Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Pull networking fixes from David Miller:
 "One last pull request before heading to Vancouver for LPC, here we have:

   1) Don't forget to free VSI contexts during ice driver unload, from
      Victor Raj.

   2) Don't forget napi delete calls during device remove in ice driver,
      from Dave Ertman.

   3) Don't request VLAN tag insertion of ibmvnic device when SKB
      doesn't have VLAN tags at all.

   4) IPV4 frag handling code has to accomodate the situation where two
      threads try to insert the same fragment into the hash table at the
      same time. From Eric Dumazet.

   5) Relatedly, don't flow separate on protocol ports for fragmented
      frames, also from Eric Dumazet.

   6) Memory leaks in qed driver, from Denis Bolotin.

   7) Correct valid MTU range in smsc95xx driver, from Stefan Wahren.

   8) Validate cls_flower nested policies properly, from Jakub Kicinski.

   9) Clearing of stats counters in mc88e6xxx driver doesn't retain
      important bits in the G1_STATS_OP register causing the chip to
      hang. Fix from Andrew Lunn"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (41 commits)
  act_mirred: clear skb->tstamp on redirect
  net: dsa: mv88e6xxx: Fix clearing of stats counters
  tipc: fix link re-establish failure
  net: sched: cls_flower: validate nested enc_opts_policy to avoid warning
  net: mvneta: correct typo
  flow_dissector: do not dissect l4 ports for fragments
  net: qualcomm: rmnet: Fix incorrect assignment of real_dev
  net: aquantia: allow rx checksum offload configuration
  net: aquantia: invalid checksumm offload implementation
  net: aquantia: fixed enable unicast on 32 macvlan
  net: aquantia: fix potential IOMMU fault after driver unbind
  net: aquantia: synchronized flow control between mac/phy
  net: smsc95xx: Fix MTU range
  net: stmmac: Fix RX packet size > 8191
  qed: Fix potential memory corruption
  qed: Fix SPQ entries not returned to pool in error flows
  qed: Fix blocking/unlimited SPQ entries leak
  qed: Fix memory/entry leak in qed_init_sp_request()
  inet: frags: better deal with smp races
  net: hns3: bugfix for not checking return value
  ...
diff --git a/.mailmap b/.mailmap
index a76be45f..28fecaf 100644
--- a/.mailmap
+++ b/.mailmap
@@ -159,6 +159,7 @@
 Peter Oruba <peter.oruba@amd.com>
 Pratyush Anand <pratyush.anand@gmail.com> <pratyush.anand@st.com>
 Praveen BP <praveenbp@ti.com>
+Punit Agrawal <punitagrawal@gmail.com> <punit.agrawal@arm.com>
 Qais Yousef <qsyousef@gmail.com> <qais.yousef@imgtec.com>
 Oleksij Rempel <linux@rempel-privat.de> <bug-track@fisher-privat.net>
 Oleksij Rempel <linux@rempel-privat.de> <external.Oleksij.Rempel@de.bosch.com>
diff --git a/Documentation/ABI/testing/sysfs-class-led-trigger-pattern b/Documentation/ABI/testing/sysfs-class-led-trigger-pattern
index fb3d1e0..1e5d172 100644
--- a/Documentation/ABI/testing/sysfs-class-led-trigger-pattern
+++ b/Documentation/ABI/testing/sysfs-class-led-trigger-pattern
@@ -37,8 +37,8 @@
 		  0-|   /             \/             \/
 		    +---0----1----2----3----4----5----6------------> time (s)
 
-		2. To make the LED go instantly from one brigntess value to another,
-		we should use use zero-time lengths (the brightness must be same as
+		2. To make the LED go instantly from one brightness value to another,
+		we should use zero-time lengths (the brightness must be same as
 		the previous tuple's). So the format should be:
 		"brightness_1 duration_1 brightness_1 0 brightness_2 duration_2
 		brightness_2 0 ...". For example:
diff --git a/Documentation/devicetree/bindings/arm/shmobile.txt b/Documentation/devicetree/bindings/arm/shmobile.txt
index f5e0f82..58c4256 100644
--- a/Documentation/devicetree/bindings/arm/shmobile.txt
+++ b/Documentation/devicetree/bindings/arm/shmobile.txt
@@ -27,7 +27,7 @@
     compatible = "renesas,r8a77470"
   - RZ/G2M (R8A774A1)
     compatible = "renesas,r8a774a1"
-  - RZ/G2E (RA8774C0)
+  - RZ/G2E (R8A774C0)
     compatible = "renesas,r8a774c0"
   - R-Car M1A (R8A77781)
     compatible = "renesas,r8a7778"
diff --git a/Documentation/devicetree/bindings/i2c/i2c-omap.txt b/Documentation/devicetree/bindings/i2c/i2c-omap.txt
index 7e49839..4b90ba9f 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-omap.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-omap.txt
@@ -1,8 +1,12 @@
 I2C for OMAP platforms
 
 Required properties :
-- compatible : Must be "ti,omap2420-i2c", "ti,omap2430-i2c", "ti,omap3-i2c"
-  or "ti,omap4-i2c"
+- compatible : Must be
+	"ti,omap2420-i2c" for OMAP2420 SoCs
+	"ti,omap2430-i2c" for OMAP2430 SoCs
+	"ti,omap3-i2c" for OMAP3 SoCs
+	"ti,omap4-i2c" for OMAP4+ SoCs
+	"ti,am654-i2c", "ti,omap4-i2c" for AM654 SoCs
 - ti,hwmods : Must be "i2c<n>", n being the instance number (1-based)
 - #address-cells = <1>;
 - #size-cells = <0>;
diff --git a/Documentation/i2c/busses/i2c-nvidia-gpu b/Documentation/i2c/busses/i2c-nvidia-gpu
new file mode 100644
index 0000000..31884d2
--- /dev/null
+++ b/Documentation/i2c/busses/i2c-nvidia-gpu
@@ -0,0 +1,18 @@
+Kernel driver i2c-nvidia-gpu
+
+Datasheet: not publicly available.
+
+Authors:
+	Ajay Gupta <ajayg@nvidia.com>
+
+Description
+-----------
+
+i2c-nvidia-gpu is a driver for I2C controller included in NVIDIA Turing
+and later GPUs and it is used to communicate with Type-C controller on GPUs.
+
+If your 'lspci -v' listing shows something like the following,
+
+01:00.3 Serial bus controller [0c80]: NVIDIA Corporation Device 1ad9 (rev a1)
+
+then this driver should support the I2C controller of your GPU.
diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt
index 73aaaa3d..804f942 100644
--- a/Documentation/x86/x86_64/mm.txt
+++ b/Documentation/x86/x86_64/mm.txt
@@ -34,23 +34,24 @@
 ____________________________________________________________|___________________________________________________________
                   |            |                  |         |
  ffff800000000000 | -128    TB | ffff87ffffffffff |    8 TB | ... guard hole, also reserved for hypervisor
- ffff880000000000 | -120    TB | ffffc7ffffffffff |   64 TB | direct mapping of all physical memory (page_offset_base)
- ffffc80000000000 |  -56    TB | ffffc8ffffffffff |    1 TB | ... unused hole
+ ffff880000000000 | -120    TB | ffff887fffffffff |  0.5 TB | LDT remap for PTI
+ ffff888000000000 | -119.5  TB | ffffc87fffffffff |   64 TB | direct mapping of all physical memory (page_offset_base)
+ ffffc88000000000 |  -55.5  TB | ffffc8ffffffffff |  0.5 TB | ... unused hole
  ffffc90000000000 |  -55    TB | ffffe8ffffffffff |   32 TB | vmalloc/ioremap space (vmalloc_base)
  ffffe90000000000 |  -23    TB | ffffe9ffffffffff |    1 TB | ... unused hole
  ffffea0000000000 |  -22    TB | ffffeaffffffffff |    1 TB | virtual memory map (vmemmap_base)
  ffffeb0000000000 |  -21    TB | ffffebffffffffff |    1 TB | ... unused hole
  ffffec0000000000 |  -20    TB | fffffbffffffffff |   16 TB | KASAN shadow memory
+__________________|____________|__________________|_________|____________________________________________________________
+                                                            |
+                                                            | Identical layout to the 56-bit one from here on:
+____________________________________________________________|____________________________________________________________
+                  |            |                  |         |
  fffffc0000000000 |   -4    TB | fffffdffffffffff |    2 TB | ... unused hole
                   |            |                  |         | vaddr_end for KASLR
  fffffe0000000000 |   -2    TB | fffffe7fffffffff |  0.5 TB | cpu_entry_area mapping
- fffffe8000000000 |   -1.5  TB | fffffeffffffffff |  0.5 TB | LDT remap for PTI
+ fffffe8000000000 |   -1.5  TB | fffffeffffffffff |  0.5 TB | ... unused hole
  ffffff0000000000 |   -1    TB | ffffff7fffffffff |  0.5 TB | %esp fixup stacks
-__________________|____________|__________________|_________|____________________________________________________________
-                                                            |
-                                                            | Identical layout to the 47-bit one from here on:
-____________________________________________________________|____________________________________________________________
-                  |            |                  |         |
  ffffff8000000000 | -512    GB | ffffffeeffffffff |  444 GB | ... unused hole
  ffffffef00000000 |  -68    GB | fffffffeffffffff |   64 GB | EFI region mapping space
  ffffffff00000000 |   -4    GB | ffffffff7fffffff |    2 GB | ... unused hole
@@ -83,7 +84,7 @@
 __________________|____________|__________________|_________|___________________________________________________________
                   |            |                  |         |
  0000800000000000 |  +64    PB | ffff7fffffffffff | ~16K PB | ... huge, still almost 64 bits wide hole of non-canonical
-                  |            |                  |         |     virtual memory addresses up to the -128 TB
+                  |            |                  |         |     virtual memory addresses up to the -64 PB
                   |            |                  |         |     starting offset of kernel mappings.
 __________________|____________|__________________|_________|___________________________________________________________
                                                             |
@@ -91,23 +92,24 @@
 ____________________________________________________________|___________________________________________________________
                   |            |                  |         |
  ff00000000000000 |  -64    PB | ff0fffffffffffff |    4 PB | ... guard hole, also reserved for hypervisor
- ff10000000000000 |  -60    PB | ff8fffffffffffff |   32 PB | direct mapping of all physical memory (page_offset_base)
- ff90000000000000 |  -28    PB | ff9fffffffffffff |    4 PB | LDT remap for PTI
+ ff10000000000000 |  -60    PB | ff10ffffffffffff | 0.25 PB | LDT remap for PTI
+ ff11000000000000 |  -59.75 PB | ff90ffffffffffff |   32 PB | direct mapping of all physical memory (page_offset_base)
+ ff91000000000000 |  -27.75 PB | ff9fffffffffffff | 3.75 PB | ... unused hole
  ffa0000000000000 |  -24    PB | ffd1ffffffffffff | 12.5 PB | vmalloc/ioremap space (vmalloc_base)
  ffd2000000000000 |  -11.5  PB | ffd3ffffffffffff |  0.5 PB | ... unused hole
  ffd4000000000000 |  -11    PB | ffd5ffffffffffff |  0.5 PB | virtual memory map (vmemmap_base)
  ffd6000000000000 |  -10.5  PB | ffdeffffffffffff | 2.25 PB | ... unused hole
  ffdf000000000000 |   -8.25 PB | fffffdffffffffff |   ~8 PB | KASAN shadow memory
- fffffc0000000000 |   -4    TB | fffffdffffffffff |    2 TB | ... unused hole
-                  |            |                  |         | vaddr_end for KASLR
- fffffe0000000000 |   -2    TB | fffffe7fffffffff |  0.5 TB | cpu_entry_area mapping
- fffffe8000000000 |   -1.5  TB | fffffeffffffffff |  0.5 TB | ... unused hole
- ffffff0000000000 |   -1    TB | ffffff7fffffffff |  0.5 TB | %esp fixup stacks
 __________________|____________|__________________|_________|____________________________________________________________
                                                             |
                                                             | Identical layout to the 47-bit one from here on:
 ____________________________________________________________|____________________________________________________________
                   |            |                  |         |
+ fffffc0000000000 |   -4    TB | fffffdffffffffff |    2 TB | ... unused hole
+                  |            |                  |         | vaddr_end for KASLR
+ fffffe0000000000 |   -2    TB | fffffe7fffffffff |  0.5 TB | cpu_entry_area mapping
+ fffffe8000000000 |   -1.5  TB | fffffeffffffffff |  0.5 TB | ... unused hole
+ ffffff0000000000 |   -1    TB | ffffff7fffffffff |  0.5 TB | %esp fixup stacks
  ffffff8000000000 | -512    GB | ffffffeeffffffff |  444 GB | ... unused hole
  ffffffef00000000 |  -68    GB | fffffffeffffffff |   64 GB | EFI region mapping space
  ffffffff00000000 |   -4    GB | ffffffff7fffffff |    2 GB | ... unused hole
diff --git a/Documentation/x86/zero-page.txt b/Documentation/x86/zero-page.txt
index 97b7adb..68aed07 100644
--- a/Documentation/x86/zero-page.txt
+++ b/Documentation/x86/zero-page.txt
@@ -25,7 +25,7 @@
 0C8/004	ALL	ext_cmd_line_ptr  cmd_line_ptr high 32bits
 140/080	ALL	edid_info	Video mode setup (struct edid_info)
 1C0/020	ALL	efi_info	EFI 32 information (struct efi_info)
-1E0/004	ALL	alk_mem_k	Alternative mem check, in KB
+1E0/004	ALL	alt_mem_k	Alternative mem check, in KB
 1E4/004	ALL	scratch		Scratch field for the kernel setup code
 1E8/001	ALL	e820_entries	Number of entries in e820_table (below)
 1E9/001	ALL	eddbuf_entries	Number of entries in eddbuf (below)
diff --git a/MAINTAINERS b/MAINTAINERS
index f485597..0abecc5 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6607,9 +6607,9 @@
 
 HID CORE LAYER
 M:	Jiri Kosina <jikos@kernel.org>
-R:	Benjamin Tissoires <benjamin.tissoires@redhat.com>
+M:	Benjamin Tissoires <benjamin.tissoires@redhat.com>
 L:	linux-input@vger.kernel.org
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jikos/hid.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/hid/hid.git
 S:	Maintained
 F:	drivers/hid/
 F:	include/linux/hid*
@@ -6861,6 +6861,13 @@
 S:	Maintained
 F:	drivers/i2c/i2c-core-acpi.c
 
+I2C CONTROLLER DRIVER FOR NVIDIA GPU
+M:	Ajay Gupta <ajayg@nvidia.com>
+L:	linux-i2c@vger.kernel.org
+S:	Maintained
+F:	Documentation/i2c/busses/i2c-nvidia-gpu
+F:	drivers/i2c/busses/i2c-nvidia-gpu.c
+
 I2C MUXES
 M:	Peter Rosin <peda@axentia.se>
 L:	linux-i2c@vger.kernel.org
@@ -8367,7 +8374,7 @@
 LIBATA PATA ARASAN COMPACT FLASH CONTROLLER
 M:	Viresh Kumar <vireshk@kernel.org>
 L:	linux-ide@vger.kernel.org
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tj/libata.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git
 S:	Maintained
 F:	include/linux/pata_arasan_cf_data.h
 F:	drivers/ata/pata_arasan_cf.c
@@ -8384,7 +8391,7 @@
 LIBATA PATA FARADAY FTIDE010 AND GEMINI SATA BRIDGE DRIVERS
 M:	Linus Walleij <linus.walleij@linaro.org>
 L:	linux-ide@vger.kernel.org
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tj/libata.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git
 S:	Maintained
 F:	drivers/ata/pata_ftide010.c
 F:	drivers/ata/sata_gemini.c
@@ -8403,7 +8410,7 @@
 LIBATA SATA PROMISE TX2/TX4 CONTROLLER DRIVER
 M:	Mikael Pettersson <mikpelinux@gmail.com>
 L:	linux-ide@vger.kernel.org
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tj/libata.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git
 S:	Maintained
 F:	drivers/ata/sata_promise.*
 
@@ -10784,6 +10791,14 @@
 S:	Maintained
 F:	arch/arm/mach-omap2/omap_hwmod.*
 
+OMAP I2C DRIVER
+M:	Vignesh R <vigneshr@ti.com>
+L:	linux-omap@vger.kernel.org
+L:	linux-i2c@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/i2c/i2c-omap.txt
+F:	drivers/i2c/busses/i2c-omap.c
+
 OMAP IMAGING SUBSYSTEM (OMAP3 ISP and OMAP4 ISS)
 M:	Laurent Pinchart <laurent.pinchart@ideasonboard.com>
 L:	linux-media@vger.kernel.org
@@ -15436,9 +15451,9 @@
 
 USB HID/HIDBP DRIVERS (USB KEYBOARDS, MICE, REMOTE CONTROLS, ...)
 M:	Jiri Kosina <jikos@kernel.org>
-R:	Benjamin Tissoires <benjamin.tissoires@redhat.com>
+M:	Benjamin Tissoires <benjamin.tissoires@redhat.com>
 L:	linux-usb@vger.kernel.org
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jikos/hid.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/hid/hid.git
 S:	Maintained
 F:	Documentation/hid/hiddev.txt
 F:	drivers/hid/usbhid/
diff --git a/arch/alpha/include/asm/termios.h b/arch/alpha/include/asm/termios.h
index 6a8c53d..b7c77bb 100644
--- a/arch/alpha/include/asm/termios.h
+++ b/arch/alpha/include/asm/termios.h
@@ -73,9 +73,15 @@
 })
 
 #define user_termios_to_kernel_termios(k, u) \
-	copy_from_user(k, u, sizeof(struct termios))
+	copy_from_user(k, u, sizeof(struct termios2))
 
 #define kernel_termios_to_user_termios(u, k) \
+	copy_to_user(u, k, sizeof(struct termios2))
+
+#define user_termios_to_kernel_termios_1(k, u) \
+	copy_from_user(k, u, sizeof(struct termios))
+
+#define kernel_termios_to_user_termios_1(u, k) \
 	copy_to_user(u, k, sizeof(struct termios))
 
 #endif	/* _ALPHA_TERMIOS_H */
diff --git a/arch/alpha/include/uapi/asm/ioctls.h b/arch/alpha/include/uapi/asm/ioctls.h
index 1e9121c..9713116 100644
--- a/arch/alpha/include/uapi/asm/ioctls.h
+++ b/arch/alpha/include/uapi/asm/ioctls.h
@@ -32,6 +32,11 @@
 #define TCXONC		_IO('t', 30)
 #define TCFLSH		_IO('t', 31)
 
+#define TCGETS2		_IOR('T', 42, struct termios2)
+#define TCSETS2		_IOW('T', 43, struct termios2)
+#define TCSETSW2	_IOW('T', 44, struct termios2)
+#define TCSETSF2	_IOW('T', 45, struct termios2)
+
 #define TIOCSWINSZ	_IOW('t', 103, struct winsize)
 #define TIOCGWINSZ	_IOR('t', 104, struct winsize)
 #define	TIOCSTART	_IO('t', 110)		/* start output, like ^Q */
diff --git a/arch/alpha/include/uapi/asm/termbits.h b/arch/alpha/include/uapi/asm/termbits.h
index de6c836..4575ba3 100644
--- a/arch/alpha/include/uapi/asm/termbits.h
+++ b/arch/alpha/include/uapi/asm/termbits.h
@@ -26,6 +26,19 @@ struct termios {
 	speed_t c_ospeed;		/* output speed */
 };
 
+/* Alpha has identical termios and termios2 */
+
+struct termios2 {
+	tcflag_t c_iflag;		/* input mode flags */
+	tcflag_t c_oflag;		/* output mode flags */
+	tcflag_t c_cflag;		/* control mode flags */
+	tcflag_t c_lflag;		/* local mode flags */
+	cc_t c_cc[NCCS];		/* control characters */
+	cc_t c_line;			/* line discipline (== c_cc[19]) */
+	speed_t c_ispeed;		/* input speed */
+	speed_t c_ospeed;		/* output speed */
+};
+
 /* Alpha has matching termios and ktermios */
 
 struct ktermios {
@@ -152,6 +165,7 @@ struct ktermios {
 #define B3000000  00034
 #define B3500000  00035
 #define B4000000  00036
+#define BOTHER    00037
 
 #define CSIZE	00001400
 #define   CS5	00000000
@@ -169,6 +183,9 @@ struct ktermios {
 #define CMSPAR	  010000000000		/* mark or space (stick) parity */
 #define CRTSCTS	  020000000000		/* flow control */
 
+#define CIBAUD	07600000
+#define IBSHIFT	16
+
 /* c_lflag bits */
 #define ISIG	0x00000080
 #define ICANON	0x00000100
diff --git a/arch/arm/boot/dts/imx53-ppd.dts b/arch/arm/boot/dts/imx53-ppd.dts
index b560ff8..5ff9a17 100644
--- a/arch/arm/boot/dts/imx53-ppd.dts
+++ b/arch/arm/boot/dts/imx53-ppd.dts
@@ -55,7 +55,7 @@
 	};
 
 	chosen {
-		stdout-path = "&uart1:115200n8";
+		stdout-path = "serial0:115200n8";
 	};
 
 	memory@70000000 {
diff --git a/arch/arm/boot/dts/imx6sll.dtsi b/arch/arm/boot/dts/imx6sll.dtsi
index ed9a980..beefa1b 100644
--- a/arch/arm/boot/dts/imx6sll.dtsi
+++ b/arch/arm/boot/dts/imx6sll.dtsi
@@ -740,7 +740,7 @@
 			i2c1: i2c@21a0000 {
 				#address-cells = <1>;
 				#size-cells = <0>;
-				compatible = "fs,imx6sll-i2c", "fsl,imx21-i2c";
+				compatible = "fsl,imx6sll-i2c", "fsl,imx21-i2c";
 				reg = <0x021a0000 0x4000>;
 				interrupts = <GIC_SPI 36 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clks IMX6SLL_CLK_I2C1>;
diff --git a/arch/arm/boot/dts/imx6sx-sdb.dtsi b/arch/arm/boot/dts/imx6sx-sdb.dtsi
index 53b3408..7d7d679 100644
--- a/arch/arm/boot/dts/imx6sx-sdb.dtsi
+++ b/arch/arm/boot/dts/imx6sx-sdb.dtsi
@@ -117,7 +117,9 @@
 		regulator-name = "enet_3v3";
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
-		gpios = <&gpio2 6 GPIO_ACTIVE_LOW>;
+		gpio = <&gpio2 6 GPIO_ACTIVE_LOW>;
+		regulator-boot-on;
+		regulator-always-on;
 	};
 
 	reg_pcie_gpio: regulator-pcie-gpio {
@@ -180,6 +182,7 @@
 	phy-supply = <&reg_enet_3v3>;
 	phy-mode = "rgmii";
 	phy-handle = <&ethphy1>;
+	phy-reset-gpios = <&gpio2 7 GPIO_ACTIVE_LOW>;
 	status = "okay";
 
 	mdio {
@@ -373,6 +376,8 @@
 				MX6SX_PAD_RGMII1_RD3__ENET1_RX_DATA_3	0x3081
 				MX6SX_PAD_RGMII1_RX_CTL__ENET1_RX_EN	0x3081
 				MX6SX_PAD_ENET2_RX_CLK__ENET2_REF_CLK_25M	0x91
+				/* phy reset */
+				MX6SX_PAD_ENET2_CRS__GPIO2_IO_7		0x10b0
 			>;
 		};
 
diff --git a/arch/arm/boot/dts/vf610m4-colibri.dts b/arch/arm/boot/dts/vf610m4-colibri.dts
index 41ec66a..ca62495 100644
--- a/arch/arm/boot/dts/vf610m4-colibri.dts
+++ b/arch/arm/boot/dts/vf610m4-colibri.dts
@@ -50,8 +50,8 @@
 	compatible = "fsl,vf610m4";
 
 	chosen {
-		bootargs = "console=ttyLP2,115200 clk_ignore_unused init=/linuxrc rw";
-		stdout-path = "&uart2";
+		bootargs = "clk_ignore_unused init=/linuxrc rw";
+		stdout-path = "serial2:115200";
 	};
 
 	memory@8c000000 {
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index 1c76168..63af623 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -1,7 +1,6 @@
 CONFIG_SYSVIPC=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
-CONFIG_PREEMPT=y
 CONFIG_CGROUPS=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_EMBEDDED=y
diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h
index 92fd2c8..12659ce 100644
--- a/arch/arm/include/asm/pgtable-2level.h
+++ b/arch/arm/include/asm/pgtable-2level.h
@@ -10,7 +10,7 @@
 #ifndef _ASM_PGTABLE_2LEVEL_H
 #define _ASM_PGTABLE_2LEVEL_H
 
-#define __PAGETABLE_PMD_FOLDED
+#define __PAGETABLE_PMD_FOLDED 1
 
 /*
  * Hardware-wise, we have a two level page table structure, where the first
diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
index 8253a1a..fef7351 100644
--- a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
+++ b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
@@ -139,6 +139,7 @@
 			clock-names = "stmmaceth";
 			tx-fifo-depth = <16384>;
 			rx-fifo-depth = <16384>;
+			snps,multicast-filter-bins = <256>;
 			status = "disabled";
 		};
 
@@ -154,6 +155,7 @@
 			clock-names = "stmmaceth";
 			tx-fifo-depth = <16384>;
 			rx-fifo-depth = <16384>;
+			snps,multicast-filter-bins = <256>;
 			status = "disabled";
 		};
 
@@ -169,6 +171,7 @@
 			clock-names = "stmmaceth";
 			tx-fifo-depth = <16384>;
 			rx-fifo-depth = <16384>;
+			snps,multicast-filter-bins = <256>;
 			status = "disabled";
 		};
 
diff --git a/arch/arm64/boot/dts/renesas/r8a7795.dtsi b/arch/arm64/boot/dts/renesas/r8a7795.dtsi
index b5f2273..a79c8d3 100644
--- a/arch/arm64/boot/dts/renesas/r8a7795.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a7795.dtsi
@@ -652,7 +652,7 @@
 			clock-names = "fck", "brg_int", "scif_clk";
 			dmas = <&dmac1 0x35>, <&dmac1 0x34>,
 			       <&dmac2 0x35>, <&dmac2 0x34>;
-			dma-names = "tx", "rx";
+			dma-names = "tx", "rx", "tx", "rx";
 			power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
 			resets = <&cpg 518>;
 			status = "disabled";
diff --git a/arch/arm64/boot/dts/renesas/r8a77980-condor.dts b/arch/arm64/boot/dts/renesas/r8a77980-condor.dts
index fe2e2c0..5a7012b 100644
--- a/arch/arm64/boot/dts/renesas/r8a77980-condor.dts
+++ b/arch/arm64/boot/dts/renesas/r8a77980-condor.dts
@@ -15,7 +15,7 @@
 
 	aliases {
 		serial0 = &scif0;
-		ethernet0 = &avb;
+		ethernet0 = &gether;
 	};
 
 	chosen {
@@ -97,23 +97,6 @@
 	};
 };
 
-&avb {
-	pinctrl-0 = <&avb_pins>;
-	pinctrl-names = "default";
-
-	phy-mode = "rgmii-id";
-	phy-handle = <&phy0>;
-	renesas,no-ether-link;
-	status = "okay";
-
-	phy0: ethernet-phy@0 {
-		rxc-skew-ps = <1500>;
-		reg = <0>;
-		interrupt-parent = <&gpio1>;
-		interrupts = <17 IRQ_TYPE_LEVEL_LOW>;
-	};
-};
-
 &canfd {
 	pinctrl-0 = <&canfd0_pins>;
 	pinctrl-names = "default";
@@ -139,6 +122,23 @@
 	clock-frequency = <32768>;
 };
 
+&gether {
+	pinctrl-0 = <&gether_pins>;
+	pinctrl-names = "default";
+
+	phy-mode = "rgmii-id";
+	phy-handle = <&phy0>;
+	renesas,no-ether-link;
+	status = "okay";
+
+	phy0: ethernet-phy@0 {
+		rxc-skew-ps = <1500>;
+		reg = <0>;
+		interrupt-parent = <&gpio4>;
+		interrupts = <23 IRQ_TYPE_LEVEL_LOW>;
+	};
+};
+
 &i2c0 {
 	pinctrl-0 = <&i2c0_pins>;
 	pinctrl-names = "default";
@@ -236,16 +236,17 @@
 };
 
 &pfc {
-	avb_pins: avb {
-		groups = "avb_mdio", "avb_rgmii";
-		function = "avb";
-	};
-
 	canfd0_pins: canfd0 {
 		groups = "canfd0_data_a";
 		function = "canfd0";
 	};
 
+	gether_pins: gether {
+		groups = "gether_mdio_a", "gether_rgmii",
+			 "gether_txcrefclk", "gether_txcrefclk_mega";
+		function = "gether";
+	};
+
 	i2c0_pins: i2c0 {
 		groups = "i2c0";
 		function = "i2c0";
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 3e20917..6b0d4df 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -24,6 +24,14 @@
 #define KERNEL_DS	UL(-1)
 #define USER_DS		(TASK_SIZE_64 - 1)
 
+/*
+ * On arm64 systems, unaligned accesses by the CPU are cheap, and so there is
+ * no point in shifting all network buffers by 2 bytes just to make some IP
+ * header fields appear aligned in memory, potentially sacrificing some DMA
+ * performance on some platforms.
+ */
+#define NET_IP_ALIGN	0
+
 #ifndef __ASSEMBLY__
 #ifdef __KERNEL__
 
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 9d9582c..9b432d9 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -483,8 +483,6 @@ void __init arm64_memblock_init(void)
 	high_memory = __va(memblock_end_of_DRAM() - 1) + 1;
 
 	dma_contiguous_reserve(arm64_dma_phys_limit);
-
-	memblock_allow_resize();
 }
 
 void __init bootmem_init(void)
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 394b8d55..d1d6601 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -659,6 +659,8 @@ void __init paging_init(void)
 
 	memblock_free(__pa_symbol(init_pg_dir),
 		      __pa_symbol(init_pg_end) - __pa_symbol(init_pg_dir));
+
+	memblock_allow_resize();
 }
 
 /*
diff --git a/arch/m68k/include/asm/pgtable_mm.h b/arch/m68k/include/asm/pgtable_mm.h
index 6181e41..fe3ddd7 100644
--- a/arch/m68k/include/asm/pgtable_mm.h
+++ b/arch/m68k/include/asm/pgtable_mm.h
@@ -55,12 +55,12 @@
  */
 #ifdef CONFIG_SUN3
 #define PTRS_PER_PTE   16
-#define __PAGETABLE_PMD_FOLDED
+#define __PAGETABLE_PMD_FOLDED 1
 #define PTRS_PER_PMD   1
 #define PTRS_PER_PGD   2048
 #elif defined(CONFIG_COLDFIRE)
 #define PTRS_PER_PTE	512
-#define __PAGETABLE_PMD_FOLDED
+#define __PAGETABLE_PMD_FOLDED 1
 #define PTRS_PER_PMD	1
 #define PTRS_PER_PGD	1024
 #else
diff --git a/arch/microblaze/include/asm/pgtable.h b/arch/microblaze/include/asm/pgtable.h
index f64ebb9..e14b662 100644
--- a/arch/microblaze/include/asm/pgtable.h
+++ b/arch/microblaze/include/asm/pgtable.h
@@ -63,7 +63,7 @@ extern int mem_init_done;
 
 #include <asm-generic/4level-fixup.h>
 
-#define __PAGETABLE_PMD_FOLDED
+#define __PAGETABLE_PMD_FOLDED 1
 
 #ifdef __KERNEL__
 #ifndef __ASSEMBLY__
diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper.c b/arch/mips/cavium-octeon/executive/cvmx-helper.c
index 75108ec..6c79e8a 100644
--- a/arch/mips/cavium-octeon/executive/cvmx-helper.c
+++ b/arch/mips/cavium-octeon/executive/cvmx-helper.c
@@ -67,7 +67,7 @@ void (*cvmx_override_pko_queue_priority) (int pko_port,
 void (*cvmx_override_ipd_port_setup) (int ipd_port);
 
 /* Port count per interface */
-static int interface_port_count[5];
+static int interface_port_count[9];
 
 /**
  * Return the number of interfaces the chip has. Each interface
diff --git a/arch/mips/mm/dma-noncoherent.c b/arch/mips/mm/dma-noncoherent.c
index e6c9485..cb38461 100644
--- a/arch/mips/mm/dma-noncoherent.c
+++ b/arch/mips/mm/dma-noncoherent.c
@@ -50,7 +50,7 @@ void *arch_dma_alloc(struct device *dev, size_t size,
 	void *ret;
 
 	ret = dma_direct_alloc_pages(dev, size, dma_handle, gfp, attrs);
-	if (!ret && !(attrs & DMA_ATTR_NON_CONSISTENT)) {
+	if (ret && !(attrs & DMA_ATTR_NON_CONSISTENT)) {
 		dma_cache_wback_inv((unsigned long) ret, size);
 		ret = (void *)UNCAC_ADDR(ret);
 	}
diff --git a/arch/nds32/include/asm/pgtable.h b/arch/nds32/include/asm/pgtable.h
index d3e19a5..9f52db9 100644
--- a/arch/nds32/include/asm/pgtable.h
+++ b/arch/nds32/include/asm/pgtable.h
@@ -4,7 +4,7 @@
 #ifndef _ASMNDS32_PGTABLE_H
 #define _ASMNDS32_PGTABLE_H
 
-#define __PAGETABLE_PMD_FOLDED
+#define __PAGETABLE_PMD_FOLDED 1
 #include <asm-generic/4level-fixup.h>
 #include <asm-generic/sizes.h>
 
diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h
index b941ac7d..c7bb74e 100644
--- a/arch/parisc/include/asm/pgtable.h
+++ b/arch/parisc/include/asm/pgtable.h
@@ -111,7 +111,7 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
 #if CONFIG_PGTABLE_LEVELS == 3
 #define BITS_PER_PMD	(PAGE_SHIFT + PMD_ORDER - BITS_PER_PMD_ENTRY)
 #else
-#define __PAGETABLE_PMD_FOLDED
+#define __PAGETABLE_PMD_FOLDED 1
 #define BITS_PER_PMD	0
 #endif
 #define PTRS_PER_PMD    (1UL << BITS_PER_PMD)
diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index 0b33577..e21053e 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -27,7 +27,7 @@
 KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO),-g)
 KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO_DWARF4), $(call cc-option, -gdwarf-4,))
 UTS_MACHINE	:= s390x
-STACK_SIZE	:= $(if $(CONFIG_KASAN),32768,16384)
+STACK_SIZE	:= $(if $(CONFIG_KASAN),65536,16384)
 CHECKFLAGS	+= -D__s390__ -D__s390x__
 
 export LD_BFD
diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile
index 5930396..b1bdd15 100644
--- a/arch/s390/boot/compressed/Makefile
+++ b/arch/s390/boot/compressed/Makefile
@@ -22,10 +22,10 @@
 OBJECTS := $(addprefix $(obj)/,$(obj-y))
 
 LDFLAGS_vmlinux := --oformat $(LD_BFD) -e startup -T
-$(obj)/vmlinux: $(obj)/vmlinux.lds $(objtree)/arch/s390/boot/startup.a $(OBJECTS)
+$(obj)/vmlinux: $(obj)/vmlinux.lds $(objtree)/arch/s390/boot/startup.a $(OBJECTS) FORCE
 	$(call if_changed,ld)
 
-OBJCOPYFLAGS_info.bin := -O binary --only-section=.vmlinux.info
+OBJCOPYFLAGS_info.bin := -O binary --only-section=.vmlinux.info --set-section-flags .vmlinux.info=load
 $(obj)/info.bin: vmlinux FORCE
 	$(call if_changed,objcopy)
 
@@ -46,17 +46,17 @@
 suffix-$(CONFIG_KERNEL_LZO)  := .lzo
 suffix-$(CONFIG_KERNEL_XZ)  := .xz
 
-$(obj)/vmlinux.bin.gz: $(vmlinux.bin.all-y)
+$(obj)/vmlinux.bin.gz: $(vmlinux.bin.all-y) FORCE
 	$(call if_changed,gzip)
-$(obj)/vmlinux.bin.bz2: $(vmlinux.bin.all-y)
+$(obj)/vmlinux.bin.bz2: $(vmlinux.bin.all-y) FORCE
 	$(call if_changed,bzip2)
-$(obj)/vmlinux.bin.lz4: $(vmlinux.bin.all-y)
+$(obj)/vmlinux.bin.lz4: $(vmlinux.bin.all-y) FORCE
 	$(call if_changed,lz4)
-$(obj)/vmlinux.bin.lzma: $(vmlinux.bin.all-y)
+$(obj)/vmlinux.bin.lzma: $(vmlinux.bin.all-y) FORCE
 	$(call if_changed,lzma)
-$(obj)/vmlinux.bin.lzo: $(vmlinux.bin.all-y)
+$(obj)/vmlinux.bin.lzo: $(vmlinux.bin.all-y) FORCE
 	$(call if_changed,lzo)
-$(obj)/vmlinux.bin.xz: $(vmlinux.bin.all-y)
+$(obj)/vmlinux.bin.xz: $(vmlinux.bin.all-y) FORCE
 	$(call if_changed,xzkern)
 
 OBJCOPYFLAGS_piggy.o := -I binary -O elf64-s390 -B s390:64-bit --rename-section .data=.vmlinux.bin.compressed
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index 259d169..c69cb04 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -64,6 +64,8 @@
 CONFIG_PREEMPT=y
 CONFIG_HZ_100=y
 CONFIG_KEXEC_FILE=y
+CONFIG_EXPOLINE=y
+CONFIG_EXPOLINE_AUTO=y
 CONFIG_MEMORY_HOTPLUG=y
 CONFIG_MEMORY_HOTREMOVE=y
 CONFIG_KSM=y
@@ -84,9 +86,11 @@
 CONFIG_HOTPLUG_PCI=y
 CONFIG_HOTPLUG_PCI_S390=y
 CONFIG_CHSC_SCH=y
+CONFIG_VFIO_AP=m
 CONFIG_CRASH_DUMP=y
 CONFIG_BINFMT_MISC=m
 CONFIG_HIBERNATION=y
+CONFIG_PM_DEBUG=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_PACKET_DIAG=m
@@ -161,8 +165,6 @@
 CONFIG_NF_CT_NETLINK=m
 CONFIG_NF_CT_NETLINK_TIMEOUT=m
 CONFIG_NF_TABLES=m
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_COUNTER=m
 CONFIG_NFT_LOG=m
@@ -365,6 +367,8 @@
 CONFIG_NET_ACT_CSUM=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_OPENVSWITCH=m
+CONFIG_VSOCKETS=m
+CONFIG_VIRTIO_VSOCKETS=m
 CONFIG_NETLINK_DIAG=m
 CONFIG_CGROUP_NET_PRIO=y
 CONFIG_BPF_JIT=y
@@ -461,6 +465,7 @@
 CONFIG_PPPOL2TP=m
 CONFIG_PPP_ASYNC=m
 CONFIG_PPP_SYNC_TTY=m
+CONFIG_ISM=m
 CONFIG_INPUT_EVDEV=y
 # CONFIG_INPUT_KEYBOARD is not set
 # CONFIG_INPUT_MOUSE is not set
@@ -486,9 +491,12 @@
 CONFIG_MLX5_INFINIBAND=m
 CONFIG_VFIO=m
 CONFIG_VFIO_PCI=m
+CONFIG_VFIO_MDEV=m
+CONFIG_VFIO_MDEV_DEVICE=m
 CONFIG_VIRTIO_PCI=m
 CONFIG_VIRTIO_BALLOON=m
 CONFIG_VIRTIO_INPUT=y
+CONFIG_S390_AP_IOMMU=y
 CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_EXT4_FS_SECURITY=y
@@ -615,7 +623,6 @@
 CONFIG_RCU_TORTURE_TEST=m
 CONFIG_RCU_CPU_STALL_TIMEOUT=300
 CONFIG_NOTIFIER_ERROR_INJECTION=m
-CONFIG_PM_NOTIFIER_ERROR_INJECT=m
 CONFIG_NETDEV_NOTIFIER_ERROR_INJECT=m
 CONFIG_FAULT_INJECTION=y
 CONFIG_FAILSLAB=y
@@ -727,3 +734,4 @@
 CONFIG_KVM=m
 CONFIG_KVM_S390_UCONTROL=y
 CONFIG_VHOST_NET=m
+CONFIG_VHOST_VSOCK=m
diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig
index 37fd60c..32f539d 100644
--- a/arch/s390/configs/performance_defconfig
+++ b/arch/s390/configs/performance_defconfig
@@ -65,6 +65,8 @@
 CONFIG_NUMA=y
 CONFIG_HZ_100=y
 CONFIG_KEXEC_FILE=y
+CONFIG_EXPOLINE=y
+CONFIG_EXPOLINE_AUTO=y
 CONFIG_MEMORY_HOTPLUG=y
 CONFIG_MEMORY_HOTREMOVE=y
 CONFIG_KSM=y
@@ -82,9 +84,11 @@
 CONFIG_HOTPLUG_PCI=y
 CONFIG_HOTPLUG_PCI_S390=y
 CONFIG_CHSC_SCH=y
+CONFIG_VFIO_AP=m
 CONFIG_CRASH_DUMP=y
 CONFIG_BINFMT_MISC=m
 CONFIG_HIBERNATION=y
+CONFIG_PM_DEBUG=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_PACKET_DIAG=m
@@ -159,8 +163,6 @@
 CONFIG_NF_CT_NETLINK=m
 CONFIG_NF_CT_NETLINK_TIMEOUT=m
 CONFIG_NF_TABLES=m
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_COUNTER=m
 CONFIG_NFT_LOG=m
@@ -362,6 +364,8 @@
 CONFIG_NET_ACT_CSUM=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_OPENVSWITCH=m
+CONFIG_VSOCKETS=m
+CONFIG_VIRTIO_VSOCKETS=m
 CONFIG_NETLINK_DIAG=m
 CONFIG_CGROUP_NET_PRIO=y
 CONFIG_BPF_JIT=y
@@ -458,6 +462,7 @@
 CONFIG_PPPOL2TP=m
 CONFIG_PPP_ASYNC=m
 CONFIG_PPP_SYNC_TTY=m
+CONFIG_ISM=m
 CONFIG_INPUT_EVDEV=y
 # CONFIG_INPUT_KEYBOARD is not set
 # CONFIG_INPUT_MOUSE is not set
@@ -483,9 +488,12 @@
 CONFIG_MLX5_INFINIBAND=m
 CONFIG_VFIO=m
 CONFIG_VFIO_PCI=m
+CONFIG_VFIO_MDEV=m
+CONFIG_VFIO_MDEV_DEVICE=m
 CONFIG_VIRTIO_PCI=m
 CONFIG_VIRTIO_BALLOON=m
 CONFIG_VIRTIO_INPUT=y
+CONFIG_S390_AP_IOMMU=y
 CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_EXT4_FS_SECURITY=y
@@ -666,3 +674,4 @@
 CONFIG_KVM=m
 CONFIG_KVM_S390_UCONTROL=y
 CONFIG_VHOST_NET=m
+CONFIG_VHOST_VSOCK=m
diff --git a/arch/s390/defconfig b/arch/s390/defconfig
index 7cb6a52..4d58a92 100644
--- a/arch/s390/defconfig
+++ b/arch/s390/defconfig
@@ -26,14 +26,23 @@
 CONFIG_CGROUP_PERF=y
 CONFIG_NAMESPACES=y
 CONFIG_USER_NS=y
+CONFIG_CHECKPOINT_RESTORE=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_EXPERT=y
 # CONFIG_SYSFS_SYSCALL is not set
-CONFIG_CHECKPOINT_RESTORE=y
 CONFIG_BPF_SYSCALL=y
 CONFIG_USERFAULTFD=y
 # CONFIG_COMPAT_BRK is not set
 CONFIG_PROFILING=y
+CONFIG_LIVEPATCH=y
+CONFIG_NR_CPUS=256
+CONFIG_NUMA=y
+CONFIG_HZ_100=y
+CONFIG_KEXEC_FILE=y
+CONFIG_CRASH_DUMP=y
+CONFIG_HIBERNATION=y
+CONFIG_PM_DEBUG=y
+CONFIG_CMM=m
 CONFIG_OPROFILE=y
 CONFIG_KPROBES=y
 CONFIG_JUMP_LABEL=y
@@ -44,11 +53,7 @@
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_IBM_PARTITION=y
 CONFIG_DEFAULT_DEADLINE=y
-CONFIG_LIVEPATCH=y
-CONFIG_NR_CPUS=256
-CONFIG_NUMA=y
-CONFIG_HZ_100=y
-CONFIG_KEXEC_FILE=y
+CONFIG_BINFMT_MISC=m
 CONFIG_MEMORY_HOTPLUG=y
 CONFIG_MEMORY_HOTREMOVE=y
 CONFIG_KSM=y
@@ -60,9 +65,6 @@
 CONFIG_ZSMALLOC=m
 CONFIG_ZSMALLOC_STAT=y
 CONFIG_IDLE_PAGE_TRACKING=y
-CONFIG_CRASH_DUMP=y
-CONFIG_BINFMT_MISC=m
-CONFIG_HIBERNATION=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
@@ -98,6 +100,7 @@
 CONFIG_BLK_DEV_RAM=y
 CONFIG_VIRTIO_BLK=y
 CONFIG_SCSI=y
+# CONFIG_SCSI_MQ_DEFAULT is not set
 CONFIG_BLK_DEV_SD=y
 CONFIG_CHR_DEV_ST=y
 CONFIG_BLK_DEV_SR=y
@@ -131,6 +134,7 @@
 CONFIG_TUN=m
 CONFIG_VIRTIO_NET=y
 # CONFIG_NET_VENDOR_ALACRITECH is not set
+# CONFIG_NET_VENDOR_AURORA is not set
 # CONFIG_NET_VENDOR_CORTINA is not set
 # CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
@@ -157,33 +161,6 @@
 CONFIG_TMPFS_POSIX_ACL=y
 CONFIG_HUGETLBFS=y
 # CONFIG_NETWORK_FILESYSTEMS is not set
-CONFIG_DEBUG_INFO=y
-CONFIG_DEBUG_INFO_DWARF4=y
-CONFIG_GDB_SCRIPTS=y
-CONFIG_UNUSED_SYMBOLS=y
-CONFIG_DEBUG_SECTION_MISMATCH=y
-CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DEBUG_PAGEALLOC=y
-CONFIG_DETECT_HUNG_TASK=y
-CONFIG_PANIC_ON_OOPS=y
-CONFIG_PROVE_LOCKING=y
-CONFIG_LOCK_STAT=y
-CONFIG_DEBUG_LOCKDEP=y
-CONFIG_DEBUG_ATOMIC_SLEEP=y
-CONFIG_DEBUG_LIST=y
-CONFIG_DEBUG_SG=y
-CONFIG_DEBUG_NOTIFIERS=y
-CONFIG_RCU_CPU_STALL_TIMEOUT=60
-CONFIG_LATENCYTOP=y
-CONFIG_SCHED_TRACER=y
-CONFIG_FTRACE_SYSCALLS=y
-CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y
-CONFIG_STACK_TRACER=y
-CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_FUNCTION_PROFILER=y
-# CONFIG_RUNTIME_TESTING_MENU is not set
-CONFIG_S390_PTDUMP=y
 CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_AUTHENC=m
 CONFIG_CRYPTO_TEST=m
@@ -193,6 +170,7 @@
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
+CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_CMAC=m
@@ -231,7 +209,6 @@
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_ZCRYPT=m
-CONFIG_ZCRYPT_MULTIDEVNODES=y
 CONFIG_PKEY=m
 CONFIG_CRYPTO_PAES_S390=m
 CONFIG_CRYPTO_SHA1_S390=m
@@ -247,4 +224,30 @@
 # CONFIG_XZ_DEC_ARM is not set
 # CONFIG_XZ_DEC_ARMTHUMB is not set
 # CONFIG_XZ_DEC_SPARC is not set
-CONFIG_CMM=m
+CONFIG_DEBUG_INFO=y
+CONFIG_DEBUG_INFO_DWARF4=y
+CONFIG_GDB_SCRIPTS=y
+CONFIG_UNUSED_SYMBOLS=y
+CONFIG_DEBUG_SECTION_MISMATCH=y
+CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y
+CONFIG_MAGIC_SYSRQ=y
+CONFIG_DEBUG_PAGEALLOC=y
+CONFIG_DETECT_HUNG_TASK=y
+CONFIG_PANIC_ON_OOPS=y
+CONFIG_PROVE_LOCKING=y
+CONFIG_LOCK_STAT=y
+CONFIG_DEBUG_LOCKDEP=y
+CONFIG_DEBUG_ATOMIC_SLEEP=y
+CONFIG_DEBUG_LIST=y
+CONFIG_DEBUG_SG=y
+CONFIG_DEBUG_NOTIFIERS=y
+CONFIG_RCU_CPU_STALL_TIMEOUT=60
+CONFIG_LATENCYTOP=y
+CONFIG_SCHED_TRACER=y
+CONFIG_FTRACE_SYSCALLS=y
+CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y
+CONFIG_STACK_TRACER=y
+CONFIG_BLK_DEV_IO_TRACE=y
+CONFIG_FUNCTION_PROFILER=y
+# CONFIG_RUNTIME_TESTING_MENU is not set
+CONFIG_S390_PTDUMP=y
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index dbd689d..ccbb53e 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -46,8 +46,6 @@ static inline int init_new_context(struct task_struct *tsk,
 		mm->context.asce_limit = STACK_TOP_MAX;
 		mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
 				   _ASCE_USER_BITS | _ASCE_TYPE_REGION3;
-		/* pgd_alloc() did not account this pud */
-		mm_inc_nr_puds(mm);
 		break;
 	case -PAGE_SIZE:
 		/* forked 5-level task, set new asce with new_mm->pgd */
@@ -63,9 +61,6 @@ static inline int init_new_context(struct task_struct *tsk,
 		/* forked 2-level compat task, set new asce with new mm->pgd */
 		mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
 				   _ASCE_USER_BITS | _ASCE_TYPE_SEGMENT;
-		/* pgd_alloc() did not account this pmd */
-		mm_inc_nr_pmds(mm);
-		mm_inc_nr_puds(mm);
 	}
 	crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm));
 	return 0;
diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index f0f9bcf..5ee7337 100644
--- a/arch/s390/include/asm/pgalloc.h
+++ b/arch/s390/include/asm/pgalloc.h
@@ -36,11 +36,11 @@ static inline void crst_table_init(unsigned long *crst, unsigned long entry)
 
 static inline unsigned long pgd_entry_type(struct mm_struct *mm)
 {
-	if (mm->context.asce_limit <= _REGION3_SIZE)
+	if (mm_pmd_folded(mm))
 		return _SEGMENT_ENTRY_EMPTY;
-	if (mm->context.asce_limit <= _REGION2_SIZE)
+	if (mm_pud_folded(mm))
 		return _REGION3_ENTRY_EMPTY;
-	if (mm->context.asce_limit <= _REGION1_SIZE)
+	if (mm_p4d_folded(mm))
 		return _REGION2_ENTRY_EMPTY;
 	return _REGION1_ENTRY_EMPTY;
 }
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 411d435..0637324 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -493,6 +493,24 @@ static inline int is_module_addr(void *addr)
 				   _REGION_ENTRY_PROTECT | \
 				   _REGION_ENTRY_NOEXEC)
 
+static inline bool mm_p4d_folded(struct mm_struct *mm)
+{
+	return mm->context.asce_limit <= _REGION1_SIZE;
+}
+#define mm_p4d_folded(mm) mm_p4d_folded(mm)
+
+static inline bool mm_pud_folded(struct mm_struct *mm)
+{
+	return mm->context.asce_limit <= _REGION2_SIZE;
+}
+#define mm_pud_folded(mm) mm_pud_folded(mm)
+
+static inline bool mm_pmd_folded(struct mm_struct *mm)
+{
+	return mm->context.asce_limit <= _REGION3_SIZE;
+}
+#define mm_pmd_folded(mm) mm_pmd_folded(mm)
+
 static inline int mm_has_pgste(struct mm_struct *mm)
 {
 #ifdef CONFIG_PGSTE
diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h
index 27248f4..ce4e17c 100644
--- a/arch/s390/include/asm/thread_info.h
+++ b/arch/s390/include/asm/thread_info.h
@@ -14,7 +14,7 @@
  * General size of kernel stacks
  */
 #ifdef CONFIG_KASAN
-#define THREAD_SIZE_ORDER 3
+#define THREAD_SIZE_ORDER 4
 #else
 #define THREAD_SIZE_ORDER 2
 #endif
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index 457b7ba..b31c779 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -136,7 +136,7 @@ static inline void pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
 				unsigned long address)
 {
-	if (tlb->mm->context.asce_limit <= _REGION3_SIZE)
+	if (mm_pmd_folded(tlb->mm))
 		return;
 	pgtable_pmd_page_dtor(virt_to_page(pmd));
 	tlb_remove_table(tlb, pmd);
@@ -152,7 +152,7 @@ static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
 static inline void p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d,
 				unsigned long address)
 {
-	if (tlb->mm->context.asce_limit <= _REGION1_SIZE)
+	if (mm_p4d_folded(tlb->mm))
 		return;
 	tlb_remove_table(tlb, p4d);
 }
@@ -167,7 +167,7 @@ static inline void p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d,
 static inline void pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
 				unsigned long address)
 {
-	if (tlb->mm->context.asce_limit <= _REGION2_SIZE)
+	if (mm_pud_folded(tlb->mm))
 		return;
 	tlb_remove_table(tlb, pud);
 }
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 724fba4..39191a0 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -236,10 +236,10 @@
 	stmg	%r6,%r15,__SF_GPRS(%r15)	# store gprs of prev task
 	lghi	%r4,__TASK_stack
 	lghi	%r1,__TASK_thread
-	lg	%r5,0(%r4,%r3)			# start of kernel stack of next
+	llill	%r5,STACK_INIT
 	stg	%r15,__THREAD_ksp(%r1,%r2)	# store kernel stack of prev
-	lgr	%r15,%r5
-	aghi	%r15,STACK_INIT			# end of kernel stack of next
+	lg	%r15,0(%r4,%r3)			# start of kernel stack of next
+	agr	%r15,%r5			# end of kernel stack of next
 	stg	%r3,__LC_CURRENT		# store task struct of next
 	stg	%r15,__LC_KERNEL_STACK		# store end of kernel stack
 	lg	%r15,__THREAD_ksp(%r1,%r3)	# load kernel stack of next
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index cc085e2..74091fd 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -373,7 +373,7 @@ static int __hw_perf_event_init(struct perf_event *event)
 		return -ENOENT;
 
 	if (ev > PERF_CPUM_CF_MAX_CTR)
-		return -EINVAL;
+		return -ENOENT;
 
 	/* Obtain the counter set to which the specified counter belongs */
 	set = get_counter_set(ev);
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 7bf604f..bfabeb1 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -1842,10 +1842,30 @@ static void cpumsf_pmu_del(struct perf_event *event, int flags)
 CPUMF_EVENT_ATTR(SF, SF_CYCLES_BASIC, PERF_EVENT_CPUM_SF);
 CPUMF_EVENT_ATTR(SF, SF_CYCLES_BASIC_DIAG, PERF_EVENT_CPUM_SF_DIAG);
 
-static struct attribute *cpumsf_pmu_events_attr[] = {
-	CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC),
-	NULL,
-	NULL,
+/* Attribute list for CPU_SF.
+ *
+ * The availablitiy depends on the CPU_MF sampling facility authorization
+ * for basic + diagnositic samples. This is determined at initialization
+ * time by the sampling facility device driver.
+ * If the authorization for basic samples is turned off, it should be
+ * also turned off for diagnostic sampling.
+ *
+ * During initialization of the device driver, check the authorization
+ * level for diagnostic sampling and installs the attribute
+ * file for diagnostic sampling if necessary.
+ *
+ * For now install a placeholder to reference all possible attributes:
+ * SF_CYCLES_BASIC and SF_CYCLES_BASIC_DIAG.
+ * Add another entry for the final NULL pointer.
+ */
+enum {
+	SF_CYCLES_BASIC_ATTR_IDX = 0,
+	SF_CYCLES_BASIC_DIAG_ATTR_IDX,
+	SF_CYCLES_ATTR_MAX
+};
+
+static struct attribute *cpumsf_pmu_events_attr[SF_CYCLES_ATTR_MAX + 1] = {
+	[SF_CYCLES_BASIC_ATTR_IDX] = CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC)
 };
 
 PMU_FORMAT_ATTR(event, "config:0-63");
@@ -2040,7 +2060,10 @@ static int __init init_cpum_sampling_pmu(void)
 
 	if (si.ad) {
 		sfb_set_limits(CPUM_SF_MIN_SDB, CPUM_SF_MAX_SDB);
-		cpumsf_pmu_events_attr[1] =
+		/* Sampling of diagnostic data authorized,
+		 * install event into attribute list of PMU device.
+		 */
+		cpumsf_pmu_events_attr[SF_CYCLES_BASIC_DIAG_ATTR_IDX] =
 			CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC_DIAG);
 	}
 
diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile
index eb8aebe..e76309f 100644
--- a/arch/s390/kernel/vdso32/Makefile
+++ b/arch/s390/kernel/vdso32/Makefile
@@ -37,7 +37,7 @@
 $(obj)/vdso32_wrapper.o : $(obj)/vdso32.so
 
 # link rule for the .so file, .lds has to be first
-$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32)
+$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) FORCE
 	$(call if_changed,vdso32ld)
 
 # strip rule for the .so file
@@ -46,12 +46,12 @@
 	$(call if_changed,objcopy)
 
 # assembly rules for the .S files
-$(obj-vdso32): %.o: %.S
+$(obj-vdso32): %.o: %.S FORCE
 	$(call if_changed_dep,vdso32as)
 
 # actual build commands
 quiet_cmd_vdso32ld = VDSO32L $@
-      cmd_vdso32ld = $(CC) $(c_flags) -Wl,-T $^ -o $@
+      cmd_vdso32ld = $(CC) $(c_flags) -Wl,-T $(filter %.lds %.o,$^) -o $@
 quiet_cmd_vdso32as = VDSO32A $@
       cmd_vdso32as = $(CC) $(a_flags) -c -o $@ $<
 
diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile
index a22b2cf..f849ac6 100644
--- a/arch/s390/kernel/vdso64/Makefile
+++ b/arch/s390/kernel/vdso64/Makefile
@@ -37,7 +37,7 @@
 $(obj)/vdso64_wrapper.o : $(obj)/vdso64.so
 
 # link rule for the .so file, .lds has to be first
-$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64)
+$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) FORCE
 	$(call if_changed,vdso64ld)
 
 # strip rule for the .so file
@@ -46,12 +46,12 @@
 	$(call if_changed,objcopy)
 
 # assembly rules for the .S files
-$(obj-vdso64): %.o: %.S
+$(obj-vdso64): %.o: %.S FORCE
 	$(call if_changed_dep,vdso64as)
 
 # actual build commands
 quiet_cmd_vdso64ld = VDSO64L $@
-      cmd_vdso64ld = $(CC) $(c_flags) -Wl,-T $^ -o $@
+      cmd_vdso64ld = $(CC) $(c_flags) -Wl,-T $(filter %.lds %.o,$^) -o $@
 quiet_cmd_vdso64as = VDSO64A $@
       cmd_vdso64as = $(CC) $(a_flags) -c -o $@ $<
 
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index 21eb7407..8429ab0 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -154,14 +154,14 @@
 	 * uncompressed image info used by the decompressor
 	 * it should match struct vmlinux_info
 	 */
-	.vmlinux.info 0 : {
+	.vmlinux.info 0 (INFO) : {
 		QUAD(_stext)					/* default_lma */
 		QUAD(startup_continue)				/* entry */
 		QUAD(__bss_start - _stext)			/* image_size */
 		QUAD(__bss_stop - __bss_start)			/* bss_size */
 		QUAD(__boot_data_start)				/* bootdata_off */
 		QUAD(__boot_data_end - __boot_data_start)	/* bootdata_size */
-	}
+	} :NONE
 
 	/* Debugging sections.	*/
 	STABS_DEBUG
diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c
index 76d89ee..814f265 100644
--- a/arch/s390/mm/pgalloc.c
+++ b/arch/s390/mm/pgalloc.c
@@ -101,6 +101,7 @@ int crst_table_upgrade(struct mm_struct *mm, unsigned long end)
 			mm->context.asce_limit = _REGION1_SIZE;
 			mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
 				_ASCE_USER_BITS | _ASCE_TYPE_REGION2;
+			mm_inc_nr_puds(mm);
 		} else {
 			crst_table_init(table, _REGION1_ENTRY_EMPTY);
 			pgd_populate(mm, (pgd_t *) table, (p4d_t *) pgd);
diff --git a/arch/s390/numa/numa.c b/arch/s390/numa/numa.c
index ae0d9e8..d31bde0 100644
--- a/arch/s390/numa/numa.c
+++ b/arch/s390/numa/numa.c
@@ -53,6 +53,7 @@ int __node_distance(int a, int b)
 {
 	return mode->distance ? mode->distance(a, b) : 0;
 }
+EXPORT_SYMBOL(__node_distance);
 
 int numa_debug_enabled;
 
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index 74c002d..28c4062 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -1305,6 +1305,7 @@ static int ubd_queue_one_vec(struct blk_mq_hw_ctx *hctx, struct request *req,
 		io_req->fds[0] = dev->cow.fd;
 	else
 		io_req->fds[0] = dev->fd;
+	io_req->error = 0;
 
 	if (req_op(req) == REQ_OP_FLUSH) {
 		io_req->op = UBD_FLUSH;
@@ -1313,9 +1314,7 @@ static int ubd_queue_one_vec(struct blk_mq_hw_ctx *hctx, struct request *req,
 		io_req->cow_offset = -1;
 		io_req->offset = off;
 		io_req->length = bvec->bv_len;
-		io_req->error = 0;
 		io_req->sector_mask = 0;
-
 		io_req->op = rq_data_dir(req) == READ ? UBD_READ : UBD_WRITE;
 		io_req->offsets[0] = 0;
 		io_req->offsets[1] = dev->cow.data_offset;
@@ -1341,11 +1340,14 @@ static int ubd_queue_one_vec(struct blk_mq_hw_ctx *hctx, struct request *req,
 static blk_status_t ubd_queue_rq(struct blk_mq_hw_ctx *hctx,
 				 const struct blk_mq_queue_data *bd)
 {
+	struct ubd *ubd_dev = hctx->queue->queuedata;
 	struct request *req = bd->rq;
 	int ret = 0;
 
 	blk_mq_start_request(req);
 
+	spin_lock_irq(&ubd_dev->lock);
+
 	if (req_op(req) == REQ_OP_FLUSH) {
 		ret = ubd_queue_one_vec(hctx, req, 0, NULL);
 	} else {
@@ -1361,9 +1363,11 @@ static blk_status_t ubd_queue_rq(struct blk_mq_hw_ctx *hctx,
 		}
 	}
 out:
-	if (ret < 0) {
+	spin_unlock_irq(&ubd_dev->lock);
+
+	if (ret < 0)
 		blk_mq_requeue_request(req, true);
-	}
+
 	return BLK_STS_OK;
 }
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index ba7e346..9d734f3 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -525,7 +525,6 @@
 	bool "ScaleMP vSMP"
 	select HYPERVISOR_GUEST
 	select PARAVIRT
-	select PARAVIRT_XXL
 	depends on X86_64 && PCI
 	depends on X86_EXTENDED_PLATFORM
 	depends on SMP
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 5b562e4..88398fd 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -213,8 +213,6 @@
 KBUILD_LDFLAGS += $(call ld-option, -z max-page-size=0x200000)
 endif
 
-# Speed up the build
-KBUILD_CFLAGS += -pipe
 # Workaround for a gcc prelease that unfortunately was shipped in a suse release
 KBUILD_CFLAGS += -Wno-sign-compare
 #
@@ -239,7 +237,7 @@
 archmacros:
 	$(Q)$(MAKE) $(build)=arch/x86/kernel arch/x86/kernel/macros.s
 
-ASM_MACRO_FLAGS = -Wa,arch/x86/kernel/macros.s -Wa,-
+ASM_MACRO_FLAGS = -Wa,arch/x86/kernel/macros.s
 export ASM_MACRO_FLAGS
 KBUILD_CFLAGS += $(ASM_MACRO_FLAGS)
 
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 4da9b1c..c1a812b 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -221,6 +221,8 @@ static inline void mce_hygon_feature_init(struct cpuinfo_x86 *c) { return mce_am
 
 int mce_available(struct cpuinfo_x86 *c);
 bool mce_is_memory_error(struct mce *m);
+bool mce_is_correctable(struct mce *m);
+int mce_usable_address(struct mce *m);
 
 DECLARE_PER_CPU(unsigned, mce_exception_count);
 DECLARE_PER_CPU(unsigned, mce_poll_count);
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index 0d6271c..1d0a777 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -232,7 +232,7 @@ static inline u64 hv_do_fast_hypercall16(u16 code, u64 input1, u64 input2)
 				      : "cc");
 	}
 #endif
-		return hv_status;
+	return hv_status;
 }
 
 /*
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index cd0cf1c..8f65728 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -33,12 +33,14 @@
 
 /*
  * Set __PAGE_OFFSET to the most negative possible address +
- * PGDIR_SIZE*16 (pgd slot 272).  The gap is to allow a space for a
- * hypervisor to fit.  Choosing 16 slots here is arbitrary, but it's
- * what Xen requires.
+ * PGDIR_SIZE*17 (pgd slot 273).
+ *
+ * The gap is to allow a space for LDT remap for PTI (1 pgd slot) and space for
+ * a hypervisor (16 slots). Choosing 16 slots for a hypervisor is arbitrary,
+ * but it's what Xen requires.
  */
-#define __PAGE_OFFSET_BASE_L5	_AC(0xff10000000000000, UL)
-#define __PAGE_OFFSET_BASE_L4	_AC(0xffff880000000000, UL)
+#define __PAGE_OFFSET_BASE_L5	_AC(0xff11000000000000, UL)
+#define __PAGE_OFFSET_BASE_L4	_AC(0xffff888000000000, UL)
 
 #ifdef CONFIG_DYNAMIC_MEMORY_LAYOUT
 #define __PAGE_OFFSET           page_offset_base
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 04edd2d..84bd9bd 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -111,9 +111,7 @@ extern unsigned int ptrs_per_p4d;
  */
 #define MAXMEM			(1UL << MAX_PHYSMEM_BITS)
 
-#define LDT_PGD_ENTRY_L4	-3UL
-#define LDT_PGD_ENTRY_L5	-112UL
-#define LDT_PGD_ENTRY		(pgtable_l5_enabled() ? LDT_PGD_ENTRY_L5 : LDT_PGD_ENTRY_L4)
+#define LDT_PGD_ENTRY		-240UL
 #define LDT_BASE_ADDR		(LDT_PGD_ENTRY << PGDIR_SHIFT)
 #define LDT_END_ADDR		(LDT_BASE_ADDR + PGDIR_SIZE)
 
diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h
index 87623c6..bd5ac6c 100644
--- a/arch/x86/include/asm/qspinlock.h
+++ b/arch/x86/include/asm/qspinlock.h
@@ -13,12 +13,15 @@
 #define queued_fetch_set_pending_acquire queued_fetch_set_pending_acquire
 static __always_inline u32 queued_fetch_set_pending_acquire(struct qspinlock *lock)
 {
-	u32 val = 0;
+	u32 val;
 
-	if (GEN_BINARY_RMWcc(LOCK_PREFIX "btsl", lock->val.counter, c,
-			     "I", _Q_PENDING_OFFSET))
-		val |= _Q_PENDING_VAL;
-
+	/*
+	 * We can't use GEN_BINARY_RMWcc() inside an if() stmt because asm goto
+	 * and CONFIG_PROFILE_ALL_BRANCHES=y results in a label inside a
+	 * statement expression, which GCC doesn't like.
+	 */
+	val = GEN_BINARY_RMWcc(LOCK_PREFIX "btsl", lock->val.counter, c,
+			       "I", _Q_PENDING_OFFSET) * _Q_PENDING_VAL;
 	val |= atomic_read(&lock->val) & ~_Q_PENDING_MASK;
 
 	return val;
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index 123e669..790ce08 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -9,7 +9,7 @@
 #include <linux/mm.h>
 #include <linux/device.h>
 
-#include <linux/uaccess.h>
+#include <asm/extable.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
 
@@ -93,12 +93,39 @@ clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
  */
 static inline int xen_safe_write_ulong(unsigned long *addr, unsigned long val)
 {
-	return __put_user(val, (unsigned long __user *)addr);
+	int ret = 0;
+
+	asm volatile("1: mov %[val], %[ptr]\n"
+		     "2:\n"
+		     ".section .fixup, \"ax\"\n"
+		     "3: sub $1, %[ret]\n"
+		     "   jmp 2b\n"
+		     ".previous\n"
+		     _ASM_EXTABLE(1b, 3b)
+		     : [ret] "+r" (ret), [ptr] "=m" (*addr)
+		     : [val] "r" (val));
+
+	return ret;
 }
 
-static inline int xen_safe_read_ulong(unsigned long *addr, unsigned long *val)
+static inline int xen_safe_read_ulong(const unsigned long *addr,
+				      unsigned long *val)
 {
-	return __get_user(*val, (unsigned long __user *)addr);
+	int ret = 0;
+	unsigned long rval = ~0ul;
+
+	asm volatile("1: mov %[ptr], %[rval]\n"
+		     "2:\n"
+		     ".section .fixup, \"ax\"\n"
+		     "3: sub $1, %[ret]\n"
+		     "   jmp 2b\n"
+		     ".previous\n"
+		     _ASM_EXTABLE(1b, 3b)
+		     : [ret] "+r" (ret), [rval] "+r" (rval)
+		     : [ptr] "m" (*addr));
+	*val = rval;
+
+	return ret;
 }
 
 #ifdef CONFIG_XEN_PV
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 8c66d2f..36d2696 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -485,7 +485,7 @@ static void mce_report_event(struct pt_regs *regs)
  * 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)
+int mce_usable_address(struct mce *m)
 {
 	if (!(m->status & MCI_STATUS_ADDRV))
 		return 0;
@@ -505,6 +505,7 @@ static int mce_usable_address(struct mce *m)
 
 	return 1;
 }
+EXPORT_SYMBOL_GPL(mce_usable_address);
 
 bool mce_is_memory_error(struct mce *m)
 {
@@ -534,7 +535,7 @@ bool mce_is_memory_error(struct mce *m)
 }
 EXPORT_SYMBOL_GPL(mce_is_memory_error);
 
-static bool mce_is_correctable(struct mce *m)
+bool mce_is_correctable(struct mce *m)
 {
 	if (m->cpuvendor == X86_VENDOR_AMD && m->status & MCI_STATUS_DEFERRED)
 		return false;
@@ -547,6 +548,7 @@ static bool mce_is_correctable(struct mce *m)
 
 	return true;
 }
+EXPORT_SYMBOL_GPL(mce_is_correctable);
 
 static bool cec_add_mce(struct mce *m)
 {
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 1c72f38..e81a2db 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -20,6 +20,7 @@
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/kexec.h>
+#include <linux/i8253.h>
 #include <asm/processor.h>
 #include <asm/hypervisor.h>
 #include <asm/hyperv-tlfs.h>
@@ -295,6 +296,16 @@ static void __init ms_hyperv_init_platform(void)
 	if (efi_enabled(EFI_BOOT))
 		x86_platform.get_nmi_reason = hv_get_nmi_reason;
 
+	/*
+	 * Hyper-V VMs have a PIT emulation quirk such that zeroing the
+	 * counter register during PIT shutdown restarts the PIT. So it
+	 * continues to interrupt @18.2 HZ. Setting i8253_clear_counter
+	 * to false tells pit_shutdown() not to zero the counter so that
+	 * the PIT really is shutdown. Generation 2 VMs don't have a PIT,
+	 * and setting this value has no effect.
+	 */
+	i8253_clear_counter_on_shutdown = false;
+
 #if IS_ENABLED(CONFIG_HYPERV)
 	/*
 	 * Setup the hook to get control post apic initialization.
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index d9ab49b..0eda91f 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -77,7 +77,7 @@ static __init int setup_vmw_sched_clock(char *s)
 }
 early_param("no-vmw-sched-clock", setup_vmw_sched_clock);
 
-static unsigned long long vmware_sched_clock(void)
+static unsigned long long notrace vmware_sched_clock(void)
 {
 	unsigned long long ns;
 
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index ab18e08..6135ae8 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -199,14 +199,6 @@ static void sanity_check_ldt_mapping(struct mm_struct *mm)
 /*
  * If PTI is enabled, this maps the LDT into the kernelmode and
  * usermode tables for the given mm.
- *
- * There is no corresponding unmap function.  Even if the LDT is freed, we
- * leave the PTEs around until the slot is reused or the mm is destroyed.
- * This is harmless: the LDT is always in ordinary memory, and no one will
- * access the freed slot.
- *
- * If we wanted to unmap freed LDTs, we'd also need to do a flush to make
- * it useful, and the flush would slow down modify_ldt().
  */
 static int
 map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
@@ -214,8 +206,7 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
 	unsigned long va;
 	bool is_vmalloc;
 	spinlock_t *ptl;
-	pgd_t *pgd;
-	int i;
+	int i, nr_pages;
 
 	if (!static_cpu_has(X86_FEATURE_PTI))
 		return 0;
@@ -229,16 +220,11 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
 	/* Check if the current mappings are sane */
 	sanity_check_ldt_mapping(mm);
 
-	/*
-	 * Did we already have the top level entry allocated?  We can't
-	 * use pgd_none() for this because it doens't do anything on
-	 * 4-level page table kernels.
-	 */
-	pgd = pgd_offset(mm, LDT_BASE_ADDR);
-
 	is_vmalloc = is_vmalloc_addr(ldt->entries);
 
-	for (i = 0; i * PAGE_SIZE < ldt->nr_entries * LDT_ENTRY_SIZE; i++) {
+	nr_pages = DIV_ROUND_UP(ldt->nr_entries * LDT_ENTRY_SIZE, PAGE_SIZE);
+
+	for (i = 0; i < nr_pages; i++) {
 		unsigned long offset = i << PAGE_SHIFT;
 		const void *src = (char *)ldt->entries + offset;
 		unsigned long pfn;
@@ -272,13 +258,39 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
 	/* Propagate LDT mapping to the user page-table */
 	map_ldt_struct_to_user(mm);
 
-	va = (unsigned long)ldt_slot_va(slot);
-	flush_tlb_mm_range(mm, va, va + LDT_SLOT_STRIDE, PAGE_SHIFT, false);
-
 	ldt->slot = slot;
 	return 0;
 }
 
+static void unmap_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt)
+{
+	unsigned long va;
+	int i, nr_pages;
+
+	if (!ldt)
+		return;
+
+	/* LDT map/unmap is only required for PTI */
+	if (!static_cpu_has(X86_FEATURE_PTI))
+		return;
+
+	nr_pages = DIV_ROUND_UP(ldt->nr_entries * LDT_ENTRY_SIZE, PAGE_SIZE);
+
+	for (i = 0; i < nr_pages; i++) {
+		unsigned long offset = i << PAGE_SHIFT;
+		spinlock_t *ptl;
+		pte_t *ptep;
+
+		va = (unsigned long)ldt_slot_va(ldt->slot) + offset;
+		ptep = get_locked_pte(mm, va, &ptl);
+		pte_clear(mm, va, ptep);
+		pte_unmap_unlock(ptep, ptl);
+	}
+
+	va = (unsigned long)ldt_slot_va(ldt->slot);
+	flush_tlb_mm_range(mm, va, va + nr_pages * PAGE_SIZE, PAGE_SHIFT, false);
+}
+
 #else /* !CONFIG_PAGE_TABLE_ISOLATION */
 
 static int
@@ -286,6 +298,10 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
 {
 	return 0;
 }
+
+static void unmap_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt)
+{
+}
 #endif /* CONFIG_PAGE_TABLE_ISOLATION */
 
 static void free_ldt_pgtables(struct mm_struct *mm)
@@ -524,6 +540,7 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
 	}
 
 	install_ldt(mm, new_ldt);
+	unmap_ldt_struct(mm, old_ldt);
 	free_ldt_struct(old_ldt);
 	error = 0;
 
diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c
index 1eae5af..891a75d 100644
--- a/arch/x86/kernel/vsmp_64.c
+++ b/arch/x86/kernel/vsmp_64.c
@@ -26,65 +26,8 @@
 
 #define TOPOLOGY_REGISTER_OFFSET 0x10
 
-#if defined CONFIG_PCI && defined CONFIG_PARAVIRT_XXL
-/*
- * Interrupt control on vSMPowered systems:
- * ~AC is a shadow of IF.  If IF is 'on' AC should be 'off'
- * and vice versa.
- */
-
-asmlinkage __visible unsigned long vsmp_save_fl(void)
-{
-	unsigned long flags = native_save_fl();
-
-	if (!(flags & X86_EFLAGS_IF) || (flags & X86_EFLAGS_AC))
-		flags &= ~X86_EFLAGS_IF;
-	return flags;
-}
-PV_CALLEE_SAVE_REGS_THUNK(vsmp_save_fl);
-
-__visible void vsmp_restore_fl(unsigned long flags)
-{
-	if (flags & X86_EFLAGS_IF)
-		flags &= ~X86_EFLAGS_AC;
-	else
-		flags |= X86_EFLAGS_AC;
-	native_restore_fl(flags);
-}
-PV_CALLEE_SAVE_REGS_THUNK(vsmp_restore_fl);
-
-asmlinkage __visible void vsmp_irq_disable(void)
-{
-	unsigned long flags = native_save_fl();
-
-	native_restore_fl((flags & ~X86_EFLAGS_IF) | X86_EFLAGS_AC);
-}
-PV_CALLEE_SAVE_REGS_THUNK(vsmp_irq_disable);
-
-asmlinkage __visible void vsmp_irq_enable(void)
-{
-	unsigned long flags = native_save_fl();
-
-	native_restore_fl((flags | X86_EFLAGS_IF) & (~X86_EFLAGS_AC));
-}
-PV_CALLEE_SAVE_REGS_THUNK(vsmp_irq_enable);
-
-static unsigned __init vsmp_patch(u8 type, void *ibuf,
-				  unsigned long addr, unsigned len)
-{
-	switch (type) {
-	case PARAVIRT_PATCH(irq.irq_enable):
-	case PARAVIRT_PATCH(irq.irq_disable):
-	case PARAVIRT_PATCH(irq.save_fl):
-	case PARAVIRT_PATCH(irq.restore_fl):
-		return paravirt_patch_default(type, ibuf, addr, len);
-	default:
-		return native_patch(type, ibuf, addr, len);
-	}
-
-}
-
-static void __init set_vsmp_pv_ops(void)
+#ifdef CONFIG_PCI
+static void __init set_vsmp_ctl(void)
 {
 	void __iomem *address;
 	unsigned int cap, ctl, cfg;
@@ -109,28 +52,12 @@ static void __init set_vsmp_pv_ops(void)
 	}
 #endif
 
-	if (cap & ctl & (1 << 4)) {
-		/* Setup irq ops and turn on vSMP  IRQ fastpath handling */
-		pv_ops.irq.irq_disable = PV_CALLEE_SAVE(vsmp_irq_disable);
-		pv_ops.irq.irq_enable = PV_CALLEE_SAVE(vsmp_irq_enable);
-		pv_ops.irq.save_fl = PV_CALLEE_SAVE(vsmp_save_fl);
-		pv_ops.irq.restore_fl = PV_CALLEE_SAVE(vsmp_restore_fl);
-		pv_ops.init.patch = vsmp_patch;
-		ctl &= ~(1 << 4);
-	}
 	writel(ctl, address + 4);
 	ctl = readl(address + 4);
 	pr_info("vSMP CTL: control set to:0x%08x\n", ctl);
 
 	early_iounmap(address, 8);
 }
-#else
-static void __init set_vsmp_pv_ops(void)
-{
-}
-#endif
-
-#ifdef CONFIG_PCI
 static int is_vsmp = -1;
 
 static void __init detect_vsmp_box(void)
@@ -164,11 +91,14 @@ static int is_vsmp_box(void)
 {
 	return 0;
 }
+static void __init set_vsmp_ctl(void)
+{
+}
 #endif
 
 static void __init vsmp_cap_cpus(void)
 {
-#if !defined(CONFIG_X86_VSMP) && defined(CONFIG_SMP)
+#if !defined(CONFIG_X86_VSMP) && defined(CONFIG_SMP) && defined(CONFIG_PCI)
 	void __iomem *address;
 	unsigned int cfg, topology, node_shift, maxcpus;
 
@@ -221,6 +151,6 @@ void __init vsmp_init(void)
 
 	vsmp_cap_cpus();
 
-	set_vsmp_pv_ops();
+	set_vsmp_ctl();
 	return;
 }
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 0d7b3ae..a5d7ed1 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -1905,7 +1905,7 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 	init_top_pgt[0] = __pgd(0);
 
 	/* Pre-constructed entries are in pfn, so convert to mfn */
-	/* L4[272] -> level3_ident_pgt  */
+	/* L4[273] -> level3_ident_pgt  */
 	/* L4[511] -> level3_kernel_pgt */
 	convert_pfn_mfn(init_top_pgt);
 
@@ -1925,8 +1925,8 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 	addr[0] = (unsigned long)pgd;
 	addr[1] = (unsigned long)l3;
 	addr[2] = (unsigned long)l2;
-	/* Graft it onto L4[272][0]. Note that we creating an aliasing problem:
-	 * Both L4[272][0] and L4[511][510] have entries that point to the same
+	/* Graft it onto L4[273][0]. Note that we creating an aliasing problem:
+	 * Both L4[273][0] and L4[511][510] have entries that point to the same
 	 * L2 (PMD) tables. Meaning that if you modify it in __va space
 	 * it will be also modified in the __ka space! (But if you just
 	 * modify the PMD table to point to other PTE's or none, then you
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index b067317..055e37e 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -656,8 +656,7 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 
 	/*
 	 * The interface requires atomic updates on p2m elements.
-	 * xen_safe_write_ulong() is using __put_user which does an atomic
-	 * store via asm().
+	 * xen_safe_write_ulong() is using an atomic store via asm().
 	 */
 	if (likely(!xen_safe_write_ulong(xen_p2m_addr + pfn, mfn)))
 		return true;
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 441c882..1c8a881 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -9,6 +9,7 @@
 #include <linux/log2.h>
 #include <linux/gfp.h>
 #include <linux/slab.h>
+#include <linux/atomic.h>
 
 #include <asm/paravirt.h>
 #include <asm/qspinlock.h>
@@ -21,6 +22,7 @@
 
 static DEFINE_PER_CPU(int, lock_kicker_irq) = -1;
 static DEFINE_PER_CPU(char *, irq_name);
+static DEFINE_PER_CPU(atomic_t, xen_qlock_wait_nest);
 static bool xen_pvspin = true;
 
 static void xen_qlock_kick(int cpu)
@@ -39,25 +41,25 @@ static void xen_qlock_kick(int cpu)
  */
 static void xen_qlock_wait(u8 *byte, u8 val)
 {
-	unsigned long flags;
 	int irq = __this_cpu_read(lock_kicker_irq);
+	atomic_t *nest_cnt = this_cpu_ptr(&xen_qlock_wait_nest);
 
 	/* If kicker interrupts not initialized yet, just spin */
 	if (irq == -1 || in_nmi())
 		return;
 
-	/* Guard against reentry. */
-	local_irq_save(flags);
+	/* Detect reentry. */
+	atomic_inc(nest_cnt);
 
-	/* If irq pending already clear it. */
-	if (xen_test_irq_pending(irq)) {
+	/* If irq pending already and no nested call clear it. */
+	if (atomic_read(nest_cnt) == 1 && xen_test_irq_pending(irq)) {
 		xen_clear_irq_pending(irq);
 	} else if (READ_ONCE(*byte) == val) {
 		/* Block until irq becomes pending (or a spurious wakeup) */
 		xen_poll_irq(irq);
 	}
 
-	local_irq_restore(flags);
+	atomic_dec(nest_cnt);
 }
 
 static irqreturn_t dummy_handler(int irq, void *dev_id)
diff --git a/block/bio.c b/block/bio.c
index d5368a4..a50d592 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1260,6 +1260,7 @@ struct bio *bio_copy_user_iov(struct request_queue *q,
 		if (ret)
 			goto cleanup;
 	} else {
+		zero_fill_bio(bio);
 		iov_iter_advance(iter, bio->bi_iter.bi_size);
 	}
 
diff --git a/block/blk-lib.c b/block/blk-lib.c
index 76f867e..e8b3bb9 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -51,16 +51,12 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 	if ((sector | nr_sects) & bs_mask)
 		return -EINVAL;
 
+	if (!nr_sects)
+		return -EINVAL;
+
 	while (nr_sects) {
-		unsigned int req_sects = nr_sects;
-		sector_t end_sect;
-
-		if (!req_sects)
-			goto fail;
-		if (req_sects > UINT_MAX >> 9)
-			req_sects = UINT_MAX >> 9;
-
-		end_sect = sector + req_sects;
+		unsigned int req_sects = min_t(unsigned int, nr_sects,
+				bio_allowed_max_sectors(q));
 
 		bio = blk_next_bio(bio, 0, gfp_mask);
 		bio->bi_iter.bi_sector = sector;
@@ -68,8 +64,8 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		bio_set_op_attrs(bio, op, 0);
 
 		bio->bi_iter.bi_size = req_sects << 9;
+		sector += req_sects;
 		nr_sects -= req_sects;
-		sector = end_sect;
 
 		/*
 		 * We can loop for a long time in here, if someone does
@@ -82,14 +78,6 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 
 	*biop = bio;
 	return 0;
-
-fail:
-	if (bio) {
-		submit_bio_wait(bio);
-		bio_put(bio);
-	}
-	*biop = NULL;
-	return -EOPNOTSUPP;
 }
 EXPORT_SYMBOL(__blkdev_issue_discard);
 
@@ -161,7 +149,7 @@ static int __blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 		return -EOPNOTSUPP;
 
 	/* Ensure that max_write_same_sectors doesn't overflow bi_size */
-	max_write_same_sectors = UINT_MAX >> 9;
+	max_write_same_sectors = bio_allowed_max_sectors(q);
 
 	while (nr_sects) {
 		bio = blk_next_bio(bio, 1, gfp_mask);
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 6b5ad27..e7696c4 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -46,7 +46,7 @@ static inline bool bio_will_gap(struct request_queue *q,
 		bio_get_first_bvec(prev_rq->bio, &pb);
 	else
 		bio_get_first_bvec(prev, &pb);
-	if (pb.bv_offset)
+	if (pb.bv_offset & queue_virt_boundary(q))
 		return true;
 
 	/*
@@ -90,7 +90,8 @@ static struct bio *blk_bio_discard_split(struct request_queue *q,
 	/* Zero-sector (unknown) and one-sector granularities are the same.  */
 	granularity = max(q->limits.discard_granularity >> 9, 1U);
 
-	max_discard_sectors = min(q->limits.max_discard_sectors, UINT_MAX >> 9);
+	max_discard_sectors = min(q->limits.max_discard_sectors,
+			bio_allowed_max_sectors(q));
 	max_discard_sectors -= max_discard_sectors % granularity;
 
 	if (unlikely(!max_discard_sectors)) {
diff --git a/block/blk.h b/block/blk.h
index a1841b8..0089fef 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -169,7 +169,7 @@ static inline bool biovec_phys_mergeable(struct request_queue *q,
 static inline bool __bvec_gap_to_prev(struct request_queue *q,
 		struct bio_vec *bprv, unsigned int offset)
 {
-	return offset ||
+	return (offset & queue_virt_boundary(q)) ||
 		((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q));
 }
 
@@ -396,6 +396,16 @@ static inline unsigned long blk_rq_deadline(struct request *rq)
 }
 
 /*
+ * The max size one bio can handle is UINT_MAX becasue bvec_iter.bi_size
+ * is defined as 'unsigned int', meantime it has to aligned to with logical
+ * block size which is the minimum accepted unit by hardware.
+ */
+static inline unsigned int bio_allowed_max_sectors(struct request_queue *q)
+{
+	return round_down(UINT_MAX, queue_logical_block_size(q)) >> 9;
+}
+
+/*
  * Internal io_context interface
  */
 void get_io_context(struct io_context *ioc);
diff --git a/drivers/acpi/nfit/mce.c b/drivers/acpi/nfit/mce.c
index e9626bf..d6c1b10 100644
--- a/drivers/acpi/nfit/mce.c
+++ b/drivers/acpi/nfit/mce.c
@@ -25,8 +25,12 @@ static int nfit_handle_mce(struct notifier_block *nb, unsigned long val,
 	struct acpi_nfit_desc *acpi_desc;
 	struct nfit_spa *nfit_spa;
 
-	/* We only care about memory errors */
-	if (!mce_is_memory_error(mce))
+	/* We only care about uncorrectable memory errors */
+	if (!mce_is_memory_error(mce) || mce_is_correctable(mce))
+		return NOTIFY_DONE;
+
+	/* Verify the address reported in the MCE is valid. */
+	if (!mce_usable_address(mce))
 		return NOTIFY_DONE;
 
 	/*
diff --git a/drivers/ata/sata_rcar.c b/drivers/ata/sata_rcar.c
index 10ecb232..4b1ff5b 100644
--- a/drivers/ata/sata_rcar.c
+++ b/drivers/ata/sata_rcar.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Renesas R-Car SATA driver
  *
  * Author: Vladimir Barinov <source@cogentembedded.com>
  * Copyright (C) 2013-2015 Cogent Embedded, Inc.
  * Copyright (C) 2013-2015 Renesas Solutions Corp.
- *
- * 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/kernel.h>
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 56452ca..0ed4b20 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -1919,6 +1919,7 @@ static int negotiate_mq(struct blkfront_info *info)
 			      GFP_KERNEL);
 	if (!info->rinfo) {
 		xenbus_dev_fatal(info->xbdev, -ENOMEM, "allocating ring_info structure");
+		info->nr_rings = 0;
 		return -ENOMEM;
 	}
 
diff --git a/drivers/clk/clk-fixed-factor.c b/drivers/clk/clk-fixed-factor.c
index ef0ca94..ff83e89 100644
--- a/drivers/clk/clk-fixed-factor.c
+++ b/drivers/clk/clk-fixed-factor.c
@@ -210,6 +210,7 @@ static int of_fixed_factor_clk_remove(struct platform_device *pdev)
 {
 	struct clk *clk = platform_get_drvdata(pdev);
 
+	of_clk_del_provider(pdev->dev.of_node);
 	clk_unregister_fixed_factor(clk);
 
 	return 0;
diff --git a/drivers/clk/meson/axg.c b/drivers/clk/meson/axg.c
index c981159..792735d 100644
--- a/drivers/clk/meson/axg.c
+++ b/drivers/clk/meson/axg.c
@@ -325,6 +325,7 @@ static struct clk_regmap axg_fclk_div2 = {
 		.ops = &clk_regmap_gate_ops,
 		.parent_names = (const char *[]){ "fclk_div2_div" },
 		.num_parents = 1,
+		.flags = CLK_IS_CRITICAL,
 	},
 };
 
@@ -349,6 +350,18 @@ static struct clk_regmap axg_fclk_div3 = {
 		.ops = &clk_regmap_gate_ops,
 		.parent_names = (const char *[]){ "fclk_div3_div" },
 		.num_parents = 1,
+		/*
+		 * FIXME:
+		 * This clock, as fdiv2, is used by the SCPI FW and is required
+		 * by the platform to operate correctly.
+		 * Until the following condition are met, we need this clock to
+		 * be marked as critical:
+		 * a) The SCPI generic driver claims and enable all the clocks
+		 *    it needs
+		 * b) CCF has a clock hand-off mechanism to make the sure the
+		 *    clock stays on until the proper driver comes along
+		 */
+		.flags = CLK_IS_CRITICAL,
 	},
 };
 
diff --git a/drivers/clk/meson/gxbb.c b/drivers/clk/meson/gxbb.c
index 9309cfa..4ada966 100644
--- a/drivers/clk/meson/gxbb.c
+++ b/drivers/clk/meson/gxbb.c
@@ -506,6 +506,18 @@ static struct clk_regmap gxbb_fclk_div3 = {
 		.ops = &clk_regmap_gate_ops,
 		.parent_names = (const char *[]){ "fclk_div3_div" },
 		.num_parents = 1,
+		/*
+		 * FIXME:
+		 * This clock, as fdiv2, is used by the SCPI FW and is required
+		 * by the platform to operate correctly.
+		 * Until the following condition are met, we need this clock to
+		 * be marked as critical:
+		 * a) The SCPI generic driver claims and enable all the clocks
+		 *    it needs
+		 * b) CCF has a clock hand-off mechanism to make the sure the
+		 *    clock stays on until the proper driver comes along
+		 */
+		.flags = CLK_IS_CRITICAL,
 	},
 };
 
diff --git a/drivers/clk/qcom/gcc-qcs404.c b/drivers/clk/qcom/gcc-qcs404.c
index e4ca6a4..ef1b267 100644
--- a/drivers/clk/qcom/gcc-qcs404.c
+++ b/drivers/clk/qcom/gcc-qcs404.c
@@ -265,7 +265,7 @@ static struct clk_fixed_factor cxo = {
 	.div = 1,
 	.hw.init = &(struct clk_init_data){
 		.name = "cxo",
-		.parent_names = (const char *[]){ "xo_board" },
+		.parent_names = (const char *[]){ "xo-board" },
 		.num_parents = 1,
 		.ops = &clk_fixed_factor_ops,
 	},
diff --git a/drivers/clocksource/i8253.c b/drivers/clocksource/i8253.c
index 9c38895..d4350bb 100644
--- a/drivers/clocksource/i8253.c
+++ b/drivers/clocksource/i8253.c
@@ -20,6 +20,13 @@
 DEFINE_RAW_SPINLOCK(i8253_lock);
 EXPORT_SYMBOL(i8253_lock);
 
+/*
+ * Handle PIT quirk in pit_shutdown() where zeroing the counter register
+ * restarts the PIT, negating the shutdown. On platforms with the quirk,
+ * platform specific code can set this to false.
+ */
+bool i8253_clear_counter_on_shutdown __ro_after_init = true;
+
 #ifdef CONFIG_CLKSRC_I8253
 /*
  * Since the PIT overflows every tick, its not very useful
@@ -109,8 +116,11 @@ static int pit_shutdown(struct clock_event_device *evt)
 	raw_spin_lock(&i8253_lock);
 
 	outb_p(0x30, PIT_MODE);
-	outb_p(0, PIT_CH0);
-	outb_p(0, PIT_CH0);
+
+	if (i8253_clear_counter_on_shutdown) {
+		outb_p(0, PIT_CH0);
+		outb_p(0, PIT_CH0);
+	}
 
 	raw_spin_unlock(&i8253_lock);
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index d0102cf..104b2e0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -151,6 +151,7 @@ extern int amdgpu_compute_multipipe;
 extern int amdgpu_gpu_recovery;
 extern int amdgpu_emu_mode;
 extern uint amdgpu_smu_memory_pool_size;
+extern uint amdgpu_dc_feature_mask;
 extern struct amdgpu_mgpu_info mgpu_info;
 
 #ifdef CONFIG_DRM_AMDGPU_SI
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 943dbf3..8de55f7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -127,6 +127,9 @@ int amdgpu_compute_multipipe = -1;
 int amdgpu_gpu_recovery = -1; /* auto */
 int amdgpu_emu_mode = 0;
 uint amdgpu_smu_memory_pool_size = 0;
+/* FBC (bit 0) disabled by default*/
+uint amdgpu_dc_feature_mask = 0;
+
 struct amdgpu_mgpu_info mgpu_info = {
 	.mutex = __MUTEX_INITIALIZER(mgpu_info.mutex),
 };
@@ -631,6 +634,14 @@ module_param(halt_if_hws_hang, int, 0644);
 MODULE_PARM_DESC(halt_if_hws_hang, "Halt if HWS hang is detected (0 = off (default), 1 = on)");
 #endif
 
+/**
+ * DOC: dcfeaturemask (uint)
+ * Override display features enabled. See enum DC_FEATURE_MASK in drivers/gpu/drm/amd/include/amd_shared.h.
+ * The default is the current set of stable display features.
+ */
+MODULE_PARM_DESC(dcfeaturemask, "all stable DC features enabled (default))");
+module_param_named(dcfeaturemask, amdgpu_dc_feature_mask, uint, 0444);
+
 static const struct pci_device_id pciidlist[] = {
 #ifdef  CONFIG_DRM_AMDGPU_SI
 	{0x1002, 0x6780, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TAHITI},
diff --git a/drivers/gpu/drm/amd/amdgpu/vega20_reg_init.c b/drivers/gpu/drm/amd/amdgpu/vega20_reg_init.c
index 2d44735..d13fc4f 100644
--- a/drivers/gpu/drm/amd/amdgpu/vega20_reg_init.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega20_reg_init.c
@@ -49,6 +49,7 @@ int vega20_reg_base_init(struct amdgpu_device *adev)
 		adev->reg_offset[SMUIO_HWIP][i] = (uint32_t *)(&(SMUIO_BASE.instance[i]));
 		adev->reg_offset[NBIF_HWIP][i] = (uint32_t *)(&(NBIO_BASE.instance[i]));
 		adev->reg_offset[THM_HWIP][i] = (uint32_t *)(&(THM_BASE.instance[i]));
+		adev->reg_offset[CLK_HWIP][i] = (uint32_t *)(&(CLK_BASE.instance[i]));
 	}
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index b0df6dc..c1262f6 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -429,6 +429,9 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 	    adev->asic_type < CHIP_RAVEN)
 		init_data.flags.gpu_vm_support = true;
 
+	if (amdgpu_dc_feature_mask & DC_FBC_MASK)
+		init_data.flags.fbc_support = true;
+
 	/* Display Core create. */
 	adev->dm.dc = dc_create(&init_data);
 
@@ -1524,13 +1527,6 @@ static int amdgpu_dm_backlight_update_status(struct backlight_device *bd)
 {
 	struct amdgpu_display_manager *dm = bl_get_data(bd);
 
-	/*
-	 * PWM interperts 0 as 100% rather than 0% because of HW
-	 * limitation for level 0.So limiting minimum brightness level
-	 * to 1.
-	 */
-	if (bd->props.brightness < 1)
-		return 1;
 	if (dc_link_set_backlight_level(dm->backlight_link,
 			bd->props.brightness, 0, 0))
 		return 0;
@@ -2707,18 +2703,11 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector,
 	drm_connector = &aconnector->base;
 
 	if (!aconnector->dc_sink) {
-		/*
-		 * Create dc_sink when necessary to MST
-		 * Don't apply fake_sink to MST
-		 */
-		if (aconnector->mst_port) {
-			dm_dp_mst_dc_sink_create(drm_connector);
-			return stream;
+		if (!aconnector->mst_port) {
+			sink = create_fake_sink(aconnector);
+			if (!sink)
+				return stream;
 		}
-
-		sink = create_fake_sink(aconnector);
-		if (!sink)
-			return stream;
 	} else {
 		sink = aconnector->dc_sink;
 	}
@@ -3308,7 +3297,7 @@ void dm_drm_plane_destroy_state(struct drm_plane *plane,
 static const struct drm_plane_funcs dm_plane_funcs = {
 	.update_plane	= drm_atomic_helper_update_plane,
 	.disable_plane	= drm_atomic_helper_disable_plane,
-	.destroy	= drm_plane_cleanup,
+	.destroy	= drm_primary_helper_destroy,
 	.reset = dm_drm_plane_reset,
 	.atomic_duplicate_state = dm_drm_plane_duplicate_state,
 	.atomic_destroy_state = dm_drm_plane_destroy_state,
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index 978b34a..924a38a 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -160,8 +160,6 @@ struct amdgpu_dm_connector {
 	struct mutex hpd_lock;
 
 	bool fake_enable;
-
-	bool mst_connected;
 };
 
 #define to_amdgpu_dm_connector(x) container_of(x, struct amdgpu_dm_connector, base)
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index 03601d7..d02c32a 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -205,40 +205,6 @@ static const struct drm_connector_funcs dm_dp_mst_connector_funcs = {
 	.atomic_get_property = amdgpu_dm_connector_atomic_get_property
 };
 
-void dm_dp_mst_dc_sink_create(struct drm_connector *connector)
-{
-	struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
-	struct dc_sink *dc_sink;
-	struct dc_sink_init_data init_params = {
-			.link = aconnector->dc_link,
-			.sink_signal = SIGNAL_TYPE_DISPLAY_PORT_MST };
-
-	/* FIXME none of this is safe. we shouldn't touch aconnector here in
-	 * atomic_check
-	 */
-
-	/*
-	 * TODO: Need to further figure out why ddc.algo is NULL while MST port exists
-	 */
-	if (!aconnector->port || !aconnector->port->aux.ddc.algo)
-		return;
-
-	ASSERT(aconnector->edid);
-
-	dc_sink = dc_link_add_remote_sink(
-		aconnector->dc_link,
-		(uint8_t *)aconnector->edid,
-		(aconnector->edid->extensions + 1) * EDID_LENGTH,
-		&init_params);
-
-	dc_sink->priv = aconnector;
-	aconnector->dc_sink = dc_sink;
-
-	if (aconnector->dc_sink)
-		amdgpu_dm_update_freesync_caps(
-				connector, aconnector->edid);
-}
-
 static int dm_dp_mst_get_modes(struct drm_connector *connector)
 {
 	struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
@@ -319,12 +285,7 @@ dm_dp_create_fake_mst_encoder(struct amdgpu_dm_connector *connector)
 	struct amdgpu_device *adev = dev->dev_private;
 	struct amdgpu_encoder *amdgpu_encoder;
 	struct drm_encoder *encoder;
-	const struct drm_connector_helper_funcs *connector_funcs =
-		connector->base.helper_private;
-	struct drm_encoder *enc_master =
-		connector_funcs->best_encoder(&connector->base);
 
-	DRM_DEBUG_KMS("enc master is %p\n", enc_master);
 	amdgpu_encoder = kzalloc(sizeof(*amdgpu_encoder), GFP_KERNEL);
 	if (!amdgpu_encoder)
 		return NULL;
@@ -354,25 +315,6 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr,
 	struct amdgpu_device *adev = dev->dev_private;
 	struct amdgpu_dm_connector *aconnector;
 	struct drm_connector *connector;
-	struct drm_connector_list_iter conn_iter;
-
-	drm_connector_list_iter_begin(dev, &conn_iter);
-	drm_for_each_connector_iter(connector, &conn_iter) {
-		aconnector = to_amdgpu_dm_connector(connector);
-		if (aconnector->mst_port == master
-				&& !aconnector->port) {
-			DRM_INFO("DM_MST: reusing connector: %p [id: %d] [master: %p]\n",
-						aconnector, connector->base.id, aconnector->mst_port);
-
-			aconnector->port = port;
-			drm_connector_set_path_property(connector, pathprop);
-
-			drm_connector_list_iter_end(&conn_iter);
-			aconnector->mst_connected = true;
-			return &aconnector->base;
-		}
-	}
-	drm_connector_list_iter_end(&conn_iter);
 
 	aconnector = kzalloc(sizeof(*aconnector), GFP_KERNEL);
 	if (!aconnector)
@@ -421,8 +363,6 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr,
 	 */
 	amdgpu_dm_connector_funcs_reset(connector);
 
-	aconnector->mst_connected = true;
-
 	DRM_INFO("DM_MST: added connector: %p [id: %d] [master: %p]\n",
 			aconnector, connector->base.id, aconnector->mst_port);
 
@@ -434,6 +374,9 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr,
 static void dm_dp_destroy_mst_connector(struct drm_dp_mst_topology_mgr *mgr,
 					struct drm_connector *connector)
 {
+	struct amdgpu_dm_connector *master = container_of(mgr, struct amdgpu_dm_connector, mst_mgr);
+	struct drm_device *dev = master->base.dev;
+	struct amdgpu_device *adev = dev->dev_private;
 	struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
 
 	DRM_INFO("DM_MST: Disabling connector: %p [id: %d] [master: %p]\n",
@@ -447,7 +390,10 @@ static void dm_dp_destroy_mst_connector(struct drm_dp_mst_topology_mgr *mgr,
 		aconnector->dc_sink = NULL;
 	}
 
-	aconnector->mst_connected = false;
+	drm_connector_unregister(connector);
+	if (adev->mode_info.rfbdev)
+		drm_fb_helper_remove_one_connector(&adev->mode_info.rfbdev->helper, connector);
+	drm_connector_put(connector);
 }
 
 static void dm_dp_mst_hotplug(struct drm_dp_mst_topology_mgr *mgr)
@@ -458,18 +404,10 @@ static void dm_dp_mst_hotplug(struct drm_dp_mst_topology_mgr *mgr)
 	drm_kms_helper_hotplug_event(dev);
 }
 
-static void dm_dp_mst_link_status_reset(struct drm_connector *connector)
-{
-	mutex_lock(&connector->dev->mode_config.mutex);
-	drm_connector_set_link_status_property(connector, DRM_MODE_LINK_STATUS_BAD);
-	mutex_unlock(&connector->dev->mode_config.mutex);
-}
-
 static void dm_dp_mst_register_connector(struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
 	struct amdgpu_device *adev = dev->dev_private;
-	struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
 
 	if (adev->mode_info.rfbdev)
 		drm_fb_helper_add_one_connector(&adev->mode_info.rfbdev->helper, connector);
@@ -477,9 +415,6 @@ static void dm_dp_mst_register_connector(struct drm_connector *connector)
 		DRM_ERROR("adev->mode_info.rfbdev is NULL\n");
 
 	drm_connector_register(connector);
-
-	if (aconnector->mst_connected)
-		dm_dp_mst_link_status_reset(connector);
 }
 
 static const struct drm_dp_mst_topology_cbs dm_mst_cbs = {
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
index 8cf51da..2da851b 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
@@ -31,6 +31,5 @@ struct amdgpu_dm_connector;
 
 void amdgpu_dm_initialize_dp_connector(struct amdgpu_display_manager *dm,
 				       struct amdgpu_dm_connector *aconnector);
-void dm_dp_mst_dc_sink_create(struct drm_connector *connector);
 
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index fb04a4a..5da2186 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -1722,7 +1722,7 @@ static void write_i2c_retimer_setting(
 		i2c_success = i2c_write(pipe_ctx, slave_address,
 				buffer, sizeof(buffer));
 		RETIMER_REDRIVER_INFO("retimer write to slave_address = 0x%x,\
-			offset = 0x%d, reg_val = 0x%d, i2c_success = %d\n",
+			offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n",
 			slave_address, buffer[0], buffer[1], i2c_success?1:0);
 		if (!i2c_success)
 			/* Write failure */
@@ -1734,7 +1734,7 @@ static void write_i2c_retimer_setting(
 		i2c_success = i2c_write(pipe_ctx, slave_address,
 				buffer, sizeof(buffer));
 		RETIMER_REDRIVER_INFO("retimer write to slave_address = 0x%x,\
-			offset = 0x%d, reg_val = 0x%d, i2c_success = %d\n",
+			offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n",
 			slave_address, buffer[0], buffer[1], i2c_success?1:0);
 		if (!i2c_success)
 			/* Write failure */
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 1995271..b57fa61 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -169,6 +169,7 @@ struct link_training_settings;
 struct dc_config {
 	bool gpu_vm_support;
 	bool disable_disp_pll_sharing;
+	bool fbc_support;
 };
 
 enum visual_confirm {
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
index b75ede5..b459867 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
@@ -1736,7 +1736,12 @@ static void set_static_screen_control(struct pipe_ctx **pipe_ctx,
 	if (events->force_trigger)
 		value |= 0x1;
 
-	value |= 0x84;
+	if (num_pipes) {
+		struct dc *dc = pipe_ctx[0]->stream->ctx->dc;
+
+		if (dc->fbc_compressor)
+			value |= 0x84;
+	}
 
 	for (i = 0; i < num_pipes; i++)
 		pipe_ctx[i]->stream_res.tg->funcs->
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
index e3624ca..7c9fd90 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
@@ -1362,7 +1362,8 @@ static bool construct(
 		pool->base.sw_i2cs[i] = NULL;
 	}
 
-	dc->fbc_compressor = dce110_compressor_create(ctx);
+	if (dc->config.fbc_support)
+		dc->fbc_compressor = dce110_compressor_create(ctx);
 
 	if (!underlay_create(ctx, &pool->base))
 		goto res_create_fail;
diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h
index 2083c30..470d7b8 100644
--- a/drivers/gpu/drm/amd/include/amd_shared.h
+++ b/drivers/gpu/drm/amd/include/amd_shared.h
@@ -133,6 +133,10 @@ enum PP_FEATURE_MASK {
 	PP_AVFS_MASK = 0x40000,
 };
 
+enum DC_FEATURE_MASK {
+	DC_FBC_MASK = 0x1,
+};
+
 /**
  * struct amd_ip_funcs - general hooks for managing amdgpu IP Blocks
  */
diff --git a/drivers/gpu/drm/amd/include/atomfirmware.h b/drivers/gpu/drm/amd/include/atomfirmware.h
index d2e7c0f..8eb0bb2 100644
--- a/drivers/gpu/drm/amd/include/atomfirmware.h
+++ b/drivers/gpu/drm/amd/include/atomfirmware.h
@@ -1325,7 +1325,7 @@ struct atom_smu_info_v3_3 {
   struct   atom_common_table_header  table_header;
   uint8_t  smuip_min_ver;
   uint8_t  smuip_max_ver;
-  uint8_t  smu_rsd1;
+  uint8_t  waflclk_ss_mode;
   uint8_t  gpuclk_ss_mode;
   uint16_t sclk_ss_percentage;
   uint16_t sclk_ss_rate_10hz;
@@ -1355,7 +1355,10 @@ struct atom_smu_info_v3_3 {
   uint32_t syspll3_1_vco_freq_10khz;
   uint32_t bootup_fclk_10khz;
   uint32_t bootup_waflclk_10khz;
-  uint32_t reserved[3];
+  uint32_t smu_info_caps;
+  uint16_t waflclk_ss_percentage;    // in unit of 0.001%
+  uint16_t smuinitoffset;
+  uint32_t reserved;
 };
 
 /*
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c
index 57143d5..99861f3 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c
@@ -120,6 +120,7 @@ static void vega20_set_default_registry_data(struct pp_hwmgr *hwmgr)
 	data->registry_data.disable_auto_wattman = 1;
 	data->registry_data.auto_wattman_debug = 0;
 	data->registry_data.auto_wattman_sample_period = 100;
+	data->registry_data.fclk_gfxclk_ratio = 0x3F6CCCCD;
 	data->registry_data.auto_wattman_threshold = 50;
 	data->registry_data.gfxoff_controlled_by_driver = 1;
 	data->gfxoff_allowed = false;
@@ -829,6 +830,28 @@ static int vega20_enable_all_smu_features(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
+static int vega20_notify_smc_display_change(struct pp_hwmgr *hwmgr)
+{
+	struct vega20_hwmgr *data = (struct vega20_hwmgr *)(hwmgr->backend);
+
+	if (data->smu_features[GNLD_DPM_UCLK].enabled)
+		return smum_send_msg_to_smc_with_parameter(hwmgr,
+			PPSMC_MSG_SetUclkFastSwitch,
+			1);
+
+	return 0;
+}
+
+static int vega20_send_clock_ratio(struct pp_hwmgr *hwmgr)
+{
+	struct vega20_hwmgr *data =
+			(struct vega20_hwmgr *)(hwmgr->backend);
+
+	return smum_send_msg_to_smc_with_parameter(hwmgr,
+			PPSMC_MSG_SetFclkGfxClkRatio,
+			data->registry_data.fclk_gfxclk_ratio);
+}
+
 static int vega20_disable_all_smu_features(struct pp_hwmgr *hwmgr)
 {
 	struct vega20_hwmgr *data =
@@ -1532,6 +1555,16 @@ static int vega20_enable_dpm_tasks(struct pp_hwmgr *hwmgr)
 			"[EnableDPMTasks] Failed to enable all smu features!",
 			return result);
 
+	result = vega20_notify_smc_display_change(hwmgr);
+	PP_ASSERT_WITH_CODE(!result,
+			"[EnableDPMTasks] Failed to notify smc display change!",
+			return result);
+
+	result = vega20_send_clock_ratio(hwmgr);
+	PP_ASSERT_WITH_CODE(!result,
+			"[EnableDPMTasks] Failed to send clock ratio!",
+			return result);
+
 	/* Initialize UVD/VCE powergating state */
 	vega20_init_powergate_state(hwmgr);
 
@@ -1972,19 +2005,6 @@ static int vega20_read_sensor(struct pp_hwmgr *hwmgr, int idx,
 	return ret;
 }
 
-static int vega20_notify_smc_display_change(struct pp_hwmgr *hwmgr,
-		bool has_disp)
-{
-	struct vega20_hwmgr *data = (struct vega20_hwmgr *)(hwmgr->backend);
-
-	if (data->smu_features[GNLD_DPM_UCLK].enabled)
-		return smum_send_msg_to_smc_with_parameter(hwmgr,
-			PPSMC_MSG_SetUclkFastSwitch,
-			has_disp ? 1 : 0);
-
-	return 0;
-}
-
 int vega20_display_clock_voltage_request(struct pp_hwmgr *hwmgr,
 		struct pp_display_clock_request *clock_req)
 {
@@ -2044,13 +2064,6 @@ static int vega20_notify_smc_display_config_after_ps_adjustment(
 	struct pp_display_clock_request clock_req;
 	int ret = 0;
 
-	if ((hwmgr->display_config->num_display > 1) &&
-	     !hwmgr->display_config->multi_monitor_in_sync &&
-	     !hwmgr->display_config->nb_pstate_switch_disable)
-		vega20_notify_smc_display_change(hwmgr, false);
-	else
-		vega20_notify_smc_display_change(hwmgr, true);
-
 	min_clocks.dcefClock = hwmgr->display_config->min_dcef_set_clk;
 	min_clocks.dcefClockInSR = hwmgr->display_config->min_dcef_deep_sleep_set_clk;
 	min_clocks.memoryClock = hwmgr->display_config->min_mem_set_clock;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.h b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.h
index 56fe6a0..25faaa5 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.h
@@ -328,6 +328,7 @@ struct vega20_registry_data {
 	uint8_t   disable_auto_wattman;
 	uint32_t  auto_wattman_debug;
 	uint32_t  auto_wattman_sample_period;
+	uint32_t  fclk_gfxclk_ratio;
 	uint8_t   auto_wattman_threshold;
 	uint8_t   log_avfs_param;
 	uint8_t   enable_enginess;
diff --git a/drivers/gpu/drm/amd/powerplay/inc/vega20_ppsmc.h b/drivers/gpu/drm/amd/powerplay/inc/vega20_ppsmc.h
index 45d64a8..4f63a73 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/vega20_ppsmc.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/vega20_ppsmc.h
@@ -105,7 +105,8 @@
 #define PPSMC_MSG_SetSystemVirtualDramAddrHigh   0x4B
 #define PPSMC_MSG_SetSystemVirtualDramAddrLow    0x4C
 #define PPSMC_MSG_WaflTest                       0x4D
-// Unused ID 0x4E to 0x50
+#define PPSMC_MSG_SetFclkGfxClkRatio             0x4E
+// Unused ID 0x4F to 0x50
 #define PPSMC_MSG_AllowGfxOff                    0x51
 #define PPSMC_MSG_DisallowGfxOff                 0x52
 #define PPSMC_MSG_GetPptLimit                    0x53
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
index e7c3ed6..9b47636 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
@@ -93,7 +93,7 @@ static void etnaviv_sched_timedout_job(struct drm_sched_job *sched_job)
 	 * If the GPU managed to complete this jobs fence, the timout is
 	 * spurious. Bail out.
 	 */
-	if (fence_completed(gpu, submit->out_fence->seqno))
+	if (dma_fence_is_signaled(submit->out_fence))
 		return;
 
 	/*
diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
index 94529aa..aef487d 100644
--- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
@@ -164,13 +164,6 @@ static u32 decon_get_frame_count(struct decon_context *ctx, bool end)
 	return frm;
 }
 
-static u32 decon_get_vblank_counter(struct exynos_drm_crtc *crtc)
-{
-	struct decon_context *ctx = crtc->ctx;
-
-	return decon_get_frame_count(ctx, false);
-}
-
 static void decon_setup_trigger(struct decon_context *ctx)
 {
 	if (!ctx->crtc->i80_mode && !(ctx->out_type & I80_HW_TRG))
@@ -536,7 +529,6 @@ static const struct exynos_drm_crtc_ops decon_crtc_ops = {
 	.disable		= decon_disable,
 	.enable_vblank		= decon_enable_vblank,
 	.disable_vblank		= decon_disable_vblank,
-	.get_vblank_counter	= decon_get_vblank_counter,
 	.atomic_begin		= decon_atomic_begin,
 	.update_plane		= decon_update_plane,
 	.disable_plane		= decon_disable_plane,
@@ -554,7 +546,6 @@ static int decon_bind(struct device *dev, struct device *master, void *data)
 	int ret;
 
 	ctx->drm_dev = drm_dev;
-	drm_dev->max_vblank_count = 0xffffffff;
 
 	for (win = ctx->first_win; win < WINDOWS_NR; win++) {
 		ctx->configs[win].pixel_formats = decon_formats;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_crtc.c b/drivers/gpu/drm/exynos/exynos_drm_crtc.c
index eea9025..2696289 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_crtc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_crtc.c
@@ -162,16 +162,6 @@ static void exynos_drm_crtc_disable_vblank(struct drm_crtc *crtc)
 		exynos_crtc->ops->disable_vblank(exynos_crtc);
 }
 
-static u32 exynos_drm_crtc_get_vblank_counter(struct drm_crtc *crtc)
-{
-	struct exynos_drm_crtc *exynos_crtc = to_exynos_crtc(crtc);
-
-	if (exynos_crtc->ops->get_vblank_counter)
-		return exynos_crtc->ops->get_vblank_counter(exynos_crtc);
-
-	return 0;
-}
-
 static const struct drm_crtc_funcs exynos_crtc_funcs = {
 	.set_config	= drm_atomic_helper_set_config,
 	.page_flip	= drm_atomic_helper_page_flip,
@@ -181,7 +171,6 @@ static const struct drm_crtc_funcs exynos_crtc_funcs = {
 	.atomic_destroy_state = drm_atomic_helper_crtc_destroy_state,
 	.enable_vblank = exynos_drm_crtc_enable_vblank,
 	.disable_vblank = exynos_drm_crtc_disable_vblank,
-	.get_vblank_counter = exynos_drm_crtc_get_vblank_counter,
 };
 
 struct exynos_drm_crtc *exynos_drm_crtc_create(struct drm_device *drm_dev,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h
index ec9604f..5e61e70 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h
@@ -135,7 +135,6 @@ struct exynos_drm_crtc_ops {
 	void (*disable)(struct exynos_drm_crtc *crtc);
 	int (*enable_vblank)(struct exynos_drm_crtc *crtc);
 	void (*disable_vblank)(struct exynos_drm_crtc *crtc);
-	u32 (*get_vblank_counter)(struct exynos_drm_crtc *crtc);
 	enum drm_mode_status (*mode_valid)(struct exynos_drm_crtc *crtc,
 		const struct drm_display_mode *mode);
 	bool (*mode_fixup)(struct exynos_drm_crtc *crtc,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
index 07af775..d81e62a 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
@@ -14,6 +14,7 @@
 
 #include <drm/drmP.h>
 #include <drm/drm_crtc_helper.h>
+#include <drm/drm_fb_helper.h>
 #include <drm/drm_mipi_dsi.h>
 #include <drm/drm_panel.h>
 #include <drm/drm_atomic_helper.h>
@@ -1474,12 +1475,12 @@ static int exynos_dsi_create_connector(struct drm_encoder *encoder)
 {
 	struct exynos_dsi *dsi = encoder_to_dsi(encoder);
 	struct drm_connector *connector = &dsi->connector;
+	struct drm_device *drm = encoder->dev;
 	int ret;
 
 	connector->polled = DRM_CONNECTOR_POLL_HPD;
 
-	ret = drm_connector_init(encoder->dev, connector,
-				 &exynos_dsi_connector_funcs,
+	ret = drm_connector_init(drm, connector, &exynos_dsi_connector_funcs,
 				 DRM_MODE_CONNECTOR_DSI);
 	if (ret) {
 		DRM_ERROR("Failed to initialize connector with drm\n");
@@ -1489,7 +1490,12 @@ static int exynos_dsi_create_connector(struct drm_encoder *encoder)
 	connector->status = connector_status_disconnected;
 	drm_connector_helper_add(connector, &exynos_dsi_connector_helper_funcs);
 	drm_connector_attach_encoder(connector, encoder);
+	if (!drm->registered)
+		return 0;
 
+	connector->funcs->reset(connector);
+	drm_fb_helper_add_one_connector(drm->fb_helper, connector);
+	drm_connector_register(connector);
 	return 0;
 }
 
@@ -1527,7 +1533,9 @@ static int exynos_dsi_host_attach(struct mipi_dsi_host *host,
 		}
 
 		dsi->panel = of_drm_find_panel(device->dev.of_node);
-		if (dsi->panel) {
+		if (IS_ERR(dsi->panel)) {
+			dsi->panel = NULL;
+		} else {
 			drm_panel_attach(dsi->panel, &dsi->connector);
 			dsi->connector.status = connector_status_connected;
 		}
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
index 918dd2c..01d1822 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
@@ -192,7 +192,7 @@ int exynos_drm_fbdev_init(struct drm_device *dev)
 	struct drm_fb_helper *helper;
 	int ret;
 
-	if (!dev->mode_config.num_crtc || !dev->mode_config.num_connector)
+	if (!dev->mode_config.num_crtc)
 		return 0;
 
 	fbdev = kzalloc(sizeof(*fbdev), GFP_KERNEL);
diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 2402395..58e166e 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -1905,7 +1905,6 @@ static struct intel_vgpu_mm *intel_vgpu_create_ggtt_mm(struct intel_vgpu *vgpu)
 		vgpu_free_mm(mm);
 		return ERR_PTR(-ENOMEM);
 	}
-	mm->ggtt_mm.last_partial_off = -1UL;
 
 	return mm;
 }
@@ -1930,7 +1929,6 @@ void _intel_vgpu_mm_release(struct kref *mm_ref)
 		invalidate_ppgtt_mm(mm);
 	} else {
 		vfree(mm->ggtt_mm.virtual_ggtt);
-		mm->ggtt_mm.last_partial_off = -1UL;
 	}
 
 	vgpu_free_mm(mm);
@@ -2168,6 +2166,8 @@ static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off,
 	struct intel_gvt_gtt_entry e, m;
 	dma_addr_t dma_addr;
 	int ret;
+	struct intel_gvt_partial_pte *partial_pte, *pos, *n;
+	bool partial_update = false;
 
 	if (bytes != 4 && bytes != 8)
 		return -EINVAL;
@@ -2178,68 +2178,57 @@ static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off,
 	if (!vgpu_gmadr_is_valid(vgpu, gma))
 		return 0;
 
-	ggtt_get_guest_entry(ggtt_mm, &e, g_gtt_index);
-
+	e.type = GTT_TYPE_GGTT_PTE;
 	memcpy((void *)&e.val64 + (off & (info->gtt_entry_size - 1)), p_data,
 			bytes);
 
 	/* If ggtt entry size is 8 bytes, and it's split into two 4 bytes
-	 * write, we assume the two 4 bytes writes are consecutive.
-	 * Otherwise, we abort and report error
+	 * write, save the first 4 bytes in a list and update virtual
+	 * PTE. Only update shadow PTE when the second 4 bytes comes.
 	 */
 	if (bytes < info->gtt_entry_size) {
-		if (ggtt_mm->ggtt_mm.last_partial_off == -1UL) {
-			/* the first partial part*/
-			ggtt_mm->ggtt_mm.last_partial_off = off;
-			ggtt_mm->ggtt_mm.last_partial_data = e.val64;
-			return 0;
-		} else if ((g_gtt_index ==
-				(ggtt_mm->ggtt_mm.last_partial_off >>
-				info->gtt_entry_size_shift)) &&
-			(off !=	ggtt_mm->ggtt_mm.last_partial_off)) {
-			/* the second partial part */
+		bool found = false;
 
-			int last_off = ggtt_mm->ggtt_mm.last_partial_off &
-				(info->gtt_entry_size - 1);
+		list_for_each_entry_safe(pos, n,
+				&ggtt_mm->ggtt_mm.partial_pte_list, list) {
+			if (g_gtt_index == pos->offset >>
+					info->gtt_entry_size_shift) {
+				if (off != pos->offset) {
+					/* the second partial part*/
+					int last_off = pos->offset &
+						(info->gtt_entry_size - 1);
 
-			memcpy((void *)&e.val64 + last_off,
-				(void *)&ggtt_mm->ggtt_mm.last_partial_data +
-				last_off, bytes);
+					memcpy((void *)&e.val64 + last_off,
+						(void *)&pos->data + last_off,
+						bytes);
 
-			ggtt_mm->ggtt_mm.last_partial_off = -1UL;
-		} else {
-			int last_offset;
+					list_del(&pos->list);
+					kfree(pos);
+					found = true;
+					break;
+				}
 
-			gvt_vgpu_err("failed to populate guest ggtt entry: abnormal ggtt entry write sequence, last_partial_off=%lx, offset=%x, bytes=%d, ggtt entry size=%d\n",
-					ggtt_mm->ggtt_mm.last_partial_off, off,
-					bytes, info->gtt_entry_size);
+				/* update of the first partial part */
+				pos->data = e.val64;
+				ggtt_set_guest_entry(ggtt_mm, &e, g_gtt_index);
+				return 0;
+			}
+		}
 
-			/* set host ggtt entry to scratch page and clear
-			 * virtual ggtt entry as not present for last
-			 * partially write offset
-			 */
-			last_offset = ggtt_mm->ggtt_mm.last_partial_off &
-					(~(info->gtt_entry_size - 1));
-
-			ggtt_get_host_entry(ggtt_mm, &m, last_offset);
-			ggtt_invalidate_pte(vgpu, &m);
-			ops->set_pfn(&m, gvt->gtt.scratch_mfn);
-			ops->clear_present(&m);
-			ggtt_set_host_entry(ggtt_mm, &m, last_offset);
-			ggtt_invalidate(gvt->dev_priv);
-
-			ggtt_get_guest_entry(ggtt_mm, &e, last_offset);
-			ops->clear_present(&e);
-			ggtt_set_guest_entry(ggtt_mm, &e, last_offset);
-
-			ggtt_mm->ggtt_mm.last_partial_off = off;
-			ggtt_mm->ggtt_mm.last_partial_data = e.val64;
-
-			return 0;
+		if (!found) {
+			/* the first partial part */
+			partial_pte = kzalloc(sizeof(*partial_pte), GFP_KERNEL);
+			if (!partial_pte)
+				return -ENOMEM;
+			partial_pte->offset = off;
+			partial_pte->data = e.val64;
+			list_add_tail(&partial_pte->list,
+				&ggtt_mm->ggtt_mm.partial_pte_list);
+			partial_update = true;
 		}
 	}
 
-	if (ops->test_present(&e)) {
+	if (!partial_update && (ops->test_present(&e))) {
 		gfn = ops->get_pfn(&e);
 		m = e;
 
@@ -2263,16 +2252,18 @@ static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off,
 		} else
 			ops->set_pfn(&m, dma_addr >> PAGE_SHIFT);
 	} else {
-		ggtt_get_host_entry(ggtt_mm, &m, g_gtt_index);
-		ggtt_invalidate_pte(vgpu, &m);
 		ops->set_pfn(&m, gvt->gtt.scratch_mfn);
 		ops->clear_present(&m);
 	}
 
 out:
+	ggtt_set_guest_entry(ggtt_mm, &e, g_gtt_index);
+
+	ggtt_get_host_entry(ggtt_mm, &e, g_gtt_index);
+	ggtt_invalidate_pte(vgpu, &e);
+
 	ggtt_set_host_entry(ggtt_mm, &m, g_gtt_index);
 	ggtt_invalidate(gvt->dev_priv);
-	ggtt_set_guest_entry(ggtt_mm, &e, g_gtt_index);
 	return 0;
 }
 
@@ -2430,6 +2421,8 @@ int intel_vgpu_init_gtt(struct intel_vgpu *vgpu)
 
 	intel_vgpu_reset_ggtt(vgpu, false);
 
+	INIT_LIST_HEAD(&gtt->ggtt_mm->ggtt_mm.partial_pte_list);
+
 	return create_scratch_page_tree(vgpu);
 }
 
@@ -2454,6 +2447,14 @@ static void intel_vgpu_destroy_all_ppgtt_mm(struct intel_vgpu *vgpu)
 
 static void intel_vgpu_destroy_ggtt_mm(struct intel_vgpu *vgpu)
 {
+	struct intel_gvt_partial_pte *pos;
+
+	list_for_each_entry(pos,
+			&vgpu->gtt.ggtt_mm->ggtt_mm.partial_pte_list, list) {
+		gvt_dbg_mm("partial PTE update on hold 0x%lx : 0x%llx\n",
+			pos->offset, pos->data);
+		kfree(pos);
+	}
 	intel_vgpu_destroy_mm(vgpu->gtt.ggtt_mm);
 	vgpu->gtt.ggtt_mm = NULL;
 }
diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h
index 7a9b361..d8cb04c 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.h
+++ b/drivers/gpu/drm/i915/gvt/gtt.h
@@ -35,7 +35,6 @@
 #define _GVT_GTT_H_
 
 #define I915_GTT_PAGE_SHIFT         12
-#define I915_GTT_PAGE_MASK		(~(I915_GTT_PAGE_SIZE - 1))
 
 struct intel_vgpu_mm;
 
@@ -133,6 +132,12 @@ enum intel_gvt_mm_type {
 
 #define GVT_RING_CTX_NR_PDPS	GEN8_3LVL_PDPES
 
+struct intel_gvt_partial_pte {
+	unsigned long offset;
+	u64 data;
+	struct list_head list;
+};
+
 struct intel_vgpu_mm {
 	enum intel_gvt_mm_type type;
 	struct intel_vgpu *vgpu;
@@ -157,8 +162,7 @@ struct intel_vgpu_mm {
 		} ppgtt_mm;
 		struct {
 			void *virtual_ggtt;
-			unsigned long last_partial_off;
-			u64 last_partial_data;
+			struct list_head partial_pte_list;
 		} ggtt_mm;
 	};
 };
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 90f50f6..aa280bb 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -1609,7 +1609,7 @@ static int bxt_gt_disp_pwron_write(struct intel_vgpu *vgpu,
 	return 0;
 }
 
-static int bxt_edp_psr_imr_iir_write(struct intel_vgpu *vgpu,
+static int edp_psr_imr_iir_write(struct intel_vgpu *vgpu,
 		unsigned int offset, void *p_data, unsigned int bytes)
 {
 	vgpu_vreg(vgpu, offset) = 0;
@@ -2607,6 +2607,9 @@ static int init_generic_mmio_info(struct intel_gvt *gvt)
 	MMIO_DFH(_MMIO(0x1a178), D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
 	MMIO_DFH(_MMIO(0x1a17c), D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
 	MMIO_DFH(_MMIO(0x2217c), D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+
+	MMIO_DH(EDP_PSR_IMR, D_BDW_PLUS, NULL, edp_psr_imr_iir_write);
+	MMIO_DH(EDP_PSR_IIR, D_BDW_PLUS, NULL, edp_psr_imr_iir_write);
 	return 0;
 }
 
@@ -3205,9 +3208,6 @@ static int init_bxt_mmio_info(struct intel_gvt *gvt)
 	MMIO_D(HSW_TVIDEO_DIP_GCP(TRANSCODER_B), D_BXT);
 	MMIO_D(HSW_TVIDEO_DIP_GCP(TRANSCODER_C), D_BXT);
 
-	MMIO_DH(EDP_PSR_IMR, D_BXT, NULL, bxt_edp_psr_imr_iir_write);
-	MMIO_DH(EDP_PSR_IIR, D_BXT, NULL, bxt_edp_psr_imr_iir_write);
-
 	MMIO_D(RC6_CTX_BASE, D_BXT);
 
 	MMIO_D(GEN8_PUSHBUS_CONTROL, D_BXT);
diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c
index 10e63ee..36a5147 100644
--- a/drivers/gpu/drm/i915/gvt/mmio_context.c
+++ b/drivers/gpu/drm/i915/gvt/mmio_context.c
@@ -131,7 +131,7 @@ static struct engine_mmio gen9_engine_mmio_list[] __cacheline_aligned = {
 	{RCS, GAMT_CHKN_BIT_REG, 0x0, false}, /* 0x4ab8 */
 
 	{RCS, GEN9_GAMT_ECO_REG_RW_IA, 0x0, false}, /* 0x4ab0 */
-	{RCS, GEN9_CSFE_CHICKEN1_RCS, 0x0, false}, /* 0x20d4 */
+	{RCS, GEN9_CSFE_CHICKEN1_RCS, 0xffff, false}, /* 0x20d4 */
 
 	{RCS, GEN8_GARBCNTL, 0x0, false}, /* 0xb004 */
 	{RCS, GEN7_FF_THREAD_MODE, 0x0, false}, /* 0x20a0 */
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 44e2c0f..ffdbbac 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1175,8 +1175,6 @@ skl_dram_get_channels_info(struct drm_i915_private *dev_priv)
 		return -EINVAL;
 	}
 
-	dram_info->valid_dimm = true;
-
 	/*
 	 * If any of the channel is single rank channel, worst case output
 	 * will be same as if single rank memory, so consider single rank
@@ -1193,8 +1191,7 @@ skl_dram_get_channels_info(struct drm_i915_private *dev_priv)
 		return -EINVAL;
 	}
 
-	if (ch0.is_16gb_dimm || ch1.is_16gb_dimm)
-		dram_info->is_16gb_dimm = true;
+	dram_info->is_16gb_dimm = ch0.is_16gb_dimm || ch1.is_16gb_dimm;
 
 	dev_priv->dram_info.symmetric_memory = intel_is_dram_symmetric(val_ch0,
 								       val_ch1,
@@ -1314,7 +1311,6 @@ bxt_get_dram_info(struct drm_i915_private *dev_priv)
 		return -EINVAL;
 	}
 
-	dram_info->valid_dimm = true;
 	dram_info->valid = true;
 	return 0;
 }
@@ -1327,12 +1323,17 @@ intel_get_dram_info(struct drm_i915_private *dev_priv)
 	int ret;
 
 	dram_info->valid = false;
-	dram_info->valid_dimm = false;
-	dram_info->is_16gb_dimm = false;
 	dram_info->rank = I915_DRAM_RANK_INVALID;
 	dram_info->bandwidth_kbps = 0;
 	dram_info->num_channels = 0;
 
+	/*
+	 * Assume 16Gb DIMMs are present until proven otherwise.
+	 * This is only used for the level 0 watermark latency
+	 * w/a which does not apply to bxt/glk.
+	 */
+	dram_info->is_16gb_dimm = !IS_GEN9_LP(dev_priv);
+
 	if (INTEL_GEN(dev_priv) < 9 || IS_GEMINILAKE(dev_priv))
 		return;
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 8624b4b..9102571 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1948,7 +1948,6 @@ struct drm_i915_private {
 
 	struct dram_info {
 		bool valid;
-		bool valid_dimm;
 		bool is_16gb_dimm;
 		u8 num_channels;
 		enum dram_rank {
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 0918728..1aaccbe 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -460,7 +460,7 @@ eb_validate_vma(struct i915_execbuffer *eb,
 	 * any non-page-aligned or non-canonical addresses.
 	 */
 	if (unlikely(entry->flags & EXEC_OBJECT_PINNED &&
-		     entry->offset != gen8_canonical_addr(entry->offset & PAGE_MASK)))
+		     entry->offset != gen8_canonical_addr(entry->offset & I915_GTT_PAGE_MASK)))
 		return -EINVAL;
 
 	/* pad_to_size was once a reserved field, so sanitize it */
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 56c7f86..47c3025 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1757,7 +1757,7 @@ static void gen6_dump_ppgtt(struct i915_hw_ppgtt *base, struct seq_file *m)
 			if (i == 4)
 				continue;
 
-			seq_printf(m, "\t\t(%03d, %04d) %08lx: ",
+			seq_printf(m, "\t\t(%03d, %04d) %08llx: ",
 				   pde, pte,
 				   (pde * GEN6_PTES + pte) * I915_GTT_PAGE_SIZE);
 			for (i = 0; i < 4; i++) {
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 7e2af5f..2803929 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -42,13 +42,15 @@
 #include "i915_selftest.h"
 #include "i915_timeline.h"
 
-#define I915_GTT_PAGE_SIZE_4K BIT(12)
-#define I915_GTT_PAGE_SIZE_64K BIT(16)
-#define I915_GTT_PAGE_SIZE_2M BIT(21)
+#define I915_GTT_PAGE_SIZE_4K	BIT_ULL(12)
+#define I915_GTT_PAGE_SIZE_64K	BIT_ULL(16)
+#define I915_GTT_PAGE_SIZE_2M	BIT_ULL(21)
 
 #define I915_GTT_PAGE_SIZE I915_GTT_PAGE_SIZE_4K
 #define I915_GTT_MAX_PAGE_SIZE I915_GTT_PAGE_SIZE_2M
 
+#define I915_GTT_PAGE_MASK -I915_GTT_PAGE_SIZE
+
 #define I915_GTT_MIN_ALIGNMENT I915_GTT_PAGE_SIZE
 
 #define I915_FENCE_REG_NONE -1
@@ -659,20 +661,20 @@ int i915_gem_gtt_insert(struct i915_address_space *vm,
 			u64 start, u64 end, unsigned int flags);
 
 /* Flags used by pin/bind&friends. */
-#define PIN_NONBLOCK		BIT(0)
-#define PIN_MAPPABLE		BIT(1)
-#define PIN_ZONE_4G		BIT(2)
-#define PIN_NONFAULT		BIT(3)
-#define PIN_NOEVICT		BIT(4)
+#define PIN_NONBLOCK		BIT_ULL(0)
+#define PIN_MAPPABLE		BIT_ULL(1)
+#define PIN_ZONE_4G		BIT_ULL(2)
+#define PIN_NONFAULT		BIT_ULL(3)
+#define PIN_NOEVICT		BIT_ULL(4)
 
-#define PIN_MBZ			BIT(5) /* I915_VMA_PIN_OVERFLOW */
-#define PIN_GLOBAL		BIT(6) /* I915_VMA_GLOBAL_BIND */
-#define PIN_USER		BIT(7) /* I915_VMA_LOCAL_BIND */
-#define PIN_UPDATE		BIT(8)
+#define PIN_MBZ			BIT_ULL(5) /* I915_VMA_PIN_OVERFLOW */
+#define PIN_GLOBAL		BIT_ULL(6) /* I915_VMA_GLOBAL_BIND */
+#define PIN_USER		BIT_ULL(7) /* I915_VMA_LOCAL_BIND */
+#define PIN_UPDATE		BIT_ULL(8)
 
-#define PIN_HIGH		BIT(9)
-#define PIN_OFFSET_BIAS		BIT(10)
-#define PIN_OFFSET_FIXED	BIT(11)
+#define PIN_HIGH		BIT_ULL(9)
+#define PIN_OFFSET_BIAS		BIT_ULL(10)
+#define PIN_OFFSET_FIXED	BIT_ULL(11)
 #define PIN_OFFSET_MASK		(-I915_GTT_PAGE_SIZE)
 
 #endif
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 7c491ea..e31c27e 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -2095,8 +2095,12 @@ enum i915_power_well_id {
 
 /* ICL PHY DFLEX registers */
 #define PORT_TX_DFLEXDPMLE1		_MMIO(0x1638C0)
-#define   DFLEXDPMLE1_DPMLETC_MASK(n)	(0xf << (4 * (n)))
-#define   DFLEXDPMLE1_DPMLETC(n, x)	((x) << (4 * (n)))
+#define   DFLEXDPMLE1_DPMLETC_MASK(tc_port)	(0xf << (4 * (tc_port)))
+#define   DFLEXDPMLE1_DPMLETC_ML0(tc_port)	(1 << (4 * (tc_port)))
+#define   DFLEXDPMLE1_DPMLETC_ML1_0(tc_port)	(3 << (4 * (tc_port)))
+#define   DFLEXDPMLE1_DPMLETC_ML3(tc_port)	(8 << (4 * (tc_port)))
+#define   DFLEXDPMLE1_DPMLETC_ML3_2(tc_port)	(12 << (4 * (tc_port)))
+#define   DFLEXDPMLE1_DPMLETC_ML3_0(tc_port)	(15 << (4 * (tc_port)))
 
 /* BXT PHY Ref registers */
 #define _PORT_REF_DW3_A			0x16218C
@@ -4593,12 +4597,12 @@ enum {
 
 #define  DRM_DIP_ENABLE			(1 << 28)
 #define  PSR_VSC_BIT_7_SET		(1 << 27)
-#define  VSC_SELECT_MASK		(0x3 << 26)
-#define  VSC_SELECT_SHIFT		26
-#define  VSC_DIP_HW_HEA_DATA		(0 << 26)
-#define  VSC_DIP_HW_HEA_SW_DATA		(1 << 26)
-#define  VSC_DIP_HW_DATA_SW_HEA		(2 << 26)
-#define  VSC_DIP_SW_HEA_DATA		(3 << 26)
+#define  VSC_SELECT_MASK		(0x3 << 25)
+#define  VSC_SELECT_SHIFT		25
+#define  VSC_DIP_HW_HEA_DATA		(0 << 25)
+#define  VSC_DIP_HW_HEA_SW_DATA		(1 << 25)
+#define  VSC_DIP_HW_DATA_SW_HEA		(2 << 25)
+#define  VSC_DIP_SW_HEA_DATA		(3 << 25)
 #define  VDIP_ENABLE_PPS		(1 << 24)
 
 /* Panel power sequencing */
diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c
index 769f3f5..ee3ca2d 100644
--- a/drivers/gpu/drm/i915/intel_audio.c
+++ b/drivers/gpu/drm/i915/intel_audio.c
@@ -144,6 +144,9 @@ static const struct {
 /* HDMI N/CTS table */
 #define TMDS_297M 297000
 #define TMDS_296M 296703
+#define TMDS_594M 594000
+#define TMDS_593M 593407
+
 static const struct {
 	int sample_rate;
 	int clock;
@@ -164,6 +167,20 @@ static const struct {
 	{ 176400, TMDS_297M, 18816, 247500 },
 	{ 192000, TMDS_296M, 23296, 281250 },
 	{ 192000, TMDS_297M, 20480, 247500 },
+	{ 44100, TMDS_593M, 8918, 937500 },
+	{ 44100, TMDS_594M, 9408, 990000 },
+	{ 48000, TMDS_593M, 5824, 562500 },
+	{ 48000, TMDS_594M, 6144, 594000 },
+	{ 32000, TMDS_593M, 5824, 843750 },
+	{ 32000, TMDS_594M, 3072, 445500 },
+	{ 88200, TMDS_593M, 17836, 937500 },
+	{ 88200, TMDS_594M, 18816, 990000 },
+	{ 96000, TMDS_593M, 11648, 562500 },
+	{ 96000, TMDS_594M, 12288, 594000 },
+	{ 176400, TMDS_593M, 35672, 937500 },
+	{ 176400, TMDS_594M, 37632, 990000 },
+	{ 192000, TMDS_593M, 23296, 562500 },
+	{ 192000, TMDS_594M, 24576, 594000 },
 };
 
 /* get AUD_CONFIG_PIXEL_CLOCK_HDMI_* value for mode */
diff --git a/drivers/gpu/drm/i915/intel_cdclk.c b/drivers/gpu/drm/i915/intel_cdclk.c
index 29075c7..8d74276 100644
--- a/drivers/gpu/drm/i915/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/intel_cdclk.c
@@ -2138,16 +2138,8 @@ void intel_set_cdclk(struct drm_i915_private *dev_priv,
 static int intel_pixel_rate_to_cdclk(struct drm_i915_private *dev_priv,
 				     int pixel_rate)
 {
-	if (INTEL_GEN(dev_priv) >= 10)
+	if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
 		return DIV_ROUND_UP(pixel_rate, 2);
-	else if (IS_GEMINILAKE(dev_priv))
-		/*
-		 * FIXME: Avoid using a pixel clock that is more than 99% of the cdclk
-		 * as a temporary workaround. Use a higher cdclk instead. (Note that
-		 * intel_compute_max_dotclk() limits the max pixel clock to 99% of max
-		 * cdclk.)
-		 */
-		return DIV_ROUND_UP(pixel_rate * 100, 2 * 99);
 	else if (IS_GEN9(dev_priv) ||
 		 IS_BROADWELL(dev_priv) || IS_HASWELL(dev_priv))
 		return pixel_rate;
@@ -2543,14 +2535,8 @@ static int intel_compute_max_dotclk(struct drm_i915_private *dev_priv)
 {
 	int max_cdclk_freq = dev_priv->max_cdclk_freq;
 
-	if (INTEL_GEN(dev_priv) >= 10)
+	if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
 		return 2 * max_cdclk_freq;
-	else if (IS_GEMINILAKE(dev_priv))
-		/*
-		 * FIXME: Limiting to 99% as a temporary workaround. See
-		 * intel_min_cdclk() for details.
-		 */
-		return 2 * max_cdclk_freq * 99 / 100;
 	else if (IS_GEN9(dev_priv) ||
 		 IS_BROADWELL(dev_priv) || IS_HASWELL(dev_priv))
 		return max_cdclk_freq;
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 9741cc4..23d8008 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -12768,17 +12768,12 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state)
 			intel_check_cpu_fifo_underruns(dev_priv);
 			intel_check_pch_fifo_underruns(dev_priv);
 
-			if (!new_crtc_state->active) {
-				/*
-				 * Make sure we don't call initial_watermarks
-				 * for ILK-style watermark updates.
-				 *
-				 * No clue what this is supposed to achieve.
-				 */
-				if (INTEL_GEN(dev_priv) >= 9)
-					dev_priv->display.initial_watermarks(intel_state,
-									     to_intel_crtc_state(new_crtc_state));
-			}
+			/* FIXME unify this for all platforms */
+			if (!new_crtc_state->active &&
+			    !HAS_GMCH_DISPLAY(dev_priv) &&
+			    dev_priv->display.initial_watermarks)
+				dev_priv->display.initial_watermarks(intel_state,
+								     to_intel_crtc_state(new_crtc_state));
 		}
 	}
 
@@ -14646,7 +14641,7 @@ static int intel_framebuffer_init(struct intel_framebuffer *intel_fb,
 	     fb->height < SKL_MIN_YUV_420_SRC_H ||
 	     (fb->width % 4) != 0 || (fb->height % 4) != 0)) {
 		DRM_DEBUG_KMS("src dimensions not correct for NV12\n");
-		return -EINVAL;
+		goto err;
 	}
 
 	for (i = 0; i < fb->format->num_planes; i++) {
diff --git a/drivers/gpu/drm/i915/intel_lpe_audio.c b/drivers/gpu/drm/i915/intel_lpe_audio.c
index cdf1955..5d5336f 100644
--- a/drivers/gpu/drm/i915/intel_lpe_audio.c
+++ b/drivers/gpu/drm/i915/intel_lpe_audio.c
@@ -297,8 +297,10 @@ void intel_lpe_audio_teardown(struct drm_i915_private *dev_priv)
 	lpe_audio_platdev_destroy(dev_priv);
 
 	irq_free_desc(dev_priv->lpe_audio.irq);
-}
 
+	dev_priv->lpe_audio.irq = -1;
+	dev_priv->lpe_audio.platdev = NULL;
+}
 
 /**
  * intel_lpe_audio_notify() - notify lpe audio event
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 1db9b832..245f002 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2881,8 +2881,7 @@ static void intel_read_wm_latency(struct drm_i915_private *dev_priv,
 		 * any underrun. If not able to get Dimm info assume 16GB dimm
 		 * to avoid any underrun.
 		 */
-		if (!dev_priv->dram_info.valid_dimm ||
-		    dev_priv->dram_info.is_16gb_dimm)
+		if (dev_priv->dram_info.is_16gb_dimm)
 			wm[0] += 1;
 
 	} else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) {
diff --git a/drivers/gpu/drm/i915/selftests/huge_pages.c b/drivers/gpu/drm/i915/selftests/huge_pages.c
index 8d03f64..5c22f2c 100644
--- a/drivers/gpu/drm/i915/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/selftests/huge_pages.c
@@ -551,7 +551,7 @@ static int igt_mock_ppgtt_misaligned_dma(void *arg)
 			err = igt_check_page_sizes(vma);
 
 			if (vma->page_sizes.gtt != I915_GTT_PAGE_SIZE_4K) {
-				pr_err("page_sizes.gtt=%u, expected %lu\n",
+				pr_err("page_sizes.gtt=%u, expected %llu\n",
 				       vma->page_sizes.gtt, I915_GTT_PAGE_SIZE_4K);
 				err = -EINVAL;
 			}
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index 8e2e269..127d815 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -1337,7 +1337,7 @@ static int igt_gtt_reserve(void *arg)
 		GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
 		if (vma->node.start != total ||
 		    vma->node.size != 2*I915_GTT_PAGE_SIZE) {
-			pr_err("i915_gem_gtt_reserve (pass 1) placement failed, found (%llx + %llx), expected (%llx + %lx)\n",
+			pr_err("i915_gem_gtt_reserve (pass 1) placement failed, found (%llx + %llx), expected (%llx + %llx)\n",
 			       vma->node.start, vma->node.size,
 			       total, 2*I915_GTT_PAGE_SIZE);
 			err = -EINVAL;
@@ -1386,7 +1386,7 @@ static int igt_gtt_reserve(void *arg)
 		GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
 		if (vma->node.start != total ||
 		    vma->node.size != 2*I915_GTT_PAGE_SIZE) {
-			pr_err("i915_gem_gtt_reserve (pass 2) placement failed, found (%llx + %llx), expected (%llx + %lx)\n",
+			pr_err("i915_gem_gtt_reserve (pass 2) placement failed, found (%llx + %llx), expected (%llx + %llx)\n",
 			       vma->node.start, vma->node.size,
 			       total, 2*I915_GTT_PAGE_SIZE);
 			err = -EINVAL;
@@ -1430,7 +1430,7 @@ static int igt_gtt_reserve(void *arg)
 		GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
 		if (vma->node.start != offset ||
 		    vma->node.size != 2*I915_GTT_PAGE_SIZE) {
-			pr_err("i915_gem_gtt_reserve (pass 3) placement failed, found (%llx + %llx), expected (%llx + %lx)\n",
+			pr_err("i915_gem_gtt_reserve (pass 3) placement failed, found (%llx + %llx), expected (%llx + %llx)\n",
 			       vma->node.start, vma->node.size,
 			       offset, 2*I915_GTT_PAGE_SIZE);
 			err = -EINVAL;
diff --git a/drivers/gpu/drm/sun4i/sun4i_lvds.c b/drivers/gpu/drm/sun4i/sun4i_lvds.c
index af7dcb6..e7eb0d1 100644
--- a/drivers/gpu/drm/sun4i/sun4i_lvds.c
+++ b/drivers/gpu/drm/sun4i/sun4i_lvds.c
@@ -75,7 +75,7 @@ static void sun4i_lvds_encoder_enable(struct drm_encoder *encoder)
 
 	DRM_DEBUG_DRIVER("Enabling LVDS output\n");
 
-	if (!IS_ERR(tcon->panel)) {
+	if (tcon->panel) {
 		drm_panel_prepare(tcon->panel);
 		drm_panel_enable(tcon->panel);
 	}
@@ -88,7 +88,7 @@ static void sun4i_lvds_encoder_disable(struct drm_encoder *encoder)
 
 	DRM_DEBUG_DRIVER("Disabling LVDS output\n");
 
-	if (!IS_ERR(tcon->panel)) {
+	if (tcon->panel) {
 		drm_panel_disable(tcon->panel);
 		drm_panel_unprepare(tcon->panel);
 	}
diff --git a/drivers/gpu/drm/sun4i/sun4i_rgb.c b/drivers/gpu/drm/sun4i/sun4i_rgb.c
index bf068da..f4a2268 100644
--- a/drivers/gpu/drm/sun4i/sun4i_rgb.c
+++ b/drivers/gpu/drm/sun4i/sun4i_rgb.c
@@ -135,7 +135,7 @@ static void sun4i_rgb_encoder_enable(struct drm_encoder *encoder)
 
 	DRM_DEBUG_DRIVER("Enabling RGB output\n");
 
-	if (!IS_ERR(tcon->panel)) {
+	if (tcon->panel) {
 		drm_panel_prepare(tcon->panel);
 		drm_panel_enable(tcon->panel);
 	}
@@ -148,7 +148,7 @@ static void sun4i_rgb_encoder_disable(struct drm_encoder *encoder)
 
 	DRM_DEBUG_DRIVER("Disabling RGB output\n");
 
-	if (!IS_ERR(tcon->panel)) {
+	if (tcon->panel) {
 		drm_panel_disable(tcon->panel);
 		drm_panel_unprepare(tcon->panel);
 	}
diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c
index c78cd35..f949287 100644
--- a/drivers/gpu/drm/sun4i/sun4i_tcon.c
+++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c
@@ -491,7 +491,8 @@ static void sun4i_tcon0_mode_set_rgb(struct sun4i_tcon *tcon,
 	sun4i_tcon0_mode_set_common(tcon, mode);
 
 	/* Set dithering if needed */
-	sun4i_tcon0_mode_set_dithering(tcon, tcon->panel->connector);
+	if (tcon->panel)
+		sun4i_tcon0_mode_set_dithering(tcon, tcon->panel->connector);
 
 	/* Adjust clock delay */
 	clk_delay = sun4i_tcon_get_clk_delay(mode, 0);
@@ -555,7 +556,7 @@ static void sun4i_tcon0_mode_set_rgb(struct sun4i_tcon *tcon,
 	 * Following code is a way to avoid quirks all around TCON
 	 * and DOTCLOCK drivers.
 	 */
-	if (!IS_ERR(tcon->panel)) {
+	if (tcon->panel) {
 		struct drm_panel *panel = tcon->panel;
 		struct drm_connector *connector = panel->connector;
 		struct drm_display_info display_info = connector->display_info;
diff --git a/drivers/gpu/vga/vga_switcheroo.c b/drivers/gpu/vga/vga_switcheroo.c
index cf2a185..a132c37 100644
--- a/drivers/gpu/vga/vga_switcheroo.c
+++ b/drivers/gpu/vga/vga_switcheroo.c
@@ -380,6 +380,9 @@ int vga_switcheroo_register_audio_client(struct pci_dev *pdev,
 			mutex_unlock(&vgasr_mutex);
 			return -EINVAL;
 		}
+		/* notify if GPU has been already bound */
+		if (ops->gpu_bound)
+			ops->gpu_bound(pdev, id);
 	}
 	mutex_unlock(&vgasr_mutex);
 
diff --git a/drivers/hid/hid-alps.c b/drivers/hid/hid-alps.c
index aec253b..3cd7229 100644
--- a/drivers/hid/hid-alps.c
+++ b/drivers/hid/hid-alps.c
@@ -660,6 +660,20 @@ static int T4_init(struct hid_device *hdev, struct alps_dev *pri_data)
 	return ret;
 }
 
+static int alps_sp_open(struct input_dev *dev)
+{
+	struct hid_device *hid = input_get_drvdata(dev);
+
+	return hid_hw_open(hid);
+}
+
+static void alps_sp_close(struct input_dev *dev)
+{
+	struct hid_device *hid = input_get_drvdata(dev);
+
+	hid_hw_close(hid);
+}
+
 static int alps_input_configured(struct hid_device *hdev, struct hid_input *hi)
 {
 	struct alps_dev *data = hid_get_drvdata(hdev);
@@ -733,6 +747,10 @@ static int alps_input_configured(struct hid_device *hdev, struct hid_input *hi)
 		input2->id.version = input->id.version;
 		input2->dev.parent = input->dev.parent;
 
+		input_set_drvdata(input2, hdev);
+		input2->open = alps_sp_open;
+		input2->close = alps_sp_close;
+
 		__set_bit(EV_KEY, input2->evbit);
 		data->sp_btn_cnt = (data->sp_btn_info & 0x0F);
 		for (i = 0; i < data->sp_btn_cnt; i++)
diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c
index dc6d647..a1fa2fc 100644
--- a/drivers/hid/hid-asus.c
+++ b/drivers/hid/hid-asus.c
@@ -359,6 +359,9 @@ static bool asus_kbd_wmi_led_control_present(struct hid_device *hdev)
 	u32 value;
 	int ret;
 
+	if (!IS_ENABLED(CONFIG_ASUS_WMI))
+		return false;
+
 	ret = asus_wmi_evaluate_method(ASUS_WMI_METHODID_DSTS2,
 				       ASUS_WMI_DEVID_KBD_BACKLIGHT, 0, &value);
 	hid_dbg(hdev, "WMI backlight check: rc %d value %x", ret, value);
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index f63489c..c0d6689 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -927,6 +927,9 @@
 #define USB_DEVICE_ID_QUANTA_OPTICAL_TOUCH_3003		0x3003
 #define USB_DEVICE_ID_QUANTA_OPTICAL_TOUCH_3008		0x3008
 
+#define I2C_VENDOR_ID_RAYDIUM		0x2386
+#define I2C_PRODUCT_ID_RAYDIUM_4B33	0x4b33
+
 #define USB_VENDOR_ID_RAZER            0x1532
 #define USB_DEVICE_ID_RAZER_BLADE_14   0x011D
 
diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c
index 52c3b01..8237dd8 100644
--- a/drivers/hid/hid-quirks.c
+++ b/drivers/hid/hid-quirks.c
@@ -107,7 +107,6 @@ static const struct hid_device_id hid_quirks[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_MOUSE_C05A), HID_QUIRK_ALWAYS_POLL },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_MOUSE_C06A), HID_QUIRK_ALWAYS_POLL },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MCS, USB_DEVICE_ID_MCS_GAMEPADBLOCK), HID_QUIRK_MULTI_INPUT },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_MGE, USB_DEVICE_ID_MGE_UPS), HID_QUIRK_NOGET },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_POWER_COVER), HID_QUIRK_NO_INIT_REPORTS },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_SURFACE_PRO_2), HID_QUIRK_NO_INIT_REPORTS },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TOUCH_COVER_2), HID_QUIRK_NO_INIT_REPORTS },
diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c
index 4aab96c..3cde7c1 100644
--- a/drivers/hid/i2c-hid/i2c-hid-core.c
+++ b/drivers/hid/i2c-hid/i2c-hid-core.c
@@ -49,6 +49,7 @@
 #define I2C_HID_QUIRK_SET_PWR_WAKEUP_DEV	BIT(0)
 #define I2C_HID_QUIRK_NO_IRQ_AFTER_RESET	BIT(1)
 #define I2C_HID_QUIRK_NO_RUNTIME_PM		BIT(2)
+#define I2C_HID_QUIRK_DELAY_AFTER_SLEEP		BIT(3)
 
 /* flags */
 #define I2C_HID_STARTED		0
@@ -158,6 +159,8 @@ struct i2c_hid {
 
 	bool			irq_wake_enabled;
 	struct mutex		reset_lock;
+
+	unsigned long		sleep_delay;
 };
 
 static const struct i2c_hid_quirks {
@@ -172,6 +175,8 @@ static const struct i2c_hid_quirks {
 	{ I2C_VENDOR_ID_HANTICK, I2C_PRODUCT_ID_HANTICK_5288,
 		I2C_HID_QUIRK_NO_IRQ_AFTER_RESET |
 		I2C_HID_QUIRK_NO_RUNTIME_PM },
+	{ I2C_VENDOR_ID_RAYDIUM, I2C_PRODUCT_ID_RAYDIUM_4B33,
+		I2C_HID_QUIRK_DELAY_AFTER_SLEEP },
 	{ 0, 0 }
 };
 
@@ -387,6 +392,7 @@ static int i2c_hid_set_power(struct i2c_client *client, int power_state)
 {
 	struct i2c_hid *ihid = i2c_get_clientdata(client);
 	int ret;
+	unsigned long now, delay;
 
 	i2c_hid_dbg(ihid, "%s\n", __func__);
 
@@ -404,9 +410,22 @@ static int i2c_hid_set_power(struct i2c_client *client, int power_state)
 			goto set_pwr_exit;
 	}
 
+	if (ihid->quirks & I2C_HID_QUIRK_DELAY_AFTER_SLEEP &&
+	    power_state == I2C_HID_PWR_ON) {
+		now = jiffies;
+		if (time_after(ihid->sleep_delay, now)) {
+			delay = jiffies_to_usecs(ihid->sleep_delay - now);
+			usleep_range(delay, delay + 1);
+		}
+	}
+
 	ret = __i2c_hid_command(client, &hid_set_power_cmd, power_state,
 		0, NULL, 0, NULL, 0);
 
+	if (ihid->quirks & I2C_HID_QUIRK_DELAY_AFTER_SLEEP &&
+	    power_state == I2C_HID_PWR_SLEEP)
+		ihid->sleep_delay = jiffies + msecs_to_jiffies(20);
+
 	if (ret)
 		dev_err(&client->dev, "failed to change power setting.\n");
 
diff --git a/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c b/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c
index cac262a..89f2976 100644
--- a/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c
+++ b/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c
@@ -331,6 +331,14 @@ static const struct dmi_system_id i2c_hid_dmi_desc_override_table[] = {
 		.driver_data = (void *)&sipodev_desc
 	},
 	{
+		.ident = "Direkt-Tek DTLAPY133-1",
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Direkt-Tek"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "DTLAPY133-1"),
+		},
+		.driver_data = (void *)&sipodev_desc
+	},
+	{
 		.ident = "Mediacom Flexbook Edge 11",
 		.matches = {
 			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "MEDIACOM"),
diff --git a/drivers/hid/usbhid/hiddev.c b/drivers/hid/usbhid/hiddev.c
index 23872d0..a746017 100644
--- a/drivers/hid/usbhid/hiddev.c
+++ b/drivers/hid/usbhid/hiddev.c
@@ -512,14 +512,24 @@ static noinline int hiddev_ioctl_usage(struct hiddev *hiddev, unsigned int cmd,
 			if (cmd == HIDIOCGCOLLECTIONINDEX) {
 				if (uref->usage_index >= field->maxusage)
 					goto inval;
+				uref->usage_index =
+					array_index_nospec(uref->usage_index,
+							   field->maxusage);
 			} else if (uref->usage_index >= field->report_count)
 				goto inval;
 		}
 
-		if ((cmd == HIDIOCGUSAGES || cmd == HIDIOCSUSAGES) &&
-		    (uref_multi->num_values > HID_MAX_MULTI_USAGES ||
-		     uref->usage_index + uref_multi->num_values > field->report_count))
-			goto inval;
+		if (cmd == HIDIOCGUSAGES || cmd == HIDIOCSUSAGES) {
+			if (uref_multi->num_values > HID_MAX_MULTI_USAGES ||
+			    uref->usage_index + uref_multi->num_values >
+			    field->report_count)
+				goto inval;
+
+			uref->usage_index =
+				array_index_nospec(uref->usage_index,
+						   field->report_count -
+						   uref_multi->num_values);
+		}
 
 		switch (cmd) {
 		case HIDIOCGUSAGE:
diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c
index 975c951..84f61ce 100644
--- a/drivers/hwmon/hwmon.c
+++ b/drivers/hwmon/hwmon.c
@@ -649,8 +649,10 @@ __hwmon_device_register(struct device *dev, const char *name, void *drvdata,
 				if (info[i]->config[j] & HWMON_T_INPUT) {
 					err = hwmon_thermal_add_sensor(dev,
 								hwdev, j);
-					if (err)
-						goto free_device;
+					if (err) {
+						device_unregister(hdev);
+						goto ida_remove;
+					}
 				}
 			}
 		}
@@ -658,8 +660,6 @@ __hwmon_device_register(struct device *dev, const char *name, void *drvdata,
 
 	return hdev;
 
-free_device:
-	device_unregister(hdev);
 free_hwmon:
 	kfree(hwdev);
 ida_remove:
diff --git a/drivers/hwmon/ibmpowernv.c b/drivers/hwmon/ibmpowernv.c
index 0ccca87..293dd1c 100644
--- a/drivers/hwmon/ibmpowernv.c
+++ b/drivers/hwmon/ibmpowernv.c
@@ -181,7 +181,7 @@ static ssize_t show_label(struct device *dev, struct device_attribute *devattr,
 	return sprintf(buf, "%s\n", sdata->label);
 }
 
-static int __init get_logical_cpu(int hwcpu)
+static int get_logical_cpu(int hwcpu)
 {
 	int cpu;
 
@@ -192,9 +192,8 @@ static int __init get_logical_cpu(int hwcpu)
 	return -ENOENT;
 }
 
-static void __init make_sensor_label(struct device_node *np,
-				     struct sensor_data *sdata,
-				     const char *label)
+static void make_sensor_label(struct device_node *np,
+			      struct sensor_data *sdata, const char *label)
 {
 	u32 id;
 	size_t n;
diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index 56ccb1e..f2c6819 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -224,6 +224,15 @@
 	  This driver can also be built as a module.  If so, the module
 	  will be called i2c-nforce2-s4985.
 
+config I2C_NVIDIA_GPU
+	tristate "NVIDIA GPU I2C controller"
+	depends on PCI
+	help
+	  If you say yes to this option, support will be included for the
+	  NVIDIA GPU I2C controller which is used to communicate with the GPU's
+	  Type-C controller. This driver can also be built as a module called
+	  i2c-nvidia-gpu.
+
 config I2C_SIS5595
 	tristate "SiS 5595"
 	depends on PCI
@@ -752,7 +761,7 @@
 
 config I2C_OMAP
 	tristate "OMAP I2C adapter"
-	depends on ARCH_OMAP
+	depends on ARCH_OMAP || ARCH_K3
 	default y if MACH_OMAP_H3 || MACH_OMAP_OSK
 	help
 	  If you say yes to this option, support will be included for the
diff --git a/drivers/i2c/busses/Makefile b/drivers/i2c/busses/Makefile
index 18b26af..5f0cb69 100644
--- a/drivers/i2c/busses/Makefile
+++ b/drivers/i2c/busses/Makefile
@@ -19,6 +19,7 @@
 obj-$(CONFIG_I2C_ISMT)		+= i2c-ismt.o
 obj-$(CONFIG_I2C_NFORCE2)	+= i2c-nforce2.o
 obj-$(CONFIG_I2C_NFORCE2_S4985)	+= i2c-nforce2-s4985.o
+obj-$(CONFIG_I2C_NVIDIA_GPU)	+= i2c-nvidia-gpu.o
 obj-$(CONFIG_I2C_PIIX4)		+= i2c-piix4.o
 obj-$(CONFIG_I2C_SIS5595)	+= i2c-sis5595.o
 obj-$(CONFIG_I2C_SIS630)	+= i2c-sis630.o
diff --git a/drivers/i2c/busses/i2c-nvidia-gpu.c b/drivers/i2c/busses/i2c-nvidia-gpu.c
new file mode 100644
index 0000000..8822357
--- /dev/null
+++ b/drivers/i2c/busses/i2c-nvidia-gpu.c
@@ -0,0 +1,368 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Nvidia GPU I2C controller Driver
+ *
+ * Copyright (C) 2018 NVIDIA Corporation. All rights reserved.
+ * Author: Ajay Gupta <ajayg@nvidia.com>
+ */
+#include <linux/delay.h>
+#include <linux/i2c.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+#include <linux/pm.h>
+#include <linux/pm_runtime.h>
+
+#include <asm/unaligned.h>
+
+/* I2C definitions */
+#define I2C_MST_CNTL				0x00
+#define I2C_MST_CNTL_GEN_START			BIT(0)
+#define I2C_MST_CNTL_GEN_STOP			BIT(1)
+#define I2C_MST_CNTL_CMD_READ			(1 << 2)
+#define I2C_MST_CNTL_CMD_WRITE			(2 << 2)
+#define I2C_MST_CNTL_BURST_SIZE_SHIFT		6
+#define I2C_MST_CNTL_GEN_NACK			BIT(28)
+#define I2C_MST_CNTL_STATUS			GENMASK(30, 29)
+#define I2C_MST_CNTL_STATUS_OKAY		(0 << 29)
+#define I2C_MST_CNTL_STATUS_NO_ACK		(1 << 29)
+#define I2C_MST_CNTL_STATUS_TIMEOUT		(2 << 29)
+#define I2C_MST_CNTL_STATUS_BUS_BUSY		(3 << 29)
+#define I2C_MST_CNTL_CYCLE_TRIGGER		BIT(31)
+
+#define I2C_MST_ADDR				0x04
+
+#define I2C_MST_I2C0_TIMING				0x08
+#define I2C_MST_I2C0_TIMING_SCL_PERIOD_100KHZ		0x10e
+#define I2C_MST_I2C0_TIMING_TIMEOUT_CLK_CNT		16
+#define I2C_MST_I2C0_TIMING_TIMEOUT_CLK_CNT_MAX		255
+#define I2C_MST_I2C0_TIMING_TIMEOUT_CHECK		BIT(24)
+
+#define I2C_MST_DATA					0x0c
+
+#define I2C_MST_HYBRID_PADCTL				0x20
+#define I2C_MST_HYBRID_PADCTL_MODE_I2C			BIT(0)
+#define I2C_MST_HYBRID_PADCTL_I2C_SCL_INPUT_RCV		BIT(14)
+#define I2C_MST_HYBRID_PADCTL_I2C_SDA_INPUT_RCV		BIT(15)
+
+struct gpu_i2c_dev {
+	struct device *dev;
+	void __iomem *regs;
+	struct i2c_adapter adapter;
+	struct i2c_board_info *gpu_ccgx_ucsi;
+};
+
+static void gpu_enable_i2c_bus(struct gpu_i2c_dev *i2cd)
+{
+	u32 val;
+
+	/* enable I2C */
+	val = readl(i2cd->regs + I2C_MST_HYBRID_PADCTL);
+	val |= I2C_MST_HYBRID_PADCTL_MODE_I2C |
+		I2C_MST_HYBRID_PADCTL_I2C_SCL_INPUT_RCV |
+		I2C_MST_HYBRID_PADCTL_I2C_SDA_INPUT_RCV;
+	writel(val, i2cd->regs + I2C_MST_HYBRID_PADCTL);
+
+	/* enable 100KHZ mode */
+	val = I2C_MST_I2C0_TIMING_SCL_PERIOD_100KHZ;
+	val |= (I2C_MST_I2C0_TIMING_TIMEOUT_CLK_CNT_MAX
+	    << I2C_MST_I2C0_TIMING_TIMEOUT_CLK_CNT);
+	val |= I2C_MST_I2C0_TIMING_TIMEOUT_CHECK;
+	writel(val, i2cd->regs + I2C_MST_I2C0_TIMING);
+}
+
+static int gpu_i2c_check_status(struct gpu_i2c_dev *i2cd)
+{
+	unsigned long target = jiffies + msecs_to_jiffies(1000);
+	u32 val;
+
+	do {
+		val = readl(i2cd->regs + I2C_MST_CNTL);
+		if (!(val & I2C_MST_CNTL_CYCLE_TRIGGER))
+			break;
+		if ((val & I2C_MST_CNTL_STATUS) !=
+				I2C_MST_CNTL_STATUS_BUS_BUSY)
+			break;
+		usleep_range(500, 600);
+	} while (time_is_after_jiffies(target));
+
+	if (time_is_before_jiffies(target)) {
+		dev_err(i2cd->dev, "i2c timeout error %x\n", val);
+		return -ETIME;
+	}
+
+	val = readl(i2cd->regs + I2C_MST_CNTL);
+	switch (val & I2C_MST_CNTL_STATUS) {
+	case I2C_MST_CNTL_STATUS_OKAY:
+		return 0;
+	case I2C_MST_CNTL_STATUS_NO_ACK:
+		return -EIO;
+	case I2C_MST_CNTL_STATUS_TIMEOUT:
+		return -ETIME;
+	default:
+		return 0;
+	}
+}
+
+static int gpu_i2c_read(struct gpu_i2c_dev *i2cd, u8 *data, u16 len)
+{
+	int status;
+	u32 val;
+
+	val = I2C_MST_CNTL_GEN_START | I2C_MST_CNTL_CMD_READ |
+		(len << I2C_MST_CNTL_BURST_SIZE_SHIFT) |
+		I2C_MST_CNTL_CYCLE_TRIGGER | I2C_MST_CNTL_GEN_NACK;
+	writel(val, i2cd->regs + I2C_MST_CNTL);
+
+	status = gpu_i2c_check_status(i2cd);
+	if (status < 0)
+		return status;
+
+	val = readl(i2cd->regs + I2C_MST_DATA);
+	switch (len) {
+	case 1:
+		data[0] = val;
+		break;
+	case 2:
+		put_unaligned_be16(val, data);
+		break;
+	case 3:
+		put_unaligned_be16(val >> 8, data);
+		data[2] = val;
+		break;
+	case 4:
+		put_unaligned_be32(val, data);
+		break;
+	default:
+		break;
+	}
+	return status;
+}
+
+static int gpu_i2c_start(struct gpu_i2c_dev *i2cd)
+{
+	writel(I2C_MST_CNTL_GEN_START, i2cd->regs + I2C_MST_CNTL);
+	return gpu_i2c_check_status(i2cd);
+}
+
+static int gpu_i2c_stop(struct gpu_i2c_dev *i2cd)
+{
+	writel(I2C_MST_CNTL_GEN_STOP, i2cd->regs + I2C_MST_CNTL);
+	return gpu_i2c_check_status(i2cd);
+}
+
+static int gpu_i2c_write(struct gpu_i2c_dev *i2cd, u8 data)
+{
+	u32 val;
+
+	writel(data, i2cd->regs + I2C_MST_DATA);
+
+	val = I2C_MST_CNTL_CMD_WRITE | (1 << I2C_MST_CNTL_BURST_SIZE_SHIFT);
+	writel(val, i2cd->regs + I2C_MST_CNTL);
+
+	return gpu_i2c_check_status(i2cd);
+}
+
+static int gpu_i2c_master_xfer(struct i2c_adapter *adap,
+			       struct i2c_msg *msgs, int num)
+{
+	struct gpu_i2c_dev *i2cd = i2c_get_adapdata(adap);
+	int status, status2;
+	int i, j;
+
+	/*
+	 * The controller supports maximum 4 byte read due to known
+	 * limitation of sending STOP after every read.
+	 */
+	for (i = 0; i < num; i++) {
+		if (msgs[i].flags & I2C_M_RD) {
+			/* program client address before starting read */
+			writel(msgs[i].addr, i2cd->regs + I2C_MST_ADDR);
+			/* gpu_i2c_read has implicit start */
+			status = gpu_i2c_read(i2cd, msgs[i].buf, msgs[i].len);
+			if (status < 0)
+				goto stop;
+		} else {
+			u8 addr = i2c_8bit_addr_from_msg(msgs + i);
+
+			status = gpu_i2c_start(i2cd);
+			if (status < 0) {
+				if (i == 0)
+					return status;
+				goto stop;
+			}
+
+			status = gpu_i2c_write(i2cd, addr);
+			if (status < 0)
+				goto stop;
+
+			for (j = 0; j < msgs[i].len; j++) {
+				status = gpu_i2c_write(i2cd, msgs[i].buf[j]);
+				if (status < 0)
+					goto stop;
+			}
+		}
+	}
+	status = gpu_i2c_stop(i2cd);
+	if (status < 0)
+		return status;
+
+	return i;
+stop:
+	status2 = gpu_i2c_stop(i2cd);
+	if (status2 < 0)
+		dev_err(i2cd->dev, "i2c stop failed %d\n", status2);
+	return status;
+}
+
+static const struct i2c_adapter_quirks gpu_i2c_quirks = {
+	.max_read_len = 4,
+	.flags = I2C_AQ_COMB_WRITE_THEN_READ,
+};
+
+static u32 gpu_i2c_functionality(struct i2c_adapter *adap)
+{
+	return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL;
+}
+
+static const struct i2c_algorithm gpu_i2c_algorithm = {
+	.master_xfer	= gpu_i2c_master_xfer,
+	.functionality	= gpu_i2c_functionality,
+};
+
+/*
+ * This driver is for Nvidia GPU cards with USB Type-C interface.
+ * We want to identify the cards using vendor ID and class code only
+ * to avoid dependency of adding product id for any new card which
+ * requires this driver.
+ * Currently there is no class code defined for UCSI device over PCI
+ * so using UNKNOWN class for now and it will be updated when UCSI
+ * over PCI gets a class code.
+ * There is no other NVIDIA cards with UNKNOWN class code. Even if the
+ * driver gets loaded for an undesired card then eventually i2c_read()
+ * (initiated from UCSI i2c_client) will timeout or UCSI commands will
+ * timeout.
+ */
+#define PCI_CLASS_SERIAL_UNKNOWN	0x0c80
+static const struct pci_device_id gpu_i2c_ids[] = {
+	{ PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID,
+		PCI_CLASS_SERIAL_UNKNOWN << 8, 0xffffff00},
+	{ }
+};
+MODULE_DEVICE_TABLE(pci, gpu_i2c_ids);
+
+static int gpu_populate_client(struct gpu_i2c_dev *i2cd, int irq)
+{
+	struct i2c_client *ccgx_client;
+
+	i2cd->gpu_ccgx_ucsi = devm_kzalloc(i2cd->dev,
+					   sizeof(*i2cd->gpu_ccgx_ucsi),
+					   GFP_KERNEL);
+	if (!i2cd->gpu_ccgx_ucsi)
+		return -ENOMEM;
+
+	strlcpy(i2cd->gpu_ccgx_ucsi->type, "ccgx-ucsi",
+		sizeof(i2cd->gpu_ccgx_ucsi->type));
+	i2cd->gpu_ccgx_ucsi->addr = 0x8;
+	i2cd->gpu_ccgx_ucsi->irq = irq;
+	ccgx_client = i2c_new_device(&i2cd->adapter, i2cd->gpu_ccgx_ucsi);
+	if (!ccgx_client)
+		return -ENODEV;
+
+	return 0;
+}
+
+static int gpu_i2c_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	struct gpu_i2c_dev *i2cd;
+	int status;
+
+	i2cd = devm_kzalloc(&pdev->dev, sizeof(*i2cd), GFP_KERNEL);
+	if (!i2cd)
+		return -ENOMEM;
+
+	i2cd->dev = &pdev->dev;
+	dev_set_drvdata(&pdev->dev, i2cd);
+
+	status = pcim_enable_device(pdev);
+	if (status < 0) {
+		dev_err(&pdev->dev, "pcim_enable_device failed %d\n", status);
+		return status;
+	}
+
+	pci_set_master(pdev);
+
+	i2cd->regs = pcim_iomap(pdev, 0, 0);
+	if (!i2cd->regs) {
+		dev_err(&pdev->dev, "pcim_iomap failed\n");
+		return -ENOMEM;
+	}
+
+	status = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSI);
+	if (status < 0) {
+		dev_err(&pdev->dev, "pci_alloc_irq_vectors err %d\n", status);
+		return status;
+	}
+
+	gpu_enable_i2c_bus(i2cd);
+
+	i2c_set_adapdata(&i2cd->adapter, i2cd);
+	i2cd->adapter.owner = THIS_MODULE;
+	strlcpy(i2cd->adapter.name, "NVIDIA GPU I2C adapter",
+		sizeof(i2cd->adapter.name));
+	i2cd->adapter.algo = &gpu_i2c_algorithm;
+	i2cd->adapter.quirks = &gpu_i2c_quirks;
+	i2cd->adapter.dev.parent = &pdev->dev;
+	status = i2c_add_adapter(&i2cd->adapter);
+	if (status < 0)
+		goto free_irq_vectors;
+
+	status = gpu_populate_client(i2cd, pdev->irq);
+	if (status < 0) {
+		dev_err(&pdev->dev, "gpu_populate_client failed %d\n", status);
+		goto del_adapter;
+	}
+
+	return 0;
+
+del_adapter:
+	i2c_del_adapter(&i2cd->adapter);
+free_irq_vectors:
+	pci_free_irq_vectors(pdev);
+	return status;
+}
+
+static void gpu_i2c_remove(struct pci_dev *pdev)
+{
+	struct gpu_i2c_dev *i2cd = dev_get_drvdata(&pdev->dev);
+
+	i2c_del_adapter(&i2cd->adapter);
+	pci_free_irq_vectors(pdev);
+}
+
+static int gpu_i2c_resume(struct device *dev)
+{
+	struct gpu_i2c_dev *i2cd = dev_get_drvdata(dev);
+
+	gpu_enable_i2c_bus(i2cd);
+	return 0;
+}
+
+static UNIVERSAL_DEV_PM_OPS(gpu_i2c_driver_pm, NULL, gpu_i2c_resume, NULL);
+
+static struct pci_driver gpu_i2c_driver = {
+	.name		= "nvidia-gpu",
+	.id_table	= gpu_i2c_ids,
+	.probe		= gpu_i2c_probe,
+	.remove		= gpu_i2c_remove,
+	.driver		= {
+		.pm	= &gpu_i2c_driver_pm,
+	},
+};
+
+module_pci_driver(gpu_i2c_driver);
+
+MODULE_AUTHOR("Ajay Gupta <ajayg@nvidia.com>");
+MODULE_DESCRIPTION("Nvidia GPU I2C controller Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c
index 527f55c..db075bc0 100644
--- a/drivers/i2c/busses/i2c-qcom-geni.c
+++ b/drivers/i2c/busses/i2c-qcom-geni.c
@@ -571,18 +571,19 @@ static int geni_i2c_probe(struct platform_device *pdev)
 
 	dev_dbg(&pdev->dev, "i2c fifo/se-dma mode. fifo depth:%d\n", tx_depth);
 
-	ret = i2c_add_adapter(&gi2c->adap);
-	if (ret) {
-		dev_err(&pdev->dev, "Error adding i2c adapter %d\n", ret);
-		return ret;
-	}
-
 	gi2c->suspended = 1;
 	pm_runtime_set_suspended(gi2c->se.dev);
 	pm_runtime_set_autosuspend_delay(gi2c->se.dev, I2C_AUTO_SUSPEND_DELAY);
 	pm_runtime_use_autosuspend(gi2c->se.dev);
 	pm_runtime_enable(gi2c->se.dev);
 
+	ret = i2c_add_adapter(&gi2c->adap);
+	if (ret) {
+		dev_err(&pdev->dev, "Error adding i2c adapter %d\n", ret);
+		pm_runtime_disable(gi2c->se.dev);
+		return ret;
+	}
+
 	return 0;
 }
 
@@ -590,8 +591,8 @@ static int geni_i2c_remove(struct platform_device *pdev)
 {
 	struct geni_i2c_dev *gi2c = platform_get_drvdata(pdev);
 
-	pm_runtime_disable(gi2c->se.dev);
 	i2c_del_adapter(&gi2c->adap);
+	pm_runtime_disable(gi2c->se.dev);
 	return 0;
 }
 
diff --git a/drivers/leds/trigger/ledtrig-pattern.c b/drivers/leds/trigger/ledtrig-pattern.c
index ce7acd1..1870cf8 100644
--- a/drivers/leds/trigger/ledtrig-pattern.c
+++ b/drivers/leds/trigger/ledtrig-pattern.c
@@ -75,8 +75,6 @@ static void pattern_trig_timer_function(struct timer_list *t)
 {
 	struct pattern_trig_data *data = from_timer(data, t, timer);
 
-	mutex_lock(&data->lock);
-
 	for (;;) {
 		if (!data->is_indefinite && !data->repeat)
 			break;
@@ -87,9 +85,10 @@ static void pattern_trig_timer_function(struct timer_list *t)
 					   data->curr->brightness);
 			mod_timer(&data->timer,
 				  jiffies + msecs_to_jiffies(data->curr->delta_t));
-
-			/* Skip the tuple with zero duration */
-			pattern_trig_update_patterns(data);
+			if (!data->next->delta_t) {
+				/* Skip the tuple with zero duration */
+				pattern_trig_update_patterns(data);
+			}
 			/* Select next tuple */
 			pattern_trig_update_patterns(data);
 		} else {
@@ -116,8 +115,6 @@ static void pattern_trig_timer_function(struct timer_list *t)
 
 		break;
 	}
-
-	mutex_unlock(&data->lock);
 }
 
 static int pattern_trig_start_pattern(struct led_classdev *led_cdev)
@@ -176,14 +173,10 @@ static ssize_t repeat_store(struct device *dev, struct device_attribute *attr,
 	if (res < -1 || res == 0)
 		return -EINVAL;
 
-	/*
-	 * Clear previous patterns' performence firstly, and remove the timer
-	 * without mutex lock to avoid dead lock.
-	 */
-	del_timer_sync(&data->timer);
-
 	mutex_lock(&data->lock);
 
+	del_timer_sync(&data->timer);
+
 	if (data->is_hw_pattern)
 		led_cdev->pattern_clear(led_cdev);
 
@@ -234,14 +227,10 @@ static ssize_t pattern_trig_store_patterns(struct led_classdev *led_cdev,
 	struct pattern_trig_data *data = led_cdev->trigger_data;
 	int ccount, cr, offset = 0, err = 0;
 
-	/*
-	 * Clear previous patterns' performence firstly, and remove the timer
-	 * without mutex lock to avoid dead lock.
-	 */
-	del_timer_sync(&data->timer);
-
 	mutex_lock(&data->lock);
 
+	del_timer_sync(&data->timer);
+
 	if (data->is_hw_pattern)
 		led_cdev->pattern_clear(led_cdev);
 
diff --git a/drivers/mtd/devices/Kconfig b/drivers/mtd/devices/Kconfig
index e514d57..aa98342 100644
--- a/drivers/mtd/devices/Kconfig
+++ b/drivers/mtd/devices/Kconfig
@@ -207,7 +207,7 @@
 config MTD_DOCG3
 	tristate "M-Systems Disk-On-Chip G3"
 	select BCH
-	select BCH_CONST_PARAMS
+	select BCH_CONST_PARAMS if !MTD_NAND_BCH
 	select BITREVERSE
 	help
 	  This provides an MTD device driver for the M-Systems DiskOnChip
diff --git a/drivers/mtd/maps/sa1100-flash.c b/drivers/mtd/maps/sa1100-flash.c
index 784c6e1..fd5fe12 100644
--- a/drivers/mtd/maps/sa1100-flash.c
+++ b/drivers/mtd/maps/sa1100-flash.c
@@ -221,7 +221,14 @@ static struct sa_info *sa1100_setup_mtd(struct platform_device *pdev,
 		info->mtd = info->subdev[0].mtd;
 		ret = 0;
 	} else if (info->num_subdev > 1) {
-		struct mtd_info *cdev[nr];
+		struct mtd_info **cdev;
+
+		cdev = kmalloc_array(nr, sizeof(*cdev), GFP_KERNEL);
+		if (!cdev) {
+			ret = -ENOMEM;
+			goto err;
+		}
+
 		/*
 		 * We detected multiple devices.  Concatenate them together.
 		 */
@@ -230,6 +237,7 @@ static struct sa_info *sa1100_setup_mtd(struct platform_device *pdev,
 
 		info->mtd = mtd_concat_create(cdev, info->num_subdev,
 					      plat->name);
+		kfree(cdev);
 		if (info->mtd == NULL) {
 			ret = -ENXIO;
 			goto err;
diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 05bd077..71050a0 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -590,7 +590,6 @@ nand_get_device(struct mtd_info *mtd, int new_state)
 
 /**
  * panic_nand_wait - [GENERIC] wait until the command is done
- * @mtd: MTD device structure
  * @chip: NAND chip structure
  * @timeo: timeout
  *
diff --git a/drivers/mtd/spi-nor/cadence-quadspi.c b/drivers/mtd/spi-nor/cadence-quadspi.c
index e24db81..d846428 100644
--- a/drivers/mtd/spi-nor/cadence-quadspi.c
+++ b/drivers/mtd/spi-nor/cadence-quadspi.c
@@ -996,7 +996,7 @@ static int cqspi_direct_read_execute(struct spi_nor *nor, u_char *buf,
 err_unmap:
 	dma_unmap_single(nor->dev, dma_dst, len, DMA_FROM_DEVICE);
 
-	return 0;
+	return ret;
 }
 
 static ssize_t cqspi_read(struct spi_nor *nor, loff_t from,
diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c
index 9407ca5..3e54e31 100644
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
@@ -3250,12 +3250,14 @@ static int spi_nor_init_params(struct spi_nor *nor,
 		memcpy(&sfdp_params, params, sizeof(sfdp_params));
 		memcpy(&prev_map, &nor->erase_map, sizeof(prev_map));
 
-		if (spi_nor_parse_sfdp(nor, &sfdp_params))
+		if (spi_nor_parse_sfdp(nor, &sfdp_params)) {
+			nor->addr_width = 0;
 			/* restore previous erase map */
 			memcpy(&nor->erase_map, &prev_map,
 			       sizeof(nor->erase_map));
-		else
+		} else {
 			memcpy(params, &sfdp_params, sizeof(*params));
+		}
 	}
 
 	return 0;
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 2e65be8..559d567 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1519,8 +1519,10 @@ static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 	if (ns->ndev)
 		nvme_nvm_update_nvm_info(ns);
 #ifdef CONFIG_NVME_MULTIPATH
-	if (ns->head->disk)
+	if (ns->head->disk) {
 		nvme_update_disk_info(ns->head->disk, ns, id);
+		blk_queue_stack_limits(ns->head->disk->queue, ns->queue);
+	}
 #endif
 }
 
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 5e3cc8c..9901afd 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -285,6 +285,7 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
 	/* set to a default value for 512 until disk is validated */
 	blk_queue_logical_block_size(q, 512);
+	blk_set_stacking_limits(&q->limits);
 
 	/* we need to propagate up the VMC settings */
 	if (ctrl->vwc & NVME_CTRL_VWC_PRESENT)
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index f4efe28..a5f9bbc 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -420,7 +420,7 @@ static void nvmet_p2pmem_ns_add_p2p(struct nvmet_ctrl *ctrl,
 	struct pci_dev *p2p_dev;
 	int ret;
 
-	if (!ctrl->p2p_client)
+	if (!ctrl->p2p_client || !ns->use_p2pmem)
 		return;
 
 	if (ns->p2p_dev) {
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index ddce100..3f7971d3 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -122,7 +122,6 @@ struct nvmet_rdma_device {
 	int			inline_page_count;
 };
 
-static struct workqueue_struct *nvmet_rdma_delete_wq;
 static bool nvmet_rdma_use_srq;
 module_param_named(use_srq, nvmet_rdma_use_srq, bool, 0444);
 MODULE_PARM_DESC(use_srq, "Use shared receive queue.");
@@ -1274,12 +1273,12 @@ static int nvmet_rdma_queue_connect(struct rdma_cm_id *cm_id,
 
 	if (queue->host_qid == 0) {
 		/* Let inflight controller teardown complete */
-		flush_workqueue(nvmet_rdma_delete_wq);
+		flush_scheduled_work();
 	}
 
 	ret = nvmet_rdma_cm_accept(cm_id, queue, &event->param.conn);
 	if (ret) {
-		queue_work(nvmet_rdma_delete_wq, &queue->release_work);
+		schedule_work(&queue->release_work);
 		/* Destroying rdma_cm id is not needed here */
 		return 0;
 	}
@@ -1344,7 +1343,7 @@ static void __nvmet_rdma_queue_disconnect(struct nvmet_rdma_queue *queue)
 
 	if (disconnect) {
 		rdma_disconnect(queue->cm_id);
-		queue_work(nvmet_rdma_delete_wq, &queue->release_work);
+		schedule_work(&queue->release_work);
 	}
 }
 
@@ -1374,7 +1373,7 @@ static void nvmet_rdma_queue_connect_fail(struct rdma_cm_id *cm_id,
 	mutex_unlock(&nvmet_rdma_queue_mutex);
 
 	pr_err("failed to connect queue %d\n", queue->idx);
-	queue_work(nvmet_rdma_delete_wq, &queue->release_work);
+	schedule_work(&queue->release_work);
 }
 
 /**
@@ -1656,17 +1655,8 @@ static int __init nvmet_rdma_init(void)
 	if (ret)
 		goto err_ib_client;
 
-	nvmet_rdma_delete_wq = alloc_workqueue("nvmet-rdma-delete-wq",
-			WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_SYSFS, 0);
-	if (!nvmet_rdma_delete_wq) {
-		ret = -ENOMEM;
-		goto err_unreg_transport;
-	}
-
 	return 0;
 
-err_unreg_transport:
-	nvmet_unregister_transport(&nvmet_rdma_ops);
 err_ib_client:
 	ib_unregister_client(&nvmet_rdma_ib_client);
 	return ret;
@@ -1674,7 +1664,6 @@ static int __init nvmet_rdma_init(void)
 
 static void __exit nvmet_rdma_exit(void)
 {
-	destroy_workqueue(nvmet_rdma_delete_wq);
 	nvmet_unregister_transport(&nvmet_rdma_ops);
 	ib_unregister_client(&nvmet_rdma_ib_client);
 	WARN_ON_ONCE(!list_empty(&nvmet_rdma_queue_list));
diff --git a/drivers/of/device.c b/drivers/of/device.c
index 0f27fad..5592437 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -149,9 +149,11 @@ int of_dma_configure(struct device *dev, struct device_node *np, bool force_dma)
 	 * set by the driver.
 	 */
 	mask = DMA_BIT_MASK(ilog2(dma_addr + size - 1) + 1);
-	dev->bus_dma_mask = mask;
 	dev->coherent_dma_mask &= mask;
 	*dev->dma_mask &= mask;
+	/* ...but only set bus mask if we found valid dma-ranges earlier */
+	if (!ret)
+		dev->bus_dma_mask = mask;
 
 	coherent = of_dma_is_coherent(np);
 	dev_dbg(dev, "device is%sdma coherent\n",
diff --git a/drivers/of/of_numa.c b/drivers/of/of_numa.c
index 35c64a4..fe6b136 100644
--- a/drivers/of/of_numa.c
+++ b/drivers/of/of_numa.c
@@ -104,9 +104,14 @@ static int __init of_numa_parse_distance_map_v1(struct device_node *map)
 		distance = of_read_number(matrix, 1);
 		matrix++;
 
+		if ((nodea == nodeb && distance != LOCAL_DISTANCE) ||
+		    (nodea != nodeb && distance <= LOCAL_DISTANCE)) {
+			pr_err("Invalid distance[node%d -> node%d] = %d\n",
+			       nodea, nodeb, distance);
+			return -EINVAL;
+		}
+
 		numa_set_distance(nodea, nodeb, distance);
-		pr_debug("distance[node%d -> node%d] = %d\n",
-			 nodea, nodeb, distance);
 
 		/* Set default distance of node B->A same as A->B */
 		if (nodeb > nodea)
diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c
index ff6ba6d..cc56cb3 100644
--- a/drivers/tty/serial/sh-sci.c
+++ b/drivers/tty/serial/sh-sci.c
@@ -1614,10 +1614,10 @@ static void sci_request_dma(struct uart_port *port)
 		hrtimer_init(&s->rx_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 		s->rx_timer.function = rx_timer_fn;
 
+		s->chan_rx_saved = s->chan_rx = chan;
+
 		if (port->type == PORT_SCIFA || port->type == PORT_SCIFB)
 			sci_submit_rx(s);
-
-		s->chan_rx_saved = s->chan_rx = chan;
 	}
 }
 
@@ -3102,6 +3102,7 @@ static struct uart_driver sci_uart_driver = {
 static int sci_remove(struct platform_device *dev)
 {
 	struct sci_port *port = platform_get_drvdata(dev);
+	unsigned int type = port->port.type;	/* uart_remove_... clears it */
 
 	sci_ports_in_use &= ~BIT(port->port.line);
 	uart_remove_one_port(&sci_uart_driver, &port->port);
@@ -3112,8 +3113,7 @@ static int sci_remove(struct platform_device *dev)
 		sysfs_remove_file(&dev->dev.kobj,
 				  &dev_attr_rx_fifo_trigger.attr);
 	}
-	if (port->port.type == PORT_SCIFA || port->port.type == PORT_SCIFB ||
-	    port->port.type == PORT_HSCIF) {
+	if (type == PORT_SCIFA || type == PORT_SCIFB || type == PORT_HSCIF) {
 		sysfs_remove_file(&dev->dev.kobj,
 				  &dev_attr_rx_fifo_timeout.attr);
 	}
diff --git a/drivers/tty/tty_baudrate.c b/drivers/tty/tty_baudrate.c
index 7576cea..f438eaa 100644
--- a/drivers/tty/tty_baudrate.c
+++ b/drivers/tty/tty_baudrate.c
@@ -77,7 +77,7 @@ speed_t tty_termios_baud_rate(struct ktermios *termios)
 		else
 			cbaud += 15;
 	}
-	return baud_table[cbaud];
+	return cbaud >= n_baud_table ? 0 : baud_table[cbaud];
 }
 EXPORT_SYMBOL(tty_termios_baud_rate);
 
@@ -113,7 +113,7 @@ speed_t tty_termios_input_baud_rate(struct ktermios *termios)
 		else
 			cbaud += 15;
 	}
-	return baud_table[cbaud];
+	return cbaud >= n_baud_table ? 0 : baud_table[cbaud];
 #else	/* IBSHIFT */
 	return tty_termios_baud_rate(termios);
 #endif	/* IBSHIFT */
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index 55370e6..41ec8e5 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -1548,7 +1548,7 @@ static void csi_K(struct vc_data *vc, int vpar)
 	scr_memsetw(start + offset, vc->vc_video_erase_char, 2 * count);
 	vc->vc_need_wrap = 0;
 	if (con_should_update(vc))
-		do_update_region(vc, (unsigned long) start, count);
+		do_update_region(vc, (unsigned long)(start + offset), count);
 }
 
 static void csi_X(struct vc_data *vc, int vpar) /* erase the following vpar positions */
diff --git a/drivers/usb/typec/ucsi/Kconfig b/drivers/usb/typec/ucsi/Kconfig
index e36d6c7..7811888 100644
--- a/drivers/usb/typec/ucsi/Kconfig
+++ b/drivers/usb/typec/ucsi/Kconfig
@@ -23,6 +23,16 @@
 
 if TYPEC_UCSI
 
+config UCSI_CCG
+	tristate "UCSI Interface Driver for Cypress CCGx"
+	depends on I2C
+	help
+	  This driver enables UCSI support on platforms that expose a
+	  Cypress CCGx Type-C controller over I2C interface.
+
+	  To compile the driver as a module, choose M here: the module will be
+	  called ucsi_ccg.
+
 config UCSI_ACPI
 	tristate "UCSI ACPI Interface Driver"
 	depends on ACPI
diff --git a/drivers/usb/typec/ucsi/Makefile b/drivers/usb/typec/ucsi/Makefile
index 7afbea5..2f4900b 100644
--- a/drivers/usb/typec/ucsi/Makefile
+++ b/drivers/usb/typec/ucsi/Makefile
@@ -8,3 +8,5 @@
 typec_ucsi-$(CONFIG_TRACING)	+= trace.o
 
 obj-$(CONFIG_UCSI_ACPI)		+= ucsi_acpi.o
+
+obj-$(CONFIG_UCSI_CCG)		+= ucsi_ccg.o
diff --git a/drivers/usb/typec/ucsi/ucsi_ccg.c b/drivers/usb/typec/ucsi/ucsi_ccg.c
new file mode 100644
index 0000000..de8a43b
--- /dev/null
+++ b/drivers/usb/typec/ucsi/ucsi_ccg.c
@@ -0,0 +1,307 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * UCSI driver for Cypress CCGx Type-C controller
+ *
+ * Copyright (C) 2017-2018 NVIDIA Corporation. All rights reserved.
+ * Author: Ajay Gupta <ajayg@nvidia.com>
+ *
+ * Some code borrowed from drivers/usb/typec/ucsi/ucsi_acpi.c
+ */
+#include <linux/acpi.h>
+#include <linux/delay.h>
+#include <linux/i2c.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+
+#include <asm/unaligned.h>
+#include "ucsi.h"
+
+struct ucsi_ccg {
+	struct device *dev;
+	struct ucsi *ucsi;
+	struct ucsi_ppm ppm;
+	struct i2c_client *client;
+};
+
+#define CCGX_RAB_INTR_REG			0x06
+#define CCGX_RAB_UCSI_CONTROL			0x39
+#define CCGX_RAB_UCSI_CONTROL_START		BIT(0)
+#define CCGX_RAB_UCSI_CONTROL_STOP		BIT(1)
+#define CCGX_RAB_UCSI_DATA_BLOCK(offset)	(0xf000 | ((offset) & 0xff))
+
+static int ccg_read(struct ucsi_ccg *uc, u16 rab, u8 *data, u32 len)
+{
+	struct i2c_client *client = uc->client;
+	const struct i2c_adapter_quirks *quirks = client->adapter->quirks;
+	unsigned char buf[2];
+	struct i2c_msg msgs[] = {
+		{
+			.addr	= client->addr,
+			.flags  = 0x0,
+			.len	= sizeof(buf),
+			.buf	= buf,
+		},
+		{
+			.addr	= client->addr,
+			.flags  = I2C_M_RD,
+			.buf	= data,
+		},
+	};
+	u32 rlen, rem_len = len, max_read_len = len;
+	int status;
+
+	/* check any max_read_len limitation on i2c adapter */
+	if (quirks && quirks->max_read_len)
+		max_read_len = quirks->max_read_len;
+
+	while (rem_len > 0) {
+		msgs[1].buf = &data[len - rem_len];
+		rlen = min_t(u16, rem_len, max_read_len);
+		msgs[1].len = rlen;
+		put_unaligned_le16(rab, buf);
+		status = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs));
+		if (status < 0) {
+			dev_err(uc->dev, "i2c_transfer failed %d\n", status);
+			return status;
+		}
+		rab += rlen;
+		rem_len -= rlen;
+	}
+
+	return 0;
+}
+
+static int ccg_write(struct ucsi_ccg *uc, u16 rab, u8 *data, u32 len)
+{
+	struct i2c_client *client = uc->client;
+	unsigned char *buf;
+	struct i2c_msg msgs[] = {
+		{
+			.addr	= client->addr,
+			.flags  = 0x0,
+		}
+	};
+	int status;
+
+	buf = kzalloc(len + sizeof(rab), GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	put_unaligned_le16(rab, buf);
+	memcpy(buf + sizeof(rab), data, len);
+
+	msgs[0].len = len + sizeof(rab);
+	msgs[0].buf = buf;
+
+	status = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs));
+	if (status < 0) {
+		dev_err(uc->dev, "i2c_transfer failed %d\n", status);
+		kfree(buf);
+		return status;
+	}
+
+	kfree(buf);
+	return 0;
+}
+
+static int ucsi_ccg_init(struct ucsi_ccg *uc)
+{
+	unsigned int count = 10;
+	u8 data;
+	int status;
+
+	data = CCGX_RAB_UCSI_CONTROL_STOP;
+	status = ccg_write(uc, CCGX_RAB_UCSI_CONTROL, &data, sizeof(data));
+	if (status < 0)
+		return status;
+
+	data = CCGX_RAB_UCSI_CONTROL_START;
+	status = ccg_write(uc, CCGX_RAB_UCSI_CONTROL, &data, sizeof(data));
+	if (status < 0)
+		return status;
+
+	/*
+	 * Flush CCGx RESPONSE queue by acking interrupts. Above ucsi control
+	 * register write will push response which must be cleared.
+	 */
+	do {
+		status = ccg_read(uc, CCGX_RAB_INTR_REG, &data, sizeof(data));
+		if (status < 0)
+			return status;
+
+		if (!data)
+			return 0;
+
+		status = ccg_write(uc, CCGX_RAB_INTR_REG, &data, sizeof(data));
+		if (status < 0)
+			return status;
+
+		usleep_range(10000, 11000);
+	} while (--count);
+
+	return -ETIMEDOUT;
+}
+
+static int ucsi_ccg_send_data(struct ucsi_ccg *uc)
+{
+	u8 *ppm = (u8 *)uc->ppm.data;
+	int status;
+	u16 rab;
+
+	rab = CCGX_RAB_UCSI_DATA_BLOCK(offsetof(struct ucsi_data, message_out));
+	status = ccg_write(uc, rab, ppm +
+			   offsetof(struct ucsi_data, message_out),
+			   sizeof(uc->ppm.data->message_out));
+	if (status < 0)
+		return status;
+
+	rab = CCGX_RAB_UCSI_DATA_BLOCK(offsetof(struct ucsi_data, ctrl));
+	return ccg_write(uc, rab, ppm + offsetof(struct ucsi_data, ctrl),
+			 sizeof(uc->ppm.data->ctrl));
+}
+
+static int ucsi_ccg_recv_data(struct ucsi_ccg *uc)
+{
+	u8 *ppm = (u8 *)uc->ppm.data;
+	int status;
+	u16 rab;
+
+	rab = CCGX_RAB_UCSI_DATA_BLOCK(offsetof(struct ucsi_data, cci));
+	status = ccg_read(uc, rab, ppm + offsetof(struct ucsi_data, cci),
+			  sizeof(uc->ppm.data->cci));
+	if (status < 0)
+		return status;
+
+	rab = CCGX_RAB_UCSI_DATA_BLOCK(offsetof(struct ucsi_data, message_in));
+	return ccg_read(uc, rab, ppm + offsetof(struct ucsi_data, message_in),
+			sizeof(uc->ppm.data->message_in));
+}
+
+static int ucsi_ccg_ack_interrupt(struct ucsi_ccg *uc)
+{
+	int status;
+	unsigned char data;
+
+	status = ccg_read(uc, CCGX_RAB_INTR_REG, &data, sizeof(data));
+	if (status < 0)
+		return status;
+
+	return ccg_write(uc, CCGX_RAB_INTR_REG, &data, sizeof(data));
+}
+
+static int ucsi_ccg_sync(struct ucsi_ppm *ppm)
+{
+	struct ucsi_ccg *uc = container_of(ppm, struct ucsi_ccg, ppm);
+	int status;
+
+	status = ucsi_ccg_recv_data(uc);
+	if (status < 0)
+		return status;
+
+	/* ack interrupt to allow next command to run */
+	return ucsi_ccg_ack_interrupt(uc);
+}
+
+static int ucsi_ccg_cmd(struct ucsi_ppm *ppm, struct ucsi_control *ctrl)
+{
+	struct ucsi_ccg *uc = container_of(ppm, struct ucsi_ccg, ppm);
+
+	ppm->data->ctrl.raw_cmd = ctrl->raw_cmd;
+	return ucsi_ccg_send_data(uc);
+}
+
+static irqreturn_t ccg_irq_handler(int irq, void *data)
+{
+	struct ucsi_ccg *uc = data;
+
+	ucsi_notify(uc->ucsi);
+
+	return IRQ_HANDLED;
+}
+
+static int ucsi_ccg_probe(struct i2c_client *client,
+			  const struct i2c_device_id *id)
+{
+	struct device *dev = &client->dev;
+	struct ucsi_ccg *uc;
+	int status;
+	u16 rab;
+
+	uc = devm_kzalloc(dev, sizeof(*uc), GFP_KERNEL);
+	if (!uc)
+		return -ENOMEM;
+
+	uc->ppm.data = devm_kzalloc(dev, sizeof(struct ucsi_data), GFP_KERNEL);
+	if (!uc->ppm.data)
+		return -ENOMEM;
+
+	uc->ppm.cmd = ucsi_ccg_cmd;
+	uc->ppm.sync = ucsi_ccg_sync;
+	uc->dev = dev;
+	uc->client = client;
+
+	/* reset ccg device and initialize ucsi */
+	status = ucsi_ccg_init(uc);
+	if (status < 0) {
+		dev_err(uc->dev, "ucsi_ccg_init failed - %d\n", status);
+		return status;
+	}
+
+	status = devm_request_threaded_irq(dev, client->irq, NULL,
+					   ccg_irq_handler,
+					   IRQF_ONESHOT | IRQF_TRIGGER_HIGH,
+					   dev_name(dev), uc);
+	if (status < 0) {
+		dev_err(uc->dev, "request_threaded_irq failed - %d\n", status);
+		return status;
+	}
+
+	uc->ucsi = ucsi_register_ppm(dev, &uc->ppm);
+	if (IS_ERR(uc->ucsi)) {
+		dev_err(uc->dev, "ucsi_register_ppm failed\n");
+		return PTR_ERR(uc->ucsi);
+	}
+
+	rab = CCGX_RAB_UCSI_DATA_BLOCK(offsetof(struct ucsi_data, version));
+	status = ccg_read(uc, rab, (u8 *)(uc->ppm.data) +
+			  offsetof(struct ucsi_data, version),
+			  sizeof(uc->ppm.data->version));
+	if (status < 0) {
+		ucsi_unregister_ppm(uc->ucsi);
+		return status;
+	}
+
+	i2c_set_clientdata(client, uc);
+	return 0;
+}
+
+static int ucsi_ccg_remove(struct i2c_client *client)
+{
+	struct ucsi_ccg *uc = i2c_get_clientdata(client);
+
+	ucsi_unregister_ppm(uc->ucsi);
+
+	return 0;
+}
+
+static const struct i2c_device_id ucsi_ccg_device_id[] = {
+	{"ccgx-ucsi", 0},
+	{}
+};
+MODULE_DEVICE_TABLE(i2c, ucsi_ccg_device_id);
+
+static struct i2c_driver ucsi_ccg_driver = {
+	.driver = {
+		.name = "ucsi_ccg",
+	},
+	.probe = ucsi_ccg_probe,
+	.remove = ucsi_ccg_remove,
+	.id_table = ucsi_ccg_device_id,
+};
+
+module_i2c_driver(ucsi_ccg_driver);
+
+MODULE_AUTHOR("Ajay Gupta <ajayg@nvidia.com>");
+MODULE_DESCRIPTION("UCSI driver for Cypress CCGx Type-C controller");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index f15f89d..7ea6fb6 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -914,7 +914,7 @@ int gnttab_dma_free_pages(struct gnttab_dma_alloc_args *args)
 
 	ret = xenmem_reservation_increase(args->nr_pages, args->frames);
 	if (ret != args->nr_pages) {
-		pr_debug("Failed to decrease reservation for DMA buffer\n");
+		pr_debug("Failed to increase reservation for DMA buffer\n");
 		ret = -EFAULT;
 	} else {
 		ret = 0;
diff --git a/drivers/xen/privcmd-buf.c b/drivers/xen/privcmd-buf.c
index df1ed37..de01a6d 100644
--- a/drivers/xen/privcmd-buf.c
+++ b/drivers/xen/privcmd-buf.c
@@ -21,15 +21,9 @@
 
 MODULE_LICENSE("GPL");
 
-static unsigned int limit = 64;
-module_param(limit, uint, 0644);
-MODULE_PARM_DESC(limit, "Maximum number of pages that may be allocated by "
-			"the privcmd-buf device per open file");
-
 struct privcmd_buf_private {
 	struct mutex lock;
 	struct list_head list;
-	unsigned int allocated;
 };
 
 struct privcmd_buf_vma_private {
@@ -60,13 +54,10 @@ static void privcmd_buf_vmapriv_free(struct privcmd_buf_vma_private *vma_priv)
 {
 	unsigned int i;
 
-	vma_priv->file_priv->allocated -= vma_priv->n_pages;
-
 	list_del(&vma_priv->list);
 
 	for (i = 0; i < vma_priv->n_pages; i++)
-		if (vma_priv->pages[i])
-			__free_page(vma_priv->pages[i]);
+		__free_page(vma_priv->pages[i]);
 
 	kfree(vma_priv);
 }
@@ -146,8 +137,7 @@ static int privcmd_buf_mmap(struct file *file, struct vm_area_struct *vma)
 	unsigned int i;
 	int ret = 0;
 
-	if (!(vma->vm_flags & VM_SHARED) || count > limit ||
-	    file_priv->allocated + count > limit)
+	if (!(vma->vm_flags & VM_SHARED))
 		return -EINVAL;
 
 	vma_priv = kzalloc(sizeof(*vma_priv) + count * sizeof(void *),
@@ -155,19 +145,15 @@ static int privcmd_buf_mmap(struct file *file, struct vm_area_struct *vma)
 	if (!vma_priv)
 		return -ENOMEM;
 
-	vma_priv->n_pages = count;
-	count = 0;
-	for (i = 0; i < vma_priv->n_pages; i++) {
+	for (i = 0; i < count; i++) {
 		vma_priv->pages[i] = alloc_page(GFP_KERNEL | __GFP_ZERO);
 		if (!vma_priv->pages[i])
 			break;
-		count++;
+		vma_priv->n_pages++;
 	}
 
 	mutex_lock(&file_priv->lock);
 
-	file_priv->allocated += count;
-
 	vma_priv->file_priv = file_priv;
 	vma_priv->users = 1;
 
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 8095352..68f322f 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3163,6 +3163,9 @@ void btrfs_destroy_inode(struct inode *inode);
 int btrfs_drop_inode(struct inode *inode);
 int __init btrfs_init_cachep(void);
 void __cold btrfs_destroy_cachep(void);
+struct inode *btrfs_iget_path(struct super_block *s, struct btrfs_key *location,
+			      struct btrfs_root *root, int *new,
+			      struct btrfs_path *path);
 struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
 			 struct btrfs_root *root, int *was_new);
 struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index b0ab41d..3f0b6d1 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1664,9 +1664,8 @@ static int cleaner_kthread(void *arg)
 	struct btrfs_root *root = arg;
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	int again;
-	struct btrfs_trans_handle *trans;
 
-	do {
+	while (1) {
 		again = 0;
 
 		/* Make the cleaner go to sleep early. */
@@ -1715,42 +1714,16 @@ static int cleaner_kthread(void *arg)
 		 */
 		btrfs_delete_unused_bgs(fs_info);
 sleep:
+		if (kthread_should_park())
+			kthread_parkme();
+		if (kthread_should_stop())
+			return 0;
 		if (!again) {
 			set_current_state(TASK_INTERRUPTIBLE);
-			if (!kthread_should_stop())
-				schedule();
+			schedule();
 			__set_current_state(TASK_RUNNING);
 		}
-	} while (!kthread_should_stop());
-
-	/*
-	 * Transaction kthread is stopped before us and wakes us up.
-	 * However we might have started a new transaction and COWed some
-	 * tree blocks when deleting unused block groups for example. So
-	 * make sure we commit the transaction we started to have a clean
-	 * shutdown when evicting the btree inode - if it has dirty pages
-	 * when we do the final iput() on it, eviction will trigger a
-	 * writeback for it which will fail with null pointer dereferences
-	 * since work queues and other resources were already released and
-	 * destroyed by the time the iput/eviction/writeback is made.
-	 */
-	trans = btrfs_attach_transaction(root);
-	if (IS_ERR(trans)) {
-		if (PTR_ERR(trans) != -ENOENT)
-			btrfs_err(fs_info,
-				  "cleaner transaction attach returned %ld",
-				  PTR_ERR(trans));
-	} else {
-		int ret;
-
-		ret = btrfs_commit_transaction(trans);
-		if (ret)
-			btrfs_err(fs_info,
-				  "cleaner open transaction commit returned %d",
-				  ret);
 	}
-
-	return 0;
 }
 
 static int transaction_kthread(void *arg)
@@ -3931,6 +3904,13 @@ void close_ctree(struct btrfs_fs_info *fs_info)
 	int ret;
 
 	set_bit(BTRFS_FS_CLOSING_START, &fs_info->flags);
+	/*
+	 * We don't want the cleaner to start new transactions, add more delayed
+	 * iputs, etc. while we're closing. We can't use kthread_stop() yet
+	 * because that frees the task_struct, and the transaction kthread might
+	 * still try to wake up the cleaner.
+	 */
+	kthread_park(fs_info->cleaner_kthread);
 
 	/* wait for the qgroup rescan worker to stop */
 	btrfs_qgroup_wait_for_completion(fs_info, false);
@@ -3958,9 +3938,8 @@ void close_ctree(struct btrfs_fs_info *fs_info)
 
 	if (!sb_rdonly(fs_info->sb)) {
 		/*
-		 * If the cleaner thread is stopped and there are
-		 * block groups queued for removal, the deletion will be
-		 * skipped when we quit the cleaner thread.
+		 * The cleaner kthread is stopped, so do one final pass over
+		 * unused block groups.
 		 */
 		btrfs_delete_unused_bgs(fs_info);
 
@@ -4359,13 +4338,23 @@ static int btrfs_destroy_pinned_extent(struct btrfs_fs_info *fs_info,
 	unpin = pinned_extents;
 again:
 	while (1) {
+		/*
+		 * The btrfs_finish_extent_commit() may get the same range as
+		 * ours between find_first_extent_bit and clear_extent_dirty.
+		 * Hence, hold the unused_bg_unpin_mutex to avoid double unpin
+		 * the same extent range.
+		 */
+		mutex_lock(&fs_info->unused_bg_unpin_mutex);
 		ret = find_first_extent_bit(unpin, 0, &start, &end,
 					    EXTENT_DIRTY, NULL);
-		if (ret)
+		if (ret) {
+			mutex_unlock(&fs_info->unused_bg_unpin_mutex);
 			break;
+		}
 
 		clear_extent_dirty(unpin, start, end);
 		btrfs_error_unpin_extent_range(fs_info, start, end);
+		mutex_unlock(&fs_info->unused_bg_unpin_mutex);
 		cond_resched();
 	}
 
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 4ba0aed..74aa552 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -75,7 +75,8 @@ static struct inode *__lookup_free_space_inode(struct btrfs_root *root,
 	 * sure NOFS is set to keep us from deadlocking.
 	 */
 	nofs_flag = memalloc_nofs_save();
-	inode = btrfs_iget(fs_info->sb, &location, root, NULL);
+	inode = btrfs_iget_path(fs_info->sb, &location, root, NULL, path);
+	btrfs_release_path(path);
 	memalloc_nofs_restore(nofs_flag);
 	if (IS_ERR(inode))
 		return inode;
@@ -838,6 +839,25 @@ int load_free_space_cache(struct btrfs_fs_info *fs_info,
 	path->search_commit_root = 1;
 	path->skip_locking = 1;
 
+	/*
+	 * We must pass a path with search_commit_root set to btrfs_iget in
+	 * order to avoid a deadlock when allocating extents for the tree root.
+	 *
+	 * When we are COWing an extent buffer from the tree root, when looking
+	 * for a free extent, at extent-tree.c:find_free_extent(), we can find
+	 * block group without its free space cache loaded. When we find one
+	 * we must load its space cache which requires reading its free space
+	 * cache's inode item from the root tree. If this inode item is located
+	 * in the same leaf that we started COWing before, then we end up in
+	 * deadlock on the extent buffer (trying to read lock it when we
+	 * previously write locked it).
+	 *
+	 * It's safe to read the inode item using the commit root because
+	 * block groups, once loaded, stay in memory forever (until they are
+	 * removed) as well as their space caches once loaded. New block groups
+	 * once created get their ->cached field set to BTRFS_CACHE_FINISHED so
+	 * we will never try to read their inode item while the fs is mounted.
+	 */
 	inode = lookup_free_space_inode(fs_info, block_group, path);
 	if (IS_ERR(inode)) {
 		btrfs_free_path(path);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index d3df5b5..9ea4c6f 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1531,12 +1531,11 @@ static noinline int run_delalloc_nocow(struct inode *inode,
 	}
 	btrfs_release_path(path);
 
-	if (cur_offset <= end && cow_start == (u64)-1) {
+	if (cur_offset <= end && cow_start == (u64)-1)
 		cow_start = cur_offset;
-		cur_offset = end;
-	}
 
 	if (cow_start != (u64)-1) {
+		cur_offset = end;
 		ret = cow_file_range(inode, locked_page, cow_start, end, end,
 				     page_started, nr_written, 1, NULL);
 		if (ret)
@@ -3570,10 +3569,11 @@ static noinline int acls_after_inode_item(struct extent_buffer *leaf,
 /*
  * read an inode from the btree into the in-memory inode
  */
-static int btrfs_read_locked_inode(struct inode *inode)
+static int btrfs_read_locked_inode(struct inode *inode,
+				   struct btrfs_path *in_path)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	struct btrfs_path *path;
+	struct btrfs_path *path = in_path;
 	struct extent_buffer *leaf;
 	struct btrfs_inode_item *inode_item;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
@@ -3589,15 +3589,18 @@ static int btrfs_read_locked_inode(struct inode *inode)
 	if (!ret)
 		filled = true;
 
-	path = btrfs_alloc_path();
-	if (!path)
-		return -ENOMEM;
+	if (!path) {
+		path = btrfs_alloc_path();
+		if (!path)
+			return -ENOMEM;
+	}
 
 	memcpy(&location, &BTRFS_I(inode)->location, sizeof(location));
 
 	ret = btrfs_lookup_inode(NULL, root, path, &location, 0);
 	if (ret) {
-		btrfs_free_path(path);
+		if (path != in_path)
+			btrfs_free_path(path);
 		return ret;
 	}
 
@@ -3722,7 +3725,8 @@ static int btrfs_read_locked_inode(struct inode *inode)
 				  btrfs_ino(BTRFS_I(inode)),
 				  root->root_key.objectid, ret);
 	}
-	btrfs_free_path(path);
+	if (path != in_path)
+		btrfs_free_path(path);
 
 	if (!maybe_acls)
 		cache_no_acl(inode);
@@ -5644,8 +5648,9 @@ static struct inode *btrfs_iget_locked(struct super_block *s,
 /* Get an inode object given its location and corresponding root.
  * Returns in *is_new if the inode was read from disk
  */
-struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
-			 struct btrfs_root *root, int *new)
+struct inode *btrfs_iget_path(struct super_block *s, struct btrfs_key *location,
+			      struct btrfs_root *root, int *new,
+			      struct btrfs_path *path)
 {
 	struct inode *inode;
 
@@ -5656,7 +5661,7 @@ struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
 	if (inode->i_state & I_NEW) {
 		int ret;
 
-		ret = btrfs_read_locked_inode(inode);
+		ret = btrfs_read_locked_inode(inode, path);
 		if (!ret) {
 			inode_tree_add(inode);
 			unlock_new_inode(inode);
@@ -5678,6 +5683,12 @@ struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
 	return inode;
 }
 
+struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
+			 struct btrfs_root *root, int *new)
+{
+	return btrfs_iget_path(s, location, root, new, NULL);
+}
+
 static struct inode *new_simple_dir(struct super_block *s,
 				    struct btrfs_key *key,
 				    struct btrfs_root *root)
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 3ca6943..802a628 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3488,6 +3488,8 @@ static int btrfs_extent_same_range(struct inode *src, u64 loff, u64 olen,
 			const u64 sz = BTRFS_I(src)->root->fs_info->sectorsize;
 
 			len = round_down(i_size_read(src), sz) - loff;
+			if (len == 0)
+				return 0;
 			olen = len;
 		}
 	}
@@ -4257,9 +4259,17 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src,
 		goto out_unlock;
 	if (len == 0)
 		olen = len = src->i_size - off;
-	/* if we extend to eof, continue to block boundary */
-	if (off + len == src->i_size)
+	/*
+	 * If we extend to eof, continue to block boundary if and only if the
+	 * destination end offset matches the destination file's size, otherwise
+	 * we would be corrupting data by placing the eof block into the middle
+	 * of a file.
+	 */
+	if (off + len == src->i_size) {
+		if (!IS_ALIGNED(len, bs) && destoff + len < inode->i_size)
+			goto out_unlock;
 		len = ALIGN(src->i_size, bs) - off;
+	}
 
 	if (len == 0) {
 		ret = 0;
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index b362b45..cbc9d0d 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1916,7 +1916,7 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
 }
 
 /* Used to sort the devices by max_avail(descending sort) */
-static int btrfs_cmp_device_free_bytes(const void *dev_info1,
+static inline int btrfs_cmp_device_free_bytes(const void *dev_info1,
 				       const void *dev_info2)
 {
 	if (((struct btrfs_device_info *)dev_info1)->max_avail >
@@ -1945,8 +1945,8 @@ static inline void btrfs_descending_sort_devices(
  * The helper to calc the free space on the devices that can be used to store
  * file data.
  */
-static int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info,
-				       u64 *free_bytes)
+static inline int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info,
+					      u64 *free_bytes)
 {
 	struct btrfs_device_info *devices_info;
 	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index cab0b1f..efcf89a8 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -440,7 +440,7 @@ static int check_block_group_item(struct btrfs_fs_info *fs_info,
 	    type != (BTRFS_BLOCK_GROUP_METADATA |
 			   BTRFS_BLOCK_GROUP_DATA)) {
 		block_group_err(fs_info, leaf, slot,
-"invalid type, have 0x%llx (%lu bits set) expect either 0x%llx, 0x%llx, 0x%llu or 0x%llx",
+"invalid type, have 0x%llx (%lu bits set) expect either 0x%llx, 0x%llx, 0x%llx or 0x%llx",
 			type, hweight64(type),
 			BTRFS_BLOCK_GROUP_DATA, BTRFS_BLOCK_GROUP_METADATA,
 			BTRFS_BLOCK_GROUP_SYSTEM,
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index e07f337..a5ce99a 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -4396,6 +4396,23 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
 	logged_end = end;
 
 	list_for_each_entry_safe(em, n, &tree->modified_extents, list) {
+		/*
+		 * Skip extents outside our logging range. It's important to do
+		 * it for correctness because if we don't ignore them, we may
+		 * log them before their ordered extent completes, and therefore
+		 * we could log them without logging their respective checksums
+		 * (the checksum items are added to the csum tree at the very
+		 * end of btrfs_finish_ordered_io()). Also leave such extents
+		 * outside of our range in the list, since we may have another
+		 * ranged fsync in the near future that needs them. If an extent
+		 * outside our range corresponds to a hole, log it to avoid
+		 * leaving gaps between extents (fsck will complain when we are
+		 * not using the NO_HOLES feature).
+		 */
+		if ((em->start > end || em->start + em->len <= start) &&
+		    em->block_start != EXTENT_MAP_HOLE)
+			continue;
+
 		list_del_init(&em->list);
 		/*
 		 * Just an arbitrary number, this can be really CPU intensive
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 27cad84..189df66 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -1931,10 +1931,17 @@ static ssize_t ceph_copy_file_range(struct file *src_file, loff_t src_off,
 	if (!prealloc_cf)
 		return -ENOMEM;
 
-	/* Start by sync'ing the source file */
+	/* Start by sync'ing the source and destination files */
 	ret = file_write_and_wait_range(src_file, src_off, (src_off + len));
-	if (ret < 0)
+	if (ret < 0) {
+		dout("failed to write src file (%zd)\n", ret);
 		goto out;
+	}
+	ret = file_write_and_wait_range(dst_file, dst_off, (dst_off + len));
+	if (ret < 0) {
+		dout("failed to write dst file (%zd)\n", ret);
+		goto out;
+	}
 
 	/*
 	 * We need FILE_WR caps for dst_ci and FILE_RD for src_ci as other
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 67a9aeb..bd13a32 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -80,12 +80,8 @@ static int parse_reply_info_in(void **p, void *end,
 	info->symlink = *p;
 	*p += info->symlink_len;
 
-	if (features & CEPH_FEATURE_DIRLAYOUTHASH)
-		ceph_decode_copy_safe(p, end, &info->dir_layout,
-				      sizeof(info->dir_layout), bad);
-	else
-		memset(&info->dir_layout, 0, sizeof(info->dir_layout));
-
+	ceph_decode_copy_safe(p, end, &info->dir_layout,
+			      sizeof(info->dir_layout), bad);
 	ceph_decode_32_safe(p, end, info->xattr_len, bad);
 	ceph_decode_need(p, end, info->xattr_len, bad);
 	info->xattr_data = *p;
@@ -3182,10 +3178,8 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc,
 	recon_state.pagelist = pagelist;
 	if (session->s_con.peer_features & CEPH_FEATURE_MDSENC)
 		recon_state.msg_version = 3;
-	else if (session->s_con.peer_features & CEPH_FEATURE_FLOCK)
-		recon_state.msg_version = 2;
 	else
-		recon_state.msg_version = 1;
+		recon_state.msg_version = 2;
 	err = iterate_session_caps(session, encode_caps_cb, &recon_state);
 	if (err < 0)
 		goto fail;
diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c
index 32d4f13..03f4d24 100644
--- a/fs/ceph/quota.c
+++ b/fs/ceph/quota.c
@@ -237,7 +237,8 @@ static bool check_quota_exceeded(struct inode *inode, enum quota_check_op op,
 		ceph_put_snap_realm(mdsc, realm);
 		realm = next;
 	}
-	ceph_put_snap_realm(mdsc, realm);
+	if (realm)
+		ceph_put_snap_realm(mdsc, realm);
 	up_read(&mdsc->snap_rwsem);
 
 	return exceeded;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 05f01fb..22a9d81 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -5835,9 +5835,10 @@ int ext4_mark_iloc_dirty(handle_t *handle,
 {
 	int err = 0;
 
-	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) {
+		put_bh(iloc->bh);
 		return -EIO;
-
+	}
 	if (IS_I_VERSION(inode))
 		inode_inc_iversion(inode);
 
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 17adcb1..437f71f 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -126,6 +126,7 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode,
 	if (!is_dx_block && type == INDEX) {
 		ext4_error_inode(inode, func, line, block,
 		       "directory leaf block found instead of index block");
+		brelse(bh);
 		return ERR_PTR(-EFSCORRUPTED);
 	}
 	if (!ext4_has_metadata_csum(inode->i_sb) ||
@@ -2811,7 +2812,9 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode)
 			list_del_init(&EXT4_I(inode)->i_orphan);
 			mutex_unlock(&sbi->s_orphan_lock);
 		}
-	}
+	} else
+		brelse(iloc.bh);
+
 	jbd_debug(4, "superblock will point to %lu\n", inode->i_ino);
 	jbd_debug(4, "orphan inode %lu will point to %d\n",
 			inode->i_ino, NEXT_ORPHAN(inode));
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index ebbc663..a5efee3 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -459,16 +459,18 @@ static int set_flexbg_block_bitmap(struct super_block *sb, handle_t *handle,
 
 		BUFFER_TRACE(bh, "get_write_access");
 		err = ext4_journal_get_write_access(handle, bh);
-		if (err)
+		if (err) {
+			brelse(bh);
 			return err;
+		}
 		ext4_debug("mark block bitmap %#04llx (+%llu/%u)\n",
 			   first_cluster, first_cluster - start, count2);
 		ext4_set_bits(bh->b_data, first_cluster - start, count2);
 
 		err = ext4_handle_dirty_metadata(handle, NULL, bh);
+		brelse(bh);
 		if (unlikely(err))
 			return err;
-		brelse(bh);
 	}
 
 	return 0;
@@ -605,7 +607,6 @@ static int setup_new_flex_group_blocks(struct super_block *sb,
 		bh = bclean(handle, sb, block);
 		if (IS_ERR(bh)) {
 			err = PTR_ERR(bh);
-			bh = NULL;
 			goto out;
 		}
 		overhead = ext4_group_overhead_blocks(sb, group);
@@ -618,9 +619,9 @@ static int setup_new_flex_group_blocks(struct super_block *sb,
 		ext4_mark_bitmap_end(EXT4_B2C(sbi, group_data[i].blocks_count),
 				     sb->s_blocksize * 8, bh->b_data);
 		err = ext4_handle_dirty_metadata(handle, NULL, bh);
+		brelse(bh);
 		if (err)
 			goto out;
-		brelse(bh);
 
 handle_ib:
 		if (bg_flags[i] & EXT4_BG_INODE_UNINIT)
@@ -635,18 +636,16 @@ static int setup_new_flex_group_blocks(struct super_block *sb,
 		bh = bclean(handle, sb, block);
 		if (IS_ERR(bh)) {
 			err = PTR_ERR(bh);
-			bh = NULL;
 			goto out;
 		}
 
 		ext4_mark_bitmap_end(EXT4_INODES_PER_GROUP(sb),
 				     sb->s_blocksize * 8, bh->b_data);
 		err = ext4_handle_dirty_metadata(handle, NULL, bh);
+		brelse(bh);
 		if (err)
 			goto out;
-		brelse(bh);
 	}
-	bh = NULL;
 
 	/* Mark group tables in block bitmap */
 	for (j = 0; j < GROUP_TABLE_COUNT; j++) {
@@ -685,7 +684,6 @@ static int setup_new_flex_group_blocks(struct super_block *sb,
 	}
 
 out:
-	brelse(bh);
 	err2 = ext4_journal_stop(handle);
 	if (err2 && !err)
 		err = err2;
@@ -873,6 +871,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
 	err = ext4_handle_dirty_metadata(handle, NULL, gdb_bh);
 	if (unlikely(err)) {
 		ext4_std_error(sb, err);
+		iloc.bh = NULL;
 		goto exit_inode;
 	}
 	brelse(dind);
@@ -924,6 +923,7 @@ static int add_new_gdb_meta_bg(struct super_block *sb,
 				     sizeof(struct buffer_head *),
 				     GFP_NOFS);
 	if (!n_group_desc) {
+		brelse(gdb_bh);
 		err = -ENOMEM;
 		ext4_warning(sb, "not enough memory for %lu groups",
 			     gdb_num + 1);
@@ -939,8 +939,6 @@ static int add_new_gdb_meta_bg(struct super_block *sb,
 	kvfree(o_group_desc);
 	BUFFER_TRACE(gdb_bh, "get_write_access");
 	err = ext4_journal_get_write_access(handle, gdb_bh);
-	if (unlikely(err))
-		brelse(gdb_bh);
 	return err;
 }
 
@@ -1124,8 +1122,10 @@ static void update_backups(struct super_block *sb, sector_t blk_off, char *data,
 			   backup_block, backup_block -
 			   ext4_group_first_block_no(sb, group));
 		BUFFER_TRACE(bh, "get_write_access");
-		if ((err = ext4_journal_get_write_access(handle, bh)))
+		if ((err = ext4_journal_get_write_access(handle, bh))) {
+			brelse(bh);
 			break;
+		}
 		lock_buffer(bh);
 		memcpy(bh->b_data, data, size);
 		if (rest)
@@ -2023,7 +2023,7 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count)
 
 	err = ext4_alloc_flex_bg_array(sb, n_group + 1);
 	if (err)
-		return err;
+		goto out;
 
 	err = ext4_mb_alloc_groupinfo(sb, n_group + 1);
 	if (err)
@@ -2059,6 +2059,10 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count)
 		n_blocks_count_retry = 0;
 		free_flex_gd(flex_gd);
 		flex_gd = NULL;
+		if (resize_inode) {
+			iput(resize_inode);
+			resize_inode = NULL;
+		}
 		goto retry;
 	}
 
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index a221f1c..53ff6c2 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -4075,6 +4075,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->s_groups_count = blocks_count;
 	sbi->s_blockfile_groups = min_t(ext4_group_t, sbi->s_groups_count,
 			(EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb)));
+	if (((u64)sbi->s_groups_count * sbi->s_inodes_per_group) !=
+	    le32_to_cpu(es->s_inodes_count)) {
+		ext4_msg(sb, KERN_ERR, "inodes count not valid: %u vs %llu",
+			 le32_to_cpu(es->s_inodes_count),
+			 ((u64)sbi->s_groups_count * sbi->s_inodes_per_group));
+		ret = -EINVAL;
+		goto failed_mount;
+	}
 	db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) /
 		   EXT4_DESC_PER_BLOCK(sb);
 	if (ext4_has_feature_meta_bg(sb)) {
@@ -4094,14 +4102,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		ret = -ENOMEM;
 		goto failed_mount;
 	}
-	if (((u64)sbi->s_groups_count * sbi->s_inodes_per_group) !=
-	    le32_to_cpu(es->s_inodes_count)) {
-		ext4_msg(sb, KERN_ERR, "inodes count not valid: %u vs %llu",
-			 le32_to_cpu(es->s_inodes_count),
-			 ((u64)sbi->s_groups_count * sbi->s_inodes_per_group));
-		ret = -EINVAL;
-		goto failed_mount;
-	}
 
 	bgl_lock_init(sbi->s_blockgroup_lock);
 
@@ -4510,6 +4510,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	percpu_counter_destroy(&sbi->s_freeinodes_counter);
 	percpu_counter_destroy(&sbi->s_dirs_counter);
 	percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
+	percpu_free_rwsem(&sbi->s_journal_flag_rwsem);
 failed_mount5:
 	ext4_ext_release(sb);
 	ext4_release_system_zone(sb);
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index f36fc5d5..7643d52 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -1031,10 +1031,8 @@ static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode,
 	inode_lock(ea_inode);
 
 	ret = ext4_reserve_inode_write(handle, ea_inode, &iloc);
-	if (ret) {
-		iloc.bh = NULL;
+	if (ret)
 		goto out;
-	}
 
 	ref_count = ext4_xattr_inode_get_ref(ea_inode);
 	ref_count += ref_change;
@@ -1080,12 +1078,10 @@ static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode,
 	}
 
 	ret = ext4_mark_iloc_dirty(handle, ea_inode, &iloc);
-	iloc.bh = NULL;
 	if (ret)
 		ext4_warning_inode(ea_inode,
 				   "ext4_mark_iloc_dirty() failed ret=%d", ret);
 out:
-	brelse(iloc.bh);
 	inode_unlock(ea_inode);
 	return ret;
 }
@@ -1388,6 +1384,12 @@ static int ext4_xattr_inode_write(handle_t *handle, struct inode *ea_inode,
 		bh = ext4_getblk(handle, ea_inode, block, 0);
 		if (IS_ERR(bh))
 			return PTR_ERR(bh);
+		if (!bh) {
+			WARN_ON_ONCE(1);
+			EXT4_ERROR_INODE(ea_inode,
+					 "ext4_getblk() return bh = NULL");
+			return -EFSCORRUPTED;
+		}
 		ret = ext4_journal_get_write_access(handle, bh);
 		if (ret)
 			goto out;
@@ -2276,8 +2278,10 @@ static struct buffer_head *ext4_xattr_get_block(struct inode *inode)
 	if (!bh)
 		return ERR_PTR(-EIO);
 	error = ext4_xattr_check_block(inode, bh);
-	if (error)
+	if (error) {
+		brelse(bh);
 		return ERR_PTR(error);
+	}
 	return bh;
 }
 
@@ -2397,6 +2401,8 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
 			error = ext4_xattr_block_set(handle, inode, &i, &bs);
 		} else if (error == -ENOSPC) {
 			if (EXT4_I(inode)->i_file_acl && !bs.s.base) {
+				brelse(bs.bh);
+				bs.bh = NULL;
 				error = ext4_xattr_block_find(inode, &i, &bs);
 				if (error)
 					goto cleanup;
@@ -2617,6 +2623,8 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode,
 	kfree(buffer);
 	if (is)
 		brelse(is->iloc.bh);
+	if (bs)
+		brelse(bs->bh);
 	kfree(is);
 	kfree(bs);
 
@@ -2696,7 +2704,6 @@ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
 			       struct ext4_inode *raw_inode, handle_t *handle)
 {
 	struct ext4_xattr_ibody_header *header;
-	struct buffer_head *bh;
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	static unsigned int mnt_count;
 	size_t min_offs;
@@ -2737,13 +2744,17 @@ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
 	 * EA block can hold new_extra_isize bytes.
 	 */
 	if (EXT4_I(inode)->i_file_acl) {
+		struct buffer_head *bh;
+
 		bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
 		error = -EIO;
 		if (!bh)
 			goto cleanup;
 		error = ext4_xattr_check_block(inode, bh);
-		if (error)
+		if (error) {
+			brelse(bh);
 			goto cleanup;
+		}
 		base = BHDR(bh);
 		end = bh->b_data + bh->b_size;
 		min_offs = end - base;
diff --git a/fs/namespace.c b/fs/namespace.c
index 98d27da..74f6429 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1540,8 +1540,13 @@ static int do_umount(struct mount *mnt, int flags)
 
 	namespace_lock();
 	lock_mount_hash();
-	event++;
 
+	/* Recheck MNT_LOCKED with the locks held */
+	retval = -EINVAL;
+	if (mnt->mnt.mnt_flags & MNT_LOCKED)
+		goto out;
+
+	event++;
 	if (flags & MNT_DETACH) {
 		if (!list_empty(&mnt->mnt_list))
 			umount_tree(mnt, UMOUNT_PROPAGATE);
@@ -1555,6 +1560,7 @@ static int do_umount(struct mount *mnt, int flags)
 			retval = 0;
 		}
 	}
+out:
 	unlock_mount_hash();
 	namespace_unlock();
 	return retval;
@@ -1645,7 +1651,7 @@ int ksys_umount(char __user *name, int flags)
 		goto dput_and_out;
 	if (!check_mnt(mnt))
 		goto dput_and_out;
-	if (mnt->mnt.mnt_flags & MNT_LOCKED)
+	if (mnt->mnt.mnt_flags & MNT_LOCKED) /* Check optimistically */
 		goto dput_and_out;
 	retval = -EPERM;
 	if (flags & MNT_FORCE && !capable(CAP_SYS_ADMIN))
@@ -1728,8 +1734,14 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry,
 		for (s = r; s; s = next_mnt(s, r)) {
 			if (!(flag & CL_COPY_UNBINDABLE) &&
 			    IS_MNT_UNBINDABLE(s)) {
-				s = skip_mnt_tree(s);
-				continue;
+				if (s->mnt.mnt_flags & MNT_LOCKED) {
+					/* Both unbindable and locked. */
+					q = ERR_PTR(-EPERM);
+					goto out;
+				} else {
+					s = skip_mnt_tree(s);
+					continue;
+				}
 			}
 			if (!(flag & CL_COPY_MNT_NS_FILE) &&
 			    is_mnt_ns_file(s->mnt.mnt_root)) {
@@ -1782,7 +1794,7 @@ void drop_collected_mounts(struct vfsmount *mnt)
 {
 	namespace_lock();
 	lock_mount_hash();
-	umount_tree(real_mount(mnt), UMOUNT_SYNC);
+	umount_tree(real_mount(mnt), 0);
 	unlock_mount_hash();
 	namespace_unlock();
 }
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index 6fc5425..2652d00 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -243,7 +243,7 @@ xfs_attr3_leaf_verify(
 	struct xfs_mount		*mp = bp->b_target->bt_mount;
 	struct xfs_attr_leafblock	*leaf = bp->b_addr;
 	struct xfs_attr_leaf_entry	*entries;
-	uint16_t			end;
+	uint32_t			end;	/* must be 32bit - see below */
 	int				i;
 
 	xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &ichdr, leaf);
@@ -293,6 +293,11 @@ xfs_attr3_leaf_verify(
 	/*
 	 * Quickly check the freemap information.  Attribute data has to be
 	 * aligned to 4-byte boundaries, and likewise for the free space.
+	 *
+	 * Note that for 64k block size filesystems, the freemap entries cannot
+	 * overflow as they are only be16 fields. However, when checking end
+	 * pointer of the freemap, we have to be careful to detect overflows and
+	 * so use uint32_t for those checks.
 	 */
 	for (i = 0; i < XFS_ATTR_LEAF_MAPSIZE; i++) {
 		if (ichdr.freemap[i].base > mp->m_attr_geo->blksize)
@@ -303,7 +308,9 @@ xfs_attr3_leaf_verify(
 			return __this_address;
 		if (ichdr.freemap[i].size & 0x3)
 			return __this_address;
-		end = ichdr.freemap[i].base + ichdr.freemap[i].size;
+
+		/* be care of 16 bit overflows here */
+		end = (uint32_t)ichdr.freemap[i].base + ichdr.freemap[i].size;
 		if (end < ichdr.freemap[i].base)
 			return __this_address;
 		if (end > mp->m_attr_geo->blksize)
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 6e2c08f..6ecdbb3 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -1608,7 +1608,7 @@ xfs_ioc_getbmap(
 	error = 0;
 out_free_buf:
 	kmem_free(buf);
-	return 0;
+	return error;
 }
 
 struct getfsmap_info {
diff --git a/fs/xfs/xfs_message.c b/fs/xfs/xfs_message.c
index 576c375..6b736ea 100644
--- a/fs/xfs/xfs_message.c
+++ b/fs/xfs/xfs_message.c
@@ -107,5 +107,5 @@ assfail(char *expr, char *file, int line)
 void
 xfs_hex_dump(void *p, int length)
 {
-	print_hex_dump(KERN_ALERT, "", DUMP_PREFIX_ADDRESS, 16, 1, p, length, 1);
+	print_hex_dump(KERN_ALERT, "", DUMP_PREFIX_OFFSET, 16, 1, p, length, 1);
 }
diff --git a/include/asm-generic/4level-fixup.h b/include/asm-generic/4level-fixup.h
index 89f3b03..e3667c9 100644
--- a/include/asm-generic/4level-fixup.h
+++ b/include/asm-generic/4level-fixup.h
@@ -3,7 +3,7 @@
 #define _4LEVEL_FIXUP_H
 
 #define __ARCH_HAS_4LEVEL_HACK
-#define __PAGETABLE_PUD_FOLDED
+#define __PAGETABLE_PUD_FOLDED 1
 
 #define PUD_SHIFT			PGDIR_SHIFT
 #define PUD_SIZE			PGDIR_SIZE
diff --git a/include/asm-generic/5level-fixup.h b/include/asm-generic/5level-fixup.h
index 9c2e070..73474bb 100644
--- a/include/asm-generic/5level-fixup.h
+++ b/include/asm-generic/5level-fixup.h
@@ -3,7 +3,7 @@
 #define _5LEVEL_FIXUP_H
 
 #define __ARCH_HAS_5LEVEL_HACK
-#define __PAGETABLE_P4D_FOLDED
+#define __PAGETABLE_P4D_FOLDED 1
 
 #define P4D_SHIFT			PGDIR_SHIFT
 #define P4D_SIZE			PGDIR_SIZE
diff --git a/include/asm-generic/pgtable-nop4d-hack.h b/include/asm-generic/pgtable-nop4d-hack.h
index 0c34215..1d6dd38 100644
--- a/include/asm-generic/pgtable-nop4d-hack.h
+++ b/include/asm-generic/pgtable-nop4d-hack.h
@@ -5,7 +5,7 @@
 #ifndef __ASSEMBLY__
 #include <asm-generic/5level-fixup.h>
 
-#define __PAGETABLE_PUD_FOLDED
+#define __PAGETABLE_PUD_FOLDED 1
 
 /*
  * Having the pud type consist of a pgd gets the size right, and allows
diff --git a/include/asm-generic/pgtable-nop4d.h b/include/asm-generic/pgtable-nop4d.h
index 1a29b2a..04cb913 100644
--- a/include/asm-generic/pgtable-nop4d.h
+++ b/include/asm-generic/pgtable-nop4d.h
@@ -4,7 +4,7 @@
 
 #ifndef __ASSEMBLY__
 
-#define __PAGETABLE_P4D_FOLDED
+#define __PAGETABLE_P4D_FOLDED 1
 
 typedef struct { pgd_t pgd; } p4d_t;
 
diff --git a/include/asm-generic/pgtable-nopmd.h b/include/asm-generic/pgtable-nopmd.h
index f35f6e8..b85b827 100644
--- a/include/asm-generic/pgtable-nopmd.h
+++ b/include/asm-generic/pgtable-nopmd.h
@@ -8,7 +8,7 @@
 
 struct mm_struct;
 
-#define __PAGETABLE_PMD_FOLDED
+#define __PAGETABLE_PMD_FOLDED 1
 
 /*
  * Having the pmd type consist of a pud gets the size right, and allows
diff --git a/include/asm-generic/pgtable-nopud.h b/include/asm-generic/pgtable-nopud.h
index e950b9c..9bef475 100644
--- a/include/asm-generic/pgtable-nopud.h
+++ b/include/asm-generic/pgtable-nopud.h
@@ -9,7 +9,7 @@
 #else
 #include <asm-generic/pgtable-nop4d.h>
 
-#define __PAGETABLE_PUD_FOLDED
+#define __PAGETABLE_PUD_FOLDED 1
 
 /*
  * Having the pud type consist of a p4d gets the size right, and allows
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 5657a20..359fb93 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -1127,4 +1127,20 @@ static inline bool arch_has_pfn_modify_check(void)
 #endif
 #endif
 
+/*
+ * On some architectures it depends on the mm if the p4d/pud or pmd
+ * layer of the page table hierarchy is folded or not.
+ */
+#ifndef mm_p4d_folded
+#define mm_p4d_folded(mm)	__is_defined(__PAGETABLE_P4D_FOLDED)
+#endif
+
+#ifndef mm_pud_folded
+#define mm_pud_folded(mm)	__is_defined(__PAGETABLE_PUD_FOLDED)
+#endif
+
+#ifndef mm_pmd_folded
+#define mm_pmd_folded(mm)	__is_defined(__PAGETABLE_PMD_FOLDED)
+#endif
+
 #endif /* _ASM_GENERIC_PGTABLE_H */
diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h
index 6b92b33..65a38c4 100644
--- a/include/linux/ceph/ceph_features.h
+++ b/include/linux/ceph/ceph_features.h
@@ -213,12 +213,6 @@ DEFINE_CEPH_FEATURE_DEPRECATED(63, 1, RESERVED_BROKEN, LUMINOUS) // client-facin
 	 CEPH_FEATURE_NEW_OSDOPREPLY_ENCODING |	\
 	 CEPH_FEATURE_CEPHX_V2)
 
-#define CEPH_FEATURES_REQUIRED_DEFAULT   \
-	(CEPH_FEATURE_NOSRCADDR |	 \
-	 CEPH_FEATURE_SUBSCRIBE2 |	 \
-	 CEPH_FEATURE_RECONNECT_SEQ |	 \
-	 CEPH_FEATURE_PGID64 |		 \
-	 CEPH_FEATURE_PGPOOL3 |		 \
-	 CEPH_FEATURE_OSDENC)
+#define CEPH_FEATURES_REQUIRED_DEFAULT	0
 
 #endif
diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h
index 6b28c1b..f8c400b 100644
--- a/include/linux/compiler_attributes.h
+++ b/include/linux/compiler_attributes.h
@@ -4,22 +4,26 @@
 
 /*
  * The attributes in this file are unconditionally defined and they directly
- * map to compiler attribute(s) -- except those that are optional.
+ * map to compiler attribute(s), unless one of the compilers does not support
+ * the attribute. In that case, __has_attribute is used to check for support
+ * and the reason is stated in its comment ("Optional: ...").
  *
  * Any other "attributes" (i.e. those that depend on a configuration option,
  * on a compiler, on an architecture, on plugins, on other attributes...)
  * should be defined elsewhere (e.g. compiler_types.h or compiler-*.h).
+ * The intention is to keep this file as simple as possible, as well as
+ * compiler- and version-agnostic (e.g. avoiding GCC_VERSION checks).
  *
  * This file is meant to be sorted (by actual attribute name,
  * not by #define identifier). Use the __attribute__((__name__)) syntax
  * (i.e. with underscores) to avoid future collisions with other macros.
- * If an attribute is optional, state the reason in the comment.
+ * Provide links to the documentation of each supported compiler, if it exists.
  */
 
 /*
- * To check for optional attributes, we use __has_attribute, which is supported
- * on gcc >= 5, clang >= 2.9 and icc >= 17. In the meantime, to support
- * 4.6 <= gcc < 5, we implement __has_attribute by hand.
+ * __has_attribute is supported on gcc >= 5, clang >= 2.9 and icc >= 17.
+ * In the meantime, to support 4.6 <= gcc < 5, we implement __has_attribute
+ * by hand.
  *
  * sparse does not support __has_attribute (yet) and defines __GNUC_MINOR__
  * depending on the compiler used to build it; however, these attributes have
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index 3439d7d..4a3f9c0 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -130,6 +130,10 @@ struct ftrace_likely_data {
 # define randomized_struct_fields_end
 #endif
 
+#ifndef asm_volatile_goto
+#define asm_volatile_goto(x...) asm goto(x)
+#endif
+
 /* Are two types/vars the same type (ignoring qualifiers)? */
 #define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b))
 
diff --git a/include/linux/hid.h b/include/linux/hid.h
index 2827b87..387c70d 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -722,8 +722,8 @@ struct hid_usage_id {
  * input will not be passed to raw_event unless hid_device_io_start is
  * called.
  *
- * raw_event and event should return 0 on no action performed, 1 when no
- * further processing should be done and negative on error
+ * raw_event and event should return negative on error, any other value will
+ * pass the event on to .event() typically return 0 for success.
  *
  * input_mapping shall return a negative value to completely ignore this usage
  * (e.g. doubled or invalid usage), zero to continue with parsing of this
diff --git a/include/linux/i8253.h b/include/linux/i8253.h
index e6bb36a..8336b2f 100644
--- a/include/linux/i8253.h
+++ b/include/linux/i8253.h
@@ -21,6 +21,7 @@
 #define PIT_LATCH	((PIT_TICK_RATE + HZ/2) / HZ)
 
 extern raw_spinlock_t i8253_lock;
+extern bool i8253_clear_counter_on_shutdown;
 extern struct clock_event_device i8253_clockevent;
 extern void clockevent_i8253_init(bool oneshot);
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index fcf9cc9..5411de9 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1744,11 +1744,15 @@ int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address);
 
 static inline void mm_inc_nr_puds(struct mm_struct *mm)
 {
+	if (mm_pud_folded(mm))
+		return;
 	atomic_long_add(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes);
 }
 
 static inline void mm_dec_nr_puds(struct mm_struct *mm)
 {
+	if (mm_pud_folded(mm))
+		return;
 	atomic_long_sub(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes);
 }
 #endif
@@ -1768,11 +1772,15 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address);
 
 static inline void mm_inc_nr_pmds(struct mm_struct *mm)
 {
+	if (mm_pmd_folded(mm))
+		return;
 	atomic_long_add(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes);
 }
 
 static inline void mm_dec_nr_pmds(struct mm_struct *mm)
 {
+	if (mm_pmd_folded(mm))
+		return;
 	atomic_long_sub(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes);
 }
 #endif
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index abe975c8..7f53ece 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -324,9 +324,8 @@ static inline unsigned int nanddev_ntargets(const struct nand_device *nand)
  */
 static inline unsigned int nanddev_neraseblocks(const struct nand_device *nand)
 {
-	return (u64)nand->memorg.luns_per_target *
-	       nand->memorg.eraseblocks_per_lun *
-	       nand->memorg.pages_per_eraseblock;
+	return nand->memorg.ntargets * nand->memorg.luns_per_target *
+	       nand->memorg.eraseblocks_per_lun;
 }
 
 /**
@@ -569,7 +568,7 @@ static inline void nanddev_pos_next_eraseblock(struct nand_device *nand,
 }
 
 /**
- * nanddev_pos_next_eraseblock() - Move a position to the next page
+ * nanddev_pos_next_page() - Move a position to the next page
  * @nand: NAND device
  * @pos: the position to update
  *
diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index 08f9247..9003e29 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -119,6 +119,8 @@ static inline int hardlockup_detector_perf_init(void) { return 0; }
 void watchdog_nmi_stop(void);
 void watchdog_nmi_start(void);
 int watchdog_nmi_probe(void);
+int watchdog_nmi_enable(unsigned int cpu);
+void watchdog_nmi_disable(unsigned int cpu);
 
 /**
  * touch_nmi_watchdog - restart NMI watchdog timeout.
diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index f5ff8a7..b01eb50 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -83,11 +83,11 @@ struct kfd_ioctl_set_cu_mask_args {
 };
 
 struct kfd_ioctl_get_queue_wave_state_args {
-	uint64_t ctl_stack_address;	/* to KFD */
-	uint32_t ctl_stack_used_size;	/* from KFD */
-	uint32_t save_area_used_size;	/* from KFD */
-	uint32_t queue_id;		/* to KFD */
-	uint32_t pad;
+	__u64 ctl_stack_address;	/* to KFD */
+	__u32 ctl_stack_used_size;	/* from KFD */
+	__u32 save_area_used_size;	/* from KFD */
+	__u32 queue_id;			/* to KFD */
+	__u32 pad;
 };
 
 /* For kfd_ioctl_set_memory_policy_args.default_policy and alternate_policy */
@@ -255,10 +255,10 @@ struct kfd_hsa_memory_exception_data {
 
 /* hw exception data */
 struct kfd_hsa_hw_exception_data {
-	uint32_t reset_type;
-	uint32_t reset_cause;
-	uint32_t memory_lost;
-	uint32_t gpu_id;
+	__u32 reset_type;
+	__u32 reset_cause;
+	__u32 memory_lost;
+	__u32 gpu_id;
 };
 
 /* Event data */
diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h
index 18803ff..4969817 100644
--- a/include/xen/xen-ops.h
+++ b/include/xen/xen-ops.h
@@ -42,16 +42,12 @@ int xen_setup_shutdown_event(void);
 
 extern unsigned long *xen_contiguous_bitmap;
 
-#ifdef CONFIG_XEN_PV
+#if defined(CONFIG_XEN_PV) || defined(CONFIG_ARM) || defined(CONFIG_ARM64)
 int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order,
 				unsigned int address_bits,
 				dma_addr_t *dma_handle);
 
 void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order);
-
-int xen_remap_pfn(struct vm_area_struct *vma, unsigned long addr,
-		  xen_pfn_t *pfn, int nr, int *err_ptr, pgprot_t prot,
-		  unsigned int domid, bool no_translate, struct page **pages);
 #else
 static inline int xen_create_contiguous_region(phys_addr_t pstart,
 					       unsigned int order,
@@ -63,7 +59,13 @@ static inline int xen_create_contiguous_region(phys_addr_t pstart,
 
 static inline void xen_destroy_contiguous_region(phys_addr_t pstart,
 						 unsigned int order) { }
+#endif
 
+#if defined(CONFIG_XEN_PV)
+int xen_remap_pfn(struct vm_area_struct *vma, unsigned long addr,
+		  xen_pfn_t *pfn, int nr, int *err_ptr, pgprot_t prot,
+		  unsigned int domid, bool no_translate, struct page **pages);
+#else
 static inline int xen_remap_pfn(struct vm_area_struct *vma, unsigned long addr,
 				xen_pfn_t *pfn, int nr, int *err_ptr,
 				pgprot_t prot,  unsigned int domid,
diff --git a/kernel/resource.c b/kernel/resource.c
index b3a3a1f..b0fbf68 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -319,16 +319,23 @@ int release_resource(struct resource *old)
 EXPORT_SYMBOL(release_resource);
 
 /**
- * Finds the lowest iomem resource that covers part of [start..end].  The
- * caller must specify start, end, flags, and desc (which may be
+ * Finds the lowest iomem resource that covers part of [@start..@end].  The
+ * caller must specify @start, @end, @flags, and @desc (which may be
  * IORES_DESC_NONE).
  *
- * If a resource is found, returns 0 and *res is overwritten with the part
- * of the resource that's within [start..end]; if none is found, returns
- * -1.
+ * If a resource is found, returns 0 and @*res is overwritten with the part
+ * of the resource that's within [@start..@end]; if none is found, returns
+ * -1 or -EINVAL for other invalid parameters.
  *
  * This function walks the whole tree and not just first level children
  * unless @first_lvl is true.
+ *
+ * @start:	start address of the resource searched for
+ * @end:	end address of same resource
+ * @flags:	flags which the resource must have
+ * @desc:	descriptor the resource must have
+ * @first_lvl:	walk only the first level children, if set
+ * @res:	return ptr, if resource found
  */
 static int find_next_iomem_res(resource_size_t start, resource_size_t end,
 			       unsigned long flags, unsigned long desc,
@@ -399,6 +406,8 @@ static int __walk_iomem_res_desc(resource_size_t start, resource_size_t end,
  * @flags: I/O resource flags
  * @start: start addr
  * @end: end addr
+ * @arg: function argument for the callback @func
+ * @func: callback function that is called for each qualifying resource area
  *
  * NOTE: For a new descriptor search, define a new IORES_DESC in
  * <linux/ioport.h> and set it in 'desc' of a target resource entry.
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f12225f..091e089 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5851,11 +5851,14 @@ void __init sched_init_smp(void)
 	/*
 	 * There's no userspace yet to cause hotplug operations; hence all the
 	 * CPU masks are stable and all blatant races in the below code cannot
-	 * happen.
+	 * happen. The hotplug lock is nevertheless taken to satisfy lockdep,
+	 * but there won't be any contention on it.
 	 */
+	cpus_read_lock();
 	mutex_lock(&sched_domains_mutex);
 	sched_init_domains(cpu_active_mask);
 	mutex_unlock(&sched_domains_mutex);
+	cpus_read_unlock();
 
 	/* Move init over to a non-isolated CPU */
 	if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_FLAG_DOMAIN)) < 0)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index ee271bb..3648d03 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2400,8 +2400,8 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
 		local = 1;
 
 	/*
-	 * Retry task to preferred node migration periodically, in case it
-	 * case it previously failed, or the scheduler moved us.
+	 * Retry to migrate task to preferred node periodically, in case it
+	 * previously failed, or the scheduler moved us.
 	 */
 	if (time_after(jiffies, p->numa_migrate_retry)) {
 		task_numa_placement(p);
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index ce32cf7..8f0644a 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -917,9 +917,6 @@ static void check_process_timers(struct task_struct *tsk,
 	struct task_cputime cputime;
 	unsigned long soft;
 
-	if (dl_task(tsk))
-		check_dl_overrun(tsk);
-
 	/*
 	 * If cputimer is not running, then there are no active
 	 * process wide timers (POSIX 1.b, itimers, RLIMIT_CPU).
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index e5222b5..923414a 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -974,10 +974,6 @@ static ssize_t map_write(struct file *file, const char __user *buf,
 	if (!new_idmap_permitted(file, ns, cap_setid, &new_map))
 		goto out;
 
-	ret = sort_idmaps(&new_map);
-	if (ret < 0)
-		goto out;
-
 	ret = -EPERM;
 	/* Map the lower ids from the parent user namespace to the
 	 * kernel global id space.
@@ -1004,6 +1000,14 @@ static ssize_t map_write(struct file *file, const char __user *buf,
 		e->lower_first = lower_first;
 	}
 
+	/*
+	 * If we want to use binary search for lookup, this clones the extent
+	 * array and sorts both copies.
+	 */
+	ret = sort_idmaps(&new_map);
+	if (ret < 0)
+		goto out;
+
 	/* Install the map */
 	if (new_map.nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) {
 		memcpy(map->extent, new_map.extent,
diff --git a/lib/raid6/test/Makefile b/lib/raid6/test/Makefile
index 5d73f5c..7977764 100644
--- a/lib/raid6/test/Makefile
+++ b/lib/raid6/test/Makefile
@@ -27,7 +27,7 @@
         CFLAGS += -I../../../arch/arm/include -mfpu=neon
         HAS_NEON = yes
 endif
-ifeq ($(ARCH),arm64)
+ifeq ($(ARCH),aarch64)
         CFLAGS += -I../../../arch/arm64/include
         HAS_NEON = yes
 endif
@@ -41,7 +41,7 @@
 		    gcc -c -x assembler - >&/dev/null &&        \
 		    rm ./-.o && echo -DCONFIG_AS_AVX512=1)
 else ifeq ($(HAS_NEON),yes)
-        OBJS   += neon.o neon1.o neon2.o neon4.o neon8.o
+        OBJS   += neon.o neon1.o neon2.o neon4.o neon8.o recov_neon.o recov_neon_inner.o
         CFLAGS += -DCONFIG_KERNEL_MODE_NEON=1
 else
         HAS_ALTIVEC := $(shell printf '\#include <altivec.h>\nvector int a;\n' |\
diff --git a/scripts/kconfig/merge_config.sh b/scripts/kconfig/merge_config.sh
index da66e77..0ef9064 100755
--- a/scripts/kconfig/merge_config.sh
+++ b/scripts/kconfig/merge_config.sh
@@ -102,7 +102,8 @@
 fi
 
 MERGE_LIST=$*
-SED_CONFIG_EXP="s/^\(# \)\{0,1\}\(${CONFIG_PREFIX}[a-zA-Z0-9_]*\)[= ].*/\2/p"
+SED_CONFIG_EXP1="s/^\(${CONFIG_PREFIX}[a-zA-Z0-9_]*\)=.*/\1/p"
+SED_CONFIG_EXP2="s/^# \(${CONFIG_PREFIX}[a-zA-Z0-9_]*\) is not set$/\1/p"
 
 TMP_FILE=$(mktemp ./.tmp.config.XXXXXXXXXX)
 
@@ -116,7 +117,7 @@
 		echo "The merge file '$MERGE_FILE' does not exist.  Exit." >&2
 		exit 1
 	fi
-	CFG_LIST=$(sed -n "$SED_CONFIG_EXP" $MERGE_FILE)
+	CFG_LIST=$(sed -n -e "$SED_CONFIG_EXP1" -e "$SED_CONFIG_EXP2" $MERGE_FILE)
 
 	for CFG in $CFG_LIST ; do
 		grep -q -w $CFG $TMP_FILE || continue
@@ -159,7 +160,7 @@
 
 
 # Check all specified config values took (might have missed-dependency issues)
-for CFG in $(sed -n "$SED_CONFIG_EXP" $TMP_FILE); do
+for CFG in $(sed -n -e "$SED_CONFIG_EXP1" -e "$SED_CONFIG_EXP2" $TMP_FILE); do
 
 	REQUESTED_VAL=$(grep -w -e "$CFG" $TMP_FILE)
 	ACTUAL_VAL=$(grep -w -e "$CFG" "$KCONFIG_CONFIG")
diff --git a/scripts/package/builddeb b/scripts/package/builddeb
index 90c9a8a..f43a274 100755
--- a/scripts/package/builddeb
+++ b/scripts/package/builddeb
@@ -81,11 +81,11 @@
 	cp System.map "$tmpdir/boot/System.map-$version"
 	cp $KCONFIG_CONFIG "$tmpdir/boot/config-$version"
 fi
-cp "$($MAKE -s image_name)" "$tmpdir/$installed_image_path"
+cp "$($MAKE -s -f $srctree/Makefile image_name)" "$tmpdir/$installed_image_path"
 
-if grep -q "^CONFIG_OF=y" $KCONFIG_CONFIG ; then
+if grep -q "^CONFIG_OF_EARLY_FLATTREE=y" $KCONFIG_CONFIG ; then
 	# Only some architectures with OF support have this target
-	if grep -q dtbs_install "${srctree}/arch/$SRCARCH/Makefile"; then
+	if [ -d "${srctree}/arch/$SRCARCH/boot/dts" ]; then
 		$MAKE KBUILD_SRC= INSTALL_DTBS_PATH="$tmpdir/usr/lib/$packagename" dtbs_install
 	fi
 fi
diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian
index 663a7f3..edcad61 100755
--- a/scripts/package/mkdebian
+++ b/scripts/package/mkdebian
@@ -88,6 +88,7 @@
 version=$KERNELRELEASE
 if [ -n "$KDEB_PKGVERSION" ]; then
 	packageversion=$KDEB_PKGVERSION
+	revision=${packageversion##*-}
 else
 	revision=$(cat .version 2>/dev/null||echo 1)
 	packageversion=$version-$revision
@@ -205,10 +206,12 @@
 #!$(command -v $MAKE) -f
 
 build:
-	\$(MAKE) KERNELRELEASE=${version} ARCH=${ARCH} KBUILD_SRC=
+	\$(MAKE) KERNELRELEASE=${version} ARCH=${ARCH} \
+	KBUILD_BUILD_VERSION=${revision} KBUILD_SRC=
 
 binary-arch:
-	\$(MAKE) KERNELRELEASE=${version} ARCH=${ARCH} KBUILD_SRC= intdeb-pkg
+	\$(MAKE) KERNELRELEASE=${version} ARCH=${ARCH} \
+	KBUILD_BUILD_VERSION=${revision} KBUILD_SRC= intdeb-pkg
 
 clean:
 	rm -rf debian/*tmp debian/files
diff --git a/scripts/package/mkspec b/scripts/package/mkspec
index e05646d..009147d 100755
--- a/scripts/package/mkspec
+++ b/scripts/package/mkspec
@@ -12,6 +12,7 @@
 # how we were called determines which rpms we build and how we build them
 if [ "$1" = prebuilt ]; then
 	S=DEL
+	MAKE="$MAKE -f $srctree/Makefile"
 else
 	S=
 fi
@@ -78,19 +79,19 @@
 $S	%setup -q
 $S
 $S	%build
-$S	make %{?_smp_mflags} KBUILD_BUILD_VERSION=%{release}
+$S	$MAKE %{?_smp_mflags} KBUILD_BUILD_VERSION=%{release}
 $S
 	%install
 	mkdir -p %{buildroot}/boot
 	%ifarch ia64
 	mkdir -p %{buildroot}/boot/efi
-	cp \$(make image_name) %{buildroot}/boot/efi/vmlinuz-$KERNELRELEASE
+	cp \$($MAKE image_name) %{buildroot}/boot/efi/vmlinuz-$KERNELRELEASE
 	ln -s efi/vmlinuz-$KERNELRELEASE %{buildroot}/boot/
 	%else
-	cp \$(make image_name) %{buildroot}/boot/vmlinuz-$KERNELRELEASE
+	cp \$($MAKE image_name) %{buildroot}/boot/vmlinuz-$KERNELRELEASE
 	%endif
-$M	make %{?_smp_mflags} INSTALL_MOD_PATH=%{buildroot} KBUILD_SRC= modules_install
-	make %{?_smp_mflags} INSTALL_HDR_PATH=%{buildroot}/usr KBUILD_SRC= headers_install
+$M	$MAKE %{?_smp_mflags} INSTALL_MOD_PATH=%{buildroot} modules_install
+	$MAKE %{?_smp_mflags} INSTALL_HDR_PATH=%{buildroot}/usr headers_install
 	cp System.map %{buildroot}/boot/System.map-$KERNELRELEASE
 	cp .config %{buildroot}/boot/config-$KERNELRELEASE
 	bzip2 -9 --keep vmlinux
diff --git a/scripts/setlocalversion b/scripts/setlocalversion
index 79f7dd5..71f3941 100755
--- a/scripts/setlocalversion
+++ b/scripts/setlocalversion
@@ -74,7 +74,7 @@
 		fi
 
 		# Check for uncommitted changes
-		if git status -uno --porcelain | grep -qv '^.. scripts/package'; then
+		if git diff-index --name-only HEAD | grep -qv "^scripts/package"; then
 			printf '%s' -dirty
 		fi
 
diff --git a/sound/pci/hda/thinkpad_helper.c b/sound/pci/hda/thinkpad_helper.c
index 97f49b7..568575b 100644
--- a/sound/pci/hda/thinkpad_helper.c
+++ b/sound/pci/hda/thinkpad_helper.c
@@ -58,8 +58,8 @@ static void hda_fixup_thinkpad_acpi(struct hda_codec *codec,
 			removefunc = false;
 		}
 		if (led_set_func(TPACPI_LED_MICMUTE, false) >= 0 &&
-		    snd_hda_gen_add_micmute_led(codec,
-						update_tpacpi_micmute) > 0)
+		    !snd_hda_gen_add_micmute_led(codec,
+						 update_tpacpi_micmute))
 			removefunc = false;
 	}
 
diff --git a/tools/arch/arm64/include/asm/barrier.h b/tools/arch/arm64/include/asm/barrier.h
index 12835ea..378c051 100644
--- a/tools/arch/arm64/include/asm/barrier.h
+++ b/tools/arch/arm64/include/asm/barrier.h
@@ -14,74 +14,75 @@
 #define wmb()		asm volatile("dmb ishst" ::: "memory")
 #define rmb()		asm volatile("dmb ishld" ::: "memory")
 
-#define smp_store_release(p, v)					\
-do {								\
-	union { typeof(*p) __val; char __c[1]; } __u =		\
-		{ .__val = (__force typeof(*p)) (v) }; 		\
-								\
-	switch (sizeof(*p)) {					\
-	case 1:							\
-		asm volatile ("stlrb %w1, %0"			\
-				: "=Q" (*p)			\
-				: "r" (*(__u8 *)__u.__c)	\
-				: "memory");			\
-		break;						\
-	case 2:							\
-		asm volatile ("stlrh %w1, %0"			\
-				: "=Q" (*p)			\
-				: "r" (*(__u16 *)__u.__c)	\
-				: "memory");			\
-		break;						\
-	case 4:							\
-		asm volatile ("stlr %w1, %0"			\
-				: "=Q" (*p)			\
-				: "r" (*(__u32 *)__u.__c)	\
-				: "memory");			\
-		break;						\
-	case 8:							\
-		asm volatile ("stlr %1, %0"			\
-				: "=Q" (*p)			\
-				: "r" (*(__u64 *)__u.__c)	\
-				: "memory");			\
-		break;						\
-	default:						\
-		/* Only to shut up gcc ... */			\
-		mb();						\
-		break;						\
-	}							\
+#define smp_store_release(p, v)						\
+do {									\
+	union { typeof(*p) __val; char __c[1]; } __u =			\
+		{ .__val = (v) }; 					\
+									\
+	switch (sizeof(*p)) {						\
+	case 1:								\
+		asm volatile ("stlrb %w1, %0"				\
+				: "=Q" (*p)				\
+				: "r" (*(__u8_alias_t *)__u.__c)	\
+				: "memory");				\
+		break;							\
+	case 2:								\
+		asm volatile ("stlrh %w1, %0"				\
+				: "=Q" (*p)				\
+				: "r" (*(__u16_alias_t *)__u.__c)	\
+				: "memory");				\
+		break;							\
+	case 4:								\
+		asm volatile ("stlr %w1, %0"				\
+				: "=Q" (*p)				\
+				: "r" (*(__u32_alias_t *)__u.__c)	\
+				: "memory");				\
+		break;							\
+	case 8:								\
+		asm volatile ("stlr %1, %0"				\
+				: "=Q" (*p)				\
+				: "r" (*(__u64_alias_t *)__u.__c)	\
+				: "memory");				\
+		break;							\
+	default:							\
+		/* Only to shut up gcc ... */				\
+		mb();							\
+		break;							\
+	}								\
 } while (0)
 
-#define smp_load_acquire(p)					\
-({								\
-	union { typeof(*p) __val; char __c[1]; } __u;		\
-								\
-	switch (sizeof(*p)) {					\
-	case 1:							\
-		asm volatile ("ldarb %w0, %1"			\
-			: "=r" (*(__u8 *)__u.__c)		\
-			: "Q" (*p) : "memory");			\
-		break;						\
-	case 2:							\
-		asm volatile ("ldarh %w0, %1"			\
-			: "=r" (*(__u16 *)__u.__c)		\
-			: "Q" (*p) : "memory");			\
-		break;						\
-	case 4:							\
-		asm volatile ("ldar %w0, %1"			\
-			: "=r" (*(__u32 *)__u.__c)		\
-			: "Q" (*p) : "memory");			\
-		break;						\
-	case 8:							\
-		asm volatile ("ldar %0, %1"			\
-			: "=r" (*(__u64 *)__u.__c)		\
-			: "Q" (*p) : "memory");			\
-		break;						\
-	default:						\
-		/* Only to shut up gcc ... */			\
-		mb();						\
-		break;						\
-	}							\
-	__u.__val;						\
+#define smp_load_acquire(p)						\
+({									\
+	union { typeof(*p) __val; char __c[1]; } __u =			\
+		{ .__c = { 0 } };					\
+									\
+	switch (sizeof(*p)) {						\
+	case 1:								\
+		asm volatile ("ldarb %w0, %1"				\
+			: "=r" (*(__u8_alias_t *)__u.__c)		\
+			: "Q" (*p) : "memory");				\
+		break;							\
+	case 2:								\
+		asm volatile ("ldarh %w0, %1"				\
+			: "=r" (*(__u16_alias_t *)__u.__c)		\
+			: "Q" (*p) : "memory");				\
+		break;							\
+	case 4:								\
+		asm volatile ("ldar %w0, %1"				\
+			: "=r" (*(__u32_alias_t *)__u.__c)		\
+			: "Q" (*p) : "memory");				\
+		break;							\
+	case 8:								\
+		asm volatile ("ldar %0, %1"				\
+			: "=r" (*(__u64_alias_t *)__u.__c)		\
+			: "Q" (*p) : "memory");				\
+		break;							\
+	default:							\
+		/* Only to shut up gcc ... */				\
+		mb();							\
+		break;							\
+	}								\
+	__u.__val;							\
 })
 
 #endif /* _TOOLS_LINUX_ASM_AARCH64_BARRIER_H */
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index 236b9b97..667c14e 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -55,7 +55,6 @@
  S - read sample value (PERF_SAMPLE_READ)
  D - pin the event to the PMU
  W - group is weak and will fallback to non-group if not schedulable,
-     only supported in 'perf stat' for now.
 
 The 'p' modifier can be used for specifying how precise the instruction
 address should be. The 'p' modifier can be specified multiple times:
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 3ccb4f0..d956554 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -387,7 +387,7 @@
 
 linux_uapi_dir := $(srctree)/tools/include/uapi/linux
 asm_generic_uapi_dir := $(srctree)/tools/include/uapi/asm-generic
-arch_asm_uapi_dir := $(srctree)/tools/arch/$(ARCH)/include/uapi/asm/
+arch_asm_uapi_dir := $(srctree)/tools/arch/$(SRCARCH)/include/uapi/asm/
 
 beauty_outdir := $(OUTPUT)trace/beauty/generated
 beauty_ioctl_outdir := $(beauty_outdir)/ioctl
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 10cf889..488779b 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -391,7 +391,12 @@ static int record__open(struct record *rec)
 					ui__warning("%s\n", msg);
 				goto try_again;
 			}
-
+			if ((errno == EINVAL || errno == EBADF) &&
+			    pos->leader != pos &&
+			    pos->weak_group) {
+			        pos = perf_evlist__reset_weak_group(evlist, pos);
+				goto try_again;
+			}
 			rc = -errno;
 			perf_evsel__open_strerror(pos, &opts->target,
 						  errno, msg, sizeof(msg));
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index d1028d7..a635abf 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -383,32 +383,6 @@ static bool perf_evsel__should_store_id(struct perf_evsel *counter)
 	return STAT_RECORD || counter->attr.read_format & PERF_FORMAT_ID;
 }
 
-static struct perf_evsel *perf_evsel__reset_weak_group(struct perf_evsel *evsel)
-{
-	struct perf_evsel *c2, *leader;
-	bool is_open = true;
-
-	leader = evsel->leader;
-	pr_debug("Weak group for %s/%d failed\n",
-			leader->name, leader->nr_members);
-
-	/*
-	 * for_each_group_member doesn't work here because it doesn't
-	 * include the first entry.
-	 */
-	evlist__for_each_entry(evsel_list, c2) {
-		if (c2 == evsel)
-			is_open = false;
-		if (c2->leader == leader) {
-			if (is_open)
-				perf_evsel__close(c2);
-			c2->leader = c2;
-			c2->nr_members = 0;
-		}
-	}
-	return leader;
-}
-
 static bool is_target_alive(struct target *_target,
 			    struct thread_map *threads)
 {
@@ -477,7 +451,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 			if ((errno == EINVAL || errno == EBADF) &&
 			    counter->leader != counter &&
 			    counter->weak_group) {
-				counter = perf_evsel__reset_weak_group(counter);
+				counter = perf_evlist__reset_weak_group(evsel_list, counter);
 				goto try_again;
 			}
 
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index b2838de..aa0c73e 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1429,6 +1429,9 @@ int cmd_top(int argc, const char **argv)
 		}
 	}
 
+	if (opts->branch_stack && callchain_param.enabled)
+		symbol_conf.show_branchflag_count = true;
+
 	sort__mode = SORT_MODE__TOP;
 	/* display thread wants entries to be collapsed in a different tree */
 	perf_hpp_list.need_collapse = 1;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index dc8a6c4..8356194 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -108,6 +108,7 @@ struct trace {
 	} stats;
 	unsigned int		max_stack;
 	unsigned int		min_stack;
+	bool			raw_augmented_syscalls;
 	bool			not_ev_qualifier;
 	bool			live;
 	bool			full_time;
@@ -1724,13 +1725,28 @@ static int trace__fprintf_sample(struct trace *trace, struct perf_evsel *evsel,
 	return printed;
 }
 
-static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sample, int *augmented_args_size)
+static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sample, int *augmented_args_size, bool raw_augmented)
 {
 	void *augmented_args = NULL;
+	/*
+	 * For now with BPF raw_augmented we hook into raw_syscalls:sys_enter
+	 * and there we get all 6 syscall args plus the tracepoint common
+	 * fields (sizeof(long)) and the syscall_nr (another long). So we check
+	 * if that is the case and if so don't look after the sc->args_size,
+	 * but always after the full raw_syscalls:sys_enter payload, which is
+	 * fixed.
+	 *
+	 * We'll revisit this later to pass s->args_size to the BPF augmenter
+	 * (now tools/perf/examples/bpf/augmented_raw_syscalls.c, so that it
+	 * copies only what we need for each syscall, like what happens when we
+	 * use syscalls:sys_enter_NAME, so that we reduce the kernel/userspace
+	 * traffic to just what is needed for each syscall.
+	 */
+	int args_size = raw_augmented ? (8 * (int)sizeof(long)) : sc->args_size;
 
-	*augmented_args_size = sample->raw_size - sc->args_size;
+	*augmented_args_size = sample->raw_size - args_size;
 	if (*augmented_args_size > 0)
-		augmented_args = sample->raw_data + sc->args_size;
+		augmented_args = sample->raw_data + args_size;
 
 	return augmented_args;
 }
@@ -1780,7 +1796,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 	 * here and avoid using augmented syscalls when the evsel is the raw_syscalls one.
 	 */
 	if (evsel != trace->syscalls.events.sys_enter)
-		augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size);
+		augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size, trace->raw_augmented_syscalls);
 	ttrace->entry_time = sample->time;
 	msg = ttrace->entry_str;
 	printed += scnprintf(msg + printed, trace__entry_str_size - printed, "%s(", sc->name);
@@ -1833,7 +1849,7 @@ static int trace__fprintf_sys_enter(struct trace *trace, struct perf_evsel *evse
 		goto out_put;
 
 	args = perf_evsel__sc_tp_ptr(evsel, args, sample);
-	augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size);
+	augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size, trace->raw_augmented_syscalls);
 	syscall__scnprintf_args(sc, msg, sizeof(msg), args, augmented_args, augmented_args_size, trace, thread);
 	fprintf(trace->output, "%s", msg);
 	err = 0;
@@ -3501,7 +3517,15 @@ int cmd_trace(int argc, const char **argv)
 		evsel->handler = trace__sys_enter;
 
 		evlist__for_each_entry(trace.evlist, evsel) {
+			bool raw_syscalls_sys_exit = strcmp(perf_evsel__name(evsel), "raw_syscalls:sys_exit") == 0;
+
+			if (raw_syscalls_sys_exit) {
+				trace.raw_augmented_syscalls = true;
+				goto init_augmented_syscall_tp;
+			}
+
 			if (strstarts(perf_evsel__name(evsel), "syscalls:sys_exit_")) {
+init_augmented_syscall_tp:
 				perf_evsel__init_augmented_syscall_tp(evsel);
 				perf_evsel__init_augmented_syscall_tp_ret(evsel);
 				evsel->handler = trace__sys_exit;
diff --git a/tools/perf/examples/bpf/augmented_raw_syscalls.c b/tools/perf/examples/bpf/augmented_raw_syscalls.c
new file mode 100644
index 0000000..90a1933
--- /dev/null
+++ b/tools/perf/examples/bpf/augmented_raw_syscalls.c
@@ -0,0 +1,131 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Augment the raw_syscalls tracepoints with the contents of the pointer arguments.
+ *
+ * Test it with:
+ *
+ * perf trace -e tools/perf/examples/bpf/augmented_raw_syscalls.c cat /etc/passwd > /dev/null
+ *
+ * This exactly matches what is marshalled into the raw_syscall:sys_enter
+ * payload expected by the 'perf trace' beautifiers.
+ *
+ * For now it just uses the existing tracepoint augmentation code in 'perf
+ * trace', in the next csets we'll hook up these with the sys_enter/sys_exit
+ * code that will combine entry/exit in a strace like way.
+ */
+
+#include <stdio.h>
+#include <linux/socket.h>
+
+/* bpf-output associated map */
+struct bpf_map SEC("maps") __augmented_syscalls__ = {
+	.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
+	.key_size = sizeof(int),
+	.value_size = sizeof(u32),
+	.max_entries = __NR_CPUS__,
+};
+
+struct syscall_enter_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	unsigned long	   args[6];
+};
+
+struct syscall_exit_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	long		   ret;
+};
+
+struct augmented_filename {
+	unsigned int	size;
+	int		reserved;
+	char		value[256];
+};
+
+#define SYS_OPEN 2
+#define SYS_OPENAT 257
+
+SEC("raw_syscalls:sys_enter")
+int sys_enter(struct syscall_enter_args *args)
+{
+	struct {
+		struct syscall_enter_args args;
+		struct augmented_filename filename;
+	} augmented_args;
+	unsigned int len = sizeof(augmented_args);
+	const void *filename_arg = NULL;
+
+	probe_read(&augmented_args.args, sizeof(augmented_args.args), args);
+	/*
+	 * Yonghong and Edward Cree sayz:
+	 *
+	 * https://www.spinics.net/lists/netdev/msg531645.html
+	 *
+	 * >>   R0=inv(id=0) R1=inv2 R6=ctx(id=0,off=0,imm=0) R7=inv64 R10=fp0,call_-1
+	 * >> 10: (bf) r1 = r6
+	 * >> 11: (07) r1 += 16
+	 * >> 12: (05) goto pc+2
+	 * >> 15: (79) r3 = *(u64 *)(r1 +0)
+	 * >> dereference of modified ctx ptr R1 off=16 disallowed
+	 * > Aha, we at least got a different error message this time.
+	 * > And indeed llvm has done that optimisation, rather than the more obvious
+	 * > 11: r3 = *(u64 *)(r1 +16)
+	 * > because it wants to have lots of reads share a single insn.  You may be able
+	 * > to defeat that optimisation by adding compiler barriers, idk.  Maybe someone
+	 * > with llvm knowledge can figure out how to stop it (ideally, llvm would know
+	 * > when it's generating for bpf backend and not do that).  -O0?  ¯\_(ツ)_/¯
+	 *
+	 * The optimization mostly likes below:
+	 *
+	 *	br1:
+	 * 	...
+	 *	r1 += 16
+	 *	goto merge
+	 *	br2:
+	 *	...
+	 *	r1 += 20
+	 *	goto merge
+	 *	merge:
+	 *	*(u64 *)(r1 + 0)
+	 *
+	 * The compiler tries to merge common loads. There is no easy way to
+	 * stop this compiler optimization without turning off a lot of other
+	 * optimizations. The easiest way is to add barriers:
+	 *
+	 * 	 __asm__ __volatile__("": : :"memory")
+	 *
+	 * 	 after the ctx memory access to prevent their down stream merging.
+	 */
+	switch (augmented_args.args.syscall_nr) {
+	case SYS_OPEN:	 filename_arg = (const void *)args->args[0];
+			__asm__ __volatile__("": : :"memory");
+			 break;
+	case SYS_OPENAT: filename_arg = (const void *)args->args[1];
+			 break;
+	}
+
+	if (filename_arg != NULL) {
+		augmented_args.filename.reserved = 0;
+		augmented_args.filename.size = probe_read_str(&augmented_args.filename.value,
+							      sizeof(augmented_args.filename.value),
+							      filename_arg);
+		if (augmented_args.filename.size < sizeof(augmented_args.filename.value)) {
+			len -= sizeof(augmented_args.filename.value) - augmented_args.filename.size;
+			len &= sizeof(augmented_args.filename.value) - 1;
+		}
+	} else {
+		len = sizeof(augmented_args.args);
+	}
+
+	perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, &augmented_args, len);
+	return 0;
+}
+
+SEC("raw_syscalls:sys_exit")
+int sys_exit(struct syscall_exit_args *args)
+{
+	return 1; /* 0 as soon as we start copying data returned by the kernel, e.g. 'read' */
+}
+
+license(GPL);
diff --git a/tools/perf/jvmti/jvmti_agent.c b/tools/perf/jvmti/jvmti_agent.c
index ac1bcdc..f7eb63c 100644
--- a/tools/perf/jvmti/jvmti_agent.c
+++ b/tools/perf/jvmti/jvmti_agent.c
@@ -125,7 +125,7 @@ perf_get_timestamp(void)
 }
 
 static int
-debug_cache_init(void)
+create_jit_cache_dir(void)
 {
 	char str[32];
 	char *base, *p;
@@ -144,8 +144,13 @@ debug_cache_init(void)
 
 	strftime(str, sizeof(str), JIT_LANG"-jit-%Y%m%d", &tm);
 
-	snprintf(jit_path, PATH_MAX - 1, "%s/.debug/", base);
-
+	ret = snprintf(jit_path, PATH_MAX, "%s/.debug/", base);
+	if (ret >= PATH_MAX) {
+		warnx("jvmti: cannot generate jit cache dir because %s/.debug/"
+			" is too long, please check the cwd, JITDUMPDIR, and"
+			" HOME variables", base);
+		return -1;
+	}
 	ret = mkdir(jit_path, 0755);
 	if (ret == -1) {
 		if (errno != EEXIST) {
@@ -154,20 +159,32 @@ debug_cache_init(void)
 		}
 	}
 
-	snprintf(jit_path, PATH_MAX - 1, "%s/.debug/jit", base);
+	ret = snprintf(jit_path, PATH_MAX, "%s/.debug/jit", base);
+	if (ret >= PATH_MAX) {
+		warnx("jvmti: cannot generate jit cache dir because"
+			" %s/.debug/jit is too long, please check the cwd,"
+			" JITDUMPDIR, and HOME variables", base);
+		return -1;
+	}
 	ret = mkdir(jit_path, 0755);
 	if (ret == -1) {
 		if (errno != EEXIST) {
-			warn("cannot create jit cache dir %s", jit_path);
+			warn("jvmti: cannot create jit cache dir %s", jit_path);
 			return -1;
 		}
 	}
 
-	snprintf(jit_path, PATH_MAX - 1, "%s/.debug/jit/%s.XXXXXXXX", base, str);
-
+	ret = snprintf(jit_path, PATH_MAX, "%s/.debug/jit/%s.XXXXXXXX", base, str);
+	if (ret >= PATH_MAX) {
+		warnx("jvmti: cannot generate jit cache dir because"
+			" %s/.debug/jit/%s.XXXXXXXX is too long, please check"
+			" the cwd, JITDUMPDIR, and HOME variables",
+			base, str);
+		return -1;
+	}
 	p = mkdtemp(jit_path);
 	if (p != jit_path) {
-		warn("cannot create jit cache dir %s", jit_path);
+		warn("jvmti: cannot create jit cache dir %s", jit_path);
 		return -1;
 	}
 
@@ -228,7 +245,7 @@ void *jvmti_open(void)
 {
 	char dump_path[PATH_MAX];
 	struct jitheader header;
-	int fd;
+	int fd, ret;
 	FILE *fp;
 
 	init_arch_timestamp();
@@ -245,12 +262,22 @@ void *jvmti_open(void)
 
 	memset(&header, 0, sizeof(header));
 
-	debug_cache_init();
+	/*
+	 * jitdump file dir
+	 */
+	if (create_jit_cache_dir() < 0)
+		return NULL;
 
 	/*
 	 * jitdump file name
 	 */
-	scnprintf(dump_path, PATH_MAX, "%s/jit-%i.dump", jit_path, getpid());
+	ret = snprintf(dump_path, PATH_MAX, "%s/jit-%i.dump", jit_path, getpid());
+	if (ret >= PATH_MAX) {
+		warnx("jvmti: cannot generate jitdump file full path because"
+			" %s/jit-%i.dump is too long, please check the cwd,"
+			" JITDUMPDIR, and HOME variables", jit_path, getpid());
+		return NULL;
+	}
 
 	fd = open(dump_path, O_CREAT|O_TRUNC|O_RDWR, 0666);
 	if (fd == -1)
diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
index 24cb0bd..f278ce5 100755
--- a/tools/perf/scripts/python/exported-sql-viewer.py
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -119,6 +119,14 @@
 		return "[kernel]"
 	return name
 
+def findnth(s, sub, n, offs=0):
+	pos = s.find(sub)
+	if pos < 0:
+		return pos
+	if n <= 1:
+		return offs + pos
+	return findnth(s[pos + 1:], sub, n - 1, offs + pos + 1)
+
 # Percent to one decimal place
 
 def PercentToOneDP(n, d):
@@ -1464,6 +1472,317 @@
 		else:
 			self.find_bar.NotFound()
 
+# Dialog data item converted and validated using a SQL table
+
+class SQLTableDialogDataItem():
+
+	def __init__(self, glb, label, placeholder_text, table_name, match_column, column_name1, column_name2, parent):
+		self.glb = glb
+		self.label = label
+		self.placeholder_text = placeholder_text
+		self.table_name = table_name
+		self.match_column = match_column
+		self.column_name1 = column_name1
+		self.column_name2 = column_name2
+		self.parent = parent
+
+		self.value = ""
+
+		self.widget = QLineEdit()
+		self.widget.editingFinished.connect(self.Validate)
+		self.widget.textChanged.connect(self.Invalidate)
+		self.red = False
+		self.error = ""
+		self.validated = True
+
+		self.last_id = 0
+		self.first_time = 0
+		self.last_time = 2 ** 64
+		if self.table_name == "<timeranges>":
+			query = QSqlQuery(self.glb.db)
+			QueryExec(query, "SELECT id, time FROM samples ORDER BY id DESC LIMIT 1")
+			if query.next():
+				self.last_id = int(query.value(0))
+				self.last_time = int(query.value(1))
+			QueryExec(query, "SELECT time FROM samples WHERE time != 0 ORDER BY id LIMIT 1")
+			if query.next():
+				self.first_time = int(query.value(0))
+			if placeholder_text:
+				placeholder_text += ", between " + str(self.first_time) + " and " + str(self.last_time)
+
+		if placeholder_text:
+			self.widget.setPlaceholderText(placeholder_text)
+
+	def ValueToIds(self, value):
+		ids = []
+		query = QSqlQuery(self.glb.db)
+		stmt = "SELECT id FROM " + self.table_name + " WHERE " + self.match_column + " = '" + value + "'"
+		ret = query.exec_(stmt)
+		if ret:
+			while query.next():
+				ids.append(str(query.value(0)))
+		return ids
+
+	def IdBetween(self, query, lower_id, higher_id, order):
+		QueryExec(query, "SELECT id FROM samples WHERE id > " + str(lower_id) + " AND id < " + str(higher_id) + " ORDER BY id " + order + " LIMIT 1")
+		if query.next():
+			return True, int(query.value(0))
+		else:
+			return False, 0
+
+	def BinarySearchTime(self, lower_id, higher_id, target_time, get_floor):
+		query = QSqlQuery(self.glb.db)
+		while True:
+			next_id = int((lower_id + higher_id) / 2)
+			QueryExec(query, "SELECT time FROM samples WHERE id = " + str(next_id))
+			if not query.next():
+				ok, dbid = self.IdBetween(query, lower_id, next_id, "DESC")
+				if not ok:
+					ok, dbid = self.IdBetween(query, next_id, higher_id, "")
+					if not ok:
+						return str(higher_id)
+				next_id = dbid
+				QueryExec(query, "SELECT time FROM samples WHERE id = " + str(next_id))
+			next_time = int(query.value(0))
+			if get_floor:
+				if target_time > next_time:
+					lower_id = next_id
+				else:
+					higher_id = next_id
+				if higher_id <= lower_id + 1:
+					return str(higher_id)
+			else:
+				if target_time >= next_time:
+					lower_id = next_id
+				else:
+					higher_id = next_id
+				if higher_id <= lower_id + 1:
+					return str(lower_id)
+
+	def ConvertRelativeTime(self, val):
+		print "val ", val
+		mult = 1
+		suffix = val[-2:]
+		if suffix == "ms":
+			mult = 1000000
+		elif suffix == "us":
+			mult = 1000
+		elif suffix == "ns":
+			mult = 1
+		else:
+			return val
+		val = val[:-2].strip()
+		if not self.IsNumber(val):
+			return val
+		val = int(val) * mult
+		if val >= 0:
+			val += self.first_time
+		else:
+			val += self.last_time
+		return str(val)
+
+	def ConvertTimeRange(self, vrange):
+		print "vrange ", vrange
+		if vrange[0] == "":
+			vrange[0] = str(self.first_time)
+		if vrange[1] == "":
+			vrange[1] = str(self.last_time)
+		vrange[0] = self.ConvertRelativeTime(vrange[0])
+		vrange[1] = self.ConvertRelativeTime(vrange[1])
+		print "vrange2 ", vrange
+		if not self.IsNumber(vrange[0]) or not self.IsNumber(vrange[1]):
+			return False
+		print "ok1"
+		beg_range = max(int(vrange[0]), self.first_time)
+		end_range = min(int(vrange[1]), self.last_time)
+		if beg_range > self.last_time or end_range < self.first_time:
+			return False
+		print "ok2"
+		vrange[0] = self.BinarySearchTime(0, self.last_id, beg_range, True)
+		vrange[1] = self.BinarySearchTime(1, self.last_id + 1, end_range, False)
+		print "vrange3 ", vrange
+		return True
+
+	def AddTimeRange(self, value, ranges):
+		print "value ", value
+		n = value.count("-")
+		if n == 1:
+			pass
+		elif n == 2:
+			if value.split("-")[1].strip() == "":
+				n = 1
+		elif n == 3:
+			n = 2
+		else:
+			return False
+		pos = findnth(value, "-", n)
+		vrange = [value[:pos].strip() ,value[pos+1:].strip()]
+		if self.ConvertTimeRange(vrange):
+			ranges.append(vrange)
+			return True
+		return False
+
+	def InvalidValue(self, value):
+		self.value = ""
+		palette = QPalette()
+		palette.setColor(QPalette.Text,Qt.red)
+		self.widget.setPalette(palette)
+		self.red = True
+		self.error = self.label + " invalid value '" + value + "'"
+		self.parent.ShowMessage(self.error)
+
+	def IsNumber(self, value):
+		try:
+			x = int(value)
+		except:
+			x = 0
+		return str(x) == value
+
+	def Invalidate(self):
+		self.validated = False
+
+	def Validate(self):
+		input_string = self.widget.text()
+		self.validated = True
+		if self.red:
+			palette = QPalette()
+			self.widget.setPalette(palette)
+			self.red = False
+		if not len(input_string.strip()):
+			self.error = ""
+			self.value = ""
+			return
+		if self.table_name == "<timeranges>":
+			ranges = []
+			for value in [x.strip() for x in input_string.split(",")]:
+				if not self.AddTimeRange(value, ranges):
+					return self.InvalidValue(value)
+			ranges = [("(" + self.column_name1 + " >= " + r[0] + " AND " + self.column_name1 + " <= " + r[1] + ")") for r in ranges]
+			self.value = " OR ".join(ranges)
+		elif self.table_name == "<ranges>":
+			singles = []
+			ranges = []
+			for value in [x.strip() for x in input_string.split(",")]:
+				if "-" in value:
+					vrange = value.split("-")
+					if len(vrange) != 2 or not self.IsNumber(vrange[0]) or not self.IsNumber(vrange[1]):
+						return self.InvalidValue(value)
+					ranges.append(vrange)
+				else:
+					if not self.IsNumber(value):
+						return self.InvalidValue(value)
+					singles.append(value)
+			ranges = [("(" + self.column_name1 + " >= " + r[0] + " AND " + self.column_name1 + " <= " + r[1] + ")") for r in ranges]
+			if len(singles):
+				ranges.append(self.column_name1 + " IN (" + ",".join(singles) + ")")
+			self.value = " OR ".join(ranges)
+		elif self.table_name:
+			all_ids = []
+			for value in [x.strip() for x in input_string.split(",")]:
+				ids = self.ValueToIds(value)
+				if len(ids):
+					all_ids.extend(ids)
+				else:
+					return self.InvalidValue(value)
+			self.value = self.column_name1 + " IN (" + ",".join(all_ids) + ")"
+			if self.column_name2:
+				self.value = "( " + self.value + " OR " + self.column_name2 + " IN (" + ",".join(all_ids) + ") )"
+		else:
+			self.value = input_string.strip()
+		self.error = ""
+		self.parent.ClearMessage()
+
+	def IsValid(self):
+		if not self.validated:
+			self.Validate()
+		if len(self.error):
+			self.parent.ShowMessage(self.error)
+			return False
+		return True
+
+# Selected branch report creation dialog
+
+class SelectedBranchDialog(QDialog):
+
+	def __init__(self, glb, parent=None):
+		super(SelectedBranchDialog, self).__init__(parent)
+
+		self.glb = glb
+
+		self.name = ""
+		self.where_clause = ""
+
+		self.setWindowTitle("Selected Branches")
+		self.setMinimumWidth(600)
+
+		items = (
+			("Report name:", "Enter a name to appear in the window title bar", "", "", "", ""),
+			("Time ranges:", "Enter time ranges", "<timeranges>", "", "samples.id", ""),
+			("CPUs:", "Enter CPUs or ranges e.g. 0,5-6", "<ranges>", "", "cpu", ""),
+			("Commands:", "Only branches with these commands will be included", "comms", "comm", "comm_id", ""),
+			("PIDs:", "Only branches with these process IDs will be included", "threads", "pid", "thread_id", ""),
+			("TIDs:", "Only branches with these thread IDs will be included", "threads", "tid", "thread_id", ""),
+			("DSOs:", "Only branches with these DSOs will be included", "dsos", "short_name", "samples.dso_id", "to_dso_id"),
+			("Symbols:", "Only branches with these symbols will be included", "symbols", "name", "symbol_id", "to_symbol_id"),
+			("Raw SQL clause: ", "Enter a raw SQL WHERE clause", "", "", "", ""),
+			)
+		self.data_items = [SQLTableDialogDataItem(glb, *x, parent=self) for x in items]
+
+		self.grid = QGridLayout()
+
+		for row in xrange(len(self.data_items)):
+			self.grid.addWidget(QLabel(self.data_items[row].label), row, 0)
+			self.grid.addWidget(self.data_items[row].widget, row, 1)
+
+		self.status = QLabel()
+
+		self.ok_button = QPushButton("Ok", self)
+		self.ok_button.setDefault(True)
+		self.ok_button.released.connect(self.Ok)
+		self.ok_button.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed)
+
+		self.cancel_button = QPushButton("Cancel", self)
+		self.cancel_button.released.connect(self.reject)
+		self.cancel_button.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed)
+
+		self.hbox = QHBoxLayout()
+		#self.hbox.addStretch()
+		self.hbox.addWidget(self.status)
+		self.hbox.addWidget(self.ok_button)
+		self.hbox.addWidget(self.cancel_button)
+
+		self.vbox = QVBoxLayout()
+		self.vbox.addLayout(self.grid)
+		self.vbox.addLayout(self.hbox)
+
+		self.setLayout(self.vbox);
+
+	def Ok(self):
+		self.name = self.data_items[0].value
+		if not self.name:
+			self.ShowMessage("Report name is required")
+			return
+		for d in self.data_items:
+			if not d.IsValid():
+				return
+		for d in self.data_items[1:]:
+			if len(d.value):
+				if len(self.where_clause):
+					self.where_clause += " AND "
+				self.where_clause += d.value
+		if len(self.where_clause):
+			self.where_clause = " AND ( " + self.where_clause + " ) "
+		else:
+			self.ShowMessage("No selection")
+			return
+		self.accept()
+
+	def ShowMessage(self, msg):
+		self.status.setText("<font color=#FF0000>" + msg)
+
+	def ClearMessage(self):
+		self.status.setText("")
+
 # Event list
 
 def GetEventList(db):
@@ -1656,7 +1975,7 @@
 	def FindDone(self, row):
 		self.find_bar.Idle()
 		if row >= 0:
-			self.view.setCurrentIndex(self.model.index(row, 0, QModelIndex()))
+			self.view.setCurrentIndex(self.model.mapFromSource(self.data_model.index(row, 0, QModelIndex())))
 		else:
 			self.find_bar.NotFound()
 
@@ -1765,6 +2084,149 @@
 	def setActiveSubWindow(self, nr):
 		self.mdi_area.setActiveSubWindow(self.mdi_area.subWindowList()[nr - 1])
 
+# Help text
+
+glb_help_text = """
+<h1>Contents</h1>
+<style>
+p.c1 {
+    text-indent: 40px;
+}
+p.c2 {
+    text-indent: 80px;
+}
+}
+</style>
+<p class=c1><a href=#reports>1. Reports</a></p>
+<p class=c2><a href=#callgraph>1.1 Context-Sensitive Call Graph</a></p>
+<p class=c2><a href=#allbranches>1.2 All branches</a></p>
+<p class=c2><a href=#selectedbranches>1.3 Selected branches</a></p>
+<p class=c1><a href=#tables>2. Tables</a></p>
+<h1 id=reports>1. Reports</h1>
+<h2 id=callgraph>1.1 Context-Sensitive Call Graph</h2>
+The result is a GUI window with a tree representing a context-sensitive
+call-graph. Expanding a couple of levels of the tree and adjusting column
+widths to suit will display something like:
+<pre>
+                                         Call Graph: pt_example
+Call Path                          Object      Count   Time(ns)  Time(%)  Branch Count   Branch Count(%)
+v- ls
+    v- 2638:2638
+        v- _start                  ld-2.19.so    1     10074071   100.0         211135            100.0
+          |- unknown               unknown       1        13198     0.1              1              0.0
+          >- _dl_start             ld-2.19.so    1      1400980    13.9          19637              9.3
+          >- _d_linit_internal     ld-2.19.so    1       448152     4.4          11094              5.3
+          v-__libc_start_main@plt  ls            1      8211741    81.5         180397             85.4
+             >- _dl_fixup          ld-2.19.so    1         7607     0.1            108              0.1
+             >- __cxa_atexit       libc-2.19.so  1        11737     0.1             10              0.0
+             >- __libc_csu_init    ls            1        10354     0.1             10              0.0
+             |- _setjmp            libc-2.19.so  1            0     0.0              4              0.0
+             v- main               ls            1      8182043    99.6         180254             99.9
+</pre>
+<h3>Points to note:</h3>
+<ul>
+<li>The top level is a command name (comm)</li>
+<li>The next level is a thread (pid:tid)</li>
+<li>Subsequent levels are functions</li>
+<li>'Count' is the number of calls</li>
+<li>'Time' is the elapsed time until the function returns</li>
+<li>Percentages are relative to the level above</li>
+<li>'Branch Count' is the total number of branches for that function and all functions that it calls
+</ul>
+<h3>Find</h3>
+Ctrl-F displays a Find bar which finds function names by either an exact match or a pattern match.
+The pattern matching symbols are ? for any character and * for zero or more characters.
+<h2 id=allbranches>1.2 All branches</h2>
+The All branches report displays all branches in chronological order.
+Not all data is fetched immediately. More records can be fetched using the Fetch bar provided.
+<h3>Disassembly</h3>
+Open a branch to display disassembly. This only works if:
+<ol>
+<li>The disassembler is available. Currently, only Intel XED is supported - see <a href=#xed>Intel XED Setup</a></li>
+<li>The object code is available. Currently, only the perf build ID cache is searched for object code.
+The default directory ~/.debug can be overridden by setting environment variable PERF_BUILDID_DIR.
+One exception is kcore where the DSO long name is used (refer dsos_view on the Tables menu),
+or alternatively, set environment variable PERF_KCORE to the kcore file name.</li>
+</ol>
+<h4 id=xed>Intel XED Setup</h4>
+To use Intel XED, libxed.so must be present.  To build and install libxed.so:
+<pre>
+git clone https://github.com/intelxed/mbuild.git mbuild
+git clone https://github.com/intelxed/xed
+cd xed
+./mfile.py --share
+sudo ./mfile.py --prefix=/usr/local install
+sudo ldconfig
+</pre>
+<h3>Find</h3>
+Ctrl-F displays a Find bar which finds substrings by either an exact match or a regular expression match.
+Refer to Python documentation for the regular expression syntax.
+All columns are searched, but only currently fetched rows are searched.
+<h2 id=selectedbranches>1.3 Selected branches</h2>
+This is the same as the <a href=#allbranches>All branches</a> report but with the data reduced
+by various selection criteria. A dialog box displays available criteria which are AND'ed together.
+<h3>1.3.1 Time ranges</h3>
+The time ranges hint text shows the total time range. Relative time ranges can also be entered in
+ms, us or ns. Also, negative values are relative to the end of trace.  Examples:
+<pre>
+	81073085947329-81073085958238	From 81073085947329 to 81073085958238
+	100us-200us		From 100us to 200us
+	10ms-			From 10ms to the end
+	-100ns			The first 100ns
+	-10ms-			The last 10ms
+</pre>
+N.B. Due to the granularity of timestamps, there could be no branches in any given time range.
+<h1 id=tables>2. Tables</h1>
+The Tables menu shows all tables and views in the database. Most tables have an associated view
+which displays the information in a more friendly way. Not all data for large tables is fetched
+immediately. More records can be fetched using the Fetch bar provided. Columns can be sorted,
+but that can be slow for large tables.
+<p>There are also tables of database meta-information.
+For SQLite3 databases, the sqlite_master table is included.
+For PostgreSQL databases, information_schema.tables/views/columns are included.
+<h3>Find</h3>
+Ctrl-F displays a Find bar which finds substrings by either an exact match or a regular expression match.
+Refer to Python documentation for the regular expression syntax.
+All columns are searched, but only currently fetched rows are searched.
+<p>N.B. Results are found in id order, so if the table is re-ordered, find-next and find-previous
+will go to the next/previous result in id order, instead of display order.
+"""
+
+# Help window
+
+class HelpWindow(QMdiSubWindow):
+
+	def __init__(self, glb, parent=None):
+		super(HelpWindow, self).__init__(parent)
+
+		self.text = QTextBrowser()
+		self.text.setHtml(glb_help_text)
+		self.text.setReadOnly(True)
+		self.text.setOpenExternalLinks(True)
+
+		self.setWidget(self.text)
+
+		AddSubWindow(glb.mainwindow.mdi_area, self, "Exported SQL Viewer Help")
+
+# Main window that only displays the help text
+
+class HelpOnlyWindow(QMainWindow):
+
+	def __init__(self, parent=None):
+		super(HelpOnlyWindow, self).__init__(parent)
+
+		self.setMinimumSize(200, 100)
+		self.resize(800, 600)
+		self.setWindowTitle("Exported SQL Viewer Help")
+		self.setWindowIcon(self.style().standardIcon(QStyle.SP_MessageBoxInformation))
+
+		self.text = QTextBrowser()
+		self.text.setHtml(glb_help_text)
+		self.text.setReadOnly(True)
+		self.text.setOpenExternalLinks(True)
+
+		self.setCentralWidget(self.text)
+
 # Font resize
 
 def ResizeFont(widget, diff):
@@ -1851,6 +2313,9 @@
 
 		self.window_menu = WindowMenu(self.mdi_area, menu)
 
+		help_menu = menu.addMenu("&Help")
+		help_menu.addAction(CreateAction("&Exported SQL Viewer Help", "Helpful information", self.Help, self, QKeySequence.HelpContents))
+
 	def Find(self):
 		win = self.mdi_area.activeSubWindow()
 		if win:
@@ -1888,6 +2353,8 @@
 			if event == "branches":
 				label = "All branches" if branches_events == 1 else "All branches " + "(id=" + dbid + ")"
 				reports_menu.addAction(CreateAction(label, "Create a new window displaying branch events", lambda x=dbid: self.NewBranchView(x), self))
+				label = "Selected branches" if branches_events == 1 else "Selected branches " + "(id=" + dbid + ")"
+				reports_menu.addAction(CreateAction(label, "Create a new window displaying branch events", lambda x=dbid: self.NewSelectedBranchView(x), self))
 
 	def TableMenu(self, tables, menu):
 		table_menu = menu.addMenu("&Tables")
@@ -1900,9 +2367,18 @@
 	def NewBranchView(self, event_id):
 		BranchWindow(self.glb, event_id, "", "", self)
 
+	def NewSelectedBranchView(self, event_id):
+		dialog = SelectedBranchDialog(self.glb, self)
+		ret = dialog.exec_()
+		if ret:
+			BranchWindow(self.glb, event_id, dialog.name, dialog.where_clause, self)
+
 	def NewTableView(self, table_name):
 		TableWindow(self.glb, table_name, self)
 
+	def Help(self):
+		HelpWindow(self.glb, self)
+
 # XED Disassembler
 
 class xed_state_t(Structure):
@@ -1929,7 +2405,12 @@
 class LibXED():
 
 	def __init__(self):
-		self.libxed = CDLL("libxed.so")
+		try:
+			self.libxed = CDLL("libxed.so")
+		except:
+			self.libxed = None
+		if not self.libxed:
+			self.libxed = CDLL("/usr/local/lib/libxed.so")
 
 		self.xed_tables_init = self.libxed.xed_tables_init
 		self.xed_tables_init.restype = None
@@ -2097,10 +2578,16 @@
 
 def Main():
 	if (len(sys.argv) < 2):
-		print >> sys.stderr, "Usage is: exported-sql-viewer.py <database name>"
+		print >> sys.stderr, "Usage is: exported-sql-viewer.py {<database name> | --help-only}"
 		raise Exception("Too few arguments")
 
 	dbname = sys.argv[1]
+	if dbname == "--help-only":
+		app = QApplication(sys.argv)
+		mainwindow = HelpOnlyWindow()
+		mainwindow.show()
+		err = app.exec_()
+		sys.exit(err)
 
 	is_sqlite3 = False
 	try:
diff --git a/tools/perf/tests/attr/test-record-group-sampling b/tools/perf/tests/attr/test-record-group-sampling
index 8a33ca4..f0729c4 100644
--- a/tools/perf/tests/attr/test-record-group-sampling
+++ b/tools/perf/tests/attr/test-record-group-sampling
@@ -37,4 +37,3 @@
 sample_period=0
 freq=0
 write_backward=0
-sample_id_all=0
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index e88e6f9..668d2a9 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1810,3 +1810,30 @@ void perf_evlist__force_leader(struct perf_evlist *evlist)
 		leader->forced_leader = true;
 	}
 }
+
+struct perf_evsel *perf_evlist__reset_weak_group(struct perf_evlist *evsel_list,
+						 struct perf_evsel *evsel)
+{
+	struct perf_evsel *c2, *leader;
+	bool is_open = true;
+
+	leader = evsel->leader;
+	pr_debug("Weak group for %s/%d failed\n",
+			leader->name, leader->nr_members);
+
+	/*
+	 * for_each_group_member doesn't work here because it doesn't
+	 * include the first entry.
+	 */
+	evlist__for_each_entry(evsel_list, c2) {
+		if (c2 == evsel)
+			is_open = false;
+		if (c2->leader == leader) {
+			if (is_open)
+				perf_evsel__close(c2);
+			c2->leader = c2;
+			c2->nr_members = 0;
+		}
+	}
+	return leader;
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index dc66436..9919eed 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -312,4 +312,7 @@ bool perf_evlist__exclude_kernel(struct perf_evlist *evlist);
 
 void perf_evlist__force_leader(struct perf_evlist *evlist);
 
+struct perf_evsel *perf_evlist__reset_weak_group(struct perf_evlist *evlist,
+						 struct perf_evsel *evsel);
+
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 6d18705..d37bb15 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -956,7 +956,6 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 		attr->sample_freq    = 0;
 		attr->sample_period  = 0;
 		attr->write_backward = 0;
-		attr->sample_id_all  = 0;
 	}
 
 	if (opts->no_samples)
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index 58f6a9c..4503f3c 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -1474,6 +1474,8 @@ static void intel_pt_calc_mtc_timestamp(struct intel_pt_decoder *decoder)
 		decoder->have_calc_cyc_to_tsc = false;
 		intel_pt_calc_cyc_to_tsc(decoder, true);
 	}
+
+	intel_pt_log_to("Setting timestamp", decoder->timestamp);
 }
 
 static void intel_pt_calc_cbr(struct intel_pt_decoder *decoder)
@@ -1514,6 +1516,8 @@ static void intel_pt_calc_cyc_timestamp(struct intel_pt_decoder *decoder)
 		decoder->timestamp = timestamp;
 
 	decoder->timestamp_insn_cnt = 0;
+
+	intel_pt_log_to("Setting timestamp", decoder->timestamp);
 }
 
 /* Walk PSB+ packets when already in sync. */
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-log.c b/tools/perf/util/intel-pt-decoder/intel-pt-log.c
index e02bc7b..5e64da27 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-log.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-log.c
@@ -31,6 +31,11 @@ static FILE *f;
 static char log_name[MAX_LOG_NAME];
 bool intel_pt_enable_logging;
 
+void *intel_pt_log_fp(void)
+{
+	return f;
+}
+
 void intel_pt_log_enable(void)
 {
 	intel_pt_enable_logging = true;
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-log.h b/tools/perf/util/intel-pt-decoder/intel-pt-log.h
index 45b64f9..cc08493 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-log.h
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-log.h
@@ -22,6 +22,7 @@
 
 struct intel_pt_pkt;
 
+void *intel_pt_log_fp(void);
 void intel_pt_log_enable(void);
 void intel_pt_log_disable(void);
 void intel_pt_log_set_name(const char *name);
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 86cc9a6..149ff36 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -206,6 +206,16 @@ static void intel_pt_dump_event(struct intel_pt *pt, unsigned char *buf,
 	intel_pt_dump(pt, buf, len);
 }
 
+static void intel_pt_log_event(union perf_event *event)
+{
+	FILE *f = intel_pt_log_fp();
+
+	if (!intel_pt_enable_logging || !f)
+		return;
+
+	perf_event__fprintf(event, f);
+}
+
 static int intel_pt_do_fix_overlap(struct intel_pt *pt, struct auxtrace_buffer *a,
 				   struct auxtrace_buffer *b)
 {
@@ -2010,9 +2020,9 @@ static int intel_pt_process_event(struct perf_session *session,
 		 event->header.type == PERF_RECORD_SWITCH_CPU_WIDE)
 		err = intel_pt_context_switch(pt, event, sample);
 
-	intel_pt_log("event %s (%u): cpu %d time %"PRIu64" tsc %#"PRIx64"\n",
-		     perf_event__name(event->header.type), event->header.type,
-		     sample->cpu, sample->time, timestamp);
+	intel_pt_log("event %u: cpu %d time %"PRIu64" tsc %#"PRIx64" ",
+		     event->header.type, sample->cpu, sample->time, timestamp);
+	intel_pt_log_event(event);
 
 	return err;
 }
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 7799788..7e49baa 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -773,7 +773,7 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu)
 
 		if (!is_arm_pmu_core(name)) {
 			pname = pe->pmu ? pe->pmu : "cpu";
-			if (strncmp(pname, name, strlen(pname)))
+			if (strcmp(pname, name))
 				continue;
 		}