ret;
@@ -1010,6 +1026,10 @@
 	unsigned int i;
 	int ret;
 
+	/* Default value cannot be changed */
+	if (ctrls->which == V4L2_CTRL_WHICH_DEF_VAL)
+		return -EINVAL;
+
 	ret = uvc_ctrl_begin(chain);
 	if (ret < 0)
 		return ret;
diff --git a/drivers/media/usb/uvc/uvc_video.c b/drivers/media/usb/uvc/uvc_video.c
index 2b276ab..075a0fe 100644
--- a/drivers/media/usb/uvc/uvc_video.c
+++ b/drivers/media/usb/uvc/uvc_video.c
@@ -694,22 +694,19 @@
 		ts.tv_nsec -= NSEC_PER_SEC;
 	}
 
-	uvc_trace(UVC_TRACE_CLOCK, "%s: SOF %u.%06llu y %llu ts %lu.%06lu "
-		  "buf ts %lu.%06lu (x1 %u/%u/%u x2 %u/%u/%u y1 %u y2 %u)\n",
+	uvc_trace(UVC_TRACE_CLOCK, "%s: SOF %u.%06llu y %llu ts %llu "
+		  "buf ts %llu (x1 %u/%u/%u x2 %u/%u/%u y1 %u y2 %u)\n",
 		  stream->dev->name,
 		  sof >> 16, div_u64(((u64)sof & 0xffff) * 1000000LLU, 65536),
-		  y, ts.tv_sec, ts.tv_nsec / NSEC_PER_USEC,
-		  vbuf->timestamp.tv_sec,
-		  (unsigned long)vbuf->timestamp.tv_usec,
+		  y, timespec_to_ns(&ts), vbuf->vb2_buf.timestamp,
 		  x1, first->host_sof, first->dev_sof,
 		  x2, last->host_sof, last->dev_sof, y1, y2);
 
 	/* Update the V4L2 buffer. */
-	vbuf->timestamp.tv_sec = ts.tv_sec;
-	vbuf->timestamp.tv_usec = ts.tv_nsec / NSEC_PER_USEC;
+	vbuf->vb2_buf.timestamp = timespec_to_ns(&ts);
 
 done:
-	spin_unlock_irqrestore(&stream->clock.lock, flags);
+	spin_unlock_irqrestore(&clock->lock, flags);
 }
 
 /* ------------------------------------------------------------------------
@@ -1034,9 +1031,7 @@
 
 		buf->buf.field = V4L2_FIELD_NONE;
 		buf->buf.sequence = stream->sequence;
-		buf->buf.timestamp.tv_sec = ts.tv_sec;
-		buf->buf.timestamp.tv_usec =
-			ts.tv_nsec / NSEC_PER_USEC;
+		buf->buf.vb2_buf.timestamp = timespec_to_ns(&ts);
 
 		/* TODO: Handle PTS and SCR. */
 		buf->state = UVC_BUF_STATE_ACTIVE;
diff --git a/drivers/media/v4l2-core/v4l2-clk.c b/drivers/media/v4l2-core/v4l2-clk.c
index 34e416a..297e10e 100644
--- a/drivers/media/v4l2-core/v4l2-clk.c
+++ b/drivers/media/v4l2-core/v4l2-clk.c
@@ -15,6 +15,7 @@
 #include <linux/list.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/of.h>
 #include <linux/slab.h>
 #include <linux/string.h>
 
@@ -39,6 +40,7 @@
 {
 	struct v4l2_clk *clk;
 	struct clk *ccf_clk = clk_get(dev, id);
+	char clk_name[V4L2_CLK_NAME_SIZE];
 
 	if (PTR_ERR(ccf_clk) == -EPROBE_DEFER)
 		return ERR_PTR(-EPROBE_DEFER);
@@ -57,6 +59,13 @@
 	mutex_lock(&clk_lock);
 	clk = v4l2_clk_find(dev_name(dev));
 
+	/* if dev_name is not found, try use the OF name to find again  */
+	if (PTR_ERR(clk) == -ENODEV && dev->of_node) {
+		v4l2_clk_name_of(clk_name, sizeof(clk_name),
+				 of_node_full_name(dev->of_node));
+		clk = v4l2_clk_find(clk_name);
+	}
+
 	if (!IS_ERR(clk))
 		atomic_inc(&clk->use_count);
 	mutex_unlock(&clk_lock);
diff --git a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
index 327e83a..8fd84a6 100644
--- a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
+++ b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
@@ -630,7 +630,7 @@
 }
 
 struct v4l2_ext_controls32 {
-	__u32 ctrl_class;
+	__u32 which;
 	__u32 count;
 	__u32 error_idx;
 	__u32 reserved[2];
@@ -673,7 +673,7 @@
 	compat_caddr_t p;
 
 	if (!access_ok(VERIFY_READ, up, sizeof(struct v4l2_ext_controls32)) ||
-		get_user(kp->ctrl_class, &up->ctrl_class) ||
+		get_user(kp->which, &up->which) ||
 		get_user(kp->count, &up->count) ||
 		get_user(kp->error_idx, &up->error_idx) ||
 		copy_from_user(kp->reserved, up->reserved,
@@ -723,7 +723,7 @@
 	compat_caddr_t p;
 
 	if (!access_ok(VERIFY_WRITE, up, sizeof(struct v4l2_ext_controls32)) ||
-		put_user(kp->ctrl_class, &up->ctrl_class) ||
+		put_user(kp->which, &up->which) ||
 		put_user(kp->count, &up->count) ||
 		put_user(kp->error_idx, &up->error_idx) ||
 		copy_to_user(up->reserved, kp->reserved, sizeof(up->reserved)))
diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c
index 4a1d9fd..c9d5537 100644
--- a/drivers/media/v4l2-core/v4l2-ctrls.c
+++ b/drivers/media/v4l2-core/v4l2-ctrls.c
@@ -1491,6 +1491,17 @@
 	return ptr_to_user(c, ctrl, ctrl->p_new);
 }
 
+/* Helper function: copy the initial control value back to the caller */
+static int def_to_user(struct v4l2_ext_control *c, struct v4l2_ctrl *ctrl)
+{
+	int idx;
+
+	for (idx = 0; idx < ctrl->elems; idx++)
+		ctrl->type_ops->init(ctrl, idx, ctrl->p_new);
+
+	return ptr_to_user(c, ctrl, ctrl->p_new);
+}
+
 /* Helper function: copy the caller-provider value to the given control value */
 static int user_to_ptr(struct v4l2_ext_control *c,
 		       struct v4l2_ctrl *ctrl,
@@ -1762,7 +1773,7 @@
 	list_for_each_entry(ref, &hdl->ctrl_refs, node) {
 		/* Search for private user controls that are compatible with
 		   VIDIOC_G/S_CTRL. */
-		if (V4L2_CTRL_ID2CLASS(ref->ctrl->id) == V4L2_CTRL_CLASS_USER &&
+		if (V4L2_CTRL_ID2WHICH(ref->ctrl->id) == V4L2_CTRL_CLASS_USER &&
 		    V4L2_CTRL_DRIVER_PRIV(ref->ctrl->id)) {
 			if (!ref->ctrl->is_int)
 				continue;
@@ -1831,7 +1842,7 @@
 	struct v4l2_ctrl_ref *ref;
 	struct v4l2_ctrl_ref *new_ref;
 	u32 id = ctrl->id;
-	u32 class_ctrl = V4L2_CTRL_ID2CLASS(id) | 1;
+	u32 class_ctrl = V4L2_CTRL_ID2WHICH(id) | 1;
 	int bucket = id % hdl->nr_of_buckets;	/* which bucket to use */
 
 	/*
@@ -2253,9 +2264,9 @@
 
 bool v4l2_ctrl_radio_filter(const struct v4l2_ctrl *ctrl)
 {
-	if (V4L2_CTRL_ID2CLASS(ctrl->id) == V4L2_CTRL_CLASS_FM_TX)
+	if (V4L2_CTRL_ID2WHICH(ctrl->id) == V4L2_CTRL_CLASS_FM_TX)
 		return true;
-	if (V4L2_CTRL_ID2CLASS(ctrl->id) == V4L2_CTRL_CLASS_FM_RX)
+	if (V4L2_CTRL_ID2WHICH(ctrl->id) == V4L2_CTRL_CLASS_FM_RX)
 		return true;
 	switch (ctrl->id) {
 	case V4L2_CID_AUDIO_MUTE:
@@ -2710,7 +2721,9 @@
 
 		cs->error_idx = i;
 
-		if (cs->ctrl_class && V4L2_CTRL_ID2CLASS(id) != cs->ctrl_class)
+		if (cs->which &&
+		    cs->which != V4L2_CTRL_WHICH_DEF_VAL &&
+		    V4L2_CTRL_ID2WHICH(id) != cs->which)
 			return -EINVAL;
 
 		/* Old-style private controls are not allowed for
@@ -2787,11 +2800,11 @@
 /* Handles the corner case where cs->count == 0. It checks whether the
    specified control class exists. If that class ID is 0, then it checks
    whether there are any controls at all. */
-static int class_check(struct v4l2_ctrl_handler *hdl, u32 ctrl_class)
+static int class_check(struct v4l2_ctrl_handler *hdl, u32 which)
 {
-	if (ctrl_class == 0)
+	if (which == 0 || which == V4L2_CTRL_WHICH_DEF_VAL)
 		return list_empty(&hdl->ctrl_refs) ? -EINVAL : 0;
-	return find_ref_lock(hdl, ctrl_class | 1) ? 0 : -EINVAL;
+	return find_ref_lock(hdl, which | 1) ? 0 : -EINVAL;
 }
 
 
@@ -2803,15 +2816,18 @@
 	struct v4l2_ctrl_helper *helpers = helper;
 	int ret;
 	int i, j;
+	bool def_value;
+
+	def_value = (cs->which == V4L2_CTRL_WHICH_DEF_VAL);
 
 	cs->error_idx = cs->count;
-	cs->ctrl_class = V4L2_CTRL_ID2CLASS(cs->ctrl_class);
+	cs->which = V4L2_CTRL_ID2WHICH(cs->which);
 
 	if (hdl == NULL)
 		return -EINVAL;
 
 	if (cs->count == 0)
-		return class_check(hdl, cs->ctrl_class);
+		return class_check(hdl, cs->which);
 
 	if (cs->count > ARRAY_SIZE(helper)) {
 		helpers = kmalloc_array(cs->count, sizeof(helper[0]),
@@ -2829,9 +2845,11 @@
 
 	for (i = 0; !ret && i < cs->count; i++) {
 		int (*ctrl_to_user)(struct v4l2_ext_control *c,
-				    struct v4l2_ctrl *ctrl) = cur_to_user;
+				    struct v4l2_ctrl *ctrl);
 		struct v4l2_ctrl *master;
 
+		ctrl_to_user = def_value ? def_to_user : cur_to_user;
+
 		if (helpers[i].mref == NULL)
 			continue;
 
@@ -2841,8 +2859,9 @@
 		v4l2_ctrl_lock(master);
 
 		/* g_volatile_ctrl will update the new control values */
-		if ((master->flags & V4L2_CTRL_FLAG_VOLATILE) ||
-			(master->has_volatiles && !is_cur_manual(master))) {
+		if (!def_value &&
+		    ((master->flags & V4L2_CTRL_FLAG_VOLATILE) ||
+		    (master->has_volatiles && !is_cur_manual(master)))) {
 			for (j = 0; j < master->ncontrols; j++)
 				cur_to_new(master->cluster[j]);
 			ret = call_op(master, g_volatile_ctrl);
@@ -3064,13 +3083,18 @@
 	int ret;
 
 	cs->error_idx = cs->count;
-	cs->ctrl_class = V4L2_CTRL_ID2CLASS(cs->ctrl_class);
+
+	/* Default value cannot be changed */
+	if (cs->which == V4L2_CTRL_WHICH_DEF_VAL)
+		return -EINVAL;
+
+	cs->which = V4L2_CTRL_ID2WHICH(cs->which);
 
 	if (hdl == NULL)
 		return -EINVAL;
 
 	if (cs->count == 0)
-		return class_check(hdl, cs->ctrl_class);
+		return class_check(hdl, cs->which);
 
 	if (cs->count > ARRAY_SIZE(helper)) {
 		helpers = kmalloc_array(cs->count, sizeof(helper[0]),
@@ -3300,7 +3324,8 @@
 int __v4l2_ctrl_modify_range(struct v4l2_ctrl *ctrl,
 			s64 min, s64 max, u64 step, s64 def)
 {
-	bool changed;
+	bool value_changed;
+	bool range_changed = false;
 	int ret;
 
 	lockdep_assert_held(ctrl->handler->lock);
@@ -3324,10 +3349,14 @@
 	default:
 		return -EINVAL;
 	}
-	ctrl->minimum = min;
-	ctrl->maximum = max;
-	ctrl->step = step;
-	ctrl->default_value = def;
+	if ((ctrl->minimum != min) || (ctrl->maximum != max) ||
+		(ctrl->step != step) || ctrl->default_value != def) {
+		range_changed = true;
+		ctrl->minimum = min;
+		ctrl->maximum = max;
+		ctrl->step = step;
+		ctrl->default_value = def;
+	}
 	cur_to_new(ctrl);
 	if (validate_new(ctrl, ctrl->p_new)) {
 		if (ctrl->type == V4L2_CTRL_TYPE_INTEGER64)
@@ -3337,12 +3366,12 @@
 	}
 
 	if (ctrl->type == V4L2_CTRL_TYPE_INTEGER64)
-		changed = *ctrl->p_new.p_s64 != *ctrl->p_cur.p_s64;
+		value_changed = *ctrl->p_new.p_s64 != *ctrl->p_cur.p_s64;
 	else
-		changed = *ctrl->p_new.p_s32 != *ctrl->p_cur.p_s32;
-	if (changed)
+		value_changed = *ctrl->p_new.p_s32 != *ctrl->p_cur.p_s32;
+	if (value_changed)
 		ret = set_ctrl(NULL, ctrl, V4L2_EVENT_CTRL_CH_RANGE);
-	else
+	else if (range_changed)
 		send_event(NULL, ctrl, V4L2_EVENT_CTRL_CH_RANGE);
 	return ret;
 }
diff --git a/drivers/media/v4l2-core/v4l2-device.c b/drivers/media/v4l2-core/v4l2-device.c
index 5b0a30b..7129e43 100644
--- a/drivers/media/v4l2-core/v4l2-device.c
+++ b/drivers/media/v4l2-core/v4l2-device.c
@@ -118,11 +118,20 @@
 		if (sd->flags & V4L2_SUBDEV_FL_IS_I2C) {
 			struct i2c_client *client = v4l2_get_subdevdata(sd);
 
-			/* We need to unregister the i2c client explicitly.
-			   We cannot rely on i2c_del_adapter to always
-			   unregister clients for us, since if the i2c bus
-			   is a platform bus, then it is never deleted. */
-			if (client)
+			/*
+			 * We need to unregister the i2c client
+			 * explicitly. We cannot rely on
+			 * i2c_del_adapter to always unregister
+			 * clients for us, since if the i2c bus is a
+			 * platform bus, then it is never deleted.
+			 *
+			 * Device tree or ACPI based devices must not
+			 * be unregistered as they have not been
+			 * registered by us, and would not be
+			 * re-created by just probing the V4L2 driver.
+			 */
+			if (client &&
+			    !client->dev.of_node && !client->dev.fwnode)
 				i2c_unregister_device(client);
 			continue;
 		}
@@ -131,7 +140,7 @@
 		if (sd->flags & V4L2_SUBDEV_FL_IS_SPI) {
 			struct spi_device *spi = v4l2_get_subdevdata(sd);
 
-			if (spi)
+			if (spi && !spi->dev.of_node && !spi->dev.fwnode)
 				spi_unregister_device(spi);
 			continue;
 		}
diff --git a/drivers/media/v4l2-core/v4l2-dv-timings.c b/drivers/media/v4l2-core/v4l2-dv-timings.c
index 6a83d61..ec258b7 100644
--- a/drivers/media/v4l2-core/v4l2-dv-timings.c
+++ b/drivers/media/v4l2-core/v4l2-dv-timings.c
@@ -209,8 +209,13 @@
 		if (v4l2_valid_dv_timings(v4l2_dv_timings_presets + i, cap,
 					  fnc, fnc_handle) &&
 		    v4l2_match_dv_timings(t, v4l2_dv_timings_presets + i,
-					  pclock_delta)) {
+					  pclock_delta, false)) {
+			u32 flags = t->bt.flags & V4L2_DV_FL_REDUCED_FPS;
+
 			*t = v4l2_dv_timings_presets[i];
+			if (can_reduce_fps(&t->bt))
+				t->bt.flags |= flags;
+
 			return true;
 		}
 	}
@@ -223,12 +228,14 @@
  * @t1 - compare this v4l2_dv_timings struct...
  * @t2 - with this struct.
  * @pclock_delta - the allowed pixelclock deviation.
+ * @match_reduced_fps - if true, then fail if V4L2_DV_FL_REDUCED_FPS does not
+ * match.
  *
  * Compare t1 with t2 with a given margin of error for the pixelclock.
  */
 bool v4l2_match_dv_timings(const struct v4l2_dv_timings *t1,
 			   const struct v4l2_dv_timings *t2,
-			   unsigned pclock_delta)
+			   unsigned pclock_delta, bool match_reduced_fps)
 {
 	if (t1->type != t2->type || t1->type != V4L2_DV_BT_656_1120)
 		return false;
@@ -239,9 +246,14 @@
 	    t1->bt.pixelclock >= t2->bt.pixelclock - pclock_delta &&
 	    t1->bt.pixelclock <= t2->bt.pixelclock + pclock_delta &&
 	    t1->bt.hfrontporch == t2->bt.hfrontporch &&
+	    t1->bt.hsync == t2->bt.hsync &&
+	    t1->bt.hbackporch == t2->bt.hbackporch &&
 	    t1->bt.vfrontporch == t2->bt.vfrontporch &&
 	    t1->bt.vsync == t2->bt.vsync &&
 	    t1->bt.vbackporch == t2->bt.vbackporch &&
+	    (!match_reduced_fps ||
+	     (t1->bt.flags & V4L2_DV_FL_REDUCED_FPS) ==
+		(t2->bt.flags & V4L2_DV_FL_REDUCED_FPS)) &&
 	    (!t1->bt.interlaced ||
 		(t1->bt.il_vfrontporch == t2->bt.il_vfrontporch &&
 		 t1->bt.il_vsync == t2->bt.il_vsync &&
diff --git a/drivers/media/v4l2-core/v4l2-flash-led-class.c b/drivers/media/v4l2-core/v4l2-flash-led-class.c
index 5bdfb8d..5d67335 100644
--- a/drivers/media/v4l2-core/v4l2-flash-led-class.c
+++ b/drivers/media/v4l2-core/v4l2-flash-led-class.c
@@ -107,10 +107,10 @@
 		if (ctrls[LED_MODE]->val != V4L2_FLASH_LED_MODE_TORCH)
 			return;
 
-		led_set_brightness(&v4l2_flash->fled_cdev->led_cdev,
+		led_set_brightness_sync(&v4l2_flash->fled_cdev->led_cdev,
 					brightness);
 	} else {
-		led_set_brightness(&v4l2_flash->iled_cdev->led_cdev,
+		led_set_brightness_sync(&v4l2_flash->iled_cdev->led_cdev,
 					brightness);
 	}
 }
@@ -206,11 +206,11 @@
 	case V4L2_CID_FLASH_LED_MODE:
 		switch (c->val) {
 		case V4L2_FLASH_LED_MODE_NONE:
-			led_set_brightness(led_cdev, LED_OFF);
+			led_set_brightness_sync(led_cdev, LED_OFF);
 			return led_set_flash_strobe(fled_cdev, false);
 		case V4L2_FLASH_LED_MODE_FLASH:
 			/* Turn the torch LED off */
-			led_set_brightness(led_cdev, LED_OFF);
+			led_set_brightness_sync(led_cdev, LED_OFF);
 			if (ctrls[STROBE_SOURCE]) {
 				external_strobe = (ctrls[STROBE_SOURCE]->val ==
 					V4L2_FLASH_STROBE_SOURCE_EXTERNAL);
diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c
index 7486af2..8a018c6 100644
--- a/drivers/media/v4l2-core/v4l2-ioctl.c
+++ b/drivers/media/v4l2-core/v4l2-ioctl.c
@@ -565,8 +565,8 @@
 	const struct v4l2_ext_controls *p = arg;
 	int i;
 
-	pr_cont("class=0x%x, count=%d, error_idx=%d",
-			p->ctrl_class, p->count, p->error_idx);
+	pr_cont("which=0x%x, count=%d, error_idx=%d",
+			p->which, p->count, p->error_idx);
 	for (i = 0; i < p->count; i++) {
 		if (!p->controls[i].size)
 			pr_cont(", id/val=0x%x/0x%x",
@@ -902,13 +902,13 @@
 	   Only when passed in through VIDIOC_G_CTRL and VIDIOC_S_CTRL
 	   is it allowed for backwards compatibility.
 	 */
-	if (!allow_priv && c->ctrl_class == V4L2_CID_PRIVATE_BASE)
+	if (!allow_priv && c->which == V4L2_CID_PRIVATE_BASE)
 		return 0;
-	if (c->ctrl_class == 0)
+	if (!c->which)
 		return 1;
 	/* Check that all controls are from the same control class. */
 	for (i = 0; i < c->count; i++) {
-		if (V4L2_CTRL_ID2CLASS(c->controls[i].id) != c->ctrl_class) {
+		if (V4L2_CTRL_ID2WHICH(c->controls[i].id) != c->which) {
 			c->error_idx = i;
 			return 0;
 		}
@@ -1969,7 +1969,7 @@
 	if (ops->vidioc_g_ext_ctrls == NULL)
 		return -ENOTTY;
 
-	ctrls.ctrl_class = V4L2_CTRL_ID2CLASS(p->id);
+	ctrls.which = V4L2_CTRL_ID2WHICH(p->id);
 	ctrls.count = 1;
 	ctrls.controls = &ctrl;
 	ctrl.id = p->id;
@@ -2003,7 +2003,7 @@
 	if (ops->vidioc_s_ext_ctrls == NULL)
 		return -ENOTTY;
 
-	ctrls.ctrl_class = V4L2_CTRL_ID2CLASS(p->id);
+	ctrls.which = V4L2_CTRL_ID2WHICH(p->id);
 	ctrls.count = 1;
 	ctrls.controls = &ctrl;
 	ctrl.id = p->id;
diff --git a/drivers/media/v4l2-core/videobuf2-core.c b/drivers/media/v4l2-core/videobuf2-core.c
index 33bdd81..c5d49d7 100644
--- a/drivers/media/v4l2-core/videobuf2-core.c
+++ b/drivers/media/v4l2-core/videobuf2-core.c
@@ -28,11 +28,161 @@
 
 #include <trace/events/vb2.h>
 
-#include "videobuf2-internal.h"
+static int debug;
+module_param(debug, int, 0644);
 
-int vb2_debug;
-EXPORT_SYMBOL_GPL(vb2_debug);
-module_param_named(debug, vb2_debug, int, 0644);
+#define dprintk(level, fmt, arg...)					      \
+	do {								      \
+		if (debug >= level)					      \
+			pr_info("vb2-core: %s: " fmt, __func__, ## arg); \
+	} while (0)
+
+#ifdef CONFIG_VIDEO_ADV_DEBUG
+
+/*
+ * If advanced debugging is on, then count how often each op is called
+ * successfully, which can either be per-buffer or per-queue.
+ *
+ * This makes it easy to check that the 'init' and 'cleanup'
+ * (and variations thereof) stay balanced.
+ */
+
+#define log_memop(vb, op)						\
+	dprintk(2, "call_memop(%p, %d, %s)%s\n",			\
+		(vb)->vb2_queue, (vb)->index, #op,			\
+		(vb)->vb2_queue->mem_ops->op ? "" : " (nop)")
+
+#define call_memop(vb, op, args...)					\
+({									\
+	struct vb2_queue *_q = (vb)->vb2_queue;				\
+	int err;							\
+									\
+	log_memop(vb, op);						\
+	err = _q->mem_ops->op ? _q->mem_ops->op(args) : 0;		\
+	if (!err)							\
+		(vb)->cnt_mem_ ## op++;					\
+	err;								\
+})
+
+#define call_ptr_memop(vb, op, args...)					\
+({									\
+	struct vb2_queue *_q = (vb)->vb2_queue;				\
+	void *ptr;							\
+									\
+	log_memop(vb, op);						\
+	ptr = _q->mem_ops->op ? _q->mem_ops->op(args) : NULL;		\
+	if (!IS_ERR_OR_NULL(ptr))					\
+		(vb)->cnt_mem_ ## op++;					\
+	ptr;								\
+})
+
+#define call_void_memop(vb, op, args...)				\
+({									\
+	struct vb2_queue *_q = (vb)->vb2_queue;				\
+									\
+	log_memop(vb, op);						\
+	if (_q->mem_ops->op)						\
+		_q->mem_ops->op(args);					\
+	(vb)->cnt_mem_ ## op++;						\
+})
+
+#define log_qop(q, op)							\
+	dprintk(2, "call_qop(%p, %s)%s\n", q, #op,			\
+		(q)->ops->op ? "" : " (nop)")
+
+#define call_qop(q, op, args...)					\
+({									\
+	int err;							\
+									\
+	log_qop(q, op);							\
+	err = (q)->ops->op ? (q)->ops->op(args) : 0;			\
+	if (!err)							\
+		(q)->cnt_ ## op++;					\
+	err;								\
+})
+
+#define call_void_qop(q, op, args...)					\
+({									\
+	log_qop(q, op);							\
+	if ((q)->ops->op)						\
+		(q)->ops->op(args);					\
+	(q)->cnt_ ## op++;						\
+})
+
+#define log_vb_qop(vb, op, args...)					\
+	dprintk(2, "call_vb_qop(%p, %d, %s)%s\n",			\
+		(vb)->vb2_queue, (vb)->index, #op,			\
+		(vb)->vb2_queue->ops->op ? "" : " (nop)")
+
+#define call_vb_qop(vb, op, args...)					\
+({									\
+	int err;							\
+									\
+	log_vb_qop(vb, op);						\
+	err = (vb)->vb2_queue->ops->op ?				\
+		(vb)->vb2_queue->ops->op(args) : 0;			\
+	if (!err)							\
+		(vb)->cnt_ ## op++;					\
+	err;								\
+})
+
+#define call_void_vb_qop(vb, op, args...)				\
+({									\
+	log_vb_qop(vb, op);						\
+	if ((vb)->vb2_queue->ops->op)					\
+		(vb)->vb2_queue->ops->op(args);				\
+	(vb)->cnt_ ## op++;						\
+})
+
+#else
+
+#define call_memop(vb, op, args...)					\
+	((vb)->vb2_queue->mem_ops->op ?					\
+		(vb)->vb2_queue->mem_ops->op(args) : 0)
+
+#define call_ptr_memop(vb, op, args...)					\
+	((vb)->vb2_queue->mem_ops->op ?					\
+		(vb)->vb2_queue->mem_ops->op(args) : NULL)
+
+#define call_void_memop(vb, op, args...)				\
+	do {								\
+		if ((vb)->vb2_queue->mem_ops->op)			\
+			(vb)->vb2_queue->mem_ops->op(args);		\
+	} while (0)
+
+#define call_qop(q, op, args...)					\
+	((q)->ops->op ? (q)->ops->op(args) : 0)
+
+#define call_void_qop(q, op, args...)					\
+	do {								\
+		if ((q)->ops->op)					\
+			(q)->ops->op(args);				\
+	} while (0)
+
+#define call_vb_qop(vb, op, args...)					\
+	((vb)->vb2_queue->ops->op ? (vb)->vb2_queue->ops->op(args) : 0)
+
+#define call_void_vb_qop(vb, op, args...)				\
+	do {								\
+		if ((vb)->vb2_queue->ops->op)				\
+			(vb)->vb2_queue->ops->op(args);			\
+	} while (0)
+
+#endif
+
+#define call_bufop(q, op, args...)					\
+({									\
+	int ret = 0;							\
+	if (q && q->buf_ops && q->buf_ops->op)				\
+		ret = q->buf_ops->op(args);				\
+	ret;								\
+})
+
+#define call_void_bufop(q, op, args...)					\
+({									\
+	if (q && q->buf_ops && q->buf_ops->op)				\
+		q->buf_ops->op(args);					\
+})
 
 static void __vb2_queue_cancel(struct vb2_queue *q);
 static void __enqueue_in_driver(struct vb2_buffer *vb);
@@ -53,7 +203,7 @@
 	 * NOTE: mmapped areas should be page aligned
 	 */
 	for (plane = 0; plane < vb->num_planes; ++plane) {
-		unsigned long size = PAGE_ALIGN(q->plane_sizes[plane]);
+		unsigned long size = PAGE_ALIGN(vb->planes[plane].length);
 
 		mem_priv = call_ptr_memop(vb, alloc, q->alloc_ctx[plane],
 				      size, dma_dir, q->gfp_flags);
@@ -62,7 +212,6 @@
 
 		/* Associate allocator private data with this plane */
 		vb->planes[plane].mem_priv = mem_priv;
-		vb->planes[plane].length = q->plane_sizes[plane];
 	}
 
 	return 0;
@@ -137,57 +286,30 @@
 }
 
 /**
- * __setup_lengths() - setup initial lengths for every plane in
- * every buffer on the queue
- */
-static void __setup_lengths(struct vb2_queue *q, unsigned int n)
-{
-	unsigned int buffer, plane;
-	struct vb2_buffer *vb;
-
-	for (buffer = q->num_buffers; buffer < q->num_buffers + n; ++buffer) {
-		vb = q->bufs[buffer];
-		if (!vb)
-			continue;
-
-		for (plane = 0; plane < vb->num_planes; ++plane)
-			vb->planes[plane].length = q->plane_sizes[plane];
-	}
-}
-
-/**
  * __setup_offsets() - setup unique offsets ("cookies") for every plane in
- * every buffer on the queue
+ * the buffer.
  */
-static void __setup_offsets(struct vb2_queue *q, unsigned int n)
+static void __setup_offsets(struct vb2_buffer *vb)
 {
-	unsigned int buffer, plane;
-	struct vb2_buffer *vb;
-	unsigned long off;
+	struct vb2_queue *q = vb->vb2_queue;
+	unsigned int plane;
+	unsigned long off = 0;
 
-	if (q->num_buffers) {
-		struct vb2_plane *p;
-		vb = q->bufs[q->num_buffers - 1];
-		p = &vb->planes[vb->num_planes - 1];
+	if (vb->index) {
+		struct vb2_buffer *prev = q->bufs[vb->index - 1];
+		struct vb2_plane *p = &prev->planes[prev->num_planes - 1];
+
 		off = PAGE_ALIGN(p->m.offset + p->length);
-	} else {
-		off = 0;
 	}
 
-	for (buffer = q->num_buffers; buffer < q->num_buffers + n; ++buffer) {
-		vb = q->bufs[buffer];
-		if (!vb)
-			continue;
+	for (plane = 0; plane < vb->num_planes; ++plane) {
+		vb->planes[plane].m.offset = off;
 
-		for (plane = 0; plane < vb->num_planes; ++plane) {
-			vb->planes[plane].m.offset = off;
+		dprintk(3, "buffer %d, plane %d offset 0x%08lx\n",
+				vb->index, plane, off);
 
-			dprintk(3, "buffer %d, plane %d offset 0x%08lx\n",
-					buffer, plane, off);
-
-			off += vb->planes[plane].length;
-			off = PAGE_ALIGN(off);
-		}
+		off += vb->planes[plane].length;
+		off = PAGE_ALIGN(off);
 	}
 }
 
@@ -199,9 +321,10 @@
  * Returns the number of buffers successfully allocated.
  */
 static int __vb2_queue_alloc(struct vb2_queue *q, enum vb2_memory memory,
-			     unsigned int num_buffers, unsigned int num_planes)
+			     unsigned int num_buffers, unsigned int num_planes,
+			     const unsigned plane_sizes[VB2_MAX_PLANES])
 {
-	unsigned int buffer;
+	unsigned int buffer, plane;
 	struct vb2_buffer *vb;
 	int ret;
 
@@ -219,6 +342,11 @@
 		vb->index = q->num_buffers + buffer;
 		vb->type = q->type;
 		vb->memory = memory;
+		for (plane = 0; plane < num_planes; ++plane) {
+			vb->planes[plane].length = plane_sizes[plane];
+			vb->planes[plane].min_length = plane_sizes[plane];
+		}
+		q->bufs[vb->index] = vb;
 
 		/* Allocate video buffer memory for the MMAP type */
 		if (memory == VB2_MEMORY_MMAP) {
@@ -226,9 +354,11 @@
 			if (ret) {
 				dprintk(1, "failed allocating memory for "
 						"buffer %d\n", buffer);
+				q->bufs[vb->index] = NULL;
 				kfree(vb);
 				break;
 			}
+			__setup_offsets(vb);
 			/*
 			 * Call the driver-provided buffer initialization
 			 * callback, if given. An error in initialization
@@ -239,18 +369,13 @@
 				dprintk(1, "buffer %d %p initialization"
 					" failed\n", buffer, vb);
 				__vb2_buf_mem_free(vb);
+				q->bufs[vb->index] = NULL;
 				kfree(vb);
 				break;
 			}
 		}
-
-		q->bufs[q->num_buffers + buffer] = vb;
 	}
 
-	__setup_lengths(q, buffer);
-	if (memory == VB2_MEMORY_MMAP)
-		__setup_offsets(q, buffer);
-
 	dprintk(1, "allocated %d buffers, %d plane(s) each\n",
 			buffer, num_planes);
 
@@ -330,7 +455,7 @@
 		bool unbalanced = q->cnt_start_streaming != q->cnt_stop_streaming ||
 				  q->cnt_wait_prepare != q->cnt_wait_finish;
 
-		if (unbalanced || vb2_debug) {
+		if (unbalanced || debug) {
 			pr_info("vb2: counters for queue %p:%s\n", q,
 				unbalanced ? " UNBALANCED!" : "");
 			pr_info("vb2:     setup: %u start_streaming: %u stop_streaming: %u\n",
@@ -356,7 +481,7 @@
 				  vb->cnt_buf_prepare != vb->cnt_buf_finish ||
 				  vb->cnt_buf_init != vb->cnt_buf_cleanup;
 
-		if (unbalanced || vb2_debug) {
+		if (unbalanced || debug) {
 			pr_info("vb2:   counters for queue %p, buffer %d:%s\n",
 				q, buffer, unbalanced ? " UNBALANCED!" : "");
 			pr_info("vb2:     buf_init: %u buf_cleanup: %u buf_prepare: %u buf_finish: %u\n",
@@ -442,13 +567,10 @@
  * Should be called from vidioc_querybuf ioctl handler in driver.
  * The passed buffer should have been verified.
  * This function fills the relevant information for the userspace.
- *
- * The return values from this function are intended to be directly returned
- * from vidioc_querybuf handler in driver.
  */
-int vb2_core_querybuf(struct vb2_queue *q, unsigned int index, void *pb)
+void vb2_core_querybuf(struct vb2_queue *q, unsigned int index, void *pb)
 {
-	return call_bufop(q, fill_user_buffer, q->bufs[index], pb);
+	call_void_bufop(q, fill_user_buffer, q->bufs[index], pb);
 }
 EXPORT_SYMBOL_GPL(vb2_core_querybuf);
 
@@ -570,6 +692,7 @@
 		unsigned int *count)
 {
 	unsigned int num_buffers, allocated_buffers, num_planes = 0;
+	unsigned plane_sizes[VB2_MAX_PLANES] = { };
 	int ret;
 
 	if (q->streaming) {
@@ -613,7 +736,6 @@
 	 */
 	num_buffers = min_t(unsigned int, *count, VB2_MAX_FRAME);
 	num_buffers = max_t(unsigned int, num_buffers, q->min_buffers_needed);
-	memset(q->plane_sizes, 0, sizeof(q->plane_sizes));
 	memset(q->alloc_ctx, 0, sizeof(q->alloc_ctx));
 	q->memory = memory;
 
@@ -621,14 +743,14 @@
 	 * Ask the driver how many buffers and planes per buffer it requires.
 	 * Driver also sets the size and allocator context for each plane.
 	 */
-	ret = call_qop(q, queue_setup, q, NULL, &num_buffers, &num_planes,
-		       q->plane_sizes, q->alloc_ctx);
+	ret = call_qop(q, queue_setup, q, &num_buffers, &num_planes,
+		       plane_sizes, q->alloc_ctx);
 	if (ret)
 		return ret;
 
 	/* Finally, allocate buffers and video memory */
 	allocated_buffers =
-		__vb2_queue_alloc(q, memory, num_buffers, num_planes);
+		__vb2_queue_alloc(q, memory, num_buffers, num_planes, plane_sizes);
 	if (allocated_buffers == 0) {
 		dprintk(1, "memory allocation failed\n");
 		return -ENOMEM;
@@ -646,9 +768,16 @@
 	 */
 	if (!ret && allocated_buffers < num_buffers) {
 		num_buffers = allocated_buffers;
+		/*
+		 * num_planes is set by the previous queue_setup(), but since it
+		 * signals to queue_setup() whether it is called from create_bufs()
+		 * vs reqbufs() we zero it here to signal that queue_setup() is
+		 * called for the reqbufs() case.
+		 */
+		num_planes = 0;
 
-		ret = call_qop(q, queue_setup, q, NULL, &num_buffers,
-			       &num_planes, q->plane_sizes, q->alloc_ctx);
+		ret = call_qop(q, queue_setup, q, &num_buffers,
+			       &num_planes, plane_sizes, q->alloc_ctx);
 
 		if (!ret && allocated_buffers < num_buffers)
 			ret = -ENOMEM;
@@ -701,9 +830,11 @@
  * from vidioc_create_bufs handler in driver.
  */
 int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory,
-		unsigned int *count, const void *parg)
+		unsigned int *count, unsigned requested_planes,
+		const unsigned requested_sizes[])
 {
 	unsigned int num_planes = 0, num_buffers, allocated_buffers;
+	unsigned plane_sizes[VB2_MAX_PLANES] = { };
 	int ret;
 
 	if (q->num_buffers == VB2_MAX_FRAME) {
@@ -712,7 +843,6 @@
 	}
 
 	if (!q->num_buffers) {
-		memset(q->plane_sizes, 0, sizeof(q->plane_sizes));
 		memset(q->alloc_ctx, 0, sizeof(q->alloc_ctx));
 		q->memory = memory;
 		q->waiting_for_buffers = !q->is_output;
@@ -720,18 +850,23 @@
 
 	num_buffers = min(*count, VB2_MAX_FRAME - q->num_buffers);
 
+	if (requested_planes && requested_sizes) {
+		num_planes = requested_planes;
+		memcpy(plane_sizes, requested_sizes, sizeof(plane_sizes));
+	}
+
 	/*
 	 * Ask the driver, whether the requested number of buffers, planes per
 	 * buffer and their sizes are acceptable
 	 */
-	ret = call_qop(q, queue_setup, q, parg, &num_buffers,
-		       &num_planes, q->plane_sizes, q->alloc_ctx);
+	ret = call_qop(q, queue_setup, q, &num_buffers,
+		       &num_planes, plane_sizes, q->alloc_ctx);
 	if (ret)
 		return ret;
 
 	/* Finally, allocate buffers and video memory */
 	allocated_buffers = __vb2_queue_alloc(q, memory, num_buffers,
-				num_planes);
+				num_planes, plane_sizes);
 	if (allocated_buffers == 0) {
 		dprintk(1, "memory allocation failed\n");
 		return -ENOMEM;
@@ -747,8 +882,8 @@
 		 * q->num_buffers contains the total number of buffers, that the
 		 * queue driver has set up
 		 */
-		ret = call_qop(q, queue_setup, q, parg, &num_buffers,
-			       &num_planes, q->plane_sizes, q->alloc_ctx);
+		ret = call_qop(q, queue_setup, q, &num_buffers,
+			       &num_planes, plane_sizes, q->alloc_ctx);
 
 		if (!ret && allocated_buffers < num_buffers)
 			ret = -ENOMEM;
@@ -964,11 +1099,12 @@
 				"reacquiring memory\n", plane);
 
 		/* Check if the provided plane buffer is large enough */
-		if (planes[plane].length < q->plane_sizes[plane]) {
+		if (planes[plane].length < vb->planes[plane].min_length) {
 			dprintk(1, "provided buffer size %u is less than "
 						"setup size %u for plane %d\n",
 						planes[plane].length,
-						q->plane_sizes[plane], plane);
+						vb->planes[plane].min_length,
+						plane);
 			ret = -EINVAL;
 			goto err;
 		}
@@ -1081,7 +1217,7 @@
 		if (planes[plane].length == 0)
 			planes[plane].length = dbuf->size;
 
-		if (planes[plane].length < q->plane_sizes[plane]) {
+		if (planes[plane].length < vb->planes[plane].min_length) {
 			dprintk(1, "invalid dmabuf length for plane %d\n",
 				plane);
 			ret = -EINVAL;
@@ -1263,9 +1399,7 @@
 		return ret;
 
 	/* Fill buffer information for the userspace */
-	ret = call_bufop(q, fill_user_buffer, vb, pb);
-	if (ret)
-		return ret;
+	call_void_bufop(q, fill_user_buffer, vb, pb);
 
 	dprintk(1, "prepare of buffer %d succeeded\n", vb->index);
 
@@ -1386,7 +1520,7 @@
 	q->waiting_for_buffers = false;
 	vb->state = VB2_BUF_STATE_QUEUED;
 
-	call_bufop(q, set_timestamp, vb, pb);
+	call_void_bufop(q, copy_timestamp, vb, pb);
 
 	trace_vb2_qbuf(q, vb);
 
@@ -1398,9 +1532,7 @@
 		__enqueue_in_driver(vb);
 
 	/* Fill buffer information for the userspace */
-	ret = call_bufop(q, fill_user_buffer, vb, pb);
-	if (ret)
-		return ret;
+	call_void_bufop(q, fill_user_buffer, vb, pb);
 
 	/*
 	 * If streamon has been called, and we haven't yet called
@@ -1623,9 +1755,7 @@
 	call_void_vb_qop(vb, buf_finish, vb);
 
 	/* Fill buffer information for the userspace */
-	ret = call_bufop(q, fill_user_buffer, vb, pb);
-	if (ret)
-		return ret;
+	call_void_bufop(q, fill_user_buffer, vb, pb);
 
 	/* Remove from videobuf queue */
 	list_del(&vb->queued_entry);
@@ -2073,6 +2203,8 @@
 }
 EXPORT_SYMBOL_GPL(vb2_core_queue_init);
 
+static int __vb2_init_fileio(struct vb2_queue *q, int read);
+static int __vb2_cleanup_fileio(struct vb2_queue *q);
 /**
  * vb2_core_queue_release() - stop streaming, release the queue and free memory
  * @q:		videobuf2 queue
@@ -2083,6 +2215,7 @@
  */
 void vb2_core_queue_release(struct vb2_queue *q)
 {
+	__vb2_cleanup_fileio(q);
 	__vb2_queue_cancel(q);
 	mutex_lock(&q->mmap_lock);
 	__vb2_queue_free(q, q->num_buffers);
@@ -2090,6 +2223,619 @@
 }
 EXPORT_SYMBOL_GPL(vb2_core_queue_release);
 
-MODULE_DESCRIPTION("Driver helper framework for Video for Linux 2");
+/**
+ * vb2_core_poll() - implements poll userspace operation
+ * @q:		videobuf2 queue
+ * @file:	file argument passed to the poll file operation handler
+ * @wait:	wait argument passed to the poll file operation handler
+ *
+ * This function implements poll file operation handler for a driver.
+ * For CAPTURE queues, if a buffer is ready to be dequeued, the userspace will
+ * be informed that the file descriptor of a video device is available for
+ * reading.
+ * For OUTPUT queues, if a buffer is ready to be dequeued, the file descriptor
+ * will be reported as available for writing.
+ *
+ * The return values from this function are intended to be directly returned
+ * from poll handler in driver.
+ */
+unsigned int vb2_core_poll(struct vb2_queue *q, struct file *file,
+		poll_table *wait)
+{
+	unsigned long req_events = poll_requested_events(wait);
+	struct vb2_buffer *vb = NULL;
+	unsigned long flags;
+
+	if (!q->is_output && !(req_events & (POLLIN | POLLRDNORM)))
+		return 0;
+	if (q->is_output && !(req_events & (POLLOUT | POLLWRNORM)))
+		return 0;
+
+	/*
+	 * Start file I/O emulator only if streaming API has not been used yet.
+	 */
+	if (q->num_buffers == 0 && !vb2_fileio_is_active(q)) {
+		if (!q->is_output && (q->io_modes & VB2_READ) &&
+				(req_events & (POLLIN | POLLRDNORM))) {
+			if (__vb2_init_fileio(q, 1))
+				return POLLERR;
+		}
+		if (q->is_output && (q->io_modes & VB2_WRITE) &&
+				(req_events & (POLLOUT | POLLWRNORM))) {
+			if (__vb2_init_fileio(q, 0))
+				return POLLERR;
+			/*
+			 * Write to OUTPUT queue can be done immediately.
+			 */
+			return POLLOUT | POLLWRNORM;
+		}
+	}
+
+	/*
+	 * There is nothing to wait for if the queue isn't streaming, or if the
+	 * error flag is set.
+	 */
+	if (!vb2_is_streaming(q) || q->error)
+		return POLLERR;
+
+	/*
+	 * For output streams you can call write() as long as there are fewer
+	 * buffers queued than there are buffers available.
+	 */
+	if (q->is_output && q->fileio && q->queued_count < q->num_buffers)
+		return POLLOUT | POLLWRNORM;
+
+	if (list_empty(&q->done_list)) {
+		/*
+		 * If the last buffer was dequeued from a capture queue,
+		 * return immediately. DQBUF will return -EPIPE.
+		 */
+		if (q->last_buffer_dequeued)
+			return POLLIN | POLLRDNORM;
+
+		poll_wait(file, &q->done_wq, wait);
+	}
+
+	/*
+	 * Take first buffer available for dequeuing.
+	 */
+	spin_lock_irqsave(&q->done_lock, flags);
+	if (!list_empty(&q->done_list))
+		vb = list_first_entry(&q->done_list, struct vb2_buffer,
+					done_entry);
+	spin_unlock_irqrestore(&q->done_lock, flags);
+
+	if (vb && (vb->state == VB2_BUF_STATE_DONE
+			|| vb->state == VB2_BUF_STATE_ERROR)) {
+		return (q->is_output) ?
+				POLLOUT | POLLWRNORM :
+				POLLIN | POLLRDNORM;
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(vb2_core_poll);
+
+/**
+ * struct vb2_fileio_buf - buffer context used by file io emulator
+ *
+ * vb2 provides a compatibility layer and emulator of file io (read and
+ * write) calls on top of streaming API. This structure is used for
+ * tracking context related to the buffers.
+ */
+struct vb2_fileio_buf {
+	void *vaddr;
+	unsigned int size;
+	unsigned int pos;
+	unsigned int queued:1;
+};
+
+/**
+ * struct vb2_fileio_data - queue context used by file io emulator
+ *
+ * @cur_index:	the index of the buffer currently being read from or
+ *		written to. If equal to q->num_buffers then a new buffer
+ *		must be dequeued.
+ * @initial_index: in the read() case all buffers are queued up immediately
+ *		in __vb2_init_fileio() and __vb2_perform_fileio() just cycles
+ *		buffers. However, in the write() case no buffers are initially
+ *		queued, instead whenever a buffer is full it is queued up by
+ *		__vb2_perform_fileio(). Only once all available buffers have
+ *		been queued up will __vb2_perform_fileio() start to dequeue
+ *		buffers. This means that initially __vb2_perform_fileio()
+ *		needs to know what buffer index to use when it is queuing up
+ *		the buffers for the first time. That initial index is stored
+ *		in this field. Once it is equal to q->num_buffers all
+ *		available buffers have been queued and __vb2_perform_fileio()
+ *		should start the normal dequeue/queue cycle.
+ *
+ * vb2 provides a compatibility layer and emulator of file io (read and
+ * write) calls on top of streaming API. For proper operation it required
+ * this structure to save the driver state between each call of the read
+ * or write function.
+ */
+struct vb2_fileio_data {
+	unsigned int count;
+	unsigned int type;
+	unsigned int memory;
+	struct vb2_buffer *b;
+	struct vb2_fileio_buf bufs[VB2_MAX_FRAME];
+	unsigned int cur_index;
+	unsigned int initial_index;
+	unsigned int q_count;
+	unsigned int dq_count;
+	unsigned read_once:1;
+	unsigned write_immediately:1;
+};
+
+/**
+ * __vb2_init_fileio() - initialize file io emulator
+ * @q:		videobuf2 queue
+ * @read:	mode selector (1 means read, 0 means write)
+ */
+static int __vb2_init_fileio(struct vb2_queue *q, int read)
+{
+	struct vb2_fileio_data *fileio;
+	int i, ret;
+	unsigned int count = 0;
+
+	/*
+	 * Sanity check
+	 */
+	if (WARN_ON((read && !(q->io_modes & VB2_READ)) ||
+		    (!read && !(q->io_modes & VB2_WRITE))))
+		return -EINVAL;
+
+	/*
+	 * Check if device supports mapping buffers to kernel virtual space.
+	 */
+	if (!q->mem_ops->vaddr)
+		return -EBUSY;
+
+	/*
+	 * Check if streaming api has not been already activated.
+	 */
+	if (q->streaming || q->num_buffers > 0)
+		return -EBUSY;
+
+	/*
+	 * Start with count 1, driver can increase it in queue_setup()
+	 */
+	count = 1;
+
+	dprintk(3, "setting up file io: mode %s, count %d, read_once %d, write_immediately %d\n",
+		(read) ? "read" : "write", count, q->fileio_read_once,
+		q->fileio_write_immediately);
+
+	fileio = kzalloc(sizeof(*fileio), GFP_KERNEL);
+	if (fileio == NULL)
+		return -ENOMEM;
+
+	fileio->b = kzalloc(q->buf_struct_size, GFP_KERNEL);
+	if (fileio->b == NULL) {
+		kfree(fileio);
+		return -ENOMEM;
+	}
+
+	fileio->read_once = q->fileio_read_once;
+	fileio->write_immediately = q->fileio_write_immediately;
+
+	/*
+	 * Request buffers and use MMAP type to force driver
+	 * to allocate buffers by itself.
+	 */
+	fileio->count = count;
+	fileio->memory = VB2_MEMORY_MMAP;
+	fileio->type = q->type;
+	q->fileio = fileio;
+	ret = vb2_core_reqbufs(q, fileio->memory, &fileio->count);
+	if (ret)
+		goto err_kfree;
+
+	/*
+	 * Check if plane_count is correct
+	 * (multiplane buffers are not supported).
+	 */
+	if (q->bufs[0]->num_planes != 1) {
+		ret = -EBUSY;
+		goto err_reqbufs;
+	}
+
+	/*
+	 * Get kernel address of each buffer.
+	 */
+	for (i = 0; i < q->num_buffers; i++) {
+		fileio->bufs[i].vaddr = vb2_plane_vaddr(q->bufs[i], 0);
+		if (fileio->bufs[i].vaddr == NULL) {
+			ret = -EINVAL;
+			goto err_reqbufs;
+		}
+		fileio->bufs[i].size = vb2_plane_size(q->bufs[i], 0);
+	}
+
+	/*
+	 * Read mode requires pre queuing of all buffers.
+	 */
+	if (read) {
+		/*
+		 * Queue all buffers.
+		 */
+		for (i = 0; i < q->num_buffers; i++) {
+			struct vb2_buffer *b = fileio->b;
+
+			memset(b, 0, q->buf_struct_size);
+			b->type = q->type;
+			b->memory = q->memory;
+			b->index = i;
+			ret = vb2_core_qbuf(q, i, b);
+			if (ret)
+				goto err_reqbufs;
+			fileio->bufs[i].queued = 1;
+		}
+		/*
+		 * All buffers have been queued, so mark that by setting
+		 * initial_index to q->num_buffers
+		 */
+		fileio->initial_index = q->num_buffers;
+		fileio->cur_index = q->num_buffers;
+	}
+
+	/*
+	 * Start streaming.
+	 */
+	ret = vb2_core_streamon(q, q->type);
+	if (ret)
+		goto err_reqbufs;
+
+	return ret;
+
+err_reqbufs:
+	fileio->count = 0;
+	vb2_core_reqbufs(q, fileio->memory, &fileio->count);
+
+err_kfree:
+	q->fileio = NULL;
+	kfree(fileio);
+	return ret;
+}
+
+/**
+ * __vb2_cleanup_fileio() - free resourced used by file io emulator
+ * @q:		videobuf2 queue
+ */
+static int __vb2_cleanup_fileio(struct vb2_queue *q)
+{
+	struct vb2_fileio_data *fileio = q->fileio;
+
+	if (fileio) {
+		vb2_core_streamoff(q, q->type);
+		q->fileio = NULL;
+		fileio->count = 0;
+		vb2_core_reqbufs(q, fileio->memory, &fileio->count);
+		kfree(fileio->b);
+		kfree(fileio);
+		dprintk(3, "file io emulator closed\n");
+	}
+	return 0;
+}
+
+/**
+ * __vb2_perform_fileio() - perform a single file io (read or write) operation
+ * @q:		videobuf2 queue
+ * @data:	pointed to target userspace buffer
+ * @count:	number of bytes to read or write
+ * @ppos:	file handle position tracking pointer
+ * @nonblock:	mode selector (1 means blocking calls, 0 means nonblocking)
+ * @read:	access mode selector (1 means read, 0 means write)
+ */
+static size_t __vb2_perform_fileio(struct vb2_queue *q, char __user *data, size_t count,
+		loff_t *ppos, int nonblock, int read)
+{
+	struct vb2_fileio_data *fileio;
+	struct vb2_fileio_buf *buf;
+	bool is_multiplanar = q->is_multiplanar;
+	/*
+	 * When using write() to write data to an output video node the vb2 core
+	 * should copy timestamps if V4L2_BUF_FLAG_TIMESTAMP_COPY is set. Nobody
+	 * else is able to provide this information with the write() operation.
+	 */
+	bool copy_timestamp = !read && q->copy_timestamp;
+	int ret, index;
+
+	dprintk(3, "mode %s, offset %ld, count %zd, %sblocking\n",
+		read ? "read" : "write", (long)*ppos, count,
+		nonblock ? "non" : "");
+
+	if (!data)
+		return -EINVAL;
+
+	/*
+	 * Initialize emulator on first call.
+	 */
+	if (!vb2_fileio_is_active(q)) {
+		ret = __vb2_init_fileio(q, read);
+		dprintk(3, "vb2_init_fileio result: %d\n", ret);
+		if (ret)
+			return ret;
+	}
+	fileio = q->fileio;
+
+	/*
+	 * Check if we need to dequeue the buffer.
+	 */
+	index = fileio->cur_index;
+	if (index >= q->num_buffers) {
+		struct vb2_buffer *b = fileio->b;
+
+		/*
+		 * Call vb2_dqbuf to get buffer back.
+		 */
+		memset(b, 0, q->buf_struct_size);
+		b->type = q->type;
+		b->memory = q->memory;
+		ret = vb2_core_dqbuf(q, b, nonblock);
+		dprintk(5, "vb2_dqbuf result: %d\n", ret);
+		if (ret)
+			return ret;
+		fileio->dq_count += 1;
+
+		fileio->cur_index = index = b->index;
+		buf = &fileio->bufs[index];
+
+		/*
+		 * Get number of bytes filled by the driver
+		 */
+		buf->pos = 0;
+		buf->queued = 0;
+		buf->size = read ? vb2_get_plane_payload(q->bufs[index], 0)
+				 : vb2_plane_size(q->bufs[index], 0);
+		/* Compensate for data_offset on read in the multiplanar case. */
+		if (is_multiplanar && read &&
+				b->planes[0].data_offset < buf->size) {
+			buf->pos = b->planes[0].data_offset;
+			buf->size -= buf->pos;
+		}
+	} else {
+		buf = &fileio->bufs[index];
+	}
+
+	/*
+	 * Limit count on last few bytes of the buffer.
+	 */
+	if (buf->pos + count > buf->size) {
+		count = buf->size - buf->pos;
+		dprintk(5, "reducing read count: %zd\n", count);
+	}
+
+	/*
+	 * Transfer data to userspace.
+	 */
+	dprintk(3, "copying %zd bytes - buffer %d, offset %u\n",
+		count, index, buf->pos);
+	if (read)
+		ret = copy_to_user(data, buf->vaddr + buf->pos, count);
+	else
+		ret = copy_from_user(buf->vaddr + buf->pos, data, count);
+	if (ret) {
+		dprintk(3, "error copying data\n");
+		return -EFAULT;
+	}
+
+	/*
+	 * Update counters.
+	 */
+	buf->pos += count;
+	*ppos += count;
+
+	/*
+	 * Queue next buffer if required.
+	 */
+	if (buf->pos == buf->size || (!read && fileio->write_immediately)) {
+		struct vb2_buffer *b = fileio->b;
+
+		/*
+		 * Check if this is the last buffer to read.
+		 */
+		if (read && fileio->read_once && fileio->dq_count == 1) {
+			dprintk(3, "read limit reached\n");
+			return __vb2_cleanup_fileio(q);
+		}
+
+		/*
+		 * Call vb2_qbuf and give buffer to the driver.
+		 */
+		memset(b, 0, q->buf_struct_size);
+		b->type = q->type;
+		b->memory = q->memory;
+		b->index = index;
+		b->planes[0].bytesused = buf->pos;
+
+		if (copy_timestamp)
+			b->timestamp = ktime_get_ns();
+		ret = vb2_core_qbuf(q, index, b);
+		dprintk(5, "vb2_dbuf result: %d\n", ret);
+		if (ret)
+			return ret;
+
+		/*
+		 * Buffer has been queued, update the status
+		 */
+		buf->pos = 0;
+		buf->queued = 1;
+		buf->size = vb2_plane_size(q->bufs[index], 0);
+		fileio->q_count += 1;
+		/*
+		 * If we are queuing up buffers for the first time, then
+		 * increase initial_index by one.
+		 */
+		if (fileio->initial_index < q->num_buffers)
+			fileio->initial_index++;
+		/*
+		 * The next buffer to use is either a buffer that's going to be
+		 * queued for the first time (initial_index < q->num_buffers)
+		 * or it is equal to q->num_buffers, meaning that the next
+		 * time we need to dequeue a buffer since we've now queued up
+		 * all the 'first time' buffers.
+		 */
+		fileio->cur_index = fileio->initial_index;
+	}
+
+	/*
+	 * Return proper number of bytes processed.
+	 */
+	if (ret == 0)
+		ret = count;
+	return ret;
+}
+
+size_t vb2_read(struct vb2_queue *q, char __user *data, size_t count,
+		loff_t *ppos, int nonblocking)
+{
+	return __vb2_perform_fileio(q, data, count, ppos, nonblocking, 1);
+}
+EXPORT_SYMBOL_GPL(vb2_read);
+
+size_t vb2_write(struct vb2_queue *q, const char __user *data, size_t count,
+		loff_t *ppos, int nonblocking)
+{
+	return __vb2_perform_fileio(q, (char __user *) data, count,
+							ppos, nonblocking, 0);
+}
+EXPORT_SYMBOL_GPL(vb2_write);
+
+struct vb2_threadio_data {
+	struct task_struct *thread;
+	vb2_thread_fnc fnc;
+	void *priv;
+	bool stop;
+};
+
+static int vb2_thread(void *data)
+{
+	struct vb2_queue *q = data;
+	struct vb2_threadio_data *threadio = q->threadio;
+	struct vb2_fileio_data *fileio = q->fileio;
+	bool copy_timestamp = false;
+	int prequeue = 0;
+	int index = 0;
+	int ret = 0;
+
+	if (q->is_output) {
+		prequeue = q->num_buffers;
+		copy_timestamp = q->copy_timestamp;
+	}
+
+	set_freezable();
+
+	for (;;) {
+		struct vb2_buffer *vb;
+		struct vb2_buffer *b = fileio->b;
+
+		/*
+		 * Call vb2_dqbuf to get buffer back.
+		 */
+		memset(b, 0, q->buf_struct_size);
+		b->type = q->type;
+		b->memory = q->memory;
+		if (prequeue) {
+			b->index = index++;
+			prequeue--;
+		} else {
+			call_void_qop(q, wait_finish, q);
+			if (!threadio->stop)
+				ret = vb2_core_dqbuf(q, b, 0);
+			call_void_qop(q, wait_prepare, q);
+			dprintk(5, "file io: vb2_dqbuf result: %d\n", ret);
+		}
+		if (ret || threadio->stop)
+			break;
+		try_to_freeze();
+
+		vb = q->bufs[b->index];
+		if (b->state == VB2_BUF_STATE_DONE)
+			if (threadio->fnc(vb, threadio->priv))
+				break;
+		call_void_qop(q, wait_finish, q);
+		if (copy_timestamp)
+			b->timestamp = ktime_get_ns();;
+		if (!threadio->stop)
+			ret = vb2_core_qbuf(q, b->index, b);
+		call_void_qop(q, wait_prepare, q);
+		if (ret || threadio->stop)
+			break;
+	}
+
+	/* Hmm, linux becomes *very* unhappy without this ... */
+	while (!kthread_should_stop()) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		schedule();
+	}
+	return 0;
+}
+
+/*
+ * This function should not be used for anything else but the videobuf2-dvb
+ * support. If you think you have another good use-case for this, then please
+ * contact the linux-media mailinglist first.
+ */
+int vb2_thread_start(struct vb2_queue *q, vb2_thread_fnc fnc, void *priv,
+		     const char *thread_name)
+{
+	struct vb2_threadio_data *threadio;
+	int ret = 0;
+
+	if (q->threadio)
+		return -EBUSY;
+	if (vb2_is_busy(q))
+		return -EBUSY;
+	if (WARN_ON(q->fileio))
+		return -EBUSY;
+
+	threadio = kzalloc(sizeof(*threadio), GFP_KERNEL);
+	if (threadio == NULL)
+		return -ENOMEM;
+	threadio->fnc = fnc;
+	threadio->priv = priv;
+
+	ret = __vb2_init_fileio(q, !q->is_output);
+	dprintk(3, "file io: vb2_init_fileio result: %d\n", ret);
+	if (ret)
+		goto nomem;
+	q->threadio = threadio;
+	threadio->thread = kthread_run(vb2_thread, q, "vb2-%s", thread_name);
+	if (IS_ERR(threadio->thread)) {
+		ret = PTR_ERR(threadio->thread);
+		threadio->thread = NULL;
+		goto nothread;
+	}
+	return 0;
+
+nothread:
+	__vb2_cleanup_fileio(q);
+nomem:
+	kfree(threadio);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(vb2_thread_start);
+
+int vb2_thread_stop(struct vb2_queue *q)
+{
+	struct vb2_threadio_data *threadio = q->threadio;
+	int err;
+
+	if (threadio == NULL)
+		return 0;
+	threadio->stop = true;
+	/* Wake up all pending sleeps in the thread */
+	vb2_queue_error(q);
+	err = kthread_stop(threadio->thread);
+	__vb2_cleanup_fileio(q);
+	threadio->thread = NULL;
+	kfree(threadio);
+	q->threadio = NULL;
+	return err;
+}
+EXPORT_SYMBOL_GPL(vb2_thread_stop);
+
+MODULE_DESCRIPTION("Media buffer core framework");
 MODULE_AUTHOR("Pawel Osciak <pawel@osciak.com>, Marek Szyprowski");
 MODULE_LICENSE("GPL");
diff --git a/drivers/media/v4l2-core/videobuf2-internal.h b/drivers/media/v4l2-core/videobuf2-internal.h
deleted file mode 100644
index 79018c7..0000000
--- a/drivers/media/v4l2-core/videobuf2-internal.h
+++ /dev/null
@@ -1,161 +0,0 @@
-#ifndef _MEDIA_VIDEOBUF2_INTERNAL_H
-#define _MEDIA_VIDEOBUF2_INTERNAL_H
-
-#include <linux/err.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <media/videobuf2-core.h>
-
-extern int vb2_debug;
-
-#define dprintk(level, fmt, arg...)					      \
-	do {								      \
-		if (vb2_debug >= level)					      \
-			pr_info("vb2: %s: " fmt, __func__, ## arg); \
-	} while (0)
-
-#ifdef CONFIG_VIDEO_ADV_DEBUG
-
-/*
- * If advanced debugging is on, then count how often each op is called
- * successfully, which can either be per-buffer or per-queue.
- *
- * This makes it easy to check that the 'init' and 'cleanup'
- * (and variations thereof) stay balanced.
- */
-
-#define log_memop(vb, op)						\
-	dprintk(2, "call_memop(%p, %d, %s)%s\n",			\
-		(vb)->vb2_queue, (vb)->index, #op,			\
-		(vb)->vb2_queue->mem_ops->op ? "" : " (nop)")
-
-#define call_memop(vb, op, args...)					\
-({									\
-	struct vb2_queue *_q = (vb)->vb2_queue;				\
-	int err;							\
-									\
-	log_memop(vb, op);						\
-	err = _q->mem_ops->op ? _q->mem_ops->op(args) : 0;		\
-	if (!err)							\
-		(vb)->cnt_mem_ ## op++;					\
-	err;								\
-})
-
-#define call_ptr_memop(vb, op, args...)					\
-({									\
-	struct vb2_queue *_q = (vb)->vb2_queue;				\
-	void *ptr;							\
-									\
-	log_memop(vb, op);						\
-	ptr = _q->mem_ops->op ? _q->mem_ops->op(args) : NULL;		\
-	if (!IS_ERR_OR_NULL(ptr))					\
-		(vb)->cnt_mem_ ## op++;					\
-	ptr;								\
-})
-
-#define call_void_memop(vb, op, args...)				\
-({									\
-	struct vb2_queue *_q = (vb)->vb2_queue;				\
-									\
-	log_memop(vb, op);						\
-	if (_q->mem_ops->op)						\
-		_q->mem_ops->op(args);					\
-	(vb)->cnt_mem_ ## op++;						\
-})
-
-#define log_qop(q, op)							\
-	dprintk(2, "call_qop(%p, %s)%s\n", q, #op,			\
-		(q)->ops->op ? "" : " (nop)")
-
-#define call_qop(q, op, args...)					\
-({									\
-	int err;							\
-									\
-	log_qop(q, op);							\
-	err = (q)->ops->op ? (q)->ops->op(args) : 0;			\
-	if (!err)							\
-		(q)->cnt_ ## op++;					\
-	err;								\
-})
-
-#define call_void_qop(q, op, args...)					\
-({									\
-	log_qop(q, op);							\
-	if ((q)->ops->op)						\
-		(q)->ops->op(args);					\
-	(q)->cnt_ ## op++;						\
-})
-
-#define log_vb_qop(vb, op, args...)					\
-	dprintk(2, "call_vb_qop(%p, %d, %s)%s\n",			\
-		(vb)->vb2_queue, (vb)->index, #op,			\
-		(vb)->vb2_queue->ops->op ? "" : " (nop)")
-
-#define call_vb_qop(vb, op, args...)					\
-({									\
-	int err;							\
-									\
-	log_vb_qop(vb, op);						\
-	err = (vb)->vb2_queue->ops->op ?				\
-		(vb)->vb2_queue->ops->op(args) : 0;			\
-	if (!err)							\
-		(vb)->cnt_ ## op++;					\
-	err;								\
-})
-
-#define call_void_vb_qop(vb, op, args...)				\
-({									\
-	log_vb_qop(vb, op);						\
-	if ((vb)->vb2_queue->ops->op)					\
-		(vb)->vb2_queue->ops->op(args);				\
-	(vb)->cnt_ ## op++;						\
-})
-
-#else
-
-#define call_memop(vb, op, args...)					\
-	((vb)->vb2_queue->mem_ops->op ?					\
-		(vb)->vb2_queue->mem_ops->op(args) : 0)
-
-#define call_ptr_memop(vb, op, args...)					\
-	((vb)->vb2_queue->mem_ops->op ?					\
-		(vb)->vb2_queue->mem_ops->op(args) : NULL)
-
-#define call_void_memop(vb, op, args...)				\
-	do {								\
-		if ((vb)->vb2_queue->mem_ops->op)			\
-			(vb)->vb2_queue->mem_ops->op(args);		\
-	} while (0)
-
-#define call_qop(q, op, args...)					\
-	((q)->ops->op ? (q)->ops->op(args) : 0)
-
-#define call_void_qop(q, op, args...)					\
-	do {								\
-		if ((q)->ops->op)					\
-			(q)->ops->op(args);				\
-	} while (0)
-
-#define call_vb_qop(vb, op, args...)					\
-	((vb)->vb2_queue->ops->op ? (vb)->vb2_queue->ops->op(args) : 0)
-
-#define call_void_vb_qop(vb, op, args...)				\
-	do {								\
-		if ((vb)->vb2_queue->ops->op)				\
-			(vb)->vb2_queue->ops->op(args);			\
-	} while (0)
-
-#endif
-
-#define call_bufop(q, op, args...)					\
-({									\
-	int ret = 0;							\
-	if (q && q->buf_ops && q->buf_ops->op)				\
-		ret = q->buf_ops->op(args);				\
-	ret;								\
-})
-
-bool vb2_buffer_in_use(struct vb2_queue *q, struct vb2_buffer *vb);
-int vb2_verify_memory_type(struct vb2_queue *q,
-		enum vb2_memory memory, unsigned int type);
-#endif /* _MEDIA_VIDEOBUF2_INTERNAL_H */
diff --git a/drivers/media/v4l2-core/videobuf2-v4l2.c b/drivers/media/v4l2-core/videobuf2-v4l2.c
index 27b4b9e..c9a2860 100644
--- a/drivers/media/v4l2-core/videobuf2-v4l2.c
+++ b/drivers/media/v4l2-core/videobuf2-v4l2.c
@@ -31,7 +31,14 @@
 
 #include <media/videobuf2-v4l2.h>
 
-#include "videobuf2-internal.h"
+static int debug;
+module_param(debug, int, 0644);
+
+#define dprintk(level, fmt, arg...)					      \
+	do {								      \
+		if (debug >= level)					      \
+			pr_info("vb2-v4l2: %s: " fmt, __func__, ## arg); \
+	} while (0)
 
 /* Flags that are set by the vb2 core */
 #define V4L2_BUFFER_MASK_FLAGS	(V4L2_BUF_FLAG_MAPPED | V4L2_BUF_FLAG_QUEUED | \
@@ -52,7 +59,7 @@
 		return 0;
 
 	/* Is memory for copying plane information present? */
-	if (NULL == b->m.planes) {
+	if (b->m.planes == NULL) {
 		dprintk(1, "multi-planar buffer passed but "
 			   "planes array not provided\n");
 		return -EINVAL;
@@ -107,7 +114,7 @@
 	return 0;
 }
 
-static int __set_timestamp(struct vb2_buffer *vb, const void *pb)
+static void __copy_timestamp(struct vb2_buffer *vb, const void *pb)
 {
 	const struct v4l2_buffer *b = pb;
 	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
@@ -118,14 +125,12 @@
 		 * For output buffers copy the timestamp if needed,
 		 * and the timecode field and flag if needed.
 		 */
-		if ((q->timestamp_flags & V4L2_BUF_FLAG_TIMESTAMP_MASK) ==
-				V4L2_BUF_FLAG_TIMESTAMP_COPY)
-			vbuf->timestamp = b->timestamp;
+		if (q->copy_timestamp)
+			vb->timestamp = timeval_to_ns(&b->timestamp);
 		vbuf->flags |= b->flags & V4L2_BUF_FLAG_TIMECODE;
 		if (b->flags & V4L2_BUF_FLAG_TIMECODE)
 			vbuf->timecode = b->timecode;
 	}
-	return 0;
 };
 
 static void vb2_warn_zero_bytesused(struct vb2_buffer *vb)
@@ -176,7 +181,7 @@
  * __fill_v4l2_buffer() - fill in a struct v4l2_buffer with information to be
  * returned to userspace
  */
-static int __fill_v4l2_buffer(struct vb2_buffer *vb, void *pb)
+static void __fill_v4l2_buffer(struct vb2_buffer *vb, void *pb)
 {
 	struct v4l2_buffer *b = pb;
 	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
@@ -191,7 +196,7 @@
 
 	b->flags = vbuf->flags;
 	b->field = vbuf->field;
-	b->timestamp = vbuf->timestamp;
+	b->timestamp = ns_to_timeval(vb->timestamp);
 	b->timecode = vbuf->timecode;
 	b->sequence = vbuf->sequence;
 	b->reserved2 = 0;
@@ -238,8 +243,7 @@
 	 */
 	b->flags &= ~V4L2_BUFFER_MASK_FLAGS;
 	b->flags |= q->timestamp_flags & V4L2_BUF_FLAG_TIMESTAMP_MASK;
-	if ((q->timestamp_flags & V4L2_BUF_FLAG_TIMESTAMP_MASK) !=
-	    V4L2_BUF_FLAG_TIMESTAMP_COPY) {
+	if (!q->copy_timestamp) {
 		/*
 		 * For non-COPY timestamps, drop timestamp source bits
 		 * and obtain the timestamp source from the queue.
@@ -272,7 +276,10 @@
 	if (vb2_buffer_in_use(q, vb))
 		b->flags |= V4L2_BUF_FLAG_MAPPED;
 
-	return 0;
+	if (!q->is_output &&
+		b->flags & V4L2_BUF_FLAG_DONE &&
+		b->flags & V4L2_BUF_FLAG_LAST)
+		q->last_buffer_dequeued = true;
 }
 
 /**
@@ -308,8 +315,7 @@
 					"for an output buffer\n");
 		return -EINVAL;
 	}
-	vbuf->timestamp.tv_sec = 0;
-	vbuf->timestamp.tv_usec = 0;
+	vb->timestamp = 0;
 	vbuf->sequence = 0;
 
 	if (V4L2_TYPE_IS_MULTIPLANAR(b->type)) {
@@ -404,8 +410,7 @@
 
 	/* Zero flags that the vb2 core handles */
 	vbuf->flags = b->flags & ~V4L2_BUFFER_MASK_FLAGS;
-	if ((vb->vb2_queue->timestamp_flags & V4L2_BUF_FLAG_TIMESTAMP_MASK) !=
-	    V4L2_BUF_FLAG_TIMESTAMP_COPY || !V4L2_TYPE_IS_OUTPUT(b->type)) {
+	if (!vb->vb2_queue->copy_timestamp || !V4L2_TYPE_IS_OUTPUT(b->type)) {
 		/*
 		 * Non-COPY timestamps and non-OUTPUT queues will get
 		 * their timestamp and timestamp source flags from the
@@ -434,7 +439,7 @@
 static const struct vb2_buf_ops v4l2_buf_ops = {
 	.fill_user_buffer	= __fill_v4l2_buffer,
 	.fill_vb2_buffer	= __fill_vb2_buffer,
-	.set_timestamp		= __set_timestamp,
+	.copy_timestamp		= __copy_timestamp,
 };
 
 /**
@@ -466,8 +471,9 @@
 	}
 	vb = q->bufs[b->index];
 	ret = __verify_planes_array(vb, b);
-
-	return ret ? ret : vb2_core_querybuf(q, b->index, b);
+	if (!ret)
+		vb2_core_querybuf(q, b->index, b);
+	return ret;
 }
 EXPORT_SYMBOL(vb2_querybuf);
 
@@ -525,14 +531,52 @@
  */
 int vb2_create_bufs(struct vb2_queue *q, struct v4l2_create_buffers *create)
 {
-	int ret = vb2_verify_memory_type(q, create->memory,
-			create->format.type);
+	unsigned requested_planes = 1;
+	unsigned requested_sizes[VIDEO_MAX_PLANES];
+	struct v4l2_format *f = &create->format;
+	int ret = vb2_verify_memory_type(q, create->memory, f->type);
+	unsigned i;
 
 	create->index = q->num_buffers;
 	if (create->count == 0)
 		return ret != -EBUSY ? ret : 0;
+
+	switch (f->type) {
+	case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE:
+	case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE:
+		requested_planes = f->fmt.pix_mp.num_planes;
+		if (requested_planes == 0 ||
+		    requested_planes > VIDEO_MAX_PLANES)
+			return -EINVAL;
+		for (i = 0; i < requested_planes; i++)
+			requested_sizes[i] =
+				f->fmt.pix_mp.plane_fmt[i].sizeimage;
+		break;
+	case V4L2_BUF_TYPE_VIDEO_CAPTURE:
+	case V4L2_BUF_TYPE_VIDEO_OUTPUT:
+		requested_sizes[0] = f->fmt.pix.sizeimage;
+		break;
+	case V4L2_BUF_TYPE_VBI_CAPTURE:
+	case V4L2_BUF_TYPE_VBI_OUTPUT:
+		requested_sizes[0] = f->fmt.vbi.samples_per_line *
+			(f->fmt.vbi.count[0] + f->fmt.vbi.count[1]);
+		break;
+	case V4L2_BUF_TYPE_SLICED_VBI_CAPTURE:
+	case V4L2_BUF_TYPE_SLICED_VBI_OUTPUT:
+		requested_sizes[0] = f->fmt.sliced.io_size;
+		break;
+	case V4L2_BUF_TYPE_SDR_CAPTURE:
+	case V4L2_BUF_TYPE_SDR_OUTPUT:
+		requested_sizes[0] = f->fmt.sdr.buffersize;
+		break;
+	default:
+		return -EINVAL;
+	}
+	for (i = 0; i < requested_planes; i++)
+		if (requested_sizes[i] == 0)
+			return -EINVAL;
 	return ret ? ret : vb2_core_create_bufs(q, create->memory,
-		&create->count, &create->format);
+		&create->count, requested_planes, requested_sizes);
 }
 EXPORT_SYMBOL_GPL(vb2_create_bufs);
 
@@ -583,10 +627,6 @@
 
 	ret = vb2_core_dqbuf(q, b, nonblocking);
 
-	if (!ret && !q->is_output &&
-			b->flags & V4L2_BUF_FLAG_LAST)
-		q->last_buffer_dequeued = true;
-
 	return ret;
 }
 
@@ -723,14 +763,13 @@
 	q->buf_ops = &v4l2_buf_ops;
 	q->is_multiplanar = V4L2_TYPE_IS_MULTIPLANAR(q->type);
 	q->is_output = V4L2_TYPE_IS_OUTPUT(q->type);
+	q->copy_timestamp = (q->timestamp_flags & V4L2_BUF_FLAG_TIMESTAMP_MASK)
+			== V4L2_BUF_FLAG_TIMESTAMP_COPY;
 
 	return vb2_core_queue_init(q);
 }
 EXPORT_SYMBOL_GPL(vb2_queue_init);
 
-static int __vb2_init_fileio(struct vb2_queue *q, int read);
-static int __vb2_cleanup_fileio(struct vb2_queue *q);
-
 /**
  * vb2_queue_release() - stop streaming, release the queue and free memory
  * @q:		videobuf2 queue
@@ -741,7 +780,6 @@
  */
 void vb2_queue_release(struct vb2_queue *q)
 {
-	__vb2_cleanup_fileio(q);
 	vb2_core_queue_release(q);
 }
 EXPORT_SYMBOL_GPL(vb2_queue_release);
@@ -769,9 +807,7 @@
 {
 	struct video_device *vfd = video_devdata(file);
 	unsigned long req_events = poll_requested_events(wait);
-	struct vb2_buffer *vb = NULL;
 	unsigned int res = 0;
-	unsigned long flags;
 
 	if (test_bit(V4L2_FL_USES_V4L2_FH, &vfd->flags)) {
 		struct v4l2_fh *fh = file->private_data;
@@ -782,611 +818,18 @@
 			poll_wait(file, &fh->wait, wait);
 	}
 
-	if (!q->is_output && !(req_events & (POLLIN | POLLRDNORM)))
-		return res;
-	if (q->is_output && !(req_events & (POLLOUT | POLLWRNORM)))
-		return res;
-
-	/*
-	 * Start file I/O emulator only if streaming API has not been used yet.
-	 */
-	if (q->num_buffers == 0 && !vb2_fileio_is_active(q)) {
-		if (!q->is_output && (q->io_modes & VB2_READ) &&
-				(req_events & (POLLIN | POLLRDNORM))) {
-			if (__vb2_init_fileio(q, 1))
-				return res | POLLERR;
-		}
-		if (q->is_output && (q->io_modes & VB2_WRITE) &&
-				(req_events & (POLLOUT | POLLWRNORM))) {
-			if (__vb2_init_fileio(q, 0))
-				return res | POLLERR;
-			/*
-			 * Write to OUTPUT queue can be done immediately.
-			 */
-			return res | POLLOUT | POLLWRNORM;
-		}
-	}
-
-	/*
-	 * There is nothing to wait for if the queue isn't streaming, or if the
-	 * error flag is set.
-	 */
-	if (!vb2_is_streaming(q) || q->error)
-		return res | POLLERR;
 	/*
 	 * For compatibility with vb1: if QBUF hasn't been called yet, then
 	 * return POLLERR as well. This only affects capture queues, output
 	 * queues will always initialize waiting_for_buffers to false.
 	 */
-	if (q->waiting_for_buffers)
-		return res | POLLERR;
+	if (q->waiting_for_buffers && (req_events & (POLLIN | POLLRDNORM)))
+		return POLLERR;
 
-	/*
-	 * For output streams you can write as long as there are fewer buffers
-	 * queued than there are buffers available.
-	 */
-	if (q->is_output && q->queued_count < q->num_buffers)
-		return res | POLLOUT | POLLWRNORM;
-
-	if (list_empty(&q->done_list)) {
-		/*
-		 * If the last buffer was dequeued from a capture queue,
-		 * return immediately. DQBUF will return -EPIPE.
-		 */
-		if (q->last_buffer_dequeued)
-			return res | POLLIN | POLLRDNORM;
-
-		poll_wait(file, &q->done_wq, wait);
-	}
-
-	/*
-	 * Take first buffer available for dequeuing.
-	 */
-	spin_lock_irqsave(&q->done_lock, flags);
-	if (!list_empty(&q->done_list))
-		vb = list_first_entry(&q->done_list, struct vb2_buffer,
-					done_entry);
-	spin_unlock_irqrestore(&q->done_lock, flags);
-
-	if (vb && (vb->state == VB2_BUF_STATE_DONE
-			|| vb->state == VB2_BUF_STATE_ERROR)) {
-		return (q->is_output) ?
-				res | POLLOUT | POLLWRNORM :
-				res | POLLIN | POLLRDNORM;
-	}
-	return res;
+	return res | vb2_core_poll(q, file, wait);
 }
 EXPORT_SYMBOL_GPL(vb2_poll);
 
-/**
- * struct vb2_fileio_buf - buffer context used by file io emulator
- *
- * vb2 provides a compatibility layer and emulator of file io (read and
- * write) calls on top of streaming API. This structure is used for
- * tracking context related to the buffers.
- */
-struct vb2_fileio_buf {
-	void *vaddr;
-	unsigned int size;
-	unsigned int pos;
-	unsigned int queued:1;
-};
-
-/**
- * struct vb2_fileio_data - queue context used by file io emulator
- *
- * @cur_index:	the index of the buffer currently being read from or
- *		written to. If equal to q->num_buffers then a new buffer
- *		must be dequeued.
- * @initial_index: in the read() case all buffers are queued up immediately
- *		in __vb2_init_fileio() and __vb2_perform_fileio() just cycles
- *		buffers. However, in the write() case no buffers are initially
- *		queued, instead whenever a buffer is full it is queued up by
- *		__vb2_perform_fileio(). Only once all available buffers have
- *		been queued up will __vb2_perform_fileio() start to dequeue
- *		buffers. This means that initially __vb2_perform_fileio()
- *		needs to know what buffer index to use when it is queuing up
- *		the buffers for the first time. That initial index is stored
- *		in this field. Once it is equal to q->num_buffers all
- *		available buffers have been queued and __vb2_perform_fileio()
- *		should start the normal dequeue/queue cycle.
- *
- * vb2 provides a compatibility layer and emulator of file io (read and
- * write) calls on top of streaming API. For proper operation it required
- * this structure to save the driver state between each call of the read
- * or write function.
- */
-struct vb2_fileio_data {
-	struct v4l2_requestbuffers req;
-	struct v4l2_plane p;
-	struct v4l2_buffer b;
-	struct vb2_fileio_buf bufs[VB2_MAX_FRAME];
-	unsigned int cur_index;
-	unsigned int initial_index;
-	unsigned int q_count;
-	unsigned int dq_count;
-	unsigned read_once:1;
-	unsigned write_immediately:1;
-};
-
-/**
- * __vb2_init_fileio() - initialize file io emulator
- * @q:		videobuf2 queue
- * @read:	mode selector (1 means read, 0 means write)
- */
-static int __vb2_init_fileio(struct vb2_queue *q, int read)
-{
-	struct vb2_fileio_data *fileio;
-	int i, ret;
-	unsigned int count = 0;
-
-	/*
-	 * Sanity check
-	 */
-	if (WARN_ON((read && !(q->io_modes & VB2_READ)) ||
-		    (!read && !(q->io_modes & VB2_WRITE))))
-		return -EINVAL;
-
-	/*
-	 * Check if device supports mapping buffers to kernel virtual space.
-	 */
-	if (!q->mem_ops->vaddr)
-		return -EBUSY;
-
-	/*
-	 * Check if streaming api has not been already activated.
-	 */
-	if (q->streaming || q->num_buffers > 0)
-		return -EBUSY;
-
-	/*
-	 * Start with count 1, driver can increase it in queue_setup()
-	 */
-	count = 1;
-
-	dprintk(3, "setting up file io: mode %s, count %d, read_once %d, write_immediately %d\n",
-		(read) ? "read" : "write", count, q->fileio_read_once,
-		q->fileio_write_immediately);
-
-	fileio = kzalloc(sizeof(struct vb2_fileio_data), GFP_KERNEL);
-	if (fileio == NULL)
-		return -ENOMEM;
-
-	fileio->read_once = q->fileio_read_once;
-	fileio->write_immediately = q->fileio_write_immediately;
-
-	/*
-	 * Request buffers and use MMAP type to force driver
-	 * to allocate buffers by itself.
-	 */
-	fileio->req.count = count;
-	fileio->req.memory = VB2_MEMORY_MMAP;
-	fileio->req.type = q->type;
-	q->fileio = fileio;
-	ret = vb2_core_reqbufs(q, fileio->req.memory, &fileio->req.count);
-	if (ret)
-		goto err_kfree;
-
-	/*
-	 * Check if plane_count is correct
-	 * (multiplane buffers are not supported).
-	 */
-	if (q->bufs[0]->num_planes != 1) {
-		ret = -EBUSY;
-		goto err_reqbufs;
-	}
-
-	/*
-	 * Get kernel address of each buffer.
-	 */
-	for (i = 0; i < q->num_buffers; i++) {
-		fileio->bufs[i].vaddr = vb2_plane_vaddr(q->bufs[i], 0);
-		if (fileio->bufs[i].vaddr == NULL) {
-			ret = -EINVAL;
-			goto err_reqbufs;
-		}
-		fileio->bufs[i].size = vb2_plane_size(q->bufs[i], 0);
-	}
-
-	/*
-	 * Read mode requires pre queuing of all buffers.
-	 */
-	if (read) {
-		bool is_multiplanar = q->is_multiplanar;
-
-		/*
-		 * Queue all buffers.
-		 */
-		for (i = 0; i < q->num_buffers; i++) {
-			struct v4l2_buffer *b = &fileio->b;
-
-			memset(b, 0, sizeof(*b));
-			b->type = q->type;
-			if (is_multiplanar) {
-				memset(&fileio->p, 0, sizeof(fileio->p));
-				b->m.planes = &fileio->p;
-				b->length = 1;
-			}
-			b->memory = q->memory;
-			b->index = i;
-			ret = vb2_internal_qbuf(q, b);
-			if (ret)
-				goto err_reqbufs;
-			fileio->bufs[i].queued = 1;
-		}
-		/*
-		 * All buffers have been queued, so mark that by setting
-		 * initial_index to q->num_buffers
-		 */
-		fileio->initial_index = q->num_buffers;
-		fileio->cur_index = q->num_buffers;
-	}
-
-	/*
-	 * Start streaming.
-	 */
-	ret = vb2_core_streamon(q, q->type);
-	if (ret)
-		goto err_reqbufs;
-
-	return ret;
-
-err_reqbufs:
-	fileio->req.count = 0;
-	vb2_core_reqbufs(q, fileio->req.memory, &fileio->req.count);
-
-err_kfree:
-	q->fileio = NULL;
-	kfree(fileio);
-	return ret;
-}
-
-/**
- * __vb2_cleanup_fileio() - free resourced used by file io emulator
- * @q:		videobuf2 queue
- */
-static int __vb2_cleanup_fileio(struct vb2_queue *q)
-{
-	struct vb2_fileio_data *fileio = q->fileio;
-
-	if (fileio) {
-		vb2_core_streamoff(q, q->type);
-		q->fileio = NULL;
-		fileio->req.count = 0;
-		vb2_reqbufs(q, &fileio->req);
-		kfree(fileio);
-		dprintk(3, "file io emulator closed\n");
-	}
-	return 0;
-}
-
-/**
- * __vb2_perform_fileio() - perform a single file io (read or write) operation
- * @q:		videobuf2 queue
- * @data:	pointed to target userspace buffer
- * @count:	number of bytes to read or write
- * @ppos:	file handle position tracking pointer
- * @nonblock:	mode selector (1 means blocking calls, 0 means nonblocking)
- * @read:	access mode selector (1 means read, 0 means write)
- */
-static size_t __vb2_perform_fileio(struct vb2_queue *q, char __user *data, size_t count,
-		loff_t *ppos, int nonblock, int read)
-{
-	struct vb2_fileio_data *fileio;
-	struct vb2_fileio_buf *buf;
-	bool is_multiplanar = q->is_multiplanar;
-	/*
-	 * When using write() to write data to an output video node the vb2 core
-	 * should set timestamps if V4L2_BUF_FLAG_TIMESTAMP_COPY is set. Nobody
-	 * else is able to provide this information with the write() operation.
-	 */
-	bool set_timestamp = !read &&
-		(q->timestamp_flags & V4L2_BUF_FLAG_TIMESTAMP_MASK) ==
-		V4L2_BUF_FLAG_TIMESTAMP_COPY;
-	int ret, index;
-
-	dprintk(3, "mode %s, offset %ld, count %zd, %sblocking\n",
-		read ? "read" : "write", (long)*ppos, count,
-		nonblock ? "non" : "");
-
-	if (!data)
-		return -EINVAL;
-
-	/*
-	 * Initialize emulator on first call.
-	 */
-	if (!vb2_fileio_is_active(q)) {
-		ret = __vb2_init_fileio(q, read);
-		dprintk(3, "vb2_init_fileio result: %d\n", ret);
-		if (ret)
-			return ret;
-	}
-	fileio = q->fileio;
-
-	/*
-	 * Check if we need to dequeue the buffer.
-	 */
-	index = fileio->cur_index;
-	if (index >= q->num_buffers) {
-		/*
-		 * Call vb2_dqbuf to get buffer back.
-		 */
-		memset(&fileio->b, 0, sizeof(fileio->b));
-		fileio->b.type = q->type;
-		fileio->b.memory = q->memory;
-		if (is_multiplanar) {
-			memset(&fileio->p, 0, sizeof(fileio->p));
-			fileio->b.m.planes = &fileio->p;
-			fileio->b.length = 1;
-		}
-		ret = vb2_internal_dqbuf(q, &fileio->b, nonblock);
-		dprintk(5, "vb2_dqbuf result: %d\n", ret);
-		if (ret)
-			return ret;
-		fileio->dq_count += 1;
-
-		fileio->cur_index = index = fileio->b.index;
-		buf = &fileio->bufs[index];
-
-		/*
-		 * Get number of bytes filled by the driver
-		 */
-		buf->pos = 0;
-		buf->queued = 0;
-		buf->size = read ? vb2_get_plane_payload(q->bufs[index], 0)
-				 : vb2_plane_size(q->bufs[index], 0);
-		/* Compensate for data_offset on read in the multiplanar case. */
-		if (is_multiplanar && read &&
-		    fileio->b.m.planes[0].data_offset < buf->size) {
-			buf->pos = fileio->b.m.planes[0].data_offset;
-			buf->size -= buf->pos;
-		}
-	} else {
-		buf = &fileio->bufs[index];
-	}
-
-	/*
-	 * Limit count on last few bytes of the buffer.
-	 */
-	if (buf->pos + count > buf->size) {
-		count = buf->size - buf->pos;
-		dprintk(5, "reducing read count: %zd\n", count);
-	}
-
-	/*
-	 * Transfer data to userspace.
-	 */
-	dprintk(3, "copying %zd bytes - buffer %d, offset %u\n",
-		count, index, buf->pos);
-	if (read)
-		ret = copy_to_user(data, buf->vaddr + buf->pos, count);
-	else
-		ret = copy_from_user(buf->vaddr + buf->pos, data, count);
-	if (ret) {
-		dprintk(3, "error copying data\n");
-		return -EFAULT;
-	}
-
-	/*
-	 * Update counters.
-	 */
-	buf->pos += count;
-	*ppos += count;
-
-	/*
-	 * Queue next buffer if required.
-	 */
-	if (buf->pos == buf->size || (!read && fileio->write_immediately)) {
-		/*
-		 * Check if this is the last buffer to read.
-		 */
-		if (read && fileio->read_once && fileio->dq_count == 1) {
-			dprintk(3, "read limit reached\n");
-			return __vb2_cleanup_fileio(q);
-		}
-
-		/*
-		 * Call vb2_qbuf and give buffer to the driver.
-		 */
-		memset(&fileio->b, 0, sizeof(fileio->b));
-		fileio->b.type = q->type;
-		fileio->b.memory = q->memory;
-		fileio->b.index = index;
-		fileio->b.bytesused = buf->pos;
-		if (is_multiplanar) {
-			memset(&fileio->p, 0, sizeof(fileio->p));
-			fileio->p.bytesused = buf->pos;
-			fileio->b.m.planes = &fileio->p;
-			fileio->b.length = 1;
-		}
-		if (set_timestamp)
-			v4l2_get_timestamp(&fileio->b.timestamp);
-		ret = vb2_internal_qbuf(q, &fileio->b);
-		dprintk(5, "vb2_dbuf result: %d\n", ret);
-		if (ret)
-			return ret;
-
-		/*
-		 * Buffer has been queued, update the status
-		 */
-		buf->pos = 0;
-		buf->queued = 1;
-		buf->size = vb2_plane_size(q->bufs[index], 0);
-		fileio->q_count += 1;
-		/*
-		 * If we are queuing up buffers for the first time, then
-		 * increase initial_index by one.
-		 */
-		if (fileio->initial_index < q->num_buffers)
-			fileio->initial_index++;
-		/*
-		 * The next buffer to use is either a buffer that's going to be
-		 * queued for the first time (initial_index < q->num_buffers)
-		 * or it is equal to q->num_buffers, meaning that the next
-		 * time we need to dequeue a buffer since we've now queued up
-		 * all the 'first time' buffers.
-		 */
-		fileio->cur_index = fileio->initial_index;
-	}
-
-	/*
-	 * Return proper number of bytes processed.
-	 */
-	if (ret == 0)
-		ret = count;
-	return ret;
-}
-
-size_t vb2_read(struct vb2_queue *q, char __user *data, size_t count,
-		loff_t *ppos, int nonblocking)
-{
-	return __vb2_perform_fileio(q, data, count, ppos, nonblocking, 1);
-}
-EXPORT_SYMBOL_GPL(vb2_read);
-
-size_t vb2_write(struct vb2_queue *q, const char __user *data, size_t count,
-		loff_t *ppos, int nonblocking)
-{
-	return __vb2_perform_fileio(q, (char __user *) data, count,
-							ppos, nonblocking, 0);
-}
-EXPORT_SYMBOL_GPL(vb2_write);
-
-struct vb2_threadio_data {
-	struct task_struct *thread;
-	vb2_thread_fnc fnc;
-	void *priv;
-	bool stop;
-};
-
-static int vb2_thread(void *data)
-{
-	struct vb2_queue *q = data;
-	struct vb2_threadio_data *threadio = q->threadio;
-	struct vb2_fileio_data *fileio = q->fileio;
-	bool set_timestamp = false;
-	int prequeue = 0;
-	int index = 0;
-	int ret = 0;
-
-	if (q->is_output) {
-		prequeue = q->num_buffers;
-		set_timestamp =
-			(q->timestamp_flags & V4L2_BUF_FLAG_TIMESTAMP_MASK) ==
-			V4L2_BUF_FLAG_TIMESTAMP_COPY;
-	}
-
-	set_freezable();
-
-	for (;;) {
-		struct vb2_buffer *vb;
-
-		/*
-		 * Call vb2_dqbuf to get buffer back.
-		 */
-		memset(&fileio->b, 0, sizeof(fileio->b));
-		fileio->b.type = q->type;
-		fileio->b.memory = q->memory;
-		if (prequeue) {
-			fileio->b.index = index++;
-			prequeue--;
-		} else {
-			call_void_qop(q, wait_finish, q);
-			if (!threadio->stop)
-				ret = vb2_internal_dqbuf(q, &fileio->b, 0);
-			call_void_qop(q, wait_prepare, q);
-			dprintk(5, "file io: vb2_dqbuf result: %d\n", ret);
-		}
-		if (ret || threadio->stop)
-			break;
-		try_to_freeze();
-
-		vb = q->bufs[fileio->b.index];
-		if (!(fileio->b.flags & V4L2_BUF_FLAG_ERROR))
-			if (threadio->fnc(vb, threadio->priv))
-				break;
-		call_void_qop(q, wait_finish, q);
-		if (set_timestamp)
-			v4l2_get_timestamp(&fileio->b.timestamp);
-		if (!threadio->stop)
-			ret = vb2_internal_qbuf(q, &fileio->b);
-		call_void_qop(q, wait_prepare, q);
-		if (ret || threadio->stop)
-			break;
-	}
-
-	/* Hmm, linux becomes *very* unhappy without this ... */
-	while (!kthread_should_stop()) {
-		set_current_state(TASK_INTERRUPTIBLE);
-		schedule();
-	}
-	return 0;
-}
-
-/*
- * This function should not be used for anything else but the videobuf2-dvb
- * support. If you think you have another good use-case for this, then please
- * contact the linux-media mailinglist first.
- */
-int vb2_thread_start(struct vb2_queue *q, vb2_thread_fnc fnc, void *priv,
-		     const char *thread_name)
-{
-	struct vb2_threadio_data *threadio;
-	int ret = 0;
-
-	if (q->threadio)
-		return -EBUSY;
-	if (vb2_is_busy(q))
-		return -EBUSY;
-	if (WARN_ON(q->fileio))
-		return -EBUSY;
-
-	threadio = kzalloc(sizeof(*threadio), GFP_KERNEL);
-	if (threadio == NULL)
-		return -ENOMEM;
-	threadio->fnc = fnc;
-	threadio->priv = priv;
-
-	ret = __vb2_init_fileio(q, !q->is_output);
-	dprintk(3, "file io: vb2_init_fileio result: %d\n", ret);
-	if (ret)
-		goto nomem;
-	q->threadio = threadio;
-	threadio->thread = kthread_run(vb2_thread, q, "vb2-%s", thread_name);
-	if (IS_ERR(threadio->thread)) {
-		ret = PTR_ERR(threadio->thread);
-		threadio->thread = NULL;
-		goto nothread;
-	}
-	return 0;
-
-nothread:
-	__vb2_cleanup_fileio(q);
-nomem:
-	kfree(threadio);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(vb2_thread_start);
-
-int vb2_thread_stop(struct vb2_queue *q)
-{
-	struct vb2_threadio_data *threadio = q->threadio;
-	int err;
-
-	if (threadio == NULL)
-		return 0;
-	threadio->stop = true;
-	/* Wake up all pending sleeps in the thread */
-	vb2_queue_error(q);
-	err = kthread_stop(threadio->thread);
-	__vb2_cleanup_fileio(q);
-	threadio->thread = NULL;
-	kfree(threadio);
-	q->threadio = NULL;
-	return err;
-}
-EXPORT_SYMBOL_GPL(vb2_thread_stop);
-
 /*
  * The following functions are not part of the vb2 core API, but are helper
  * functions that plug into struct v4l2_ioctl_ops, struct v4l2_file_operations
@@ -1440,8 +883,8 @@
 		return res;
 	if (vb2_queue_is_busy(vdev, file))
 		return -EBUSY;
-	res = vb2_core_create_bufs(vdev->queue, p->memory, &p->count,
-			&p->format);
+
+	res = vb2_create_bufs(vdev->queue, p);
 	if (res == 0)
 		vdev->queue->owner = file->private_data;
 	return res;
diff --git a/drivers/mfd/timberdale.c b/drivers/mfd/timberdale.c
index 6ce36d6..c9339f8 100644
--- a/drivers/mfd/timberdale.c
+++ b/drivers/mfd/timberdale.c
@@ -39,8 +39,8 @@
 #include <linux/spi/max7301.h>
 #include <linux/spi/mc33880.h>
 
-#include <media/timb_radio.h>
-#include <media/timb_video.h>
+#include <linux/platform_data/media/timb_radio.h>
+#include <linux/platform_data/media/timb_video.h>
 
 #include <linux/timb_dma.h>
 
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index d848616..5914263 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -171,11 +171,7 @@
 
 static inline int mmc_get_devidx(struct gendisk *disk)
 {
-	int devmaj = MAJOR(disk_devt(disk));
-	int devidx = MINOR(disk_devt(disk)) / perdev_minors;
-
-	if (!devmaj)
-		devidx = disk->first_minor / perdev_minors;
+	int devidx = disk->first_minor / perdev_minors;
 	return devidx;
 }
 
@@ -344,7 +340,7 @@
 	struct mmc_blk_ioc_data *idata;
 	int err;
 
-	idata = kzalloc(sizeof(*idata), GFP_KERNEL);
+	idata = kmalloc(sizeof(*idata), GFP_KERNEL);
 	if (!idata) {
 		err = -ENOMEM;
 		goto out;
@@ -364,7 +360,7 @@
 	if (!idata->buf_bytes)
 		return idata;
 
-	idata->buf = kzalloc(idata->buf_bytes, GFP_KERNEL);
+	idata->buf = kmalloc(idata->buf_bytes, GFP_KERNEL);
 	if (!idata->buf) {
 		err = -ENOMEM;
 		goto idata_err;
@@ -2244,6 +2240,7 @@
 	md->disk->queue = md->queue.queue;
 	md->disk->driverfs_dev = parent;
 	set_disk_ro(md->disk, md->read_only || default_ro);
+	md->disk->flags = GENHD_FL_EXT_DEVT;
 	if (area_type & (MMC_BLK_DATA_AREA_RPMB | MMC_BLK_DATA_AREA_BOOT))
 		md->disk->flags |= GENHD_FL_NO_PART_SCAN;
 
diff --git a/drivers/mmc/core/bus.c b/drivers/mmc/core/bus.c
index 972ff84..4bc48f1 100644
--- a/drivers/mmc/core/bus.c
+++ b/drivers/mmc/core/bus.c
@@ -349,6 +349,8 @@
 
 	card->dev.of_node = mmc_of_find_child_device(card->host, 0);
 
+	device_enable_async_suspend(&card->dev);
+
 	ret = device_add(&card->dev);
 	if (ret)
 		return ret;
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index 5ae89e4..f95d41f 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -55,7 +55,6 @@
  */
 #define MMC_BKOPS_MAX_TIMEOUT	(4 * 60 * 1000) /* max time to wait in ms */
 
-static struct workqueue_struct *workqueue;
 static const unsigned freqs[] = { 400000, 300000, 200000, 100000 };
 
 /*
@@ -66,21 +65,16 @@
 bool use_spi_crc = 1;
 module_param(use_spi_crc, bool, 0);
 
-/*
- * Internal function. Schedule delayed work in the MMC work queue.
- */
 static int mmc_schedule_delayed_work(struct delayed_work *work,
 				     unsigned long delay)
 {
-	return queue_delayed_work(workqueue, work, delay);
-}
-
-/*
- * Internal function. Flush all scheduled work from the MMC work queue.
- */
-static void mmc_flush_scheduled_work(void)
-{
-	flush_workqueue(workqueue);
+	/*
+	 * We use the system_freezable_wq, because of two reasons.
+	 * First, it allows several works (not the same work item) to be
+	 * executed simultaneously. Second, the queue becomes frozen when
+	 * userspace becomes frozen during system PM.
+	 */
+	return queue_delayed_work(system_freezable_wq, work, delay);
 }
 
 #ifdef CONFIG_FAIL_MMC_REQUEST
@@ -1485,7 +1479,7 @@
 	if (IS_ERR(mmc->supply.vmmc)) {
 		if (PTR_ERR(mmc->supply.vmmc) == -EPROBE_DEFER)
 			return -EPROBE_DEFER;
-		dev_info(dev, "No vmmc regulator found\n");
+		dev_dbg(dev, "No vmmc regulator found\n");
 	} else {
 		ret = mmc_regulator_get_ocrmask(mmc->supply.vmmc);
 		if (ret > 0)
@@ -1497,7 +1491,7 @@
 	if (IS_ERR(mmc->supply.vqmmc)) {
 		if (PTR_ERR(mmc->supply.vqmmc) == -EPROBE_DEFER)
 			return -EPROBE_DEFER;
-		dev_info(dev, "No vqmmc regulator found\n");
+		dev_dbg(dev, "No vqmmc regulator found\n");
 	}
 
 	return 0;
@@ -2476,15 +2470,20 @@
 	 * sdio_reset sends CMD52 to reset card.  Since we do not know
 	 * if the card is being re-initialized, just send it.  CMD52
 	 * should be ignored by SD/eMMC cards.
+	 * Skip it if we already know that we do not support SDIO commands
 	 */
-	sdio_reset(host);
+	if (!(host->caps2 & MMC_CAP2_NO_SDIO))
+		sdio_reset(host);
+
 	mmc_go_idle(host);
 
 	mmc_send_if_cond(host, host->ocr_avail);
 
 	/* Order's important: probe SDIO, then SD, then MMC */
-	if (!mmc_attach_sdio(host))
-		return 0;
+	if (!(host->caps2 & MMC_CAP2_NO_SDIO))
+		if (!mmc_attach_sdio(host))
+			return 0;
+
 	if (!mmc_attach_sd(host))
 		return 0;
 	if (!mmc_attach_mmc(host))
@@ -2498,9 +2497,6 @@
 {
 	int ret;
 
-	if (host->caps & MMC_CAP_NONREMOVABLE)
-		return 0;
-
 	if (!host->card || mmc_card_removed(host->card))
 		return 1;
 
@@ -2536,6 +2532,9 @@
 	if (!card)
 		return 1;
 
+	if (host->caps & MMC_CAP_NONREMOVABLE)
+		return 0;
+
 	ret = mmc_card_removed(card);
 	/*
 	 * The card will be considered unchanged unless we have been asked to
@@ -2567,11 +2566,6 @@
 		container_of(work, struct mmc_host, detect.work);
 	int i;
 
-	if (host->trigger_card_event && host->ops->card_event) {
-		host->ops->card_event(host);
-		host->trigger_card_event = false;
-	}
-
 	if (host->rescan_disable)
 		return;
 
@@ -2580,6 +2574,13 @@
 		return;
 	host->rescan_entered = 1;
 
+	if (host->trigger_card_event && host->ops->card_event) {
+		mmc_claim_host(host);
+		host->ops->card_event(host);
+		mmc_release_host(host);
+		host->trigger_card_event = false;
+	}
+
 	mmc_bus_get(host);
 
 	/*
@@ -2611,15 +2612,14 @@
 	 */
 	mmc_bus_put(host);
 
+	mmc_claim_host(host);
 	if (!(host->caps & MMC_CAP_NONREMOVABLE) && host->ops->get_cd &&
 			host->ops->get_cd(host) == 0) {
-		mmc_claim_host(host);
 		mmc_power_off(host);
 		mmc_release_host(host);
 		goto out;
 	}
 
-	mmc_claim_host(host);
 	for (i = 0; i < ARRAY_SIZE(freqs); i++) {
 		if (!mmc_rescan_try_freq(host, max(freqs[i], host->f_min)))
 			break;
@@ -2663,7 +2663,6 @@
 
 	host->rescan_disable = 1;
 	cancel_delayed_work_sync(&host->detect);
-	mmc_flush_scheduled_work();
 
 	/* clear pm flags now and let card drivers set them as needed */
 	host->pm_flags = 0;
@@ -2759,14 +2758,13 @@
 }
 EXPORT_SYMBOL(mmc_flush_cache);
 
-#ifdef CONFIG_PM
-
+#ifdef CONFIG_PM_SLEEP
 /* Do the card removal on suspend if card is assumed removeable
  * Do that in pm notifier while userspace isn't yet frozen, so we will be able
    to sync the card.
 */
-int mmc_pm_notify(struct notifier_block *notify_block,
-					unsigned long mode, void *unused)
+static int mmc_pm_notify(struct notifier_block *notify_block,
+			unsigned long mode, void *unused)
 {
 	struct mmc_host *host = container_of(
 		notify_block, struct mmc_host, pm_notify);
@@ -2813,6 +2811,17 @@
 
 	return 0;
 }
+
+void mmc_register_pm_notifier(struct mmc_host *host)
+{
+	host->pm_notify.notifier_call = mmc_pm_notify;
+	register_pm_notifier(&host->pm_notify);
+}
+
+void mmc_unregister_pm_notifier(struct mmc_host *host)
+{
+	unregister_pm_notifier(&host->pm_notify);
+}
 #endif
 
 /**
@@ -2836,13 +2845,9 @@
 {
 	int ret;
 
-	workqueue = alloc_ordered_workqueue("kmmcd", 0);
-	if (!workqueue)
-		return -ENOMEM;
-
 	ret = mmc_register_bus();
 	if (ret)
-		goto destroy_workqueue;
+		return ret;
 
 	ret = mmc_register_host_class();
 	if (ret)
@@ -2858,9 +2863,6 @@
 	mmc_unregister_host_class();
 unregister_bus:
 	mmc_unregister_bus();
-destroy_workqueue:
-	destroy_workqueue(workqueue);
-
 	return ret;
 }
 
@@ -2869,7 +2871,6 @@
 	sdio_unregister_bus();
 	mmc_unregister_host_class();
 	mmc_unregister_bus();
-	destroy_workqueue(workqueue);
 }
 
 subsys_initcall(mmc_init);
diff --git a/drivers/mmc/core/core.h b/drivers/mmc/core/core.h
index 09241e5..0fa86a2 100644
--- a/drivers/mmc/core/core.h
+++ b/drivers/mmc/core/core.h
@@ -90,5 +90,13 @@
 int mmc_hs200_to_hs400(struct mmc_card *card);
 int mmc_hs400_to_hs200(struct mmc_card *card);
 
+#ifdef CONFIG_PM_SLEEP
+void mmc_register_pm_notifier(struct mmc_host *host);
+void mmc_unregister_pm_notifier(struct mmc_host *host);
+#else
+static inline void mmc_register_pm_notifier(struct mmc_host *host) { }
+static inline void mmc_unregister_pm_notifier(struct mmc_host *host) { }
+#endif
+
 #endif
 
diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c
index da950c4..0aecd5c 100644
--- a/drivers/mmc/core/host.c
+++ b/drivers/mmc/core/host.c
@@ -21,7 +21,6 @@
 #include <linux/export.h>
 #include <linux/leds.h>
 #include <linux/slab.h>
-#include <linux/suspend.h>
 
 #include <linux/mmc/host.h>
 #include <linux/mmc/card.h>
@@ -275,7 +274,8 @@
 		host->caps2 |= MMC_CAP2_FULL_PWR_CYCLE;
 	if (of_property_read_bool(np, "keep-power-in-suspend"))
 		host->pm_caps |= MMC_PM_KEEP_POWER;
-	if (of_property_read_bool(np, "enable-sdio-wakeup"))
+	if (of_property_read_bool(np, "wakeup-source") ||
+	    of_property_read_bool(np, "enable-sdio-wakeup")) /* legacy */
 		host->pm_caps |= MMC_PM_WAKE_SDIO_IRQ;
 	if (of_property_read_bool(np, "mmc-ddr-1_8v"))
 		host->caps |= MMC_CAP_1_8V_DDR;
@@ -348,9 +348,6 @@
 	spin_lock_init(&host->lock);
 	init_waitqueue_head(&host->wq);
 	INIT_DELAYED_WORK(&host->detect, mmc_rescan);
-#ifdef CONFIG_PM
-	host->pm_notify.notifier_call = mmc_pm_notify;
-#endif
 	setup_timer(&host->retune_timer, mmc_retune_timer, (unsigned long)host);
 
 	/*
@@ -395,7 +392,7 @@
 #endif
 
 	mmc_start_host(host);
-	register_pm_notifier(&host->pm_notify);
+	mmc_register_pm_notifier(host);
 
 	return 0;
 }
@@ -412,7 +409,7 @@
  */
 void mmc_remove_host(struct mmc_host *host)
 {
-	unregister_pm_notifier(&host->pm_notify);
+	mmc_unregister_pm_notifier(host);
 	mmc_stop_host(host);
 
 #ifdef CONFIG_DEBUG_FS
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index 3a9a79e..bf49e44 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -1076,8 +1076,7 @@
 	mmc_set_clock(host, max_dtr);
 
 	/* Switch card to HS mode */
-	val = EXT_CSD_TIMING_HS |
-	      card->drive_strength << EXT_CSD_DRV_STR_SHIFT;
+	val = EXT_CSD_TIMING_HS;
 	err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
 			   EXT_CSD_HS_TIMING, val,
 			   card->ext_csd.generic_cmd6_time,
@@ -1160,8 +1159,7 @@
 	mmc_set_clock(host, max_dtr);
 
 	/* Switch HS400 to HS DDR */
-	val = EXT_CSD_TIMING_HS |
-	      card->drive_strength << EXT_CSD_DRV_STR_SHIFT;
+	val = EXT_CSD_TIMING_HS;
 	err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL, EXT_CSD_HS_TIMING,
 			   val, card->ext_csd.generic_cmd6_time,
 			   true, send_status, true);
@@ -1907,16 +1905,8 @@
  */
 static int mmc_resume(struct mmc_host *host)
 {
-	int err = 0;
-
-	if (!(host->caps & MMC_CAP_RUNTIME_RESUME)) {
-		err = _mmc_resume(host);
-		pm_runtime_set_active(&host->card->dev);
-		pm_runtime_mark_last_busy(&host->card->dev);
-	}
 	pm_runtime_enable(&host->card->dev);
-
-	return err;
+	return 0;
 }
 
 /*
@@ -1944,12 +1934,9 @@
 {
 	int err;
 
-	if (!(host->caps & (MMC_CAP_AGGRESSIVE_PM | MMC_CAP_RUNTIME_RESUME)))
-		return 0;
-
 	err = _mmc_resume(host);
-	if (err)
-		pr_err("%s: error %d doing aggressive resume\n",
+	if (err && err != -ENOMEDIUM)
+		pr_err("%s: error %d doing runtime resume\n",
 			mmc_hostname(host), err);
 
 	return 0;
diff --git a/drivers/mmc/core/mmc_ops.c b/drivers/mmc/core/mmc_ops.c
index 1f44426..2c90635 100644
--- a/drivers/mmc/core/mmc_ops.c
+++ b/drivers/mmc/core/mmc_ops.c
@@ -489,6 +489,7 @@
 	unsigned long timeout;
 	u32 status = 0;
 	bool use_r1b_resp = use_busy_signal;
+	bool expired = false;
 
 	mmc_retune_hold(host);
 
@@ -545,6 +546,12 @@
 	timeout = jiffies + msecs_to_jiffies(timeout_ms);
 	do {
 		if (send_status) {
+			/*
+			 * Due to the possibility of being preempted after
+			 * sending the status command, check the expiration
+			 * time first.
+			 */
+			expired = time_after(jiffies, timeout);
 			err = __mmc_send_status(card, &status, ignore_crc);
 			if (err)
 				goto out;
@@ -565,7 +572,7 @@
 		}
 
 		/* Timeout if the device never leaves the program state. */
-		if (time_after(jiffies, timeout)) {
+		if (expired && R1_CURRENT_STATE(status) == R1_STATE_PRG) {
 			pr_err("%s: Card stuck in programming state! %s\n",
 				mmc_hostname(host), __func__);
 			err = -ETIMEDOUT;
diff --git a/drivers/mmc/core/pwrseq.h b/drivers/mmc/core/pwrseq.h
index 096da48..133de04 100644
--- a/drivers/mmc/core/pwrseq.h
+++ b/drivers/mmc/core/pwrseq.h
@@ -16,7 +16,7 @@
 };
 
 struct mmc_pwrseq {
-	struct mmc_pwrseq_ops *ops;
+	const struct mmc_pwrseq_ops *ops;
 };
 
 #ifdef CONFIG_OF
diff --git a/drivers/mmc/core/pwrseq_emmc.c b/drivers/mmc/core/pwrseq_emmc.c
index ad4f94e..4a82bc7 100644
--- a/drivers/mmc/core/pwrseq_emmc.c
+++ b/drivers/mmc/core/pwrseq_emmc.c
@@ -51,7 +51,7 @@
 	kfree(pwrseq);
 }
 
-static struct mmc_pwrseq_ops mmc_pwrseq_emmc_ops = {
+static const struct mmc_pwrseq_ops mmc_pwrseq_emmc_ops = {
 	.post_power_on = mmc_pwrseq_emmc_reset,
 	.free = mmc_pwrseq_emmc_free,
 };
diff --git a/drivers/mmc/core/pwrseq_simple.c b/drivers/mmc/core/pwrseq_simple.c
index d10538b..2b16263 100644
--- a/drivers/mmc/core/pwrseq_simple.c
+++ b/drivers/mmc/core/pwrseq_simple.c
@@ -87,7 +87,7 @@
 	kfree(pwrseq);
 }
 
-static struct mmc_pwrseq_ops mmc_pwrseq_simple_ops = {
+static const struct mmc_pwrseq_ops mmc_pwrseq_simple_ops = {
 	.pre_power_on = mmc_pwrseq_simple_pre_power_on,
 	.post_power_on = mmc_pwrseq_simple_post_power_on,
 	.power_off = mmc_pwrseq_simple_power_off,
diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c
index 141eaa9..f2b164b 100644
--- a/drivers/mmc/core/sd.c
+++ b/drivers/mmc/core/sd.c
@@ -1128,16 +1128,8 @@
  */
 static int mmc_sd_resume(struct mmc_host *host)
 {
-	int err = 0;
-
-	if (!(host->caps & MMC_CAP_RUNTIME_RESUME)) {
-		err = _mmc_sd_resume(host);
-		pm_runtime_set_active(&host->card->dev);
-		pm_runtime_mark_last_busy(&host->card->dev);
-	}
 	pm_runtime_enable(&host->card->dev);
-
-	return err;
+	return 0;
 }
 
 /*
@@ -1165,12 +1157,9 @@
 {
 	int err;
 
-	if (!(host->caps & (MMC_CAP_AGGRESSIVE_PM | MMC_CAP_RUNTIME_RESUME)))
-		return 0;
-
 	err = _mmc_sd_resume(host);
-	if (err)
-		pr_err("%s: error %d doing aggressive resume\n",
+	if (err && err != -ENOMEDIUM)
+		pr_err("%s: error %d doing runtime resume\n",
 			mmc_hostname(host), err);
 
 	return 0;
diff --git a/drivers/mmc/core/sdio.c b/drivers/mmc/core/sdio.c
index 16d838e..d61ba1a0 100644
--- a/drivers/mmc/core/sdio.c
+++ b/drivers/mmc/core/sdio.c
@@ -630,7 +630,7 @@
 	 */
 	if (!powered_resume && (rocr & ocr & R4_18V_PRESENT)) {
 		err = mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_180,
-					ocr);
+					ocr_card);
 		if (err == -EAGAIN) {
 			sdio_reset(host);
 			mmc_go_idle(host);
diff --git a/drivers/mmc/core/sdio_bus.c b/drivers/mmc/core/sdio_bus.c
index 7e327a6..86f5b32 100644
--- a/drivers/mmc/core/sdio_bus.c
+++ b/drivers/mmc/core/sdio_bus.c
@@ -322,6 +322,7 @@
 
 	sdio_set_of_node(func);
 	sdio_acpi_set_handle(func);
+	device_enable_async_suspend(&func->dev);
 	ret = device_add(&func->dev);
 	if (ret == 0)
 		sdio_func_set_present(func);
diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig
index 1dee533..1526b8a 100644
--- a/drivers/mmc/host/Kconfig
+++ b/drivers/mmc/host/Kconfig
@@ -455,6 +455,7 @@
 config MMC_MVSDIO
 	tristate "Marvell MMC/SD/SDIO host driver"
 	depends on PLAT_ORION
+	depends on OF
 	---help---
 	  This selects the Marvell SDIO host driver.
 	  SDIO may currently be found on the Kirkwood 88F6281 and 88F6192
diff --git a/drivers/mmc/host/atmel-mci-regs.h b/drivers/mmc/host/atmel-mci-regs.h
deleted file mode 100644
index 0aa44e6..0000000
--- a/drivers/mmc/host/atmel-mci-regs.h
+++ /dev/null
@@ -1,171 +0,0 @@
-/*
- * Atmel MultiMedia Card Interface driver
- *
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-/*
- * Superset of MCI IP registers integrated in Atmel AVR32 and AT91 Processors
- * Registers and bitfields marked with [2] are only available in MCI2
- */
-
-#ifndef __DRIVERS_MMC_ATMEL_MCI_H__
-#define __DRIVERS_MMC_ATMEL_MCI_H__
-
-/* MCI Register Definitions */
-#define ATMCI_CR			0x0000	/* Control */
-# define ATMCI_CR_MCIEN			(  1 <<  0)	/* MCI Enable */
-# define ATMCI_CR_MCIDIS		(  1 <<  1)	/* MCI Disable */
-# define ATMCI_CR_PWSEN			(  1 <<  2)	/* Power Save Enable */
-# define ATMCI_CR_PWSDIS		(  1 <<  3)	/* Power Save Disable */
-# define ATMCI_CR_SWRST			(  1 <<  7)	/* Software Reset */
-#define ATMCI_MR			0x0004	/* Mode */
-# define ATMCI_MR_CLKDIV(x)		((x) <<  0)	/* Clock Divider */
-# define ATMCI_MR_PWSDIV(x)		((x) <<  8)	/* Power Saving Divider */
-# define ATMCI_MR_RDPROOF		(  1 << 11)	/* Read Proof */
-# define ATMCI_MR_WRPROOF		(  1 << 12)	/* Write Proof */
-# define ATMCI_MR_PDCFBYTE		(  1 << 13)	/* Force Byte Transfer */
-# define ATMCI_MR_PDCPADV		(  1 << 14)	/* Padding Value */
-# define ATMCI_MR_PDCMODE		(  1 << 15)	/* PDC-oriented Mode */
-# define ATMCI_MR_CLKODD(x)		((x) << 16)	/* LSB of Clock Divider */
-#define ATMCI_DTOR			0x0008	/* Data Timeout */
-# define ATMCI_DTOCYC(x)		((x) <<  0)	/* Data Timeout Cycles */
-# define ATMCI_DTOMUL(x)		((x) <<  4)	/* Data Timeout Multiplier */
-#define ATMCI_SDCR			0x000c	/* SD Card / SDIO */
-# define ATMCI_SDCSEL_SLOT_A		(  0 <<  0)	/* Select SD slot A */
-# define ATMCI_SDCSEL_SLOT_B		(  1 <<  0)	/* Select SD slot A */
-# define ATMCI_SDCSEL_MASK		(  3 <<  0)
-# define ATMCI_SDCBUS_1BIT		(  0 <<  6)	/* 1-bit data bus */
-# define ATMCI_SDCBUS_4BIT		(  2 <<  6)	/* 4-bit data bus */
-# define ATMCI_SDCBUS_8BIT		(  3 <<  6)	/* 8-bit data bus[2] */
-# define ATMCI_SDCBUS_MASK		(  3 <<  6)
-#define ATMCI_ARGR			0x0010	/* Command Argument */
-#define ATMCI_CMDR			0x0014	/* Command */
-# define ATMCI_CMDR_CMDNB(x)		((x) <<  0)	/* Command Opcode */
-# define ATMCI_CMDR_RSPTYP_NONE		(  0 <<  6)	/* No response */
-# define ATMCI_CMDR_RSPTYP_48BIT	(  1 <<  6)	/* 48-bit response */
-# define ATMCI_CMDR_RSPTYP_136BIT	(  2 <<  6)	/* 136-bit response */
-# define ATMCI_CMDR_SPCMD_INIT		(  1 <<  8)	/* Initialization command */
-# define ATMCI_CMDR_SPCMD_SYNC		(  2 <<  8)	/* Synchronized command */
-# define ATMCI_CMDR_SPCMD_INT		(  4 <<  8)	/* Interrupt command */
-# define ATMCI_CMDR_SPCMD_INTRESP	(  5 <<  8)	/* Interrupt response */
-# define ATMCI_CMDR_OPDCMD		(  1 << 11)	/* Open Drain */
-# define ATMCI_CMDR_MAXLAT_5CYC		(  0 << 12)	/* Max latency 5 cycles */
-# define ATMCI_CMDR_MAXLAT_64CYC	(  1 << 12)	/* Max latency 64 cycles */
-# define ATMCI_CMDR_START_XFER		(  1 << 16)	/* Start data transfer */
-# define ATMCI_CMDR_STOP_XFER		(  2 << 16)	/* Stop data transfer */
-# define ATMCI_CMDR_TRDIR_WRITE		(  0 << 18)	/* Write data */
-# define ATMCI_CMDR_TRDIR_READ		(  1 << 18)	/* Read data */
-# define ATMCI_CMDR_BLOCK		(  0 << 19)	/* Single-block transfer */
-# define ATMCI_CMDR_MULTI_BLOCK		(  1 << 19)	/* Multi-block transfer */
-# define ATMCI_CMDR_STREAM		(  2 << 19)	/* MMC Stream transfer */
-# define ATMCI_CMDR_SDIO_BYTE		(  4 << 19)	/* SDIO Byte transfer */
-# define ATMCI_CMDR_SDIO_BLOCK		(  5 << 19)	/* SDIO Block transfer */
-# define ATMCI_CMDR_SDIO_SUSPEND	(  1 << 24)	/* SDIO Suspend Command */
-# define ATMCI_CMDR_SDIO_RESUME		(  2 << 24)	/* SDIO Resume Command */
-#define ATMCI_BLKR			0x0018	/* Block */
-# define ATMCI_BCNT(x)			((x) <<  0)	/* Data Block Count */
-# define ATMCI_BLKLEN(x)		((x) << 16)	/* Data Block Length */
-#define ATMCI_CSTOR			0x001c	/* Completion Signal Timeout[2] */
-# define ATMCI_CSTOCYC(x)		((x) <<  0)	/* CST cycles */
-# define ATMCI_CSTOMUL(x)		((x) <<  4)	/* CST multiplier */
-#define ATMCI_RSPR			0x0020	/* Response 0 */
-#define ATMCI_RSPR1			0x0024	/* Response 1 */
-#define ATMCI_RSPR2			0x0028	/* Response 2 */
-#define ATMCI_RSPR3			0x002c	/* Response 3 */
-#define ATMCI_RDR			0x0030	/* Receive Data */
-#define ATMCI_TDR			0x0034	/* Transmit Data */
-#define ATMCI_SR			0x0040	/* Status */
-#define ATMCI_IER			0x0044	/* Interrupt Enable */
-#define ATMCI_IDR			0x0048	/* Interrupt Disable */
-#define ATMCI_IMR			0x004c	/* Interrupt Mask */
-# define ATMCI_CMDRDY			(  1 <<   0)	/* Command Ready */
-# define ATMCI_RXRDY			(  1 <<   1)	/* Receiver Ready */
-# define ATMCI_TXRDY			(  1 <<   2)	/* Transmitter Ready */
-# define ATMCI_BLKE			(  1 <<   3)	/* Data Block Ended */
-# define ATMCI_DTIP			(  1 <<   4)	/* Data Transfer In Progress */
-# define ATMCI_NOTBUSY			(  1 <<   5)	/* Data Not Busy */
-# define ATMCI_ENDRX			(  1 <<   6)    /* End of RX Buffer */
-# define ATMCI_ENDTX			(  1 <<   7)    /* End of TX Buffer */
-# define ATMCI_SDIOIRQA			(  1 <<   8)	/* SDIO IRQ in slot A */
-# define ATMCI_SDIOIRQB			(  1 <<   9)	/* SDIO IRQ in slot B */
-# define ATMCI_SDIOWAIT			(  1 <<  12)    /* SDIO Read Wait Operation Status */
-# define ATMCI_CSRCV			(  1 <<  13)    /* CE-ATA Completion Signal Received */
-# define ATMCI_RXBUFF			(  1 <<  14)    /* RX Buffer Full */
-# define ATMCI_TXBUFE			(  1 <<  15)    /* TX Buffer Empty */
-# define ATMCI_RINDE			(  1 <<  16)	/* Response Index Error */
-# define ATMCI_RDIRE			(  1 <<  17)	/* Response Direction Error */
-# define ATMCI_RCRCE			(  1 <<  18)	/* Response CRC Error */
-# define ATMCI_RENDE			(  1 <<  19)	/* Response End Bit Error */
-# define ATMCI_RTOE			(  1 <<  20)	/* Response Time-Out Error */
-# define ATMCI_DCRCE			(  1 <<  21)	/* Data CRC Error */
-# define ATMCI_DTOE			(  1 <<  22)	/* Data Time-Out Error */
-# define ATMCI_CSTOE			(  1 <<  23)    /* Completion Signal Time-out Error */
-# define ATMCI_BLKOVRE			(  1 <<  24)    /* DMA Block Overrun Error */
-# define ATMCI_DMADONE			(  1 <<  25)    /* DMA Transfer Done */
-# define ATMCI_FIFOEMPTY		(  1 <<  26)    /* FIFO Empty Flag */
-# define ATMCI_XFRDONE			(  1 <<  27)    /* Transfer Done Flag */
-# define ATMCI_ACKRCV			(  1 <<  28)    /* Boot Operation Acknowledge Received */
-# define ATMCI_ACKRCVE			(  1 <<  29)    /* Boot Operation Acknowledge Error */
-# define ATMCI_OVRE			(  1 <<  30)	/* RX Overrun Error */
-# define ATMCI_UNRE			(  1 <<  31)	/* TX Underrun Error */
-#define ATMCI_DMA			0x0050	/* DMA Configuration[2] */
-# define ATMCI_DMA_OFFSET(x)		((x) <<  0)	/* DMA Write Buffer Offset */
-# define ATMCI_DMA_CHKSIZE(x)		((x) <<  4)	/* DMA Channel Read and Write Chunk Size */
-# define ATMCI_DMAEN			(  1 <<  8)	/* DMA Hardware Handshaking Enable */
-#define ATMCI_CFG			0x0054	/* Configuration[2] */
-# define ATMCI_CFG_FIFOMODE_1DATA	(  1 <<  0)	/* MCI Internal FIFO control mode */
-# define ATMCI_CFG_FERRCTRL_COR		(  1 <<  4)	/* Flow Error flag reset control mode */
-# define ATMCI_CFG_HSMODE		(  1 <<  8)	/* High Speed Mode */
-# define ATMCI_CFG_LSYNC		(  1 << 12)	/* Synchronize on the last block */
-#define ATMCI_WPMR			0x00e4	/* Write Protection Mode[2] */
-# define ATMCI_WP_EN			(  1 <<  0)	/* WP Enable */
-# define ATMCI_WP_KEY			(0x4d4349 << 8)	/* WP Key */
-#define ATMCI_WPSR			0x00e8	/* Write Protection Status[2] */
-# define ATMCI_GET_WP_VS(x)		((x) & 0x0f)
-# define ATMCI_GET_WP_VSRC(x)		(((x) >> 8) & 0xffff)
-#define ATMCI_VERSION			0x00FC  /* Version */
-#define ATMCI_FIFO_APERTURE		0x0200	/* FIFO Aperture[2] */
-
-/* This is not including the FIFO Aperture on MCI2 */
-#define ATMCI_REGS_SIZE		0x100
-
-/* Register access macros */
-#ifdef CONFIG_AVR32
-#define atmci_readl(port, reg)			\
-	__raw_readl((port)->regs + reg)
-#define atmci_writel(port, reg, value)			\
-	__raw_writel((value), (port)->regs + reg)
-#else
-#define atmci_readl(port, reg)			\
-	readl_relaxed((port)->regs + reg)
-#define atmci_writel(port, reg, value)			\
-	writel_relaxed((value), (port)->regs + reg)
-#endif
-
-/* On AVR chips the Peripheral DMA Controller is not connected to MCI. */
-#ifdef CONFIG_AVR32
-#	define ATMCI_PDC_CONNECTED	0
-#else
-#	define ATMCI_PDC_CONNECTED	1
-#endif
-
-/*
- * Fix sconfig's burst size according to atmel MCI. We need to convert them as:
- * 1 -> 0, 4 -> 1, 8 -> 2, 16 -> 3.
- *
- * This can be done by finding most significant bit set.
- */
-static inline unsigned int atmci_convert_chksize(unsigned int maxburst)
-{
-	if (maxburst > 1)
-		return fls(maxburst) - 2;
-	else
-		return 0;
-}
-
-#endif /* __DRIVERS_MMC_ATMEL_MCI_H__ */
diff --git a/drivers/mmc/host/atmel-mci.c b/drivers/mmc/host/atmel-mci.c
index bf62e42..a36ebda 100644
--- a/drivers/mmc/host/atmel-mci.c
+++ b/drivers/mmc/host/atmel-mci.c
@@ -44,7 +44,141 @@
 #include <asm/io.h>
 #include <asm/unaligned.h>
 
-#include "atmel-mci-regs.h"
+/*
+ * Superset of MCI IP registers integrated in Atmel AVR32 and AT91 Processors
+ * Registers and bitfields marked with [2] are only available in MCI2
+ */
+
+/* MCI Register Definitions */
+#define	ATMCI_CR			0x0000	/* Control */
+#define		ATMCI_CR_MCIEN			BIT(0)		/* MCI Enable */
+#define		ATMCI_CR_MCIDIS			BIT(1)		/* MCI Disable */
+#define		ATMCI_CR_PWSEN			BIT(2)		/* Power Save Enable */
+#define		ATMCI_CR_PWSDIS			BIT(3)		/* Power Save Disable */
+#define		ATMCI_CR_SWRST			BIT(7)		/* Software Reset */
+#define	ATMCI_MR			0x0004	/* Mode */
+#define		ATMCI_MR_CLKDIV(x)		((x) <<  0)	/* Clock Divider */
+#define		ATMCI_MR_PWSDIV(x)		((x) <<  8)	/* Power Saving Divider */
+#define		ATMCI_MR_RDPROOF		BIT(11)		/* Read Proof */
+#define		ATMCI_MR_WRPROOF		BIT(12)		/* Write Proof */
+#define		ATMCI_MR_PDCFBYTE		BIT(13)		/* Force Byte Transfer */
+#define		ATMCI_MR_PDCPADV		BIT(14)		/* Padding Value */
+#define		ATMCI_MR_PDCMODE		BIT(15)		/* PDC-oriented Mode */
+#define		ATMCI_MR_CLKODD(x)		((x) << 16)	/* LSB of Clock Divider */
+#define	ATMCI_DTOR			0x0008	/* Data Timeout */
+#define		ATMCI_DTOCYC(x)			((x) <<  0)	/* Data Timeout Cycles */
+#define		ATMCI_DTOMUL(x)			((x) <<  4)	/* Data Timeout Multiplier */
+#define	ATMCI_SDCR			0x000c	/* SD Card / SDIO */
+#define		ATMCI_SDCSEL_SLOT_A		(0 <<  0)	/* Select SD slot A */
+#define		ATMCI_SDCSEL_SLOT_B		(1 <<  0)	/* Select SD slot A */
+#define		ATMCI_SDCSEL_MASK		(3 <<  0)
+#define		ATMCI_SDCBUS_1BIT		(0 <<  6)	/* 1-bit data bus */
+#define		ATMCI_SDCBUS_4BIT		(2 <<  6)	/* 4-bit data bus */
+#define		ATMCI_SDCBUS_8BIT		(3 <<  6)	/* 8-bit data bus[2] */
+#define		ATMCI_SDCBUS_MASK		(3 <<  6)
+#define	ATMCI_ARGR			0x0010	/* Command Argument */
+#define	ATMCI_CMDR			0x0014	/* Command */
+#define		ATMCI_CMDR_CMDNB(x)		((x) <<  0)	/* Command Opcode */
+#define		ATMCI_CMDR_RSPTYP_NONE		(0 <<  6)	/* No response */
+#define		ATMCI_CMDR_RSPTYP_48BIT		(1 <<  6)	/* 48-bit response */
+#define		ATMCI_CMDR_RSPTYP_136BIT	(2 <<  6)	/* 136-bit response */
+#define		ATMCI_CMDR_SPCMD_INIT		(1 <<  8)	/* Initialization command */
+#define		ATMCI_CMDR_SPCMD_SYNC		(2 <<  8)	/* Synchronized command */
+#define		ATMCI_CMDR_SPCMD_INT		(4 <<  8)	/* Interrupt command */
+#define		ATMCI_CMDR_SPCMD_INTRESP	(5 <<  8)	/* Interrupt response */
+#define		ATMCI_CMDR_OPDCMD		(1 << 11)	/* Open Drain */
+#define		ATMCI_CMDR_MAXLAT_5CYC		(0 << 12)	/* Max latency 5 cycles */
+#define		ATMCI_CMDR_MAXLAT_64CYC		(1 << 12)	/* Max latency 64 cycles */
+#define		ATMCI_CMDR_START_XFER		(1 << 16)	/* Start data transfer */
+#define		ATMCI_CMDR_STOP_XFER		(2 << 16)	/* Stop data transfer */
+#define		ATMCI_CMDR_TRDIR_WRITE		(0 << 18)	/* Write data */
+#define		ATMCI_CMDR_TRDIR_READ		(1 << 18)	/* Read data */
+#define		ATMCI_CMDR_BLOCK		(0 << 19)	/* Single-block transfer */
+#define		ATMCI_CMDR_MULTI_BLOCK		(1 << 19)	/* Multi-block transfer */
+#define		ATMCI_CMDR_STREAM		(2 << 19)	/* MMC Stream transfer */
+#define		ATMCI_CMDR_SDIO_BYTE		(4 << 19)	/* SDIO Byte transfer */
+#define		ATMCI_CMDR_SDIO_BLOCK		(5 << 19)	/* SDIO Block transfer */
+#define		ATMCI_CMDR_SDIO_SUSPEND		(1 << 24)	/* SDIO Suspend Command */
+#define		ATMCI_CMDR_SDIO_RESUME		(2 << 24)	/* SDIO Resume Command */
+#define	ATMCI_BLKR			0x0018	/* Block */
+#define		ATMCI_BCNT(x)			((x) <<  0)	/* Data Block Count */
+#define		ATMCI_BLKLEN(x)			((x) << 16)	/* Data Block Length */
+#define	ATMCI_CSTOR			0x001c	/* Completion Signal Timeout[2] */
+#define		ATMCI_CSTOCYC(x)		((x) <<  0)	/* CST cycles */
+#define		ATMCI_CSTOMUL(x)		((x) <<  4)	/* CST multiplier */
+#define	ATMCI_RSPR			0x0020	/* Response 0 */
+#define	ATMCI_RSPR1			0x0024	/* Response 1 */
+#define	ATMCI_RSPR2			0x0028	/* Response 2 */
+#define	ATMCI_RSPR3			0x002c	/* Response 3 */
+#define	ATMCI_RDR			0x0030	/* Receive Data */
+#define	ATMCI_TDR			0x0034	/* Transmit Data */
+#define	ATMCI_SR			0x0040	/* Status */
+#define	ATMCI_IER			0x0044	/* Interrupt Enable */
+#define	ATMCI_IDR			0x0048	/* Interrupt Disable */
+#define	ATMCI_IMR			0x004c	/* Interrupt Mask */
+#define		ATMCI_CMDRDY			BIT(0)		/* Command Ready */
+#define		ATMCI_RXRDY			BIT(1)		/* Receiver Ready */
+#define		ATMCI_TXRDY			BIT(2)		/* Transmitter Ready */
+#define		ATMCI_BLKE			BIT(3)		/* Data Block Ended */
+#define		ATMCI_DTIP			BIT(4)		/* Data Transfer In Progress */
+#define		ATMCI_NOTBUSY			BIT(5)		/* Data Not Busy */
+#define		ATMCI_ENDRX			BIT(6)		/* End of RX Buffer */
+#define		ATMCI_ENDTX			BIT(7)		/* End of TX Buffer */
+#define		ATMCI_SDIOIRQA			BIT(8)		/* SDIO IRQ in slot A */
+#define		ATMCI_SDIOIRQB			BIT(9)		/* SDIO IRQ in slot B */
+#define		ATMCI_SDIOWAIT			BIT(12)		/* SDIO Read Wait Operation Status */
+#define		ATMCI_CSRCV			BIT(13)		/* CE-ATA Completion Signal Received */
+#define		ATMCI_RXBUFF			BIT(14)		/* RX Buffer Full */
+#define		ATMCI_TXBUFE			BIT(15)		/* TX Buffer Empty */
+#define		ATMCI_RINDE			BIT(16)		/* Response Index Error */
+#define		ATMCI_RDIRE			BIT(17)		/* Response Direction Error */
+#define		ATMCI_RCRCE			BIT(18)		/* Response CRC Error */
+#define		ATMCI_RENDE			BIT(19)		/* Response End Bit Error */
+#define		ATMCI_RTOE			BIT(20)		/* Response Time-Out Error */
+#define		ATMCI_DCRCE			BIT(21)		/* Data CRC Error */
+#define		ATMCI_DTOE			BIT(22)		/* Data Time-Out Error */
+#define		ATMCI_CSTOE			BIT(23)		/* Completion Signal Time-out Error */
+#define		ATMCI_BLKOVRE			BIT(24)		/* DMA Block Overrun Error */
+#define		ATMCI_DMADONE			BIT(25)		/* DMA Transfer Done */
+#define		ATMCI_FIFOEMPTY			BIT(26)		/* FIFO Empty Flag */
+#define		ATMCI_XFRDONE			BIT(27)		/* Transfer Done Flag */
+#define		ATMCI_ACKRCV			BIT(28)		/* Boot Operation Acknowledge Received */
+#define		ATMCI_ACKRCVE			BIT(29)		/* Boot Operation Acknowledge Error */
+#define		ATMCI_OVRE			BIT(30)		/* RX Overrun Error */
+#define		ATMCI_UNRE			BIT(31)		/* TX Underrun Error */
+#define	ATMCI_DMA			0x0050	/* DMA Configuration[2] */
+#define		ATMCI_DMA_OFFSET(x)		((x) <<  0)	/* DMA Write Buffer Offset */
+#define		ATMCI_DMA_CHKSIZE(x)		((x) <<  4)	/* DMA Channel Read and Write Chunk Size */
+#define		ATMCI_DMAEN			BIT(8)	/* DMA Hardware Handshaking Enable */
+#define	ATMCI_CFG			0x0054	/* Configuration[2] */
+#define		ATMCI_CFG_FIFOMODE_1DATA	BIT(0)		/* MCI Internal FIFO control mode */
+#define		ATMCI_CFG_FERRCTRL_COR		BIT(4)		/* Flow Error flag reset control mode */
+#define		ATMCI_CFG_HSMODE		BIT(8)		/* High Speed Mode */
+#define		ATMCI_CFG_LSYNC			BIT(12)		/* Synchronize on the last block */
+#define	ATMCI_WPMR			0x00e4	/* Write Protection Mode[2] */
+#define		ATMCI_WP_EN			BIT(0)		/* WP Enable */
+#define		ATMCI_WP_KEY			(0x4d4349 << 8)	/* WP Key */
+#define	ATMCI_WPSR			0x00e8	/* Write Protection Status[2] */
+#define		ATMCI_GET_WP_VS(x)		((x) & 0x0f)
+#define		ATMCI_GET_WP_VSRC(x)		(((x) >> 8) & 0xffff)
+#define	ATMCI_VERSION			0x00FC  /* Version */
+#define	ATMCI_FIFO_APERTURE		0x0200	/* FIFO Aperture[2] */
+
+/* This is not including the FIFO Aperture on MCI2 */
+#define	ATMCI_REGS_SIZE		0x100
+
+/* Register access macros */
+#define	atmci_readl(port, reg)				\
+	__raw_readl((port)->regs + reg)
+#define	atmci_writel(port, reg, value)			\
+	__raw_writel((value), (port)->regs + reg)
+
+/* On AVR chips the Peripheral DMA Controller is not connected to MCI. */
+#ifdef CONFIG_AVR32
+#	define ATMCI_PDC_CONNECTED	0
+#else
+#	define ATMCI_PDC_CONNECTED	1
+#endif
 
 #define AUTOSUSPEND_DELAY	50
 
@@ -584,6 +718,29 @@
 	return atmci_readl(host, ATMCI_VERSION) & 0x00000fff;
 }
 
+/*
+ * Fix sconfig's burst size according to atmel MCI. We need to convert them as:
+ * 1 -> 0, 4 -> 1, 8 -> 2, 16 -> 3.
+ * With version 0x600, we need to convert them as: 1 -> 0, 2 -> 1, 4 -> 2,
+ * 8 -> 3, 16 -> 4.
+ *
+ * This can be done by finding most significant bit set.
+ */
+static inline unsigned int atmci_convert_chksize(struct atmel_mci *host,
+						 unsigned int maxburst)
+{
+	unsigned int version = atmci_get_version(host);
+	unsigned int offset = 2;
+
+	if (version >= 0x600)
+		offset = 1;
+
+	if (maxburst > 1)
+		return fls(maxburst) - offset;
+	else
+		return 0;
+}
+
 static void atmci_timeout_timer(unsigned long data)
 {
 	struct atmel_mci *host;
@@ -1034,11 +1191,13 @@
 	if (data->flags & MMC_DATA_READ) {
 		direction = DMA_FROM_DEVICE;
 		host->dma_conf.direction = slave_dirn = DMA_DEV_TO_MEM;
-		maxburst = atmci_convert_chksize(host->dma_conf.src_maxburst);
+		maxburst = atmci_convert_chksize(host,
+						 host->dma_conf.src_maxburst);
 	} else {
 		direction = DMA_TO_DEVICE;
 		host->dma_conf.direction = slave_dirn = DMA_MEM_TO_DEV;
-		maxburst = atmci_convert_chksize(host->dma_conf.dst_maxburst);
+		maxburst = atmci_convert_chksize(host,
+						 host->dma_conf.dst_maxburst);
 	}
 
 	if (host->caps.has_dma_conf_reg)
diff --git a/drivers/mmc/host/cb710-mmc.h b/drivers/mmc/host/cb710-mmc.h
index 8984ec8..8ecd9e5 100644
--- a/drivers/mmc/host/cb710-mmc.h
+++ b/drivers/mmc/host/cb710-mmc.h
@@ -29,8 +29,7 @@
 
 static inline struct cb710_slot *cb710_mmc_to_slot(struct mmc_host *mmc)
 {
-	struct platform_device *pdev = container_of(mmc_dev(mmc),
-		struct platform_device, dev);
+	struct platform_device *pdev = to_platform_device(mmc_dev(mmc));
 	return cb710_pdev_to_slot(pdev);
 }
 
diff --git a/drivers/mmc/host/dw_mmc-pltfm.c b/drivers/mmc/host/dw_mmc-pltfm.c
index 7e1d13b..81bdeeb 100644
--- a/drivers/mmc/host/dw_mmc-pltfm.c
+++ b/drivers/mmc/host/dw_mmc-pltfm.c
@@ -60,7 +60,7 @@
 
 	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	/* Get registers' physical base address */
-	host->phy_regs = (void *)(regs->start);
+	host->phy_regs = regs->start;
 	host->regs = devm_ioremap_resource(&pdev->dev, regs);
 	if (IS_ERR(host->regs))
 		return PTR_ERR(host->regs);
diff --git a/drivers/mmc/host/dw_mmc-rockchip.c b/drivers/mmc/host/dw_mmc-rockchip.c
index 9becebe..d9c92f3 100644
--- a/drivers/mmc/host/dw_mmc-rockchip.c
+++ b/drivers/mmc/host/dw_mmc-rockchip.c
@@ -239,20 +239,12 @@
 	return 0;
 }
 
-/* Common capabilities of RK3288 SoC */
-static unsigned long dw_mci_rk3288_dwmmc_caps[4] = {
-	MMC_CAP_RUNTIME_RESUME, /* emmc */
-	MMC_CAP_RUNTIME_RESUME, /* sdmmc */
-	MMC_CAP_RUNTIME_RESUME, /* sdio0 */
-	MMC_CAP_RUNTIME_RESUME, /* sdio1 */
-};
 static const struct dw_mci_drv_data rk2928_drv_data = {
 	.prepare_command        = dw_mci_rockchip_prepare_command,
 	.init			= dw_mci_rockchip_init,
 };
 
 static const struct dw_mci_drv_data rk3288_drv_data = {
-	.caps			= dw_mci_rk3288_dwmmc_caps,
 	.prepare_command        = dw_mci_rockchip_prepare_command,
 	.set_ios		= dw_mci_rk3288_set_ios,
 	.execute_tuning		= dw_mci_rk3288_execute_tuning,
diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index 7a6cedb..7128351 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -699,7 +699,7 @@
 	int ret = 0;
 
 	/* Set external dma config: burst size, burst width */
-	cfg.dst_addr = (dma_addr_t)(host->phy_regs + fifo_offset);
+	cfg.dst_addr = host->phy_regs + fifo_offset;
 	cfg.src_addr = cfg.dst_addr;
 	cfg.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
 	cfg.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
@@ -1634,12 +1634,6 @@
 	else
 		cmd->error = 0;
 
-	if (cmd->error) {
-		/* newer ip versions need a delay between retries */
-		if (host->quirks & DW_MCI_QUIRK_RETRY_DELAY)
-			mdelay(20);
-	}
-
 	return cmd->error;
 }
 
@@ -2355,16 +2349,6 @@
 
 	pending = mci_readl(host, MINTSTS); /* read-only mask reg */
 
-	/*
-	 * DTO fix - version 2.10a and below, and only if internal DMA
-	 * is configured.
-	 */
-	if (host->quirks & DW_MCI_QUIRK_IDMAC_DTO) {
-		if (!pending &&
-		    ((mci_readl(host, STATUS) >> 17) & 0x1fff))
-			pending |= SDMMC_INT_DATA_OVER;
-	}
-
 	if (pending) {
 		/* Check volt switch first, since it can look like an error */
 		if ((host->state == STATE_SENDING_CMD11) &&
@@ -3165,9 +3149,6 @@
 	/* Now that slots are all setup, we can enable card detect */
 	dw_mci_enable_cd(host);
 
-	if (host->quirks & DW_MCI_QUIRK_IDMAC_DTO)
-		dev_info(host->dev, "Internal DMAC interrupt fix enabled.\n");
-
 	return 0;
 
 err_dmaunmap:
diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c
index 33dfd7e..82a97ac 100644
--- a/drivers/mmc/host/mtk-sd.c
+++ b/drivers/mmc/host/mtk-sd.c
@@ -972,7 +972,7 @@
 		if ((events & MSDC_INT_XFER_COMPL) && (!stop || !stop->error)) {
 			data->bytes_xfered = data->blocks * data->blksz;
 		} else {
-			dev_err(host->dev, "interrupt events: %x\n", events);
+			dev_dbg(host->dev, "interrupt events: %x\n", events);
 			msdc_reset_hw(host);
 			host->error |= REQ_DAT_ERR;
 			data->bytes_xfered = 0;
@@ -982,10 +982,10 @@
 			else if (events & MSDC_INT_DATCRCERR)
 				data->error = -EILSEQ;
 
-			dev_err(host->dev, "%s: cmd=%d; blocks=%d",
+			dev_dbg(host->dev, "%s: cmd=%d; blocks=%d",
 				__func__, mrq->cmd->opcode, data->blocks);
-			dev_err(host->dev, "data_error=%d xfer_size=%d\n",
-					(int)data->error, data->bytes_xfered);
+			dev_dbg(host->dev, "data_error=%d xfer_size=%d\n",
+				(int)data->error, data->bytes_xfered);
 		}
 
 		msdc_data_xfer_next(host, mrq, data);
@@ -1543,7 +1543,6 @@
 	mmc->f_min = host->src_clk_freq / (4 * 255);
 
 	mmc->caps |= MMC_CAP_ERASE | MMC_CAP_CMD23;
-	mmc->caps |= MMC_CAP_RUNTIME_RESUME;
 	/* MMC core transfer sizes tunable parameters */
 	mmc->max_segs = MAX_BD_NUM;
 	mmc->max_seg_size = BDMA_DESC_BUFLEN;
diff --git a/drivers/mmc/host/mvsdio.c b/drivers/mmc/host/mvsdio.c
index a448498..42296e5 100644
--- a/drivers/mmc/host/mvsdio.c
+++ b/drivers/mmc/host/mvsdio.c
@@ -20,15 +20,12 @@
 #include <linux/scatterlist.h>
 #include <linux/irq.h>
 #include <linux/clk.h>
-#include <linux/gpio.h>
-#include <linux/of_gpio.h>
 #include <linux/of_irq.h>
 #include <linux/mmc/host.h>
 #include <linux/mmc/slot-gpio.h>
 
 #include <asm/sizes.h>
 #include <asm/unaligned.h>
-#include <linux/platform_data/mmc-mvsdio.h>
 
 #include "mvsdio.h"
 
@@ -704,6 +701,10 @@
 	struct resource *r;
 	int ret, irq;
 
+	if (!np) {
+		dev_err(&pdev->dev, "no DT node\n");
+		return -ENODEV;
+	}
 	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	irq = platform_get_irq(pdev, 0);
 	if (!r || irq < 0)
@@ -727,8 +728,12 @@
 	 * fixed rate clock).
 	 */
 	host->clk = devm_clk_get(&pdev->dev, NULL);
-	if (!IS_ERR(host->clk))
-		clk_prepare_enable(host->clk);
+	if (IS_ERR(host->clk)) {
+		dev_err(&pdev->dev, "no clock associated\n");
+		ret = -EINVAL;
+		goto out;
+	}
+	clk_prepare_enable(host->clk);
 
 	mmc->ops = &mvsd_ops;
 
@@ -744,45 +749,10 @@
 	mmc->max_seg_size = mmc->max_blk_size * mmc->max_blk_count;
 	mmc->max_req_size = mmc->max_blk_size * mmc->max_blk_count;
 
-	if (np) {
-		if (IS_ERR(host->clk)) {
-			dev_err(&pdev->dev, "DT platforms must have a clock associated\n");
-			ret = -EINVAL;
-			goto out;
-		}
-
-		host->base_clock = clk_get_rate(host->clk) / 2;
-		ret = mmc_of_parse(mmc);
-		if (ret < 0)
-			goto out;
-	} else {
-		const struct mvsdio_platform_data *mvsd_data;
-
-		mvsd_data = pdev->dev.platform_data;
-		if (!mvsd_data) {
-			ret = -ENXIO;
-			goto out;
-		}
-		mmc->caps = MMC_CAP_4_BIT_DATA | MMC_CAP_SDIO_IRQ |
-			    MMC_CAP_SD_HIGHSPEED | MMC_CAP_MMC_HIGHSPEED;
-		host->base_clock = mvsd_data->clock / 2;
-		/* GPIO 0 regarded as invalid for backward compatibility */
-		if (mvsd_data->gpio_card_detect &&
-		    gpio_is_valid(mvsd_data->gpio_card_detect)) {
-			ret = mmc_gpio_request_cd(mmc,
-						  mvsd_data->gpio_card_detect,
-						  0);
-			if (ret)
-				goto out;
-		} else {
-			mmc->caps |= MMC_CAP_NEEDS_POLL;
-		}
-
-		if (mvsd_data->gpio_write_protect &&
-		    gpio_is_valid(mvsd_data->gpio_write_protect))
-			mmc_gpio_request_ro(mmc, mvsd_data->gpio_write_protect);
-	}
-
+	host->base_clock = clk_get_rate(host->clk) / 2;
+	ret = mmc_of_parse(mmc);
+	if (ret < 0)
+		goto out;
 	if (maxfreq)
 		mmc->f_max = maxfreq;
 
diff --git a/drivers/mmc/host/of_mmc_spi.c b/drivers/mmc/host/of_mmc_spi.c
index 6e218fb..660170c 100644
--- a/drivers/mmc/host/of_mmc_spi.c
+++ b/drivers/mmc/host/of_mmc_spi.c
@@ -55,8 +55,8 @@
 {
 	struct of_mmc_spi *oms = to_of_mmc_spi(dev);
 
-	return request_threaded_irq(oms->detect_irq, NULL, irqhandler, 0,
-				    dev_name(dev), mmc);
+	return request_threaded_irq(oms->detect_irq, NULL, irqhandler,
+					IRQF_ONESHOT, dev_name(dev), mmc);
 }
 
 static void of_mmc_spi_exit(struct device *dev, void *mmc)
diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c
index 7fb0753..b6639ea 100644
--- a/drivers/mmc/host/omap_hsmmc.c
+++ b/drivers/mmc/host/omap_hsmmc.c
@@ -2250,10 +2250,8 @@
 	pm_runtime_get_sync(host->dev);
 	mmc_remove_host(host->mmc);
 
-	if (host->tx_chan)
-		dma_release_channel(host->tx_chan);
-	if (host->rx_chan)
-		dma_release_channel(host->rx_chan);
+	dma_release_channel(host->tx_chan);
+	dma_release_channel(host->rx_chan);
 
 	pm_runtime_put_sync(host->dev);
 	pm_runtime_disable(host->dev);
diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c
index 1f1582f..f25f292 100644
--- a/drivers/mmc/host/sdhci-esdhc-imx.c
+++ b/drivers/mmc/host/sdhci-esdhc-imx.c
@@ -76,6 +76,7 @@
 #define ESDHC_STD_TUNING_EN		(1 << 24)
 /* NOTE: the minimum valid tuning start tap for mx6sl is 1 */
 #define ESDHC_TUNING_START_TAP		0x1
+#define ESDHC_TUNING_STEP_MASK		0x00070000
 #define ESDHC_TUNING_STEP_SHIFT		16
 
 /* pinctrl state */
@@ -489,9 +490,11 @@
 				m |= ESDHC_MIX_CTRL_FBCLK_SEL;
 				tuning_ctrl = readl(host->ioaddr + ESDHC_TUNING_CTRL);
 				tuning_ctrl |= ESDHC_STD_TUNING_EN | ESDHC_TUNING_START_TAP;
-				if (imx_data->boarddata.tuning_step)
+				if (imx_data->boarddata.tuning_step) {
+					tuning_ctrl &= ~ESDHC_TUNING_STEP_MASK;
 					tuning_ctrl |= imx_data->boarddata.tuning_step << ESDHC_TUNING_STEP_SHIFT;
-					writel(tuning_ctrl, host->ioaddr + ESDHC_TUNING_CTRL);
+				}
+				writel(tuning_ctrl, host->ioaddr + ESDHC_TUNING_CTRL);
 			} else {
 				v &= ~ESDHC_MIX_CTRL_EXE_TUNE;
 			}
diff --git a/drivers/mmc/host/sdhci-of-at91.c b/drivers/mmc/host/sdhci-of-at91.c
index 06d0b50..7e7d8f0 100644
--- a/drivers/mmc/host/sdhci-of-at91.c
+++ b/drivers/mmc/host/sdhci-of-at91.c
@@ -21,6 +21,8 @@
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
+#include <linux/pm.h>
+#include <linux/pm_runtime.h>
 
 #include "sdhci-pltfm.h"
 
@@ -51,6 +53,60 @@
 	{}
 };
 
+#ifdef CONFIG_PM
+static int sdhci_at91_runtime_suspend(struct device *dev)
+{
+	struct sdhci_host *host = dev_get_drvdata(dev);
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct sdhci_at91_priv *priv = pltfm_host->priv;
+	int ret;
+
+	ret = sdhci_runtime_suspend_host(host);
+
+	clk_disable_unprepare(priv->gck);
+	clk_disable_unprepare(priv->hclock);
+	clk_disable_unprepare(priv->mainck);
+
+	return ret;
+}
+
+static int sdhci_at91_runtime_resume(struct device *dev)
+{
+	struct sdhci_host *host = dev_get_drvdata(dev);
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct sdhci_at91_priv *priv = pltfm_host->priv;
+	int ret;
+
+	ret = clk_prepare_enable(priv->mainck);
+	if (ret) {
+		dev_err(dev, "can't enable mainck\n");
+		return ret;
+	}
+
+	ret = clk_prepare_enable(priv->hclock);
+	if (ret) {
+		dev_err(dev, "can't enable hclock\n");
+		return ret;
+	}
+
+	ret = clk_prepare_enable(priv->gck);
+	if (ret) {
+		dev_err(dev, "can't enable gck\n");
+		return ret;
+	}
+
+	return sdhci_runtime_resume_host(host);
+}
+#endif /* CONFIG_PM */
+
+static const struct dev_pm_ops sdhci_at91_dev_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
+	SET_RUNTIME_PM_OPS(sdhci_at91_runtime_suspend,
+			   sdhci_at91_runtime_resume,
+			   NULL)
+};
+
 static int sdhci_at91_probe(struct platform_device *pdev)
 {
 	const struct of_device_id	*match;
@@ -144,12 +200,23 @@
 
 	sdhci_get_of_property(pdev);
 
+	pm_runtime_get_noresume(&pdev->dev);
+	pm_runtime_set_active(&pdev->dev);
+	pm_runtime_enable(&pdev->dev);
+	pm_runtime_set_autosuspend_delay(&pdev->dev, 50);
+	pm_runtime_use_autosuspend(&pdev->dev);
+
 	ret = sdhci_add_host(host);
 	if (ret)
-		goto clocks_disable_unprepare;
+		goto pm_runtime_disable;
+
+	pm_runtime_put_autosuspend(&pdev->dev);
 
 	return 0;
 
+pm_runtime_disable:
+	pm_runtime_disable(&pdev->dev);
+	pm_runtime_set_suspended(&pdev->dev);
 clocks_disable_unprepare:
 	clk_disable_unprepare(priv->gck);
 	clk_disable_unprepare(priv->mainck);
@@ -165,6 +232,10 @@
 	struct sdhci_pltfm_host	*pltfm_host = sdhci_priv(host);
 	struct sdhci_at91_priv	*priv = pltfm_host->priv;
 
+	pm_runtime_get_sync(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
+	pm_runtime_put_noidle(&pdev->dev);
+
 	sdhci_pltfm_unregister(pdev);
 
 	clk_disable_unprepare(priv->gck);
@@ -178,7 +249,7 @@
 	.driver		= {
 		.name	= "sdhci-at91",
 		.of_match_table = sdhci_at91_dt_match,
-		.pm	= SDHCI_PLTFM_PMOPS,
+		.pm	= &sdhci_at91_dev_pm_ops,
 	},
 	.probe		= sdhci_at91_probe,
 	.remove		= sdhci_at91_remove,
diff --git a/drivers/mmc/host/sdhci-of-esdhc.c b/drivers/mmc/host/sdhci-of-esdhc.c
index 90e94a0..83b1226 100644
--- a/drivers/mmc/host/sdhci-of-esdhc.c
+++ b/drivers/mmc/host/sdhci-of-esdhc.c
@@ -584,6 +584,8 @@
 {
 	struct sdhci_host *host;
 	struct device_node *np;
+	struct sdhci_pltfm_host *pltfm_host;
+	struct sdhci_esdhc *esdhc;
 	int ret;
 
 	np = pdev->dev.of_node;
@@ -600,6 +602,14 @@
 
 	sdhci_get_of_property(pdev);
 
+	pltfm_host = sdhci_priv(host);
+	esdhc = pltfm_host->priv;
+	if (esdhc->vendor_ver == VENDOR_V_22)
+		host->quirks2 |= SDHCI_QUIRK2_HOST_NO_CMD23;
+
+	if (esdhc->vendor_ver > VENDOR_V_22)
+		host->quirks &= ~SDHCI_QUIRK_NO_BUSY_IRQ;
+
 	if (of_device_is_compatible(np, "fsl,p5040-esdhc") ||
 	    of_device_is_compatible(np, "fsl,p5020-esdhc") ||
 	    of_device_is_compatible(np, "fsl,p4080-esdhc") ||
diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c
index cf7ad45..cc851b0 100644
--- a/drivers/mmc/host/sdhci-pci-core.c
+++ b/drivers/mmc/host/sdhci-pci-core.c
@@ -277,7 +277,7 @@
 	if (sdhci_pci_spt_drive_strength > 0)
 		drive_strength = sdhci_pci_spt_drive_strength & 0xf;
 	else
-		drive_strength = 1; /* 33-ohm */
+		drive_strength = 0; /* Default 50-ohm */
 
 	if ((mmc_driver_type_mask(drive_strength) & card_drv) == 0)
 		drive_strength = 0; /* Default 50-ohm */
@@ -1464,7 +1464,7 @@
 
 static int sdhci_pci_runtime_suspend(struct device *dev)
 {
-	struct pci_dev *pdev = container_of(dev, struct pci_dev, dev);
+	struct pci_dev *pdev = to_pci_dev(dev);
 	struct sdhci_pci_chip *chip;
 	struct sdhci_pci_slot *slot;
 	int i, ret;
@@ -1500,7 +1500,7 @@
 
 static int sdhci_pci_runtime_resume(struct device *dev)
 {
-	struct pci_dev *pdev = container_of(dev, struct pci_dev, dev);
+	struct pci_dev *pdev = to_pci_dev(dev);
 	struct sdhci_pci_chip *chip;
 	struct sdhci_pci_slot *slot;
 	int i, ret;
diff --git a/drivers/mmc/host/sdhci-pltfm.c b/drivers/mmc/host/sdhci-pltfm.c
index 87fb5ea..072bb27 100644
--- a/drivers/mmc/host/sdhci-pltfm.c
+++ b/drivers/mmc/host/sdhci-pltfm.c
@@ -104,7 +104,8 @@
 	if (of_find_property(np, "keep-power-in-suspend", NULL))
 		host->mmc->pm_caps |= MMC_PM_KEEP_POWER;
 
-	if (of_find_property(np, "enable-sdio-wakeup", NULL))
+	if (of_property_read_bool(np, "wakeup-source") ||
+	    of_property_read_bool(np, "enable-sdio-wakeup")) /* legacy */
 		host->mmc->pm_caps |= MMC_PM_WAKE_SDIO_IRQ;
 }
 #else
diff --git a/drivers/mmc/host/sdhci-tegra.c b/drivers/mmc/host/sdhci-tegra.c
index ad28b49..83c4bf7 100644
--- a/drivers/mmc/host/sdhci-tegra.c
+++ b/drivers/mmc/host/sdhci-tegra.c
@@ -22,12 +22,20 @@
 #include <linux/of_device.h>
 #include <linux/mmc/card.h>
 #include <linux/mmc/host.h>
+#include <linux/mmc/mmc.h>
 #include <linux/mmc/slot-gpio.h>
 #include <linux/gpio/consumer.h>
 
 #include "sdhci-pltfm.h"
 
 /* Tegra SDHOST controller vendor register definitions */
+#define SDHCI_TEGRA_VENDOR_CLOCK_CTRL			0x100
+#define SDHCI_CLOCK_CTRL_TAP_MASK			0x00ff0000
+#define SDHCI_CLOCK_CTRL_TAP_SHIFT			16
+#define SDHCI_CLOCK_CTRL_SDR50_TUNING_OVERRIDE		BIT(5)
+#define SDHCI_CLOCK_CTRL_PADPIPE_CLKEN_OVERRIDE		BIT(3)
+#define SDHCI_CLOCK_CTRL_SPI_MODE_CLKEN_OVERRIDE	BIT(2)
+
 #define SDHCI_TEGRA_VENDOR_MISC_CTRL		0x120
 #define SDHCI_MISC_CTRL_ENABLE_SDR104		0x8
 #define SDHCI_MISC_CTRL_ENABLE_SDR50		0x10
@@ -37,9 +45,9 @@
 #define NVQUIRK_FORCE_SDHCI_SPEC_200	BIT(0)
 #define NVQUIRK_ENABLE_BLOCK_GAP_DET	BIT(1)
 #define NVQUIRK_ENABLE_SDHCI_SPEC_300	BIT(2)
-#define NVQUIRK_DISABLE_SDR50		BIT(3)
-#define NVQUIRK_DISABLE_SDR104		BIT(4)
-#define NVQUIRK_DISABLE_DDR50		BIT(5)
+#define NVQUIRK_ENABLE_SDR50		BIT(3)
+#define NVQUIRK_ENABLE_SDR104		BIT(4)
+#define NVQUIRK_ENABLE_DDR50		BIT(5)
 
 struct sdhci_tegra_soc_data {
 	const struct sdhci_pltfm_data *pdata;
@@ -49,6 +57,7 @@
 struct sdhci_tegra {
 	const struct sdhci_tegra_soc_data *soc_data;
 	struct gpio_desc *power_gpio;
+	bool ddr_signaling;
 };
 
 static u16 tegra_sdhci_readw(struct sdhci_host *host, int reg)
@@ -124,25 +133,33 @@
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
 	struct sdhci_tegra *tegra_host = pltfm_host->priv;
 	const struct sdhci_tegra_soc_data *soc_data = tegra_host->soc_data;
-	u32 misc_ctrl;
+	u32 misc_ctrl, clk_ctrl;
 
 	sdhci_reset(host, mask);
 
 	if (!(mask & SDHCI_RESET_ALL))
 		return;
 
-	misc_ctrl = sdhci_readw(host, SDHCI_TEGRA_VENDOR_MISC_CTRL);
+	misc_ctrl = sdhci_readl(host, SDHCI_TEGRA_VENDOR_MISC_CTRL);
 	/* Erratum: Enable SDHCI spec v3.00 support */
 	if (soc_data->nvquirks & NVQUIRK_ENABLE_SDHCI_SPEC_300)
 		misc_ctrl |= SDHCI_MISC_CTRL_ENABLE_SDHCI_SPEC_300;
-	/* Don't advertise UHS modes which aren't supported yet */
-	if (soc_data->nvquirks & NVQUIRK_DISABLE_SDR50)
-		misc_ctrl &= ~SDHCI_MISC_CTRL_ENABLE_SDR50;
-	if (soc_data->nvquirks & NVQUIRK_DISABLE_DDR50)
-		misc_ctrl &= ~SDHCI_MISC_CTRL_ENABLE_DDR50;
-	if (soc_data->nvquirks & NVQUIRK_DISABLE_SDR104)
-		misc_ctrl &= ~SDHCI_MISC_CTRL_ENABLE_SDR104;
-	sdhci_writew(host, misc_ctrl, SDHCI_TEGRA_VENDOR_MISC_CTRL);
+	/* Advertise UHS modes as supported by host */
+	if (soc_data->nvquirks & NVQUIRK_ENABLE_SDR50)
+		misc_ctrl |= SDHCI_MISC_CTRL_ENABLE_SDR50;
+	if (soc_data->nvquirks & NVQUIRK_ENABLE_DDR50)
+		misc_ctrl |= SDHCI_MISC_CTRL_ENABLE_DDR50;
+	if (soc_data->nvquirks & NVQUIRK_ENABLE_SDR104)
+		misc_ctrl |= SDHCI_MISC_CTRL_ENABLE_SDR104;
+	sdhci_writel(host, misc_ctrl, SDHCI_TEGRA_VENDOR_MISC_CTRL);
+
+	clk_ctrl = sdhci_readl(host, SDHCI_TEGRA_VENDOR_CLOCK_CTRL);
+	clk_ctrl &= ~SDHCI_CLOCK_CTRL_SPI_MODE_CLKEN_OVERRIDE;
+	if (soc_data->nvquirks & SDHCI_MISC_CTRL_ENABLE_SDR50)
+		clk_ctrl |= SDHCI_CLOCK_CTRL_SDR50_TUNING_OVERRIDE;
+	sdhci_writel(host, clk_ctrl, SDHCI_TEGRA_VENDOR_CLOCK_CTRL);
+
+	tegra_host->ddr_signaling = false;
 }
 
 static void tegra_sdhci_set_bus_width(struct sdhci_host *host, int bus_width)
@@ -164,15 +181,99 @@
 	sdhci_writeb(host, ctrl, SDHCI_HOST_CONTROL);
 }
 
+static void tegra_sdhci_set_clock(struct sdhci_host *host, unsigned int clock)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct sdhci_tegra *tegra_host = pltfm_host->priv;
+	unsigned long host_clk;
+
+	if (!clock)
+		return;
+
+	host_clk = tegra_host->ddr_signaling ? clock * 2 : clock;
+	clk_set_rate(pltfm_host->clk, host_clk);
+	host->max_clk = clk_get_rate(pltfm_host->clk);
+
+	return sdhci_set_clock(host, clock);
+}
+
+static void tegra_sdhci_set_uhs_signaling(struct sdhci_host *host,
+					  unsigned timing)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct sdhci_tegra *tegra_host = pltfm_host->priv;
+
+	if (timing == MMC_TIMING_UHS_DDR50)
+		tegra_host->ddr_signaling = true;
+
+	return sdhci_set_uhs_signaling(host, timing);
+}
+
+static unsigned int tegra_sdhci_get_max_clock(struct sdhci_host *host)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+
+	/*
+	 * DDR modes require the host to run at double the card frequency, so
+	 * the maximum rate we can support is half of the module input clock.
+	 */
+	return clk_round_rate(pltfm_host->clk, UINT_MAX) / 2;
+}
+
+static void tegra_sdhci_set_tap(struct sdhci_host *host, unsigned int tap)
+{
+	u32 reg;
+
+	reg = sdhci_readl(host, SDHCI_TEGRA_VENDOR_CLOCK_CTRL);
+	reg &= ~SDHCI_CLOCK_CTRL_TAP_MASK;
+	reg |= tap << SDHCI_CLOCK_CTRL_TAP_SHIFT;
+	sdhci_writel(host, reg, SDHCI_TEGRA_VENDOR_CLOCK_CTRL);
+}
+
+static int tegra_sdhci_execute_tuning(struct sdhci_host *host, u32 opcode)
+{
+	unsigned int min, max;
+
+	/*
+	 * Start search for minimum tap value at 10, as smaller values are
+	 * may wrongly be reported as working but fail at higher speeds,
+	 * according to the TRM.
+	 */
+	min = 10;
+	while (min < 255) {
+		tegra_sdhci_set_tap(host, min);
+		if (!mmc_send_tuning(host->mmc, opcode, NULL))
+			break;
+		min++;
+	}
+
+	/* Find the maximum tap value that still passes. */
+	max = min + 1;
+	while (max < 255) {
+		tegra_sdhci_set_tap(host, max);
+		if (mmc_send_tuning(host->mmc, opcode, NULL)) {
+			max--;
+			break;
+		}
+		max++;
+	}
+
+	/* The TRM states the ideal tap value is at 75% in the passing range. */
+	tegra_sdhci_set_tap(host, min + ((max - min) * 3 / 4));
+
+	return mmc_send_tuning(host->mmc, opcode, NULL);
+}
+
 static const struct sdhci_ops tegra_sdhci_ops = {
 	.get_ro     = tegra_sdhci_get_ro,
 	.read_w     = tegra_sdhci_readw,
 	.write_l    = tegra_sdhci_writel,
-	.set_clock  = sdhci_set_clock,
+	.set_clock  = tegra_sdhci_set_clock,
 	.set_bus_width = tegra_sdhci_set_bus_width,
 	.reset      = tegra_sdhci_reset,
-	.set_uhs_signaling = sdhci_set_uhs_signaling,
-	.get_max_clock = sdhci_pltfm_clk_get_max_clock,
+	.platform_execute_tuning = tegra_sdhci_execute_tuning,
+	.set_uhs_signaling = tegra_sdhci_set_uhs_signaling,
+	.get_max_clock = tegra_sdhci_get_max_clock,
 };
 
 static const struct sdhci_pltfm_data sdhci_tegra20_pdata = {
@@ -184,7 +285,7 @@
 	.ops  = &tegra_sdhci_ops,
 };
 
-static struct sdhci_tegra_soc_data soc_data_tegra20 = {
+static const struct sdhci_tegra_soc_data soc_data_tegra20 = {
 	.pdata = &sdhci_tegra20_pdata,
 	.nvquirks = NVQUIRK_FORCE_SDHCI_SPEC_200 |
 		    NVQUIRK_ENABLE_BLOCK_GAP_DET,
@@ -197,14 +298,15 @@
 		  SDHCI_QUIRK_NO_HISPD_BIT |
 		  SDHCI_QUIRK_BROKEN_ADMA_ZEROLEN_DESC |
 		  SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN,
+	.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN,
 	.ops  = &tegra_sdhci_ops,
 };
 
-static struct sdhci_tegra_soc_data soc_data_tegra30 = {
+static const struct sdhci_tegra_soc_data soc_data_tegra30 = {
 	.pdata = &sdhci_tegra30_pdata,
 	.nvquirks = NVQUIRK_ENABLE_SDHCI_SPEC_300 |
-		    NVQUIRK_DISABLE_SDR50 |
-		    NVQUIRK_DISABLE_SDR104,
+		    NVQUIRK_ENABLE_SDR50 |
+		    NVQUIRK_ENABLE_SDR104,
 };
 
 static const struct sdhci_ops tegra114_sdhci_ops = {
@@ -212,11 +314,12 @@
 	.read_w     = tegra_sdhci_readw,
 	.write_w    = tegra_sdhci_writew,
 	.write_l    = tegra_sdhci_writel,
-	.set_clock  = sdhci_set_clock,
+	.set_clock  = tegra_sdhci_set_clock,
 	.set_bus_width = tegra_sdhci_set_bus_width,
 	.reset      = tegra_sdhci_reset,
-	.set_uhs_signaling = sdhci_set_uhs_signaling,
-	.get_max_clock = sdhci_pltfm_clk_get_max_clock,
+	.platform_execute_tuning = tegra_sdhci_execute_tuning,
+	.set_uhs_signaling = tegra_sdhci_set_uhs_signaling,
+	.get_max_clock = tegra_sdhci_get_max_clock,
 };
 
 static const struct sdhci_pltfm_data sdhci_tegra114_pdata = {
@@ -226,17 +329,34 @@
 		  SDHCI_QUIRK_NO_HISPD_BIT |
 		  SDHCI_QUIRK_BROKEN_ADMA_ZEROLEN_DESC |
 		  SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN,
+	.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN,
 	.ops  = &tegra114_sdhci_ops,
 };
 
-static struct sdhci_tegra_soc_data soc_data_tegra114 = {
+static const struct sdhci_tegra_soc_data soc_data_tegra114 = {
 	.pdata = &sdhci_tegra114_pdata,
-	.nvquirks = NVQUIRK_DISABLE_SDR50 |
-		    NVQUIRK_DISABLE_DDR50 |
-		    NVQUIRK_DISABLE_SDR104,
+	.nvquirks = NVQUIRK_ENABLE_SDR50 |
+		    NVQUIRK_ENABLE_DDR50 |
+		    NVQUIRK_ENABLE_SDR104,
+};
+
+static const struct sdhci_pltfm_data sdhci_tegra210_pdata = {
+	.quirks = SDHCI_QUIRK_BROKEN_TIMEOUT_VAL |
+		  SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK |
+		  SDHCI_QUIRK_SINGLE_POWER_WRITE |
+		  SDHCI_QUIRK_NO_HISPD_BIT |
+		  SDHCI_QUIRK_BROKEN_ADMA_ZEROLEN_DESC |
+		  SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN,
+	.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN,
+	.ops  = &tegra114_sdhci_ops,
+};
+
+static const struct sdhci_tegra_soc_data soc_data_tegra210 = {
+	.pdata = &sdhci_tegra210_pdata,
 };
 
 static const struct of_device_id sdhci_tegra_dt_match[] = {
+	{ .compatible = "nvidia,tegra210-sdhci", .data = &soc_data_tegra210 },
 	{ .compatible = "nvidia,tegra124-sdhci", .data = &soc_data_tegra114 },
 	{ .compatible = "nvidia,tegra114-sdhci", .data = &soc_data_tegra114 },
 	{ .compatible = "nvidia,tegra30-sdhci", .data = &soc_data_tegra30 },
@@ -271,6 +391,7 @@
 		rc = -ENOMEM;
 		goto err_alloc_tegra_host;
 	}
+	tegra_host->ddr_signaling = false;
 	tegra_host->soc_data = soc_data;
 	pltfm_host->priv = tegra_host;
 
@@ -278,6 +399,9 @@
 	if (rc)
 		goto err_parse_dt;
 
+	if (tegra_host->soc_data->nvquirks & NVQUIRK_ENABLE_DDR50)
+		host->mmc->caps |= MMC_CAP_1_8V_DDR;
+
 	tegra_host->power_gpio = devm_gpiod_get_optional(&pdev->dev, "power",
 							 GPIOD_OUT_HIGH);
 	if (IS_ERR(tegra_host->power_gpio)) {
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index b48565e..d622435 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -492,7 +492,7 @@
 		host->align_buffer, host->align_buffer_sz, direction);
 	if (dma_mapping_error(mmc_dev(host->mmc), host->align_addr))
 		goto fail;
-	BUG_ON(host->align_addr & host->align_mask);
+	BUG_ON(host->align_addr & SDHCI_ADMA2_MASK);
 
 	host->sg_count = sdhci_pre_dma_transfer(host, data);
 	if (host->sg_count < 0)
@@ -514,8 +514,8 @@
 		 * the (up to three) bytes that screw up the
 		 * alignment.
 		 */
-		offset = (host->align_sz - (addr & host->align_mask)) &
-			 host->align_mask;
+		offset = (SDHCI_ADMA2_ALIGN - (addr & SDHCI_ADMA2_MASK)) &
+			 SDHCI_ADMA2_MASK;
 		if (offset) {
 			if (data->flags & MMC_DATA_WRITE) {
 				buffer = sdhci_kmap_atomic(sg, &flags);
@@ -529,8 +529,8 @@
 
 			BUG_ON(offset > 65536);
 
-			align += host->align_sz;
-			align_addr += host->align_sz;
+			align += SDHCI_ADMA2_ALIGN;
+			align_addr += SDHCI_ADMA2_ALIGN;
 
 			desc += host->desc_sz;
 
@@ -540,9 +540,12 @@
 
 		BUG_ON(len > 65536);
 
-		/* tran, valid */
-		sdhci_adma_write_desc(host, desc, addr, len, ADMA2_TRAN_VALID);
-		desc += host->desc_sz;
+		if (len) {
+			/* tran, valid */
+			sdhci_adma_write_desc(host, desc, addr, len,
+					      ADMA2_TRAN_VALID);
+			desc += host->desc_sz;
+		}
 
 		/*
 		 * If this triggers then we have a calculation bug
@@ -608,7 +611,7 @@
 	/* Do a quick scan of the SG list for any unaligned mappings */
 	has_unaligned = false;
 	for_each_sg(data->sg, sg, host->sg_count, i)
-		if (sg_dma_address(sg) & host->align_mask) {
+		if (sg_dma_address(sg) & SDHCI_ADMA2_MASK) {
 			has_unaligned = true;
 			break;
 		}
@@ -620,15 +623,15 @@
 		align = host->align_buffer;
 
 		for_each_sg(data->sg, sg, host->sg_count, i) {
-			if (sg_dma_address(sg) & host->align_mask) {
-				size = host->align_sz -
-				       (sg_dma_address(sg) & host->align_mask);
+			if (sg_dma_address(sg) & SDHCI_ADMA2_MASK) {
+				size = SDHCI_ADMA2_ALIGN -
+				       (sg_dma_address(sg) & SDHCI_ADMA2_MASK);
 
 				buffer = sdhci_kmap_atomic(sg, &flags);
 				memcpy(buffer, align, size);
 				sdhci_kunmap_atomic(buffer, &flags);
 
-				align += host->align_sz;
+				align += SDHCI_ADMA2_ALIGN;
 			}
 		}
 	}
@@ -768,8 +771,7 @@
 		if (unlikely(broken)) {
 			for_each_sg(data->sg, sg, data->sg_len, i) {
 				if (sg->length & 0x3) {
-					DBG("Reverting to PIO because of "
-						"transfer size (%d)\n",
+					DBG("Reverting to PIO because of transfer size (%d)\n",
 						sg->length);
 					host->flags &= ~SDHCI_REQ_USE_DMA;
 					break;
@@ -803,8 +805,7 @@
 		if (unlikely(broken)) {
 			for_each_sg(data->sg, sg, data->sg_len, i) {
 				if (sg->offset & 0x3) {
-					DBG("Reverting to PIO because of "
-						"bad alignment\n");
+					DBG("Reverting to PIO because of bad alignment\n");
 					host->flags &= ~SDHCI_REQ_USE_DMA;
 					break;
 				}
@@ -1016,8 +1017,8 @@
 
 	while (sdhci_readl(host, SDHCI_PRESENT_STATE) & mask) {
 		if (timeout == 0) {
-			pr_err("%s: Controller never released "
-				"inhibit bit(s).\n", mmc_hostname(host->mmc));
+			pr_err("%s: Controller never released inhibit bit(s).\n",
+			       mmc_hostname(host->mmc));
 			sdhci_dumpregs(host);
 			cmd->error = -EIO;
 			tasklet_schedule(&host->finish_tasklet);
@@ -1254,8 +1255,8 @@
 	while (!((clk = sdhci_readw(host, SDHCI_CLOCK_CONTROL))
 		& SDHCI_CLOCK_INT_STABLE)) {
 		if (timeout == 0) {
-			pr_err("%s: Internal clock never "
-				"stabilised.\n", mmc_hostname(host->mmc));
+			pr_err("%s: Internal clock never stabilised.\n",
+			       mmc_hostname(host->mmc));
 			sdhci_dumpregs(host);
 			return;
 		}
@@ -1274,19 +1275,6 @@
 	struct mmc_host *mmc = host->mmc;
 	u8 pwr = 0;
 
-	if (!IS_ERR(mmc->supply.vmmc)) {
-		spin_unlock_irq(&host->lock);
-		mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, vdd);
-		spin_lock_irq(&host->lock);
-
-		if (mode != MMC_POWER_OFF)
-			sdhci_writeb(host, SDHCI_POWER_ON, SDHCI_POWER_CONTROL);
-		else
-			sdhci_writeb(host, 0, SDHCI_POWER_CONTROL);
-
-		return;
-	}
-
 	if (mode != MMC_POWER_OFF) {
 		switch (1 << vdd) {
 		case MMC_VDD_165_195:
@@ -1301,7 +1289,9 @@
 			pwr = SDHCI_POWER_330;
 			break;
 		default:
-			BUG();
+			WARN(1, "%s: Invalid vdd %#x\n",
+			     mmc_hostname(host->mmc), vdd);
+			break;
 		}
 	}
 
@@ -1345,6 +1335,12 @@
 		if (host->quirks & SDHCI_QUIRK_DELAY_AFTER_POWER)
 			mdelay(10);
 	}
+
+	if (!IS_ERR(mmc->supply.vmmc)) {
+		spin_unlock_irq(&host->lock);
+		mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, vdd);
+		spin_lock_irq(&host->lock);
+	}
 }
 
 /*****************************************************************************\
@@ -1540,8 +1536,8 @@
 			else if (ios->drv_type == MMC_SET_DRIVER_TYPE_D)
 				ctrl_2 |= SDHCI_CTRL_DRV_TYPE_D;
 			else {
-				pr_warn("%s: invalid driver type, default to "
-					"driver type B\n", mmc_hostname(mmc));
+				pr_warn("%s: invalid driver type, default to driver type B\n",
+					mmc_hostname(mmc));
 				ctrl_2 |= SDHCI_CTRL_DRV_TYPE_B;
 			}
 
@@ -2015,10 +2011,7 @@
 		spin_lock_irqsave(&host->lock, flags);
 
 		if (!host->tuning_done) {
-			pr_info(DRIVER_NAME ": Timeout waiting for "
-				"Buffer Read Ready interrupt during tuning "
-				"procedure, falling back to fixed sampling "
-				"clock\n");
+			pr_info(DRIVER_NAME ": Timeout waiting for Buffer Read Ready interrupt during tuning procedure, falling back to fixed sampling clock\n");
 			ctrl = sdhci_readw(host, SDHCI_HOST_CONTROL2);
 			ctrl &= ~SDHCI_CTRL_TUNED_CLK;
 			ctrl &= ~SDHCI_CTRL_EXEC_TUNING;
@@ -2046,9 +2039,7 @@
 		sdhci_writew(host, ctrl, SDHCI_HOST_CONTROL2);
 	}
 	if (!(ctrl & SDHCI_CTRL_TUNED_CLK)) {
-		pr_info(DRIVER_NAME ": Tuning procedure"
-			" failed, falling back to fixed sampling"
-			" clock\n");
+		pr_info(DRIVER_NAME ": Tuning procedure failed, falling back to fixed sampling clock\n");
 		err = -EIO;
 	}
 
@@ -2293,8 +2284,8 @@
 	spin_lock_irqsave(&host->lock, flags);
 
 	if (host->mrq) {
-		pr_err("%s: Timeout waiting for hardware "
-			"interrupt.\n", mmc_hostname(host->mmc));
+		pr_err("%s: Timeout waiting for hardware interrupt.\n",
+		       mmc_hostname(host->mmc));
 		sdhci_dumpregs(host);
 
 		if (host->data) {
@@ -2325,9 +2316,8 @@
 	BUG_ON(intmask == 0);
 
 	if (!host->cmd) {
-		pr_err("%s: Got command interrupt 0x%08x even "
-			"though no command operation was in progress.\n",
-			mmc_hostname(host->mmc), (unsigned)intmask);
+		pr_err("%s: Got command interrupt 0x%08x even though no command operation was in progress.\n",
+		       mmc_hostname(host->mmc), (unsigned)intmask);
 		sdhci_dumpregs(host);
 		return;
 	}
@@ -2356,8 +2346,7 @@
 	 */
 	if (host->cmd->flags & MMC_RSP_BUSY) {
 		if (host->cmd->data)
-			DBG("Cannot wait for busy signal when also "
-				"doing a data transfer");
+			DBG("Cannot wait for busy signal when also doing a data transfer");
 		else if (!(host->quirks & SDHCI_QUIRK_NO_BUSY_IRQ)
 				&& !host->busy_handle) {
 			/* Mark that command complete before busy is ended */
@@ -2451,9 +2440,8 @@
 			}
 		}
 
-		pr_err("%s: Got data interrupt 0x%08x even "
-			"though no data operation was in progress.\n",
-			mmc_hostname(host->mmc), (unsigned)intmask);
+		pr_err("%s: Got data interrupt 0x%08x even though no data operation was in progress.\n",
+		       mmc_hostname(host->mmc), (unsigned)intmask);
 		sdhci_dumpregs(host);
 
 		return;
@@ -2760,7 +2748,7 @@
 
 static void sdhci_runtime_pm_bus_on(struct sdhci_host *host)
 {
-	if (host->runtime_suspended || host->bus_on)
+	if (host->bus_on)
 		return;
 	host->bus_on = true;
 	pm_runtime_get_noresume(host->mmc->parent);
@@ -2768,7 +2756,7 @@
 
 static void sdhci_runtime_pm_bus_off(struct sdhci_host *host)
 {
-	if (host->runtime_suspended || !host->bus_on)
+	if (!host->bus_on)
 		return;
 	host->bus_on = false;
 	pm_runtime_put_noidle(host->mmc->parent);
@@ -2896,9 +2884,8 @@
 	host->version = (host->version & SDHCI_SPEC_VER_MASK)
 				>> SDHCI_SPEC_VER_SHIFT;
 	if (host->version > SDHCI_SPEC_300) {
-		pr_err("%s: Unknown controller version (%d). "
-			"You may experience problems.\n", mmc_hostname(mmc),
-			host->version);
+		pr_err("%s: Unknown controller version (%d). You may experience problems.\n",
+		       mmc_hostname(mmc), host->version);
 	}
 
 	caps[0] = (host->quirks & SDHCI_QUIRK_MISSING_CAPS) ? host->caps :
@@ -2967,24 +2954,17 @@
 		if (host->flags & SDHCI_USE_64_BIT_DMA) {
 			host->adma_table_sz = (SDHCI_MAX_SEGS * 2 + 1) *
 					      SDHCI_ADMA2_64_DESC_SZ;
-			host->align_buffer_sz = SDHCI_MAX_SEGS *
-						SDHCI_ADMA2_64_ALIGN;
 			host->desc_sz = SDHCI_ADMA2_64_DESC_SZ;
-			host->align_sz = SDHCI_ADMA2_64_ALIGN;
-			host->align_mask = SDHCI_ADMA2_64_ALIGN - 1;
 		} else {
 			host->adma_table_sz = (SDHCI_MAX_SEGS * 2 + 1) *
 					      SDHCI_ADMA2_32_DESC_SZ;
-			host->align_buffer_sz = SDHCI_MAX_SEGS *
-						SDHCI_ADMA2_32_ALIGN;
 			host->desc_sz = SDHCI_ADMA2_32_DESC_SZ;
-			host->align_sz = SDHCI_ADMA2_32_ALIGN;
-			host->align_mask = SDHCI_ADMA2_32_ALIGN - 1;
 		}
 		host->adma_table = dma_alloc_coherent(mmc_dev(mmc),
 						      host->adma_table_sz,
 						      &host->adma_addr,
 						      GFP_KERNEL);
+		host->align_buffer_sz = SDHCI_MAX_SEGS * SDHCI_ADMA2_ALIGN;
 		host->align_buffer = kmalloc(host->align_buffer_sz, GFP_KERNEL);
 		if (!host->adma_table || !host->align_buffer) {
 			if (host->adma_table)
@@ -2998,7 +2978,7 @@
 			host->flags &= ~SDHCI_USE_ADMA;
 			host->adma_table = NULL;
 			host->align_buffer = NULL;
-		} else if (host->adma_addr & host->align_mask) {
+		} else if (host->adma_addr & (SDHCI_ADMA2_DESC_ALIGN - 1)) {
 			pr_warn("%s: unable to allocate aligned ADMA descriptor\n",
 				mmc_hostname(mmc));
 			host->flags &= ~SDHCI_USE_ADMA;
@@ -3031,8 +3011,8 @@
 	if (host->max_clk == 0 || host->quirks &
 			SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN) {
 		if (!host->ops->get_max_clock) {
-			pr_err("%s: Hardware doesn't specify base clock "
-			       "frequency.\n", mmc_hostname(mmc));
+			pr_err("%s: Hardware doesn't specify base clock frequency.\n",
+			       mmc_hostname(mmc));
 			return -ENODEV;
 		}
 		host->max_clk = host->ops->get_max_clock(host);
@@ -3294,8 +3274,8 @@
 		mmc->ocr_avail_mmc &= host->ocr_avail_mmc;
 
 	if (mmc->ocr_avail == 0) {
-		pr_err("%s: Hardware doesn't report any "
-			"support voltages.\n", mmc_hostname(mmc));
+		pr_err("%s: Hardware doesn't report any support voltages.\n",
+		       mmc_hostname(mmc));
 		return -ENODEV;
 	}
 
diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h
index 9d4aa31..7654ae5 100644
--- a/drivers/mmc/host/sdhci.h
+++ b/drivers/mmc/host/sdhci.h
@@ -272,22 +272,27 @@
 /* ADMA2 32-bit DMA descriptor size */
 #define SDHCI_ADMA2_32_DESC_SZ	8
 
-/* ADMA2 32-bit DMA alignment */
-#define SDHCI_ADMA2_32_ALIGN	4
-
 /* ADMA2 32-bit descriptor */
 struct sdhci_adma2_32_desc {
 	__le16	cmd;
 	__le16	len;
 	__le32	addr;
-}  __packed __aligned(SDHCI_ADMA2_32_ALIGN);
+}  __packed __aligned(4);
+
+/* ADMA2 data alignment */
+#define SDHCI_ADMA2_ALIGN	4
+#define SDHCI_ADMA2_MASK	(SDHCI_ADMA2_ALIGN - 1)
+
+/*
+ * ADMA2 descriptor alignment.  Some controllers (e.g. Intel) require 8 byte
+ * alignment for the descriptor table even in 32-bit DMA mode.  Memory
+ * allocation is at least 8 byte aligned anyway, so just stipulate 8 always.
+ */
+#define SDHCI_ADMA2_DESC_ALIGN	8
 
 /* ADMA2 64-bit DMA descriptor size */
 #define SDHCI_ADMA2_64_DESC_SZ	12
 
-/* ADMA2 64-bit DMA alignment */
-#define SDHCI_ADMA2_64_ALIGN	8
-
 /*
  * ADMA2 64-bit descriptor. Note 12-byte descriptor can't always be 8-byte
  * aligned.
@@ -482,8 +487,6 @@
 	dma_addr_t align_addr;	/* Mapped bounce buffer */
 
 	unsigned int desc_sz;	/* ADMA descriptor size */
-	unsigned int align_sz;	/* ADMA alignment */
-	unsigned int align_mask;	/* ADMA alignment mask */
 
 	struct tasklet_struct finish_tasklet;	/* Tasklet structures */
 
diff --git a/drivers/mmc/host/sh_mmcif.c b/drivers/mmc/host/sh_mmcif.c
index ad9ffea7..1ca8a13 100644
--- a/drivers/mmc/host/sh_mmcif.c
+++ b/drivers/mmc/host/sh_mmcif.c
@@ -397,38 +397,26 @@
 }
 
 static struct dma_chan *
-sh_mmcif_request_dma_one(struct sh_mmcif_host *host,
-			 struct sh_mmcif_plat_data *pdata,
-			 enum dma_transfer_direction direction)
+sh_mmcif_request_dma_pdata(struct sh_mmcif_host *host, uintptr_t slave_id)
 {
-	struct dma_slave_config cfg = { 0, };
-	struct dma_chan *chan;
-	void *slave_data = NULL;
-	struct resource *res;
-	struct device *dev = sh_mmcif_host_to_dev(host);
 	dma_cap_mask_t mask;
-	int ret;
 
 	dma_cap_zero(mask);
 	dma_cap_set(DMA_SLAVE, mask);
-
-	if (pdata)
-		slave_data = direction == DMA_MEM_TO_DEV ?
-			(void *)pdata->slave_id_tx :
-			(void *)pdata->slave_id_rx;
-
-	chan = dma_request_slave_channel_compat(mask, shdma_chan_filter,
-				slave_data, dev,
-				direction == DMA_MEM_TO_DEV ? "tx" : "rx");
-
-	dev_dbg(dev, "%s: %s: got channel %p\n", __func__,
-		direction == DMA_MEM_TO_DEV ? "TX" : "RX", chan);
-
-	if (!chan)
+	if (slave_id <= 0)
 		return NULL;
 
-	res = platform_get_resource(host->pd, IORESOURCE_MEM, 0);
+	return dma_request_channel(mask, shdma_chan_filter, (void *)slave_id);
+}
 
+static int sh_mmcif_dma_slave_config(struct sh_mmcif_host *host,
+				     struct dma_chan *chan,
+				     enum dma_transfer_direction direction)
+{
+	struct resource *res;
+	struct dma_slave_config cfg = { 0, };
+
+	res = platform_get_resource(host->pd, IORESOURCE_MEM, 0);
 	cfg.direction = direction;
 
 	if (direction == DMA_DEV_TO_MEM) {
@@ -439,38 +427,42 @@
 		cfg.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
 	}
 
-	ret = dmaengine_slave_config(chan, &cfg);
-	if (ret < 0) {
-		dma_release_channel(chan);
-		return NULL;
-	}
-
-	return chan;
+	return dmaengine_slave_config(chan, &cfg);
 }
 
-static void sh_mmcif_request_dma(struct sh_mmcif_host *host,
-				 struct sh_mmcif_plat_data *pdata)
+static void sh_mmcif_request_dma(struct sh_mmcif_host *host)
 {
 	struct device *dev = sh_mmcif_host_to_dev(host);
 	host->dma_active = false;
 
-	if (pdata) {
-		if (pdata->slave_id_tx <= 0 || pdata->slave_id_rx <= 0)
-			return;
-	} else if (!dev->of_node) {
-		return;
-	}
-
 	/* We can only either use DMA for both Tx and Rx or not use it at all */
-	host->chan_tx = sh_mmcif_request_dma_one(host, pdata, DMA_MEM_TO_DEV);
-	if (!host->chan_tx)
-		return;
+	if (IS_ENABLED(CONFIG_SUPERH) && dev->platform_data) {
+		struct sh_mmcif_plat_data *pdata = dev->platform_data;
 
-	host->chan_rx = sh_mmcif_request_dma_one(host, pdata, DMA_DEV_TO_MEM);
-	if (!host->chan_rx) {
-		dma_release_channel(host->chan_tx);
-		host->chan_tx = NULL;
+		host->chan_tx = sh_mmcif_request_dma_pdata(host,
+							pdata->slave_id_tx);
+		host->chan_rx = sh_mmcif_request_dma_pdata(host,
+							pdata->slave_id_rx);
+	} else {
+		host->chan_tx = dma_request_slave_channel(dev, "tx");
+		host->chan_tx = dma_request_slave_channel(dev, "rx");
 	}
+	dev_dbg(dev, "%s: got channel TX %p RX %p\n", __func__, host->chan_tx,
+		host->chan_rx);
+
+	if (!host->chan_tx || !host->chan_rx ||
+	    sh_mmcif_dma_slave_config(host, host->chan_tx, DMA_MEM_TO_DEV) ||
+	    sh_mmcif_dma_slave_config(host, host->chan_rx, DMA_DEV_TO_MEM))
+		goto error;
+
+	return;
+
+error:
+	if (host->chan_tx)
+		dma_release_channel(host->chan_tx);
+	if (host->chan_rx)
+		dma_release_channel(host->chan_rx);
+	host->chan_tx = host->chan_rx = NULL;
 }
 
 static void sh_mmcif_release_dma(struct sh_mmcif_host *host)
@@ -1102,7 +1094,7 @@
 	if (ios->power_mode == MMC_POWER_UP) {
 		if (!host->card_present) {
 			/* See if we also get DMA */
-			sh_mmcif_request_dma(host, dev->platform_data);
+			sh_mmcif_request_dma(host);
 			host->card_present = true;
 		}
 		sh_mmcif_set_power(host, ios);
diff --git a/drivers/mmc/host/usdhi6rol0.c b/drivers/mmc/host/usdhi6rol0.c
index 4498e92..b47122d 100644
--- a/drivers/mmc/host/usdhi6rol0.c
+++ b/drivers/mmc/host/usdhi6rol0.c
@@ -1634,7 +1634,7 @@
 	struct usdhi6_host *host = container_of(d, struct usdhi6_host, timeout_work);
 	struct mmc_request *mrq = host->mrq;
 	struct mmc_data *data = mrq ? mrq->data : NULL;
-	struct scatterlist *sg = host->sg ?: data->sg;
+	struct scatterlist *sg;
 
 	dev_warn(mmc_dev(host->mmc),
 		 "%s timeout wait %u CMD%d: IRQ 0x%08x:0x%08x, last IRQ 0x%08x\n",
@@ -1666,6 +1666,7 @@
 	case USDHI6_WAIT_FOR_MWRITE:
 	case USDHI6_WAIT_FOR_READ:
 	case USDHI6_WAIT_FOR_WRITE:
+		sg = host->sg ?: data->sg;
 		dev_dbg(mmc_dev(host->mmc),
 			"%c: page #%u @ +0x%zx %ux%u in SG%u. Current SG %u bytes @ %u\n",
 			data->flags & MMC_DATA_READ ? 'R' : 'W', host->page_idx,
diff --git a/drivers/mtd/maps/pcmciamtd.c b/drivers/mtd/maps/pcmciamtd.c
index 3dad211..70bb403 100644
--- a/drivers/mtd/maps/pcmciamtd.c
+++ b/drivers/mtd/maps/pcmciamtd.c
@@ -30,7 +30,7 @@
 
 struct pcmciamtd_dev {
 	struct pcmcia_device	*p_dev;
-	caddr_t		win_base;	/* ioremapped address of PCMCIA window */
+	void __iomem	*win_base;	/* ioremapped address of PCMCIA window */
 	unsigned int	win_size;	/* size of window */
 	unsigned int	offset;		/* offset into card the window currently points at */
 	struct map_info	pcmcia_map;
@@ -80,7 +80,7 @@
 /* read/write{8,16} copy_{from,to} routines with window remapping
  * to access whole card
  */
-static caddr_t remap_window(struct map_info *map, unsigned long to)
+static void __iomem *remap_window(struct map_info *map, unsigned long to)
 {
 	struct pcmciamtd_dev *dev = (struct pcmciamtd_dev *)map->map_priv_1;
 	struct resource *win = (struct resource *) map->map_priv_2;
@@ -107,7 +107,7 @@
 
 static map_word pcmcia_read8_remap(struct map_info *map, unsigned long ofs)
 {
-	caddr_t addr;
+	void __iomem *addr;
 	map_word d = {{0}};
 
 	addr = remap_window(map, ofs);
@@ -122,7 +122,7 @@
 
 static map_word pcmcia_read16_remap(struct map_info *map, unsigned long ofs)
 {
-	caddr_t addr;
+	void __iomem *addr;
 	map_word d = {{0}};
 
 	addr = remap_window(map, ofs);
@@ -143,7 +143,7 @@
 	pr_debug("to = %p from = %lu len = %zd\n", to, from, len);
 	while(len) {
 		int toread = win_size - (from & (win_size-1));
-		caddr_t addr;
+		void __iomem *addr;
 
 		if(toread > len)
 			toread = len;
@@ -163,7 +163,7 @@
 
 static void pcmcia_write8_remap(struct map_info *map, map_word d, unsigned long adr)
 {
-	caddr_t addr = remap_window(map, adr);
+	void __iomem *addr = remap_window(map, adr);
 
 	if(!addr)
 		return;
@@ -175,7 +175,7 @@
 
 static void pcmcia_write16_remap(struct map_info *map, map_word d, unsigned long adr)
 {
-	caddr_t addr = remap_window(map, adr);
+	void __iomem *addr = remap_window(map, adr);
 	if(!addr)
 		return;
 
@@ -192,7 +192,7 @@
 	pr_debug("to = %lu from = %p len = %zd\n", to, from, len);
 	while(len) {
 		int towrite = win_size - (to & (win_size-1));
-		caddr_t addr;
+		void __iomem *addr;
 
 		if(towrite > len)
 			towrite = len;
@@ -216,7 +216,7 @@
 
 static map_word pcmcia_read8(struct map_info *map, unsigned long ofs)
 {
-	caddr_t win_base = (caddr_t)map->map_priv_2;
+	void __iomem *win_base = (void __iomem *)map->map_priv_2;
 	map_word d = {{0}};
 
 	if(DEV_REMOVED(map))
@@ -231,7 +231,7 @@
 
 static map_word pcmcia_read16(struct map_info *map, unsigned long ofs)
 {
-	caddr_t win_base = (caddr_t)map->map_priv_2;
+	void __iomem *win_base = (void __iomem *)map->map_priv_2;
 	map_word d = {{0}};
 
 	if(DEV_REMOVED(map))
@@ -246,7 +246,7 @@
 
 static void pcmcia_copy_from(struct map_info *map, void *to, unsigned long from, ssize_t len)
 {
-	caddr_t win_base = (caddr_t)map->map_priv_2;
+	void __iomem *win_base = (void __iomem *)map->map_priv_2;
 
 	if(DEV_REMOVED(map))
 		return;
@@ -258,7 +258,7 @@
 
 static void pcmcia_write8(struct map_info *map, map_word d, unsigned long adr)
 {
-	caddr_t win_base = (caddr_t)map->map_priv_2;
+	void __iomem *win_base = (void __iomem *)map->map_priv_2;
 
 	if(DEV_REMOVED(map))
 		return;
@@ -271,7 +271,7 @@
 
 static void pcmcia_write16(struct map_info *map, map_word d, unsigned long adr)
 {
-	caddr_t win_base = (caddr_t)map->map_priv_2;
+	void __iomem *win_base = (void __iomem *)map->map_priv_2;
 
 	if(DEV_REMOVED(map))
 		return;
@@ -284,7 +284,7 @@
 
 static void pcmcia_copy_to(struct map_info *map, unsigned long to, const void *from, ssize_t len)
 {
-	caddr_t win_base = (caddr_t)map->map_priv_2;
+	void __iomem *win_base = (void __iomem *)map->map_priv_2;
 
 	if(DEV_REMOVED(map))
 		return;
diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
index 95c13b2f..ffa2884 100644
--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -426,15 +426,6 @@
 	mtd->erasesize_mask = (1 << mtd->erasesize_shift) - 1;
 	mtd->writesize_mask = (1 << mtd->writesize_shift) - 1;
 
-	if (mtd->dev.parent) {
-		if (!mtd->owner && mtd->dev.parent->driver)
-			mtd->owner = mtd->dev.parent->driver->owner;
-		if (!mtd->name)
-			mtd->name = dev_name(mtd->dev.parent);
-	} else {
-		pr_debug("mtd device won't show a device symlink in sysfs\n");
-	}
-
 	/* Some chips always power up locked. Unlock them now */
 	if ((mtd->flags & MTD_WRITEABLE) && (mtd->flags & MTD_POWERUP_LOCK)) {
 		error = mtd_unlock(mtd, 0, mtd->size);
@@ -549,6 +540,21 @@
 	return 0;
 }
 
+/*
+ * Set a few defaults based on the parent devices, if not provided by the
+ * driver
+ */
+static void mtd_set_dev_defaults(struct mtd_info *mtd)
+{
+	if (mtd->dev.parent) {
+		if (!mtd->owner && mtd->dev.parent->driver)
+			mtd->owner = mtd->dev.parent->driver->owner;
+		if (!mtd->name)
+			mtd->name = dev_name(mtd->dev.parent);
+	} else {
+		pr_debug("mtd device won't show a device symlink in sysfs\n");
+	}
+}
 
 /**
  * mtd_device_parse_register - parse partitions and register an MTD device.
@@ -587,6 +593,8 @@
 	int ret;
 	struct mtd_partition *real_parts = NULL;
 
+	mtd_set_dev_defaults(mtd);
+
 	ret = parse_mtd_partitions(mtd, types, &real_parts, parser_data);
 	if (ret <= 0 && nr_parts && parts) {
 		real_parts = kmemdup(parts, sizeof(*parts) * nr_parts,
diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c
index 4988390..32477c4 100644
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
@@ -516,8 +516,8 @@
 	status_old = read_sr(nor);
 
 	/* Cannot unlock; would unlock larger region than requested */
-	if (stm_is_locked_sr(nor, status_old, ofs - mtd->erasesize,
-			     mtd->erasesize))
+	if (stm_is_locked_sr(nor, ofs - mtd->erasesize, mtd->erasesize,
+			     status_old))
 		return -EINVAL;
 
 	/*
@@ -1200,8 +1200,7 @@
 
 	if (JEDEC_MFR(info) == SNOR_MFR_ATMEL ||
 	    JEDEC_MFR(info) == SNOR_MFR_INTEL ||
-	    JEDEC_MFR(info) == SNOR_MFR_SST ||
-	    JEDEC_MFR(info) == SNOR_MFR_WINBOND) {
+	    JEDEC_MFR(info) == SNOR_MFR_SST) {
 		write_enable(nor);
 		write_sr(nor, 0);
 	}
@@ -1217,8 +1216,7 @@
 	mtd->_read = spi_nor_read;
 
 	/* NOR protection support for STmicro/Micron chips and similar */
-	if (JEDEC_MFR(info) == SNOR_MFR_MICRON ||
-	    JEDEC_MFR(info) == SNOR_MFR_WINBOND) {
+	if (JEDEC_MFR(info) == SNOR_MFR_MICRON) {
 		nor->flash_lock = stm_lock;
 		nor->flash_unlock = stm_unlock;
 		nor->flash_is_locked = stm_is_locked;
diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c
index 5606563..17ec948 100644
--- a/drivers/mtd/ubi/wl.c
+++ b/drivers/mtd/ubi/wl.c
@@ -628,6 +628,7 @@
 	return __erase_worker(ubi, &wl_wrk);
 }
 
+static int ensure_wear_leveling(struct ubi_device *ubi, int nested);
 /**
  * wear_leveling_worker - wear-leveling worker function.
  * @ubi: UBI device description object
@@ -649,6 +650,7 @@
 #endif
 	struct ubi_wl_entry *e1, *e2;
 	struct ubi_vid_hdr *vid_hdr;
+	int dst_leb_clean = 0;
 
 	kfree(wrk);
 	if (shutdown)
@@ -753,6 +755,7 @@
 
 	err = ubi_io_read_vid_hdr(ubi, e1->pnum, vid_hdr, 0);
 	if (err && err != UBI_IO_BITFLIPS) {
+		dst_leb_clean = 1;
 		if (err == UBI_IO_FF) {
 			/*
 			 * We are trying to move PEB without a VID header. UBI
@@ -798,10 +801,12 @@
 			 * protection queue.
 			 */
 			protect = 1;
+			dst_leb_clean = 1;
 			goto out_not_moved;
 		}
 		if (err == MOVE_RETRY) {
 			scrubbing = 1;
+			dst_leb_clean = 1;
 			goto out_not_moved;
 		}
 		if (err == MOVE_TARGET_BITFLIPS || err == MOVE_TARGET_WR_ERR ||
@@ -827,6 +832,7 @@
 					ubi->erroneous_peb_count);
 				goto out_error;
 			}
+			dst_leb_clean = 1;
 			erroneous = 1;
 			goto out_not_moved;
 		}
@@ -897,15 +903,24 @@
 		wl_tree_add(e1, &ubi->scrub);
 	else
 		wl_tree_add(e1, &ubi->used);
+	if (dst_leb_clean) {
+		wl_tree_add(e2, &ubi->free);
+		ubi->free_count++;
+	}
+
 	ubi_assert(!ubi->move_to_put);
 	ubi->move_from = ubi->move_to = NULL;
 	ubi->wl_scheduled = 0;
 	spin_unlock(&ubi->wl_lock);
 
 	ubi_free_vid_hdr(ubi, vid_hdr);
-	err = do_sync_erase(ubi, e2, vol_id, lnum, torture);
-	if (err)
-		goto out_ro;
+	if (dst_leb_clean) {
+		ensure_wear_leveling(ubi, 1);
+	} else {
+		err = do_sync_erase(ubi, e2, vol_id, lnum, torture);
+		if (err)
+			goto out_ro;
+	}
 
 	mutex_unlock(&ubi->move_mutex);
 	return 0;
diff --git a/drivers/net/wireless/ath/wil6210/debugfs.c b/drivers/net/wireless/ath/wil6210/debugfs.c
index 97bc186..a1d10b8 100644
--- a/drivers/net/wireless/ath/wil6210/debugfs.c
+++ b/drivers/net/wireless/ath/wil6210/debugfs.c
@@ -580,16 +580,10 @@
 	long channel;
 	bool on;
 
-	char *kbuf = kmalloc(len + 1, GFP_KERNEL);
+	char *kbuf = memdup_user_nul(buf, len);
 
-	if (!kbuf)
-		return -ENOMEM;
-	if (copy_from_user(kbuf, buf, len)) {
-		kfree(kbuf);
-		return -EIO;
-	}
-
-	kbuf[len] = '\0';
+	if (IS_ERR(kbuf))
+		return PTR_ERR(kbuf);
 	rc = kstrtol(kbuf, 0, &channel);
 	kfree(kbuf);
 	if (rc)
diff --git a/drivers/net/wireless/marvell/libertas/debugfs.c b/drivers/net/wireless/marvell/libertas/debugfs.c
index 26cbf1d..faed182 100644
--- a/drivers/net/wireless/marvell/libertas/debugfs.c
+++ b/drivers/net/wireless/marvell/libertas/debugfs.c
@@ -56,19 +56,15 @@
 				loff_t *ppos)
 {
 	struct lbs_private *priv = file->private_data;
-	ssize_t buf_size, ret;
+	ssize_t ret;
 	struct sleep_params sp;
 	int p1, p2, p3, p4, p5, p6;
-	unsigned long addr = get_zeroed_page(GFP_KERNEL);
-	char *buf = (char *)addr;
-	if (!buf)
-		return -ENOMEM;
+	char *buf;
 
-	buf_size = min(count, len - 1);
-	if (copy_from_user(buf, user_buf, buf_size)) {
-		ret = -EFAULT;
-		goto out_unlock;
-	}
+	buf = memdup_user_nul(user_buf, min(count, len - 1));
+	if (IS_ERR(buf))
+		return PTR_ERR(buf);
+
 	ret = sscanf(buf, "%d %d %d %d %d %d", &p1, &p2, &p3, &p4, &p5, &p6);
 	if (ret != 6) {
 		ret = -EINVAL;
@@ -88,7 +84,7 @@
 		ret = -EINVAL;
 
 out_unlock:
-	free_page(addr);
+	kfree(buf);
 	return ret;
 }
 
@@ -125,18 +121,14 @@
 				loff_t *ppos)
 {
 	struct lbs_private *priv = file->private_data;
-	ssize_t buf_size, ret;
+	ssize_t ret;
 	int host_sleep;
-	unsigned long addr = get_zeroed_page(GFP_KERNEL);
-	char *buf = (char *)addr;
-	if (!buf)
-		return -ENOMEM;
+	char *buf;
 
-	buf_size = min(count, len - 1);
-	if (copy_from_user(buf, user_buf, buf_size)) {
-		ret = -EFAULT;
-		goto out_unlock;
-	}
+	buf = memdup_user_nul(user_buf, min(count, len - 1));
+	if (IS_ERR(buf))
+		return PTR_ERR(buf);
+
 	ret = sscanf(buf, "%d", &host_sleep);
 	if (ret != 1) {
 		ret = -EINVAL;
@@ -162,7 +154,7 @@
 		ret = count;
 
 out_unlock:
-	free_page(addr);
+	kfree(buf);
 	return ret;
 }
 
@@ -281,21 +273,15 @@
 	struct cmd_ds_802_11_subscribe_event *events;
 	struct mrvl_ie_thresholds *tlv;
 	struct lbs_private *priv = file->private_data;
-	ssize_t buf_size;
 	int value, freq, new_mask;
 	uint16_t curr_mask;
 	char *buf;
 	int ret;
 
-	buf = (char *)get_zeroed_page(GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
+	buf = memdup_user_nul(userbuf, min(count, len - 1));
+	if (IS_ERR(buf))
+		return PTR_ERR(buf);
 
-	buf_size = min(count, len - 1);
-	if (copy_from_user(buf, userbuf, buf_size)) {
-		ret = -EFAULT;
-		goto out_page;
-	}
 	ret = sscanf(buf, "%d %d %d", &value, &freq, &new_mask);
 	if (ret != 3) {
 		ret = -EINVAL;
@@ -343,7 +329,7 @@
  out_events:
 	kfree(events);
  out_page:
-	free_page((unsigned long)buf);
+	kfree(buf);
 	return ret;
 }
 
@@ -472,22 +458,15 @@
 				    size_t count, loff_t *ppos)
 {
 	struct lbs_private *priv = file->private_data;
-	ssize_t res, buf_size;
-	unsigned long addr = get_zeroed_page(GFP_KERNEL);
-	char *buf = (char *)addr;
-	if (!buf)
-		return -ENOMEM;
+	char *buf;
 
-	buf_size = min(count, len - 1);
-	if (copy_from_user(buf, userbuf, buf_size)) {
-		res = -EFAULT;
-		goto out_unlock;
-	}
+	buf = memdup_user_nul(userbuf, min(count, len - 1));
+	if (IS_ERR(buf))
+		return PTR_ERR(buf);
+
 	priv->mac_offset = simple_strtoul(buf, NULL, 16);
-	res = count;
-out_unlock:
-	free_page(addr);
-	return res;
+	kfree(buf);
+	return count;
 }
 
 static ssize_t lbs_wrmac_write(struct file *file,
@@ -496,18 +475,14 @@
 {
 
 	struct lbs_private *priv = file->private_data;
-	ssize_t res, buf_size;
+	ssize_t res;
 	u32 offset, value;
-	unsigned long addr = get_zeroed_page(GFP_KERNEL);
-	char *buf = (char *)addr;
-	if (!buf)
-		return -ENOMEM;
+	char *buf;
 
-	buf_size = min(count, len - 1);
-	if (copy_from_user(buf, userbuf, buf_size)) {
-		res = -EFAULT;
-		goto out_unlock;
-	}
+	buf = memdup_user_nul(userbuf, min(count, len - 1));
+	if (IS_ERR(buf))
+		return PTR_ERR(buf);
+
 	res = sscanf(buf, "%x %x", &offset, &value);
 	if (res != 2) {
 		res = -EFAULT;
@@ -520,7 +495,7 @@
 	if (!res)
 		res = count;
 out_unlock:
-	free_page(addr);
+	kfree(buf);
 	return res;
 }
 
@@ -554,22 +529,16 @@
 				    size_t count, loff_t *ppos)
 {
 	struct lbs_private *priv = file->private_data;
-	ssize_t res, buf_size;
-	unsigned long addr = get_zeroed_page(GFP_KERNEL);
-	char *buf = (char *)addr;
-	if (!buf)
-		return -ENOMEM;
+	char *buf;
 
-	buf_size = min(count, len - 1);
-	if (copy_from_user(buf, userbuf, buf_size)) {
-		res = -EFAULT;
-		goto out_unlock;
-	}
+	buf = memdup_user_nul(userbuf, min(count, len - 1));
+	if (IS_ERR(buf))
+		return PTR_ERR(buf);
+
 	priv->bbp_offset = simple_strtoul(buf, NULL, 16);
-	res = count;
-out_unlock:
-	free_page(addr);
-	return res;
+	kfree(buf);
+
+	return count;
 }
 
 static ssize_t lbs_wrbbp_write(struct file *file,
@@ -578,18 +547,14 @@
 {
 
 	struct lbs_private *priv = file->private_data;
-	ssize_t res, buf_size;
+	ssize_t res;
 	u32 offset, value;
-	unsigned long addr = get_zeroed_page(GFP_KERNEL);
-	char *buf = (char *)addr;
-	if (!buf)
-		return -ENOMEM;
+	char *buf;
 
-	buf_size = min(count, len - 1);
-	if (copy_from_user(buf, userbuf, buf_size)) {
-		res = -EFAULT;
-		goto out_unlock;
-	}
+	buf = memdup_user_nul(userbuf, min(count, len - 1));
+	if (IS_ERR(buf))
+		return PTR_ERR(buf);
+
 	res = sscanf(buf, "%x %x", &offset, &value);
 	if (res != 2) {
 		res = -EFAULT;
@@ -602,7 +567,7 @@
 	if (!res)
 		res = count;
 out_unlock:
-	free_page(addr);
+	kfree(buf);
 	return res;
 }
 
@@ -636,22 +601,15 @@
 				    size_t count, loff_t *ppos)
 {
 	struct lbs_private *priv = file->private_data;
-	ssize_t res, buf_size;
-	unsigned long addr = get_zeroed_page(GFP_KERNEL);
-	char *buf = (char *)addr;
-	if (!buf)
-		return -ENOMEM;
+	char *buf;
 
-	buf_size = min(count, len - 1);
-	if (copy_from_user(buf, userbuf, buf_size)) {
-		res = -EFAULT;
-		goto out_unlock;
-	}
+	buf = memdup_user_nul(userbuf, min(count, len - 1));
+	if (IS_ERR(buf))
+		return PTR_ERR(buf);
+
 	priv->rf_offset = simple_strtoul(buf, NULL, 16);
-	res = count;
-out_unlock:
-	free_page(addr);
-	return res;
+	kfree(buf);
+	return count;
 }
 
 static ssize_t lbs_wrrf_write(struct file *file,
@@ -660,18 +618,14 @@
 {
 
 	struct lbs_private *priv = file->private_data;
-	ssize_t res, buf_size;
+	ssize_t res;
 	u32 offset, value;
-	unsigned long addr = get_zeroed_page(GFP_KERNEL);
-	char *buf = (char *)addr;
-	if (!buf)
-		return -ENOMEM;
+	char *buf;
 
-	buf_size = min(count, len - 1);
-	if (copy_from_user(buf, userbuf, buf_size)) {
-		res = -EFAULT;
-		goto out_unlock;
-	}
+	buf = memdup_user_nul(userbuf, min(count, len - 1));
+	if (IS_ERR(buf))
+		return PTR_ERR(buf);
+
 	res = sscanf(buf, "%x %x", &offset, &value);
 	if (res != 2) {
 		res = -EFAULT;
@@ -684,7 +638,7 @@
 	if (!res)
 		res = count;
 out_unlock:
-	free_page(addr);
+	kfree(buf);
 	return res;
 }
 
@@ -915,16 +869,9 @@
 	if (cnt == 0)
 		return 0;
 
-	pdata = kmalloc(cnt + 1, GFP_KERNEL);
-	if (pdata == NULL)
-		return 0;
-
-	if (copy_from_user(pdata, buf, cnt)) {
-		lbs_deb_debugfs("Copy from user failed\n");
-		kfree(pdata);
-		return 0;
-	}
-	pdata[cnt] = '\0';
+	pdata = memdup_user_nul(buf, cnt);
+	if (IS_ERR(pdata))
+		return PTR_ERR(pdata);
 
 	p0 = pdata;
 	for (i = 0; i < num_of_items; i++) {
diff --git a/drivers/net/wireless/marvell/mwifiex/debugfs.c b/drivers/net/wireless/marvell/mwifiex/debugfs.c
index 5e55629..0b9c580 100644
--- a/drivers/net/wireless/marvell/mwifiex/debugfs.c
+++ b/drivers/net/wireless/marvell/mwifiex/debugfs.c
@@ -447,20 +447,13 @@
 mwifiex_regrdwr_write(struct file *file,
 		      const char __user *ubuf, size_t count, loff_t *ppos)
 {
-	unsigned long addr = get_zeroed_page(GFP_KERNEL);
-	char *buf = (char *) addr;
-	size_t buf_size = min_t(size_t, count, PAGE_SIZE - 1);
+	char *buf;
 	int ret;
 	u32 reg_type = 0, reg_offset = 0, reg_value = UINT_MAX;
 
-	if (!buf)
-		return -ENOMEM;
-
-
-	if (copy_from_user(buf, ubuf, buf_size)) {
-		ret = -EFAULT;
-		goto done;
-	}
+	buf = memdup_user_nul(ubuf, min(count, (size_t)(PAGE_SIZE - 1)));
+	if (IS_ERR(buf))
+		return PTR_ERR(buf);
 
 	sscanf(buf, "%u %x %x", &reg_type, &reg_offset, &reg_value);
 
@@ -474,7 +467,7 @@
 		ret = count;
 	}
 done:
-	free_page(addr);
+	kfree(buf);
 	return ret;
 }
 
@@ -572,17 +565,11 @@
 	int ret;
 	unsigned long debug_mask;
 	struct mwifiex_private *priv = (void *)file->private_data;
-	unsigned long addr = get_zeroed_page(GFP_KERNEL);
-	char *buf = (void *)addr;
-	size_t buf_size = min(count, (size_t)(PAGE_SIZE - 1));
+	char *buf;
 
-	if (!buf)
-		return -ENOMEM;
-
-	if (copy_from_user(buf, ubuf, buf_size)) {
-		ret = -EFAULT;
-		goto done;
-	}
+	buf = memdup_user_nul(ubuf, min(count, (size_t)(PAGE_SIZE - 1)));
+	if (IS_ERR(buf))
+		return PTR_ERR(buf);
 
 	if (kstrtoul(buf, 0, &debug_mask)) {
 		ret = -EINVAL;
@@ -592,7 +579,7 @@
 	priv->adapter->debug_mask = debug_mask;
 	ret = count;
 done:
-	free_page(addr);
+	kfree(buf);
 	return ret;
 }
 
@@ -609,17 +596,11 @@
 	struct mwifiex_ds_mem_rw mem_rw;
 	u16 cmd_action;
 	struct mwifiex_private *priv = (void *)file->private_data;
-	unsigned long addr = get_zeroed_page(GFP_KERNEL);
-	char *buf = (void *)addr;
-	size_t buf_size = min(count, (size_t)(PAGE_SIZE - 1));
+	char *buf;
 
-	if (!buf)
-		return -ENOMEM;
-
-	if (copy_from_user(buf, ubuf, buf_size)) {
-		ret = -EFAULT;
-		goto done;
-	}
+	buf = memdup_user_nul(ubuf, min(count, (size_t)(PAGE_SIZE - 1)));
+	if (IS_ERR(buf))
+		return PTR_ERR(buf);
 
 	ret = sscanf(buf, "%c %x %x", &cmd, &mem_rw.addr, &mem_rw.value);
 	if (ret != 3) {
@@ -645,7 +626,7 @@
 		ret = count;
 
 done:
-	free_page(addr);
+	kfree(buf);
 	return ret;
 }
 
@@ -686,20 +667,13 @@
 mwifiex_rdeeprom_write(struct file *file,
 		       const char __user *ubuf, size_t count, loff_t *ppos)
 {
-	unsigned long addr = get_zeroed_page(GFP_KERNEL);
-	char *buf = (char *) addr;
-	size_t buf_size = min_t(size_t, count, PAGE_SIZE - 1);
+	char *buf;
 	int ret = 0;
 	int offset = -1, bytes = -1;
 
-	if (!buf)
-		return -ENOMEM;
-
-
-	if (copy_from_user(buf, ubuf, buf_size)) {
-		ret = -EFAULT;
-		goto done;
-	}
+	buf = memdup_user_nul(ubuf, min(count, (size_t)(PAGE_SIZE - 1)));
+	if (IS_ERR(buf))
+		return PTR_ERR(buf);
 
 	sscanf(buf, "%d %d", &offset, &bytes);
 
@@ -712,7 +686,7 @@
 		ret = count;
 	}
 done:
-	free_page(addr);
+	kfree(buf);
 	return ret;
 }
 
@@ -771,21 +745,15 @@
 		    size_t count, loff_t *ppos)
 {
 	struct mwifiex_private *priv = (void *)file->private_data;
-	unsigned long addr = get_zeroed_page(GFP_KERNEL);
-	char *buf = (char *)addr;
-	size_t buf_size = min_t(size_t, count, PAGE_SIZE - 1);
+	char *buf;
 	int ret, arg_num;
 	struct mwifiex_ds_hs_cfg hscfg;
 	int conditions = HS_CFG_COND_DEF;
 	u32 gpio = HS_CFG_GPIO_DEF, gap = HS_CFG_GAP_DEF;
 
-	if (!buf)
-		return -ENOMEM;
-
-	if (copy_from_user(buf, ubuf, buf_size)) {
-		ret = -EFAULT;
-		goto done;
-	}
+	buf = memdup_user_nul(ubuf, min(count, (size_t)(PAGE_SIZE - 1)));
+	if (IS_ERR(buf))
+		return PTR_ERR(buf);
 
 	arg_num = sscanf(buf, "%d %x %x", &conditions, &gpio, &gap);
 
@@ -823,7 +791,7 @@
 	priv->adapter->hs_enabling = false;
 	ret = count;
 done:
-	free_page(addr);
+	kfree(buf);
 	return ret;
 }
 
diff --git a/drivers/net/wireless/ti/wlcore/debugfs.c b/drivers/net/wireless/ti/wlcore/debugfs.c
index 8367f9e..7f672f6 100644
--- a/drivers/net/wireless/ti/wlcore/debugfs.c
+++ b/drivers/net/wireless/ti/wlcore/debugfs.c
@@ -1205,26 +1205,11 @@
 
 static loff_t dev_mem_seek(struct file *file, loff_t offset, int orig)
 {
-	loff_t ret;
-
 	/* only requests of dword-aligned size and offset are supported */
 	if (offset % 4)
 		return -EINVAL;
 
-	switch (orig) {
-	case SEEK_SET:
-		file->f_pos = offset;
-		ret = file->f_pos;
-		break;
-	case SEEK_CUR:
-		file->f_pos += offset;
-		ret = file->f_pos;
-		break;
-	default:
-		ret = -EINVAL;
-	}
-
-	return ret;
+	return no_seek_end_llseek(file, offset, orig);
 }
 
 static const struct file_operations dev_mem_ops = {
diff --git a/drivers/pci/host/Kconfig b/drivers/pci/host/Kconfig
index f131ba9..c0ad9aa 100644
--- a/drivers/pci/host/Kconfig
+++ b/drivers/pci/host/Kconfig
@@ -5,6 +5,7 @@
 	bool "TI DRA7xx PCIe controller"
 	select PCIE_DW
 	depends on OF && HAS_IOMEM && TI_PIPE3
+	depends on BROKEN
 	help
 	 Enables support for the PCIe controller in the DRA7xx SoC.  There
 	 are two instances of PCIe controller in DRA7xx.  This controller can
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 7eaa4c8..7a0df3f 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -257,6 +257,7 @@
 {
 	msi_set_mask_bit(data, 1);
 }
+EXPORT_SYMBOL_GPL(pci_msi_mask_irq);
 
 /**
  * pci_msi_unmask_irq - Generic irq chip callback to unmask PCI/MSI interrupts
@@ -266,6 +267,7 @@
 {
 	msi_set_mask_bit(data, 0);
 }
+EXPORT_SYMBOL_GPL(pci_msi_unmask_irq);
 
 void default_restore_msi_irqs(struct pci_dev *dev)
 {
@@ -1126,6 +1128,7 @@
 {
 	return to_pci_dev(desc->dev);
 }
+EXPORT_SYMBOL(msi_desc_to_pci_dev);
 
 void *msi_desc_to_pci_sysdata(struct msi_desc *desc)
 {
@@ -1285,6 +1288,7 @@
 	domain->bus_token = DOMAIN_BUS_PCI_MSI;
 	return domain;
 }
+EXPORT_SYMBOL_GPL(pci_msi_create_irq_domain);
 
 /**
  * pci_msi_domain_alloc_irqs - Allocate interrupts for @dev in @domain
diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c
index a32ba75..d3f32d6 100644
--- a/drivers/pci/pci-acpi.c
+++ b/drivers/pci/pci-acpi.c
@@ -9,7 +9,9 @@
 
 #include <linux/delay.h>
 #include <linux/init.h>
+#include <linux/irqdomain.h>
 #include <linux/pci.h>
+#include <linux/msi.h>
 #include <linux/pci_hotplug.h>
 #include <linux/module.h>
 #include <linux/pci-aspm.h>
@@ -689,6 +691,46 @@
 	.cleanup = pci_acpi_cleanup,
 };
 
+
+static struct fwnode_handle *(*pci_msi_get_fwnode_cb)(struct device *dev);
+
+/**
+ * pci_msi_register_fwnode_provider - Register callback to retrieve fwnode
+ * @fn:       Callback matching a device to a fwnode that identifies a PCI
+ *            MSI domain.
+ *
+ * This should be called by irqchip driver, which is the parent of
+ * the MSI domain to provide callback interface to query fwnode.
+ */
+void
+pci_msi_register_fwnode_provider(struct fwnode_handle *(*fn)(struct device *))
+{
+	pci_msi_get_fwnode_cb = fn;
+}
+
+/**
+ * pci_host_bridge_acpi_msi_domain - Retrieve MSI domain of a PCI host bridge
+ * @bus:      The PCI host bridge bus.
+ *
+ * This function uses the callback function registered by
+ * pci_msi_register_fwnode_provider() to retrieve the irq_domain with
+ * type DOMAIN_BUS_PCI_MSI of the specified host bridge bus.
+ * This returns NULL on error or when the domain is not found.
+ */
+struct irq_domain *pci_host_bridge_acpi_msi_domain(struct pci_bus *bus)
+{
+	struct fwnode_handle *fwnode;
+
+	if (!pci_msi_get_fwnode_cb)
+		return NULL;
+
+	fwnode = pci_msi_get_fwnode_cb(&bus->dev);
+	if (!fwnode)
+		return NULL;
+
+	return irq_find_matching_fwnode(fwnode, DOMAIN_BUS_PCI_MSI);
+}
+
 static int __init acpi_pci_init(void)
 {
 	int ret;
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index edb19842..553a029 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -672,6 +672,8 @@
 	 * should be called from here.
 	 */
 	d = pci_host_bridge_of_msi_domain(bus);
+	if (!d)
+		d = pci_host_bridge_acpi_msi_domain(bus);
 
 	return d;
 }
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index be3755c..166637f 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -551,14 +551,6 @@
 	};
 }
 
-int armpmu_register(struct arm_pmu *armpmu, int type)
-{
-	armpmu_init(armpmu);
-	pr_info("enabled with %s PMU driver, %d counters available\n",
-			armpmu->name, armpmu->num_events);
-	return perf_pmu_register(&armpmu->pmu, armpmu->name, type);
-}
-
 /* Set at runtime when we know what CPU type we are. */
 static struct arm_pmu *__oprofile_cpu_pmu;
 
@@ -887,6 +879,8 @@
 		return -ENOMEM;
 	}
 
+	armpmu_init(pmu);
+
 	if (!__oprofile_cpu_pmu)
 		__oprofile_cpu_pmu = pmu;
 
@@ -912,10 +906,13 @@
 	if (ret)
 		goto out_free;
 
-	ret = armpmu_register(pmu, -1);
+	ret = perf_pmu_register(&pmu->pmu, pmu->name, -1);
 	if (ret)
 		goto out_destroy;
 
+	pr_info("enabled with %s PMU driver, %d counters available\n",
+			pmu->name, pmu->num_events);
+
 	return 0;
 
 out_destroy:
diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig
index 312c78b..99a4c10 100644
--- a/drivers/pinctrl/Kconfig
+++ b/drivers/pinctrl/Kconfig
@@ -244,7 +244,7 @@
 	select PINMUX
 	select GENERIC_PINCONF
 	help
-	  This selectes the pinctrl driver for Xilinx Zynq.
+	  This selects the pinctrl driver for Xilinx Zynq.
 
 source "drivers/pinctrl/bcm/Kconfig"
 source "drivers/pinctrl/berlin/Kconfig"
@@ -252,6 +252,7 @@
 source "drivers/pinctrl/intel/Kconfig"
 source "drivers/pinctrl/mvebu/Kconfig"
 source "drivers/pinctrl/nomadik/Kconfig"
+source "drivers/pinctrl/pxa/Kconfig"
 source "drivers/pinctrl/qcom/Kconfig"
 source "drivers/pinctrl/samsung/Kconfig"
 source "drivers/pinctrl/sh-pfc/Kconfig"
diff --git a/drivers/pinctrl/Makefile b/drivers/pinctrl/Makefile
index 738cb49..bf1b5ca 100644
--- a/drivers/pinctrl/Makefile
+++ b/drivers/pinctrl/Makefile
@@ -41,15 +41,16 @@
 obj-$(CONFIG_PINCTRL_ZYNQ)	+= pinctrl-zynq.o
 
 obj-$(CONFIG_ARCH_BCM)		+= bcm/
-obj-$(CONFIG_ARCH_BERLIN)	+= berlin/
+obj-$(CONFIG_PINCTRL_BERLIN)	+= berlin/
 obj-y				+= freescale/
 obj-$(CONFIG_X86)		+= intel/
-obj-$(CONFIG_PLAT_ORION)        += mvebu/
+obj-$(CONFIG_PINCTRL_MVEBU)	+= mvebu/
 obj-y				+= nomadik/
+obj-$(CONFIG_ARCH_PXA)		+= pxa/
 obj-$(CONFIG_ARCH_QCOM)		+= qcom/
 obj-$(CONFIG_PINCTRL_SAMSUNG)	+= samsung/
 obj-$(CONFIG_PINCTRL_SH_PFC)	+= sh-pfc/
-obj-$(CONFIG_PLAT_SPEAR)	+= spear/
+obj-$(CONFIG_PINCTRL_SPEAR)	+= spear/
 obj-$(CONFIG_ARCH_SUNXI)	+= sunxi/
 obj-$(CONFIG_PINCTRL_UNIPHIER)	+= uniphier/
 obj-$(CONFIG_ARCH_VT8500)	+= vt8500/
diff --git a/drivers/pinctrl/bcm/Kconfig b/drivers/pinctrl/bcm/Kconfig
index cd11d4d..2cc7438 100644
--- a/drivers/pinctrl/bcm/Kconfig
+++ b/drivers/pinctrl/bcm/Kconfig
@@ -9,6 +9,7 @@
 	select PINCONF
 	select GENERIC_PINCONF
 	select REGMAP_MMIO
+	default ARCH_BCM_MOBILE
 	help
 	  Say Y here to support Broadcom BCM281xx pinctrl driver, which is used
 	  for the BCM281xx SoC family, including BCM11130, BCM11140, BCM11351,
@@ -20,27 +21,41 @@
 	select PINMUX
 	select PINCONF
 
-config PINCTRL_CYGNUS_GPIO
-	bool "Broadcom Cygnus GPIO (with PINCONF) driver"
-	depends on OF_GPIO && ARCH_BCM_CYGNUS
+config PINCTRL_IPROC_GPIO
+	bool "Broadcom iProc GPIO (with PINCONF) driver"
+	depends on OF_GPIO && (ARCH_BCM_IPROC || COMPILE_TEST)
 	select GPIOLIB_IRQCHIP
 	select PINCONF
 	select GENERIC_PINCONF
-	default ARCH_BCM_CYGNUS
+	default ARCH_BCM_IPROC
 	help
-	  Say yes here to enable the Broadcom Cygnus GPIO driver.
+	  Say yes here to enable the Broadcom iProc GPIO driver.
+
+	  The Broadcom iProc based SoCs- Cygnus, NS2, NSP and Stingray, use
+	  same GPIO Controller IP hence this driver could be used for all.
 
 	  The Broadcom Cygnus SoC has 3 GPIO controllers including the ASIU
 	  GPIO controller (ASIU), the chipCommonG GPIO controller (CCM), and
 	  the always-ON GPIO controller (CRMU/AON). All 3 GPIO controllers are
 	  supported by this driver.
 
-	  All 3 Cygnus GPIO controllers support basic PINCONF functions such
+	  The Broadcom NSP has two GPIO controllers including the ChipcommonA
+	  GPIO, the ChipcommonB GPIO. Later controller is supported by this
+	  driver.
+
+	  The Broadcom NS2 has two GPIO controller including the CRMU GPIO,
+	  the ChipcommonG GPIO. Both controllers are supported by this driver.
+
+	  The Broadcom Stingray GPIO controllers are supported by this driver.
+
+	  All above SoCs GPIO controllers support basic PINCONF functions such
 	  as bias pull up, pull down, and drive strength configurations, when
 	  these pins are muxed to GPIO.
 
-	  Pins from the ASIU GPIO can be individually muxed to GPIO function,
-	  through interaction with the Cygnus IOMUX controller.
+	  It provides the framework where pins from the individual GPIO can be
+	  individually muxed to GPIO function, through interaction with the
+	  SoCs IOMUX controller. This features could be used only on SoCs which
+	  support individual pin muxing.
 
 config PINCTRL_CYGNUS_MUX
 	bool "Broadcom Cygnus IOMUX driver"
@@ -54,3 +69,20 @@
 	  The Broadcom Cygnus IOMUX driver supports group based IOMUX
 	  configuration, with the exception that certain individual pins
 	  can be overrided to GPIO function
+
+config PINCTRL_NSP_GPIO
+	bool "Broadcom NSP GPIO (with PINCONF) driver"
+	depends on OF_GPIO && (ARCH_BCM_NSP || COMPILE_TEST)
+	select GPIOLIB_IRQCHIP
+	select PINCONF
+	select GENERIC_PINCONF
+	default ARCH_BCM_NSP
+	help
+	  Say yes here to enable the Broadcom NSP GPIO driver.
+
+	  The Broadcom Northstar Plus SoC ChipcommonA GPIO controller is
+	  supported by this driver.
+
+	  The ChipcommonA GPIO controller support basic PINCONF functions such
+	  as bias pull up, pull down, and drive strength configurations, when
+	  these pins are muxed to GPIO.
diff --git a/drivers/pinctrl/bcm/Makefile b/drivers/pinctrl/bcm/Makefile
index 2b2f70e..6148367d 100644
--- a/drivers/pinctrl/bcm/Makefile
+++ b/drivers/pinctrl/bcm/Makefile
@@ -2,5 +2,6 @@
 
 obj-$(CONFIG_PINCTRL_BCM281XX)		+= pinctrl-bcm281xx.o
 obj-$(CONFIG_PINCTRL_BCM2835)		+= pinctrl-bcm2835.o
-obj-$(CONFIG_PINCTRL_CYGNUS_GPIO)	+= pinctrl-cygnus-gpio.o
+obj-$(CONFIG_PINCTRL_IPROC_GPIO)	+= pinctrl-iproc-gpio.o
 obj-$(CONFIG_PINCTRL_CYGNUS_MUX)	+= pinctrl-cygnus-mux.o
+obj-$(CONFIG_PINCTRL_NSP_GPIO)		+= pinctrl-nsp-gpio.o
diff --git a/drivers/pinctrl/bcm/pinctrl-bcm2835.c b/drivers/pinctrl/bcm/pinctrl-bcm2835.c
index 2e6ca69..75b0d8c 100644
--- a/drivers/pinctrl/bcm/pinctrl-bcm2835.c
+++ b/drivers/pinctrl/bcm/pinctrl-bcm2835.c
@@ -795,7 +795,7 @@
 	return 0;
 
 out:
-	kfree(maps);
+	bcm2835_pctl_dt_free_map(pctldev, maps, num_pins * maps_per_pin);
 	return err;
 }
 
diff --git a/drivers/pinctrl/bcm/pinctrl-cygnus-gpio.c b/drivers/pinctrl/bcm/pinctrl-cygnus-gpio.c
deleted file mode 100644
index 12a48f4..0000000
--- a/drivers/pinctrl/bcm/pinctrl-cygnus-gpio.c
+++ /dev/null
@@ -1,784 +0,0 @@
-/*
- * Copyright (C) 2014-2015 Broadcom Corporation
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation version 2.
- *
- * This program is distributed "as is" WITHOUT ANY WARRANTY of any
- * kind, whether express or implied; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * This file contains the Broadcom Cygnus GPIO driver that supports 3
- * GPIO controllers on Cygnus including the ASIU GPIO controller, the
- * chipCommonG GPIO controller, and the always-on GPIO controller. Basic
- * PINCONF such as bias pull up/down, and drive strength are also supported
- * in this driver.
- *
- * Pins from the ASIU GPIO can be individually muxed to GPIO function,
- * through the interaction with the Cygnus IOMUX controller
- */
-
-#include <linux/kernel.h>
-#include <linux/slab.h>
-#include <linux/interrupt.h>
-#include <linux/io.h>
-#include <linux/gpio.h>
-#include <linux/ioport.h>
-#include <linux/of_device.h>
-#include <linux/of_irq.h>
-#include <linux/pinctrl/pinctrl.h>
-#include <linux/pinctrl/pinconf.h>
-#include <linux/pinctrl/pinconf-generic.h>
-
-#include "../pinctrl-utils.h"
-
-#define CYGNUS_GPIO_DATA_IN_OFFSET   0x00
-#define CYGNUS_GPIO_DATA_OUT_OFFSET  0x04
-#define CYGNUS_GPIO_OUT_EN_OFFSET    0x08
-#define CYGNUS_GPIO_INT_TYPE_OFFSET  0x0c
-#define CYGNUS_GPIO_INT_DE_OFFSET    0x10
-#define CYGNUS_GPIO_INT_EDGE_OFFSET  0x14
-#define CYGNUS_GPIO_INT_MSK_OFFSET   0x18
-#define CYGNUS_GPIO_INT_STAT_OFFSET  0x1c
-#define CYGNUS_GPIO_INT_MSTAT_OFFSET 0x20
-#define CYGNUS_GPIO_INT_CLR_OFFSET   0x24
-#define CYGNUS_GPIO_PAD_RES_OFFSET   0x34
-#define CYGNUS_GPIO_RES_EN_OFFSET    0x38
-
-/* drive strength control for ASIU GPIO */
-#define CYGNUS_GPIO_ASIU_DRV0_CTRL_OFFSET 0x58
-
-/* drive strength control for CCM/CRMU (AON) GPIO */
-#define CYGNUS_GPIO_DRV0_CTRL_OFFSET  0x00
-
-#define GPIO_BANK_SIZE 0x200
-#define NGPIOS_PER_BANK 32
-#define GPIO_BANK(pin) ((pin) / NGPIOS_PER_BANK)
-
-#define CYGNUS_GPIO_REG(pin, reg) (GPIO_BANK(pin) * GPIO_BANK_SIZE + (reg))
-#define CYGNUS_GPIO_SHIFT(pin) ((pin) % NGPIOS_PER_BANK)
-
-#define GPIO_DRV_STRENGTH_BIT_SHIFT  20
-#define GPIO_DRV_STRENGTH_BITS       3
-#define GPIO_DRV_STRENGTH_BIT_MASK   ((1 << GPIO_DRV_STRENGTH_BITS) - 1)
-
-/*
- * Cygnus GPIO core
- *
- * @dev: pointer to device
- * @base: I/O register base for Cygnus GPIO controller
- * @io_ctrl: I/O register base for certain type of Cygnus GPIO controller that
- * has the PINCONF support implemented outside of the GPIO block
- * @lock: lock to protect access to I/O registers
- * @gc: GPIO chip
- * @num_banks: number of GPIO banks, each bank supports up to 32 GPIOs
- * @pinmux_is_supported: flag to indicate this GPIO controller contains pins
- * that can be individually muxed to GPIO
- * @pctl: pointer to pinctrl_dev
- * @pctldesc: pinctrl descriptor
- */
-struct cygnus_gpio {
-	struct device *dev;
-
-	void __iomem *base;
-	void __iomem *io_ctrl;
-
-	spinlock_t lock;
-
-	struct gpio_chip gc;
-	unsigned num_banks;
-
-	bool pinmux_is_supported;
-
-	struct pinctrl_dev *pctl;
-	struct pinctrl_desc pctldesc;
-};
-
-static inline struct cygnus_gpio *to_cygnus_gpio(struct gpio_chip *gc)
-{
-	return container_of(gc, struct cygnus_gpio, gc);
-}
-
-/*
- * Mapping from PINCONF pins to GPIO pins is 1-to-1
- */
-static inline unsigned cygnus_pin_to_gpio(unsigned pin)
-{
-	return pin;
-}
-
-/**
- *  cygnus_set_bit - set or clear one bit (corresponding to the GPIO pin) in a
- *  Cygnus GPIO register
- *
- *  @cygnus_gpio: Cygnus GPIO device
- *  @reg: register offset
- *  @gpio: GPIO pin
- *  @set: set or clear
- */
-static inline void cygnus_set_bit(struct cygnus_gpio *chip, unsigned int reg,
-				  unsigned gpio, bool set)
-{
-	unsigned int offset = CYGNUS_GPIO_REG(gpio, reg);
-	unsigned int shift = CYGNUS_GPIO_SHIFT(gpio);
-	u32 val;
-
-	val = readl(chip->base + offset);
-	if (set)
-		val |= BIT(shift);
-	else
-		val &= ~BIT(shift);
-	writel(val, chip->base + offset);
-}
-
-static inline bool cygnus_get_bit(struct cygnus_gpio *chip, unsigned int reg,
-				  unsigned gpio)
-{
-	unsigned int offset = CYGNUS_GPIO_REG(gpio, reg);
-	unsigned int shift = CYGNUS_GPIO_SHIFT(gpio);
-
-	return !!(readl(chip->base + offset) & BIT(shift));
-}
-
-static void cygnus_gpio_irq_handler(struct irq_desc *desc)
-{
-	struct gpio_chip *gc = irq_desc_get_handler_data(desc);
-	struct cygnus_gpio *chip = to_cygnus_gpio(gc);
-	struct irq_chip *irq_chip = irq_desc_get_chip(desc);
-	int i, bit;
-
-	chained_irq_enter(irq_chip, desc);
-
-	/* go through the entire GPIO banks and handle all interrupts */
-	for (i = 0; i < chip->num_banks; i++) {
-		unsigned long val = readl(chip->base + (i * GPIO_BANK_SIZE) +
-					  CYGNUS_GPIO_INT_MSTAT_OFFSET);
-
-		for_each_set_bit(bit, &val, NGPIOS_PER_BANK) {
-			unsigned pin = NGPIOS_PER_BANK * i + bit;
-			int child_irq = irq_find_mapping(gc->irqdomain, pin);
-
-			/*
-			 * Clear the interrupt before invoking the
-			 * handler, so we do not leave any window
-			 */
-			writel(BIT(bit), chip->base + (i * GPIO_BANK_SIZE) +
-			       CYGNUS_GPIO_INT_CLR_OFFSET);
-
-			generic_handle_irq(child_irq);
-		}
-	}
-
-	chained_irq_exit(irq_chip, desc);
-}
-
-
-static void cygnus_gpio_irq_ack(struct irq_data *d)
-{
-	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
-	struct cygnus_gpio *chip = to_cygnus_gpio(gc);
-	unsigned gpio = d->hwirq;
-	unsigned int offset = CYGNUS_GPIO_REG(gpio,
-			CYGNUS_GPIO_INT_CLR_OFFSET);
-	unsigned int shift = CYGNUS_GPIO_SHIFT(gpio);
-	u32 val = BIT(shift);
-
-	writel(val, chip->base + offset);
-}
-
-/**
- *  cygnus_gpio_irq_set_mask - mask/unmask a GPIO interrupt
- *
- *  @d: IRQ chip data
- *  @unmask: mask/unmask GPIO interrupt
- */
-static void cygnus_gpio_irq_set_mask(struct irq_data *d, bool unmask)
-{
-	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
-	struct cygnus_gpio *chip = to_cygnus_gpio(gc);
-	unsigned gpio = d->hwirq;
-
-	cygnus_set_bit(chip, CYGNUS_GPIO_INT_MSK_OFFSET, gpio, unmask);
-}
-
-static void cygnus_gpio_irq_mask(struct irq_data *d)
-{
-	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
-	struct cygnus_gpio *chip = to_cygnus_gpio(gc);
-	unsigned long flags;
-
-	spin_lock_irqsave(&chip->lock, flags);
-	cygnus_gpio_irq_set_mask(d, false);
-	spin_unlock_irqrestore(&chip->lock, flags);
-}
-
-static void cygnus_gpio_irq_unmask(struct irq_data *d)
-{
-	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
-	struct cygnus_gpio *chip = to_cygnus_gpio(gc);
-	unsigned long flags;
-
-	spin_lock_irqsave(&chip->lock, flags);
-	cygnus_gpio_irq_set_mask(d, true);
-	spin_unlock_irqrestore(&chip->lock, flags);
-}
-
-static int cygnus_gpio_irq_set_type(struct irq_data *d, unsigned int type)
-{
-	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
-	struct cygnus_gpio *chip = to_cygnus_gpio(gc);
-	unsigned gpio = d->hwirq;
-	bool level_triggered = false;
-	bool dual_edge = false;
-	bool rising_or_high = false;
-	unsigned long flags;
-
-	switch (type & IRQ_TYPE_SENSE_MASK) {
-	case IRQ_TYPE_EDGE_RISING:
-		rising_or_high = true;
-		break;
-
-	case IRQ_TYPE_EDGE_FALLING:
-		break;
-
-	case IRQ_TYPE_EDGE_BOTH:
-		dual_edge = true;
-		break;
-
-	case IRQ_TYPE_LEVEL_HIGH:
-		level_triggered = true;
-		rising_or_high = true;
-		break;
-
-	case IRQ_TYPE_LEVEL_LOW:
-		level_triggered = true;
-		break;
-
-	default:
-		dev_err(chip->dev, "invalid GPIO IRQ type 0x%x\n",
-			type);
-		return -EINVAL;
-	}
-
-	spin_lock_irqsave(&chip->lock, flags);
-	cygnus_set_bit(chip, CYGNUS_GPIO_INT_TYPE_OFFSET, gpio,
-		       level_triggered);
-	cygnus_set_bit(chip, CYGNUS_GPIO_INT_DE_OFFSET, gpio, dual_edge);
-	cygnus_set_bit(chip, CYGNUS_GPIO_INT_EDGE_OFFSET, gpio,
-		       rising_or_high);
-	spin_unlock_irqrestore(&chip->lock, flags);
-
-	dev_dbg(chip->dev,
-		"gpio:%u level_triggered:%d dual_edge:%d rising_or_high:%d\n",
-		gpio, level_triggered, dual_edge, rising_or_high);
-
-	return 0;
-}
-
-static struct irq_chip cygnus_gpio_irq_chip = {
-	.name = "bcm-cygnus-gpio",
-	.irq_ack = cygnus_gpio_irq_ack,
-	.irq_mask = cygnus_gpio_irq_mask,
-	.irq_unmask = cygnus_gpio_irq_unmask,
-	.irq_set_type = cygnus_gpio_irq_set_type,
-};
-
-/*
- * Request the Cygnus IOMUX pinmux controller to mux individual pins to GPIO
- */
-static int cygnus_gpio_request(struct gpio_chip *gc, unsigned offset)
-{
-	struct cygnus_gpio *chip = to_cygnus_gpio(gc);
-	unsigned gpio = gc->base + offset;
-
-	/* not all Cygnus GPIO pins can be muxed individually */
-	if (!chip->pinmux_is_supported)
-		return 0;
-
-	return pinctrl_request_gpio(gpio);
-}
-
-static void cygnus_gpio_free(struct gpio_chip *gc, unsigned offset)
-{
-	struct cygnus_gpio *chip = to_cygnus_gpio(gc);
-	unsigned gpio = gc->base + offset;
-
-	if (!chip->pinmux_is_supported)
-		return;
-
-	pinctrl_free_gpio(gpio);
-}
-
-static int cygnus_gpio_direction_input(struct gpio_chip *gc, unsigned gpio)
-{
-	struct cygnus_gpio *chip = to_cygnus_gpio(gc);
-	unsigned long flags;
-
-	spin_lock_irqsave(&chip->lock, flags);
-	cygnus_set_bit(chip, CYGNUS_GPIO_OUT_EN_OFFSET, gpio, false);
-	spin_unlock_irqrestore(&chip->lock, flags);
-
-	dev_dbg(chip->dev, "gpio:%u set input\n", gpio);
-
-	return 0;
-}
-
-static int cygnus_gpio_direction_output(struct gpio_chip *gc, unsigned gpio,
-					int val)
-{
-	struct cygnus_gpio *chip = to_cygnus_gpio(gc);
-	unsigned long flags;
-
-	spin_lock_irqsave(&chip->lock, flags);
-	cygnus_set_bit(chip, CYGNUS_GPIO_OUT_EN_OFFSET, gpio, true);
-	cygnus_set_bit(chip, CYGNUS_GPIO_DATA_OUT_OFFSET, gpio, !!(val));
-	spin_unlock_irqrestore(&chip->lock, flags);
-
-	dev_dbg(chip->dev, "gpio:%u set output, value:%d\n", gpio, val);
-
-	return 0;
-}
-
-static void cygnus_gpio_set(struct gpio_chip *gc, unsigned gpio, int val)
-{
-	struct cygnus_gpio *chip = to_cygnus_gpio(gc);
-	unsigned long flags;
-
-	spin_lock_irqsave(&chip->lock, flags);
-	cygnus_set_bit(chip, CYGNUS_GPIO_DATA_OUT_OFFSET, gpio, !!(val));
-	spin_unlock_irqrestore(&chip->lock, flags);
-
-	dev_dbg(chip->dev, "gpio:%u set, value:%d\n", gpio, val);
-}
-
-static int cygnus_gpio_get(struct gpio_chip *gc, unsigned gpio)
-{
-	struct cygnus_gpio *chip = to_cygnus_gpio(gc);
-	unsigned int offset = CYGNUS_GPIO_REG(gpio,
-					      CYGNUS_GPIO_DATA_IN_OFFSET);
-	unsigned int shift = CYGNUS_GPIO_SHIFT(gpio);
-
-	return !!(readl(chip->base + offset) & BIT(shift));
-}
-
-static int cygnus_get_groups_count(struct pinctrl_dev *pctldev)
-{
-	return 1;
-}
-
-/*
- * Only one group: "gpio_grp", since this local pinctrl device only performs
- * GPIO specific PINCONF configurations
- */
-static const char *cygnus_get_group_name(struct pinctrl_dev *pctldev,
-					 unsigned selector)
-{
-	return "gpio_grp";
-}
-
-static const struct pinctrl_ops cygnus_pctrl_ops = {
-	.get_groups_count = cygnus_get_groups_count,
-	.get_group_name = cygnus_get_group_name,
-	.dt_node_to_map = pinconf_generic_dt_node_to_map_pin,
-	.dt_free_map = pinctrl_utils_dt_free_map,
-};
-
-static int cygnus_gpio_set_pull(struct cygnus_gpio *chip, unsigned gpio,
-				bool disable, bool pull_up)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&chip->lock, flags);
-
-	if (disable) {
-		cygnus_set_bit(chip, CYGNUS_GPIO_RES_EN_OFFSET, gpio, false);
-	} else {
-		cygnus_set_bit(chip, CYGNUS_GPIO_PAD_RES_OFFSET, gpio,
-			       pull_up);
-		cygnus_set_bit(chip, CYGNUS_GPIO_RES_EN_OFFSET, gpio, true);
-	}
-
-	spin_unlock_irqrestore(&chip->lock, flags);
-
-	dev_dbg(chip->dev, "gpio:%u set pullup:%d\n", gpio, pull_up);
-
-	return 0;
-}
-
-static void cygnus_gpio_get_pull(struct cygnus_gpio *chip, unsigned gpio,
-				 bool *disable, bool *pull_up)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&chip->lock, flags);
-	*disable = !cygnus_get_bit(chip, CYGNUS_GPIO_RES_EN_OFFSET, gpio);
-	*pull_up = cygnus_get_bit(chip, CYGNUS_GPIO_PAD_RES_OFFSET, gpio);
-	spin_unlock_irqrestore(&chip->lock, flags);
-}
-
-static int cygnus_gpio_set_strength(struct cygnus_gpio *chip, unsigned gpio,
-				    unsigned strength)
-{
-	void __iomem *base;
-	unsigned int i, offset, shift;
-	u32 val;
-	unsigned long flags;
-
-	/* make sure drive strength is supported */
-	if (strength < 2 ||  strength > 16 || (strength % 2))
-		return -ENOTSUPP;
-
-	if (chip->io_ctrl) {
-		base = chip->io_ctrl;
-		offset = CYGNUS_GPIO_DRV0_CTRL_OFFSET;
-	} else {
-		base = chip->base;
-		offset = CYGNUS_GPIO_REG(gpio,
-					 CYGNUS_GPIO_ASIU_DRV0_CTRL_OFFSET);
-	}
-
-	shift = CYGNUS_GPIO_SHIFT(gpio);
-
-	dev_dbg(chip->dev, "gpio:%u set drive strength:%d mA\n", gpio,
-		strength);
-
-	spin_lock_irqsave(&chip->lock, flags);
-	strength = (strength / 2) - 1;
-	for (i = 0; i < GPIO_DRV_STRENGTH_BITS; i++) {
-		val = readl(base + offset);
-		val &= ~BIT(shift);
-		val |= ((strength >> i) & 0x1) << shift;
-		writel(val, base + offset);
-		offset += 4;
-	}
-	spin_unlock_irqrestore(&chip->lock, flags);
-
-	return 0;
-}
-
-static int cygnus_gpio_get_strength(struct cygnus_gpio *chip, unsigned gpio,
-				    u16 *strength)
-{
-	void __iomem *base;
-	unsigned int i, offset, shift;
-	u32 val;
-	unsigned long flags;
-
-	if (chip->io_ctrl) {
-		base = chip->io_ctrl;
-		offset = CYGNUS_GPIO_DRV0_CTRL_OFFSET;
-	} else {
-		base = chip->base;
-		offset = CYGNUS_GPIO_REG(gpio,
-					 CYGNUS_GPIO_ASIU_DRV0_CTRL_OFFSET);
-	}
-
-	shift = CYGNUS_GPIO_SHIFT(gpio);
-
-	spin_lock_irqsave(&chip->lock, flags);
-	*strength = 0;
-	for (i = 0; i < GPIO_DRV_STRENGTH_BITS; i++) {
-		val = readl(base + offset) & BIT(shift);
-		val >>= shift;
-		*strength += (val << i);
-		offset += 4;
-	}
-
-	/* convert to mA */
-	*strength = (*strength + 1) * 2;
-	spin_unlock_irqrestore(&chip->lock, flags);
-
-	return 0;
-}
-
-static int cygnus_pin_config_get(struct pinctrl_dev *pctldev, unsigned pin,
-				 unsigned long *config)
-{
-	struct cygnus_gpio *chip = pinctrl_dev_get_drvdata(pctldev);
-	enum pin_config_param param = pinconf_to_config_param(*config);
-	unsigned gpio = cygnus_pin_to_gpio(pin);
-	u16 arg;
-	bool disable, pull_up;
-	int ret;
-
-	switch (param) {
-	case PIN_CONFIG_BIAS_DISABLE:
-		cygnus_gpio_get_pull(chip, gpio, &disable, &pull_up);
-		if (disable)
-			return 0;
-		else
-			return -EINVAL;
-
-	case PIN_CONFIG_BIAS_PULL_UP:
-		cygnus_gpio_get_pull(chip, gpio, &disable, &pull_up);
-		if (!disable && pull_up)
-			return 0;
-		else
-			return -EINVAL;
-
-	case PIN_CONFIG_BIAS_PULL_DOWN:
-		cygnus_gpio_get_pull(chip, gpio, &disable, &pull_up);
-		if (!disable && !pull_up)
-			return 0;
-		else
-			return -EINVAL;
-
-	case PIN_CONFIG_DRIVE_STRENGTH:
-		ret = cygnus_gpio_get_strength(chip, gpio, &arg);
-		if (ret)
-			return ret;
-		else
-			*config = pinconf_to_config_packed(param, arg);
-
-		return 0;
-
-	default:
-		return -ENOTSUPP;
-	}
-
-	return -ENOTSUPP;
-}
-
-static int cygnus_pin_config_set(struct pinctrl_dev *pctldev, unsigned pin,
-				 unsigned long *configs, unsigned num_configs)
-{
-	struct cygnus_gpio *chip = pinctrl_dev_get_drvdata(pctldev);
-	enum pin_config_param param;
-	u16 arg;
-	unsigned i, gpio = cygnus_pin_to_gpio(pin);
-	int ret = -ENOTSUPP;
-
-	for (i = 0; i < num_configs; i++) {
-		param = pinconf_to_config_param(configs[i]);
-		arg = pinconf_to_config_argument(configs[i]);
-
-		switch (param) {
-		case PIN_CONFIG_BIAS_DISABLE:
-			ret = cygnus_gpio_set_pull(chip, gpio, true, false);
-			if (ret < 0)
-				goto out;
-			break;
-
-		case PIN_CONFIG_BIAS_PULL_UP:
-			ret = cygnus_gpio_set_pull(chip, gpio, false, true);
-			if (ret < 0)
-				goto out;
-			break;
-
-		case PIN_CONFIG_BIAS_PULL_DOWN:
-			ret = cygnus_gpio_set_pull(chip, gpio, false, false);
-			if (ret < 0)
-				goto out;
-			break;
-
-		case PIN_CONFIG_DRIVE_STRENGTH:
-			ret = cygnus_gpio_set_strength(chip, gpio, arg);
-			if (ret < 0)
-				goto out;
-			break;
-
-		default:
-			dev_err(chip->dev, "invalid configuration\n");
-			return -ENOTSUPP;
-		}
-	} /* for each config */
-
-out:
-	return ret;
-}
-
-static const struct pinconf_ops cygnus_pconf_ops = {
-	.is_generic = true,
-	.pin_config_get = cygnus_pin_config_get,
-	.pin_config_set = cygnus_pin_config_set,
-};
-
-/*
- * Cygnus GPIO controller supports some PINCONF related configurations such as
- * pull up, pull down, and drive strength, when the pin is configured to GPIO
- *
- * Here a local pinctrl device is created with simple 1-to-1 pin mapping to the
- * local GPIO pins
- */
-static int cygnus_gpio_register_pinconf(struct cygnus_gpio *chip)
-{
-	struct pinctrl_desc *pctldesc = &chip->pctldesc;
-	struct pinctrl_pin_desc *pins;
-	struct gpio_chip *gc = &chip->gc;
-	int i;
-
-	pins = devm_kcalloc(chip->dev, gc->ngpio, sizeof(*pins), GFP_KERNEL);
-	if (!pins)
-		return -ENOMEM;
-
-	for (i = 0; i < gc->ngpio; i++) {
-		pins[i].number = i;
-		pins[i].name = devm_kasprintf(chip->dev, GFP_KERNEL,
-					      "gpio-%d", i);
-		if (!pins[i].name)
-			return -ENOMEM;
-	}
-
-	pctldesc->name = dev_name(chip->dev);
-	pctldesc->pctlops = &cygnus_pctrl_ops;
-	pctldesc->pins = pins;
-	pctldesc->npins = gc->ngpio;
-	pctldesc->confops = &cygnus_pconf_ops;
-
-	chip->pctl = pinctrl_register(pctldesc, chip->dev, chip);
-	if (IS_ERR(chip->pctl)) {
-		dev_err(chip->dev, "unable to register pinctrl device\n");
-		return PTR_ERR(chip->pctl);
-	}
-
-	return 0;
-}
-
-static void cygnus_gpio_unregister_pinconf(struct cygnus_gpio *chip)
-{
-	if (chip->pctl)
-		pinctrl_unregister(chip->pctl);
-}
-
-struct cygnus_gpio_data {
-	unsigned num_gpios;
-};
-
-static const struct cygnus_gpio_data cygnus_cmm_gpio_data = {
-	.num_gpios = 24,
-};
-
-static const struct cygnus_gpio_data cygnus_asiu_gpio_data = {
-	.num_gpios = 146,
-};
-
-static const struct cygnus_gpio_data cygnus_crmu_gpio_data = {
-	.num_gpios = 6,
-};
-
-static const struct of_device_id cygnus_gpio_of_match[] = {
-	{
-		.compatible = "brcm,cygnus-ccm-gpio",
-		.data = &cygnus_cmm_gpio_data,
-	},
-	{
-		.compatible = "brcm,cygnus-asiu-gpio",
-		.data = &cygnus_asiu_gpio_data,
-	},
-	{
-		.compatible = "brcm,cygnus-crmu-gpio",
-		.data = &cygnus_crmu_gpio_data,
-	}
-};
-
-static int cygnus_gpio_probe(struct platform_device *pdev)
-{
-	struct device *dev = &pdev->dev;
-	struct resource *res;
-	struct cygnus_gpio *chip;
-	struct gpio_chip *gc;
-	u32 ngpios;
-	int irq, ret;
-	const struct of_device_id *match;
-	const struct cygnus_gpio_data *gpio_data;
-
-	match = of_match_device(cygnus_gpio_of_match, dev);
-	if (!match)
-		return -ENODEV;
-	gpio_data = match->data;
-	ngpios = gpio_data->num_gpios;
-
-	chip = devm_kzalloc(dev, sizeof(*chip), GFP_KERNEL);
-	if (!chip)
-		return -ENOMEM;
-
-	chip->dev = dev;
-	platform_set_drvdata(pdev, chip);
-
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	chip->base = devm_ioremap_resource(dev, res);
-	if (IS_ERR(chip->base)) {
-		dev_err(dev, "unable to map I/O memory\n");
-		return PTR_ERR(chip->base);
-	}
-
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
-	if (res) {
-		chip->io_ctrl = devm_ioremap_resource(dev, res);
-		if (IS_ERR(chip->io_ctrl)) {
-			dev_err(dev, "unable to map I/O memory\n");
-			return PTR_ERR(chip->io_ctrl);
-		}
-	}
-
-	spin_lock_init(&chip->lock);
-
-	gc = &chip->gc;
-	gc->base = -1;
-	gc->ngpio = ngpios;
-	chip->num_banks = (ngpios + NGPIOS_PER_BANK - 1) / NGPIOS_PER_BANK;
-	gc->label = dev_name(dev);
-	gc->dev = dev;
-	gc->of_node = dev->of_node;
-	gc->request = cygnus_gpio_request;
-	gc->free = cygnus_gpio_free;
-	gc->direction_input = cygnus_gpio_direction_input;
-	gc->direction_output = cygnus_gpio_direction_output;
-	gc->set = cygnus_gpio_set;
-	gc->get = cygnus_gpio_get;
-
-	chip->pinmux_is_supported = of_property_read_bool(dev->of_node,
-							"gpio-ranges");
-
-	ret = gpiochip_add(gc);
-	if (ret < 0) {
-		dev_err(dev, "unable to add GPIO chip\n");
-		return ret;
-	}
-
-	ret = cygnus_gpio_register_pinconf(chip);
-	if (ret) {
-		dev_err(dev, "unable to register pinconf\n");
-		goto err_rm_gpiochip;
-	}
-
-	/* optional GPIO interrupt support */
-	irq = platform_get_irq(pdev, 0);
-	if (irq) {
-		ret = gpiochip_irqchip_add(gc, &cygnus_gpio_irq_chip, 0,
-					   handle_simple_irq, IRQ_TYPE_NONE);
-		if (ret) {
-			dev_err(dev, "no GPIO irqchip\n");
-			goto err_unregister_pinconf;
-		}
-
-		gpiochip_set_chained_irqchip(gc, &cygnus_gpio_irq_chip, irq,
-					     cygnus_gpio_irq_handler);
-	}
-
-	return 0;
-
-err_unregister_pinconf:
-	cygnus_gpio_unregister_pinconf(chip);
-
-err_rm_gpiochip:
-	gpiochip_remove(gc);
-
-	return ret;
-}
-
-static struct platform_driver cygnus_gpio_driver = {
-	.driver = {
-		.name = "cygnus-gpio",
-		.of_match_table = cygnus_gpio_of_match,
-	},
-	.probe = cygnus_gpio_probe,
-};
-
-static int __init cygnus_gpio_init(void)
-{
-	return platform_driver_probe(&cygnus_gpio_driver, cygnus_gpio_probe);
-}
-arch_initcall_sync(cygnus_gpio_init);
diff --git a/drivers/pinctrl/bcm/pinctrl-iproc-gpio.c b/drivers/pinctrl/bcm/pinctrl-iproc-gpio.c
new file mode 100644
index 0000000..314591a
--- /dev/null
+++ b/drivers/pinctrl/bcm/pinctrl-iproc-gpio.c
@@ -0,0 +1,758 @@
+/*
+ * Copyright (C) 2014-2015 Broadcom Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * This file contains the Broadcom Iproc GPIO driver that supports 3
+ * GPIO controllers on Iproc including the ASIU GPIO controller, the
+ * chipCommonG GPIO controller, and the always-on GPIO controller. Basic
+ * PINCONF such as bias pull up/down, and drive strength are also supported
+ * in this driver.
+ *
+ * It provides the functionality where pins from the GPIO can be
+ * individually muxed to GPIO function, if individual pad
+ * configuration is supported, through the interaction with respective
+ * SoCs IOMUX controller.
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/gpio.h>
+#include <linux/ioport.h>
+#include <linux/of_device.h>
+#include <linux/of_irq.h>
+#include <linux/pinctrl/pinctrl.h>
+#include <linux/pinctrl/pinconf.h>
+#include <linux/pinctrl/pinconf-generic.h>
+
+#include "../pinctrl-utils.h"
+
+#define IPROC_GPIO_DATA_IN_OFFSET   0x00
+#define IPROC_GPIO_DATA_OUT_OFFSET  0x04
+#define IPROC_GPIO_OUT_EN_OFFSET    0x08
+#define IPROC_GPIO_INT_TYPE_OFFSET  0x0c
+#define IPROC_GPIO_INT_DE_OFFSET    0x10
+#define IPROC_GPIO_INT_EDGE_OFFSET  0x14
+#define IPROC_GPIO_INT_MSK_OFFSET   0x18
+#define IPROC_GPIO_INT_STAT_OFFSET  0x1c
+#define IPROC_GPIO_INT_MSTAT_OFFSET 0x20
+#define IPROC_GPIO_INT_CLR_OFFSET   0x24
+#define IPROC_GPIO_PAD_RES_OFFSET   0x34
+#define IPROC_GPIO_RES_EN_OFFSET    0x38
+
+/* drive strength control for ASIU GPIO */
+#define IPROC_GPIO_ASIU_DRV0_CTRL_OFFSET 0x58
+
+/* drive strength control for CCM/CRMU (AON) GPIO */
+#define IPROC_GPIO_DRV0_CTRL_OFFSET  0x00
+
+#define GPIO_BANK_SIZE 0x200
+#define NGPIOS_PER_BANK 32
+#define GPIO_BANK(pin) ((pin) / NGPIOS_PER_BANK)
+
+#define IPROC_GPIO_REG(pin, reg) (GPIO_BANK(pin) * GPIO_BANK_SIZE + (reg))
+#define IPROC_GPIO_SHIFT(pin) ((pin) % NGPIOS_PER_BANK)
+
+#define GPIO_DRV_STRENGTH_BIT_SHIFT  20
+#define GPIO_DRV_STRENGTH_BITS       3
+#define GPIO_DRV_STRENGTH_BIT_MASK   ((1 << GPIO_DRV_STRENGTH_BITS) - 1)
+
+/*
+ * Iproc GPIO core
+ *
+ * @dev: pointer to device
+ * @base: I/O register base for Iproc GPIO controller
+ * @io_ctrl: I/O register base for certain type of Iproc GPIO controller that
+ * has the PINCONF support implemented outside of the GPIO block
+ * @lock: lock to protect access to I/O registers
+ * @gc: GPIO chip
+ * @num_banks: number of GPIO banks, each bank supports up to 32 GPIOs
+ * @pinmux_is_supported: flag to indicate this GPIO controller contains pins
+ * that can be individually muxed to GPIO
+ * @pctl: pointer to pinctrl_dev
+ * @pctldesc: pinctrl descriptor
+ */
+struct iproc_gpio {
+	struct device *dev;
+
+	void __iomem *base;
+	void __iomem *io_ctrl;
+
+	spinlock_t lock;
+
+	struct gpio_chip gc;
+	unsigned num_banks;
+
+	bool pinmux_is_supported;
+
+	struct pinctrl_dev *pctl;
+	struct pinctrl_desc pctldesc;
+};
+
+static inline struct iproc_gpio *to_iproc_gpio(struct gpio_chip *gc)
+{
+	return container_of(gc, struct iproc_gpio, gc);
+}
+
+/*
+ * Mapping from PINCONF pins to GPIO pins is 1-to-1
+ */
+static inline unsigned iproc_pin_to_gpio(unsigned pin)
+{
+	return pin;
+}
+
+/**
+ *  iproc_set_bit - set or clear one bit (corresponding to the GPIO pin) in a
+ *  Iproc GPIO register
+ *
+ *  @iproc_gpio: Iproc GPIO device
+ *  @reg: register offset
+ *  @gpio: GPIO pin
+ *  @set: set or clear
+ */
+static inline void iproc_set_bit(struct iproc_gpio *chip, unsigned int reg,
+				  unsigned gpio, bool set)
+{
+	unsigned int offset = IPROC_GPIO_REG(gpio, reg);
+	unsigned int shift = IPROC_GPIO_SHIFT(gpio);
+	u32 val;
+
+	val = readl(chip->base + offset);
+	if (set)
+		val |= BIT(shift);
+	else
+		val &= ~BIT(shift);
+	writel(val, chip->base + offset);
+}
+
+static inline bool iproc_get_bit(struct iproc_gpio *chip, unsigned int reg,
+				  unsigned gpio)
+{
+	unsigned int offset = IPROC_GPIO_REG(gpio, reg);
+	unsigned int shift = IPROC_GPIO_SHIFT(gpio);
+
+	return !!(readl(chip->base + offset) & BIT(shift));
+}
+
+static void iproc_gpio_irq_handler(struct irq_desc *desc)
+{
+	struct gpio_chip *gc = irq_desc_get_handler_data(desc);
+	struct iproc_gpio *chip = to_iproc_gpio(gc);
+	struct irq_chip *irq_chip = irq_desc_get_chip(desc);
+	int i, bit;
+
+	chained_irq_enter(irq_chip, desc);
+
+	/* go through the entire GPIO banks and handle all interrupts */
+	for (i = 0; i < chip->num_banks; i++) {
+		unsigned long val = readl(chip->base + (i * GPIO_BANK_SIZE) +
+					  IPROC_GPIO_INT_MSTAT_OFFSET);
+
+		for_each_set_bit(bit, &val, NGPIOS_PER_BANK) {
+			unsigned pin = NGPIOS_PER_BANK * i + bit;
+			int child_irq = irq_find_mapping(gc->irqdomain, pin);
+
+			/*
+			 * Clear the interrupt before invoking the
+			 * handler, so we do not leave any window
+			 */
+			writel(BIT(bit), chip->base + (i * GPIO_BANK_SIZE) +
+			       IPROC_GPIO_INT_CLR_OFFSET);
+
+			generic_handle_irq(child_irq);
+		}
+	}
+
+	chained_irq_exit(irq_chip, desc);
+}
+
+
+static void iproc_gpio_irq_ack(struct irq_data *d)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct iproc_gpio *chip = to_iproc_gpio(gc);
+	unsigned gpio = d->hwirq;
+	unsigned int offset = IPROC_GPIO_REG(gpio,
+			IPROC_GPIO_INT_CLR_OFFSET);
+	unsigned int shift = IPROC_GPIO_SHIFT(gpio);
+	u32 val = BIT(shift);
+
+	writel(val, chip->base + offset);
+}
+
+/**
+ *  iproc_gpio_irq_set_mask - mask/unmask a GPIO interrupt
+ *
+ *  @d: IRQ chip data
+ *  @unmask: mask/unmask GPIO interrupt
+ */
+static void iproc_gpio_irq_set_mask(struct irq_data *d, bool unmask)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct iproc_gpio *chip = to_iproc_gpio(gc);
+	unsigned gpio = d->hwirq;
+
+	iproc_set_bit(chip, IPROC_GPIO_INT_MSK_OFFSET, gpio, unmask);
+}
+
+static void iproc_gpio_irq_mask(struct irq_data *d)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct iproc_gpio *chip = to_iproc_gpio(gc);
+	unsigned long flags;
+
+	spin_lock_irqsave(&chip->lock, flags);
+	iproc_gpio_irq_set_mask(d, false);
+	spin_unlock_irqrestore(&chip->lock, flags);
+}
+
+static void iproc_gpio_irq_unmask(struct irq_data *d)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct iproc_gpio *chip = to_iproc_gpio(gc);
+	unsigned long flags;
+
+	spin_lock_irqsave(&chip->lock, flags);
+	iproc_gpio_irq_set_mask(d, true);
+	spin_unlock_irqrestore(&chip->lock, flags);
+}
+
+static int iproc_gpio_irq_set_type(struct irq_data *d, unsigned int type)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct iproc_gpio *chip = to_iproc_gpio(gc);
+	unsigned gpio = d->hwirq;
+	bool level_triggered = false;
+	bool dual_edge = false;
+	bool rising_or_high = false;
+	unsigned long flags;
+
+	switch (type & IRQ_TYPE_SENSE_MASK) {
+	case IRQ_TYPE_EDGE_RISING:
+		rising_or_high = true;
+		break;
+
+	case IRQ_TYPE_EDGE_FALLING:
+		break;
+
+	case IRQ_TYPE_EDGE_BOTH:
+		dual_edge = true;
+		break;
+
+	case IRQ_TYPE_LEVEL_HIGH:
+		level_triggered = true;
+		rising_or_high = true;
+		break;
+
+	case IRQ_TYPE_LEVEL_LOW:
+		level_triggered = true;
+		break;
+
+	default:
+		dev_err(chip->dev, "invalid GPIO IRQ type 0x%x\n",
+			type);
+		return -EINVAL;
+	}
+
+	spin_lock_irqsave(&chip->lock, flags);
+	iproc_set_bit(chip, IPROC_GPIO_INT_TYPE_OFFSET, gpio,
+		       level_triggered);
+	iproc_set_bit(chip, IPROC_GPIO_INT_DE_OFFSET, gpio, dual_edge);
+	iproc_set_bit(chip, IPROC_GPIO_INT_EDGE_OFFSET, gpio,
+		       rising_or_high);
+	spin_unlock_irqrestore(&chip->lock, flags);
+
+	dev_dbg(chip->dev,
+		"gpio:%u level_triggered:%d dual_edge:%d rising_or_high:%d\n",
+		gpio, level_triggered, dual_edge, rising_or_high);
+
+	return 0;
+}
+
+static struct irq_chip iproc_gpio_irq_chip = {
+	.name = "bcm-iproc-gpio",
+	.irq_ack = iproc_gpio_irq_ack,
+	.irq_mask = iproc_gpio_irq_mask,
+	.irq_unmask = iproc_gpio_irq_unmask,
+	.irq_set_type = iproc_gpio_irq_set_type,
+};
+
+/*
+ * Request the Iproc IOMUX pinmux controller to mux individual pins to GPIO
+ */
+static int iproc_gpio_request(struct gpio_chip *gc, unsigned offset)
+{
+	struct iproc_gpio *chip = to_iproc_gpio(gc);
+	unsigned gpio = gc->base + offset;
+
+	/* not all Iproc GPIO pins can be muxed individually */
+	if (!chip->pinmux_is_supported)
+		return 0;
+
+	return pinctrl_request_gpio(gpio);
+}
+
+static void iproc_gpio_free(struct gpio_chip *gc, unsigned offset)
+{
+	struct iproc_gpio *chip = to_iproc_gpio(gc);
+	unsigned gpio = gc->base + offset;
+
+	if (!chip->pinmux_is_supported)
+		return;
+
+	pinctrl_free_gpio(gpio);
+}
+
+static int iproc_gpio_direction_input(struct gpio_chip *gc, unsigned gpio)
+{
+	struct iproc_gpio *chip = to_iproc_gpio(gc);
+	unsigned long flags;
+
+	spin_lock_irqsave(&chip->lock, flags);
+	iproc_set_bit(chip, IPROC_GPIO_OUT_EN_OFFSET, gpio, false);
+	spin_unlock_irqrestore(&chip->lock, flags);
+
+	dev_dbg(chip->dev, "gpio:%u set input\n", gpio);
+
+	return 0;
+}
+
+static int iproc_gpio_direction_output(struct gpio_chip *gc, unsigned gpio,
+					int val)
+{
+	struct iproc_gpio *chip = to_iproc_gpio(gc);
+	unsigned long flags;
+
+	spin_lock_irqsave(&chip->lock, flags);
+	iproc_set_bit(chip, IPROC_GPIO_OUT_EN_OFFSET, gpio, true);
+	iproc_set_bit(chip, IPROC_GPIO_DATA_OUT_OFFSET, gpio, !!(val));
+	spin_unlock_irqrestore(&chip->lock, flags);
+
+	dev_dbg(chip->dev, "gpio:%u set output, value:%d\n", gpio, val);
+
+	return 0;
+}
+
+static void iproc_gpio_set(struct gpio_chip *gc, unsigned gpio, int val)
+{
+	struct iproc_gpio *chip = to_iproc_gpio(gc);
+	unsigned long flags;
+
+	spin_lock_irqsave(&chip->lock, flags);
+	iproc_set_bit(chip, IPROC_GPIO_DATA_OUT_OFFSET, gpio, !!(val));
+	spin_unlock_irqrestore(&chip->lock, flags);
+
+	dev_dbg(chip->dev, "gpio:%u set, value:%d\n", gpio, val);
+}
+
+static int iproc_gpio_get(struct gpio_chip *gc, unsigned gpio)
+{
+	struct iproc_gpio *chip = to_iproc_gpio(gc);
+	unsigned int offset = IPROC_GPIO_REG(gpio,
+					      IPROC_GPIO_DATA_IN_OFFSET);
+	unsigned int shift = IPROC_GPIO_SHIFT(gpio);
+
+	return !!(readl(chip->base + offset) & BIT(shift));
+}
+
+static int iproc_get_groups_count(struct pinctrl_dev *pctldev)
+{
+	return 1;
+}
+
+/*
+ * Only one group: "gpio_grp", since this local pinctrl device only performs
+ * GPIO specific PINCONF configurations
+ */
+static const char *iproc_get_group_name(struct pinctrl_dev *pctldev,
+					 unsigned selector)
+{
+	return "gpio_grp";
+}
+
+static const struct pinctrl_ops iproc_pctrl_ops = {
+	.get_groups_count = iproc_get_groups_count,
+	.get_group_name = iproc_get_group_name,
+	.dt_node_to_map = pinconf_generic_dt_node_to_map_pin,
+	.dt_free_map = pinctrl_utils_dt_free_map,
+};
+
+static int iproc_gpio_set_pull(struct iproc_gpio *chip, unsigned gpio,
+				bool disable, bool pull_up)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&chip->lock, flags);
+
+	if (disable) {
+		iproc_set_bit(chip, IPROC_GPIO_RES_EN_OFFSET, gpio, false);
+	} else {
+		iproc_set_bit(chip, IPROC_GPIO_PAD_RES_OFFSET, gpio,
+			       pull_up);
+		iproc_set_bit(chip, IPROC_GPIO_RES_EN_OFFSET, gpio, true);
+	}
+
+	spin_unlock_irqrestore(&chip->lock, flags);
+
+	dev_dbg(chip->dev, "gpio:%u set pullup:%d\n", gpio, pull_up);
+
+	return 0;
+}
+
+static void iproc_gpio_get_pull(struct iproc_gpio *chip, unsigned gpio,
+				 bool *disable, bool *pull_up)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&chip->lock, flags);
+	*disable = !iproc_get_bit(chip, IPROC_GPIO_RES_EN_OFFSET, gpio);
+	*pull_up = iproc_get_bit(chip, IPROC_GPIO_PAD_RES_OFFSET, gpio);
+	spin_unlock_irqrestore(&chip->lock, flags);
+}
+
+static int iproc_gpio_set_strength(struct iproc_gpio *chip, unsigned gpio,
+				    unsigned strength)
+{
+	void __iomem *base;
+	unsigned int i, offset, shift;
+	u32 val;
+	unsigned long flags;
+
+	/* make sure drive strength is supported */
+	if (strength < 2 ||  strength > 16 || (strength % 2))
+		return -ENOTSUPP;
+
+	if (chip->io_ctrl) {
+		base = chip->io_ctrl;
+		offset = IPROC_GPIO_DRV0_CTRL_OFFSET;
+	} else {
+		base = chip->base;
+		offset = IPROC_GPIO_REG(gpio,
+					 IPROC_GPIO_ASIU_DRV0_CTRL_OFFSET);
+	}
+
+	shift = IPROC_GPIO_SHIFT(gpio);
+
+	dev_dbg(chip->dev, "gpio:%u set drive strength:%d mA\n", gpio,
+		strength);
+
+	spin_lock_irqsave(&chip->lock, flags);
+	strength = (strength / 2) - 1;
+	for (i = 0; i < GPIO_DRV_STRENGTH_BITS; i++) {
+		val = readl(base + offset);
+		val &= ~BIT(shift);
+		val |= ((strength >> i) & 0x1) << shift;
+		writel(val, base + offset);
+		offset += 4;
+	}
+	spin_unlock_irqrestore(&chip->lock, flags);
+
+	return 0;
+}
+
+static int iproc_gpio_get_strength(struct iproc_gpio *chip, unsigned gpio,
+				    u16 *strength)
+{
+	void __iomem *base;
+	unsigned int i, offset, shift;
+	u32 val;
+	unsigned long flags;
+
+	if (chip->io_ctrl) {
+		base = chip->io_ctrl;
+		offset = IPROC_GPIO_DRV0_CTRL_OFFSET;
+	} else {
+		base = chip->base;
+		offset = IPROC_GPIO_REG(gpio,
+					 IPROC_GPIO_ASIU_DRV0_CTRL_OFFSET);
+	}
+
+	shift = IPROC_GPIO_SHIFT(gpio);
+
+	spin_lock_irqsave(&chip->lock, flags);
+	*strength = 0;
+	for (i = 0; i < GPIO_DRV_STRENGTH_BITS; i++) {
+		val = readl(base + offset) & BIT(shift);
+		val >>= shift;
+		*strength += (val << i);
+		offset += 4;
+	}
+
+	/* convert to mA */
+	*strength = (*strength + 1) * 2;
+	spin_unlock_irqrestore(&chip->lock, flags);
+
+	return 0;
+}
+
+static int iproc_pin_config_get(struct pinctrl_dev *pctldev, unsigned pin,
+				 unsigned long *config)
+{
+	struct iproc_gpio *chip = pinctrl_dev_get_drvdata(pctldev);
+	enum pin_config_param param = pinconf_to_config_param(*config);
+	unsigned gpio = iproc_pin_to_gpio(pin);
+	u16 arg;
+	bool disable, pull_up;
+	int ret;
+
+	switch (param) {
+	case PIN_CONFIG_BIAS_DISABLE:
+		iproc_gpio_get_pull(chip, gpio, &disable, &pull_up);
+		if (disable)
+			return 0;
+		else
+			return -EINVAL;
+
+	case PIN_CONFIG_BIAS_PULL_UP:
+		iproc_gpio_get_pull(chip, gpio, &disable, &pull_up);
+		if (!disable && pull_up)
+			return 0;
+		else
+			return -EINVAL;
+
+	case PIN_CONFIG_BIAS_PULL_DOWN:
+		iproc_gpio_get_pull(chip, gpio, &disable, &pull_up);
+		if (!disable && !pull_up)
+			return 0;
+		else
+			return -EINVAL;
+
+	case PIN_CONFIG_DRIVE_STRENGTH:
+		ret = iproc_gpio_get_strength(chip, gpio, &arg);
+		if (ret)
+			return ret;
+		*config = pinconf_to_config_packed(param, arg);
+
+		return 0;
+
+	default:
+		return -ENOTSUPP;
+	}
+
+	return -ENOTSUPP;
+}
+
+static int iproc_pin_config_set(struct pinctrl_dev *pctldev, unsigned pin,
+				 unsigned long *configs, unsigned num_configs)
+{
+	struct iproc_gpio *chip = pinctrl_dev_get_drvdata(pctldev);
+	enum pin_config_param param;
+	u16 arg;
+	unsigned i, gpio = iproc_pin_to_gpio(pin);
+	int ret = -ENOTSUPP;
+
+	for (i = 0; i < num_configs; i++) {
+		param = pinconf_to_config_param(configs[i]);
+		arg = pinconf_to_config_argument(configs[i]);
+
+		switch (param) {
+		case PIN_CONFIG_BIAS_DISABLE:
+			ret = iproc_gpio_set_pull(chip, gpio, true, false);
+			if (ret < 0)
+				goto out;
+			break;
+
+		case PIN_CONFIG_BIAS_PULL_UP:
+			ret = iproc_gpio_set_pull(chip, gpio, false, true);
+			if (ret < 0)
+				goto out;
+			break;
+
+		case PIN_CONFIG_BIAS_PULL_DOWN:
+			ret = iproc_gpio_set_pull(chip, gpio, false, false);
+			if (ret < 0)
+				goto out;
+			break;
+
+		case PIN_CONFIG_DRIVE_STRENGTH:
+			ret = iproc_gpio_set_strength(chip, gpio, arg);
+			if (ret < 0)
+				goto out;
+			break;
+
+		default:
+			dev_err(chip->dev, "invalid configuration\n");
+			return -ENOTSUPP;
+		}
+	} /* for each config */
+
+out:
+	return ret;
+}
+
+static const struct pinconf_ops iproc_pconf_ops = {
+	.is_generic = true,
+	.pin_config_get = iproc_pin_config_get,
+	.pin_config_set = iproc_pin_config_set,
+};
+
+/*
+ * Iproc GPIO controller supports some PINCONF related configurations such as
+ * pull up, pull down, and drive strength, when the pin is configured to GPIO
+ *
+ * Here a local pinctrl device is created with simple 1-to-1 pin mapping to the
+ * local GPIO pins
+ */
+static int iproc_gpio_register_pinconf(struct iproc_gpio *chip)
+{
+	struct pinctrl_desc *pctldesc = &chip->pctldesc;
+	struct pinctrl_pin_desc *pins;
+	struct gpio_chip *gc = &chip->gc;
+	int i;
+
+	pins = devm_kcalloc(chip->dev, gc->ngpio, sizeof(*pins), GFP_KERNEL);
+	if (!pins)
+		return -ENOMEM;
+
+	for (i = 0; i < gc->ngpio; i++) {
+		pins[i].number = i;
+		pins[i].name = devm_kasprintf(chip->dev, GFP_KERNEL,
+					      "gpio-%d", i);
+		if (!pins[i].name)
+			return -ENOMEM;
+	}
+
+	pctldesc->name = dev_name(chip->dev);
+	pctldesc->pctlops = &iproc_pctrl_ops;
+	pctldesc->pins = pins;
+	pctldesc->npins = gc->ngpio;
+	pctldesc->confops = &iproc_pconf_ops;
+
+	chip->pctl = pinctrl_register(pctldesc, chip->dev, chip);
+	if (IS_ERR(chip->pctl)) {
+		dev_err(chip->dev, "unable to register pinctrl device\n");
+		return PTR_ERR(chip->pctl);
+	}
+
+	return 0;
+}
+
+static void iproc_gpio_unregister_pinconf(struct iproc_gpio *chip)
+{
+	pinctrl_unregister(chip->pctl);
+}
+
+static const struct of_device_id iproc_gpio_of_match[] = {
+	{ .compatible = "brcm,cygnus-ccm-gpio" },
+	{ .compatible = "brcm,cygnus-asiu-gpio" },
+	{ .compatible = "brcm,cygnus-crmu-gpio" },
+	{ .compatible = "brcm,iproc-gpio" },
+	{ }
+};
+
+static int iproc_gpio_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct resource *res;
+	struct iproc_gpio *chip;
+	struct gpio_chip *gc;
+	u32 ngpios;
+	int irq, ret;
+
+	chip = devm_kzalloc(dev, sizeof(*chip), GFP_KERNEL);
+	if (!chip)
+		return -ENOMEM;
+
+	chip->dev = dev;
+	platform_set_drvdata(pdev, chip);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	chip->base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(chip->base)) {
+		dev_err(dev, "unable to map I/O memory\n");
+		return PTR_ERR(chip->base);
+	}
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	if (res) {
+		chip->io_ctrl = devm_ioremap_resource(dev, res);
+		if (IS_ERR(chip->io_ctrl)) {
+			dev_err(dev, "unable to map I/O memory\n");
+			return PTR_ERR(chip->io_ctrl);
+		}
+	}
+
+	if (of_property_read_u32(dev->of_node, "ngpios", &ngpios)) {
+		dev_err(&pdev->dev, "missing ngpios DT property\n");
+		return -ENODEV;
+	}
+
+	spin_lock_init(&chip->lock);
+
+	gc = &chip->gc;
+	gc->base = -1;
+	gc->ngpio = ngpios;
+	chip->num_banks = (ngpios + NGPIOS_PER_BANK - 1) / NGPIOS_PER_BANK;
+	gc->label = dev_name(dev);
+	gc->dev = dev;
+	gc->of_node = dev->of_node;
+	gc->request = iproc_gpio_request;
+	gc->free = iproc_gpio_free;
+	gc->direction_input = iproc_gpio_direction_input;
+	gc->direction_output = iproc_gpio_direction_output;
+	gc->set = iproc_gpio_set;
+	gc->get = iproc_gpio_get;
+
+	chip->pinmux_is_supported = of_property_read_bool(dev->of_node,
+							"gpio-ranges");
+
+	ret = gpiochip_add(gc);
+	if (ret < 0) {
+		dev_err(dev, "unable to add GPIO chip\n");
+		return ret;
+	}
+
+	ret = iproc_gpio_register_pinconf(chip);
+	if (ret) {
+		dev_err(dev, "unable to register pinconf\n");
+		goto err_rm_gpiochip;
+	}
+
+	/* optional GPIO interrupt support */
+	irq = platform_get_irq(pdev, 0);
+	if (irq) {
+		ret = gpiochip_irqchip_add(gc, &iproc_gpio_irq_chip, 0,
+					   handle_simple_irq, IRQ_TYPE_NONE);
+		if (ret) {
+			dev_err(dev, "no GPIO irqchip\n");
+			goto err_unregister_pinconf;
+		}
+
+		gpiochip_set_chained_irqchip(gc, &iproc_gpio_irq_chip, irq,
+					     iproc_gpio_irq_handler);
+	}
+
+	return 0;
+
+err_unregister_pinconf:
+	iproc_gpio_unregister_pinconf(chip);
+
+err_rm_gpiochip:
+	gpiochip_remove(gc);
+
+	return ret;
+}
+
+static struct platform_driver iproc_gpio_driver = {
+	.driver = {
+		.name = "iproc-gpio",
+		.of_match_table = iproc_gpio_of_match,
+	},
+	.probe = iproc_gpio_probe,
+};
+
+static int __init iproc_gpio_init(void)
+{
+	return platform_driver_probe(&iproc_gpio_driver, iproc_gpio_probe);
+}
+arch_initcall_sync(iproc_gpio_init);
diff --git a/drivers/pinctrl/bcm/pinctrl-nsp-gpio.c b/drivers/pinctrl/bcm/pinctrl-nsp-gpio.c
new file mode 100644
index 0000000..725c36f
--- /dev/null
+++ b/drivers/pinctrl/bcm/pinctrl-nsp-gpio.c
@@ -0,0 +1,749 @@
+/*
+ * Copyright (C) 2015 Broadcom Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * This file contains the Broadcom Northstar Plus (NSP) GPIO driver that
+ * supports the chipCommonA GPIO controller. Basic PINCONF such as bias,
+ * pull up/down, slew and drive strength are also supported in this driver.
+ *
+ * Pins from the chipCommonA  GPIO can be individually muxed to GPIO function,
+ * through the interaction with the NSP IOMUX controller.
+ */
+
+#include <linux/gpio.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/ioport.h>
+#include <linux/kernel.h>
+#include <linux/of_address.h>
+#include <linux/of_device.h>
+#include <linux/of_irq.h>
+#include <linux/pinctrl/pinconf.h>
+#include <linux/pinctrl/pinconf-generic.h>
+#include <linux/pinctrl/pinctrl.h>
+#include <linux/slab.h>
+
+#include "../pinctrl-utils.h"
+
+#define NSP_CHIP_A_INT_STATUS		0x00
+#define NSP_CHIP_A_INT_MASK		0x04
+#define NSP_GPIO_DATA_IN		0x40
+#define NSP_GPIO_DATA_OUT		0x44
+#define NSP_GPIO_OUT_EN			0x48
+#define NSP_GPIO_INT_POLARITY		0x50
+#define NSP_GPIO_INT_MASK		0x54
+#define NSP_GPIO_EVENT			0x58
+#define NSP_GPIO_EVENT_INT_MASK		0x5c
+#define NSP_GPIO_EVENT_INT_POLARITY	0x64
+#define NSP_CHIP_A_GPIO_INT_BIT		0x01
+
+/* I/O parameters offset for chipcommon A GPIO */
+#define NSP_GPIO_DRV_CTRL		0x00
+#define NSP_GPIO_HYSTERESIS_EN		0x10
+#define NSP_GPIO_SLEW_RATE_EN		0x14
+#define NSP_PULL_UP_EN			0x18
+#define NSP_PULL_DOWN_EN		0x1c
+#define GPIO_DRV_STRENGTH_BITS		0x03
+
+/*
+ * nsp GPIO core
+ *
+ * @dev: pointer to device
+ * @base: I/O register base for nsp GPIO controller
+ * @io_ctrl: I/O register base for PINCONF support outside the GPIO block
+ * @gc: GPIO chip
+ * @pctl: pointer to pinctrl_dev
+ * @pctldesc: pinctrl descriptor
+ * @irq_domain: pointer to irq domain
+ * @lock: lock to protect access to I/O registers
+ */
+struct nsp_gpio {
+	struct device *dev;
+	void __iomem *base;
+	void __iomem *io_ctrl;
+	struct gpio_chip gc;
+	struct pinctrl_dev *pctl;
+	struct pinctrl_desc pctldesc;
+	struct irq_domain *irq_domain;
+	spinlock_t lock;
+};
+
+enum base_type {
+	REG,
+	IO_CTRL
+};
+
+static inline struct nsp_gpio *to_nsp_gpio(struct gpio_chip *gc)
+{
+	return container_of(gc, struct nsp_gpio, gc);
+}
+
+/*
+ * Mapping from PINCONF pins to GPIO pins is 1-to-1
+ */
+static inline unsigned nsp_pin_to_gpio(unsigned pin)
+{
+	return pin;
+}
+
+/*
+ *  nsp_set_bit - set or clear one bit (corresponding to the GPIO pin) in a
+ *  nsp GPIO register
+ *
+ *  @nsp_gpio: nsp GPIO device
+ *  @base_type: reg base to modify
+ *  @reg: register offset
+ *  @gpio: GPIO pin
+ *  @set: set or clear
+ */
+static inline void nsp_set_bit(struct nsp_gpio *chip, enum base_type address,
+			       unsigned int reg, unsigned gpio, bool set)
+{
+	u32 val;
+	void __iomem *base_address;
+
+	if (address == IO_CTRL)
+		base_address = chip->io_ctrl;
+	else
+		base_address = chip->base;
+
+	val = readl(base_address + reg);
+	if (set)
+		val |= BIT(gpio);
+	else
+		val &= ~BIT(gpio);
+
+	writel(val, base_address + reg);
+}
+
+/*
+ *  nsp_get_bit - get one bit (corresponding to the GPIO pin) in a
+ *  nsp GPIO register
+ */
+static inline bool nsp_get_bit(struct nsp_gpio *chip, enum base_type address,
+			       unsigned int reg, unsigned gpio)
+{
+	if (address == IO_CTRL)
+		return !!(readl(chip->io_ctrl + reg) & BIT(gpio));
+	else
+		return !!(readl(chip->base + reg) & BIT(gpio));
+}
+
+static irqreturn_t nsp_gpio_irq_handler(int irq, void *data)
+{
+	struct nsp_gpio *chip = (struct nsp_gpio *)data;
+	struct gpio_chip gc = chip->gc;
+	int bit;
+	unsigned long int_bits = 0;
+	u32 int_status;
+
+	/* go through the entire GPIOs and handle all interrupts */
+	int_status = readl(chip->base + NSP_CHIP_A_INT_STATUS);
+	if (int_status & NSP_CHIP_A_GPIO_INT_BIT) {
+		unsigned int event, level;
+
+		/* Get level and edge interrupts */
+		event = readl(chip->base + NSP_GPIO_EVENT_INT_MASK) &
+			      readl(chip->base + NSP_GPIO_EVENT);
+		level = readl(chip->base + NSP_GPIO_DATA_IN) ^
+			      readl(chip->base + NSP_GPIO_INT_POLARITY);
+		level &= readl(chip->base + NSP_GPIO_INT_MASK);
+		int_bits = level | event;
+
+		for_each_set_bit(bit, &int_bits, gc.ngpio) {
+			/*
+			 * Clear the interrupt before invoking the
+			 * handler, so we do not leave any window
+			 */
+			writel(BIT(bit), chip->base + NSP_GPIO_EVENT);
+			generic_handle_irq(
+				irq_linear_revmap(chip->irq_domain, bit));
+		}
+	}
+
+	return  int_bits ? IRQ_HANDLED : IRQ_NONE;
+}
+
+static void nsp_gpio_irq_ack(struct irq_data *d)
+{
+	struct nsp_gpio *chip = irq_data_get_irq_chip_data(d);
+	unsigned gpio = d->hwirq;
+	u32 val = BIT(gpio);
+	u32 trigger_type;
+
+	trigger_type = irq_get_trigger_type(d->irq);
+	if (trigger_type & (IRQ_TYPE_EDGE_FALLING | IRQ_TYPE_EDGE_RISING))
+		nsp_set_bit(chip, REG, NSP_GPIO_EVENT, gpio, val);
+}
+
+/*
+ *  nsp_gpio_irq_set_mask - mask/unmask a GPIO interrupt
+ *
+ *  @d: IRQ chip data
+ *  @unmask: mask/unmask GPIO interrupt
+ */
+static void nsp_gpio_irq_set_mask(struct irq_data *d, bool unmask)
+{
+	struct nsp_gpio *chip = irq_data_get_irq_chip_data(d);
+	unsigned gpio = d->hwirq;
+	u32 trigger_type;
+
+	trigger_type = irq_get_trigger_type(d->irq);
+	if (trigger_type & (IRQ_TYPE_EDGE_FALLING | IRQ_TYPE_EDGE_RISING))
+		nsp_set_bit(chip, REG, NSP_GPIO_EVENT_INT_MASK, gpio, unmask);
+	else
+		nsp_set_bit(chip, REG, NSP_GPIO_INT_MASK, gpio, unmask);
+}
+
+static void nsp_gpio_irq_mask(struct irq_data *d)
+{
+	struct nsp_gpio *chip = irq_data_get_irq_chip_data(d);
+	unsigned long flags;
+
+	spin_lock_irqsave(&chip->lock, flags);
+	nsp_gpio_irq_set_mask(d, false);
+	spin_unlock_irqrestore(&chip->lock, flags);
+}
+
+static void nsp_gpio_irq_unmask(struct irq_data *d)
+{
+	struct nsp_gpio *chip = irq_data_get_irq_chip_data(d);
+	unsigned long flags;
+
+	spin_lock_irqsave(&chip->lock, flags);
+	nsp_gpio_irq_set_mask(d, true);
+	spin_unlock_irqrestore(&chip->lock, flags);
+}
+
+static int nsp_gpio_irq_set_type(struct irq_data *d, unsigned int type)
+{
+	struct nsp_gpio *chip = irq_data_get_irq_chip_data(d);
+	unsigned gpio = d->hwirq;
+	bool level_low;
+	bool falling;
+	unsigned long flags;
+
+	spin_lock_irqsave(&chip->lock, flags);
+	falling = nsp_get_bit(chip, REG, NSP_GPIO_EVENT_INT_POLARITY, gpio);
+	level_low = nsp_get_bit(chip, REG, NSP_GPIO_INT_POLARITY, gpio);
+
+	switch (type & IRQ_TYPE_SENSE_MASK) {
+	case IRQ_TYPE_EDGE_RISING:
+		falling = false;
+		break;
+
+	case IRQ_TYPE_EDGE_FALLING:
+		falling = true;
+		break;
+
+	case IRQ_TYPE_LEVEL_HIGH:
+		level_low = false;
+		break;
+
+	case IRQ_TYPE_LEVEL_LOW:
+		level_low = true;
+		break;
+
+	default:
+		dev_err(chip->dev, "invalid GPIO IRQ type 0x%x\n",
+			type);
+		spin_unlock_irqrestore(&chip->lock, flags);
+		return -EINVAL;
+	}
+
+	nsp_set_bit(chip, REG, NSP_GPIO_EVENT_INT_POLARITY, gpio, falling);
+	nsp_set_bit(chip, REG, NSP_GPIO_INT_POLARITY, gpio, level_low);
+	spin_unlock_irqrestore(&chip->lock, flags);
+
+	dev_dbg(chip->dev, "gpio:%u level_low:%s falling:%s\n", gpio,
+		level_low ? "true" : "false", falling ? "true" : "false");
+	return 0;
+}
+
+static struct irq_chip nsp_gpio_irq_chip = {
+	.name = "gpio-a",
+	.irq_enable = nsp_gpio_irq_unmask,
+	.irq_disable = nsp_gpio_irq_mask,
+	.irq_ack = nsp_gpio_irq_ack,
+	.irq_mask = nsp_gpio_irq_mask,
+	.irq_unmask = nsp_gpio_irq_unmask,
+	.irq_set_type = nsp_gpio_irq_set_type,
+};
+
+/*
+ * Request the nsp IOMUX pinmux controller to mux individual pins to GPIO
+ */
+static int nsp_gpio_request(struct gpio_chip *gc, unsigned offset)
+{
+	unsigned gpio = gc->base + offset;
+
+	return pinctrl_request_gpio(gpio);
+}
+
+static void nsp_gpio_free(struct gpio_chip *gc, unsigned offset)
+{
+	unsigned gpio = gc->base + offset;
+
+	pinctrl_free_gpio(gpio);
+}
+
+static int nsp_gpio_direction_input(struct gpio_chip *gc, unsigned gpio)
+{
+	struct nsp_gpio *chip = to_nsp_gpio(gc);
+	unsigned long flags;
+
+	spin_lock_irqsave(&chip->lock, flags);
+	nsp_set_bit(chip, REG, NSP_GPIO_OUT_EN, gpio, false);
+	spin_unlock_irqrestore(&chip->lock, flags);
+
+	dev_dbg(chip->dev, "gpio:%u set input\n", gpio);
+	return 0;
+}
+
+static int nsp_gpio_direction_output(struct gpio_chip *gc, unsigned gpio,
+				     int val)
+{
+	struct nsp_gpio *chip = to_nsp_gpio(gc);
+	unsigned long flags;
+
+	spin_lock_irqsave(&chip->lock, flags);
+	nsp_set_bit(chip, REG, NSP_GPIO_OUT_EN, gpio, true);
+	nsp_set_bit(chip, REG, NSP_GPIO_DATA_OUT, gpio, !!(val));
+	spin_unlock_irqrestore(&chip->lock, flags);
+
+	dev_dbg(chip->dev, "gpio:%u set output, value:%d\n", gpio, val);
+	return 0;
+}
+
+static void nsp_gpio_set(struct gpio_chip *gc, unsigned gpio, int val)
+{
+	struct nsp_gpio *chip = to_nsp_gpio(gc);
+	unsigned long flags;
+
+	spin_lock_irqsave(&chip->lock, flags);
+	nsp_set_bit(chip, REG, NSP_GPIO_DATA_OUT, gpio, !!(val));
+	spin_unlock_irqrestore(&chip->lock, flags);
+
+	dev_dbg(chip->dev, "gpio:%u set, value:%d\n", gpio, val);
+}
+
+static int nsp_gpio_get(struct gpio_chip *gc, unsigned gpio)
+{
+	struct nsp_gpio *chip = to_nsp_gpio(gc);
+
+	return !!(readl(chip->base + NSP_GPIO_DATA_IN) & BIT(gpio));
+}
+
+static int nsp_gpio_to_irq(struct gpio_chip *gc, unsigned offset)
+{
+	struct nsp_gpio *chip = to_nsp_gpio(gc);
+
+	return irq_linear_revmap(chip->irq_domain, offset);
+}
+
+static int nsp_get_groups_count(struct pinctrl_dev *pctldev)
+{
+	return 1;
+}
+
+/*
+ * Only one group: "gpio_grp", since this local pinctrl device only performs
+ * GPIO specific PINCONF configurations
+ */
+static const char *nsp_get_group_name(struct pinctrl_dev *pctldev,
+				      unsigned selector)
+{
+	return "gpio_grp";
+}
+
+static const struct pinctrl_ops nsp_pctrl_ops = {
+	.get_groups_count = nsp_get_groups_count,
+	.get_group_name = nsp_get_group_name,
+	.dt_node_to_map = pinconf_generic_dt_node_to_map_pin,
+	.dt_free_map = pinctrl_utils_dt_free_map,
+};
+
+static int nsp_gpio_set_slew(struct nsp_gpio *chip, unsigned gpio, u16 slew)
+{
+	if (slew)
+		nsp_set_bit(chip, IO_CTRL, NSP_GPIO_SLEW_RATE_EN, gpio, true);
+	else
+		nsp_set_bit(chip, IO_CTRL, NSP_GPIO_SLEW_RATE_EN, gpio, false);
+
+	return 0;
+}
+
+static int nsp_gpio_set_pull(struct nsp_gpio *chip, unsigned gpio,
+			     bool pull_up, bool pull_down)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&chip->lock, flags);
+	nsp_set_bit(chip, IO_CTRL, NSP_PULL_DOWN_EN, gpio, pull_down);
+	nsp_set_bit(chip, IO_CTRL, NSP_PULL_UP_EN, gpio, pull_up);
+	spin_unlock_irqrestore(&chip->lock, flags);
+
+	dev_dbg(chip->dev, "gpio:%u set pullup:%d pulldown: %d\n",
+		gpio, pull_up, pull_down);
+	return 0;
+}
+
+static void nsp_gpio_get_pull(struct nsp_gpio *chip, unsigned gpio,
+			      bool *pull_up, bool *pull_down)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&chip->lock, flags);
+	*pull_up = nsp_get_bit(chip, IO_CTRL, NSP_PULL_UP_EN, gpio);
+	*pull_down = nsp_get_bit(chip, IO_CTRL, NSP_PULL_DOWN_EN, gpio);
+	spin_unlock_irqrestore(&chip->lock, flags);
+}
+
+static int nsp_gpio_set_strength(struct nsp_gpio *chip, unsigned gpio,
+				 u16 strength)
+{
+	u32 offset, shift, i;
+	u32 val;
+	unsigned long flags;
+
+	/* make sure drive strength is supported */
+	if (strength < 2 || strength > 16 || (strength % 2))
+		return -ENOTSUPP;
+
+	shift = gpio;
+	offset = NSP_GPIO_DRV_CTRL;
+	dev_dbg(chip->dev, "gpio:%u set drive strength:%d mA\n", gpio,
+		strength);
+	spin_lock_irqsave(&chip->lock, flags);
+	strength = (strength / 2) - 1;
+	for (i = GPIO_DRV_STRENGTH_BITS; i > 0; i--) {
+		val = readl(chip->io_ctrl + offset);
+		val &= ~BIT(shift);
+		val |= ((strength >> (i-1)) & 0x1) << shift;
+		writel(val, chip->io_ctrl + offset);
+		offset += 4;
+	}
+	spin_unlock_irqrestore(&chip->lock, flags);
+
+	return 0;
+}
+
+static int nsp_gpio_get_strength(struct nsp_gpio *chip, unsigned gpio,
+				 u16 *strength)
+{
+	unsigned int offset, shift;
+	u32 val;
+	unsigned long flags;
+	int i;
+
+	offset = NSP_GPIO_DRV_CTRL;
+	shift = gpio;
+
+	spin_lock_irqsave(&chip->lock, flags);
+	*strength = 0;
+	for (i = (GPIO_DRV_STRENGTH_BITS - 1); i >= 0; i--) {
+		val = readl(chip->io_ctrl + offset) & BIT(shift);
+		val >>= shift;
+		*strength += (val << i);
+		offset += 4;
+	}
+
+	/* convert to mA */
+	*strength = (*strength + 1) * 2;
+	spin_unlock_irqrestore(&chip->lock, flags);
+
+	return 0;
+}
+
+int nsp_pin_config_group_get(struct pinctrl_dev *pctldev, unsigned selector,
+			     unsigned long *config)
+{
+	return 0;
+}
+
+int nsp_pin_config_group_set(struct pinctrl_dev *pctldev, unsigned selector,
+			     unsigned long *configs, unsigned num_configs)
+{
+	return 0;
+}
+
+static int nsp_pin_config_get(struct pinctrl_dev *pctldev, unsigned pin,
+			      unsigned long *config)
+{
+	struct nsp_gpio *chip = pinctrl_dev_get_drvdata(pctldev);
+	enum pin_config_param param = pinconf_to_config_param(*config);
+	unsigned int gpio;
+	u16 arg = 0;
+	bool pull_up, pull_down;
+	int ret;
+
+	gpio = nsp_pin_to_gpio(pin);
+	switch (param) {
+	case PIN_CONFIG_BIAS_DISABLE:
+		nsp_gpio_get_pull(chip, gpio, &pull_up, &pull_down);
+		if ((pull_up == false) && (pull_down == false))
+			return 0;
+		else
+			return -EINVAL;
+
+	case PIN_CONFIG_BIAS_PULL_UP:
+		nsp_gpio_get_pull(chip, gpio, &pull_up, &pull_down);
+		if (pull_up)
+			return 0;
+		else
+			return -EINVAL;
+
+	case PIN_CONFIG_BIAS_PULL_DOWN:
+		nsp_gpio_get_pull(chip, gpio, &pull_up, &pull_down);
+		if (pull_down)
+			return 0;
+		else
+			return -EINVAL;
+
+	case PIN_CONFIG_DRIVE_STRENGTH:
+		ret = nsp_gpio_get_strength(chip, gpio, &arg);
+		if (ret)
+			return ret;
+		*config = pinconf_to_config_packed(param, arg);
+		return 0;
+
+	default:
+		return -ENOTSUPP;
+	}
+}
+
+static int nsp_pin_config_set(struct pinctrl_dev *pctldev, unsigned pin,
+			      unsigned long *configs, unsigned num_configs)
+{
+	struct nsp_gpio *chip = pinctrl_dev_get_drvdata(pctldev);
+	enum pin_config_param param;
+	u16 arg;
+	unsigned int i, gpio;
+	int ret = -ENOTSUPP;
+
+	gpio = nsp_pin_to_gpio(pin);
+	for (i = 0; i < num_configs; i++) {
+		param = pinconf_to_config_param(configs[i]);
+		arg = pinconf_to_config_argument(configs[i]);
+
+		switch (param) {
+		case PIN_CONFIG_BIAS_DISABLE:
+			ret = nsp_gpio_set_pull(chip, gpio, false, false);
+			if (ret < 0)
+				goto out;
+			break;
+
+		case PIN_CONFIG_BIAS_PULL_UP:
+			ret = nsp_gpio_set_pull(chip, gpio, true, false);
+			if (ret < 0)
+				goto out;
+			break;
+
+		case PIN_CONFIG_BIAS_PULL_DOWN:
+			ret = nsp_gpio_set_pull(chip, gpio, false, true);
+			if (ret < 0)
+				goto out;
+			break;
+
+		case PIN_CONFIG_DRIVE_STRENGTH:
+			ret = nsp_gpio_set_strength(chip, gpio, arg);
+			if (ret < 0)
+				goto out;
+			break;
+
+		case PIN_CONFIG_SLEW_RATE:
+			ret = nsp_gpio_set_slew(chip, gpio, arg);
+			if (ret < 0)
+				goto out;
+			break;
+
+		default:
+			dev_err(chip->dev, "invalid configuration\n");
+			return -ENOTSUPP;
+		}
+	}
+
+out:
+	return ret;
+}
+
+static const struct pinconf_ops nsp_pconf_ops = {
+	.is_generic = true,
+	.pin_config_get = nsp_pin_config_get,
+	.pin_config_set = nsp_pin_config_set,
+	.pin_config_group_get = nsp_pin_config_group_get,
+	.pin_config_group_set = nsp_pin_config_group_set,
+};
+
+/*
+ * NSP GPIO controller supports some PINCONF related configurations such as
+ * pull up, pull down, slew and drive strength, when the pin is configured
+ * to GPIO.
+ *
+ * Here a local pinctrl device is created with simple 1-to-1 pin mapping to the
+ * local GPIO pins
+ */
+static int nsp_gpio_register_pinconf(struct nsp_gpio *chip)
+{
+	struct pinctrl_desc *pctldesc = &chip->pctldesc;
+	struct pinctrl_pin_desc *pins;
+	struct gpio_chip *gc = &chip->gc;
+	int i;
+
+	pins = devm_kcalloc(chip->dev, gc->ngpio, sizeof(*pins), GFP_KERNEL);
+	if (!pins)
+		return -ENOMEM;
+	for (i = 0; i < gc->ngpio; i++) {
+		pins[i].number = i;
+		pins[i].name = devm_kasprintf(chip->dev, GFP_KERNEL,
+					      "gpio-%d", i);
+		if (!pins[i].name)
+			return -ENOMEM;
+	}
+	pctldesc->name = dev_name(chip->dev);
+	pctldesc->pctlops = &nsp_pctrl_ops;
+	pctldesc->pins = pins;
+	pctldesc->npins = gc->ngpio;
+	pctldesc->confops = &nsp_pconf_ops;
+
+	chip->pctl = pinctrl_register(pctldesc, chip->dev, chip);
+	if (IS_ERR(chip->pctl)) {
+		dev_err(chip->dev, "unable to register pinctrl device\n");
+		return PTR_ERR(chip->pctl);
+	}
+
+	return 0;
+}
+
+static const struct of_device_id nsp_gpio_of_match[] = {
+	{.compatible = "brcm,nsp-gpio-a",},
+	{}
+};
+
+static int nsp_gpio_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct resource *res;
+	struct nsp_gpio *chip;
+	struct gpio_chip *gc;
+	u32 val, count;
+	int irq, ret;
+
+	if (of_property_read_u32(pdev->dev.of_node, "ngpios", &val)) {
+		dev_err(&pdev->dev, "Missing ngpios OF property\n");
+		return -ENODEV;
+	}
+
+	chip = devm_kzalloc(dev, sizeof(*chip), GFP_KERNEL);
+	if (!chip)
+		return -ENOMEM;
+
+	chip->dev = dev;
+	platform_set_drvdata(pdev, chip);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	chip->base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(chip->base)) {
+		dev_err(dev, "unable to map I/O memory\n");
+		return PTR_ERR(chip->base);
+	}
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	chip->io_ctrl = devm_ioremap_resource(dev, res);
+	if (IS_ERR(chip->io_ctrl)) {
+		dev_err(dev, "unable to map I/O memory\n");
+		return PTR_ERR(chip->io_ctrl);
+	}
+
+	spin_lock_init(&chip->lock);
+	gc = &chip->gc;
+	gc->base = -1;
+	gc->can_sleep = false;
+	gc->ngpio = val;
+	gc->label = dev_name(dev);
+	gc->dev = dev;
+	gc->of_node = dev->of_node;
+	gc->request = nsp_gpio_request;
+	gc->free = nsp_gpio_free;
+	gc->direction_input = nsp_gpio_direction_input;
+	gc->direction_output = nsp_gpio_direction_output;
+	gc->set = nsp_gpio_set;
+	gc->get = nsp_gpio_get;
+	gc->to_irq = nsp_gpio_to_irq;
+
+	/* optional GPIO interrupt support */
+	irq = platform_get_irq(pdev, 0);
+	if (irq > 0) {
+		/* Create irq domain so that each pin can be assigned an IRQ.*/
+		chip->irq_domain = irq_domain_add_linear(gc->of_node, gc->ngpio,
+							 &irq_domain_simple_ops,
+							 chip);
+		if (!chip->irq_domain) {
+			dev_err(&pdev->dev, "Couldn't allocate IRQ domain\n");
+			return -ENXIO;
+		}
+
+		/* Map each gpio to an IRQ and set the handler for gpiolib. */
+		for (count = 0; count < gc->ngpio; count++) {
+			int irq = irq_create_mapping(chip->irq_domain, count);
+
+			irq_set_chip_and_handler(irq, &nsp_gpio_irq_chip,
+						 handle_simple_irq);
+			irq_set_chip_data(irq, chip);
+		}
+
+		/* Install ISR for this GPIO controller. */
+		ret = devm_request_irq(&pdev->dev, irq, nsp_gpio_irq_handler,
+				       IRQF_SHARED, "gpio-a", chip);
+		if (ret) {
+			dev_err(&pdev->dev, "Unable to request IRQ%d: %d\n",
+				irq, ret);
+			goto err_rm_gpiochip;
+		}
+
+		val = readl(chip->base + NSP_CHIP_A_INT_MASK);
+		val = val | NSP_CHIP_A_GPIO_INT_BIT;
+		writel(val, (chip->base + NSP_CHIP_A_INT_MASK));
+	}
+
+	ret = gpiochip_add(gc);
+	if (ret < 0) {
+		dev_err(dev, "unable to add GPIO chip\n");
+		return ret;
+	}
+
+	ret = nsp_gpio_register_pinconf(chip);
+	if (ret) {
+		dev_err(dev, "unable to register pinconf\n");
+		goto err_rm_gpiochip;
+	}
+
+	return 0;
+
+err_rm_gpiochip:
+	gpiochip_remove(gc);
+
+	return ret;
+}
+
+static struct platform_driver nsp_gpio_driver = {
+	.driver = {
+		.name = "nsp-gpio-a",
+		.of_match_table = nsp_gpio_of_match,
+	},
+	.probe = nsp_gpio_probe,
+};
+
+static int __init nsp_gpio_init(void)
+{
+	return platform_driver_probe(&nsp_gpio_driver, nsp_gpio_probe);
+}
+arch_initcall_sync(nsp_gpio_init);
diff --git a/drivers/pinctrl/berlin/Makefile b/drivers/pinctrl/berlin/Makefile
index 06f94029..6f641ce 100644
--- a/drivers/pinctrl/berlin/Makefile
+++ b/drivers/pinctrl/berlin/Makefile
@@ -1,4 +1,4 @@
-obj-$(CONFIG_PINCTRL_BERLIN)		+= berlin.o
+obj-y					+= berlin.o
 obj-$(CONFIG_PINCTRL_BERLIN_BG2)	+= berlin-bg2.o
 obj-$(CONFIG_PINCTRL_BERLIN_BG2CD)	+= berlin-bg2cd.o
 obj-$(CONFIG_PINCTRL_BERLIN_BG2Q)	+= berlin-bg2q.o
diff --git a/drivers/pinctrl/mediatek/pinctrl-mt8127.c b/drivers/pinctrl/mediatek/pinctrl-mt8127.c
index b317b0b..98e0beb 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mt8127.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mt8127.c
@@ -351,7 +351,7 @@
 	return platform_driver_register(&mtk_pinctrl_driver);
 }
 
-module_init(mtk_pinctrl_init);
+arch_initcall(mtk_pinctrl_init);
 
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("MediaTek MT8127 Pinctrl Driver");
diff --git a/drivers/pinctrl/mediatek/pinctrl-mt8135.c b/drivers/pinctrl/mediatek/pinctrl-mt8135.c
index 404f117..1c153b8 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mt8135.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mt8135.c
@@ -366,7 +366,7 @@
 	return platform_driver_register(&mtk_pinctrl_driver);
 }
 
-module_init(mtk_pinctrl_init);
+arch_initcall(mtk_pinctrl_init);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("MediaTek Pinctrl Driver");
diff --git a/drivers/pinctrl/mediatek/pinctrl-mt8173.c b/drivers/pinctrl/mediatek/pinctrl-mt8173.c
index ad27184..a62514e 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mt8173.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mt8173.c
@@ -394,7 +394,7 @@
 	return platform_driver_register(&mtk_pinctrl_driver);
 }
 
-module_init(mtk_pinctrl_init);
+arch_initcall(mtk_pinctrl_init);
 
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("MediaTek Pinctrl Driver");
diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
index 5c71727..e22cbaf 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
@@ -509,6 +509,9 @@
 
 	err = pinconf_generic_parse_dt_config(node, pctldev, &configs,
 		&num_configs);
+	if (err)
+		return err;
+
 	if (num_configs)
 		has_config = 1;
 
@@ -520,21 +523,23 @@
 	if (has_config && num_pins >= 1)
 		maps_per_pin++;
 
-	if (!num_pins || !maps_per_pin)
-		return -EINVAL;
+	if (!num_pins || !maps_per_pin) {
+		err = -EINVAL;
+		goto exit;
+	}
 
 	reserve = num_pins * maps_per_pin;
 
 	err = pinctrl_utils_reserve_map(pctldev, map,
 			reserved_maps, num_maps, reserve);
 	if (err < 0)
-		goto fail;
+		goto exit;
 
 	for (i = 0; i < num_pins; i++) {
 		err = of_property_read_u32_index(node, "pinmux",
 				i, &pinfunc);
 		if (err)
-			goto fail;
+			goto exit;
 
 		pin = MTK_GET_PIN_NO(pinfunc);
 		func = MTK_GET_PIN_FUNC(pinfunc);
@@ -543,20 +548,21 @@
 				func >= ARRAY_SIZE(mtk_gpio_functions)) {
 			dev_err(pctl->dev, "invalid pins value.\n");
 			err = -EINVAL;
-			goto fail;
+			goto exit;
 		}
 
 		grp = mtk_pctrl_find_group_by_pin(pctl, pin);
 		if (!grp) {
 			dev_err(pctl->dev, "unable to match pin %d to group\n",
 					pin);
-			return -EINVAL;
+			err = -EINVAL;
+			goto exit;
 		}
 
 		err = mtk_pctrl_dt_node_to_map_func(pctl, pin, func, grp, map,
 				reserved_maps, num_maps);
 		if (err < 0)
-			goto fail;
+			goto exit;
 
 		if (has_config) {
 			err = pinctrl_utils_add_map_configs(pctldev, map,
@@ -564,13 +570,14 @@
 					configs, num_configs,
 					PIN_MAP_TYPE_CONFIGS_GROUP);
 			if (err < 0)
-				goto fail;
+				goto exit;
 		}
 	}
 
-	return 0;
+	err = 0;
 
-fail:
+exit:
+	kfree(configs);
 	return err;
 }
 
@@ -591,6 +598,7 @@
 				&reserved_maps, num_maps);
 		if (ret < 0) {
 			pinctrl_utils_dt_free_map(pctldev, *map, *num_maps);
+			of_node_put(np);
 			return ret;
 		}
 	}
diff --git a/drivers/pinctrl/mvebu/Makefile b/drivers/pinctrl/mvebu/Makefile
index 554d8af..18270cd 100644
--- a/drivers/pinctrl/mvebu/Makefile
+++ b/drivers/pinctrl/mvebu/Makefile
@@ -1,4 +1,4 @@
-obj-$(CONFIG_PINCTRL_MVEBU)	+= pinctrl-mvebu.o
+obj-y				+= pinctrl-mvebu.o
 obj-$(CONFIG_PINCTRL_DOVE)	+= pinctrl-dove.o
 obj-$(CONFIG_PINCTRL_KIRKWOOD)	+= pinctrl-kirkwood.o
 obj-$(CONFIG_PINCTRL_ARMADA_370) += pinctrl-armada-370.o
diff --git a/drivers/pinctrl/mvebu/pinctrl-mvebu.c b/drivers/pinctrl/mvebu/pinctrl-mvebu.c
index 77d2221..e4d4738 100644
--- a/drivers/pinctrl/mvebu/pinctrl-mvebu.c
+++ b/drivers/pinctrl/mvebu/pinctrl-mvebu.c
@@ -663,28 +663,20 @@
 	/* assign mpp modes to groups */
 	for (n = 0; n < soc->nmodes; n++) {
 		struct mvebu_mpp_mode *mode = &soc->modes[n];
-		struct mvebu_pinctrl_group *grp =
-			mvebu_pinctrl_find_group_by_pid(pctl, mode->pid);
+		struct mvebu_mpp_ctrl_setting *set = &mode->settings[0];
+		struct mvebu_pinctrl_group *grp;
 		unsigned num_settings;
 
-		if (!grp) {
-			dev_warn(&pdev->dev, "unknown pinctrl group %d\n",
-				mode->pid);
-			continue;
-		}
-
-		for (num_settings = 0; ;) {
-			struct mvebu_mpp_ctrl_setting *set =
-				&mode->settings[num_settings];
-
+		for (num_settings = 0; ; set++) {
 			if (!set->name)
 				break;
-			num_settings++;
 
 			/* skip unsupported settings for this variant */
 			if (pctl->variant && !(pctl->variant & set->variant))
 				continue;
 
+			num_settings++;
+
 			/* find gpio/gpo/gpi settings */
 			if (strcmp(set->name, "gpio") == 0)
 				set->flags = MVEBU_SETTING_GPI |
@@ -695,6 +687,17 @@
 				set->flags = MVEBU_SETTING_GPI;
 		}
 
+		/* skip modes with no settings for this variant */
+		if (!num_settings)
+			continue;
+
+		grp = mvebu_pinctrl_find_group_by_pid(pctl, mode->pid);
+		if (!grp) {
+			dev_warn(&pdev->dev, "unknown pinctrl group %d\n",
+				mode->pid);
+			continue;
+		}
+
 		grp->settings = mode->settings;
 		grp->num_settings = num_settings;
 	}
diff --git a/drivers/pinctrl/pinconf-generic.c b/drivers/pinctrl/pinconf-generic.c
index 099a344..79e6159 100644
--- a/drivers/pinctrl/pinconf-generic.c
+++ b/drivers/pinctrl/pinconf-generic.c
@@ -220,6 +220,7 @@
  * parse the config properties into generic pinconfig values.
  * @np: node containing the pinconfig properties
  * @configs: array with nconfigs entries containing the generic pinconf values
+ *           must be freed when no longer necessary.
  * @nconfigs: umber of configurations
  */
 int pinconf_generic_parse_dt_config(struct device_node *np,
diff --git a/drivers/pinctrl/pinctrl-adi2.c b/drivers/pinctrl/pinctrl-adi2.c
index fd342df..8e9e8ea 100644
--- a/drivers/pinctrl/pinctrl-adi2.c
+++ b/drivers/pinctrl/pinctrl-adi2.c
@@ -1102,32 +1102,24 @@
 	},
 };
 
+static struct platform_driver * const drivers[] = {
+	&adi_pinctrl_driver,
+	&adi_gpio_pint_driver,
+	&adi_gpio_driver,
+};
+
 static int __init adi_pinctrl_setup(void)
 {
 	int ret;
 
-	ret = platform_driver_register(&adi_pinctrl_driver);
+	ret = platform_register_drivers(drivers, ARRAY_SIZE(drivers));
 	if (ret)
 		return ret;
 
-	ret = platform_driver_register(&adi_gpio_pint_driver);
-	if (ret)
-		goto pint_error;
-
-	ret = platform_driver_register(&adi_gpio_driver);
-	if (ret)
-		goto gpio_error;
-
 #ifdef CONFIG_PM
 	register_syscore_ops(&gpio_pm_syscore_ops);
 #endif
-	return ret;
-gpio_error:
-	platform_driver_unregister(&adi_gpio_pint_driver);
-pint_error:
-	platform_driver_unregister(&adi_pinctrl_driver);
-
-	return ret;
+	return 0;
 }
 arch_initcall(adi_pinctrl_setup);
 
diff --git a/drivers/pinctrl/pinctrl-at91-pio4.c b/drivers/pinctrl/pinctrl-at91-pio4.c
index 33edd07..d5bdceb 100644
--- a/drivers/pinctrl/pinctrl-at91-pio4.c
+++ b/drivers/pinctrl/pinctrl-at91-pio4.c
@@ -500,7 +500,8 @@
 	if (!num_pins) {
 		dev_err(pctldev->dev, "no pins found in node %s\n",
 			of_node_full_name(np));
-		return -EINVAL;
+		ret = -EINVAL;
+		goto exit;
 	}
 
 	/*
@@ -514,19 +515,19 @@
 	ret = pinctrl_utils_reserve_map(pctldev, map, reserved_maps, num_maps,
 					reserve);
 	if (ret < 0)
-		return ret;
+		goto exit;
 
 	for (i = 0; i < num_pins; i++) {
 		const char *group, *func;
 
 		ret = of_property_read_u32_index(np, "pinmux", i, &pinfunc);
 		if (ret)
-			return ret;
+			goto exit;
 
 		ret = atmel_pctl_xlate_pinfunc(pctldev, np, pinfunc, &group,
 					       &func);
 		if (ret)
-			return ret;
+			goto exit;
 
 		pinctrl_utils_add_map_mux(pctldev, map, reserved_maps, num_maps,
 					  group, func);
@@ -537,11 +538,13 @@
 					configs, num_configs,
 					PIN_MAP_TYPE_CONFIGS_GROUP);
 			if (ret < 0)
-				return ret;
+				goto exit;
 		}
 	}
 
-	return 0;
+exit:
+	kfree(configs);
+	return ret;
 }
 
 static int atmel_pctl_dt_node_to_map(struct pinctrl_dev *pctldev,
@@ -1000,7 +1003,7 @@
 		atmel_pioctrl->irqs[i] = res->start;
 		irq_set_chained_handler(res->start, atmel_gpio_irq_handler);
 		irq_set_handler_data(res->start, atmel_pioctrl);
-		dev_dbg(dev, "bank %i: hwirq=%u\n", i, res->start);
+		dev_dbg(dev, "bank %i: irq=%pr\n", i, res);
 	}
 
 	atmel_pioctrl->irq_domain = irq_domain_add_linear(dev->of_node,
diff --git a/drivers/pinctrl/pinctrl-at91.c b/drivers/pinctrl/pinctrl-at91.c
index 0d2fc0c..47b625b 100644
--- a/drivers/pinctrl/pinctrl-at91.c
+++ b/drivers/pinctrl/pinctrl-at91.c
@@ -1828,20 +1828,20 @@
 	.remove = at91_pinctrl_remove,
 };
 
+static struct platform_driver * const drivers[] = {
+	&at91_gpio_driver,
+	&at91_pinctrl_driver,
+};
+
 static int __init at91_pinctrl_init(void)
 {
-	int ret;
-
-	ret = platform_driver_register(&at91_gpio_driver);
-	if (ret)
-		return ret;
-	return platform_driver_register(&at91_pinctrl_driver);
+	return platform_register_drivers(drivers, ARRAY_SIZE(drivers));
 }
 arch_initcall(at91_pinctrl_init);
 
 static void __exit at91_pinctrl_exit(void)
 {
-	platform_driver_unregister(&at91_pinctrl_driver);
+	platform_unregister_drivers(drivers, ARRAY_SIZE(drivers));
 }
 
 module_exit(at91_pinctrl_exit);
diff --git a/drivers/pinctrl/pinctrl-lantiq.h b/drivers/pinctrl/pinctrl-lantiq.h
index eb89ba0..e137d13 100644
--- a/drivers/pinctrl/pinctrl-lantiq.h
+++ b/drivers/pinctrl/pinctrl-lantiq.h
@@ -162,6 +162,14 @@
 	GPIO53,
 	GPIO54,
 	GPIO55,
+	GPIO56,
+	GPIO57,
+	GPIO58,
+	GPIO59,
+	GPIO60, /* 60 */
+	GPIO61,
+	GPIO62,
+	GPIO63,
 
 	GPIO64,
 	GPIO65,
diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c
index a065112..9128826 100644
--- a/drivers/pinctrl/pinctrl-rockchip.c
+++ b/drivers/pinctrl/pinctrl-rockchip.c
@@ -614,6 +614,40 @@
 	}
 }
 
+#define RK3228_PULL_OFFSET		0x100
+
+static void rk3228_calc_pull_reg_and_bit(struct rockchip_pin_bank *bank,
+				    int pin_num, struct regmap **regmap,
+				    int *reg, u8 *bit)
+{
+	struct rockchip_pinctrl *info = bank->drvdata;
+
+	*regmap = info->regmap_base;
+	*reg = RK3228_PULL_OFFSET;
+	*reg += bank->bank_num * RK3188_PULL_BANK_STRIDE;
+	*reg += ((pin_num / RK3188_PULL_PINS_PER_REG) * 4);
+
+	*bit = (pin_num % RK3188_PULL_PINS_PER_REG);
+	*bit *= RK3188_PULL_BITS_PER_PIN;
+}
+
+#define RK3228_DRV_GRF_OFFSET		0x200
+
+static void rk3228_calc_drv_reg_and_bit(struct rockchip_pin_bank *bank,
+				    int pin_num, struct regmap **regmap,
+				    int *reg, u8 *bit)
+{
+	struct rockchip_pinctrl *info = bank->drvdata;
+
+	*regmap = info->regmap_base;
+	*reg = RK3228_DRV_GRF_OFFSET;
+	*reg += bank->bank_num * RK3288_DRV_BANK_STRIDE;
+	*reg += ((pin_num / RK3288_DRV_PINS_PER_REG) * 4);
+
+	*bit = (pin_num % RK3288_DRV_PINS_PER_REG);
+	*bit *= RK3288_DRV_BITS_PER_PIN;
+}
+
 #define RK3368_PULL_GRF_OFFSET		0x100
 #define RK3368_PULL_PMU_OFFSET		0x10
 
@@ -1258,8 +1292,10 @@
 		func->groups[i] = child->name;
 		grp = &info->groups[grp_index++];
 		ret = rockchip_pinctrl_parse_groups(child, grp, info, i++);
-		if (ret)
+		if (ret) {
+			of_node_put(child);
 			return ret;
+		}
 	}
 
 	return 0;
@@ -1304,6 +1340,7 @@
 		ret = rockchip_pinctrl_parse_functions(child, info, i++);
 		if (ret) {
 			dev_err(&pdev->dev, "failed to parse function\n");
+			of_node_put(child);
 			return ret;
 		}
 	}
@@ -2143,6 +2180,23 @@
 		.pull_calc_reg		= rk3188_calc_pull_reg_and_bit,
 };
 
+static struct rockchip_pin_bank rk3228_pin_banks[] = {
+	PIN_BANK(0, 32, "gpio0"),
+	PIN_BANK(1, 32, "gpio1"),
+	PIN_BANK(2, 32, "gpio2"),
+	PIN_BANK(3, 32, "gpio3"),
+};
+
+static struct rockchip_pin_ctrl rk3228_pin_ctrl = {
+		.pin_banks		= rk3228_pin_banks,
+		.nr_banks		= ARRAY_SIZE(rk3228_pin_banks),
+		.label			= "RK3228-GPIO",
+		.type			= RK3288,
+		.grf_mux_offset		= 0x0,
+		.pull_calc_reg		= rk3228_calc_pull_reg_and_bit,
+		.drv_calc_reg		= rk3228_calc_drv_reg_and_bit,
+};
+
 static struct rockchip_pin_bank rk3288_pin_banks[] = {
 	PIN_BANK_IOMUX_FLAGS(0, 24, "gpio0", IOMUX_SOURCE_PMU,
 					     IOMUX_SOURCE_PMU,
@@ -2220,6 +2274,8 @@
 		.data = (void *)&rk3066b_pin_ctrl },
 	{ .compatible = "rockchip,rk3188-pinctrl",
 		.data = (void *)&rk3188_pin_ctrl },
+	{ .compatible = "rockchip,rk3228-pinctrl",
+		.data = (void *)&rk3228_pin_ctrl },
 	{ .compatible = "rockchip,rk3288-pinctrl",
 		.data = (void *)&rk3288_pin_ctrl },
 	{ .compatible = "rockchip,rk3368-pinctrl",
diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c
index ef04b96..d24e5f1d 100644
--- a/drivers/pinctrl/pinctrl-single.c
+++ b/drivers/pinctrl/pinctrl-single.c
@@ -1484,10 +1484,7 @@
 static void pcs_free_resources(struct pcs_device *pcs)
 {
 	pcs_irq_free(pcs);
-
-	if (pcs->pctl)
-		pinctrl_unregister(pcs->pctl);
-
+	pinctrl_unregister(pcs->pctl);
 	pcs_free_funcs(pcs);
 	pcs_free_pingroups(pcs);
 }
diff --git a/drivers/pinctrl/pinctrl-tegra-xusb.c b/drivers/pinctrl/pinctrl-tegra-xusb.c
index 84a43e6..bd3aa5a 100644
--- a/drivers/pinctrl/pinctrl-tegra-xusb.c
+++ b/drivers/pinctrl/pinctrl-tegra-xusb.c
@@ -253,8 +253,10 @@
 		err = tegra_xusb_padctl_parse_subnode(padctl, np, maps,
 						      &reserved_maps,
 						      num_maps);
-		if (err < 0)
+		if (err < 0) {
+			of_node_put(np);
 			return err;
+		}
 	}
 
 	return 0;
diff --git a/drivers/pinctrl/pinctrl-tegra.c b/drivers/pinctrl/pinctrl-tegra.c
index 0fd7fd2..9da4da2 100644
--- a/drivers/pinctrl/pinctrl-tegra.c
+++ b/drivers/pinctrl/pinctrl-tegra.c
@@ -217,6 +217,7 @@
 		if (ret < 0) {
 			pinctrl_utils_dt_free_map(pctldev, *map,
 				*num_maps);
+			of_node_put(np);
 			return ret;
 		}
 	}
diff --git a/drivers/pinctrl/pinctrl-xway.c b/drivers/pinctrl/pinctrl-xway.c
index ae724bd..7db7469 100644
--- a/drivers/pinctrl/pinctrl-xway.c
+++ b/drivers/pinctrl/pinctrl-xway.c
@@ -7,6 +7,7 @@
  *  publishhed by the Free Software Foundation.
  *
  *  Copyright (C) 2012 John Crispin <blogic@openwrt.org>
+ *  Copyright (C) 2015 Martin Schiller <mschiller@tdt.de>
  */
 
 #include <linux/err.h>
@@ -24,7 +25,7 @@
 
 #include <lantiq_soc.h>
 
-/* we have 3 1/2 banks of 16 bit each */
+/* we have up to 4 banks of 16 bit each */
 #define PINS			16
 #define PORT3			3
 #define PORT(x)			(x / PINS)
@@ -35,7 +36,7 @@
 #define MUX_ALT1	0x2
 
 /*
- * each bank has this offset apart from the 1/2 bank that is mixed into the
+ * each bank has this offset apart from the 4th bank that is mixed into the
  * other 3 ranges
  */
 #define REG_OFF			0x30
@@ -51,7 +52,7 @@
 #define GPIO_PUDSEL(p)		(GPIO_BASE(p) + 0x1c)
 #define GPIO_PUDEN(p)		(GPIO_BASE(p) + 0x20)
 
-/* the 1/2 port needs special offsets for some registers */
+/* the 4th port needs special offsets for some registers */
 #define GPIO3_OD		(GPIO_BASE(0) + 0x24)
 #define GPIO3_PUDSEL		(GPIO_BASE(0) + 0x28)
 #define GPIO3_PUDEN		(GPIO_BASE(0) + 0x2C)
@@ -80,17 +81,18 @@
 #define FUNC_MUX(f, m)		\
 	{ .func = f, .mux = XWAY_MUX_##m, }
 
-#define XWAY_MAX_PIN		32
-#define XR9_MAX_PIN		56
-
 enum xway_mux {
 	XWAY_MUX_GPIO = 0,
 	XWAY_MUX_SPI,
 	XWAY_MUX_ASC,
+	XWAY_MUX_USIF,
 	XWAY_MUX_PCI,
+	XWAY_MUX_CBUS,
 	XWAY_MUX_CGU,
 	XWAY_MUX_EBU,
+	XWAY_MUX_EBU2,
 	XWAY_MUX_JTAG,
+	XWAY_MUX_MCD,
 	XWAY_MUX_EXIN,
 	XWAY_MUX_TDM,
 	XWAY_MUX_STP,
@@ -103,9 +105,15 @@
 	XWAY_MUX_DFE,
 	XWAY_MUX_SDIO,
 	XWAY_MUX_GPHY,
+	XWAY_MUX_SSI,
+	XWAY_MUX_WIFI,
 	XWAY_MUX_NONE = 0xffff,
 };
 
+/* ---------  DEPRECATED: xr9 related code --------- */
+/* ----------  use xrx100/xrx200 instead  ---------- */
+#define XR9_MAX_PIN		56
+
 static const struct ltq_mfp_pin xway_mfp[] = {
 	/*       pin    f0	f1	f2	f3   */
 	MFP_XWAY(GPIO0, GPIO,	EXIN,	NONE,	TDM),
@@ -113,7 +121,7 @@
 	MFP_XWAY(GPIO2, GPIO,	CGU,	EXIN,	GPHY),
 	MFP_XWAY(GPIO3, GPIO,	CGU,	NONE,	PCI),
 	MFP_XWAY(GPIO4, GPIO,	STP,	NONE,	ASC),
-	MFP_XWAY(GPIO5, GPIO,	STP,	NONE,	GPHY),
+	MFP_XWAY(GPIO5, GPIO,	STP,	GPHY,	NONE),
 	MFP_XWAY(GPIO6, GPIO,	STP,	GPT,	ASC),
 	MFP_XWAY(GPIO7, GPIO,	CGU,	PCI,	GPHY),
 	MFP_XWAY(GPIO8, GPIO,	CGU,	NMI,	NONE),
@@ -152,10 +160,10 @@
 	MFP_XWAY(GPIO41, GPIO,	NONE,	NONE,	NONE),
 	MFP_XWAY(GPIO42, GPIO,	MDIO,	NONE,	NONE),
 	MFP_XWAY(GPIO43, GPIO,	MDIO,	NONE,	NONE),
-	MFP_XWAY(GPIO44, GPIO,	NONE,	GPHY,	SIN),
+	MFP_XWAY(GPIO44, GPIO,	MII,	SIN,	GPHY),
 	MFP_XWAY(GPIO45, GPIO,	NONE,	GPHY,	SIN),
 	MFP_XWAY(GPIO46, GPIO,	NONE,	NONE,	EXIN),
-	MFP_XWAY(GPIO47, GPIO,	NONE,	GPHY,	SIN),
+	MFP_XWAY(GPIO47, GPIO,	MII,	GPHY,	SIN),
 	MFP_XWAY(GPIO48, GPIO,	EBU,	NONE,	NONE),
 	MFP_XWAY(GPIO49, GPIO,	EBU,	NONE,	NONE),
 	MFP_XWAY(GPIO50, GPIO,	NONE,	NONE,	NONE),
@@ -166,42 +174,6 @@
 	MFP_XWAY(GPIO55, GPIO,	NONE,	NONE,	NONE),
 };
 
-static const struct ltq_mfp_pin ase_mfp[] = {
-	/*       pin    f0	f1	f2	f3   */
-	MFP_XWAY(GPIO0, GPIO,	EXIN,	MII,	TDM),
-	MFP_XWAY(GPIO1, GPIO,	STP,	DFE,	EBU),
-	MFP_XWAY(GPIO2, GPIO,	STP,	DFE,	EPHY),
-	MFP_XWAY(GPIO3, GPIO,	STP,	EPHY,	EBU),
-	MFP_XWAY(GPIO4, GPIO,	GPT,	EPHY,	MII),
-	MFP_XWAY(GPIO5, GPIO,	MII,	ASC,	GPT),
-	MFP_XWAY(GPIO6, GPIO,	MII,	ASC,	EXIN),
-	MFP_XWAY(GPIO7, GPIO,	SPI,	MII,	JTAG),
-	MFP_XWAY(GPIO8, GPIO,	SPI,	MII,	JTAG),
-	MFP_XWAY(GPIO9, GPIO,	SPI,	MII,	JTAG),
-	MFP_XWAY(GPIO10, GPIO,	SPI,	MII,	JTAG),
-	MFP_XWAY(GPIO11, GPIO,	EBU,	CGU,	JTAG),
-	MFP_XWAY(GPIO12, GPIO,	EBU,	MII,	SDIO),
-	MFP_XWAY(GPIO13, GPIO,	EBU,	MII,	CGU),
-	MFP_XWAY(GPIO14, GPIO,	EBU,	SPI,	CGU),
-	MFP_XWAY(GPIO15, GPIO,	EBU,	SPI,	SDIO),
-	MFP_XWAY(GPIO16, GPIO,	NONE,	NONE,	NONE),
-	MFP_XWAY(GPIO17, GPIO,	NONE,	NONE,	NONE),
-	MFP_XWAY(GPIO18, GPIO,	NONE,	NONE,	NONE),
-	MFP_XWAY(GPIO19, GPIO,	EBU,	MII,	SDIO),
-	MFP_XWAY(GPIO20, GPIO,	EBU,	MII,	SDIO),
-	MFP_XWAY(GPIO21, GPIO,	EBU,	MII,	SDIO),
-	MFP_XWAY(GPIO22, GPIO,	EBU,	MII,	CGU),
-	MFP_XWAY(GPIO23, GPIO,	EBU,	MII,	CGU),
-	MFP_XWAY(GPIO24, GPIO,	EBU,	NONE,	MII),
-	MFP_XWAY(GPIO25, GPIO,	EBU,	MII,	GPT),
-	MFP_XWAY(GPIO26, GPIO,	EBU,	MII,	SDIO),
-	MFP_XWAY(GPIO27, GPIO,	EBU,	NONE,	MII),
-	MFP_XWAY(GPIO28, GPIO,	MII,	EBU,	SDIO),
-	MFP_XWAY(GPIO29, GPIO,	EBU,	MII,	EXIN),
-	MFP_XWAY(GPIO30, GPIO,	NONE,	NONE,	NONE),
-	MFP_XWAY(GPIO31, GPIO,	NONE,	NONE,	NONE),
-};
-
 static const unsigned pins_jtag[] = {GPIO15, GPIO16, GPIO17, GPIO19, GPIO35};
 static const unsigned pins_asc0[] = {GPIO11, GPIO12};
 static const unsigned pins_asc0_cts_rts[] = {GPIO9, GPIO10};
@@ -231,6 +203,8 @@
 static const unsigned pins_nand_rdy[] = {GPIO48};
 static const unsigned pins_nand_rd[] = {GPIO49};
 
+static const unsigned xway_exin_pin_map[] = {GPIO0, GPIO1, GPIO2, GPIO39, GPIO46, GPIO9};
+
 static const unsigned pins_exin0[] = {GPIO0};
 static const unsigned pins_exin1[] = {GPIO1};
 static const unsigned pins_exin2[] = {GPIO2};
@@ -240,7 +214,7 @@
 
 static const unsigned pins_spi[] = {GPIO16, GPIO17, GPIO18};
 static const unsigned pins_spi_cs1[] = {GPIO15};
-static const unsigned pins_spi_cs2[] = {GPIO21};
+static const unsigned pins_spi_cs2[] = {GPIO22};
 static const unsigned pins_spi_cs3[] = {GPIO13};
 static const unsigned pins_spi_cs4[] = {GPIO10};
 static const unsigned pins_spi_cs5[] = {GPIO9};
@@ -264,25 +238,6 @@
 static const unsigned pins_pci_req3[] = {GPIO3};
 static const unsigned pins_pci_req4[] = {GPIO37};
 
-static const unsigned ase_pins_jtag[] = {GPIO7, GPIO8, GPIO9, GPIO10, GPIO11};
-static const unsigned ase_pins_asc[] = {GPIO5, GPIO6};
-static const unsigned ase_pins_stp[] = {GPIO1, GPIO2, GPIO3};
-static const unsigned ase_pins_ephy[] = {GPIO2, GPIO3, GPIO4};
-static const unsigned ase_pins_dfe[] = {GPIO1, GPIO2};
-
-static const unsigned ase_pins_spi[] = {GPIO8, GPIO9, GPIO10};
-static const unsigned ase_pins_spi_cs1[] = {GPIO7};
-static const unsigned ase_pins_spi_cs2[] = {GPIO15};
-static const unsigned ase_pins_spi_cs3[] = {GPIO14};
-
-static const unsigned ase_pins_exin0[] = {GPIO6};
-static const unsigned ase_pins_exin1[] = {GPIO29};
-static const unsigned ase_pins_exin2[] = {GPIO0};
-
-static const unsigned ase_pins_gpt1[] = {GPIO5};
-static const unsigned ase_pins_gpt2[] = {GPIO4};
-static const unsigned ase_pins_gpt3[] = {GPIO25};
-
 static const struct ltq_pin_group xway_grps[] = {
 	GRP_MUX("exin0", EXIN, pins_exin0),
 	GRP_MUX("exin1", EXIN, pins_exin1),
@@ -338,24 +293,6 @@
 	GRP_MUX("gphy1 led2", GPHY, pins_gphy1_led2),
 };
 
-static const struct ltq_pin_group ase_grps[] = {
-	GRP_MUX("exin0", EXIN, ase_pins_exin0),
-	GRP_MUX("exin1", EXIN, ase_pins_exin1),
-	GRP_MUX("exin2", EXIN, ase_pins_exin2),
-	GRP_MUX("jtag", JTAG, ase_pins_jtag),
-	GRP_MUX("stp", STP, ase_pins_stp),
-	GRP_MUX("asc", ASC, ase_pins_asc),
-	GRP_MUX("gpt1", GPT, ase_pins_gpt1),
-	GRP_MUX("gpt2", GPT, ase_pins_gpt2),
-	GRP_MUX("gpt3", GPT, ase_pins_gpt3),
-	GRP_MUX("ephy", EPHY, ase_pins_ephy),
-	GRP_MUX("dfe", DFE, ase_pins_dfe),
-	GRP_MUX("spi", SPI, ase_pins_spi),
-	GRP_MUX("spi_cs1", SPI, ase_pins_spi_cs1),
-	GRP_MUX("spi_cs2", SPI, ase_pins_spi_cs2),
-	GRP_MUX("spi_cs3", SPI, ase_pins_spi_cs3),
-};
-
 static const char * const xway_pci_grps[] = {"gnt1", "gnt2",
 						"gnt3", "req1",
 						"req2", "req3"};
@@ -395,30 +332,6 @@
 						"req1", "req2",
 						"req3", "req4"};
 
-/* ase */
-static const char * const ase_exin_grps[] = {"exin0", "exin1", "exin2"};
-static const char * const ase_gpt_grps[] = {"gpt1", "gpt2", "gpt3"};
-static const char * const ase_dfe_grps[] = {"dfe"};
-static const char * const ase_ephy_grps[] = {"ephy"};
-static const char * const ase_asc_grps[] = {"asc"};
-static const char * const ase_jtag_grps[] = {"jtag"};
-static const char * const ase_stp_grps[] = {"stp"};
-static const char * const ase_spi_grps[] = {"spi", "spi_cs1",
-						"spi_cs2", "spi_cs3"};
-
-static const struct ltq_pmx_func danube_funcs[] = {
-	{"spi",		ARRAY_AND_SIZE(xway_spi_grps)},
-	{"asc",		ARRAY_AND_SIZE(xway_asc_grps)},
-	{"cgu",		ARRAY_AND_SIZE(xway_cgu_grps)},
-	{"jtag",	ARRAY_AND_SIZE(xway_jtag_grps)},
-	{"exin",	ARRAY_AND_SIZE(xway_exin_grps)},
-	{"stp",		ARRAY_AND_SIZE(xway_stp_grps)},
-	{"gpt",		ARRAY_AND_SIZE(xway_gpt_grps)},
-	{"nmi",		ARRAY_AND_SIZE(xway_nmi_grps)},
-	{"pci",		ARRAY_AND_SIZE(xway_pci_grps)},
-	{"ebu",		ARRAY_AND_SIZE(xway_ebu_grps)},
-};
-
 static const struct ltq_pmx_func xrx_funcs[] = {
 	{"spi",		ARRAY_AND_SIZE(xway_spi_grps)},
 	{"asc",		ARRAY_AND_SIZE(xway_asc_grps)},
@@ -434,17 +347,991 @@
 	{"gphy",	ARRAY_AND_SIZE(xrx_gphy_grps)},
 };
 
+/* ---------  ase related code --------- */
+#define ASE_MAX_PIN		32
+
+static const struct ltq_mfp_pin ase_mfp[] = {
+	/*       pin    f0	f1	f2	f3   */
+	MFP_XWAY(GPIO0, GPIO,	EXIN,	MII,	TDM),
+	MFP_XWAY(GPIO1, GPIO,	STP,	DFE,	EBU),
+	MFP_XWAY(GPIO2, GPIO,	STP,	DFE,	EPHY),
+	MFP_XWAY(GPIO3, GPIO,	STP,	EPHY,	EBU),
+	MFP_XWAY(GPIO4, GPIO,	GPT,	EPHY,	MII),
+	MFP_XWAY(GPIO5, GPIO,	MII,	ASC,	GPT),
+	MFP_XWAY(GPIO6, GPIO,	MII,	ASC,	EXIN),
+	MFP_XWAY(GPIO7, GPIO,	SPI,	MII,	JTAG),
+	MFP_XWAY(GPIO8, GPIO,	SPI,	MII,	JTAG),
+	MFP_XWAY(GPIO9, GPIO,	SPI,	MII,	JTAG),
+	MFP_XWAY(GPIO10, GPIO,	SPI,	MII,	JTAG),
+	MFP_XWAY(GPIO11, GPIO,	EBU,	CGU,	JTAG),
+	MFP_XWAY(GPIO12, GPIO,	EBU,	MII,	SDIO),
+	MFP_XWAY(GPIO13, GPIO,	EBU,	MII,	CGU),
+	MFP_XWAY(GPIO14, GPIO,	EBU,	SPI,	CGU),
+	MFP_XWAY(GPIO15, GPIO,	EBU,	SPI,	SDIO),
+	MFP_XWAY(GPIO16, GPIO,	NONE,	NONE,	NONE),
+	MFP_XWAY(GPIO17, GPIO,	NONE,	NONE,	NONE),
+	MFP_XWAY(GPIO18, GPIO,	NONE,	NONE,	NONE),
+	MFP_XWAY(GPIO19, GPIO,	EBU,	MII,	SDIO),
+	MFP_XWAY(GPIO20, GPIO,	EBU,	MII,	SDIO),
+	MFP_XWAY(GPIO21, GPIO,	EBU,	MII,	EBU2),
+	MFP_XWAY(GPIO22, GPIO,	EBU,	MII,	CGU),
+	MFP_XWAY(GPIO23, GPIO,	EBU,	MII,	CGU),
+	MFP_XWAY(GPIO24, GPIO,	EBU,	EBU2,	MDIO),
+	MFP_XWAY(GPIO25, GPIO,	EBU,	MII,	GPT),
+	MFP_XWAY(GPIO26, GPIO,	EBU,	MII,	SDIO),
+	MFP_XWAY(GPIO27, GPIO,	EBU,	NONE,	MDIO),
+	MFP_XWAY(GPIO28, GPIO,	MII,	EBU,	SDIO),
+	MFP_XWAY(GPIO29, GPIO,	EBU,	MII,	EXIN),
+	MFP_XWAY(GPIO30, GPIO,	NONE,	NONE,	NONE),
+	MFP_XWAY(GPIO31, GPIO,	NONE,	NONE,	NONE),
+};
+
+static const unsigned ase_exin_pin_map[] = {GPIO6, GPIO29, GPIO0};
+
+static const unsigned ase_pins_exin0[] = {GPIO6};
+static const unsigned ase_pins_exin1[] = {GPIO29};
+static const unsigned ase_pins_exin2[] = {GPIO0};
+
+static const unsigned ase_pins_jtag[] = {GPIO7, GPIO8, GPIO9, GPIO10, GPIO11};
+static const unsigned ase_pins_asc[] = {GPIO5, GPIO6};
+static const unsigned ase_pins_stp[] = {GPIO1, GPIO2, GPIO3};
+static const unsigned ase_pins_mdio[] = {GPIO24, GPIO27};
+static const unsigned ase_pins_ephy_led0[] = {GPIO2};
+static const unsigned ase_pins_ephy_led1[] = {GPIO3};
+static const unsigned ase_pins_ephy_led2[] = {GPIO4};
+static const unsigned ase_pins_dfe_led0[] = {GPIO1};
+static const unsigned ase_pins_dfe_led1[] = {GPIO2};
+
+static const unsigned ase_pins_spi[] = {GPIO8, GPIO9, GPIO10}; /* DEPRECATED */
+static const unsigned ase_pins_spi_di[] = {GPIO8};
+static const unsigned ase_pins_spi_do[] = {GPIO9};
+static const unsigned ase_pins_spi_clk[] = {GPIO10};
+static const unsigned ase_pins_spi_cs1[] = {GPIO7};
+static const unsigned ase_pins_spi_cs2[] = {GPIO15};
+static const unsigned ase_pins_spi_cs3[] = {GPIO14};
+
+static const unsigned ase_pins_gpt1[] = {GPIO5};
+static const unsigned ase_pins_gpt2[] = {GPIO4};
+static const unsigned ase_pins_gpt3[] = {GPIO25};
+
+static const unsigned ase_pins_clkout0[] = {GPIO23};
+static const unsigned ase_pins_clkout1[] = {GPIO22};
+static const unsigned ase_pins_clkout2[] = {GPIO14};
+
+static const struct ltq_pin_group ase_grps[] = {
+	GRP_MUX("exin0", EXIN, ase_pins_exin0),
+	GRP_MUX("exin1", EXIN, ase_pins_exin1),
+	GRP_MUX("exin2", EXIN, ase_pins_exin2),
+	GRP_MUX("jtag", JTAG, ase_pins_jtag),
+	GRP_MUX("spi", SPI, ase_pins_spi), /* DEPRECATED */
+	GRP_MUX("spi_di", SPI, ase_pins_spi_di),
+	GRP_MUX("spi_do", SPI, ase_pins_spi_do),
+	GRP_MUX("spi_clk", SPI, ase_pins_spi_clk),
+	GRP_MUX("spi_cs1", SPI, ase_pins_spi_cs1),
+	GRP_MUX("spi_cs2", SPI, ase_pins_spi_cs2),
+	GRP_MUX("spi_cs3", SPI, ase_pins_spi_cs3),
+	GRP_MUX("asc", ASC, ase_pins_asc),
+	GRP_MUX("stp", STP, ase_pins_stp),
+	GRP_MUX("gpt1", GPT, ase_pins_gpt1),
+	GRP_MUX("gpt2", GPT, ase_pins_gpt2),
+	GRP_MUX("gpt3", GPT, ase_pins_gpt3),
+	GRP_MUX("clkout0", CGU, ase_pins_clkout0),
+	GRP_MUX("clkout1", CGU, ase_pins_clkout1),
+	GRP_MUX("clkout2", CGU, ase_pins_clkout2),
+	GRP_MUX("mdio", MDIO, ase_pins_mdio),
+	GRP_MUX("dfe led0", DFE, ase_pins_dfe_led0),
+	GRP_MUX("dfe led1", DFE, ase_pins_dfe_led1),
+	GRP_MUX("ephy led0", EPHY, ase_pins_ephy_led0),
+	GRP_MUX("ephy led1", EPHY, ase_pins_ephy_led1),
+	GRP_MUX("ephy led2", EPHY, ase_pins_ephy_led2),
+};
+
+static const char * const ase_exin_grps[] = {"exin0", "exin1", "exin2"};
+static const char * const ase_gpt_grps[] = {"gpt1", "gpt2", "gpt3"};
+static const char * const ase_cgu_grps[] = {"clkout0", "clkout1",
+						"clkout2"};
+static const char * const ase_mdio_grps[] = {"mdio"};
+static const char * const ase_dfe_grps[] = {"dfe led0", "dfe led1"};
+static const char * const ase_ephy_grps[] = {"ephy led0", "ephy led1",
+						"ephy led2"};
+static const char * const ase_asc_grps[] = {"asc"};
+static const char * const ase_jtag_grps[] = {"jtag"};
+static const char * const ase_stp_grps[] = {"stp"};
+static const char * const ase_spi_grps[] = {"spi",  /* DEPRECATED */
+						"spi_di", "spi_do",
+						"spi_clk", "spi_cs1",
+						"spi_cs2", "spi_cs3"};
+
 static const struct ltq_pmx_func ase_funcs[] = {
 	{"spi",		ARRAY_AND_SIZE(ase_spi_grps)},
 	{"asc",		ARRAY_AND_SIZE(ase_asc_grps)},
+	{"cgu",		ARRAY_AND_SIZE(ase_cgu_grps)},
 	{"jtag",	ARRAY_AND_SIZE(ase_jtag_grps)},
 	{"exin",	ARRAY_AND_SIZE(ase_exin_grps)},
 	{"stp",		ARRAY_AND_SIZE(ase_stp_grps)},
 	{"gpt",		ARRAY_AND_SIZE(ase_gpt_grps)},
+	{"mdio",	ARRAY_AND_SIZE(ase_mdio_grps)},
 	{"ephy",	ARRAY_AND_SIZE(ase_ephy_grps)},
 	{"dfe",		ARRAY_AND_SIZE(ase_dfe_grps)},
 };
 
+/* ---------  danube related code --------- */
+#define DANUBE_MAX_PIN		32
+
+static const struct ltq_mfp_pin danube_mfp[] = {
+	/*       pin    f0	f1	f2	f3   */
+	MFP_XWAY(GPIO0, GPIO,	EXIN,	SDIO,	TDM),
+	MFP_XWAY(GPIO1, GPIO,	EXIN,	CBUS,	MII),
+	MFP_XWAY(GPIO2, GPIO,	CGU,	EXIN,	MII),
+	MFP_XWAY(GPIO3, GPIO,	CGU,	SDIO,	PCI),
+	MFP_XWAY(GPIO4, GPIO,	STP,	DFE,	ASC),
+	MFP_XWAY(GPIO5, GPIO,	STP,	MII,	DFE),
+	MFP_XWAY(GPIO6, GPIO,	STP,	GPT,	ASC),
+	MFP_XWAY(GPIO7, GPIO,	CGU,	CBUS,	MII),
+	MFP_XWAY(GPIO8, GPIO,	CGU,	NMI,	MII),
+	MFP_XWAY(GPIO9, GPIO,	ASC,	SPI,	MII),
+	MFP_XWAY(GPIO10, GPIO,	ASC,	SPI,	MII),
+	MFP_XWAY(GPIO11, GPIO,	ASC,	CBUS,	SPI),
+	MFP_XWAY(GPIO12, GPIO,	ASC,	CBUS,	MCD),
+	MFP_XWAY(GPIO13, GPIO,	EBU,	SPI,	MII),
+	MFP_XWAY(GPIO14, GPIO,	CGU,	CBUS,	MII),
+	MFP_XWAY(GPIO15, GPIO,	SPI,	SDIO,	JTAG),
+	MFP_XWAY(GPIO16, GPIO,	SPI,	SDIO,	JTAG),
+	MFP_XWAY(GPIO17, GPIO,	SPI,	SDIO,	JTAG),
+	MFP_XWAY(GPIO18, GPIO,	SPI,	SDIO,	JTAG),
+	MFP_XWAY(GPIO19, GPIO,	PCI,	SDIO,	MII),
+	MFP_XWAY(GPIO20, GPIO,	JTAG,	SDIO,	MII),
+	MFP_XWAY(GPIO21, GPIO,	PCI,	EBU,	GPT),
+	MFP_XWAY(GPIO22, GPIO,	SPI,	MCD,	MII),
+	MFP_XWAY(GPIO23, GPIO,	EBU,	PCI,	STP),
+	MFP_XWAY(GPIO24, GPIO,	EBU,	TDM,	PCI),
+	MFP_XWAY(GPIO25, GPIO,	TDM,	SDIO,	ASC),
+	MFP_XWAY(GPIO26, GPIO,	EBU,	TDM,	SDIO),
+	MFP_XWAY(GPIO27, GPIO,	TDM,	SDIO,	ASC),
+	MFP_XWAY(GPIO28, GPIO,	GPT,	MII,	SDIO),
+	MFP_XWAY(GPIO29, GPIO,	PCI,	CBUS,	MII),
+	MFP_XWAY(GPIO30, GPIO,	PCI,	CBUS,	MII),
+	MFP_XWAY(GPIO31, GPIO,	EBU,	PCI,	MII),
+};
+
+static const unsigned danube_exin_pin_map[] = {GPIO0, GPIO1, GPIO2};
+
+static const unsigned danube_pins_exin0[] = {GPIO0};
+static const unsigned danube_pins_exin1[] = {GPIO1};
+static const unsigned danube_pins_exin2[] = {GPIO2};
+
+static const unsigned danube_pins_jtag[] = {GPIO15, GPIO16, GPIO17, GPIO18, GPIO20};
+static const unsigned danube_pins_asc0[] = {GPIO11, GPIO12};
+static const unsigned danube_pins_asc0_cts_rts[] = {GPIO9, GPIO10};
+static const unsigned danube_pins_stp[] = {GPIO4, GPIO5, GPIO6};
+static const unsigned danube_pins_nmi[] = {GPIO8};
+
+static const unsigned danube_pins_dfe_led0[] = {GPIO4};
+static const unsigned danube_pins_dfe_led1[] = {GPIO5};
+
+static const unsigned danube_pins_ebu_a24[] = {GPIO13};
+static const unsigned danube_pins_ebu_clk[] = {GPIO21};
+static const unsigned danube_pins_ebu_cs1[] = {GPIO23};
+static const unsigned danube_pins_ebu_a23[] = {GPIO24};
+static const unsigned danube_pins_ebu_wait[] = {GPIO26};
+static const unsigned danube_pins_ebu_a25[] = {GPIO31};
+
+static const unsigned danube_pins_nand_ale[] = {GPIO13};
+static const unsigned danube_pins_nand_cs1[] = {GPIO23};
+static const unsigned danube_pins_nand_cle[] = {GPIO24};
+
+static const unsigned danube_pins_spi[] = {GPIO16, GPIO17, GPIO18}; /* DEPRECATED */
+static const unsigned danube_pins_spi_di[] = {GPIO16};
+static const unsigned danube_pins_spi_do[] = {GPIO17};
+static const unsigned danube_pins_spi_clk[] = {GPIO18};
+static const unsigned danube_pins_spi_cs1[] = {GPIO15};
+static const unsigned danube_pins_spi_cs2[] = {GPIO21};
+static const unsigned danube_pins_spi_cs3[] = {GPIO13};
+static const unsigned danube_pins_spi_cs4[] = {GPIO10};
+static const unsigned danube_pins_spi_cs5[] = {GPIO9};
+static const unsigned danube_pins_spi_cs6[] = {GPIO11};
+
+static const unsigned danube_pins_gpt1[] = {GPIO28};
+static const unsigned danube_pins_gpt2[] = {GPIO21};
+static const unsigned danube_pins_gpt3[] = {GPIO6};
+
+static const unsigned danube_pins_clkout0[] = {GPIO8};
+static const unsigned danube_pins_clkout1[] = {GPIO7};
+static const unsigned danube_pins_clkout2[] = {GPIO3};
+static const unsigned danube_pins_clkout3[] = {GPIO2};
+
+static const unsigned danube_pins_pci_gnt1[] = {GPIO30};
+static const unsigned danube_pins_pci_gnt2[] = {GPIO23};
+static const unsigned danube_pins_pci_gnt3[] = {GPIO19};
+static const unsigned danube_pins_pci_req1[] = {GPIO29};
+static const unsigned danube_pins_pci_req2[] = {GPIO31};
+static const unsigned danube_pins_pci_req3[] = {GPIO3};
+
+static const struct ltq_pin_group danube_grps[] = {
+	GRP_MUX("exin0", EXIN, danube_pins_exin0),
+	GRP_MUX("exin1", EXIN, danube_pins_exin1),
+	GRP_MUX("exin2", EXIN, danube_pins_exin2),
+	GRP_MUX("jtag", JTAG, danube_pins_jtag),
+	GRP_MUX("ebu a23", EBU, danube_pins_ebu_a23),
+	GRP_MUX("ebu a24", EBU, danube_pins_ebu_a24),
+	GRP_MUX("ebu a25", EBU, danube_pins_ebu_a25),
+	GRP_MUX("ebu clk", EBU, danube_pins_ebu_clk),
+	GRP_MUX("ebu cs1", EBU, danube_pins_ebu_cs1),
+	GRP_MUX("ebu wait", EBU, danube_pins_ebu_wait),
+	GRP_MUX("nand ale", EBU, danube_pins_nand_ale),
+	GRP_MUX("nand cs1", EBU, danube_pins_nand_cs1),
+	GRP_MUX("nand cle", EBU, danube_pins_nand_cle),
+	GRP_MUX("spi", SPI, danube_pins_spi), /* DEPRECATED */
+	GRP_MUX("spi_di", SPI, danube_pins_spi_di),
+	GRP_MUX("spi_do", SPI, danube_pins_spi_do),
+	GRP_MUX("spi_clk", SPI, danube_pins_spi_clk),
+	GRP_MUX("spi_cs1", SPI, danube_pins_spi_cs1),
+	GRP_MUX("spi_cs2", SPI, danube_pins_spi_cs2),
+	GRP_MUX("spi_cs3", SPI, danube_pins_spi_cs3),
+	GRP_MUX("spi_cs4", SPI, danube_pins_spi_cs4),
+	GRP_MUX("spi_cs5", SPI, danube_pins_spi_cs5),
+	GRP_MUX("spi_cs6", SPI, danube_pins_spi_cs6),
+	GRP_MUX("asc0", ASC, danube_pins_asc0),
+	GRP_MUX("asc0 cts rts", ASC, danube_pins_asc0_cts_rts),
+	GRP_MUX("stp", STP, danube_pins_stp),
+	GRP_MUX("nmi", NMI, danube_pins_nmi),
+	GRP_MUX("gpt1", GPT, danube_pins_gpt1),
+	GRP_MUX("gpt2", GPT, danube_pins_gpt2),
+	GRP_MUX("gpt3", GPT, danube_pins_gpt3),
+	GRP_MUX("clkout0", CGU, danube_pins_clkout0),
+	GRP_MUX("clkout1", CGU, danube_pins_clkout1),
+	GRP_MUX("clkout2", CGU, danube_pins_clkout2),
+	GRP_MUX("clkout3", CGU, danube_pins_clkout3),
+	GRP_MUX("gnt1", PCI, danube_pins_pci_gnt1),
+	GRP_MUX("gnt2", PCI, danube_pins_pci_gnt2),
+	GRP_MUX("gnt3", PCI, danube_pins_pci_gnt3),
+	GRP_MUX("req1", PCI, danube_pins_pci_req1),
+	GRP_MUX("req2", PCI, danube_pins_pci_req2),
+	GRP_MUX("req3", PCI, danube_pins_pci_req3),
+	GRP_MUX("dfe led0", DFE, danube_pins_dfe_led0),
+	GRP_MUX("dfe led1", DFE, danube_pins_dfe_led1),
+};
+
+static const char * const danube_pci_grps[] = {"gnt1", "gnt2",
+						"gnt3", "req1",
+						"req2", "req3"};
+static const char * const danube_spi_grps[] = {"spi", /* DEPRECATED */
+						"spi_di", "spi_do",
+						"spi_clk", "spi_cs1",
+						"spi_cs2", "spi_cs3",
+						"spi_cs4", "spi_cs5",
+						"spi_cs6"};
+static const char * const danube_cgu_grps[] = {"clkout0", "clkout1",
+						"clkout2", "clkout3"};
+static const char * const danube_ebu_grps[] = {"ebu a23", "ebu a24",
+						"ebu a25", "ebu cs1",
+						"ebu wait", "ebu clk",
+						"nand ale", "nand cs1",
+						"nand cle"};
+static const char * const danube_dfe_grps[] = {"dfe led0", "dfe led1"};
+static const char * const danube_exin_grps[] = {"exin0", "exin1", "exin2"};
+static const char * const danube_gpt_grps[] = {"gpt1", "gpt2", "gpt3"};
+static const char * const danube_asc_grps[] = {"asc0", "asc0 cts rts"};
+static const char * const danube_jtag_grps[] = {"jtag"};
+static const char * const danube_stp_grps[] = {"stp"};
+static const char * const danube_nmi_grps[] = {"nmi"};
+
+static const struct ltq_pmx_func danube_funcs[] = {
+	{"spi",		ARRAY_AND_SIZE(danube_spi_grps)},
+	{"asc",		ARRAY_AND_SIZE(danube_asc_grps)},
+	{"cgu",		ARRAY_AND_SIZE(danube_cgu_grps)},
+	{"jtag",	ARRAY_AND_SIZE(danube_jtag_grps)},
+	{"exin",	ARRAY_AND_SIZE(danube_exin_grps)},
+	{"stp",		ARRAY_AND_SIZE(danube_stp_grps)},
+	{"gpt",		ARRAY_AND_SIZE(danube_gpt_grps)},
+	{"nmi",		ARRAY_AND_SIZE(danube_nmi_grps)},
+	{"pci",		ARRAY_AND_SIZE(danube_pci_grps)},
+	{"ebu",		ARRAY_AND_SIZE(danube_ebu_grps)},
+	{"dfe",		ARRAY_AND_SIZE(danube_dfe_grps)},
+};
+
+/* ---------  xrx100 related code --------- */
+#define XRX100_MAX_PIN		56
+
+static const struct ltq_mfp_pin xrx100_mfp[] = {
+	/*       pin    f0	f1	f2	f3   */
+	MFP_XWAY(GPIO0, GPIO,	EXIN,	SDIO,	TDM),
+	MFP_XWAY(GPIO1, GPIO,	EXIN,	CBUS,	SIN),
+	MFP_XWAY(GPIO2, GPIO,	CGU,	EXIN,	NONE),
+	MFP_XWAY(GPIO3, GPIO,	CGU,	SDIO,	PCI),
+	MFP_XWAY(GPIO4, GPIO,	STP,	DFE,	ASC),
+	MFP_XWAY(GPIO5, GPIO,	STP,	NONE,	DFE),
+	MFP_XWAY(GPIO6, GPIO,	STP,	GPT,	ASC),
+	MFP_XWAY(GPIO7, GPIO,	CGU,	CBUS,	NONE),
+	MFP_XWAY(GPIO8, GPIO,	CGU,	NMI,	NONE),
+	MFP_XWAY(GPIO9, GPIO,	ASC,	SPI,	EXIN),
+	MFP_XWAY(GPIO10, GPIO,	ASC,	SPI,	EXIN),
+	MFP_XWAY(GPIO11, GPIO,	ASC,	CBUS,	SPI),
+	MFP_XWAY(GPIO12, GPIO,	ASC,	CBUS,	MCD),
+	MFP_XWAY(GPIO13, GPIO,	EBU,	SPI,	NONE),
+	MFP_XWAY(GPIO14, GPIO,	CGU,	NONE,	NONE),
+	MFP_XWAY(GPIO15, GPIO,	SPI,	SDIO,	MCD),
+	MFP_XWAY(GPIO16, GPIO,	SPI,	SDIO,	NONE),
+	MFP_XWAY(GPIO17, GPIO,	SPI,	SDIO,	NONE),
+	MFP_XWAY(GPIO18, GPIO,	SPI,	SDIO,	NONE),
+	MFP_XWAY(GPIO19, GPIO,	PCI,	SDIO,	CGU),
+	MFP_XWAY(GPIO20, GPIO,	NONE,	SDIO,	EBU),
+	MFP_XWAY(GPIO21, GPIO,	PCI,	EBU,	GPT),
+	MFP_XWAY(GPIO22, GPIO,	SPI,	NONE,	EBU),
+	MFP_XWAY(GPIO23, GPIO,	EBU,	PCI,	STP),
+	MFP_XWAY(GPIO24, GPIO,	EBU,	TDM,	PCI),
+	MFP_XWAY(GPIO25, GPIO,	TDM,	SDIO,	ASC),
+	MFP_XWAY(GPIO26, GPIO,	EBU,	TDM,	SDIO),
+	MFP_XWAY(GPIO27, GPIO,	TDM,	SDIO,	ASC),
+	MFP_XWAY(GPIO28, GPIO,	GPT,	NONE,	SDIO),
+	MFP_XWAY(GPIO29, GPIO,	PCI,	CBUS,	NONE),
+	MFP_XWAY(GPIO30, GPIO,	PCI,	CBUS,	NONE),
+	MFP_XWAY(GPIO31, GPIO,	EBU,	PCI,	NONE),
+	MFP_XWAY(GPIO32, GPIO,	MII,	NONE,	EBU),
+	MFP_XWAY(GPIO33, GPIO,	MII,	NONE,	EBU),
+	MFP_XWAY(GPIO34, GPIO,	SIN,	SSI,	NONE),
+	MFP_XWAY(GPIO35, GPIO,	SIN,	SSI,	NONE),
+	MFP_XWAY(GPIO36, GPIO,	SIN,	SSI,	NONE),
+	MFP_XWAY(GPIO37, GPIO,	PCI,	NONE,	NONE),
+	MFP_XWAY(GPIO38, GPIO,	PCI,	NONE,	NONE),
+	MFP_XWAY(GPIO39, GPIO,	NONE,	EXIN,	NONE),
+	MFP_XWAY(GPIO40, GPIO,	MII,	TDM,	NONE),
+	MFP_XWAY(GPIO41, GPIO,	MII,	TDM,	NONE),
+	MFP_XWAY(GPIO42, GPIO,	MDIO,	NONE,	NONE),
+	MFP_XWAY(GPIO43, GPIO,	MDIO,	NONE,	NONE),
+	MFP_XWAY(GPIO44, GPIO,	MII,	SIN,	NONE),
+	MFP_XWAY(GPIO45, GPIO,	MII,	NONE,	SIN),
+	MFP_XWAY(GPIO46, GPIO,	MII,	NONE,	EXIN),
+	MFP_XWAY(GPIO47, GPIO,	MII,	NONE,	SIN),
+	MFP_XWAY(GPIO48, GPIO,	EBU,	NONE,	NONE),
+	MFP_XWAY(GPIO49, GPIO,	EBU,	NONE,	NONE),
+	MFP_XWAY(GPIO50, GPIO,	NONE,	NONE,	NONE),
+	MFP_XWAY(GPIO51, GPIO,	NONE,	NONE,	NONE),
+	MFP_XWAY(GPIO52, GPIO,	NONE,	NONE,	NONE),
+	MFP_XWAY(GPIO53, GPIO,	NONE,	NONE,	NONE),
+	MFP_XWAY(GPIO54, GPIO,	NONE,	NONE,	NONE),
+	MFP_XWAY(GPIO55, GPIO,	NONE,	NONE,	NONE),
+};
+
+static const unsigned xrx100_exin_pin_map[] = {GPIO0, GPIO1, GPIO2, GPIO39, GPIO10, GPIO9};
+
+static const unsigned xrx100_pins_exin0[] = {GPIO0};
+static const unsigned xrx100_pins_exin1[] = {GPIO1};
+static const unsigned xrx100_pins_exin2[] = {GPIO2};
+static const unsigned xrx100_pins_exin3[] = {GPIO39};
+static const unsigned xrx100_pins_exin4[] = {GPIO10};
+static const unsigned xrx100_pins_exin5[] = {GPIO9};
+
+static const unsigned xrx100_pins_asc0[] = {GPIO11, GPIO12};
+static const unsigned xrx100_pins_asc0_cts_rts[] = {GPIO9, GPIO10};
+static const unsigned xrx100_pins_stp[] = {GPIO4, GPIO5, GPIO6};
+static const unsigned xrx100_pins_nmi[] = {GPIO8};
+static const unsigned xrx100_pins_mdio[] = {GPIO42, GPIO43};
+
+static const unsigned xrx100_pins_dfe_led0[] = {GPIO4};
+static const unsigned xrx100_pins_dfe_led1[] = {GPIO5};
+
+static const unsigned xrx100_pins_ebu_a24[] = {GPIO13};
+static const unsigned xrx100_pins_ebu_clk[] = {GPIO21};
+static const unsigned xrx100_pins_ebu_cs1[] = {GPIO23};
+static const unsigned xrx100_pins_ebu_a23[] = {GPIO24};
+static const unsigned xrx100_pins_ebu_wait[] = {GPIO26};
+static const unsigned xrx100_pins_ebu_a25[] = {GPIO31};
+
+static const unsigned xrx100_pins_nand_ale[] = {GPIO13};
+static const unsigned xrx100_pins_nand_cs1[] = {GPIO23};
+static const unsigned xrx100_pins_nand_cle[] = {GPIO24};
+static const unsigned xrx100_pins_nand_rdy[] = {GPIO48};
+static const unsigned xrx100_pins_nand_rd[] = {GPIO49};
+
+static const unsigned xrx100_pins_spi_di[] = {GPIO16};
+static const unsigned xrx100_pins_spi_do[] = {GPIO17};
+static const unsigned xrx100_pins_spi_clk[] = {GPIO18};
+static const unsigned xrx100_pins_spi_cs1[] = {GPIO15};
+static const unsigned xrx100_pins_spi_cs2[] = {GPIO22};
+static const unsigned xrx100_pins_spi_cs3[] = {GPIO13};
+static const unsigned xrx100_pins_spi_cs4[] = {GPIO10};
+static const unsigned xrx100_pins_spi_cs5[] = {GPIO9};
+static const unsigned xrx100_pins_spi_cs6[] = {GPIO11};
+
+static const unsigned xrx100_pins_gpt1[] = {GPIO28};
+static const unsigned xrx100_pins_gpt2[] = {GPIO21};
+static const unsigned xrx100_pins_gpt3[] = {GPIO6};
+
+static const unsigned xrx100_pins_clkout0[] = {GPIO8};
+static const unsigned xrx100_pins_clkout1[] = {GPIO7};
+static const unsigned xrx100_pins_clkout2[] = {GPIO3};
+static const unsigned xrx100_pins_clkout3[] = {GPIO2};
+
+static const unsigned xrx100_pins_pci_gnt1[] = {GPIO30};
+static const unsigned xrx100_pins_pci_gnt2[] = {GPIO23};
+static const unsigned xrx100_pins_pci_gnt3[] = {GPIO19};
+static const unsigned xrx100_pins_pci_gnt4[] = {GPIO38};
+static const unsigned xrx100_pins_pci_req1[] = {GPIO29};
+static const unsigned xrx100_pins_pci_req2[] = {GPIO31};
+static const unsigned xrx100_pins_pci_req3[] = {GPIO3};
+static const unsigned xrx100_pins_pci_req4[] = {GPIO37};
+
+static const struct ltq_pin_group xrx100_grps[] = {
+	GRP_MUX("exin0", EXIN, xrx100_pins_exin0),
+	GRP_MUX("exin1", EXIN, xrx100_pins_exin1),
+	GRP_MUX("exin2", EXIN, xrx100_pins_exin2),
+	GRP_MUX("exin3", EXIN, xrx100_pins_exin3),
+	GRP_MUX("exin4", EXIN, xrx100_pins_exin4),
+	GRP_MUX("exin5", EXIN, xrx100_pins_exin5),
+	GRP_MUX("ebu a23", EBU, xrx100_pins_ebu_a23),
+	GRP_MUX("ebu a24", EBU, xrx100_pins_ebu_a24),
+	GRP_MUX("ebu a25", EBU, xrx100_pins_ebu_a25),
+	GRP_MUX("ebu clk", EBU, xrx100_pins_ebu_clk),
+	GRP_MUX("ebu cs1", EBU, xrx100_pins_ebu_cs1),
+	GRP_MUX("ebu wait", EBU, xrx100_pins_ebu_wait),
+	GRP_MUX("nand ale", EBU, xrx100_pins_nand_ale),
+	GRP_MUX("nand cs1", EBU, xrx100_pins_nand_cs1),
+	GRP_MUX("nand cle", EBU, xrx100_pins_nand_cle),
+	GRP_MUX("nand rdy", EBU, xrx100_pins_nand_rdy),
+	GRP_MUX("nand rd", EBU, xrx100_pins_nand_rd),
+	GRP_MUX("spi_di", SPI, xrx100_pins_spi_di),
+	GRP_MUX("spi_do", SPI, xrx100_pins_spi_do),
+	GRP_MUX("spi_clk", SPI, xrx100_pins_spi_clk),
+	GRP_MUX("spi_cs1", SPI, xrx100_pins_spi_cs1),
+	GRP_MUX("spi_cs2", SPI, xrx100_pins_spi_cs2),
+	GRP_MUX("spi_cs3", SPI, xrx100_pins_spi_cs3),
+	GRP_MUX("spi_cs4", SPI, xrx100_pins_spi_cs4),
+	GRP_MUX("spi_cs5", SPI, xrx100_pins_spi_cs5),
+	GRP_MUX("spi_cs6", SPI, xrx100_pins_spi_cs6),
+	GRP_MUX("asc0", ASC, xrx100_pins_asc0),
+	GRP_MUX("asc0 cts rts", ASC, xrx100_pins_asc0_cts_rts),
+	GRP_MUX("stp", STP, xrx100_pins_stp),
+	GRP_MUX("nmi", NMI, xrx100_pins_nmi),
+	GRP_MUX("gpt1", GPT, xrx100_pins_gpt1),
+	GRP_MUX("gpt2", GPT, xrx100_pins_gpt2),
+	GRP_MUX("gpt3", GPT, xrx100_pins_gpt3),
+	GRP_MUX("clkout0", CGU, xrx100_pins_clkout0),
+	GRP_MUX("clkout1", CGU, xrx100_pins_clkout1),
+	GRP_MUX("clkout2", CGU, xrx100_pins_clkout2),
+	GRP_MUX("clkout3", CGU, xrx100_pins_clkout3),
+	GRP_MUX("gnt1", PCI, xrx100_pins_pci_gnt1),
+	GRP_MUX("gnt2", PCI, xrx100_pins_pci_gnt2),
+	GRP_MUX("gnt3", PCI, xrx100_pins_pci_gnt3),
+	GRP_MUX("gnt4", PCI, xrx100_pins_pci_gnt4),
+	GRP_MUX("req1", PCI, xrx100_pins_pci_req1),
+	GRP_MUX("req2", PCI, xrx100_pins_pci_req2),
+	GRP_MUX("req3", PCI, xrx100_pins_pci_req3),
+	GRP_MUX("req4", PCI, xrx100_pins_pci_req4),
+	GRP_MUX("mdio", MDIO, xrx100_pins_mdio),
+	GRP_MUX("dfe led0", DFE, xrx100_pins_dfe_led0),
+	GRP_MUX("dfe led1", DFE, xrx100_pins_dfe_led1),
+};
+
+static const char * const xrx100_pci_grps[] = {"gnt1", "gnt2",
+						"gnt3", "gnt4",
+						"req1", "req2",
+						"req3", "req4"};
+static const char * const xrx100_spi_grps[] = {"spi_di", "spi_do",
+						"spi_clk", "spi_cs1",
+						"spi_cs2", "spi_cs3",
+						"spi_cs4", "spi_cs5",
+						"spi_cs6"};
+static const char * const xrx100_cgu_grps[] = {"clkout0", "clkout1",
+						"clkout2", "clkout3"};
+static const char * const xrx100_ebu_grps[] = {"ebu a23", "ebu a24",
+						"ebu a25", "ebu cs1",
+						"ebu wait", "ebu clk",
+						"nand ale", "nand cs1",
+						"nand cle", "nand rdy",
+						"nand rd"};
+static const char * const xrx100_exin_grps[] = {"exin0", "exin1", "exin2",
+						"exin3", "exin4", "exin5"};
+static const char * const xrx100_gpt_grps[] = {"gpt1", "gpt2", "gpt3"};
+static const char * const xrx100_asc_grps[] = {"asc0", "asc0 cts rts"};
+static const char * const xrx100_stp_grps[] = {"stp"};
+static const char * const xrx100_nmi_grps[] = {"nmi"};
+static const char * const xrx100_mdio_grps[] = {"mdio"};
+static const char * const xrx100_dfe_grps[] = {"dfe led0", "dfe led1"};
+
+static const struct ltq_pmx_func xrx100_funcs[] = {
+	{"spi",		ARRAY_AND_SIZE(xrx100_spi_grps)},
+	{"asc",		ARRAY_AND_SIZE(xrx100_asc_grps)},
+	{"cgu",		ARRAY_AND_SIZE(xrx100_cgu_grps)},
+	{"exin",	ARRAY_AND_SIZE(xrx100_exin_grps)},
+	{"stp",		ARRAY_AND_SIZE(xrx100_stp_grps)},
+	{"gpt",		ARRAY_AND_SIZE(xrx100_gpt_grps)},
+	{"nmi",		ARRAY_AND_SIZE(xrx100_nmi_grps)},
+	{"pci",		ARRAY_AND_SIZE(xrx100_pci_grps)},
+	{"ebu",		ARRAY_AND_SIZE(xrx100_ebu_grps)},
+	{"mdio",	ARRAY_AND_SIZE(xrx100_mdio_grps)},
+	{"dfe",		ARRAY_AND_SIZE(xrx100_dfe_grps)},
+};
+
+/* ---------  xrx200 related code --------- */
+#define XRX200_MAX_PIN		50
+
+static const struct ltq_mfp_pin xrx200_mfp[] = {
+	/*       pin    f0	f1	f2	f3   */
+	MFP_XWAY(GPIO0, GPIO,	EXIN,	SDIO,	TDM),
+	MFP_XWAY(GPIO1, GPIO,	EXIN,	CBUS,	SIN),
+	MFP_XWAY(GPIO2, GPIO,	CGU,	EXIN,	GPHY),
+	MFP_XWAY(GPIO3, GPIO,	CGU,	SDIO,	PCI),
+	MFP_XWAY(GPIO4, GPIO,	STP,	DFE,	USIF),
+	MFP_XWAY(GPIO5, GPIO,	STP,	GPHY,	DFE),
+	MFP_XWAY(GPIO6, GPIO,	STP,	GPT,	USIF),
+	MFP_XWAY(GPIO7, GPIO,	CGU,	CBUS,	GPHY),
+	MFP_XWAY(GPIO8, GPIO,	CGU,	NMI,	NONE),
+	MFP_XWAY(GPIO9, GPIO,	USIF,	SPI,	EXIN),
+	MFP_XWAY(GPIO10, GPIO,	USIF,	SPI,	EXIN),
+	MFP_XWAY(GPIO11, GPIO,	USIF,	CBUS,	SPI),
+	MFP_XWAY(GPIO12, GPIO,	USIF,	CBUS,	MCD),
+	MFP_XWAY(GPIO13, GPIO,	EBU,	SPI,	NONE),
+	MFP_XWAY(GPIO14, GPIO,	CGU,	CBUS,	USIF),
+	MFP_XWAY(GPIO15, GPIO,	SPI,	SDIO,	MCD),
+	MFP_XWAY(GPIO16, GPIO,	SPI,	SDIO,	NONE),
+	MFP_XWAY(GPIO17, GPIO,	SPI,	SDIO,	NONE),
+	MFP_XWAY(GPIO18, GPIO,	SPI,	SDIO,	NONE),
+	MFP_XWAY(GPIO19, GPIO,	PCI,	SDIO,	CGU),
+	MFP_XWAY(GPIO20, GPIO,	NONE,	SDIO,	EBU),
+	MFP_XWAY(GPIO21, GPIO,	PCI,	EBU,	GPT),
+	MFP_XWAY(GPIO22, GPIO,	SPI,	CGU,	EBU),
+	MFP_XWAY(GPIO23, GPIO,	EBU,	PCI,	STP),
+	MFP_XWAY(GPIO24, GPIO,	EBU,	TDM,	PCI),
+	MFP_XWAY(GPIO25, GPIO,	TDM,	SDIO,	USIF),
+	MFP_XWAY(GPIO26, GPIO,	EBU,	TDM,	SDIO),
+	MFP_XWAY(GPIO27, GPIO,	TDM,	SDIO,	USIF),
+	MFP_XWAY(GPIO28, GPIO,	GPT,	PCI,	SDIO),
+	MFP_XWAY(GPIO29, GPIO,	PCI,	CBUS,	EXIN),
+	MFP_XWAY(GPIO30, GPIO,	PCI,	CBUS,	NONE),
+	MFP_XWAY(GPIO31, GPIO,	EBU,	PCI,	NONE),
+	MFP_XWAY(GPIO32, GPIO,	MII,	NONE,	EBU),
+	MFP_XWAY(GPIO33, GPIO,	MII,	NONE,	EBU),
+	MFP_XWAY(GPIO34, GPIO,	SIN,	SSI,	NONE),
+	MFP_XWAY(GPIO35, GPIO,	SIN,	SSI,	NONE),
+	MFP_XWAY(GPIO36, GPIO,	SIN,	SSI,	EXIN),
+	MFP_XWAY(GPIO37, GPIO,	USIF,	NONE,	PCI),
+	MFP_XWAY(GPIO38, GPIO,	PCI,	USIF,	NONE),
+	MFP_XWAY(GPIO39, GPIO,	USIF,	EXIN,	NONE),
+	MFP_XWAY(GPIO40, GPIO,	MII,	TDM,	NONE),
+	MFP_XWAY(GPIO41, GPIO,	MII,	TDM,	NONE),
+	MFP_XWAY(GPIO42, GPIO,	MDIO,	NONE,	NONE),
+	MFP_XWAY(GPIO43, GPIO,	MDIO,	NONE,	NONE),
+	MFP_XWAY(GPIO44, GPIO,	MII,	SIN,	GPHY),
+	MFP_XWAY(GPIO45, GPIO,	MII,	GPHY,	SIN),
+	MFP_XWAY(GPIO46, GPIO,	MII,	NONE,	EXIN),
+	MFP_XWAY(GPIO47, GPIO,	MII,	GPHY,	SIN),
+	MFP_XWAY(GPIO48, GPIO,	EBU,	NONE,	NONE),
+	MFP_XWAY(GPIO49, GPIO,	EBU,	NONE,	NONE),
+};
+
+static const unsigned xrx200_exin_pin_map[] = {GPIO0, GPIO1, GPIO2, GPIO39, GPIO10, GPIO9};
+
+static const unsigned xrx200_pins_exin0[] = {GPIO0};
+static const unsigned xrx200_pins_exin1[] = {GPIO1};
+static const unsigned xrx200_pins_exin2[] = {GPIO2};
+static const unsigned xrx200_pins_exin3[] = {GPIO39};
+static const unsigned xrx200_pins_exin4[] = {GPIO10};
+static const unsigned xrx200_pins_exin5[] = {GPIO9};
+
+static const unsigned xrx200_pins_usif_uart_rx[] = {GPIO11};
+static const unsigned xrx200_pins_usif_uart_tx[] = {GPIO12};
+static const unsigned xrx200_pins_usif_uart_rts[] = {GPIO9};
+static const unsigned xrx200_pins_usif_uart_cts[] = {GPIO10};
+static const unsigned xrx200_pins_usif_uart_dtr[] = {GPIO4};
+static const unsigned xrx200_pins_usif_uart_dsr[] = {GPIO6};
+static const unsigned xrx200_pins_usif_uart_dcd[] = {GPIO25};
+static const unsigned xrx200_pins_usif_uart_ri[] = {GPIO27};
+
+static const unsigned xrx200_pins_usif_spi_di[] = {GPIO11};
+static const unsigned xrx200_pins_usif_spi_do[] = {GPIO12};
+static const unsigned xrx200_pins_usif_spi_clk[] = {GPIO38};
+static const unsigned xrx200_pins_usif_spi_cs0[] = {GPIO37};
+static const unsigned xrx200_pins_usif_spi_cs1[] = {GPIO39};
+static const unsigned xrx200_pins_usif_spi_cs2[] = {GPIO14};
+
+static const unsigned xrx200_pins_stp[] = {GPIO4, GPIO5, GPIO6};
+static const unsigned xrx200_pins_nmi[] = {GPIO8};
+static const unsigned xrx200_pins_mdio[] = {GPIO42, GPIO43};
+
+static const unsigned xrx200_pins_dfe_led0[] = {GPIO4};
+static const unsigned xrx200_pins_dfe_led1[] = {GPIO5};
+
+static const unsigned xrx200_pins_gphy0_led0[] = {GPIO5};
+static const unsigned xrx200_pins_gphy0_led1[] = {GPIO7};
+static const unsigned xrx200_pins_gphy0_led2[] = {GPIO2};
+static const unsigned xrx200_pins_gphy1_led0[] = {GPIO44};
+static const unsigned xrx200_pins_gphy1_led1[] = {GPIO45};
+static const unsigned xrx200_pins_gphy1_led2[] = {GPIO47};
+
+static const unsigned xrx200_pins_ebu_a24[] = {GPIO13};
+static const unsigned xrx200_pins_ebu_clk[] = {GPIO21};
+static const unsigned xrx200_pins_ebu_cs1[] = {GPIO23};
+static const unsigned xrx200_pins_ebu_a23[] = {GPIO24};
+static const unsigned xrx200_pins_ebu_wait[] = {GPIO26};
+static const unsigned xrx200_pins_ebu_a25[] = {GPIO31};
+
+static const unsigned xrx200_pins_nand_ale[] = {GPIO13};
+static const unsigned xrx200_pins_nand_cs1[] = {GPIO23};
+static const unsigned xrx200_pins_nand_cle[] = {GPIO24};
+static const unsigned xrx200_pins_nand_rdy[] = {GPIO48};
+static const unsigned xrx200_pins_nand_rd[] = {GPIO49};
+
+static const unsigned xrx200_pins_spi_di[] = {GPIO16};
+static const unsigned xrx200_pins_spi_do[] = {GPIO17};
+static const unsigned xrx200_pins_spi_clk[] = {GPIO18};
+static const unsigned xrx200_pins_spi_cs1[] = {GPIO15};
+static const unsigned xrx200_pins_spi_cs2[] = {GPIO22};
+static const unsigned xrx200_pins_spi_cs3[] = {GPIO13};
+static const unsigned xrx200_pins_spi_cs4[] = {GPIO10};
+static const unsigned xrx200_pins_spi_cs5[] = {GPIO9};
+static const unsigned xrx200_pins_spi_cs6[] = {GPIO11};
+
+static const unsigned xrx200_pins_gpt1[] = {GPIO28};
+static const unsigned xrx200_pins_gpt2[] = {GPIO21};
+static const unsigned xrx200_pins_gpt3[] = {GPIO6};
+
+static const unsigned xrx200_pins_clkout0[] = {GPIO8};
+static const unsigned xrx200_pins_clkout1[] = {GPIO7};
+static const unsigned xrx200_pins_clkout2[] = {GPIO3};
+static const unsigned xrx200_pins_clkout3[] = {GPIO2};
+
+static const unsigned xrx200_pins_pci_gnt1[] = {GPIO28};
+static const unsigned xrx200_pins_pci_gnt2[] = {GPIO23};
+static const unsigned xrx200_pins_pci_gnt3[] = {GPIO19};
+static const unsigned xrx200_pins_pci_gnt4[] = {GPIO38};
+static const unsigned xrx200_pins_pci_req1[] = {GPIO29};
+static const unsigned xrx200_pins_pci_req2[] = {GPIO31};
+static const unsigned xrx200_pins_pci_req3[] = {GPIO3};
+static const unsigned xrx200_pins_pci_req4[] = {GPIO37};
+
+static const struct ltq_pin_group xrx200_grps[] = {
+	GRP_MUX("exin0", EXIN, xrx200_pins_exin0),
+	GRP_MUX("exin1", EXIN, xrx200_pins_exin1),
+	GRP_MUX("exin2", EXIN, xrx200_pins_exin2),
+	GRP_MUX("exin3", EXIN, xrx200_pins_exin3),
+	GRP_MUX("exin4", EXIN, xrx200_pins_exin4),
+	GRP_MUX("exin5", EXIN, xrx200_pins_exin5),
+	GRP_MUX("ebu a23", EBU, xrx200_pins_ebu_a23),
+	GRP_MUX("ebu a24", EBU, xrx200_pins_ebu_a24),
+	GRP_MUX("ebu a25", EBU, xrx200_pins_ebu_a25),
+	GRP_MUX("ebu clk", EBU, xrx200_pins_ebu_clk),
+	GRP_MUX("ebu cs1", EBU, xrx200_pins_ebu_cs1),
+	GRP_MUX("ebu wait", EBU, xrx200_pins_ebu_wait),
+	GRP_MUX("nand ale", EBU, xrx200_pins_nand_ale),
+	GRP_MUX("nand cs1", EBU, xrx200_pins_nand_cs1),
+	GRP_MUX("nand cle", EBU, xrx200_pins_nand_cle),
+	GRP_MUX("nand rdy", EBU, xrx200_pins_nand_rdy),
+	GRP_MUX("nand rd", EBU, xrx200_pins_nand_rd),
+	GRP_MUX("spi_di", SPI, xrx200_pins_spi_di),
+	GRP_MUX("spi_do", SPI, xrx200_pins_spi_do),
+	GRP_MUX("spi_clk", SPI, xrx200_pins_spi_clk),
+	GRP_MUX("spi_cs1", SPI, xrx200_pins_spi_cs1),
+	GRP_MUX("spi_cs2", SPI, xrx200_pins_spi_cs2),
+	GRP_MUX("spi_cs3", SPI, xrx200_pins_spi_cs3),
+	GRP_MUX("spi_cs4", SPI, xrx200_pins_spi_cs4),
+	GRP_MUX("spi_cs5", SPI, xrx200_pins_spi_cs5),
+	GRP_MUX("spi_cs6", SPI, xrx200_pins_spi_cs6),
+	GRP_MUX("usif uart_rx", USIF, xrx200_pins_usif_uart_rx),
+	GRP_MUX("usif uart_rx", USIF, xrx200_pins_usif_uart_tx),
+	GRP_MUX("usif uart_rts", USIF, xrx200_pins_usif_uart_rts),
+	GRP_MUX("usif uart_cts", USIF, xrx200_pins_usif_uart_cts),
+	GRP_MUX("usif uart_dtr", USIF, xrx200_pins_usif_uart_dtr),
+	GRP_MUX("usif uart_dsr", USIF, xrx200_pins_usif_uart_dsr),
+	GRP_MUX("usif uart_dcd", USIF, xrx200_pins_usif_uart_dcd),
+	GRP_MUX("usif uart_ri", USIF, xrx200_pins_usif_uart_ri),
+	GRP_MUX("usif spi_di", USIF, xrx200_pins_usif_spi_di),
+	GRP_MUX("usif spi_do", USIF, xrx200_pins_usif_spi_do),
+	GRP_MUX("usif spi_clk", USIF, xrx200_pins_usif_spi_clk),
+	GRP_MUX("usif spi_cs0", USIF, xrx200_pins_usif_spi_cs0),
+	GRP_MUX("usif spi_cs1", USIF, xrx200_pins_usif_spi_cs1),
+	GRP_MUX("usif spi_cs2", USIF, xrx200_pins_usif_spi_cs2),
+	GRP_MUX("stp", STP, xrx200_pins_stp),
+	GRP_MUX("nmi", NMI, xrx200_pins_nmi),
+	GRP_MUX("gpt1", GPT, xrx200_pins_gpt1),
+	GRP_MUX("gpt2", GPT, xrx200_pins_gpt2),
+	GRP_MUX("gpt3", GPT, xrx200_pins_gpt3),
+	GRP_MUX("clkout0", CGU, xrx200_pins_clkout0),
+	GRP_MUX("clkout1", CGU, xrx200_pins_clkout1),
+	GRP_MUX("clkout2", CGU, xrx200_pins_clkout2),
+	GRP_MUX("clkout3", CGU, xrx200_pins_clkout3),
+	GRP_MUX("gnt1", PCI, xrx200_pins_pci_gnt1),
+	GRP_MUX("gnt2", PCI, xrx200_pins_pci_gnt2),
+	GRP_MUX("gnt3", PCI, xrx200_pins_pci_gnt3),
+	GRP_MUX("gnt4", PCI, xrx200_pins_pci_gnt4),
+	GRP_MUX("req1", PCI, xrx200_pins_pci_req1),
+	GRP_MUX("req2", PCI, xrx200_pins_pci_req2),
+	GRP_MUX("req3", PCI, xrx200_pins_pci_req3),
+	GRP_MUX("req4", PCI, xrx200_pins_pci_req4),
+	GRP_MUX("mdio", MDIO, xrx200_pins_mdio),
+	GRP_MUX("dfe led0", DFE, xrx200_pins_dfe_led0),
+	GRP_MUX("dfe led1", DFE, xrx200_pins_dfe_led1),
+	GRP_MUX("gphy0 led0", GPHY, xrx200_pins_gphy0_led0),
+	GRP_MUX("gphy0 led1", GPHY, xrx200_pins_gphy0_led1),
+	GRP_MUX("gphy0 led2", GPHY, xrx200_pins_gphy0_led2),
+	GRP_MUX("gphy1 led0", GPHY, xrx200_pins_gphy1_led0),
+	GRP_MUX("gphy1 led1", GPHY, xrx200_pins_gphy1_led1),
+	GRP_MUX("gphy1 led2", GPHY, xrx200_pins_gphy1_led2),
+};
+
+static const char * const xrx200_pci_grps[] = {"gnt1", "gnt2",
+						"gnt3", "gnt4",
+						"req1", "req2",
+						"req3", "req4"};
+static const char * const xrx200_spi_grps[] = {"spi_di", "spi_do",
+						"spi_clk", "spi_cs1",
+						"spi_cs2", "spi_cs3",
+						"spi_cs4", "spi_cs5",
+						"spi_cs6"};
+static const char * const xrx200_cgu_grps[] = {"clkout0", "clkout1",
+						"clkout2", "clkout3"};
+static const char * const xrx200_ebu_grps[] = {"ebu a23", "ebu a24",
+						"ebu a25", "ebu cs1",
+						"ebu wait", "ebu clk",
+						"nand ale", "nand cs1",
+						"nand cle", "nand rdy",
+						"nand rd"};
+static const char * const xrx200_exin_grps[] = {"exin0", "exin1", "exin2",
+						"exin3", "exin4", "exin5"};
+static const char * const xrx200_gpt_grps[] = {"gpt1", "gpt2", "gpt3"};
+static const char * const xrx200_usif_grps[] = {"usif uart_rx", "usif uart_tx",
+						"usif uart_rts", "usif uart_cts",
+						"usif uart_dtr", "usif uart_dsr",
+						"usif uart_dcd", "usif uart_ri",
+						"usif spi_di", "usif spi_do",
+						"usif spi_clk", "usif spi_cs0",
+						"usif spi_cs1", "usif spi_cs2"};
+static const char * const xrx200_stp_grps[] = {"stp"};
+static const char * const xrx200_nmi_grps[] = {"nmi"};
+static const char * const xrx200_mdio_grps[] = {"mdio"};
+static const char * const xrx200_dfe_grps[] = {"dfe led0", "dfe led1"};
+static const char * const xrx200_gphy_grps[] = {"gphy0 led0", "gphy0 led1",
+						"gphy0 led2", "gphy1 led0",
+						"gphy1 led1", "gphy1 led2"};
+
+static const struct ltq_pmx_func xrx200_funcs[] = {
+	{"spi",		ARRAY_AND_SIZE(xrx200_spi_grps)},
+	{"usif",	ARRAY_AND_SIZE(xrx200_usif_grps)},
+	{"cgu",		ARRAY_AND_SIZE(xrx200_cgu_grps)},
+	{"exin",	ARRAY_AND_SIZE(xrx200_exin_grps)},
+	{"stp",		ARRAY_AND_SIZE(xrx200_stp_grps)},
+	{"gpt",		ARRAY_AND_SIZE(xrx200_gpt_grps)},
+	{"nmi",		ARRAY_AND_SIZE(xrx200_nmi_grps)},
+	{"pci",		ARRAY_AND_SIZE(xrx200_pci_grps)},
+	{"ebu",		ARRAY_AND_SIZE(xrx200_ebu_grps)},
+	{"mdio",	ARRAY_AND_SIZE(xrx200_mdio_grps)},
+	{"dfe",		ARRAY_AND_SIZE(xrx200_dfe_grps)},
+	{"gphy",	ARRAY_AND_SIZE(xrx200_gphy_grps)},
+};
+
+/* ---------  xrx300 related code --------- */
+#define XRX300_MAX_PIN		64
+
+static const struct ltq_mfp_pin xrx300_mfp[] = {
+	/*       pin    f0	f1	f2	f3   */
+	MFP_XWAY(GPIO0, GPIO,	EXIN,	EPHY,	NONE),
+	MFP_XWAY(GPIO1, GPIO,	NONE,	EXIN,	NONE),
+	MFP_XWAY(GPIO2, NONE,	NONE,	NONE,	NONE),
+	MFP_XWAY(GPIO3, GPIO,	CGU,	NONE,	NONE),
+	MFP_XWAY(GPIO4, GPIO,	STP,	DFE,	NONE),
+	MFP_XWAY(GPIO5, GPIO,	STP,	EPHY,	DFE),
+	MFP_XWAY(GPIO6, GPIO,	STP,	NONE,	NONE),
+	MFP_XWAY(GPIO7, NONE,	NONE,	NONE,	NONE),
+	MFP_XWAY(GPIO8, GPIO,	CGU,	GPHY,	EPHY),
+	MFP_XWAY(GPIO9, GPIO,	WIFI,	NONE,	EXIN),
+	MFP_XWAY(GPIO10, GPIO,	USIF,	SPI,	EXIN),
+	MFP_XWAY(GPIO11, GPIO,	USIF,	WIFI,	SPI),
+	MFP_XWAY(GPIO12, NONE,	NONE,	NONE,	NONE),
+	MFP_XWAY(GPIO13, GPIO,	EBU,	NONE,	NONE),
+	MFP_XWAY(GPIO14, GPIO,	CGU,	USIF,	EPHY),
+	MFP_XWAY(GPIO15, GPIO,	SPI,	NONE,	MCD),
+	MFP_XWAY(GPIO16, GPIO,	SPI,	EXIN,	NONE),
+	MFP_XWAY(GPIO17, GPIO,	SPI,	NONE,	NONE),
+	MFP_XWAY(GPIO18, GPIO,	SPI,	NONE,	NONE),
+	MFP_XWAY(GPIO19, GPIO,	USIF,	NONE,	EPHY),
+	MFP_XWAY(GPIO20, NONE,	NONE,	NONE,	NONE),
+	MFP_XWAY(GPIO21, NONE,	NONE,	NONE,	NONE),
+	MFP_XWAY(GPIO22, NONE,	NONE,	NONE,	NONE),
+	MFP_XWAY(GPIO23, GPIO,	EBU,	NONE,	NONE),
+	MFP_XWAY(GPIO24, GPIO,	EBU,	NONE,	NONE),
+	MFP_XWAY(GPIO25, GPIO,	TDM,	NONE,	NONE),
+	MFP_XWAY(GPIO26, GPIO,	TDM,	NONE,	NONE),
+	MFP_XWAY(GPIO27, GPIO,	TDM,	NONE,	NONE),
+	MFP_XWAY(GPIO28, NONE,	NONE,	NONE,	NONE),
+	MFP_XWAY(GPIO29, NONE,	NONE,	NONE,	NONE),
+	MFP_XWAY(GPIO30, NONE,	NONE,	NONE,	NONE),
+	MFP_XWAY(GPIO31, NONE,	NONE,	NONE,	NONE),
+	MFP_XWAY(GPIO32, NONE,	NONE,	NONE,	NONE),
+	MFP_XWAY(GPIO33, NONE,	NONE,	NONE,	NONE),
+	MFP_XWAY(GPIO34, GPIO,	NONE,	SSI,	NONE),
+	MFP_XWAY(GPIO35, GPIO,	NONE,	SSI,	NONE),
+	MFP_XWAY(GPIO36, GPIO,	NONE,	SSI,	NONE),
+	MFP_XWAY(GPIO37, NONE,	NONE,	NONE,	NONE),
+	MFP_XWAY(GPIO38, NONE,	NONE,	NONE,	NONE),
+	MFP_XWAY(GPIO39, NONE,	NONE,	NONE,	NONE),
+	MFP_XWAY(GPIO40, NONE,	NONE,	NONE,	NONE),
+	MFP_XWAY(GPIO41, NONE,	NONE,	NONE,	NONE),
+	MFP_XWAY(GPIO42, GPIO,	MDIO,	NONE,	NONE),
+	MFP_XWAY(GPIO43, GPIO,	MDIO,	NONE,	NONE),
+	MFP_XWAY(GPIO44, NONE,	NONE,	NONE,	NONE),
+	MFP_XWAY(GPIO45, NONE,	NONE,	NONE,	NONE),
+	MFP_XWAY(GPIO46, NONE,	NONE,	NONE,	NONE),
+	MFP_XWAY(GPIO47, NONE,	NONE,	NONE,	NONE),
+	MFP_XWAY(GPIO48, GPIO,	EBU,	NONE,	NONE),
+	MFP_XWAY(GPIO49, GPIO,	EBU,	NONE,	NONE),
+	MFP_XWAY(GPIO50, GPIO,	EBU,	NONE,	NONE),
+	MFP_XWAY(GPIO51, GPIO,	EBU,	NONE,	NONE),
+	MFP_XWAY(GPIO52, GPIO,	EBU,	NONE,	NONE),
+	MFP_XWAY(GPIO53, GPIO,	EBU,	NONE,	NONE),
+	MFP_XWAY(GPIO54, GPIO,	EBU,	NONE,	NONE),
+	MFP_XWAY(GPIO55, GPIO,	EBU,	NONE,	NONE),
+	MFP_XWAY(GPIO56, GPIO,	EBU,	NONE,	NONE),
+	MFP_XWAY(GPIO57, GPIO,	EBU,	NONE,	NONE),
+	MFP_XWAY(GPIO58, GPIO,	EBU,	TDM,	NONE),
+	MFP_XWAY(GPIO59, GPIO,	EBU,	NONE,	NONE),
+	MFP_XWAY(GPIO60, GPIO,	EBU,	NONE,	NONE),
+	MFP_XWAY(GPIO61, GPIO,	EBU,	NONE,	NONE),
+	MFP_XWAY(GPIO62, NONE,	NONE,	NONE,	NONE),
+	MFP_XWAY(GPIO63, NONE,	NONE,	NONE,	NONE),
+};
+
+static const unsigned xrx300_exin_pin_map[] = {GPIO0, GPIO1, GPIO16, GPIO10, GPIO9};
+
+static const unsigned xrx300_pins_exin0[] = {GPIO0};
+static const unsigned xrx300_pins_exin1[] = {GPIO1};
+static const unsigned xrx300_pins_exin2[] = {GPIO16};
+/* EXIN3 is not available on xrX300 */
+static const unsigned xrx300_pins_exin4[] = {GPIO10};
+static const unsigned xrx300_pins_exin5[] = {GPIO9};
+
+static const unsigned xrx300_pins_usif_uart_rx[] = {GPIO11};
+static const unsigned xrx300_pins_usif_uart_tx[] = {GPIO10};
+
+static const unsigned xrx300_pins_usif_spi_di[] = {GPIO11};
+static const unsigned xrx300_pins_usif_spi_do[] = {GPIO10};
+static const unsigned xrx300_pins_usif_spi_clk[] = {GPIO19};
+static const unsigned xrx300_pins_usif_spi_cs0[] = {GPIO14};
+
+static const unsigned xrx300_pins_stp[] = {GPIO4, GPIO5, GPIO6};
+static const unsigned xrx300_pins_mdio[] = {GPIO42, GPIO43};
+
+static const unsigned xrx300_pins_dfe_led0[] = {GPIO4};
+static const unsigned xrx300_pins_dfe_led1[] = {GPIO5};
+
+static const unsigned xrx300_pins_ephy0_led0[] = {GPIO5};
+static const unsigned xrx300_pins_ephy0_led1[] = {GPIO8};
+static const unsigned xrx300_pins_ephy1_led0[] = {GPIO14};
+static const unsigned xrx300_pins_ephy1_led1[] = {GPIO19};
+
+static const unsigned xrx300_pins_nand_ale[] = {GPIO13};
+static const unsigned xrx300_pins_nand_cs1[] = {GPIO23};
+static const unsigned xrx300_pins_nand_cle[] = {GPIO24};
+static const unsigned xrx300_pins_nand_rdy[] = {GPIO48};
+static const unsigned xrx300_pins_nand_rd[] = {GPIO49};
+static const unsigned xrx300_pins_nand_d1[] = {GPIO50};
+static const unsigned xrx300_pins_nand_d0[] = {GPIO51};
+static const unsigned xrx300_pins_nand_d2[] = {GPIO52};
+static const unsigned xrx300_pins_nand_d7[] = {GPIO53};
+static const unsigned xrx300_pins_nand_d6[] = {GPIO54};
+static const unsigned xrx300_pins_nand_d5[] = {GPIO55};
+static const unsigned xrx300_pins_nand_d4[] = {GPIO56};
+static const unsigned xrx300_pins_nand_d3[] = {GPIO57};
+static const unsigned xrx300_pins_nand_cs0[] = {GPIO58};
+static const unsigned xrx300_pins_nand_wr[] = {GPIO59};
+static const unsigned xrx300_pins_nand_wp[] = {GPIO60};
+static const unsigned xrx300_pins_nand_se[] = {GPIO61};
+
+static const unsigned xrx300_pins_spi_di[] = {GPIO16};
+static const unsigned xrx300_pins_spi_do[] = {GPIO17};
+static const unsigned xrx300_pins_spi_clk[] = {GPIO18};
+static const unsigned xrx300_pins_spi_cs1[] = {GPIO15};
+/* SPI_CS2 is not available on xrX300 */
+/* SPI_CS3 is not available on xrX300 */
+static const unsigned xrx300_pins_spi_cs4[] = {GPIO10};
+/* SPI_CS5 is not available on xrX300 */
+static const unsigned xrx300_pins_spi_cs6[] = {GPIO11};
+
+/* CLKOUT0 is not available on xrX300 */
+/* CLKOUT1 is not available on xrX300 */
+static const unsigned xrx300_pins_clkout2[] = {GPIO3};
+
+static const struct ltq_pin_group xrx300_grps[] = {
+	GRP_MUX("exin0", EXIN, xrx300_pins_exin0),
+	GRP_MUX("exin1", EXIN, xrx300_pins_exin1),
+	GRP_MUX("exin2", EXIN, xrx300_pins_exin2),
+	GRP_MUX("exin4", EXIN, xrx300_pins_exin4),
+	GRP_MUX("exin5", EXIN, xrx300_pins_exin5),
+	GRP_MUX("nand ale", EBU, xrx300_pins_nand_ale),
+	GRP_MUX("nand cs1", EBU, xrx300_pins_nand_cs1),
+	GRP_MUX("nand cle", EBU, xrx300_pins_nand_cle),
+	GRP_MUX("nand rdy", EBU, xrx300_pins_nand_rdy),
+	GRP_MUX("nand rd", EBU, xrx300_pins_nand_rd),
+	GRP_MUX("nand d1", EBU, xrx300_pins_nand_d1),
+	GRP_MUX("nand d0", EBU, xrx300_pins_nand_d0),
+	GRP_MUX("nand d2", EBU, xrx300_pins_nand_d2),
+	GRP_MUX("nand d7", EBU, xrx300_pins_nand_d7),
+	GRP_MUX("nand d6", EBU, xrx300_pins_nand_d6),
+	GRP_MUX("nand d5", EBU, xrx300_pins_nand_d5),
+	GRP_MUX("nand d4", EBU, xrx300_pins_nand_d4),
+	GRP_MUX("nand d3", EBU, xrx300_pins_nand_d3),
+	GRP_MUX("nand cs0", EBU, xrx300_pins_nand_cs0),
+	GRP_MUX("nand wr", EBU, xrx300_pins_nand_wr),
+	GRP_MUX("nand wp", EBU, xrx300_pins_nand_wp),
+	GRP_MUX("nand se", EBU, xrx300_pins_nand_se),
+	GRP_MUX("spi_di", SPI, xrx300_pins_spi_di),
+	GRP_MUX("spi_do", SPI, xrx300_pins_spi_do),
+	GRP_MUX("spi_clk", SPI, xrx300_pins_spi_clk),
+	GRP_MUX("spi_cs1", SPI, xrx300_pins_spi_cs1),
+	GRP_MUX("spi_cs4", SPI, xrx300_pins_spi_cs4),
+	GRP_MUX("spi_cs6", SPI, xrx300_pins_spi_cs6),
+	GRP_MUX("usif uart_rx", USIF, xrx300_pins_usif_uart_rx),
+	GRP_MUX("usif uart_tx", USIF, xrx300_pins_usif_uart_tx),
+	GRP_MUX("usif spi_di", USIF, xrx300_pins_usif_spi_di),
+	GRP_MUX("usif spi_do", USIF, xrx300_pins_usif_spi_do),
+	GRP_MUX("usif spi_clk", USIF, xrx300_pins_usif_spi_clk),
+	GRP_MUX("usif spi_cs0", USIF, xrx300_pins_usif_spi_cs0),
+	GRP_MUX("stp", STP, xrx300_pins_stp),
+	GRP_MUX("clkout2", CGU, xrx300_pins_clkout2),
+	GRP_MUX("mdio", MDIO, xrx300_pins_mdio),
+	GRP_MUX("dfe led0", DFE, xrx300_pins_dfe_led0),
+	GRP_MUX("dfe led1", DFE, xrx300_pins_dfe_led1),
+	GRP_MUX("ephy0 led0", GPHY, xrx300_pins_ephy0_led0),
+	GRP_MUX("ephy0 led1", GPHY, xrx300_pins_ephy0_led1),
+	GRP_MUX("ephy1 led0", GPHY, xrx300_pins_ephy1_led0),
+	GRP_MUX("ephy1 led1", GPHY, xrx300_pins_ephy1_led1),
+};
+
+static const char * const xrx300_spi_grps[] = {"spi_di", "spi_do",
+						"spi_clk", "spi_cs1",
+						"spi_cs4", "spi_cs6"};
+static const char * const xrx300_cgu_grps[] = {"clkout2"};
+static const char * const xrx300_ebu_grps[] = {"nand ale", "nand cs1",
+						"nand cle", "nand rdy",
+						"nand rd", "nand d1",
+						"nand d0", "nand d2",
+						"nand d7", "nand d6",
+						"nand d5", "nand d4",
+						"nand d3", "nand cs0",
+						"nand wr", "nand wp",
+						"nand se"};
+static const char * const xrx300_exin_grps[] = {"exin0", "exin1", "exin2",
+						"exin4", "exin5"};
+static const char * const xrx300_usif_grps[] = {"usif uart_rx", "usif uart_tx",
+						"usif spi_di", "usif spi_do",
+						"usif spi_clk", "usif spi_cs0"};
+static const char * const xrx300_stp_grps[] = {"stp"};
+static const char * const xrx300_mdio_grps[] = {"mdio"};
+static const char * const xrx300_dfe_grps[] = {"dfe led0", "dfe led1"};
+static const char * const xrx300_gphy_grps[] = {"ephy0 led0", "ephy0 led1",
+						"ephy1 led0", "ephy1 led1"};
+
+static const struct ltq_pmx_func xrx300_funcs[] = {
+	{"spi",		ARRAY_AND_SIZE(xrx300_spi_grps)},
+	{"usif",	ARRAY_AND_SIZE(xrx300_usif_grps)},
+	{"cgu",		ARRAY_AND_SIZE(xrx300_cgu_grps)},
+	{"exin",	ARRAY_AND_SIZE(xrx300_exin_grps)},
+	{"stp",		ARRAY_AND_SIZE(xrx300_stp_grps)},
+	{"ebu",		ARRAY_AND_SIZE(xrx300_ebu_grps)},
+	{"mdio",	ARRAY_AND_SIZE(xrx300_mdio_grps)},
+	{"dfe",		ARRAY_AND_SIZE(xrx300_dfe_grps)},
+	{"ephy",	ARRAY_AND_SIZE(xrx300_gphy_grps)},
+};
+
 /* ---------  pinconf related code --------- */
 static int xway_pinconf_get(struct pinctrl_dev *pctldev,
 				unsigned pin,
@@ -676,6 +1563,10 @@
 {
 	struct ltq_pinmux_info *info = dev_get_drvdata(chip->dev);
 
+	if (PORT(pin) == PORT3)
+		gpio_setbit(info->membase[0], GPIO3_OD, PORT_PIN(pin));
+	else
+		gpio_setbit(info->membase[0], GPIO_OD(pin), PORT_PIN(pin));
 	gpio_setbit(info->membase[0], GPIO_DIR(pin), PORT_PIN(pin));
 	xway_gpio_set(chip, pin, val);
 
@@ -695,10 +1586,7 @@
 
 
 /* --------- register the pinctrl layer --------- */
-static const unsigned xway_exin_pin_map[] = {GPIO0, GPIO1, GPIO2, GPIO39, GPIO46, GPIO9};
-static const unsigned ase_exin_pins_map[] = {GPIO6, GPIO29, GPIO0};
-
-static struct pinctrl_xway_soc {
+struct pinctrl_xway_soc {
 	int pin_count;
 	const struct ltq_mfp_pin *mfp;
 	const struct ltq_pin_group *grps;
@@ -707,22 +1595,54 @@
 	unsigned int num_funcs;
 	const unsigned *exin;
 	unsigned int num_exin;
-} soc_cfg[] = {
-	/* legacy xway */
-	{XWAY_MAX_PIN, xway_mfp,
-		xway_grps, ARRAY_SIZE(xway_grps),
-		danube_funcs, ARRAY_SIZE(danube_funcs),
-		xway_exin_pin_map, 3},
-	/* xway xr9 series */
-	{XR9_MAX_PIN, xway_mfp,
-		xway_grps, ARRAY_SIZE(xway_grps),
-		xrx_funcs, ARRAY_SIZE(xrx_funcs),
-		xway_exin_pin_map, 6},
-	/* xway ase series */
-	{XWAY_MAX_PIN, ase_mfp,
-		ase_grps, ARRAY_SIZE(ase_grps),
-		ase_funcs, ARRAY_SIZE(ase_funcs),
-		ase_exin_pins_map, 3},
+};
+
+/* xway xr9 series (DEPRECATED: Use XWAY xRX100/xRX200 Family) */
+static struct pinctrl_xway_soc xr9_pinctrl = {
+	XR9_MAX_PIN, xway_mfp,
+	xway_grps, ARRAY_SIZE(xway_grps),
+	xrx_funcs, ARRAY_SIZE(xrx_funcs),
+	xway_exin_pin_map, 6
+};
+
+/* XWAY AMAZON Family */
+static struct pinctrl_xway_soc ase_pinctrl = {
+	ASE_MAX_PIN, ase_mfp,
+	ase_grps, ARRAY_SIZE(ase_grps),
+	ase_funcs, ARRAY_SIZE(ase_funcs),
+	ase_exin_pin_map, 3
+};
+
+/* XWAY DANUBE Family */
+static struct pinctrl_xway_soc danube_pinctrl = {
+	DANUBE_MAX_PIN, danube_mfp,
+	danube_grps, ARRAY_SIZE(danube_grps),
+	danube_funcs, ARRAY_SIZE(danube_funcs),
+	danube_exin_pin_map, 3
+};
+
+/* XWAY xRX100 Family */
+static struct pinctrl_xway_soc xrx100_pinctrl = {
+	XRX100_MAX_PIN, xrx100_mfp,
+	xrx100_grps, ARRAY_SIZE(xrx100_grps),
+	xrx100_funcs, ARRAY_SIZE(xrx100_funcs),
+	xrx100_exin_pin_map, 6
+};
+
+/* XWAY xRX200 Family */
+static struct pinctrl_xway_soc xrx200_pinctrl = {
+	XRX200_MAX_PIN, xrx200_mfp,
+	xrx200_grps, ARRAY_SIZE(xrx200_grps),
+	xrx200_funcs, ARRAY_SIZE(xrx200_funcs),
+	xrx200_exin_pin_map, 6
+};
+
+/* XWAY xRX300 Family */
+static struct pinctrl_xway_soc xrx300_pinctrl = {
+	XRX300_MAX_PIN, xrx300_mfp,
+	xrx300_grps, ARRAY_SIZE(xrx300_grps),
+	xrx300_funcs, ARRAY_SIZE(xrx300_funcs),
+	xrx300_exin_pin_map, 5
 };
 
 static struct pinctrl_gpio_range xway_gpio_range = {
@@ -731,9 +1651,14 @@
 };
 
 static const struct of_device_id xway_match[] = {
-	{ .compatible = "lantiq,pinctrl-xway", .data = &soc_cfg[0]},
-	{ .compatible = "lantiq,pinctrl-xr9", .data = &soc_cfg[1]},
-	{ .compatible = "lantiq,pinctrl-ase", .data = &soc_cfg[2]},
+	{ .compatible = "lantiq,pinctrl-xway", .data = &danube_pinctrl}, /*DEPRECATED*/
+	{ .compatible = "lantiq,pinctrl-xr9", .data = &xr9_pinctrl}, /*DEPRECATED*/
+	{ .compatible = "lantiq,pinctrl-ase", .data = &ase_pinctrl}, /*DEPRECATED*/
+	{ .compatible = "lantiq,ase-pinctrl", .data = &ase_pinctrl},
+	{ .compatible = "lantiq,danube-pinctrl", .data = &danube_pinctrl},
+	{ .compatible = "lantiq,xrx100-pinctrl", .data = &xrx100_pinctrl},
+	{ .compatible = "lantiq,xrx200-pinctrl", .data = &xrx200_pinctrl},
+	{ .compatible = "lantiq,xrx300-pinctrl", .data = &xrx300_pinctrl},
 	{},
 };
 MODULE_DEVICE_TABLE(of, xway_match);
@@ -755,7 +1680,7 @@
 	if (match)
 		xway_soc = (const struct pinctrl_xway_soc *) match->data;
 	else
-		xway_soc = &soc_cfg[0];
+		xway_soc = &danube_pinctrl;
 
 	/* find out how many pads we have */
 	xway_chip.ngpio = xway_soc->pin_count;
diff --git a/drivers/pinctrl/pxa/Kconfig b/drivers/pinctrl/pxa/Kconfig
new file mode 100644
index 0000000..990667f
--- /dev/null
+++ b/drivers/pinctrl/pxa/Kconfig
@@ -0,0 +1,17 @@
+if (ARCH_PXA || COMPILE_TEST)
+
+config PINCTRL_PXA
+	bool
+	select PINMUX
+	select PINCONF
+	select GENERIC_PINCONF
+
+config PINCTRL_PXA27X
+	tristate "Marvell PXA27x pin controller driver"
+	select PINCTRL_PXA
+	default y if PXA27x
+	help
+	  This is the pinctrl, pinmux, pinconf driver for the Marvell
+	  PXA2xx block found in the pxa25x and pxa27x platforms.
+
+endif
diff --git a/drivers/pinctrl/pxa/Makefile b/drivers/pinctrl/pxa/Makefile
new file mode 100644
index 0000000..f1d56af
--- /dev/null
+++ b/drivers/pinctrl/pxa/Makefile
@@ -0,0 +1,2 @@
+# Marvell PXA pin control drivers
+obj-$(CONFIG_PINCTRL_PXA27X)	+= pinctrl-pxa2xx.o pinctrl-pxa27x.o
diff --git a/drivers/pinctrl/pxa/pinctrl-pxa27x.c b/drivers/pinctrl/pxa/pinctrl-pxa27x.c
new file mode 100644
index 0000000..2e2c370
--- /dev/null
+++ b/drivers/pinctrl/pxa/pinctrl-pxa27x.c
@@ -0,0 +1,566 @@
+/*
+ * Marvell PXA27x family pin control
+ *
+ * Copyright (C) 2015 Robert Jarzmik
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ */
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/pinctrl/pinctrl.h>
+
+#include "pinctrl-pxa2xx.h"
+
+static const struct pxa_desc_pin pxa27x_pins[] = {
+	PXA_GPIO_ONLY_PIN(PXA_PINCTRL_PIN(0)),
+	PXA_GPIO_ONLY_PIN(PXA_PINCTRL_PIN(1)),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(9),
+		     PXA_FUNCTION(0, 3, "FFCTS"),
+		     PXA_FUNCTION(1, 1, "HZ_CLK"),
+		     PXA_FUNCTION(1, 3, "CHOUT<0>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(10),
+		     PXA_FUNCTION(0, 1, "FFDCD"),
+		     PXA_FUNCTION(0, 3, "USB_P3_5"),
+		     PXA_FUNCTION(1, 1, "HZ_CLK"),
+		     PXA_FUNCTION(1, 3, "CHOUT<1>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(11),
+		     PXA_FUNCTION(0, 1, "EXT_SYNC<0>"),
+		     PXA_FUNCTION(0, 2, "SSPRXD2"),
+		     PXA_FUNCTION(0, 3, "USB_P3_1"),
+		     PXA_FUNCTION(1, 1, "CHOUT<0>"),
+		     PXA_FUNCTION(1, 1, "PWM_OUT<2>"),
+		     PXA_FUNCTION(1, 3, "48_MHz")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(12),
+		     PXA_FUNCTION(0, 1, "EXT_SYNC<1>"),
+		     PXA_FUNCTION(0, 2, "CIF_DD<7>"),
+		     PXA_FUNCTION(1, 1, "CHOUT<1>"),
+		     PXA_FUNCTION(1, 1, "PWM_OUT<3>"),
+		     PXA_FUNCTION(1, 3, "48_MHz")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(13),
+		     PXA_FUNCTION(0, 1, "CLK_EXT"),
+		     PXA_FUNCTION(0, 2, "KP_DKIN<7>"),
+		     PXA_FUNCTION(0, 3, "KP_MKIN<7>"),
+		     PXA_FUNCTION(1, 1, "SSPTXD2")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(14),
+		     PXA_FUNCTION(0, 1, "L_VSYNC"),
+		     PXA_FUNCTION(0, 2, "SSPSFRM2"),
+		     PXA_FUNCTION(1, 1, "SSPSFRM2"),
+		     PXA_FUNCTION(1, 3, "UCLK")),
+	PXA_GPIO_ONLY_PIN(PXA_PINCTRL_PIN(15)),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(16),
+		     PXA_FUNCTION(0, 1, "KP_MKIN<5>"),
+		     PXA_FUNCTION(1, 2, "PWM_OUT<0>"),
+		     PXA_FUNCTION(1, 3, "FFTXD")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(17),
+		     PXA_FUNCTION(0, 1, "KP_MKIN<6>"),
+		     PXA_FUNCTION(0, 2, "CIF_DD<6>"),
+		     PXA_FUNCTION(1, 2, "PWM_OUT<1>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(18),
+		     PXA_FUNCTION(0, 1, "RDY")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(19),
+		     PXA_FUNCTION(0, 1, "SSPSCLK2"),
+		     PXA_FUNCTION(0, 3, "FFRXD"),
+		     PXA_FUNCTION(1, 1, "SSPSCLK2"),
+		     PXA_FUNCTION(1, 2, "L_CS"),
+		     PXA_FUNCTION(1, 3, "nURST")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(20),
+		     PXA_FUNCTION(0, 1, "DREQ<0>"),
+		     PXA_FUNCTION(0, 2, "MBREQ"),
+		     PXA_FUNCTION(1, 1, "nSDCS<2>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(21),
+		     PXA_FUNCTION(1, 1, "nSDCS<3>"),
+		     PXA_FUNCTION(1, 2, "DVAL<0>"),
+		     PXA_FUNCTION(1, 3, "MBGNT")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(22),
+		     PXA_FUNCTION(0, 1, "SSPEXTCLK2"),
+		     PXA_FUNCTION(0, 2, "SSPSCLKEN2"),
+		     PXA_FUNCTION(0, 3, "SSPSCLK2"),
+		     PXA_FUNCTION(1, 1, "KP_MKOUT<7>"),
+		     PXA_FUNCTION(1, 2, "SSPSYSCLK2"),
+		     PXA_FUNCTION(1, 3, "SSPSCLK2")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(23),
+		     PXA_FUNCTION(0, 2, "SSPSCLK"),
+		     PXA_FUNCTION(1, 1, "CIF_MCLK"),
+		     PXA_FUNCTION(1, 1, "SSPSCLK")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(24),
+		     PXA_FUNCTION(0, 1, "CIF_FV"),
+		     PXA_FUNCTION(0, 2, "SSPSFRM"),
+		     PXA_FUNCTION(1, 1, "CIF_FV"),
+		     PXA_FUNCTION(1, 2, "SSPSFRM")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(25),
+		     PXA_FUNCTION(0, 1, "CIF_LV"),
+		     PXA_FUNCTION(1, 1, "CIF_LV"),
+		     PXA_FUNCTION(1, 2, "SSPTXD")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(26),
+		     PXA_FUNCTION(0, 1, "SSPRXD"),
+		     PXA_FUNCTION(0, 2, "CIF_PCLK"),
+		     PXA_FUNCTION(0, 3, "FFCTS")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(27),
+		     PXA_FUNCTION(0, 1, "SSPEXTCLK"),
+		     PXA_FUNCTION(0, 2, "SSPSCLKEN"),
+		     PXA_FUNCTION(0, 3, "CIF_DD<0>"),
+		     PXA_FUNCTION(1, 1, "SSPSYSCLK"),
+		     PXA_FUNCTION(1, 3, "FFRTS")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(28),
+		     PXA_FUNCTION(0, 1, "AC97_BITCLK"),
+		     PXA_FUNCTION(0, 2, "I2S_BITCLK"),
+		     PXA_FUNCTION(0, 3, "SSPSFRM"),
+		     PXA_FUNCTION(1, 1, "I2S_BITCLK"),
+		     PXA_FUNCTION(1, 3, "SSPSFRM")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(29),
+		     PXA_FUNCTION(0, 1, "AC97_SDATA_IN_0"),
+		     PXA_FUNCTION(0, 2, "I2S_SDATA_IN"),
+		     PXA_FUNCTION(0, 3, "SSPSCLK"),
+		     PXA_FUNCTION(1, 1, "SSPRXD2"),
+		     PXA_FUNCTION(1, 3, "SSPSCLK")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(30),
+		     PXA_FUNCTION(1, 1, "I2S_SDATA_OUT"),
+		     PXA_FUNCTION(1, 2, "AC97_SDATA_OUT"),
+		     PXA_FUNCTION(1, 3, "USB_P3_2")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(31),
+		     PXA_FUNCTION(1, 1, "I2S_SYNC"),
+		     PXA_FUNCTION(1, 2, "AC97_SYNC"),
+		     PXA_FUNCTION(1, 3, "USB_P3_6")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(32),
+		     PXA_FUNCTION(1, 1, "MSSCLK"),
+		     PXA_FUNCTION(1, 2, "MMCLK")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(33),
+		     PXA_FUNCTION(0, 1, "FFRXD"),
+		     PXA_FUNCTION(0, 2, "FFDSR"),
+		     PXA_FUNCTION(1, 1, "DVAL<1>"),
+		     PXA_FUNCTION(1, 2, "nCS<5>"),
+		     PXA_FUNCTION(1, 3, "MBGNT")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(34),
+		     PXA_FUNCTION(0, 1, "FFRXD"),
+		     PXA_FUNCTION(0, 2, "KP_MKIN<3>"),
+		     PXA_FUNCTION(0, 3, "SSPSCLK3"),
+		     PXA_FUNCTION(1, 1, "USB_P2_2"),
+		     PXA_FUNCTION(1, 3, "SSPSCLK3")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(35),
+		     PXA_FUNCTION(0, 1, "FFCTS"),
+		     PXA_FUNCTION(0, 2, "USB_P2_1"),
+		     PXA_FUNCTION(0, 3, "SSPSFRM3"),
+		     PXA_FUNCTION(1, 2, "KP_MKOUT<6>"),
+		     PXA_FUNCTION(1, 3, "SSPTXD3")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(36),
+		     PXA_FUNCTION(0, 1, "FFDCD"),
+		     PXA_FUNCTION(0, 2, "SSPSCLK2"),
+		     PXA_FUNCTION(0, 3, "KP_MKIN<7>"),
+		     PXA_FUNCTION(1, 1, "USB_P2_4"),
+		     PXA_FUNCTION(1, 2, "SSPSCLK2")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(37),
+		     PXA_FUNCTION(0, 1, "FFDSR"),
+		     PXA_FUNCTION(0, 2, "SSPSFRM2"),
+		     PXA_FUNCTION(0, 3, "KP_MKIN<3>"),
+		     PXA_FUNCTION(1, 1, "USB_P2_8"),
+		     PXA_FUNCTION(1, 2, "SSPSFRM2"),
+		     PXA_FUNCTION(1, 3, "FFTXD")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(38),
+		     PXA_FUNCTION(0, 1, "FFRI"),
+		     PXA_FUNCTION(0, 2, "KP_MKIN<4>"),
+		     PXA_FUNCTION(0, 3, "USB_P2_3"),
+		     PXA_FUNCTION(1, 1, "SSPTXD3"),
+		     PXA_FUNCTION(1, 2, "SSPTXD2"),
+		     PXA_FUNCTION(1, 3, "PWM_OUT<0>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(39),
+		     PXA_FUNCTION(0, 1, "KP_MKIN<4>"),
+		     PXA_FUNCTION(0, 3, "SSPSFRM3"),
+		     PXA_FUNCTION(1, 1, "USB_P2_6"),
+		     PXA_FUNCTION(1, 2, "FFTXD"),
+		     PXA_FUNCTION(1, 3, "SSPSFRM3")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(40),
+		     PXA_FUNCTION(0, 1, "SSPRXD2"),
+		     PXA_FUNCTION(0, 3, "USB_P2_5"),
+		     PXA_FUNCTION(1, 1, "KP_MKOUT<6>"),
+		     PXA_FUNCTION(1, 2, "FFDTR"),
+		     PXA_FUNCTION(1, 3, "SSPSCLK3")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(41),
+		     PXA_FUNCTION(0, 1, "FFRXD"),
+		     PXA_FUNCTION(0, 2, "USB_P2_7"),
+		     PXA_FUNCTION(0, 3, "SSPRXD3"),
+		     PXA_FUNCTION(1, 1, "KP_MKOUT<7>"),
+		     PXA_FUNCTION(1, 2, "FFRTS")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(42),
+		     PXA_FUNCTION(0, 1, "BTRXD"),
+		     PXA_FUNCTION(0, 2, "ICP_RXD"),
+		     PXA_FUNCTION(1, 3, "CIF_MCLK")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(43),
+		     PXA_FUNCTION(0, 3, "CIF_FV"),
+		     PXA_FUNCTION(1, 1, "ICP_TXD"),
+		     PXA_FUNCTION(1, 2, "BTTXD"),
+		     PXA_FUNCTION(1, 3, "CIF_FV")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(44),
+		     PXA_FUNCTION(0, 1, "BTCTS"),
+		     PXA_FUNCTION(0, 3, "CIF_LV"),
+		     PXA_FUNCTION(1, 3, "CIF_LV")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(45),
+		     PXA_FUNCTION(0, 3, "CIF_PCLK"),
+		     PXA_FUNCTION(1, 1, "AC97_SYSCLK"),
+		     PXA_FUNCTION(1, 2, "BTRTS"),
+		     PXA_FUNCTION(1, 3, "SSPSYSCLK3")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(46),
+		     PXA_FUNCTION(0, 1, "ICP_RXD"),
+		     PXA_FUNCTION(0, 2, "STD_RXD"),
+		     PXA_FUNCTION(1, 2, "PWM_OUT<2>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(47),
+		     PXA_FUNCTION(0, 1, "CIF_DD<0>"),
+		     PXA_FUNCTION(1, 1, "STD_TXD"),
+		     PXA_FUNCTION(1, 2, "ICP_TXD"),
+		     PXA_FUNCTION(1, 3, "PWM_OUT<3>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(48),
+		     PXA_FUNCTION(0, 1, "CIF_DD<5>"),
+		     PXA_FUNCTION(1, 1, "BB_OB_DAT<1>"),
+		     PXA_FUNCTION(1, 2, "nPOE")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(49),
+		     PXA_FUNCTION(1, 2, "nPWE")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(50),
+		     PXA_FUNCTION(0, 1, "CIF_DD<3>"),
+		     PXA_FUNCTION(0, 3, "SSPSCLK2"),
+		     PXA_FUNCTION(1, 1, "BB_OB_DAT<2>"),
+		     PXA_FUNCTION(1, 2, "nPIOR"),
+		     PXA_FUNCTION(1, 3, "SSPSCLK2")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(51),
+		     PXA_FUNCTION(0, 1, "CIF_DD<2>"),
+		     PXA_FUNCTION(1, 1, "BB_OB_DAT<3>"),
+		     PXA_FUNCTION(1, 2, "nPIOW")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(52),
+		     PXA_FUNCTION(0, 1, "CIF_DD<4>"),
+		     PXA_FUNCTION(0, 2, "SSPSCLK3"),
+		     PXA_FUNCTION(1, 1, "BB_OB_CLK"),
+		     PXA_FUNCTION(1, 2, "SSPSCLK3")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(53),
+		     PXA_FUNCTION(0, 1, "FFRXD"),
+		     PXA_FUNCTION(0, 2, "USB_P2_3"),
+		     PXA_FUNCTION(1, 1, "BB_OB_STB"),
+		     PXA_FUNCTION(1, 2, "CIF_MCLK"),
+		     PXA_FUNCTION(1, 3, "SSPSYSCLK")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(54),
+		     PXA_FUNCTION(0, 2, "BB_OB_WAIT"),
+		     PXA_FUNCTION(0, 3, "CIF_PCLK"),
+		     PXA_FUNCTION(1, 2, "nPCE<2>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(55),
+		     PXA_FUNCTION(0, 1, "CIF_DD<1>"),
+		     PXA_FUNCTION(0, 2, "BB_IB_DAT<1>"),
+		     PXA_FUNCTION(1, 2, "nPREG")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(56),
+		     PXA_FUNCTION(0, 1, "nPWAIT"),
+		     PXA_FUNCTION(0, 2, "BB_IB_DAT<2>"),
+		     PXA_FUNCTION(1, 1, "USB_P3_4")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(57),
+		     PXA_FUNCTION(0, 1, "nIOS16"),
+		     PXA_FUNCTION(0, 2, "BB_IB_DAT<3>"),
+		     PXA_FUNCTION(1, 3, "SSPTXD")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(58),
+		     PXA_FUNCTION(0, 2, "LDD<0>"),
+		     PXA_FUNCTION(1, 2, "LDD<0>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(59),
+		     PXA_FUNCTION(0, 2, "LDD<1>"),
+		     PXA_FUNCTION(1, 2, "LDD<1>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(60),
+		     PXA_FUNCTION(0, 2, "LDD<2>"),
+		     PXA_FUNCTION(1, 2, "LDD<2>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(61),
+		     PXA_FUNCTION(0, 2, "LDD<3>"),
+		     PXA_FUNCTION(1, 2, "LDD<3>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(62),
+		     PXA_FUNCTION(0, 2, "LDD<4>"),
+		     PXA_FUNCTION(1, 2, "LDD<4>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(63),
+		     PXA_FUNCTION(0, 2, "LDD<5>"),
+		     PXA_FUNCTION(1, 2, "LDD<5>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(64),
+		     PXA_FUNCTION(0, 2, "LDD<6>"),
+		     PXA_FUNCTION(1, 2, "LDD<6>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(65),
+		     PXA_FUNCTION(0, 2, "LDD<7>"),
+		     PXA_FUNCTION(1, 2, "LDD<7>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(66),
+		     PXA_FUNCTION(0, 2, "LDD<8>"),
+		     PXA_FUNCTION(1, 2, "LDD<8>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(67),
+		     PXA_FUNCTION(0, 2, "LDD<9>"),
+		     PXA_FUNCTION(1, 2, "LDD<9>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(68),
+		     PXA_FUNCTION(0, 2, "LDD<10>"),
+		     PXA_FUNCTION(1, 2, "LDD<10>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(69),
+		     PXA_FUNCTION(0, 2, "LDD<11>"),
+		     PXA_FUNCTION(1, 2, "LDD<11>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(70),
+		     PXA_FUNCTION(0, 2, "LDD<12>"),
+		     PXA_FUNCTION(1, 2, "LDD<12>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(71),
+		     PXA_FUNCTION(0, 2, "LDD<13>"),
+		     PXA_FUNCTION(1, 2, "LDD<13>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(72),
+		     PXA_FUNCTION(0, 2, "LDD<14>"),
+		     PXA_FUNCTION(1, 2, "LDD<14>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(73),
+		     PXA_FUNCTION(0, 2, "LDD<15>"),
+		     PXA_FUNCTION(1, 2, "LDD<15>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(74),
+		     PXA_FUNCTION(1, 2, "L_FCLK_RD")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(75),
+		     PXA_FUNCTION(1, 2, "L_LCLK_A0")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(76),
+		     PXA_FUNCTION(1, 2, "L_PCLK_WR")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(77),
+		     PXA_FUNCTION(1, 2, "L_BIAS")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(78),
+		     PXA_FUNCTION(1, 1, "nPCE<2>"),
+		     PXA_FUNCTION(1, 2, "nCS<2>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(79),
+		     PXA_FUNCTION(1, 1, "PSKTSEL"),
+		     PXA_FUNCTION(1, 2, "nCS<3>"),
+		     PXA_FUNCTION(1, 3, "PWM_OUT<2>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(80),
+		     PXA_FUNCTION(0, 1, "DREQ<1>"),
+		     PXA_FUNCTION(0, 2, "MBREQ"),
+		     PXA_FUNCTION(1, 2, "nCS<4>"),
+		     PXA_FUNCTION(1, 3, "PWM_OUT<3>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(81),
+		     PXA_FUNCTION(0, 2, "CIF_DD<0>"),
+		     PXA_FUNCTION(1, 1, "SSPTXD3"),
+		     PXA_FUNCTION(1, 2, "BB_OB_DAT<0>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(82),
+		     PXA_FUNCTION(0, 1, "SSPRXD3"),
+		     PXA_FUNCTION(0, 2, "BB_IB_DAT<0>"),
+		     PXA_FUNCTION(0, 3, "CIF_DD<5>"),
+		     PXA_FUNCTION(1, 3, "FFDTR")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(83),
+		     PXA_FUNCTION(0, 1, "SSPSFRM3"),
+		     PXA_FUNCTION(0, 2, "BB_IB_CLK"),
+		     PXA_FUNCTION(0, 3, "CIF_DD<5>"),
+		     PXA_FUNCTION(1, 1, "SSPSFRM3"),
+		     PXA_FUNCTION(1, 2, "FFTXD"),
+		     PXA_FUNCTION(1, 3, "FFRTS")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(84),
+		     PXA_FUNCTION(0, 1, "SSPCLK3"),
+		     PXA_FUNCTION(0, 2, "BB_IB_STB"),
+		     PXA_FUNCTION(0, 3, "CIF_FV"),
+		     PXA_FUNCTION(1, 1, "SSPCLK3"),
+		     PXA_FUNCTION(1, 3, "CIF_FV")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(85),
+		     PXA_FUNCTION(0, 1, "FFRXD"),
+		     PXA_FUNCTION(0, 2, "DREQ<2>"),
+		     PXA_FUNCTION(0, 3, "CIF_LV"),
+		     PXA_FUNCTION(1, 1, "nPCE<1>"),
+		     PXA_FUNCTION(1, 2, "BB_IB_WAIT"),
+		     PXA_FUNCTION(1, 3, "CIF_LV")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(86),
+		     PXA_FUNCTION(0, 1, "SSPRXD2"),
+		     PXA_FUNCTION(0, 2, "LDD<16>"),
+		     PXA_FUNCTION(0, 3, "USB_P3_5"),
+		     PXA_FUNCTION(1, 1, "nPCE<1>"),
+		     PXA_FUNCTION(1, 2, "LDD<16>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(87),
+		     PXA_FUNCTION(0, 1, "nPCE<2>"),
+		     PXA_FUNCTION(0, 2, "LDD<17>"),
+		     PXA_FUNCTION(0, 3, "USB_P3_1"),
+		     PXA_FUNCTION(1, 1, "SSPTXD2"),
+		     PXA_FUNCTION(1, 2, "LDD<17>"),
+		     PXA_FUNCTION(1, 3, "SSPSFRM2")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(88),
+		     PXA_FUNCTION(0, 1, "USBHPWR<1>"),
+		     PXA_FUNCTION(0, 2, "SSPRXD2"),
+		     PXA_FUNCTION(0, 3, "SSPSFRM2"),
+		     PXA_FUNCTION(1, 2, "SSPTXD2"),
+		     PXA_FUNCTION(1, 3, "SSPSFRM2")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(89),
+		     PXA_FUNCTION(0, 1, "SSPRXD3"),
+		     PXA_FUNCTION(0, 3, "FFRI"),
+		     PXA_FUNCTION(1, 1, "AC97_SYSCLK"),
+		     PXA_FUNCTION(1, 2, "USBHPEN<1>"),
+		     PXA_FUNCTION(1, 3, "SSPTXD2")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(90),
+		     PXA_FUNCTION(0, 1, "KP_MKIN<5>"),
+		     PXA_FUNCTION(0, 3, "USB_P3_5"),
+		     PXA_FUNCTION(1, 1, "CIF_DD<4>"),
+		     PXA_FUNCTION(1, 2, "nURST")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(91),
+		     PXA_FUNCTION(0, 1, "KP_MKIN<6>"),
+		     PXA_FUNCTION(0, 3, "USB_P3_1"),
+		     PXA_FUNCTION(1, 1, "CIF_DD<5>"),
+		     PXA_FUNCTION(1, 2, "UCLK")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(92),
+		     PXA_FUNCTION(0, 1, "MMDAT<0>"),
+		     PXA_FUNCTION(1, 1, "MMDAT<0>"),
+		     PXA_FUNCTION(1, 2, "MSBS")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(93),
+		     PXA_FUNCTION(0, 1, "KP_DKIN<0>"),
+		     PXA_FUNCTION(0, 2, "CIF_DD<6>"),
+		     PXA_FUNCTION(1, 1, "AC97_SDATA_OUT")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(94),
+		     PXA_FUNCTION(0, 1, "KP_DKIN<1>"),
+		     PXA_FUNCTION(0, 2, "CIF_DD<5>"),
+		     PXA_FUNCTION(1, 1, "AC97_SYNC")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(95),
+		     PXA_FUNCTION(0, 1, "KP_DKIN<2>"),
+		     PXA_FUNCTION(0, 2, "CIF_DD<4>"),
+		     PXA_FUNCTION(0, 3, "KP_MKIN<6>"),
+		     PXA_FUNCTION(1, 1, "AC97_RESET_n")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(96),
+		     PXA_FUNCTION(0, 1, "KP_DKIN<3>"),
+		     PXA_FUNCTION(0, 2, "MBREQ"),
+		     PXA_FUNCTION(0, 3, "FFRXD"),
+		     PXA_FUNCTION(1, 2, "DVAL<1>"),
+		     PXA_FUNCTION(1, 3, "KP_MKOUT<6>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(97),
+		     PXA_FUNCTION(0, 1, "KP_DKIN<4>"),
+		     PXA_FUNCTION(0, 2, "DREQ<1>"),
+		     PXA_FUNCTION(0, 3, "KP_MKIN<3>"),
+		     PXA_FUNCTION(1, 2, "MBGNT")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(98),
+		     PXA_FUNCTION(0, 1, "KP_DKIN<5>"),
+		     PXA_FUNCTION(0, 2, "CIF_DD<0>"),
+		     PXA_FUNCTION(0, 3, "KP_MKIN<4>"),
+		     PXA_FUNCTION(1, 1, "AC97_SYSCLK"),
+		     PXA_FUNCTION(1, 3, "FFRTS")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(99),
+		     PXA_FUNCTION(0, 1, "KP_DKIN<6>"),
+		     PXA_FUNCTION(0, 2, "AC97_SDATA_IN_1"),
+		     PXA_FUNCTION(0, 3, "KP_MKIN<5>"),
+		     PXA_FUNCTION(1, 3, "FFTXD")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(100),
+		     PXA_FUNCTION(0, 1, "KP_MKIN<0>"),
+		     PXA_FUNCTION(0, 2, "DREQ<2>"),
+		     PXA_FUNCTION(0, 3, "FFCTS")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(101),
+		     PXA_FUNCTION(0, 1, "KP_MKIN<1>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(102),
+		     PXA_FUNCTION(0, 1, "KP_MKIN<2>"),
+		     PXA_FUNCTION(0, 3, "FFRXD"),
+		     PXA_FUNCTION(1, 1, "nPCE<1>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(103),
+		     PXA_FUNCTION(0, 1, "CIF_DD<3>"),
+		     PXA_FUNCTION(1, 2, "KP_MKOUT<0>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(104),
+		     PXA_FUNCTION(0, 1, "CIF_DD<2>"),
+		     PXA_FUNCTION(1, 1, "PSKTSEL"),
+		     PXA_FUNCTION(1, 2, "KP_MKOUT<1>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(105),
+		     PXA_FUNCTION(0, 1, "CIF_DD<1>"),
+		     PXA_FUNCTION(1, 1, "nPCE<2>"),
+		     PXA_FUNCTION(1, 2, "KP_MKOUT<2>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(106),
+		     PXA_FUNCTION(0, 1, "CIF_DD<9>"),
+		     PXA_FUNCTION(1, 2, "KP_MKOUT<3>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(107),
+		     PXA_FUNCTION(0, 1, "CIF_DD<8>"),
+		     PXA_FUNCTION(1, 2, "KP_MKOUT<4>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(108),
+		     PXA_FUNCTION(0, 1, "CIF_DD<7>"),
+		     PXA_FUNCTION(1, 1, "CHOUT<0>"),
+		     PXA_FUNCTION(1, 2, "KP_MKOUT<5>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(109),
+		     PXA_FUNCTION(0, 1, "MMDAT<1>"),
+		     PXA_FUNCTION(0, 2, "MSSDIO"),
+		     PXA_FUNCTION(1, 1, "MMDAT<1>"),
+		     PXA_FUNCTION(1, 2, "MSSDIO")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(110),
+		     PXA_FUNCTION(0, 1, "MMDAT<2>"),
+		     PXA_FUNCTION(1, 1, "MMDAT<2>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(111),
+		     PXA_FUNCTION(0, 1, "MMDAT<3>"),
+		     PXA_FUNCTION(1, 1, "MMDAT<3>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(112),
+		     PXA_FUNCTION(0, 1, "MMCMD"),
+		     PXA_FUNCTION(0, 2, "nMSINS"),
+		     PXA_FUNCTION(1, 1, "MMCMD")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(113),
+		     PXA_FUNCTION(0, 3, "USB_P3_3"),
+		     PXA_FUNCTION(1, 1, "I2S_SYSCLK"),
+		     PXA_FUNCTION(1, 2, "AC97_RESET_n")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(114),
+		     PXA_FUNCTION(0, 1, "CIF_DD<1>"),
+		     PXA_FUNCTION(1, 1, "UEN"),
+		     PXA_FUNCTION(1, 2, "UVS0")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(115),
+		     PXA_FUNCTION(0, 1, "DREQ<0>"),
+		     PXA_FUNCTION(0, 2, "CIF_DD<3>"),
+		     PXA_FUNCTION(0, 3, "MBREQ"),
+		     PXA_FUNCTION(1, 1, "UEN"),
+		     PXA_FUNCTION(1, 2, "nUVS1"),
+		     PXA_FUNCTION(1, 3, "PWM_OUT<1>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(116),
+		     PXA_FUNCTION(0, 1, "CIF_DD<2>"),
+		     PXA_FUNCTION(0, 2, "AC97_SDATA_IN_0"),
+		     PXA_FUNCTION(0, 3, "UDET"),
+		     PXA_FUNCTION(1, 1, "DVAL<0>"),
+		     PXA_FUNCTION(1, 2, "nUVS2"),
+		     PXA_FUNCTION(1, 3, "MBGNT")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(117),
+		     PXA_FUNCTION(0, 1, "SCL"),
+		     PXA_FUNCTION(1, 1, "SCL")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(118),
+		     PXA_FUNCTION(0, 1, "SDA"),
+		     PXA_FUNCTION(1, 1, "SDA")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(119),
+		     PXA_FUNCTION(0, 1, "USBHPWR<2>")),
+	PXA_GPIO_PIN(PXA_PINCTRL_PIN(120),
+		     PXA_FUNCTION(1, 2, "USBHPEN<2>")),
+};
+
+static int pxa27x_pinctrl_probe(struct platform_device *pdev)
+{
+	int ret, i;
+	void __iomem *base_af[8];
+	void __iomem *base_dir[4];
+	void __iomem *base_sleep[4];
+	struct resource *res;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	base_af[0] = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(base_af[0]))
+		return PTR_ERR(base_af[0]);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	base_dir[0] = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(base_dir[0]))
+		return PTR_ERR(base_dir[0]);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 2);
+	base_dir[3] = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(base_dir[3]))
+		return PTR_ERR(base_dir[3]);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 3);
+	base_sleep[0] = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(base_sleep[0]))
+		return PTR_ERR(base_sleep[0]);
+
+	for (i = 0; i < ARRAY_SIZE(base_af); i++)
+		base_af[i] = base_af[0] + sizeof(base_af[0]) * i;
+	for (i = 0; i < 3; i++)
+		base_dir[i] = base_dir[0] + sizeof(base_dir[0]) * i;
+	for (i = 0; i < ARRAY_SIZE(base_sleep); i++)
+		base_sleep[i] = base_sleep[0] + sizeof(base_af[0]) * i;
+
+	ret = pxa2xx_pinctrl_init(pdev, pxa27x_pins, ARRAY_SIZE(pxa27x_pins),
+				  base_af, base_dir, base_sleep);
+	return ret;
+}
+
+static const struct of_device_id pxa27x_pinctrl_match[] = {
+	{ .compatible = "marvell,pxa27x-pinctrl", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, pxa27x_pinctrl_match);
+
+static struct platform_driver pxa27x_pinctrl_driver = {
+	.probe	= pxa27x_pinctrl_probe,
+	.driver	= {
+		.name		= "pxa27x-pinctrl",
+		.of_match_table	= pxa27x_pinctrl_match,
+	},
+};
+module_platform_driver(pxa27x_pinctrl_driver);
+
+MODULE_AUTHOR("Robert Jarzmik <robert.jarzmik@free.fr>");
+MODULE_DESCRIPTION("Marvell PXA27x pinctrl driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/pinctrl/pxa/pinctrl-pxa2xx.c b/drivers/pinctrl/pxa/pinctrl-pxa2xx.c
new file mode 100644
index 0000000..d90e205
--- /dev/null
+++ b/drivers/pinctrl/pxa/pinctrl-pxa2xx.c
@@ -0,0 +1,436 @@
+/*
+ * Marvell PXA2xx family pin control
+ *
+ * Copyright (C) 2015 Robert Jarzmik
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ */
+
+#include <linux/bitops.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/module.h>
+#include <linux/pinctrl/pinconf.h>
+#include <linux/pinctrl/pinconf-generic.h>
+#include <linux/pinctrl/pinmux.h>
+#include <linux/pinctrl/pinctrl.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#include "../pinctrl-utils.h"
+#include "pinctrl-pxa2xx.h"
+
+static int pxa2xx_pctrl_get_groups_count(struct pinctrl_dev *pctldev)
+{
+	struct pxa_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev);
+
+	return pctl->ngroups;
+}
+
+static const char *pxa2xx_pctrl_get_group_name(struct pinctrl_dev *pctldev,
+					       unsigned tgroup)
+{
+	struct pxa_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev);
+	struct pxa_pinctrl_group *group = pctl->groups + tgroup;
+
+	return group->name;
+}
+
+static int pxa2xx_pctrl_get_group_pins(struct pinctrl_dev *pctldev,
+				       unsigned tgroup,
+				       const unsigned **pins,
+				       unsigned *num_pins)
+{
+	struct pxa_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev);
+	struct pxa_pinctrl_group *group = pctl->groups + tgroup;
+
+	*pins = (unsigned *)&group->pin;
+	*num_pins = 1;
+
+	return 0;
+}
+
+static const struct pinctrl_ops pxa2xx_pctl_ops = {
+#ifdef CONFIG_OF
+	.dt_node_to_map		= pinconf_generic_dt_node_to_map_all,
+	.dt_free_map		= pinctrl_utils_dt_free_map,
+#endif
+	.get_groups_count	= pxa2xx_pctrl_get_groups_count,
+	.get_group_name		= pxa2xx_pctrl_get_group_name,
+	.get_group_pins		= pxa2xx_pctrl_get_group_pins,
+};
+
+static struct pxa_desc_function *
+pxa_desc_by_func_group(struct pxa_pinctrl *pctl, const char *pin_name,
+		       const char *func_name)
+{
+	int i;
+	struct pxa_desc_function *df;
+
+	for (i = 0; i < pctl->npins; i++) {
+		const struct pxa_desc_pin *pin = pctl->ppins + i;
+
+		if (!strcmp(pin->pin.name, pin_name))
+			for (df = pin->functions; df->name; df++)
+				if (!strcmp(df->name, func_name))
+					return df;
+	}
+
+	return NULL;
+}
+
+static int pxa2xx_pmx_gpio_set_direction(struct pinctrl_dev *pctldev,
+					 struct pinctrl_gpio_range *range,
+					 unsigned pin,
+					 bool input)
+{
+	struct pxa_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev);
+	unsigned long flags;
+	uint32_t val;
+	void __iomem *gpdr;
+
+	gpdr = pctl->base_gpdr[pin / 32];
+	dev_dbg(pctl->dev, "set_direction(pin=%d): dir=%d\n",
+		pin, !input);
+
+	spin_lock_irqsave(&pctl->lock, flags);
+
+	val = readl_relaxed(gpdr);
+	val = (val & ~BIT(pin % 32)) | (input ? 0 : BIT(pin % 32));
+	writel_relaxed(val, gpdr);
+
+	spin_unlock_irqrestore(&pctl->lock, flags);
+
+	return 0;
+}
+
+static const char *pxa2xx_pmx_get_func_name(struct pinctrl_dev *pctldev,
+					    unsigned function)
+{
+	struct pxa_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev);
+	struct pxa_pinctrl_function *pf = pctl->functions + function;
+
+	return pf->name;
+}
+
+static int pxa2xx_get_functions_count(struct pinctrl_dev *pctldev)
+{
+	struct pxa_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev);
+
+	return pctl->nfuncs;
+}
+
+static int pxa2xx_pmx_get_func_groups(struct pinctrl_dev *pctldev,
+				      unsigned function,
+				      const char * const **groups,
+				      unsigned * const num_groups)
+{
+	struct pxa_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev);
+	struct pxa_pinctrl_function *pf = pctl->functions + function;
+
+	*groups = pf->groups;
+	*num_groups = pf->ngroups;
+
+	return 0;
+}
+
+static int pxa2xx_pmx_set_mux(struct pinctrl_dev *pctldev, unsigned function,
+			      unsigned tgroup)
+{
+	struct pxa_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev);
+	struct pxa_pinctrl_group *group = pctl->groups + tgroup;
+	struct pxa_desc_function *df;
+	int pin, shift;
+	unsigned long flags;
+	void __iomem *gafr, *gpdr;
+	u32 val;
+
+
+	df = pxa_desc_by_func_group(pctl, group->name,
+				    (pctl->functions + function)->name);
+	if (!df)
+		return -EINVAL;
+
+	pin = group->pin;
+	gafr = pctl->base_gafr[pin / 16];
+	gpdr = pctl->base_gpdr[pin / 32];
+	shift = (pin % 16) << 1;
+	dev_dbg(pctl->dev, "set_mux(pin=%d): af=%d dir=%d\n",
+		pin, df->muxval >> 1, df->muxval & 0x1);
+
+	spin_lock_irqsave(&pctl->lock, flags);
+
+	val = readl_relaxed(gafr);
+	val = (val & ~(0x3 << shift)) | ((df->muxval >> 1) << shift);
+	writel_relaxed(val, gafr);
+
+	val = readl_relaxed(gpdr);
+	val = (val & ~BIT(pin % 32)) | ((df->muxval & 1) ? BIT(pin % 32) : 0);
+	writel_relaxed(val, gpdr);
+
+	spin_unlock_irqrestore(&pctl->lock, flags);
+
+	return 0;
+}
+static const struct pinmux_ops pxa2xx_pinmux_ops = {
+	.get_functions_count = pxa2xx_get_functions_count,
+	.get_function_name = pxa2xx_pmx_get_func_name,
+	.get_function_groups = pxa2xx_pmx_get_func_groups,
+	.set_mux = pxa2xx_pmx_set_mux,
+	.gpio_set_direction = pxa2xx_pmx_gpio_set_direction,
+};
+
+static int pxa2xx_pconf_group_get(struct pinctrl_dev *pctldev,
+				  unsigned group,
+				  unsigned long *config)
+{
+	struct pxa_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev);
+	struct pxa_pinctrl_group *g = pctl->groups + group;
+	unsigned long flags;
+	unsigned pin = g->pin;
+	void __iomem *pgsr = pctl->base_pgsr[pin / 32];
+	u32 val;
+
+	spin_lock_irqsave(&pctl->lock, flags);
+	val = readl_relaxed(pgsr) & BIT(pin % 32);
+	*config = val ? PIN_CONFIG_LOW_POWER_MODE : 0;
+	spin_unlock_irqrestore(&pctl->lock, flags);
+
+	dev_dbg(pctl->dev, "get sleep gpio state(pin=%d) %d\n",
+		pin, !!val);
+	return 0;
+}
+
+static int pxa2xx_pconf_group_set(struct pinctrl_dev *pctldev,
+				  unsigned group,
+				  unsigned long *configs,
+				  unsigned num_configs)
+{
+	struct pxa_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev);
+	struct pxa_pinctrl_group *g = pctl->groups + group;
+	unsigned long flags;
+	unsigned pin = g->pin;
+	void __iomem *pgsr = pctl->base_pgsr[pin / 32];
+	int i, is_set = 0;
+	u32 val;
+
+	for (i = 0; i < num_configs; i++) {
+		switch (pinconf_to_config_param(configs[i])) {
+		case PIN_CONFIG_LOW_POWER_MODE:
+			is_set = pinconf_to_config_argument(configs[i]);
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	dev_dbg(pctl->dev, "set sleep gpio state(pin=%d) %d\n",
+		pin, is_set);
+
+	spin_lock_irqsave(&pctl->lock, flags);
+	val = readl_relaxed(pgsr);
+	val = (val & ~BIT(pin % 32)) | (is_set ? BIT(pin % 32) : 0);
+	writel_relaxed(val, pgsr);
+	spin_unlock_irqrestore(&pctl->lock, flags);
+
+	return 0;
+}
+
+static const struct pinconf_ops pxa2xx_pconf_ops = {
+	.pin_config_group_get	= pxa2xx_pconf_group_get,
+	.pin_config_group_set	= pxa2xx_pconf_group_set,
+	.is_generic		= true,
+};
+
+static struct pinctrl_desc pxa2xx_pinctrl_desc = {
+	.confops	= &pxa2xx_pconf_ops,
+	.pctlops	= &pxa2xx_pctl_ops,
+	.pmxops		= &pxa2xx_pinmux_ops,
+};
+
+static const struct pxa_pinctrl_function *
+pxa2xx_find_function(struct pxa_pinctrl *pctl, const char *fname,
+		     const struct pxa_pinctrl_function *functions)
+{
+	const struct pxa_pinctrl_function *func;
+
+	for (func = functions; func->name; func++)
+		if (!strcmp(fname, func->name))
+			return func;
+
+	return NULL;
+}
+
+static int pxa2xx_build_functions(struct pxa_pinctrl *pctl)
+{
+	int i;
+	struct pxa_pinctrl_function *functions;
+	struct pxa_desc_function *df;
+
+	/*
+	 * Each pin can have at most 6 alternate functions, and 2 gpio functions
+	 * which are common to each pin. As there are more than 2 pins without
+	 * alternate function, 6 * npins is an absolute high limit of the number
+	 * of functions.
+	 */
+	functions = devm_kcalloc(pctl->dev, pctl->npins * 6,
+				 sizeof(*functions), GFP_KERNEL);
+	if (!functions)
+		return -ENOMEM;
+
+	for (i = 0; i < pctl->npins; i++)
+		for (df = pctl->ppins[i].functions; df->name; df++)
+			if (!pxa2xx_find_function(pctl, df->name, functions))
+				(functions + pctl->nfuncs++)->name = df->name;
+	pctl->functions = devm_kmemdup(pctl->dev, functions,
+				       pctl->nfuncs * sizeof(*functions),
+				       GFP_KERNEL);
+	if (!pctl->functions)
+		return -ENOMEM;
+
+	devm_kfree(pctl->dev, functions);
+	return 0;
+}
+
+static int pxa2xx_build_groups(struct pxa_pinctrl *pctl)
+{
+	int i, j, ngroups;
+	struct pxa_pinctrl_function *func;
+	struct pxa_desc_function *df;
+	char **gtmp;
+
+	gtmp = devm_kmalloc_array(pctl->dev, pctl->npins, sizeof(*gtmp),
+				  GFP_KERNEL);
+	if (!gtmp)
+		return -ENOMEM;
+
+	for (i = 0; i < pctl->nfuncs; i++) {
+		ngroups = 0;
+		for (j = 0; j < pctl->npins; j++)
+			for (df = pctl->ppins[j].functions; df->name;
+			     df++)
+				if (!strcmp(pctl->functions[i].name,
+					    df->name))
+					gtmp[ngroups++] = (char *)
+						pctl->ppins[j].pin.name;
+		func = pctl->functions + i;
+		func->ngroups = ngroups;
+		func->groups =
+			devm_kmalloc_array(pctl->dev, ngroups,
+					   sizeof(char *), GFP_KERNEL);
+		if (!func->groups)
+			return -ENOMEM;
+
+		memcpy(func->groups, gtmp, ngroups * sizeof(*gtmp));
+	}
+
+	devm_kfree(pctl->dev, gtmp);
+	return 0;
+}
+
+static int pxa2xx_build_state(struct pxa_pinctrl *pctl,
+			      const struct pxa_desc_pin *ppins, int npins)
+{
+	struct pxa_pinctrl_group *group;
+	struct pinctrl_pin_desc *pins;
+	int ret, i;
+
+	pctl->npins = npins;
+	pctl->ppins = ppins;
+	pctl->ngroups = npins;
+
+	pctl->desc.npins = npins;
+	pins = devm_kcalloc(pctl->dev, npins, sizeof(*pins), GFP_KERNEL);
+	if (!pins)
+		return -ENOMEM;
+
+	pctl->desc.pins = pins;
+	for (i = 0; i < npins; i++)
+		pins[i] = ppins[i].pin;
+
+	pctl->groups = devm_kmalloc_array(pctl->dev, pctl->ngroups,
+					  sizeof(*pctl->groups), GFP_KERNEL);
+	if (!pctl->groups)
+		return -ENOMEM;
+
+	for (i = 0; i < npins; i++) {
+		group = pctl->groups + i;
+		group->name = ppins[i].pin.name;
+		group->pin = ppins[i].pin.number;
+	}
+
+	ret = pxa2xx_build_functions(pctl);
+	if (ret)
+		return ret;
+
+	ret = pxa2xx_build_groups(pctl);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+int pxa2xx_pinctrl_init(struct platform_device *pdev,
+			const struct pxa_desc_pin *ppins, int npins,
+			void __iomem *base_gafr[], void __iomem *base_gpdr[],
+			void __iomem *base_pgsr[])
+{
+	struct pxa_pinctrl *pctl;
+	int ret, i, maxpin = 0;
+
+	for (i = 0; i < npins; i++)
+		maxpin = max_t(int, ppins[i].pin.number, maxpin);
+
+	pctl = devm_kzalloc(&pdev->dev, sizeof(*pctl), GFP_KERNEL);
+	if (!pctl)
+		return -ENOMEM;
+	pctl->base_gafr = devm_kcalloc(&pdev->dev, roundup(maxpin, 16),
+				       sizeof(*pctl->base_gafr), GFP_KERNEL);
+	pctl->base_gpdr = devm_kcalloc(&pdev->dev, roundup(maxpin, 32),
+				       sizeof(*pctl->base_gpdr), GFP_KERNEL);
+	pctl->base_pgsr = devm_kcalloc(&pdev->dev, roundup(maxpin, 32),
+				       sizeof(*pctl->base_pgsr), GFP_KERNEL);
+	if (!pctl->base_gafr || !pctl->base_gpdr || !pctl->base_pgsr)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, pctl);
+	spin_lock_init(&pctl->lock);
+
+	pctl->dev = &pdev->dev;
+	pctl->desc = pxa2xx_pinctrl_desc;
+	pctl->desc.name = dev_name(&pdev->dev);
+	pctl->desc.owner = THIS_MODULE;
+
+	for (i = 0; i < roundup(maxpin, 16); i += 16)
+		pctl->base_gafr[i / 16] = base_gafr[i / 16];
+	for (i = 0; i < roundup(maxpin, 32); i += 32) {
+		pctl->base_gpdr[i / 32] = base_gpdr[i / 32];
+		pctl->base_pgsr[i / 32] = base_pgsr[i / 32];
+	}
+
+	ret = pxa2xx_build_state(pctl, ppins, npins);
+	if (ret)
+		return ret;
+
+	pctl->pctl_dev = pinctrl_register(&pctl->desc, &pdev->dev, pctl);
+	if (IS_ERR(pctl->pctl_dev)) {
+		dev_err(&pdev->dev, "couldn't register pinctrl driver\n");
+		return PTR_ERR(pctl->pctl_dev);
+	}
+
+	dev_info(&pdev->dev, "initialized pxa2xx pinctrl driver\n");
+
+	return 0;
+}
+
+int pxa2xx_pinctrl_exit(struct platform_device *pdev)
+{
+	struct pxa_pinctrl *pctl = platform_get_drvdata(pdev);
+
+	pinctrl_unregister(pctl->pctl_dev);
+	return 0;
+}
diff --git a/drivers/pinctrl/pxa/pinctrl-pxa2xx.h b/drivers/pinctrl/pxa/pinctrl-pxa2xx.h
new file mode 100644
index 0000000..8be1e0b
--- /dev/null
+++ b/drivers/pinctrl/pxa/pinctrl-pxa2xx.h
@@ -0,0 +1,92 @@
+/*
+ * Marvell PXA2xx family pin control
+ *
+ * Copyright (C) 2015 Robert Jarzmik
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ */
+
+#ifndef __PINCTRL_PXA_H
+#define __PINCTRL_PXA_H
+
+#define PXA_FUNCTION(_dir, _af, _name)				\
+	{							\
+		.name = _name,					\
+		.muxval = (_dir | (_af << 1)),			\
+	}
+
+#define PXA_PIN(_pin, funcs...)					\
+	{							\
+		.pin = _pin,					\
+		.functions = (struct pxa_desc_function[]){	\
+			funcs, { } },				\
+	}
+
+#define PXA_GPIO_PIN(_pin, funcs...)				\
+	{							\
+		.pin = _pin,					\
+		.functions = (struct pxa_desc_function[]){	\
+			PXA_FUNCTION(0, 0, "gpio_in"),		\
+			PXA_FUNCTION(1, 0, "gpio_out"),		\
+			funcs, { } },				\
+	}
+
+#define PXA_GPIO_ONLY_PIN(_pin)					\
+	{							\
+		.pin = _pin,					\
+		.functions = (struct pxa_desc_function[]){	\
+			PXA_FUNCTION(0, 0, "gpio_in"),		\
+			PXA_FUNCTION(1, 0, "gpio_out"),		\
+			{ } },					\
+	}
+
+#define PXA_PINCTRL_PIN(pin)		\
+	PINCTRL_PIN(pin, "P" #pin)
+
+struct pxa_desc_function {
+	const char	*name;
+	u8		muxval;
+};
+
+struct pxa_desc_pin {
+	struct pinctrl_pin_desc		pin;
+	struct pxa_desc_function	*functions;
+};
+
+struct pxa_pinctrl_group {
+	const char	*name;
+	unsigned	pin;
+};
+
+struct pxa_pinctrl_function {
+	const char	*name;
+	const char	**groups;
+	unsigned	ngroups;
+};
+
+struct pxa_pinctrl {
+	spinlock_t			lock;
+	void __iomem			**base_gafr;
+	void __iomem			**base_gpdr;
+	void __iomem			**base_pgsr;
+	struct device			*dev;
+	struct pinctrl_desc		desc;
+	struct pinctrl_dev		*pctl_dev;
+	unsigned			npins;
+	const struct pxa_desc_pin	*ppins;
+	unsigned			ngroups;
+	struct pxa_pinctrl_group	*groups;
+	unsigned			nfuncs;
+	struct pxa_pinctrl_function	*functions;
+	char				*name;
+};
+
+int pxa2xx_pinctrl_init(struct platform_device *pdev,
+			const struct pxa_desc_pin *ppins, int npins,
+			void __iomem *base_gafr[], void __iomem *base_gpdr[],
+			void __iomem *base_gpsr[]);
+
+#endif /* __PINCTRL_PXA_H */
diff --git a/drivers/pinctrl/qcom/Kconfig b/drivers/pinctrl/qcom/Kconfig
index 383263a..eeac8cb 100644
--- a/drivers/pinctrl/qcom/Kconfig
+++ b/drivers/pinctrl/qcom/Kconfig
@@ -63,6 +63,14 @@
 	  This is the pinctrl, pinmux, pinconf and gpiolib driver for the
 	  Qualcomm TLMM block found on the Qualcomm 8916 platform.
 
+config PINCTRL_MSM8996
+	tristate "Qualcomm MSM8996 pin controller driver"
+	depends on GPIOLIB && OF
+	select PINCTRL_MSM
+	help
+	  This is the pinctrl, pinmux, pinconf and gpiolib driver for the
+	  Qualcomm TLMM block found in the Qualcomm MSM8996 platform.
+
 config PINCTRL_QDF2XXX
 	tristate "Qualcomm Technologies QDF2xxx pin controller driver"
 	depends on GPIOLIB && ACPI
diff --git a/drivers/pinctrl/qcom/Makefile b/drivers/pinctrl/qcom/Makefile
index 13b190e..dfb50a9 100644
--- a/drivers/pinctrl/qcom/Makefile
+++ b/drivers/pinctrl/qcom/Makefile
@@ -7,6 +7,7 @@
 obj-$(CONFIG_PINCTRL_MSM8960)	+= pinctrl-msm8960.o
 obj-$(CONFIG_PINCTRL_MSM8X74)	+= pinctrl-msm8x74.o
 obj-$(CONFIG_PINCTRL_MSM8916)	+= pinctrl-msm8916.o
+obj-$(CONFIG_PINCTRL_MSM8996)   += pinctrl-msm8996.o
 obj-$(CONFIG_PINCTRL_QDF2XXX)	+= pinctrl-qdf2xxx.o
 obj-$(CONFIG_PINCTRL_QCOM_SPMI_PMIC) += pinctrl-spmi-gpio.o
 obj-$(CONFIG_PINCTRL_QCOM_SPMI_PMIC) += pinctrl-spmi-mpp.o
diff --git a/drivers/pinctrl/qcom/pinctrl-msm8996.c b/drivers/pinctrl/qcom/pinctrl-msm8996.c
new file mode 100644
index 0000000..c257927
--- /dev/null
+++ b/drivers/pinctrl/qcom/pinctrl-msm8996.c
@@ -0,0 +1,1942 @@
+/*
+ * Copyright (c) 2014-2015, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/pinctrl/pinctrl.h>
+
+#include "pinctrl-msm.h"
+
+#define FUNCTION(fname)			                \
+	[msm_mux_##fname] = {		                \
+		.name = #fname,				\
+		.groups = fname##_groups,               \
+		.ngroups = ARRAY_SIZE(fname##_groups),	\
+	}
+
+#define REG_BASE 0x0
+#define REG_SIZE 0x1000
+#define PINGROUP(id, f1, f2, f3, f4, f5, f6, f7, f8, f9)	\
+	{					        \
+		.name = "gpio" #id,			\
+		.pins = gpio##id##_pins,		\
+		.npins = (unsigned)ARRAY_SIZE(gpio##id##_pins),	\
+		.funcs = (int[]){			\
+			msm_mux_gpio, /* gpio mode */	\
+			msm_mux_##f1,			\
+			msm_mux_##f2,			\
+			msm_mux_##f3,			\
+			msm_mux_##f4,			\
+			msm_mux_##f5,			\
+			msm_mux_##f6,			\
+			msm_mux_##f7,			\
+			msm_mux_##f8,			\
+			msm_mux_##f9			\
+		},				        \
+		.nfuncs = 10,				\
+		.ctl_reg = REG_BASE + REG_SIZE * id,	\
+		.io_reg = REG_BASE + 0x4 + REG_SIZE * id,		\
+		.intr_cfg_reg = REG_BASE + 0x8 + REG_SIZE * id,		\
+		.intr_status_reg = REG_BASE + 0xc + REG_SIZE * id,	\
+		.intr_target_reg = REG_BASE + 0x8 + REG_SIZE * id,	\
+		.mux_bit = 2,			\
+		.pull_bit = 0,			\
+		.drv_bit = 6,			\
+		.oe_bit = 9,			\
+		.in_bit = 0,			\
+		.out_bit = 1,			\
+		.intr_enable_bit = 0,		\
+		.intr_status_bit = 0,		\
+		.intr_target_bit = 5,		\
+		.intr_target_kpss_val = 3,	\
+		.intr_raw_status_bit = 4,	\
+		.intr_polarity_bit = 1,		\
+		.intr_detection_bit = 2,	\
+		.intr_detection_width = 2,	\
+	}
+
+#define SDC_QDSD_PINGROUP(pg_name, ctl, pull, drv)	\
+	{					        \
+		.name = #pg_name,			\
+		.pins = pg_name##_pins,			\
+		.npins = (unsigned)ARRAY_SIZE(pg_name##_pins),	\
+		.ctl_reg = ctl,				\
+		.io_reg = 0,				\
+		.intr_cfg_reg = 0,			\
+		.intr_status_reg = 0,			\
+		.intr_target_reg = 0,			\
+		.mux_bit = -1,				\
+		.pull_bit = pull,			\
+		.drv_bit = drv,				\
+		.oe_bit = -1,				\
+		.in_bit = -1,				\
+		.out_bit = -1,				\
+		.intr_enable_bit = -1,			\
+		.intr_status_bit = -1,			\
+		.intr_target_bit = -1,			\
+		.intr_raw_status_bit = -1,		\
+		.intr_polarity_bit = -1,		\
+		.intr_detection_bit = -1,		\
+		.intr_detection_width = -1,		\
+	}
+static const struct pinctrl_pin_desc msm8996_pins[] = {
+	PINCTRL_PIN(0, "GPIO_0"),
+	PINCTRL_PIN(1, "GPIO_1"),
+	PINCTRL_PIN(2, "GPIO_2"),
+	PINCTRL_PIN(3, "GPIO_3"),
+	PINCTRL_PIN(4, "GPIO_4"),
+	PINCTRL_PIN(5, "GPIO_5"),
+	PINCTRL_PIN(6, "GPIO_6"),
+	PINCTRL_PIN(7, "GPIO_7"),
+	PINCTRL_PIN(8, "GPIO_8"),
+	PINCTRL_PIN(9, "GPIO_9"),
+	PINCTRL_PIN(10, "GPIO_10"),
+	PINCTRL_PIN(11, "GPIO_11"),
+	PINCTRL_PIN(12, "GPIO_12"),
+	PINCTRL_PIN(13, "GPIO_13"),
+	PINCTRL_PIN(14, "GPIO_14"),
+	PINCTRL_PIN(15, "GPIO_15"),
+	PINCTRL_PIN(16, "GPIO_16"),
+	PINCTRL_PIN(17, "GPIO_17"),
+	PINCTRL_PIN(18, "GPIO_18"),
+	PINCTRL_PIN(19, "GPIO_19"),
+	PINCTRL_PIN(20, "GPIO_20"),
+	PINCTRL_PIN(21, "GPIO_21"),
+	PINCTRL_PIN(22, "GPIO_22"),
+	PINCTRL_PIN(23, "GPIO_23"),
+	PINCTRL_PIN(24, "GPIO_24"),
+	PINCTRL_PIN(25, "GPIO_25"),
+	PINCTRL_PIN(26, "GPIO_26"),
+	PINCTRL_PIN(27, "GPIO_27"),
+	PINCTRL_PIN(28, "GPIO_28"),
+	PINCTRL_PIN(29, "GPIO_29"),
+	PINCTRL_PIN(30, "GPIO_30"),
+	PINCTRL_PIN(31, "GPIO_31"),
+	PINCTRL_PIN(32, "GPIO_32"),
+	PINCTRL_PIN(33, "GPIO_33"),
+	PINCTRL_PIN(34, "GPIO_34"),
+	PINCTRL_PIN(35, "GPIO_35"),
+	PINCTRL_PIN(36, "GPIO_36"),
+	PINCTRL_PIN(37, "GPIO_37"),
+	PINCTRL_PIN(38, "GPIO_38"),
+	PINCTRL_PIN(39, "GPIO_39"),
+	PINCTRL_PIN(40, "GPIO_40"),
+	PINCTRL_PIN(41, "GPIO_41"),
+	PINCTRL_PIN(42, "GPIO_42"),
+	PINCTRL_PIN(43, "GPIO_43"),
+	PINCTRL_PIN(44, "GPIO_44"),
+	PINCTRL_PIN(45, "GPIO_45"),
+	PINCTRL_PIN(46, "GPIO_46"),
+	PINCTRL_PIN(47, "GPIO_47"),
+	PINCTRL_PIN(48, "GPIO_48"),
+	PINCTRL_PIN(49, "GPIO_49"),
+	PINCTRL_PIN(50, "GPIO_50"),
+	PINCTRL_PIN(51, "GPIO_51"),
+	PINCTRL_PIN(52, "GPIO_52"),
+	PINCTRL_PIN(53, "GPIO_53"),
+	PINCTRL_PIN(54, "GPIO_54"),
+	PINCTRL_PIN(55, "GPIO_55"),
+	PINCTRL_PIN(56, "GPIO_56"),
+	PINCTRL_PIN(57, "GPIO_57"),
+	PINCTRL_PIN(58, "GPIO_58"),
+	PINCTRL_PIN(59, "GPIO_59"),
+	PINCTRL_PIN(60, "GPIO_60"),
+	PINCTRL_PIN(61, "GPIO_61"),
+	PINCTRL_PIN(62, "GPIO_62"),
+	PINCTRL_PIN(63, "GPIO_63"),
+	PINCTRL_PIN(64, "GPIO_64"),
+	PINCTRL_PIN(65, "GPIO_65"),
+	PINCTRL_PIN(66, "GPIO_66"),
+	PINCTRL_PIN(67, "GPIO_67"),
+	PINCTRL_PIN(68, "GPIO_68"),
+	PINCTRL_PIN(69, "GPIO_69"),
+	PINCTRL_PIN(70, "GPIO_70"),
+	PINCTRL_PIN(71, "GPIO_71"),
+	PINCTRL_PIN(72, "GPIO_72"),
+	PINCTRL_PIN(73, "GPIO_73"),
+	PINCTRL_PIN(74, "GPIO_74"),
+	PINCTRL_PIN(75, "GPIO_75"),
+	PINCTRL_PIN(76, "GPIO_76"),
+	PINCTRL_PIN(77, "GPIO_77"),
+	PINCTRL_PIN(78, "GPIO_78"),
+	PINCTRL_PIN(79, "GPIO_79"),
+	PINCTRL_PIN(80, "GPIO_80"),
+	PINCTRL_PIN(81, "GPIO_81"),
+	PINCTRL_PIN(82, "GPIO_82"),
+	PINCTRL_PIN(83, "GPIO_83"),
+	PINCTRL_PIN(84, "GPIO_84"),
+	PINCTRL_PIN(85, "GPIO_85"),
+	PINCTRL_PIN(86, "GPIO_86"),
+	PINCTRL_PIN(87, "GPIO_87"),
+	PINCTRL_PIN(88, "GPIO_88"),
+	PINCTRL_PIN(89, "GPIO_89"),
+	PINCTRL_PIN(90, "GPIO_90"),
+	PINCTRL_PIN(91, "GPIO_91"),
+	PINCTRL_PIN(92, "GPIO_92"),
+	PINCTRL_PIN(93, "GPIO_93"),
+	PINCTRL_PIN(94, "GPIO_94"),
+	PINCTRL_PIN(95, "GPIO_95"),
+	PINCTRL_PIN(96, "GPIO_96"),
+	PINCTRL_PIN(97, "GPIO_97"),
+	PINCTRL_PIN(98, "GPIO_98"),
+	PINCTRL_PIN(99, "GPIO_99"),
+	PINCTRL_PIN(100, "GPIO_100"),
+	PINCTRL_PIN(101, "GPIO_101"),
+	PINCTRL_PIN(102, "GPIO_102"),
+	PINCTRL_PIN(103, "GPIO_103"),
+	PINCTRL_PIN(104, "GPIO_104"),
+	PINCTRL_PIN(105, "GPIO_105"),
+	PINCTRL_PIN(106, "GPIO_106"),
+	PINCTRL_PIN(107, "GPIO_107"),
+	PINCTRL_PIN(108, "GPIO_108"),
+	PINCTRL_PIN(109, "GPIO_109"),
+	PINCTRL_PIN(110, "GPIO_110"),
+	PINCTRL_PIN(111, "GPIO_111"),
+	PINCTRL_PIN(112, "GPIO_112"),
+	PINCTRL_PIN(113, "GPIO_113"),
+	PINCTRL_PIN(114, "GPIO_114"),
+	PINCTRL_PIN(115, "GPIO_115"),
+	PINCTRL_PIN(116, "GPIO_116"),
+	PINCTRL_PIN(117, "GPIO_117"),
+	PINCTRL_PIN(118, "GPIO_118"),
+	PINCTRL_PIN(119, "GPIO_119"),
+	PINCTRL_PIN(120, "GPIO_120"),
+	PINCTRL_PIN(121, "GPIO_121"),
+	PINCTRL_PIN(122, "GPIO_122"),
+	PINCTRL_PIN(123, "GPIO_123"),
+	PINCTRL_PIN(124, "GPIO_124"),
+	PINCTRL_PIN(125, "GPIO_125"),
+	PINCTRL_PIN(126, "GPIO_126"),
+	PINCTRL_PIN(127, "GPIO_127"),
+	PINCTRL_PIN(128, "GPIO_128"),
+	PINCTRL_PIN(129, "GPIO_129"),
+	PINCTRL_PIN(130, "GPIO_130"),
+	PINCTRL_PIN(131, "GPIO_131"),
+	PINCTRL_PIN(132, "GPIO_132"),
+	PINCTRL_PIN(133, "GPIO_133"),
+	PINCTRL_PIN(134, "GPIO_134"),
+	PINCTRL_PIN(135, "GPIO_135"),
+	PINCTRL_PIN(136, "GPIO_136"),
+	PINCTRL_PIN(137, "GPIO_137"),
+	PINCTRL_PIN(138, "GPIO_138"),
+	PINCTRL_PIN(139, "GPIO_139"),
+	PINCTRL_PIN(140, "GPIO_140"),
+	PINCTRL_PIN(141, "GPIO_141"),
+	PINCTRL_PIN(142, "GPIO_142"),
+	PINCTRL_PIN(143, "GPIO_143"),
+	PINCTRL_PIN(144, "GPIO_144"),
+	PINCTRL_PIN(145, "GPIO_145"),
+	PINCTRL_PIN(146, "GPIO_146"),
+	PINCTRL_PIN(147, "GPIO_147"),
+	PINCTRL_PIN(148, "GPIO_148"),
+	PINCTRL_PIN(149, "GPIO_149"),
+	PINCTRL_PIN(150, "SDC1_CLK"),
+	PINCTRL_PIN(151, "SDC1_CMD"),
+	PINCTRL_PIN(152, "SDC1_DATA"),
+	PINCTRL_PIN(153, "SDC2_CLK"),
+	PINCTRL_PIN(154, "SDC2_CMD"),
+	PINCTRL_PIN(155, "SDC2_DATA"),
+	PINCTRL_PIN(156, "SDC1_RCLK"),
+};
+
+#define DECLARE_MSM_GPIO_PINS(pin) \
+	static const unsigned int gpio##pin##_pins[] = { pin }
+DECLARE_MSM_GPIO_PINS(0);
+DECLARE_MSM_GPIO_PINS(1);
+DECLARE_MSM_GPIO_PINS(2);
+DECLARE_MSM_GPIO_PINS(3);
+DECLARE_MSM_GPIO_PINS(4);
+DECLARE_MSM_GPIO_PINS(5);
+DECLARE_MSM_GPIO_PINS(6);
+DECLARE_MSM_GPIO_PINS(7);
+DECLARE_MSM_GPIO_PINS(8);
+DECLARE_MSM_GPIO_PINS(9);
+DECLARE_MSM_GPIO_PINS(10);
+DECLARE_MSM_GPIO_PINS(11);
+DECLARE_MSM_GPIO_PINS(12);
+DECLARE_MSM_GPIO_PINS(13);
+DECLARE_MSM_GPIO_PINS(14);
+DECLARE_MSM_GPIO_PINS(15);
+DECLARE_MSM_GPIO_PINS(16);
+DECLARE_MSM_GPIO_PINS(17);
+DECLARE_MSM_GPIO_PINS(18);
+DECLARE_MSM_GPIO_PINS(19);
+DECLARE_MSM_GPIO_PINS(20);
+DECLARE_MSM_GPIO_PINS(21);
+DECLARE_MSM_GPIO_PINS(22);
+DECLARE_MSM_GPIO_PINS(23);
+DECLARE_MSM_GPIO_PINS(24);
+DECLARE_MSM_GPIO_PINS(25);
+DECLARE_MSM_GPIO_PINS(26);
+DECLARE_MSM_GPIO_PINS(27);
+DECLARE_MSM_GPIO_PINS(28);
+DECLARE_MSM_GPIO_PINS(29);
+DECLARE_MSM_GPIO_PINS(30);
+DECLARE_MSM_GPIO_PINS(31);
+DECLARE_MSM_GPIO_PINS(32);
+DECLARE_MSM_GPIO_PINS(33);
+DECLARE_MSM_GPIO_PINS(34);
+DECLARE_MSM_GPIO_PINS(35);
+DECLARE_MSM_GPIO_PINS(36);
+DECLARE_MSM_GPIO_PINS(37);
+DECLARE_MSM_GPIO_PINS(38);
+DECLARE_MSM_GPIO_PINS(39);
+DECLARE_MSM_GPIO_PINS(40);
+DECLARE_MSM_GPIO_PINS(41);
+DECLARE_MSM_GPIO_PINS(42);
+DECLARE_MSM_GPIO_PINS(43);
+DECLARE_MSM_GPIO_PINS(44);
+DECLARE_MSM_GPIO_PINS(45);
+DECLARE_MSM_GPIO_PINS(46);
+DECLARE_MSM_GPIO_PINS(47);
+DECLARE_MSM_GPIO_PINS(48);
+DECLARE_MSM_GPIO_PINS(49);
+DECLARE_MSM_GPIO_PINS(50);
+DECLARE_MSM_GPIO_PINS(51);
+DECLARE_MSM_GPIO_PINS(52);
+DECLARE_MSM_GPIO_PINS(53);
+DECLARE_MSM_GPIO_PINS(54);
+DECLARE_MSM_GPIO_PINS(55);
+DECLARE_MSM_GPIO_PINS(56);
+DECLARE_MSM_GPIO_PINS(57);
+DECLARE_MSM_GPIO_PINS(58);
+DECLARE_MSM_GPIO_PINS(59);
+DECLARE_MSM_GPIO_PINS(60);
+DECLARE_MSM_GPIO_PINS(61);
+DECLARE_MSM_GPIO_PINS(62);
+DECLARE_MSM_GPIO_PINS(63);
+DECLARE_MSM_GPIO_PINS(64);
+DECLARE_MSM_GPIO_PINS(65);
+DECLARE_MSM_GPIO_PINS(66);
+DECLARE_MSM_GPIO_PINS(67);
+DECLARE_MSM_GPIO_PINS(68);
+DECLARE_MSM_GPIO_PINS(69);
+DECLARE_MSM_GPIO_PINS(70);
+DECLARE_MSM_GPIO_PINS(71);
+DECLARE_MSM_GPIO_PINS(72);
+DECLARE_MSM_GPIO_PINS(73);
+DECLARE_MSM_GPIO_PINS(74);
+DECLARE_MSM_GPIO_PINS(75);
+DECLARE_MSM_GPIO_PINS(76);
+DECLARE_MSM_GPIO_PINS(77);
+DECLARE_MSM_GPIO_PINS(78);
+DECLARE_MSM_GPIO_PINS(79);
+DECLARE_MSM_GPIO_PINS(80);
+DECLARE_MSM_GPIO_PINS(81);
+DECLARE_MSM_GPIO_PINS(82);
+DECLARE_MSM_GPIO_PINS(83);
+DECLARE_MSM_GPIO_PINS(84);
+DECLARE_MSM_GPIO_PINS(85);
+DECLARE_MSM_GPIO_PINS(86);
+DECLARE_MSM_GPIO_PINS(87);
+DECLARE_MSM_GPIO_PINS(88);
+DECLARE_MSM_GPIO_PINS(89);
+DECLARE_MSM_GPIO_PINS(90);
+DECLARE_MSM_GPIO_PINS(91);
+DECLARE_MSM_GPIO_PINS(92);
+DECLARE_MSM_GPIO_PINS(93);
+DECLARE_MSM_GPIO_PINS(94);
+DECLARE_MSM_GPIO_PINS(95);
+DECLARE_MSM_GPIO_PINS(96);
+DECLARE_MSM_GPIO_PINS(97);
+DECLARE_MSM_GPIO_PINS(98);
+DECLARE_MSM_GPIO_PINS(99);
+DECLARE_MSM_GPIO_PINS(100);
+DECLARE_MSM_GPIO_PINS(101);
+DECLARE_MSM_GPIO_PINS(102);
+DECLARE_MSM_GPIO_PINS(103);
+DECLARE_MSM_GPIO_PINS(104);
+DECLARE_MSM_GPIO_PINS(105);
+DECLARE_MSM_GPIO_PINS(106);
+DECLARE_MSM_GPIO_PINS(107);
+DECLARE_MSM_GPIO_PINS(108);
+DECLARE_MSM_GPIO_PINS(109);
+DECLARE_MSM_GPIO_PINS(110);
+DECLARE_MSM_GPIO_PINS(111);
+DECLARE_MSM_GPIO_PINS(112);
+DECLARE_MSM_GPIO_PINS(113);
+DECLARE_MSM_GPIO_PINS(114);
+DECLARE_MSM_GPIO_PINS(115);
+DECLARE_MSM_GPIO_PINS(116);
+DECLARE_MSM_GPIO_PINS(117);
+DECLARE_MSM_GPIO_PINS(118);
+DECLARE_MSM_GPIO_PINS(119);
+DECLARE_MSM_GPIO_PINS(120);
+DECLARE_MSM_GPIO_PINS(121);
+DECLARE_MSM_GPIO_PINS(122);
+DECLARE_MSM_GPIO_PINS(123);
+DECLARE_MSM_GPIO_PINS(124);
+DECLARE_MSM_GPIO_PINS(125);
+DECLARE_MSM_GPIO_PINS(126);
+DECLARE_MSM_GPIO_PINS(127);
+DECLARE_MSM_GPIO_PINS(128);
+DECLARE_MSM_GPIO_PINS(129);
+DECLARE_MSM_GPIO_PINS(130);
+DECLARE_MSM_GPIO_PINS(131);
+DECLARE_MSM_GPIO_PINS(132);
+DECLARE_MSM_GPIO_PINS(133);
+DECLARE_MSM_GPIO_PINS(134);
+DECLARE_MSM_GPIO_PINS(135);
+DECLARE_MSM_GPIO_PINS(136);
+DECLARE_MSM_GPIO_PINS(137);
+DECLARE_MSM_GPIO_PINS(138);
+DECLARE_MSM_GPIO_PINS(139);
+DECLARE_MSM_GPIO_PINS(140);
+DECLARE_MSM_GPIO_PINS(141);
+DECLARE_MSM_GPIO_PINS(142);
+DECLARE_MSM_GPIO_PINS(143);
+DECLARE_MSM_GPIO_PINS(144);
+DECLARE_MSM_GPIO_PINS(145);
+DECLARE_MSM_GPIO_PINS(146);
+DECLARE_MSM_GPIO_PINS(147);
+DECLARE_MSM_GPIO_PINS(148);
+DECLARE_MSM_GPIO_PINS(149);
+
+static const unsigned int sdc1_clk_pins[] = { 150 };
+static const unsigned int sdc1_cmd_pins[] = { 151 };
+static const unsigned int sdc1_data_pins[] = { 152 };
+static const unsigned int sdc2_clk_pins[] = { 153 };
+static const unsigned int sdc2_cmd_pins[] = { 154 };
+static const unsigned int sdc2_data_pins[] = { 155 };
+static const unsigned int sdc1_rclk_pins[] = { 156 };
+
+enum msm8996_functions {
+	msm_mux_adsp_ext,
+	msm_mux_atest_bbrx0,
+	msm_mux_atest_bbrx1,
+	msm_mux_atest_char,
+	msm_mux_atest_char0,
+	msm_mux_atest_char1,
+	msm_mux_atest_char2,
+	msm_mux_atest_char3,
+	msm_mux_atest_gpsadc0,
+	msm_mux_atest_gpsadc1,
+	msm_mux_atest_tsens,
+	msm_mux_atest_tsens2,
+	msm_mux_atest_usb1,
+	msm_mux_atest_usb10,
+	msm_mux_atest_usb11,
+	msm_mux_atest_usb12,
+	msm_mux_atest_usb13,
+	msm_mux_atest_usb2,
+	msm_mux_atest_usb20,
+	msm_mux_atest_usb21,
+	msm_mux_atest_usb22,
+	msm_mux_atest_usb23,
+	msm_mux_audio_ref,
+	msm_mux_bimc_dte0,
+	msm_mux_bimc_dte1,
+	msm_mux_blsp10_spi,
+	msm_mux_blsp11_i2c_scl_b,
+	msm_mux_blsp11_i2c_sda_b,
+	msm_mux_blsp11_uart_rx_b,
+	msm_mux_blsp11_uart_tx_b,
+	msm_mux_blsp1_spi,
+	msm_mux_blsp2_spi,
+	msm_mux_blsp_i2c1,
+	msm_mux_blsp_i2c10,
+	msm_mux_blsp_i2c11,
+	msm_mux_blsp_i2c12,
+	msm_mux_blsp_i2c2,
+	msm_mux_blsp_i2c3,
+	msm_mux_blsp_i2c4,
+	msm_mux_blsp_i2c5,
+	msm_mux_blsp_i2c6,
+	msm_mux_blsp_i2c7,
+	msm_mux_blsp_i2c8,
+	msm_mux_blsp_i2c9,
+	msm_mux_blsp_spi1,
+	msm_mux_blsp_spi10,
+	msm_mux_blsp_spi11,
+	msm_mux_blsp_spi12,
+	msm_mux_blsp_spi2,
+	msm_mux_blsp_spi3,
+	msm_mux_blsp_spi4,
+	msm_mux_blsp_spi5,
+	msm_mux_blsp_spi6,
+	msm_mux_blsp_spi7,
+	msm_mux_blsp_spi8,
+	msm_mux_blsp_spi9,
+	msm_mux_blsp_uart1,
+	msm_mux_blsp_uart10,
+	msm_mux_blsp_uart11,
+	msm_mux_blsp_uart12,
+	msm_mux_blsp_uart2,
+	msm_mux_blsp_uart3,
+	msm_mux_blsp_uart4,
+	msm_mux_blsp_uart5,
+	msm_mux_blsp_uart6,
+	msm_mux_blsp_uart7,
+	msm_mux_blsp_uart8,
+	msm_mux_blsp_uart9,
+	msm_mux_blsp_uim1,
+	msm_mux_blsp_uim10,
+	msm_mux_blsp_uim11,
+	msm_mux_blsp_uim12,
+	msm_mux_blsp_uim2,
+	msm_mux_blsp_uim3,
+	msm_mux_blsp_uim4,
+	msm_mux_blsp_uim5,
+	msm_mux_blsp_uim6,
+	msm_mux_blsp_uim7,
+	msm_mux_blsp_uim8,
+	msm_mux_blsp_uim9,
+	msm_mux_btfm_slimbus,
+	msm_mux_cam_mclk,
+	msm_mux_cci_async,
+	msm_mux_cci_i2c,
+	msm_mux_cci_timer0,
+	msm_mux_cci_timer1,
+	msm_mux_cci_timer2,
+	msm_mux_cci_timer3,
+	msm_mux_cci_timer4,
+	msm_mux_cri_trng,
+	msm_mux_cri_trng0,
+	msm_mux_cri_trng1,
+	msm_mux_dac_calib0,
+	msm_mux_dac_calib1,
+	msm_mux_dac_calib10,
+	msm_mux_dac_calib11,
+	msm_mux_dac_calib12,
+	msm_mux_dac_calib13,
+	msm_mux_dac_calib14,
+	msm_mux_dac_calib15,
+	msm_mux_dac_calib16,
+	msm_mux_dac_calib17,
+	msm_mux_dac_calib18,
+	msm_mux_dac_calib19,
+	msm_mux_dac_calib2,
+	msm_mux_dac_calib20,
+	msm_mux_dac_calib21,
+	msm_mux_dac_calib22,
+	msm_mux_dac_calib23,
+	msm_mux_dac_calib24,
+	msm_mux_dac_calib25,
+	msm_mux_dac_calib26,
+	msm_mux_dac_calib3,
+	msm_mux_dac_calib4,
+	msm_mux_dac_calib5,
+	msm_mux_dac_calib6,
+	msm_mux_dac_calib7,
+	msm_mux_dac_calib8,
+	msm_mux_dac_calib9,
+	msm_mux_dac_gpio,
+	msm_mux_dbg_out,
+	msm_mux_ddr_bist,
+	msm_mux_edp_hot,
+	msm_mux_edp_lcd,
+	msm_mux_gcc_gp1_clk_a,
+	msm_mux_gcc_gp1_clk_b,
+	msm_mux_gcc_gp2_clk_a,
+	msm_mux_gcc_gp2_clk_b,
+	msm_mux_gcc_gp3_clk_a,
+	msm_mux_gcc_gp3_clk_b,
+	msm_mux_gsm_tx,
+	msm_mux_hdmi_cec,
+	msm_mux_hdmi_ddc,
+	msm_mux_hdmi_hot,
+	msm_mux_hdmi_rcv,
+	msm_mux_isense_dbg,
+	msm_mux_ldo_en,
+	msm_mux_ldo_update,
+	msm_mux_lpass_slimbus,
+	msm_mux_m_voc,
+	msm_mux_mdp_vsync,
+	msm_mux_mdp_vsync_p_b,
+	msm_mux_mdp_vsync_s_b,
+	msm_mux_modem_tsync,
+	msm_mux_mss_lte,
+	msm_mux_nav_dr,
+	msm_mux_nav_pps,
+	msm_mux_pa_indicator,
+	msm_mux_pci_e0,
+	msm_mux_pci_e1,
+	msm_mux_pci_e2,
+	msm_mux_pll_bypassnl,
+	msm_mux_pll_reset,
+	msm_mux_pri_mi2s,
+	msm_mux_prng_rosc,
+	msm_mux_pwr_crypto,
+	msm_mux_pwr_modem,
+	msm_mux_pwr_nav,
+	msm_mux_qdss_cti,
+	msm_mux_qdss_cti_trig_in_a,
+	msm_mux_qdss_cti_trig_in_b,
+	msm_mux_qdss_cti_trig_out_a,
+	msm_mux_qdss_cti_trig_out_b,
+	msm_mux_qdss_stm0,
+	msm_mux_qdss_stm1,
+	msm_mux_qdss_stm10,
+	msm_mux_qdss_stm11,
+	msm_mux_qdss_stm12,
+	msm_mux_qdss_stm13,
+	msm_mux_qdss_stm14,
+	msm_mux_qdss_stm15,
+	msm_mux_qdss_stm16,
+	msm_mux_qdss_stm17,
+	msm_mux_qdss_stm18,
+	msm_mux_qdss_stm19,
+	msm_mux_qdss_stm2,
+	msm_mux_qdss_stm20,
+	msm_mux_qdss_stm21,
+	msm_mux_qdss_stm22,
+	msm_mux_qdss_stm23,
+	msm_mux_qdss_stm24,
+	msm_mux_qdss_stm25,
+	msm_mux_qdss_stm26,
+	msm_mux_qdss_stm27,
+	msm_mux_qdss_stm28,
+	msm_mux_qdss_stm29,
+	msm_mux_qdss_stm3,
+	msm_mux_qdss_stm30,
+	msm_mux_qdss_stm31,
+	msm_mux_qdss_stm4,
+	msm_mux_qdss_stm5,
+	msm_mux_qdss_stm6,
+	msm_mux_qdss_stm7,
+	msm_mux_qdss_stm8,
+	msm_mux_qdss_stm9,
+	msm_mux_qdss_traceclk_a,
+	msm_mux_qdss_traceclk_b,
+	msm_mux_qdss_tracectl_a,
+	msm_mux_qdss_tracectl_b,
+	msm_mux_qdss_tracedata_11,
+	msm_mux_qdss_tracedata_12,
+	msm_mux_qdss_tracedata_a,
+	msm_mux_qdss_tracedata_b,
+	msm_mux_qspi0,
+	msm_mux_qspi1,
+	msm_mux_qspi2,
+	msm_mux_qspi3,
+	msm_mux_qspi_clk,
+	msm_mux_qspi_cs,
+	msm_mux_qua_mi2s,
+	msm_mux_sd_card,
+	msm_mux_sd_write,
+	msm_mux_sdc40,
+	msm_mux_sdc41,
+	msm_mux_sdc42,
+	msm_mux_sdc43,
+	msm_mux_sdc4_clk,
+	msm_mux_sdc4_cmd,
+	msm_mux_sec_mi2s,
+	msm_mux_spkr_i2s,
+	msm_mux_ssbi1,
+	msm_mux_ssbi2,
+	msm_mux_ssc_irq,
+	msm_mux_ter_mi2s,
+	msm_mux_tsense_pwm1,
+	msm_mux_tsense_pwm2,
+	msm_mux_tsif1_clk,
+	msm_mux_tsif1_data,
+	msm_mux_tsif1_en,
+	msm_mux_tsif1_error,
+	msm_mux_tsif1_sync,
+	msm_mux_tsif2_clk,
+	msm_mux_tsif2_data,
+	msm_mux_tsif2_en,
+	msm_mux_tsif2_error,
+	msm_mux_tsif2_sync,
+	msm_mux_uim1,
+	msm_mux_uim2,
+	msm_mux_uim3,
+	msm_mux_uim4,
+	msm_mux_uim_batt,
+	msm_mux_vfr_1,
+	msm_mux_gpio,
+	msm_mux_NA,
+};
+
+static const char * const gpio_groups[] = {
+	"gpio0", "gpio1", "gpio2", "gpio3", "gpio4", "gpio5", "gpio6", "gpio7",
+	"gpio8", "gpio9", "gpio10", "gpio11", "gpio12", "gpio13", "gpio14",
+	"gpio15", "gpio16", "gpio17", "gpio18", "gpio19", "gpio20", "gpio21",
+	"gpio22", "gpio23", "gpio24", "gpio25", "gpio26", "gpio27", "gpio28",
+	"gpio29", "gpio30", "gpio31", "gpio32", "gpio33", "gpio34", "gpio35",
+	"gpio36", "gpio37", "gpio38", "gpio39", "gpio40", "gpio41", "gpio42",
+	"gpio43", "gpio44", "gpio45", "gpio46", "gpio47", "gpio48", "gpio49",
+	"gpio50", "gpio51", "gpio52", "gpio53", "gpio54", "gpio55", "gpio56",
+	"gpio57", "gpio58", "gpio59", "gpio60", "gpio61", "gpio62", "gpio63",
+	"gpio64", "gpio65", "gpio66", "gpio67", "gpio68", "gpio69", "gpio70",
+	"gpio71", "gpio72", "gpio73", "gpio74", "gpio75", "gpio76", "gpio77",
+	"gpio78", "gpio79", "gpio80", "gpio81", "gpio82", "gpio83", "gpio84",
+	"gpio85", "gpio86", "gpio87", "gpio88", "gpio89", "gpio90", "gpio91",
+	"gpio92", "gpio93", "gpio94", "gpio95", "gpio96", "gpio97", "gpio98",
+	"gpio99", "gpio100", "gpio101", "gpio102", "gpio103", "gpio104",
+	"gpio105", "gpio106", "gpio107", "gpio108", "gpio109", "gpio110",
+	"gpio111", "gpio112", "gpio113", "gpio114", "gpio115", "gpio116",
+	"gpio117", "gpio118", "gpio119", "gpio120", "gpio121", "gpio122",
+	"gpio123", "gpio124", "gpio125", "gpio126", "gpio127", "gpio128",
+	"gpio129", "gpio130", "gpio131", "gpio132", "gpio133", "gpio134",
+	"gpio135", "gpio136", "gpio137", "gpio138", "gpio139", "gpio140",
+	"gpio141", "gpio142", "gpio143", "gpio144", "gpio145", "gpio146",
+	"gpio147", "gpio148", "gpio149"
+};
+
+
+static const char * const blsp_uart1_groups[] = {
+	"gpio0", "gpio1", "gpio2", "gpio3",
+};
+static const char * const blsp_spi1_groups[] = {
+	"gpio0", "gpio1", "gpio2", "gpio3",
+};
+static const char * const blsp_i2c1_groups[] = {
+	"gpio2", "gpio3",
+};
+static const char * const blsp_uim1_groups[] = {
+	"gpio0", "gpio1",
+};
+static const char * const atest_tsens_groups[] = {
+	"gpio3",
+};
+static const char * const bimc_dte1_groups[] = {
+	"gpio3", "gpio5",
+};
+static const char * const blsp_spi8_groups[] = {
+	"gpio4", "gpio5", "gpio6", "gpio7",
+};
+static const char * const blsp_uart8_groups[] = {
+	"gpio4", "gpio5", "gpio6", "gpio7",
+};
+static const char * const blsp_uim8_groups[] = {
+	"gpio4", "gpio5",
+};
+static const char * const qdss_cti_trig_out_b_groups[] = {
+	"gpio4",
+};
+static const char * const dac_calib0_groups[] = {
+	"gpio4", "gpio41",
+};
+static const char * const bimc_dte0_groups[] = {
+	"gpio4", "gpio6",
+};
+static const char * const qdss_cti_trig_in_b_groups[] = {
+	"gpio5",
+};
+static const char * const dac_calib1_groups[] = {
+	"gpio5", "gpio42",
+};
+static const char * const dac_calib2_groups[] = {
+	"gpio6", "gpio43",
+};
+static const char * const atest_tsens2_groups[] = {
+	"gpio7",
+};
+static const char * const blsp_spi10_groups[] = {
+	"gpio8", "gpio9", "gpio10", "gpio11",
+};
+static const char * const blsp_uart10_groups[] = {
+	"gpio8", "gpio9", "gpio10", "gpio11",
+};
+static const char * const blsp_uim10_groups[] = {
+	"gpio8", "gpio9",
+};
+static const char * const atest_bbrx1_groups[] = {
+	"gpio8",
+};
+static const char * const atest_usb12_groups[] = {
+	"gpio9",
+};
+static const char * const mdp_vsync_groups[] = {
+	"gpio10", "gpio11", "gpio12",
+};
+static const char * const edp_lcd_groups[] = {
+	"gpio10",
+};
+static const char * const blsp_i2c10_groups[] = {
+	"gpio10", "gpio11",
+};
+static const char * const atest_usb11_groups[] = {
+	"gpio10",
+};
+static const char * const atest_gpsadc0_groups[] = {
+	"gpio11",
+};
+static const char * const edp_hot_groups[] = {
+	"gpio11",
+};
+static const char * const atest_usb10_groups[] = {
+	"gpio11",
+};
+static const char * const m_voc_groups[] = {
+	"gpio12",
+};
+static const char * const dac_gpio_groups[] = {
+	"gpio12",
+};
+static const char * const atest_char_groups[] = {
+	"gpio12",
+};
+static const char * const cam_mclk_groups[] = {
+	"gpio13", "gpio14", "gpio15", "gpio16",
+};
+static const char * const pll_bypassnl_groups[] = {
+	"gpio13",
+};
+static const char * const qdss_stm7_groups[] = {
+	"gpio13",
+};
+static const char * const blsp_i2c8_groups[] = {
+	"gpio6", "gpio7",
+};
+static const char * const atest_usb1_groups[] = {
+	"gpio7",
+};
+static const char * const atest_usb13_groups[] = {
+	"gpio8",
+};
+static const char * const atest_bbrx0_groups[] = {
+	"gpio9",
+};
+static const char * const atest_gpsadc1_groups[] = {
+	"gpio10",
+};
+static const char * const qdss_tracedata_b_groups[] = {
+	"gpio13", "gpio14", "gpio15", "gpio16", "gpio17", "gpio18", "gpio19",
+	"gpio21", "gpio22", "gpio23", "gpio26", "gpio29", "gpio57", "gpio58",
+	"gpio92", "gpio93",
+};
+static const char * const pll_reset_groups[] = {
+	"gpio14",
+};
+static const char * const qdss_stm6_groups[] = {
+	"gpio14",
+};
+static const char * const qdss_stm5_groups[] = {
+	"gpio15",
+};
+static const char * const qdss_stm4_groups[] = {
+	"gpio16",
+};
+static const char * const atest_usb2_groups[] = {
+	"gpio16",
+};
+static const char * const dac_calib3_groups[] = {
+	"gpio17", "gpio44",
+};
+static const char * const cci_i2c_groups[] = {
+	"gpio17", "gpio18", "gpio19", "gpio20",
+};
+static const char * const qdss_stm3_groups[] = {
+	"gpio17",
+};
+static const char * const atest_usb23_groups[] = {
+	"gpio17",
+};
+static const char * const atest_char3_groups[] = {
+	"gpio17",
+};
+static const char * const dac_calib4_groups[] = {
+	"gpio18", "gpio45",
+};
+static const char * const qdss_stm2_groups[] = {
+	"gpio18",
+};
+static const char * const atest_usb22_groups[] = {
+	"gpio18",
+};
+static const char * const atest_char2_groups[] = {
+	"gpio18",
+};
+static const char * const dac_calib5_groups[] = {
+	"gpio19", "gpio46",
+};
+static const char * const qdss_stm1_groups[] = {
+	"gpio19",
+};
+static const char * const atest_usb21_groups[] = {
+	"gpio19",
+};
+static const char * const atest_char1_groups[] = {
+	"gpio19",
+};
+static const char * const dac_calib6_groups[] = {
+	"gpio20", "gpio47",
+};
+static const char * const dbg_out_groups[] = {
+	"gpio20",
+};
+static const char * const qdss_stm0_groups[] = {
+	"gpio20",
+};
+static const char * const atest_usb20_groups[] = {
+	"gpio20",
+};
+static const char * const atest_char0_groups[] = {
+	"gpio20",
+};
+static const char * const dac_calib7_groups[] = {
+	"gpio21", "gpio48",
+};
+static const char * const cci_timer0_groups[] = {
+	"gpio21",
+};
+static const char * const qdss_stm13_groups[] = {
+	"gpio21",
+};
+static const char * const dac_calib8_groups[] = {
+	"gpio22", "gpio49",
+};
+static const char * const cci_timer1_groups[] = {
+	"gpio22",
+};
+static const char * const qdss_stm12_groups[] = {
+	"gpio22",
+};
+static const char * const dac_calib9_groups[] = {
+	"gpio23", "gpio50",
+};
+static const char * const cci_timer2_groups[] = {
+	"gpio23",
+};
+static const char * const qdss_stm11_groups[] = {
+	"gpio23",
+};
+static const char * const dac_calib10_groups[] = {
+	"gpio24", "gpio51",
+};
+static const char * const cci_timer3_groups[] = {
+	"gpio24",
+};
+static const char * const cci_async_groups[] = {
+	"gpio24", "gpio25", "gpio26",
+};
+static const char * const blsp1_spi_groups[] = {
+	"gpio24", "gpio27", "gpio28", "gpio90",
+};
+static const char * const qdss_stm10_groups[] = {
+	"gpio24",
+};
+static const char * const qdss_cti_trig_in_a_groups[] = {
+	"gpio24",
+};
+static const char * const dac_calib11_groups[] = {
+	"gpio25", "gpio52",
+};
+static const char * const cci_timer4_groups[] = {
+	"gpio25",
+};
+static const char * const blsp_spi6_groups[] = {
+	"gpio25", "gpio26", "gpio27", "gpio28",
+};
+static const char * const blsp_uart6_groups[] = {
+	"gpio25", "gpio26", "gpio27", "gpio28",
+};
+static const char * const blsp_uim6_groups[] = {
+	"gpio25", "gpio26",
+};
+static const char * const blsp2_spi_groups[] = {
+	"gpio25", "gpio29", "gpio30",
+};
+static const char * const qdss_stm9_groups[] = {
+	"gpio25",
+};
+static const char * const qdss_cti_trig_out_a_groups[] = {
+	"gpio25",
+};
+static const char * const dac_calib12_groups[] = {
+	"gpio26", "gpio53",
+};
+static const char * const qdss_stm8_groups[] = {
+	"gpio26",
+};
+static const char * const dac_calib13_groups[] = {
+	"gpio27", "gpio54",
+};
+static const char * const blsp_i2c6_groups[] = {
+	"gpio27", "gpio28",
+};
+static const char * const qdss_tracectl_a_groups[] = {
+	"gpio27",
+};
+static const char * const dac_calib14_groups[] = {
+	"gpio28", "gpio55",
+};
+static const char * const qdss_traceclk_a_groups[] = {
+	"gpio28",
+};
+static const char * const dac_calib15_groups[] = {
+	"gpio29", "gpio56",
+};
+static const char * const dac_calib16_groups[] = {
+	"gpio30", "gpio57",
+};
+static const char * const hdmi_rcv_groups[] = {
+	"gpio30",
+};
+static const char * const dac_calib17_groups[] = {
+	"gpio31", "gpio58",
+};
+static const char * const pwr_modem_groups[] = {
+	"gpio31",
+};
+static const char * const hdmi_cec_groups[] = {
+	"gpio31",
+};
+static const char * const pwr_nav_groups[] = {
+	"gpio32",
+};
+static const char * const dac_calib18_groups[] = {
+	"gpio32", "gpio59",
+};
+static const char * const hdmi_ddc_groups[] = {
+	"gpio32", "gpio33",
+};
+static const char * const pwr_crypto_groups[] = {
+	"gpio33",
+};
+static const char * const dac_calib19_groups[] = {
+	"gpio33", "gpio60",
+};
+static const char * const dac_calib20_groups[] = {
+	"gpio34", "gpio61",
+};
+static const char * const hdmi_hot_groups[] = {
+	"gpio34",
+};
+static const char * const dac_calib21_groups[] = {
+	"gpio35", "gpio62",
+};
+static const char * const pci_e0_groups[] = {
+	"gpio35", "gpio36",
+};
+static const char * const dac_calib22_groups[] = {
+	"gpio36", "gpio63",
+};
+static const char * const dac_calib23_groups[] = {
+	"gpio37", "gpio64",
+};
+static const char * const blsp_i2c2_groups[] = {
+	"gpio43", "gpio44",
+};
+static const char * const blsp_spi3_groups[] = {
+	"gpio45", "gpio46", "gpio47", "gpio48",
+};
+static const char * const blsp_uart3_groups[] = {
+	"gpio45", "gpio46", "gpio47", "gpio48",
+};
+static const char * const blsp_uim3_groups[] = {
+	"gpio45", "gpio46",
+};
+static const char * const blsp_i2c3_groups[] = {
+	"gpio47", "gpio48",
+};
+static const char * const dac_calib24_groups[] = {
+	"gpio38", "gpio65",
+};
+static const char * const dac_calib25_groups[] = {
+	"gpio39", "gpio66",
+};
+static const char * const tsif1_sync_groups[] = {
+	"gpio39",
+};
+static const char * const sd_write_groups[] = {
+	"gpio40",
+};
+static const char * const tsif1_error_groups[] = {
+	"gpio40",
+};
+static const char * const blsp_spi2_groups[] = {
+	"gpio41", "gpio42", "gpio43", "gpio44",
+};
+static const char * const blsp_uart2_groups[] = {
+	"gpio41", "gpio42", "gpio43", "gpio44",
+};
+static const char * const blsp_uim2_groups[] = {
+	"gpio41", "gpio42",
+};
+static const char * const qdss_cti_groups[] = {
+	"gpio41", "gpio42", "gpio100", "gpio101",
+};
+static const char * const uim3_groups[] = {
+	"gpio49", "gpio50", "gpio51", "gpio52",
+};
+static const char * const blsp_spi9_groups[] = {
+	"gpio49", "gpio50", "gpio51", "gpio52",
+};
+static const char * const blsp_uart9_groups[] = {
+	"gpio49", "gpio50", "gpio51", "gpio52",
+};
+static const char * const blsp_uim9_groups[] = {
+	"gpio49", "gpio50",
+};
+static const char * const blsp10_spi_groups[] = {
+	"gpio49", "gpio50", "gpio51", "gpio52", "gpio88",
+};
+static const char * const blsp_i2c9_groups[] = {
+	"gpio51", "gpio52",
+};
+static const char * const blsp_spi7_groups[] = {
+	"gpio53", "gpio54", "gpio55", "gpio56",
+};
+static const char * const blsp_uart7_groups[] = {
+	"gpio53", "gpio54", "gpio55", "gpio56",
+};
+static const char * const blsp_uim7_groups[] = {
+	"gpio53", "gpio54",
+};
+static const char * const qdss_tracedata_a_groups[] = {
+	"gpio53", "gpio54", "gpio63", "gpio64", "gpio65", "gpio66", "gpio67",
+	"gpio74", "gpio75", "gpio76", "gpio77", "gpio85", "gpio86", "gpio87",
+	"gpio89", "gpio90",
+};
+static const char * const blsp_i2c7_groups[] = {
+	"gpio55", "gpio56",
+};
+static const char * const qua_mi2s_groups[] = {
+	"gpio57", "gpio58", "gpio59", "gpio60", "gpio61", "gpio62", "gpio63",
+};
+static const char * const gcc_gp1_clk_a_groups[] = {
+	"gpio57",
+};
+static const char * const uim4_groups[] = {
+	"gpio58", "gpio59", "gpio60", "gpio61",
+};
+static const char * const blsp_spi11_groups[] = {
+	"gpio58", "gpio59", "gpio60", "gpio61",
+};
+static const char * const blsp_uart11_groups[] = {
+	"gpio58", "gpio59", "gpio60", "gpio61",
+};
+static const char * const blsp_uim11_groups[] = {
+	"gpio58", "gpio59",
+};
+static const char * const gcc_gp2_clk_a_groups[] = {
+	"gpio58",
+};
+static const char * const gcc_gp3_clk_a_groups[] = {
+	"gpio59",
+};
+static const char * const blsp_i2c11_groups[] = {
+	"gpio60", "gpio61",
+};
+static const char * const cri_trng0_groups[] = {
+	"gpio60",
+};
+static const char * const cri_trng1_groups[] = {
+	"gpio61",
+};
+static const char * const cri_trng_groups[] = {
+	"gpio62",
+};
+static const char * const qdss_stm18_groups[] = {
+	"gpio63",
+};
+static const char * const pri_mi2s_groups[] = {
+	"gpio64", "gpio65", "gpio66", "gpio67", "gpio68",
+};
+static const char * const qdss_stm17_groups[] = {
+	"gpio64",
+};
+static const char * const blsp_spi4_groups[] = {
+	"gpio65", "gpio66", "gpio67", "gpio68",
+};
+static const char * const blsp_uart4_groups[] = {
+	"gpio65", "gpio66", "gpio67", "gpio68",
+};
+static const char * const blsp_uim4_groups[] = {
+	"gpio65", "gpio66",
+};
+static const char * const qdss_stm16_groups[] = {
+	"gpio65",
+};
+static const char * const qdss_stm15_groups[] = {
+	"gpio66",
+};
+static const char * const dac_calib26_groups[] = {
+	"gpio67",
+};
+static const char * const blsp_i2c4_groups[] = {
+	"gpio67", "gpio68",
+};
+static const char * const qdss_stm14_groups[] = {
+	"gpio67",
+};
+static const char * const spkr_i2s_groups[] = {
+	"gpio69", "gpio70", "gpio71", "gpio72",
+};
+static const char * const audio_ref_groups[] = {
+	"gpio69",
+};
+static const char * const lpass_slimbus_groups[] = {
+	"gpio70", "gpio71", "gpio72",
+};
+static const char * const isense_dbg_groups[] = {
+	"gpio70",
+};
+static const char * const tsense_pwm1_groups[] = {
+	"gpio71",
+};
+static const char * const tsense_pwm2_groups[] = {
+	"gpio71",
+};
+static const char * const btfm_slimbus_groups[] = {
+	"gpio73", "gpio74",
+};
+static const char * const ter_mi2s_groups[] = {
+	"gpio74", "gpio75", "gpio76", "gpio77", "gpio78",
+};
+static const char * const qdss_stm22_groups[] = {
+	"gpio74",
+};
+static const char * const qdss_stm21_groups[] = {
+	"gpio75",
+};
+static const char * const qdss_stm20_groups[] = {
+	"gpio76",
+};
+static const char * const qdss_stm19_groups[] = {
+	"gpio77",
+};
+static const char * const ssc_irq_groups[] = {
+	"gpio78", "gpio79", "gpio80", "gpio117", "gpio118", "gpio119",
+	"gpio120", "gpio121", "gpio122", "gpio123", "gpio124", "gpio125",
+};
+static const char * const gcc_gp1_clk_b_groups[] = {
+	"gpio78",
+};
+static const char * const sec_mi2s_groups[] = {
+	"gpio79", "gpio80", "gpio81", "gpio82", "gpio83",
+};
+static const char * const blsp_spi5_groups[] = {
+	"gpio81", "gpio82", "gpio83", "gpio84",
+};
+static const char * const blsp_uart5_groups[] = {
+	"gpio81", "gpio82", "gpio83", "gpio84",
+};
+static const char * const blsp_uim5_groups[] = {
+	"gpio81", "gpio82",
+};
+static const char * const gcc_gp2_clk_b_groups[] = {
+	"gpio81",
+};
+static const char * const gcc_gp3_clk_b_groups[] = {
+	"gpio82",
+};
+static const char * const blsp_i2c5_groups[] = {
+	"gpio83", "gpio84",
+};
+static const char * const blsp_spi12_groups[] = {
+	"gpio85", "gpio86", "gpio87", "gpio88",
+};
+static const char * const blsp_uart12_groups[] = {
+	"gpio85", "gpio86", "gpio87", "gpio88",
+};
+static const char * const blsp_uim12_groups[] = {
+	"gpio85", "gpio86",
+};
+static const char * const qdss_stm25_groups[] = {
+	"gpio85",
+};
+static const char * const qdss_stm31_groups[] = {
+	"gpio86",
+};
+static const char * const blsp_i2c12_groups[] = {
+	"gpio87", "gpio88",
+};
+static const char * const qdss_stm30_groups[] = {
+	"gpio87",
+};
+static const char * const qdss_stm29_groups[] = {
+	"gpio88",
+};
+static const char * const tsif1_clk_groups[] = {
+	"gpio89",
+};
+static const char * const qdss_stm28_groups[] = {
+	"gpio89",
+};
+static const char * const tsif1_en_groups[] = {
+	"gpio90",
+};
+static const char * const tsif1_data_groups[] = {
+	"gpio91",
+};
+static const char * const sdc4_cmd_groups[] = {
+	"gpio91",
+};
+static const char * const qdss_stm27_groups[] = {
+	"gpio91",
+};
+static const char * const qdss_traceclk_b_groups[] = {
+	"gpio91",
+};
+static const char * const tsif2_error_groups[] = {
+	"gpio92",
+};
+static const char * const sdc43_groups[] = {
+	"gpio92",
+};
+static const char * const vfr_1_groups[] = {
+	"gpio92",
+};
+static const char * const qdss_stm26_groups[] = {
+	"gpio92",
+};
+static const char * const tsif2_clk_groups[] = {
+	"gpio93",
+};
+static const char * const sdc4_clk_groups[] = {
+	"gpio93",
+};
+static const char * const qdss_stm24_groups[] = {
+	"gpio93",
+};
+static const char * const tsif2_en_groups[] = {
+	"gpio94",
+};
+static const char * const sdc42_groups[] = {
+	"gpio94",
+};
+static const char * const qdss_stm23_groups[] = {
+	"gpio94",
+};
+static const char * const qdss_tracectl_b_groups[] = {
+	"gpio94",
+};
+static const char * const sd_card_groups[] = {
+	"gpio95",
+};
+static const char * const tsif2_data_groups[] = {
+	"gpio95",
+};
+static const char * const sdc41_groups[] = {
+	"gpio95",
+};
+static const char * const tsif2_sync_groups[] = {
+	"gpio96",
+};
+static const char * const sdc40_groups[] = {
+	"gpio96",
+};
+static const char * const mdp_vsync_p_b_groups[] = {
+	"gpio97",
+};
+static const char * const ldo_en_groups[] = {
+	"gpio97",
+};
+static const char * const mdp_vsync_s_b_groups[] = {
+	"gpio98",
+};
+static const char * const ldo_update_groups[] = {
+	"gpio98",
+};
+static const char * const blsp11_uart_tx_b_groups[] = {
+	"gpio100",
+};
+static const char * const blsp11_uart_rx_b_groups[] = {
+	"gpio101",
+};
+static const char * const blsp11_i2c_sda_b_groups[] = {
+	"gpio102",
+};
+static const char * const prng_rosc_groups[] = {
+	"gpio102",
+};
+static const char * const blsp11_i2c_scl_b_groups[] = {
+	"gpio103",
+};
+static const char * const uim2_groups[] = {
+	"gpio105", "gpio106", "gpio107", "gpio108",
+};
+static const char * const uim1_groups[] = {
+	"gpio109", "gpio110", "gpio111", "gpio112",
+};
+static const char * const uim_batt_groups[] = {
+	"gpio113",
+};
+static const char * const pci_e2_groups[] = {
+	"gpio114", "gpio115", "gpio116",
+};
+static const char * const pa_indicator_groups[] = {
+	"gpio116",
+};
+static const char * const adsp_ext_groups[] = {
+	"gpio118",
+};
+static const char * const ddr_bist_groups[] = {
+	"gpio121", "gpio122", "gpio123", "gpio124",
+};
+static const char * const qdss_tracedata_11_groups[] = {
+	"gpio123",
+};
+static const char * const qdss_tracedata_12_groups[] = {
+	"gpio124",
+};
+static const char * const modem_tsync_groups[] = {
+	"gpio128",
+};
+static const char * const nav_dr_groups[] = {
+	"gpio128",
+};
+static const char * const nav_pps_groups[] = {
+	"gpio128",
+};
+static const char * const pci_e1_groups[] = {
+	"gpio130", "gpio131", "gpio132",
+};
+static const char * const gsm_tx_groups[] = {
+	"gpio134", "gpio135",
+};
+static const char * const qspi_cs_groups[] = {
+	"gpio138", "gpio141",
+};
+static const char * const ssbi2_groups[] = {
+	"gpio139",
+};
+static const char * const ssbi1_groups[] = {
+	"gpio140",
+};
+static const char * const mss_lte_groups[] = {
+	"gpio144", "gpio145",
+};
+static const char * const qspi_clk_groups[] = {
+	"gpio145",
+};
+static const char * const qspi0_groups[] = {
+	"gpio146",
+};
+static const char * const qspi1_groups[] = {
+	"gpio147",
+};
+static const char * const qspi2_groups[] = {
+	"gpio148",
+};
+static const char * const qspi3_groups[] = {
+	"gpio149",
+};
+
+static const struct msm_function msm8996_functions[] = {
+	FUNCTION(adsp_ext),
+	FUNCTION(atest_bbrx0),
+	FUNCTION(atest_bbrx1),
+	FUNCTION(atest_char),
+	FUNCTION(atest_char0),
+	FUNCTION(atest_char1),
+	FUNCTION(atest_char2),
+	FUNCTION(atest_char3),
+	FUNCTION(atest_gpsadc0),
+	FUNCTION(atest_gpsadc1),
+	FUNCTION(atest_tsens),
+	FUNCTION(atest_tsens2),
+	FUNCTION(atest_usb1),
+	FUNCTION(atest_usb10),
+	FUNCTION(atest_usb11),
+	FUNCTION(atest_usb12),
+	FUNCTION(atest_usb13),
+	FUNCTION(atest_usb2),
+	FUNCTION(atest_usb20),
+	FUNCTION(atest_usb21),
+	FUNCTION(atest_usb22),
+	FUNCTION(atest_usb23),
+	FUNCTION(audio_ref),
+	FUNCTION(bimc_dte0),
+	FUNCTION(bimc_dte1),
+	FUNCTION(blsp10_spi),
+	FUNCTION(blsp11_i2c_scl_b),
+	FUNCTION(blsp11_i2c_sda_b),
+	FUNCTION(blsp11_uart_rx_b),
+	FUNCTION(blsp11_uart_tx_b),
+	FUNCTION(blsp1_spi),
+	FUNCTION(blsp2_spi),
+	FUNCTION(blsp_i2c1),
+	FUNCTION(blsp_i2c10),
+	FUNCTION(blsp_i2c11),
+	FUNCTION(blsp_i2c12),
+	FUNCTION(blsp_i2c2),
+	FUNCTION(blsp_i2c3),
+	FUNCTION(blsp_i2c4),
+	FUNCTION(blsp_i2c5),
+	FUNCTION(blsp_i2c6),
+	FUNCTION(blsp_i2c7),
+	FUNCTION(blsp_i2c8),
+	FUNCTION(blsp_i2c9),
+	FUNCTION(blsp_spi1),
+	FUNCTION(blsp_spi10),
+	FUNCTION(blsp_spi11),
+	FUNCTION(blsp_spi12),
+	FUNCTION(blsp_spi2),
+	FUNCTION(blsp_spi3),
+	FUNCTION(blsp_spi4),
+	FUNCTION(blsp_spi5),
+	FUNCTION(blsp_spi6),
+	FUNCTION(blsp_spi7),
+	FUNCTION(blsp_spi8),
+	FUNCTION(blsp_spi9),
+	FUNCTION(blsp_uart1),
+	FUNCTION(blsp_uart10),
+	FUNCTION(blsp_uart11),
+	FUNCTION(blsp_uart12),
+	FUNCTION(blsp_uart2),
+	FUNCTION(blsp_uart3),
+	FUNCTION(blsp_uart4),
+	FUNCTION(blsp_uart5),
+	FUNCTION(blsp_uart6),
+	FUNCTION(blsp_uart7),
+	FUNCTION(blsp_uart8),
+	FUNCTION(blsp_uart9),
+	FUNCTION(blsp_uim1),
+	FUNCTION(blsp_uim10),
+	FUNCTION(blsp_uim11),
+	FUNCTION(blsp_uim12),
+	FUNCTION(blsp_uim2),
+	FUNCTION(blsp_uim3),
+	FUNCTION(blsp_uim4),
+	FUNCTION(blsp_uim5),
+	FUNCTION(blsp_uim6),
+	FUNCTION(blsp_uim7),
+	FUNCTION(blsp_uim8),
+	FUNCTION(blsp_uim9),
+	FUNCTION(btfm_slimbus),
+	FUNCTION(cam_mclk),
+	FUNCTION(cci_async),
+	FUNCTION(cci_i2c),
+	FUNCTION(cci_timer0),
+	FUNCTION(cci_timer1),
+	FUNCTION(cci_timer2),
+	FUNCTION(cci_timer3),
+	FUNCTION(cci_timer4),
+	FUNCTION(cri_trng),
+	FUNCTION(cri_trng0),
+	FUNCTION(cri_trng1),
+	FUNCTION(dac_calib0),
+	FUNCTION(dac_calib1),
+	FUNCTION(dac_calib10),
+	FUNCTION(dac_calib11),
+	FUNCTION(dac_calib12),
+	FUNCTION(dac_calib13),
+	FUNCTION(dac_calib14),
+	FUNCTION(dac_calib15),
+	FUNCTION(dac_calib16),
+	FUNCTION(dac_calib17),
+	FUNCTION(dac_calib18),
+	FUNCTION(dac_calib19),
+	FUNCTION(dac_calib2),
+	FUNCTION(dac_calib20),
+	FUNCTION(dac_calib21),
+	FUNCTION(dac_calib22),
+	FUNCTION(dac_calib23),
+	FUNCTION(dac_calib24),
+	FUNCTION(dac_calib25),
+	FUNCTION(dac_calib26),
+	FUNCTION(dac_calib3),
+	FUNCTION(dac_calib4),
+	FUNCTION(dac_calib5),
+	FUNCTION(dac_calib6),
+	FUNCTION(dac_calib7),
+	FUNCTION(dac_calib8),
+	FUNCTION(dac_calib9),
+	FUNCTION(dac_gpio),
+	FUNCTION(dbg_out),
+	FUNCTION(ddr_bist),
+	FUNCTION(edp_hot),
+	FUNCTION(edp_lcd),
+	FUNCTION(gcc_gp1_clk_a),
+	FUNCTION(gcc_gp1_clk_b),
+	FUNCTION(gcc_gp2_clk_a),
+	FUNCTION(gcc_gp2_clk_b),
+	FUNCTION(gcc_gp3_clk_a),
+	FUNCTION(gcc_gp3_clk_b),
+	FUNCTION(gpio),
+	FUNCTION(gsm_tx),
+	FUNCTION(hdmi_cec),
+	FUNCTION(hdmi_ddc),
+	FUNCTION(hdmi_hot),
+	FUNCTION(hdmi_rcv),
+	FUNCTION(isense_dbg),
+	FUNCTION(ldo_en),
+	FUNCTION(ldo_update),
+	FUNCTION(lpass_slimbus),
+	FUNCTION(m_voc),
+	FUNCTION(mdp_vsync),
+	FUNCTION(mdp_vsync_p_b),
+	FUNCTION(mdp_vsync_s_b),
+	FUNCTION(modem_tsync),
+	FUNCTION(mss_lte),
+	FUNCTION(nav_dr),
+	FUNCTION(nav_pps),
+	FUNCTION(pa_indicator),
+	FUNCTION(pci_e0),
+	FUNCTION(pci_e1),
+	FUNCTION(pci_e2),
+	FUNCTION(pll_bypassnl),
+	FUNCTION(pll_reset),
+	FUNCTION(pri_mi2s),
+	FUNCTION(prng_rosc),
+	FUNCTION(pwr_crypto),
+	FUNCTION(pwr_modem),
+	FUNCTION(pwr_nav),
+	FUNCTION(qdss_cti),
+	FUNCTION(qdss_cti_trig_in_a),
+	FUNCTION(qdss_cti_trig_in_b),
+	FUNCTION(qdss_cti_trig_out_a),
+	FUNCTION(qdss_cti_trig_out_b),
+	FUNCTION(qdss_stm0),
+	FUNCTION(qdss_stm1),
+	FUNCTION(qdss_stm10),
+	FUNCTION(qdss_stm11),
+	FUNCTION(qdss_stm12),
+	FUNCTION(qdss_stm13),
+	FUNCTION(qdss_stm14),
+	FUNCTION(qdss_stm15),
+	FUNCTION(qdss_stm16),
+	FUNCTION(qdss_stm17),
+	FUNCTION(qdss_stm18),
+	FUNCTION(qdss_stm19),
+	FUNCTION(qdss_stm2),
+	FUNCTION(qdss_stm20),
+	FUNCTION(qdss_stm21),
+	FUNCTION(qdss_stm22),
+	FUNCTION(qdss_stm23),
+	FUNCTION(qdss_stm24),
+	FUNCTION(qdss_stm25),
+	FUNCTION(qdss_stm26),
+	FUNCTION(qdss_stm27),
+	FUNCTION(qdss_stm28),
+	FUNCTION(qdss_stm29),
+	FUNCTION(qdss_stm3),
+	FUNCTION(qdss_stm30),
+	FUNCTION(qdss_stm31),
+	FUNCTION(qdss_stm4),
+	FUNCTION(qdss_stm5),
+	FUNCTION(qdss_stm6),
+	FUNCTION(qdss_stm7),
+	FUNCTION(qdss_stm8),
+	FUNCTION(qdss_stm9),
+	FUNCTION(qdss_traceclk_a),
+	FUNCTION(qdss_traceclk_b),
+	FUNCTION(qdss_tracectl_a),
+	FUNCTION(qdss_tracectl_b),
+	FUNCTION(qdss_tracedata_11),
+	FUNCTION(qdss_tracedata_12),
+	FUNCTION(qdss_tracedata_a),
+	FUNCTION(qdss_tracedata_b),
+	FUNCTION(qspi0),
+	FUNCTION(qspi1),
+	FUNCTION(qspi2),
+	FUNCTION(qspi3),
+	FUNCTION(qspi_clk),
+	FUNCTION(qspi_cs),
+	FUNCTION(qua_mi2s),
+	FUNCTION(sd_card),
+	FUNCTION(sd_write),
+	FUNCTION(sdc40),
+	FUNCTION(sdc41),
+	FUNCTION(sdc42),
+	FUNCTION(sdc43),
+	FUNCTION(sdc4_clk),
+	FUNCTION(sdc4_cmd),
+	FUNCTION(sec_mi2s),
+	FUNCTION(spkr_i2s),
+	FUNCTION(ssbi1),
+	FUNCTION(ssbi2),
+	FUNCTION(ssc_irq),
+	FUNCTION(ter_mi2s),
+	FUNCTION(tsense_pwm1),
+	FUNCTION(tsense_pwm2),
+	FUNCTION(tsif1_clk),
+	FUNCTION(tsif1_data),
+	FUNCTION(tsif1_en),
+	FUNCTION(tsif1_error),
+	FUNCTION(tsif1_sync),
+	FUNCTION(tsif2_clk),
+	FUNCTION(tsif2_data),
+	FUNCTION(tsif2_en),
+	FUNCTION(tsif2_error),
+	FUNCTION(tsif2_sync),
+	FUNCTION(uim1),
+	FUNCTION(uim2),
+	FUNCTION(uim3),
+	FUNCTION(uim4),
+	FUNCTION(uim_batt),
+	FUNCTION(vfr_1),
+};
+
+static const struct msm_pingroup msm8996_groups[] = {
+	PINGROUP(0, blsp_spi1, blsp_uart1, blsp_uim1, NA, NA, NA, NA, NA, NA),
+	PINGROUP(1, blsp_spi1, blsp_uart1, blsp_uim1, NA, NA, NA, NA, NA, NA),
+	PINGROUP(2, blsp_spi1, blsp_uart1, blsp_i2c1, NA, NA, NA, NA, NA, NA),
+	PINGROUP(3, blsp_spi1, blsp_uart1, blsp_i2c1, NA, atest_tsens,
+		 bimc_dte1, NA, NA, NA),
+	PINGROUP(4, blsp_spi8, blsp_uart8, blsp_uim8, NA, qdss_cti_trig_out_b,
+		 dac_calib0, bimc_dte0, NA, NA),
+	PINGROUP(5, blsp_spi8, blsp_uart8, blsp_uim8, NA, qdss_cti_trig_in_b,
+		 dac_calib1, bimc_dte1, NA, NA),
+	PINGROUP(6, blsp_spi8, blsp_uart8, blsp_i2c8, NA, dac_calib2,
+		 bimc_dte0, NA, NA, NA),
+	PINGROUP(7, blsp_spi8, blsp_uart8, blsp_i2c8, NA, atest_tsens2,
+		 atest_usb1, NA, NA, NA),
+	PINGROUP(8, blsp_spi10, blsp_uart10, blsp_uim10, NA, atest_bbrx1,
+		 atest_usb13, NA, NA, NA),
+	PINGROUP(9, blsp_spi10, blsp_uart10, blsp_uim10, atest_bbrx0,
+		 atest_usb12, NA, NA, NA, NA),
+	PINGROUP(10, mdp_vsync, blsp_spi10, blsp_uart10, blsp_i2c10,
+		 atest_gpsadc1, atest_usb11, NA, NA, NA),
+	PINGROUP(11, mdp_vsync, blsp_spi10, blsp_uart10, blsp_i2c10,
+		 atest_gpsadc0, atest_usb10, NA, NA, NA),
+	PINGROUP(12, mdp_vsync, m_voc, dac_gpio, atest_char, NA, NA, NA, NA,
+		 NA),
+	PINGROUP(13, cam_mclk, pll_bypassnl, qdss_stm7, qdss_tracedata_b, NA,
+		 NA, NA, NA, NA),
+	PINGROUP(14, cam_mclk, pll_reset, qdss_stm6, qdss_tracedata_b, NA, NA,
+		 NA, NA, NA),
+	PINGROUP(15, cam_mclk, qdss_stm5, qdss_tracedata_b, NA, NA, NA, NA, NA,
+		 NA),
+	PINGROUP(16, cam_mclk, qdss_stm4, qdss_tracedata_b, NA, atest_usb2, NA,
+		 NA, NA, NA),
+	PINGROUP(17, cci_i2c, qdss_stm3, qdss_tracedata_b, dac_calib3,
+		 atest_usb23, atest_char3, NA, NA, NA),
+	PINGROUP(18, cci_i2c, qdss_stm2, qdss_tracedata_b, dac_calib4,
+		 atest_usb22, atest_char2, NA, NA, NA),
+	PINGROUP(19, cci_i2c, qdss_stm1, qdss_tracedata_b, dac_calib5,
+		 atest_usb21, atest_char1, NA, NA, NA),
+	PINGROUP(20, cci_i2c, dbg_out, qdss_stm0, dac_calib6, atest_usb20,
+		 atest_char0, NA, NA, NA),
+	PINGROUP(21, cci_timer0, qdss_stm13, qdss_tracedata_b, dac_calib7, NA,
+		 NA, NA, NA, NA),
+	PINGROUP(22, cci_timer1, qdss_stm12, qdss_tracedata_b, dac_calib8, NA,
+		 NA, NA, NA, NA),
+	PINGROUP(23, cci_timer2, blsp1_spi, qdss_stm11, qdss_tracedata_b,
+		 dac_calib9, NA, NA, NA, NA),
+	PINGROUP(24, cci_timer3, cci_async, blsp1_spi, qdss_stm10,
+		 qdss_cti_trig_in_a, dac_calib10, NA, NA, NA),
+	PINGROUP(25, cci_timer4, cci_async, blsp_spi6, blsp_uart6, blsp_uim6,
+		 blsp2_spi, qdss_stm9, qdss_cti_trig_out_a, dac_calib11),
+	PINGROUP(26, cci_async, blsp_spi6, blsp_uart6, blsp_uim6, qdss_stm8,
+		 qdss_tracedata_b, dac_calib12, NA, NA),
+	PINGROUP(27, blsp_spi6, blsp_uart6, blsp_i2c6, blsp1_spi,
+		 qdss_tracectl_a, dac_calib13, NA, NA, NA),
+	PINGROUP(28, blsp_spi6, blsp_uart6, blsp_i2c6, blsp1_spi,
+		 qdss_traceclk_a, dac_calib14, NA, NA, NA),
+	PINGROUP(29, blsp2_spi, NA, qdss_tracedata_b, dac_calib15, NA, NA, NA,
+		 NA, NA),
+	PINGROUP(30, hdmi_rcv, blsp2_spi, dac_calib16, NA, NA, NA, NA, NA, NA),
+	PINGROUP(31, hdmi_cec, pwr_modem, dac_calib17, NA, NA, NA, NA, NA, NA),
+	PINGROUP(32, hdmi_ddc, pwr_nav, NA, dac_calib18, NA, NA, NA, NA, NA),
+	PINGROUP(33, hdmi_ddc, pwr_crypto, NA, dac_calib19, NA, NA, NA, NA, NA),
+	PINGROUP(34, hdmi_hot, NA, dac_calib20, NA, NA, NA, NA, NA, NA),
+	PINGROUP(35, pci_e0, NA, dac_calib21, NA, NA, NA, NA, NA, NA),
+	PINGROUP(36, pci_e0, NA, dac_calib22, NA, NA, NA, NA, NA, NA),
+	PINGROUP(37, NA, dac_calib23, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(38, NA, dac_calib24, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(39, tsif1_sync, NA, dac_calib25, NA, NA, NA, NA, NA, NA),
+	PINGROUP(40, sd_write, tsif1_error, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(41, blsp_spi2, blsp_uart2, blsp_uim2, NA, qdss_cti,
+		 dac_calib0, NA, NA, NA),
+	PINGROUP(42, blsp_spi2, blsp_uart2, blsp_uim2, NA, qdss_cti,
+		 dac_calib1, NA, NA, NA),
+	PINGROUP(43, blsp_spi2, blsp_uart2, blsp_i2c2, NA, dac_calib2, NA, NA,
+		 NA, NA),
+	PINGROUP(44, blsp_spi2, blsp_uart2, blsp_i2c2, NA, dac_calib3, NA, NA,
+		 NA, NA),
+	PINGROUP(45, blsp_spi3, blsp_uart3, blsp_uim3, NA, dac_calib4, NA, NA,
+		 NA, NA),
+	PINGROUP(46, blsp_spi3, blsp_uart3, blsp_uim3, NA, dac_calib5, NA, NA,
+		 NA, NA),
+	PINGROUP(47, blsp_spi3, blsp_uart3, blsp_i2c3, dac_calib6, NA, NA, NA,
+		 NA, NA),
+	PINGROUP(48, blsp_spi3, blsp_uart3, blsp_i2c3, dac_calib7, NA, NA, NA,
+		 NA, NA),
+	PINGROUP(49, uim3, blsp_spi9, blsp_uart9, blsp_uim9, blsp10_spi,
+		 dac_calib8, NA, NA, NA),
+	PINGROUP(50, uim3, blsp_spi9, blsp_uart9, blsp_uim9, blsp10_spi,
+		 dac_calib9, NA, NA, NA),
+	PINGROUP(51, uim3, blsp_spi9, blsp_uart9, blsp_i2c9, blsp10_spi,
+		 dac_calib10, NA, NA, NA),
+	PINGROUP(52, uim3, blsp_spi9, blsp_uart9, blsp_i2c9,
+		 blsp10_spi, dac_calib11, NA, NA, NA),
+	PINGROUP(53, blsp_spi7, blsp_uart7, blsp_uim7, NA, qdss_tracedata_a,
+		 dac_calib12, NA, NA, NA),
+	PINGROUP(54, blsp_spi7, blsp_uart7, blsp_uim7, NA, NA,
+		 qdss_tracedata_a, dac_calib13, NA, NA),
+	PINGROUP(55, blsp_spi7, blsp_uart7, blsp_i2c7, NA, dac_calib14, NA, NA,
+		 NA, NA),
+	PINGROUP(56, blsp_spi7, blsp_uart7, blsp_i2c7, NA, dac_calib15, NA, NA,
+		 NA, NA),
+	PINGROUP(57, qua_mi2s, gcc_gp1_clk_a, NA, qdss_tracedata_b,
+		 dac_calib16, NA, NA, NA, NA),
+	PINGROUP(58, qua_mi2s, uim4, blsp_spi11, blsp_uart11, blsp_uim11,
+		 gcc_gp2_clk_a, NA, qdss_tracedata_b, dac_calib17),
+	PINGROUP(59, qua_mi2s, uim4, blsp_spi11, blsp_uart11, blsp_uim11,
+		 gcc_gp3_clk_a, NA, dac_calib18, NA),
+	PINGROUP(60, qua_mi2s, uim4, blsp_spi11, blsp_uart11, blsp_i2c11,
+		 cri_trng0, NA, dac_calib19, NA),
+	PINGROUP(61, qua_mi2s, uim4, blsp_spi11, blsp_uart11,
+		 blsp_i2c11, cri_trng1, NA, dac_calib20, NA),
+	PINGROUP(62, qua_mi2s, cri_trng, NA, dac_calib21, NA, NA, NA, NA, NA),
+	PINGROUP(63, qua_mi2s, NA, NA, qdss_stm18, qdss_tracedata_a,
+		 dac_calib22, NA, NA, NA),
+	PINGROUP(64, pri_mi2s, NA, qdss_stm17, qdss_tracedata_a, dac_calib23,
+		 NA, NA, NA, NA),
+	PINGROUP(65, pri_mi2s, blsp_spi4, blsp_uart4, blsp_uim4, NA,
+		 qdss_stm16, qdss_tracedata_a, dac_calib24, NA),
+	PINGROUP(66, pri_mi2s, blsp_spi4, blsp_uart4, blsp_uim4, NA,
+		 qdss_stm15, qdss_tracedata_a, dac_calib25, NA),
+	PINGROUP(67, pri_mi2s, blsp_spi4, blsp_uart4, blsp_i2c4, qdss_stm14,
+		 qdss_tracedata_a, dac_calib26, NA, NA),
+	PINGROUP(68, pri_mi2s, blsp_spi4, blsp_uart4, blsp_i2c4, NA, NA, NA,
+		 NA, NA),
+	PINGROUP(69, spkr_i2s, audio_ref, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(70, lpass_slimbus, spkr_i2s, isense_dbg, NA, NA, NA, NA, NA,
+		 NA),
+	PINGROUP(71, lpass_slimbus, spkr_i2s, tsense_pwm1, tsense_pwm2, NA, NA,
+		 NA, NA, NA),
+	PINGROUP(72, lpass_slimbus, spkr_i2s, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(73, btfm_slimbus, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(74, btfm_slimbus, ter_mi2s, qdss_stm22, qdss_tracedata_a, NA,
+		 NA, NA, NA, NA),
+	PINGROUP(75, ter_mi2s, qdss_stm21, qdss_tracedata_a, NA, NA, NA, NA,
+		 NA, NA),
+	PINGROUP(76, ter_mi2s, qdss_stm20, qdss_tracedata_a, NA, NA, NA, NA,
+		 NA, NA),
+	PINGROUP(77, ter_mi2s, qdss_stm19, qdss_tracedata_a, NA, NA, NA, NA,
+		 NA, NA),
+	PINGROUP(78, ter_mi2s, gcc_gp1_clk_b, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(79, sec_mi2s, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(80, sec_mi2s, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(81, sec_mi2s, blsp_spi5, blsp_uart5, blsp_uim5, gcc_gp2_clk_b,
+		 NA, NA, NA, NA),
+	PINGROUP(82, sec_mi2s, blsp_spi5, blsp_uart5, blsp_uim5, gcc_gp3_clk_b,
+		 NA, NA, NA, NA),
+	PINGROUP(83, sec_mi2s, blsp_spi5, blsp_uart5, blsp_i2c5, NA, NA, NA,
+		 NA, NA),
+	PINGROUP(84, blsp_spi5, blsp_uart5, blsp_i2c5, NA, NA, NA, NA, NA, NA),
+	PINGROUP(85, blsp_spi12, blsp_uart12, blsp_uim12, NA, qdss_stm25,
+		 qdss_tracedata_a, NA, NA, NA),
+	PINGROUP(86, blsp_spi12, blsp_uart12, blsp_uim12, NA, NA, qdss_stm31,
+		 qdss_tracedata_a, NA, NA),
+	PINGROUP(87, blsp_spi12, blsp_uart12, blsp_i2c12, NA, qdss_stm30,
+		 qdss_tracedata_a, NA, NA, NA),
+	PINGROUP(88, blsp_spi12, blsp_uart12, blsp_i2c12, blsp10_spi, NA,
+		 qdss_stm29, NA, NA, NA),
+	PINGROUP(89, tsif1_clk, qdss_stm28, qdss_tracedata_a, NA, NA, NA, NA,
+		 NA, NA),
+	PINGROUP(90, tsif1_en, blsp1_spi, qdss_tracedata_a, NA, NA, NA, NA, NA,
+		 NA),
+	PINGROUP(91, tsif1_data, sdc4_cmd, qdss_stm27, qdss_traceclk_b, NA, NA,
+		 NA, NA, NA),
+	PINGROUP(92, tsif2_error, sdc43, vfr_1, qdss_stm26, qdss_tracedata_b,
+		 NA, NA, NA, NA),
+	PINGROUP(93, tsif2_clk, sdc4_clk, NA, qdss_stm24, qdss_tracedata_b, NA,
+		 NA, NA, NA),
+	PINGROUP(94, tsif2_en, sdc42, NA, qdss_stm23, qdss_tracectl_b, NA, NA,
+		 NA, NA),
+	PINGROUP(95, tsif2_data, sdc41, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(96, tsif2_sync, sdc40, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(97, NA, NA, mdp_vsync_p_b, ldo_en, NA, NA, NA, NA, NA),
+	PINGROUP(98, NA, NA, mdp_vsync_s_b, ldo_update, NA, NA, NA, NA, NA),
+	PINGROUP(99, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(100, NA, NA, blsp11_uart_tx_b, qdss_cti, NA, NA, NA, NA, NA),
+	PINGROUP(101, NA, blsp11_uart_rx_b, qdss_cti, NA, NA, NA, NA, NA, NA),
+	PINGROUP(102, NA, blsp11_i2c_sda_b, prng_rosc, NA, NA, NA, NA, NA, NA),
+	PINGROUP(103, NA, blsp11_i2c_scl_b, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(104, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(105, uim2, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(106, uim2, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(107, uim2, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(108, uim2, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(109, uim1, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(110, uim1, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(111, uim1, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(112, uim1, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(113, uim_batt, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(114, NA, pci_e2, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(115, NA, pci_e2, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(116, NA, pa_indicator, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(117, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(118, adsp_ext, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(119, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(120, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(121, ddr_bist, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(122, ddr_bist, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(123, ddr_bist, qdss_tracedata_11, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(124, ddr_bist, qdss_tracedata_12, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(125, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(126, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(127, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(128, NA, modem_tsync, nav_dr, nav_pps, NA, NA, NA, NA, NA),
+	PINGROUP(129, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(130, pci_e1, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(131, pci_e1, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(132, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(133, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(134, gsm_tx, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(135, gsm_tx, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(136, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(137, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(138, NA, qspi_cs, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(139, NA, ssbi2, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(140, NA, ssbi1, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(141, NA, qspi_cs, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(142, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(143, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(144, mss_lte, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(145, mss_lte, qspi_clk, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(146, NA, qspi0, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(147, NA, qspi1, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(148, NA, qspi2, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(149, NA, qspi3, NA, NA, NA, NA, NA, NA, NA),
+	SDC_QDSD_PINGROUP(sdc1_clk, 0x12c000, 13, 6),
+	SDC_QDSD_PINGROUP(sdc1_cmd, 0x12c000, 11, 3),
+	SDC_QDSD_PINGROUP(sdc1_data, 0x12c000, 9, 0),
+	SDC_QDSD_PINGROUP(sdc2_clk, 0x12d000, 14, 6),
+	SDC_QDSD_PINGROUP(sdc2_cmd, 0x12d000, 11, 3),
+	SDC_QDSD_PINGROUP(sdc2_data, 0x12d000, 9, 0),
+	SDC_QDSD_PINGROUP(sdc1_rclk, 0x12c000, 15, 0),
+};
+
+static const struct msm_pinctrl_soc_data msm8996_pinctrl = {
+	.pins = msm8996_pins,
+	.npins = ARRAY_SIZE(msm8996_pins),
+	.functions = msm8996_functions,
+	.nfunctions = ARRAY_SIZE(msm8996_functions),
+	.groups = msm8996_groups,
+	.ngroups = ARRAY_SIZE(msm8996_groups),
+	.ngpios = 150,
+};
+
+static int msm8996_pinctrl_probe(struct platform_device *pdev)
+{
+	return msm_pinctrl_probe(pdev, &msm8996_pinctrl);
+}
+
+static const struct of_device_id msm8996_pinctrl_of_match[] = {
+	{ .compatible = "qcom,msm8996-pinctrl", },
+	{ }
+};
+
+static struct platform_driver msm8996_pinctrl_driver = {
+	.driver = {
+		.name = "msm8996-pinctrl",
+		.of_match_table = msm8996_pinctrl_of_match,
+	},
+	.probe = msm8996_pinctrl_probe,
+	.remove = msm_pinctrl_remove,
+};
+
+static int __init msm8996_pinctrl_init(void)
+{
+	return platform_driver_register(&msm8996_pinctrl_driver);
+}
+arch_initcall(msm8996_pinctrl_init);
+
+static void __exit msm8996_pinctrl_exit(void)
+{
+	platform_driver_unregister(&msm8996_pinctrl_driver);
+}
+module_exit(msm8996_pinctrl_exit);
+
+MODULE_DESCRIPTION("Qualcomm msm8996 pinctrl driver");
+MODULE_LICENSE("GPL v2");
+MODULE_DEVICE_TABLE(of, msm8996_pinctrl_of_match);
diff --git a/drivers/pinctrl/qcom/pinctrl-qdf2xxx.c b/drivers/pinctrl/qcom/pinctrl-qdf2xxx.c
index e9ff3bc..f448534 100644
--- a/drivers/pinctrl/qcom/pinctrl-qdf2xxx.c
+++ b/drivers/pinctrl/qcom/pinctrl-qdf2xxx.c
@@ -32,6 +32,9 @@
 
 static struct msm_pinctrl_soc_data qdf2xxx_pinctrl;
 
+/* A reasonable limit to the number of GPIOS */
+#define MAX_GPIOS	256
+
 static int qdf2xxx_pinctrl_probe(struct platform_device *pdev)
 {
 	struct pinctrl_pin_desc *pins;
@@ -42,11 +45,13 @@
 
 	/* Query the number of GPIOs from ACPI */
 	ret = device_property_read_u32(&pdev->dev, "num-gpios", &num_gpios);
-	if (ret < 0)
-		return ret;
-
-	if (!num_gpios) {
+	if (ret < 0) {
 		dev_warn(&pdev->dev, "missing num-gpios property\n");
+		return ret;
+	}
+
+	if (!num_gpios || num_gpios > MAX_GPIOS) {
+		dev_warn(&pdev->dev, "invalid num-gpios property\n");
 		return -ENODEV;
 	}
 
@@ -55,6 +60,9 @@
 	groups = devm_kcalloc(&pdev->dev, num_gpios,
 		sizeof(struct msm_pingroup), GFP_KERNEL);
 
+	if (!pins || !groups)
+		return -ENOMEM;
+
 	for (i = 0; i < num_gpios; i++) {
 		pins[i].number = i;
 
diff --git a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c
index 6c42ca1..77f6a5c 100644
--- a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c
+++ b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c
@@ -14,6 +14,7 @@
 #include <linux/gpio.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/of_irq.h>
 #include <linux/pinctrl/pinconf-generic.h>
 #include <linux/pinctrl/pinconf.h>
 #include <linux/pinctrl/pinmux.h>
@@ -693,18 +694,19 @@
 	struct pmic_gpio_pad *pad, *pads;
 	struct pmic_gpio_state *state;
 	int ret, npins, i;
-	u32 res[2];
+	u32 reg;
 
-	ret = of_property_read_u32_array(dev->of_node, "reg", res, 2);
+	ret = of_property_read_u32(dev->of_node, "reg", &reg);
 	if (ret < 0) {
-		dev_err(dev, "missing base address and/or range");
+		dev_err(dev, "missing base address");
 		return ret;
 	}
 
-	npins = res[1] / PMIC_GPIO_ADDRESS_RANGE;
-
+	npins = platform_irq_count(pdev);
 	if (!npins)
 		return -EINVAL;
+	if (npins < 0)
+		return npins;
 
 	BUG_ON(npins > ARRAY_SIZE(pmic_gpio_groups));
 
@@ -752,7 +754,7 @@
 		if (pad->irq < 0)
 			return pad->irq;
 
-		pad->base = res[0] + i * PMIC_GPIO_ADDRESS_RANGE;
+		pad->base = reg + i * PMIC_GPIO_ADDRESS_RANGE;
 
 		ret = pmic_gpio_populate(state, pad);
 		if (ret < 0)
@@ -804,6 +806,7 @@
 static const struct of_device_id pmic_gpio_of_match[] = {
 	{ .compatible = "qcom,pm8916-gpio" },	/* 4 GPIO's */
 	{ .compatible = "qcom,pm8941-gpio" },	/* 36 GPIO's */
+	{ .compatible = "qcom,pm8994-gpio" },	/* 22 GPIO's */
 	{ .compatible = "qcom,pma8084-gpio" },	/* 22 GPIO's */
 	{ },
 };
diff --git a/drivers/pinctrl/qcom/pinctrl-spmi-mpp.c b/drivers/pinctrl/qcom/pinctrl-spmi-mpp.c
index 9ce0e30..2df4f29 100644
--- a/drivers/pinctrl/qcom/pinctrl-spmi-mpp.c
+++ b/drivers/pinctrl/qcom/pinctrl-spmi-mpp.c
@@ -14,6 +14,7 @@
 #include <linux/gpio.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/of_irq.h>
 #include <linux/pinctrl/pinconf-generic.h>
 #include <linux/pinctrl/pinconf.h>
 #include <linux/pinctrl/pinmux.h>
@@ -795,17 +796,19 @@
 	struct pmic_mpp_pad *pad, *pads;
 	struct pmic_mpp_state *state;
 	int ret, npins, i;
-	u32 res[2];
+	u32 reg;
 
-	ret = of_property_read_u32_array(dev->of_node, "reg", res, 2);
+	ret = of_property_read_u32(dev->of_node, "reg", &reg);
 	if (ret < 0) {
-		dev_err(dev, "missing base address and/or range");
+		dev_err(dev, "missing base address");
 		return ret;
 	}
 
-	npins = res[1] / PMIC_MPP_ADDRESS_RANGE;
+	npins = platform_irq_count(pdev);
 	if (!npins)
 		return -EINVAL;
+	if (npins < 0)
+		return npins;
 
 	BUG_ON(npins > ARRAY_SIZE(pmic_mpp_groups));
 
@@ -854,7 +857,7 @@
 		if (pad->irq < 0)
 			return pad->irq;
 
-		pad->base = res[0] + i * PMIC_MPP_ADDRESS_RANGE;
+		pad->base = reg + i * PMIC_MPP_ADDRESS_RANGE;
 
 		ret = pmic_mpp_populate(state, pad);
 		if (ret < 0)
@@ -907,6 +910,7 @@
 	{ .compatible = "qcom,pm8841-mpp" },	/* 4 MPP's */
 	{ .compatible = "qcom,pm8916-mpp" },	/* 4 MPP's */
 	{ .compatible = "qcom,pm8941-mpp" },	/* 8 MPP's */
+	{ .compatible = "qcom,pm8994-mpp" },	/* 8 MPP's */
 	{ .compatible = "qcom,pma8084-mpp" },	/* 8 MPP's */
 	{ },
 };
diff --git a/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c b/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c
index 19a3c3b..e51176e 100644
--- a/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c
+++ b/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c
@@ -23,6 +23,7 @@
 #include <linux/gpio.h>
 #include <linux/interrupt.h>
 #include <linux/of_device.h>
+#include <linux/of_irq.h>
 
 #include <dt-bindings/pinctrl/qcom,pmic-gpio.h>
 
@@ -650,11 +651,12 @@
 }
 
 static const struct of_device_id pm8xxx_gpio_of_match[] = {
-	{ .compatible = "qcom,pm8018-gpio", .data = (void *)6 },
-	{ .compatible = "qcom,pm8038-gpio", .data = (void *)12 },
-	{ .compatible = "qcom,pm8058-gpio", .data = (void *)40 },
-	{ .compatible = "qcom,pm8917-gpio", .data = (void *)38 },
-	{ .compatible = "qcom,pm8921-gpio", .data = (void *)44 },
+	{ .compatible = "qcom,pm8018-gpio" },
+	{ .compatible = "qcom,pm8038-gpio" },
+	{ .compatible = "qcom,pm8058-gpio" },
+	{ .compatible = "qcom,pm8917-gpio" },
+	{ .compatible = "qcom,pm8921-gpio" },
+	{ .compatible = "qcom,ssbi-gpio" },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, pm8xxx_gpio_of_match);
@@ -665,14 +667,19 @@
 	struct pinctrl_pin_desc *pins;
 	struct pm8xxx_gpio *pctrl;
 	int ret;
-	int i;
+	int i, npins;
 
 	pctrl = devm_kzalloc(&pdev->dev, sizeof(*pctrl), GFP_KERNEL);
 	if (!pctrl)
 		return -ENOMEM;
 
 	pctrl->dev = &pdev->dev;
-	pctrl->npins = (unsigned long)of_device_get_match_data(&pdev->dev);
+	npins = platform_irq_count(pdev);
+	if (!npins)
+		return -EINVAL;
+	if (npins < 0)
+		return npins;
+	pctrl->npins = npins;
 
 	pctrl->regmap = dev_get_regmap(pdev->dev.parent, NULL);
 	if (!pctrl->regmap) {
diff --git a/drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c b/drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c
index b868ef1..e9f01de 100644
--- a/drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c
+++ b/drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c
@@ -23,6 +23,7 @@
 #include <linux/gpio.h>
 #include <linux/interrupt.h>
 #include <linux/of_device.h>
+#include <linux/of_irq.h>
 
 #include <dt-bindings/pinctrl/qcom,pmic-mpp.h>
 
@@ -741,11 +742,12 @@
 }
 
 static const struct of_device_id pm8xxx_mpp_of_match[] = {
-	{ .compatible = "qcom,pm8018-mpp", .data = (void *)6 },
-	{ .compatible = "qcom,pm8038-mpp", .data = (void *)6 },
-	{ .compatible = "qcom,pm8917-mpp", .data = (void *)10 },
-	{ .compatible = "qcom,pm8821-mpp", .data = (void *)4 },
-	{ .compatible = "qcom,pm8921-mpp", .data = (void *)12 },
+	{ .compatible = "qcom,pm8018-mpp" },
+	{ .compatible = "qcom,pm8038-mpp" },
+	{ .compatible = "qcom,pm8917-mpp" },
+	{ .compatible = "qcom,pm8821-mpp" },
+	{ .compatible = "qcom,pm8921-mpp" },
+	{ .compatible = "qcom,ssbi-mpp" },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, pm8xxx_mpp_of_match);
@@ -756,14 +758,19 @@
 	struct pinctrl_pin_desc *pins;
 	struct pm8xxx_mpp *pctrl;
 	int ret;
-	int i;
+	int i, npins;
 
 	pctrl = devm_kzalloc(&pdev->dev, sizeof(*pctrl), GFP_KERNEL);
 	if (!pctrl)
 		return -ENOMEM;
 
 	pctrl->dev = &pdev->dev;
-	pctrl->npins = (unsigned long)of_device_get_match_data(&pdev->dev);
+	npins = platform_irq_count(pdev);
+	if (!npins)
+		return -EINVAL;
+	if (npins < 0)
+		return npins;
+	pctrl->npins = npins;
 
 	pctrl->regmap = dev_get_regmap(pdev->dev.parent, NULL);
 	if (!pctrl->regmap) {
diff --git a/drivers/pinctrl/samsung/pinctrl-exynos.c b/drivers/pinctrl/samsung/pinctrl-exynos.c
index 71ccf6a..16e2293 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos.c
+++ b/drivers/pinctrl/samsung/pinctrl-exynos.c
@@ -1150,6 +1150,109 @@
 	},
 };
 
+/* pin banks of exynos5410 pin-controller 0 */
+static const struct samsung_pin_bank_data exynos5410_pin_banks0[] __initconst = {
+	EXYNOS_PIN_BANK_EINTG(8, 0x000, "gpa0", 0x00),
+	EXYNOS_PIN_BANK_EINTG(6, 0x020, "gpa1", 0x04),
+	EXYNOS_PIN_BANK_EINTG(8, 0x040, "gpa2", 0x08),
+	EXYNOS_PIN_BANK_EINTG(5, 0x060, "gpb0", 0x0c),
+	EXYNOS_PIN_BANK_EINTG(5, 0x080, "gpb1", 0x10),
+	EXYNOS_PIN_BANK_EINTG(4, 0x0A0, "gpb2", 0x14),
+	EXYNOS_PIN_BANK_EINTG(4, 0x0C0, "gpb3", 0x18),
+	EXYNOS_PIN_BANK_EINTG(7, 0x0E0, "gpc0", 0x1c),
+	EXYNOS_PIN_BANK_EINTG(4, 0x100, "gpc3", 0x20),
+	EXYNOS_PIN_BANK_EINTG(7, 0x120, "gpc1", 0x24),
+	EXYNOS_PIN_BANK_EINTG(7, 0x140, "gpc2", 0x28),
+	EXYNOS_PIN_BANK_EINTN(2, 0x160, "gpm5"),
+	EXYNOS_PIN_BANK_EINTG(8, 0x180, "gpd1", 0x2c),
+	EXYNOS_PIN_BANK_EINTG(8, 0x1A0, "gpe0", 0x30),
+	EXYNOS_PIN_BANK_EINTG(2, 0x1C0, "gpe1", 0x34),
+	EXYNOS_PIN_BANK_EINTG(6, 0x1E0, "gpf0", 0x38),
+	EXYNOS_PIN_BANK_EINTG(8, 0x200, "gpf1", 0x3c),
+	EXYNOS_PIN_BANK_EINTG(8, 0x220, "gpg0", 0x40),
+	EXYNOS_PIN_BANK_EINTG(8, 0x240, "gpg1", 0x44),
+	EXYNOS_PIN_BANK_EINTG(2, 0x260, "gpg2", 0x48),
+	EXYNOS_PIN_BANK_EINTG(4, 0x280, "gph0", 0x4c),
+	EXYNOS_PIN_BANK_EINTG(8, 0x2A0, "gph1", 0x50),
+	EXYNOS_PIN_BANK_EINTN(8, 0x2C0, "gpm7"),
+	EXYNOS_PIN_BANK_EINTN(6, 0x2E0, "gpy0"),
+	EXYNOS_PIN_BANK_EINTN(4, 0x300, "gpy1"),
+	EXYNOS_PIN_BANK_EINTN(6, 0x320, "gpy2"),
+	EXYNOS_PIN_BANK_EINTN(8, 0x340, "gpy3"),
+	EXYNOS_PIN_BANK_EINTN(8, 0x360, "gpy4"),
+	EXYNOS_PIN_BANK_EINTN(8, 0x380, "gpy5"),
+	EXYNOS_PIN_BANK_EINTN(8, 0x3A0, "gpy6"),
+	EXYNOS_PIN_BANK_EINTN(8, 0x3C0, "gpy7"),
+	EXYNOS_PIN_BANK_EINTW(8, 0xC00, "gpx0", 0x00),
+	EXYNOS_PIN_BANK_EINTW(8, 0xC20, "gpx1", 0x04),
+	EXYNOS_PIN_BANK_EINTW(8, 0xC40, "gpx2", 0x08),
+	EXYNOS_PIN_BANK_EINTW(8, 0xC60, "gpx3", 0x0c),
+};
+
+/* pin banks of exynos5410 pin-controller 1 */
+static const struct samsung_pin_bank_data exynos5410_pin_banks1[] __initconst = {
+	EXYNOS_PIN_BANK_EINTG(5, 0x000, "gpj0", 0x00),
+	EXYNOS_PIN_BANK_EINTG(8, 0x020, "gpj1", 0x04),
+	EXYNOS_PIN_BANK_EINTG(8, 0x040, "gpj2", 0x08),
+	EXYNOS_PIN_BANK_EINTG(8, 0x060, "gpj3", 0x0c),
+	EXYNOS_PIN_BANK_EINTG(2, 0x080, "gpj4", 0x10),
+	EXYNOS_PIN_BANK_EINTG(8, 0x0A0, "gpk0", 0x14),
+	EXYNOS_PIN_BANK_EINTG(8, 0x0C0, "gpk1", 0x18),
+	EXYNOS_PIN_BANK_EINTG(8, 0x0E0, "gpk2", 0x1c),
+	EXYNOS_PIN_BANK_EINTG(7, 0x100, "gpk3", 0x20),
+};
+
+/* pin banks of exynos5410 pin-controller 2 */
+static const struct samsung_pin_bank_data exynos5410_pin_banks2[] __initconst = {
+	EXYNOS_PIN_BANK_EINTG(8, 0x000, "gpv0", 0x00),
+	EXYNOS_PIN_BANK_EINTG(8, 0x020, "gpv1", 0x04),
+	EXYNOS_PIN_BANK_EINTG(8, 0x060, "gpv2", 0x08),
+	EXYNOS_PIN_BANK_EINTG(8, 0x080, "gpv3", 0x0c),
+	EXYNOS_PIN_BANK_EINTG(2, 0x0C0, "gpv4", 0x10),
+};
+
+/* pin banks of exynos5410 pin-controller 3 */
+static const struct samsung_pin_bank_data exynos5410_pin_banks3[] __initconst = {
+	EXYNOS_PIN_BANK_EINTG(7, 0x000, "gpz", 0x00),
+};
+
+/*
+ * Samsung pinctrl driver data for Exynos5410 SoC. Exynos5410 SoC includes
+ * four gpio/pin-mux/pinconfig controllers.
+ */
+const struct samsung_pin_ctrl exynos5410_pin_ctrl[] __initconst = {
+	{
+		/* pin-controller instance 0 data */
+		.pin_banks	= exynos5410_pin_banks0,
+		.nr_banks	= ARRAY_SIZE(exynos5410_pin_banks0),
+		.eint_gpio_init = exynos_eint_gpio_init,
+		.eint_wkup_init = exynos_eint_wkup_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
+	}, {
+		/* pin-controller instance 1 data */
+		.pin_banks	= exynos5410_pin_banks1,
+		.nr_banks	= ARRAY_SIZE(exynos5410_pin_banks1),
+		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
+	}, {
+		/* pin-controller instance 2 data */
+		.pin_banks	= exynos5410_pin_banks2,
+		.nr_banks	= ARRAY_SIZE(exynos5410_pin_banks2),
+		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
+	}, {
+		/* pin-controller instance 3 data */
+		.pin_banks	= exynos5410_pin_banks3,
+		.nr_banks	= ARRAY_SIZE(exynos5410_pin_banks3),
+		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
+	},
+};
+
 /* pin banks of exynos5420 pin-controller 0 */
 static const struct samsung_pin_bank_data exynos5420_pin_banks0[] __initconst = {
 	EXYNOS_PIN_BANK_EINTG(8, 0x000, "gpy7", 0x00),
diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.c b/drivers/pinctrl/samsung/pinctrl-samsung.c
index 3f622cc..48294e7 100644
--- a/drivers/pinctrl/samsung/pinctrl-samsung.c
+++ b/drivers/pinctrl/samsung/pinctrl-samsung.c
@@ -1222,6 +1222,8 @@
 		.data = (void *)exynos5250_pin_ctrl },
 	{ .compatible = "samsung,exynos5260-pinctrl",
 		.data = (void *)exynos5260_pin_ctrl },
+	{ .compatible = "samsung,exynos5410-pinctrl",
+		.data = (void *)exynos5410_pin_ctrl },
 	{ .compatible = "samsung,exynos5420-pinctrl",
 		.data = (void *)exynos5420_pin_ctrl },
 	{ .compatible = "samsung,exynos5433-pinctrl",
diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.h b/drivers/pinctrl/samsung/pinctrl-samsung.h
index c1239ff..cd31bfa 100644
--- a/drivers/pinctrl/samsung/pinctrl-samsung.h
+++ b/drivers/pinctrl/samsung/pinctrl-samsung.h
@@ -270,6 +270,7 @@
 extern const struct samsung_pin_ctrl exynos4415_pin_ctrl[];
 extern const struct samsung_pin_ctrl exynos5250_pin_ctrl[];
 extern const struct samsung_pin_ctrl exynos5260_pin_ctrl[];
+extern const struct samsung_pin_ctrl exynos5410_pin_ctrl[];
 extern const struct samsung_pin_ctrl exynos5420_pin_ctrl[];
 extern const struct samsung_pin_ctrl exynos5433_pin_ctrl[];
 extern const struct samsung_pin_ctrl exynos7_pin_ctrl[];
diff --git a/drivers/pinctrl/sh-pfc/pfc-emev2.c b/drivers/pinctrl/sh-pfc/pfc-emev2.c
index 02118ab..1cbbe04 100644
--- a/drivers/pinctrl/sh-pfc/pfc-emev2.c
+++ b/drivers/pinctrl/sh-pfc/pfc-emev2.c
@@ -258,18 +258,18 @@
 
 	/* GPSR0 */
 	/* V9 */
-	PINMUX_DATA(JT_SEL_MARK, FN_JT_SEL),
+	PINMUX_SINGLE(JT_SEL),
 	/* U9 */
-	PINMUX_DATA(ERR_RST_REQB_MARK, FN_ERR_RST_REQB),
+	PINMUX_SINGLE(ERR_RST_REQB),
 	/* V8 */
-	PINMUX_DATA(REF_CLKO_MARK, FN_REF_CLKO),
+	PINMUX_SINGLE(REF_CLKO),
 	/* U8 */
-	PINMUX_DATA(EXT_CLKI_MARK, FN_EXT_CLKI),
+	PINMUX_SINGLE(EXT_CLKI),
 	/* B22*/
 	PINMUX_IPSR_NOFN(LCD3_1_0_PORT18, LCD3_PXCLK, SEL_LCD3_1_0_00),
 	PINMUX_IPSR_NOFN(LCD3_1_0_PORT18, YUV3_CLK_O, SEL_LCD3_1_0_01),
 	/* C21 */
-	PINMUX_DATA(LCD3_PXCLKB_MARK, FN_LCD3_PXCLKB),
+	PINMUX_SINGLE(LCD3_PXCLKB),
 	/* A21 */
 	PINMUX_IPSR_NOFN(LCD3_1_0_PORT20, LCD3_CLK_I, SEL_LCD3_1_0_00),
 	PINMUX_IPSR_NOFN(LCD3_1_0_PORT20, YUV3_CLK_I, SEL_LCD3_1_0_01),
@@ -285,17 +285,17 @@
 
 	/* GPSR1 */
 	/* A20 */
-	PINMUX_DATA(LCD3_R0_MARK, FN_LCD3_R0),
+	PINMUX_SINGLE(LCD3_R0),
 	/* B20 */
-	PINMUX_DATA(LCD3_R1_MARK, FN_LCD3_R1),
+	PINMUX_SINGLE(LCD3_R1),
 	/* A19 */
-	PINMUX_DATA(LCD3_R2_MARK, FN_LCD3_R2),
+	PINMUX_SINGLE(LCD3_R2),
 	/* B19 */
-	PINMUX_DATA(LCD3_R3_MARK, FN_LCD3_R3),
+	PINMUX_SINGLE(LCD3_R3),
 	/* C19 */
-	PINMUX_DATA(LCD3_R4_MARK, FN_LCD3_R4),
+	PINMUX_SINGLE(LCD3_R4),
 	/* B18 */
-	PINMUX_DATA(LCD3_R5_MARK, FN_LCD3_R5),
+	PINMUX_SINGLE(LCD3_R5),
 	/* C18 */
 	PINMUX_IPSR_NOFN(LCD3_9_8_PORT38, LCD3_R6, SEL_LCD3_9_8_00),
 	PINMUX_IPSR_NOFN(LCD3_9_8_PORT38, TP33_CLK, SEL_LCD3_9_8_10),
@@ -367,9 +367,9 @@
 	PINMUX_IPSR_NOFN(LCD3_11_10_PORT43, YUV3_D15, SEL_LCD3_11_10_01),
 	PINMUX_IPSR_NOFN(LCD3_11_10_PORT43, TP33_DATA15, SEL_LCD3_11_10_10),
 	/* AA9 */
-	PINMUX_DATA(IIC0_SCL_MARK, FN_IIC0_SCL),
+	PINMUX_SINGLE(IIC0_SCL),
 	/* AA8 */
-	PINMUX_DATA(IIC0_SDA_MARK, FN_IIC0_SDA),
+	PINMUX_SINGLE(IIC0_SDA),
 	/* Y9 */
 	PINMUX_IPSR_NOFN(IIC_1_0_PORT46, IIC1_SCL, SEL_IIC_1_0_00),
 	PINMUX_IPSR_NOFN(IIC_1_0_PORT46, UART3_RX, SEL_IIC_1_0_01),
@@ -377,51 +377,51 @@
 	PINMUX_IPSR_NOFN(IIC_1_0_PORT47, IIC1_SDA, SEL_IIC_1_0_00),
 	PINMUX_IPSR_NOFN(IIC_1_0_PORT47, UART3_TX, SEL_IIC_1_0_01),
 	/* AC19 */
-	PINMUX_DATA(SD_CKI_MARK, FN_SD_CKI),
+	PINMUX_SINGLE(SD_CKI),
 	/* AB18 */
-	PINMUX_DATA(SDI0_CKO_MARK, FN_SDI0_CKO),
+	PINMUX_SINGLE(SDI0_CKO),
 	/* AC18 */
-	PINMUX_DATA(SDI0_CKI_MARK, FN_SDI0_CKI),
+	PINMUX_SINGLE(SDI0_CKI),
 	/* Y12 */
-	PINMUX_DATA(SDI0_CMD_MARK, FN_SDI0_CMD),
+	PINMUX_SINGLE(SDI0_CMD),
 	/* AA13 */
-	PINMUX_DATA(SDI0_DATA0_MARK, FN_SDI0_DATA0),
+	PINMUX_SINGLE(SDI0_DATA0),
 	/* Y13 */
-	PINMUX_DATA(SDI0_DATA1_MARK, FN_SDI0_DATA1),
+	PINMUX_SINGLE(SDI0_DATA1),
 	/* AA14 */
-	PINMUX_DATA(SDI0_DATA2_MARK, FN_SDI0_DATA2),
+	PINMUX_SINGLE(SDI0_DATA2),
 	/* Y14 */
-	PINMUX_DATA(SDI0_DATA3_MARK, FN_SDI0_DATA3),
+	PINMUX_SINGLE(SDI0_DATA3),
 	/* AA15 */
-	PINMUX_DATA(SDI0_DATA4_MARK, FN_SDI0_DATA4),
+	PINMUX_SINGLE(SDI0_DATA4),
 	/* Y15 */
-	PINMUX_DATA(SDI0_DATA5_MARK, FN_SDI0_DATA5),
+	PINMUX_SINGLE(SDI0_DATA5),
 	/* AA16 */
-	PINMUX_DATA(SDI0_DATA6_MARK, FN_SDI0_DATA6),
+	PINMUX_SINGLE(SDI0_DATA6),
 	/* Y16 */
-	PINMUX_DATA(SDI0_DATA7_MARK, FN_SDI0_DATA7),
+	PINMUX_SINGLE(SDI0_DATA7),
 	/* AB22 */
-	PINMUX_DATA(SDI1_CKO_MARK, FN_SDI1_CKO),
+	PINMUX_SINGLE(SDI1_CKO),
 	/* AA23 */
-	PINMUX_DATA(SDI1_CKI_MARK, FN_SDI1_CKI),
+	PINMUX_SINGLE(SDI1_CKI),
 	/* AC21 */
-	PINMUX_DATA(SDI1_CMD_MARK, FN_SDI1_CMD),
+	PINMUX_SINGLE(SDI1_CMD),
 
 	/* GPSR2 */
 	/* AB21 */
-	PINMUX_DATA(SDI1_DATA0_MARK, FN_SDI1_DATA0),
+	PINMUX_SINGLE(SDI1_DATA0),
 	/* AB20 */
-	PINMUX_DATA(SDI1_DATA1_MARK, FN_SDI1_DATA1),
+	PINMUX_SINGLE(SDI1_DATA1),
 	/* AB19 */
-	PINMUX_DATA(SDI1_DATA2_MARK, FN_SDI1_DATA2),
+	PINMUX_SINGLE(SDI1_DATA2),
 	/* AA19 */
-	PINMUX_DATA(SDI1_DATA3_MARK, FN_SDI1_DATA3),
+	PINMUX_SINGLE(SDI1_DATA3),
 	/* J23 */
-	PINMUX_DATA(AB_CLK_MARK, FN_AB_CLK),
+	PINMUX_SINGLE(AB_CLK),
 	/* D21 */
-	PINMUX_DATA(AB_CSB0_MARK, FN_AB_CSB0),
+	PINMUX_SINGLE(AB_CSB0),
 	/* E21 */
-	PINMUX_DATA(AB_CSB1_MARK, FN_AB_CSB1),
+	PINMUX_SINGLE(AB_CSB1),
 	/* F20 */
 	PINMUX_IPSR_NOFN(AB_1_0_PORT71, AB_CSB2, SEL_AB_1_0_00),
 	PINMUX_IPSR_NOFN(AB_1_0_PORT71, CF_CSB0, SEL_AB_1_0_10),
@@ -514,7 +514,7 @@
 
 	/* GPSR3 */
 	/* M21 */
-	PINMUX_DATA(AB_A20_MARK, FN_AB_A20),
+	PINMUX_SINGLE(AB_A20),
 	/* N21 */
 	PINMUX_IPSR_NOFN(AB_9_8_PORT97, AB_A21, SEL_AB_9_8_00),
 	PINMUX_IPSR_NOFN(AB_9_8_PORT97, SDI2_CKO, SEL_AB_9_8_01),
@@ -541,13 +541,13 @@
 	PINMUX_IPSR_NOFN(AB_13_12_PORT104, AB_A28, SEL_AB_13_12_00),
 	PINMUX_IPSR_NOFN(AB_13_12_PORT104, AB_BEN1, SEL_AB_13_12_10),
 	/* B8 */
-	PINMUX_DATA(USI0_CS1_MARK, FN_USI0_CS1),
+	PINMUX_SINGLE(USI0_CS1),
 	/* B9 */
-	PINMUX_DATA(USI0_CS2_MARK, FN_USI0_CS2),
+	PINMUX_SINGLE(USI0_CS2),
 	/* C10 */
-	PINMUX_DATA(USI1_DI_MARK, FN_USI1_DI),
+	PINMUX_SINGLE(USI1_DI),
 	/* D10 */
-	PINMUX_DATA(USI1_DO_MARK, FN_USI1_DO),
+	PINMUX_SINGLE(USI1_DO),
 	/* AB5 */
 	PINMUX_IPSR_NOFN(USI_1_0_PORT109, USI2_CLK, SEL_USI_1_0_00),
 	PINMUX_IPSR_NOFN(USI_1_0_PORT109, DTV_BCLK_B, SEL_USI_1_0_01),
@@ -587,49 +587,49 @@
 	PINMUX_IPSR_NOFN(USI_9_8_PORT121, PWM1, SEL_USI_9_8_00),
 	PINMUX_IPSR_NOFN(USI_9_8_PORT121, USI4_DO, SEL_USI_9_8_01),
 	/* V20 */
-	PINMUX_DATA(NTSC_CLK_MARK, FN_NTSC_CLK),
+	PINMUX_SINGLE(NTSC_CLK),
 	/* P20 */
-	PINMUX_DATA(NTSC_DATA0_MARK, FN_NTSC_DATA0),
+	PINMUX_SINGLE(NTSC_DATA0),
 	/* P18 */
-	PINMUX_DATA(NTSC_DATA1_MARK, FN_NTSC_DATA1),
+	PINMUX_SINGLE(NTSC_DATA1),
 	/* R20 */
-	PINMUX_DATA(NTSC_DATA2_MARK, FN_NTSC_DATA2),
+	PINMUX_SINGLE(NTSC_DATA2),
 	/* R18 */
-	PINMUX_DATA(NTSC_DATA3_MARK, FN_NTSC_DATA3),
+	PINMUX_SINGLE(NTSC_DATA3),
 	/* T20 */
-	PINMUX_DATA(NTSC_DATA4_MARK, FN_NTSC_DATA4),
+	PINMUX_SINGLE(NTSC_DATA4),
 
 	/* GPRS3 */
 	/* T18 */
-	PINMUX_DATA(NTSC_DATA5_MARK, FN_NTSC_DATA5),
+	PINMUX_SINGLE(NTSC_DATA5),
 	/* U20 */
-	PINMUX_DATA(NTSC_DATA6_MARK, FN_NTSC_DATA6),
+	PINMUX_SINGLE(NTSC_DATA6),
 	/* U18 */
-	PINMUX_DATA(NTSC_DATA7_MARK, FN_NTSC_DATA7),
+	PINMUX_SINGLE(NTSC_DATA7),
 	/* W23 */
-	PINMUX_DATA(CAM_CLKO_MARK, FN_CAM_CLKO),
+	PINMUX_SINGLE(CAM_CLKO),
 	/* Y23 */
-	PINMUX_DATA(CAM_CLKI_MARK, FN_CAM_CLKI),
+	PINMUX_SINGLE(CAM_CLKI),
 	/* W22 */
-	PINMUX_DATA(CAM_VS_MARK, FN_CAM_VS),
+	PINMUX_SINGLE(CAM_VS),
 	/* V21 */
-	PINMUX_DATA(CAM_HS_MARK, FN_CAM_HS),
+	PINMUX_SINGLE(CAM_HS),
 	/* T21 */
-	PINMUX_DATA(CAM_YUV0_MARK, FN_CAM_YUV0),
+	PINMUX_SINGLE(CAM_YUV0),
 	/* T22 */
-	PINMUX_DATA(CAM_YUV1_MARK, FN_CAM_YUV1),
+	PINMUX_SINGLE(CAM_YUV1),
 	/* T23 */
-	PINMUX_DATA(CAM_YUV2_MARK, FN_CAM_YUV2),
+	PINMUX_SINGLE(CAM_YUV2),
 	/* U21 */
-	PINMUX_DATA(CAM_YUV3_MARK, FN_CAM_YUV3),
+	PINMUX_SINGLE(CAM_YUV3),
 	/* U22 */
-	PINMUX_DATA(CAM_YUV4_MARK, FN_CAM_YUV4),
+	PINMUX_SINGLE(CAM_YUV4),
 	/* U23 */
-	PINMUX_DATA(CAM_YUV5_MARK, FN_CAM_YUV5),
+	PINMUX_SINGLE(CAM_YUV5),
 	/* V22 */
-	PINMUX_DATA(CAM_YUV6_MARK, FN_CAM_YUV6),
+	PINMUX_SINGLE(CAM_YUV6),
 	/* V23 */
-	PINMUX_DATA(CAM_YUV7_MARK, FN_CAM_YUV7),
+	PINMUX_SINGLE(CAM_YUV7),
 	/* K22 */
 	PINMUX_IPSR_NOFN(HSI_1_0_PORT143, USI5_CLK_B, SEL_HSI_1_0_01),
 	/* K23 */
@@ -647,17 +647,17 @@
 	/* M22 */
 	PINMUX_IPSR_NOFN(HSI_1_0_PORT150, USI5_DI_B, SEL_HSI_1_0_01),
 	/* D13 */
-	PINMUX_DATA(JT_TDO_MARK, FN_JT_TDO),
+	PINMUX_SINGLE(JT_TDO),
 	/* F13 */
-	PINMUX_DATA(JT_TDOEN_MARK, FN_JT_TDOEN),
+	PINMUX_SINGLE(JT_TDOEN),
 	/* AA12 */
-	PINMUX_DATA(USB_VBUS_MARK, FN_USB_VBUS),
+	PINMUX_SINGLE(USB_VBUS),
 	/* A12 */
-	PINMUX_DATA(LOWPWR_MARK, FN_LOWPWR),
+	PINMUX_SINGLE(LOWPWR),
 	/* Y11 */
-	PINMUX_DATA(UART1_RX_MARK, FN_UART1_RX),
+	PINMUX_SINGLE(UART1_RX),
 	/* Y10 */
-	PINMUX_DATA(UART1_TX_MARK, FN_UART1_TX),
+	PINMUX_SINGLE(UART1_TX),
 	/* AA10 */
 	PINMUX_IPSR_NOFN(UART_1_0_PORT157, UART1_CTSB, SEL_UART_1_0_00),
 	PINMUX_IPSR_NOFN(UART_1_0_PORT157, UART2_RX, SEL_UART_1_0_01),
@@ -749,7 +749,7 @@
 };
 
 static const unsigned int cf_data8_pins[] = {
-	/* CF_D[0:8] */
+	/* CF_D[0:7] */
 	77, 78, 79, 80,
 	81, 82, 83, 84,
 };
diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a7740.c b/drivers/pinctrl/sh-pfc/pfc-r8a7740.c
index 279e9dd..7f7c8a6e 100644
--- a/drivers/pinctrl/sh-pfc/pfc-r8a7740.c
+++ b/drivers/pinctrl/sh-pfc/pfc-r8a7740.c
@@ -2214,7 +2214,7 @@
 	LCD1_D8_MARK,
 };
 static const unsigned int lcd1_data12_pins[] = {
-	/* D[0:12] */
+	/* D[0:11] */
 	4, 3, 2, 1, 0, 91, 92, 23,
 	93, 94, 21, 201,
 };
diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a7778.c b/drivers/pinctrl/sh-pfc/pfc-r8a7778.c
index bbd35dc..ad09a67 100644
--- a/drivers/pinctrl/sh-pfc/pfc-r8a7778.c
+++ b/drivers/pinctrl/sh-pfc/pfc-r8a7778.c
@@ -548,17 +548,17 @@
 static const u16 pinmux_data[] = {
 	PINMUX_DATA_GP_ALL(), /* PINMUX_DATA(GP_M_N_DATA, GP_M_N_FN...), */
 
-	PINMUX_DATA(PENC0_MARK,		FN_PENC0),
-	PINMUX_DATA(PENC1_MARK,		FN_PENC1),
-	PINMUX_DATA(A1_MARK,		FN_A1),
-	PINMUX_DATA(A2_MARK,		FN_A2),
-	PINMUX_DATA(A3_MARK,		FN_A3),
-	PINMUX_DATA(WE0_MARK,		FN_WE0),
-	PINMUX_DATA(AUDIO_CLKA_MARK,	FN_AUDIO_CLKA),
-	PINMUX_DATA(AUDIO_CLKB_MARK,	FN_AUDIO_CLKB),
-	PINMUX_DATA(SSI_SCK34_MARK,	FN_SSI_SCK34),
-	PINMUX_DATA(AVS1_MARK,		FN_AVS1),
-	PINMUX_DATA(AVS2_MARK,		FN_AVS2),
+	PINMUX_SINGLE(PENC0),
+	PINMUX_SINGLE(PENC1),
+	PINMUX_SINGLE(A1),
+	PINMUX_SINGLE(A2),
+	PINMUX_SINGLE(A3),
+	PINMUX_SINGLE(WE0),
+	PINMUX_SINGLE(AUDIO_CLKA),
+	PINMUX_SINGLE(AUDIO_CLKB),
+	PINMUX_SINGLE(SSI_SCK34),
+	PINMUX_SINGLE(AVS1),
+	PINMUX_SINGLE(AVS2),
 
 	/* IPSR0 */
 	PINMUX_IPSR_DATA(IP0_1_0,	PRESETOUT),
diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a7779.c b/drivers/pinctrl/sh-pfc/pfc-r8a7779.c
index ed4e078..bd17ecc 100644
--- a/drivers/pinctrl/sh-pfc/pfc-r8a7779.c
+++ b/drivers/pinctrl/sh-pfc/pfc-r8a7779.c
@@ -23,13 +23,6 @@
 
 #include "sh_pfc.h"
 
-#define PORT_GP_9(bank, fn, sfx)					\
-	PORT_GP_1(bank, 0, fn, sfx), PORT_GP_1(bank, 1, fn, sfx),	\
-	PORT_GP_1(bank, 2, fn, sfx), PORT_GP_1(bank, 3, fn, sfx),	\
-	PORT_GP_1(bank, 4, fn, sfx), PORT_GP_1(bank, 5, fn, sfx),	\
-	PORT_GP_1(bank, 6, fn, sfx), PORT_GP_1(bank, 7, fn, sfx),	\
-	PORT_GP_1(bank, 8, fn, sfx)
-
 #define CPU_ALL_PORT(fn, sfx)						\
 	PORT_GP_32(0, fn, sfx),						\
 	PORT_GP_32(1, fn, sfx),						\
@@ -609,14 +602,14 @@
 static const u16 pinmux_data[] = {
 	PINMUX_DATA_GP_ALL(), /* PINMUX_DATA(GP_M_N_DATA, GP_M_N_FN...), */
 
-	PINMUX_DATA(AVS1_MARK, FN_AVS1),
-	PINMUX_DATA(AVS1_MARK, FN_AVS1),
-	PINMUX_DATA(A17_MARK, FN_A17),
-	PINMUX_DATA(A18_MARK, FN_A18),
-	PINMUX_DATA(A19_MARK, FN_A19),
+	PINMUX_SINGLE(AVS1),
+	PINMUX_SINGLE(AVS1),
+	PINMUX_SINGLE(A17),
+	PINMUX_SINGLE(A18),
+	PINMUX_SINGLE(A19),
 
-	PINMUX_DATA(USB_PENC0_MARK, FN_USB_PENC0),
-	PINMUX_DATA(USB_PENC1_MARK, FN_USB_PENC1),
+	PINMUX_SINGLE(USB_PENC0),
+	PINMUX_SINGLE(USB_PENC1),
 
 	PINMUX_IPSR_DATA(IP0_2_0, USB_PENC2),
 	PINMUX_IPSR_MSEL(IP0_2_0, SCK0, SEL_SCIF0_0),
@@ -2289,6 +2282,35 @@
 static const unsigned int scif5_clk_d_mux[] = {
 	SCK5_D_MARK,
 };
+/* - SCIF Clock ------------------------------------------------------------- */
+static const unsigned int scif_clk_pins[] = {
+	/* SCIF_CLK */
+	RCAR_GP_PIN(4, 28),
+};
+static const unsigned int scif_clk_mux[] = {
+	SCIF_CLK_MARK,
+};
+static const unsigned int scif_clk_b_pins[] = {
+	/* SCIF_CLK */
+	RCAR_GP_PIN(4, 5),
+};
+static const unsigned int scif_clk_b_mux[] = {
+	SCIF_CLK_B_MARK,
+};
+static const unsigned int scif_clk_c_pins[] = {
+	/* SCIF_CLK */
+	RCAR_GP_PIN(4, 18),
+};
+static const unsigned int scif_clk_c_mux[] = {
+	SCIF_CLK_C_MARK,
+};
+static const unsigned int scif_clk_d_pins[] = {
+	/* SCIF_CLK */
+	RCAR_GP_PIN(2, 29),
+};
+static const unsigned int scif_clk_d_mux[] = {
+	SCIF_CLK_D_MARK,
+};
 /* - SDHI0 ------------------------------------------------------------------ */
 static const unsigned int sdhi0_data1_pins[] = {
 	/* D0 */
@@ -2700,6 +2722,10 @@
 	SH_PFC_PIN_GROUP(scif5_clk_c),
 	SH_PFC_PIN_GROUP(scif5_data_d),
 	SH_PFC_PIN_GROUP(scif5_clk_d),
+	SH_PFC_PIN_GROUP(scif_clk),
+	SH_PFC_PIN_GROUP(scif_clk_b),
+	SH_PFC_PIN_GROUP(scif_clk_c),
+	SH_PFC_PIN_GROUP(scif_clk_d),
 	SH_PFC_PIN_GROUP(sdhi0_data1),
 	SH_PFC_PIN_GROUP(sdhi0_data4),
 	SH_PFC_PIN_GROUP(sdhi0_ctrl),
@@ -2909,6 +2935,13 @@
 	"scif5_clk_d",
 };
 
+static const char * const scif_clk_groups[] = {
+	"scif_clk",
+	"scif_clk_b",
+	"scif_clk_c",
+	"scif_clk_d",
+};
+
 static const char * const sdhi0_groups[] = {
 	"sdhi0_data1",
 	"sdhi0_data4",
@@ -3004,6 +3037,7 @@
 	SH_PFC_FUNCTION(scif3),
 	SH_PFC_FUNCTION(scif4),
 	SH_PFC_FUNCTION(scif5),
+	SH_PFC_FUNCTION(scif_clk),
 	SH_PFC_FUNCTION(usb0),
 	SH_PFC_FUNCTION(usb1),
 	SH_PFC_FUNCTION(usb2),
diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a7790.c b/drivers/pinctrl/sh-pfc/pfc-r8a7790.c
index d9924b0..a8b629b 100644
--- a/drivers/pinctrl/sh-pfc/pfc-r8a7790.c
+++ b/drivers/pinctrl/sh-pfc/pfc-r8a7790.c
@@ -26,23 +26,6 @@
 #include "core.h"
 #include "sh_pfc.h"
 
-#define PORT_GP_30(bank, fn, sfx)					\
-	PORT_GP_1(bank, 0,  fn, sfx), PORT_GP_1(bank, 1,  fn, sfx),	\
-	PORT_GP_1(bank, 2,  fn, sfx), PORT_GP_1(bank, 3,  fn, sfx),	\
-	PORT_GP_1(bank, 4,  fn, sfx), PORT_GP_1(bank, 5,  fn, sfx),	\
-	PORT_GP_1(bank, 6,  fn, sfx), PORT_GP_1(bank, 7,  fn, sfx),	\
-	PORT_GP_1(bank, 8,  fn, sfx), PORT_GP_1(bank, 9,  fn, sfx),	\
-	PORT_GP_1(bank, 10, fn, sfx), PORT_GP_1(bank, 11, fn, sfx),	\
-	PORT_GP_1(bank, 12, fn, sfx), PORT_GP_1(bank, 13, fn, sfx),	\
-	PORT_GP_1(bank, 14, fn, sfx), PORT_GP_1(bank, 15, fn, sfx),	\
-	PORT_GP_1(bank, 16, fn, sfx), PORT_GP_1(bank, 17, fn, sfx),	\
-	PORT_GP_1(bank, 18, fn, sfx), PORT_GP_1(bank, 19, fn, sfx),	\
-	PORT_GP_1(bank, 20, fn, sfx), PORT_GP_1(bank, 21, fn, sfx),	\
-	PORT_GP_1(bank, 22, fn, sfx), PORT_GP_1(bank, 23, fn, sfx),	\
-	PORT_GP_1(bank, 24, fn, sfx), PORT_GP_1(bank, 25, fn, sfx),	\
-	PORT_GP_1(bank, 26, fn, sfx), PORT_GP_1(bank, 27, fn, sfx),	\
-	PORT_GP_1(bank, 28, fn, sfx), PORT_GP_1(bank, 29, fn, sfx)
-
 #define CPU_ALL_PORT(fn, sfx)						\
 	PORT_GP_32(0, fn, sfx),						\
 	PORT_GP_30(1, fn, sfx),						\
@@ -806,15 +789,15 @@
 static const u16 pinmux_data[] = {
 	PINMUX_DATA_GP_ALL(), /* PINMUX_DATA(GP_M_N_DATA, GP_M_N_FN...), */
 
-	PINMUX_DATA(VI1_DATA7_VI1_B7_MARK, FN_VI1_DATA7_VI1_B7),
-	PINMUX_DATA(USB0_PWEN_MARK, FN_USB0_PWEN),
-	PINMUX_DATA(USB0_OVC_VBUS_MARK, FN_USB0_OVC_VBUS),
-	PINMUX_DATA(USB2_PWEN_MARK, FN_USB2_PWEN),
-	PINMUX_DATA(USB2_OVC_MARK, FN_USB2_OVC),
-	PINMUX_DATA(AVS1_MARK, FN_AVS1),
-	PINMUX_DATA(AVS2_MARK, FN_AVS2),
-	PINMUX_DATA(DU_DOTCLKIN0_MARK, FN_DU_DOTCLKIN0),
-	PINMUX_DATA(DU_DOTCLKIN2_MARK, FN_DU_DOTCLKIN2),
+	PINMUX_SINGLE(VI1_DATA7_VI1_B7),
+	PINMUX_SINGLE(USB0_PWEN),
+	PINMUX_SINGLE(USB0_OVC_VBUS),
+	PINMUX_SINGLE(USB2_PWEN),
+	PINMUX_SINGLE(USB2_OVC),
+	PINMUX_SINGLE(AVS1),
+	PINMUX_SINGLE(AVS2),
+	PINMUX_SINGLE(DU_DOTCLKIN0),
+	PINMUX_SINGLE(DU_DOTCLKIN2),
 
 	PINMUX_IPSR_DATA(IP0_2_0, D0),
 	PINMUX_IPSR_MSEL(IP0_2_0, MSIOF3_SCK_B, SEL_SOF3_1),
@@ -3236,6 +3219,21 @@
 static const unsigned int scifb2_data_c_mux[] = {
 	SCIFB2_RXD_C_MARK, SCIFB2_TXD_C_MARK,
 };
+/* - SCIF Clock ------------------------------------------------------------- */
+static const unsigned int scif_clk_pins[] = {
+	/* SCIF_CLK */
+	RCAR_GP_PIN(4, 26),
+};
+static const unsigned int scif_clk_mux[] = {
+	SCIF_CLK_MARK,
+};
+static const unsigned int scif_clk_b_pins[] = {
+	/* SCIF_CLK */
+	RCAR_GP_PIN(5, 4),
+};
+static const unsigned int scif_clk_b_mux[] = {
+	SCIF_CLK_B_MARK,
+};
 /* - SDHI0 ------------------------------------------------------------------ */
 static const unsigned int sdhi0_data1_pins[] = {
 	/* D0 */
@@ -4139,6 +4137,8 @@
 	SH_PFC_PIN_GROUP(scifb2_clk_b),
 	SH_PFC_PIN_GROUP(scifb2_ctrl_b),
 	SH_PFC_PIN_GROUP(scifb2_data_c),
+	SH_PFC_PIN_GROUP(scif_clk),
+	SH_PFC_PIN_GROUP(scif_clk_b),
 	SH_PFC_PIN_GROUP(sdhi0_data1),
 	SH_PFC_PIN_GROUP(sdhi0_data4),
 	SH_PFC_PIN_GROUP(sdhi0_ctrl),
@@ -4555,6 +4555,11 @@
 	"scifb2_data_c",
 };
 
+static const char * const scif_clk_groups[] = {
+	"scif_clk",
+	"scif_clk_b",
+};
+
 static const char * const sdhi0_groups[] = {
 	"sdhi0_data1",
 	"sdhi0_data4",
@@ -4729,6 +4734,7 @@
 	SH_PFC_FUNCTION(scifb0),
 	SH_PFC_FUNCTION(scifb1),
 	SH_PFC_FUNCTION(scifb2),
+	SH_PFC_FUNCTION(scif_clk),
 	SH_PFC_FUNCTION(sdhi0),
 	SH_PFC_FUNCTION(sdhi1),
 	SH_PFC_FUNCTION(sdhi2),
diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a7791.c b/drivers/pinctrl/sh-pfc/pfc-r8a7791.c
index 87a4f44..4cfbb94 100644
--- a/drivers/pinctrl/sh-pfc/pfc-r8a7791.c
+++ b/drivers/pinctrl/sh-pfc/pfc-r8a7791.c
@@ -2,6 +2,7 @@
  * r8a7791 processor support - PFC hardware block.
  *
  * Copyright (C) 2013 Renesas Electronics Corporation
+ * Copyright (C) 2014-2015 Cogent Embedded, Inc.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2
@@ -13,21 +14,6 @@
 #include "core.h"
 #include "sh_pfc.h"
 
-#define PORT_GP_26(bank, fn, sfx)					\
-	PORT_GP_1(bank, 0,  fn, sfx), PORT_GP_1(bank, 1,  fn, sfx),	\
-	PORT_GP_1(bank, 2,  fn, sfx), PORT_GP_1(bank, 3,  fn, sfx),	\
-	PORT_GP_1(bank, 4,  fn, sfx), PORT_GP_1(bank, 5,  fn, sfx),	\
-	PORT_GP_1(bank, 6,  fn, sfx), PORT_GP_1(bank, 7,  fn, sfx),	\
-	PORT_GP_1(bank, 8,  fn, sfx), PORT_GP_1(bank, 9,  fn, sfx),	\
-	PORT_GP_1(bank, 10, fn, sfx), PORT_GP_1(bank, 11, fn, sfx),	\
-	PORT_GP_1(bank, 12, fn, sfx), PORT_GP_1(bank, 13, fn, sfx),	\
-	PORT_GP_1(bank, 14, fn, sfx), PORT_GP_1(bank, 15, fn, sfx),	\
-	PORT_GP_1(bank, 16, fn, sfx), PORT_GP_1(bank, 17, fn, sfx),	\
-	PORT_GP_1(bank, 18, fn, sfx), PORT_GP_1(bank, 19, fn, sfx),	\
-	PORT_GP_1(bank, 20, fn, sfx), PORT_GP_1(bank, 21, fn, sfx),	\
-	PORT_GP_1(bank, 22, fn, sfx), PORT_GP_1(bank, 23, fn, sfx),	\
-	PORT_GP_1(bank, 24, fn, sfx), PORT_GP_1(bank, 25, fn, sfx)
-
 #define CPU_ALL_PORT(fn, sfx)						\
 	PORT_GP_32(0, fn, sfx),						\
 	PORT_GP_26(1, fn, sfx),						\
@@ -787,23 +773,23 @@
 static const u16 pinmux_data[] = {
 	PINMUX_DATA_GP_ALL(), /* PINMUX_DATA(GP_M_N_DATA, GP_M_N_FN...), */
 
-	PINMUX_DATA(EX_CS0_N_MARK, FN_EX_CS0_N),
-	PINMUX_DATA(RD_N_MARK, FN_RD_N),
-	PINMUX_DATA(AUDIO_CLKA_MARK, FN_AUDIO_CLKA),
-	PINMUX_DATA(VI0_CLK_MARK, FN_VI0_CLK),
-	PINMUX_DATA(VI0_DATA0_VI0_B0_MARK, FN_VI0_DATA0_VI0_B0),
-	PINMUX_DATA(VI0_DATA1_VI0_B1_MARK, FN_VI0_DATA1_VI0_B1),
-	PINMUX_DATA(VI0_DATA2_VI0_B2_MARK, FN_VI0_DATA2_VI0_B2),
-	PINMUX_DATA(VI0_DATA4_VI0_B4_MARK, FN_VI0_DATA4_VI0_B4),
-	PINMUX_DATA(VI0_DATA5_VI0_B5_MARK, FN_VI0_DATA5_VI0_B5),
-	PINMUX_DATA(VI0_DATA6_VI0_B6_MARK, FN_VI0_DATA6_VI0_B6),
-	PINMUX_DATA(VI0_DATA7_VI0_B7_MARK, FN_VI0_DATA7_VI0_B7),
-	PINMUX_DATA(USB0_PWEN_MARK, FN_USB0_PWEN),
-	PINMUX_DATA(USB0_OVC_MARK, FN_USB0_OVC),
-	PINMUX_DATA(USB1_PWEN_MARK, FN_USB1_PWEN),
-	PINMUX_DATA(USB1_OVC_MARK, FN_USB1_OVC),
-	PINMUX_DATA(DU0_DOTCLKIN_MARK, FN_DU0_DOTCLKIN),
-	PINMUX_DATA(SD1_CLK_MARK, FN_SD1_CLK),
+	PINMUX_SINGLE(EX_CS0_N),
+	PINMUX_SINGLE(RD_N),
+	PINMUX_SINGLE(AUDIO_CLKA),
+	PINMUX_SINGLE(VI0_CLK),
+	PINMUX_SINGLE(VI0_DATA0_VI0_B0),
+	PINMUX_SINGLE(VI0_DATA1_VI0_B1),
+	PINMUX_SINGLE(VI0_DATA2_VI0_B2),
+	PINMUX_SINGLE(VI0_DATA4_VI0_B4),
+	PINMUX_SINGLE(VI0_DATA5_VI0_B5),
+	PINMUX_SINGLE(VI0_DATA6_VI0_B6),
+	PINMUX_SINGLE(VI0_DATA7_VI0_B7),
+	PINMUX_SINGLE(USB0_PWEN),
+	PINMUX_SINGLE(USB0_OVC),
+	PINMUX_SINGLE(USB1_PWEN),
+	PINMUX_SINGLE(USB1_OVC),
+	PINMUX_SINGLE(DU0_DOTCLKIN),
+	PINMUX_SINGLE(SD1_CLK),
 
 	/* IPSR0 */
 	PINMUX_IPSR_DATA(IP0_0, D0),
@@ -1740,6 +1726,82 @@
 	AUDIO_CLKOUT_MARK,
 };
 
+/* - AVB -------------------------------------------------------------------- */
+static const unsigned int avb_link_pins[] = {
+	RCAR_GP_PIN(5, 14),
+};
+static const unsigned int avb_link_mux[] = {
+	AVB_LINK_MARK,
+};
+static const unsigned int avb_magic_pins[] = {
+	RCAR_GP_PIN(5, 11),
+};
+static const unsigned int avb_magic_mux[] = {
+	AVB_MAGIC_MARK,
+};
+static const unsigned int avb_phy_int_pins[] = {
+	RCAR_GP_PIN(5, 16),
+};
+static const unsigned int avb_phy_int_mux[] = {
+	AVB_PHY_INT_MARK,
+};
+static const unsigned int avb_mdio_pins[] = {
+	RCAR_GP_PIN(5, 12), RCAR_GP_PIN(5, 9),
+};
+static const unsigned int avb_mdio_mux[] = {
+	AVB_MDC_MARK, AVB_MDIO_MARK,
+};
+static const unsigned int avb_mii_pins[] = {
+	RCAR_GP_PIN(5, 18), RCAR_GP_PIN(5, 19), RCAR_GP_PIN(5, 20),
+	RCAR_GP_PIN(5, 21),
+
+	RCAR_GP_PIN(5, 0), RCAR_GP_PIN(5, 1), RCAR_GP_PIN(5, 2),
+	RCAR_GP_PIN(5, 3),
+
+	RCAR_GP_PIN(5, 8), RCAR_GP_PIN(5, 13), RCAR_GP_PIN(5, 10),
+	RCAR_GP_PIN(5, 15), RCAR_GP_PIN(5, 26), RCAR_GP_PIN(5, 27),
+	RCAR_GP_PIN(5, 28), RCAR_GP_PIN(5, 29),
+};
+static const unsigned int avb_mii_mux[] = {
+	AVB_TXD0_MARK, AVB_TXD1_MARK, AVB_TXD2_MARK,
+	AVB_TXD3_MARK,
+
+	AVB_RXD0_MARK, AVB_RXD1_MARK, AVB_RXD2_MARK,
+	AVB_RXD3_MARK,
+
+	AVB_RX_ER_MARK, AVB_RX_CLK_MARK, AVB_RX_DV_MARK,
+	AVB_CRS_MARK, AVB_TX_EN_MARK, AVB_TX_ER_MARK,
+	AVB_TX_CLK_MARK, AVB_COL_MARK,
+};
+static const unsigned int avb_gmii_pins[] = {
+	RCAR_GP_PIN(5, 18), RCAR_GP_PIN(5, 19), RCAR_GP_PIN(5, 20),
+	RCAR_GP_PIN(5, 21), RCAR_GP_PIN(5, 22), RCAR_GP_PIN(5, 23),
+	RCAR_GP_PIN(5, 24), RCAR_GP_PIN(5, 25),
+
+	RCAR_GP_PIN(5, 0), RCAR_GP_PIN(5, 1), RCAR_GP_PIN(5, 2),
+	RCAR_GP_PIN(5, 3), RCAR_GP_PIN(5, 4), RCAR_GP_PIN(5, 5),
+	RCAR_GP_PIN(5, 6), RCAR_GP_PIN(5, 7),
+
+	RCAR_GP_PIN(5, 8), RCAR_GP_PIN(5, 13), RCAR_GP_PIN(5, 10),
+	RCAR_GP_PIN(5, 15), RCAR_GP_PIN(5, 30), RCAR_GP_PIN(5, 17),
+	RCAR_GP_PIN(5, 26), RCAR_GP_PIN(5, 27), RCAR_GP_PIN(5, 28),
+	RCAR_GP_PIN(5, 29),
+};
+static const unsigned int avb_gmii_mux[] = {
+	AVB_TXD0_MARK, AVB_TXD1_MARK, AVB_TXD2_MARK,
+	AVB_TXD3_MARK, AVB_TXD4_MARK, AVB_TXD5_MARK,
+	AVB_TXD6_MARK, AVB_TXD7_MARK,
+
+	AVB_RXD0_MARK, AVB_RXD1_MARK, AVB_RXD2_MARK,
+	AVB_RXD3_MARK, AVB_RXD4_MARK, AVB_RXD5_MARK,
+	AVB_RXD6_MARK, AVB_RXD7_MARK,
+
+	AVB_RX_ER_MARK, AVB_RX_CLK_MARK, AVB_RX_DV_MARK,
+	AVB_CRS_MARK, AVB_GTX_CLK_MARK, AVB_GTXREFCLK_MARK,
+	AVB_TX_EN_MARK, AVB_TX_ER_MARK, AVB_TX_CLK_MARK,
+	AVB_COL_MARK,
+};
+
 /* - CAN -------------------------------------------------------------------- */
 
 static const unsigned int can0_data_pins[] = {
@@ -3602,6 +3664,23 @@
 static const unsigned int scifb2_data_d_mux[] = {
 	SCIFB2_RXD_D_MARK, SCIFB2_TXD_D_MARK,
 };
+
+/* - SCIF Clock ------------------------------------------------------------- */
+static const unsigned int scif_clk_pins[] = {
+	/* SCIF_CLK */
+	RCAR_GP_PIN(2, 29),
+};
+static const unsigned int scif_clk_mux[] = {
+	SCIF_CLK_MARK,
+};
+static const unsigned int scif_clk_b_pins[] = {
+	/* SCIF_CLK */
+	RCAR_GP_PIN(7, 19),
+};
+static const unsigned int scif_clk_b_mux[] = {
+	SCIF_CLK_B_MARK,
+};
+
 /* - SDHI0 ------------------------------------------------------------------ */
 static const unsigned int sdhi0_data1_pins[] = {
 	/* D0 */
@@ -4258,6 +4337,12 @@
 	SH_PFC_PIN_GROUP(audio_clk_b_b),
 	SH_PFC_PIN_GROUP(audio_clk_c),
 	SH_PFC_PIN_GROUP(audio_clkout),
+	SH_PFC_PIN_GROUP(avb_link),
+	SH_PFC_PIN_GROUP(avb_magic),
+	SH_PFC_PIN_GROUP(avb_phy_int),
+	SH_PFC_PIN_GROUP(avb_mdio),
+	SH_PFC_PIN_GROUP(avb_mii),
+	SH_PFC_PIN_GROUP(avb_gmii),
 	SH_PFC_PIN_GROUP(can0_data),
 	SH_PFC_PIN_GROUP(can0_data_b),
 	SH_PFC_PIN_GROUP(can0_data_c),
@@ -4510,6 +4595,8 @@
 	SH_PFC_PIN_GROUP(scifb2_data_c),
 	SH_PFC_PIN_GROUP(scifb2_clk_c),
 	SH_PFC_PIN_GROUP(scifb2_data_d),
+	SH_PFC_PIN_GROUP(scif_clk),
+	SH_PFC_PIN_GROUP(scif_clk_b),
 	SH_PFC_PIN_GROUP(sdhi0_data1),
 	SH_PFC_PIN_GROUP(sdhi0_data4),
 	SH_PFC_PIN_GROUP(sdhi0_ctrl),
@@ -4597,6 +4684,15 @@
 	"audio_clkout",
 };
 
+static const char * const avb_groups[] = {
+	"avb_link",
+	"avb_magic",
+	"avb_phy_int",
+	"avb_mdio",
+	"avb_mii",
+	"avb_gmii",
+};
+
 static const char * const can0_groups[] = {
 	"can0_data",
 	"can0_data_b",
@@ -4976,6 +5072,11 @@
 	"scifb2_data_d",
 };
 
+static const char * const scif_clk_groups[] = {
+	"scif_clk",
+	"scif_clk_b",
+};
+
 static const char * const sdhi0_groups[] = {
 	"sdhi0_data1",
 	"sdhi0_data4",
@@ -5081,6 +5182,7 @@
 
 static const struct sh_pfc_function pinmux_functions[] = {
 	SH_PFC_FUNCTION(audio_clk),
+	SH_PFC_FUNCTION(avb),
 	SH_PFC_FUNCTION(can0),
 	SH_PFC_FUNCTION(can1),
 	SH_PFC_FUNCTION(du),
@@ -5126,6 +5228,7 @@
 	SH_PFC_FUNCTION(scifb0),
 	SH_PFC_FUNCTION(scifb1),
 	SH_PFC_FUNCTION(scifb2),
+	SH_PFC_FUNCTION(scif_clk),
 	SH_PFC_FUNCTION(sdhi0),
 	SH_PFC_FUNCTION(sdhi1),
 	SH_PFC_FUNCTION(sdhi2),
diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a7794.c b/drivers/pinctrl/sh-pfc/pfc-r8a7794.c
index 086f679..3718c78 100644
--- a/drivers/pinctrl/sh-pfc/pfc-r8a7794.c
+++ b/drivers/pinctrl/sh-pfc/pfc-r8a7794.c
@@ -15,25 +15,6 @@
 #include "core.h"
 #include "sh_pfc.h"
 
-#define PORT_GP_26(bank, fn, sfx)					\
-	PORT_GP_1(bank, 0,  fn, sfx), PORT_GP_1(bank, 1,  fn, sfx),	\
-	PORT_GP_1(bank, 2,  fn, sfx), PORT_GP_1(bank, 3,  fn, sfx),	\
-	PORT_GP_1(bank, 4,  fn, sfx), PORT_GP_1(bank, 5,  fn, sfx),	\
-	PORT_GP_1(bank, 6,  fn, sfx), PORT_GP_1(bank, 7,  fn, sfx),	\
-	PORT_GP_1(bank, 8,  fn, sfx), PORT_GP_1(bank, 9,  fn, sfx),	\
-	PORT_GP_1(bank, 10, fn, sfx), PORT_GP_1(bank, 11, fn, sfx),	\
-	PORT_GP_1(bank, 12, fn, sfx), PORT_GP_1(bank, 13, fn, sfx),	\
-	PORT_GP_1(bank, 14, fn, sfx), PORT_GP_1(bank, 15, fn, sfx),	\
-	PORT_GP_1(bank, 16, fn, sfx), PORT_GP_1(bank, 17, fn, sfx),	\
-	PORT_GP_1(bank, 18, fn, sfx), PORT_GP_1(bank, 19, fn, sfx),	\
-	PORT_GP_1(bank, 20, fn, sfx), PORT_GP_1(bank, 21, fn, sfx),	\
-	PORT_GP_1(bank, 22, fn, sfx), PORT_GP_1(bank, 23, fn, sfx),	\
-	PORT_GP_1(bank, 24, fn, sfx), PORT_GP_1(bank, 25, fn, sfx)
-
-#define PORT_GP_28(bank, fn, sfx)					\
-	PORT_GP_26(bank, fn, sfx),					\
-	PORT_GP_1(bank, 26, fn, sfx), PORT_GP_1(bank, 27, fn, sfx)
-
 #define CPU_ALL_PORT(fn, sfx)						\
 	PORT_GP_32(0, fn, sfx),						\
 	PORT_GP_26(1, fn, sfx),						\
@@ -618,28 +599,28 @@
 static const u16 pinmux_data[] = {
 	PINMUX_DATA_GP_ALL(), /* PINMUX_DATA(GP_M_N_DATA, GP_M_N_FN...), */
 
-	PINMUX_DATA(A2_MARK, FN_A2),
-	PINMUX_DATA(WE0_N_MARK, FN_WE0_N),
-	PINMUX_DATA(WE1_N_MARK, FN_WE1_N),
-	PINMUX_DATA(DACK0_MARK, FN_DACK0),
-	PINMUX_DATA(USB0_PWEN_MARK, FN_USB0_PWEN),
-	PINMUX_DATA(USB0_OVC_MARK, FN_USB0_OVC),
-	PINMUX_DATA(USB1_PWEN_MARK, FN_USB1_PWEN),
-	PINMUX_DATA(USB1_OVC_MARK, FN_USB1_OVC),
-	PINMUX_DATA(SD0_CLK_MARK, FN_SD0_CLK),
-	PINMUX_DATA(SD0_CMD_MARK, FN_SD0_CMD),
-	PINMUX_DATA(SD0_DATA0_MARK, FN_SD0_DATA0),
-	PINMUX_DATA(SD0_DATA1_MARK, FN_SD0_DATA1),
-	PINMUX_DATA(SD0_DATA2_MARK, FN_SD0_DATA2),
-	PINMUX_DATA(SD0_DATA3_MARK, FN_SD0_DATA3),
-	PINMUX_DATA(SD0_CD_MARK, FN_SD0_CD),
-	PINMUX_DATA(SD0_WP_MARK, FN_SD0_WP),
-	PINMUX_DATA(SD1_CLK_MARK, FN_SD1_CLK),
-	PINMUX_DATA(SD1_CMD_MARK, FN_SD1_CMD),
-	PINMUX_DATA(SD1_DATA0_MARK, FN_SD1_DATA0),
-	PINMUX_DATA(SD1_DATA1_MARK, FN_SD1_DATA1),
-	PINMUX_DATA(SD1_DATA2_MARK, FN_SD1_DATA2),
-	PINMUX_DATA(SD1_DATA3_MARK, FN_SD1_DATA3),
+	PINMUX_SINGLE(A2),
+	PINMUX_SINGLE(WE0_N),
+	PINMUX_SINGLE(WE1_N),
+	PINMUX_SINGLE(DACK0),
+	PINMUX_SINGLE(USB0_PWEN),
+	PINMUX_SINGLE(USB0_OVC),
+	PINMUX_SINGLE(USB1_PWEN),
+	PINMUX_SINGLE(USB1_OVC),
+	PINMUX_SINGLE(SD0_CLK),
+	PINMUX_SINGLE(SD0_CMD),
+	PINMUX_SINGLE(SD0_DATA0),
+	PINMUX_SINGLE(SD0_DATA1),
+	PINMUX_SINGLE(SD0_DATA2),
+	PINMUX_SINGLE(SD0_DATA3),
+	PINMUX_SINGLE(SD0_CD),
+	PINMUX_SINGLE(SD0_WP),
+	PINMUX_SINGLE(SD1_CLK),
+	PINMUX_SINGLE(SD1_CMD),
+	PINMUX_SINGLE(SD1_DATA0),
+	PINMUX_SINGLE(SD1_DATA1),
+	PINMUX_SINGLE(SD1_DATA2),
+	PINMUX_SINGLE(SD1_DATA3),
 
 	/* IPSR0 */
 	PINMUX_IPSR_DATA(IP0_0, SD1_CD),
@@ -2644,6 +2625,21 @@
 static const unsigned int scifb2_ctrl_mux[] = {
 	SCIFB2_RTS_N_MARK, SCIFB2_CTS_N_MARK,
 };
+/* - SCIF Clock ------------------------------------------------------------- */
+static const unsigned int scif_clk_pins[] = {
+	/* SCIF_CLK */
+	RCAR_GP_PIN(1, 23),
+};
+static const unsigned int scif_clk_mux[] = {
+	SCIF_CLK_MARK,
+};
+static const unsigned int scif_clk_b_pins[] = {
+	/* SCIF_CLK */
+	RCAR_GP_PIN(3, 29),
+};
+static const unsigned int scif_clk_b_mux[] = {
+	SCIF_CLK_B_MARK,
+};
 /* - SDHI0 ------------------------------------------------------------------ */
 static const unsigned int sdhi0_data1_pins[] = {
 	/* D0 */
@@ -3071,6 +3067,8 @@
 	SH_PFC_PIN_GROUP(scifb2_data),
 	SH_PFC_PIN_GROUP(scifb2_clk),
 	SH_PFC_PIN_GROUP(scifb2_ctrl),
+	SH_PFC_PIN_GROUP(scif_clk),
+	SH_PFC_PIN_GROUP(scif_clk_b),
 	SH_PFC_PIN_GROUP(sdhi0_data1),
 	SH_PFC_PIN_GROUP(sdhi0_data4),
 	SH_PFC_PIN_GROUP(sdhi0_ctrl),
@@ -3354,6 +3352,11 @@
 	"scifb2_ctrl",
 };
 
+static const char * const scif_clk_groups[] = {
+	"scif_clk",
+	"scif_clk_b",
+};
+
 static const char * const sdhi0_groups[] = {
 	"sdhi0_data1",
 	"sdhi0_data4",
@@ -3441,6 +3444,7 @@
 	SH_PFC_FUNCTION(scifb0),
 	SH_PFC_FUNCTION(scifb1),
 	SH_PFC_FUNCTION(scifb2),
+	SH_PFC_FUNCTION(scif_clk),
 	SH_PFC_FUNCTION(sdhi0),
 	SH_PFC_FUNCTION(sdhi1),
 	SH_PFC_FUNCTION(sdhi2),
diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a7795.c b/drivers/pinctrl/sh-pfc/pfc-r8a7795.c
index 7ddb2ad..ce4f5cd 100644
--- a/drivers/pinctrl/sh-pfc/pfc-r8a7795.c
+++ b/drivers/pinctrl/sh-pfc/pfc-r8a7795.c
@@ -13,46 +13,15 @@
 #include "core.h"
 #include "sh_pfc.h"
 
-#define PORT_GP_3(bank, fn, sfx)					\
-	PORT_GP_1(bank, 0,  fn, sfx), PORT_GP_1(bank, 1,  fn, sfx),	\
-	PORT_GP_1(bank, 2,  fn, sfx), PORT_GP_1(bank, 3,  fn, sfx)
-
-#define PORT_GP_14(bank, fn, sfx)					\
-	PORT_GP_3(bank, fn, sfx),					\
-	PORT_GP_1(bank, 4,  fn, sfx), PORT_GP_1(bank, 5,  fn, sfx),	\
-	PORT_GP_1(bank, 6,  fn, sfx), PORT_GP_1(bank, 7,  fn, sfx),	\
-	PORT_GP_1(bank, 8,  fn, sfx), PORT_GP_1(bank, 9,  fn, sfx),	\
-	PORT_GP_1(bank, 10, fn, sfx), PORT_GP_1(bank, 11, fn, sfx),	\
-	PORT_GP_1(bank, 12, fn, sfx), PORT_GP_1(bank, 13, fn, sfx),	\
-	PORT_GP_1(bank, 14, fn, sfx)
-
-#define PORT_GP_15(bank, fn, sfx)					\
-	PORT_GP_14(bank, fn, sfx),   PORT_GP_1(bank, 15, fn, sfx)
-
-#define PORT_GP_17(bank, fn, sfx)					\
-	PORT_GP_15(bank, fn, sfx),					\
-	PORT_GP_1(bank, 16, fn, sfx), PORT_GP_1(bank, 17, fn, sfx)
-
-#define PORT_GP_25(bank, fn, sfx)					\
-	PORT_GP_17(bank, fn, sfx),					\
-	PORT_GP_1(bank, 18, fn, sfx), PORT_GP_1(bank, 19, fn, sfx),	\
-	PORT_GP_1(bank, 20, fn, sfx), PORT_GP_1(bank, 21, fn, sfx),	\
-	PORT_GP_1(bank, 22, fn, sfx), PORT_GP_1(bank, 23, fn, sfx),	\
-	PORT_GP_1(bank, 24, fn, sfx), PORT_GP_1(bank, 25, fn, sfx)
-
-#define PORT_GP_27(bank, fn, sfx)					\
-	PORT_GP_25(bank, fn, sfx),					\
-	PORT_GP_1(bank, 26, fn, sfx), PORT_GP_1(bank, 27, fn, sfx)
-
 #define CPU_ALL_PORT(fn, sfx)						\
-	PORT_GP_15(0, fn, sfx),						\
-	PORT_GP_27(1, fn, sfx),						\
-	PORT_GP_14(2, fn, sfx),						\
-	PORT_GP_15(3, fn, sfx),						\
-	PORT_GP_17(4, fn, sfx),						\
-	PORT_GP_25(5, fn, sfx),						\
+	PORT_GP_16(0, fn, sfx),						\
+	PORT_GP_28(1, fn, sfx),						\
+	PORT_GP_15(2, fn, sfx),						\
+	PORT_GP_16(3, fn, sfx),						\
+	PORT_GP_18(4, fn, sfx),						\
+	PORT_GP_26(5, fn, sfx),						\
 	PORT_GP_32(6, fn, sfx),						\
-	PORT_GP_3(7, fn, sfx)
+	PORT_GP_4(7, fn, sfx)
 /*
  * F_() : just information
  * FM() : macro for FN_xxx / xxx_MARK
@@ -495,7 +464,7 @@
 #define MOD_SEL1_13		FM(SEL_SCIF3_0)		FM(SEL_SCIF3_1)
 #define MOD_SEL1_12		FM(SEL_SCIF2_0)		FM(SEL_SCIF2_1)
 #define MOD_SEL1_11		FM(SEL_SCIF1_0)		FM(SEL_SCIF1_1)
-#define MOD_SEL1_10		FM(SEL_SCIF_0)		FM(SEL_SCIF_1)
+#define MOD_SEL1_10		FM(SEL_SATA_0)		FM(SEL_SATA_1)
 #define MOD_SEL1_9		FM(SEL_REMOCON_0)	FM(SEL_REMOCON_1)
 #define MOD_SEL1_6		FM(SEL_RCAN0_0)		FM(SEL_RCAN0_1)
 #define MOD_SEL1_5		FM(SEL_PWM6_0)		FM(SEL_PWM6_1)
@@ -580,6 +549,25 @@
 static const u16 pinmux_data[] = {
 	PINMUX_DATA_GP_ALL(),
 
+	PINMUX_SINGLE(AVS1),
+	PINMUX_SINGLE(AVS2),
+	PINMUX_SINGLE(HDMI0_CEC),
+	PINMUX_SINGLE(HDMI1_CEC),
+	PINMUX_SINGLE(MSIOF0_RXD),
+	PINMUX_SINGLE(MSIOF0_SCK),
+	PINMUX_SINGLE(MSIOF0_TXD),
+	PINMUX_SINGLE(SD2_CMD),
+	PINMUX_SINGLE(SD3_CLK),
+	PINMUX_SINGLE(SD3_CMD),
+	PINMUX_SINGLE(SD3_DAT0),
+	PINMUX_SINGLE(SD3_DAT1),
+	PINMUX_SINGLE(SD3_DAT2),
+	PINMUX_SINGLE(SD3_DAT3),
+	PINMUX_SINGLE(SD3_DS),
+	PINMUX_SINGLE(SSI_SCK5),
+	PINMUX_SINGLE(SSI_SDATA5),
+	PINMUX_SINGLE(SSI_WS5),
+
 	/* IPSR0 */
 	PINMUX_IPSR_DATA(IP0_3_0,	AVB_MDC),
 	PINMUX_IPSR_MSEL(IP0_3_0,	MSIOF2_SS2_C,		SEL_MSIOF2_2),
@@ -1033,7 +1021,7 @@
 	PINMUX_IPSR_DATA(IP9_19_16,	SD2_DAT3),
 
 	PINMUX_IPSR_DATA(IP9_23_20,	SD2_DS),
-	PINMUX_IPSR_MSEL(IP9_23_20,	SATA_DEVSLP_B,		SEL_SCIF_1),
+	PINMUX_IPSR_MSEL(IP9_23_20,	SATA_DEVSLP_B,		SEL_SATA_1),
 
 	PINMUX_IPSR_DATA(IP9_27_24,	SD3_DAT4),
 	PINMUX_IPSR_MSEL(IP9_27_24,	SD2_CD_A,		SEL_SDHI2_0),
@@ -1293,7 +1281,7 @@
 
 	PINMUX_IPSR_DATA(IP15_11_8,	SSI_SDATA6),
 	PINMUX_IPSR_MSEL(IP15_11_8,	SIM0_CLK_D,		SEL_SIMCARD_3),
-	PINMUX_IPSR_MSEL(IP15_11_8,	SATA_DEVSLP_A,		SEL_SCIF_0),
+	PINMUX_IPSR_MSEL(IP15_11_8,	SATA_DEVSLP_A,		SEL_SATA_0),
 
 	PINMUX_IPSR_DATA(IP15_15_12,	SSI_SCK78),
 	PINMUX_IPSR_MSEL(IP15_15_12,	HRX2_B,			SEL_HSCIF2_1),
@@ -1612,6 +1600,191 @@
 	AVB_AVTP_CAPTURE_B_MARK,
 };
 
+/* - HSCIF0 ----------------------------------------------------------------- */
+static const unsigned int hscif0_data_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(5, 13), RCAR_GP_PIN(5, 14),
+};
+static const unsigned int hscif0_data_mux[] = {
+	HRX0_MARK, HTX0_MARK,
+};
+static const unsigned int hscif0_clk_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(5, 12),
+};
+static const unsigned int hscif0_clk_mux[] = {
+	HSCK0_MARK,
+};
+static const unsigned int hscif0_ctrl_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(5, 16), RCAR_GP_PIN(5, 15),
+};
+static const unsigned int hscif0_ctrl_mux[] = {
+	HRTS0_N_MARK, HCTS0_N_MARK,
+};
+/* - HSCIF1 ----------------------------------------------------------------- */
+static const unsigned int hscif1_data_a_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(5, 5), RCAR_GP_PIN(5, 6),
+};
+static const unsigned int hscif1_data_a_mux[] = {
+	HRX1_A_MARK, HTX1_A_MARK,
+};
+static const unsigned int hscif1_clk_a_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(6, 21),
+};
+static const unsigned int hscif1_clk_a_mux[] = {
+	HSCK1_A_MARK,
+};
+static const unsigned int hscif1_ctrl_a_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(5, 8), RCAR_GP_PIN(5, 7),
+};
+static const unsigned int hscif1_ctrl_a_mux[] = {
+	HRTS1_N_A_MARK, HCTS1_N_A_MARK,
+};
+
+static const unsigned int hscif1_data_b_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(5, 1), RCAR_GP_PIN(5, 2),
+};
+static const unsigned int hscif1_data_b_mux[] = {
+	HRX1_B_MARK, HTX1_B_MARK,
+};
+static const unsigned int hscif1_clk_b_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(5, 0),
+};
+static const unsigned int hscif1_clk_b_mux[] = {
+	HSCK1_B_MARK,
+};
+static const unsigned int hscif1_ctrl_b_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(5, 4), RCAR_GP_PIN(5, 3),
+};
+static const unsigned int hscif1_ctrl_b_mux[] = {
+	HRTS1_N_B_MARK, HCTS1_N_B_MARK,
+};
+/* - HSCIF2 ----------------------------------------------------------------- */
+static const unsigned int hscif2_data_a_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(6, 8), RCAR_GP_PIN(6, 9),
+};
+static const unsigned int hscif2_data_a_mux[] = {
+	HRX2_A_MARK, HTX2_A_MARK,
+};
+static const unsigned int hscif2_clk_a_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(6, 10),
+};
+static const unsigned int hscif2_clk_a_mux[] = {
+	HSCK2_A_MARK,
+};
+static const unsigned int hscif2_ctrl_a_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(6, 7), RCAR_GP_PIN(6, 6),
+};
+static const unsigned int hscif2_ctrl_a_mux[] = {
+	HRTS2_N_A_MARK, HCTS2_N_A_MARK,
+};
+
+static const unsigned int hscif2_data_b_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(6, 17), RCAR_GP_PIN(6, 18),
+};
+static const unsigned int hscif2_data_b_mux[] = {
+	HRX2_B_MARK, HTX2_B_MARK,
+};
+static const unsigned int hscif2_clk_b_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(6, 21),
+};
+static const unsigned int hscif2_clk_b_mux[] = {
+	HSCK1_B_MARK,
+};
+static const unsigned int hscif2_ctrl_b_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(6, 20), RCAR_GP_PIN(6, 19),
+};
+static const unsigned int hscif2_ctrl_b_mux[] = {
+	HRTS2_N_B_MARK, HCTS2_N_B_MARK,
+};
+/* - HSCIF3 ----------------------------------------------------------------- */
+static const unsigned int hscif3_data_a_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(1, 23), RCAR_GP_PIN(1, 24),
+};
+static const unsigned int hscif3_data_a_mux[] = {
+	HRX3_A_MARK, HTX3_A_MARK,
+};
+static const unsigned int hscif3_clk_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(1, 22),
+};
+static const unsigned int hscif3_clk_mux[] = {
+	HSCK3_MARK,
+};
+static const unsigned int hscif3_ctrl_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(1, 26), RCAR_GP_PIN(1, 25),
+};
+static const unsigned int hscif3_ctrl_mux[] = {
+	HRTS3_N_MARK, HCTS3_N_MARK,
+};
+
+static const unsigned int hscif3_data_b_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(0, 10), RCAR_GP_PIN(0, 11),
+};
+static const unsigned int hscif3_data_b_mux[] = {
+	HRX3_B_MARK, HTX3_B_MARK,
+};
+static const unsigned int hscif3_data_c_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(0, 14), RCAR_GP_PIN(0, 15),
+};
+static const unsigned int hscif3_data_c_mux[] = {
+	HRX3_C_MARK, HTX3_C_MARK,
+};
+static const unsigned int hscif3_data_d_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(2, 7), RCAR_GP_PIN(2, 8),
+};
+static const unsigned int hscif3_data_d_mux[] = {
+	HRX3_D_MARK, HTX3_D_MARK,
+};
+/* - HSCIF4 ----------------------------------------------------------------- */
+static const unsigned int hscif4_data_a_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(1, 12), RCAR_GP_PIN(1, 13),
+};
+static const unsigned int hscif4_data_a_mux[] = {
+	HRX4_A_MARK, HTX4_A_MARK,
+};
+static const unsigned int hscif4_clk_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(1, 11),
+};
+static const unsigned int hscif4_clk_mux[] = {
+	HSCK4_MARK,
+};
+static const unsigned int hscif4_ctrl_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(1, 15), RCAR_GP_PIN(1, 14),
+};
+static const unsigned int hscif4_ctrl_mux[] = {
+	HRTS4_N_MARK, HCTS3_N_MARK,
+};
+
+static const unsigned int hscif4_data_b_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(1, 8), RCAR_GP_PIN(1, 11),
+};
+static const unsigned int hscif4_data_b_mux[] = {
+	HRX4_B_MARK, HTX4_B_MARK,
+};
+
 /* - I2C -------------------------------------------------------------------- */
 static const unsigned int i2c1_a_pins[] = {
 	/* SDA, SCL */
@@ -1663,6 +1836,678 @@
 	SDA6_C_MARK, SCL6_C_MARK,
 };
 
+/* - MSIOF0 ----------------------------------------------------------------- */
+static const unsigned int msiof0_clk_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(5, 17),
+};
+static const unsigned int msiof0_clk_mux[] = {
+	MSIOF0_SCK_MARK,
+};
+static const unsigned int msiof0_sync_pins[] = {
+	/* SYNC */
+	RCAR_GP_PIN(5, 18),
+};
+static const unsigned int msiof0_sync_mux[] = {
+	MSIOF0_SYNC_MARK,
+};
+static const unsigned int msiof0_ss1_pins[] = {
+	/* SS1 */
+	RCAR_GP_PIN(5, 19),
+};
+static const unsigned int msiof0_ss1_mux[] = {
+	MSIOF0_SS1_MARK,
+};
+static const unsigned int msiof0_ss2_pins[] = {
+	/* SS2 */
+	RCAR_GP_PIN(5, 21),
+};
+static const unsigned int msiof0_ss2_mux[] = {
+	MSIOF0_SS2_MARK,
+};
+static const unsigned int msiof0_txd_pins[] = {
+	/* TXD */
+	RCAR_GP_PIN(5, 20),
+};
+static const unsigned int msiof0_txd_mux[] = {
+	MSIOF0_TXD_MARK,
+};
+static const unsigned int msiof0_rxd_pins[] = {
+	/* RXD */
+	RCAR_GP_PIN(5, 22),
+};
+static const unsigned int msiof0_rxd_mux[] = {
+	MSIOF0_RXD_MARK,
+};
+/* - MSIOF1 ----------------------------------------------------------------- */
+static const unsigned int msiof1_clk_a_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(6, 8),
+};
+static const unsigned int msiof1_clk_a_mux[] = {
+	MSIOF1_SCK_A_MARK,
+};
+static const unsigned int msiof1_sync_a_pins[] = {
+	/* SYNC */
+	RCAR_GP_PIN(6, 9),
+};
+static const unsigned int msiof1_sync_a_mux[] = {
+	MSIOF1_SYNC_A_MARK,
+};
+static const unsigned int msiof1_ss1_a_pins[] = {
+	/* SS1 */
+	RCAR_GP_PIN(6, 5),
+};
+static const unsigned int msiof1_ss1_a_mux[] = {
+	MSIOF1_SS1_A_MARK,
+};
+static const unsigned int msiof1_ss2_a_pins[] = {
+	/* SS2 */
+	RCAR_GP_PIN(6, 6),
+};
+static const unsigned int msiof1_ss2_a_mux[] = {
+	MSIOF1_SS2_A_MARK,
+};
+static const unsigned int msiof1_txd_a_pins[] = {
+	/* TXD */
+	RCAR_GP_PIN(6, 7),
+};
+static const unsigned int msiof1_txd_a_mux[] = {
+	MSIOF1_TXD_A_MARK,
+};
+static const unsigned int msiof1_rxd_a_pins[] = {
+	/* RXD */
+	RCAR_GP_PIN(6, 10),
+};
+static const unsigned int msiof1_rxd_a_mux[] = {
+	MSIOF1_RXD_A_MARK,
+};
+static const unsigned int msiof1_clk_b_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(5, 9),
+};
+static const unsigned int msiof1_clk_b_mux[] = {
+	MSIOF1_SCK_B_MARK,
+};
+static const unsigned int msiof1_sync_b_pins[] = {
+	/* SYNC */
+	RCAR_GP_PIN(5, 3),
+};
+static const unsigned int msiof1_sync_b_mux[] = {
+	MSIOF1_SYNC_B_MARK,
+};
+static const unsigned int msiof1_ss1_b_pins[] = {
+	/* SS1 */
+	RCAR_GP_PIN(5, 4),
+};
+static const unsigned int msiof1_ss1_b_mux[] = {
+	MSIOF1_SS1_B_MARK,
+};
+static const unsigned int msiof1_ss2_b_pins[] = {
+	/* SS2 */
+	RCAR_GP_PIN(5, 0),
+};
+static const unsigned int msiof1_ss2_b_mux[] = {
+	MSIOF1_SS2_B_MARK,
+};
+static const unsigned int msiof1_txd_b_pins[] = {
+	/* TXD */
+	RCAR_GP_PIN(5, 8),
+};
+static const unsigned int msiof1_txd_b_mux[] = {
+	MSIOF1_TXD_B_MARK,
+};
+static const unsigned int msiof1_rxd_b_pins[] = {
+	/* RXD */
+	RCAR_GP_PIN(5, 7),
+};
+static const unsigned int msiof1_rxd_b_mux[] = {
+	MSIOF1_RXD_B_MARK,
+};
+static const unsigned int msiof1_clk_c_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(6, 17),
+};
+static const unsigned int msiof1_clk_c_mux[] = {
+	MSIOF1_SCK_C_MARK,
+};
+static const unsigned int msiof1_sync_c_pins[] = {
+	/* SYNC */
+	RCAR_GP_PIN(6, 18),
+};
+static const unsigned int msiof1_sync_c_mux[] = {
+	MSIOF1_SYNC_C_MARK,
+};
+static const unsigned int msiof1_ss1_c_pins[] = {
+	/* SS1 */
+	RCAR_GP_PIN(6, 21),
+};
+static const unsigned int msiof1_ss1_c_mux[] = {
+	MSIOF1_SS1_C_MARK,
+};
+static const unsigned int msiof1_ss2_c_pins[] = {
+	/* SS2 */
+	RCAR_GP_PIN(6, 27),
+};
+static const unsigned int msiof1_ss2_c_mux[] = {
+	MSIOF1_SS2_C_MARK,
+};
+static const unsigned int msiof1_txd_c_pins[] = {
+	/* TXD */
+	RCAR_GP_PIN(6, 20),
+};
+static const unsigned int msiof1_txd_c_mux[] = {
+	MSIOF1_TXD_C_MARK,
+};
+static const unsigned int msiof1_rxd_c_pins[] = {
+	/* RXD */
+	RCAR_GP_PIN(6, 19),
+};
+static const unsigned int msiof1_rxd_c_mux[] = {
+	MSIOF1_RXD_C_MARK,
+};
+static const unsigned int msiof1_clk_d_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(5, 12),
+};
+static const unsigned int msiof1_clk_d_mux[] = {
+	MSIOF1_SCK_D_MARK,
+};
+static const unsigned int msiof1_sync_d_pins[] = {
+	/* SYNC */
+	RCAR_GP_PIN(5, 15),
+};
+static const unsigned int msiof1_sync_d_mux[] = {
+	MSIOF1_SYNC_D_MARK,
+};
+static const unsigned int msiof1_ss1_d_pins[] = {
+	/* SS1 */
+	RCAR_GP_PIN(5, 16),
+};
+static const unsigned int msiof1_ss1_d_mux[] = {
+	MSIOF1_SS1_D_MARK,
+};
+static const unsigned int msiof1_ss2_d_pins[] = {
+	/* SS2 */
+	RCAR_GP_PIN(5, 21),
+};
+static const unsigned int msiof1_ss2_d_mux[] = {
+	MSIOF1_SS2_D_MARK,
+};
+static const unsigned int msiof1_txd_d_pins[] = {
+	/* TXD */
+	RCAR_GP_PIN(5, 14),
+};
+static const unsigned int msiof1_txd_d_mux[] = {
+	MSIOF1_TXD_D_MARK,
+};
+static const unsigned int msiof1_rxd_d_pins[] = {
+	/* RXD */
+	RCAR_GP_PIN(5, 13),
+};
+static const unsigned int msiof1_rxd_d_mux[] = {
+	MSIOF1_RXD_D_MARK,
+};
+static const unsigned int msiof1_clk_e_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(3, 0),
+};
+static const unsigned int msiof1_clk_e_mux[] = {
+	MSIOF1_SCK_E_MARK,
+};
+static const unsigned int msiof1_sync_e_pins[] = {
+	/* SYNC */
+	RCAR_GP_PIN(3, 1),
+};
+static const unsigned int msiof1_sync_e_mux[] = {
+	MSIOF1_SYNC_E_MARK,
+};
+static const unsigned int msiof1_ss1_e_pins[] = {
+	/* SS1 */
+	RCAR_GP_PIN(3, 4),
+};
+static const unsigned int msiof1_ss1_e_mux[] = {
+	MSIOF1_SS1_E_MARK,
+};
+static const unsigned int msiof1_ss2_e_pins[] = {
+	/* SS2 */
+	RCAR_GP_PIN(3, 5),
+};
+static const unsigned int msiof1_ss2_e_mux[] = {
+	MSIOF1_SS2_E_MARK,
+};
+static const unsigned int msiof1_txd_e_pins[] = {
+	/* TXD */
+	RCAR_GP_PIN(3, 3),
+};
+static const unsigned int msiof1_txd_e_mux[] = {
+	MSIOF1_TXD_E_MARK,
+};
+static const unsigned int msiof1_rxd_e_pins[] = {
+	/* RXD */
+	RCAR_GP_PIN(3, 2),
+};
+static const unsigned int msiof1_rxd_e_mux[] = {
+	MSIOF1_RXD_E_MARK,
+};
+static const unsigned int msiof1_clk_f_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(5, 23),
+};
+static const unsigned int msiof1_clk_f_mux[] = {
+	MSIOF1_SCK_F_MARK,
+};
+static const unsigned int msiof1_sync_f_pins[] = {
+	/* SYNC */
+	RCAR_GP_PIN(5, 24),
+};
+static const unsigned int msiof1_sync_f_mux[] = {
+	MSIOF1_SYNC_F_MARK,
+};
+static const unsigned int msiof1_ss1_f_pins[] = {
+	/* SS1 */
+	RCAR_GP_PIN(6, 1),
+};
+static const unsigned int msiof1_ss1_f_mux[] = {
+	MSIOF1_SS1_F_MARK,
+};
+static const unsigned int msiof1_ss2_f_pins[] = {
+	/* SS2 */
+	RCAR_GP_PIN(6, 2),
+};
+static const unsigned int msiof1_ss2_f_mux[] = {
+	MSIOF1_SS2_F_MARK,
+};
+static const unsigned int msiof1_txd_f_pins[] = {
+	/* TXD */
+	RCAR_GP_PIN(6, 0),
+};
+static const unsigned int msiof1_txd_f_mux[] = {
+	MSIOF1_TXD_F_MARK,
+};
+static const unsigned int msiof1_rxd_f_pins[] = {
+	/* RXD */
+	RCAR_GP_PIN(5, 25),
+};
+static const unsigned int msiof1_rxd_f_mux[] = {
+	MSIOF1_RXD_F_MARK,
+};
+static const unsigned int msiof1_clk_g_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(3, 6),
+};
+static const unsigned int msiof1_clk_g_mux[] = {
+	MSIOF1_SCK_G_MARK,
+};
+static const unsigned int msiof1_sync_g_pins[] = {
+	/* SYNC */
+	RCAR_GP_PIN(3, 7),
+};
+static const unsigned int msiof1_sync_g_mux[] = {
+	MSIOF1_SYNC_G_MARK,
+};
+static const unsigned int msiof1_ss1_g_pins[] = {
+	/* SS1 */
+	RCAR_GP_PIN(3, 10),
+};
+static const unsigned int msiof1_ss1_g_mux[] = {
+	MSIOF1_SS1_G_MARK,
+};
+static const unsigned int msiof1_ss2_g_pins[] = {
+	/* SS2 */
+	RCAR_GP_PIN(3, 11),
+};
+static const unsigned int msiof1_ss2_g_mux[] = {
+	MSIOF1_SS2_G_MARK,
+};
+static const unsigned int msiof1_txd_g_pins[] = {
+	/* TXD */
+	RCAR_GP_PIN(3, 9),
+};
+static const unsigned int msiof1_txd_g_mux[] = {
+	MSIOF1_TXD_G_MARK,
+};
+static const unsigned int msiof1_rxd_g_pins[] = {
+	/* RXD */
+	RCAR_GP_PIN(3, 8),
+};
+static const unsigned int msiof1_rxd_g_mux[] = {
+	MSIOF1_RXD_G_MARK,
+};
+/* - MSIOF2 ----------------------------------------------------------------- */
+static const unsigned int msiof2_clk_a_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(1, 9),
+};
+static const unsigned int msiof2_clk_a_mux[] = {
+	MSIOF2_SCK_A_MARK,
+};
+static const unsigned int msiof2_sync_a_pins[] = {
+	/* SYNC */
+	RCAR_GP_PIN(1, 8),
+};
+static const unsigned int msiof2_sync_a_mux[] = {
+	MSIOF2_SYNC_A_MARK,
+};
+static const unsigned int msiof2_ss1_a_pins[] = {
+	/* SS1 */
+	RCAR_GP_PIN(1, 6),
+};
+static const unsigned int msiof2_ss1_a_mux[] = {
+	MSIOF2_SS1_A_MARK,
+};
+static const unsigned int msiof2_ss2_a_pins[] = {
+	/* SS2 */
+	RCAR_GP_PIN(1, 7),
+};
+static const unsigned int msiof2_ss2_a_mux[] = {
+	MSIOF2_SS2_A_MARK,
+};
+static const unsigned int msiof2_txd_a_pins[] = {
+	/* TXD */
+	RCAR_GP_PIN(1, 11),
+};
+static const unsigned int msiof2_txd_a_mux[] = {
+	MSIOF2_TXD_A_MARK,
+};
+static const unsigned int msiof2_rxd_a_pins[] = {
+	/* RXD */
+	RCAR_GP_PIN(1, 10),
+};
+static const unsigned int msiof2_rxd_a_mux[] = {
+	MSIOF2_RXD_A_MARK,
+};
+static const unsigned int msiof2_clk_b_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(0, 4),
+};
+static const unsigned int msiof2_clk_b_mux[] = {
+	MSIOF2_SCK_B_MARK,
+};
+static const unsigned int msiof2_sync_b_pins[] = {
+	/* SYNC */
+	RCAR_GP_PIN(0, 5),
+};
+static const unsigned int msiof2_sync_b_mux[] = {
+	MSIOF2_SYNC_B_MARK,
+};
+static const unsigned int msiof2_ss1_b_pins[] = {
+	/* SS1 */
+	RCAR_GP_PIN(0, 0),
+};
+static const unsigned int msiof2_ss1_b_mux[] = {
+	MSIOF2_SS1_B_MARK,
+};
+static const unsigned int msiof2_ss2_b_pins[] = {
+	/* SS2 */
+	RCAR_GP_PIN(0, 1),
+};
+static const unsigned int msiof2_ss2_b_mux[] = {
+	MSIOF2_SS2_B_MARK,
+};
+static const unsigned int msiof2_txd_b_pins[] = {
+	/* TXD */
+	RCAR_GP_PIN(0, 7),
+};
+static const unsigned int msiof2_txd_b_mux[] = {
+	MSIOF2_TXD_B_MARK,
+};
+static const unsigned int msiof2_rxd_b_pins[] = {
+	/* RXD */
+	RCAR_GP_PIN(0, 6),
+};
+static const unsigned int msiof2_rxd_b_mux[] = {
+	MSIOF2_RXD_B_MARK,
+};
+static const unsigned int msiof2_clk_c_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(2, 12),
+};
+static const unsigned int msiof2_clk_c_mux[] = {
+	MSIOF2_SCK_C_MARK,
+};
+static const unsigned int msiof2_sync_c_pins[] = {
+	/* SYNC */
+	RCAR_GP_PIN(2, 11),
+};
+static const unsigned int msiof2_sync_c_mux[] = {
+	MSIOF2_SYNC_C_MARK,
+};
+static const unsigned int msiof2_ss1_c_pins[] = {
+	/* SS1 */
+	RCAR_GP_PIN(2, 10),
+};
+static const unsigned int msiof2_ss1_c_mux[] = {
+	MSIOF2_SS1_C_MARK,
+};
+static const unsigned int msiof2_ss2_c_pins[] = {
+	/* SS2 */
+	RCAR_GP_PIN(2, 9),
+};
+static const unsigned int msiof2_ss2_c_mux[] = {
+	MSIOF2_SS2_C_MARK,
+};
+static const unsigned int msiof2_txd_c_pins[] = {
+	/* TXD */
+	RCAR_GP_PIN(2, 14),
+};
+static const unsigned int msiof2_txd_c_mux[] = {
+	MSIOF2_TXD_C_MARK,
+};
+static const unsigned int msiof2_rxd_c_pins[] = {
+	/* RXD */
+	RCAR_GP_PIN(2, 13),
+};
+static const unsigned int msiof2_rxd_c_mux[] = {
+	MSIOF2_RXD_C_MARK,
+};
+static const unsigned int msiof2_clk_d_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(0, 8),
+};
+static const unsigned int msiof2_clk_d_mux[] = {
+	MSIOF2_SCK_D_MARK,
+};
+static const unsigned int msiof2_sync_d_pins[] = {
+	/* SYNC */
+	RCAR_GP_PIN(0, 9),
+};
+static const unsigned int msiof2_sync_d_mux[] = {
+	MSIOF2_SYNC_D_MARK,
+};
+static const unsigned int msiof2_ss1_d_pins[] = {
+	/* SS1 */
+	RCAR_GP_PIN(0, 12),
+};
+static const unsigned int msiof2_ss1_d_mux[] = {
+	MSIOF2_SS1_D_MARK,
+};
+static const unsigned int msiof2_ss2_d_pins[] = {
+	/* SS2 */
+	RCAR_GP_PIN(0, 13),
+};
+static const unsigned int msiof2_ss2_d_mux[] = {
+	MSIOF2_SS2_D_MARK,
+};
+static const unsigned int msiof2_txd_d_pins[] = {
+	/* TXD */
+	RCAR_GP_PIN(0, 11),
+};
+static const unsigned int msiof2_txd_d_mux[] = {
+	MSIOF2_TXD_D_MARK,
+};
+static const unsigned int msiof2_rxd_d_pins[] = {
+	/* RXD */
+	RCAR_GP_PIN(0, 10),
+};
+static const unsigned int msiof2_rxd_d_mux[] = {
+	MSIOF2_RXD_D_MARK,
+};
+/* - MSIOF3 ----------------------------------------------------------------- */
+static const unsigned int msiof3_clk_a_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(0, 0),
+};
+static const unsigned int msiof3_clk_a_mux[] = {
+	MSIOF3_SCK_A_MARK,
+};
+static const unsigned int msiof3_sync_a_pins[] = {
+	/* SYNC */
+	RCAR_GP_PIN(0, 1),
+};
+static const unsigned int msiof3_sync_a_mux[] = {
+	MSIOF3_SYNC_A_MARK,
+};
+static const unsigned int msiof3_ss1_a_pins[] = {
+	/* SS1 */
+	RCAR_GP_PIN(0, 14),
+};
+static const unsigned int msiof3_ss1_a_mux[] = {
+	MSIOF3_SS1_A_MARK,
+};
+static const unsigned int msiof3_ss2_a_pins[] = {
+	/* SS2 */
+	RCAR_GP_PIN(0, 15),
+};
+static const unsigned int msiof3_ss2_a_mux[] = {
+	MSIOF3_SS2_A_MARK,
+};
+static const unsigned int msiof3_txd_a_pins[] = {
+	/* TXD */
+	RCAR_GP_PIN(0, 3),
+};
+static const unsigned int msiof3_txd_a_mux[] = {
+	MSIOF3_TXD_A_MARK,
+};
+static const unsigned int msiof3_rxd_a_pins[] = {
+	/* RXD */
+	RCAR_GP_PIN(0, 2),
+};
+static const unsigned int msiof3_rxd_a_mux[] = {
+	MSIOF3_RXD_A_MARK,
+};
+static const unsigned int msiof3_clk_b_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(1, 2),
+};
+static const unsigned int msiof3_clk_b_mux[] = {
+	MSIOF3_SCK_B_MARK,
+};
+static const unsigned int msiof3_sync_b_pins[] = {
+	/* SYNC */
+	RCAR_GP_PIN(1, 0),
+};
+static const unsigned int msiof3_sync_b_mux[] = {
+	MSIOF3_SYNC_B_MARK,
+};
+static const unsigned int msiof3_ss1_b_pins[] = {
+	/* SS1 */
+	RCAR_GP_PIN(1, 4),
+};
+static const unsigned int msiof3_ss1_b_mux[] = {
+	MSIOF3_SS1_B_MARK,
+};
+static const unsigned int msiof3_ss2_b_pins[] = {
+	/* SS2 */
+	RCAR_GP_PIN(1, 5),
+};
+static const unsigned int msiof3_ss2_b_mux[] = {
+	MSIOF3_SS2_B_MARK,
+};
+static const unsigned int msiof3_txd_b_pins[] = {
+	/* TXD */
+	RCAR_GP_PIN(1, 1),
+};
+static const unsigned int msiof3_txd_b_mux[] = {
+	MSIOF3_TXD_B_MARK,
+};
+static const unsigned int msiof3_rxd_b_pins[] = {
+	/* RXD */
+	RCAR_GP_PIN(1, 3),
+};
+static const unsigned int msiof3_rxd_b_mux[] = {
+	MSIOF3_RXD_B_MARK,
+};
+static const unsigned int msiof3_clk_c_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(1, 12),
+};
+static const unsigned int msiof3_clk_c_mux[] = {
+	MSIOF3_SCK_C_MARK,
+};
+static const unsigned int msiof3_sync_c_pins[] = {
+	/* SYNC */
+	RCAR_GP_PIN(1, 13),
+};
+static const unsigned int msiof3_sync_c_mux[] = {
+	MSIOF3_SYNC_C_MARK,
+};
+static const unsigned int msiof3_txd_c_pins[] = {
+	/* TXD */
+	RCAR_GP_PIN(1, 15),
+};
+static const unsigned int msiof3_txd_c_mux[] = {
+	MSIOF3_TXD_C_MARK,
+};
+static const unsigned int msiof3_rxd_c_pins[] = {
+	/* RXD */
+	RCAR_GP_PIN(1, 14),
+};
+static const unsigned int msiof3_rxd_c_mux[] = {
+	MSIOF3_RXD_C_MARK,
+};
+static const unsigned int msiof3_clk_d_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(1, 22),
+};
+static const unsigned int msiof3_clk_d_mux[] = {
+	MSIOF3_SCK_D_MARK,
+};
+static const unsigned int msiof3_sync_d_pins[] = {
+	/* SYNC */
+	RCAR_GP_PIN(1, 23),
+};
+static const unsigned int msiof3_sync_d_mux[] = {
+	MSIOF3_SYNC_D_MARK,
+};
+static const unsigned int msiof3_ss1_d_pins[] = {
+	/* SS1 */
+	RCAR_GP_PIN(1, 26),
+};
+static const unsigned int msiof3_ss1_d_mux[] = {
+	MSIOF3_SS1_D_MARK,
+};
+static const unsigned int msiof3_txd_d_pins[] = {
+	/* TXD */
+	RCAR_GP_PIN(1, 25),
+};
+static const unsigned int msiof3_txd_d_mux[] = {
+	MSIOF3_TXD_D_MARK,
+};
+static const unsigned int msiof3_rxd_d_pins[] = {
+	/* RXD */
+	RCAR_GP_PIN(1, 24),
+};
+static const unsigned int msiof3_rxd_d_mux[] = {
+	MSIOF3_RXD_D_MARK,
+};
+
+/* - SATA --------------------------------------------------------------------*/
+static const unsigned int sata0_devslp_a_pins[] = {
+	/* DEVSLP */
+	RCAR_GP_PIN(6, 16),
+};
+static const unsigned int sata0_devslp_a_mux[] = {
+	SATA_DEVSLP_A_MARK,
+};
+static const unsigned int sata0_devslp_b_pins[] = {
+	/* DEVSLP */
+	RCAR_GP_PIN(4, 6),
+};
+static const unsigned int sata0_devslp_b_mux[] = {
+	SATA_DEVSLP_B_MARK,
+};
+
 /* - SCIF0 ------------------------------------------------------------------ */
 static const unsigned int scif0_data_pins[] = {
 	/* RX, TX */
@@ -1845,6 +2690,228 @@
 static const unsigned int scif5_clk_mux[] = {
 	SCK5_MARK,
 };
+/* - SDHI0 ------------------------------------------------------------------ */
+static const unsigned int sdhi0_data1_pins[] = {
+	/* D0 */
+	RCAR_GP_PIN(3, 2),
+};
+static const unsigned int sdhi0_data1_mux[] = {
+	SD0_DAT0_MARK,
+};
+static const unsigned int sdhi0_data4_pins[] = {
+	/* D[0:3] */
+	RCAR_GP_PIN(3, 2), RCAR_GP_PIN(3, 3),
+	RCAR_GP_PIN(3, 4), RCAR_GP_PIN(3, 5),
+};
+static const unsigned int sdhi0_data4_mux[] = {
+	SD0_DAT0_MARK, SD0_DAT1_MARK,
+	SD0_DAT2_MARK, SD0_DAT3_MARK,
+};
+static const unsigned int sdhi0_ctrl_pins[] = {
+	/* CLK, CMD */
+	RCAR_GP_PIN(3, 0), RCAR_GP_PIN(3, 1),
+};
+static const unsigned int sdhi0_ctrl_mux[] = {
+	SD0_CLK_MARK, SD0_CMD_MARK,
+};
+static const unsigned int sdhi0_cd_pins[] = {
+	/* CD */
+	RCAR_GP_PIN(3, 12),
+};
+static const unsigned int sdhi0_cd_mux[] = {
+	SD0_CD_MARK,
+};
+static const unsigned int sdhi0_wp_pins[] = {
+	/* WP */
+	RCAR_GP_PIN(3, 13),
+};
+static const unsigned int sdhi0_wp_mux[] = {
+	SD0_WP_MARK,
+};
+/* - SDHI1 ------------------------------------------------------------------ */
+static const unsigned int sdhi1_data1_pins[] = {
+	/* D0 */
+	RCAR_GP_PIN(3, 8),
+};
+static const unsigned int sdhi1_data1_mux[] = {
+	SD1_DAT0_MARK,
+};
+static const unsigned int sdhi1_data4_pins[] = {
+	/* D[0:3] */
+	RCAR_GP_PIN(3, 8),  RCAR_GP_PIN(3, 9),
+	RCAR_GP_PIN(3, 10), RCAR_GP_PIN(3, 11),
+};
+static const unsigned int sdhi1_data4_mux[] = {
+	SD1_DAT0_MARK, SD1_DAT1_MARK,
+	SD1_DAT2_MARK, SD1_DAT3_MARK,
+};
+static const unsigned int sdhi1_ctrl_pins[] = {
+	/* CLK, CMD */
+	RCAR_GP_PIN(3, 6), RCAR_GP_PIN(3, 7),
+};
+static const unsigned int sdhi1_ctrl_mux[] = {
+	SD1_CLK_MARK, SD1_CMD_MARK,
+};
+static const unsigned int sdhi1_cd_pins[] = {
+	/* CD */
+	RCAR_GP_PIN(3, 14),
+};
+static const unsigned int sdhi1_cd_mux[] = {
+	SD1_CD_MARK,
+};
+static const unsigned int sdhi1_wp_pins[] = {
+	/* WP */
+	RCAR_GP_PIN(3, 15),
+};
+static const unsigned int sdhi1_wp_mux[] = {
+	SD1_WP_MARK,
+};
+/* - SDHI2 ------------------------------------------------------------------ */
+static const unsigned int sdhi2_data1_pins[] = {
+	/* D0 */
+	RCAR_GP_PIN(4, 2),
+};
+static const unsigned int sdhi2_data1_mux[] = {
+	SD2_DAT0_MARK,
+};
+static const unsigned int sdhi2_data4_pins[] = {
+	/* D[0:3] */
+	RCAR_GP_PIN(4, 2), RCAR_GP_PIN(4, 3),
+	RCAR_GP_PIN(4, 4), RCAR_GP_PIN(4, 5),
+};
+static const unsigned int sdhi2_data4_mux[] = {
+	SD2_DAT0_MARK, SD2_DAT1_MARK,
+	SD2_DAT2_MARK, SD2_DAT3_MARK,
+};
+static const unsigned int sdhi2_data8_pins[] = {
+	/* D[0:7] */
+	RCAR_GP_PIN(4, 2),  RCAR_GP_PIN(4, 3),
+	RCAR_GP_PIN(4, 4),  RCAR_GP_PIN(4, 5),
+	RCAR_GP_PIN(3, 8),  RCAR_GP_PIN(3, 9),
+	RCAR_GP_PIN(3, 10), RCAR_GP_PIN(3, 11),
+};
+static const unsigned int sdhi2_data8_mux[] = {
+	SD2_DAT0_MARK, SD2_DAT1_MARK,
+	SD2_DAT2_MARK, SD2_DAT3_MARK,
+	SD2_DAT4_MARK, SD2_DAT5_MARK,
+	SD2_DAT6_MARK, SD2_DAT7_MARK,
+};
+static const unsigned int sdhi2_ctrl_pins[] = {
+	/* CLK, CMD */
+	RCAR_GP_PIN(4, 0), RCAR_GP_PIN(4, 1),
+};
+static const unsigned int sdhi2_ctrl_mux[] = {
+	SD2_CLK_MARK, SD2_CMD_MARK,
+};
+static const unsigned int sdhi2_cd_a_pins[] = {
+	/* CD */
+	RCAR_GP_PIN(4, 13),
+};
+static const unsigned int sdhi2_cd_a_mux[] = {
+	SD2_CD_A_MARK,
+};
+static const unsigned int sdhi2_cd_b_pins[] = {
+	/* CD */
+	RCAR_GP_PIN(5, 10),
+};
+static const unsigned int sdhi2_cd_b_mux[] = {
+	SD2_CD_B_MARK,
+};
+static const unsigned int sdhi2_wp_a_pins[] = {
+	/* WP */
+	RCAR_GP_PIN(4, 14),
+};
+static const unsigned int sdhi2_wp_a_mux[] = {
+	SD2_WP_A_MARK,
+};
+static const unsigned int sdhi2_wp_b_pins[] = {
+	/* WP */
+	RCAR_GP_PIN(5, 11),
+};
+static const unsigned int sdhi2_wp_b_mux[] = {
+	SD2_WP_B_MARK,
+};
+static const unsigned int sdhi2_ds_pins[] = {
+	/* DS */
+	RCAR_GP_PIN(4, 6),
+};
+static const unsigned int sdhi2_ds_mux[] = {
+	SD2_DS_MARK,
+};
+/* - SDHI3 ------------------------------------------------------------------ */
+static const unsigned int sdhi3_data1_pins[] = {
+	/* D0 */
+	RCAR_GP_PIN(4, 9),
+};
+static const unsigned int sdhi3_data1_mux[] = {
+	SD3_DAT0_MARK,
+};
+static const unsigned int sdhi3_data4_pins[] = {
+	/* D[0:3] */
+	RCAR_GP_PIN(4, 9),  RCAR_GP_PIN(4, 10),
+	RCAR_GP_PIN(4, 11), RCAR_GP_PIN(4, 12),
+};
+static const unsigned int sdhi3_data4_mux[] = {
+	SD3_DAT0_MARK, SD3_DAT1_MARK,
+	SD3_DAT2_MARK, SD3_DAT3_MARK,
+};
+static const unsigned int sdhi3_data8_pins[] = {
+	/* D[0:7] */
+	RCAR_GP_PIN(4, 9),  RCAR_GP_PIN(4, 10),
+	RCAR_GP_PIN(4, 11), RCAR_GP_PIN(4, 12),
+	RCAR_GP_PIN(4, 13), RCAR_GP_PIN(4, 14),
+	RCAR_GP_PIN(4, 15), RCAR_GP_PIN(4, 16),
+};
+static const unsigned int sdhi3_data8_mux[] = {
+	SD3_DAT0_MARK, SD3_DAT1_MARK,
+	SD3_DAT2_MARK, SD3_DAT3_MARK,
+	SD3_DAT4_MARK, SD3_DAT5_MARK,
+	SD3_DAT6_MARK, SD3_DAT7_MARK,
+};
+static const unsigned int sdhi3_ctrl_pins[] = {
+	/* CLK, CMD */
+	RCAR_GP_PIN(4, 7), RCAR_GP_PIN(4, 8),
+};
+static const unsigned int sdhi3_ctrl_mux[] = {
+	SD3_CLK_MARK, SD3_CMD_MARK,
+};
+static const unsigned int sdhi3_cd_pins[] = {
+	/* CD */
+	RCAR_GP_PIN(4, 15),
+};
+static const unsigned int sdhi3_cd_mux[] = {
+	SD3_CD_MARK,
+};
+static const unsigned int sdhi3_wp_pins[] = {
+	/* WP */
+	RCAR_GP_PIN(4, 16),
+};
+static const unsigned int sdhi3_wp_mux[] = {
+	SD3_WP_MARK,
+};
+static const unsigned int sdhi3_ds_pins[] = {
+	/* DS */
+	RCAR_GP_PIN(4, 17),
+};
+static const unsigned int sdhi3_ds_mux[] = {
+	SD3_DS_MARK,
+};
+
+/* - SCIF Clock ------------------------------------------------------------- */
+static const unsigned int scif_clk_a_pins[] = {
+	/* SCIF_CLK */
+	RCAR_GP_PIN(6, 23),
+};
+static const unsigned int scif_clk_a_mux[] = {
+	SCIF_CLK_A_MARK,
+};
+static const unsigned int scif_clk_b_pins[] = {
+	/* SCIF_CLK */
+	RCAR_GP_PIN(5, 9),
+};
+static const unsigned int scif_clk_b_mux[] = {
+	SCIF_CLK_B_MARK,
+};
 
 /* - SSI -------------------------------------------------------------------- */
 static const unsigned int ssi0_data_pins[] = {
@@ -2050,6 +3117,31 @@
 	SH_PFC_PIN_GROUP(avb_avtp_capture_a),
 	SH_PFC_PIN_GROUP(avb_avtp_match_b),
 	SH_PFC_PIN_GROUP(avb_avtp_capture_b),
+	SH_PFC_PIN_GROUP(hscif0_data),
+	SH_PFC_PIN_GROUP(hscif0_clk),
+	SH_PFC_PIN_GROUP(hscif0_ctrl),
+	SH_PFC_PIN_GROUP(hscif1_data_a),
+	SH_PFC_PIN_GROUP(hscif1_clk_a),
+	SH_PFC_PIN_GROUP(hscif1_ctrl_a),
+	SH_PFC_PIN_GROUP(hscif1_data_b),
+	SH_PFC_PIN_GROUP(hscif1_clk_b),
+	SH_PFC_PIN_GROUP(hscif1_ctrl_b),
+	SH_PFC_PIN_GROUP(hscif2_data_a),
+	SH_PFC_PIN_GROUP(hscif2_clk_a),
+	SH_PFC_PIN_GROUP(hscif2_ctrl_a),
+	SH_PFC_PIN_GROUP(hscif2_data_b),
+	SH_PFC_PIN_GROUP(hscif2_clk_b),
+	SH_PFC_PIN_GROUP(hscif2_ctrl_b),
+	SH_PFC_PIN_GROUP(hscif3_data_a),
+	SH_PFC_PIN_GROUP(hscif3_clk),
+	SH_PFC_PIN_GROUP(hscif3_ctrl),
+	SH_PFC_PIN_GROUP(hscif3_data_b),
+	SH_PFC_PIN_GROUP(hscif3_data_c),
+	SH_PFC_PIN_GROUP(hscif3_data_d),
+	SH_PFC_PIN_GROUP(hscif4_data_a),
+	SH_PFC_PIN_GROUP(hscif4_clk),
+	SH_PFC_PIN_GROUP(hscif4_ctrl),
+	SH_PFC_PIN_GROUP(hscif4_data_b),
 	SH_PFC_PIN_GROUP(i2c1_a),
 	SH_PFC_PIN_GROUP(i2c1_b),
 	SH_PFC_PIN_GROUP(i2c2_a),
@@ -2057,6 +3149,101 @@
 	SH_PFC_PIN_GROUP(i2c6_a),
 	SH_PFC_PIN_GROUP(i2c6_b),
 	SH_PFC_PIN_GROUP(i2c6_c),
+	SH_PFC_PIN_GROUP(msiof0_clk),
+	SH_PFC_PIN_GROUP(msiof0_sync),
+	SH_PFC_PIN_GROUP(msiof0_ss1),
+	SH_PFC_PIN_GROUP(msiof0_ss2),
+	SH_PFC_PIN_GROUP(msiof0_txd),
+	SH_PFC_PIN_GROUP(msiof0_rxd),
+	SH_PFC_PIN_GROUP(msiof1_clk_a),
+	SH_PFC_PIN_GROUP(msiof1_sync_a),
+	SH_PFC_PIN_GROUP(msiof1_ss1_a),
+	SH_PFC_PIN_GROUP(msiof1_ss2_a),
+	SH_PFC_PIN_GROUP(msiof1_txd_a),
+	SH_PFC_PIN_GROUP(msiof1_rxd_a),
+	SH_PFC_PIN_GROUP(msiof1_clk_b),
+	SH_PFC_PIN_GROUP(msiof1_sync_b),
+	SH_PFC_PIN_GROUP(msiof1_ss1_b),
+	SH_PFC_PIN_GROUP(msiof1_ss2_b),
+	SH_PFC_PIN_GROUP(msiof1_txd_b),
+	SH_PFC_PIN_GROUP(msiof1_rxd_b),
+	SH_PFC_PIN_GROUP(msiof1_clk_c),
+	SH_PFC_PIN_GROUP(msiof1_sync_c),
+	SH_PFC_PIN_GROUP(msiof1_ss1_c),
+	SH_PFC_PIN_GROUP(msiof1_ss2_c),
+	SH_PFC_PIN_GROUP(msiof1_txd_c),
+	SH_PFC_PIN_GROUP(msiof1_rxd_c),
+	SH_PFC_PIN_GROUP(msiof1_clk_d),
+	SH_PFC_PIN_GROUP(msiof1_sync_d),
+	SH_PFC_PIN_GROUP(msiof1_ss1_d),
+	SH_PFC_PIN_GROUP(msiof1_ss2_d),
+	SH_PFC_PIN_GROUP(msiof1_txd_d),
+	SH_PFC_PIN_GROUP(msiof1_rxd_d),
+	SH_PFC_PIN_GROUP(msiof1_clk_e),
+	SH_PFC_PIN_GROUP(msiof1_sync_e),
+	SH_PFC_PIN_GROUP(msiof1_ss1_e),
+	SH_PFC_PIN_GROUP(msiof1_ss2_e),
+	SH_PFC_PIN_GROUP(msiof1_txd_e),
+	SH_PFC_PIN_GROUP(msiof1_rxd_e),
+	SH_PFC_PIN_GROUP(msiof1_clk_f),
+	SH_PFC_PIN_GROUP(msiof1_sync_f),
+	SH_PFC_PIN_GROUP(msiof1_ss1_f),
+	SH_PFC_PIN_GROUP(msiof1_ss2_f),
+	SH_PFC_PIN_GROUP(msiof1_txd_f),
+	SH_PFC_PIN_GROUP(msiof1_rxd_f),
+	SH_PFC_PIN_GROUP(msiof1_clk_g),
+	SH_PFC_PIN_GROUP(msiof1_sync_g),
+	SH_PFC_PIN_GROUP(msiof1_ss1_g),
+	SH_PFC_PIN_GROUP(msiof1_ss2_g),
+	SH_PFC_PIN_GROUP(msiof1_txd_g),
+	SH_PFC_PIN_GROUP(msiof1_rxd_g),
+	SH_PFC_PIN_GROUP(msiof2_clk_a),
+	SH_PFC_PIN_GROUP(msiof2_sync_a),
+	SH_PFC_PIN_GROUP(msiof2_ss1_a),
+	SH_PFC_PIN_GROUP(msiof2_ss2_a),
+	SH_PFC_PIN_GROUP(msiof2_txd_a),
+	SH_PFC_PIN_GROUP(msiof2_rxd_a),
+	SH_PFC_PIN_GROUP(msiof2_clk_b),
+	SH_PFC_PIN_GROUP(msiof2_sync_b),
+	SH_PFC_PIN_GROUP(msiof2_ss1_b),
+	SH_PFC_PIN_GROUP(msiof2_ss2_b),
+	SH_PFC_PIN_GROUP(msiof2_txd_b),
+	SH_PFC_PIN_GROUP(msiof2_rxd_b),
+	SH_PFC_PIN_GROUP(msiof2_clk_c),
+	SH_PFC_PIN_GROUP(msiof2_sync_c),
+	SH_PFC_PIN_GROUP(msiof2_ss1_c),
+	SH_PFC_PIN_GROUP(msiof2_ss2_c),
+	SH_PFC_PIN_GROUP(msiof2_txd_c),
+	SH_PFC_PIN_GROUP(msiof2_rxd_c),
+	SH_PFC_PIN_GROUP(msiof2_clk_d),
+	SH_PFC_PIN_GROUP(msiof2_sync_d),
+	SH_PFC_PIN_GROUP(msiof2_ss1_d),
+	SH_PFC_PIN_GROUP(msiof2_ss2_d),
+	SH_PFC_PIN_GROUP(msiof2_txd_d),
+	SH_PFC_PIN_GROUP(msiof2_rxd_d),
+	SH_PFC_PIN_GROUP(msiof3_clk_a),
+	SH_PFC_PIN_GROUP(msiof3_sync_a),
+	SH_PFC_PIN_GROUP(msiof3_ss1_a),
+	SH_PFC_PIN_GROUP(msiof3_ss2_a),
+	SH_PFC_PIN_GROUP(msiof3_txd_a),
+	SH_PFC_PIN_GROUP(msiof3_rxd_a),
+	SH_PFC_PIN_GROUP(msiof3_clk_b),
+	SH_PFC_PIN_GROUP(msiof3_sync_b),
+	SH_PFC_PIN_GROUP(msiof3_ss1_b),
+	SH_PFC_PIN_GROUP(msiof3_ss2_b),
+	SH_PFC_PIN_GROUP(msiof3_txd_b),
+	SH_PFC_PIN_GROUP(msiof3_rxd_b),
+	SH_PFC_PIN_GROUP(msiof3_clk_c),
+	SH_PFC_PIN_GROUP(msiof3_sync_c),
+	SH_PFC_PIN_GROUP(msiof3_txd_c),
+	SH_PFC_PIN_GROUP(msiof3_rxd_c),
+	SH_PFC_PIN_GROUP(msiof3_clk_d),
+	SH_PFC_PIN_GROUP(msiof3_sync_d),
+	SH_PFC_PIN_GROUP(msiof3_ss1_d),
+	SH_PFC_PIN_GROUP(msiof3_txd_d),
+	SH_PFC_PIN_GROUP(msiof3_rxd_d),
+	SH_PFC_PIN_GROUP(sata0_devslp_a),
+	SH_PFC_PIN_GROUP(sata0_devslp_b),
 	SH_PFC_PIN_GROUP(scif0_data),
 	SH_PFC_PIN_GROUP(scif0_clk),
 	SH_PFC_PIN_GROUP(scif0_ctrl),
@@ -2082,6 +3269,34 @@
 	SH_PFC_PIN_GROUP(scif4_ctrl_c),
 	SH_PFC_PIN_GROUP(scif5_data),
 	SH_PFC_PIN_GROUP(scif5_clk),
+	SH_PFC_PIN_GROUP(scif_clk_a),
+	SH_PFC_PIN_GROUP(scif_clk_b),
+	SH_PFC_PIN_GROUP(sdhi0_data1),
+	SH_PFC_PIN_GROUP(sdhi0_data4),
+	SH_PFC_PIN_GROUP(sdhi0_ctrl),
+	SH_PFC_PIN_GROUP(sdhi0_cd),
+	SH_PFC_PIN_GROUP(sdhi0_wp),
+	SH_PFC_PIN_GROUP(sdhi1_data1),
+	SH_PFC_PIN_GROUP(sdhi1_data4),
+	SH_PFC_PIN_GROUP(sdhi1_ctrl),
+	SH_PFC_PIN_GROUP(sdhi1_cd),
+	SH_PFC_PIN_GROUP(sdhi1_wp),
+	SH_PFC_PIN_GROUP(sdhi2_data1),
+	SH_PFC_PIN_GROUP(sdhi2_data4),
+	SH_PFC_PIN_GROUP(sdhi2_data8),
+	SH_PFC_PIN_GROUP(sdhi2_ctrl),
+	SH_PFC_PIN_GROUP(sdhi2_cd_a),
+	SH_PFC_PIN_GROUP(sdhi2_wp_a),
+	SH_PFC_PIN_GROUP(sdhi2_cd_b),
+	SH_PFC_PIN_GROUP(sdhi2_wp_b),
+	SH_PFC_PIN_GROUP(sdhi2_ds),
+	SH_PFC_PIN_GROUP(sdhi3_data1),
+	SH_PFC_PIN_GROUP(sdhi3_data4),
+	SH_PFC_PIN_GROUP(sdhi3_data8),
+	SH_PFC_PIN_GROUP(sdhi3_ctrl),
+	SH_PFC_PIN_GROUP(sdhi3_cd),
+	SH_PFC_PIN_GROUP(sdhi3_wp),
+	SH_PFC_PIN_GROUP(sdhi3_ds),
 	SH_PFC_PIN_GROUP(ssi0_data),
 	SH_PFC_PIN_GROUP(ssi01239_ctrl),
 	SH_PFC_PIN_GROUP(ssi1_data_a),
@@ -2141,6 +3356,46 @@
 	"avb_avtp_capture_b",
 };
 
+static const char * const hscif0_groups[] = {
+	"hscif0_data",
+	"hscif0_clk",
+	"hscif0_ctrl",
+};
+
+static const char * const hscif1_groups[] = {
+	"hscif1_data_a",
+	"hscif1_clk_a",
+	"hscif1_ctrl_a",
+	"hscif1_data_b",
+	"hscif1_clk_b",
+	"hscif1_ctrl_b",
+};
+
+static const char * const hscif2_groups[] = {
+	"hscif2_data_a",
+	"hscif2_clk_a",
+	"hscif2_ctrl_a",
+	"hscif2_data_b",
+	"hscif2_clk_b",
+	"hscif2_ctrl_b",
+};
+
+static const char * const hscif3_groups[] = {
+	"hscif3_data_a",
+	"hscif3_clk",
+	"hscif3_ctrl",
+	"hscif3_data_b",
+	"hscif3_data_c",
+	"hscif3_data_d",
+};
+
+static const char * const hscif4_groups[] = {
+	"hscif4_data_a",
+	"hscif4_clk",
+	"hscif4_ctrl",
+	"hscif4_data_b",
+};
+
 static const char * const i2c1_groups[] = {
 	"i2c1_a",
 	"i2c1_b",
@@ -2157,6 +3412,116 @@
 	"i2c6_c",
 };
 
+static const char * const msiof0_groups[] = {
+	"msiof0_clk",
+	"msiof0_sync",
+	"msiof0_ss1",
+	"msiof0_ss2",
+	"msiof0_txd",
+	"msiof0_rxd",
+};
+
+static const char * const msiof1_groups[] = {
+	"msiof1_clk_a",
+	"msiof1_sync_a",
+	"msiof1_ss1_a",
+	"msiof1_ss2_a",
+	"msiof1_txd_a",
+	"msiof1_rxd_a",
+	"msiof1_clk_b",
+	"msiof1_sync_b",
+	"msiof1_ss1_b",
+	"msiof1_ss2_b",
+	"msiof1_txd_b",
+	"msiof1_rxd_b",
+	"msiof1_clk_c",
+	"msiof1_sync_c",
+	"msiof1_ss1_c",
+	"msiof1_ss2_c",
+	"msiof1_txd_c",
+	"msiof1_rxd_c",
+	"msiof1_clk_d",
+	"msiof1_sync_d",
+	"msiof1_ss1_d",
+	"msiof1_ss2_d",
+	"msiof1_txd_d",
+	"msiof1_rxd_d",
+	"msiof1_clk_e",
+	"msiof1_sync_e",
+	"msiof1_ss1_e",
+	"msiof1_ss2_e",
+	"msiof1_txd_e",
+	"msiof1_rxd_e",
+	"msiof1_clk_f",
+	"msiof1_sync_f",
+	"msiof1_ss1_f",
+	"msiof1_ss2_f",
+	"msiof1_txd_f",
+	"msiof1_rxd_f",
+	"msiof1_clk_g",
+	"msiof1_sync_g",
+	"msiof1_ss1_g",
+	"msiof1_ss2_g",
+	"msiof1_txd_g",
+	"msiof1_rxd_g",
+};
+
+static const char * const msiof2_groups[] = {
+	"msiof2_clk_a",
+	"msiof2_sync_a",
+	"msiof2_ss1_a",
+	"msiof2_ss2_a",
+	"msiof2_txd_a",
+	"msiof2_rxd_a",
+	"msiof2_clk_b",
+	"msiof2_sync_b",
+	"msiof2_ss1_b",
+	"msiof2_ss2_b",
+	"msiof2_txd_b",
+	"msiof2_rxd_b",
+	"msiof2_clk_c",
+	"msiof2_sync_c",
+	"msiof2_ss1_c",
+	"msiof2_ss2_c",
+	"msiof2_txd_c",
+	"msiof2_rxd_c",
+	"msiof2_clk_d",
+	"msiof2_sync_d",
+	"msiof2_ss1_d",
+	"msiof2_ss2_d",
+	"msiof2_txd_d",
+	"msiof2_rxd_d",
+};
+
+static const char * const msiof3_groups[] = {
+	"msiof3_clk_a",
+	"msiof3_sync_a",
+	"msiof3_ss1_a",
+	"msiof3_ss2_a",
+	"msiof3_txd_a",
+	"msiof3_rxd_a",
+	"msiof3_clk_b",
+	"msiof3_sync_b",
+	"msiof3_ss1_b",
+	"msiof3_ss2_b",
+	"msiof3_txd_b",
+	"msiof3_rxd_b",
+	"msiof3_clk_c",
+	"msiof3_sync_c",
+	"msiof3_txd_c",
+	"msiof3_rxd_c",
+	"msiof3_clk_d",
+	"msiof3_sync_d",
+	"msiof3_ss1_d",
+	"msiof3_txd_d",
+	"msiof3_rxd_d",
+};
+
+static const char * const sata0_groups[] = {
+	"sata0_devslp_a",
+	"sata0_devslp_b",
+};
+
 static const char * const scif0_groups[] = {
 	"scif0_data",
 	"scif0_clk",
@@ -2200,6 +3565,49 @@
 	"scif5_clk",
 };
 
+static const char * const scif_clk_groups[] = {
+	"scif_clk_a",
+	"scif_clk_b",
+};
+
+static const char * const sdhi0_groups[] = {
+	"sdhi0_data1",
+	"sdhi0_data4",
+	"sdhi0_ctrl",
+	"sdhi0_cd",
+	"sdhi0_wp",
+};
+
+static const char * const sdhi1_groups[] = {
+	"sdhi1_data1",
+	"sdhi1_data4",
+	"sdhi1_ctrl",
+	"sdhi1_cd",
+	"sdhi1_wp",
+};
+
+static const char * const sdhi2_groups[] = {
+	"sdhi2_data1",
+	"sdhi2_data4",
+	"sdhi2_data8",
+	"sdhi2_ctrl",
+	"sdhi2_cd_a",
+	"sdhi2_wp_a",
+	"sdhi2_cd_b",
+	"sdhi2_wp_b",
+	"sdhi2_ds",
+};
+
+static const char * const sdhi3_groups[] = {
+	"sdhi3_data1",
+	"sdhi3_data4",
+	"sdhi3_data8",
+	"sdhi3_ctrl",
+	"sdhi3_cd",
+	"sdhi3_wp",
+	"sdhi3_ds",
+};
+
 static const char * const ssi_groups[] = {
 	"ssi0_data",
 	"ssi01239_ctrl",
@@ -2231,15 +3639,30 @@
 static const struct sh_pfc_function pinmux_functions[] = {
 	SH_PFC_FUNCTION(audio_clk),
 	SH_PFC_FUNCTION(avb),
+	SH_PFC_FUNCTION(hscif0),
+	SH_PFC_FUNCTION(hscif1),
+	SH_PFC_FUNCTION(hscif2),
+	SH_PFC_FUNCTION(hscif3),
+	SH_PFC_FUNCTION(hscif4),
 	SH_PFC_FUNCTION(i2c1),
 	SH_PFC_FUNCTION(i2c2),
 	SH_PFC_FUNCTION(i2c6),
+	SH_PFC_FUNCTION(msiof0),
+	SH_PFC_FUNCTION(msiof1),
+	SH_PFC_FUNCTION(msiof2),
+	SH_PFC_FUNCTION(msiof3),
+	SH_PFC_FUNCTION(sata0),
 	SH_PFC_FUNCTION(scif0),
 	SH_PFC_FUNCTION(scif1),
 	SH_PFC_FUNCTION(scif2),
 	SH_PFC_FUNCTION(scif3),
 	SH_PFC_FUNCTION(scif4),
 	SH_PFC_FUNCTION(scif5),
+	SH_PFC_FUNCTION(scif_clk),
+	SH_PFC_FUNCTION(sdhi0),
+	SH_PFC_FUNCTION(sdhi1),
+	SH_PFC_FUNCTION(sdhi2),
+	SH_PFC_FUNCTION(sdhi3),
 	SH_PFC_FUNCTION(ssi),
 };
 
diff --git a/drivers/pinctrl/sh-pfc/pfc-sh73a0.c b/drivers/pinctrl/sh-pfc/pfc-sh73a0.c
index 6a69c8c..d25e6f6 100644
--- a/drivers/pinctrl/sh-pfc/pfc-sh73a0.c
+++ b/drivers/pinctrl/sh-pfc/pfc-sh73a0.c
@@ -2059,7 +2059,7 @@
 	LCD2D8_MARK,
 };
 static const unsigned int lcd2_data12_pins[] = {
-	/* D[0:12] */
+	/* D[0:11] */
 	128, 129, 142, 143, 144, 145, 138, 139,
 	140, 141, 130, 131,
 };
@@ -2198,6 +2198,420 @@
 static const unsigned int mmc0_ctrl_1_mux[] = {
 	MMCCMD1_MARK, MMCCLK1_MARK,
 };
+/* - MSIOF0 ----------------------------------------------------------------- */
+static const unsigned int msiof0_rsck_pins[] = {
+	/* RSCK */
+	66,
+};
+static const unsigned int msiof0_rsck_mux[] = {
+	MSIOF0_RSCK_MARK,
+};
+static const unsigned int msiof0_tsck_pins[] = {
+	/* TSCK */
+	64,
+};
+static const unsigned int msiof0_tsck_mux[] = {
+	MSIOF0_TSCK_MARK,
+};
+static const unsigned int msiof0_rsync_pins[] = {
+	/* RSYNC */
+	67,
+};
+static const unsigned int msiof0_rsync_mux[] = {
+	MSIOF0_RSYNC_MARK,
+};
+static const unsigned int msiof0_tsync_pins[] = {
+	/* TSYNC */
+	63,
+};
+static const unsigned int msiof0_tsync_mux[] = {
+	MSIOF0_TSYNC_MARK,
+};
+static const unsigned int msiof0_ss1_pins[] = {
+	/* SS1 */
+	62,
+};
+static const unsigned int msiof0_ss1_mux[] = {
+	MSIOF0_SS1_MARK,
+};
+static const unsigned int msiof0_ss2_pins[] = {
+	/* SS2 */
+	71,
+};
+static const unsigned int msiof0_ss2_mux[] = {
+	MSIOF0_SS2_MARK,
+};
+static const unsigned int msiof0_rxd_pins[] = {
+	/* RXD */
+	70,
+};
+static const unsigned int msiof0_rxd_mux[] = {
+	MSIOF0_RXD_MARK,
+};
+static const unsigned int msiof0_txd_pins[] = {
+	/* TXD */
+	65,
+};
+static const unsigned int msiof0_txd_mux[] = {
+	MSIOF0_TXD_MARK,
+};
+static const unsigned int msiof0_mck0_pins[] = {
+	/* MSCK0 */
+	68,
+};
+static const unsigned int msiof0_mck0_mux[] = {
+	MSIOF0_MCK0_MARK,
+};
+
+static const unsigned int msiof0_mck1_pins[] = {
+	/* MSCK1 */
+	69,
+};
+static const unsigned int msiof0_mck1_mux[] = {
+	MSIOF0_MCK1_MARK,
+};
+
+static const unsigned int msiof0l_rsck_pins[] = {
+	/* RSCK */
+	214,
+};
+static const unsigned int msiof0l_rsck_mux[] = {
+	MSIOF0L_RSCK_MARK,
+};
+static const unsigned int msiof0l_tsck_pins[] = {
+	/* TSCK */
+	219,
+};
+static const unsigned int msiof0l_tsck_mux[] = {
+	MSIOF0L_TSCK_MARK,
+};
+static const unsigned int msiof0l_rsync_pins[] = {
+	/* RSYNC */
+	215,
+};
+static const unsigned int msiof0l_rsync_mux[] = {
+	MSIOF0L_RSYNC_MARK,
+};
+static const unsigned int msiof0l_tsync_pins[] = {
+	/* TSYNC */
+	217,
+};
+static const unsigned int msiof0l_tsync_mux[] = {
+	MSIOF0L_TSYNC_MARK,
+};
+static const unsigned int msiof0l_ss1_a_pins[] = {
+	/* SS1 */
+	207,
+};
+static const unsigned int msiof0l_ss1_a_mux[] = {
+	PORT207_MSIOF0L_SS1_MARK,
+};
+static const unsigned int msiof0l_ss1_b_pins[] = {
+	/* SS1 */
+	210,
+};
+static const unsigned int msiof0l_ss1_b_mux[] = {
+	PORT210_MSIOF0L_SS1_MARK,
+};
+static const unsigned int msiof0l_ss2_a_pins[] = {
+	/* SS2 */
+	208,
+};
+static const unsigned int msiof0l_ss2_a_mux[] = {
+	PORT208_MSIOF0L_SS2_MARK,
+};
+static const unsigned int msiof0l_ss2_b_pins[] = {
+	/* SS2 */
+	211,
+};
+static const unsigned int msiof0l_ss2_b_mux[] = {
+	PORT211_MSIOF0L_SS2_MARK,
+};
+static const unsigned int msiof0l_rxd_pins[] = {
+	/* RXD */
+	221,
+};
+static const unsigned int msiof0l_rxd_mux[] = {
+	MSIOF0L_RXD_MARK,
+};
+static const unsigned int msiof0l_txd_pins[] = {
+	/* TXD */
+	222,
+};
+static const unsigned int msiof0l_txd_mux[] = {
+	MSIOF0L_TXD_MARK,
+};
+static const unsigned int msiof0l_mck0_pins[] = {
+	/* MSCK0 */
+	212,
+};
+static const unsigned int msiof0l_mck0_mux[] = {
+	MSIOF0L_MCK0_MARK,
+};
+static const unsigned int msiof0l_mck1_pins[] = {
+	/* MSCK1 */
+	213,
+};
+static const unsigned int msiof0l_mck1_mux[] = {
+	MSIOF0L_MCK1_MARK,
+};
+/* - MSIOF1 ----------------------------------------------------------------- */
+static const unsigned int msiof1_rsck_pins[] = {
+	/* RSCK */
+	234,
+};
+static const unsigned int msiof1_rsck_mux[] = {
+	MSIOF1_RSCK_MARK,
+};
+static const unsigned int msiof1_tsck_pins[] = {
+	/* TSCK */
+	232,
+};
+static const unsigned int msiof1_tsck_mux[] = {
+	MSIOF1_TSCK_MARK,
+};
+static const unsigned int msiof1_rsync_pins[] = {
+	/* RSYNC */
+	235,
+};
+static const unsigned int msiof1_rsync_mux[] = {
+	MSIOF1_RSYNC_MARK,
+};
+static const unsigned int msiof1_tsync_pins[] = {
+	/* TSYNC */
+	231,
+};
+static const unsigned int msiof1_tsync_mux[] = {
+	MSIOF1_TSYNC_MARK,
+};
+static const unsigned int msiof1_ss1_pins[] = {
+	/* SS1 */
+	238,
+};
+static const unsigned int msiof1_ss1_mux[] = {
+	MSIOF1_SS1_MARK,
+};
+static const unsigned int msiof1_ss2_pins[] = {
+	/* SS2 */
+	239,
+};
+static const unsigned int msiof1_ss2_mux[] = {
+	MSIOF1_SS2_MARK,
+};
+static const unsigned int msiof1_rxd_pins[] = {
+	/* RXD */
+	233,
+};
+static const unsigned int msiof1_rxd_mux[] = {
+	MSIOF1_RXD_MARK,
+};
+static const unsigned int msiof1_txd_pins[] = {
+	/* TXD */
+	230,
+};
+static const unsigned int msiof1_txd_mux[] = {
+	MSIOF1_TXD_MARK,
+};
+static const unsigned int msiof1_mck0_pins[] = {
+	/* MSCK0 */
+	236,
+};
+static const unsigned int msiof1_mck0_mux[] = {
+	MSIOF1_MCK0_MARK,
+};
+static const unsigned int msiof1_mck1_pins[] = {
+	/* MSCK1 */
+	237,
+};
+static const unsigned int msiof1_mck1_mux[] = {
+	MSIOF1_MCK1_MARK,
+};
+/* - MSIOF2 ----------------------------------------------------------------- */
+static const unsigned int msiof2_rsck_pins[] = {
+	/* RSCK */
+	151,
+};
+static const unsigned int msiof2_rsck_mux[] = {
+	MSIOF2_RSCK_MARK,
+};
+static const unsigned int msiof2_tsck_pins[] = {
+	/* TSCK */
+	135,
+};
+static const unsigned int msiof2_tsck_mux[] = {
+	MSIOF2_TSCK_MARK,
+};
+static const unsigned int msiof2_rsync_pins[] = {
+	/* RSYNC */
+	152,
+};
+static const unsigned int msiof2_rsync_mux[] = {
+	MSIOF2_RSYNC_MARK,
+};
+static const unsigned int msiof2_tsync_pins[] = {
+	/* TSYNC */
+	133,
+};
+static const unsigned int msiof2_tsync_mux[] = {
+	MSIOF2_TSYNC_MARK,
+};
+static const unsigned int msiof2_ss1_a_pins[] = {
+	/* SS1 */
+	131,
+};
+static const unsigned int msiof2_ss1_a_mux[] = {
+	PORT131_MSIOF2_SS1_MARK,
+};
+static const unsigned int msiof2_ss1_b_pins[] = {
+	/* SS1 */
+	153,
+};
+static const unsigned int msiof2_ss1_b_mux[] = {
+	PORT153_MSIOF2_SS1_MARK,
+};
+static const unsigned int msiof2_ss2_a_pins[] = {
+	/* SS2 */
+	132,
+};
+static const unsigned int msiof2_ss2_a_mux[] = {
+	PORT132_MSIOF2_SS2_MARK,
+};
+static const unsigned int msiof2_ss2_b_pins[] = {
+	/* SS2 */
+	156,
+};
+static const unsigned int msiof2_ss2_b_mux[] = {
+	PORT156_MSIOF2_SS2_MARK,
+};
+static const unsigned int msiof2_rxd_a_pins[] = {
+	/* RXD */
+	130,
+};
+static const unsigned int msiof2_rxd_a_mux[] = {
+	PORT130_MSIOF2_RXD_MARK,
+};
+static const unsigned int msiof2_rxd_b_pins[] = {
+	/* RXD */
+	157,
+};
+static const unsigned int msiof2_rxd_b_mux[] = {
+	PORT157_MSIOF2_RXD_MARK,
+};
+static const unsigned int msiof2_txd_pins[] = {
+	/* TXD */
+	134,
+};
+static const unsigned int msiof2_txd_mux[] = {
+	MSIOF2_TXD_MARK,
+};
+static const unsigned int msiof2_mck0_pins[] = {
+	/* MSCK0 */
+	154,
+};
+static const unsigned int msiof2_mck0_mux[] = {
+	MSIOF2_MCK0_MARK,
+};
+static const unsigned int msiof2_mck1_pins[] = {
+	/* MSCK1 */
+	155,
+};
+static const unsigned int msiof2_mck1_mux[] = {
+	MSIOF2_MCK1_MARK,
+};
+
+static const unsigned int msiof2r_tsck_pins[] = {
+	/* TSCK */
+	248,
+};
+static const unsigned int msiof2r_tsck_mux[] = {
+	MSIOF2R_TSCK_MARK,
+};
+static const unsigned int msiof2r_tsync_pins[] = {
+	/* TSYNC */
+	249,
+};
+static const unsigned int msiof2r_tsync_mux[] = {
+	MSIOF2R_TSYNC_MARK,
+};
+static const unsigned int msiof2r_rxd_pins[] = {
+	/* RXD */
+	244,
+};
+static const unsigned int msiof2r_rxd_mux[] = {
+	MSIOF2R_RXD_MARK,
+};
+static const unsigned int msiof2r_txd_pins[] = {
+	/* TXD */
+	245,
+};
+static const unsigned int msiof2r_txd_mux[] = {
+	MSIOF2R_TXD_MARK,
+};
+/* - MSIOF3 (Pin function name of MSIOF3 is named BBIF1) -------------------- */
+static const unsigned int msiof3_rsck_pins[] = {
+	/* RSCK */
+	115,
+};
+static const unsigned int msiof3_rsck_mux[] = {
+	BBIF1_RSCK_MARK,
+};
+static const unsigned int msiof3_tsck_pins[] = {
+	/* TSCK */
+	112,
+};
+static const unsigned int msiof3_tsck_mux[] = {
+	BBIF1_TSCK_MARK,
+};
+static const unsigned int msiof3_rsync_pins[] = {
+	/* RSYNC */
+	116,
+};
+static const unsigned int msiof3_rsync_mux[] = {
+	BBIF1_RSYNC_MARK,
+};
+static const unsigned int msiof3_tsync_pins[] = {
+	/* TSYNC */
+	113,
+};
+static const unsigned int msiof3_tsync_mux[] = {
+	BBIF1_TSYNC_MARK,
+};
+static const unsigned int msiof3_ss1_pins[] = {
+	/* SS1 */
+	117,
+};
+static const unsigned int msiof3_ss1_mux[] = {
+	BBIF1_SS1_MARK,
+};
+static const unsigned int msiof3_ss2_pins[] = {
+	/* SS2 */
+	109,
+};
+static const unsigned int msiof3_ss2_mux[] = {
+	BBIF1_SS2_MARK,
+};
+static const unsigned int msiof3_rxd_pins[] = {
+	/* RXD */
+	111,
+};
+static const unsigned int msiof3_rxd_mux[] = {
+	BBIF1_RXD_MARK,
+};
+static const unsigned int msiof3_txd_pins[] = {
+	/* TXD */
+	114,
+};
+static const unsigned int msiof3_txd_mux[] = {
+	BBIF1_TXD_MARK,
+};
+static const unsigned int msiof3_flow_pins[] = {
+	/* FLOW */
+	117,
+};
+static const unsigned int msiof3_flow_mux[] = {
+	BBIF1_FLOW_MARK,
+};
+
 /* - SCIFA0 ----------------------------------------------------------------- */
 static const unsigned int scifa0_data_pins[] = {
 	/* RXD, TXD */
@@ -2782,6 +3196,64 @@
 	SH_PFC_PIN_GROUP(mmc0_data4_1),
 	SH_PFC_PIN_GROUP(mmc0_data8_1),
 	SH_PFC_PIN_GROUP(mmc0_ctrl_1),
+	SH_PFC_PIN_GROUP(msiof0_rsck),
+	SH_PFC_PIN_GROUP(msiof0_tsck),
+	SH_PFC_PIN_GROUP(msiof0_rsync),
+	SH_PFC_PIN_GROUP(msiof0_tsync),
+	SH_PFC_PIN_GROUP(msiof0_ss1),
+	SH_PFC_PIN_GROUP(msiof0_ss2),
+	SH_PFC_PIN_GROUP(msiof0_rxd),
+	SH_PFC_PIN_GROUP(msiof0_txd),
+	SH_PFC_PIN_GROUP(msiof0_mck0),
+	SH_PFC_PIN_GROUP(msiof0_mck1),
+	SH_PFC_PIN_GROUP(msiof0l_rsck),
+	SH_PFC_PIN_GROUP(msiof0l_tsck),
+	SH_PFC_PIN_GROUP(msiof0l_rsync),
+	SH_PFC_PIN_GROUP(msiof0l_tsync),
+	SH_PFC_PIN_GROUP(msiof0l_ss1_a),
+	SH_PFC_PIN_GROUP(msiof0l_ss1_b),
+	SH_PFC_PIN_GROUP(msiof0l_ss2_a),
+	SH_PFC_PIN_GROUP(msiof0l_ss2_b),
+	SH_PFC_PIN_GROUP(msiof0l_rxd),
+	SH_PFC_PIN_GROUP(msiof0l_txd),
+	SH_PFC_PIN_GROUP(msiof0l_mck0),
+	SH_PFC_PIN_GROUP(msiof0l_mck1),
+	SH_PFC_PIN_GROUP(msiof1_rsck),
+	SH_PFC_PIN_GROUP(msiof1_tsck),
+	SH_PFC_PIN_GROUP(msiof1_rsync),
+	SH_PFC_PIN_GROUP(msiof1_tsync),
+	SH_PFC_PIN_GROUP(msiof1_ss1),
+	SH_PFC_PIN_GROUP(msiof1_ss2),
+	SH_PFC_PIN_GROUP(msiof1_rxd),
+	SH_PFC_PIN_GROUP(msiof1_txd),
+	SH_PFC_PIN_GROUP(msiof1_mck0),
+	SH_PFC_PIN_GROUP(msiof1_mck1),
+	SH_PFC_PIN_GROUP(msiof2_rsck),
+	SH_PFC_PIN_GROUP(msiof2_tsck),
+	SH_PFC_PIN_GROUP(msiof2_rsync),
+	SH_PFC_PIN_GROUP(msiof2_tsync),
+	SH_PFC_PIN_GROUP(msiof2_ss1_a),
+	SH_PFC_PIN_GROUP(msiof2_ss1_b),
+	SH_PFC_PIN_GROUP(msiof2_ss2_a),
+	SH_PFC_PIN_GROUP(msiof2_ss2_b),
+	SH_PFC_PIN_GROUP(msiof2_rxd_a),
+	SH_PFC_PIN_GROUP(msiof2_rxd_b),
+	SH_PFC_PIN_GROUP(msiof2_txd),
+	SH_PFC_PIN_GROUP(msiof2_mck0),
+	SH_PFC_PIN_GROUP(msiof2_mck1),
+	SH_PFC_PIN_GROUP(msiof2r_tsck),
+	SH_PFC_PIN_GROUP(msiof2r_tsync),
+	SH_PFC_PIN_GROUP(msiof2r_rxd),
+	SH_PFC_PIN_GROUP(msiof2r_txd),
+	SH_PFC_PIN_GROUP(msiof3_rsck),
+	SH_PFC_PIN_GROUP(msiof3_tsck),
+	SH_PFC_PIN_GROUP(msiof3_rsync),
+	SH_PFC_PIN_GROUP(msiof3_tsync),
+	SH_PFC_PIN_GROUP(msiof3_ss1),
+	SH_PFC_PIN_GROUP(msiof3_ss2),
+	SH_PFC_PIN_GROUP(msiof3_rxd),
+	SH_PFC_PIN_GROUP(msiof3_txd),
+	SH_PFC_PIN_GROUP(msiof3_flow),
 	SH_PFC_PIN_GROUP(scifa0_data),
 	SH_PFC_PIN_GROUP(scifa0_clk),
 	SH_PFC_PIN_GROUP(scifa0_ctrl),
@@ -2982,6 +3454,76 @@
 	"mmc0_ctrl_1",
 };
 
+static const char * const msiof0_groups[] = {
+	"msiof0_rsck",
+	"msiof0_tsck",
+	"msiof0_rsync",
+	"msiof0_tsync",
+	"msiof0_ss1",
+	"msiof0_ss2",
+	"msiof0_rxd",
+	"msiof0_txd",
+	"msiof0_mck0",
+	"msiof0_mck1",
+	"msiof0l_rsck",
+	"msiof0l_tsck",
+	"msiof0l_rsync",
+	"msiof0l_tsync",
+	"msiof0l_ss1_a",
+	"msiof0l_ss1_b",
+	"msiof0l_ss2_a",
+	"msiof0l_ss2_b",
+	"msiof0l_rxd",
+	"msiof0l_txd",
+	"msiof0l_mck0",
+	"msiof0l_mck1",
+};
+
+static const char * const msiof1_groups[] = {
+	"msiof1_rsck",
+	"msiof1_tsck",
+	"msiof1_rsync",
+	"msiof1_tsync",
+	"msiof1_ss1",
+	"msiof1_ss2",
+	"msiof1_rxd",
+	"msiof1_txd",
+	"msiof1_mck0",
+	"msiof1_mck1",
+};
+
+static const char * const msiof2_groups[] = {
+	"msiof2_rsck",
+	"msiof2_tsck",
+	"msiof2_rsync",
+	"msiof2_tsync",
+	"msiof2_ss1_a",
+	"msiof2_ss1_b",
+	"msiof2_ss2_a",
+	"msiof2_ss2_b",
+	"msiof2_rxd_a",
+	"msiof2_rxd_b",
+	"msiof2_txd",
+	"msiof2_mck0",
+	"msiof2_mck1",
+	"msiof2r_tsck",
+	"msiof2r_tsync",
+	"msiof2r_rxd",
+	"msiof2r_txd",
+};
+
+static const char * const msiof3_groups[] = {
+	"msiof3_rsck",
+	"msiof3_tsck",
+	"msiof3_rsync",
+	"msiof3_tsync",
+	"msiof3_ss1",
+	"msiof3_ss2",
+	"msiof3_rxd",
+	"msiof3_txd",
+	"msiof3_flow",
+};
+
 static const char * const scifa0_groups[] = {
 	"scifa0_data",
 	"scifa0_clk",
@@ -3116,6 +3658,10 @@
 	SH_PFC_FUNCTION(lcd),
 	SH_PFC_FUNCTION(lcd2),
 	SH_PFC_FUNCTION(mmc0),
+	SH_PFC_FUNCTION(msiof0),
+	SH_PFC_FUNCTION(msiof1),
+	SH_PFC_FUNCTION(msiof2),
+	SH_PFC_FUNCTION(msiof3),
 	SH_PFC_FUNCTION(scifa0),
 	SH_PFC_FUNCTION(scifa1),
 	SH_PFC_FUNCTION(scifa2),
diff --git a/drivers/pinctrl/sh-pfc/pfc-sh7734.c b/drivers/pinctrl/sh-pfc/pfc-sh7734.c
index 9842bb1..b0b328b 100644
--- a/drivers/pinctrl/sh-pfc/pfc-sh7734.c
+++ b/drivers/pinctrl/sh-pfc/pfc-sh7734.c
@@ -14,14 +14,6 @@
 
 #include "sh_pfc.h"
 
-#define PORT_GP_12(bank, fn, sfx)					\
-	PORT_GP_1(bank, 0, fn, sfx),  PORT_GP_1(bank, 1, fn, sfx),	\
-	PORT_GP_1(bank, 2, fn, sfx),  PORT_GP_1(bank, 3, fn, sfx),	\
-	PORT_GP_1(bank, 4, fn, sfx),  PORT_GP_1(bank, 5, fn, sfx),	\
-	PORT_GP_1(bank, 6, fn, sfx),  PORT_GP_1(bank, 7, fn, sfx),	\
-	PORT_GP_1(bank, 8, fn, sfx),  PORT_GP_1(bank, 9, fn, sfx),	\
-	PORT_GP_1(bank, 10, fn, sfx), PORT_GP_1(bank, 11, fn, sfx)
-
 #define CPU_ALL_PORT(fn, sfx)						\
 	PORT_GP_32(0, fn, sfx),						\
 	PORT_GP_32(1, fn, sfx),						\
@@ -585,15 +577,18 @@
 static const u16 pinmux_data[] = {
 	PINMUX_DATA_GP_ALL(), /* PINMUX_DATA(GP_M_N_DATA, GP_M_N_FN...), */
 
-	PINMUX_DATA(CLKOUT_MARK, FN_CLKOUT),
-	PINMUX_DATA(BS_MARK, FN_BS), PINMUX_DATA(CS0_MARK, FN_CS0),
-	PINMUX_DATA(EX_CS0_MARK, FN_EX_CS0),
-	PINMUX_DATA(RD_MARK, FN_RD), PINMUX_DATA(WE0_MARK, FN_WE0),
-	PINMUX_DATA(WE1_MARK, FN_WE1),
-	PINMUX_DATA(SCL0_MARK, FN_SCL0), PINMUX_DATA(PENC0_MARK, FN_PENC0),
-	PINMUX_DATA(USB_OVC0_MARK, FN_USB_OVC0),
-	PINMUX_DATA(IRQ2_B_MARK, FN_IRQ2_B),
-		PINMUX_DATA(IRQ3_B_MARK, FN_IRQ3_B),
+	PINMUX_SINGLE(CLKOUT),
+	PINMUX_SINGLE(BS),
+	PINMUX_SINGLE(CS0),
+	PINMUX_SINGLE(EX_CS0),
+	PINMUX_SINGLE(RD),
+	PINMUX_SINGLE(WE0),
+	PINMUX_SINGLE(WE1),
+	PINMUX_SINGLE(SCL0),
+	PINMUX_SINGLE(PENC0),
+	PINMUX_SINGLE(USB_OVC0),
+	PINMUX_SINGLE(IRQ2_B),
+	PINMUX_SINGLE(IRQ3_B),
 
 	/* IPSR0 */
 	PINMUX_IPSR_DATA(IP0_1_0, A0),
diff --git a/drivers/pinctrl/sh-pfc/pinctrl.c b/drivers/pinctrl/sh-pfc/pinctrl.c
index 863c3e30..87b0a59 100644
--- a/drivers/pinctrl/sh-pfc/pinctrl.c
+++ b/drivers/pinctrl/sh-pfc/pinctrl.c
@@ -273,8 +273,10 @@
 	for_each_child_of_node(np, child) {
 		ret = sh_pfc_dt_subnode_to_map(pctldev, child, map, num_maps,
 					       &index);
-		if (ret < 0)
+		if (ret < 0) {
+			of_node_put(child);
 			goto done;
+		}
 	}
 
 	/* If no mapping has been found in child nodes try the config node. */
diff --git a/drivers/pinctrl/sh-pfc/sh_pfc.h b/drivers/pinctrl/sh-pfc/sh_pfc.h
index 7b373d43..2123ab4 100644
--- a/drivers/pinctrl/sh-pfc/sh_pfc.h
+++ b/drivers/pinctrl/sh-pfc/sh_pfc.h
@@ -199,28 +199,82 @@
 	PINMUX_DATA(fn##_MARK, FN_##ms, FN_##ipsr, FN_##fn)
 
 /*
+ * Describe a pinmux configuration for a single-function pin with GPIO
+ * capability.
+ *   - fn: Function name
+ */
+#define PINMUX_SINGLE(fn)						\
+	PINMUX_DATA(fn##_MARK, FN_##fn)
+
+/*
  * GP port style (32 ports banks)
  */
 
 #define PORT_GP_CFG_1(bank, pin, fn, sfx, cfg) fn(bank, pin, GP_##bank##_##pin, sfx, cfg)
 #define PORT_GP_1(bank, pin, fn, sfx)	PORT_GP_CFG_1(bank, pin, fn, sfx, 0)
 
-#define PORT_GP_CFG_32(bank, fn, sfx, cfg)				\
+#define PORT_GP_CFG_4(bank, fn, sfx, cfg)						\
 	PORT_GP_CFG_1(bank, 0,  fn, sfx, cfg), PORT_GP_CFG_1(bank, 1,  fn, sfx, cfg),	\
-	PORT_GP_CFG_1(bank, 2,  fn, sfx, cfg), PORT_GP_CFG_1(bank, 3,  fn, sfx, cfg),	\
+	PORT_GP_CFG_1(bank, 2,  fn, sfx, cfg), PORT_GP_CFG_1(bank, 3,  fn, sfx, cfg)
+#define PORT_GP_4(bank, fn, sfx)	PORT_GP_CFG_4(bank, fn, sfx, 0)
+
+#define PORT_GP_CFG_8(bank, fn, sfx, cfg)						\
+	PORT_GP_CFG_4(bank, fn, sfx, cfg),						\
 	PORT_GP_CFG_1(bank, 4,  fn, sfx, cfg), PORT_GP_CFG_1(bank, 5,  fn, sfx, cfg),	\
-	PORT_GP_CFG_1(bank, 6,  fn, sfx, cfg), PORT_GP_CFG_1(bank, 7,  fn, sfx, cfg),	\
+	PORT_GP_CFG_1(bank, 6,  fn, sfx, cfg), PORT_GP_CFG_1(bank, 7,  fn, sfx, cfg)
+#define PORT_GP_8(bank, fn, sfx)	PORT_GP_CFG_8(bank, fn, sfx, 0)
+
+#define PORT_GP_CFG_9(bank, fn, sfx, cfg)						\
+	PORT_GP_CFG_8(bank, fn, sfx, cfg),						\
+	PORT_GP_CFG_1(bank, 8,  fn, sfx, cfg)
+#define PORT_GP_9(bank, fn, sfx)	PORT_GP_CFG_9(bank, fn, sfx, 0)
+
+#define PORT_GP_CFG_12(bank, fn, sfx, cfg)						\
+	PORT_GP_CFG_8(bank, fn, sfx, cfg),						\
 	PORT_GP_CFG_1(bank, 8,  fn, sfx, cfg), PORT_GP_CFG_1(bank, 9,  fn, sfx, cfg),	\
-	PORT_GP_CFG_1(bank, 10, fn, sfx, cfg), PORT_GP_CFG_1(bank, 11, fn, sfx, cfg),	\
-	PORT_GP_CFG_1(bank, 12, fn, sfx, cfg), PORT_GP_CFG_1(bank, 13, fn, sfx, cfg),	\
-	PORT_GP_CFG_1(bank, 14, fn, sfx, cfg), PORT_GP_CFG_1(bank, 15, fn, sfx, cfg),	\
-	PORT_GP_CFG_1(bank, 16, fn, sfx, cfg), PORT_GP_CFG_1(bank, 17, fn, sfx, cfg),	\
+	PORT_GP_CFG_1(bank, 10, fn, sfx, cfg), PORT_GP_CFG_1(bank, 11, fn, sfx, cfg)
+#define PORT_GP_12(bank, fn, sfx)	PORT_GP_CFG_12(bank, fn, sfx, 0)
+
+#define PORT_GP_CFG_14(bank, fn, sfx, cfg)						\
+	PORT_GP_CFG_12(bank, fn, sfx, cfg),						\
+	PORT_GP_CFG_1(bank, 12, fn, sfx, cfg), PORT_GP_CFG_1(bank, 13, fn, sfx, cfg)
+#define PORT_GP_14(bank, fn, sfx)	PORT_GP_CFG_14(bank, fn, sfx, 0)
+
+#define PORT_GP_CFG_15(bank, fn, sfx, cfg)						\
+	PORT_GP_CFG_14(bank, fn, sfx, cfg),						\
+	PORT_GP_CFG_1(bank, 14, fn, sfx, cfg)
+#define PORT_GP_15(bank, fn, sfx)	PORT_GP_CFG_15(bank, fn, sfx, 0)
+
+#define PORT_GP_CFG_16(bank, fn, sfx, cfg)						\
+	PORT_GP_CFG_14(bank, fn, sfx, cfg),						\
+	PORT_GP_CFG_1(bank, 14, fn, sfx, cfg), PORT_GP_CFG_1(bank, 15, fn, sfx, cfg)
+#define PORT_GP_16(bank, fn, sfx)	PORT_GP_CFG_16(bank, fn, sfx, 0)
+
+#define PORT_GP_CFG_18(bank, fn, sfx, cfg)						\
+	PORT_GP_CFG_16(bank, fn, sfx, cfg),						\
+	PORT_GP_CFG_1(bank, 16, fn, sfx, cfg), PORT_GP_CFG_1(bank, 17, fn, sfx, cfg)
+#define PORT_GP_18(bank, fn, sfx)	PORT_GP_CFG_18(bank, fn, sfx, 0)
+
+#define PORT_GP_CFG_26(bank, fn, sfx, cfg)						\
+	PORT_GP_CFG_18(bank, fn, sfx, cfg),						\
 	PORT_GP_CFG_1(bank, 18, fn, sfx, cfg), PORT_GP_CFG_1(bank, 19, fn, sfx, cfg),	\
 	PORT_GP_CFG_1(bank, 20, fn, sfx, cfg), PORT_GP_CFG_1(bank, 21, fn, sfx, cfg),	\
 	PORT_GP_CFG_1(bank, 22, fn, sfx, cfg), PORT_GP_CFG_1(bank, 23, fn, sfx, cfg),	\
-	PORT_GP_CFG_1(bank, 24, fn, sfx, cfg), PORT_GP_CFG_1(bank, 25, fn, sfx, cfg),	\
-	PORT_GP_CFG_1(bank, 26, fn, sfx, cfg), PORT_GP_CFG_1(bank, 27, fn, sfx, cfg),	\
-	PORT_GP_CFG_1(bank, 28, fn, sfx, cfg), PORT_GP_CFG_1(bank, 29, fn, sfx, cfg),	\
+	PORT_GP_CFG_1(bank, 24, fn, sfx, cfg), PORT_GP_CFG_1(bank, 25, fn, sfx, cfg)
+#define PORT_GP_26(bank, fn, sfx)	PORT_GP_CFG_26(bank, fn, sfx, 0)
+
+#define PORT_GP_CFG_28(bank, fn, sfx, cfg)						\
+	PORT_GP_CFG_26(bank, fn, sfx, cfg),						\
+	PORT_GP_CFG_1(bank, 26, fn, sfx, cfg), PORT_GP_CFG_1(bank, 27, fn, sfx, cfg)
+#define PORT_GP_28(bank, fn, sfx)	PORT_GP_CFG_28(bank, fn, sfx, 0)
+
+#define PORT_GP_CFG_30(bank, fn, sfx, cfg)						\
+	PORT_GP_CFG_28(bank, fn, sfx, cfg),						\
+	PORT_GP_CFG_1(bank, 28, fn, sfx, cfg), PORT_GP_CFG_1(bank, 29, fn, sfx, cfg)
+#define PORT_GP_30(bank, fn, sfx)	PORT_GP_CFG_30(bank, fn, sfx, 0)
+
+#define PORT_GP_CFG_32(bank, fn, sfx, cfg)						\
+	PORT_GP_CFG_30(bank, fn, sfx, cfg),						\
 	PORT_GP_CFG_1(bank, 30, fn, sfx, cfg), PORT_GP_CFG_1(bank, 31, fn, sfx, cfg)
 #define PORT_GP_32(bank, fn, sfx)	PORT_GP_CFG_32(bank, fn, sfx, 0)
 
diff --git a/drivers/pinctrl/sirf/pinctrl-atlas7.c b/drivers/pinctrl/sirf/pinctrl-atlas7.c
index 829018c..053d98e 100644
--- a/drivers/pinctrl/sirf/pinctrl-atlas7.c
+++ b/drivers/pinctrl/sirf/pinctrl-atlas7.c
@@ -161,6 +161,9 @@
 #define IN_DISABLE_VAL_1_REG_SET	0x0A88
 #define IN_DISABLE_VAL_1_REG_CLR	0x0A8C
 
+/* Offset of the SDIO9SEL*/
+#define SYS2PCI_SDIO9SEL 0x14
+
 struct dt_params {
 	const char *property;
 	int value;
@@ -370,6 +373,7 @@
 	struct pinctrl_desc pctl_desc;
 	struct atlas7_pinctrl_data *pctl_data;
 	void __iomem *regs[ATLAS7_PINCTRL_REG_BANKS];
+	void __iomem *sys2pci_base;
 	u32 status_ds[NUM_OF_IN_DISABLE_REG];
 	u32 status_dsv[NUM_OF_IN_DISABLE_REG];
 	struct atlas7_pad_status sleep_data[ATLAS7_PINCTRL_TOTAL_PINS];
@@ -885,11 +889,12 @@
 		62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 56, 53, 55, };
 static const unsigned int lvds_analog_pins[] = { 149, 150, 151, 152, 153, 154,
 		155, 156, 157, 158, };
-static const unsigned int nd_df_pins[] = { 44, 43, 42, 41, 40, 39, 38, 37,
-		47, 46, 52, 51, 45, 49, 50, 48, 124, };
-static const unsigned int nd_df_nowp_pins[] = { 44, 43, 42, 41, 40, 39, 38,
-		37, 47, 46, 52, 51, 45, 49, 50, 48, };
+static const unsigned int nd_df_basic_pins[] = { 44, 43, 42, 41, 40, 39, 38,
+		37, 47, 46, 52, 45, 49, 50, 48, };
+static const unsigned int nd_df_wp_pins[] = { 124, };
+static const unsigned int nd_df_cs_pins[] = { 51, };
 static const unsigned int ps_pins[] = { 120, 119, 121, };
+static const unsigned int ps_no_dir_pins[] = { 119, };
 static const unsigned int pwc_core_on_pins[] = { 8, };
 static const unsigned int pwc_ext_on_pins[] = { 6, };
 static const unsigned int pwc_gpio3_clk_pins[] = { 3, };
@@ -944,7 +949,7 @@
 static const unsigned int sd2_cdb_pins1[] = { 161, };
 static const unsigned int sd2_wpb_pins0[] = { 123, };
 static const unsigned int sd2_wpb_pins1[] = { 163, };
-static const unsigned int sd3_pins[] = { 85, 86, 87, 88, 89, 90, };
+static const unsigned int sd3_9_pins[] = { 85, 86, 87, 88, 89, 90, };
 static const unsigned int sd5_pins[] = { 91, 92, 93, 94, 95, 96, };
 static const unsigned int sd6_pins0[] = { 79, 78, 74, 75, 76, 77, };
 static const unsigned int sd6_pins1[] = { 101, 99, 100, 110, 109, 111, };
@@ -998,9 +1003,9 @@
 		81, 82, 83, 84, 108, 103, 104, 105, 106, 107, 102, 97, 98,
 		99, 100, };
 static const unsigned int vi_vip1_low8bit_pins[] = { 74, 75, 76, 77, 78, 79,
-		80, 81, };
-static const unsigned int vi_vip1_high8bit_pins[] = { 82, 83, 84, 108, 103,
-		104, 105, 106, };
+		80, 81, 82, 83, 84, };
+static const unsigned int vi_vip1_high8bit_pins[] = { 82, 83, 84, 103, 104,
+		105, 106, 107, 102, 97, 98, };
 
 /* definition of pin group table */
 struct atlas7_pin_group altas7_pin_groups[] = {
@@ -1142,9 +1147,11 @@
 	GROUP("ld_ldd_lck_grp", ld_ldd_lck_pins),
 	GROUP("lr_lcdrom_grp", lr_lcdrom_pins),
 	GROUP("lvds_analog_grp", lvds_analog_pins),
-	GROUP("nd_df_grp", nd_df_pins),
-	GROUP("nd_df_nowp_grp", nd_df_nowp_pins),
+	GROUP("nd_df_basic_grp", nd_df_basic_pins),
+	GROUP("nd_df_wp_grp", nd_df_wp_pins),
+	GROUP("nd_df_cs_grp", nd_df_cs_pins),
 	GROUP("ps_grp", ps_pins),
+	GROUP("ps_no_dir_grp", ps_no_dir_pins),
 	GROUP("pwc_core_on_grp", pwc_core_on_pins),
 	GROUP("pwc_ext_on_grp", pwc_ext_on_pins),
 	GROUP("pwc_gpio3_clk_grp", pwc_gpio3_clk_pins),
@@ -1196,7 +1203,7 @@
 	GROUP("sd2_cdb_grp1", sd2_cdb_pins1),
 	GROUP("sd2_wpb_grp0", sd2_wpb_pins0),
 	GROUP("sd2_wpb_grp1", sd2_wpb_pins1),
-	GROUP("sd3_grp", sd3_pins),
+	GROUP("sd3_9_grp", sd3_9_pins),
 	GROUP("sd5_grp", sd5_pins),
 	GROUP("sd6_grp0", sd6_pins0),
 	GROUP("sd6_grp1", sd6_pins1),
@@ -1421,9 +1428,11 @@
 static const char * const ld_ldd_lck_grp[] = { "ld_ldd_lck_grp", };
 static const char * const lr_lcdrom_grp[] = { "lr_lcdrom_grp", };
 static const char * const lvds_analog_grp[] = { "lvds_analog_grp", };
-static const char * const nd_df_grp[] = { "nd_df_grp", };
-static const char * const nd_df_nowp_grp[] = { "nd_df_nowp_grp", };
+static const char * const nd_df_basic_grp[] = { "nd_df_basic_grp", };
+static const char * const nd_df_wp_grp[] = { "nd_df_wp_grp", };
+static const char * const nd_df_cs_grp[] = { "nd_df_cs_grp", };
 static const char * const ps_grp[] = { "ps_grp", };
+static const char * const ps_no_dir_grp[] = { "ps_no_dir_grp", };
 static const char * const pwc_core_on_grp[] = { "pwc_core_on_grp", };
 static const char * const pwc_ext_on_grp[] = { "pwc_ext_on_grp", };
 static const char * const pwc_gpio3_clk_grp[] = { "pwc_gpio3_clk_grp", };
@@ -1478,7 +1487,7 @@
 static const char * const sd2_cdb_grp1[] = { "sd2_cdb_grp1", };
 static const char * const sd2_wpb_grp0[] = { "sd2_wpb_grp0", };
 static const char * const sd2_wpb_grp1[] = { "sd2_wpb_grp1", };
-static const char * const sd3_grp[] = { "sd3_grp", };
+static const char * const sd3_9_grp[] = { "sd3_9_grp", };
 static const char * const sd5_grp[] = { "sd5_grp", };
 static const char * const sd6_grp0[] = { "sd6_grp0", };
 static const char * const sd6_grp1[] = { "sd6_grp1", };
@@ -3174,7 +3183,7 @@
 	.pad_mux_list = lvds_analog_grp_pad_mux,
 };
 
-static struct atlas7_pad_mux nd_df_grp_pad_mux[] = {
+static struct atlas7_pad_mux nd_df_basic_grp_pad_mux[] = {
 	MUX(1, 44, 1, N, N, N, N),
 	MUX(1, 43, 1, N, N, N, N),
 	MUX(1, 42, 1, N, N, N, N),
@@ -3186,41 +3195,33 @@
 	MUX(1, 47, 1, N, N, N, N),
 	MUX(1, 46, 1, N, N, N, N),
 	MUX(1, 52, 1, N, N, N, N),
-	MUX(1, 51, 1, N, N, N, N),
 	MUX(1, 45, 1, N, N, N, N),
 	MUX(1, 49, 1, N, N, N, N),
 	MUX(1, 50, 1, N, N, N, N),
 	MUX(1, 48, 1, N, N, N, N),
+};
+
+static struct atlas7_grp_mux nd_df_basic_grp_mux = {
+	.pad_mux_count = ARRAY_SIZE(nd_df_basic_grp_pad_mux),
+	.pad_mux_list = nd_df_basic_grp_pad_mux,
+};
+
+static struct atlas7_pad_mux nd_df_wp_grp_pad_mux[] = {
 	MUX(1, 124, 4, N, N, N, N),
 };
 
-static struct atlas7_grp_mux nd_df_grp_mux = {
-	.pad_mux_count = ARRAY_SIZE(nd_df_grp_pad_mux),
-	.pad_mux_list = nd_df_grp_pad_mux,
+static struct atlas7_grp_mux nd_df_wp_grp_mux = {
+	.pad_mux_count = ARRAY_SIZE(nd_df_wp_grp_pad_mux),
+	.pad_mux_list = nd_df_wp_grp_pad_mux,
 };
 
-static struct atlas7_pad_mux nd_df_nowp_grp_pad_mux[] = {
-	MUX(1, 44, 1, N, N, N, N),
-	MUX(1, 43, 1, N, N, N, N),
-	MUX(1, 42, 1, N, N, N, N),
-	MUX(1, 41, 1, N, N, N, N),
-	MUX(1, 40, 1, N, N, N, N),
-	MUX(1, 39, 1, N, N, N, N),
-	MUX(1, 38, 1, N, N, N, N),
-	MUX(1, 37, 1, N, N, N, N),
-	MUX(1, 47, 1, N, N, N, N),
-	MUX(1, 46, 1, N, N, N, N),
-	MUX(1, 52, 1, N, N, N, N),
+static struct atlas7_pad_mux nd_df_cs_grp_pad_mux[] = {
 	MUX(1, 51, 1, N, N, N, N),
-	MUX(1, 45, 1, N, N, N, N),
-	MUX(1, 49, 1, N, N, N, N),
-	MUX(1, 50, 1, N, N, N, N),
-	MUX(1, 48, 1, N, N, N, N),
 };
 
-static struct atlas7_grp_mux nd_df_nowp_grp_mux = {
-	.pad_mux_count = ARRAY_SIZE(nd_df_nowp_grp_pad_mux),
-	.pad_mux_list = nd_df_nowp_grp_pad_mux,
+static struct atlas7_grp_mux nd_df_cs_grp_mux = {
+	.pad_mux_count = ARRAY_SIZE(nd_df_cs_grp_pad_mux),
+	.pad_mux_list = nd_df_cs_grp_pad_mux,
 };
 
 static struct atlas7_pad_mux ps_grp_pad_mux[] = {
@@ -3234,6 +3235,15 @@
 	.pad_mux_list = ps_grp_pad_mux,
 };
 
+static struct atlas7_pad_mux ps_no_dir_grp_pad_mux[] = {
+	MUX(1, 119, 2, N, N, N, N),
+};
+
+static struct atlas7_grp_mux ps_no_dir_grp_mux = {
+	.pad_mux_count = ARRAY_SIZE(ps_no_dir_grp_pad_mux),
+	.pad_mux_list = ps_no_dir_grp_pad_mux,
+};
+
 static struct atlas7_pad_mux pwc_core_on_grp_pad_mux[] = {
 	MUX(0, 8, 1, N, N, N, N),
 };
@@ -3743,7 +3753,7 @@
 	.pad_mux_list = sd2_wpb_grp1_pad_mux,
 };
 
-static struct atlas7_pad_mux sd3_grp_pad_mux[] = {
+static struct atlas7_pad_mux sd3_9_grp_pad_mux[] = {
 	MUX(1, 85, 1, N, N, N, N),
 	MUX(1, 86, 1, N, N, N, N),
 	MUX(1, 87, 1, N, N, N, N),
@@ -3752,9 +3762,9 @@
 	MUX(1, 90, 1, N, N, N, N),
 };
 
-static struct atlas7_grp_mux sd3_grp_mux = {
-	.pad_mux_count = ARRAY_SIZE(sd3_grp_pad_mux),
-	.pad_mux_list = sd3_grp_pad_mux,
+static struct atlas7_grp_mux sd3_9_grp_mux = {
+	.pad_mux_count = ARRAY_SIZE(sd3_9_grp_pad_mux),
+	.pad_mux_list = sd3_9_grp_pad_mux,
 };
 
 static struct atlas7_pad_mux sd5_grp_pad_mux[] = {
@@ -4296,6 +4306,9 @@
 	MUX(1, 79, 1, N, N, N, N),
 	MUX(1, 80, 1, N, N, N, N),
 	MUX(1, 81, 1, N, N, N, N),
+	MUX(1, 82, 1, N, N, N, N),
+	MUX(1, 83, 1, N, N, N, N),
+	MUX(1, 84, 1, N, N, N, N),
 };
 
 static struct atlas7_grp_mux vi_vip1_low8bit_grp_mux = {
@@ -4307,11 +4320,14 @@
 	MUX(1, 82, 1, N, N, N, N),
 	MUX(1, 83, 1, N, N, N, N),
 	MUX(1, 84, 1, N, N, N, N),
-	MUX(1, 108, 2, N, N, N, N),
 	MUX(1, 103, 2, N, N, N, N),
 	MUX(1, 104, 2, N, N, N, N),
 	MUX(1, 105, 2, N, N, N, N),
 	MUX(1, 106, 2, N, N, N, N),
+	MUX(1, 107, 2, N, N, N, N),
+	MUX(1, 102, 2, N, N, N, N),
+	MUX(1, 97, 2, N, N, N, N),
+	MUX(1, 98, 2, N, N, N, N),
 };
 
 static struct atlas7_grp_mux vi_vip1_high8bit_grp_mux = {
@@ -4598,9 +4614,11 @@
 	FUNCTION("ld_ldd_lck", ld_ldd_lck_grp, &ld_ldd_lck_grp_mux),
 	FUNCTION("lr_lcdrom", lr_lcdrom_grp, &lr_lcdrom_grp_mux),
 	FUNCTION("lvds_analog", lvds_analog_grp, &lvds_analog_grp_mux),
-	FUNCTION("nd_df", nd_df_grp, &nd_df_grp_mux),
-	FUNCTION("nd_df_nowp", nd_df_nowp_grp, &nd_df_nowp_grp_mux),
+	FUNCTION("nd_df_basic", nd_df_basic_grp, &nd_df_basic_grp_mux),
+	FUNCTION("nd_df_wp", nd_df_wp_grp, &nd_df_wp_grp_mux),
+	FUNCTION("nd_df_cs", nd_df_cs_grp, &nd_df_cs_grp_mux),
 	FUNCTION("ps", ps_grp, &ps_grp_mux),
+	FUNCTION("ps_no_dir", ps_no_dir_grp, &ps_no_dir_grp_mux),
 	FUNCTION("pwc_core_on", pwc_core_on_grp, &pwc_core_on_grp_mux),
 	FUNCTION("pwc_ext_on", pwc_ext_on_grp, &pwc_ext_on_grp_mux),
 	FUNCTION("pwc_gpio3_clk", pwc_gpio3_clk_grp, &pwc_gpio3_clk_grp_mux),
@@ -4686,10 +4704,11 @@
 	FUNCTION("sd2_cdb_m1", sd2_cdb_grp1, &sd2_cdb_grp1_mux),
 	FUNCTION("sd2_wpb_m0", sd2_wpb_grp0, &sd2_wpb_grp0_mux),
 	FUNCTION("sd2_wpb_m1", sd2_wpb_grp1, &sd2_wpb_grp1_mux),
-	FUNCTION("sd3", sd3_grp, &sd3_grp_mux),
+	FUNCTION("sd3", sd3_9_grp, &sd3_9_grp_mux),
 	FUNCTION("sd5", sd5_grp, &sd5_grp_mux),
 	FUNCTION("sd6_m0", sd6_grp0, &sd6_grp0_mux),
 	FUNCTION("sd6_m1", sd6_grp1, &sd6_grp1_mux),
+	FUNCTION("sd9", sd3_9_grp, &sd3_9_grp_mux),
 	FUNCTION("sp0_ext_ldo_on",
 			sp0_ext_ldo_on_grp,
 			&sp0_ext_ldo_on_grp_mux),
@@ -5097,6 +5116,14 @@
 	pr_debug("PMX DUMP ### Function:[%s] Group:[%s] #### START >>>\n",
 			pmx_func->name, pin_grp->name);
 
+	/* the sd3 and sd9 pin select by SYS2PCI_SDIO9SEL register */
+	if (pin_grp->pins == (unsigned int *)&sd3_9_pins) {
+		if (!strcmp(pmx_func->name, "sd9"))
+			writel(1, pmx->sys2pci_base + SYS2PCI_SDIO9SEL);
+		else
+			writel(0, pmx->sys2pci_base + SYS2PCI_SDIO9SEL);
+	}
+
 	grp_mux = pmx_func->grpmux;
 
 	for (idx = 0; idx < grp_mux->pad_mux_count; idx++) {
@@ -5385,12 +5412,27 @@
 	struct atlas7_pmx *pmx;
 	struct device_node *np = pdev->dev.of_node;
 	u32 banks = ATLAS7_PINCTRL_REG_BANKS;
+	struct device_node *sys2pci_np;
+	struct resource res;
 
 	/* Create state holders etc for this driver */
 	pmx = devm_kzalloc(&pdev->dev, sizeof(*pmx), GFP_KERNEL);
 	if (!pmx)
 		return -ENOMEM;
 
+	/* The sd3 and sd9 shared all pins, and the function select by
+	 * SYS2PCI_SDIO9SEL register
+	 */
+	sys2pci_np = of_find_node_by_name(NULL, "sys2pci");
+	if (!sys2pci_np)
+		return -EINVAL;
+	ret = of_address_to_resource(sys2pci_np, 0, &res);
+	if (ret)
+		return ret;
+	pmx->sys2pci_base = devm_ioremap_resource(&pdev->dev, &res);
+	if (IS_ERR(pmx->sys2pci_base))
+		return -ENOMEM;
+
 	pmx->dev = &pdev->dev;
 
 	pmx->pctl_data = &atlas7_ioc_data;
diff --git a/drivers/pinctrl/sirf/pinctrl-sirf.c b/drivers/pinctrl/sirf/pinctrl-sirf.c
index 2a8d697..edf40df 100644
--- a/drivers/pinctrl/sirf/pinctrl-sirf.c
+++ b/drivers/pinctrl/sirf/pinctrl-sirf.c
@@ -85,12 +85,16 @@
 	/* calculate number of maps required */
 	for_each_child_of_node(np_config, np) {
 		ret = of_property_read_string(np, "sirf,function", &function);
-		if (ret < 0)
+		if (ret < 0) {
+			of_node_put(np);
 			return ret;
+		}
 
 		ret = of_property_count_strings(np, "sirf,pins");
-		if (ret < 0)
+		if (ret < 0) {
+			of_node_put(np);
 			return ret;
+		}
 
 		count += ret;
 	}
diff --git a/drivers/pinctrl/spear/Makefile b/drivers/pinctrl/spear/Makefile
index 0e400eb..37b8412 100644
--- a/drivers/pinctrl/spear/Makefile
+++ b/drivers/pinctrl/spear/Makefile
@@ -1,7 +1,7 @@
 # SPEAr pinmux support
 
 obj-$(CONFIG_PINCTRL_SPEAR_PLGPIO)	+= pinctrl-plgpio.o
-obj-$(CONFIG_PINCTRL_SPEAR)	+= pinctrl-spear.o
+obj-y				+= pinctrl-spear.o
 obj-$(CONFIG_PINCTRL_SPEAR3XX)	+= pinctrl-spear3xx.o
 obj-$(CONFIG_PINCTRL_SPEAR300)	+= pinctrl-spear300.o
 obj-$(CONFIG_PINCTRL_SPEAR310)	+= pinctrl-spear310.o
diff --git a/drivers/pinctrl/sunxi/Kconfig b/drivers/pinctrl/sunxi/Kconfig
index e68fd95..f8dbc8b 100644
--- a/drivers/pinctrl/sunxi/Kconfig
+++ b/drivers/pinctrl/sunxi/Kconfig
@@ -51,8 +51,17 @@
 	depends on RESET_CONTROLLER
 	select PINCTRL_SUNXI_COMMON
 
+config PINCTRL_SUN8I_H3
+	def_bool MACH_SUN8I
+	select PINCTRL_SUNXI_COMMON
+
 config PINCTRL_SUN9I_A80
 	def_bool MACH_SUN9I
 	select PINCTRL_SUNXI_COMMON
 
+config PINCTRL_SUN9I_A80_R
+	def_bool MACH_SUN9I
+	depends on RESET_CONTROLLER
+	select PINCTRL_SUNXI_COMMON
+
 endif
diff --git a/drivers/pinctrl/sunxi/Makefile b/drivers/pinctrl/sunxi/Makefile
index e080290..ef82f22 100644
--- a/drivers/pinctrl/sunxi/Makefile
+++ b/drivers/pinctrl/sunxi/Makefile
@@ -13,4 +13,6 @@
 obj-$(CONFIG_PINCTRL_SUN8I_A23_R)	+= pinctrl-sun8i-a23-r.o
 obj-$(CONFIG_PINCTRL_SUN8I_A33)		+= pinctrl-sun8i-a33.o
 obj-$(CONFIG_PINCTRL_SUN8I_A83T)	+= pinctrl-sun8i-a83t.o
+obj-$(CONFIG_PINCTRL_SUN8I_H3)		+= pinctrl-sun8i-h3.o
 obj-$(CONFIG_PINCTRL_SUN9I_A80)		+= pinctrl-sun9i-a80.o
+obj-$(CONFIG_PINCTRL_SUN9I_A80_R)	+= pinctrl-sun9i-a80-r.o
diff --git a/drivers/pinctrl/sunxi/pinctrl-sun8i-h3.c b/drivers/pinctrl/sunxi/pinctrl-sun8i-h3.c
new file mode 100644
index 0000000..77d4cf0
--- /dev/null
+++ b/drivers/pinctrl/sunxi/pinctrl-sun8i-h3.c
@@ -0,0 +1,515 @@
+/*
+ * Allwinner H3 SoCs pinctrl driver.
+ *
+ * Copyright (C) 2015 Jens Kuske <jenskuske@gmail.com>
+ *
+ * Based on pinctrl-sun8i-a23.c, which is:
+ * Copyright (C) 2014 Chen-Yu Tsai <wens@csie.org>
+ * Copyright (C) 2014 Maxime Ripard <maxime.ripard@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/pinctrl/pinctrl.h>
+
+#include "pinctrl-sunxi.h"
+
+static const struct sunxi_desc_pin sun8i_h3_pins[] = {
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(A, 0),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "uart2"),		/* TX */
+		  SUNXI_FUNCTION(0x3, "jtag"),		/* MS */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 0)),	/* PA_EINT0 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(A, 1),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "uart2"),		/* RX */
+		  SUNXI_FUNCTION(0x3, "jtag"),		/* CK */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 1)),	/* PA_EINT1 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(A, 2),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "uart2"),		/* RTS */
+		  SUNXI_FUNCTION(0x3, "jtag"),		/* DO */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 2)),	/* PA_EINT2 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(A, 3),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "uart2"),		/* CTS */
+		  SUNXI_FUNCTION(0x3, "jtag"),		/* DI */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 3)),	/* PA_EINT3 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(A, 4),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "uart0"),		/* TX */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 4)),	/* PA_EINT4 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(A, 5),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "uart0"),		/* RX */
+		  SUNXI_FUNCTION(0x3, "pwm0"),
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 5)),	/* PA_EINT5 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(A, 6),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "sim"),		/* PWREN */
+		  SUNXI_FUNCTION(0x3, "pwm1"),
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 6)),	/* PA_EINT6 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(A, 7),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "sim"),		/* CLK */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 7)),	/* PA_EINT7 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(A, 8),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "sim"),		/* DATA */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 8)),	/* PA_EINT8 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(A, 9),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "sim"),		/* RST */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 9)),	/* PA_EINT9 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(A, 10),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "sim"),		/* DET */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 10)),	/* PA_EINT10 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(A, 11),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "i2c0"),		/* SCK */
+		  SUNXI_FUNCTION(0x3, "di"),		/* TX */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 11)),	/* PA_EINT11 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(A, 12),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "i2c0"),		/* SDA */
+		  SUNXI_FUNCTION(0x3, "di"),		/* RX */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 12)),	/* PA_EINT12 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(A, 13),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "spi1"),		/* CS */
+		  SUNXI_FUNCTION(0x3, "uart3"),		/* TX */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 13)),	/* PA_EINT13 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(A, 14),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "spi1"),		/* CLK */
+		  SUNXI_FUNCTION(0x3, "uart3"),		/* RX */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 14)),	/* PA_EINT14 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(A, 15),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "spi1"),		/* MOSI */
+		  SUNXI_FUNCTION(0x3, "uart3"),		/* RTS */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 15)),	/* PA_EINT15 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(A, 16),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "spi1"),		/* MISO */
+		  SUNXI_FUNCTION(0x3, "uart3"),		/* CTS */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 16)),	/* PA_EINT16 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(A, 17),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "spdif"),		/* OUT */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 17)),	/* PA_EINT17 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(A, 18),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "i2s0"),		/* SYNC */
+		  SUNXI_FUNCTION(0x3, "i2c1"),		/* SCK */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 18)),	/* PA_EINT18 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(A, 19),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "i2s0"),		/* CLK */
+		  SUNXI_FUNCTION(0x3, "i2c1"),		/* SDA */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 19)),	/* PA_EINT19 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(A, 20),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "i2s0"),		/* DOUT */
+		  SUNXI_FUNCTION(0x3, "sim"),		/* VPPEN */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 20)),	/* PA_EINT20 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(A, 21),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "i2s0"),		/* DIN */
+		  SUNXI_FUNCTION(0x3, "sim"),		/* VPPPP */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 21)),	/* PA_EINT21 */
+	/* Hole */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 0),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "nand0"),		/* WE */
+		  SUNXI_FUNCTION(0x3, "spi0")),		/* MOSI */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 1),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "nand0"),		/* ALE */
+		  SUNXI_FUNCTION(0x3, "spi0")),		/* MISO */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 2),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "nand0"),		/* CLE */
+		  SUNXI_FUNCTION(0x3, "spi0")),		/* CLK */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 3),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "nand0"),		/* CE1 */
+		  SUNXI_FUNCTION(0x3, "spi0")),		/* CS */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 4),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "nand0")),	/* CE0 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 5),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "nand0"),		/* RE */
+		  SUNXI_FUNCTION(0x3, "mmc2")),		/* CLK */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 6),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "nand0"),		/* RB0 */
+		  SUNXI_FUNCTION(0x3, "mmc2")),		/* CMD */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 7),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "nand0")),	/* RB1 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 8),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "nand0"),		/* DQ0 */
+		  SUNXI_FUNCTION(0x3, "mmc2")),		/* D0 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 9),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "nand0"),		/* DQ1 */
+		  SUNXI_FUNCTION(0x3, "mmc2")),		/* D1 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 10),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "nand0"),		/* DQ2 */
+		  SUNXI_FUNCTION(0x3, "mmc2")),		/* D2 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 11),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "nand0"),		/* DQ3 */
+		  SUNXI_FUNCTION(0x3, "mmc2")),		/* D3 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 12),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "nand0"),		/* DQ4 */
+		  SUNXI_FUNCTION(0x3, "mmc2")),		/* D4 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 13),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "nand0"),		/* DQ5 */
+		  SUNXI_FUNCTION(0x3, "mmc2")),		/* D5 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 14),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "nand"),		/* DQ6 */
+		  SUNXI_FUNCTION(0x3, "mmc2")),		/* D6 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 15),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "nand"),		/* DQ7 */
+		  SUNXI_FUNCTION(0x3, "mmc2")),		/* D7 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 16),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "nand"),		/* DQS */
+		  SUNXI_FUNCTION(0x3, "mmc2")),		/* RST */
+	/* Hole */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 0),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "emac")),		/* RXD3 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 1),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "emac")),		/* RXD2 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 2),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "emac")),		/* RXD1 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 3),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "emac")),		/* RXD0 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 4),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "emac")),		/* RXCK */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 5),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "emac")),		/* RXCTL/RXDV */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 6),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "emac")),		/* RXERR */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 7),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "emac")),		/* TXD3 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 8),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "emac")),		/* TXD2 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 9),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "emac")),		/* TXD1 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 10),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "emac")),		/* TXD0 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 11),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "emac")),		/* CRS */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 12),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "emac")),		/* TXCK */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 13),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "emac")),		/* TXCTL/TXEN */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 14),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "emac")),		/* TXERR */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 15),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "emac")),		/* CLKIN/COL */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 16),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "emac")),		/* MDC */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 17),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "emac")),		/* MDIO */
+	/* Hole */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 0),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "csi"),		/* PCLK */
+		  SUNXI_FUNCTION(0x3, "ts")),		/* CLK */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 1),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "csi"),		/* MCLK */
+		  SUNXI_FUNCTION(0x3, "ts")),		/* ERR */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 2),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "csi"),		/* HSYNC */
+		  SUNXI_FUNCTION(0x3, "ts")),		/* SYNC */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 3),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "csi"),		/* VSYNC */
+		  SUNXI_FUNCTION(0x3, "ts")),		/* DVLD */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 4),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "csi"),		/* D0 */
+		  SUNXI_FUNCTION(0x3, "ts")),		/* D0 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 5),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "csi"),		/* D1 */
+		  SUNXI_FUNCTION(0x3, "ts")),		/* D1 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 6),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "csi"),		/* D2 */
+		  SUNXI_FUNCTION(0x3, "ts")),		/* D2 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 7),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "csi"),		/* D3 */
+		  SUNXI_FUNCTION(0x3, "ts")),		/* D3 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 8),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "csi"),		/* D4 */
+		  SUNXI_FUNCTION(0x3, "ts")),		/* D4 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 9),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "csi"),		/* D5 */
+		  SUNXI_FUNCTION(0x3, "ts")),		/* D5 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 10),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "csi"),		/* D6 */
+		  SUNXI_FUNCTION(0x3, "ts")),		/* D6 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 11),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "csi"),		/* D7 */
+		  SUNXI_FUNCTION(0x3, "ts")),		/* D7 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 12),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "csi"),		/* SCK */
+		  SUNXI_FUNCTION(0x3, "i2c2")),		/* SCK */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 13),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "csi"),		/* SDA */
+		  SUNXI_FUNCTION(0x3, "i2c2")),		/* SDA */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 14),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out")),
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 15),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out")),
+	/* Hole */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(F, 0),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "mmc0"),		/* D1 */
+		  SUNXI_FUNCTION(0x3, "jtag")),		/* MS */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(F, 1),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "mmc0"),		/* D0 */
+		  SUNXI_FUNCTION(0x3, "jtag")),		/* DI */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(F, 2),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "mmc0"),		/* CLK */
+		  SUNXI_FUNCTION(0x3, "uart0")),	/* TX */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(F, 3),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "mmc0"),		/* CMD */
+		  SUNXI_FUNCTION(0x3, "jtag")),		/* DO */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(F, 4),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "mmc0"),		/* D3 */
+		  SUNXI_FUNCTION(0x3, "uart0")),	/* RX */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(F, 5),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "mmc0"),		/* D2 */
+		  SUNXI_FUNCTION(0x3, "jtag")),		/* CK */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(F, 6),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out")),
+	/* Hole */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 0),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "mmc1"),		/* CLK */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 1, 0)),	/* PG_EINT0 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 1),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "mmc1"),		/* CMD */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 1, 1)),	/* PG_EINT1 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 2),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "mmc1"),		/* D0 */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 1, 2)),	/* PG_EINT2 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 3),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "mmc1"),		/* D1 */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 1, 3)),	/* PG_EINT3 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 4),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "mmc1"),		/* D2 */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 1, 4)),	/* PG_EINT4 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 5),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "mmc1"),		/* D3 */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 1, 5)),	/* PG_EINT5 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 6),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "uart1"),		/* TX */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 1, 6)),	/* PG_EINT6 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 7),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "uart1"),		/* RX */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 1, 7)),	/* PG_EINT7 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 8),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "uart1"),		/* RTS */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 1, 8)),	/* PG_EINT8 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 9),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "uart1"),		/* CTS */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 1, 9)),	/* PG_EINT9 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 10),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "i2s1"),		/* SYNC */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 1, 10)),	/* PG_EINT10 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 11),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "i2s1"),		/* CLK */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 1, 11)),	/* PG_EINT11 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 12),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "i2s1"),		/* DOUT */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 1, 12)),	/* PG_EINT12 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 13),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "i2s1"),		/* DIN */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 1, 13)),	/* PG_EINT13 */
+};
+
+static const struct sunxi_pinctrl_desc sun8i_h3_pinctrl_data = {
+	.pins = sun8i_h3_pins,
+	.npins = ARRAY_SIZE(sun8i_h3_pins),
+	.irq_banks = 2,
+};
+
+static int sun8i_h3_pinctrl_probe(struct platform_device *pdev)
+{
+	return sunxi_pinctrl_init(pdev,
+				  &sun8i_h3_pinctrl_data);
+}
+
+static const struct of_device_id sun8i_h3_pinctrl_match[] = {
+	{ .compatible = "allwinner,sun8i-h3-pinctrl", },
+	{}
+};
+
+static struct platform_driver sun8i_h3_pinctrl_driver = {
+	.probe	= sun8i_h3_pinctrl_probe,
+	.driver	= {
+		.name		= "sun8i-h3-pinctrl",
+		.of_match_table	= sun8i_h3_pinctrl_match,
+	},
+};
+builtin_platform_driver(sun8i_h3_pinctrl_driver);
diff --git a/drivers/pinctrl/sunxi/pinctrl-sun9i-a80-r.c b/drivers/pinctrl/sunxi/pinctrl-sun9i-a80-r.c
new file mode 100644
index 0000000..42547ff
--- /dev/null
+++ b/drivers/pinctrl/sunxi/pinctrl-sun9i-a80-r.c
@@ -0,0 +1,181 @@
+/*
+ * Allwinner A80 SoCs special pins pinctrl driver.
+ *
+ * Copyright (C) 2014 Maxime Ripard
+ * Maxime Ripard <maxime.ripard@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/pinctrl/pinctrl.h>
+#include <linux/reset.h>
+
+#include "pinctrl-sunxi.h"
+
+static const struct sunxi_desc_pin sun9i_a80_r_pins[] = {
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(L, 0),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x3, "s_uart"),	/* TX */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 0)),	/* PL_EINT0 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(L, 1),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x3, "s_uart"),	/* RX */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 1)),	/* PL_EINT1 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(L, 2),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x3, "s_jtag"),	/* TMS */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 2)),	/* PL_EINT2 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(L, 3),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x3, "s_jtag"),	/* TCK */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 3)),	/* PL_EINT3 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(L, 4),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x3, "s_jtag"),	/* TDO */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 4)),	/* PL_EINT4 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(L, 5),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x3, "s_jtag"),	/* TDI */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 5)),	/* PL_EINT5 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(L, 6),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x3, "s_cir_rx"),
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 6)),	/* PL_EINT6 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(L, 7),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x3, "1wire"),
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 7)),	/* PL_EINT7 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(L, 8),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "s_ps2"),		/* SCK1 */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 8)),	/* PL_EINT8 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(L, 9),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "s_ps2"),		/* SDA1 */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 9)),	/* PL_EINT9 */
+
+	/* Hole */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(M, 0),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 1, 0)),	/* PM_EINT0 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(M, 1),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 1, 1)),	/* PM_EINT1 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(M, 2),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 1, 2)),	/* PM_EINT2 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(M, 3),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 1, 3)),	/* PM_EINT3 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(M, 4),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x3, "s_i2s1"),	/* LRCKR */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 1, 4)),	/* PM_EINT4 */
+
+	/* Hole */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(M, 8),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x3, "s_i2c1"),	/* SCK */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 1, 8)),	/* PM_EINT8 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(M, 9),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x3, "s_i2c1"),	/* SDA */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 1, 9)),	/* PM_EINT9 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(M, 10),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "s_i2s0"),	/* MCLK */
+		  SUNXI_FUNCTION(0x3, "s_i2s1")),	/* MCLK */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(M, 11),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "s_i2s0"),	/* BCLK */
+		  SUNXI_FUNCTION(0x3, "s_i2s1")),	/* BCLK */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(M, 12),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "s_i2s0"),	/* LRCK */
+		  SUNXI_FUNCTION(0x3, "s_i2s1")),	/* LRCK */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(M, 13),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "s_i2s0"),	/* DIN */
+		  SUNXI_FUNCTION(0x3, "s_i2s1")),	/* DIN */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(M, 14),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "s_i2s0"),	/* DOUT */
+		  SUNXI_FUNCTION(0x3, "s_i2s1")),	/* DOUT */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(M, 15),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 1, 15)),	/* PM_EINT15 */
+
+	/* Hole */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(N, 0),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "s_i2c0"),	/* SCK */
+		  SUNXI_FUNCTION(0x3, "s_rsb")),	/* SCK */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(N, 1),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "s_i2c0"),	/* SDA */
+		  SUNXI_FUNCTION(0x3, "s_rsb")),	/* SDA */
+};
+
+static const struct sunxi_pinctrl_desc sun9i_a80_r_pinctrl_data = {
+	.pins = sun9i_a80_r_pins,
+	.npins = ARRAY_SIZE(sun9i_a80_r_pins),
+	.pin_base = PL_BASE,
+	.irq_banks = 2,
+};
+
+static int sun9i_a80_r_pinctrl_probe(struct platform_device *pdev)
+{
+	return sunxi_pinctrl_init(pdev,
+				  &sun9i_a80_r_pinctrl_data);
+}
+
+static const struct of_device_id sun9i_a80_r_pinctrl_match[] = {
+	{ .compatible = "allwinner,sun9i-a80-r-pinctrl", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, sun9i_a80_r_pinctrl_match);
+
+static struct platform_driver sun9i_a80_r_pinctrl_driver = {
+	.probe	= sun9i_a80_r_pinctrl_probe,
+	.driver	= {
+		.name		= "sun9i-a80-r-pinctrl",
+		.owner		= THIS_MODULE,
+		.of_match_table	= sun9i_a80_r_pinctrl_match,
+	},
+};
+module_platform_driver(sun9i_a80_r_pinctrl_driver);
+
+MODULE_AUTHOR("Maxime Ripard <maxime.ripard@free-electrons.com");
+MODULE_DESCRIPTION("Allwinner A80 R_PIO pinctrl driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/pinctrl/uniphier/Kconfig b/drivers/pinctrl/uniphier/Kconfig
index ad90707..7abd614 100644
--- a/drivers/pinctrl/uniphier/Kconfig
+++ b/drivers/pinctrl/uniphier/Kconfig
@@ -1,32 +1,35 @@
-if ARCH_UNIPHIER
-
-config PINCTRL_UNIPHIER
-	bool
+menuconfig PINCTRL_UNIPHIER
+	bool "UniPhier SoC pinctrl drivers"
+	depends on ARCH_UNIPHIER
+	depends on OF && MFD_SYSCON
+	default y
 	select PINMUX
 	select GENERIC_PINCONF
 
+if PINCTRL_UNIPHIER
+
 config PINCTRL_UNIPHIER_PH1_LD4
 	tristate "UniPhier PH1-LD4 SoC pinctrl driver"
-	select PINCTRL_UNIPHIER
+	default y
 
 config PINCTRL_UNIPHIER_PH1_PRO4
 	tristate "UniPhier PH1-Pro4 SoC pinctrl driver"
-	select PINCTRL_UNIPHIER
+	default y
 
 config PINCTRL_UNIPHIER_PH1_SLD8
 	tristate "UniPhier PH1-sLD8 SoC pinctrl driver"
-	select PINCTRL_UNIPHIER
+	default y
 
 config PINCTRL_UNIPHIER_PH1_PRO5
 	tristate "UniPhier PH1-Pro5 SoC pinctrl driver"
-	select PINCTRL_UNIPHIER
+	default y
 
 config PINCTRL_UNIPHIER_PROXSTREAM2
 	tristate "UniPhier ProXstream2 SoC pinctrl driver"
-	select PINCTRL_UNIPHIER
+	default y
 
 config PINCTRL_UNIPHIER_PH1_LD6B
 	tristate "UniPhier PH1-LD6b SoC pinctrl driver"
-	select PINCTRL_UNIPHIER
+	default y
 
 endif
diff --git a/drivers/s390/char/sclp_early.c b/drivers/s390/char/sclp_early.c
index 7bc6df3..6804354 100644
--- a/drivers/s390/char/sclp_early.c
+++ b/drivers/s390/char/sclp_early.c
@@ -40,10 +40,14 @@
 	u8	fac85;			/* 85 */
 	u8	_pad_86[91 - 86];	/* 86-90 */
 	u8	flags;			/* 91 */
-	u8	_pad_92[100 - 92];	/* 92-99 */
+	u8	_pad_92[99 - 92];	/* 92-98 */
+	u8	hamaxpow;		/* 99 */
 	u32	rnsize2;		/* 100-103 */
 	u64	rnmax2;			/* 104-111 */
-	u8	_pad_112[120 - 112];	/* 112-119 */
+	u8	_pad_112[116 - 112];	/* 112-115 */
+	u8	fac116;			/* 116 */
+	u8	_pad_117[119 - 117];	/* 117-118 */
+	u8	fac119;			/* 119 */
 	u16	hcpua;			/* 120-121 */
 	u8	_pad_122[4096 - 122];	/* 122-4095 */
 } __packed __aligned(PAGE_SIZE);
@@ -108,6 +112,8 @@
 	sclp.facilities = sccb->facilities;
 	sclp.has_sprp = !!(sccb->fac84 & 0x02);
 	sclp.has_core_type = !!(sccb->fac84 & 0x01);
+	sclp.has_esca = !!(sccb->fac116 & 0x08);
+	sclp.has_hvs = !!(sccb->fac119 & 0x80);
 	if (sccb->fac85 & 0x02)
 		S390_lowcore.machine_flags |= MACHINE_FLAG_ESOP;
 	sclp.rnmax = sccb->rnmax ? sccb->rnmax : sccb->rnmax2;
@@ -115,6 +121,11 @@
 	sclp.rzm <<= 20;
 	sclp.ibc = sccb->ibc;
 
+	if (sccb->hamaxpow && sccb->hamaxpow < 64)
+		sclp.hamax = (1UL << sccb->hamaxpow) - 1;
+	else
+		sclp.hamax = U64_MAX;
+
 	if (!sccb->hcpua) {
 		if (MACHINE_IS_VM)
 			sclp.max_cores = 64;
@@ -131,6 +142,7 @@
 			continue;
 		sclp.has_siif = cpue->siif;
 		sclp.has_sigpif = cpue->sigpif;
+		sclp.has_sief2 = cpue->sief2;
 		break;
 	}
 
diff --git a/drivers/s390/char/vmcp.c b/drivers/s390/char/vmcp.c
index 0fdedad..2a67b49 100644
--- a/drivers/s390/char/vmcp.c
+++ b/drivers/s390/char/vmcp.c
@@ -88,14 +88,9 @@
 
 	if (count > 240)
 		return -EINVAL;
-	cmd = kmalloc(count + 1, GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
-	if (copy_from_user(cmd, buff, count)) {
-		kfree(cmd);
-		return -EFAULT;
-	}
-	cmd[count] = '\0';
+	cmd = memdup_user_nul(buff, count);
+	if (IS_ERR(cmd))
+		return PTR_ERR(cmd);
 	session = file->private_data;
 	if (mutex_lock_interruptible(&session->mutex)) {
 		kfree(cmd);
diff --git a/drivers/s390/char/vmur.c b/drivers/s390/char/vmur.c
index 0efb27f..6c30e93a 100644
--- a/drivers/s390/char/vmur.c
+++ b/drivers/s390/char/vmur.c
@@ -782,24 +782,11 @@
 
 static loff_t ur_llseek(struct file *file, loff_t offset, int whence)
 {
-	loff_t newpos;
-
 	if ((file->f_flags & O_ACCMODE) != O_RDONLY)
 		return -ESPIPE; /* seek allowed only for reader */
 	if (offset % PAGE_SIZE)
 		return -ESPIPE; /* only multiples of 4K allowed */
-	switch (whence) {
-	case 0: /* SEEK_SET */
-		newpos = offset;
-		break;
-	case 1: /* SEEK_CUR */
-		newpos = file->f_pos + offset;
-		break;
-	default:
-		return -EINVAL;
-	}
-	file->f_pos = newpos;
-	return newpos;
+	return no_seek_end_llseek(file, offset, whence);
 }
 
 static const struct file_operations ur_fops = {
diff --git a/drivers/s390/char/zcore.c b/drivers/s390/char/zcore.c
index 823f41f..3339b86 100644
--- a/drivers/s390/char/zcore.c
+++ b/drivers/s390/char/zcore.c
@@ -385,18 +385,7 @@
 	loff_t rc;
 
 	mutex_lock(&zcore_mutex);
-	switch (orig) {
-	case 0:
-		file->f_pos = offset;
-		rc = file->f_pos;
-		break;
-	case 1:
-		file->f_pos += offset;
-		rc = file->f_pos;
-		break;
-	default:
-		rc = -EINVAL;
-	}
+	rc = no_seek_end_llseek(file, offset, orig);
 	mutex_unlock(&zcore_mutex);
 	return rc;
 }
diff --git a/drivers/sbus/char/openprom.c b/drivers/sbus/char/openprom.c
index 5843288..e077ebd 100644
--- a/drivers/sbus/char/openprom.c
+++ b/drivers/sbus/char/openprom.c
@@ -390,16 +390,9 @@
 	if ((ssize_t)len < 0 || (ssize_t)(len + 1) < 0)
 		return -EINVAL;
 
-	tmp = kmalloc(len + 1, GFP_KERNEL);
-	if (!tmp)
-		return -ENOMEM;
-
-	if (copy_from_user(tmp, user, len)) {
-		kfree(tmp);
-		return -EFAULT;
-	}
-
-	tmp[len] = '\0';
+	tmp = memdup_user_nul(user, len);
+	if (IS_ERR(tmp))
+		return PTR_ERR(tmp);
 
 	*ptr = tmp;
 
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 3d22fc3..4e08d1cd 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -2885,10 +2885,13 @@
 
 	/*
 	 * Use the device's preferred I/O size for reads and writes
-	 * unless the reported value is unreasonably large (or garbage).
+	 * unless the reported value is unreasonably small, large, or
+	 * garbage.
 	 */
-	if (sdkp->opt_xfer_blocks && sdkp->opt_xfer_blocks <= dev_max &&
-	    sdkp->opt_xfer_blocks <= SD_DEF_XFER_BLOCKS)
+	if (sdkp->opt_xfer_blocks &&
+	    sdkp->opt_xfer_blocks <= dev_max &&
+	    sdkp->opt_xfer_blocks <= SD_DEF_XFER_BLOCKS &&
+	    sdkp->opt_xfer_blocks * sdp->sector_size >= PAGE_CACHE_SIZE)
 		rw_max = q->limits.io_opt =
 			logical_to_sectors(sdp, sdkp->opt_xfer_blocks);
 	else
diff --git a/drivers/soc/qcom/spm.c b/drivers/soc/qcom/spm.c
index b04b05a..0ad66fa 100644
--- a/drivers/soc/qcom/spm.c
+++ b/drivers/soc/qcom/spm.c
@@ -116,7 +116,7 @@
 
 static DEFINE_PER_CPU(struct spm_driver_data *, cpu_spm_drv);
 
-typedef int (*idle_fn)(int);
+typedef int (*idle_fn)(void);
 static DEFINE_PER_CPU(idle_fn*, qcom_idle_ops);
 
 static inline void spm_register_write(struct spm_driver_data *drv,
@@ -179,10 +179,10 @@
 	return -1;
 }
 
-static int qcom_cpu_spc(int cpu)
+static int qcom_cpu_spc(void)
 {
 	int ret;
-	struct spm_driver_data *drv = per_cpu(cpu_spm_drv, cpu);
+	struct spm_driver_data *drv = __this_cpu_read(cpu_spm_drv);
 
 	spm_set_low_power_mode(drv, PM_SLEEP_MODE_SPC);
 	ret = cpu_suspend(0, qcom_pm_collapse);
@@ -197,9 +197,9 @@
 	return ret;
 }
 
-static int qcom_idle_enter(int cpu, unsigned long index)
+static int qcom_idle_enter(unsigned long index)
 {
-	return per_cpu(qcom_idle_ops, cpu)[index](cpu);
+	return __this_cpu_read(qcom_idle_ops)[index]();
 }
 
 static const struct of_device_id qcom_idle_state_match[] __initconst = {
diff --git a/drivers/staging/lustre/lustre/llite/file.c b/drivers/staging/lustre/lustre/llite/file.c
index 02f2759..31cd6b3 100644
--- a/drivers/staging/lustre/lustre/llite/file.c
+++ b/drivers/staging/lustre/lustre/llite/file.c
@@ -3139,7 +3139,7 @@
 	.lock	   = ll_file_noflock
 };
 
-struct inode_operations ll_file_inode_operations = {
+const struct inode_operations ll_file_inode_operations = {
 	.setattr	= ll_setattr,
 	.getattr	= ll_getattr,
 	.permission	= ll_inode_permission,
diff --git a/drivers/staging/lustre/lustre/llite/llite_internal.h b/drivers/staging/lustre/lustre/llite/llite_internal.h
index 9096d31..6102b29 100644
--- a/drivers/staging/lustre/lustre/llite/llite_internal.h
+++ b/drivers/staging/lustre/lustre/llite/llite_internal.h
@@ -705,7 +705,7 @@
 extern struct file_operations ll_file_operations;
 extern struct file_operations ll_file_operations_flock;
 extern struct file_operations ll_file_operations_noflock;
-extern struct inode_operations ll_file_inode_operations;
+extern const struct inode_operations ll_file_inode_operations;
 int ll_have_md_lock(struct inode *inode, __u64 *bits,
 		    ldlm_mode_t l_req_mode);
 ldlm_mode_t ll_take_md_lock(struct inode *inode, __u64 bits,
@@ -805,7 +805,7 @@
 				      const struct lu_fid *fid);
 
 /* llite/symlink.c */
-extern struct inode_operations ll_fast_symlink_inode_operations;
+extern const struct inode_operations ll_fast_symlink_inode_operations;
 
 /* llite/llite_close.c */
 struct ll_close_queue {
diff --git a/drivers/staging/lustre/lustre/llite/namei.c b/drivers/staging/lustre/lustre/llite/namei.c
index 2ca2200..64db5e8 100644
--- a/drivers/staging/lustre/lustre/llite/namei.c
+++ b/drivers/staging/lustre/lustre/llite/namei.c
@@ -126,9 +126,7 @@
 				rc = cl_file_inode_init(inode, md);
 			}
 			if (rc != 0) {
-				make_bad_inode(inode);
-				unlock_new_inode(inode);
-				iput(inode);
+				iget_failed(inode);
 				inode = ERR_PTR(rc);
 			} else
 				unlock_new_inode(inode);
diff --git a/drivers/staging/lustre/lustre/llite/symlink.c b/drivers/staging/lustre/lustre/llite/symlink.c
index 69b2036..2610348 100644
--- a/drivers/staging/lustre/lustre/llite/symlink.c
+++ b/drivers/staging/lustre/lustre/llite/symlink.c
@@ -118,12 +118,20 @@
 	return rc;
 }
 
-static const char *ll_follow_link(struct dentry *dentry, void **cookie)
+static void ll_put_link(void *p)
 {
-	struct inode *inode = d_inode(dentry);
+	ptlrpc_req_finished(p);
+}
+
+static const char *ll_get_link(struct dentry *dentry,
+			       struct inode *inode,
+			       struct delayed_call *done)
+{
 	struct ptlrpc_request *request = NULL;
 	int rc;
 	char *symname = NULL;
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
 
 	CDEBUG(D_VFSTRACE, "VFS Op\n");
 	ll_inode_size_lock(inode);
@@ -135,22 +143,16 @@
 	}
 
 	/* symname may contain a pointer to the request message buffer,
-	 * we delay request releasing until ll_put_link then.
+	 * we delay request releasing then.
 	 */
-	*cookie = request;
+	set_delayed_call(done, ll_put_link, request);
 	return symname;
 }
 
-static void ll_put_link(struct inode *unused, void *cookie)
-{
-	ptlrpc_req_finished(cookie);
-}
-
-struct inode_operations ll_fast_symlink_inode_operations = {
+const struct inode_operations ll_fast_symlink_inode_operations = {
 	.readlink	= generic_readlink,
 	.setattr	= ll_setattr,
-	.follow_link	= ll_follow_link,
-	.put_link	= ll_put_link,
+	.get_link	= ll_get_link,
 	.getattr	= ll_getattr,
 	.permission	= ll_inode_permission,
 	.setxattr	= ll_setxattr,
diff --git a/drivers/staging/lustre/lustre/llite/xattr.c b/drivers/staging/lustre/lustre/llite/xattr.c
index 4b7eb33..660b8ac 100644
--- a/drivers/staging/lustre/lustre/llite/xattr.c
+++ b/drivers/staging/lustre/lustre/llite/xattr.c
@@ -60,10 +60,10 @@
 static
 int get_xattr_type(const char *name)
 {
-	if (!strcmp(name, POSIX_ACL_XATTR_ACCESS))
+	if (!strcmp(name, XATTR_NAME_POSIX_ACL_ACCESS))
 		return XATTR_ACL_ACCESS_T;
 
-	if (!strcmp(name, POSIX_ACL_XATTR_DEFAULT))
+	if (!strcmp(name, XATTR_NAME_POSIX_ACL_DEFAULT))
 		return XATTR_ACL_DEFAULT_T;
 
 	if (!strncmp(name, XATTR_USER_PREFIX,
diff --git a/drivers/staging/media/bcm2048/radio-bcm2048.c b/drivers/staging/media/bcm2048/radio-bcm2048.c
index b10d601..93bffbac 100644
--- a/drivers/staging/media/bcm2048/radio-bcm2048.c
+++ b/drivers/staging/media/bcm2048/radio-bcm2048.c
@@ -1000,8 +1000,8 @@
 		timeout = BCM2048_AUTO_SEARCH_TIMEOUT;
 
 	if (!wait_for_completion_timeout(&bdev->compl,
-			msecs_to_jiffies(timeout)))
-			dev_err(&bdev->client->dev, "IRQ timeout.\n");
+		msecs_to_jiffies(timeout)))
+		dev_err(&bdev->client->dev, "IRQ timeout.\n");
 
 	if (value)
 		if (!bdev->scan_state)
diff --git a/drivers/staging/media/davinci_vpfe/Kconfig b/drivers/staging/media/davinci_vpfe/Kconfig
index 4de2f082..f40a069 100644
--- a/drivers/staging/media/davinci_vpfe/Kconfig
+++ b/drivers/staging/media/davinci_vpfe/Kconfig
@@ -2,6 +2,8 @@
 	tristate "DM365 VPFE Media Controller Capture Driver"
 	depends on VIDEO_V4L2 && ARCH_DAVINCI_DM365 && !VIDEO_DM365_ISIF
 	depends on HAS_DMA
+	depends on VIDEO_V4L2_SUBDEV_API
+	depends on VIDEO_DAVINCI_VPBE_DISPLAY
 	select VIDEOBUF2_DMA_CONTIG
 	help
 	  Support for DM365 VPFE based Media Controller Capture driver.
diff --git a/drivers/staging/media/davinci_vpfe/dm365_ipipe.c b/drivers/staging/media/davinci_vpfe/dm365_ipipe.c
index b1dfa2c..c492914 100644
--- a/drivers/staging/media/davinci_vpfe/dm365_ipipe.c
+++ b/drivers/staging/media/davinci_vpfe/dm365_ipipe.c
@@ -1536,8 +1536,9 @@
  * @fse: pointer to v4l2_subdev_frame_size_enum structure.
  */
 static int
-ipipe_enum_frame_size(struct v4l2_subdev *sd, struct v4l2_subdev_pad_config *cfg,
-			  struct v4l2_subdev_frame_size_enum *fse)
+ipipe_enum_frame_size(struct v4l2_subdev *sd,
+		       struct v4l2_subdev_pad_config *cfg,
+		       struct v4l2_subdev_frame_size_enum *fse)
 {
 	struct vpfe_ipipe_device *ipipe = v4l2_get_subdevdata(sd);
 	struct v4l2_mbus_framefmt format;
diff --git a/drivers/staging/media/davinci_vpfe/dm365_ipipe_hw.c b/drivers/staging/media/davinci_vpfe/dm365_ipipe_hw.c
index 2a3a56b..b1d5e23 100644
--- a/drivers/staging/media/davinci_vpfe/dm365_ipipe_hw.c
+++ b/drivers/staging/media/davinci_vpfe/dm365_ipipe_hw.c
@@ -254,7 +254,7 @@
 	void __iomem *ipipe_base = ipipe->base_addr;
 	struct v4l2_mbus_framefmt *outformat;
 	u32 color_pat;
-	u32 ipipe_mode;
+	int ipipe_mode;
 	u32 data_path;
 
 	/* enable clock to IPIPE */
diff --git a/drivers/staging/media/davinci_vpfe/dm365_resizer.c b/drivers/staging/media/davinci_vpfe/dm365_resizer.c
index acb293e..d892fee 100644
--- a/drivers/staging/media/davinci_vpfe/dm365_resizer.c
+++ b/drivers/staging/media/davinci_vpfe/dm365_resizer.c
@@ -63,16 +63,11 @@
 	if (pix == MEDIA_BUS_FMT_UYVY8_2X8 ||
 	    pix == MEDIA_BUS_FMT_SGRBG12_1X12) {
 		*line_len = width << 1;
-	} else if (pix == MEDIA_BUS_FMT_Y8_1X8 ||
-		   pix == MEDIA_BUS_FMT_UV8_1X8) {
-		*line_len = width;
-		*line_len_c = width;
 	} else {
-		/* YUV 420 */
-		/* round width to upper 32 byte boundary */
 		*line_len = width;
 		*line_len_c = width;
 	}
+
 	/* adjust the line len to be a multiple of 32 */
 	*line_len += 31;
 	*line_len &= ~0x1f;
diff --git a/drivers/staging/media/davinci_vpfe/vpfe_mc_capture.c b/drivers/staging/media/davinci_vpfe/vpfe_mc_capture.c
index 01df068..69b678c 100644
--- a/drivers/staging/media/davinci_vpfe/vpfe_mc_capture.c
+++ b/drivers/staging/media/davinci_vpfe/vpfe_mc_capture.c
@@ -227,7 +227,7 @@
 		return 0;
 
 	vpfe_dev->clks = kcalloc(vpfe_cfg->num_clocks,
-				 sizeof(struct clock *), GFP_KERNEL);
+				 sizeof(*vpfe_dev->clks), GFP_KERNEL);
 	if (vpfe_dev->clks == NULL)
 		return -ENOMEM;
 
diff --git a/drivers/staging/media/davinci_vpfe/vpfe_video.c b/drivers/staging/media/davinci_vpfe/vpfe_video.c
index 0fdff91..adb2bc8 100644
--- a/drivers/staging/media/davinci_vpfe/vpfe_video.c
+++ b/drivers/staging/media/davinci_vpfe/vpfe_video.c
@@ -470,7 +470,7 @@
 {
 	struct vpfe_pipeline *pipe = &video->pipe;
 
-	v4l2_get_timestamp(&video->cur_frm->vb.timestamp);
+	video->cur_frm->vb.vb2_buf.timestamp = ktime_get_ns();
 	vb2_buffer_done(&video->cur_frm->vb.vb2_buf, VB2_BUF_STATE_DONE);
 	if (pipe->state == VPFE_PIPELINE_STREAM_CONTINUOUS)
 		video->cur_frm = video->next_frm;
@@ -1078,7 +1078,7 @@
  * the buffer nbuffers and buffer size
  */
 static int
-vpfe_buffer_queue_setup(struct vb2_queue *vq, const void *parg,
+vpfe_buffer_queue_setup(struct vb2_queue *vq,
 			unsigned int *nbuffers, unsigned int *nplanes,
 			unsigned int sizes[], void *alloc_ctxs[])
 {
diff --git a/drivers/staging/media/lirc/lirc_imon.c b/drivers/staging/media/lirc/lirc_imon.c
index 534b810..ff1926c 100644
--- a/drivers/staging/media/lirc/lirc_imon.c
+++ b/drivers/staging/media/lirc/lirc_imon.c
@@ -885,12 +885,14 @@
 		vendor, product, ifnum, usbdev->bus->busnum, usbdev->devnum);
 
 	/* Everything went fine. Just unlock and return retval (with is 0) */
+	mutex_unlock(&context->ctx_lock);
 	goto driver_unlock;
 
 unregister_lirc:
 	lirc_unregister_driver(driver->minor);
 
 free_tx_urb:
+	mutex_unlock(&context->ctx_lock);
 	usb_free_urb(tx_urb);
 
 free_rx_urb:
diff --git a/drivers/staging/media/lirc/lirc_parallel.c b/drivers/staging/media/lirc/lirc_parallel.c
index c140834..d009bcb 100644
--- a/drivers/staging/media/lirc/lirc_parallel.c
+++ b/drivers/staging/media/lirc/lirc_parallel.c
@@ -33,7 +33,7 @@
 #include <linux/fs.h>
 #include <linux/kernel.h>
 #include <linux/ioport.h>
-#include <linux/time.h>
+#include <linux/ktime.h>
 #include <linux/mm.h>
 #include <linux/delay.h>
 
@@ -144,25 +144,22 @@
 
 static unsigned int init_lirc_timer(void)
 {
-	struct timeval tv, now;
+	ktime_t kt, now, timeout;
 	unsigned int level, newlevel, timeelapsed, newtimer;
 	int count = 0;
 
-	do_gettimeofday(&tv);
-	tv.tv_sec++;                     /* wait max. 1 sec. */
+	kt = ktime_get();
+	/* wait max. 1 sec. */
+	timeout = ktime_add_ns(kt, NSEC_PER_SEC);
 	level = lirc_get_timer();
 	do {
 		newlevel = lirc_get_timer();
 		if (level == 0 && newlevel != 0)
 			count++;
 		level = newlevel;
-		do_gettimeofday(&now);
-	} while (count < 1000 && (now.tv_sec < tv.tv_sec
-			     || (now.tv_sec == tv.tv_sec
-				 && now.tv_usec < tv.tv_usec)));
-
-	timeelapsed = (now.tv_sec + 1 - tv.tv_sec)*1000000
-		     + (now.tv_usec - tv.tv_usec);
+		now = ktime_get();
+	} while (count < 1000 && (ktime_before(now, timeout)));
+	timeelapsed = ktime_us_delta(now, kt);
 	if (count >= 1000 && timeelapsed > 0) {
 		if (default_timer == 0) {
 			/* autodetect timer */
@@ -220,8 +217,8 @@
 
 static void lirc_lirc_irq_handler(void *blah)
 {
-	struct timeval tv;
-	static struct timeval lasttv;
+	ktime_t kt, delkt;
+	static ktime_t lastkt;
 	static int init;
 	long signal;
 	int data;
@@ -244,16 +241,14 @@
 
 #ifdef LIRC_TIMER
 	if (init) {
-		do_gettimeofday(&tv);
+		kt = ktime_get();
 
-		signal = tv.tv_sec - lasttv.tv_sec;
-		if (signal > 15)
+		delkt = ktime_sub(kt, lastkt);
+		if (ktime_compare(delkt, ktime_set(15, 0)) > 0)
 			/* really long time */
 			data = PULSE_MASK;
 		else
-			data = (int) (signal*1000000 +
-					 tv.tv_usec - lasttv.tv_usec +
-					 LIRC_SFH506_DELAY);
+			data = (int)(ktime_to_us(delkt) + LIRC_SFH506_DELAY);
 
 		rbuf_write(data); /* space */
 	} else {
@@ -301,7 +296,7 @@
 			data = 1;
 		rbuf_write(PULSE_BIT|data); /* pulse */
 	}
-	do_gettimeofday(&lasttv);
+	lastkt = ktime_get();
 #else
 	/* add your code here */
 #endif
diff --git a/drivers/staging/media/lirc/lirc_sasem.c b/drivers/staging/media/lirc/lirc_sasem.c
index f2dca69..2218d00 100644
--- a/drivers/staging/media/lirc/lirc_sasem.c
+++ b/drivers/staging/media/lirc/lirc_sasem.c
@@ -42,6 +42,7 @@
 #include <linux/slab.h>
 #include <linux/uaccess.h>
 #include <linux/usb.h>
+#include <linux/ktime.h>
 
 #include <media/lirc.h>
 #include <media/lirc_dev.h>
@@ -111,7 +112,7 @@
 	} tx;
 
 	/* for dealing with repeat codes (wish there was a toggle bit!) */
-	struct timeval presstime;
+	ktime_t presstime;
 	char lastcode[8];
 	int codesaved;
 };
@@ -566,8 +567,8 @@
 {
 	int len = urb->actual_length;
 	unsigned char *buf = urb->transfer_buffer;
-	long ms;
-	struct timeval tv;
+	u64 ns;
+	ktime_t kt;
 
 	if (len != 8) {
 		dev_warn(&context->dev->dev,
@@ -584,9 +585,8 @@
 	 */
 
 	/* get the time since the last button press */
-	do_gettimeofday(&tv);
-	ms = (tv.tv_sec - context->presstime.tv_sec) * 1000 +
-	     (tv.tv_usec - context->presstime.tv_usec) / 1000;
+	kt = ktime_get();
+	ns = ktime_to_ns(ktime_sub(kt, context->presstime));
 
 	if (memcmp(buf, "\x08\0\0\0\0\0\0\0", 8) == 0) {
 		/*
@@ -600,10 +600,9 @@
 		 *   in that time and then get a false repeat of the previous
 		 *   press but it is long enough for a genuine repeat
 		 */
-		if ((ms < 250) && (context->codesaved != 0)) {
+		if ((ns < 250 * NSEC_PER_MSEC) && (context->codesaved != 0)) {
 			memcpy(buf, &context->lastcode, 8);
-			context->presstime.tv_sec = tv.tv_sec;
-			context->presstime.tv_usec = tv.tv_usec;
+			context->presstime = kt;
 		}
 	} else {
 		/* save the current valid code for repeats */
@@ -613,8 +612,7 @@
 		 * just for safety reasons
 		 */
 		context->codesaved = 1;
-		context->presstime.tv_sec = tv.tv_sec;
-		context->presstime.tv_usec = tv.tv_usec;
+		context->presstime = kt;
 	}
 
 	lirc_buffer_write(context->driver->rbuf, buf);
diff --git a/drivers/staging/media/lirc/lirc_serial.c b/drivers/staging/media/lirc/lirc_serial.c
index 64a7b2f..b798b31 100644
--- a/drivers/staging/media/lirc/lirc_serial.c
+++ b/drivers/staging/media/lirc/lirc_serial.c
@@ -59,7 +59,7 @@
 #include <linux/ioport.h>
 #include <linux/kernel.h>
 #include <linux/serial_reg.h>
-#include <linux/time.h>
+#include <linux/ktime.h>
 #include <linux/string.h>
 #include <linux/types.h>
 #include <linux/wait.h>
@@ -204,7 +204,7 @@
 
 #define RBUF_LEN 256
 
-static struct timeval lasttv = {0, 0};
+static ktime_t lastkt;
 
 static struct lirc_buffer rbuf;
 
@@ -542,10 +542,10 @@
 
 static irqreturn_t lirc_irq_handler(int i, void *blah)
 {
-	struct timeval tv;
+	ktime_t kt;
 	int counter, dcd;
 	u8 status;
-	long deltv;
+	ktime_t delkt;
 	int data;
 	static int last_dcd = -1;
 
@@ -565,7 +565,7 @@
 		if ((status & hardware[type].signal_pin_change)
 		    && sense != -1) {
 			/* get current time */
-			do_gettimeofday(&tv);
+			kt = ktime_get();
 
 			/* New mode, written by Trent Piepho
 			   <xyzzy@u.washington.edu>. */
@@ -594,34 +594,20 @@
 			dcd = (status & hardware[type].signal_pin) ? 1 : 0;
 
 			if (dcd == last_dcd) {
-				pr_warn("ignoring spike: %d %d %lx %lx %lx %lx\n",
-					dcd, sense,
-					tv.tv_sec, lasttv.tv_sec,
-					(unsigned long)tv.tv_usec,
-					(unsigned long)lasttv.tv_usec);
+				pr_warn("ignoring spike: %d %d %llx %llx\n",
+					dcd, sense, ktime_to_us(kt),
+					ktime_to_us(lastkt));
 				continue;
 			}
 
-			deltv = tv.tv_sec-lasttv.tv_sec;
-			if (tv.tv_sec < lasttv.tv_sec ||
-			    (tv.tv_sec == lasttv.tv_sec &&
-			     tv.tv_usec < lasttv.tv_usec)) {
-				pr_warn("AIEEEE: your clock just jumped backwards\n");
-				pr_warn("%d %d %lx %lx %lx %lx\n",
-					dcd, sense,
-					tv.tv_sec, lasttv.tv_sec,
-					(unsigned long)tv.tv_usec,
-					(unsigned long)lasttv.tv_usec);
-				data = PULSE_MASK;
-			} else if (deltv > 15) {
+			delkt = ktime_sub(kt, lastkt);
+			if (ktime_compare(delkt, ktime_set(15, 0)) > 0) {
 				data = PULSE_MASK; /* really long time */
 				if (!(dcd^sense)) {
 					/* sanity check */
-					pr_warn("AIEEEE: %d %d %lx %lx %lx %lx\n",
-						dcd, sense,
-						tv.tv_sec, lasttv.tv_sec,
-						(unsigned long)tv.tv_usec,
-						(unsigned long)lasttv.tv_usec);
+					pr_warn("AIEEEE: %d %d %llx %llx\n",
+						dcd, sense, ktime_to_us(kt),
+						ktime_to_us(lastkt));
 					/*
 					 * detecting pulse while this
 					 * MUST be a space!
@@ -629,11 +615,9 @@
 					sense = sense ? 0 : 1;
 				}
 			} else
-				data = (int) (deltv*1000000 +
-					       tv.tv_usec -
-					       lasttv.tv_usec);
+				data = (int) ktime_to_us(delkt);
 			frbwrite(dcd^sense ? data : (data|PULSE_BIT));
-			lasttv = tv;
+			lastkt = kt;
 			last_dcd = dcd;
 			wake_up_interruptible(&rbuf.wait_poll);
 		}
@@ -790,7 +774,7 @@
 	unsigned long flags;
 
 	/* initialize timestamp */
-	do_gettimeofday(&lasttv);
+	lastkt = ktime_get();
 
 	spin_lock_irqsave(&hardware[type].lock, flags);
 
@@ -979,7 +963,7 @@
 
 	spin_lock_irqsave(&hardware[type].lock, flags);
 	/* Enable Interrupt */
-	do_gettimeofday(&lasttv);
+	lastkt = ktime_get();
 	soutp(UART_IER, sinp(UART_IER)|UART_IER_MSI);
 	off();
 
diff --git a/drivers/staging/media/omap4iss/Kconfig b/drivers/staging/media/omap4iss/Kconfig
index 8d4e3bd..4618346 100644
--- a/drivers/staging/media/omap4iss/Kconfig
+++ b/drivers/staging/media/omap4iss/Kconfig
@@ -1,6 +1,6 @@
 config VIDEO_OMAP4
 	tristate "OMAP 4 Camera support"
-	depends on VIDEO_V4L2=y && VIDEO_V4L2_SUBDEV_API && I2C=y && ARCH_OMAP4
+	depends on VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API && I2C && ARCH_OMAP4
 	depends on HAS_DMA
 	select MFD_SYSCON
 	select VIDEOBUF2_DMA_CONTIG
diff --git a/drivers/staging/media/omap4iss/iss.c b/drivers/staging/media/omap4iss/iss.c
index aa76ccd..e27a988 100644
--- a/drivers/staging/media/omap4iss/iss.c
+++ b/drivers/staging/media/omap4iss/iss.c
@@ -601,8 +601,8 @@
 		subdev = media_entity_to_v4l2_subdev(entity);
 		ret = v4l2_subdev_call(subdev, video, s_stream, 0);
 		if (ret < 0) {
-			dev_dbg(iss->dev, "%s: module stop timeout.\n",
-				subdev->name);
+			dev_warn(iss->dev, "%s: module stop timeout.\n",
+				 subdev->name);
 			/* If the entity failed to stopped, assume it has
 			 * crashed. Mark it as such, the ISS will be reset when
 			 * applications will release it.
diff --git a/drivers/staging/media/omap4iss/iss.h b/drivers/staging/media/omap4iss/iss.h
index 35df8b4..5929357 100644
--- a/drivers/staging/media/omap4iss/iss.h
+++ b/drivers/staging/media/omap4iss/iss.h
@@ -20,7 +20,7 @@
 #include <linux/platform_device.h>
 #include <linux/wait.h>
 
-#include <media/omap4iss.h>
+#include <linux/platform_data/media/omap4iss.h>
 
 #include "iss_regs.h"
 #include "iss_csiphy.h"
diff --git a/drivers/staging/media/omap4iss/iss_csi2.c b/drivers/staging/media/omap4iss/iss_csi2.c
index c6e6d47..b941035 100644
--- a/drivers/staging/media/omap4iss/iss_csi2.c
+++ b/drivers/staging/media/omap4iss/iss_csi2.c
@@ -674,6 +674,9 @@
 	status = iss_reg_read(csi2->iss, csi2->regs1, CSI2_CTX_IRQSTATUS(n));
 	iss_reg_write(csi2->iss, csi2->regs1, CSI2_CTX_IRQSTATUS(n), status);
 
+	if (omap4iss_module_sync_is_stopping(&csi2->wait, &csi2->stopping))
+		return;
+
 	/* Propagate frame number */
 	if (status & CSI2_CTX_IRQ_FS) {
 		struct iss_pipeline *pipe =
@@ -776,9 +779,6 @@
 		pipe->error = true;
 	}
 
-	if (omap4iss_module_sync_is_stopping(&csi2->wait, &csi2->stopping))
-		return;
-
 	/* Successful cases */
 	if (csi2_irqstatus & CSI2_IRQ_CONTEXT0)
 		csi2_isr_ctx(csi2, &csi2->contexts[0]);
diff --git a/drivers/staging/media/omap4iss/iss_csiphy.h b/drivers/staging/media/omap4iss/iss_csiphy.h
index e9ca439..a0f2d97 100644
--- a/drivers/staging/media/omap4iss/iss_csiphy.h
+++ b/drivers/staging/media/omap4iss/iss_csiphy.h
@@ -14,7 +14,7 @@
 #ifndef OMAP4_ISS_CSI_PHY_H
 #define OMAP4_ISS_CSI_PHY_H
 
-#include <media/omap4iss.h>
+#include <linux/platform_data/media/omap4iss.h>
 
 struct iss_csi2_device;
 
diff --git a/drivers/staging/media/omap4iss/iss_resizer.c b/drivers/staging/media/omap4iss/iss_resizer.c
index 9c8180b..108961e 100644
--- a/drivers/staging/media/omap4iss/iss_resizer.c
+++ b/drivers/staging/media/omap4iss/iss_resizer.c
@@ -158,8 +158,8 @@
 	/* Program UV buffer address... Hardcoded to be contiguous! */
 	if ((informat->code == MEDIA_BUS_FMT_UYVY8_1X16) &&
 	    (outformat->code == MEDIA_BUS_FMT_YUYV8_1_5X8)) {
-		u32 c_addr = addr + (resizer->video_out.bpl_value *
-				     (outformat->height - 1));
+		u32 c_addr = addr + resizer->video_out.bpl_value
+			   * outformat->height;
 
 		/* Ensure Y_BAD_L[6:0] = C_BAD_L[6:0]*/
 		if ((c_addr ^ addr) & 0x7f) {
diff --git a/drivers/staging/media/omap4iss/iss_video.c b/drivers/staging/media/omap4iss/iss_video.c
index 2a0158b..e9aeca08 100644
--- a/drivers/staging/media/omap4iss/iss_video.c
+++ b/drivers/staging/media/omap4iss/iss_video.c
@@ -287,7 +287,6 @@
  */
 
 static int iss_video_queue_setup(struct vb2_queue *vq,
-				 const void *parg,
 				 unsigned int *count, unsigned int *num_planes,
 				 unsigned int sizes[], void *alloc_ctxs[])
 {
@@ -434,7 +433,7 @@
 	list_del(&buf->list);
 	spin_unlock_irqrestore(&video->qlock, flags);
 
-	v4l2_get_timestamp(&buf->vb.timestamp);
+	buf->vb.vb2_buf.timestamp = ktime_get_ns();
 
 	/* Do frame number propagation only if this is the output video node.
 	 * Frame number either comes from the CSI receivers or it gets
diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c
index 5381a72..e513940 100644
--- a/drivers/tty/sysrq.c
+++ b/drivers/tty/sysrq.c
@@ -133,6 +133,12 @@
 {
 	char *killer = NULL;
 
+	/* we need to release the RCU read lock here,
+	 * otherwise we get an annoying
+	 * 'BUG: sleeping function called from invalid context'
+	 * complaint from the kernel before the panic.
+	 */
+	rcu_read_unlock();
 	panic_on_oops = 1;	/* force panic */
 	wmb();
 	*killer = 1;
diff --git a/drivers/usb/core/devices.c b/drivers/usb/core/devices.c
index 2a3bbdf..cffa0a0 100644
--- a/drivers/usb/core/devices.c
+++ b/drivers/usb/core/devices.c
@@ -661,32 +661,8 @@
 	return 0;
 }
 
-static loff_t usb_device_lseek(struct file *file, loff_t offset, int orig)
-{
-	loff_t ret;
-
-	mutex_lock(&file_inode(file)->i_mutex);
-
-	switch (orig) {
-	case 0:
-		file->f_pos = offset;
-		ret = file->f_pos;
-		break;
-	case 1:
-		file->f_pos += offset;
-		ret = file->f_pos;
-		break;
-	case 2:
-	default:
-		ret = -EINVAL;
-	}
-
-	mutex_unlock(&file_inode(file)->i_mutex);
-	return ret;
-}
-
 const struct file_operations usbfs_devices_fops = {
-	.llseek =	usb_device_lseek,
+	.llseek =	no_seek_end_llseek,
 	.read =		usb_device_read,
 	.poll =		usb_device_poll,
 };
diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c
index 38ae877c..dbc3e14 100644
--- a/drivers/usb/core/devio.c
+++ b/drivers/usb/core/devio.c
@@ -157,30 +157,6 @@
 			ps->dev->state != USB_STATE_NOTATTACHED);
 }
 
-static loff_t usbdev_lseek(struct file *file, loff_t offset, int orig)
-{
-	loff_t ret;
-
-	mutex_lock(&file_inode(file)->i_mutex);
-
-	switch (orig) {
-	case 0:
-		file->f_pos = offset;
-		ret = file->f_pos;
-		break;
-	case 1:
-		file->f_pos += offset;
-		ret = file->f_pos;
-		break;
-	case 2:
-	default:
-		ret = -EINVAL;
-	}
-
-	mutex_unlock(&file_inode(file)->i_mutex);
-	return ret;
-}
-
 static ssize_t usbdev_read(struct file *file, char __user *buf, size_t nbytes,
 			   loff_t *ppos)
 {
@@ -2366,7 +2342,7 @@
 
 const struct file_operations usbdev_file_operations = {
 	.owner =	  THIS_MODULE,
-	.llseek =	  usbdev_lseek,
+	.llseek =	  no_seek_end_llseek,
 	.read =		  usbdev_read,
 	.poll =		  usbdev_poll,
 	.unlocked_ioctl = usbdev_ioctl,
diff --git a/drivers/usb/gadget/function/uvc_queue.c b/drivers/usb/gadget/function/uvc_queue.c
index 51d4a17..912694f 100644
--- a/drivers/usb/gadget/function/uvc_queue.c
+++ b/drivers/usb/gadget/function/uvc_queue.c
@@ -41,7 +41,7 @@
  * videobuf2 queue operations
  */
 
-static int uvc_queue_setup(struct vb2_queue *vq, const void *parg,
+static int uvc_queue_setup(struct vb2_queue *vq,
 			   unsigned int *nbuffers, unsigned int *nplanes,
 			   unsigned int sizes[], void *alloc_ctxs[])
 {
@@ -329,7 +329,7 @@
 
 	buf->buf.field = V4L2_FIELD_NONE;
 	buf->buf.sequence = queue->sequence++;
-	v4l2_get_timestamp(&buf->buf.timestamp);
+	buf->buf.vb2_buf.timestamp = ktime_get_ns();
 
 	vb2_set_plane_payload(&buf->buf.vb2_buf, 0, buf->bytesused);
 	vb2_buffer_done(&buf->buf.vb2_buf, VB2_BUF_STATE_DONE);
diff --git a/drivers/usb/host/uhci-debug.c b/drivers/usb/host/uhci-debug.c
index 1b28a00..9c6635d 100644
--- a/drivers/usb/host/uhci-debug.c
+++ b/drivers/usb/host/uhci-debug.c
@@ -584,27 +584,8 @@
 
 static loff_t uhci_debug_lseek(struct file *file, loff_t off, int whence)
 {
-	struct uhci_debug *up;
-	loff_t new = -1;
-
-	up = file->private_data;
-
-	/*
-	 * XXX: atomic 64bit seek access, but that needs to be fixed in the VFS
-	 */
-	switch (whence) {
-	case 0:
-		new = off;
-		break;
-	case 1:
-		new = file->f_pos + off;
-		break;
-	}
-
-	if (new < 0 || new > up->size)
-		return -EINVAL;
-
-	return (file->f_pos = new);
+	struct uhci_debug *up = file->private_data;
+	return no_seek_end_llseek_size(file, off, whence, up->size);
 }
 
 static ssize_t uhci_debug_read(struct file *file, char __user *buf,
diff --git a/drivers/usb/misc/sisusbvga/sisusb.c b/drivers/usb/misc/sisusbvga/sisusb.c
index 306d685..8efbaba 100644
--- a/drivers/usb/misc/sisusbvga/sisusb.c
+++ b/drivers/usb/misc/sisusbvga/sisusb.c
@@ -2825,21 +2825,7 @@
 		return -ENODEV;
 	}
 
-	switch (orig) {
-		case 0:
-			file->f_pos = offset;
-			ret = file->f_pos;
-			/* never negative, no force_successful_syscall needed */
-			break;
-		case 1:
-			file->f_pos += offset;
-			ret = file->f_pos;
-			/* never negative, no force_successful_syscall needed */
-			break;
-		default:
-			/* seeking relative to "end of file" is not supported */
-			ret = -EINVAL;
-	}
+	ret = no_seek_end_llseek(file, offset, orig);
 
 	mutex_unlock(&sisusb->lock);
 	return ret;
diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile
index aa8a7f7..9b7a35c 100644
--- a/drivers/xen/Makefile
+++ b/drivers/xen/Makefile
@@ -1,6 +1,6 @@
 obj-$(CONFIG_HOTPLUG_CPU)		+= cpu_hotplug.o
 obj-$(CONFIG_X86)			+= fallback.o
-obj-y	+= grant-table.o features.o balloon.o manage.o preempt.o
+obj-y	+= grant-table.o features.o balloon.o manage.o preempt.o time.o
 obj-y	+= events/
 obj-y	+= xenbus/
 
diff --git a/drivers/xen/acpi.c b/drivers/xen/acpi.c
index 90307c0..6893c79 100644
--- a/drivers/xen/acpi.c
+++ b/drivers/xen/acpi.c
@@ -58,7 +58,7 @@
 		 bits, val_a, val_b))
 		return -1;
 
-	HYPERVISOR_dom0_op(&op);
+	HYPERVISOR_platform_op(&op);
 	return 1;
 }
 
diff --git a/drivers/xen/efi.c b/drivers/xen/efi.c
index f745db2..be7e56a 100644
--- a/drivers/xen/efi.c
+++ b/drivers/xen/efi.c
@@ -42,7 +42,7 @@
 {
 	struct xen_platform_op op = INIT_EFI_OP(get_time);
 
-	if (HYPERVISOR_dom0_op(&op) < 0)
+	if (HYPERVISOR_platform_op(&op) < 0)
 		return EFI_UNSUPPORTED;
 
 	if (tm) {
@@ -67,7 +67,7 @@
 	BUILD_BUG_ON(sizeof(*tm) != sizeof(efi_data(op).u.set_time));
 	memcpy(&efi_data(op).u.set_time, tm, sizeof(*tm));
 
-	if (HYPERVISOR_dom0_op(&op) < 0)
+	if (HYPERVISOR_platform_op(&op) < 0)
 		return EFI_UNSUPPORTED;
 
 	return efi_data(op).status;
@@ -79,7 +79,7 @@
 {
 	struct xen_platform_op op = INIT_EFI_OP(get_wakeup_time);
 
-	if (HYPERVISOR_dom0_op(&op) < 0)
+	if (HYPERVISOR_platform_op(&op) < 0)
 		return EFI_UNSUPPORTED;
 
 	if (tm) {
@@ -108,7 +108,7 @@
 	else
 		efi_data(op).misc |= XEN_EFI_SET_WAKEUP_TIME_ENABLE_ONLY;
 
-	if (HYPERVISOR_dom0_op(&op) < 0)
+	if (HYPERVISOR_platform_op(&op) < 0)
 		return EFI_UNSUPPORTED;
 
 	return efi_data(op).status;
@@ -129,7 +129,7 @@
 	efi_data(op).u.get_variable.size = *data_size;
 	set_xen_guest_handle(efi_data(op).u.get_variable.data, data);
 
-	if (HYPERVISOR_dom0_op(&op) < 0)
+	if (HYPERVISOR_platform_op(&op) < 0)
 		return EFI_UNSUPPORTED;
 
 	*data_size = efi_data(op).u.get_variable.size;
@@ -152,7 +152,7 @@
 	memcpy(&efi_data(op).u.get_next_variable_name.vendor_guid, vendor,
 	       sizeof(*vendor));
 
-	if (HYPERVISOR_dom0_op(&op) < 0)
+	if (HYPERVISOR_platform_op(&op) < 0)
 		return EFI_UNSUPPORTED;
 
 	*name_size = efi_data(op).u.get_next_variable_name.size;
@@ -178,7 +178,7 @@
 	efi_data(op).u.set_variable.size = data_size;
 	set_xen_guest_handle(efi_data(op).u.set_variable.data, data);
 
-	if (HYPERVISOR_dom0_op(&op) < 0)
+	if (HYPERVISOR_platform_op(&op) < 0)
 		return EFI_UNSUPPORTED;
 
 	return efi_data(op).status;
@@ -196,7 +196,7 @@
 
 	efi_data(op).u.query_variable_info.attr = attr;
 
-	if (HYPERVISOR_dom0_op(&op) < 0)
+	if (HYPERVISOR_platform_op(&op) < 0)
 		return EFI_UNSUPPORTED;
 
 	*storage_space = efi_data(op).u.query_variable_info.max_store_size;
@@ -210,7 +210,7 @@
 {
 	struct xen_platform_op op = INIT_EFI_OP(get_next_high_monotonic_count);
 
-	if (HYPERVISOR_dom0_op(&op) < 0)
+	if (HYPERVISOR_platform_op(&op) < 0)
 		return EFI_UNSUPPORTED;
 
 	*count = efi_data(op).misc;
@@ -232,7 +232,7 @@
 	efi_data(op).u.update_capsule.capsule_count = count;
 	efi_data(op).u.update_capsule.sg_list = sg_list;
 
-	if (HYPERVISOR_dom0_op(&op) < 0)
+	if (HYPERVISOR_platform_op(&op) < 0)
 		return EFI_UNSUPPORTED;
 
 	return efi_data(op).status;
@@ -252,7 +252,7 @@
 					capsules);
 	efi_data(op).u.query_capsule_capabilities.capsule_count = count;
 
-	if (HYPERVISOR_dom0_op(&op) < 0)
+	if (HYPERVISOR_platform_op(&op) < 0)
 		return EFI_UNSUPPORTED;
 
 	*max_size = efi_data(op).u.query_capsule_capabilities.max_capsule_size;
@@ -331,7 +331,7 @@
 	};
 	union xenpf_efi_info *info = &op.u.firmware_info.u.efi_info;
 
-	if (!xen_initial_domain() || HYPERVISOR_dom0_op(&op) < 0)
+	if (!xen_initial_domain() || HYPERVISOR_platform_op(&op) < 0)
 		return NULL;
 
 	/* Here we know that Xen runs on EFI platform. */
@@ -347,7 +347,7 @@
 	info->vendor.bufsz = sizeof(vendor);
 	set_xen_guest_handle(info->vendor.name, vendor);
 
-	if (HYPERVISOR_dom0_op(&op) == 0) {
+	if (HYPERVISOR_platform_op(&op) == 0) {
 		efi_systab_xen.fw_vendor = __pa_symbol(vendor);
 		efi_systab_xen.fw_revision = info->vendor.revision;
 	} else
@@ -357,14 +357,14 @@
 	op.u.firmware_info.type = XEN_FW_EFI_INFO;
 	op.u.firmware_info.index = XEN_FW_EFI_VERSION;
 
-	if (HYPERVISOR_dom0_op(&op) == 0)
+	if (HYPERVISOR_platform_op(&op) == 0)
 		efi_systab_xen.hdr.revision = info->version;
 
 	op.cmd = XENPF_firmware_info;
 	op.u.firmware_info.type = XEN_FW_EFI_INFO;
 	op.u.firmware_info.index = XEN_FW_EFI_RT_VERSION;
 
-	if (HYPERVISOR_dom0_op(&op) == 0)
+	if (HYPERVISOR_platform_op(&op) == 0)
 		efi.runtime_version = info->version;
 
 	return &efi_systab_xen;
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index 1be5dd04..dc49538 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -518,7 +518,7 @@
 	mutex_unlock(&priv->lock);
 }
 
-static struct mmu_notifier_ops gntdev_mmu_ops = {
+static const struct mmu_notifier_ops gntdev_mmu_ops = {
 	.release                = mn_release,
 	.invalidate_page        = mn_invl_page,
 	.invalidate_range_start = mn_invl_range_start,
@@ -748,6 +748,206 @@
 	return rc;
 }
 
+#define GNTDEV_COPY_BATCH 24
+
+struct gntdev_copy_batch {
+	struct gnttab_copy ops[GNTDEV_COPY_BATCH];
+	struct page *pages[GNTDEV_COPY_BATCH];
+	s16 __user *status[GNTDEV_COPY_BATCH];
+	unsigned int nr_ops;
+	unsigned int nr_pages;
+};
+
+static int gntdev_get_page(struct gntdev_copy_batch *batch, void __user *virt,
+			   bool writeable, unsigned long *gfn)
+{
+	unsigned long addr = (unsigned long)virt;
+	struct page *page;
+	unsigned long xen_pfn;
+	int ret;
+
+	ret = get_user_pages_fast(addr, 1, writeable, &page);
+	if (ret < 0)
+		return ret;
+
+	batch->pages[batch->nr_pages++] = page;
+
+	xen_pfn = page_to_xen_pfn(page) + XEN_PFN_DOWN(addr & ~PAGE_MASK);
+	*gfn = pfn_to_gfn(xen_pfn);
+
+	return 0;
+}
+
+static void gntdev_put_pages(struct gntdev_copy_batch *batch)
+{
+	unsigned int i;
+
+	for (i = 0; i < batch->nr_pages; i++)
+		put_page(batch->pages[i]);
+	batch->nr_pages = 0;
+}
+
+static int gntdev_copy(struct gntdev_copy_batch *batch)
+{
+	unsigned int i;
+
+	gnttab_batch_copy(batch->ops, batch->nr_ops);
+	gntdev_put_pages(batch);
+
+	/*
+	 * For each completed op, update the status if the op failed
+	 * and all previous ops for the segment were successful.
+	 */
+	for (i = 0; i < batch->nr_ops; i++) {
+		s16 status = batch->ops[i].status;
+		s16 old_status;
+
+		if (status == GNTST_okay)
+			continue;
+
+		if (__get_user(old_status, batch->status[i]))
+			return -EFAULT;
+
+		if (old_status != GNTST_okay)
+			continue;
+
+		if (__put_user(status, batch->status[i]))
+			return -EFAULT;
+	}
+
+	batch->nr_ops = 0;
+	return 0;
+}
+
+static int gntdev_grant_copy_seg(struct gntdev_copy_batch *batch,
+				 struct gntdev_grant_copy_segment *seg,
+				 s16 __user *status)
+{
+	uint16_t copied = 0;
+
+	/*
+	 * Disallow local -> local copies since there is only space in
+	 * batch->pages for one page per-op and this would be a very
+	 * expensive memcpy().
+	 */
+	if (!(seg->flags & (GNTCOPY_source_gref | GNTCOPY_dest_gref)))
+		return -EINVAL;
+
+	/* Can't cross page if source/dest is a grant ref. */
+	if (seg->flags & GNTCOPY_source_gref) {
+		if (seg->source.foreign.offset + seg->len > XEN_PAGE_SIZE)
+			return -EINVAL;
+	}
+	if (seg->flags & GNTCOPY_dest_gref) {
+		if (seg->dest.foreign.offset + seg->len > XEN_PAGE_SIZE)
+			return -EINVAL;
+	}
+
+	if (put_user(GNTST_okay, status))
+		return -EFAULT;
+
+	while (copied < seg->len) {
+		struct gnttab_copy *op;
+		void __user *virt;
+		size_t len, off;
+		unsigned long gfn;
+		int ret;
+
+		if (batch->nr_ops >= GNTDEV_COPY_BATCH) {
+			ret = gntdev_copy(batch);
+			if (ret < 0)
+				return ret;
+		}
+
+		len = seg->len - copied;
+
+		op = &batch->ops[batch->nr_ops];
+		op->flags = 0;
+
+		if (seg->flags & GNTCOPY_source_gref) {
+			op->source.u.ref = seg->source.foreign.ref;
+			op->source.domid = seg->source.foreign.domid;
+			op->source.offset = seg->source.foreign.offset + copied;
+			op->flags |= GNTCOPY_source_gref;
+		} else {
+			virt = seg->source.virt + copied;
+			off = (unsigned long)virt & ~XEN_PAGE_MASK;
+			len = min(len, (size_t)XEN_PAGE_SIZE - off);
+
+			ret = gntdev_get_page(batch, virt, false, &gfn);
+			if (ret < 0)
+				return ret;
+
+			op->source.u.gmfn = gfn;
+			op->source.domid = DOMID_SELF;
+			op->source.offset = off;
+		}
+
+		if (seg->flags & GNTCOPY_dest_gref) {
+			op->dest.u.ref = seg->dest.foreign.ref;
+			op->dest.domid = seg->dest.foreign.domid;
+			op->dest.offset = seg->dest.foreign.offset + copied;
+			op->flags |= GNTCOPY_dest_gref;
+		} else {
+			virt = seg->dest.virt + copied;
+			off = (unsigned long)virt & ~XEN_PAGE_MASK;
+			len = min(len, (size_t)XEN_PAGE_SIZE - off);
+
+			ret = gntdev_get_page(batch, virt, true, &gfn);
+			if (ret < 0)
+				return ret;
+
+			op->dest.u.gmfn = gfn;
+			op->dest.domid = DOMID_SELF;
+			op->dest.offset = off;
+		}
+
+		op->len = len;
+		copied += len;
+
+		batch->status[batch->nr_ops] = status;
+		batch->nr_ops++;
+	}
+
+	return 0;
+}
+
+static long gntdev_ioctl_grant_copy(struct gntdev_priv *priv, void __user *u)
+{
+	struct ioctl_gntdev_grant_copy copy;
+	struct gntdev_copy_batch batch;
+	unsigned int i;
+	int ret = 0;
+
+	if (copy_from_user(&copy, u, sizeof(copy)))
+		return -EFAULT;
+
+	batch.nr_ops = 0;
+	batch.nr_pages = 0;
+
+	for (i = 0; i < copy.count; i++) {
+		struct gntdev_grant_copy_segment seg;
+
+		if (copy_from_user(&seg, &copy.segments[i], sizeof(seg))) {
+			ret = -EFAULT;
+			goto out;
+		}
+
+		ret = gntdev_grant_copy_seg(&batch, &seg, &copy.segments[i].status);
+		if (ret < 0)
+			goto out;
+
+		cond_resched();
+	}
+	if (batch.nr_ops)
+		ret = gntdev_copy(&batch);
+	return ret;
+
+  out:
+	gntdev_put_pages(&batch);
+	return ret;
+}
+
 static long gntdev_ioctl(struct file *flip,
 			 unsigned int cmd, unsigned long arg)
 {
@@ -767,6 +967,9 @@
 	case IOCTL_GNTDEV_SET_UNMAP_NOTIFY:
 		return gntdev_ioctl_notify(priv, ptr);
 
+	case IOCTL_GNTDEV_GRANT_COPY:
+		return gntdev_ioctl_grant_copy(priv, ptr);
+
 	default:
 		pr_debug("priv %p, unknown cmd %x\n", priv, cmd);
 		return -ENOIOCTLCMD;
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index c49f79e..effbaf9 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -128,7 +128,7 @@
 	int result;
 };
 
-static struct gnttab_ops *gnttab_interface;
+static const struct gnttab_ops *gnttab_interface;
 
 static int grant_table_version;
 static int grefs_per_grant_frame;
@@ -1013,7 +1013,7 @@
 	return rc;
 }
 
-static struct gnttab_ops gnttab_v1_ops = {
+static const struct gnttab_ops gnttab_v1_ops = {
 	.map_frames			= gnttab_map_frames_v1,
 	.unmap_frames			= gnttab_unmap_frames_v1,
 	.update_entry			= gnttab_update_entry_v1,
diff --git a/drivers/xen/pcpu.c b/drivers/xen/pcpu.c
index 49e88f2..cdc6daa 100644
--- a/drivers/xen/pcpu.c
+++ b/drivers/xen/pcpu.c
@@ -78,7 +78,7 @@
 		.u.cpu_ol.cpuid		= cpu_id,
 	};
 
-	return HYPERVISOR_dom0_op(&op);
+	return HYPERVISOR_platform_op(&op);
 }
 
 static int xen_pcpu_up(uint32_t cpu_id)
@@ -89,7 +89,7 @@
 		.u.cpu_ol.cpuid		= cpu_id,
 	};
 
-	return HYPERVISOR_dom0_op(&op);
+	return HYPERVISOR_platform_op(&op);
 }
 
 static ssize_t show_online(struct device *dev,
@@ -277,7 +277,7 @@
 		.u.pcpu_info.xen_cpuid = cpu,
 	};
 
-	ret = HYPERVISOR_dom0_op(&op);
+	ret = HYPERVISOR_platform_op(&op);
 	if (ret)
 		return ret;
 
@@ -364,7 +364,7 @@
 	op.cmd = XENPF_get_cpuinfo;
 	while (cpu_id <= max_id) {
 		op.u.pcpu_info.xen_cpuid = cpu_id;
-		if (HYPERVISOR_dom0_op(&op)) {
+		if (HYPERVISOR_platform_op(&op)) {
 			cpu_id++;
 			continue;
 		}
diff --git a/drivers/xen/time.c b/drivers/xen/time.c
new file mode 100644
index 0000000..71078425
--- /dev/null
+++ b/drivers/xen/time.c
@@ -0,0 +1,88 @@
+/*
+ * Xen stolen ticks accounting.
+ */
+#include <linux/kernel.h>
+#include <linux/kernel_stat.h>
+#include <linux/math64.h>
+#include <linux/gfp.h>
+
+#include <asm/xen/hypervisor.h>
+#include <asm/xen/hypercall.h>
+
+#include <xen/events.h>
+#include <xen/features.h>
+#include <xen/interface/xen.h>
+#include <xen/interface/vcpu.h>
+#include <xen/xen-ops.h>
+
+/* runstate info updated by Xen */
+static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate);
+
+/* return an consistent snapshot of 64-bit time/counter value */
+static u64 get64(const u64 *p)
+{
+	u64 ret;
+
+	if (BITS_PER_LONG < 64) {
+		u32 *p32 = (u32 *)p;
+		u32 h, l, h2;
+
+		/*
+		 * Read high then low, and then make sure high is
+		 * still the same; this will only loop if low wraps
+		 * and carries into high.
+		 * XXX some clean way to make this endian-proof?
+		 */
+		do {
+			h = READ_ONCE(p32[1]);
+			l = READ_ONCE(p32[0]);
+			h2 = READ_ONCE(p32[1]);
+		} while(h2 != h);
+
+		ret = (((u64)h) << 32) | l;
+	} else
+		ret = READ_ONCE(*p);
+
+	return ret;
+}
+
+/*
+ * Runstate accounting
+ */
+void xen_get_runstate_snapshot(struct vcpu_runstate_info *res)
+{
+	u64 state_time;
+	struct vcpu_runstate_info *state;
+
+	BUG_ON(preemptible());
+
+	state = this_cpu_ptr(&xen_runstate);
+
+	/*
+	 * The runstate info is always updated by the hypervisor on
+	 * the current CPU, so there's no need to use anything
+	 * stronger than a compiler barrier when fetching it.
+	 */
+	do {
+		state_time = get64(&state->state_entry_time);
+		*res = READ_ONCE(*state);
+	} while (get64(&state->state_entry_time) != state_time);
+}
+
+/* return true when a vcpu could run but has no real cpu to run on */
+bool xen_vcpu_stolen(int vcpu)
+{
+	return per_cpu(xen_runstate, vcpu).state == RUNSTATE_runnable;
+}
+
+void xen_setup_runstate_info(int cpu)
+{
+	struct vcpu_register_runstate_memory_area area;
+
+	area.addr.v = &per_cpu(xen_runstate, cpu);
+
+	if (HYPERVISOR_vcpu_op(VCPUOP_register_runstate_memory_area,
+			       cpu, &area))
+		BUG();
+}
+
diff --git a/drivers/xen/xen-acpi-cpuhotplug.c b/drivers/xen/xen-acpi-cpuhotplug.c
index f4a3694..fdc9e67 100644
--- a/drivers/xen/xen-acpi-cpuhotplug.c
+++ b/drivers/xen/xen-acpi-cpuhotplug.c
@@ -206,7 +206,7 @@
 	op.u.cpu_add.acpi_id = pr->acpi_id;
 	op.u.cpu_add.pxm = pxm;
 
-	cpu_id = HYPERVISOR_dom0_op(&op);
+	cpu_id = HYPERVISOR_platform_op(&op);
 	if (cpu_id < 0)
 		pr_err(PREFIX "Failed to hotadd CPU for acpi_id %d\n",
 				pr->acpi_id);
diff --git a/drivers/xen/xen-acpi-pad.c b/drivers/xen/xen-acpi-pad.c
index f83b754..23d1808 100644
--- a/drivers/xen/xen-acpi-pad.c
+++ b/drivers/xen/xen-acpi-pad.c
@@ -36,7 +36,7 @@
 	op.u.core_parking.type = XEN_CORE_PARKING_SET;
 	op.u.core_parking.idle_nums = idle_nums;
 
-	return HYPERVISOR_dom0_op(&op);
+	return HYPERVISOR_platform_op(&op);
 }
 
 static int xen_acpi_pad_idle_cpus_num(void)
@@ -46,7 +46,7 @@
 	op.cmd = XENPF_core_parking;
 	op.u.core_parking.type = XEN_CORE_PARKING_GET;
 
-	return HYPERVISOR_dom0_op(&op)
+	return HYPERVISOR_platform_op(&op)
 	       ?: op.u.core_parking.idle_nums;
 }
 
diff --git a/drivers/xen/xen-acpi-processor.c b/drivers/xen/xen-acpi-processor.c
index 70fa4380..076970a 100644
--- a/drivers/xen/xen-acpi-processor.c
+++ b/drivers/xen/xen-acpi-processor.c
@@ -116,7 +116,7 @@
 	set_xen_guest_handle(op.u.set_pminfo.power.states, dst_cx_states);
 
 	if (!no_hypercall)
-		ret = HYPERVISOR_dom0_op(&op);
+		ret = HYPERVISOR_platform_op(&op);
 
 	if (!ret) {
 		pr_debug("ACPI CPU%u - C-states uploaded.\n", _pr->acpi_id);
@@ -244,7 +244,7 @@
 	}
 
 	if (!no_hypercall)
-		ret = HYPERVISOR_dom0_op(&op);
+		ret = HYPERVISOR_platform_op(&op);
 
 	if (!ret) {
 		struct acpi_processor_performance *perf;
@@ -302,7 +302,7 @@
 	info = &op.u.pcpu_info;
 	info->xen_cpuid = 0;
 
-	ret = HYPERVISOR_dom0_op(&op);
+	ret = HYPERVISOR_platform_op(&op);
 	if (ret)
 		return NR_CPUS;
 
@@ -310,7 +310,7 @@
 	last_cpu = op.u.pcpu_info.max_present;
 	for (i = 0; i <= last_cpu; i++) {
 		info->xen_cpuid = i;
-		ret = HYPERVISOR_dom0_op(&op);
+		ret = HYPERVISOR_platform_op(&op);
 		if (ret)
 			continue;
 		max_acpi_id = max(info->acpi_id, max_acpi_id);
diff --git a/drivers/xen/xenfs/xensyms.c b/drivers/xen/xenfs/xensyms.c
index f8b1285..a03f261 100644
--- a/drivers/xen/xenfs/xensyms.c
+++ b/drivers/xen/xenfs/xensyms.c
@@ -31,7 +31,7 @@
 
 	symnum = symdata->symnum;
 
-	ret = HYPERVISOR_dom0_op(&xs->op);
+	ret = HYPERVISOR_platform_op(&xs->op);
 	if (ret < 0)
 		return ret;
 
@@ -50,7 +50,7 @@
 		set_xen_guest_handle(symdata->name, xs->name);
 		symdata->symnum--; /* Rewind */
 
-		ret = HYPERVISOR_dom0_op(&xs->op);
+		ret = HYPERVISOR_platform_op(&xs->op);
 		if (ret < 0)
 			return ret;
 	}
diff --git a/firmware/WHENCE b/firmware/WHENCE
index 0c4d96d..de6f22e 100644
--- a/firmware/WHENCE
+++ b/firmware/WHENCE
@@ -677,7 +677,7 @@
 
 Licence: GPLv2 or later
 
-ARM assembly source code available at http://www.linuxtv.org/downloads/firmware/Boot.S
+ARM assembly source code available at https://linuxtv.org/downloads/firmware/Boot.S
 
 --------------------------------------------------------------------------
 
diff --git a/fs/9p/acl.c b/fs/9p/acl.c
index a7e2889..9da967f 100644
--- a/fs/9p/acl.c
+++ b/fs/9p/acl.c
@@ -67,8 +67,8 @@
 		return 0;
 	}
 	/* get the default/access acl values and cache them */
-	dacl = __v9fs_get_acl(fid, POSIX_ACL_XATTR_DEFAULT);
-	pacl = __v9fs_get_acl(fid, POSIX_ACL_XATTR_ACCESS);
+	dacl = __v9fs_get_acl(fid, XATTR_NAME_POSIX_ACL_DEFAULT);
+	pacl = __v9fs_get_acl(fid, XATTR_NAME_POSIX_ACL_ACCESS);
 
 	if (!IS_ERR(dacl) && !IS_ERR(pacl)) {
 		set_cached_acl(inode, ACL_TYPE_DEFAULT, dacl);
@@ -133,10 +133,10 @@
 		goto err_free_out;
 	switch (type) {
 	case ACL_TYPE_ACCESS:
-		name = POSIX_ACL_XATTR_ACCESS;
+		name = XATTR_NAME_POSIX_ACL_ACCESS;
 		break;
 	case ACL_TYPE_DEFAULT:
-		name = POSIX_ACL_XATTR_DEFAULT;
+		name = XATTR_NAME_POSIX_ACL_DEFAULT;
 		break;
 	default:
 		BUG();
@@ -220,15 +220,12 @@
 	struct posix_acl *acl;
 	int error;
 
-	if (strcmp(name, "") != 0)
-		return -EINVAL;
-
 	v9ses = v9fs_dentry2v9ses(dentry);
 	/*
 	 * We allow set/get/list of acl when access=client is not specified
 	 */
 	if ((v9ses->flags & V9FS_ACCESS_MASK) != V9FS_ACCESS_CLIENT)
-		return v9fs_xattr_get(dentry, handler->prefix, buffer, size);
+		return v9fs_xattr_get(dentry, handler->name, buffer, size);
 
 	acl = v9fs_get_cached_acl(d_inode(dentry), handler->flags);
 	if (IS_ERR(acl))
@@ -250,16 +247,13 @@
 	struct v9fs_session_info *v9ses;
 	struct inode *inode = d_inode(dentry);
 
-	if (strcmp(name, "") != 0)
-		return -EINVAL;
-
 	v9ses = v9fs_dentry2v9ses(dentry);
 	/*
 	 * set the attribute on the remote. Without even looking at the
 	 * xattr value. We leave it to the server to validate
 	 */
 	if ((v9ses->flags & V9FS_ACCESS_MASK) != V9FS_ACCESS_CLIENT)
-		return v9fs_xattr_set(dentry, handler->prefix, value, size,
+		return v9fs_xattr_set(dentry, handler->name, value, size,
 				      flags);
 
 	if (S_ISLNK(inode->i_mode))
@@ -319,7 +313,7 @@
 	default:
 		BUG();
 	}
-	retval = v9fs_xattr_set(dentry, handler->prefix, value, size, flags);
+	retval = v9fs_xattr_set(dentry, handler->name, value, size, flags);
 	if (!retval)
 		set_cached_acl(inode, handler->flags, acl);
 err_out:
@@ -328,14 +322,14 @@
 }
 
 const struct xattr_handler v9fs_xattr_acl_access_handler = {
-	.prefix	= POSIX_ACL_XATTR_ACCESS,
+	.name	= XATTR_NAME_POSIX_ACL_ACCESS,
 	.flags	= ACL_TYPE_ACCESS,
 	.get	= v9fs_xattr_get_acl,
 	.set	= v9fs_xattr_set_acl,
 };
 
 const struct xattr_handler v9fs_xattr_acl_default_handler = {
-	.prefix	= POSIX_ACL_XATTR_DEFAULT,
+	.name	= XATTR_NAME_POSIX_ACL_DEFAULT,
 	.flags	= ACL_TYPE_DEFAULT,
 	.get	= v9fs_xattr_get_acl,
 	.set	= v9fs_xattr_set_acl,
diff --git a/fs/9p/cache.c b/fs/9p/cache.c
index a69260f..103ca5e 100644
--- a/fs/9p/cache.c
+++ b/fs/9p/cache.c
@@ -243,14 +243,14 @@
 	if (!v9inode->fscache)
 		return;
 
-	spin_lock(&v9inode->fscache_lock);
+	mutex_lock(&v9inode->fscache_lock);
 
 	if ((filp->f_flags & O_ACCMODE) != O_RDONLY)
 		v9fs_cache_inode_flush_cookie(inode);
 	else
 		v9fs_cache_inode_get_cookie(inode);
 
-	spin_unlock(&v9inode->fscache_lock);
+	mutex_unlock(&v9inode->fscache_lock);
 }
 
 void v9fs_cache_inode_reset_cookie(struct inode *inode)
@@ -264,7 +264,7 @@
 
 	old = v9inode->fscache;
 
-	spin_lock(&v9inode->fscache_lock);
+	mutex_lock(&v9inode->fscache_lock);
 	fscache_relinquish_cookie(v9inode->fscache, 1);
 
 	v9ses = v9fs_inode2v9ses(inode);
@@ -274,7 +274,7 @@
 	p9_debug(P9_DEBUG_FSC, "inode %p revalidating cookie old %p new %p\n",
 		 inode, old, v9inode->fscache);
 
-	spin_unlock(&v9inode->fscache_lock);
+	mutex_unlock(&v9inode->fscache_lock);
 }
 
 int __v9fs_fscache_release_page(struct page *page, gfp_t gfp)
diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h
index 0923f2c..6877050 100644
--- a/fs/9p/v9fs.h
+++ b/fs/9p/v9fs.h
@@ -123,7 +123,7 @@
 
 struct v9fs_inode {
 #ifdef CONFIG_9P_FSCACHE
-	spinlock_t fscache_lock;
+	struct mutex fscache_lock;
 	struct fscache_cookie *fscache;
 #endif
 	struct p9_qid qid;
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 5110785..3a08b3e 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -244,7 +244,7 @@
 		return NULL;
 #ifdef CONFIG_9P_FSCACHE
 	v9inode->fscache = NULL;
-	spin_lock_init(&v9inode->fscache_lock);
+	mutex_init(&v9inode->fscache_lock);
 #endif
 	v9inode->writeback_fid = NULL;
 	v9inode->cache_validity = 0;
@@ -1223,18 +1223,26 @@
 }
 
 /**
- * v9fs_vfs_follow_link - follow a symlink path
+ * v9fs_vfs_get_link - follow a symlink path
  * @dentry: dentry for symlink
- * @cookie: place to pass the data to put_link()
+ * @inode: inode for symlink
+ * @done: delayed call for when we are done with the return value
  */
 
-static const char *v9fs_vfs_follow_link(struct dentry *dentry, void **cookie)
+static const char *v9fs_vfs_get_link(struct dentry *dentry,
+				     struct inode *inode,
+				     struct delayed_call *done)
 {
-	struct v9fs_session_info *v9ses = v9fs_dentry2v9ses(dentry);
-	struct p9_fid *fid = v9fs_fid_lookup(dentry);
+	struct v9fs_session_info *v9ses;
+	struct p9_fid *fid;
 	struct p9_wstat *st;
 	char *res;
 
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+
+	v9ses = v9fs_dentry2v9ses(dentry);
+	fid = v9fs_fid_lookup(dentry);
 	p9_debug(P9_DEBUG_VFS, "%pd\n", dentry);
 
 	if (IS_ERR(fid))
@@ -1259,7 +1267,8 @@
 
 	p9stat_free(st);
 	kfree(st);
-	return *cookie = res;
+	set_delayed_call(done, kfree_link, res);
+	return res;
 }
 
 /**
@@ -1452,8 +1461,7 @@
 
 static const struct inode_operations v9fs_symlink_inode_operations = {
 	.readlink = generic_readlink,
-	.follow_link = v9fs_vfs_follow_link,
-	.put_link = kfree_put_link,
+	.get_link = v9fs_vfs_get_link,
 	.getattr = v9fs_vfs_getattr,
 	.setattr = v9fs_vfs_setattr,
 };
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index cb899af..a34702c 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -899,26 +899,34 @@
 }
 
 /**
- * v9fs_vfs_follow_link_dotl - follow a symlink path
+ * v9fs_vfs_get_link_dotl - follow a symlink path
  * @dentry: dentry for symlink
- * @cookie: place to pass the data to put_link()
+ * @inode: inode for symlink
+ * @done: destructor for return value
  */
 
 static const char *
-v9fs_vfs_follow_link_dotl(struct dentry *dentry, void **cookie)
+v9fs_vfs_get_link_dotl(struct dentry *dentry,
+		       struct inode *inode,
+		       struct delayed_call *done)
 {
-	struct p9_fid *fid = v9fs_fid_lookup(dentry);
+	struct p9_fid *fid;
 	char *target;
 	int retval;
 
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+
 	p9_debug(P9_DEBUG_VFS, "%pd\n", dentry);
 
+	fid = v9fs_fid_lookup(dentry);
 	if (IS_ERR(fid))
 		return ERR_CAST(fid);
 	retval = p9_client_readlink(fid, &target);
 	if (retval)
 		return ERR_PTR(retval);
-	return *cookie = target;
+	set_delayed_call(done, kfree_link, target);
+	return target;
 }
 
 int v9fs_refresh_inode_dotl(struct p9_fid *fid, struct inode *inode)
@@ -984,8 +992,7 @@
 
 const struct inode_operations v9fs_symlink_inode_operations_dotl = {
 	.readlink = generic_readlink,
-	.follow_link = v9fs_vfs_follow_link_dotl,
-	.put_link = kfree_put_link,
+	.get_link = v9fs_vfs_get_link_dotl,
 	.getattr = v9fs_vfs_getattr_dotl,
 	.setattr = v9fs_vfs_setattr_dotl,
 	.setxattr = generic_setxattr,
diff --git a/fs/9p/xattr.c b/fs/9p/xattr.c
index e3d026a..9dd9b47 100644
--- a/fs/9p/xattr.c
+++ b/fs/9p/xattr.c
@@ -143,8 +143,6 @@
 {
 	const char *full_name = xattr_full_name(handler, name);
 
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
 	return v9fs_xattr_get(dentry, full_name, buffer, size);
 }
 
@@ -154,8 +152,6 @@
 {
 	const char *full_name = xattr_full_name(handler, name);
 
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
 	return v9fs_xattr_set(dentry, full_name, value, size, flags);
 }
 
diff --git a/fs/Kconfig b/fs/Kconfig
index 6ce72d8..2bb1ef8 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -73,6 +73,16 @@
           for filesystems like NFS and for the flock() system
           call. Disabling this option saves about 11k.
 
+config MANDATORY_FILE_LOCKING
+	bool "Enable Mandatory file locking"
+	depends on FILE_LOCKING
+	default y
+	help
+	  This option enables files appropriately marked files on appropriely
+	  mounted filesystems to support mandatory locking.
+
+	  To the best of my knowledge this is dead code that no one cares about.
+
 source "fs/notify/Kconfig"
 
 source "fs/quota/Kconfig"
diff --git a/fs/adfs/adfs.h b/fs/adfs/adfs.h
index 24575d9..ea4aba5 100644
--- a/fs/adfs/adfs.h
+++ b/fs/adfs/adfs.h
@@ -45,7 +45,7 @@
 struct adfs_sb_info {
 	union { struct {
 		struct adfs_discmap *s_map;	/* bh list containing map	 */
-		struct adfs_dir_ops *s_dir;	/* directory operations		 */
+		const struct adfs_dir_ops *s_dir; /* directory operations	 */
 		};
 		struct rcu_head rcu;		/* used only at shutdown time	 */
 	};
@@ -168,8 +168,8 @@
 extern const struct inode_operations adfs_dir_inode_operations;
 extern const struct file_operations adfs_dir_operations;
 extern const struct dentry_operations adfs_dentry_operations;
-extern struct adfs_dir_ops adfs_f_dir_ops;
-extern struct adfs_dir_ops adfs_fplus_dir_ops;
+extern const struct adfs_dir_ops adfs_f_dir_ops;
+extern const struct adfs_dir_ops adfs_fplus_dir_ops;
 
 extern int adfs_dir_update(struct super_block *sb, struct object_info *obj,
 			   int wait);
diff --git a/fs/adfs/dir.c b/fs/adfs/dir.c
index 51c279a..fd4cf2c 100644
--- a/fs/adfs/dir.c
+++ b/fs/adfs/dir.c
@@ -21,7 +21,7 @@
 {
 	struct inode *inode = file_inode(file);
 	struct super_block *sb = inode->i_sb;
-	struct adfs_dir_ops *ops = ADFS_SB(sb)->s_dir;
+	const struct adfs_dir_ops *ops = ADFS_SB(sb)->s_dir;
 	struct object_info obj;
 	struct adfs_dir dir;
 	int ret = 0;
@@ -69,7 +69,7 @@
 {
 	int ret = -EINVAL;
 #ifdef CONFIG_ADFS_FS_RW
-	struct adfs_dir_ops *ops = ADFS_SB(sb)->s_dir;
+	const struct adfs_dir_ops *ops = ADFS_SB(sb)->s_dir;
 	struct adfs_dir dir;
 
 	printk(KERN_INFO "adfs_dir_update: object %06X in dir %06X\n",
@@ -129,7 +129,7 @@
 adfs_dir_lookup_byname(struct inode *inode, struct qstr *name, struct object_info *obj)
 {
 	struct super_block *sb = inode->i_sb;
-	struct adfs_dir_ops *ops = ADFS_SB(sb)->s_dir;
+	const struct adfs_dir_ops *ops = ADFS_SB(sb)->s_dir;
 	struct adfs_dir dir;
 	int ret;
 
diff --git a/fs/adfs/dir_f.c b/fs/adfs/dir_f.c
index 4bbe853..0fbfd0b 100644
--- a/fs/adfs/dir_f.c
+++ b/fs/adfs/dir_f.c
@@ -476,7 +476,7 @@
 	dir->sb = NULL;
 }
 
-struct adfs_dir_ops adfs_f_dir_ops = {
+const struct adfs_dir_ops adfs_f_dir_ops = {
 	.read		= adfs_f_read,
 	.setpos		= adfs_f_setpos,
 	.getnext	= adfs_f_getnext,
diff --git a/fs/adfs/dir_fplus.c b/fs/adfs/dir_fplus.c
index 82d14cd..c92cfb6 100644
--- a/fs/adfs/dir_fplus.c
+++ b/fs/adfs/dir_fplus.c
@@ -256,7 +256,7 @@
 	dir->sb = NULL;
 }
 
-struct adfs_dir_ops adfs_fplus_dir_ops = {
+const struct adfs_dir_ops adfs_fplus_dir_ops = {
 	.read		= adfs_fplus_read,
 	.setpos		= adfs_fplus_setpos,
 	.getnext	= adfs_fplus_getnext,
diff --git a/fs/affs/affs.h b/fs/affs/affs.h
index c69a87e..cc2b2ef 100644
--- a/fs/affs/affs.h
+++ b/fs/affs/affs.h
@@ -138,7 +138,7 @@
 extern int	affs_remove_header(struct dentry *dentry);
 extern u32	affs_checksum_block(struct super_block *sb, struct buffer_head *bh);
 extern void	affs_fix_checksum(struct super_block *sb, struct buffer_head *bh);
-extern void	secs_to_datestamp(time_t secs, struct affs_date *ds);
+extern void	secs_to_datestamp(time64_t secs, struct affs_date *ds);
 extern umode_t	prot_to_mode(u32 prot);
 extern void	mode_to_prot(struct inode *inode);
 __printf(3, 4)
diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c
index 5fa92bc..d6c7a51 100644
--- a/fs/affs/amigaffs.c
+++ b/fs/affs/amigaffs.c
@@ -8,6 +8,7 @@
  *  Please send bug reports to: hjw@zvw.de
  */
 
+#include <linux/math64.h>
 #include "affs.h"
 
 /*
@@ -366,22 +367,22 @@
 }
 
 void
-secs_to_datestamp(time_t secs, struct affs_date *ds)
+secs_to_datestamp(time64_t secs, struct affs_date *ds)
 {
 	u32	 days;
 	u32	 minute;
+	s32	 rem;
 
 	secs -= sys_tz.tz_minuteswest * 60 + ((8 * 365 + 2) * 24 * 60 * 60);
 	if (secs < 0)
 		secs = 0;
-	days    = secs / 86400;
-	secs   -= days * 86400;
-	minute  = secs / 60;
-	secs   -= minute * 60;
+	days    = div_s64_rem(secs, 86400, &rem);
+	minute  = rem / 60;
+	rem    -= minute * 60;
 
 	ds->days = cpu_to_be32(days);
 	ds->mins = cpu_to_be32(minute);
-	ds->ticks = cpu_to_be32(secs * 50);
+	ds->ticks = cpu_to_be32(rem * 50);
 }
 
 umode_t
diff --git a/fs/affs/inode.c b/fs/affs/inode.c
index 1734950..0fdb0f5 100644
--- a/fs/affs/inode.c
+++ b/fs/affs/inode.c
@@ -140,6 +140,7 @@
 		break;
 	case ST_SOFTLINK:
 		inode->i_mode |= S_IFLNK;
+		inode_nohighmem(inode);
 		inode->i_op = &affs_symlink_inode_operations;
 		inode->i_data.a_ops = &affs_symlink_aops;
 		break;
diff --git a/fs/affs/namei.c b/fs/affs/namei.c
index 181e05b..00d3002 100644
--- a/fs/affs/namei.c
+++ b/fs/affs/namei.c
@@ -344,6 +344,7 @@
 		return -ENOSPC;
 
 	inode->i_op = &affs_symlink_inode_operations;
+	inode_nohighmem(inode);
 	inode->i_data.a_ops = &affs_symlink_aops;
 	inode->i_mode = S_IFLNK | 0777;
 	mode_to_prot(inode);
diff --git a/fs/affs/super.c b/fs/affs/super.c
index 5b50c4c..8836df5 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -32,7 +32,7 @@
 	struct affs_root_tail *tail = AFFS_ROOT_TAIL(sb, bh);
 
 	lock_buffer(bh);
-	secs_to_datestamp(get_seconds(), &tail->disk_change);
+	secs_to_datestamp(ktime_get_real_seconds(), &tail->disk_change);
 	affs_fix_checksum(sb, bh);
 	unlock_buffer(bh);
 
diff --git a/fs/affs/symlink.c b/fs/affs/symlink.c
index ea5b69a..69b03db 100644
--- a/fs/affs/symlink.c
+++ b/fs/affs/symlink.c
@@ -14,13 +14,13 @@
 {
 	struct buffer_head *bh;
 	struct inode *inode = page->mapping->host;
-	char *link = kmap(page);
+	char *link = page_address(page);
 	struct slink_front *lf;
 	int			 i, j;
 	char			 c;
 	char			 lc;
 
-	pr_debug("follow_link(ino=%lu)\n", inode->i_ino);
+	pr_debug("get_link(ino=%lu)\n", inode->i_ino);
 
 	bh = affs_bread(inode->i_sb, inode->i_ino);
 	if (!bh)
@@ -57,12 +57,10 @@
 	link[i] = '\0';
 	affs_brelse(bh);
 	SetPageUptodate(page);
-	kunmap(page);
 	unlock_page(page);
 	return 0;
 fail:
 	SetPageError(page);
-	kunmap(page);
 	unlock_page(page);
 	return -EIO;
 }
@@ -73,7 +71,6 @@
 
 const struct inode_operations affs_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= page_follow_link_light,
-	.put_link	= page_put_link,
+	.get_link	= page_get_link,
 	.setattr	= affs_notify_change,
 };
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index e06f5a2..86cc726 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -56,6 +56,7 @@
 	case AFS_FTYPE_SYMLINK:
 		inode->i_mode	= S_IFLNK | vnode->status.mode;
 		inode->i_op	= &page_symlink_inode_operations;
+		inode_nohighmem(inode);
 		break;
 	default:
 		printk("kAFS: AFS vnode with undefined type\n");
diff --git a/fs/afs/proc.c b/fs/afs/proc.c
index 24a905b..2853b40 100644
--- a/fs/afs/proc.c
+++ b/fs/afs/proc.c
@@ -230,14 +230,9 @@
 	if (size <= 1 || size >= PAGE_SIZE)
 		return -EINVAL;
 
-	kbuf = kmalloc(size + 1, GFP_KERNEL);
-	if (!kbuf)
-		return -ENOMEM;
-
-	ret = -EFAULT;
-	if (copy_from_user(kbuf, buf, size) != 0)
-		goto done;
-	kbuf[size] = 0;
+	kbuf = memdup_user_nul(buf, size);
+	if (IS_ERR(kbuf))
+		return PTR_ERR(kbuf);
 
 	/* trim to first NL */
 	name = memchr(kbuf, '\n', size);
@@ -315,15 +310,9 @@
 	if (size <= 1 || size >= PAGE_SIZE)
 		return -EINVAL;
 
-	ret = -ENOMEM;
-	kbuf = kmalloc(size + 1, GFP_KERNEL);
-	if (!kbuf)
-		goto nomem;
-
-	ret = -EFAULT;
-	if (copy_from_user(kbuf, buf, size) != 0)
-		goto infault;
-	kbuf[size] = 0;
+	kbuf = memdup_user_nul(buf, size);
+	if (IS_ERR(kbuf))
+		return PTR_ERR(kbuf);
 
 	/* trim to first NL */
 	s = memchr(kbuf, '\n', size);
@@ -337,9 +326,7 @@
 	if (ret >= 0)
 		ret = size;	/* consume everything, always */
 
-infault:
 	kfree(kbuf);
-nomem:
 	_leave(" = %d", ret);
 	return ret;
 }
diff --git a/fs/autofs4/symlink.c b/fs/autofs4/symlink.c
index da0c334..84e037d 100644
--- a/fs/autofs4/symlink.c
+++ b/fs/autofs4/symlink.c
@@ -12,10 +12,16 @@
 
 #include "autofs_i.h"
 
-static const char *autofs4_follow_link(struct dentry *dentry, void **cookie)
+static const char *autofs4_get_link(struct dentry *dentry,
+				    struct inode *inode,
+				    struct delayed_call *done)
 {
-	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
-	struct autofs_info *ino = autofs4_dentry_ino(dentry);
+	struct autofs_sb_info *sbi;
+	struct autofs_info *ino;
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+	sbi = autofs4_sbi(dentry->d_sb);
+	ino = autofs4_dentry_ino(dentry);
 	if (ino && !autofs4_oz_mode(sbi))
 		ino->last_used = jiffies;
 	return d_inode(dentry)->i_private;
@@ -23,5 +29,5 @@
 
 const struct inode_operations autofs4_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= autofs4_follow_link
+	.get_link	= autofs4_get_link
 };
diff --git a/fs/bad_inode.c b/fs/bad_inode.c
index 861b1e1..103f5d7 100644
--- a/fs/bad_inode.c
+++ b/fs/bad_inode.c
@@ -192,7 +192,7 @@
  *	Returns true if the inode in question has been marked as bad.
  */
  
-int is_bad_inode(struct inode *inode)
+bool is_bad_inode(struct inode *inode)
 {
 	return (inode->i_op == &bad_inode_ops);	
 }
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index 46aedac..25250fa 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -42,7 +42,7 @@
 static struct inode *befs_alloc_inode(struct super_block *sb);
 static void befs_destroy_inode(struct inode *inode);
 static void befs_destroy_inodecache(void);
-static const char *befs_follow_link(struct dentry *, void **);
+static int befs_symlink_readpage(struct file *, struct page *);
 static int befs_utf2nls(struct super_block *sb, const char *in, int in_len,
 			char **out, int *out_len);
 static int befs_nls2utf(struct super_block *sb, const char *in, int in_len,
@@ -79,10 +79,8 @@
 	.bmap		= befs_bmap,
 };
 
-static const struct inode_operations befs_symlink_inode_operations = {
-	.readlink	= generic_readlink,
-	.follow_link	= befs_follow_link,
-	.put_link	= kfree_put_link,
+static const struct address_space_operations befs_symlink_aops = {
+	.readpage	= befs_symlink_readpage,
 };
 
 /* 
@@ -398,7 +396,9 @@
 		inode->i_fop = &befs_dir_operations;
 	} else if (S_ISLNK(inode->i_mode)) {
 		if (befs_ino->i_flags & BEFS_LONG_SYMLINK) {
-			inode->i_op = &befs_symlink_inode_operations;
+			inode->i_op = &page_symlink_inode_operations;
+			inode_nohighmem(inode);
+			inode->i_mapping->a_ops = &befs_symlink_aops;
 		} else {
 			inode->i_link = befs_ino->i_data.symlink;
 			inode->i_op = &simple_symlink_inode_operations;
@@ -463,31 +463,33 @@
  * The data stream become link name. Unless the LONG_SYMLINK
  * flag is set.
  */
-static const char *
-befs_follow_link(struct dentry *dentry, void **cookie)
+static int befs_symlink_readpage(struct file *unused, struct page *page)
 {
-	struct super_block *sb = dentry->d_sb;
-	struct befs_inode_info *befs_ino = BEFS_I(d_inode(dentry));
+	struct inode *inode = page->mapping->host;
+	struct super_block *sb = inode->i_sb;
+	struct befs_inode_info *befs_ino = BEFS_I(inode);
 	befs_data_stream *data = &befs_ino->i_data.ds;
 	befs_off_t len = data->size;
-	char *link;
+	char *link = page_address(page);
 
-	if (len == 0) {
+	if (len == 0 || len > PAGE_SIZE) {
 		befs_error(sb, "Long symlink with illegal length");
-		return ERR_PTR(-EIO);
+		goto fail;
 	}
 	befs_debug(sb, "Follow long symlink");
 
-	link = kmalloc(len, GFP_NOFS);
-	if (!link)
-		return ERR_PTR(-ENOMEM);
 	if (befs_read_lsymlink(sb, data, link, len) != len) {
-		kfree(link);
 		befs_error(sb, "Failed to read entire long symlink");
-		return ERR_PTR(-EIO);
+		goto fail;
 	}
 	link[len - 1] = '\0';
-	return *cookie = link;
+	SetPageUptodate(page);
+	unlock_page(page);
+	return 0;
+fail:
+	SetPageError(page);
+	unlock_page(page);
+	return -EIO;
 }
 
 /*
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 44d4a1e..01b8e0d 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1042,12 +1042,9 @@
 static void flush_disk(struct block_device *bdev, bool kill_dirty)
 {
 	if (__invalidate_device(bdev, kill_dirty)) {
-		char name[BDEVNAME_SIZE] = "";
-
-		if (bdev->bd_disk)
-			disk_name(bdev->bd_disk, 0, name);
 		printk(KERN_WARNING "VFS: busy inodes on changed media or "
-		       "resized disk %s\n", name);
+		       "resized disk %s\n",
+		       bdev->bd_disk ? bdev->bd_disk->disk_name : "");
 	}
 
 	if (!bdev->bd_disk)
@@ -1071,12 +1068,9 @@
 	disk_size = (loff_t)get_capacity(disk) << 9;
 	bdev_size = i_size_read(bdev->bd_inode);
 	if (disk_size != bdev_size) {
-		char name[BDEVNAME_SIZE];
-
-		disk_name(disk, 0, name);
 		printk(KERN_INFO
 		       "%s: detected capacity change from %lld to %lld\n",
-		       name, bdev_size, disk_size);
+		       disk->disk_name, bdev_size, disk_size);
 		i_size_write(bdev->bd_inode, disk_size);
 		flush_disk(bdev, false);
 	}
diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index 9a0124a..f89db0c 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -37,10 +37,10 @@
 
 	switch (type) {
 	case ACL_TYPE_ACCESS:
-		name = POSIX_ACL_XATTR_ACCESS;
+		name = XATTR_NAME_POSIX_ACL_ACCESS;
 		break;
 	case ACL_TYPE_DEFAULT:
-		name = POSIX_ACL_XATTR_DEFAULT;
+		name = XATTR_NAME_POSIX_ACL_DEFAULT;
 		break;
 	default:
 		BUG();
@@ -81,7 +81,7 @@
 
 	switch (type) {
 	case ACL_TYPE_ACCESS:
-		name = POSIX_ACL_XATTR_ACCESS;
+		name = XATTR_NAME_POSIX_ACL_ACCESS;
 		if (acl) {
 			ret = posix_acl_equiv_mode(acl, &inode->i_mode);
 			if (ret < 0)
@@ -94,7 +94,7 @@
 	case ACL_TYPE_DEFAULT:
 		if (!S_ISDIR(inode->i_mode))
 			return acl ? -EINVAL : 0;
-		name = POSIX_ACL_XATTR_DEFAULT;
+		name = XATTR_NAME_POSIX_ACL_DEFAULT;
 		break;
 	default:
 		return -EINVAL;
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 35489e7..b7e4e34 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -4024,7 +4024,8 @@
 				struct btrfs_ioctl_space_info *space);
 void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, int lock,
 			       struct btrfs_ioctl_balance_args *bargs);
-
+ssize_t btrfs_dedupe_file_range(struct file *src_file, u64 loff, u64 olen,
+			   struct file *dst_file, u64 dst_loff);
 
 /* file.c */
 int btrfs_auto_defrag_init(void);
@@ -4055,6 +4056,11 @@
 		      loff_t pos, size_t write_bytes,
 		      struct extent_state **cached);
 int btrfs_fdatawrite_range(struct inode *inode, loff_t start, loff_t end);
+ssize_t btrfs_copy_file_range(struct file *file_in, loff_t pos_in,
+			      struct file *file_out, loff_t pos_out,
+			      size_t len, unsigned int flags);
+int btrfs_clone_file_range(struct file *file_in, loff_t pos_in,
+			   struct file *file_out, loff_t pos_out, u64 len);
 
 /* tree-defrag.c */
 int btrfs_defrag_leaves(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 974be09..42a378a 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -923,7 +923,7 @@
 	if (bio_flags & EXTENT_BIO_TREE_LOG)
 		return 0;
 #ifdef CONFIG_X86
-	if (cpu_has_xmm4_2)
+	if (static_cpu_has_safe(X86_FEATURE_XMM4_2))
 		return 0;
 #endif
 	return 1;
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 0f09526..e3d9022 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2934,6 +2934,9 @@
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= btrfs_ioctl,
 #endif
+	.copy_file_range = btrfs_copy_file_range,
+	.clone_file_range = btrfs_clone_file_range,
+	.dedupe_file_range = btrfs_dedupe_file_range,
 };
 
 void btrfs_auto_defrag_exit(void)
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index a70c579..3b8856e 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3550,10 +3550,10 @@
 	int scanned = 0;
 
 	if (!xattr_access) {
-		xattr_access = btrfs_name_hash(POSIX_ACL_XATTR_ACCESS,
-					strlen(POSIX_ACL_XATTR_ACCESS));
-		xattr_default = btrfs_name_hash(POSIX_ACL_XATTR_DEFAULT,
-					strlen(POSIX_ACL_XATTR_DEFAULT));
+		xattr_access = btrfs_name_hash(XATTR_NAME_POSIX_ACL_ACCESS,
+					strlen(XATTR_NAME_POSIX_ACL_ACCESS));
+		xattr_default = btrfs_name_hash(XATTR_NAME_POSIX_ACL_DEFAULT,
+					strlen(XATTR_NAME_POSIX_ACL_DEFAULT));
 	}
 
 	slot++;
@@ -3774,6 +3774,7 @@
 		break;
 	case S_IFLNK:
 		inode->i_op = &btrfs_symlink_inode_operations;
+		inode_nohighmem(inode);
 		inode->i_mapping->a_ops = &btrfs_symlink_aops;
 		break;
 	default:
@@ -9705,6 +9706,7 @@
 	btrfs_free_path(path);
 
 	inode->i_op = &btrfs_symlink_inode_operations;
+	inode_nohighmem(inode);
 	inode->i_mapping->a_ops = &btrfs_symlink_aops;
 	inode_set_bytes(inode, name_len);
 	btrfs_i_size_write(inode, name_len);
@@ -9994,7 +9996,7 @@
 	.setattr	= btrfs_setattr,
 	.mknod		= btrfs_mknod,
 	.setxattr	= btrfs_setxattr,
-	.getxattr	= btrfs_getxattr,
+	.getxattr	= generic_getxattr,
 	.listxattr	= btrfs_listxattr,
 	.removexattr	= btrfs_removexattr,
 	.permission	= btrfs_permission,
@@ -10071,7 +10073,7 @@
 	.getattr	= btrfs_getattr,
 	.setattr	= btrfs_setattr,
 	.setxattr	= btrfs_setxattr,
-	.getxattr	= btrfs_getxattr,
+	.getxattr	= generic_getxattr,
 	.listxattr      = btrfs_listxattr,
 	.removexattr	= btrfs_removexattr,
 	.permission	= btrfs_permission,
@@ -10085,7 +10087,7 @@
 	.setattr	= btrfs_setattr,
 	.permission	= btrfs_permission,
 	.setxattr	= btrfs_setxattr,
-	.getxattr	= btrfs_getxattr,
+	.getxattr	= generic_getxattr,
 	.listxattr	= btrfs_listxattr,
 	.removexattr	= btrfs_removexattr,
 	.get_acl	= btrfs_get_acl,
@@ -10094,13 +10096,12 @@
 };
 static const struct inode_operations btrfs_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= page_follow_link_light,
-	.put_link	= page_put_link,
+	.get_link	= page_get_link,
 	.getattr	= btrfs_getattr,
 	.setattr	= btrfs_setattr,
 	.permission	= btrfs_permission,
 	.setxattr	= btrfs_setxattr,
-	.getxattr	= btrfs_getxattr,
+	.getxattr	= generic_getxattr,
 	.listxattr	= btrfs_listxattr,
 	.removexattr	= btrfs_removexattr,
 	.update_time	= btrfs_update_time,
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index da94138..e219973 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -2962,7 +2962,7 @@
 		flush_dcache_page(dst_page);
 
 		if (memcmp(addr, dst_addr, cmp_len))
-			ret = BTRFS_SAME_DATA_DIFFERS;
+			ret = -EBADE;
 
 		kunmap_atomic(addr);
 		kunmap_atomic(dst_addr);
@@ -3098,53 +3098,16 @@
 
 #define BTRFS_MAX_DEDUPE_LEN	(16 * 1024 * 1024)
 
-static long btrfs_ioctl_file_extent_same(struct file *file,
-			struct btrfs_ioctl_same_args __user *argp)
+ssize_t btrfs_dedupe_file_range(struct file *src_file, u64 loff, u64 olen,
+				struct file *dst_file, u64 dst_loff)
 {
-	struct btrfs_ioctl_same_args *same = NULL;
-	struct btrfs_ioctl_same_extent_info *info;
-	struct inode *src = file_inode(file);
-	u64 off;
-	u64 len;
-	int i;
-	int ret;
-	unsigned long size;
+	struct inode *src = file_inode(src_file);
+	struct inode *dst = file_inode(dst_file);
 	u64 bs = BTRFS_I(src)->root->fs_info->sb->s_blocksize;
-	bool is_admin = capable(CAP_SYS_ADMIN);
-	u16 count;
+	ssize_t res;
 
-	if (!(file->f_mode & FMODE_READ))
-		return -EINVAL;
-
-	ret = mnt_want_write_file(file);
-	if (ret)
-		return ret;
-
-	if (get_user(count, &argp->dest_count)) {
-		ret = -EFAULT;
-		goto out;
-	}
-
-	size = offsetof(struct btrfs_ioctl_same_args __user, info[count]);
-
-	same = memdup_user(argp, size);
-
-	if (IS_ERR(same)) {
-		ret = PTR_ERR(same);
-		same = NULL;
-		goto out;
-	}
-
-	off = same->logical_offset;
-	len = same->length;
-
-	/*
-	 * Limit the total length we will dedupe for each operation.
-	 * This is intended to bound the total time spent in this
-	 * ioctl to something sane.
-	 */
-	if (len > BTRFS_MAX_DEDUPE_LEN)
-		len = BTRFS_MAX_DEDUPE_LEN;
+	if (olen > BTRFS_MAX_DEDUPE_LEN)
+		olen = BTRFS_MAX_DEDUPE_LEN;
 
 	if (WARN_ON_ONCE(bs < PAGE_CACHE_SIZE)) {
 		/*
@@ -3152,58 +3115,13 @@
 		 * result, btrfs_cmp_data() won't correctly handle
 		 * this situation without an update.
 		 */
-		ret = -EINVAL;
-		goto out;
+		return -EINVAL;
 	}
 
-	ret = -EISDIR;
-	if (S_ISDIR(src->i_mode))
-		goto out;
-
-	ret = -EACCES;
-	if (!S_ISREG(src->i_mode))
-		goto out;
-
-	/* pre-format output fields to sane values */
-	for (i = 0; i < count; i++) {
-		same->info[i].bytes_deduped = 0ULL;
-		same->info[i].status = 0;
-	}
-
-	for (i = 0, info = same->info; i < count; i++, info++) {
-		struct inode *dst;
-		struct fd dst_file = fdget(info->fd);
-		if (!dst_file.file) {
-			info->status = -EBADF;
-			continue;
-		}
-		dst = file_inode(dst_file.file);
-
-		if (!(is_admin || (dst_file.file->f_mode & FMODE_WRITE))) {
-			info->status = -EINVAL;
-		} else if (file->f_path.mnt != dst_file.file->f_path.mnt) {
-			info->status = -EXDEV;
-		} else if (S_ISDIR(dst->i_mode)) {
-			info->status = -EISDIR;
-		} else if (!S_ISREG(dst->i_mode)) {
-			info->status = -EACCES;
-		} else {
-			info->status = btrfs_extent_same(src, off, len, dst,
-							info->logical_offset);
-			if (info->status == 0)
-				info->bytes_deduped += len;
-		}
-		fdput(dst_file);
-	}
-
-	ret = copy_to_user(argp, same, size);
-	if (ret)
-		ret = -EFAULT;
-
-out:
-	mnt_drop_write_file(file);
-	kfree(same);
-	return ret;
+	res = btrfs_extent_same(src, loff, olen, dst, dst_loff);
+	if (res)
+		return res;
+	return olen;
 }
 
 static int clone_finish_inode_update(struct btrfs_trans_handle *trans,
@@ -3779,17 +3697,16 @@
 	return ret;
 }
 
-static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
-				       u64 off, u64 olen, u64 destoff)
+static noinline int btrfs_clone_files(struct file *file, struct file *file_src,
+					u64 off, u64 olen, u64 destoff)
 {
 	struct inode *inode = file_inode(file);
+	struct inode *src = file_inode(file_src);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
-	struct fd src_file;
-	struct inode *src;
 	int ret;
 	u64 len = olen;
 	u64 bs = root->fs_info->sb->s_blocksize;
-	int same_inode = 0;
+	int same_inode = src == inode;
 
 	/*
 	 * TODO:
@@ -3802,49 +3719,20 @@
 	 *   be either compressed or non-compressed.
 	 */
 
-	/* the destination must be opened for writing */
-	if (!(file->f_mode & FMODE_WRITE) || (file->f_flags & O_APPEND))
-		return -EINVAL;
-
 	if (btrfs_root_readonly(root))
 		return -EROFS;
 
-	ret = mnt_want_write_file(file);
-	if (ret)
-		return ret;
-
-	src_file = fdget(srcfd);
-	if (!src_file.file) {
-		ret = -EBADF;
-		goto out_drop_write;
-	}
-
-	ret = -EXDEV;
-	if (src_file.file->f_path.mnt != file->f_path.mnt)
-		goto out_fput;
-
-	src = file_inode(src_file.file);
-
-	ret = -EINVAL;
-	if (src == inode)
-		same_inode = 1;
-
-	/* the src must be open for reading */
-	if (!(src_file.file->f_mode & FMODE_READ))
-		goto out_fput;
+	if (file_src->f_path.mnt != file->f_path.mnt ||
+	    src->i_sb != inode->i_sb)
+		return -EXDEV;
 
 	/* don't make the dst file partly checksummed */
 	if ((BTRFS_I(src)->flags & BTRFS_INODE_NODATASUM) !=
 	    (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM))
-		goto out_fput;
+		return -EINVAL;
 
-	ret = -EISDIR;
 	if (S_ISDIR(src->i_mode) || S_ISDIR(inode->i_mode))
-		goto out_fput;
-
-	ret = -EXDEV;
-	if (src->i_sb != inode->i_sb)
-		goto out_fput;
+		return -EISDIR;
 
 	if (!same_inode) {
 		btrfs_double_inode_lock(src, inode);
@@ -3921,21 +3809,25 @@
 		btrfs_double_inode_unlock(src, inode);
 	else
 		mutex_unlock(&src->i_mutex);
-out_fput:
-	fdput(src_file);
-out_drop_write:
-	mnt_drop_write_file(file);
 	return ret;
 }
 
-static long btrfs_ioctl_clone_range(struct file *file, void __user *argp)
+ssize_t btrfs_copy_file_range(struct file *file_in, loff_t pos_in,
+			      struct file *file_out, loff_t pos_out,
+			      size_t len, unsigned int flags)
 {
-	struct btrfs_ioctl_clone_range_args args;
+	ssize_t ret;
 
-	if (copy_from_user(&args, argp, sizeof(args)))
-		return -EFAULT;
-	return btrfs_ioctl_clone(file, args.src_fd, args.src_offset,
-				 args.src_length, args.dest_offset);
+	ret = btrfs_clone_files(file_out, file_in, pos_in, len, pos_out);
+	if (ret == 0)
+		ret = len;
+	return ret;
+}
+
+int btrfs_clone_file_range(struct file *src_file, loff_t off,
+		struct file *dst_file, loff_t destoff, u64 len)
+{
+	return btrfs_clone_files(dst_file, src_file, off, len, destoff);
 }
 
 /*
@@ -5485,10 +5377,6 @@
 		return btrfs_ioctl_dev_info(root, argp);
 	case BTRFS_IOC_BALANCE:
 		return btrfs_ioctl_balance(file, NULL);
-	case BTRFS_IOC_CLONE:
-		return btrfs_ioctl_clone(file, arg, 0, 0, 0);
-	case BTRFS_IOC_CLONE_RANGE:
-		return btrfs_ioctl_clone_range(file, argp);
 	case BTRFS_IOC_TRANS_START:
 		return btrfs_ioctl_trans_start(file);
 	case BTRFS_IOC_TRANS_END:
@@ -5566,8 +5454,6 @@
 		return btrfs_ioctl_get_fslabel(file, argp);
 	case BTRFS_IOC_SET_FSLABEL:
 		return btrfs_ioctl_set_fslabel(file, argp);
-	case BTRFS_IOC_FILE_EXTENT_SAME:
-		return btrfs_ioctl_file_extent_same(file, argp);
 	case BTRFS_IOC_GET_SUPPORTED_FEATURES:
 		return btrfs_ioctl_get_supported_features(file, argp);
 	case BTRFS_IOC_GET_FEATURES:
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 24154e4..a0434c17 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1514,9 +1514,7 @@
 		if ((flags ^ s->s_flags) & MS_RDONLY)
 			error = -EBUSY;
 	} else {
-		char b[BDEVNAME_SIZE];
-
-		strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id));
+		snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev);
 		btrfs_sb(s)->bdev_holder = fs_type;
 		error = btrfs_fill_super(s, fs_devices, data,
 					 flags & MS_SILENT ? 1 : 0);
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index 1fcd7b6..7cbef1a 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -351,137 +351,89 @@
 	return ret;
 }
 
-/*
- * List of handlers for synthetic system.* attributes.  All real ondisk
- * attributes are handled directly.
- */
+static int btrfs_xattr_handler_get(const struct xattr_handler *handler,
+				   struct dentry *dentry, const char *name,
+				   void *buffer, size_t size)
+{
+	struct inode *inode = d_inode(dentry);
+
+	name = xattr_full_name(handler, name);
+	return __btrfs_getxattr(inode, name, buffer, size);
+}
+
+static int btrfs_xattr_handler_set(const struct xattr_handler *handler,
+				   struct dentry *dentry, const char *name,
+				   const void *buffer, size_t size,
+				   int flags)
+{
+	struct inode *inode = d_inode(dentry);
+
+	name = xattr_full_name(handler, name);
+	return __btrfs_setxattr(NULL, inode, name, buffer, size, flags);
+}
+
+static int btrfs_xattr_handler_set_prop(const struct xattr_handler *handler,
+					struct dentry *dentry,
+					const char *name, const void *value,
+					size_t size, int flags)
+{
+	name = xattr_full_name(handler, name);
+	return btrfs_set_prop(d_inode(dentry), name, value, size, flags);
+}
+
+static const struct xattr_handler btrfs_security_xattr_handler = {
+	.prefix = XATTR_SECURITY_PREFIX,
+	.get = btrfs_xattr_handler_get,
+	.set = btrfs_xattr_handler_set,
+};
+
+static const struct xattr_handler btrfs_trusted_xattr_handler = {
+	.prefix = XATTR_TRUSTED_PREFIX,
+	.get = btrfs_xattr_handler_get,
+	.set = btrfs_xattr_handler_set,
+};
+
+static const struct xattr_handler btrfs_user_xattr_handler = {
+	.prefix = XATTR_USER_PREFIX,
+	.get = btrfs_xattr_handler_get,
+	.set = btrfs_xattr_handler_set,
+};
+
+static const struct xattr_handler btrfs_btrfs_xattr_handler = {
+	.prefix = XATTR_BTRFS_PREFIX,
+	.get = btrfs_xattr_handler_get,
+	.set = btrfs_xattr_handler_set_prop,
+};
+
 const struct xattr_handler *btrfs_xattr_handlers[] = {
+	&btrfs_security_xattr_handler,
 #ifdef CONFIG_BTRFS_FS_POSIX_ACL
 	&posix_acl_access_xattr_handler,
 	&posix_acl_default_xattr_handler,
 #endif
+	&btrfs_trusted_xattr_handler,
+	&btrfs_user_xattr_handler,
+	&btrfs_btrfs_xattr_handler,
 	NULL,
 };
 
-/*
- * Check if the attribute is in a supported namespace.
- *
- * This is applied after the check for the synthetic attributes in the system
- * namespace.
- */
-static int btrfs_is_valid_xattr(const char *name)
-{
-	int len = strlen(name);
-	int prefixlen = 0;
-
-	if (!strncmp(name, XATTR_SECURITY_PREFIX,
-			XATTR_SECURITY_PREFIX_LEN))
-		prefixlen = XATTR_SECURITY_PREFIX_LEN;
-	else if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
-		prefixlen = XATTR_SYSTEM_PREFIX_LEN;
-	else if (!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN))
-		prefixlen = XATTR_TRUSTED_PREFIX_LEN;
-	else if (!strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN))
-		prefixlen = XATTR_USER_PREFIX_LEN;
-	else if (!strncmp(name, XATTR_BTRFS_PREFIX, XATTR_BTRFS_PREFIX_LEN))
-		prefixlen = XATTR_BTRFS_PREFIX_LEN;
-	else
-		return -EOPNOTSUPP;
-
-	/*
-	 * The name cannot consist of just prefix
-	 */
-	if (len <= prefixlen)
-		return -EINVAL;
-
-	return 0;
-}
-
-ssize_t btrfs_getxattr(struct dentry *dentry, const char *name,
-		       void *buffer, size_t size)
-{
-	int ret;
-
-	/*
-	 * If this is a request for a synthetic attribute in the system.*
-	 * namespace use the generic infrastructure to resolve a handler
-	 * for it via sb->s_xattr.
-	 */
-	if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
-		return generic_getxattr(dentry, name, buffer, size);
-
-	ret = btrfs_is_valid_xattr(name);
-	if (ret)
-		return ret;
-	return __btrfs_getxattr(d_inode(dentry), name, buffer, size);
-}
-
 int btrfs_setxattr(struct dentry *dentry, const char *name, const void *value,
 		   size_t size, int flags)
 {
 	struct btrfs_root *root = BTRFS_I(d_inode(dentry))->root;
-	int ret;
 
-	/*
-	 * The permission on security.* and system.* is not checked
-	 * in permission().
-	 */
 	if (btrfs_root_readonly(root))
 		return -EROFS;
-
-	/*
-	 * If this is a request for a synthetic attribute in the system.*
-	 * namespace use the generic infrastructure to resolve a handler
-	 * for it via sb->s_xattr.
-	 */
-	if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
-		return generic_setxattr(dentry, name, value, size, flags);
-
-	ret = btrfs_is_valid_xattr(name);
-	if (ret)
-		return ret;
-
-	if (!strncmp(name, XATTR_BTRFS_PREFIX, XATTR_BTRFS_PREFIX_LEN))
-		return btrfs_set_prop(d_inode(dentry), name,
-				      value, size, flags);
-
-	if (size == 0)
-		value = "";  /* empty EA, do not remove */
-
-	return __btrfs_setxattr(NULL, d_inode(dentry), name, value, size,
-				flags);
+	return generic_setxattr(dentry, name, value, size, flags);
 }
 
 int btrfs_removexattr(struct dentry *dentry, const char *name)
 {
 	struct btrfs_root *root = BTRFS_I(d_inode(dentry))->root;
-	int ret;
 
-	/*
-	 * The permission on security.* and system.* is not checked
-	 * in permission().
-	 */
 	if (btrfs_root_readonly(root))
 		return -EROFS;
-
-	/*
-	 * If this is a request for a synthetic attribute in the system.*
-	 * namespace use the generic infrastructure to resolve a handler
-	 * for it via sb->s_xattr.
-	 */
-	if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
-		return generic_removexattr(dentry, name);
-
-	ret = btrfs_is_valid_xattr(name);
-	if (ret)
-		return ret;
-
-	if (!strncmp(name, XATTR_BTRFS_PREFIX, XATTR_BTRFS_PREFIX_LEN))
-		return btrfs_set_prop(d_inode(dentry), name,
-				      NULL, 0, XATTR_REPLACE);
-
-	return __btrfs_setxattr(NULL, d_inode(dentry), name, NULL, 0,
-				XATTR_REPLACE);
+	return generic_removexattr(dentry, name);
 }
 
 static int btrfs_initxattrs(struct inode *inode,
diff --git a/fs/btrfs/xattr.h b/fs/btrfs/xattr.h
index 5049608..96807b3 100644
--- a/fs/btrfs/xattr.h
+++ b/fs/btrfs/xattr.h
@@ -28,8 +28,6 @@
 extern int __btrfs_setxattr(struct btrfs_trans_handle *trans,
 			    struct inode *inode, const char *name,
 			    const void *value, size_t size, int flags);
-extern ssize_t btrfs_getxattr(struct dentry *dentry, const char *name,
-		void *buffer, size_t size);
 extern int btrfs_setxattr(struct dentry *dentry, const char *name,
 		const void *value, size_t size, int flags);
 extern int btrfs_removexattr(struct dentry *dentry, const char *name);
diff --git a/fs/buffer.c b/fs/buffer.c
index 4f4cd95..e1632ab 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -134,13 +134,10 @@
 
 static void buffer_io_error(struct buffer_head *bh, char *msg)
 {
-	char b[BDEVNAME_SIZE];
-
 	if (!test_bit(BH_Quiet, &bh->b_state))
 		printk_ratelimited(KERN_ERR
-			"Buffer I/O error on dev %s, logical block %llu%s\n",
-			bdevname(bh->b_bdev, b),
-			(unsigned long long)bh->b_blocknr, msg);
+			"Buffer I/O error on dev %pg, logical block %llu%s\n",
+			bh->b_bdev, (unsigned long long)bh->b_blocknr, msg);
 }
 
 /*
@@ -237,15 +234,13 @@
 	 * elsewhere, don't buffer_error if we had some unmapped buffers
 	 */
 	if (all_mapped) {
-		char b[BDEVNAME_SIZE];
-
 		printk("__find_get_block_slow() failed. "
 			"block=%llu, b_blocknr=%llu\n",
 			(unsigned long long)block,
 			(unsigned long long)bh->b_blocknr);
 		printk("b_state=0x%08lx, b_size=%zu\n",
 			bh->b_state, bh->b_size);
-		printk("device %s blocksize: %d\n", bdevname(bdev, b),
+		printk("device %pg blocksize: %d\n", bdev,
 			1 << bd_inode->i_blkbits);
 	}
 out_unlock:
@@ -531,10 +526,8 @@
 
 static void do_thaw_one(struct super_block *sb, void *unused)
 {
-	char b[BDEVNAME_SIZE];
 	while (sb->s_bdev && !thaw_bdev(sb->s_bdev, sb))
-		printk(KERN_WARNING "Emergency Thaw on %s\n",
-		       bdevname(sb->s_bdev, b));
+		printk(KERN_WARNING "Emergency Thaw on %pg\n", sb->s_bdev);
 }
 
 static void do_thaw_all(struct work_struct *work)
@@ -1074,12 +1067,10 @@
 	 * pagecache index.  (this comparison is done using sector_t types).
 	 */
 	if (unlikely(index != block >> sizebits)) {
-		char b[BDEVNAME_SIZE];
-
 		printk(KERN_ERR "%s: requested out-of-range block %llu for "
-			"device %s\n",
+			"device %pg\n",
 			__func__, (unsigned long long)block,
-			bdevname(bdev, b));
+			bdev);
 		return -EIO;
 	}
 
diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c
index f601def..452e98d 100644
--- a/fs/cachefiles/daemon.c
+++ b/fs/cachefiles/daemon.c
@@ -226,15 +226,9 @@
 		return -EOPNOTSUPP;
 
 	/* drag the command string into the kernel so we can parse it */
-	data = kmalloc(datalen + 1, GFP_KERNEL);
-	if (!data)
-		return -ENOMEM;
-
-	ret = -EFAULT;
-	if (copy_from_user(data, _data, datalen) != 0)
-		goto error;
-
-	data[datalen] = '\0';
+	data = memdup_user_nul(_data, datalen);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
 
 	ret = -EINVAL;
 	if (memchr(data, '\0', datalen))
diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c
index 8f84646..f197084 100644
--- a/fs/ceph/acl.c
+++ b/fs/ceph/acl.c
@@ -49,10 +49,10 @@
 
 	switch (type) {
 	case ACL_TYPE_ACCESS:
-		name = POSIX_ACL_XATTR_ACCESS;
+		name = XATTR_NAME_POSIX_ACL_ACCESS;
 		break;
 	case ACL_TYPE_DEFAULT:
-		name = POSIX_ACL_XATTR_DEFAULT;
+		name = XATTR_NAME_POSIX_ACL_DEFAULT;
 		break;
 	default:
 		BUG();
@@ -92,7 +92,7 @@
 
 	switch (type) {
 	case ACL_TYPE_ACCESS:
-		name = POSIX_ACL_XATTR_ACCESS;
+		name = XATTR_NAME_POSIX_ACL_ACCESS;
 		if (acl) {
 			ret = posix_acl_equiv_mode(acl, &new_mode);
 			if (ret < 0)
@@ -106,7 +106,7 @@
 			ret = acl ? -EINVAL : 0;
 			goto out;
 		}
-		name = POSIX_ACL_XATTR_DEFAULT;
+		name = XATTR_NAME_POSIX_ACL_DEFAULT;
 		break;
 	default:
 		ret = -EINVAL;
@@ -202,11 +202,11 @@
 	ceph_pagelist_encode_32(pagelist, acl && default_acl ? 2 : 1);
 
 	if (acl) {
-		size_t len = strlen(POSIX_ACL_XATTR_ACCESS);
+		size_t len = strlen(XATTR_NAME_POSIX_ACL_ACCESS);
 		err = ceph_pagelist_reserve(pagelist, len + val_size1 + 8);
 		if (err)
 			goto out_err;
-		ceph_pagelist_encode_string(pagelist, POSIX_ACL_XATTR_ACCESS,
+		ceph_pagelist_encode_string(pagelist, XATTR_NAME_POSIX_ACL_ACCESS,
 					    len);
 		err = posix_acl_to_xattr(&init_user_ns, acl,
 					 tmp_buf, val_size1);
@@ -216,12 +216,12 @@
 		ceph_pagelist_append(pagelist, tmp_buf, val_size1);
 	}
 	if (default_acl) {
-		size_t len = strlen(POSIX_ACL_XATTR_DEFAULT);
+		size_t len = strlen(XATTR_NAME_POSIX_ACL_DEFAULT);
 		err = ceph_pagelist_reserve(pagelist, len + val_size2 + 8);
 		if (err)
 			goto out_err;
 		err = ceph_pagelist_encode_string(pagelist,
-						  POSIX_ACL_XATTR_DEFAULT, len);
+						  XATTR_NAME_POSIX_ACL_DEFAULT, len);
 		err = posix_acl_to_xattr(&init_user_ns, default_acl,
 					 tmp_buf, val_size2);
 		if (err < 0)
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 498dcfa..da55eb8 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1756,7 +1756,7 @@
  */
 static const struct inode_operations ceph_symlink_iops = {
 	.readlink = generic_readlink,
-	.follow_link = simple_follow_link,
+	.get_link = simple_get_link,
 	.setattr = ceph_setattr,
 	.getattr = ceph_getattr,
 	.setxattr = ceph_setxattr,
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index cbc0f4b..b7fcb31 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -900,8 +900,7 @@
 
 const struct inode_operations cifs_symlink_inode_ops = {
 	.readlink = generic_readlink,
-	.follow_link = cifs_follow_link,
-	.put_link = kfree_put_link,
+	.get_link = cifs_get_link,
 	.permission = cifs_permission,
 	/* BB add the following two eventually */
 	/* revalidate: cifs_revalidate,
@@ -914,6 +913,59 @@
 #endif
 };
 
+static int cifs_clone_file_range(struct file *src_file, loff_t off,
+		struct file *dst_file, loff_t destoff, u64 len)
+{
+	struct inode *src_inode = file_inode(src_file);
+	struct inode *target_inode = file_inode(dst_file);
+	struct cifsFileInfo *smb_file_src = src_file->private_data;
+	struct cifsFileInfo *smb_file_target = dst_file->private_data;
+	struct cifs_tcon *target_tcon = tlink_tcon(smb_file_target->tlink);
+	unsigned int xid;
+	int rc;
+
+	cifs_dbg(FYI, "clone range\n");
+
+	xid = get_xid();
+
+	if (!src_file->private_data || !dst_file->private_data) {
+		rc = -EBADF;
+		cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n");
+		goto out;
+	}
+
+	/*
+	 * Note: cifs case is easier than btrfs since server responsible for
+	 * checks for proper open modes and file type and if it wants
+	 * server could even support copy of range where source = target
+	 */
+	lock_two_nondirectories(target_inode, src_inode);
+
+	if (len == 0)
+		len = src_inode->i_size - off;
+
+	cifs_dbg(FYI, "about to flush pages\n");
+	/* should we flush first and last page first */
+	truncate_inode_pages_range(&target_inode->i_data, destoff,
+				   PAGE_CACHE_ALIGN(destoff + len)-1);
+
+	if (target_tcon->ses->server->ops->duplicate_extents)
+		rc = target_tcon->ses->server->ops->duplicate_extents(xid,
+			smb_file_src, smb_file_target, off, len, destoff);
+	else
+		rc = -EOPNOTSUPP;
+
+	/* force revalidate of size and timestamps of target file now
+	   that target is updated on the server */
+	CIFS_I(target_inode)->time = 0;
+	/* although unlocking in the reverse order from locking is not
+	   strictly necessary here it is a little cleaner to be consistent */
+	unlock_two_nondirectories(src_inode, target_inode);
+out:
+	free_xid(xid);
+	return rc;
+}
+
 const struct file_operations cifs_file_ops = {
 	.read_iter = cifs_loose_read_iter,
 	.write_iter = cifs_file_write_iter,
@@ -926,6 +978,7 @@
 	.splice_read = generic_file_splice_read,
 	.llseek = cifs_llseek,
 	.unlocked_ioctl	= cifs_ioctl,
+	.clone_file_range = cifs_clone_file_range,
 	.setlease = cifs_setlease,
 	.fallocate = cifs_fallocate,
 };
@@ -942,6 +995,8 @@
 	.splice_read = generic_file_splice_read,
 	.llseek = cifs_llseek,
 	.unlocked_ioctl	= cifs_ioctl,
+	.clone_file_range = cifs_clone_file_range,
+	.clone_file_range = cifs_clone_file_range,
 	.setlease = cifs_setlease,
 	.fallocate = cifs_fallocate,
 };
@@ -958,6 +1013,7 @@
 	.mmap = cifs_file_mmap,
 	.splice_read = generic_file_splice_read,
 	.unlocked_ioctl  = cifs_ioctl,
+	.clone_file_range = cifs_clone_file_range,
 	.llseek = cifs_llseek,
 	.setlease = cifs_setlease,
 	.fallocate = cifs_fallocate,
@@ -974,6 +1030,7 @@
 	.splice_read = generic_file_splice_read,
 	.llseek = cifs_llseek,
 	.unlocked_ioctl	= cifs_ioctl,
+	.clone_file_range = cifs_clone_file_range,
 	.setlease = cifs_setlease,
 	.fallocate = cifs_fallocate,
 };
@@ -989,6 +1046,7 @@
 	.splice_read = generic_file_splice_read,
 	.llseek = cifs_llseek,
 	.unlocked_ioctl	= cifs_ioctl,
+	.clone_file_range = cifs_clone_file_range,
 	.setlease = cifs_setlease,
 	.fallocate = cifs_fallocate,
 };
@@ -1004,6 +1062,7 @@
 	.mmap = cifs_file_mmap,
 	.splice_read = generic_file_splice_read,
 	.unlocked_ioctl  = cifs_ioctl,
+	.clone_file_range = cifs_clone_file_range,
 	.llseek = cifs_llseek,
 	.setlease = cifs_setlease,
 	.fallocate = cifs_fallocate,
@@ -1014,6 +1073,7 @@
 	.release = cifs_closedir,
 	.read    = generic_read_dir,
 	.unlocked_ioctl  = cifs_ioctl,
+	.clone_file_range = cifs_clone_file_range,
 	.llseek = generic_file_llseek,
 };
 
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index c3cc160..68c4547 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -120,9 +120,8 @@
 #endif
 
 /* Functions related to symlinks */
-extern const char *cifs_follow_link(struct dentry *direntry, void **cookie);
-extern int cifs_readlink(struct dentry *direntry, char __user *buffer,
-			 int buflen);
+extern const char *cifs_get_link(struct dentry *, struct inode *,
+			struct delayed_call *);
 extern int cifs_symlink(struct inode *inode, struct dentry *direntry,
 			const char *symname);
 extern int	cifs_removexattr(struct dentry *, const char *);
@@ -131,7 +130,6 @@
 extern ssize_t	cifs_getxattr(struct dentry *, const char *, void *, size_t);
 extern ssize_t	cifs_listxattr(struct dentry *, char *, size_t);
 extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg);
-
 #ifdef CONFIG_CIFS_NFSD_EXPORT
 extern const struct export_operations cifs_export_ops;
 #endif /* CONFIG_CIFS_NFSD_EXPORT */
diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c
index 35cf990..7a3b84e 100644
--- a/fs/cifs/ioctl.c
+++ b/fs/cifs/ioctl.c
@@ -34,18 +34,69 @@
 #include "cifs_ioctl.h"
 #include <linux/btrfs.h>
 
+static int cifs_file_clone_range(unsigned int xid, struct file *src_file,
+			  struct file *dst_file)
+{
+	struct inode *src_inode = file_inode(src_file);
+	struct inode *target_inode = file_inode(dst_file);
+	struct cifsFileInfo *smb_file_src;
+	struct cifsFileInfo *smb_file_target;
+	struct cifs_tcon *src_tcon;
+	struct cifs_tcon *target_tcon;
+	int rc;
+
+	cifs_dbg(FYI, "ioctl clone range\n");
+
+	if (!src_file->private_data || !dst_file->private_data) {
+		rc = -EBADF;
+		cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n");
+		goto out;
+	}
+
+	rc = -EXDEV;
+	smb_file_target = dst_file->private_data;
+	smb_file_src = src_file->private_data;
+	src_tcon = tlink_tcon(smb_file_src->tlink);
+	target_tcon = tlink_tcon(smb_file_target->tlink);
+
+	if (src_tcon->ses != target_tcon->ses) {
+		cifs_dbg(VFS, "source and target of copy not on same server\n");
+		goto out;
+	}
+
+	/*
+	 * Note: cifs case is easier than btrfs since server responsible for
+	 * checks for proper open modes and file type and if it wants
+	 * server could even support copy of range where source = target
+	 */
+	lock_two_nondirectories(target_inode, src_inode);
+
+	cifs_dbg(FYI, "about to flush pages\n");
+	/* should we flush first and last page first */
+	truncate_inode_pages(&target_inode->i_data, 0);
+
+	if (target_tcon->ses->server->ops->clone_range)
+		rc = target_tcon->ses->server->ops->clone_range(xid,
+			smb_file_src, smb_file_target, 0, src_inode->i_size, 0);
+	else
+		rc = -EOPNOTSUPP;
+
+	/* force revalidate of size and timestamps of target file now
+	   that target is updated on the server */
+	CIFS_I(target_inode)->time = 0;
+	/* although unlocking in the reverse order from locking is not
+	   strictly necessary here it is a little cleaner to be consistent */
+	unlock_two_nondirectories(src_inode, target_inode);
+out:
+	return rc;
+}
+
 static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file,
-			unsigned long srcfd, u64 off, u64 len, u64 destoff,
-			bool dup_extents)
+			unsigned long srcfd)
 {
 	int rc;
-	struct cifsFileInfo *smb_file_target = dst_file->private_data;
-	struct inode *target_inode = file_inode(dst_file);
-	struct cifs_tcon *target_tcon;
 	struct fd src_file;
-	struct cifsFileInfo *smb_file_src;
 	struct inode *src_inode;
-	struct cifs_tcon *src_tcon;
 
 	cifs_dbg(FYI, "ioctl clone range\n");
 	/* the destination must be opened for writing */
@@ -73,69 +124,13 @@
 		goto out_fput;
 	}
 
-	if ((!src_file.file->private_data) || (!dst_file->private_data)) {
-		rc = -EBADF;
-		cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n");
-		goto out_fput;
-	}
-
-	rc = -EXDEV;
-	smb_file_target = dst_file->private_data;
-	smb_file_src = src_file.file->private_data;
-	src_tcon = tlink_tcon(smb_file_src->tlink);
-	target_tcon = tlink_tcon(smb_file_target->tlink);
-
-	/* check source and target on same server (or volume if dup_extents) */
-	if (dup_extents && (src_tcon != target_tcon)) {
-		cifs_dbg(VFS, "source and target of copy not on same share\n");
-		goto out_fput;
-	}
-
-	if (!dup_extents && (src_tcon->ses != target_tcon->ses)) {
-		cifs_dbg(VFS, "source and target of copy not on same server\n");
-		goto out_fput;
-	}
-
 	src_inode = file_inode(src_file.file);
 	rc = -EINVAL;
 	if (S_ISDIR(src_inode->i_mode))
 		goto out_fput;
 
-	/*
-	 * Note: cifs case is easier than btrfs since server responsible for
-	 * checks for proper open modes and file type and if it wants
-	 * server could even support copy of range where source = target
-	 */
-	lock_two_nondirectories(target_inode, src_inode);
+	rc = cifs_file_clone_range(xid, src_file.file, dst_file);
 
-	/* determine range to clone */
-	rc = -EINVAL;
-	if (off + len > src_inode->i_size || off + len < off)
-		goto out_unlock;
-	if (len == 0)
-		len = src_inode->i_size - off;
-
-	cifs_dbg(FYI, "about to flush pages\n");
-	/* should we flush first and last page first */
-	truncate_inode_pages_range(&target_inode->i_data, destoff,
-				   PAGE_CACHE_ALIGN(destoff + len)-1);
-
-	if (dup_extents && target_tcon->ses->server->ops->duplicate_extents)
-		rc = target_tcon->ses->server->ops->duplicate_extents(xid,
-			smb_file_src, smb_file_target, off, len, destoff);
-	else if (!dup_extents && target_tcon->ses->server->ops->clone_range)
-		rc = target_tcon->ses->server->ops->clone_range(xid,
-			smb_file_src, smb_file_target, off, len, destoff);
-	else
-		rc = -EOPNOTSUPP;
-
-	/* force revalidate of size and timestamps of target file now
-	   that target is updated on the server */
-	CIFS_I(target_inode)->time = 0;
-out_unlock:
-	/* although unlocking in the reverse order from locking is not
-	   strictly necessary here it is a little cleaner to be consistent */
-	unlock_two_nondirectories(src_inode, target_inode);
 out_fput:
 	fdput(src_file);
 out_drop_write:
@@ -256,10 +251,7 @@
 			}
 			break;
 		case CIFS_IOC_COPYCHUNK_FILE:
-			rc = cifs_ioctl_clone(xid, filep, arg, 0, 0, 0, false);
-			break;
-		case BTRFS_IOC_CLONE:
-			rc = cifs_ioctl_clone(xid, filep, arg, 0, 0, 0, true);
+			rc = cifs_ioctl_clone(xid, filep, arg);
 			break;
 		case CIFS_IOC_SET_INTEGRITY:
 			if (pSMBFile == NULL)
diff --git a/fs/cifs/link.c b/fs/cifs/link.c
index e3548f7..062c237 100644
--- a/fs/cifs/link.c
+++ b/fs/cifs/link.c
@@ -627,9 +627,9 @@
 }
 
 const char *
-cifs_follow_link(struct dentry *direntry, void **cookie)
+cifs_get_link(struct dentry *direntry, struct inode *inode,
+	      struct delayed_call *done)
 {
-	struct inode *inode = d_inode(direntry);
 	int rc = -ENOMEM;
 	unsigned int xid;
 	char *full_path = NULL;
@@ -639,6 +639,9 @@
 	struct cifs_tcon *tcon;
 	struct TCP_Server_Info *server;
 
+	if (!direntry)
+		return ERR_PTR(-ECHILD);
+
 	xid = get_xid();
 
 	tlink = cifs_sb_tlink(cifs_sb);
@@ -678,7 +681,8 @@
 		kfree(target_path);
 		return ERR_PTR(rc);
 	}
-	return *cookie = target_path;
+	set_delayed_call(done, kfree_link, target_path);
+	return target_path;
 }
 
 int
diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c
index ff9e1f8..f5dc2f0 100644
--- a/fs/cifs/xattr.c
+++ b/fs/cifs/xattr.c
@@ -190,8 +190,8 @@
 #endif /* CONFIG_CIFS_ACL */
 	} else {
 		int temp;
-		temp = strncmp(ea_name, POSIX_ACL_XATTR_ACCESS,
-			strlen(POSIX_ACL_XATTR_ACCESS));
+		temp = strncmp(ea_name, XATTR_NAME_POSIX_ACL_ACCESS,
+			strlen(XATTR_NAME_POSIX_ACL_ACCESS));
 		if (temp == 0) {
 #ifdef CONFIG_CIFS_POSIX
 			if (sb->s_flags & MS_POSIXACL)
@@ -203,8 +203,8 @@
 #else
 			cifs_dbg(FYI, "set POSIX ACL not supported\n");
 #endif
-		} else if (strncmp(ea_name, POSIX_ACL_XATTR_DEFAULT,
-				   strlen(POSIX_ACL_XATTR_DEFAULT)) == 0) {
+		} else if (strncmp(ea_name, XATTR_NAME_POSIX_ACL_DEFAULT,
+				   strlen(XATTR_NAME_POSIX_ACL_DEFAULT)) == 0) {
 #ifdef CONFIG_CIFS_POSIX
 			if (sb->s_flags & MS_POSIXACL)
 				rc = CIFSSMBSetPosixACL(xid, pTcon, full_path,
@@ -292,8 +292,8 @@
 			rc = pTcon->ses->server->ops->query_all_EAs(xid, pTcon,
 				full_path, ea_name, ea_value, buf_size,
 				cifs_sb->local_nls, cifs_remap(cifs_sb));
-	} else if (strncmp(ea_name, POSIX_ACL_XATTR_ACCESS,
-			  strlen(POSIX_ACL_XATTR_ACCESS)) == 0) {
+	} else if (strncmp(ea_name, XATTR_NAME_POSIX_ACL_ACCESS,
+			  strlen(XATTR_NAME_POSIX_ACL_ACCESS)) == 0) {
 #ifdef CONFIG_CIFS_POSIX
 		if (sb->s_flags & MS_POSIXACL)
 			rc = CIFSSMBGetPosixACL(xid, pTcon, full_path,
@@ -303,8 +303,8 @@
 #else
 		cifs_dbg(FYI, "Query POSIX ACL not supported yet\n");
 #endif /* CONFIG_CIFS_POSIX */
-	} else if (strncmp(ea_name, POSIX_ACL_XATTR_DEFAULT,
-			  strlen(POSIX_ACL_XATTR_DEFAULT)) == 0) {
+	} else if (strncmp(ea_name, XATTR_NAME_POSIX_ACL_DEFAULT,
+			  strlen(XATTR_NAME_POSIX_ACL_DEFAULT)) == 0) {
 #ifdef CONFIG_CIFS_POSIX
 		if (sb->s_flags & MS_POSIXACL)
 			rc = CIFSSMBGetPosixACL(xid, pTcon, full_path,
diff --git a/fs/coda/cnode.c b/fs/coda/cnode.c
index 7740b1c..1bfb7ba 100644
--- a/fs/coda/cnode.c
+++ b/fs/coda/cnode.c
@@ -8,6 +8,7 @@
 
 #include <linux/coda.h>
 #include <linux/coda_psdev.h>
+#include <linux/pagemap.h>
 #include "coda_linux.h"
 
 static inline int coda_fideq(struct CodaFid *fid1, struct CodaFid *fid2)
@@ -17,8 +18,7 @@
 
 static const struct inode_operations coda_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= page_follow_link_light,
-	.put_link	= page_put_link,
+	.get_link	= page_get_link,
 	.setattr	= coda_setattr,
 };
 
@@ -35,6 +35,7 @@
                 inode->i_fop = &coda_dir_operations;
         } else if (S_ISLNK(inode->i_mode)) {
 		inode->i_op = &coda_symlink_inode_operations;
+		inode_nohighmem(inode);
 		inode->i_data.a_ops = &coda_symlink_aops;
 		inode->i_mapping = &inode->i_data;
 	} else
diff --git a/fs/coda/symlink.c b/fs/coda/symlink.c
index ab94ef6..03736e2 100644
--- a/fs/coda/symlink.c
+++ b/fs/coda/symlink.c
@@ -26,7 +26,7 @@
 	int error;
 	struct coda_inode_info *cii;
 	unsigned int len = PAGE_SIZE;
-	char *p = kmap(page);
+	char *p = page_address(page);
 
 	cii = ITOC(inode);
 
@@ -34,13 +34,11 @@
 	if (error)
 		goto fail;
 	SetPageUptodate(page);
-	kunmap(page);
 	unlock_page(page);
 	return 0;
 
 fail:
 	SetPageError(page);
-	kunmap(page);
 	unlock_page(page);
 	return error;
 }
diff --git a/fs/compat.c b/fs/compat.c
index 6fd272d..a71936a3 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -792,7 +792,7 @@
 		       const void __user *, data)
 {
 	char *kernel_type;
-	unsigned long data_page;
+	void *options;
 	char *kernel_dev;
 	int retval;
 
@@ -806,26 +806,25 @@
 	if (IS_ERR(kernel_dev))
 		goto out1;
 
-	retval = copy_mount_options(data, &data_page);
-	if (retval < 0)
+	options = copy_mount_options(data);
+	retval = PTR_ERR(options);
+	if (IS_ERR(options))
 		goto out2;
 
-	retval = -EINVAL;
-
-	if (kernel_type && data_page) {
+	if (kernel_type && options) {
 		if (!strcmp(kernel_type, NCPFS_NAME)) {
-			do_ncp_super_data_conv((void *)data_page);
+			do_ncp_super_data_conv(options);
 		} else if (!strcmp(kernel_type, NFS4_NAME)) {
-			if (do_nfs4_super_data_conv((void *) data_page))
+			retval = -EINVAL;
+			if (do_nfs4_super_data_conv(options))
 				goto out3;
 		}
 	}
 
-	retval = do_mount(kernel_dev, dir_name, kernel_type,
-			flags, (void*)data_page);
+	retval = do_mount(kernel_dev, dir_name, kernel_type, flags, options);
 
  out3:
-	free_page(data_page);
+	kfree(options);
  out2:
 	kfree(kernel_dev);
  out1:
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index dcf26537..a5b8eb6 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -58,6 +58,8 @@
 #include <linux/atalk.h>
 #include <linux/gfp.h>
 
+#include "internal.h"
+
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_sock.h>
 #include <net/bluetooth/rfcomm.h>
@@ -115,19 +117,38 @@
 #include <asm/fbio.h>
 #endif
 
-static int w_long(unsigned int fd, unsigned int cmd,
-		compat_ulong_t __user *argp)
-{
-	mm_segment_t old_fs = get_fs();
-	int err;
-	unsigned long val;
+#define convert_in_user(srcptr, dstptr)			\
+({							\
+	typeof(*srcptr) val;				\
+							\
+	get_user(val, srcptr) || put_user(val, dstptr);	\
+})
 
-	set_fs (KERNEL_DS);
-	err = sys_ioctl(fd, cmd, (unsigned long)&val);
-	set_fs (old_fs);
-	if (!err && put_user(val, argp))
+static int do_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	int err;
+
+	err = security_file_ioctl(file, cmd, arg);
+	if (err)
+		return err;
+
+	return vfs_ioctl(file, cmd, arg);
+}
+
+static int w_long(struct file *file,
+		unsigned int cmd, compat_ulong_t __user *argp)
+{
+	int err;
+	unsigned long __user *valp = compat_alloc_user_space(sizeof(*valp));
+
+	if (valp == NULL)
 		return -EFAULT;
-	return err;
+	err = do_ioctl(file, cmd, (unsigned long)valp);
+	if (err)
+		return err;
+	if (convert_in_user(valp, argp))
+		return -EFAULT;
+	return 0;
 }
 
 struct compat_video_event {
@@ -139,23 +160,23 @@
 	} u;
 };
 
-static int do_video_get_event(unsigned int fd, unsigned int cmd,
-		struct compat_video_event __user *up)
+static int do_video_get_event(struct file *file,
+		unsigned int cmd, struct compat_video_event __user *up)
 {
-	struct video_event kevent;
-	mm_segment_t old_fs = get_fs();
+	struct video_event __user *kevent =
+		compat_alloc_user_space(sizeof(*kevent));
 	int err;
 
-	set_fs(KERNEL_DS);
-	err = sys_ioctl(fd, cmd, (unsigned long) &kevent);
-	set_fs(old_fs);
+	if (kevent == NULL)
+		return -EFAULT;
 
+	err = do_ioctl(file, cmd, (unsigned long)kevent);
 	if (!err) {
-		err  = put_user(kevent.type, &up->type);
-		err |= put_user(kevent.timestamp, &up->timestamp);
-		err |= put_user(kevent.u.size.w, &up->u.size.w);
-		err |= put_user(kevent.u.size.h, &up->u.size.h);
-		err |= put_user(kevent.u.size.aspect_ratio,
+		err  = convert_in_user(&kevent->type, &up->type);
+		err |= convert_in_user(&kevent->timestamp, &up->timestamp);
+		err |= convert_in_user(&kevent->u.size.w, &up->u.size.w);
+		err |= convert_in_user(&kevent->u.size.h, &up->u.size.h);
+		err |= convert_in_user(&kevent->u.size.aspect_ratio,
 				&up->u.size.aspect_ratio);
 		if (err)
 			err = -EFAULT;
@@ -169,8 +190,8 @@
         int32_t size;
 };
 
-static int do_video_stillpicture(unsigned int fd, unsigned int cmd,
-	struct compat_video_still_picture __user *up)
+static int do_video_stillpicture(struct file *file,
+		unsigned int cmd, struct compat_video_still_picture __user *up)
 {
 	struct video_still_picture __user *up_native;
 	compat_uptr_t fp;
@@ -190,7 +211,7 @@
 	if (err)
 		return -EFAULT;
 
-	err = sys_ioctl(fd, cmd, (unsigned long) up_native);
+	err = do_ioctl(file, cmd, (unsigned long) up_native);
 
 	return err;
 }
@@ -200,8 +221,8 @@
 	compat_uptr_t palette;
 };
 
-static int do_video_set_spu_palette(unsigned int fd, unsigned int cmd,
-		struct compat_video_spu_palette __user *up)
+static int do_video_set_spu_palette(struct file *file,
+		unsigned int cmd, struct compat_video_spu_palette __user *up)
 {
 	struct video_spu_palette __user *up_native;
 	compat_uptr_t palp;
@@ -218,7 +239,7 @@
 	if (err)
 		return -EFAULT;
 
-	err = sys_ioctl(fd, cmd, (unsigned long) up_native);
+	err = do_ioctl(file, cmd, (unsigned long) up_native);
 
 	return err;
 }
@@ -276,7 +297,7 @@
 	return 0;
 }
 
-static int sg_ioctl_trans(unsigned int fd, unsigned int cmd,
+static int sg_ioctl_trans(struct file *file, unsigned int cmd,
 			sg_io_hdr32_t __user *sgio32)
 {
 	sg_io_hdr_t __user *sgio;
@@ -289,7 +310,7 @@
 	if (get_user(interface_id, &sgio32->interface_id))
 		return -EFAULT;
 	if (interface_id != 'S')
-		return sys_ioctl(fd, cmd, (unsigned long)sgio32);
+		return do_ioctl(file, cmd, (unsigned long)sgio32);
 
 	if (get_user(iovec_count, &sgio32->iovec_count))
 		return -EFAULT;
@@ -349,7 +370,7 @@
 	if (put_user(compat_ptr(data), &sgio->usr_ptr))
 		return -EFAULT;
 
-	err = sys_ioctl(fd, cmd, (unsigned long) sgio);
+	err = do_ioctl(file, cmd, (unsigned long) sgio);
 
 	if (err >= 0) {
 		void __user *datap;
@@ -380,13 +401,13 @@
 	int unused;
 };
 
-static int sg_grt_trans(unsigned int fd, unsigned int cmd, struct
-			compat_sg_req_info __user *o)
+static int sg_grt_trans(struct file *file,
+		unsigned int cmd, struct compat_sg_req_info __user *o)
 {
 	int err, i;
 	sg_req_info_t __user *r;
 	r = compat_alloc_user_space(sizeof(sg_req_info_t)*SG_MAX_QUEUE);
-	err = sys_ioctl(fd,cmd,(unsigned long)r);
+	err = do_ioctl(file, cmd, (unsigned long)r);
 	if (err < 0)
 		return err;
 	for (i = 0; i < SG_MAX_QUEUE; i++) {
@@ -412,8 +433,8 @@
 #define PPPIOCSPASS32	_IOW('t', 71, struct sock_fprog32)
 #define PPPIOCSACTIVE32	_IOW('t', 70, struct sock_fprog32)
 
-static int ppp_sock_fprog_ioctl_trans(unsigned int fd, unsigned int cmd,
-			struct sock_fprog32 __user *u_fprog32)
+static int ppp_sock_fprog_ioctl_trans(struct file *file,
+		unsigned int cmd, struct sock_fprog32 __user *u_fprog32)
 {
 	struct sock_fprog __user *u_fprog64 = compat_alloc_user_space(sizeof(struct sock_fprog));
 	void __user *fptr64;
@@ -435,7 +456,7 @@
 	else
 		cmd = PPPIOCSACTIVE;
 
-	return sys_ioctl(fd, cmd, (unsigned long) u_fprog64);
+	return do_ioctl(file, cmd, (unsigned long) u_fprog64);
 }
 
 struct ppp_option_data32 {
@@ -451,7 +472,7 @@
 };
 #define PPPIOCGIDLE32		_IOR('t', 63, struct ppp_idle32)
 
-static int ppp_gidle(unsigned int fd, unsigned int cmd,
+static int ppp_gidle(struct file *file, unsigned int cmd,
 		struct ppp_idle32 __user *idle32)
 {
 	struct ppp_idle __user *idle;
@@ -460,7 +481,7 @@
 
 	idle = compat_alloc_user_space(sizeof(*idle));
 
-	err = sys_ioctl(fd, PPPIOCGIDLE, (unsigned long) idle);
+	err = do_ioctl(file, PPPIOCGIDLE, (unsigned long) idle);
 
 	if (!err) {
 		if (get_user(xmit, &idle->xmit_idle) ||
@@ -472,7 +493,7 @@
 	return err;
 }
 
-static int ppp_scompress(unsigned int fd, unsigned int cmd,
+static int ppp_scompress(struct file *file, unsigned int cmd,
 	struct ppp_option_data32 __user *odata32)
 {
 	struct ppp_option_data __user *odata;
@@ -492,7 +513,7 @@
 			 sizeof(__u32) + sizeof(int)))
 		return -EFAULT;
 
-	return sys_ioctl(fd, PPPIOCSCOMPRESS, (unsigned long) odata);
+	return do_ioctl(file, PPPIOCSCOMPRESS, (unsigned long) odata);
 }
 
 #ifdef CONFIG_BLOCK
@@ -512,12 +533,13 @@
 };
 #define MTIOCPOS32	_IOR('m', 3, struct mtpos32)
 
-static int mt_ioctl_trans(unsigned int fd, unsigned int cmd, void __user *argp)
+static int mt_ioctl_trans(struct file *file,
+		unsigned int cmd, void __user *argp)
 {
-	mm_segment_t old_fs = get_fs();
-	struct mtget get;
+	/* NULL initialization to make gcc shut up */
+	struct mtget __user *get = NULL;
 	struct mtget32 __user *umget32;
-	struct mtpos pos;
+	struct mtpos __user *pos = NULL;
 	struct mtpos32 __user *upos32;
 	unsigned long kcmd;
 	void *karg;
@@ -526,32 +548,34 @@
 	switch(cmd) {
 	case MTIOCPOS32:
 		kcmd = MTIOCPOS;
-		karg = &pos;
+		pos = compat_alloc_user_space(sizeof(*pos));
+		karg = pos;
 		break;
 	default:	/* MTIOCGET32 */
 		kcmd = MTIOCGET;
-		karg = &get;
+		get = compat_alloc_user_space(sizeof(*get));
+		karg = get;
 		break;
 	}
-	set_fs (KERNEL_DS);
-	err = sys_ioctl (fd, kcmd, (unsigned long)karg);
-	set_fs (old_fs);
+	if (karg == NULL)
+		return -EFAULT;
+	err = do_ioctl(file, kcmd, (unsigned long)karg);
 	if (err)
 		return err;
 	switch (cmd) {
 	case MTIOCPOS32:
 		upos32 = argp;
-		err = __put_user(pos.mt_blkno, &upos32->mt_blkno);
+		err = convert_in_user(&pos->mt_blkno, &upos32->mt_blkno);
 		break;
 	case MTIOCGET32:
 		umget32 = argp;
-		err = __put_user(get.mt_type, &umget32->mt_type);
-		err |= __put_user(get.mt_resid, &umget32->mt_resid);
-		err |= __put_user(get.mt_dsreg, &umget32->mt_dsreg);
-		err |= __put_user(get.mt_gstat, &umget32->mt_gstat);
-		err |= __put_user(get.mt_erreg, &umget32->mt_erreg);
-		err |= __put_user(get.mt_fileno, &umget32->mt_fileno);
-		err |= __put_user(get.mt_blkno, &umget32->mt_blkno);
+		err = convert_in_user(&get->mt_type, &umget32->mt_type);
+		err |= convert_in_user(&get->mt_resid, &umget32->mt_resid);
+		err |= convert_in_user(&get->mt_dsreg, &umget32->mt_dsreg);
+		err |= convert_in_user(&get->mt_gstat, &umget32->mt_gstat);
+		err |= convert_in_user(&get->mt_erreg, &umget32->mt_erreg);
+		err |= convert_in_user(&get->mt_fileno, &umget32->mt_fileno);
+		err |= convert_in_user(&get->mt_blkno, &umget32->mt_blkno);
 		break;
 	}
 	return err ? -EFAULT: 0;
@@ -605,42 +629,41 @@
         compat_int_t    reserved[1];
 };
 
-static int serial_struct_ioctl(unsigned fd, unsigned cmd,
-			struct serial_struct32 __user *ss32)
+static int serial_struct_ioctl(struct file *file,
+		unsigned cmd, struct serial_struct32 __user *ss32)
 {
         typedef struct serial_struct32 SS32;
         int err;
-        struct serial_struct ss;
-        mm_segment_t oldseg = get_fs();
+	struct serial_struct __user *ss = compat_alloc_user_space(sizeof(*ss));
         __u32 udata;
 	unsigned int base;
+	unsigned char *iomem_base;
 
+	if (ss == NULL)
+		return -EFAULT;
         if (cmd == TIOCSSERIAL) {
-                if (!access_ok(VERIFY_READ, ss32, sizeof(SS32)))
-                        return -EFAULT;
-                if (__copy_from_user(&ss, ss32, offsetof(SS32, iomem_base)))
+		if (copy_in_user(ss, ss32, offsetof(SS32, iomem_base)) ||
+		    get_user(udata, &ss32->iomem_base))
 			return -EFAULT;
-                if (__get_user(udata, &ss32->iomem_base))
+		iomem_base = compat_ptr(udata);
+		if (put_user(iomem_base, &ss->iomem_base) ||
+		    convert_in_user(&ss32->iomem_reg_shift,
+		      &ss->iomem_reg_shift) ||
+		    convert_in_user(&ss32->port_high, &ss->port_high) ||
+		    put_user(0UL, &ss->iomap_base))
 			return -EFAULT;
-                ss.iomem_base = compat_ptr(udata);
-                if (__get_user(ss.iomem_reg_shift, &ss32->iomem_reg_shift) ||
-		    __get_user(ss.port_high, &ss32->port_high))
-			return -EFAULT;
-                ss.iomap_base = 0UL;
         }
-        set_fs(KERNEL_DS);
-                err = sys_ioctl(fd,cmd,(unsigned long)(&ss));
-        set_fs(oldseg);
+	err = do_ioctl(file, cmd, (unsigned long)ss);
         if (cmd == TIOCGSERIAL && err >= 0) {
-                if (!access_ok(VERIFY_WRITE, ss32, sizeof(SS32)))
-                        return -EFAULT;
-                if (__copy_to_user(ss32,&ss,offsetof(SS32,iomem_base)))
+		if (copy_in_user(ss32, ss, offsetof(SS32, iomem_base)) ||
+		    get_user(iomem_base, &ss->iomem_base))
 			return -EFAULT;
-		base = (unsigned long)ss.iomem_base  >> 32 ?
-			0xffffffff : (unsigned)(unsigned long)ss.iomem_base;
-		if (__put_user(base, &ss32->iomem_base) ||
-		    __put_user(ss.iomem_reg_shift, &ss32->iomem_reg_shift) ||
-		    __put_user(ss.port_high, &ss32->port_high))
+		base = (unsigned long)iomem_base  >> 32 ?
+			0xffffffff : (unsigned)(unsigned long)iomem_base;
+		if (put_user(base, &ss32->iomem_base) ||
+		    convert_in_user(&ss->iomem_reg_shift,
+		      &ss32->iomem_reg_shift) ||
+		    convert_in_user(&ss->port_high, &ss32->port_high))
 			return -EFAULT;
         }
         return err;
@@ -674,8 +697,8 @@
 	struct i2c_msg msgs[0];
 };
 
-static int do_i2c_rdwr_ioctl(unsigned int fd, unsigned int cmd,
-			struct i2c_rdwr_ioctl_data32    __user *udata)
+static int do_i2c_rdwr_ioctl(struct file *file,
+	unsigned int cmd, struct i2c_rdwr_ioctl_data32 __user *udata)
 {
 	struct i2c_rdwr_aligned		__user *tdata;
 	struct i2c_msg			__user *tmsgs;
@@ -708,11 +731,11 @@
 		    put_user(compat_ptr(datap), &tmsgs[i].buf))
 			return -EFAULT;
 	}
-	return sys_ioctl(fd, cmd, (unsigned long)tdata);
+	return do_ioctl(file, cmd, (unsigned long)tdata);
 }
 
-static int do_i2c_smbus_ioctl(unsigned int fd, unsigned int cmd,
-			struct i2c_smbus_ioctl_data32   __user *udata)
+static int do_i2c_smbus_ioctl(struct file *file,
+		unsigned int cmd, struct i2c_smbus_ioctl_data32   __user *udata)
 {
 	struct i2c_smbus_ioctl_data	__user *tdata;
 	compat_caddr_t			datap;
@@ -734,7 +757,7 @@
 	    __put_user(compat_ptr(datap), &tdata->data))
 		return -EFAULT;
 
-	return sys_ioctl(fd, cmd, (unsigned long)tdata);
+	return do_ioctl(file, cmd, (unsigned long)tdata);
 }
 
 #define RTC_IRQP_READ32		_IOR('p', 0x0b, compat_ulong_t)
@@ -742,29 +765,27 @@
 #define RTC_EPOCH_READ32	_IOR('p', 0x0d, compat_ulong_t)
 #define RTC_EPOCH_SET32		_IOW('p', 0x0e, compat_ulong_t)
 
-static int rtc_ioctl(unsigned fd, unsigned cmd, void __user *argp)
+static int rtc_ioctl(struct file *file,
+		unsigned cmd, void __user *argp)
 {
-	mm_segment_t oldfs = get_fs();
-	compat_ulong_t val32;
-	unsigned long kval;
+	unsigned long __user *valp = compat_alloc_user_space(sizeof(*valp));
 	int ret;
 
+	if (valp == NULL)
+		return -EFAULT;
 	switch (cmd) {
 	case RTC_IRQP_READ32:
 	case RTC_EPOCH_READ32:
-		set_fs(KERNEL_DS);
-		ret = sys_ioctl(fd, (cmd == RTC_IRQP_READ32) ?
+		ret = do_ioctl(file, (cmd == RTC_IRQP_READ32) ?
 					RTC_IRQP_READ : RTC_EPOCH_READ,
-					(unsigned long)&kval);
-		set_fs(oldfs);
+					(unsigned long)valp);
 		if (ret)
 			return ret;
-		val32 = kval;
-		return put_user(val32, (unsigned int __user *)argp);
+		return convert_in_user(valp, (unsigned int __user *)argp);
 	case RTC_IRQP_SET32:
-		return sys_ioctl(fd, RTC_IRQP_SET, (unsigned long)argp);
+		return do_ioctl(file, RTC_IRQP_SET, (unsigned long)argp);
 	case RTC_EPOCH_SET32:
-		return sys_ioctl(fd, RTC_EPOCH_SET, (unsigned long)argp);
+		return do_ioctl(file, RTC_EPOCH_SET, (unsigned long)argp);
 	}
 
 	return -ENOIOCTLCMD;
@@ -1284,12 +1305,6 @@
 COMPATIBLE_IOCTL(PCIIOC_MMAP_IS_IO)
 COMPATIBLE_IOCTL(PCIIOC_MMAP_IS_MEM)
 COMPATIBLE_IOCTL(PCIIOC_WRITE_COMBINE)
-/* NBD */
-COMPATIBLE_IOCTL(NBD_DO_IT)
-COMPATIBLE_IOCTL(NBD_CLEAR_SOCK)
-COMPATIBLE_IOCTL(NBD_CLEAR_QUE)
-COMPATIBLE_IOCTL(NBD_PRINT_DEBUG)
-COMPATIBLE_IOCTL(NBD_DISCONNECT)
 /* i2c */
 COMPATIBLE_IOCTL(I2C_SLAVE)
 COMPATIBLE_IOCTL(I2C_SLAVE_FORCE)
@@ -1436,53 +1451,53 @@
  * a compat_ioctl operation in the place that handleѕ the
  * ioctl for the native case.
  */
-static long do_ioctl_trans(int fd, unsigned int cmd,
+static long do_ioctl_trans(unsigned int cmd,
 		 unsigned long arg, struct file *file)
 {
 	void __user *argp = compat_ptr(arg);
 
 	switch (cmd) {
 	case PPPIOCGIDLE32:
-		return ppp_gidle(fd, cmd, argp);
+		return ppp_gidle(file, cmd, argp);
 	case PPPIOCSCOMPRESS32:
-		return ppp_scompress(fd, cmd, argp);
+		return ppp_scompress(file, cmd, argp);
 	case PPPIOCSPASS32:
 	case PPPIOCSACTIVE32:
-		return ppp_sock_fprog_ioctl_trans(fd, cmd, argp);
+		return ppp_sock_fprog_ioctl_trans(file, cmd, argp);
 #ifdef CONFIG_BLOCK
 	case SG_IO:
-		return sg_ioctl_trans(fd, cmd, argp);
+		return sg_ioctl_trans(file, cmd, argp);
 	case SG_GET_REQUEST_TABLE:
-		return sg_grt_trans(fd, cmd, argp);
+		return sg_grt_trans(file, cmd, argp);
 	case MTIOCGET32:
 	case MTIOCPOS32:
-		return mt_ioctl_trans(fd, cmd, argp);
+		return mt_ioctl_trans(file, cmd, argp);
 #endif
 	/* Serial */
 	case TIOCGSERIAL:
 	case TIOCSSERIAL:
-		return serial_struct_ioctl(fd, cmd, argp);
+		return serial_struct_ioctl(file, cmd, argp);
 	/* i2c */
 	case I2C_FUNCS:
-		return w_long(fd, cmd, argp);
+		return w_long(file, cmd, argp);
 	case I2C_RDWR:
-		return do_i2c_rdwr_ioctl(fd, cmd, argp);
+		return do_i2c_rdwr_ioctl(file, cmd, argp);
 	case I2C_SMBUS:
-		return do_i2c_smbus_ioctl(fd, cmd, argp);
+		return do_i2c_smbus_ioctl(file, cmd, argp);
 	/* Not implemented in the native kernel */
 	case RTC_IRQP_READ32:
 	case RTC_IRQP_SET32:
 	case RTC_EPOCH_READ32:
 	case RTC_EPOCH_SET32:
-		return rtc_ioctl(fd, cmd, argp);
+		return rtc_ioctl(file, cmd, argp);
 
 	/* dvb */
 	case VIDEO_GET_EVENT:
-		return do_video_get_event(fd, cmd, argp);
+		return do_video_get_event(file, cmd, argp);
 	case VIDEO_STILLPICTURE:
-		return do_video_stillpicture(fd, cmd, argp);
+		return do_video_stillpicture(file, cmd, argp);
 	case VIDEO_SET_SPU_PALETTE:
-		return do_video_set_spu_palette(fd, cmd, argp);
+		return do_video_set_spu_palette(file, cmd, argp);
 	}
 
 	/*
@@ -1508,12 +1523,7 @@
 	case KDSKBMETA:
 	case KDSKBLED:
 	case KDSETLED:
-	/* NBD */
-	case NBD_SET_SOCK:
-	case NBD_SET_BLKSIZE:
-	case NBD_SET_SIZE:
-	case NBD_SET_SIZE_BLOCKS:
-		return do_vfs_ioctl(file, fd, cmd, arg);
+		return vfs_ioctl(file, cmd, arg);
 	}
 
 	return -ENOIOCTLCMD;
@@ -1580,6 +1590,11 @@
 		goto out_fput;
 #endif
 
+	case FICLONE:
+	case FICLONERANGE:
+	case FIDEDUPERANGE:
+		goto do_ioctl;
+
 	case FIBMAP:
 	case FIGETBSZ:
 	case FIONREAD:
@@ -1602,7 +1617,7 @@
 	if (compat_ioctl_check_table(XFORM(cmd)))
 		goto found_handler;
 
-	error = do_ioctl_trans(fd, cmd, arg, f.file);
+	error = do_ioctl_trans(cmd, arg, f.file);
 	if (error == -ENOIOCTLCMD)
 		error = -ENOTTY;
 
diff --git a/fs/configfs/configfs_internal.h b/fs/configfs/configfs_internal.h
index b65d1ef..ccc31fa 100644
--- a/fs/configfs/configfs_internal.h
+++ b/fs/configfs/configfs_internal.h
@@ -53,13 +53,14 @@
 #define CONFIGFS_ROOT		0x0001
 #define CONFIGFS_DIR		0x0002
 #define CONFIGFS_ITEM_ATTR	0x0004
+#define CONFIGFS_ITEM_BIN_ATTR	0x0008
 #define CONFIGFS_ITEM_LINK	0x0020
 #define CONFIGFS_USET_DIR	0x0040
 #define CONFIGFS_USET_DEFAULT	0x0080
 #define CONFIGFS_USET_DROPPING	0x0100
 #define CONFIGFS_USET_IN_MKDIR	0x0200
 #define CONFIGFS_USET_CREATING	0x0400
-#define CONFIGFS_NOT_PINNED	(CONFIGFS_ITEM_ATTR)
+#define CONFIGFS_NOT_PINNED	(CONFIGFS_ITEM_ATTR | CONFIGFS_ITEM_BIN_ATTR)
 
 extern struct mutex configfs_symlink_mutex;
 extern spinlock_t configfs_dirent_lock;
@@ -72,6 +73,8 @@
 extern int configfs_create(struct dentry *, umode_t mode, void (*init)(struct inode *));
 
 extern int configfs_create_file(struct config_item *, const struct configfs_attribute *);
+extern int configfs_create_bin_file(struct config_item *,
+				    const struct configfs_bin_attribute *);
 extern int configfs_make_dirent(struct configfs_dirent *,
 				struct dentry *, void *, umode_t, int);
 extern int configfs_dirent_is_ready(struct configfs_dirent *);
@@ -88,7 +91,7 @@
 extern struct rw_semaphore configfs_rename_sem;
 extern const struct file_operations configfs_dir_operations;
 extern const struct file_operations configfs_file_operations;
-extern const struct file_operations bin_fops;
+extern const struct file_operations configfs_bin_file_operations;
 extern const struct inode_operations configfs_dir_inode_operations;
 extern const struct inode_operations configfs_root_inode_operations;
 extern const struct inode_operations configfs_symlink_inode_operations;
@@ -119,6 +122,13 @@
 	return ((struct configfs_attribute *) sd->s_element);
 }
 
+static inline struct configfs_bin_attribute *to_bin_attr(struct dentry *dentry)
+{
+	struct configfs_attribute *attr = to_attr(dentry);
+
+	return container_of(attr, struct configfs_bin_attribute, cb_attr);
+}
+
 static inline struct config_item *configfs_get_config_item(struct dentry *dentry)
 {
 	struct config_item * item = NULL;
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index a7a1b21..7ae97e8 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -255,6 +255,12 @@
 	inode->i_fop = &configfs_file_operations;
 }
 
+static void configfs_init_bin_file(struct inode *inode)
+{
+	inode->i_size = 0;
+	inode->i_fop = &configfs_bin_file_operations;
+}
+
 static void init_symlink(struct inode * inode)
 {
 	inode->i_op = &configfs_symlink_inode_operations;
@@ -423,7 +429,9 @@
 	spin_unlock(&configfs_dirent_lock);
 
 	error = configfs_create(dentry, (attr->ca_mode & S_IALLUGO) | S_IFREG,
-				configfs_init_file);
+				(sd->s_type & CONFIGFS_ITEM_BIN_ATTR) ?
+					configfs_init_bin_file :
+					configfs_init_file);
 	if (error) {
 		configfs_put(sd);
 		return error;
@@ -583,6 +591,7 @@
 {
 	struct config_item_type *t = item->ci_type;
 	struct configfs_attribute *attr;
+	struct configfs_bin_attribute *bin_attr;
 	int error = 0;
 	int i;
 
@@ -594,6 +603,13 @@
 				break;
 		}
 	}
+	if (t->ct_bin_attrs) {
+		for (i = 0; (bin_attr = t->ct_bin_attrs[i]) != NULL; i++) {
+			error = configfs_create_bin_file(item, bin_attr);
+			if (error)
+				break;
+		}
+	}
 
 	if (error)
 		detach_attrs(item);
diff --git a/fs/configfs/file.c b/fs/configfs/file.c
index d39099e..3687187 100644
--- a/fs/configfs/file.c
+++ b/fs/configfs/file.c
@@ -28,6 +28,7 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/mutex.h>
+#include <linux/vmalloc.h>
 #include <asm/uaccess.h>
 
 #include <linux/configfs.h>
@@ -48,6 +49,10 @@
 	struct configfs_item_operations	* ops;
 	struct mutex		mutex;
 	int			needs_read_fill;
+	bool			read_in_progress;
+	bool			write_in_progress;
+	char			*bin_buffer;
+	int			bin_buffer_size;
 };
 
 
@@ -123,6 +128,87 @@
 	return retval;
 }
 
+/**
+ *	configfs_read_bin_file - read a binary attribute.
+ *	@file:	file pointer.
+ *	@buf:	buffer to fill.
+ *	@count:	number of bytes to read.
+ *	@ppos:	starting offset in file.
+ *
+ *	Userspace wants to read a binary attribute file. The attribute
+ *	descriptor is in the file's ->d_fsdata. The target item is in the
+ *	directory's ->d_fsdata.
+ *
+ *	We check whether we need to refill the buffer. If so we will
+ *	call the attributes' attr->read() twice. The first time we
+ *	will pass a NULL as a buffer pointer, which the attributes' method
+ *	will use to return the size of the buffer required. If no error
+ *	occurs we will allocate the buffer using vmalloc and call
+ *	attr->read() again passing that buffer as an argument.
+ *	Then we just copy to user-space using simple_read_from_buffer.
+ */
+
+static ssize_t
+configfs_read_bin_file(struct file *file, char __user *buf,
+		       size_t count, loff_t *ppos)
+{
+	struct configfs_buffer *buffer = file->private_data;
+	struct dentry *dentry = file->f_path.dentry;
+	struct config_item *item = to_item(dentry->d_parent);
+	struct configfs_bin_attribute *bin_attr = to_bin_attr(dentry);
+	ssize_t retval = 0;
+	ssize_t len = min_t(size_t, count, PAGE_SIZE);
+
+	mutex_lock(&buffer->mutex);
+
+	/* we don't support switching read/write modes */
+	if (buffer->write_in_progress) {
+		retval = -ETXTBSY;
+		goto out;
+	}
+	buffer->read_in_progress = 1;
+
+	if (buffer->needs_read_fill) {
+		/* perform first read with buf == NULL to get extent */
+		len = bin_attr->read(item, NULL, 0);
+		if (len <= 0) {
+			retval = len;
+			goto out;
+		}
+
+		/* do not exceed the maximum value */
+		if (bin_attr->cb_max_size && len > bin_attr->cb_max_size) {
+			retval = -EFBIG;
+			goto out;
+		}
+
+		buffer->bin_buffer = vmalloc(len);
+		if (buffer->bin_buffer == NULL) {
+			retval = -ENOMEM;
+			goto out;
+		}
+		buffer->bin_buffer_size = len;
+
+		/* perform second read to fill buffer */
+		len = bin_attr->read(item, buffer->bin_buffer, len);
+		if (len < 0) {
+			retval = len;
+			vfree(buffer->bin_buffer);
+			buffer->bin_buffer_size = 0;
+			buffer->bin_buffer = NULL;
+			goto out;
+		}
+
+		buffer->needs_read_fill = 0;
+	}
+
+	retval = simple_read_from_buffer(buf, count, ppos, buffer->bin_buffer,
+					buffer->bin_buffer_size);
+out:
+	mutex_unlock(&buffer->mutex);
+	return retval;
+}
+
 
 /**
  *	fill_write_buffer - copy buffer from userspace.
@@ -209,10 +295,80 @@
 	return len;
 }
 
-static int check_perm(struct inode * inode, struct file * file)
+/**
+ *	configfs_write_bin_file - write a binary attribute.
+ *	@file:	file pointer
+ *	@buf:	data to write
+ *	@count:	number of bytes
+ *	@ppos:	starting offset
+ *
+ *	Writing to a binary attribute file is similar to a normal read.
+ *	We buffer the consecutive writes (binary attribute files do not
+ *	support lseek) in a continuously growing buffer, but we don't
+ *	commit until the close of the file.
+ */
+
+static ssize_t
+configfs_write_bin_file(struct file *file, const char __user *buf,
+			size_t count, loff_t *ppos)
+{
+	struct configfs_buffer *buffer = file->private_data;
+	struct dentry *dentry = file->f_path.dentry;
+	struct configfs_bin_attribute *bin_attr = to_bin_attr(dentry);
+	void *tbuf = NULL;
+	ssize_t len;
+
+	mutex_lock(&buffer->mutex);
+
+	/* we don't support switching read/write modes */
+	if (buffer->read_in_progress) {
+		len = -ETXTBSY;
+		goto out;
+	}
+	buffer->write_in_progress = 1;
+
+	/* buffer grows? */
+	if (*ppos + count > buffer->bin_buffer_size) {
+
+		if (bin_attr->cb_max_size &&
+			*ppos + count > bin_attr->cb_max_size) {
+			len = -EFBIG;
+		}
+
+		tbuf = vmalloc(*ppos + count);
+		if (tbuf == NULL) {
+			len = -ENOMEM;
+			goto out;
+		}
+
+		/* copy old contents */
+		if (buffer->bin_buffer) {
+			memcpy(tbuf, buffer->bin_buffer,
+				buffer->bin_buffer_size);
+			vfree(buffer->bin_buffer);
+		}
+
+		/* clear the new area */
+		memset(tbuf + buffer->bin_buffer_size, 0,
+			*ppos + count - buffer->bin_buffer_size);
+		buffer->bin_buffer = tbuf;
+		buffer->bin_buffer_size = *ppos + count;
+	}
+
+	len = simple_write_to_buffer(buffer->bin_buffer,
+			buffer->bin_buffer_size, ppos, buf, count);
+	if (len > 0)
+		*ppos += len;
+out:
+	mutex_unlock(&buffer->mutex);
+	return len;
+}
+
+static int check_perm(struct inode * inode, struct file * file, int type)
 {
 	struct config_item *item = configfs_get_config_item(file->f_path.dentry->d_parent);
 	struct configfs_attribute * attr = to_attr(file->f_path.dentry);
+	struct configfs_bin_attribute *bin_attr = NULL;
 	struct configfs_buffer * buffer;
 	struct configfs_item_operations * ops = NULL;
 	int error = 0;
@@ -220,6 +376,9 @@
 	if (!item || !attr)
 		goto Einval;
 
+	if (type & CONFIGFS_ITEM_BIN_ATTR)
+		bin_attr = to_bin_attr(file->f_path.dentry);
+
 	/* Grab the module reference for this attribute if we have one */
 	if (!try_module_get(attr->ca_owner)) {
 		error = -ENODEV;
@@ -236,9 +395,14 @@
 	 * and we must have a store method.
 	 */
 	if (file->f_mode & FMODE_WRITE) {
-		if (!(inode->i_mode & S_IWUGO) || !attr->store)
+		if (!(inode->i_mode & S_IWUGO))
 			goto Eaccess;
 
+		if ((type & CONFIGFS_ITEM_ATTR) && !attr->store)
+			goto Eaccess;
+
+		if ((type & CONFIGFS_ITEM_BIN_ATTR) && !bin_attr->write)
+			goto Eaccess;
 	}
 
 	/* File needs read support.
@@ -246,7 +410,13 @@
 	 * must be a show method for it.
 	 */
 	if (file->f_mode & FMODE_READ) {
-		if (!(inode->i_mode & S_IRUGO) || !attr->show)
+		if (!(inode->i_mode & S_IRUGO))
+			goto Eaccess;
+
+		if ((type & CONFIGFS_ITEM_ATTR) && !attr->show)
+			goto Eaccess;
+
+		if ((type & CONFIGFS_ITEM_BIN_ATTR) && !bin_attr->read)
 			goto Eaccess;
 	}
 
@@ -260,6 +430,8 @@
 	}
 	mutex_init(&buffer->mutex);
 	buffer->needs_read_fill = 1;
+	buffer->read_in_progress = 0;
+	buffer->write_in_progress = 0;
 	buffer->ops = ops;
 	file->private_data = buffer;
 	goto Done;
@@ -277,12 +449,7 @@
 	return error;
 }
 
-static int configfs_open_file(struct inode * inode, struct file * filp)
-{
-	return check_perm(inode,filp);
-}
-
-static int configfs_release(struct inode * inode, struct file * filp)
+static int configfs_release(struct inode *inode, struct file *filp)
 {
 	struct config_item * item = to_item(filp->f_path.dentry->d_parent);
 	struct configfs_attribute * attr = to_attr(filp->f_path.dentry);
@@ -303,6 +470,47 @@
 	return 0;
 }
 
+static int configfs_open_file(struct inode *inode, struct file *filp)
+{
+	return check_perm(inode, filp, CONFIGFS_ITEM_ATTR);
+}
+
+static int configfs_open_bin_file(struct inode *inode, struct file *filp)
+{
+	return check_perm(inode, filp, CONFIGFS_ITEM_BIN_ATTR);
+}
+
+static int configfs_release_bin_file(struct inode *inode, struct file *filp)
+{
+	struct configfs_buffer *buffer = filp->private_data;
+	struct dentry *dentry = filp->f_path.dentry;
+	struct config_item *item = to_item(dentry->d_parent);
+	struct configfs_bin_attribute *bin_attr = to_bin_attr(dentry);
+	ssize_t len = 0;
+	int ret;
+
+	buffer->read_in_progress = 0;
+
+	if (buffer->write_in_progress) {
+		buffer->write_in_progress = 0;
+
+		len = bin_attr->write(item, buffer->bin_buffer,
+				buffer->bin_buffer_size);
+
+		/* vfree on NULL is safe */
+		vfree(buffer->bin_buffer);
+		buffer->bin_buffer = NULL;
+		buffer->bin_buffer_size = 0;
+		buffer->needs_read_fill = 1;
+	}
+
+	ret = configfs_release(inode, filp);
+	if (len < 0)
+		return len;
+	return ret;
+}
+
+
 const struct file_operations configfs_file_operations = {
 	.read		= configfs_read_file,
 	.write		= configfs_write_file,
@@ -311,6 +519,14 @@
 	.release	= configfs_release,
 };
 
+const struct file_operations configfs_bin_file_operations = {
+	.read		= configfs_read_bin_file,
+	.write		= configfs_write_bin_file,
+	.llseek		= NULL,		/* bin file is not seekable */
+	.open		= configfs_open_bin_file,
+	.release	= configfs_release_bin_file,
+};
+
 /**
  *	configfs_create_file - create an attribute file for an item.
  *	@item:	item we're creating for.
@@ -332,3 +548,24 @@
 	return error;
 }
 
+/**
+ *	configfs_create_bin_file - create a binary attribute file for an item.
+ *	@item:	item we're creating for.
+ *	@attr:	atrribute descriptor.
+ */
+
+int configfs_create_bin_file(struct config_item *item,
+		const struct configfs_bin_attribute *bin_attr)
+{
+	struct dentry *dir = item->ci_dentry;
+	struct configfs_dirent *parent_sd = dir->d_fsdata;
+	umode_t mode = (bin_attr->cb_attr.ca_mode & S_IALLUGO) | S_IFREG;
+	int error = 0;
+
+	mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_NORMAL);
+	error = configfs_make_dirent(parent_sd, NULL, (void *) bin_attr, mode,
+				     CONFIGFS_ITEM_BIN_ATTR);
+	mutex_unlock(&dir->d_inode->i_mutex);
+
+	return error;
+}
diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c
index eae8757..0cc810e 100644
--- a/fs/configfs/inode.c
+++ b/fs/configfs/inode.c
@@ -218,7 +218,7 @@
 	if (sd->s_type & (CONFIGFS_DIR | CONFIGFS_ITEM_LINK))
 		return sd->s_dentry->d_name.name;
 
-	if (sd->s_type & CONFIGFS_ITEM_ATTR) {
+	if (sd->s_type & (CONFIGFS_ITEM_ATTR | CONFIGFS_ITEM_BIN_ATTR)) {
 		attr = sd->s_element;
 		return attr->ca_name;
 	}
diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c
index ec5c832..db6d692 100644
--- a/fs/configfs/symlink.c
+++ b/fs/configfs/symlink.c
@@ -279,27 +279,33 @@
 
 }
 
-static const char *configfs_follow_link(struct dentry *dentry, void **cookie)
+static const char *configfs_get_link(struct dentry *dentry,
+				     struct inode *inode,
+				     struct delayed_call *done)
 {
-	unsigned long page = get_zeroed_page(GFP_KERNEL);
+	char *body;
 	int error;
 
-	if (!page)
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+
+	body = kzalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!body)
 		return ERR_PTR(-ENOMEM);
 
-	error = configfs_getlink(dentry, (char *)page);
+	error = configfs_getlink(dentry, body);
 	if (!error) {
-		return *cookie = (void *)page;
+		set_delayed_call(done, kfree_link, body);
+		return body;
 	}
 
-	free_page(page);
+	kfree(body);
 	return ERR_PTR(error);
 }
 
 const struct inode_operations configfs_symlink_inode_operations = {
-	.follow_link = configfs_follow_link,
+	.get_link = configfs_get_link,
 	.readlink = generic_readlink,
-	.put_link = free_page_put_link,
 	.setattr = configfs_setattr,
 };
 
diff --git a/fs/coredump.c b/fs/coredump.c
index 1777331..b3c153c 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -32,6 +32,7 @@
 #include <linux/pipe_fs_i.h>
 #include <linux/oom.h>
 #include <linux/compat.h>
+#include <linux/timekeeping.h>
 
 #include <asm/uaccess.h>
 #include <asm/mmu_context.h>
@@ -232,9 +233,10 @@
 				break;
 			/* UNIX time of coredump */
 			case 't': {
-				struct timeval tv;
-				do_gettimeofday(&tv);
-				err = cn_printf(cn, "%lu", tv.tv_sec);
+				time64_t time;
+
+				time = ktime_get_real_seconds();
+				err = cn_printf(cn, "%lld", time);
 				break;
 			}
 			/* hostname */
diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index 355c522..b862bc2 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -100,6 +100,7 @@
 		break;
 	case S_IFLNK:
 		inode->i_op = &page_symlink_inode_operations;
+		inode_nohighmem(inode);
 		inode->i_data.a_ops = &cramfs_aops;
 		break;
 	default:
diff --git a/fs/dcache.c b/fs/dcache.c
index 5c33aeb..8d38cd0 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1734,7 +1734,7 @@
 	}
 
 	if (unlikely(!(inode->i_opflags & IOP_NOFOLLOW))) {
-		if (unlikely(inode->i_op->follow_link)) {
+		if (unlikely(inode->i_op->get_link)) {
 			add_flags = DCACHE_SYMLINK_TYPE;
 			goto type_determined;
 		}
@@ -3303,18 +3303,18 @@
  * @new_dentry: new dentry
  * @old_dentry: old dentry
  *
- * Returns 1 if new_dentry is a subdirectory of the parent (at any depth).
- * Returns 0 otherwise.
+ * Returns true if new_dentry is a subdirectory of the parent (at any depth).
+ * Returns false otherwise.
  * Caller must ensure that "new_dentry" is pinned before calling is_subdir()
  */
   
-int is_subdir(struct dentry *new_dentry, struct dentry *old_dentry)
+bool is_subdir(struct dentry *new_dentry, struct dentry *old_dentry)
 {
-	int result;
+	bool result;
 	unsigned seq;
 
 	if (new_dentry == old_dentry)
-		return 1;
+		return true;
 
 	do {
 		/* for restarting inner loop in case of seq retry */
@@ -3325,9 +3325,9 @@
 		 */
 		rcu_read_lock();
 		if (d_ancestor(old_dentry, new_dentry))
-			result = 1;
+			result = true;
 		else
-			result = 0;
+			result = false;
 		rcu_read_unlock();
 	} while (read_seqretry(&rename_lock, seq));
 
diff --git a/fs/dlm/user.c b/fs/dlm/user.c
index 173b387..1925d6d 100644
--- a/fs/dlm/user.c
+++ b/fs/dlm/user.c
@@ -515,14 +515,9 @@
 	if (count > sizeof(struct dlm_write_request) + DLM_RESNAME_MAXLEN)
 		return -EINVAL;
 
-	kbuf = kzalloc(count + 1, GFP_NOFS);
-	if (!kbuf)
-		return -ENOMEM;
-
-	if (copy_from_user(kbuf, buf, count)) {
-		error = -EFAULT;
-		goto out_free;
-	}
+	kbuf = memdup_user_nul(buf, count);
+	if (!IS_ERR(kbuf))
+		return PTR_ERR(kbuf);
 
 	if (check_version(kbuf)) {
 		error = -EBADE;
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index e2e47ba..040aa87 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -282,9 +282,7 @@
 	if (rc) {
 		ecryptfs_do_unlink(directory_inode, ecryptfs_dentry,
 				   ecryptfs_inode);
-		make_bad_inode(ecryptfs_inode);
-		unlock_new_inode(ecryptfs_inode);
-		iput(ecryptfs_inode);
+		iget_failed(ecryptfs_inode);
 		goto out;
 	}
 	unlock_new_inode(ecryptfs_inode);
@@ -674,16 +672,24 @@
 	return rc ? ERR_PTR(rc) : buf;
 }
 
-static const char *ecryptfs_follow_link(struct dentry *dentry, void **cookie)
+static const char *ecryptfs_get_link(struct dentry *dentry,
+				     struct inode *inode,
+				     struct delayed_call *done)
 {
 	size_t len;
-	char *buf = ecryptfs_readlink_lower(dentry, &len);
+	char *buf;
+
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+
+	buf = ecryptfs_readlink_lower(dentry, &len);
 	if (IS_ERR(buf))
 		return buf;
 	fsstack_copy_attr_atime(d_inode(dentry),
 				d_inode(ecryptfs_dentry_to_lower(dentry)));
 	buf[len] = '\0';
-	return *cookie = buf;
+	set_delayed_call(done, kfree_link, buf);
+	return buf;
 }
 
 /**
@@ -1095,8 +1101,7 @@
 
 const struct inode_operations ecryptfs_symlink_iops = {
 	.readlink = generic_readlink,
-	.follow_link = ecryptfs_follow_link,
-	.put_link = kfree_put_link,
+	.get_link = ecryptfs_get_link,
 	.permission = ecryptfs_permission,
 	.setattr = ecryptfs_setattr,
 	.getattr = ecryptfs_getattr_link,
diff --git a/fs/efs/inode.c b/fs/efs/inode.c
index 079d2030..cdf0872 100644
--- a/fs/efs/inode.c
+++ b/fs/efs/inode.c
@@ -151,6 +151,7 @@
 			break;
 		case S_IFLNK:
 			inode->i_op = &page_symlink_inode_operations;
+			inode_nohighmem(inode);
 			inode->i_data.a_ops = &efs_symlink_aops;
 			break;
 		case S_IFCHR:
diff --git a/fs/efs/symlink.c b/fs/efs/symlink.c
index 75117d0..4870cc8 100644
--- a/fs/efs/symlink.c
+++ b/fs/efs/symlink.c
@@ -13,7 +13,7 @@
 
 static int efs_symlink_readpage(struct file *file, struct page *page)
 {
-	char *link = kmap(page);
+	char *link = page_address(page);
 	struct buffer_head * bh;
 	struct inode * inode = page->mapping->host;
 	efs_block_t size = inode->i_size;
@@ -39,12 +39,10 @@
 	}
 	link[size] = '\0';
 	SetPageUptodate(page);
-	kunmap(page);
 	unlock_page(page);
 	return 0;
 fail:
 	SetPageError(page);
-	kunmap(page);
 	unlock_page(page);
 	return err;
 }
diff --git a/fs/exec.c b/fs/exec.c
index b06623a..828ec5f 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -119,7 +119,7 @@
 	int error = PTR_ERR(tmp);
 	static const struct open_flags uselib_flags = {
 		.open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC,
-		.acc_mode = MAY_READ | MAY_EXEC | MAY_OPEN,
+		.acc_mode = MAY_READ | MAY_EXEC,
 		.intent = LOOKUP_OPEN,
 		.lookup_flags = LOOKUP_FOLLOW,
 	};
@@ -763,7 +763,7 @@
 	int err;
 	struct open_flags open_exec_flags = {
 		.open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC,
-		.acc_mode = MAY_EXEC | MAY_OPEN,
+		.acc_mode = MAY_EXEC,
 		.intent = LOOKUP_OPEN,
 		.lookup_flags = LOOKUP_FOLLOW,
 	};
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index 60f03b7..9eaf595 100644
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -1224,6 +1224,7 @@
 			inode->i_link = (char *)oi->i_data;
 		} else {
 			inode->i_op = &page_symlink_inode_operations;
+			inode_nohighmem(inode);
 			inode->i_mapping->a_ops = &exofs_aops;
 		}
 	} else {
diff --git a/fs/exofs/namei.c b/fs/exofs/namei.c
index 994e078..c20d77d 100644
--- a/fs/exofs/namei.c
+++ b/fs/exofs/namei.c
@@ -111,6 +111,7 @@
 	if (l > sizeof(oi->i_data)) {
 		/* slow symlink */
 		inode->i_op = &page_symlink_inode_operations;
+		inode_nohighmem(inode);
 		inode->i_mapping->a_ops = &exofs_aops;
 		memset(oi->i_data, 0, sizeof(oi->i_data));
 
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 0aa9bf6..338eefd 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -1420,6 +1420,7 @@
 				sizeof(ei->i_data) - 1);
 		} else {
 			inode->i_op = &ext2_symlink_inode_operations;
+			inode_nohighmem(inode);
 			if (test_opt(inode->i_sb, NOBH))
 				inode->i_mapping->a_ops = &ext2_nobh_aops;
 			else
diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c
index 3267a80..7a2be8f 100644
--- a/fs/ext2/namei.c
+++ b/fs/ext2/namei.c
@@ -183,6 +183,7 @@
 	if (l > sizeof (EXT2_I(inode)->i_data)) {
 		/* slow symlink */
 		inode->i_op = &ext2_symlink_inode_operations;
+		inode_nohighmem(inode);
 		if (test_opt(inode->i_sb, NOBH))
 			inode->i_mapping->a_ops = &ext2_nobh_aops;
 		else
diff --git a/fs/ext2/symlink.c b/fs/ext2/symlink.c
index ae17179..3495d8a 100644
--- a/fs/ext2/symlink.c
+++ b/fs/ext2/symlink.c
@@ -22,8 +22,7 @@
 
 const struct inode_operations ext2_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= page_follow_link_light,
-	.put_link	= page_put_link,
+	.get_link	= page_get_link,
 	.setattr	= ext2_setattr,
 #ifdef CONFIG_EXT2_FS_XATTR
 	.setxattr	= generic_setxattr,
@@ -35,7 +34,7 @@
  
 const struct inode_operations ext2_fast_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= simple_follow_link,
+	.get_link	= simple_get_link,
 	.setattr	= ext2_setattr,
 #ifdef CONFIG_EXT2_FS_XATTR
 	.setxattr	= generic_setxattr,
diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c
index fa70848..f57a7ab 100644
--- a/fs/ext2/xattr.c
+++ b/fs/ext2/xattr.c
@@ -77,10 +77,8 @@
 		printk("\n"); \
 	} while (0)
 # define ea_bdebug(bh, f...) do { \
-		char b[BDEVNAME_SIZE]; \
-		printk(KERN_DEBUG "block %s:%lu: ", \
-			bdevname(bh->b_bdev, b), \
-			(unsigned long) bh->b_blocknr); \
+		printk(KERN_DEBUG "block %pg:%lu: ", \
+			bh->b_bdev, (unsigned long) bh->b_blocknr); \
 		printk(f); \
 		printk("\n"); \
 	} while (0)
@@ -292,16 +290,21 @@
 		const struct xattr_handler *handler =
 			ext2_xattr_handler(entry->e_name_index);
 
-		if (handler) {
-			size_t size = handler->list(handler, dentry, buffer,
-						    rest, entry->e_name,
-						    entry->e_name_len);
+		if (handler && (!handler->list || handler->list(dentry))) {
+			const char *prefix = handler->prefix ?: handler->name;
+			size_t prefix_len = strlen(prefix);
+			size_t size = prefix_len + entry->e_name_len + 1;
+
 			if (buffer) {
 				if (size > rest) {
 					error = -ERANGE;
 					goto cleanup;
 				}
-				buffer += size;
+				memcpy(buffer, prefix, prefix_len);
+				buffer += prefix_len;
+				memcpy(buffer, entry->e_name, entry->e_name_len);
+				buffer += entry->e_name_len;
+				*buffer++ = 0;
 			}
 			rest -= size;
 		}
diff --git a/fs/ext2/xattr_security.c b/fs/ext2/xattr_security.c
index dfb0875..ba97f24 100644
--- a/fs/ext2/xattr_security.c
+++ b/fs/ext2/xattr_security.c
@@ -7,29 +7,11 @@
 #include <linux/security.h>
 #include "xattr.h"
 
-static size_t
-ext2_xattr_security_list(const struct xattr_handler *handler,
-			 struct dentry *dentry, char *list, size_t list_size,
-			 const char *name, size_t name_len)
-{
-	const int prefix_len = XATTR_SECURITY_PREFIX_LEN;
-	const size_t total_len = prefix_len + name_len + 1;
-
-	if (list && total_len <= list_size) {
-		memcpy(list, XATTR_SECURITY_PREFIX, prefix_len);
-		memcpy(list+prefix_len, name, name_len);
-		list[prefix_len + name_len] = '\0';
-	}
-	return total_len;
-}
-
 static int
 ext2_xattr_security_get(const struct xattr_handler *handler,
 			struct dentry *dentry, const char *name,
 			void *buffer, size_t size)
 {
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
 	return ext2_xattr_get(d_inode(dentry), EXT2_XATTR_INDEX_SECURITY, name,
 			      buffer, size);
 }
@@ -39,8 +21,6 @@
 			struct dentry *dentry, const char *name,
 			const void *value, size_t size, int flags)
 {
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
 	return ext2_xattr_set(d_inode(dentry), EXT2_XATTR_INDEX_SECURITY, name,
 			      value, size, flags);
 }
@@ -71,7 +51,6 @@
 
 const struct xattr_handler ext2_xattr_security_handler = {
 	.prefix	= XATTR_SECURITY_PREFIX,
-	.list	= ext2_xattr_security_list,
 	.get	= ext2_xattr_security_get,
 	.set	= ext2_xattr_security_set,
 };
diff --git a/fs/ext2/xattr_trusted.c b/fs/ext2/xattr_trusted.c
index 3150dd3..2c94d19 100644
--- a/fs/ext2/xattr_trusted.c
+++ b/fs/ext2/xattr_trusted.c
@@ -8,23 +8,10 @@
 #include "ext2.h"
 #include "xattr.h"
 
-static size_t
-ext2_xattr_trusted_list(const struct xattr_handler *handler,
-			struct dentry *dentry, char *list, size_t list_size,
-			const char *name, size_t name_len)
+static bool
+ext2_xattr_trusted_list(struct dentry *dentry)
 {
-	const int prefix_len = XATTR_TRUSTED_PREFIX_LEN;
-	const size_t total_len = prefix_len + name_len + 1;
-
-	if (!capable(CAP_SYS_ADMIN))
-		return 0;
-
-	if (list && total_len <= list_size) {
-		memcpy(list, XATTR_TRUSTED_PREFIX, prefix_len);
-		memcpy(list+prefix_len, name, name_len);
-		list[prefix_len + name_len] = '\0';
-	}
-	return total_len;
+	return capable(CAP_SYS_ADMIN);
 }
 
 static int
@@ -32,8 +19,6 @@
 		       struct dentry *dentry, const char *name,
 		       void *buffer, size_t size)
 {
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
 	return ext2_xattr_get(d_inode(dentry), EXT2_XATTR_INDEX_TRUSTED, name,
 			      buffer, size);
 }
@@ -43,8 +28,6 @@
 		       struct dentry *dentry, const char *name,
 		       const void *value, size_t size, int flags)
 {
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
 	return ext2_xattr_set(d_inode(dentry), EXT2_XATTR_INDEX_TRUSTED, name,
 			      value, size, flags);
 }
diff --git a/fs/ext2/xattr_user.c b/fs/ext2/xattr_user.c
index 339a49b..72a2a96 100644
--- a/fs/ext2/xattr_user.c
+++ b/fs/ext2/xattr_user.c
@@ -10,23 +10,10 @@
 #include "ext2.h"
 #include "xattr.h"
 
-static size_t
-ext2_xattr_user_list(const struct xattr_handler *handler,
-		     struct dentry *dentry, char *list, size_t list_size,
-		     const char *name, size_t name_len)
+static bool
+ext2_xattr_user_list(struct dentry *dentry)
 {
-	const size_t prefix_len = XATTR_USER_PREFIX_LEN;
-	const size_t total_len = prefix_len + name_len + 1;
-
-	if (!test_opt(dentry->d_sb, XATTR_USER))
-		return 0;
-
-	if (list && total_len <= list_size) {
-		memcpy(list, XATTR_USER_PREFIX, prefix_len);
-		memcpy(list+prefix_len, name, name_len);
-		list[prefix_len + name_len] = '\0';
-	}
-	return total_len;
+	return test_opt(dentry->d_sb, XATTR_USER);
 }
 
 static int
@@ -34,8 +21,6 @@
 		    struct dentry *dentry, const char *name,
 		    void *buffer, size_t size)
 {
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
 	if (!test_opt(dentry->d_sb, XATTR_USER))
 		return -EOPNOTSUPP;
 	return ext2_xattr_get(d_inode(dentry), EXT2_XATTR_INDEX_USER,
@@ -47,8 +32,6 @@
 		    struct dentry *dentry, const char *name,
 		    const void *value, size_t size, int flags)
 {
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
 	if (!test_opt(dentry->d_sb, XATTR_USER))
 		return -EOPNOTSUPP;
 
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index ea433a7..b3bd912 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -4283,6 +4283,7 @@
 			inode->i_op = &ext4_symlink_inode_operations;
 			ext4_set_aops(inode);
 		}
+		inode_nohighmem(inode);
 	} else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) ||
 	      S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) {
 		inode->i_op = &ext4_special_inode_operations;
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index a969ab3..f27e0c2 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -3132,6 +3132,7 @@
 	if ((disk_link.len > EXT4_N_BLOCKS * 4)) {
 		if (!encryption_required)
 			inode->i_op = &ext4_symlink_inode_operations;
+		inode_nohighmem(inode);
 		ext4_set_aops(inode);
 		/*
 		 * We cannot call page_symlink() with transaction started
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 17fbe38..090b349 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -52,9 +52,8 @@
  */
 static void buffer_io_error(struct buffer_head *bh)
 {
-	char b[BDEVNAME_SIZE];
-	printk_ratelimited(KERN_ERR "Buffer I/O error on device %s, logical block %llu\n",
-			bdevname(bh->b_bdev, b),
+	printk_ratelimited(KERN_ERR "Buffer I/O error on device %pg, logical block %llu\n",
+		       bh->b_bdev,
 			(unsigned long long)bh->b_blocknr);
 }
 
diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c
index e8e7af6..6f7ee30 100644
--- a/fs/ext4/symlink.c
+++ b/fs/ext4/symlink.c
@@ -23,17 +23,21 @@
 #include "xattr.h"
 
 #ifdef CONFIG_EXT4_FS_ENCRYPTION
-static const char *ext4_encrypted_follow_link(struct dentry *dentry, void **cookie)
+static const char *ext4_encrypted_get_link(struct dentry *dentry,
+					   struct inode *inode,
+					   struct delayed_call *done)
 {
 	struct page *cpage = NULL;
 	char *caddr, *paddr = NULL;
 	struct ext4_str cstr, pstr;
-	struct inode *inode = d_inode(dentry);
 	struct ext4_encrypted_symlink_data *sd;
 	loff_t size = min_t(loff_t, i_size_read(inode), PAGE_SIZE - 1);
 	int res;
 	u32 plen, max_size = inode->i_sb->s_blocksize;
 
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+
 	res = ext4_get_encryption_info(inode);
 	if (res)
 		return ERR_PTR(res);
@@ -45,7 +49,7 @@
 		cpage = read_mapping_page(inode->i_mapping, 0, NULL);
 		if (IS_ERR(cpage))
 			return ERR_CAST(cpage);
-		caddr = kmap(cpage);
+		caddr = page_address(cpage);
 		caddr[size] = 0;
 	}
 
@@ -75,24 +79,20 @@
 	/* Null-terminate the name */
 	if (res <= plen)
 		paddr[res] = '\0';
-	if (cpage) {
-		kunmap(cpage);
+	if (cpage)
 		page_cache_release(cpage);
-	}
-	return *cookie = paddr;
+	set_delayed_call(done, kfree_link, paddr);
+	return paddr;
 errout:
-	if (cpage) {
-		kunmap(cpage);
+	if (cpage)
 		page_cache_release(cpage);
-	}
 	kfree(paddr);
 	return ERR_PTR(res);
 }
 
 const struct inode_operations ext4_encrypted_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link    = ext4_encrypted_follow_link,
-	.put_link       = kfree_put_link,
+	.get_link	= ext4_encrypted_get_link,
 	.setattr	= ext4_setattr,
 	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
@@ -103,8 +103,7 @@
 
 const struct inode_operations ext4_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= page_follow_link_light,
-	.put_link	= page_put_link,
+	.get_link	= page_get_link,
 	.setattr	= ext4_setattr,
 	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
@@ -114,7 +113,7 @@
 
 const struct inode_operations ext4_fast_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link    = simple_follow_link,
+	.get_link	= simple_get_link,
 	.setattr	= ext4_setattr,
 	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 6b6b3e7..a95151e 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -68,10 +68,8 @@
 		printk("\n"); \
 	} while (0)
 # define ea_bdebug(bh, f...) do { \
-		char b[BDEVNAME_SIZE]; \
-		printk(KERN_DEBUG "block %s:%lu: ", \
-			bdevname(bh->b_bdev, b), \
-			(unsigned long) bh->b_blocknr); \
+		printk(KERN_DEBUG "block %pg:%lu: ",		   \
+		       bh->b_bdev, (unsigned long) bh->b_blocknr); \
 		printk(f); \
 		printk("\n"); \
 	} while (0)
@@ -404,19 +402,24 @@
 		const struct xattr_handler *handler =
 			ext4_xattr_handler(entry->e_name_index);
 
-		if (handler) {
-			size_t size = handler->list(handler, dentry, buffer,
-						    rest, entry->e_name,
-						    entry->e_name_len);
+		if (handler && (!handler->list || handler->list(dentry))) {
+			const char *prefix = handler->prefix ?: handler->name;
+			size_t prefix_len = strlen(prefix);
+			size_t size = prefix_len + entry->e_name_len + 1;
+
 			if (buffer) {
 				if (size > rest)
 					return -ERANGE;
-				buffer += size;
+				memcpy(buffer, prefix, prefix_len);
+				buffer += prefix_len;
+				memcpy(buffer, entry->e_name, entry->e_name_len);
+				buffer += entry->e_name_len;
+				*buffer++ = 0;
 			}
 			rest -= size;
 		}
 	}
-	return buffer_size - rest;
+	return buffer_size - rest;  /* total size */
 }
 
 static int
diff --git a/fs/ext4/xattr_security.c b/fs/ext4/xattr_security.c
index 36f4c1a..3e81bdc 100644
--- a/fs/ext4/xattr_security.c
+++ b/fs/ext4/xattr_security.c
@@ -11,30 +11,11 @@
 #include "ext4.h"
 #include "xattr.h"
 
-static size_t
-ext4_xattr_security_list(const struct xattr_handler *handler,
-			 struct dentry *dentry, char *list, size_t list_size,
-			 const char *name, size_t name_len)
-{
-	const size_t prefix_len = sizeof(XATTR_SECURITY_PREFIX)-1;
-	const size_t total_len = prefix_len + name_len + 1;
-
-
-	if (list && total_len <= list_size) {
-		memcpy(list, XATTR_SECURITY_PREFIX, prefix_len);
-		memcpy(list+prefix_len, name, name_len);
-		list[prefix_len + name_len] = '\0';
-	}
-	return total_len;
-}
-
 static int
 ext4_xattr_security_get(const struct xattr_handler *handler,
 			struct dentry *dentry, const char *name,
 			void *buffer, size_t size)
 {
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
 	return ext4_xattr_get(d_inode(dentry), EXT4_XATTR_INDEX_SECURITY,
 			      name, buffer, size);
 }
@@ -44,8 +25,6 @@
 			struct dentry *dentry, const char *name,
 			const void *value, size_t size, int flags)
 {
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
 	return ext4_xattr_set(d_inode(dentry), EXT4_XATTR_INDEX_SECURITY,
 			      name, value, size, flags);
 }
@@ -79,7 +58,6 @@
 
 const struct xattr_handler ext4_xattr_security_handler = {
 	.prefix	= XATTR_SECURITY_PREFIX,
-	.list	= ext4_xattr_security_list,
 	.get	= ext4_xattr_security_get,
 	.set	= ext4_xattr_security_set,
 };
diff --git a/fs/ext4/xattr_trusted.c b/fs/ext4/xattr_trusted.c
index 4880890..2a3c6f9 100644
--- a/fs/ext4/xattr_trusted.c
+++ b/fs/ext4/xattr_trusted.c
@@ -12,23 +12,10 @@
 #include "ext4.h"
 #include "xattr.h"
 
-static size_t
-ext4_xattr_trusted_list(const struct xattr_handler *handler,
-			struct dentry *dentry, char *list, size_t list_size,
-			const char *name, size_t name_len)
+static bool
+ext4_xattr_trusted_list(struct dentry *dentry)
 {
-	const size_t prefix_len = XATTR_TRUSTED_PREFIX_LEN;
-	const size_t total_len = prefix_len + name_len + 1;
-
-	if (!capable(CAP_SYS_ADMIN))
-		return 0;
-
-	if (list && total_len <= list_size) {
-		memcpy(list, XATTR_TRUSTED_PREFIX, prefix_len);
-		memcpy(list+prefix_len, name, name_len);
-		list[prefix_len + name_len] = '\0';
-	}
-	return total_len;
+	return capable(CAP_SYS_ADMIN);
 }
 
 static int
@@ -36,8 +23,6 @@
 		       struct dentry *dentry, const char *name, void *buffer,
 		       size_t size)
 {
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
 	return ext4_xattr_get(d_inode(dentry), EXT4_XATTR_INDEX_TRUSTED,
 			      name, buffer, size);
 }
@@ -47,8 +32,6 @@
 		       struct dentry *dentry, const char *name,
 		       const void *value, size_t size, int flags)
 {
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
 	return ext4_xattr_set(d_inode(dentry), EXT4_XATTR_INDEX_TRUSTED,
 			      name, value, size, flags);
 }
diff --git a/fs/ext4/xattr_user.c b/fs/ext4/xattr_user.c
index d2dec33..d152f43 100644
--- a/fs/ext4/xattr_user.c
+++ b/fs/ext4/xattr_user.c
@@ -11,23 +11,10 @@
 #include "ext4.h"
 #include "xattr.h"
 
-static size_t
-ext4_xattr_user_list(const struct xattr_handler *handler,
-		     struct dentry *dentry, char *list, size_t list_size,
-		     const char *name, size_t name_len)
+static bool
+ext4_xattr_user_list(struct dentry *dentry)
 {
-	const size_t prefix_len = XATTR_USER_PREFIX_LEN;
-	const size_t total_len = prefix_len + name_len + 1;
-
-	if (!test_opt(dentry->d_sb, XATTR_USER))
-		return 0;
-
-	if (list && total_len <= list_size) {
-		memcpy(list, XATTR_USER_PREFIX, prefix_len);
-		memcpy(list+prefix_len, name, name_len);
-		list[prefix_len + name_len] = '\0';
-	}
-	return total_len;
+	return test_opt(dentry->d_sb, XATTR_USER);
 }
 
 static int
@@ -35,8 +22,6 @@
 		    struct dentry *dentry, const char *name,
 		    void *buffer, size_t size)
 {
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
 	if (!test_opt(dentry->d_sb, XATTR_USER))
 		return -EOPNOTSUPP;
 	return ext4_xattr_get(d_inode(dentry), EXT4_XATTR_INDEX_USER,
@@ -48,8 +33,6 @@
 		    struct dentry *dentry, const char *name,
 		    const void *value, size_t size, int flags)
 {
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
 	if (!test_opt(dentry->d_sb, XATTR_USER))
 		return -EOPNOTSUPP;
 	return ext4_xattr_set(d_inode(dentry), EXT4_XATTR_INDEX_USER,
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index 478e5d5..ad1b18a 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -211,12 +211,10 @@
 
 	mutex_lock(&f2fs_stat_mutex);
 	list_for_each_entry(si, &f2fs_stat_list, stat_list) {
-		char devname[BDEVNAME_SIZE];
-
 		update_general_status(si->sbi);
 
-		seq_printf(s, "\n=====[ partition info(%s). #%d ]=====\n",
-			bdevname(si->sbi->sb->s_bdev, devname), i++);
+		seq_printf(s, "\n=====[ partition info(%pg). #%d ]=====\n",
+			si->sbi->sb->s_bdev, i++);
 		seq_printf(s, "[SB: 1] [CP: 2] [SIT: %d] [NAT: %d] ",
 			   si->sit_area_segs, si->nat_area_segs);
 		seq_printf(s, "[SSA: %d] [MAIN: %d",
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 9db5500..ec6067c 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1602,13 +1602,11 @@
 
 static inline bool f2fs_may_extent_tree(struct inode *inode)
 {
-	mode_t mode = inode->i_mode;
-
 	if (!test_opt(F2FS_I_SB(inode), EXTENT_CACHE) ||
 			is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT))
 		return false;
 
-	return S_ISREG(mode);
+	return S_ISREG(inode->i_mode);
 }
 
 static inline void *f2fs_kvmalloc(size_t size, gfp_t flags)
@@ -2121,7 +2119,7 @@
 static inline bool f2fs_may_encrypt(struct inode *inode)
 {
 #ifdef CONFIG_F2FS_FS_ENCRYPTION
-	mode_t mode = inode->i_mode;
+	umode_t mode = inode->i_mode;
 
 	return (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode));
 #else
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 97e20de..5528801 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -202,6 +202,7 @@
 			inode->i_op = &f2fs_encrypted_symlink_inode_operations;
 		else
 			inode->i_op = &f2fs_symlink_inode_operations;
+		inode_nohighmem(inode);
 		inode->i_mapping->a_ops = &f2fs_dblock_aops;
 	} else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) ||
 			S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) {
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index 2c32110..e7587fc 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -315,12 +315,15 @@
 	return err;
 }
 
-static const char *f2fs_follow_link(struct dentry *dentry, void **cookie)
+static const char *f2fs_get_link(struct dentry *dentry,
+				 struct inode *inode,
+				 struct delayed_call *done)
 {
-	const char *link = page_follow_link_light(dentry, cookie);
+	const char *link = page_get_link(dentry, inode, done);
 	if (!IS_ERR(link) && !*link) {
 		/* this is broken symlink case */
-		page_put_link(NULL, *cookie);
+		do_delayed_call(done);
+		clear_delayed_call(done);
 		link = ERR_PTR(-ENOENT);
 	}
 	return link;
@@ -351,6 +354,7 @@
 		inode->i_op = &f2fs_encrypted_symlink_inode_operations;
 	else
 		inode->i_op = &f2fs_symlink_inode_operations;
+	inode_nohighmem(inode);
 	inode->i_mapping->a_ops = &f2fs_dblock_aops;
 
 	f2fs_lock_op(sbi);
@@ -923,18 +927,22 @@
 }
 
 #ifdef CONFIG_F2FS_FS_ENCRYPTION
-static const char *f2fs_encrypted_follow_link(struct dentry *dentry, void **cookie)
+static const char *f2fs_encrypted_get_link(struct dentry *dentry,
+					   struct inode *inode,
+					   struct delayed_call *done)
 {
 	struct page *cpage = NULL;
 	char *caddr, *paddr = NULL;
 	struct f2fs_str cstr;
 	struct f2fs_str pstr = FSTR_INIT(NULL, 0);
-	struct inode *inode = d_inode(dentry);
 	struct f2fs_encrypted_symlink_data *sd;
 	loff_t size = min_t(loff_t, i_size_read(inode), PAGE_SIZE - 1);
 	u32 max_size = inode->i_sb->s_blocksize;
 	int res;
 
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+
 	res = f2fs_get_encryption_info(inode);
 	if (res)
 		return ERR_PTR(res);
@@ -942,7 +950,7 @@
 	cpage = read_mapping_page(inode->i_mapping, 0, NULL);
 	if (IS_ERR(cpage))
 		return ERR_CAST(cpage);
-	caddr = kmap(cpage);
+	caddr = page_address(cpage);
 	caddr[size] = 0;
 
 	/* Symlink is encrypted */
@@ -982,21 +990,19 @@
 	/* Null-terminate the name */
 	paddr[res] = '\0';
 
-	kunmap(cpage);
 	page_cache_release(cpage);
-	return *cookie = paddr;
+	set_delayed_call(done, kfree_link, paddr);
+	return paddr;
 errout:
 	kfree(cstr.name);
 	f2fs_fname_crypto_free_buffer(&pstr);
-	kunmap(cpage);
 	page_cache_release(cpage);
 	return ERR_PTR(res);
 }
 
 const struct inode_operations f2fs_encrypted_symlink_inode_operations = {
 	.readlink       = generic_readlink,
-	.follow_link    = f2fs_encrypted_follow_link,
-	.put_link       = kfree_put_link,
+	.get_link       = f2fs_encrypted_get_link,
 	.getattr	= f2fs_getattr,
 	.setattr	= f2fs_setattr,
 	.setxattr	= generic_setxattr,
@@ -1031,8 +1037,7 @@
 
 const struct inode_operations f2fs_symlink_inode_operations = {
 	.readlink       = generic_readlink,
-	.follow_link    = f2fs_follow_link,
-	.put_link       = page_put_link,
+	.get_link       = f2fs_get_link,
 	.getattr	= f2fs_getattr,
 	.setattr	= f2fs_setattr,
 #ifdef CONFIG_F2FS_FS_XATTR
diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c
index 862368a..036952a 100644
--- a/fs/f2fs/xattr.c
+++ b/fs/f2fs/xattr.c
@@ -25,38 +25,6 @@
 #include "f2fs.h"
 #include "xattr.h"
 
-static size_t f2fs_xattr_generic_list(const struct xattr_handler *handler,
-		struct dentry *dentry, char *list, size_t list_size,
-		const char *name, size_t len)
-{
-	struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb);
-	int total_len, prefix_len;
-
-	switch (handler->flags) {
-	case F2FS_XATTR_INDEX_USER:
-		if (!test_opt(sbi, XATTR_USER))
-			return -EOPNOTSUPP;
-		break;
-	case F2FS_XATTR_INDEX_TRUSTED:
-		if (!capable(CAP_SYS_ADMIN))
-			return -EPERM;
-		break;
-	case F2FS_XATTR_INDEX_SECURITY:
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	prefix_len = strlen(handler->prefix);
-	total_len = prefix_len + len + 1;
-	if (list && total_len <= list_size) {
-		memcpy(list, handler->prefix, prefix_len);
-		memcpy(list + prefix_len, name, len);
-		list[prefix_len + len] = '\0';
-	}
-	return total_len;
-}
-
 static int f2fs_xattr_generic_get(const struct xattr_handler *handler,
 		struct dentry *dentry, const char *name, void *buffer,
 		size_t size)
@@ -77,8 +45,6 @@
 	default:
 		return -EINVAL;
 	}
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
 	return f2fs_getxattr(d_inode(dentry), handler->flags, name,
 			     buffer, size, NULL);
 }
@@ -103,24 +69,20 @@
 	default:
 		return -EINVAL;
 	}
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
-
 	return f2fs_setxattr(d_inode(dentry), handler->flags, name,
 					value, size, NULL, flags);
 }
 
-static size_t f2fs_xattr_advise_list(const struct xattr_handler *handler,
-		struct dentry *dentry, char *list, size_t list_size,
-		const char *name, size_t len)
+static bool f2fs_xattr_user_list(struct dentry *dentry)
 {
-	const char *xname = F2FS_SYSTEM_ADVISE_PREFIX;
-	size_t size;
+	struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb);
 
-	size = strlen(xname) + 1;
-	if (list && size <= list_size)
-		memcpy(list, xname, size);
-	return size;
+	return test_opt(sbi, XATTR_USER);
+}
+
+static bool f2fs_xattr_trusted_list(struct dentry *dentry)
+{
+	return capable(CAP_SYS_ADMIN);
 }
 
 static int f2fs_xattr_advise_get(const struct xattr_handler *handler,
@@ -129,9 +91,6 @@
 {
 	struct inode *inode = d_inode(dentry);
 
-	if (strcmp(name, "") != 0)
-		return -EINVAL;
-
 	if (buffer)
 		*((char *)buffer) = F2FS_I(inode)->i_advise;
 	return sizeof(char);
@@ -143,8 +102,6 @@
 {
 	struct inode *inode = d_inode(dentry);
 
-	if (strcmp(name, "") != 0)
-		return -EINVAL;
 	if (!inode_owner_or_capable(inode))
 		return -EPERM;
 	if (value == NULL)
@@ -183,7 +140,7 @@
 const struct xattr_handler f2fs_xattr_user_handler = {
 	.prefix	= XATTR_USER_PREFIX,
 	.flags	= F2FS_XATTR_INDEX_USER,
-	.list	= f2fs_xattr_generic_list,
+	.list	= f2fs_xattr_user_list,
 	.get	= f2fs_xattr_generic_get,
 	.set	= f2fs_xattr_generic_set,
 };
@@ -191,15 +148,14 @@
 const struct xattr_handler f2fs_xattr_trusted_handler = {
 	.prefix	= XATTR_TRUSTED_PREFIX,
 	.flags	= F2FS_XATTR_INDEX_TRUSTED,
-	.list	= f2fs_xattr_generic_list,
+	.list	= f2fs_xattr_trusted_list,
 	.get	= f2fs_xattr_generic_get,
 	.set	= f2fs_xattr_generic_set,
 };
 
 const struct xattr_handler f2fs_xattr_advise_handler = {
-	.prefix = F2FS_SYSTEM_ADVISE_PREFIX,
+	.name	= F2FS_SYSTEM_ADVISE_NAME,
 	.flags	= F2FS_XATTR_INDEX_ADVISE,
-	.list   = f2fs_xattr_advise_list,
 	.get    = f2fs_xattr_advise_get,
 	.set    = f2fs_xattr_advise_set,
 };
@@ -207,7 +163,6 @@
 const struct xattr_handler f2fs_xattr_security_handler = {
 	.prefix	= XATTR_SECURITY_PREFIX,
 	.flags	= F2FS_XATTR_INDEX_SECURITY,
-	.list	= f2fs_xattr_generic_list,
 	.get	= f2fs_xattr_generic_get,
 	.set	= f2fs_xattr_generic_set,
 };
@@ -455,20 +410,27 @@
 	list_for_each_xattr(entry, base_addr) {
 		const struct xattr_handler *handler =
 			f2fs_xattr_handler(entry->e_name_index);
+		const char *prefix;
+		size_t prefix_len;
 		size_t size;
 
-		if (!handler)
+		if (!handler || (handler->list && !handler->list(dentry)))
 			continue;
 
-		size = handler->list(handler, dentry, buffer, rest,
-				     entry->e_name, entry->e_name_len);
-		if (buffer && size > rest) {
-			error = -ERANGE;
-			goto cleanup;
+		prefix = handler->prefix ?: handler->name;
+		prefix_len = strlen(prefix);
+		size = prefix_len + entry->e_name_len + 1;
+		if (buffer) {
+			if (size > rest) {
+				error = -ERANGE;
+				goto cleanup;
+			}
+			memcpy(buffer, prefix, prefix_len);
+			buffer += prefix_len;
+			memcpy(buffer, entry->e_name, entry->e_name_len);
+			buffer += entry->e_name_len;
+			*buffer++ = 0;
 		}
-
-		if (buffer)
-			buffer += size;
 		rest -= size;
 	}
 	error = buffer_size - rest;
diff --git a/fs/f2fs/xattr.h b/fs/f2fs/xattr.h
index 71a7100..79dccc8 100644
--- a/fs/f2fs/xattr.h
+++ b/fs/f2fs/xattr.h
@@ -27,7 +27,7 @@
 #define F2FS_XATTR_REFCOUNT_MAX         1024
 
 /* Name indexes */
-#define F2FS_SYSTEM_ADVISE_PREFIX		"system.advise"
+#define F2FS_SYSTEM_ADVISE_NAME			"system.advise"
 #define F2FS_XATTR_INDEX_USER			1
 #define F2FS_XATTR_INDEX_POSIX_ACL_ACCESS	2
 #define F2FS_XATTR_INDEX_POSIX_ACL_DEFAULT	3
diff --git a/fs/fcntl.c b/fs/fcntl.c
index ee85cd4..350a2c8 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -51,7 +51,8 @@
 	       if (arg & O_NDELAY)
 		   arg |= O_NONBLOCK;
 
-	if (arg & O_DIRECT) {
+	/* Pipe packetized mode is controlled by O_DIRECT flag */
+	if (!S_ISFIFO(filp->f_inode->i_mode) && (arg & O_DIRECT)) {
 		if (!filp->f_mapping || !filp->f_mapping->a_ops ||
 			!filp->f_mapping->a_ops->direct_IO)
 				return -EINVAL;
diff --git a/fs/file.c b/fs/file.c
index 39f8f15..1aed0ad 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -25,9 +25,9 @@
 
 int sysctl_nr_open __read_mostly = 1024*1024;
 int sysctl_nr_open_min = BITS_PER_LONG;
-/* our max() is unusable in constant expressions ;-/ */
-#define __const_max(x, y) ((x) < (y) ? (x) : (y))
-int sysctl_nr_open_max = __const_max(INT_MAX, ~(size_t)0/sizeof(void *)) &
+/* our min() is unusable in constant expressions ;-/ */
+#define __const_min(x, y) ((x) < (y) ? (x) : (y))
+int sysctl_nr_open_max = __const_min(INT_MAX, ~(size_t)0/sizeof(void *)) &
 			 -BITS_PER_LONG;
 
 static void *alloc_fdmem(size_t size)
diff --git a/fs/freevxfs/vxfs_inode.c b/fs/freevxfs/vxfs_inode.c
index ef73ed6..3e2ccad 100644
--- a/fs/freevxfs/vxfs_inode.c
+++ b/fs/freevxfs/vxfs_inode.c
@@ -326,6 +326,7 @@
 	} else if (S_ISLNK(ip->i_mode)) {
 		if (!VXFS_ISIMMED(vip)) {
 			ip->i_op = &page_symlink_inode_operations;
+			inode_nohighmem(ip);
 			ip->i_mapping->a_ops = &vxfs_aops;
 		} else {
 			ip->i_op = &simple_symlink_inode_operations;
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 5e2e087..712601f 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -1365,15 +1365,19 @@
 	return err;
 }
 
-static const char *fuse_follow_link(struct dentry *dentry, void **cookie)
+static const char *fuse_get_link(struct dentry *dentry,
+				 struct inode *inode,
+				 struct delayed_call *done)
 {
-	struct inode *inode = d_inode(dentry);
 	struct fuse_conn *fc = get_fuse_conn(inode);
 	FUSE_ARGS(args);
 	char *link;
 	ssize_t ret;
 
-	link = (char *) __get_free_page(GFP_KERNEL);
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+
+	link = kmalloc(PAGE_SIZE, GFP_KERNEL);
 	if (!link)
 		return ERR_PTR(-ENOMEM);
 
@@ -1385,11 +1389,11 @@
 	args.out.args[0].value = link;
 	ret = fuse_simple_request(fc, &args);
 	if (ret < 0) {
-		free_page((unsigned long) link);
+		kfree(link);
 		link = ERR_PTR(ret);
 	} else {
 		link[ret] = '\0';
-		*cookie = link;
+		set_delayed_call(done, kfree_link, link);
 	}
 	fuse_invalidate_atime(inode);
 	return link;
@@ -1909,8 +1913,7 @@
 
 static const struct inode_operations fuse_symlink_inode_operations = {
 	.setattr	= fuse_setattr,
-	.follow_link	= fuse_follow_link,
-	.put_link	= free_page_put_link,
+	.get_link	= fuse_get_link,
 	.readlink	= generic_readlink,
 	.getattr	= fuse_getattr,
 	.setxattr	= fuse_setxattr,
diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c
index 1be3b06..7919326 100644
--- a/fs/gfs2/acl.c
+++ b/fs/gfs2/acl.c
@@ -31,9 +31,9 @@
 {
 	switch (type) {
 	case ACL_TYPE_ACCESS:
-		return GFS2_POSIX_ACL_ACCESS;
+		return XATTR_POSIX_ACL_ACCESS;
 	case ACL_TYPE_DEFAULT:
-		return GFS2_POSIX_ACL_DEFAULT;
+		return XATTR_POSIX_ACL_DEFAULT;
 	}
 	return NULL;
 }
diff --git a/fs/gfs2/acl.h b/fs/gfs2/acl.h
index 2d65ec4..3af4f40 100644
--- a/fs/gfs2/acl.h
+++ b/fs/gfs2/acl.h
@@ -12,8 +12,6 @@
 
 #include "incore.h"
 
-#define GFS2_POSIX_ACL_ACCESS		"posix_acl_access"
-#define GFS2_POSIX_ACL_DEFAULT		"posix_acl_default"
 #define GFS2_ACL_MAX_ENTRIES(sdp) ((300 << (sdp)->sd_sb.sb_bsize_shift) >> 12)
 
 extern struct posix_acl *gfs2_get_acl(struct inode *inode, int type);
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 1caee05..93f0746 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -914,7 +914,7 @@
 failed:
 	gfs2_trans_end(sdp);
 	gfs2_inplace_release(ip);
-	if (ip->i_res->rs_qa_qd_num)
+	if (ip->i_qadata && ip->i_qadata->qa_qd_num)
 		gfs2_quota_unlock(ip);
 	if (inode == sdp->sd_rindex) {
 		gfs2_glock_dq(&m_ip->i_gh);
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 61296ec..0860f0b 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -787,8 +787,8 @@
 	if (error)
 		goto out_rlist;
 
-	if (gfs2_rs_active(ip->i_res)) /* needs to be done with the rgrp glock held */
-		gfs2_rs_deltree(ip->i_res);
+	if (gfs2_rs_active(&ip->i_res)) /* needs to be done with the rgrp glock held */
+		gfs2_rs_deltree(&ip->i_res);
 
 	error = gfs2_trans_begin(sdp, rg_blocks + RES_DINODE +
 				 RES_INDIRECT + RES_STATFS + RES_QUOTA,
@@ -1291,13 +1291,9 @@
 	if (ret)
 		return ret;
 
-	ret = get_write_access(inode);
-	if (ret)
-		return ret;
-
 	inode_dio_wait(inode);
 
-	ret = gfs2_rs_alloc(ip);
+	ret = gfs2_rsqa_alloc(ip);
 	if (ret)
 		goto out;
 
@@ -1307,10 +1303,9 @@
 		goto out;
 	}
 
-	gfs2_rs_deltree(ip->i_res);
 	ret = do_shrink(inode, oldsize, newsize);
 out:
-	put_write_access(inode);
+	gfs2_rsqa_delete(ip, NULL);
 	return ret;
 }
 
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index ad8a5b7..6a92592 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -82,6 +82,8 @@
 
 #define gfs2_disk_hash2offset(h) (((u64)(h)) >> 1)
 #define gfs2_dir_offset2hash(p) ((u32)(((u64)(p)) << 1))
+#define GFS2_HASH_INDEX_MASK 0xffffc000
+#define GFS2_USE_HASH_FLAG 0x2000
 
 struct qstr gfs2_qdot __read_mostly;
 struct qstr gfs2_qdotdot __read_mostly;
@@ -108,7 +110,7 @@
 	struct buffer_head *bh;
 	int error;
 
-	error = gfs2_meta_read(ip->i_gl, block, DIO_WAIT, &bh);
+	error = gfs2_meta_read(ip->i_gl, block, DIO_WAIT, 0, &bh);
 	if (error)
 		return error;
 	if (gfs2_metatype_check(GFS2_SB(&ip->i_inode), bh, GFS2_METATYPE_JD)) {
@@ -305,7 +307,7 @@
 			BUG_ON(extlen < 1);
 			bh = gfs2_meta_ra(ip->i_gl, dblock, extlen);
 		} else {
-			error = gfs2_meta_read(ip->i_gl, dblock, DIO_WAIT, &bh);
+			error = gfs2_meta_read(ip->i_gl, dblock, DIO_WAIT, 0, &bh);
 			if (error)
 				goto fail;
 		}
@@ -443,6 +445,27 @@
 	return 0;
 }
 
+/* Look for the dirent that contains the offset specified in data. Once we
+ * find that dirent, there must be space available there for the new dirent */
+static int gfs2_dirent_find_offset(const struct gfs2_dirent *dent,
+				  const struct qstr *name,
+				  void *ptr)
+{
+	unsigned required = GFS2_DIRENT_SIZE(name->len);
+	unsigned actual = GFS2_DIRENT_SIZE(be16_to_cpu(dent->de_name_len));
+	unsigned totlen = be16_to_cpu(dent->de_rec_len);
+
+	if (ptr < (void *)dent || ptr >= (void *)dent + totlen)
+		return 0;
+	if (gfs2_dirent_sentinel(dent))
+		actual = 0;
+	if (ptr < (void *)dent + actual)
+		return -1;
+	if ((void *)dent + totlen >= ptr + required)
+		return 1;
+	return -1;
+}
+
 static int gfs2_dirent_find_space(const struct gfs2_dirent *dent,
 				  const struct qstr *name,
 				  void *opaque)
@@ -682,21 +705,17 @@
 	prev->de_rec_len = cpu_to_be16(prev_rec_len);
 }
 
-/*
- * Takes a dent from which to grab space as an argument. Returns the
- * newly created dent.
- */
-static struct gfs2_dirent *gfs2_init_dirent(struct inode *inode,
-					    struct gfs2_dirent *dent,
-					    const struct qstr *name,
-					    struct buffer_head *bh)
+
+static struct gfs2_dirent *do_init_dirent(struct inode *inode,
+					  struct gfs2_dirent *dent,
+					  const struct qstr *name,
+					  struct buffer_head *bh,
+					  unsigned offset)
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_dirent *ndent;
-	unsigned offset = 0, totlen;
+	unsigned totlen;
 
-	if (!gfs2_dirent_sentinel(dent))
-		offset = GFS2_DIRENT_SIZE(be16_to_cpu(dent->de_name_len));
 	totlen = be16_to_cpu(dent->de_rec_len);
 	BUG_ON(offset + name->len > totlen);
 	gfs2_trans_add_meta(ip->i_gl, bh);
@@ -706,16 +725,35 @@
 	return ndent;
 }
 
-static struct gfs2_dirent *gfs2_dirent_alloc(struct inode *inode,
-					     struct buffer_head *bh,
-					     const struct qstr *name)
+
+/*
+ * Takes a dent from which to grab space as an argument. Returns the
+ * newly created dent.
+ */
+static struct gfs2_dirent *gfs2_init_dirent(struct inode *inode,
+					    struct gfs2_dirent *dent,
+					    const struct qstr *name,
+					    struct buffer_head *bh)
+{
+	unsigned offset = 0;
+
+	if (!gfs2_dirent_sentinel(dent))
+		offset = GFS2_DIRENT_SIZE(be16_to_cpu(dent->de_name_len));
+	return do_init_dirent(inode, dent, name, bh, offset);
+}
+
+static struct gfs2_dirent *gfs2_dirent_split_alloc(struct inode *inode,
+						   struct buffer_head *bh,
+						   const struct qstr *name,
+						   void *ptr)
 {
 	struct gfs2_dirent *dent;
 	dent = gfs2_dirent_scan(inode, bh->b_data, bh->b_size,
-				gfs2_dirent_find_space, name, NULL);
+				gfs2_dirent_find_offset, name, ptr);
 	if (!dent || IS_ERR(dent))
 		return dent;
-	return gfs2_init_dirent(inode, dent, name, bh);
+	return do_init_dirent(inode, dent, name, bh,
+			      (unsigned)(ptr - (void *)dent));
 }
 
 static int get_leaf(struct gfs2_inode *dip, u64 leaf_no,
@@ -723,7 +761,7 @@
 {
 	int error;
 
-	error = gfs2_meta_read(dip->i_gl, leaf_no, DIO_WAIT, bhp);
+	error = gfs2_meta_read(dip->i_gl, leaf_no, DIO_WAIT, 0, bhp);
 	if (!error && gfs2_metatype_check(GFS2_SB(&dip->i_inode), *bhp, GFS2_METATYPE_LF)) {
 		/* pr_info("block num=%llu\n", leaf_no); */
 		error = -EIO;
@@ -1051,10 +1089,11 @@
 		if (!gfs2_dirent_sentinel(dent) &&
 		    be32_to_cpu(dent->de_hash) < divider) {
 			struct qstr str;
+			void *ptr = ((char *)dent - obh->b_data) + nbh->b_data;
 			str.name = (char*)(dent+1);
 			str.len = be16_to_cpu(dent->de_name_len);
 			str.hash = be32_to_cpu(dent->de_hash);
-			new = gfs2_dirent_alloc(inode, nbh, &str);
+			new = gfs2_dirent_split_alloc(inode, nbh, &str, ptr);
 			if (IS_ERR(new)) {
 				error = PTR_ERR(new);
 				break;
@@ -1186,10 +1225,10 @@
 	int ret = 0;
 
 	dent_a = *(const struct gfs2_dirent **)a;
-	hash_a = be32_to_cpu(dent_a->de_hash);
+	hash_a = dent_a->de_cookie;
 
 	dent_b = *(const struct gfs2_dirent **)b;
-	hash_b = be32_to_cpu(dent_b->de_hash);
+	hash_b = dent_b->de_cookie;
 
 	if (hash_a > hash_b)
 		ret = 1;
@@ -1227,19 +1266,20 @@
  */
 
 static int do_filldir_main(struct gfs2_inode *dip, struct dir_context *ctx,
-			   const struct gfs2_dirent **darr, u32 entries,
-			   int *copied)
+			   struct gfs2_dirent **darr, u32 entries,
+			   u32 sort_start, int *copied)
 {
 	const struct gfs2_dirent *dent, *dent_next;
 	u64 off, off_next;
 	unsigned int x, y;
 	int run = 0;
 
-	sort(darr, entries, sizeof(struct gfs2_dirent *), compare_dents, NULL);
+	if (sort_start < entries)
+		sort(&darr[sort_start], entries - sort_start,
+		     sizeof(struct gfs2_dirent *), compare_dents, NULL);
 
 	dent_next = darr[0];
-	off_next = be32_to_cpu(dent_next->de_hash);
-	off_next = gfs2_disk_hash2offset(off_next);
+	off_next = dent_next->de_cookie;
 
 	for (x = 0, y = 1; x < entries; x++, y++) {
 		dent = dent_next;
@@ -1247,8 +1287,7 @@
 
 		if (y < entries) {
 			dent_next = darr[y];
-			off_next = be32_to_cpu(dent_next->de_hash);
-			off_next = gfs2_disk_hash2offset(off_next);
+			off_next = dent_next->de_cookie;
 
 			if (off < ctx->pos)
 				continue;
@@ -1295,6 +1334,40 @@
 	return ptr;
 }
 
+
+static int gfs2_set_cookies(struct gfs2_sbd *sdp, struct buffer_head *bh,
+			    unsigned leaf_nr, struct gfs2_dirent **darr,
+			    unsigned entries)
+{
+	int sort_id = -1;
+	int i;
+	
+	for (i = 0; i < entries; i++) {
+		unsigned offset;
+
+		darr[i]->de_cookie = be32_to_cpu(darr[i]->de_hash);
+		darr[i]->de_cookie = gfs2_disk_hash2offset(darr[i]->de_cookie);
+
+		if (!sdp->sd_args.ar_loccookie)
+			continue;
+		offset = (char *)(darr[i]) -
+			 (bh->b_data + gfs2_dirent_offset(bh->b_data));
+		offset /= GFS2_MIN_DIRENT_SIZE;
+		offset += leaf_nr * sdp->sd_max_dents_per_leaf;
+		if (offset >= GFS2_USE_HASH_FLAG ||
+		    leaf_nr >= GFS2_USE_HASH_FLAG) {
+			darr[i]->de_cookie |= GFS2_USE_HASH_FLAG;
+			if (sort_id < 0)
+				sort_id = i;
+			continue;
+		}
+		darr[i]->de_cookie &= GFS2_HASH_INDEX_MASK;
+		darr[i]->de_cookie |= offset;
+	}
+	return sort_id;
+}	
+
+
 static int gfs2_dir_read_leaf(struct inode *inode, struct dir_context *ctx,
 			      int *copied, unsigned *depth,
 			      u64 leaf_no)
@@ -1304,12 +1377,11 @@
 	struct buffer_head *bh;
 	struct gfs2_leaf *lf;
 	unsigned entries = 0, entries2 = 0;
-	unsigned leaves = 0;
-	const struct gfs2_dirent **darr, *dent;
+	unsigned leaves = 0, leaf = 0, offset, sort_offset;
+	struct gfs2_dirent **darr, *dent;
 	struct dirent_gather g;
 	struct buffer_head **larr;
-	int leaf = 0;
-	int error, i;
+	int error, i, need_sort = 0, sort_id;
 	u64 lfn = leaf_no;
 
 	do {
@@ -1325,6 +1397,11 @@
 		brelse(bh);
 	} while(lfn);
 
+	if (*depth < GFS2_DIR_MAX_DEPTH || !sdp->sd_args.ar_loccookie) {
+		need_sort = 1;
+		sort_offset = 0;
+	}
+
 	if (!entries)
 		return 0;
 
@@ -1338,8 +1415,8 @@
 	larr = gfs2_alloc_sort_buffer((leaves + entries + 99) * sizeof(void *));
 	if (!larr)
 		goto out;
-	darr = (const struct gfs2_dirent **)(larr + leaves);
-	g.pdent = darr;
+	darr = (struct gfs2_dirent **)(larr + leaves);
+	g.pdent = (const struct gfs2_dirent **)darr;
 	g.offset = 0;
 	lfn = leaf_no;
 
@@ -1350,6 +1427,7 @@
 		lf = (struct gfs2_leaf *)bh->b_data;
 		lfn = be64_to_cpu(lf->lf_next);
 		if (lf->lf_entries) {
+			offset = g.offset;
 			entries2 += be16_to_cpu(lf->lf_entries);
 			dent = gfs2_dirent_scan(inode, bh->b_data, bh->b_size,
 						gfs2_dirent_gather, NULL, &g);
@@ -1367,17 +1445,26 @@
 				goto out_free;
 			}
 			error = 0;
+			sort_id = gfs2_set_cookies(sdp, bh, leaf, &darr[offset],
+						   be16_to_cpu(lf->lf_entries));
+			if (!need_sort && sort_id >= 0) {
+				need_sort = 1;
+				sort_offset = offset + sort_id;
+			}
 			larr[leaf++] = bh;
 		} else {
+			larr[leaf++] = NULL;
 			brelse(bh);
 		}
 	} while(lfn);
 
 	BUG_ON(entries2 != entries);
-	error = do_filldir_main(ip, ctx, darr, entries, copied);
+	error = do_filldir_main(ip, ctx, darr, entries, need_sort ?
+				sort_offset : entries, copied);
 out_free:
 	for(i = 0; i < leaf; i++)
-		brelse(larr[i]);
+		if (larr[i])
+			brelse(larr[i]);
 	kvfree(larr);
 out:
 	return error;
@@ -1483,7 +1570,7 @@
 	struct gfs2_inode *dip = GFS2_I(inode);
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	struct dirent_gather g;
-	const struct gfs2_dirent **darr, *dent;
+	struct gfs2_dirent **darr, *dent;
 	struct buffer_head *dibh;
 	int copied = 0;
 	int error;
@@ -1507,7 +1594,7 @@
 	/* 96 is max number of dirents which can be stuffed into an inode */
 	darr = kmalloc(96 * sizeof(struct gfs2_dirent *), GFP_NOFS);
 	if (darr) {
-		g.pdent = darr;
+		g.pdent = (const struct gfs2_dirent **)darr;
 		g.offset = 0;
 		dent = gfs2_dirent_scan(inode, dibh->b_data, dibh->b_size,
 					gfs2_dirent_gather, NULL, &g);
@@ -1524,8 +1611,9 @@
 			error = -EIO;
 			goto out;
 		}
+		gfs2_set_cookies(sdp, dibh, 0, darr, dip->i_entries);
 		error = do_filldir_main(dip, ctx, darr,
-					dip->i_entries, &copied);
+					dip->i_entries, 0, &copied);
 out:
 		kfree(darr);
 	}
@@ -1560,15 +1648,22 @@
 
 	dent = gfs2_dirent_search(dir, name, gfs2_dirent_find, &bh);
 	if (dent) {
+		struct inode *inode;
+		u16 rahead;
+
 		if (IS_ERR(dent))
 			return ERR_CAST(dent);
 		dtype = be16_to_cpu(dent->de_type);
+		rahead = be16_to_cpu(dent->de_rahead);
 		addr = be64_to_cpu(dent->de_inum.no_addr);
 		formal_ino = be64_to_cpu(dent->de_inum.no_formal_ino);
 		brelse(bh);
 		if (fail_on_exist)
 			return ERR_PTR(-EEXIST);
-		return gfs2_inode_lookup(dir->i_sb, dtype, addr, formal_ino, 0);
+		inode = gfs2_inode_lookup(dir->i_sb, dtype, addr, formal_ino, 0);
+		if (!IS_ERR(inode))
+			GFS2_I(inode)->i_rahead = rahead;
+		return inode;
 	}
 	return ERR_PTR(-ENOENT);
 }
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 5e42546..7412863 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -298,9 +298,9 @@
 		gfsflags &= ~GFS2_DIF_TOPDIR;
 		if (gfsflags & GFS2_DIF_INHERIT_JDATA)
 			gfsflags ^= (GFS2_DIF_JDATA | GFS2_DIF_INHERIT_JDATA);
-		return do_gfs2_set_flags(filp, gfsflags, ~0);
+		return do_gfs2_set_flags(filp, gfsflags, ~GFS2_DIF_SYSTEM);
 	}
-	return do_gfs2_set_flags(filp, gfsflags, ~GFS2_DIF_JDATA);
+	return do_gfs2_set_flags(filp, gfsflags, ~(GFS2_DIF_SYSTEM | GFS2_DIF_JDATA));
 }
 
 static long gfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
@@ -336,8 +336,8 @@
 	size_t blks = (size + sdp->sd_sb.sb_bsize - 1) >> sdp->sd_sb.sb_bsize_shift;
 	int hint = min_t(size_t, INT_MAX, blks);
 
-	if (hint > atomic_read(&ip->i_res->rs_sizehint))
-		atomic_set(&ip->i_res->rs_sizehint, hint);
+	if (hint > atomic_read(&ip->i_res.rs_sizehint))
+		atomic_set(&ip->i_res.rs_sizehint, hint);
 }
 
 /**
@@ -397,14 +397,10 @@
 	/* Update file times before taking page lock */
 	file_update_time(vma->vm_file);
 
-	ret = get_write_access(inode);
+	ret = gfs2_rsqa_alloc(ip);
 	if (ret)
 		goto out;
 
-	ret = gfs2_rs_alloc(ip);
-	if (ret)
-		goto out_write_access;
-
 	gfs2_size_hint(vma->vm_file, pos, PAGE_CACHE_SIZE);
 
 	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
@@ -486,8 +482,6 @@
 		set_page_dirty(page);
 		wait_for_stable_page(page);
 	}
-out_write_access:
-	put_write_access(inode);
 out:
 	sb_end_pagefault(inode->i_sb);
 	return block_page_mkwrite_return(ret);
@@ -623,7 +617,7 @@
 	if (!(file->f_mode & FMODE_WRITE))
 		return 0;
 
-	gfs2_rs_delete(ip, &inode->i_writecount);
+	gfs2_rsqa_delete(ip, &inode->i_writecount);
 	return 0;
 }
 
@@ -703,7 +697,7 @@
 	struct gfs2_inode *ip = GFS2_I(file_inode(file));
 	int ret;
 
-	ret = gfs2_rs_alloc(ip);
+	ret = gfs2_rsqa_alloc(ip);
 	if (ret)
 		return ret;
 
@@ -938,13 +932,14 @@
 	if (ret)
 		goto out_unlock;
 
-	ret = gfs2_rs_alloc(ip);
+	ret = gfs2_rsqa_alloc(ip);
 	if (ret)
 		goto out_putw;
 
 	ret = __gfs2_fallocate(file, mode, offset, len);
 	if (ret)
-		gfs2_rs_deltree(ip->i_res);
+		gfs2_rs_deltree(&ip->i_res);
+
 out_putw:
 	put_write_access(inode);
 out_unlock:
@@ -962,7 +957,7 @@
 	int error;
 	struct gfs2_inode *ip = GFS2_I(out->f_mapping->host);
 
-	error = gfs2_rs_alloc(ip);
+	error = gfs2_rsqa_alloc(ip);
 	if (error)
 		return (ssize_t)error;
 
@@ -1018,7 +1013,7 @@
 	struct gfs2_inode *ip = GFS2_I(file_inode(file));
 	struct gfs2_glock *gl;
 	unsigned int state;
-	int flags;
+	u16 flags;
 	int error = 0;
 	int sleeptime;
 
@@ -1032,7 +1027,10 @@
 		if (fl_gh->gh_state == state)
 			goto out;
 		locks_lock_file_wait(file,
-				     &(struct file_lock){.fl_type = F_UNLCK});
+				     &(struct file_lock) {
+					     .fl_type = F_UNLCK,
+					     .fl_flags = FL_FLOCK
+				     });
 		gfs2_glock_dq(fl_gh);
 		gfs2_holder_reinit(state, flags, fl_gh);
 	} else {
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 32e7471..a4ff7b56 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -446,7 +446,7 @@
 {
 	const struct gfs2_glock_operations *glops = gl->gl_ops;
 	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
-	unsigned int lck_flags = gh ? gh->gh_flags : 0;
+	unsigned int lck_flags = (unsigned int)(gh ? gh->gh_flags : 0);
 	int ret;
 
 	lck_flags &= (LM_FLAG_TRY | LM_FLAG_TRY_1CB | LM_FLAG_NOEXP |
@@ -750,7 +750,7 @@
  *
  */
 
-void gfs2_holder_init(struct gfs2_glock *gl, unsigned int state, unsigned flags,
+void gfs2_holder_init(struct gfs2_glock *gl, unsigned int state, u16 flags,
 		      struct gfs2_holder *gh)
 {
 	INIT_LIST_HEAD(&gh->gh_list);
@@ -774,7 +774,7 @@
  *
  */
 
-void gfs2_holder_reinit(unsigned int state, unsigned flags, struct gfs2_holder *gh)
+void gfs2_holder_reinit(unsigned int state, u16 flags, struct gfs2_holder *gh)
 {
 	gh->gh_state = state;
 	gh->gh_flags = flags;
@@ -1080,7 +1080,7 @@
 
 int gfs2_glock_nq_num(struct gfs2_sbd *sdp, u64 number,
 		      const struct gfs2_glock_operations *glops,
-		      unsigned int state, int flags, struct gfs2_holder *gh)
+		      unsigned int state, u16 flags, struct gfs2_holder *gh)
 {
 	struct gfs2_glock *gl;
 	int error;
@@ -1417,14 +1417,14 @@
 static void glock_hash_walk(glock_examiner examiner, const struct gfs2_sbd *sdp)
 {
 	struct gfs2_glock *gl;
-	struct rhash_head *pos, *next;
+	struct rhash_head *pos;
 	const struct bucket_table *tbl;
 	int i;
 
 	rcu_read_lock();
 	tbl = rht_dereference_rcu(gl_hash_table.tbl, &gl_hash_table);
 	for (i = 0; i < tbl->size; i++) {
-		rht_for_each_entry_safe(gl, pos, next, tbl, i, gl_node) {
+		rht_for_each_entry_rcu(gl, pos, tbl, i, gl_node) {
 			if ((gl->gl_name.ln_sbd == sdp) &&
 			    lockref_get_not_dead(&gl->gl_lockref))
 				examiner(gl);
@@ -1506,7 +1506,9 @@
 	flush_workqueue(glock_workqueue);
 	glock_hash_walk(clear_glock, sdp);
 	flush_workqueue(glock_workqueue);
-	wait_event(sdp->sd_glock_wait, atomic_read(&sdp->sd_glock_disposal) == 0);
+	wait_event_timeout(sdp->sd_glock_wait,
+			   atomic_read(&sdp->sd_glock_disposal) == 0,
+			   HZ * 600);
 	glock_hash_walk(dump_glock_func, sdp);
 }
 
@@ -1539,7 +1541,7 @@
 	return "??";
 }
 
-static const char *hflags2str(char *buf, unsigned flags, unsigned long iflags)
+static const char *hflags2str(char *buf, u16 flags, unsigned long iflags)
 {
 	char *p = buf;
 	if (flags & LM_FLAG_TRY)
diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h
index f7cdaa8..46ab67f 100644
--- a/fs/gfs2/glock.h
+++ b/fs/gfs2/glock.h
@@ -79,15 +79,15 @@
  * requested had acquired and released the lock.
  */
 
-#define LM_FLAG_TRY		0x00000001
-#define LM_FLAG_TRY_1CB		0x00000002
-#define LM_FLAG_NOEXP		0x00000004
-#define LM_FLAG_ANY		0x00000008
-#define LM_FLAG_PRIORITY	0x00000010
-#define GL_ASYNC		0x00000040
-#define GL_EXACT		0x00000080
-#define GL_SKIP			0x00000100
-#define GL_NOCACHE		0x00000400
+#define LM_FLAG_TRY		0x0001
+#define LM_FLAG_TRY_1CB		0x0002
+#define LM_FLAG_NOEXP		0x0004
+#define LM_FLAG_ANY		0x0008
+#define LM_FLAG_PRIORITY	0x0010
+#define GL_ASYNC		0x0040
+#define GL_EXACT		0x0080
+#define GL_SKIP			0x0100
+#define GL_NOCACHE		0x0400
   
 /*
  * lm_async_cb return flags
@@ -183,8 +183,8 @@
 			  int create, struct gfs2_glock **glp);
 extern void gfs2_glock_put(struct gfs2_glock *gl);
 extern void gfs2_holder_init(struct gfs2_glock *gl, unsigned int state,
-			     unsigned flags, struct gfs2_holder *gh);
-extern void gfs2_holder_reinit(unsigned int state, unsigned flags,
+			     u16 flags, struct gfs2_holder *gh);
+extern void gfs2_holder_reinit(unsigned int state, u16 flags,
 			       struct gfs2_holder *gh);
 extern void gfs2_holder_uninit(struct gfs2_holder *gh);
 extern int gfs2_glock_nq(struct gfs2_holder *gh);
@@ -195,7 +195,7 @@
 extern void gfs2_glock_dq_uninit(struct gfs2_holder *gh);
 extern int gfs2_glock_nq_num(struct gfs2_sbd *sdp, u64 number,
 			     const struct gfs2_glock_operations *glops,
-			     unsigned int state, int flags,
+			     unsigned int state, u16 flags,
 			     struct gfs2_holder *gh);
 extern int gfs2_glock_nq_m(unsigned int num_gh, struct gfs2_holder *ghs);
 extern void gfs2_glock_dq_m(unsigned int num_gh, struct gfs2_holder *ghs);
@@ -215,7 +215,7 @@
  */
 
 static inline int gfs2_glock_nq_init(struct gfs2_glock *gl,
-				     unsigned int state, int flags,
+				     unsigned int state, u16 flags,
 				     struct gfs2_holder *gh)
 {
 	int error;
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index de7b4f9..845fb09 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -259,8 +259,8 @@
 
 	struct gfs2_glock *gh_gl;
 	struct pid *gh_owner_pid;
-	unsigned int gh_state;
-	unsigned gh_flags;
+	u16 gh_flags;
+	u16 gh_state;
 
 	int gh_error;
 	unsigned long gh_iflags; /* HIF_... */
@@ -270,6 +270,13 @@
 /* Number of quota types we support */
 #define GFS2_MAXQUOTAS 2
 
+struct gfs2_qadata { /* quota allocation data */
+	/* Quota stuff */
+	struct gfs2_quota_data *qa_qd[2 * GFS2_MAXQUOTAS];
+	struct gfs2_holder qa_qd_ghs[2 * GFS2_MAXQUOTAS];
+	unsigned int qa_qd_num;
+};
+
 /* Resource group multi-block reservation, in order of appearance:
 
    Step 1. Function prepares to write, allocates a mb, sets the size hint.
@@ -288,11 +295,6 @@
 	struct gfs2_rbm rs_rbm;       /* Start of reservation */
 	u32 rs_free;                  /* how many blocks are still free */
 	u64 rs_inum;                  /* Inode number for reservation */
-
-	/* ancillary quota stuff */
-	struct gfs2_quota_data *rs_qa_qd[2 * GFS2_MAXQUOTAS];
-	struct gfs2_holder rs_qa_qd_ghs[2 * GFS2_MAXQUOTAS];
-	unsigned int rs_qa_qd_num;
 };
 
 /*
@@ -391,7 +393,8 @@
 	struct gfs2_glock *i_gl; /* Move into i_gh? */
 	struct gfs2_holder i_iopen_gh;
 	struct gfs2_holder i_gh; /* for prepare/commit_write only */
-	struct gfs2_blkreserv *i_res; /* rgrp multi-block reservation */
+	struct gfs2_qadata *i_qadata; /* quota allocation data */
+	struct gfs2_blkreserv i_res; /* rgrp multi-block reservation */
 	struct gfs2_rgrpd *i_rgd;
 	u64 i_goal;	/* goal block for allocations */
 	struct rw_semaphore i_rw_mutex;
@@ -402,6 +405,7 @@
 	u32 i_diskflags;
 	u8 i_height;
 	u8 i_depth;
+	u16 i_rahead;
 };
 
 /*
@@ -558,6 +562,8 @@
 	unsigned int ar_errors:2;               /* errors=withdraw | panic */
 	unsigned int ar_nobarrier:1;            /* do not send barriers */
 	unsigned int ar_rgrplvb:1;		/* use lvbs for rgrp info */
+	unsigned int ar_loccookie:1;		/* use location based readdir
+						   cookies */
 	int ar_commit;				/* Commit interval */
 	int ar_statfs_quantum;			/* The fast statfs interval */
 	int ar_quota_quantum;			/* The quota interval */
@@ -685,6 +691,7 @@
 	u64 sd_heightsize[GFS2_MAX_META_HEIGHT + 1];
 	u32 sd_max_jheight; /* Max height of journaled file's meta tree */
 	u64 sd_jheightsize[GFS2_MAX_META_HEIGHT + 1];
+	u32 sd_max_dents_per_leaf; /* Max number of dirents in a leaf block */
 
 	struct gfs2_args sd_args;	/* Mount arguments */
 	struct gfs2_tune sd_tune;	/* Filesystem tuning structure */
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 063fdfc..3e94400 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -191,13 +191,13 @@
 fail_refresh:
 	ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
 	ip->i_iopen_gh.gh_gl->gl_object = NULL;
-	gfs2_glock_dq_uninit(&ip->i_iopen_gh);
+	gfs2_glock_dq_wait(&ip->i_iopen_gh);
+	gfs2_holder_uninit(&ip->i_iopen_gh);
 fail_iopen:
 	if (io_gl)
 		gfs2_glock_put(io_gl);
 fail_put:
 	ip->i_gl->gl_object = NULL;
-	gfs2_glock_put(ip->i_gl);
 fail:
 	iget_failed(inode);
 	return ERR_PTR(error);
@@ -593,7 +593,7 @@
 	struct gfs2_inode *dip = GFS2_I(dir), *ip;
 	struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
 	struct gfs2_glock *io_gl;
-	int error, free_vfs_inode = 0;
+	int error, free_vfs_inode = 1;
 	u32 aflags = 0;
 	unsigned blocks = 1;
 	struct gfs2_diradd da = { .bh = NULL, .save_loc = 1, };
@@ -601,7 +601,7 @@
 	if (!name->len || name->len > GFS2_FNAMESIZE)
 		return -ENAMETOOLONG;
 
-	error = gfs2_rs_alloc(dip);
+	error = gfs2_rsqa_alloc(dip);
 	if (error)
 		return error;
 
@@ -650,10 +650,10 @@
 
 	error = posix_acl_create(dir, &mode, &default_acl, &acl);
 	if (error)
-		goto fail_free_vfs_inode;
+		goto fail_gunlock;
 
 	ip = GFS2_I(inode);
-	error = gfs2_rs_alloc(ip);
+	error = gfs2_rsqa_alloc(ip);
 	if (error)
 		goto fail_free_acls;
 
@@ -685,6 +685,11 @@
 		ip->i_entries = 2;
 		break;
 	}
+
+	/* Force SYSTEM flag on all files and subdirs of a SYSTEM directory */
+	if (dip->i_diskflags & GFS2_DIF_SYSTEM)
+		ip->i_diskflags |= GFS2_DIF_SYSTEM;
+
 	gfs2_set_inode_flags(inode);
 
 	if ((GFS2_I(d_inode(sdp->sd_root_dir)) == dip) ||
@@ -733,6 +738,9 @@
 	gfs2_set_iop(inode);
 	insert_inode_hash(inode);
 
+	free_vfs_inode = 0; /* After this point, the inode is no longer
+			       considered free. Any failures need to undo
+			       the gfs2 structures. */
 	if (default_acl) {
 		error = gfs2_set_acl(inode, default_acl, ACL_TYPE_DEFAULT);
 		posix_acl_release(default_acl);
@@ -766,24 +774,19 @@
 	return error;
 
 fail_gunlock3:
-	gfs2_glock_dq_uninit(ghs + 1);
-	if (ip->i_gl)
-		gfs2_glock_put(ip->i_gl);
-	goto fail_gunlock;
-
+	gfs2_glock_dq_uninit(&ip->i_iopen_gh);
+	gfs2_glock_put(io_gl);
 fail_gunlock2:
 	gfs2_glock_dq_uninit(ghs + 1);
 fail_free_inode:
 	if (ip->i_gl)
 		gfs2_glock_put(ip->i_gl);
-	gfs2_rs_delete(ip, NULL);
+	gfs2_rsqa_delete(ip, NULL);
 fail_free_acls:
 	if (default_acl)
 		posix_acl_release(default_acl);
 	if (acl)
 		posix_acl_release(acl);
-fail_free_vfs_inode:
-	free_vfs_inode = 1;
 fail_gunlock:
 	gfs2_dir_no_add(&da);
 	gfs2_glock_dq_uninit(ghs);
@@ -898,7 +901,7 @@
 	if (S_ISDIR(inode->i_mode))
 		return -EPERM;
 
-	error = gfs2_rs_alloc(dip);
+	error = gfs2_rsqa_alloc(dip);
 	if (error)
 		return error;
 
@@ -1371,7 +1374,7 @@
 	if (error)
 		return error;
 
-	error = gfs2_rs_alloc(ndip);
+	error = gfs2_rsqa_alloc(ndip);
 	if (error)
 		return error;
 
@@ -1712,24 +1715,30 @@
 }
 
 /**
- * gfs2_follow_link - Follow a symbolic link
+ * gfs2_get_link - Follow a symbolic link
  * @dentry: The dentry of the link
- * @nd: Data that we pass to vfs_follow_link()
+ * @inode: The inode of the link
+ * @done: destructor for return value
  *
  * This can handle symlinks of any size.
  *
  * Returns: 0 on success or error code
  */
 
-static const char *gfs2_follow_link(struct dentry *dentry, void **cookie)
+static const char *gfs2_get_link(struct dentry *dentry,
+				 struct inode *inode,
+				 struct delayed_call *done)
 {
-	struct gfs2_inode *ip = GFS2_I(d_inode(dentry));
+	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_holder i_gh;
 	struct buffer_head *dibh;
 	unsigned int size;
 	char *buf;
 	int error;
 
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+
 	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &i_gh);
 	error = gfs2_glock_nq(&i_gh);
 	if (error) {
@@ -1759,7 +1768,7 @@
 out:
 	gfs2_glock_dq_uninit(&i_gh);
 	if (!IS_ERR(buf))
-		*cookie = buf;
+		set_delayed_call(done, kfree_link, buf);
 	return buf;
 }
 
@@ -1854,11 +1863,7 @@
 	if (!(attr->ia_valid & ATTR_GID) || gid_eq(ogid, ngid))
 		ogid = ngid = NO_GID_QUOTA_CHANGE;
 
-	error = get_write_access(inode);
-	if (error)
-		return error;
-
-	error = gfs2_rs_alloc(ip);
+	error = gfs2_rsqa_alloc(ip);
 	if (error)
 		goto out;
 
@@ -1898,7 +1903,6 @@
 out_gunlock_q:
 	gfs2_quota_unlock(ip);
 out:
-	put_write_access(inode);
 	return error;
 }
 
@@ -1920,7 +1924,7 @@
 	struct gfs2_holder i_gh;
 	int error;
 
-	error = gfs2_rs_alloc(ip);
+	error = gfs2_rsqa_alloc(ip);
 	if (error)
 		return error;
 
@@ -2002,7 +2006,7 @@
 	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
 	ret = gfs2_glock_nq(&gh);
 	if (ret == 0) {
-		ret = gfs2_rs_alloc(ip);
+		ret = gfs2_rsqa_alloc(ip);
 		if (ret == 0)
 			ret = generic_setxattr(dentry, name, data, size, flags);
 		gfs2_glock_dq(&gh);
@@ -2043,7 +2047,7 @@
 	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
 	ret = gfs2_glock_nq(&gh);
 	if (ret == 0) {
-		ret = gfs2_rs_alloc(ip);
+		ret = gfs2_rsqa_alloc(ip);
 		if (ret == 0)
 			ret = generic_removexattr(dentry, name);
 		gfs2_glock_dq(&gh);
@@ -2132,8 +2136,7 @@
 
 const struct inode_operations gfs2_symlink_iops = {
 	.readlink = generic_readlink,
-	.follow_link = gfs2_follow_link,
-	.put_link = kfree_put_link,
+	.get_link = gfs2_get_link,
 	.permission = gfs2_permission,
 	.setattr = gfs2_setattr,
 	.getattr = gfs2_getattr,
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 536e7a6..0ff028c 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -716,6 +716,9 @@
 	}
 	trace_gfs2_log_flush(sdp, 1);
 
+	if (type == SHUTDOWN_FLUSH)
+		clear_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
+
 	sdp->sd_log_flush_head = sdp->sd_log_head;
 	sdp->sd_log_flush_wrapped = 0;
 	tr = sdp->sd_log_tr;
diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c
index fb2b42c..1d709d4 100644
--- a/fs/gfs2/main.c
+++ b/fs/gfs2/main.c
@@ -41,7 +41,9 @@
 	inode_init_once(&ip->i_inode);
 	init_rwsem(&ip->i_rw_mutex);
 	INIT_LIST_HEAD(&ip->i_trunc_list);
-	ip->i_res = NULL;
+	ip->i_qadata = NULL;
+	memset(&ip->i_res, 0, sizeof(ip->i_res));
+	RB_CLEAR_NODE(&ip->i_res.rs_node);
 	ip->i_hash_cache = NULL;
 }
 
@@ -135,10 +137,10 @@
 	if (!gfs2_quotad_cachep)
 		goto fail;
 
-	gfs2_rsrv_cachep = kmem_cache_create("gfs2_mblk",
-					     sizeof(struct gfs2_blkreserv),
+	gfs2_qadata_cachep = kmem_cache_create("gfs2_qadata",
+					       sizeof(struct gfs2_qadata),
 					       0, 0, NULL);
-	if (!gfs2_rsrv_cachep)
+	if (!gfs2_qadata_cachep)
 		goto fail;
 
 	register_shrinker(&gfs2_qd_shrinker);
@@ -193,8 +195,8 @@
 	unregister_shrinker(&gfs2_qd_shrinker);
 	gfs2_glock_exit();
 
-	if (gfs2_rsrv_cachep)
-		kmem_cache_destroy(gfs2_rsrv_cachep);
+	if (gfs2_qadata_cachep)
+		kmem_cache_destroy(gfs2_qadata_cachep);
 
 	if (gfs2_quotad_cachep)
 		kmem_cache_destroy(gfs2_quotad_cachep);
@@ -238,7 +240,7 @@
 	rcu_barrier();
 
 	mempool_destroy(gfs2_page_pool);
-	kmem_cache_destroy(gfs2_rsrv_cachep);
+	kmem_cache_destroy(gfs2_qadata_cachep);
 	kmem_cache_destroy(gfs2_quotad_cachep);
 	kmem_cache_destroy(gfs2_rgrpd_cachep);
 	kmem_cache_destroy(gfs2_bufdata_cachep);
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index 0e1d4be..e137d96 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -187,6 +187,52 @@
 	return bh;
 }
 
+static void gfs2_meta_read_endio(struct bio *bio)
+{
+	struct bio_vec *bvec;
+	int i;
+
+	bio_for_each_segment_all(bvec, bio, i) {
+		struct page *page = bvec->bv_page;
+		struct buffer_head *bh = page_buffers(page);
+		unsigned int len = bvec->bv_len;
+
+		while (bh_offset(bh) < bvec->bv_offset)
+			bh = bh->b_this_page;
+		do {
+			struct buffer_head *next = bh->b_this_page;
+			len -= bh->b_size;
+			bh->b_end_io(bh, !bio->bi_error);
+			bh = next;
+		} while (bh && len);
+	}
+	bio_put(bio);
+}
+
+/*
+ * Submit several consecutive buffer head I/O requests as a single bio I/O
+ * request.  (See submit_bh_wbc.)
+ */
+static void gfs2_submit_bhs(int rw, struct buffer_head *bhs[], int num)
+{
+	struct buffer_head *bh = bhs[0];
+	struct bio *bio;
+	int i;
+
+	if (!num)
+		return;
+
+	bio = bio_alloc(GFP_NOIO, num);
+	bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
+	bio->bi_bdev = bh->b_bdev;
+	for (i = 0; i < num; i++) {
+		bh = bhs[i];
+		bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh));
+	}
+	bio->bi_end_io = gfs2_meta_read_endio;
+	submit_bio(rw, bio);
+}
+
 /**
  * gfs2_meta_read - Read a block from disk
  * @gl: The glock covering the block
@@ -198,10 +244,11 @@
  */
 
 int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
-		   struct buffer_head **bhp)
+		   int rahead, struct buffer_head **bhp)
 {
 	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
-	struct buffer_head *bh;
+	struct buffer_head *bh, *bhs[2];
+	int num = 0;
 
 	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) {
 		*bhp = NULL;
@@ -213,14 +260,31 @@
 	lock_buffer(bh);
 	if (buffer_uptodate(bh)) {
 		unlock_buffer(bh);
-		return 0;
+		flags &= ~DIO_WAIT;
+	} else {
+		bh->b_end_io = end_buffer_read_sync;
+		get_bh(bh);
+		bhs[num++] = bh;
 	}
-	bh->b_end_io = end_buffer_read_sync;
-	get_bh(bh);
-	submit_bh(READ_SYNC | REQ_META | REQ_PRIO, bh);
+
+	if (rahead) {
+		bh = gfs2_getbuf(gl, blkno + 1, CREATE);
+
+		lock_buffer(bh);
+		if (buffer_uptodate(bh)) {
+			unlock_buffer(bh);
+			brelse(bh);
+		} else {
+			bh->b_end_io = end_buffer_read_sync;
+			bhs[num++] = bh;
+		}
+	}
+
+	gfs2_submit_bhs(READ_SYNC | REQ_META | REQ_PRIO, bhs, num);
 	if (!(flags & DIO_WAIT))
 		return 0;
 
+	bh = *bhp;
 	wait_on_buffer(bh);
 	if (unlikely(!buffer_uptodate(bh))) {
 		struct gfs2_trans *tr = current->journal_info;
@@ -341,8 +405,12 @@
 	struct buffer_head *bh;
 	int ret = 0;
 	u32 mtype = height ? GFS2_METATYPE_IN : GFS2_METATYPE_DI;
+	int rahead = 0;
 
-	ret = gfs2_meta_read(gl, num, DIO_WAIT, &bh);
+	if (num == ip->i_no_addr)
+		rahead = ip->i_rahead;
+
+	ret = gfs2_meta_read(gl, num, DIO_WAIT, rahead, &bh);
 	if (ret == 0 && gfs2_metatype_check(sdp, bh, mtype)) {
 		brelse(bh);
 		ret = -EIO;
diff --git a/fs/gfs2/meta_io.h b/fs/gfs2/meta_io.h
index 8ca1615..c5086c8 100644
--- a/fs/gfs2/meta_io.h
+++ b/fs/gfs2/meta_io.h
@@ -53,7 +53,7 @@
 
 extern struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno);
 extern int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
-			  struct buffer_head **bhp);
+			  int rahead, struct buffer_head **bhp);
 extern int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh);
 extern struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno,
 				       int create);
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index baab99b..dbed9e2 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -352,6 +352,9 @@
 	sdp->sd_jheightsize[x] = ~0;
 	gfs2_assert(sdp, sdp->sd_max_jheight <= GFS2_MAX_META_HEIGHT);
 
+	sdp->sd_max_dents_per_leaf = (sdp->sd_sb.sb_bsize -
+				      sizeof(struct gfs2_leaf)) /
+				     GFS2_MIN_DIRENT_SIZE;
 	return 0;
 }
 
@@ -910,8 +913,7 @@
 fail_ut_i:
 	iput(sdp->sd_sc_inode);
 fail:
-	if (pn)
-		iput(pn);
+	iput(pn);
 	return error;
 }
 
@@ -1315,9 +1317,7 @@
 		if ((flags ^ s->s_flags) & MS_RDONLY)
 			goto error_super;
 	} else {
-		char b[BDEVNAME_SIZE];
-
-		strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id));
+		snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev);
 		sb_set_blocksize(s, block_size(bdev));
 		error = fill_super(s, &args, flags & MS_SILENT ? 1 : 0);
 		if (error)
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 3a31226..be6d9c4 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -388,7 +388,7 @@
 	error = gfs2_block_map(&ip->i_inode, block, &bh_map, 0);
 	if (error)
 		goto fail;
-	error = gfs2_meta_read(ip->i_gl, bh_map.b_blocknr, DIO_WAIT, &bh);
+	error = gfs2_meta_read(ip->i_gl, bh_map.b_blocknr, DIO_WAIT, 0, &bh);
 	if (error)
 		goto fail;
 	error = -EIO;
@@ -527,37 +527,70 @@
 	qd_put(qd);
 }
 
+/**
+ * gfs2_qa_alloc - make sure we have a quota allocations data structure,
+ *                 if necessary
+ * @ip: the inode for this reservation
+ */
+int gfs2_qa_alloc(struct gfs2_inode *ip)
+{
+	int error = 0;
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+
+	if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF)
+		return 0;
+
+	down_write(&ip->i_rw_mutex);
+	if (ip->i_qadata == NULL) {
+		ip->i_qadata = kmem_cache_zalloc(gfs2_qadata_cachep, GFP_NOFS);
+		if (!ip->i_qadata)
+			error = -ENOMEM;
+	}
+	up_write(&ip->i_rw_mutex);
+	return error;
+}
+
+void gfs2_qa_delete(struct gfs2_inode *ip, atomic_t *wcount)
+{
+	down_write(&ip->i_rw_mutex);
+	if (ip->i_qadata && ((wcount == NULL) || (atomic_read(wcount) <= 1))) {
+		kmem_cache_free(gfs2_qadata_cachep, ip->i_qadata);
+		ip->i_qadata = NULL;
+	}
+	up_write(&ip->i_rw_mutex);
+}
+
 int gfs2_quota_hold(struct gfs2_inode *ip, kuid_t uid, kgid_t gid)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct gfs2_quota_data **qd;
 	int error;
 
-	if (ip->i_res == NULL) {
-		error = gfs2_rs_alloc(ip);
+	if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF)
+		return 0;
+
+	if (ip->i_qadata == NULL) {
+		error = gfs2_rsqa_alloc(ip);
 		if (error)
 			return error;
 	}
 
-	qd = ip->i_res->rs_qa_qd;
+	qd = ip->i_qadata->qa_qd;
 
-	if (gfs2_assert_warn(sdp, !ip->i_res->rs_qa_qd_num) ||
+	if (gfs2_assert_warn(sdp, !ip->i_qadata->qa_qd_num) ||
 	    gfs2_assert_warn(sdp, !test_bit(GIF_QD_LOCKED, &ip->i_flags)))
 		return -EIO;
 
-	if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF)
-		return 0;
-
 	error = qdsb_get(sdp, make_kqid_uid(ip->i_inode.i_uid), qd);
 	if (error)
 		goto out;
-	ip->i_res->rs_qa_qd_num++;
+	ip->i_qadata->qa_qd_num++;
 	qd++;
 
 	error = qdsb_get(sdp, make_kqid_gid(ip->i_inode.i_gid), qd);
 	if (error)
 		goto out;
-	ip->i_res->rs_qa_qd_num++;
+	ip->i_qadata->qa_qd_num++;
 	qd++;
 
 	if (!uid_eq(uid, NO_UID_QUOTA_CHANGE) &&
@@ -565,7 +598,7 @@
 		error = qdsb_get(sdp, make_kqid_uid(uid), qd);
 		if (error)
 			goto out;
-		ip->i_res->rs_qa_qd_num++;
+		ip->i_qadata->qa_qd_num++;
 		qd++;
 	}
 
@@ -574,7 +607,7 @@
 		error = qdsb_get(sdp, make_kqid_gid(gid), qd);
 		if (error)
 			goto out;
-		ip->i_res->rs_qa_qd_num++;
+		ip->i_qadata->qa_qd_num++;
 		qd++;
 	}
 
@@ -587,17 +620,17 @@
 void gfs2_quota_unhold(struct gfs2_inode *ip)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
-	unsigned int x;
+	u32 x;
 
-	if (ip->i_res == NULL)
+	if (ip->i_qadata == NULL)
 		return;
 	gfs2_assert_warn(sdp, !test_bit(GIF_QD_LOCKED, &ip->i_flags));
 
-	for (x = 0; x < ip->i_res->rs_qa_qd_num; x++) {
-		qdsb_put(ip->i_res->rs_qa_qd[x]);
-		ip->i_res->rs_qa_qd[x] = NULL;
+	for (x = 0; x < ip->i_qadata->qa_qd_num; x++) {
+		qdsb_put(ip->i_qadata->qa_qd[x]);
+		ip->i_qadata->qa_qd[x] = NULL;
 	}
-	ip->i_res->rs_qa_qd_num = 0;
+	ip->i_qadata->qa_qd_num = 0;
 }
 
 static int sort_qd(const void *a, const void *b)
@@ -843,7 +876,7 @@
 	unsigned int nalloc = 0, blocks;
 	int error;
 
-	error = gfs2_rs_alloc(ip);
+	error = gfs2_rsqa_alloc(ip);
 	if (error)
 		return error;
 
@@ -1003,23 +1036,23 @@
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct gfs2_quota_data *qd;
-	unsigned int x;
+	u32 x;
 	int error = 0;
 
-	error = gfs2_quota_hold(ip, uid, gid);
-	if (error)
-		return error;
-
 	if (capable(CAP_SYS_RESOURCE) ||
 	    sdp->sd_args.ar_quota != GFS2_QUOTA_ON)
 		return 0;
 
-	sort(ip->i_res->rs_qa_qd, ip->i_res->rs_qa_qd_num,
+	error = gfs2_quota_hold(ip, uid, gid);
+	if (error)
+		return error;
+
+	sort(ip->i_qadata->qa_qd, ip->i_qadata->qa_qd_num,
 	     sizeof(struct gfs2_quota_data *), sort_qd, NULL);
 
-	for (x = 0; x < ip->i_res->rs_qa_qd_num; x++) {
-		qd = ip->i_res->rs_qa_qd[x];
-		error = do_glock(qd, NO_FORCE, &ip->i_res->rs_qa_qd_ghs[x]);
+	for (x = 0; x < ip->i_qadata->qa_qd_num; x++) {
+		qd = ip->i_qadata->qa_qd[x];
+		error = do_glock(qd, NO_FORCE, &ip->i_qadata->qa_qd_ghs[x]);
 		if (error)
 			break;
 	}
@@ -1028,7 +1061,7 @@
 		set_bit(GIF_QD_LOCKED, &ip->i_flags);
 	else {
 		while (x--)
-			gfs2_glock_dq_uninit(&ip->i_res->rs_qa_qd_ghs[x]);
+			gfs2_glock_dq_uninit(&ip->i_qadata->qa_qd_ghs[x]);
 		gfs2_quota_unhold(ip);
 	}
 
@@ -1076,20 +1109,20 @@
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct gfs2_quota_data *qda[4];
 	unsigned int count = 0;
-	unsigned int x;
+	u32 x;
 	int found;
 
 	if (!test_and_clear_bit(GIF_QD_LOCKED, &ip->i_flags))
 		goto out;
 
-	for (x = 0; x < ip->i_res->rs_qa_qd_num; x++) {
+	for (x = 0; x < ip->i_qadata->qa_qd_num; x++) {
 		struct gfs2_quota_data *qd;
 		int sync;
 
-		qd = ip->i_res->rs_qa_qd[x];
+		qd = ip->i_qadata->qa_qd[x];
 		sync = need_sync(qd);
 
-		gfs2_glock_dq_uninit(&ip->i_res->rs_qa_qd_ghs[x]);
+		gfs2_glock_dq_uninit(&ip->i_qadata->qa_qd_ghs[x]);
 		if (!sync)
 			continue;
 
@@ -1158,7 +1191,7 @@
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct gfs2_quota_data *qd;
 	s64 value, warn, limit;
-	unsigned int x;
+	u32 x;
 	int error = 0;
 
 	ap->allowed = UINT_MAX; /* Assume we are permitted a whole lot */
@@ -1168,8 +1201,8 @@
         if (sdp->sd_args.ar_quota != GFS2_QUOTA_ON)
                 return 0;
 
-	for (x = 0; x < ip->i_res->rs_qa_qd_num; x++) {
-		qd = ip->i_res->rs_qa_qd[x];
+	for (x = 0; x < ip->i_qadata->qa_qd_num; x++) {
+		qd = ip->i_qadata->qa_qd[x];
 
 		if (!(qid_eq(qd->qd_id, make_kqid_uid(uid)) ||
 		      qid_eq(qd->qd_id, make_kqid_gid(gid))))
@@ -1216,15 +1249,17 @@
 		       kuid_t uid, kgid_t gid)
 {
 	struct gfs2_quota_data *qd;
-	unsigned int x;
+	u32 x;
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 
-	if (gfs2_assert_warn(GFS2_SB(&ip->i_inode), change))
+	if (sdp->sd_args.ar_quota != GFS2_QUOTA_ON ||
+	    gfs2_assert_warn(sdp, change))
 		return;
 	if (ip->i_diskflags & GFS2_DIF_SYSTEM)
 		return;
 
-	for (x = 0; x < ip->i_res->rs_qa_qd_num; x++) {
-		qd = ip->i_res->rs_qa_qd[x];
+	for (x = 0; x < ip->i_qadata->qa_qd_num; x++) {
+		qd = ip->i_qadata->qa_qd[x];
 
 		if (qid_eq(qd->qd_id, make_kqid_uid(uid)) ||
 		    qid_eq(qd->qd_id, make_kqid_gid(gid))) {
@@ -1635,7 +1670,7 @@
 	if (error)
 		return error;
 
-	error = gfs2_rs_alloc(ip);
+	error = gfs2_rsqa_alloc(ip);
 	if (error)
 		goto out_put;
 
diff --git a/fs/gfs2/quota.h b/fs/gfs2/quota.h
index ad04b3ac..5e47c93 100644
--- a/fs/gfs2/quota.h
+++ b/fs/gfs2/quota.h
@@ -18,6 +18,8 @@
 #define NO_UID_QUOTA_CHANGE INVALID_UID
 #define NO_GID_QUOTA_CHANGE INVALID_GID
 
+extern int gfs2_qa_alloc(struct gfs2_inode *ip);
+extern void gfs2_qa_delete(struct gfs2_inode *ip, atomic_t *wcount);
 extern int gfs2_quota_hold(struct gfs2_inode *ip, kuid_t uid, kgid_t gid);
 extern void gfs2_quota_unhold(struct gfs2_inode *ip);
 
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index c134c04..07c0265 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -596,27 +596,13 @@
 }
 
 /**
- * gfs2_rs_alloc - make sure we have a reservation assigned to the inode
+ * gfs2_rsqa_alloc - make sure we have a reservation assigned to the inode
+ *                 plus a quota allocations data structure, if necessary
  * @ip: the inode for this reservation
  */
-int gfs2_rs_alloc(struct gfs2_inode *ip)
+int gfs2_rsqa_alloc(struct gfs2_inode *ip)
 {
-	int error = 0;
-
-	down_write(&ip->i_rw_mutex);
-	if (ip->i_res)
-		goto out;
-
-	ip->i_res = kmem_cache_zalloc(gfs2_rsrv_cachep, GFP_NOFS);
-	if (!ip->i_res) {
-		error = -ENOMEM;
-		goto out;
-	}
-
-	RB_CLEAR_NODE(&ip->i_res->rs_node);
-out:
-	up_write(&ip->i_rw_mutex);
-	return error;
+	return gfs2_qa_alloc(ip);
 }
 
 static void dump_rs(struct seq_file *seq, const struct gfs2_blkreserv *rs)
@@ -678,21 +664,20 @@
 }
 
 /**
- * gfs2_rs_delete - delete a multi-block reservation
+ * gfs2_rsqa_delete - delete a multi-block reservation and quota allocation
  * @ip: The inode for this reservation
  * @wcount: The inode's write count, or NULL
  *
  */
-void gfs2_rs_delete(struct gfs2_inode *ip, atomic_t *wcount)
+void gfs2_rsqa_delete(struct gfs2_inode *ip, atomic_t *wcount)
 {
 	down_write(&ip->i_rw_mutex);
-	if (ip->i_res && ((wcount == NULL) || (atomic_read(wcount) <= 1))) {
-		gfs2_rs_deltree(ip->i_res);
-		BUG_ON(ip->i_res->rs_free);
-		kmem_cache_free(gfs2_rsrv_cachep, ip->i_res);
-		ip->i_res = NULL;
+	if ((wcount == NULL) || (atomic_read(wcount) <= 1)) {
+		gfs2_rs_deltree(&ip->i_res);
+		BUG_ON(ip->i_res.rs_free);
 	}
 	up_write(&ip->i_rw_mutex);
+	gfs2_qa_delete(ip, wcount);
 }
 
 /**
@@ -1158,7 +1143,7 @@
 
 	for (x = 0; x < length; x++) {
 		bi = rgd->rd_bits + x;
-		error = gfs2_meta_read(gl, rgd->rd_addr + x, 0, &bi->bi_bh);
+		error = gfs2_meta_read(gl, rgd->rd_addr + x, 0, 0, &bi->bi_bh);
 		if (error)
 			goto fail;
 	}
@@ -1456,7 +1441,7 @@
 {
 	struct rb_node **newn, *parent = NULL;
 	int rc;
-	struct gfs2_blkreserv *rs = ip->i_res;
+	struct gfs2_blkreserv *rs = &ip->i_res;
 	struct gfs2_rgrpd *rgd = rs->rs_rbm.rgd;
 	u64 fsblock = gfs2_rbm_to_block(&rs->rs_rbm);
 
@@ -1503,7 +1488,7 @@
 {
 	struct gfs2_rbm rbm = { .rgd = rgd, };
 	u64 goal;
-	struct gfs2_blkreserv *rs = ip->i_res;
+	struct gfs2_blkreserv *rs = &ip->i_res;
 	u32 extlen;
 	u32 free_blocks = rgd->rd_free_clone - rgd->rd_reserved;
 	int ret;
@@ -1574,7 +1559,7 @@
 	}
 
 	if (n) {
-		while ((rs_cmp(block, length, rs) == 0) && (ip->i_res != rs)) {
+		while ((rs_cmp(block, length, rs) == 0) && (&ip->i_res != rs)) {
 			block = gfs2_rbm_to_block(&rs->rs_rbm) + rs->rs_free;
 			n = n->rb_right;
 			if (n == NULL)
@@ -1804,7 +1789,7 @@
 			continue;
 		*last_unlinked = block;
 
-		error = gfs2_glock_get(sdp, block, &gfs2_inode_glops, CREATE, &gl);
+		error = gfs2_glock_get(sdp, block, &gfs2_iopen_glops, CREATE, &gl);
 		if (error)
 			continue;
 
@@ -1984,7 +1969,7 @@
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct gfs2_rgrpd *begin = NULL;
-	struct gfs2_blkreserv *rs = ip->i_res;
+	struct gfs2_blkreserv *rs = &ip->i_res;
 	int error = 0, rg_locked, flags = 0;
 	u64 last_unlinked = NO_BLOCK;
 	int loops = 0;
@@ -2113,7 +2098,7 @@
 
 void gfs2_inplace_release(struct gfs2_inode *ip)
 {
-	struct gfs2_blkreserv *rs = ip->i_res;
+	struct gfs2_blkreserv *rs = &ip->i_res;
 
 	if (rs->rs_rgd_gh.gh_gl)
 		gfs2_glock_dq_uninit(&rs->rs_rgd_gh);
@@ -2267,7 +2252,7 @@
 static void gfs2_adjust_reservation(struct gfs2_inode *ip,
 				    const struct gfs2_rbm *rbm, unsigned len)
 {
-	struct gfs2_blkreserv *rs = ip->i_res;
+	struct gfs2_blkreserv *rs = &ip->i_res;
 	struct gfs2_rgrpd *rgd = rbm->rgd;
 	unsigned rlen;
 	u64 block;
@@ -2310,8 +2295,8 @@
 {
 	u64 goal;
 
-	if (gfs2_rs_active(ip->i_res)) {
-		*rbm = ip->i_res->rs_rbm;
+	if (gfs2_rs_active(&ip->i_res)) {
+		*rbm = ip->i_res.rs_rbm;
 		return;
 	}
 
@@ -2365,7 +2350,7 @@
 	gfs2_alloc_extent(&rbm, dinode, nblocks);
 	block = gfs2_rbm_to_block(&rbm);
 	rbm.rgd->rd_last_alloc = block - rbm.rgd->rd_data0;
-	if (gfs2_rs_active(ip->i_res))
+	if (gfs2_rs_active(&ip->i_res))
 		gfs2_adjust_reservation(ip, &rbm, *nblocks);
 	ndata = *nblocks;
 	if (dinode)
diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h
index c0ab33f..66b51cf 100644
--- a/fs/gfs2/rgrp.h
+++ b/fs/gfs2/rgrp.h
@@ -49,9 +49,9 @@
 extern int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *n,
 			     bool dinode, u64 *generation);
 
-extern int gfs2_rs_alloc(struct gfs2_inode *ip);
+extern int gfs2_rsqa_alloc(struct gfs2_inode *ip);
 extern void gfs2_rs_deltree(struct gfs2_blkreserv *rs);
-extern void gfs2_rs_delete(struct gfs2_inode *ip, atomic_t *wcount);
+extern void gfs2_rsqa_delete(struct gfs2_inode *ip, atomic_t *wcount);
 extern void __gfs2_free_blocks(struct gfs2_inode *ip, u64 bstart, u32 blen, int meta);
 extern void gfs2_free_meta(struct gfs2_inode *ip, u64 bstart, u32 blen);
 extern void gfs2_free_di(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip);
@@ -78,7 +78,7 @@
 extern int gfs2_fitrim(struct file *filp, void __user *argp);
 
 /* This is how to tell if a reservation is in the rgrp tree: */
-static inline bool gfs2_rs_active(struct gfs2_blkreserv *rs)
+static inline bool gfs2_rs_active(const struct gfs2_blkreserv *rs)
 {
 	return rs && !RB_EMPTY_NODE(&rs->rs_node);
 }
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 894fb01..8f960a5 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -83,6 +83,8 @@
 	Opt_nobarrier,
 	Opt_rgrplvb,
 	Opt_norgrplvb,
+	Opt_loccookie,
+	Opt_noloccookie,
 	Opt_error,
 };
 
@@ -122,6 +124,8 @@
 	{Opt_nobarrier, "nobarrier"},
 	{Opt_rgrplvb, "rgrplvb"},
 	{Opt_norgrplvb, "norgrplvb"},
+	{Opt_loccookie, "loccookie"},
+	{Opt_noloccookie, "noloccookie"},
 	{Opt_error, NULL}
 };
 
@@ -278,6 +282,12 @@
 		case Opt_norgrplvb:
 			args->ar_rgrplvb = 0;
 			break;
+		case Opt_loccookie:
+			args->ar_loccookie = 1;
+			break;
+		case Opt_noloccookie:
+			args->ar_loccookie = 0;
+			break;
 		case Opt_error:
 		default:
 			pr_warn("invalid mount option: %s\n", o);
@@ -556,6 +566,7 @@
 	struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
 
 	gfs2_trans_add_meta(l_ip->i_gl, l_bh);
+	gfs2_trans_add_meta(m_ip->i_gl, m_bh);
 
 	spin_lock(&sdp->sd_statfs_spin);
 	m_sc->sc_total += l_sc->sc_total;
@@ -564,10 +575,8 @@
 	memset(l_sc, 0, sizeof(struct gfs2_statfs_change));
 	memset(l_bh->b_data + sizeof(struct gfs2_dinode),
 	       0, sizeof(struct gfs2_statfs_change));
-	spin_unlock(&sdp->sd_statfs_spin);
-
-	gfs2_trans_add_meta(m_ip->i_gl, m_bh);
 	gfs2_statfs_change_out(m_sc, m_bh->b_data + sizeof(struct gfs2_dinode));
+	spin_unlock(&sdp->sd_statfs_spin);
 }
 
 int gfs2_statfs_sync(struct super_block *sb, int type)
@@ -842,10 +851,6 @@
 	gfs2_quota_sync(sdp->sd_vfs, 0);
 	gfs2_statfs_sync(sdp->sd_vfs, 0);
 
-	down_write(&sdp->sd_log_flush_lock);
-	clear_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
-	up_write(&sdp->sd_log_flush_lock);
-
 	gfs2_log_flush(sdp, NULL, SHUTDOWN_FLUSH);
 	wait_event(sdp->sd_reserving_log_wait, atomic_read(&sdp->sd_reserving_log) == 0);
 	gfs2_assert_warn(sdp, atomic_read(&sdp->sd_log_blks_free) == sdp->sd_jdesc->jd_blocks);
@@ -1419,6 +1424,8 @@
 		seq_puts(s, ",demote_interface_used");
 	if (args->ar_rgrplvb)
 		seq_puts(s, ",rgrplvb");
+	if (args->ar_loccookie)
+		seq_puts(s, ",loccookie");
 	return 0;
 }
 
@@ -1512,6 +1519,7 @@
 	struct gfs2_sbd *sdp = sb->s_fs_info;
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_holder gh;
+	struct address_space *metamapping;
 	int error;
 
 	if (test_bit(GIF_FREE_VFS_INODE, &ip->i_flags)) {
@@ -1526,7 +1534,8 @@
 	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, &gh);
 	if (unlikely(error)) {
 		ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
-		gfs2_glock_dq_uninit(&ip->i_iopen_gh);
+		gfs2_glock_dq_wait(&ip->i_iopen_gh);
+		gfs2_holder_uninit(&ip->i_iopen_gh);
 		goto out;
 	}
 
@@ -1575,8 +1584,8 @@
 
 out_truncate:
 	gfs2_log_flush(sdp, ip->i_gl, NORMAL_FLUSH);
+	metamapping = gfs2_glock2aspace(ip->i_gl);
 	if (test_bit(GLF_DIRTY, &ip->i_gl->gl_flags)) {
-		struct address_space *metamapping = gfs2_glock2aspace(ip->i_gl);
 		filemap_fdatawrite(metamapping);
 		filemap_fdatawait(metamapping);
 	}
@@ -1589,16 +1598,17 @@
 		goto out_unlock;
 	/* Needs to be done before glock release & also in a transaction */
 	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages(metamapping, 0);
 	gfs2_trans_end(sdp);
 
 out_unlock:
 	/* Error path for case 1 */
-	if (gfs2_rs_active(ip->i_res))
-		gfs2_rs_deltree(ip->i_res);
+	if (gfs2_rs_active(&ip->i_res))
+		gfs2_rs_deltree(&ip->i_res);
 
 	if (test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags)) {
 		ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
-		gfs2_glock_dq(&ip->i_iopen_gh);
+		gfs2_glock_dq_wait(&ip->i_iopen_gh);
 	}
 	gfs2_holder_uninit(&ip->i_iopen_gh);
 	gfs2_glock_dq_uninit(&gh);
@@ -1607,7 +1617,7 @@
 out:
 	/* Case 3 starts here */
 	truncate_inode_pages_final(&inode->i_data);
-	gfs2_rs_delete(ip, NULL);
+	gfs2_rsqa_delete(ip, NULL);
 	gfs2_ordered_del_inode(ip);
 	clear_inode(inode);
 	gfs2_dir_hash_inval(ip);
@@ -1619,7 +1629,8 @@
 	if (ip->i_iopen_gh.gh_gl) {
 		ip->i_iopen_gh.gh_gl->gl_object = NULL;
 		ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
-		gfs2_glock_dq_uninit(&ip->i_iopen_gh);
+		gfs2_glock_dq_wait(&ip->i_iopen_gh);
+		gfs2_holder_uninit(&ip->i_iopen_gh);
 	}
 }
 
@@ -1632,7 +1643,9 @@
 		ip->i_flags = 0;
 		ip->i_gl = NULL;
 		ip->i_rgd = NULL;
-		ip->i_res = NULL;
+		memset(&ip->i_res, 0, sizeof(ip->i_res));
+		RB_CLEAR_NODE(&ip->i_res.rs_node);
+		ip->i_rahead = 0;
 	}
 	return &ip->i_inode;
 }
diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c
index 86d2035..cf64583 100644
--- a/fs/gfs2/util.c
+++ b/fs/gfs2/util.c
@@ -27,7 +27,7 @@
 struct kmem_cache *gfs2_bufdata_cachep __read_mostly;
 struct kmem_cache *gfs2_rgrpd_cachep __read_mostly;
 struct kmem_cache *gfs2_quotad_cachep __read_mostly;
-struct kmem_cache *gfs2_rsrv_cachep __read_mostly;
+struct kmem_cache *gfs2_qadata_cachep __read_mostly;
 mempool_t *gfs2_page_pool __read_mostly;
 
 void gfs2_assert_i(struct gfs2_sbd *sdp)
diff --git a/fs/gfs2/util.h b/fs/gfs2/util.h
index cbdcbdf..c81295f 100644
--- a/fs/gfs2/util.h
+++ b/fs/gfs2/util.h
@@ -149,7 +149,7 @@
 extern struct kmem_cache *gfs2_bufdata_cachep;
 extern struct kmem_cache *gfs2_rgrpd_cachep;
 extern struct kmem_cache *gfs2_quotad_cachep;
-extern struct kmem_cache *gfs2_rsrv_cachep;
+extern struct kmem_cache *gfs2_qadata_cachep;
 extern mempool_t *gfs2_page_pool;
 
 static inline unsigned int gfs2_tune_get_i(struct gfs2_tune *gt,
diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c
index 53ce76a..e8dfb47 100644
--- a/fs/gfs2/xattr.c
+++ b/fs/gfs2/xattr.c
@@ -119,7 +119,7 @@
 	__be64 *eablk, *end;
 	int error;
 
-	error = gfs2_meta_read(ip->i_gl, ip->i_eattr, DIO_WAIT, &bh);
+	error = gfs2_meta_read(ip->i_gl, ip->i_eattr, DIO_WAIT, 0, &bh);
 	if (error)
 		return error;
 
@@ -143,7 +143,7 @@
 			break;
 		bn = be64_to_cpu(*eablk);
 
-		error = gfs2_meta_read(ip->i_gl, bn, DIO_WAIT, &eabh);
+		error = gfs2_meta_read(ip->i_gl, bn, DIO_WAIT, 0, &eabh);
 		if (error)
 			break;
 		error = ea_foreach_i(ip, eabh, ea_call, data);
@@ -477,7 +477,7 @@
 		return -ENOMEM;
 
 	for (x = 0; x < nptrs; x++) {
-		error = gfs2_meta_read(ip->i_gl, be64_to_cpu(*dataptrs), 0,
+		error = gfs2_meta_read(ip->i_gl, be64_to_cpu(*dataptrs), 0, 0,
 				       bh + x);
 		if (error) {
 			while (x--)
@@ -979,7 +979,7 @@
 	if (ip->i_diskflags & GFS2_DIF_EA_INDIRECT) {
 		__be64 *end;
 
-		error = gfs2_meta_read(ip->i_gl, ip->i_eattr, DIO_WAIT,
+		error = gfs2_meta_read(ip->i_gl, ip->i_eattr, DIO_WAIT, 0,
 				       &indbh);
 		if (error)
 			return error;
@@ -1237,56 +1237,6 @@
 				size, flags, handler->flags);
 }
 
-
-static int ea_acl_chmod_unstuffed(struct gfs2_inode *ip,
-				  struct gfs2_ea_header *ea, char *data)
-{
-	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
-	unsigned int amount = GFS2_EA_DATA_LEN(ea);
-	unsigned int nptrs = DIV_ROUND_UP(amount, sdp->sd_jbsize);
-	int ret;
-
-	ret = gfs2_trans_begin(sdp, nptrs + RES_DINODE, 0);
-	if (ret)
-		return ret;
-
-	ret = gfs2_iter_unstuffed(ip, ea, data, NULL);
-	gfs2_trans_end(sdp);
-
-	return ret;
-}
-
-int gfs2_xattr_acl_chmod(struct gfs2_inode *ip, struct iattr *attr, char *data)
-{
-	struct inode *inode = &ip->i_inode;
-	struct gfs2_sbd *sdp = GFS2_SB(inode);
-	struct gfs2_ea_location el;
-	int error;
-
-	error = gfs2_ea_find(ip, GFS2_EATYPE_SYS, GFS2_POSIX_ACL_ACCESS, &el);
-	if (error)
-		return error;
-
-	if (GFS2_EA_IS_STUFFED(el.el_ea)) {
-		error = gfs2_trans_begin(sdp, RES_DINODE + RES_EATTR, 0);
-		if (error == 0) {
-			gfs2_trans_add_meta(ip->i_gl, el.el_bh);
-			memcpy(GFS2_EA2DATA(el.el_ea), data,
-			       GFS2_EA_DATA_LEN(el.el_ea));
-		}
-	} else {
-		error = ea_acl_chmod_unstuffed(ip, el.el_ea, data);
-	}
-
-	brelse(el.el_bh);
-	if (error)
-		return error;
-
-	error = gfs2_setattr_simple(inode, attr);
-	gfs2_trans_end(sdp);
-	return error;
-}
-
 static int ea_dealloc_indirect(struct gfs2_inode *ip)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
@@ -1306,7 +1256,7 @@
 
 	memset(&rlist, 0, sizeof(struct gfs2_rgrp_list));
 
-	error = gfs2_meta_read(ip->i_gl, ip->i_eattr, DIO_WAIT, &indbh);
+	error = gfs2_meta_read(ip->i_gl, ip->i_eattr, DIO_WAIT, 0, &indbh);
 	if (error)
 		return error;
 
diff --git a/fs/gfs2/xattr.h b/fs/gfs2/xattr.h
index d392f83..2d887c8 100644
--- a/fs/gfs2/xattr.h
+++ b/fs/gfs2/xattr.h
@@ -62,6 +62,5 @@
 /* Exported to acl.c */
 
 extern int gfs2_xattr_acl_get(struct gfs2_inode *ip, const char *name, char **data);
-extern int gfs2_xattr_acl_chmod(struct gfs2_inode *ip, struct iattr *attr, char *data);
 
 #endif /* __EATTR_DOT_H__ */
diff --git a/fs/hfs/mdb.c b/fs/hfs/mdb.c
index aa3f0d6..a3ec3ae7 100644
--- a/fs/hfs/mdb.c
+++ b/fs/hfs/mdb.c
@@ -166,7 +166,7 @@
 		pr_warn("continuing without an alternate MDB\n");
 	}
 
-	HFS_SB(sb)->bitmap = (__be32 *)__get_free_pages(GFP_KERNEL, PAGE_SIZE < 8192 ? 1 : 0);
+	HFS_SB(sb)->bitmap = kmalloc(8192, GFP_KERNEL);
 	if (!HFS_SB(sb)->bitmap)
 		goto out;
 
@@ -360,7 +360,7 @@
 	unload_nls(HFS_SB(sb)->nls_io);
 	unload_nls(HFS_SB(sb)->nls_disk);
 
-	free_pages((unsigned long)HFS_SB(sb)->bitmap, PAGE_SIZE < 8192 ? 1 : 0);
+	kfree(HFS_SB(sb)->bitmap);
 	kfree(HFS_SB(sb));
 	sb->s_fs_info = NULL;
 }
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index 6dd107d..19b33f8 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -403,6 +403,7 @@
 	} else if (S_ISLNK(inode->i_mode)) {
 		sbi->file_count++;
 		inode->i_op = &page_symlink_inode_operations;
+		inode_nohighmem(inode);
 		inode->i_mapping->a_ops = &hfsplus_aops;
 		hip->clump_blocks = 1;
 	} else
@@ -526,6 +527,7 @@
 			inode->i_mapping->a_ops = &hfsplus_aops;
 		} else if (S_ISLNK(inode->i_mode)) {
 			inode->i_op = &page_symlink_inode_operations;
+			inode_nohighmem(inode);
 			inode->i_mapping->a_ops = &hfsplus_aops;
 		} else {
 			init_special_inode(inode, inode->i_mode,
diff --git a/fs/hfsplus/posix_acl.c b/fs/hfsplus/posix_acl.c
index df0c9af..afb33ed 100644
--- a/fs/hfsplus/posix_acl.c
+++ b/fs/hfsplus/posix_acl.c
@@ -21,10 +21,10 @@
 
 	switch (type) {
 	case ACL_TYPE_ACCESS:
-		xattr_name = POSIX_ACL_XATTR_ACCESS;
+		xattr_name = XATTR_NAME_POSIX_ACL_ACCESS;
 		break;
 	case ACL_TYPE_DEFAULT:
-		xattr_name = POSIX_ACL_XATTR_DEFAULT;
+		xattr_name = XATTR_NAME_POSIX_ACL_DEFAULT;
 		break;
 	default:
 		return ERR_PTR(-EINVAL);
@@ -66,7 +66,7 @@
 
 	switch (type) {
 	case ACL_TYPE_ACCESS:
-		xattr_name = POSIX_ACL_XATTR_ACCESS;
+		xattr_name = XATTR_NAME_POSIX_ACL_ACCESS;
 		if (acl) {
 			err = posix_acl_equiv_mode(acl, &inode->i_mode);
 			if (err < 0)
@@ -76,7 +76,7 @@
 		break;
 
 	case ACL_TYPE_DEFAULT:
-		xattr_name = POSIX_ACL_XATTR_DEFAULT;
+		xattr_name = XATTR_NAME_POSIX_ACL_DEFAULT;
 		if (!S_ISDIR(inode->i_mode))
 			return acl ? -EACCES : 0;
 		break;
diff --git a/fs/hfsplus/xattr.c b/fs/hfsplus/xattr.c
index e41a010..ab01530 100644
--- a/fs/hfsplus/xattr.c
+++ b/fs/hfsplus/xattr.c
@@ -431,9 +431,6 @@
 	char *xattr_name;
 	int res;
 
-	if (!strcmp(name, ""))
-		return -EINVAL;
-
 	xattr_name = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN + 1,
 		GFP_KERNEL);
 	if (!xattr_name)
@@ -589,9 +586,6 @@
 	int res;
 	char *xattr_name;
 
-	if (!strcmp(name, ""))
-		return -EINVAL;
-
 	xattr_name = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN + 1,
 			     GFP_KERNEL);
 	if (!xattr_name)
@@ -853,9 +847,6 @@
 				struct dentry *dentry, const char *name,
 				void *buffer, size_t size)
 {
-	if (!strcmp(name, ""))
-		return -EINVAL;
-
 	/*
 	 * Don't allow retrieving properly prefixed attributes
 	 * by prepending them with "osx."
@@ -876,9 +867,6 @@
 				struct dentry *dentry, const char *name,
 				const void *buffer, size_t size, int flags)
 {
-	if (!strcmp(name, ""))
-		return -EINVAL;
-
 	/*
 	 * Don't allow setting properly prefixed attributes
 	 * by prepending them with "osx."
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 2ac99db..f49be23 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -730,15 +730,13 @@
 
 	init_special_inode(inode, mode, dev);
 	err = do_mknod(name, mode, MAJOR(dev), MINOR(dev));
-	if (!err)
+	if (err)
 		goto out_free;
 
 	err = read_name(inode, name);
 	__putname(name);
 	if (err)
 		goto out_put;
-	if (err)
-		goto out_put;
 
 	d_instantiate(dentry, inode);
 	return 0;
@@ -892,9 +890,14 @@
 	.setattr	= hostfs_setattr,
 };
 
-static const char *hostfs_follow_link(struct dentry *dentry, void **cookie)
+static const char *hostfs_get_link(struct dentry *dentry,
+				   struct inode *inode,
+				   struct delayed_call *done)
 {
-	char *link = __getname();
+	char *link;
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+	link = kmalloc(PATH_MAX, GFP_KERNEL);
 	if (link) {
 		char *path = dentry_name(dentry);
 		int err = -ENOMEM;
@@ -905,25 +908,20 @@
 			__putname(path);
 		}
 		if (err < 0) {
-			__putname(link);
+			kfree(link);
 			return ERR_PTR(err);
 		}
 	} else {
 		return ERR_PTR(-ENOMEM);
 	}
 
-	return *cookie = link;
-}
-
-static void hostfs_put_link(struct inode *unused, void *cookie)
-{
-	__putname(cookie);
+	set_delayed_call(done, kfree_link, link);
+	return link;
 }
 
 static const struct inode_operations hostfs_link_iops = {
 	.readlink	= generic_readlink,
-	.follow_link	= hostfs_follow_link,
-	.put_link	= hostfs_put_link,
+	.get_link	= hostfs_get_link,
 };
 
 static int hostfs_fill_sb_common(struct super_block *sb, void *d, int silent)
diff --git a/fs/hpfs/inode.c b/fs/hpfs/inode.c
index 933c737..1f3c6d7 100644
--- a/fs/hpfs/inode.c
+++ b/fs/hpfs/inode.c
@@ -77,6 +77,7 @@
 			kfree(ea);
 			i->i_mode = S_IFLNK | 0777;
 			i->i_op = &page_symlink_inode_operations;
+			inode_nohighmem(i);
 			i->i_data.a_ops = &hpfs_symlink_aops;
 			set_nlink(i, 1);
 			i->i_size = ea_size;
diff --git a/fs/hpfs/map.c b/fs/hpfs/map.c
index a69bbc1..a136929 100644
--- a/fs/hpfs/map.c
+++ b/fs/hpfs/map.c
@@ -133,7 +133,7 @@
 void hpfs_load_hotfix_map(struct super_block *s, struct hpfs_spare_block *spareblock)
 {
 	struct quad_buffer_head qbh;
-	u32 *directory;
+	__le32 *directory;
 	u32 n_hotfixes, n_used_hotfixes;
 	unsigned i;
 
diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c
index ae4d5a1..506765a 100644
--- a/fs/hpfs/namei.c
+++ b/fs/hpfs/namei.c
@@ -332,6 +332,7 @@
 	result->i_blocks = 1;
 	set_nlink(result, 1);
 	result->i_size = strlen(symlink);
+	inode_nohighmem(result);
 	result->i_op = &page_symlink_inode_operations;
 	result->i_data.a_ops = &hpfs_symlink_aops;
 
@@ -500,7 +501,7 @@
 
 static int hpfs_symlink_readpage(struct file *file, struct page *page)
 {
-	char *link = kmap(page);
+	char *link = page_address(page);
 	struct inode *i = page->mapping->host;
 	struct fnode *fnode;
 	struct buffer_head *bh;
@@ -516,14 +517,12 @@
 		goto fail;
 	hpfs_unlock(i->i_sb);
 	SetPageUptodate(page);
-	kunmap(page);
 	unlock_page(page);
 	return 0;
 
 fail:
 	hpfs_unlock(i->i_sb);
 	SetPageError(page);
-	kunmap(page);
 	unlock_page(page);
 	return err;
 }
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index de4bdfac..d8f51ee 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -760,6 +760,7 @@
 			break;
 		case S_IFLNK:
 			inode->i_op = &page_symlink_inode_operations;
+			inode_nohighmem(inode);
 			break;
 		}
 		lockdep_annotate_inode_mutex_key(inode);
diff --git a/fs/inode.c b/fs/inode.c
index 1be5f90..4230f66 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -225,7 +225,7 @@
 	inode_detach_wb(inode);
 	security_inode_free(inode);
 	fsnotify_inode_delete(inode);
-	locks_free_lock_context(inode->i_flctx);
+	locks_free_lock_context(inode);
 	if (!inode->i_nlink) {
 		WARN_ON(atomic_long_read(&inode->i_sb->s_remove_count) == 0);
 		atomic_long_dec(&inode->i_sb->s_remove_count);
@@ -2028,3 +2028,9 @@
 				  new_flags) != old_flags));
 }
 EXPORT_SYMBOL(inode_set_flags);
+
+void inode_nohighmem(struct inode *inode)
+{
+	mapping_set_gfp_mask(inode->i_mapping, GFP_USER);
+}
+EXPORT_SYMBOL(inode_nohighmem);
diff --git a/fs/internal.h b/fs/internal.h
index 71859c4d..b71deee 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -55,7 +55,7 @@
 /*
  * namespace.c
  */
-extern int copy_mount_options(const void __user *, unsigned long *);
+extern void *copy_mount_options(const void __user *);
 extern char *copy_mount_string(const void __user *);
 
 extern struct vfsmount *lookup_mnt(struct path *);
@@ -151,3 +151,10 @@
  * fs/nsfs.c
  */
 extern struct dentry_operations ns_dentry_operations;
+
+/*
+ * fs/ioctl.c
+ */
+extern int do_vfs_ioctl(struct file *file, unsigned int fd, unsigned int cmd,
+		    unsigned long arg);
+extern long vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 5d01d26..29466c3 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -15,6 +15,7 @@
 #include <linux/writeback.h>
 #include <linux/buffer_head.h>
 #include <linux/falloc.h>
+#include "internal.h"
 
 #include <asm/ioctls.h>
 
@@ -32,8 +33,7 @@
  *
  * Returns 0 on success, -errno on error.
  */
-static long vfs_ioctl(struct file *filp, unsigned int cmd,
-		      unsigned long arg)
+long vfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
 	int error = -ENOTTY;
 
@@ -215,6 +215,29 @@
 	return error;
 }
 
+static long ioctl_file_clone(struct file *dst_file, unsigned long srcfd,
+			     u64 off, u64 olen, u64 destoff)
+{
+	struct fd src_file = fdget(srcfd);
+	int ret;
+
+	if (!src_file.file)
+		return -EBADF;
+	ret = vfs_clone_file_range(src_file.file, off, dst_file, destoff, olen);
+	fdput(src_file);
+	return ret;
+}
+
+static long ioctl_file_clone_range(struct file *file, void __user *argp)
+{
+	struct file_clone_range args;
+
+	if (copy_from_user(&args, argp, sizeof(args)))
+		return -EFAULT;
+	return ioctl_file_clone(file, args.src_fd, args.src_offset,
+				args.src_length, args.dest_offset);
+}
+
 #ifdef CONFIG_BLOCK
 
 static inline sector_t logical_to_blk(struct inode *inode, loff_t offset)
@@ -545,6 +568,41 @@
 	return thaw_super(sb);
 }
 
+static long ioctl_file_dedupe_range(struct file *file, void __user *arg)
+{
+	struct file_dedupe_range __user *argp = arg;
+	struct file_dedupe_range *same = NULL;
+	int ret;
+	unsigned long size;
+	u16 count;
+
+	if (get_user(count, &argp->dest_count)) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	size = offsetof(struct file_dedupe_range __user, info[count]);
+
+	same = memdup_user(argp, size);
+	if (IS_ERR(same)) {
+		ret = PTR_ERR(same);
+		same = NULL;
+		goto out;
+	}
+
+	ret = vfs_dedupe_file_range(file, same);
+	if (ret)
+		goto out;
+
+	ret = copy_to_user(argp, same, size);
+	if (ret)
+		ret = -EFAULT;
+
+out:
+	kfree(same);
+	return ret;
+}
+
 /*
  * When you add any new common ioctls to the switches above and below
  * please update compat_sys_ioctl() too.
@@ -600,6 +658,15 @@
 	case FIGETBSZ:
 		return put_user(inode->i_sb->s_blocksize, argp);
 
+	case FICLONE:
+		return ioctl_file_clone(filp, arg, 0, 0, 0);
+
+	case FICLONERANGE:
+		return ioctl_file_clone_range(filp, argp);
+
+	case FIDEDUPERANGE:
+		return ioctl_file_dedupe_range(filp, argp);
+
 	default:
 		if (S_ISREG(inode->i_mode))
 			error = file_ioctl(filp, cmd, arg);
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index d67a16f..61abdc4 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -1417,6 +1417,7 @@
 		inode->i_fop = &isofs_dir_operations;
 	} else if (S_ISLNK(inode->i_mode)) {
 		inode->i_op = &page_symlink_inode_operations;
+		inode_nohighmem(inode);
 		inode->i_data.a_ops = &isofs_symlink_aops;
 	} else
 		/* XXX - parse_rock_ridge_inode() had already set i_rdev. */
diff --git a/fs/isofs/rock.c b/fs/isofs/rock.c
index 735d752..5384ceb 100644
--- a/fs/isofs/rock.c
+++ b/fs/isofs/rock.c
@@ -687,7 +687,7 @@
 	struct inode *inode = page->mapping->host;
 	struct iso_inode_info *ei = ISOFS_I(inode);
 	struct isofs_sb_info *sbi = ISOFS_SB(inode->i_sb);
-	char *link = kmap(page);
+	char *link = page_address(page);
 	unsigned long bufsize = ISOFS_BUFFER_SIZE(inode);
 	struct buffer_head *bh;
 	char *rpnt = link;
@@ -774,7 +774,6 @@
 	brelse(bh);
 	*rpnt = '\0';
 	SetPageUptodate(page);
-	kunmap(page);
 	unlock_page(page);
 	return 0;
 
@@ -791,7 +790,6 @@
 	brelse(bh);
 error:
 	SetPageError(page);
-	kunmap(page);
 	unlock_page(page);
 	return -EIO;
 }
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index ca181e8..081dff0 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -764,13 +764,11 @@
 
 static void warn_dirty_buffer(struct buffer_head *bh)
 {
-	char b[BDEVNAME_SIZE];
-
 	printk(KERN_WARNING
-	       "JBD2: Spotted dirty metadata buffer (dev = %s, blocknr = %llu). "
+	       "JBD2: Spotted dirty metadata buffer (dev = %pg, blocknr = %llu). "
 	       "There's a risk of filesystem corruption in case of system "
 	       "crash.\n",
-	       bdevname(bh->b_bdev, b), (unsigned long long)bh->b_blocknr);
+	       bh->b_bdev, (unsigned long long)bh->b_blocknr);
 }
 
 /* Call t_frozen trigger and copy buffer data into jh->b_frozen_data. */
diff --git a/fs/jffs2/security.c b/fs/jffs2/security.c
index bf12fe5..7a28fac 100644
--- a/fs/jffs2/security.c
+++ b/fs/jffs2/security.c
@@ -52,9 +52,6 @@
 				   struct dentry *dentry, const char *name,
 				   void *buffer, size_t size)
 {
-	if (!strcmp(name, ""))
-		return -EINVAL;
-
 	return do_jffs2_getxattr(d_inode(dentry), JFFS2_XPREFIX_SECURITY,
 				 name, buffer, size);
 }
@@ -63,31 +60,12 @@
 				   struct dentry *dentry, const char *name,
 				   const void *buffer, size_t size, int flags)
 {
-	if (!strcmp(name, ""))
-		return -EINVAL;
-
 	return do_jffs2_setxattr(d_inode(dentry), JFFS2_XPREFIX_SECURITY,
 				 name, buffer, size, flags);
 }
 
-static size_t jffs2_security_listxattr(const struct xattr_handler *handler,
-				       struct dentry *dentry, char *list,
-				       size_t list_size, const char *name,
-				       size_t name_len)
-{
-	size_t retlen = XATTR_SECURITY_PREFIX_LEN + name_len + 1;
-
-	if (list && retlen <= list_size) {
-		strcpy(list, XATTR_SECURITY_PREFIX);
-		strcpy(list + XATTR_SECURITY_PREFIX_LEN, name);
-	}
-
-	return retlen;
-}
-
 const struct xattr_handler jffs2_security_xattr_handler = {
 	.prefix = XATTR_SECURITY_PREFIX,
-	.list = jffs2_security_listxattr,
 	.set = jffs2_security_setxattr,
 	.get = jffs2_security_getxattr
 };
diff --git a/fs/jffs2/symlink.c b/fs/jffs2/symlink.c
index 8ce2f24..2cabd64 100644
--- a/fs/jffs2/symlink.c
+++ b/fs/jffs2/symlink.c
@@ -14,7 +14,7 @@
 const struct inode_operations jffs2_symlink_inode_operations =
 {
 	.readlink =	generic_readlink,
-	.follow_link =	simple_follow_link,
+	.get_link =	simple_get_link,
 	.setattr =	jffs2_setattr,
 	.setxattr =	jffs2_setxattr,
 	.getxattr =	jffs2_getxattr,
diff --git a/fs/jffs2/xattr.c b/fs/jffs2/xattr.c
index 4c2c036..da3e185 100644
--- a/fs/jffs2/xattr.c
+++ b/fs/jffs2/xattr.c
@@ -967,7 +967,8 @@
 	struct jffs2_xattr_ref *ref, **pref;
 	struct jffs2_xattr_datum *xd;
 	const struct xattr_handler *xhandle;
-	ssize_t len, rc;
+	const char *prefix;
+	ssize_t prefix_len, len, rc;
 	int retry = 0;
 
 	rc = check_xattr_ref_inode(c, ic);
@@ -998,18 +999,23 @@
 			}
 		}
 		xhandle = xprefix_to_handler(xd->xprefix);
-		if (!xhandle)
+		if (!xhandle || (xhandle->list && !xhandle->list(dentry)))
 			continue;
+		prefix = xhandle->prefix ?: xhandle->name;
+		prefix_len = strlen(prefix);
+		rc = prefix_len + xd->name_len + 1;
+
 		if (buffer) {
-			rc = xhandle->list(xhandle, dentry, buffer + len,
-					   size - len, xd->xname,
-					   xd->name_len);
-		} else {
-			rc = xhandle->list(xhandle, dentry, NULL, 0,
-					   xd->xname, xd->name_len);
+			if (rc > size - len) {
+				rc = -ERANGE;
+				goto out;
+			}
+			memcpy(buffer, prefix, prefix_len);
+			buffer += prefix_len;
+			memcpy(buffer, xd->xname, xd->name_len);
+			buffer += xd->name_len;
+			*buffer++ = 0;
 		}
-		if (rc < 0)
-			goto out;
 		len += rc;
 	}
 	rc = len;
diff --git a/fs/jffs2/xattr_trusted.c b/fs/jffs2/xattr_trusted.c
index a562da0..b2555ef 100644
--- a/fs/jffs2/xattr_trusted.c
+++ b/fs/jffs2/xattr_trusted.c
@@ -20,8 +20,6 @@
 				  struct dentry *dentry, const char *name,
 				  void *buffer, size_t size)
 {
-	if (!strcmp(name, ""))
-		return -EINVAL;
 	return do_jffs2_getxattr(d_inode(dentry), JFFS2_XPREFIX_TRUSTED,
 				 name, buffer, size);
 }
@@ -30,28 +28,13 @@
 				  struct dentry *dentry, const char *name,
 				  const void *buffer, size_t size, int flags)
 {
-	if (!strcmp(name, ""))
-		return -EINVAL;
 	return do_jffs2_setxattr(d_inode(dentry), JFFS2_XPREFIX_TRUSTED,
 				 name, buffer, size, flags);
 }
 
-static size_t jffs2_trusted_listxattr(const struct xattr_handler *handler,
-				      struct dentry *dentry, char *list,
-				      size_t list_size, const char *name,
-				      size_t name_len)
+static bool jffs2_trusted_listxattr(struct dentry *dentry)
 {
-	size_t retlen = XATTR_TRUSTED_PREFIX_LEN + name_len + 1;
-
-	if (!capable(CAP_SYS_ADMIN))
-		return 0;
-
-	if (list && retlen<=list_size) {
-		strcpy(list, XATTR_TRUSTED_PREFIX);
-		strcpy(list + XATTR_TRUSTED_PREFIX_LEN, name);
-	}
-
-	return retlen;
+	return capable(CAP_SYS_ADMIN);
 }
 
 const struct xattr_handler jffs2_trusted_xattr_handler = {
diff --git a/fs/jffs2/xattr_user.c b/fs/jffs2/xattr_user.c
index cbc0472..539bd63 100644
--- a/fs/jffs2/xattr_user.c
+++ b/fs/jffs2/xattr_user.c
@@ -20,8 +20,6 @@
 			       struct dentry *dentry, const char *name,
 			       void *buffer, size_t size)
 {
-	if (!strcmp(name, ""))
-		return -EINVAL;
 	return do_jffs2_getxattr(d_inode(dentry), JFFS2_XPREFIX_USER,
 				 name, buffer, size);
 }
@@ -30,30 +28,12 @@
 			       struct dentry *dentry, const char *name,
 			       const void *buffer, size_t size, int flags)
 {
-	if (!strcmp(name, ""))
-		return -EINVAL;
 	return do_jffs2_setxattr(d_inode(dentry), JFFS2_XPREFIX_USER,
 				 name, buffer, size, flags);
 }
 
-static size_t jffs2_user_listxattr(const struct xattr_handler *handler,
-				   struct dentry *dentry, char *list,
-				   size_t list_size, const char *name,
-				   size_t name_len)
-{
-	size_t retlen = XATTR_USER_PREFIX_LEN + name_len + 1;
-
-	if (list && retlen <= list_size) {
-		strcpy(list, XATTR_USER_PREFIX);
-		strcpy(list + XATTR_USER_PREFIX_LEN, name);
-	}
-
-	return retlen;
-}
-
 const struct xattr_handler jffs2_user_xattr_handler = {
 	.prefix = XATTR_USER_PREFIX,
-	.list = jffs2_user_listxattr,
 	.set = jffs2_user_setxattr,
 	.get = jffs2_user_getxattr
 };
diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c
index 0c8ca83..4945685 100644
--- a/fs/jfs/acl.c
+++ b/fs/jfs/acl.c
@@ -40,10 +40,10 @@
 
 	switch(type) {
 		case ACL_TYPE_ACCESS:
-			ea_name = POSIX_ACL_XATTR_ACCESS;
+			ea_name = XATTR_NAME_POSIX_ACL_ACCESS;
 			break;
 		case ACL_TYPE_DEFAULT:
-			ea_name = POSIX_ACL_XATTR_DEFAULT;
+			ea_name = XATTR_NAME_POSIX_ACL_DEFAULT;
 			break;
 		default:
 			return ERR_PTR(-EINVAL);
@@ -82,7 +82,7 @@
 
 	switch (type) {
 	case ACL_TYPE_ACCESS:
-		ea_name = POSIX_ACL_XATTR_ACCESS;
+		ea_name = XATTR_NAME_POSIX_ACL_ACCESS;
 		if (acl) {
 			rc = posix_acl_equiv_mode(acl, &inode->i_mode);
 			if (rc < 0)
@@ -94,7 +94,7 @@
 		}
 		break;
 	case ACL_TYPE_DEFAULT:
-		ea_name = POSIX_ACL_XATTR_DEFAULT;
+		ea_name = XATTR_NAME_POSIX_ACL_DEFAULT;
 		break;
 	default:
 		return -EINVAL;
diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c
index 41aa3ca..9d9bae6 100644
--- a/fs/jfs/inode.c
+++ b/fs/jfs/inode.c
@@ -60,6 +60,7 @@
 	} else if (S_ISLNK(inode->i_mode)) {
 		if (inode->i_size >= IDATASIZE) {
 			inode->i_op = &page_symlink_inode_operations;
+			inode_nohighmem(inode);
 			inode->i_mapping->a_ops = &jfs_aops;
 		} else {
 			inode->i_op = &jfs_fast_symlink_inode_operations;
diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c
index a69bdf2..a270cb7 100644
--- a/fs/jfs/jfs_logmgr.c
+++ b/fs/jfs/jfs_logmgr.c
@@ -1835,17 +1835,16 @@
 	for (i = 0; i < LOGPAGES;) {
 		char *buffer;
 		uint offset;
-		struct page *page;
+		struct page *page = alloc_page(GFP_KERNEL | __GFP_ZERO);
 
-		buffer = (char *) get_zeroed_page(GFP_KERNEL);
-		if (buffer == NULL)
+		if (!page)
 			goto error;
-		page = virt_to_page(buffer);
+		buffer = page_address(page);
 		for (offset = 0; offset < PAGE_SIZE; offset += LOGPSIZE) {
 			lbuf = kmalloc(sizeof(struct lbuf), GFP_KERNEL);
 			if (lbuf == NULL) {
 				if (offset == 0)
-					free_page((unsigned long) buffer);
+					__free_page(page);
 				goto error;
 			}
 			if (offset) /* we already have one reference */
diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c
index 9d7551f..701f893 100644
--- a/fs/jfs/namei.c
+++ b/fs/jfs/namei.c
@@ -983,6 +983,7 @@
 		jfs_info("jfs_symlink: allocate extent ip:0x%p", ip);
 
 		ip->i_op = &jfs_symlink_inode_operations;
+		inode_nohighmem(ip);
 		ip->i_mapping->a_ops = &jfs_aops;
 
 		/*
diff --git a/fs/jfs/symlink.c b/fs/jfs/symlink.c
index 5929e23..f8db4fd 100644
--- a/fs/jfs/symlink.c
+++ b/fs/jfs/symlink.c
@@ -23,7 +23,7 @@
 
 const struct inode_operations jfs_fast_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= simple_follow_link,
+	.get_link	= simple_get_link,
 	.setattr	= jfs_setattr,
 	.setxattr	= jfs_setxattr,
 	.getxattr	= jfs_getxattr,
@@ -33,8 +33,7 @@
 
 const struct inode_operations jfs_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= page_follow_link_light,
-	.put_link	= page_put_link,
+	.get_link	= page_get_link,
 	.setattr	= jfs_setattr,
 	.setxattr	= jfs_setxattr,
 	.getxattr	= jfs_getxattr,
diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c
index 756dd56..16405ae 100644
--- a/fs/kernfs/inode.c
+++ b/fs/kernfs/inode.c
@@ -205,7 +205,7 @@
 	if (!attrs)
 		return -ENOMEM;
 
-	return simple_xattr_remove(&attrs->xattrs, name);
+	return simple_xattr_set(&attrs->xattrs, name, NULL, 0, XATTR_REPLACE);
 }
 
 ssize_t kernfs_iop_getxattr(struct dentry *dentry, const char *name, void *buf,
@@ -230,7 +230,7 @@
 	if (!attrs)
 		return -ENOMEM;
 
-	return simple_xattr_list(&attrs->xattrs, buf, size);
+	return simple_xattr_list(d_inode(dentry), &attrs->xattrs, buf, size);
 }
 
 static inline void set_default_inode_attr(struct inode *inode, umode_t mode)
diff --git a/fs/kernfs/symlink.c b/fs/kernfs/symlink.c
index db27252..117b8b3 100644
--- a/fs/kernfs/symlink.c
+++ b/fs/kernfs/symlink.c
@@ -112,18 +112,25 @@
 	return error;
 }
 
-static const char *kernfs_iop_follow_link(struct dentry *dentry, void **cookie)
+static const char *kernfs_iop_get_link(struct dentry *dentry,
+				       struct inode *inode,
+				       struct delayed_call *done)
 {
-	int error = -ENOMEM;
-	unsigned long page = get_zeroed_page(GFP_KERNEL);
-	if (!page)
+	char *body;
+	int error;
+
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+	body = kzalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!body)
 		return ERR_PTR(-ENOMEM);
-	error = kernfs_getlink(dentry, (char *)page);
+	error = kernfs_getlink(dentry, body);
 	if (unlikely(error < 0)) {
-		free_page((unsigned long)page);
+		kfree(body);
 		return ERR_PTR(error);
 	}
-	return *cookie = (char *)page;
+	set_delayed_call(done, kfree_link, body);
+	return body;
 }
 
 const struct inode_operations kernfs_symlink_iops = {
@@ -132,8 +139,7 @@
 	.getxattr	= kernfs_iop_getxattr,
 	.listxattr	= kernfs_iop_listxattr,
 	.readlink	= generic_readlink,
-	.follow_link	= kernfs_iop_follow_link,
-	.put_link	= free_page_put_link,
+	.get_link	= kernfs_iop_get_link,
 	.setattr	= kernfs_iop_setattr,
 	.getattr	= kernfs_iop_getattr,
 	.permission	= kernfs_iop_permission,
diff --git a/fs/libfs.c b/fs/libfs.c
index c7cbfb09..0149129 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -1019,17 +1019,12 @@
 }
 EXPORT_SYMBOL(noop_fsync);
 
-void kfree_put_link(struct inode *unused, void *cookie)
+/* Because kfree isn't assignment-compatible with void(void*) ;-/ */
+void kfree_link(void *p)
 {
-	kfree(cookie);
+	kfree(p);
 }
-EXPORT_SYMBOL(kfree_put_link);
-
-void free_page_put_link(struct inode *unused, void *cookie)
-{
-	free_page((unsigned long) cookie);
-}
-EXPORT_SYMBOL(free_page_put_link);
+EXPORT_SYMBOL(kfree_link);
 
 /*
  * nop .set_page_dirty method so that people can use .page_mkwrite on
@@ -1092,14 +1087,15 @@
 }
 EXPORT_SYMBOL(simple_nosetlease);
 
-const char *simple_follow_link(struct dentry *dentry, void **cookie)
+const char *simple_get_link(struct dentry *dentry, struct inode *inode,
+			    struct delayed_call *done)
 {
-	return d_inode(dentry)->i_link;
+	return inode->i_link;
 }
-EXPORT_SYMBOL(simple_follow_link);
+EXPORT_SYMBOL(simple_get_link);
 
 const struct inode_operations simple_symlink_inode_operations = {
-	.follow_link = simple_follow_link,
+	.get_link = simple_get_link,
 	.readlink = generic_readlink
 };
 EXPORT_SYMBOL(simple_symlink_inode_operations);
diff --git a/fs/locks.c b/fs/locks.c
index 0d2b326..af1ed74 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -119,7 +119,6 @@
 #include <linux/fdtable.h>
 #include <linux/fs.h>
 #include <linux/init.h>
-#include <linux/module.h>
 #include <linux/security.h>
 #include <linux/slab.h>
 #include <linux/syscalls.h>
@@ -230,16 +229,44 @@
 		ctx = smp_load_acquire(&inode->i_flctx);
 	}
 out:
+	trace_locks_get_lock_context(inode, type, ctx);
 	return ctx;
 }
 
-void
-locks_free_lock_context(struct file_lock_context *ctx)
+static void
+locks_dump_ctx_list(struct list_head *list, char *list_type)
 {
-	if (ctx) {
-		WARN_ON_ONCE(!list_empty(&ctx->flc_flock));
-		WARN_ON_ONCE(!list_empty(&ctx->flc_posix));
-		WARN_ON_ONCE(!list_empty(&ctx->flc_lease));
+	struct file_lock *fl;
+
+	list_for_each_entry(fl, list, fl_list) {
+		pr_warn("%s: fl_owner=%p fl_flags=0x%x fl_type=0x%x fl_pid=%u\n", list_type, fl->fl_owner, fl->fl_flags, fl->fl_type, fl->fl_pid);
+	}
+}
+
+static void
+locks_check_ctx_lists(struct inode *inode)
+{
+	struct file_lock_context *ctx = inode->i_flctx;
+
+	if (unlikely(!list_empty(&ctx->flc_flock) ||
+		     !list_empty(&ctx->flc_posix) ||
+		     !list_empty(&ctx->flc_lease))) {
+		pr_warn("Leaked locks on dev=0x%x:0x%x ino=0x%lx:\n",
+			MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev),
+			inode->i_ino);
+		locks_dump_ctx_list(&ctx->flc_flock, "FLOCK");
+		locks_dump_ctx_list(&ctx->flc_posix, "POSIX");
+		locks_dump_ctx_list(&ctx->flc_lease, "LEASE");
+	}
+}
+
+void
+locks_free_lock_context(struct inode *inode)
+{
+	struct file_lock_context *ctx = inode->i_flctx;
+
+	if (unlikely(ctx)) {
+		locks_check_ctx_lists(inode);
 		kmem_cache_free(flctx_cache, ctx);
 	}
 }
@@ -934,7 +961,8 @@
 	return error;
 }
 
-static int __posix_lock_file(struct inode *inode, struct file_lock *request, struct file_lock *conflock)
+static int posix_lock_inode(struct inode *inode, struct file_lock *request,
+			    struct file_lock *conflock)
 {
 	struct file_lock *fl, *tmp;
 	struct file_lock *new_fl = NULL;
@@ -1142,6 +1170,8 @@
 	if (new_fl2)
 		locks_free_lock(new_fl2);
 	locks_dispose_list(&dispose);
+	trace_posix_lock_inode(inode, request, error);
+
 	return error;
 }
 
@@ -1162,7 +1192,7 @@
 int posix_lock_file(struct file *filp, struct file_lock *fl,
 			struct file_lock *conflock)
 {
-	return __posix_lock_file(file_inode(filp), fl, conflock);
+	return posix_lock_inode(file_inode(filp), fl, conflock);
 }
 EXPORT_SYMBOL(posix_lock_file);
 
@@ -1178,7 +1208,7 @@
 	int error;
 	might_sleep ();
 	for (;;) {
-		error = __posix_lock_file(inode, fl, NULL);
+		error = posix_lock_inode(inode, fl, NULL);
 		if (error != FILE_LOCK_DEFERRED)
 			break;
 		error = wait_event_interruptible(fl->fl_wait, !fl->fl_next);
@@ -1191,6 +1221,7 @@
 	return error;
 }
 
+#ifdef CONFIG_MANDATORY_FILE_LOCKING
 /**
  * locks_mandatory_locked - Check for an active lock
  * @file: the file to check
@@ -1227,20 +1258,16 @@
 
 /**
  * locks_mandatory_area - Check for a conflicting lock
- * @read_write: %FLOCK_VERIFY_WRITE for exclusive access, %FLOCK_VERIFY_READ
- *		for shared
- * @inode:      the file to check
+ * @inode:	the file to check
  * @filp:       how the file was opened (if it was)
- * @offset:     start of area to check
- * @count:      length of area to check
+ * @start:	first byte in the file to check
+ * @end:	lastbyte in the file to check
+ * @type:	%F_WRLCK for a write lock, else %F_RDLCK
  *
  * Searches the inode's list of locks to find any POSIX locks which conflict.
- * This function is called from rw_verify_area() and
- * locks_verify_truncate().
  */
-int locks_mandatory_area(int read_write, struct inode *inode,
-			 struct file *filp, loff_t offset,
-			 size_t count)
+int locks_mandatory_area(struct inode *inode, struct file *filp, loff_t start,
+			 loff_t end, unsigned char type)
 {
 	struct file_lock fl;
 	int error;
@@ -1252,15 +1279,15 @@
 	fl.fl_flags = FL_POSIX | FL_ACCESS;
 	if (filp && !(filp->f_flags & O_NONBLOCK))
 		sleep = true;
-	fl.fl_type = (read_write == FLOCK_VERIFY_WRITE) ? F_WRLCK : F_RDLCK;
-	fl.fl_start = offset;
-	fl.fl_end = offset + count - 1;
+	fl.fl_type = type;
+	fl.fl_start = start;
+	fl.fl_end = end;
 
 	for (;;) {
 		if (filp) {
 			fl.fl_owner = filp;
 			fl.fl_flags &= ~FL_SLEEP;
-			error = __posix_lock_file(inode, &fl, NULL);
+			error = posix_lock_inode(inode, &fl, NULL);
 			if (!error)
 				break;
 		}
@@ -1268,7 +1295,7 @@
 		if (sleep)
 			fl.fl_flags |= FL_SLEEP;
 		fl.fl_owner = current->files;
-		error = __posix_lock_file(inode, &fl, NULL);
+		error = posix_lock_inode(inode, &fl, NULL);
 		if (error != FILE_LOCK_DEFERRED)
 			break;
 		error = wait_event_interruptible(fl.fl_wait, !fl.fl_next);
@@ -1289,6 +1316,7 @@
 }
 
 EXPORT_SYMBOL(locks_mandatory_area);
+#endif /* CONFIG_MANDATORY_FILE_LOCKING */
 
 static void lease_clear_pending(struct file_lock *fl, int arg)
 {
@@ -1503,12 +1531,10 @@
 	ctx = smp_load_acquire(&inode->i_flctx);
 	if (ctx && !list_empty_careful(&ctx->flc_lease)) {
 		spin_lock(&ctx->flc_lock);
-		if (!list_empty(&ctx->flc_lease)) {
-			fl = list_first_entry(&ctx->flc_lease,
-						struct file_lock, fl_list);
-			if (fl->fl_type == F_WRLCK)
-				has_lease = true;
-		}
+		fl = list_first_entry_or_null(&ctx->flc_lease,
+					      struct file_lock, fl_list);
+		if (fl && (fl->fl_type == F_WRLCK))
+			has_lease = true;
 		spin_unlock(&ctx->flc_lock);
 	}
 
@@ -2165,6 +2191,8 @@
 	if (file_lock == NULL)
 		return -ENOLCK;
 
+	inode = file_inode(filp);
+
 	/*
 	 * This might block, so we do it before checking the inode.
 	 */
@@ -2172,8 +2200,6 @@
 	if (copy_from_user(&flock, l, sizeof(flock)))
 		goto out;
 
-	inode = file_inode(filp);
-
 	/* Don't allow mandatory locks on files that may be memory mapped
 	 * and shared.
 	 */
@@ -2182,7 +2208,6 @@
 		goto out;
 	}
 
-again:
 	error = flock_to_posix_lock(filp, file_lock, &flock);
 	if (error)
 		goto out;
@@ -2221,23 +2246,29 @@
 	error = do_lock_file_wait(filp, cmd, file_lock);
 
 	/*
-	 * Attempt to detect a close/fcntl race and recover by
-	 * releasing the lock that was just acquired.
+	 * Attempt to detect a close/fcntl race and recover by releasing the
+	 * lock that was just acquired. There is no need to do that when we're
+	 * unlocking though, or for OFD locks.
 	 */
-	/*
-	 * we need that spin_lock here - it prevents reordering between
-	 * update of i_flctx->flc_posix and check for it done in close().
-	 * rcu_read_lock() wouldn't do.
-	 */
-	spin_lock(&current->files->file_lock);
-	f = fcheck(fd);
-	spin_unlock(&current->files->file_lock);
-	if (!error && f != filp && flock.l_type != F_UNLCK) {
-		flock.l_type = F_UNLCK;
-		goto again;
+	if (!error && file_lock->fl_type != F_UNLCK &&
+	    !(file_lock->fl_flags & FL_OFDLCK)) {
+		/*
+		 * We need that spin_lock here - it prevents reordering between
+		 * update of i_flctx->flc_posix and check for it done in
+		 * close(). rcu_read_lock() wouldn't do.
+		 */
+		spin_lock(&current->files->file_lock);
+		f = fcheck(fd);
+		spin_unlock(&current->files->file_lock);
+		if (f != filp) {
+			file_lock->fl_type = F_UNLCK;
+			error = do_lock_file_wait(filp, cmd, file_lock);
+			WARN_ON_ONCE(error);
+			error = -EBADF;
+		}
 	}
-
 out:
+	trace_fcntl_setlk(inode, file_lock, error);
 	locks_free_lock(file_lock);
 	return error;
 }
@@ -2322,7 +2353,6 @@
 		goto out;
 	}
 
-again:
 	error = flock64_to_posix_lock(filp, file_lock, &flock);
 	if (error)
 		goto out;
@@ -2361,17 +2391,27 @@
 	error = do_lock_file_wait(filp, cmd, file_lock);
 
 	/*
-	 * Attempt to detect a close/fcntl race and recover by
-	 * releasing the lock that was just acquired.
+	 * Attempt to detect a close/fcntl race and recover by releasing the
+	 * lock that was just acquired. There is no need to do that when we're
+	 * unlocking though, or for OFD locks.
 	 */
-	spin_lock(&current->files->file_lock);
-	f = fcheck(fd);
-	spin_unlock(&current->files->file_lock);
-	if (!error && f != filp && flock.l_type != F_UNLCK) {
-		flock.l_type = F_UNLCK;
-		goto again;
+	if (!error && file_lock->fl_type != F_UNLCK &&
+	    !(file_lock->fl_flags & FL_OFDLCK)) {
+		/*
+		 * We need that spin_lock here - it prevents reordering between
+		 * update of i_flctx->flc_posix and check for it done in
+		 * close(). rcu_read_lock() wouldn't do.
+		 */
+		spin_lock(&current->files->file_lock);
+		f = fcheck(fd);
+		spin_unlock(&current->files->file_lock);
+		if (f != filp) {
+			file_lock->fl_type = F_UNLCK;
+			error = do_lock_file_wait(filp, cmd, file_lock);
+			WARN_ON_ONCE(error);
+			error = -EBADF;
+		}
 	}
-
 out:
 	locks_free_lock(file_lock);
 	return error;
@@ -2385,6 +2425,7 @@
  */
 void locks_remove_posix(struct file *filp, fl_owner_t owner)
 {
+	int error;
 	struct file_lock lock;
 	struct file_lock_context *ctx;
 
@@ -2407,10 +2448,11 @@
 	lock.fl_ops = NULL;
 	lock.fl_lmops = NULL;
 
-	vfs_lock_file(filp, F_SETLK, &lock, NULL);
+	error = vfs_lock_file(filp, F_SETLK, &lock, NULL);
 
 	if (lock.fl_ops && lock.fl_ops->fl_release_private)
 		lock.fl_ops->fl_release_private(&lock);
+	trace_locks_remove_posix(file_inode(filp), &lock, error);
 }
 
 EXPORT_SYMBOL(locks_remove_posix);
@@ -2706,7 +2748,7 @@
 	proc_create("locks", 0, NULL, &proc_locks_operations);
 	return 0;
 }
-module_init(proc_locks_init);
+fs_initcall(proc_locks_init);
 #endif
 
 static int __init filelock_init(void)
diff --git a/fs/logfs/dir.c b/fs/logfs/dir.c
index f9b45d4..542468e 100644
--- a/fs/logfs/dir.c
+++ b/fs/logfs/dir.c
@@ -528,7 +528,8 @@
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
 
-	inode->i_op = &logfs_symlink_iops;
+	inode->i_op = &page_symlink_inode_operations;
+	inode_nohighmem(inode);
 	inode->i_mapping->a_ops = &logfs_reg_aops;
 
 	return __logfs_create(dir, dentry, inode, target, destlen);
@@ -776,12 +777,6 @@
 	return -EIO;
 }
 
-const struct inode_operations logfs_symlink_iops = {
-	.readlink	= generic_readlink,
-	.follow_link	= page_follow_link_light,
-	.put_link	= page_put_link,
-};
-
 const struct inode_operations logfs_dir_iops = {
 	.create		= logfs_create,
 	.link		= logfs_link,
diff --git a/fs/logfs/inode.c b/fs/logfs/inode.c
index af49e2d..0fce46d 100644
--- a/fs/logfs/inode.c
+++ b/fs/logfs/inode.c
@@ -64,7 +64,8 @@
 		inode->i_mapping->a_ops = &logfs_reg_aops;
 		break;
 	case S_IFLNK:
-		inode->i_op = &logfs_symlink_iops;
+		inode->i_op = &page_symlink_inode_operations;
+		inode_nohighmem(inode);
 		inode->i_mapping->a_ops = &logfs_reg_aops;
 		break;
 	case S_IFSOCK:	/* fall through */
diff --git a/fs/logfs/logfs.h b/fs/logfs/logfs.h
index 5f09376..39d91f8 100644
--- a/fs/logfs/logfs.h
+++ b/fs/logfs/logfs.h
@@ -302,7 +302,7 @@
 	struct inode *inode;
 	struct logfs_transaction *ta;
 	unsigned long alias_map[LOGFS_BLOCK_FACTOR / BITS_PER_LONG];
-	struct logfs_block_ops *ops;
+	const struct logfs_block_ops *ops;
 	int full;
 	int partial;
 	int reserved_bytes;
@@ -495,7 +495,6 @@
 #endif
 
 /* dir.c */
-extern const struct inode_operations logfs_symlink_iops;
 extern const struct inode_operations logfs_dir_iops;
 extern const struct file_operations logfs_dir_fops;
 int logfs_replay_journal(struct super_block *sb);
@@ -579,7 +578,7 @@
 int get_page_reserve(struct inode *inode, struct page *page);
 void logfs_get_wblocks(struct super_block *sb, struct page *page, int lock);
 void logfs_put_wblocks(struct super_block *sb, struct page *page, int lock);
-extern struct logfs_block_ops indirect_block_ops;
+extern const struct logfs_block_ops indirect_block_ops;
 
 /* segment.c */
 int logfs_erase_segment(struct super_block *sb, u32 ofs, int ensure_erase);
diff --git a/fs/logfs/readwrite.c b/fs/logfs/readwrite.c
index 380d86e..20973c9 100644
--- a/fs/logfs/readwrite.c
+++ b/fs/logfs/readwrite.c
@@ -569,13 +569,13 @@
 }
 
 
-static struct logfs_block_ops inode_block_ops = {
+static const struct logfs_block_ops inode_block_ops = {
 	.write_block = inode_write_block,
 	.free_block = inode_free_block,
 	.write_alias = inode_write_alias,
 };
 
-struct logfs_block_ops indirect_block_ops = {
+const struct logfs_block_ops indirect_block_ops = {
 	.write_block = indirect_write_block,
 	.free_block = indirect_free_block,
 	.write_alias = indirect_write_alias,
diff --git a/fs/logfs/segment.c b/fs/logfs/segment.c
index 6de0fbf..d270e4b 100644
--- a/fs/logfs/segment.c
+++ b/fs/logfs/segment.c
@@ -197,7 +197,7 @@
 	return 0;
 }
 
-static struct logfs_block_ops btree_block_ops = {
+static const struct logfs_block_ops btree_block_ops = {
 	.write_block	= btree_write_block,
 	.free_block	= __free_block,
 	.write_alias	= btree_write_alias,
diff --git a/fs/minix/inode.c b/fs/minix/inode.c
index 086cd0a..cb1789c 100644
--- a/fs/minix/inode.c
+++ b/fs/minix/inode.c
@@ -435,8 +435,7 @@
 
 static const struct inode_operations minix_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= page_follow_link_light,
-	.put_link	= page_put_link,
+	.get_link	= page_get_link,
 	.getattr	= minix_getattr,
 };
 
@@ -452,6 +451,7 @@
 		inode->i_mapping->a_ops = &minix_aops;
 	} else if (S_ISLNK(inode->i_mode)) {
 		inode->i_op = &minix_symlink_inode_operations;
+		inode_nohighmem(inode);
 		inode->i_mapping->a_ops = &minix_aops;
 	} else
 		init_special_inode(inode, inode->i_mode, rdev);
diff --git a/fs/minix/itree_v1.c b/fs/minix/itree_v1.c
index 282e15a..46ca39d 100644
--- a/fs/minix/itree_v1.c
+++ b/fs/minix/itree_v1.c
@@ -24,16 +24,15 @@
 static int block_to_path(struct inode * inode, long block, int offsets[DEPTH])
 {
 	int n = 0;
-	char b[BDEVNAME_SIZE];
 
 	if (block < 0) {
-		printk("MINIX-fs: block_to_path: block %ld < 0 on dev %s\n",
-			block, bdevname(inode->i_sb->s_bdev, b));
+		printk("MINIX-fs: block_to_path: block %ld < 0 on dev %pg\n",
+			block, inode->i_sb->s_bdev);
 	} else if (block >= (minix_sb(inode->i_sb)->s_max_size/BLOCK_SIZE)) {
 		if (printk_ratelimit())
 			printk("MINIX-fs: block_to_path: "
-			       "block %ld too big on dev %s\n",
-				block, bdevname(inode->i_sb->s_bdev, b));
+			       "block %ld too big on dev %pg\n",
+				block, inode->i_sb->s_bdev);
 	} else if (block < 7) {
 		offsets[n++] = block;
 	} else if ((block -= 7) < 512) {
diff --git a/fs/minix/itree_v2.c b/fs/minix/itree_v2.c
index 78e2d93..1ee1013 100644
--- a/fs/minix/itree_v2.c
+++ b/fs/minix/itree_v2.c
@@ -26,18 +26,17 @@
 static int block_to_path(struct inode * inode, long block, int offsets[DEPTH])
 {
 	int n = 0;
-	char b[BDEVNAME_SIZE];
 	struct super_block *sb = inode->i_sb;
 
 	if (block < 0) {
-		printk("MINIX-fs: block_to_path: block %ld < 0 on dev %s\n",
-			block, bdevname(sb->s_bdev, b));
+		printk("MINIX-fs: block_to_path: block %ld < 0 on dev %pg\n",
+			block, sb->s_bdev);
 	} else if ((u64)block * (u64)sb->s_blocksize >=
 			minix_sb(sb)->s_max_size) {
 		if (printk_ratelimit())
 			printk("MINIX-fs: block_to_path: "
-			       "block %ld too big on dev %s\n",
-				block, bdevname(sb->s_bdev, b));
+			       "block %ld too big on dev %pg\n",
+				block, sb->s_bdev);
 	} else if (block < DIRCOUNT) {
 		offsets[n++] = block;
 	} else if ((block -= DIRCOUNT) < INDIRCOUNT(sb)) {
diff --git a/fs/namei.c b/fs/namei.c
index 0c3974c..bceefd5 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -505,13 +505,13 @@
 	int		total_link_count;
 	struct saved {
 		struct path link;
-		void *cookie;
+		struct delayed_call done;
 		const char *name;
-		struct inode *inode;
 		unsigned seq;
 	} *stack, internal[EMBEDDED_LEVELS];
 	struct filename	*name;
 	struct nameidata *saved;
+	struct inode	*link_inode;
 	unsigned	root_seq;
 	int		dfd;
 };
@@ -534,10 +534,8 @@
 	current->nameidata = old;
 	if (old)
 		old->total_link_count = now->total_link_count;
-	if (now->stack != now->internal) {
+	if (now->stack != now->internal)
 		kfree(now->stack);
-		now->stack = now->internal;
-	}
 }
 
 static int __nd_alloc_stack(struct nameidata *nd)
@@ -592,11 +590,8 @@
 	int i = nd->depth;
 	while (i--) {
 		struct saved *last = nd->stack + i;
-		struct inode *inode = last->inode;
-		if (last->cookie && inode->i_op->put_link) {
-			inode->i_op->put_link(inode, last->cookie);
-			last->cookie = NULL;
-		}
+		do_delayed_call(&last->done);
+		clear_delayed_call(&last->done);
 	}
 }
 
@@ -657,7 +652,7 @@
  * Path walking has 2 modes, rcu-walk and ref-walk (see
  * Documentation/filesystems/path-lookup.txt).  In situations when we can't
  * continue in RCU mode, we attempt to drop out of rcu-walk mode and grab
- * normal reference counts on dentries and vfsmounts to transition to rcu-walk
+ * normal reference counts on dentries and vfsmounts to transition to ref-walk
  * mode.  Refcounts are grabbed at the last known good point before rcu-walk
  * got stuck, so ref-walk may continue from there. If this is not successful
  * (eg. a seqcount has changed), then failure is returned and it's up to caller
@@ -807,19 +802,19 @@
 
 static void set_root(struct nameidata *nd)
 {
-	get_fs_root(current->fs, &nd->root);
-}
-
-static void set_root_rcu(struct nameidata *nd)
-{
 	struct fs_struct *fs = current->fs;
-	unsigned seq;
 
-	do {
-		seq = read_seqcount_begin(&fs->seq);
-		nd->root = fs->root;
-		nd->root_seq = __read_seqcount_begin(&nd->root.dentry->d_seq);
-	} while (read_seqcount_retry(&fs->seq, seq));
+	if (nd->flags & LOOKUP_RCU) {
+		unsigned seq;
+
+		do {
+			seq = read_seqcount_begin(&fs->seq);
+			nd->root = fs->root;
+			nd->root_seq = __read_seqcount_begin(&nd->root.dentry->d_seq);
+		} while (read_seqcount_retry(&fs->seq, seq));
+	} else {
+		get_fs_root(fs, &nd->root);
+	}
 }
 
 static void path_put_conditional(struct path *path, struct nameidata *nd)
@@ -841,8 +836,28 @@
 	nd->path.dentry = path->dentry;
 }
 
+static int nd_jump_root(struct nameidata *nd)
+{
+	if (nd->flags & LOOKUP_RCU) {
+		struct dentry *d;
+		nd->path = nd->root;
+		d = nd->path.dentry;
+		nd->inode = d->d_inode;
+		nd->seq = nd->root_seq;
+		if (unlikely(read_seqcount_retry(&d->d_seq, nd->seq)))
+			return -ECHILD;
+	} else {
+		path_put(&nd->path);
+		nd->path = nd->root;
+		path_get(&nd->path);
+		nd->inode = nd->path.dentry->d_inode;
+	}
+	nd->flags |= LOOKUP_JUMPED;
+	return 0;
+}
+
 /*
- * Helper to directly jump to a known parsed path from ->follow_link,
+ * Helper to directly jump to a known parsed path from ->get_link,
  * caller must have taken a reference to path beforehand.
  */
 void nd_jump_link(struct path *path)
@@ -858,9 +873,7 @@
 static inline void put_link(struct nameidata *nd)
 {
 	struct saved *last = nd->stack + --nd->depth;
-	struct inode *inode = last->inode;
-	if (last->cookie && inode->i_op->put_link)
-		inode->i_op->put_link(inode, last->cookie);
+	do_delayed_call(&last->done);
 	if (!(nd->flags & LOOKUP_RCU))
 		path_put(&last->link);
 }
@@ -892,7 +905,7 @@
 		return 0;
 
 	/* Allowed if owner and follower match. */
-	inode = nd->stack[0].inode;
+	inode = nd->link_inode;
 	if (uid_eq(current_cred()->fsuid, inode->i_uid))
 		return 0;
 
@@ -983,7 +996,7 @@
 {
 	struct saved *last = nd->stack + nd->depth - 1;
 	struct dentry *dentry = last->link.dentry;
-	struct inode *inode = last->inode;
+	struct inode *inode = nd->link_inode;
 	int error;
 	const char *res;
 
@@ -1004,36 +1017,27 @@
 	nd->last_type = LAST_BIND;
 	res = inode->i_link;
 	if (!res) {
+		const char * (*get)(struct dentry *, struct inode *,
+				struct delayed_call *);
+		get = inode->i_op->get_link;
 		if (nd->flags & LOOKUP_RCU) {
-			if (unlikely(unlazy_walk(nd, NULL, 0)))
-				return ERR_PTR(-ECHILD);
+			res = get(NULL, inode, &last->done);
+			if (res == ERR_PTR(-ECHILD)) {
+				if (unlikely(unlazy_walk(nd, NULL, 0)))
+					return ERR_PTR(-ECHILD);
+				res = get(dentry, inode, &last->done);
+			}
+		} else {
+			res = get(dentry, inode, &last->done);
 		}
-		res = inode->i_op->follow_link(dentry, &last->cookie);
-		if (IS_ERR_OR_NULL(res)) {
-			last->cookie = NULL;
+		if (IS_ERR_OR_NULL(res))
 			return res;
-		}
 	}
 	if (*res == '/') {
-		if (nd->flags & LOOKUP_RCU) {
-			struct dentry *d;
-			if (!nd->root.mnt)
-				set_root_rcu(nd);
-			nd->path = nd->root;
-			d = nd->path.dentry;
-			nd->inode = d->d_inode;
-			nd->seq = nd->root_seq;
-			if (unlikely(read_seqcount_retry(&d->d_seq, nd->seq)))
-				return ERR_PTR(-ECHILD);
-		} else {
-			if (!nd->root.mnt)
-				set_root(nd);
-			path_put(&nd->path);
-			nd->path = nd->root;
-			path_get(&nd->root);
-			nd->inode = nd->path.dentry->d_inode;
-		}
-		nd->flags |= LOOKUP_JUMPED;
+		if (!nd->root.mnt)
+			set_root(nd);
+		if (unlikely(nd_jump_root(nd)))
+			return ERR_PTR(-ECHILD);
 		while (unlikely(*++res == '/'))
 			;
 	}
@@ -1294,8 +1298,6 @@
 static int follow_dotdot_rcu(struct nameidata *nd)
 {
 	struct inode *inode = nd->inode;
-	if (!nd->root.mnt)
-		set_root_rcu(nd);
 
 	while (1) {
 		if (path_equal(&nd->path, &nd->root))
@@ -1415,9 +1417,6 @@
 
 static int follow_dotdot(struct nameidata *nd)
 {
-	if (!nd->root.mnt)
-		set_root(nd);
-
 	while(1) {
 		struct dentry *old = nd->path.dentry;
 
@@ -1655,6 +1654,8 @@
 static inline int handle_dots(struct nameidata *nd, int type)
 {
 	if (type == LAST_DOTDOT) {
+		if (!nd->root.mnt)
+			set_root(nd);
 		if (nd->flags & LOOKUP_RCU) {
 			return follow_dotdot_rcu(nd);
 		} else
@@ -1691,8 +1692,8 @@
 
 	last = nd->stack + nd->depth++;
 	last->link = *link;
-	last->cookie = NULL;
-	last->inode = inode;
+	clear_delayed_call(&last->done);
+	nd->link_inode = inode;
 	last->seq = seq;
 	return 1;
 }
@@ -2020,18 +2021,19 @@
 	}
 
 	nd->root.mnt = NULL;
+	nd->path.mnt = NULL;
+	nd->path.dentry = NULL;
 
 	nd->m_seq = read_seqbegin(&mount_lock);
 	if (*s == '/') {
-		if (flags & LOOKUP_RCU) {
+		if (flags & LOOKUP_RCU)
 			rcu_read_lock();
-			set_root_rcu(nd);
-			nd->seq = nd->root_seq;
-		} else {
-			set_root(nd);
-			path_get(&nd->root);
-		}
-		nd->path = nd->root;
+		set_root(nd);
+		if (likely(!nd_jump_root(nd)))
+			return s;
+		nd->root.mnt = NULL;
+		rcu_read_unlock();
+		return ERR_PTR(-ECHILD);
 	} else if (nd->dfd == AT_FDCWD) {
 		if (flags & LOOKUP_RCU) {
 			struct fs_struct *fs = current->fs;
@@ -2042,11 +2044,14 @@
 			do {
 				seq = read_seqcount_begin(&fs->seq);
 				nd->path = fs->pwd;
+				nd->inode = nd->path.dentry->d_inode;
 				nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
 			} while (read_seqcount_retry(&fs->seq, seq));
 		} else {
 			get_fs_pwd(current->fs, &nd->path);
+			nd->inode = nd->path.dentry->d_inode;
 		}
+		return s;
 	} else {
 		/* Caller must check execute permissions on the starting path component */
 		struct fd f = fdget_raw(nd->dfd);
@@ -2076,16 +2081,6 @@
 		fdput(f);
 		return s;
 	}
-
-	nd->inode = nd->path.dentry->d_inode;
-	if (!(flags & LOOKUP_RCU))
-		return s;
-	if (likely(!read_seqcount_retry(&nd->path.dentry->d_seq, nd->seq)))
-		return s;
-	if (!(nd->flags & LOOKUP_ROOT))
-		nd->root.mnt = NULL;
-	rcu_read_unlock();
-	return ERR_PTR(-ECHILD);
 }
 
 static const char *trailing_symlink(struct nameidata *nd)
@@ -2278,6 +2273,8 @@
  *
  * Note that this routine is purely a helper for filesystem usage and should
  * not be called by generic code.
+ *
+ * The caller must hold base->i_mutex.
  */
 struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
 {
@@ -2321,6 +2318,75 @@
 }
 EXPORT_SYMBOL(lookup_one_len);
 
+/**
+ * lookup_one_len_unlocked - filesystem helper to lookup single pathname component
+ * @name:	pathname component to lookup
+ * @base:	base directory to lookup from
+ * @len:	maximum length @len should be interpreted to
+ *
+ * Note that this routine is purely a helper for filesystem usage and should
+ * not be called by generic code.
+ *
+ * Unlike lookup_one_len, it should be called without the parent
+ * i_mutex held, and will take the i_mutex itself if necessary.
+ */
+struct dentry *lookup_one_len_unlocked(const char *name,
+				       struct dentry *base, int len)
+{
+	struct qstr this;
+	unsigned int c;
+	int err;
+	struct dentry *ret;
+
+	this.name = name;
+	this.len = len;
+	this.hash = full_name_hash(name, len);
+	if (!len)
+		return ERR_PTR(-EACCES);
+
+	if (unlikely(name[0] == '.')) {
+		if (len < 2 || (len == 2 && name[1] == '.'))
+			return ERR_PTR(-EACCES);
+	}
+
+	while (len--) {
+		c = *(const unsigned char *)name++;
+		if (c == '/' || c == '\0')
+			return ERR_PTR(-EACCES);
+	}
+	/*
+	 * See if the low-level filesystem might want
+	 * to use its own hash..
+	 */
+	if (base->d_flags & DCACHE_OP_HASH) {
+		int err = base->d_op->d_hash(base, &this);
+		if (err < 0)
+			return ERR_PTR(err);
+	}
+
+	err = inode_permission(base->d_inode, MAY_EXEC);
+	if (err)
+		return ERR_PTR(err);
+
+	/*
+	 * __d_lookup() is used to try to get a quick answer and avoid the
+	 * mutex.  A false-negative does no harm.
+	 */
+	ret = __d_lookup(base, &this);
+	if (ret && unlikely(ret->d_flags & DCACHE_OP_REVALIDATE)) {
+		dput(ret);
+		ret = NULL;
+	}
+	if (ret)
+		return ret;
+
+	mutex_lock(&base->d_inode->i_mutex);
+	ret =  __lookup_hash(&this, base, 0);
+	mutex_unlock(&base->d_inode->i_mutex);
+	return ret;
+}
+EXPORT_SYMBOL(lookup_one_len_unlocked);
+
 int user_path_at_empty(int dfd, const char __user *name, unsigned flags,
 		 struct path *path, int *empty)
 {
@@ -2669,10 +2735,6 @@
 	struct inode *inode = dentry->d_inode;
 	int error;
 
-	/* O_PATH? */
-	if (!acc_mode)
-		return 0;
-
 	if (!inode)
 		return -ENOENT;
 
@@ -2694,7 +2756,7 @@
 		break;
 	}
 
-	error = inode_permission(inode, acc_mode);
+	error = inode_permission(inode, MAY_OPEN | acc_mode);
 	if (error)
 		return error;
 
@@ -2886,7 +2948,7 @@
 	if (*opened & FILE_CREATED) {
 		WARN_ON(!(open_flag & O_CREAT));
 		fsnotify_create(dir, dentry);
-		acc_mode = MAY_OPEN;
+		acc_mode = 0;
 	}
 	error = may_open(&file->f_path, acc_mode, open_flag);
 	if (error)
@@ -3099,7 +3161,7 @@
 		/* Don't check for write permission, don't truncate */
 		open_flag &= ~O_TRUNC;
 		will_truncate = false;
-		acc_mode = MAY_OPEN;
+		acc_mode = 0;
 		path_to_nameidata(&path, nd);
 		goto finish_open_created;
 	}
@@ -3183,10 +3245,11 @@
 		got_write = true;
 	}
 finish_open_created:
-	error = may_open(&nd->path, acc_mode, open_flag);
-	if (error)
-		goto out;
-
+	if (likely(!(open_flag & O_PATH))) {
+		error = may_open(&nd->path, acc_mode, open_flag);
+		if (error)
+			goto out;
+	}
 	BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */
 	error = vfs_open(&nd->path, file, current_cred());
 	if (!error) {
@@ -3273,7 +3336,7 @@
 		goto out2;
 	audit_inode(nd->name, child, 0);
 	/* Don't check for other permissions, the inode was just created */
-	error = may_open(&path, MAY_OPEN, op->open_flag);
+	error = may_open(&path, 0, op->open_flag);
 	if (error)
 		goto out2;
 	file->f_path.mnt = path.mnt;
@@ -4495,73 +4558,74 @@
 
 /*
  * A helper for ->readlink().  This should be used *ONLY* for symlinks that
- * have ->follow_link() touching nd only in nd_set_link().  Using (or not
- * using) it for any given inode is up to filesystem.
+ * have ->get_link() not calling nd_jump_link().  Using (or not using) it
+ * for any given inode is up to filesystem.
  */
 int generic_readlink(struct dentry *dentry, char __user *buffer, int buflen)
 {
-	void *cookie;
+	DEFINE_DELAYED_CALL(done);
 	struct inode *inode = d_inode(dentry);
 	const char *link = inode->i_link;
 	int res;
 
 	if (!link) {
-		link = inode->i_op->follow_link(dentry, &cookie);
+		link = inode->i_op->get_link(dentry, inode, &done);
 		if (IS_ERR(link))
 			return PTR_ERR(link);
 	}
 	res = readlink_copy(buffer, buflen, link);
-	if (inode->i_op->put_link)
-		inode->i_op->put_link(inode, cookie);
+	do_delayed_call(&done);
 	return res;
 }
 EXPORT_SYMBOL(generic_readlink);
 
 /* get the link contents into pagecache */
-static char *page_getlink(struct dentry * dentry, struct page **ppage)
+const char *page_get_link(struct dentry *dentry, struct inode *inode,
+			  struct delayed_call *callback)
 {
 	char *kaddr;
 	struct page *page;
-	struct address_space *mapping = dentry->d_inode->i_mapping;
-	page = read_mapping_page(mapping, 0, NULL);
-	if (IS_ERR(page))
-		return (char*)page;
-	*ppage = page;
-	kaddr = kmap(page);
-	nd_terminate_link(kaddr, dentry->d_inode->i_size, PAGE_SIZE - 1);
+	struct address_space *mapping = inode->i_mapping;
+
+	if (!dentry) {
+		page = find_get_page(mapping, 0);
+		if (!page)
+			return ERR_PTR(-ECHILD);
+		if (!PageUptodate(page)) {
+			put_page(page);
+			return ERR_PTR(-ECHILD);
+		}
+	} else {
+		page = read_mapping_page(mapping, 0, NULL);
+		if (IS_ERR(page))
+			return (char*)page;
+	}
+	set_delayed_call(callback, page_put_link, page);
+	BUG_ON(mapping_gfp_mask(mapping) & __GFP_HIGHMEM);
+	kaddr = page_address(page);
+	nd_terminate_link(kaddr, inode->i_size, PAGE_SIZE - 1);
 	return kaddr;
 }
 
+EXPORT_SYMBOL(page_get_link);
+
+void page_put_link(void *arg)
+{
+	put_page(arg);
+}
+EXPORT_SYMBOL(page_put_link);
+
 int page_readlink(struct dentry *dentry, char __user *buffer, int buflen)
 {
-	struct page *page = NULL;
-	int res = readlink_copy(buffer, buflen, page_getlink(dentry, &page));
-	if (page) {
-		kunmap(page);
-		page_cache_release(page);
-	}
+	DEFINE_DELAYED_CALL(done);
+	int res = readlink_copy(buffer, buflen,
+				page_get_link(dentry, d_inode(dentry),
+					      &done));
+	do_delayed_call(&done);
 	return res;
 }
 EXPORT_SYMBOL(page_readlink);
 
-const char *page_follow_link_light(struct dentry *dentry, void **cookie)
-{
-	struct page *page = NULL;
-	char *res = page_getlink(dentry, &page);
-	if (!IS_ERR(res))
-		*cookie = page;
-	return res;
-}
-EXPORT_SYMBOL(page_follow_link_light);
-
-void page_put_link(struct inode *unused, void *cookie)
-{
-	struct page *page = cookie;
-	kunmap(page);
-	page_cache_release(page);
-}
-EXPORT_SYMBOL(page_put_link);
-
 /*
  * The nofs argument instructs pagecache_write_begin to pass AOP_FLAG_NOFS
  */
@@ -4571,7 +4635,6 @@
 	struct page *page;
 	void *fsdata;
 	int err;
-	char *kaddr;
 	unsigned int flags = AOP_FLAG_UNINTERRUPTIBLE;
 	if (nofs)
 		flags |= AOP_FLAG_NOFS;
@@ -4582,9 +4645,7 @@
 	if (err)
 		goto fail;
 
-	kaddr = kmap_atomic(page);
-	memcpy(kaddr, symname, len-1);
-	kunmap_atomic(kaddr);
+	memcpy(page_address(page), symname, len-1);
 
 	err = pagecache_write_end(NULL, mapping, 0, len-1, len-1,
 							page, fsdata);
@@ -4609,7 +4670,6 @@
 
 const struct inode_operations page_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= page_follow_link_light,
-	.put_link	= page_put_link,
+	.get_link	= page_get_link,
 };
 EXPORT_SYMBOL(page_symlink_inode_operations);
diff --git a/fs/namespace.c b/fs/namespace.c
index 0570729..a830e14 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1584,6 +1584,14 @@
 	return ns_capable(current->nsproxy->mnt_ns->user_ns, CAP_SYS_ADMIN);
 }
 
+static inline bool may_mandlock(void)
+{
+#ifndef	CONFIG_MANDATORY_FILE_LOCKING
+	return false;
+#endif
+	return capable(CAP_SYS_ADMIN);
+}
+
 /*
  * Now umount can handle mount points as well as block devices.
  * This is important for filesystems which use unnamed block devices.
@@ -2601,18 +2609,18 @@
 	return n;
 }
 
-int copy_mount_options(const void __user * data, unsigned long *where)
+void *copy_mount_options(const void __user * data)
 {
 	int i;
-	unsigned long page;
 	unsigned long size;
+	char *copy;
 
-	*where = 0;
 	if (!data)
-		return 0;
+		return NULL;
 
-	if (!(page = __get_free_page(GFP_KERNEL)))
-		return -ENOMEM;
+	copy = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!copy)
+		return ERR_PTR(-ENOMEM);
 
 	/* We only care that *some* data at the address the user
 	 * gave us is valid.  Just in case, we'll zero
@@ -2623,15 +2631,14 @@
 	if (size > PAGE_SIZE)
 		size = PAGE_SIZE;
 
-	i = size - exact_copy_from_user((void *)page, data, size);
+	i = size - exact_copy_from_user(copy, data, size);
 	if (!i) {
-		free_page(page);
-		return -EFAULT;
+		kfree(copy);
+		return ERR_PTR(-EFAULT);
 	}
 	if (i != PAGE_SIZE)
-		memset((char *)page + i, 0, PAGE_SIZE - i);
-	*where = page;
-	return 0;
+		memset(copy + i, 0, PAGE_SIZE - i);
+	return copy;
 }
 
 char *copy_mount_string(const void __user *data)
@@ -2677,6 +2684,8 @@
 				   type_page, flags, data_page);
 	if (!retval && !may_mount())
 		retval = -EPERM;
+	if (!retval && (flags & MS_MANDLOCK) && !may_mandlock())
+		retval = -EPERM;
 	if (retval)
 		goto dput_out;
 
@@ -2896,7 +2905,7 @@
 	int ret;
 	char *kernel_type;
 	char *kernel_dev;
-	unsigned long data_page;
+	void *options;
 
 	kernel_type = copy_mount_string(type);
 	ret = PTR_ERR(kernel_type);
@@ -2908,14 +2917,14 @@
 	if (IS_ERR(kernel_dev))
 		goto out_dev;
 
-	ret = copy_mount_options(data, &data_page);
-	if (ret < 0)
+	options = copy_mount_options(data);
+	ret = PTR_ERR(options);
+	if (IS_ERR(options))
 		goto out_data;
 
-	ret = do_mount(kernel_dev, dir_name, kernel_type, flags,
-		(void *) data_page);
+	ret = do_mount(kernel_dev, dir_name, kernel_type, flags, options);
 
-	free_page(data_page);
+	kfree(options);
 out_data:
 	kfree(kernel_dev);
 out_dev:
@@ -2939,9 +2948,9 @@
 	return &mnt->mnt == root->mnt && is_subdir(dentry, root->dentry);
 }
 
-int path_is_under(struct path *path1, struct path *path2)
+bool path_is_under(struct path *path1, struct path *path2)
 {
-	int res;
+	bool res;
 	read_seqlock_excl(&mount_lock);
 	res = is_path_reachable(real_mount(path1->mnt), path1->dentry, path2);
 	read_sequnlock_excl(&mount_lock);
diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c
index 9605a2f..ce1eb3f 100644
--- a/fs/ncpfs/inode.c
+++ b/fs/ncpfs/inode.c
@@ -244,8 +244,7 @@
 #if defined(CONFIG_NCPFS_EXTRAS) || defined(CONFIG_NCPFS_NFS_NS)
 static const struct inode_operations ncp_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= page_follow_link_light,
-	.put_link	= page_put_link,
+	.get_link	= page_get_link,
 	.setattr	= ncp_notify_change,
 };
 #endif
@@ -283,6 +282,7 @@
 #if defined(CONFIG_NCPFS_EXTRAS) || defined(CONFIG_NCPFS_NFS_NS)
 		} else if (S_ISLNK(inode->i_mode)) {
 			inode->i_op = &ncp_symlink_inode_operations;
+			inode_nohighmem(inode);
 			inode->i_data.a_ops = &ncp_symlink_aops;
 #endif
 		} else {
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index c7e8b87..bdb4dc7 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -408,9 +408,10 @@
 				inode->i_fop = NULL;
 				inode->i_flags |= S_AUTOMOUNT;
 			}
-		} else if (S_ISLNK(inode->i_mode))
+		} else if (S_ISLNK(inode->i_mode)) {
 			inode->i_op = &nfs_symlink_inode_operations;
-		else
+			inode_nohighmem(inode);
+		} else
 			init_special_inode(inode, inode->i_mode, fattr->rdev);
 
 		memset(&inode->i_atime, 0, sizeof(inode->i_atime));
@@ -1086,6 +1087,27 @@
 		|| NFS_STALE(inode);
 }
 
+int nfs_revalidate_mapping_rcu(struct inode *inode)
+{
+	struct nfs_inode *nfsi = NFS_I(inode);
+	unsigned long *bitlock = &nfsi->flags;
+	int ret = 0;
+
+	if (IS_SWAPFILE(inode))
+		goto out;
+	if (nfs_mapping_need_revalidate_inode(inode)) {
+		ret = -ECHILD;
+		goto out;
+	}
+	spin_lock(&inode->i_lock);
+	if (test_bit(NFS_INO_INVALIDATING, bitlock) ||
+	    (nfsi->cache_validity & NFS_INO_INVALID_DATA))
+		ret = -ECHILD;
+	spin_unlock(&inode->i_lock);
+out:
+	return ret;
+}
+
 /**
  * __nfs_revalidate_mapping - Revalidate the pagecache
  * @inode - pointer to host inode
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index 1ebe2fc..17c0fa1 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -284,12 +284,12 @@
 	int error;
 
 	error = nfs3_list_one_acl(inode, ACL_TYPE_ACCESS,
-			POSIX_ACL_XATTR_ACCESS, data, size, &result);
+			XATTR_NAME_POSIX_ACL_ACCESS, data, size, &result);
 	if (error)
 		return error;
 
 	error = nfs3_list_one_acl(inode, ACL_TYPE_DEFAULT,
-			POSIX_ACL_XATTR_DEFAULT, data, size, &result);
+			XATTR_NAME_POSIX_ACL_DEFAULT, data, size, &result);
 	if (error)
 		return error;
 	return result;
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index db9b5fe..26f9a23 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -195,65 +195,27 @@
 	return nfs42_proc_allocate(filep, offset, len);
 }
 
-static noinline long
-nfs42_ioctl_clone(struct file *dst_file, unsigned long srcfd,
-		  u64 src_off, u64 dst_off, u64 count)
+static int nfs42_clone_file_range(struct file *src_file, loff_t src_off,
+		struct file *dst_file, loff_t dst_off, u64 count)
 {
 	struct inode *dst_inode = file_inode(dst_file);
 	struct nfs_server *server = NFS_SERVER(dst_inode);
-	struct fd src_file;
-	struct inode *src_inode;
+	struct inode *src_inode = file_inode(src_file);
 	unsigned int bs = server->clone_blksize;
 	bool same_inode = false;
 	int ret;
 
-	/* dst file must be opened for writing */
-	if (!(dst_file->f_mode & FMODE_WRITE))
-		return -EINVAL;
-
-	ret = mnt_want_write_file(dst_file);
-	if (ret)
-		return ret;
-
-	src_file = fdget(srcfd);
-	if (!src_file.file) {
-		ret = -EBADF;
-		goto out_drop_write;
-	}
-
-	src_inode = file_inode(src_file.file);
-
-	if (src_inode == dst_inode)
-		same_inode = true;
-
-	/* src file must be opened for reading */
-	if (!(src_file.file->f_mode & FMODE_READ))
-		goto out_fput;
-
-	/* src and dst must be regular files */
-	ret = -EISDIR;
-	if (!S_ISREG(src_inode->i_mode) || !S_ISREG(dst_inode->i_mode))
-		goto out_fput;
-
-	ret = -EXDEV;
-	if (src_file.file->f_path.mnt != dst_file->f_path.mnt ||
-	    src_inode->i_sb != dst_inode->i_sb)
-		goto out_fput;
-
 	/* check alignment w.r.t. clone_blksize */
 	ret = -EINVAL;
 	if (bs) {
 		if (!IS_ALIGNED(src_off, bs) || !IS_ALIGNED(dst_off, bs))
-			goto out_fput;
+			goto out;
 		if (!IS_ALIGNED(count, bs) && i_size_read(src_inode) != (src_off + count))
-			goto out_fput;
+			goto out;
 	}
 
-	/* verify if ranges are overlapped within the same file */
-	if (same_inode) {
-		if (dst_off + count > src_off && dst_off < src_off + count)
-			goto out_fput;
-	}
+	if (src_inode == dst_inode)
+		same_inode = true;
 
 	/* XXX: do we lock at all? what if server needs CB_RECALL_LAYOUT? */
 	if (same_inode) {
@@ -275,7 +237,7 @@
 	if (ret)
 		goto out_unlock;
 
-	ret = nfs42_proc_clone(src_file.file, dst_file, src_off, dst_off, count);
+	ret = nfs42_proc_clone(src_file, dst_file, src_off, dst_off, count);
 
 	/* truncate inode page cache of the dst range so that future reads can fetch
 	 * new data from server */
@@ -292,37 +254,9 @@
 		mutex_unlock(&dst_inode->i_mutex);
 		mutex_unlock(&src_inode->i_mutex);
 	}
-out_fput:
-	fdput(src_file);
-out_drop_write:
-	mnt_drop_write_file(dst_file);
+out:
 	return ret;
 }
-
-static long nfs42_ioctl_clone_range(struct file *dst_file, void __user *argp)
-{
-	struct btrfs_ioctl_clone_range_args args;
-
-	if (copy_from_user(&args, argp, sizeof(args)))
-		return -EFAULT;
-
-	return nfs42_ioctl_clone(dst_file, args.src_fd, args.src_offset,
-				 args.dest_offset, args.src_length);
-}
-
-long nfs4_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
-{
-	void __user *argp = (void __user *)arg;
-
-	switch (cmd) {
-	case BTRFS_IOC_CLONE:
-		return nfs42_ioctl_clone(file, arg, 0, 0, 0);
-	case BTRFS_IOC_CLONE_RANGE:
-		return nfs42_ioctl_clone_range(file, argp);
-	}
-
-	return -ENOTTY;
-}
 #endif /* CONFIG_NFS_V4_2 */
 
 const struct file_operations nfs4_file_operations = {
@@ -342,8 +276,7 @@
 #ifdef CONFIG_NFS_V4_2
 	.llseek		= nfs4_file_llseek,
 	.fallocate	= nfs42_fallocate,
-	.unlocked_ioctl = nfs4_ioctl,
-	.compat_ioctl	= nfs4_ioctl,
+	.clone_file_range = nfs42_clone_file_range,
 #else
 	.llseek		= nfs_file_llseek,
 #endif
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 8981803..c57d1332c 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -6253,9 +6253,6 @@
 				   const void *buf, size_t buflen,
 				   int flags)
 {
-	if (strcmp(key, "") != 0)
-		return -EINVAL;
-
 	return nfs4_proc_set_acl(d_inode(dentry), buf, buflen);
 }
 
@@ -6263,32 +6260,15 @@
 				   struct dentry *dentry, const char *key,
 				   void *buf, size_t buflen)
 {
-	if (strcmp(key, "") != 0)
-		return -EINVAL;
-
 	return nfs4_proc_get_acl(d_inode(dentry), buf, buflen);
 }
 
-static size_t nfs4_xattr_list_nfs4_acl(const struct xattr_handler *handler,
-				       struct dentry *dentry, char *list,
-				       size_t list_len, const char *name,
-				       size_t name_len)
+static bool nfs4_xattr_list_nfs4_acl(struct dentry *dentry)
 {
-	size_t len = sizeof(XATTR_NAME_NFSV4_ACL);
-
-	if (!nfs4_server_supports_acls(NFS_SERVER(d_inode(dentry))))
-		return 0;
-
-	if (list && len <= list_len)
-		memcpy(list, XATTR_NAME_NFSV4_ACL, len);
-	return len;
+	return nfs4_server_supports_acls(NFS_SERVER(d_inode(dentry)));
 }
 
 #ifdef CONFIG_NFS_V4_SECURITY_LABEL
-static inline int nfs4_server_supports_labels(struct nfs_server *server)
-{
-	return server->caps & NFS_CAP_SECURITY_LABEL;
-}
 
 static int nfs4_xattr_set_nfs4_label(const struct xattr_handler *handler,
 				     struct dentry *dentry, const char *key,
@@ -6310,29 +6290,34 @@
 	return -EOPNOTSUPP;
 }
 
-static size_t nfs4_xattr_list_nfs4_label(const struct xattr_handler *handler,
-					 struct dentry *dentry, char *list,
-					 size_t list_len, const char *name,
-					 size_t name_len)
+static ssize_t
+nfs4_listxattr_nfs4_label(struct inode *inode, char *list, size_t list_len)
 {
-	size_t len = 0;
+	int len = 0;
 
-	if (nfs_server_capable(d_inode(dentry), NFS_CAP_SECURITY_LABEL)) {
-		len = security_inode_listsecurity(d_inode(dentry), NULL, 0);
-		if (list && len <= list_len)
-			security_inode_listsecurity(d_inode(dentry), list, len);
+	if (nfs_server_capable(inode, NFS_CAP_SECURITY_LABEL)) {
+		len = security_inode_listsecurity(inode, list, list_len);
+		if (list_len && len > list_len)
+			return -ERANGE;
 	}
 	return len;
 }
 
 static const struct xattr_handler nfs4_xattr_nfs4_label_handler = {
 	.prefix = XATTR_SECURITY_PREFIX,
-	.list	= nfs4_xattr_list_nfs4_label,
 	.get	= nfs4_xattr_get_nfs4_label,
 	.set	= nfs4_xattr_set_nfs4_label,
 };
-#endif
 
+#else
+
+static ssize_t
+nfs4_listxattr_nfs4_label(struct inode *inode, char *list, size_t list_len)
+{
+	return 0;
+}
+
+#endif
 
 /*
  * nfs_fhget will use either the mounted_on_fileid or the fileid
@@ -8749,6 +8734,24 @@
 #endif
 };
 
+ssize_t nfs4_listxattr(struct dentry *dentry, char *list, size_t size)
+{
+	ssize_t error, error2;
+
+	error = generic_listxattr(dentry, list, size);
+	if (error < 0)
+		return error;
+	if (list) {
+		list += error;
+		size -= error;
+	}
+
+	error2 = nfs4_listxattr_nfs4_label(d_inode(dentry), list, size);
+	if (error2 < 0)
+		return error2;
+	return error + error2;
+}
+
 static const struct inode_operations nfs4_dir_inode_operations = {
 	.create		= nfs_create,
 	.lookup		= nfs_lookup,
@@ -8765,7 +8768,7 @@
 	.setattr	= nfs_setattr,
 	.getxattr	= generic_getxattr,
 	.setxattr	= generic_setxattr,
-	.listxattr	= generic_listxattr,
+	.listxattr	= nfs4_listxattr,
 	.removexattr	= generic_removexattr,
 };
 
@@ -8775,7 +8778,7 @@
 	.setattr	= nfs_setattr,
 	.getxattr	= generic_getxattr,
 	.setxattr	= generic_setxattr,
-	.listxattr	= generic_listxattr,
+	.listxattr	= nfs4_listxattr,
 	.removexattr	= generic_removexattr,
 };
 
@@ -8834,7 +8837,7 @@
 };
 
 static const struct xattr_handler nfs4_xattr_nfs4_acl_handler = {
-	.prefix	= XATTR_NAME_NFSV4_ACL,
+	.name	= XATTR_NAME_NFSV4_ACL,
 	.list	= nfs4_xattr_list_nfs4_acl,
 	.get	= nfs4_xattr_get_nfs4_acl,
 	.set	= nfs4_xattr_set_nfs4_acl,
diff --git a/fs/nfs/symlink.c b/fs/nfs/symlink.c
index b6de433..4fe3eea 100644
--- a/fs/nfs/symlink.c
+++ b/fs/nfs/symlink.c
@@ -42,21 +42,35 @@
 	return -EIO;
 }
 
-static const char *nfs_follow_link(struct dentry *dentry, void **cookie)
+static const char *nfs_get_link(struct dentry *dentry,
+				struct inode *inode,
+				struct delayed_call *done)
 {
-	struct inode *inode = d_inode(dentry);
 	struct page *page;
 	void *err;
 
-	err = ERR_PTR(nfs_revalidate_mapping(inode, inode->i_mapping));
-	if (err)
-		return err;
-	page = read_cache_page(&inode->i_data, 0,
-				(filler_t *)nfs_symlink_filler, inode);
-	if (IS_ERR(page))
-		return ERR_CAST(page);
-	*cookie = page;
-	return kmap(page);
+	if (!dentry) {
+		err = ERR_PTR(nfs_revalidate_mapping_rcu(inode));
+		if (err)
+			return err;
+		page = find_get_page(inode->i_mapping, 0);
+		if (!page)
+			return ERR_PTR(-ECHILD);
+		if (!PageUptodate(page)) {
+			put_page(page);
+			return ERR_PTR(-ECHILD);
+		}
+	} else {
+		err = ERR_PTR(nfs_revalidate_mapping(inode, inode->i_mapping));
+		if (err)
+			return err;
+		page = read_cache_page(&inode->i_data, 0,
+					(filler_t *)nfs_symlink_filler, inode);
+		if (IS_ERR(page))
+			return ERR_CAST(page);
+	}
+	set_delayed_call(done, page_put_link, page);
+	return page_address(page);
 }
 
 /*
@@ -64,8 +78,7 @@
  */
 const struct inode_operations nfs_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= nfs_follow_link,
-	.put_link	= page_put_link,
+	.get_link	= nfs_get_link,
 	.getattr	= nfs_getattr,
 	.setattr	= nfs_setattr,
 };
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index 00575d7..2246454 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -823,7 +823,7 @@
 		} else
 			dchild = dget(dparent);
 	} else
-		dchild = lookup_one_len(name, dparent, namlen);
+		dchild = lookup_one_len_unlocked(name, dparent, namlen);
 	if (IS_ERR(dchild))
 		return rv;
 	if (d_mountpoint(dchild))
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index a9f096c..819ad81 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -774,8 +774,9 @@
 		clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
 
 	/* check stateid */
-	status = nfs4_preprocess_stateid_op(rqstp, cstate, &read->rd_stateid,
-			RD_STATE, &read->rd_filp, &read->rd_tmp_file);
+	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
+					&read->rd_stateid, RD_STATE,
+					&read->rd_filp, &read->rd_tmp_file);
 	if (status) {
 		dprintk("NFSD: nfsd4_read: couldn't process stateid!\n");
 		goto out;
@@ -921,7 +922,8 @@
 
 	if (setattr->sa_iattr.ia_valid & ATTR_SIZE) {
 		status = nfs4_preprocess_stateid_op(rqstp, cstate,
-			&setattr->sa_stateid, WR_STATE, NULL, NULL);
+				&cstate->current_fh, &setattr->sa_stateid,
+				WR_STATE, NULL, NULL);
 		if (status) {
 			dprintk("NFSD: nfsd4_setattr: couldn't process stateid!\n");
 			return status;
@@ -985,8 +987,8 @@
 	if (write->wr_offset >= OFFSET_MAX)
 		return nfserr_inval;
 
-	status = nfs4_preprocess_stateid_op(rqstp, cstate, stateid, WR_STATE,
-			&filp, NULL);
+	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
+						stateid, WR_STATE, &filp, NULL);
 	if (status) {
 		dprintk("NFSD: nfsd4_write: couldn't process stateid!\n");
 		return status;
@@ -1010,13 +1012,54 @@
 }
 
 static __be32
+nfsd4_clone(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
+		struct nfsd4_clone *clone)
+{
+	struct file *src, *dst;
+	__be32 status;
+
+	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->save_fh,
+					    &clone->cl_src_stateid, RD_STATE,
+					    &src, NULL);
+	if (status) {
+		dprintk("NFSD: %s: couldn't process src stateid!\n", __func__);
+		goto out;
+	}
+
+	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
+					    &clone->cl_dst_stateid, WR_STATE,
+					    &dst, NULL);
+	if (status) {
+		dprintk("NFSD: %s: couldn't process dst stateid!\n", __func__);
+		goto out_put_src;
+	}
+
+	/* fix up for NFS-specific error code */
+	if (!S_ISREG(file_inode(src)->i_mode) ||
+	    !S_ISREG(file_inode(dst)->i_mode)) {
+		status = nfserr_wrong_type;
+		goto out_put_dst;
+	}
+
+	status = nfsd4_clone_file_range(src, clone->cl_src_pos,
+			dst, clone->cl_dst_pos, clone->cl_count);
+
+out_put_dst:
+	fput(dst);
+out_put_src:
+	fput(src);
+out:
+	return status;
+}
+
+static __be32
 nfsd4_fallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		struct nfsd4_fallocate *fallocate, int flags)
 {
 	__be32 status = nfserr_notsupp;
 	struct file *file;
 
-	status = nfs4_preprocess_stateid_op(rqstp, cstate,
+	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
 					    &fallocate->falloc_stateid,
 					    WR_STATE, &file, NULL);
 	if (status != nfs_ok) {
@@ -1055,7 +1098,7 @@
 	__be32 status;
 	struct file *file;
 
-	status = nfs4_preprocess_stateid_op(rqstp, cstate,
+	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
 					    &seek->seek_stateid,
 					    RD_STATE, &file, NULL);
 	if (status) {
@@ -2279,6 +2322,12 @@
 		.op_name = "OP_DEALLOCATE",
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
 	},
+	[OP_CLONE] = {
+		.op_func = (nfsd4op_func)nfsd4_clone,
+		.op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME,
+		.op_name = "OP_CLONE",
+		.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
+	},
 	[OP_SEEK] = {
 		.op_func = (nfsd4op_func)nfsd4_seek,
 		.op_name = "OP_SEEK",
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 6b800b5b..df5dba6 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -4797,10 +4797,9 @@
  */
 __be32
 nfs4_preprocess_stateid_op(struct svc_rqst *rqstp,
-		struct nfsd4_compound_state *cstate, stateid_t *stateid,
-		int flags, struct file **filpp, bool *tmp_file)
+		struct nfsd4_compound_state *cstate, struct svc_fh *fhp,
+		stateid_t *stateid, int flags, struct file **filpp, bool *tmp_file)
 {
-	struct svc_fh *fhp = &cstate->current_fh;
 	struct inode *ino = d_inode(fhp->fh_dentry);
 	struct net *net = SVC_NET(rqstp);
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 51c9e9c..d6ef095 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -1675,6 +1675,25 @@
 }
 
 static __be32
+nfsd4_decode_clone(struct nfsd4_compoundargs *argp, struct nfsd4_clone *clone)
+{
+	DECODE_HEAD;
+
+	status = nfsd4_decode_stateid(argp, &clone->cl_src_stateid);
+	if (status)
+		return status;
+	status = nfsd4_decode_stateid(argp, &clone->cl_dst_stateid);
+	if (status)
+		return status;
+
+	READ_BUF(8 + 8 + 8);
+	p = xdr_decode_hyper(p, &clone->cl_src_pos);
+	p = xdr_decode_hyper(p, &clone->cl_dst_pos);
+	p = xdr_decode_hyper(p, &clone->cl_count);
+	DECODE_TAIL;
+}
+
+static __be32
 nfsd4_decode_seek(struct nfsd4_compoundargs *argp, struct nfsd4_seek *seek)
 {
 	DECODE_HEAD;
@@ -1785,6 +1804,7 @@
 	[OP_READ_PLUS]		= (nfsd4_dec)nfsd4_decode_notsupp,
 	[OP_SEEK]		= (nfsd4_dec)nfsd4_decode_seek,
 	[OP_WRITE_SAME]		= (nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_CLONE]		= (nfsd4_dec)nfsd4_decode_clone,
 };
 
 static inline bool
@@ -2838,14 +2858,14 @@
 	__be32 nfserr;
 	int ignore_crossmnt = 0;
 
-	dentry = lookup_one_len(name, cd->rd_fhp->fh_dentry, namlen);
+	dentry = lookup_one_len_unlocked(name, cd->rd_fhp->fh_dentry, namlen);
 	if (IS_ERR(dentry))
 		return nfserrno(PTR_ERR(dentry));
 	if (d_really_is_negative(dentry)) {
 		/*
-		 * nfsd_buffered_readdir drops the i_mutex between
-		 * readdir and calling this callback, leaving a window
-		 * where this directory entry could have gone away.
+		 * we're not holding the i_mutex here, so there's
+		 * a window where this directory entry could have gone
+		 * away.
 		 */
 		dput(dentry);
 		return nfserr_noent;
@@ -4292,6 +4312,7 @@
 	[OP_READ_PLUS]		= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_SEEK]		= (nfsd4_enc)nfsd4_encode_seek,
 	[OP_WRITE_SAME]		= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_CLONE]		= (nfsd4_enc)nfsd4_encode_noop,
 };
 
 /*
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 77fdf4d..99432b7 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -578,8 +578,8 @@
 struct nfsd_net;
 
 extern __be32 nfs4_preprocess_stateid_op(struct svc_rqst *rqstp,
-		struct nfsd4_compound_state *cstate, stateid_t *stateid,
-		int flags, struct file **filp, bool *tmp_file);
+		struct nfsd4_compound_state *cstate, struct svc_fh *fhp,
+		stateid_t *stateid, int flags, struct file **filp, bool *tmp_file);
 __be32 nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
 		     stateid_t *stateid, unsigned char typemask,
 		     struct nfs4_stid **s, struct nfsd_net *nn);
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 994d66f..d41c149 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -36,6 +36,7 @@
 #endif /* CONFIG_NFSD_V3 */
 
 #ifdef CONFIG_NFSD_V4
+#include "../internal.h"
 #include "acl.h"
 #include "idmap.h"
 #endif /* CONFIG_NFSD_V4 */
@@ -217,10 +218,16 @@
 		host_err = PTR_ERR(dentry);
 		if (IS_ERR(dentry))
 			goto out_nfserr;
-		/*
-		 * check if we have crossed a mount point ...
-		 */
 		if (nfsd_mountpoint(dentry, exp)) {
+			/*
+			 * We don't need the i_mutex after all.  It's
+			 * still possible we could open this (regular
+			 * files can be mountpoints too), but the
+			 * i_mutex is just there to prevent renames of
+			 * something that we might be about to delegate,
+			 * and a mountpoint won't be renamed:
+			 */
+			fh_unlock(fhp);
 			if ((host_err = nfsd_cross_mnt(rqstp, &dentry, &exp))) {
 				dput(dentry);
 				goto out_nfserr;
@@ -498,6 +505,13 @@
 }
 #endif
 
+__be32 nfsd4_clone_file_range(struct file *src, u64 src_pos, struct file *dst,
+		u64 dst_pos, u64 count)
+{
+	return nfserrno(vfs_clone_file_range(src, src_pos, dst, dst_pos,
+			count));
+}
+
 __be32 nfsd4_vfs_fallocate(struct svc_rqst *rqstp, struct svc_fh *fhp,
 			   struct file *file, loff_t offset, loff_t len,
 			   int flags)
@@ -1809,7 +1823,6 @@
 	offset = *offsetp;
 
 	while (1) {
-		struct inode *dir_inode = file_inode(file);
 		unsigned int reclen;
 
 		cdp->err = nfserr_eof; /* will be cleared on successful read */
@@ -1828,15 +1841,6 @@
 		if (!size)
 			break;
 
-		/*
-		 * Various filldir functions may end up calling back into
-		 * lookup_one_len() and the file system's ->lookup() method.
-		 * These expect i_mutex to be held, as it would within readdir.
-		 */
-		host_err = mutex_lock_killable(&dir_inode->i_mutex);
-		if (host_err)
-			break;
-
 		de = (struct buffered_dirent *)buf.dirent;
 		while (size > 0) {
 			offset = de->offset;
@@ -1853,7 +1857,6 @@
 			size -= reclen;
 			de = (struct buffered_dirent *)((char *)de + reclen);
 		}
-		mutex_unlock(&dir_inode->i_mutex);
 		if (size > 0) /* We bailed out early */
 			break;
 
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index fcfc48c..c11ba31 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -56,6 +56,8 @@
 		    struct xdr_netobj *);
 __be32		nfsd4_vfs_fallocate(struct svc_rqst *, struct svc_fh *,
 				    struct file *, loff_t, loff_t, int);
+__be32		nfsd4_clone_file_range(struct file *, u64, struct file *,
+			u64, u64);
 #endif /* CONFIG_NFSD_V4 */
 __be32		nfsd_create(struct svc_rqst *, struct svc_fh *,
 				char *name, int len, struct iattr *attrs,
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index ce7362c..d955481 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -491,6 +491,15 @@
 	u64		falloc_length;
 };
 
+struct nfsd4_clone {
+	/* request */
+	stateid_t	cl_src_stateid;
+	stateid_t	cl_dst_stateid;
+	u64		cl_src_pos;
+	u64		cl_dst_pos;
+	u64		cl_count;
+};
+
 struct nfsd4_seek {
 	/* request */
 	stateid_t	seek_stateid;
@@ -555,6 +564,7 @@
 		/* NFSv4.2 */
 		struct nfsd4_fallocate		allocate;
 		struct nfsd4_fallocate		deallocate;
+		struct nfsd4_clone		clone;
 		struct nfsd4_seek		seek;
 	} u;
 	struct nfs4_replay *			replay;
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index ac2f649..10b2252 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -510,6 +510,7 @@
 		inode->i_mapping->a_ops = &nilfs_aops;
 	} else if (S_ISLNK(inode->i_mode)) {
 		inode->i_op = &nilfs_symlink_inode_operations;
+		inode_nohighmem(inode);
 		inode->i_mapping->a_ops = &nilfs_aops;
 	} else {
 		inode->i_op = &nilfs_special_inode_operations;
diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c
index c9a1a491..7ccdb96 100644
--- a/fs/nilfs2/namei.c
+++ b/fs/nilfs2/namei.c
@@ -161,6 +161,7 @@
 
 	/* slow symlink */
 	inode->i_op = &nilfs_symlink_inode_operations;
+	inode_nohighmem(inode);
 	inode->i_mapping->a_ops = &nilfs_aops;
 	err = page_symlink(inode, symname, l);
 	if (err)
@@ -568,8 +569,7 @@
 
 const struct inode_operations nilfs_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= page_follow_link_light,
-	.put_link	= page_put_link,
+	.get_link	= page_get_link,
 	.permission     = nilfs_permission,
 };
 
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 354013e..c734384 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -1316,13 +1316,11 @@
 	}
 
 	if (!s->s_root) {
-		char b[BDEVNAME_SIZE];
-
-		s_new = true;
+ 		s_new = true;
 
 		/* New superblock instance created */
 		s->s_mode = mode;
-		strlcpy(s->s_id, bdevname(sd.bdev, b), sizeof(s->s_id));
+		snprintf(s->s_id, sizeof(s->s_id), "%pg", sd.bdev);
 		sb_set_blocksize(s, block_size(sd.bdev));
 
 		err = nilfs_fill_super(s, data, flags & MS_SILENT ? 1 : 0);
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index 8f87e05..97a563b 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -361,6 +361,7 @@
 		    break;
 	    case S_IFLNK:
 		    inode->i_op = &ocfs2_symlink_inode_operations;
+		    inode_nohighmem(inode);
 		    i_size_write(inode, le64_to_cpu(fe->i_size));
 		    break;
 	    default:
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 3123408..afb81ea 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -1958,6 +1958,7 @@
 	inode->i_rdev = 0;
 	newsize = l - 1;
 	inode->i_op = &ocfs2_symlink_inode_operations;
+	inode_nohighmem(inode);
 	if (l > ocfs2_fast_symlink_chars(sb)) {
 		u32 offset = 0;
 
diff --git a/fs/ocfs2/symlink.c b/fs/ocfs2/symlink.c
index 66edce7..6c2a3e3 100644
--- a/fs/ocfs2/symlink.c
+++ b/fs/ocfs2/symlink.c
@@ -88,8 +88,7 @@
 
 const struct inode_operations ocfs2_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= page_follow_link_light,
-	.put_link	= page_put_link,
+	.get_link	= page_get_link,
 	.getattr	= ocfs2_getattr,
 	.setattr	= ocfs2_setattr,
 	.setxattr	= generic_setxattr,
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index e9164f0..f0e241f 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -544,8 +544,7 @@
 
 	if (name_index > 0 && name_index < OCFS2_XATTR_MAX)
 		handler = ocfs2_xattr_handler_map[name_index];
-
-	return handler ? handler->prefix : NULL;
+	return handler ? xattr_prefix(handler) : NULL;
 }
 
 static u32 ocfs2_xattr_name_hash(struct inode *inode,
@@ -884,14 +883,39 @@
 	return ret;
 }
 
-static int ocfs2_xattr_list_entry(char *buffer, size_t size,
-				  size_t *result, const char *prefix,
+static int ocfs2_xattr_list_entry(struct super_block *sb,
+				  char *buffer, size_t size,
+				  size_t *result, int type,
 				  const char *name, int name_len)
 {
 	char *p = buffer + *result;
-	int prefix_len = strlen(prefix);
-	int total_len = prefix_len + name_len + 1;
+	const char *prefix;
+	int prefix_len;
+	int total_len;
 
+	switch(type) {
+	case OCFS2_XATTR_INDEX_USER:
+		if (OCFS2_SB(sb)->s_mount_opt & OCFS2_MOUNT_NOUSERXATTR)
+			return 0;
+		break;
+
+	case OCFS2_XATTR_INDEX_POSIX_ACL_ACCESS:
+	case OCFS2_XATTR_INDEX_POSIX_ACL_DEFAULT:
+		if (!(sb->s_flags & MS_POSIXACL))
+			return 0;
+		break;
+
+	case OCFS2_XATTR_INDEX_TRUSTED:
+		if (!capable(CAP_SYS_ADMIN))
+			return 0;
+		break;
+	}
+
+	prefix = ocfs2_xattr_prefix(type);
+	if (!prefix)
+		return 0;
+	prefix_len = strlen(prefix);
+	total_len = prefix_len + name_len + 1;
 	*result += total_len;
 
 	/* we are just looking for how big our buffer needs to be */
@@ -914,23 +938,20 @@
 {
 	size_t result = 0;
 	int i, type, ret;
-	const char *prefix, *name;
+	const char *name;
 
 	for (i = 0 ; i < le16_to_cpu(header->xh_count); i++) {
 		struct ocfs2_xattr_entry *entry = &header->xh_entries[i];
 		type = ocfs2_xattr_get_type(entry);
-		prefix = ocfs2_xattr_prefix(type);
+		name = (const char *)header +
+			le16_to_cpu(entry->xe_name_offset);
 
-		if (prefix) {
-			name = (const char *)header +
-				le16_to_cpu(entry->xe_name_offset);
-
-			ret = ocfs2_xattr_list_entry(buffer, buffer_size,
-						     &result, prefix, name,
-						     entry->xe_name_len);
-			if (ret)
-				return ret;
-		}
+		ret = ocfs2_xattr_list_entry(inode->i_sb,
+					     buffer, buffer_size,
+					     &result, type, name,
+					     entry->xe_name_len);
+		if (ret)
+			return ret;
 	}
 
 	return result;
@@ -4033,32 +4054,30 @@
 	int ret = 0, type;
 	struct ocfs2_xattr_tree_list *xl = (struct ocfs2_xattr_tree_list *)para;
 	int i, block_off, new_offset;
-	const char *prefix, *name;
+	const char *name;
 
 	for (i = 0 ; i < le16_to_cpu(bucket_xh(bucket)->xh_count); i++) {
 		struct ocfs2_xattr_entry *entry = &bucket_xh(bucket)->xh_entries[i];
 		type = ocfs2_xattr_get_type(entry);
-		prefix = ocfs2_xattr_prefix(type);
 
-		if (prefix) {
-			ret = ocfs2_xattr_bucket_get_name_value(inode->i_sb,
-								bucket_xh(bucket),
-								i,
-								&block_off,
-								&new_offset);
-			if (ret)
-				break;
+		ret = ocfs2_xattr_bucket_get_name_value(inode->i_sb,
+							bucket_xh(bucket),
+							i,
+							&block_off,
+							&new_offset);
+		if (ret)
+			break;
 
-			name = (const char *)bucket_block(bucket, block_off) +
-				new_offset;
-			ret = ocfs2_xattr_list_entry(xl->buffer,
-						     xl->buffer_size,
-						     &xl->result,
-						     prefix, name,
-						     entry->xe_name_len);
-			if (ret)
-				break;
-		}
+		name = (const char *)bucket_block(bucket, block_off) +
+			new_offset;
+		ret = ocfs2_xattr_list_entry(inode->i_sb,
+					     xl->buffer,
+					     xl->buffer_size,
+					     &xl->result,
+					     type, name,
+					     entry->xe_name_len);
+		if (ret)
+			break;
 	}
 
 	return ret;
@@ -7226,31 +7245,14 @@
 leave:
 	return ret;
 }
+
 /*
  * 'security' attributes support
  */
-static size_t ocfs2_xattr_security_list(const struct xattr_handler *handler,
-					struct dentry *dentry, char *list,
-					size_t list_size, const char *name,
-					size_t name_len)
-{
-	const size_t prefix_len = XATTR_SECURITY_PREFIX_LEN;
-	const size_t total_len = prefix_len + name_len + 1;
-
-	if (list && total_len <= list_size) {
-		memcpy(list, XATTR_SECURITY_PREFIX, prefix_len);
-		memcpy(list + prefix_len, name, name_len);
-		list[prefix_len + name_len] = '\0';
-	}
-	return total_len;
-}
-
 static int ocfs2_xattr_security_get(const struct xattr_handler *handler,
 				    struct dentry *dentry, const char *name,
 				    void *buffer, size_t size)
 {
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
 	return ocfs2_xattr_get(d_inode(dentry), OCFS2_XATTR_INDEX_SECURITY,
 			       name, buffer, size);
 }
@@ -7259,9 +7261,6 @@
 				    struct dentry *dentry, const char *name,
 				    const void *value, size_t size, int flags)
 {
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
-
 	return ocfs2_xattr_set(d_inode(dentry), OCFS2_XATTR_INDEX_SECURITY,
 			       name, value, size, flags);
 }
@@ -7314,7 +7313,6 @@
 
 const struct xattr_handler ocfs2_xattr_security_handler = {
 	.prefix	= XATTR_SECURITY_PREFIX,
-	.list	= ocfs2_xattr_security_list,
 	.get	= ocfs2_xattr_security_get,
 	.set	= ocfs2_xattr_security_set,
 };
@@ -7322,31 +7320,10 @@
 /*
  * 'trusted' attributes support
  */
-static size_t ocfs2_xattr_trusted_list(const struct xattr_handler *handler,
-				       struct dentry *dentry, char *list,
-				       size_t list_size, const char *name,
-				       size_t name_len)
-{
-	const size_t prefix_len = XATTR_TRUSTED_PREFIX_LEN;
-	const size_t total_len = prefix_len + name_len + 1;
-
-	if (!capable(CAP_SYS_ADMIN))
-		return 0;
-
-	if (list && total_len <= list_size) {
-		memcpy(list, XATTR_TRUSTED_PREFIX, prefix_len);
-		memcpy(list + prefix_len, name, name_len);
-		list[prefix_len + name_len] = '\0';
-	}
-	return total_len;
-}
-
 static int ocfs2_xattr_trusted_get(const struct xattr_handler *handler,
 				   struct dentry *dentry, const char *name,
 				   void *buffer, size_t size)
 {
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
 	return ocfs2_xattr_get(d_inode(dentry), OCFS2_XATTR_INDEX_TRUSTED,
 			       name, buffer, size);
 }
@@ -7355,16 +7332,12 @@
 				   struct dentry *dentry, const char *name,
 				   const void *value, size_t size, int flags)
 {
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
-
 	return ocfs2_xattr_set(d_inode(dentry), OCFS2_XATTR_INDEX_TRUSTED,
 			       name, value, size, flags);
 }
 
 const struct xattr_handler ocfs2_xattr_trusted_handler = {
 	.prefix	= XATTR_TRUSTED_PREFIX,
-	.list	= ocfs2_xattr_trusted_list,
 	.get	= ocfs2_xattr_trusted_get,
 	.set	= ocfs2_xattr_trusted_set,
 };
@@ -7372,34 +7345,12 @@
 /*
  * 'user' attributes support
  */
-static size_t ocfs2_xattr_user_list(const struct xattr_handler *handler,
-				    struct dentry *dentry, char *list,
-				    size_t list_size, const char *name,
-				    size_t name_len)
-{
-	const size_t prefix_len = XATTR_USER_PREFIX_LEN;
-	const size_t total_len = prefix_len + name_len + 1;
-	struct ocfs2_super *osb = OCFS2_SB(dentry->d_sb);
-
-	if (osb->s_mount_opt & OCFS2_MOUNT_NOUSERXATTR)
-		return 0;
-
-	if (list && total_len <= list_size) {
-		memcpy(list, XATTR_USER_PREFIX, prefix_len);
-		memcpy(list + prefix_len, name, name_len);
-		list[prefix_len + name_len] = '\0';
-	}
-	return total_len;
-}
-
 static int ocfs2_xattr_user_get(const struct xattr_handler *handler,
 				struct dentry *dentry, const char *name,
 				void *buffer, size_t size)
 {
 	struct ocfs2_super *osb = OCFS2_SB(dentry->d_sb);
 
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
 	if (osb->s_mount_opt & OCFS2_MOUNT_NOUSERXATTR)
 		return -EOPNOTSUPP;
 	return ocfs2_xattr_get(d_inode(dentry), OCFS2_XATTR_INDEX_USER, name,
@@ -7412,8 +7363,6 @@
 {
 	struct ocfs2_super *osb = OCFS2_SB(dentry->d_sb);
 
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
 	if (osb->s_mount_opt & OCFS2_MOUNT_NOUSERXATTR)
 		return -EOPNOTSUPP;
 
@@ -7423,7 +7372,6 @@
 
 const struct xattr_handler ocfs2_xattr_user_handler = {
 	.prefix	= XATTR_USER_PREFIX,
-	.list	= ocfs2_xattr_user_list,
 	.get	= ocfs2_xattr_user_get,
 	.set	= ocfs2_xattr_user_set,
 };
diff --git a/fs/open.c b/fs/open.c
index b6f1e96..b25b154 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -887,7 +887,7 @@
 static inline int build_open_flags(int flags, umode_t mode, struct open_flags *op)
 {
 	int lookup_flags = 0;
-	int acc_mode;
+	int acc_mode = ACC_MODE(flags);
 
 	if (flags & (O_CREAT | __O_TMPFILE))
 		op->mode = (mode & S_IALLUGO) | S_IFREG;
@@ -909,7 +909,6 @@
 	if (flags & __O_TMPFILE) {
 		if ((flags & O_TMPFILE_MASK) != O_TMPFILE)
 			return -EINVAL;
-		acc_mode = MAY_OPEN | ACC_MODE(flags);
 		if (!(acc_mode & MAY_WRITE))
 			return -EINVAL;
 	} else if (flags & O_PATH) {
@@ -919,8 +918,6 @@
 		 */
 		flags &= O_DIRECTORY | O_NOFOLLOW | O_PATH;
 		acc_mode = 0;
-	} else {
-		acc_mode = MAY_OPEN | ACC_MODE(flags);
 	}
 
 	op->open_flag = flags;
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index 4060ffd..964a60f 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -131,57 +131,23 @@
 	return err;
 }
 
-
-struct ovl_link_data {
-	struct dentry *realdentry;
-	void *cookie;
-};
-
-static const char *ovl_follow_link(struct dentry *dentry, void **cookie)
+static const char *ovl_get_link(struct dentry *dentry,
+				struct inode *inode,
+				struct delayed_call *done)
 {
 	struct dentry *realdentry;
 	struct inode *realinode;
-	struct ovl_link_data *data = NULL;
-	const char *ret;
+
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
 
 	realdentry = ovl_dentry_real(dentry);
 	realinode = realdentry->d_inode;
 
-	if (WARN_ON(!realinode->i_op->follow_link))
+	if (WARN_ON(!realinode->i_op->get_link))
 		return ERR_PTR(-EPERM);
 
-	if (realinode->i_op->put_link) {
-		data = kmalloc(sizeof(struct ovl_link_data), GFP_KERNEL);
-		if (!data)
-			return ERR_PTR(-ENOMEM);
-		data->realdentry = realdentry;
-	}
-
-	ret = realinode->i_op->follow_link(realdentry, cookie);
-	if (IS_ERR_OR_NULL(ret)) {
-		kfree(data);
-		return ret;
-	}
-
-	if (data)
-		data->cookie = *cookie;
-
-	*cookie = data;
-
-	return ret;
-}
-
-static void ovl_put_link(struct inode *unused, void *c)
-{
-	struct inode *realinode;
-	struct ovl_link_data *data = c;
-
-	if (!data)
-		return;
-
-	realinode = data->realdentry->d_inode;
-	realinode->i_op->put_link(realinode, data->cookie);
-	kfree(data);
+	return realinode->i_op->get_link(realdentry, realinode, done);
 }
 
 static int ovl_readlink(struct dentry *dentry, char __user *buf, int bufsiz)
@@ -378,8 +344,7 @@
 
 static const struct inode_operations ovl_symlink_inode_operations = {
 	.setattr	= ovl_setattr,
-	.follow_link	= ovl_follow_link,
-	.put_link	= ovl_put_link,
+	.get_link	= ovl_get_link,
 	.readlink	= ovl_readlink,
 	.getattr	= ovl_getattr,
 	.setxattr	= ovl_setxattr,
diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index 4adde1e..711dd51 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -769,8 +769,6 @@
 	struct posix_acl *acl;
 	int error;
 
-	if (strcmp(name, "") != 0)
-		return -EINVAL;
 	if (!IS_POSIXACL(d_backing_inode(dentry)))
 		return -EOPNOTSUPP;
 	if (d_is_symlink(dentry))
@@ -797,8 +795,6 @@
 	struct posix_acl *acl = NULL;
 	int ret;
 
-	if (strcmp(name, "") != 0)
-		return -EINVAL;
 	if (!IS_POSIXACL(inode))
 		return -EOPNOTSUPP;
 	if (!inode->i_op->set_acl)
@@ -827,25 +823,14 @@
 	return ret;
 }
 
-static size_t
-posix_acl_xattr_list(const struct xattr_handler *handler,
-		     struct dentry *dentry, char *list, size_t list_size,
-		     const char *name, size_t name_len)
+static bool
+posix_acl_xattr_list(struct dentry *dentry)
 {
-	const char *xname = handler->prefix;
-	size_t size;
-
-	if (!IS_POSIXACL(d_backing_inode(dentry)))
-		return 0;
-
-	size = strlen(xname) + 1;
-	if (list && size <= list_size)
-		memcpy(list, xname, size);
-	return size;
+	return IS_POSIXACL(d_backing_inode(dentry));
 }
 
 const struct xattr_handler posix_acl_access_xattr_handler = {
-	.prefix = POSIX_ACL_XATTR_ACCESS,
+	.name = XATTR_NAME_POSIX_ACL_ACCESS,
 	.flags = ACL_TYPE_ACCESS,
 	.list = posix_acl_xattr_list,
 	.get = posix_acl_xattr_get,
@@ -854,7 +839,7 @@
 EXPORT_SYMBOL_GPL(posix_acl_access_xattr_handler);
 
 const struct xattr_handler posix_acl_default_xattr_handler = {
-	.prefix = POSIX_ACL_XATTR_DEFAULT,
+	.name = XATTR_NAME_POSIX_ACL_DEFAULT,
 	.flags = ACL_TYPE_DEFAULT,
 	.list = posix_acl_xattr_list,
 	.get = posix_acl_xattr_get,
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 4bd5d31..2cf5d7e 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1564,12 +1564,16 @@
 		return -ENOENT;
 }
 
-static const char *proc_pid_follow_link(struct dentry *dentry, void **cookie)
+static const char *proc_pid_get_link(struct dentry *dentry,
+				     struct inode *inode,
+				     struct delayed_call *done)
 {
-	struct inode *inode = d_inode(dentry);
 	struct path path;
 	int error = -EACCES;
 
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+
 	/* Are we allowed to snoop on the tasks file descriptors? */
 	if (!proc_fd_access_allowed(inode))
 		goto out;
@@ -1630,7 +1634,7 @@
 
 const struct inode_operations proc_pid_link_inode_operations = {
 	.readlink	= proc_pid_readlink,
-	.follow_link	= proc_pid_follow_link,
+	.get_link	= proc_pid_get_link,
 	.setattr	= proc_setattr,
 };
 
@@ -1895,7 +1899,7 @@
 	.d_delete	= pid_delete_dentry,
 };
 
-static int proc_map_files_get_link(struct dentry *dentry, struct path *path)
+static int map_files_get_link(struct dentry *dentry, struct path *path)
 {
 	unsigned long vm_start, vm_end;
 	struct vm_area_struct *vma;
@@ -1945,20 +1949,22 @@
  * path to the file in question.
  */
 static const char *
-proc_map_files_follow_link(struct dentry *dentry, void **cookie)
+proc_map_files_get_link(struct dentry *dentry,
+			struct inode *inode,
+		        struct delayed_call *done)
 {
 	if (!capable(CAP_SYS_ADMIN))
 		return ERR_PTR(-EPERM);
 
-	return proc_pid_follow_link(dentry, NULL);
+	return proc_pid_get_link(dentry, inode, done);
 }
 
 /*
- * Identical to proc_pid_link_inode_operations except for follow_link()
+ * Identical to proc_pid_link_inode_operations except for get_link()
  */
 static const struct inode_operations proc_map_files_link_inode_operations = {
 	.readlink	= proc_pid_readlink,
-	.follow_link	= proc_map_files_follow_link,
+	.get_link	= proc_map_files_get_link,
 	.setattr	= proc_setattr,
 };
 
@@ -1975,7 +1981,7 @@
 		return -ENOENT;
 
 	ei = PROC_I(inode);
-	ei->op.proc_get_link = proc_map_files_get_link;
+	ei->op.proc_get_link = map_files_get_link;
 
 	inode->i_op = &proc_map_files_link_inode_operations;
 	inode->i_size = 64;
@@ -2359,7 +2365,7 @@
 				   size_t count, loff_t *ppos)
 {
 	struct inode * inode = file_inode(file);
-	char *page;
+	void *page;
 	ssize_t length;
 	struct task_struct *task = get_proc_task(inode);
 
@@ -2374,14 +2380,11 @@
 	if (*ppos != 0)
 		goto out;
 
-	length = -ENOMEM;
-	page = (char*)__get_free_page(GFP_TEMPORARY);
-	if (!page)
+	page = memdup_user(buf, count);
+	if (IS_ERR(page)) {
+		length = PTR_ERR(page);
 		goto out;
-
-	length = -EFAULT;
-	if (copy_from_user(page, buf, count))
-		goto out_free;
+	}
 
 	/* Guard against adverse ptrace interaction */
 	length = mutex_lock_interruptible(&task->signal->cred_guard_mutex);
@@ -2390,10 +2393,10 @@
 
 	length = security_setprocattr(task,
 				      (char*)file->f_path.dentry->d_name.name,
-				      (void*)page, count);
+				      page, count);
 	mutex_unlock(&task->signal->cred_guard_mutex);
 out_free:
-	free_page((unsigned long) page);
+	kfree(page);
 out:
 	put_task_struct(task);
 out_no_task:
diff --git a/fs/proc/fd.c b/fs/proc/fd.c
index 3c2a915..56afa5e 100644
--- a/fs/proc/fd.c
+++ b/fs/proc/fd.c
@@ -258,6 +258,7 @@
 				     name, len, instantiate, p,
 				     (void *)(unsigned long)fd))
 			goto out_fd_loop;
+		cond_resched();
 		rcu_read_lock();
 	}
 	rcu_read_unlock();
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index bd95b9fd..d0e9b9b 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -393,24 +393,25 @@
 };
 #endif
 
-static const char *proc_follow_link(struct dentry *dentry, void **cookie)
-{
-	struct proc_dir_entry *pde = PDE(d_inode(dentry));
-	if (unlikely(!use_pde(pde)))
-		return ERR_PTR(-EINVAL);
-	*cookie = pde;
-	return pde->data;
-}
-
-static void proc_put_link(struct inode *unused, void *p)
+static void proc_put_link(void *p)
 {
 	unuse_pde(p);
 }
 
+static const char *proc_get_link(struct dentry *dentry,
+				 struct inode *inode,
+				 struct delayed_call *done)
+{
+	struct proc_dir_entry *pde = PDE(inode);
+	if (unlikely(!use_pde(pde)))
+		return ERR_PTR(-EINVAL);
+	set_delayed_call(done, proc_put_link, pde);
+	return pde->data;
+}
+
 const struct inode_operations proc_link_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= proc_follow_link,
-	.put_link	= proc_put_link,
+	.get_link	= proc_get_link,
 };
 
 struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index f6e8354..1dece878 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -30,14 +30,18 @@
 	&mntns_operations,
 };
 
-static const char *proc_ns_follow_link(struct dentry *dentry, void **cookie)
+static const char *proc_ns_get_link(struct dentry *dentry,
+				    struct inode *inode,
+				    struct delayed_call *done)
 {
-	struct inode *inode = d_inode(dentry);
 	const struct proc_ns_operations *ns_ops = PROC_I(inode)->ns_ops;
 	struct task_struct *task;
 	struct path ns_path;
 	void *error = ERR_PTR(-EACCES);
 
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+
 	task = get_proc_task(inode);
 	if (!task)
 		return error;
@@ -74,7 +78,7 @@
 
 static const struct inode_operations proc_ns_link_inode_operations = {
 	.readlink	= proc_ns_readlink,
-	.follow_link	= proc_ns_follow_link,
+	.get_link	= proc_ns_get_link,
 	.setattr	= proc_setattr,
 };
 
diff --git a/fs/proc/self.c b/fs/proc/self.c
index 113b8d0..67e8db4 100644
--- a/fs/proc/self.c
+++ b/fs/proc/self.c
@@ -18,26 +18,28 @@
 	return readlink_copy(buffer, buflen, tmp);
 }
 
-static const char *proc_self_follow_link(struct dentry *dentry, void **cookie)
+static const char *proc_self_get_link(struct dentry *dentry,
+				      struct inode *inode,
+				      struct delayed_call *done)
 {
-	struct pid_namespace *ns = dentry->d_sb->s_fs_info;
+	struct pid_namespace *ns = inode->i_sb->s_fs_info;
 	pid_t tgid = task_tgid_nr_ns(current, ns);
 	char *name;
 
 	if (!tgid)
 		return ERR_PTR(-ENOENT);
 	/* 11 for max length of signed int in decimal + NULL term */
-	name = kmalloc(12, GFP_KERNEL);
-	if (!name)
-		return ERR_PTR(-ENOMEM);
+	name = kmalloc(12, dentry ? GFP_KERNEL : GFP_ATOMIC);
+	if (unlikely(!name))
+		return dentry ? ERR_PTR(-ENOMEM) : ERR_PTR(-ECHILD);
 	sprintf(name, "%d", tgid);
-	return *cookie = name;
+	set_delayed_call(done, kfree_link, name);
+	return name;
 }
 
 static const struct inode_operations proc_self_inode_operations = {
 	.readlink	= proc_self_readlink,
-	.follow_link	= proc_self_follow_link,
-	.put_link	= kfree_put_link,
+	.get_link	= proc_self_get_link,
 };
 
 static unsigned self_inum;
diff --git a/fs/proc/thread_self.c b/fs/proc/thread_self.c
index 947b0f4..9eacd59 100644
--- a/fs/proc/thread_self.c
+++ b/fs/proc/thread_self.c
@@ -19,26 +19,29 @@
 	return readlink_copy(buffer, buflen, tmp);
 }
 
-static const char *proc_thread_self_follow_link(struct dentry *dentry, void **cookie)
+static const char *proc_thread_self_get_link(struct dentry *dentry,
+					     struct inode *inode,
+					     struct delayed_call *done)
 {
-	struct pid_namespace *ns = dentry->d_sb->s_fs_info;
+	struct pid_namespace *ns = inode->i_sb->s_fs_info;
 	pid_t tgid = task_tgid_nr_ns(current, ns);
 	pid_t pid = task_pid_nr_ns(current, ns);
 	char *name;
 
 	if (!pid)
 		return ERR_PTR(-ENOENT);
-	name = kmalloc(PROC_NUMBUF + 6 + PROC_NUMBUF, GFP_KERNEL);
-	if (!name)
-		return ERR_PTR(-ENOMEM);
+	name = kmalloc(PROC_NUMBUF + 6 + PROC_NUMBUF,
+				dentry ? GFP_KERNEL : GFP_ATOMIC);
+	if (unlikely(!name))
+		return dentry ? ERR_PTR(-ENOMEM) : ERR_PTR(-ECHILD);
 	sprintf(name, "%d/task/%d", tgid, pid);
-	return *cookie = name;
+	set_delayed_call(done, kfree_link, name);
+	return name;
 }
 
 static const struct inode_operations proc_thread_self_inode_operations = {
 	.readlink	= proc_thread_self_readlink,
-	.follow_link	= proc_thread_self_follow_link,
-	.put_link	= kfree_put_link,
+	.get_link	= proc_thread_self_get_link,
 };
 
 static unsigned thread_self_inum;
diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c
index 8ebd9a3..2256e7e 100644
--- a/fs/proc_namespace.c
+++ b/fs/proc_namespace.c
@@ -95,9 +95,9 @@
 {
 	struct proc_mounts *p = m->private;
 	struct mount *r = real_mount(mnt);
-	int err = 0;
 	struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt };
 	struct super_block *sb = mnt_path.dentry->d_sb;
+	int err;
 
 	if (sb->s_op->show_devname) {
 		err = sb->s_op->show_devname(m, mnt_path.dentry);
@@ -131,16 +131,17 @@
 	struct mount *r = real_mount(mnt);
 	struct super_block *sb = mnt->mnt_sb;
 	struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt };
-	int err = 0;
+	int err;
 
 	seq_printf(m, "%i %i %u:%u ", r->mnt_id, r->mnt_parent->mnt_id,
 		   MAJOR(sb->s_dev), MINOR(sb->s_dev));
-	if (sb->s_op->show_path)
+	if (sb->s_op->show_path) {
 		err = sb->s_op->show_path(m, mnt->mnt_root);
-	else
+		if (err)
+			goto out;
+	} else {
 		seq_dentry(m, mnt->mnt_root, " \t\n\\");
-	if (err)
-		goto out;
+	}
 	seq_putc(m, ' ');
 
 	/* mountpoints outside of chroot jail will give SEQ_SKIP on this */
@@ -168,12 +169,13 @@
 	seq_puts(m, " - ");
 	show_type(m, sb);
 	seq_putc(m, ' ');
-	if (sb->s_op->show_devname)
+	if (sb->s_op->show_devname) {
 		err = sb->s_op->show_devname(m, mnt->mnt_root);
-	else
+		if (err)
+			goto out;
+	} else {
 		mangle(m, r->mnt_devname ? r->mnt_devname : "none");
-	if (err)
-		goto out;
+	}
 	seq_puts(m, sb->s_flags & MS_RDONLY ? " ro" : " rw");
 	err = show_sb_opts(m, sb);
 	if (err)
@@ -191,7 +193,7 @@
 	struct mount *r = real_mount(mnt);
 	struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt };
 	struct super_block *sb = mnt_path.dentry->d_sb;
-	int err = 0;
+	int err;
 
 	/* device */
 	if (sb->s_op->show_devname) {
@@ -220,8 +222,7 @@
 	/* optional statistics */
 	if (sb->s_op->show_stats) {
 		seq_putc(m, ' ');
-		if (!err)
-			err = sb->s_op->show_stats(m, mnt_path.dentry);
+		err = sb->s_op->show_stats(m, mnt_path.dentry);
 	}
 
 	seq_putc(m, '\n');
diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c
index c4bcb77..f37b3de 100644
--- a/fs/qnx4/inode.c
+++ b/fs/qnx4/inode.c
@@ -316,6 +316,7 @@
 		inode->i_fop = &qnx4_dir_operations;
 	} else if (S_ISLNK(inode->i_mode)) {
 		inode->i_op = &page_symlink_inode_operations;
+		inode_nohighmem(inode);
 		inode->i_mapping->a_ops = &qnx4_aops;
 		qnx4_i(inode)->mmu_private = inode->i_size;
 	} else {
diff --git a/fs/qnx6/inode.c b/fs/qnx6/inode.c
index 32d2e1a..9728b54 100644
--- a/fs/qnx6/inode.c
+++ b/fs/qnx6/inode.c
@@ -582,6 +582,7 @@
 		inode->i_mapping->a_ops = &qnx6_aops;
 	} else if (S_ISLNK(inode->i_mode)) {
 		inode->i_op = &page_symlink_inode_operations;
+		inode_nohighmem(inode);
 		inode->i_mapping->a_ops = &qnx6_aops;
 	} else
 		init_special_inode(inode, inode->i_mode, 0);
diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c
index 889d558..38981b0 100644
--- a/fs/ramfs/inode.c
+++ b/fs/ramfs/inode.c
@@ -79,6 +79,7 @@
 			break;
 		case S_IFLNK:
 			inode->i_op = &page_symlink_inode_operations;
+			inode_nohighmem(inode);
 			break;
 		}
 	}
diff --git a/fs/read_write.c b/fs/read_write.c
index 819ef3f..06b07d5 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -16,6 +16,7 @@
 #include <linux/pagemap.h>
 #include <linux/splice.h>
 #include <linux/compat.h>
+#include <linux/mount.h>
 #include "internal.h"
 
 #include <asm/uaccess.h>
@@ -171,6 +172,45 @@
 EXPORT_SYMBOL(fixed_size_llseek);
 
 /**
+ * no_seek_end_llseek - llseek implementation for fixed-sized devices
+ * @file:	file structure to seek on
+ * @offset:	file offset to seek to
+ * @whence:	type of seek
+ *
+ */
+loff_t no_seek_end_llseek(struct file *file, loff_t offset, int whence)
+{
+	switch (whence) {
+	case SEEK_SET: case SEEK_CUR:
+		return generic_file_llseek_size(file, offset, whence,
+						~0ULL, 0);
+	default:
+		return -EINVAL;
+	}
+}
+EXPORT_SYMBOL(no_seek_end_llseek);
+
+/**
+ * no_seek_end_llseek_size - llseek implementation for fixed-sized devices
+ * @file:	file structure to seek on
+ * @offset:	file offset to seek to
+ * @whence:	type of seek
+ * @size:	maximal offset allowed
+ *
+ */
+loff_t no_seek_end_llseek_size(struct file *file, loff_t offset, int whence, loff_t size)
+{
+	switch (whence) {
+	case SEEK_SET: case SEEK_CUR:
+		return generic_file_llseek_size(file, offset, whence,
+						size, 0);
+	default:
+		return -EINVAL;
+	}
+}
+EXPORT_SYMBOL(no_seek_end_llseek_size);
+
+/**
  * noop_llseek - No Operation Performed llseek implementation
  * @file:	file structure to seek on
  * @offset:	file offset to seek to
@@ -395,9 +435,8 @@
 	}
 
 	if (unlikely(inode->i_flctx && mandatory_lock(inode))) {
-		retval = locks_mandatory_area(
-			read_write == READ ? FLOCK_VERIFY_READ : FLOCK_VERIFY_WRITE,
-			inode, file, pos, count);
+		retval = locks_mandatory_area(inode, file, pos, pos + count - 1,
+				read_write == READ ? F_RDLCK : F_WRLCK);
 		if (retval < 0)
 			return retval;
 	}
@@ -1327,3 +1366,299 @@
 	return do_sendfile(out_fd, in_fd, NULL, count, 0);
 }
 #endif
+
+/*
+ * copy_file_range() differs from regular file read and write in that it
+ * specifically allows return partial success.  When it does so is up to
+ * the copy_file_range method.
+ */
+ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
+			    struct file *file_out, loff_t pos_out,
+			    size_t len, unsigned int flags)
+{
+	struct inode *inode_in = file_inode(file_in);
+	struct inode *inode_out = file_inode(file_out);
+	ssize_t ret;
+
+	if (flags != 0)
+		return -EINVAL;
+
+	/* copy_file_range allows full ssize_t len, ignoring MAX_RW_COUNT  */
+	ret = rw_verify_area(READ, file_in, &pos_in, len);
+	if (ret >= 0)
+		ret = rw_verify_area(WRITE, file_out, &pos_out, len);
+	if (ret < 0)
+		return ret;
+
+	if (!(file_in->f_mode & FMODE_READ) ||
+	    !(file_out->f_mode & FMODE_WRITE) ||
+	    (file_out->f_flags & O_APPEND))
+		return -EBADF;
+
+	/* this could be relaxed once a method supports cross-fs copies */
+	if (inode_in->i_sb != inode_out->i_sb)
+		return -EXDEV;
+
+	if (len == 0)
+		return 0;
+
+	ret = mnt_want_write_file(file_out);
+	if (ret)
+		return ret;
+
+	ret = -EOPNOTSUPP;
+	if (file_out->f_op->copy_file_range)
+		ret = file_out->f_op->copy_file_range(file_in, pos_in, file_out,
+						      pos_out, len, flags);
+	if (ret == -EOPNOTSUPP)
+		ret = do_splice_direct(file_in, &pos_in, file_out, &pos_out,
+				len > MAX_RW_COUNT ? MAX_RW_COUNT : len, 0);
+
+	if (ret > 0) {
+		fsnotify_access(file_in);
+		add_rchar(current, ret);
+		fsnotify_modify(file_out);
+		add_wchar(current, ret);
+	}
+	inc_syscr(current);
+	inc_syscw(current);
+
+	mnt_drop_write_file(file_out);
+
+	return ret;
+}
+EXPORT_SYMBOL(vfs_copy_file_range);
+
+SYSCALL_DEFINE6(copy_file_range, int, fd_in, loff_t __user *, off_in,
+		int, fd_out, loff_t __user *, off_out,
+		size_t, len, unsigned int, flags)
+{
+	loff_t pos_in;
+	loff_t pos_out;
+	struct fd f_in;
+	struct fd f_out;
+	ssize_t ret = -EBADF;
+
+	f_in = fdget(fd_in);
+	if (!f_in.file)
+		goto out2;
+
+	f_out = fdget(fd_out);
+	if (!f_out.file)
+		goto out1;
+
+	ret = -EFAULT;
+	if (off_in) {
+		if (copy_from_user(&pos_in, off_in, sizeof(loff_t)))
+			goto out;
+	} else {
+		pos_in = f_in.file->f_pos;
+	}
+
+	if (off_out) {
+		if (copy_from_user(&pos_out, off_out, sizeof(loff_t)))
+			goto out;
+	} else {
+		pos_out = f_out.file->f_pos;
+	}
+
+	ret = vfs_copy_file_range(f_in.file, pos_in, f_out.file, pos_out, len,
+				  flags);
+	if (ret > 0) {
+		pos_in += ret;
+		pos_out += ret;
+
+		if (off_in) {
+			if (copy_to_user(off_in, &pos_in, sizeof(loff_t)))
+				ret = -EFAULT;
+		} else {
+			f_in.file->f_pos = pos_in;
+		}
+
+		if (off_out) {
+			if (copy_to_user(off_out, &pos_out, sizeof(loff_t)))
+				ret = -EFAULT;
+		} else {
+			f_out.file->f_pos = pos_out;
+		}
+	}
+
+out:
+	fdput(f_out);
+out1:
+	fdput(f_in);
+out2:
+	return ret;
+}
+
+static int clone_verify_area(struct file *file, loff_t pos, u64 len, bool write)
+{
+	struct inode *inode = file_inode(file);
+
+	if (unlikely(pos < 0))
+		return -EINVAL;
+
+	 if (unlikely((loff_t) (pos + len) < 0))
+		return -EINVAL;
+
+	if (unlikely(inode->i_flctx && mandatory_lock(inode))) {
+		loff_t end = len ? pos + len - 1 : OFFSET_MAX;
+		int retval;
+
+		retval = locks_mandatory_area(inode, file, pos, end,
+				write ? F_WRLCK : F_RDLCK);
+		if (retval < 0)
+			return retval;
+	}
+
+	return security_file_permission(file, write ? MAY_WRITE : MAY_READ);
+}
+
+int vfs_clone_file_range(struct file *file_in, loff_t pos_in,
+		struct file *file_out, loff_t pos_out, u64 len)
+{
+	struct inode *inode_in = file_inode(file_in);
+	struct inode *inode_out = file_inode(file_out);
+	int ret;
+
+	if (inode_in->i_sb != inode_out->i_sb ||
+	    file_in->f_path.mnt != file_out->f_path.mnt)
+		return -EXDEV;
+
+	if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
+		return -EISDIR;
+	if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
+		return -EINVAL;
+
+	if (!(file_in->f_mode & FMODE_READ) ||
+	    !(file_out->f_mode & FMODE_WRITE) ||
+	    (file_out->f_flags & O_APPEND) ||
+	    !file_in->f_op->clone_file_range)
+		return -EBADF;
+
+	ret = clone_verify_area(file_in, pos_in, len, false);
+	if (ret)
+		return ret;
+
+	ret = clone_verify_area(file_out, pos_out, len, true);
+	if (ret)
+		return ret;
+
+	if (pos_in + len > i_size_read(inode_in))
+		return -EINVAL;
+
+	ret = mnt_want_write_file(file_out);
+	if (ret)
+		return ret;
+
+	ret = file_in->f_op->clone_file_range(file_in, pos_in,
+			file_out, pos_out, len);
+	if (!ret) {
+		fsnotify_access(file_in);
+		fsnotify_modify(file_out);
+	}
+
+	mnt_drop_write_file(file_out);
+	return ret;
+}
+EXPORT_SYMBOL(vfs_clone_file_range);
+
+int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same)
+{
+	struct file_dedupe_range_info *info;
+	struct inode *src = file_inode(file);
+	u64 off;
+	u64 len;
+	int i;
+	int ret;
+	bool is_admin = capable(CAP_SYS_ADMIN);
+	u16 count = same->dest_count;
+	struct file *dst_file;
+	loff_t dst_off;
+	ssize_t deduped;
+
+	if (!(file->f_mode & FMODE_READ))
+		return -EINVAL;
+
+	if (same->reserved1 || same->reserved2)
+		return -EINVAL;
+
+	off = same->src_offset;
+	len = same->src_length;
+
+	ret = -EISDIR;
+	if (S_ISDIR(src->i_mode))
+		goto out;
+
+	ret = -EINVAL;
+	if (!S_ISREG(src->i_mode))
+		goto out;
+
+	ret = clone_verify_area(file, off, len, false);
+	if (ret < 0)
+		goto out;
+	ret = 0;
+
+	/* pre-format output fields to sane values */
+	for (i = 0; i < count; i++) {
+		same->info[i].bytes_deduped = 0ULL;
+		same->info[i].status = FILE_DEDUPE_RANGE_SAME;
+	}
+
+	for (i = 0, info = same->info; i < count; i++, info++) {
+		struct inode *dst;
+		struct fd dst_fd = fdget(info->dest_fd);
+
+		dst_file = dst_fd.file;
+		if (!dst_file) {
+			info->status = -EBADF;
+			goto next_loop;
+		}
+		dst = file_inode(dst_file);
+
+		ret = mnt_want_write_file(dst_file);
+		if (ret) {
+			info->status = ret;
+			goto next_loop;
+		}
+
+		dst_off = info->dest_offset;
+		ret = clone_verify_area(dst_file, dst_off, len, true);
+		if (ret < 0) {
+			info->status = ret;
+			goto next_file;
+		}
+		ret = 0;
+
+		if (info->reserved) {
+			info->status = -EINVAL;
+		} else if (!(is_admin || (dst_file->f_mode & FMODE_WRITE))) {
+			info->status = -EINVAL;
+		} else if (file->f_path.mnt != dst_file->f_path.mnt) {
+			info->status = -EXDEV;
+		} else if (S_ISDIR(dst->i_mode)) {
+			info->status = -EISDIR;
+		} else if (dst_file->f_op->dedupe_file_range == NULL) {
+			info->status = -EINVAL;
+		} else {
+			deduped = dst_file->f_op->dedupe_file_range(file, off,
+							len, dst_file,
+							info->dest_offset);
+			if (deduped == -EBADE)
+				info->status = FILE_DEDUPE_RANGE_DIFFERS;
+			else if (deduped < 0)
+				info->status = deduped;
+			else
+				info->bytes_deduped += deduped;
+		}
+
+next_file:
+		mnt_drop_write_file(dst_file);
+next_loop:
+		fdput(dst_fd);
+	}
+
+out:
+	return ret;
+}
+EXPORT_SYMBOL(vfs_dedupe_file_range);
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index 3d8e7e6..ae9e5b3 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -1361,6 +1361,7 @@
 		inode->i_fop = &reiserfs_dir_operations;
 	} else if (S_ISLNK(inode->i_mode)) {
 		inode->i_op = &reiserfs_symlink_inode_operations;
+		inode_nohighmem(inode);
 		inode->i_mapping->a_ops = &reiserfs_address_space_operations;
 	} else {
 		inode->i_blocks = 0;
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index 9d6486d..44c2bdc 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -618,12 +618,10 @@
 
 static void reiserfs_end_buffer_io_sync(struct buffer_head *bh, int uptodate)
 {
-	char b[BDEVNAME_SIZE];
-
 	if (buffer_journaled(bh)) {
 		reiserfs_warning(NULL, "clm-2084",
-				 "pinned buffer %lu:%s sent to disk",
-				 bh->b_blocknr, bdevname(bh->b_bdev, b));
+				 "pinned buffer %lu:%pg sent to disk",
+				 bh->b_blocknr, bh->b_bdev);
 	}
 	if (uptodate)
 		set_buffer_uptodate(bh);
@@ -2387,11 +2385,10 @@
 	int replay_count = 0;
 	int continue_replay = 1;
 	int ret;
-	char b[BDEVNAME_SIZE];
 
 	cur_dblock = SB_ONDISK_JOURNAL_1st_BLOCK(sb);
-	reiserfs_info(sb, "checking transaction log (%s)\n",
-		      bdevname(journal->j_dev_bd, b));
+	reiserfs_info(sb, "checking transaction log (%pg)\n",
+		      journal->j_dev_bd);
 	start = get_seconds();
 
 	/*
@@ -2651,8 +2648,8 @@
 
 	set_blocksize(journal->j_dev_bd, super->s_blocksize);
 	reiserfs_info(super,
-		      "journal_init_dev: journal device: %s\n",
-		      bdevname(journal->j_dev_bd, b));
+		      "journal_init_dev: journal device: %pg\n",
+		      journal->j_dev_bd);
 	return 0;
 }
 
@@ -2724,7 +2721,6 @@
 	struct reiserfs_journal_header *jh;
 	struct reiserfs_journal *journal;
 	struct reiserfs_journal_list *jl;
-	char b[BDEVNAME_SIZE];
 	int ret;
 
 	journal = SB_JOURNAL(sb) = vzalloc(sizeof(struct reiserfs_journal));
@@ -2794,10 +2790,10 @@
 	    && (le32_to_cpu(jh->jh_journal.jp_journal_magic) !=
 		sb_jp_journal_magic(rs))) {
 		reiserfs_warning(sb, "sh-460",
-				 "journal header magic %x (device %s) does "
+				 "journal header magic %x (device %pg) does "
 				 "not match to magic found in super block %x",
 				 jh->jh_journal.jp_journal_magic,
-				 bdevname(journal->j_dev_bd, b),
+				 journal->j_dev_bd,
 				 sb_jp_journal_magic(rs));
 		brelse(bhjh);
 		goto free_and_return;
@@ -2818,10 +2814,10 @@
 		journal->j_max_trans_age = commit_max_age;
 	}
 
-	reiserfs_info(sb, "journal params: device %s, size %u, "
+	reiserfs_info(sb, "journal params: device %pg, size %u, "
 		      "journal first block %u, max trans len %u, max batch %u, "
 		      "max commit age %u, max trans age %u\n",
-		      bdevname(journal->j_dev_bd, b),
+		      journal->j_dev_bd,
 		      SB_ONDISK_JOURNAL_SIZE(sb),
 		      SB_ONDISK_JOURNAL_1st_BLOCK(sb),
 		      journal->j_trans_max,
diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c
index 47f9698..2a12d46 100644
--- a/fs/reiserfs/namei.c
+++ b/fs/reiserfs/namei.c
@@ -1170,6 +1170,7 @@
 	reiserfs_update_inode_transaction(parent_dir);
 
 	inode->i_op = &reiserfs_symlink_inode_operations;
+	inode_nohighmem(inode);
 	inode->i_mapping->a_ops = &reiserfs_address_space_operations;
 
 	retval = reiserfs_add_entry(&th, parent_dir, dentry->d_name.name,
@@ -1664,8 +1665,7 @@
  */
 const struct inode_operations reiserfs_symlink_inode_operations = {
 	.readlink = generic_readlink,
-	.follow_link = page_follow_link_light,
-	.put_link = page_put_link,
+	.get_link	= page_get_link,
 	.setattr = reiserfs_setattr,
 	.setxattr = reiserfs_setxattr,
 	.getxattr = reiserfs_getxattr,
diff --git a/fs/reiserfs/prints.c b/fs/reiserfs/prints.c
index ae1dc84..4f3f928 100644
--- a/fs/reiserfs/prints.c
+++ b/fs/reiserfs/prints.c
@@ -139,11 +139,9 @@
 
 static void sprintf_buffer_head(char *buf, struct buffer_head *bh)
 {
-	char b[BDEVNAME_SIZE];
-
 	sprintf(buf,
-		"dev %s, size %zd, blocknr %llu, count %d, state 0x%lx, page %p, (%s, %s, %s)",
-		bdevname(bh->b_bdev, b), bh->b_size,
+		"dev %pg, size %zd, blocknr %llu, count %d, state 0x%lx, page %p, (%s, %s, %s)",
+		bh->b_bdev, bh->b_size,
 		(unsigned long long)bh->b_blocknr, atomic_read(&(bh->b_count)),
 		bh->b_state, bh->b_page,
 		buffer_uptodate(bh) ? "UPTODATE" : "!UPTODATE",
@@ -530,7 +528,6 @@
 	    (struct reiserfs_super_block *)(bh->b_data);
 	int skipped, data_blocks;
 	char *version;
-	char b[BDEVNAME_SIZE];
 
 	if (is_reiserfs_3_5(rs)) {
 		version = "3.5";
@@ -543,7 +540,7 @@
 		return 1;
 	}
 
-	printk("%s\'s super block is in block %llu\n", bdevname(bh->b_bdev, b),
+	printk("%pg\'s super block is in block %llu\n", bh->b_bdev,
 	       (unsigned long long)bh->b_blocknr);
 	printk("Reiserfs version %s\n", version);
 	printk("Block count %u\n", sb_block_count(rs));
diff --git a/fs/reiserfs/procfs.c b/fs/reiserfs/procfs.c
index 621b9f3..fe99915 100644
--- a/fs/reiserfs/procfs.c
+++ b/fs/reiserfs/procfs.c
@@ -303,11 +303,10 @@
 	struct reiserfs_sb_info *r = REISERFS_SB(sb);
 	struct reiserfs_super_block *rs = r->s_rs;
 	struct journal_params *jp = &rs->s_v1.s_journal;
-	char b[BDEVNAME_SIZE];
 
 	seq_printf(m,		/* on-disk fields */
 		   "jp_journal_1st_block: \t%i\n"
-		   "jp_journal_dev: \t%s[%x]\n"
+		   "jp_journal_dev: \t%pg[%x]\n"
 		   "jp_journal_size: \t%i\n"
 		   "jp_journal_trans_max: \t%i\n"
 		   "jp_journal_magic: \t%i\n"
@@ -348,7 +347,7 @@
 		   "prepare: \t%12lu\n"
 		   "prepare_retry: \t%12lu\n",
 		   DJP(jp_journal_1st_block),
-		   bdevname(SB_JOURNAL(sb)->j_dev_bd, b),
+		   SB_JOURNAL(sb)->j_dev_bd,
 		   DJP(jp_journal_dev),
 		   DJP(jp_journal_size),
 		   DJP(jp_journal_trans_max),
diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c
index 66b26fd..e5ddb4e 100644
--- a/fs/reiserfs/xattr.c
+++ b/fs/reiserfs/xattr.c
@@ -756,7 +756,8 @@
 		return NULL;
 
 	for_each_xattr_handler(handlers, xah) {
-		if (strncmp(xah->prefix, name, strlen(xah->prefix)) == 0)
+		const char *prefix = xattr_prefix(xah);
+		if (strncmp(prefix, name, strlen(prefix)) == 0)
 			break;
 	}
 
@@ -839,19 +840,16 @@
 
 		handler = find_xattr_handler_prefix(b->dentry->d_sb->s_xattr,
 						    name);
-		if (!handler)	/* Unsupported xattr name */
+		if (!handler /* Unsupported xattr name */ ||
+		    (handler->list && !handler->list(b->dentry)))
 			return 0;
+		size = namelen + 1;
 		if (b->buf) {
-			size = handler->list(handler, b->dentry,
-					     b->buf + b->pos, b->size, name,
-					     namelen);
 			if (size > b->size)
 				return -ERANGE;
-		} else {
-			size = handler->list(handler, b->dentry,
-					     NULL, 0, name, namelen);
+			memcpy(b->buf + b->pos, name, namelen);
+			b->buf[b->pos + namelen] = 0;
 		}
-
 		b->pos += size;
 	}
 	return 0;
diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c
index 4b34b9d..558a16b 100644
--- a/fs/reiserfs/xattr_acl.c
+++ b/fs/reiserfs/xattr_acl.c
@@ -186,10 +186,10 @@
 
 	switch (type) {
 	case ACL_TYPE_ACCESS:
-		name = POSIX_ACL_XATTR_ACCESS;
+		name = XATTR_NAME_POSIX_ACL_ACCESS;
 		break;
 	case ACL_TYPE_DEFAULT:
-		name = POSIX_ACL_XATTR_DEFAULT;
+		name = XATTR_NAME_POSIX_ACL_DEFAULT;
 		break;
 	default:
 		BUG();
@@ -244,7 +244,7 @@
 
 	switch (type) {
 	case ACL_TYPE_ACCESS:
-		name = POSIX_ACL_XATTR_ACCESS;
+		name = XATTR_NAME_POSIX_ACL_ACCESS;
 		if (acl) {
 			error = posix_acl_equiv_mode(acl, &inode->i_mode);
 			if (error < 0)
@@ -256,7 +256,7 @@
 		}
 		break;
 	case ACL_TYPE_DEFAULT:
-		name = POSIX_ACL_XATTR_DEFAULT;
+		name = XATTR_NAME_POSIX_ACL_DEFAULT;
 		if (!S_ISDIR(inode->i_mode))
 			return acl ? -EACCES : 0;
 		break;
diff --git a/fs/reiserfs/xattr_security.c b/fs/reiserfs/xattr_security.c
index ac659af..ab0217d 100644
--- a/fs/reiserfs/xattr_security.c
+++ b/fs/reiserfs/xattr_security.c
@@ -34,21 +34,9 @@
 	return reiserfs_xattr_set(d_inode(dentry), name, buffer, size, flags);
 }
 
-static size_t security_list(const struct xattr_handler *handler,
-			    struct dentry *dentry, char *list, size_t list_len,
-			    const char *name, size_t namelen)
+static bool security_list(struct dentry *dentry)
 {
-	const size_t len = namelen + 1;
-
-	if (IS_PRIVATE(d_inode(dentry)))
-		return 0;
-
-	if (list && len <= list_len) {
-		memcpy(list, name, namelen);
-		list[namelen] = '\0';
-	}
-
-	return len;
+	return !IS_PRIVATE(d_inode(dentry));
 }
 
 /* Initializes the security context for a new inode and returns the number
diff --git a/fs/reiserfs/xattr_trusted.c b/fs/reiserfs/xattr_trusted.c
index a338adf..64b67aa 100644
--- a/fs/reiserfs/xattr_trusted.c
+++ b/fs/reiserfs/xattr_trusted.c
@@ -33,20 +33,9 @@
 	return reiserfs_xattr_set(d_inode(dentry), name, buffer, size, flags);
 }
 
-static size_t trusted_list(const struct xattr_handler *handler,
-			   struct dentry *dentry, char *list, size_t list_size,
-			   const char *name, size_t name_len)
+static bool trusted_list(struct dentry *dentry)
 {
-	const size_t len = name_len + 1;
-
-	if (!capable(CAP_SYS_ADMIN) || IS_PRIVATE(d_inode(dentry)))
-		return 0;
-
-	if (list && len <= list_size) {
-		memcpy(list, name, name_len);
-		list[name_len] = '\0';
-	}
-	return len;
+	return capable(CAP_SYS_ADMIN) && !IS_PRIVATE(d_inode(dentry));
 }
 
 const struct xattr_handler reiserfs_xattr_trusted_handler = {
diff --git a/fs/reiserfs/xattr_user.c b/fs/reiserfs/xattr_user.c
index 39c9667..12e6306 100644
--- a/fs/reiserfs/xattr_user.c
+++ b/fs/reiserfs/xattr_user.c
@@ -30,19 +30,9 @@
 	return reiserfs_xattr_set(d_inode(dentry), name, buffer, size, flags);
 }
 
-static size_t user_list(const struct xattr_handler *handler,
-			struct dentry *dentry, char *list, size_t list_size,
-			const char *name, size_t name_len)
+static bool user_list(struct dentry *dentry)
 {
-	const size_t len = name_len + 1;
-
-	if (!reiserfs_xattrs_user(dentry->d_sb))
-		return 0;
-	if (list && len <= list_size) {
-		memcpy(list, name, name_len);
-		list[name_len] = '\0';
-	}
-	return len;
+	return reiserfs_xattrs_user(dentry->d_sb);
 }
 
 const struct xattr_handler reiserfs_xattr_user_handler = {
diff --git a/fs/romfs/super.c b/fs/romfs/super.c
index 268733c..bb894e7 100644
--- a/fs/romfs/super.c
+++ b/fs/romfs/super.c
@@ -360,6 +360,7 @@
 		break;
 	case ROMFH_SYM:
 		i->i_op = &page_symlink_inode_operations;
+		inode_nohighmem(i);
 		i->i_data.a_ops = &romfs_aops;
 		mode |= S_IRWXUGO;
 		break;
diff --git a/fs/select.c b/fs/select.c
index 0155473..79d0d49 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -778,8 +778,8 @@
 	return mask;
 }
 
-static int do_poll(unsigned int nfds,  struct poll_list *list,
-		   struct poll_wqueues *wait, struct timespec *end_time)
+static int do_poll(struct poll_list *list, struct poll_wqueues *wait,
+		   struct timespec *end_time)
 {
 	poll_table* pt = &wait->pt;
 	ktime_t expire, *to = NULL;
@@ -908,7 +908,7 @@
 	}
 
 	poll_initwait(&table);
-	fdcount = do_poll(nfds, head, &table, end_time);
+	fdcount = do_poll(head, &table, end_time);
 	poll_freewait(&table);
 
 	for (walk = head; walk; walk = walk->next) {
diff --git a/fs/splice.c b/fs/splice.c
index 4cf700d..82bc0d6 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -415,6 +415,7 @@
 			 */
 			if (!page->mapping) {
 				unlock_page(page);
+retry_lookup:
 				page = find_or_create_page(mapping, index,
 						mapping_gfp_mask(mapping));
 
@@ -439,13 +440,10 @@
 			error = mapping->a_ops->readpage(in, page);
 			if (unlikely(error)) {
 				/*
-				 * We really should re-lookup the page here,
-				 * but it complicates things a lot. Instead
-				 * lets just do what we already stored, and
-				 * we'll get it the next time we are called.
+				 * Re-lookup the page
 				 */
 				if (error == AOP_TRUNCATED_PAGE)
-					error = 0;
+					goto retry_lookup;
 
 				break;
 			}
diff --git a/fs/squashfs/inode.c b/fs/squashfs/inode.c
index a1ce5ce..0927b1e 100644
--- a/fs/squashfs/inode.c
+++ b/fs/squashfs/inode.c
@@ -41,6 +41,7 @@
 #include <linux/fs.h>
 #include <linux/vfs.h>
 #include <linux/xattr.h>
+#include <linux/pagemap.h>
 
 #include "squashfs_fs.h"
 #include "squashfs_fs_sb.h"
@@ -291,6 +292,7 @@
 		set_nlink(inode, le32_to_cpu(sqsh_ino->nlink));
 		inode->i_size = le32_to_cpu(sqsh_ino->symlink_size);
 		inode->i_op = &squashfs_symlink_inode_ops;
+		inode_nohighmem(inode);
 		inode->i_data.a_ops = &squashfs_symlink_aops;
 		inode->i_mode |= S_IFLNK;
 		squashfs_i(inode)->start = block;
diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c
index 5056bab..dded920 100644
--- a/fs/squashfs/super.c
+++ b/fs/squashfs/super.c
@@ -80,7 +80,6 @@
 {
 	struct squashfs_sb_info *msblk;
 	struct squashfs_super_block *sblk = NULL;
-	char b[BDEVNAME_SIZE];
 	struct inode *root;
 	long long root_inode;
 	unsigned short flags;
@@ -124,8 +123,8 @@
 	sb->s_magic = le32_to_cpu(sblk->s_magic);
 	if (sb->s_magic != SQUASHFS_MAGIC) {
 		if (!silent)
-			ERROR("Can't find a SQUASHFS superblock on %s\n",
-						bdevname(sb->s_bdev, b));
+			ERROR("Can't find a SQUASHFS superblock on %pg\n",
+						sb->s_bdev);
 		goto failed_mount;
 	}
 
@@ -178,7 +177,7 @@
 	msblk->inodes = le32_to_cpu(sblk->inodes);
 	flags = le16_to_cpu(sblk->flags);
 
-	TRACE("Found valid superblock on %s\n", bdevname(sb->s_bdev, b));
+	TRACE("Found valid superblock on %pg\n", sb->s_bdev);
 	TRACE("Inodes are %scompressed\n", SQUASHFS_UNCOMPRESSED_INODES(flags)
 				? "un" : "");
 	TRACE("Data is %scompressed\n", SQUASHFS_UNCOMPRESSED_DATA(flags)
diff --git a/fs/squashfs/symlink.c b/fs/squashfs/symlink.c
index 12806df..dbcc2f5 100644
--- a/fs/squashfs/symlink.c
+++ b/fs/squashfs/symlink.c
@@ -119,8 +119,7 @@
 
 const struct inode_operations squashfs_symlink_inode_ops = {
 	.readlink = generic_readlink,
-	.follow_link = page_follow_link_light,
-	.put_link = page_put_link,
+	.get_link = page_get_link,
 	.getxattr = generic_getxattr,
 	.listxattr = squashfs_listxattr
 };
diff --git a/fs/squashfs/xattr.c b/fs/squashfs/xattr.c
index 6a4cc34..1e9de96 100644
--- a/fs/squashfs/xattr.c
+++ b/fs/squashfs/xattr.c
@@ -58,7 +58,7 @@
 		struct squashfs_xattr_entry entry;
 		struct squashfs_xattr_val val;
 		const struct xattr_handler *handler;
-		int name_size, prefix_size = 0;
+		int name_size;
 
 		err = squashfs_read_metadata(sb, &entry, &start, &offset,
 							sizeof(entry));
@@ -67,15 +67,16 @@
 
 		name_size = le16_to_cpu(entry.size);
 		handler = squashfs_xattr_handler(le16_to_cpu(entry.type));
-		if (handler)
-			prefix_size = handler->list(handler, d, buffer, rest,
-						    NULL, name_size);
-		if (prefix_size) {
+		if (handler && (!handler->list || handler->list(d))) {
+			const char *prefix = handler->prefix ?: handler->name;
+			size_t prefix_size = strlen(prefix);
+
 			if (buffer) {
 				if (prefix_size + name_size + 1 > rest) {
 					err = -ERANGE;
 					goto failed;
 				}
+				memcpy(buffer, prefix, prefix_size);
 				buffer += prefix_size;
 			}
 			err = squashfs_read_metadata(sb, buffer, &start,
@@ -212,25 +213,10 @@
 }
 
 
-static size_t squashfs_xattr_handler_list(const struct xattr_handler *handler,
-					  struct dentry *d, char *list,
-					  size_t list_size, const char *name,
-					  size_t name_len)
-{
-	int len = strlen(handler->prefix);
-
-	if (list && len <= list_size)
-		memcpy(list, handler->prefix, len);
-	return len;
-}
-
 static int squashfs_xattr_handler_get(const struct xattr_handler *handler,
 				      struct dentry *d, const char *name,
 				      void *buffer, size_t size)
 {
-	if (name[0] == '\0')
-		return  -EINVAL;
-
 	return squashfs_xattr_get(d_inode(d), handler->flags, name,
 		buffer, size);
 }
@@ -241,22 +227,15 @@
 static const struct xattr_handler squashfs_xattr_user_handler = {
 	.prefix	= XATTR_USER_PREFIX,
 	.flags	= SQUASHFS_XATTR_USER,
-	.list	= squashfs_xattr_handler_list,
 	.get	= squashfs_xattr_handler_get
 };
 
 /*
  * Trusted namespace support
  */
-static size_t squashfs_trusted_xattr_handler_list(const struct xattr_handler *handler,
-						  struct dentry *d, char *list,
-						  size_t list_size, const char *name,
-						  size_t name_len)
+static bool squashfs_trusted_xattr_handler_list(struct dentry *d)
 {
-	if (!capable(CAP_SYS_ADMIN))
-		return 0;
-	return squashfs_xattr_handler_list(handler, d, list, list_size, name,
-					   name_len);
+	return capable(CAP_SYS_ADMIN);
 }
 
 static const struct xattr_handler squashfs_xattr_trusted_handler = {
@@ -272,7 +251,6 @@
 static const struct xattr_handler squashfs_xattr_security_handler = {
 	.prefix	= XATTR_SECURITY_PREFIX,
 	.flags	= SQUASHFS_XATTR_SECURITY,
-	.list	= squashfs_xattr_handler_list,
 	.get	= squashfs_xattr_handler_get
 };
 
diff --git a/fs/super.c b/fs/super.c
index 954aeb8..cc658a2 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -1012,10 +1012,8 @@
 		blkdev_put(bdev, mode);
 		down_write(&s->s_umount);
 	} else {
-		char b[BDEVNAME_SIZE];
-
 		s->s_mode = mode;
-		strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id));
+		snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev);
 		sb_set_blocksize(s, block_size(bdev));
 		error = fill_super(s, data, flags & MS_SILENT ? 1 : 0);
 		if (error) {
diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c
index 02fa1dc..07ac18c 100644
--- a/fs/sysv/inode.c
+++ b/fs/sysv/inode.c
@@ -146,8 +146,7 @@
 
 static const struct inode_operations sysv_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= page_follow_link_light,
-	.put_link	= page_put_link,
+	.get_link	= page_get_link,
 	.getattr	= sysv_getattr,
 };
 
@@ -163,6 +162,7 @@
 		inode->i_mapping->a_ops = &sysv_aops;
 	} else if (S_ISLNK(inode->i_mode)) {
 		inode->i_op = &sysv_symlink_inode_operations;
+		inode_nohighmem(inode);
 		inode->i_mapping->a_ops = &sysv_aops;
 	} else
 		init_special_inode(inode, inode->i_mode, rdev);
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index 0edc128..eff6280 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -1608,7 +1608,7 @@
 
 const struct inode_operations ubifs_symlink_inode_operations = {
 	.readlink    = generic_readlink,
-	.follow_link = simple_follow_link,
+	.get_link    = simple_get_link,
 	.setattr     = ubifs_setattr,
 	.getattr     = ubifs_getattr,
 	.setxattr    = ubifs_setxattr,
diff --git a/fs/ubifs/key.h b/fs/ubifs/key.h
index 92a8491..c0a95e3 100644
--- a/fs/ubifs/key.h
+++ b/fs/ubifs/key.h
@@ -34,6 +34,12 @@
  * node. We use "r5" hash borrowed from reiserfs.
  */
 
+/*
+ * Lot's of the key helpers require a struct ubifs_info *c as the first parameter.
+ * But we are not using it at all currently. That's designed for future extensions of
+ * different c->key_format. But right now, there is only one key type, UBIFS_SIMPLE_KEY_FMT.
+ */
+
 #ifndef __UBIFS_KEY_H__
 #define __UBIFS_KEY_H__
 
diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c
index e8b01b7..e53292d 100644
--- a/fs/ubifs/xattr.c
+++ b/fs/ubifs/xattr.c
@@ -267,7 +267,7 @@
 
 	if (!strncmp(nm->name, XATTR_TRUSTED_PREFIX,
 		     XATTR_TRUSTED_PREFIX_LEN)) {
-		if (nm->name[sizeof(XATTR_TRUSTED_PREFIX) - 1] == '\0')
+		if (nm->name[XATTR_TRUSTED_PREFIX_LEN] == '\0')
 			return -EINVAL;
 		type = TRUSTED_XATTR;
 	} else if (!strncmp(nm->name, XATTR_USER_PREFIX,
@@ -277,7 +277,7 @@
 		type = USER_XATTR;
 	} else if (!strncmp(nm->name, XATTR_SECURITY_PREFIX,
 				     XATTR_SECURITY_PREFIX_LEN)) {
-		if (nm->name[sizeof(XATTR_SECURITY_PREFIX) - 1] == '\0')
+		if (nm->name[XATTR_SECURITY_PREFIX_LEN] == '\0')
 			return -EINVAL;
 		type = SECURITY_XATTR;
 	} else
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 8d0b3ad..0557463 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -1540,7 +1540,8 @@
 		break;
 	case ICBTAG_FILE_TYPE_SYMLINK:
 		inode->i_data.a_ops = &udf_symlink_aops;
-		inode->i_op = &udf_symlink_inode_operations;
+		inode->i_op = &page_symlink_inode_operations;
+		inode_nohighmem(inode);
 		inode->i_mode = S_IFLNK | S_IRWXUGO;
 		break;
 	case ICBTAG_FILE_TYPE_MAIN:
diff --git a/fs/udf/namei.c b/fs/udf/namei.c
index c97b5a8..42eafb9 100644
--- a/fs/udf/namei.c
+++ b/fs/udf/namei.c
@@ -921,7 +921,8 @@
 	}
 
 	inode->i_data.a_ops = &udf_symlink_aops;
-	inode->i_op = &udf_symlink_inode_operations;
+	inode->i_op = &page_symlink_inode_operations;
+	inode_nohighmem(inode);
 
 	if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) {
 		struct kernel_lb_addr eloc;
@@ -1344,8 +1345,3 @@
 	.rename				= udf_rename,
 	.tmpfile			= udf_tmpfile,
 };
-const struct inode_operations udf_symlink_inode_operations = {
-	.readlink	= generic_readlink,
-	.follow_link	= page_follow_link_light,
-	.put_link	= page_put_link,
-};
diff --git a/fs/udf/symlink.c b/fs/udf/symlink.c
index 862535b..8d61977 100644
--- a/fs/udf/symlink.c
+++ b/fs/udf/symlink.c
@@ -107,7 +107,7 @@
 	struct buffer_head *bh = NULL;
 	unsigned char *symlink;
 	int err;
-	unsigned char *p = kmap(page);
+	unsigned char *p = page_address(page);
 	struct udf_inode_info *iinfo;
 	uint32_t pos;
 
@@ -141,7 +141,6 @@
 
 	up_read(&iinfo->i_data_sem);
 	SetPageUptodate(page);
-	kunmap(page);
 	unlock_page(page);
 	return 0;
 
@@ -149,7 +148,6 @@
 	up_read(&iinfo->i_data_sem);
 	SetPageError(page);
 out_unmap:
-	kunmap(page);
 	unlock_page(page);
 	return err;
 }
diff --git a/fs/udf/udfdecl.h b/fs/udf/udfdecl.h
index 47bb3f5..ce169b4 100644
--- a/fs/udf/udfdecl.h
+++ b/fs/udf/udfdecl.h
@@ -85,7 +85,6 @@
 extern const struct file_operations udf_dir_operations;
 extern const struct inode_operations udf_file_inode_operations;
 extern const struct file_operations udf_file_operations;
-extern const struct inode_operations udf_symlink_inode_operations;
 extern const struct address_space_operations udf_aops;
 extern const struct address_space_operations udf_adinicb_aops;
 extern const struct address_space_operations udf_symlink_aops;
diff --git a/fs/ufs/Makefile b/fs/ufs/Makefile
index 392db25..ec4a6b4 100644
--- a/fs/ufs/Makefile
+++ b/fs/ufs/Makefile
@@ -5,5 +5,5 @@
 obj-$(CONFIG_UFS_FS) += ufs.o
 
 ufs-objs := balloc.o cylinder.o dir.o file.o ialloc.o inode.o \
-	    namei.o super.o symlink.o util.o
+	    namei.o super.o util.o
 ccflags-$(CONFIG_UFS_DEBUG)    += -DDEBUG
diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c
index a064cf44..d897e16 100644
--- a/fs/ufs/inode.c
+++ b/fs/ufs/inode.c
@@ -528,11 +528,12 @@
 		inode->i_mapping->a_ops = &ufs_aops;
 	} else if (S_ISLNK(inode->i_mode)) {
 		if (!inode->i_blocks) {
-			inode->i_op = &ufs_fast_symlink_inode_operations;
 			inode->i_link = (char *)UFS_I(inode)->i_u1.i_symlink;
+			inode->i_op = &simple_symlink_inode_operations;
 		} else {
-			inode->i_op = &ufs_symlink_inode_operations;
 			inode->i_mapping->a_ops = &ufs_aops;
+			inode->i_op = &page_symlink_inode_operations;
+			inode_nohighmem(inode);
 		}
 	} else
 		init_special_inode(inode, inode->i_mode,
diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c
index 4796655..acf4a3b 100644
--- a/fs/ufs/namei.c
+++ b/fs/ufs/namei.c
@@ -123,14 +123,15 @@
 
 	if (l > UFS_SB(sb)->s_uspi->s_maxsymlinklen) {
 		/* slow symlink */
-		inode->i_op = &ufs_symlink_inode_operations;
+		inode->i_op = &page_symlink_inode_operations;
+		inode_nohighmem(inode);
 		inode->i_mapping->a_ops = &ufs_aops;
 		err = page_symlink(inode, symname, l);
 		if (err)
 			goto out_fail;
 	} else {
 		/* fast symlink */
-		inode->i_op = &ufs_fast_symlink_inode_operations;
+		inode->i_op = &simple_symlink_inode_operations;
 		inode->i_link = (char *)UFS_I(inode)->i_u1.i_symlink;
 		memcpy(inode->i_link, symname, l);
 		inode->i_size = l-1;
diff --git a/fs/ufs/symlink.c b/fs/ufs/symlink.c
deleted file mode 100644
index 874480b..0000000
--- a/fs/ufs/symlink.c
+++ /dev/null
@@ -1,42 +0,0 @@
-/*
- *  linux/fs/ufs/symlink.c
- *
- * Only fast symlinks left here - the rest is done by generic code. AV, 1999
- *
- * Copyright (C) 1998
- * Daniel Pirkl <daniel.pirkl@emai.cz>
- * Charles University, Faculty of Mathematics and Physics
- *
- *  from
- *
- *  linux/fs/ext2/symlink.c
- *
- * Copyright (C) 1992, 1993, 1994, 1995
- * Remy Card (card@masi.ibp.fr)
- * Laboratoire MASI - Institut Blaise Pascal
- * Universite Pierre et Marie Curie (Paris VI)
- *
- *  from
- *
- *  linux/fs/minix/symlink.c
- *
- *  Copyright (C) 1991, 1992  Linus Torvalds
- *
- *  ext2 symlink handling code
- */
-
-#include "ufs_fs.h"
-#include "ufs.h"
-
-const struct inode_operations ufs_fast_symlink_inode_operations = {
-	.readlink	= generic_readlink,
-	.follow_link	= simple_follow_link,
-	.setattr	= ufs_setattr,
-};
-
-const struct inode_operations ufs_symlink_inode_operations = {
-	.readlink	= generic_readlink,
-	.follow_link	= page_follow_link_light,
-	.put_link	= page_put_link,
-	.setattr	= ufs_setattr,
-};
diff --git a/fs/ufs/ufs.h b/fs/ufs/ufs.h
index 7da4aca..c87f4c3 100644
--- a/fs/ufs/ufs.h
+++ b/fs/ufs/ufs.h
@@ -136,10 +136,6 @@
 void ufs_panic(struct super_block *, const char *, const char *, ...);
 void ufs_mark_sb_dirty(struct super_block *sb);
 
-/* symlink.c */
-extern const struct inode_operations ufs_fast_symlink_inode_operations;
-extern const struct inode_operations ufs_symlink_inode_operations;
-
 static inline struct ufs_sb_info *UFS_SB(struct super_block *sb)
 {
 	return sb->s_fs_info;
diff --git a/fs/xattr.c b/fs/xattr.c
index 9b932b9..d5dd6c8 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -208,25 +208,6 @@
 	return error;
 }
 
-/* Compare an extended attribute value with the given value */
-int vfs_xattr_cmp(struct dentry *dentry, const char *xattr_name,
-		  const char *value, size_t size, gfp_t flags)
-{
-	char *xattr_value = NULL;
-	int rc;
-
-	rc = vfs_getxattr_alloc(dentry, xattr_name, &xattr_value, 0, flags);
-	if (rc < 0)
-		return rc;
-
-	if ((rc != size) || (memcmp(xattr_value, value, rc) != 0))
-		rc = -EINVAL;
-	else
-		rc = 0;
-	kfree(xattr_value);
-	return rc;
-}
-
 ssize_t
 vfs_getxattr(struct dentry *dentry, const char *name, void *value, size_t size)
 {
@@ -324,7 +305,6 @@
 {
 	int error;
 	void *kvalue = NULL;
-	void *vvalue = NULL;	/* If non-NULL, we used vmalloc() */
 	char kname[XATTR_NAME_MAX + 1];
 
 	if (flags & ~(XATTR_CREATE|XATTR_REPLACE))
@@ -341,10 +321,9 @@
 			return -E2BIG;
 		kvalue = kmalloc(size, GFP_KERNEL | __GFP_NOWARN);
 		if (!kvalue) {
-			vvalue = vmalloc(size);
-			if (!vvalue)
+			kvalue = vmalloc(size);
+			if (!kvalue)
 				return -ENOMEM;
-			kvalue = vvalue;
 		}
 		if (copy_from_user(kvalue, value, size)) {
 			error = -EFAULT;
@@ -357,10 +336,8 @@
 
 	error = vfs_setxattr(d, kname, kvalue, size, flags);
 out:
-	if (vvalue)
-		vfree(vvalue);
-	else
-		kfree(kvalue);
+	kvfree(kvalue);
+
 	return error;
 }
 
@@ -428,7 +405,6 @@
 {
 	ssize_t error;
 	void *kvalue = NULL;
-	void *vvalue = NULL;
 	char kname[XATTR_NAME_MAX + 1];
 
 	error = strncpy_from_user(kname, name, sizeof(kname));
@@ -442,10 +418,9 @@
 			size = XATTR_SIZE_MAX;
 		kvalue = kzalloc(size, GFP_KERNEL | __GFP_NOWARN);
 		if (!kvalue) {
-			vvalue = vmalloc(size);
-			if (!vvalue)
+			kvalue = vmalloc(size);
+			if (!kvalue)
 				return -ENOMEM;
-			kvalue = vvalue;
 		}
 	}
 
@@ -461,10 +436,9 @@
 		   than XATTR_SIZE_MAX bytes. Not possible. */
 		error = -E2BIG;
 	}
-	if (vvalue)
-		vfree(vvalue);
-	else
-		kfree(kvalue);
+
+	kvfree(kvalue);
+
 	return error;
 }
 
@@ -521,17 +495,15 @@
 {
 	ssize_t error;
 	char *klist = NULL;
-	char *vlist = NULL;	/* If non-NULL, we used vmalloc() */
 
 	if (size) {
 		if (size > XATTR_LIST_MAX)
 			size = XATTR_LIST_MAX;
 		klist = kmalloc(size, __GFP_NOWARN | GFP_KERNEL);
 		if (!klist) {
-			vlist = vmalloc(size);
-			if (!vlist)
+			klist = vmalloc(size);
+			if (!klist)
 				return -ENOMEM;
-			klist = vlist;
 		}
 	}
 
@@ -544,10 +516,9 @@
 		   than XATTR_LIST_MAX bytes. Not possible. */
 		error = -E2BIG;
 	}
-	if (vlist)
-		vfree(vlist);
-	else
-		kfree(klist);
+
+	kvfree(klist);
+
 	return error;
 }
 
@@ -700,13 +671,20 @@
 		return NULL;
 
 	for_each_xattr_handler(handlers, handler) {
-		const char *n = strcmp_prefix(*name, handler->prefix);
+		const char *n;
+
+		n = strcmp_prefix(*name, xattr_prefix(handler));
 		if (n) {
+			if (!handler->prefix ^ !*n) {
+				if (*n)
+					continue;
+				return ERR_PTR(-EINVAL);
+			}
 			*name = n;
-			break;
+			return handler;
 		}
 	}
-	return handler;
+	return ERR_PTR(-EOPNOTSUPP);
 }
 
 /*
@@ -718,8 +696,8 @@
 	const struct xattr_handler *handler;
 
 	handler = xattr_resolve_name(dentry->d_sb->s_xattr, &name);
-	if (!handler)
-		return -EOPNOTSUPP;
+	if (IS_ERR(handler))
+		return PTR_ERR(handler);
 	return handler->get(handler, dentry, name, buffer, size);
 }
 
@@ -735,19 +713,25 @@
 
 	if (!buffer) {
 		for_each_xattr_handler(handlers, handler) {
-			size += handler->list(handler, dentry, NULL, 0,
-					      NULL, 0);
+			if (!handler->name ||
+			    (handler->list && !handler->list(dentry)))
+				continue;
+			size += strlen(handler->name) + 1;
 		}
 	} else {
 		char *buf = buffer;
+		size_t len;
 
 		for_each_xattr_handler(handlers, handler) {
-			size = handler->list(handler, dentry, buf, buffer_size,
-					     NULL, 0);
-			if (size > buffer_size)
+			if (!handler->name ||
+			    (handler->list && !handler->list(dentry)))
+				continue;
+			len = strlen(handler->name);
+			if (len + 1 > buffer_size)
 				return -ERANGE;
-			buf += size;
-			buffer_size -= size;
+			memcpy(buf, handler->name, len + 1);
+			buf += len + 1;
+			buffer_size -= len + 1;
 		}
 		size = buf - buffer;
 	}
@@ -765,8 +749,8 @@
 	if (size == 0)
 		value = "";  /* empty EA, do not remove */
 	handler = xattr_resolve_name(dentry->d_sb->s_xattr, &name);
-	if (!handler)
-		return -EOPNOTSUPP;
+	if (IS_ERR(handler))
+		return PTR_ERR(handler);
 	return handler->set(handler, dentry, name, value, size, flags);
 }
 
@@ -780,8 +764,8 @@
 	const struct xattr_handler *handler;
 
 	handler = xattr_resolve_name(dentry->d_sb->s_xattr, &name);
-	if (!handler)
-		return -EOPNOTSUPP;
+	if (IS_ERR(handler))
+		return PTR_ERR(handler);
 	return handler->set(handler, dentry, name, NULL, 0, XATTR_REPLACE);
 }
 
@@ -808,7 +792,7 @@
 const char *xattr_full_name(const struct xattr_handler *handler,
 			    const char *name)
 {
-	size_t prefix_len = strlen(handler->prefix);
+	size_t prefix_len = strlen(xattr_prefix(handler));
 
 	return name - prefix_len;
 }
@@ -863,8 +847,22 @@
 	return ret;
 }
 
-static int __simple_xattr_set(struct simple_xattrs *xattrs, const char *name,
-			      const void *value, size_t size, int flags)
+/**
+ * simple_xattr_set - xattr SET operation for in-memory/pseudo filesystems
+ * @xattrs: target simple_xattr list
+ * @name: name of the extended attribute
+ * @value: value of the xattr. If %NULL, will remove the attribute.
+ * @size: size of the new xattr
+ * @flags: %XATTR_{CREATE|REPLACE}
+ *
+ * %XATTR_CREATE is set, the xattr shouldn't exist already; otherwise fails
+ * with -EEXIST.  If %XATTR_REPLACE is set, the xattr should exist;
+ * otherwise, fails with -ENODATA.
+ *
+ * Returns 0 on success, -errno on failure.
+ */
+int simple_xattr_set(struct simple_xattrs *xattrs, const char *name,
+		     const void *value, size_t size, int flags)
 {
 	struct simple_xattr *xattr;
 	struct simple_xattr *new_xattr = NULL;
@@ -914,73 +912,64 @@
 
 }
 
-/**
- * simple_xattr_set - xattr SET operation for in-memory/pseudo filesystems
- * @xattrs: target simple_xattr list
- * @name: name of the new extended attribute
- * @value: value of the new xattr. If %NULL, will remove the attribute
- * @size: size of the new xattr
- * @flags: %XATTR_{CREATE|REPLACE}
- *
- * %XATTR_CREATE is set, the xattr shouldn't exist already; otherwise fails
- * with -EEXIST.  If %XATTR_REPLACE is set, the xattr should exist;
- * otherwise, fails with -ENODATA.
- *
- * Returns 0 on success, -errno on failure.
- */
-int simple_xattr_set(struct simple_xattrs *xattrs, const char *name,
-		     const void *value, size_t size, int flags)
-{
-	if (size == 0)
-		value = ""; /* empty EA, do not remove */
-	return __simple_xattr_set(xattrs, name, value, size, flags);
-}
-
-/*
- * xattr REMOVE operation for in-memory/pseudo filesystems
- */
-int simple_xattr_remove(struct simple_xattrs *xattrs, const char *name)
-{
-	return __simple_xattr_set(xattrs, name, NULL, 0, XATTR_REPLACE);
-}
-
 static bool xattr_is_trusted(const char *name)
 {
 	return !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN);
 }
 
+static int xattr_list_one(char **buffer, ssize_t *remaining_size,
+			  const char *name)
+{
+	size_t len = strlen(name) + 1;
+	if (*buffer) {
+		if (*remaining_size < len)
+			return -ERANGE;
+		memcpy(*buffer, name, len);
+		*buffer += len;
+	}
+	*remaining_size -= len;
+	return 0;
+}
+
 /*
  * xattr LIST operation for in-memory/pseudo filesystems
  */
-ssize_t simple_xattr_list(struct simple_xattrs *xattrs, char *buffer,
-			  size_t size)
+ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs,
+			  char *buffer, size_t size)
 {
 	bool trusted = capable(CAP_SYS_ADMIN);
 	struct simple_xattr *xattr;
-	size_t used = 0;
+	ssize_t remaining_size = size;
+	int err;
+
+#ifdef CONFIG_FS_POSIX_ACL
+	if (inode->i_acl) {
+		err = xattr_list_one(&buffer, &remaining_size,
+				     XATTR_NAME_POSIX_ACL_ACCESS);
+		if (err)
+			return err;
+	}
+	if (inode->i_default_acl) {
+		err = xattr_list_one(&buffer, &remaining_size,
+				     XATTR_NAME_POSIX_ACL_DEFAULT);
+		if (err)
+			return err;
+	}
+#endif
 
 	spin_lock(&xattrs->lock);
 	list_for_each_entry(xattr, &xattrs->head, list) {
-		size_t len;
-
 		/* skip "trusted." attributes for unprivileged callers */
 		if (!trusted && xattr_is_trusted(xattr->name))
 			continue;
 
-		len = strlen(xattr->name) + 1;
-		used += len;
-		if (buffer) {
-			if (size < used) {
-				used = -ERANGE;
-				break;
-			}
-			memcpy(buffer, xattr->name, len);
-			buffer += len;
-		}
+		err = xattr_list_one(&buffer, &remaining_size, xattr->name);
+		if (err)
+			return err;
 	}
 	spin_unlock(&xattrs->lock);
 
-	return used;
+	return size - remaining_size;
 }
 
 /*
diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c
index 6bb470f..2d5df1f 100644
--- a/fs/xfs/xfs_acl.c
+++ b/fs/xfs/xfs_acl.c
@@ -252,29 +252,6 @@
 	return error;
 }
 
-static int
-xfs_acl_exists(struct inode *inode, unsigned char *name)
-{
-	int len = XFS_ACL_MAX_SIZE(XFS_M(inode->i_sb));
-
-	return (xfs_attr_get(XFS_I(inode), name, NULL, &len,
-			    ATTR_ROOT|ATTR_KERNOVAL) == 0);
-}
-
-int
-posix_acl_access_exists(struct inode *inode)
-{
-	return xfs_acl_exists(inode, SGI_ACL_FILE);
-}
-
-int
-posix_acl_default_exists(struct inode *inode)
-{
-	if (!S_ISDIR(inode->i_mode))
-		return 0;
-	return xfs_acl_exists(inode, SGI_ACL_DEFAULT);
-}
-
 int
 xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 {
diff --git a/fs/xfs/xfs_acl.h b/fs/xfs/xfs_acl.h
index 52f8255..286fa89 100644
--- a/fs/xfs/xfs_acl.h
+++ b/fs/xfs/xfs_acl.h
@@ -24,16 +24,12 @@
 #ifdef CONFIG_XFS_POSIX_ACL
 extern struct posix_acl *xfs_get_acl(struct inode *inode, int type);
 extern int xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type);
-extern int posix_acl_access_exists(struct inode *inode);
-extern int posix_acl_default_exists(struct inode *inode);
 #else
 static inline struct posix_acl *xfs_get_acl(struct inode *inode, int type)
 {
 	return NULL;
 }
 # define xfs_set_acl					NULL
-# define posix_acl_access_exists(inode)			0
-# define posix_acl_default_exists(inode)		0
 #endif /* CONFIG_XFS_POSIX_ACL */
 
 extern void xfs_forget_acl(struct inode *inode, const char *name, int xflags);
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 3243cdf..ace91e7 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -1632,13 +1632,9 @@
 	btp->bt_meta_sectormask = sectorsize - 1;
 
 	if (set_blocksize(btp->bt_bdev, sectorsize)) {
-		char name[BDEVNAME_SIZE];
-
-		bdevname(btp->bt_bdev, name);
-
 		xfs_warn(btp->bt_mount,
-			"Cannot set_blocksize to %u on device %s",
-			sectorsize, name);
+			"Cannot set_blocksize to %u on device %pg",
+			sectorsize, btp->bt_bdev);
 		return -EINVAL;
 	}
 
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 245268a..06eafaf 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -414,13 +414,17 @@
  * uio is kmalloced for this reason...
  */
 STATIC const char *
-xfs_vn_follow_link(
+xfs_vn_get_link(
 	struct dentry		*dentry,
-	void			**cookie)
+	struct inode		*inode,
+	struct delayed_call	*done)
 {
 	char			*link;
 	int			error = -ENOMEM;
 
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+
 	link = kmalloc(MAXPATHLEN+1, GFP_KERNEL);
 	if (!link)
 		goto out_err;
@@ -429,7 +433,8 @@
 	if (unlikely(error))
 		goto out_kfree;
 
-	return *cookie = link;
+	set_delayed_call(done, kfree_link, link);
+	return link;
 
  out_kfree:
 	kfree(link);
@@ -1172,8 +1177,7 @@
 
 static const struct inode_operations xfs_symlink_inode_operations = {
 	.readlink		= generic_readlink,
-	.follow_link		= xfs_vn_follow_link,
-	.put_link		= kfree_put_link,
+	.get_link		= xfs_vn_get_link,
 	.getattr		= xfs_vn_getattr,
 	.setattr		= xfs_vn_setattr,
 	.setxattr		= generic_setxattr,
diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c
index 839b35c..110f1d7 100644
--- a/fs/xfs/xfs_xattr.c
+++ b/fs/xfs/xfs_xattr.c
@@ -39,9 +39,6 @@
 	struct xfs_inode *ip = XFS_I(d_inode(dentry));
 	int error, asize = size;
 
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
-
 	/* Convert Linux syscall to XFS internal ATTR flags */
 	if (!size) {
 		xflags |= ATTR_KERNOVAL;
@@ -84,9 +81,6 @@
 	struct xfs_inode	*ip = XFS_I(d_inode(dentry));
 	int			error;
 
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
-
 	/* Convert Linux syscall to XFS internal ATTR flags */
 	if (flags & XATTR_CREATE)
 		xflags |= ATTR_CREATE;
@@ -135,24 +129,35 @@
 	NULL
 };
 
-static unsigned int xfs_xattr_prefix_len(int flags)
+static int
+__xfs_xattr_put_listent(
+	struct xfs_attr_list_context *context,
+	char *prefix,
+	int prefix_len,
+	unsigned char *name,
+	int namelen)
 {
-	if (flags & XFS_ATTR_SECURE)
-		return sizeof("security");
-	else if (flags & XFS_ATTR_ROOT)
-		return sizeof("trusted");
-	else
-		return sizeof("user");
-}
+	char *offset;
+	int arraytop;
 
-static const char *xfs_xattr_prefix(int flags)
-{
-	if (flags & XFS_ATTR_SECURE)
-		return xfs_xattr_security_handler.prefix;
-	else if (flags & XFS_ATTR_ROOT)
-		return xfs_xattr_trusted_handler.prefix;
-	else
-		return xfs_xattr_user_handler.prefix;
+	if (!context->alist)
+		goto compute_size;
+
+	arraytop = context->count + prefix_len + namelen + 1;
+	if (arraytop > context->firstu) {
+		context->count = -1;	/* insufficient space */
+		return 1;
+	}
+	offset = (char *)context->alist + context->count;
+	strncpy(offset, prefix, prefix_len);
+	offset += prefix_len;
+	strncpy(offset, (char *)name, namelen);			/* real name */
+	offset += namelen;
+	*offset = '\0';
+
+compute_size:
+	context->count += prefix_len + namelen + 1;
+	return 0;
 }
 
 static int
@@ -164,61 +169,55 @@
 	int		valuelen,
 	unsigned char	*value)
 {
-	unsigned int prefix_len = xfs_xattr_prefix_len(flags);
-	char *offset;
-	int arraytop;
+	char *prefix;
+	int prefix_len;
 
 	ASSERT(context->count >= 0);
 
-	/*
-	 * Only show root namespace entries if we are actually allowed to
-	 * see them.
-	 */
-	if ((flags & XFS_ATTR_ROOT) && !capable(CAP_SYS_ADMIN))
-		return 0;
+	if (flags & XFS_ATTR_ROOT) {
+#ifdef CONFIG_XFS_POSIX_ACL
+		if (namelen == SGI_ACL_FILE_SIZE &&
+		    strncmp(name, SGI_ACL_FILE,
+			    SGI_ACL_FILE_SIZE) == 0) {
+			int ret = __xfs_xattr_put_listent(
+					context, XATTR_SYSTEM_PREFIX,
+					XATTR_SYSTEM_PREFIX_LEN,
+					XATTR_POSIX_ACL_ACCESS,
+					strlen(XATTR_POSIX_ACL_ACCESS));
+			if (ret)
+				return ret;
+		} else if (namelen == SGI_ACL_DEFAULT_SIZE &&
+			 strncmp(name, SGI_ACL_DEFAULT,
+				 SGI_ACL_DEFAULT_SIZE) == 0) {
+			int ret = __xfs_xattr_put_listent(
+					context, XATTR_SYSTEM_PREFIX,
+					XATTR_SYSTEM_PREFIX_LEN,
+					XATTR_POSIX_ACL_DEFAULT,
+					strlen(XATTR_POSIX_ACL_DEFAULT));
+			if (ret)
+				return ret;
+		}
+#endif
 
-	arraytop = context->count + prefix_len + namelen + 1;
-	if (arraytop > context->firstu) {
-		context->count = -1;	/* insufficient space */
-		return 1;
+		/*
+		 * Only show root namespace entries if we are actually allowed to
+		 * see them.
+		 */
+		if (!capable(CAP_SYS_ADMIN))
+			return 0;
+
+		prefix = XATTR_TRUSTED_PREFIX;
+		prefix_len = XATTR_TRUSTED_PREFIX_LEN;
+	} else if (flags & XFS_ATTR_SECURE) {
+		prefix = XATTR_SECURITY_PREFIX;
+		prefix_len = XATTR_SECURITY_PREFIX_LEN;
+	} else {
+		prefix = XATTR_USER_PREFIX;
+		prefix_len = XATTR_USER_PREFIX_LEN;
 	}
-	offset = (char *)context->alist + context->count;
-	strncpy(offset, xfs_xattr_prefix(flags), prefix_len);
-	offset += prefix_len;
-	strncpy(offset, (char *)name, namelen);			/* real name */
-	offset += namelen;
-	*offset = '\0';
-	context->count += prefix_len + namelen + 1;
-	return 0;
-}
 
-static int
-xfs_xattr_put_listent_sizes(
-	struct xfs_attr_list_context *context,
-	int		flags,
-	unsigned char	*name,
-	int		namelen,
-	int		valuelen,
-	unsigned char	*value)
-{
-	context->count += xfs_xattr_prefix_len(flags) + namelen + 1;
-	return 0;
-}
-
-static int
-list_one_attr(const char *name, const size_t len, void *data,
-		size_t size, ssize_t *result)
-{
-	char *p = data + *result;
-
-	*result += len;
-	if (!size)
-		return 0;
-	if (*result > size)
-		return -ERANGE;
-
-	strcpy(p, name);
-	return 0;
+	return __xfs_xattr_put_listent(context, prefix, prefix_len, name,
+				       namelen);
 }
 
 ssize_t
@@ -227,7 +226,6 @@
 	struct xfs_attr_list_context context;
 	struct attrlist_cursor_kern cursor = { 0 };
 	struct inode		*inode = d_inode(dentry);
-	int			error;
 
 	/*
 	 * First read the regular on-disk attributes.
@@ -236,37 +234,14 @@
 	context.dp = XFS_I(inode);
 	context.cursor = &cursor;
 	context.resynch = 1;
-	context.alist = data;
+	context.alist = size ? data : NULL;
 	context.bufsize = size;
 	context.firstu = context.bufsize;
-
-	if (size)
-		context.put_listent = xfs_xattr_put_listent;
-	else
-		context.put_listent = xfs_xattr_put_listent_sizes;
+	context.put_listent = xfs_xattr_put_listent;
 
 	xfs_attr_list_int(&context);
 	if (context.count < 0)
 		return -ERANGE;
 
-	/*
-	 * Then add the two synthetic ACL attributes.
-	 */
-	if (posix_acl_access_exists(inode)) {
-		error = list_one_attr(POSIX_ACL_XATTR_ACCESS,
-				strlen(POSIX_ACL_XATTR_ACCESS) + 1,
-				data, size, &context.count);
-		if (error)
-			return error;
-	}
-
-	if (posix_acl_default_exists(inode)) {
-		error = list_one_attr(POSIX_ACL_XATTR_DEFAULT,
-				strlen(POSIX_ACL_XATTR_DEFAULT) + 1,
-				data, size, &context.count);
-		if (error)
-			return error;
-	}
-
 	return context.count;
 }
diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
index b42afad..0f45f93 100644
--- a/include/asm-generic/barrier.h
+++ b/include/asm-generic/barrier.h
@@ -93,7 +93,7 @@
 #endif	/* CONFIG_SMP */
 
 #ifndef smp_store_mb
-#define smp_store_mb(var, value)  do { WRITE_ONCE(var, value); mb(); } while (0)
+#define smp_store_mb(var, value)  do { WRITE_ONCE(var, value); smp_mb(); } while (0)
 #endif
 
 #ifndef smp_mb__before_atomic
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 14b0ff32..3a6803c 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -569,7 +569,7 @@
 }
 
 /*
- * untrack_pfn_vma is called while unmapping a pfnmap for a region.
+ * untrack_pfn is called while unmapping a pfnmap for a region.
  * untrack can be called for a specific region indicated by pfn and size or
  * can be for the entire vma (in which case pfn, size are zero).
  */
@@ -577,6 +577,13 @@
 			       unsigned long pfn, unsigned long size)
 {
 }
+
+/*
+ * untrack_pfn_moved is called while mremapping a pfnmap for a new region.
+ */
+static inline void untrack_pfn_moved(struct vm_area_struct *vma)
+{
+}
 #else
 extern int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
 			   unsigned long pfn, unsigned long addr,
@@ -586,6 +593,7 @@
 extern int track_pfn_copy(struct vm_area_struct *vma);
 extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
 			unsigned long size);
+extern void untrack_pfn_moved(struct vm_area_struct *vma);
 #endif
 
 #ifdef __HAVE_COLOR_ZERO_PAGE
diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h
index e2aadbc..39e1cb2 100644
--- a/include/asm-generic/qspinlock.h
+++ b/include/asm-generic/qspinlock.h
@@ -12,8 +12,9 @@
  * GNU General Public License for more details.
  *
  * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P.
+ * (C) Copyright 2015 Hewlett-Packard Enterprise Development LP
  *
- * Authors: Waiman Long <waiman.long@hp.com>
+ * Authors: Waiman Long <waiman.long@hpe.com>
  */
 #ifndef __ASM_GENERIC_QSPINLOCK_H
 #define __ASM_GENERIC_QSPINLOCK_H
@@ -62,7 +63,7 @@
 static __always_inline int queued_spin_trylock(struct qspinlock *lock)
 {
 	if (!atomic_read(&lock->val) &&
-	   (atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL) == 0))
+	   (atomic_cmpxchg_acquire(&lock->val, 0, _Q_LOCKED_VAL) == 0))
 		return 1;
 	return 0;
 }
@@ -77,7 +78,7 @@
 {
 	u32 val;
 
-	val = atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL);
+	val = atomic_cmpxchg_acquire(&lock->val, 0, _Q_LOCKED_VAL);
 	if (likely(val == 0))
 		return;
 	queued_spin_lock_slowpath(lock, val);
@@ -93,7 +94,7 @@
 	/*
 	 * smp_mb__before_atomic() in order to guarantee release semantics
 	 */
-	smp_mb__before_atomic_dec();
+	smp_mb__before_atomic();
 	atomic_sub(_Q_LOCKED_VAL, &lock->val);
 }
 #endif
diff --git a/include/clocksource/arm_arch_timer.h b/include/clocksource/arm_arch_timer.h
index 9916d0e..25d0914 100644
--- a/include/clocksource/arm_arch_timer.h
+++ b/include/clocksource/arm_arch_timer.h
@@ -23,6 +23,12 @@
 #define ARCH_TIMER_CTRL_IT_MASK		(1 << 1)
 #define ARCH_TIMER_CTRL_IT_STAT		(1 << 2)
 
+#define CNTHCTL_EL1PCTEN		(1 << 0)
+#define CNTHCTL_EL1PCEN			(1 << 1)
+#define CNTHCTL_EVNTEN			(1 << 2)
+#define CNTHCTL_EVNTDIR			(1 << 3)
+#define CNTHCTL_EVNTI			(0xF << 4)
+
 enum arch_timer_reg {
 	ARCH_TIMER_REG_CTRL,
 	ARCH_TIMER_REG_TVAL,
diff --git a/include/crypto/aead.h b/include/crypto/aead.h
index 077cae1..84d13b1 100644
--- a/include/crypto/aead.h
+++ b/include/crypto/aead.h
@@ -128,6 +128,7 @@
  * @exit: Deinitialize the cryptographic transformation object. This is a
  *	  counterpart to @init, used to remove various changes set in
  *	  @init.
+ * @base: Definition of a generic crypto cipher algorithm.
  *
  * All fields except @ivsize is mandatory and must be filled.
  */
diff --git a/include/crypto/akcipher.h b/include/crypto/akcipher.h
index 45cd5b3..354de15 100644
--- a/include/crypto/akcipher.h
+++ b/include/crypto/akcipher.h
@@ -21,9 +21,9 @@
  * @src:	Source data
  * @dst:	Destination data
  * @src_len:	Size of the input buffer
- * @dst_len:	Size of the output buffer. It needs to be at leaset
+ * @dst_len:	Size of the output buffer. It needs to be at least
  *		as big as the expected result depending	on the operation
- *		After operation it will be updated with the acctual size of the
+ *		After operation it will be updated with the actual size of the
  *		result.
  *		In case of error where the dst sgl size was insufficient,
  *		it will be updated to the size required for the operation.
@@ -59,7 +59,7 @@
  *		algorithm. In case of error, where the dst_len was insufficient,
  *		the req->dst_len will be updated to the size required for the
  *		operation
- * @encrypt:	Function performs an encrytp operation as defined by public key
+ * @encrypt:	Function performs an encrypt operation as defined by public key
  *		algorithm. In case of error, where the dst_len was insufficient,
  *		the req->dst_len will be updated to the size required for the
  *		operation
@@ -73,7 +73,7 @@
  * @set_priv_key: Function invokes the algorithm specific set private key
  *		function, which knows how to decode and interpret
  *		the BER encoded private key
- * @max_size:	Function returns dest buffer size reqired for a given key.
+ * @max_size:	Function returns dest buffer size required for a given key.
  * @init:	Initialize the cryptographic transformation object.
  *		This function is used to initialize the cryptographic
  *		transformation object. This function is called only once at
@@ -232,7 +232,7 @@
 }
 
 /**
- * akcipher_request_set_crypt() -- Sets reqest parameters
+ * akcipher_request_set_crypt() -- Sets request parameters
  *
  * Sets parameters required by crypto operation
  *
diff --git a/include/crypto/internal/akcipher.h b/include/crypto/internal/akcipher.h
index 9a2bda1..479a007 100644
--- a/include/crypto/internal/akcipher.h
+++ b/include/crypto/internal/akcipher.h
@@ -13,6 +13,22 @@
 #ifndef _CRYPTO_AKCIPHER_INT_H
 #define _CRYPTO_AKCIPHER_INT_H
 #include <crypto/akcipher.h>
+#include <crypto/algapi.h>
+
+struct akcipher_instance {
+	void (*free)(struct akcipher_instance *inst);
+	union {
+		struct {
+			char head[offsetof(struct akcipher_alg, base)];
+			struct crypto_instance base;
+		} s;
+		struct akcipher_alg alg;
+	};
+};
+
+struct crypto_akcipher_spawn {
+	struct crypto_spawn base;
+};
 
 /*
  * Transform internal helpers.
@@ -38,6 +54,56 @@
 	return crypto_akcipher_tfm(tfm)->__crt_alg->cra_name;
 }
 
+static inline struct crypto_instance *akcipher_crypto_instance(
+		struct akcipher_instance *inst)
+{
+	return container_of(&inst->alg.base, struct crypto_instance, alg);
+}
+
+static inline struct akcipher_instance *akcipher_instance(
+		struct crypto_instance *inst)
+{
+	return container_of(&inst->alg, struct akcipher_instance, alg.base);
+}
+
+static inline struct akcipher_instance *akcipher_alg_instance(
+		struct crypto_akcipher *akcipher)
+{
+	return akcipher_instance(crypto_tfm_alg_instance(&akcipher->base));
+}
+
+static inline void *akcipher_instance_ctx(struct akcipher_instance *inst)
+{
+	return crypto_instance_ctx(akcipher_crypto_instance(inst));
+}
+
+static inline void crypto_set_akcipher_spawn(
+		struct crypto_akcipher_spawn *spawn,
+		struct crypto_instance *inst)
+{
+	crypto_set_spawn(&spawn->base, inst);
+}
+
+int crypto_grab_akcipher(struct crypto_akcipher_spawn *spawn, const char *name,
+		u32 type, u32 mask);
+
+static inline struct crypto_akcipher *crypto_spawn_akcipher(
+		struct crypto_akcipher_spawn *spawn)
+{
+	return crypto_spawn_tfm2(&spawn->base);
+}
+
+static inline void crypto_drop_akcipher(struct crypto_akcipher_spawn *spawn)
+{
+	crypto_drop_spawn(&spawn->base);
+}
+
+static inline struct akcipher_alg *crypto_spawn_akcipher_alg(
+		struct crypto_akcipher_spawn *spawn)
+{
+	return container_of(spawn->base.alg, struct akcipher_alg, base);
+}
+
 /**
  * crypto_register_akcipher() -- Register public key algorithm
  *
@@ -57,4 +123,16 @@
  * @alg:	algorithm definition
  */
 void crypto_unregister_akcipher(struct akcipher_alg *alg);
+
+/**
+ * akcipher_register_instance() -- Unregister public key template instance
+ *
+ * Function registers an implementation of an asymmetric key algorithm
+ * created from a template
+ *
+ * @tmpl:	the template from which the algorithm was created
+ * @inst:	the template instance
+ */
+int akcipher_register_instance(struct crypto_template *tmpl,
+		struct akcipher_instance *inst);
 #endif
diff --git a/include/crypto/internal/rsa.h b/include/crypto/internal/rsa.h
index f997e2d..c7585bd 100644
--- a/include/crypto/internal/rsa.h
+++ b/include/crypto/internal/rsa.h
@@ -27,4 +27,6 @@
 		       unsigned int key_len);
 
 void rsa_free_key(struct rsa_key *rsa_key);
+
+extern struct crypto_template rsa_pkcs1pad_tmpl;
 #endif
diff --git a/include/crypto/md5.h b/include/crypto/md5.h
index 146af825..327deac 100644
--- a/include/crypto/md5.h
+++ b/include/crypto/md5.h
@@ -13,6 +13,8 @@
 #define MD5_H2	0x98badcfeUL
 #define MD5_H3	0x10325476UL
 
+extern const u8 md5_zero_message_hash[MD5_DIGEST_SIZE];
+
 struct md5_state {
 	u32 hash[MD5_HASH_WORDS];
 	u32 block[MD5_BLOCK_WORDS];
diff --git a/include/crypto/sha.h b/include/crypto/sha.h
index dd7905a..c94d3eb 100644
--- a/include/crypto/sha.h
+++ b/include/crypto/sha.h
@@ -64,6 +64,12 @@
 #define SHA512_H6	0x1f83d9abfb41bd6bULL
 #define SHA512_H7	0x5be0cd19137e2179ULL
 
+extern const u8 sha1_zero_message_hash[SHA1_DIGEST_SIZE];
+
+extern const u8 sha224_zero_message_hash[SHA224_DIGEST_SIZE];
+
+extern const u8 sha256_zero_message_hash[SHA256_DIGEST_SIZE];
+
 struct sha1_state {
 	u32 state[SHA1_DIGEST_SIZE / 4];
 	u64 count;
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index d2f4147..13a3d53 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -279,6 +279,12 @@
 	u32		vgic_lr[VGIC_V2_MAX_LRS];
 };
 
+/*
+ * LRs are stored in reverse order in memory. make sure we index them
+ * correctly.
+ */
+#define VGIC_V3_LR_INDEX(lr)		(VGIC_V3_MAX_LRS - 1 - lr)
+
 struct vgic_v3_cpu_if {
 #ifdef CONFIG_KVM_ARM_VGIC_V3
 	u32		vgic_hcr;
diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h
new file mode 100644
index 0000000..b5abfda
--- /dev/null
+++ b/include/linux/arm-smccc.h
@@ -0,0 +1,104 @@
+/*
+ * Copyright (c) 2015, Linaro Limited
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+#ifndef __LINUX_ARM_SMCCC_H
+#define __LINUX_ARM_SMCCC_H
+
+#include <linux/linkage.h>
+#include <linux/types.h>
+
+/*
+ * This file provides common defines for ARM SMC Calling Convention as
+ * specified in
+ * http://infocenter.arm.com/help/topic/com.arm.doc.den0028a/index.html
+ */
+
+#define ARM_SMCCC_STD_CALL		0
+#define ARM_SMCCC_FAST_CALL		1
+#define ARM_SMCCC_TYPE_SHIFT		31
+
+#define ARM_SMCCC_SMC_32		0
+#define ARM_SMCCC_SMC_64		1
+#define ARM_SMCCC_CALL_CONV_SHIFT	30
+
+#define ARM_SMCCC_OWNER_MASK		0x3F
+#define ARM_SMCCC_OWNER_SHIFT		24
+
+#define ARM_SMCCC_FUNC_MASK		0xFFFF
+
+#define ARM_SMCCC_IS_FAST_CALL(smc_val)	\
+	((smc_val) & (ARM_SMCCC_FAST_CALL << ARM_SMCCC_TYPE_SHIFT))
+#define ARM_SMCCC_IS_64(smc_val) \
+	((smc_val) & (ARM_SMCCC_SMC_64 << ARM_SMCCC_CALL_CONV_SHIFT))
+#define ARM_SMCCC_FUNC_NUM(smc_val)	((smc_val) & ARM_SMCCC_FUNC_MASK)
+#define ARM_SMCCC_OWNER_NUM(smc_val) \
+	(((smc_val) >> ARM_SMCCC_OWNER_SHIFT) & ARM_SMCCC_OWNER_MASK)
+
+#define ARM_SMCCC_CALL_VAL(type, calling_convention, owner, func_num) \
+	(((type) << ARM_SMCCC_TYPE_SHIFT) | \
+	((calling_convention) << ARM_SMCCC_CALL_CONV_SHIFT) | \
+	(((owner) & ARM_SMCCC_OWNER_MASK) << ARM_SMCCC_OWNER_SHIFT) | \
+	((func_num) & ARM_SMCCC_FUNC_MASK))
+
+#define ARM_SMCCC_OWNER_ARCH		0
+#define ARM_SMCCC_OWNER_CPU		1
+#define ARM_SMCCC_OWNER_SIP		2
+#define ARM_SMCCC_OWNER_OEM		3
+#define ARM_SMCCC_OWNER_STANDARD	4
+#define ARM_SMCCC_OWNER_TRUSTED_APP	48
+#define ARM_SMCCC_OWNER_TRUSTED_APP_END	49
+#define ARM_SMCCC_OWNER_TRUSTED_OS	50
+#define ARM_SMCCC_OWNER_TRUSTED_OS_END	63
+
+/**
+ * struct arm_smccc_res - Result from SMC/HVC call
+ * @a0-a3 result values from registers 0 to 3
+ */
+struct arm_smccc_res {
+	unsigned long a0;
+	unsigned long a1;
+	unsigned long a2;
+	unsigned long a3;
+};
+
+/**
+ * arm_smccc_smc() - make SMC calls
+ * @a0-a7: arguments passed in registers 0 to 7
+ * @res: result values from registers 0 to 3
+ *
+ * This function is used to make SMC calls following SMC Calling Convention.
+ * The content of the supplied param are copied to registers 0 to 7 prior
+ * to the SMC instruction. The return values are updated with the content
+ * from register 0 to 3 on return from the SMC instruction.
+ */
+asmlinkage void arm_smccc_smc(unsigned long a0, unsigned long a1,
+			unsigned long a2, unsigned long a3, unsigned long a4,
+			unsigned long a5, unsigned long a6, unsigned long a7,
+			struct arm_smccc_res *res);
+
+/**
+ * arm_smccc_hvc() - make HVC calls
+ * @a0-a7: arguments passed in registers 0 to 7
+ * @res: result values from registers 0 to 3
+ *
+ * This function is used to make HVC calls following SMC Calling
+ * Convention.  The content of the supplied param are copied to registers 0
+ * to 7 prior to the HVC instruction. The return values are updated with
+ * the content from register 0 to 3 on return from the HVC instruction.
+ */
+asmlinkage void arm_smccc_hvc(unsigned long a0, unsigned long a1,
+			unsigned long a2, unsigned long a3, unsigned long a4,
+			unsigned long a5, unsigned long a6, unsigned long a7,
+			struct arm_smccc_res *res);
+
+#endif /*__LINUX_ARM_SMCCC_H*/
diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h
index f589222..35b22f9 100644
--- a/include/linux/bootmem.h
+++ b/include/linux/bootmem.h
@@ -19,6 +19,10 @@
  * highest page
  */
 extern unsigned long max_pfn;
+/*
+ * highest possible page
+ */
+extern unsigned long long max_possible_pfn;
 
 #ifndef CONFIG_NO_BOOTMEM
 /*
diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index 7784b59..6013021 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -62,12 +62,18 @@
  * @suspend:		suspend function for the clocksource, if necessary
  * @resume:		resume function for the clocksource, if necessary
  * @owner:		module reference, must be set by clocksource in modules
+ *
+ * Note: This struct is not used in hotpathes of the timekeeping code
+ * because the timekeeper caches the hot path fields in its own data
+ * structure, so no line cache alignment is required,
+ *
+ * The pointer to the clocksource itself is handed to the read
+ * callback. If you need extra information there you can wrap struct
+ * clocksource into your own struct. Depending on the amount of
+ * information you need you should consider to cache line align that
+ * structure.
  */
 struct clocksource {
-	/*
-	 * Hotpath data, fits in a single cache line when the
-	 * clocksource itself is cacheline aligned.
-	 */
 	cycle_t (*read)(struct clocksource *cs);
 	cycle_t mask;
 	u32 mult;
@@ -95,7 +101,7 @@
 	cycle_t wd_last;
 #endif
 	struct module *owner;
-} ____cacheline_aligned;
+};
 
 /*
  * Clock source flags bits::
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 4dac103..00b042c 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -299,6 +299,23 @@
 	__u.__val;					\
 })
 
+/**
+ * smp_cond_acquire() - Spin wait for cond with ACQUIRE ordering
+ * @cond: boolean expression to wait for
+ *
+ * Equivalent to using smp_load_acquire() on the condition variable but employs
+ * the control dependency of the wait to reduce the barrier on many platforms.
+ *
+ * The control dependency provides a LOAD->STORE order, the additional RMB
+ * provides LOAD->LOAD order, together they provide LOAD->{LOAD,STORE} order,
+ * aka. ACQUIRE.
+ */
+#define smp_cond_acquire(cond)	do {		\
+	while (!(cond))				\
+		cpu_relax();			\
+	smp_rmb(); /* ctrl + rmb := acquire */	\
+} while (0)
+
 #endif /* __KERNEL__ */
 
 #endif /* __ASSEMBLY__ */
diff --git a/include/linux/component.h b/include/linux/component.h
index c00dcc3..a559eeb 100644
--- a/include/linux/component.h
+++ b/include/linux/component.h
@@ -1,39 +1,48 @@
 #ifndef COMPONENT_H
 #define COMPONENT_H
 
+#include <linux/stddef.h>
+
 struct device;
 
 struct component_ops {
-	int (*bind)(struct device *, struct device *, void *);
-	void (*unbind)(struct device *, struct device *, void *);
+	int (*bind)(struct device *comp, struct device *master,
+		    void *master_data);
+	void (*unbind)(struct device *comp, struct device *master,
+		       void *master_data);
 };
 
 int component_add(struct device *, const struct component_ops *);
 void component_del(struct device *, const struct component_ops *);
 
-int component_bind_all(struct device *, void *);
-void component_unbind_all(struct device *, void *);
+int component_bind_all(struct device *master, void *master_data);
+void component_unbind_all(struct device *master, void *master_data);
 
 struct master;
 
 struct component_master_ops {
-	int (*add_components)(struct device *, struct master *);
-	int (*bind)(struct device *);
-	void (*unbind)(struct device *);
+	int (*bind)(struct device *master);
+	void (*unbind)(struct device *master);
 };
 
-int component_master_add(struct device *, const struct component_master_ops *);
 void component_master_del(struct device *,
 	const struct component_master_ops *);
 
-int component_master_add_child(struct master *master,
-	int (*compare)(struct device *, void *), void *compare_data);
-
 struct component_match;
 
 int component_master_add_with_match(struct device *,
 	const struct component_master_ops *, struct component_match *);
-void component_match_add(struct device *, struct component_match **,
+void component_match_add_release(struct device *master,
+	struct component_match **matchptr,
+	void (*release)(struct device *, void *),
 	int (*compare)(struct device *, void *), void *compare_data);
 
+static inline void component_match_add(struct device *master,
+	struct component_match **matchptr,
+	int (*compare)(struct device *, void *), void *compare_data)
+{
+	component_match_add_release(master, matchptr, NULL, compare,
+				    compare_data);
+}
+
 #endif
diff --git a/include/linux/configfs.h b/include/linux/configfs.h
index 758a029..f7300d0 100644
--- a/include/linux/configfs.h
+++ b/include/linux/configfs.h
@@ -51,6 +51,7 @@
 struct configfs_item_operations;
 struct configfs_group_operations;
 struct configfs_attribute;
+struct configfs_bin_attribute;
 struct configfs_subsystem;
 
 struct config_item {
@@ -84,6 +85,7 @@
 	struct configfs_item_operations		*ct_item_ops;
 	struct configfs_group_operations	*ct_group_ops;
 	struct configfs_attribute		**ct_attrs;
+	struct configfs_bin_attribute		**ct_bin_attrs;
 };
 
 /**
@@ -154,6 +156,54 @@
 	.store		= _pfx##_name##_store,		\
 }
 
+struct file;
+struct vm_area_struct;
+
+struct configfs_bin_attribute {
+	struct configfs_attribute cb_attr;	/* std. attribute */
+	void *cb_private;			/* for user       */
+	size_t cb_max_size;			/* max core size  */
+	ssize_t (*read)(struct config_item *, void *, size_t);
+	ssize_t (*write)(struct config_item *, const void *, size_t);
+};
+
+#define CONFIGFS_BIN_ATTR(_pfx, _name, _priv, _maxsz)		\
+static struct configfs_bin_attribute _pfx##attr_##_name = {	\
+	.cb_attr = {						\
+		.ca_name	= __stringify(_name),		\
+		.ca_mode	= S_IRUGO | S_IWUSR,		\
+		.ca_owner	= THIS_MODULE,			\
+	},							\
+	.cb_private	= _priv,				\
+	.cb_max_size	= _maxsz,				\
+	.read		= _pfx##_name##_read,			\
+	.write		= _pfx##_name##_write,			\
+}
+
+#define CONFIGFS_BIN_ATTR_RO(_pfx, _name, _priv, _maxsz)	\
+static struct configfs_attribute _pfx##attr_##_name = {		\
+	.cb_attr = {						\
+		.ca_name	= __stringify(_name),		\
+		.ca_mode	= S_IRUGO,			\
+		.ca_owner	= THIS_MODULE,			\
+	},							\
+	.cb_private	= _priv,				\
+	.cb_max_size	= _maxsz,				\
+	.read		= _pfx##_name##_read,			\
+}
+
+#define CONFIGFS_BIN_ATTR_WO(_pfx, _name, _priv, _maxsz)	\
+static struct configfs_attribute _pfx##attr_##_name = {		\
+	.cb_attr = {						\
+		.ca_name	= __stringify(_name),		\
+		.ca_mode	= S_IWUSR,			\
+		.ca_owner	= THIS_MODULE,			\
+	},							\
+	.cb_private	= _priv,				\
+	.cb_max_size	= _maxsz,				\
+	.write		= _pfx##_name##_write,			\
+}
+
 /*
  * If allow_link() exists, the item can symlink(2) out to other
  * items.  If the item is a group, it may support mkdir(2).
diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h
index 68b575a..d259274 100644
--- a/include/linux/context_tracking.h
+++ b/include/linux/context_tracking.h
@@ -86,7 +86,7 @@
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
 static inline void guest_enter(void)
 {
-	if (vtime_accounting_enabled())
+	if (vtime_accounting_cpu_enabled())
 		vtime_guest_enter(current);
 	else
 		current->flags |= PF_VCPU;
@@ -100,7 +100,7 @@
 	if (context_tracking_is_enabled())
 		__context_tracking_exit(CONTEXT_GUEST);
 
-	if (vtime_accounting_enabled())
+	if (vtime_accounting_cpu_enabled())
 		vtime_guest_exit(current);
 	else
 		current->flags &= ~PF_VCPU;
diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h
index ee956c5..1d34fe6 100644
--- a/include/linux/context_tracking_state.h
+++ b/include/linux/context_tracking_state.h
@@ -22,12 +22,12 @@
 };
 
 #ifdef CONFIG_CONTEXT_TRACKING
-extern struct static_key context_tracking_enabled;
+extern struct static_key_false context_tracking_enabled;
 DECLARE_PER_CPU(struct context_tracking, context_tracking);
 
 static inline bool context_tracking_is_enabled(void)
 {
-	return static_key_false(&context_tracking_enabled);
+	return static_branch_unlikely(&context_tracking_enabled);
 }
 
 static inline bool context_tracking_cpu_is_enabled(void)
diff --git a/include/linux/delayed_call.h b/include/linux/delayed_call.h
new file mode 100644
index 0000000..f7fa76a
--- /dev/null
+++ b/include/linux/delayed_call.h
@@ -0,0 +1,34 @@
+#ifndef _DELAYED_CALL_H
+#define _DELAYED_CALL_H
+
+/*
+ * Poor man's closures; I wish we could've done them sanely polymorphic,
+ * but...
+ */
+
+struct delayed_call {
+	void (*fn)(void *);
+	void *arg;
+};
+
+#define DEFINE_DELAYED_CALL(name) struct delayed_call name = {NULL, NULL}
+
+/* I really wish we had closures with sane typechecking... */
+static inline void set_delayed_call(struct delayed_call *call,
+		void (*fn)(void *), void *arg)
+{
+	call->fn = fn;
+	call->arg = arg;
+}
+
+static inline void do_delayed_call(struct delayed_call *call)
+{
+	if (call->fn)
+		call->fn(call->arg);
+}
+
+static inline void clear_delayed_call(struct delayed_call *call)
+{
+	call->fn = NULL;
+}
+#endif
diff --git a/include/linux/edac.h b/include/linux/edac.h
index 4fe67b8..9e0d789 100644
--- a/include/linux/edac.h
+++ b/include/linux/edac.h
@@ -28,12 +28,10 @@
 extern int edac_op_state;
 extern int edac_err_assert;
 extern atomic_t edac_handlers;
-extern struct bus_type edac_subsys;
 
 extern int edac_handler_set(void);
 extern void edac_atomic_assert_error(void);
 extern struct bus_type *edac_get_sysfs_subsys(void);
-extern void edac_put_sysfs_subsys(void);
 
 enum {
 	EDAC_REPORTING_ENABLED,
@@ -237,8 +235,10 @@
 #define MEM_FLAG_FB_DDR2        BIT(MEM_FB_DDR2)
 #define MEM_FLAG_RDDR2          BIT(MEM_RDDR2)
 #define MEM_FLAG_XDR            BIT(MEM_XDR)
-#define MEM_FLAG_DDR3		 BIT(MEM_DDR3)
-#define MEM_FLAG_RDDR3		 BIT(MEM_RDDR3)
+#define MEM_FLAG_DDR3           BIT(MEM_DDR3)
+#define MEM_FLAG_RDDR3          BIT(MEM_RDDR3)
+#define MEM_FLAG_DDR4           BIT(MEM_DDR4)
+#define MEM_FLAG_RDDR4          BIT(MEM_RDDR4)
 
 /**
  * enum edac-type - Error Detection and Correction capabilities and mode
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 3aa5142..731262c 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -31,6 +31,7 @@
 #include <linux/blk_types.h>
 #include <linux/workqueue.h>
 #include <linux/percpu-rwsem.h>
+#include <linux/delayed_call.h>
 
 #include <asm/byteorder.h>
 #include <uapi/linux/fs.h>
@@ -1042,7 +1043,7 @@
 extern int fcntl_getlease(struct file *filp);
 
 /* fs/locks.c */
-void locks_free_lock_context(struct file_lock_context *ctx);
+void locks_free_lock_context(struct inode *inode);
 void locks_free_lock(struct file_lock *fl);
 extern void locks_init_lock(struct file_lock *);
 extern struct file_lock * locks_alloc_lock(void);
@@ -1103,7 +1104,7 @@
 }
 
 static inline void
-locks_free_lock_context(struct file_lock_context *ctx)
+locks_free_lock_context(struct inode *inode)
 {
 }
 
@@ -1629,16 +1630,21 @@
 #ifndef CONFIG_MMU
 	unsigned (*mmap_capabilities)(struct file *);
 #endif
+	ssize_t (*copy_file_range)(struct file *, loff_t, struct file *,
+			loff_t, size_t, unsigned int);
+	int (*clone_file_range)(struct file *, loff_t, struct file *, loff_t,
+			u64);
+	ssize_t (*dedupe_file_range)(struct file *, u64, u64, struct file *,
+			u64);
 };
 
 struct inode_operations {
 	struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
-	const char * (*follow_link) (struct dentry *, void **);
+	const char * (*get_link) (struct dentry *, struct inode *, struct delayed_call *);
 	int (*permission) (struct inode *, int);
 	struct posix_acl * (*get_acl)(struct inode *, int);
 
 	int (*readlink) (struct dentry *, char __user *,int);
-	void (*put_link) (struct inode *, void *);
 
 	int (*create) (struct inode *,struct dentry *, umode_t, bool);
 	int (*link) (struct dentry *,struct inode *,struct dentry *);
@@ -1680,6 +1686,12 @@
 		unsigned long, loff_t *);
 extern ssize_t vfs_writev(struct file *, const struct iovec __user *,
 		unsigned long, loff_t *);
+extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *,
+				   loff_t, size_t, unsigned int);
+extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in,
+		struct file *file_out, loff_t pos_out, u64 len);
+extern int vfs_dedupe_file_range(struct file *file,
+				 struct file_dedupe_range *same);
 
 struct super_operations {
    	struct inode *(*alloc_inode)(struct super_block *sb);
@@ -2027,12 +2039,9 @@
 
 #define MAX_RW_COUNT (INT_MAX & PAGE_CACHE_MASK)
 
-#define FLOCK_VERIFY_READ  1
-#define FLOCK_VERIFY_WRITE 2
-
-#ifdef CONFIG_FILE_LOCKING
+#ifdef CONFIG_MANDATORY_FILE_LOCKING
 extern int locks_mandatory_locked(struct file *);
-extern int locks_mandatory_area(int, struct inode *, struct file *, loff_t, size_t);
+extern int locks_mandatory_area(struct inode *, struct file *, loff_t, loff_t, unsigned char);
 
 /*
  * Candidates for mandatory locking have the setgid bit set
@@ -2062,19 +2071,59 @@
 }
 
 static inline int locks_verify_truncate(struct inode *inode,
-				    struct file *filp,
+				    struct file *f,
 				    loff_t size)
 {
-	if (inode->i_flctx && mandatory_lock(inode))
-		return locks_mandatory_area(
-			FLOCK_VERIFY_WRITE, inode, filp,
-			size < inode->i_size ? size : inode->i_size,
-			(size < inode->i_size ? inode->i_size - size
-			 : size - inode->i_size)
-		);
+	if (!inode->i_flctx || !mandatory_lock(inode))
+		return 0;
+
+	if (size < inode->i_size) {
+		return locks_mandatory_area(inode, f, size, inode->i_size - 1,
+				F_WRLCK);
+	} else {
+		return locks_mandatory_area(inode, f, inode->i_size, size - 1,
+				F_WRLCK);
+	}
+}
+
+#else /* !CONFIG_MANDATORY_FILE_LOCKING */
+
+static inline int locks_mandatory_locked(struct file *file)
+{
 	return 0;
 }
 
+static inline int locks_mandatory_area(struct inode *inode, struct file *filp,
+                                       loff_t start, loff_t end, unsigned char type)
+{
+	return 0;
+}
+
+static inline int __mandatory_lock(struct inode *inode)
+{
+	return 0;
+}
+
+static inline int mandatory_lock(struct inode *inode)
+{
+	return 0;
+}
+
+static inline int locks_verify_locked(struct file *file)
+{
+	return 0;
+}
+
+static inline int locks_verify_truncate(struct inode *inode, struct file *filp,
+					size_t size)
+{
+	return 0;
+}
+
+#endif /* CONFIG_MANDATORY_FILE_LOCKING */
+
+
+#ifdef CONFIG_FILE_LOCKING
 static inline int break_lease(struct inode *inode, unsigned int mode)
 {
 	/*
@@ -2136,39 +2185,6 @@
 }
 
 #else /* !CONFIG_FILE_LOCKING */
-static inline int locks_mandatory_locked(struct file *file)
-{
-	return 0;
-}
-
-static inline int locks_mandatory_area(int rw, struct inode *inode,
-				       struct file *filp, loff_t offset,
-				       size_t count)
-{
-	return 0;
-}
-
-static inline int __mandatory_lock(struct inode *inode)
-{
-	return 0;
-}
-
-static inline int mandatory_lock(struct inode *inode)
-{
-	return 0;
-}
-
-static inline int locks_verify_locked(struct file *file)
-{
-	return 0;
-}
-
-static inline int locks_verify_truncate(struct inode *inode, struct file *filp,
-					size_t size)
-{
-	return 0;
-}
-
 static inline int break_lease(struct inode *inode, unsigned int mode)
 {
 	return 0;
@@ -2291,9 +2307,9 @@
 {
 }
 
-static inline int sb_is_blkdev_sb(struct super_block *sb)
+static inline bool sb_is_blkdev_sb(struct super_block *sb)
 {
-	return 0;
+	return false;
 }
 #endif
 extern int sync_filesystem(struct super_block *);
@@ -2371,7 +2387,7 @@
 
 /* Invalid inode operations -- fs/bad_inode.c */
 extern void make_bad_inode(struct inode *);
-extern int is_bad_inode(struct inode *);
+extern bool is_bad_inode(struct inode *);
 
 #ifdef CONFIG_BLOCK
 /*
@@ -2532,8 +2548,8 @@
 extern struct file * open_exec(const char *);
  
 /* fs/dcache.c -- generic fs support functions */
-extern int is_subdir(struct dentry *, struct dentry *);
-extern int path_is_under(struct path *, struct path *);
+extern bool is_subdir(struct dentry *, struct dentry *);
+extern bool path_is_under(struct path *, struct path *);
 
 extern char *file_path(struct file *, char *, int);
 
@@ -2660,6 +2676,8 @@
 		int whence, loff_t maxsize, loff_t eof);
 extern loff_t fixed_size_llseek(struct file *file, loff_t offset,
 		int whence, loff_t size);
+extern loff_t no_seek_end_llseek_size(struct file *, loff_t, int, loff_t);
+extern loff_t no_seek_end_llseek(struct file *, loff_t, int);
 extern int generic_file_open(struct inode * inode, struct file * filp);
 extern int nonseekable_open(struct inode * inode, struct file * filp);
 
@@ -2736,14 +2754,14 @@
 
 extern int readlink_copy(char __user *, int, const char *);
 extern int page_readlink(struct dentry *, char __user *, int);
-extern const char *page_follow_link_light(struct dentry *, void **);
-extern void page_put_link(struct inode *, void *);
+extern const char *page_get_link(struct dentry *, struct inode *,
+				 struct delayed_call *);
+extern void page_put_link(void *);
 extern int __page_symlink(struct inode *inode, const char *symname, int len,
 		int nofs);
 extern int page_symlink(struct inode *inode, const char *symname, int len);
 extern const struct inode_operations page_symlink_inode_operations;
-extern void kfree_put_link(struct inode *, void *);
-extern void free_page_put_link(struct inode *, void *);
+extern void kfree_link(void *);
 extern int generic_readlink(struct dentry *, char __user *, int);
 extern void generic_fillattr(struct inode *, struct kstat *);
 int vfs_getattr_nosec(struct path *path, struct kstat *stat);
@@ -2754,7 +2772,8 @@
 void inode_sub_bytes(struct inode *inode, loff_t bytes);
 loff_t inode_get_bytes(struct inode *inode);
 void inode_set_bytes(struct inode *inode, loff_t bytes);
-const char *simple_follow_link(struct dentry *, void **);
+const char *simple_get_link(struct dentry *, struct inode *,
+			    struct delayed_call *);
 extern const struct inode_operations simple_symlink_inode_operations;
 
 extern int iterate_dir(struct file *, struct dir_context *);
@@ -2764,8 +2783,6 @@
 extern int vfs_fstat(unsigned int, struct kstat *);
 extern int vfs_fstatat(int , const char __user *, struct kstat *, int);
 
-extern int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
-		    unsigned long arg);
 extern int __generic_block_fiemap(struct inode *inode,
 				  struct fiemap_extent_info *fieinfo,
 				  loff_t start, loff_t len,
@@ -2963,7 +2980,7 @@
 #define OPEN_FMODE(flag) ((__force fmode_t)(((flag + 1) & O_ACCMODE) | \
 					    (flag & __FMODE_NONOTIFY)))
 
-static inline int is_sxid(umode_t mode)
+static inline bool is_sxid(umode_t mode)
 {
 	return (mode & S_ISUID) || ((mode & S_ISGID) && (mode & S_IXGRP));
 }
@@ -3025,5 +3042,6 @@
 }
 
 extern bool path_noexec(const struct path *path);
+extern void inode_nohighmem(struct inode *inode);
 
 #endif /* _LINUX_FS_H */
diff --git a/include/linux/fsl/edac.h b/include/linux/fsl/edac.h
new file mode 100644
index 0000000..90d64d4
--- /dev/null
+++ b/include/linux/fsl/edac.h
@@ -0,0 +1,8 @@
+#ifndef FSL_EDAC_H
+#define FSL_EDAC_H
+
+struct mpc85xx_edac_pci_plat_data {
+	struct device_node *of_node;
+};
+
+#endif
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index eae6548..60048c5 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -586,6 +586,7 @@
 
 extern int skip_trace(unsigned long ip);
 extern void ftrace_module_init(struct module *mod);
+extern void ftrace_release_mod(struct module *mod);
 
 extern void ftrace_disable_daemon(void);
 extern void ftrace_enable_daemon(void);
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 685c262..b0eb064 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -96,9 +96,7 @@
 				struct address_space *mapping,
 				pgoff_t idx, unsigned long address);
 
-#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE
 pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud);
-#endif
 
 extern int hugepages_treat_as_movable;
 extern int sysctl_hugetlb_shm_group;
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 1c1ff7e..f2cb8d4 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -150,7 +150,7 @@
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
 # define INIT_VTIME(tsk)						\
-	.vtime_seqlock = __SEQLOCK_UNLOCKED(tsk.vtime_seqlock),	\
+	.vtime_seqcount = SEQCNT_ZERO(tsk.vtime_seqcount),	\
 	.vtime_snap = 0,				\
 	.vtime_snap_whence = VTIME_SYS,
 #else
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index ad16809..cb30edb 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -195,6 +195,7 @@
 extern void disable_percpu_irq(unsigned int irq);
 extern void enable_irq(unsigned int irq);
 extern void enable_percpu_irq(unsigned int irq, unsigned int type);
+extern bool irq_percpu_is_enabled(unsigned int irq);
 extern void irq_wake_thread(unsigned int irq, void *dev_id);
 
 /* The following three functions are for the core kernel use only. */
diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h
index bae69e5..9c94026 100644
--- a/include/linux/irqchip/arm-gic.h
+++ b/include/linux/irqchip/arm-gic.h
@@ -103,10 +103,21 @@
 void gic_cascade_irq(unsigned int gic_nr, unsigned int irq);
 int gic_cpu_if_down(unsigned int gic_nr);
 
+/*
+ * Subdrivers that need some preparatory work can initialize their
+ * chips and call this to register their GICs.
+ */
+int gic_of_init(struct device_node *node, struct device_node *parent);
+
+/*
+ * Legacy platforms not converted to DT yet must use this to init
+ * their GIC
+ */
 void gic_init(unsigned int nr, int start,
 	      void __iomem *dist , void __iomem *cpu);
 
-int gicv2m_of_init(struct device_node *node, struct irq_domain *parent);
+int gicv2m_init(struct fwnode_handle *parent_handle,
+		struct irq_domain *parent);
 
 void gic_send_sgi(unsigned int cpu_id, unsigned int irq);
 int gic_get_cpu_id(unsigned int cpu);
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index a587a33..dcca77c 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -1,6 +1,8 @@
 #ifndef _LINUX_IRQDESC_H
 #define _LINUX_IRQDESC_H
 
+#include <linux/rcupdate.h>
+
 /*
  * Core internal functions to deal with irq descriptors
  */
@@ -40,6 +42,7 @@
  *			IRQF_NO_SUSPEND set
  * @force_resume_depth:	number of irqactions on a irq descriptor with
  *			IRQF_FORCE_RESUME set
+ * @rcu:		rcu head for delayed free
  * @dir:		/proc/irq/ procfs entry
  * @name:		flow handler name for /proc/interrupts output
  */
@@ -82,6 +85,9 @@
 #ifdef CONFIG_PROC_FS
 	struct proc_dir_entry	*dir;
 #endif
+#ifdef CONFIG_SPARSE_IRQ
+	struct rcu_head		rcu;
+#endif
 	int			parent_irq;
 	struct module		*owner;
 	const char		*name;
diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index d5e5c5b..f64622a 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -211,6 +211,11 @@
 	return node ? &node->fwnode : NULL;
 }
 
+static inline bool is_fwnode_irqchip(struct fwnode_handle *fwnode)
+{
+	return fwnode && fwnode->type == FWNODE_IRQCHIP;
+}
+
 static inline struct irq_domain *irq_find_matching_host(struct device_node *node,
 							enum irq_domain_bus_token bus_token)
 {
@@ -367,6 +372,9 @@
 	return __irq_domain_alloc_irqs(domain, -1, nr_irqs, node, arg, false);
 }
 
+extern int irq_domain_alloc_irqs_recursive(struct irq_domain *domain,
+					   unsigned int irq_base,
+					   unsigned int nr_irqs, void *arg);
 extern int irq_domain_set_hwirq_and_chip(struct irq_domain *domain,
 					 unsigned int virq,
 					 irq_hw_number_t hwirq,
@@ -410,6 +418,11 @@
 static inline void irq_dispose_mapping(unsigned int virq) { }
 static inline void irq_domain_activate_irq(struct irq_data *data) { }
 static inline void irq_domain_deactivate_irq(struct irq_data *data) { }
+static inline struct irq_domain *irq_find_matching_fwnode(
+	struct fwnode_handle *fwnode, enum irq_domain_bus_token bus_token)
+{
+	return NULL;
+}
 #endif /* !CONFIG_IRQ_DOMAIN */
 
 #endif /* _LINUX_IRQDOMAIN_H */
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 350dfb0..7311c32 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -255,6 +255,7 @@
 __printf(1, 2)
 void panic(const char *fmt, ...)
 	__noreturn __cold;
+void nmi_panic_self_stop(struct pt_regs *);
 extern void oops_enter(void);
 extern void oops_exit(void);
 void print_oops_end_marker(void);
@@ -446,6 +447,33 @@
 extern bool crash_kexec_post_notifiers;
 
 /*
+ * panic_cpu is used for synchronizing panic() and crash_kexec() execution. It
+ * holds a CPU number which is executing panic() currently. A value of
+ * PANIC_CPU_INVALID means no CPU has entered panic() or crash_kexec().
+ */
+extern atomic_t panic_cpu;
+#define PANIC_CPU_INVALID	-1
+
+/*
+ * A variant of panic() called from NMI context. We return if we've already
+ * panicked on this CPU. If another CPU already panicked, loop in
+ * nmi_panic_self_stop() which can provide architecture dependent code such
+ * as saving register state for crash dump.
+ */
+#define nmi_panic(regs, fmt, ...)					\
+do {									\
+	int old_cpu, cpu;						\
+									\
+	cpu = raw_smp_processor_id();					\
+	old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, cpu);	\
+									\
+	if (old_cpu == PANIC_CPU_INVALID)				\
+		panic(fmt, ##__VA_ARGS__);				\
+	else if (old_cpu != cpu)					\
+		nmi_panic_self_stop(regs);				\
+} while (0)
+
+/*
  * Only to be used by arch init code. If the user over-wrote the default
  * CONFIG_PANIC_TIMEOUT, honor it.
  */
diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index d140b1e..7b68d27 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -237,6 +237,7 @@
 					  unsigned int size, bool get_value);
 extern void *kexec_purgatory_get_symbol_addr(struct kimage *image,
 					     const char *name);
+extern void __crash_kexec(struct pt_regs *);
 extern void crash_kexec(struct pt_regs *);
 int kexec_should_crash(struct task_struct *);
 void crash_save_cpu(struct pt_regs *regs, int cpu);
@@ -332,6 +333,7 @@
 #else /* !CONFIG_KEXEC_CORE */
 struct pt_regs;
 struct task_struct;
+static inline void __crash_kexec(struct pt_regs *regs) { }
 static inline void crash_kexec(struct pt_regs *regs) { }
 static inline int kexec_should_crash(struct task_struct *p) { return 0; }
 #define kexec_in_progress false
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index c923350..f707f74 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -111,38 +111,13 @@
 }
 
 /*
- * vcpu->requests bit members
+ * Architecture-independent vcpu->requests bit members
+ * Bits 4-7 are reserved for more arch-independent bits.
  */
 #define KVM_REQ_TLB_FLUSH          0
-#define KVM_REQ_MIGRATE_TIMER      1
-#define KVM_REQ_REPORT_TPR_ACCESS  2
-#define KVM_REQ_MMU_RELOAD         3
-#define KVM_REQ_TRIPLE_FAULT       4
-#define KVM_REQ_PENDING_TIMER      5
-#define KVM_REQ_UNHALT             6
-#define KVM_REQ_MMU_SYNC           7
-#define KVM_REQ_CLOCK_UPDATE       8
-#define KVM_REQ_KICK               9
-#define KVM_REQ_DEACTIVATE_FPU    10
-#define KVM_REQ_EVENT             11
-#define KVM_REQ_APF_HALT          12
-#define KVM_REQ_STEAL_UPDATE      13
-#define KVM_REQ_NMI               14
-#define KVM_REQ_PMU               15
-#define KVM_REQ_PMI               16
-#define KVM_REQ_WATCHDOG          17
-#define KVM_REQ_MASTERCLOCK_UPDATE 18
-#define KVM_REQ_MCLOCK_INPROGRESS 19
-#define KVM_REQ_EPR_EXIT          20
-#define KVM_REQ_SCAN_IOAPIC       21
-#define KVM_REQ_GLOBAL_CLOCK_UPDATE 22
-#define KVM_REQ_ENABLE_IBS        23
-#define KVM_REQ_DISABLE_IBS       24
-#define KVM_REQ_APIC_PAGE_RELOAD  25
-#define KVM_REQ_SMI               26
-#define KVM_REQ_HV_CRASH          27
-#define KVM_REQ_IOAPIC_EOI_EXIT   28
-#define KVM_REQ_HV_RESET          29
+#define KVM_REQ_MMU_RELOAD         1
+#define KVM_REQ_PENDING_TIMER      2
+#define KVM_REQ_UNHALT             3
 
 #define KVM_USERSPACE_IRQ_SOURCE_ID		0
 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID	1
@@ -318,6 +293,11 @@
 	u32 adapter_id;
 };
 
+struct kvm_hv_sint {
+	u32 vcpu;
+	u32 sint;
+};
+
 struct kvm_kernel_irq_routing_entry {
 	u32 gsi;
 	u32 type;
@@ -331,6 +311,7 @@
 		} irqchip;
 		struct msi_msg msi;
 		struct kvm_s390_adapter_int adapter;
+		struct kvm_hv_sint hv_sint;
 	};
 	struct hlist_node link;
 };
@@ -439,10 +420,13 @@
 
 /* The guest did something we don't support. */
 #define vcpu_unimpl(vcpu, fmt, ...)					\
-	kvm_pr_unimpl("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__)
+	kvm_pr_unimpl("vcpu%i, guest rIP: 0x%lx " fmt,			\
+			(vcpu)->vcpu_id, kvm_rip_read(vcpu), ## __VA_ARGS__)
 
 #define vcpu_debug(vcpu, fmt, ...)					\
 	kvm_debug("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__)
+#define vcpu_err(vcpu, fmt, ...)					\
+	kvm_err("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__)
 
 static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i)
 {
@@ -465,6 +449,11 @@
 	struct kvm_vcpu *vcpu;
 	int i;
 
+	if (id < 0 || id >= KVM_MAX_VCPUS)
+		return NULL;
+	vcpu = kvm_get_vcpu(kvm, id);
+	if (vcpu && vcpu->vcpu_id == id)
+		return vcpu;
 	kvm_for_each_vcpu(i, vcpu, kvm)
 		if (vcpu->vcpu_id == id)
 			return vcpu;
@@ -484,12 +473,12 @@
 
 #ifdef __KVM_HAVE_IOAPIC
 void kvm_vcpu_request_scan_ioapic(struct kvm *kvm);
-void kvm_arch_irq_routing_update(struct kvm *kvm);
+void kvm_arch_post_irq_routing_update(struct kvm *kvm);
 #else
 static inline void kvm_vcpu_request_scan_ioapic(struct kvm *kvm)
 {
 }
-static inline void kvm_arch_irq_routing_update(struct kvm *kvm)
+static inline void kvm_arch_post_irq_routing_update(struct kvm *kvm)
 {
 }
 #endif
@@ -634,7 +623,7 @@
 int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len);
 int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len);
 struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn);
-int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn);
+bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn);
 unsigned long kvm_host_page_size(struct kvm *kvm, gfn_t gfn);
 void mark_page_dirty(struct kvm *kvm, gfn_t gfn);
 
@@ -668,8 +657,6 @@
 
 void kvm_flush_remote_tlbs(struct kvm *kvm);
 void kvm_reload_remote_mmus(struct kvm *kvm);
-void kvm_make_mclock_inprogress_request(struct kvm *kvm);
-void kvm_make_scan_ioapic_request(struct kvm *kvm);
 bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req);
 
 long kvm_arch_dev_ioctl(struct file *filp,
@@ -990,11 +977,6 @@
 	return kvm_is_error_hva(hva);
 }
 
-static inline void kvm_migrate_timers(struct kvm_vcpu *vcpu)
-{
-	set_bit(KVM_REQ_MIGRATE_TIMER, &vcpu->requests);
-}
-
 enum kvm_stat_kind {
 	KVM_STAT_VM,
 	KVM_STAT_VCPU,
@@ -1004,7 +986,6 @@
 	const char *name;
 	int offset;
 	enum kvm_stat_kind kind;
-	struct dentry *dentry;
 };
 extern struct kvm_stats_debugfs_item debugfs_entries[];
 extern struct dentry *kvm_debugfs_dir;
@@ -1091,6 +1072,7 @@
 {
 }
 #endif
+void kvm_arch_irq_routing_update(struct kvm *kvm);
 
 static inline int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 {
diff --git a/include/linux/kvm_para.h b/include/linux/kvm_para.h
index 00a97bb..35e568f 100644
--- a/include/linux/kvm_para.h
+++ b/include/linux/kvm_para.h
@@ -4,10 +4,8 @@
 #include <uapi/linux/kvm_para.h>
 
 
-static inline int kvm_para_has_feature(unsigned int feature)
+static inline bool kvm_para_has_feature(unsigned int feature)
 {
-	if (kvm_arch_para_features() & (1UL << feature))
-		return 1;
-	return 0;
+	return !!(kvm_arch_para_features() & (1UL << feature));
 }
 #endif /* __LINUX_KVM_PARA_H */
diff --git a/include/linux/leds.h b/include/linux/leds.h
index fa359c7..bc1476f 100644
--- a/include/linux/leds.h
+++ b/include/linux/leds.h
@@ -44,9 +44,9 @@
 #define LED_BLINK_ONESHOT	(1 << 17)
 #define LED_BLINK_ONESHOT_STOP	(1 << 18)
 #define LED_BLINK_INVERT	(1 << 19)
-#define LED_SYSFS_DISABLE	(1 << 20)
-#define SET_BRIGHTNESS_ASYNC	(1 << 21)
-#define SET_BRIGHTNESS_SYNC	(1 << 22)
+#define LED_BLINK_BRIGHTNESS_CHANGE (1 << 20)
+#define LED_BLINK_DISABLE	(1 << 21)
+#define LED_SYSFS_DISABLE	(1 << 22)
 #define LED_DEV_CAP_FLASH	(1 << 23)
 
 	/* Set LED brightness level */
@@ -57,8 +57,8 @@
 	 * Set LED brightness level immediately - it can block the caller for
 	 * the time required for accessing a LED device register.
 	 */
-	int		(*brightness_set_sync)(struct led_classdev *led_cdev,
-					enum led_brightness brightness);
+	int (*brightness_set_blocking)(struct led_classdev *led_cdev,
+				       enum led_brightness brightness);
 	/* Get LED brightness level */
 	enum led_brightness (*brightness_get)(struct led_classdev *led_cdev);
 
@@ -156,10 +156,25 @@
  *
  * Set an LED's brightness, and, if necessary, cancel the
  * software blink timer that implements blinking when the
- * hardware doesn't.
+ * hardware doesn't. This function is guaranteed not to sleep.
  */
 extern void led_set_brightness(struct led_classdev *led_cdev,
 			       enum led_brightness brightness);
+
+/**
+ * led_set_brightness_sync - set LED brightness synchronously
+ * @led_cdev: the LED to set
+ * @brightness: the brightness to set it to
+ *
+ * Set an LED's brightness immediately. This function will block
+ * the caller for the time required for accessing device registers,
+ * and it can sleep.
+ *
+ * Returns: 0 on success or negative error value on failure
+ */
+extern int led_set_brightness_sync(struct led_classdev *led_cdev,
+				   enum led_brightness value);
+
 /**
  * led_update_brightness - update LED brightness
  * @led_cdev: the LED to query
@@ -231,6 +246,8 @@
 /* Registration functions for complex triggers */
 extern int led_trigger_register(struct led_trigger *trigger);
 extern void led_trigger_unregister(struct led_trigger *trigger);
+extern int devm_led_trigger_register(struct device *dev,
+				     struct led_trigger *trigger);
 
 extern void led_trigger_register_simple(const char *name,
 				struct led_trigger **trigger);
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 600c1e0..851821b 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -205,6 +205,7 @@
 	ATA_LFLAG_NO_LPM	= (1 << 8), /* disable LPM on this link */
 	ATA_LFLAG_RST_ONCE	= (1 << 9), /* limit recovery to one reset */
 	ATA_LFLAG_CHANGED	= (1 << 10), /* LPM state changed on this link */
+	ATA_LFLAG_NO_DB_DELAY	= (1 << 11), /* no debounce delay on link resume */
 
 	/* struct ata_port flags */
 	ATA_FLAG_SLAVE_POSS	= (1 << 0), /* host supports slave dev */
diff --git a/include/linux/list.h b/include/linux/list.h
index 993395a..5356f4d 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -24,7 +24,7 @@
 
 static inline void INIT_LIST_HEAD(struct list_head *list)
 {
-	list->next = list;
+	WRITE_ONCE(list->next, list);
 	list->prev = list;
 }
 
@@ -42,7 +42,7 @@
 	next->prev = new;
 	new->next = next;
 	new->prev = prev;
-	prev->next = new;
+	WRITE_ONCE(prev->next, new);
 }
 #else
 extern void __list_add(struct list_head *new,
@@ -186,7 +186,7 @@
  */
 static inline int list_empty(const struct list_head *head)
 {
-	return head->next == head;
+	return READ_ONCE(head->next) == head;
 }
 
 /**
@@ -608,7 +608,7 @@
 
 static inline int hlist_empty(const struct hlist_head *h)
 {
-	return !h->first;
+	return !READ_ONCE(h->first);
 }
 
 static inline void __hlist_del(struct hlist_node *n)
@@ -642,7 +642,7 @@
 	n->next = first;
 	if (first)
 		first->pprev = &n->next;
-	h->first = n;
+	WRITE_ONCE(h->first, n);
 	n->pprev = &h->first;
 }
 
@@ -653,14 +653,14 @@
 	n->pprev = next->pprev;
 	n->next = next;
 	next->pprev = &n->next;
-	*(n->pprev) = n;
+	WRITE_ONCE(*(n->pprev), n);
 }
 
 static inline void hlist_add_behind(struct hlist_node *n,
 				    struct hlist_node *prev)
 {
 	n->next = prev->next;
-	prev->next = n;
+	WRITE_ONCE(prev->next, n);
 	n->pprev = &prev->next;
 
 	if (n->next)
diff --git a/include/linux/list_bl.h b/include/linux/list_bl.h
index 8132214..ee7229a 100644
--- a/include/linux/list_bl.h
+++ b/include/linux/list_bl.h
@@ -70,7 +70,7 @@
 
 static inline int hlist_bl_empty(const struct hlist_bl_head *h)
 {
-	return !((unsigned long)h->first & ~LIST_BL_LOCKMASK);
+	return !((unsigned long)READ_ONCE(h->first) & ~LIST_BL_LOCKMASK);
 }
 
 static inline void hlist_bl_add_head(struct hlist_bl_node *n,
diff --git a/include/linux/list_nulls.h b/include/linux/list_nulls.h
index 444d2b1..b01fe10 100644
--- a/include/linux/list_nulls.h
+++ b/include/linux/list_nulls.h
@@ -57,7 +57,7 @@
 
 static inline int hlist_nulls_empty(const struct hlist_nulls_head *h)
 {
-	return is_a_nulls(h->first);
+	return is_a_nulls(READ_ONCE(h->first));
 }
 
 static inline void hlist_nulls_add_head(struct hlist_nulls_node *n,
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 24daf8f..fec66f8 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -25,6 +25,7 @@
 	MEMBLOCK_NONE		= 0x0,	/* No special request */
 	MEMBLOCK_HOTPLUG	= 0x1,	/* hotpluggable region */
 	MEMBLOCK_MIRROR		= 0x2,	/* mirrored region */
+	MEMBLOCK_NOMAP		= 0x4,	/* don't add to kernel direct mapping */
 };
 
 struct memblock_region {
@@ -82,6 +83,7 @@
 int memblock_mark_hotplug(phys_addr_t base, phys_addr_t size);
 int memblock_clear_hotplug(phys_addr_t base, phys_addr_t size);
 int memblock_mark_mirror(phys_addr_t base, phys_addr_t size);
+int memblock_mark_nomap(phys_addr_t base, phys_addr_t size);
 ulong choose_memblock_flags(void);
 
 /* Low level functions */
@@ -184,6 +186,11 @@
 	return m->flags & MEMBLOCK_MIRROR;
 }
 
+static inline bool memblock_is_nomap(struct memblock_region *m)
+{
+	return m->flags & MEMBLOCK_NOMAP;
+}
+
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 int memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn,
 			    unsigned long  *end_pfn);
@@ -319,6 +326,7 @@
 phys_addr_t memblock_end_of_DRAM(void);
 void memblock_enforce_memory_limit(phys_addr_t memory_limit);
 int memblock_is_memory(phys_addr_t addr);
+int memblock_is_map_memory(phys_addr_t addr);
 int memblock_is_region_memory(phys_addr_t base, phys_addr_t size);
 int memblock_is_reserved(phys_addr_t addr);
 bool memblock_is_region_reserved(phys_addr_t base, phys_addr_t size);
diff --git a/include/linux/mfd/wm8350/pmic.h b/include/linux/mfd/wm8350/pmic.h
index 579b50c..7a09e7f 100644
--- a/include/linux/mfd/wm8350/pmic.h
+++ b/include/linux/mfd/wm8350/pmic.h
@@ -715,7 +715,6 @@
 
 struct wm8350_led {
 	struct platform_device *pdev;
-	struct mutex mutex;
 	struct work_struct work;
 	spinlock_t value_lock;
 	enum led_brightness value;
diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h
index f67b2ec..89df7ab 100644
--- a/include/linux/mmc/dw_mmc.h
+++ b/include/linux/mmc/dw_mmc.h
@@ -172,7 +172,7 @@
 	/* For edmac */
 	struct dw_mci_dma_slave *dms;
 	/* Registers's physical base address */
-	void                    *phy_regs;
+	resource_size_t		phy_regs;
 
 	u32			cmd_status;
 	u32			data_status;
@@ -235,16 +235,10 @@
 };
 
 /* IP Quirks/flags. */
-/* DTO fix for command transmission with IDMAC configured */
-#define DW_MCI_QUIRK_IDMAC_DTO			BIT(0)
-/* delay needed between retries on some 2.11a implementations */
-#define DW_MCI_QUIRK_RETRY_DELAY		BIT(1)
-/* High Speed Capable - Supports HS cards (up to 50MHz) */
-#define DW_MCI_QUIRK_HIGHSPEED			BIT(2)
 /* Unreliable card detection */
-#define DW_MCI_QUIRK_BROKEN_CARD_DETECTION	BIT(3)
+#define DW_MCI_QUIRK_BROKEN_CARD_DETECTION	BIT(0)
 /* Timer for broken data transfer over scheme */
-#define DW_MCI_QUIRK_BROKEN_DTO			BIT(4)
+#define DW_MCI_QUIRK_BROKEN_DTO			BIT(1)
 
 struct dma_pdata;
 
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 8673ffe..8dd4d29 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -212,7 +212,9 @@
 	u32			ocr_avail_sdio;	/* SDIO-specific OCR */
 	u32			ocr_avail_sd;	/* SD-specific OCR */
 	u32			ocr_avail_mmc;	/* MMC-specific OCR */
+#ifdef CONFIG_PM_SLEEP
 	struct notifier_block	pm_notify;
+#endif
 	u32			max_current_330;
 	u32			max_current_300;
 	u32			max_current_180;
@@ -259,7 +261,6 @@
 #define MMC_CAP_UHS_SDR50	(1 << 17)	/* Host supports UHS SDR50 mode */
 #define MMC_CAP_UHS_SDR104	(1 << 18)	/* Host supports UHS SDR104 mode */
 #define MMC_CAP_UHS_DDR50	(1 << 19)	/* Host supports UHS DDR50 mode */
-#define MMC_CAP_RUNTIME_RESUME	(1 << 20)	/* Resume at runtime_resume. */
 #define MMC_CAP_DRIVER_TYPE_A	(1 << 23)	/* Host supports Driver Type A */
 #define MMC_CAP_DRIVER_TYPE_C	(1 << 24)	/* Host supports Driver Type C */
 #define MMC_CAP_DRIVER_TYPE_D	(1 << 25)	/* Host supports Driver Type D */
@@ -289,6 +290,7 @@
 #define MMC_CAP2_HSX00_1_2V	(MMC_CAP2_HS200_1_2V_SDR | MMC_CAP2_HS400_1_2V)
 #define MMC_CAP2_SDIO_IRQ_NOTHREAD (1 << 17)
 #define MMC_CAP2_NO_WRITE_PROTECT (1 << 18)	/* No physical write protect pin, assume that card is always read-write */
+#define MMC_CAP2_NO_SDIO	(1 << 19)	/* Do not send SDIO commands during initialization */
 
 	mmc_pm_flag_t		pm_caps;	/* supported pm features */
 
@@ -434,8 +436,6 @@
 
 int mmc_regulator_get_supply(struct mmc_host *mmc);
 
-int mmc_pm_notify(struct notifier_block *notify_block, unsigned long, void *);
-
 static inline int mmc_card_is_removable(struct mmc_host *host)
 {
 	return !(host->caps & MMC_CAP_NONREMOVABLE);
diff --git a/include/linux/msi.h b/include/linux/msi.h
index f71a25e..1c6342a 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -174,6 +174,7 @@
 #include <asm/msi.h>
 
 struct irq_domain;
+struct irq_domain_ops;
 struct irq_chip;
 struct device_node;
 struct fwnode_handle;
@@ -279,6 +280,23 @@
 int platform_msi_domain_alloc_irqs(struct device *dev, unsigned int nvec,
 				   irq_write_msi_msg_t write_msi_msg);
 void platform_msi_domain_free_irqs(struct device *dev);
+
+/* When an MSI domain is used as an intermediate domain */
+int msi_domain_prepare_irqs(struct irq_domain *domain, struct device *dev,
+			    int nvec, msi_alloc_info_t *args);
+int msi_domain_populate_irqs(struct irq_domain *domain, struct device *dev,
+			     int virq, int nvec, msi_alloc_info_t *args);
+struct irq_domain *
+platform_msi_create_device_domain(struct device *dev,
+				  unsigned int nvec,
+				  irq_write_msi_msg_t write_msi_msg,
+				  const struct irq_domain_ops *ops,
+				  void *host_data);
+int platform_msi_domain_alloc(struct irq_domain *domain, unsigned int virq,
+			      unsigned int nr_irqs);
+void platform_msi_domain_free(struct irq_domain *domain, unsigned int virq,
+			      unsigned int nvec);
+void *platform_msi_get_host_data(struct irq_domain *domain);
 #endif /* CONFIG_GENERIC_MSI_IRQ_DOMAIN */
 
 #ifdef CONFIG_PCI_MSI_IRQ_DOMAIN
diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h
index c8723b62..bc742da 100644
--- a/include/linux/mtd/spi-nor.h
+++ b/include/linux/mtd/spi-nor.h
@@ -25,7 +25,7 @@
 #define SNOR_MFR_MACRONIX	CFI_MFR_MACRONIX
 #define SNOR_MFR_SPANSION	CFI_MFR_AMD
 #define SNOR_MFR_SST		CFI_MFR_SST
-#define SNOR_MFR_WINBOND	0xef
+#define SNOR_MFR_WINBOND	0xef /* Also used by some Spansion */
 
 /*
  * Note on opcode nomenclature: some opcodes have a format like
diff --git a/include/linux/namei.h b/include/linux/namei.h
index d8c6334..d0f25d8 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -77,6 +77,7 @@
 extern int kern_path_mountpoint(int, const char *, struct path *, unsigned int);
 
 extern struct dentry *lookup_one_len(const char *, struct dentry *, int);
+extern struct dentry *lookup_one_len_unlocked(const char *, struct dentry *, int);
 
 extern int follow_down_one(struct path *);
 extern int follow_down(struct path *);
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index e7e7853..43aeabd 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -139,10 +139,10 @@
 Needs to be updated if more operations are defined in future.*/
 
 #define FIRST_NFS4_OP	OP_ACCESS
-#define LAST_NFS4_OP 	OP_WRITE_SAME
 #define LAST_NFS40_OP	OP_RELEASE_LOCKOWNER
 #define LAST_NFS41_OP	OP_RECLAIM_COMPLETE
-#define LAST_NFS42_OP	OP_WRITE_SAME
+#define LAST_NFS42_OP	OP_CLONE
+#define LAST_NFS4_OP	LAST_NFS42_OP
 
 enum nfsstat4 {
 	NFS4_OK = 0,
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index c0e9614..37a3d29 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -359,6 +359,7 @@
 extern int nfs_revalidate_inode_rcu(struct nfs_server *server, struct inode *inode);
 extern int __nfs_revalidate_inode(struct nfs_server *, struct inode *);
 extern int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping);
+extern int nfs_revalidate_mapping_rcu(struct inode *inode);
 extern int nfs_revalidate_mapping_protected(struct inode *inode, struct address_space *mapping);
 extern int nfs_setattr(struct dentry *, struct iattr *);
 extern void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, struct nfs_fattr *);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 6ae25aa..d86378c 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1946,6 +1946,16 @@
 pci_host_bridge_of_msi_domain(struct pci_bus *bus) { return NULL; }
 #endif  /* CONFIG_OF */
 
+#ifdef CONFIG_ACPI
+struct irq_domain *pci_host_bridge_acpi_msi_domain(struct pci_bus *bus);
+
+void
+pci_msi_register_fwnode_provider(struct fwnode_handle *(*fn)(struct device *));
+#else
+static inline struct irq_domain *
+pci_host_bridge_acpi_msi_domain(struct pci_bus *bus) { return NULL; }
+#endif
+
 #ifdef CONFIG_EEH
 static inline struct eeh_dev *pci_dev_to_eeh_dev(struct pci_dev *pdev)
 {
diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index 12c9b48..84f542d 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -116,7 +116,7 @@
  */
 static inline void percpu_ref_kill(struct percpu_ref *ref)
 {
-	return percpu_ref_kill_and_confirm(ref, NULL);
+	percpu_ref_kill_and_confirm(ref, NULL);
 }
 
 /*
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index caebf2a..4bc6daf 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -18,12 +18,6 @@
 #define PERCPU_MODULE_RESERVE		0
 #endif
 
-#ifndef PERCPU_ENOUGH_ROOM
-#define PERCPU_ENOUGH_ROOM						\
-	(ALIGN(__per_cpu_end - __per_cpu_start, SMP_CACHE_BYTES) +	\
-	 PERCPU_MODULE_RESERVE)
-#endif
-
 /* minimum unit size, also is the maximum supported allocation size */
 #define PCPU_MIN_UNIT_SIZE		PFN_ALIGN(32 << 10)
 
diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h
index bfa673b..83b5e34 100644
--- a/include/linux/perf/arm_pmu.h
+++ b/include/linux/perf/arm_pmu.h
@@ -111,8 +111,6 @@
 
 #define to_arm_pmu(p) (container_of(p, struct arm_pmu, pmu))
 
-int armpmu_register(struct arm_pmu *armpmu, int type);
-
 u64 armpmu_event_update(struct perf_event *event);
 
 int armpmu_event_set_period(struct perf_event *event);
diff --git a/include/linux/platform_data/camera-rcar.h b/include/linux/platform_data/camera-rcar.h
deleted file mode 100644
index dfc83c5..0000000
--- a/include/linux/platform_data/camera-rcar.h
+++ /dev/null
@@ -1,25 +0,0 @@
-/*
- * Platform data for Renesas R-Car VIN soc-camera driver
- *
- * Copyright (C) 2011-2013 Renesas Solutions Corp.
- * Copyright (C) 2013 Cogent Embedded, Inc., <source@cogentembedded.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- */
-
-#ifndef __CAMERA_RCAR_H_
-#define __CAMERA_RCAR_H_
-
-#define RCAR_VIN_HSYNC_ACTIVE_LOW	(1 << 0)
-#define RCAR_VIN_VSYNC_ACTIVE_LOW	(1 << 1)
-#define RCAR_VIN_BT601			(1 << 2)
-#define RCAR_VIN_BT656			(1 << 3)
-
-struct rcar_vin_platform_data {
-	unsigned int flags;
-};
-
-#endif /* __CAMERA_RCAR_H_ */
diff --git a/include/linux/platform_data/irq-renesas-intc-irqpin.h b/include/linux/platform_data/irq-renesas-intc-irqpin.h
deleted file mode 100644
index e4cb911..0000000
--- a/include/linux/platform_data/irq-renesas-intc-irqpin.h
+++ /dev/null
@@ -1,29 +0,0 @@
-/*
- * Renesas INTC External IRQ Pin Driver
- *
- *  Copyright (C) 2013 Magnus Damm
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- */
-
-#ifndef __IRQ_RENESAS_INTC_IRQPIN_H__
-#define __IRQ_RENESAS_INTC_IRQPIN_H__
-
-struct renesas_intc_irqpin_config {
-	unsigned int sense_bitfield_width;
-	unsigned int irq_base;
-	bool control_parent;
-};
-
-#endif /* __IRQ_RENESAS_INTC_IRQPIN_H__ */
diff --git a/include/linux/platform_data/camera-mx2.h b/include/linux/platform_data/media/camera-mx2.h
similarity index 100%
rename from include/linux/platform_data/camera-mx2.h
rename to include/linux/platform_data/media/camera-mx2.h
diff --git a/include/linux/platform_data/camera-mx3.h b/include/linux/platform_data/media/camera-mx3.h
similarity index 100%
rename from include/linux/platform_data/camera-mx3.h
rename to include/linux/platform_data/media/camera-mx3.h
diff --git a/include/linux/platform_data/camera-pxa.h b/include/linux/platform_data/media/camera-pxa.h
similarity index 100%
rename from include/linux/platform_data/camera-pxa.h
rename to include/linux/platform_data/media/camera-pxa.h
diff --git a/include/linux/platform_data/coda.h b/include/linux/platform_data/media/coda.h
similarity index 100%
rename from include/linux/platform_data/coda.h
rename to include/linux/platform_data/media/coda.h
diff --git a/include/media/gpio-ir-recv.h b/include/linux/platform_data/media/gpio-ir-recv.h
similarity index 99%
rename from include/media/gpio-ir-recv.h
rename to include/linux/platform_data/media/gpio-ir-recv.h
index 0142736..0c298f5 100644
--- a/include/media/gpio-ir-recv.h
+++ b/include/linux/platform_data/media/gpio-ir-recv.h
@@ -21,4 +21,3 @@
 };
 
 #endif /* __GPIO_IR_RECV_H__ */
-
diff --git a/include/media/ir-rx51.h b/include/linux/platform_data/media/ir-rx51.h
similarity index 100%
rename from include/media/ir-rx51.h
rename to include/linux/platform_data/media/ir-rx51.h
diff --git a/include/media/mmp-camera.h b/include/linux/platform_data/media/mmp-camera.h
similarity index 100%
rename from include/media/mmp-camera.h
rename to include/linux/platform_data/media/mmp-camera.h
diff --git a/include/media/omap1_camera.h b/include/linux/platform_data/media/omap1_camera.h
similarity index 100%
rename from include/media/omap1_camera.h
rename to include/linux/platform_data/media/omap1_camera.h
diff --git a/include/media/omap4iss.h b/include/linux/platform_data/media/omap4iss.h
similarity index 100%
rename from include/media/omap4iss.h
rename to include/linux/platform_data/media/omap4iss.h
diff --git a/include/media/s5p_hdmi.h b/include/linux/platform_data/media/s5p_hdmi.h
similarity index 99%
rename from include/media/s5p_hdmi.h
rename to include/linux/platform_data/media/s5p_hdmi.h
index 181642b..bb9cacb 100644
--- a/include/media/s5p_hdmi.h
+++ b/include/linux/platform_data/media/s5p_hdmi.h
@@ -34,4 +34,3 @@
 };
 
 #endif /* S5P_HDMI_H */
-
diff --git a/include/media/si4713.h b/include/linux/platform_data/media/si4713.h
similarity index 96%
rename from include/media/si4713.h
rename to include/linux/platform_data/media/si4713.h
index be4f58e..932668a 100644
--- a/include/media/si4713.h
+++ b/include/linux/platform_data/media/si4713.h
@@ -1,5 +1,5 @@
 /*
- * include/media/si4713.h
+ * include/linux/platform_data/media/si4713.h
  *
  * Board related data definitions for Si4713 i2c device driver.
  *
diff --git a/include/media/sii9234.h b/include/linux/platform_data/media/sii9234.h
similarity index 100%
rename from include/media/sii9234.h
rename to include/linux/platform_data/media/sii9234.h
diff --git a/include/media/soc_camera_platform.h b/include/linux/platform_data/media/soc_camera_platform.h
similarity index 100%
rename from include/media/soc_camera_platform.h
rename to include/linux/platform_data/media/soc_camera_platform.h
diff --git a/include/media/timb_radio.h b/include/linux/platform_data/media/timb_radio.h
similarity index 100%
rename from include/media/timb_radio.h
rename to include/linux/platform_data/media/timb_radio.h
diff --git a/include/media/timb_video.h b/include/linux/platform_data/media/timb_video.h
similarity index 100%
rename from include/media/timb_video.h
rename to include/linux/platform_data/media/timb_video.h
diff --git a/include/linux/platform_data/mmc-mvsdio.h b/include/linux/platform_data/mmc-mvsdio.h
deleted file mode 100644
index d02704cd..0000000
--- a/include/linux/platform_data/mmc-mvsdio.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/*
- * This file is licensed under the terms of the GNU General Public
- * License version 2.  This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#ifndef __MMC_MVSDIO_H
-#define __MMC_MVSDIO_H
-
-#include <linux/mbus.h>
-
-struct mvsdio_platform_data {
-	unsigned int clock;
-	int gpio_card_detect;
-	int gpio_write_protect;
-};
-
-#endif
diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h
index dc777be..6abd019 100644
--- a/include/linux/platform_device.h
+++ b/include/linux/platform_device.h
@@ -51,6 +51,7 @@
 extern struct resource *platform_get_resource(struct platform_device *,
 					      unsigned int, unsigned int);
 extern int platform_get_irq(struct platform_device *, unsigned int);
+extern int platform_irq_count(struct platform_device *);
 extern struct resource *platform_get_resource_byname(struct platform_device *,
 						     unsigned int,
 						     const char *);
diff --git a/include/linux/posix_acl_xattr.h b/include/linux/posix_acl_xattr.h
index 6f14ee2..e5e8ec4 100644
--- a/include/linux/posix_acl_xattr.h
+++ b/include/linux/posix_acl_xattr.h
@@ -9,16 +9,12 @@
 #ifndef _POSIX_ACL_XATTR_H
 #define _POSIX_ACL_XATTR_H
 
+#include <uapi/linux/xattr.h>
 #include <linux/posix_acl.h>
 
-/* Extended attribute names */
-#define POSIX_ACL_XATTR_ACCESS	"system.posix_acl_access"
-#define POSIX_ACL_XATTR_DEFAULT	"system.posix_acl_default"
-
 /* Supported ACL a_version fields */
 #define POSIX_ACL_XATTR_VERSION	0x0002
 
-
 /* An undefined entry e_id value */
 #define ACL_UNDEFINED_ID	(-1)
 
diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index 5ed5409..14ec165 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -179,32 +179,31 @@
 }
 
 /**
- * list_splice_init_rcu - splice an RCU-protected list into an existing list.
+ * __list_splice_init_rcu - join an RCU-protected list into an existing list.
  * @list:	the RCU-protected list to splice
- * @head:	the place in the list to splice the first list into
+ * @prev:	points to the last element of the existing list
+ * @next:	points to the first element of the existing list
  * @sync:	function to sync: synchronize_rcu(), synchronize_sched(), ...
  *
- * @head can be RCU-read traversed concurrently with this function.
+ * The list pointed to by @prev and @next can be RCU-read traversed
+ * concurrently with this function.
  *
  * Note that this function blocks.
  *
- * Important note: the caller must take whatever action is necessary to
- *	prevent any other updates to @head.  In principle, it is possible
- *	to modify the list as soon as sync() begins execution.
- *	If this sort of thing becomes necessary, an alternative version
- *	based on call_rcu() could be created.  But only if -really-
- *	needed -- there is no shortage of RCU API members.
+ * Important note: the caller must take whatever action is necessary to prevent
+ * any other updates to the existing list.  In principle, it is possible to
+ * modify the list as soon as sync() begins execution. If this sort of thing
+ * becomes necessary, an alternative version based on call_rcu() could be
+ * created.  But only if -really- needed -- there is no shortage of RCU API
+ * members.
  */
-static inline void list_splice_init_rcu(struct list_head *list,
-					struct list_head *head,
-					void (*sync)(void))
+static inline void __list_splice_init_rcu(struct list_head *list,
+					  struct list_head *prev,
+					  struct list_head *next,
+					  void (*sync)(void))
 {
 	struct list_head *first = list->next;
 	struct list_head *last = list->prev;
-	struct list_head *at = head->next;
-
-	if (list_empty(list))
-		return;
 
 	/*
 	 * "first" and "last" tracking list, so initialize it.  RCU readers
@@ -231,10 +230,40 @@
 	 * this function.
 	 */
 
-	last->next = at;
-	rcu_assign_pointer(list_next_rcu(head), first);
-	first->prev = head;
-	at->prev = last;
+	last->next = next;
+	rcu_assign_pointer(list_next_rcu(prev), first);
+	first->prev = prev;
+	next->prev = last;
+}
+
+/**
+ * list_splice_init_rcu - splice an RCU-protected list into an existing list,
+ *                        designed for stacks.
+ * @list:	the RCU-protected list to splice
+ * @head:	the place in the existing list to splice the first list into
+ * @sync:	function to sync: synchronize_rcu(), synchronize_sched(), ...
+ */
+static inline void list_splice_init_rcu(struct list_head *list,
+					struct list_head *head,
+					void (*sync)(void))
+{
+	if (!list_empty(list))
+		__list_splice_init_rcu(list, head, head->next, sync);
+}
+
+/**
+ * list_splice_tail_init_rcu - splice an RCU-protected list into an existing
+ *                             list, designed for queues.
+ * @list:	the RCU-protected list to splice
+ * @head:	the place in the existing list to splice the first list into
+ * @sync:	function to sync: synchronize_rcu(), synchronize_sched(), ...
+ */
+static inline void list_splice_tail_init_rcu(struct list_head *list,
+					     struct list_head *head,
+					     void (*sync)(void))
+{
+	if (!list_empty(list))
+		__list_splice_init_rcu(list, head->prev, head, sync);
 }
 
 /**
@@ -305,6 +334,42 @@
 		pos = list_entry_rcu(pos->member.next, typeof(*pos), member))
 
 /**
+ * list_entry_lockless - get the struct for this entry
+ * @ptr:        the &struct list_head pointer.
+ * @type:       the type of the struct this is embedded in.
+ * @member:     the name of the list_head within the struct.
+ *
+ * This primitive may safely run concurrently with the _rcu list-mutation
+ * primitives such as list_add_rcu(), but requires some implicit RCU
+ * read-side guarding.  One example is running within a special
+ * exception-time environment where preemption is disabled and where
+ * lockdep cannot be invoked (in which case updaters must use RCU-sched,
+ * as in synchronize_sched(), call_rcu_sched(), and friends).  Another
+ * example is when items are added to the list, but never deleted.
+ */
+#define list_entry_lockless(ptr, type, member) \
+	container_of((typeof(ptr))lockless_dereference(ptr), type, member)
+
+/**
+ * list_for_each_entry_lockless - iterate over rcu list of given type
+ * @pos:	the type * to use as a loop cursor.
+ * @head:	the head for your list.
+ * @member:	the name of the list_struct within the struct.
+ *
+ * This primitive may safely run concurrently with the _rcu list-mutation
+ * primitives such as list_add_rcu(), but requires some implicit RCU
+ * read-side guarding.  One example is running within a special
+ * exception-time environment where preemption is disabled and where
+ * lockdep cannot be invoked (in which case updaters must use RCU-sched,
+ * as in synchronize_sched(), call_rcu_sched(), and friends).  Another
+ * example is when items are added to the list, but never deleted.
+ */
+#define list_for_each_entry_lockless(pos, head, member) \
+	for (pos = list_entry_lockless((head)->next, typeof(*pos), member); \
+	     &pos->member != (head); \
+	     pos = list_entry_lockless(pos->member.next, typeof(*pos), member))
+
+/**
  * list_for_each_entry_continue_rcu - continue iteration over list of given type
  * @pos:	the type * to use as a loop cursor.
  * @head:	the head for your list.
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index a0189ba..14e6f47 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -48,10 +48,17 @@
 
 #include <asm/barrier.h>
 
+#ifndef CONFIG_TINY_RCU
 extern int rcu_expedited; /* for sysctl */
+extern int rcu_normal;    /* also for sysctl */
+#endif /* #ifndef CONFIG_TINY_RCU */
 
 #ifdef CONFIG_TINY_RCU
 /* Tiny RCU doesn't expedite, as its purpose in life is instead to be tiny. */
+static inline bool rcu_gp_is_normal(void)  /* Internal RCU use. */
+{
+	return true;
+}
 static inline bool rcu_gp_is_expedited(void)  /* Internal RCU use. */
 {
 	return false;
@@ -65,6 +72,7 @@
 {
 }
 #else /* #ifdef CONFIG_TINY_RCU */
+bool rcu_gp_is_normal(void);     /* Internal RCU use. */
 bool rcu_gp_is_expedited(void);  /* Internal RCU use. */
 void rcu_expedite_gp(void);
 void rcu_unexpedite_gp(void);
@@ -321,7 +329,6 @@
 
 /* Internal to kernel */
 void rcu_init(void);
-void rcu_end_inkernel_boot(void);
 void rcu_sched_qs(void);
 void rcu_bh_qs(void);
 void rcu_check_callbacks(int user);
@@ -329,6 +336,12 @@
 int rcu_cpu_notify(struct notifier_block *self,
 		   unsigned long action, void *hcpu);
 
+#ifndef CONFIG_TINY_RCU
+void rcu_end_inkernel_boot(void);
+#else /* #ifndef CONFIG_TINY_RCU */
+static inline void rcu_end_inkernel_boot(void) { }
+#endif /* #ifndef CONFIG_TINY_RCU */
+
 #ifdef CONFIG_RCU_STALL_COMMON
 void rcu_sysrq_start(void);
 void rcu_sysrq_end(void);
@@ -379,9 +392,9 @@
  */
 #define RCU_NONIDLE(a) \
 	do { \
-		rcu_irq_enter(); \
+		rcu_irq_enter_irqson(); \
 		do { a; } while (0); \
-		rcu_irq_exit(); \
+		rcu_irq_exit_irqson(); \
 	} while (0)
 
 /*
@@ -741,7 +754,7 @@
  * The tracing infrastructure traces RCU (we want that), but unfortunately
  * some of the RCU checks causes tracing to lock up the system.
  *
- * The tracing version of rcu_dereference_raw() must not call
+ * The no-tracing version of rcu_dereference_raw() must not call
  * rcu_read_lock_held().
  */
 #define rcu_dereference_raw_notrace(p) __rcu_dereference_check((p), 1, __rcu)
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 4c1aaf9..64809ae 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -181,6 +181,14 @@
 {
 }
 
+static inline void rcu_irq_exit_irqson(void)
+{
+}
+
+static inline void rcu_irq_enter_irqson(void)
+{
+}
+
 static inline void rcu_irq_exit(void)
 {
 }
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 60d15a0..ad1eda9 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -37,7 +37,7 @@
 /*
  * Note a virtualization-based context switch.  This is simply a
  * wrapper around rcu_note_context_switch(), which allows TINY_RCU
- * to save a few bytes.
+ * to save a few bytes. The caller must have disabled interrupts.
  */
 static inline void rcu_virt_note_context_switch(int cpu)
 {
@@ -97,6 +97,8 @@
 void rcu_idle_exit(void);
 void rcu_irq_enter(void);
 void rcu_irq_exit(void);
+void rcu_irq_enter_irqson(void);
+void rcu_irq_exit_irqson(void);
 
 void exit_rcu(void);
 
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index d68bb40..1839434 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -788,10 +788,16 @@
  *
  * @reg_offset: Offset of the status/mask register within the bank
  * @mask:       Mask used to flag/control the register.
+ * @type_reg_offset: Offset register for the irq type setting.
+ * @type_rising_mask: Mask bit to configure RISING type irq.
+ * @type_falling_mask: Mask bit to configure FALLING type irq.
  */
 struct regmap_irq {
 	unsigned int reg_offset;
 	unsigned int mask;
+	unsigned int type_reg_offset;
+	unsigned int type_rising_mask;
+	unsigned int type_falling_mask;
 };
 
 #define REGMAP_IRQ_REG(_irq, _off, _mask)		\
@@ -811,18 +817,23 @@
  * @ack_base:    Base ack address. If zero then the chip is clear on read.
  *               Using zero value is possible with @use_ack bit.
  * @wake_base:   Base address for wake enables.  If zero unsupported.
+ * @type_base:   Base address for irq type.  If zero unsupported.
  * @irq_reg_stride:  Stride to use for chips where registers are not contiguous.
  * @init_ack_masked: Ack all masked interrupts once during initalization.
  * @mask_invert: Inverted mask register: cleared bits are masked out.
  * @use_ack:     Use @ack register even if it is zero.
  * @ack_invert:  Inverted ack register: cleared bits for ack.
  * @wake_invert: Inverted wake register: cleared bits are wake enabled.
+ * @type_invert: Invert the type flags.
  * @runtime_pm:  Hold a runtime PM lock on the device when accessing it.
  *
  * @num_regs:    Number of registers in each control bank.
  * @irqs:        Descriptors for individual IRQs.  Interrupt numbers are
  *               assigned based on the index in the array of the interrupt.
  * @num_irqs:    Number of descriptors.
+ * @num_type_reg:    Number of type registers.
+ * @type_reg_stride: Stride to use for chips where type registers are not
+ *			contiguous.
  */
 struct regmap_irq_chip {
 	const char *name;
@@ -832,6 +843,7 @@
 	unsigned int unmask_base;
 	unsigned int ack_base;
 	unsigned int wake_base;
+	unsigned int type_base;
 	unsigned int irq_reg_stride;
 	bool init_ack_masked:1;
 	bool mask_invert:1;
@@ -839,11 +851,15 @@
 	bool ack_invert:1;
 	bool wake_invert:1;
 	bool runtime_pm:1;
+	bool type_invert:1;
 
 	int num_regs;
 
 	const struct regmap_irq *irqs;
 	int num_irqs;
+
+	int num_type_reg;
+	unsigned int type_reg_stride;
 };
 
 struct regmap_irq_chip_data;
@@ -1021,7 +1037,7 @@
 }
 
 static inline int regmap_register_patch(struct regmap *map,
-					const struct reg_default *regs,
+					const struct reg_sequence *regs,
 					int num_regs)
 {
 	WARN_ONCE(1, "regmap API is disabled");
diff --git a/include/linux/sched.h b/include/linux/sched.h
index fbf25f1..61aa9bb 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -177,9 +177,9 @@
 extern void calc_global_load(unsigned long ticks);
 
 #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
-extern void update_cpu_load_nohz(void);
+extern void update_cpu_load_nohz(int active);
 #else
-static inline void update_cpu_load_nohz(void) { }
+static inline void update_cpu_load_nohz(int active) { }
 #endif
 
 extern unsigned long get_parent_ip(unsigned long addr);
@@ -377,6 +377,7 @@
 extern void sched_show_task(struct task_struct *p);
 
 #ifdef CONFIG_LOCKUP_DETECTOR
+extern void touch_softlockup_watchdog_sched(void);
 extern void touch_softlockup_watchdog(void);
 extern void touch_softlockup_watchdog_sync(void);
 extern void touch_all_softlockup_watchdogs(void);
@@ -387,6 +388,9 @@
 extern unsigned int  hardlockup_panic;
 void lockup_detector_init(void);
 #else
+static inline void touch_softlockup_watchdog_sched(void)
+{
+}
 static inline void touch_softlockup_watchdog(void)
 {
 }
@@ -1269,8 +1273,13 @@
 #endif
 
 #ifdef CONFIG_SMP
-	/* Per entity load average tracking */
-	struct sched_avg	avg;
+	/*
+	 * Per entity load average tracking.
+	 *
+	 * Put into separate cache line so it does not
+	 * collide with read-mostly values above.
+	 */
+	struct sched_avg	avg ____cacheline_aligned_in_smp;
 #endif
 };
 
@@ -1456,14 +1465,15 @@
 	/* Used for emulating ABI behavior of previous Linux versions */
 	unsigned int personality;
 
-	unsigned in_execve:1;	/* Tell the LSMs that the process is doing an
-				 * execve */
-	unsigned in_iowait:1;
-
-	/* Revert to default priority/policy when forking */
+	/* scheduler bits, serialized by scheduler locks */
 	unsigned sched_reset_on_fork:1;
 	unsigned sched_contributes_to_load:1;
 	unsigned sched_migrated:1;
+	unsigned :0; /* force alignment to the next boundary */
+
+	/* unserialized, strictly 'current' */
+	unsigned in_execve:1; /* bit to tell LSMs we're in execve */
+	unsigned in_iowait:1;
 #ifdef CONFIG_MEMCG
 	unsigned memcg_may_oom:1;
 #endif
@@ -1520,11 +1530,14 @@
 	cputime_t gtime;
 	struct prev_cputime prev_cputime;
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
-	seqlock_t vtime_seqlock;
+	seqcount_t vtime_seqcount;
 	unsigned long long vtime_snap;
 	enum {
-		VTIME_SLEEPING = 0,
+		/* Task is sleeping or running in a CPU with VTIME inactive */
+		VTIME_INACTIVE = 0,
+		/* Task runs in userspace in a CPU with VTIME active */
 		VTIME_USER,
+		/* Task runs in kernelspace in a CPU with VTIME active */
 		VTIME_SYS,
 	} vtime_snap_whence;
 #endif
@@ -2003,7 +2016,8 @@
 }
 
 /**
- * is_global_init - check if a task structure is init
+ * is_global_init - check if a task structure is init. Since init
+ * is free to have sub-threads we need to check tgid.
  * @tsk: Task structure to be checked.
  *
  * Check if a task structure is the first user space task the kernel created.
@@ -2012,7 +2026,7 @@
  */
 static inline int is_global_init(struct task_struct *tsk)
 {
-	return tsk->pid == 1;
+	return task_tgid_nr(tsk) == 1;
 }
 
 extern struct pid *cad_pid;
diff --git a/include/linux/sched_clock.h b/include/linux/sched_clock.h
index efa931c..411b52e 100644
--- a/include/linux/sched_clock.h
+++ b/include/linux/sched_clock.h
@@ -10,11 +10,17 @@
 
 #ifdef CONFIG_GENERIC_SCHED_CLOCK
 extern void sched_clock_postinit(void);
-#else
-static inline void sched_clock_postinit(void) { }
-#endif
 
 extern void sched_clock_register(u64 (*read)(void), int bits,
 				 unsigned long rate);
+#else
+static inline void sched_clock_postinit(void) { }
+
+static inline void sched_clock_register(u64 (*read)(void), int bits,
+					unsigned long rate)
+{
+	;
+}
+#endif
 
 #endif
diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h
index 0e1b1540..3cc9632 100644
--- a/include/linux/stop_machine.h
+++ b/include/linux/stop_machine.h
@@ -29,7 +29,7 @@
 
 int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg);
 int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *arg);
-void stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg,
+bool stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg,
 			 struct cpu_stop_work *work_buf);
 int stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg);
 int try_stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg);
@@ -65,7 +65,7 @@
 	preempt_enable();
 }
 
-static inline void stop_one_cpu_nowait(unsigned int cpu,
+static inline bool stop_one_cpu_nowait(unsigned int cpu,
 				       cpu_stop_fn_t fn, void *arg,
 				       struct cpu_stop_work *work_buf)
 {
@@ -74,7 +74,10 @@
 		work_buf->fn = fn;
 		work_buf->arg = arg;
 		schedule_work(&work_buf->work);
+		return true;
 	}
+
+	return false;
 }
 
 static inline int stop_cpus(const struct cpumask *cpumask,
diff --git a/include/linux/string.h b/include/linux/string.h
index 9ef7795..9eebc66 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -10,6 +10,7 @@
 
 extern char *strndup_user(const char __user *, long);
 extern void *memdup_user(const void __user *, size_t);
+extern void *memdup_user_nul(const void __user *, size_t);
 
 /*
  * Include machine specific inline routines
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index c2b66a2..185815c 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -886,6 +886,9 @@
 			const char __user *const __user *envp, int flags);
 
 asmlinkage long sys_membarrier(int cmd, int flags);
+asmlinkage long sys_copy_file_range(int fd_in, loff_t __user *off_in,
+				    int fd_out, loff_t __user *off_out,
+				    size_t len, unsigned int flags);
 
 asmlinkage long sys_mlock2(unsigned long start, size_t len, int flags);
 
diff --git a/include/linux/time.h b/include/linux/time.h
index beebe3a..297f09f 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -125,6 +125,32 @@
 
 extern struct timespec timespec_trunc(struct timespec t, unsigned gran);
 
+/*
+ * Validates if a timespec/timeval used to inject a time offset is valid.
+ * Offsets can be postive or negative. The value of the timeval/timespec
+ * is the sum of its fields, but *NOTE*: the field tv_usec/tv_nsec must
+ * always be non-negative.
+ */
+static inline bool timeval_inject_offset_valid(const struct timeval *tv)
+{
+	/* We don't check the tv_sec as it can be positive or negative */
+
+	/* Can't have more microseconds then a second */
+	if (tv->tv_usec < 0 || tv->tv_usec >= USEC_PER_SEC)
+		return false;
+	return true;
+}
+
+static inline bool timespec_inject_offset_valid(const struct timespec *ts)
+{
+	/* We don't check the tv_sec as it can be positive or negative */
+
+	/* Can't have more nanoseconds then a second */
+	if (ts->tv_nsec < 0 || ts->tv_nsec >= NSEC_PER_SEC)
+		return false;
+	return true;
+}
+
 #define CURRENT_TIME		(current_kernel_time())
 #define CURRENT_TIME_SEC	((struct timespec) { get_seconds(), 0 })
 
diff --git a/include/linux/tracepoint-defs.h b/include/linux/tracepoint-defs.h
new file mode 100644
index 0000000..e1ee97c
--- /dev/null
+++ b/include/linux/tracepoint-defs.h
@@ -0,0 +1,27 @@
+#ifndef TRACEPOINT_DEFS_H
+#define TRACEPOINT_DEFS_H 1
+
+/*
+ * File can be included directly by headers who only want to access
+ * tracepoint->key to guard out of line trace calls. Otherwise
+ * linux/tracepoint.h should be used.
+ */
+
+#include <linux/atomic.h>
+#include <linux/static_key.h>
+
+struct tracepoint_func {
+	void *func;
+	void *data;
+	int prio;
+};
+
+struct tracepoint {
+	const char *name;		/* Tracepoint name */
+	struct static_key key;
+	void (*regfunc)(void);
+	void (*unregfunc)(void);
+	struct tracepoint_func __rcu *funcs;
+};
+
+#endif
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 696a339c..78e8397 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -17,26 +17,12 @@
 #include <linux/errno.h>
 #include <linux/types.h>
 #include <linux/rcupdate.h>
-#include <linux/static_key.h>
+#include <linux/tracepoint-defs.h>
 
 struct module;
 struct tracepoint;
 struct notifier_block;
 
-struct tracepoint_func {
-	void *func;
-	void *data;
-	int prio;
-};
-
-struct tracepoint {
-	const char *name;		/* Tracepoint name */
-	struct static_key key;
-	void (*regfunc)(void);
-	void (*unregfunc)(void);
-	struct tracepoint_func __rcu *funcs;
-};
-
 struct trace_enum_map {
 	const char		*system;
 	const char		*enum_string;
@@ -171,8 +157,8 @@
 				TP_PROTO(data_proto),			\
 				TP_ARGS(data_args),			\
 				TP_CONDITION(cond),			\
-				rcu_irq_enter(),			\
-				rcu_irq_exit());			\
+				rcu_irq_enter_irqson(),			\
+				rcu_irq_exit_irqson());			\
 	}
 #else
 #define __DECLARE_TRACE_RCU(name, proto, args, cond, data_proto, data_args)
diff --git a/include/linux/uio.h b/include/linux/uio.h
index 8b01e1c..fd9bcfe 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -82,7 +82,7 @@
 			 struct iov_iter *i);
 size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes,
 			 struct iov_iter *i);
-size_t copy_to_iter(void *addr, size_t bytes, struct iov_iter *i);
+size_t copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i);
 size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i);
 size_t copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i);
 size_t iov_iter_zero(size_t bytes, struct iov_iter *);
@@ -145,7 +145,7 @@
 {
 	i->count = count;
 }
-size_t csum_and_copy_to_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i);
+size_t csum_and_copy_to_iter(const void *addr, size_t bytes, __wsum *csum, struct iov_iter *i);
 size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i);
 
 int import_iovec(int type, const struct iovec __user * uvector,
diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h
index 73ea2fb..16c0ed6 100644
--- a/include/linux/videodev2.h
+++ b/include/linux/videodev2.h
@@ -46,7 +46,7 @@
  * All kernel-specific stuff were moved to media/v4l2-dev.h, so
  * no #if __KERNEL tests are allowed here
  *
- *	See http://linuxtv.org for more info
+ *	See https://linuxtv.org for more info
  *
  *	Author: Bill Dirks <bill@thedirks.org>
  *		Justin Schoeman
diff --git a/include/linux/vtime.h b/include/linux/vtime.h
index c5165fd..fa21969 100644
--- a/include/linux/vtime.h
+++ b/include/linux/vtime.h
@@ -10,16 +10,27 @@
 struct task_struct;
 
 /*
- * vtime_accounting_enabled() definitions/declarations
+ * vtime_accounting_cpu_enabled() definitions/declarations
  */
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
-static inline bool vtime_accounting_enabled(void) { return true; }
+static inline bool vtime_accounting_cpu_enabled(void) { return true; }
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
+/*
+ * Checks if vtime is enabled on some CPU. Cputime readers want to be careful
+ * in that case and compute the tickless cputime.
+ * For now vtime state is tied to context tracking. We might want to decouple
+ * those later if necessary.
+ */
 static inline bool vtime_accounting_enabled(void)
 {
-	if (context_tracking_is_enabled()) {
+	return context_tracking_is_enabled();
+}
+
+static inline bool vtime_accounting_cpu_enabled(void)
+{
+	if (vtime_accounting_enabled()) {
 		if (context_tracking_cpu_is_enabled())
 			return true;
 	}
@@ -29,7 +40,7 @@
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */
 
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING
-static inline bool vtime_accounting_enabled(void) { return false; }
+static inline bool vtime_accounting_cpu_enabled(void) { return false; }
 #endif /* !CONFIG_VIRT_CPU_ACCOUNTING */
 
 
@@ -44,7 +55,7 @@
 extern void vtime_common_task_switch(struct task_struct *prev);
 static inline void vtime_task_switch(struct task_struct *prev)
 {
-	if (vtime_accounting_enabled())
+	if (vtime_accounting_cpu_enabled())
 		vtime_common_task_switch(prev);
 }
 #endif /* __ARCH_HAS_VTIME_TASK_SWITCH */
@@ -59,7 +70,7 @@
 extern void vtime_common_account_irq_enter(struct task_struct *tsk);
 static inline void vtime_account_irq_enter(struct task_struct *tsk)
 {
-	if (vtime_accounting_enabled())
+	if (vtime_accounting_cpu_enabled())
 		vtime_common_account_irq_enter(tsk);
 }
 #endif /* __ARCH_HAS_VTIME_ACCOUNT */
@@ -78,7 +89,7 @@
 
 static inline void vtime_account_irq_exit(struct task_struct *tsk)
 {
-	if (vtime_accounting_enabled())
+	if (vtime_accounting_cpu_enabled())
 		vtime_gen_account_irq_exit(tsk);
 }
 
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 0496c31..ae71a76 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -102,6 +102,36 @@
 	q->func		= func;
 }
 
+/**
+ * waitqueue_active -- locklessly test for waiters on the queue
+ * @q: the waitqueue to test for waiters
+ *
+ * returns true if the wait list is not empty
+ *
+ * NOTE: this function is lockless and requires care, incorrect usage _will_
+ * lead to sporadic and non-obvious failure.
+ *
+ * Use either while holding wait_queue_head_t::lock or when used for wakeups
+ * with an extra smp_mb() like:
+ *
+ *      CPU0 - waker                    CPU1 - waiter
+ *
+ *                                      for (;;) {
+ *      @cond = true;                     prepare_to_wait(&wq, &wait, state);
+ *      smp_mb();                         // smp_mb() from set_current_state()
+ *      if (waitqueue_active(wq))         if (@cond)
+ *        wake_up(wq);                      break;
+ *                                        schedule();
+ *                                      }
+ *                                      finish_wait(&wq, &wait);
+ *
+ * Because without the explicit smp_mb() it's possible for the
+ * waitqueue_active() load to get hoisted over the @cond store such that we'll
+ * observe an empty wait list while the waiter might not observe @cond.
+ *
+ * Also note that this 'optimization' trades a spin_lock() for an smp_mb(),
+ * which (when the lock is uncontended) are of roughly equal cost.
+ */
 static inline int waitqueue_active(wait_queue_head_t *q)
 {
 	return !list_empty(&q->task_list);
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 0197358..0e32bc7 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -618,4 +618,10 @@
 { return 0; }
 #endif	/* CONFIG_SYSFS */
 
+#ifdef CONFIG_WQ_WATCHDOG
+void wq_watchdog_touch(int cpu);
+#else	/* CONFIG_WQ_WATCHDOG */
+static inline void wq_watchdog_touch(int cpu) { }
+#endif	/* CONFIG_WQ_WATCHDOG */
+
 #endif
diff --git a/include/linux/xattr.h b/include/linux/xattr.h
index 89474b9..4457541 100644
--- a/include/linux/xattr.h
+++ b/include/linux/xattr.h
@@ -19,12 +19,16 @@
 struct inode;
 struct dentry;
 
+/*
+ * struct xattr_handler: When @name is set, match attributes with exactly that
+ * name.  When @prefix is set instead, match attributes with that prefix and
+ * with a non-empty suffix.
+ */
 struct xattr_handler {
+	const char *name;
 	const char *prefix;
 	int flags;      /* fs private flags */
-	size_t (*list)(const struct xattr_handler *, struct dentry *dentry,
-		       char *list, size_t list_size, const char *name,
-		       size_t name_len);
+	bool (*list)(struct dentry *dentry);
 	int (*get)(const struct xattr_handler *, struct dentry *dentry,
 		   const char *name, void *buffer, size_t size);
 	int (*set)(const struct xattr_handler *, struct dentry *dentry,
@@ -53,8 +57,11 @@
 int generic_removexattr(struct dentry *dentry, const char *name);
 ssize_t vfs_getxattr_alloc(struct dentry *dentry, const char *name,
 			   char **xattr_value, size_t size, gfp_t flags);
-int vfs_xattr_cmp(struct dentry *dentry, const char *xattr_name,
-		  const char *value, size_t size, gfp_t flags);
+
+static inline const char *xattr_prefix(const struct xattr_handler *handler)
+{
+	return handler->prefix ?: handler->name;
+}
 
 struct simple_xattrs {
 	struct list_head head;
@@ -95,8 +102,7 @@
 		     void *buffer, size_t size);
 int simple_xattr_set(struct simple_xattrs *xattrs, const char *name,
 		     const void *value, size_t size, int flags);
-int simple_xattr_remove(struct simple_xattrs *xattrs, const char *name);
-ssize_t simple_xattr_list(struct simple_xattrs *xattrs, char *buffer,
+ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, char *buffer,
 			  size_t size);
 void simple_xattr_list_add(struct simple_xattrs *xattrs,
 			   struct simple_xattr *new_xattr);
diff --git a/include/media/cx2341x.h b/include/media/drv-intf/cx2341x.h
similarity index 100%
rename from include/media/cx2341x.h
rename to include/media/drv-intf/cx2341x.h
diff --git a/include/media/cx25840.h b/include/media/drv-intf/cx25840.h
similarity index 100%
rename from include/media/cx25840.h
rename to include/media/drv-intf/cx25840.h
diff --git a/include/media/exynos-fimc.h b/include/media/drv-intf/exynos-fimc.h
similarity index 100%
rename from include/media/exynos-fimc.h
rename to include/media/drv-intf/exynos-fimc.h
diff --git a/include/media/msp3400.h b/include/media/drv-intf/msp3400.h
similarity index 99%
rename from include/media/msp3400.h
rename to include/media/drv-intf/msp3400.h
index 90cf22a..1e6e802 100644
--- a/include/media/msp3400.h
+++ b/include/media/drv-intf/msp3400.h
@@ -223,4 +223,3 @@
  */
 
 #endif /* MSP3400_H */
-
diff --git a/include/media/s3c_camif.h b/include/media/drv-intf/s3c_camif.h
similarity index 100%
rename from include/media/s3c_camif.h
rename to include/media/drv-intf/s3c_camif.h
diff --git a/include/media/saa7146.h b/include/media/drv-intf/saa7146.h
similarity index 100%
rename from include/media/saa7146.h
rename to include/media/drv-intf/saa7146.h
diff --git a/include/media/saa7146_vv.h b/include/media/drv-intf/saa7146_vv.h
similarity index 99%
rename from include/media/saa7146_vv.h
rename to include/media/drv-intf/saa7146_vv.h
index 92766f7..0da6ccc 100644
--- a/include/media/saa7146_vv.h
+++ b/include/media/drv-intf/saa7146_vv.h
@@ -4,7 +4,7 @@
 #include <media/v4l2-common.h>
 #include <media/v4l2-ioctl.h>
 #include <media/v4l2-fh.h>
-#include <media/saa7146.h>
+#include <media/drv-intf/saa7146.h>
 #include <media/videobuf-dma-sg.h>
 
 #define MAX_SAA7146_CAPTURE_BUFFERS	32	/* arbitrary */
diff --git a/include/media/sh_mobile_ceu.h b/include/media/drv-intf/sh_mobile_ceu.h
similarity index 100%
rename from include/media/sh_mobile_ceu.h
rename to include/media/drv-intf/sh_mobile_ceu.h
diff --git a/include/media/sh_mobile_csi2.h b/include/media/drv-intf/sh_mobile_csi2.h
similarity index 100%
rename from include/media/sh_mobile_csi2.h
rename to include/media/drv-intf/sh_mobile_csi2.h
diff --git a/include/media/sh_vou.h b/include/media/drv-intf/sh_vou.h
similarity index 100%
rename from include/media/sh_vou.h
rename to include/media/drv-intf/sh_vou.h
diff --git a/include/media/si476x.h b/include/media/drv-intf/si476x.h
similarity index 93%
rename from include/media/si476x.h
rename to include/media/drv-intf/si476x.h
index e02e241..ad87fa8 100644
--- a/include/media/si476x.h
+++ b/include/media/drv-intf/si476x.h
@@ -1,5 +1,5 @@
 /*
- * include/media/si476x.h -- Common definitions for si476x driver
+ * include/media/drv-intf/si476x.h -- Common definitions for si476x driver
  *
  * Copyright (C) 2012 Innovative Converged Devices(ICD)
  * Copyright (C) 2013 Andrey Smirnov
diff --git a/include/media/soc_mediabus.h b/include/media/drv-intf/soc_mediabus.h
similarity index 100%
rename from include/media/soc_mediabus.h
rename to include/media/drv-intf/soc_mediabus.h
diff --git a/include/media/tea575x.h b/include/media/drv-intf/tea575x.h
similarity index 98%
rename from include/media/tea575x.h
rename to include/media/drv-intf/tea575x.h
index 5d09657..fb272d48 100644
--- a/include/media/tea575x.h
+++ b/include/media/drv-intf/tea575x.h
@@ -63,7 +63,7 @@
 	u32 band;			/* 0: FM, 1: FM-Japan, 2: AM */
 	u32 freq;			/* frequency */
 	struct mutex mutex;
-	struct snd_tea575x_ops *ops;
+	const struct snd_tea575x_ops *ops;
 	void *private_data;
 	u8 card[32];
 	u8 bus_info[32];
diff --git a/include/media/ad9389b.h b/include/media/i2c/ad9389b.h
similarity index 100%
rename from include/media/ad9389b.h
rename to include/media/i2c/ad9389b.h
diff --git a/include/media/adp1653.h b/include/media/i2c/adp1653.h
similarity index 98%
rename from include/media/adp1653.h
rename to include/media/i2c/adp1653.h
index 9779c85..0b67093 100644
--- a/include/media/adp1653.h
+++ b/include/media/i2c/adp1653.h
@@ -1,5 +1,5 @@
 /*
- * include/media/adp1653.h
+ * include/media/i2c/adp1653.h
  *
  * Copyright (C) 2008--2011 Nokia Corporation
  *
diff --git a/include/media/adv7183.h b/include/media/i2c/adv7183.h
similarity index 100%
rename from include/media/adv7183.h
rename to include/media/i2c/adv7183.h
diff --git a/include/media/adv7343.h b/include/media/i2c/adv7343.h
similarity index 100%
rename from include/media/adv7343.h
rename to include/media/i2c/adv7343.h
diff --git a/include/media/adv7393.h b/include/media/i2c/adv7393.h
similarity index 100%
rename from include/media/adv7393.h
rename to include/media/i2c/adv7393.h
diff --git a/include/media/adv7511.h b/include/media/i2c/adv7511.h
similarity index 100%
rename from include/media/adv7511.h
rename to include/media/i2c/adv7511.h
diff --git a/include/media/adv7604.h b/include/media/i2c/adv7604.h
similarity index 100%
rename from include/media/adv7604.h
rename to include/media/i2c/adv7604.h
diff --git a/include/media/adv7842.h b/include/media/i2c/adv7842.h
similarity index 100%
rename from include/media/adv7842.h
rename to include/media/i2c/adv7842.h
diff --git a/include/media/ak881x.h b/include/media/i2c/ak881x.h
similarity index 100%
rename from include/media/ak881x.h
rename to include/media/i2c/ak881x.h
diff --git a/include/media/as3645a.h b/include/media/i2c/as3645a.h
similarity index 98%
rename from include/media/as3645a.h
rename to include/media/i2c/as3645a.h
index 5075496..0e07484 100644
--- a/include/media/as3645a.h
+++ b/include/media/i2c/as3645a.h
@@ -1,5 +1,5 @@
 /*
- * include/media/as3645a.h
+ * include/media/i2c/as3645a.h
  *
  * Copyright (C) 2008-2011 Nokia Corporation
  *
diff --git a/include/media/bt819.h b/include/media/i2c/bt819.h
similarity index 100%
rename from include/media/bt819.h
rename to include/media/i2c/bt819.h
diff --git a/include/media/cs5345.h b/include/media/i2c/cs5345.h
similarity index 100%
rename from include/media/cs5345.h
rename to include/media/i2c/cs5345.h
diff --git a/include/media/cs53l32a.h b/include/media/i2c/cs53l32a.h
similarity index 100%
rename from include/media/cs53l32a.h
rename to include/media/i2c/cs53l32a.h
diff --git a/include/media/ir-kbd-i2c.h b/include/media/i2c/ir-kbd-i2c.h
similarity index 100%
rename from include/media/ir-kbd-i2c.h
rename to include/media/i2c/ir-kbd-i2c.h
diff --git a/include/media/lm3560.h b/include/media/i2c/lm3560.h
similarity index 98%
rename from include/media/lm3560.h
rename to include/media/i2c/lm3560.h
index 4667070..5ed942a 100644
--- a/include/media/lm3560.h
+++ b/include/media/i2c/lm3560.h
@@ -1,5 +1,5 @@
 /*
- * include/media/lm3560.h
+ * include/media/i2c/lm3560.h
  *
  * Copyright (C) 2013 Texas Instruments
  *
diff --git a/include/media/lm3646.h b/include/media/i2c/lm3646.h
similarity index 98%
rename from include/media/lm3646.h
rename to include/media/i2c/lm3646.h
index c6acf5a..724c100 100644
--- a/include/media/lm3646.h
+++ b/include/media/i2c/lm3646.h
@@ -1,5 +1,5 @@
 /*
- * include/media/lm3646.h
+ * include/media/i2c/lm3646.h
  *
  * Copyright (C) 2014 Texas Instruments
  *
diff --git a/include/media/m52790.h b/include/media/i2c/m52790.h
similarity index 100%
rename from include/media/m52790.h
rename to include/media/i2c/m52790.h
diff --git a/include/media/m5mols.h b/include/media/i2c/m5mols.h
similarity index 100%
rename from include/media/m5mols.h
rename to include/media/i2c/m5mols.h
diff --git a/include/media/mt9m032.h b/include/media/i2c/mt9m032.h
similarity index 100%
rename from include/media/mt9m032.h
rename to include/media/i2c/mt9m032.h
diff --git a/include/media/mt9p031.h b/include/media/i2c/mt9p031.h
similarity index 100%
rename from include/media/mt9p031.h
rename to include/media/i2c/mt9p031.h
diff --git a/include/media/mt9t001.h b/include/media/i2c/mt9t001.h
similarity index 100%
rename from include/media/mt9t001.h
rename to include/media/i2c/mt9t001.h
diff --git a/include/media/mt9t112.h b/include/media/i2c/mt9t112.h
similarity index 100%
rename from include/media/mt9t112.h
rename to include/media/i2c/mt9t112.h
diff --git a/include/media/mt9v011.h b/include/media/i2c/mt9v011.h
similarity index 100%
rename from include/media/mt9v011.h
rename to include/media/i2c/mt9v011.h
diff --git a/include/media/mt9v022.h b/include/media/i2c/mt9v022.h
similarity index 100%
rename from include/media/mt9v022.h
rename to include/media/i2c/mt9v022.h
diff --git a/include/media/mt9v032.h b/include/media/i2c/mt9v032.h
similarity index 100%
rename from include/media/mt9v032.h
rename to include/media/i2c/mt9v032.h
diff --git a/include/media/noon010pc30.h b/include/media/i2c/noon010pc30.h
similarity index 100%
rename from include/media/noon010pc30.h
rename to include/media/i2c/noon010pc30.h
diff --git a/include/media/ov2659.h b/include/media/i2c/ov2659.h
similarity index 100%
rename from include/media/ov2659.h
rename to include/media/i2c/ov2659.h
diff --git a/include/media/ov7670.h b/include/media/i2c/ov7670.h
similarity index 100%
rename from include/media/ov7670.h
rename to include/media/i2c/ov7670.h
diff --git a/include/media/ov772x.h b/include/media/i2c/ov772x.h
similarity index 100%
rename from include/media/ov772x.h
rename to include/media/i2c/ov772x.h
diff --git a/include/media/ov9650.h b/include/media/i2c/ov9650.h
similarity index 100%
rename from include/media/ov9650.h
rename to include/media/i2c/ov9650.h
diff --git a/include/media/rj54n1cb0c.h b/include/media/i2c/rj54n1cb0c.h
similarity index 100%
rename from include/media/rj54n1cb0c.h
rename to include/media/i2c/rj54n1cb0c.h
diff --git a/include/media/s5c73m3.h b/include/media/i2c/s5c73m3.h
similarity index 100%
rename from include/media/s5c73m3.h
rename to include/media/i2c/s5c73m3.h
diff --git a/include/media/s5k4ecgx.h b/include/media/i2c/s5k4ecgx.h
similarity index 100%
rename from include/media/s5k4ecgx.h
rename to include/media/i2c/s5k4ecgx.h
diff --git a/include/media/s5k6aa.h b/include/media/i2c/s5k6aa.h
similarity index 100%
rename from include/media/s5k6aa.h
rename to include/media/i2c/s5k6aa.h
diff --git a/include/media/saa6588.h b/include/media/i2c/saa6588.h
similarity index 100%
rename from include/media/saa6588.h
rename to include/media/i2c/saa6588.h
diff --git a/include/media/saa7115.h b/include/media/i2c/saa7115.h
similarity index 99%
rename from include/media/saa7115.h
rename to include/media/i2c/saa7115.h
index 76911e7..53954c9 100644
--- a/include/media/saa7115.h
+++ b/include/media/i2c/saa7115.h
@@ -138,4 +138,3 @@
 };
 
 #endif
-
diff --git a/include/media/saa7127.h b/include/media/i2c/saa7127.h
similarity index 99%
rename from include/media/saa7127.h
rename to include/media/i2c/saa7127.h
index bbcf862..7005ba7 100644
--- a/include/media/saa7127.h
+++ b/include/media/i2c/saa7127.h
@@ -38,4 +38,3 @@
 };
 
 #endif
-
diff --git a/include/media/smiapp.h b/include/media/i2c/smiapp.h
similarity index 98%
rename from include/media/smiapp.h
rename to include/media/i2c/smiapp.h
index 268a3cd..029142d 100644
--- a/include/media/smiapp.h
+++ b/include/media/i2c/smiapp.h
@@ -1,5 +1,5 @@
 /*
- * include/media/smiapp.h
+ * include/media/i2c/smiapp.h
  *
  * Generic driver for SMIA/SMIA++ compliant camera modules
  *
diff --git a/include/media/sr030pc30.h b/include/media/i2c/sr030pc30.h
similarity index 100%
rename from include/media/sr030pc30.h
rename to include/media/i2c/sr030pc30.h
diff --git a/include/media/tc358743.h b/include/media/i2c/tc358743.h
similarity index 100%
rename from include/media/tc358743.h
rename to include/media/i2c/tc358743.h
diff --git a/include/media/ths7303.h b/include/media/i2c/ths7303.h
similarity index 100%
rename from include/media/ths7303.h
rename to include/media/i2c/ths7303.h
diff --git a/include/media/tvaudio.h b/include/media/i2c/tvaudio.h
similarity index 100%
rename from include/media/tvaudio.h
rename to include/media/i2c/tvaudio.h
diff --git a/include/media/tvp514x.h b/include/media/i2c/tvp514x.h
similarity index 100%
rename from include/media/tvp514x.h
rename to include/media/i2c/tvp514x.h
diff --git a/include/media/tvp5150.h b/include/media/i2c/tvp5150.h
similarity index 99%
rename from include/media/tvp5150.h
rename to include/media/i2c/tvp5150.h
index 72bd2a2..649908a 100644
--- a/include/media/tvp5150.h
+++ b/include/media/i2c/tvp5150.h
@@ -31,4 +31,3 @@
 #define TVP5150_BLACK_SCREEN 1
 
 #endif
-
diff --git a/include/media/tvp7002.h b/include/media/i2c/tvp7002.h
similarity index 100%
rename from include/media/tvp7002.h
rename to include/media/i2c/tvp7002.h
diff --git a/include/media/tw9910.h b/include/media/i2c/tw9910.h
similarity index 100%
rename from include/media/tw9910.h
rename to include/media/i2c/tw9910.h
diff --git a/include/media/uda1342.h b/include/media/i2c/uda1342.h
similarity index 100%
rename from include/media/uda1342.h
rename to include/media/i2c/uda1342.h
diff --git a/include/media/upd64031a.h b/include/media/i2c/upd64031a.h
similarity index 100%
rename from include/media/upd64031a.h
rename to include/media/i2c/upd64031a.h
diff --git a/include/media/upd64083.h b/include/media/i2c/upd64083.h
similarity index 100%
rename from include/media/upd64083.h
rename to include/media/i2c/upd64083.h
diff --git a/include/media/wm8775.h b/include/media/i2c/wm8775.h
similarity index 100%
rename from include/media/wm8775.h
rename to include/media/i2c/wm8775.h
diff --git a/include/media/lirc.h b/include/media/lirc.h
index 4b3ab29..554988c 100644
--- a/include/media/lirc.h
+++ b/include/media/lirc.h
@@ -1,168 +1 @@
-/*
- * lirc.h - linux infrared remote control header file
- * last modified 2010/07/13 by Jarod Wilson
- */
-
-#ifndef _LINUX_LIRC_H
-#define _LINUX_LIRC_H
-
-#include <linux/types.h>
-#include <linux/ioctl.h>
-
-#define PULSE_BIT       0x01000000
-#define PULSE_MASK      0x00FFFFFF
-
-#define LIRC_MODE2_SPACE     0x00000000
-#define LIRC_MODE2_PULSE     0x01000000
-#define LIRC_MODE2_FREQUENCY 0x02000000
-#define LIRC_MODE2_TIMEOUT   0x03000000
-
-#define LIRC_VALUE_MASK      0x00FFFFFF
-#define LIRC_MODE2_MASK      0xFF000000
-
-#define LIRC_SPACE(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_SPACE)
-#define LIRC_PULSE(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_PULSE)
-#define LIRC_FREQUENCY(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_FREQUENCY)
-#define LIRC_TIMEOUT(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_TIMEOUT)
-
-#define LIRC_VALUE(val) ((val)&LIRC_VALUE_MASK)
-#define LIRC_MODE2(val) ((val)&LIRC_MODE2_MASK)
-
-#define LIRC_IS_SPACE(val) (LIRC_MODE2(val) == LIRC_MODE2_SPACE)
-#define LIRC_IS_PULSE(val) (LIRC_MODE2(val) == LIRC_MODE2_PULSE)
-#define LIRC_IS_FREQUENCY(val) (LIRC_MODE2(val) == LIRC_MODE2_FREQUENCY)
-#define LIRC_IS_TIMEOUT(val) (LIRC_MODE2(val) == LIRC_MODE2_TIMEOUT)
-
-/* used heavily by lirc userspace */
-#define lirc_t int
-
-/*** lirc compatible hardware features ***/
-
-#define LIRC_MODE2SEND(x) (x)
-#define LIRC_SEND2MODE(x) (x)
-#define LIRC_MODE2REC(x) ((x) << 16)
-#define LIRC_REC2MODE(x) ((x) >> 16)
-
-#define LIRC_MODE_RAW                  0x00000001
-#define LIRC_MODE_PULSE                0x00000002
-#define LIRC_MODE_MODE2                0x00000004
-#define LIRC_MODE_LIRCCODE             0x00000010
-
-
-#define LIRC_CAN_SEND_RAW              LIRC_MODE2SEND(LIRC_MODE_RAW)
-#define LIRC_CAN_SEND_PULSE            LIRC_MODE2SEND(LIRC_MODE_PULSE)
-#define LIRC_CAN_SEND_MODE2            LIRC_MODE2SEND(LIRC_MODE_MODE2)
-#define LIRC_CAN_SEND_LIRCCODE         LIRC_MODE2SEND(LIRC_MODE_LIRCCODE)
-
-#define LIRC_CAN_SEND_MASK             0x0000003f
-
-#define LIRC_CAN_SET_SEND_CARRIER      0x00000100
-#define LIRC_CAN_SET_SEND_DUTY_CYCLE   0x00000200
-#define LIRC_CAN_SET_TRANSMITTER_MASK  0x00000400
-
-#define LIRC_CAN_REC_RAW               LIRC_MODE2REC(LIRC_MODE_RAW)
-#define LIRC_CAN_REC_PULSE             LIRC_MODE2REC(LIRC_MODE_PULSE)
-#define LIRC_CAN_REC_MODE2             LIRC_MODE2REC(LIRC_MODE_MODE2)
-#define LIRC_CAN_REC_LIRCCODE          LIRC_MODE2REC(LIRC_MODE_LIRCCODE)
-
-#define LIRC_CAN_REC_MASK              LIRC_MODE2REC(LIRC_CAN_SEND_MASK)
-
-#define LIRC_CAN_SET_REC_CARRIER       (LIRC_CAN_SET_SEND_CARRIER << 16)
-#define LIRC_CAN_SET_REC_DUTY_CYCLE    (LIRC_CAN_SET_SEND_DUTY_CYCLE << 16)
-
-#define LIRC_CAN_SET_REC_DUTY_CYCLE_RANGE 0x40000000
-#define LIRC_CAN_SET_REC_CARRIER_RANGE    0x80000000
-#define LIRC_CAN_GET_REC_RESOLUTION       0x20000000
-#define LIRC_CAN_SET_REC_TIMEOUT          0x10000000
-#define LIRC_CAN_SET_REC_FILTER           0x08000000
-
-#define LIRC_CAN_MEASURE_CARRIER          0x02000000
-#define LIRC_CAN_USE_WIDEBAND_RECEIVER    0x04000000
-
-#define LIRC_CAN_SEND(x) ((x)&LIRC_CAN_SEND_MASK)
-#define LIRC_CAN_REC(x) ((x)&LIRC_CAN_REC_MASK)
-
-#define LIRC_CAN_NOTIFY_DECODE            0x01000000
-
-/*** IOCTL commands for lirc driver ***/
-
-#define LIRC_GET_FEATURES              _IOR('i', 0x00000000, __u32)
-
-#define LIRC_GET_SEND_MODE             _IOR('i', 0x00000001, __u32)
-#define LIRC_GET_REC_MODE              _IOR('i', 0x00000002, __u32)
-#define LIRC_GET_SEND_CARRIER          _IOR('i', 0x00000003, __u32)
-#define LIRC_GET_REC_CARRIER           _IOR('i', 0x00000004, __u32)
-#define LIRC_GET_SEND_DUTY_CYCLE       _IOR('i', 0x00000005, __u32)
-#define LIRC_GET_REC_DUTY_CYCLE        _IOR('i', 0x00000006, __u32)
-#define LIRC_GET_REC_RESOLUTION        _IOR('i', 0x00000007, __u32)
-
-#define LIRC_GET_MIN_TIMEOUT           _IOR('i', 0x00000008, __u32)
-#define LIRC_GET_MAX_TIMEOUT           _IOR('i', 0x00000009, __u32)
-
-#define LIRC_GET_MIN_FILTER_PULSE      _IOR('i', 0x0000000a, __u32)
-#define LIRC_GET_MAX_FILTER_PULSE      _IOR('i', 0x0000000b, __u32)
-#define LIRC_GET_MIN_FILTER_SPACE      _IOR('i', 0x0000000c, __u32)
-#define LIRC_GET_MAX_FILTER_SPACE      _IOR('i', 0x0000000d, __u32)
-
-/* code length in bits, currently only for LIRC_MODE_LIRCCODE */
-#define LIRC_GET_LENGTH                _IOR('i', 0x0000000f, __u32)
-
-#define LIRC_SET_SEND_MODE             _IOW('i', 0x00000011, __u32)
-#define LIRC_SET_REC_MODE              _IOW('i', 0x00000012, __u32)
-/* Note: these can reset the according pulse_width */
-#define LIRC_SET_SEND_CARRIER          _IOW('i', 0x00000013, __u32)
-#define LIRC_SET_REC_CARRIER           _IOW('i', 0x00000014, __u32)
-#define LIRC_SET_SEND_DUTY_CYCLE       _IOW('i', 0x00000015, __u32)
-#define LIRC_SET_REC_DUTY_CYCLE        _IOW('i', 0x00000016, __u32)
-#define LIRC_SET_TRANSMITTER_MASK      _IOW('i', 0x00000017, __u32)
-
-/*
- * when a timeout != 0 is set the driver will send a
- * LIRC_MODE2_TIMEOUT data packet, otherwise LIRC_MODE2_TIMEOUT is
- * never sent, timeout is disabled by default
- */
-#define LIRC_SET_REC_TIMEOUT           _IOW('i', 0x00000018, __u32)
-
-/* 1 enables, 0 disables timeout reports in MODE2 */
-#define LIRC_SET_REC_TIMEOUT_REPORTS   _IOW('i', 0x00000019, __u32)
-
-/*
- * pulses shorter than this are filtered out by hardware (software
- * emulation in lirc_dev?)
- */
-#define LIRC_SET_REC_FILTER_PULSE      _IOW('i', 0x0000001a, __u32)
-/*
- * spaces shorter than this are filtered out by hardware (software
- * emulation in lirc_dev?)
- */
-#define LIRC_SET_REC_FILTER_SPACE      _IOW('i', 0x0000001b, __u32)
-/*
- * if filter cannot be set independently for pulse/space, this should
- * be used
- */
-#define LIRC_SET_REC_FILTER            _IOW('i', 0x0000001c, __u32)
-
-/*
- * if enabled from the next key press on the driver will send
- * LIRC_MODE2_FREQUENCY packets
- */
-#define LIRC_SET_MEASURE_CARRIER_MODE	_IOW('i', 0x0000001d, __u32)
-
-/*
- * to set a range use
- * LIRC_SET_REC_DUTY_CYCLE_RANGE/LIRC_SET_REC_CARRIER_RANGE with the
- * lower bound first and later
- * LIRC_SET_REC_DUTY_CYCLE/LIRC_SET_REC_CARRIER with the upper bound
- */
-
-#define LIRC_SET_REC_DUTY_CYCLE_RANGE  _IOW('i', 0x0000001e, __u32)
-#define LIRC_SET_REC_CARRIER_RANGE     _IOW('i', 0x0000001f, __u32)
-
-#define LIRC_NOTIFY_DECODE             _IO('i', 0x00000020)
-
-#define LIRC_SETUP_START               _IO('i', 0x00000021)
-#define LIRC_SETUP_END                 _IO('i', 0x00000022)
-
-#define LIRC_SET_WIDEBAND_RECEIVER     _IOW('i', 0x00000023, __u32)
-
-#endif
+#include <uapi/linux/lirc.h>
diff --git a/include/media/rc-core.h b/include/media/rc-core.h
index ec921f6..f649470 100644
--- a/include/media/rc-core.h
+++ b/include/media/rc-core.h
@@ -239,6 +239,7 @@
 	memset(ev, 0, sizeof(*ev));
 }
 
+#define IR_DEFAULT_TIMEOUT	MS_TO_NS(125)
 #define IR_MAX_DURATION         500000000	/* 500 ms */
 #define US_TO_NS(usec)		((usec) * 1000)
 #define MS_TO_US(msec)		((msec) * 1000)
diff --git a/include/media/rc-map.h b/include/media/rc-map.h
index 7c4bbc4..7844e98 100644
--- a/include/media/rc-map.h
+++ b/include/media/rc-map.h
@@ -33,26 +33,26 @@
 	RC_TYPE_XMP		= 18,	/* XMP protocol */
 };
 
-#define RC_BIT_NONE		0
-#define RC_BIT_UNKNOWN		(1 << RC_TYPE_UNKNOWN)
-#define RC_BIT_OTHER		(1 << RC_TYPE_OTHER)
-#define RC_BIT_RC5		(1 << RC_TYPE_RC5)
-#define RC_BIT_RC5X		(1 << RC_TYPE_RC5X)
-#define RC_BIT_RC5_SZ		(1 << RC_TYPE_RC5_SZ)
-#define RC_BIT_JVC		(1 << RC_TYPE_JVC)
-#define RC_BIT_SONY12		(1 << RC_TYPE_SONY12)
-#define RC_BIT_SONY15		(1 << RC_TYPE_SONY15)
-#define RC_BIT_SONY20		(1 << RC_TYPE_SONY20)
-#define RC_BIT_NEC		(1 << RC_TYPE_NEC)
-#define RC_BIT_SANYO		(1 << RC_TYPE_SANYO)
-#define RC_BIT_MCE_KBD		(1 << RC_TYPE_MCE_KBD)
-#define RC_BIT_RC6_0		(1 << RC_TYPE_RC6_0)
-#define RC_BIT_RC6_6A_20	(1 << RC_TYPE_RC6_6A_20)
-#define RC_BIT_RC6_6A_24	(1 << RC_TYPE_RC6_6A_24)
-#define RC_BIT_RC6_6A_32	(1 << RC_TYPE_RC6_6A_32)
-#define RC_BIT_RC6_MCE		(1 << RC_TYPE_RC6_MCE)
-#define RC_BIT_SHARP		(1 << RC_TYPE_SHARP)
-#define RC_BIT_XMP		(1 << RC_TYPE_XMP)
+#define RC_BIT_NONE		0ULL
+#define RC_BIT_UNKNOWN		(1ULL << RC_TYPE_UNKNOWN)
+#define RC_BIT_OTHER		(1ULL << RC_TYPE_OTHER)
+#define RC_BIT_RC5		(1ULL << RC_TYPE_RC5)
+#define RC_BIT_RC5X		(1ULL << RC_TYPE_RC5X)
+#define RC_BIT_RC5_SZ		(1ULL << RC_TYPE_RC5_SZ)
+#define RC_BIT_JVC		(1ULL << RC_TYPE_JVC)
+#define RC_BIT_SONY12		(1ULL << RC_TYPE_SONY12)
+#define RC_BIT_SONY15		(1ULL << RC_TYPE_SONY15)
+#define RC_BIT_SONY20		(1ULL << RC_TYPE_SONY20)
+#define RC_BIT_NEC		(1ULL << RC_TYPE_NEC)
+#define RC_BIT_SANYO		(1ULL << RC_TYPE_SANYO)
+#define RC_BIT_MCE_KBD		(1ULL << RC_TYPE_MCE_KBD)
+#define RC_BIT_RC6_0		(1ULL << RC_TYPE_RC6_0)
+#define RC_BIT_RC6_6A_20	(1ULL << RC_TYPE_RC6_6A_20)
+#define RC_BIT_RC6_6A_24	(1ULL << RC_TYPE_RC6_6A_24)
+#define RC_BIT_RC6_6A_32	(1ULL << RC_TYPE_RC6_6A_32)
+#define RC_BIT_RC6_MCE		(1ULL << RC_TYPE_RC6_MCE)
+#define RC_BIT_SHARP		(1ULL << RC_TYPE_SHARP)
+#define RC_BIT_XMP		(1ULL << RC_TYPE_XMP)
 
 #define RC_BIT_ALL	(RC_BIT_UNKNOWN | RC_BIT_OTHER | \
 			 RC_BIT_RC5 | RC_BIT_RC5X | RC_BIT_RC5_SZ | \
diff --git a/include/media/v4l2-clk.h b/include/media/v4l2-clk.h
index 3ef6e3d..2b94662 100644
--- a/include/media/v4l2-clk.h
+++ b/include/media/v4l2-clk.h
@@ -65,7 +65,12 @@
 	return __v4l2_clk_register_fixed(dev_id, rate, THIS_MODULE);
 }
 
+#define V4L2_CLK_NAME_SIZE 64
+
 #define v4l2_clk_name_i2c(name, size, adap, client) snprintf(name, size, \
 			  "%d-%04x", adap, client)
 
+#define v4l2_clk_name_of(name, size, of_full_name) snprintf(name, size, \
+			  "of-%s", of_full_name)
+
 #endif
diff --git a/include/media/v4l2-dv-timings.h b/include/media/v4l2-dv-timings.h
index a209526..1113c88 100644
--- a/include/media/v4l2-dv-timings.h
+++ b/include/media/v4l2-dv-timings.h
@@ -107,12 +107,14 @@
  * @standard:	  the timings according to the standard.
  * @pclock_delta: maximum delta in Hz between standard->pixelclock and
  * 		the measured timings.
+ * @match_reduced_fps: if true, then fail if V4L2_DV_FL_REDUCED_FPS does not
+ * match.
  *
  * Returns true if the two timings match, returns false otherwise.
  */
 bool v4l2_match_dv_timings(const struct v4l2_dv_timings *measured,
 			   const struct v4l2_dv_timings *standard,
-			   unsigned pclock_delta);
+			   unsigned pclock_delta, bool match_reduced_fps);
 
 /**
  * v4l2_print_dv_timings() - log the contents of a dv_timings struct
@@ -183,4 +185,25 @@
  */
 struct v4l2_fract v4l2_calc_aspect_ratio(u8 hor_landscape, u8 vert_portrait);
 
+/*
+ * reduce_fps - check if conditions for reduced fps are true.
+ * bt - v4l2 timing structure
+ * For different timings reduced fps is allowed if following conditions
+ * are met -
+ * For CVT timings: if reduced blanking v2 (vsync == 8) is true.
+ * For CEA861 timings: if V4L2_DV_FL_CAN_REDUCE_FPS flag is true.
+ */
+static inline  bool can_reduce_fps(struct v4l2_bt_timings *bt)
+{
+	if ((bt->standards & V4L2_DV_BT_STD_CVT) && (bt->vsync == 8))
+		return true;
+
+	if ((bt->standards & V4L2_DV_BT_STD_CEA861) &&
+	    (bt->flags & V4L2_DV_FL_CAN_REDUCE_FPS))
+		return true;
+
+	return false;
+}
+
+
 #endif
diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h
index 647ebfe..ef03ae5 100644
--- a/include/media/videobuf2-core.h
+++ b/include/media/videobuf2-core.h
@@ -129,6 +129,8 @@
  * @dbuf_mapped:	flag to show whether dbuf is mapped or not
  * @bytesused:	number of bytes occupied by data in the plane (payload)
  * @length:	size of this plane (NOT the payload) in bytes
+ * @min_length:	minimum required size of this plane (NOT the payload) in bytes.
+ *		@length is always greater or equal to @min_length.
  * @offset:	when memory in the associated struct vb2_buffer is
  *		VB2_MEMORY_MMAP, equals the offset from the start of
  *		the device memory for this plane (or is a "cookie" that
@@ -150,6 +152,7 @@
 	unsigned int		dbuf_mapped;
 	unsigned int		bytesused;
 	unsigned int		length;
+	unsigned int		min_length;
 	union {
 		unsigned int	offset;
 		unsigned long	userptr;
@@ -211,6 +214,7 @@
  * @num_planes:		number of planes in the buffer
  *			on an internal driver queue
  * @planes:		private per-plane information; do not change
+ * @timestamp:		frame timestamp in ns
  */
 struct vb2_buffer {
 	struct vb2_queue	*vb2_queue;
@@ -219,6 +223,7 @@
 	unsigned int		memory;
 	unsigned int		num_planes;
 	struct vb2_plane	planes[VB2_MAX_PLANES];
+	u64			timestamp;
 
 	/* private: internal use only
 	 *
@@ -268,21 +273,26 @@
  * struct vb2_ops - driver-specific callbacks
  *
  * @queue_setup:	called from VIDIOC_REQBUFS and VIDIOC_CREATE_BUFS
- *			handlers before memory allocation, or, if
- *			*num_planes != 0, after the allocation to verify a
- *			smaller number of buffers. Driver should return
- *			the required number of buffers in *num_buffers, the
- *			required number of planes per buffer in *num_planes; the
- *			size of each plane should be set in the sizes[] array
- *			and optional per-plane allocator specific context in the
- *			alloc_ctxs[] array. When called from VIDIOC_REQBUFS,
- *			fmt == NULL, the driver has to use the currently
- *			configured format and *num_buffers is the total number
- *			of buffers, that are being allocated. When called from
- *			VIDIOC_CREATE_BUFS, fmt != NULL and it describes the
- *			target frame format (if the format isn't valid the
- *			callback must return -EINVAL). In this case *num_buffers
- *			are being allocated additionally to q->num_buffers.
+ *			handlers before memory allocation. It can be called
+ *			twice: if the original number of requested buffers
+ *			could not be allocated, then it will be called a
+ *			second time with the actually allocated number of
+ *			buffers to verify if that is OK.
+ *			The driver should return the required number of buffers
+ *			in *num_buffers, the required number of planes per
+ *			buffer in *num_planes, the size of each plane should be
+ *			set in the sizes[] array and optional per-plane
+ *			allocator specific context in the alloc_ctxs[] array.
+ *			When called from VIDIOC_REQBUFS, *num_planes == 0, the
+ *			driver has to use the currently configured format to
+ *			determine the plane sizes and *num_buffers is the total
+ *			number of buffers that are being allocated. When called
+ *			from VIDIOC_CREATE_BUFS, *num_planes != 0 and it
+ *			describes the requested number of planes and sizes[]
+ *			contains the requested plane sizes. If either
+ *			*num_planes or the requested sizes are invalid callback
+ *			must return -EINVAL. In this case *num_buffers are
+ *			being allocated additionally to q->num_buffers.
  * @wait_prepare:	release any locks taken while calling vb2 functions;
  *			it is called before an ioctl needs to wait for a new
  *			buffer to arrive; required to avoid a deadlock in
@@ -344,7 +354,7 @@
  *			pre-queued buffers before calling STREAMON.
  */
 struct vb2_ops {
-	int (*queue_setup)(struct vb2_queue *q, const void *parg,
+	int (*queue_setup)(struct vb2_queue *q,
 			   unsigned int *num_buffers, unsigned int *num_planes,
 			   unsigned int sizes[], void *alloc_ctxs[]);
 
@@ -362,11 +372,22 @@
 	void (*buf_queue)(struct vb2_buffer *vb);
 };
 
+/**
+ * struct vb2_ops - driver-specific callbacks
+ *
+ * @fill_user_buffer:	given a vb2_buffer fill in the userspace structure.
+ *			For V4L2 this is a struct v4l2_buffer.
+ * @fill_vb2_buffer:	given a userspace structure, fill in the vb2_buffer.
+ *			If the userspace structure is invalid, then this op
+ *			will return an error.
+ * @copy_timestamp:	copy the timestamp from a userspace structure to
+ *			the vb2_buffer struct.
+ */
 struct vb2_buf_ops {
-	int (*fill_user_buffer)(struct vb2_buffer *vb, void *pb);
+	void (*fill_user_buffer)(struct vb2_buffer *vb, void *pb);
 	int (*fill_vb2_buffer)(struct vb2_buffer *vb, const void *pb,
 				struct vb2_plane *planes);
-	int (*set_timestamp)(struct vb2_buffer *vb, const void *pb);
+	void (*copy_timestamp)(struct vb2_buffer *vb, const void *pb);
 };
 
 /**
@@ -429,6 +450,7 @@
  *		called since poll() needs to return POLLERR in that situation.
  * @is_multiplanar: set if buffer type is multiplanar
  * @is_output:	set if buffer type is output
+ * @copy_timestamp: set if vb2-core should set timestamps
  * @last_buffer_dequeued: used in poll() and DQBUF to immediately return if the
  *		last decoded buffer was already dequeued. Set for capture queues
  *		when a buffer with the V4L2_BUF_FLAG_LAST is dequeued.
@@ -470,7 +492,6 @@
 	wait_queue_head_t		done_wq;
 
 	void				*alloc_ctx[VB2_MAX_PLANES];
-	unsigned int			plane_sizes[VB2_MAX_PLANES];
 
 	unsigned int			streaming:1;
 	unsigned int			start_streaming_called:1;
@@ -478,6 +499,7 @@
 	unsigned int			waiting_for_buffers:1;
 	unsigned int			is_multiplanar:1;
 	unsigned int			is_output:1;
+	unsigned int			copy_timestamp:1;
 	unsigned int			last_buffer_dequeued:1;
 
 	struct vb2_fileio_data		*fileio;
@@ -503,11 +525,12 @@
 void vb2_discard_done(struct vb2_queue *q);
 int vb2_wait_for_all_buffers(struct vb2_queue *q);
 
-int vb2_core_querybuf(struct vb2_queue *q, unsigned int index, void *pb);
+void vb2_core_querybuf(struct vb2_queue *q, unsigned int index, void *pb);
 int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory,
 		unsigned int *count);
 int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory,
-		unsigned int *count, const void *parg);
+		unsigned int *count, unsigned requested_planes,
+		const unsigned int requested_sizes[]);
 int vb2_core_prepare_buf(struct vb2_queue *q, unsigned int index, void *pb);
 int vb2_core_qbuf(struct vb2_queue *q, unsigned int index, void *pb);
 int vb2_core_dqbuf(struct vb2_queue *q, void *pb, bool nonblocking);
@@ -531,6 +554,42 @@
 				    unsigned long pgoff,
 				    unsigned long flags);
 #endif
+unsigned int vb2_core_poll(struct vb2_queue *q, struct file *file,
+		poll_table *wait);
+size_t vb2_read(struct vb2_queue *q, char __user *data, size_t count,
+		loff_t *ppos, int nonblock);
+size_t vb2_write(struct vb2_queue *q, const char __user *data, size_t count,
+		loff_t *ppos, int nonblock);
+
+/*
+ * vb2_thread_fnc - callback function for use with vb2_thread
+ *
+ * This is called whenever a buffer is dequeued in the thread.
+ */
+typedef int (*vb2_thread_fnc)(struct vb2_buffer *vb, void *priv);
+
+/**
+ * vb2_thread_start() - start a thread for the given queue.
+ * @q:		videobuf queue
+ * @fnc:	callback function
+ * @priv:	priv pointer passed to the callback function
+ * @thread_name:the name of the thread. This will be prefixed with "vb2-".
+ *
+ * This starts a thread that will queue and dequeue until an error occurs
+ * or @vb2_thread_stop is called.
+ *
+ * This function should not be used for anything else but the videobuf2-dvb
+ * support. If you think you have another good use-case for this, then please
+ * contact the linux-media mailinglist first.
+ */
+int vb2_thread_start(struct vb2_queue *q, vb2_thread_fnc fnc, void *priv,
+		     const char *thread_name);
+
+/**
+ * vb2_thread_stop() - stop the thread for the given queue.
+ * @q:		videobuf queue
+ */
+int vb2_thread_stop(struct vb2_queue *q);
 
 /**
  * vb2_is_streaming() - return streaming status of the queue
@@ -635,4 +694,11 @@
 	q->last_buffer_dequeued = false;
 }
 
+/*
+ * The following functions are not part of the vb2 core API, but are useful
+ * functions for videobuf2-*.
+ */
+bool vb2_buffer_in_use(struct vb2_queue *q, struct vb2_buffer *vb);
+int vb2_verify_memory_type(struct vb2_queue *q,
+		enum vb2_memory memory, unsigned int type);
 #endif /* _MEDIA_VIDEOBUF2_CORE_H */
diff --git a/include/media/videobuf2-v4l2.h b/include/media/videobuf2-v4l2.h
index 5abab1e..3cc836f 100644
--- a/include/media/videobuf2-v4l2.h
+++ b/include/media/videobuf2-v4l2.h
@@ -28,7 +28,6 @@
  * @vb2_buf:	video buffer 2
  * @flags:	buffer informational flags
  * @field:	enum v4l2_field; field order of the image in the buffer
- * @timestamp:	frame timestamp
  * @timecode:	frame timecode
  * @sequence:	sequence count of this frame
  * Should contain enough information to be able to cover all the fields
@@ -39,7 +38,6 @@
 
 	__u32			flags;
 	__u32			field;
-	struct timeval		timestamp;
 	struct v4l2_timecode	timecode;
 	__u32			sequence;
 };
@@ -65,42 +63,8 @@
 
 int __must_check vb2_queue_init(struct vb2_queue *q);
 void vb2_queue_release(struct vb2_queue *q);
-
-unsigned int vb2_poll(struct vb2_queue *q, struct file *file, poll_table *wait);
-size_t vb2_read(struct vb2_queue *q, char __user *data, size_t count,
-		loff_t *ppos, int nonblock);
-size_t vb2_write(struct vb2_queue *q, const char __user *data, size_t count,
-		loff_t *ppos, int nonblock);
-
-/*
- * vb2_thread_fnc - callback function for use with vb2_thread
- *
- * This is called whenever a buffer is dequeued in the thread.
- */
-typedef int (*vb2_thread_fnc)(struct vb2_buffer *vb, void *priv);
-
-/**
- * vb2_thread_start() - start a thread for the given queue.
- * @q:		videobuf queue
- * @fnc:	callback function
- * @priv:	priv pointer passed to the callback function
- * @thread_name:the name of the thread. This will be prefixed with "vb2-".
- *
- * This starts a thread that will queue and dequeue until an error occurs
- * or @vb2_thread_stop is called.
- *
- * This function should not be used for anything else but the videobuf2-dvb
- * support. If you think you have another good use-case for this, then please
- * contact the linux-media mailinglist first.
- */
-int vb2_thread_start(struct vb2_queue *q, vb2_thread_fnc fnc, void *priv,
-		     const char *thread_name);
-
-/**
- * vb2_thread_stop() - stop the thread for the given queue.
- * @q:		videobuf queue
- */
-int vb2_thread_stop(struct vb2_queue *q);
+unsigned int vb2_poll(struct vb2_queue *q, struct file *file,
+		poll_table *wait);
 
 /*
  * The following functions are not part of the vb2 core API, but are simple
diff --git a/include/sound/soc.h b/include/sound/soc.h
index a8b4b9c..fb955e6 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -1655,7 +1655,7 @@
 /* Helper functions */
 static inline void snd_soc_dapm_mutex_lock(struct snd_soc_dapm_context *dapm)
 {
-	mutex_lock(&dapm->card->dapm_mutex);
+	mutex_lock_nested(&dapm->card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME);
 }
 
 static inline void snd_soc_dapm_mutex_unlock(struct snd_soc_dapm_context *dapm)
diff --git a/include/trace/events/filelock.h b/include/trace/events/filelock.h
index c72f2dc..63a7680 100644
--- a/include/trace/events/filelock.h
+++ b/include/trace/events/filelock.h
@@ -34,6 +34,83 @@
 			{ F_WRLCK, "F_WRLCK" },		\
 			{ F_UNLCK, "F_UNLCK" })
 
+TRACE_EVENT(locks_get_lock_context,
+	TP_PROTO(struct inode *inode, int type, struct file_lock_context *ctx),
+
+	TP_ARGS(inode, type, ctx),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, i_ino)
+		__field(dev_t, s_dev)
+		__field(unsigned char, type)
+		__field(struct file_lock_context *, ctx)
+	),
+
+	TP_fast_assign(
+		__entry->s_dev = inode->i_sb->s_dev;
+		__entry->i_ino = inode->i_ino;
+		__entry->type = type;
+		__entry->ctx = ctx;
+	),
+
+	TP_printk("dev=0x%x:0x%x ino=0x%lx type=%s ctx=%p",
+		  MAJOR(__entry->s_dev), MINOR(__entry->s_dev),
+		  __entry->i_ino, show_fl_type(__entry->type), __entry->ctx)
+);
+
+DECLARE_EVENT_CLASS(filelock_lock,
+	TP_PROTO(struct inode *inode, struct file_lock *fl, int ret),
+
+	TP_ARGS(inode, fl, ret),
+
+	TP_STRUCT__entry(
+		__field(struct file_lock *, fl)
+		__field(unsigned long, i_ino)
+		__field(dev_t, s_dev)
+		__field(struct file_lock *, fl_next)
+		__field(fl_owner_t, fl_owner)
+		__field(unsigned int, fl_pid)
+		__field(unsigned int, fl_flags)
+		__field(unsigned char, fl_type)
+		__field(loff_t, fl_start)
+		__field(loff_t, fl_end)
+		__field(int, ret)
+	),
+
+	TP_fast_assign(
+		__entry->fl = fl ? fl : NULL;
+		__entry->s_dev = inode->i_sb->s_dev;
+		__entry->i_ino = inode->i_ino;
+		__entry->fl_next = fl ? fl->fl_next : NULL;
+		__entry->fl_owner = fl ? fl->fl_owner : NULL;
+		__entry->fl_pid = fl ? fl->fl_pid : 0;
+		__entry->fl_flags = fl ? fl->fl_flags : 0;
+		__entry->fl_type = fl ? fl->fl_type : 0;
+		__entry->fl_start = fl ? fl->fl_start : 0;
+		__entry->fl_end = fl ? fl->fl_end : 0;
+		__entry->ret = ret;
+	),
+
+	TP_printk("fl=0x%p dev=0x%x:0x%x ino=0x%lx fl_next=0x%p fl_owner=0x%p fl_pid=%u fl_flags=%s fl_type=%s fl_start=%lld fl_end=%lld ret=%d",
+		__entry->fl, MAJOR(__entry->s_dev), MINOR(__entry->s_dev),
+		__entry->i_ino, __entry->fl_next, __entry->fl_owner,
+		__entry->fl_pid, show_fl_flags(__entry->fl_flags),
+		show_fl_type(__entry->fl_type),
+		__entry->fl_start, __entry->fl_end, __entry->ret)
+);
+
+DEFINE_EVENT(filelock_lock, posix_lock_inode,
+		TP_PROTO(struct inode *inode, struct file_lock *fl, int ret),
+		TP_ARGS(inode, fl, ret));
+
+DEFINE_EVENT(filelock_lock, fcntl_setlk,
+		TP_PROTO(struct inode *inode, struct file_lock *fl, int ret),
+		TP_ARGS(inode, fl, ret));
+
+DEFINE_EVENT(filelock_lock, locks_remove_posix,
+		TP_PROTO(struct inode *inode, struct file_lock *fl, int ret),
+		TP_ARGS(inode, fl, ret));
+
 DECLARE_EVENT_CLASS(filelock_lease,
 
 	TP_PROTO(struct inode *inode, struct file_lock *fl),
diff --git a/include/trace/events/v4l2.h b/include/trace/events/v4l2.h
index 22afa26..ee7754c 100644
--- a/include/trace/events/v4l2.h
+++ b/include/trace/events/v4l2.h
@@ -184,7 +184,7 @@
 		__field(int, minor)
 		__field(u32, flags)
 		__field(u32, field)
-		__field(s64, timestamp)
+		__field(u64, timestamp)
 		__field(u32, timecode_type)
 		__field(u32, timecode_flags)
 		__field(u8, timecode_frames)
@@ -205,7 +205,7 @@
 		__entry->minor = owner ? owner->vdev->minor : -1;
 		__entry->flags = vbuf->flags;
 		__entry->field = vbuf->field;
-		__entry->timestamp = timeval_to_ns(&vbuf->timestamp);
+		__entry->timestamp = vb->timestamp;
 		__entry->timecode_type = vbuf->timecode.type;
 		__entry->timecode_flags = vbuf->timecode.flags;
 		__entry->timecode_frames = vbuf->timecode.frames;
diff --git a/include/trace/events/vb2.h b/include/trace/events/vb2.h
index bfeceeb..c1a2241 100644
--- a/include/trace/events/vb2.h
+++ b/include/trace/events/vb2.h
@@ -18,6 +18,7 @@
 		__field(u32, index)
 		__field(u32, type)
 		__field(u32, bytesused)
+		__field(u64, timestamp)
 	),
 
 	TP_fast_assign(
@@ -28,14 +29,16 @@
 		__entry->index = vb->index;
 		__entry->type = vb->type;
 		__entry->bytesused = vb->planes[0].bytesused;
+		__entry->timestamp = vb->timestamp;
 	),
 
 	TP_printk("owner = %p, queued = %u, owned_by_drv = %d, index = %u, "
-		  "type = %u, bytesused = %u", __entry->owner,
+		  "type = %u, bytesused = %u, timestamp = %llu", __entry->owner,
 		  __entry->queued_count,
 		  __entry->owned_by_drv_count,
 		  __entry->index, __entry->type,
-		  __entry->bytesused
+		  __entry->bytesused,
+		  __entry->timestamp
 	)
 )
 
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 1324b02..2622b33 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -715,9 +715,11 @@
 __SYSCALL(__NR_membarrier, sys_membarrier)
 #define __NR_mlock2 284
 __SYSCALL(__NR_mlock2, sys_mlock2)
+#define __NR_copy_file_range 285
+__SYSCALL(__NR_copy_file_range, sys_copy_file_range)
 
 #undef __NR_syscalls
-#define __NR_syscalls 285
+#define __NR_syscalls 286
 
 /*
  * All syscalls below here should go away really,
diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h
index 0b69a77..ee2d542 100644
--- a/include/uapi/drm/drm_fourcc.h
+++ b/include/uapi/drm/drm_fourcc.h
@@ -225,7 +225,7 @@
  * - multiple of 128 pixels for the width
  * - multiple of  32 pixels for the height
  *
- * For more information: see http://linuxtv.org/downloads/v4l-dvb-apis/re32.html
+ * For more information: see https://linuxtv.org/downloads/v4l-dvb-apis/re32.html
  */
 #define DRM_FORMAT_MOD_SAMSUNG_64_32_TILE	fourcc_mod_code(SAMSUNG, 1)
 
diff --git a/include/uapi/linux/dvb/video.h b/include/uapi/linux/dvb/video.h
index d3d14a59..4939256 100644
--- a/include/uapi/linux/dvb/video.h
+++ b/include/uapi/linux/dvb/video.h
@@ -26,7 +26,6 @@
 
 #include <linux/types.h>
 #ifndef __KERNEL__
-#include <stdint.h>
 #include <time.h>
 #endif
 
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index f15d980..b38e647 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -39,12 +39,48 @@
 #define RENAME_EXCHANGE		(1 << 1)	/* Exchange source and dest */
 #define RENAME_WHITEOUT		(1 << 2)	/* Whiteout source */
 
+struct file_clone_range {
+	__s64 src_fd;
+	__u64 src_offset;
+	__u64 src_length;
+	__u64 dest_offset;
+};
+
 struct fstrim_range {
 	__u64 start;
 	__u64 len;
 	__u64 minlen;
 };
 
+/* extent-same (dedupe) ioctls; these MUST match the btrfs ioctl definitions */
+#define FILE_DEDUPE_RANGE_SAME		0
+#define FILE_DEDUPE_RANGE_DIFFERS	1
+
+/* from struct btrfs_ioctl_file_extent_same_info */
+struct file_dedupe_range_info {
+	__s64 dest_fd;		/* in - destination file */
+	__u64 dest_offset;	/* in - start of extent in destination */
+	__u64 bytes_deduped;	/* out - total # of bytes we were able
+				 * to dedupe from this file. */
+	/* status of this dedupe operation:
+	 * < 0 for error
+	 * == FILE_DEDUPE_RANGE_SAME if dedupe succeeds
+	 * == FILE_DEDUPE_RANGE_DIFFERS if data differs
+	 */
+	__s32 status;		/* out - see above description */
+	__u32 reserved;		/* must be zero */
+};
+
+/* from struct btrfs_ioctl_file_extent_same_args */
+struct file_dedupe_range {
+	__u64 src_offset;	/* in - start of extent in source */
+	__u64 src_length;	/* in - length of extent */
+	__u16 dest_count;	/* in - total elements in info array */
+	__u16 reserved1;	/* must be zero */
+	__u32 reserved2;	/* must be zero */
+	struct file_dedupe_range_info info[0];
+};
+
 /* And dynamically-tunable limits and defaults: */
 struct files_stat_struct {
 	unsigned long nr_files;		/* read only */
@@ -159,6 +195,9 @@
 #define FIFREEZE	_IOWR('X', 119, int)	/* Freeze */
 #define FITHAW		_IOWR('X', 120, int)	/* Thaw */
 #define FITRIM		_IOWR('X', 121, struct fstrim_range)	/* Trim */
+#define FICLONE		_IOW(0x94, 9, int)
+#define FICLONERANGE	_IOW(0x94, 13, struct file_clone_range)
+#define FIDEDUPERANGE	_IOWR(0x94, 54, struct file_dedupe_range)
 
 #define	FS_IOC_GETFLAGS			_IOR('f', 1, long)
 #define	FS_IOC_SETFLAGS			_IOW('f', 2, long)
diff --git a/include/uapi/linux/gfs2_ondisk.h b/include/uapi/linux/gfs2_ondisk.h
index 1a763ea..7c4be77 100644
--- a/include/uapi/linux/gfs2_ondisk.h
+++ b/include/uapi/linux/gfs2_ondisk.h
@@ -297,6 +297,8 @@
 
 #define GFS2_FNAMESIZE		255
 #define GFS2_DIRENT_SIZE(name_len) ((sizeof(struct gfs2_dirent) + (name_len) + 7) & ~7)
+#define GFS2_MIN_DIRENT_SIZE (GFS2_DIRENT_SIZE(1))
+
 
 struct gfs2_dirent {
 	struct gfs2_inum de_inum;
@@ -304,11 +306,12 @@
 	__be16 de_rec_len;
 	__be16 de_name_len;
 	__be16 de_type;
+	__be16 de_rahead;
 	union {
-		__u8 __pad[14];
+		__u8 __pad[12];
 		struct {
-			__be16 de_rahead;
-			__u8 pad2[12];
+			__u32 de_cookie; /* ondisk value not used */
+			__u8 pad3[8];
 		};
 	};
 };
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 03f3618..9da9051 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -154,6 +154,20 @@
 	__u32 flags;
 	__u32 reserved[9];
 };
+
+struct kvm_hyperv_exit {
+#define KVM_EXIT_HYPERV_SYNIC          1
+	__u32 type;
+	union {
+		struct {
+			__u32 msr;
+			__u64 control;
+			__u64 evt_page;
+			__u64 msg_page;
+		} synic;
+	} u;
+};
+
 #define KVM_S390_GET_SKEYS_NONE   1
 #define KVM_S390_SKEYS_MAX        1048576
 
@@ -184,6 +198,7 @@
 #define KVM_EXIT_SYSTEM_EVENT     24
 #define KVM_EXIT_S390_STSI        25
 #define KVM_EXIT_IOAPIC_EOI       26
+#define KVM_EXIT_HYPERV           27
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -338,6 +353,8 @@
 		struct {
 			__u8 vector;
 		} eoi;
+		/* KVM_EXIT_HYPERV */
+		struct kvm_hyperv_exit hyperv;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -831,6 +848,8 @@
 #define KVM_CAP_GUEST_DEBUG_HW_WPS 120
 #define KVM_CAP_SPLIT_IRQCHIP 121
 #define KVM_CAP_IOEVENTFD_ANY_LENGTH 122
+#define KVM_CAP_HYPERV_SYNIC 123
+#define KVM_CAP_S390_RI 124
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -854,10 +873,16 @@
 	__u32 adapter_id;
 };
 
+struct kvm_irq_routing_hv_sint {
+	__u32 vcpu;
+	__u32 sint;
+};
+
 /* gsi routing entry types */
 #define KVM_IRQ_ROUTING_IRQCHIP 1
 #define KVM_IRQ_ROUTING_MSI 2
 #define KVM_IRQ_ROUTING_S390_ADAPTER 3
+#define KVM_IRQ_ROUTING_HV_SINT 4
 
 struct kvm_irq_routing_entry {
 	__u32 gsi;
@@ -868,6 +893,7 @@
 		struct kvm_irq_routing_irqchip irqchip;
 		struct kvm_irq_routing_msi msi;
 		struct kvm_irq_routing_s390_adapter adapter;
+		struct kvm_irq_routing_hv_sint hv_sint;
 		__u32 pad[8];
 	} u;
 };
diff --git a/include/uapi/linux/lirc.h b/include/uapi/linux/lirc.h
new file mode 100644
index 0000000..4b3ab29
--- /dev/null
+++ b/include/uapi/linux/lirc.h
@@ -0,0 +1,168 @@
+/*
+ * lirc.h - linux infrared remote control header file
+ * last modified 2010/07/13 by Jarod Wilson
+ */
+
+#ifndef _LINUX_LIRC_H
+#define _LINUX_LIRC_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+#define PULSE_BIT       0x01000000
+#define PULSE_MASK      0x00FFFFFF
+
+#define LIRC_MODE2_SPACE     0x00000000
+#define LIRC_MODE2_PULSE     0x01000000
+#define LIRC_MODE2_FREQUENCY 0x02000000
+#define LIRC_MODE2_TIMEOUT   0x03000000
+
+#define LIRC_VALUE_MASK      0x00FFFFFF
+#define LIRC_MODE2_MASK      0xFF000000
+
+#define LIRC_SPACE(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_SPACE)
+#define LIRC_PULSE(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_PULSE)
+#define LIRC_FREQUENCY(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_FREQUENCY)
+#define LIRC_TIMEOUT(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_TIMEOUT)
+
+#define LIRC_VALUE(val) ((val)&LIRC_VALUE_MASK)
+#define LIRC_MODE2(val) ((val)&LIRC_MODE2_MASK)
+
+#define LIRC_IS_SPACE(val) (LIRC_MODE2(val) == LIRC_MODE2_SPACE)
+#define LIRC_IS_PULSE(val) (LIRC_MODE2(val) == LIRC_MODE2_PULSE)
+#define LIRC_IS_FREQUENCY(val) (LIRC_MODE2(val) == LIRC_MODE2_FREQUENCY)
+#define LIRC_IS_TIMEOUT(val) (LIRC_MODE2(val) == LIRC_MODE2_TIMEOUT)
+
+/* used heavily by lirc userspace */
+#define lirc_t int
+
+/*** lirc compatible hardware features ***/
+
+#define LIRC_MODE2SEND(x) (x)
+#define LIRC_SEND2MODE(x) (x)
+#define LIRC_MODE2REC(x) ((x) << 16)
+#define LIRC_REC2MODE(x) ((x) >> 16)
+
+#define LIRC_MODE_RAW                  0x00000001
+#define LIRC_MODE_PULSE                0x00000002
+#define LIRC_MODE_MODE2                0x00000004
+#define LIRC_MODE_LIRCCODE             0x00000010
+
+
+#define LIRC_CAN_SEND_RAW              LIRC_MODE2SEND(LIRC_MODE_RAW)
+#define LIRC_CAN_SEND_PULSE            LIRC_MODE2SEND(LIRC_MODE_PULSE)
+#define LIRC_CAN_SEND_MODE2            LIRC_MODE2SEND(LIRC_MODE_MODE2)
+#define LIRC_CAN_SEND_LIRCCODE         LIRC_MODE2SEND(LIRC_MODE_LIRCCODE)
+
+#define LIRC_CAN_SEND_MASK             0x0000003f
+
+#define LIRC_CAN_SET_SEND_CARRIER      0x00000100
+#define LIRC_CAN_SET_SEND_DUTY_CYCLE   0x00000200
+#define LIRC_CAN_SET_TRANSMITTER_MASK  0x00000400
+
+#define LIRC_CAN_REC_RAW               LIRC_MODE2REC(LIRC_MODE_RAW)
+#define LIRC_CAN_REC_PULSE             LIRC_MODE2REC(LIRC_MODE_PULSE)
+#define LIRC_CAN_REC_MODE2             LIRC_MODE2REC(LIRC_MODE_MODE2)
+#define LIRC_CAN_REC_LIRCCODE          LIRC_MODE2REC(LIRC_MODE_LIRCCODE)
+
+#define LIRC_CAN_REC_MASK              LIRC_MODE2REC(LIRC_CAN_SEND_MASK)
+
+#define LIRC_CAN_SET_REC_CARRIER       (LIRC_CAN_SET_SEND_CARRIER << 16)
+#define LIRC_CAN_SET_REC_DUTY_CYCLE    (LIRC_CAN_SET_SEND_DUTY_CYCLE << 16)
+
+#define LIRC_CAN_SET_REC_DUTY_CYCLE_RANGE 0x40000000
+#define LIRC_CAN_SET_REC_CARRIER_RANGE    0x80000000
+#define LIRC_CAN_GET_REC_RESOLUTION       0x20000000
+#define LIRC_CAN_SET_REC_TIMEOUT          0x10000000
+#define LIRC_CAN_SET_REC_FILTER           0x08000000
+
+#define LIRC_CAN_MEASURE_CARRIER          0x02000000
+#define LIRC_CAN_USE_WIDEBAND_RECEIVER    0x04000000
+
+#define LIRC_CAN_SEND(x) ((x)&LIRC_CAN_SEND_MASK)
+#define LIRC_CAN_REC(x) ((x)&LIRC_CAN_REC_MASK)
+
+#define LIRC_CAN_NOTIFY_DECODE            0x01000000
+
+/*** IOCTL commands for lirc driver ***/
+
+#define LIRC_GET_FEATURES              _IOR('i', 0x00000000, __u32)
+
+#define LIRC_GET_SEND_MODE             _IOR('i', 0x00000001, __u32)
+#define LIRC_GET_REC_MODE              _IOR('i', 0x00000002, __u32)
+#define LIRC_GET_SEND_CARRIER          _IOR('i', 0x00000003, __u32)
+#define LIRC_GET_REC_CARRIER           _IOR('i', 0x00000004, __u32)
+#define LIRC_GET_SEND_DUTY_CYCLE       _IOR('i', 0x00000005, __u32)
+#define LIRC_GET_REC_DUTY_CYCLE        _IOR('i', 0x00000006, __u32)
+#define LIRC_GET_REC_RESOLUTION        _IOR('i', 0x00000007, __u32)
+
+#define LIRC_GET_MIN_TIMEOUT           _IOR('i', 0x00000008, __u32)
+#define LIRC_GET_MAX_TIMEOUT           _IOR('i', 0x00000009, __u32)
+
+#define LIRC_GET_MIN_FILTER_PULSE      _IOR('i', 0x0000000a, __u32)
+#define LIRC_GET_MAX_FILTER_PULSE      _IOR('i', 0x0000000b, __u32)
+#define LIRC_GET_MIN_FILTER_SPACE      _IOR('i', 0x0000000c, __u32)
+#define LIRC_GET_MAX_FILTER_SPACE      _IOR('i', 0x0000000d, __u32)
+
+/* code length in bits, currently only for LIRC_MODE_LIRCCODE */
+#define LIRC_GET_LENGTH                _IOR('i', 0x0000000f, __u32)
+
+#define LIRC_SET_SEND_MODE             _IOW('i', 0x00000011, __u32)
+#define LIRC_SET_REC_MODE              _IOW('i', 0x00000012, __u32)
+/* Note: these can reset the according pulse_width */
+#define LIRC_SET_SEND_CARRIER          _IOW('i', 0x00000013, __u32)
+#define LIRC_SET_REC_CARRIER           _IOW('i', 0x00000014, __u32)
+#define LIRC_SET_SEND_DUTY_CYCLE       _IOW('i', 0x00000015, __u32)
+#define LIRC_SET_REC_DUTY_CYCLE        _IOW('i', 0x00000016, __u32)
+#define LIRC_SET_TRANSMITTER_MASK      _IOW('i', 0x00000017, __u32)
+
+/*
+ * when a timeout != 0 is set the driver will send a
+ * LIRC_MODE2_TIMEOUT data packet, otherwise LIRC_MODE2_TIMEOUT is
+ * never sent, timeout is disabled by default
+ */
+#define LIRC_SET_REC_TIMEOUT           _IOW('i', 0x00000018, __u32)
+
+/* 1 enables, 0 disables timeout reports in MODE2 */
+#define LIRC_SET_REC_TIMEOUT_REPORTS   _IOW('i', 0x00000019, __u32)
+
+/*
+ * pulses shorter than this are filtered out by hardware (software
+ * emulation in lirc_dev?)
+ */
+#define LIRC_SET_REC_FILTER_PULSE      _IOW('i', 0x0000001a, __u32)
+/*
+ * spaces shorter than this are filtered out by hardware (software
+ * emulation in lirc_dev?)
+ */
+#define LIRC_SET_REC_FILTER_SPACE      _IOW('i', 0x0000001b, __u32)
+/*
+ * if filter cannot be set independently for pulse/space, this should
+ * be used
+ */
+#define LIRC_SET_REC_FILTER            _IOW('i', 0x0000001c, __u32)
+
+/*
+ * if enabled from the next key press on the driver will send
+ * LIRC_MODE2_FREQUENCY packets
+ */
+#define LIRC_SET_MEASURE_CARRIER_MODE	_IOW('i', 0x0000001d, __u32)
+
+/*
+ * to set a range use
+ * LIRC_SET_REC_DUTY_CYCLE_RANGE/LIRC_SET_REC_CARRIER_RANGE with the
+ * lower bound first and later
+ * LIRC_SET_REC_DUTY_CYCLE/LIRC_SET_REC_CARRIER with the upper bound
+ */
+
+#define LIRC_SET_REC_DUTY_CYCLE_RANGE  _IOW('i', 0x0000001e, __u32)
+#define LIRC_SET_REC_CARRIER_RANGE     _IOW('i', 0x0000001f, __u32)
+
+#define LIRC_NOTIFY_DECODE             _IO('i', 0x00000020)
+
+#define LIRC_SETUP_START               _IO('i', 0x00000021)
+#define LIRC_SETUP_END                 _IO('i', 0x00000022)
+
+#define LIRC_SET_WIDEBAND_RECEIVER     _IOW('i', 0x00000023, __u32)
+
+#endif
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index d801bb0..1afe962 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -171,6 +171,9 @@
 	PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT	= 12, /* indirect jumps */
 	PERF_SAMPLE_BRANCH_CALL_SHIFT		= 13, /* direct call */
 
+	PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT	= 14, /* no flags */
+	PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT	= 15, /* no cycles */
+
 	PERF_SAMPLE_BRANCH_MAX_SHIFT		/* non-ABI */
 };
 
@@ -192,6 +195,9 @@
 	PERF_SAMPLE_BRANCH_IND_JUMP	= 1U << PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT,
 	PERF_SAMPLE_BRANCH_CALL		= 1U << PERF_SAMPLE_BRANCH_CALL_SHIFT,
 
+	PERF_SAMPLE_BRANCH_NO_FLAGS	= 1U << PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT,
+	PERF_SAMPLE_BRANCH_NO_CYCLES	= 1U << PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT,
+
 	PERF_SAMPLE_BRANCH_MAX		= 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT,
 };
 
diff --git a/include/uapi/linux/usb/video.h b/include/uapi/linux/usb/video.h
index 3b3b95e..69ab695 100644
--- a/include/uapi/linux/usb/video.h
+++ b/include/uapi/linux/usb/video.h
@@ -28,6 +28,7 @@
 
 /* A.3. Video Interface Protocol Codes */
 #define UVC_PC_PROTOCOL_UNDEFINED			0x00
+#define UVC_PC_PROTOCOL_15				0x01
 
 /* A.5. Video Class-Specific VC Interface Descriptor Subtypes */
 #define UVC_VC_DESCRIPTOR_UNDEFINED			0x00
diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h
index 1bdce50..2d225bc 100644
--- a/include/uapi/linux/v4l2-controls.h
+++ b/include/uapi/linux/v4l2-controls.h
@@ -158,8 +158,10 @@
  * We reserve 16 controls for this driver. */
 #define V4L2_CID_USER_S2255_BASE		(V4L2_CID_USER_BASE + 0x1030)
 
-/* The base for the si476x driver controls. See include/media/si476x.h for the list
- * of controls. Total of 16 controls is reserved for this driver */
+/*
+ * The base for the si476x driver controls. See include/media/drv-intf/si476x.h
+ * for the list of controls. Total of 16 controls is reserved for this driver
+ */
 #define V4L2_CID_USER_SI476X_BASE		(V4L2_CID_USER_BASE + 0x1040)
 
 /* The base for the TI VPE driver controls. Total of 16 controls is reserved for
diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h
index a0e87d1..14cd5eb 100644
--- a/include/uapi/linux/videodev2.h
+++ b/include/uapi/linux/videodev2.h
@@ -46,7 +46,7 @@
  * All kernel-specific stuff were moved to media/v4l2-dev.h, so
  * no #if __KERNEL tests are allowed here
  *
- *	See http://linuxtv.org for more info
+ *	See https://linuxtv.org for more info
  *
  *	Author: Bill Dirks <bill@thedirks.org>
  *		Justin Schoeman
@@ -1476,7 +1476,12 @@
 } __attribute__ ((packed));
 
 struct v4l2_ext_controls {
-	__u32 ctrl_class;
+	union {
+#ifndef __KERNEL__
+		__u32 ctrl_class;
+#endif
+		__u32 which;
+	};
 	__u32 count;
 	__u32 error_idx;
 	__u32 reserved[2];
@@ -1484,9 +1489,14 @@
 };
 
 #define V4L2_CTRL_ID_MASK      	  (0x0fffffff)
+#ifndef __KERNEL__
 #define V4L2_CTRL_ID2CLASS(id)    ((id) & 0x0fff0000UL)
+#endif
+#define V4L2_CTRL_ID2WHICH(id)    ((id) & 0x0fff0000UL)
 #define V4L2_CTRL_DRIVER_PRIV(id) (((id) & 0xffff) >= 0x1000)
 #define V4L2_CTRL_MAX_DIMS	  (4)
+#define V4L2_CTRL_WHICH_CUR_VAL   0
+#define V4L2_CTRL_WHICH_DEF_VAL   0x0f000000
 
 enum v4l2_ctrl_type {
 	V4L2_CTRL_TYPE_INTEGER	     = 1,
diff --git a/include/uapi/xen/gntdev.h b/include/uapi/xen/gntdev.h
index aa7610a..d066197 100644
--- a/include/uapi/xen/gntdev.h
+++ b/include/uapi/xen/gntdev.h
@@ -144,6 +144,56 @@
 	__u32 event_channel_port;
 };
 
+struct gntdev_grant_copy_segment {
+	union {
+		void __user *virt;
+		struct {
+			grant_ref_t ref;
+			__u16 offset;
+			domid_t domid;
+		} foreign;
+	} source, dest;
+	__u16 len;
+
+	__u16 flags;  /* GNTCOPY_* */
+	__s16 status; /* GNTST_* */
+};
+
+/*
+ * Copy between grant references and local buffers.
+ *
+ * The copy is split into @count @segments, each of which can copy
+ * to/from one grant reference.
+ *
+ * Each segment is similar to struct gnttab_copy in the hypervisor ABI
+ * except the local buffer is specified using a virtual address
+ * (instead of a GFN and offset).
+ *
+ * The local buffer may cross a Xen page boundary -- the driver will
+ * split segments into multiple ops if required.
+ *
+ * Returns 0 if all segments have been processed and @status in each
+ * segment is valid.  Note that one or more segments may have failed
+ * (status != GNTST_okay).
+ *
+ * If the driver had to split a segment into two or more ops, @status
+ * includes the status of the first failed op for that segment (or
+ * GNTST_okay if all ops were successful).
+ *
+ * If -1 is returned, the status of all segments is undefined.
+ *
+ * EINVAL: A segment has local buffers for both source and
+ *         destination.
+ * EINVAL: A segment crosses the boundary of a foreign page.
+ * EFAULT: A segment's local buffer is not accessible.
+ */
+#define IOCTL_GNTDEV_GRANT_COPY \
+	_IOC(_IOC_NONE, 'G', 8, sizeof(struct ioctl_gntdev_grant_copy))
+struct ioctl_gntdev_grant_copy {
+	unsigned int count;
+	struct gntdev_grant_copy_segment __user *segments;
+};
+
 /* Clear (set to zero) the byte specified by index */
 #define UNMAP_NOTIFY_CLEAR_BYTE 0x1
 /* Send an interrupt on the indicated event channel */
diff --git a/include/xen/interface/platform.h b/include/xen/interface/platform.h
index 8e03587..732efb0 100644
--- a/include/xen/interface/platform.h
+++ b/include/xen/interface/platform.h
@@ -35,14 +35,23 @@
  * Set clock such that it would read <secs,nsecs> after 00:00:00 UTC,
  * 1 January, 1970 if the current system time was <system_time>.
  */
-#define XENPF_settime             17
-struct xenpf_settime {
+#define XENPF_settime32             17
+struct xenpf_settime32 {
 	/* IN variables. */
 	uint32_t secs;
 	uint32_t nsecs;
 	uint64_t system_time;
 };
-DEFINE_GUEST_HANDLE_STRUCT(xenpf_settime_t);
+DEFINE_GUEST_HANDLE_STRUCT(xenpf_settime32_t);
+#define XENPF_settime64           62
+struct xenpf_settime64 {
+    /* IN variables. */
+    uint64_t secs;
+    uint32_t nsecs;
+    uint32_t mbz;
+    uint64_t system_time;
+};
+DEFINE_GUEST_HANDLE_STRUCT(xenpf_settime64_t);
 
 /*
  * Request memory range (@mfn, @mfn+@nr_mfns-1) to have type @type.
@@ -495,7 +504,8 @@
 	uint32_t cmd;
 	uint32_t interface_version; /* XENPF_INTERFACE_VERSION */
 	union {
-		struct xenpf_settime           settime;
+		struct xenpf_settime32         settime32;
+		struct xenpf_settime64         settime64;
 		struct xenpf_add_memtype       add_memtype;
 		struct xenpf_del_memtype       del_memtype;
 		struct xenpf_read_memtype      read_memtype;
diff --git a/include/xen/interface/xen.h b/include/xen/interface/xen.h
index 167071c..d133112 100644
--- a/include/xen/interface/xen.h
+++ b/include/xen/interface/xen.h
@@ -48,7 +48,7 @@
 #define __HYPERVISOR_set_callbacks         4
 #define __HYPERVISOR_fpu_taskswitch        5
 #define __HYPERVISOR_sched_op_compat       6
-#define __HYPERVISOR_dom0_op               7
+#define __HYPERVISOR_platform_op           7
 #define __HYPERVISOR_set_debugreg          8
 #define __HYPERVISOR_get_debugreg          9
 #define __HYPERVISOR_update_descriptor    10
diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h
index e4e214a..86abe07 100644
--- a/include/xen/xen-ops.h
+++ b/include/xen/xen-ops.h
@@ -5,6 +5,7 @@
 #include <linux/notifier.h>
 #include <linux/efi.h>
 #include <asm/xen/interface.h>
+#include <xen/interface/vcpu.h>
 
 DECLARE_PER_CPU(struct vcpu_info *, xen_vcpu);
 
@@ -18,6 +19,10 @@
 void xen_resume_notifier_register(struct notifier_block *nb);
 void xen_resume_notifier_unregister(struct notifier_block *nb);
 
+bool xen_vcpu_stolen(int vcpu);
+void xen_setup_runstate_info(int cpu);
+void xen_get_runstate_snapshot(struct vcpu_runstate_info *res);
+
 int xen_setup_shutdown_event(void);
 
 extern unsigned long *xen_contiguous_bitmap;
diff --git a/init/main.c b/init/main.c
index 9e64d70..c6ebefa 100644
--- a/init/main.c
+++ b/init/main.c
@@ -943,6 +943,8 @@
 
 	flush_delayed_fput();
 
+	rcu_end_inkernel_boot();
+
 	if (ramdisk_execute_command) {
 		ret = run_init_process(ramdisk_execute_command);
 		if (!ret)
diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c
index d8560ee..9ad37b9 100644
--- a/kernel/context_tracking.c
+++ b/kernel/context_tracking.c
@@ -24,7 +24,7 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/context_tracking.h>
 
-struct static_key context_tracking_enabled = STATIC_KEY_INIT_FALSE;
+DEFINE_STATIC_KEY_FALSE(context_tracking_enabled);
 EXPORT_SYMBOL_GPL(context_tracking_enabled);
 
 DEFINE_PER_CPU(struct context_tracking, context_tracking);
@@ -191,7 +191,7 @@
 
 	if (!per_cpu(context_tracking.active, cpu)) {
 		per_cpu(context_tracking.active, cpu) = true;
-		static_key_slow_inc(&context_tracking_enabled);
+		static_branch_inc(&context_tracking_enabled);
 	}
 
 	if (initialized)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index ef2d6ea..bf82441 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -126,6 +126,37 @@
 	return data.ret;
 }
 
+static void event_function_call(struct perf_event *event,
+				int (*active)(void *),
+				void (*inactive)(void *),
+				void *data)
+{
+	struct perf_event_context *ctx = event->ctx;
+	struct task_struct *task = ctx->task;
+
+	if (!task) {
+		cpu_function_call(event->cpu, active, data);
+		return;
+	}
+
+again:
+	if (!task_function_call(task, active, data))
+		return;
+
+	raw_spin_lock_irq(&ctx->lock);
+	if (ctx->is_active) {
+		/*
+		 * Reload the task pointer, it might have been changed by
+		 * a concurrent perf_event_context_sched_out().
+		 */
+		task = ctx->task;
+		raw_spin_unlock_irq(&ctx->lock);
+		goto again;
+	}
+	inactive(data);
+	raw_spin_unlock_irq(&ctx->lock);
+}
+
 #define EVENT_OWNER_KERNEL ((void *) -1)
 
 static bool is_kernel_event(struct perf_event *event)
@@ -1629,6 +1660,17 @@
 	bool detach_group;
 };
 
+static void ___perf_remove_from_context(void *info)
+{
+	struct remove_event *re = info;
+	struct perf_event *event = re->event;
+	struct perf_event_context *ctx = event->ctx;
+
+	if (re->detach_group)
+		perf_group_detach(event);
+	list_del_event(event, ctx);
+}
+
 /*
  * Cross CPU call to remove a performance event
  *
@@ -1656,7 +1698,6 @@
 	return 0;
 }
 
-
 /*
  * Remove the event from a task's (or a CPU's) list of events.
  *
@@ -1673,7 +1714,6 @@
 static void perf_remove_from_context(struct perf_event *event, bool detach_group)
 {
 	struct perf_event_context *ctx = event->ctx;
-	struct task_struct *task = ctx->task;
 	struct remove_event re = {
 		.event = event,
 		.detach_group = detach_group,
@@ -1681,44 +1721,8 @@
 
 	lockdep_assert_held(&ctx->mutex);
 
-	if (!task) {
-		/*
-		 * Per cpu events are removed via an smp call. The removal can
-		 * fail if the CPU is currently offline, but in that case we
-		 * already called __perf_remove_from_context from
-		 * perf_event_exit_cpu.
-		 */
-		cpu_function_call(event->cpu, __perf_remove_from_context, &re);
-		return;
-	}
-
-retry:
-	if (!task_function_call(task, __perf_remove_from_context, &re))
-		return;
-
-	raw_spin_lock_irq(&ctx->lock);
-	/*
-	 * If we failed to find a running task, but find the context active now
-	 * that we've acquired the ctx->lock, retry.
-	 */
-	if (ctx->is_active) {
-		raw_spin_unlock_irq(&ctx->lock);
-		/*
-		 * Reload the task pointer, it might have been changed by
-		 * a concurrent perf_event_context_sched_out().
-		 */
-		task = ctx->task;
-		goto retry;
-	}
-
-	/*
-	 * Since the task isn't running, its safe to remove the event, us
-	 * holding the ctx->lock ensures the task won't get scheduled in.
-	 */
-	if (detach_group)
-		perf_group_detach(event);
-	list_del_event(event, ctx);
-	raw_spin_unlock_irq(&ctx->lock);
+	event_function_call(event, __perf_remove_from_context,
+			    ___perf_remove_from_context, &re);
 }
 
 /*
@@ -1762,6 +1766,20 @@
 	return 0;
 }
 
+void ___perf_event_disable(void *info)
+{
+	struct perf_event *event = info;
+
+	/*
+	 * Since we have the lock this context can't be scheduled
+	 * in, so we can change the state safely.
+	 */
+	if (event->state == PERF_EVENT_STATE_INACTIVE) {
+		update_group_times(event);
+		event->state = PERF_EVENT_STATE_OFF;
+	}
+}
+
 /*
  * Disable a event.
  *
@@ -1778,43 +1796,16 @@
 static void _perf_event_disable(struct perf_event *event)
 {
 	struct perf_event_context *ctx = event->ctx;
-	struct task_struct *task = ctx->task;
-
-	if (!task) {
-		/*
-		 * Disable the event on the cpu that it's on
-		 */
-		cpu_function_call(event->cpu, __perf_event_disable, event);
-		return;
-	}
-
-retry:
-	if (!task_function_call(task, __perf_event_disable, event))
-		return;
 
 	raw_spin_lock_irq(&ctx->lock);
-	/*
-	 * If the event is still active, we need to retry the cross-call.
-	 */
-	if (event->state == PERF_EVENT_STATE_ACTIVE) {
+	if (event->state <= PERF_EVENT_STATE_OFF) {
 		raw_spin_unlock_irq(&ctx->lock);
-		/*
-		 * Reload the task pointer, it might have been changed by
-		 * a concurrent perf_event_context_sched_out().
-		 */
-		task = ctx->task;
-		goto retry;
-	}
-
-	/*
-	 * Since we have the lock this context can't be scheduled
-	 * in, so we can change the state safely.
-	 */
-	if (event->state == PERF_EVENT_STATE_INACTIVE) {
-		update_group_times(event);
-		event->state = PERF_EVENT_STATE_OFF;
+		return;
 	}
 	raw_spin_unlock_irq(&ctx->lock);
+
+	event_function_call(event, __perf_event_disable,
+			    ___perf_event_disable, event);
 }
 
 /*
@@ -2067,6 +2058,18 @@
 		ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE, task);
 }
 
+static void ___perf_install_in_context(void *info)
+{
+	struct perf_event *event = info;
+	struct perf_event_context *ctx = event->ctx;
+
+	/*
+	 * Since the task isn't running, its safe to add the event, us holding
+	 * the ctx->lock ensures the task won't get scheduled in.
+	 */
+	add_event_to_ctx(event, ctx);
+}
+
 /*
  * Cross CPU call to install and enable a performance event
  *
@@ -2143,48 +2146,14 @@
 			struct perf_event *event,
 			int cpu)
 {
-	struct task_struct *task = ctx->task;
-
 	lockdep_assert_held(&ctx->mutex);
 
 	event->ctx = ctx;
 	if (event->cpu != -1)
 		event->cpu = cpu;
 
-	if (!task) {
-		/*
-		 * Per cpu events are installed via an smp call and
-		 * the install is always successful.
-		 */
-		cpu_function_call(cpu, __perf_install_in_context, event);
-		return;
-	}
-
-retry:
-	if (!task_function_call(task, __perf_install_in_context, event))
-		return;
-
-	raw_spin_lock_irq(&ctx->lock);
-	/*
-	 * If we failed to find a running task, but find the context active now
-	 * that we've acquired the ctx->lock, retry.
-	 */
-	if (ctx->is_active) {
-		raw_spin_unlock_irq(&ctx->lock);
-		/*
-		 * Reload the task pointer, it might have been changed by
-		 * a concurrent perf_event_context_sched_out().
-		 */
-		task = ctx->task;
-		goto retry;
-	}
-
-	/*
-	 * Since the task isn't running, its safe to add the event, us holding
-	 * the ctx->lock ensures the task won't get scheduled in.
-	 */
-	add_event_to_ctx(event, ctx);
-	raw_spin_unlock_irq(&ctx->lock);
+	event_function_call(event, __perf_install_in_context,
+			    ___perf_install_in_context, event);
 }
 
 /*
@@ -2287,6 +2256,11 @@
 	return 0;
 }
 
+void ___perf_event_enable(void *info)
+{
+	__perf_event_mark_enabled((struct perf_event *)info);
+}
+
 /*
  * Enable a event.
  *
@@ -2299,58 +2273,26 @@
 static void _perf_event_enable(struct perf_event *event)
 {
 	struct perf_event_context *ctx = event->ctx;
-	struct task_struct *task = ctx->task;
-
-	if (!task) {
-		/*
-		 * Enable the event on the cpu that it's on
-		 */
-		cpu_function_call(event->cpu, __perf_event_enable, event);
-		return;
-	}
 
 	raw_spin_lock_irq(&ctx->lock);
-	if (event->state >= PERF_EVENT_STATE_INACTIVE)
-		goto out;
+	if (event->state >= PERF_EVENT_STATE_INACTIVE) {
+		raw_spin_unlock_irq(&ctx->lock);
+		return;
+	}
 
 	/*
 	 * If the event is in error state, clear that first.
-	 * That way, if we see the event in error state below, we
-	 * know that it has gone back into error state, as distinct
-	 * from the task having been scheduled away before the
-	 * cross-call arrived.
+	 *
+	 * That way, if we see the event in error state below, we know that it
+	 * has gone back into error state, as distinct from the task having
+	 * been scheduled away before the cross-call arrived.
 	 */
 	if (event->state == PERF_EVENT_STATE_ERROR)
 		event->state = PERF_EVENT_STATE_OFF;
-
-retry:
-	if (!ctx->is_active) {
-		__perf_event_mark_enabled(event);
-		goto out;
-	}
-
 	raw_spin_unlock_irq(&ctx->lock);
 
-	if (!task_function_call(task, __perf_event_enable, event))
-		return;
-
-	raw_spin_lock_irq(&ctx->lock);
-
-	/*
-	 * If the context is active and the event is still off,
-	 * we need to retry the cross-call.
-	 */
-	if (ctx->is_active && event->state == PERF_EVENT_STATE_OFF) {
-		/*
-		 * task could have been flipped by a concurrent
-		 * perf_event_context_sched_out()
-		 */
-		task = ctx->task;
-		goto retry;
-	}
-
-out:
-	raw_spin_unlock_irq(&ctx->lock);
+	event_function_call(event, __perf_event_enable,
+			    ___perf_event_enable, event);
 }
 
 /*
@@ -3154,15 +3096,16 @@
  * Enable all of a task's events that have been marked enable-on-exec.
  * This expects task == current.
  */
-static void perf_event_enable_on_exec(struct perf_event_context *ctx)
+static void perf_event_enable_on_exec(int ctxn)
 {
-	struct perf_event_context *clone_ctx = NULL;
+	struct perf_event_context *ctx, *clone_ctx = NULL;
 	struct perf_event *event;
 	unsigned long flags;
 	int enabled = 0;
 	int ret;
 
 	local_irq_save(flags);
+	ctx = current->perf_event_ctxp[ctxn];
 	if (!ctx || !ctx->nr_events)
 		goto out;
 
@@ -3205,17 +3148,11 @@
 
 void perf_event_exec(void)
 {
-	struct perf_event_context *ctx;
 	int ctxn;
 
 	rcu_read_lock();
-	for_each_task_context_nr(ctxn) {
-		ctx = current->perf_event_ctxp[ctxn];
-		if (!ctx)
-			continue;
-
-		perf_event_enable_on_exec(ctx);
-	}
+	for_each_task_context_nr(ctxn)
+		perf_event_enable_on_exec(ctxn);
 	rcu_read_unlock();
 }
 
@@ -4154,6 +4091,22 @@
 	u64 value;
 };
 
+static void ___perf_event_period(void *info)
+{
+	struct period_event *pe = info;
+	struct perf_event *event = pe->event;
+	u64 value = pe->value;
+
+	if (event->attr.freq) {
+		event->attr.sample_freq = value;
+	} else {
+		event->attr.sample_period = value;
+		event->hw.sample_period = value;
+	}
+
+	local64_set(&event->hw.period_left, 0);
+}
+
 static int __perf_event_period(void *info)
 {
 	struct period_event *pe = info;
@@ -4190,8 +4143,6 @@
 static int perf_event_period(struct perf_event *event, u64 __user *arg)
 {
 	struct period_event pe = { .event = event, };
-	struct perf_event_context *ctx = event->ctx;
-	struct task_struct *task;
 	u64 value;
 
 	if (!is_sampling_event(event))
@@ -4206,34 +4157,10 @@
 	if (event->attr.freq && value > sysctl_perf_event_sample_rate)
 		return -EINVAL;
 
-	task = ctx->task;
 	pe.value = value;
 
-	if (!task) {
-		cpu_function_call(event->cpu, __perf_event_period, &pe);
-		return 0;
-	}
-
-retry:
-	if (!task_function_call(task, __perf_event_period, &pe))
-		return 0;
-
-	raw_spin_lock_irq(&ctx->lock);
-	if (ctx->is_active) {
-		raw_spin_unlock_irq(&ctx->lock);
-		task = ctx->task;
-		goto retry;
-	}
-
-	if (event->attr.freq) {
-		event->attr.sample_freq = value;
-	} else {
-		event->attr.sample_period = value;
-		event->hw.sample_period = value;
-	}
-
-	local64_set(&event->hw.period_left, 0);
-	raw_spin_unlock_irq(&ctx->lock);
+	event_function_call(event, __perf_event_period,
+			    ___perf_event_period, &pe);
 
 	return 0;
 }
@@ -6493,9 +6420,6 @@
 
 	/* Recursion avoidance in each contexts */
 	int				recursion[PERF_NR_CONTEXTS];
-
-	/* Keeps track of cpu being initialized/exited */
-	bool				online;
 };
 
 static DEFINE_PER_CPU(struct swevent_htable, swevent_htable);
@@ -6753,14 +6677,8 @@
 	hwc->state = !(flags & PERF_EF_START);
 
 	head = find_swevent_head(swhash, event);
-	if (!head) {
-		/*
-		 * We can race with cpu hotplug code. Do not
-		 * WARN if the cpu just got unplugged.
-		 */
-		WARN_ON_ONCE(swhash->online);
+	if (WARN_ON_ONCE(!head))
 		return -EINVAL;
-	}
 
 	hlist_add_head_rcu(&event->hlist_entry, head);
 	perf_event_update_userpage(event);
@@ -6828,7 +6746,6 @@
 	int err = 0;
 
 	mutex_lock(&swhash->hlist_mutex);
-
 	if (!swevent_hlist_deref(swhash) && cpu_online(cpu)) {
 		struct swevent_hlist *hlist;
 
@@ -9291,7 +9208,6 @@
 	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
 
 	mutex_lock(&swhash->hlist_mutex);
-	swhash->online = true;
 	if (swhash->hlist_refcount > 0) {
 		struct swevent_hlist *hlist;
 
@@ -9333,14 +9249,7 @@
 
 static void perf_event_exit_cpu(int cpu)
 {
-	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
-
 	perf_event_exit_cpu_context(cpu);
-
-	mutex_lock(&swhash->hlist_mutex);
-	swhash->online = false;
-	swevent_hlist_release(swhash);
-	mutex_unlock(&swhash->hlist_mutex);
 }
 #else
 static inline void perf_event_exit_cpu(int cpu) { }
diff --git a/kernel/fork.c b/kernel/fork.c
index fce002e..291b08c 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -380,6 +380,7 @@
 #endif
 	tsk->splice_pipe = NULL;
 	tsk->task_frag.page = NULL;
+	tsk->wake_q.next = NULL;
 
 	account_kernel_stack(ti, 1);
 
@@ -1348,9 +1349,9 @@
 	prev_cputime_init(&p->prev_cputime);
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
-	seqlock_init(&p->vtime_seqlock);
+	seqcount_init(&p->vtime_seqcount);
 	p->vtime_snap = 0;
-	p->vtime_snap_whence = VTIME_SLEEPING;
+	p->vtime_snap_whence = VTIME_INACTIVE;
 #endif
 
 #if defined(SPLIT_RSS_COUNTING)
diff --git a/kernel/futex.c b/kernel/futex.c
index 684d754..8a310e2 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -725,9 +725,12 @@
 }
 
 /*
+ * Drops a reference to the pi_state object and frees or caches it
+ * when the last reference is gone.
+ *
  * Must be called with the hb lock held.
  */
-static void free_pi_state(struct futex_pi_state *pi_state)
+static void put_pi_state(struct futex_pi_state *pi_state)
 {
 	if (!pi_state)
 		return;
@@ -1706,31 +1709,35 @@
 		 * exist yet, look it up one more time to ensure we have a
 		 * reference to it. If the lock was taken, ret contains the
 		 * vpid of the top waiter task.
+		 * If the lock was not taken, we have pi_state and an initial
+		 * refcount on it. In case of an error we have nothing.
 		 */
 		if (ret > 0) {
 			WARN_ON(pi_state);
 			drop_count++;
 			task_count++;
 			/*
-			 * If we acquired the lock, then the user
-			 * space value of uaddr2 should be vpid. It
-			 * cannot be changed by the top waiter as it
-			 * is blocked on hb2 lock if it tries to do
-			 * so. If something fiddled with it behind our
-			 * back the pi state lookup might unearth
-			 * it. So we rather use the known value than
-			 * rereading and handing potential crap to
-			 * lookup_pi_state.
+			 * If we acquired the lock, then the user space value
+			 * of uaddr2 should be vpid. It cannot be changed by
+			 * the top waiter as it is blocked on hb2 lock if it
+			 * tries to do so. If something fiddled with it behind
+			 * our back the pi state lookup might unearth it. So
+			 * we rather use the known value than rereading and
+			 * handing potential crap to lookup_pi_state.
+			 *
+			 * If that call succeeds then we have pi_state and an
+			 * initial refcount on it.
 			 */
 			ret = lookup_pi_state(ret, hb2, &key2, &pi_state);
 		}
 
 		switch (ret) {
 		case 0:
+			/* We hold a reference on the pi state. */
 			break;
+
+			/* If the above failed, then pi_state is NULL */
 		case -EFAULT:
-			free_pi_state(pi_state);
-			pi_state = NULL;
 			double_unlock_hb(hb1, hb2);
 			hb_waiters_dec(hb2);
 			put_futex_key(&key2);
@@ -1746,8 +1753,6 @@
 			 *   exit to complete.
 			 * - The user space value changed.
 			 */
-			free_pi_state(pi_state);
-			pi_state = NULL;
 			double_unlock_hb(hb1, hb2);
 			hb_waiters_dec(hb2);
 			put_futex_key(&key2);
@@ -1801,30 +1806,58 @@
 		 * of requeue_pi if we couldn't acquire the lock atomically.
 		 */
 		if (requeue_pi) {
-			/* Prepare the waiter to take the rt_mutex. */
+			/*
+			 * Prepare the waiter to take the rt_mutex. Take a
+			 * refcount on the pi_state and store the pointer in
+			 * the futex_q object of the waiter.
+			 */
 			atomic_inc(&pi_state->refcount);
 			this->pi_state = pi_state;
 			ret = rt_mutex_start_proxy_lock(&pi_state->pi_mutex,
 							this->rt_waiter,
 							this->task);
 			if (ret == 1) {
-				/* We got the lock. */
+				/*
+				 * We got the lock. We do neither drop the
+				 * refcount on pi_state nor clear
+				 * this->pi_state because the waiter needs the
+				 * pi_state for cleaning up the user space
+				 * value. It will drop the refcount after
+				 * doing so.
+				 */
 				requeue_pi_wake_futex(this, &key2, hb2);
 				drop_count++;
 				continue;
 			} else if (ret) {
-				/* -EDEADLK */
+				/*
+				 * rt_mutex_start_proxy_lock() detected a
+				 * potential deadlock when we tried to queue
+				 * that waiter. Drop the pi_state reference
+				 * which we took above and remove the pointer
+				 * to the state from the waiters futex_q
+				 * object.
+				 */
 				this->pi_state = NULL;
-				free_pi_state(pi_state);
-				goto out_unlock;
+				put_pi_state(pi_state);
+				/*
+				 * We stop queueing more waiters and let user
+				 * space deal with the mess.
+				 */
+				break;
 			}
 		}
 		requeue_futex(this, hb1, hb2, &key2);
 		drop_count++;
 	}
 
+	/*
+	 * We took an extra initial reference to the pi_state either
+	 * in futex_proxy_trylock_atomic() or in lookup_pi_state(). We
+	 * need to drop it here again.
+	 */
+	put_pi_state(pi_state);
+
 out_unlock:
-	free_pi_state(pi_state);
 	double_unlock_hb(hb1, hb2);
 	wake_up_q(&wake_q);
 	hb_waiters_dec(hb2);
@@ -1973,7 +2006,7 @@
 	__unqueue_futex(q);
 
 	BUG_ON(!q->pi_state);
-	free_pi_state(q->pi_state);
+	put_pi_state(q->pi_state);
 	q->pi_state = NULL;
 
 	spin_unlock(q->lock_ptr);
@@ -2755,6 +2788,11 @@
 		if (q.pi_state && (q.pi_state->owner != current)) {
 			spin_lock(q.lock_ptr);
 			ret = fixup_pi_state_owner(uaddr2, &q, current);
+			/*
+			 * Drop the reference to the pi state which
+			 * the requeue_pi() code acquired for us.
+			 */
+			put_pi_state(q.pi_state);
 			spin_unlock(q.lock_ptr);
 		}
 	} else {
@@ -3046,7 +3084,8 @@
 
 	if (op & FUTEX_CLOCK_REALTIME) {
 		flags |= FLAGS_CLOCKRT;
-		if (cmd != FUTEX_WAIT_BITSET && cmd != FUTEX_WAIT_REQUEUE_PI)
+		if (cmd != FUTEX_WAIT && cmd != FUTEX_WAIT_BITSET && \
+		    cmd != FUTEX_WAIT_REQUEUE_PI)
 			return -ENOSYS;
 	}
 
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 1520645..5797909 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -338,7 +338,6 @@
 	raw_spin_lock_irq(&desc->lock);
 
 	desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
-	kstat_incr_irqs_this_cpu(desc);
 
 	action = desc->action;
 	if (unlikely(!action || irqd_irq_disabled(&desc->irq_data))) {
@@ -346,6 +345,7 @@
 		goto out_unlock;
 	}
 
+	kstat_incr_irqs_this_cpu(desc);
 	irqd_set(&desc->irq_data, IRQD_IRQ_INPROGRESS);
 	raw_spin_unlock_irq(&desc->lock);
 
@@ -412,13 +412,13 @@
 		goto out_unlock;
 
 	desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
-	kstat_incr_irqs_this_cpu(desc);
 
 	if (unlikely(!desc->action || irqd_irq_disabled(&desc->irq_data))) {
 		desc->istate |= IRQS_PENDING;
 		goto out_unlock;
 	}
 
+	kstat_incr_irqs_this_cpu(desc);
 	handle_irq_event(desc);
 
 out_unlock:
@@ -462,7 +462,6 @@
 		goto out_unlock;
 
 	desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
-	kstat_incr_irqs_this_cpu(desc);
 
 	/*
 	 * If its disabled or no action available
@@ -473,6 +472,7 @@
 		goto out_unlock;
 	}
 
+	kstat_incr_irqs_this_cpu(desc);
 	handle_irq_event(desc);
 
 	cond_unmask_irq(desc);
@@ -532,7 +532,6 @@
 		goto out;
 
 	desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
-	kstat_incr_irqs_this_cpu(desc);
 
 	/*
 	 * If its disabled or no action available
@@ -544,6 +543,7 @@
 		goto out;
 	}
 
+	kstat_incr_irqs_this_cpu(desc);
 	if (desc->istate & IRQS_ONESHOT)
 		mask_irq(desc);
 
@@ -950,6 +950,7 @@
 	data = data->parent_data;
 	data->chip->irq_ack(data);
 }
+EXPORT_SYMBOL_GPL(irq_chip_ack_parent);
 
 /**
  * irq_chip_mask_parent - Mask the parent interrupt
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 239e2ae..0409da0 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -159,6 +159,7 @@
 
 	raw_spin_lock_init(&desc->lock);
 	lockdep_set_class(&desc->lock, &irq_desc_lock_class);
+	init_rcu_head(&desc->rcu);
 
 	desc_set_defaults(irq, desc, node, owner);
 
@@ -171,6 +172,15 @@
 	return NULL;
 }
 
+static void delayed_free_desc(struct rcu_head *rhp)
+{
+	struct irq_desc *desc = container_of(rhp, struct irq_desc, rcu);
+
+	free_masks(desc);
+	free_percpu(desc->kstat_irqs);
+	kfree(desc);
+}
+
 static void free_desc(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
@@ -187,9 +197,12 @@
 	delete_irq_desc(irq);
 	mutex_unlock(&sparse_irq_lock);
 
-	free_masks(desc);
-	free_percpu(desc->kstat_irqs);
-	kfree(desc);
+	/*
+	 * We free the descriptor, masks and stat fields via RCU. That
+	 * allows demultiplex interrupts to do rcu based management of
+	 * the child interrupts.
+	 */
+	call_rcu(&desc->rcu, delayed_free_desc);
 }
 
 static int alloc_descs(unsigned int start, unsigned int cnt, int node,
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 22aa961..8cf95de 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -60,6 +60,7 @@
 	fwid->fwnode.type = FWNODE_IRQCHIP;
 	return &fwid->fwnode;
 }
+EXPORT_SYMBOL_GPL(irq_domain_alloc_fwnode);
 
 /**
  * irq_domain_free_fwnode - Free a non-OF-backed fwnode_handle
@@ -70,13 +71,14 @@
 {
 	struct irqchip_fwid *fwid;
 
-	if (WARN_ON(fwnode->type != FWNODE_IRQCHIP))
+	if (WARN_ON(!is_fwnode_irqchip(fwnode)))
 		return;
 
 	fwid = container_of(fwnode, struct irqchip_fwid, fwnode);
 	kfree(fwid->name);
 	kfree(fwid);
 }
+EXPORT_SYMBOL_GPL(irq_domain_free_fwnode);
 
 /**
  * __irq_domain_add() - Allocate a new irq_domain data structure
@@ -1013,6 +1015,7 @@
 
 	return NULL;
 }
+EXPORT_SYMBOL_GPL(irq_domain_get_irq_data);
 
 /**
  * irq_domain_set_hwirq_and_chip - Set hwirq and irqchip of @virq at @domain
@@ -1125,9 +1128,9 @@
 	}
 }
 
-static int irq_domain_alloc_irqs_recursive(struct irq_domain *domain,
-					   unsigned int irq_base,
-					   unsigned int nr_irqs, void *arg)
+int irq_domain_alloc_irqs_recursive(struct irq_domain *domain,
+				    unsigned int irq_base,
+				    unsigned int nr_irqs, void *arg)
 {
 	int ret = 0;
 	struct irq_domain *parent = domain->parent;
@@ -1343,6 +1346,7 @@
 
 	return (irq_data && irq_data->domain == domain) ? irq_data : NULL;
 }
+EXPORT_SYMBOL_GPL(irq_domain_get_irq_data);
 
 /**
  * irq_domain_set_info - Set the complete data for a @virq in @domain
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 0eebaee..8411872 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1434,6 +1434,7 @@
 	if (!desc)
 		return NULL;
 
+	chip_bus_lock(desc);
 	raw_spin_lock_irqsave(&desc->lock, flags);
 
 	/*
@@ -1447,7 +1448,7 @@
 		if (!action) {
 			WARN(1, "Trying to free already-free IRQ %d\n", irq);
 			raw_spin_unlock_irqrestore(&desc->lock, flags);
-
+			chip_bus_sync_unlock(desc);
 			return NULL;
 		}
 
@@ -1475,6 +1476,7 @@
 #endif
 
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
+	chip_bus_sync_unlock(desc);
 
 	unregister_handler_proc(irq, action);
 
@@ -1553,9 +1555,7 @@
 		desc->affinity_notify = NULL;
 #endif
 
-	chip_bus_lock(desc);
 	kfree(__free_irq(irq, dev_id));
-	chip_bus_sync_unlock(desc);
 }
 EXPORT_SYMBOL(free_irq);
 
@@ -1743,6 +1743,31 @@
 }
 EXPORT_SYMBOL_GPL(enable_percpu_irq);
 
+/**
+ * irq_percpu_is_enabled - Check whether the per cpu irq is enabled
+ * @irq:	Linux irq number to check for
+ *
+ * Must be called from a non migratable context. Returns the enable
+ * state of a per cpu interrupt on the current cpu.
+ */
+bool irq_percpu_is_enabled(unsigned int irq)
+{
+	unsigned int cpu = smp_processor_id();
+	struct irq_desc *desc;
+	unsigned long flags;
+	bool is_enabled;
+
+	desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_PERCPU);
+	if (!desc)
+		return false;
+
+	is_enabled = cpumask_test_cpu(cpu, desc->percpu_enabled);
+	irq_put_desc_unlock(desc, flags);
+
+	return is_enabled;
+}
+EXPORT_SYMBOL_GPL(irq_percpu_is_enabled);
+
 void disable_percpu_irq(unsigned int irq)
 {
 	unsigned int cpu = smp_processor_id();
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index 6b0c0b7..15b249e 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -252,6 +252,60 @@
 					   &msi_domain_ops, info);
 }
 
+int msi_domain_prepare_irqs(struct irq_domain *domain, struct device *dev,
+			    int nvec, msi_alloc_info_t *arg)
+{
+	struct msi_domain_info *info = domain->host_data;
+	struct msi_domain_ops *ops = info->ops;
+	int ret;
+
+	ret = ops->msi_check(domain, info, dev);
+	if (ret == 0)
+		ret = ops->msi_prepare(domain, dev, nvec, arg);
+
+	return ret;
+}
+
+int msi_domain_populate_irqs(struct irq_domain *domain, struct device *dev,
+			     int virq, int nvec, msi_alloc_info_t *arg)
+{
+	struct msi_domain_info *info = domain->host_data;
+	struct msi_domain_ops *ops = info->ops;
+	struct msi_desc *desc;
+	int ret = 0;
+
+	for_each_msi_entry(desc, dev) {
+		/* Don't even try the multi-MSI brain damage. */
+		if (WARN_ON(!desc->irq || desc->nvec_used != 1)) {
+			ret = -EINVAL;
+			break;
+		}
+
+		if (!(desc->irq >= virq && desc->irq < (virq + nvec)))
+			continue;
+
+		ops->set_desc(arg, desc);
+		/* Assumes the domain mutex is held! */
+		ret = irq_domain_alloc_irqs_recursive(domain, virq, 1, arg);
+		if (ret)
+			break;
+
+		irq_set_msi_desc_off(virq, 0, desc);
+	}
+
+	if (ret) {
+		/* Mop up the damage */
+		for_each_msi_entry(desc, dev) {
+			if (!(desc->irq >= virq && desc->irq < (virq + nvec)))
+				continue;
+
+			irq_domain_free_irqs_common(domain, desc->irq, 1);
+		}
+	}
+
+	return ret;
+}
+
 /**
  * msi_domain_alloc_irqs - Allocate interrupts from a MSI interrupt domain
  * @domain:	The domain to allocate from
@@ -270,9 +324,7 @@
 	struct msi_desc *desc;
 	int i, ret, virq = -1;
 
-	ret = ops->msi_check(domain, info, dev);
-	if (ret == 0)
-		ret = ops->msi_prepare(domain, dev, nvec, &arg);
+	ret = msi_domain_prepare_irqs(domain, dev, nvec, &arg);
 	if (ret)
 		return ret;
 
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index 11b64a6..c823f30 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -853,7 +853,12 @@
 struct kimage *kexec_crash_image;
 int kexec_load_disabled;
 
-void crash_kexec(struct pt_regs *regs)
+/*
+ * No panic_cpu check version of crash_kexec().  This function is called
+ * only when panic_cpu holds the current CPU number; this is the only CPU
+ * which processes crash_kexec routines.
+ */
+void __crash_kexec(struct pt_regs *regs)
 {
 	/* Take the kexec_mutex here to prevent sys_kexec_load
 	 * running on one cpu from replacing the crash kernel
@@ -876,6 +881,29 @@
 	}
 }
 
+void crash_kexec(struct pt_regs *regs)
+{
+	int old_cpu, this_cpu;
+
+	/*
+	 * Only one CPU is allowed to execute the crash_kexec() code as with
+	 * panic().  Otherwise parallel calls of panic() and crash_kexec()
+	 * may stop each other.  To exclude them, we use panic_cpu here too.
+	 */
+	this_cpu = raw_smp_processor_id();
+	old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, this_cpu);
+	if (old_cpu == PANIC_CPU_INVALID) {
+		/* This is the 1st CPU which comes here, so go ahead. */
+		__crash_kexec(regs);
+
+		/*
+		 * Reset panic_cpu to allow another panic()/crash_kexec()
+		 * call.
+		 */
+		atomic_set(&panic_cpu, PANIC_CPU_INVALID);
+	}
+}
+
 size_t crash_get_memory_size(void)
 {
 	size_t size = 0;
diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c
index e83b264..152da4a 100644
--- a/kernel/ksysfs.c
+++ b/kernel/ksysfs.c
@@ -20,7 +20,7 @@
 #include <linux/capability.h>
 #include <linux/compiler.h>
 
-#include <linux/rcupdate.h>	/* rcu_expedited */
+#include <linux/rcupdate.h>	/* rcu_expedited and rcu_normal */
 
 #define KERNEL_ATTR_RO(_name) \
 static struct kobj_attribute _name##_attr = __ATTR_RO(_name)
@@ -144,11 +144,12 @@
 }
 KERNEL_ATTR_RO(fscaps);
 
+#ifndef CONFIG_TINY_RCU
 int rcu_expedited;
 static ssize_t rcu_expedited_show(struct kobject *kobj,
 				  struct kobj_attribute *attr, char *buf)
 {
-	return sprintf(buf, "%d\n", rcu_expedited);
+	return sprintf(buf, "%d\n", READ_ONCE(rcu_expedited));
 }
 static ssize_t rcu_expedited_store(struct kobject *kobj,
 				   struct kobj_attribute *attr,
@@ -161,6 +162,24 @@
 }
 KERNEL_ATTR_RW(rcu_expedited);
 
+int rcu_normal;
+static ssize_t rcu_normal_show(struct kobject *kobj,
+			       struct kobj_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%d\n", READ_ONCE(rcu_normal));
+}
+static ssize_t rcu_normal_store(struct kobject *kobj,
+				struct kobj_attribute *attr,
+				const char *buf, size_t count)
+{
+	if (kstrtoint(buf, 0, &rcu_normal))
+		return -EINVAL;
+
+	return count;
+}
+KERNEL_ATTR_RW(rcu_normal);
+#endif /* #ifndef CONFIG_TINY_RCU */
+
 /*
  * Make /sys/kernel/notes give the raw contents of our kernel .notes section.
  */
@@ -202,7 +221,10 @@
 	&kexec_crash_size_attr.attr,
 	&vmcoreinfo_attr.attr,
 #endif
+#ifndef CONFIG_TINY_RCU
 	&rcu_expedited_attr.attr,
+	&rcu_normal_attr.attr,
+#endif
 	NULL
 };
 
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index 87e9ce6a..393d187 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -14,8 +14,9 @@
  * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P.
  * (C) Copyright 2013-2014 Red Hat, Inc.
  * (C) Copyright 2015 Intel Corp.
+ * (C) Copyright 2015 Hewlett-Packard Enterprise Development LP
  *
- * Authors: Waiman Long <waiman.long@hp.com>
+ * Authors: Waiman Long <waiman.long@hpe.com>
  *          Peter Zijlstra <peterz@infradead.org>
  */
 
@@ -176,7 +177,12 @@
 {
 	struct __qspinlock *l = (void *)lock;
 
-	return (u32)xchg(&l->tail, tail >> _Q_TAIL_OFFSET) << _Q_TAIL_OFFSET;
+	/*
+	 * Use release semantics to make sure that the MCS node is properly
+	 * initialized before changing the tail code.
+	 */
+	return (u32)xchg_release(&l->tail,
+				 tail >> _Q_TAIL_OFFSET) << _Q_TAIL_OFFSET;
 }
 
 #else /* _Q_PENDING_BITS == 8 */
@@ -208,7 +214,11 @@
 
 	for (;;) {
 		new = (val & _Q_LOCKED_PENDING_MASK) | tail;
-		old = atomic_cmpxchg(&lock->val, val, new);
+		/*
+		 * Use release semantics to make sure that the MCS node is
+		 * properly initialized before changing the tail code.
+		 */
+		old = atomic_cmpxchg_release(&lock->val, val, new);
 		if (old == val)
 			break;
 
@@ -238,18 +248,20 @@
  */
 
 static __always_inline void __pv_init_node(struct mcs_spinlock *node) { }
-static __always_inline void __pv_wait_node(struct mcs_spinlock *node) { }
+static __always_inline void __pv_wait_node(struct mcs_spinlock *node,
+					   struct mcs_spinlock *prev) { }
 static __always_inline void __pv_kick_node(struct qspinlock *lock,
 					   struct mcs_spinlock *node) { }
-static __always_inline void __pv_wait_head(struct qspinlock *lock,
-					   struct mcs_spinlock *node) { }
+static __always_inline u32  __pv_wait_head_or_lock(struct qspinlock *lock,
+						   struct mcs_spinlock *node)
+						   { return 0; }
 
 #define pv_enabled()		false
 
 #define pv_init_node		__pv_init_node
 #define pv_wait_node		__pv_wait_node
 #define pv_kick_node		__pv_kick_node
-#define pv_wait_head		__pv_wait_head
+#define pv_wait_head_or_lock	__pv_wait_head_or_lock
 
 #ifdef CONFIG_PARAVIRT_SPINLOCKS
 #define queued_spin_lock_slowpath	native_queued_spin_lock_slowpath
@@ -319,7 +331,11 @@
 		if (val == new)
 			new |= _Q_PENDING_VAL;
 
-		old = atomic_cmpxchg(&lock->val, val, new);
+		/*
+		 * Acquire semantic is required here as the function may
+		 * return immediately if the lock was free.
+		 */
+		old = atomic_cmpxchg_acquire(&lock->val, val, new);
 		if (old == val)
 			break;
 
@@ -382,6 +398,7 @@
 	 * p,*,* -> n,*,*
 	 */
 	old = xchg_tail(lock, tail);
+	next = NULL;
 
 	/*
 	 * if there was a previous node; link it and wait until reaching the
@@ -391,8 +408,18 @@
 		prev = decode_tail(old);
 		WRITE_ONCE(prev->next, node);
 
-		pv_wait_node(node);
+		pv_wait_node(node, prev);
 		arch_mcs_spin_lock_contended(&node->locked);
+
+		/*
+		 * While waiting for the MCS lock, the next pointer may have
+		 * been set by another lock waiter. We optimistically load
+		 * the next pointer & prefetch the cacheline for writing
+		 * to reduce latency in the upcoming MCS unlock operation.
+		 */
+		next = READ_ONCE(node->next);
+		if (next)
+			prefetchw(next);
 	}
 
 	/*
@@ -406,11 +433,22 @@
 	 * sequentiality; this is because the set_locked() function below
 	 * does not imply a full barrier.
 	 *
+	 * The PV pv_wait_head_or_lock function, if active, will acquire
+	 * the lock and return a non-zero value. So we have to skip the
+	 * smp_load_acquire() call. As the next PV queue head hasn't been
+	 * designated yet, there is no way for the locked value to become
+	 * _Q_SLOW_VAL. So both the set_locked() and the
+	 * atomic_cmpxchg_relaxed() calls will be safe.
+	 *
+	 * If PV isn't active, 0 will be returned instead.
+	 *
 	 */
-	pv_wait_head(lock, node);
-	while ((val = smp_load_acquire(&lock->val.counter)) & _Q_LOCKED_PENDING_MASK)
-		cpu_relax();
+	if ((val = pv_wait_head_or_lock(lock, node)))
+		goto locked;
 
+	smp_cond_acquire(!((val = atomic_read(&lock->val)) & _Q_LOCKED_PENDING_MASK));
+
+locked:
 	/*
 	 * claim the lock:
 	 *
@@ -422,11 +460,17 @@
 	 * to grab the lock.
 	 */
 	for (;;) {
-		if (val != tail) {
+		/* In the PV case we might already have _Q_LOCKED_VAL set */
+		if ((val & _Q_TAIL_MASK) != tail) {
 			set_locked(lock);
 			break;
 		}
-		old = atomic_cmpxchg(&lock->val, val, _Q_LOCKED_VAL);
+		/*
+		 * The smp_load_acquire() call above has provided the necessary
+		 * acquire semantics required for locking. At most two
+		 * iterations of this loop may be ran.
+		 */
+		old = atomic_cmpxchg_relaxed(&lock->val, val, _Q_LOCKED_VAL);
 		if (old == val)
 			goto release;	/* No contention */
 
@@ -434,10 +478,12 @@
 	}
 
 	/*
-	 * contended path; wait for next, release.
+	 * contended path; wait for next if not observed yet, release.
 	 */
-	while (!(next = READ_ONCE(node->next)))
-		cpu_relax();
+	if (!next) {
+		while (!(next = READ_ONCE(node->next)))
+			cpu_relax();
+	}
 
 	arch_mcs_spin_unlock_contended(&next->locked);
 	pv_kick_node(lock, next);
@@ -462,7 +508,7 @@
 #undef pv_init_node
 #undef pv_wait_node
 #undef pv_kick_node
-#undef pv_wait_head
+#undef pv_wait_head_or_lock
 
 #undef  queued_spin_lock_slowpath
 #define queued_spin_lock_slowpath	__pv_queued_spin_lock_slowpath
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index f0450ff..87bb235 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -23,6 +23,20 @@
 #define _Q_SLOW_VAL	(3U << _Q_LOCKED_OFFSET)
 
 /*
+ * Queue Node Adaptive Spinning
+ *
+ * A queue node vCPU will stop spinning if the vCPU in the previous node is
+ * not running. The one lock stealing attempt allowed at slowpath entry
+ * mitigates the slight slowdown for non-overcommitted guest with this
+ * aggressive wait-early mechanism.
+ *
+ * The status of the previous node will be checked at fixed interval
+ * controlled by PV_PREV_CHECK_MASK. This is to ensure that we won't
+ * pound on the cacheline of the previous node too heavily.
+ */
+#define PV_PREV_CHECK_MASK	0xff
+
+/*
  * Queue node uses: vcpu_running & vcpu_halted.
  * Queue head uses: vcpu_running & vcpu_hashed.
  */
@@ -41,6 +55,94 @@
 };
 
 /*
+ * By replacing the regular queued_spin_trylock() with the function below,
+ * it will be called once when a lock waiter enter the PV slowpath before
+ * being queued. By allowing one lock stealing attempt here when the pending
+ * bit is off, it helps to reduce the performance impact of lock waiter
+ * preemption without the drawback of lock starvation.
+ */
+#define queued_spin_trylock(l)	pv_queued_spin_steal_lock(l)
+static inline bool pv_queued_spin_steal_lock(struct qspinlock *lock)
+{
+	struct __qspinlock *l = (void *)lock;
+
+	return !(atomic_read(&lock->val) & _Q_LOCKED_PENDING_MASK) &&
+		(cmpxchg(&l->locked, 0, _Q_LOCKED_VAL) == 0);
+}
+
+/*
+ * The pending bit is used by the queue head vCPU to indicate that it
+ * is actively spinning on the lock and no lock stealing is allowed.
+ */
+#if _Q_PENDING_BITS == 8
+static __always_inline void set_pending(struct qspinlock *lock)
+{
+	struct __qspinlock *l = (void *)lock;
+
+	WRITE_ONCE(l->pending, 1);
+}
+
+static __always_inline void clear_pending(struct qspinlock *lock)
+{
+	struct __qspinlock *l = (void *)lock;
+
+	WRITE_ONCE(l->pending, 0);
+}
+
+/*
+ * The pending bit check in pv_queued_spin_steal_lock() isn't a memory
+ * barrier. Therefore, an atomic cmpxchg() is used to acquire the lock
+ * just to be sure that it will get it.
+ */
+static __always_inline int trylock_clear_pending(struct qspinlock *lock)
+{
+	struct __qspinlock *l = (void *)lock;
+
+	return !READ_ONCE(l->locked) &&
+	       (cmpxchg(&l->locked_pending, _Q_PENDING_VAL, _Q_LOCKED_VAL)
+			== _Q_PENDING_VAL);
+}
+#else /* _Q_PENDING_BITS == 8 */
+static __always_inline void set_pending(struct qspinlock *lock)
+{
+	atomic_set_mask(_Q_PENDING_VAL, &lock->val);
+}
+
+static __always_inline void clear_pending(struct qspinlock *lock)
+{
+	atomic_clear_mask(_Q_PENDING_VAL, &lock->val);
+}
+
+static __always_inline int trylock_clear_pending(struct qspinlock *lock)
+{
+	int val = atomic_read(&lock->val);
+
+	for (;;) {
+		int old, new;
+
+		if (val  & _Q_LOCKED_MASK)
+			break;
+
+		/*
+		 * Try to clear pending bit & set locked bit
+		 */
+		old = val;
+		new = (val & ~_Q_PENDING_MASK) | _Q_LOCKED_VAL;
+		val = atomic_cmpxchg(&lock->val, old, new);
+
+		if (val == old)
+			return 1;
+	}
+	return 0;
+}
+#endif /* _Q_PENDING_BITS == 8 */
+
+/*
+ * Include queued spinlock statistics code
+ */
+#include "qspinlock_stat.h"
+
+/*
  * Lock and MCS node addresses hash table for fast lookup
  *
  * Hashing is done on a per-cacheline basis to minimize the need to access
@@ -100,10 +202,13 @@
 {
 	unsigned long offset, hash = hash_ptr(lock, pv_lock_hash_bits);
 	struct pv_hash_entry *he;
+	int hopcnt = 0;
 
 	for_each_hash_entry(he, offset, hash) {
+		hopcnt++;
 		if (!cmpxchg(&he->lock, NULL, lock)) {
 			WRITE_ONCE(he->node, node);
+			qstat_hop(hopcnt);
 			return &he->lock;
 		}
 	}
@@ -144,6 +249,20 @@
 }
 
 /*
+ * Return true if when it is time to check the previous node which is not
+ * in a running state.
+ */
+static inline bool
+pv_wait_early(struct pv_node *prev, int loop)
+{
+
+	if ((loop & PV_PREV_CHECK_MASK) != 0)
+		return false;
+
+	return READ_ONCE(prev->state) != vcpu_running;
+}
+
+/*
  * Initialize the PV part of the mcs_spinlock node.
  */
 static void pv_init_node(struct mcs_spinlock *node)
@@ -161,15 +280,23 @@
  * pv_kick_node() is used to set _Q_SLOW_VAL and fill in hash table on its
  * behalf.
  */
-static void pv_wait_node(struct mcs_spinlock *node)
+static void pv_wait_node(struct mcs_spinlock *node, struct mcs_spinlock *prev)
 {
 	struct pv_node *pn = (struct pv_node *)node;
+	struct pv_node *pp = (struct pv_node *)prev;
+	int waitcnt = 0;
 	int loop;
+	bool wait_early;
 
-	for (;;) {
-		for (loop = SPIN_THRESHOLD; loop; loop--) {
+	/* waitcnt processing will be compiled out if !QUEUED_LOCK_STAT */
+	for (;; waitcnt++) {
+		for (wait_early = false, loop = SPIN_THRESHOLD; loop; loop--) {
 			if (READ_ONCE(node->locked))
 				return;
+			if (pv_wait_early(pp, loop)) {
+				wait_early = true;
+				break;
+			}
 			cpu_relax();
 		}
 
@@ -184,12 +311,17 @@
 		 */
 		smp_store_mb(pn->state, vcpu_halted);
 
-		if (!READ_ONCE(node->locked))
+		if (!READ_ONCE(node->locked)) {
+			qstat_inc(qstat_pv_wait_node, true);
+			qstat_inc(qstat_pv_wait_again, waitcnt);
+			qstat_inc(qstat_pv_wait_early, wait_early);
 			pv_wait(&pn->state, vcpu_halted);
+		}
 
 		/*
-		 * If pv_kick_node() changed us to vcpu_hashed, retain that value
-		 * so that pv_wait_head() knows to not also try to hash this lock.
+		 * If pv_kick_node() changed us to vcpu_hashed, retain that
+		 * value so that pv_wait_head_or_lock() knows to not also try
+		 * to hash this lock.
 		 */
 		cmpxchg(&pn->state, vcpu_halted, vcpu_running);
 
@@ -200,6 +332,7 @@
 		 * So it is better to spin for a while in the hope that the
 		 * MCS lock will be released soon.
 		 */
+		qstat_inc(qstat_pv_spurious_wakeup, !READ_ONCE(node->locked));
 	}
 
 	/*
@@ -212,8 +345,9 @@
 /*
  * Called after setting next->locked = 1 when we're the lock owner.
  *
- * Instead of waking the waiters stuck in pv_wait_node() advance their state such
- * that they're waiting in pv_wait_head(), this avoids a wake/sleep cycle.
+ * Instead of waking the waiters stuck in pv_wait_node() advance their state
+ * such that they're waiting in pv_wait_head_or_lock(), this avoids a
+ * wake/sleep cycle.
  */
 static void pv_kick_node(struct qspinlock *lock, struct mcs_spinlock *node)
 {
@@ -242,14 +376,19 @@
 }
 
 /*
- * Wait for l->locked to become clear; halt the vcpu after a short spin.
+ * Wait for l->locked to become clear and acquire the lock;
+ * halt the vcpu after a short spin.
  * __pv_queued_spin_unlock() will wake us.
+ *
+ * The current value of the lock will be returned for additional processing.
  */
-static void pv_wait_head(struct qspinlock *lock, struct mcs_spinlock *node)
+static u32
+pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node)
 {
 	struct pv_node *pn = (struct pv_node *)node;
 	struct __qspinlock *l = (void *)lock;
 	struct qspinlock **lp = NULL;
+	int waitcnt = 0;
 	int loop;
 
 	/*
@@ -259,12 +398,25 @@
 	if (READ_ONCE(pn->state) == vcpu_hashed)
 		lp = (struct qspinlock **)1;
 
-	for (;;) {
+	for (;; waitcnt++) {
+		/*
+		 * Set correct vCPU state to be used by queue node wait-early
+		 * mechanism.
+		 */
+		WRITE_ONCE(pn->state, vcpu_running);
+
+		/*
+		 * Set the pending bit in the active lock spinning loop to
+		 * disable lock stealing before attempting to acquire the lock.
+		 */
+		set_pending(lock);
 		for (loop = SPIN_THRESHOLD; loop; loop--) {
-			if (!READ_ONCE(l->locked))
-				return;
+			if (trylock_clear_pending(lock))
+				goto gotlock;
 			cpu_relax();
 		}
+		clear_pending(lock);
+
 
 		if (!lp) { /* ONCE */
 			lp = pv_hash(lock, pn);
@@ -280,51 +432,50 @@
 			 *
 			 * Matches the smp_rmb() in __pv_queued_spin_unlock().
 			 */
-			if (!cmpxchg(&l->locked, _Q_LOCKED_VAL, _Q_SLOW_VAL)) {
+			if (xchg(&l->locked, _Q_SLOW_VAL) == 0) {
 				/*
-				 * The lock is free and _Q_SLOW_VAL has never
-				 * been set. Therefore we need to unhash before
-				 * getting the lock.
+				 * The lock was free and now we own the lock.
+				 * Change the lock value back to _Q_LOCKED_VAL
+				 * and unhash the table.
 				 */
+				WRITE_ONCE(l->locked, _Q_LOCKED_VAL);
 				WRITE_ONCE(*lp, NULL);
-				return;
+				goto gotlock;
 			}
 		}
+		WRITE_ONCE(pn->state, vcpu_halted);
+		qstat_inc(qstat_pv_wait_head, true);
+		qstat_inc(qstat_pv_wait_again, waitcnt);
 		pv_wait(&l->locked, _Q_SLOW_VAL);
 
 		/*
 		 * The unlocker should have freed the lock before kicking the
 		 * CPU. So if the lock is still not free, it is a spurious
-		 * wakeup and so the vCPU should wait again after spinning for
-		 * a while.
+		 * wakeup or another vCPU has stolen the lock. The current
+		 * vCPU should spin again.
 		 */
+		qstat_inc(qstat_pv_spurious_wakeup, READ_ONCE(l->locked));
 	}
 
 	/*
-	 * Lock is unlocked now; the caller will acquire it without waiting.
-	 * As with pv_wait_node() we rely on the caller to do a load-acquire
-	 * for us.
+	 * The cmpxchg() or xchg() call before coming here provides the
+	 * acquire semantics for locking. The dummy ORing of _Q_LOCKED_VAL
+	 * here is to indicate to the compiler that the value will always
+	 * be nozero to enable better code optimization.
 	 */
+gotlock:
+	return (u32)(atomic_read(&lock->val) | _Q_LOCKED_VAL);
 }
 
 /*
- * PV version of the unlock function to be used in stead of
- * queued_spin_unlock().
+ * PV versions of the unlock fastpath and slowpath functions to be used
+ * instead of queued_spin_unlock().
  */
-__visible void __pv_queued_spin_unlock(struct qspinlock *lock)
+__visible void
+__pv_queued_spin_unlock_slowpath(struct qspinlock *lock, u8 locked)
 {
 	struct __qspinlock *l = (void *)lock;
 	struct pv_node *node;
-	u8 locked;
-
-	/*
-	 * We must not unlock if SLOW, because in that case we must first
-	 * unhash. Otherwise it would be possible to have multiple @lock
-	 * entries, which would be BAD.
-	 */
-	locked = cmpxchg(&l->locked, _Q_LOCKED_VAL, 0);
-	if (likely(locked == _Q_LOCKED_VAL))
-		return;
 
 	if (unlikely(locked != _Q_SLOW_VAL)) {
 		WARN(!debug_locks_silent,
@@ -338,7 +489,7 @@
 	 * so we need a barrier to order the read of the node data in
 	 * pv_unhash *after* we've read the lock being _Q_SLOW_VAL.
 	 *
-	 * Matches the cmpxchg() in pv_wait_head() setting _Q_SLOW_VAL.
+	 * Matches the cmpxchg() in pv_wait_head_or_lock() setting _Q_SLOW_VAL.
 	 */
 	smp_rmb();
 
@@ -361,14 +512,35 @@
 	 * vCPU is harmless other than the additional latency in completing
 	 * the unlock.
 	 */
+	qstat_inc(qstat_pv_kick_unlock, true);
 	pv_kick(node->cpu);
 }
+
 /*
  * Include the architecture specific callee-save thunk of the
  * __pv_queued_spin_unlock(). This thunk is put together with
- * __pv_queued_spin_unlock() near the top of the file to make sure
- * that the callee-save thunk and the real unlock function are close
- * to each other sharing consecutive instruction cachelines.
+ * __pv_queued_spin_unlock() to make the callee-save thunk and the real unlock
+ * function close to each other sharing consecutive instruction cachelines.
+ * Alternatively, architecture specific version of __pv_queued_spin_unlock()
+ * can be defined.
  */
 #include <asm/qspinlock_paravirt.h>
 
+#ifndef __pv_queued_spin_unlock
+__visible void __pv_queued_spin_unlock(struct qspinlock *lock)
+{
+	struct __qspinlock *l = (void *)lock;
+	u8 locked;
+
+	/*
+	 * We must not unlock if SLOW, because in that case we must first
+	 * unhash. Otherwise it would be possible to have multiple @lock
+	 * entries, which would be BAD.
+	 */
+	locked = cmpxchg(&l->locked, _Q_LOCKED_VAL, 0);
+	if (likely(locked == _Q_LOCKED_VAL))
+		return;
+
+	__pv_queued_spin_unlock_slowpath(lock, locked);
+}
+#endif /* __pv_queued_spin_unlock */
diff --git a/kernel/locking/qspinlock_stat.h b/kernel/locking/qspinlock_stat.h
new file mode 100644
index 0000000..640dcec
--- /dev/null
+++ b/kernel/locking/qspinlock_stat.h
@@ -0,0 +1,300 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Authors: Waiman Long <waiman.long@hpe.com>
+ */
+
+/*
+ * When queued spinlock statistical counters are enabled, the following
+ * debugfs files will be created for reporting the counter values:
+ *
+ * <debugfs>/qlockstat/
+ *   pv_hash_hops	- average # of hops per hashing operation
+ *   pv_kick_unlock	- # of vCPU kicks issued at unlock time
+ *   pv_kick_wake	- # of vCPU kicks used for computing pv_latency_wake
+ *   pv_latency_kick	- average latency (ns) of vCPU kick operation
+ *   pv_latency_wake	- average latency (ns) from vCPU kick to wakeup
+ *   pv_lock_stealing	- # of lock stealing operations
+ *   pv_spurious_wakeup	- # of spurious wakeups
+ *   pv_wait_again	- # of vCPU wait's that happened after a vCPU kick
+ *   pv_wait_early	- # of early vCPU wait's
+ *   pv_wait_head	- # of vCPU wait's at the queue head
+ *   pv_wait_node	- # of vCPU wait's at a non-head queue node
+ *
+ * Writing to the "reset_counters" file will reset all the above counter
+ * values.
+ *
+ * These statistical counters are implemented as per-cpu variables which are
+ * summed and computed whenever the corresponding debugfs files are read. This
+ * minimizes added overhead making the counters usable even in a production
+ * environment.
+ *
+ * There may be slight difference between pv_kick_wake and pv_kick_unlock.
+ */
+enum qlock_stats {
+	qstat_pv_hash_hops,
+	qstat_pv_kick_unlock,
+	qstat_pv_kick_wake,
+	qstat_pv_latency_kick,
+	qstat_pv_latency_wake,
+	qstat_pv_lock_stealing,
+	qstat_pv_spurious_wakeup,
+	qstat_pv_wait_again,
+	qstat_pv_wait_early,
+	qstat_pv_wait_head,
+	qstat_pv_wait_node,
+	qstat_num,	/* Total number of statistical counters */
+	qstat_reset_cnts = qstat_num,
+};
+
+#ifdef CONFIG_QUEUED_LOCK_STAT
+/*
+ * Collect pvqspinlock statistics
+ */
+#include <linux/debugfs.h>
+#include <linux/sched.h>
+#include <linux/fs.h>
+
+static const char * const qstat_names[qstat_num + 1] = {
+	[qstat_pv_hash_hops]	   = "pv_hash_hops",
+	[qstat_pv_kick_unlock]     = "pv_kick_unlock",
+	[qstat_pv_kick_wake]       = "pv_kick_wake",
+	[qstat_pv_spurious_wakeup] = "pv_spurious_wakeup",
+	[qstat_pv_latency_kick]	   = "pv_latency_kick",
+	[qstat_pv_latency_wake]    = "pv_latency_wake",
+	[qstat_pv_lock_stealing]   = "pv_lock_stealing",
+	[qstat_pv_wait_again]      = "pv_wait_again",
+	[qstat_pv_wait_early]      = "pv_wait_early",
+	[qstat_pv_wait_head]       = "pv_wait_head",
+	[qstat_pv_wait_node]       = "pv_wait_node",
+	[qstat_reset_cnts]         = "reset_counters",
+};
+
+/*
+ * Per-cpu counters
+ */
+static DEFINE_PER_CPU(unsigned long, qstats[qstat_num]);
+static DEFINE_PER_CPU(u64, pv_kick_time);
+
+/*
+ * Function to read and return the qlock statistical counter values
+ *
+ * The following counters are handled specially:
+ * 1. qstat_pv_latency_kick
+ *    Average kick latency (ns) = pv_latency_kick/pv_kick_unlock
+ * 2. qstat_pv_latency_wake
+ *    Average wake latency (ns) = pv_latency_wake/pv_kick_wake
+ * 3. qstat_pv_hash_hops
+ *    Average hops/hash = pv_hash_hops/pv_kick_unlock
+ */
+static ssize_t qstat_read(struct file *file, char __user *user_buf,
+			  size_t count, loff_t *ppos)
+{
+	char buf[64];
+	int cpu, counter, len;
+	u64 stat = 0, kicks = 0;
+
+	/*
+	 * Get the counter ID stored in file->f_inode->i_private
+	 */
+	if (!file->f_inode) {
+		WARN_ON_ONCE(1);
+		return -EBADF;
+	}
+	counter = (long)(file->f_inode->i_private);
+
+	if (counter >= qstat_num)
+		return -EBADF;
+
+	for_each_possible_cpu(cpu) {
+		stat += per_cpu(qstats[counter], cpu);
+		/*
+		 * Need to sum additional counter for some of them
+		 */
+		switch (counter) {
+
+		case qstat_pv_latency_kick:
+		case qstat_pv_hash_hops:
+			kicks += per_cpu(qstats[qstat_pv_kick_unlock], cpu);
+			break;
+
+		case qstat_pv_latency_wake:
+			kicks += per_cpu(qstats[qstat_pv_kick_wake], cpu);
+			break;
+		}
+	}
+
+	if (counter == qstat_pv_hash_hops) {
+		u64 frac;
+
+		frac = 100ULL * do_div(stat, kicks);
+		frac = DIV_ROUND_CLOSEST_ULL(frac, kicks);
+
+		/*
+		 * Return a X.XX decimal number
+		 */
+		len = snprintf(buf, sizeof(buf) - 1, "%llu.%02llu\n", stat, frac);
+	} else {
+		/*
+		 * Round to the nearest ns
+		 */
+		if ((counter == qstat_pv_latency_kick) ||
+		    (counter == qstat_pv_latency_wake)) {
+			stat = 0;
+			if (kicks)
+				stat = DIV_ROUND_CLOSEST_ULL(stat, kicks);
+		}
+		len = snprintf(buf, sizeof(buf) - 1, "%llu\n", stat);
+	}
+
+	return simple_read_from_buffer(user_buf, count, ppos, buf, len);
+}
+
+/*
+ * Function to handle write request
+ *
+ * When counter = reset_cnts, reset all the counter values.
+ * Since the counter updates aren't atomic, the resetting is done twice
+ * to make sure that the counters are very likely to be all cleared.
+ */
+static ssize_t qstat_write(struct file *file, const char __user *user_buf,
+			   size_t count, loff_t *ppos)
+{
+	int cpu;
+
+	/*
+	 * Get the counter ID stored in file->f_inode->i_private
+	 */
+	if (!file->f_inode) {
+		WARN_ON_ONCE(1);
+		return -EBADF;
+	}
+	if ((long)(file->f_inode->i_private) != qstat_reset_cnts)
+		return count;
+
+	for_each_possible_cpu(cpu) {
+		int i;
+		unsigned long *ptr = per_cpu_ptr(qstats, cpu);
+
+		for (i = 0 ; i < qstat_num; i++)
+			WRITE_ONCE(ptr[i], 0);
+		for (i = 0 ; i < qstat_num; i++)
+			WRITE_ONCE(ptr[i], 0);
+	}
+	return count;
+}
+
+/*
+ * Debugfs data structures
+ */
+static const struct file_operations fops_qstat = {
+	.read = qstat_read,
+	.write = qstat_write,
+	.llseek = default_llseek,
+};
+
+/*
+ * Initialize debugfs for the qspinlock statistical counters
+ */
+static int __init init_qspinlock_stat(void)
+{
+	struct dentry *d_qstat = debugfs_create_dir("qlockstat", NULL);
+	int i;
+
+	if (!d_qstat) {
+		pr_warn("Could not create 'qlockstat' debugfs directory\n");
+		return 0;
+	}
+
+	/*
+	 * Create the debugfs files
+	 *
+	 * As reading from and writing to the stat files can be slow, only
+	 * root is allowed to do the read/write to limit impact to system
+	 * performance.
+	 */
+	for (i = 0; i < qstat_num; i++)
+		debugfs_create_file(qstat_names[i], 0400, d_qstat,
+				   (void *)(long)i, &fops_qstat);
+
+	debugfs_create_file(qstat_names[qstat_reset_cnts], 0200, d_qstat,
+			   (void *)(long)qstat_reset_cnts, &fops_qstat);
+	return 0;
+}
+fs_initcall(init_qspinlock_stat);
+
+/*
+ * Increment the PV qspinlock statistical counters
+ */
+static inline void qstat_inc(enum qlock_stats stat, bool cond)
+{
+	if (cond)
+		this_cpu_inc(qstats[stat]);
+}
+
+/*
+ * PV hash hop count
+ */
+static inline void qstat_hop(int hopcnt)
+{
+	this_cpu_add(qstats[qstat_pv_hash_hops], hopcnt);
+}
+
+/*
+ * Replacement function for pv_kick()
+ */
+static inline void __pv_kick(int cpu)
+{
+	u64 start = sched_clock();
+
+	per_cpu(pv_kick_time, cpu) = start;
+	pv_kick(cpu);
+	this_cpu_add(qstats[qstat_pv_latency_kick], sched_clock() - start);
+}
+
+/*
+ * Replacement function for pv_wait()
+ */
+static inline void __pv_wait(u8 *ptr, u8 val)
+{
+	u64 *pkick_time = this_cpu_ptr(&pv_kick_time);
+
+	*pkick_time = 0;
+	pv_wait(ptr, val);
+	if (*pkick_time) {
+		this_cpu_add(qstats[qstat_pv_latency_wake],
+			     sched_clock() - *pkick_time);
+		qstat_inc(qstat_pv_kick_wake, true);
+	}
+}
+
+#define pv_kick(c)	__pv_kick(c)
+#define pv_wait(p, v)	__pv_wait(p, v)
+
+/*
+ * PV unfair trylock count tracking function
+ */
+static inline int qstat_spin_steal_lock(struct qspinlock *lock)
+{
+	int ret = pv_queued_spin_steal_lock(lock);
+
+	qstat_inc(qstat_pv_lock_stealing, ret);
+	return ret;
+}
+#undef  queued_spin_trylock
+#define queued_spin_trylock(l)	qstat_spin_steal_lock(l)
+
+#else /* CONFIG_QUEUED_LOCK_STAT */
+
+static inline void qstat_inc(enum qlock_stats stat, bool cond)	{ }
+static inline void qstat_hop(int hopcnt)			{ }
+
+#endif /* CONFIG_QUEUED_LOCK_STAT */
diff --git a/kernel/module.c b/kernel/module.c
index 8f051a1..38c7bd5 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -3571,6 +3571,12 @@
 	synchronize_sched();
 	mutex_unlock(&module_mutex);
  free_module:
+	/*
+	 * Ftrace needs to clean up what it initialized.
+	 * This does nothing if ftrace_module_init() wasn't called,
+	 * but it must be called outside of module_mutex.
+	 */
+	ftrace_release_mod(mod);
 	/* Free lock-classes; relies on the preceding sync_rcu() */
 	lockdep_free_key_range(mod->module_core, mod->core_size);
 
diff --git a/kernel/panic.c b/kernel/panic.c
index 4b150bc..b333380 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -61,6 +61,17 @@
 		cpu_relax();
 }
 
+/*
+ * Stop ourselves in NMI context if another CPU has already panicked. Arch code
+ * may override this to prepare for crash dumping, e.g. save regs info.
+ */
+void __weak nmi_panic_self_stop(struct pt_regs *regs)
+{
+	panic_smp_self_stop();
+}
+
+atomic_t panic_cpu = ATOMIC_INIT(PANIC_CPU_INVALID);
+
 /**
  *	panic - halt the system
  *	@fmt: The text string to print
@@ -71,17 +82,17 @@
  */
 void panic(const char *fmt, ...)
 {
-	static DEFINE_SPINLOCK(panic_lock);
 	static char buf[1024];
 	va_list args;
 	long i, i_next = 0;
 	int state = 0;
+	int old_cpu, this_cpu;
 
 	/*
 	 * Disable local interrupts. This will prevent panic_smp_self_stop
 	 * from deadlocking the first cpu that invokes the panic, since
 	 * there is nothing to prevent an interrupt handler (that runs
-	 * after the panic_lock is acquired) from invoking panic again.
+	 * after setting panic_cpu) from invoking panic() again.
 	 */
 	local_irq_disable();
 
@@ -94,8 +105,16 @@
 	 * multiple parallel invocations of panic, all other CPUs either
 	 * stop themself or will wait until they are stopped by the 1st CPU
 	 * with smp_send_stop().
+	 *
+	 * `old_cpu == PANIC_CPU_INVALID' means this is the 1st CPU which
+	 * comes here, so go ahead.
+	 * `old_cpu == this_cpu' means we came from nmi_panic() which sets
+	 * panic_cpu to this CPU.  In this case, this is also the 1st CPU.
 	 */
-	if (!spin_trylock(&panic_lock))
+	this_cpu = raw_smp_processor_id();
+	old_cpu  = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, this_cpu);
+
+	if (old_cpu != PANIC_CPU_INVALID && old_cpu != this_cpu)
 		panic_smp_self_stop();
 
 	console_verbose();
@@ -117,9 +136,11 @@
 	 * everything else.
 	 * If we want to run this after calling panic_notifiers, pass
 	 * the "crash_kexec_post_notifiers" option to the kernel.
+	 *
+	 * Bypass the panic_cpu check and call __crash_kexec directly.
 	 */
 	if (!crash_kexec_post_notifiers)
-		crash_kexec(NULL);
+		__crash_kexec(NULL);
 
 	/*
 	 * Note smp_send_stop is the usual smp shutdown function, which
@@ -142,9 +163,11 @@
 	 * panic_notifiers and dumping kmsg before kdump.
 	 * Note: since some panic_notifiers can make crashed kernel
 	 * more unstable, it can increase risks of the kdump failure too.
+	 *
+	 * Bypass the panic_cpu check and call __crash_kexec directly.
 	 */
 	if (crash_kexec_post_notifiers)
-		crash_kexec(NULL);
+		__crash_kexec(NULL);
 
 	bust_spinlocks(0);
 
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index d89328e..d2988d0 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -162,6 +162,27 @@
 #define RTWS_SYNC		7
 #define RTWS_STUTTER		8
 #define RTWS_STOPPING		9
+static const char * const rcu_torture_writer_state_names[] = {
+	"RTWS_FIXED_DELAY",
+	"RTWS_DELAY",
+	"RTWS_REPLACE",
+	"RTWS_DEF_FREE",
+	"RTWS_EXP_SYNC",
+	"RTWS_COND_GET",
+	"RTWS_COND_SYNC",
+	"RTWS_SYNC",
+	"RTWS_STUTTER",
+	"RTWS_STOPPING",
+};
+
+static const char *rcu_torture_writer_state_getname(void)
+{
+	unsigned int i = READ_ONCE(rcu_torture_writer_state);
+
+	if (i >= ARRAY_SIZE(rcu_torture_writer_state_names))
+		return "???";
+	return rcu_torture_writer_state_names[i];
+}
 
 #if defined(MODULE) || defined(CONFIG_RCU_TORTURE_TEST_RUNNABLE)
 #define RCUTORTURE_RUNNABLE_INIT 1
@@ -1307,7 +1328,8 @@
 
 		rcutorture_get_gp_data(cur_ops->ttype,
 				       &flags, &gpnum, &completed);
-		pr_alert("??? Writer stall state %d g%lu c%lu f%#x\n",
+		pr_alert("??? Writer stall state %s(%d) g%lu c%lu f%#x\n",
+			 rcu_torture_writer_state_getname(),
 			 rcu_torture_writer_state,
 			 gpnum, completed, flags);
 		show_rcu_gp_kthreads();
diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c
index a63a1ea..9b9cdd5 100644
--- a/kernel/rcu/srcu.c
+++ b/kernel/rcu/srcu.c
@@ -489,7 +489,7 @@
  */
 void synchronize_srcu(struct srcu_struct *sp)
 {
-	__synchronize_srcu(sp, rcu_gp_is_expedited()
+	__synchronize_srcu(sp, (rcu_gp_is_expedited() && !rcu_gp_is_normal())
 			   ? SYNCHRONIZE_SRCU_EXP_TRYCOUNT
 			   : SYNCHRONIZE_SRCU_TRYCOUNT);
 }
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index f07343b..e41dd41 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -68,10 +68,6 @@
 
 /* Data structures. */
 
-static struct lock_class_key rcu_node_class[RCU_NUM_LVLS];
-static struct lock_class_key rcu_fqs_class[RCU_NUM_LVLS];
-static struct lock_class_key rcu_exp_class[RCU_NUM_LVLS];
-
 /*
  * In order to export the rcu_state name to the tracing tools, it
  * needs to be added in the __tracepoint_string section.
@@ -246,24 +242,17 @@
  */
 void rcu_sched_qs(void)
 {
-	unsigned long flags;
-
-	if (__this_cpu_read(rcu_sched_data.cpu_no_qs.s)) {
-		trace_rcu_grace_period(TPS("rcu_sched"),
-				       __this_cpu_read(rcu_sched_data.gpnum),
-				       TPS("cpuqs"));
-		__this_cpu_write(rcu_sched_data.cpu_no_qs.b.norm, false);
-		if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp))
-			return;
-		local_irq_save(flags);
-		if (__this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp)) {
-			__this_cpu_write(rcu_sched_data.cpu_no_qs.b.exp, false);
-			rcu_report_exp_rdp(&rcu_sched_state,
-					   this_cpu_ptr(&rcu_sched_data),
-					   true);
-		}
-		local_irq_restore(flags);
-	}
+	if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.s))
+		return;
+	trace_rcu_grace_period(TPS("rcu_sched"),
+			       __this_cpu_read(rcu_sched_data.gpnum),
+			       TPS("cpuqs"));
+	__this_cpu_write(rcu_sched_data.cpu_no_qs.b.norm, false);
+	if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp))
+		return;
+	__this_cpu_write(rcu_sched_data.cpu_no_qs.b.exp, false);
+	rcu_report_exp_rdp(&rcu_sched_state,
+			   this_cpu_ptr(&rcu_sched_data), true);
 }
 
 void rcu_bh_qs(void)
@@ -300,17 +289,16 @@
  * We inform the RCU core by emulating a zero-duration dyntick-idle
  * period, which we in turn do by incrementing the ->dynticks counter
  * by two.
+ *
+ * The caller must have disabled interrupts.
  */
 static void rcu_momentary_dyntick_idle(void)
 {
-	unsigned long flags;
 	struct rcu_data *rdp;
 	struct rcu_dynticks *rdtp;
 	int resched_mask;
 	struct rcu_state *rsp;
 
-	local_irq_save(flags);
-
 	/*
 	 * Yes, we can lose flag-setting operations.  This is OK, because
 	 * the flag will be set again after some delay.
@@ -340,13 +328,12 @@
 		smp_mb__after_atomic(); /* Later stuff after QS. */
 		break;
 	}
-	local_irq_restore(flags);
 }
 
 /*
  * Note a context switch.  This is a quiescent state for RCU-sched,
  * and requires special handling for preemptible RCU.
- * The caller must have disabled preemption.
+ * The caller must have disabled interrupts.
  */
 void rcu_note_context_switch(void)
 {
@@ -376,9 +363,14 @@
  */
 void rcu_all_qs(void)
 {
+	unsigned long flags;
+
 	barrier(); /* Avoid RCU read-side critical sections leaking down. */
-	if (unlikely(raw_cpu_read(rcu_sched_qs_mask)))
+	if (unlikely(raw_cpu_read(rcu_sched_qs_mask))) {
+		local_irq_save(flags);
 		rcu_momentary_dyntick_idle();
+		local_irq_restore(flags);
+	}
 	this_cpu_inc(rcu_qs_ctr);
 	barrier(); /* Avoid RCU read-side critical sections leaking up. */
 }
@@ -605,25 +597,25 @@
  * The caller must have disabled interrupts to prevent races with
  * normal callback registry.
  */
-static int
+static bool
 cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp)
 {
 	int i;
 
 	if (rcu_gp_in_progress(rsp))
-		return 0;  /* No, a grace period is already in progress. */
+		return false;  /* No, a grace period is already in progress. */
 	if (rcu_future_needs_gp(rsp))
-		return 1;  /* Yes, a no-CBs CPU needs one. */
+		return true;  /* Yes, a no-CBs CPU needs one. */
 	if (!rdp->nxttail[RCU_NEXT_TAIL])
-		return 0;  /* No, this is a no-CBs (or offline) CPU. */
+		return false;  /* No, this is a no-CBs (or offline) CPU. */
 	if (*rdp->nxttail[RCU_NEXT_READY_TAIL])
-		return 1;  /* Yes, this CPU has newly registered callbacks. */
+		return true;  /* Yes, CPU has newly registered callbacks. */
 	for (i = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++)
 		if (rdp->nxttail[i - 1] != rdp->nxttail[i] &&
 		    ULONG_CMP_LT(READ_ONCE(rsp->completed),
 				 rdp->nxtcompleted[i]))
-			return 1;  /* Yes, CBs for future grace period. */
-	return 0; /* No grace period needed. */
+			return true;  /* Yes, CBs for future grace period. */
+	return false; /* No grace period needed. */
 }
 
 /*
@@ -740,7 +732,7 @@
  *
  * Exit from an interrupt handler, which might possibly result in entering
  * idle mode, in other words, leaving the mode in which read-side critical
- * sections can occur.
+ * sections can occur.  The caller must have disabled interrupts.
  *
  * This code assumes that the idle loop never does anything that might
  * result in unbalanced calls to irq_enter() and irq_exit().  If your
@@ -753,11 +745,10 @@
  */
 void rcu_irq_exit(void)
 {
-	unsigned long flags;
 	long long oldval;
 	struct rcu_dynticks *rdtp;
 
-	local_irq_save(flags);
+	RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_exit() invoked with irqs enabled!!!");
 	rdtp = this_cpu_ptr(&rcu_dynticks);
 	oldval = rdtp->dynticks_nesting;
 	rdtp->dynticks_nesting--;
@@ -768,6 +759,17 @@
 	else
 		rcu_eqs_enter_common(oldval, true);
 	rcu_sysidle_enter(1);
+}
+
+/*
+ * Wrapper for rcu_irq_exit() where interrupts are enabled.
+ */
+void rcu_irq_exit_irqson(void)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	rcu_irq_exit();
 	local_irq_restore(flags);
 }
 
@@ -865,7 +867,7 @@
  *
  * Enter an interrupt handler, which might possibly result in exiting
  * idle mode, in other words, entering the mode in which read-side critical
- * sections can occur.
+ * sections can occur.  The caller must have disabled interrupts.
  *
  * Note that the Linux kernel is fully capable of entering an interrupt
  * handler that it never exits, for example when doing upcalls to
@@ -881,11 +883,10 @@
  */
 void rcu_irq_enter(void)
 {
-	unsigned long flags;
 	struct rcu_dynticks *rdtp;
 	long long oldval;
 
-	local_irq_save(flags);
+	RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_enter() invoked with irqs enabled!!!");
 	rdtp = this_cpu_ptr(&rcu_dynticks);
 	oldval = rdtp->dynticks_nesting;
 	rdtp->dynticks_nesting++;
@@ -896,6 +897,17 @@
 	else
 		rcu_eqs_exit_common(oldval, true);
 	rcu_sysidle_exit(1);
+}
+
+/*
+ * Wrapper for rcu_irq_enter() where interrupts are enabled.
+ */
+void rcu_irq_enter_irqson(void)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	rcu_irq_enter();
 	local_irq_restore(flags);
 }
 
@@ -1187,6 +1199,16 @@
 }
 
 /*
+ * Convert a ->gp_state value to a character string.
+ */
+static const char *gp_state_getname(short gs)
+{
+	if (gs < 0 || gs >= ARRAY_SIZE(gp_state_names))
+		return "???";
+	return gp_state_names[gs];
+}
+
+/*
  * Complain about starvation of grace-period kthread.
  */
 static void rcu_check_gp_kthread_starvation(struct rcu_state *rsp)
@@ -1196,12 +1218,16 @@
 
 	j = jiffies;
 	gpa = READ_ONCE(rsp->gp_activity);
-	if (j - gpa > 2 * HZ)
-		pr_err("%s kthread starved for %ld jiffies! g%lu c%lu f%#x s%d ->state=%#lx\n",
+	if (j - gpa > 2 * HZ) {
+		pr_err("%s kthread starved for %ld jiffies! g%lu c%lu f%#x %s(%d) ->state=%#lx\n",
 		       rsp->name, j - gpa,
 		       rsp->gpnum, rsp->completed,
-		       rsp->gp_flags, rsp->gp_state,
-		       rsp->gp_kthread ? rsp->gp_kthread->state : 0);
+		       rsp->gp_flags,
+		       gp_state_getname(rsp->gp_state), rsp->gp_state,
+		       rsp->gp_kthread ? rsp->gp_kthread->state : ~0);
+		if (rsp->gp_kthread)
+			sched_show_task(rsp->gp_kthread);
+	}
 }
 
 /*
@@ -1214,7 +1240,7 @@
 	struct rcu_node *rnp;
 
 	rcu_for_each_leaf_node(rsp, rnp) {
-		raw_spin_lock_irqsave(&rnp->lock, flags);
+		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		if (rnp->qsmask != 0) {
 			for (cpu = 0; cpu <= rnp->grphi - rnp->grplo; cpu++)
 				if (rnp->qsmask & (1UL << cpu))
@@ -1237,7 +1263,7 @@
 
 	/* Only let one CPU complain about others per time interval. */
 
-	raw_spin_lock_irqsave(&rnp->lock, flags);
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	delta = jiffies - READ_ONCE(rsp->jiffies_stall);
 	if (delta < RCU_STALL_RAT_DELAY || !rcu_gp_in_progress(rsp)) {
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
@@ -1256,7 +1282,7 @@
 	       rsp->name);
 	print_cpu_stall_info_begin();
 	rcu_for_each_leaf_node(rsp, rnp) {
-		raw_spin_lock_irqsave(&rnp->lock, flags);
+		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		ndetected += rcu_print_task_stall(rnp);
 		if (rnp->qsmask != 0) {
 			for (cpu = 0; cpu <= rnp->grphi - rnp->grplo; cpu++)
@@ -1327,7 +1353,7 @@
 
 	rcu_dump_cpu_stacks(rsp);
 
-	raw_spin_lock_irqsave(&rnp->lock, flags);
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	if (ULONG_CMP_GE(jiffies, READ_ONCE(rsp->jiffies_stall)))
 		WRITE_ONCE(rsp->jiffies_stall,
 			   jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
@@ -1534,10 +1560,8 @@
 	 * hold it, acquire the root rcu_node structure's lock in order to
 	 * start one (if needed).
 	 */
-	if (rnp != rnp_root) {
-		raw_spin_lock(&rnp_root->lock);
-		smp_mb__after_unlock_lock();
-	}
+	if (rnp != rnp_root)
+		raw_spin_lock_rcu_node(rnp_root);
 
 	/*
 	 * Get a new grace-period number.  If there really is no grace
@@ -1786,11 +1810,10 @@
 	if ((rdp->gpnum == READ_ONCE(rnp->gpnum) &&
 	     rdp->completed == READ_ONCE(rnp->completed) &&
 	     !unlikely(READ_ONCE(rdp->gpwrap))) || /* w/out lock. */
-	    !raw_spin_trylock(&rnp->lock)) { /* irqs already off, so later. */
+	    !raw_spin_trylock_rcu_node(rnp)) { /* irqs already off, so later. */
 		local_irq_restore(flags);
 		return;
 	}
-	smp_mb__after_unlock_lock();
 	needwake = __note_gp_changes(rsp, rnp, rdp);
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	if (needwake)
@@ -1805,21 +1828,20 @@
 }
 
 /*
- * Initialize a new grace period.  Return 0 if no grace period required.
+ * Initialize a new grace period.  Return false if no grace period required.
  */
-static int rcu_gp_init(struct rcu_state *rsp)
+static bool rcu_gp_init(struct rcu_state *rsp)
 {
 	unsigned long oldmask;
 	struct rcu_data *rdp;
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
 	WRITE_ONCE(rsp->gp_activity, jiffies);
-	raw_spin_lock_irq(&rnp->lock);
-	smp_mb__after_unlock_lock();
+	raw_spin_lock_irq_rcu_node(rnp);
 	if (!READ_ONCE(rsp->gp_flags)) {
 		/* Spurious wakeup, tell caller to go back to sleep.  */
 		raw_spin_unlock_irq(&rnp->lock);
-		return 0;
+		return false;
 	}
 	WRITE_ONCE(rsp->gp_flags, 0); /* Clear all flags: New grace period. */
 
@@ -1829,7 +1851,7 @@
 		 * Not supposed to be able to happen.
 		 */
 		raw_spin_unlock_irq(&rnp->lock);
-		return 0;
+		return false;
 	}
 
 	/* Advance to a new grace period and initialize state. */
@@ -1847,8 +1869,7 @@
 	 */
 	rcu_for_each_leaf_node(rsp, rnp) {
 		rcu_gp_slow(rsp, gp_preinit_delay);
-		raw_spin_lock_irq(&rnp->lock);
-		smp_mb__after_unlock_lock();
+		raw_spin_lock_irq_rcu_node(rnp);
 		if (rnp->qsmaskinit == rnp->qsmaskinitnext &&
 		    !rnp->wait_blkd_tasks) {
 			/* Nothing to do on this leaf rcu_node structure. */
@@ -1904,8 +1925,7 @@
 	 */
 	rcu_for_each_node_breadth_first(rsp, rnp) {
 		rcu_gp_slow(rsp, gp_init_delay);
-		raw_spin_lock_irq(&rnp->lock);
-		smp_mb__after_unlock_lock();
+		raw_spin_lock_irq_rcu_node(rnp);
 		rdp = this_cpu_ptr(rsp->rda);
 		rcu_preempt_check_blocked_tasks(rnp);
 		rnp->qsmask = rnp->qsmaskinit;
@@ -1923,7 +1943,7 @@
 		WRITE_ONCE(rsp->gp_activity, jiffies);
 	}
 
-	return 1;
+	return true;
 }
 
 /*
@@ -1973,8 +1993,7 @@
 	}
 	/* Clear flag to prevent immediate re-entry. */
 	if (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
-		raw_spin_lock_irq(&rnp->lock);
-		smp_mb__after_unlock_lock();
+		raw_spin_lock_irq_rcu_node(rnp);
 		WRITE_ONCE(rsp->gp_flags,
 			   READ_ONCE(rsp->gp_flags) & ~RCU_GP_FLAG_FQS);
 		raw_spin_unlock_irq(&rnp->lock);
@@ -1993,8 +2012,7 @@
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
 	WRITE_ONCE(rsp->gp_activity, jiffies);
-	raw_spin_lock_irq(&rnp->lock);
-	smp_mb__after_unlock_lock();
+	raw_spin_lock_irq_rcu_node(rnp);
 	gp_duration = jiffies - rsp->gp_start;
 	if (gp_duration > rsp->gp_max)
 		rsp->gp_max = gp_duration;
@@ -2019,8 +2037,7 @@
 	 * grace period is recorded in any of the rcu_node structures.
 	 */
 	rcu_for_each_node_breadth_first(rsp, rnp) {
-		raw_spin_lock_irq(&rnp->lock);
-		smp_mb__after_unlock_lock();
+		raw_spin_lock_irq_rcu_node(rnp);
 		WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp));
 		WARN_ON_ONCE(rnp->qsmask);
 		WRITE_ONCE(rnp->completed, rsp->gpnum);
@@ -2035,8 +2052,7 @@
 		rcu_gp_slow(rsp, gp_cleanup_delay);
 	}
 	rnp = rcu_get_root(rsp);
-	raw_spin_lock_irq(&rnp->lock);
-	smp_mb__after_unlock_lock(); /* Order GP before ->completed update. */
+	raw_spin_lock_irq_rcu_node(rnp); /* Order GP before ->completed update. */
 	rcu_nocb_gp_set(rnp, nocb);
 
 	/* Declare grace period done. */
@@ -2284,8 +2300,7 @@
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		rnp_c = rnp;
 		rnp = rnp->parent;
-		raw_spin_lock_irqsave(&rnp->lock, flags);
-		smp_mb__after_unlock_lock();
+		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		oldmask = rnp_c->qsmask;
 	}
 
@@ -2332,8 +2347,7 @@
 	gps = rnp->gpnum;
 	mask = rnp->grpmask;
 	raw_spin_unlock(&rnp->lock);	/* irqs remain disabled. */
-	raw_spin_lock(&rnp_p->lock);	/* irqs already disabled. */
-	smp_mb__after_unlock_lock();
+	raw_spin_lock_rcu_node(rnp_p);	/* irqs already disabled. */
 	rcu_report_qs_rnp(mask, rsp, rnp_p, gps, flags);
 }
 
@@ -2355,8 +2369,7 @@
 	struct rcu_node *rnp;
 
 	rnp = rdp->mynode;
-	raw_spin_lock_irqsave(&rnp->lock, flags);
-	smp_mb__after_unlock_lock();
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	if ((rdp->cpu_no_qs.b.norm &&
 	     rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) ||
 	    rdp->gpnum != rnp->gpnum || rnp->completed == rnp->gpnum ||
@@ -2582,8 +2595,7 @@
 		rnp = rnp->parent;
 		if (!rnp)
 			break;
-		raw_spin_lock(&rnp->lock); /* irqs already disabled. */
-		smp_mb__after_unlock_lock(); /* GP memory ordering. */
+		raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
 		rnp->qsmaskinit &= ~mask;
 		rnp->qsmask &= ~mask;
 		if (rnp->qsmaskinit) {
@@ -2611,8 +2623,7 @@
 
 	/* Remove outgoing CPU from mask in the leaf rcu_node structure. */
 	mask = rdp->grpmask;
-	raw_spin_lock_irqsave(&rnp->lock, flags);
-	smp_mb__after_unlock_lock();	/* Enforce GP memory-order guarantee. */
+	raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */
 	rnp->qsmaskinitnext &= ~mask;
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 }
@@ -2809,8 +2820,7 @@
 	rcu_for_each_leaf_node(rsp, rnp) {
 		cond_resched_rcu_qs();
 		mask = 0;
-		raw_spin_lock_irqsave(&rnp->lock, flags);
-		smp_mb__after_unlock_lock();
+		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		if (rnp->qsmask == 0) {
 			if (rcu_state_p == &rcu_sched_state ||
 			    rsp != rcu_state_p ||
@@ -2881,8 +2891,7 @@
 	/* rnp_old == rcu_get_root(rsp), rnp == NULL. */
 
 	/* Reached the root of the rcu_node tree, acquire lock. */
-	raw_spin_lock_irqsave(&rnp_old->lock, flags);
-	smp_mb__after_unlock_lock();
+	raw_spin_lock_irqsave_rcu_node(rnp_old, flags);
 	raw_spin_unlock(&rnp_old->fqslock);
 	if (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
 		rsp->n_force_qs_lh++;
@@ -2914,7 +2923,7 @@
 	/* Does this CPU require a not-yet-started grace period? */
 	local_irq_save(flags);
 	if (cpu_needs_another_gp(rsp, rdp)) {
-		raw_spin_lock(&rcu_get_root(rsp)->lock); /* irqs disabled. */
+		raw_spin_lock_rcu_node(rcu_get_root(rsp)); /* irqs disabled. */
 		needwake = rcu_start_gp(rsp);
 		raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags);
 		if (needwake)
@@ -3005,8 +3014,7 @@
 		if (!rcu_gp_in_progress(rsp)) {
 			struct rcu_node *rnp_root = rcu_get_root(rsp);
 
-			raw_spin_lock(&rnp_root->lock);
-			smp_mb__after_unlock_lock();
+			raw_spin_lock_rcu_node(rnp_root);
 			needwake = rcu_start_gp(rsp);
 			raw_spin_unlock(&rnp_root->lock);
 			if (needwake)
@@ -3365,7 +3373,6 @@
 {
 	unsigned long s;
 
-	smp_mb(); /* Caller's modifications seen first by other CPUs. */
 	s = (READ_ONCE(*sp) + 3) & ~0x1;
 	smp_mb(); /* Above access must not bleed into critical section. */
 	return s;
@@ -3392,6 +3399,7 @@
 }
 static unsigned long rcu_exp_gp_seq_snap(struct rcu_state *rsp)
 {
+	smp_mb(); /* Caller's modifications seen first by other CPUs. */
 	return rcu_seq_snap(&rsp->expedited_sequence);
 }
 static bool rcu_exp_gp_seq_done(struct rcu_state *rsp, unsigned long s)
@@ -3426,8 +3434,7 @@
 	 * CPUs for the current rcu_node structure up the rcu_node tree.
 	 */
 	rcu_for_each_leaf_node(rsp, rnp) {
-		raw_spin_lock_irqsave(&rnp->lock, flags);
-		smp_mb__after_unlock_lock();
+		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		if (rnp->expmaskinit == rnp->expmaskinitnext) {
 			raw_spin_unlock_irqrestore(&rnp->lock, flags);
 			continue;  /* No new CPUs, nothing to do. */
@@ -3447,8 +3454,7 @@
 		rnp_up = rnp->parent;
 		done = false;
 		while (rnp_up) {
-			raw_spin_lock_irqsave(&rnp_up->lock, flags);
-			smp_mb__after_unlock_lock();
+			raw_spin_lock_irqsave_rcu_node(rnp_up, flags);
 			if (rnp_up->expmaskinit)
 				done = true;
 			rnp_up->expmaskinit |= mask;
@@ -3472,8 +3478,7 @@
 
 	sync_exp_reset_tree_hotplug(rsp);
 	rcu_for_each_node_breadth_first(rsp, rnp) {
-		raw_spin_lock_irqsave(&rnp->lock, flags);
-		smp_mb__after_unlock_lock();
+		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		WARN_ON_ONCE(rnp->expmask);
 		rnp->expmask = rnp->expmaskinit;
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
@@ -3531,8 +3536,7 @@
 		mask = rnp->grpmask;
 		raw_spin_unlock(&rnp->lock); /* irqs remain disabled */
 		rnp = rnp->parent;
-		raw_spin_lock(&rnp->lock); /* irqs already disabled */
-		smp_mb__after_unlock_lock();
+		raw_spin_lock_rcu_node(rnp); /* irqs already disabled */
 		WARN_ON_ONCE(!(rnp->expmask & mask));
 		rnp->expmask &= ~mask;
 	}
@@ -3549,8 +3553,7 @@
 {
 	unsigned long flags;
 
-	raw_spin_lock_irqsave(&rnp->lock, flags);
-	smp_mb__after_unlock_lock();
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	__rcu_report_exp_rnp(rsp, rnp, wake, flags);
 }
 
@@ -3564,8 +3567,7 @@
 {
 	unsigned long flags;
 
-	raw_spin_lock_irqsave(&rnp->lock, flags);
-	smp_mb__after_unlock_lock();
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	if (!(rnp->expmask & mask)) {
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		return;
@@ -3609,7 +3611,7 @@
  */
 static struct rcu_node *exp_funnel_lock(struct rcu_state *rsp, unsigned long s)
 {
-	struct rcu_data *rdp;
+	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, raw_smp_processor_id());
 	struct rcu_node *rnp0;
 	struct rcu_node *rnp1 = NULL;
 
@@ -3623,7 +3625,7 @@
 	if (!mutex_is_locked(&rnp0->exp_funnel_mutex)) {
 		if (mutex_trylock(&rnp0->exp_funnel_mutex)) {
 			if (sync_exp_work_done(rsp, rnp0, NULL,
-					       &rsp->expedited_workdone0, s))
+					       &rdp->expedited_workdone0, s))
 				return NULL;
 			return rnp0;
 		}
@@ -3637,14 +3639,13 @@
 	 * can be inexact, as it is just promoting locality and is not
 	 * strictly needed for correctness.
 	 */
-	rdp = per_cpu_ptr(rsp->rda, raw_smp_processor_id());
-	if (sync_exp_work_done(rsp, NULL, NULL, &rsp->expedited_workdone1, s))
+	if (sync_exp_work_done(rsp, NULL, NULL, &rdp->expedited_workdone1, s))
 		return NULL;
 	mutex_lock(&rdp->exp_funnel_mutex);
 	rnp0 = rdp->mynode;
 	for (; rnp0 != NULL; rnp0 = rnp0->parent) {
 		if (sync_exp_work_done(rsp, rnp1, rdp,
-				       &rsp->expedited_workdone2, s))
+				       &rdp->expedited_workdone2, s))
 			return NULL;
 		mutex_lock(&rnp0->exp_funnel_mutex);
 		if (rnp1)
@@ -3654,7 +3655,7 @@
 		rnp1 = rnp0;
 	}
 	if (sync_exp_work_done(rsp, rnp1, rdp,
-			       &rsp->expedited_workdone3, s))
+			       &rdp->expedited_workdone3, s))
 		return NULL;
 	return rnp1;
 }
@@ -3708,8 +3709,7 @@
 
 	sync_exp_reset_tree(rsp);
 	rcu_for_each_leaf_node(rsp, rnp) {
-		raw_spin_lock_irqsave(&rnp->lock, flags);
-		smp_mb__after_unlock_lock();
+		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 
 		/* Each pass checks a CPU for identity, offline, and idle. */
 		mask_ofl_test = 0;
@@ -3741,24 +3741,22 @@
 			ret = smp_call_function_single(cpu, func, rsp, 0);
 			if (!ret) {
 				mask_ofl_ipi &= ~mask;
-			} else {
-				/* Failed, raced with offline. */
-				raw_spin_lock_irqsave(&rnp->lock, flags);
-				if (cpu_online(cpu) &&
-				    (rnp->expmask & mask)) {
-					raw_spin_unlock_irqrestore(&rnp->lock,
-								   flags);
-					schedule_timeout_uninterruptible(1);
-					if (cpu_online(cpu) &&
-					    (rnp->expmask & mask))
-						goto retry_ipi;
-					raw_spin_lock_irqsave(&rnp->lock,
-							      flags);
-				}
-				if (!(rnp->expmask & mask))
-					mask_ofl_ipi &= ~mask;
-				raw_spin_unlock_irqrestore(&rnp->lock, flags);
+				continue;
 			}
+			/* Failed, raced with offline. */
+			raw_spin_lock_irqsave_rcu_node(rnp, flags);
+			if (cpu_online(cpu) &&
+			    (rnp->expmask & mask)) {
+				raw_spin_unlock_irqrestore(&rnp->lock, flags);
+				schedule_timeout_uninterruptible(1);
+				if (cpu_online(cpu) &&
+				    (rnp->expmask & mask))
+					goto retry_ipi;
+				raw_spin_lock_irqsave_rcu_node(rnp, flags);
+			}
+			if (!(rnp->expmask & mask))
+				mask_ofl_ipi &= ~mask;
+			raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		}
 		/* Report quiescent states for those that went offline. */
 		mask_ofl_test |= mask_ofl_ipi;
@@ -3773,6 +3771,7 @@
 	unsigned long jiffies_stall;
 	unsigned long jiffies_start;
 	unsigned long mask;
+	int ndetected;
 	struct rcu_node *rnp;
 	struct rcu_node *rnp_root = rcu_get_root(rsp);
 	int ret;
@@ -3785,7 +3784,7 @@
 				rsp->expedited_wq,
 				sync_rcu_preempt_exp_done(rnp_root),
 				jiffies_stall);
-		if (ret > 0)
+		if (ret > 0 || sync_rcu_preempt_exp_done(rnp_root))
 			return;
 		if (ret < 0) {
 			/* Hit a signal, disable CPU stall warnings. */
@@ -3795,14 +3794,16 @@
 		}
 		pr_err("INFO: %s detected expedited stalls on CPUs/tasks: {",
 		       rsp->name);
+		ndetected = 0;
 		rcu_for_each_leaf_node(rsp, rnp) {
-			(void)rcu_print_task_exp_stall(rnp);
+			ndetected = rcu_print_task_exp_stall(rnp);
 			mask = 1;
 			for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask <<= 1) {
 				struct rcu_data *rdp;
 
 				if (!(rnp->expmask & mask))
 					continue;
+				ndetected++;
 				rdp = per_cpu_ptr(rsp->rda, cpu);
 				pr_cont(" %d-%c%c%c", cpu,
 					"O."[cpu_online(cpu)],
@@ -3811,8 +3812,23 @@
 			}
 			mask <<= 1;
 		}
-		pr_cont(" } %lu jiffies s: %lu\n",
-			jiffies - jiffies_start, rsp->expedited_sequence);
+		pr_cont(" } %lu jiffies s: %lu root: %#lx/%c\n",
+			jiffies - jiffies_start, rsp->expedited_sequence,
+			rnp_root->expmask, ".T"[!!rnp_root->exp_tasks]);
+		if (!ndetected) {
+			pr_err("blocking rcu_node structures:");
+			rcu_for_each_node_breadth_first(rsp, rnp) {
+				if (rnp == rnp_root)
+					continue; /* printed unconditionally */
+				if (sync_rcu_preempt_exp_done(rnp))
+					continue;
+				pr_cont(" l=%u:%d-%d:%#lx/%c",
+					rnp->level, rnp->grplo, rnp->grphi,
+					rnp->expmask,
+					".T"[!!rnp->exp_tasks]);
+			}
+			pr_cont("\n");
+		}
 		rcu_for_each_leaf_node(rsp, rnp) {
 			mask = 1;
 			for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask <<= 1) {
@@ -3847,6 +3863,16 @@
 	struct rcu_node *rnp;
 	struct rcu_state *rsp = &rcu_sched_state;
 
+	/* If only one CPU, this is automatically a grace period. */
+	if (rcu_blocking_is_gp())
+		return;
+
+	/* If expedited grace periods are prohibited, fall back to normal. */
+	if (rcu_gp_is_normal()) {
+		wait_rcu_gp(call_rcu_sched);
+		return;
+	}
+
 	/* Take a snapshot of the sequence number.  */
 	s = rcu_exp_gp_seq_snap(rsp);
 
@@ -4135,7 +4161,7 @@
 		rnp = rnp->parent;
 		if (rnp == NULL)
 			return;
-		raw_spin_lock(&rnp->lock); /* Interrupts already disabled. */
+		raw_spin_lock_rcu_node(rnp); /* Interrupts already disabled. */
 		rnp->qsmaskinit |= mask;
 		raw_spin_unlock(&rnp->lock); /* Interrupts remain disabled. */
 	}
@@ -4152,7 +4178,7 @@
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
 	/* Set up local state, ensuring consistent view of global state. */
-	raw_spin_lock_irqsave(&rnp->lock, flags);
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	rdp->grpmask = 1UL << (cpu - rdp->mynode->grplo);
 	rdp->dynticks = &per_cpu(rcu_dynticks, cpu);
 	WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != DYNTICK_TASK_EXIT_IDLE);
@@ -4179,7 +4205,7 @@
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
 	/* Set up local state, ensuring consistent view of global state. */
-	raw_spin_lock_irqsave(&rnp->lock, flags);
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	rdp->qlen_last_fqs_check = 0;
 	rdp->n_force_qs_snap = rsp->n_force_qs;
 	rdp->blimit = blimit;
@@ -4198,8 +4224,7 @@
 	 */
 	rnp = rdp->mynode;
 	mask = rdp->grpmask;
-	raw_spin_lock(&rnp->lock);		/* irqs already disabled. */
-	smp_mb__after_unlock_lock();
+	raw_spin_lock_rcu_node(rnp);		/* irqs already disabled. */
 	rnp->qsmaskinitnext |= mask;
 	rnp->expmaskinitnext |= mask;
 	if (!rdp->beenonline)
@@ -4327,14 +4352,14 @@
 		t = kthread_create(rcu_gp_kthread, rsp, "%s", rsp->name);
 		BUG_ON(IS_ERR(t));
 		rnp = rcu_get_root(rsp);
-		raw_spin_lock_irqsave(&rnp->lock, flags);
+		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		rsp->gp_kthread = t;
 		if (kthread_prio) {
 			sp.sched_priority = kthread_prio;
 			sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
 		}
-		wake_up_process(t);
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+		wake_up_process(t);
 	}
 	rcu_spawn_nocb_kthreads();
 	rcu_spawn_boost_kthreads();
@@ -4385,12 +4410,14 @@
 /*
  * Helper function for rcu_init() that initializes one rcu_state structure.
  */
-static void __init rcu_init_one(struct rcu_state *rsp,
-		struct rcu_data __percpu *rda)
+static void __init rcu_init_one(struct rcu_state *rsp)
 {
 	static const char * const buf[] = RCU_NODE_NAME_INIT;
 	static const char * const fqs[] = RCU_FQS_NAME_INIT;
 	static const char * const exp[] = RCU_EXP_NAME_INIT;
+	static struct lock_class_key rcu_node_class[RCU_NUM_LVLS];
+	static struct lock_class_key rcu_fqs_class[RCU_NUM_LVLS];
+	static struct lock_class_key rcu_exp_class[RCU_NUM_LVLS];
 	static u8 fl_mask = 0x1;
 
 	int levelcnt[RCU_NUM_LVLS];		/* # nodes in each level. */
@@ -4576,8 +4603,8 @@
 
 	rcu_bootup_announce();
 	rcu_init_geometry();
-	rcu_init_one(&rcu_bh_state, &rcu_bh_data);
-	rcu_init_one(&rcu_sched_state, &rcu_sched_data);
+	rcu_init_one(&rcu_bh_state);
+	rcu_init_one(&rcu_sched_state);
 	if (dump_tree)
 		rcu_dump_rcu_node_tree(&rcu_sched_state);
 	__rcu_init_preempt();
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 9fb4e238..83360b4 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -178,6 +178,8 @@
 				/*  beginning of each expedited GP. */
 	unsigned long expmaskinitnext;
 				/* Online CPUs for next expedited GP. */
+				/*  Any CPU that has ever been online will */
+				/*  have its bit set. */
 	unsigned long grpmask;	/* Mask to apply to parent qsmask. */
 				/*  Only one bit will be set in this mask. */
 	int	grplo;		/* lowest-numbered CPU or group here. */
@@ -384,6 +386,10 @@
 	struct rcu_head oom_head;
 #endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */
 	struct mutex exp_funnel_mutex;
+	atomic_long_t expedited_workdone0;	/* # done by others #0. */
+	atomic_long_t expedited_workdone1;	/* # done by others #1. */
+	atomic_long_t expedited_workdone2;	/* # done by others #2. */
+	atomic_long_t expedited_workdone3;	/* # done by others #3. */
 
 	/* 7) Callback offloading. */
 #ifdef CONFIG_RCU_NOCB_CPU
@@ -498,10 +504,6 @@
 	/* End of fields guarded by barrier_mutex. */
 
 	unsigned long expedited_sequence;	/* Take a ticket. */
-	atomic_long_t expedited_workdone0;	/* # done by others #0. */
-	atomic_long_t expedited_workdone1;	/* # done by others #1. */
-	atomic_long_t expedited_workdone2;	/* # done by others #2. */
-	atomic_long_t expedited_workdone3;	/* # done by others #3. */
 	atomic_long_t expedited_normal;		/* # fallbacks to normal. */
 	atomic_t expedited_need_qs;		/* # CPUs left to check in. */
 	wait_queue_head_t expedited_wq;		/* Wait for check-ins. */
@@ -545,6 +547,18 @@
 #define RCU_GP_CLEANUP   5	/* Grace-period cleanup started. */
 #define RCU_GP_CLEANED   6	/* Grace-period cleanup complete. */
 
+#ifndef RCU_TREE_NONCORE
+static const char * const gp_state_names[] = {
+	"RCU_GP_IDLE",
+	"RCU_GP_WAIT_GPS",
+	"RCU_GP_DONE_GPS",
+	"RCU_GP_WAIT_FQS",
+	"RCU_GP_DOING_FQS",
+	"RCU_GP_CLEANUP",
+	"RCU_GP_CLEANED",
+};
+#endif /* #ifndef RCU_TREE_NONCORE */
+
 extern struct list_head rcu_struct_flavors;
 
 /* Sequence through rcu_state structures for each RCU flavor. */
@@ -664,3 +678,42 @@
 #else /* #ifdef CONFIG_PPC */
 #define smp_mb__after_unlock_lock()	do { } while (0)
 #endif /* #else #ifdef CONFIG_PPC */
+
+/*
+ * Wrappers for the rcu_node::lock acquire.
+ *
+ * Because the rcu_nodes form a tree, the tree traversal locking will observe
+ * different lock values, this in turn means that an UNLOCK of one level
+ * followed by a LOCK of another level does not imply a full memory barrier;
+ * and most importantly transitivity is lost.
+ *
+ * In order to restore full ordering between tree levels, augment the regular
+ * lock acquire functions with smp_mb__after_unlock_lock().
+ */
+static inline void raw_spin_lock_rcu_node(struct rcu_node *rnp)
+{
+	raw_spin_lock(&rnp->lock);
+	smp_mb__after_unlock_lock();
+}
+
+static inline void raw_spin_lock_irq_rcu_node(struct rcu_node *rnp)
+{
+	raw_spin_lock_irq(&rnp->lock);
+	smp_mb__after_unlock_lock();
+}
+
+#define raw_spin_lock_irqsave_rcu_node(rnp, flags)	\
+do {							\
+	typecheck(unsigned long, flags);		\
+	raw_spin_lock_irqsave(&(rnp)->lock, flags);	\
+	smp_mb__after_unlock_lock();			\
+} while (0)
+
+static inline bool raw_spin_trylock_rcu_node(struct rcu_node *rnp)
+{
+	bool locked = raw_spin_trylock(&rnp->lock);
+
+	if (locked)
+		smp_mb__after_unlock_lock();
+	return locked;
+}
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 630c197..9467a8b 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -63,8 +63,7 @@
 
 /*
  * Check the RCU kernel configuration parameters and print informative
- * messages about anything out of the ordinary.  If you like #ifdef, you
- * will love this function.
+ * messages about anything out of the ordinary.
  */
 static void __init rcu_bootup_announce_oddness(void)
 {
@@ -147,8 +146,8 @@
  * the corresponding expedited grace period will also be the end of the
  * normal grace period.
  */
-static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp,
-				   unsigned long flags) __releases(rnp->lock)
+static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp)
+	__releases(rnp->lock) /* But leaves rrupts disabled. */
 {
 	int blkd_state = (rnp->gp_tasks ? RCU_GP_TASKS : 0) +
 			 (rnp->exp_tasks ? RCU_EXP_TASKS : 0) +
@@ -236,7 +235,7 @@
 		rnp->gp_tasks = &t->rcu_node_entry;
 	if (!rnp->exp_tasks && (blkd_state & RCU_EXP_BLKD))
 		rnp->exp_tasks = &t->rcu_node_entry;
-	raw_spin_unlock(&rnp->lock);
+	raw_spin_unlock(&rnp->lock); /* rrupts remain disabled. */
 
 	/*
 	 * Report the quiescent state for the expedited GP.  This expedited
@@ -251,7 +250,6 @@
 	} else {
 		WARN_ON_ONCE(t->rcu_read_unlock_special.b.exp_need_qs);
 	}
-	local_irq_restore(flags);
 }
 
 /*
@@ -286,12 +284,11 @@
  * predating the current grace period drain, in other words, until
  * rnp->gp_tasks becomes NULL.
  *
- * Caller must disable preemption.
+ * Caller must disable interrupts.
  */
 static void rcu_preempt_note_context_switch(void)
 {
 	struct task_struct *t = current;
-	unsigned long flags;
 	struct rcu_data *rdp;
 	struct rcu_node *rnp;
 
@@ -301,8 +298,7 @@
 		/* Possibly blocking in an RCU read-side critical section. */
 		rdp = this_cpu_ptr(rcu_state_p->rda);
 		rnp = rdp->mynode;
-		raw_spin_lock_irqsave(&rnp->lock, flags);
-		smp_mb__after_unlock_lock();
+		raw_spin_lock_rcu_node(rnp);
 		t->rcu_read_unlock_special.b.blocked = true;
 		t->rcu_blocked_node = rnp;
 
@@ -318,7 +314,7 @@
 				       (rnp->qsmask & rdp->grpmask)
 				       ? rnp->gpnum
 				       : rnp->gpnum + 1);
-		rcu_preempt_ctxt_queue(rnp, rdp, flags);
+		rcu_preempt_ctxt_queue(rnp, rdp);
 	} else if (t->rcu_read_lock_nesting < 0 &&
 		   t->rcu_read_unlock_special.s) {
 
@@ -450,20 +446,13 @@
 
 		/*
 		 * Remove this task from the list it blocked on.  The task
-		 * now remains queued on the rcu_node corresponding to
-		 * the CPU it first blocked on, so the first attempt to
-		 * acquire the task's rcu_node's ->lock will succeed.
-		 * Keep the loop and add a WARN_ON() out of sheer paranoia.
+		 * now remains queued on the rcu_node corresponding to the
+		 * CPU it first blocked on, so there is no longer any need
+		 * to loop.  Retain a WARN_ON_ONCE() out of sheer paranoia.
 		 */
-		for (;;) {
-			rnp = t->rcu_blocked_node;
-			raw_spin_lock(&rnp->lock);  /* irqs already disabled. */
-			smp_mb__after_unlock_lock();
-			if (rnp == t->rcu_blocked_node)
-				break;
-			WARN_ON_ONCE(1);
-			raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
-		}
+		rnp = t->rcu_blocked_node;
+		raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
+		WARN_ON_ONCE(rnp != t->rcu_blocked_node);
 		empty_norm = !rcu_preempt_blocked_readers_cgp(rnp);
 		empty_exp = sync_rcu_preempt_exp_done(rnp);
 		smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */
@@ -527,7 +516,7 @@
 	unsigned long flags;
 	struct task_struct *t;
 
-	raw_spin_lock_irqsave(&rnp->lock, flags);
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	if (!rcu_preempt_blocked_readers_cgp(rnp)) {
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		return;
@@ -748,6 +737,12 @@
 	struct rcu_state *rsp = rcu_state_p;
 	unsigned long s;
 
+	/* If expedited grace periods are prohibited, fall back to normal. */
+	if (rcu_gp_is_normal()) {
+		wait_rcu_gp(call_rcu);
+		return;
+	}
+
 	s = rcu_exp_gp_seq_snap(rsp);
 
 	rnp_unlock = exp_funnel_lock(rsp, s);
@@ -788,7 +783,7 @@
  */
 static void __init __rcu_init_preempt(void)
 {
-	rcu_init_one(rcu_state_p, rcu_data_p);
+	rcu_init_one(rcu_state_p);
 }
 
 /*
@@ -989,8 +984,7 @@
 	    READ_ONCE(rnp->boost_tasks) == NULL)
 		return 0;  /* Nothing left to boost. */
 
-	raw_spin_lock_irqsave(&rnp->lock, flags);
-	smp_mb__after_unlock_lock();
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 
 	/*
 	 * Recheck under the lock: all tasks in need of boosting
@@ -1176,8 +1170,7 @@
 			   "rcub/%d", rnp_index);
 	if (IS_ERR(t))
 		return PTR_ERR(t);
-	raw_spin_lock_irqsave(&rnp->lock, flags);
-	smp_mb__after_unlock_lock();
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	rnp->boost_kthread_task = t;
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	sp.sched_priority = kthread_prio;
@@ -1524,7 +1517,8 @@
 	struct rcu_state *rsp;
 	int tne;
 
-	if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL))
+	if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL) ||
+	    rcu_is_nocb_cpu(smp_processor_id()))
 		return;
 
 	/* Handle nohz enablement switches conservatively. */
@@ -1538,10 +1532,6 @@
 	if (!tne)
 		return;
 
-	/* If this is a no-CBs CPU, no callbacks, just return. */
-	if (rcu_is_nocb_cpu(smp_processor_id()))
-		return;
-
 	/*
 	 * If a non-lazy callback arrived at a CPU having only lazy
 	 * callbacks, invoke RCU core for the side-effect of recalculating
@@ -1567,8 +1557,7 @@
 		if (!*rdp->nxttail[RCU_DONE_TAIL])
 			continue;
 		rnp = rdp->mynode;
-		raw_spin_lock(&rnp->lock); /* irqs already disabled. */
-		smp_mb__after_unlock_lock();
+		raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
 		needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
 		raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
 		if (needwake)
@@ -2068,8 +2057,7 @@
 	bool needwake;
 	struct rcu_node *rnp = rdp->mynode;
 
-	raw_spin_lock_irqsave(&rnp->lock, flags);
-	smp_mb__after_unlock_lock();
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	needwake = rcu_start_future_gp(rnp, rdp, &c);
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	if (needwake)
diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c
index ef7093c..1088e64 100644
--- a/kernel/rcu/tree_trace.c
+++ b/kernel/rcu/tree_trace.c
@@ -1,5 +1,5 @@
 /*
- * Read-Copy Update tracing for classic implementation
+ * Read-Copy Update tracing for hierarchical implementation.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -16,6 +16,7 @@
  * http://www.gnu.org/licenses/gpl-2.0.html.
  *
  * Copyright IBM Corporation, 2008
+ * Author: Paul E. McKenney
  *
  * Papers:  http://www.rdrop.com/users/paulmck/RCU
  *
@@ -33,9 +34,7 @@
 #include <linux/sched.h>
 #include <linux/atomic.h>
 #include <linux/bitops.h>
-#include <linux/module.h>
 #include <linux/completion.h>
-#include <linux/moduleparam.h>
 #include <linux/percpu.h>
 #include <linux/notifier.h>
 #include <linux/cpu.h>
@@ -183,14 +182,20 @@
 
 static int show_rcuexp(struct seq_file *m, void *v)
 {
+	int cpu;
 	struct rcu_state *rsp = (struct rcu_state *)m->private;
+	struct rcu_data *rdp;
+	unsigned long s0 = 0, s1 = 0, s2 = 0, s3 = 0;
 
+	for_each_possible_cpu(cpu) {
+		rdp = per_cpu_ptr(rsp->rda, cpu);
+		s0 += atomic_long_read(&rdp->expedited_workdone0);
+		s1 += atomic_long_read(&rdp->expedited_workdone1);
+		s2 += atomic_long_read(&rdp->expedited_workdone2);
+		s3 += atomic_long_read(&rdp->expedited_workdone3);
+	}
 	seq_printf(m, "s=%lu wd0=%lu wd1=%lu wd2=%lu wd3=%lu n=%lu enq=%d sc=%lu\n",
-		   rsp->expedited_sequence,
-		   atomic_long_read(&rsp->expedited_workdone0),
-		   atomic_long_read(&rsp->expedited_workdone1),
-		   atomic_long_read(&rsp->expedited_workdone2),
-		   atomic_long_read(&rsp->expedited_workdone3),
+		   rsp->expedited_sequence, s0, s1, s2, s3,
 		   atomic_long_read(&rsp->expedited_normal),
 		   atomic_read(&rsp->expedited_need_qs),
 		   rsp->expedited_sequence / 2);
@@ -319,7 +324,7 @@
 	unsigned long gpmax;
 	struct rcu_node *rnp = &rsp->node[0];
 
-	raw_spin_lock_irqsave(&rnp->lock, flags);
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	completed = READ_ONCE(rsp->completed);
 	gpnum = READ_ONCE(rsp->gpnum);
 	if (completed == gpnum)
@@ -487,16 +492,4 @@
 	debugfs_remove_recursive(rcudir);
 	return 1;
 }
-
-static void __exit rcutree_trace_cleanup(void)
-{
-	debugfs_remove_recursive(rcudir);
-}
-
-
-module_init(rcutree_trace_init);
-module_exit(rcutree_trace_cleanup);
-
-MODULE_AUTHOR("Paul E. McKenney");
-MODULE_DESCRIPTION("Read-Copy Update tracing for hierarchical implementation");
-MODULE_LICENSE("GPL");
+device_initcall(rcutree_trace_init);
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 5f748c5..76b94e1 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -60,7 +60,12 @@
 #endif
 #define MODULE_PARAM_PREFIX "rcupdate."
 
+#ifndef CONFIG_TINY_RCU
 module_param(rcu_expedited, int, 0);
+module_param(rcu_normal, int, 0);
+static int rcu_normal_after_boot;
+module_param(rcu_normal_after_boot, int, 0);
+#endif /* #ifndef CONFIG_TINY_RCU */
 
 #if defined(CONFIG_DEBUG_LOCK_ALLOC) && defined(CONFIG_PREEMPT_COUNT)
 /**
@@ -113,6 +118,17 @@
 
 #ifndef CONFIG_TINY_RCU
 
+/*
+ * Should expedited grace-period primitives always fall back to their
+ * non-expedited counterparts?  Intended for use within RCU.  Note
+ * that if the user specifies both rcu_expedited and rcu_normal, then
+ * rcu_normal wins.
+ */
+bool rcu_gp_is_normal(void)
+{
+	return READ_ONCE(rcu_normal);
+}
+
 static atomic_t rcu_expedited_nesting =
 	ATOMIC_INIT(IS_ENABLED(CONFIG_RCU_EXPEDITE_BOOT) ? 1 : 0);
 
@@ -157,8 +173,6 @@
 }
 EXPORT_SYMBOL_GPL(rcu_unexpedite_gp);
 
-#endif /* #ifndef CONFIG_TINY_RCU */
-
 /*
  * Inform RCU of the end of the in-kernel boot sequence.
  */
@@ -166,8 +180,12 @@
 {
 	if (IS_ENABLED(CONFIG_RCU_EXPEDITE_BOOT))
 		rcu_unexpedite_gp();
+	if (rcu_normal_after_boot)
+		WRITE_ONCE(rcu_normal, 1);
 }
 
+#endif /* #ifndef CONFIG_TINY_RCU */
+
 #ifdef CONFIG_PREEMPT_RCU
 
 /*
diff --git a/kernel/sched/auto_group.c b/kernel/sched/auto_group.c
index 750ed60..a5d966c 100644
--- a/kernel/sched/auto_group.c
+++ b/kernel/sched/auto_group.c
@@ -212,7 +212,7 @@
 	ag = autogroup_task_get(p);
 
 	down_write(&ag->lock);
-	err = sched_group_set_shares(ag->tg, prio_to_weight[nice + 20]);
+	err = sched_group_set_shares(ag->tg, sched_prio_to_weight[nice + 20]);
 	if (!err)
 		ag->nice = nice;
 	up_write(&ag->lock);
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index caf4041..bc54e84 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -354,7 +354,7 @@
 		return;
 
 	sched_clock_tick();
-	touch_softlockup_watchdog();
+	touch_softlockup_watchdog_sched();
 }
 EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 732e993..77d97a6 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -731,7 +731,7 @@
 	if (current->policy == SCHED_RR) {
 		struct sched_rt_entity *rt_se = &current->rt;
 
-		return rt_se->run_list.prev == rt_se->run_list.next;
+		return list_is_singular(&rt_se->run_list);
 	}
 
 	/*
@@ -823,8 +823,8 @@
 		return;
 	}
 
-	load->weight = scale_load(prio_to_weight[prio]);
-	load->inv_weight = prio_to_wmult[prio];
+	load->weight = scale_load(sched_prio_to_weight[prio]);
+	load->inv_weight = sched_prio_to_wmult[prio];
 }
 
 static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
@@ -1071,8 +1071,8 @@
 {
 	lockdep_assert_held(&rq->lock);
 
-	dequeue_task(rq, p, 0);
 	p->on_rq = TASK_ON_RQ_MIGRATING;
+	dequeue_task(rq, p, 0);
 	set_task_cpu(p, new_cpu);
 	raw_spin_unlock(&rq->lock);
 
@@ -1080,8 +1080,8 @@
 
 	raw_spin_lock(&rq->lock);
 	BUG_ON(task_cpu(p) != new_cpu);
-	p->on_rq = TASK_ON_RQ_QUEUED;
 	enqueue_task(rq, p, 0);
+	p->on_rq = TASK_ON_RQ_QUEUED;
 	check_preempt_curr(rq, p, 0);
 
 	return rq;
@@ -1274,6 +1274,15 @@
 	WARN_ON_ONCE(p->state != TASK_RUNNING && p->state != TASK_WAKING &&
 			!p->on_rq);
 
+	/*
+	 * Migrating fair class task must have p->on_rq = TASK_ON_RQ_MIGRATING,
+	 * because schedstat_wait_{start,end} rebase migrating task's wait_start
+	 * time relying on p->on_rq.
+	 */
+	WARN_ON_ONCE(p->state == TASK_RUNNING &&
+		     p->sched_class == &fair_sched_class &&
+		     (p->on_rq && !task_on_rq_migrating(p)));
+
 #ifdef CONFIG_LOCKDEP
 	/*
 	 * The caller should hold either p->pi_lock or rq->lock, when changing
@@ -1310,9 +1319,11 @@
 		src_rq = task_rq(p);
 		dst_rq = cpu_rq(cpu);
 
+		p->on_rq = TASK_ON_RQ_MIGRATING;
 		deactivate_task(src_rq, p, 0);
 		set_task_cpu(p, cpu);
 		activate_task(dst_rq, p, 0);
+		p->on_rq = TASK_ON_RQ_QUEUED;
 		check_preempt_curr(dst_rq, p, 0);
 	} else {
 		/*
@@ -1905,6 +1916,97 @@
 	raw_spin_unlock(&rq->lock);
 }
 
+/*
+ * Notes on Program-Order guarantees on SMP systems.
+ *
+ *  MIGRATION
+ *
+ * The basic program-order guarantee on SMP systems is that when a task [t]
+ * migrates, all its activity on its old cpu [c0] happens-before any subsequent
+ * execution on its new cpu [c1].
+ *
+ * For migration (of runnable tasks) this is provided by the following means:
+ *
+ *  A) UNLOCK of the rq(c0)->lock scheduling out task t
+ *  B) migration for t is required to synchronize *both* rq(c0)->lock and
+ *     rq(c1)->lock (if not at the same time, then in that order).
+ *  C) LOCK of the rq(c1)->lock scheduling in task
+ *
+ * Transitivity guarantees that B happens after A and C after B.
+ * Note: we only require RCpc transitivity.
+ * Note: the cpu doing B need not be c0 or c1
+ *
+ * Example:
+ *
+ *   CPU0            CPU1            CPU2
+ *
+ *   LOCK rq(0)->lock
+ *   sched-out X
+ *   sched-in Y
+ *   UNLOCK rq(0)->lock
+ *
+ *                                   LOCK rq(0)->lock // orders against CPU0
+ *                                   dequeue X
+ *                                   UNLOCK rq(0)->lock
+ *
+ *                                   LOCK rq(1)->lock
+ *                                   enqueue X
+ *                                   UNLOCK rq(1)->lock
+ *
+ *                   LOCK rq(1)->lock // orders against CPU2
+ *                   sched-out Z
+ *                   sched-in X
+ *                   UNLOCK rq(1)->lock
+ *
+ *
+ *  BLOCKING -- aka. SLEEP + WAKEUP
+ *
+ * For blocking we (obviously) need to provide the same guarantee as for
+ * migration. However the means are completely different as there is no lock
+ * chain to provide order. Instead we do:
+ *
+ *   1) smp_store_release(X->on_cpu, 0)
+ *   2) smp_cond_acquire(!X->on_cpu)
+ *
+ * Example:
+ *
+ *   CPU0 (schedule)  CPU1 (try_to_wake_up) CPU2 (schedule)
+ *
+ *   LOCK rq(0)->lock LOCK X->pi_lock
+ *   dequeue X
+ *   sched-out X
+ *   smp_store_release(X->on_cpu, 0);
+ *
+ *                    smp_cond_acquire(!X->on_cpu);
+ *                    X->state = WAKING
+ *                    set_task_cpu(X,2)
+ *
+ *                    LOCK rq(2)->lock
+ *                    enqueue X
+ *                    X->state = RUNNING
+ *                    UNLOCK rq(2)->lock
+ *
+ *                                          LOCK rq(2)->lock // orders against CPU1
+ *                                          sched-out Z
+ *                                          sched-in X
+ *                                          UNLOCK rq(2)->lock
+ *
+ *                    UNLOCK X->pi_lock
+ *   UNLOCK rq(0)->lock
+ *
+ *
+ * However; for wakeups there is a second guarantee we must provide, namely we
+ * must observe the state that lead to our wakeup. That is, not only must our
+ * task observe its own prior state, it must also observe the stores prior to
+ * its wakeup.
+ *
+ * This means that any means of doing remote wakeups must order the CPU doing
+ * the wakeup against the CPU the task is going to end up running on. This,
+ * however, is already required for the regular Program-Order guarantee above,
+ * since the waking CPU is the one issueing the ACQUIRE (smp_cond_acquire).
+ *
+ */
+
 /**
  * try_to_wake_up - wake up a thread
  * @p: the thread to be awakened
@@ -1968,19 +2070,13 @@
 	/*
 	 * If the owning (remote) cpu is still in the middle of schedule() with
 	 * this task as prev, wait until its done referencing the task.
-	 */
-	while (p->on_cpu)
-		cpu_relax();
-	/*
-	 * Combined with the control dependency above, we have an effective
-	 * smp_load_acquire() without the need for full barriers.
 	 *
 	 * Pairs with the smp_store_release() in finish_lock_switch().
 	 *
 	 * This ensures that tasks getting woken will be fully ordered against
 	 * their previous state and preserve Program Order.
 	 */
-	smp_rmb();
+	smp_cond_acquire(!p->on_cpu);
 
 	p->sched_contributes_to_load = !!task_contributes_to_load(p);
 	p->state = TASK_WAKING;
@@ -2109,6 +2205,10 @@
 	p->se.vruntime			= 0;
 	INIT_LIST_HEAD(&p->se.group_node);
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	p->se.cfs_rq			= NULL;
+#endif
+
 #ifdef CONFIG_SCHEDSTATS
 	memset(&p->se.statistics, 0, sizeof(p->se.statistics));
 #endif
@@ -3109,7 +3209,6 @@
 
 	cpu = smp_processor_id();
 	rq = cpu_rq(cpu);
-	rcu_note_context_switch();
 	prev = rq->curr;
 
 	/*
@@ -3128,13 +3227,16 @@
 	if (sched_feat(HRTICK))
 		hrtick_clear(rq);
 
+	local_irq_disable();
+	rcu_note_context_switch();
+
 	/*
 	 * Make sure that signal_pending_state()->signal_pending() below
 	 * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE)
 	 * done by the caller to avoid the race with signal_wake_up().
 	 */
 	smp_mb__before_spinlock();
-	raw_spin_lock_irq(&rq->lock);
+	raw_spin_lock(&rq->lock);
 	lockdep_pin_lock(&rq->lock);
 
 	rq->clock_skip_update <<= 1; /* promote REQ to ACT */
@@ -7355,6 +7457,9 @@
  */
 struct task_group root_task_group;
 LIST_HEAD(task_groups);
+
+/* Cacheline aligned slab cache for task_group */
+static struct kmem_cache *task_group_cache __read_mostly;
 #endif
 
 DECLARE_PER_CPU(cpumask_var_t, load_balance_mask);
@@ -7412,11 +7517,12 @@
 #endif /* CONFIG_RT_GROUP_SCHED */
 
 #ifdef CONFIG_CGROUP_SCHED
+	task_group_cache = KMEM_CACHE(task_group, 0);
+
 	list_add(&root_task_group.list, &task_groups);
 	INIT_LIST_HEAD(&root_task_group.children);
 	INIT_LIST_HEAD(&root_task_group.siblings);
 	autogroup_init(&init_task);
-
 #endif /* CONFIG_CGROUP_SCHED */
 
 	for_each_possible_cpu(i) {
@@ -7697,7 +7803,7 @@
 	free_fair_sched_group(tg);
 	free_rt_sched_group(tg);
 	autogroup_free(tg);
-	kfree(tg);
+	kmem_cache_free(task_group_cache, tg);
 }
 
 /* allocate runqueue etc for a new task group */
@@ -7705,7 +7811,7 @@
 {
 	struct task_group *tg;
 
-	tg = kzalloc(sizeof(*tg), GFP_KERNEL);
+	tg = kmem_cache_alloc(task_group_cache, GFP_KERNEL | __GFP_ZERO);
 	if (!tg)
 		return ERR_PTR(-ENOMEM);
 
@@ -8610,3 +8716,44 @@
 	pr_info("Task dump for CPU %d:\n", cpu);
 	sched_show_task(cpu_curr(cpu));
 }
+
+/*
+ * Nice levels are multiplicative, with a gentle 10% change for every
+ * nice level changed. I.e. when a CPU-bound task goes from nice 0 to
+ * nice 1, it will get ~10% less CPU time than another CPU-bound task
+ * that remained on nice 0.
+ *
+ * The "10% effect" is relative and cumulative: from _any_ nice level,
+ * if you go up 1 level, it's -10% CPU usage, if you go down 1 level
+ * it's +10% CPU usage. (to achieve that we use a multiplier of 1.25.
+ * If a task goes up by ~10% and another task goes down by ~10% then
+ * the relative distance between them is ~25%.)
+ */
+const int sched_prio_to_weight[40] = {
+ /* -20 */     88761,     71755,     56483,     46273,     36291,
+ /* -15 */     29154,     23254,     18705,     14949,     11916,
+ /* -10 */      9548,      7620,      6100,      4904,      3906,
+ /*  -5 */      3121,      2501,      1991,      1586,      1277,
+ /*   0 */      1024,       820,       655,       526,       423,
+ /*   5 */       335,       272,       215,       172,       137,
+ /*  10 */       110,        87,        70,        56,        45,
+ /*  15 */        36,        29,        23,        18,        15,
+};
+
+/*
+ * Inverse (2^32/x) values of the sched_prio_to_weight[] array, precalculated.
+ *
+ * In cases where the weight does not change often, we can use the
+ * precalculated inverse to speed up arithmetics by turning divisions
+ * into multiplications:
+ */
+const u32 sched_prio_to_wmult[40] = {
+ /* -20 */     48388,     59856,     76040,     92818,    118348,
+ /* -15 */    147320,    184698,    229616,    287308,    360437,
+ /* -10 */    449829,    563644,    704093,    875809,   1099582,
+ /*  -5 */   1376151,   1717300,   2157191,   2708050,   3363326,
+ /*   0 */   4194304,   5237765,   6557202,   8165337,  10153587,
+ /*   5 */  12820798,  15790321,  19976592,  24970740,  31350126,
+ /*  10 */  39045157,  49367440,  61356676,  76695844,  95443717,
+ /*  15 */ 119304647, 148102320, 186737708, 238609294, 286331153,
+};
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 05de80b..b2ab2ff 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -5,6 +5,9 @@
 #include <linux/static_key.h>
 #include <linux/context_tracking.h>
 #include "sched.h"
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt.h>
+#endif
 
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
@@ -466,7 +469,7 @@
 	cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
 	struct rq *rq = this_rq();
 
-	if (vtime_accounting_enabled())
+	if (vtime_accounting_cpu_enabled())
 		return;
 
 	if (sched_clock_irqtime) {
@@ -680,7 +683,7 @@
 {
 	unsigned long long delta = vtime_delta(tsk);
 
-	WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_SLEEPING);
+	WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_INACTIVE);
 	tsk->vtime_snap += delta;
 
 	/* CHECKME: always safe to convert nsecs to cputime? */
@@ -696,37 +699,37 @@
 
 void vtime_account_system(struct task_struct *tsk)
 {
-	write_seqlock(&tsk->vtime_seqlock);
+	write_seqcount_begin(&tsk->vtime_seqcount);
 	__vtime_account_system(tsk);
-	write_sequnlock(&tsk->vtime_seqlock);
+	write_seqcount_end(&tsk->vtime_seqcount);
 }
 
 void vtime_gen_account_irq_exit(struct task_struct *tsk)
 {
-	write_seqlock(&tsk->vtime_seqlock);
+	write_seqcount_begin(&tsk->vtime_seqcount);
 	__vtime_account_system(tsk);
 	if (context_tracking_in_user())
 		tsk->vtime_snap_whence = VTIME_USER;
-	write_sequnlock(&tsk->vtime_seqlock);
+	write_seqcount_end(&tsk->vtime_seqcount);
 }
 
 void vtime_account_user(struct task_struct *tsk)
 {
 	cputime_t delta_cpu;
 
-	write_seqlock(&tsk->vtime_seqlock);
+	write_seqcount_begin(&tsk->vtime_seqcount);
 	delta_cpu = get_vtime_delta(tsk);
 	tsk->vtime_snap_whence = VTIME_SYS;
 	account_user_time(tsk, delta_cpu, cputime_to_scaled(delta_cpu));
-	write_sequnlock(&tsk->vtime_seqlock);
+	write_seqcount_end(&tsk->vtime_seqcount);
 }
 
 void vtime_user_enter(struct task_struct *tsk)
 {
-	write_seqlock(&tsk->vtime_seqlock);
+	write_seqcount_begin(&tsk->vtime_seqcount);
 	__vtime_account_system(tsk);
 	tsk->vtime_snap_whence = VTIME_USER;
-	write_sequnlock(&tsk->vtime_seqlock);
+	write_seqcount_end(&tsk->vtime_seqcount);
 }
 
 void vtime_guest_enter(struct task_struct *tsk)
@@ -738,19 +741,19 @@
 	 * synchronization against the reader (task_gtime())
 	 * that can thus safely catch up with a tickless delta.
 	 */
-	write_seqlock(&tsk->vtime_seqlock);
+	write_seqcount_begin(&tsk->vtime_seqcount);
 	__vtime_account_system(tsk);
 	current->flags |= PF_VCPU;
-	write_sequnlock(&tsk->vtime_seqlock);
+	write_seqcount_end(&tsk->vtime_seqcount);
 }
 EXPORT_SYMBOL_GPL(vtime_guest_enter);
 
 void vtime_guest_exit(struct task_struct *tsk)
 {
-	write_seqlock(&tsk->vtime_seqlock);
+	write_seqcount_begin(&tsk->vtime_seqcount);
 	__vtime_account_system(tsk);
 	current->flags &= ~PF_VCPU;
-	write_sequnlock(&tsk->vtime_seqlock);
+	write_seqcount_end(&tsk->vtime_seqcount);
 }
 EXPORT_SYMBOL_GPL(vtime_guest_exit);
 
@@ -763,24 +766,26 @@
 
 void arch_vtime_task_switch(struct task_struct *prev)
 {
-	write_seqlock(&prev->vtime_seqlock);
-	prev->vtime_snap_whence = VTIME_SLEEPING;
-	write_sequnlock(&prev->vtime_seqlock);
+	write_seqcount_begin(&prev->vtime_seqcount);
+	prev->vtime_snap_whence = VTIME_INACTIVE;
+	write_seqcount_end(&prev->vtime_seqcount);
 
-	write_seqlock(&current->vtime_seqlock);
+	write_seqcount_begin(&current->vtime_seqcount);
 	current->vtime_snap_whence = VTIME_SYS;
 	current->vtime_snap = sched_clock_cpu(smp_processor_id());
-	write_sequnlock(&current->vtime_seqlock);
+	write_seqcount_end(&current->vtime_seqcount);
 }
 
 void vtime_init_idle(struct task_struct *t, int cpu)
 {
 	unsigned long flags;
 
-	write_seqlock_irqsave(&t->vtime_seqlock, flags);
+	local_irq_save(flags);
+	write_seqcount_begin(&t->vtime_seqcount);
 	t->vtime_snap_whence = VTIME_SYS;
 	t->vtime_snap = sched_clock_cpu(cpu);
-	write_sequnlock_irqrestore(&t->vtime_seqlock, flags);
+	write_seqcount_end(&t->vtime_seqcount);
+	local_irq_restore(flags);
 }
 
 cputime_t task_gtime(struct task_struct *t)
@@ -788,17 +793,17 @@
 	unsigned int seq;
 	cputime_t gtime;
 
-	if (!context_tracking_is_enabled())
+	if (!vtime_accounting_enabled())
 		return t->gtime;
 
 	do {
-		seq = read_seqbegin(&t->vtime_seqlock);
+		seq = read_seqcount_begin(&t->vtime_seqcount);
 
 		gtime = t->gtime;
-		if (t->flags & PF_VCPU)
+		if (t->vtime_snap_whence == VTIME_SYS && t->flags & PF_VCPU)
 			gtime += vtime_delta(t);
 
-	} while (read_seqretry(&t->vtime_seqlock, seq));
+	} while (read_seqcount_retry(&t->vtime_seqcount, seq));
 
 	return gtime;
 }
@@ -821,7 +826,7 @@
 		*udelta = 0;
 		*sdelta = 0;
 
-		seq = read_seqbegin(&t->vtime_seqlock);
+		seq = read_seqcount_begin(&t->vtime_seqcount);
 
 		if (u_dst)
 			*u_dst = *u_src;
@@ -829,7 +834,7 @@
 			*s_dst = *s_src;
 
 		/* Task is sleeping, nothing to add */
-		if (t->vtime_snap_whence == VTIME_SLEEPING ||
+		if (t->vtime_snap_whence == VTIME_INACTIVE ||
 		    is_idle_task(t))
 			continue;
 
@@ -845,7 +850,7 @@
 			if (t->vtime_snap_whence == VTIME_SYS)
 				*sdelta = delta;
 		}
-	} while (read_seqretry(&t->vtime_seqlock, seq));
+	} while (read_seqcount_retry(&t->vtime_seqcount, seq));
 }
 
 
@@ -853,6 +858,14 @@
 {
 	cputime_t udelta, sdelta;
 
+	if (!vtime_accounting_enabled()) {
+		if (utime)
+			*utime = t->utime;
+		if (stime)
+			*stime = t->stime;
+		return;
+	}
+
 	fetch_task_cputime(t, utime, stime, &t->utime,
 			   &t->stime, &udelta, &sdelta);
 	if (utime)
@@ -866,6 +879,14 @@
 {
 	cputime_t udelta, sdelta;
 
+	if (!vtime_accounting_enabled()) {
+		if (utimescaled)
+			*utimescaled = t->utimescaled;
+		if (stimescaled)
+			*stimescaled = t->stimescaled;
+		return;
+	}
+
 	fetch_task_cputime(t, utimescaled, stimescaled,
 			   &t->utimescaled, &t->stimescaled, &udelta, &sdelta);
 	if (utimescaled)
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 8b0a15e..cd64c97 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -176,8 +176,10 @@
 		}
 	}
 
-	if (leftmost)
+	if (leftmost) {
 		dl_rq->pushable_dl_tasks_leftmost = &p->pushable_dl_tasks;
+		dl_rq->earliest_dl.next = p->dl.deadline;
+	}
 
 	rb_link_node(&p->pushable_dl_tasks, parent, link);
 	rb_insert_color(&p->pushable_dl_tasks, &dl_rq->pushable_dl_tasks_root);
@@ -195,6 +197,10 @@
 
 		next_node = rb_next(&p->pushable_dl_tasks);
 		dl_rq->pushable_dl_tasks_leftmost = next_node;
+		if (next_node) {
+			dl_rq->earliest_dl.next = rb_entry(next_node,
+				struct task_struct, pushable_dl_tasks)->dl.deadline;
+		}
 	}
 
 	rb_erase(&p->pushable_dl_tasks, &dl_rq->pushable_dl_tasks_root);
@@ -782,42 +788,14 @@
 
 #ifdef CONFIG_SMP
 
-static struct task_struct *pick_next_earliest_dl_task(struct rq *rq, int cpu);
-
-static inline u64 next_deadline(struct rq *rq)
-{
-	struct task_struct *next = pick_next_earliest_dl_task(rq, rq->cpu);
-
-	if (next && dl_prio(next->prio))
-		return next->dl.deadline;
-	else
-		return 0;
-}
-
 static void inc_dl_deadline(struct dl_rq *dl_rq, u64 deadline)
 {
 	struct rq *rq = rq_of_dl_rq(dl_rq);
 
 	if (dl_rq->earliest_dl.curr == 0 ||
 	    dl_time_before(deadline, dl_rq->earliest_dl.curr)) {
-		/*
-		 * If the dl_rq had no -deadline tasks, or if the new task
-		 * has shorter deadline than the current one on dl_rq, we
-		 * know that the previous earliest becomes our next earliest,
-		 * as the new task becomes the earliest itself.
-		 */
-		dl_rq->earliest_dl.next = dl_rq->earliest_dl.curr;
 		dl_rq->earliest_dl.curr = deadline;
 		cpudl_set(&rq->rd->cpudl, rq->cpu, deadline, 1);
-	} else if (dl_rq->earliest_dl.next == 0 ||
-		   dl_time_before(deadline, dl_rq->earliest_dl.next)) {
-		/*
-		 * On the other hand, if the new -deadline task has a
-		 * a later deadline than the earliest one on dl_rq, but
-		 * it is earlier than the next (if any), we must
-		 * recompute the next-earliest.
-		 */
-		dl_rq->earliest_dl.next = next_deadline(rq);
 	}
 }
 
@@ -839,7 +817,6 @@
 
 		entry = rb_entry(leftmost, struct sched_dl_entity, rb_node);
 		dl_rq->earliest_dl.curr = entry->deadline;
-		dl_rq->earliest_dl.next = next_deadline(rq);
 		cpudl_set(&rq->rd->cpudl, rq->cpu, entry->deadline, 1);
 	}
 }
@@ -1274,28 +1251,6 @@
 	return 0;
 }
 
-/* Returns the second earliest -deadline task, NULL otherwise */
-static struct task_struct *pick_next_earliest_dl_task(struct rq *rq, int cpu)
-{
-	struct rb_node *next_node = rq->dl.rb_leftmost;
-	struct sched_dl_entity *dl_se;
-	struct task_struct *p = NULL;
-
-next_node:
-	next_node = rb_next(next_node);
-	if (next_node) {
-		dl_se = rb_entry(next_node, struct sched_dl_entity, rb_node);
-		p = dl_task_of(dl_se);
-
-		if (pick_dl_task(rq, p, cpu))
-			return p;
-
-		goto next_node;
-	}
-
-	return NULL;
-}
-
 /*
  * Return the earliest pushable rq's task, which is suitable to be executed
  * on the CPU, NULL otherwise:
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 90e26b1..1926606 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -738,12 +738,56 @@
 	update_curr(cfs_rq_of(&rq->curr->se));
 }
 
+#ifdef CONFIG_SCHEDSTATS
 static inline void
 update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	schedstat_set(se->statistics.wait_start, rq_clock(rq_of(cfs_rq)));
+	u64 wait_start = rq_clock(rq_of(cfs_rq));
+
+	if (entity_is_task(se) && task_on_rq_migrating(task_of(se)) &&
+	    likely(wait_start > se->statistics.wait_start))
+		wait_start -= se->statistics.wait_start;
+
+	se->statistics.wait_start = wait_start;
 }
 
+static void
+update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	struct task_struct *p;
+	u64 delta = rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start;
+
+	if (entity_is_task(se)) {
+		p = task_of(se);
+		if (task_on_rq_migrating(p)) {
+			/*
+			 * Preserve migrating task's wait time so wait_start
+			 * time stamp can be adjusted to accumulate wait time
+			 * prior to migration.
+			 */
+			se->statistics.wait_start = delta;
+			return;
+		}
+		trace_sched_stat_wait(p, delta);
+	}
+
+	se->statistics.wait_max = max(se->statistics.wait_max, delta);
+	se->statistics.wait_count++;
+	se->statistics.wait_sum += delta;
+	se->statistics.wait_start = 0;
+}
+#else
+static inline void
+update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+}
+
+static inline void
+update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+}
+#endif
+
 /*
  * Task is being enqueued - update stats:
  */
@@ -757,23 +801,6 @@
 		update_stats_wait_start(cfs_rq, se);
 }
 
-static void
-update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
-	schedstat_set(se->statistics.wait_max, max(se->statistics.wait_max,
-			rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start));
-	schedstat_set(se->statistics.wait_count, se->statistics.wait_count + 1);
-	schedstat_set(se->statistics.wait_sum, se->statistics.wait_sum +
-			rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start);
-#ifdef CONFIG_SCHEDSTATS
-	if (entity_is_task(se)) {
-		trace_sched_stat_wait(task_of(se),
-			rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start);
-	}
-#endif
-	schedstat_set(se->statistics.wait_start, 0);
-}
-
 static inline void
 update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
@@ -2155,6 +2182,7 @@
 	unsigned long migrate, next_scan, now = jiffies;
 	struct task_struct *p = current;
 	struct mm_struct *mm = p->mm;
+	u64 runtime = p->se.sum_exec_runtime;
 	struct vm_area_struct *vma;
 	unsigned long start, end;
 	unsigned long nr_pte_updates = 0;
@@ -2277,6 +2305,17 @@
 	else
 		reset_ptenuma_scan(p);
 	up_read(&mm->mmap_sem);
+
+	/*
+	 * Make sure tasks use at least 32x as much time to run other code
+	 * than they used here, to limit NUMA PTE scanning overhead to 3% max.
+	 * Usually update_task_scan_period slows down scanning enough; on an
+	 * overloaded system we need to limit overhead on a per task basis.
+	 */
+	if (unlikely(p->se.sum_exec_runtime != runtime)) {
+		u64 diff = p->se.sum_exec_runtime - runtime;
+		p->node_stamp += 32 * diff;
+	}
 }
 
 /*
@@ -2670,12 +2709,64 @@
 {
 	long delta = cfs_rq->avg.load_avg - cfs_rq->tg_load_avg_contrib;
 
+	/*
+	 * No need to update load_avg for root_task_group as it is not used.
+	 */
+	if (cfs_rq->tg == &root_task_group)
+		return;
+
 	if (force || abs(delta) > cfs_rq->tg_load_avg_contrib / 64) {
 		atomic_long_add(delta, &cfs_rq->tg->load_avg);
 		cfs_rq->tg_load_avg_contrib = cfs_rq->avg.load_avg;
 	}
 }
 
+/*
+ * Called within set_task_rq() right before setting a task's cpu. The
+ * caller only guarantees p->pi_lock is held; no other assumptions,
+ * including the state of rq->lock, should be made.
+ */
+void set_task_rq_fair(struct sched_entity *se,
+		      struct cfs_rq *prev, struct cfs_rq *next)
+{
+	if (!sched_feat(ATTACH_AGE_LOAD))
+		return;
+
+	/*
+	 * We are supposed to update the task to "current" time, then its up to
+	 * date and ready to go to new CPU/cfs_rq. But we have difficulty in
+	 * getting what current time is, so simply throw away the out-of-date
+	 * time. This will result in the wakee task is less decayed, but giving
+	 * the wakee more load sounds not bad.
+	 */
+	if (se->avg.last_update_time && prev) {
+		u64 p_last_update_time;
+		u64 n_last_update_time;
+
+#ifndef CONFIG_64BIT
+		u64 p_last_update_time_copy;
+		u64 n_last_update_time_copy;
+
+		do {
+			p_last_update_time_copy = prev->load_last_update_time_copy;
+			n_last_update_time_copy = next->load_last_update_time_copy;
+
+			smp_rmb();
+
+			p_last_update_time = prev->avg.last_update_time;
+			n_last_update_time = next->avg.last_update_time;
+
+		} while (p_last_update_time != p_last_update_time_copy ||
+			 n_last_update_time != n_last_update_time_copy);
+#else
+		p_last_update_time = prev->avg.last_update_time;
+		n_last_update_time = next->avg.last_update_time;
+#endif
+		__update_load_avg(p_last_update_time, cpu_of(rq_of(prev)),
+				  &se->avg, 0, 0, NULL);
+		se->avg.last_update_time = n_last_update_time;
+	}
+}
 #else /* CONFIG_FAIR_GROUP_SCHED */
 static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) {}
 #endif /* CONFIG_FAIR_GROUP_SCHED */
@@ -2689,7 +2780,7 @@
 	int decayed, removed = 0;
 
 	if (atomic_long_read(&cfs_rq->removed_load_avg)) {
-		long r = atomic_long_xchg(&cfs_rq->removed_load_avg, 0);
+		s64 r = atomic_long_xchg(&cfs_rq->removed_load_avg, 0);
 		sa->load_avg = max_t(long, sa->load_avg - r, 0);
 		sa->load_sum = max_t(s64, sa->load_sum - r * LOAD_AVG_MAX, 0);
 		removed = 1;
@@ -2809,6 +2900,27 @@
 		max_t(s64,  cfs_rq->runnable_load_sum - se->avg.load_sum, 0);
 }
 
+#ifndef CONFIG_64BIT
+static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq)
+{
+	u64 last_update_time_copy;
+	u64 last_update_time;
+
+	do {
+		last_update_time_copy = cfs_rq->load_last_update_time_copy;
+		smp_rmb();
+		last_update_time = cfs_rq->avg.last_update_time;
+	} while (last_update_time != last_update_time_copy);
+
+	return last_update_time;
+}
+#else
+static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq)
+{
+	return cfs_rq->avg.last_update_time;
+}
+#endif
+
 /*
  * Task first catches up with cfs_rq, and then subtract
  * itself from the cfs_rq (task must be off the queue now).
@@ -2818,41 +2930,20 @@
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
 	u64 last_update_time;
 
-#ifndef CONFIG_64BIT
-	u64 last_update_time_copy;
+	/*
+	 * Newly created task or never used group entity should not be removed
+	 * from its (source) cfs_rq
+	 */
+	if (se->avg.last_update_time == 0)
+		return;
 
-	do {
-		last_update_time_copy = cfs_rq->load_last_update_time_copy;
-		smp_rmb();
-		last_update_time = cfs_rq->avg.last_update_time;
-	} while (last_update_time != last_update_time_copy);
-#else
-	last_update_time = cfs_rq->avg.last_update_time;
-#endif
+	last_update_time = cfs_rq_last_update_time(cfs_rq);
 
 	__update_load_avg(last_update_time, cpu_of(rq_of(cfs_rq)), &se->avg, 0, 0, NULL);
 	atomic_long_add(se->avg.load_avg, &cfs_rq->removed_load_avg);
 	atomic_long_add(se->avg.util_avg, &cfs_rq->removed_util_avg);
 }
 
-/*
- * Update the rq's load with the elapsed running time before entering
- * idle. if the last scheduled task is not a CFS task, idle_enter will
- * be the only way to update the runnable statistic.
- */
-void idle_enter_fair(struct rq *this_rq)
-{
-}
-
-/*
- * Update the rq's load with the elapsed idle time before a task is
- * scheduled. if the newly scheduled task is not a CFS task, idle_exit will
- * be the only way to update the runnable statistic.
- */
-void idle_exit_fair(struct rq *this_rq)
-{
-}
-
 static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq)
 {
 	return cfs_rq->runnable_load_avg;
@@ -4240,42 +4331,37 @@
  */
 
 /*
- * The exact cpuload at various idx values, calculated at every tick would be
- * load = (2^idx - 1) / 2^idx * load + 1 / 2^idx * cur_load
+ * The exact cpuload calculated at every tick would be:
  *
- * If a cpu misses updates for n-1 ticks (as it was idle) and update gets called
- * on nth tick when cpu may be busy, then we have:
- * load = ((2^idx - 1) / 2^idx)^(n-1) * load
- * load = (2^idx - 1) / 2^idx) * load + 1 / 2^idx * cur_load
+ *   load' = (1 - 1/2^i) * load + (1/2^i) * cur_load
+ *
+ * If a cpu misses updates for n ticks (as it was idle) and update gets
+ * called on the n+1-th tick when cpu may be busy, then we have:
+ *
+ *   load_n   = (1 - 1/2^i)^n * load_0
+ *   load_n+1 = (1 - 1/2^i)   * load_n + (1/2^i) * cur_load
  *
  * decay_load_missed() below does efficient calculation of
- * load = ((2^idx - 1) / 2^idx)^(n-1) * load
- * avoiding 0..n-1 loop doing load = ((2^idx - 1) / 2^idx) * load
+ *
+ *   load' = (1 - 1/2^i)^n * load
+ *
+ * Because x^(n+m) := x^n * x^m we can decompose any x^n in power-of-2 factors.
+ * This allows us to precompute the above in said factors, thereby allowing the
+ * reduction of an arbitrary n in O(log_2 n) steps. (See also
+ * fixed_power_int())
  *
  * The calculation is approximated on a 128 point scale.
- * degrade_zero_ticks is the number of ticks after which load at any
- * particular idx is approximated to be zero.
- * degrade_factor is a precomputed table, a row for each load idx.
- * Each column corresponds to degradation factor for a power of two ticks,
- * based on 128 point scale.
- * Example:
- * row 2, col 3 (=12) says that the degradation at load idx 2 after
- * 8 ticks is 12/128 (which is an approximation of exact factor 3^8/4^8).
- *
- * With this power of 2 load factors, we can degrade the load n times
- * by looking at 1 bits in n and doing as many mult/shift instead of
- * n mult/shifts needed by the exact degradation.
  */
 #define DEGRADE_SHIFT		7
-static const unsigned char
-		degrade_zero_ticks[CPU_LOAD_IDX_MAX] = {0, 8, 32, 64, 128};
-static const unsigned char
-		degrade_factor[CPU_LOAD_IDX_MAX][DEGRADE_SHIFT + 1] = {
-					{0, 0, 0, 0, 0, 0, 0, 0},
-					{64, 32, 8, 0, 0, 0, 0, 0},
-					{96, 72, 40, 12, 1, 0, 0},
-					{112, 98, 75, 43, 15, 1, 0},
-					{120, 112, 98, 76, 45, 16, 2} };
+
+static const u8 degrade_zero_ticks[CPU_LOAD_IDX_MAX] = {0, 8, 32, 64, 128};
+static const u8 degrade_factor[CPU_LOAD_IDX_MAX][DEGRADE_SHIFT + 1] = {
+	{   0,   0,  0,  0,  0,  0, 0, 0 },
+	{  64,  32,  8,  0,  0,  0, 0, 0 },
+	{  96,  72, 40, 12,  1,  0, 0, 0 },
+	{ 112,  98, 75, 43, 15,  1, 0, 0 },
+	{ 120, 112, 98, 76, 45, 16, 2, 0 }
+};
 
 /*
  * Update cpu_load for any missed ticks, due to tickless idle. The backlog
@@ -4306,14 +4392,46 @@
 	return load;
 }
 
-/*
+/**
+ * __update_cpu_load - update the rq->cpu_load[] statistics
+ * @this_rq: The rq to update statistics for
+ * @this_load: The current load
+ * @pending_updates: The number of missed updates
+ * @active: !0 for NOHZ_FULL
+ *
  * Update rq->cpu_load[] statistics. This function is usually called every
- * scheduler tick (TICK_NSEC). With tickless idle this will not be called
- * every tick. We fix it up based on jiffies.
+ * scheduler tick (TICK_NSEC).
+ *
+ * This function computes a decaying average:
+ *
+ *   load[i]' = (1 - 1/2^i) * load[i] + (1/2^i) * load
+ *
+ * Because of NOHZ it might not get called on every tick which gives need for
+ * the @pending_updates argument.
+ *
+ *   load[i]_n = (1 - 1/2^i) * load[i]_n-1 + (1/2^i) * load_n-1
+ *             = A * load[i]_n-1 + B ; A := (1 - 1/2^i), B := (1/2^i) * load
+ *             = A * (A * load[i]_n-2 + B) + B
+ *             = A * (A * (A * load[i]_n-3 + B) + B) + B
+ *             = A^3 * load[i]_n-3 + (A^2 + A + 1) * B
+ *             = A^n * load[i]_0 + (A^(n-1) + A^(n-2) + ... + 1) * B
+ *             = A^n * load[i]_0 + ((1 - A^n) / (1 - A)) * B
+ *             = (1 - 1/2^i)^n * (load[i]_0 - load) + load
+ *
+ * In the above we've assumed load_n := load, which is true for NOHZ_FULL as
+ * any change in load would have resulted in the tick being turned back on.
+ *
+ * For regular NOHZ, this reduces to:
+ *
+ *   load[i]_n = (1 - 1/2^i)^n * load[i]_0
+ *
+ * see decay_load_misses(). For NOHZ_FULL we get to subtract and add the extra
+ * term. See the @active paramter.
  */
 static void __update_cpu_load(struct rq *this_rq, unsigned long this_load,
-			      unsigned long pending_updates)
+			      unsigned long pending_updates, int active)
 {
+	unsigned long tickless_load = active ? this_rq->cpu_load[0] : 0;
 	int i, scale;
 
 	this_rq->nr_load_updates++;
@@ -4325,8 +4443,9 @@
 
 		/* scale is effectively 1 << i now, and >> i divides by scale */
 
-		old_load = this_rq->cpu_load[i];
+		old_load = this_rq->cpu_load[i] - tickless_load;
 		old_load = decay_load_missed(old_load, pending_updates - 1, i);
+		old_load += tickless_load;
 		new_load = this_load;
 		/*
 		 * Round up the averaging division if load is increasing. This
@@ -4381,16 +4500,17 @@
 	pending_updates = curr_jiffies - this_rq->last_load_update_tick;
 	this_rq->last_load_update_tick = curr_jiffies;
 
-	__update_cpu_load(this_rq, load, pending_updates);
+	__update_cpu_load(this_rq, load, pending_updates, 0);
 }
 
 /*
  * Called from tick_nohz_idle_exit() -- try and fix up the ticks we missed.
  */
-void update_cpu_load_nohz(void)
+void update_cpu_load_nohz(int active)
 {
 	struct rq *this_rq = this_rq();
 	unsigned long curr_jiffies = READ_ONCE(jiffies);
+	unsigned long load = active ? weighted_cpuload(cpu_of(this_rq)) : 0;
 	unsigned long pending_updates;
 
 	if (curr_jiffies == this_rq->last_load_update_tick)
@@ -4401,10 +4521,11 @@
 	if (pending_updates) {
 		this_rq->last_load_update_tick = curr_jiffies;
 		/*
-		 * We were idle, this means load 0, the current load might be
-		 * !0 due to remote wakeups and the sort.
+		 * In the regular NOHZ case, we were idle, this means load 0.
+		 * In the NOHZ_FULL case, we were non-idle, we should consider
+		 * its weighted load.
 		 */
-		__update_cpu_load(this_rq, 0, pending_updates);
+		__update_cpu_load(this_rq, load, pending_updates, active);
 	}
 	raw_spin_unlock(&this_rq->lock);
 }
@@ -4420,7 +4541,7 @@
 	 * See the mess around update_idle_cpu_load() / update_cpu_load_nohz().
 	 */
 	this_rq->last_load_update_tick = jiffies;
-	__update_cpu_load(this_rq, load, 1);
+	__update_cpu_load(this_rq, load, 1, 1);
 }
 
 /*
@@ -5007,8 +5128,7 @@
 /*
  * Called immediately before a task is migrated to a new cpu; task_cpu(p) and
  * cfs_rq_of(p) references at time of call are still valid and identify the
- * previous cpu.  However, the caller only guarantees p->pi_lock is held; no
- * other assumptions, including the state of rq->lock, should be made.
+ * previous cpu. The caller guarantees p->pi_lock or task_rq(p)->lock is held.
  */
 static void migrate_task_rq_fair(struct task_struct *p)
 {
@@ -5721,8 +5841,8 @@
 {
 	lockdep_assert_held(&env->src_rq->lock);
 
-	deactivate_task(env->src_rq, p, 0);
 	p->on_rq = TASK_ON_RQ_MIGRATING;
+	deactivate_task(env->src_rq, p, 0);
 	set_task_cpu(p, env->dst_cpu);
 }
 
@@ -5855,8 +5975,8 @@
 	lockdep_assert_held(&rq->lock);
 
 	BUG_ON(task_rq(p) != rq);
-	p->on_rq = TASK_ON_RQ_QUEUED;
 	activate_task(rq, p, 0);
+	p->on_rq = TASK_ON_RQ_QUEUED;
 	check_preempt_curr(rq, p, 0);
 }
 
@@ -6302,7 +6422,7 @@
 			bool *overload)
 {
 	unsigned long load;
-	int i;
+	int i, nr_running;
 
 	memset(sgs, 0, sizeof(*sgs));
 
@@ -6319,7 +6439,8 @@
 		sgs->group_util += cpu_util(i);
 		sgs->sum_nr_running += rq->cfs.h_nr_running;
 
-		if (rq->nr_running > 1)
+		nr_running = rq->nr_running;
+		if (nr_running > 1)
 			*overload = true;
 
 #ifdef CONFIG_NUMA_BALANCING
@@ -6327,7 +6448,10 @@
 		sgs->nr_preferred_running += rq->nr_preferred_running;
 #endif
 		sgs->sum_weighted_load += weighted_cpuload(i);
-		if (idle_cpu(i))
+		/*
+		 * No need to call idle_cpu() if nr_running is not 0
+		 */
+		if (!nr_running && idle_cpu(i))
 			sgs->idle_cpus++;
 	}
 
@@ -7248,8 +7372,6 @@
 	int pulled_task = 0;
 	u64 curr_cost = 0;
 
-	idle_enter_fair(this_rq);
-
 	/*
 	 * We must set idle_stamp _before_ calling idle_balance(), such that we
 	 * measure the duration of idle_balance() as idle time.
@@ -7330,10 +7452,8 @@
 	if (this_rq->nr_running != this_rq->cfs.h_nr_running)
 		pulled_task = -1;
 
-	if (pulled_task) {
-		idle_exit_fair(this_rq);
+	if (pulled_task)
 		this_rq->idle_stamp = 0;
-	}
 
 	return pulled_task;
 }
diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c
index c4ae0f1..47ce9493 100644
--- a/kernel/sched/idle_task.c
+++ b/kernel/sched/idle_task.c
@@ -47,7 +47,6 @@
 
 static void put_prev_task_idle(struct rq *rq, struct task_struct *prev)
 {
-	idle_exit_fair(rq);
 	rq_last_tick_reset(rq);
 }
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b242775..10f1637 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -248,7 +248,12 @@
 	unsigned long shares;
 
 #ifdef	CONFIG_SMP
-	atomic_long_t load_avg;
+	/*
+	 * load_avg can be heavily contended at clock tick time, so put
+	 * it in its own cacheline separated from the fields above which
+	 * will also be accessed at each tick.
+	 */
+	atomic_long_t load_avg ____cacheline_aligned;
 #endif
 #endif
 
@@ -335,7 +340,15 @@
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);
-#endif
+
+#ifdef CONFIG_SMP
+extern void set_task_rq_fair(struct sched_entity *se,
+			     struct cfs_rq *prev, struct cfs_rq *next);
+#else /* !CONFIG_SMP */
+static inline void set_task_rq_fair(struct sched_entity *se,
+			     struct cfs_rq *prev, struct cfs_rq *next) { }
+#endif /* CONFIG_SMP */
+#endif /* CONFIG_FAIR_GROUP_SCHED */
 
 #else /* CONFIG_CGROUP_SCHED */
 
@@ -933,6 +946,7 @@
 #endif
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
+	set_task_rq_fair(&p->se, p->se.cfs_rq, tg->cfs_rq[cpu]);
 	p->se.cfs_rq = tg->cfs_rq[cpu];
 	p->se.parent = tg->se[cpu];
 #endif
@@ -1076,7 +1090,7 @@
 	 * In particular, the load of prev->state in finish_task_switch() must
 	 * happen before this.
 	 *
-	 * Pairs with the control dependency and rmb in try_to_wake_up().
+	 * Pairs with the smp_cond_acquire() in try_to_wake_up().
 	 */
 	smp_store_release(&prev->on_cpu, 0);
 #endif
@@ -1113,46 +1127,8 @@
 #define WEIGHT_IDLEPRIO                3
 #define WMULT_IDLEPRIO         1431655765
 
-/*
- * Nice levels are multiplicative, with a gentle 10% change for every
- * nice level changed. I.e. when a CPU-bound task goes from nice 0 to
- * nice 1, it will get ~10% less CPU time than another CPU-bound task
- * that remained on nice 0.
- *
- * The "10% effect" is relative and cumulative: from _any_ nice level,
- * if you go up 1 level, it's -10% CPU usage, if you go down 1 level
- * it's +10% CPU usage. (to achieve that we use a multiplier of 1.25.
- * If a task goes up by ~10% and another task goes down by ~10% then
- * the relative distance between them is ~25%.)
- */
-static const int prio_to_weight[40] = {
- /* -20 */     88761,     71755,     56483,     46273,     36291,
- /* -15 */     29154,     23254,     18705,     14949,     11916,
- /* -10 */      9548,      7620,      6100,      4904,      3906,
- /*  -5 */      3121,      2501,      1991,      1586,      1277,
- /*   0 */      1024,       820,       655,       526,       423,
- /*   5 */       335,       272,       215,       172,       137,
- /*  10 */       110,        87,        70,        56,        45,
- /*  15 */        36,        29,        23,        18,        15,
-};
-
-/*
- * Inverse (2^32/x) values of the prio_to_weight[] array, precalculated.
- *
- * In cases where the weight does not change often, we can use the
- * precalculated inverse to speed up arithmetics by turning divisions
- * into multiplications:
- */
-static const u32 prio_to_wmult[40] = {
- /* -20 */     48388,     59856,     76040,     92818,    118348,
- /* -15 */    147320,    184698,    229616,    287308,    360437,
- /* -10 */    449829,    563644,    704093,    875809,   1099582,
- /*  -5 */   1376151,   1717300,   2157191,   2708050,   3363326,
- /*   0 */   4194304,   5237765,   6557202,   8165337,  10153587,
- /*   5 */  12820798,  15790321,  19976592,  24970740,  31350126,
- /*  10 */  39045157,  49367440,  61356676,  76695844,  95443717,
- /*  15 */ 119304647, 148102320, 186737708, 238609294, 286331153,
-};
+extern const int sched_prio_to_weight[40];
+extern const u32 sched_prio_to_wmult[40];
 
 #define ENQUEUE_WAKEUP		0x01
 #define ENQUEUE_HEAD		0x02
@@ -1252,16 +1228,8 @@
 
 extern void trigger_load_balance(struct rq *rq);
 
-extern void idle_enter_fair(struct rq *this_rq);
-extern void idle_exit_fair(struct rq *this_rq);
-
 extern void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask);
 
-#else
-
-static inline void idle_enter_fair(struct rq *rq) { }
-static inline void idle_exit_fair(struct rq *rq) { }
-
 #endif
 
 #ifdef CONFIG_CPU_IDLE
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index a3bbaee..edb6de4 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -28,7 +28,6 @@
  */
 struct cpu_stop_done {
 	atomic_t		nr_todo;	/* nr left to execute */
-	bool			executed;	/* actually executed? */
 	int			ret;		/* collected return value */
 	struct completion	completion;	/* fired if nr_todo reaches 0 */
 };
@@ -63,14 +62,10 @@
 }
 
 /* signal completion unless @done is NULL */
-static void cpu_stop_signal_done(struct cpu_stop_done *done, bool executed)
+static void cpu_stop_signal_done(struct cpu_stop_done *done)
 {
-	if (done) {
-		if (executed)
-			done->executed = true;
-		if (atomic_dec_and_test(&done->nr_todo))
-			complete(&done->completion);
-	}
+	if (atomic_dec_and_test(&done->nr_todo))
+		complete(&done->completion);
 }
 
 static void __cpu_stop_queue_work(struct cpu_stopper *stopper,
@@ -81,17 +76,21 @@
 }
 
 /* queue @work to @stopper.  if offline, @work is completed immediately */
-static void cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work)
+static bool cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work)
 {
 	struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
 	unsigned long flags;
+	bool enabled;
 
 	spin_lock_irqsave(&stopper->lock, flags);
-	if (stopper->enabled)
+	enabled = stopper->enabled;
+	if (enabled)
 		__cpu_stop_queue_work(stopper, work);
-	else
-		cpu_stop_signal_done(work->done, false);
+	else if (work->done)
+		cpu_stop_signal_done(work->done);
 	spin_unlock_irqrestore(&stopper->lock, flags);
+
+	return enabled;
 }
 
 /**
@@ -124,9 +123,10 @@
 	struct cpu_stop_work work = { .fn = fn, .arg = arg, .done = &done };
 
 	cpu_stop_init_done(&done, 1);
-	cpu_stop_queue_work(cpu, &work);
+	if (!cpu_stop_queue_work(cpu, &work))
+		return -ENOENT;
 	wait_for_completion(&done.completion);
-	return done.executed ? done.ret : -ENOENT;
+	return done.ret;
 }
 
 /* This controls the threads on each CPU. */
@@ -258,7 +258,6 @@
 	struct cpu_stop_work work1, work2;
 	struct multi_stop_data msdata;
 
-	preempt_disable();
 	msdata = (struct multi_stop_data){
 		.fn = fn,
 		.data = arg,
@@ -277,16 +276,11 @@
 
 	if (cpu1 > cpu2)
 		swap(cpu1, cpu2);
-	if (cpu_stop_queue_two_works(cpu1, &work1, cpu2, &work2)) {
-		preempt_enable();
+	if (cpu_stop_queue_two_works(cpu1, &work1, cpu2, &work2))
 		return -ENOENT;
-	}
-
-	preempt_enable();
 
 	wait_for_completion(&done.completion);
-
-	return done.executed ? done.ret : -ENOENT;
+	return done.ret;
 }
 
 /**
@@ -302,23 +296,28 @@
  *
  * CONTEXT:
  * Don't care.
+ *
+ * RETURNS:
+ * true if cpu_stop_work was queued successfully and @fn will be called,
+ * false otherwise.
  */
-void stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg,
+bool stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg,
 			struct cpu_stop_work *work_buf)
 {
 	*work_buf = (struct cpu_stop_work){ .fn = fn, .arg = arg, };
-	cpu_stop_queue_work(cpu, work_buf);
+	return cpu_stop_queue_work(cpu, work_buf);
 }
 
 /* static data for stop_cpus */
 static DEFINE_MUTEX(stop_cpus_mutex);
 
-static void queue_stop_cpus_work(const struct cpumask *cpumask,
+static bool queue_stop_cpus_work(const struct cpumask *cpumask,
 				 cpu_stop_fn_t fn, void *arg,
 				 struct cpu_stop_done *done)
 {
 	struct cpu_stop_work *work;
 	unsigned int cpu;
+	bool queued = false;
 
 	/*
 	 * Disable preemption while queueing to avoid getting
@@ -331,9 +330,12 @@
 		work->fn = fn;
 		work->arg = arg;
 		work->done = done;
-		cpu_stop_queue_work(cpu, work);
+		if (cpu_stop_queue_work(cpu, work))
+			queued = true;
 	}
 	lg_global_unlock(&stop_cpus_lock);
+
+	return queued;
 }
 
 static int __stop_cpus(const struct cpumask *cpumask,
@@ -342,9 +344,10 @@
 	struct cpu_stop_done done;
 
 	cpu_stop_init_done(&done, cpumask_weight(cpumask));
-	queue_stop_cpus_work(cpumask, fn, arg, &done);
+	if (!queue_stop_cpus_work(cpumask, fn, arg, &done))
+		return -ENOENT;
 	wait_for_completion(&done.completion);
-	return done.executed ? done.ret : -ENOENT;
+	return done.ret;
 }
 
 /**
@@ -432,7 +435,6 @@
 {
 	struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
 	struct cpu_stop_work *work;
-	int ret;
 
 repeat:
 	work = NULL;
@@ -448,23 +450,19 @@
 		cpu_stop_fn_t fn = work->fn;
 		void *arg = work->arg;
 		struct cpu_stop_done *done = work->done;
-		char ksym_buf[KSYM_NAME_LEN] __maybe_unused;
+		int ret;
 
-		/* cpu stop callbacks are not allowed to sleep */
-		preempt_disable();
-
+		/* cpu stop callbacks must not sleep, make in_atomic() == T */
+		preempt_count_inc();
 		ret = fn(arg);
-		if (ret)
-			done->ret = ret;
-
-		/* restore preemption and check it's still balanced */
-		preempt_enable();
+		if (done) {
+			if (ret)
+				done->ret = ret;
+			cpu_stop_signal_done(done);
+		}
+		preempt_count_dec();
 		WARN_ONCE(preempt_count(),
-			  "cpu_stop: %s(%p) leaked preempt count\n",
-			  kallsyms_lookup((unsigned long)fn, NULL, NULL, NULL,
-					  ksym_buf), arg);
-
-		cpu_stop_signal_done(done, true);
+			  "cpu_stop: %pf(%p) leaked preempt count\n", fn, arg);
 		goto repeat;
 	}
 }
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 0623787..2c5e3a8 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -174,6 +174,7 @@
 cond_syscall(sys_setfsgid);
 cond_syscall(sys_capget);
 cond_syscall(sys_capset);
+cond_syscall(sys_copy_file_range);
 
 /* arch-specific weak syscall entries */
 cond_syscall(sys_pciconfig_read);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index dc6858d..5faf89a 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -2047,9 +2047,8 @@
 		  void *data)
 {
 	int *i, vleft, first = 1, err = 0;
-	unsigned long page = 0;
 	size_t left;
-	char *kbuf;
+	char *kbuf = NULL, *p;
 	
 	if (!tbl_data || !table->maxlen || !*lenp || (*ppos && !write)) {
 		*lenp = 0;
@@ -2078,15 +2077,9 @@
 
 		if (left > PAGE_SIZE - 1)
 			left = PAGE_SIZE - 1;
-		page = __get_free_page(GFP_TEMPORARY);
-		kbuf = (char *) page;
-		if (!kbuf)
-			return -ENOMEM;
-		if (copy_from_user(kbuf, buffer, left)) {
-			err = -EFAULT;
-			goto free;
-		}
-		kbuf[left] = 0;
+		p = kbuf = memdup_user_nul(buffer, left);
+		if (IS_ERR(kbuf))
+			return PTR_ERR(kbuf);
 	}
 
 	for (; left && vleft--; i++, first=0) {
@@ -2094,11 +2087,11 @@
 		bool neg;
 
 		if (write) {
-			left -= proc_skip_spaces(&kbuf);
+			left -= proc_skip_spaces(&p);
 
 			if (!left)
 				break;
-			err = proc_get_long(&kbuf, &left, &lval, &neg,
+			err = proc_get_long(&p, &left, &lval, &neg,
 					     proc_wspace_sep,
 					     sizeof(proc_wspace_sep), NULL);
 			if (err)
@@ -2125,10 +2118,9 @@
 	if (!write && !first && left && !err)
 		err = proc_put_char(&buffer, &left, '\n');
 	if (write && !err && left)
-		left -= proc_skip_spaces(&kbuf);
-free:
+		left -= proc_skip_spaces(&p);
 	if (write) {
-		free_page(page);
+		kfree(kbuf);
 		if (first)
 			return err ? : -EINVAL;
 	}
@@ -2310,9 +2302,8 @@
 {
 	unsigned long *i, *min, *max;
 	int vleft, first = 1, err = 0;
-	unsigned long page = 0;
 	size_t left;
-	char *kbuf;
+	char *kbuf = NULL, *p;
 
 	if (!data || !table->maxlen || !*lenp || (*ppos && !write)) {
 		*lenp = 0;
@@ -2340,15 +2331,9 @@
 
 		if (left > PAGE_SIZE - 1)
 			left = PAGE_SIZE - 1;
-		page = __get_free_page(GFP_TEMPORARY);
-		kbuf = (char *) page;
-		if (!kbuf)
-			return -ENOMEM;
-		if (copy_from_user(kbuf, buffer, left)) {
-			err = -EFAULT;
-			goto free;
-		}
-		kbuf[left] = 0;
+		p = kbuf = memdup_user_nul(buffer, left);
+		if (IS_ERR(kbuf))
+			return PTR_ERR(kbuf);
 	}
 
 	for (; left && vleft--; i++, first = 0) {
@@ -2357,9 +2342,9 @@
 		if (write) {
 			bool neg;
 
-			left -= proc_skip_spaces(&kbuf);
+			left -= proc_skip_spaces(&p);
 
-			err = proc_get_long(&kbuf, &left, &val, &neg,
+			err = proc_get_long(&p, &left, &val, &neg,
 					     proc_wspace_sep,
 					     sizeof(proc_wspace_sep), NULL);
 			if (err)
@@ -2385,10 +2370,9 @@
 	if (!write && !first && left && !err)
 		err = proc_put_char(&buffer, &left, '\n');
 	if (write && !err)
-		left -= proc_skip_spaces(&kbuf);
-free:
+		left -= proc_skip_spaces(&p);
 	if (write) {
-		free_page(page);
+		kfree(kbuf);
 		if (first)
 			return err ? : -EINVAL;
 	}
@@ -2650,34 +2634,27 @@
 	}
 
 	if (write) {
-		unsigned long page = 0;
-		char *kbuf;
+		char *kbuf, *p;
 
 		if (left > PAGE_SIZE - 1)
 			left = PAGE_SIZE - 1;
 
-		page = __get_free_page(GFP_TEMPORARY);
-		kbuf = (char *) page;
-		if (!kbuf)
-			return -ENOMEM;
-		if (copy_from_user(kbuf, buffer, left)) {
-			free_page(page);
-			return -EFAULT;
-                }
-		kbuf[left] = 0;
+		p = kbuf = memdup_user_nul(buffer, left);
+		if (IS_ERR(kbuf))
+			return PTR_ERR(kbuf);
 
 		tmp_bitmap = kzalloc(BITS_TO_LONGS(bitmap_len) * sizeof(unsigned long),
 				     GFP_KERNEL);
 		if (!tmp_bitmap) {
-			free_page(page);
+			kfree(kbuf);
 			return -ENOMEM;
 		}
-		proc_skip_char(&kbuf, &left, '\n');
+		proc_skip_char(&p, &left, '\n');
 		while (!err && left) {
 			unsigned long val_a, val_b;
 			bool neg;
 
-			err = proc_get_long(&kbuf, &left, &val_a, &neg, tr_a,
+			err = proc_get_long(&p, &left, &val_a, &neg, tr_a,
 					     sizeof(tr_a), &c);
 			if (err)
 				break;
@@ -2688,12 +2665,12 @@
 
 			val_b = val_a;
 			if (left) {
-				kbuf++;
+				p++;
 				left--;
 			}
 
 			if (c == '-') {
-				err = proc_get_long(&kbuf, &left, &val_b,
+				err = proc_get_long(&p, &left, &val_b,
 						     &neg, tr_b, sizeof(tr_b),
 						     &c);
 				if (err)
@@ -2704,16 +2681,16 @@
 					break;
 				}
 				if (left) {
-					kbuf++;
+					p++;
 					left--;
 				}
 			}
 
 			bitmap_set(tmp_bitmap, val_a, val_b - val_a + 1);
 			first = 0;
-			proc_skip_char(&kbuf, &left, '\n');
+			proc_skip_char(&p, &left, '\n');
 		}
-		free_page(page);
+		kfree(kbuf);
 	} else {
 		unsigned long bit_a, bit_b = 0;
 
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 7fbba63..e840ed8 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -271,11 +271,27 @@
 		__pm_wakeup_event(ws, MSEC_PER_SEC);
 	return ret;
 }
+
+static int alarmtimer_resume(struct device *dev)
+{
+	struct rtc_device *rtc;
+
+	rtc = alarmtimer_get_rtcdev();
+	if (rtc)
+		rtc_timer_cancel(rtc, &rtctimer);
+	return 0;
+}
+
 #else
 static int alarmtimer_suspend(struct device *dev)
 {
 	return 0;
 }
+
+static int alarmtimer_resume(struct device *dev)
+{
+	return 0;
+}
 #endif
 
 static void alarmtimer_freezerset(ktime_t absexp, enum alarmtimer_type type)
@@ -800,6 +816,7 @@
 /* Suspend hook structures */
 static const struct dev_pm_ops alarmtimer_pm_ops = {
 	.suspend = alarmtimer_suspend,
+	.resume = alarmtimer_resume,
 };
 
 static struct platform_driver alarmtimer_driver = {
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 1347882..664de53 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -218,8 +218,8 @@
 
 		/* Check the deviation from the watchdog clocksource. */
 		if (abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD) {
-			pr_warn("timekeeping watchdog: Marking clocksource '%s' as unstable because the skew is too large:\n",
-				cs->name);
+			pr_warn("timekeeping watchdog on CPU%d: Marking clocksource '%s' as unstable because the skew is too large:\n",
+				smp_processor_id(), cs->name);
 			pr_warn("                      '%s' wd_now: %llx wd_last: %llx mask: %llx\n",
 				watchdog->name, wdnow, wdlast, watchdog->mask);
 			pr_warn("                      '%s' cs_now: %llx cs_last: %llx mask: %llx\n",
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 149cc80..36f2ca0 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -16,8 +16,11 @@
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/rtc.h>
+#include <linux/math64.h>
 
 #include "ntp_internal.h"
+#include "timekeeping_internal.h"
+
 
 /*
  * NTP timekeeping variables:
@@ -70,7 +73,7 @@
 static s64			time_freq;
 
 /* time at last adjustment (secs):					*/
-static long			time_reftime;
+static time64_t		time_reftime;
 
 static long			time_adjust;
 
@@ -297,25 +300,27 @@
 	if (!(time_status & STA_PLL))
 		return;
 
-	if (!(time_status & STA_NANO))
+	if (!(time_status & STA_NANO)) {
+		/* Make sure the multiplication below won't overflow */
+		offset = clamp(offset, -USEC_PER_SEC, USEC_PER_SEC);
 		offset *= NSEC_PER_USEC;
+	}
 
 	/*
 	 * Scale the phase adjustment and
 	 * clamp to the operating range.
 	 */
-	offset = min(offset, MAXPHASE);
-	offset = max(offset, -MAXPHASE);
+	offset = clamp(offset, -MAXPHASE, MAXPHASE);
 
 	/*
 	 * Select how the frequency is to be controlled
 	 * and in which mode (PLL or FLL).
 	 */
-	secs = get_seconds() - time_reftime;
+	secs = (long)(__ktime_get_real_seconds() - time_reftime);
 	if (unlikely(time_status & STA_FREQHOLD))
 		secs = 0;
 
-	time_reftime = get_seconds();
+	time_reftime = __ktime_get_real_seconds();
 
 	offset64    = offset;
 	freq_adj    = ntp_update_offset_fll(offset64, secs);
@@ -390,10 +395,11 @@
  *
  * Also handles leap second processing, and returns leap offset
  */
-int second_overflow(unsigned long secs)
+int second_overflow(time64_t secs)
 {
 	s64 delta;
 	int leap = 0;
+	s32 rem;
 
 	/*
 	 * Leap second processing. If in leap-insert state at the end of the
@@ -404,19 +410,19 @@
 	case TIME_OK:
 		if (time_status & STA_INS) {
 			time_state = TIME_INS;
-			ntp_next_leap_sec = secs + SECS_PER_DAY -
-						(secs % SECS_PER_DAY);
+			div_s64_rem(secs, SECS_PER_DAY, &rem);
+			ntp_next_leap_sec = secs + SECS_PER_DAY - rem;
 		} else if (time_status & STA_DEL) {
 			time_state = TIME_DEL;
-			ntp_next_leap_sec = secs + SECS_PER_DAY -
-						 ((secs+1) % SECS_PER_DAY);
+			div_s64_rem(secs + 1, SECS_PER_DAY, &rem);
+			ntp_next_leap_sec = secs + SECS_PER_DAY - rem;
 		}
 		break;
 	case TIME_INS:
 		if (!(time_status & STA_INS)) {
 			ntp_next_leap_sec = TIME64_MAX;
 			time_state = TIME_OK;
-		} else if (secs % SECS_PER_DAY == 0) {
+		} else if (secs == ntp_next_leap_sec) {
 			leap = -1;
 			time_state = TIME_OOP;
 			printk(KERN_NOTICE
@@ -427,7 +433,7 @@
 		if (!(time_status & STA_DEL)) {
 			ntp_next_leap_sec = TIME64_MAX;
 			time_state = TIME_OK;
-		} else if ((secs + 1) % SECS_PER_DAY == 0) {
+		} else if (secs == ntp_next_leap_sec) {
 			leap = 1;
 			ntp_next_leap_sec = TIME64_MAX;
 			time_state = TIME_WAIT;
@@ -590,7 +596,7 @@
 	 * reference time to current time.
 	 */
 	if (!(time_status & STA_PLL) && (txc->status & STA_PLL))
-		time_reftime = get_seconds();
+		time_reftime = __ktime_get_real_seconds();
 
 	/* only set allowed bits */
 	time_status &= STA_RONLY;
@@ -674,8 +680,14 @@
 			return -EINVAL;
 	}
 
-	if ((txc->modes & ADJ_SETOFFSET) && (!capable(CAP_SYS_TIME)))
-		return -EPERM;
+	if (txc->modes & ADJ_SETOFFSET) {
+		/* In order to inject time, you gotta be super-user! */
+		if (!capable(CAP_SYS_TIME))
+			return -EPERM;
+
+		if (!timeval_inject_offset_valid(&txc->time))
+			return -EINVAL;
+	}
 
 	/*
 	 * Check for potential multiplication overflows that can
diff --git a/kernel/time/ntp_internal.h b/kernel/time/ntp_internal.h
index af92447..d8a7c11 100644
--- a/kernel/time/ntp_internal.h
+++ b/kernel/time/ntp_internal.h
@@ -6,7 +6,7 @@
 /* Returns how long ticks are at present, in ns / 2^NTP_SCALE_SHIFT. */
 extern u64 ntp_tick_length(void);
 extern ktime_t ntp_get_next_leap(void);
-extern int second_overflow(unsigned long secs);
+extern int second_overflow(time64_t secs);
 extern int ntp_validate_timex(struct timex *);
 extern int __do_adjtimex(struct timex *, struct timespec64 *, s32 *);
 extern void __hardpps(const struct timespec64 *, const struct timespec64 *);
diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c
index ce033c7..9cff0ab 100644
--- a/kernel/time/posix-clock.c
+++ b/kernel/time/posix-clock.c
@@ -69,10 +69,10 @@
 static unsigned int posix_clock_poll(struct file *fp, poll_table *wait)
 {
 	struct posix_clock *clk = get_posix_clock(fp);
-	int result = 0;
+	unsigned int result = 0;
 
 	if (!clk)
-		return -ENODEV;
+		return POLLERR;
 
 	if (clk->ops.poll)
 		result = clk->ops.poll(clk, fp, wait);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 7c7ec45..9cc20af 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -143,7 +143,7 @@
 	 * when we go busy again does not account too much ticks.
 	 */
 	if (ts->tick_stopped) {
-		touch_softlockup_watchdog();
+		touch_softlockup_watchdog_sched();
 		if (is_idle_task(current))
 			ts->idle_jiffies++;
 	}
@@ -430,7 +430,7 @@
 	tick_do_update_jiffies64(now);
 	local_irq_restore(flags);
 
-	touch_softlockup_watchdog();
+	touch_softlockup_watchdog_sched();
 }
 
 /*
@@ -603,15 +603,31 @@
 
 	/*
 	 * If the tick is due in the next period, keep it ticking or
-	 * restart it proper.
+	 * force prod the timer.
 	 */
 	delta = next_tick - basemono;
 	if (delta <= (u64)TICK_NSEC) {
 		tick.tv64 = 0;
+		/*
+		 * We've not stopped the tick yet, and there's a timer in the
+		 * next period, so no point in stopping it either, bail.
+		 */
 		if (!ts->tick_stopped)
 			goto out;
+
+		/*
+		 * If, OTOH, we did stop it, but there's a pending (expired)
+		 * timer reprogram the timer hardware to fire now.
+		 *
+		 * We will not restart the tick proper, just prod the timer
+		 * hardware into firing an interrupt to process the pending
+		 * timers. Just like tick_irq_exit() will not restart the tick
+		 * for 'normal' interrupts.
+		 *
+		 * Only once we exit the idle loop will we re-enable the tick,
+		 * see tick_nohz_idle_exit().
+		 */
 		if (delta == 0) {
-			/* Tick is stopped, but required now. Enforce it */
 			tick_nohz_restart(ts, now);
 			goto out;
 		}
@@ -694,14 +710,14 @@
 	return tick;
 }
 
-static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now)
+static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now, int active)
 {
 	/* Update jiffies first */
 	tick_do_update_jiffies64(now);
-	update_cpu_load_nohz();
+	update_cpu_load_nohz(active);
 
 	calc_load_exit_idle();
-	touch_softlockup_watchdog();
+	touch_softlockup_watchdog_sched();
 	/*
 	 * Cancel the scheduled timer and restore the tick
 	 */
@@ -725,7 +741,7 @@
 	if (can_stop_full_tick())
 		tick_nohz_stop_sched_tick(ts, ktime_get(), cpu);
 	else if (ts->tick_stopped)
-		tick_nohz_restart_sched_tick(ts, ktime_get());
+		tick_nohz_restart_sched_tick(ts, ktime_get(), 1);
 #endif
 }
 
@@ -875,7 +891,7 @@
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 	unsigned long ticks;
 
-	if (vtime_accounting_enabled())
+	if (vtime_accounting_cpu_enabled())
 		return;
 	/*
 	 * We stopped the tick in idle. Update process times would miss the
@@ -916,7 +932,7 @@
 		tick_nohz_stop_idle(ts, now);
 
 	if (ts->tick_stopped) {
-		tick_nohz_restart_sched_tick(ts, now);
+		tick_nohz_restart_sched_tick(ts, now, 0);
 		tick_nohz_account_idle_ticks(ts);
 	}
 
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index d563c19..34b4ced 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -305,8 +305,7 @@
 
 	delta = timekeeping_get_delta(tkr);
 
-	nsec = delta * tkr->mult + tkr->xtime_nsec;
-	nsec >>= tkr->shift;
+	nsec = (delta * tkr->mult + tkr->xtime_nsec) >> tkr->shift;
 
 	/* If arch requires, add in get_arch_timeoffset() */
 	return nsec + arch_gettimeoffset();
@@ -846,6 +845,19 @@
 }
 EXPORT_SYMBOL_GPL(ktime_get_real_seconds);
 
+/**
+ * __ktime_get_real_seconds - The same as ktime_get_real_seconds
+ * but without the sequence counter protect. This internal function
+ * is called just when timekeeping lock is already held.
+ */
+time64_t __ktime_get_real_seconds(void)
+{
+	struct timekeeper *tk = &tk_core.timekeeper;
+
+	return tk->xtime_sec;
+}
+
+
 #ifdef CONFIG_NTP_PPS
 
 /**
@@ -959,7 +971,7 @@
 	struct timespec64 ts64, tmp;
 	int ret = 0;
 
-	if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC)
+	if (!timespec_inject_offset_valid(ts))
 		return -EINVAL;
 
 	ts64 = timespec_to_timespec64(*ts);
@@ -1592,9 +1604,12 @@
 {
 	s64 interval = tk->cycle_interval;
 	s64 xinterval = tk->xtime_interval;
+	u32 base = tk->tkr_mono.clock->mult;
+	u32 max = tk->tkr_mono.clock->maxadj;
+	u32 cur_adj = tk->tkr_mono.mult;
 	s64 tick_error;
 	bool negative;
-	u32 adj;
+	u32 adj_scale;
 
 	/* Remove any current error adj from freq calculation */
 	if (tk->ntp_err_mult)
@@ -1613,13 +1628,33 @@
 	/* preserve the direction of correction */
 	negative = (tick_error < 0);
 
-	/* Sort out the magnitude of the correction */
+	/* If any adjustment would pass the max, just return */
+	if (negative && (cur_adj - 1) <= (base - max))
+		return;
+	if (!negative && (cur_adj + 1) >= (base + max))
+		return;
+	/*
+	 * Sort out the magnitude of the correction, but
+	 * avoid making so large a correction that we go
+	 * over the max adjustment.
+	 */
+	adj_scale = 0;
 	tick_error = abs(tick_error);
-	for (adj = 0; tick_error > interval; adj++)
+	while (tick_error > interval) {
+		u32 adj = 1 << (adj_scale + 1);
+
+		/* Check if adjustment gets us within 1 unit from the max */
+		if (negative && (cur_adj - adj) <= (base - max))
+			break;
+		if (!negative && (cur_adj + adj) >= (base + max))
+			break;
+
+		adj_scale++;
 		tick_error >>= 1;
+	}
 
 	/* scale the corrections */
-	timekeeping_apply_adjustment(tk, offset, negative, adj);
+	timekeeping_apply_adjustment(tk, offset, negative, adj_scale);
 }
 
 /*
diff --git a/kernel/time/timekeeping_internal.h b/kernel/time/timekeeping_internal.h
index 4ea005a..5be7627 100644
--- a/kernel/time/timekeeping_internal.h
+++ b/kernel/time/timekeeping_internal.h
@@ -17,7 +17,11 @@
 {
 	cycle_t ret = (now - last) & mask;
 
-	return (s64) ret > 0 ? ret : 0;
+	/*
+	 * Prevent time going backwards by checking the MSB of mask in
+	 * the result. If set, return 0.
+	 */
+	return ret & ~(mask >> 1) ? 0 : ret;
 }
 #else
 static inline cycle_t clocksource_delta(cycle_t now, cycle_t last, cycle_t mask)
@@ -26,4 +30,6 @@
 }
 #endif
 
+extern time64_t __ktime_get_real_seconds(void);
+
 #endif /* _TIMEKEEPING_INTERNAL_H */
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index a990824..2aeb6ff 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -349,16 +349,10 @@
 	if (count >= BLK_TN_MAX_MSG)
 		return -EINVAL;
 
-	msg = kmalloc(count + 1, GFP_KERNEL);
-	if (msg == NULL)
-		return -ENOMEM;
+	msg = memdup_user_nul(buffer, count);
+	if (IS_ERR(msg))
+		return PTR_ERR(msg);
 
-	if (copy_from_user(msg, buffer, count)) {
-		kfree(msg);
-		return -EFAULT;
-	}
-
-	msg[count] = '\0';
 	bt = filp->private_data;
 	__trace_note_message(bt, "%s", msg);
 	kfree(msg);
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 4f6ef69..f333e57 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1340,15 +1340,9 @@
 	if (cnt >= PAGE_SIZE)
 		return -EINVAL;
 
-	buf = (char *)__get_free_page(GFP_TEMPORARY);
-	if (!buf)
-		return -ENOMEM;
-
-	if (copy_from_user(buf, ubuf, cnt)) {
-		free_page((unsigned long) buf);
-		return -EFAULT;
-	}
-	buf[cnt] = '\0';
+	buf = memdup_user_nul(ubuf, cnt);
+	if (IS_ERR(buf))
+		return PTR_ERR(buf);
 
 	mutex_lock(&event_mutex);
 	file = event_file_data(filp);
@@ -1356,7 +1350,7 @@
 		err = apply_event_filter(file, buf);
 	mutex_unlock(&event_mutex);
 
-	free_page((unsigned long) buf);
+	kfree(buf);
 	if (err < 0)
 		return err;
 
@@ -1507,18 +1501,12 @@
 	if (cnt >= PAGE_SIZE)
 		return -EINVAL;
 
-	buf = (char *)__get_free_page(GFP_TEMPORARY);
-	if (!buf)
-		return -ENOMEM;
-
-	if (copy_from_user(buf, ubuf, cnt)) {
-		free_page((unsigned long) buf);
-		return -EFAULT;
-	}
-	buf[cnt] = '\0';
+	buf = memdup_user_nul(ubuf, cnt);
+	if (IS_ERR(buf))
+		return PTR_ERR(buf);
 
 	err = apply_subsystem_event_filter(dir, buf);
-	free_page((unsigned long) buf);
+	kfree(buf);
 	if (err < 0)
 		return err;
 
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 42a4009..4b5e8ed6 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -237,28 +237,23 @@
 	if (cnt >= PAGE_SIZE)
 		return -EINVAL;
 
-	buf = (char *)__get_free_page(GFP_TEMPORARY);
-	if (!buf)
-		return -ENOMEM;
+	buf = memdup_user_nul(ubuf, cnt);
+	if (IS_ERR(buf))
+		return PTR_ERR(buf);
 
-	if (copy_from_user(buf, ubuf, cnt)) {
-		free_page((unsigned long)buf);
-		return -EFAULT;
-	}
-	buf[cnt] = '\0';
 	strim(buf);
 
 	mutex_lock(&event_mutex);
 	event_file = event_file_data(file);
 	if (unlikely(!event_file)) {
 		mutex_unlock(&event_mutex);
-		free_page((unsigned long)buf);
+		kfree(buf);
 		return -ENODEV;
 	}
 	ret = trigger_process_regex(event_file, buf);
 	mutex_unlock(&event_mutex);
 
-	free_page((unsigned long)buf);
+	kfree(buf);
 	if (ret < 0)
 		goto out;
 
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 88fefa6..9bafc21 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -602,8 +602,7 @@
 	struct uid_gid_map new_map;
 	unsigned idx;
 	struct uid_gid_extent *extent = NULL;
-	unsigned long page = 0;
-	char *kbuf, *pos, *next_line;
+	char *kbuf = NULL, *pos, *next_line;
 	ssize_t ret = -EINVAL;
 
 	/*
@@ -638,23 +637,18 @@
 	if (cap_valid(cap_setid) && !file_ns_capable(file, ns, CAP_SYS_ADMIN))
 		goto out;
 
-	/* Get a buffer */
-	ret = -ENOMEM;
-	page = __get_free_page(GFP_TEMPORARY);
-	kbuf = (char *) page;
-	if (!page)
-		goto out;
-
 	/* Only allow < page size writes at the beginning of the file */
 	ret = -EINVAL;
 	if ((*ppos != 0) || (count >= PAGE_SIZE))
 		goto out;
 
 	/* Slurp in the user data */
-	ret = -EFAULT;
-	if (copy_from_user(kbuf, buf, count))
+	kbuf = memdup_user_nul(buf, count);
+	if (IS_ERR(kbuf)) {
+		ret = PTR_ERR(kbuf);
+		kbuf = NULL;
 		goto out;
-	kbuf[count] = '\0';
+	}
 
 	/* Parse the user data */
 	ret = -EINVAL;
@@ -756,8 +750,7 @@
 	ret = count;
 out:
 	mutex_unlock(&userns_state_mutex);
-	if (page)
-		free_page(page);
+	kfree(kbuf);
 	return ret;
 }
 
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 18f34cf..b3ace6e 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -20,6 +20,7 @@
 #include <linux/smpboot.h>
 #include <linux/sched/rt.h>
 #include <linux/tick.h>
+#include <linux/workqueue.h>
 
 #include <asm/irq_regs.h>
 #include <linux/kvm_para.h>
@@ -225,7 +226,15 @@
 	__this_cpu_write(watchdog_touch_ts, get_timestamp());
 }
 
-void touch_softlockup_watchdog(void)
+/**
+ * touch_softlockup_watchdog_sched - touch watchdog on scheduler stalls
+ *
+ * Call when the scheduler may have stalled for legitimate reasons
+ * preventing the watchdog task from executing - e.g. the scheduler
+ * entering idle state.  This should only be used for scheduler events.
+ * Use touch_softlockup_watchdog() for everything else.
+ */
+void touch_softlockup_watchdog_sched(void)
 {
 	/*
 	 * Preemption can be enabled.  It doesn't matter which CPU's timestamp
@@ -233,6 +242,12 @@
 	 */
 	raw_cpu_write(watchdog_touch_ts, 0);
 }
+
+void touch_softlockup_watchdog(void)
+{
+	touch_softlockup_watchdog_sched();
+	wq_watchdog_touch(raw_smp_processor_id());
+}
 EXPORT_SYMBOL(touch_softlockup_watchdog);
 
 void touch_all_softlockup_watchdogs(void)
@@ -246,6 +261,7 @@
 	 */
 	for_each_watchdog_cpu(cpu)
 		per_cpu(watchdog_touch_ts, cpu) = 0;
+	wq_watchdog_touch(-1);
 }
 
 #ifdef CONFIG_HARDLOCKUP_DETECTOR
@@ -351,7 +367,7 @@
 			trigger_allbutself_cpu_backtrace();
 
 		if (hardlockup_panic)
-			panic("Hard LOCKUP");
+			nmi_panic(regs, "Hard LOCKUP");
 
 		__this_cpu_write(hard_watchdog_warn, true);
 		return;
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index c579dba..61a0264 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -148,6 +148,8 @@
 	int			id;		/* I: pool ID */
 	unsigned int		flags;		/* X: flags */
 
+	unsigned long		watchdog_ts;	/* L: watchdog timestamp */
+
 	struct list_head	worklist;	/* L: list of pending works */
 	int			nr_workers;	/* L: total number of workers */
 
@@ -1083,6 +1085,8 @@
 	struct pool_workqueue *pwq = get_work_pwq(work);
 
 	trace_workqueue_activate_work(work);
+	if (list_empty(&pwq->pool->worklist))
+		pwq->pool->watchdog_ts = jiffies;
 	move_linked_works(work, &pwq->pool->worklist, NULL);
 	__clear_bit(WORK_STRUCT_DELAYED_BIT, work_data_bits(work));
 	pwq->nr_active++;
@@ -1385,6 +1389,8 @@
 		trace_workqueue_activate_work(work);
 		pwq->nr_active++;
 		worklist = &pwq->pool->worklist;
+		if (list_empty(worklist))
+			pwq->pool->watchdog_ts = jiffies;
 	} else {
 		work_flags |= WORK_STRUCT_DELAYED;
 		worklist = &pwq->delayed_works;
@@ -2157,6 +2163,8 @@
 			list_first_entry(&pool->worklist,
 					 struct work_struct, entry);
 
+		pool->watchdog_ts = jiffies;
+
 		if (likely(!(*work_data_bits(work) & WORK_STRUCT_LINKED))) {
 			/* optimization path, not strictly necessary */
 			process_one_work(worker, work);
@@ -2240,6 +2248,7 @@
 					struct pool_workqueue, mayday_node);
 		struct worker_pool *pool = pwq->pool;
 		struct work_struct *work, *n;
+		bool first = true;
 
 		__set_current_state(TASK_RUNNING);
 		list_del_init(&pwq->mayday_node);
@@ -2256,9 +2265,14 @@
 		 * process'em.
 		 */
 		WARN_ON_ONCE(!list_empty(scheduled));
-		list_for_each_entry_safe(work, n, &pool->worklist, entry)
-			if (get_work_pwq(work) == pwq)
+		list_for_each_entry_safe(work, n, &pool->worklist, entry) {
+			if (get_work_pwq(work) == pwq) {
+				if (first)
+					pool->watchdog_ts = jiffies;
 				move_linked_works(work, scheduled, &n);
+			}
+			first = false;
+		}
 
 		if (!list_empty(scheduled)) {
 			process_scheduled_works(rescuer);
@@ -2316,6 +2330,37 @@
 	goto repeat;
 }
 
+/**
+ * check_flush_dependency - check for flush dependency sanity
+ * @target_wq: workqueue being flushed
+ * @target_work: work item being flushed (NULL for workqueue flushes)
+ *
+ * %current is trying to flush the whole @target_wq or @target_work on it.
+ * If @target_wq doesn't have %WQ_MEM_RECLAIM, verify that %current is not
+ * reclaiming memory or running on a workqueue which doesn't have
+ * %WQ_MEM_RECLAIM as that can break forward-progress guarantee leading to
+ * a deadlock.
+ */
+static void check_flush_dependency(struct workqueue_struct *target_wq,
+				   struct work_struct *target_work)
+{
+	work_func_t target_func = target_work ? target_work->func : NULL;
+	struct worker *worker;
+
+	if (target_wq->flags & WQ_MEM_RECLAIM)
+		return;
+
+	worker = current_wq_worker();
+
+	WARN_ONCE(current->flags & PF_MEMALLOC,
+		  "workqueue: PF_MEMALLOC task %d(%s) is flushing !WQ_MEM_RECLAIM %s:%pf",
+		  current->pid, current->comm, target_wq->name, target_func);
+	WARN_ONCE(worker && (worker->current_pwq->wq->flags & WQ_MEM_RECLAIM),
+		  "workqueue: WQ_MEM_RECLAIM %s:%pf is flushing !WQ_MEM_RECLAIM %s:%pf",
+		  worker->current_pwq->wq->name, worker->current_func,
+		  target_wq->name, target_func);
+}
+
 struct wq_barrier {
 	struct work_struct	work;
 	struct completion	done;
@@ -2525,6 +2570,8 @@
 		list_add_tail(&this_flusher.list, &wq->flusher_overflow);
 	}
 
+	check_flush_dependency(wq, NULL);
+
 	mutex_unlock(&wq->mutex);
 
 	wait_for_completion(&this_flusher.done);
@@ -2697,6 +2744,8 @@
 		pwq = worker->current_pwq;
 	}
 
+	check_flush_dependency(pwq->wq, work);
+
 	insert_wq_barrier(pwq, barr, work, worker);
 	spin_unlock_irq(&pool->lock);
 
@@ -3069,6 +3118,7 @@
 	pool->cpu = -1;
 	pool->node = NUMA_NO_NODE;
 	pool->flags |= POOL_DISASSOCIATED;
+	pool->watchdog_ts = jiffies;
 	INIT_LIST_HEAD(&pool->worklist);
 	INIT_LIST_HEAD(&pool->idle_list);
 	hash_init(pool->busy_hash);
@@ -3601,7 +3651,6 @@
 					const struct workqueue_attrs *attrs)
 {
 	struct apply_wqattrs_ctx *ctx;
-	int ret = -ENOMEM;
 
 	/* only unbound workqueues can change attributes */
 	if (WARN_ON(!(wq->flags & WQ_UNBOUND)))
@@ -3612,16 +3661,14 @@
 		return -EINVAL;
 
 	ctx = apply_wqattrs_prepare(wq, attrs);
+	if (!ctx)
+		return -ENOMEM;
 
 	/* the ctx has been prepared successfully, let's commit it */
-	if (ctx) {
-		apply_wqattrs_commit(ctx);
-		ret = 0;
-	}
-
+	apply_wqattrs_commit(ctx);
 	apply_wqattrs_cleanup(ctx);
 
-	return ret;
+	return 0;
 }
 
 /**
@@ -4308,7 +4355,9 @@
 
 		pr_info("pool %d:", pool->id);
 		pr_cont_pool_info(pool);
-		pr_cont(" workers=%d", pool->nr_workers);
+		pr_cont(" hung=%us workers=%d",
+			jiffies_to_msecs(jiffies - pool->watchdog_ts) / 1000,
+			pool->nr_workers);
 		if (pool->manager)
 			pr_cont(" manager: %d",
 				task_pid_nr(pool->manager->task));
@@ -5167,6 +5216,154 @@
 static void workqueue_sysfs_unregister(struct workqueue_struct *wq)	{ }
 #endif	/* CONFIG_SYSFS */
 
+/*
+ * Workqueue watchdog.
+ *
+ * Stall may be caused by various bugs - missing WQ_MEM_RECLAIM, illegal
+ * flush dependency, a concurrency managed work item which stays RUNNING
+ * indefinitely.  Workqueue stalls can be very difficult to debug as the
+ * usual warning mechanisms don't trigger and internal workqueue state is
+ * largely opaque.
+ *
+ * Workqueue watchdog monitors all worker pools periodically and dumps
+ * state if some pools failed to make forward progress for a while where
+ * forward progress is defined as the first item on ->worklist changing.
+ *
+ * This mechanism is controlled through the kernel parameter
+ * "workqueue.watchdog_thresh" which can be updated at runtime through the
+ * corresponding sysfs parameter file.
+ */
+#ifdef CONFIG_WQ_WATCHDOG
+
+static void wq_watchdog_timer_fn(unsigned long data);
+
+static unsigned long wq_watchdog_thresh = 30;
+static struct timer_list wq_watchdog_timer =
+	TIMER_DEFERRED_INITIALIZER(wq_watchdog_timer_fn, 0, 0);
+
+static unsigned long wq_watchdog_touched = INITIAL_JIFFIES;
+static DEFINE_PER_CPU(unsigned long, wq_watchdog_touched_cpu) = INITIAL_JIFFIES;
+
+static void wq_watchdog_reset_touched(void)
+{
+	int cpu;
+
+	wq_watchdog_touched = jiffies;
+	for_each_possible_cpu(cpu)
+		per_cpu(wq_watchdog_touched_cpu, cpu) = jiffies;
+}
+
+static void wq_watchdog_timer_fn(unsigned long data)
+{
+	unsigned long thresh = READ_ONCE(wq_watchdog_thresh) * HZ;
+	bool lockup_detected = false;
+	struct worker_pool *pool;
+	int pi;
+
+	if (!thresh)
+		return;
+
+	rcu_read_lock();
+
+	for_each_pool(pool, pi) {
+		unsigned long pool_ts, touched, ts;
+
+		if (list_empty(&pool->worklist))
+			continue;
+
+		/* get the latest of pool and touched timestamps */
+		pool_ts = READ_ONCE(pool->watchdog_ts);
+		touched = READ_ONCE(wq_watchdog_touched);
+
+		if (time_after(pool_ts, touched))
+			ts = pool_ts;
+		else
+			ts = touched;
+
+		if (pool->cpu >= 0) {
+			unsigned long cpu_touched =
+				READ_ONCE(per_cpu(wq_watchdog_touched_cpu,
+						  pool->cpu));
+			if (time_after(cpu_touched, ts))
+				ts = cpu_touched;
+		}
+
+		/* did we stall? */
+		if (time_after(jiffies, ts + thresh)) {
+			lockup_detected = true;
+			pr_emerg("BUG: workqueue lockup - pool");
+			pr_cont_pool_info(pool);
+			pr_cont(" stuck for %us!\n",
+				jiffies_to_msecs(jiffies - pool_ts) / 1000);
+		}
+	}
+
+	rcu_read_unlock();
+
+	if (lockup_detected)
+		show_workqueue_state();
+
+	wq_watchdog_reset_touched();
+	mod_timer(&wq_watchdog_timer, jiffies + thresh);
+}
+
+void wq_watchdog_touch(int cpu)
+{
+	if (cpu >= 0)
+		per_cpu(wq_watchdog_touched_cpu, cpu) = jiffies;
+	else
+		wq_watchdog_touched = jiffies;
+}
+
+static void wq_watchdog_set_thresh(unsigned long thresh)
+{
+	wq_watchdog_thresh = 0;
+	del_timer_sync(&wq_watchdog_timer);
+
+	if (thresh) {
+		wq_watchdog_thresh = thresh;
+		wq_watchdog_reset_touched();
+		mod_timer(&wq_watchdog_timer, jiffies + thresh * HZ);
+	}
+}
+
+static int wq_watchdog_param_set_thresh(const char *val,
+					const struct kernel_param *kp)
+{
+	unsigned long thresh;
+	int ret;
+
+	ret = kstrtoul(val, 0, &thresh);
+	if (ret)
+		return ret;
+
+	if (system_wq)
+		wq_watchdog_set_thresh(thresh);
+	else
+		wq_watchdog_thresh = thresh;
+
+	return 0;
+}
+
+static const struct kernel_param_ops wq_watchdog_thresh_ops = {
+	.set	= wq_watchdog_param_set_thresh,
+	.get	= param_get_ulong,
+};
+
+module_param_cb(watchdog_thresh, &wq_watchdog_thresh_ops, &wq_watchdog_thresh,
+		0644);
+
+static void wq_watchdog_init(void)
+{
+	wq_watchdog_set_thresh(wq_watchdog_thresh);
+}
+
+#else	/* CONFIG_WQ_WATCHDOG */
+
+static inline void wq_watchdog_init(void) { }
+
+#endif	/* CONFIG_WQ_WATCHDOG */
+
 static void __init wq_numa_init(void)
 {
 	cpumask_var_t *tbl;
@@ -5290,6 +5487,9 @@
 	       !system_unbound_wq || !system_freezable_wq ||
 	       !system_power_efficient_wq ||
 	       !system_freezable_power_efficient_wq);
+
+	wq_watchdog_init();
+
 	return 0;
 }
 early_initcall(init_workqueues);
diff --git a/lib/842/842_decompress.c b/lib/842/842_decompress.c
index 8881dad2..a7f278d 100644
--- a/lib/842/842_decompress.c
+++ b/lib/842/842_decompress.c
@@ -69,7 +69,7 @@
 	((s) == 2 ? be16_to_cpu(get_unaligned((__be16 *)d)) :	\
 	 (s) == 4 ? be32_to_cpu(get_unaligned((__be32 *)d)) :	\
 	 (s) == 8 ? be64_to_cpu(get_unaligned((__be64 *)d)) :	\
-	 WARN(1, "pr_debug param err invalid size %x\n", s))
+	 0)
 
 static int next_bits(struct sw842_param *p, u64 *d, u8 n);
 
@@ -202,10 +202,14 @@
 		return -EINVAL;
 	}
 
-	pr_debug("index%x to %lx off %lx adjoff %lx tot %lx data %lx\n",
-		 size, (unsigned long)index, (unsigned long)(index * size),
-		 (unsigned long)offset, (unsigned long)total,
-		 (unsigned long)beN_to_cpu(&p->ostart[offset], size));
+	if (size != 2 && size != 4 && size != 8)
+		WARN(1, "__do_index invalid size %x\n", size);
+	else
+		pr_debug("index%x to %lx off %lx adjoff %lx tot %lx data %lx\n",
+			 size, (unsigned long)index,
+			 (unsigned long)(index * size), (unsigned long)offset,
+			 (unsigned long)total,
+			 (unsigned long)beN_to_cpu(&p->ostart[offset], size));
 
 	memcpy(p->out, &p->ostart[offset], size);
 	p->out += size;
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 0d76ecc..e2a236a 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -812,6 +812,17 @@
 	default 0 if !BOOTPARAM_HUNG_TASK_PANIC
 	default 1 if BOOTPARAM_HUNG_TASK_PANIC
 
+config WQ_WATCHDOG
+	bool "Detect Workqueue Stalls"
+	depends on DEBUG_KERNEL
+	help
+	  Say Y here to enable stall detection on workqueues.  If a
+	  worker pool doesn't make forward progress on a pending work
+	  item for over a given amount of time, 30s by default, a
+	  warning message is printed along with dump of workqueue
+	  state.  This can be configured through kernel parameter
+	  "workqueue.watchdog_thresh" and its sysfs counterpart.
+
 endmenu # "Debug lockups and hangs"
 
 config PANIC_ON_OOPS
@@ -1546,8 +1557,7 @@
 
 config FAIL_MMC_REQUEST
 	bool "Fault-injection capability for MMC IO"
-	select DEBUG_FS
-	depends on FAULT_INJECTION && MMC
+	depends on FAULT_INJECTION_DEBUG_FS && MMC
 	help
 	  Provide fault-injection capability for MMC IO.
 	  This will make the mmc core return data errors. This is
diff --git a/lib/atomic64_test.c b/lib/atomic64_test.c
index 83c33a5b..d62de8b 100644
--- a/lib/atomic64_test.c
+++ b/lib/atomic64_test.c
@@ -16,6 +16,10 @@
 #include <linux/kernel.h>
 #include <linux/atomic.h>
 
+#ifdef CONFIG_X86
+#include <asm/processor.h>	/* for boot_cpu_has below */
+#endif
+
 #define TEST(bit, op, c_op, val)				\
 do {								\
 	atomic##bit##_set(&v, v0);				\
@@ -27,6 +31,65 @@
 		(unsigned long long)r);				\
 } while (0)
 
+/*
+ * Test for a atomic operation family,
+ * @test should be a macro accepting parameters (bit, op, ...)
+ */
+
+#define FAMILY_TEST(test, bit, op, args...)	\
+do {						\
+	test(bit, op, ##args);		\
+	test(bit, op##_acquire, ##args);	\
+	test(bit, op##_release, ##args);	\
+	test(bit, op##_relaxed, ##args);	\
+} while (0)
+
+#define TEST_RETURN(bit, op, c_op, val)				\
+do {								\
+	atomic##bit##_set(&v, v0);				\
+	r = v0;							\
+	r c_op val;						\
+	BUG_ON(atomic##bit##_##op(val, &v) != r);		\
+	BUG_ON(atomic##bit##_read(&v) != r);			\
+} while (0)
+
+#define RETURN_FAMILY_TEST(bit, op, c_op, val)			\
+do {								\
+	FAMILY_TEST(TEST_RETURN, bit, op, c_op, val);		\
+} while (0)
+
+#define TEST_ARGS(bit, op, init, ret, expect, args...)		\
+do {								\
+	atomic##bit##_set(&v, init);				\
+	BUG_ON(atomic##bit##_##op(&v, ##args) != ret);		\
+	BUG_ON(atomic##bit##_read(&v) != expect);		\
+} while (0)
+
+#define XCHG_FAMILY_TEST(bit, init, new)				\
+do {									\
+	FAMILY_TEST(TEST_ARGS, bit, xchg, init, init, new, new);	\
+} while (0)
+
+#define CMPXCHG_FAMILY_TEST(bit, init, new, wrong)			\
+do {									\
+	FAMILY_TEST(TEST_ARGS, bit, cmpxchg, 				\
+			init, init, new, init, new);			\
+	FAMILY_TEST(TEST_ARGS, bit, cmpxchg,				\
+			init, init, init, wrong, new);			\
+} while (0)
+
+#define INC_RETURN_FAMILY_TEST(bit, i)			\
+do {							\
+	FAMILY_TEST(TEST_ARGS, bit, inc_return,		\
+			i, (i) + one, (i) + one);	\
+} while (0)
+
+#define DEC_RETURN_FAMILY_TEST(bit, i)			\
+do {							\
+	FAMILY_TEST(TEST_ARGS, bit, dec_return,		\
+			i, (i) - one, (i) - one);	\
+} while (0)
+
 static __init void test_atomic(void)
 {
 	int v0 = 0xaaa31337;
@@ -45,6 +108,18 @@
 	TEST(, and, &=, v1);
 	TEST(, xor, ^=, v1);
 	TEST(, andnot, &= ~, v1);
+
+	RETURN_FAMILY_TEST(, add_return, +=, onestwos);
+	RETURN_FAMILY_TEST(, add_return, +=, -one);
+	RETURN_FAMILY_TEST(, sub_return, -=, onestwos);
+	RETURN_FAMILY_TEST(, sub_return, -=, -one);
+
+	INC_RETURN_FAMILY_TEST(, v0);
+	DEC_RETURN_FAMILY_TEST(, v0);
+
+	XCHG_FAMILY_TEST(, v0, v1);
+	CMPXCHG_FAMILY_TEST(, v0, v1, onestwos);
+
 }
 
 #define INIT(c) do { atomic64_set(&v, c); r = c; } while (0)
@@ -74,25 +149,10 @@
 	TEST(64, xor, ^=, v1);
 	TEST(64, andnot, &= ~, v1);
 
-	INIT(v0);
-	r += onestwos;
-	BUG_ON(atomic64_add_return(onestwos, &v) != r);
-	BUG_ON(v.counter != r);
-
-	INIT(v0);
-	r += -one;
-	BUG_ON(atomic64_add_return(-one, &v) != r);
-	BUG_ON(v.counter != r);
-
-	INIT(v0);
-	r -= onestwos;
-	BUG_ON(atomic64_sub_return(onestwos, &v) != r);
-	BUG_ON(v.counter != r);
-
-	INIT(v0);
-	r -= -one;
-	BUG_ON(atomic64_sub_return(-one, &v) != r);
-	BUG_ON(v.counter != r);
+	RETURN_FAMILY_TEST(64, add_return, +=, onestwos);
+	RETURN_FAMILY_TEST(64, add_return, +=, -one);
+	RETURN_FAMILY_TEST(64, sub_return, -=, onestwos);
+	RETURN_FAMILY_TEST(64, sub_return, -=, -one);
 
 	INIT(v0);
 	atomic64_inc(&v);
@@ -100,33 +160,15 @@
 	BUG_ON(v.counter != r);
 
 	INIT(v0);
-	r += one;
-	BUG_ON(atomic64_inc_return(&v) != r);
-	BUG_ON(v.counter != r);
-
-	INIT(v0);
 	atomic64_dec(&v);
 	r -= one;
 	BUG_ON(v.counter != r);
 
-	INIT(v0);
-	r -= one;
-	BUG_ON(atomic64_dec_return(&v) != r);
-	BUG_ON(v.counter != r);
+	INC_RETURN_FAMILY_TEST(64, v0);
+	DEC_RETURN_FAMILY_TEST(64, v0);
 
-	INIT(v0);
-	BUG_ON(atomic64_xchg(&v, v1) != v0);
-	r = v1;
-	BUG_ON(v.counter != r);
-
-	INIT(v0);
-	BUG_ON(atomic64_cmpxchg(&v, v0, v1) != v0);
-	r = v1;
-	BUG_ON(v.counter != r);
-
-	INIT(v0);
-	BUG_ON(atomic64_cmpxchg(&v, v2, v1) != v0);
-	BUG_ON(v.counter != r);
+	XCHG_FAMILY_TEST(64, v0, v1);
+	CMPXCHG_FAMILY_TEST(64, v0, v1, v2);
 
 	INIT(v0);
 	BUG_ON(atomic64_add_unless(&v, one, v0));
diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c
index e3952e9c..fe42b6e 100644
--- a/lib/dynamic_debug.c
+++ b/lib/dynamic_debug.c
@@ -657,14 +657,9 @@
 		pr_warn("expected <%d bytes into control\n", USER_BUF_PAGE);
 		return -E2BIG;
 	}
-	tmpbuf = kmalloc(len + 1, GFP_KERNEL);
-	if (!tmpbuf)
-		return -ENOMEM;
-	if (copy_from_user(tmpbuf, ubuf, len)) {
-		kfree(tmpbuf);
-		return -EFAULT;
-	}
-	tmpbuf[len] = '\0';
+	tmpbuf = memdup_user_nul(ubuf, len);
+	if (IS_ERR(tmpbuf))
+		return PTR_ERR(tmpbuf);
 	vpr_info("read %d bytes from userspace\n", (int)len);
 
 	ret = ddebug_exec_queries(tmpbuf, NULL);
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 75232ad..5fecddc 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -369,7 +369,7 @@
 	kunmap_atomic(from);
 }
 
-static void memcpy_to_page(struct page *page, size_t offset, char *from, size_t len)
+static void memcpy_to_page(struct page *page, size_t offset, const char *from, size_t len)
 {
 	char *to = kmap_atomic(page);
 	memcpy(to + offset, from, len);
@@ -383,9 +383,9 @@
 	kunmap_atomic(addr);
 }
 
-size_t copy_to_iter(void *addr, size_t bytes, struct iov_iter *i)
+size_t copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
 {
-	char *from = addr;
+	const char *from = addr;
 	if (unlikely(bytes > i->count))
 		bytes = i->count;
 
@@ -704,10 +704,10 @@
 }
 EXPORT_SYMBOL(csum_and_copy_from_iter);
 
-size_t csum_and_copy_to_iter(void *addr, size_t bytes, __wsum *csum,
+size_t csum_and_copy_to_iter(const void *addr, size_t bytes, __wsum *csum,
 			     struct iov_iter *i)
 {
-	char *from = addr;
+	const char *from = addr;
 	__wsum sum, next;
 	size_t off = 0;
 	if (unlikely(bytes > i->count))
@@ -849,3 +849,4 @@
 	iov_iter_init(i, rw, iov, 1, len);
 	return 0;
 }
+EXPORT_SYMBOL(import_single_range);
diff --git a/lib/list_debug.c b/lib/list_debug.c
index c24c2f7..3859bf6 100644
--- a/lib/list_debug.c
+++ b/lib/list_debug.c
@@ -37,7 +37,7 @@
 	next->prev = new;
 	new->next = next;
 	new->prev = prev;
-	prev->next = new;
+	WRITE_ONCE(prev->next, new);
 }
 EXPORT_SYMBOL(__list_add);
 
diff --git a/lib/mpi/mpicoder.c b/lib/mpi/mpicoder.c
index 3db76b8..ec533a6 100644
--- a/lib/mpi/mpicoder.c
+++ b/lib/mpi/mpicoder.c
@@ -135,7 +135,9 @@
  * @buf:	bufer to which the output will be written to. Needs to be at
  *		leaset mpi_get_size(a) long.
  * @buf_len:	size of the buf.
- * @nbytes:	receives the actual length of the data written.
+ * @nbytes:	receives the actual length of the data written on success and
+ *		the data to-be-written on -EOVERFLOW in case buf_len was too
+ *		small.
  * @sign:	if not NULL, it will be set to the sign of a.
  *
  * Return:	0 on success or error code in case of error
@@ -148,7 +150,7 @@
 	unsigned int n = mpi_get_size(a);
 	int i, lzeros = 0;
 
-	if (buf_len < n || !buf || !nbytes)
+	if (!buf || !nbytes)
 		return -EINVAL;
 
 	if (sign)
@@ -163,6 +165,11 @@
 			break;
 	}
 
+	if (buf_len < n - lzeros) {
+		*nbytes = n - lzeros;
+		return -EOVERFLOW;
+	}
+
 	p = buf;
 	*nbytes = n - lzeros;
 
@@ -332,7 +339,8 @@
  * @nbytes:	in/out param - it has the be set to the maximum number of
  *		bytes that can be written to sgl. This has to be at least
  *		the size of the integer a. On return it receives the actual
- *		length of the data written.
+ *		length of the data written on success or the data that would
+ *		be written if buffer was too small.
  * @sign:	if not NULL, it will be set to the sign of a.
  *
  * Return:	0 on success or error code in case of error
@@ -345,7 +353,7 @@
 	unsigned int n = mpi_get_size(a);
 	int i, x, y = 0, lzeros = 0, buf_len;
 
-	if (!nbytes || *nbytes < n)
+	if (!nbytes)
 		return -EINVAL;
 
 	if (sign)
@@ -360,6 +368,11 @@
 			break;
 	}
 
+	if (*nbytes < n - lzeros) {
+		*nbytes = n - lzeros;
+		return -EOVERFLOW;
+	}
+
 	*nbytes = n - lzeros;
 	buf_len = sgl->length;
 	p2 = sg_virt(sgl);
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index f9cee8e..ac3f947 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -31,6 +31,9 @@
 #include <linux/dcache.h>
 #include <linux/cred.h>
 #include <net/addrconf.h>
+#ifdef CONFIG_BLOCK
+#include <linux/blkdev.h>
+#endif
 
 #include <asm/page.h>		/* for PAGE_SIZE */
 #include <asm/sections.h>	/* for dereference_function_descriptor() */
@@ -613,6 +616,26 @@
 	return buf;
 }
 
+#ifdef CONFIG_BLOCK
+static noinline_for_stack
+char *bdev_name(char *buf, char *end, struct block_device *bdev,
+		struct printf_spec spec, const char *fmt)
+{
+	struct gendisk *hd = bdev->bd_disk;
+	
+	buf = string(buf, end, hd->disk_name, spec);
+	if (bdev->bd_part->partno) {
+		if (isdigit(hd->disk_name[strlen(hd->disk_name)-1])) {
+			if (buf < end)
+				*buf = 'p';
+			buf++;
+		}
+		buf = number(buf, end, bdev->bd_part->partno, spec);
+	}
+	return buf;
+}
+#endif
+
 static noinline_for_stack
 char *symbol_string(char *buf, char *end, void *ptr,
 		    struct printf_spec spec, const char *fmt)
@@ -1443,6 +1466,7 @@
  *           (default assumed to be phys_addr_t, passed by reference)
  * - 'd[234]' For a dentry name (optionally 2-4 last components)
  * - 'D[234]' Same as 'd' but for a struct file
+ * - 'g' For block_device name (gendisk + partition number)
  * - 'C' For a clock, it prints the name (Common Clock Framework) or address
  *       (legacy clock framework) of the clock
  * - 'Cn' For a clock, it prints the name (Common Clock Framework) or address
@@ -1600,6 +1624,11 @@
 		return dentry_name(buf, end,
 				   ((const struct file *)ptr)->f_path.dentry,
 				   spec, fmt);
+#ifdef CONFIG_BLOCK
+	case 'g':
+		return bdev_name(buf, end, ptr, spec, fmt);
+#endif
+
 	}
 	spec.flags |= SMALL;
 	if (spec.field_width == -1) {
diff --git a/mm/bootmem.c b/mm/bootmem.c
index 3b63807..91e32bc 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -33,6 +33,7 @@
 unsigned long max_low_pfn;
 unsigned long min_low_pfn;
 unsigned long max_pfn;
+unsigned long long max_possible_pfn;
 
 bootmem_data_t bootmem_node_data[MAX_NUMNODES] __initdata;
 
diff --git a/mm/memblock.c b/mm/memblock.c
index d300f13..07ff069 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -822,6 +822,17 @@
 	return memblock_setclr_flag(base, size, 1, MEMBLOCK_MIRROR);
 }
 
+/**
+ * memblock_mark_nomap - Mark a memory region with flag MEMBLOCK_NOMAP.
+ * @base: the base phys addr of the region
+ * @size: the size of the region
+ *
+ * Return 0 on success, -errno on failure.
+ */
+int __init_memblock memblock_mark_nomap(phys_addr_t base, phys_addr_t size)
+{
+	return memblock_setclr_flag(base, size, 1, MEMBLOCK_NOMAP);
+}
 
 /**
  * __next_reserved_mem_region - next function for for_each_reserved_region()
@@ -913,6 +924,10 @@
 		if ((flags & MEMBLOCK_MIRROR) && !memblock_is_mirror(m))
 			continue;
 
+		/* skip nomap memory unless we were asked for it explicitly */
+		if (!(flags & MEMBLOCK_NOMAP) && memblock_is_nomap(m))
+			continue;
+
 		if (!type_b) {
 			if (out_start)
 				*out_start = m_start;
@@ -1022,6 +1037,10 @@
 		if ((flags & MEMBLOCK_MIRROR) && !memblock_is_mirror(m))
 			continue;
 
+		/* skip nomap memory unless we were asked for it explicitly */
+		if (!(flags & MEMBLOCK_NOMAP) && memblock_is_nomap(m))
+			continue;
+
 		if (!type_b) {
 			if (out_start)
 				*out_start = m_start;
@@ -1519,6 +1538,15 @@
 	return memblock_search(&memblock.memory, addr) != -1;
 }
 
+int __init_memblock memblock_is_map_memory(phys_addr_t addr)
+{
+	int i = memblock_search(&memblock.memory, addr);
+
+	if (i == -1)
+		return false;
+	return !memblock_is_nomap(&memblock.memory.regions[i]);
+}
+
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 int __init_memblock memblock_search_pfn_nid(unsigned long pfn,
 			 unsigned long *start_pfn, unsigned long *end_pfn)
diff --git a/mm/mremap.c b/mm/mremap.c
index c25bc62..de824e7 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -319,6 +319,10 @@
 	hiwater_vm = mm->hiwater_vm;
 	vm_stat_account(mm, vma->vm_flags, vma->vm_file, new_len>>PAGE_SHIFT);
 
+	/* Tell pfnmap has moved from this vma */
+	if (unlikely(vma->vm_flags & VM_PFNMAP))
+		untrack_pfn_moved(vma);
+
 	if (do_munmap(mm, old_addr, old_len) < 0) {
 		/* OOM: unable to split vma, just get accounts right */
 		vm_unacct_memory(excess >> PAGE_SHIFT);
diff --git a/mm/nobootmem.c b/mm/nobootmem.c
index e57cf24..99feb2b 100644
--- a/mm/nobootmem.c
+++ b/mm/nobootmem.c
@@ -31,6 +31,7 @@
 unsigned long max_low_pfn;
 unsigned long min_low_pfn;
 unsigned long max_pfn;
+unsigned long long max_possible_pfn;
 
 static void * __init __alloc_memory_core_early(int nid, u64 size, u64 align,
 					u64 goal, u64 limit)
diff --git a/mm/shmem.c b/mm/shmem.c
index 2afcdbb..5813b7f 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2438,7 +2438,6 @@
 	int len;
 	struct inode *inode;
 	struct page *page;
-	char *kaddr;
 	struct shmem_inode_info *info;
 
 	len = strlen(symname) + 1;
@@ -2477,9 +2476,8 @@
 		}
 		inode->i_mapping->a_ops = &shmem_aops;
 		inode->i_op = &shmem_symlink_inode_operations;
-		kaddr = kmap_atomic(page);
-		memcpy(kaddr, symname, len);
-		kunmap_atomic(kaddr);
+		inode_nohighmem(inode);
+		memcpy(page_address(page), symname, len);
 		SetPageUptodate(page);
 		set_page_dirty(page);
 		unlock_page(page);
@@ -2492,23 +2490,34 @@
 	return 0;
 }
 
-static const char *shmem_follow_link(struct dentry *dentry, void **cookie)
+static void shmem_put_link(void *arg)
 {
-	struct page *page = NULL;
-	int error = shmem_getpage(d_inode(dentry), 0, &page, SGP_READ, NULL);
-	if (error)
-		return ERR_PTR(error);
-	unlock_page(page);
-	*cookie = page;
-	return kmap(page);
+	mark_page_accessed(arg);
+	put_page(arg);
 }
 
-static void shmem_put_link(struct inode *unused, void *cookie)
+static const char *shmem_get_link(struct dentry *dentry,
+				  struct inode *inode,
+				  struct delayed_call *done)
 {
-	struct page *page = cookie;
-	kunmap(page);
-	mark_page_accessed(page);
-	page_cache_release(page);
+	struct page *page = NULL;
+	int error;
+	if (!dentry) {
+		page = find_get_page(inode->i_mapping, 0);
+		if (!page)
+			return ERR_PTR(-ECHILD);
+		if (!PageUptodate(page)) {
+			put_page(page);
+			return ERR_PTR(-ECHILD);
+		}
+	} else {
+		error = shmem_getpage(inode, 0, &page, SGP_READ, NULL);
+		if (error)
+			return ERR_PTR(error);
+		unlock_page(page);
+	}
+	set_delayed_call(done, shmem_put_link, page);
+	return page_address(page);
 }
 
 #ifdef CONFIG_TMPFS_XATTR
@@ -2555,122 +2564,74 @@
 	return 0;
 }
 
+static int shmem_xattr_handler_get(const struct xattr_handler *handler,
+				   struct dentry *dentry, const char *name,
+				   void *buffer, size_t size)
+{
+	struct shmem_inode_info *info = SHMEM_I(d_inode(dentry));
+
+	name = xattr_full_name(handler, name);
+	return simple_xattr_get(&info->xattrs, name, buffer, size);
+}
+
+static int shmem_xattr_handler_set(const struct xattr_handler *handler,
+				   struct dentry *dentry, const char *name,
+				   const void *value, size_t size, int flags)
+{
+	struct shmem_inode_info *info = SHMEM_I(d_inode(dentry));
+
+	name = xattr_full_name(handler, name);
+	return simple_xattr_set(&info->xattrs, name, value, size, flags);
+}
+
+static const struct xattr_handler shmem_security_xattr_handler = {
+	.prefix = XATTR_SECURITY_PREFIX,
+	.get = shmem_xattr_handler_get,
+	.set = shmem_xattr_handler_set,
+};
+
+static const struct xattr_handler shmem_trusted_xattr_handler = {
+	.prefix = XATTR_TRUSTED_PREFIX,
+	.get = shmem_xattr_handler_get,
+	.set = shmem_xattr_handler_set,
+};
+
 static const struct xattr_handler *shmem_xattr_handlers[] = {
 #ifdef CONFIG_TMPFS_POSIX_ACL
 	&posix_acl_access_xattr_handler,
 	&posix_acl_default_xattr_handler,
 #endif
+	&shmem_security_xattr_handler,
+	&shmem_trusted_xattr_handler,
 	NULL
 };
 
-static int shmem_xattr_validate(const char *name)
-{
-	struct { const char *prefix; size_t len; } arr[] = {
-		{ XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN },
-		{ XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN }
-	};
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(arr); i++) {
-		size_t preflen = arr[i].len;
-		if (strncmp(name, arr[i].prefix, preflen) == 0) {
-			if (!name[preflen])
-				return -EINVAL;
-			return 0;
-		}
-	}
-	return -EOPNOTSUPP;
-}
-
-static ssize_t shmem_getxattr(struct dentry *dentry, const char *name,
-			      void *buffer, size_t size)
-{
-	struct shmem_inode_info *info = SHMEM_I(d_inode(dentry));
-	int err;
-
-	/*
-	 * If this is a request for a synthetic attribute in the system.*
-	 * namespace use the generic infrastructure to resolve a handler
-	 * for it via sb->s_xattr.
-	 */
-	if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
-		return generic_getxattr(dentry, name, buffer, size);
-
-	err = shmem_xattr_validate(name);
-	if (err)
-		return err;
-
-	return simple_xattr_get(&info->xattrs, name, buffer, size);
-}
-
-static int shmem_setxattr(struct dentry *dentry, const char *name,
-			  const void *value, size_t size, int flags)
-{
-	struct shmem_inode_info *info = SHMEM_I(d_inode(dentry));
-	int err;
-
-	/*
-	 * If this is a request for a synthetic attribute in the system.*
-	 * namespace use the generic infrastructure to resolve a handler
-	 * for it via sb->s_xattr.
-	 */
-	if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
-		return generic_setxattr(dentry, name, value, size, flags);
-
-	err = shmem_xattr_validate(name);
-	if (err)
-		return err;
-
-	return simple_xattr_set(&info->xattrs, name, value, size, flags);
-}
-
-static int shmem_removexattr(struct dentry *dentry, const char *name)
-{
-	struct shmem_inode_info *info = SHMEM_I(d_inode(dentry));
-	int err;
-
-	/*
-	 * If this is a request for a synthetic attribute in the system.*
-	 * namespace use the generic infrastructure to resolve a handler
-	 * for it via sb->s_xattr.
-	 */
-	if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
-		return generic_removexattr(dentry, name);
-
-	err = shmem_xattr_validate(name);
-	if (err)
-		return err;
-
-	return simple_xattr_remove(&info->xattrs, name);
-}
-
 static ssize_t shmem_listxattr(struct dentry *dentry, char *buffer, size_t size)
 {
 	struct shmem_inode_info *info = SHMEM_I(d_inode(dentry));
-	return simple_xattr_list(&info->xattrs, buffer, size);
+	return simple_xattr_list(d_inode(dentry), &info->xattrs, buffer, size);
 }
 #endif /* CONFIG_TMPFS_XATTR */
 
 static const struct inode_operations shmem_short_symlink_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= simple_follow_link,
+	.get_link	= simple_get_link,
 #ifdef CONFIG_TMPFS_XATTR
-	.setxattr	= shmem_setxattr,
-	.getxattr	= shmem_getxattr,
+	.setxattr	= generic_setxattr,
+	.getxattr	= generic_getxattr,
 	.listxattr	= shmem_listxattr,
-	.removexattr	= shmem_removexattr,
+	.removexattr	= generic_removexattr,
 #endif
 };
 
 static const struct inode_operations shmem_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= shmem_follow_link,
-	.put_link	= shmem_put_link,
+	.get_link	= shmem_get_link,
 #ifdef CONFIG_TMPFS_XATTR
-	.setxattr	= shmem_setxattr,
-	.getxattr	= shmem_getxattr,
+	.setxattr	= generic_setxattr,
+	.getxattr	= generic_getxattr,
 	.listxattr	= shmem_listxattr,
-	.removexattr	= shmem_removexattr,
+	.removexattr	= generic_removexattr,
 #endif
 };
 
@@ -3142,10 +3103,10 @@
 	.getattr	= shmem_getattr,
 	.setattr	= shmem_setattr,
 #ifdef CONFIG_TMPFS_XATTR
-	.setxattr	= shmem_setxattr,
-	.getxattr	= shmem_getxattr,
+	.setxattr	= generic_setxattr,
+	.getxattr	= generic_getxattr,
 	.listxattr	= shmem_listxattr,
-	.removexattr	= shmem_removexattr,
+	.removexattr	= generic_removexattr,
 	.set_acl	= simple_set_acl,
 #endif
 };
@@ -3164,10 +3125,10 @@
 	.tmpfile	= shmem_tmpfile,
 #endif
 #ifdef CONFIG_TMPFS_XATTR
-	.setxattr	= shmem_setxattr,
-	.getxattr	= shmem_getxattr,
+	.setxattr	= generic_setxattr,
+	.getxattr	= generic_getxattr,
 	.listxattr	= shmem_listxattr,
-	.removexattr	= shmem_removexattr,
+	.removexattr	= generic_removexattr,
 #endif
 #ifdef CONFIG_TMPFS_POSIX_ACL
 	.setattr	= shmem_setattr,
@@ -3177,10 +3138,10 @@
 
 static const struct inode_operations shmem_special_inode_operations = {
 #ifdef CONFIG_TMPFS_XATTR
-	.setxattr	= shmem_setxattr,
-	.getxattr	= shmem_getxattr,
+	.setxattr	= generic_setxattr,
+	.getxattr	= generic_getxattr,
 	.listxattr	= shmem_listxattr,
-	.removexattr	= shmem_removexattr,
+	.removexattr	= generic_removexattr,
 #endif
 #ifdef CONFIG_TMPFS_POSIX_ACL
 	.setattr	= shmem_setattr,
diff --git a/mm/util.c b/mm/util.c
index 9af1c12..2d28f79 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -176,6 +176,37 @@
 }
 EXPORT_SYMBOL(strndup_user);
 
+/**
+ * memdup_user_nul - duplicate memory region from user space and NUL-terminate
+ *
+ * @src: source address in user space
+ * @len: number of bytes to copy
+ *
+ * Returns an ERR_PTR() on failure.
+ */
+void *memdup_user_nul(const void __user *src, size_t len)
+{
+	char *p;
+
+	/*
+	 * Always use GFP_KERNEL, since copy_from_user() can sleep and
+	 * cause pagefault, which makes it pointless to use GFP_NOFS
+	 * or GFP_ATOMIC.
+	 */
+	p = kmalloc_track_caller(len + 1, GFP_KERNEL);
+	if (!p)
+		return ERR_PTR(-ENOMEM);
+
+	if (copy_from_user(p, src, len)) {
+		kfree(p);
+		return ERR_PTR(-EFAULT);
+	}
+	p[len] = '\0';
+
+	return p;
+}
+EXPORT_SYMBOL(memdup_user_nul);
+
 void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
 		struct vm_area_struct *prev, struct rb_node *rb_parent)
 {
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 4ebc17d..c54fd29 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1483,6 +1483,7 @@
 		BUG();
 	cpumask_copy(cpu_stat_off, cpu_online_mask);
 
+	vmstat_wq = alloc_workqueue("vmstat", WQ_FREEZABLE|WQ_MEM_RECLAIM, 0);
 	schedule_delayed_work(&shepherd,
 		round_jiffies_relative(sysctl_stat_interval));
 }
@@ -1550,7 +1551,6 @@
 
 	start_shepherd_timer();
 	cpu_notifier_register_done();
-	vmstat_wq = alloc_workqueue("vmstat", WQ_FREEZABLE|WQ_MEM_RECLAIM, 0);
 #endif
 #ifdef CONFIG_PROC_FS
 	proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations);
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index 6e70ddb..199bc76 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -105,7 +105,7 @@
 /* How many bytes left in this page. */
 static unsigned int rest_of_page(void *data)
 {
-	return PAGE_SIZE - ((unsigned long)data % PAGE_SIZE);
+	return PAGE_SIZE - offset_in_page(data);
 }
 
 /**
@@ -143,7 +143,6 @@
 static void req_done(struct virtqueue *vq)
 {
 	struct virtio_chan *chan = vq->vdev->priv;
-	struct p9_fcall *rc;
 	unsigned int len;
 	struct p9_req_t *req;
 	unsigned long flags;
@@ -152,8 +151,8 @@
 
 	while (1) {
 		spin_lock_irqsave(&chan->lock, flags);
-		rc = virtqueue_get_buf(chan->vq, &len);
-		if (rc == NULL) {
+		req = virtqueue_get_buf(chan->vq, &len);
+		if (req == NULL) {
 			spin_unlock_irqrestore(&chan->lock, flags);
 			break;
 		}
@@ -161,9 +160,6 @@
 		spin_unlock_irqrestore(&chan->lock, flags);
 		/* Wakeup if anyone waiting for VirtIO ring space. */
 		wake_up(chan->vc_wq);
-		p9_debug(P9_DEBUG_TRANS, ": rc %p\n", rc);
-		p9_debug(P9_DEBUG_TRANS, ": lookup tag %d\n", rc->tag);
-		req = p9_tag_lookup(chan->client, rc->tag);
 		p9_client_cb(chan->client, req, REQ_STATUS_RCVD);
 	}
 }
@@ -284,7 +280,7 @@
 	if (in)
 		sgs[out_sgs + in_sgs++] = chan->sg + out;
 
-	err = virtqueue_add_sgs(chan->vq, sgs, out_sgs, in_sgs, req->tc,
+	err = virtqueue_add_sgs(chan->vq, sgs, out_sgs, in_sgs, req,
 				GFP_ATOMIC);
 	if (err < 0) {
 		if (err == -ENOSPC) {
@@ -369,7 +365,7 @@
 			return -ENOMEM;
 
 		*need_drop = 0;
-		p -= (*offs = (unsigned long)p % PAGE_SIZE);
+		p -= (*offs = offset_in_page(p));
 		for (index = 0; index < nr_pages; index++) {
 			if (is_vmalloc_addr(p))
 				(*pages)[index] = vmalloc_to_page(p);
@@ -469,7 +465,7 @@
 	}
 
 	BUG_ON(out_sgs + in_sgs > ARRAY_SIZE(sgs));
-	err = virtqueue_add_sgs(chan->vq, sgs, out_sgs, in_sgs, req->tc,
+	err = virtqueue_add_sgs(chan->vq, sgs, out_sgs, in_sgs, req,
 				GFP_ATOMIC);
 	if (err < 0) {
 		if (err == -ENOSPC) {
diff --git a/net/rxrpc/ar-key.c b/net/rxrpc/ar-key.c
index da3cc09..3f65716 100644
--- a/net/rxrpc/ar-key.c
+++ b/net/rxrpc/ar-key.c
@@ -896,15 +896,9 @@
 	if (optlen <= 0 || optlen > PAGE_SIZE - 1)
 		return -EINVAL;
 
-	description = kmalloc(optlen + 1, GFP_KERNEL);
-	if (!description)
-		return -ENOMEM;
-
-	if (copy_from_user(description, optval, optlen)) {
-		kfree(description);
-		return -EFAULT;
-	}
-	description[optlen] = 0;
+	description = memdup_user_nul(optval, optlen);
+	if (IS_ERR(description))
+		return PTR_ERR(description);
 
 	key = request_key(&key_type_rxrpc, description, NULL);
 	if (IS_ERR(key)) {
@@ -933,15 +927,9 @@
 	if (optlen <= 0 || optlen > PAGE_SIZE - 1)
 		return -EINVAL;
 
-	description = kmalloc(optlen + 1, GFP_KERNEL);
-	if (!description)
-		return -ENOMEM;
-
-	if (copy_from_user(description, optval, optlen)) {
-		kfree(description);
-		return -EFAULT;
-	}
-	description[optlen] = 0;
+	description = memdup_user_nul(optval, optlen);
+	if (IS_ERR(description))
+		return PTR_ERR(description);
 
 	key = request_key(&key_type_keyring, description, NULL);
 	if (IS_ERR(key)) {
diff --git a/scripts/ld-version.sh b/scripts/ld-version.sh
index 198580d..d154f08 100755
--- a/scripts/ld-version.sh
+++ b/scripts/ld-version.sh
@@ -2,7 +2,9 @@
 # extract linker version number from stdin and turn into single number
 	{
 	gsub(".*)", "");
+	gsub(".*version ", "");
+	gsub("-.*", "");
 	split($1,a, ".");
-	print a[1]*10000000 + a[2]*100000 + a[3]*10000 + a[4]*100 + a[5];
+	print a[1]*100000000 + a[2]*1000000 + a[3]*10000 + a[4]*100 + a[5];
 	exit
 	}
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index dacf71a..ba6c34e 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -62,7 +62,7 @@
 			-Wl,--start-group                                    \
 				 ${KBUILD_VMLINUX_MAIN}                      \
 			-Wl,--end-group                                      \
-			-lutil -lrt ${1}
+			-lutil -lrt -lpthread ${1}
 		rm -f linux
 	fi
 }
diff --git a/security/integrity/iint.c b/security/integrity/iint.c
index 3d2f5b4..c2e3ccd 100644
--- a/security/integrity/iint.c
+++ b/security/integrity/iint.c
@@ -234,12 +234,13 @@
 	}
 
 	rc = integrity_kernel_read(file, 0, buf, size);
-	if (rc < 0)
-		kfree(buf);
-	else if (rc != size)
-		rc = -EIO;
-	else
+	if (rc == size) {
 		*data = buf;
+	} else {
+		kfree(buf);
+		if (rc >= 0)
+			rc = -EIO;
+	}
 out:
 	fput(file);
 	return rc;
diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c
index c02da25..73c60ba 100644
--- a/security/selinux/selinuxfs.c
+++ b/security/selinux/selinuxfs.c
@@ -147,23 +147,16 @@
 	ssize_t length;
 	int new_value;
 
-	length = -ENOMEM;
 	if (count >= PAGE_SIZE)
-		goto out;
+		return -ENOMEM;
 
 	/* No partial writes. */
-	length = -EINVAL;
 	if (*ppos != 0)
-		goto out;
+		return -EINVAL;
 
-	length = -ENOMEM;
-	page = (char *)get_zeroed_page(GFP_KERNEL);
-	if (!page)
-		goto out;
-
-	length = -EFAULT;
-	if (copy_from_user(page, buf, count))
-		goto out;
+	page = memdup_user_nul(buf, count);
+	if (IS_ERR(page))
+		return PTR_ERR(page);
 
 	length = -EINVAL;
 	if (sscanf(page, "%d", &new_value) != 1)
@@ -186,7 +179,7 @@
 	}
 	length = count;
 out:
-	free_page((unsigned long) page);
+	kfree(page);
 	return length;
 }
 #else
@@ -275,27 +268,20 @@
 				 size_t count, loff_t *ppos)
 
 {
-	char *page = NULL;
+	char *page;
 	ssize_t length;
 	int new_value;
 
-	length = -ENOMEM;
 	if (count >= PAGE_SIZE)
-		goto out;
+		return -ENOMEM;
 
 	/* No partial writes. */
-	length = -EINVAL;
 	if (*ppos != 0)
-		goto out;
+		return -EINVAL;
 
-	length = -ENOMEM;
-	page = (char *)get_zeroed_page(GFP_KERNEL);
-	if (!page)
-		goto out;
-
-	length = -EFAULT;
-	if (copy_from_user(page, buf, count))
-		goto out;
+	page = memdup_user_nul(buf, count);
+	if (IS_ERR(page))
+		return PTR_ERR(page);
 
 	length = -EINVAL;
 	if (sscanf(page, "%d", &new_value) != 1)
@@ -313,7 +299,7 @@
 
 	length = count;
 out:
-	free_page((unsigned long) page);
+	kfree(page);
 	return length;
 }
 #else
@@ -611,31 +597,24 @@
 static ssize_t sel_write_checkreqprot(struct file *file, const char __user *buf,
 				      size_t count, loff_t *ppos)
 {
-	char *page = NULL;
+	char *page;
 	ssize_t length;
 	unsigned int new_value;
 
 	length = task_has_security(current, SECURITY__SETCHECKREQPROT);
 	if (length)
-		goto out;
+		return length;
 
-	length = -ENOMEM;
 	if (count >= PAGE_SIZE)
-		goto out;
+		return -ENOMEM;
 
 	/* No partial writes. */
-	length = -EINVAL;
 	if (*ppos != 0)
-		goto out;
+		return -EINVAL;
 
-	length = -ENOMEM;
-	page = (char *)get_zeroed_page(GFP_KERNEL);
-	if (!page)
-		goto out;
-
-	length = -EFAULT;
-	if (copy_from_user(page, buf, count))
-		goto out;
+	page = memdup_user_nul(buf, count);
+	if (IS_ERR(page))
+		return PTR_ERR(page);
 
 	length = -EINVAL;
 	if (sscanf(page, "%u", &new_value) != 1)
@@ -644,7 +623,7 @@
 	selinux_checkreqprot = new_value ? 1 : 0;
 	length = count;
 out:
-	free_page((unsigned long) page);
+	kfree(page);
 	return length;
 }
 static const struct file_operations sel_checkreqprot_ops = {
@@ -1100,14 +1079,12 @@
 	if (*ppos != 0)
 		goto out;
 
-	length = -ENOMEM;
-	page = (char *)get_zeroed_page(GFP_KERNEL);
-	if (!page)
+	page = memdup_user_nul(buf, count);
+	if (IS_ERR(page)) {
+		length = PTR_ERR(page);
+		page = NULL;
 		goto out;
-
-	length = -EFAULT;
-	if (copy_from_user(page, buf, count))
-		goto out;
+	}
 
 	length = -EINVAL;
 	if (sscanf(page, "%d", &new_value) != 1)
@@ -1121,7 +1098,7 @@
 
 out:
 	mutex_unlock(&sel_mutex);
-	free_page((unsigned long) page);
+	kfree(page);
 	return length;
 }
 
@@ -1154,14 +1131,12 @@
 	if (*ppos != 0)
 		goto out;
 
-	length = -ENOMEM;
-	page = (char *)get_zeroed_page(GFP_KERNEL);
-	if (!page)
+	page = memdup_user_nul(buf, count);
+	if (IS_ERR(page)) {
+		length = PTR_ERR(page);
+		page = NULL;
 		goto out;
-
-	length = -EFAULT;
-	if (copy_from_user(page, buf, count))
-		goto out;
+	}
 
 	length = -EINVAL;
 	if (sscanf(page, "%d", &new_value) != 1)
@@ -1176,7 +1151,7 @@
 
 out:
 	mutex_unlock(&sel_mutex);
-	free_page((unsigned long) page);
+	kfree(page);
 	return length;
 }
 
@@ -1292,31 +1267,24 @@
 					     size_t count, loff_t *ppos)
 
 {
-	char *page = NULL;
+	char *page;
 	ssize_t ret;
 	int new_value;
 
 	ret = task_has_security(current, SECURITY__SETSECPARAM);
 	if (ret)
-		goto out;
+		return ret;
 
-	ret = -ENOMEM;
 	if (count >= PAGE_SIZE)
-		goto out;
+		return -ENOMEM;
 
 	/* No partial writes. */
-	ret = -EINVAL;
 	if (*ppos != 0)
-		goto out;
+		return -EINVAL;
 
-	ret = -ENOMEM;
-	page = (char *)get_zeroed_page(GFP_KERNEL);
-	if (!page)
-		goto out;
-
-	ret = -EFAULT;
-	if (copy_from_user(page, buf, count))
-		goto out;
+	page = memdup_user_nul(buf, count);
+	if (IS_ERR(page))
+		return PTR_ERR(page);
 
 	ret = -EINVAL;
 	if (sscanf(page, "%u", &new_value) != 1)
@@ -1326,7 +1294,7 @@
 
 	ret = count;
 out:
-	free_page((unsigned long)page);
+	kfree(page);
 	return ret;
 }
 
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index ff81026..37fdd54 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -1519,8 +1519,6 @@
  * @inode: the object
  * @buffer: where they go
  * @buffer_size: size of buffer
- *
- * Returns 0 on success, -EINVAL otherwise
  */
 static int smack_inode_listsecurity(struct inode *inode, char *buffer,
 				    size_t buffer_size)
diff --git a/security/smack/smackfs.c b/security/smack/smackfs.c
index 94bd9e4..e249a66 100644
--- a/security/smack/smackfs.c
+++ b/security/smack/smackfs.c
@@ -497,14 +497,9 @@
 		}
 	}
 
-	data = kmalloc(count + 1, GFP_KERNEL);
-	if (data == NULL)
-		return -ENOMEM;
-
-	if (copy_from_user(data, buf, count) != 0) {
-		rc = -EFAULT;
-		goto out;
-	}
+	data = memdup_user_nul(buf, count);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
 
 	/*
 	 * In case of parsing only part of user buf,
@@ -884,16 +879,10 @@
 	    (count < SMK_CIPSOMIN || count > SMK_CIPSOMAX))
 		return -EINVAL;
 
-	data = kzalloc(count + 1, GFP_KERNEL);
-	if (data == NULL)
-		return -ENOMEM;
+	data = memdup_user_nul(buf, count);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
 
-	if (copy_from_user(data, buf, count) != 0) {
-		rc = -EFAULT;
-		goto unlockedout;
-	}
-
-	data[count] = '\0';
 	rule = data;
 	/*
 	 * Only allow one writer at a time. Writes should be
@@ -946,7 +935,6 @@
 
 out:
 	mutex_unlock(&smack_cipso_lock);
-unlockedout:
 	kfree(data);
 	return rc;
 }
@@ -1187,14 +1175,9 @@
 	if (count < SMK_NETLBLADDRMIN)
 		return -EINVAL;
 
-	data = kzalloc(count + 1, GFP_KERNEL);
-	if (data == NULL)
-		return -ENOMEM;
-
-	if (copy_from_user(data, buf, count) != 0) {
-		rc = -EFAULT;
-		goto free_data_out;
-	}
+	data = memdup_user_nul(buf, count);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
 
 	smack = kzalloc(count + 1, GFP_KERNEL);
 	if (smack == NULL) {
@@ -1202,8 +1185,6 @@
 		goto free_data_out;
 	}
 
-	data[count] = '\0';
-
 	rc = sscanf(data, "%hhd.%hhd.%hhd.%hhd/%u %s",
 		&host[0], &host[1], &host[2], &host[3], &masks, smack);
 	if (rc != 6) {
@@ -1454,14 +1435,9 @@
 	if (count < SMK_NETLBLADDRMIN)
 		return -EINVAL;
 
-	data = kzalloc(count + 1, GFP_KERNEL);
-	if (data == NULL)
-		return -ENOMEM;
-
-	if (copy_from_user(data, buf, count) != 0) {
-		rc = -EFAULT;
-		goto free_data_out;
-	}
+	data = memdup_user_nul(buf, count);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
 
 	smack = kzalloc(count + 1, GFP_KERNEL);
 	if (smack == NULL) {
@@ -1469,8 +1445,6 @@
 		goto free_data_out;
 	}
 
-	data[count] = '\0';
-
 	i = sscanf(data, "%x:%x:%x:%x:%x:%x:%x:%x/%u %s",
 			&scanned[0], &scanned[1], &scanned[2], &scanned[3],
 			&scanned[4], &scanned[5], &scanned[6], &scanned[7],
@@ -1865,14 +1839,9 @@
 	if (!smack_privileged(CAP_MAC_ADMIN))
 		return -EPERM;
 
-	data = kzalloc(count + 1, GFP_KERNEL);
-	if (data == NULL)
-		return -ENOMEM;
-
-	if (copy_from_user(data, buf, count) != 0) {
-		rc = -EFAULT;
-		goto out;
-	}
+	data = memdup_user_nul(buf, count);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
 
 	skp = smk_import_entry(data, count);
 	if (IS_ERR(skp)) {
@@ -2041,14 +2010,9 @@
 	if (!smack_privileged(CAP_MAC_ADMIN))
 		return -EPERM;
 
-	data = kzalloc(count + 1, GFP_KERNEL);
-	if (data == NULL)
-		return -ENOMEM;
-
-	if (copy_from_user(data, buf, count) != 0) {
-		kfree(data);
-		return -EFAULT;
-	}
+	data = memdup_user_nul(buf, count);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
 
 	rc = smk_parse_label_list(data, &list_tmp);
 	kfree(data);
@@ -2133,14 +2097,9 @@
 	if (!smack_privileged(CAP_MAC_ADMIN))
 		return -EPERM;
 
-	data = kzalloc(count + 1, GFP_KERNEL);
-	if (data == NULL)
-		return -ENOMEM;
-
-	if (copy_from_user(data, buf, count) != 0) {
-		rc = -EFAULT;
-		goto freeout;
-	}
+	data = memdup_user_nul(buf, count);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
 
 	/*
 	 * Clear the smack_unconfined on invalid label errors. This means
@@ -2696,19 +2655,15 @@
 	if (!smack_privileged(CAP_MAC_ADMIN))
 		return -EPERM;
 
-	data = kzalloc(count + 1, GFP_KERNEL);
-	if (data == NULL)
-		return -ENOMEM;
+	data = memdup_user_nul(buf, count);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
 
-	if (copy_from_user(data, buf, count) != 0)
-		rc = -EFAULT;
-	else {
-		skp = smk_import_entry(data, count);
-		if (IS_ERR(skp))
-			rc = PTR_ERR(skp);
-		else
-			smack_syslog_label = skp;
-	}
+	skp = smk_import_entry(data, count);
+	if (IS_ERR(skp))
+		rc = PTR_ERR(skp);
+	else
+		smack_syslog_label = skp;
 
 	kfree(data);
 	return rc;
@@ -2798,14 +2753,9 @@
 	if (*ppos != 0)
 		return -EINVAL;
 
-	data = kzalloc(count + 1, GFP_KERNEL);
-	if (data == NULL)
-		return -ENOMEM;
-
-	if (copy_from_user(data, buf, count) != 0) {
-		kfree(data);
-		return -EFAULT;
-	}
+	data = memdup_user_nul(buf, count);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
 
 	rc = smk_parse_label_list(data, &list_tmp);
 	kfree(data);
diff --git a/security/tomoyo/securityfs_if.c b/security/tomoyo/securityfs_if.c
index 179a955..06ab41b1 100644
--- a/security/tomoyo/securityfs_if.c
+++ b/security/tomoyo/securityfs_if.c
@@ -43,13 +43,9 @@
 	int error;
 	if (!count || count >= TOMOYO_EXEC_TMPSIZE - 10)
 		return -ENOMEM;
-	data = kzalloc(count + 1, GFP_NOFS);
-	if (!data)
-		return -ENOMEM;
-	if (copy_from_user(data, buf, count)) {
-		error = -EFAULT;
-		goto out;
-	}
+	data = memdup_user_nul(buf, count);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
 	tomoyo_normalize_line(data);
 	if (tomoyo_correct_domain(data)) {
 		const int idx = tomoyo_read_lock();
@@ -87,7 +83,6 @@
 		tomoyo_read_unlock(idx);
 	} else
 		error = -EINVAL;
-out:
 	kfree(data);
 	return error ? error : count;
 }
diff --git a/sound/pci/es1968.c b/sound/pci/es1968.c
index e0d9363..514f260 100644
--- a/sound/pci/es1968.c
+++ b/sound/pci/es1968.c
@@ -113,7 +113,7 @@
 #include <sound/initval.h>
 
 #ifdef CONFIG_SND_ES1968_RADIO
-#include <media/tea575x.h>
+#include <media/drv-intf/tea575x.h>
 #endif
 
 #define CARD_NAME "ESS Maestro1/2"
@@ -2605,7 +2605,7 @@
 	}
 }
 
-static struct snd_tea575x_ops snd_es1968_tea_ops = {
+static const struct snd_tea575x_ops snd_es1968_tea_ops = {
 	.set_pins = snd_es1968_tea575x_set_pins,
 	.get_pins = snd_es1968_tea575x_get_pins,
 	.set_direction = snd_es1968_tea575x_set_direction,
diff --git a/sound/pci/fm801.c b/sound/pci/fm801.c
index 1fdd92b6..759295a 100644
--- a/sound/pci/fm801.c
+++ b/sound/pci/fm801.c
@@ -30,7 +30,7 @@
 #include <sound/initval.h>
 
 #ifdef CONFIG_SND_FM801_TEA575X_BOOL
-#include <media/tea575x.h>
+#include <media/drv-intf/tea575x.h>
 #endif
 
 MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
@@ -815,7 +815,7 @@
 	fm801_writew(chip, GPIO_CTRL, reg);
 }
 
-static struct snd_tea575x_ops snd_fm801_tea_ops = {
+static const struct snd_tea575x_ops snd_fm801_tea_ops = {
 	.set_pins = snd_fm801_tea575x_set_pins,
 	.get_pins = snd_fm801_tea575x_get_pins,
 	.set_direction = snd_fm801_tea575x_set_direction,
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index fe96428..3a89d82 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -67,6 +67,10 @@
 	ALC_HEADSET_TYPE_OMTP,
 };
 
+enum {
+	ALC_KEY_MICMUTE_INDEX,
+};
+
 struct alc_customize_define {
 	unsigned int  sku_cfg;
 	unsigned char port_connectivity;
@@ -123,6 +127,7 @@
 	unsigned int pll_coef_idx, pll_coef_bit;
 	unsigned int coef0;
 	struct input_dev *kb_dev;
+	u8 alc_mute_keycode_map[1];
 };
 
 /*
@@ -3462,12 +3467,43 @@
 
 	/* GPIO2 just toggles on a keypress/keyrelease cycle. Therefore
 	   send both key on and key off event for every interrupt. */
-	input_report_key(spec->kb_dev, KEY_MICMUTE, 1);
+	input_report_key(spec->kb_dev, spec->alc_mute_keycode_map[ALC_KEY_MICMUTE_INDEX], 1);
 	input_sync(spec->kb_dev);
-	input_report_key(spec->kb_dev, KEY_MICMUTE, 0);
+	input_report_key(spec->kb_dev, spec->alc_mute_keycode_map[ALC_KEY_MICMUTE_INDEX], 0);
 	input_sync(spec->kb_dev);
 }
 
+static int alc_register_micmute_input_device(struct hda_codec *codec)
+{
+	struct alc_spec *spec = codec->spec;
+	int i;
+
+	spec->kb_dev = input_allocate_device();
+	if (!spec->kb_dev) {
+		codec_err(codec, "Out of memory (input_allocate_device)\n");
+		return -ENOMEM;
+	}
+
+	spec->alc_mute_keycode_map[ALC_KEY_MICMUTE_INDEX] = KEY_MICMUTE;
+
+	spec->kb_dev->name = "Microphone Mute Button";
+	spec->kb_dev->evbit[0] = BIT_MASK(EV_KEY);
+	spec->kb_dev->keycodesize = sizeof(spec->alc_mute_keycode_map[0]);
+	spec->kb_dev->keycodemax = ARRAY_SIZE(spec->alc_mute_keycode_map);
+	spec->kb_dev->keycode = spec->alc_mute_keycode_map;
+	for (i = 0; i < ARRAY_SIZE(spec->alc_mute_keycode_map); i++)
+		set_bit(spec->alc_mute_keycode_map[i], spec->kb_dev->keybit);
+
+	if (input_register_device(spec->kb_dev)) {
+		codec_err(codec, "input_register_device failed\n");
+		input_free_device(spec->kb_dev);
+		spec->kb_dev = NULL;
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
 static void alc280_fixup_hp_gpio2_mic_hotkey(struct hda_codec *codec,
 					     const struct hda_fixup *fix, int action)
 {
@@ -3485,20 +3521,8 @@
 	struct alc_spec *spec = codec->spec;
 
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
-		spec->kb_dev = input_allocate_device();
-		if (!spec->kb_dev) {
-			codec_err(codec, "Out of memory (input_allocate_device)\n");
+		if (alc_register_micmute_input_device(codec) != 0)
 			return;
-		}
-		spec->kb_dev->name = "Microphone Mute Button";
-		spec->kb_dev->evbit[0] = BIT_MASK(EV_KEY);
-		spec->kb_dev->keybit[BIT_WORD(KEY_MICMUTE)] = BIT_MASK(KEY_MICMUTE);
-		if (input_register_device(spec->kb_dev)) {
-			codec_err(codec, "input_register_device failed\n");
-			input_free_device(spec->kb_dev);
-			spec->kb_dev = NULL;
-			return;
-		}
 
 		snd_hda_add_verbs(codec, gpio_init);
 		snd_hda_codec_write_cache(codec, codec->core.afg, 0,
@@ -3528,6 +3552,47 @@
 	}
 }
 
+static void alc233_fixup_lenovo_line2_mic_hotkey(struct hda_codec *codec,
+					     const struct hda_fixup *fix, int action)
+{
+	/* Line2 = mic mute hotkey
+	   GPIO2 = mic mute LED */
+	static const struct hda_verb gpio_init[] = {
+		{ 0x01, AC_VERB_SET_GPIO_MASK, 0x04 },
+		{ 0x01, AC_VERB_SET_GPIO_DIRECTION, 0x04 },
+		{}
+	};
+
+	struct alc_spec *spec = codec->spec;
+
+	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
+		if (alc_register_micmute_input_device(codec) != 0)
+			return;
+
+		snd_hda_add_verbs(codec, gpio_init);
+		snd_hda_jack_detect_enable_callback(codec, 0x1b,
+						    gpio2_mic_hotkey_event);
+
+		spec->gen.cap_sync_hook = alc_fixup_gpio_mic_mute_hook;
+		spec->gpio_led = 0;
+		spec->mute_led_polarity = 0;
+		spec->gpio_mic_led_mask = 0x04;
+		return;
+	}
+
+	if (!spec->kb_dev)
+		return;
+
+	switch (action) {
+	case HDA_FIXUP_ACT_PROBE:
+		spec->init_amp = ALC_INIT_DEFAULT;
+		break;
+	case HDA_FIXUP_ACT_FREE:
+		input_unregister_device(spec->kb_dev);
+		spec->kb_dev = NULL;
+	}
+}
+
 static void alc269_fixup_hp_line1_mic1_led(struct hda_codec *codec,
 				const struct hda_fixup *fix, int action)
 {
@@ -4628,6 +4693,7 @@
 	ALC275_FIXUP_DELL_XPS,
 	ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE,
 	ALC293_FIXUP_LENOVO_SPK_NOISE,
+	ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY,
 };
 
 static const struct hda_fixup alc269_fixups[] = {
@@ -5237,6 +5303,10 @@
 		.chained = true,
 		.chain_id = ALC269_FIXUP_THINKPAD_ACPI
 	},
+	[ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc233_fixup_lenovo_line2_mic_hotkey,
+	},
 };
 
 static const struct snd_pci_quirk alc269_fixup_tbl[] = {
@@ -5386,6 +5456,7 @@
 	SND_PCI_QUIRK(0x17aa, 0x2223, "ThinkPad T550", ALC292_FIXUP_TPT440_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x2226, "ThinkPad X250", ALC292_FIXUP_TPT440_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x2233, "Thinkpad", ALC293_FIXUP_LENOVO_SPK_NOISE),
+	SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
 	SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC),
 	SND_PCI_QUIRK(0x17aa, 0x3978, "IdeaPad Y410P", ALC269_FIXUP_NO_SHUTUP),
 	SND_PCI_QUIRK(0x17aa, 0x5013, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
diff --git a/sound/soc/codecs/arizona.c b/sound/soc/codecs/arizona.c
index b3ea24d..93b4008 100644
--- a/sound/soc/codecs/arizona.c
+++ b/sound/soc/codecs/arizona.c
@@ -1537,7 +1537,7 @@
 	bool reconfig;
 	unsigned int aif_tx_state, aif_rx_state;
 
-	if (params_rate(params) % 8000)
+	if (params_rate(params) % 4000)
 		rates = &arizona_44k1_bclk_rates[0];
 	else
 		rates = &arizona_48k_bclk_rates[0];
diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c
index ef76940..3e3c7f6 100644
--- a/sound/soc/codecs/rt5645.c
+++ b/sound/soc/codecs/rt5645.c
@@ -1667,9 +1667,13 @@
 			RT5645_PWR_CLS_D_L,
 			RT5645_PWR_CLS_D | RT5645_PWR_CLS_D_R |
 			RT5645_PWR_CLS_D_L);
+		snd_soc_update_bits(codec, RT5645_GEN_CTRL3,
+			RT5645_DET_CLK_MASK, RT5645_DET_CLK_MODE1);
 		break;
 
 	case SND_SOC_DAPM_PRE_PMD:
+		snd_soc_update_bits(codec, RT5645_GEN_CTRL3,
+			RT5645_DET_CLK_MASK, RT5645_DET_CLK_DIS);
 		snd_soc_write(codec, RT5645_EQ_CTRL2, 0);
 		snd_soc_update_bits(codec, RT5645_PWR_DIG1,
 			RT5645_PWR_CLS_D | RT5645_PWR_CLS_D_R |
diff --git a/sound/soc/codecs/rt5645.h b/sound/soc/codecs/rt5645.h
index 093e46d..205e071 100644
--- a/sound/soc/codecs/rt5645.h
+++ b/sound/soc/codecs/rt5645.h
@@ -2122,6 +2122,10 @@
 /* General Control3 (0xfc) */
 #define RT5645_JD_PSV_MODE			(0x1 << 12)
 #define RT5645_IRQ_CLK_GATE_CTRL		(0x1 << 11)
+#define RT5645_DET_CLK_MASK			(0x3 << 9)
+#define RT5645_DET_CLK_DIS			(0x0 << 9)
+#define RT5645_DET_CLK_MODE1			(0x1 << 9)
+#define RT5645_DET_CLK_MODE2			(0x2 << 9)
 #define RT5645_MICINDET_MANU			(0x1 << 7)
 #define RT5645_RING2_SLEEVE_GND			(0x1 << 5)
 
diff --git a/sound/soc/intel/skylake/skl-topology.c b/sound/soc/intel/skylake/skl-topology.c
index ffea427..ad4d0f8 100644
--- a/sound/soc/intel/skylake/skl-topology.c
+++ b/sound/soc/intel/skylake/skl-topology.c
@@ -1240,7 +1240,6 @@
 	 */
 	ret = snd_soc_tplg_component_load(&platform->component,
 					&skl_tplg_ops, fw, 0);
-	release_firmware(fw);
 	if (ret < 0) {
 		dev_err(bus->dev, "tplg component load failed%d\n", ret);
 		return -EINVAL;
@@ -1249,5 +1248,7 @@
 	skl->resource.max_mcps = SKL_MAX_MCPS;
 	skl->resource.max_mem = SKL_FW_MAX_MEM;
 
+	skl->tplg = fw;
+
 	return 0;
 }
diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c
index 5319529..caa69c4 100644
--- a/sound/soc/intel/skylake/skl.c
+++ b/sound/soc/intel/skylake/skl.c
@@ -25,6 +25,7 @@
 #include <linux/pci.h>
 #include <linux/pm_runtime.h>
 #include <linux/platform_device.h>
+#include <linux/firmware.h>
 #include <sound/pcm.h>
 #include "skl.h"
 
@@ -520,6 +521,9 @@
 	struct hdac_ext_bus *ebus = pci_get_drvdata(pci);
 	struct skl *skl = ebus_to_skl(ebus);
 
+	if (skl->tplg)
+		release_firmware(skl->tplg);
+
 	if (pci_dev_run_wake(pci))
 		pm_runtime_get_noresume(&pci->dev);
 	pci_dev_put(pci);
diff --git a/sound/soc/intel/skylake/skl.h b/sound/soc/intel/skylake/skl.h
index dd2e79a..a0709e3 100644
--- a/sound/soc/intel/skylake/skl.h
+++ b/sound/soc/intel/skylake/skl.h
@@ -68,6 +68,8 @@
 	struct skl_dsp_resource resource;
 	struct list_head ppl_list;
 	struct list_head dapm_path_list;
+
+	const struct firmware *tplg;
 };
 
 #define skl_to_ebus(s)	(&(s)->ebus)
diff --git a/tools/Makefile b/tools/Makefile
index 7dc820a..0ba0df3 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -96,7 +96,7 @@
 	$(call descend,$(@:_install=),install)
 
 selftests_install:
-	$(call descend,testing/$(@:_clean=),install)
+	$(call descend,testing/$(@:_install=),install)
 
 turbostat_install x86_energy_perf_policy_install:
 	$(call descend,power/x86/$(@:_install=),install)
diff --git a/tools/build/Makefile b/tools/build/Makefile
index a930362..0d5a0e3 100644
--- a/tools/build/Makefile
+++ b/tools/build/Makefile
@@ -25,7 +25,7 @@
 MAKEFLAGS := --no-print-directory
 build     := -f $(srctree)/tools/build/Makefile.build dir=. obj
 
-all: fixdep
+all: $(OUTPUT)fixdep
 
 clean:
 	$(call QUIET_CLEAN, fixdep)
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 37ff4c9..02db3cd 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -7,7 +7,7 @@
 
 feature_check = $(eval $(feature_check_code))
 define feature_check_code
-  feature-$(1) := $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS) $(FEATURE_CHECK_CFLAGS-$(1))" LDFLAGS="$(LDFLAGS) $(FEATURE_CHECK_LDFLAGS-$(1))" -C $(feature_dir) test-$1.bin >/dev/null 2>/dev/null && echo 1 || echo 0)
+  feature-$(1) := $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS) $(FEATURE_CHECK_CFLAGS-$(1))" LDFLAGS="$(LDFLAGS) $(FEATURE_CHECK_LDFLAGS-$(1))" -C $(feature_dir) $(OUTPUT_FEATURES)test-$1.bin >/dev/null 2>/dev/null && echo 1 || echo 0)
 endef
 
 feature_set = $(eval $(feature_set_code))
@@ -101,7 +101,6 @@
   #
   $(foreach feat,$(FEATURE_TESTS),$(call feature_set,$(feat)))
 else
-  $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS)" LDFLAGS=$(LDFLAGS) -i -j -C $(feature_dir) $(addsuffix .bin,$(FEATURE_TESTS)) >/dev/null 2>&1)
   $(foreach feat,$(FEATURE_TESTS),$(call feature_check,$(feat)))
 endif
 
@@ -123,13 +122,31 @@
     MSG = $(shell printf '...%30s: %s' $(1) $(2))
 endef
 
-FEATURE_DUMP_FILENAME = $(OUTPUT)FEATURE-DUMP$(FEATURE_USER)
-FEATURE_DUMP := $(foreach feat,$(FEATURE_DISPLAY),feature-$(feat)($(feature-$(feat))))
-FEATURE_DUMP_FILE := $(shell touch $(FEATURE_DUMP_FILENAME); cat $(FEATURE_DUMP_FILENAME))
+#
+# generates feature value assignment for name, like:
+#   $(call feature_assign,dwarf) == feature-dwarf=1
+#
+feature_assign = feature-$(1)=$(feature-$(1))
 
-ifeq ($(dwarf-post-unwind),1)
-  FEATURE_DUMP += dwarf-post-unwind($(dwarf-post-unwind-text))
-endif
+FEATURE_DUMP_FILENAME = $(OUTPUT)FEATURE-DUMP$(FEATURE_USER)
+FEATURE_DUMP := $(shell touch $(FEATURE_DUMP_FILENAME); cat $(FEATURE_DUMP_FILENAME))
+
+feature_dump_check = $(eval $(feature_dump_check_code))
+define feature_dump_check_code
+  ifeq ($(findstring $(1),$(FEATURE_DUMP)),)
+    $(2) := 1
+  endif
+endef
+
+#
+# First check if any test from FEATURE_DISPLAY
+# and set feature_display := 1 if it does
+$(foreach feat,$(FEATURE_DISPLAY),$(call feature_dump_check,$(call feature_assign,$(feat)),feature_display))
+
+#
+# Now also check if any other test changed,
+# so we force FEATURE-DUMP generation
+$(foreach feat,$(FEATURE_TESTS),$(call feature_dump_check,$(call feature_assign,$(feat)),feature_dump_changed))
 
 # The $(feature_display) controls the default detection message
 # output. It's set if:
@@ -138,13 +155,13 @@
 # - one of the $(FEATURE_DISPLAY) is not detected
 # - VF is enabled
 
-ifneq ("$(FEATURE_DUMP)","$(FEATURE_DUMP_FILE)")
-  $(shell echo "$(FEATURE_DUMP)" > $(FEATURE_DUMP_FILENAME))
-  feature_display := 1
+ifeq ($(feature_dump_changed),1)
+  $(shell rm -f $(FEATURE_DUMP_FILENAME))
+  $(foreach feat,$(FEATURE_TESTS),$(shell echo "$(call feature_assign,$(feat))" >> $(FEATURE_DUMP_FILENAME)))
 endif
 
 feature_display_check = $(eval $(feature_check_display_code))
-define feature_display_check_code
+define feature_check_display_code
   ifneq ($(feature-$(1)), 1)
     feature_display := 1
   endif
@@ -161,11 +178,6 @@
   $(info )
   $(info Auto-detecting system features:)
   $(foreach feat,$(FEATURE_DISPLAY),$(call feature_print_status,$(feat),))
-
-  ifeq ($(dwarf-post-unwind),1)
-    $(call feature_print_text,"DWARF post unwind library", $(dwarf-post-unwind-text))
-  endif
-
   ifneq ($(feature_verbose),1)
     $(info )
   endif
diff --git a/tools/build/Makefile.include b/tools/build/Makefile.include
index 4e09ad6..be630be 100644
--- a/tools/build/Makefile.include
+++ b/tools/build/Makefile.include
@@ -4,7 +4,7 @@
 fixdep:
 else
 fixdep:
-	$(Q)$(MAKE) -C $(srctree)/tools/build fixdep
+	$(Q)$(MAKE) -C $(srctree)/tools/build CFLAGS= LDFLAGS= $(OUTPUT)fixdep
 endif
 
 .PHONY: fixdep
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index cea04ce9..bf8f035 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -1,4 +1,3 @@
-
 FILES=					\
 	test-all.bin			\
 	test-backtrace.bin		\
@@ -38,38 +37,40 @@
 	test-bpf.bin			\
 	test-get_cpuid.bin
 
+FILES := $(addprefix $(OUTPUT),$(FILES))
+
 CC := $(CROSS_COMPILE)gcc -MD
 PKG_CONFIG := $(CROSS_COMPILE)pkg-config
 
 all: $(FILES)
 
-__BUILD = $(CC) $(CFLAGS) -Wall -Werror -o $(OUTPUT)$@ $(patsubst %.bin,%.c,$@) $(LDFLAGS)
-  BUILD = $(__BUILD) > $(OUTPUT)$(@:.bin=.make.output) 2>&1
+__BUILD = $(CC) $(CFLAGS) -Wall -Werror -o $@ $(patsubst %.bin,%.c,$(@F)) $(LDFLAGS)
+  BUILD = $(__BUILD) > $(@:.bin=.make.output) 2>&1
 
 ###############################
 
-test-all.bin:
+$(OUTPUT)test-all.bin:
 	$(BUILD) -fstack-protector-all -O2 -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -laudit -I/usr/include/slang -lslang $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz -llzma
 
-test-hello.bin:
+$(OUTPUT)test-hello.bin:
 	$(BUILD)
 
-test-pthread-attr-setaffinity-np.bin:
+$(OUTPUT)test-pthread-attr-setaffinity-np.bin:
 	$(BUILD) -D_GNU_SOURCE -lpthread
 
-test-stackprotector-all.bin:
+$(OUTPUT)test-stackprotector-all.bin:
 	$(BUILD) -fstack-protector-all
 
-test-fortify-source.bin:
+$(OUTPUT)test-fortify-source.bin:
 	$(BUILD) -O2 -D_FORTIFY_SOURCE=2
 
-test-bionic.bin:
+$(OUTPUT)test-bionic.bin:
 	$(BUILD)
 
-test-libelf.bin:
+$(OUTPUT)test-libelf.bin:
 	$(BUILD) -lelf
 
-test-glibc.bin:
+$(OUTPUT)test-glibc.bin:
 	$(BUILD)
 
 DWARFLIBS := -ldw
@@ -77,37 +78,37 @@
 DWARFLIBS += -lelf -lebl -lz -llzma -lbz2
 endif
 
-test-dwarf.bin:
+$(OUTPUT)test-dwarf.bin:
 	$(BUILD) $(DWARFLIBS)
 
-test-libelf-mmap.bin:
+$(OUTPUT)test-libelf-mmap.bin:
 	$(BUILD) -lelf
 
-test-libelf-getphdrnum.bin:
+$(OUTPUT)test-libelf-getphdrnum.bin:
 	$(BUILD) -lelf
 
-test-libnuma.bin:
+$(OUTPUT)test-libnuma.bin:
 	$(BUILD) -lnuma
 
-test-numa_num_possible_cpus.bin:
+$(OUTPUT)test-numa_num_possible_cpus.bin:
 	$(BUILD) -lnuma
 
-test-libunwind.bin:
+$(OUTPUT)test-libunwind.bin:
 	$(BUILD) -lelf
 
-test-libunwind-debug-frame.bin:
+$(OUTPUT)test-libunwind-debug-frame.bin:
 	$(BUILD) -lelf
 
-test-libaudit.bin:
+$(OUTPUT)test-libaudit.bin:
 	$(BUILD) -laudit
 
-test-libslang.bin:
+$(OUTPUT)test-libslang.bin:
 	$(BUILD) -I/usr/include/slang -lslang
 
-test-gtk2.bin:
+$(OUTPUT)test-gtk2.bin:
 	$(BUILD) $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null)
 
-test-gtk2-infobar.bin:
+$(OUTPUT)test-gtk2-infobar.bin:
 	$(BUILD) $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null)
 
 grep-libs  = $(filter -l%,$(1))
@@ -119,63 +120,63 @@
 PERL_EMBED_CCOPTS = `perl -MExtUtils::Embed -e ccopts 2>/dev/null`
 FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS)
 
-test-libperl.bin:
+$(OUTPUT)test-libperl.bin:
 	$(BUILD) $(FLAGS_PERL_EMBED)
 
-test-libpython.bin:
+$(OUTPUT)test-libpython.bin:
 	$(BUILD)
 
-test-libpython-version.bin:
+$(OUTPUT)test-libpython-version.bin:
 	$(BUILD)
 
-test-libbfd.bin:
+$(OUTPUT)test-libbfd.bin:
 	$(BUILD) -DPACKAGE='"perf"' -lbfd -lz -liberty -ldl
 
-test-liberty.bin:
-	$(CC) $(CFLAGS) -Wall -Werror -o $(OUTPUT)$@ test-libbfd.c -DPACKAGE='"perf"' $(LDFLAGS) -lbfd -ldl -liberty
+$(OUTPUT)test-liberty.bin:
+	$(CC) $(CFLAGS) -Wall -Werror -o $@ test-libbfd.c -DPACKAGE='"perf"' $(LDFLAGS) -lbfd -ldl -liberty
 
-test-liberty-z.bin:
-	$(CC) $(CFLAGS) -Wall -Werror -o $(OUTPUT)$@ test-libbfd.c -DPACKAGE='"perf"' $(LDFLAGS) -lbfd -ldl -liberty -lz
+$(OUTPUT)test-liberty-z.bin:
+	$(CC) $(CFLAGS) -Wall -Werror -o $@ test-libbfd.c -DPACKAGE='"perf"' $(LDFLAGS) -lbfd -ldl -liberty -lz
 
-test-cplus-demangle.bin:
+$(OUTPUT)test-cplus-demangle.bin:
 	$(BUILD) -liberty
 
-test-backtrace.bin:
+$(OUTPUT)test-backtrace.bin:
 	$(BUILD)
 
-test-timerfd.bin:
+$(OUTPUT)test-timerfd.bin:
 	$(BUILD)
 
-test-libdw-dwarf-unwind.bin:
+$(OUTPUT)test-libdw-dwarf-unwind.bin:
 	$(BUILD) # -ldw provided by $(FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind)
 
-test-libbabeltrace.bin:
+$(OUTPUT)test-libbabeltrace.bin:
 	$(BUILD) # -lbabeltrace provided by $(FEATURE_CHECK_LDFLAGS-libbabeltrace)
 
-test-sync-compare-and-swap.bin:
+$(OUTPUT)test-sync-compare-and-swap.bin:
 	$(BUILD)
 
-test-compile-32.bin:
-	$(CC) -m32 -o $(OUTPUT)$@ test-compile.c
+$(OUTPUT)test-compile-32.bin:
+	$(CC) -m32 -o $@ test-compile.c
 
-test-compile-x32.bin:
-	$(CC) -mx32 -o $(OUTPUT)$@ test-compile.c
+$(OUTPUT)test-compile-x32.bin:
+	$(CC) -mx32 -o $@ test-compile.c
 
-test-zlib.bin:
+$(OUTPUT)test-zlib.bin:
 	$(BUILD) -lz
 
-test-lzma.bin:
+$(OUTPUT)test-lzma.bin:
 	$(BUILD) -llzma
 
-test-get_cpuid.bin:
+$(OUTPUT)test-get_cpuid.bin:
 	$(BUILD)
 
-test-bpf.bin:
+$(OUTPUT)test-bpf.bin:
 	$(BUILD)
 
--include *.d
+-include $(OUTPUT)*.d
 
 ###############################
 
 clean:
-	rm -f $(FILES) *.d $(FILES:.bin=.make.output)
+	rm -f $(FILES) $(OUTPUT)*.d $(FILES:.bin=.make.output)
diff --git a/tools/perf/util/include/linux/bitmap.h b/tools/include/linux/bitmap.h
similarity index 94%
rename from tools/perf/util/include/linux/bitmap.h
rename to tools/include/linux/bitmap.h
index 40bd214..28f5493 100644
--- a/tools/perf/util/include/linux/bitmap.h
+++ b/tools/include/linux/bitmap.h
@@ -11,6 +11,8 @@
 void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
 		 const unsigned long *bitmap2, int bits);
 
+#define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1)))
+
 #define BITMAP_LAST_WORD_MASK(nbits)					\
 (									\
 	((nbits) % BITS_PER_LONG) ?					\
diff --git a/tools/include/linux/string.h b/tools/include/linux/string.h
new file mode 100644
index 0000000..e26223f
--- /dev/null
+++ b/tools/include/linux/string.h
@@ -0,0 +1,15 @@
+#ifndef _TOOLS_LINUX_STRING_H_
+#define _TOOLS_LINUX_STRING_H_
+
+
+#include <linux/types.h>	/* for size_t */
+
+void *memdup(const void *src, size_t len);
+
+int strtobool(const char *s, bool *res);
+
+#ifndef __UCLIBC__
+extern size_t strlcpy(char *dest, const char *src, size_t size);
+#endif
+
+#endif /* _LINUX_STRING_H_ */
diff --git a/tools/perf/util/bitmap.c b/tools/lib/bitmap.c
similarity index 100%
rename from tools/perf/util/bitmap.c
rename to tools/lib/bitmap.c
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index a3caaf3..919b717 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -71,7 +71,21 @@
 INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/arch/$(ARCH)/include/uapi -I$(srctree)/include/uapi
 FEATURE_CHECK_CFLAGS-bpf = $(INCLUDES)
 
+check_feat := 1
+NON_CHECK_FEAT_TARGETS := clean TAGS tags cscope help
+ifdef MAKECMDGOALS
+ifeq ($(filter-out $(NON_CHECK_FEAT_TARGETS),$(MAKECMDGOALS)),)
+  check_feat := 0
+endif
+endif
+
+ifeq ($(check_feat),1)
+ifeq ($(FEATURES_DUMP),)
 include $(srctree)/tools/build/Makefile.feature
+else
+include $(FEATURES_DUMP)
+endif
+endif
 
 export prefix libdir src obj
 
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index a633105..5bdc6ea 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -83,3 +83,17 @@
 	log_buf[0] = 0;
 	return sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
 }
+
+int bpf_map_update_elem(int fd, void *key, void *value,
+			u64 flags)
+{
+	union bpf_attr attr;
+
+	bzero(&attr, sizeof(attr));
+	attr.map_fd = fd;
+	attr.key = ptr_to_u64(key);
+	attr.value = ptr_to_u64(value);
+	attr.flags = flags;
+
+	return sys_bpf(BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr));
+}
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 854b736..a764655 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -20,4 +20,6 @@
 		     u32 kern_version, char *log_buf,
 		     size_t log_buf_sz);
 
+int bpf_map_update_elem(int fd, void *key, void *value,
+			u64 flags);
 #endif
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index e176bad..8334a5a 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -152,29 +152,36 @@
 	} *reloc_desc;
 	int nr_reloc;
 
-	int fd;
+	struct {
+		int nr;
+		int *fds;
+	} instances;
+	bpf_program_prep_t preprocessor;
 
 	struct bpf_object *obj;
 	void *priv;
 	bpf_program_clear_priv_t clear_priv;
 };
 
+struct bpf_map {
+	int fd;
+	char *name;
+	struct bpf_map_def def;
+	void *priv;
+	bpf_map_clear_priv_t clear_priv;
+};
+
 static LIST_HEAD(bpf_objects_list);
 
 struct bpf_object {
 	char license[64];
 	u32 kern_version;
-	void *maps_buf;
-	size_t maps_buf_sz;
 
 	struct bpf_program *programs;
 	size_t nr_programs;
-	int *map_fds;
-	/*
-	 * This field is required because maps_buf will be freed and
-	 * maps_buf_sz will be set to 0 after loaded.
-	 */
-	size_t nr_map_fds;
+	struct bpf_map *maps;
+	size_t nr_maps;
+
 	bool loaded;
 
 	/*
@@ -188,6 +195,7 @@
 		Elf *elf;
 		GElf_Ehdr ehdr;
 		Elf_Data *symbols;
+		size_t strtabidx;
 		struct {
 			GElf_Shdr shdr;
 			Elf_Data *data;
@@ -206,10 +214,25 @@
 
 static void bpf_program__unload(struct bpf_program *prog)
 {
+	int i;
+
 	if (!prog)
 		return;
 
-	zclose(prog->fd);
+	/*
+	 * If the object is opened but the program was never loaded,
+	 * it is possible that prog->instances.nr == -1.
+	 */
+	if (prog->instances.nr > 0) {
+		for (i = 0; i < prog->instances.nr; i++)
+			zclose(prog->instances.fds[i]);
+	} else if (prog->instances.nr != -1) {
+		pr_warning("Internal error: instances.nr is %d\n",
+			   prog->instances.nr);
+	}
+
+	prog->instances.nr = -1;
+	zfree(&prog->instances.fds);
 }
 
 static void bpf_program__exit(struct bpf_program *prog)
@@ -260,7 +283,8 @@
 	memcpy(prog->insns, data,
 	       prog->insns_cnt * sizeof(struct bpf_insn));
 	prog->idx = idx;
-	prog->fd = -1;
+	prog->instances.fds = NULL;
+	prog->instances.nr = -1;
 
 	return 0;
 errout:
@@ -469,21 +493,77 @@
 bpf_object__init_maps(struct bpf_object *obj, void *data,
 		      size_t size)
 {
-	if (size == 0) {
+	size_t nr_maps;
+	int i;
+
+	nr_maps = size / sizeof(struct bpf_map_def);
+	if (!data || !nr_maps) {
 		pr_debug("%s doesn't need map definition\n",
 			 obj->path);
 		return 0;
 	}
 
-	obj->maps_buf = malloc(size);
-	if (!obj->maps_buf) {
-		pr_warning("malloc maps failed: %s\n", obj->path);
+	pr_debug("maps in %s: %zd bytes\n", obj->path, size);
+
+	obj->maps = calloc(nr_maps, sizeof(obj->maps[0]));
+	if (!obj->maps) {
+		pr_warning("alloc maps for object failed\n");
 		return -ENOMEM;
 	}
+	obj->nr_maps = nr_maps;
 
-	obj->maps_buf_sz = size;
-	memcpy(obj->maps_buf, data, size);
-	pr_debug("maps in %s: %ld bytes\n", obj->path, (long)size);
+	for (i = 0; i < nr_maps; i++) {
+		struct bpf_map_def *def = &obj->maps[i].def;
+
+		/*
+		 * fill all fd with -1 so won't close incorrect
+		 * fd (fd=0 is stdin) when failure (zclose won't close
+		 * negative fd)).
+		 */
+		obj->maps[i].fd = -1;
+
+		/* Save map definition into obj->maps */
+		*def = ((struct bpf_map_def *)data)[i];
+	}
+	return 0;
+}
+
+static int
+bpf_object__init_maps_name(struct bpf_object *obj, int maps_shndx)
+{
+	int i;
+	Elf_Data *symbols = obj->efile.symbols;
+
+	if (!symbols || maps_shndx < 0)
+		return -EINVAL;
+
+	for (i = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) {
+		GElf_Sym sym;
+		size_t map_idx;
+		const char *map_name;
+
+		if (!gelf_getsym(symbols, i, &sym))
+			continue;
+		if (sym.st_shndx != maps_shndx)
+			continue;
+
+		map_name = elf_strptr(obj->efile.elf,
+				      obj->efile.strtabidx,
+				      sym.st_name);
+		map_idx = sym.st_value / sizeof(struct bpf_map_def);
+		if (map_idx >= obj->nr_maps) {
+			pr_warning("index of map \"%s\" is buggy: %zu > %zu\n",
+				   map_name, map_idx, obj->nr_maps);
+			continue;
+		}
+		obj->maps[map_idx].name = strdup(map_name);
+		if (!obj->maps[map_idx].name) {
+			pr_warning("failed to alloc map name\n");
+			return -ENOMEM;
+		}
+		pr_debug("map %zu is \"%s\"\n", map_idx,
+			 obj->maps[map_idx].name);
+	}
 	return 0;
 }
 
@@ -492,7 +572,7 @@
 	Elf *elf = obj->efile.elf;
 	GElf_Ehdr *ep = &obj->efile.ehdr;
 	Elf_Scn *scn = NULL;
-	int idx = 0, err = 0;
+	int idx = 0, err = 0, maps_shndx = -1;
 
 	/* Elf is corrupted/truncated, avoid calling elf_strptr. */
 	if (!elf_rawdata(elf_getscn(elf, ep->e_shstrndx), NULL)) {
@@ -542,16 +622,19 @@
 			err = bpf_object__init_kversion(obj,
 							data->d_buf,
 							data->d_size);
-		else if (strcmp(name, "maps") == 0)
+		else if (strcmp(name, "maps") == 0) {
 			err = bpf_object__init_maps(obj, data->d_buf,
 						    data->d_size);
-		else if (sh.sh_type == SHT_SYMTAB) {
+			maps_shndx = idx;
+		} else if (sh.sh_type == SHT_SYMTAB) {
 			if (obj->efile.symbols) {
 				pr_warning("bpf: multiple SYMTAB in %s\n",
 					   obj->path);
 				err = -LIBBPF_ERRNO__FORMAT;
-			} else
+			} else {
 				obj->efile.symbols = data;
+				obj->efile.strtabidx = sh.sh_link;
+			}
 		} else if ((sh.sh_type == SHT_PROGBITS) &&
 			   (sh.sh_flags & SHF_EXECINSTR) &&
 			   (data->d_size > 0)) {
@@ -586,6 +669,13 @@
 		if (err)
 			goto out;
 	}
+
+	if (!obj->efile.strtabidx || obj->efile.strtabidx >= idx) {
+		pr_warning("Corrupted ELF file: index of strtab invalid\n");
+		return LIBBPF_ERRNO__FORMAT;
+	}
+	if (maps_shndx >= 0)
+		err = bpf_object__init_maps_name(obj, maps_shndx);
 out:
 	return err;
 }
@@ -668,37 +758,15 @@
 bpf_object__create_maps(struct bpf_object *obj)
 {
 	unsigned int i;
-	size_t nr_maps;
-	int *pfd;
 
-	nr_maps = obj->maps_buf_sz / sizeof(struct bpf_map_def);
-	if (!obj->maps_buf || !nr_maps) {
-		pr_debug("don't need create maps for %s\n",
-			 obj->path);
-		return 0;
-	}
+	for (i = 0; i < obj->nr_maps; i++) {
+		struct bpf_map_def *def = &obj->maps[i].def;
+		int *pfd = &obj->maps[i].fd;
 
-	obj->map_fds = malloc(sizeof(int) * nr_maps);
-	if (!obj->map_fds) {
-		pr_warning("realloc perf_bpf_map_fds failed\n");
-		return -ENOMEM;
-	}
-	obj->nr_map_fds = nr_maps;
-
-	/* fill all fd with -1 */
-	memset(obj->map_fds, -1, sizeof(int) * nr_maps);
-
-	pfd = obj->map_fds;
-	for (i = 0; i < nr_maps; i++) {
-		struct bpf_map_def def;
-
-		def = *(struct bpf_map_def *)(obj->maps_buf +
-				i * sizeof(struct bpf_map_def));
-
-		*pfd = bpf_create_map(def.type,
-				      def.key_size,
-				      def.value_size,
-				      def.max_entries);
+		*pfd = bpf_create_map(def->type,
+				      def->key_size,
+				      def->value_size,
+				      def->max_entries);
 		if (*pfd < 0) {
 			size_t j;
 			int err = *pfd;
@@ -706,22 +774,17 @@
 			pr_warning("failed to create map: %s\n",
 				   strerror(errno));
 			for (j = 0; j < i; j++)
-				zclose(obj->map_fds[j]);
-			obj->nr_map_fds = 0;
-			zfree(&obj->map_fds);
+				zclose(obj->maps[j].fd);
 			return err;
 		}
 		pr_debug("create map: fd=%d\n", *pfd);
-		pfd++;
 	}
 
-	zfree(&obj->maps_buf);
-	obj->maps_buf_sz = 0;
 	return 0;
 }
 
 static int
-bpf_program__relocate(struct bpf_program *prog, int *map_fds)
+bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj)
 {
 	int i;
 
@@ -741,7 +804,7 @@
 			return -LIBBPF_ERRNO__RELOC;
 		}
 		insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD;
-		insns[insn_idx].imm = map_fds[map_idx];
+		insns[insn_idx].imm = obj->maps[map_idx].fd;
 	}
 
 	zfree(&prog->reloc_desc);
@@ -760,7 +823,7 @@
 	for (i = 0; i < obj->nr_programs; i++) {
 		prog = &obj->programs[i];
 
-		err = bpf_program__relocate(prog, obj->map_fds);
+		err = bpf_program__relocate(prog, obj);
 		if (err) {
 			pr_warning("failed to relocate '%s'\n",
 				   prog->section_name);
@@ -784,8 +847,7 @@
 		Elf_Data *data = obj->efile.reloc[i].data;
 		int idx = shdr->sh_info;
 		struct bpf_program *prog;
-		size_t nr_maps = obj->maps_buf_sz /
-				 sizeof(struct bpf_map_def);
+		size_t nr_maps = obj->nr_maps;
 
 		if (shdr->sh_type != SHT_REL) {
 			pr_warning("internal error at %d\n", __LINE__);
@@ -860,13 +922,73 @@
 bpf_program__load(struct bpf_program *prog,
 		  char *license, u32 kern_version)
 {
-	int err, fd;
+	int err = 0, fd, i;
 
-	err = load_program(prog->insns, prog->insns_cnt,
-			   license, kern_version, &fd);
-	if (!err)
-		prog->fd = fd;
+	if (prog->instances.nr < 0 || !prog->instances.fds) {
+		if (prog->preprocessor) {
+			pr_warning("Internal error: can't load program '%s'\n",
+				   prog->section_name);
+			return -LIBBPF_ERRNO__INTERNAL;
+		}
 
+		prog->instances.fds = malloc(sizeof(int));
+		if (!prog->instances.fds) {
+			pr_warning("Not enough memory for BPF fds\n");
+			return -ENOMEM;
+		}
+		prog->instances.nr = 1;
+		prog->instances.fds[0] = -1;
+	}
+
+	if (!prog->preprocessor) {
+		if (prog->instances.nr != 1) {
+			pr_warning("Program '%s' is inconsistent: nr(%d) != 1\n",
+				   prog->section_name, prog->instances.nr);
+		}
+		err = load_program(prog->insns, prog->insns_cnt,
+				   license, kern_version, &fd);
+		if (!err)
+			prog->instances.fds[0] = fd;
+		goto out;
+	}
+
+	for (i = 0; i < prog->instances.nr; i++) {
+		struct bpf_prog_prep_result result;
+		bpf_program_prep_t preprocessor = prog->preprocessor;
+
+		bzero(&result, sizeof(result));
+		err = preprocessor(prog, i, prog->insns,
+				   prog->insns_cnt, &result);
+		if (err) {
+			pr_warning("Preprocessing the %dth instance of program '%s' failed\n",
+				   i, prog->section_name);
+			goto out;
+		}
+
+		if (!result.new_insn_ptr || !result.new_insn_cnt) {
+			pr_debug("Skip loading the %dth instance of program '%s'\n",
+				 i, prog->section_name);
+			prog->instances.fds[i] = -1;
+			if (result.pfd)
+				*result.pfd = -1;
+			continue;
+		}
+
+		err = load_program(result.new_insn_ptr,
+				   result.new_insn_cnt,
+				   license, kern_version, &fd);
+
+		if (err) {
+			pr_warning("Loading the %dth instance of program '%s' failed\n",
+					i, prog->section_name);
+			goto out;
+		}
+
+		if (result.pfd)
+			*result.pfd = fd;
+		prog->instances.fds[i] = fd;
+	}
+out:
 	if (err)
 		pr_warning("failed to load program '%s'\n",
 			   prog->section_name);
@@ -970,10 +1092,8 @@
 	if (!obj)
 		return -EINVAL;
 
-	for (i = 0; i < obj->nr_map_fds; i++)
-		zclose(obj->map_fds[i]);
-	zfree(&obj->map_fds);
-	obj->nr_map_fds = 0;
+	for (i = 0; i < obj->nr_maps; i++)
+		zclose(obj->maps[i].fd);
 
 	for (i = 0; i < obj->nr_programs; i++)
 		bpf_program__unload(&obj->programs[i]);
@@ -1016,7 +1136,16 @@
 	bpf_object__elf_finish(obj);
 	bpf_object__unload(obj);
 
-	zfree(&obj->maps_buf);
+	for (i = 0; i < obj->nr_maps; i++) {
+		zfree(&obj->maps[i].name);
+		if (obj->maps[i].clear_priv)
+			obj->maps[i].clear_priv(&obj->maps[i],
+						obj->maps[i].priv);
+		obj->maps[i].priv = NULL;
+		obj->maps[i].clear_priv = NULL;
+	}
+	zfree(&obj->maps);
+	obj->nr_maps = 0;
 
 	if (obj->programs && obj->nr_programs) {
 		for (i = 0; i < obj->nr_programs; i++)
@@ -1121,5 +1250,142 @@
 
 int bpf_program__fd(struct bpf_program *prog)
 {
-	return prog->fd;
+	return bpf_program__nth_fd(prog, 0);
+}
+
+int bpf_program__set_prep(struct bpf_program *prog, int nr_instances,
+			  bpf_program_prep_t prep)
+{
+	int *instances_fds;
+
+	if (nr_instances <= 0 || !prep)
+		return -EINVAL;
+
+	if (prog->instances.nr > 0 || prog->instances.fds) {
+		pr_warning("Can't set pre-processor after loading\n");
+		return -EINVAL;
+	}
+
+	instances_fds = malloc(sizeof(int) * nr_instances);
+	if (!instances_fds) {
+		pr_warning("alloc memory failed for fds\n");
+		return -ENOMEM;
+	}
+
+	/* fill all fd with -1 */
+	memset(instances_fds, -1, sizeof(int) * nr_instances);
+
+	prog->instances.nr = nr_instances;
+	prog->instances.fds = instances_fds;
+	prog->preprocessor = prep;
+	return 0;
+}
+
+int bpf_program__nth_fd(struct bpf_program *prog, int n)
+{
+	int fd;
+
+	if (n >= prog->instances.nr || n < 0) {
+		pr_warning("Can't get the %dth fd from program %s: only %d instances\n",
+			   n, prog->section_name, prog->instances.nr);
+		return -EINVAL;
+	}
+
+	fd = prog->instances.fds[n];
+	if (fd < 0) {
+		pr_warning("%dth instance of program '%s' is invalid\n",
+			   n, prog->section_name);
+		return -ENOENT;
+	}
+
+	return fd;
+}
+
+int bpf_map__get_fd(struct bpf_map *map)
+{
+	if (!map)
+		return -EINVAL;
+
+	return map->fd;
+}
+
+int bpf_map__get_def(struct bpf_map *map, struct bpf_map_def *pdef)
+{
+	if (!map || !pdef)
+		return -EINVAL;
+
+	*pdef = map->def;
+	return 0;
+}
+
+const char *bpf_map__get_name(struct bpf_map *map)
+{
+	if (!map)
+		return NULL;
+	return map->name;
+}
+
+int bpf_map__set_private(struct bpf_map *map, void *priv,
+			 bpf_map_clear_priv_t clear_priv)
+{
+	if (!map)
+		return -EINVAL;
+
+	if (map->priv) {
+		if (map->clear_priv)
+			map->clear_priv(map, map->priv);
+	}
+
+	map->priv = priv;
+	map->clear_priv = clear_priv;
+	return 0;
+}
+
+int bpf_map__get_private(struct bpf_map *map, void **ppriv)
+{
+	if (!map)
+		return -EINVAL;
+
+	if (ppriv)
+		*ppriv = map->priv;
+	return 0;
+}
+
+struct bpf_map *
+bpf_map__next(struct bpf_map *prev, struct bpf_object *obj)
+{
+	size_t idx;
+	struct bpf_map *s, *e;
+
+	if (!obj || !obj->maps)
+		return NULL;
+
+	s = obj->maps;
+	e = obj->maps + obj->nr_maps;
+
+	if (prev == NULL)
+		return s;
+
+	if ((prev < s) || (prev >= e)) {
+		pr_warning("error in %s: map handler doesn't belong to object\n",
+			   __func__);
+		return NULL;
+	}
+
+	idx = (prev - obj->maps) + 1;
+	if (idx >= obj->nr_maps)
+		return NULL;
+	return &obj->maps[idx];
+}
+
+struct bpf_map *
+bpf_object__get_map_by_name(struct bpf_object *obj, const char *name)
+{
+	struct bpf_map *pos;
+
+	bpf_map__for_each(pos, obj) {
+		if (pos->name && !strcmp(pos->name, name))
+			return pos;
+	}
+	return NULL;
 }
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index c9a9aef..a51594c 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -88,6 +88,70 @@
 
 int bpf_program__fd(struct bpf_program *prog);
 
+struct bpf_insn;
+
+/*
+ * Libbpf allows callers to adjust BPF programs before being loaded
+ * into kernel. One program in an object file can be transform into
+ * multiple variants to be attached to different code.
+ *
+ * bpf_program_prep_t, bpf_program__set_prep and bpf_program__nth_fd
+ * are APIs for this propose.
+ *
+ * - bpf_program_prep_t:
+ *   It defines 'preprocessor', which is a caller defined function
+ *   passed to libbpf through bpf_program__set_prep(), and will be
+ *   called before program is loaded. The processor should adjust
+ *   the program one time for each instances according to the number
+ *   passed to it.
+ *
+ * - bpf_program__set_prep:
+ *   Attachs a preprocessor to a BPF program. The number of instances
+ *   whould be created is also passed through this function.
+ *
+ * - bpf_program__nth_fd:
+ *   After the program is loaded, get resuling fds from bpf program for
+ *   each instances.
+ *
+ * If bpf_program__set_prep() is not used, the program whould be loaded
+ * without adjustment during bpf_object__load(). The program has only
+ * one instance. In this case bpf_program__fd(prog) is equal to
+ * bpf_program__nth_fd(prog, 0).
+ */
+
+struct bpf_prog_prep_result {
+	/*
+	 * If not NULL, load new instruction array.
+	 * If set to NULL, don't load this instance.
+	 */
+	struct bpf_insn *new_insn_ptr;
+	int new_insn_cnt;
+
+	/* If not NULL, result fd is set to it */
+	int *pfd;
+};
+
+/*
+ * Parameters of bpf_program_prep_t:
+ *  - prog:	The bpf_program being loaded.
+ *  - n:	Index of instance being generated.
+ *  - insns:	BPF instructions array.
+ *  - insns_cnt:Number of instructions in insns.
+ *  - res:	Output parameter, result of transformation.
+ *
+ * Return value:
+ *  - Zero: pre-processing success.
+ *  - Non-zero: pre-processing, stop loading.
+ */
+typedef int (*bpf_program_prep_t)(struct bpf_program *prog, int n,
+				  struct bpf_insn *insns, int insns_cnt,
+				  struct bpf_prog_prep_result *res);
+
+int bpf_program__set_prep(struct bpf_program *prog, int nr_instance,
+			  bpf_program_prep_t prep);
+
+int bpf_program__nth_fd(struct bpf_program *prog, int n);
+
 /*
  * We don't need __attribute__((packed)) now since it is
  * unnecessary for 'bpf_map_def' because they are all aligned.
@@ -101,4 +165,28 @@
 	unsigned int max_entries;
 };
 
+/*
+ * There is another 'struct bpf_map' in include/linux/map.h. However,
+ * it is not a uapi header so no need to consider name clash.
+ */
+struct bpf_map;
+struct bpf_map *
+bpf_object__get_map_by_name(struct bpf_object *obj, const char *name);
+
+struct bpf_map *
+bpf_map__next(struct bpf_map *map, struct bpf_object *obj);
+#define bpf_map__for_each(pos, obj)		\
+	for ((pos) = bpf_map__next(NULL, (obj));	\
+	     (pos) != NULL;				\
+	     (pos) = bpf_map__next((pos), (obj)))
+
+int bpf_map__get_fd(struct bpf_map *map);
+int bpf_map__get_def(struct bpf_map *map, struct bpf_map_def *pdef);
+const char *bpf_map__get_name(struct bpf_map *map);
+
+typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *);
+int bpf_map__set_private(struct bpf_map *map, void *priv,
+			 bpf_map_clear_priv_t clear_priv);
+int bpf_map__get_private(struct bpf_map *map, void **ppriv);
+
 #endif
diff --git a/tools/lib/find_bit.c b/tools/lib/find_bit.c
new file mode 100644
index 0000000..9122a9e
--- /dev/null
+++ b/tools/lib/find_bit.c
@@ -0,0 +1,84 @@
+/* bit search implementation
+ *
+ * Copied from lib/find_bit.c to tools/lib/find_bit.c
+ *
+ * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * Copyright (C) 2008 IBM Corporation
+ * 'find_last_bit' is written by Rusty Russell <rusty@rustcorp.com.au>
+ * (Inspired by David Howell's find_next_bit implementation)
+ *
+ * Rewritten by Yury Norov <yury.norov@gmail.com> to decrease
+ * size and improve performance, 2015.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/bitops.h>
+#include <linux/bitmap.h>
+#include <linux/kernel.h>
+
+#if !defined(find_next_bit)
+
+/*
+ * This is a common helper function for find_next_bit and
+ * find_next_zero_bit.  The difference is the "invert" argument, which
+ * is XORed with each fetched word before searching it for one bits.
+ */
+static unsigned long _find_next_bit(const unsigned long *addr,
+		unsigned long nbits, unsigned long start, unsigned long invert)
+{
+	unsigned long tmp;
+
+	if (!nbits || start >= nbits)
+		return nbits;
+
+	tmp = addr[start / BITS_PER_LONG] ^ invert;
+
+	/* Handle 1st word. */
+	tmp &= BITMAP_FIRST_WORD_MASK(start);
+	start = round_down(start, BITS_PER_LONG);
+
+	while (!tmp) {
+		start += BITS_PER_LONG;
+		if (start >= nbits)
+			return nbits;
+
+		tmp = addr[start / BITS_PER_LONG] ^ invert;
+	}
+
+	return min(start + __ffs(tmp), nbits);
+}
+#endif
+
+#ifndef find_next_bit
+/*
+ * Find the next set bit in a memory region.
+ */
+unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
+			    unsigned long offset)
+{
+	return _find_next_bit(addr, size, offset, 0UL);
+}
+#endif
+
+#ifndef find_first_bit
+/*
+ * Find the first set bit in a memory region.
+ */
+unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
+{
+	unsigned long idx;
+
+	for (idx = 0; idx * BITS_PER_LONG < size; idx++) {
+		if (addr[idx])
+			return min(idx * BITS_PER_LONG + __ffs(addr[idx]), size);
+	}
+
+	return size;
+}
+#endif
diff --git a/tools/lib/string.c b/tools/lib/string.c
new file mode 100644
index 0000000..bd239bc
--- /dev/null
+++ b/tools/lib/string.c
@@ -0,0 +1,89 @@
+/*
+ *  linux/tools/lib/string.c
+ *
+ *  Copied from linux/lib/string.c, where it is:
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ *  More specifically, the first copied function was strtobool, which
+ *  was introduced by:
+ *
+ *  d0f1fed29e6e ("Add a strtobool function matching semantics of existing in kernel equivalents")
+ *  Author: Jonathan Cameron <jic23@cam.ac.uk>
+ */
+
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <linux/string.h>
+#include <linux/compiler.h>
+
+/**
+ * memdup - duplicate region of memory
+ *
+ * @src: memory region to duplicate
+ * @len: memory region length
+ */
+void *memdup(const void *src, size_t len)
+{
+	void *p = malloc(len);
+
+	if (p)
+		memcpy(p, src, len);
+
+	return p;
+}
+
+/**
+ * strtobool - convert common user inputs into boolean values
+ * @s: input string
+ * @res: result
+ *
+ * This routine returns 0 iff the first character is one of 'Yy1Nn0'.
+ * Otherwise it will return -EINVAL.  Value pointed to by res is
+ * updated upon finding a match.
+ */
+int strtobool(const char *s, bool *res)
+{
+	switch (s[0]) {
+	case 'y':
+	case 'Y':
+	case '1':
+		*res = true;
+		break;
+	case 'n':
+	case 'N':
+	case '0':
+		*res = false;
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+/**
+ * strlcpy - Copy a C-string into a sized buffer
+ * @dest: Where to copy the string to
+ * @src: Where to copy the string from
+ * @size: size of destination buffer
+ *
+ * Compatible with *BSD: the result is always a valid
+ * NUL-terminated string that fits in the buffer (unless,
+ * of course, the buffer size is zero). It does not pad
+ * out the result like strncpy() does.
+ *
+ * If libc has strlcpy() then that version will override this
+ * implementation:
+ */
+size_t __weak strlcpy(char *dest, const char *src, size_t size)
+{
+	size_t ret = strlen(src);
+
+	if (size) {
+		size_t len = (ret >= size) ? size - 1 : ret;
+		memcpy(dest, src, len);
+		dest[len] = '\0';
+	}
+	return ret;
+}
diff --git a/tools/lib/subcmd/Build b/tools/lib/subcmd/Build
new file mode 100644
index 0000000..ee31288
--- /dev/null
+++ b/tools/lib/subcmd/Build
@@ -0,0 +1,7 @@
+libsubcmd-y += exec-cmd.o
+libsubcmd-y += help.o
+libsubcmd-y += pager.o
+libsubcmd-y += parse-options.o
+libsubcmd-y += run-command.o
+libsubcmd-y += sigchain.o
+libsubcmd-y += subcmd-config.o
diff --git a/tools/lib/subcmd/Makefile b/tools/lib/subcmd/Makefile
new file mode 100644
index 0000000..629cf8c
--- /dev/null
+++ b/tools/lib/subcmd/Makefile
@@ -0,0 +1,48 @@
+include ../../scripts/Makefile.include
+include ../../perf/config/utilities.mak		# QUIET_CLEAN
+
+ifeq ($(srctree),)
+srctree := $(patsubst %/,%,$(dir $(shell pwd)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+#$(info Determined 'srctree' to be $(srctree))
+endif
+
+CC = $(CROSS_COMPILE)gcc
+AR = $(CROSS_COMPILE)ar
+RM = rm -f
+
+MAKEFLAGS += --no-print-directory
+
+LIBFILE = $(OUTPUT)libsubcmd.a
+
+CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
+CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -Werror -O6 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
+CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
+
+CFLAGS += -I$(srctree)/tools/include/
+CFLAGS += -I$(srctree)/include/uapi
+CFLAGS += -I$(srctree)/include
+
+SUBCMD_IN := $(OUTPUT)libsubcmd-in.o
+
+all:
+
+export srctree OUTPUT CC LD CFLAGS V
+include $(srctree)/tools/build/Makefile.include
+
+all: fixdep $(LIBFILE)
+
+$(SUBCMD_IN): FORCE
+	@$(MAKE) $(build)=libsubcmd
+
+$(LIBFILE): $(SUBCMD_IN)
+	$(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(SUBCMD_IN)
+
+clean:
+	$(call QUIET_CLEAN, libsubcmd) $(RM) $(LIBFILE); \
+	find $(if $(OUTPUT),$(OUTPUT),.) -name \*.o -or -name \*.o.cmd -or -name \*.o.d | xargs $(RM)
+
+FORCE:
+
+.PHONY: clean FORCE
diff --git a/tools/lib/subcmd/exec-cmd.c b/tools/lib/subcmd/exec-cmd.c
new file mode 100644
index 0000000..1ae833a
--- /dev/null
+++ b/tools/lib/subcmd/exec-cmd.c
@@ -0,0 +1,209 @@
+#include <linux/compiler.h>
+#include <linux/string.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <string.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include "subcmd-util.h"
+#include "exec-cmd.h"
+#include "subcmd-config.h"
+
+#define MAX_ARGS	32
+#define PATH_MAX	4096
+
+static const char *argv_exec_path;
+static const char *argv0_path;
+
+void exec_cmd_init(const char *exec_name, const char *prefix,
+		   const char *exec_path, const char *exec_path_env)
+{
+	subcmd_config.exec_name		= exec_name;
+	subcmd_config.prefix		= prefix;
+	subcmd_config.exec_path		= exec_path;
+	subcmd_config.exec_path_env	= exec_path_env;
+}
+
+#define is_dir_sep(c) ((c) == '/')
+
+static int is_absolute_path(const char *path)
+{
+	return path[0] == '/';
+}
+
+static const char *get_pwd_cwd(void)
+{
+	static char cwd[PATH_MAX + 1];
+	char *pwd;
+	struct stat cwd_stat, pwd_stat;
+	if (getcwd(cwd, PATH_MAX) == NULL)
+		return NULL;
+	pwd = getenv("PWD");
+	if (pwd && strcmp(pwd, cwd)) {
+		stat(cwd, &cwd_stat);
+		if (!stat(pwd, &pwd_stat) &&
+		    pwd_stat.st_dev == cwd_stat.st_dev &&
+		    pwd_stat.st_ino == cwd_stat.st_ino) {
+			strlcpy(cwd, pwd, PATH_MAX);
+		}
+	}
+	return cwd;
+}
+
+static const char *make_nonrelative_path(const char *path)
+{
+	static char buf[PATH_MAX + 1];
+
+	if (is_absolute_path(path)) {
+		if (strlcpy(buf, path, PATH_MAX) >= PATH_MAX)
+			die("Too long path: %.*s", 60, path);
+	} else {
+		const char *cwd = get_pwd_cwd();
+		if (!cwd)
+			die("Cannot determine the current working directory");
+		if (snprintf(buf, PATH_MAX, "%s/%s", cwd, path) >= PATH_MAX)
+			die("Too long path: %.*s", 60, path);
+	}
+	return buf;
+}
+
+char *system_path(const char *path)
+{
+	char *buf = NULL;
+
+	if (is_absolute_path(path))
+		return strdup(path);
+
+	astrcatf(&buf, "%s/%s", subcmd_config.prefix, path);
+
+	return buf;
+}
+
+const char *extract_argv0_path(const char *argv0)
+{
+	const char *slash;
+
+	if (!argv0 || !*argv0)
+		return NULL;
+	slash = argv0 + strlen(argv0);
+
+	while (argv0 <= slash && !is_dir_sep(*slash))
+		slash--;
+
+	if (slash >= argv0) {
+		argv0_path = strndup(argv0, slash - argv0);
+		return argv0_path ? slash + 1 : NULL;
+	}
+
+	return argv0;
+}
+
+void set_argv_exec_path(const char *exec_path)
+{
+	argv_exec_path = exec_path;
+	/*
+	 * Propagate this setting to external programs.
+	 */
+	setenv(subcmd_config.exec_path_env, exec_path, 1);
+}
+
+
+/* Returns the highest-priority location to look for subprograms. */
+char *get_argv_exec_path(void)
+{
+	char *env;
+
+	if (argv_exec_path)
+		return strdup(argv_exec_path);
+
+	env = getenv(subcmd_config.exec_path_env);
+	if (env && *env)
+		return strdup(env);
+
+	return system_path(subcmd_config.exec_path);
+}
+
+static void add_path(char **out, const char *path)
+{
+	if (path && *path) {
+		if (is_absolute_path(path))
+			astrcat(out, path);
+		else
+			astrcat(out, make_nonrelative_path(path));
+
+		astrcat(out, ":");
+	}
+}
+
+void setup_path(void)
+{
+	const char *old_path = getenv("PATH");
+	char *new_path = NULL;
+	char *tmp = get_argv_exec_path();
+
+	add_path(&new_path, tmp);
+	add_path(&new_path, argv0_path);
+	free(tmp);
+
+	if (old_path)
+		astrcat(&new_path, old_path);
+	else
+		astrcat(&new_path, "/usr/local/bin:/usr/bin:/bin");
+
+	setenv("PATH", new_path, 1);
+
+	free(new_path);
+}
+
+static const char **prepare_exec_cmd(const char **argv)
+{
+	int argc;
+	const char **nargv;
+
+	for (argc = 0; argv[argc]; argc++)
+		; /* just counting */
+	nargv = malloc(sizeof(*nargv) * (argc + 2));
+
+	nargv[0] = subcmd_config.exec_name;
+	for (argc = 0; argv[argc]; argc++)
+		nargv[argc + 1] = argv[argc];
+	nargv[argc + 1] = NULL;
+	return nargv;
+}
+
+int execv_cmd(const char **argv) {
+	const char **nargv = prepare_exec_cmd(argv);
+
+	/* execvp() can only ever return if it fails */
+	execvp(subcmd_config.exec_name, (char **)nargv);
+
+	free(nargv);
+	return -1;
+}
+
+
+int execl_cmd(const char *cmd,...)
+{
+	int argc;
+	const char *argv[MAX_ARGS + 1];
+	const char *arg;
+	va_list param;
+
+	va_start(param, cmd);
+	argv[0] = cmd;
+	argc = 1;
+	while (argc < MAX_ARGS) {
+		arg = argv[argc++] = va_arg(param, char *);
+		if (!arg)
+			break;
+	}
+	va_end(param);
+	if (MAX_ARGS <= argc) {
+		fprintf(stderr, " Error: too many args to run %s\n", cmd);
+		return -1;
+	}
+
+	argv[argc] = NULL;
+	return execv_cmd(argv);
+}
diff --git a/tools/lib/subcmd/exec-cmd.h b/tools/lib/subcmd/exec-cmd.h
new file mode 100644
index 0000000..5d08bda
--- /dev/null
+++ b/tools/lib/subcmd/exec-cmd.h
@@ -0,0 +1,16 @@
+#ifndef __SUBCMD_EXEC_CMD_H
+#define __SUBCMD_EXEC_CMD_H
+
+extern void exec_cmd_init(const char *exec_name, const char *prefix,
+			  const char *exec_path, const char *exec_path_env);
+
+extern void set_argv_exec_path(const char *exec_path);
+extern const char *extract_argv0_path(const char *path);
+extern void setup_path(void);
+extern int execv_cmd(const char **argv); /* NULL terminated */
+extern int execl_cmd(const char *cmd, ...);
+/* get_argv_exec_path and system_path return malloc'd string, caller must free it */
+extern char *get_argv_exec_path(void);
+extern char *system_path(const char *path);
+
+#endif /* __SUBCMD_EXEC_CMD_H */
diff --git a/tools/lib/subcmd/help.c b/tools/lib/subcmd/help.c
new file mode 100644
index 0000000..e228c3c
--- /dev/null
+++ b/tools/lib/subcmd/help.c
@@ -0,0 +1,268 @@
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <termios.h>
+#include <sys/ioctl.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <dirent.h>
+#include "subcmd-util.h"
+#include "help.h"
+#include "exec-cmd.h"
+
+void add_cmdname(struct cmdnames *cmds, const char *name, size_t len)
+{
+	struct cmdname *ent = malloc(sizeof(*ent) + len + 1);
+
+	ent->len = len;
+	memcpy(ent->name, name, len);
+	ent->name[len] = 0;
+
+	ALLOC_GROW(cmds->names, cmds->cnt + 1, cmds->alloc);
+	cmds->names[cmds->cnt++] = ent;
+}
+
+void clean_cmdnames(struct cmdnames *cmds)
+{
+	unsigned int i;
+
+	for (i = 0; i < cmds->cnt; ++i)
+		zfree(&cmds->names[i]);
+	zfree(&cmds->names);
+	cmds->cnt = 0;
+	cmds->alloc = 0;
+}
+
+int cmdname_compare(const void *a_, const void *b_)
+{
+	struct cmdname *a = *(struct cmdname **)a_;
+	struct cmdname *b = *(struct cmdname **)b_;
+	return strcmp(a->name, b->name);
+}
+
+void uniq(struct cmdnames *cmds)
+{
+	unsigned int i, j;
+
+	if (!cmds->cnt)
+		return;
+
+	for (i = j = 1; i < cmds->cnt; i++)
+		if (strcmp(cmds->names[i]->name, cmds->names[i-1]->name))
+			cmds->names[j++] = cmds->names[i];
+
+	cmds->cnt = j;
+}
+
+void exclude_cmds(struct cmdnames *cmds, struct cmdnames *excludes)
+{
+	size_t ci, cj, ei;
+	int cmp;
+
+	ci = cj = ei = 0;
+	while (ci < cmds->cnt && ei < excludes->cnt) {
+		cmp = strcmp(cmds->names[ci]->name, excludes->names[ei]->name);
+		if (cmp < 0)
+			cmds->names[cj++] = cmds->names[ci++];
+		else if (cmp == 0)
+			ci++, ei++;
+		else if (cmp > 0)
+			ei++;
+	}
+
+	while (ci < cmds->cnt)
+		cmds->names[cj++] = cmds->names[ci++];
+
+	cmds->cnt = cj;
+}
+
+static void get_term_dimensions(struct winsize *ws)
+{
+	char *s = getenv("LINES");
+
+	if (s != NULL) {
+		ws->ws_row = atoi(s);
+		s = getenv("COLUMNS");
+		if (s != NULL) {
+			ws->ws_col = atoi(s);
+			if (ws->ws_row && ws->ws_col)
+				return;
+		}
+	}
+#ifdef TIOCGWINSZ
+	if (ioctl(1, TIOCGWINSZ, ws) == 0 &&
+	    ws->ws_row && ws->ws_col)
+		return;
+#endif
+	ws->ws_row = 25;
+	ws->ws_col = 80;
+}
+
+static void pretty_print_string_list(struct cmdnames *cmds, int longest)
+{
+	int cols = 1, rows;
+	int space = longest + 1; /* min 1 SP between words */
+	struct winsize win;
+	int max_cols;
+	int i, j;
+
+	get_term_dimensions(&win);
+	max_cols = win.ws_col - 1; /* don't print *on* the edge */
+
+	if (space < max_cols)
+		cols = max_cols / space;
+	rows = (cmds->cnt + cols - 1) / cols;
+
+	for (i = 0; i < rows; i++) {
+		printf("  ");
+
+		for (j = 0; j < cols; j++) {
+			unsigned int n = j * rows + i;
+			unsigned int size = space;
+
+			if (n >= cmds->cnt)
+				break;
+			if (j == cols-1 || n + rows >= cmds->cnt)
+				size = 1;
+			printf("%-*s", size, cmds->names[n]->name);
+		}
+		putchar('\n');
+	}
+}
+
+static int is_executable(const char *name)
+{
+	struct stat st;
+
+	if (stat(name, &st) || /* stat, not lstat */
+	    !S_ISREG(st.st_mode))
+		return 0;
+
+	return st.st_mode & S_IXUSR;
+}
+
+static int has_extension(const char *filename, const char *ext)
+{
+	size_t len = strlen(filename);
+	size_t extlen = strlen(ext);
+
+	return len > extlen && !memcmp(filename + len - extlen, ext, extlen);
+}
+
+static void list_commands_in_dir(struct cmdnames *cmds,
+					 const char *path,
+					 const char *prefix)
+{
+	int prefix_len;
+	DIR *dir = opendir(path);
+	struct dirent *de;
+	char *buf = NULL;
+
+	if (!dir)
+		return;
+	if (!prefix)
+		prefix = "perf-";
+	prefix_len = strlen(prefix);
+
+	astrcatf(&buf, "%s/", path);
+
+	while ((de = readdir(dir)) != NULL) {
+		int entlen;
+
+		if (prefixcmp(de->d_name, prefix))
+			continue;
+
+		astrcat(&buf, de->d_name);
+		if (!is_executable(buf))
+			continue;
+
+		entlen = strlen(de->d_name) - prefix_len;
+		if (has_extension(de->d_name, ".exe"))
+			entlen -= 4;
+
+		add_cmdname(cmds, de->d_name + prefix_len, entlen);
+	}
+	closedir(dir);
+	free(buf);
+}
+
+void load_command_list(const char *prefix,
+		struct cmdnames *main_cmds,
+		struct cmdnames *other_cmds)
+{
+	const char *env_path = getenv("PATH");
+	char *exec_path = get_argv_exec_path();
+
+	if (exec_path) {
+		list_commands_in_dir(main_cmds, exec_path, prefix);
+		qsort(main_cmds->names, main_cmds->cnt,
+		      sizeof(*main_cmds->names), cmdname_compare);
+		uniq(main_cmds);
+	}
+
+	if (env_path) {
+		char *paths, *path, *colon;
+		path = paths = strdup(env_path);
+		while (1) {
+			if ((colon = strchr(path, ':')))
+				*colon = 0;
+			if (!exec_path || strcmp(path, exec_path))
+				list_commands_in_dir(other_cmds, path, prefix);
+
+			if (!colon)
+				break;
+			path = colon + 1;
+		}
+		free(paths);
+
+		qsort(other_cmds->names, other_cmds->cnt,
+		      sizeof(*other_cmds->names), cmdname_compare);
+		uniq(other_cmds);
+	}
+	free(exec_path);
+	exclude_cmds(other_cmds, main_cmds);
+}
+
+void list_commands(const char *title, struct cmdnames *main_cmds,
+		   struct cmdnames *other_cmds)
+{
+	unsigned int i, longest = 0;
+
+	for (i = 0; i < main_cmds->cnt; i++)
+		if (longest < main_cmds->names[i]->len)
+			longest = main_cmds->names[i]->len;
+	for (i = 0; i < other_cmds->cnt; i++)
+		if (longest < other_cmds->names[i]->len)
+			longest = other_cmds->names[i]->len;
+
+	if (main_cmds->cnt) {
+		char *exec_path = get_argv_exec_path();
+		printf("available %s in '%s'\n", title, exec_path);
+		printf("----------------");
+		mput_char('-', strlen(title) + strlen(exec_path));
+		putchar('\n');
+		pretty_print_string_list(main_cmds, longest);
+		putchar('\n');
+		free(exec_path);
+	}
+
+	if (other_cmds->cnt) {
+		printf("%s available from elsewhere on your $PATH\n", title);
+		printf("---------------------------------------");
+		mput_char('-', strlen(title));
+		putchar('\n');
+		pretty_print_string_list(other_cmds, longest);
+		putchar('\n');
+	}
+}
+
+int is_in_cmdlist(struct cmdnames *c, const char *s)
+{
+	unsigned int i;
+
+	for (i = 0; i < c->cnt; i++)
+		if (!strcmp(s, c->names[i]->name))
+			return 1;
+	return 0;
+}
diff --git a/tools/perf/util/help.h b/tools/lib/subcmd/help.h
similarity index 73%
rename from tools/perf/util/help.h
rename to tools/lib/subcmd/help.h
index 7f5c6de..e145a02 100644
--- a/tools/perf/util/help.h
+++ b/tools/lib/subcmd/help.h
@@ -1,12 +1,14 @@
-#ifndef __PERF_HELP_H
-#define __PERF_HELP_H
+#ifndef __SUBCMD_HELP_H
+#define __SUBCMD_HELP_H
+
+#include <sys/types.h>
 
 struct cmdnames {
 	size_t alloc;
 	size_t cnt;
 	struct cmdname {
 		size_t len; /* also used for similarity index in help.c */
-		char name[FLEX_ARRAY];
+		char name[];
 	} **names;
 };
 
@@ -20,10 +22,13 @@
 		struct cmdnames *main_cmds,
 		struct cmdnames *other_cmds);
 void add_cmdname(struct cmdnames *cmds, const char *name, size_t len);
+void clean_cmdnames(struct cmdnames *cmds);
+int cmdname_compare(const void *a, const void *b);
+void uniq(struct cmdnames *cmds);
 /* Here we require that excludes is a sorted list. */
 void exclude_cmds(struct cmdnames *cmds, struct cmdnames *excludes);
 int is_in_cmdlist(struct cmdnames *c, const char *s);
 void list_commands(const char *title, struct cmdnames *main_cmds,
 		   struct cmdnames *other_cmds);
 
-#endif /* __PERF_HELP_H */
+#endif /* __SUBCMD_HELP_H */
diff --git a/tools/perf/util/pager.c b/tools/lib/subcmd/pager.c
similarity index 84%
rename from tools/perf/util/pager.c
rename to tools/lib/subcmd/pager.c
index 53ef006..d50f3b58 100644
--- a/tools/perf/util/pager.c
+++ b/tools/lib/subcmd/pager.c
@@ -1,6 +1,12 @@
-#include "cache.h"
+#include <sys/select.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <signal.h>
+#include "pager.h"
 #include "run-command.h"
 #include "sigchain.h"
+#include "subcmd-config.h"
 
 /*
  * This is split up from the rest of git so that we can do
@@ -9,6 +15,11 @@
 
 static int spawned_pager;
 
+void pager_init(const char *pager_env)
+{
+	subcmd_config.pager_env = pager_env;
+}
+
 static void pager_preexec(void)
 {
 	/*
@@ -46,7 +57,7 @@
 
 void setup_pager(void)
 {
-	const char *pager = getenv("PERF_PAGER");
+	const char *pager = getenv(subcmd_config.pager_env);
 
 	if (!isatty(1))
 		return;
@@ -85,11 +96,5 @@
 
 int pager_in_use(void)
 {
-	const char *env;
-
-	if (spawned_pager)
-		return 1;
-
-	env = getenv("PERF_PAGER_IN_USE");
-	return env ? perf_config_bool("PERF_PAGER_IN_USE", env) : 0;
+	return spawned_pager;
 }
diff --git a/tools/lib/subcmd/pager.h b/tools/lib/subcmd/pager.h
new file mode 100644
index 0000000..8b83714
--- /dev/null
+++ b/tools/lib/subcmd/pager.h
@@ -0,0 +1,9 @@
+#ifndef __SUBCMD_PAGER_H
+#define __SUBCMD_PAGER_H
+
+extern void pager_init(const char *pager_env);
+
+extern void setup_pager(void);
+extern int pager_in_use(void);
+
+#endif /* __SUBCMD_PAGER_H */
diff --git a/tools/perf/util/parse-options.c b/tools/lib/subcmd/parse-options.c
similarity index 78%
rename from tools/perf/util/parse-options.c
rename to tools/lib/subcmd/parse-options.c
index 9fca092..981bb44 100644
--- a/tools/perf/util/parse-options.c
+++ b/tools/lib/subcmd/parse-options.c
@@ -1,37 +1,66 @@
-#include "util.h"
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdint.h>
+#include <string.h>
+#include <ctype.h>
+#include "subcmd-util.h"
 #include "parse-options.h"
-#include "cache.h"
-#include "header.h"
-#include <linux/string.h>
+#include "subcmd-config.h"
+#include "pager.h"
 
 #define OPT_SHORT 1
 #define OPT_UNSET 2
 
-static struct strbuf error_buf = STRBUF_INIT;
+char *error_buf;
 
 static int opterror(const struct option *opt, const char *reason, int flags)
 {
 	if (flags & OPT_SHORT)
-		return error("switch `%c' %s", opt->short_name, reason);
-	if (flags & OPT_UNSET)
-		return error("option `no-%s' %s", opt->long_name, reason);
-	return error("option `%s' %s", opt->long_name, reason);
+		fprintf(stderr, " Error: switch `%c' %s", opt->short_name, reason);
+	else if (flags & OPT_UNSET)
+		fprintf(stderr, " Error: option `no-%s' %s", opt->long_name, reason);
+	else
+		fprintf(stderr, " Error: option `%s' %s", opt->long_name, reason);
+
+	return -1;
+}
+
+static const char *skip_prefix(const char *str, const char *prefix)
+{
+	size_t len = strlen(prefix);
+	return strncmp(str, prefix, len) ? NULL : str + len;
+}
+
+static void optwarning(const struct option *opt, const char *reason, int flags)
+{
+	if (flags & OPT_SHORT)
+		fprintf(stderr, " Warning: switch `%c' %s", opt->short_name, reason);
+	else if (flags & OPT_UNSET)
+		fprintf(stderr, " Warning: option `no-%s' %s", opt->long_name, reason);
+	else
+		fprintf(stderr, " Warning: option `%s' %s", opt->long_name, reason);
 }
 
 static int get_arg(struct parse_opt_ctx_t *p, const struct option *opt,
 		   int flags, const char **arg)
 {
+	const char *res;
+
 	if (p->opt) {
-		*arg = p->opt;
+		res = p->opt;
 		p->opt = NULL;
 	} else if ((opt->flags & PARSE_OPT_LASTARG_DEFAULT) && (p->argc == 1 ||
 		    **(p->argv + 1) == '-')) {
-		*arg = (const char *)opt->defval;
+		res = (const char *)opt->defval;
 	} else if (p->argc > 1) {
 		p->argc--;
-		*arg = *++p->argv;
+		res = *++p->argv;
 	} else
 		return opterror(opt, "requires a value", flags);
+	if (arg)
+		*arg = res;
 	return 0;
 }
 
@@ -55,11 +84,11 @@
 
 			if (((flags & OPT_SHORT) && p->excl_opt->short_name) ||
 			    p->excl_opt->long_name == NULL) {
-				scnprintf(msg, sizeof(msg), "cannot be used with switch `%c'",
-					  p->excl_opt->short_name);
+				snprintf(msg, sizeof(msg), "cannot be used with switch `%c'",
+					 p->excl_opt->short_name);
 			} else {
-				scnprintf(msg, sizeof(msg), "cannot be used with %s",
-					  p->excl_opt->long_name);
+				snprintf(msg, sizeof(msg), "cannot be used with %s",
+					 p->excl_opt->long_name);
 			}
 			opterror(opt, msg, flags);
 			return -3;
@@ -91,6 +120,64 @@
 		}
 	}
 
+	if (opt->flags & PARSE_OPT_NOBUILD) {
+		char reason[128];
+		bool noarg = false;
+
+		err = snprintf(reason, sizeof(reason),
+				opt->flags & PARSE_OPT_CANSKIP ?
+					"is being ignored because %s " :
+					"is not available because %s",
+				opt->build_opt);
+		reason[sizeof(reason) - 1] = '\0';
+
+		if (err < 0)
+			strncpy(reason, opt->flags & PARSE_OPT_CANSKIP ?
+					"is being ignored" :
+					"is not available",
+					sizeof(reason));
+
+		if (!(opt->flags & PARSE_OPT_CANSKIP))
+			return opterror(opt, reason, flags);
+
+		err = 0;
+		if (unset)
+			noarg = true;
+		if (opt->flags & PARSE_OPT_NOARG)
+			noarg = true;
+		if (opt->flags & PARSE_OPT_OPTARG && !p->opt)
+			noarg = true;
+
+		switch (opt->type) {
+		case OPTION_BOOLEAN:
+		case OPTION_INCR:
+		case OPTION_BIT:
+		case OPTION_SET_UINT:
+		case OPTION_SET_PTR:
+		case OPTION_END:
+		case OPTION_ARGUMENT:
+		case OPTION_GROUP:
+			noarg = true;
+			break;
+		case OPTION_CALLBACK:
+		case OPTION_STRING:
+		case OPTION_INTEGER:
+		case OPTION_UINTEGER:
+		case OPTION_LONG:
+		case OPTION_U64:
+		default:
+			break;
+		}
+
+		if (!noarg)
+			err = get_arg(p, opt, flags, NULL);
+		if (err)
+			return err;
+
+		optwarning(opt, reason, flags);
+		return 0;
+	}
+
 	switch (opt->type) {
 	case OPTION_BIT:
 		if (unset)
@@ -327,14 +414,16 @@
 		return get_value(p, options, flags);
 	}
 
-	if (ambiguous_option)
-		return error("Ambiguous option: %s "
-			"(could be --%s%s or --%s%s)",
-			arg,
-			(ambiguous_flags & OPT_UNSET) ?  "no-" : "",
-			ambiguous_option->long_name,
-			(abbrev_flags & OPT_UNSET) ?  "no-" : "",
-			abbrev_option->long_name);
+	if (ambiguous_option) {
+		 fprintf(stderr,
+			 " Error: Ambiguous option: %s (could be --%s%s or --%s%s)",
+			 arg,
+			 (ambiguous_flags & OPT_UNSET) ?  "no-" : "",
+			 ambiguous_option->long_name,
+			 (abbrev_flags & OPT_UNSET) ?  "no-" : "",
+			 abbrev_option->long_name);
+		 return -1;
+	}
 	if (abbrev_option)
 		return get_value(p, abbrev_option, abbrev_flags);
 	return -2;
@@ -346,7 +435,7 @@
 		return;
 
 	if (!prefixcmp(arg, "no-")) {
-		error ("did you mean `--%s` (with two dashes ?)", arg);
+		fprintf(stderr, " Error: did you mean `--%s` (with two dashes ?)", arg);
 		exit(129);
 	}
 
@@ -354,14 +443,14 @@
 		if (!options->long_name)
 			continue;
 		if (!prefixcmp(options->long_name, arg)) {
-			error ("did you mean `--%s` (with two dashes ?)", arg);
+			fprintf(stderr, " Error: did you mean `--%s` (with two dashes ?)", arg);
 			exit(129);
 		}
 	}
 }
 
-void parse_options_start(struct parse_opt_ctx_t *ctx,
-			 int argc, const char **argv, int flags)
+static void parse_options_start(struct parse_opt_ctx_t *ctx,
+				int argc, const char **argv, int flags)
 {
 	memset(ctx, 0, sizeof(*ctx));
 	ctx->argc = argc - 1;
@@ -378,9 +467,9 @@
 				       const struct option *, int,
 				       struct parse_opt_ctx_t *);
 
-int parse_options_step(struct parse_opt_ctx_t *ctx,
-		       const struct option *options,
-		       const char * const usagestr[])
+static int parse_options_step(struct parse_opt_ctx_t *ctx,
+			      const struct option *options,
+			      const char * const usagestr[])
 {
 	int internal_help = !(ctx->flags & PARSE_OPT_NO_INTERNAL_HELP);
 	int excl_short_opt = 1;
@@ -489,7 +578,7 @@
 	return PARSE_OPT_HELP;
 }
 
-int parse_options_end(struct parse_opt_ctx_t *ctx)
+static int parse_options_end(struct parse_opt_ctx_t *ctx)
 {
 	memmove(ctx->out + ctx->cpidx, ctx->argv, ctx->argc * sizeof(*ctx->out));
 	ctx->out[ctx->cpidx + ctx->argc] = NULL;
@@ -501,22 +590,20 @@
 {
 	struct parse_opt_ctx_t ctx;
 
-	perf_env__set_cmdline(&perf_env, argc, argv);
-
 	/* build usage string if it's not provided */
 	if (subcommands && !usagestr[0]) {
-		struct strbuf buf = STRBUF_INIT;
+		char *buf = NULL;
 
-		strbuf_addf(&buf, "perf %s [<options>] {", argv[0]);
+		astrcatf(&buf, "%s %s [<options>] {", subcmd_config.exec_name, argv[0]);
+
 		for (int i = 0; subcommands[i]; i++) {
 			if (i)
-				strbuf_addstr(&buf, "|");
-			strbuf_addstr(&buf, subcommands[i]);
+				astrcat(&buf, "|");
+			astrcat(&buf, subcommands[i]);
 		}
-		strbuf_addstr(&buf, "}");
+		astrcat(&buf, "}");
 
-		usagestr[0] = strdup(buf.buf);
-		strbuf_release(&buf);
+		usagestr[0] = buf;
 	}
 
 	parse_options_start(&ctx, argc, argv, flags);
@@ -541,13 +628,11 @@
 		putchar('\n');
 		exit(130);
 	default: /* PARSE_OPT_UNKNOWN */
-		if (ctx.argv[0][1] == '-') {
-			strbuf_addf(&error_buf, "unknown option `%s'",
-				    ctx.argv[0] + 2);
-		} else {
-			strbuf_addf(&error_buf, "unknown switch `%c'",
-				    *ctx.opt);
-		}
+		if (ctx.argv[0][1] == '-')
+			astrcatf(&error_buf, "unknown option `%s'",
+				 ctx.argv[0] + 2);
+		else
+			astrcatf(&error_buf, "unknown switch `%c'", *ctx.opt);
 		usage_with_options(usagestr, options);
 	}
 
@@ -647,6 +732,10 @@
 		pad = USAGE_OPTS_WIDTH;
 	}
 	fprintf(stderr, "%*s%s\n", pad + USAGE_GAP, "", opts->help);
+	if (opts->flags & PARSE_OPT_NOBUILD)
+		fprintf(stderr, "%*s(not built-in because %s)\n",
+			USAGE_OPTS_WIDTH + USAGE_GAP, "",
+			opts->build_opt);
 }
 
 static int option__cmp(const void *va, const void *vb)
@@ -672,16 +761,18 @@
 
 static struct option *options__order(const struct option *opts)
 {
-	int nr_opts = 0;
+	int nr_opts = 0, len;
 	const struct option *o = opts;
 	struct option *ordered;
 
 	for (o = opts; o->type != OPTION_END; o++)
 		++nr_opts;
 
-	ordered = memdup(opts, sizeof(*o) * (nr_opts + 1));
-	if (ordered == NULL)
+	len = sizeof(*o) * (nr_opts + 1);
+	ordered = malloc(len);
+	if (!ordered)
 		goto out;
+	memcpy(ordered, opts, len);
 
 	qsort(ordered, nr_opts, sizeof(*o), option__cmp);
 out:
@@ -719,9 +810,9 @@
 	return false;
 }
 
-int usage_with_options_internal(const char * const *usagestr,
-				const struct option *opts, int full,
-				struct parse_opt_ctx_t *ctx)
+static int usage_with_options_internal(const char * const *usagestr,
+				       const struct option *opts, int full,
+				       struct parse_opt_ctx_t *ctx)
 {
 	struct option *ordered;
 
@@ -730,9 +821,9 @@
 
 	setup_pager();
 
-	if (strbuf_avail(&error_buf)) {
-		fprintf(stderr, "  Error: %s\n", error_buf.buf);
-		strbuf_release(&error_buf);
+	if (error_buf) {
+		fprintf(stderr, "  Error: %s\n", error_buf);
+		zfree(&error_buf);
 	}
 
 	fprintf(stderr, "\n Usage: %s\n", *usagestr++);
@@ -768,7 +859,6 @@
 void usage_with_options(const char * const *usagestr,
 			const struct option *opts)
 {
-	exit_browser(false);
 	usage_with_options_internal(usagestr, opts, 0, NULL);
 	exit(129);
 }
@@ -777,13 +867,15 @@
 			    const struct option *opts, const char *fmt, ...)
 {
 	va_list ap;
-
-	exit_browser(false);
+	char *tmp = error_buf;
 
 	va_start(ap, fmt);
-	strbuf_addv(&error_buf, fmt, ap);
+	if (vasprintf(&error_buf, fmt, ap) == -1)
+		die("vasprintf failed");
 	va_end(ap);
 
+	free(tmp);
+
 	usage_with_options_internal(usagestr, opts, 0, NULL);
 	exit(129);
 }
@@ -853,15 +945,39 @@
 	return 0;
 }
 
-void set_option_flag(struct option *opts, int shortopt, const char *longopt,
-		     int flag)
+static struct option *
+find_option(struct option *opts, int shortopt, const char *longopt)
 {
 	for (; opts->type != OPTION_END; opts++) {
 		if ((shortopt && opts->short_name == shortopt) ||
 		    (opts->long_name && longopt &&
-		     !strcmp(opts->long_name, longopt))) {
-			opts->flags |= flag;
-			break;
-		}
+		     !strcmp(opts->long_name, longopt)))
+			return opts;
 	}
+	return NULL;
+}
+
+void set_option_flag(struct option *opts, int shortopt, const char *longopt,
+		     int flag)
+{
+	struct option *opt = find_option(opts, shortopt, longopt);
+
+	if (opt)
+		opt->flags |= flag;
+	return;
+}
+
+void set_option_nobuild(struct option *opts, int shortopt,
+			const char *longopt,
+			const char *build_opt,
+			bool can_skip)
+{
+	struct option *opt = find_option(opts, shortopt, longopt);
+
+	if (!opt)
+		return;
+
+	opt->flags |= PARSE_OPT_NOBUILD;
+	opt->flags |= can_skip ? PARSE_OPT_CANSKIP : 0;
+	opt->build_opt = build_opt;
 }
diff --git a/tools/perf/util/parse-options.h b/tools/lib/subcmd/parse-options.h
similarity index 94%
rename from tools/perf/util/parse-options.h
rename to tools/lib/subcmd/parse-options.h
index a8e407b..13a2cc1 100644
--- a/tools/perf/util/parse-options.h
+++ b/tools/lib/subcmd/parse-options.h
@@ -1,8 +1,8 @@
-#ifndef __PERF_PARSE_OPTIONS_H
-#define __PERF_PARSE_OPTIONS_H
+#ifndef __SUBCMD_PARSE_OPTIONS_H
+#define __SUBCMD_PARSE_OPTIONS_H
 
-#include <linux/kernel.h>
 #include <stdbool.h>
+#include <stdint.h>
 
 enum parse_opt_type {
 	/* special types */
@@ -41,6 +41,8 @@
 	PARSE_OPT_DISABLED = 32,
 	PARSE_OPT_EXCLUSIVE = 64,
 	PARSE_OPT_NOEMPTY  = 128,
+	PARSE_OPT_NOBUILD  = 256,
+	PARSE_OPT_CANSKIP  = 512,
 };
 
 struct option;
@@ -96,6 +98,7 @@
 	void *value;
 	const char *argh;
 	const char *help;
+	const char *build_opt;
 
 	int flags;
 	parse_opt_cb *callback;
@@ -149,6 +152,9 @@
 /* parse_options() will filter out the processed options and leave the
  * non-option argments in argv[].
  * Returns the number of arguments left in argv[].
+ *
+ * NOTE: parse_options() and parse_options_subcommand() may call exit() in the
+ * case of an error (or for 'special' options like --list-cmds or --list-opts).
  */
 extern int parse_options(int argc, const char **argv,
                          const struct option *options,
@@ -195,15 +201,6 @@
 			       const char *optstr,
 			       bool short_opt);
 
-extern void parse_options_start(struct parse_opt_ctx_t *ctx,
-				int argc, const char **argv, int flags);
-
-extern int parse_options_step(struct parse_opt_ctx_t *ctx,
-			      const struct option *options,
-			      const char * const usagestr[]);
-
-extern int parse_options_end(struct parse_opt_ctx_t *ctx);
-
 
 /*----- some often used options -----*/
 extern int parse_opt_abbrev_cb(const struct option *, const char *, int);
@@ -226,4 +223,7 @@
 extern const char *parse_options_fix_filename(const char *prefix, const char *file);
 
 void set_option_flag(struct option *opts, int sopt, const char *lopt, int flag);
-#endif /* __PERF_PARSE_OPTIONS_H */
+void set_option_nobuild(struct option *opts, int shortopt, const char *longopt,
+			const char *build_opt, bool can_skip);
+
+#endif /* __SUBCMD_PARSE_OPTIONS_H */
diff --git a/tools/perf/util/run-command.c b/tools/lib/subcmd/run-command.c
similarity index 90%
rename from tools/perf/util/run-command.c
rename to tools/lib/subcmd/run-command.c
index 34622b5..f4f6c9e 100644
--- a/tools/perf/util/run-command.c
+++ b/tools/lib/subcmd/run-command.c
@@ -1,7 +1,15 @@
-#include "cache.h"
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <string.h>
+#include <errno.h>
+#include <sys/wait.h>
+#include "subcmd-util.h"
 #include "run-command.h"
-#include "exec_cmd.h"
-#include "debug.h"
+#include "exec-cmd.h"
+
+#define STRERR_BUFSIZE 128
 
 static inline void close_pair(int fd[2])
 {
@@ -112,8 +120,8 @@
 		}
 		if (cmd->preexec_cb)
 			cmd->preexec_cb();
-		if (cmd->perf_cmd) {
-			execv_perf_cmd(cmd->argv);
+		if (cmd->exec_cmd) {
+			execv_cmd(cmd->argv);
 		} else {
 			execvp(cmd->argv[0], (char *const*) cmd->argv);
 		}
@@ -164,8 +172,8 @@
 		if (waiting < 0) {
 			if (errno == EINTR)
 				continue;
-			error("waitpid failed (%s)",
-			      strerror_r(errno, sbuf, sizeof(sbuf)));
+			fprintf(stderr, " Error: waitpid failed (%s)",
+				strerror_r(errno, sbuf, sizeof(sbuf)));
 			return -ERR_RUN_COMMAND_WAITPID;
 		}
 		if (waiting != pid)
@@ -207,7 +215,7 @@
 	memset(cmd, 0, sizeof(*cmd));
 	cmd->argv = argv;
 	cmd->no_stdin = opt & RUN_COMMAND_NO_STDIN ? 1 : 0;
-	cmd->perf_cmd = opt & RUN_PERF_CMD ? 1 : 0;
+	cmd->exec_cmd = opt & RUN_EXEC_CMD ? 1 : 0;
 	cmd->stdout_to_stderr = opt & RUN_COMMAND_STDOUT_TO_STDERR ? 1 : 0;
 }
 
diff --git a/tools/perf/util/run-command.h b/tools/lib/subcmd/run-command.h
similarity index 86%
rename from tools/perf/util/run-command.h
rename to tools/lib/subcmd/run-command.h
index 1ef264d..fe2befe 100644
--- a/tools/perf/util/run-command.h
+++ b/tools/lib/subcmd/run-command.h
@@ -1,5 +1,7 @@
-#ifndef __PERF_RUN_COMMAND_H
-#define __PERF_RUN_COMMAND_H
+#ifndef __SUBCMD_RUN_COMMAND_H
+#define __SUBCMD_RUN_COMMAND_H
+
+#include <unistd.h>
 
 enum {
 	ERR_RUN_COMMAND_FORK = 10000,
@@ -41,7 +43,7 @@
 	unsigned no_stdin:1;
 	unsigned no_stdout:1;
 	unsigned no_stderr:1;
-	unsigned perf_cmd:1; /* if this is to be perf sub-command */
+	unsigned exec_cmd:1; /* if this is to be external sub-command */
 	unsigned stdout_to_stderr:1;
 	void (*preexec_cb)(void);
 };
@@ -51,8 +53,8 @@
 int run_command(struct child_process *);
 
 #define RUN_COMMAND_NO_STDIN 1
-#define RUN_PERF_CMD	     2	/*If this is to be perf sub-command */
+#define RUN_EXEC_CMD	     2	/*If this is to be external sub-command */
 #define RUN_COMMAND_STDOUT_TO_STDERR 4
 int run_command_v_opt(const char **argv, int opt);
 
-#endif /* __PERF_RUN_COMMAND_H */
+#endif /* __SUBCMD_RUN_COMMAND_H */
diff --git a/tools/perf/util/sigchain.c b/tools/lib/subcmd/sigchain.c
similarity index 95%
rename from tools/perf/util/sigchain.c
rename to tools/lib/subcmd/sigchain.c
index ba785e9..3537c34 100644
--- a/tools/perf/util/sigchain.c
+++ b/tools/lib/subcmd/sigchain.c
@@ -1,5 +1,6 @@
+#include <signal.h>
+#include "subcmd-util.h"
 #include "sigchain.h"
-#include "cache.h"
 
 #define SIGCHAIN_MAX_SIGNALS 32
 
diff --git a/tools/lib/subcmd/sigchain.h b/tools/lib/subcmd/sigchain.h
new file mode 100644
index 0000000..0c919f2
--- /dev/null
+++ b/tools/lib/subcmd/sigchain.h
@@ -0,0 +1,10 @@
+#ifndef __SUBCMD_SIGCHAIN_H
+#define __SUBCMD_SIGCHAIN_H
+
+typedef void (*sigchain_fun)(int);
+
+int sigchain_pop(int sig);
+
+void sigchain_push_common(sigchain_fun f);
+
+#endif /* __SUBCMD_SIGCHAIN_H */
diff --git a/tools/lib/subcmd/subcmd-config.c b/tools/lib/subcmd/subcmd-config.c
new file mode 100644
index 0000000..d017c72
--- /dev/null
+++ b/tools/lib/subcmd/subcmd-config.c
@@ -0,0 +1,11 @@
+#include "subcmd-config.h"
+
+#define UNDEFINED "SUBCMD_HAS_NOT_BEEN_INITIALIZED"
+
+struct subcmd_config subcmd_config = {
+	.exec_name	= UNDEFINED,
+	.prefix		= UNDEFINED,
+	.exec_path	= UNDEFINED,
+	.exec_path_env	= UNDEFINED,
+	.pager_env	= UNDEFINED,
+};
diff --git a/tools/lib/subcmd/subcmd-config.h b/tools/lib/subcmd/subcmd-config.h
new file mode 100644
index 0000000..cc85140
--- /dev/null
+++ b/tools/lib/subcmd/subcmd-config.h
@@ -0,0 +1,14 @@
+#ifndef __PERF_SUBCMD_CONFIG_H
+#define __PERF_SUBCMD_CONFIG_H
+
+struct subcmd_config {
+	const char *exec_name;
+	const char *prefix;
+	const char *exec_path;
+	const char *exec_path_env;
+	const char *pager_env;
+};
+
+extern struct subcmd_config subcmd_config;
+
+#endif /* __PERF_SUBCMD_CONFIG_H */
diff --git a/tools/lib/subcmd/subcmd-util.h b/tools/lib/subcmd/subcmd-util.h
new file mode 100644
index 0000000..fc2e45d8
--- /dev/null
+++ b/tools/lib/subcmd/subcmd-util.h
@@ -0,0 +1,91 @@
+#ifndef __SUBCMD_UTIL_H
+#define __SUBCMD_UTIL_H
+
+#include <stdarg.h>
+#include <stdlib.h>
+#include <stdio.h>
+
+#define NORETURN __attribute__((__noreturn__))
+
+static inline void report(const char *prefix, const char *err, va_list params)
+{
+	char msg[1024];
+	vsnprintf(msg, sizeof(msg), err, params);
+	fprintf(stderr, " %s%s\n", prefix, msg);
+}
+
+static NORETURN inline void die(const char *err, ...)
+{
+	va_list params;
+
+	va_start(params, err);
+	report(" Fatal: ", err, params);
+	exit(128);
+	va_end(params);
+}
+
+#define zfree(ptr) ({ free(*ptr); *ptr = NULL; })
+
+#define alloc_nr(x) (((x)+16)*3/2)
+
+/*
+ * Realloc the buffer pointed at by variable 'x' so that it can hold
+ * at least 'nr' entries; the number of entries currently allocated
+ * is 'alloc', using the standard growing factor alloc_nr() macro.
+ *
+ * DO NOT USE any expression with side-effect for 'x' or 'alloc'.
+ */
+#define ALLOC_GROW(x, nr, alloc) \
+	do { \
+		if ((nr) > alloc) { \
+			if (alloc_nr(alloc) < (nr)) \
+				alloc = (nr); \
+			else \
+				alloc = alloc_nr(alloc); \
+			x = xrealloc((x), alloc * sizeof(*(x))); \
+		} \
+	} while(0)
+
+static inline void *xrealloc(void *ptr, size_t size)
+{
+	void *ret = realloc(ptr, size);
+	if (!ret && !size)
+		ret = realloc(ptr, 1);
+	if (!ret) {
+		ret = realloc(ptr, size);
+		if (!ret && !size)
+			ret = realloc(ptr, 1);
+		if (!ret)
+			die("Out of memory, realloc failed");
+	}
+	return ret;
+}
+
+#define astrcatf(out, fmt, ...)						\
+({									\
+	char *tmp = *(out);						\
+	if (asprintf((out), "%s" fmt, tmp ?: "", ## __VA_ARGS__) == -1)	\
+		die("asprintf failed");					\
+	free(tmp);							\
+})
+
+static inline void astrcat(char **out, const char *add)
+{
+	char *tmp = *out;
+
+	if (asprintf(out, "%s%s", tmp ?: "", add) == -1)
+		die("asprintf failed");
+
+	free(tmp);
+}
+
+static inline int prefixcmp(const char *str, const char *prefix)
+{
+	for (; ; str++, prefix++)
+		if (!*prefix)
+			return 0;
+		else if (*str != *prefix)
+			return (unsigned char)*prefix - (unsigned char)*str;
+}
+
+#endif /* __SUBCMD_UTIL_H */
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 2a912df6..ea69ce3 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -4735,73 +4735,80 @@
 	return 1;
 }
 
-static void print_event_fields(struct trace_seq *s, void *data,
-			       int size __maybe_unused,
-			       struct event_format *event)
+void pevent_print_field(struct trace_seq *s, void *data,
+			struct format_field *field)
 {
-	struct format_field *field;
 	unsigned long long val;
 	unsigned int offset, len, i;
+	struct pevent *pevent = field->event->pevent;
+
+	if (field->flags & FIELD_IS_ARRAY) {
+		offset = field->offset;
+		len = field->size;
+		if (field->flags & FIELD_IS_DYNAMIC) {
+			val = pevent_read_number(pevent, data + offset, len);
+			offset = val;
+			len = offset >> 16;
+			offset &= 0xffff;
+		}
+		if (field->flags & FIELD_IS_STRING &&
+		    is_printable_array(data + offset, len)) {
+			trace_seq_printf(s, "%s", (char *)data + offset);
+		} else {
+			trace_seq_puts(s, "ARRAY[");
+			for (i = 0; i < len; i++) {
+				if (i)
+					trace_seq_puts(s, ", ");
+				trace_seq_printf(s, "%02x",
+						 *((unsigned char *)data + offset + i));
+			}
+			trace_seq_putc(s, ']');
+			field->flags &= ~FIELD_IS_STRING;
+		}
+	} else {
+		val = pevent_read_number(pevent, data + field->offset,
+					 field->size);
+		if (field->flags & FIELD_IS_POINTER) {
+			trace_seq_printf(s, "0x%llx", val);
+		} else if (field->flags & FIELD_IS_SIGNED) {
+			switch (field->size) {
+			case 4:
+				/*
+				 * If field is long then print it in hex.
+				 * A long usually stores pointers.
+				 */
+				if (field->flags & FIELD_IS_LONG)
+					trace_seq_printf(s, "0x%x", (int)val);
+				else
+					trace_seq_printf(s, "%d", (int)val);
+				break;
+			case 2:
+				trace_seq_printf(s, "%2d", (short)val);
+				break;
+			case 1:
+				trace_seq_printf(s, "%1d", (char)val);
+				break;
+			default:
+				trace_seq_printf(s, "%lld", val);
+			}
+		} else {
+			if (field->flags & FIELD_IS_LONG)
+				trace_seq_printf(s, "0x%llx", val);
+			else
+				trace_seq_printf(s, "%llu", val);
+		}
+	}
+}
+
+void pevent_print_fields(struct trace_seq *s, void *data,
+			 int size __maybe_unused, struct event_format *event)
+{
+	struct format_field *field;
 
 	field = event->format.fields;
 	while (field) {
 		trace_seq_printf(s, " %s=", field->name);
-		if (field->flags & FIELD_IS_ARRAY) {
-			offset = field->offset;
-			len = field->size;
-			if (field->flags & FIELD_IS_DYNAMIC) {
-				val = pevent_read_number(event->pevent, data + offset, len);
-				offset = val;
-				len = offset >> 16;
-				offset &= 0xffff;
-			}
-			if (field->flags & FIELD_IS_STRING &&
-			    is_printable_array(data + offset, len)) {
-				trace_seq_printf(s, "%s", (char *)data + offset);
-			} else {
-				trace_seq_puts(s, "ARRAY[");
-				for (i = 0; i < len; i++) {
-					if (i)
-						trace_seq_puts(s, ", ");
-					trace_seq_printf(s, "%02x",
-							 *((unsigned char *)data + offset + i));
-				}
-				trace_seq_putc(s, ']');
-				field->flags &= ~FIELD_IS_STRING;
-			}
-		} else {
-			val = pevent_read_number(event->pevent, data + field->offset,
-						 field->size);
-			if (field->flags & FIELD_IS_POINTER) {
-				trace_seq_printf(s, "0x%llx", val);
-			} else if (field->flags & FIELD_IS_SIGNED) {
-				switch (field->size) {
-				case 4:
-					/*
-					 * If field is long then print it in hex.
-					 * A long usually stores pointers.
-					 */
-					if (field->flags & FIELD_IS_LONG)
-						trace_seq_printf(s, "0x%x", (int)val);
-					else
-						trace_seq_printf(s, "%d", (int)val);
-					break;
-				case 2:
-					trace_seq_printf(s, "%2d", (short)val);
-					break;
-				case 1:
-					trace_seq_printf(s, "%1d", (char)val);
-					break;
-				default:
-					trace_seq_printf(s, "%lld", val);
-				}
-			} else {
-				if (field->flags & FIELD_IS_LONG)
-					trace_seq_printf(s, "0x%llx", val);
-				else
-					trace_seq_printf(s, "%llu", val);
-			}
-		}
+		pevent_print_field(s, data, field);
 		field = field->next;
 	}
 }
@@ -4827,7 +4834,7 @@
 
 	if (event->flags & EVENT_FL_FAILED) {
 		trace_seq_printf(s, "[FAILED TO PARSE]");
-		print_event_fields(s, data, size, event);
+		pevent_print_fields(s, data, size, event);
 		return;
 	}
 
@@ -4968,13 +4975,12 @@
 				    sizeof(long) != 8) {
 					char *p;
 
-					ls = 2;
 					/* make %l into %ll */
-					p = strchr(format, 'l');
-					if (p)
+					if (ls == 1 && (p = strchr(format, 'l')))
 						memmove(p+1, p, strlen(p)+1);
 					else if (strcmp(format, "%p") == 0)
 						strcpy(format, "0x%llx");
+					ls = 2;
 				}
 				switch (ls) {
 				case -2:
@@ -5302,7 +5308,7 @@
 	int print_pretty = 1;
 
 	if (event->pevent->print_raw || (event->flags & EVENT_FL_PRINTRAW))
-		print_event_fields(s, record->data, record->size, event);
+		pevent_print_fields(s, record->data, record->size, event);
 	else {
 
 		if (event->handler && !(event->flags & EVENT_FL_NOHANDLE))
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 6fc83c7..706d9bc 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -705,6 +705,10 @@
 					  struct cmdline *next);
 int pevent_cmdline_pid(struct pevent *pevent, struct cmdline *cmdline);
 
+void pevent_print_field(struct trace_seq *s, void *data,
+			struct format_field *field);
+void pevent_print_fields(struct trace_seq *s, void *data,
+			 int size __maybe_unused, struct event_format *event);
 void pevent_event_info(struct trace_seq *s, struct event_format *event,
 		       struct pevent_record *record);
 int pevent_strerror(struct pevent *pevent, enum pevent_errno errnum,
diff --git a/tools/lib/util/find_next_bit.c b/tools/lib/util/find_next_bit.c
deleted file mode 100644
index 41b44f6..0000000
--- a/tools/lib/util/find_next_bit.c
+++ /dev/null
@@ -1,89 +0,0 @@
-/* find_next_bit.c: fallback find next bit implementation
- *
- * Copied from lib/find_next_bit.c to tools/lib/next_bit.c
- *
- * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells (dhowells@redhat.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#include <linux/bitops.h>
-#include <asm/types.h>
-#include <asm/byteorder.h>
-
-#define BITOP_WORD(nr)		((nr) / BITS_PER_LONG)
-
-#ifndef find_next_bit
-/*
- * Find the next set bit in a memory region.
- */
-unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
-			    unsigned long offset)
-{
-	const unsigned long *p = addr + BITOP_WORD(offset);
-	unsigned long result = offset & ~(BITS_PER_LONG-1);
-	unsigned long tmp;
-
-	if (offset >= size)
-		return size;
-	size -= result;
-	offset %= BITS_PER_LONG;
-	if (offset) {
-		tmp = *(p++);
-		tmp &= (~0UL << offset);
-		if (size < BITS_PER_LONG)
-			goto found_first;
-		if (tmp)
-			goto found_middle;
-		size -= BITS_PER_LONG;
-		result += BITS_PER_LONG;
-	}
-	while (size & ~(BITS_PER_LONG-1)) {
-		if ((tmp = *(p++)))
-			goto found_middle;
-		result += BITS_PER_LONG;
-		size -= BITS_PER_LONG;
-	}
-	if (!size)
-		return result;
-	tmp = *p;
-
-found_first:
-	tmp &= (~0UL >> (BITS_PER_LONG - size));
-	if (tmp == 0UL)		/* Are any bits set? */
-		return result + size;	/* Nope. */
-found_middle:
-	return result + __ffs(tmp);
-}
-#endif
-
-#ifndef find_first_bit
-/*
- * Find the first set bit in a memory region.
- */
-unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
-{
-	const unsigned long *p = addr;
-	unsigned long result = 0;
-	unsigned long tmp;
-
-	while (size & ~(BITS_PER_LONG-1)) {
-		if ((tmp = *(p++)))
-			goto found;
-		result += BITS_PER_LONG;
-		size -= BITS_PER_LONG;
-	}
-	if (!size)
-		return result;
-
-	tmp = (*p) & (~0UL >> (BITS_PER_LONG - size));
-	if (tmp == 0UL)		/* Are any bits set? */
-		return result + size;	/* Nope. */
-found:
-	return result + __ffs(tmp);
-}
-#endif
diff --git a/tools/perf/Build b/tools/perf/Build
index 7223745..6b67e6f 100644
--- a/tools/perf/Build
+++ b/tools/perf/Build
@@ -1,5 +1,6 @@
 perf-y += builtin-bench.o
 perf-y += builtin-annotate.o
+perf-y += builtin-config.o
 perf-y += builtin-diff.o
 perf-y += builtin-evlist.o
 perf-y += builtin-help.o
@@ -19,6 +20,7 @@
 perf-y += builtin-inject.o
 perf-y += builtin-mem.o
 perf-y += builtin-data.o
+perf-y += builtin-version.o
 
 perf-$(CONFIG_AUDIT) += builtin-trace.o
 perf-$(CONFIG_LIBELF) += builtin-probe.o
@@ -34,8 +36,12 @@
 
 CFLAGS_builtin-help.o      += $(paths)
 CFLAGS_builtin-timechart.o += $(paths)
-CFLAGS_perf.o              += -DPERF_HTML_PATH="BUILD_STR($(htmldir_SQ))" -include $(OUTPUT)PERF-VERSION-FILE
+CFLAGS_perf.o              += -DPERF_HTML_PATH="BUILD_STR($(htmldir_SQ))"	\
+			      -DPERF_EXEC_PATH="BUILD_STR($(perfexecdir_SQ))"	\
+			      -DPREFIX="BUILD_STR($(prefix_SQ))"		\
+			      -include $(OUTPUT)PERF-VERSION-FILE
 CFLAGS_builtin-trace.o	   += -DSTRACE_GROUPS_DIR="BUILD_STR($(STRACE_GROUPS_DIR_SQ))"
+CFLAGS_builtin-report.o	   += -DTIPDIR="BUILD_STR($(tipdir_SQ))"
 
 libperf-y += util/
 libperf-y += arch/
diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
new file mode 100644
index 0000000..b9ca1e3
--- /dev/null
+++ b/tools/perf/Documentation/perf-config.txt
@@ -0,0 +1,103 @@
+perf-config(1)
+==============
+
+NAME
+----
+perf-config - Get and set variables in a configuration file.
+
+SYNOPSIS
+--------
+[verse]
+'perf config' -l | --list
+
+DESCRIPTION
+-----------
+You can manage variables in a configuration file with this command.
+
+OPTIONS
+-------
+
+-l::
+--list::
+	Show current config variables, name and value, for all sections.
+
+CONFIGURATION FILE
+------------------
+
+The perf configuration file contains many variables to change various
+aspects of each of its tools, including output, disk usage, etc.
+The '$HOME/.perfconfig' file is used to store a per-user configuration.
+The file '$(sysconfdir)/perfconfig' can be used to
+store a system-wide default configuration.
+
+Syntax
+~~~~~~
+
+The file consist of sections. A section starts with its name
+surrounded by square brackets and continues till the next section
+begins. Each variable must be in a section, and have the form
+'name = value', for example:
+
+	[section]
+		name1 = value1
+		name2 = value2
+
+Section names are case sensitive and can contain any characters except
+newline (double quote `"` and backslash have to be escaped as `\"` and `\\`,
+respectively). Section headers can't span multiple lines.
+
+Example
+~~~~~~~
+
+Given a $HOME/.perfconfig like this:
+
+#
+# This is the config file, and
+# a '#' and ';' character indicates a comment
+#
+
+	[colors]
+		# Color variables
+		top = red, default
+		medium = green, default
+		normal = lightgray, default
+		selected = white, lightgray
+		code = blue, default
+		addr = magenta, default
+		root = white, blue
+
+	[tui]
+		# Defaults if linked with libslang
+		report = on
+		annotate = on
+		top = on
+
+	[buildid]
+		# Default, disable using /dev/null
+		dir = ~/.debug
+
+	[annotate]
+		# Defaults
+		hide_src_code = false
+		use_offset = true
+		jump_arrows = true
+		show_nr_jumps = false
+
+	[help]
+		# Format can be man, info, web or html
+		format = man
+		autocorrect = 0
+
+	[ui]
+		show-headers = true
+
+	[call-graph]
+		# fp (framepointer), dwarf
+		record-mode = fp
+		print-type = graph
+		order = caller
+		sort-key = function
+
+SEE ALSO
+--------
+linkperf:perf[1]
diff --git a/tools/perf/Documentation/perf-evlist.txt b/tools/perf/Documentation/perf-evlist.txt
index 1ceb370..6f7200f 100644
--- a/tools/perf/Documentation/perf-evlist.txt
+++ b/tools/perf/Documentation/perf-evlist.txt
@@ -32,6 +32,9 @@
 --group::
 	Show event group information.
 
+--trace-fields::
+	Show tracepoint field names.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-list[1],
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index e630a7d..3a1a32f 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -207,11 +207,23 @@
 In per-thread mode with inheritance mode on (default), samples are captured only when
 the thread executes on the designated CPUs. Default is to monitor all CPUs.
 
+-B::
+--no-buildid::
+Do not save the build ids of binaries in the perf.data files. This skips
+post processing after recording, which sometimes makes the final step in
+the recording process to take a long time, as it needs to process all
+events looking for mmap records. The downside is that it can misresolve
+symbols if the workload binaries used when recording get locally rebuilt
+or upgraded, because the only key available in this case is the
+pathname. You can also set the "record.build-id" config variable to
+'skip to have this behaviour permanently.
+
 -N::
 --no-buildid-cache::
 Do not update the buildid cache. This saves some overhead in situations
 where the information in the perf.data file (which includes buildids)
-is sufficient.
+is sufficient.  You can also set the "record.build-id" config variable to
+'no-cache' to have the same effect.
 
 -G name,...::
 --cgroup name,...::
@@ -314,11 +326,17 @@
 Record context switch events i.e. events of type PERF_RECORD_SWITCH or
 PERF_RECORD_SWITCH_CPU_WIDE.
 
---clang-path::
+--clang-path=PATH::
 Path to clang binary to use for compiling BPF scriptlets.
+(enabled when BPF support is on)
 
---clang-opt::
+--clang-opt=OPTIONS::
 Options passed to clang when compiling BPF scriptlets.
+(enabled when BPF support is on)
+
+--vmlinux=PATH::
+Specify vmlinux path which has debuginfo.
+(enabled when BPF prologue is on)
 
 SEE ALSO
 --------
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 5ce8da1..8a301f6 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -117,6 +117,30 @@
 	And default sort keys are changed to comm, dso_from, symbol_from, dso_to
 	and symbol_to, see '--branch-stack'.
 
+	If the data file has tracepoint event(s), following (dynamic) sort keys
+	are also available:
+	trace, trace_fields, [<event>.]<field>[/raw]
+
+	- trace: pretty printed trace output in a single column
+	- trace_fields: fields in tracepoints in separate columns
+	- <field name>: optional event and field name for a specific field
+
+	The last form consists of event and field names.  If event name is
+	omitted, it searches all events for matching field name.  The matched
+	field will be shown only for the event has the field.  The event name
+	supports substring match so user doesn't need to specify full subsystem
+	and event name everytime.  For example, 'sched:sched_switch' event can
+	be shortened to 'switch' as long as it's not ambiguous.  Also event can
+	be specified by its index (starting from 1) preceded by the '%'.
+	So '%1' is the first event, '%2' is the second, and so on.
+
+	The field name can have '/raw' suffix which disables pretty printing
+	and shows raw field value like hex numbers.  The --raw-trace option
+	has the same effect for all dynamic sort keys.
+
+	The default sort keys are changed to 'trace' if all events in the data
+	file are tracepoint.
+
 -F::
 --fields=::
 	Specify output field - multiple keys can be specified in CSV format.
@@ -170,17 +194,18 @@
         Dump raw trace in ASCII.
 
 -g::
---call-graph=<print_type,threshold[,print_limit],order,sort_key,branch>::
+--call-graph=<print_type,threshold[,print_limit],order,sort_key[,branch],value>::
         Display call chains using type, min percent threshold, print limit,
-	call order, sort key and branch.  Note that ordering of parameters is not
-	fixed so any parement can be given in an arbitraty order.  One exception
-	is the print_limit which should be preceded by threshold.
+	call order, sort key, optional branch and value.  Note that ordering of
+	parameters is not fixed so any parement can be given in an arbitraty order.
+	One exception is the print_limit which should be preceded by threshold.
 
 	print_type can be either:
 	- flat: single column, linear exposure of call chains.
 	- graph: use a graph tree, displaying absolute overhead rates. (default)
 	- fractal: like graph, but displays relative rates. Each branch of
 		 the tree is considered as a new profiled object.
+	- folded: call chains are displayed in a line, separated by semicolons
 	- none: disable call chain display.
 
 	threshold is a percentage value which specifies a minimum percent to be
@@ -204,6 +229,11 @@
 	- branch: include last branch information in callgraph when available.
 	          Usually more convenient to use --branch-history for this.
 
+	value can be:
+	- percent: diplay overhead percent (default)
+	- period: display event period
+	- count: display event count
+
 --children::
 	Accumulate callchain of children to parent entry so that then can
 	show up in the output.  The output will have a new "Children" column
@@ -365,6 +395,9 @@
 --socket-filter::
 	Only report the samples on the processor socket that match with this filter
 
+--raw-trace::
+	When displaying traceevent output, do not use print fmt or plugins.
+
 include::callchain-overhead-calculation.txt[]
 
 SEE ALSO
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 4e074a6..52ef7a9 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -10,6 +10,8 @@
 [verse]
 'perf stat' [-e <EVENT> | --event=EVENT] [-a] <command>
 'perf stat' [-e <EVENT> | --event=EVENT] [-a] -- <command> [<options>]
+'perf stat' [-e <EVENT> | --event=EVENT] [-a] record [-o file] -- <command> [<options>]
+'perf stat' report [-i file]
 
 DESCRIPTION
 -----------
@@ -22,6 +24,11 @@
 <command>...::
 	Any command you can specify in a shell.
 
+record::
+	See STAT RECORD.
+
+report::
+	See STAT REPORT.
 
 -e::
 --event=::
@@ -159,6 +166,33 @@
 
 Print statistics of transactional execution if supported.
 
+STAT RECORD
+-----------
+Stores stat data into perf data file.
+
+-o file::
+--output file::
+Output file name.
+
+STAT REPORT
+-----------
+Reads and reports stat data from perf data file.
+
+-i file::
+--input file::
+Input file name.
+
+--per-socket::
+Aggregate counts per processor socket for system-wide mode measurements.
+
+--per-core::
+Aggregate counts per physical processor for system-wide mode measurements.
+
+-A::
+--no-aggr::
+Do not aggregate counts across all monitored CPUs.
+
+
 EXAMPLES
 --------
 
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 556cec0..b0e60e1 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -230,6 +230,9 @@
 	The various filters must be specified as a comma separated list: --branch-filter any_ret,u,k
 	Note that this feature may not be available on all processors.
 
+--raw-trace::
+	When displaying traceevent output, do not use print fmt or plugins.
+
 INTERACTIVE PROMPTING KEYS
 --------------------------
 
diff --git a/tools/perf/Documentation/tips.txt b/tools/perf/Documentation/tips.txt
new file mode 100644
index 0000000..a1c10e3
--- /dev/null
+++ b/tools/perf/Documentation/tips.txt
@@ -0,0 +1,14 @@
+For a higher level overview, try: perf report --sort comm,dso
+Sample related events with: perf record -e '{cycles,instructions}:S'
+Compare performance results with: perf diff [<old file> <new file>]
+Boolean options have negative forms, e.g.: perf report --no-children
+Customize output of perf script with: perf script -F event,ip,sym
+Generate a script for your data: perf script -g <lang>
+Save output of perf stat using: perf stat record <target workload>
+Create an archive with symtabs to analyse on other machine: perf archive
+Search options using a keyword: perf report -h <keyword>
+Use parent filter to see specific call path: perf report -p <regex>
+List events using substring match: perf list <keyword>
+To see list of saved events and attributes: perf evlist -v
+Use --symfs <dir> if your symbol files are in non-standard locations
+To see callchains in a more compact form: perf report -g folded
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 39c38cb..ddf922f 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -1,6 +1,7 @@
 tools/perf
 tools/arch/alpha/include/asm/barrier.h
 tools/arch/arm/include/asm/barrier.h
+tools/arch/arm64/include/asm/barrier.h
 tools/arch/ia64/include/asm/barrier.h
 tools/arch/mips/include/asm/barrier.h
 tools/arch/powerpc/include/asm/barrier.h
@@ -20,14 +21,17 @@
 tools/lib/bpf
 tools/lib/api
 tools/lib/bpf
+tools/lib/subcmd
 tools/lib/hweight.c
 tools/lib/rbtree.c
+tools/lib/string.c
 tools/lib/symbol/kallsyms.c
 tools/lib/symbol/kallsyms.h
-tools/lib/util/find_next_bit.c
+tools/lib/find_bit.c
 tools/include/asm/atomic.h
 tools/include/asm/barrier.h
 tools/include/asm/bug.h
+tools/include/asm-generic/atomic-gcc.h
 tools/include/asm-generic/barrier.h
 tools/include/asm-generic/bitops/arch_hweight.h
 tools/include/asm-generic/bitops/atomic.h
@@ -50,6 +54,7 @@
 tools/include/linux/poison.h
 tools/include/linux/rbtree.h
 tools/include/linux/rbtree_augmented.h
+tools/include/linux/string.h
 tools/include/linux/types.h
 tools/include/linux/err.h
 include/asm-generic/bitops/arch_hweight.h
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 0d19d54..0a22407 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -145,9 +145,10 @@
 STRIP   = strip
 AWK     = awk
 
-LIB_DIR          = $(srctree)/tools/lib/api/
+LIB_DIR		= $(srctree)/tools/lib/api/
 TRACE_EVENT_DIR = $(srctree)/tools/lib/traceevent/
-BPF_DIR = $(srctree)/tools/lib/bpf/
+BPF_DIR		= $(srctree)/tools/lib/bpf/
+SUBCMD_DIR	= $(srctree)/tools/lib/subcmd/
 
 # include config/Makefile by default and rule out
 # non-config cases
@@ -184,15 +185,17 @@
 ifneq ($(OUTPUT),)
   TE_PATH=$(OUTPUT)
   BPF_PATH=$(OUTPUT)
+  SUBCMD_PATH=$(OUTPUT)
 ifneq ($(subdir),)
-  LIB_PATH=$(OUTPUT)/../lib/api/
+  API_PATH=$(OUTPUT)/../lib/api/
 else
-  LIB_PATH=$(OUTPUT)
+  API_PATH=$(OUTPUT)
 endif
 else
   TE_PATH=$(TRACE_EVENT_DIR)
-  LIB_PATH=$(LIB_DIR)
+  API_PATH=$(LIB_DIR)
   BPF_PATH=$(BPF_DIR)
+  SUBCMD_PATH=$(SUBCMD_DIR)
 endif
 
 LIBTRACEEVENT = $(TE_PATH)libtraceevent.a
@@ -201,11 +204,13 @@
 LIBTRACEEVENT_DYNAMIC_LIST = $(TE_PATH)libtraceevent-dynamic-list
 LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS = -Xlinker --dynamic-list=$(LIBTRACEEVENT_DYNAMIC_LIST)
 
-LIBAPI = $(LIB_PATH)libapi.a
+LIBAPI = $(API_PATH)libapi.a
 export LIBAPI
 
 LIBBPF = $(BPF_PATH)libbpf.a
 
+LIBSUBCMD = $(SUBCMD_PATH)libsubcmd.a
+
 # python extension build directories
 PYTHON_EXTBUILD     := $(OUTPUT)python_ext_build/
 PYTHON_EXTBUILD_LIB := $(PYTHON_EXTBUILD)lib/
@@ -257,7 +262,7 @@
 
 LIB_FILE=$(OUTPUT)libperf.a
 
-PERFLIBS = $(LIB_FILE) $(LIBAPI) $(LIBTRACEEVENT)
+PERFLIBS = $(LIB_FILE) $(LIBAPI) $(LIBTRACEEVENT) $(LIBSUBCMD)
 ifndef NO_LIBBPF
   PERFLIBS += $(LIBBPF)
 endif
@@ -420,7 +425,7 @@
 	$(call QUIET_CLEAN, libtraceevent)
 	$(Q)$(MAKE) -C $(TRACE_EVENT_DIR) O=$(OUTPUT) clean >/dev/null
 
-install-traceevent-plugins: $(LIBTRACEEVENT)
+install-traceevent-plugins: libtraceevent_plugins
 	$(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) install_plugins
 
 $(LIBAPI): fixdep FORCE
@@ -431,12 +436,19 @@
 	$(Q)$(MAKE) -C $(LIB_DIR) O=$(OUTPUT) clean >/dev/null
 
 $(LIBBPF): fixdep FORCE
-	$(Q)$(MAKE) -C $(BPF_DIR) O=$(OUTPUT) $(OUTPUT)libbpf.a
+	$(Q)$(MAKE) -C $(BPF_DIR) O=$(OUTPUT) $(OUTPUT)libbpf.a FEATURES_DUMP=$(realpath $(OUTPUT)FEATURE-DUMP)
 
 $(LIBBPF)-clean:
 	$(call QUIET_CLEAN, libbpf)
 	$(Q)$(MAKE) -C $(BPF_DIR) O=$(OUTPUT) clean >/dev/null
 
+$(LIBSUBCMD): fixdep FORCE
+	$(Q)$(MAKE) -C $(SUBCMD_DIR) O=$(OUTPUT) $(OUTPUT)libsubcmd.a
+
+$(LIBSUBCMD)-clean:
+	$(call QUIET_CLEAN, libsubcmd)
+	$(Q)$(MAKE) -C $(SUBCMD_DIR) O=$(OUTPUT) clean
+
 help:
 	@echo 'Perf make targets:'
 	@echo '  doc		- make *all* documentation (see below)'
@@ -476,7 +488,7 @@
 $(DOC_TARGETS):
 	$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) $(@:doc=all)
 
-TAG_FOLDERS= . ../lib/traceevent ../lib/api ../lib/symbol ../include ../lib/bpf
+TAG_FOLDERS= . ../lib ../include
 TAG_FILES= ../../include/uapi/linux/perf_event.h
 
 TAGS:
@@ -555,6 +567,9 @@
 	$(call QUIET_INSTALL, perf_completion-script) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d'; \
 		$(INSTALL) perf-completion.sh '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d/perf'
+	$(call QUIET_INSTALL, perf-tip) \
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(tip_instdir_SQ)'; \
+		$(INSTALL) Documentation/tips.txt -t '$(DESTDIR_SQ)$(tip_instdir_SQ)'
 
 install-tests: all install-gtk
 	$(call QUIET_INSTALL, tests) \
@@ -582,15 +597,16 @@
 #
 config-clean:
 	$(call QUIET_CLEAN, config)
-	$(Q)$(MAKE) -C $(srctree)/tools/build/feature/ clean >/dev/null
+	$(Q)$(MAKE) -C $(srctree)/tools/build/feature/ $(if $(OUTPUT),OUTPUT=$(OUTPUT)feature/,) clean >/dev/null
 
-clean: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean config-clean
+clean: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean config-clean
 	$(call QUIET_CLEAN, core-objs)  $(RM) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(LANG_BINDINGS)
-	$(Q)find . -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
+	$(Q)find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
 	$(Q)$(RM) $(OUTPUT).config-detected
 	$(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32
 	$(call QUIET_CLEAN, core-gen)   $(RM)  *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)FEATURE-DUMP $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex* \
-		$(OUTPUT)util/intel-pt-decoder/inat-tables.c
+		$(OUTPUT)util/intel-pt-decoder/inat-tables.c $(OUTPUT)fixdep \
+		$(OUTPUT)tests/llvm-src-{base,kbuild,prologue}.c
 	$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
 	$(python-clean)
 
diff --git a/tools/perf/arch/x86/include/arch-tests.h b/tools/perf/arch/x86/include/arch-tests.h
index 7ed00f4..b48de2f 100644
--- a/tools/perf/arch/x86/include/arch-tests.h
+++ b/tools/perf/arch/x86/include/arch-tests.h
@@ -2,10 +2,10 @@
 #define ARCH_TESTS_H
 
 /* Tests */
-int test__rdpmc(void);
-int test__perf_time_to_tsc(void);
-int test__insn_x86(void);
-int test__intel_cqm_count_nmi_context(void);
+int test__rdpmc(int subtest);
+int test__perf_time_to_tsc(int subtest);
+int test__insn_x86(int subtest);
+int test__intel_cqm_count_nmi_context(int subtest);
 
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 struct thread;
diff --git a/tools/perf/arch/x86/tests/insn-x86.c b/tools/perf/arch/x86/tests/insn-x86.c
index b6115df..08d9b2bc 100644
--- a/tools/perf/arch/x86/tests/insn-x86.c
+++ b/tools/perf/arch/x86/tests/insn-x86.c
@@ -171,7 +171,7 @@
  * verbose (-v) option to see all the instructions and whether or not they
  * decoded successfuly.
  */
-int test__insn_x86(void)
+int test__insn_x86(int subtest __maybe_unused)
 {
 	int ret = 0;
 
diff --git a/tools/perf/arch/x86/tests/intel-cqm.c b/tools/perf/arch/x86/tests/intel-cqm.c
index d28c1b6..3e89ba8 100644
--- a/tools/perf/arch/x86/tests/intel-cqm.c
+++ b/tools/perf/arch/x86/tests/intel-cqm.c
@@ -33,7 +33,7 @@
  * the last read counter value to avoid triggering a WARN_ON_ONCE() in
  * smp_call_function_many() caused by sending IPIs from NMI context.
  */
-int test__intel_cqm_count_nmi_context(void)
+int test__intel_cqm_count_nmi_context(int subtest __maybe_unused)
 {
 	struct perf_evlist *evlist = NULL;
 	struct perf_evsel *evsel = NULL;
@@ -54,7 +54,7 @@
 
 	ret = parse_events(evlist, "intel_cqm/llc_occupancy/", NULL);
 	if (ret) {
-		pr_debug("parse_events failed\n");
+		pr_debug("parse_events failed, is \"intel_cqm/llc_occupancy/\" available?\n");
 		err = TEST_SKIP;
 		goto out;
 	}
diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
index 658cd20..9d29ee2 100644
--- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c
+++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
@@ -35,13 +35,12 @@
  * %0 is returned, otherwise %-1 is returned.  If TSC conversion is not
  * supported then then the test passes but " (not supported)" is printed.
  */
-int test__perf_time_to_tsc(void)
+int test__perf_time_to_tsc(int subtest __maybe_unused)
 {
 	struct record_opts opts = {
 		.mmap_pages	     = UINT_MAX,
 		.user_freq	     = UINT_MAX,
 		.user_interval	     = ULLONG_MAX,
-		.freq		     = 4000,
 		.target		     = {
 			.uses_mmap   = true,
 		},
diff --git a/tools/perf/arch/x86/tests/rdpmc.c b/tools/perf/arch/x86/tests/rdpmc.c
index e768821..7bb0d13 100644
--- a/tools/perf/arch/x86/tests/rdpmc.c
+++ b/tools/perf/arch/x86/tests/rdpmc.c
@@ -149,7 +149,7 @@
 	return 0;
 }
 
-int test__rdpmc(void)
+int test__rdpmc(int subtest __maybe_unused)
 {
 	int status = 0;
 	int wret = 0;
diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build
index ff63649..4659703 100644
--- a/tools/perf/arch/x86/util/Build
+++ b/tools/perf/arch/x86/util/Build
@@ -5,6 +5,7 @@
 libperf-y += perf_regs.o
 
 libperf-$(CONFIG_DWARF) += dwarf-regs.o
+libperf-$(CONFIG_BPF_PROLOGUE) += dwarf-regs.o
 
 libperf-$(CONFIG_LIBUNWIND)          += unwind-libunwind.o
 libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c
index 9b94ce5..8d8150f 100644
--- a/tools/perf/arch/x86/util/intel-bts.c
+++ b/tools/perf/arch/x86/util/intel-bts.c
@@ -327,7 +327,7 @@
 
 	evlist__for_each(btsr->evlist, evsel) {
 		if (evsel->attr.type == btsr->intel_bts_pmu->type)
-			return perf_evlist__disable_event(btsr->evlist, evsel);
+			return perf_evsel__disable(evsel);
 	}
 	return -EINVAL;
 }
@@ -340,7 +340,7 @@
 
 	evlist__for_each(btsr->evlist, evsel) {
 		if (evsel->attr.type == btsr->intel_bts_pmu->type)
-			return perf_evlist__enable_event(btsr->evlist, evsel);
+			return perf_evsel__enable(evsel);
 	}
 	return -EINVAL;
 }
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index b02af06..f05daac 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -26,7 +26,7 @@
 #include "../../util/evlist.h"
 #include "../../util/evsel.h"
 #include "../../util/cpumap.h"
-#include "../../util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "../../util/parse-events.h"
 #include "../../util/pmu.h"
 #include "../../util/debug.h"
@@ -725,7 +725,7 @@
 
 	evlist__for_each(ptr->evlist, evsel) {
 		if (evsel->attr.type == ptr->intel_pt_pmu->type)
-			return perf_evlist__disable_event(ptr->evlist, evsel);
+			return perf_evsel__disable(evsel);
 	}
 	return -EINVAL;
 }
@@ -738,7 +738,7 @@
 
 	evlist__for_each(ptr->evlist, evsel) {
 		if (evsel->attr.type == ptr->intel_pt_pmu->type)
-			return perf_evlist__enable_event(ptr->evlist, evsel);
+			return perf_evsel__enable(evsel);
 	}
 	return -EINVAL;
 }
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index fc9bebd..0999ac5 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -11,7 +11,7 @@
 #include "../perf.h"
 #include "../util/util.h"
 #include "../util/stat.h"
-#include "../util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "../util/header.h"
 #include "bench.h"
 #include "futex.h"
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index bc6a16ad..6a18ce2 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -5,7 +5,7 @@
 #include "../perf.h"
 #include "../util/util.h"
 #include "../util/stat.h"
-#include "../util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "../util/header.h"
 #include "bench.h"
 #include "futex.h"
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index ad0d9b5..7182386 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -11,7 +11,7 @@
 #include "../perf.h"
 #include "../util/util.h"
 #include "../util/stat.h"
-#include "../util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "../util/header.h"
 #include "bench.h"
 #include "futex.h"
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index 6d8c9fa..91aaf2a 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -10,7 +10,7 @@
 #include "../perf.h"
 #include "../util/util.h"
 #include "../util/stat.h"
-#include "../util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "../util/header.h"
 #include "bench.h"
 #include "futex.h"
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index e5e41d3..f416bd7 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -11,7 +11,7 @@
 #include "../perf.h"
 #include "../util/util.h"
 #include "../util/stat.h"
-#include "../util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "../util/header.h"
 #include "bench.h"
 #include "futex.h"
diff --git a/tools/perf/bench/mem-functions.c b/tools/perf/bench/mem-functions.c
index 9419b94..a91aa85 100644
--- a/tools/perf/bench/mem-functions.c
+++ b/tools/perf/bench/mem-functions.c
@@ -8,7 +8,7 @@
 
 #include "../perf.h"
 #include "../util/util.h"
-#include "../util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "../util/header.h"
 #include "../util/cloexec.h"
 #include "bench.h"
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 492df27..5049d63 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -7,7 +7,7 @@
 #include "../perf.h"
 #include "../builtin.h"
 #include "../util/util.h"
-#include "../util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "../util/cloexec.h"
 
 #include "bench.h"
diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c
index d4ff1b5..bfaf950 100644
--- a/tools/perf/bench/sched-messaging.c
+++ b/tools/perf/bench/sched-messaging.c
@@ -11,7 +11,7 @@
 
 #include "../perf.h"
 #include "../util/util.h"
-#include "../util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "../builtin.h"
 #include "bench.h"
 
diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c
index 005cc28..1dc2d13 100644
--- a/tools/perf/bench/sched-pipe.c
+++ b/tools/perf/bench/sched-pipe.c
@@ -10,7 +10,7 @@
  */
 #include "../perf.h"
 #include "../util/util.h"
-#include "../util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "../builtin.h"
 #include "bench.h"
 
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 2bf9b3f..cc5c126 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -21,7 +21,7 @@
 #include "util/evsel.h"
 #include "util/annotate.h"
 #include "util/event.h"
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/parse-events.h"
 #include "util/thread.h"
 #include "util/sort.h"
@@ -47,7 +47,7 @@
 };
 
 static int perf_evsel__add_sample(struct perf_evsel *evsel,
-				  struct perf_sample *sample __maybe_unused,
+				  struct perf_sample *sample,
 				  struct addr_location *al,
 				  struct perf_annotate *ann)
 {
@@ -72,7 +72,10 @@
 		return 0;
 	}
 
-	he = __hists__add_entry(hists, al, NULL, NULL, NULL, 1, 1, 0, true);
+	sample->period = 1;
+	sample->weight = 1;
+
+	he = __hists__add_entry(hists, al, NULL, NULL, NULL, sample, true);
 	if (he == NULL)
 		return -ENOMEM;
 
@@ -343,18 +346,19 @@
 		return ret;
 
 	argc = parse_options(argc, argv, options, annotate_usage, 0);
+	if (argc) {
+		/*
+		 * Special case: if there's an argument left then assume that
+		 * it's a symbol filter:
+		 */
+		if (argc > 1)
+			usage_with_options(annotate_usage, options);
 
-	if (annotate.use_stdio)
-		use_browser = 0;
-	else if (annotate.use_tui)
-		use_browser = 1;
-	else if (annotate.use_gtk)
-		use_browser = 2;
+		annotate.sym_hist_filter = argv[0];
+	}
 
 	file.path  = input_name;
 
-	setup_browser(true);
-
 	annotate.session = perf_session__new(&file, false, &annotate.tool);
 	if (annotate.session == NULL)
 		return -1;
@@ -366,19 +370,17 @@
 	if (ret < 0)
 		goto out_delete;
 
-	if (setup_sorting() < 0)
+	if (setup_sorting(NULL) < 0)
 		usage_with_options(annotate_usage, options);
 
-	if (argc) {
-		/*
-		 * Special case: if there's an argument left then assume that
-		 * it's a symbol filter:
-		 */
-		if (argc > 1)
-			usage_with_options(annotate_usage, options);
+	if (annotate.use_stdio)
+		use_browser = 0;
+	else if (annotate.use_tui)
+		use_browser = 1;
+	else if (annotate.use_gtk)
+		use_browser = 2;
 
-		annotate.sym_hist_filter = argv[0];
-	}
+	setup_browser(true);
 
 	ret = __cmd_annotate(&annotate);
 
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index b17aed3..a1cddc6 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -16,7 +16,7 @@
  */
 #include "perf.h"
 #include "util/util.h"
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "builtin.h"
 #include "bench/bench.h"
 
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index 7b8450c..d93bff7 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -16,7 +16,7 @@
 #include "util/cache.h"
 #include "util/debug.h"
 #include "util/header.h"
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/strlist.h"
 #include "util/build-id.h"
 #include "util/session.h"
diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c
index 918b4de..5e914ee 100644
--- a/tools/perf/builtin-buildid-list.c
+++ b/tools/perf/builtin-buildid-list.c
@@ -12,7 +12,7 @@
 #include "util/build-id.h"
 #include "util/cache.h"
 #include "util/debug.h"
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/session.h"
 #include "util/symbol.h"
 #include "util/data.h"
@@ -110,7 +110,7 @@
 	setup_pager();
 
 	if (show_kernel)
-		return sysfs__fprintf_build_id(stdout);
+		return !(sysfs__fprintf_build_id(stdout) > 0);
 
 	return perf_session__list_build_ids(force, with_hits);
 }
diff --git a/tools/perf/builtin-config.c b/tools/perf/builtin-config.c
new file mode 100644
index 0000000..f04e804
--- /dev/null
+++ b/tools/perf/builtin-config.c
@@ -0,0 +1,66 @@
+/*
+ * builtin-config.c
+ *
+ * Copyright (C) 2015, Taeung Song <treeze.taeung@gmail.com>
+ *
+ */
+#include "builtin.h"
+
+#include "perf.h"
+
+#include "util/cache.h"
+#include <subcmd/parse-options.h>
+#include "util/util.h"
+#include "util/debug.h"
+
+static const char * const config_usage[] = {
+	"perf config [options]",
+	NULL
+};
+
+enum actions {
+	ACTION_LIST = 1
+} actions;
+
+static struct option config_options[] = {
+	OPT_SET_UINT('l', "list", &actions,
+		     "show current config variables", ACTION_LIST),
+	OPT_END()
+};
+
+static int show_config(const char *key, const char *value,
+		       void *cb __maybe_unused)
+{
+	if (value)
+		printf("%s=%s\n", key, value);
+	else
+		printf("%s\n", key);
+
+	return 0;
+}
+
+int cmd_config(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+	int ret = 0;
+
+	argc = parse_options(argc, argv, config_options, config_usage,
+			     PARSE_OPT_STOP_AT_NON_OPTION);
+
+	switch (actions) {
+	case ACTION_LIST:
+		if (argc) {
+			pr_err("Error: takes no arguments\n");
+			parse_options_usage(config_usage, config_options, "l", 1);
+		} else {
+			ret = perf_config(show_config, NULL);
+			if (ret < 0)
+				pr_err("Nothing configured, "
+				       "please check your ~/.perfconfig file\n");
+		}
+		break;
+	default:
+		usage_with_options(config_usage, config_options);
+	}
+
+	return ret;
+}
diff --git a/tools/perf/builtin-data.c b/tools/perf/builtin-data.c
index d6525bc..b97bc15 100644
--- a/tools/perf/builtin-data.c
+++ b/tools/perf/builtin-data.c
@@ -2,7 +2,7 @@
 #include "builtin.h"
 #include "perf.h"
 #include "debug.h"
-#include "parse-options.h"
+#include <subcmd/parse-options.h>
 #include "data-convert-bt.h"
 
 typedef int (*data_cmd_fn_t)(int argc, const char **argv, const char *prefix);
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 0b180a8..36ccc2b 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -311,11 +311,11 @@
 }
 
 static int hists__add_entry(struct hists *hists,
-			    struct addr_location *al, u64 period,
-			    u64 weight, u64 transaction)
+			    struct addr_location *al,
+			    struct perf_sample *sample)
 {
-	if (__hists__add_entry(hists, al, NULL, NULL, NULL, period, weight,
-			       transaction, true) != NULL)
+	if (__hists__add_entry(hists, al, NULL, NULL, NULL,
+			       sample, true) != NULL)
 		return 0;
 	return -ENOMEM;
 }
@@ -336,8 +336,7 @@
 		return -1;
 	}
 
-	if (hists__add_entry(hists, &al, sample->period,
-			     sample->weight, sample->transaction)) {
+	if (hists__add_entry(hists, &al, sample)) {
 		pr_warning("problem incrementing symbol period, skipping event\n");
 		goto out_put;
 	}
@@ -1208,7 +1207,7 @@
 		BUG_ON(1);
 	}
 
-	list_add(&fmt->sort_list, &perf_hpp__sort_list);
+	perf_hpp__register_sort_field(fmt);
 	return 0;
 }
 
@@ -1280,7 +1279,7 @@
 
 	sort__mode = SORT_MODE__DIFF;
 
-	if (setup_sorting() < 0)
+	if (setup_sorting(NULL) < 0)
 		usage_with_options(diff_usage, options);
 
 	setup_pager();
diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c
index f4d6251..8a31f51 100644
--- a/tools/perf/builtin-evlist.c
+++ b/tools/perf/builtin-evlist.c
@@ -12,7 +12,7 @@
 #include "util/evlist.h"
 #include "util/evsel.h"
 #include "util/parse-events.h"
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/session.h"
 #include "util/data.h"
 #include "util/debug.h"
@@ -26,14 +26,22 @@
 		.mode = PERF_DATA_MODE_READ,
 		.force = details->force,
 	};
+	bool has_tracepoint = false;
 
 	session = perf_session__new(&file, 0, NULL);
 	if (session == NULL)
 		return -1;
 
-	evlist__for_each(session->evlist, pos)
+	evlist__for_each(session->evlist, pos) {
 		perf_evsel__fprintf(pos, details, stdout);
 
+		if (pos->attr.type == PERF_TYPE_TRACEPOINT)
+			has_tracepoint = true;
+	}
+
+	if (has_tracepoint && !details->trace_fields)
+		printf("# Tip: use 'perf evlist --trace-fields' to show fields for tracepoint events\n");
+
 	perf_session__delete(session);
 	return 0;
 }
@@ -49,6 +57,7 @@
 	OPT_BOOLEAN('g', "group", &details.event_group,
 		    "Show event group information"),
 	OPT_BOOLEAN('f', "force", &details.force, "don't complain, do it"),
+	OPT_BOOLEAN(0, "trace-fields", &details.trace_fields, "Show tracepoint fields"),
 	OPT_END()
 	};
 	const char * const evlist_usage[] = {
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index a7d588b..96c1a4c 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -6,11 +6,11 @@
 #include "perf.h"
 #include "util/cache.h"
 #include "builtin.h"
-#include "util/exec_cmd.h"
+#include <subcmd/exec-cmd.h>
 #include "common-cmds.h"
-#include "util/parse-options.h"
-#include "util/run-command.h"
-#include "util/help.h"
+#include <subcmd/parse-options.h>
+#include <subcmd/run-command.h>
+#include <subcmd/help.h>
 #include "util/debug.h"
 
 static struct man_viewer_list {
@@ -407,7 +407,7 @@
 #ifndef open_html
 static void open_html(const char *path)
 {
-	execl_perf_cmd("web--browse", "-c", "help.browser", path, NULL);
+	execl_cmd("web--browse", "-c", "help.browser", path, NULL);
 }
 #endif
 
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 99d127f..0022e02 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -18,7 +18,7 @@
 #include "util/data.h"
 #include "util/auxtrace.h"
 
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 
 #include <linux/list.h>
 
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 93ce665..1180105 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -12,7 +12,7 @@
 #include "util/tool.h"
 #include "util/callchain.h"
 
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/trace-event.h"
 #include "util/data.h"
 #include "util/cpumap.h"
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index dd94b4c..4418d921 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -10,7 +10,7 @@
 #include "util/header.h"
 #include "util/session.h"
 #include "util/intlist.h"
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/trace-event.h"
 #include "util/debug.h"
 #include "util/tool.h"
@@ -1351,7 +1351,6 @@
 	disable_buildid_cache();
 
 	use_browser = 0;
-	setup_browser(false);
 
 	if (argc) {
 		argc = parse_options(argc, argv, live_options,
@@ -1409,8 +1408,6 @@
 	err = kvm_events_live_report(kvm);
 
 out:
-	exit_browser(0);
-
 	if (kvm->session)
 		perf_session__delete(kvm->session);
 	kvm->session = NULL;
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index bf679e2..5e22db4 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -14,7 +14,7 @@
 #include "util/parse-events.h"
 #include "util/cache.h"
 #include "util/pmu.h"
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 
 int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 {
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index de16aae..ce3bfb4 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -9,7 +9,7 @@
 #include "util/thread.h"
 #include "util/header.h"
 
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/trace-event.h"
 
 #include "util/debug.h"
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 80170aa..3901700 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -1,7 +1,7 @@
 #include "builtin.h"
 #include "perf.h"
 
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/trace-event.h"
 #include "util/tool.h"
 #include "util/session.h"
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 132afc9..9af859b 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -37,7 +37,7 @@
 #include "util/strfilter.h"
 #include "util/symbol.h"
 #include "util/debug.h"
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/probe-finder.h"
 #include "util/probe-event.h"
 #include "util/probe-file.h"
@@ -249,6 +249,9 @@
 
 	return ret;
 }
+#else
+# define opt_show_lines NULL
+# define opt_show_vars NULL
 #endif
 static int opt_add_probe_event(const struct option *opt,
 			      const char *str, int unset __maybe_unused)
@@ -473,7 +476,6 @@
 		opt_add_probe_event),
 	OPT_BOOLEAN('f', "force", &probe_conf.force_add, "forcibly add events"
 		    " with existing name"),
-#ifdef HAVE_DWARF_SUPPORT
 	OPT_CALLBACK('L', "line", NULL,
 		     "FUNC[:RLN[+NUM|-RLN2]]|SRC:ALN[+NUM|-ALN2]",
 		     "Show source code lines.", opt_show_lines),
@@ -490,7 +492,6 @@
 		   "directory", "path to kernel source"),
 	OPT_BOOLEAN('\0', "no-inlines", &probe_conf.no_inlines,
 		"Don't search inlined functions"),
-#endif
 	OPT__DRY_RUN(&probe_event_dry_run),
 	OPT_INTEGER('\0', "max-probes", &probe_conf.max_probes,
 		 "Set how many probe points can be found for a probe."),
@@ -521,6 +522,16 @@
 #ifdef HAVE_DWARF_SUPPORT
 	set_option_flag(options, 'L', "line", PARSE_OPT_EXCLUSIVE);
 	set_option_flag(options, 'V', "vars", PARSE_OPT_EXCLUSIVE);
+#else
+# define set_nobuild(s, l, c) set_option_nobuild(options, s, l, "NO_DWARF=1", c)
+	set_nobuild('L', "line", false);
+	set_nobuild('V', "vars", false);
+	set_nobuild('\0', "externs", false);
+	set_nobuild('\0', "range", false);
+	set_nobuild('k', "vmlinux", true);
+	set_nobuild('s', "source", true);
+	set_nobuild('\0', "no-inlines", true);
+# undef set_nobuild
 #endif
 	set_option_flag(options, 'F', "funcs", PARSE_OPT_EXCLUSIVE);
 
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 199fc31..dc4e0ad 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -11,7 +11,7 @@
 
 #include "util/build-id.h"
 #include "util/util.h"
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/parse-events.h"
 
 #include "util/callchain.h"
@@ -452,6 +452,8 @@
 
 	if (!rec->opts.full_auxtrace)
 		perf_header__clear_feat(&session->header, HEADER_AUXTRACE);
+
+	perf_header__clear_feat(&session->header, HEADER_STAT);
 }
 
 static volatile int workload_exec_errno;
@@ -813,8 +815,12 @@
 	}
 
 	ret = parse_callchain_record_opt(arg, &callchain_param);
-	if (!ret)
+	if (!ret) {
+		/* Enable data address sampling for DWARF unwind. */
+		if (callchain_param.record_mode == CALLCHAIN_DWARF)
+			record->sample_address = true;
 		callchain_debug();
+	}
 
 	return ret;
 }
@@ -837,6 +843,19 @@
 
 static int perf_record_config(const char *var, const char *value, void *cb)
 {
+	struct record *rec = cb;
+
+	if (!strcmp(var, "record.build-id")) {
+		if (!strcmp(value, "cache"))
+			rec->no_buildid_cache = false;
+		else if (!strcmp(value, "no-cache"))
+			rec->no_buildid_cache = true;
+		else if (!strcmp(value, "skip"))
+			rec->no_buildid = true;
+		else
+			return -1;
+		return 0;
+	}
 	if (!strcmp(var, "record.call-graph"))
 		var = "call-graph.record-mode"; /* fall-through */
 
@@ -1113,12 +1132,12 @@
 			"per thread proc mmap processing timeout in ms"),
 	OPT_BOOLEAN(0, "switch-events", &record.opts.record_switch_events,
 		    "Record context switch events"),
-#ifdef HAVE_LIBBPF_SUPPORT
 	OPT_STRING(0, "clang-path", &llvm_param.clang_path, "clang path",
 		   "clang binary to use for compiling BPF scriptlets"),
 	OPT_STRING(0, "clang-opt", &llvm_param.clang_opt, "clang options",
 		   "options passed to clang when compiling BPF scriptlets"),
-#endif
+	OPT_STRING(0, "vmlinux", &symbol_conf.vmlinux_name,
+		   "file", "vmlinux pathname"),
 	OPT_END()
 };
 
@@ -1130,6 +1149,27 @@
 	struct record *rec = &record;
 	char errbuf[BUFSIZ];
 
+#ifndef HAVE_LIBBPF_SUPPORT
+# define set_nobuild(s, l, c) set_option_nobuild(record_options, s, l, "NO_LIBBPF=1", c)
+	set_nobuild('\0', "clang-path", true);
+	set_nobuild('\0', "clang-opt", true);
+# undef set_nobuild
+#endif
+
+#ifndef HAVE_BPF_PROLOGUE
+# if !defined (HAVE_DWARF_SUPPORT)
+#  define REASON  "NO_DWARF=1"
+# elif !defined (HAVE_LIBBPF_SUPPORT)
+#  define REASON  "NO_LIBBPF=1"
+# else
+#  define REASON  "this architecture doesn't support BPF prologue"
+# endif
+# define set_nobuild(s, l, c) set_option_nobuild(record_options, s, l, REASON, c)
+	set_nobuild('\0', "vmlinux", true);
+# undef set_nobuild
+# undef REASON
+#endif
+
 	rec->evlist = perf_evlist__new();
 	if (rec->evlist == NULL)
 		return -ENOMEM;
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index f256fac..d5a42ee 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -27,7 +27,7 @@
 #include "util/session.h"
 #include "util/tool.h"
 
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/parse-events.h"
 
 #include "util/thread.h"
@@ -45,7 +45,6 @@
 	struct perf_tool	tool;
 	struct perf_session	*session;
 	bool			use_tui, use_gtk, use_stdio;
-	bool			hide_unresolved;
 	bool			dont_use_callchains;
 	bool			show_full_info;
 	bool			show_threads;
@@ -146,7 +145,7 @@
 	struct hist_entry_iter iter = {
 		.evsel 			= evsel,
 		.sample 		= sample,
-		.hide_unresolved 	= rep->hide_unresolved,
+		.hide_unresolved 	= symbol_conf.hide_unresolved,
 		.add_entry_cb 		= hist_iter__report_callback,
 	};
 	int ret = 0;
@@ -157,7 +156,7 @@
 		return -1;
 	}
 
-	if (rep->hide_unresolved && al.sym == NULL)
+	if (symbol_conf.hide_unresolved && al.sym == NULL)
 		goto out_put;
 
 	if (rep->cpu_list && !test_bit(sample->cpu, rep->cpu_bitmap))
@@ -434,7 +433,7 @@
 	int ret;
 	struct perf_session *session = rep->session;
 	struct perf_evlist *evlist = session->evlist;
-	const char *help = "For a higher level overview, try: perf report --sort comm,dso";
+	const char *help = perf_tip(TIPDIR);
 
 	switch (use_browser) {
 	case 1:
@@ -514,20 +513,26 @@
 	if (rep->cpu_list) {
 		ret = perf_session__cpu_bitmap(session, rep->cpu_list,
 					       rep->cpu_bitmap);
-		if (ret)
+		if (ret) {
+			ui__error("failed to set cpu bitmap\n");
 			return ret;
+		}
 	}
 
 	if (rep->show_threads)
 		perf_read_values_init(&rep->show_threads_values);
 
 	ret = report__setup_sample_type(rep);
-	if (ret)
+	if (ret) {
+		/* report__setup_sample_type() already showed error message */
 		return ret;
+	}
 
 	ret = perf_session__process_events(session);
-	if (ret)
+	if (ret) {
+		ui__error("failed to process sample\n");
 		return ret;
+	}
 
 	report__warn_kptr_restrict(rep);
 
@@ -625,7 +630,7 @@
 	return 0;
 }
 
-#define CALLCHAIN_DEFAULT_OPT  "graph,0.5,caller,function"
+#define CALLCHAIN_DEFAULT_OPT  "graph,0.5,caller,function,percent"
 
 const char report_callchain_help[] = "Display call graph (stack chain/backtrace):\n\n"
 				     CALLCHAIN_REPORT_HELP
@@ -708,7 +713,7 @@
 	OPT_BOOLEAN('x', "exclude-other", &symbol_conf.exclude_other,
 		    "Only display entries with parent-match"),
 	OPT_CALLBACK_DEFAULT('g', "call-graph", &report,
-			     "print_type,threshold[,print_limit],order,sort_key[,branch]",
+			     "print_type,threshold[,print_limit],order,sort_key[,branch],value",
 			     report_callchain_help, &report_parse_callchain_opt,
 			     callchain_default_opt),
 	OPT_BOOLEAN(0, "children", &symbol_conf.cumulate_callchain,
@@ -740,7 +745,7 @@
 	OPT_STRING_NOEMPTY('t', "field-separator", &symbol_conf.field_sep, "separator",
 		   "separator for columns, no spaces will be added between "
 		   "columns '.' is reserved."),
-	OPT_BOOLEAN('U', "hide-unresolved", &report.hide_unresolved,
+	OPT_BOOLEAN('U', "hide-unresolved", &symbol_conf.hide_unresolved,
 		    "Only display entries resolved to a symbol"),
 	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
 		    "Look for files with symbols relative to this directory"),
@@ -783,6 +788,8 @@
 		    "Show callgraph from reference event"),
 	OPT_INTEGER(0, "socket-filter", &report.socket_filter,
 		    "only show processor socket that match with this filter"),
+	OPT_BOOLEAN(0, "raw-trace", &symbol_conf.raw_trace,
+		    "Show raw trace event output (do not use print fmt or plugins)"),
 	OPT_END()
 	};
 	struct perf_data_file file = {
@@ -796,6 +803,16 @@
 	perf_config(report__config, &report);
 
 	argc = parse_options(argc, argv, options, report_usage, 0);
+	if (argc) {
+		/*
+		 * Special case: if there's an argument left then assume that
+		 * it's a symbol filter:
+		 */
+		if (argc > 1)
+			usage_with_options(report_usage, options);
+
+		report.symbol_filter_str = argv[0];
+	}
 
 	if (symbol_conf.vmlinux_name &&
 	    access(symbol_conf.vmlinux_name, R_OK)) {
@@ -882,7 +899,7 @@
 		symbol_conf.cumulate_callchain = false;
 	}
 
-	if (setup_sorting() < 0) {
+	if (setup_sorting(session->evlist) < 0) {
 		if (sort_order)
 			parse_options_usage(report_usage, options, "s", 1);
 		if (field_order)
@@ -941,17 +958,6 @@
 	if (symbol__init(&session->header.env) < 0)
 		goto error;
 
-	if (argc) {
-		/*
-		 * Special case: if there's an argument left then assume that
-		 * it's a symbol filter:
-		 */
-		if (argc > 1)
-			usage_with_options(report_usage, options);
-
-		report.symbol_filter_str = argv[0];
-	}
-
 	sort__setup_elide(stdout);
 
 	ret = __cmd_report(&report);
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index e3d3e32..871b55ae 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -12,7 +12,7 @@
 #include "util/tool.h"
 #include "util/cloexec.h"
 
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/trace-event.h"
 
 #include "util/debug.h"
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 72b5deb..c691214 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -3,9 +3,9 @@
 #include "perf.h"
 #include "util/cache.h"
 #include "util/debug.h"
-#include "util/exec_cmd.h"
+#include <subcmd/exec-cmd.h>
 #include "util/header.h"
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/perf_regs.h"
 #include "util/session.h"
 #include "util/tool.h"
@@ -18,7 +18,11 @@
 #include "util/sort.h"
 #include "util/data.h"
 #include "util/auxtrace.h"
+#include "util/cpumap.h"
+#include "util/thread_map.h"
+#include "util/stat.h"
 #include <linux/bitmap.h>
+#include "asm/bug.h"
 
 static char const		*script_name;
 static char const		*generate_script_lang;
@@ -32,6 +36,7 @@
 static bool			nanosecs;
 static const char		*cpu_list;
 static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
+static struct perf_stat_config	stat_config;
 
 unsigned int scripting_max_stack = PERF_MAX_STACK_DEPTH;
 
@@ -130,6 +135,18 @@
 
 		.invalid_fields = PERF_OUTPUT_TRACE,
 	},
+
+	[PERF_TYPE_BREAKPOINT] = {
+		.user_set = false,
+
+		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
+			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
+			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
+			      PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
+			      PERF_OUTPUT_PERIOD,
+
+		.invalid_fields = PERF_OUTPUT_TRACE,
+	},
 };
 
 static bool output_set_by_user(void)
@@ -204,6 +221,9 @@
 	struct perf_event_attr *attr = &evsel->attr;
 	bool allow_user_set;
 
+	if (perf_header__has_feat(&session->header, HEADER_STAT))
+		return 0;
+
 	allow_user_set = perf_header__has_feat(&session->header,
 					       HEADER_AUXTRACE);
 
@@ -588,8 +608,35 @@
 	printf("  %-4s ", str);
 }
 
-static void process_event(union perf_event *event, struct perf_sample *sample,
-			  struct perf_evsel *evsel, struct addr_location *al)
+struct perf_script {
+	struct perf_tool	tool;
+	struct perf_session	*session;
+	bool			show_task_events;
+	bool			show_mmap_events;
+	bool			show_switch_events;
+	bool			allocated;
+	struct cpu_map		*cpus;
+	struct thread_map	*threads;
+	int			name_width;
+};
+
+static int perf_evlist__max_name_len(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+	int max = 0;
+
+	evlist__for_each(evlist, evsel) {
+		int len = strlen(perf_evsel__name(evsel));
+
+		max = MAX(len, max);
+	}
+
+	return max;
+}
+
+static void process_event(struct perf_script *script, union perf_event *event,
+			  struct perf_sample *sample, struct perf_evsel *evsel,
+			  struct addr_location *al)
 {
 	struct thread *thread = al->thread;
 	struct perf_event_attr *attr = &evsel->attr;
@@ -604,7 +651,12 @@
 
 	if (PRINT_FIELD(EVNAME)) {
 		const char *evname = perf_evsel__name(evsel);
-		printf("%s: ", evname ? evname : "[unknown]");
+
+		if (!script->name_width)
+			script->name_width = perf_evlist__max_name_len(script->session->evlist);
+
+		printf("%*s: ", script->name_width,
+		       evname ? evname : "[unknown]");
 	}
 
 	if (print_flags)
@@ -643,65 +695,81 @@
 	printf("\n");
 }
 
-static int default_start_script(const char *script __maybe_unused,
-				int argc __maybe_unused,
-				const char **argv __maybe_unused)
-{
-	return 0;
-}
-
-static int default_flush_script(void)
-{
-	return 0;
-}
-
-static int default_stop_script(void)
-{
-	return 0;
-}
-
-static int default_generate_script(struct pevent *pevent __maybe_unused,
-				   const char *outfile __maybe_unused)
-{
-	return 0;
-}
-
-static struct scripting_ops default_scripting_ops = {
-	.start_script		= default_start_script,
-	.flush_script		= default_flush_script,
-	.stop_script		= default_stop_script,
-	.process_event		= process_event,
-	.generate_script	= default_generate_script,
-};
-
 static struct scripting_ops	*scripting_ops;
 
+static void __process_stat(struct perf_evsel *counter, u64 tstamp)
+{
+	int nthreads = thread_map__nr(counter->threads);
+	int ncpus = perf_evsel__nr_cpus(counter);
+	int cpu, thread;
+	static int header_printed;
+
+	if (counter->system_wide)
+		nthreads = 1;
+
+	if (!header_printed) {
+		printf("%3s %8s %15s %15s %15s %15s %s\n",
+		       "CPU", "THREAD", "VAL", "ENA", "RUN", "TIME", "EVENT");
+		header_printed = 1;
+	}
+
+	for (thread = 0; thread < nthreads; thread++) {
+		for (cpu = 0; cpu < ncpus; cpu++) {
+			struct perf_counts_values *counts;
+
+			counts = perf_counts(counter->counts, cpu, thread);
+
+			printf("%3d %8d %15" PRIu64 " %15" PRIu64 " %15" PRIu64 " %15" PRIu64 " %s\n",
+				counter->cpus->map[cpu],
+				thread_map__pid(counter->threads, thread),
+				counts->val,
+				counts->ena,
+				counts->run,
+				tstamp,
+				perf_evsel__name(counter));
+		}
+	}
+}
+
+static void process_stat(struct perf_evsel *counter, u64 tstamp)
+{
+	if (scripting_ops && scripting_ops->process_stat)
+		scripting_ops->process_stat(&stat_config, counter, tstamp);
+	else
+		__process_stat(counter, tstamp);
+}
+
+static void process_stat_interval(u64 tstamp)
+{
+	if (scripting_ops && scripting_ops->process_stat_interval)
+		scripting_ops->process_stat_interval(tstamp);
+}
+
 static void setup_scripting(void)
 {
 	setup_perl_scripting();
 	setup_python_scripting();
-
-	scripting_ops = &default_scripting_ops;
 }
 
 static int flush_scripting(void)
 {
-	return scripting_ops->flush_script();
+	return scripting_ops ? scripting_ops->flush_script() : 0;
 }
 
 static int cleanup_scripting(void)
 {
 	pr_debug("\nperf script stopped\n");
 
-	return scripting_ops->stop_script();
+	return scripting_ops ? scripting_ops->stop_script() : 0;
 }
 
-static int process_sample_event(struct perf_tool *tool __maybe_unused,
+static int process_sample_event(struct perf_tool *tool,
 				union perf_event *event,
 				struct perf_sample *sample,
 				struct perf_evsel *evsel,
 				struct machine *machine)
 {
+	struct perf_script *scr = container_of(tool, struct perf_script, tool);
 	struct addr_location al;
 
 	if (debug_mode) {
@@ -727,20 +795,16 @@
 	if (cpu_list && !test_bit(sample->cpu, cpu_bitmap))
 		goto out_put;
 
-	scripting_ops->process_event(event, sample, evsel, &al);
+	if (scripting_ops)
+		scripting_ops->process_event(event, sample, evsel, &al);
+	else
+		process_event(scr, event, sample, evsel, &al);
+
 out_put:
 	addr_location__put(&al);
 	return 0;
 }
 
-struct perf_script {
-	struct perf_tool	tool;
-	struct perf_session	*session;
-	bool			show_task_events;
-	bool			show_mmap_events;
-	bool			show_switch_events;
-};
-
 static int process_attr(struct perf_tool *tool, union perf_event *event,
 			struct perf_evlist **pevlist)
 {
@@ -1156,6 +1220,8 @@
 			type = PERF_TYPE_TRACEPOINT;
 		else if (!strcmp(str, "raw"))
 			type = PERF_TYPE_RAW;
+		else if (!strcmp(str, "break"))
+			type = PERF_TYPE_BREAKPOINT;
 		else {
 			fprintf(stderr, "Invalid event type in field string.\n");
 			rc = -EINVAL;
@@ -1421,7 +1487,7 @@
 	char first_half[BUFSIZ];
 	char *script_root;
 
-	snprintf(scripts_path, MAXPATHLEN, "%s/scripts", perf_exec_path());
+	snprintf(scripts_path, MAXPATHLEN, "%s/scripts", get_argv_exec_path());
 
 	scripts_dir = opendir(scripts_path);
 	if (!scripts_dir)
@@ -1542,7 +1608,7 @@
 	if (!session)
 		return -1;
 
-	snprintf(scripts_path, MAXPATHLEN, "%s/scripts", perf_exec_path());
+	snprintf(scripts_path, MAXPATHLEN, "%s/scripts", get_argv_exec_path());
 
 	scripts_dir = opendir(scripts_path);
 	if (!scripts_dir) {
@@ -1600,7 +1666,7 @@
 	char lang_path[MAXPATHLEN];
 	char *__script_root;
 
-	snprintf(scripts_path, MAXPATHLEN, "%s/scripts", perf_exec_path());
+	snprintf(scripts_path, MAXPATHLEN, "%s/scripts", get_argv_exec_path());
 
 	scripts_dir = opendir(scripts_path);
 	if (!scripts_dir)
@@ -1695,6 +1761,87 @@
 	}
 }
 
+static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
+				    union perf_event *event,
+				    struct perf_session *session)
+{
+	struct stat_round_event *round = &event->stat_round;
+	struct perf_evsel *counter;
+
+	evlist__for_each(session->evlist, counter) {
+		perf_stat_process_counter(&stat_config, counter);
+		process_stat(counter, round->time);
+	}
+
+	process_stat_interval(round->time);
+	return 0;
+}
+
+static int process_stat_config_event(struct perf_tool *tool __maybe_unused,
+				     union perf_event *event,
+				     struct perf_session *session __maybe_unused)
+{
+	perf_event__read_stat_config(&stat_config, &event->stat_config);
+	return 0;
+}
+
+static int set_maps(struct perf_script *script)
+{
+	struct perf_evlist *evlist = script->session->evlist;
+
+	if (!script->cpus || !script->threads)
+		return 0;
+
+	if (WARN_ONCE(script->allocated, "stats double allocation\n"))
+		return -EINVAL;
+
+	perf_evlist__set_maps(evlist, script->cpus, script->threads);
+
+	if (perf_evlist__alloc_stats(evlist, true))
+		return -ENOMEM;
+
+	script->allocated = true;
+	return 0;
+}
+
+static
+int process_thread_map_event(struct perf_tool *tool,
+			     union perf_event *event,
+			     struct perf_session *session __maybe_unused)
+{
+	struct perf_script *script = container_of(tool, struct perf_script, tool);
+
+	if (script->threads) {
+		pr_warning("Extra thread map event, ignoring.\n");
+		return 0;
+	}
+
+	script->threads = thread_map__new_event(&event->thread_map);
+	if (!script->threads)
+		return -ENOMEM;
+
+	return set_maps(script);
+}
+
+static
+int process_cpu_map_event(struct perf_tool *tool __maybe_unused,
+			  union perf_event *event,
+			  struct perf_session *session __maybe_unused)
+{
+	struct perf_script *script = container_of(tool, struct perf_script, tool);
+
+	if (script->cpus) {
+		pr_warning("Extra cpu map event, ignoring.\n");
+		return 0;
+	}
+
+	script->cpus = cpu_map__new_data(&event->cpu_map.data);
+	if (!script->cpus)
+		return -ENOMEM;
+
+	return set_maps(script);
+}
+
 int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	bool show_full_info = false;
@@ -1723,6 +1870,11 @@
 			.auxtrace_info	 = perf_event__process_auxtrace_info,
 			.auxtrace	 = perf_event__process_auxtrace,
 			.auxtrace_error	 = perf_event__process_auxtrace_error,
+			.stat		 = perf_event__process_stat_event,
+			.stat_round	 = process_stat_round_event,
+			.stat_config	 = process_stat_config_event,
+			.thread_map	 = process_thread_map_event,
+			.cpu_map	 = process_cpu_map_event,
 			.ordered_events	 = true,
 			.ordering_requires_timestamps = true,
 		},
@@ -1836,7 +1988,7 @@
 		scripting_max_stack = itrace_synth_opts.callchain_sz;
 
 	/* make sure PERF_EXEC_PATH is set for scripts */
-	perf_set_argv_exec_path(perf_exec_path());
+	set_argv_exec_path(get_argv_exec_path());
 
 	if (argc && !script_name && !rec_script_path && !rep_script_path) {
 		int live_pipe[2];
@@ -2076,6 +2228,7 @@
 	flush_scripting();
 
 out_delete:
+	perf_evlist__free_stats(session->evlist);
 	perf_session__delete(session);
 
 	if (script_started)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index e77880b..7f56824 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -45,7 +45,7 @@
 #include "builtin.h"
 #include "util/cgroup.h"
 #include "util/util.h"
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/parse-events.h"
 #include "util/pmu.h"
 #include "util/event.h"
@@ -59,6 +59,9 @@
 #include "util/thread.h"
 #include "util/thread_map.h"
 #include "util/counts.h"
+#include "util/session.h"
+#include "util/tool.h"
+#include "asm/bug.h"
 
 #include <stdlib.h>
 #include <sys/prctl.h>
@@ -126,6 +129,21 @@
 static const char		*output_name;
 static int			output_fd;
 
+struct perf_stat {
+	bool			 record;
+	struct perf_data_file	 file;
+	struct perf_session	*session;
+	u64			 bytes_written;
+	struct perf_tool	 tool;
+	bool			 maps_allocated;
+	struct cpu_map		*cpus;
+	struct thread_map	*threads;
+	enum aggr_mode		 aggr_mode;
+};
+
+static struct perf_stat		perf_stat;
+#define STAT_RECORD		perf_stat.record
+
 static volatile int done = 0;
 
 static struct perf_stat_config stat_config = {
@@ -161,15 +179,43 @@
 
 	attr->inherit = !no_inherit;
 
-	if (target__has_cpu(&target))
-		return perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel));
+	/*
+	 * Some events get initialized with sample_(period/type) set,
+	 * like tracepoints. Clear it up for counting.
+	 */
+	attr->sample_period = 0;
 
-	if (!target__has_task(&target) && perf_evsel__is_group_leader(evsel)) {
+	/*
+	 * But set sample_type to PERF_SAMPLE_IDENTIFIER, which should be harmless
+	 * while avoiding that older tools show confusing messages.
+	 *
+	 * However for pipe sessions we need to keep it zero,
+	 * because script's perf_evsel__check_attr is triggered
+	 * by attr->sample_type != 0, and we can't run it on
+	 * stat sessions.
+	 */
+	if (!(STAT_RECORD && perf_stat.file.is_pipe))
+		attr->sample_type = PERF_SAMPLE_IDENTIFIER;
+
+	/*
+	 * Disabling all counters initially, they will be enabled
+	 * either manually by us or by kernel via enable_on_exec
+	 * set later.
+	 */
+	if (perf_evsel__is_group_leader(evsel)) {
 		attr->disabled = 1;
-		if (!initial_delay)
+
+		/*
+		 * In case of initial_delay we enable tracee
+		 * events manually.
+		 */
+		if (target__none(&target) && !initial_delay)
 			attr->enable_on_exec = 1;
 	}
 
+	if (target__has_cpu(&target))
+		return perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel));
+
 	return perf_evsel__open_per_thread(evsel, evsel_list->threads);
 }
 
@@ -185,6 +231,42 @@
 	return 0;
 }
 
+static int process_synthesized_event(struct perf_tool *tool __maybe_unused,
+				     union perf_event *event,
+				     struct perf_sample *sample __maybe_unused,
+				     struct machine *machine __maybe_unused)
+{
+	if (perf_data_file__write(&perf_stat.file, event, event->header.size) < 0) {
+		pr_err("failed to write perf data, error: %m\n");
+		return -1;
+	}
+
+	perf_stat.bytes_written += event->header.size;
+	return 0;
+}
+
+static int write_stat_round_event(u64 tm, u64 type)
+{
+	return perf_event__synthesize_stat_round(NULL, tm, type,
+						 process_synthesized_event,
+						 NULL);
+}
+
+#define WRITE_STAT_ROUND_EVENT(time, interval) \
+	write_stat_round_event(time, PERF_STAT_ROUND_TYPE__ ## interval)
+
+#define SID(e, x, y) xyarray__entry(e->sample_id, x, y)
+
+static int
+perf_evsel__write_stat_event(struct perf_evsel *counter, u32 cpu, u32 thread,
+			     struct perf_counts_values *count)
+{
+	struct perf_sample_id *sid = SID(counter, cpu, thread);
+
+	return perf_event__synthesize_stat(NULL, cpu, thread, sid->id, count,
+					   process_synthesized_event, NULL);
+}
+
 /*
  * Read out the results of a single counter:
  * do not aggregate counts across CPUs in system-wide mode
@@ -208,6 +290,13 @@
 			count = perf_counts(counter->counts, cpu, thread);
 			if (perf_evsel__read(counter, cpu, thread, count))
 				return -1;
+
+			if (STAT_RECORD) {
+				if (perf_evsel__write_stat_event(counter, cpu, thread, count)) {
+					pr_err("failed to write stat event\n");
+					return -1;
+				}
+			}
 		}
 	}
 
@@ -241,21 +330,26 @@
 	clock_gettime(CLOCK_MONOTONIC, &ts);
 	diff_timespec(&rs, &ts, &ref_time);
 
+	if (STAT_RECORD) {
+		if (WRITE_STAT_ROUND_EVENT(rs.tv_sec * NSECS_PER_SEC + rs.tv_nsec, INTERVAL))
+			pr_err("failed to write stat round event\n");
+	}
+
 	print_counters(&rs, 0, NULL);
 }
 
-static void handle_initial_delay(void)
+static void enable_counters(void)
 {
-	struct perf_evsel *counter;
-
-	if (initial_delay) {
-		const int ncpus = cpu_map__nr(evsel_list->cpus),
-			nthreads = thread_map__nr(evsel_list->threads);
-
+	if (initial_delay)
 		usleep(initial_delay * 1000);
-		evlist__for_each(evsel_list, counter)
-			perf_evsel__enable(counter, ncpus, nthreads);
-	}
+
+	/*
+	 * We need to enable counters only if:
+	 * - we don't have tracee (attaching to task or cpu)
+	 * - we have initial delay configured
+	 */
+	if (!target__none(&target) || initial_delay)
+		perf_evlist__enable(evsel_list);
 }
 
 static volatile int workload_exec_errno;
@@ -271,6 +365,135 @@
 	workload_exec_errno = info->si_value.sival_int;
 }
 
+static bool has_unit(struct perf_evsel *counter)
+{
+	return counter->unit && *counter->unit;
+}
+
+static bool has_scale(struct perf_evsel *counter)
+{
+	return counter->scale != 1;
+}
+
+static int perf_stat_synthesize_config(bool is_pipe)
+{
+	struct perf_evsel *counter;
+	int err;
+
+	if (is_pipe) {
+		err = perf_event__synthesize_attrs(NULL, perf_stat.session,
+						   process_synthesized_event);
+		if (err < 0) {
+			pr_err("Couldn't synthesize attrs.\n");
+			return err;
+		}
+	}
+
+	/*
+	 * Synthesize other events stuff not carried within
+	 * attr event - unit, scale, name
+	 */
+	evlist__for_each(evsel_list, counter) {
+		if (!counter->supported)
+			continue;
+
+		/*
+		 * Synthesize unit and scale only if it's defined.
+		 */
+		if (has_unit(counter)) {
+			err = perf_event__synthesize_event_update_unit(NULL, counter, process_synthesized_event);
+			if (err < 0) {
+				pr_err("Couldn't synthesize evsel unit.\n");
+				return err;
+			}
+		}
+
+		if (has_scale(counter)) {
+			err = perf_event__synthesize_event_update_scale(NULL, counter, process_synthesized_event);
+			if (err < 0) {
+				pr_err("Couldn't synthesize evsel scale.\n");
+				return err;
+			}
+		}
+
+		if (counter->own_cpus) {
+			err = perf_event__synthesize_event_update_cpus(NULL, counter, process_synthesized_event);
+			if (err < 0) {
+				pr_err("Couldn't synthesize evsel scale.\n");
+				return err;
+			}
+		}
+
+		/*
+		 * Name is needed only for pipe output,
+		 * perf.data carries event names.
+		 */
+		if (is_pipe) {
+			err = perf_event__synthesize_event_update_name(NULL, counter, process_synthesized_event);
+			if (err < 0) {
+				pr_err("Couldn't synthesize evsel name.\n");
+				return err;
+			}
+		}
+	}
+
+	err = perf_event__synthesize_thread_map2(NULL, evsel_list->threads,
+						process_synthesized_event,
+						NULL);
+	if (err < 0) {
+		pr_err("Couldn't synthesize thread map.\n");
+		return err;
+	}
+
+	err = perf_event__synthesize_cpu_map(NULL, evsel_list->cpus,
+					     process_synthesized_event, NULL);
+	if (err < 0) {
+		pr_err("Couldn't synthesize thread map.\n");
+		return err;
+	}
+
+	err = perf_event__synthesize_stat_config(NULL, &stat_config,
+						 process_synthesized_event, NULL);
+	if (err < 0) {
+		pr_err("Couldn't synthesize config.\n");
+		return err;
+	}
+
+	return 0;
+}
+
+#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
+
+static int __store_counter_ids(struct perf_evsel *counter,
+			       struct cpu_map *cpus,
+			       struct thread_map *threads)
+{
+	int cpu, thread;
+
+	for (cpu = 0; cpu < cpus->nr; cpu++) {
+		for (thread = 0; thread < threads->nr; thread++) {
+			int fd = FD(counter, cpu, thread);
+
+			if (perf_evlist__id_add_fd(evsel_list, counter,
+						   cpu, thread, fd) < 0)
+				return -1;
+		}
+	}
+
+	return 0;
+}
+
+static int store_counter_ids(struct perf_evsel *counter)
+{
+	struct cpu_map *cpus = counter->cpus;
+	struct thread_map *threads = counter->threads;
+
+	if (perf_evsel__alloc_id(counter, cpus->nr, threads->nr))
+		return -ENOMEM;
+
+	return __store_counter_ids(counter, cpus, threads);
+}
+
 static int __run_perf_stat(int argc, const char **argv)
 {
 	int interval = stat_config.interval;
@@ -281,6 +504,7 @@
 	size_t l;
 	int status = 0;
 	const bool forks = (argc > 0);
+	bool is_pipe = STAT_RECORD ? perf_stat.file.is_pipe : false;
 
 	if (interval) {
 		ts.tv_sec  = interval / 1000;
@@ -291,7 +515,7 @@
 	}
 
 	if (forks) {
-		if (perf_evlist__prepare_workload(evsel_list, &target, argv, false,
+		if (perf_evlist__prepare_workload(evsel_list, &target, argv, is_pipe,
 						  workload_exec_failed_signal) < 0) {
 			perror("failed to prepare workload");
 			return -1;
@@ -335,6 +559,9 @@
 		l = strlen(counter->unit);
 		if (l > unit_width)
 			unit_width = l;
+
+		if (STAT_RECORD && store_counter_ids(counter))
+			return -1;
 	}
 
 	if (perf_evlist__apply_filters(evsel_list, &counter)) {
@@ -344,6 +571,24 @@
 		return -1;
 	}
 
+	if (STAT_RECORD) {
+		int err, fd = perf_data_file__fd(&perf_stat.file);
+
+		if (is_pipe) {
+			err = perf_header__write_pipe(perf_data_file__fd(&perf_stat.file));
+		} else {
+			err = perf_session__write_header(perf_stat.session, evsel_list,
+							 fd, false);
+		}
+
+		if (err < 0)
+			return err;
+
+		err = perf_stat_synthesize_config(is_pipe);
+		if (err < 0)
+			return err;
+	}
+
 	/*
 	 * Enable counters and exec the command:
 	 */
@@ -352,7 +597,7 @@
 
 	if (forks) {
 		perf_evlist__start_workload(evsel_list);
-		handle_initial_delay();
+		enable_counters();
 
 		if (interval) {
 			while (!waitpid(child_pid, &status, WNOHANG)) {
@@ -371,7 +616,7 @@
 		if (WIFSIGNALED(status))
 			psignal(WTERMSIG(status), argv[0]);
 	} else {
-		handle_initial_delay();
+		enable_counters();
 		while (!done) {
 			nanosleep(&ts, NULL);
 			if (interval)
@@ -810,8 +1055,8 @@
 		else if (target.cpu_list)
 			fprintf(output, "\'CPU(s) %s", target.cpu_list);
 		else if (!target__has_task(&target)) {
-			fprintf(output, "\'%s", argv[0]);
-			for (i = 1; i < argc; i++)
+			fprintf(output, "\'%s", argv ? argv[0] : "pipe");
+			for (i = 1; argv && (i < argc); i++)
 				fprintf(output, " %s", argv[i]);
 		} else if (target.pid)
 			fprintf(output, "process id \'%s", target.pid);
@@ -847,6 +1092,10 @@
 	struct perf_evsel *counter;
 	char buf[64], *prefix = NULL;
 
+	/* Do not print anything if we record to the pipe. */
+	if (STAT_RECORD && perf_stat.file.is_pipe)
+		return;
+
 	if (interval)
 		print_interval(prefix = buf, ts);
 	else
@@ -1077,6 +1326,109 @@
 	return cpus_aggr_map ? 0 : -ENOMEM;
 }
 
+static void perf_stat__exit_aggr_mode(void)
+{
+	cpu_map__put(aggr_map);
+	cpu_map__put(cpus_aggr_map);
+	aggr_map = NULL;
+	cpus_aggr_map = NULL;
+}
+
+static inline int perf_env__get_cpu(struct perf_env *env, struct cpu_map *map, int idx)
+{
+	int cpu;
+
+	if (idx > map->nr)
+		return -1;
+
+	cpu = map->map[idx];
+
+	if (cpu >= env->nr_cpus_online)
+		return -1;
+
+	return cpu;
+}
+
+static int perf_env__get_socket(struct cpu_map *map, int idx, void *data)
+{
+	struct perf_env *env = data;
+	int cpu = perf_env__get_cpu(env, map, idx);
+
+	return cpu == -1 ? -1 : env->cpu[cpu].socket_id;
+}
+
+static int perf_env__get_core(struct cpu_map *map, int idx, void *data)
+{
+	struct perf_env *env = data;
+	int core = -1, cpu = perf_env__get_cpu(env, map, idx);
+
+	if (cpu != -1) {
+		int socket_id = env->cpu[cpu].socket_id;
+
+		/*
+		 * Encode socket in upper 16 bits
+		 * core_id is relative to socket, and
+		 * we need a global id. So we combine
+		 * socket + core id.
+		 */
+		core = (socket_id << 16) | (env->cpu[cpu].core_id & 0xffff);
+	}
+
+	return core;
+}
+
+static int perf_env__build_socket_map(struct perf_env *env, struct cpu_map *cpus,
+				      struct cpu_map **sockp)
+{
+	return cpu_map__build_map(cpus, sockp, perf_env__get_socket, env);
+}
+
+static int perf_env__build_core_map(struct perf_env *env, struct cpu_map *cpus,
+				    struct cpu_map **corep)
+{
+	return cpu_map__build_map(cpus, corep, perf_env__get_core, env);
+}
+
+static int perf_stat__get_socket_file(struct cpu_map *map, int idx)
+{
+	return perf_env__get_socket(map, idx, &perf_stat.session->header.env);
+}
+
+static int perf_stat__get_core_file(struct cpu_map *map, int idx)
+{
+	return perf_env__get_core(map, idx, &perf_stat.session->header.env);
+}
+
+static int perf_stat_init_aggr_mode_file(struct perf_stat *st)
+{
+	struct perf_env *env = &st->session->header.env;
+
+	switch (stat_config.aggr_mode) {
+	case AGGR_SOCKET:
+		if (perf_env__build_socket_map(env, evsel_list->cpus, &aggr_map)) {
+			perror("cannot build socket map");
+			return -1;
+		}
+		aggr_get_id = perf_stat__get_socket_file;
+		break;
+	case AGGR_CORE:
+		if (perf_env__build_core_map(env, evsel_list->cpus, &aggr_map)) {
+			perror("cannot build core map");
+			return -1;
+		}
+		aggr_get_id = perf_stat__get_core_file;
+		break;
+	case AGGR_NONE:
+	case AGGR_GLOBAL:
+	case AGGR_THREAD:
+	case AGGR_UNSET:
+	default:
+		break;
+	}
+
+	return 0;
+}
+
 /*
  * Add default attributes, if there were no attributes specified or
  * if -d/--detailed, -d -d or -d -d -d is used:
@@ -1236,6 +1588,225 @@
 	return perf_evlist__add_default_attrs(evsel_list, very_very_detailed_attrs);
 }
 
+static const char * const recort_usage[] = {
+	"perf stat record [<options>]",
+	NULL,
+};
+
+static void init_features(struct perf_session *session)
+{
+	int feat;
+
+	for (feat = HEADER_FIRST_FEATURE; feat < HEADER_LAST_FEATURE; feat++)
+		perf_header__set_feat(&session->header, feat);
+
+	perf_header__clear_feat(&session->header, HEADER_BUILD_ID);
+	perf_header__clear_feat(&session->header, HEADER_TRACING_DATA);
+	perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK);
+	perf_header__clear_feat(&session->header, HEADER_AUXTRACE);
+}
+
+static int __cmd_record(int argc, const char **argv)
+{
+	struct perf_session *session;
+	struct perf_data_file *file = &perf_stat.file;
+
+	argc = parse_options(argc, argv, stat_options, record_usage,
+			     PARSE_OPT_STOP_AT_NON_OPTION);
+
+	if (output_name)
+		file->path = output_name;
+
+	if (run_count != 1 || forever) {
+		pr_err("Cannot use -r option with perf stat record.\n");
+		return -1;
+	}
+
+	session = perf_session__new(file, false, NULL);
+	if (session == NULL) {
+		pr_err("Perf session creation failed.\n");
+		return -1;
+	}
+
+	init_features(session);
+
+	session->evlist   = evsel_list;
+	perf_stat.session = session;
+	perf_stat.record  = true;
+	return argc;
+}
+
+static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
+				    union perf_event *event,
+				    struct perf_session *session)
+{
+	struct stat_round_event *round = &event->stat_round;
+	struct perf_evsel *counter;
+	struct timespec tsh, *ts = NULL;
+	const char **argv = session->header.env.cmdline_argv;
+	int argc = session->header.env.nr_cmdline;
+
+	evlist__for_each(evsel_list, counter)
+		perf_stat_process_counter(&stat_config, counter);
+
+	if (round->type == PERF_STAT_ROUND_TYPE__FINAL)
+		update_stats(&walltime_nsecs_stats, round->time);
+
+	if (stat_config.interval && round->time) {
+		tsh.tv_sec  = round->time / NSECS_PER_SEC;
+		tsh.tv_nsec = round->time % NSECS_PER_SEC;
+		ts = &tsh;
+	}
+
+	print_counters(ts, argc, argv);
+	return 0;
+}
+
+static
+int process_stat_config_event(struct perf_tool *tool __maybe_unused,
+			      union perf_event *event,
+			      struct perf_session *session __maybe_unused)
+{
+	struct perf_stat *st = container_of(tool, struct perf_stat, tool);
+
+	perf_event__read_stat_config(&stat_config, &event->stat_config);
+
+	if (cpu_map__empty(st->cpus)) {
+		if (st->aggr_mode != AGGR_UNSET)
+			pr_warning("warning: processing task data, aggregation mode not set\n");
+		return 0;
+	}
+
+	if (st->aggr_mode != AGGR_UNSET)
+		stat_config.aggr_mode = st->aggr_mode;
+
+	if (perf_stat.file.is_pipe)
+		perf_stat_init_aggr_mode();
+	else
+		perf_stat_init_aggr_mode_file(st);
+
+	return 0;
+}
+
+static int set_maps(struct perf_stat *st)
+{
+	if (!st->cpus || !st->threads)
+		return 0;
+
+	if (WARN_ONCE(st->maps_allocated, "stats double allocation\n"))
+		return -EINVAL;
+
+	perf_evlist__set_maps(evsel_list, st->cpus, st->threads);
+
+	if (perf_evlist__alloc_stats(evsel_list, true))
+		return -ENOMEM;
+
+	st->maps_allocated = true;
+	return 0;
+}
+
+static
+int process_thread_map_event(struct perf_tool *tool __maybe_unused,
+			     union perf_event *event,
+			     struct perf_session *session __maybe_unused)
+{
+	struct perf_stat *st = container_of(tool, struct perf_stat, tool);
+
+	if (st->threads) {
+		pr_warning("Extra thread map event, ignoring.\n");
+		return 0;
+	}
+
+	st->threads = thread_map__new_event(&event->thread_map);
+	if (!st->threads)
+		return -ENOMEM;
+
+	return set_maps(st);
+}
+
+static
+int process_cpu_map_event(struct perf_tool *tool __maybe_unused,
+			  union perf_event *event,
+			  struct perf_session *session __maybe_unused)
+{
+	struct perf_stat *st = container_of(tool, struct perf_stat, tool);
+	struct cpu_map *cpus;
+
+	if (st->cpus) {
+		pr_warning("Extra cpu map event, ignoring.\n");
+		return 0;
+	}
+
+	cpus = cpu_map__new_data(&event->cpu_map.data);
+	if (!cpus)
+		return -ENOMEM;
+
+	st->cpus = cpus;
+	return set_maps(st);
+}
+
+static const char * const report_usage[] = {
+	"perf stat report [<options>]",
+	NULL,
+};
+
+static struct perf_stat perf_stat = {
+	.tool = {
+		.attr		= perf_event__process_attr,
+		.event_update	= perf_event__process_event_update,
+		.thread_map	= process_thread_map_event,
+		.cpu_map	= process_cpu_map_event,
+		.stat_config	= process_stat_config_event,
+		.stat		= perf_event__process_stat_event,
+		.stat_round	= process_stat_round_event,
+	},
+	.aggr_mode = AGGR_UNSET,
+};
+
+static int __cmd_report(int argc, const char **argv)
+{
+	struct perf_session *session;
+	const struct option options[] = {
+	OPT_STRING('i', "input", &input_name, "file", "input file name"),
+	OPT_SET_UINT(0, "per-socket", &perf_stat.aggr_mode,
+		     "aggregate counts per processor socket", AGGR_SOCKET),
+	OPT_SET_UINT(0, "per-core", &perf_stat.aggr_mode,
+		     "aggregate counts per physical processor core", AGGR_CORE),
+	OPT_SET_UINT('A', "no-aggr", &perf_stat.aggr_mode,
+		     "disable CPU count aggregation", AGGR_NONE),
+	OPT_END()
+	};
+	struct stat st;
+	int ret;
+
+	argc = parse_options(argc, argv, options, report_usage, 0);
+
+	if (!input_name || !strlen(input_name)) {
+		if (!fstat(STDIN_FILENO, &st) && S_ISFIFO(st.st_mode))
+			input_name = "-";
+		else
+			input_name = "perf.data";
+	}
+
+	perf_stat.file.path = input_name;
+	perf_stat.file.mode = PERF_DATA_MODE_READ;
+
+	session = perf_session__new(&perf_stat.file, false, &perf_stat.tool);
+	if (session == NULL)
+		return -1;
+
+	perf_stat.session  = session;
+	stat_config.output = stderr;
+	evsel_list         = session->evlist;
+
+	ret = perf_session__process_events(session);
+	if (ret)
+		return ret;
+
+	perf_session__delete(session);
+	return 0;
+}
+
 int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	const char * const stat_usage[] = {
@@ -1246,6 +1817,7 @@
 	const char *mode;
 	FILE *output = stderr;
 	unsigned int interval;
+	const char * const stat_subcommands[] = { "record", "report" };
 
 	setlocale(LC_ALL, "");
 
@@ -1253,12 +1825,30 @@
 	if (evsel_list == NULL)
 		return -ENOMEM;
 
-	argc = parse_options(argc, argv, stat_options, stat_usage,
-		PARSE_OPT_STOP_AT_NON_OPTION);
+	argc = parse_options_subcommand(argc, argv, stat_options, stat_subcommands,
+					(const char **) stat_usage,
+					PARSE_OPT_STOP_AT_NON_OPTION);
+
+	if (csv_sep) {
+		csv_output = true;
+		if (!strcmp(csv_sep, "\\t"))
+			csv_sep = "\t";
+	} else
+		csv_sep = DEFAULT_SEPARATOR;
+
+	if (argc && !strncmp(argv[0], "rec", 3)) {
+		argc = __cmd_record(argc, argv);
+		if (argc < 0)
+			return -1;
+	} else if (argc && !strncmp(argv[0], "rep", 3))
+		return __cmd_report(argc, argv);
 
 	interval = stat_config.interval;
 
-	if (output_name && strcmp(output_name, "-"))
+	/*
+	 * For record command the -o is already taken care of.
+	 */
+	if (!STAT_RECORD && output_name && strcmp(output_name, "-"))
 		output = NULL;
 
 	if (output_name && output_fd) {
@@ -1296,13 +1886,6 @@
 
 	stat_config.output = output;
 
-	if (csv_sep) {
-		csv_output = true;
-		if (!strcmp(csv_sep, "\\t"))
-			csv_sep = "\t";
-	} else
-		csv_sep = DEFAULT_SEPARATOR;
-
 	/*
 	 * let the spreadsheet do the pretty-printing
 	 */
@@ -1425,6 +2008,42 @@
 	if (!forever && status != -1 && !interval)
 		print_counters(NULL, argc, argv);
 
+	if (STAT_RECORD) {
+		/*
+		 * We synthesize the kernel mmap record just so that older tools
+		 * don't emit warnings about not being able to resolve symbols
+		 * due to /proc/sys/kernel/kptr_restrict settings and instear provide
+		 * a saner message about no samples being in the perf.data file.
+		 *
+		 * This also serves to suppress a warning about f_header.data.size == 0
+		 * in header.c at the moment 'perf stat record' gets introduced, which
+		 * is not really needed once we start adding the stat specific PERF_RECORD_
+		 * records, but the need to suppress the kptr_restrict messages in older
+		 * tools remain  -acme
+		 */
+		int fd = perf_data_file__fd(&perf_stat.file);
+		int err = perf_event__synthesize_kernel_mmap((void *)&perf_stat,
+							     process_synthesized_event,
+							     &perf_stat.session->machines.host);
+		if (err) {
+			pr_warning("Couldn't synthesize the kernel mmap record, harmless, "
+				   "older tools may produce warnings about this file\n.");
+		}
+
+		if (!interval) {
+			if (WRITE_STAT_ROUND_EVENT(walltime_nsecs_stats.max, FINAL))
+				pr_err("failed to write stat round event\n");
+		}
+
+		if (!perf_stat.file.is_pipe) {
+			perf_stat.session->header.data_size += perf_stat.bytes_written;
+			perf_session__write_header(perf_stat.session, evsel_list, fd, true);
+		}
+
+		perf_session__delete(perf_stat.session);
+	}
+
+	perf_stat__exit_aggr_mode();
 	perf_evlist__free_stats(evsel_list);
 out:
 	perf_evlist__delete(evsel_list);
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 30e5962..bd7a775 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -30,7 +30,7 @@
 
 #include "perf.h"
 #include "util/header.h"
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/parse-events.h"
 #include "util/event.h"
 #include "util/session.h"
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 7e2e72e..bf01cbb 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -34,7 +34,7 @@
 #include "util/top.h"
 #include "util/util.h"
 #include <linux/rbtree.h>
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/parse-events.h"
 #include "util/cpumap.h"
 #include "util/xyarray.h"
@@ -175,42 +175,40 @@
 					int counter, u64 ip)
 {
 	struct annotation *notes;
-	struct symbol *sym;
+	struct symbol *sym = he->ms.sym;
 	int err = 0;
 
-	if (he == NULL || he->ms.sym == NULL ||
-	    ((top->sym_filter_entry == NULL ||
-	      top->sym_filter_entry->ms.sym != he->ms.sym) && use_browser != 1))
+	if (sym == NULL || (use_browser == 0 &&
+			    (top->sym_filter_entry == NULL ||
+			     top->sym_filter_entry->ms.sym != sym)))
 		return;
 
-	sym = he->ms.sym;
 	notes = symbol__annotation(sym);
 
 	if (pthread_mutex_trylock(&notes->lock))
 		return;
 
-	ip = he->ms.map->map_ip(he->ms.map, ip);
-
-	if (ui__has_annotation())
-		err = hist_entry__inc_addr_samples(he, counter, ip);
+	err = hist_entry__inc_addr_samples(he, counter, ip);
 
 	pthread_mutex_unlock(&notes->lock);
 
-	/*
-	 * This function is now called with he->hists->lock held.
-	 * Release it before going to sleep.
-	 */
-	pthread_mutex_unlock(&he->hists->lock);
+	if (unlikely(err)) {
+		/*
+		 * This function is now called with he->hists->lock held.
+		 * Release it before going to sleep.
+		 */
+		pthread_mutex_unlock(&he->hists->lock);
 
-	if (err == -ERANGE && !he->ms.map->erange_warned)
-		ui__warn_map_erange(he->ms.map, sym, ip);
-	else if (err == -ENOMEM) {
-		pr_err("Not enough memory for annotating '%s' symbol!\n",
-		       sym->name);
-		sleep(1);
+		if (err == -ERANGE && !he->ms.map->erange_warned)
+			ui__warn_map_erange(he->ms.map, sym, ip);
+		else if (err == -ENOMEM) {
+			pr_err("Not enough memory for annotating '%s' symbol!\n",
+			       sym->name);
+			sleep(1);
+		}
+
+		pthread_mutex_lock(&he->hists->lock);
 	}
-
-	pthread_mutex_lock(&he->hists->lock);
 }
 
 static void perf_top__show_details(struct perf_top *top)
@@ -687,14 +685,8 @@
 	struct hist_entry *he = iter->he;
 	struct perf_evsel *evsel = iter->evsel;
 
-	if (sort__has_sym && single) {
-		u64 ip = al->addr;
-
-		if (al->map)
-			ip = al->map->unmap_ip(al->map, ip);
-
-		perf_top__record_precise_ip(top, he, evsel->idx, ip);
-	}
+	if (sort__has_sym && single)
+		perf_top__record_precise_ip(top, he, evsel->idx, al->addr);
 
 	hist__account_cycles(iter->sample->branch_stack, al, iter->sample,
 		     !(top->record_opts.branch_stack & PERF_SAMPLE_BRANCH_ANY));
@@ -964,7 +956,7 @@
 	if (ret)
 		goto out_delete;
 
-	if (perf_session__register_idle_thread(top->session) == NULL)
+	if (perf_session__register_idle_thread(top->session) < 0)
 		goto out_delete;
 
 	machine__synthesize_threads(&top->session->machines.host, &opts->target,
@@ -1218,6 +1210,8 @@
 	OPT_CALLBACK('j', "branch-filter", &opts->branch_stack,
 		     "branch filter mask", "branch stack filter modes",
 		     parse_branch_stack),
+	OPT_BOOLEAN(0, "raw-trace", &symbol_conf.raw_trace,
+		    "Show raw trace event output (do not use print fmt or plugins)"),
 	OPT_END()
 	};
 	const char * const top_usage[] = {
@@ -1239,11 +1233,17 @@
 	if (argc)
 		usage_with_options(top_usage, options);
 
+	if (!top.evlist->nr_entries &&
+	    perf_evlist__add_default(top.evlist) < 0) {
+		pr_err("Not enough memory for event selector list\n");
+		goto out_delete_evlist;
+	}
+
 	sort__mode = SORT_MODE__TOP;
 	/* display thread wants entries to be collapsed in a different tree */
 	sort__need_collapse = 1;
 
-	if (setup_sorting() < 0) {
+	if (setup_sorting(top.evlist) < 0) {
 		if (sort_order)
 			parse_options_usage(top_usage, options, "s", 1);
 		if (field_order)
@@ -1279,12 +1279,9 @@
 	if (target__none(target))
 		target->system_wide = true;
 
-	if (perf_evlist__create_maps(top.evlist, target) < 0)
-		usage_with_options(top_usage, options);
-
-	if (!top.evlist->nr_entries &&
-	    perf_evlist__add_default(top.evlist) < 0) {
-		ui__error("Not enough memory for event selector list\n");
+	if (perf_evlist__create_maps(top.evlist, target) < 0) {
+		ui__error("Couldn't create thread/CPU maps: %s\n",
+			  errno == ENOENT ? "No such process" : strerror_r(errno, errbuf, sizeof(errbuf)));
 		goto out_delete_evlist;
 	}
 
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index c783d8f..20916dd 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -22,11 +22,11 @@
 #include "util/color.h"
 #include "util/debug.h"
 #include "util/evlist.h"
-#include "util/exec_cmd.h"
+#include <subcmd/exec-cmd.h>
 #include "util/machine.h"
 #include "util/session.h"
 #include "util/thread.h"
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/strlist.h"
 #include "util/intlist.h"
 #include "util/thread_map.h"
diff --git a/tools/perf/builtin-version.c b/tools/perf/builtin-version.c
new file mode 100644
index 0000000..9b10cda
--- /dev/null
+++ b/tools/perf/builtin-version.c
@@ -0,0 +1,10 @@
+#include "util/util.h"
+#include "builtin.h"
+#include "perf.h"
+
+int cmd_version(int argc __maybe_unused, const char **argv __maybe_unused,
+		const char *prefix __maybe_unused)
+{
+	printf("perf version %s\n", perf_version_string);
+	return 0;
+}
diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h
index 3688ad2..3f871b5 100644
--- a/tools/perf/builtin.h
+++ b/tools/perf/builtin.h
@@ -17,6 +17,7 @@
 extern int cmd_bench(int argc, const char **argv, const char *prefix);
 extern int cmd_buildid_cache(int argc, const char **argv, const char *prefix);
 extern int cmd_buildid_list(int argc, const char **argv, const char *prefix);
+extern int cmd_config(int argc, const char **argv, const char *prefix);
 extern int cmd_diff(int argc, const char **argv, const char *prefix);
 extern int cmd_evlist(int argc, const char **argv, const char *prefix);
 extern int cmd_help(int argc, const char **argv, const char *prefix);
diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt
index 00fcaf8..ab5cbaa 100644
--- a/tools/perf/command-list.txt
+++ b/tools/perf/command-list.txt
@@ -9,6 +9,7 @@
 perf-buildid-list		mainporcelain common
 perf-data			mainporcelain common
 perf-diff			mainporcelain common
+perf-config			mainporcelain common
 perf-evlist			mainporcelain common
 perf-inject			mainporcelain common
 perf-kmem			mainporcelain common
@@ -25,4 +26,4 @@
 perf-test			mainporcelain common
 perf-timechart			mainporcelain common
 perf-top			mainporcelain common
-perf-trace			mainporcelain common
+perf-trace			mainporcelain audit
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index de89ec5..254d06e 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -135,8 +135,6 @@
 
 ifeq ($(DEBUG),0)
   CFLAGS += -O6
-else
-  CFLAGS += $(call cc-option,-Og,-O0)
 endif
 
 ifdef PARSER_DEBUG
@@ -318,6 +316,18 @@
       CFLAGS += -DHAVE_LIBBPF_SUPPORT
       $(call detected,CONFIG_LIBBPF)
     endif
+
+    ifndef NO_DWARF
+      ifdef PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET
+        CFLAGS += -DHAVE_BPF_PROLOGUE
+        $(call detected,CONFIG_BPF_PROLOGUE)
+      else
+        msg := $(warning BPF prologue is not supported by architecture $(ARCH), missing regs_query_register_offset());
+      endif
+    else
+      msg := $(warning DWARF support is off, BPF prologue is disabled);
+    endif
+
   endif # NO_LIBBPF
 endif # NO_LIBELF
 
@@ -681,6 +691,7 @@
 template_dir = share/perf-core/templates
 STRACE_GROUPS_DIR = share/perf-core/strace/groups
 htmldir = share/doc/perf-doc
+tipdir = share/doc/perf-tip
 ifeq ($(prefix),/usr)
 sysconfdir = /etc
 ETC_PERFCONFIG = $(sysconfdir)/perfconfig
@@ -707,6 +718,7 @@
 perfexecdir_SQ = $(subst ','\'',$(perfexecdir))
 template_dir_SQ = $(subst ','\'',$(template_dir))
 htmldir_SQ = $(subst ','\'',$(htmldir))
+tipdir_SQ = $(subst ','\'',$(tipdir))
 prefix_SQ = $(subst ','\'',$(prefix))
 sysconfdir_SQ = $(subst ','\'',$(sysconfdir))
 libdir_SQ = $(subst ','\'',$(libdir))
@@ -714,12 +726,15 @@
 ifneq ($(filter /%,$(firstword $(perfexecdir))),)
 perfexec_instdir = $(perfexecdir)
 STRACE_GROUPS_INSTDIR = $(STRACE_GROUPS_DIR)
+tip_instdir = $(tipdir)
 else
 perfexec_instdir = $(prefix)/$(perfexecdir)
 STRACE_GROUPS_INSTDIR = $(prefix)/$(STRACE_GROUPS_DIR)
+tip_instdir = $(prefix)/$(tipdir)
 endif
 perfexec_instdir_SQ = $(subst ','\'',$(perfexec_instdir))
 STRACE_GROUPS_INSTDIR_SQ = $(subst ','\'',$(STRACE_GROUPS_INSTDIR))
+tip_instdir_SQ = $(subst ','\'',$(tip_instdir))
 
 # If we install to $(HOME) we keep the traceevent default:
 # $(HOME)/.traceevent/plugins
@@ -741,6 +756,10 @@
   $(call print_var,sysconfdir)
   $(call print_var,LIBUNWIND_DIR)
   $(call print_var,LIBDW_DIR)
+
+  ifeq ($(dwarf-post-unwind),1)
+    $(call feature_print_text,"DWARF post unwind library", $(dwarf-post-unwind-text))
+  endif
   $(info )
 endif
 
@@ -756,6 +775,7 @@
 $(call detected_var,STRACE_GROUPS_DIR_SQ)
 $(call detected_var,prefix_SQ)
 $(call detected_var,perfexecdir_SQ)
+$(call detected_var,tipdir_SQ)
 $(call detected_var,LIBDIR)
 $(call detected_var,GTK_CFLAGS)
 $(call detected_var,PERL_EMBED_CCOPTS)
diff --git a/tools/perf/config/utilities.mak b/tools/perf/config/utilities.mak
index 0ebef09..c16ce83 100644
--- a/tools/perf/config/utilities.mak
+++ b/tools/perf/config/utilities.mak
@@ -177,22 +177,3 @@
 endef
 _ge_attempt = $(if $(get-executable),$(get-executable),$(call _gea_err,$(2)))
 _gea_err  = $(if $(1),$(error Please set '$(1)' appropriately))
-
-# try-run
-# Usage: option = $(call try-run, $(CC)...-o "$$TMP",option-ok,otherwise)
-# Exit code chooses option. "$$TMP" is can be used as temporary file and
-# is automatically cleaned up.
-try-run = $(shell set -e;		\
-	TMP="$(TMPOUT).$$$$.tmp";	\
-	TMPO="$(TMPOUT).$$$$.o";	\
-	if ($(1)) >/dev/null 2>&1;	\
-	then echo "$(2)";		\
-	else echo "$(3)";		\
-	fi;				\
-	rm -f "$$TMP" "$$TMPO")
-
-# cc-option
-# Usage: cflags-y += $(call cc-option,-march=winchip-c6,-march=i586)
-
-cc-option = $(call try-run,\
-	$(CC) $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS) $(1) -c -x c /dev/null -o "$$TMP",$(1),$(2))
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 3d4c7c0..a929618 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -9,16 +9,18 @@
 #include "builtin.h"
 
 #include "util/env.h"
-#include "util/exec_cmd.h"
+#include <subcmd/exec-cmd.h>
 #include "util/cache.h"
 #include "util/quote.h"
-#include "util/run-command.h"
+#include <subcmd/run-command.h>
 #include "util/parse-events.h"
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/bpf-loader.h"
 #include "util/debug.h"
 #include <api/fs/tracing_path.h>
 #include <pthread.h>
+#include <stdlib.h>
+#include <time.h>
 
 const char perf_usage_string[] =
 	"perf [--version] [--help] [OPTIONS] COMMAND [ARGS]";
@@ -39,6 +41,7 @@
 static struct cmd_struct commands[] = {
 	{ "buildid-cache", cmd_buildid_cache, 0 },
 	{ "buildid-list", cmd_buildid_list, 0 },
+	{ "config",	cmd_config,	0 },
 	{ "diff",	cmd_diff,	0 },
 	{ "evlist",	cmd_evlist,	0 },
 	{ "help",	cmd_help,	0 },
@@ -118,7 +121,7 @@
 {
 	switch (use_pager) {
 	case 0:
-		setenv("PERF_PAGER", "cat", 1);
+		setenv(PERF_PAGER_ENVIRONMENT, "cat", 1);
 		break;
 	case 1:
 		/* setup_pager(); */
@@ -182,9 +185,9 @@
 		if (!prefixcmp(cmd, CMD_EXEC_PATH)) {
 			cmd += strlen(CMD_EXEC_PATH);
 			if (*cmd == '=')
-				perf_set_argv_exec_path(cmd + 1);
+				set_argv_exec_path(cmd + 1);
 			else {
-				puts(perf_exec_path());
+				puts(get_argv_exec_path());
 				exit(0);
 			}
 		} else if (!strcmp(cmd, "--html-path")) {
@@ -383,6 +386,7 @@
 		use_pager = 1;
 	commit_pager_choice();
 
+	perf_env__set_cmdline(&perf_env, argc, argv);
 	status = p->fn(argc, argv, prefix);
 	exit_browser(status);
 	perf_env__exit(&perf_env);
@@ -528,14 +532,20 @@
 	const char *cmd;
 	char sbuf[STRERR_BUFSIZE];
 
+	/* libsubcmd init */
+	exec_cmd_init("perf", PREFIX, PERF_EXEC_PATH, EXEC_PATH_ENVIRONMENT);
+	pager_init(PERF_PAGER_ENVIRONMENT);
+
 	/* The page_size is placed in util object. */
 	page_size = sysconf(_SC_PAGE_SIZE);
 	cacheline_size = sysconf(_SC_LEVEL1_DCACHE_LINESIZE);
 
-	cmd = perf_extract_argv0_path(argv[0]);
+	cmd = extract_argv0_path(argv[0]);
 	if (!cmd)
 		cmd = "perf-help";
 
+	srandom(time(NULL));
+
 	/* get debugfs/tracefs mount point from /proc/mounts */
 	tracing_path_mount();
 
diff --git a/tools/perf/scripts/python/stat-cpi.py b/tools/perf/scripts/python/stat-cpi.py
new file mode 100644
index 0000000..8b60f34
--- /dev/null
+++ b/tools/perf/scripts/python/stat-cpi.py
@@ -0,0 +1,77 @@
+#!/usr/bin/env python
+
+data    = {}
+times   = []
+threads = []
+cpus    = []
+
+def get_key(time, event, cpu, thread):
+    return "%d-%s-%d-%d" % (time, event, cpu, thread)
+
+def store_key(time, cpu, thread):
+    if (time not in times):
+        times.append(time)
+
+    if (cpu not in cpus):
+        cpus.append(cpu)
+
+    if (thread not in threads):
+        threads.append(thread)
+
+def store(time, event, cpu, thread, val, ena, run):
+    #print "event %s cpu %d, thread %d, time %d, val %d, ena %d, run %d" % \
+    #      (event, cpu, thread, time, val, ena, run)
+
+    store_key(time, cpu, thread)
+    key = get_key(time, event, cpu, thread)
+    data[key] = [ val, ena, run]
+
+def get(time, event, cpu, thread):
+    key = get_key(time, event, cpu, thread)
+    return data[key][0]
+
+def stat__cycles_k(cpu, thread, time, val, ena, run):
+    store(time, "cycles", cpu, thread, val, ena, run);
+
+def stat__instructions_k(cpu, thread, time, val, ena, run):
+    store(time, "instructions", cpu, thread, val, ena, run);
+
+def stat__cycles_u(cpu, thread, time, val, ena, run):
+    store(time, "cycles", cpu, thread, val, ena, run);
+
+def stat__instructions_u(cpu, thread, time, val, ena, run):
+    store(time, "instructions", cpu, thread, val, ena, run);
+
+def stat__cycles(cpu, thread, time, val, ena, run):
+    store(time, "cycles", cpu, thread, val, ena, run);
+
+def stat__instructions(cpu, thread, time, val, ena, run):
+    store(time, "instructions", cpu, thread, val, ena, run);
+
+def stat__interval(time):
+    for cpu in cpus:
+        for thread in threads:
+            cyc = get(time, "cycles", cpu, thread)
+            ins = get(time, "instructions", cpu, thread)
+            cpi = 0
+
+            if ins != 0:
+                cpi = cyc/float(ins)
+
+            print "%15f: cpu %d, thread %d -> cpi %f (%d/%d)" % (time/(float(1000000000)), cpu, thread, cpi, cyc, ins)
+
+def trace_end():
+    pass
+# XXX trace_end callback could be used as an alternative place
+#     to compute same values as in the script above:
+#
+#    for time in times:
+#        for cpu in cpus:
+#            for thread in threads:
+#                cyc = get(time, "cycles", cpu, thread)
+#                ins = get(time, "instructions", cpu, thread)
+#
+#                if ins != 0:
+#                    cpi = cyc/float(ins)
+#
+#                print "time %.9f, cpu %d, thread %d -> cpi %f" % (time/(float(1000000000)), cpu, thread, cpi)
diff --git a/tools/perf/tests/.gitignore b/tools/perf/tests/.gitignore
index 489fc9f..bf016c4 100644
--- a/tools/perf/tests/.gitignore
+++ b/tools/perf/tests/.gitignore
@@ -1,2 +1,3 @@
 llvm-src-base.c
 llvm-src-kbuild.c
+llvm-src-prologue.c
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index f41ebf8..614899b 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -31,24 +31,34 @@
 perf-y += parse-no-sample-id-all.o
 perf-y += kmod-path.o
 perf-y += thread-map.o
-perf-y += llvm.o llvm-src-base.o llvm-src-kbuild.o
+perf-y += llvm.o llvm-src-base.o llvm-src-kbuild.o llvm-src-prologue.o
 perf-y += bpf.o
 perf-y += topology.o
+perf-y += cpumap.o
+perf-y += stat.o
+perf-y += event_update.o
 
-$(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c
+$(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build
 	$(call rule_mkdir)
 	$(Q)echo '#include <tests/llvm.h>' > $@
 	$(Q)echo 'const char test_llvm__bpf_base_prog[] =' >> $@
 	$(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@
 	$(Q)echo ';' >> $@
 
-$(OUTPUT)tests/llvm-src-kbuild.c: tests/bpf-script-test-kbuild.c
+$(OUTPUT)tests/llvm-src-kbuild.c: tests/bpf-script-test-kbuild.c tests/Build
 	$(call rule_mkdir)
 	$(Q)echo '#include <tests/llvm.h>' > $@
 	$(Q)echo 'const char test_llvm__bpf_test_kbuild_prog[] =' >> $@
 	$(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@
 	$(Q)echo ';' >> $@
 
+$(OUTPUT)tests/llvm-src-prologue.c: tests/bpf-script-test-prologue.c tests/Build
+	$(call rule_mkdir)
+	$(Q)echo '#include <tests/llvm.h>' > $@
+	$(Q)echo 'const char test_llvm__bpf_test_prologue_prog[] =' >> $@
+	$(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@
+	$(Q)echo ';' >> $@
+
 ifeq ($(ARCH),$(filter $(ARCH),x86 arm arm64))
 perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o
 endif
diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c
index 638875a..28d1605 100644
--- a/tools/perf/tests/attr.c
+++ b/tools/perf/tests/attr.c
@@ -24,7 +24,7 @@
 #include <linux/kernel.h>
 #include "../perf.h"
 #include "util.h"
-#include "exec_cmd.h"
+#include <subcmd/exec-cmd.h>
 #include "tests.h"
 
 #define ENV "PERF_TEST_ATTR"
@@ -153,7 +153,7 @@
 	return system(cmd);
 }
 
-int test__attr(void)
+int test__attr(int subtest __maybe_unused)
 {
 	struct stat st;
 	char path_perf[PATH_MAX];
@@ -164,7 +164,7 @@
 		return run_dir("./tests", "./perf");
 
 	/* Then installed path. */
-	snprintf(path_dir,  PATH_MAX, "%s/tests", perf_exec_path());
+	snprintf(path_dir,  PATH_MAX, "%s/tests", get_argv_exec_path());
 	snprintf(path_perf, PATH_MAX, "%s/perf", BINDIR);
 
 	if (!lstat(path_dir, &st) &&
diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c
index a02b035..fb80c9e 100644
--- a/tools/perf/tests/bp_signal.c
+++ b/tools/perf/tests/bp_signal.c
@@ -111,7 +111,7 @@
 	return count;
 }
 
-int test__bp_signal(void)
+int test__bp_signal(int subtest __maybe_unused)
 {
 	struct sigaction sa;
 	long long count1, count2;
diff --git a/tools/perf/tests/bp_signal_overflow.c b/tools/perf/tests/bp_signal_overflow.c
index e765377..89f92fa6 100644
--- a/tools/perf/tests/bp_signal_overflow.c
+++ b/tools/perf/tests/bp_signal_overflow.c
@@ -58,7 +58,7 @@
 #define EXECUTIONS 10000
 #define THRESHOLD  100
 
-int test__bp_signal_overflow(void)
+int test__bp_signal_overflow(int subtest __maybe_unused)
 {
 	struct perf_event_attr pe;
 	struct sigaction sa;
diff --git a/tools/perf/tests/bpf-script-test-prologue.c b/tools/perf/tests/bpf-script-test-prologue.c
new file mode 100644
index 0000000..7230e62
--- /dev/null
+++ b/tools/perf/tests/bpf-script-test-prologue.c
@@ -0,0 +1,35 @@
+/*
+ * bpf-script-test-prologue.c
+ * Test BPF prologue
+ */
+#ifndef LINUX_VERSION_CODE
+# error Need LINUX_VERSION_CODE
+# error Example: for 4.2 kernel, put 'clang-opt="-DLINUX_VERSION_CODE=0x40200" into llvm section of ~/.perfconfig'
+#endif
+#define SEC(NAME) __attribute__((section(NAME), used))
+
+#include <uapi/linux/fs.h>
+
+#define FMODE_READ		0x1
+#define FMODE_WRITE		0x2
+
+static void (*bpf_trace_printk)(const char *fmt, int fmt_size, ...) =
+	(void *) 6;
+
+SEC("func=null_lseek file->f_mode offset orig")
+int bpf_func__null_lseek(void *ctx, int err, unsigned long f_mode,
+			 unsigned long offset, unsigned long orig)
+{
+	if (err)
+		return 0;
+	if (f_mode & FMODE_WRITE)
+		return 0;
+	if (offset & 1)
+		return 0;
+	if (orig == SEEK_CUR)
+		return 0;
+	return 1;
+}
+
+char _license[] SEC("license") = "GPL";
+int _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index ec16f78..33689a0 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -19,6 +19,29 @@
 	return 0;
 }
 
+#ifdef HAVE_BPF_PROLOGUE
+
+static int llseek_loop(void)
+{
+	int fds[2], i;
+
+	fds[0] = open("/dev/null", O_RDONLY);
+	fds[1] = open("/dev/null", O_RDWR);
+
+	if (fds[0] < 0 || fds[1] < 0)
+		return -1;
+
+	for (i = 0; i < NR_ITERS; i++) {
+		lseek(fds[i % 2], i, (i / 2) % 2 ? SEEK_CUR : SEEK_SET);
+		lseek(fds[(i + 1) % 2], i, (i / 2) % 2 ? SEEK_CUR : SEEK_SET);
+	}
+	close(fds[0]);
+	close(fds[1]);
+	return 0;
+}
+
+#endif
+
 static struct {
 	enum test_llvm__testcase prog_id;
 	const char *desc;
@@ -37,6 +60,17 @@
 		&epoll_pwait_loop,
 		(NR_ITERS + 1) / 2,
 	},
+#ifdef HAVE_BPF_PROLOGUE
+	{
+		LLVM_TESTCASE_BPF_PROLOGUE,
+		"Test BPF prologue generation",
+		"[bpf_prologue_test]",
+		"fix kbuild first",
+		"check your vmlinux setting?",
+		&llseek_loop,
+		(NR_ITERS + 1) / 4,
+	},
+#endif
 };
 
 static int do_test(struct bpf_object *obj, int (*func)(void),
@@ -68,8 +102,7 @@
 	err = parse_events_load_bpf_obj(&parse_evlist, &parse_evlist.list, obj);
 	if (err || list_empty(&parse_evlist.list)) {
 		pr_debug("Failed to add events selected by BPF\n");
-		if (!err)
-			return TEST_FAIL;
+		return TEST_FAIL;
 	}
 
 	snprintf(pid, sizeof(pid), "%d", getpid());
@@ -123,8 +156,10 @@
 		}
 	}
 
-	if (count != expect)
+	if (count != expect) {
 		pr_debug("BPF filter result incorrect\n");
+		goto out_delete_evlist;
+	}
 
 	ret = TEST_OK;
 
@@ -146,7 +181,7 @@
 	return obj;
 }
 
-static int __test__bpf(int index)
+static int __test__bpf(int idx)
 {
 	int ret;
 	void *obj_buf;
@@ -154,54 +189,72 @@
 	struct bpf_object *obj;
 
 	ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz,
-				       bpf_testcase_table[index].prog_id,
+				       bpf_testcase_table[idx].prog_id,
 				       true);
 	if (ret != TEST_OK || !obj_buf || !obj_buf_sz) {
 		pr_debug("Unable to get BPF object, %s\n",
-			 bpf_testcase_table[index].msg_compile_fail);
-		if (index == 0)
+			 bpf_testcase_table[idx].msg_compile_fail);
+		if (idx == 0)
 			return TEST_SKIP;
 		else
 			return TEST_FAIL;
 	}
 
 	obj = prepare_bpf(obj_buf, obj_buf_sz,
-			  bpf_testcase_table[index].name);
+			  bpf_testcase_table[idx].name);
 	if (!obj) {
 		ret = TEST_FAIL;
 		goto out;
 	}
 
 	ret = do_test(obj,
-		      bpf_testcase_table[index].target_func,
-		      bpf_testcase_table[index].expect_result);
+		      bpf_testcase_table[idx].target_func,
+		      bpf_testcase_table[idx].expect_result);
 out:
 	bpf__clear();
 	return ret;
 }
 
-int test__bpf(void)
+int test__bpf_subtest_get_nr(void)
 {
-	unsigned int i;
+	return (int)ARRAY_SIZE(bpf_testcase_table);
+}
+
+const char *test__bpf_subtest_get_desc(int i)
+{
+	if (i < 0 || i >= (int)ARRAY_SIZE(bpf_testcase_table))
+		return NULL;
+	return bpf_testcase_table[i].desc;
+}
+
+int test__bpf(int i)
+{
 	int err;
 
+	if (i < 0 || i >= (int)ARRAY_SIZE(bpf_testcase_table))
+		return TEST_FAIL;
+
 	if (geteuid() != 0) {
 		pr_debug("Only root can run BPF test\n");
 		return TEST_SKIP;
 	}
 
-	for (i = 0; i < ARRAY_SIZE(bpf_testcase_table); i++) {
-		err = __test__bpf(i);
-
-		if (err != TEST_OK)
-			return err;
-	}
-
-	return TEST_OK;
+	err = __test__bpf(i);
+	return err;
 }
 
 #else
-int test__bpf(void)
+int test__bpf_subtest_get_nr(void)
+{
+	return 0;
+}
+
+const char *test__bpf_subtest_get_desc(int i __maybe_unused)
+{
+	return NULL;
+}
+
+int test__bpf(int i __maybe_unused)
 {
 	pr_debug("Skip BPF test because BPF support is not compiled\n");
 	return TEST_SKIP;
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 80c442e..f2b1dca 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -11,7 +11,7 @@
 #include "tests.h"
 #include "debug.h"
 #include "color.h"
-#include "parse-options.h"
+#include <subcmd/parse-options.h>
 #include "symbol.h"
 
 struct test __weak arch_tests[] = {
@@ -160,6 +160,11 @@
 	{
 		.desc = "Test LLVM searching and compiling",
 		.func = test__llvm,
+		.subtest = {
+			.skip_if_fail	= true,
+			.get_nr		= test__llvm_subtest_get_nr,
+			.get_desc	= test__llvm_subtest_get_desc,
+		},
 	},
 	{
 		.desc = "Test topology in session",
@@ -168,6 +173,35 @@
 	{
 		.desc = "Test BPF filter",
 		.func = test__bpf,
+		.subtest = {
+			.skip_if_fail	= true,
+			.get_nr		= test__bpf_subtest_get_nr,
+			.get_desc	= test__bpf_subtest_get_desc,
+		},
+	},
+	{
+		.desc = "Test thread map synthesize",
+		.func = test__thread_map_synthesize,
+	},
+	{
+		.desc = "Test cpu map synthesize",
+		.func = test__cpu_map_synthesize,
+	},
+	{
+		.desc = "Test stat config synthesize",
+		.func = test__synthesize_stat_config,
+	},
+	{
+		.desc = "Test stat synthesize",
+		.func = test__synthesize_stat,
+	},
+	{
+		.desc = "Test stat round synthesize",
+		.func = test__synthesize_stat_round,
+	},
+	{
+		.desc = "Test attr update synthesize",
+		.func = test__event_update,
 	},
 	{
 		.func = NULL,
@@ -203,7 +237,7 @@
 	return false;
 }
 
-static int run_test(struct test *test)
+static int run_test(struct test *test, int subtest)
 {
 	int status, err = -1, child = fork();
 	char sbuf[STRERR_BUFSIZE];
@@ -216,7 +250,22 @@
 
 	if (!child) {
 		pr_debug("test child forked, pid %d\n", getpid());
-		err = test->func();
+		if (!verbose) {
+			int nullfd = open("/dev/null", O_WRONLY);
+			if (nullfd >= 0) {
+				close(STDERR_FILENO);
+				close(STDOUT_FILENO);
+
+				dup2(nullfd, STDOUT_FILENO);
+				dup2(STDOUT_FILENO, STDERR_FILENO);
+				close(nullfd);
+			}
+		} else {
+			signal(SIGSEGV, sighandler_dump_stack);
+			signal(SIGFPE, sighandler_dump_stack);
+		}
+
+		err = test->func(subtest);
 		exit(err);
 	}
 
@@ -237,6 +286,40 @@
 	for (j = 0; j < ARRAY_SIZE(tests); j++)	\
 		for (t = &tests[j][0]; t->func; t++)
 
+static int test_and_print(struct test *t, bool force_skip, int subtest)
+{
+	int err;
+
+	if (!force_skip) {
+		pr_debug("\n--- start ---\n");
+		err = run_test(t, subtest);
+		pr_debug("---- end ----\n");
+	} else {
+		pr_debug("\n--- force skipped ---\n");
+		err = TEST_SKIP;
+	}
+
+	if (!t->subtest.get_nr)
+		pr_debug("%s:", t->desc);
+	else
+		pr_debug("%s subtest %d:", t->desc, subtest);
+
+	switch (err) {
+	case TEST_OK:
+		pr_info(" Ok\n");
+		break;
+	case TEST_SKIP:
+		color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip\n");
+		break;
+	case TEST_FAIL:
+	default:
+		color_fprintf(stderr, PERF_COLOR_RED, " FAILED!\n");
+		break;
+	}
+
+	return err;
+}
+
 static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
 {
 	struct test *t;
@@ -264,21 +347,43 @@
 			continue;
 		}
 
-		pr_debug("\n--- start ---\n");
-		err = run_test(t);
-		pr_debug("---- end ----\n%s:", t->desc);
+		if (!t->subtest.get_nr) {
+			test_and_print(t, false, -1);
+		} else {
+			int subn = t->subtest.get_nr();
+			/*
+			 * minus 2 to align with normal testcases.
+			 * For subtest we print additional '.x' in number.
+			 * for example:
+			 *
+			 * 35: Test LLVM searching and compiling                        :
+			 * 35.1: Basic BPF llvm compiling test                          : Ok
+			 */
+			int subw = width > 2 ? width - 2 : width;
+			bool skip = false;
+			int subi;
 
-		switch (err) {
-		case TEST_OK:
-			pr_info(" Ok\n");
-			break;
-		case TEST_SKIP:
-			color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip\n");
-			break;
-		case TEST_FAIL:
-		default:
-			color_fprintf(stderr, PERF_COLOR_RED, " FAILED!\n");
-			break;
+			if (subn <= 0) {
+				color_fprintf(stderr, PERF_COLOR_YELLOW,
+					      " Skip (not compiled in)\n");
+				continue;
+			}
+			pr_info("\n");
+
+			for (subi = 0; subi < subn; subi++) {
+				int len = strlen(t->subtest.get_desc(subi));
+
+				if (subw < len)
+					subw = len;
+			}
+
+			for (subi = 0; subi < subn; subi++) {
+				pr_info("%2d.%1d: %-*s:", i, subi + 1, subw,
+					t->subtest.get_desc(subi));
+				err = test_and_print(t, skip, subi);
+				if (err != TEST_OK && t->subtest.skip_if_fail)
+					skip = true;
+			}
 		}
 	}
 
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index a767a64..313a48c 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -433,7 +433,6 @@
 
 static int do_test_code_reading(bool try_kcore)
 {
-	struct machines machines;
 	struct machine *machine;
 	struct thread *thread;
 	struct record_opts opts = {
@@ -459,8 +458,7 @@
 
 	pid = getpid();
 
-	machines__init(&machines);
-	machine = &machines.host;
+	machine = machine__new_host();
 
 	ret = machine__create_kernel_maps(machine);
 	if (ret < 0) {
@@ -549,6 +547,13 @@
 		if (ret < 0) {
 			if (!excl_kernel) {
 				excl_kernel = true;
+				/*
+				 * Both cpus and threads are now owned by evlist
+				 * and will be freed by following perf_evlist__set_maps
+				 * call. Getting refference to keep them alive.
+				 */
+				cpu_map__get(cpus);
+				thread_map__get(threads);
 				perf_evlist__set_maps(evlist, NULL, NULL);
 				perf_evlist__delete(evlist);
 				evlist = NULL;
@@ -594,14 +599,13 @@
 		cpu_map__put(cpus);
 		thread_map__put(threads);
 	}
-	machines__destroy_kernel_maps(&machines);
 	machine__delete_threads(machine);
-	machines__exit(&machines);
+	machine__delete(machine);
 
 	return err;
 }
 
-int test__code_reading(void)
+int test__code_reading(int subtest __maybe_unused)
 {
 	int ret;
 
diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c
new file mode 100644
index 0000000..4cb6418
--- /dev/null
+++ b/tools/perf/tests/cpumap.c
@@ -0,0 +1,88 @@
+#include "tests.h"
+#include "cpumap.h"
+
+static int process_event_mask(struct perf_tool *tool __maybe_unused,
+			 union perf_event *event,
+			 struct perf_sample *sample __maybe_unused,
+			 struct machine *machine __maybe_unused)
+{
+	struct cpu_map_event *map_event = &event->cpu_map;
+	struct cpu_map_mask *mask;
+	struct cpu_map_data *data;
+	struct cpu_map *map;
+	int i;
+
+	data = &map_event->data;
+
+	TEST_ASSERT_VAL("wrong type", data->type == PERF_CPU_MAP__MASK);
+
+	mask = (struct cpu_map_mask *)data->data;
+
+	TEST_ASSERT_VAL("wrong nr",   mask->nr == 1);
+
+	for (i = 0; i < 20; i++) {
+		TEST_ASSERT_VAL("wrong cpu", test_bit(i, mask->mask));
+	}
+
+	map = cpu_map__new_data(data);
+	TEST_ASSERT_VAL("wrong nr",  map->nr == 20);
+
+	for (i = 0; i < 20; i++) {
+		TEST_ASSERT_VAL("wrong cpu", map->map[i] == i);
+	}
+
+	cpu_map__put(map);
+	return 0;
+}
+
+static int process_event_cpus(struct perf_tool *tool __maybe_unused,
+			 union perf_event *event,
+			 struct perf_sample *sample __maybe_unused,
+			 struct machine *machine __maybe_unused)
+{
+	struct cpu_map_event *map_event = &event->cpu_map;
+	struct cpu_map_entries *cpus;
+	struct cpu_map_data *data;
+	struct cpu_map *map;
+
+	data = &map_event->data;
+
+	TEST_ASSERT_VAL("wrong type", data->type == PERF_CPU_MAP__CPUS);
+
+	cpus = (struct cpu_map_entries *)data->data;
+
+	TEST_ASSERT_VAL("wrong nr",   cpus->nr == 2);
+	TEST_ASSERT_VAL("wrong cpu",  cpus->cpu[0] == 1);
+	TEST_ASSERT_VAL("wrong cpu",  cpus->cpu[1] == 256);
+
+	map = cpu_map__new_data(data);
+	TEST_ASSERT_VAL("wrong nr",  map->nr == 2);
+	TEST_ASSERT_VAL("wrong cpu", map->map[0] == 1);
+	TEST_ASSERT_VAL("wrong cpu", map->map[1] == 256);
+	TEST_ASSERT_VAL("wrong refcnt", atomic_read(&map->refcnt) == 1);
+	cpu_map__put(map);
+	return 0;
+}
+
+
+int test__cpu_map_synthesize(int subtest __maybe_unused)
+{
+	struct cpu_map *cpus;
+
+	/* This one is better stores in mask. */
+	cpus = cpu_map__new("0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19");
+
+	TEST_ASSERT_VAL("failed to synthesize map",
+		!perf_event__synthesize_cpu_map(NULL, cpus, process_event_mask, NULL));
+
+	cpu_map__put(cpus);
+
+	/* This one is better stores in cpu values. */
+	cpus = cpu_map__new("1,256");
+
+	TEST_ASSERT_VAL("failed to synthesize map",
+		!perf_event__synthesize_cpu_map(NULL, cpus, process_event_cpus, NULL));
+
+	cpu_map__put(cpus);
+	return 0;
+}
diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c
index a218aea..dc673ff 100644
--- a/tools/perf/tests/dso-data.c
+++ b/tools/perf/tests/dso-data.c
@@ -110,7 +110,7 @@
 	return fd;
 }
 
-int test__dso_data(void)
+int test__dso_data(int subtest __maybe_unused)
 {
 	struct machine machine;
 	struct dso *dso;
@@ -245,7 +245,7 @@
 	return setrlimit(RLIMIT_NOFILE, &rlim);
 }
 
-int test__dso_data_cache(void)
+int test__dso_data_cache(int subtest __maybe_unused)
 {
 	struct machine machine;
 	long nr_end, nr = open_files_cnt();
@@ -302,7 +302,7 @@
 	return 0;
 }
 
-int test__dso_data_reopen(void)
+int test__dso_data_reopen(int subtest __maybe_unused)
 {
 	struct machine machine;
 	long nr_end, nr = open_files_cnt();
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index 0722179..1c5c022 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -51,6 +51,12 @@
 		"krava_1",
 		"test__dwarf_unwind"
 	};
+	/*
+	 * The funcs[MAX_STACK] array index, based on the
+	 * callchain order setup.
+	 */
+	int idx = callchain_param.order == ORDER_CALLER ?
+		  MAX_STACK - *cnt - 1 : *cnt;
 
 	if (*cnt >= MAX_STACK) {
 		pr_debug("failed: crossed the max stack value %d\n", MAX_STACK);
@@ -63,8 +69,10 @@
 		return -1;
 	}
 
-	pr_debug("got: %s 0x%" PRIx64 "\n", symbol, entry->ip);
-	return strcmp((const char *) symbol, funcs[(*cnt)++]);
+	(*cnt)++;
+	pr_debug("got: %s 0x%" PRIx64 ", expecting %s\n",
+		 symbol, entry->ip, funcs[idx]);
+	return strcmp((const char *) symbol, funcs[idx]);
 }
 
 __attribute__ ((noinline))
@@ -105,8 +113,16 @@
 	/* Any possible value should be 'thread' */
 	struct thread *thread = *(struct thread **)p1;
 
-	if (global_unwind_retval == -INT_MAX)
+	if (global_unwind_retval == -INT_MAX) {
+		/* Call unwinder twice for both callchain orders. */
+		callchain_param.order = ORDER_CALLER;
+
 		global_unwind_retval = unwind_thread(thread);
+		if (!global_unwind_retval) {
+			callchain_param.order = ORDER_CALLEE;
+			global_unwind_retval = unwind_thread(thread);
+		}
+	}
 
 	return p1 - p2;
 }
@@ -142,21 +158,23 @@
 	return krava_2(thread);
 }
 
-int test__dwarf_unwind(void)
+int test__dwarf_unwind(int subtest __maybe_unused)
 {
-	struct machines machines;
 	struct machine *machine;
 	struct thread *thread;
 	int err = -1;
 
-	machines__init(&machines);
-
-	machine = machines__find(&machines, HOST_KERNEL_ID);
+	machine = machine__new_host();
 	if (!machine) {
 		pr_err("Could not get machine\n");
 		return -1;
 	}
 
+	if (machine__create_kernel_maps(machine)) {
+		pr_err("Failed to create kernel maps\n");
+		return -1;
+	}
+
 	callchain_param.record_mode = CALLCHAIN_DWARF;
 
 	if (init_live_machine(machine)) {
@@ -178,7 +196,6 @@
 
  out:
 	machine__delete_threads(machine);
-	machine__exit(machine);
-	machines__exit(&machines);
+	machine__delete(machine);
 	return err;
 }
diff --git a/tools/perf/tests/event_update.c b/tools/perf/tests/event_update.c
new file mode 100644
index 0000000..012eab5
--- /dev/null
+++ b/tools/perf/tests/event_update.c
@@ -0,0 +1,117 @@
+#include <linux/compiler.h>
+#include "evlist.h"
+#include "evsel.h"
+#include "machine.h"
+#include "tests.h"
+#include "debug.h"
+
+static int process_event_unit(struct perf_tool *tool __maybe_unused,
+			      union perf_event *event,
+			      struct perf_sample *sample __maybe_unused,
+			      struct machine *machine __maybe_unused)
+{
+	struct event_update_event *ev = (struct event_update_event *) event;
+
+	TEST_ASSERT_VAL("wrong id", ev->id == 123);
+	TEST_ASSERT_VAL("wrong id", ev->type == PERF_EVENT_UPDATE__UNIT);
+	TEST_ASSERT_VAL("wrong unit", !strcmp(ev->data, "KRAVA"));
+	return 0;
+}
+
+static int process_event_scale(struct perf_tool *tool __maybe_unused,
+			       union perf_event *event,
+			       struct perf_sample *sample __maybe_unused,
+			       struct machine *machine __maybe_unused)
+{
+	struct event_update_event *ev = (struct event_update_event *) event;
+	struct event_update_event_scale *ev_data;
+
+	ev_data = (struct event_update_event_scale *) ev->data;
+
+	TEST_ASSERT_VAL("wrong id", ev->id == 123);
+	TEST_ASSERT_VAL("wrong id", ev->type == PERF_EVENT_UPDATE__SCALE);
+	TEST_ASSERT_VAL("wrong scale", ev_data->scale = 0.123);
+	return 0;
+}
+
+struct event_name {
+	struct perf_tool tool;
+	const char *name;
+};
+
+static int process_event_name(struct perf_tool *tool,
+			      union perf_event *event,
+			      struct perf_sample *sample __maybe_unused,
+			      struct machine *machine __maybe_unused)
+{
+	struct event_name *tmp = container_of(tool, struct event_name, tool);
+	struct event_update_event *ev = (struct event_update_event*) event;
+
+	TEST_ASSERT_VAL("wrong id", ev->id == 123);
+	TEST_ASSERT_VAL("wrong id", ev->type == PERF_EVENT_UPDATE__NAME);
+	TEST_ASSERT_VAL("wrong name", !strcmp(ev->data, tmp->name));
+	return 0;
+}
+
+static int process_event_cpus(struct perf_tool *tool __maybe_unused,
+			      union perf_event *event,
+			      struct perf_sample *sample __maybe_unused,
+			      struct machine *machine __maybe_unused)
+{
+	struct event_update_event *ev = (struct event_update_event*) event;
+	struct event_update_event_cpus *ev_data;
+	struct cpu_map *map;
+
+	ev_data = (struct event_update_event_cpus*) ev->data;
+
+	map = cpu_map__new_data(&ev_data->cpus);
+
+	TEST_ASSERT_VAL("wrong id", ev->id == 123);
+	TEST_ASSERT_VAL("wrong type", ev->type == PERF_EVENT_UPDATE__CPUS);
+	TEST_ASSERT_VAL("wrong cpus", map->nr == 3);
+	TEST_ASSERT_VAL("wrong cpus", map->map[0] == 1);
+	TEST_ASSERT_VAL("wrong cpus", map->map[1] == 2);
+	TEST_ASSERT_VAL("wrong cpus", map->map[2] == 3);
+	cpu_map__put(map);
+	return 0;
+}
+
+int test__event_update(int subtest __maybe_unused)
+{
+	struct perf_evlist *evlist;
+	struct perf_evsel *evsel;
+	struct event_name tmp;
+
+	evlist = perf_evlist__new_default();
+	TEST_ASSERT_VAL("failed to get evlist", evlist);
+
+	evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("failed to allos ids",
+			!perf_evsel__alloc_id(evsel, 1, 1));
+
+	perf_evlist__id_add(evlist, evsel, 0, 0, 123);
+
+	evsel->unit = strdup("KRAVA");
+
+	TEST_ASSERT_VAL("failed to synthesize attr update unit",
+			!perf_event__synthesize_event_update_unit(NULL, evsel, process_event_unit));
+
+	evsel->scale = 0.123;
+
+	TEST_ASSERT_VAL("failed to synthesize attr update scale",
+			!perf_event__synthesize_event_update_scale(NULL, evsel, process_event_scale));
+
+	tmp.name = perf_evsel__name(evsel);
+
+	TEST_ASSERT_VAL("failed to synthesize attr update name",
+			!perf_event__synthesize_event_update_name(&tmp.tool, evsel, process_event_name));
+
+	evsel->own_cpus = cpu_map__new("1,2,3");
+
+	TEST_ASSERT_VAL("failed to synthesize attr update cpus",
+			!perf_event__synthesize_event_update_cpus(&tmp.tool, evsel, process_event_cpus));
+
+	cpu_map__put(evsel->own_cpus);
+	return 0;
+}
diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c
index 3fa7159..2de4a4f 100644
--- a/tools/perf/tests/evsel-roundtrip-name.c
+++ b/tools/perf/tests/evsel-roundtrip-name.c
@@ -95,7 +95,7 @@
 #define perf_evsel__name_array_test(names) \
 	__perf_evsel__name_array_test(names, ARRAY_SIZE(names))
 
-int test__perf_evsel__roundtrip_name_test(void)
+int test__perf_evsel__roundtrip_name_test(int subtest __maybe_unused)
 {
 	int err = 0, ret = 0;
 
@@ -103,7 +103,8 @@
 	if (err)
 		ret = err;
 
-	err = perf_evsel__name_array_test(perf_evsel__sw_names);
+	err = __perf_evsel__name_array_test(perf_evsel__sw_names,
+					    PERF_COUNT_SW_DUMMY + 1);
 	if (err)
 		ret = err;
 
diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c
index 790e413..1984b3b 100644
--- a/tools/perf/tests/evsel-tp-sched.c
+++ b/tools/perf/tests/evsel-tp-sched.c
@@ -32,7 +32,7 @@
 	return ret;
 }
 
-int test__perf_evsel__tp_sched_test(void)
+int test__perf_evsel__tp_sched_test(int subtest __maybe_unused)
 {
 	struct perf_evsel *evsel = perf_evsel__newtp("sched", "sched_switch");
 	int ret = 0;
diff --git a/tools/perf/tests/fdarray.c b/tools/perf/tests/fdarray.c
index d24b837..c809463 100644
--- a/tools/perf/tests/fdarray.c
+++ b/tools/perf/tests/fdarray.c
@@ -25,7 +25,7 @@
 	return printed + fdarray__fprintf(fda, fp);
 }
 
-int test__fdarray__filter(void)
+int test__fdarray__filter(int subtest __maybe_unused)
 {
 	int nr_fds, expected_fd[2], fd, err = TEST_FAIL;
 	struct fdarray *fda = fdarray__new(5, 5);
@@ -103,7 +103,7 @@
 	return err;
 }
 
-int test__fdarray__add(void)
+int test__fdarray__add(int subtest __maybe_unused)
 {
 	int err = TEST_FAIL;
 	struct fdarray *fda = fdarray__new(2, 2);
diff --git a/tools/perf/tests/hists_common.c b/tools/perf/tests/hists_common.c
index ce80b27..bcfd081 100644
--- a/tools/perf/tests/hists_common.c
+++ b/tools/perf/tests/hists_common.c
@@ -87,6 +87,11 @@
 		return NULL;
 	}
 
+	if (machine__create_kernel_maps(machine)) {
+		pr_debug("Cannot create kernel maps\n");
+		return NULL;
+	}
+
 	for (i = 0; i < ARRAY_SIZE(fake_threads); i++) {
 		struct thread *thread;
 
@@ -150,7 +155,6 @@
 out:
 	pr_debug("Not enough memory for machine setup\n");
 	machine__delete_threads(machine);
-	machine__delete(machine);
 	return NULL;
 }
 
diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c
index 7ed73701..e360892 100644
--- a/tools/perf/tests/hists_cumulate.c
+++ b/tools/perf/tests/hists_cumulate.c
@@ -281,7 +281,7 @@
 	symbol_conf.cumulate_callchain = false;
 	perf_evsel__reset_sample_bit(evsel, CALLCHAIN);
 
-	setup_sorting();
+	setup_sorting(NULL);
 	callchain_register_param(&callchain_param);
 
 	err = add_hist_entries(hists, machine);
@@ -428,7 +428,7 @@
 	symbol_conf.cumulate_callchain = false;
 	perf_evsel__set_sample_bit(evsel, CALLCHAIN);
 
-	setup_sorting();
+	setup_sorting(NULL);
 	callchain_register_param(&callchain_param);
 
 	err = add_hist_entries(hists, machine);
@@ -486,7 +486,7 @@
 	symbol_conf.cumulate_callchain = true;
 	perf_evsel__reset_sample_bit(evsel, CALLCHAIN);
 
-	setup_sorting();
+	setup_sorting(NULL);
 	callchain_register_param(&callchain_param);
 
 	err = add_hist_entries(hists, machine);
@@ -670,7 +670,7 @@
 	symbol_conf.cumulate_callchain = true;
 	perf_evsel__set_sample_bit(evsel, CALLCHAIN);
 
-	setup_sorting();
+	setup_sorting(NULL);
 	callchain_register_param(&callchain_param);
 
 	err = add_hist_entries(hists, machine);
@@ -686,7 +686,7 @@
 	return err;
 }
 
-int test__hists_cumulate(void)
+int test__hists_cumulate(int subtest __maybe_unused)
 {
 	int err = TEST_FAIL;
 	struct machines machines;
diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c
index 818acf8..2a784be 100644
--- a/tools/perf/tests/hists_filter.c
+++ b/tools/perf/tests/hists_filter.c
@@ -104,7 +104,7 @@
 	return TEST_FAIL;
 }
 
-int test__hists_filter(void)
+int test__hists_filter(int subtest __maybe_unused)
 {
 	int err = TEST_FAIL;
 	struct machines machines;
@@ -122,7 +122,7 @@
 		goto out;
 
 	/* default sort order (comm,dso,sym) will be used */
-	if (setup_sorting() < 0)
+	if (setup_sorting(NULL) < 0)
 		goto out;
 
 	machines__init(&machines);
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index 8c102b0..c764d69 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -64,7 +64,7 @@
 	struct perf_evsel *evsel;
 	struct addr_location al;
 	struct hist_entry *he;
-	struct perf_sample sample = { .period = 1, };
+	struct perf_sample sample = { .period = 1, .weight = 1, };
 	size_t i = 0, k;
 
 	/*
@@ -90,7 +90,7 @@
 				goto out;
 
 			he = __hists__add_entry(hists, &al, NULL,
-						NULL, NULL, 1, 1, 0, true);
+						NULL, NULL, &sample, true);
 			if (he == NULL) {
 				addr_location__put(&al);
 				goto out;
@@ -116,7 +116,7 @@
 				goto out;
 
 			he = __hists__add_entry(hists, &al, NULL,
-						NULL, NULL, 1, 1, 0, true);
+						NULL, NULL, &sample, true);
 			if (he == NULL) {
 				addr_location__put(&al);
 				goto out;
@@ -274,7 +274,7 @@
 	return __validate_link(leader, 0) || __validate_link(other, 1);
 }
 
-int test__hists_link(void)
+int test__hists_link(int subtest __maybe_unused)
 {
 	int err = -1;
 	struct hists *hists, *first_hists;
@@ -294,7 +294,7 @@
 		goto out;
 
 	/* default sort order (comm,dso,sym) will be used */
-	if (setup_sorting() < 0)
+	if (setup_sorting(NULL) < 0)
 		goto out;
 
 	machines__init(&machines);
diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c
index adbebc8..ebe6cd4 100644
--- a/tools/perf/tests/hists_output.c
+++ b/tools/perf/tests/hists_output.c
@@ -134,7 +134,7 @@
 	field_order = NULL;
 	sort_order = NULL; /* equivalent to sort_order = "comm,dso,sym" */
 
-	setup_sorting();
+	setup_sorting(NULL);
 
 	/*
 	 * expected output:
@@ -236,7 +236,7 @@
 	field_order = "overhead,cpu";
 	sort_order = "pid";
 
-	setup_sorting();
+	setup_sorting(NULL);
 
 	/*
 	 * expected output:
@@ -292,7 +292,7 @@
 	field_order = "comm,overhead,dso";
 	sort_order = NULL;
 
-	setup_sorting();
+	setup_sorting(NULL);
 
 	/*
 	 * expected output:
@@ -366,7 +366,7 @@
 	field_order = "dso,sym,comm,overhead,dso";
 	sort_order = "sym";
 
-	setup_sorting();
+	setup_sorting(NULL);
 
 	/*
 	 * expected output:
@@ -468,7 +468,7 @@
 	field_order = "cpu,pid,comm,dso,sym";
 	sort_order = "dso,pid";
 
-	setup_sorting();
+	setup_sorting(NULL);
 
 	/*
 	 * expected output:
@@ -576,7 +576,7 @@
 	return err;
 }
 
-int test__hists_output(void)
+int test__hists_output(int subtest __maybe_unused)
 {
 	int err = TEST_FAIL;
 	struct machines machines;
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index a2e2269..ddb78fa 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -49,13 +49,12 @@
  * when an event is disabled but a dummy software event is not disabled.  If the
  * test passes %0 is returned, otherwise %-1 is returned.
  */
-int test__keep_tracking(void)
+int test__keep_tracking(int subtest __maybe_unused)
 {
 	struct record_opts opts = {
 		.mmap_pages	     = UINT_MAX,
 		.user_freq	     = UINT_MAX,
 		.user_interval	     = ULLONG_MAX,
-		.freq		     = 4000,
 		.target		     = {
 			.uses_mmap   = true,
 		},
@@ -124,7 +123,7 @@
 
 	evsel = perf_evlist__last(evlist);
 
-	CHECK__(perf_evlist__disable_event(evlist, evsel));
+	CHECK__(perf_evsel__disable(evsel));
 
 	comm = "Test COMM 2";
 	CHECK__(prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0));
diff --git a/tools/perf/tests/kmod-path.c b/tools/perf/tests/kmod-path.c
index 08c433b..d2af781 100644
--- a/tools/perf/tests/kmod-path.c
+++ b/tools/perf/tests/kmod-path.c
@@ -49,7 +49,7 @@
 #define M(path, c, e) \
 	TEST_ASSERT_VAL("failed", !test_is_kernel_module(path, c, e))
 
-int test__kmod_path__parse(void)
+int test__kmod_path__parse(int subtest __maybe_unused)
 {
 	/* path                alloc_name  alloc_ext   kmod  comp   name     ext */
 	T("/xxxx/xxxx/x-x.ko", true      , true      , true, false, "[x_x]", NULL);
diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c
index bc4cf50..06f45c1 100644
--- a/tools/perf/tests/llvm.c
+++ b/tools/perf/tests/llvm.c
@@ -44,13 +44,17 @@
 		.source = test_llvm__bpf_test_kbuild_prog,
 		.desc = "Test kbuild searching",
 	},
+	[LLVM_TESTCASE_BPF_PROLOGUE] = {
+		.source = test_llvm__bpf_test_prologue_prog,
+		.desc = "Compile source for BPF prologue generation test",
+	},
 };
 
 
 int
 test_llvm__fetch_bpf_obj(void **p_obj_buf,
 			 size_t *p_obj_buf_sz,
-			 enum test_llvm__testcase index,
+			 enum test_llvm__testcase idx,
 			 bool force)
 {
 	const char *source;
@@ -59,11 +63,11 @@
 	char *tmpl_new = NULL, *clang_opt_new = NULL;
 	int err, old_verbose, ret = TEST_FAIL;
 
-	if (index >= __LLVM_TESTCASE_MAX)
+	if (idx >= __LLVM_TESTCASE_MAX)
 		return TEST_FAIL;
 
-	source = bpf_source_table[index].source;
-	desc = bpf_source_table[index].desc;
+	source = bpf_source_table[idx].source;
+	desc = bpf_source_table[idx].desc;
 
 	perf_config(perf_config_cb, NULL);
 
@@ -127,44 +131,39 @@
 	return ret;
 }
 
-int test__llvm(void)
+int test__llvm(int subtest)
 {
-	enum test_llvm__testcase i;
+	int ret;
+	void *obj_buf = NULL;
+	size_t obj_buf_sz = 0;
 
-	for (i = 0; i < __LLVM_TESTCASE_MAX; i++) {
-		int ret;
-		void *obj_buf = NULL;
-		size_t obj_buf_sz = 0;
+	if ((subtest < 0) || (subtest >= __LLVM_TESTCASE_MAX))
+		return TEST_FAIL;
 
-		ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz,
-					       i, false);
+	ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz,
+				       subtest, false);
 
-		if (ret == TEST_OK) {
-			ret = test__bpf_parsing(obj_buf, obj_buf_sz);
-			if (ret != TEST_OK)
-				pr_debug("Failed to parse test case '%s'\n",
-					 bpf_source_table[i].desc);
-		}
-		free(obj_buf);
-
-		switch (ret) {
-		case TEST_SKIP:
-			return TEST_SKIP;
-		case TEST_OK:
-			break;
-		default:
-			/*
-			 * Test 0 is the basic LLVM test. If test 0
-			 * fail, the basic LLVM support not functional
-			 * so the whole test should fail. If other test
-			 * case fail, it can be fixed by adjusting
-			 * config so don't report error.
-			 */
-			if (i == 0)
-				return TEST_FAIL;
-			else
-				return TEST_SKIP;
+	if (ret == TEST_OK) {
+		ret = test__bpf_parsing(obj_buf, obj_buf_sz);
+		if (ret != TEST_OK) {
+			pr_debug("Failed to parse test case '%s'\n",
+				 bpf_source_table[subtest].desc);
 		}
 	}
-	return TEST_OK;
+	free(obj_buf);
+
+	return ret;
+}
+
+int test__llvm_subtest_get_nr(void)
+{
+	return __LLVM_TESTCASE_MAX;
+}
+
+const char *test__llvm_subtest_get_desc(int subtest)
+{
+	if ((subtest < 0) || (subtest >= __LLVM_TESTCASE_MAX))
+		return NULL;
+
+	return bpf_source_table[subtest].desc;
 }
diff --git a/tools/perf/tests/llvm.h b/tools/perf/tests/llvm.h
index d91d8f4..5150b4d 100644
--- a/tools/perf/tests/llvm.h
+++ b/tools/perf/tests/llvm.h
@@ -6,10 +6,12 @@
 
 extern const char test_llvm__bpf_base_prog[];
 extern const char test_llvm__bpf_test_kbuild_prog[];
+extern const char test_llvm__bpf_test_prologue_prog[];
 
 enum test_llvm__testcase {
 	LLVM_TESTCASE_BASE,
 	LLVM_TESTCASE_KBUILD,
+	LLVM_TESTCASE_BPF_PROLOGUE,
 	__LLVM_TESTCASE_MAX,
 };
 
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index 8ea3dff..c1fbb8e 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -259,7 +259,8 @@
 tarpkg:
 	@cmd="$(PERF)/tests/perf-targz-src-pkg $(PERF)"; \
 	echo "- $@: $$cmd" && echo $$cmd > $@ && \
-	( eval $$cmd ) >> $@ 2>&1
+	( eval $$cmd ) >> $@ 2>&1 && \
+	rm -f $@
 
 make_kernelsrc:
 	@echo "- make -C <kernelsrc> tools/perf"
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 4495493..359e98fc 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -16,7 +16,7 @@
  * Then it checks if the number of syscalls reported as perf events by
  * the kernel corresponds to the number of syscalls made.
  */
-int test__basic_mmap(void)
+int test__basic_mmap(int subtest __maybe_unused)
 {
 	int err = -1;
 	union perf_event *event;
diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c
index 145050e..0c5ce44 100644
--- a/tools/perf/tests/mmap-thread-lookup.c
+++ b/tools/perf/tests/mmap-thread-lookup.c
@@ -149,7 +149,6 @@
 
 static int mmap_events(synth_cb synth)
 {
-	struct machines machines;
 	struct machine *machine;
 	int err, i;
 
@@ -162,8 +161,7 @@
 	 */
 	TEST_ASSERT_VAL("failed to create threads", !threads_create());
 
-	machines__init(&machines);
-	machine = &machines.host;
+	machine = machine__new_host();
 
 	dump_trace = verbose > 1 ? 1 : 0;
 
@@ -203,7 +201,7 @@
 	}
 
 	machine__delete_threads(machine);
-	machines__exit(&machines);
+	machine__delete(machine);
 	return err;
 }
 
@@ -221,7 +219,7 @@
  *
  * by using all thread objects.
  */
-int test__mmap_thread_lookup(void)
+int test__mmap_thread_lookup(int subtest __maybe_unused)
 {
 	/* perf_event__synthesize_threads synthesize */
 	TEST_ASSERT_VAL("failed with sythesizing all",
diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c
index 2006485..53c2273 100644
--- a/tools/perf/tests/openat-syscall-all-cpus.c
+++ b/tools/perf/tests/openat-syscall-all-cpus.c
@@ -7,7 +7,7 @@
 #include "debug.h"
 #include "stat.h"
 
-int test__openat_syscall_event_on_all_cpus(void)
+int test__openat_syscall_event_on_all_cpus(int subtest __maybe_unused)
 {
 	int err = -1, fd, cpu;
 	struct cpu_map *cpus;
diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c
index 5e811cd..eb99a105 100644
--- a/tools/perf/tests/openat-syscall-tp-fields.c
+++ b/tools/perf/tests/openat-syscall-tp-fields.c
@@ -6,7 +6,7 @@
 #include "tests.h"
 #include "debug.h"
 
-int test__syscall_openat_tp_fields(void)
+int test__syscall_openat_tp_fields(int subtest __maybe_unused)
 {
 	struct record_opts opts = {
 		.target = {
diff --git a/tools/perf/tests/openat-syscall.c b/tools/perf/tests/openat-syscall.c
index 033b547..1184f9b 100644
--- a/tools/perf/tests/openat-syscall.c
+++ b/tools/perf/tests/openat-syscall.c
@@ -5,7 +5,7 @@
 #include "debug.h"
 #include "tests.h"
 
-int test__openat_syscall_event(void)
+int test__openat_syscall_event(int subtest __maybe_unused)
 {
 	int err = -1, fd;
 	struct perf_evsel *evsel;
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 636d7b4..abe8849 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1765,7 +1765,7 @@
 	fprintf(stderr, " Warning: %s\n", msg);
 }
 
-int test__parse_events(void)
+int test__parse_events(int subtest __maybe_unused)
 {
 	int ret1, ret2 = 0;
 
diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c
index 2c63ea6..294c76b 100644
--- a/tools/perf/tests/parse-no-sample-id-all.c
+++ b/tools/perf/tests/parse-no-sample-id-all.c
@@ -67,7 +67,7 @@
  *
  * Return: %0 on success, %-1 if the test fails.
  */
-int test__parse_no_sample_id_all(void)
+int test__parse_no_sample_id_all(int subtest __maybe_unused)
 {
 	int err;
 
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index 7a228a2..1cc78ce 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -32,7 +32,7 @@
 	return cpu;
 }
 
-int test__PERF_RECORD(void)
+int test__PERF_RECORD(int subtest __maybe_unused)
 {
 	struct record_opts opts = {
 		.target = {
@@ -40,12 +40,11 @@
 			.uses_mmap = true,
 		},
 		.no_buffering = true,
-		.freq	      = 10,
 		.mmap_pages   = 256,
 	};
 	cpu_set_t cpu_mask;
 	size_t cpu_mask_size = sizeof(cpu_mask);
-	struct perf_evlist *evlist = perf_evlist__new_default();
+	struct perf_evlist *evlist = perf_evlist__new_dummy();
 	struct perf_evsel *evsel;
 	struct perf_sample sample;
 	const char *cmd = "sleep";
@@ -61,6 +60,9 @@
 	int total_events = 0, nr_events[PERF_RECORD_MAX] = { 0, };
 	char sbuf[STRERR_BUFSIZE];
 
+	if (evlist == NULL) /* Fallback for kernels lacking PERF_COUNT_SW_DUMMY */
+		evlist = perf_evlist__new_default();
+
 	if (evlist == NULL || argv == NULL) {
 		pr_debug("Not enough memory to create evlist\n");
 		goto out;
diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c
index faa04e9..1e2ba26 100644
--- a/tools/perf/tests/pmu.c
+++ b/tools/perf/tests/pmu.c
@@ -133,7 +133,7 @@
 	return &terms;
 }
 
-int test__pmu(void)
+int test__pmu(int subtest __maybe_unused)
 {
 	char *format = test_format_dir_get();
 	LIST_HEAD(formats);
diff --git a/tools/perf/tests/python-use.c b/tools/perf/tests/python-use.c
index 7760277..7a52834 100644
--- a/tools/perf/tests/python-use.c
+++ b/tools/perf/tests/python-use.c
@@ -4,11 +4,12 @@
 
 #include <stdio.h>
 #include <stdlib.h>
+#include <linux/compiler.h>
 #include "tests.h"
 
 extern int verbose;
 
-int test__python_use(void)
+int test__python_use(int subtest __maybe_unused)
 {
 	char *cmd;
 	int ret;
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index 30c0218..5f23710 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -290,7 +290,7 @@
  * checks sample format bits separately and together.  If the test passes %0 is
  * returned, otherwise %-1 is returned.
  */
-int test__sample_parsing(void)
+int test__sample_parsing(int subtest __maybe_unused)
 {
 	const u64 rf[] = {4, 5, 6, 7, 12, 13, 14, 15};
 	u64 sample_type;
diff --git a/tools/perf/tests/stat.c b/tools/perf/tests/stat.c
new file mode 100644
index 0000000..6a20ff2
--- /dev/null
+++ b/tools/perf/tests/stat.c
@@ -0,0 +1,111 @@
+#include <linux/compiler.h>
+#include "event.h"
+#include "tests.h"
+#include "stat.h"
+#include "counts.h"
+#include "debug.h"
+
+static bool has_term(struct stat_config_event *config,
+		     u64 tag, u64 val)
+{
+	unsigned i;
+
+	for (i = 0; i < config->nr; i++) {
+		if ((config->data[i].tag == tag) &&
+		    (config->data[i].val == val))
+			return true;
+	}
+
+	return false;
+}
+
+static int process_stat_config_event(struct perf_tool *tool __maybe_unused,
+				     union perf_event *event,
+				     struct perf_sample *sample __maybe_unused,
+				     struct machine *machine __maybe_unused)
+{
+	struct stat_config_event *config = &event->stat_config;
+	struct perf_stat_config stat_config;
+
+#define HAS(term, val) \
+	has_term(config, PERF_STAT_CONFIG_TERM__##term, val)
+
+	TEST_ASSERT_VAL("wrong nr",        config->nr == PERF_STAT_CONFIG_TERM__MAX);
+	TEST_ASSERT_VAL("wrong aggr_mode", HAS(AGGR_MODE, AGGR_CORE));
+	TEST_ASSERT_VAL("wrong scale",     HAS(SCALE, 1));
+	TEST_ASSERT_VAL("wrong interval",  HAS(INTERVAL, 1));
+
+#undef HAS
+
+	perf_event__read_stat_config(&stat_config, config);
+
+	TEST_ASSERT_VAL("wrong aggr_mode", stat_config.aggr_mode == AGGR_CORE);
+	TEST_ASSERT_VAL("wrong scale",     stat_config.scale == 1);
+	TEST_ASSERT_VAL("wrong interval",  stat_config.interval == 1);
+	return 0;
+}
+
+int test__synthesize_stat_config(int subtest __maybe_unused)
+{
+	struct perf_stat_config stat_config = {
+		.aggr_mode	= AGGR_CORE,
+		.scale		= 1,
+		.interval	= 1,
+	};
+
+	TEST_ASSERT_VAL("failed to synthesize stat_config",
+		!perf_event__synthesize_stat_config(NULL, &stat_config, process_stat_config_event, NULL));
+
+	return 0;
+}
+
+static int process_stat_event(struct perf_tool *tool __maybe_unused,
+			      union perf_event *event,
+			      struct perf_sample *sample __maybe_unused,
+			      struct machine *machine __maybe_unused)
+{
+	struct stat_event *st = &event->stat;
+
+	TEST_ASSERT_VAL("wrong cpu",    st->cpu    == 1);
+	TEST_ASSERT_VAL("wrong thread", st->thread == 2);
+	TEST_ASSERT_VAL("wrong id",     st->id     == 3);
+	TEST_ASSERT_VAL("wrong val",    st->val    == 100);
+	TEST_ASSERT_VAL("wrong run",    st->ena    == 200);
+	TEST_ASSERT_VAL("wrong ena",    st->run    == 300);
+	return 0;
+}
+
+int test__synthesize_stat(int subtest __maybe_unused)
+{
+	struct perf_counts_values count;
+
+	count.val = 100;
+	count.ena = 200;
+	count.run = 300;
+
+	TEST_ASSERT_VAL("failed to synthesize stat_config",
+		!perf_event__synthesize_stat(NULL, 1, 2, 3, &count, process_stat_event, NULL));
+
+	return 0;
+}
+
+static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
+				    union perf_event *event,
+				    struct perf_sample *sample __maybe_unused,
+				    struct machine *machine __maybe_unused)
+{
+	struct stat_round_event *stat_round = &event->stat_round;
+
+	TEST_ASSERT_VAL("wrong time", stat_round->time == 0xdeadbeef);
+	TEST_ASSERT_VAL("wrong type", stat_round->type == PERF_STAT_ROUND_TYPE__INTERVAL);
+	return 0;
+}
+
+int test__synthesize_stat_round(int subtest __maybe_unused)
+{
+	TEST_ASSERT_VAL("failed to synthesize stat_config",
+		!perf_event__synthesize_stat_round(NULL, 0xdeadbeef, PERF_STAT_ROUND_TYPE__INTERVAL,
+						   process_stat_round_event, NULL));
+
+	return 0;
+}
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index 5b83f56..36e8ce1 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -122,7 +122,7 @@
 	return err;
 }
 
-int test__sw_clock_freq(void)
+int test__sw_clock_freq(int subtest __maybe_unused)
 {
 	int ret;
 
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
index a02af50..ebd8016 100644
--- a/tools/perf/tests/switch-tracking.c
+++ b/tools/perf/tests/switch-tracking.c
@@ -305,7 +305,7 @@
  * evsel->system_wide and evsel->tracking flags (respectively) with other events
  * sometimes enabled or disabled.
  */
-int test__switch_tracking(void)
+int test__switch_tracking(int subtest __maybe_unused)
 {
 	const char *sched_switch = "sched:sched_switch";
 	struct switch_tracking switch_tracking = { .tids = NULL, };
@@ -455,7 +455,7 @@
 
 	perf_evlist__enable(evlist);
 
-	err = perf_evlist__disable_event(evlist, cpu_clocks_evsel);
+	err = perf_evsel__disable(cpu_clocks_evsel);
 	if (err) {
 		pr_debug("perf_evlist__disable_event failed!\n");
 		goto out_err;
@@ -474,7 +474,7 @@
 		goto out_err;
 	}
 
-	err = perf_evlist__disable_event(evlist, cycles_evsel);
+	err = perf_evsel__disable(cycles_evsel);
 	if (err) {
 		pr_debug("perf_evlist__disable_event failed!\n");
 		goto out_err;
@@ -500,7 +500,7 @@
 		goto out_err;
 	}
 
-	err = perf_evlist__enable_event(evlist, cycles_evsel);
+	err = perf_evsel__enable(cycles_evsel);
 	if (err) {
 		pr_debug("perf_evlist__disable_event failed!\n");
 		goto out_err;
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index add1638..2dfff7a 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -31,7 +31,7 @@
  * if the number of exit event reported by the kernel is 1 or not
  * in order to check the kernel returns correct number of event.
  */
-int test__task_exit(void)
+int test__task_exit(int subtest __maybe_unused)
 {
 	int err = -1;
 	union perf_event *event;
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 3c8734a..82b2b5e 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -1,6 +1,8 @@
 #ifndef TESTS_H
 #define TESTS_H
 
+#include <stdbool.h>
+
 #define TEST_ASSERT_VAL(text, cond)					 \
 do {									 \
 	if (!(cond)) {							 \
@@ -26,48 +28,63 @@
 
 struct test {
 	const char *desc;
-	int (*func)(void);
+	int (*func)(int subtest);
+	struct {
+		bool skip_if_fail;
+		int (*get_nr)(void);
+		const char *(*get_desc)(int subtest);
+	} subtest;
 };
 
 /* Tests */
-int test__vmlinux_matches_kallsyms(void);
-int test__openat_syscall_event(void);
-int test__openat_syscall_event_on_all_cpus(void);
-int test__basic_mmap(void);
-int test__PERF_RECORD(void);
-int test__perf_evsel__roundtrip_name_test(void);
-int test__perf_evsel__tp_sched_test(void);
-int test__syscall_openat_tp_fields(void);
-int test__pmu(void);
-int test__attr(void);
-int test__dso_data(void);
-int test__dso_data_cache(void);
-int test__dso_data_reopen(void);
-int test__parse_events(void);
-int test__hists_link(void);
-int test__python_use(void);
-int test__bp_signal(void);
-int test__bp_signal_overflow(void);
-int test__task_exit(void);
-int test__sw_clock_freq(void);
-int test__code_reading(void);
-int test__sample_parsing(void);
-int test__keep_tracking(void);
-int test__parse_no_sample_id_all(void);
-int test__dwarf_unwind(void);
-int test__hists_filter(void);
-int test__mmap_thread_lookup(void);
-int test__thread_mg_share(void);
-int test__hists_output(void);
-int test__hists_cumulate(void);
-int test__switch_tracking(void);
-int test__fdarray__filter(void);
-int test__fdarray__add(void);
-int test__kmod_path__parse(void);
-int test__thread_map(void);
-int test__llvm(void);
-int test__bpf(void);
-int test_session_topology(void);
+int test__vmlinux_matches_kallsyms(int subtest);
+int test__openat_syscall_event(int subtest);
+int test__openat_syscall_event_on_all_cpus(int subtest);
+int test__basic_mmap(int subtest);
+int test__PERF_RECORD(int subtest);
+int test__perf_evsel__roundtrip_name_test(int subtest);
+int test__perf_evsel__tp_sched_test(int subtest);
+int test__syscall_openat_tp_fields(int subtest);
+int test__pmu(int subtest);
+int test__attr(int subtest);
+int test__dso_data(int subtest);
+int test__dso_data_cache(int subtest);
+int test__dso_data_reopen(int subtest);
+int test__parse_events(int subtest);
+int test__hists_link(int subtest);
+int test__python_use(int subtest);
+int test__bp_signal(int subtest);
+int test__bp_signal_overflow(int subtest);
+int test__task_exit(int subtest);
+int test__sw_clock_freq(int subtest);
+int test__code_reading(int subtest);
+int test__sample_parsing(int subtest);
+int test__keep_tracking(int subtest);
+int test__parse_no_sample_id_all(int subtest);
+int test__dwarf_unwind(int subtest);
+int test__hists_filter(int subtest);
+int test__mmap_thread_lookup(int subtest);
+int test__thread_mg_share(int subtest);
+int test__hists_output(int subtest);
+int test__hists_cumulate(int subtest);
+int test__switch_tracking(int subtest);
+int test__fdarray__filter(int subtest);
+int test__fdarray__add(int subtest);
+int test__kmod_path__parse(int subtest);
+int test__thread_map(int subtest);
+int test__llvm(int subtest);
+const char *test__llvm_subtest_get_desc(int subtest);
+int test__llvm_subtest_get_nr(void);
+int test__bpf(int subtest);
+const char *test__bpf_subtest_get_desc(int subtest);
+int test__bpf_subtest_get_nr(void);
+int test_session_topology(int subtest);
+int test__thread_map_synthesize(int subtest);
+int test__cpu_map_synthesize(int subtest);
+int test__synthesize_stat_config(int subtest);
+int test__synthesize_stat(int subtest);
+int test__synthesize_stat_round(int subtest);
+int test__event_update(int subtest);
 
 #if defined(__arm__) || defined(__aarch64__)
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
diff --git a/tools/perf/tests/thread-map.c b/tools/perf/tests/thread-map.c
index 138a0e3..fccde84 100644
--- a/tools/perf/tests/thread-map.c
+++ b/tools/perf/tests/thread-map.c
@@ -4,7 +4,7 @@
 #include "thread_map.h"
 #include "debug.h"
 
-int test__thread_map(void)
+int test__thread_map(int subtest __maybe_unused)
 {
 	struct thread_map *map;
 
@@ -40,3 +40,46 @@
 	thread_map__put(map);
 	return 0;
 }
+
+static int process_event(struct perf_tool *tool __maybe_unused,
+			 union perf_event *event,
+			 struct perf_sample *sample __maybe_unused,
+			 struct machine *machine __maybe_unused)
+{
+	struct thread_map_event *map = &event->thread_map;
+	struct thread_map *threads;
+
+	TEST_ASSERT_VAL("wrong nr",   map->nr == 1);
+	TEST_ASSERT_VAL("wrong pid",  map->entries[0].pid == (u64) getpid());
+	TEST_ASSERT_VAL("wrong comm", !strcmp(map->entries[0].comm, "perf"));
+
+	threads = thread_map__new_event(&event->thread_map);
+	TEST_ASSERT_VAL("failed to alloc map", threads);
+
+	TEST_ASSERT_VAL("wrong nr", threads->nr == 1);
+	TEST_ASSERT_VAL("wrong pid",
+			thread_map__pid(threads, 0) == getpid());
+	TEST_ASSERT_VAL("wrong comm",
+			thread_map__comm(threads, 0) &&
+			!strcmp(thread_map__comm(threads, 0), "perf"));
+	TEST_ASSERT_VAL("wrong refcnt",
+			atomic_read(&threads->refcnt) == 1);
+	thread_map__put(threads);
+	return 0;
+}
+
+int test__thread_map_synthesize(int subtest __maybe_unused)
+{
+	struct thread_map *threads;
+
+	/* test map on current pid */
+	threads = thread_map__new_by_pid(getpid());
+	TEST_ASSERT_VAL("failed to alloc map", threads);
+
+	thread_map__read_comms(threads);
+
+	TEST_ASSERT_VAL("failed to synthesize map",
+		!perf_event__synthesize_thread_map2(NULL, threads, process_event, NULL));
+
+	return 0;
+}
diff --git a/tools/perf/tests/thread-mg-share.c b/tools/perf/tests/thread-mg-share.c
index 01fabb1..188b631 100644
--- a/tools/perf/tests/thread-mg-share.c
+++ b/tools/perf/tests/thread-mg-share.c
@@ -4,7 +4,7 @@
 #include "map.h"
 #include "debug.h"
 
-int test__thread_mg_share(void)
+int test__thread_mg_share(int subtest __maybe_unused)
 {
 	struct machines machines;
 	struct machine *machine;
diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c
index f5bb096..98fe69a 100644
--- a/tools/perf/tests/topology.c
+++ b/tools/perf/tests/topology.c
@@ -84,7 +84,7 @@
 	return 0;
 }
 
-int test_session_topology(void)
+int test_session_topology(int subtest __maybe_unused)
 {
 	char path[PATH_MAX];
 	struct cpu_map *map;
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index d677e01..f0bfc9e 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -18,7 +18,7 @@
 
 #define UM(x) kallsyms_map->unmap_ip(kallsyms_map, (x))
 
-int test__vmlinux_matches_kallsyms(void)
+int test__vmlinux_matches_kallsyms(int subtest __maybe_unused)
 {
 	int err = -1;
 	struct rb_node *nd;
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index e9703c0..d372021 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -528,7 +528,7 @@
 		.colorset = HE_COLORSET_SELECTED,
 		.name	  = "selected",
 		.fg	  = "black",
-		.bg	  = "lightgray",
+		.bg	  = "yellow",
 	},
 	{
 		.colorset = HE_COLORSET_CODE,
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index fa9eb92..901d481 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -178,12 +178,51 @@
 	return n;
 }
 
+static int callchain_node__count_flat_rows(struct callchain_node *node)
+{
+	struct callchain_list *chain;
+	char folded_sign = 0;
+	int n = 0;
+
+	list_for_each_entry(chain, &node->parent_val, list) {
+		if (!folded_sign) {
+			/* only check first chain list entry */
+			folded_sign = callchain_list__folded(chain);
+			if (folded_sign == '+')
+				return 1;
+		}
+		n++;
+	}
+
+	list_for_each_entry(chain, &node->val, list) {
+		if (!folded_sign) {
+			/* node->parent_val list might be empty */
+			folded_sign = callchain_list__folded(chain);
+			if (folded_sign == '+')
+				return 1;
+		}
+		n++;
+	}
+
+	return n;
+}
+
+static int callchain_node__count_folded_rows(struct callchain_node *node __maybe_unused)
+{
+	return 1;
+}
+
 static int callchain_node__count_rows(struct callchain_node *node)
 {
 	struct callchain_list *chain;
 	bool unfolded = false;
 	int n = 0;
 
+	if (callchain_param.mode == CHAIN_FLAT)
+		return callchain_node__count_flat_rows(node);
+	else if (callchain_param.mode == CHAIN_FOLDED)
+		return callchain_node__count_folded_rows(node);
+
 	list_for_each_entry(chain, &node->val, list) {
 		++n;
 		unfolded = chain->unfolded;
@@ -263,7 +302,7 @@
 	chain = list_entry(node->val.next, struct callchain_list, list);
 	chain->has_children = has_sibling;
 
-	if (!list_empty(&node->val)) {
+	if (node->val.next != node->val.prev) {
 		chain = list_entry(node->val.prev, struct callchain_list, list);
 		chain->has_children = !RB_EMPTY_ROOT(&node->rb_root);
 	}
@@ -279,6 +318,9 @@
 	for (nd = rb_first(root); nd; nd = rb_next(nd)) {
 		struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node);
 		callchain_node__init_have_children(node, has_sibling);
+		if (callchain_param.mode == CHAIN_FLAT ||
+		    callchain_param.mode == CHAIN_FOLDED)
+			callchain_node__make_parent_list(node);
 	}
 }
 
@@ -298,6 +340,9 @@
 	struct callchain_list *cl = container_of(ms, struct callchain_list, ms);
 	bool has_children;
 
+	if (!he || !ms)
+		return false;
+
 	if (ms == &he->ms)
 		has_children = hist_entry__toggle_fold(he);
 	else
@@ -574,6 +619,231 @@
 
 #define LEVEL_OFFSET_STEP 3
 
+static int hist_browser__show_callchain_list(struct hist_browser *browser,
+					     struct callchain_node *node,
+					     struct callchain_list *chain,
+					     unsigned short row, u64 total,
+					     bool need_percent, int offset,
+					     print_callchain_entry_fn print,
+					     struct callchain_print_arg *arg)
+{
+	char bf[1024], *alloc_str;
+	const char *str;
+
+	if (arg->row_offset != 0) {
+		arg->row_offset--;
+		return 0;
+	}
+
+	alloc_str = NULL;
+	str = callchain_list__sym_name(chain, bf, sizeof(bf),
+				       browser->show_dso);
+
+	if (need_percent) {
+		char buf[64];
+
+		callchain_node__scnprintf_value(node, buf, sizeof(buf),
+						total);
+
+		if (asprintf(&alloc_str, "%s %s", buf, str) < 0)
+			str = "Not enough memory!";
+		else
+			str = alloc_str;
+	}
+
+	print(browser, chain, str, offset, row, arg);
+
+	free(alloc_str);
+	return 1;
+}
+
+static int hist_browser__show_callchain_flat(struct hist_browser *browser,
+					     struct rb_root *root,
+					     unsigned short row, u64 total,
+					     print_callchain_entry_fn print,
+					     struct callchain_print_arg *arg,
+					     check_output_full_fn is_output_full)
+{
+	struct rb_node *node;
+	int first_row = row, offset = LEVEL_OFFSET_STEP;
+	bool need_percent;
+
+	node = rb_first(root);
+	need_percent = node && rb_next(node);
+
+	while (node) {
+		struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
+		struct rb_node *next = rb_next(node);
+		struct callchain_list *chain;
+		char folded_sign = ' ';
+		int first = true;
+		int extra_offset = 0;
+
+		list_for_each_entry(chain, &child->parent_val, list) {
+			bool was_first = first;
+
+			if (first)
+				first = false;
+			else if (need_percent)
+				extra_offset = LEVEL_OFFSET_STEP;
+
+			folded_sign = callchain_list__folded(chain);
+
+			row += hist_browser__show_callchain_list(browser, child,
+							chain, row, total,
+							was_first && need_percent,
+							offset + extra_offset,
+							print, arg);
+
+			if (is_output_full(browser, row))
+				goto out;
+
+			if (folded_sign == '+')
+				goto next;
+		}
+
+		list_for_each_entry(chain, &child->val, list) {
+			bool was_first = first;
+
+			if (first)
+				first = false;
+			else if (need_percent)
+				extra_offset = LEVEL_OFFSET_STEP;
+
+			folded_sign = callchain_list__folded(chain);
+
+			row += hist_browser__show_callchain_list(browser, child,
+							chain, row, total,
+							was_first && need_percent,
+							offset + extra_offset,
+							print, arg);
+
+			if (is_output_full(browser, row))
+				goto out;
+
+			if (folded_sign == '+')
+				break;
+		}
+
+next:
+		if (is_output_full(browser, row))
+			break;
+		node = next;
+	}
+out:
+	return row - first_row;
+}
+
+static char *hist_browser__folded_callchain_str(struct hist_browser *browser,
+						struct callchain_list *chain,
+						char *value_str, char *old_str)
+{
+	char bf[1024];
+	const char *str;
+	char *new;
+
+	str = callchain_list__sym_name(chain, bf, sizeof(bf),
+				       browser->show_dso);
+	if (old_str) {
+		if (asprintf(&new, "%s%s%s", old_str,
+			     symbol_conf.field_sep ?: ";", str) < 0)
+			new = NULL;
+	} else {
+		if (value_str) {
+			if (asprintf(&new, "%s %s", value_str, str) < 0)
+				new = NULL;
+		} else {
+			if (asprintf(&new, "%s", str) < 0)
+				new = NULL;
+		}
+	}
+	return new;
+}
+
+static int hist_browser__show_callchain_folded(struct hist_browser *browser,
+					       struct rb_root *root,
+					       unsigned short row, u64 total,
+					       print_callchain_entry_fn print,
+					       struct callchain_print_arg *arg,
+					       check_output_full_fn is_output_full)
+{
+	struct rb_node *node;
+	int first_row = row, offset = LEVEL_OFFSET_STEP;
+	bool need_percent;
+
+	node = rb_first(root);
+	need_percent = node && rb_next(node);
+
+	while (node) {
+		struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
+		struct rb_node *next = rb_next(node);
+		struct callchain_list *chain, *first_chain = NULL;
+		int first = true;
+		char *value_str = NULL, *value_str_alloc = NULL;
+		char *chain_str = NULL, *chain_str_alloc = NULL;
+
+		if (arg->row_offset != 0) {
+			arg->row_offset--;
+			goto next;
+		}
+
+		if (need_percent) {
+			char buf[64];
+
+			callchain_node__scnprintf_value(child, buf, sizeof(buf), total);
+			if (asprintf(&value_str, "%s", buf) < 0) {
+				value_str = (char *)"<...>";
+				goto do_print;
+			}
+			value_str_alloc = value_str;
+		}
+
+		list_for_each_entry(chain, &child->parent_val, list) {
+			chain_str = hist_browser__folded_callchain_str(browser,
+						chain, value_str, chain_str);
+			if (first) {
+				first = false;
+				first_chain = chain;
+			}
+
+			if (chain_str == NULL) {
+				chain_str = (char *)"Not enough memory!";
+				goto do_print;
+			}
+
+			chain_str_alloc = chain_str;
+		}
+
+		list_for_each_entry(chain, &child->val, list) {
+			chain_str = hist_browser__folded_callchain_str(browser,
+						chain, value_str, chain_str);
+			if (first) {
+				first = false;
+				first_chain = chain;
+			}
+
+			if (chain_str == NULL) {
+				chain_str = (char *)"Not enough memory!";
+				goto do_print;
+			}
+
+			chain_str_alloc = chain_str;
+		}
+
+do_print:
+		print(browser, first_chain, chain_str, offset, row++, arg);
+		free(value_str_alloc);
+		free(chain_str_alloc);
+
+next:
+		if (is_output_full(browser, row))
+			break;
+		node = next;
+	}
+
+	return row - first_row;
+}
+
 static int hist_browser__show_callchain(struct hist_browser *browser,
 					struct rb_root *root, int level,
 					unsigned short row, u64 total,
@@ -592,15 +862,12 @@
 	while (node) {
 		struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
 		struct rb_node *next = rb_next(node);
-		u64 cumul = callchain_cumul_hits(child);
 		struct callchain_list *chain;
 		char folded_sign = ' ';
 		int first = true;
 		int extra_offset = 0;
 
 		list_for_each_entry(chain, &child->val, list) {
-			char bf[1024], *alloc_str;
-			const char *str;
 			bool was_first = first;
 
 			if (first)
@@ -609,31 +876,16 @@
 				extra_offset = LEVEL_OFFSET_STEP;
 
 			folded_sign = callchain_list__folded(chain);
-			if (arg->row_offset != 0) {
-				arg->row_offset--;
-				goto do_next;
-			}
 
-			alloc_str = NULL;
-			str = callchain_list__sym_name(chain, bf, sizeof(bf),
-						       browser->show_dso);
+			row += hist_browser__show_callchain_list(browser, child,
+							chain, row, total,
+							was_first && need_percent,
+							offset + extra_offset,
+							print, arg);
 
-			if (was_first && need_percent) {
-				double percent = cumul * 100.0 / total;
-
-				if (asprintf(&alloc_str, "%2.2f%% %s", percent, str) < 0)
-					str = "Not enough memory!";
-				else
-					str = alloc_str;
-			}
-
-			print(browser, chain, str, offset + extra_offset, row, arg);
-
-			free(alloc_str);
-
-			if (is_output_full(browser, ++row))
+			if (is_output_full(browser, row))
 				goto out;
-do_next:
+
 			if (folded_sign == '+')
 				break;
 		}
@@ -789,7 +1041,8 @@
 		hist_browser__gotorc(browser, row, 0);
 
 		perf_hpp__for_each_format(fmt) {
-			if (perf_hpp__should_skip(fmt) || column++ < browser->b.horiz_scroll)
+			if (perf_hpp__should_skip(fmt, entry->hists) ||
+			    column++ < browser->b.horiz_scroll)
 				continue;
 
 			if (current_entry && browser->b.navkeypressed) {
@@ -844,10 +1097,22 @@
 				total = entry->stat.period;
 		}
 
-		printed += hist_browser__show_callchain(browser,
+		if (callchain_param.mode == CHAIN_FLAT) {
+			printed += hist_browser__show_callchain_flat(browser,
+					&entry->sorted_chain, row, total,
+					hist_browser__show_callchain_entry, &arg,
+					hist_browser__check_output_full);
+		} else if (callchain_param.mode == CHAIN_FOLDED) {
+			printed += hist_browser__show_callchain_folded(browser,
+					&entry->sorted_chain, row, total,
+					hist_browser__show_callchain_entry, &arg,
+					hist_browser__check_output_full);
+		} else {
+			printed += hist_browser__show_callchain(browser,
 					&entry->sorted_chain, 1, row, total,
 					hist_browser__show_callchain_entry, &arg,
 					hist_browser__check_output_full);
+		}
 
 		if (arg.is_current_entry)
 			browser->he_selection = entry;
@@ -880,7 +1145,7 @@
 	}
 
 	perf_hpp__for_each_format(fmt) {
-		if (perf_hpp__should_skip(fmt)  || column++ < browser->b.horiz_scroll)
+		if (perf_hpp__should_skip(fmt, hists)  || column++ < browser->b.horiz_scroll)
 			continue;
 
 		ret = fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists));
@@ -928,6 +1193,8 @@
 	}
 
 	ui_browser__hists_init_top(browser);
+	hb->he_selection = NULL;
+	hb->selection = NULL;
 
 	for (nd = browser->top; nd; nd = rb_next(nd)) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
@@ -1033,6 +1300,9 @@
 	 * and stop when we printed enough lines to fill the screen.
 	 */
 do_offset:
+	if (!nd)
+		return;
+
 	if (offset > 0) {
 		do {
 			h = rb_entry(nd, struct hist_entry, rb_node);
@@ -1145,7 +1415,7 @@
 		printed += fprintf(fp, "%c ", folded_sign);
 
 	perf_hpp__for_each_format(fmt) {
-		if (perf_hpp__should_skip(fmt))
+		if (perf_hpp__should_skip(fmt, he->hists))
 			continue;
 
 		if (!first) {
@@ -1794,10 +2064,9 @@
 	SLang_reset_tty();
 	SLang_init_tty(0, 0, 0);
 
-	if (min_pcnt) {
+	if (min_pcnt)
 		browser->min_pcnt = min_pcnt;
-		hist_browser__update_nr_entries(browser);
-	}
+	hist_browser__update_nr_entries(browser);
 
 	browser->pstack = pstack__new(3);
 	if (browser->pstack == NULL)
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index 4b3585e..0f8dcfd 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -89,8 +89,8 @@
 				perf_gtk__hpp_color_overhead_acc;
 }
 
-static void perf_gtk__add_callchain(struct rb_root *root, GtkTreeStore *store,
-				    GtkTreeIter *parent, int col, u64 total)
+static void perf_gtk__add_callchain_flat(struct rb_root *root, GtkTreeStore *store,
+					 GtkTreeIter *parent, int col, u64 total)
 {
 	struct rb_node *nd;
 	bool has_single_node = (rb_first(root) == rb_last(root));
@@ -100,13 +100,132 @@
 		struct callchain_list *chain;
 		GtkTreeIter iter, new_parent;
 		bool need_new_parent;
-		double percent;
-		u64 hits, child_total;
 
 		node = rb_entry(nd, struct callchain_node, rb_node);
 
-		hits = callchain_cumul_hits(node);
-		percent = 100.0 * hits / total;
+		new_parent = *parent;
+		need_new_parent = !has_single_node;
+
+		callchain_node__make_parent_list(node);
+
+		list_for_each_entry(chain, &node->parent_val, list) {
+			char buf[128];
+
+			gtk_tree_store_append(store, &iter, &new_parent);
+
+			callchain_node__scnprintf_value(node, buf, sizeof(buf), total);
+			gtk_tree_store_set(store, &iter, 0, buf, -1);
+
+			callchain_list__sym_name(chain, buf, sizeof(buf), false);
+			gtk_tree_store_set(store, &iter, col, buf, -1);
+
+			if (need_new_parent) {
+				/*
+				 * Only show the top-most symbol in a callchain
+				 * if it's not the only callchain.
+				 */
+				new_parent = iter;
+				need_new_parent = false;
+			}
+		}
+
+		list_for_each_entry(chain, &node->val, list) {
+			char buf[128];
+
+			gtk_tree_store_append(store, &iter, &new_parent);
+
+			callchain_node__scnprintf_value(node, buf, sizeof(buf), total);
+			gtk_tree_store_set(store, &iter, 0, buf, -1);
+
+			callchain_list__sym_name(chain, buf, sizeof(buf), false);
+			gtk_tree_store_set(store, &iter, col, buf, -1);
+
+			if (need_new_parent) {
+				/*
+				 * Only show the top-most symbol in a callchain
+				 * if it's not the only callchain.
+				 */
+				new_parent = iter;
+				need_new_parent = false;
+			}
+		}
+	}
+}
+
+static void perf_gtk__add_callchain_folded(struct rb_root *root, GtkTreeStore *store,
+					   GtkTreeIter *parent, int col, u64 total)
+{
+	struct rb_node *nd;
+
+	for (nd = rb_first(root); nd; nd = rb_next(nd)) {
+		struct callchain_node *node;
+		struct callchain_list *chain;
+		GtkTreeIter iter;
+		char buf[64];
+		char *str, *str_alloc = NULL;
+		bool first = true;
+
+		node = rb_entry(nd, struct callchain_node, rb_node);
+
+		callchain_node__make_parent_list(node);
+
+		list_for_each_entry(chain, &node->parent_val, list) {
+			char name[1024];
+
+			callchain_list__sym_name(chain, name, sizeof(name), false);
+
+			if (asprintf(&str, "%s%s%s",
+				     first ? "" : str_alloc,
+				     first ? "" : symbol_conf.field_sep ?: "; ",
+				     name) < 0)
+				return;
+
+			first = false;
+			free(str_alloc);
+			str_alloc = str;
+		}
+
+		list_for_each_entry(chain, &node->val, list) {
+			char name[1024];
+
+			callchain_list__sym_name(chain, name, sizeof(name), false);
+
+			if (asprintf(&str, "%s%s%s",
+				     first ? "" : str_alloc,
+				     first ? "" : symbol_conf.field_sep ?: "; ",
+				     name) < 0)
+				return;
+
+			first = false;
+			free(str_alloc);
+			str_alloc = str;
+		}
+
+		gtk_tree_store_append(store, &iter, parent);
+
+		callchain_node__scnprintf_value(node, buf, sizeof(buf), total);
+		gtk_tree_store_set(store, &iter, 0, buf, -1);
+
+		gtk_tree_store_set(store, &iter, col, str, -1);
+
+		free(str_alloc);
+	}
+}
+
+static void perf_gtk__add_callchain_graph(struct rb_root *root, GtkTreeStore *store,
+					  GtkTreeIter *parent, int col, u64 total)
+{
+	struct rb_node *nd;
+	bool has_single_node = (rb_first(root) == rb_last(root));
+
+	for (nd = rb_first(root); nd; nd = rb_next(nd)) {
+		struct callchain_node *node;
+		struct callchain_list *chain;
+		GtkTreeIter iter, new_parent;
+		bool need_new_parent;
+		u64 child_total;
+
+		node = rb_entry(nd, struct callchain_node, rb_node);
 
 		new_parent = *parent;
 		need_new_parent = !has_single_node && (node->val_nr > 1);
@@ -116,7 +235,7 @@
 
 			gtk_tree_store_append(store, &iter, &new_parent);
 
-			scnprintf(buf, sizeof(buf), "%5.2f%%", percent);
+			callchain_node__scnprintf_value(node, buf, sizeof(buf), total);
 			gtk_tree_store_set(store, &iter, 0, buf, -1);
 
 			callchain_list__sym_name(chain, buf, sizeof(buf), false);
@@ -138,11 +257,22 @@
 			child_total = total;
 
 		/* Now 'iter' contains info of the last callchain_list */
-		perf_gtk__add_callchain(&node->rb_root, store, &iter, col,
-					child_total);
+		perf_gtk__add_callchain_graph(&node->rb_root, store, &iter, col,
+					      child_total);
 	}
 }
 
+static void perf_gtk__add_callchain(struct rb_root *root, GtkTreeStore *store,
+				    GtkTreeIter *parent, int col, u64 total)
+{
+	if (callchain_param.mode == CHAIN_FLAT)
+		perf_gtk__add_callchain_flat(root, store, parent, col, total);
+	else if (callchain_param.mode == CHAIN_FOLDED)
+		perf_gtk__add_callchain_folded(root, store, parent, col, total);
+	else
+		perf_gtk__add_callchain_graph(root, store, parent, col, total);
+}
+
 static void on_row_activated(GtkTreeView *view, GtkTreePath *path,
 			     GtkTreeViewColumn *col __maybe_unused,
 			     gpointer user_data __maybe_unused)
@@ -188,7 +318,7 @@
 	col_idx = 0;
 
 	perf_hpp__for_each_format(fmt) {
-		if (perf_hpp__should_skip(fmt))
+		if (perf_hpp__should_skip(fmt, hists))
 			continue;
 
 		/*
@@ -238,7 +368,7 @@
 		col_idx = 0;
 
 		perf_hpp__for_each_format(fmt) {
-			if (perf_hpp__should_skip(fmt))
+			if (perf_hpp__should_skip(fmt, h->hists))
 				continue;
 
 			if (fmt->color)
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 5029ba2..bf2a66e 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -443,7 +443,6 @@
 
 void perf_hpp__init(void)
 {
-	struct list_head *list;
 	int i;
 
 	for (i = 0; i < PERF_HPP__MAX_INDEX; i++) {
@@ -484,17 +483,6 @@
 
 	if (symbol_conf.show_total_period)
 		hpp_dimension__add_output(PERF_HPP__PERIOD);
-
-	/* prepend overhead field for backward compatiblity.  */
-	list = &perf_hpp__format[PERF_HPP__OVERHEAD].sort_list;
-	if (list_empty(list))
-		list_add(list, &perf_hpp__sort_list);
-
-	if (symbol_conf.cumulate_callchain) {
-		list = &perf_hpp__format[PERF_HPP__OVERHEAD_ACC].sort_list;
-		if (list_empty(list))
-			list_add(list, &perf_hpp__sort_list);
-	}
 }
 
 void perf_hpp__column_register(struct perf_hpp_fmt *format)
@@ -619,7 +607,7 @@
 	struct perf_hpp dummy_hpp;
 
 	perf_hpp__for_each_format(fmt) {
-		if (perf_hpp__should_skip(fmt))
+		if (perf_hpp__should_skip(fmt, hists))
 			continue;
 
 		if (first)
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index dfcbc90..387110d 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -34,10 +34,10 @@
 	return ret;
 }
 
-static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain,
+static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_node *node,
+				     struct callchain_list *chain,
 				     int depth, int depth_mask, int period,
-				     u64 total_samples, u64 hits,
-				     int left_margin)
+				     u64 total_samples, int left_margin)
 {
 	int i;
 	size_t ret = 0;
@@ -50,10 +50,9 @@
 		else
 			ret += fprintf(fp, " ");
 		if (!period && i == depth - 1) {
-			double percent;
-
-			percent = hits * 100.0 / total_samples;
-			ret += percent_color_fprintf(fp, "--%2.2f%%-- ", percent);
+			ret += fprintf(fp, "--");
+			ret += callchain_node__fprintf_value(node, fp, total_samples);
+			ret += fprintf(fp, "--");
 		} else
 			ret += fprintf(fp, "%s", "          ");
 	}
@@ -82,13 +81,14 @@
 					 int depth_mask, int left_margin)
 {
 	struct rb_node *node, *next;
-	struct callchain_node *child;
+	struct callchain_node *child = NULL;
 	struct callchain_list *chain;
 	int new_depth_mask = depth_mask;
 	u64 remaining;
 	size_t ret = 0;
 	int i;
 	uint entries_printed = 0;
+	int cumul_count = 0;
 
 	remaining = total_samples;
 
@@ -100,6 +100,7 @@
 		child = rb_entry(node, struct callchain_node, rb_node);
 		cumul = callchain_cumul_hits(child);
 		remaining -= cumul;
+		cumul_count += callchain_cumul_counts(child);
 
 		/*
 		 * The depth mask manages the output of pipes that show
@@ -120,10 +121,9 @@
 						   left_margin);
 		i = 0;
 		list_for_each_entry(chain, &child->val, list) {
-			ret += ipchain__fprintf_graph(fp, chain, depth,
+			ret += ipchain__fprintf_graph(fp, child, chain, depth,
 						      new_depth_mask, i++,
 						      total_samples,
-						      cumul,
 						      left_margin);
 		}
 
@@ -143,14 +143,23 @@
 
 	if (callchain_param.mode == CHAIN_GRAPH_REL &&
 		remaining && remaining != total_samples) {
+		struct callchain_node rem_node = {
+			.hit = remaining,
+		};
 
 		if (!rem_sq_bracket)
 			return ret;
 
+		if (callchain_param.value == CCVAL_COUNT && child && child->parent) {
+			rem_node.count = child->parent->children_count - cumul_count;
+			if (rem_node.count <= 0)
+				return ret;
+		}
+
 		new_depth_mask &= ~(1 << (depth - 1));
-		ret += ipchain__fprintf_graph(fp, &rem_hits, depth,
+		ret += ipchain__fprintf_graph(fp, &rem_node, &rem_hits, depth,
 					      new_depth_mask, 0, total_samples,
-					      remaining, left_margin);
+					      left_margin);
 	}
 
 	return ret;
@@ -243,13 +252,63 @@
 	struct rb_node *rb_node = rb_first(tree);
 
 	while (rb_node) {
-		double percent;
+		chain = rb_entry(rb_node, struct callchain_node, rb_node);
+
+		ret += fprintf(fp, "           ");
+		ret += callchain_node__fprintf_value(chain, fp, total_samples);
+		ret += fprintf(fp, "\n");
+		ret += __callchain__fprintf_flat(fp, chain, total_samples);
+		ret += fprintf(fp, "\n");
+		if (++entries_printed == callchain_param.print_limit)
+			break;
+
+		rb_node = rb_next(rb_node);
+	}
+
+	return ret;
+}
+
+static size_t __callchain__fprintf_folded(FILE *fp, struct callchain_node *node)
+{
+	const char *sep = symbol_conf.field_sep ?: ";";
+	struct callchain_list *chain;
+	size_t ret = 0;
+	char bf[1024];
+	bool first;
+
+	if (!node)
+		return 0;
+
+	ret += __callchain__fprintf_folded(fp, node->parent);
+
+	first = (ret == 0);
+	list_for_each_entry(chain, &node->val, list) {
+		if (chain->ip >= PERF_CONTEXT_MAX)
+			continue;
+		ret += fprintf(fp, "%s%s", first ? "" : sep,
+			       callchain_list__sym_name(chain,
+						bf, sizeof(bf), false));
+		first = false;
+	}
+
+	return ret;
+}
+
+static size_t callchain__fprintf_folded(FILE *fp, struct rb_root *tree,
+					u64 total_samples)
+{
+	size_t ret = 0;
+	u32 entries_printed = 0;
+	struct callchain_node *chain;
+	struct rb_node *rb_node = rb_first(tree);
+
+	while (rb_node) {
 
 		chain = rb_entry(rb_node, struct callchain_node, rb_node);
-		percent = chain->hit * 100.0 / total_samples;
 
-		ret = percent_color_fprintf(fp, "           %6.2f%%\n", percent);
-		ret += __callchain__fprintf_flat(fp, chain, total_samples);
+		ret += callchain_node__fprintf_value(chain, fp, total_samples);
+		ret += fprintf(fp, " ");
+		ret += __callchain__fprintf_folded(fp, chain);
 		ret += fprintf(fp, "\n");
 		if (++entries_printed == callchain_param.print_limit)
 			break;
@@ -278,6 +337,9 @@
 	case CHAIN_FLAT:
 		return callchain__fprintf_flat(fp, &he->sorted_chain, total_samples);
 		break;
+	case CHAIN_FOLDED:
+		return callchain__fprintf_folded(fp, &he->sorted_chain, total_samples);
+		break;
 	case CHAIN_NONE:
 		break;
 	default:
@@ -323,7 +385,7 @@
 		return 0;
 
 	perf_hpp__for_each_format(fmt) {
-		if (perf_hpp__should_skip(fmt))
+		if (perf_hpp__should_skip(fmt, he->hists))
 			continue;
 
 		/*
@@ -402,7 +464,7 @@
 	fprintf(fp, "# ");
 
 	perf_hpp__for_each_format(fmt) {
-		if (perf_hpp__should_skip(fmt))
+		if (perf_hpp__should_skip(fmt, hists))
 			continue;
 
 		if (!first)
@@ -428,7 +490,7 @@
 	perf_hpp__for_each_format(fmt) {
 		unsigned int i;
 
-		if (perf_hpp__should_skip(fmt))
+		if (perf_hpp__should_skip(fmt, hists))
 			continue;
 
 		if (!first)
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 591b3fe..5eec53a 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -6,24 +6,20 @@
 libperf-y += ctype.o
 libperf-y += db-export.o
 libperf-y += env.o
-libperf-y += environment.o
 libperf-y += event.o
 libperf-y += evlist.o
 libperf-y += evsel.o
-libperf-y += exec_cmd.o
-libperf-y += find_next_bit.o
-libperf-y += help.o
+libperf-y += find_bit.o
 libperf-y += kallsyms.o
 libperf-y += levenshtein.o
 libperf-y += llvm-utils.o
-libperf-y += parse-options.o
 libperf-y += parse-events.o
 libperf-y += perf_regs.o
 libperf-y += path.o
 libperf-y += rbtree.o
+libperf-y += libstring.o
 libperf-y += bitmap.o
 libperf-y += hweight.o
-libperf-y += run-command.o
 libperf-y += quote.o
 libperf-y += strbuf.o
 libperf-y += string.o
@@ -32,11 +28,9 @@
 libperf-y += top.o
 libperf-y += usage.o
 libperf-y += wrapper.o
-libperf-y += sigchain.o
 libperf-y += dso.o
 libperf-y += symbol.o
 libperf-y += color.o
-libperf-y += pager.o
 libperf-y += header.o
 libperf-y += callchain.o
 libperf-y += values.o
@@ -86,8 +80,11 @@
 libperf-$(CONFIG_AUXTRACE) += intel-bts.o
 libperf-y += parse-branch-options.o
 libperf-y += parse-regs-options.o
+libperf-y += term.o
+libperf-y += help-unknown-cmd.o
 
 libperf-$(CONFIG_LIBBPF) += bpf-loader.o
+libperf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o
 libperf-$(CONFIG_LIBELF) += symbol-elf.o
 libperf-$(CONFIG_LIBELF) += probe-file.o
 libperf-$(CONFIG_LIBELF) += probe-event.o
@@ -110,7 +107,6 @@
 libperf-$(CONFIG_LZMA) += lzma.o
 
 CFLAGS_config.o   += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
-CFLAGS_exec_cmd.o += -DPERF_EXEC_PATH="BUILD_STR($(perfexecdir_SQ))" -DPREFIX="BUILD_STR($(prefix_SQ))"
 
 $(OUTPUT)util/parse-events-flex.c: util/parse-events.l $(OUTPUT)util/parse-events-bison.c
 	$(call rule_mkdir)
@@ -136,8 +132,10 @@
 $(OUTPUT)util/parse-events.o: $(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-bison.c
 $(OUTPUT)util/pmu.o: $(OUTPUT)util/pmu-flex.c $(OUTPUT)util/pmu-bison.c
 
-CFLAGS_find_next_bit.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
+CFLAGS_bitmap.o        += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
+CFLAGS_find_bit.o      += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
 CFLAGS_rbtree.o        += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
+CFLAGS_libstring.o     += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
 CFLAGS_hweight.o       += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
 CFLAGS_parse-events.o  += -Wno-redundant-decls
 
@@ -145,7 +143,11 @@
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
 
-$(OUTPUT)util/find_next_bit.o: ../lib/util/find_next_bit.c FORCE
+$(OUTPUT)util/bitmap.o: ../lib/bitmap.c FORCE
+	$(call rule_mkdir)
+	$(call if_changed_dep,cc_o_c)
+
+$(OUTPUT)util/find_bit.o: ../lib/find_bit.c FORCE
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
 
@@ -153,6 +155,10 @@
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
 
+$(OUTPUT)util/libstring.o: ../lib/string.c FORCE
+	$(call rule_mkdir)
+	$(call if_changed_dep,cc_o_c)
+
 $(OUTPUT)util/hweight.o: ../lib/hweight.c FORCE
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 1dd1949..b795b69 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -65,6 +65,11 @@
 
 	name++;
 
+#ifdef __arm__
+	if (strchr(name, '+'))
+		return -1;
+#endif
+
 	tok = strchr(name, '>');
 	if (tok == NULL)
 		return -1;
@@ -246,7 +251,11 @@
 		return -1;
 
 	target = ++s;
+#ifdef __arm__
+	comment = strchr(s, ';');
+#else
 	comment = strchr(s, '#');
+#endif
 
 	if (comment != NULL)
 		s = comment - 1;
@@ -354,6 +363,20 @@
 	{ .name = "addq",  .ops  = &mov_ops, },
 	{ .name = "addw",  .ops  = &mov_ops, },
 	{ .name = "and",   .ops  = &mov_ops, },
+#ifdef __arm__
+	{ .name = "b",     .ops  = &jump_ops, }, // might also be a call
+	{ .name = "bcc",   .ops  = &jump_ops, },
+	{ .name = "bcs",   .ops  = &jump_ops, },
+	{ .name = "beq",   .ops  = &jump_ops, },
+	{ .name = "bge",   .ops  = &jump_ops, },
+	{ .name = "bgt",   .ops  = &jump_ops, },
+	{ .name = "bhi",   .ops  = &jump_ops, },
+	{ .name = "bl",    .ops  = &call_ops, },
+	{ .name = "blt",   .ops  = &jump_ops, },
+	{ .name = "bls",   .ops  = &jump_ops, },
+	{ .name = "blx",   .ops  = &call_ops, },
+	{ .name = "bne",   .ops  = &jump_ops, },
+#endif
 	{ .name = "bts",   .ops  = &mov_ops, },
 	{ .name = "call",  .ops  = &call_ops, },
 	{ .name = "callq", .ops  = &call_ops, },
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 7f10430a..360fda0 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -45,7 +45,7 @@
 #include "event.h"
 #include "session.h"
 #include "debug.h"
-#include "parse-options.h"
+#include <subcmd/parse-options.h>
 
 #include "intel-pt.h"
 #include "intel-bts.h"
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 4c50411..540a7efa 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -5,11 +5,15 @@
  * Copyright (C) 2015 Huawei Inc.
  */
 
+#include <linux/bpf.h>
 #include <bpf/libbpf.h>
 #include <linux/err.h>
+#include <linux/string.h>
 #include "perf.h"
 #include "debug.h"
 #include "bpf-loader.h"
+#include "bpf-prologue.h"
+#include "llvm-utils.h"
 #include "probe-event.h"
 #include "probe-finder.h" // for MAX_PROBES
 #include "llvm-utils.h"
@@ -32,6 +36,10 @@
 
 struct bpf_prog_priv {
 	struct perf_probe_event pev;
+	bool need_prologue;
+	struct bpf_insn *insns_buf;
+	int nr_types;
+	int *type_mapping;
 };
 
 static bool libbpf_initialized;
@@ -106,10 +114,178 @@
 	struct bpf_prog_priv *priv = _priv;
 
 	cleanup_perf_probe_events(&priv->pev, 1);
+	zfree(&priv->insns_buf);
+	zfree(&priv->type_mapping);
 	free(priv);
 }
 
 static int
+prog_config__exec(const char *value, struct perf_probe_event *pev)
+{
+	pev->uprobes = true;
+	pev->target = strdup(value);
+	if (!pev->target)
+		return -ENOMEM;
+	return 0;
+}
+
+static int
+prog_config__module(const char *value, struct perf_probe_event *pev)
+{
+	pev->uprobes = false;
+	pev->target = strdup(value);
+	if (!pev->target)
+		return -ENOMEM;
+	return 0;
+}
+
+static int
+prog_config__bool(const char *value, bool *pbool, bool invert)
+{
+	int err;
+	bool bool_value;
+
+	if (!pbool)
+		return -EINVAL;
+
+	err = strtobool(value, &bool_value);
+	if (err)
+		return err;
+
+	*pbool = invert ? !bool_value : bool_value;
+	return 0;
+}
+
+static int
+prog_config__inlines(const char *value,
+		     struct perf_probe_event *pev __maybe_unused)
+{
+	return prog_config__bool(value, &probe_conf.no_inlines, true);
+}
+
+static int
+prog_config__force(const char *value,
+		   struct perf_probe_event *pev __maybe_unused)
+{
+	return prog_config__bool(value, &probe_conf.force_add, false);
+}
+
+static struct {
+	const char *key;
+	const char *usage;
+	const char *desc;
+	int (*func)(const char *, struct perf_probe_event *);
+} bpf_prog_config_terms[] = {
+	{
+		.key	= "exec",
+		.usage	= "exec=<full path of file>",
+		.desc	= "Set uprobe target",
+		.func	= prog_config__exec,
+	},
+	{
+		.key	= "module",
+		.usage	= "module=<module name>    ",
+		.desc	= "Set kprobe module",
+		.func	= prog_config__module,
+	},
+	{
+		.key	= "inlines",
+		.usage	= "inlines=[yes|no]        ",
+		.desc	= "Probe at inline symbol",
+		.func	= prog_config__inlines,
+	},
+	{
+		.key	= "force",
+		.usage	= "force=[yes|no]          ",
+		.desc	= "Forcibly add events with existing name",
+		.func	= prog_config__force,
+	},
+};
+
+static int
+do_prog_config(const char *key, const char *value,
+	       struct perf_probe_event *pev)
+{
+	unsigned int i;
+
+	pr_debug("config bpf program: %s=%s\n", key, value);
+	for (i = 0; i < ARRAY_SIZE(bpf_prog_config_terms); i++)
+		if (strcmp(key, bpf_prog_config_terms[i].key) == 0)
+			return bpf_prog_config_terms[i].func(value, pev);
+
+	pr_debug("BPF: ERROR: invalid program config option: %s=%s\n",
+		 key, value);
+
+	pr_debug("\nHint: Valid options are:\n");
+	for (i = 0; i < ARRAY_SIZE(bpf_prog_config_terms); i++)
+		pr_debug("\t%s:\t%s\n", bpf_prog_config_terms[i].usage,
+			 bpf_prog_config_terms[i].desc);
+	pr_debug("\n");
+
+	return -BPF_LOADER_ERRNO__PROGCONF_TERM;
+}
+
+static const char *
+parse_prog_config_kvpair(const char *config_str, struct perf_probe_event *pev)
+{
+	char *text = strdup(config_str);
+	char *sep, *line;
+	const char *main_str = NULL;
+	int err = 0;
+
+	if (!text) {
+		pr_debug("No enough memory: dup config_str failed\n");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	line = text;
+	while ((sep = strchr(line, ';'))) {
+		char *equ;
+
+		*sep = '\0';
+		equ = strchr(line, '=');
+		if (!equ) {
+			pr_warning("WARNING: invalid config in BPF object: %s\n",
+				   line);
+			pr_warning("\tShould be 'key=value'.\n");
+			goto nextline;
+		}
+		*equ = '\0';
+
+		err = do_prog_config(line, equ + 1, pev);
+		if (err)
+			break;
+nextline:
+		line = sep + 1;
+	}
+
+	if (!err)
+		main_str = config_str + (line - text);
+	free(text);
+
+	return err ? ERR_PTR(err) : main_str;
+}
+
+static int
+parse_prog_config(const char *config_str, struct perf_probe_event *pev)
+{
+	int err;
+	const char *main_str = parse_prog_config_kvpair(config_str, pev);
+
+	if (IS_ERR(main_str))
+		return PTR_ERR(main_str);
+
+	err = parse_perf_probe_command(main_str, pev);
+	if (err < 0) {
+		pr_debug("bpf: '%s' is not a valid config string\n",
+			 config_str);
+		/* parse failed, don't need clear pev. */
+		return -BPF_LOADER_ERRNO__CONFIG;
+	}
+	return 0;
+}
+
+static int
 config_bpf_program(struct bpf_program *prog)
 {
 	struct perf_probe_event *pev = NULL;
@@ -117,6 +293,10 @@
 	const char *config_str;
 	int err;
 
+	/* Initialize per-program probing setting */
+	probe_conf.no_inlines = false;
+	probe_conf.force_add = false;
+
 	config_str = bpf_program__title(prog, false);
 	if (IS_ERR(config_str)) {
 		pr_debug("bpf: unable to get title for program\n");
@@ -131,13 +311,9 @@
 	pev = &priv->pev;
 
 	pr_debug("bpf: config program '%s'\n", config_str);
-	err = parse_perf_probe_command(config_str, pev);
-	if (err < 0) {
-		pr_debug("bpf: '%s' is not a valid config string\n",
-			 config_str);
-		err = -BPF_LOADER_ERRNO__CONFIG;
+	err = parse_prog_config(config_str, pev);
+	if (err)
 		goto errout;
-	}
 
 	if (pev->group && strcmp(pev->group, PERF_BPF_PROBE_GROUP)) {
 		pr_debug("bpf: '%s': group for event is set and not '%s'.\n",
@@ -197,6 +373,220 @@
 	return err;
 }
 
+static int
+preproc_gen_prologue(struct bpf_program *prog, int n,
+		     struct bpf_insn *orig_insns, int orig_insns_cnt,
+		     struct bpf_prog_prep_result *res)
+{
+	struct probe_trace_event *tev;
+	struct perf_probe_event *pev;
+	struct bpf_prog_priv *priv;
+	struct bpf_insn *buf;
+	size_t prologue_cnt = 0;
+	int i, err;
+
+	err = bpf_program__get_private(prog, (void **)&priv);
+	if (err || !priv)
+		goto errout;
+
+	pev = &priv->pev;
+
+	if (n < 0 || n >= priv->nr_types)
+		goto errout;
+
+	/* Find a tev belongs to that type */
+	for (i = 0; i < pev->ntevs; i++) {
+		if (priv->type_mapping[i] == n)
+			break;
+	}
+
+	if (i >= pev->ntevs) {
+		pr_debug("Internal error: prologue type %d not found\n", n);
+		return -BPF_LOADER_ERRNO__PROLOGUE;
+	}
+
+	tev = &pev->tevs[i];
+
+	buf = priv->insns_buf;
+	err = bpf__gen_prologue(tev->args, tev->nargs,
+				buf, &prologue_cnt,
+				BPF_MAXINSNS - orig_insns_cnt);
+	if (err) {
+		const char *title;
+
+		title = bpf_program__title(prog, false);
+		if (!title)
+			title = "[unknown]";
+
+		pr_debug("Failed to generate prologue for program %s\n",
+			 title);
+		return err;
+	}
+
+	memcpy(&buf[prologue_cnt], orig_insns,
+	       sizeof(struct bpf_insn) * orig_insns_cnt);
+
+	res->new_insn_ptr = buf;
+	res->new_insn_cnt = prologue_cnt + orig_insns_cnt;
+	res->pfd = NULL;
+	return 0;
+
+errout:
+	pr_debug("Internal error in preproc_gen_prologue\n");
+	return -BPF_LOADER_ERRNO__PROLOGUE;
+}
+
+/*
+ * compare_tev_args is reflexive, transitive and antisymmetric.
+ * I can proof it but this margin is too narrow to contain.
+ */
+static int compare_tev_args(const void *ptev1, const void *ptev2)
+{
+	int i, ret;
+	const struct probe_trace_event *tev1 =
+		*(const struct probe_trace_event **)ptev1;
+	const struct probe_trace_event *tev2 =
+		*(const struct probe_trace_event **)ptev2;
+
+	ret = tev2->nargs - tev1->nargs;
+	if (ret)
+		return ret;
+
+	for (i = 0; i < tev1->nargs; i++) {
+		struct probe_trace_arg *arg1, *arg2;
+		struct probe_trace_arg_ref *ref1, *ref2;
+
+		arg1 = &tev1->args[i];
+		arg2 = &tev2->args[i];
+
+		ret = strcmp(arg1->value, arg2->value);
+		if (ret)
+			return ret;
+
+		ref1 = arg1->ref;
+		ref2 = arg2->ref;
+
+		while (ref1 && ref2) {
+			ret = ref2->offset - ref1->offset;
+			if (ret)
+				return ret;
+
+			ref1 = ref1->next;
+			ref2 = ref2->next;
+		}
+
+		if (ref1 || ref2)
+			return ref2 ? 1 : -1;
+	}
+
+	return 0;
+}
+
+/*
+ * Assign a type number to each tevs in a pev.
+ * mapping is an array with same slots as tevs in that pev.
+ * nr_types will be set to number of types.
+ */
+static int map_prologue(struct perf_probe_event *pev, int *mapping,
+			int *nr_types)
+{
+	int i, type = 0;
+	struct probe_trace_event **ptevs;
+
+	size_t array_sz = sizeof(*ptevs) * pev->ntevs;
+
+	ptevs = malloc(array_sz);
+	if (!ptevs) {
+		pr_debug("No ehough memory: alloc ptevs failed\n");
+		return -ENOMEM;
+	}
+
+	pr_debug("In map_prologue, ntevs=%d\n", pev->ntevs);
+	for (i = 0; i < pev->ntevs; i++)
+		ptevs[i] = &pev->tevs[i];
+
+	qsort(ptevs, pev->ntevs, sizeof(*ptevs),
+	      compare_tev_args);
+
+	for (i = 0; i < pev->ntevs; i++) {
+		int n;
+
+		n = ptevs[i] - pev->tevs;
+		if (i == 0) {
+			mapping[n] = type;
+			pr_debug("mapping[%d]=%d\n", n, type);
+			continue;
+		}
+
+		if (compare_tev_args(ptevs + i, ptevs + i - 1) == 0)
+			mapping[n] = type;
+		else
+			mapping[n] = ++type;
+
+		pr_debug("mapping[%d]=%d\n", n, mapping[n]);
+	}
+	free(ptevs);
+	*nr_types = type + 1;
+
+	return 0;
+}
+
+static int hook_load_preprocessor(struct bpf_program *prog)
+{
+	struct perf_probe_event *pev;
+	struct bpf_prog_priv *priv;
+	bool need_prologue = false;
+	int err, i;
+
+	err = bpf_program__get_private(prog, (void **)&priv);
+	if (err || !priv) {
+		pr_debug("Internal error when hook preprocessor\n");
+		return -BPF_LOADER_ERRNO__INTERNAL;
+	}
+
+	pev = &priv->pev;
+	for (i = 0; i < pev->ntevs; i++) {
+		struct probe_trace_event *tev = &pev->tevs[i];
+
+		if (tev->nargs > 0) {
+			need_prologue = true;
+			break;
+		}
+	}
+
+	/*
+	 * Since all tevs don't have argument, we don't need generate
+	 * prologue.
+	 */
+	if (!need_prologue) {
+		priv->need_prologue = false;
+		return 0;
+	}
+
+	priv->need_prologue = true;
+	priv->insns_buf = malloc(sizeof(struct bpf_insn) * BPF_MAXINSNS);
+	if (!priv->insns_buf) {
+		pr_debug("No enough memory: alloc insns_buf failed\n");
+		return -ENOMEM;
+	}
+
+	priv->type_mapping = malloc(sizeof(int) * pev->ntevs);
+	if (!priv->type_mapping) {
+		pr_debug("No enough memory: alloc type_mapping failed\n");
+		return -ENOMEM;
+	}
+	memset(priv->type_mapping, -1,
+	       sizeof(int) * pev->ntevs);
+
+	err = map_prologue(pev, priv->type_mapping, &priv->nr_types);
+	if (err)
+		return err;
+
+	err = bpf_program__set_prep(prog, priv->nr_types,
+				    preproc_gen_prologue);
+	return err;
+}
+
 int bpf__probe(struct bpf_object *obj)
 {
 	int err = 0;
@@ -231,6 +621,18 @@
 			pr_debug("bpf_probe: failed to apply perf probe events");
 			goto out;
 		}
+
+		/*
+		 * After probing, let's consider prologue, which
+		 * adds program fetcher to BPF programs.
+		 *
+		 * hook_load_preprocessorr() hooks pre-processor
+		 * to bpf_program, let it generate prologue
+		 * dynamically during loading.
+		 */
+		err = hook_load_preprocessor(prog);
+		if (err)
+			goto out;
 	}
 out:
 	return err < 0 ? err : 0;
@@ -314,7 +716,14 @@
 		for (i = 0; i < pev->ntevs; i++) {
 			tev = &pev->tevs[i];
 
-			fd = bpf_program__fd(prog);
+			if (priv->need_prologue) {
+				int type = priv->type_mapping[i];
+
+				fd = bpf_program__nth_fd(prog, type);
+			} else {
+				fd = bpf_program__fd(prog);
+			}
+
 			if (fd < 0) {
 				pr_debug("bpf: failed to get file descriptor\n");
 				return fd;
@@ -340,6 +749,10 @@
 	[ERRCODE_OFFSET(EVENTNAME)]	= "No event name found in config string",
 	[ERRCODE_OFFSET(INTERNAL)]	= "BPF loader internal error",
 	[ERRCODE_OFFSET(COMPILE)]	= "Error when compiling BPF scriptlet",
+	[ERRCODE_OFFSET(PROGCONF_TERM)]	= "Invalid program config term in config string",
+	[ERRCODE_OFFSET(PROLOGUE)]	= "Failed to generate prologue",
+	[ERRCODE_OFFSET(PROLOGUE2BIG)]	= "Prologue too big for program",
+	[ERRCODE_OFFSET(PROLOGUEOOB)]	= "Offset out of bound for prologue",
 };
 
 static int
@@ -420,7 +833,11 @@
 			int err, char *buf, size_t size)
 {
 	bpf__strerror_head(err, buf, size);
-	bpf__strerror_entry(EEXIST, "Probe point exist. Try use 'perf probe -d \"*\"'");
+	case BPF_LOADER_ERRNO__PROGCONF_TERM: {
+		scnprintf(buf, size, "%s (add -v to see detail)", emsg);
+		break;
+	}
+	bpf__strerror_entry(EEXIST, "Probe point exist. Try 'perf probe -d \"*\"' and set 'force=yes'");
 	bpf__strerror_entry(EACCES, "You need to be root");
 	bpf__strerror_entry(EPERM, "You need to be root, and /proc/sys/kernel/kptr_restrict should be 0");
 	bpf__strerror_entry(ENOENT, "You need to check probing points in BPF file");
diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h
index 9caf3ae..6fdc045 100644
--- a/tools/perf/util/bpf-loader.h
+++ b/tools/perf/util/bpf-loader.h
@@ -20,6 +20,10 @@
 	BPF_LOADER_ERRNO__EVENTNAME,	/* Event name is missing */
 	BPF_LOADER_ERRNO__INTERNAL,	/* BPF loader internal error */
 	BPF_LOADER_ERRNO__COMPILE,	/* Error when compiling BPF scriptlet */
+	BPF_LOADER_ERRNO__PROGCONF_TERM,/* Invalid program config term in config string */
+	BPF_LOADER_ERRNO__PROLOGUE,	/* Failed to generate prologue */
+	BPF_LOADER_ERRNO__PROLOGUE2BIG,	/* Prologue too big for program */
+	BPF_LOADER_ERRNO__PROLOGUEOOB,	/* Offset out of bound for prologue */
 	__BPF_LOADER_ERRNO__END,
 };
 
diff --git a/tools/perf/util/bpf-prologue.c b/tools/perf/util/bpf-prologue.c
new file mode 100644
index 0000000..6cdbee1
--- /dev/null
+++ b/tools/perf/util/bpf-prologue.c
@@ -0,0 +1,455 @@
+/*
+ * bpf-prologue.c
+ *
+ * Copyright (C) 2015 He Kuang <hekuang@huawei.com>
+ * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
+ * Copyright (C) 2015 Huawei Inc.
+ */
+
+#include <bpf/libbpf.h>
+#include "perf.h"
+#include "debug.h"
+#include "bpf-loader.h"
+#include "bpf-prologue.h"
+#include "probe-finder.h"
+#include <dwarf-regs.h>
+#include <linux/filter.h>
+
+#define BPF_REG_SIZE		8
+
+#define JMP_TO_ERROR_CODE	-1
+#define JMP_TO_SUCCESS_CODE	-2
+#define JMP_TO_USER_CODE	-3
+
+struct bpf_insn_pos {
+	struct bpf_insn *begin;
+	struct bpf_insn *end;
+	struct bpf_insn *pos;
+};
+
+static inline int
+pos_get_cnt(struct bpf_insn_pos *pos)
+{
+	return pos->pos - pos->begin;
+}
+
+static int
+append_insn(struct bpf_insn new_insn, struct bpf_insn_pos *pos)
+{
+	if (!pos->pos)
+		return -BPF_LOADER_ERRNO__PROLOGUE2BIG;
+
+	if (pos->pos + 1 >= pos->end) {
+		pr_err("bpf prologue: prologue too long\n");
+		pos->pos = NULL;
+		return -BPF_LOADER_ERRNO__PROLOGUE2BIG;
+	}
+
+	*(pos->pos)++ = new_insn;
+	return 0;
+}
+
+static int
+check_pos(struct bpf_insn_pos *pos)
+{
+	if (!pos->pos || pos->pos >= pos->end)
+		return -BPF_LOADER_ERRNO__PROLOGUE2BIG;
+	return 0;
+}
+
+/* Give it a shorter name */
+#define ins(i, p) append_insn((i), (p))
+
+/*
+ * Give a register name (in 'reg'), generate instruction to
+ * load register into an eBPF register rd:
+ *   'ldd target_reg, offset(ctx_reg)', where:
+ * ctx_reg is pre initialized to pointer of 'struct pt_regs'.
+ */
+static int
+gen_ldx_reg_from_ctx(struct bpf_insn_pos *pos, int ctx_reg,
+		     const char *reg, int target_reg)
+{
+	int offset = regs_query_register_offset(reg);
+
+	if (offset < 0) {
+		pr_err("bpf: prologue: failed to get register %s\n",
+		       reg);
+		return offset;
+	}
+	ins(BPF_LDX_MEM(BPF_DW, target_reg, ctx_reg, offset), pos);
+
+	return check_pos(pos);
+}
+
+/*
+ * Generate a BPF_FUNC_probe_read function call.
+ *
+ * src_base_addr_reg is a register holding base address,
+ * dst_addr_reg is a register holding dest address (on stack),
+ * result is:
+ *
+ *  *[dst_addr_reg] = *([src_base_addr_reg] + offset)
+ *
+ * Arguments of BPF_FUNC_probe_read:
+ *     ARG1: ptr to stack (dest)
+ *     ARG2: size (8)
+ *     ARG3: unsafe ptr (src)
+ */
+static int
+gen_read_mem(struct bpf_insn_pos *pos,
+	     int src_base_addr_reg,
+	     int dst_addr_reg,
+	     long offset)
+{
+	/* mov arg3, src_base_addr_reg */
+	if (src_base_addr_reg != BPF_REG_ARG3)
+		ins(BPF_MOV64_REG(BPF_REG_ARG3, src_base_addr_reg), pos);
+	/* add arg3, #offset */
+	if (offset)
+		ins(BPF_ALU64_IMM(BPF_ADD, BPF_REG_ARG3, offset), pos);
+
+	/* mov arg2, #reg_size */
+	ins(BPF_ALU64_IMM(BPF_MOV, BPF_REG_ARG2, BPF_REG_SIZE), pos);
+
+	/* mov arg1, dst_addr_reg */
+	if (dst_addr_reg != BPF_REG_ARG1)
+		ins(BPF_MOV64_REG(BPF_REG_ARG1, dst_addr_reg), pos);
+
+	/* Call probe_read  */
+	ins(BPF_EMIT_CALL(BPF_FUNC_probe_read), pos);
+	/*
+	 * Error processing: if read fail, goto error code,
+	 * will be relocated. Target should be the start of
+	 * error processing code.
+	 */
+	ins(BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, JMP_TO_ERROR_CODE),
+	    pos);
+
+	return check_pos(pos);
+}
+
+/*
+ * Each arg should be bare register. Fetch and save them into argument
+ * registers (r3 - r5).
+ *
+ * BPF_REG_1 should have been initialized with pointer to
+ * 'struct pt_regs'.
+ */
+static int
+gen_prologue_fastpath(struct bpf_insn_pos *pos,
+		      struct probe_trace_arg *args, int nargs)
+{
+	int i, err = 0;
+
+	for (i = 0; i < nargs; i++) {
+		err = gen_ldx_reg_from_ctx(pos, BPF_REG_1, args[i].value,
+					   BPF_PROLOGUE_START_ARG_REG + i);
+		if (err)
+			goto errout;
+	}
+
+	return check_pos(pos);
+errout:
+	return err;
+}
+
+/*
+ * Slow path:
+ *   At least one argument has the form of 'offset($rx)'.
+ *
+ * Following code first stores them into stack, then loads all of then
+ * to r2 - r5.
+ * Before final loading, the final result should be:
+ *
+ * low address
+ * BPF_REG_FP - 24  ARG3
+ * BPF_REG_FP - 16  ARG2
+ * BPF_REG_FP - 8   ARG1
+ * BPF_REG_FP
+ * high address
+ *
+ * For each argument (described as: offn(...off2(off1(reg)))),
+ * generates following code:
+ *
+ *  r7 <- fp
+ *  r7 <- r7 - stack_offset  // Ideal code should initialize r7 using
+ *                           // fp before generating args. However,
+ *                           // eBPF won't regard r7 as stack pointer
+ *                           // if it is generated by minus 8 from
+ *                           // another stack pointer except fp.
+ *                           // This is why we have to set r7
+ *                           // to fp for each variable.
+ *  r3 <- value of 'reg'-> generated using gen_ldx_reg_from_ctx()
+ *  (r7) <- r3       // skip following instructions for bare reg
+ *  r3 <- r3 + off1  . // skip if off1 == 0
+ *  r2 <- 8           \
+ *  r1 <- r7           |-> generated by gen_read_mem()
+ *  call probe_read    /
+ *  jnei r0, 0, err  ./
+ *  r3 <- (r7)
+ *  r3 <- r3 + off2  . // skip if off2 == 0
+ *  r2 <- 8           \  // r2 may be broken by probe_read, so set again
+ *  r1 <- r7           |-> generated by gen_read_mem()
+ *  call probe_read    /
+ *  jnei r0, 0, err  ./
+ *  ...
+ */
+static int
+gen_prologue_slowpath(struct bpf_insn_pos *pos,
+		      struct probe_trace_arg *args, int nargs)
+{
+	int err, i;
+
+	for (i = 0; i < nargs; i++) {
+		struct probe_trace_arg *arg = &args[i];
+		const char *reg = arg->value;
+		struct probe_trace_arg_ref *ref = NULL;
+		int stack_offset = (i + 1) * -8;
+
+		pr_debug("prologue: fetch arg %d, base reg is %s\n",
+			 i, reg);
+
+		/* value of base register is stored into ARG3 */
+		err = gen_ldx_reg_from_ctx(pos, BPF_REG_CTX, reg,
+					   BPF_REG_ARG3);
+		if (err) {
+			pr_err("prologue: failed to get offset of register %s\n",
+			       reg);
+			goto errout;
+		}
+
+		/* Make r7 the stack pointer. */
+		ins(BPF_MOV64_REG(BPF_REG_7, BPF_REG_FP), pos);
+		/* r7 += -8 */
+		ins(BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, stack_offset), pos);
+		/*
+		 * Store r3 (base register) onto stack
+		 * Ensure fp[offset] is set.
+		 * fp is the only valid base register when storing
+		 * into stack. We are not allowed to use r7 as base
+		 * register here.
+		 */
+		ins(BPF_STX_MEM(BPF_DW, BPF_REG_FP, BPF_REG_ARG3,
+				stack_offset), pos);
+
+		ref = arg->ref;
+		while (ref) {
+			pr_debug("prologue: arg %d: offset %ld\n",
+				 i, ref->offset);
+			err = gen_read_mem(pos, BPF_REG_3, BPF_REG_7,
+					   ref->offset);
+			if (err) {
+				pr_err("prologue: failed to generate probe_read function call\n");
+				goto errout;
+			}
+
+			ref = ref->next;
+			/*
+			 * Load previous result into ARG3. Use
+			 * BPF_REG_FP instead of r7 because verifier
+			 * allows FP based addressing only.
+			 */
+			if (ref)
+				ins(BPF_LDX_MEM(BPF_DW, BPF_REG_ARG3,
+						BPF_REG_FP, stack_offset), pos);
+		}
+	}
+
+	/* Final pass: read to registers */
+	for (i = 0; i < nargs; i++)
+		ins(BPF_LDX_MEM(BPF_DW, BPF_PROLOGUE_START_ARG_REG + i,
+				BPF_REG_FP, -BPF_REG_SIZE * (i + 1)), pos);
+
+	ins(BPF_JMP_IMM(BPF_JA, BPF_REG_0, 0, JMP_TO_SUCCESS_CODE), pos);
+
+	return check_pos(pos);
+errout:
+	return err;
+}
+
+static int
+prologue_relocate(struct bpf_insn_pos *pos, struct bpf_insn *error_code,
+		  struct bpf_insn *success_code, struct bpf_insn *user_code)
+{
+	struct bpf_insn *insn;
+
+	if (check_pos(pos))
+		return -BPF_LOADER_ERRNO__PROLOGUE2BIG;
+
+	for (insn = pos->begin; insn < pos->pos; insn++) {
+		struct bpf_insn *target;
+		u8 class = BPF_CLASS(insn->code);
+		u8 opcode;
+
+		if (class != BPF_JMP)
+			continue;
+		opcode = BPF_OP(insn->code);
+		if (opcode == BPF_CALL)
+			continue;
+
+		switch (insn->off) {
+		case JMP_TO_ERROR_CODE:
+			target = error_code;
+			break;
+		case JMP_TO_SUCCESS_CODE:
+			target = success_code;
+			break;
+		case JMP_TO_USER_CODE:
+			target = user_code;
+			break;
+		default:
+			pr_err("bpf prologue: internal error: relocation failed\n");
+			return -BPF_LOADER_ERRNO__PROLOGUE;
+		}
+
+		insn->off = target - (insn + 1);
+	}
+	return 0;
+}
+
+int bpf__gen_prologue(struct probe_trace_arg *args, int nargs,
+		      struct bpf_insn *new_prog, size_t *new_cnt,
+		      size_t cnt_space)
+{
+	struct bpf_insn *success_code = NULL;
+	struct bpf_insn *error_code = NULL;
+	struct bpf_insn *user_code = NULL;
+	struct bpf_insn_pos pos;
+	bool fastpath = true;
+	int err = 0, i;
+
+	if (!new_prog || !new_cnt)
+		return -EINVAL;
+
+	if (cnt_space > BPF_MAXINSNS)
+		cnt_space = BPF_MAXINSNS;
+
+	pos.begin = new_prog;
+	pos.end = new_prog + cnt_space;
+	pos.pos = new_prog;
+
+	if (!nargs) {
+		ins(BPF_ALU64_IMM(BPF_MOV, BPF_PROLOGUE_FETCH_RESULT_REG, 0),
+		    &pos);
+
+		if (check_pos(&pos))
+			goto errout;
+
+		*new_cnt = pos_get_cnt(&pos);
+		return 0;
+	}
+
+	if (nargs > BPF_PROLOGUE_MAX_ARGS) {
+		pr_warning("bpf: prologue: %d arguments are dropped\n",
+			   nargs - BPF_PROLOGUE_MAX_ARGS);
+		nargs = BPF_PROLOGUE_MAX_ARGS;
+	}
+
+	/* First pass: validation */
+	for (i = 0; i < nargs; i++) {
+		struct probe_trace_arg_ref *ref = args[i].ref;
+
+		if (args[i].value[0] == '@') {
+			/* TODO: fetch global variable */
+			pr_err("bpf: prologue: global %s%+ld not support\n",
+				args[i].value, ref ? ref->offset : 0);
+			return -ENOTSUP;
+		}
+
+		while (ref) {
+			/* fastpath is true if all args has ref == NULL */
+			fastpath = false;
+
+			/*
+			 * Instruction encodes immediate value using
+			 * s32, ref->offset is long. On systems which
+			 * can't fill long in s32, refuse to process if
+			 * ref->offset too large (or small).
+			 */
+#ifdef __LP64__
+#define OFFSET_MAX	((1LL << 31) - 1)
+#define OFFSET_MIN	((1LL << 31) * -1)
+			if (ref->offset > OFFSET_MAX ||
+					ref->offset < OFFSET_MIN) {
+				pr_err("bpf: prologue: offset out of bound: %ld\n",
+				       ref->offset);
+				return -BPF_LOADER_ERRNO__PROLOGUEOOB;
+			}
+#endif
+			ref = ref->next;
+		}
+	}
+	pr_debug("prologue: pass validation\n");
+
+	if (fastpath) {
+		/* If all variables are registers... */
+		pr_debug("prologue: fast path\n");
+		err = gen_prologue_fastpath(&pos, args, nargs);
+		if (err)
+			goto errout;
+	} else {
+		pr_debug("prologue: slow path\n");
+
+		/* Initialization: move ctx to a callee saved register. */
+		ins(BPF_MOV64_REG(BPF_REG_CTX, BPF_REG_ARG1), &pos);
+
+		err = gen_prologue_slowpath(&pos, args, nargs);
+		if (err)
+			goto errout;
+		/*
+		 * start of ERROR_CODE (only slow pass needs error code)
+		 *   mov r2 <- 1  // r2 is error number
+		 *   mov r3 <- 0  // r3, r4... should be touched or
+		 *                // verifier would complain
+		 *   mov r4 <- 0
+		 *   ...
+		 *   goto usercode
+		 */
+		error_code = pos.pos;
+		ins(BPF_ALU64_IMM(BPF_MOV, BPF_PROLOGUE_FETCH_RESULT_REG, 1),
+		    &pos);
+
+		for (i = 0; i < nargs; i++)
+			ins(BPF_ALU64_IMM(BPF_MOV,
+					  BPF_PROLOGUE_START_ARG_REG + i,
+					  0),
+			    &pos);
+		ins(BPF_JMP_IMM(BPF_JA, BPF_REG_0, 0, JMP_TO_USER_CODE),
+				&pos);
+	}
+
+	/*
+	 * start of SUCCESS_CODE:
+	 *   mov r2 <- 0
+	 *   goto usercode  // skip
+	 */
+	success_code = pos.pos;
+	ins(BPF_ALU64_IMM(BPF_MOV, BPF_PROLOGUE_FETCH_RESULT_REG, 0), &pos);
+
+	/*
+	 * start of USER_CODE:
+	 *   Restore ctx to r1
+	 */
+	user_code = pos.pos;
+	if (!fastpath) {
+		/*
+		 * Only slow path needs restoring of ctx. In fast path,
+		 * register are loaded directly from r1.
+		 */
+		ins(BPF_MOV64_REG(BPF_REG_ARG1, BPF_REG_CTX), &pos);
+		err = prologue_relocate(&pos, error_code, success_code,
+					user_code);
+		if (err)
+			goto errout;
+	}
+
+	err = check_pos(&pos);
+	if (err)
+		goto errout;
+
+	*new_cnt = pos_get_cnt(&pos);
+	return 0;
+errout:
+	return err;
+}
diff --git a/tools/perf/util/bpf-prologue.h b/tools/perf/util/bpf-prologue.h
new file mode 100644
index 0000000..d94cbea
--- /dev/null
+++ b/tools/perf/util/bpf-prologue.h
@@ -0,0 +1,34 @@
+/*
+ * Copyright (C) 2015, He Kuang <hekuang@huawei.com>
+ * Copyright (C) 2015, Huawei Inc.
+ */
+#ifndef __BPF_PROLOGUE_H
+#define __BPF_PROLOGUE_H
+
+#include <linux/compiler.h>
+#include <linux/filter.h>
+#include "probe-event.h"
+
+#define BPF_PROLOGUE_MAX_ARGS 3
+#define BPF_PROLOGUE_START_ARG_REG BPF_REG_3
+#define BPF_PROLOGUE_FETCH_RESULT_REG BPF_REG_2
+
+#ifdef HAVE_BPF_PROLOGUE
+int bpf__gen_prologue(struct probe_trace_arg *args, int nargs,
+		      struct bpf_insn *new_prog, size_t *new_cnt,
+		      size_t cnt_space);
+#else
+static inline int
+bpf__gen_prologue(struct probe_trace_arg *args __maybe_unused,
+		  int nargs __maybe_unused,
+		  struct bpf_insn *new_prog __maybe_unused,
+		  size_t *new_cnt,
+		  size_t cnt_space __maybe_unused)
+{
+	if (!new_cnt)
+		return -EINVAL;
+	*new_cnt = 0;
+	return -ENOTSUP;
+}
+#endif
+#endif /* __BPF_PROLOGUE_H */
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 217b5a6..6a7e273 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -91,7 +91,7 @@
 		bid += 2;
 	}
 
-	return raw - build_id;
+	return (bid - bf) + 1;
 }
 
 int sysfs__sprintf_build_id(const char *root_dir, char *sbuild_id)
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index c861373..07b5d63 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -4,9 +4,12 @@
 #include <stdbool.h>
 #include "util.h"
 #include "strbuf.h"
+#include <subcmd/pager.h>
 #include "../perf.h"
 #include "../ui/ui.h"
 
+#include <linux/string.h>
+
 #define CMD_EXEC_PATH "--exec-path"
 #define CMD_PERF_DIR "--perf-dir="
 #define CMD_WORK_TREE "--work-tree="
@@ -18,6 +21,7 @@
 #define DEFAULT_PERF_DIR_ENVIRONMENT ".perf"
 #define PERF_DEBUGFS_ENVIRONMENT "PERF_DEBUGFS_DIR"
 #define PERF_TRACEFS_ENVIRONMENT "PERF_TRACEFS_DIR"
+#define PERF_PAGER_ENVIRONMENT "PERF_PAGER"
 
 typedef int (*config_fn_t)(const char *, const char *, void *);
 extern int perf_default_config(const char *, const char *, void *);
@@ -28,11 +32,6 @@
 extern int config_error_nonbool(const char *);
 extern const char *perf_config_dirname(const char *, const char *);
 
-/* pager.c */
-extern void setup_pager(void);
-extern int pager_in_use(void);
-extern int pager_use_color;
-
 char *alias_lookup(const char *alias);
 int split_cmdline(char *cmdline, const char ***argv);
 
@@ -71,9 +70,4 @@
 extern char *perf_pathdup(const char *fmt, ...)
 	__attribute__((format (printf, 1, 2)));
 
-#ifndef __UCLIBC__
-/* Matches the libc/libbsd function attribute so we declare this unconditionally: */
-extern size_t strlcpy(char *dest, const char *src, size_t size);
-#endif
-
 #endif /* __PERF_CACHE_H */
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 735ad48..53c43eb 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -44,6 +44,10 @@
 		callchain_param.mode = CHAIN_GRAPH_REL;
 		return 0;
 	}
+	if (!strncmp(value, "folded", strlen(value))) {
+		callchain_param.mode = CHAIN_FOLDED;
+		return 0;
+	}
 	return -1;
 }
 
@@ -79,6 +83,23 @@
 	return -1;
 }
 
+static int parse_callchain_value(const char *value)
+{
+	if (!strncmp(value, "percent", strlen(value))) {
+		callchain_param.value = CCVAL_PERCENT;
+		return 0;
+	}
+	if (!strncmp(value, "period", strlen(value))) {
+		callchain_param.value = CCVAL_PERIOD;
+		return 0;
+	}
+	if (!strncmp(value, "count", strlen(value))) {
+		callchain_param.value = CCVAL_COUNT;
+		return 0;
+	}
+	return -1;
+}
+
 static int
 __parse_callchain_report_opt(const char *arg, bool allow_record_opt)
 {
@@ -102,7 +123,8 @@
 
 		if (!parse_callchain_mode(tok) ||
 		    !parse_callchain_order(tok) ||
-		    !parse_callchain_sort_key(tok)) {
+		    !parse_callchain_sort_key(tok) ||
+		    !parse_callchain_value(tok)) {
 			/* parsing ok - move on to the next */
 			try_stack_size = false;
 			goto next;
@@ -218,6 +240,7 @@
 
 		switch (mode) {
 		case CHAIN_FLAT:
+		case CHAIN_FOLDED:
 			if (rnode->hit < chain->hit)
 				p = &(*p)->rb_left;
 			else
@@ -267,6 +290,7 @@
 sort_chain_flat(struct rb_root *rb_root, struct callchain_root *root,
 		u64 min_hit, struct callchain_param *param __maybe_unused)
 {
+	*rb_root = RB_ROOT;
 	__sort_chain_flat(rb_root, &root->node, min_hit);
 }
 
@@ -338,6 +362,7 @@
 		param->sort = sort_chain_graph_rel;
 		break;
 	case CHAIN_FLAT:
+	case CHAIN_FOLDED:
 		param->sort = sort_chain_flat;
 		break;
 	case CHAIN_NONE:
@@ -363,6 +388,7 @@
 	}
 	new->parent = parent;
 	INIT_LIST_HEAD(&new->val);
+	INIT_LIST_HEAD(&new->parent_val);
 
 	if (inherit_children) {
 		struct rb_node *n;
@@ -431,6 +457,8 @@
 
 	new->children_hit = 0;
 	new->hit = period;
+	new->children_count = 0;
+	new->count = 1;
 	return new;
 }
 
@@ -478,6 +506,9 @@
 	parent->children_hit = callchain_cumul_hits(new);
 	new->val_nr = parent->val_nr - idx_local;
 	parent->val_nr = idx_local;
+	new->count = parent->count;
+	new->children_count = parent->children_count;
+	parent->children_count = callchain_cumul_counts(new);
 
 	/* create a new child for the new branch if any */
 	if (idx_total < cursor->nr) {
@@ -488,6 +519,8 @@
 
 		parent->hit = 0;
 		parent->children_hit += period;
+		parent->count = 0;
+		parent->children_count += 1;
 
 		node = callchain_cursor_current(cursor);
 		new = add_child(parent, cursor, period);
@@ -510,6 +543,7 @@
 		rb_insert_color(&new->rb_node_in, &parent->rb_root_in);
 	} else {
 		parent->hit = period;
+		parent->count = 1;
 	}
 }
 
@@ -556,6 +590,7 @@
 
 inc_children_hit:
 	root->children_hit += period;
+	root->children_count++;
 }
 
 static int
@@ -608,6 +643,7 @@
 	/* we match 100% of the path, increment the hit */
 	if (matches == root->val_nr && cursor->pos == cursor->nr) {
 		root->hit += period;
+		root->count++;
 		return 0;
 	}
 
@@ -799,12 +835,72 @@
 	return bf;
 }
 
+char *callchain_node__scnprintf_value(struct callchain_node *node,
+				      char *bf, size_t bfsize, u64 total)
+{
+	double percent = 0.0;
+	u64 period = callchain_cumul_hits(node);
+	unsigned count = callchain_cumul_counts(node);
+
+	if (callchain_param.mode == CHAIN_FOLDED) {
+		period = node->hit;
+		count = node->count;
+	}
+
+	switch (callchain_param.value) {
+	case CCVAL_PERIOD:
+		scnprintf(bf, bfsize, "%"PRIu64, period);
+		break;
+	case CCVAL_COUNT:
+		scnprintf(bf, bfsize, "%u", count);
+		break;
+	case CCVAL_PERCENT:
+	default:
+		if (total)
+			percent = period * 100.0 / total;
+		scnprintf(bf, bfsize, "%.2f%%", percent);
+		break;
+	}
+	return bf;
+}
+
+int callchain_node__fprintf_value(struct callchain_node *node,
+				 FILE *fp, u64 total)
+{
+	double percent = 0.0;
+	u64 period = callchain_cumul_hits(node);
+	unsigned count = callchain_cumul_counts(node);
+
+	if (callchain_param.mode == CHAIN_FOLDED) {
+		period = node->hit;
+		count = node->count;
+	}
+
+	switch (callchain_param.value) {
+	case CCVAL_PERIOD:
+		return fprintf(fp, "%"PRIu64, period);
+	case CCVAL_COUNT:
+		return fprintf(fp, "%u", count);
+	case CCVAL_PERCENT:
+	default:
+		if (total)
+			percent = period * 100.0 / total;
+		return percent_color_fprintf(fp, "%.2f%%", percent);
+	}
+	return 0;
+}
+
 static void free_callchain_node(struct callchain_node *node)
 {
 	struct callchain_list *list, *tmp;
 	struct callchain_node *child;
 	struct rb_node *n;
 
+	list_for_each_entry_safe(list, tmp, &node->parent_val, list) {
+		list_del(&list->list);
+		free(list);
+	}
+
 	list_for_each_entry_safe(list, tmp, &node->val, list) {
 		list_del(&list->list);
 		free(list);
@@ -828,3 +924,69 @@
 
 	free_callchain_node(&root->node);
 }
+
+static u64 decay_callchain_node(struct callchain_node *node)
+{
+	struct callchain_node *child;
+	struct rb_node *n;
+	u64 child_hits = 0;
+
+	n = rb_first(&node->rb_root_in);
+	while (n) {
+		child = container_of(n, struct callchain_node, rb_node_in);
+
+		child_hits += decay_callchain_node(child);
+		n = rb_next(n);
+	}
+
+	node->hit = (node->hit * 7) / 8;
+	node->children_hit = child_hits;
+
+	return node->hit;
+}
+
+void decay_callchain(struct callchain_root *root)
+{
+	if (!symbol_conf.use_callchain)
+		return;
+
+	decay_callchain_node(&root->node);
+}
+
+int callchain_node__make_parent_list(struct callchain_node *node)
+{
+	struct callchain_node *parent = node->parent;
+	struct callchain_list *chain, *new;
+	LIST_HEAD(head);
+
+	while (parent) {
+		list_for_each_entry_reverse(chain, &parent->val, list) {
+			new = malloc(sizeof(*new));
+			if (new == NULL)
+				goto out;
+			*new = *chain;
+			new->has_children = false;
+			list_add_tail(&new->list, &head);
+		}
+		parent = parent->parent;
+	}
+
+	list_for_each_entry_safe_reverse(chain, new, &head, list)
+		list_move_tail(&chain->list, &node->parent_val);
+
+	if (!list_empty(&node->parent_val)) {
+		chain = list_first_entry(&node->parent_val, struct callchain_list, list);
+		chain->has_children = rb_prev(&node->rb_node) || rb_next(&node->rb_node);
+
+		chain = list_first_entry(&node->val, struct callchain_list, list);
+		chain->has_children = false;
+	}
+	return 0;
+
+out:
+	list_for_each_entry_safe(chain, new, &head, list) {
+		list_del(&chain->list);
+		free(chain);
+	}
+	return -ENOMEM;
+}
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index fce8161..18dd222 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -24,12 +24,13 @@
 #define CALLCHAIN_RECORD_HELP  CALLCHAIN_HELP RECORD_MODE_HELP RECORD_SIZE_HELP
 
 #define CALLCHAIN_REPORT_HELP						\
-	HELP_PAD "print_type:\tcall graph printing style (graph|flat|fractal|none)\n" \
+	HELP_PAD "print_type:\tcall graph printing style (graph|flat|fractal|folded|none)\n" \
 	HELP_PAD "threshold:\tminimum call graph inclusion threshold (<percent>)\n" \
 	HELP_PAD "print_limit:\tmaximum number of call graph entry (<number>)\n" \
 	HELP_PAD "order:\t\tcall graph order (caller|callee)\n" \
 	HELP_PAD "sort_key:\tcall graph sort key (function|address)\n"	\
-	HELP_PAD "branch:\t\tinclude last branch info to call graph (branch)\n"
+	HELP_PAD "branch:\t\tinclude last branch info to call graph (branch)\n" \
+	HELP_PAD "value:\t\tcall graph value (percent|period|count)\n"
 
 enum perf_call_graph_mode {
 	CALLCHAIN_NONE,
@@ -43,7 +44,8 @@
 	CHAIN_NONE,
 	CHAIN_FLAT,
 	CHAIN_GRAPH_ABS,
-	CHAIN_GRAPH_REL
+	CHAIN_GRAPH_REL,
+	CHAIN_FOLDED,
 };
 
 enum chain_order {
@@ -54,11 +56,14 @@
 struct callchain_node {
 	struct callchain_node	*parent;
 	struct list_head	val;
+	struct list_head	parent_val;
 	struct rb_node		rb_node_in; /* to insert nodes in an rbtree */
 	struct rb_node		rb_node;    /* to sort nodes in an output tree */
 	struct rb_root		rb_root_in; /* input tree of children */
 	struct rb_root		rb_root;    /* sorted output tree of children */
 	unsigned int		val_nr;
+	unsigned int		count;
+	unsigned int		children_count;
 	u64			hit;
 	u64			children_hit;
 };
@@ -78,6 +83,12 @@
 	CCKEY_ADDRESS
 };
 
+enum chain_value {
+	CCVAL_PERCENT,
+	CCVAL_PERIOD,
+	CCVAL_COUNT,
+};
+
 struct callchain_param {
 	bool			enabled;
 	enum perf_call_graph_mode record_mode;
@@ -90,6 +101,7 @@
 	bool			order_set;
 	enum chain_key		key;
 	bool			branch_callstack;
+	enum chain_value	value;
 };
 
 extern struct callchain_param callchain_param;
@@ -131,6 +143,7 @@
 static inline void callchain_init(struct callchain_root *root)
 {
 	INIT_LIST_HEAD(&root->node.val);
+	INIT_LIST_HEAD(&root->node.parent_val);
 
 	root->node.parent = NULL;
 	root->node.hit = 0;
@@ -144,6 +157,11 @@
 	return node->hit + node->children_hit;
 }
 
+static inline unsigned callchain_cumul_counts(struct callchain_node *node)
+{
+	return node->count + node->children_count;
+}
+
 int callchain_register_param(struct callchain_param *param);
 int callchain_append(struct callchain_root *root,
 		     struct callchain_cursor *cursor,
@@ -229,7 +247,13 @@
 
 char *callchain_list__sym_name(struct callchain_list *cl,
 			       char *bf, size_t bfsize, bool show_dso);
+char *callchain_node__scnprintf_value(struct callchain_node *node,
+				      char *bf, size_t bfsize, u64 total);
+int callchain_node__fprintf_value(struct callchain_node *node,
+				  FILE *fp, u64 total);
 
 void free_callchain(struct callchain_root *root);
+void decay_callchain(struct callchain_root *root);
+int callchain_node__make_parent_list(struct callchain_node *node);
 
 #endif	/* __PERF_CALLCHAIN_H */
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 32e12ecf..90aa1b4 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -1,6 +1,6 @@
 #include "util.h"
 #include "../perf.h"
-#include "parse-options.h"
+#include <subcmd/parse-options.h>
 #include "evsel.h"
 #include "cgroup.h"
 #include "evlist.h"
diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c
index 9b95654..e5fb88b 100644
--- a/tools/perf/util/color.c
+++ b/tools/perf/util/color.c
@@ -24,7 +24,7 @@
  auto_color:
 	if (stdout_is_tty < 0)
 		stdout_is_tty = isatty(1);
-	if (stdout_is_tty || (pager_in_use() && pager_use_color)) {
+	if (stdout_is_tty || pager_in_use()) {
 		char *term = getenv("TERM");
 		if (term && strcmp(term, "dumb"))
 			return 1;
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 2e452ac1..d3e12e3 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -10,7 +10,7 @@
  */
 #include "util.h"
 #include "cache.h"
-#include "exec_cmd.h"
+#include <subcmd/exec-cmd.h>
 #include "util/hist.h"  /* perf_hist_config */
 #include "util/llvm-utils.h"   /* perf_llvm_config */
 
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 10af1e7..fa93509 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -5,6 +5,7 @@
 #include <assert.h>
 #include <stdio.h>
 #include <stdlib.h>
+#include <linux/bitmap.h>
 #include "asm/bug.h"
 
 static struct cpu_map *cpu_map__default_new(void)
@@ -179,6 +180,56 @@
 	return cpus;
 }
 
+static struct cpu_map *cpu_map__from_entries(struct cpu_map_entries *cpus)
+{
+	struct cpu_map *map;
+
+	map = cpu_map__empty_new(cpus->nr);
+	if (map) {
+		unsigned i;
+
+		for (i = 0; i < cpus->nr; i++) {
+			/*
+			 * Special treatment for -1, which is not real cpu number,
+			 * and we need to use (int) -1 to initialize map[i],
+			 * otherwise it would become 65535.
+			 */
+			if (cpus->cpu[i] == (u16) -1)
+				map->map[i] = -1;
+			else
+				map->map[i] = (int) cpus->cpu[i];
+		}
+	}
+
+	return map;
+}
+
+static struct cpu_map *cpu_map__from_mask(struct cpu_map_mask *mask)
+{
+	struct cpu_map *map;
+	int nr, nbits = mask->nr * mask->long_size * BITS_PER_BYTE;
+
+	nr = bitmap_weight(mask->mask, nbits);
+
+	map = cpu_map__empty_new(nr);
+	if (map) {
+		int cpu, i = 0;
+
+		for_each_set_bit(cpu, mask->mask, nbits)
+			map->map[i++] = cpu;
+	}
+	return map;
+
+}
+
+struct cpu_map *cpu_map__new_data(struct cpu_map_data *data)
+{
+	if (data->type == PERF_CPU_MAP__CPUS)
+		return cpu_map__from_entries((struct cpu_map_entries *)data->data);
+	else
+		return cpu_map__from_mask((struct cpu_map_mask *)data->data);
+}
+
 size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp)
 {
 	int i;
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 85f7772..71c41b9 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -17,6 +17,7 @@
 struct cpu_map *cpu_map__new(const char *cpu_list);
 struct cpu_map *cpu_map__empty_new(int nr);
 struct cpu_map *cpu_map__dummy_new(void);
+struct cpu_map *cpu_map__new_data(struct cpu_map_data *data);
 struct cpu_map *cpu_map__read(FILE *file);
 size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp);
 int cpu_map__get_socket_id(int cpu);
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index 5bfc119..34cd1e4 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -63,6 +63,7 @@
 			struct bt_ctf_field_type	*s32;
 			struct bt_ctf_field_type	*u32;
 			struct bt_ctf_field_type	*string;
+			struct bt_ctf_field_type	*u32_hex;
 			struct bt_ctf_field_type	*u64_hex;
 		};
 		struct bt_ctf_field_type *array[6];
@@ -982,6 +983,7 @@
 	CREATE_INT_TYPE(cw->data.u64, 64, false, false);
 	CREATE_INT_TYPE(cw->data.s32, 32, true,  false);
 	CREATE_INT_TYPE(cw->data.u32, 32, false, false);
+	CREATE_INT_TYPE(cw->data.u32_hex, 32, false, true);
 	CREATE_INT_TYPE(cw->data.u64_hex, 64, false, true);
 
 	cw->data.string  = bt_ctf_field_type_string_create();
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 425df5c8..e8e9a9d 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -1243,6 +1243,8 @@
 	if (dso != NULL) {
 		__dsos__add(dsos, dso);
 		dso__set_basename(dso);
+		/* Put dso here because __dsos_add already got it */
+		dso__put(dso);
 	}
 	return dso;
 }
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 6af4f7c..7dd5939 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -25,15 +25,6 @@
 {
 	int i;
 
-	/*
-	 * If env->cmdline_argv has already been set, do not override it.  This allows
-	 * a command to set the cmdline, parse args and then call another
-	 * builtin function that implements a command -- e.g, cmd_kvm calling
-	 * cmd_record.
-	 */
-	if (env->cmdline_argv != NULL)
-		return 0;
-
 	/* do not include NULL termination */
 	env->cmdline_argv = calloc(argc, sizeof(char *));
 	if (env->cmdline_argv == NULL)
diff --git a/tools/perf/util/environment.c b/tools/perf/util/environment.c
deleted file mode 100644
index 7405123..0000000
--- a/tools/perf/util/environment.c
+++ /dev/null
@@ -1,8 +0,0 @@
-/*
- * We put all the perf config variables in this same object
- * file, so that programs can link against the config parser
- * without having to link against all the rest of perf.
- */
-#include "cache.h"
-
-int pager_use_color = 1;
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 8b10621..cd61bb1 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -10,6 +10,8 @@
 #include "thread.h"
 #include "thread_map.h"
 #include "symbol/kallsyms.h"
+#include "asm/bug.h"
+#include "stat.h"
 
 static const char *perf_event__names[] = {
 	[0]					= "TOTAL",
@@ -37,6 +39,12 @@
 	[PERF_RECORD_AUXTRACE_INFO]		= "AUXTRACE_INFO",
 	[PERF_RECORD_AUXTRACE]			= "AUXTRACE",
 	[PERF_RECORD_AUXTRACE_ERROR]		= "AUXTRACE_ERROR",
+	[PERF_RECORD_THREAD_MAP]		= "THREAD_MAP",
+	[PERF_RECORD_CPU_MAP]			= "CPU_MAP",
+	[PERF_RECORD_STAT_CONFIG]		= "STAT_CONFIG",
+	[PERF_RECORD_STAT]			= "STAT",
+	[PERF_RECORD_STAT_ROUND]		= "STAT_ROUND",
+	[PERF_RECORD_EVENT_UPDATE]		= "EVENT_UPDATE",
 };
 
 const char *perf_event__name(unsigned int id)
@@ -699,6 +707,274 @@
 	return err;
 }
 
+int perf_event__synthesize_thread_map2(struct perf_tool *tool,
+				      struct thread_map *threads,
+				      perf_event__handler_t process,
+				      struct machine *machine)
+{
+	union perf_event *event;
+	int i, err, size;
+
+	size  = sizeof(event->thread_map);
+	size +=	threads->nr * sizeof(event->thread_map.entries[0]);
+
+	event = zalloc(size);
+	if (!event)
+		return -ENOMEM;
+
+	event->header.type = PERF_RECORD_THREAD_MAP;
+	event->header.size = size;
+	event->thread_map.nr = threads->nr;
+
+	for (i = 0; i < threads->nr; i++) {
+		struct thread_map_event_entry *entry = &event->thread_map.entries[i];
+		char *comm = thread_map__comm(threads, i);
+
+		if (!comm)
+			comm = (char *) "";
+
+		entry->pid = thread_map__pid(threads, i);
+		strncpy((char *) &entry->comm, comm, sizeof(entry->comm));
+	}
+
+	err = process(tool, event, NULL, machine);
+
+	free(event);
+	return err;
+}
+
+static void synthesize_cpus(struct cpu_map_entries *cpus,
+			    struct cpu_map *map)
+{
+	int i;
+
+	cpus->nr = map->nr;
+
+	for (i = 0; i < map->nr; i++)
+		cpus->cpu[i] = map->map[i];
+}
+
+static void synthesize_mask(struct cpu_map_mask *mask,
+			    struct cpu_map *map, int max)
+{
+	int i;
+
+	mask->nr = BITS_TO_LONGS(max);
+	mask->long_size = sizeof(long);
+
+	for (i = 0; i < map->nr; i++)
+		set_bit(map->map[i], mask->mask);
+}
+
+static size_t cpus_size(struct cpu_map *map)
+{
+	return sizeof(struct cpu_map_entries) + map->nr * sizeof(u16);
+}
+
+static size_t mask_size(struct cpu_map *map, int *max)
+{
+	int i;
+
+	*max = 0;
+
+	for (i = 0; i < map->nr; i++) {
+		/* bit possition of the cpu is + 1 */
+		int bit = map->map[i] + 1;
+
+		if (bit > *max)
+			*max = bit;
+	}
+
+	return sizeof(struct cpu_map_mask) + BITS_TO_LONGS(*max) * sizeof(long);
+}
+
+void *cpu_map_data__alloc(struct cpu_map *map, size_t *size, u16 *type, int *max)
+{
+	size_t size_cpus, size_mask;
+	bool is_dummy = cpu_map__empty(map);
+
+	/*
+	 * Both array and mask data have variable size based
+	 * on the number of cpus and their actual values.
+	 * The size of the 'struct cpu_map_data' is:
+	 *
+	 *   array = size of 'struct cpu_map_entries' +
+	 *           number of cpus * sizeof(u64)
+	 *
+	 *   mask  = size of 'struct cpu_map_mask' +
+	 *           maximum cpu bit converted to size of longs
+	 *
+	 * and finaly + the size of 'struct cpu_map_data'.
+	 */
+	size_cpus = cpus_size(map);
+	size_mask = mask_size(map, max);
+
+	if (is_dummy || (size_cpus < size_mask)) {
+		*size += size_cpus;
+		*type  = PERF_CPU_MAP__CPUS;
+	} else {
+		*size += size_mask;
+		*type  = PERF_CPU_MAP__MASK;
+	}
+
+	*size += sizeof(struct cpu_map_data);
+	return zalloc(*size);
+}
+
+void cpu_map_data__synthesize(struct cpu_map_data *data, struct cpu_map *map,
+			      u16 type, int max)
+{
+	data->type = type;
+
+	switch (type) {
+	case PERF_CPU_MAP__CPUS:
+		synthesize_cpus((struct cpu_map_entries *) data->data, map);
+		break;
+	case PERF_CPU_MAP__MASK:
+		synthesize_mask((struct cpu_map_mask *) data->data, map, max);
+	default:
+		break;
+	};
+}
+
+static struct cpu_map_event* cpu_map_event__new(struct cpu_map *map)
+{
+	size_t size = sizeof(struct cpu_map_event);
+	struct cpu_map_event *event;
+	int max;
+	u16 type;
+
+	event = cpu_map_data__alloc(map, &size, &type, &max);
+	if (!event)
+		return NULL;
+
+	event->header.type = PERF_RECORD_CPU_MAP;
+	event->header.size = size;
+	event->data.type   = type;
+
+	cpu_map_data__synthesize(&event->data, map, type, max);
+	return event;
+}
+
+int perf_event__synthesize_cpu_map(struct perf_tool *tool,
+				   struct cpu_map *map,
+				   perf_event__handler_t process,
+				   struct machine *machine)
+{
+	struct cpu_map_event *event;
+	int err;
+
+	event = cpu_map_event__new(map);
+	if (!event)
+		return -ENOMEM;
+
+	err = process(tool, (union perf_event *) event, NULL, machine);
+
+	free(event);
+	return err;
+}
+
+int perf_event__synthesize_stat_config(struct perf_tool *tool,
+				       struct perf_stat_config *config,
+				       perf_event__handler_t process,
+				       struct machine *machine)
+{
+	struct stat_config_event *event;
+	int size, i = 0, err;
+
+	size  = sizeof(*event);
+	size += (PERF_STAT_CONFIG_TERM__MAX * sizeof(event->data[0]));
+
+	event = zalloc(size);
+	if (!event)
+		return -ENOMEM;
+
+	event->header.type = PERF_RECORD_STAT_CONFIG;
+	event->header.size = size;
+	event->nr          = PERF_STAT_CONFIG_TERM__MAX;
+
+#define ADD(__term, __val)					\
+	event->data[i].tag = PERF_STAT_CONFIG_TERM__##__term;	\
+	event->data[i].val = __val;				\
+	i++;
+
+	ADD(AGGR_MODE,	config->aggr_mode)
+	ADD(INTERVAL,	config->interval)
+	ADD(SCALE,	config->scale)
+
+	WARN_ONCE(i != PERF_STAT_CONFIG_TERM__MAX,
+		  "stat config terms unbalanced\n");
+#undef ADD
+
+	err = process(tool, (union perf_event *) event, NULL, machine);
+
+	free(event);
+	return err;
+}
+
+int perf_event__synthesize_stat(struct perf_tool *tool,
+				u32 cpu, u32 thread, u64 id,
+				struct perf_counts_values *count,
+				perf_event__handler_t process,
+				struct machine *machine)
+{
+	struct stat_event event;
+
+	event.header.type = PERF_RECORD_STAT;
+	event.header.size = sizeof(event);
+	event.header.misc = 0;
+
+	event.id        = id;
+	event.cpu       = cpu;
+	event.thread    = thread;
+	event.val       = count->val;
+	event.ena       = count->ena;
+	event.run       = count->run;
+
+	return process(tool, (union perf_event *) &event, NULL, machine);
+}
+
+int perf_event__synthesize_stat_round(struct perf_tool *tool,
+				      u64 evtime, u64 type,
+				      perf_event__handler_t process,
+				      struct machine *machine)
+{
+	struct stat_round_event event;
+
+	event.header.type = PERF_RECORD_STAT_ROUND;
+	event.header.size = sizeof(event);
+	event.header.misc = 0;
+
+	event.time = evtime;
+	event.type = type;
+
+	return process(tool, (union perf_event *) &event, NULL, machine);
+}
+
+void perf_event__read_stat_config(struct perf_stat_config *config,
+				  struct stat_config_event *event)
+{
+	unsigned i;
+
+	for (i = 0; i < event->nr; i++) {
+
+		switch (event->data[i].tag) {
+#define CASE(__term, __val)					\
+		case PERF_STAT_CONFIG_TERM__##__term:		\
+			config->__val = event->data[i].val;	\
+			break;
+
+		CASE(AGGR_MODE, aggr_mode)
+		CASE(SCALE,     scale)
+		CASE(INTERVAL,  interval)
+#undef CASE
+		default:
+			pr_warning("unknown stat config term %" PRIu64 "\n",
+				   event->data[i].tag);
+		}
+	}
+}
+
 size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp)
 {
 	const char *s;
@@ -783,6 +1059,38 @@
 		       event->mmap2.filename);
 }
 
+size_t perf_event__fprintf_thread_map(union perf_event *event, FILE *fp)
+{
+	struct thread_map *threads = thread_map__new_event(&event->thread_map);
+	size_t ret;
+
+	ret = fprintf(fp, " nr: ");
+
+	if (threads)
+		ret += thread_map__fprintf(threads, fp);
+	else
+		ret += fprintf(fp, "failed to get threads from event\n");
+
+	thread_map__put(threads);
+	return ret;
+}
+
+size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp)
+{
+	struct cpu_map *cpus = cpu_map__new_data(&event->cpu_map.data);
+	size_t ret;
+
+	ret = fprintf(fp, " nr: ");
+
+	if (cpus)
+		ret += cpu_map__fprintf(cpus, fp);
+	else
+		ret += fprintf(fp, "failed to get cpumap from event\n");
+
+	cpu_map__put(cpus);
+	return ret;
+}
+
 int perf_event__process_mmap(struct perf_tool *tool __maybe_unused,
 			     union perf_event *event,
 			     struct perf_sample *sample,
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index a0dbcbd..b7ffb7e 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -226,6 +226,12 @@
 	PERF_RECORD_AUXTRACE_INFO		= 70,
 	PERF_RECORD_AUXTRACE			= 71,
 	PERF_RECORD_AUXTRACE_ERROR		= 72,
+	PERF_RECORD_THREAD_MAP			= 73,
+	PERF_RECORD_CPU_MAP			= 74,
+	PERF_RECORD_STAT_CONFIG			= 75,
+	PERF_RECORD_STAT			= 76,
+	PERF_RECORD_STAT_ROUND			= 77,
+	PERF_RECORD_EVENT_UPDATE		= 78,
 	PERF_RECORD_HEADER_MAX
 };
 
@@ -270,12 +276,61 @@
 	u32 nr_proc_map_timeout;
 };
 
+enum {
+	PERF_CPU_MAP__CPUS = 0,
+	PERF_CPU_MAP__MASK = 1,
+};
+
+struct cpu_map_entries {
+	u16	nr;
+	u16	cpu[];
+};
+
+struct cpu_map_mask {
+	u16	nr;
+	u16	long_size;
+	unsigned long mask[];
+};
+
+struct cpu_map_data {
+	u16	type;
+	char	data[];
+};
+
+struct cpu_map_event {
+	struct perf_event_header	header;
+	struct cpu_map_data		data;
+};
+
 struct attr_event {
 	struct perf_event_header header;
 	struct perf_event_attr attr;
 	u64 id[];
 };
 
+enum {
+	PERF_EVENT_UPDATE__UNIT  = 0,
+	PERF_EVENT_UPDATE__SCALE = 1,
+	PERF_EVENT_UPDATE__NAME  = 2,
+	PERF_EVENT_UPDATE__CPUS  = 3,
+};
+
+struct event_update_event_cpus {
+	struct cpu_map_data cpus;
+};
+
+struct event_update_event_scale {
+	double scale;
+};
+
+struct event_update_event {
+	struct perf_event_header header;
+	u64 type;
+	u64 id;
+
+	char data[];
+};
+
 #define MAX_EVENT_NAME 64
 
 struct perf_trace_event_type {
@@ -356,6 +411,63 @@
 	u32 next_prev_tid;
 };
 
+struct thread_map_event_entry {
+	u64	pid;
+	char	comm[16];
+};
+
+struct thread_map_event {
+	struct perf_event_header	header;
+	u64				nr;
+	struct thread_map_event_entry	entries[];
+};
+
+enum {
+	PERF_STAT_CONFIG_TERM__AGGR_MODE	= 0,
+	PERF_STAT_CONFIG_TERM__INTERVAL		= 1,
+	PERF_STAT_CONFIG_TERM__SCALE		= 2,
+	PERF_STAT_CONFIG_TERM__MAX		= 3,
+};
+
+struct stat_config_event_entry {
+	u64	tag;
+	u64	val;
+};
+
+struct stat_config_event {
+	struct perf_event_header	header;
+	u64				nr;
+	struct stat_config_event_entry	data[];
+};
+
+struct stat_event {
+	struct perf_event_header	header;
+
+	u64	id;
+	u32	cpu;
+	u32	thread;
+
+	union {
+		struct {
+			u64 val;
+			u64 ena;
+			u64 run;
+		};
+		u64 values[3];
+	};
+};
+
+enum {
+	PERF_STAT_ROUND_TYPE__INTERVAL	= 0,
+	PERF_STAT_ROUND_TYPE__FINAL	= 1,
+};
+
+struct stat_round_event {
+	struct perf_event_header	header;
+	u64				type;
+	u64				time;
+};
+
 union perf_event {
 	struct perf_event_header	header;
 	struct mmap_event		mmap;
@@ -368,6 +480,7 @@
 	struct throttle_event		throttle;
 	struct sample_event		sample;
 	struct attr_event		attr;
+	struct event_update_event	event_update;
 	struct event_type_event		event_type;
 	struct tracing_data_event	tracing_data;
 	struct build_id_event		build_id;
@@ -378,12 +491,20 @@
 	struct aux_event		aux;
 	struct itrace_start_event	itrace_start;
 	struct context_switch_event	context_switch;
+	struct thread_map_event		thread_map;
+	struct cpu_map_event		cpu_map;
+	struct stat_config_event	stat_config;
+	struct stat_event		stat;
+	struct stat_round_event		stat_round;
 };
 
 void perf_event__print_totals(void);
 
 struct perf_tool;
 struct thread_map;
+struct cpu_map;
+struct perf_stat_config;
+struct perf_counts_values;
 
 typedef int (*perf_event__handler_t)(struct perf_tool *tool,
 				     union perf_event *event,
@@ -395,6 +516,14 @@
 				      perf_event__handler_t process,
 				      struct machine *machine, bool mmap_data,
 				      unsigned int proc_map_timeout);
+int perf_event__synthesize_thread_map2(struct perf_tool *tool,
+				      struct thread_map *threads,
+				      perf_event__handler_t process,
+				      struct machine *machine);
+int perf_event__synthesize_cpu_map(struct perf_tool *tool,
+				   struct cpu_map *cpus,
+				   perf_event__handler_t process,
+				   struct machine *machine);
 int perf_event__synthesize_threads(struct perf_tool *tool,
 				   perf_event__handler_t process,
 				   struct machine *machine, bool mmap_data,
@@ -402,7 +531,21 @@
 int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 				       perf_event__handler_t process,
 				       struct machine *machine);
-
+int perf_event__synthesize_stat_config(struct perf_tool *tool,
+				       struct perf_stat_config *config,
+				       perf_event__handler_t process,
+				       struct machine *machine);
+void perf_event__read_stat_config(struct perf_stat_config *config,
+				  struct stat_config_event *event);
+int perf_event__synthesize_stat(struct perf_tool *tool,
+				u32 cpu, u32 thread, u64 id,
+				struct perf_counts_values *count,
+				perf_event__handler_t process,
+				struct machine *machine);
+int perf_event__synthesize_stat_round(struct perf_tool *tool,
+				      u64 time, u64 type,
+				      perf_event__handler_t process,
+				      struct machine *machine);
 int perf_event__synthesize_modules(struct perf_tool *tool,
 				   perf_event__handler_t process,
 				   struct machine *machine);
@@ -499,9 +642,14 @@
 size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_thread_map(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf(union perf_event *event, FILE *fp);
 
 u64 kallsyms__get_function_start(const char *kallsyms_filename,
 				 const char *symbol_name);
 
+void *cpu_map_data__alloc(struct cpu_map *map, size_t *size, u16 *type, int *max);
+void  cpu_map_data__synthesize(struct cpu_map_data *data, struct cpu_map *map,
+			       u16 type, int max);
 #endif /* __PERF_RECORD_H */
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index d139219..d81f13d 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -18,7 +18,7 @@
 #include <unistd.h>
 
 #include "parse-events.h"
-#include "parse-options.h"
+#include <subcmd/parse-options.h>
 
 #include <sys/mman.h>
 
@@ -68,6 +68,18 @@
 	return evlist;
 }
 
+struct perf_evlist *perf_evlist__new_dummy(void)
+{
+	struct perf_evlist *evlist = perf_evlist__new();
+
+	if (evlist && perf_evlist__add_dummy(evlist)) {
+		perf_evlist__delete(evlist);
+		evlist = NULL;
+	}
+
+	return evlist;
+}
+
 /**
  * perf_evlist__set_id_pos - set the positions of event ids.
  * @evlist: selected event list
@@ -248,6 +260,22 @@
 	return -ENOMEM;
 }
 
+int perf_evlist__add_dummy(struct perf_evlist *evlist)
+{
+	struct perf_event_attr attr = {
+		.type	= PERF_TYPE_SOFTWARE,
+		.config = PERF_COUNT_SW_DUMMY,
+		.size	= sizeof(attr), /* to capture ABI version */
+	};
+	struct perf_evsel *evsel = perf_evsel__new(&attr);
+
+	if (evsel == NULL)
+		return -ENOMEM;
+
+	perf_evlist__add(evlist, evsel);
+	return 0;
+}
+
 static int perf_evlist__add_attrs(struct perf_evlist *evlist,
 				  struct perf_event_attr *attrs, size_t nr_attrs)
 {
@@ -336,20 +364,12 @@
 
 void perf_evlist__disable(struct perf_evlist *evlist)
 {
-	int cpu, thread;
 	struct perf_evsel *pos;
-	int nr_cpus = cpu_map__nr(evlist->cpus);
-	int nr_threads;
 
-	for (cpu = 0; cpu < nr_cpus; cpu++) {
-		evlist__for_each(evlist, pos) {
-			if (!perf_evsel__is_group_leader(pos) || !pos->fd)
-				continue;
-			nr_threads = perf_evlist__nr_threads(evlist, pos);
-			for (thread = 0; thread < nr_threads; thread++)
-				ioctl(FD(pos, cpu, thread),
-				      PERF_EVENT_IOC_DISABLE, 0);
-		}
+	evlist__for_each(evlist, pos) {
+		if (!perf_evsel__is_group_leader(pos) || !pos->fd)
+			continue;
+		perf_evsel__disable(pos);
 	}
 
 	evlist->enabled = false;
@@ -357,20 +377,12 @@
 
 void perf_evlist__enable(struct perf_evlist *evlist)
 {
-	int cpu, thread;
 	struct perf_evsel *pos;
-	int nr_cpus = cpu_map__nr(evlist->cpus);
-	int nr_threads;
 
-	for (cpu = 0; cpu < nr_cpus; cpu++) {
-		evlist__for_each(evlist, pos) {
-			if (!perf_evsel__is_group_leader(pos) || !pos->fd)
-				continue;
-			nr_threads = perf_evlist__nr_threads(evlist, pos);
-			for (thread = 0; thread < nr_threads; thread++)
-				ioctl(FD(pos, cpu, thread),
-				      PERF_EVENT_IOC_ENABLE, 0);
-		}
+	evlist__for_each(evlist, pos) {
+		if (!perf_evsel__is_group_leader(pos) || !pos->fd)
+			continue;
+		perf_evsel__enable(pos);
 	}
 
 	evlist->enabled = true;
@@ -381,48 +393,6 @@
 	(evlist->enabled ? perf_evlist__disable : perf_evlist__enable)(evlist);
 }
 
-int perf_evlist__disable_event(struct perf_evlist *evlist,
-			       struct perf_evsel *evsel)
-{
-	int cpu, thread, err;
-	int nr_cpus = cpu_map__nr(evlist->cpus);
-	int nr_threads = perf_evlist__nr_threads(evlist, evsel);
-
-	if (!evsel->fd)
-		return 0;
-
-	for (cpu = 0; cpu < nr_cpus; cpu++) {
-		for (thread = 0; thread < nr_threads; thread++) {
-			err = ioctl(FD(evsel, cpu, thread),
-				    PERF_EVENT_IOC_DISABLE, 0);
-			if (err)
-				return err;
-		}
-	}
-	return 0;
-}
-
-int perf_evlist__enable_event(struct perf_evlist *evlist,
-			      struct perf_evsel *evsel)
-{
-	int cpu, thread, err;
-	int nr_cpus = cpu_map__nr(evlist->cpus);
-	int nr_threads = perf_evlist__nr_threads(evlist, evsel);
-
-	if (!evsel->fd)
-		return -EINVAL;
-
-	for (cpu = 0; cpu < nr_cpus; cpu++) {
-		for (thread = 0; thread < nr_threads; thread++) {
-			err = ioctl(FD(evsel, cpu, thread),
-				    PERF_EVENT_IOC_ENABLE, 0);
-			if (err)
-				return err;
-		}
-	}
-	return 0;
-}
-
 static int perf_evlist__enable_event_cpu(struct perf_evlist *evlist,
 					 struct perf_evsel *evsel, int cpu)
 {
@@ -550,9 +520,9 @@
 	evsel->id[evsel->ids++] = id;
 }
 
-static int perf_evlist__id_add_fd(struct perf_evlist *evlist,
-				  struct perf_evsel *evsel,
-				  int cpu, int thread, int fd)
+int perf_evlist__id_add_fd(struct perf_evlist *evlist,
+			   struct perf_evsel *evsel,
+			   int cpu, int thread, int fd)
 {
 	u64 read_data[4] = { 0, };
 	int id_idx = 1; /* The first entry is the counter value */
@@ -1486,7 +1456,7 @@
 	perf_evlist__update_id_pos(evlist);
 
 	evlist__for_each(evlist, evsel) {
-		err = perf_evsel__open(evsel, evlist->cpus, evlist->threads);
+		err = perf_evsel__open(evsel, evsel->cpus, evsel->threads);
 		if (err < 0)
 			goto out_err;
 	}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index a459fe7..7c4d9a2 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -67,6 +67,7 @@
 
 struct perf_evlist *perf_evlist__new(void);
 struct perf_evlist *perf_evlist__new_default(void);
+struct perf_evlist *perf_evlist__new_dummy(void);
 void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus,
 		       struct thread_map *threads);
 void perf_evlist__exit(struct perf_evlist *evlist);
@@ -81,6 +82,8 @@
 #define perf_evlist__add_default_attrs(evlist, array) \
 	__perf_evlist__add_default_attrs(evlist, array, ARRAY_SIZE(array))
 
+int perf_evlist__add_dummy(struct perf_evlist *evlist);
+
 int perf_evlist__add_newtp(struct perf_evlist *evlist,
 			   const char *sys, const char *name, void *handler);
 
@@ -97,6 +100,9 @@
 
 void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel,
 			 int cpu, int thread, u64 id);
+int perf_evlist__id_add_fd(struct perf_evlist *evlist,
+			   struct perf_evsel *evsel,
+			   int cpu, int thread, int fd);
 
 int perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd);
 int perf_evlist__alloc_pollfd(struct perf_evlist *evlist);
@@ -149,10 +155,6 @@
 void perf_evlist__enable(struct perf_evlist *evlist);
 void perf_evlist__toggle_enable(struct perf_evlist *evlist);
 
-int perf_evlist__disable_event(struct perf_evlist *evlist,
-			       struct perf_evsel *evsel);
-int perf_evlist__enable_event(struct perf_evlist *evlist,
-			      struct perf_evsel *evsel);
 int perf_evlist__enable_event_idx(struct perf_evlist *evlist,
 				  struct perf_evsel *evsel, int idx);
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 397fb4e..cdbaf9b 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -36,6 +36,7 @@
 	bool cloexec;
 	bool clockid;
 	bool clockid_wrong;
+	bool lbr_flags;
 } perf_missing_features;
 
 static clockid_t clockid;
@@ -574,7 +575,9 @@
 			} else {
 				perf_evsel__set_sample_bit(evsel, BRANCH_STACK);
 				attr->branch_sample_type = PERF_SAMPLE_BRANCH_USER |
-							PERF_SAMPLE_BRANCH_CALL_STACK;
+							PERF_SAMPLE_BRANCH_CALL_STACK |
+							PERF_SAMPLE_BRANCH_NO_CYCLES |
+							PERF_SAMPLE_BRANCH_NO_FLAGS;
 			}
 		} else
 			 pr_warning("Cannot use LBR callstack with branch stack. "
@@ -981,13 +984,26 @@
 	return -1;
 }
 
-int perf_evsel__enable(struct perf_evsel *evsel, int ncpus, int nthreads)
+int perf_evsel__enable(struct perf_evsel *evsel)
 {
+	int nthreads = thread_map__nr(evsel->threads);
+	int ncpus = cpu_map__nr(evsel->cpus);
+
 	return perf_evsel__run_ioctl(evsel, ncpus, nthreads,
 				     PERF_EVENT_IOC_ENABLE,
 				     0);
 }
 
+int perf_evsel__disable(struct perf_evsel *evsel)
+{
+	int nthreads = thread_map__nr(evsel->threads);
+	int ncpus = cpu_map__nr(evsel->cpus);
+
+	return perf_evsel__run_ioctl(evsel, ncpus, nthreads,
+				     PERF_EVENT_IOC_DISABLE,
+				     0);
+}
+
 int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
 	if (ncpus == 0 || nthreads == 0)
@@ -1192,6 +1208,7 @@
 		bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW),
 		bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER),
 		bit_name(IDENTIFIER), bit_name(REGS_INTR), bit_name(DATA_SRC),
+		bit_name(WEIGHT),
 		{ .name = NULL, }
 	};
 #undef bit_name
@@ -1323,6 +1340,9 @@
 		evsel->attr.mmap2 = 0;
 	if (perf_missing_features.exclude_guest)
 		evsel->attr.exclude_guest = evsel->attr.exclude_host = 0;
+	if (perf_missing_features.lbr_flags)
+		evsel->attr.branch_sample_type &= ~(PERF_SAMPLE_BRANCH_NO_FLAGS |
+				     PERF_SAMPLE_BRANCH_NO_CYCLES);
 retry_sample_id:
 	if (perf_missing_features.sample_id_all)
 		evsel->attr.sample_id_all = 0;
@@ -1441,6 +1461,12 @@
 	} else if (!perf_missing_features.sample_id_all) {
 		perf_missing_features.sample_id_all = true;
 		goto retry_sample_id;
+	} else if (!perf_missing_features.lbr_flags &&
+			(evsel->attr.branch_sample_type &
+			 (PERF_SAMPLE_BRANCH_NO_CYCLES |
+			  PERF_SAMPLE_BRANCH_NO_FLAGS))) {
+		perf_missing_features.lbr_flags = true;
+		goto fallback_missing_features;
 	}
 
 out_close:
@@ -2272,6 +2298,29 @@
 		printed += comma_fprintf(fp, &first, " %s=%" PRIu64,
 					 term, (u64)evsel->attr.sample_freq);
 	}
+
+	if (details->trace_fields) {
+		struct format_field *field;
+
+		if (evsel->attr.type != PERF_TYPE_TRACEPOINT) {
+			printed += comma_fprintf(fp, &first, " (not a tracepoint)");
+			goto out;
+		}
+
+		field = evsel->tp_format->format.fields;
+		if (field == NULL) {
+			printed += comma_fprintf(fp, &first, " (no trace field)");
+			goto out;
+		}
+
+		printed += comma_fprintf(fp, &first, " trace_fields: %s", field->name);
+
+		field = field->next;
+		while (field) {
+			printed += comma_fprintf(fp, &first, "%s", field->name);
+			field = field->next;
+		}
+	}
 out:
 	fputc('\n', fp);
 	return ++printed;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 0e49bd7..8e75434 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -227,7 +227,8 @@
 			      const char *op, const char *filter);
 int perf_evsel__apply_filter(struct perf_evsel *evsel, int ncpus, int nthreads,
 			     const char *filter);
-int perf_evsel__enable(struct perf_evsel *evsel, int ncpus, int nthreads);
+int perf_evsel__enable(struct perf_evsel *evsel);
+int perf_evsel__disable(struct perf_evsel *evsel);
 
 int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
 			     struct cpu_map *cpus);
@@ -368,6 +369,7 @@
 	bool verbose;
 	bool event_group;
 	bool force;
+	bool trace_fields;
 };
 
 int perf_evsel__fprintf(struct perf_evsel *evsel,
diff --git a/tools/perf/util/exec_cmd.c b/tools/perf/util/exec_cmd.c
deleted file mode 100644
index 7adf4ad..0000000
--- a/tools/perf/util/exec_cmd.c
+++ /dev/null
@@ -1,148 +0,0 @@
-#include "cache.h"
-#include "exec_cmd.h"
-#include "quote.h"
-
-#include <string.h>
-
-#define MAX_ARGS	32
-
-static const char *argv_exec_path;
-static const char *argv0_path;
-
-const char *system_path(const char *path)
-{
-	static const char *prefix = PREFIX;
-	struct strbuf d = STRBUF_INIT;
-
-	if (is_absolute_path(path))
-		return path;
-
-	strbuf_addf(&d, "%s/%s", prefix, path);
-	path = strbuf_detach(&d, NULL);
-	return path;
-}
-
-const char *perf_extract_argv0_path(const char *argv0)
-{
-	const char *slash;
-
-	if (!argv0 || !*argv0)
-		return NULL;
-	slash = argv0 + strlen(argv0);
-
-	while (argv0 <= slash && !is_dir_sep(*slash))
-		slash--;
-
-	if (slash >= argv0) {
-		argv0_path = strndup(argv0, slash - argv0);
-		return argv0_path ? slash + 1 : NULL;
-	}
-
-	return argv0;
-}
-
-void perf_set_argv_exec_path(const char *exec_path)
-{
-	argv_exec_path = exec_path;
-	/*
-	 * Propagate this setting to external programs.
-	 */
-	setenv(EXEC_PATH_ENVIRONMENT, exec_path, 1);
-}
-
-
-/* Returns the highest-priority, location to look for perf programs. */
-const char *perf_exec_path(void)
-{
-	const char *env;
-
-	if (argv_exec_path)
-		return argv_exec_path;
-
-	env = getenv(EXEC_PATH_ENVIRONMENT);
-	if (env && *env) {
-		return env;
-	}
-
-	return system_path(PERF_EXEC_PATH);
-}
-
-static void add_path(struct strbuf *out, const char *path)
-{
-	if (path && *path) {
-		if (is_absolute_path(path))
-			strbuf_addstr(out, path);
-		else
-			strbuf_addstr(out, make_nonrelative_path(path));
-
-		strbuf_addch(out, PATH_SEP);
-	}
-}
-
-void setup_path(void)
-{
-	const char *old_path = getenv("PATH");
-	struct strbuf new_path = STRBUF_INIT;
-
-	add_path(&new_path, perf_exec_path());
-	add_path(&new_path, argv0_path);
-
-	if (old_path)
-		strbuf_addstr(&new_path, old_path);
-	else
-		strbuf_addstr(&new_path, "/usr/local/bin:/usr/bin:/bin");
-
-	setenv("PATH", new_path.buf, 1);
-
-	strbuf_release(&new_path);
-}
-
-static const char **prepare_perf_cmd(const char **argv)
-{
-	int argc;
-	const char **nargv;
-
-	for (argc = 0; argv[argc]; argc++)
-		; /* just counting */
-	nargv = malloc(sizeof(*nargv) * (argc + 2));
-
-	nargv[0] = "perf";
-	for (argc = 0; argv[argc]; argc++)
-		nargv[argc + 1] = argv[argc];
-	nargv[argc + 1] = NULL;
-	return nargv;
-}
-
-int execv_perf_cmd(const char **argv) {
-	const char **nargv = prepare_perf_cmd(argv);
-
-	/* execvp() can only ever return if it fails */
-	execvp("perf", (char **)nargv);
-
-	free(nargv);
-	return -1;
-}
-
-
-int execl_perf_cmd(const char *cmd,...)
-{
-	int argc;
-	const char *argv[MAX_ARGS + 1];
-	const char *arg;
-	va_list param;
-
-	va_start(param, cmd);
-	argv[0] = cmd;
-	argc = 1;
-	while (argc < MAX_ARGS) {
-		arg = argv[argc++] = va_arg(param, char *);
-		if (!arg)
-			break;
-	}
-	va_end(param);
-	if (MAX_ARGS <= argc)
-		return error("too many args to run %s", cmd);
-
-	argv[argc] = NULL;
-	return execv_perf_cmd(argv);
-}
diff --git a/tools/perf/util/exec_cmd.h b/tools/perf/util/exec_cmd.h
deleted file mode 100644
index bc4b915..0000000
--- a/tools/perf/util/exec_cmd.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef __PERF_EXEC_CMD_H
-#define __PERF_EXEC_CMD_H
-
-extern void perf_set_argv_exec_path(const char *exec_path);
-extern const char *perf_extract_argv0_path(const char *path);
-extern const char *perf_exec_path(void);
-extern void setup_path(void);
-extern int execv_perf_cmd(const char **argv); /* NULL terminated */
-extern int execl_perf_cmd(const char *cmd, ...);
-extern const char *system_path(const char *path);
-
-#endif /* __PERF_EXEC_CMD_H */
diff --git a/tools/perf/util/generate-cmdlist.sh b/tools/perf/util/generate-cmdlist.sh
index 36a885d..0ac2037 100755
--- a/tools/perf/util/generate-cmdlist.sh
+++ b/tools/perf/util/generate-cmdlist.sh
@@ -36,4 +36,19 @@
      }' "Documentation/perf-$cmd.txt"
 done
 echo "#endif /* HAVE_LIBELF_SUPPORT */"
+
+echo "#ifdef HAVE_LIBAUDIT_SUPPORT"
+sed -n -e 's/^perf-\([^ 	]*\)[ 	].* audit*/\1/p' command-list.txt |
+sort |
+while read cmd
+do
+     sed -n '
+     /^NAME/,/perf-'"$cmd"'/H
+     ${
+            x
+            s/.*perf-'"$cmd"' - \(.*\)/  {"'"$cmd"'", "\1"},/
+	    p
+     }' "Documentation/perf-$cmd.txt"
+done
+echo "#endif /* HAVE_LIBELF_SUPPORT */"
 echo "};"
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 4383800..f50b723 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -724,7 +724,7 @@
 done:
 	free(buf);
 	fclose(fp);
-	free(node_map);
+	cpu_map__put(node_map);
 	return ret;
 }
 
@@ -868,6 +868,13 @@
 	return err;
 }
 
+static int write_stat(int fd __maybe_unused,
+		      struct perf_header *h __maybe_unused,
+		      struct perf_evlist *evlist __maybe_unused)
+{
+	return 0;
+}
+
 static void print_hostname(struct perf_header *ph, int fd __maybe_unused,
 			   FILE *fp)
 {
@@ -1159,6 +1166,12 @@
 	fprintf(fp, "# contains AUX area data (e.g. instruction trace)\n");
 }
 
+static void print_stat(struct perf_header *ph __maybe_unused,
+		       int fd __maybe_unused, FILE *fp)
+{
+	fprintf(fp, "# contains stat data\n");
+}
+
 static void print_pmu_mappings(struct perf_header *ph, int fd __maybe_unused,
 			       FILE *fp)
 {
@@ -1948,6 +1961,7 @@
 	FEAT_OPP(HEADER_PMU_MAPPINGS,	pmu_mappings),
 	FEAT_OPP(HEADER_GROUP_DESC,	group_desc),
 	FEAT_OPP(HEADER_AUXTRACE,	auxtrace),
+	FEAT_OPA(HEADER_STAT,		stat),
 };
 
 struct header_print_data {
@@ -2686,6 +2700,152 @@
 	return err;
 }
 
+static struct event_update_event *
+event_update_event__new(size_t size, u64 type, u64 id)
+{
+	struct event_update_event *ev;
+
+	size += sizeof(*ev);
+	size  = PERF_ALIGN(size, sizeof(u64));
+
+	ev = zalloc(size);
+	if (ev) {
+		ev->header.type = PERF_RECORD_EVENT_UPDATE;
+		ev->header.size = (u16)size;
+		ev->type = type;
+		ev->id = id;
+	}
+	return ev;
+}
+
+int
+perf_event__synthesize_event_update_unit(struct perf_tool *tool,
+					 struct perf_evsel *evsel,
+					 perf_event__handler_t process)
+{
+	struct event_update_event *ev;
+	size_t size = strlen(evsel->unit);
+	int err;
+
+	ev = event_update_event__new(size + 1, PERF_EVENT_UPDATE__UNIT, evsel->id[0]);
+	if (ev == NULL)
+		return -ENOMEM;
+
+	strncpy(ev->data, evsel->unit, size);
+	err = process(tool, (union perf_event *)ev, NULL, NULL);
+	free(ev);
+	return err;
+}
+
+int
+perf_event__synthesize_event_update_scale(struct perf_tool *tool,
+					  struct perf_evsel *evsel,
+					  perf_event__handler_t process)
+{
+	struct event_update_event *ev;
+	struct event_update_event_scale *ev_data;
+	int err;
+
+	ev = event_update_event__new(sizeof(*ev_data), PERF_EVENT_UPDATE__SCALE, evsel->id[0]);
+	if (ev == NULL)
+		return -ENOMEM;
+
+	ev_data = (struct event_update_event_scale *) ev->data;
+	ev_data->scale = evsel->scale;
+	err = process(tool, (union perf_event*) ev, NULL, NULL);
+	free(ev);
+	return err;
+}
+
+int
+perf_event__synthesize_event_update_name(struct perf_tool *tool,
+					 struct perf_evsel *evsel,
+					 perf_event__handler_t process)
+{
+	struct event_update_event *ev;
+	size_t len = strlen(evsel->name);
+	int err;
+
+	ev = event_update_event__new(len + 1, PERF_EVENT_UPDATE__NAME, evsel->id[0]);
+	if (ev == NULL)
+		return -ENOMEM;
+
+	strncpy(ev->data, evsel->name, len);
+	err = process(tool, (union perf_event*) ev, NULL, NULL);
+	free(ev);
+	return err;
+}
+
+int
+perf_event__synthesize_event_update_cpus(struct perf_tool *tool,
+					struct perf_evsel *evsel,
+					perf_event__handler_t process)
+{
+	size_t size = sizeof(struct event_update_event);
+	struct event_update_event *ev;
+	int max, err;
+	u16 type;
+
+	if (!evsel->own_cpus)
+		return 0;
+
+	ev = cpu_map_data__alloc(evsel->own_cpus, &size, &type, &max);
+	if (!ev)
+		return -ENOMEM;
+
+	ev->header.type = PERF_RECORD_EVENT_UPDATE;
+	ev->header.size = (u16)size;
+	ev->type = PERF_EVENT_UPDATE__CPUS;
+	ev->id   = evsel->id[0];
+
+	cpu_map_data__synthesize((struct cpu_map_data *) ev->data,
+				 evsel->own_cpus,
+				 type, max);
+
+	err = process(tool, (union perf_event*) ev, NULL, NULL);
+	free(ev);
+	return err;
+}
+
+size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp)
+{
+	struct event_update_event *ev = &event->event_update;
+	struct event_update_event_scale *ev_scale;
+	struct event_update_event_cpus *ev_cpus;
+	struct cpu_map *map;
+	size_t ret;
+
+	ret = fprintf(fp, "\n... id:    %" PRIu64 "\n", ev->id);
+
+	switch (ev->type) {
+	case PERF_EVENT_UPDATE__SCALE:
+		ev_scale = (struct event_update_event_scale *) ev->data;
+		ret += fprintf(fp, "... scale: %f\n", ev_scale->scale);
+		break;
+	case PERF_EVENT_UPDATE__UNIT:
+		ret += fprintf(fp, "... unit:  %s\n", ev->data);
+		break;
+	case PERF_EVENT_UPDATE__NAME:
+		ret += fprintf(fp, "... name:  %s\n", ev->data);
+		break;
+	case PERF_EVENT_UPDATE__CPUS:
+		ev_cpus = (struct event_update_event_cpus *) ev->data;
+		ret += fprintf(fp, "... ");
+
+		map = cpu_map__new_data(&ev_cpus->cpus);
+		if (map)
+			ret += cpu_map__fprintf(map, fp);
+		else
+			ret += fprintf(fp, "failed to get cpus\n");
+		break;
+	default:
+		ret += fprintf(fp, "... unknown type\n");
+		break;
+	}
+
+	return ret;
+}
+
 int perf_event__synthesize_attrs(struct perf_tool *tool,
 				   struct perf_session *session,
 				   perf_event__handler_t process)
@@ -2745,6 +2905,51 @@
 	return 0;
 }
 
+int perf_event__process_event_update(struct perf_tool *tool __maybe_unused,
+				     union perf_event *event,
+				     struct perf_evlist **pevlist)
+{
+	struct event_update_event *ev = &event->event_update;
+	struct event_update_event_scale *ev_scale;
+	struct event_update_event_cpus *ev_cpus;
+	struct perf_evlist *evlist;
+	struct perf_evsel *evsel;
+	struct cpu_map *map;
+
+	if (!pevlist || *pevlist == NULL)
+		return -EINVAL;
+
+	evlist = *pevlist;
+
+	evsel = perf_evlist__id2evsel(evlist, ev->id);
+	if (evsel == NULL)
+		return -EINVAL;
+
+	switch (ev->type) {
+	case PERF_EVENT_UPDATE__UNIT:
+		evsel->unit = strdup(ev->data);
+		break;
+	case PERF_EVENT_UPDATE__NAME:
+		evsel->name = strdup(ev->data);
+		break;
+	case PERF_EVENT_UPDATE__SCALE:
+		ev_scale = (struct event_update_event_scale *) ev->data;
+		evsel->scale = ev_scale->scale;
+	case PERF_EVENT_UPDATE__CPUS:
+		ev_cpus = (struct event_update_event_cpus *) ev->data;
+
+		map = cpu_map__new_data(&ev_cpus->cpus);
+		if (map)
+			evsel->own_cpus = map;
+		else
+			pr_err("failed to get event_update cpus\n");
+	default:
+		break;
+	}
+
+	return 0;
+}
+
 int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd,
 					struct perf_evlist *evlist,
 					perf_event__handler_t process)
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 05f27cb..cff9892 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -31,6 +31,7 @@
 	HEADER_PMU_MAPPINGS,
 	HEADER_GROUP_DESC,
 	HEADER_AUXTRACE,
+	HEADER_STAT,
 	HEADER_LAST_FEATURE,
 	HEADER_FEAT_BITS	= 256,
 };
@@ -105,8 +106,24 @@
 int perf_event__synthesize_attrs(struct perf_tool *tool,
 				 struct perf_session *session,
 				 perf_event__handler_t process);
+int perf_event__synthesize_event_update_unit(struct perf_tool *tool,
+					     struct perf_evsel *evsel,
+					     perf_event__handler_t process);
+int perf_event__synthesize_event_update_scale(struct perf_tool *tool,
+					      struct perf_evsel *evsel,
+					      perf_event__handler_t process);
+int perf_event__synthesize_event_update_name(struct perf_tool *tool,
+					     struct perf_evsel *evsel,
+					     perf_event__handler_t process);
+int perf_event__synthesize_event_update_cpus(struct perf_tool *tool,
+					     struct perf_evsel *evsel,
+					     perf_event__handler_t process);
 int perf_event__process_attr(struct perf_tool *tool, union perf_event *event,
 			     struct perf_evlist **pevlist);
+int perf_event__process_event_update(struct perf_tool *tool __maybe_unused,
+				     union perf_event *event,
+				     struct perf_evlist **pevlist);
+size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp);
 
 int perf_event__synthesize_tracing_data(struct perf_tool *tool,
 					int fd, struct perf_evlist *evlist,
diff --git a/tools/perf/util/help-unknown-cmd.c b/tools/perf/util/help-unknown-cmd.c
new file mode 100644
index 0000000..dc1e41c
--- /dev/null
+++ b/tools/perf/util/help-unknown-cmd.c
@@ -0,0 +1,103 @@
+#include "cache.h"
+#include <subcmd/help.h>
+#include "../builtin.h"
+#include "levenshtein.h"
+
+static int autocorrect;
+static struct cmdnames aliases;
+
+static int perf_unknown_cmd_config(const char *var, const char *value, void *cb)
+{
+	if (!strcmp(var, "help.autocorrect"))
+		autocorrect = perf_config_int(var,value);
+	/* Also use aliases for command lookup */
+	if (!prefixcmp(var, "alias."))
+		add_cmdname(&aliases, var + 6, strlen(var + 6));
+
+	return perf_default_config(var, value, cb);
+}
+
+static int levenshtein_compare(const void *p1, const void *p2)
+{
+	const struct cmdname *const *c1 = p1, *const *c2 = p2;
+	const char *s1 = (*c1)->name, *s2 = (*c2)->name;
+	int l1 = (*c1)->len;
+	int l2 = (*c2)->len;
+	return l1 != l2 ? l1 - l2 : strcmp(s1, s2);
+}
+
+static void add_cmd_list(struct cmdnames *cmds, struct cmdnames *old)
+{
+	unsigned int i;
+
+	ALLOC_GROW(cmds->names, cmds->cnt + old->cnt, cmds->alloc);
+
+	for (i = 0; i < old->cnt; i++)
+		cmds->names[cmds->cnt++] = old->names[i];
+	zfree(&old->names);
+	old->cnt = 0;
+}
+
+const char *help_unknown_cmd(const char *cmd)
+{
+	unsigned int i, n = 0, best_similarity = 0;
+	struct cmdnames main_cmds, other_cmds;
+
+	memset(&main_cmds, 0, sizeof(main_cmds));
+	memset(&other_cmds, 0, sizeof(main_cmds));
+	memset(&aliases, 0, sizeof(aliases));
+
+	perf_config(perf_unknown_cmd_config, NULL);
+
+	load_command_list("perf-", &main_cmds, &other_cmds);
+
+	add_cmd_list(&main_cmds, &aliases);
+	add_cmd_list(&main_cmds, &other_cmds);
+	qsort(main_cmds.names, main_cmds.cnt,
+	      sizeof(main_cmds.names), cmdname_compare);
+	uniq(&main_cmds);
+
+	if (main_cmds.cnt) {
+		/* This reuses cmdname->len for similarity index */
+		for (i = 0; i < main_cmds.cnt; ++i)
+			main_cmds.names[i]->len =
+				levenshtein(cmd, main_cmds.names[i]->name, 0, 2, 1, 4);
+
+		qsort(main_cmds.names, main_cmds.cnt,
+		      sizeof(*main_cmds.names), levenshtein_compare);
+
+		best_similarity = main_cmds.names[0]->len;
+		n = 1;
+		while (n < main_cmds.cnt && best_similarity == main_cmds.names[n]->len)
+			++n;
+	}
+
+	if (autocorrect && n == 1) {
+		const char *assumed = main_cmds.names[0]->name;
+
+		main_cmds.names[0] = NULL;
+		clean_cmdnames(&main_cmds);
+		fprintf(stderr, "WARNING: You called a perf program named '%s', "
+			"which does not exist.\n"
+			"Continuing under the assumption that you meant '%s'\n",
+			cmd, assumed);
+		if (autocorrect > 0) {
+			fprintf(stderr, "in %0.1f seconds automatically...\n",
+				(float)autocorrect/10.0);
+			poll(NULL, 0, autocorrect * 100);
+		}
+		return assumed;
+	}
+
+	fprintf(stderr, "perf: '%s' is not a perf-command. See 'perf --help'.\n", cmd);
+
+	if (main_cmds.cnt && best_similarity < 6) {
+		fprintf(stderr, "\nDid you mean %s?\n",
+			n < 2 ? "this": "one of these");
+
+		for (i = 0; i < n; i++)
+			fprintf(stderr, "\t%s\n", main_cmds.names[i]->name);
+	}
+
+	exit(1);
+}
diff --git a/tools/perf/util/help-unknown-cmd.h b/tools/perf/util/help-unknown-cmd.h
new file mode 100644
index 0000000..e69de29
--- /dev/null
+++ b/tools/perf/util/help-unknown-cmd.h
diff --git a/tools/perf/util/help.c b/tools/perf/util/help.c
deleted file mode 100644
index 86c37c4..0000000
--- a/tools/perf/util/help.c
+++ /dev/null
@@ -1,339 +0,0 @@
-#include "cache.h"
-#include "../builtin.h"
-#include "exec_cmd.h"
-#include "levenshtein.h"
-#include "help.h"
-#include <termios.h>
-
-void add_cmdname(struct cmdnames *cmds, const char *name, size_t len)
-{
-	struct cmdname *ent = malloc(sizeof(*ent) + len + 1);
-
-	ent->len = len;
-	memcpy(ent->name, name, len);
-	ent->name[len] = 0;
-
-	ALLOC_GROW(cmds->names, cmds->cnt + 1, cmds->alloc);
-	cmds->names[cmds->cnt++] = ent;
-}
-
-static void clean_cmdnames(struct cmdnames *cmds)
-{
-	unsigned int i;
-
-	for (i = 0; i < cmds->cnt; ++i)
-		zfree(&cmds->names[i]);
-	zfree(&cmds->names);
-	cmds->cnt = 0;
-	cmds->alloc = 0;
-}
-
-static int cmdname_compare(const void *a_, const void *b_)
-{
-	struct cmdname *a = *(struct cmdname **)a_;
-	struct cmdname *b = *(struct cmdname **)b_;
-	return strcmp(a->name, b->name);
-}
-
-static void uniq(struct cmdnames *cmds)
-{
-	unsigned int i, j;
-
-	if (!cmds->cnt)
-		return;
-
-	for (i = j = 1; i < cmds->cnt; i++)
-		if (strcmp(cmds->names[i]->name, cmds->names[i-1]->name))
-			cmds->names[j++] = cmds->names[i];
-
-	cmds->cnt = j;
-}
-
-void exclude_cmds(struct cmdnames *cmds, struct cmdnames *excludes)
-{
-	size_t ci, cj, ei;
-	int cmp;
-
-	ci = cj = ei = 0;
-	while (ci < cmds->cnt && ei < excludes->cnt) {
-		cmp = strcmp(cmds->names[ci]->name, excludes->names[ei]->name);
-		if (cmp < 0)
-			cmds->names[cj++] = cmds->names[ci++];
-		else if (cmp == 0)
-			ci++, ei++;
-		else if (cmp > 0)
-			ei++;
-	}
-
-	while (ci < cmds->cnt)
-		cmds->names[cj++] = cmds->names[ci++];
-
-	cmds->cnt = cj;
-}
-
-static void pretty_print_string_list(struct cmdnames *cmds, int longest)
-{
-	int cols = 1, rows;
-	int space = longest + 1; /* min 1 SP between words */
-	struct winsize win;
-	int max_cols;
-	int i, j;
-
-	get_term_dimensions(&win);
-	max_cols = win.ws_col - 1; /* don't print *on* the edge */
-
-	if (space < max_cols)
-		cols = max_cols / space;
-	rows = (cmds->cnt + cols - 1) / cols;
-
-	for (i = 0; i < rows; i++) {
-		printf("  ");
-
-		for (j = 0; j < cols; j++) {
-			unsigned int n = j * rows + i;
-			unsigned int size = space;
-
-			if (n >= cmds->cnt)
-				break;
-			if (j == cols-1 || n + rows >= cmds->cnt)
-				size = 1;
-			printf("%-*s", size, cmds->names[n]->name);
-		}
-		putchar('\n');
-	}
-}
-
-static int is_executable(const char *name)
-{
-	struct stat st;
-
-	if (stat(name, &st) || /* stat, not lstat */
-	    !S_ISREG(st.st_mode))
-		return 0;
-
-	return st.st_mode & S_IXUSR;
-}
-
-static void list_commands_in_dir(struct cmdnames *cmds,
-					 const char *path,
-					 const char *prefix)
-{
-	int prefix_len;
-	DIR *dir = opendir(path);
-	struct dirent *de;
-	struct strbuf buf = STRBUF_INIT;
-	int len;
-
-	if (!dir)
-		return;
-	if (!prefix)
-		prefix = "perf-";
-	prefix_len = strlen(prefix);
-
-	strbuf_addf(&buf, "%s/", path);
-	len = buf.len;
-
-	while ((de = readdir(dir)) != NULL) {
-		int entlen;
-
-		if (prefixcmp(de->d_name, prefix))
-			continue;
-
-		strbuf_setlen(&buf, len);
-		strbuf_addstr(&buf, de->d_name);
-		if (!is_executable(buf.buf))
-			continue;
-
-		entlen = strlen(de->d_name) - prefix_len;
-		if (has_extension(de->d_name, ".exe"))
-			entlen -= 4;
-
-		add_cmdname(cmds, de->d_name + prefix_len, entlen);
-	}
-	closedir(dir);
-	strbuf_release(&buf);
-}
-
-void load_command_list(const char *prefix,
-		struct cmdnames *main_cmds,
-		struct cmdnames *other_cmds)
-{
-	const char *env_path = getenv("PATH");
-	const char *exec_path = perf_exec_path();
-
-	if (exec_path) {
-		list_commands_in_dir(main_cmds, exec_path, prefix);
-		qsort(main_cmds->names, main_cmds->cnt,
-		      sizeof(*main_cmds->names), cmdname_compare);
-		uniq(main_cmds);
-	}
-
-	if (env_path) {
-		char *paths, *path, *colon;
-		path = paths = strdup(env_path);
-		while (1) {
-			if ((colon = strchr(path, PATH_SEP)))
-				*colon = 0;
-			if (!exec_path || strcmp(path, exec_path))
-				list_commands_in_dir(other_cmds, path, prefix);
-
-			if (!colon)
-				break;
-			path = colon + 1;
-		}
-		free(paths);
-
-		qsort(other_cmds->names, other_cmds->cnt,
-		      sizeof(*other_cmds->names), cmdname_compare);
-		uniq(other_cmds);
-	}
-	exclude_cmds(other_cmds, main_cmds);
-}
-
-void list_commands(const char *title, struct cmdnames *main_cmds,
-		   struct cmdnames *other_cmds)
-{
-	unsigned int i, longest = 0;
-
-	for (i = 0; i < main_cmds->cnt; i++)
-		if (longest < main_cmds->names[i]->len)
-			longest = main_cmds->names[i]->len;
-	for (i = 0; i < other_cmds->cnt; i++)
-		if (longest < other_cmds->names[i]->len)
-			longest = other_cmds->names[i]->len;
-
-	if (main_cmds->cnt) {
-		const char *exec_path = perf_exec_path();
-		printf("available %s in '%s'\n", title, exec_path);
-		printf("----------------");
-		mput_char('-', strlen(title) + strlen(exec_path));
-		putchar('\n');
-		pretty_print_string_list(main_cmds, longest);
-		putchar('\n');
-	}
-
-	if (other_cmds->cnt) {
-		printf("%s available from elsewhere on your $PATH\n", title);
-		printf("---------------------------------------");
-		mput_char('-', strlen(title));
-		putchar('\n');
-		pretty_print_string_list(other_cmds, longest);
-		putchar('\n');
-	}
-}
-
-int is_in_cmdlist(struct cmdnames *c, const char *s)
-{
-	unsigned int i;
-
-	for (i = 0; i < c->cnt; i++)
-		if (!strcmp(s, c->names[i]->name))
-			return 1;
-	return 0;
-}
-
-static int autocorrect;
-static struct cmdnames aliases;
-
-static int perf_unknown_cmd_config(const char *var, const char *value, void *cb)
-{
-	if (!strcmp(var, "help.autocorrect"))
-		autocorrect = perf_config_int(var,value);
-	/* Also use aliases for command lookup */
-	if (!prefixcmp(var, "alias."))
-		add_cmdname(&aliases, var + 6, strlen(var + 6));
-
-	return perf_default_config(var, value, cb);
-}
-
-static int levenshtein_compare(const void *p1, const void *p2)
-{
-	const struct cmdname *const *c1 = p1, *const *c2 = p2;
-	const char *s1 = (*c1)->name, *s2 = (*c2)->name;
-	int l1 = (*c1)->len;
-	int l2 = (*c2)->len;
-	return l1 != l2 ? l1 - l2 : strcmp(s1, s2);
-}
-
-static void add_cmd_list(struct cmdnames *cmds, struct cmdnames *old)
-{
-	unsigned int i;
-
-	ALLOC_GROW(cmds->names, cmds->cnt + old->cnt, cmds->alloc);
-
-	for (i = 0; i < old->cnt; i++)
-		cmds->names[cmds->cnt++] = old->names[i];
-	zfree(&old->names);
-	old->cnt = 0;
-}
-
-const char *help_unknown_cmd(const char *cmd)
-{
-	unsigned int i, n = 0, best_similarity = 0;
-	struct cmdnames main_cmds, other_cmds;
-
-	memset(&main_cmds, 0, sizeof(main_cmds));
-	memset(&other_cmds, 0, sizeof(main_cmds));
-	memset(&aliases, 0, sizeof(aliases));
-
-	perf_config(perf_unknown_cmd_config, NULL);
-
-	load_command_list("perf-", &main_cmds, &other_cmds);
-
-	add_cmd_list(&main_cmds, &aliases);
-	add_cmd_list(&main_cmds, &other_cmds);
-	qsort(main_cmds.names, main_cmds.cnt,
-	      sizeof(main_cmds.names), cmdname_compare);
-	uniq(&main_cmds);
-
-	if (main_cmds.cnt) {
-		/* This reuses cmdname->len for similarity index */
-		for (i = 0; i < main_cmds.cnt; ++i)
-			main_cmds.names[i]->len =
-				levenshtein(cmd, main_cmds.names[i]->name, 0, 2, 1, 4);
-
-		qsort(main_cmds.names, main_cmds.cnt,
-		      sizeof(*main_cmds.names), levenshtein_compare);
-
-		best_similarity = main_cmds.names[0]->len;
-		n = 1;
-		while (n < main_cmds.cnt && best_similarity == main_cmds.names[n]->len)
-			++n;
-	}
-
-	if (autocorrect && n == 1) {
-		const char *assumed = main_cmds.names[0]->name;
-
-		main_cmds.names[0] = NULL;
-		clean_cmdnames(&main_cmds);
-		fprintf(stderr, "WARNING: You called a perf program named '%s', "
-			"which does not exist.\n"
-			"Continuing under the assumption that you meant '%s'\n",
-			cmd, assumed);
-		if (autocorrect > 0) {
-			fprintf(stderr, "in %0.1f seconds automatically...\n",
-				(float)autocorrect/10.0);
-			poll(NULL, 0, autocorrect * 100);
-		}
-		return assumed;
-	}
-
-	fprintf(stderr, "perf: '%s' is not a perf-command. See 'perf --help'.\n", cmd);
-
-	if (main_cmds.cnt && best_similarity < 6) {
-		fprintf(stderr, "\nDid you mean %s?\n",
-			n < 2 ? "this": "one of these");
-
-		for (i = 0; i < n; i++)
-			fprintf(stderr, "\t%s\n", main_cmds.names[i]->name);
-	}
-
-	exit(1);
-}
-
-int cmd_version(int argc __maybe_unused, const char **argv __maybe_unused,
-		const char *prefix __maybe_unused)
-{
-	printf("perf version %s\n", perf_version_string);
-	return 0;
-}
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 4fd37d6..c226303 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -254,6 +254,7 @@
 	he_stat__decay(&he->stat);
 	if (symbol_conf.cumulate_callchain)
 		he_stat__decay(he->stat_acc);
+	decay_callchain(he->callchain);
 
 	diff = prev_period - he->stat.period;
 
@@ -270,6 +271,8 @@
 
 	if (sort__need_collapse)
 		rb_erase(&he->rb_node_in, &hists->entries_collapsed);
+	else
+		rb_erase(&he->rb_node_in, hists->entries_in);
 
 	--hists->nr_entries;
 	if (!he->filtered)
@@ -367,6 +370,25 @@
 		if (symbol_conf.use_callchain)
 			callchain_init(he->callchain);
 
+		if (he->raw_data) {
+			he->raw_data = memdup(he->raw_data, he->raw_size);
+
+			if (he->raw_data == NULL) {
+				map__put(he->ms.map);
+				if (he->branch_info) {
+					map__put(he->branch_info->from.map);
+					map__put(he->branch_info->to.map);
+					free(he->branch_info);
+				}
+				if (he->mem_info) {
+					map__put(he->mem_info->iaddr.map);
+					map__put(he->mem_info->daddr.map);
+				}
+				free(he->stat_acc);
+				free(he);
+				return NULL;
+			}
+		}
 		INIT_LIST_HEAD(&he->pairs.node);
 		thread__get(he->thread);
 	}
@@ -459,7 +481,7 @@
 				      struct symbol *sym_parent,
 				      struct branch_info *bi,
 				      struct mem_info *mi,
-				      u64 period, u64 weight, u64 transaction,
+				      struct perf_sample *sample,
 				      bool sample_self)
 {
 	struct hist_entry entry = {
@@ -476,15 +498,17 @@
 		.level	 = al->level,
 		.stat = {
 			.nr_events = 1,
-			.period	= period,
-			.weight = weight,
+			.period	= sample->period,
+			.weight = sample->weight,
 		},
 		.parent = sym_parent,
 		.filtered = symbol__parent_filter(sym_parent) | al->filtered,
 		.hists	= hists,
 		.branch_info = bi,
 		.mem_info = mi,
-		.transaction = transaction,
+		.transaction = sample->transaction,
+		.raw_data = sample->raw_data,
+		.raw_size = sample->raw_size,
 	};
 
 	return hists__findnew_entry(hists, &entry, al, sample_self);
@@ -524,12 +548,13 @@
 	u64 cost;
 	struct mem_info *mi = iter->priv;
 	struct hists *hists = evsel__hists(iter->evsel);
+	struct perf_sample *sample = iter->sample;
 	struct hist_entry *he;
 
 	if (mi == NULL)
 		return -EINVAL;
 
-	cost = iter->sample->weight;
+	cost = sample->weight;
 	if (!cost)
 		cost = 1;
 
@@ -540,8 +565,10 @@
 	 * and this is indirectly achieved by passing period=weight here
 	 * and the he_stat__add_period() function.
 	 */
+	sample->period = cost;
+
 	he = __hists__add_entry(hists, al, iter->parent, NULL, mi,
-				cost, cost, 0, true);
+				sample, true);
 	if (!he)
 		return -ENOMEM;
 
@@ -628,6 +655,7 @@
 	struct branch_info *bi;
 	struct perf_evsel *evsel = iter->evsel;
 	struct hists *hists = evsel__hists(evsel);
+	struct perf_sample *sample = iter->sample;
 	struct hist_entry *he = NULL;
 	int i = iter->curr;
 	int err = 0;
@@ -641,9 +669,11 @@
 	 * The report shows the percentage of total branches captured
 	 * and not events sampled. Thus we use a pseudo period of 1.
 	 */
+	sample->period = 1;
+	sample->weight = bi->flags.cycles ? bi->flags.cycles : 1;
+
 	he = __hists__add_entry(hists, al, iter->parent, &bi[i], NULL,
-				1, bi->flags.cycles ? bi->flags.cycles : 1,
-				0, true);
+				sample, true);
 	if (he == NULL)
 		return -ENOMEM;
 
@@ -680,8 +710,7 @@
 	struct hist_entry *he;
 
 	he = __hists__add_entry(evsel__hists(evsel), al, iter->parent, NULL, NULL,
-				sample->period, sample->weight,
-				sample->transaction, true);
+				sample, true);
 	if (he == NULL)
 		return -ENOMEM;
 
@@ -742,8 +771,7 @@
 	int err = 0;
 
 	he = __hists__add_entry(hists, al, iter->parent, NULL, NULL,
-				sample->period, sample->weight,
-				sample->transaction, true);
+				sample, true);
 	if (he == NULL)
 		return -ENOMEM;
 
@@ -795,6 +823,8 @@
 			.sym = al->sym,
 		},
 		.parent = iter->parent,
+		.raw_data = sample->raw_data,
+		.raw_size = sample->raw_size,
 	};
 	int i;
 	struct callchain_cursor cursor;
@@ -816,8 +846,7 @@
 	}
 
 	he = __hists__add_entry(evsel__hists(evsel), al, iter->parent, NULL, NULL,
-				sample->period, sample->weight,
-				sample->transaction, false);
+				sample, false);
 	if (he == NULL)
 		return -ENOMEM;
 
@@ -924,9 +953,6 @@
 	int64_t cmp = 0;
 
 	perf_hpp__for_each_sort_list(fmt) {
-		if (perf_hpp__should_skip(fmt))
-			continue;
-
 		cmp = fmt->cmp(fmt, left, right);
 		if (cmp)
 			break;
@@ -942,9 +968,6 @@
 	int64_t cmp = 0;
 
 	perf_hpp__for_each_sort_list(fmt) {
-		if (perf_hpp__should_skip(fmt))
-			continue;
-
 		cmp = fmt->collapse(fmt, left, right);
 		if (cmp)
 			break;
@@ -975,6 +998,8 @@
 	if (he->srcfile && he->srcfile[0])
 		free(he->srcfile);
 	free_callchain(he->callchain);
+	free(he->trace_output);
+	free(he->raw_data);
 	free(he);
 }
 
@@ -982,9 +1007,8 @@
  * collapse the histogram
  */
 
-static bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
-					 struct rb_root *root,
-					 struct hist_entry *he)
+bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
+				  struct rb_root *root, struct hist_entry *he)
 {
 	struct rb_node **p = &root->rb_node;
 	struct rb_node *parent = NULL;
@@ -1024,7 +1048,7 @@
 	return true;
 }
 
-static struct rb_root *hists__get_rotate_entries_in(struct hists *hists)
+struct rb_root *hists__get_rotate_entries_in(struct hists *hists)
 {
 	struct rb_root *root;
 
@@ -1088,7 +1112,7 @@
 	int64_t cmp = 0;
 
 	perf_hpp__for_each_sort_list(fmt) {
-		if (perf_hpp__should_skip(fmt))
+		if (perf_hpp__should_skip(fmt, a->hists))
 			continue;
 
 		cmp = fmt->sort(fmt, a, b);
@@ -1559,10 +1583,8 @@
 	return 0;
 }
 
-static int hists_evsel__init(struct perf_evsel *evsel)
+int __hists__init(struct hists *hists)
 {
-	struct hists *hists = evsel__hists(evsel);
-
 	memset(hists, 0, sizeof(*hists));
 	hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT;
 	hists->entries_in = &hists->entries_in_array[0];
@@ -1573,6 +1595,43 @@
 	return 0;
 }
 
+static void hists__delete_remaining_entries(struct rb_root *root)
+{
+	struct rb_node *node;
+	struct hist_entry *he;
+
+	while (!RB_EMPTY_ROOT(root)) {
+		node = rb_first(root);
+		rb_erase(node, root);
+
+		he = rb_entry(node, struct hist_entry, rb_node_in);
+		hist_entry__delete(he);
+	}
+}
+
+static void hists__delete_all_entries(struct hists *hists)
+{
+	hists__delete_entries(hists);
+	hists__delete_remaining_entries(&hists->entries_in_array[0]);
+	hists__delete_remaining_entries(&hists->entries_in_array[1]);
+	hists__delete_remaining_entries(&hists->entries_collapsed);
+}
+
+static void hists_evsel__exit(struct perf_evsel *evsel)
+{
+	struct hists *hists = evsel__hists(evsel);
+
+	hists__delete_all_entries(hists);
+}
+
+static int hists_evsel__init(struct perf_evsel *evsel)
+{
+	struct hists *hists = evsel__hists(evsel);
+
+	__hists__init(hists);
+	return 0;
+}
+
 /*
  * XXX We probably need a hists_evsel__exit() to free the hist_entries
  * stored in the rbtree...
@@ -1581,7 +1640,8 @@
 int hists__init(void)
 {
 	int err = perf_evsel__object_config(sizeof(struct hists_evsel),
-					    hists_evsel__init, NULL);
+					    hists_evsel__init,
+					    hists_evsel__exit);
 	if (err)
 		fputs("FATAL ERROR: Couldn't setup hists class\n", stderr);
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index a48a207..d4ec482 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -52,6 +52,7 @@
 	HISTC_MEM_IADDR_SYMBOL,
 	HISTC_TRANSACTION,
 	HISTC_CYCLES,
+	HISTC_TRACE,
 	HISTC_NR_COLS, /* Last entry */
 };
 
@@ -114,8 +115,8 @@
 				      struct addr_location *al,
 				      struct symbol *parent,
 				      struct branch_info *bi,
-				      struct mem_info *mi, u64 period,
-				      u64 weight, u64 transaction,
+				      struct mem_info *mi,
+				      struct perf_sample *sample,
 				      bool sample_self);
 int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
 			 int max_stack_depth, void *arg);
@@ -184,6 +185,11 @@
 }
 
 int hists__init(void);
+int __hists__init(struct hists *hists);
+
+struct rb_root *hists__get_rotate_entries_in(struct hists *hists);
+bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
+				  struct rb_root *root, struct hist_entry *he);
 
 struct perf_hpp {
 	char *buf;
@@ -261,10 +267,20 @@
 
 bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format);
 bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b);
+bool perf_hpp__is_dynamic_entry(struct perf_hpp_fmt *format);
+bool perf_hpp__defined_dynamic_entry(struct perf_hpp_fmt *fmt, struct hists *hists);
 
-static inline bool perf_hpp__should_skip(struct perf_hpp_fmt *format)
+static inline bool perf_hpp__should_skip(struct perf_hpp_fmt *format,
+					 struct hists *hists)
 {
-	return format->elide;
+	if (format->elide)
+		return true;
+
+	if (perf_hpp__is_dynamic_entry(format) &&
+	    !perf_hpp__defined_dynamic_entry(format, hists))
+		return true;
+
+	return false;
 }
 
 void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists);
diff --git a/tools/perf/util/include/linux/string.h b/tools/perf/util/include/linux/string.h
deleted file mode 100644
index 6f19c54..0000000
--- a/tools/perf/util/include/linux/string.h
+++ /dev/null
@@ -1,3 +0,0 @@
-#include <string.h>
-
-void *memdup(const void *src, size_t len);
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 97f963a..81a2eb7 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -1744,7 +1744,7 @@
 	auxtrace_heap__free(&pt->heap);
 	intel_pt_free_events(session);
 	session->auxtrace = NULL;
-	thread__delete(pt->unknown_thread);
+	thread__put(pt->unknown_thread);
 	free(pt);
 }
 
@@ -2153,7 +2153,7 @@
 	return 0;
 
 err_delete_thread:
-	thread__delete(pt->unknown_thread);
+	thread__zput(pt->unknown_thread);
 err_free_queues:
 	intel_pt_log_disable();
 	auxtrace_queues__free(&pt->queues);
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 8b303ff..ad79297 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -25,6 +25,7 @@
 
 int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 {
+	memset(machine, 0, sizeof(*machine));
 	map_groups__init(&machine->kmaps, machine);
 	RB_CLEAR_NODE(&machine->rb_node);
 	dsos__init(&machine->dsos);
@@ -44,6 +45,8 @@
 	machine->comm_exec = false;
 	machine->kernel_start = 0;
 
+	memset(machine->vmlinux_maps, 0, sizeof(machine->vmlinux_maps));
+
 	machine->root_dir = strdup(root_dir);
 	if (machine->root_dir == NULL)
 		return -ENOMEM;
@@ -122,6 +125,7 @@
 
 void machine__exit(struct machine *machine)
 {
+	machine__destroy_kernel_maps(machine);
 	map_groups__exit(&machine->kmaps);
 	dsos__exit(&machine->dsos);
 	machine__exit_vdso(machine);
@@ -348,13 +352,18 @@
 	}
 
 	th->mg = map_groups__get(leader->mg);
-
+out_put:
+	thread__put(leader);
 	return;
-
 out_err:
 	pr_err("Failed to join map groups for %d:%d\n", th->pid_, th->tid);
+	goto out_put;
 }
 
+/*
+ * Caller must eventually drop thread->refcnt returned with a successfull
+ * lookup/new thread inserted.
+ */
 static struct thread *____machine__findnew_thread(struct machine *machine,
 						  pid_t pid, pid_t tid,
 						  bool create)
@@ -372,7 +381,7 @@
 	if (th != NULL) {
 		if (th->tid == tid) {
 			machine__update_thread_pid(machine, th, pid);
-			return th;
+			return thread__get(th);
 		}
 
 		machine->last_match = NULL;
@@ -385,7 +394,7 @@
 		if (th->tid == tid) {
 			machine->last_match = th;
 			machine__update_thread_pid(machine, th, pid);
-			return th;
+			return thread__get(th);
 		}
 
 		if (tid < th->tid)
@@ -413,7 +422,7 @@
 		if (thread__init_map_groups(th, machine)) {
 			rb_erase_init(&th->rb_node, &machine->threads);
 			RB_CLEAR_NODE(&th->rb_node);
-			thread__delete(th);
+			thread__put(th);
 			return NULL;
 		}
 		/*
@@ -437,7 +446,7 @@
 	struct thread *th;
 
 	pthread_rwlock_wrlock(&machine->threads_lock);
-	th = thread__get(__machine__findnew_thread(machine, pid, tid));
+	th = __machine__findnew_thread(machine, pid, tid);
 	pthread_rwlock_unlock(&machine->threads_lock);
 	return th;
 }
@@ -447,7 +456,7 @@
 {
 	struct thread *th;
 	pthread_rwlock_rdlock(&machine->threads_lock);
-	th =  thread__get(____machine__findnew_thread(machine, pid, tid, false));
+	th =  ____machine__findnew_thread(machine, pid, tid, false);
 	pthread_rwlock_unlock(&machine->threads_lock);
 	return th;
 }
@@ -560,11 +569,29 @@
 	return 0;
 }
 
+static void dso__adjust_kmod_long_name(struct dso *dso, const char *filename)
+{
+	const char *dup_filename;
+
+	if (!filename || !dso || !dso->long_name)
+		return;
+	if (dso->long_name[0] != '[')
+		return;
+	if (!strchr(filename, '/'))
+		return;
+
+	dup_filename = strdup(filename);
+	if (!dup_filename)
+		return;
+
+	dso__set_long_name(dso, dup_filename, true);
+}
+
 struct map *machine__findnew_module_map(struct machine *machine, u64 start,
 					const char *filename)
 {
 	struct map *map = NULL;
-	struct dso *dso;
+	struct dso *dso = NULL;
 	struct kmod_path m;
 
 	if (kmod_path__parse_name(&m, filename))
@@ -572,8 +599,15 @@
 
 	map = map_groups__find_by_name(&machine->kmaps, MAP__FUNCTION,
 				       m.name);
-	if (map)
+	if (map) {
+		/*
+		 * If the map's dso is an offline module, give dso__load()
+		 * a chance to find the file path of that module by fixing
+		 * long_name.
+		 */
+		dso__adjust_kmod_long_name(map->dso, filename);
 		goto out;
+	}
 
 	dso = machine__findnew_module_dso(machine, &m, filename);
 	if (dso == NULL)
@@ -585,7 +619,11 @@
 
 	map_groups__insert(&machine->kmaps, map);
 
+	/* Put the map here because map_groups__insert alread got it */
+	map__put(map);
 out:
+	/* put the dso here, corresponding to  machine__findnew_module_dso */
+	dso__put(dso);
 	free(m.name);
 	return map;
 }
@@ -740,6 +778,9 @@
 	enum map_type type;
 	u64 start = machine__get_running_kernel_start(machine, NULL);
 
+	/* In case of renewal the kernel map, destroy previous one */
+	machine__destroy_kernel_maps(machine);
+
 	for (type = 0; type < MAP__NR_TYPES; ++type) {
 		struct kmap *kmap;
 		struct map *map;
@@ -788,6 +829,7 @@
 				kmap->ref_reloc_sym = NULL;
 		}
 
+		map__put(machine->vmlinux_maps[type]);
 		machine->vmlinux_maps[type] = NULL;
 	}
 }
@@ -1084,11 +1126,14 @@
 	struct dso *kernel = machine__get_kernel(machine);
 	const char *name;
 	u64 addr = machine__get_running_kernel_start(machine, &name);
-	if (!addr)
+	int ret;
+
+	if (!addr || kernel == NULL)
 		return -1;
 
-	if (kernel == NULL ||
-	    __machine__create_kernel_maps(machine, kernel) < 0)
+	ret = __machine__create_kernel_maps(machine, kernel);
+	dso__put(kernel);
+	if (ret < 0)
 		return -1;
 
 	if (symbol_conf.use_modules && machine__create_modules(machine) < 0) {
@@ -1609,6 +1654,8 @@
 		}
 	}
 
+	if (symbol_conf.hide_unresolved && al.sym == NULL)
+		return 0;
 	return callchain_cursor_append(&callchain_cursor, al.addr, al.map, al.sym);
 }
 
@@ -1863,6 +1910,9 @@
 static int unwind_entry(struct unwind_entry *entry, void *arg)
 {
 	struct callchain_cursor *cursor = arg;
+
+	if (symbol_conf.hide_unresolved && entry->sym == NULL)
+		return 0;
 	return callchain_cursor_append(cursor, entry->ip,
 				       entry->map, entry->sym);
 }
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index afc6b56..171b6d1 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -26,8 +26,8 @@
 static inline int is_anon_memory(const char *filename)
 {
 	return !strcmp(filename, "//anon") ||
-	       !strcmp(filename, "/dev/zero (deleted)") ||
-	       !strcmp(filename, "/anon_hugepage (deleted)");
+	       !strncmp(filename, "/dev/zero", sizeof("/dev/zero") - 1) ||
+	       !strncmp(filename, "/anon_hugepage", sizeof("/anon_hugepage") - 1);
 }
 
 static inline int is_no_dso_memory(const char *filename)
@@ -691,6 +691,7 @@
 			__map_groups__insert(pos->groups, before);
 			if (verbose >= 2)
 				map__fprintf(before, fp);
+			map__put(before);
 		}
 
 		if (map->end < pos->end) {
@@ -705,6 +706,7 @@
 			__map_groups__insert(pos->groups, after);
 			if (verbose >= 2)
 				map__fprintf(after, fp);
+			map__put(after);
 		}
 put_map:
 		map__put(pos);
@@ -742,6 +744,7 @@
 		if (new == NULL)
 			goto out_unlock;
 		map_groups__insert(mg, new);
+		map__put(new);
 	}
 
 	err = 0;
diff --git a/tools/perf/util/parse-branch-options.c b/tools/perf/util/parse-branch-options.c
index 355eecf..afc088d 100644
--- a/tools/perf/util/parse-branch-options.c
+++ b/tools/perf/util/parse-branch-options.c
@@ -1,7 +1,7 @@
 #include "perf.h"
 #include "util/util.h"
 #include "util/debug.h"
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/parse-branch-options.h"
 
 #define BRANCH_OPT(n, m) \
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index e48d9da..4f7b0ef 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -4,9 +4,9 @@
 #include "../perf.h"
 #include "evlist.h"
 #include "evsel.h"
-#include "parse-options.h"
+#include <subcmd/parse-options.h>
 #include "parse-events.h"
-#include "exec_cmd.h"
+#include <subcmd/exec-cmd.h>
 #include "string.h"
 #include "symbol.h"
 #include "cache.h"
@@ -124,6 +124,10 @@
 		.symbol = "dummy",
 		.alias  = "",
 	},
+	[PERF_COUNT_SW_BPF_OUTPUT] = {
+		.symbol = "bpf-output",
+		.alias  = "",
+	},
 };
 
 #define __PERF_EVENT_FIELD(config, name) \
@@ -1879,7 +1883,7 @@
 
 	for (i = 0; i < max; i++, syms++) {
 
-		if (event_glob != NULL &&
+		if (event_glob != NULL && syms->symbol != NULL &&
 		    !(strglobmatch(syms->symbol, event_glob) ||
 		      (syms->alias && strglobmatch(syms->alias, event_glob))))
 			continue;
diff --git a/tools/perf/util/parse-regs-options.c b/tools/perf/util/parse-regs-options.c
index 4f2c1c2..646ecf7 100644
--- a/tools/perf/util/parse-regs-options.c
+++ b/tools/perf/util/parse-regs-options.c
@@ -1,7 +1,7 @@
 #include "perf.h"
 #include "util/util.h"
 #include "util/debug.h"
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/parse-regs-options.h"
 
 int
diff --git a/tools/perf/util/path.c b/tools/perf/util/path.c
index 5d13cb4..3654d96 100644
--- a/tools/perf/util/path.c
+++ b/tools/perf/util/path.c
@@ -22,24 +22,6 @@
 	return ".";
 }
 
-/*
- * If libc has strlcpy() then that version will override this
- * implementation:
- */
-size_t __weak strlcpy(char *dest, const char *src, size_t size)
-{
-	size_t ret = strlen(src);
-
-	if (size) {
-		size_t len = (ret >= size) ? size - 1 : ret;
-
-		memcpy(dest, src, len);
-		dest[len] = '\0';
-	}
-
-	return ret;
-}
-
 static char *get_pathname(void)
 {
 	static char pathname_array[4][PATH_MAX];
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index e4b173d..b597bcc 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -220,6 +220,7 @@
 	alias->scale = 1.0;
 	alias->unit[0] = '\0';
 	alias->per_pkg = false;
+	alias->snapshot = false;
 
 	ret = parse_events_terms(&alias->terms, val);
 	if (ret) {
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 03875f9..93996ec 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -2326,8 +2326,11 @@
 		goto out;
 
 	if (!allow_suffix) {
-		pr_warning("Error: event \"%s\" already exists. "
-			   "(Use -f to force duplicates.)\n", buf);
+		pr_warning("Error: event \"%s\" already exists.\n"
+			   " Hint: Remove existing event by 'perf probe -d'\n"
+			   "       or force duplicates by 'perf probe -f'\n"
+			   "       or set 'force=yes' in BPF source.\n",
+			   buf);
 		ret = -EEXIST;
 		goto out;
 	}
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 05012bb..2be10fb 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -654,6 +654,7 @@
 static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf)
 {
 	Dwarf_Attribute fb_attr;
+	Dwarf_Frame *frame = NULL;
 	size_t nops;
 	int ret;
 
@@ -686,11 +687,11 @@
 #if _ELFUTILS_PREREQ(0, 142)
 	} else if (nops == 1 && pf->fb_ops[0].atom == DW_OP_call_frame_cfa &&
 		   pf->cfi != NULL) {
-		Dwarf_Frame *frame;
 		if (dwarf_cfi_addrframe(pf->cfi, pf->addr, &frame) != 0 ||
 		    dwarf_frame_cfa(frame, &pf->fb_ops, &nops) != 0) {
 			pr_warning("Failed to get call frame on 0x%jx\n",
 				   (uintmax_t)pf->addr);
+			free(frame);
 			return -ENOENT;
 		}
 #endif
@@ -699,7 +700,8 @@
 	/* Call finder's callback handler */
 	ret = pf->callback(sc_die, pf);
 
-	/* *pf->fb_ops will be cached in libdw. Don't free it. */
+	/* Since *pf->fb_ops can be a part of frame. we should free it here. */
+	free(frame);
 	pf->fb_ops = NULL;
 
 	return ret;
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 51be28b..8162ba0 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -10,6 +10,8 @@
 util/evlist.c
 util/evsel.c
 util/cpumap.c
+../lib/bitmap.c
+../lib/find_bit.c
 ../lib/hweight.c
 util/thread_map.c
 util/util.c
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index a8e825f..d72fafc 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -41,6 +41,9 @@
 #include "../thread-stack.h"
 #include "../trace-event.h"
 #include "../machine.h"
+#include "thread_map.h"
+#include "cpumap.h"
+#include "stat.h"
 
 PyMODINIT_FUNC initperf_trace_context(void);
 
@@ -859,6 +862,104 @@
 	}
 }
 
+static void get_handler_name(char *str, size_t size,
+			     struct perf_evsel *evsel)
+{
+	char *p = str;
+
+	scnprintf(str, size, "stat__%s", perf_evsel__name(evsel));
+
+	while ((p = strchr(p, ':'))) {
+		*p = '_';
+		p++;
+	}
+}
+
+static void
+process_stat(struct perf_evsel *counter, int cpu, int thread, u64 tstamp,
+	     struct perf_counts_values *count)
+{
+	PyObject *handler, *t;
+	static char handler_name[256];
+	int n = 0;
+
+	t = PyTuple_New(MAX_FIELDS);
+	if (!t)
+		Py_FatalError("couldn't create Python tuple");
+
+	get_handler_name(handler_name, sizeof(handler_name),
+			 counter);
+
+	handler = get_handler(handler_name);
+	if (!handler) {
+		pr_debug("can't find python handler %s\n", handler_name);
+		return;
+	}
+
+	PyTuple_SetItem(t, n++, PyInt_FromLong(cpu));
+	PyTuple_SetItem(t, n++, PyInt_FromLong(thread));
+
+	tuple_set_u64(t, n++, tstamp);
+	tuple_set_u64(t, n++, count->val);
+	tuple_set_u64(t, n++, count->ena);
+	tuple_set_u64(t, n++, count->run);
+
+	if (_PyTuple_Resize(&t, n) == -1)
+		Py_FatalError("error resizing Python tuple");
+
+	call_object(handler, t, handler_name);
+
+	Py_DECREF(t);
+}
+
+static void python_process_stat(struct perf_stat_config *config,
+				struct perf_evsel *counter, u64 tstamp)
+{
+	struct thread_map *threads = counter->threads;
+	struct cpu_map *cpus = counter->cpus;
+	int cpu, thread;
+
+	if (config->aggr_mode == AGGR_GLOBAL) {
+		process_stat(counter, -1, -1, tstamp,
+			     &counter->counts->aggr);
+		return;
+	}
+
+	for (thread = 0; thread < threads->nr; thread++) {
+		for (cpu = 0; cpu < cpus->nr; cpu++) {
+			process_stat(counter, cpus->map[cpu],
+				     thread_map__pid(threads, thread), tstamp,
+				     perf_counts(counter->counts, cpu, thread));
+		}
+	}
+}
+
+static void python_process_stat_interval(u64 tstamp)
+{
+	PyObject *handler, *t;
+	static const char handler_name[] = "stat__interval";
+	int n = 0;
+
+	t = PyTuple_New(MAX_FIELDS);
+	if (!t)
+		Py_FatalError("couldn't create Python tuple");
+
+	handler = get_handler(handler_name);
+	if (!handler) {
+		pr_debug("can't find python handler %s\n", handler_name);
+		return;
+	}
+
+	tuple_set_u64(t, n++, tstamp);
+
+	if (_PyTuple_Resize(&t, n) == -1)
+		Py_FatalError("error resizing Python tuple");
+
+	call_object(handler, t, handler_name);
+
+	Py_DECREF(t);
+}
+
 static int run_start_sub(void)
 {
 	main_module = PyImport_AddModule("__main__");
@@ -1201,10 +1302,12 @@
 }
 
 struct scripting_ops python_scripting_ops = {
-	.name = "Python",
-	.start_script = python_start_script,
-	.flush_script = python_flush_script,
-	.stop_script = python_stop_script,
-	.process_event = python_process_event,
-	.generate_script = python_generate_script,
+	.name			= "Python",
+	.start_script		= python_start_script,
+	.flush_script		= python_flush_script,
+	.stop_script		= python_stop_script,
+	.process_event		= python_process_event,
+	.process_stat		= python_process_stat,
+	.process_stat_interval	= python_process_stat_interval,
+	.generate_script	= python_generate_script,
 };
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index c35ffdd..d5636ba 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -17,6 +17,7 @@
 #include "asm/bug.h"
 #include "auxtrace.h"
 #include "thread-stack.h"
+#include "stat.h"
 
 static int perf_session__deliver_event(struct perf_session *session,
 				       union perf_event *event,
@@ -36,6 +37,9 @@
 	if (perf_data_file__is_pipe(file))
 		return 0;
 
+	if (perf_header__has_feat(&session->header, HEADER_STAT))
+		return 0;
+
 	if (!perf_evlist__valid_sample_type(session->evlist)) {
 		pr_err("non matching sample_type\n");
 		return -1;
@@ -205,6 +209,18 @@
 	return 0;
 }
 
+static int process_event_synth_event_update_stub(struct perf_tool *tool __maybe_unused,
+						 union perf_event *event __maybe_unused,
+						 struct perf_evlist **pevlist
+						 __maybe_unused)
+{
+	if (dump_trace)
+		perf_event__fprintf_event_update(event, stdout);
+
+	dump_printf(": unhandled!\n");
+	return 0;
+}
+
 static int process_event_sample_stub(struct perf_tool *tool __maybe_unused,
 				     union perf_event *event __maybe_unused,
 				     struct perf_sample *sample __maybe_unused,
@@ -296,6 +312,67 @@
 	return 0;
 }
 
+
+static
+int process_event_thread_map_stub(struct perf_tool *tool __maybe_unused,
+				  union perf_event *event __maybe_unused,
+				  struct perf_session *session __maybe_unused)
+{
+	if (dump_trace)
+		perf_event__fprintf_thread_map(event, stdout);
+
+	dump_printf(": unhandled!\n");
+	return 0;
+}
+
+static
+int process_event_cpu_map_stub(struct perf_tool *tool __maybe_unused,
+			       union perf_event *event __maybe_unused,
+			       struct perf_session *session __maybe_unused)
+{
+	if (dump_trace)
+		perf_event__fprintf_cpu_map(event, stdout);
+
+	dump_printf(": unhandled!\n");
+	return 0;
+}
+
+static
+int process_event_stat_config_stub(struct perf_tool *tool __maybe_unused,
+				   union perf_event *event __maybe_unused,
+				   struct perf_session *session __maybe_unused)
+{
+	if (dump_trace)
+		perf_event__fprintf_stat_config(event, stdout);
+
+	dump_printf(": unhandled!\n");
+	return 0;
+}
+
+static int process_stat_stub(struct perf_tool *tool __maybe_unused,
+			     union perf_event *event __maybe_unused,
+			     struct perf_session *perf_session
+			     __maybe_unused)
+{
+	if (dump_trace)
+		perf_event__fprintf_stat(event, stdout);
+
+	dump_printf(": unhandled!\n");
+	return 0;
+}
+
+static int process_stat_round_stub(struct perf_tool *tool __maybe_unused,
+				   union perf_event *event __maybe_unused,
+				   struct perf_session *perf_session
+				   __maybe_unused)
+{
+	if (dump_trace)
+		perf_event__fprintf_stat_round(event, stdout);
+
+	dump_printf(": unhandled!\n");
+	return 0;
+}
+
 void perf_tool__fill_defaults(struct perf_tool *tool)
 {
 	if (tool->sample == NULL)
@@ -328,6 +405,8 @@
 		tool->unthrottle = process_event_stub;
 	if (tool->attr == NULL)
 		tool->attr = process_event_synth_attr_stub;
+	if (tool->event_update == NULL)
+		tool->event_update = process_event_synth_event_update_stub;
 	if (tool->tracing_data == NULL)
 		tool->tracing_data = process_event_synth_tracing_data_stub;
 	if (tool->build_id == NULL)
@@ -346,6 +425,16 @@
 		tool->auxtrace = process_event_auxtrace_stub;
 	if (tool->auxtrace_error == NULL)
 		tool->auxtrace_error = process_event_auxtrace_error_stub;
+	if (tool->thread_map == NULL)
+		tool->thread_map = process_event_thread_map_stub;
+	if (tool->cpu_map == NULL)
+		tool->cpu_map = process_event_cpu_map_stub;
+	if (tool->stat_config == NULL)
+		tool->stat_config = process_event_stat_config_stub;
+	if (tool->stat == NULL)
+		tool->stat = process_stat_stub;
+	if (tool->stat_round == NULL)
+		tool->stat_round = process_stat_round_stub;
 }
 
 static void swap_sample_id_all(union perf_event *event, void *data)
@@ -569,6 +658,13 @@
 	mem_bswap_64(event->attr.id, size);
 }
 
+static void perf_event__event_update_swap(union perf_event *event,
+					  bool sample_id_all __maybe_unused)
+{
+	event->event_update.type = bswap_64(event->event_update.type);
+	event->event_update.id   = bswap_64(event->event_update.id);
+}
+
 static void perf_event__event_type_swap(union perf_event *event,
 					bool sample_id_all __maybe_unused)
 {
@@ -616,6 +712,81 @@
 	event->auxtrace_error.ip   = bswap_64(event->auxtrace_error.ip);
 }
 
+static void perf_event__thread_map_swap(union perf_event *event,
+					bool sample_id_all __maybe_unused)
+{
+	unsigned i;
+
+	event->thread_map.nr = bswap_64(event->thread_map.nr);
+
+	for (i = 0; i < event->thread_map.nr; i++)
+		event->thread_map.entries[i].pid = bswap_64(event->thread_map.entries[i].pid);
+}
+
+static void perf_event__cpu_map_swap(union perf_event *event,
+				     bool sample_id_all __maybe_unused)
+{
+	struct cpu_map_data *data = &event->cpu_map.data;
+	struct cpu_map_entries *cpus;
+	struct cpu_map_mask *mask;
+	unsigned i;
+
+	data->type = bswap_64(data->type);
+
+	switch (data->type) {
+	case PERF_CPU_MAP__CPUS:
+		cpus = (struct cpu_map_entries *)data->data;
+
+		cpus->nr = bswap_16(cpus->nr);
+
+		for (i = 0; i < cpus->nr; i++)
+			cpus->cpu[i] = bswap_16(cpus->cpu[i]);
+		break;
+	case PERF_CPU_MAP__MASK:
+		mask = (struct cpu_map_mask *) data->data;
+
+		mask->nr = bswap_16(mask->nr);
+		mask->long_size = bswap_16(mask->long_size);
+
+		switch (mask->long_size) {
+		case 4: mem_bswap_32(&mask->mask, mask->nr); break;
+		case 8: mem_bswap_64(&mask->mask, mask->nr); break;
+		default:
+			pr_err("cpu_map swap: unsupported long size\n");
+		}
+	default:
+		break;
+	}
+}
+
+static void perf_event__stat_config_swap(union perf_event *event,
+					 bool sample_id_all __maybe_unused)
+{
+	u64 size;
+
+	size  = event->stat_config.nr * sizeof(event->stat_config.data[0]);
+	size += 1; /* nr item itself */
+	mem_bswap_64(&event->stat_config.nr, size);
+}
+
+static void perf_event__stat_swap(union perf_event *event,
+				  bool sample_id_all __maybe_unused)
+{
+	event->stat.id     = bswap_64(event->stat.id);
+	event->stat.thread = bswap_32(event->stat.thread);
+	event->stat.cpu    = bswap_32(event->stat.cpu);
+	event->stat.val    = bswap_64(event->stat.val);
+	event->stat.ena    = bswap_64(event->stat.ena);
+	event->stat.run    = bswap_64(event->stat.run);
+}
+
+static void perf_event__stat_round_swap(union perf_event *event,
+					bool sample_id_all __maybe_unused)
+{
+	event->stat_round.type = bswap_64(event->stat_round.type);
+	event->stat_round.time = bswap_64(event->stat_round.time);
+}
+
 typedef void (*perf_event__swap_op)(union perf_event *event,
 				    bool sample_id_all);
 
@@ -643,6 +814,12 @@
 	[PERF_RECORD_AUXTRACE_INFO]	  = perf_event__auxtrace_info_swap,
 	[PERF_RECORD_AUXTRACE]		  = perf_event__auxtrace_swap,
 	[PERF_RECORD_AUXTRACE_ERROR]	  = perf_event__auxtrace_error_swap,
+	[PERF_RECORD_THREAD_MAP]	  = perf_event__thread_map_swap,
+	[PERF_RECORD_CPU_MAP]		  = perf_event__cpu_map_swap,
+	[PERF_RECORD_STAT_CONFIG]	  = perf_event__stat_config_swap,
+	[PERF_RECORD_STAT]		  = perf_event__stat_swap,
+	[PERF_RECORD_STAT_ROUND]	  = perf_event__stat_round_swap,
+	[PERF_RECORD_EVENT_UPDATE]	  = perf_event__event_update_swap,
 	[PERF_RECORD_HEADER_MAX]	  = NULL,
 };
 
@@ -1154,6 +1331,8 @@
 			perf_session__set_comm_exec(session);
 		}
 		return err;
+	case PERF_RECORD_EVENT_UPDATE:
+		return tool->event_update(tool, event, &session->evlist);
 	case PERF_RECORD_HEADER_EVENT_TYPE:
 		/*
 		 * Depreceated, but we need to handle it for sake
@@ -1179,6 +1358,16 @@
 	case PERF_RECORD_AUXTRACE_ERROR:
 		perf_session__auxtrace_error_inc(session, event);
 		return tool->auxtrace_error(tool, event, session);
+	case PERF_RECORD_THREAD_MAP:
+		return tool->thread_map(tool, event, session);
+	case PERF_RECORD_CPU_MAP:
+		return tool->cpu_map(tool, event, session);
+	case PERF_RECORD_STAT_CONFIG:
+		return tool->stat_config(tool, event, session);
+	case PERF_RECORD_STAT:
+		return tool->stat(tool, event, session);
+	case PERF_RECORD_STAT_ROUND:
+		return tool->stat_round(tool, event, session);
 	default:
 		return -EINVAL;
 	}
@@ -1311,17 +1500,20 @@
 	return machine__findnew_thread(&session->machines.host, -1, pid);
 }
 
-struct thread *perf_session__register_idle_thread(struct perf_session *session)
+int perf_session__register_idle_thread(struct perf_session *session)
 {
 	struct thread *thread;
+	int err = 0;
 
 	thread = machine__findnew_thread(&session->machines.host, 0, 0);
 	if (thread == NULL || thread__set_comm(thread, "swapper", 0)) {
 		pr_err("problem inserting idle task.\n");
-		thread = NULL;
+		err = -1;
 	}
 
-	return thread;
+	/* machine__findnew_thread() got the thread, so put it */
+	thread__put(thread);
+	return err;
 }
 
 static void perf_session__warn_about_errors(const struct perf_session *session)
@@ -1676,7 +1868,7 @@
 	u64 size = perf_data_file__size(session->file);
 	int err;
 
-	if (perf_session__register_idle_thread(session) == NULL)
+	if (perf_session__register_idle_thread(session) < 0)
 		return -ENOMEM;
 
 	if (!perf_data_file__is_pipe(session->file))
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 3e900c0..5f792e3 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -89,7 +89,7 @@
 }
 
 struct thread *perf_session__findnew(struct perf_session *session, pid_t pid);
-struct thread *perf_session__register_idle_thread(struct perf_session *session);
+int perf_session__register_idle_thread(struct perf_session *session);
 
 size_t perf_session__fprintf(struct perf_session *session, FILE *fp);
 
diff --git a/tools/perf/util/sigchain.h b/tools/perf/util/sigchain.h
deleted file mode 100644
index 959d64e..0000000
--- a/tools/perf/util/sigchain.h
+++ /dev/null
@@ -1,10 +0,0 @@
-#ifndef __PERF_SIGCHAIN_H
-#define __PERF_SIGCHAIN_H
-
-typedef void (*sigchain_fun)(int);
-
-int sigchain_pop(int sig);
-
-void sigchain_push_common(sigchain_fun f);
-
-#endif /* __PERF_SIGCHAIN_H */
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 2d8ccd4..ec72234 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -4,6 +4,8 @@
 #include "comm.h"
 #include "symbol.h"
 #include "evsel.h"
+#include "evlist.h"
+#include <traceevent/event-parse.h>
 
 regex_t		parent_regex;
 const char	default_parent_pattern[] = "^sys_|^do_page_fault";
@@ -13,6 +15,7 @@
 const char	default_mem_sort_order[] = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked";
 const char	default_top_sort_order[] = "dso,symbol";
 const char	default_diff_sort_order[] = "dso,symbol";
+const char	default_tracepoint_sort_order[] = "trace";
 const char	*sort_order;
 const char	*field_order;
 regex_t		ignore_callees_regex;
@@ -443,6 +446,70 @@
 	.se_width_idx	= HISTC_SOCKET,
 };
 
+/* --sort trace */
+
+static char *get_trace_output(struct hist_entry *he)
+{
+	struct trace_seq seq;
+	struct perf_evsel *evsel;
+	struct pevent_record rec = {
+		.data = he->raw_data,
+		.size = he->raw_size,
+	};
+
+	evsel = hists_to_evsel(he->hists);
+
+	trace_seq_init(&seq);
+	if (symbol_conf.raw_trace) {
+		pevent_print_fields(&seq, he->raw_data, he->raw_size,
+				    evsel->tp_format);
+	} else {
+		pevent_event_info(&seq, evsel->tp_format, &rec);
+	}
+	return seq.buffer;
+}
+
+static int64_t
+sort__trace_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	struct perf_evsel *evsel;
+
+	evsel = hists_to_evsel(left->hists);
+	if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
+		return 0;
+
+	if (left->trace_output == NULL)
+		left->trace_output = get_trace_output(left);
+	if (right->trace_output == NULL)
+		right->trace_output = get_trace_output(right);
+
+	hists__new_col_len(left->hists, HISTC_TRACE, strlen(left->trace_output));
+	hists__new_col_len(right->hists, HISTC_TRACE, strlen(right->trace_output));
+
+	return strcmp(right->trace_output, left->trace_output);
+}
+
+static int hist_entry__trace_snprintf(struct hist_entry *he, char *bf,
+				    size_t size, unsigned int width)
+{
+	struct perf_evsel *evsel;
+
+	evsel = hists_to_evsel(he->hists);
+	if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
+		return scnprintf(bf, size, "%-*.*s", width, width, "N/A");
+
+	if (he->trace_output == NULL)
+		he->trace_output = get_trace_output(he);
+	return repsep_snprintf(bf, size, "%-*.*s", width, width, he->trace_output);
+}
+
+struct sort_entry sort_trace = {
+	.se_header      = "Trace output",
+	.se_cmp	        = sort__trace_cmp,
+	.se_snprintf    = hist_entry__trace_snprintf,
+	.se_width_idx	= HISTC_TRACE,
+};
+
 /* sort keys for branch stacks */
 
 static int64_t
@@ -1312,6 +1379,7 @@
 	DIM(SORT_LOCAL_WEIGHT, "local_weight", sort_local_weight),
 	DIM(SORT_GLOBAL_WEIGHT, "weight", sort_global_weight),
 	DIM(SORT_TRANSACTION, "transaction", sort_transaction),
+	DIM(SORT_TRACE, "trace", sort_trace),
 };
 
 #undef DIM
@@ -1529,6 +1597,455 @@
 	return 0;
 }
 
+struct hpp_dynamic_entry {
+	struct perf_hpp_fmt hpp;
+	struct perf_evsel *evsel;
+	struct format_field *field;
+	unsigned dynamic_len;
+	bool raw_trace;
+};
+
+static int hde_width(struct hpp_dynamic_entry *hde)
+{
+	if (!hde->hpp.len) {
+		int len = hde->dynamic_len;
+		int namelen = strlen(hde->field->name);
+		int fieldlen = hde->field->size;
+
+		if (namelen > len)
+			len = namelen;
+
+		if (!(hde->field->flags & FIELD_IS_STRING)) {
+			/* length for print hex numbers */
+			fieldlen = hde->field->size * 2 + 2;
+		}
+		if (fieldlen > len)
+			len = fieldlen;
+
+		hde->hpp.len = len;
+	}
+	return hde->hpp.len;
+}
+
+static void update_dynamic_len(struct hpp_dynamic_entry *hde,
+			       struct hist_entry *he)
+{
+	char *str, *pos;
+	struct format_field *field = hde->field;
+	size_t namelen;
+	bool last = false;
+
+	if (hde->raw_trace)
+		return;
+
+	/* parse pretty print result and update max length */
+	if (!he->trace_output)
+		he->trace_output = get_trace_output(he);
+
+	namelen = strlen(field->name);
+	str = he->trace_output;
+
+	while (str) {
+		pos = strchr(str, ' ');
+		if (pos == NULL) {
+			last = true;
+			pos = str + strlen(str);
+		}
+
+		if (!strncmp(str, field->name, namelen)) {
+			size_t len;
+
+			str += namelen + 1;
+			len = pos - str;
+
+			if (len > hde->dynamic_len)
+				hde->dynamic_len = len;
+			break;
+		}
+
+		if (last)
+			str = NULL;
+		else
+			str = pos + 1;
+	}
+}
+
+static int __sort__hde_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+			      struct perf_evsel *evsel __maybe_unused)
+{
+	struct hpp_dynamic_entry *hde;
+	size_t len = fmt->user_len;
+
+	hde = container_of(fmt, struct hpp_dynamic_entry, hpp);
+
+	if (!len)
+		len = hde_width(hde);
+
+	return scnprintf(hpp->buf, hpp->size, "%*.*s", len, len, hde->field->name);
+}
+
+static int __sort__hde_width(struct perf_hpp_fmt *fmt,
+			     struct perf_hpp *hpp __maybe_unused,
+			     struct perf_evsel *evsel __maybe_unused)
+{
+	struct hpp_dynamic_entry *hde;
+	size_t len = fmt->user_len;
+
+	hde = container_of(fmt, struct hpp_dynamic_entry, hpp);
+
+	if (!len)
+		len = hde_width(hde);
+
+	return len;
+}
+
+bool perf_hpp__defined_dynamic_entry(struct perf_hpp_fmt *fmt, struct hists *hists)
+{
+	struct hpp_dynamic_entry *hde;
+
+	hde = container_of(fmt, struct hpp_dynamic_entry, hpp);
+
+	return hists_to_evsel(hists) == hde->evsel;
+}
+
+static int __sort__hde_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+			     struct hist_entry *he)
+{
+	struct hpp_dynamic_entry *hde;
+	size_t len = fmt->user_len;
+	char *str, *pos;
+	struct format_field *field;
+	size_t namelen;
+	bool last = false;
+	int ret;
+
+	hde = container_of(fmt, struct hpp_dynamic_entry, hpp);
+
+	if (!len)
+		len = hde_width(hde);
+
+	if (hde->raw_trace)
+		goto raw_field;
+
+	field = hde->field;
+	namelen = strlen(field->name);
+	str = he->trace_output;
+
+	while (str) {
+		pos = strchr(str, ' ');
+		if (pos == NULL) {
+			last = true;
+			pos = str + strlen(str);
+		}
+
+		if (!strncmp(str, field->name, namelen)) {
+			str += namelen + 1;
+			str = strndup(str, pos - str);
+
+			if (str == NULL)
+				return scnprintf(hpp->buf, hpp->size,
+						 "%*.*s", len, len, "ERROR");
+			break;
+		}
+
+		if (last)
+			str = NULL;
+		else
+			str = pos + 1;
+	}
+
+	if (str == NULL) {
+		struct trace_seq seq;
+raw_field:
+		trace_seq_init(&seq);
+		pevent_print_field(&seq, he->raw_data, hde->field);
+		str = seq.buffer;
+	}
+
+	ret = scnprintf(hpp->buf, hpp->size, "%*.*s", len, len, str);
+	free(str);
+	return ret;
+}
+
+static int64_t __sort__hde_cmp(struct perf_hpp_fmt *fmt,
+			       struct hist_entry *a, struct hist_entry *b)
+{
+	struct hpp_dynamic_entry *hde;
+	struct format_field *field;
+	unsigned offset, size;
+
+	hde = container_of(fmt, struct hpp_dynamic_entry, hpp);
+
+	field = hde->field;
+	if (field->flags & FIELD_IS_DYNAMIC) {
+		unsigned long long dyn;
+
+		pevent_read_number_field(field, a->raw_data, &dyn);
+		offset = dyn & 0xffff;
+		size = (dyn >> 16) & 0xffff;
+
+		/* record max width for output */
+		if (size > hde->dynamic_len)
+			hde->dynamic_len = size;
+	} else {
+		offset = field->offset;
+		size = field->size;
+
+		update_dynamic_len(hde, a);
+		update_dynamic_len(hde, b);
+	}
+
+	return memcmp(a->raw_data + offset, b->raw_data + offset, size);
+}
+
+bool perf_hpp__is_dynamic_entry(struct perf_hpp_fmt *fmt)
+{
+	return fmt->cmp == __sort__hde_cmp;
+}
+
+static struct hpp_dynamic_entry *
+__alloc_dynamic_entry(struct perf_evsel *evsel, struct format_field *field)
+{
+	struct hpp_dynamic_entry *hde;
+
+	hde = malloc(sizeof(*hde));
+	if (hde == NULL) {
+		pr_debug("Memory allocation failed\n");
+		return NULL;
+	}
+
+	hde->evsel = evsel;
+	hde->field = field;
+	hde->dynamic_len = 0;
+
+	hde->hpp.name = field->name;
+	hde->hpp.header = __sort__hde_header;
+	hde->hpp.width  = __sort__hde_width;
+	hde->hpp.entry  = __sort__hde_entry;
+	hde->hpp.color  = NULL;
+
+	hde->hpp.cmp = __sort__hde_cmp;
+	hde->hpp.collapse = __sort__hde_cmp;
+	hde->hpp.sort = __sort__hde_cmp;
+
+	INIT_LIST_HEAD(&hde->hpp.list);
+	INIT_LIST_HEAD(&hde->hpp.sort_list);
+	hde->hpp.elide = false;
+	hde->hpp.len = 0;
+	hde->hpp.user_len = 0;
+
+	return hde;
+}
+
+static int parse_field_name(char *str, char **event, char **field, char **opt)
+{
+	char *event_name, *field_name, *opt_name;
+
+	event_name = str;
+	field_name = strchr(str, '.');
+
+	if (field_name) {
+		*field_name++ = '\0';
+	} else {
+		event_name = NULL;
+		field_name = str;
+	}
+
+	opt_name = strchr(field_name, '/');
+	if (opt_name)
+		*opt_name++ = '\0';
+
+	*event = event_name;
+	*field = field_name;
+	*opt   = opt_name;
+
+	return 0;
+}
+
+/* find match evsel using a given event name.  The event name can be:
+ *   1. '%' + event index (e.g. '%1' for first event)
+ *   2. full event name (e.g. sched:sched_switch)
+ *   3. partial event name (should not contain ':')
+ */
+static struct perf_evsel *find_evsel(struct perf_evlist *evlist, char *event_name)
+{
+	struct perf_evsel *evsel = NULL;
+	struct perf_evsel *pos;
+	bool full_name;
+
+	/* case 1 */
+	if (event_name[0] == '%') {
+		int nr = strtol(event_name+1, NULL, 0);
+
+		if (nr > evlist->nr_entries)
+			return NULL;
+
+		evsel = perf_evlist__first(evlist);
+		while (--nr > 0)
+			evsel = perf_evsel__next(evsel);
+
+		return evsel;
+	}
+
+	full_name = !!strchr(event_name, ':');
+	evlist__for_each(evlist, pos) {
+		/* case 2 */
+		if (full_name && !strcmp(pos->name, event_name))
+			return pos;
+		/* case 3 */
+		if (!full_name && strstr(pos->name, event_name)) {
+			if (evsel) {
+				pr_debug("'%s' event is ambiguous: it can be %s or %s\n",
+					 event_name, evsel->name, pos->name);
+				return NULL;
+			}
+			evsel = pos;
+		}
+	}
+
+	return evsel;
+}
+
+static int __dynamic_dimension__add(struct perf_evsel *evsel,
+				    struct format_field *field,
+				    bool raw_trace)
+{
+	struct hpp_dynamic_entry *hde;
+
+	hde = __alloc_dynamic_entry(evsel, field);
+	if (hde == NULL)
+		return -ENOMEM;
+
+	hde->raw_trace = raw_trace;
+
+	perf_hpp__register_sort_field(&hde->hpp);
+	return 0;
+}
+
+static int add_evsel_fields(struct perf_evsel *evsel, bool raw_trace)
+{
+	int ret;
+	struct format_field *field;
+
+	field = evsel->tp_format->format.fields;
+	while (field) {
+		ret = __dynamic_dimension__add(evsel, field, raw_trace);
+		if (ret < 0)
+			return ret;
+
+		field = field->next;
+	}
+	return 0;
+}
+
+static int add_all_dynamic_fields(struct perf_evlist *evlist, bool raw_trace)
+{
+	int ret;
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel) {
+		if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
+			continue;
+
+		ret = add_evsel_fields(evsel, raw_trace);
+		if (ret < 0)
+			return ret;
+	}
+	return 0;
+}
+
+static int add_all_matching_fields(struct perf_evlist *evlist,
+				   char *field_name, bool raw_trace)
+{
+	int ret = -ESRCH;
+	struct perf_evsel *evsel;
+	struct format_field *field;
+
+	evlist__for_each(evlist, evsel) {
+		if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
+			continue;
+
+		field = pevent_find_any_field(evsel->tp_format, field_name);
+		if (field == NULL)
+			continue;
+
+		ret = __dynamic_dimension__add(evsel, field, raw_trace);
+		if (ret < 0)
+			break;
+	}
+	return ret;
+}
+
+static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok)
+{
+	char *str, *event_name, *field_name, *opt_name;
+	struct perf_evsel *evsel;
+	struct format_field *field;
+	bool raw_trace = symbol_conf.raw_trace;
+	int ret = 0;
+
+	if (evlist == NULL)
+		return -ENOENT;
+
+	str = strdup(tok);
+	if (str == NULL)
+		return -ENOMEM;
+
+	if (parse_field_name(str, &event_name, &field_name, &opt_name) < 0) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (opt_name) {
+		if (strcmp(opt_name, "raw")) {
+			pr_debug("unsupported field option %s\n", opt_name);
+			ret = -EINVAL;
+			goto out;
+		}
+		raw_trace = true;
+	}
+
+	if (!strcmp(field_name, "trace_fields")) {
+		ret = add_all_dynamic_fields(evlist, raw_trace);
+		goto out;
+	}
+
+	if (event_name == NULL) {
+		ret = add_all_matching_fields(evlist, field_name, raw_trace);
+		goto out;
+	}
+
+	evsel = find_evsel(evlist, event_name);
+	if (evsel == NULL) {
+		pr_debug("Cannot find event: %s\n", event_name);
+		ret = -ENOENT;
+		goto out;
+	}
+
+	if (evsel->attr.type != PERF_TYPE_TRACEPOINT) {
+		pr_debug("%s is not a tracepoint event\n", event_name);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (!strcmp(field_name, "*")) {
+		ret = add_evsel_fields(evsel, raw_trace);
+	} else {
+		field = pevent_find_any_field(evsel->tp_format, field_name);
+		if (field == NULL) {
+			pr_debug("Cannot find event field for %s.%s\n",
+				 event_name, field_name);
+			return -ENOENT;
+		}
+
+		ret = __dynamic_dimension__add(evsel, field, raw_trace);
+	}
+
+out:
+	free(str);
+	return ret;
+}
+
 static int __sort_dimension__add(struct sort_dimension *sd)
 {
 	if (sd->taken)
@@ -1583,7 +2100,8 @@
 	return __hpp_dimension__add_output(&hpp_sort_dimensions[col]);
 }
 
-int sort_dimension__add(const char *tok)
+static int sort_dimension__add(const char *tok,
+			       struct perf_evlist *evlist __maybe_unused)
 {
 	unsigned int i;
 
@@ -1664,10 +2182,13 @@
 		return 0;
 	}
 
+	if (!add_dynamic_entry(evlist, tok))
+		return 0;
+
 	return -ESRCH;
 }
 
-static const char *get_default_sort_order(void)
+static const char *get_default_sort_order(struct perf_evlist *evlist)
 {
 	const char *default_sort_orders[] = {
 		default_sort_order,
@@ -1675,14 +2196,33 @@
 		default_mem_sort_order,
 		default_top_sort_order,
 		default_diff_sort_order,
+		default_tracepoint_sort_order,
 	};
+	bool use_trace = true;
+	struct perf_evsel *evsel;
 
 	BUG_ON(sort__mode >= ARRAY_SIZE(default_sort_orders));
 
+	if (evlist == NULL)
+		goto out_no_evlist;
+
+	evlist__for_each(evlist, evsel) {
+		if (evsel->attr.type != PERF_TYPE_TRACEPOINT) {
+			use_trace = false;
+			break;
+		}
+	}
+
+	if (use_trace) {
+		sort__mode = SORT_MODE__TRACEPOINT;
+		if (symbol_conf.raw_trace)
+			return "trace_fields";
+	}
+out_no_evlist:
 	return default_sort_orders[sort__mode];
 }
 
-static int setup_sort_order(void)
+static int setup_sort_order(struct perf_evlist *evlist)
 {
 	char *new_sort_order;
 
@@ -1703,7 +2243,7 @@
 	 * because it's checked over the rest of the code.
 	 */
 	if (asprintf(&new_sort_order, "%s,%s",
-		     get_default_sort_order(), sort_order + 1) < 0) {
+		     get_default_sort_order(evlist), sort_order + 1) < 0) {
 		error("Not enough memory to set up --sort");
 		return -ENOMEM;
 	}
@@ -1712,13 +2252,41 @@
 	return 0;
 }
 
-static int __setup_sorting(void)
+/*
+ * Adds 'pre,' prefix into 'str' is 'pre' is
+ * not already part of 'str'.
+ */
+static char *prefix_if_not_in(const char *pre, char *str)
+{
+	char *n;
+
+	if (!str || strstr(str, pre))
+		return str;
+
+	if (asprintf(&n, "%s,%s", pre, str) < 0)
+		return NULL;
+
+	free(str);
+	return n;
+}
+
+static char *setup_overhead(char *keys)
+{
+	keys = prefix_if_not_in("overhead", keys);
+
+	if (symbol_conf.cumulate_callchain)
+		keys = prefix_if_not_in("overhead_children", keys);
+
+	return keys;
+}
+
+static int __setup_sorting(struct perf_evlist *evlist)
 {
 	char *tmp, *tok, *str;
 	const char *sort_keys;
 	int ret = 0;
 
-	ret = setup_sort_order();
+	ret = setup_sort_order(evlist);
 	if (ret)
 		return ret;
 
@@ -1732,7 +2300,7 @@
 			return 0;
 		}
 
-		sort_keys = get_default_sort_order();
+		sort_keys = get_default_sort_order(evlist);
 	}
 
 	str = strdup(sort_keys);
@@ -1741,9 +2309,20 @@
 		return -ENOMEM;
 	}
 
+	/*
+	 * Prepend overhead fields for backward compatibility.
+	 */
+	if (!is_strict_order(field_order)) {
+		str = setup_overhead(str);
+		if (str == NULL) {
+			error("Not enough memory to setup overhead keys");
+			return -ENOMEM;
+		}
+	}
+
 	for (tok = strtok_r(str, ", ", &tmp);
 			tok; tok = strtok_r(NULL, ", ", &tmp)) {
-		ret = sort_dimension__add(tok);
+		ret = sort_dimension__add(tok, evlist);
 		if (ret == -EINVAL) {
 			error("Invalid --sort key: `%s'", tok);
 			break;
@@ -1954,16 +2533,16 @@
 	return ret;
 }
 
-int setup_sorting(void)
+int setup_sorting(struct perf_evlist *evlist)
 {
 	int err;
 
-	err = __setup_sorting();
+	err = __setup_sorting(evlist);
 	if (err < 0)
 		return err;
 
 	if (parent_pattern != default_parent_pattern) {
-		err = sort_dimension__add("parent");
+		err = sort_dimension__add("parent", evlist);
 		if (err < 0)
 			return err;
 	}
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 3122885..687bbb12 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -18,7 +18,7 @@
 #include "debug.h"
 #include "header.h"
 
-#include "parse-options.h"
+#include <subcmd/parse-options.h>
 #include "parse-events.h"
 #include "hist.h"
 #include "thread.h"
@@ -122,6 +122,9 @@
 	struct branch_info	*branch_info;
 	struct hists		*hists;
 	struct mem_info		*mem_info;
+	void			*raw_data;
+	u32			raw_size;
+	void			*trace_output;
 	struct callchain_root	callchain[0]; /* must be last member */
 };
 
@@ -164,6 +167,7 @@
 	SORT_MODE__MEMORY,
 	SORT_MODE__TOP,
 	SORT_MODE__DIFF,
+	SORT_MODE__TRACEPOINT,
 };
 
 enum sort_type {
@@ -180,6 +184,7 @@
 	SORT_LOCAL_WEIGHT,
 	SORT_GLOBAL_WEIGHT,
 	SORT_TRANSACTION,
+	SORT_TRACE,
 
 	/* branch stack specific sort keys */
 	__SORT_BRANCH_STACK,
@@ -209,8 +214,6 @@
  */
 
 struct sort_entry {
-	struct list_head list;
-
 	const char *se_header;
 
 	int64_t (*se_cmp)(struct hist_entry *, struct hist_entry *);
@@ -224,10 +227,11 @@
 extern struct sort_entry sort_thread;
 extern struct list_head hist_entry__sort_list;
 
-int setup_sorting(void);
+struct perf_evlist;
+struct pevent;
+int setup_sorting(struct perf_evlist *evlist);
 int setup_output_field(void);
 void reset_output_field(void);
-extern int sort_dimension__add(const char *);
 void sort__setup_elide(FILE *fp);
 void perf_hpp__set_elide(int idx, bool elide);
 
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 2d9d830..2f901d1 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -341,3 +341,65 @@
 
 	return 0;
 }
+
+int perf_event__process_stat_event(struct perf_tool *tool __maybe_unused,
+				   union perf_event *event,
+				   struct perf_session *session)
+{
+	struct perf_counts_values count;
+	struct stat_event *st = &event->stat;
+	struct perf_evsel *counter;
+
+	count.val = st->val;
+	count.ena = st->ena;
+	count.run = st->run;
+
+	counter = perf_evlist__id2evsel(session->evlist, st->id);
+	if (!counter) {
+		pr_err("Failed to resolve counter for stat event.\n");
+		return -EINVAL;
+	}
+
+	*perf_counts(counter->counts, st->cpu, st->thread) = count;
+	counter->supported = true;
+	return 0;
+}
+
+size_t perf_event__fprintf_stat(union perf_event *event, FILE *fp)
+{
+	struct stat_event *st = (struct stat_event *) event;
+	size_t ret;
+
+	ret  = fprintf(fp, "\n... id %" PRIu64 ", cpu %d, thread %d\n",
+		       st->id, st->cpu, st->thread);
+	ret += fprintf(fp, "... value %" PRIu64 ", enabled %" PRIu64 ", running %" PRIu64 "\n",
+		       st->val, st->ena, st->run);
+
+	return ret;
+}
+
+size_t perf_event__fprintf_stat_round(union perf_event *event, FILE *fp)
+{
+	struct stat_round_event *rd = (struct stat_round_event *)event;
+	size_t ret;
+
+	ret = fprintf(fp, "\n... time %" PRIu64 ", type %s\n", rd->time,
+		      rd->type == PERF_STAT_ROUND_TYPE__FINAL ? "FINAL" : "INTERVAL");
+
+	return ret;
+}
+
+size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp)
+{
+	struct perf_stat_config sc;
+	size_t ret;
+
+	perf_event__read_stat_config(&sc, &event->stat_config);
+
+	ret  = fprintf(fp, "\n");
+	ret += fprintf(fp, "... aggr_mode %d\n", sc.aggr_mode);
+	ret += fprintf(fp, "... scale     %d\n", sc.scale);
+	ret += fprintf(fp, "... interval  %u\n", sc.interval);
+
+	return ret;
+}
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index da1d11c..086f4e1 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -90,4 +90,14 @@
 
 int perf_stat_process_counter(struct perf_stat_config *config,
 			      struct perf_evsel *counter);
+struct perf_tool;
+union perf_event;
+struct perf_session;
+int perf_event__process_stat_event(struct perf_tool *tool,
+				   union perf_event *event,
+				   struct perf_session *session);
+
+size_t perf_event__fprintf_stat(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_stat_round(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp);
 #endif
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index fc8781d..7f7e072 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -342,22 +342,6 @@
 	return s;
 }
 
-/**
- * memdup - duplicate region of memory
- * @src: memory region to duplicate
- * @len: memory region length
- */
-void *memdup(const void *src, size_t len)
-{
-	void *p;
-
-	p = malloc(len);
-	if (p)
-		memcpy(p, src, len);
-
-	return p;
-}
-
 char *asprintf_expr_inout_ints(const char *var, bool in, size_t nints, int *ints)
 {
 	/*
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 475d88d..562b8eb 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -1026,8 +1026,8 @@
 				curr_dso->long_name_len = dso->long_name_len;
 				curr_map = map__new2(start, curr_dso,
 						     map->type);
+				dso__put(curr_dso);
 				if (curr_map == NULL) {
-					dso__put(curr_dso);
 					goto out_elf_end;
 				}
 				if (adjust_kernel_syms) {
@@ -1042,7 +1042,14 @@
 				}
 				curr_dso->symtab_type = dso->symtab_type;
 				map_groups__insert(kmaps, curr_map);
+				/*
+				 * Add it before we drop the referece to curr_map,
+				 * i.e. while we still are sure to have a reference
+				 * to this DSO via curr_map->dso.
+				 */
 				dsos__add(&map->groups->machine->dsos, curr_dso);
+				/* kmaps already got it */
+				map__put(curr_map);
 				dso__set_loaded(curr_dso, map->type);
 			} else
 				curr_dso = curr_map->dso;
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index cd08027..3b2de6e 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -39,6 +39,7 @@
 	.cumulate_callchain	= true,
 	.show_hist_headers	= true,
 	.symfs			= "",
+	.event_group		= true,
 };
 
 static enum dso_binary_type binary_type_symtab[] = {
@@ -1860,24 +1861,44 @@
 	zfree(&vmlinux_path);
 }
 
+static const char * const vmlinux_paths[] = {
+	"vmlinux",
+	"/boot/vmlinux"
+};
+
+static const char * const vmlinux_paths_upd[] = {
+	"/boot/vmlinux-%s",
+	"/usr/lib/debug/boot/vmlinux-%s",
+	"/lib/modules/%s/build/vmlinux",
+	"/usr/lib/debug/lib/modules/%s/vmlinux",
+	"/usr/lib/debug/boot/vmlinux-%s.debug"
+};
+
+static int vmlinux_path__add(const char *new_entry)
+{
+	vmlinux_path[vmlinux_path__nr_entries] = strdup(new_entry);
+	if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
+		return -1;
+	++vmlinux_path__nr_entries;
+
+	return 0;
+}
+
 static int vmlinux_path__init(struct perf_env *env)
 {
 	struct utsname uts;
 	char bf[PATH_MAX];
 	char *kernel_version;
+	unsigned int i;
 
-	vmlinux_path = malloc(sizeof(char *) * 6);
+	vmlinux_path = malloc(sizeof(char *) * (ARRAY_SIZE(vmlinux_paths) +
+			      ARRAY_SIZE(vmlinux_paths_upd)));
 	if (vmlinux_path == NULL)
 		return -1;
 
-	vmlinux_path[vmlinux_path__nr_entries] = strdup("vmlinux");
-	if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
-		goto out_fail;
-	++vmlinux_path__nr_entries;
-	vmlinux_path[vmlinux_path__nr_entries] = strdup("/boot/vmlinux");
-	if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
-		goto out_fail;
-	++vmlinux_path__nr_entries;
+	for (i = 0; i < ARRAY_SIZE(vmlinux_paths); i++)
+		if (vmlinux_path__add(vmlinux_paths[i]) < 0)
+			goto out_fail;
 
 	/* only try kernel version if no symfs was given */
 	if (symbol_conf.symfs[0] != 0)
@@ -1892,28 +1913,11 @@
 		kernel_version = uts.release;
 	}
 
-	snprintf(bf, sizeof(bf), "/boot/vmlinux-%s", kernel_version);
-	vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
-	if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
-		goto out_fail;
-	++vmlinux_path__nr_entries;
-	snprintf(bf, sizeof(bf), "/usr/lib/debug/boot/vmlinux-%s",
-		 kernel_version);
-	vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
-	if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
-		goto out_fail;
-        ++vmlinux_path__nr_entries;
-	snprintf(bf, sizeof(bf), "/lib/modules/%s/build/vmlinux", kernel_version);
-	vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
-	if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
-		goto out_fail;
-	++vmlinux_path__nr_entries;
-	snprintf(bf, sizeof(bf), "/usr/lib/debug/lib/modules/%s/vmlinux",
-		 kernel_version);
-	vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
-	if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
-		goto out_fail;
-	++vmlinux_path__nr_entries;
+	for (i = 0; i < ARRAY_SIZE(vmlinux_paths_upd); i++) {
+		snprintf(bf, sizeof(bf), vmlinux_paths_upd[i], kernel_version);
+		if (vmlinux_path__add(bf) < 0)
+			goto out_fail;
+	}
 
 	return 0;
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index dcd786e..ccd1caa 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -108,7 +108,9 @@
 			show_hist_headers,
 			branch_callstack,
 			has_filter,
-			show_ref_callgraph;
+			show_ref_callgraph,
+			hide_unresolved,
+			raw_trace;
 	const char	*vmlinux_name,
 			*kallsyms_name,
 			*source_prefix,
diff --git a/tools/perf/util/term.c b/tools/perf/util/term.c
new file mode 100644
index 0000000..90b47d8
--- /dev/null
+++ b/tools/perf/util/term.c
@@ -0,0 +1,35 @@
+#include "util.h"
+
+void get_term_dimensions(struct winsize *ws)
+{
+	char *s = getenv("LINES");
+
+	if (s != NULL) {
+		ws->ws_row = atoi(s);
+		s = getenv("COLUMNS");
+		if (s != NULL) {
+			ws->ws_col = atoi(s);
+			if (ws->ws_row && ws->ws_col)
+				return;
+		}
+	}
+#ifdef TIOCGWINSZ
+	if (ioctl(1, TIOCGWINSZ, ws) == 0 &&
+	    ws->ws_row && ws->ws_col)
+		return;
+#endif
+	ws->ws_row = 25;
+	ws->ws_col = 80;
+}
+
+void set_term_quiet_input(struct termios *old)
+{
+	struct termios tc;
+
+	tcgetattr(0, old);
+	tc = *old;
+	tc.c_lflag &= ~(ICANON | ECHO);
+	tc.c_cc[VMIN] = 0;
+	tc.c_cc[VTIME] = 0;
+	tcsetattr(0, TCSANOW, &tc);
+}
diff --git a/tools/perf/util/term.h b/tools/perf/util/term.h
new file mode 100644
index 0000000..2c06a61
--- /dev/null
+++ b/tools/perf/util/term.h
@@ -0,0 +1,10 @@
+#ifndef __PERF_TERM_H
+#define __PERF_TERM_H
+
+struct termios;
+struct winsize;
+
+void get_term_dimensions(struct winsize *ws);
+void set_term_quiet_input(struct termios *old);
+
+#endif /* __PERF_TERM_H */
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 0a9ae80..dfd00c6 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -19,8 +19,10 @@
 		thread->mg = map_groups__new(machine);
 	} else {
 		leader = __machine__findnew_thread(machine, pid, pid);
-		if (leader)
+		if (leader) {
 			thread->mg = map_groups__get(leader->mg);
+			thread__put(leader);
+		}
 	}
 
 	return thread->mg ? 0 : -1;
@@ -53,7 +55,7 @@
 			goto err_thread;
 
 		list_add(&comm->list, &thread->comm_list);
-		atomic_set(&thread->refcnt, 0);
+		atomic_set(&thread->refcnt, 1);
 		RB_CLEAR_NODE(&thread->rb_node);
 	}
 
@@ -95,6 +97,10 @@
 void thread__put(struct thread *thread)
 {
 	if (thread && atomic_dec_and_test(&thread->refcnt)) {
+		/*
+		 * Remove it from the dead_threads list, as last reference
+		 * is gone.
+		 */
 		list_del_init(&thread->node);
 		thread__delete(thread);
 	}
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index 6ec3c5c..08afc690 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -13,6 +13,7 @@
 #include "thread_map.h"
 #include "util.h"
 #include "debug.h"
+#include "event.h"
 
 /* Skip "." and ".." directories */
 static int filter(const struct dirent *dir)
@@ -304,6 +305,7 @@
 
 out_free_threads:
 	zfree(&threads);
+	strlist__delete(slist);
 	goto out;
 }
 
@@ -408,3 +410,29 @@
 	for (i = 0; i < threads->nr; ++i)
 		comm_init(threads, i);
 }
+
+static void thread_map__copy_event(struct thread_map *threads,
+				   struct thread_map_event *event)
+{
+	unsigned i;
+
+	threads->nr = (int) event->nr;
+
+	for (i = 0; i < event->nr; i++) {
+		thread_map__set_pid(threads, i, (pid_t) event->entries[i].pid);
+		threads->map[i].comm = strndup(event->entries[i].comm, 16);
+	}
+
+	atomic_set(&threads->refcnt, 1);
+}
+
+struct thread_map *thread_map__new_event(struct thread_map_event *event)
+{
+	struct thread_map *threads;
+
+	threads = thread_map__alloc(event->nr);
+	if (threads)
+		thread_map__copy_event(threads, event);
+
+	return threads;
+}
diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h
index af679d8..85e4c7c 100644
--- a/tools/perf/util/thread_map.h
+++ b/tools/perf/util/thread_map.h
@@ -16,11 +16,14 @@
 	struct thread_map_data map[];
 };
 
+struct thread_map_event;
+
 struct thread_map *thread_map__new_dummy(void);
 struct thread_map *thread_map__new_by_pid(pid_t pid);
 struct thread_map *thread_map__new_by_tid(pid_t tid);
 struct thread_map *thread_map__new_by_uid(uid_t uid);
 struct thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid);
+struct thread_map *thread_map__new_event(struct thread_map_event *event);
 
 struct thread_map *thread_map__get(struct thread_map *map);
 void thread_map__put(struct thread_map *map);
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index cab8cc2..55de4cf 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -50,12 +50,18 @@
 			throttle,
 			unthrottle;
 	event_attr_op	attr;
+	event_attr_op	event_update;
 	event_op2	tracing_data;
 	event_oe	finished_round;
 	event_op2	build_id,
 			id_index,
 			auxtrace_info,
-			auxtrace_error;
+			auxtrace_error,
+			thread_map,
+			cpu_map,
+			stat_config,
+			stat,
+			stat_round;
 	event_op3	auxtrace;
 	bool		ordered_events;
 	bool		ordering_requires_timestamps;
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index b85ee55..bce5b1d 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -65,6 +65,7 @@
 struct addr_location;
 
 struct perf_session;
+struct perf_stat_config;
 
 struct scripting_ops {
 	const char *name;
@@ -75,6 +76,9 @@
 			       struct perf_sample *sample,
 			       struct perf_evsel *evsel,
 			       struct addr_location *al);
+	void (*process_stat)(struct perf_stat_config *config,
+			     struct perf_evsel *evsel, u64 tstamp);
+	void (*process_stat_interval)(u64 tstamp);
 	int (*generate_script) (struct pevent *pevent, const char *outfile);
 };
 
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 2dcfe9a..cf5e250 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -11,6 +11,7 @@
 #include <linux/types.h>
 #include "event.h"
 #include "perf_regs.h"
+#include "callchain.h"
 
 static char *debuginfo_path;
 
@@ -52,25 +53,28 @@
 	return __report_module(&al, ip, ui);
 }
 
+/*
+ * Store all entries within entries array,
+ * we will process it after we finish unwind.
+ */
 static int entry(u64 ip, struct unwind_info *ui)
 
 {
-	struct unwind_entry e;
+	struct unwind_entry *e = &ui->entries[ui->idx++];
 	struct addr_location al;
 
 	if (__report_module(&al, ip, ui))
 		return -1;
 
-	e.ip  = ip;
-	e.map = al.map;
-	e.sym = al.sym;
+	e->ip  = ip;
+	e->map = al.map;
+	e->sym = al.sym;
 
 	pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n",
 		 al.sym ? al.sym->name : "''",
 		 ip,
 		 al.map ? al.map->map_ip(al.map, ip) : (u64) 0);
-
-	return ui->cb(&e, ui->arg);
+	return 0;
 }
 
 static pid_t next_thread(Dwfl *dwfl, void *arg, void **thread_argp)
@@ -92,6 +96,16 @@
 	thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
 			      MAP__FUNCTION, addr, &al);
 	if (!al.map) {
+		/*
+		 * We've seen cases (softice) where DWARF unwinder went
+		 * through non executable mmaps, which we need to lookup
+		 * in MAP__VARIABLE tree.
+		 */
+		thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
+				      MAP__VARIABLE, addr, &al);
+	}
+
+	if (!al.map) {
 		pr_debug("unwind: no map for %lx\n", (unsigned long)addr);
 		return -1;
 	}
@@ -168,7 +182,7 @@
 			struct perf_sample *data,
 			int max_stack)
 {
-	struct unwind_info ui = {
+	struct unwind_info *ui, ui_buf = {
 		.sample		= data,
 		.thread		= thread,
 		.machine	= thread->mg->machine,
@@ -177,35 +191,54 @@
 		.max_stack	= max_stack,
 	};
 	Dwarf_Word ip;
-	int err = -EINVAL;
+	int err = -EINVAL, i;
 
 	if (!data->user_regs.regs)
 		return -EINVAL;
 
-	ui.dwfl = dwfl_begin(&offline_callbacks);
-	if (!ui.dwfl)
+	ui = zalloc(sizeof(ui_buf) + sizeof(ui_buf.entries[0]) * max_stack);
+	if (!ui)
+		return -ENOMEM;
+
+	*ui = ui_buf;
+
+	ui->dwfl = dwfl_begin(&offline_callbacks);
+	if (!ui->dwfl)
 		goto out;
 
 	err = perf_reg_value(&ip, &data->user_regs, PERF_REG_IP);
 	if (err)
 		goto out;
 
-	err = report_module(ip, &ui);
+	err = report_module(ip, ui);
 	if (err)
 		goto out;
 
-	if (!dwfl_attach_state(ui.dwfl, EM_NONE, thread->tid, &callbacks, &ui))
+	if (!dwfl_attach_state(ui->dwfl, EM_NONE, thread->tid, &callbacks, ui))
 		goto out;
 
-	err = dwfl_getthread_frames(ui.dwfl, thread->tid, frame_callback, &ui);
+	err = dwfl_getthread_frames(ui->dwfl, thread->tid, frame_callback, ui);
 
-	if (err && !ui.max_stack)
+	if (err && !ui->max_stack)
 		err = 0;
 
+	/*
+	 * Display what we got based on the order setup.
+	 */
+	for (i = 0; i < ui->idx && !err; i++) {
+		int j = i;
+
+		if (callchain_param.order == ORDER_CALLER)
+			j = ui->idx - i - 1;
+
+		err = ui->entries[j].ip ? ui->cb(&ui->entries[j], ui->arg) : 0;
+	}
+
  out:
 	if (err)
 		pr_debug("unwind: failed with '%s'\n", dwfl_errmsg(-1));
 
-	dwfl_end(ui.dwfl);
+	dwfl_end(ui->dwfl);
+	free(ui);
 	return 0;
 }
diff --git a/tools/perf/util/unwind-libdw.h b/tools/perf/util/unwind-libdw.h
index 417a142..5832866 100644
--- a/tools/perf/util/unwind-libdw.h
+++ b/tools/perf/util/unwind-libdw.h
@@ -16,6 +16,8 @@
 	unwind_entry_cb_t	cb;
 	void			*arg;
 	int			max_stack;
+	int			idx;
+	struct unwind_entry	entries[];
 };
 
 #endif /* __PERF_UNWIND_LIBDW_H */
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index c83832b..ee7e372 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -319,6 +319,15 @@
 
 	thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
 			      MAP__FUNCTION, ip, &al);
+	if (!al.map) {
+		/*
+		 * We've seen cases (softice) where DWARF unwinder went
+		 * through non executable mmaps, which we need to lookup
+		 * in MAP__VARIABLE tree.
+		 */
+		thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
+				      MAP__VARIABLE, ip, &al);
+	}
 	return al.map;
 }
 
@@ -416,20 +425,19 @@
 static int access_dso_mem(struct unwind_info *ui, unw_word_t addr,
 			  unw_word_t *data)
 {
-	struct addr_location al;
+	struct map *map;
 	ssize_t size;
 
-	thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
-			      MAP__FUNCTION, addr, &al);
-	if (!al.map) {
+	map = find_map(addr, ui);
+	if (!map) {
 		pr_debug("unwind: no map for %lx\n", (unsigned long)addr);
 		return -1;
 	}
 
-	if (!al.map->dso)
+	if (!map->dso)
 		return -1;
 
-	size = dso__data_read_addr(al.map->dso, al.map, ui->machine,
+	size = dso__data_read_addr(map->dso, map, ui->machine,
 				   addr, (u8 *) data, sizeof(*data));
 
 	return !(size == sizeof(*data));
@@ -614,23 +622,48 @@
 static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
 		       void *arg, int max_stack)
 {
+	u64 val;
+	unw_word_t ips[max_stack];
 	unw_addr_space_t addr_space;
 	unw_cursor_t c;
-	int ret;
+	int ret, i = 0;
 
-	addr_space = thread__priv(ui->thread);
-	if (addr_space == NULL)
-		return -1;
-
-	ret = unw_init_remote(&c, addr_space, ui);
+	ret = perf_reg_value(&val, &ui->sample->user_regs, PERF_REG_IP);
 	if (ret)
-		display_error(ret);
+		return ret;
 
-	while (!ret && (unw_step(&c) > 0) && max_stack--) {
-		unw_word_t ip;
+	ips[i++] = (unw_word_t) val;
 
-		unw_get_reg(&c, UNW_REG_IP, &ip);
-		ret = ip ? entry(ip, ui->thread, cb, arg) : 0;
+	/*
+	 * If we need more than one entry, do the DWARF
+	 * unwind itself.
+	 */
+	if (max_stack - 1 > 0) {
+		addr_space = thread__priv(ui->thread);
+		if (addr_space == NULL)
+			return -1;
+
+		ret = unw_init_remote(&c, addr_space, ui);
+		if (ret)
+			display_error(ret);
+
+		while (!ret && (unw_step(&c) > 0) && i < max_stack) {
+			unw_get_reg(&c, UNW_REG_IP, &ips[i]);
+			++i;
+		}
+
+		max_stack = i;
+	}
+
+	/*
+	 * Display what we got based on the order setup.
+	 */
+	for (i = 0; i < max_stack && !ret; i++) {
+		int j = i;
+
+		if (callchain_param.order == ORDER_CALLER)
+			j = max_stack - i - 1;
+		ret = ips[j] ? entry(ips[j], ui->thread, cb, arg) : 0;
 	}
 
 	return ret;
@@ -640,24 +673,17 @@
 			struct thread *thread,
 			struct perf_sample *data, int max_stack)
 {
-	u64 ip;
 	struct unwind_info ui = {
 		.sample       = data,
 		.thread       = thread,
 		.machine      = thread->mg->machine,
 	};
-	int ret;
 
 	if (!data->user_regs.regs)
 		return -EINVAL;
 
-	ret = perf_reg_value(&ip, &data->user_regs, PERF_REG_IP);
-	if (ret)
-		return ret;
+	if (max_stack <= 0)
+		return -EINVAL;
 
-	ret = entry(ip, thread, cb, arg);
-	if (ret)
-		return -ENOMEM;
-
-	return --max_stack > 0 ? get_entries(&ui, cb, arg, max_stack) : 0;
+	return get_entries(&ui, cb, arg, max_stack);
 }
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 47b1e36..88b8f8d 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -16,12 +16,15 @@
 #include <linux/kernel.h>
 #include <unistd.h>
 #include "callchain.h"
+#include "strlist.h"
+#include <subcmd/exec-cmd.h>
 
 struct callchain_param	callchain_param = {
 	.mode	= CHAIN_GRAPH_ABS,
 	.min_percent = 0.5,
 	.order  = ORDER_CALLEE,
-	.key	= CCKEY_FUNCTION
+	.key	= CCKEY_FUNCTION,
+	.value	= CCVAL_PERCENT,
 };
 
 /*
@@ -351,41 +354,8 @@
 {
 	psignal(sig, "perf");
 	dump_stack();
-	exit(sig);
-}
-
-void get_term_dimensions(struct winsize *ws)
-{
-	char *s = getenv("LINES");
-
-	if (s != NULL) {
-		ws->ws_row = atoi(s);
-		s = getenv("COLUMNS");
-		if (s != NULL) {
-			ws->ws_col = atoi(s);
-			if (ws->ws_row && ws->ws_col)
-				return;
-		}
-	}
-#ifdef TIOCGWINSZ
-	if (ioctl(1, TIOCGWINSZ, ws) == 0 &&
-	    ws->ws_row && ws->ws_col)
-		return;
-#endif
-	ws->ws_row = 25;
-	ws->ws_col = 80;
-}
-
-void set_term_quiet_input(struct termios *old)
-{
-	struct termios tc;
-
-	tcgetattr(0, old);
-	tc = *old;
-	tc.c_lflag &= ~(ICANON | ECHO);
-	tc.c_cc[VMIN] = 0;
-	tc.c_cc[VTIME] = 0;
-	tcsetattr(0, TCSANOW, &tc);
+	signal(sig, SIG_DFL);
+	raise(sig);
 }
 
 int parse_nsec_time(const char *str, u64 *ptime)
@@ -695,3 +665,28 @@
 		*puint = (version << 16) + (patchlevel << 8) + sublevel;
 	return 0;
 }
+
+const char *perf_tip(const char *dirpath)
+{
+	struct strlist *tips;
+	struct str_node *node;
+	char *tip = NULL;
+	struct strlist_config conf = {
+		.dirname = system_path(dirpath) ,
+	};
+
+	tips = strlist__new("tips.txt", &conf);
+	if (tips == NULL || strlist__nr_entries(tips) == 1) {
+		tip = (char *)"Cannot find tips.txt file";
+		goto out;
+	}
+
+	node = strlist__entry(tips, random() % strlist__nr_entries(tips));
+	if (asprintf(&tip, "Tip: %s", node->s) < 0)
+		tip = (char *)"Tip: get more memory! ;-)";
+
+out:
+	strlist__delete(tips);
+
+	return tip;
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index dcc6590..fe915e6 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -53,6 +53,7 @@
 #include <stdlib.h>
 #include <stdarg.h>
 #include <string.h>
+#include <term.h>
 #include <errno.h>
 #include <limits.h>
 #include <sys/param.h>
@@ -150,12 +151,6 @@
 extern int prefixcmp(const char *str, const char *prefix);
 extern void set_buildid_dir(const char *dir);
 
-static inline const char *skip_prefix(const char *str, const char *prefix)
-{
-	size_t len = strlen(prefix);
-	return strncmp(str, prefix, len) ? NULL : str + len;
-}
-
 #ifdef __GLIBC_PREREQ
 #if __GLIBC_PREREQ(2, 1)
 #define HAVE_STRCHRNUL
@@ -186,14 +181,6 @@
 
 #define zfree(ptr) ({ free(*ptr); *ptr = NULL; })
 
-static inline int has_extension(const char *filename, const char *ext)
-{
-	size_t len = strlen(filename);
-	size_t extlen = strlen(ext);
-
-	return len > extlen && !memcmp(filename + len - extlen, ext, extlen);
-}
-
 /* Sane ctype - no locale, and works with signed chars */
 #undef isascii
 #undef isspace
@@ -282,9 +269,6 @@
 extern unsigned int page_size;
 extern int cacheline_size;
 
-void get_term_dimensions(struct winsize *ws);
-void set_term_quiet_input(struct termios *old);
-
 struct parse_tag {
 	char tag;
 	int mult;
@@ -358,4 +342,6 @@
 #define KVER_FMT	"%d.%d.%d"
 #define KVER_PARAM(x)	KVER_VERSION(x), KVER_PATCHLEVEL(x), KVER_SUBLEVEL(x)
 
+const char *perf_tip(const char *dirpath);
+
 #endif /* GIT_COMPAT_UTIL_H */
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
index 5236e07..0f80eef 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
@@ -38,8 +38,6 @@
 #
 # Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
 
-grace=120
-
 T=/tmp/kvm-test-1-run.sh.$$
 trap 'rm -rf $T' 0
 touch $T
@@ -152,7 +150,7 @@
 qemu_args="`specify_qemu_cpus "$QEMU" "$qemu_args" "$cpu_count"`"
 
 # Generate architecture-specific and interaction-specific qemu arguments
-qemu_args="$qemu_args `identify_qemu_args "$QEMU" "$builddir/console.log"`"
+qemu_args="$qemu_args `identify_qemu_args "$QEMU" "$resdir/console.log"`"
 
 # Generate qemu -append arguments
 qemu_append="`identify_qemu_append "$QEMU"`"
@@ -168,7 +166,7 @@
 	touch $resdir/buildonly
 	exit 0
 fi
-echo "NOTE: $QEMU either did not run or was interactive" > $builddir/console.log
+echo "NOTE: $QEMU either did not run or was interactive" > $resdir/console.log
 echo $QEMU $qemu_args -m 512 -kernel $resdir/bzImage -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd
 ( $QEMU $qemu_args -m 512 -kernel $resdir/bzImage -append "$qemu_append $boot_args"; echo $? > $resdir/qemu-retval ) &
 qemu_pid=$!
@@ -214,7 +212,7 @@
 		else
 			break
 		fi
-		if test $kruntime -ge $((seconds + grace))
+		if test $kruntime -ge $((seconds + $TORTURE_SHUTDOWN_GRACE))
 		then
 			echo "!!! PID $qemu_pid hung at $kruntime vs. $seconds seconds" >> $resdir/Warnings 2>&1
 			kill -KILL $qemu_pid
@@ -224,6 +222,5 @@
 	done
 fi
 
-cp $builddir/console.log $resdir
 parse-torture.sh $resdir/console.log $title
 parse-console.sh $resdir/console.log $title
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index f648360..4a43176 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -42,6 +42,7 @@
 TORTURE_BOOT_IMAGE=""
 TORTURE_INITRD="$KVM/initrd"; export TORTURE_INITRD
 TORTURE_KMAKE_ARG=""
+TORTURE_SHUTDOWN_GRACE=180
 TORTURE_SUITE=rcu
 resdir=""
 configs=""
@@ -149,6 +150,11 @@
 		resdir=$2
 		shift
 		;;
+	--shutdown-grace)
+		checkarg --shutdown-grace "(seconds)" "$#" "$2" '^[0-9]*$' '^error'
+		TORTURE_SHUTDOWN_GRACE=$2
+		shift
+		;;
 	--torture)
 		checkarg --torture "(suite name)" "$#" "$2" '^\(lock\|rcu\)$' '^--'
 		TORTURE_SUITE=$2
@@ -266,6 +272,7 @@
 TORTURE_QEMU_CMD="$TORTURE_QEMU_CMD"; export TORTURE_QEMU_CMD
 TORTURE_QEMU_INTERACTIVE="$TORTURE_QEMU_INTERACTIVE"; export TORTURE_QEMU_INTERACTIVE
 TORTURE_QEMU_MAC="$TORTURE_QEMU_MAC"; export TORTURE_QEMU_MAC
+TORTURE_SHUTDOWN_GRACE="$TORTURE_SHUTDOWN_GRACE"; export TORTURE_SHUTDOWN_GRACE
 TORTURE_SUITE="$TORTURE_SUITE"; export TORTURE_SUITE
 if ! test -e $resdir
 then
@@ -307,10 +314,10 @@
 }
 
 # Dump out the scripting required to run one test batch.
-function dump(first, pastlast)
+function dump(first, pastlast, batchnum)
 {
-	print "echo ----Start batch: `date`";
-	print "echo ----Start batch: `date` >> " rd "/log";
+	print "echo ----Start batch " batchnum ": `date`";
+	print "echo ----Start batch " batchnum ": `date` >> " rd "/log";
 	jn=1
 	for (j = first; j < pastlast; j++) {
 		builddir=KVM "/b" jn
@@ -371,25 +378,28 @@
 	njobs = i;
 	nc = ncpus;
 	first = 0;
+	batchnum = 1;
 
 	# Each pass through the following loop considers one test.
 	for (i = 0; i < njobs; i++) {
 		if (ncpus == 0) {
 			# Sequential test specified, each test its own batch.
-			dump(i, i + 1);
+			dump(i, i + 1, batchnum);
 			first = i;
+			batchnum++;
 		} else if (nc < cpus[i] && i != 0) {
 			# Out of CPUs, dump out a batch.
-			dump(first, i);
+			dump(first, i, batchnum);
 			first = i;
 			nc = ncpus;
+			batchnum++;
 		}
 		# Account for the CPUs needed by the current test.
 		nc -= cpus[i];
 	}
 	# Dump the last batch.
 	if (ncpus != 0)
-		dump(first, i);
+		dump(first, i, batchnum);
 }' >> $T/script
 
 cat << ___EOF___ >> $T/script
diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh
index d8f35cf..844787a 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-console.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh
@@ -24,9 +24,6 @@
 #
 # Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
 
-T=/tmp/abat-chk-badness.sh.$$
-trap 'rm -f $T' 0
-
 file="$1"
 title="$2"
 
@@ -36,9 +33,41 @@
 then
 	print_warning Console output contains nul bytes, old qemu still running?
 fi
-egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|Stall ended before state dump start' < $file | grep -v 'ODEBUG: ' | grep -v 'Warning: unable to open an initial console' > $T
-if test -s $T
+egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|detected stalls on CPUs/tasks:|Stall ended before state dump start' < $file | grep -v 'ODEBUG: ' | grep -v 'Warning: unable to open an initial console' > $1.diags
+if test -s $1.diags
 then
 	print_warning Assertion failure in $file $title
-	cat $T
+	# cat $1.diags
+	summary=""
+	n_badness=`grep -c Badness $1`
+	if test "$n_badness" -ne 0
+	then
+		summary="$summary  Badness: $n_badness"
+	fi
+	n_warn=`grep -v 'Warning: unable to open an initial console' $1 | egrep -c 'WARNING:|Warn'`
+	if test "$n_warn" -ne 0
+	then
+		summary="$summary  Warnings: $n_warn"
+	fi
+	n_bugs=`egrep -c 'BUG|Oops:' $1`
+	if test "$n_bugs" -ne 0
+	then
+		summary="$summary  Bugs: $n_bugs"
+	fi
+	n_calltrace=`grep -c 'Call Trace:' $1`
+	if test "$n_calltrace" -ne 0
+	then
+		summary="$summary  Call Traces: $n_calltrace"
+	fi
+	n_lockdep=`grep -c =========== $1`
+	if test "$n_badness" -ne 0
+	then
+		summary="$summary  lockdep: $n_badness"
+	fi
+	n_stalls=`egrep -c 'detected stalls on CPUs/tasks:|Stall ended before state dump start' $1`
+	if test "$n_stalls" -ne 0
+	then
+		summary="$summary  Stalls: $n_stalls"
+	fi
+	print_warning Summary: $summary
 fi
diff --git a/tools/testing/selftests/rcutorture/doc/TINY_RCU.txt b/tools/testing/selftests/rcutorture/doc/TINY_RCU.txt
index 9ef33a7..24396ae 100644
--- a/tools/testing/selftests/rcutorture/doc/TINY_RCU.txt
+++ b/tools/testing/selftests/rcutorture/doc/TINY_RCU.txt
@@ -20,7 +20,6 @@
 
 CONFIG_NO_HZ_FULL_SYSIDLE
 CONFIG_RCU_NOCB_CPU
-CONFIG_RCU_USER_QS
 
 	Meaningless for TINY_RCU.
 
diff --git a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
index 657f3a0..4e2b189 100644
--- a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
+++ b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
@@ -72,10 +72,6 @@
 
 	Always used in KVM testing.
 
-CONFIG_RCU_USER_QS
-
-	Redundant with CONFIG_NO_HZ_FULL.
-
 CONFIG_PREEMPT_RCU
 CONFIG_TREE_RCU
 
diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index 882fe83..b9453b8 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -1246,11 +1246,24 @@
 # error "Do not know how to find your architecture's registers and syscalls"
 #endif
 
+/* Use PTRACE_GETREGS and PTRACE_SETREGS when available. This is useful for
+ * architectures without HAVE_ARCH_TRACEHOOK (e.g. User-mode Linux).
+ */
+#if defined(__x86_64__) || defined(__i386__)
+#define HAVE_GETREGS
+#endif
+
 /* Architecture-specific syscall fetching routine. */
 int get_syscall(struct __test_metadata *_metadata, pid_t tracee)
 {
-	struct iovec iov;
 	ARCH_REGS regs;
+#ifdef HAVE_GETREGS
+	EXPECT_EQ(0, ptrace(PTRACE_GETREGS, tracee, 0, &regs)) {
+		TH_LOG("PTRACE_GETREGS failed");
+		return -1;
+	}
+#else
+	struct iovec iov;
 
 	iov.iov_base = &regs;
 	iov.iov_len = sizeof(regs);
@@ -1258,6 +1271,7 @@
 		TH_LOG("PTRACE_GETREGSET failed");
 		return -1;
 	}
+#endif
 
 	return regs.SYSCALL_NUM;
 }
@@ -1266,13 +1280,16 @@
 void change_syscall(struct __test_metadata *_metadata,
 		    pid_t tracee, int syscall)
 {
-	struct iovec iov;
 	int ret;
 	ARCH_REGS regs;
-
+#ifdef HAVE_GETREGS
+	ret = ptrace(PTRACE_GETREGS, tracee, 0, &regs);
+#else
+	struct iovec iov;
 	iov.iov_base = &regs;
 	iov.iov_len = sizeof(regs);
 	ret = ptrace(PTRACE_GETREGSET, tracee, NT_PRSTATUS, &iov);
+#endif
 	EXPECT_EQ(0, ret);
 
 #if defined(__x86_64__) || defined(__i386__) || defined(__powerpc__) || \
@@ -1312,9 +1329,13 @@
 	if (syscall == -1)
 		regs.SYSCALL_RET = 1;
 
+#ifdef HAVE_GETREGS
+	ret = ptrace(PTRACE_SETREGS, tracee, 0, &regs);
+#else
 	iov.iov_base = &regs;
 	iov.iov_len = sizeof(regs);
 	ret = ptrace(PTRACE_SETREGSET, tracee, NT_PRSTATUS, &iov);
+#endif
 	EXPECT_EQ(0, ret);
 }
 
diff --git a/tools/testing/selftests/timers/clocksource-switch.c b/tools/testing/selftests/timers/clocksource-switch.c
index 627ec74..fd88e30 100644
--- a/tools/testing/selftests/timers/clocksource-switch.c
+++ b/tools/testing/selftests/timers/clocksource-switch.c
@@ -97,7 +97,7 @@
 int change_clocksource(char *clocksource)
 {
 	int fd;
-	size_t size;
+	ssize_t size;
 
 	fd = open("/sys/devices/system/clocksource/clocksource0/current_clocksource", O_WRONLY);
 
diff --git a/virt/kvm/arm/vgic-v3.c b/virt/kvm/arm/vgic-v3.c
index 487d635..453eafd 100644
--- a/virt/kvm/arm/vgic-v3.c
+++ b/virt/kvm/arm/vgic-v3.c
@@ -28,6 +28,7 @@
 
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_arm.h>
+#include <asm/kvm_asm.h>
 #include <asm/kvm_mmu.h>
 
 /* These are for GICv2 emulation only */
@@ -36,18 +37,12 @@
 #define GICH_LR_PHYSID_CPUID		(7UL << GICH_LR_PHYSID_CPUID_SHIFT)
 #define ICH_LR_VIRTUALID_MASK		(BIT_ULL(32) - 1)
 
-/*
- * LRs are stored in reverse order in memory. make sure we index them
- * correctly.
- */
-#define LR_INDEX(lr)			(VGIC_V3_MAX_LRS - 1 - lr)
-
 static u32 ich_vtr_el2;
 
 static struct vgic_lr vgic_v3_get_lr(const struct kvm_vcpu *vcpu, int lr)
 {
 	struct vgic_lr lr_desc;
-	u64 val = vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[LR_INDEX(lr)];
+	u64 val = vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[VGIC_V3_LR_INDEX(lr)];
 
 	if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3)
 		lr_desc.irq = val & ICH_LR_VIRTUALID_MASK;
@@ -111,7 +106,7 @@
 		lr_val |= ((u64)lr_desc.hwirq) << ICH_LR_PHYS_ID_SHIFT;
 	}
 
-	vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[LR_INDEX(lr)] = lr_val;
+	vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[VGIC_V3_LR_INDEX(lr)] = lr_val;
 
 	if (!(lr_desc.state & LR_STATE_MASK))
 		vcpu->arch.vgic_cpu.vgic_v3.vgic_elrsr |= (1U << lr);
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index 7a2f449..043032c 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -878,7 +878,7 @@
 				       true);
 }
 
-struct kvm_io_device_ops vgic_io_ops = {
+static struct kvm_io_device_ops vgic_io_ops = {
 	.read	= vgic_handle_mmio_read,
 	.write	= vgic_handle_mmio_write,
 };
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index 77d42be..3531599 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -57,8 +57,7 @@
 
 void kvm_async_pf_deinit(void)
 {
-	if (async_pf_cache)
-		kmem_cache_destroy(async_pf_cache);
+	kmem_cache_destroy(async_pf_cache);
 	async_pf_cache = NULL;
 }
 
diff --git a/virt/kvm/irqchip.c b/virt/kvm/irqchip.c
index f0b08a2..fe84e1a 100644
--- a/virt/kvm/irqchip.c
+++ b/virt/kvm/irqchip.c
@@ -166,6 +166,10 @@
 	return r;
 }
 
+void __attribute__((weak)) kvm_arch_irq_routing_update(struct kvm *kvm)
+{
+}
+
 int kvm_set_irq_routing(struct kvm *kvm,
 			const struct kvm_irq_routing_entry *ue,
 			unsigned nr,
@@ -219,9 +223,10 @@
 	old = kvm->irq_routing;
 	rcu_assign_pointer(kvm->irq_routing, new);
 	kvm_irq_routing_update(kvm);
+	kvm_arch_irq_routing_update(kvm);
 	mutex_unlock(&kvm->irq_lock);
 
-	kvm_arch_irq_routing_update(kvm);
+	kvm_arch_post_irq_routing_update(kvm);
 
 	synchronize_srcu_expedited(&kvm->irq_srcu);
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 484079e..314c777 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -206,16 +206,6 @@
 	kvm_make_all_cpus_request(kvm, KVM_REQ_MMU_RELOAD);
 }
 
-void kvm_make_mclock_inprogress_request(struct kvm *kvm)
-{
-	kvm_make_all_cpus_request(kvm, KVM_REQ_MCLOCK_INPROGRESS);
-}
-
-void kvm_make_scan_ioapic_request(struct kvm *kvm)
-{
-	kvm_make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC);
-}
-
 int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
 {
 	struct page *page;
@@ -1164,15 +1154,15 @@
 	return __gfn_to_memslot(kvm_vcpu_memslots(vcpu), gfn);
 }
 
-int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn)
+bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn)
 {
 	struct kvm_memory_slot *memslot = gfn_to_memslot(kvm, gfn);
 
 	if (!memslot || memslot->id >= KVM_USER_MEM_SLOTS ||
 	      memslot->flags & KVM_MEMSLOT_INVALID)
-		return 0;
+		return false;
 
-	return 1;
+	return true;
 }
 EXPORT_SYMBOL_GPL(kvm_is_visible_gfn);
 
@@ -2257,7 +2247,7 @@
 static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
 {
 	int r;
-	struct kvm_vcpu *vcpu, *v;
+	struct kvm_vcpu *vcpu;
 
 	if (id >= KVM_MAX_VCPUS)
 		return -EINVAL;
@@ -2281,12 +2271,10 @@
 		r = -EINVAL;
 		goto unlock_vcpu_destroy;
 	}
-
-	kvm_for_each_vcpu(r, v, kvm)
-		if (v->vcpu_id == id) {
-			r = -EEXIST;
-			goto unlock_vcpu_destroy;
-		}
+	if (kvm_get_vcpu_by_id(kvm, id)) {
+		r = -EEXIST;
+		goto unlock_vcpu_destroy;
+	}
 
 	BUG_ON(kvm->vcpus[atomic_read(&kvm->online_vcpus)]);
 
@@ -3449,10 +3437,9 @@
 		goto out;
 
 	for (p = debugfs_entries; p->name; ++p) {
-		p->dentry = debugfs_create_file(p->name, 0444, kvm_debugfs_dir,
-						(void *)(long)p->offset,
-						stat_fops[p->kind]);
-		if (p->dentry == NULL)
+		if (!debugfs_create_file(p->name, 0444, kvm_debugfs_dir,
+					 (void *)(long)p->offset,
+					 stat_fops[p->kind]))
 			goto out_dir;
 	}
 
@@ -3464,15 +3451,6 @@
 	return r;
 }
 
-static void kvm_exit_debug(void)
-{
-	struct kvm_stats_debugfs_item *p;
-
-	for (p = debugfs_entries; p->name; ++p)
-		debugfs_remove(p->dentry);
-	debugfs_remove(kvm_debugfs_dir);
-}
-
 static int kvm_suspend(void)
 {
 	if (kvm_usage_count)
@@ -3630,7 +3608,7 @@
 
 void kvm_exit(void)
 {
-	kvm_exit_debug();
+	debugfs_remove_recursive(kvm_debugfs_dir);
 	misc_deregister(&kvm_dev);
 	kmem_cache_destroy(kvm_vcpu_cache);
 	kvm_async_pf_deinit();