Merge tag 'powerpc-5.16-2' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux
Pull more powerpc fixes from Michael Ellerman:
- Fix a bug in copying of sigset_t for 32-bit systems, which caused X
to not start.
- Fix handling of shared LSIs (rare) with the xive interrupt controller
(Power9/10).
- Fix missing TOC setup in some KVM code, which could result in oopses
depending on kernel data layout.
- Fix DMA mapping when we have persistent memory and only one DMA
window available.
- Fix further problems with STRICT_KERNEL_RWX on 8xx, exposed by a
recent fix.
- A couple of other minor fixes.
Thanks to Alexey Kardashevskiy, Aneesh Kumar K.V, Cédric Le Goater,
Christian Zigotzky, Christophe Leroy, Daniel Axtens, Finn Thain, Greg
Kurz, Masahiro Yamada, Nicholas Piggin, and Uwe Kleine-König.
* tag 'powerpc-5.16-2' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux:
powerpc/xive: Change IRQ domain to a tree domain
powerpc/8xx: Fix pinned TLBs with CONFIG_STRICT_KERNEL_RWX
powerpc/signal32: Fix sigset_t copy
powerpc/book3e: Fix TLBCAM preset at boot
powerpc/pseries/ddw: Do not try direct mapping with persistent memory and one window
powerpc/pseries/ddw: simplify enable_ddw()
powerpc/pseries/ddw: Revert "Extend upper limit for huge DMA window for persistent memory"
powerpc/pseries: Fix numa FORM2 parsing fallback code
powerpc/pseries: rename numa_dist_table to form2_distances
powerpc: clean vdso32 and vdso64 directories
powerpc/83xx/mpc8349emitx: Drop unused variable
KVM: PPC: Book3S HV: Use GLOBAL_TOC for kvmppc_h_set_dabr/xdabr()
diff --git a/.mailmap b/.mailmap
index 14314e3..6277bb2 100644
--- a/.mailmap
+++ b/.mailmap
@@ -71,6 +71,9 @@
Chao Yu <chao@kernel.org> <yuchao0@huawei.com>
Chris Chiu <chris.chiu@canonical.com> <chiu@endlessm.com>
Chris Chiu <chris.chiu@canonical.com> <chiu@endlessos.org>
+Christian Borntraeger <borntraeger@linux.ibm.com> <borntraeger@de.ibm.com>
+Christian Borntraeger <borntraeger@linux.ibm.com> <cborntra@de.ibm.com>
+Christian Borntraeger <borntraeger@linux.ibm.com> <borntrae@de.ibm.com>
Christophe Ricard <christophe.ricard@gmail.com>
Christoph Hellwig <hch@lst.de>
Colin Ian King <colin.king@intel.com> <colin.king@canonical.com>
diff --git a/Documentation/admin-guide/laptops/thinkpad-acpi.rst b/Documentation/admin-guide/laptops/thinkpad-acpi.rst
index 6721a80..475eb0e 100644
--- a/Documentation/admin-guide/laptops/thinkpad-acpi.rst
+++ b/Documentation/admin-guide/laptops/thinkpad-acpi.rst
@@ -1520,15 +1520,15 @@
Lenovo X1 Carbon 2nd gen (2014)'s adaptive keyboard. The value can be read
and set.
-- 1 = Home mode
-- 2 = Web-browser mode
-- 3 = Web-conference mode
-- 4 = Function mode
-- 5 = Layflat mode
+- 0 = Home mode
+- 1 = Web-browser mode
+- 2 = Web-conference mode
+- 3 = Function mode
+- 4 = Layflat mode
For more details about which buttons will appear depending on the mode, please
review the laptop's user guide:
-http://www.lenovo.com/shop/americas/content/user_guides/x1carbon_2_ug_en.pdf
+https://download.lenovo.com/ibmdl/pub/pc/pccbbs/mobiles_pdf/x1carbon_2_ug_en.pdf
Battery charge control
----------------------
diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst
index 4261620..0e486f4 100644
--- a/Documentation/admin-guide/sysctl/kernel.rst
+++ b/Documentation/admin-guide/sysctl/kernel.rst
@@ -1099,7 +1099,7 @@
===============
Enables/disables task delay accounting (see
-:doc:`accounting/delay-accounting.rst`). Enabling this feature incurs
+Documentation/accounting/delay-accounting.rst. Enabling this feature incurs
a small amount of overhead in the scheduler but is useful for debugging
and performance tuning. It is required by some tools such as iotop.
diff --git a/Documentation/arm/marvell.rst b/Documentation/arm/marvell.rst
index 8323c79..9485a5a 100644
--- a/Documentation/arm/marvell.rst
+++ b/Documentation/arm/marvell.rst
@@ -104,6 +104,8 @@
Not supported by the Linux kernel.
+ Homepage:
+ https://web.archive.org/web/20110924171043/http://www.marvell.com/embedded-processors/discovery-innovation/
Core:
Feroceon 88fr571-vd ARMv5 compatible
@@ -120,6 +122,7 @@
- 88F6707
- 88F6W11
+ - Product infos: https://web.archive.org/web/20141002083258/http://www.marvell.com/embedded-processors/armada-370/
- Product Brief: https://web.archive.org/web/20121115063038/http://www.marvell.com/embedded-processors/armada-300/assets/Marvell_ARMADA_370_SoC.pdf
- Hardware Spec: https://web.archive.org/web/20140617183747/http://www.marvell.com/embedded-processors/armada-300/assets/ARMADA370-datasheet.pdf
- Functional Spec: https://web.archive.org/web/20140617183701/http://www.marvell.com/embedded-processors/armada-300/assets/ARMADA370-FunctionalSpec-datasheet.pdf
@@ -127,9 +130,29 @@
Core:
Sheeva ARMv7 compatible PJ4B
+ Armada XP Flavors:
+ - MV78230
+ - MV78260
+ - MV78460
+
+ NOTE:
+ not to be confused with the non-SMP 78xx0 SoCs
+
+ - Product infos: https://web.archive.org/web/20150101215721/http://www.marvell.com/embedded-processors/armada-xp/
+ - Product Brief: https://web.archive.org/web/20121021173528/http://www.marvell.com/embedded-processors/armada-xp/assets/Marvell-ArmadaXP-SoC-product%20brief.pdf
+ - Functional Spec: https://web.archive.org/web/20180829171131/http://www.marvell.com/embedded-processors/armada-xp/assets/ARMADA-XP-Functional-SpecDatasheet.pdf
+ - Hardware Specs:
+ - https://web.archive.org/web/20141127013651/http://www.marvell.com/embedded-processors/armada-xp/assets/HW_MV78230_OS.PDF
+ - https://web.archive.org/web/20141222000224/http://www.marvell.com/embedded-processors/armada-xp/assets/HW_MV78260_OS.PDF
+ - https://web.archive.org/web/20141222000230/http://www.marvell.com/embedded-processors/armada-xp/assets/HW_MV78460_OS.PDF
+
+ Core:
+ Sheeva ARMv7 compatible Dual-core or Quad-core PJ4B-MP
+
Armada 375 Flavors:
- 88F6720
+ - Product infos: https://web.archive.org/web/20140108032402/http://www.marvell.com/embedded-processors/armada-375/
- Product Brief: https://web.archive.org/web/20131216023516/http://www.marvell.com/embedded-processors/armada-300/assets/ARMADA_375_SoC-01_product_brief.pdf
Core:
@@ -162,29 +185,6 @@
Core:
ARM Cortex-A9
- Armada XP Flavors:
- - MV78230
- - MV78260
- - MV78460
-
- NOTE:
- not to be confused with the non-SMP 78xx0 SoCs
-
- Product Brief:
- https://web.archive.org/web/20121021173528/http://www.marvell.com/embedded-processors/armada-xp/assets/Marvell-ArmadaXP-SoC-product%20brief.pdf
-
- Functional Spec:
- https://web.archive.org/web/20180829171131/http://www.marvell.com/embedded-processors/armada-xp/assets/ARMADA-XP-Functional-SpecDatasheet.pdf
-
- - Hardware Specs:
-
- - https://web.archive.org/web/20141127013651/http://www.marvell.com/embedded-processors/armada-xp/assets/HW_MV78230_OS.PDF
- - https://web.archive.org/web/20141222000224/http://www.marvell.com/embedded-processors/armada-xp/assets/HW_MV78260_OS.PDF
- - https://web.archive.org/web/20141222000230/http://www.marvell.com/embedded-processors/armada-xp/assets/HW_MV78460_OS.PDF
-
- Core:
- Sheeva ARMv7 compatible Dual-core or Quad-core PJ4B-MP
-
Linux kernel mach directory:
arch/arm/mach-mvebu
Linux kernel plat directory:
@@ -436,7 +436,7 @@
- Flavors:
- 88DE3010, Armada 1000 (no Linux support)
- Core: Marvell PJ1 (ARMv5TE), Dual-core
- - Product Brief: http://www.marvell.com.cn/digital-entertainment/assets/armada_1000_pb.pdf
+ - Product Brief: https://web.archive.org/web/20131103162620/http://www.marvell.com/digital-entertainment/assets/armada_1000_pb.pdf
- 88DE3005, Armada 1500 Mini
- Design name: BG2CD
- Core: ARM Cortex-A9, PL310 L2CC
diff --git a/Documentation/bpf/index.rst b/Documentation/bpf/index.rst
index 37f273a..610450f 100644
--- a/Documentation/bpf/index.rst
+++ b/Documentation/bpf/index.rst
@@ -15,7 +15,7 @@
libbpf
======
-Documentation/bpf/libbpf/libbpf.rst is a userspace library for loading and interacting with bpf programs.
+Documentation/bpf/libbpf/index.rst is a userspace library for loading and interacting with bpf programs.
BPF Type Format (BTF)
=====================
diff --git a/Documentation/doc-guide/sphinx.rst b/Documentation/doc-guide/sphinx.rst
index ec3e71f..e445cb1 100644
--- a/Documentation/doc-guide/sphinx.rst
+++ b/Documentation/doc-guide/sphinx.rst
@@ -27,7 +27,7 @@
==============
The ReST markups currently used by the Documentation/ files are meant to be
-built with ``Sphinx`` version 1.3 or higher.
+built with ``Sphinx`` version 1.7 or higher.
There's a script that checks for the Sphinx requirements. Please see
:ref:`sphinx-pre-install` for further details.
@@ -43,10 +43,6 @@
.. note::
- #) Sphinx versions below 1.5 don't work properly with Python's
- docutils version 0.13.1 or higher. So, if you're willing to use
- those versions, you should run ``pip install 'docutils==0.12'``.
-
#) It is recommended to use the RTD theme for html output. Depending
on the Sphinx version, it should be installed separately,
with ``pip install sphinx_rtd_theme``.
@@ -55,13 +51,13 @@
those expressions are written using LaTeX notation. It needs texlive
installed with amsfonts and amsmath in order to evaluate them.
-In summary, if you want to install Sphinx version 1.7.9, you should do::
+In summary, if you want to install Sphinx version 2.4.4, you should do::
- $ virtualenv sphinx_1.7.9
- $ . sphinx_1.7.9/bin/activate
- (sphinx_1.7.9) $ pip install -r Documentation/sphinx/requirements.txt
+ $ virtualenv sphinx_2.4.4
+ $ . sphinx_2.4.4/bin/activate
+ (sphinx_2.4.4) $ pip install -r Documentation/sphinx/requirements.txt
-After running ``. sphinx_1.7.9/bin/activate``, the prompt will change,
+After running ``. sphinx_2.4.4/bin/activate``, the prompt will change,
in order to indicate that you're using the new environment. If you
open a new shell, you need to rerun this command to enter again at
the virtual environment before building the documentation.
@@ -81,7 +77,7 @@
PDF and LaTeX builds
--------------------
-Such builds are currently supported only with Sphinx versions 1.4 and higher.
+Such builds are currently supported only with Sphinx versions 2.4 and higher.
For PDF and LaTeX output, you'll also need ``XeLaTeX`` version 3.14159265.
@@ -104,8 +100,8 @@
You should run:
sudo dnf install -y texlive-luatex85
- /usr/bin/virtualenv sphinx_1.7.9
- . sphinx_1.7.9/bin/activate
+ /usr/bin/virtualenv sphinx_2.4.4
+ . sphinx_2.4.4/bin/activate
pip install -r Documentation/sphinx/requirements.txt
Can't build as 1 mandatory dependency is missing at ./scripts/sphinx-pre-install line 468.
diff --git a/Documentation/filesystems/autofs.rst b/Documentation/filesystems/autofs.rst
index 681c6a4..4f490278 100644
--- a/Documentation/filesystems/autofs.rst
+++ b/Documentation/filesystems/autofs.rst
@@ -35,7 +35,7 @@
required with any user-space program. Subsequent text refers to this
as the "automount daemon" or simply "the daemon".
-"autofs" is a Linux kernel module with provides the "autofs"
+"autofs" is a Linux kernel module which provides the "autofs"
filesystem type. Several "autofs" filesystems can be mounted and they
can each be managed separately, or all managed by the same daemon.
diff --git a/Documentation/power/energy-model.rst b/Documentation/power/energy-model.rst
index 8a2788a..5ac62a7 100644
--- a/Documentation/power/energy-model.rst
+++ b/Documentation/power/energy-model.rst
@@ -84,6 +84,16 @@
2.2 Registration of performance domains
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+Registration of 'advanced' EM
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The 'advanced' EM gets it's name due to the fact that the driver is allowed
+to provide more precised power model. It's not limited to some implemented math
+formula in the framework (like it's in 'simple' EM case). It can better reflect
+the real power measurements performed for each performance state. Thus, this
+registration method should be preferred in case considering EM static power
+(leakage) is important.
+
Drivers are expected to register performance domains into the EM framework by
calling the following API::
@@ -103,6 +113,18 @@
See Section 3. for an example of driver implementing this
callback, or Section 2.4 for further documentation on this API
+Registration of 'simple' EM
+~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The 'simple' EM is registered using the framework helper function
+cpufreq_register_em_with_opp(). It implements a power model which is tight to
+math formula::
+
+ Power = C * V^2 * f
+
+The EM which is registered using this method might not reflect correctly the
+physics of a real device, e.g. when static power (leakage) is important.
+
2.3 Accessing performance domains
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
@@ -138,6 +160,10 @@
3. Example driver
-----------------
+The CPUFreq framework supports dedicated callback for registering
+the EM for a given CPU(s) 'policy' object: cpufreq_driver::register_em().
+That callback has to be implemented properly for a given driver,
+because the framework would call it at the right time during setup.
This section provides a simple example of a CPUFreq driver registering a
performance domain in the Energy Model framework using the (fake) 'foo'
protocol. The driver implements an est_power() function to be provided to the
@@ -167,25 +193,22 @@
20 return 0;
21 }
22
- 23 static int foo_cpufreq_init(struct cpufreq_policy *policy)
+ 23 static void foo_cpufreq_register_em(struct cpufreq_policy *policy)
24 {
25 struct em_data_callback em_cb = EM_DATA_CB(est_power);
26 struct device *cpu_dev;
- 27 int nr_opp, ret;
+ 27 int nr_opp;
28
29 cpu_dev = get_cpu_device(cpumask_first(policy->cpus));
30
- 31 /* Do the actual CPUFreq init work ... */
- 32 ret = do_foo_cpufreq_init(policy);
- 33 if (ret)
- 34 return ret;
- 35
- 36 /* Find the number of OPPs for this policy */
- 37 nr_opp = foo_get_nr_opp(policy);
+ 31 /* Find the number of OPPs for this policy */
+ 32 nr_opp = foo_get_nr_opp(policy);
+ 33
+ 34 /* And register the new performance domain */
+ 35 em_dev_register_perf_domain(cpu_dev, nr_opp, &em_cb, policy->cpus,
+ 36 true);
+ 37 }
38
- 39 /* And register the new performance domain */
- 40 em_dev_register_perf_domain(cpu_dev, nr_opp, &em_cb, policy->cpus,
- 41 true);
- 42
- 43 return 0;
- 44 }
+ 39 static struct cpufreq_driver foo_cpufreq_driver = {
+ 40 .register_em = foo_cpufreq_register_em,
+ 41 };
diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst
index e35ab74..b398b85 100644
--- a/Documentation/process/changes.rst
+++ b/Documentation/process/changes.rst
@@ -54,7 +54,7 @@
iptables 1.4.2 iptables -V
openssl & libcrypto 1.0.0 openssl version
bc 1.06.95 bc --version
-Sphinx\ [#f1]_ 1.3 sphinx-build --version
+Sphinx\ [#f1]_ 1.7 sphinx-build --version
====================== =============== ========================================
.. [#f1] Sphinx is needed only to build the Kernel documentation
diff --git a/Documentation/process/submitting-patches.rst b/Documentation/process/submitting-patches.rst
index a0cc969..da085d6 100644
--- a/Documentation/process/submitting-patches.rst
+++ b/Documentation/process/submitting-patches.rst
@@ -22,8 +22,8 @@
easier.
Some subsystems and maintainer trees have additional information about
-their workflow and expectations, see :ref:`Documentation/process/maintainer
-handbooks <maintainer_handbooks_main>`.
+their workflow and expectations, see
+:ref:`Documentation/process/maintainer-handbooks.rst <maintainer_handbooks_main>`.
Obtain a current source tree
----------------------------
diff --git a/Documentation/trace/ftrace.rst b/Documentation/trace/ftrace.rst
index 4e5b26f..b3166c4 100644
--- a/Documentation/trace/ftrace.rst
+++ b/Documentation/trace/ftrace.rst
@@ -2442,11 +2442,10 @@
#!/bin/bash
tracefs=`sed -ne 's/^tracefs \(.*\) tracefs.*/\1/p' /proc/mounts`
- echo nop > $tracefs/tracing/current_tracer
- echo 0 > $tracefs/tracing/tracing_on
- echo $$ > $tracefs/tracing/set_ftrace_pid
- echo function > $tracefs/tracing/current_tracer
- echo 1 > $tracefs/tracing/tracing_on
+ echo 0 > $tracefs/tracing_on
+ echo $$ > $tracefs/set_ftrace_pid
+ echo function > $tracefs/current_tracer
+ echo 1 > $tracefs/tracing_on
exec "$@"
diff --git a/Documentation/translations/it_IT/doc-guide/sphinx.rst b/Documentation/translations/it_IT/doc-guide/sphinx.rst
index 0046d75..9762452 100644
--- a/Documentation/translations/it_IT/doc-guide/sphinx.rst
+++ b/Documentation/translations/it_IT/doc-guide/sphinx.rst
@@ -35,7 +35,7 @@
====================
I marcatori ReST utilizzati nei file in Documentation/ sono pensati per essere
-processati da ``Sphinx`` nella versione 1.3 o superiore.
+processati da ``Sphinx`` nella versione 1.7 o superiore.
Esiste uno script che verifica i requisiti Sphinx. Per ulteriori dettagli
consultate :ref:`it_sphinx-pre-install`.
@@ -53,11 +53,6 @@
.. note::
- #) Le versioni di Sphinx inferiori alla 1.5 non funzionano bene
- con il pacchetto Python docutils versione 0.13.1 o superiore.
- Se volete usare queste versioni, allora dovere eseguire
- ``pip install 'docutils==0.12'``.
-
#) Viene raccomandato l'uso del tema RTD per la documentazione in HTML.
A seconda della versione di Sphinx, potrebbe essere necessaria
l'installazione tramite il comando ``pip install sphinx_rtd_theme``.
@@ -67,13 +62,13 @@
utilizzando LaTeX. Per una corretta interpretazione, è necessario aver
installato texlive con i pacchetti amdfonts e amsmath.
-Riassumendo, se volete installare la versione 1.7.9 di Sphinx dovete eseguire::
+Riassumendo, se volete installare la versione 2.4.4 di Sphinx dovete eseguire::
- $ virtualenv sphinx_1.7.9
- $ . sphinx_1.7.9/bin/activate
- (sphinx_1.7.9) $ pip install -r Documentation/sphinx/requirements.txt
+ $ virtualenv sphinx_2.4.4
+ $ . sphinx_2.4.4/bin/activate
+ (sphinx_2.4.4) $ pip install -r Documentation/sphinx/requirements.txt
-Dopo aver eseguito ``. sphinx_1.7.9/bin/activate``, il prompt cambierà per
+Dopo aver eseguito ``. sphinx_2.4.4/bin/activate``, il prompt cambierà per
indicare che state usando il nuovo ambiente. Se aprite un nuova sessione,
prima di generare la documentazione, dovrete rieseguire questo comando per
rientrare nell'ambiente virtuale.
@@ -94,7 +89,7 @@
--------------------------
Al momento, la generazione di questi documenti è supportata solo dalle
-versioni di Sphinx superiori alla 1.4.
+versioni di Sphinx superiori alla 2.4.
Per la generazione di PDF e LaTeX, avrete bisogno anche del pacchetto
``XeLaTeX`` nella versione 3.14159265
@@ -119,8 +114,8 @@
You should run:
sudo dnf install -y texlive-luatex85
- /usr/bin/virtualenv sphinx_1.7.9
- . sphinx_1.7.9/bin/activate
+ /usr/bin/virtualenv sphinx_2.4.4
+ . sphinx_2.4.4/bin/activate
pip install -r Documentation/sphinx/requirements.txt
Can't build as 1 mandatory dependency is missing at ./scripts/sphinx-pre-install line 468.
diff --git a/Documentation/translations/it_IT/process/changes.rst b/Documentation/translations/it_IT/process/changes.rst
index 87d0818..dc71933 100644
--- a/Documentation/translations/it_IT/process/changes.rst
+++ b/Documentation/translations/it_IT/process/changes.rst
@@ -57,7 +57,7 @@
iptables 1.4.2 iptables -V
openssl & libcrypto 1.0.0 openssl version
bc 1.06.95 bc --version
-Sphinx\ [#f1]_ 1.3 sphinx-build --version
+Sphinx\ [#f1]_ 1.7 sphinx-build --version
====================== ================= ========================================
.. [#f1] Sphinx è necessario solo per produrre la documentazione del Kernel
diff --git a/Documentation/translations/zh_CN/doc-guide/sphinx.rst b/Documentation/translations/zh_CN/doc-guide/sphinx.rst
index 951595c..23eac67 100644
--- a/Documentation/translations/zh_CN/doc-guide/sphinx.rst
+++ b/Documentation/translations/zh_CN/doc-guide/sphinx.rst
@@ -26,7 +26,7 @@
安装Sphinx
==========
-Documentation/ 下的ReST文件现在使用sphinx1.3或更高版本构建。
+Documentation/ 下的ReST文件现在使用sphinx1.7或更高版本构建。
这有一个脚本可以检查Sphinx的依赖项。更多详细信息见
:ref:`sphinx-pre-install_zh` 。
@@ -40,22 +40,19 @@
.. note::
- #) 低于1.5版本的Sphinx无法与Python的0.13.1或更高版本docutils一起正常工作。
- 如果您想使用这些版本，那么应该运行 ``pip install 'docutils==0.12'`` 。
-
#) html输出建议使用RTD主题。根据Sphinx版本的不同，它应该用
``pip install sphinx_rtd_theme`` 单独安装。
#) 一些ReST页面包含数学表达式。由于Sphinx的工作方式，这些表达式是使用 LaTeX
编写的。它需要安装amsfonts和amsmath宏包，以便显示。
-总之，如您要安装Sphinx 1.7.9版本，应执行::
+总之，如您要安装Sphinx 2.4.4版本，应执行::
- $ virtualenv sphinx_1.7.9
- $ . sphinx_1.7.9/bin/activate
- (sphinx_1.7.9) $ pip install -r Documentation/sphinx/requirements.txt
+ $ virtualenv sphinx_2.4.4
+ $ . sphinx_2.4.4/bin/activate
+ (sphinx_2.4.4) $ pip install -r Documentation/sphinx/requirements.txt
-在运行 ``. sphinx_1.7.9/bin/activate`` 之后，提示符将变化，以指示您正在使用新
+在运行 ``. sphinx_2.4.4/bin/activate`` 之后，提示符将变化，以指示您正在使用新
环境。如果您打开了一个新的shell，那么在构建文档之前，您需要重新运行此命令以再
次进入虚拟环境中。
@@ -71,7 +68,7 @@
PDF和LaTeX构建
--------------
-目前只有Sphinx 1.4及更高版本才支持这种构建。
+目前只有Sphinx 2.4及更高版本才支持这种构建。
对于PDF和LaTeX输出，还需要 ``XeLaTeX`` 3.14159265版本。（译注：此版本号真实
存在）
@@ -93,8 +90,8 @@
You should run:
sudo dnf install -y texlive-luatex85
- /usr/bin/virtualenv sphinx_1.7.9
- . sphinx_1.7.9/bin/activate
+ /usr/bin/virtualenv sphinx_2.4.4
+ . sphinx_2.4.4/bin/activate
pip install -r Documentation/sphinx/requirements.txt
Can't build as 1 mandatory dependency is missing at ./scripts/sphinx-pre-install line 468.
diff --git a/Documentation/translations/zh_CN/process/management-style.rst b/Documentation/translations/zh_CN/process/management-style.rst
index c6a5bb2..8053ae4 100644
--- a/Documentation/translations/zh_CN/process/management-style.rst
+++ b/Documentation/translations/zh_CN/process/management-style.rst
@@ -36,14 +36,14 @@
每个人都认为管理者做决定，而且决策很重要。决定越大越痛苦，管理者就必须越高级。
这很明显，但事实并非如此。
-游戏的名字是 **避免** 做出决定。尤其是，如果有人告诉你“选择（a）或（b），
+最重要的是 **避免** 做出决定。尤其是，如果有人告诉你“选择（a）或（b），
我们真的需要你来做决定”，你就是陷入麻烦的管理者。你管理的人比你更了解细节，
所以如果他们来找你做技术决策，你完蛋了。你显然没有能力为他们做这个决定。
（推论：如果你管理的人不比你更了解细节，你也会被搞砸，尽管原因完全不同。
也就是说，你的工作是错的，他们应该管理你的才智）
-所以游戏的名字是 **避免** 做出决定，至少是那些大而痛苦的决定。做一些小的
+所以最重要的是 **避免** 做出决定，至少是那些大而痛苦的决定。做一些小的
和非结果性的决定是很好的，并且使您看起来好像知道自己在做什么，所以内核管理者
需要做的是将那些大的和痛苦的决定变成那些没有人真正关心的小事情。
diff --git a/MAINTAINERS b/MAINTAINERS
index 7a2345c..5250298 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3733,7 +3733,7 @@
BROADCOM BNX2X 10 GIGABIT ETHERNET DRIVER
M: Ariel Elior <aelior@marvell.com>
M: Sudarsana Kalluru <skalluru@marvell.com>
-M: GR-everest-linux-l2@marvell.com
+M: Manish Chopra <manishc@marvell.com>
L: netdev@vger.kernel.org
S: Supported
F: drivers/net/ethernet/broadcom/bnx2x/
@@ -10445,7 +10445,7 @@
F: arch/riscv/kvm/
KERNEL VIRTUAL MACHINE for s390 (KVM/s390)
-M: Christian Borntraeger <borntraeger@de.ibm.com>
+M: Christian Borntraeger <borntraeger@linux.ibm.com>
M: Janosch Frank <frankja@linux.ibm.com>
R: David Hildenbrand <david@redhat.com>
R: Claudio Imbrenda <imbrenda@linux.ibm.com>
@@ -15593,7 +15593,7 @@
QLOGIC QL4xxx ETHERNET DRIVER
M: Ariel Elior <aelior@marvell.com>
-M: GR-everest-linux-l2@marvell.com
+M: Manish Chopra <manishc@marvell.com>
L: netdev@vger.kernel.org
S: Supported
F: drivers/net/ethernet/qlogic/qed/
@@ -16573,7 +16573,7 @@
S390
M: Heiko Carstens <hca@linux.ibm.com>
M: Vasily Gorbik <gor@linux.ibm.com>
-M: Christian Borntraeger <borntraeger@de.ibm.com>
+M: Christian Borntraeger <borntraeger@linux.ibm.com>
R: Alexander Gordeev <agordeev@linux.ibm.com>
L: linux-s390@vger.kernel.org
S: Supported
@@ -20317,7 +20317,8 @@
F: arch/x86/kernel/cpu/vmware.c
VMWARE PVRDMA DRIVER
-M: Adit Ranadive <aditr@vmware.com>
+M: Bryan Tan <bryantan@vmware.com>
+M: Vishnu Dasa <vdasa@vmware.com>
M: VMware PV-Drivers <pv-drivers@vmware.com>
L: linux-rdma@vger.kernel.org
S: Maintained
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index f0f9e8b..c2724d9 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1463,6 +1463,7 @@
bool "High Memory Support"
depends on MMU
select KMAP_LOCAL
+ select KMAP_LOCAL_NON_LINEAR_PTE_ARRAY
help
The address space of ARM processors is only 4 Gigabytes large
and it has to accommodate user address space, kernel address
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 2f03cbf..e4727dc 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -223,7 +223,14 @@
r = 1;
break;
case KVM_CAP_NR_VCPUS:
- r = num_online_cpus();
+ /*
+ * ARM64 treats KVM_CAP_NR_CPUS differently from all other
+ * architectures, as it does not always bound it to
+ * KVM_CAP_MAX_VCPUS. It should not matter much because
+ * this is just an advisory value.
+ */
+ r = min_t(unsigned int, num_online_cpus(),
+ kvm_arm_default_max_vcpus());
break;
case KVM_CAP_MAX_VCPUS:
case KVM_CAP_MAX_VCPU_ID:
diff --git a/arch/hexagon/include/asm/timer-regs.h b/arch/hexagon/include/asm/timer-regs.h
deleted file mode 100644
index ee6c614..0000000
--- a/arch/hexagon/include/asm/timer-regs.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Timer support for Hexagon
- *
- * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved.
- */
-
-#ifndef _ASM_TIMER_REGS_H
-#define _ASM_TIMER_REGS_H
-
-/* This stuff should go into a platform specific file */
-#define TCX0_CLK_RATE 19200
-#define TIMER_ENABLE 0
-#define TIMER_CLR_ON_MATCH 1
-
-/*
- * 8x50 HDD Specs 5-8. Simulator co-sim not fixed until
- * release 1.1, and then it's "adjustable" and probably not defaulted.
- */
-#define RTOS_TIMER_INT 3
-#ifdef CONFIG_HEXAGON_COMET
-#define RTOS_TIMER_REGS_ADDR 0xAB000000UL
-#endif
-#define SLEEP_CLK_RATE 32000
-
-#endif
diff --git a/arch/hexagon/include/asm/timex.h b/arch/hexagon/include/asm/timex.h
index 8d4ec76..dfe69e1 100644
--- a/arch/hexagon/include/asm/timex.h
+++ b/arch/hexagon/include/asm/timex.h
@@ -7,11 +7,10 @@
#define _ASM_TIMEX_H
#include <asm-generic/timex.h>
-#include <asm/timer-regs.h>
#include <asm/hexagon_vm.h>
/* Using TCX0 as our clock. CLOCK_TICK_RATE scheduled to be removed. */
-#define CLOCK_TICK_RATE TCX0_CLK_RATE
+#define CLOCK_TICK_RATE 19200
#define ARCH_HAS_READ_CURRENT_TIMER
diff --git a/arch/hexagon/kernel/.gitignore b/arch/hexagon/kernel/.gitignore
new file mode 100644
index 0000000..c5f676c
--- /dev/null
+++ b/arch/hexagon/kernel/.gitignore
@@ -0,0 +1 @@
+vmlinux.lds
diff --git a/arch/hexagon/kernel/time.c b/arch/hexagon/kernel/time.c
index feffe52..febc957 100644
--- a/arch/hexagon/kernel/time.c
+++ b/arch/hexagon/kernel/time.c
@@ -17,9 +17,10 @@
#include <linux/of_irq.h>
#include <linux/module.h>
-#include <asm/timer-regs.h>
#include <asm/hexagon_vm.h>
+#define TIMER_ENABLE BIT(0)
+
/*
* For the clocksource we need:
* pcycle frequency (600MHz)
@@ -33,6 +34,13 @@
cycles_t thread_freq_mhz;
cycles_t sleep_clk_freq;
+/*
+ * 8x50 HDD Specs 5-8. Simulator co-sim not fixed until
+ * release 1.1, and then it's "adjustable" and probably not defaulted.
+ */
+#define RTOS_TIMER_INT 3
+#define RTOS_TIMER_REGS_ADDR 0xAB000000UL
+
static struct resource rtos_timer_resources[] = {
{
.start = RTOS_TIMER_REGS_ADDR,
@@ -80,7 +88,7 @@
iowrite32(0, &rtos_timer->clear);
iowrite32(delta, &rtos_timer->match);
- iowrite32(1 << TIMER_ENABLE, &rtos_timer->enable);
+ iowrite32(TIMER_ENABLE, &rtos_timer->enable);
return 0;
}
diff --git a/arch/hexagon/lib/io.c b/arch/hexagon/lib/io.c
index d35d69d..55f7539 100644
--- a/arch/hexagon/lib/io.c
+++ b/arch/hexagon/lib/io.c
@@ -27,6 +27,7 @@
*dst++ = *src;
}
+EXPORT_SYMBOL(__raw_readsw);
/*
* __raw_writesw - read words a short at a time
@@ -47,6 +48,7 @@
}
+EXPORT_SYMBOL(__raw_writesw);
/* Pretty sure len is pre-adjusted for the length of the access already */
void __raw_readsl(const void __iomem *addr, void *data, int len)
@@ -62,6 +64,7 @@
}
+EXPORT_SYMBOL(__raw_readsl);
void __raw_writesl(void __iomem *addr, const void *data, int len)
{
@@ -76,3 +79,4 @@
}
+EXPORT_SYMBOL(__raw_writesl);
diff --git a/arch/m68k/kernel/traps.c b/arch/m68k/kernel/traps.c
index 99058a6..34d6458 100644
--- a/arch/m68k/kernel/traps.c
+++ b/arch/m68k/kernel/traps.c
@@ -1145,7 +1145,7 @@
*/
asmlinkage void fpsp040_die(void)
{
- force_fatal_sig(SIGSEGV);
+ force_exit_sig(SIGSEGV);
}
#ifdef CONFIG_M68KFPU_EMU
diff --git a/arch/mips/bcm63xx/clk.c b/arch/mips/bcm63xx/clk.c
index 5a3e325..1c91064 100644
--- a/arch/mips/bcm63xx/clk.c
+++ b/arch/mips/bcm63xx/clk.c
@@ -381,6 +381,12 @@
EXPORT_SYMBOL(clk_disable);
+struct clk *clk_get_parent(struct clk *clk)
+{
+ return NULL;
+}
+EXPORT_SYMBOL(clk_get_parent);
+
unsigned long clk_get_rate(struct clk *clk)
{
if (!clk)
diff --git a/arch/mips/generic/yamon-dt.c b/arch/mips/generic/yamon-dt.c
index a3aa22c..a07a5ed 100644
--- a/arch/mips/generic/yamon-dt.c
+++ b/arch/mips/generic/yamon-dt.c
@@ -75,7 +75,7 @@
__init int yamon_dt_append_memory(void *fdt,
const struct yamon_mem_region *regions)
{
- unsigned long phys_memsize, memsize;
+ unsigned long phys_memsize = 0, memsize;
__be32 mem_array[2 * MAX_MEM_ARRAY_ENTRIES];
unsigned int mem_entries;
int i, err, mem_off;
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index 70e32de..72d02d36 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -387,3 +387,4 @@
446 n32 landlock_restrict_self sys_landlock_restrict_self
# 447 reserved for memfd_secret
448 n32 process_mrelease sys_process_mrelease
+449 n32 futex_waitv sys_futex_waitv
diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl
index 1ca7bc3..e2c481f 100644
--- a/arch/mips/kernel/syscalls/syscall_n64.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n64.tbl
@@ -363,3 +363,4 @@
446 n64 landlock_restrict_self sys_landlock_restrict_self
# 447 reserved for memfd_secret
448 n64 process_mrelease sys_process_mrelease
+449 n64 futex_waitv sys_futex_waitv
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index a61c35e..3714c97 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -436,3 +436,4 @@
446 o32 landlock_restrict_self sys_landlock_restrict_self
# 447 reserved for memfd_secret
448 o32 process_mrelease sys_process_mrelease
+449 o32 futex_waitv sys_futex_waitv
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index 562aa87..aa20d07 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -1067,7 +1067,7 @@
r = 1;
break;
case KVM_CAP_NR_VCPUS:
- r = num_online_cpus();
+ r = min_t(unsigned int, num_online_cpus(), KVM_MAX_VCPUS);
break;
case KVM_CAP_MAX_VCPUS:
r = KVM_MAX_VCPUS;
diff --git a/arch/mips/lantiq/clk.c b/arch/mips/lantiq/clk.c
index dd819e3..4916ccc 100644
--- a/arch/mips/lantiq/clk.c
+++ b/arch/mips/lantiq/clk.c
@@ -158,6 +158,12 @@
}
EXPORT_SYMBOL(clk_deactivate);
+struct clk *clk_get_parent(struct clk *clk)
+{
+ return NULL;
+}
+EXPORT_SYMBOL(clk_get_parent);
+
static inline u32 get_counter_resolution(void)
{
u32 res;
diff --git a/arch/parisc/configs/generic-32bit_defconfig b/arch/parisc/configs/generic-32bit_defconfig
index d6fd8fa..53061cb 100644
--- a/arch/parisc/configs/generic-32bit_defconfig
+++ b/arch/parisc/configs/generic-32bit_defconfig
@@ -231,6 +231,7 @@
CONFIG_CRC_CCITT=m
CONFIG_CRC_T10DIF=y
CONFIG_FONTS=y
+CONFIG_PRINTK_TIME=y
CONFIG_MAGIC_SYSRQ=y
CONFIG_DEBUG_FS=y
CONFIG_DEBUG_MEMORY_INIT=y
diff --git a/arch/parisc/include/asm/assembly.h b/arch/parisc/include/asm/assembly.h
index 7085df0..39e7985 100644
--- a/arch/parisc/include/asm/assembly.h
+++ b/arch/parisc/include/asm/assembly.h
@@ -3,38 +3,19 @@
* Copyright (C) 1999 Hewlett-Packard (Frank Rowand)
* Copyright (C) 1999 Philipp Rumpf <prumpf@tux.org>
* Copyright (C) 1999 SuSE GmbH
+ * Copyright (C) 2021 Helge Deller <deller@gmx.de>
*/
#ifndef _PARISC_ASSEMBLY_H
#define _PARISC_ASSEMBLY_H
-#define CALLEE_FLOAT_FRAME_SIZE 80
-
#ifdef CONFIG_64BIT
-#define LDREG ldd
-#define STREG std
-#define LDREGX ldd,s
-#define LDREGM ldd,mb
-#define STREGM std,ma
-#define SHRREG shrd
-#define SHLREG shld
-#define ANDCM andcm,*
-#define COND(x) * ## x
#define RP_OFFSET 16
#define FRAME_SIZE 128
#define CALLEE_REG_FRAME_SIZE 144
#define REG_SZ 8
#define ASM_ULONG_INSN .dword
#else /* CONFIG_64BIT */
-#define LDREG ldw
-#define STREG stw
-#define LDREGX ldwx,s
-#define LDREGM ldwm
-#define STREGM stwm
-#define SHRREG shr
-#define SHLREG shlw
-#define ANDCM andcm
-#define COND(x) x
#define RP_OFFSET 20
#define FRAME_SIZE 64
#define CALLEE_REG_FRAME_SIZE 128
@@ -45,6 +26,7 @@
/* Frame alignment for 32- and 64-bit */
#define FRAME_ALIGN 64
+#define CALLEE_FLOAT_FRAME_SIZE 80
#define CALLEE_SAVE_FRAME_SIZE (CALLEE_REG_FRAME_SIZE + CALLEE_FLOAT_FRAME_SIZE)
#ifdef CONFIG_PA20
@@ -68,6 +50,28 @@
#ifdef __ASSEMBLY__
#ifdef CONFIG_64BIT
+#define LDREG ldd
+#define STREG std
+#define LDREGX ldd,s
+#define LDREGM ldd,mb
+#define STREGM std,ma
+#define SHRREG shrd
+#define SHLREG shld
+#define ANDCM andcm,*
+#define COND(x) * ## x
+#else /* CONFIG_64BIT */
+#define LDREG ldw
+#define STREG stw
+#define LDREGX ldwx,s
+#define LDREGM ldwm
+#define STREGM stwm
+#define SHRREG shr
+#define SHLREG shlw
+#define ANDCM andcm
+#define COND(x) x
+#endif
+
+#ifdef CONFIG_64BIT
/* the 64-bit pa gnu assembler unfortunately defaults to .level 1.1 or 2.0 so
* work around that for now... */
.level 2.0w
diff --git a/arch/parisc/include/asm/jump_label.h b/arch/parisc/include/asm/jump_label.h
index 7efb1aa..af2a598 100644
--- a/arch/parisc/include/asm/jump_label.h
+++ b/arch/parisc/include/asm/jump_label.h
@@ -5,6 +5,7 @@
#ifndef __ASSEMBLY__
#include <linux/types.h>
+#include <linux/stringify.h>
#include <asm/assembly.h>
#define JUMP_LABEL_NOP_SIZE 4
diff --git a/arch/parisc/include/asm/rt_sigframe.h b/arch/parisc/include/asm/rt_sigframe.h
index 4b9e3d7..2b3010a 100644
--- a/arch/parisc/include/asm/rt_sigframe.h
+++ b/arch/parisc/include/asm/rt_sigframe.h
@@ -2,7 +2,7 @@
#ifndef _ASM_PARISC_RT_SIGFRAME_H
#define _ASM_PARISC_RT_SIGFRAME_H
-#define SIGRETURN_TRAMP 3
+#define SIGRETURN_TRAMP 4
#define SIGRESTARTBLOCK_TRAMP 5
#define TRAMP_SIZE (SIGRETURN_TRAMP + SIGRESTARTBLOCK_TRAMP)
diff --git a/arch/parisc/kernel/signal.c b/arch/parisc/kernel/signal.c
index bbfe23c..46b1050 100644
--- a/arch/parisc/kernel/signal.c
+++ b/arch/parisc/kernel/signal.c
@@ -288,21 +288,22 @@
already in userspace. The first words of tramp are used to
save the previous sigrestartblock trampoline that might be
on the stack. We start the sigreturn trampoline at
- SIGRESTARTBLOCK_TRAMP. */
+ SIGRESTARTBLOCK_TRAMP+X. */
err |= __put_user(in_syscall ? INSN_LDI_R25_1 : INSN_LDI_R25_0,
&frame->tramp[SIGRESTARTBLOCK_TRAMP+0]);
- err |= __put_user(INSN_BLE_SR2_R0,
+ err |= __put_user(INSN_LDI_R20,
&frame->tramp[SIGRESTARTBLOCK_TRAMP+1]);
- err |= __put_user(INSN_LDI_R20,
+ err |= __put_user(INSN_BLE_SR2_R0,
&frame->tramp[SIGRESTARTBLOCK_TRAMP+2]);
+ err |= __put_user(INSN_NOP, &frame->tramp[SIGRESTARTBLOCK_TRAMP+3]);
- start = (unsigned long) &frame->tramp[SIGRESTARTBLOCK_TRAMP+0];
- end = (unsigned long) &frame->tramp[SIGRESTARTBLOCK_TRAMP+3];
+ start = (unsigned long) &frame->tramp[0];
+ end = (unsigned long) &frame->tramp[TRAMP_SIZE];
flush_user_dcache_range_asm(start, end);
flush_user_icache_range_asm(start, end);
/* TRAMP Words 0-4, Length 5 = SIGRESTARTBLOCK_TRAMP
- * TRAMP Words 5-7, Length 3 = SIGRETURN_TRAMP
+ * TRAMP Words 5-9, Length 4 = SIGRETURN_TRAMP
* So the SIGRETURN_TRAMP is at the end of SIGRESTARTBLOCK_TRAMP
*/
rp = (unsigned long) &frame->tramp[SIGRESTARTBLOCK_TRAMP];
diff --git a/arch/parisc/kernel/signal32.h b/arch/parisc/kernel/signal32.h
index a5bdbb56..f166250 100644
--- a/arch/parisc/kernel/signal32.h
+++ b/arch/parisc/kernel/signal32.h
@@ -36,7 +36,7 @@
compat_int_t rf_sar;
};
-#define COMPAT_SIGRETURN_TRAMP 3
+#define COMPAT_SIGRETURN_TRAMP 4
#define COMPAT_SIGRESTARTBLOCK_TRAMP 5
#define COMPAT_TRAMP_SIZE (COMPAT_SIGRETURN_TRAMP + \
COMPAT_SIGRESTARTBLOCK_TRAMP)
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index bf751e0..358c000 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -446,3 +446,4 @@
446 common landlock_restrict_self sys_landlock_restrict_self
# 447 reserved for memfd_secret
448 common process_mrelease sys_process_mrelease
+449 common futex_waitv sys_futex_waitv
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index 00a9c9c..3e053e2 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -1063,7 +1063,7 @@
* We kill the task with a SIGSEGV in this situation.
*/
if (do_setcontext(new_ctx, regs, 0)) {
- force_fatal_sig(SIGSEGV);
+ force_exit_sig(SIGSEGV);
return -EFAULT;
}
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index ef51853..d1e1fc0 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -704,7 +704,7 @@
*/
if (__get_user_sigset(&set, &new_ctx->uc_sigmask)) {
- force_fatal_sig(SIGSEGV);
+ force_exit_sig(SIGSEGV);
return -EFAULT;
}
set_current_blocked(&set);
@@ -713,7 +713,7 @@
return -EFAULT;
if (__unsafe_restore_sigcontext(current, NULL, 0, &new_ctx->uc_mcontext)) {
user_read_access_end();
- force_fatal_sig(SIGSEGV);
+ force_exit_sig(SIGSEGV);
return -EFAULT;
}
user_read_access_end();
diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c
index f9ea0e5..3fa6d24 100644
--- a/arch/powerpc/kernel/watchdog.c
+++ b/arch/powerpc/kernel/watchdog.c
@@ -187,6 +187,12 @@
if (sysctl_hardlockup_all_cpu_backtrace)
trigger_allbutself_cpu_backtrace();
+ /*
+ * Force flush any remote buffers that might be stuck in IRQ context
+ * and therefore could not run their irq_work.
+ */
+ printk_trigger_flush();
+
if (hardlockup_panic)
nmi_panic(NULL, "Hard LOCKUP");
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 35e9ccc..a72920f 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -641,9 +641,9 @@
* implementations just count online CPUs.
*/
if (hv_enabled)
- r = num_present_cpus();
+ r = min_t(unsigned int, num_present_cpus(), KVM_MAX_VCPUS);
else
- r = num_online_cpus();
+ r = min_t(unsigned int, num_online_cpus(), KVM_MAX_VCPUS);
break;
case KVM_CAP_MAX_VCPUS:
r = KVM_MAX_VCPUS;
diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
index 5927c94..8a107ed 100644
--- a/arch/riscv/Makefile
+++ b/arch/riscv/Makefile
@@ -107,11 +107,13 @@
vdso_install:
$(Q)$(MAKE) $(build)=arch/riscv/kernel/vdso $@
+ifeq ($(KBUILD_EXTMOD),)
ifeq ($(CONFIG_MMU),y)
prepare: vdso_prepare
vdso_prepare: prepare0
$(Q)$(MAKE) $(build)=arch/riscv/kernel/vdso include/generated/vdso-offsets.h
endif
+endif
ifneq ($(CONFIG_XIP_KERNEL),y)
ifeq ($(CONFIG_RISCV_M_MODE)$(CONFIG_SOC_CANAAN),yy)
diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig
index c252fd5..ef473e2 100644
--- a/arch/riscv/configs/defconfig
+++ b/arch/riscv/configs/defconfig
@@ -19,6 +19,8 @@
CONFIG_SOC_MICROCHIP_POLARFIRE=y
CONFIG_SMP=y
CONFIG_HOTPLUG_CPU=y
+CONFIG_VIRTUALIZATION=y
+CONFIG_KVM=m
CONFIG_JUMP_LABEL=y
CONFIG_MODULES=y
CONFIG_MODULE_UNLOAD=y
diff --git a/arch/riscv/configs/rv32_defconfig b/arch/riscv/configs/rv32_defconfig
index 434ef5b..6e9f12f 100644
--- a/arch/riscv/configs/rv32_defconfig
+++ b/arch/riscv/configs/rv32_defconfig
@@ -19,6 +19,8 @@
CONFIG_ARCH_RV32I=y
CONFIG_SMP=y
CONFIG_HOTPLUG_CPU=y
+CONFIG_VIRTUALIZATION=y
+CONFIG_KVM=m
CONFIG_JUMP_LABEL=y
CONFIG_MODULES=y
CONFIG_MODULE_UNLOAD=y
diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c
index e3d3aed..fb84619 100644
--- a/arch/riscv/kvm/vcpu.c
+++ b/arch/riscv/kvm/vcpu.c
@@ -740,7 +740,7 @@
* Ensure we set mode to IN_GUEST_MODE after we disable
* interrupts and before the final VCPU requests check.
* See the comment in kvm_vcpu_exiting_guest_mode() and
- * Documentation/virtual/kvm/vcpu-requests.rst
+ * Documentation/virt/kvm/vcpu-requests.rst
*/
vcpu->mode = IN_GUEST_MODE;
diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c
index eb3c045..3b0e703 100644
--- a/arch/riscv/kvm/vcpu_sbi.c
+++ b/arch/riscv/kvm/vcpu_sbi.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/**
+/*
* Copyright (c) 2019 Western Digital Corporation or its affiliates.
*
* Authors:
diff --git a/arch/riscv/kvm/vm.c b/arch/riscv/kvm/vm.c
index 26399df..fb18af3 100644
--- a/arch/riscv/kvm/vm.c
+++ b/arch/riscv/kvm/vm.c
@@ -74,7 +74,7 @@
r = 1;
break;
case KVM_CAP_NR_VCPUS:
- r = num_online_cpus();
+ r = min_t(unsigned int, num_online_cpus(), KVM_MAX_VCPUS);
break;
case KVM_CAP_MAX_VCPUS:
r = KVM_MAX_VCPUS;
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 8857ec3..2a5bb4f 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -47,7 +47,7 @@
config KASAN_SHADOW_OFFSET
hex
depends on KASAN
- default 0x18000000000000
+ default 0x1C000000000000
config S390
def_bool y
@@ -194,6 +194,7 @@
select HAVE_RELIABLE_STACKTRACE
select HAVE_RSEQ
select HAVE_SAMPLE_FTRACE_DIRECT
+ select HAVE_SAMPLE_FTRACE_DIRECT_MULTI
select HAVE_SOFTIRQ_ON_OWN_STACK
select HAVE_SYSCALL_TRACEPOINTS
select HAVE_VIRT_CPU_ACCOUNTING
diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index 69c45f6..609e369 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -77,10 +77,12 @@
KBUILD_CFLAGS_DECOMPRESSOR += $(cflags-y)
ifneq ($(call cc-option,-mstack-size=8192 -mstack-guard=128),)
-cflags-$(CONFIG_CHECK_STACK) += -mstack-size=$(STACK_SIZE)
-ifeq ($(call cc-option,-mstack-size=8192),)
-cflags-$(CONFIG_CHECK_STACK) += -mstack-guard=$(CONFIG_STACK_GUARD)
-endif
+ CC_FLAGS_CHECK_STACK := -mstack-size=$(STACK_SIZE)
+ ifeq ($(call cc-option,-mstack-size=8192),)
+ CC_FLAGS_CHECK_STACK += -mstack-guard=$(CONFIG_STACK_GUARD)
+ endif
+ export CC_FLAGS_CHECK_STACK
+ cflags-$(CONFIG_CHECK_STACK) += $(CC_FLAGS_CHECK_STACK)
endif
ifdef CONFIG_EXPOLINE
diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
index 7571dee..1aa11a8 100644
--- a/arch/s390/boot/startup.c
+++ b/arch/s390/boot/startup.c
@@ -149,82 +149,56 @@
static void setup_kernel_memory_layout(void)
{
- bool vmalloc_size_verified = false;
- unsigned long vmemmap_off;
- unsigned long vspace_left;
+ unsigned long vmemmap_start;
unsigned long rte_size;
unsigned long pages;
- unsigned long vmax;
pages = ident_map_size / PAGE_SIZE;
/* vmemmap contains a multiple of PAGES_PER_SECTION struct pages */
vmemmap_size = SECTION_ALIGN_UP(pages) * sizeof(struct page);
/* choose kernel address space layout: 4 or 3 levels. */
- vmemmap_off = round_up(ident_map_size, _REGION3_SIZE);
+ vmemmap_start = round_up(ident_map_size, _REGION3_SIZE);
if (IS_ENABLED(CONFIG_KASAN) ||
vmalloc_size > _REGION2_SIZE ||
- vmemmap_off + vmemmap_size + vmalloc_size + MODULES_LEN > _REGION2_SIZE)
- vmax = _REGION1_SIZE;
- else
- vmax = _REGION2_SIZE;
-
- /* keep vmemmap_off aligned to a top level region table entry */
- rte_size = vmax == _REGION1_SIZE ? _REGION2_SIZE : _REGION3_SIZE;
- MODULES_END = vmax;
- if (is_prot_virt_host()) {
- /*
- * forcing modules and vmalloc area under the ultravisor
- * secure storage limit, so that any vmalloc allocation
- * we do could be used to back secure guest storage.
- */
- adjust_to_uv_max(&MODULES_END);
- }
-
-#ifdef CONFIG_KASAN
- if (MODULES_END < vmax) {
- /* force vmalloc and modules below kasan shadow */
- MODULES_END = min(MODULES_END, KASAN_SHADOW_START);
+ vmemmap_start + vmemmap_size + vmalloc_size + MODULES_LEN >
+ _REGION2_SIZE) {
+ MODULES_END = _REGION1_SIZE;
+ rte_size = _REGION2_SIZE;
} else {
- /*
- * leave vmalloc and modules above kasan shadow but make
- * sure they don't overlap with it
- */
- vmalloc_size = min(vmalloc_size, vmax - KASAN_SHADOW_END - MODULES_LEN);
- vmalloc_size_verified = true;
- vspace_left = KASAN_SHADOW_START;
+ MODULES_END = _REGION2_SIZE;
+ rte_size = _REGION3_SIZE;
}
+ /*
+ * forcing modules and vmalloc area under the ultravisor
+ * secure storage limit, so that any vmalloc allocation
+ * we do could be used to back secure guest storage.
+ */
+ adjust_to_uv_max(&MODULES_END);
+#ifdef CONFIG_KASAN
+ /* force vmalloc and modules below kasan shadow */
+ MODULES_END = min(MODULES_END, KASAN_SHADOW_START);
#endif
MODULES_VADDR = MODULES_END - MODULES_LEN;
VMALLOC_END = MODULES_VADDR;
- if (vmalloc_size_verified) {
- VMALLOC_START = VMALLOC_END - vmalloc_size;
- } else {
- vmemmap_off = round_up(ident_map_size, rte_size);
+ /* allow vmalloc area to occupy up to about 1/2 of the rest virtual space left */
+ vmalloc_size = min(vmalloc_size, round_down(VMALLOC_END / 2, _REGION3_SIZE));
+ VMALLOC_START = VMALLOC_END - vmalloc_size;
- if (vmemmap_off + vmemmap_size > VMALLOC_END ||
- vmalloc_size > VMALLOC_END - vmemmap_off - vmemmap_size) {
- /*
- * allow vmalloc area to occupy up to 1/2 of
- * the rest virtual space left.
- */
- vmalloc_size = min(vmalloc_size, VMALLOC_END / 2);
- }
- VMALLOC_START = VMALLOC_END - vmalloc_size;
- vspace_left = VMALLOC_START;
- }
-
- pages = vspace_left / (PAGE_SIZE + sizeof(struct page));
+ /* split remaining virtual space between 1:1 mapping & vmemmap array */
+ pages = VMALLOC_START / (PAGE_SIZE + sizeof(struct page));
pages = SECTION_ALIGN_UP(pages);
- vmemmap_off = round_up(vspace_left - pages * sizeof(struct page), rte_size);
- /* keep vmemmap left most starting from a fresh region table entry */
- vmemmap_off = min(vmemmap_off, round_up(ident_map_size, rte_size));
- /* take care that identity map is lower then vmemmap */
- ident_map_size = min(ident_map_size, vmemmap_off);
+ /* keep vmemmap_start aligned to a top level region table entry */
+ vmemmap_start = round_down(VMALLOC_START - pages * sizeof(struct page), rte_size);
+ /* vmemmap_start is the future VMEM_MAX_PHYS, make sure it is within MAX_PHYSMEM */
+ vmemmap_start = min(vmemmap_start, 1UL << MAX_PHYSMEM_BITS);
+ /* make sure identity map doesn't overlay with vmemmap */
+ ident_map_size = min(ident_map_size, vmemmap_start);
vmemmap_size = SECTION_ALIGN_UP(ident_map_size / PAGE_SIZE) * sizeof(struct page);
- VMALLOC_START = max(vmemmap_off + vmemmap_size, VMALLOC_START);
- vmemmap = (struct page *)vmemmap_off;
+ /* make sure vmemmap doesn't overlay with vmalloc area */
+ VMALLOC_START = max(vmemmap_start + vmemmap_size, VMALLOC_START);
+ vmemmap = (struct page *)vmemmap_start;
}
/*
diff --git a/arch/s390/include/asm/kexec.h b/arch/s390/include/asm/kexec.h
index ea398a0..7f3c9ac 100644
--- a/arch/s390/include/asm/kexec.h
+++ b/arch/s390/include/asm/kexec.h
@@ -74,6 +74,12 @@
int arch_kexec_do_relocs(int r_type, void *loc, unsigned long val,
unsigned long addr);
+#define ARCH_HAS_KIMAGE_ARCH
+
+struct kimage_arch {
+ void *ipl_buf;
+};
+
extern const struct kexec_file_ops s390_kexec_image_ops;
extern const struct kexec_file_ops s390_kexec_elf_ops;
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index d72a6df..785d54c 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -191,8 +191,8 @@
return rc;
} else {
/* Check for swapped kdump oldmem areas */
- if (oldmem_data.start && from - oldmem_data.size < oldmem_data.size) {
- from -= oldmem_data.size;
+ if (oldmem_data.start && from - oldmem_data.start < oldmem_data.size) {
+ from -= oldmem_data.start;
len = min(count, oldmem_data.size - from);
} else if (oldmem_data.start && from < oldmem_data.size) {
len = min(count, oldmem_data.size - from);
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index e2cc357..5ad1dde 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -2156,7 +2156,7 @@
buf = vzalloc(report->size);
if (!buf)
- return ERR_PTR(-ENOMEM);
+ goto out;
ptr = buf;
memcpy(ptr, report->ipib, report->ipib->hdr.len);
@@ -2195,6 +2195,7 @@
}
BUG_ON(ptr > buf + report->size);
+out:
return buf;
}
diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c
index 528edff..9975ad2 100644
--- a/arch/s390/kernel/machine_kexec_file.c
+++ b/arch/s390/kernel/machine_kexec_file.c
@@ -12,6 +12,7 @@
#include <linux/kexec.h>
#include <linux/module_signature.h>
#include <linux/verification.h>
+#include <linux/vmalloc.h>
#include <asm/boot_data.h>
#include <asm/ipl.h>
#include <asm/setup.h>
@@ -170,6 +171,7 @@
struct kexec_buf buf;
unsigned long addr;
void *ptr, *end;
+ int ret;
buf.image = image;
@@ -199,9 +201,13 @@
ptr += len;
}
+ ret = -ENOMEM;
buf.buffer = ipl_report_finish(data->report);
+ if (!buf.buffer)
+ goto out;
buf.bufsz = data->report->size;
buf.memsz = buf.bufsz;
+ image->arch.ipl_buf = buf.buffer;
data->memsz += buf.memsz;
@@ -209,7 +215,9 @@
data->kernel_buf + offsetof(struct lowcore, ipl_parmblock_ptr);
*lc_ipl_parmblock_ptr = (__u32)buf.mem;
- return kexec_add_buffer(&buf);
+ ret = kexec_add_buffer(&buf);
+out:
+ return ret;
}
void *kexec_file_add_components(struct kimage *image,
@@ -322,3 +330,11 @@
}
return 0;
}
+
+int arch_kimage_file_post_load_cleanup(struct kimage *image)
+{
+ vfree(image->arch.ipl_buf);
+ image->arch.ipl_buf = NULL;
+
+ return kexec_image_post_load_cleanup_default(image);
+}
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 40405f2..225ab2d 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -606,7 +606,7 @@
static void __init setup_memory_end(void)
{
- memblock_remove(ident_map_size, ULONG_MAX);
+ memblock_remove(ident_map_size, PHYS_ADDR_MAX - ident_map_size);
max_pfn = max_low_pfn = PFN_DOWN(ident_map_size);
pr_notice("The maximum memory size is %luMB\n", ident_map_size >> 20);
}
@@ -638,14 +638,6 @@
#endif
/*
- * Make sure that the area above identity mapping is protected
- */
-static void __init reserve_above_ident_map(void)
-{
- memblock_reserve(ident_map_size, ULONG_MAX);
-}
-
-/*
* Reserve memory for kdump kernel to be loaded with kexec
*/
static void __init reserve_crashkernel(void)
@@ -785,7 +777,6 @@
}
memblock_set_bottom_up(false);
memblock_set_node(0, ULONG_MAX, &memblock.memory, 0);
- memblock_dump_all();
}
/*
@@ -826,9 +817,6 @@
storage_key_init_range(start, end);
psw_set_key(PAGE_DEFAULT_KEY);
-
- /* Only cosmetics */
- memblock_enforce_memory_limit(memblock_end_of_DRAM());
}
static void __init relocate_amode31_section(void)
@@ -999,24 +987,24 @@
setup_control_program_code();
/* Do some memory reservations *before* memory is added to memblock */
- reserve_above_ident_map();
reserve_kernel();
reserve_initrd();
reserve_certificate_list();
reserve_mem_detect_info();
+ memblock_set_current_limit(ident_map_size);
memblock_allow_resize();
/* Get information about *all* installed memory */
memblock_add_mem_detect_info();
free_mem_detect_info();
+ setup_memory_end();
+ memblock_dump_all();
+ setup_memory();
relocate_amode31_section();
setup_cr();
-
setup_uv();
- setup_memory_end();
- setup_memory();
dma_contiguous_reserve(ident_map_size);
vmcp_cma_reserve();
if (MACHINE_HAS_EDAT2)
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index df5261e..ed9c5c2 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -451,3 +451,4 @@
446 common landlock_restrict_self sys_landlock_restrict_self sys_landlock_restrict_self
# 447 reserved for memfd_secret
448 common process_mrelease sys_process_mrelease sys_process_mrelease
+449 common futex_waitv sys_futex_waitv sys_futex_waitv
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index 035705c..2b78078 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -84,7 +84,7 @@
{
if (user_mode(regs)) {
report_user_fault(regs, SIGSEGV, 0);
- force_fatal_sig(SIGSEGV);
+ force_exit_sig(SIGSEGV);
} else
die(regs, "Unknown program exception");
}
diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile
index e3e6ac5..245bddf 100644
--- a/arch/s390/kernel/vdso32/Makefile
+++ b/arch/s390/kernel/vdso32/Makefile
@@ -22,7 +22,7 @@
KBUILD_CFLAGS_32 := $(filter-out -m64,$(KBUILD_CFLAGS))
KBUILD_CFLAGS_32 += -m31 -fPIC -shared -fno-common -fno-builtin
-LDFLAGS_vdso32.so.dbg += -fPIC -shared -nostdlib -soname=linux-vdso32.so.1 \
+LDFLAGS_vdso32.so.dbg += -fPIC -shared -soname=linux-vdso32.so.1 \
--hash-style=both --build-id=sha1 -melf_s390 -T
$(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_32)
diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile
index 6568de2..9e2b95a 100644
--- a/arch/s390/kernel/vdso64/Makefile
+++ b/arch/s390/kernel/vdso64/Makefile
@@ -8,8 +8,9 @@
include $(srctree)/lib/vdso/Makefile
obj-vdso64 = vdso_user_wrapper.o note.o
obj-cvdso64 = vdso64_generic.o getcpu.o
-CFLAGS_REMOVE_getcpu.o = -pg $(CC_FLAGS_FTRACE) $(CC_FLAGS_EXPOLINE)
-CFLAGS_REMOVE_vdso64_generic.o = -pg $(CC_FLAGS_FTRACE) $(CC_FLAGS_EXPOLINE)
+VDSO_CFLAGS_REMOVE := -pg $(CC_FLAGS_FTRACE) $(CC_FLAGS_EXPOLINE) $(CC_FLAGS_CHECK_STACK)
+CFLAGS_REMOVE_getcpu.o = $(VDSO_CFLAGS_REMOVE)
+CFLAGS_REMOVE_vdso64_generic.o = $(VDSO_CFLAGS_REMOVE)
# Build rules
@@ -25,7 +26,7 @@
KBUILD_CFLAGS_64 := $(filter-out -m64,$(KBUILD_CFLAGS))
KBUILD_CFLAGS_64 += -m64 -fPIC -shared -fno-common -fno-builtin
-ldflags-y := -fPIC -shared -nostdlib -soname=linux-vdso64.so.1 \
+ldflags-y := -fPIC -shared -soname=linux-vdso64.so.1 \
--hash-style=both --build-id=sha1 -T
$(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_64)
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index c6257f6..14a18ba 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -585,6 +585,8 @@
r = KVM_MAX_VCPUS;
else if (sclp.has_esca && sclp.has_64bscao)
r = KVM_S390_ESCA_CPU_SLOTS;
+ if (ext == KVM_CAP_NR_VCPUS)
+ r = min_t(unsigned int, num_online_cpus(), r);
break;
case KVM_CAP_S390_COW:
r = MACHINE_HAS_ESOP;
diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c
index cd677bc..ffab163 100644
--- a/arch/sparc/kernel/signal_32.c
+++ b/arch/sparc/kernel/signal_32.c
@@ -244,7 +244,7 @@
get_sigframe(ksig, regs, sigframe_size);
if (invalid_frame_pointer(sf, sigframe_size)) {
- force_fatal_sig(SIGILL);
+ force_exit_sig(SIGILL);
return -EINVAL;
}
@@ -336,7 +336,7 @@
sf = (struct rt_signal_frame __user *)
get_sigframe(ksig, regs, sigframe_size);
if (invalid_frame_pointer(sf, sigframe_size)) {
- force_fatal_sig(SIGILL);
+ force_exit_sig(SIGILL);
return -EINVAL;
}
diff --git a/arch/sparc/kernel/windows.c b/arch/sparc/kernel/windows.c
index bbbd40c..8f20862 100644
--- a/arch/sparc/kernel/windows.c
+++ b/arch/sparc/kernel/windows.c
@@ -122,7 +122,7 @@
if ((sp & 7) ||
copy_to_user((char __user *) sp, &tp->reg_window[window],
sizeof(struct reg_window32))) {
- force_fatal_sig(SIGILL);
+ force_exit_sig(SIGILL);
return;
}
}
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 95dd1ee..7399327 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -193,7 +193,7 @@
select HAVE_DYNAMIC_FTRACE_WITH_ARGS if X86_64
select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
select HAVE_SAMPLE_FTRACE_DIRECT if X86_64
- select HAVE_SAMPLE_FTRACE_MULTI_DIRECT if X86_64
+ select HAVE_SAMPLE_FTRACE_DIRECT_MULTI if X86_64
select HAVE_EBPF_JIT
select HAVE_EFFICIENT_UNALIGNED_ACCESS
select HAVE_EISA
diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
index 0b6b277..fd2ee94 100644
--- a/arch/x86/entry/vsyscall/vsyscall_64.c
+++ b/arch/x86/entry/vsyscall/vsyscall_64.c
@@ -226,7 +226,7 @@
if ((!tmp && regs->orig_ax != syscall_nr) || regs->ip != address) {
warn_bad_vsyscall(KERN_DEBUG, regs,
"seccomp tried to change syscall nr or ip");
- force_fatal_sig(SIGSYS);
+ force_exit_sig(SIGSYS);
return true;
}
regs->orig_ax = -1;
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 24f4a06..96eb7db 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -177,6 +177,9 @@
return;
}
+ if (!hv_vp_index)
+ return;
+
hv_reenlightenment_cb = cb;
/* Make sure callback is registered before we write to MSRs */
@@ -383,20 +386,13 @@
*/
void __init hyperv_init(void)
{
- u64 guest_id, required_msrs;
+ u64 guest_id;
union hv_x64_msr_hypercall_contents hypercall_msr;
int cpuhp;
if (x86_hyper_type != X86_HYPER_MS_HYPERV)
return;
- /* Absolutely required MSRs */
- required_msrs = HV_MSR_HYPERCALL_AVAILABLE |
- HV_MSR_VP_INDEX_AVAILABLE;
-
- if ((ms_hyperv.features & required_msrs) != required_msrs)
- return;
-
if (hv_common_init())
return;
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index e5d8700..6ac61f8 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -363,6 +363,7 @@
unsigned int cr4_smap:1;
unsigned int cr4_smep:1;
unsigned int cr4_la57:1;
+ unsigned int efer_lma:1;
};
};
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 4794b71..ff55df6 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -163,12 +163,22 @@
cpuid(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS,
&eax, &hyp_signature[0], &hyp_signature[1], &hyp_signature[2]);
- if (eax >= HYPERV_CPUID_MIN &&
- eax <= HYPERV_CPUID_MAX &&
- !memcmp("Microsoft Hv", hyp_signature, 12))
- return HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS;
+ if (eax < HYPERV_CPUID_MIN || eax > HYPERV_CPUID_MAX ||
+ memcmp("Microsoft Hv", hyp_signature, 12))
+ return 0;
- return 0;
+ /* HYPERCALL and VP_INDEX MSRs are mandatory for all features. */
+ eax = cpuid_eax(HYPERV_CPUID_FEATURES);
+ if (!(eax & HV_MSR_HYPERCALL_AVAILABLE)) {
+ pr_warn("x86/hyperv: HYPERCALL MSR not available.\n");
+ return 0;
+ }
+ if (!(eax & HV_MSR_VP_INDEX_AVAILABLE)) {
+ pr_warn("x86/hyperv: VP_INDEX MSR not available.\n");
+ return 0;
+ }
+
+ return HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS;
}
static unsigned char hv_get_nmi_reason(void)
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index e9ee8b5..04143a6 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -964,6 +964,9 @@
struct unwind_state state;
unsigned long addr = 0;
+ if (!try_get_task_stack(p))
+ return 0;
+
for (unwind_start(&state, p, NULL, NULL); !unwind_done(&state);
unwind_next_frame(&state)) {
addr = unwind_get_return_address(&state);
@@ -974,6 +977,8 @@
break;
}
+ put_task_stack(p);
+
return addr;
}
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index cce1c89..c21bcd6 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -160,7 +160,7 @@
user_access_end();
Efault:
pr_alert("could not access userspace vm86 info\n");
- force_fatal_sig(SIGSEGV);
+ force_exit_sig(SIGSEGV);
goto exit_vm86;
}
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index e19dabf..07e9215 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -125,7 +125,7 @@
}
}
-struct kvm_cpuid_entry2 *kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu)
+static struct kvm_cpuid_entry2 *kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu)
{
u32 base = vcpu->arch.kvm_cpuid_base;
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 4a555f3..5e19e6e 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -2022,7 +2022,7 @@
{
bool longmode;
- longmode = is_64_bit_mode(vcpu);
+ longmode = is_64_bit_hypercall(vcpu);
if (longmode)
kvm_rax_write(vcpu, result);
else {
@@ -2171,7 +2171,7 @@
}
#ifdef CONFIG_X86_64
- if (is_64_bit_mode(vcpu)) {
+ if (is_64_bit_hypercall(vcpu)) {
hc.param = kvm_rcx_read(vcpu);
hc.ingpa = kvm_rdx_read(vcpu);
hc.outgpa = kvm_r8_read(vcpu);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 3379437..3be9bee 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4682,6 +4682,7 @@
/* PKEY and LA57 are active iff long mode is active. */
ext.cr4_pke = ____is_efer_lma(regs) && ____is_cr4_pke(regs);
ext.cr4_la57 = ____is_efer_lma(regs) && ____is_cr4_la57(regs);
+ ext.efer_lma = ____is_efer_lma(regs);
}
ext.valid = 1;
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 902c52a..21ac0a5 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -237,7 +237,6 @@
static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
{
struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
- bool es_active = argp->id == KVM_SEV_ES_INIT;
int asid, ret;
if (kvm->created_vcpus)
@@ -247,7 +246,8 @@
if (unlikely(sev->active))
return ret;
- sev->es_active = es_active;
+ sev->active = true;
+ sev->es_active = argp->id == KVM_SEV_ES_INIT;
asid = sev_asid_new(sev);
if (asid < 0)
goto e_no_asid;
@@ -257,8 +257,6 @@
if (ret)
goto e_free;
- sev->active = true;
- sev->asid = asid;
INIT_LIST_HEAD(&sev->regions_list);
return 0;
@@ -268,6 +266,7 @@
sev->asid = 0;
e_no_asid:
sev->es_active = false;
+ sev->active = false;
return ret;
}
@@ -1530,7 +1529,7 @@
return sev_issue_cmd(kvm, SEV_CMD_RECEIVE_FINISH, &data, &argp->error);
}
-static bool cmd_allowed_from_miror(u32 cmd_id)
+static bool is_cmd_allowed_from_mirror(u32 cmd_id)
{
/*
* Allow mirrors VM to call KVM_SEV_LAUNCH_UPDATE_VMSA to enable SEV-ES
@@ -1757,7 +1756,7 @@
/* Only the enc_context_owner handles some memory enc operations. */
if (is_mirroring_enc_context(kvm) &&
- !cmd_allowed_from_miror(sev_cmd.id)) {
+ !is_cmd_allowed_from_mirror(sev_cmd.id)) {
r = -EINVAL;
goto out;
}
@@ -1990,7 +1989,12 @@
mutex_unlock(&source_kvm->lock);
mutex_lock(&kvm->lock);
- if (sev_guest(kvm)) {
+ /*
+ * Disallow out-of-band SEV/SEV-ES init if the target is already an
+ * SEV guest, or if vCPUs have been created. KVM relies on vCPUs being
+ * created after SEV/SEV-ES initialization, e.g. to init intercepts.
+ */
+ if (sev_guest(kvm) || kvm->created_vcpus) {
ret = -EINVAL;
goto e_mirror_unlock;
}
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 437e685..5faad3d 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -247,7 +247,7 @@
#ifdef CONFIG_KVM_AMD_SEV
struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
- return sev_guest(kvm) && sev->es_active;
+ return sev->es_active && !WARN_ON_ONCE(!sev->active);
#else
return false;
#endif
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index b213ca9..1e2f669 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -670,33 +670,39 @@
static void nested_cache_shadow_vmcs12(struct kvm_vcpu *vcpu,
struct vmcs12 *vmcs12)
{
- struct kvm_host_map map;
- struct vmcs12 *shadow;
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ struct gfn_to_hva_cache *ghc = &vmx->nested.shadow_vmcs12_cache;
if (!nested_cpu_has_shadow_vmcs(vmcs12) ||
vmcs12->vmcs_link_pointer == INVALID_GPA)
return;
- shadow = get_shadow_vmcs12(vcpu);
-
- if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->vmcs_link_pointer), &map))
+ if (ghc->gpa != vmcs12->vmcs_link_pointer &&
+ kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc,
+ vmcs12->vmcs_link_pointer, VMCS12_SIZE))
return;
- memcpy(shadow, map.hva, VMCS12_SIZE);
- kvm_vcpu_unmap(vcpu, &map, false);
+ kvm_read_guest_cached(vmx->vcpu.kvm, ghc, get_shadow_vmcs12(vcpu),
+ VMCS12_SIZE);
}
static void nested_flush_cached_shadow_vmcs12(struct kvm_vcpu *vcpu,
struct vmcs12 *vmcs12)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
+ struct gfn_to_hva_cache *ghc = &vmx->nested.shadow_vmcs12_cache;
if (!nested_cpu_has_shadow_vmcs(vmcs12) ||
vmcs12->vmcs_link_pointer == INVALID_GPA)
return;
- kvm_write_guest(vmx->vcpu.kvm, vmcs12->vmcs_link_pointer,
- get_shadow_vmcs12(vcpu), VMCS12_SIZE);
+ if (ghc->gpa != vmcs12->vmcs_link_pointer &&
+ kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc,
+ vmcs12->vmcs_link_pointer, VMCS12_SIZE))
+ return;
+
+ kvm_write_guest_cached(vmx->vcpu.kvm, ghc, get_shadow_vmcs12(vcpu),
+ VMCS12_SIZE);
}
/*
@@ -2830,6 +2836,17 @@
return 0;
}
+static int nested_vmx_check_address_space_size(struct kvm_vcpu *vcpu,
+ struct vmcs12 *vmcs12)
+{
+#ifdef CONFIG_X86_64
+ if (CC(!!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE) !=
+ !!(vcpu->arch.efer & EFER_LMA)))
+ return -EINVAL;
+#endif
+ return 0;
+}
+
static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu,
struct vmcs12 *vmcs12)
{
@@ -2854,18 +2871,16 @@
return -EINVAL;
#ifdef CONFIG_X86_64
- ia32e = !!(vcpu->arch.efer & EFER_LMA);
+ ia32e = !!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE);
#else
ia32e = false;
#endif
if (ia32e) {
- if (CC(!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE)) ||
- CC(!(vmcs12->host_cr4 & X86_CR4_PAE)))
+ if (CC(!(vmcs12->host_cr4 & X86_CR4_PAE)))
return -EINVAL;
} else {
- if (CC(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE) ||
- CC(vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) ||
+ if (CC(vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) ||
CC(vmcs12->host_cr4 & X86_CR4_PCIDE) ||
CC((vmcs12->host_rip) >> 32))
return -EINVAL;
@@ -2910,9 +2925,9 @@
static int nested_vmx_check_vmcs_link_ptr(struct kvm_vcpu *vcpu,
struct vmcs12 *vmcs12)
{
- int r = 0;
- struct vmcs12 *shadow;
- struct kvm_host_map map;
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ struct gfn_to_hva_cache *ghc = &vmx->nested.shadow_vmcs12_cache;
+ struct vmcs_hdr hdr;
if (vmcs12->vmcs_link_pointer == INVALID_GPA)
return 0;
@@ -2920,17 +2935,21 @@
if (CC(!page_address_valid(vcpu, vmcs12->vmcs_link_pointer)))
return -EINVAL;
- if (CC(kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->vmcs_link_pointer), &map)))
+ if (ghc->gpa != vmcs12->vmcs_link_pointer &&
+ CC(kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc,
+ vmcs12->vmcs_link_pointer, VMCS12_SIZE)))
+ return -EINVAL;
+
+ if (CC(kvm_read_guest_offset_cached(vcpu->kvm, ghc, &hdr,
+ offsetof(struct vmcs12, hdr),
+ sizeof(hdr))))
return -EINVAL;
- shadow = map.hva;
+ if (CC(hdr.revision_id != VMCS12_REVISION) ||
+ CC(hdr.shadow_vmcs != nested_cpu_has_shadow_vmcs(vmcs12)))
+ return -EINVAL;
- if (CC(shadow->hdr.revision_id != VMCS12_REVISION) ||
- CC(shadow->hdr.shadow_vmcs != nested_cpu_has_shadow_vmcs(vmcs12)))
- r = -EINVAL;
-
- kvm_vcpu_unmap(vcpu, &map, false);
- return r;
+ return 0;
}
/*
@@ -3535,6 +3554,9 @@
if (nested_vmx_check_controls(vcpu, vmcs12))
return nested_vmx_fail(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
+ if (nested_vmx_check_address_space_size(vcpu, vmcs12))
+ return nested_vmx_fail(vcpu, VMXERR_ENTRY_INVALID_HOST_STATE_FIELD);
+
if (nested_vmx_check_host_state(vcpu, vmcs12))
return nested_vmx_fail(vcpu, VMXERR_ENTRY_INVALID_HOST_STATE_FIELD);
@@ -5264,10 +5286,11 @@
return 1;
if (vmx->nested.current_vmptr != vmptr) {
- struct kvm_host_map map;
- struct vmcs12 *new_vmcs12;
+ struct gfn_to_hva_cache *ghc = &vmx->nested.vmcs12_cache;
+ struct vmcs_hdr hdr;
- if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmptr), &map)) {
+ if (ghc->gpa != vmptr &&
+ kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, vmptr, VMCS12_SIZE)) {
/*
* Reads from an unbacked page return all 1s,
* which means that the 32 bits located at the
@@ -5278,12 +5301,16 @@
VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID);
}
- new_vmcs12 = map.hva;
+ if (kvm_read_guest_offset_cached(vcpu->kvm, ghc, &hdr,
+ offsetof(struct vmcs12, hdr),
+ sizeof(hdr))) {
+ return nested_vmx_fail(vcpu,
+ VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID);
+ }
- if (new_vmcs12->hdr.revision_id != VMCS12_REVISION ||
- (new_vmcs12->hdr.shadow_vmcs &&
+ if (hdr.revision_id != VMCS12_REVISION ||
+ (hdr.shadow_vmcs &&
!nested_cpu_has_vmx_shadow_vmcs(vcpu))) {
- kvm_vcpu_unmap(vcpu, &map, false);
return nested_vmx_fail(vcpu,
VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID);
}
@@ -5294,8 +5321,11 @@
* Load VMCS12 from guest memory since it is not already
* cached.
*/
- memcpy(vmx->nested.cached_vmcs12, new_vmcs12, VMCS12_SIZE);
- kvm_vcpu_unmap(vcpu, &map, false);
+ if (kvm_read_guest_cached(vcpu->kvm, ghc, vmx->nested.cached_vmcs12,
+ VMCS12_SIZE)) {
+ return nested_vmx_fail(vcpu,
+ VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID);
+ }
set_current_vmptr(vmx, vmptr);
}
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index a4ead60..4df2ac2 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -142,6 +142,16 @@
struct vmcs12 *cached_shadow_vmcs12;
/*
+ * GPA to HVA cache for accessing vmcs12->vmcs_link_pointer
+ */
+ struct gfn_to_hva_cache shadow_vmcs12_cache;
+
+ /*
+ * GPA to HVA cache for VMCS12
+ */
+ struct gfn_to_hva_cache vmcs12_cache;
+
+ /*
* Indicates if the shadow vmcs or enlightened vmcs must be updated
* with the data held by struct vmcs12.
*/
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index dc7eb5f..5a403d9 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3307,9 +3307,9 @@
"xor %1, %1\n"
"2:\n"
_ASM_EXTABLE_UA(1b, 2b)
- : "+r" (st_preempted),
- "+&r" (err)
- : "m" (st->preempted));
+ : "+q" (st_preempted),
+ "+&r" (err),
+ "+m" (st->preempted));
if (err)
goto out;
@@ -4179,7 +4179,7 @@
r = !static_call(kvm_x86_cpu_has_accelerated_tpr)();
break;
case KVM_CAP_NR_VCPUS:
- r = num_online_cpus();
+ r = min_t(unsigned int, num_online_cpus(), KVM_MAX_VCPUS);
break;
case KVM_CAP_MAX_VCPUS:
r = KVM_MAX_VCPUS;
@@ -8848,7 +8848,7 @@
trace_kvm_hypercall(nr, a0, a1, a2, a3);
- op_64_bit = is_64_bit_mode(vcpu);
+ op_64_bit = is_64_bit_hypercall(vcpu);
if (!op_64_bit) {
nr &= 0xFFFFFFFF;
a0 &= 0xFFFFFFFF;
@@ -9547,12 +9547,16 @@
if (!kvm_apic_hw_enabled(vcpu->arch.apic))
return;
- if (to_hv_vcpu(vcpu))
+ if (to_hv_vcpu(vcpu)) {
bitmap_or((ulong *)eoi_exit_bitmap,
vcpu->arch.ioapic_handled_vectors,
to_hv_synic(vcpu)->vec_bitmap, 256);
+ static_call(kvm_x86_load_eoi_exitmap)(vcpu, eoi_exit_bitmap);
+ return;
+ }
- static_call(kvm_x86_load_eoi_exitmap)(vcpu, eoi_exit_bitmap);
+ static_call(kvm_x86_load_eoi_exitmap)(
+ vcpu, (u64 *)vcpu->arch.ioapic_handled_vectors);
}
void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index ea264c4..997669a 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -153,12 +153,24 @@
{
int cs_db, cs_l;
+ WARN_ON_ONCE(vcpu->arch.guest_state_protected);
+
if (!is_long_mode(vcpu))
return false;
static_call(kvm_x86_get_cs_db_l_bits)(vcpu, &cs_db, &cs_l);
return cs_l;
}
+static inline bool is_64_bit_hypercall(struct kvm_vcpu *vcpu)
+{
+ /*
+ * If running with protected guest state, the CS register is not
+ * accessible. The hypercall register values will have had to been
+ * provided in 64-bit mode, so assume the guest is in 64-bit.
+ */
+ return vcpu->arch.guest_state_protected || is_64_bit_mode(vcpu);
+}
+
static inline bool x86_exception_has_error_code(unsigned int vector)
{
static u32 exception_has_error_code = BIT(DF_VECTOR) | BIT(TS_VECTOR) |
diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index 8f62bae..dff2bdf 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -127,9 +127,9 @@
state_entry_time = vx->runstate_entry_time;
state_entry_time |= XEN_RUNSTATE_UPDATE;
- BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->state_entry_time) !=
+ BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, state_entry_time) !=
sizeof(state_entry_time));
- BUILD_BUG_ON(sizeof(((struct compat_vcpu_runstate_info *)0)->state_entry_time) !=
+ BUILD_BUG_ON(sizeof_field(struct compat_vcpu_runstate_info, state_entry_time) !=
sizeof(state_entry_time));
if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache,
@@ -144,9 +144,9 @@
*/
BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, state) !=
offsetof(struct compat_vcpu_runstate_info, state));
- BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->state) !=
+ BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, state) !=
sizeof(vx->current_runstate));
- BUILD_BUG_ON(sizeof(((struct compat_vcpu_runstate_info *)0)->state) !=
+ BUILD_BUG_ON(sizeof_field(struct compat_vcpu_runstate_info, state) !=
sizeof(vx->current_runstate));
if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache,
@@ -163,9 +163,9 @@
offsetof(struct vcpu_runstate_info, time) - sizeof(u64));
BUILD_BUG_ON(offsetof(struct compat_vcpu_runstate_info, state_entry_time) !=
offsetof(struct compat_vcpu_runstate_info, time) - sizeof(u64));
- BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->time) !=
- sizeof(((struct compat_vcpu_runstate_info *)0)->time));
- BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->time) !=
+ BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, time) !=
+ sizeof_field(struct compat_vcpu_runstate_info, time));
+ BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, time) !=
sizeof(vx->runstate_times));
if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache,
@@ -205,9 +205,9 @@
BUILD_BUG_ON(offsetof(struct vcpu_info, evtchn_upcall_pending) !=
offsetof(struct compat_vcpu_info, evtchn_upcall_pending));
BUILD_BUG_ON(sizeof(rc) !=
- sizeof(((struct vcpu_info *)0)->evtchn_upcall_pending));
+ sizeof_field(struct vcpu_info, evtchn_upcall_pending));
BUILD_BUG_ON(sizeof(rc) !=
- sizeof(((struct compat_vcpu_info *)0)->evtchn_upcall_pending));
+ sizeof_field(struct compat_vcpu_info, evtchn_upcall_pending));
/*
* For efficiency, this mirrors the checks for using the valid
@@ -299,7 +299,7 @@
break;
case KVM_XEN_ATTR_TYPE_SHARED_INFO:
- data->u.shared_info.gfn = gpa_to_gfn(kvm->arch.xen.shinfo_gfn);
+ data->u.shared_info.gfn = kvm->arch.xen.shinfo_gfn;
r = 0;
break;
@@ -698,7 +698,7 @@
kvm_hv_hypercall_enabled(vcpu))
return kvm_hv_hypercall(vcpu);
- longmode = is_64_bit_mode(vcpu);
+ longmode = is_64_bit_hypercall(vcpu);
if (!longmode) {
params[0] = (u32)kvm_rbx_read(vcpu);
params[1] = (u32)kvm_rcx_read(vcpu);
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 88b1fce..663aabf 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -640,7 +640,7 @@
*/
ret = blk_queue_enter(q, 0);
if (ret)
- return ret;
+ goto fail;
rcu_read_lock();
spin_lock_irq(&q->queue_lock);
@@ -676,13 +676,13 @@
new_blkg = blkg_alloc(pos, q, GFP_KERNEL);
if (unlikely(!new_blkg)) {
ret = -ENOMEM;
- goto fail;
+ goto fail_exit_queue;
}
if (radix_tree_preload(GFP_KERNEL)) {
blkg_free(new_blkg);
ret = -ENOMEM;
- goto fail;
+ goto fail_exit_queue;
}
rcu_read_lock();
@@ -722,9 +722,10 @@
fail_unlock:
spin_unlock_irq(&q->queue_lock);
rcu_read_unlock();
+fail_exit_queue:
+ blk_queue_exit(q);
fail:
blkdev_put_no_open(bdev);
- blk_queue_exit(q);
/*
* If queue was bypassing, we should retry. Do so after a
* short msleep(). It isn't strictly necessary but queue
diff --git a/block/blk-core.c b/block/blk-core.c
index 9ee32f8..f0f38ca 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -363,8 +363,10 @@
blk_queue_flag_set(QUEUE_FLAG_DEAD, q);
blk_sync_queue(q);
- if (queue_is_mq(q))
+ if (queue_is_mq(q)) {
+ blk_mq_cancel_work_sync(q);
blk_mq_exit_queue(q);
+ }
/*
* In theory, request pool of sched_tags belongs to request queue.
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 8e364bd..1fce6d1 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -379,7 +379,7 @@
* @rq is being submitted. Analyze what needs to be done and put it on the
* right queue.
*/
-bool blk_insert_flush(struct request *rq)
+void blk_insert_flush(struct request *rq)
{
struct request_queue *q = rq->q;
unsigned long fflags = q->queue_flags; /* may change, cache */
@@ -409,7 +409,7 @@
*/
if (!policy) {
blk_mq_end_request(rq, 0);
- return true;
+ return;
}
BUG_ON(rq->bio != rq->biotail); /*assumes zero or single bio rq */
@@ -420,8 +420,10 @@
* for normal execution.
*/
if ((policy & REQ_FSEQ_DATA) &&
- !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH)))
- return false;
+ !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) {
+ blk_mq_request_bypass_insert(rq, false, true);
+ return;
+ }
/*
* @rq should go through flush machinery. Mark it part of flush
@@ -437,8 +439,6 @@
spin_lock_irq(&fq->mq_flush_lock);
blk_flush_complete_seq(rq, fq, REQ_FSEQ_ACTIONS & ~policy, 0);
spin_unlock_irq(&fq->mq_flush_lock);
-
- return true;
}
/**
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 3ab34c4..8799fa7 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2543,8 +2543,7 @@
return NULL;
}
-static inline bool blk_mq_can_use_cached_rq(struct request *rq,
- struct bio *bio)
+static inline bool blk_mq_can_use_cached_rq(struct request *rq, struct bio *bio)
{
if (blk_mq_get_hctx_type(bio->bi_opf) != rq->mq_hctx->type)
return false;
@@ -2565,7 +2564,6 @@
bool checked = false;
if (plug) {
-
rq = rq_list_peek(&plug->cached_rq);
if (rq && rq->q == q) {
if (unlikely(!submit_bio_checks(bio)))
@@ -2587,12 +2585,14 @@
fallback:
if (unlikely(bio_queue_enter(bio)))
return NULL;
- if (!checked && !submit_bio_checks(bio))
- return NULL;
+ if (unlikely(!checked && !submit_bio_checks(bio)))
+ goto out_put;
rq = blk_mq_get_new_requests(q, plug, bio, nsegs, same_queue_rq);
- if (!rq)
- blk_queue_exit(q);
- return rq;
+ if (rq)
+ return rq;
+out_put:
+ blk_queue_exit(q);
+ return NULL;
}
/**
@@ -2647,8 +2647,10 @@
return;
}
- if (op_is_flush(bio->bi_opf) && blk_insert_flush(rq))
+ if (op_is_flush(bio->bi_opf)) {
+ blk_insert_flush(rq);
return;
+ }
if (plug && (q->nr_hw_queues == 1 ||
blk_mq_is_shared_tags(rq->mq_hctx->flags) ||
@@ -4417,6 +4419,19 @@
}
EXPORT_SYMBOL(blk_mq_rq_cpu);
+void blk_mq_cancel_work_sync(struct request_queue *q)
+{
+ if (queue_is_mq(q)) {
+ struct blk_mq_hw_ctx *hctx;
+ int i;
+
+ cancel_delayed_work_sync(&q->requeue_work);
+
+ queue_for_each_hw_ctx(q, hctx, i)
+ cancel_delayed_work_sync(&hctx->run_work);
+ }
+}
+
static int __init blk_mq_init(void)
{
int i;
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 8acfa65..afcf993 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -128,6 +128,8 @@
void blk_mq_free_plug_rqs(struct blk_plug *plug);
void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule);
+void blk_mq_cancel_work_sync(struct request_queue *q);
+
void blk_mq_release(struct request_queue *q);
static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q,
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index cef1f71..cd75b0f 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -791,16 +791,6 @@
blk_free_queue_stats(q->stats);
- if (queue_is_mq(q)) {
- struct blk_mq_hw_ctx *hctx;
- int i;
-
- cancel_delayed_work_sync(&q->requeue_work);
-
- queue_for_each_hw_ctx(q, hctx, i)
- cancel_delayed_work_sync(&hctx->run_work);
- }
-
blk_exit_queue(q);
blk_queue_free_zone_bitmaps(q);
diff --git a/block/blk.h b/block/blk.h
index b4fed20..ccde6e6 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -271,7 +271,7 @@
*/
#define ELV_ON_HASH(rq) ((rq)->rq_flags & RQF_HASHED)
-bool blk_insert_flush(struct request *rq);
+void blk_insert_flush(struct request *rq);
int elevator_switch_mq(struct request_queue *q,
struct elevator_type *new_e);
diff --git a/block/elevator.c b/block/elevator.c
index 1f39f6e..19a78d5 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -694,12 +694,18 @@
if (!e)
return;
+ /*
+ * We are called before adding disk, when there isn't any FS I/O,
+ * so freezing queue plus canceling dispatch work is enough to
+ * drain any dispatch activities originated from passthrough
+ * requests, then no need to quiesce queue which may add long boot
+ * latency, especially when lots of disks are involved.
+ */
blk_mq_freeze_queue(q);
- blk_mq_quiesce_queue(q);
+ blk_mq_cancel_work_sync(q);
err = blk_mq_init_sched(q, e);
- blk_mq_unquiesce_queue(q);
blk_mq_unfreeze_queue(q);
if (err) {
diff --git a/block/genhd.c b/block/genhd.c
index c5392cc..30362ae 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1111,6 +1111,8 @@
might_sleep();
WARN_ON_ONCE(disk_live(disk));
+ blk_mq_cancel_work_sync(disk->queue);
+
disk_release_events(disk);
kfree(disk->random);
xa_destroy(&disk->part_tbl);
diff --git a/block/ioprio.c b/block/ioprio.c
index 0e4ff24..313c14a 100644
--- a/block/ioprio.c
+++ b/block/ioprio.c
@@ -69,7 +69,14 @@
switch (class) {
case IOPRIO_CLASS_RT:
- if (!capable(CAP_SYS_NICE) && !capable(CAP_SYS_ADMIN))
+ /*
+ * Originally this only checked for CAP_SYS_ADMIN,
+ * which was implicitly allowed for pid 0 by security
+ * modules such as SELinux. Make sure we check
+ * CAP_SYS_ADMIN first to avoid a denial/avc for
+ * possibly missing CAP_SYS_NICE permission.
+ */
+ if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_NICE))
return -EPERM;
fallthrough;
/* rt has prio field too */
diff --git a/drivers/acpi/glue.c b/drivers/acpi/glue.c
index 7cd0009..ef10480 100644
--- a/drivers/acpi/glue.c
+++ b/drivers/acpi/glue.c
@@ -347,28 +347,3 @@
acpi_unbind_one(dev);
}
-
-int acpi_dev_turn_off_if_unused(struct device *dev, void *not_used)
-{
- struct acpi_device *adev = to_acpi_device(dev);
-
- /*
- * Skip device objects with device IDs, because they may be in use even
- * if they are not companions of any physical device objects.
- */
- if (adev->pnp.type.hardware_id)
- return 0;
-
- mutex_lock(&adev->physical_node_lock);
-
- /*
- * Device objects without device IDs are not in use if they have no
- * corresponding physical device objects.
- */
- if (list_empty(&adev->physical_node_list))
- acpi_device_set_power(adev, ACPI_STATE_D3_COLD);
-
- mutex_unlock(&adev->physical_node_lock);
-
- return 0;
-}
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index 8fbdc17..d91b560 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -117,7 +117,6 @@
bool acpi_device_is_first_physical_node(struct acpi_device *adev,
const struct device *dev);
int acpi_bus_register_early_device(int type);
-int acpi_dev_turn_off_if_unused(struct device *dev, void *not_used);
/* --------------------------------------------------------------------------
Device Matching and Notification
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index a50f196..2c80765 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -2564,12 +2564,6 @@
}
}
- /*
- * Make sure that power management resources are not blocked by ACPI
- * device objects with no users.
- */
- bus_for_each_dev(&acpi_bus_type, NULL, NULL, acpi_dev_turn_off_if_unused);
-
acpi_turn_off_unused_power_resources();
acpi_scan_initialized = true;
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index d60f347..1e1167e 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -438,6 +438,7 @@
/* AMD */
{ PCI_VDEVICE(AMD, 0x7800), board_ahci }, /* AMD Hudson-2 */
{ PCI_VDEVICE(AMD, 0x7900), board_ahci }, /* AMD CZ */
+ { PCI_VDEVICE(AMD, 0x7901), board_ahci_mobile }, /* AMD Green Sardine */
/* AMD is using RAID class only for ahci controllers */
{ PCI_VENDOR_ID_AMD, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID,
PCI_CLASS_STORAGE_RAID << 8, 0xffffff, board_ahci },
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index 8a6835b..f76b841 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -2323,6 +2323,18 @@
EXPORT_SYMBOL_GPL(ahci_port_resume);
#ifdef CONFIG_PM
+static void ahci_handle_s2idle(struct ata_port *ap)
+{
+ void __iomem *port_mmio = ahci_port_base(ap);
+ u32 devslp;
+
+ if (pm_suspend_via_firmware())
+ return;
+ devslp = readl(port_mmio + PORT_DEVSLP);
+ if ((devslp & PORT_DEVSLP_ADSE))
+ ata_msleep(ap, devslp_idle_timeout);
+}
+
static int ahci_port_suspend(struct ata_port *ap, pm_message_t mesg)
{
const char *emsg = NULL;
@@ -2336,6 +2348,9 @@
ata_port_freeze(ap);
}
+ if (acpi_storage_d3(ap->host->dev))
+ ahci_handle_s2idle(ap);
+
ahci_rpm_put_port(ap);
return rc;
}
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 8a0ccb1..59ad8c9 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -2031,8 +2031,9 @@
dev->horkage |= ATA_HORKAGE_NO_DMA_LOG;
goto retry;
}
- ata_dev_err(dev, "Read log page 0x%02x failed, Emask 0x%x\n",
- (unsigned int)page, err_mask);
+ ata_dev_err(dev,
+ "Read log 0x%02x page 0x%02x failed, Emask 0x%x\n",
+ (unsigned int)log, (unsigned int)page, err_mask);
}
return err_mask;
@@ -2177,6 +2178,9 @@
struct ata_port *ap = dev->link->ap;
unsigned int err_mask;
+ if (!ata_identify_page_supported(dev, ATA_LOG_SATA_SETTINGS))
+ return;
+
err_mask = ata_read_log_page(dev,
ATA_LOG_IDENTIFY_DEVICE,
ATA_LOG_SATA_SETTINGS,
@@ -2453,7 +2457,8 @@
* Check device sleep capability. Get DevSlp timing variables
* from SATA Settings page of Identify Device Data Log.
*/
- if (!ata_id_has_devslp(dev->id))
+ if (!ata_id_has_devslp(dev->id) ||
+ !ata_identify_page_supported(dev, ATA_LOG_SATA_SETTINGS))
return;
err_mask = ata_read_log_page(dev,
diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c
index 4e88597..5b78e86 100644
--- a/drivers/ata/libata-sata.c
+++ b/drivers/ata/libata-sata.c
@@ -922,7 +922,7 @@
ata_ncq_prio_enable_show, ata_ncq_prio_enable_store);
EXPORT_SYMBOL_GPL(dev_attr_ncq_prio_enable);
-struct attribute *ata_ncq_sdev_attrs[] = {
+static struct attribute *ata_ncq_sdev_attrs[] = {
&dev_attr_unload_heads.attr,
&dev_attr_ncq_prio_enable.attr,
&dev_attr_ncq_prio_supported.attr,
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index 072ed61..60d9374 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -523,6 +523,7 @@
config GPIO_ROCKCHIP
tristate "Rockchip GPIO support"
depends on ARCH_ROCKCHIP || COMPILE_TEST
+ select GENERIC_IRQ_CHIP
select GPIOLIB_IRQCHIP
default ARCH_ROCKCHIP
help
diff --git a/drivers/gpio/gpio-virtio.c b/drivers/gpio/gpio-virtio.c
index aeec4bf..84f96b7 100644
--- a/drivers/gpio/gpio-virtio.c
+++ b/drivers/gpio/gpio-virtio.c
@@ -434,7 +434,7 @@
ret = generic_handle_domain_irq(vgpio->gc.irq.domain, gpio);
if (ret)
dev_err(dev, "failed to handle interrupt: %d\n", ret);
- };
+ }
}
static void virtio_gpio_request_vq(struct virtqueue *vq)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
index b9c11c2..0de66f5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
@@ -827,6 +827,7 @@
amdgpu_connector_get_edid(connector);
ret = amdgpu_connector_ddc_get_modes(connector);
+ amdgpu_get_native_mode(connector);
return ret;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 5625f77..188accb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3509,6 +3509,9 @@
adev->rmmio_size = pci_resource_len(adev->pdev, 2);
}
+ for (i = 0; i < AMD_IP_BLOCK_TYPE_NUM; i++)
+ atomic_set(&adev->pm.pwr_state[i], POWER_STATE_UNKNOWN);
+
adev->rmmio = ioremap(adev->rmmio_base, adev->rmmio_size);
if (adev->rmmio == NULL) {
return -ENOMEM;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index ff70bc2..4e36694 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -587,6 +587,9 @@
amdgpu_device_ip_block_add(adev, &nv_common_ip_block);
break;
default:
+ dev_err(adev->dev,
+ "Failed to add common ip block(GC_HWIP:0x%x)\n",
+ adev->ip_versions[GC_HWIP][0]);
return -EINVAL;
}
return 0;
@@ -619,6 +622,9 @@
amdgpu_device_ip_block_add(adev, &gmc_v10_0_ip_block);
break;
default:
+ dev_err(adev->dev,
+ "Failed to add gmc ip block(GC_HWIP:0x%x)\n",
+ adev->ip_versions[GC_HWIP][0]);
return -EINVAL;
}
return 0;
@@ -648,6 +654,9 @@
amdgpu_device_ip_block_add(adev, &navi10_ih_ip_block);
break;
default:
+ dev_err(adev->dev,
+ "Failed to add ih ip block(OSSSYS_HWIP:0x%x)\n",
+ adev->ip_versions[OSSSYS_HWIP][0]);
return -EINVAL;
}
return 0;
@@ -688,6 +697,9 @@
amdgpu_device_ip_block_add(adev, &psp_v13_0_ip_block);
break;
default:
+ dev_err(adev->dev,
+ "Failed to add psp ip block(MP0_HWIP:0x%x)\n",
+ adev->ip_versions[MP0_HWIP][0]);
return -EINVAL;
}
return 0;
@@ -726,6 +738,9 @@
amdgpu_device_ip_block_add(adev, &smu_v13_0_ip_block);
break;
default:
+ dev_err(adev->dev,
+ "Failed to add smu ip block(MP1_HWIP:0x%x)\n",
+ adev->ip_versions[MP1_HWIP][0]);
return -EINVAL;
}
return 0;
@@ -753,6 +768,9 @@
amdgpu_device_ip_block_add(adev, &dm_ip_block);
break;
default:
+ dev_err(adev->dev,
+ "Failed to add dm ip block(DCE_HWIP:0x%x)\n",
+ adev->ip_versions[DCE_HWIP][0]);
return -EINVAL;
}
} else if (adev->ip_versions[DCI_HWIP][0]) {
@@ -763,6 +781,9 @@
amdgpu_device_ip_block_add(adev, &dm_ip_block);
break;
default:
+ dev_err(adev->dev,
+ "Failed to add dm ip block(DCI_HWIP:0x%x)\n",
+ adev->ip_versions[DCI_HWIP][0]);
return -EINVAL;
}
#endif
@@ -796,6 +817,9 @@
amdgpu_device_ip_block_add(adev, &gfx_v10_0_ip_block);
break;
default:
+ dev_err(adev->dev,
+ "Failed to add gfx ip block(GC_HWIP:0x%x)\n",
+ adev->ip_versions[GC_HWIP][0]);
return -EINVAL;
}
return 0;
@@ -829,6 +853,9 @@
amdgpu_device_ip_block_add(adev, &sdma_v5_2_ip_block);
break;
default:
+ dev_err(adev->dev,
+ "Failed to add sdma ip block(SDMA0_HWIP:0x%x)\n",
+ adev->ip_versions[SDMA0_HWIP][0]);
return -EINVAL;
}
return 0;
@@ -845,6 +872,9 @@
amdgpu_device_ip_block_add(adev, &uvd_v7_0_ip_block);
break;
default:
+ dev_err(adev->dev,
+ "Failed to add uvd v7 ip block(UVD_HWIP:0x%x)\n",
+ adev->ip_versions[UVD_HWIP][0]);
return -EINVAL;
}
switch (adev->ip_versions[VCE_HWIP][0]) {
@@ -855,6 +885,9 @@
amdgpu_device_ip_block_add(adev, &vce_v4_0_ip_block);
break;
default:
+ dev_err(adev->dev,
+ "Failed to add VCE v4 ip block(VCE_HWIP:0x%x)\n",
+ adev->ip_versions[VCE_HWIP][0]);
return -EINVAL;
}
} else {
@@ -893,6 +926,9 @@
amdgpu_device_ip_block_add(adev, &vcn_v3_0_ip_block);
break;
default:
+ dev_err(adev->dev,
+ "Failed to add vcn/jpeg ip block(UVD_HWIP:0x%x)\n",
+ adev->ip_versions[UVD_HWIP][0]);
return -EINVAL;
}
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index 0fad2bf..567df2d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -386,6 +386,7 @@
"%s", "xgmi_hive_info");
if (ret) {
dev_err(adev->dev, "XGMI: failed initializing kobject for xgmi hive\n");
+ kobject_put(&hive->kobj);
kfree(hive);
hive = NULL;
goto pro_end;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 003ba6a..93e33dd 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -1226,6 +1226,11 @@
bool hanging;
dqm_lock(dqm);
+ if (!dqm->sched_running) {
+ dqm_unlock(dqm);
+ return 0;
+ }
+
if (!dqm->is_hws_hang)
unmap_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES, 0);
hanging = dqm->is_hws_hang || dqm->is_resetting;
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 c911b30..c27cb47 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -4242,7 +4242,8 @@
} else if (dc_link_detect(link, DETECT_REASON_BOOT)) {
amdgpu_dm_update_connector_after_detect(aconnector);
register_backlight_device(dm, link);
-
+ if (dm->num_of_edps)
+ update_connector_ext_caps(aconnector);
if (psr_feature_enabled)
amdgpu_dm_set_psr_caps(link);
}
diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h
index f1a46d1..4b9e68a 100644
--- a/drivers/gpu/drm/amd/include/amd_shared.h
+++ b/drivers/gpu/drm/amd/include/amd_shared.h
@@ -98,7 +98,8 @@
AMD_IP_BLOCK_TYPE_ACP,
AMD_IP_BLOCK_TYPE_VCN,
AMD_IP_BLOCK_TYPE_MES,
- AMD_IP_BLOCK_TYPE_JPEG
+ AMD_IP_BLOCK_TYPE_JPEG,
+ AMD_IP_BLOCK_TYPE_NUM,
};
enum amd_clockgating_state {
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
index 03581d5..08362d5 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
@@ -927,6 +927,13 @@
{
int ret = 0;
const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+ enum ip_power_state pwr_state = gate ? POWER_STATE_OFF : POWER_STATE_ON;
+
+ if (atomic_read(&adev->pm.pwr_state[block_type]) == pwr_state) {
+ dev_dbg(adev->dev, "IP block%d already in the target %s state!",
+ block_type, gate ? "gate" : "ungate");
+ return 0;
+ }
switch (block_type) {
case AMD_IP_BLOCK_TYPE_UVD:
@@ -979,6 +986,9 @@
break;
}
+ if (!ret)
+ atomic_set(&adev->pm.pwr_state[block_type], pwr_state);
+
return ret;
}
diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
index 98f1b3d..16e3f72 100644
--- a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
+++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
@@ -417,6 +417,12 @@
enum amd_dpm_forced_level forced_level;
};
+enum ip_power_state {
+ POWER_STATE_UNKNOWN,
+ POWER_STATE_ON,
+ POWER_STATE_OFF,
+};
+
struct amdgpu_pm {
struct mutex mutex;
u32 current_sclk;
@@ -452,6 +458,8 @@
struct i2c_adapter smu_i2c;
struct mutex smu_i2c_mutex;
struct list_head pm_attr_list;
+
+ atomic_t pwr_state[AMD_IP_BLOCK_TYPE_NUM];
};
#define R600_SSTU_DFLT 0
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.c
index cbc3f99..2238ee1 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.c
@@ -309,6 +309,7 @@
{
int ret = 0, size = 0;
uint32_t cur_value = 0;
+ int i;
smu_cmn_get_sysfs_buf(&buf, &size);
@@ -334,8 +335,6 @@
size += sysfs_emit_at(buf, size, "VDDC: %7umV %10umV\n",
CYAN_SKILLFISH_VDDC_MIN, CYAN_SKILLFISH_VDDC_MAX);
break;
- case SMU_GFXCLK:
- case SMU_SCLK:
case SMU_FCLK:
case SMU_MCLK:
case SMU_SOCCLK:
@@ -346,6 +345,25 @@
return ret;
size += sysfs_emit_at(buf, size, "0: %uMhz *\n", cur_value);
break;
+ case SMU_SCLK:
+ case SMU_GFXCLK:
+ ret = cyan_skillfish_get_current_clk_freq(smu, clk_type, &cur_value);
+ if (ret)
+ return ret;
+ if (cur_value == CYAN_SKILLFISH_SCLK_MAX)
+ i = 2;
+ else if (cur_value == CYAN_SKILLFISH_SCLK_MIN)
+ i = 0;
+ else
+ i = 1;
+ size += sysfs_emit_at(buf, size, "0: %uMhz %s\n", CYAN_SKILLFISH_SCLK_MIN,
+ i == 0 ? "*" : "");
+ size += sysfs_emit_at(buf, size, "1: %uMhz %s\n",
+ i == 1 ? cur_value : cyan_skillfish_sclk_default,
+ i == 1 ? "*" : "");
+ size += sysfs_emit_at(buf, size, "2: %uMhz %s\n", CYAN_SKILLFISH_SCLK_MAX,
+ i == 2 ? "*" : "");
+ break;
default:
dev_warn(smu->adev->dev, "Unsupported clock type\n");
return ret;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
index 71161f6..60a5570 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
@@ -1265,7 +1265,7 @@
enum smu_clk_type clk_type, char *buf)
{
uint16_t *curve_settings;
- int i, size = 0, ret = 0;
+ int i, levels, size = 0, ret = 0;
uint32_t cur_value = 0, value = 0, count = 0;
uint32_t freq_values[3] = {0};
uint32_t mark_index = 0;
@@ -1319,14 +1319,17 @@
freq_values[1] = cur_value;
mark_index = cur_value == freq_values[0] ? 0 :
cur_value == freq_values[2] ? 2 : 1;
- if (mark_index != 1)
- freq_values[1] = (freq_values[0] + freq_values[2]) / 2;
- for (i = 0; i < 3; i++) {
+ levels = 3;
+ if (mark_index != 1) {
+ levels = 2;
+ freq_values[1] = freq_values[2];
+ }
+
+ for (i = 0; i < levels; i++) {
size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n", i, freq_values[i],
i == mark_index ? "*" : "");
}
-
}
break;
case SMU_PCIE:
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
index 421f38e..c02ed65 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
@@ -683,6 +683,7 @@
int i, size = 0, ret = 0;
uint32_t cur_value = 0, value = 0, count = 0;
bool cur_value_match_level = false;
+ uint32_t min, max;
memset(&metrics, 0, sizeof(metrics));
@@ -743,6 +744,13 @@
if (ret)
return ret;
break;
+ case SMU_GFXCLK:
+ case SMU_SCLK:
+ ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GetGfxclkFrequency, 0, &cur_value);
+ if (ret) {
+ return ret;
+ }
+ break;
default:
break;
}
@@ -768,6 +776,24 @@
if (!cur_value_match_level)
size += sysfs_emit_at(buf, size, " %uMhz *\n", cur_value);
break;
+ case SMU_GFXCLK:
+ case SMU_SCLK:
+ min = (smu->gfx_actual_hard_min_freq > 0) ? smu->gfx_actual_hard_min_freq : smu->gfx_default_hard_min_freq;
+ max = (smu->gfx_actual_soft_max_freq > 0) ? smu->gfx_actual_soft_max_freq : smu->gfx_default_soft_max_freq;
+ if (cur_value == max)
+ i = 2;
+ else if (cur_value == min)
+ i = 0;
+ else
+ i = 1;
+ size += sysfs_emit_at(buf, size, "0: %uMhz %s\n", min,
+ i == 0 ? "*" : "");
+ size += sysfs_emit_at(buf, size, "1: %uMhz %s\n",
+ i == 1 ? cur_value : VANGOGH_UMD_PSTATE_STANDARD_GFXCLK,
+ i == 1 ? "*" : "");
+ size += sysfs_emit_at(buf, size, "2: %uMhz %s\n", max,
+ i == 2 ? "*" : "");
+ break;
default:
break;
}
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c
index 8215bbf..caf1775 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c
@@ -697,6 +697,11 @@
case SMU_FCLK:
return smu_cmn_send_smc_msg_with_param(smu,
SMU_MSG_GetFclkFrequency, 0, value);
+ case SMU_GFXCLK:
+ case SMU_SCLK:
+ return smu_cmn_send_smc_msg_with_param(smu,
+ SMU_MSG_GetGfxclkFrequency, 0, value);
+ break;
default:
return -EINVAL;
}
@@ -967,6 +972,7 @@
{
int i, size = 0, ret = 0;
uint32_t cur_value = 0, value = 0, count = 0;
+ uint32_t min, max;
smu_cmn_get_sysfs_buf(&buf, &size);
@@ -1005,6 +1011,27 @@
cur_value == value ? "*" : "");
}
break;
+ case SMU_GFXCLK:
+ case SMU_SCLK:
+ ret = yellow_carp_get_current_clk_freq(smu, clk_type, &cur_value);
+ if (ret)
+ goto print_clk_out;
+ min = (smu->gfx_actual_hard_min_freq > 0) ? smu->gfx_actual_hard_min_freq : smu->gfx_default_hard_min_freq;
+ max = (smu->gfx_actual_soft_max_freq > 0) ? smu->gfx_actual_soft_max_freq : smu->gfx_default_soft_max_freq;
+ if (cur_value == max)
+ i = 2;
+ else if (cur_value == min)
+ i = 0;
+ else
+ i = 1;
+ size += sysfs_emit_at(buf, size, "0: %uMhz %s\n", min,
+ i == 0 ? "*" : "");
+ size += sysfs_emit_at(buf, size, "1: %uMhz %s\n",
+ i == 1 ? cur_value : YELLOW_CARP_UMD_PSTATE_GFXCLK,
+ i == 1 ? "*" : "");
+ size += sysfs_emit_at(buf, size, "2: %uMhz %s\n", max,
+ i == 2 ? "*" : "");
+ break;
default:
break;
}
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.h b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.h
index b3ad835..a9205a8 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.h
@@ -24,5 +24,6 @@
#define __YELLOW_CARP_PPT_H__
extern void yellow_carp_set_ppt_funcs(struct smu_context *smu);
+#define YELLOW_CARP_UMD_PSTATE_GFXCLK 1100
#endif
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
index 843d2cb..ea6f50c 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
@@ -139,9 +139,13 @@
const char *message = smu_get_message_name(smu, msg);
switch (reg_c2pmsg_90) {
- case SMU_RESP_NONE:
+ case SMU_RESP_NONE: {
+ u32 msg_idx = RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_66);
+ u32 prm = RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_82);
dev_err_ratelimited(adev->dev,
- "SMU: I'm not done with your previous command!");
+ "SMU: I'm not done with your previous command: SMN_C2PMSG_66:0x%08X SMN_C2PMSG_82:0x%08X",
+ msg_idx, prm);
+ }
break;
case SMU_RESP_OK:
/* The SMU executed the command. It completed with a
diff --git a/drivers/gpu/drm/drm_gem_cma_helper.c b/drivers/gpu/drm/drm_gem_cma_helper.c
index d533881..9d05674 100644
--- a/drivers/gpu/drm/drm_gem_cma_helper.c
+++ b/drivers/gpu/drm/drm_gem_cma_helper.c
@@ -210,8 +210,13 @@
dma_buf_vunmap(gem_obj->import_attach->dmabuf, &map);
drm_prime_gem_destroy(gem_obj, cma_obj->sgt);
} else if (cma_obj->vaddr) {
- dma_free_wc(gem_obj->dev->dev, cma_obj->base.size,
- cma_obj->vaddr, cma_obj->paddr);
+ if (cma_obj->map_noncoherent)
+ dma_free_noncoherent(gem_obj->dev->dev, cma_obj->base.size,
+ cma_obj->vaddr, cma_obj->paddr,
+ DMA_TO_DEVICE);
+ else
+ dma_free_wc(gem_obj->dev->dev, cma_obj->base.size,
+ cma_obj->vaddr, cma_obj->paddr);
}
drm_gem_object_release(gem_obj);
diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c
index 168c84a..71fbdcd 100644
--- a/drivers/gpu/drm/i915/display/icl_dsi.c
+++ b/drivers/gpu/drm/i915/display/icl_dsi.c
@@ -696,10 +696,7 @@
intel_de_write(dev_priv, ICL_DPCLKA_CFGCR0, val);
for_each_dsi_phy(phy, intel_dsi->phys) {
- if (DISPLAY_VER(dev_priv) >= 12)
- val |= ICL_DPCLKA_CFGCR0_DDI_CLK_OFF(phy);
- else
- val &= ~ICL_DPCLKA_CFGCR0_DDI_CLK_OFF(phy);
+ val &= ~ICL_DPCLKA_CFGCR0_DDI_CLK_OFF(phy);
}
intel_de_write(dev_priv, ICL_DPCLKA_CFGCR0, val);
@@ -1135,8 +1132,6 @@
gen11_dsi_enable_port_and_phy(struct intel_encoder *encoder,
const struct intel_crtc_state *crtc_state)
{
- struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-
/* step 4a: power up all lanes of the DDI used by DSI */
gen11_dsi_power_up_lanes(encoder);
@@ -1162,8 +1157,7 @@
gen11_dsi_configure_transcoder(encoder, crtc_state);
/* Step 4l: Gate DDI clocks */
- if (DISPLAY_VER(dev_priv) == 11)
- gen11_dsi_gate_clocks(encoder);
+ gen11_dsi_gate_clocks(encoder);
}
static void gen11_dsi_powerup_panel(struct intel_encoder *encoder)
@@ -1271,7 +1265,8 @@
if (DISPLAY_VER(i915) == 13) {
for_each_dsi_port(port, intel_dsi->ports)
intel_de_rmw(i915, TGL_DSI_CHKN_REG(port),
- TGL_DSI_CHKN_LSHS_GB, 0x4);
+ TGL_DSI_CHKN_LSHS_GB_MASK,
+ TGL_DSI_CHKN_LSHS_GB(4));
}
}
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index 38b47e7..c48557d 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -3080,8 +3080,8 @@
ce = intel_engine_create_virtual(siblings, num_siblings,
FORCE_VIRTUAL);
- if (!ce) {
- err = ERR_PTR(-ENOMEM);
+ if (IS_ERR(ce)) {
+ err = ERR_CAST(ce);
goto unwind;
}
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index da9055c..bcee121 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -11717,7 +11717,9 @@
#define TGL_DSI_CHKN_REG(port) _MMIO_PORT(port, \
_TGL_DSI_CHKN_REG_0, \
_TGL_DSI_CHKN_REG_1)
-#define TGL_DSI_CHKN_LSHS_GB REG_GENMASK(15, 12)
+#define TGL_DSI_CHKN_LSHS_GB_MASK REG_GENMASK(15, 12)
+#define TGL_DSI_CHKN_LSHS_GB(byte_clocks) REG_FIELD_PREP(TGL_DSI_CHKN_LSHS_GB_MASK, \
+ (byte_clocks))
/* Display Stream Splitter Control */
#define DSS_CTL1 _MMIO(0x67400)
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdmigv100.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdmigv100.c
index 6e3c450..3ff4934 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdmigv100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdmigv100.c
@@ -62,7 +62,6 @@
nvkm_wr32(device, 0x6f0108 + hdmi, vendor_infoframe.header);
nvkm_wr32(device, 0x6f010c + hdmi, vendor_infoframe.subpack0_low);
nvkm_wr32(device, 0x6f0110 + hdmi, vendor_infoframe.subpack0_high);
- nvkm_wr32(device, 0x6f0110 + hdmi, 0x00000000);
nvkm_wr32(device, 0x6f0114 + hdmi, 0x00000000);
nvkm_wr32(device, 0x6f0118 + hdmi, 0x00000000);
nvkm_wr32(device, 0x6f011c + hdmi, 0x00000000);
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 5bc5f77..f91fb31 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -704,9 +704,13 @@
int ret;
dma_resv_for_each_fence(&cursor, obj->resv, write, fence) {
+ /* Make sure to grab an additional ref on the added fence */
+ dma_fence_get(fence);
ret = drm_sched_job_add_dependency(job, fence);
- if (ret)
+ if (ret) {
+ dma_fence_put(fence);
return ret;
+ }
}
return 0;
}
diff --git a/drivers/gpu/drm/sun4i/Kconfig b/drivers/gpu/drm/sun4i/Kconfig
index 5755f04..8c796de 100644
--- a/drivers/gpu/drm/sun4i/Kconfig
+++ b/drivers/gpu/drm/sun4i/Kconfig
@@ -46,6 +46,7 @@
default MACH_SUN8I
select CRC_CCITT
select DRM_MIPI_DSI
+ select RESET_CONTROLLER
select PHY_SUN6I_MIPI_DPHY
help
Choose this option if you want have an Allwinner SoC with
diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c
index 7f11ea0..ca873a3 100644
--- a/drivers/hv/hv_balloon.c
+++ b/drivers/hv/hv_balloon.c
@@ -480,7 +480,7 @@
MODULE_PARM_DESC(pressure_report_delay, "Delay in secs in reporting pressure");
static atomic_t trans_id = ATOMIC_INIT(0);
-static int dm_ring_size = 20 * 1024;
+static int dm_ring_size = VMBUS_RING_SIZE(16 * 1024);
/*
* Driver specific state.
diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index fedc0fa..f5aacaf 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -1906,7 +1906,8 @@
int ret;
/* Currently only counter for QP is supported */
- if (nla_get_u32(tb[RDMA_NLDEV_ATTR_STAT_RES]) != RDMA_NLDEV_ATTR_RES_QP)
+ if (!tb[RDMA_NLDEV_ATTR_STAT_RES] ||
+ nla_get_u32(tb[RDMA_NLDEV_ATTR_STAT_RES]) != RDMA_NLDEV_ATTR_RES_QP)
return -EINVAL;
mode = nla_get_u32(tb[RDMA_NLDEV_ATTR_STAT_MODE]);
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 692d5ff..c18634b 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -1232,6 +1232,9 @@
INIT_LIST_HEAD(&qp->rdma_mrs);
INIT_LIST_HEAD(&qp->sig_mrs);
+ qp->send_cq = attr->send_cq;
+ qp->recv_cq = attr->recv_cq;
+
rdma_restrack_new(&qp->res, RDMA_RESTRACK_QP);
WARN_ONCE(!udata && !caller, "Missing kernel QP owner");
rdma_restrack_set_name(&qp->res, udata ? NULL : caller);
diff --git a/drivers/infiniband/hw/hfi1/verbs.c b/drivers/infiniband/hw/hfi1/verbs.c
index ed9fa0d..dc9211f 100644
--- a/drivers/infiniband/hw/hfi1/verbs.c
+++ b/drivers/infiniband/hw/hfi1/verbs.c
@@ -1628,8 +1628,7 @@
n++;
names_out =
- kmalloc((n + num_extra_names) * sizeof(struct rdma_stat_desc) +
- names_len,
+ kzalloc((n + num_extra_names) * sizeof(*q) + names_len,
GFP_KERNEL);
if (!names_out) {
*num_cntrs = 0;
@@ -1637,7 +1636,7 @@
return -ENOMEM;
}
- p = names_out + (n + num_extra_names) * sizeof(struct rdma_stat_desc);
+ p = names_out + (n + num_extra_names) * sizeof(*q);
memcpy(p, names_in, names_len);
q = (struct rdma_stat_desc *)names_out;
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index ceca059..0d2fa33 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -2215,6 +2215,11 @@
.get_hw_stats = mlx4_ib_get_hw_stats,
};
+static const struct ib_device_ops mlx4_ib_hw_stats_ops1 = {
+ .alloc_hw_device_stats = mlx4_ib_alloc_hw_device_stats,
+ .get_hw_stats = mlx4_ib_get_hw_stats,
+};
+
static int mlx4_ib_alloc_diag_counters(struct mlx4_ib_dev *ibdev)
{
struct mlx4_ib_diag_counters *diag = ibdev->diag_counters;
@@ -2227,9 +2232,16 @@
return 0;
for (i = 0; i < MLX4_DIAG_COUNTERS_TYPES; i++) {
- /* i == 1 means we are building port counters */
- if (i && !per_port)
- continue;
+ /*
+ * i == 1 means we are building port counters, set a different
+ * stats ops without port stats callback.
+ */
+ if (i && !per_port) {
+ ib_set_device_ops(&ibdev->ib_dev,
+ &mlx4_ib_hw_stats_ops1);
+
+ return 0;
+ }
ret = __mlx4_ib_alloc_diag_counters(ibdev, &diag[i].descs,
&diag[i].offset,
diff --git a/drivers/net/amt.c b/drivers/net/amt.c
index 47a04c3..b732ee9 100644
--- a/drivers/net/amt.c
+++ b/drivers/net/amt.c
@@ -3286,7 +3286,7 @@
{
rtnl_link_unregister(&amt_link_ops);
unregister_netdevice_notifier(&amt_notifier_block);
- cancel_delayed_work(&source_gc_wq);
+ cancel_delayed_work_sync(&source_gc_wq);
__amt_source_gc_work();
destroy_workqueue(amt_wq);
}
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
index fc0e660..3f1704c 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
@@ -559,6 +559,11 @@
goto err_exit;
if (fw.len == 0xFFFFU) {
+ if (sw.len > sizeof(self->rpc)) {
+ printk(KERN_INFO "Invalid sw len: %x\n", sw.len);
+ err = -EINVAL;
+ goto err_exit;
+ }
err = hw_atl_utils_fw_rpc_call(self, sw.len);
if (err < 0)
goto err_exit;
@@ -567,6 +572,11 @@
if (rpc) {
if (fw.len) {
+ if (fw.len > sizeof(self->rpc)) {
+ printk(KERN_INFO "Invalid fw len: %x\n", fw.len);
+ err = -EINVAL;
+ goto err_exit;
+ }
err =
hw_atl_utils_fw_downld_dwords(self,
self->rpc_addr,
diff --git a/drivers/net/ethernet/asix/ax88796c_main.h b/drivers/net/ethernet/asix/ax88796c_main.h
index 80263c3..4a83c99 100644
--- a/drivers/net/ethernet/asix/ax88796c_main.h
+++ b/drivers/net/ethernet/asix/ax88796c_main.h
@@ -127,9 +127,9 @@
#define AX_PRIV_FLAGS_MASK (AX_CAP_COMP)
unsigned long flags;
- #define EVENT_INTR BIT(0)
- #define EVENT_TX BIT(1)
- #define EVENT_SET_MULTI BIT(2)
+ #define EVENT_INTR 0
+ #define EVENT_TX 1
+ #define EVENT_SET_MULTI 2
};
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init_ops.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init_ops.h
index 1835d2e..fc7fce6 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init_ops.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init_ops.h
@@ -635,11 +635,13 @@
{
int i, rc;
struct bnx2x_ilt *ilt = BP_ILT(bp);
- struct ilt_client_info *ilt_cli = &ilt->clients[cli_num];
+ struct ilt_client_info *ilt_cli;
if (!ilt || !ilt->lines)
return -1;
+ ilt_cli = &ilt->clients[cli_num];
+
if (ilt_cli->flags & (ILT_CLIENT_SKIP_INIT | ILT_CLIENT_SKIP_MEM))
return 0;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index d0d5da9..4c9507d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -2258,6 +2258,16 @@
}
}
+/* Must hold rtnl_lock */
+static inline bool bnxt_sriov_cfg(struct bnxt *bp)
+{
+#if defined(CONFIG_BNXT_SRIOV)
+ return BNXT_PF(bp) && (bp->pf.active_vfs || bp->sriov_cfg);
+#else
+ return false;
+#endif
+}
+
extern const u16 bnxt_lhint_arr[];
int bnxt_alloc_rx_data(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
index 5c464ea..951c4c5 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -360,7 +360,7 @@
NL_SET_ERR_MSG_MOD(extack, "Live patch already applied");
break;
default:
- netdev_err(bp->dev, "Unexpected live patch error: %hhd\n", err);
+ netdev_err(bp->dev, "Unexpected live patch error: %d\n", err);
NL_SET_ERR_MSG_MOD(extack, "Failed to activate live patch");
break;
}
@@ -441,12 +441,13 @@
switch (action) {
case DEVLINK_RELOAD_ACTION_DRIVER_REINIT: {
- if (BNXT_PF(bp) && bp->pf.active_vfs) {
+ rtnl_lock();
+ if (bnxt_sriov_cfg(bp)) {
NL_SET_ERR_MSG_MOD(extack,
- "reload is unsupported when VFs are allocated");
+ "reload is unsupported while VFs are allocated or being configured");
+ rtnl_unlock();
return -EOPNOTSUPP;
}
- rtnl_lock();
if (bp->dev->reg_state == NETREG_UNREGISTERED) {
rtnl_unlock();
return -ENODEV;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
index e6a4a76..1471b61 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
@@ -1868,7 +1868,7 @@
struct flow_cls_offload *flower = type_data;
struct bnxt *bp = priv->bp;
- if (flower->common.chain_index)
+ if (!tc_cls_can_offload_and_chain0(bp->dev, type_data))
return -EOPNOTSUPP;
switch (type) {
diff --git a/drivers/net/ethernet/dec/tulip/de4x5.c b/drivers/net/ethernet/dec/tulip/de4x5.c
index 13121c4..71730ef 100644
--- a/drivers/net/ethernet/dec/tulip/de4x5.c
+++ b/drivers/net/ethernet/dec/tulip/de4x5.c
@@ -4709,6 +4709,10 @@
lp->ibn = 3;
lp->active = *p++;
if (MOTO_SROM_BUG) lp->active = 0;
+ /* if (MOTO_SROM_BUG) statement indicates lp->active could
+ * be 8 (i.e. the size of array lp->phy) */
+ if (WARN_ON(lp->active >= ARRAY_SIZE(lp->phy)))
+ return -EINVAL;
lp->phy[lp->active].gep = (*p ? p : NULL); p += (2 * (*p) + 1);
lp->phy[lp->active].rst = (*p ? p : NULL); p += (2 * (*p) + 1);
lp->phy[lp->active].mc = get_unaligned_le16(p); p += 2;
@@ -5000,19 +5004,23 @@
}
if ((j == limit) && (i < DE4X5_MAX_MII)) {
for (k=0; k < DE4X5_MAX_PHY && lp->phy[k].id; k++);
- lp->phy[k].addr = i;
- lp->phy[k].id = id;
- lp->phy[k].spd.reg = GENERIC_REG; /* ANLPA register */
- lp->phy[k].spd.mask = GENERIC_MASK; /* 100Mb/s technologies */
- lp->phy[k].spd.value = GENERIC_VALUE; /* TX & T4, H/F Duplex */
- lp->mii_cnt++;
- lp->active++;
- printk("%s: Using generic MII device control. If the board doesn't operate,\nplease mail the following dump to the author:\n", dev->name);
- j = de4x5_debug;
- de4x5_debug |= DEBUG_MII;
- de4x5_dbg_mii(dev, k);
- de4x5_debug = j;
- printk("\n");
+ if (k < DE4X5_MAX_PHY) {
+ lp->phy[k].addr = i;
+ lp->phy[k].id = id;
+ lp->phy[k].spd.reg = GENERIC_REG; /* ANLPA register */
+ lp->phy[k].spd.mask = GENERIC_MASK; /* 100Mb/s technologies */
+ lp->phy[k].spd.value = GENERIC_VALUE; /* TX & T4, H/F Duplex */
+ lp->mii_cnt++;
+ lp->active++;
+ printk("%s: Using generic MII device control. If the board doesn't operate,\nplease mail the following dump to the author:\n", dev->name);
+ j = de4x5_debug;
+ de4x5_debug |= DEBUG_MII;
+ de4x5_dbg_mii(dev, k);
+ de4x5_debug = j;
+ printk("\n");
+ } else {
+ goto purgatory;
+ }
}
}
purgatory:
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 714e961..6451c83 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -4550,10 +4550,10 @@
fsl_mc_portal_free(priv->mc_io);
- free_netdev(net_dev);
-
dev_dbg(net_dev->dev.parent, "Removed interface %s\n", net_dev->name);
+ free_netdev(net_dev);
+
return 0;
}
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
index 23d9cbf..740850b 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
@@ -400,6 +400,10 @@
return;
if (!HNS_DSAF_IS_DEBUG(dsaf_dev)) {
+ /* DSAF_MAX_PORT_NUM is 6, but DSAF_GE_NUM is 8.
+ We need check to prevent array overflow */
+ if (port >= DSAF_MAX_PORT_NUM)
+ return;
reg_val_1 = 0x1 << port;
port_rst_off = dsaf_dev->mac_cb[port]->port_rst_off;
/* there is difference between V1 and V2 in register.*/
diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c
index 5039a25..0bf3d47b 100644
--- a/drivers/net/ethernet/intel/e100.c
+++ b/drivers/net/ethernet/intel/e100.c
@@ -3003,9 +3003,10 @@
struct net_device *netdev = pci_get_drvdata(pdev);
struct nic *nic = netdev_priv(netdev);
+ netif_device_detach(netdev);
+
if (netif_running(netdev))
e100_down(nic);
- netif_device_detach(netdev);
if ((nic->flags & wol_magic) | e100_asf(nic)) {
/* enable reverse auto-negotiation */
@@ -3022,7 +3023,7 @@
*enable_wake = false;
}
- pci_clear_master(pdev);
+ pci_disable_device(pdev);
}
static int __e100_power_off(struct pci_dev *pdev, bool wake)
@@ -3042,8 +3043,6 @@
__e100_shutdown(to_pci_dev(dev_d), &wake);
- device_wakeup_disable(dev_d);
-
return 0;
}
@@ -3051,6 +3050,14 @@
{
struct net_device *netdev = dev_get_drvdata(dev_d);
struct nic *nic = netdev_priv(netdev);
+ int err;
+
+ err = pci_enable_device(to_pci_dev(dev_d));
+ if (err) {
+ netdev_err(netdev, "Resume cannot enable PCI device, aborting\n");
+ return err;
+ }
+ pci_set_master(to_pci_dev(dev_d));
/* disable reverse auto-negotiation */
if (nic->phy == phy_82552_v) {
@@ -3062,10 +3069,11 @@
smartspeed & ~(E100_82552_REV_ANEG));
}
- netif_device_attach(netdev);
if (netif_running(netdev))
e100_up(nic);
+ netif_device_attach(netdev);
+
return 0;
}
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 3d528fb..4d939af 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -161,6 +161,7 @@
__I40E_VSI_OVERFLOW_PROMISC,
__I40E_VSI_REINIT_REQUESTED,
__I40E_VSI_DOWN_REQUESTED,
+ __I40E_VSI_RELEASING,
/* This must be last as it determines the size of the BITMAP */
__I40E_VSI_STATE_SIZE__,
};
@@ -1247,6 +1248,7 @@
void i40e_ptp_init(struct i40e_pf *pf);
void i40e_ptp_stop(struct i40e_pf *pf);
int i40e_ptp_alloc_pins(struct i40e_pf *pf);
+int i40e_update_adq_vsi_queues(struct i40e_vsi *vsi, int vsi_offset);
int i40e_is_vsi_uplink_mode_veb(struct i40e_vsi *vsi);
i40e_status i40e_get_partition_bw_setting(struct i40e_pf *pf);
i40e_status i40e_set_partition_bw_setting(struct i40e_pf *pf);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index ba86213..e118cf9 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -1790,6 +1790,7 @@
bool is_add)
{
struct i40e_pf *pf = vsi->back;
+ u16 num_tc_qps = 0;
u16 sections = 0;
u8 netdev_tc = 0;
u16 numtc = 1;
@@ -1797,13 +1798,33 @@
u8 offset;
u16 qmap;
int i;
- u16 num_tc_qps = 0;
sections = I40E_AQ_VSI_PROP_QUEUE_MAP_VALID;
offset = 0;
+ /* zero out queue mapping, it will get updated on the end of the function */
+ memset(ctxt->info.queue_mapping, 0, sizeof(ctxt->info.queue_mapping));
+
+ if (vsi->type == I40E_VSI_MAIN) {
+ /* This code helps add more queue to the VSI if we have
+ * more cores than RSS can support, the higher cores will
+ * be served by ATR or other filters. Furthermore, the
+ * non-zero req_queue_pairs says that user requested a new
+ * queue count via ethtool's set_channels, so use this
+ * value for queues distribution across traffic classes
+ */
+ if (vsi->req_queue_pairs > 0)
+ vsi->num_queue_pairs = vsi->req_queue_pairs;
+ else if (pf->flags & I40E_FLAG_MSIX_ENABLED)
+ vsi->num_queue_pairs = pf->num_lan_msix;
+ }
/* Number of queues per enabled TC */
- num_tc_qps = vsi->alloc_queue_pairs;
+ if (vsi->type == I40E_VSI_MAIN ||
+ (vsi->type == I40E_VSI_SRIOV && vsi->num_queue_pairs != 0))
+ num_tc_qps = vsi->num_queue_pairs;
+ else
+ num_tc_qps = vsi->alloc_queue_pairs;
+
if (enabled_tc && (vsi->back->flags & I40E_FLAG_DCB_ENABLED)) {
/* Find numtc from enabled TC bitmap */
for (i = 0, numtc = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) {
@@ -1881,15 +1902,11 @@
}
ctxt->info.tc_mapping[i] = cpu_to_le16(qmap);
}
-
- /* Set actual Tx/Rx queue pairs */
- vsi->num_queue_pairs = offset;
- if ((vsi->type == I40E_VSI_MAIN) && (numtc == 1)) {
- if (vsi->req_queue_pairs > 0)
- vsi->num_queue_pairs = vsi->req_queue_pairs;
- else if (pf->flags & I40E_FLAG_MSIX_ENABLED)
- vsi->num_queue_pairs = pf->num_lan_msix;
- }
+ /* Do not change previously set num_queue_pairs for PFs and VFs*/
+ if ((vsi->type == I40E_VSI_MAIN && numtc != 1) ||
+ (vsi->type == I40E_VSI_SRIOV && vsi->num_queue_pairs == 0) ||
+ (vsi->type != I40E_VSI_MAIN && vsi->type != I40E_VSI_SRIOV))
+ vsi->num_queue_pairs = offset;
/* Scheduler section valid can only be set for ADD VSI */
if (is_add) {
@@ -2623,7 +2640,8 @@
for (v = 0; v < pf->num_alloc_vsi; v++) {
if (pf->vsi[v] &&
- (pf->vsi[v]->flags & I40E_VSI_FLAG_FILTER_CHANGED)) {
+ (pf->vsi[v]->flags & I40E_VSI_FLAG_FILTER_CHANGED) &&
+ !test_bit(__I40E_VSI_RELEASING, pf->vsi[v]->state)) {
int ret = i40e_sync_vsi_filters(pf->vsi[v]);
if (ret) {
@@ -5427,6 +5445,58 @@
}
/**
+ * i40e_update_adq_vsi_queues - update queue mapping for ADq VSI
+ * @vsi: the VSI being reconfigured
+ * @vsi_offset: offset from main VF VSI
+ */
+int i40e_update_adq_vsi_queues(struct i40e_vsi *vsi, int vsi_offset)
+{
+ struct i40e_vsi_context ctxt = {};
+ struct i40e_pf *pf;
+ struct i40e_hw *hw;
+ int ret;
+
+ if (!vsi)
+ return I40E_ERR_PARAM;
+ pf = vsi->back;
+ hw = &pf->hw;
+
+ ctxt.seid = vsi->seid;
+ ctxt.pf_num = hw->pf_id;
+ ctxt.vf_num = vsi->vf_id + hw->func_caps.vf_base_id + vsi_offset;
+ ctxt.uplink_seid = vsi->uplink_seid;
+ ctxt.connection_type = I40E_AQ_VSI_CONN_TYPE_NORMAL;
+ ctxt.flags = I40E_AQ_VSI_TYPE_VF;
+ ctxt.info = vsi->info;
+
+ i40e_vsi_setup_queue_map(vsi, &ctxt, vsi->tc_config.enabled_tc,
+ false);
+ if (vsi->reconfig_rss) {
+ vsi->rss_size = min_t(int, pf->alloc_rss_size,
+ vsi->num_queue_pairs);
+ ret = i40e_vsi_config_rss(vsi);
+ if (ret) {
+ dev_info(&pf->pdev->dev, "Failed to reconfig rss for num_queues\n");
+ return ret;
+ }
+ vsi->reconfig_rss = false;
+ }
+
+ ret = i40e_aq_update_vsi_params(hw, &ctxt, NULL);
+ if (ret) {
+ dev_info(&pf->pdev->dev, "Update vsi config failed, err %s aq_err %s\n",
+ i40e_stat_str(hw, ret),
+ i40e_aq_str(hw, hw->aq.asq_last_status));
+ return ret;
+ }
+ /* update the local VSI info with updated queue map */
+ i40e_vsi_update_queue_map(vsi, &ctxt);
+ vsi->info.valid_sections = 0;
+
+ return ret;
+}
+
+/**
* i40e_vsi_config_tc - Configure VSI Tx Scheduler for given TC map
* @vsi: VSI to be configured
* @enabled_tc: TC bitmap
@@ -5717,24 +5787,6 @@
}
/**
- * i40e_is_any_channel - channel exist or not
- * @vsi: ptr to VSI to which channels are associated with
- *
- * Returns true or false if channel(s) exist for associated VSI or not
- **/
-static bool i40e_is_any_channel(struct i40e_vsi *vsi)
-{
- struct i40e_channel *ch, *ch_tmp;
-
- list_for_each_entry_safe(ch, ch_tmp, &vsi->ch_list, list) {
- if (ch->initialized)
- return true;
- }
-
- return false;
-}
-
-/**
* i40e_get_max_queues_for_channel
* @vsi: ptr to VSI to which channels are associated with
*
@@ -6240,26 +6292,15 @@
/* By default we are in VEPA mode, if this is the first VF/VMDq
* VSI to be added switch to VEB mode.
*/
- if ((!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) ||
- (!i40e_is_any_channel(vsi))) {
- if (!is_power_of_2(vsi->tc_config.tc_info[0].qcount)) {
- dev_dbg(&pf->pdev->dev,
- "Failed to create channel. Override queues (%u) not power of 2\n",
- vsi->tc_config.tc_info[0].qcount);
- return -EINVAL;
- }
- if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) {
- pf->flags |= I40E_FLAG_VEB_MODE_ENABLED;
+ if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) {
+ pf->flags |= I40E_FLAG_VEB_MODE_ENABLED;
- if (vsi->type == I40E_VSI_MAIN) {
- if (pf->flags & I40E_FLAG_TC_MQPRIO)
- i40e_do_reset(pf, I40E_PF_RESET_FLAG,
- true);
- else
- i40e_do_reset_safe(pf,
- I40E_PF_RESET_FLAG);
- }
+ if (vsi->type == I40E_VSI_MAIN) {
+ if (pf->flags & I40E_FLAG_TC_MQPRIO)
+ i40e_do_reset(pf, I40E_PF_RESET_FLAG, true);
+ else
+ i40e_do_reset_safe(pf, I40E_PF_RESET_FLAG);
}
/* now onwards for main VSI, number of queues will be value
* of TC0's queue count
@@ -7912,12 +7953,20 @@
vsi->seid);
need_reset = true;
goto exit;
- } else {
- dev_info(&vsi->back->pdev->dev,
- "Setup channel (id:%u) utilizing num_queues %d\n",
- vsi->seid, vsi->tc_config.tc_info[0].qcount);
+ } else if (enabled_tc &&
+ (!is_power_of_2(vsi->tc_config.tc_info[0].qcount))) {
+ netdev_info(netdev,
+ "Failed to create channel. Override queues (%u) not power of 2\n",
+ vsi->tc_config.tc_info[0].qcount);
+ ret = -EINVAL;
+ need_reset = true;
+ goto exit;
}
+ dev_info(&vsi->back->pdev->dev,
+ "Setup channel (id:%u) utilizing num_queues %d\n",
+ vsi->seid, vsi->tc_config.tc_info[0].qcount);
+
if (pf->flags & I40E_FLAG_TC_MQPRIO) {
if (vsi->mqprio_qopt.max_rate[0]) {
u64 max_tx_rate = vsi->mqprio_qopt.max_rate[0];
@@ -8482,9 +8531,8 @@
err = i40e_add_del_cloud_filter(vsi, filter, true);
if (err) {
- dev_err(&pf->pdev->dev,
- "Failed to add cloud filter, err %s\n",
- i40e_stat_str(&pf->hw, err));
+ dev_err(&pf->pdev->dev, "Failed to add cloud filter, err %d\n",
+ err);
goto err;
}
@@ -13771,7 +13819,7 @@
dev_info(&pf->pdev->dev, "Can't remove PF VSI\n");
return -ENODEV;
}
-
+ set_bit(__I40E_VSI_RELEASING, vsi->state);
uplink_seid = vsi->uplink_seid;
if (vsi->type != I40E_VSI_SRIOV) {
if (vsi->netdev_registered) {
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 472f56b..80ae264 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -183,17 +183,18 @@
/***********************misc routines*****************************/
/**
- * i40e_vc_disable_vf
+ * i40e_vc_reset_vf
* @vf: pointer to the VF info
- *
- * Disable the VF through a SW reset.
+ * @notify_vf: notify vf about reset or not
+ * Reset VF handler.
**/
-static inline void i40e_vc_disable_vf(struct i40e_vf *vf)
+static void i40e_vc_reset_vf(struct i40e_vf *vf, bool notify_vf)
{
struct i40e_pf *pf = vf->pf;
int i;
- i40e_vc_notify_vf_reset(vf);
+ if (notify_vf)
+ i40e_vc_notify_vf_reset(vf);
/* We want to ensure that an actual reset occurs initiated after this
* function was called. However, we do not want to wait forever, so
@@ -211,9 +212,14 @@
usleep_range(10000, 20000);
}
- dev_warn(&vf->pf->pdev->dev,
- "Failed to initiate reset for VF %d after 200 milliseconds\n",
- vf->vf_id);
+ if (notify_vf)
+ dev_warn(&vf->pf->pdev->dev,
+ "Failed to initiate reset for VF %d after 200 milliseconds\n",
+ vf->vf_id);
+ else
+ dev_dbg(&vf->pf->pdev->dev,
+ "Failed to initiate reset for VF %d after 200 milliseconds\n",
+ vf->vf_id);
}
/**
@@ -674,14 +680,13 @@
u16 vsi_queue_id,
struct virtchnl_rxq_info *info)
{
+ u16 pf_queue_id = i40e_vc_get_pf_queue_id(vf, vsi_id, vsi_queue_id);
struct i40e_pf *pf = vf->pf;
+ struct i40e_vsi *vsi = pf->vsi[vf->lan_vsi_idx];
struct i40e_hw *hw = &pf->hw;
struct i40e_hmc_obj_rxq rx_ctx;
- u16 pf_queue_id;
int ret = 0;
- pf_queue_id = i40e_vc_get_pf_queue_id(vf, vsi_id, vsi_queue_id);
-
/* clear the context structure first */
memset(&rx_ctx, 0, sizeof(struct i40e_hmc_obj_rxq));
@@ -719,6 +724,10 @@
}
rx_ctx.rxmax = info->max_pkt_size;
+ /* if port VLAN is configured increase the max packet size */
+ if (vsi->info.pvid)
+ rx_ctx.rxmax += VLAN_HLEN;
+
/* enable 32bytes desc always */
rx_ctx.dsize = 1;
@@ -2106,20 +2115,6 @@
}
/**
- * i40e_vc_reset_vf_msg
- * @vf: pointer to the VF info
- *
- * called from the VF to reset itself,
- * unlike other virtchnl messages, PF driver
- * doesn't send the response back to the VF
- **/
-static void i40e_vc_reset_vf_msg(struct i40e_vf *vf)
-{
- if (test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states))
- i40e_reset_vf(vf, false);
-}
-
-/**
* i40e_vc_config_promiscuous_mode_msg
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
@@ -2217,11 +2212,12 @@
struct virtchnl_vsi_queue_config_info *qci =
(struct virtchnl_vsi_queue_config_info *)msg;
struct virtchnl_queue_pair_info *qpi;
- struct i40e_pf *pf = vf->pf;
u16 vsi_id, vsi_queue_id = 0;
- u16 num_qps_all = 0;
+ struct i40e_pf *pf = vf->pf;
i40e_status aq_ret = 0;
int i, j = 0, idx = 0;
+ struct i40e_vsi *vsi;
+ u16 num_qps_all = 0;
if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
aq_ret = I40E_ERR_PARAM;
@@ -2310,9 +2306,15 @@
pf->vsi[vf->lan_vsi_idx]->num_queue_pairs =
qci->num_queue_pairs;
} else {
- for (i = 0; i < vf->num_tc; i++)
- pf->vsi[vf->ch[i].vsi_idx]->num_queue_pairs =
- vf->ch[i].num_qps;
+ for (i = 0; i < vf->num_tc; i++) {
+ vsi = pf->vsi[vf->ch[i].vsi_idx];
+ vsi->num_queue_pairs = vf->ch[i].num_qps;
+
+ if (i40e_update_adq_vsi_queues(vsi, i)) {
+ aq_ret = I40E_ERR_CONFIG;
+ goto error_param;
+ }
+ }
}
error_param:
@@ -2607,8 +2609,7 @@
} else {
/* successful request */
vf->num_req_queues = req_pairs;
- i40e_vc_notify_vf_reset(vf);
- i40e_reset_vf(vf, false);
+ i40e_vc_reset_vf(vf, true);
return 0;
}
@@ -3803,8 +3804,7 @@
vf->num_req_queues = 0;
/* reset the VF in order to allocate resources */
- i40e_vc_notify_vf_reset(vf);
- i40e_reset_vf(vf, false);
+ i40e_vc_reset_vf(vf, true);
return I40E_SUCCESS;
@@ -3844,8 +3844,7 @@
}
/* reset the VF in order to allocate resources */
- i40e_vc_notify_vf_reset(vf);
- i40e_reset_vf(vf, false);
+ i40e_vc_reset_vf(vf, true);
return I40E_SUCCESS;
@@ -3907,7 +3906,7 @@
i40e_vc_notify_vf_link_state(vf);
break;
case VIRTCHNL_OP_RESET_VF:
- i40e_vc_reset_vf_msg(vf);
+ i40e_vc_reset_vf(vf, false);
ret = 0;
break;
case VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE:
@@ -4161,7 +4160,7 @@
/* Force the VF interface down so it has to bring up with new MAC
* address
*/
- i40e_vc_disable_vf(vf);
+ i40e_vc_reset_vf(vf, true);
dev_info(&pf->pdev->dev, "Bring down and up the VF interface to make this change effective.\n");
error_param:
@@ -4170,34 +4169,6 @@
}
/**
- * i40e_vsi_has_vlans - True if VSI has configured VLANs
- * @vsi: pointer to the vsi
- *
- * Check if a VSI has configured any VLANs. False if we have a port VLAN or if
- * we have no configured VLANs. Do not call while holding the
- * mac_filter_hash_lock.
- */
-static bool i40e_vsi_has_vlans(struct i40e_vsi *vsi)
-{
- bool have_vlans;
-
- /* If we have a port VLAN, then the VSI cannot have any VLANs
- * configured, as all MAC/VLAN filters will be assigned to the PVID.
- */
- if (vsi->info.pvid)
- return false;
-
- /* Since we don't have a PVID, we know that if the device is in VLAN
- * mode it must be because of a VLAN filter configured on this VSI.
- */
- spin_lock_bh(&vsi->mac_filter_hash_lock);
- have_vlans = i40e_is_vsi_in_vlan(vsi);
- spin_unlock_bh(&vsi->mac_filter_hash_lock);
-
- return have_vlans;
-}
-
-/**
* i40e_ndo_set_vf_port_vlan
* @netdev: network interface device structure
* @vf_id: VF identifier
@@ -4253,19 +4224,9 @@
/* duplicate request, so just return success */
goto error_pvid;
- if (i40e_vsi_has_vlans(vsi)) {
- dev_err(&pf->pdev->dev,
- "VF %d has already configured VLAN filters and the administrator is requesting a port VLAN override.\nPlease unload and reload the VF driver for this change to take effect.\n",
- vf_id);
- /* Administrator Error - knock the VF offline until he does
- * the right thing by reconfiguring his network correctly
- * and then reloading the VF driver.
- */
- i40e_vc_disable_vf(vf);
- /* During reset the VF got a new VSI, so refresh the pointer. */
- vsi = pf->vsi[vf->lan_vsi_idx];
- }
-
+ i40e_vc_reset_vf(vf, true);
+ /* During reset the VF got a new VSI, so refresh a pointer. */
+ vsi = pf->vsi[vf->lan_vsi_idx];
/* Locked once because multiple functions below iterate list */
spin_lock_bh(&vsi->mac_filter_hash_lock);
@@ -4641,7 +4602,7 @@
goto out;
vf->trusted = setting;
- i40e_vc_disable_vf(vf);
+ i40e_vc_reset_vf(vf, true);
dev_info(&pf->pdev->dev, "VF %u is now %strusted\n",
vf_id, setting ? "" : "un");
diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h
index e6e7c1d..75635bd 100644
--- a/drivers/net/ethernet/intel/iavf/iavf.h
+++ b/drivers/net/ethernet/intel/iavf/iavf.h
@@ -39,6 +39,7 @@
#include "iavf_txrx.h"
#include "iavf_fdir.h"
#include "iavf_adv_rss.h"
+#include <linux/bitmap.h>
#define DEFAULT_DEBUG_LEVEL_SHIFT 3
#define PFX "iavf: "
diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
index 5a359a0..144a776 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
@@ -1776,6 +1776,7 @@
{
struct iavf_adapter *adapter = netdev_priv(netdev);
u32 num_req = ch->combined_count;
+ int i;
if ((adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) &&
adapter->num_tc) {
@@ -1786,7 +1787,7 @@
/* All of these should have already been checked by ethtool before this
* even gets to us, but just to be sure.
*/
- if (num_req > adapter->vsi_res->num_queue_pairs)
+ if (num_req == 0 || num_req > adapter->vsi_res->num_queue_pairs)
return -EINVAL;
if (num_req == adapter->num_active_queues)
@@ -1798,6 +1799,20 @@
adapter->num_req_queues = num_req;
adapter->flags |= IAVF_FLAG_REINIT_ITR_NEEDED;
iavf_schedule_reset(adapter);
+
+ /* wait for the reset is done */
+ for (i = 0; i < IAVF_RESET_WAIT_COMPLETE_COUNT; i++) {
+ msleep(IAVF_RESET_WAIT_MS);
+ if (adapter->flags & IAVF_FLAG_RESET_PENDING)
+ continue;
+ break;
+ }
+ if (i == IAVF_RESET_WAIT_COMPLETE_COUNT) {
+ adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED;
+ adapter->num_active_queues = num_req;
+ return -EOPNOTSUPP;
+ }
+
return 0;
}
@@ -1844,14 +1859,13 @@
if (hfunc)
*hfunc = ETH_RSS_HASH_TOP;
- if (!indir)
- return 0;
+ if (key)
+ memcpy(key, adapter->rss_key, adapter->rss_key_size);
- memcpy(key, adapter->rss_key, adapter->rss_key_size);
-
- /* Each 32 bits pointed by 'indir' is stored with a lut entry */
- for (i = 0; i < adapter->rss_lut_size; i++)
- indir[i] = (u32)adapter->rss_lut[i];
+ if (indir)
+ /* Each 32 bits pointed by 'indir' is stored with a lut entry */
+ for (i = 0; i < adapter->rss_lut_size; i++)
+ indir[i] = (u32)adapter->rss_lut[i];
return 0;
}
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 847d67e..336e6bf9 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -697,6 +697,23 @@
}
/**
+ * iavf_restore_filters
+ * @adapter: board private structure
+ *
+ * Restore existing non MAC filters when VF netdev comes back up
+ **/
+static void iavf_restore_filters(struct iavf_adapter *adapter)
+{
+ /* re-add all VLAN filters */
+ if (VLAN_ALLOWED(adapter)) {
+ u16 vid;
+
+ for_each_set_bit(vid, adapter->vsi.active_vlans, VLAN_N_VID)
+ iavf_add_vlan(adapter, vid);
+ }
+}
+
+/**
* iavf_vlan_rx_add_vid - Add a VLAN filter to a device
* @netdev: network device struct
* @proto: unused protocol data
@@ -709,8 +726,11 @@
if (!VLAN_ALLOWED(adapter))
return -EIO;
+
if (iavf_add_vlan(adapter, vid) == NULL)
return -ENOMEM;
+
+ set_bit(vid, adapter->vsi.active_vlans);
return 0;
}
@@ -725,11 +745,13 @@
{
struct iavf_adapter *adapter = netdev_priv(netdev);
- if (VLAN_ALLOWED(adapter)) {
- iavf_del_vlan(adapter, vid);
- return 0;
- }
- return -EIO;
+ if (!VLAN_ALLOWED(adapter))
+ return -EIO;
+
+ iavf_del_vlan(adapter, vid);
+ clear_bit(vid, adapter->vsi.active_vlans);
+
+ return 0;
}
/**
@@ -1639,8 +1661,7 @@
iavf_set_promiscuous(adapter, FLAG_VF_MULTICAST_PROMISC);
return 0;
}
-
- if ((adapter->aq_required & IAVF_FLAG_AQ_RELEASE_PROMISC) &&
+ if ((adapter->aq_required & IAVF_FLAG_AQ_RELEASE_PROMISC) ||
(adapter->aq_required & IAVF_FLAG_AQ_RELEASE_ALLMULTI)) {
iavf_set_promiscuous(adapter, 0);
return 0;
@@ -2123,8 +2144,8 @@
iavf_free_misc_irq(adapter);
iavf_reset_interrupt_capability(adapter);
- iavf_free_queues(adapter);
iavf_free_q_vectors(adapter);
+ iavf_free_queues(adapter);
memset(adapter->vf_res, 0, IAVF_VIRTCHNL_VF_RESOURCE_SIZE);
iavf_shutdown_adminq(&adapter->hw);
adapter->netdev->flags &= ~IFF_UP;
@@ -2410,7 +2431,7 @@
/* check for error indications */
val = rd32(hw, hw->aq.arq.len);
- if (val == 0xdeadbeef) /* indicates device in reset */
+ if (val == 0xdeadbeef || val == 0xffffffff) /* device in reset */
goto freedom;
oldval = val;
if (val & IAVF_VF_ARQLEN1_ARQVFE_MASK) {
@@ -3095,8 +3116,10 @@
return -ENOMEM;
while (!mutex_trylock(&adapter->crit_lock)) {
- if (--count == 0)
- goto err;
+ if (--count == 0) {
+ kfree(filter);
+ return err;
+ }
udelay(1);
}
@@ -3107,11 +3130,11 @@
/* start out with flow type and eth type IPv4 to begin with */
filter->f.flow_type = VIRTCHNL_TCP_V4_FLOW;
err = iavf_parse_cls_flower(adapter, cls_flower, filter);
- if (err < 0)
+ if (err)
goto err;
err = iavf_handle_tclass(adapter, tc, filter);
- if (err < 0)
+ if (err)
goto err;
/* add filter to the list */
@@ -3308,6 +3331,9 @@
spin_unlock_bh(&adapter->mac_vlan_list_lock);
+ /* Restore VLAN filters that were removed with IFF_DOWN */
+ iavf_restore_filters(adapter);
+
iavf_configure(adapter);
iavf_up_complete(adapter);
@@ -3503,7 +3529,8 @@
{
struct iavf_adapter *adapter = netdev_priv(netdev);
- if (!(adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN))
+ if (adapter->vf_res &&
+ !(adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN))
features &= ~(NETIF_F_HW_VLAN_CTAG_TX |
NETIF_F_HW_VLAN_CTAG_RX |
NETIF_F_HW_VLAN_CTAG_FILTER);
diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c
index 6433c90..072391c 100644
--- a/drivers/net/ethernet/lantiq_etop.c
+++ b/drivers/net/ethernet/lantiq_etop.c
@@ -25,6 +25,7 @@
#include <linux/io.h>
#include <linux/dma-mapping.h>
#include <linux/module.h>
+#include <linux/property.h>
#include <asm/checksum.h>
@@ -239,6 +240,7 @@
{
struct ltq_etop_priv *priv = netdev_priv(dev);
int i;
+ int err;
ltq_pmu_enable(PMU_PPE);
@@ -273,7 +275,13 @@
if (IS_TX(i)) {
ltq_dma_alloc_tx(&ch->dma);
- request_irq(irq, ltq_etop_dma_irq, 0, "etop_tx", priv);
+ err = request_irq(irq, ltq_etop_dma_irq, 0, "etop_tx", priv);
+ if (err) {
+ netdev_err(dev,
+ "Unable to get Tx DMA IRQ %d\n",
+ irq);
+ return err;
+ }
} else if (IS_RX(i)) {
ltq_dma_alloc_rx(&ch->dma);
for (ch->dma.desc = 0; ch->dma.desc < LTQ_DESC_NUM;
@@ -281,7 +289,13 @@
if (ltq_etop_alloc_skb(ch))
return -ENOMEM;
ch->dma.desc = 0;
- request_irq(irq, ltq_etop_dma_irq, 0, "etop_rx", priv);
+ err = request_irq(irq, ltq_etop_dma_irq, 0, "etop_rx", priv);
+ if (err) {
+ netdev_err(dev,
+ "Unable to get Rx DMA IRQ %d\n",
+ irq);
+ return err;
+ }
}
ch->dma.irq = irq;
}
@@ -726,7 +740,7 @@
},
};
-int __init
+static int __init
init_ltq_etop(void)
{
int ret = platform_driver_probe(<q_mii_driver, ltq_etop_probe);
diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c
index 62a97c4..ef87897 100644
--- a/drivers/net/ethernet/marvell/mvmdio.c
+++ b/drivers/net/ethernet/marvell/mvmdio.c
@@ -429,12 +429,14 @@
};
MODULE_DEVICE_TABLE(of, orion_mdio_match);
+#ifdef CONFIG_ACPI
static const struct acpi_device_id orion_mdio_acpi_match[] = {
{ "MRVL0100", BUS_TYPE_SMI },
{ "MRVL0101", BUS_TYPE_XSMI },
{ },
};
MODULE_DEVICE_TABLE(acpi, orion_mdio_acpi_match);
+#endif
static struct platform_driver orion_mdio_driver = {
.probe = orion_mdio_probe,
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
index c7fd466..a09a507 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
@@ -236,10 +236,11 @@
u64 lmt_addr, val, tbl_base;
int pf, vf, num_vfs, hw_vfs;
void __iomem *lmt_map_base;
- int index = 0, off = 0;
- int bytes_not_copied;
int buf_size = 10240;
+ size_t off = 0;
+ int index = 0;
char *buf;
+ int ret;
/* don't allow partial reads */
if (*ppos != 0)
@@ -303,15 +304,17 @@
}
off += scnprintf(&buf[off], buf_size - 1 - off, "\n");
- bytes_not_copied = copy_to_user(buffer, buf, off);
+ ret = min(off, count);
+ if (copy_to_user(buffer, buf, ret))
+ ret = -EFAULT;
kfree(buf);
iounmap(lmt_map_base);
- if (bytes_not_copied)
- return -EFAULT;
+ if (ret < 0)
+ return ret;
- *ppos = off;
- return off;
+ *ppos = ret;
+ return ret;
}
RVU_DEBUG_FOPS(lmtst_map_table, lmtst_map_table_display, NULL);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index f71ec4d..8eaa24d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -339,6 +339,8 @@
case MLX5_CMD_OP_PAGE_FAULT_RESUME:
case MLX5_CMD_OP_QUERY_ESW_FUNCTIONS:
case MLX5_CMD_OP_DEALLOC_SF:
+ case MLX5_CMD_OP_DESTROY_UCTX:
+ case MLX5_CMD_OP_DESTROY_UMEM:
return MLX5_CMD_STAT_OK;
case MLX5_CMD_OP_QUERY_HCA_CAP:
@@ -464,9 +466,7 @@
case MLX5_CMD_OP_MODIFY_GENERAL_OBJECT:
case MLX5_CMD_OP_QUERY_GENERAL_OBJECT:
case MLX5_CMD_OP_CREATE_UCTX:
- case MLX5_CMD_OP_DESTROY_UCTX:
case MLX5_CMD_OP_CREATE_UMEM:
- case MLX5_CMD_OP_DESTROY_UMEM:
case MLX5_CMD_OP_ALLOC_MEMIC:
case MLX5_CMD_OP_MODIFY_XRQ:
case MLX5_CMD_OP_RELEASE_XRQ_ERROR:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cq.c b/drivers/net/ethernet/mellanox/mlx5/core/cq.c
index 02e77ff..5371ad0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cq.c
@@ -164,13 +164,14 @@
MLX5_SET(destroy_cq_in, in, cqn, cq->cqn);
MLX5_SET(destroy_cq_in, in, uid, cq->uid);
err = mlx5_cmd_exec_in(dev, destroy_cq, in);
+ if (err)
+ return err;
synchronize_irq(cq->irqn);
-
mlx5_cq_put(cq);
wait_for_completion(&cq->free);
- return err;
+ return 0;
}
EXPORT_SYMBOL(mlx5_core_destroy_cq);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
index 07c8d981..10d1950 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
@@ -507,6 +507,8 @@
if (!mlx5_debugfs_root)
return;
- if (cq->dbg)
+ if (cq->dbg) {
rem_res_tree(cq->dbg);
+ cq->dbg = NULL;
+ }
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
index c1c6e74..2445e2a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
@@ -1356,9 +1356,13 @@
int
mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv,
struct mlx5_flow_attr *attr,
+ struct mlx5e_tc_mod_hdr_acts *mod_acts,
const struct flow_action_entry *act,
struct netlink_ext_ack *extack)
{
+ bool clear_action = act->ct.action & TCA_CT_ACT_CLEAR;
+ int err;
+
if (!priv) {
NL_SET_ERR_MSG_MOD(extack,
"offload of ct action isn't available");
@@ -1369,6 +1373,17 @@
attr->ct_attr.ct_action = act->ct.action;
attr->ct_attr.nf_ft = act->ct.flow_table;
+ if (!clear_action)
+ goto out;
+
+ err = mlx5_tc_ct_entry_set_registers(priv, mod_acts, 0, 0, 0, 0);
+ if (err) {
+ NL_SET_ERR_MSG_MOD(extack, "Failed to set registers for ct clear");
+ return err;
+ }
+ attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
+
+out:
return 0;
}
@@ -1898,23 +1913,16 @@
memcpy(pre_ct_attr, attr, attr_sz);
- err = mlx5_tc_ct_entry_set_registers(ct_priv, mod_acts, 0, 0, 0, 0);
- if (err) {
- ct_dbg("Failed to set register for ct clear");
- goto err_set_registers;
- }
-
mod_hdr = mlx5_modify_header_alloc(priv->mdev, ct_priv->ns_type,
mod_acts->num_actions,
mod_acts->actions);
if (IS_ERR(mod_hdr)) {
err = PTR_ERR(mod_hdr);
ct_dbg("Failed to add create ct clear mod hdr");
- goto err_set_registers;
+ goto err_mod_hdr;
}
pre_ct_attr->modify_hdr = mod_hdr;
- pre_ct_attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
rule = mlx5_tc_rule_insert(priv, orig_spec, pre_ct_attr);
if (IS_ERR(rule)) {
@@ -1930,7 +1938,7 @@
err_insert:
mlx5_modify_header_dealloc(priv->mdev, mod_hdr);
-err_set_registers:
+err_mod_hdr:
netdev_warn(priv->netdev,
"Failed to offload ct clear flow, err %d\n", err);
kfree(pre_ct_attr);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h
index 363329f..99662af 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h
@@ -110,6 +110,7 @@
int
mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv,
struct mlx5_flow_attr *attr,
+ struct mlx5e_tc_mod_hdr_acts *mod_acts,
const struct flow_action_entry *act,
struct netlink_ext_ack *extack);
@@ -172,6 +173,7 @@
static inline int
mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv,
struct mlx5_flow_attr *attr,
+ struct mlx5e_tc_mod_hdr_acts *mod_acts,
const struct flow_action_entry *act,
struct netlink_ext_ack *extack)
{
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h
index 8f64f2c..b689701 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h
@@ -102,6 +102,7 @@
refcount_t refcnt;
struct rcu_head rcu_head;
struct completion init_done;
+ struct completion del_hw_done;
int tunnel_id; /* the mapped tunnel id of this flow */
struct mlx5_flow_attr *attr;
};
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
index 660cca7..042b1ab 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
@@ -245,8 +245,14 @@
struct list_head *flow_list,
int index)
{
- if (IS_ERR(mlx5e_flow_get(flow)))
+ if (IS_ERR(mlx5e_flow_get(flow))) {
+ /* Flow is being deleted concurrently. Wait for it to be
+ * unoffloaded from hardware, otherwise deleting encap will
+ * fail.
+ */
+ wait_for_completion(&flow->del_hw_done);
return;
+ }
wait_for_completion(&flow->init_done);
flow->tmp_entry_index = index;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
index 62abce0..a2a9f685 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
@@ -55,6 +55,7 @@
DECLARE_BITMAP(flags, MLX5E_NUM_PRIV_RX_FLAGS);
/* resync */
+ spinlock_t lock; /* protects resync fields */
struct mlx5e_ktls_rx_resync_ctx resync;
struct list_head list;
};
@@ -386,14 +387,18 @@
struct mlx5e_icosq *sq;
bool trigger_poll;
- memcpy(info->rec_seq, &priv_rx->resync.sw_rcd_sn_be, sizeof(info->rec_seq));
-
sq = &c->async_icosq;
ktls_resync = sq->ktls_resync;
+ trigger_poll = false;
spin_lock_bh(&ktls_resync->lock);
- list_add_tail(&priv_rx->list, &ktls_resync->list);
- trigger_poll = !test_and_set_bit(MLX5E_SQ_STATE_PENDING_TLS_RX_RESYNC, &sq->state);
+ spin_lock_bh(&priv_rx->lock);
+ memcpy(info->rec_seq, &priv_rx->resync.sw_rcd_sn_be, sizeof(info->rec_seq));
+ if (list_empty(&priv_rx->list)) {
+ list_add_tail(&priv_rx->list, &ktls_resync->list);
+ trigger_poll = !test_and_set_bit(MLX5E_SQ_STATE_PENDING_TLS_RX_RESYNC, &sq->state);
+ }
+ spin_unlock_bh(&priv_rx->lock);
spin_unlock_bh(&ktls_resync->lock);
if (!trigger_poll)
@@ -617,6 +622,8 @@
if (err)
goto err_create_key;
+ INIT_LIST_HEAD(&priv_rx->list);
+ spin_lock_init(&priv_rx->lock);
priv_rx->crypto_info =
*(struct tls12_crypto_info_aes_gcm_128 *)crypto_info;
@@ -730,10 +737,14 @@
priv_rx = list_first_entry(&local_list,
struct mlx5e_ktls_offload_context_rx,
list);
+ spin_lock(&priv_rx->lock);
cseg = post_static_params(sq, priv_rx);
- if (IS_ERR(cseg))
+ if (IS_ERR(cseg)) {
+ spin_unlock(&priv_rx->lock);
break;
- list_del(&priv_rx->list);
+ }
+ list_del_init(&priv_rx->list);
+ spin_unlock(&priv_rx->lock);
db_cseg = cseg;
}
if (db_cseg)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 835caa1c..3d45f4a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1600,6 +1600,7 @@
else
mlx5e_tc_unoffload_fdb_rules(esw, flow, attr);
}
+ complete_all(&flow->del_hw_done);
if (mlx5_flow_has_geneve_opt(flow))
mlx5_geneve_tlv_option_del(priv->mdev->geneve);
@@ -3607,7 +3608,9 @@
attr->dest_chain = act->chain_index;
break;
case FLOW_ACTION_CT:
- err = mlx5_tc_ct_parse_action(get_ct_priv(priv), attr, act, extack);
+ err = mlx5_tc_ct_parse_action(get_ct_priv(priv), attr,
+ &parse_attr->mod_hdr_acts,
+ act, extack);
if (err)
return err;
@@ -4276,7 +4279,9 @@
NL_SET_ERR_MSG_MOD(extack, "Sample action with connection tracking is not supported");
return -EOPNOTSUPP;
}
- err = mlx5_tc_ct_parse_action(get_ct_priv(priv), attr, act, extack);
+ err = mlx5_tc_ct_parse_action(get_ct_priv(priv), attr,
+ &parse_attr->mod_hdr_acts,
+ act, extack);
if (err)
return err;
@@ -4465,6 +4470,7 @@
INIT_LIST_HEAD(&flow->l3_to_l2_reformat);
refcount_set(&flow->refcnt, 1);
init_completion(&flow->init_done);
+ init_completion(&flow->del_hw_done);
*__flow = flow;
*__parse_attr = parse_attr;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index ec136b4..51a8cec 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1305,12 +1305,17 @@
*/
int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs)
{
+ bool toggle_lag;
int ret;
if (!mlx5_esw_allowed(esw))
return 0;
- mlx5_lag_disable_change(esw->dev);
+ toggle_lag = esw->mode == MLX5_ESWITCH_NONE;
+
+ if (toggle_lag)
+ mlx5_lag_disable_change(esw->dev);
+
down_write(&esw->mode_lock);
if (esw->mode == MLX5_ESWITCH_NONE) {
ret = mlx5_eswitch_enable_locked(esw, MLX5_ESWITCH_LEGACY, num_vfs);
@@ -1324,7 +1329,10 @@
esw->esw_funcs.num_vfs = num_vfs;
}
up_write(&esw->mode_lock);
- mlx5_lag_enable_change(esw->dev);
+
+ if (toggle_lag)
+ mlx5_lag_enable_change(esw->dev);
+
return ret;
}
@@ -1572,6 +1580,11 @@
esw->enabled_vports = 0;
esw->mode = MLX5_ESWITCH_NONE;
esw->offloads.inline_mode = MLX5_INLINE_MODE_NONE;
+ if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, reformat) &&
+ MLX5_CAP_ESW_FLOWTABLE_FDB(dev, decap))
+ esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_BASIC;
+ else
+ esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE;
dev->priv.eswitch = esw;
BLOCKING_INIT_NOTIFIER_HEAD(&esw->n_head);
@@ -1934,7 +1947,7 @@
return err;
}
-u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev)
+u8 mlx5_eswitch_mode(const struct mlx5_core_dev *dev)
{
struct mlx5_eswitch *esw = dev->priv.eswitch;
@@ -1948,7 +1961,7 @@
struct mlx5_eswitch *esw;
esw = dev->priv.eswitch;
- return mlx5_esw_allowed(esw) ? esw->offloads.encap :
+ return (mlx5_eswitch_mode(dev) == MLX5_ESWITCH_OFFLOADS) ? esw->offloads.encap :
DEVLINK_ESWITCH_ENCAP_MODE_NONE;
}
EXPORT_SYMBOL(mlx5_eswitch_get_encap_mode);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index f4eaa58..a464556 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -3183,12 +3183,6 @@
u64 mapping_id;
int err;
- if (MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, reformat) &&
- MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, decap))
- esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_BASIC;
- else
- esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE;
-
mutex_init(&esw->offloads.termtbl_mutex);
mlx5_rdma_enable_roce(esw->dev);
@@ -3286,7 +3280,6 @@
esw_offloads_metadata_uninit(esw);
mlx5_rdma_disable_roce(esw->dev);
mutex_destroy(&esw->offloads.termtbl_mutex);
- esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE;
}
static int esw_mode_from_devlink(u16 mode, u16 *mlx5_mode)
@@ -3630,7 +3623,7 @@
*encap = esw->offloads.encap;
unlock:
up_write(&esw->mode_lock);
- return 0;
+ return err;
}
static bool
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
index 31c99d5..7e0e04c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
@@ -40,7 +40,7 @@
#define MLX5_FC_STATS_PERIOD msecs_to_jiffies(1000)
/* Max number of counters to query in bulk read is 32K */
#define MLX5_SW_MAX_COUNTERS_BULK BIT(15)
-#define MLX5_SF_NUM_COUNTERS_BULK 6
+#define MLX5_SF_NUM_COUNTERS_BULK 8
#define MLX5_FC_POOL_MAX_THRESHOLD BIT(18)
#define MLX5_FC_POOL_USED_BUFF_RATIO 10
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index 48d2ea6..4ddf6b3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -615,6 +615,7 @@
bool is_bonded, is_in_lag, mode_supported;
int bond_status = 0;
int num_slaves = 0;
+ int changed = 0;
int idx;
if (!netif_is_lag_master(upper))
@@ -653,27 +654,27 @@
*/
is_in_lag = num_slaves == MLX5_MAX_PORTS && bond_status == 0x3;
- if (!mlx5_lag_is_ready(ldev) && is_in_lag) {
- NL_SET_ERR_MSG_MOD(info->info.extack,
- "Can't activate LAG offload, PF is configured with more than 64 VFs");
- return 0;
- }
-
/* Lag mode must be activebackup or hash. */
mode_supported = tracker->tx_type == NETDEV_LAG_TX_TYPE_ACTIVEBACKUP ||
tracker->tx_type == NETDEV_LAG_TX_TYPE_HASH;
- if (is_in_lag && !mode_supported)
- NL_SET_ERR_MSG_MOD(info->info.extack,
- "Can't activate LAG offload, TX type isn't supported");
-
is_bonded = is_in_lag && mode_supported;
if (tracker->is_bonded != is_bonded) {
tracker->is_bonded = is_bonded;
- return 1;
+ changed = 1;
}
- return 0;
+ if (!is_in_lag)
+ return changed;
+
+ if (!mlx5_lag_is_ready(ldev))
+ NL_SET_ERR_MSG_MOD(info->info.extack,
+ "Can't activate LAG offload, PF is configured with more than 64 VFs");
+ else if (!mode_supported)
+ NL_SET_ERR_MSG_MOD(info->info.extack,
+ "Can't activate LAG offload, TX type isn't supported");
+
+ return changed;
}
static int mlx5_handle_changelowerstate_event(struct mlx5_lag *ldev,
@@ -716,9 +717,6 @@
ldev = container_of(this, struct mlx5_lag, nb);
- if (!mlx5_lag_is_ready(ldev) && event == NETDEV_CHANGELOWERSTATE)
- return NOTIFY_DONE;
-
tracker = ldev->tracker;
switch (event) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c
index 49089cb..8cbd36c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c
@@ -135,25 +135,14 @@
static int dr_domain_query_vport(struct mlx5dr_domain *dmn,
u16 vport_number,
+ bool other_vport,
struct mlx5dr_cmd_vport_cap *vport_caps)
{
- u16 cmd_vport = vport_number;
- bool other_vport = true;
int ret;
- if (vport_number == MLX5_VPORT_UPLINK) {
- dr_domain_fill_uplink_caps(dmn, vport_caps);
- return 0;
- }
-
- if (dmn->info.caps.is_ecpf && vport_number == MLX5_VPORT_ECPF) {
- other_vport = false;
- cmd_vport = 0;
- }
-
ret = mlx5dr_cmd_query_esw_vport_context(dmn->mdev,
other_vport,
- cmd_vport,
+ vport_number,
&vport_caps->icm_address_rx,
&vport_caps->icm_address_tx);
if (ret)
@@ -161,7 +150,7 @@
ret = mlx5dr_cmd_query_gvmi(dmn->mdev,
other_vport,
- cmd_vport,
+ vport_number,
&vport_caps->vport_gvmi);
if (ret)
return ret;
@@ -176,9 +165,15 @@
{
return dr_domain_query_vport(dmn,
dmn->info.caps.is_ecpf ? MLX5_VPORT_ECPF : 0,
+ false,
&dmn->info.caps.vports.esw_manager_caps);
}
+static void dr_domain_query_uplink(struct mlx5dr_domain *dmn)
+{
+ dr_domain_fill_uplink_caps(dmn, &dmn->info.caps.vports.uplink_caps);
+}
+
static struct mlx5dr_cmd_vport_cap *
dr_domain_add_vport_cap(struct mlx5dr_domain *dmn, u16 vport)
{
@@ -190,7 +185,7 @@
if (!vport_caps)
return NULL;
- ret = dr_domain_query_vport(dmn, vport, vport_caps);
+ ret = dr_domain_query_vport(dmn, vport, true, vport_caps);
if (ret) {
kvfree(vport_caps);
return NULL;
@@ -207,16 +202,26 @@
return vport_caps;
}
+static bool dr_domain_is_esw_mgr_vport(struct mlx5dr_domain *dmn, u16 vport)
+{
+ struct mlx5dr_cmd_caps *caps = &dmn->info.caps;
+
+ return (caps->is_ecpf && vport == MLX5_VPORT_ECPF) ||
+ (!caps->is_ecpf && vport == 0);
+}
+
struct mlx5dr_cmd_vport_cap *
mlx5dr_domain_get_vport_cap(struct mlx5dr_domain *dmn, u16 vport)
{
struct mlx5dr_cmd_caps *caps = &dmn->info.caps;
struct mlx5dr_cmd_vport_cap *vport_caps;
- if ((caps->is_ecpf && vport == MLX5_VPORT_ECPF) ||
- (!caps->is_ecpf && vport == 0))
+ if (dr_domain_is_esw_mgr_vport(dmn, vport))
return &caps->vports.esw_manager_caps;
+ if (vport == MLX5_VPORT_UPLINK)
+ return &caps->vports.uplink_caps;
+
vport_load:
vport_caps = xa_load(&caps->vports.vports_caps_xa, vport);
if (vport_caps)
@@ -241,17 +246,6 @@
}
}
-static int dr_domain_query_uplink(struct mlx5dr_domain *dmn)
-{
- struct mlx5dr_cmd_vport_cap *vport_caps;
-
- vport_caps = mlx5dr_domain_get_vport_cap(dmn, MLX5_VPORT_UPLINK);
- if (!vport_caps)
- return -EINVAL;
-
- return 0;
-}
-
static int dr_domain_query_fdb_caps(struct mlx5_core_dev *mdev,
struct mlx5dr_domain *dmn)
{
@@ -281,11 +275,7 @@
goto free_vports_caps_xa;
}
- ret = dr_domain_query_uplink(dmn);
- if (ret) {
- mlx5dr_err(dmn, "Failed to query uplink vport caps (err: %d)", ret);
- goto free_vports_caps_xa;
- }
+ dr_domain_query_uplink(dmn);
return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c
index 75c775b..7933652 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c
@@ -924,11 +924,12 @@
/* Check that all mask data was consumed */
for (i = 0; i < consumed_mask.match_sz; i++) {
- if (consumed_mask.match_buf[i]) {
- mlx5dr_dbg(dmn, "Match param mask contains unsupported parameters\n");
- ret = -EOPNOTSUPP;
- goto free_consumed_mask;
- }
+ if (!((u8 *)consumed_mask.match_buf)[i])
+ continue;
+
+ mlx5dr_dbg(dmn, "Match param mask contains unsupported parameters\n");
+ ret = -EOPNOTSUPP;
+ goto free_consumed_mask;
}
ret = 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
index 3028b776..2333c24 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
@@ -764,6 +764,7 @@
struct mlx5dr_vports {
struct mlx5dr_cmd_vport_cap esw_manager_caps;
+ struct mlx5dr_cmd_vport_cap uplink_caps;
struct xarray vports_caps_xa;
};
diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c
index cc2d907..23a336c 100644
--- a/drivers/net/ethernet/sis/sis900.c
+++ b/drivers/net/ethernet/sis/sis900.c
@@ -392,7 +392,7 @@
/* get MAC address from EEPROM */
for (i = 0; i < 3; i++)
addr[i] = read_eeprom(ioaddr, i + EEPROMMACAddr);
- eth_hw_addr_set(net_dev, (u8 *)addr);
+ eth_hw_addr_set(net_dev, (u8 *)addr);
rc = 1;
break;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
index 8520812..b7c2579 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
@@ -485,8 +485,28 @@
}
#endif /* CONFIG_PM_SLEEP */
-static SIMPLE_DEV_PM_OPS(socfpga_dwmac_pm_ops, stmmac_suspend,
- socfpga_dwmac_resume);
+static int __maybe_unused socfpga_dwmac_runtime_suspend(struct device *dev)
+{
+ struct net_device *ndev = dev_get_drvdata(dev);
+ struct stmmac_priv *priv = netdev_priv(ndev);
+
+ stmmac_bus_clks_config(priv, false);
+
+ return 0;
+}
+
+static int __maybe_unused socfpga_dwmac_runtime_resume(struct device *dev)
+{
+ struct net_device *ndev = dev_get_drvdata(dev);
+ struct stmmac_priv *priv = netdev_priv(ndev);
+
+ return stmmac_bus_clks_config(priv, true);
+}
+
+static const struct dev_pm_ops socfpga_dwmac_pm_ops = {
+ SET_SYSTEM_SLEEP_PM_OPS(stmmac_suspend, socfpga_dwmac_resume)
+ SET_RUNTIME_PM_OPS(socfpga_dwmac_runtime_suspend, socfpga_dwmac_runtime_resume, NULL)
+};
static const struct socfpga_dwmac_ops socfpga_gen5_ops = {
.set_phy_mode = socfpga_gen5_set_phy_mode,
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index d3f350c..2eb2845 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -511,6 +511,14 @@
return true;
}
+static inline u32 stmmac_cdc_adjust(struct stmmac_priv *priv)
+{
+ /* Correct the clk domain crossing(CDC) error */
+ if (priv->plat->has_gmac4 && priv->plat->clk_ptp_rate)
+ return (2 * NSEC_PER_SEC) / priv->plat->clk_ptp_rate;
+ return 0;
+}
+
/* stmmac_get_tx_hwtstamp - get HW TX timestamps
* @priv: driver private structure
* @p : descriptor pointer
@@ -524,7 +532,6 @@
{
struct skb_shared_hwtstamps shhwtstamp;
bool found = false;
- s64 adjust = 0;
u64 ns = 0;
if (!priv->hwts_tx_en)
@@ -543,12 +550,7 @@
}
if (found) {
- /* Correct the clk domain crossing(CDC) error */
- if (priv->plat->has_gmac4 && priv->plat->clk_ptp_rate) {
- adjust += -(2 * (NSEC_PER_SEC /
- priv->plat->clk_ptp_rate));
- ns += adjust;
- }
+ ns -= stmmac_cdc_adjust(priv);
memset(&shhwtstamp, 0, sizeof(struct skb_shared_hwtstamps));
shhwtstamp.hwtstamp = ns_to_ktime(ns);
@@ -573,7 +575,6 @@
{
struct skb_shared_hwtstamps *shhwtstamp = NULL;
struct dma_desc *desc = p;
- u64 adjust = 0;
u64 ns = 0;
if (!priv->hwts_rx_en)
@@ -586,11 +587,7 @@
if (stmmac_get_rx_timestamp_status(priv, p, np, priv->adv_ts)) {
stmmac_get_timestamp(priv, desc, priv->adv_ts, &ns);
- /* Correct the clk domain crossing(CDC) error */
- if (priv->plat->has_gmac4 && priv->plat->clk_ptp_rate) {
- adjust += 2 * (NSEC_PER_SEC / priv->plat->clk_ptp_rate);
- ns -= adjust;
- }
+ ns -= stmmac_cdc_adjust(priv);
netdev_dbg(priv->dev, "get valid RX hw timestamp %llu\n", ns);
shhwtstamp = skb_hwtstamps(skb);
diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c
index bfdf89e..8a19a06 100644
--- a/drivers/net/hamradio/6pack.c
+++ b/drivers/net/hamradio/6pack.c
@@ -306,7 +306,6 @@
{
/* Finish setting up the DEVICE info. */
dev->netdev_ops = &sp_netdev_ops;
- dev->needs_free_netdev = true;
dev->mtu = SIXP_MTU;
dev->hard_header_len = AX25_MAX_HEADER_LEN;
dev->header_ops = &ax25_header_ops;
diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c
index 5528d97..ef790fd 100644
--- a/drivers/net/ipa/ipa_endpoint.c
+++ b/drivers/net/ipa/ipa_endpoint.c
@@ -853,6 +853,7 @@
u32 offset;
u32 val;
+ /* This should only be changed when HOL_BLOCK_EN is disabled */
offset = IPA_REG_ENDP_INIT_HOL_BLOCK_TIMER_N_OFFSET(endpoint_id);
val = hol_block_timer_val(ipa, microseconds);
iowrite32(val, ipa->reg_virt + offset);
@@ -868,6 +869,9 @@
val = enable ? HOL_BLOCK_EN_FMASK : 0;
offset = IPA_REG_ENDP_INIT_HOL_BLOCK_EN_N_OFFSET(endpoint_id);
iowrite32(val, endpoint->ipa->reg_virt + offset);
+ /* When enabling, the register must be written twice for IPA v4.5+ */
+ if (enable && endpoint->ipa->version >= IPA_VERSION_4_5)
+ iowrite32(val, endpoint->ipa->reg_virt + offset);
}
void ipa_endpoint_modem_hol_block_clear_all(struct ipa *ipa)
@@ -880,6 +884,7 @@
if (endpoint->toward_ipa || endpoint->ee_id != GSI_EE_MODEM)
continue;
+ ipa_endpoint_init_hol_block_enable(endpoint, false);
ipa_endpoint_init_hol_block_timer(endpoint, 0);
ipa_endpoint_init_hol_block_enable(endpoint, true);
}
diff --git a/drivers/net/ipa/ipa_resource.c b/drivers/net/ipa/ipa_resource.c
index e3da95d..06cec71 100644
--- a/drivers/net/ipa/ipa_resource.c
+++ b/drivers/net/ipa/ipa_resource.c
@@ -52,7 +52,7 @@
return false;
}
- group_count = data->rsrc_group_src_count;
+ group_count = data->rsrc_group_dst_count;
if (!group_count || group_count > IPA_RESOURCE_GROUP_MAX)
return false;
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index fecc9a1..1572878 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1010,6 +1010,7 @@
{
struct tun_struct *tun = netdev_priv(dev);
int txq = skb->queue_mapping;
+ struct netdev_queue *queue;
struct tun_file *tfile;
int len = skb->len;
@@ -1054,6 +1055,10 @@
if (ptr_ring_produce(&tfile->tx_ring, skb))
goto drop;
+ /* NETIF_F_LLTX requires to do our own update of trans_start */
+ queue = netdev_get_tx_queue(dev, txq);
+ queue->trans_start = jiffies;
+
/* Notify and wake up reader process */
if (tfile->flags & TUN_FASYNC)
kill_fasync(&tfile->fasync, SIGIO, POLL_IN);
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 4a02f33..f9877a3 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -9603,12 +9603,9 @@
netdev->hw_features &= ~NETIF_F_RXCSUM;
}
- if (le16_to_cpu(udev->descriptor.idVendor) == VENDOR_ID_LENOVO) {
- switch (le16_to_cpu(udev->descriptor.idProduct)) {
- case DEVICE_ID_THINKPAD_THUNDERBOLT3_DOCK_GEN2:
- case DEVICE_ID_THINKPAD_USB_C_DOCK_GEN2:
- tp->lenovo_macpassthru = 1;
- }
+ if (udev->parent &&
+ le16_to_cpu(udev->parent->descriptor.idVendor) == VENDOR_ID_LENOVO) {
+ tp->lenovo_macpassthru = 1;
}
if (le16_to_cpu(udev->descriptor.bcdDevice) == 0x3011 && udev->serial &&
diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c
index bae9d42..ecab9064 100644
--- a/drivers/pinctrl/pinctrl-amd.c
+++ b/drivers/pinctrl/pinctrl-amd.c
@@ -598,14 +598,14 @@
#define PIN_IRQ_PENDING (BIT(INTERRUPT_STS_OFF) | BIT(WAKE_STS_OFF))
-static irqreturn_t amd_gpio_irq_handler(int irq, void *dev_id)
+static bool do_amd_gpio_irq_handler(int irq, void *dev_id)
{
struct amd_gpio *gpio_dev = dev_id;
struct gpio_chip *gc = &gpio_dev->gc;
- irqreturn_t ret = IRQ_NONE;
unsigned int i, irqnr;
unsigned long flags;
u32 __iomem *regs;
+ bool ret = false;
u32 regval;
u64 status, mask;
@@ -627,6 +627,14 @@
/* Each status bit covers four pins */
for (i = 0; i < 4; i++) {
regval = readl(regs + i);
+ /* caused wake on resume context for shared IRQ */
+ if (irq < 0 && (regval & BIT(WAKE_STS_OFF))) {
+ dev_dbg(&gpio_dev->pdev->dev,
+ "Waking due to GPIO %d: 0x%x",
+ irqnr + i, regval);
+ return true;
+ }
+
if (!(regval & PIN_IRQ_PENDING) ||
!(regval & BIT(INTERRUPT_MASK_OFF)))
continue;
@@ -650,9 +658,12 @@
}
writel(regval, regs + i);
raw_spin_unlock_irqrestore(&gpio_dev->lock, flags);
- ret = IRQ_HANDLED;
+ ret = true;
}
}
+ /* did not cause wake on resume context for shared IRQ */
+ if (irq < 0)
+ return false;
/* Signal EOI to the GPIO unit */
raw_spin_lock_irqsave(&gpio_dev->lock, flags);
@@ -664,6 +675,16 @@
return ret;
}
+static irqreturn_t amd_gpio_irq_handler(int irq, void *dev_id)
+{
+ return IRQ_RETVAL(do_amd_gpio_irq_handler(irq, dev_id));
+}
+
+static bool __maybe_unused amd_gpio_check_wake(void *dev_id)
+{
+ return do_amd_gpio_irq_handler(-1, dev_id);
+}
+
static int amd_get_groups_count(struct pinctrl_dev *pctldev)
{
struct amd_gpio *gpio_dev = pinctrl_dev_get_drvdata(pctldev);
@@ -1033,6 +1054,7 @@
goto out2;
platform_set_drvdata(pdev, gpio_dev);
+ acpi_register_wakeup_handler(gpio_dev->irq, amd_gpio_check_wake, gpio_dev);
dev_dbg(&pdev->dev, "amd gpio driver loaded\n");
return ret;
@@ -1050,6 +1072,7 @@
gpio_dev = platform_get_drvdata(pdev);
gpiochip_remove(&gpio_dev->gc);
+ acpi_unregister_wakeup_handler(amd_gpio_check_wake, gpio_dev);
return 0;
}
diff --git a/drivers/pinctrl/pinctrl-apple-gpio.c b/drivers/pinctrl/pinctrl-apple-gpio.c
index 0cc346b..a786107 100644
--- a/drivers/pinctrl/pinctrl-apple-gpio.c
+++ b/drivers/pinctrl/pinctrl-apple-gpio.c
@@ -258,7 +258,7 @@
pctl->base + REG_IRQ(irqgrp, data->hwirq));
}
-static int apple_gpio_irq_type(unsigned int type)
+static unsigned int apple_gpio_irq_type(unsigned int type)
{
switch (type & IRQ_TYPE_SENSE_MASK) {
case IRQ_TYPE_EDGE_RISING:
@@ -272,7 +272,7 @@
case IRQ_TYPE_LEVEL_LOW:
return REG_GPIOx_IN_IRQ_LO;
default:
- return -EINVAL;
+ return REG_GPIOx_IN_IRQ_OFF;
}
}
@@ -288,7 +288,7 @@
{
struct apple_gpio_pinctrl *pctl =
gpiochip_get_data(irq_data_get_irq_chip_data(data));
- int irqtype = apple_gpio_irq_type(irqd_get_trigger_type(data));
+ unsigned int irqtype = apple_gpio_irq_type(irqd_get_trigger_type(data));
apple_gpio_set_reg(pctl, data->hwirq, REG_GPIOx_MODE,
FIELD_PREP(REG_GPIOx_MODE, irqtype));
@@ -313,10 +313,10 @@
{
struct apple_gpio_pinctrl *pctl =
gpiochip_get_data(irq_data_get_irq_chip_data(data));
- int irqtype = apple_gpio_irq_type(type);
+ unsigned int irqtype = apple_gpio_irq_type(type);
- if (irqtype < 0)
- return irqtype;
+ if (irqtype == REG_GPIOx_IN_IRQ_OFF)
+ return -EINVAL;
apple_gpio_set_reg(pctl, data->hwirq, REG_GPIOx_MODE,
FIELD_PREP(REG_GPIOx_MODE, irqtype));
diff --git a/drivers/pinctrl/qcom/Kconfig b/drivers/pinctrl/qcom/Kconfig
index b9191f1..3e0c007 100644
--- a/drivers/pinctrl/qcom/Kconfig
+++ b/drivers/pinctrl/qcom/Kconfig
@@ -197,6 +197,7 @@
select PINMUX
select PINCONF
select GENERIC_PINCONF
+ select GPIOLIB
select GPIOLIB_IRQCHIP
select IRQ_DOMAIN_HIERARCHY
help
@@ -211,6 +212,7 @@
select PINMUX
select PINCONF
select GENERIC_PINCONF
+ select GPIOLIB
select GPIOLIB_IRQCHIP
select IRQ_DOMAIN_HIERARCHY
help
diff --git a/drivers/pinctrl/qcom/pinctrl-sdm845.c b/drivers/pinctrl/qcom/pinctrl-sdm845.c
index c51793f..fdfd7b8 100644
--- a/drivers/pinctrl/qcom/pinctrl-sdm845.c
+++ b/drivers/pinctrl/qcom/pinctrl-sdm845.c
@@ -1310,6 +1310,7 @@
.ngpios = 151,
.wakeirq_map = sdm845_pdc_map,
.nwakeirq_map = ARRAY_SIZE(sdm845_pdc_map),
+ .wakeirq_dual_edge_errata = true,
};
static const struct msm_pinctrl_soc_data sdm845_acpi_pinctrl = {
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8350.c b/drivers/pinctrl/qcom/pinctrl-sm8350.c
index 4d8f863..1c042d3 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8350.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8350.c
@@ -1597,10 +1597,10 @@
[200] = PINGROUP(200, qdss_gpio, _, _, _, _, _, _, _, _),
[201] = PINGROUP(201, _, _, _, _, _, _, _, _, _),
[202] = PINGROUP(202, _, _, _, _, _, _, _, _, _),
- [203] = UFS_RESET(ufs_reset, 0x1d8000),
- [204] = SDC_PINGROUP(sdc2_clk, 0x1cf000, 14, 6),
- [205] = SDC_PINGROUP(sdc2_cmd, 0x1cf000, 11, 3),
- [206] = SDC_PINGROUP(sdc2_data, 0x1cf000, 9, 0),
+ [203] = UFS_RESET(ufs_reset, 0xd8000),
+ [204] = SDC_PINGROUP(sdc2_clk, 0xcf000, 14, 6),
+ [205] = SDC_PINGROUP(sdc2_cmd, 0xcf000, 11, 3),
+ [206] = SDC_PINGROUP(sdc2_data, 0xcf000, 9, 0),
};
static const struct msm_gpio_wakeirq_map sm8350_pdc_map[] = {
diff --git a/drivers/pinctrl/ralink/pinctrl-mt7620.c b/drivers/pinctrl/ralink/pinctrl-mt7620.c
index 425d55a..6853b5b 100644
--- a/drivers/pinctrl/ralink/pinctrl-mt7620.c
+++ b/drivers/pinctrl/ralink/pinctrl-mt7620.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0-only
+#include <asm/mach-ralink/ralink_regs.h>
#include <asm/mach-ralink/mt7620.h>
#include <linux/module.h>
#include <linux/platform_device.h>
diff --git a/drivers/pinctrl/tegra/pinctrl-tegra.c b/drivers/pinctrl/tegra/pinctrl-tegra.c
index 8d734bfc..50bd26a 100644
--- a/drivers/pinctrl/tegra/pinctrl-tegra.c
+++ b/drivers/pinctrl/tegra/pinctrl-tegra.c
@@ -275,7 +275,7 @@
return 0;
}
-static struct tegra_pingroup *tegra_pinctrl_get_group(struct pinctrl_dev *pctldev,
+static const struct tegra_pingroup *tegra_pinctrl_get_group(struct pinctrl_dev *pctldev,
unsigned int offset)
{
struct tegra_pmx *pmx = pinctrl_dev_get_drvdata(pctldev);
@@ -289,7 +289,7 @@
continue;
for (j = 0; j < num_pins; j++) {
if (offset == pins[j])
- return (struct tegra_pingroup *)&pmx->soc->groups[group];
+ return &pmx->soc->groups[group];
}
}
diff --git a/drivers/pinctrl/tegra/pinctrl-tegra194.c b/drivers/pinctrl/tegra/pinctrl-tegra194.c
index b4fef91..5c1dfcb 100644
--- a/drivers/pinctrl/tegra/pinctrl-tegra194.c
+++ b/drivers/pinctrl/tegra/pinctrl-tegra194.c
@@ -1387,7 +1387,6 @@
.schmitt_bit = schmitt_b, \
.drvtype_bit = 13, \
.lpdr_bit = e_lpdr, \
- .drv_reg = -1, \
#define drive_touch_clk_pcc4 DRV_PINGROUP_ENTRY_Y(0x2004, 12, 5, 20, 5, -1, -1, -1, -1, 1)
#define drive_uart3_rx_pcc6 DRV_PINGROUP_ENTRY_Y(0x200c, 12, 5, 20, 5, -1, -1, -1, -1, 1)
diff --git a/drivers/platform/mellanox/mlxreg-lc.c b/drivers/platform/mellanox/mlxreg-lc.c
index 0b7f58f..c897a2f 100644
--- a/drivers/platform/mellanox/mlxreg-lc.c
+++ b/drivers/platform/mellanox/mlxreg-lc.c
@@ -413,7 +413,7 @@
int size)
{
struct mlxreg_hotplug_device *dev = devs;
- int i;
+ int i, ret;
/* Create static I2C device feeding by auxiliary or main power. */
for (i = 0; i < size; i++, dev++) {
@@ -423,6 +423,7 @@
dev->brdinfo->type, dev->nr, dev->brdinfo->addr);
dev->adapter = NULL;
+ ret = PTR_ERR(dev->client);
goto fail_create_static_devices;
}
}
@@ -435,7 +436,7 @@
i2c_unregister_device(dev->client);
dev->client = NULL;
}
- return IS_ERR(dev->client);
+ return ret;
}
static void
diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig
index d4c079f..7400bc5 100644
--- a/drivers/platform/x86/Kconfig
+++ b/drivers/platform/x86/Kconfig
@@ -185,7 +185,7 @@
config AMD_PMC
tristate "AMD SoC PMC driver"
- depends on ACPI && PCI
+ depends on ACPI && PCI && RTC_CLASS
help
The driver provides support for AMD Power Management Controller
primarily responsible for S2Idle transactions that are driven from
diff --git a/drivers/platform/x86/dell/Kconfig b/drivers/platform/x86/dell/Kconfig
index 2fffa57..fe224a5 100644
--- a/drivers/platform/x86/dell/Kconfig
+++ b/drivers/platform/x86/dell/Kconfig
@@ -187,7 +187,7 @@
config DELL_WMI_DESCRIPTOR
tristate
- default m
+ default n
depends on ACPI_WMI
config DELL_WMI_LED
diff --git a/drivers/platform/x86/hp_accel.c b/drivers/platform/x86/hp_accel.c
index b183967..435a91f 100644
--- a/drivers/platform/x86/hp_accel.c
+++ b/drivers/platform/x86/hp_accel.c
@@ -331,9 +331,11 @@
INIT_WORK(&hpled_led.work, delayed_set_status_worker);
ret = led_classdev_register(NULL, &hpled_led.led_classdev);
if (ret) {
+ i8042_remove_filter(hp_accel_i8042_filter);
lis3lv02d_joystick_disable(&lis3_dev);
lis3lv02d_poweroff(&lis3_dev);
flush_work(&hpled_led.work);
+ lis3lv02d_remove_fs(&lis3_dev);
return ret;
}
diff --git a/drivers/platform/x86/samsung-laptop.c b/drivers/platform/x86/samsung-laptop.c
index 7ee010a..c1d9ed9 100644
--- a/drivers/platform/x86/samsung-laptop.c
+++ b/drivers/platform/x86/samsung-laptop.c
@@ -152,7 +152,7 @@
static const struct sabi_config sabi_configs[] = {
{
- /* I don't know if it is really 2, but it it is
+ /* I don't know if it is really 2, but it is
* less than 3 anyway */
.sabi_version = 2,
diff --git a/drivers/platform/x86/think-lmi.c b/drivers/platform/x86/think-lmi.c
index 9472aae..c4d9c45 100644
--- a/drivers/platform/x86/think-lmi.c
+++ b/drivers/platform/x86/think-lmi.c
@@ -888,8 +888,10 @@
break;
if (!item)
break;
- if (!*item)
+ if (!*item) {
+ kfree(item);
continue;
+ }
/* It is not allowed to have '/' for file name. Convert it into '\'. */
strreplace(item, '/', '\\');
@@ -902,6 +904,7 @@
setting = kzalloc(sizeof(*setting), GFP_KERNEL);
if (!setting) {
ret = -ENOMEM;
+ kfree(item);
goto fail_clear_attr;
}
setting->index = i;
@@ -916,7 +919,6 @@
}
kobject_init(&setting->kobj, &tlmi_attr_setting_ktype);
tlmi_priv.setting[i] = setting;
- tlmi_priv.settings_count++;
kfree(item);
}
@@ -983,7 +985,12 @@
static int tlmi_probe(struct wmi_device *wdev, const void *context)
{
- tlmi_analyze();
+ int ret;
+
+ ret = tlmi_analyze();
+ if (ret)
+ return ret;
+
return tlmi_sysfs_init();
}
diff --git a/drivers/platform/x86/think-lmi.h b/drivers/platform/x86/think-lmi.h
index f8e2682..2ce5086 100644
--- a/drivers/platform/x86/think-lmi.h
+++ b/drivers/platform/x86/think-lmi.h
@@ -55,7 +55,6 @@
struct think_lmi {
struct wmi_device *wmi_device;
- int settings_count;
bool can_set_bios_settings;
bool can_get_bios_selections;
bool can_set_bios_password;
diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index 9c632df..b3ac9c3 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -1105,15 +1105,6 @@
return status;
}
-/* Query FW and update rfkill sw state for all rfkill switches */
-static void tpacpi_rfk_update_swstate_all(void)
-{
- unsigned int i;
-
- for (i = 0; i < TPACPI_RFK_SW_MAX; i++)
- tpacpi_rfk_update_swstate(tpacpi_rfkill_switches[i]);
-}
-
/*
* Sync the HW-blocking state of all rfkill switches,
* do notice it causes the rfkill core to schedule uevents
@@ -3074,9 +3065,6 @@
if (wlsw == TPACPI_RFK_RADIO_OFF)
tpacpi_rfk_update_hwblock_state(true);
- /* Sync sw blocking state */
- tpacpi_rfk_update_swstate_all();
-
/* Sync hw blocking state last if it is hw-unblocked */
if (wlsw == TPACPI_RFK_RADIO_ON)
tpacpi_rfk_update_hwblock_state(false);
@@ -8766,6 +8754,7 @@
TPACPI_Q_LNV3('N', '2', 'E', TPACPI_FAN_2CTL), /* P1 / X1 Extreme (1st gen) */
TPACPI_Q_LNV3('N', '2', 'O', TPACPI_FAN_2CTL), /* P1 / X1 Extreme (2nd gen) */
TPACPI_Q_LNV3('N', '2', 'V', TPACPI_FAN_2CTL), /* P1 / X1 Extreme (3nd gen) */
+ TPACPI_Q_LNV3('N', '4', '0', TPACPI_FAN_2CTL), /* P1 / X1 Extreme (4nd gen) */
TPACPI_Q_LNV3('N', '3', '0', TPACPI_FAN_2CTL), /* P15 (1st gen) / P15v (1st gen) */
TPACPI_Q_LNV3('N', '3', '2', TPACPI_FAN_2CTL), /* X1 Carbon (9th gen) */
};
diff --git a/drivers/powercap/dtpm_cpu.c b/drivers/powercap/dtpm_cpu.c
index 44faa3a..b740866 100644
--- a/drivers/powercap/dtpm_cpu.c
+++ b/drivers/powercap/dtpm_cpu.c
@@ -166,16 +166,13 @@
static int cpuhp_dtpm_cpu_offline(unsigned int cpu)
{
- struct em_perf_domain *pd;
struct dtpm_cpu *dtpm_cpu;
- pd = em_cpu_get(cpu);
- if (!pd)
- return -EINVAL;
-
dtpm_cpu = per_cpu(dtpm_per_cpu, cpu);
+ if (dtpm_cpu)
+ dtpm_update_power(&dtpm_cpu->dtpm);
- return dtpm_update_power(&dtpm_cpu->dtpm);
+ return 0;
}
static int cpuhp_dtpm_cpu_online(unsigned int cpu)
diff --git a/drivers/ptp/ptp_clockmatrix.c b/drivers/ptp/ptp_clockmatrix.c
index 6bc5791..08e429a 100644
--- a/drivers/ptp/ptp_clockmatrix.c
+++ b/drivers/ptp/ptp_clockmatrix.c
@@ -1699,12 +1699,9 @@
/* PTP Hardware Clock interface */
-/**
+/*
* Maximum absolute value for write phase offset in picoseconds
*
- * @channel: channel
- * @delta_ns: delta in nanoseconds
- *
* Destination signed register is 32-bit register in resolution of 50ps
*
* 0x7fffffff * 50 = 2147483647 * 50 = 107374182350
diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c
index 34f943c..0f1b5a7 100644
--- a/drivers/ptp/ptp_ocp.c
+++ b/drivers/ptp/ptp_ocp.c
@@ -1304,10 +1304,11 @@
if (!ext)
return -ENOMEM;
- err = -EINVAL;
ext->mem = ptp_ocp_get_mem(bp, r);
- if (!ext->mem)
+ if (IS_ERR(ext->mem)) {
+ err = PTR_ERR(ext->mem);
goto out;
+ }
ext->bp = bp;
ext->info = r->extra;
@@ -1371,8 +1372,8 @@
void __iomem *mem;
mem = ptp_ocp_get_mem(bp, r);
- if (!mem)
- return -EINVAL;
+ if (IS_ERR(mem))
+ return PTR_ERR(mem);
bp_assign_entry(bp, r, mem);
diff --git a/drivers/s390/block/dasd_devmap.c b/drivers/s390/block/dasd_devmap.c
index 2c40fe1..6043c83 100644
--- a/drivers/s390/block/dasd_devmap.c
+++ b/drivers/s390/block/dasd_devmap.c
@@ -731,7 +731,7 @@
ff_flag = (devmap->features & DASD_FEATURE_FAILFAST) != 0;
else
ff_flag = (DASD_FEATURE_DEFAULT & DASD_FEATURE_FAILFAST) != 0;
- return snprintf(buf, PAGE_SIZE, ff_flag ? "1\n" : "0\n");
+ return sysfs_emit(buf, ff_flag ? "1\n" : "0\n");
}
static ssize_t dasd_ff_store(struct device *dev, struct device_attribute *attr,
@@ -773,7 +773,7 @@
spin_unlock(&dasd_devmap_lock);
out:
- return snprintf(buf, PAGE_SIZE, ro_flag ? "1\n" : "0\n");
+ return sysfs_emit(buf, ro_flag ? "1\n" : "0\n");
}
static ssize_t
@@ -834,7 +834,7 @@
erplog = (devmap->features & DASD_FEATURE_ERPLOG) != 0;
else
erplog = (DASD_FEATURE_DEFAULT & DASD_FEATURE_ERPLOG) != 0;
- return snprintf(buf, PAGE_SIZE, erplog ? "1\n" : "0\n");
+ return sysfs_emit(buf, erplog ? "1\n" : "0\n");
}
static ssize_t
@@ -1033,13 +1033,13 @@
dasd_put_device(device);
goto out;
} else {
- len = snprintf(buf, PAGE_SIZE, "%s\n",
- device->discipline->name);
+ len = sysfs_emit(buf, "%s\n",
+ device->discipline->name);
dasd_put_device(device);
return len;
}
out:
- len = snprintf(buf, PAGE_SIZE, "none\n");
+ len = sysfs_emit(buf, "none\n");
return len;
}
@@ -1056,30 +1056,30 @@
if (!IS_ERR(device)) {
switch (device->state) {
case DASD_STATE_NEW:
- len = snprintf(buf, PAGE_SIZE, "new\n");
+ len = sysfs_emit(buf, "new\n");
break;
case DASD_STATE_KNOWN:
- len = snprintf(buf, PAGE_SIZE, "detected\n");
+ len = sysfs_emit(buf, "detected\n");
break;
case DASD_STATE_BASIC:
- len = snprintf(buf, PAGE_SIZE, "basic\n");
+ len = sysfs_emit(buf, "basic\n");
break;
case DASD_STATE_UNFMT:
- len = snprintf(buf, PAGE_SIZE, "unformatted\n");
+ len = sysfs_emit(buf, "unformatted\n");
break;
case DASD_STATE_READY:
- len = snprintf(buf, PAGE_SIZE, "ready\n");
+ len = sysfs_emit(buf, "ready\n");
break;
case DASD_STATE_ONLINE:
- len = snprintf(buf, PAGE_SIZE, "online\n");
+ len = sysfs_emit(buf, "online\n");
break;
default:
- len = snprintf(buf, PAGE_SIZE, "no stat\n");
+ len = sysfs_emit(buf, "no stat\n");
break;
}
dasd_put_device(device);
} else
- len = snprintf(buf, PAGE_SIZE, "unknown\n");
+ len = sysfs_emit(buf, "unknown\n");
return len;
}
@@ -1120,7 +1120,7 @@
device = dasd_device_from_cdev(to_ccwdev(dev));
vendor = "";
if (IS_ERR(device))
- return snprintf(buf, PAGE_SIZE, "%s\n", vendor);
+ return sysfs_emit(buf, "%s\n", vendor);
if (device->discipline && device->discipline->get_uid &&
!device->discipline->get_uid(device, &uid))
@@ -1128,7 +1128,7 @@
dasd_put_device(device);
- return snprintf(buf, PAGE_SIZE, "%s\n", vendor);
+ return sysfs_emit(buf, "%s\n", vendor);
}
static DEVICE_ATTR(vendor, 0444, dasd_vendor_show, NULL);
@@ -1148,7 +1148,7 @@
device = dasd_device_from_cdev(to_ccwdev(dev));
uid_string[0] = 0;
if (IS_ERR(device))
- return snprintf(buf, PAGE_SIZE, "%s\n", uid_string);
+ return sysfs_emit(buf, "%s\n", uid_string);
if (device->discipline && device->discipline->get_uid &&
!device->discipline->get_uid(device, &uid)) {
@@ -1183,7 +1183,7 @@
}
dasd_put_device(device);
- return snprintf(buf, PAGE_SIZE, "%s\n", uid_string);
+ return sysfs_emit(buf, "%s\n", uid_string);
}
static DEVICE_ATTR(uid, 0444, dasd_uid_show, NULL);
@@ -1201,7 +1201,7 @@
eer_flag = dasd_eer_enabled(devmap->device);
else
eer_flag = 0;
- return snprintf(buf, PAGE_SIZE, eer_flag ? "1\n" : "0\n");
+ return sysfs_emit(buf, eer_flag ? "1\n" : "0\n");
}
static ssize_t
@@ -1243,7 +1243,7 @@
device = dasd_device_from_cdev(to_ccwdev(dev));
if (IS_ERR(device))
return -ENODEV;
- len = snprintf(buf, PAGE_SIZE, "%lu\n", device->default_expires);
+ len = sysfs_emit(buf, "%lu\n", device->default_expires);
dasd_put_device(device);
return len;
}
@@ -1283,7 +1283,7 @@
device = dasd_device_from_cdev(to_ccwdev(dev));
if (IS_ERR(device))
return -ENODEV;
- len = snprintf(buf, PAGE_SIZE, "%lu\n", device->default_retries);
+ len = sysfs_emit(buf, "%lu\n", device->default_retries);
dasd_put_device(device);
return len;
}
@@ -1324,7 +1324,7 @@
device = dasd_device_from_cdev(to_ccwdev(dev));
if (IS_ERR(device))
return -ENODEV;
- len = snprintf(buf, PAGE_SIZE, "%lu\n", device->blk_timeout);
+ len = sysfs_emit(buf, "%lu\n", device->blk_timeout);
dasd_put_device(device);
return len;
}
@@ -1398,11 +1398,11 @@
return -ENODEV;
if (!device->discipline || !device->discipline->hpf_enabled) {
dasd_put_device(device);
- return snprintf(buf, PAGE_SIZE, "%d\n", dasd_nofcx);
+ return sysfs_emit(buf, "%d\n", dasd_nofcx);
}
hpf = device->discipline->hpf_enabled(device);
dasd_put_device(device);
- return snprintf(buf, PAGE_SIZE, "%d\n", hpf);
+ return sysfs_emit(buf, "%d\n", hpf);
}
static DEVICE_ATTR(hpf, 0444, dasd_hpf_show, NULL);
@@ -1416,13 +1416,13 @@
devmap = dasd_find_busid(dev_name(dev));
if (IS_ERR(devmap)) {
- rc = snprintf(buf, PAGE_SIZE, "ignore\n");
+ rc = sysfs_emit(buf, "ignore\n");
} else {
spin_lock(&dasd_devmap_lock);
if (devmap->features & DASD_FEATURE_FAILONSLCK)
- rc = snprintf(buf, PAGE_SIZE, "fail\n");
+ rc = sysfs_emit(buf, "fail\n");
else
- rc = snprintf(buf, PAGE_SIZE, "ignore\n");
+ rc = sysfs_emit(buf, "ignore\n");
spin_unlock(&dasd_devmap_lock);
}
return rc;
@@ -1457,14 +1457,14 @@
device = dasd_device_from_cdev(to_ccwdev(dev));
if (IS_ERR(device))
- return snprintf(buf, PAGE_SIZE, "none\n");
+ return sysfs_emit(buf, "none\n");
if (test_bit(DASD_FLAG_IS_RESERVED, &device->flags))
- rc = snprintf(buf, PAGE_SIZE, "reserved\n");
+ rc = sysfs_emit(buf, "reserved\n");
else if (test_bit(DASD_FLAG_LOCK_STOLEN, &device->flags))
- rc = snprintf(buf, PAGE_SIZE, "lost\n");
+ rc = sysfs_emit(buf, "lost\n");
else
- rc = snprintf(buf, PAGE_SIZE, "none\n");
+ rc = sysfs_emit(buf, "none\n");
dasd_put_device(device);
return rc;
}
@@ -1531,7 +1531,7 @@
device = dasd_device_from_cdev(to_ccwdev(dev));
if (IS_ERR(device))
return -ENODEV;
- len = snprintf(buf, PAGE_SIZE, "%lu\n", device->path_thrhld);
+ len = sysfs_emit(buf, "%lu\n", device->path_thrhld);
dasd_put_device(device);
return len;
}
@@ -1578,7 +1578,7 @@
else
flag = (DASD_FEATURE_DEFAULT &
DASD_FEATURE_PATH_AUTODISABLE) != 0;
- return snprintf(buf, PAGE_SIZE, flag ? "1\n" : "0\n");
+ return sysfs_emit(buf, flag ? "1\n" : "0\n");
}
static ssize_t
@@ -1616,7 +1616,7 @@
device = dasd_device_from_cdev(to_ccwdev(dev));
if (IS_ERR(device))
return -ENODEV;
- len = snprintf(buf, PAGE_SIZE, "%lu\n", device->path_interval);
+ len = sysfs_emit(buf, "%lu\n", device->path_interval);
dasd_put_device(device);
return len;
}
@@ -1662,9 +1662,9 @@
return -ENODEV;
fc_sec = dasd_path_get_fcs_device(device);
if (fc_sec == -EINVAL)
- rc = snprintf(buf, PAGE_SIZE, "Inconsistent\n");
+ rc = sysfs_emit(buf, "Inconsistent\n");
else
- rc = snprintf(buf, PAGE_SIZE, "%s\n", dasd_path_get_fcs_str(fc_sec));
+ rc = sysfs_emit(buf, "%s\n", dasd_path_get_fcs_str(fc_sec));
dasd_put_device(device);
return rc;
@@ -1677,7 +1677,7 @@
struct dasd_path *path = to_dasd_path(kobj);
unsigned int fc_sec = path->fc_security;
- return snprintf(buf, PAGE_SIZE, "%s\n", dasd_path_get_fcs_str(fc_sec));
+ return sysfs_emit(buf, "%s\n", dasd_path_get_fcs_str(fc_sec));
}
static struct kobj_attribute path_fcs_attribute =
@@ -1698,7 +1698,7 @@
val = _func(device); \
dasd_put_device(device); \
\
- return snprintf(buf, PAGE_SIZE, "%d\n", val); \
+ return sysfs_emit(buf, "%d\n", val); \
} \
static DEVICE_ATTR(_name, 0444, dasd_##_name##_show, NULL); \
diff --git a/drivers/s390/char/raw3270.c b/drivers/s390/char/raw3270.c
index 646ec796..dfde0d9 100644
--- a/drivers/s390/char/raw3270.c
+++ b/drivers/s390/char/raw3270.c
@@ -1047,24 +1047,24 @@
static ssize_t
raw3270_model_show(struct device *dev, struct device_attribute *attr, char *buf)
{
- return snprintf(buf, PAGE_SIZE, "%i\n",
- ((struct raw3270 *) dev_get_drvdata(dev))->model);
+ return sysfs_emit(buf, "%i\n",
+ ((struct raw3270 *)dev_get_drvdata(dev))->model);
}
static DEVICE_ATTR(model, 0444, raw3270_model_show, NULL);
static ssize_t
raw3270_rows_show(struct device *dev, struct device_attribute *attr, char *buf)
{
- return snprintf(buf, PAGE_SIZE, "%i\n",
- ((struct raw3270 *) dev_get_drvdata(dev))->rows);
+ return sysfs_emit(buf, "%i\n",
+ ((struct raw3270 *)dev_get_drvdata(dev))->rows);
}
static DEVICE_ATTR(rows, 0444, raw3270_rows_show, NULL);
static ssize_t
raw3270_columns_show(struct device *dev, struct device_attribute *attr, char *buf)
{
- return snprintf(buf, PAGE_SIZE, "%i\n",
- ((struct raw3270 *) dev_get_drvdata(dev))->cols);
+ return sysfs_emit(buf, "%i\n",
+ ((struct raw3270 *)dev_get_drvdata(dev))->cols);
}
static DEVICE_ATTR(columns, 0444, raw3270_columns_show, NULL);
diff --git a/drivers/s390/cio/chp.c b/drivers/s390/cio/chp.c
index 1097e76..5440f28 100644
--- a/drivers/s390/cio/chp.c
+++ b/drivers/s390/cio/chp.c
@@ -285,7 +285,7 @@
if (status < 0)
return status;
- return snprintf(buf, PAGE_SIZE, "%d\n", status);
+ return sysfs_emit(buf, "%d\n", status);
}
static int cfg_wait_idle(void);
diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index 73a3531..10d2655 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -1695,10 +1695,8 @@
mcp->in_mb |= MBX_13|MBX_12|MBX_11|MBX_10;
if (IS_FWI2_CAPABLE(vha->hw))
mcp->in_mb |= MBX_19|MBX_18|MBX_17|MBX_16;
- if (IS_QLA27XX(vha->hw) || IS_QLA28XX(vha->hw)) {
- mcp->in_mb |= MBX_15;
- mcp->out_mb |= MBX_7|MBX_21|MBX_22|MBX_23;
- }
+ if (IS_QLA27XX(vha->hw) || IS_QLA28XX(vha->hw))
+ mcp->in_mb |= MBX_15|MBX_21|MBX_22|MBX_23;
mcp->tov = MBX_TOV_SECONDS;
mcp->flags = 0;
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index 55addd7..7afcec2 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -792,6 +792,7 @@
int i, ret;
struct scsi_device *sdev = to_scsi_device(dev);
enum scsi_device_state state = 0;
+ bool rescan_dev = false;
for (i = 0; i < ARRAY_SIZE(sdev_states); i++) {
const int len = strlen(sdev_states[i].name);
@@ -810,20 +811,27 @@
}
mutex_lock(&sdev->state_mutex);
- ret = scsi_device_set_state(sdev, state);
- /*
- * If the device state changes to SDEV_RUNNING, we need to
- * run the queue to avoid I/O hang, and rescan the device
- * to revalidate it. Running the queue first is necessary
- * because another thread may be waiting inside
- * blk_mq_freeze_queue_wait() and because that call may be
- * waiting for pending I/O to finish.
- */
- if (ret == 0 && state == SDEV_RUNNING) {
+ if (sdev->sdev_state == SDEV_RUNNING && state == SDEV_RUNNING) {
+ ret = count;
+ } else {
+ ret = scsi_device_set_state(sdev, state);
+ if (ret == 0 && state == SDEV_RUNNING)
+ rescan_dev = true;
+ }
+ mutex_unlock(&sdev->state_mutex);
+
+ if (rescan_dev) {
+ /*
+ * If the device state changes to SDEV_RUNNING, we need to
+ * run the queue to avoid I/O hang, and rescan the device
+ * to revalidate it. Running the queue first is necessary
+ * because another thread may be waiting inside
+ * blk_mq_freeze_queue_wait() and because that call may be
+ * waiting for pending I/O to finish.
+ */
blk_mq_run_hw_queues(sdev->request_queue, true);
scsi_rescan_device(dev);
}
- mutex_unlock(&sdev->state_mutex);
return ret == 0 ? count : -EINVAL;
}
diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index 78343d3..554b6f7 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -1899,12 +1899,12 @@
}
spin_unlock_irqrestore(&session->lock, flags);
- if (session->transport->session_recovery_timedout)
- session->transport->session_recovery_timedout(session);
-
ISCSI_DBG_TRANS_SESSION(session, "Unblocking SCSI target\n");
scsi_target_unblock(&session->dev, SDEV_TRANSPORT_OFFLINE);
ISCSI_DBG_TRANS_SESSION(session, "Completed unblocking SCSI target\n");
+
+ if (session->transport->session_recovery_timedout)
+ session->transport->session_recovery_timedout(session);
}
static void __iscsi_unblock_session(struct work_struct *work)
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index afd3814..13c09db 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -6453,9 +6453,8 @@
irqreturn_t ret = IRQ_NONE;
int tag;
- pending = ufshcd_readl(hba, REG_UTP_TASK_REQ_DOOR_BELL);
-
spin_lock_irqsave(hba->host->host_lock, flags);
+ pending = ufshcd_readl(hba, REG_UTP_TASK_REQ_DOOR_BELL);
issued = hba->outstanding_tasks & ~pending;
for_each_set_bit(tag, &issued, hba->nutmrs) {
struct request *req = hba->tmf_rqs[tag];
@@ -6616,11 +6615,6 @@
err = wait_for_completion_io_timeout(&wait,
msecs_to_jiffies(TM_CMD_TIMEOUT));
if (!err) {
- /*
- * Make sure that ufshcd_compl_tm() does not trigger a
- * use-after-free.
- */
- req->end_io_data = NULL;
ufshcd_add_tm_upiu_trace(hba, task_tag, UFS_TM_ERR);
dev_err(hba->dev, "%s: task management cmd 0x%.2x timed-out\n",
__func__, tm_function);
@@ -7116,6 +7110,7 @@
goto release;
}
+ lrbp->cmd = NULL;
err = SUCCESS;
release:
diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c
index 8b3d268..b808c94 100644
--- a/drivers/spi/spi-cadence-quadspi.c
+++ b/drivers/spi/spi-cadence-quadspi.c
@@ -37,6 +37,7 @@
#define CQSPI_NEEDS_WR_DELAY BIT(0)
#define CQSPI_DISABLE_DAC_MODE BIT(1)
#define CQSPI_SUPPORT_EXTERNAL_DMA BIT(2)
+#define CQSPI_NO_SUPPORT_WR_COMPLETION BIT(3)
/* Capabilities */
#define CQSPI_SUPPORTS_OCTAL BIT(0)
@@ -86,6 +87,7 @@
struct cqspi_flash_pdata f_pdata[CQSPI_MAX_CHIPSELECT];
bool use_dma_read;
u32 pd_dev_id;
+ bool wr_completion;
};
struct cqspi_driver_platdata {
@@ -996,9 +998,11 @@
* polling on the controller's side. spinand and spi-nor will take
* care of polling the status register.
*/
- reg = readl(reg_base + CQSPI_REG_WR_COMPLETION_CTRL);
- reg |= CQSPI_REG_WR_DISABLE_AUTO_POLL;
- writel(reg, reg_base + CQSPI_REG_WR_COMPLETION_CTRL);
+ if (cqspi->wr_completion) {
+ reg = readl(reg_base + CQSPI_REG_WR_COMPLETION_CTRL);
+ reg |= CQSPI_REG_WR_DISABLE_AUTO_POLL;
+ writel(reg, reg_base + CQSPI_REG_WR_COMPLETION_CTRL);
+ }
reg = readl(reg_base + CQSPI_REG_SIZE);
reg &= ~CQSPI_REG_SIZE_ADDRESS_MASK;
@@ -1736,6 +1740,10 @@
cqspi->master_ref_clk_hz = clk_get_rate(cqspi->clk);
master->max_speed_hz = cqspi->master_ref_clk_hz;
+
+ /* write completion is supported by default */
+ cqspi->wr_completion = true;
+
ddata = of_device_get_match_data(dev);
if (ddata) {
if (ddata->quirks & CQSPI_NEEDS_WR_DELAY)
@@ -1747,6 +1755,8 @@
cqspi->use_direct_mode = true;
if (ddata->quirks & CQSPI_SUPPORT_EXTERNAL_DMA)
cqspi->use_dma_read = true;
+ if (ddata->quirks & CQSPI_NO_SUPPORT_WR_COMPLETION)
+ cqspi->wr_completion = false;
if (of_device_is_compatible(pdev->dev.of_node,
"xlnx,versal-ospi-1.0"))
@@ -1859,6 +1869,10 @@
.quirks = CQSPI_DISABLE_DAC_MODE,
};
+static const struct cqspi_driver_platdata socfpga_qspi = {
+ .quirks = CQSPI_NO_SUPPORT_WR_COMPLETION,
+};
+
static const struct cqspi_driver_platdata versal_ospi = {
.hwcaps_mask = CQSPI_SUPPORTS_OCTAL,
.quirks = CQSPI_DISABLE_DAC_MODE | CQSPI_SUPPORT_EXTERNAL_DMA,
@@ -1887,6 +1901,10 @@
.compatible = "xlnx,versal-ospi-1.0",
.data = (void *)&versal_ospi,
},
+ {
+ .compatible = "intel,socfpga-qspi",
+ .data = (void *)&socfpga_qspi,
+ },
{ /* end of table */ }
};
diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c
index 5d98611..c72e501 100644
--- a/drivers/spi/spi-fsl-lpspi.c
+++ b/drivers/spi/spi-fsl-lpspi.c
@@ -912,7 +912,7 @@
ret = devm_spi_register_controller(&pdev->dev, controller);
if (ret < 0) {
- dev_err(&pdev->dev, "spi_register_controller error.\n");
+ dev_err_probe(&pdev->dev, ret, "spi_register_controller error: %i\n", ret);
goto out_pm_get;
}
diff --git a/drivers/spi/spi-geni-qcom.c b/drivers/spi/spi-geni-qcom.c
index 27a446f..e2affaee 100644
--- a/drivers/spi/spi-geni-qcom.c
+++ b/drivers/spi/spi-geni-qcom.c
@@ -491,22 +491,26 @@
int ret;
mas->tx = dma_request_chan(mas->dev, "tx");
- ret = dev_err_probe(mas->dev, IS_ERR(mas->tx), "Failed to get tx DMA ch\n");
- if (ret < 0)
+ if (IS_ERR(mas->tx)) {
+ ret = dev_err_probe(mas->dev, PTR_ERR(mas->tx),
+ "Failed to get tx DMA ch\n");
goto err_tx;
+ }
mas->rx = dma_request_chan(mas->dev, "rx");
- ret = dev_err_probe(mas->dev, IS_ERR(mas->rx), "Failed to get rx DMA ch\n");
- if (ret < 0)
+ if (IS_ERR(mas->rx)) {
+ ret = dev_err_probe(mas->dev, PTR_ERR(mas->rx),
+ "Failed to get rx DMA ch\n");
goto err_rx;
+ }
return 0;
err_rx:
- dma_release_channel(mas->tx);
- mas->tx = NULL;
-err_tx:
mas->rx = NULL;
+ dma_release_channel(mas->tx);
+err_tx:
+ mas->tx = NULL;
return ret;
}
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index b23e675..fdd530b 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -3099,12 +3099,6 @@
device_del(&ctlr->dev);
- /* Release the last reference on the controller if its driver
- * has not yet been converted to devm_spi_alloc_master/slave().
- */
- if (!ctlr->devm_allocated)
- put_device(&ctlr->dev);
-
/* free bus id */
mutex_lock(&board_lock);
if (found == ctlr)
@@ -3113,6 +3107,12 @@
if (IS_ENABLED(CONFIG_SPI_DYNAMIC))
mutex_unlock(&ctlr->add_lock);
+
+ /* Release the last reference on the controller if its driver
+ * has not yet been converted to devm_spi_alloc_master/slave().
+ */
+ if (!ctlr->devm_allocated)
+ put_device(&ctlr->dev);
}
EXPORT_SYMBOL_GPL(spi_unregister_controller);
diff --git a/drivers/thermal/intel/int340x_thermal/Kconfig b/drivers/thermal/intel/int340x_thermal/Kconfig
index 45c31f3..5d046de 100644
--- a/drivers/thermal/intel/int340x_thermal/Kconfig
+++ b/drivers/thermal/intel/int340x_thermal/Kconfig
@@ -5,12 +5,12 @@
config INT340X_THERMAL
tristate "ACPI INT340X thermal drivers"
- depends on X86 && ACPI && PCI
+ depends on X86_64 && ACPI && PCI
select THERMAL_GOV_USER_SPACE
select ACPI_THERMAL_REL
select ACPI_FAN
select INTEL_SOC_DTS_IOSF_CORE
- select PROC_THERMAL_MMIO_RAPL if X86_64 && POWERCAP
+ select PROC_THERMAL_MMIO_RAPL if POWERCAP
help
Newer laptops and tablets that use ACPI may have thermal sensors and
other devices with thermal control capabilities outside the core
diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 648829a..82654dc 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -421,6 +421,8 @@
{
struct thermal_instance *pos;
tz->temperature = THERMAL_TEMP_INVALID;
+ tz->prev_low_trip = -INT_MAX;
+ tz->prev_high_trip = INT_MAX;
list_for_each_entry(pos, &tz->thermal_instances, tz_node)
pos->initialized = false;
}
diff --git a/drivers/video/console/sticon.c b/drivers/video/console/sticon.c
index 1b45116..40496e9 100644
--- a/drivers/video/console/sticon.c
+++ b/drivers/video/console/sticon.c
@@ -332,13 +332,13 @@
bool blink, bool underline, bool reverse,
bool italic)
{
- u8 attr = ((color & 0x70) >> 1) | ((color & 7));
+ u8 fg = color & 7;
+ u8 bg = (color & 0x70) >> 4;
- if (reverse) {
- color = ((color >> 3) & 0x7) | ((color & 0x7) << 3);
- }
-
- return attr;
+ if (reverse)
+ return (fg << 3) | bg;
+ else
+ return (bg << 3) | fg;
}
static void sticon_invert_region(struct vc_data *conp, u16 *p, int count)
diff --git a/drivers/video/fbdev/efifb.c b/drivers/video/fbdev/efifb.c
index edca370..ea42ba6 100644
--- a/drivers/video/fbdev/efifb.c
+++ b/drivers/video/fbdev/efifb.c
@@ -351,6 +351,17 @@
char *option = NULL;
efi_memory_desc_t md;
+ /*
+ * Generic drivers must not be registered if a framebuffer exists.
+ * If a native driver was probed, the display hardware was already
+ * taken and attempting to use the system framebuffer is dangerous.
+ */
+ if (num_registered_fb > 0) {
+ dev_err(&dev->dev,
+ "efifb: a framebuffer is already registered\n");
+ return -EINVAL;
+ }
+
if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI || pci_dev_disabled)
return -ENODEV;
diff --git a/drivers/video/fbdev/simplefb.c b/drivers/video/fbdev/simplefb.c
index 62f0ded..b63074f 100644
--- a/drivers/video/fbdev/simplefb.c
+++ b/drivers/video/fbdev/simplefb.c
@@ -407,6 +407,17 @@
struct simplefb_par *par;
struct resource *mem;
+ /*
+ * Generic drivers must not be registered if a framebuffer exists.
+ * If a native driver was probed, the display hardware was already
+ * taken and attempting to use the system framebuffer is dangerous.
+ */
+ if (num_registered_fb > 0) {
+ dev_err(&pdev->dev,
+ "simplefb: a framebuffer is already registered\n");
+ return -EINVAL;
+ }
+
if (fb_get_options("simplefb", NULL))
return -ENODEV;
diff --git a/fs/attr.c b/fs/attr.c
index 473d21b..66899b6 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -35,7 +35,7 @@
kuid_t uid)
{
kuid_t kuid = i_uid_into_mnt(mnt_userns, inode);
- if (uid_eq(current_fsuid(), kuid) && uid_eq(uid, kuid))
+ if (uid_eq(current_fsuid(), kuid) && uid_eq(uid, inode->i_uid))
return true;
if (capable_wrt_inode_uidgid(mnt_userns, inode, CAP_CHOWN))
return true;
@@ -62,7 +62,7 @@
{
kgid_t kgid = i_gid_into_mnt(mnt_userns, inode);
if (uid_eq(current_fsuid(), i_uid_into_mnt(mnt_userns, inode)) &&
- (in_group_p(gid) || gid_eq(gid, kgid)))
+ (in_group_p(gid) || gid_eq(gid, inode->i_gid)))
return true;
if (capable_wrt_inode_uidgid(mnt_userns, inode, CAP_CHOWN))
return true;
diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index 309516e..43c8995 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -234,6 +234,13 @@
ordered_list);
if (!test_bit(WORK_DONE_BIT, &work->flags))
break;
+ /*
+ * Orders all subsequent loads after reading WORK_DONE_BIT,
+ * paired with the smp_mb__before_atomic in btrfs_work_helper
+ * this guarantees that the ordered function will see all
+ * updates from ordinary work function.
+ */
+ smp_rmb();
/*
* we are going to call the ordered done function, but
@@ -317,6 +324,13 @@
thresh_exec_hook(wq);
work->func(work);
if (need_order) {
+ /*
+ * Ensures all memory accesses done in the work function are
+ * ordered before setting the WORK_DONE_BIT. Ensuring the thread
+ * which is going to executed the ordered work sees them.
+ * Pairs with the smp_rmb in run_ordered_work.
+ */
+ smp_mb__before_atomic();
set_bit(WORK_DONE_BIT, &work->flags);
run_ordered_work(wq, work);
} else {
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 59c3be8..514ead6 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3978,11 +3978,23 @@
*/
static void write_dev_flush(struct btrfs_device *device)
{
- struct request_queue *q = bdev_get_queue(device->bdev);
struct bio *bio = device->flush_bio;
+#ifndef CONFIG_BTRFS_FS_CHECK_INTEGRITY
+ /*
+ * When a disk has write caching disabled, we skip submission of a bio
+ * with flush and sync requests before writing the superblock, since
+ * it's not needed. However when the integrity checker is enabled, this
+ * results in reports that there are metadata blocks referred by a
+ * superblock that were not properly flushed. So don't skip the bio
+ * submission only when the integrity checker is enabled for the sake
+ * of simplicity, since this is a debug tool and not meant for use in
+ * non-debug builds.
+ */
+ struct request_queue *q = bdev_get_queue(device->bdev);
if (!test_bit(QUEUE_FLAG_WC, &q->queue_flags))
return;
+#endif
bio_reset(bio);
bio->bi_end_io = btrfs_end_empty_barrier;
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index fb8cc96..92138ac 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3985,6 +3985,10 @@
bool need_unlock; /* for mut. excl. ops lock */
int ret;
+ if (!arg)
+ btrfs_warn(fs_info,
+ "IOC_BALANCE ioctl (v1) is deprecated and will be removed in kernel 5.18");
+
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c
index 65cb076..9febb80 100644
--- a/fs/btrfs/lzo.c
+++ b/fs/btrfs/lzo.c
@@ -125,6 +125,7 @@
static int copy_compressed_data_to_page(char *compressed_data,
size_t compressed_size,
struct page **out_pages,
+ unsigned long max_nr_page,
u32 *cur_out,
const u32 sectorsize)
{
@@ -133,6 +134,9 @@
struct page *cur_page;
char *kaddr;
+ if ((*cur_out / PAGE_SIZE) >= max_nr_page)
+ return -E2BIG;
+
/*
* We never allow a segment header crossing sector boundary, previous
* run should ensure we have enough space left inside the sector.
@@ -161,6 +165,10 @@
orig_out + compressed_size - *cur_out);
kunmap(cur_page);
+
+ if ((*cur_out / PAGE_SIZE) >= max_nr_page)
+ return -E2BIG;
+
cur_page = out_pages[*cur_out / PAGE_SIZE];
/* Allocate a new page */
if (!cur_page) {
@@ -203,6 +211,7 @@
const u32 sectorsize = btrfs_sb(mapping->host->i_sb)->sectorsize;
struct page *page_in = NULL;
char *sizes_ptr;
+ const unsigned long max_nr_page = *out_pages;
int ret = 0;
/* Points to the file offset of input data */
u64 cur_in = start;
@@ -210,6 +219,7 @@
u32 cur_out = 0;
u32 len = *total_out;
+ ASSERT(max_nr_page > 0);
*out_pages = 0;
*total_out = 0;
*total_in = 0;
@@ -248,7 +258,8 @@
}
ret = copy_compressed_data_to_page(workspace->cbuf, out_len,
- pages, &cur_out, sectorsize);
+ pages, max_nr_page,
+ &cur_out, sectorsize);
if (ret < 0)
goto out;
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index cf82ea6..8f6ceea 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -73,8 +73,8 @@
u64 physical_for_dev_replace;
atomic_t refs;
u8 mirror_num;
- int have_csum:1;
- int io_error:1;
+ unsigned int have_csum:1;
+ unsigned int io_error:1;
u8 csum[BTRFS_CSUM_SIZE];
struct scrub_recover *recover;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 61ac57b..0997e3c 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -7559,6 +7559,19 @@
fs_info->fs_devices->total_rw_bytes = 0;
/*
+ * Lockdep complains about possible circular locking dependency between
+ * a disk's open_mutex (struct gendisk.open_mutex), the rw semaphores
+ * used for freeze procection of a fs (struct super_block.s_writers),
+ * which we take when starting a transaction, and extent buffers of the
+ * chunk tree if we call read_one_dev() while holding a lock on an
+ * extent buffer of the chunk tree. Since we are mounting the filesystem
+ * and at this point there can't be any concurrent task modifying the
+ * chunk tree, to keep it simple, just skip locking on the chunk tree.
+ */
+ ASSERT(!test_bit(BTRFS_FS_OPEN, &fs_info->flags));
+ path->skip_locking = 1;
+
+ /*
* Read all device items, and then all the chunk items. All
* device items are found before any chunk item (their object id
* is smaller than the lowest possible object id for a chunk
@@ -7583,10 +7596,6 @@
goto error;
break;
}
- /*
- * The nodes on level 1 are not locked but we don't need to do
- * that during mount time as nothing else can access the tree
- */
node = path->nodes[1];
if (node) {
if (last_ra_node != node->start) {
@@ -7614,7 +7623,6 @@
* requirement for chunk allocation, see the comment on
* top of btrfs_chunk_alloc() for details.
*/
- ASSERT(!test_bit(BTRFS_FS_OPEN, &fs_info->flags));
chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk);
ret = read_one_chunk(&found_key, leaf, chunk);
if (ret)
diff --git a/fs/cifs/cifs_swn.c b/fs/cifs/cifs_swn.c
index 12bde7b..23a1ed2 100644
--- a/fs/cifs/cifs_swn.c
+++ b/fs/cifs/cifs_swn.c
@@ -393,26 +393,14 @@
static int cifs_swn_resource_state_changed(struct cifs_swn_reg *swnreg, const char *name, int state)
{
- int i;
-
switch (state) {
case CIFS_SWN_RESOURCE_STATE_UNAVAILABLE:
cifs_dbg(FYI, "%s: resource name '%s' become unavailable\n", __func__, name);
- for (i = 0; i < swnreg->tcon->ses->chan_count; i++) {
- spin_lock(&GlobalMid_Lock);
- if (swnreg->tcon->ses->chans[i].server->tcpStatus != CifsExiting)
- swnreg->tcon->ses->chans[i].server->tcpStatus = CifsNeedReconnect;
- spin_unlock(&GlobalMid_Lock);
- }
+ cifs_ses_mark_for_reconnect(swnreg->tcon->ses);
break;
case CIFS_SWN_RESOURCE_STATE_AVAILABLE:
cifs_dbg(FYI, "%s: resource name '%s' become available\n", __func__, name);
- for (i = 0; i < swnreg->tcon->ses->chan_count; i++) {
- spin_lock(&GlobalMid_Lock);
- if (swnreg->tcon->ses->chans[i].server->tcpStatus != CifsExiting)
- swnreg->tcon->ses->chans[i].server->tcpStatus = CifsNeedReconnect;
- spin_unlock(&GlobalMid_Lock);
- }
+ cifs_ses_mark_for_reconnect(swnreg->tcon->ses);
break;
case CIFS_SWN_RESOURCE_STATE_UNKNOWN:
cifs_dbg(FYI, "%s: resource name '%s' changed to unknown state\n", __func__, name);
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index f3073a6..4f5a3e8 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -599,6 +599,7 @@
bool is_server_using_iface(struct TCP_Server_Info *server,
struct cifs_server_iface *iface);
bool is_ses_using_iface(struct cifs_ses *ses, struct cifs_server_iface *iface);
+void cifs_ses_mark_for_reconnect(struct cifs_ses *ses);
void extract_unc_hostname(const char *unc, const char **h, size_t *len);
int copy_path_name(char *dst, const char *src);
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 82577a7..67e4c55 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -1452,8 +1452,10 @@
tcp_ses->max_in_flight = 0;
tcp_ses->credits = 1;
if (primary_server) {
+ spin_lock(&cifs_tcp_ses_lock);
++primary_server->srv_count;
tcp_ses->primary_server = primary_server;
+ spin_unlock(&cifs_tcp_ses_lock);
}
init_waitqueue_head(&tcp_ses->response_q);
init_waitqueue_head(&tcp_ses->request_q);
@@ -4111,18 +4113,6 @@
}
#ifdef CONFIG_CIFS_DFS_UPCALL
-static void mark_tcon_tcp_ses_for_reconnect(struct cifs_tcon *tcon)
-{
- int i;
-
- for (i = 0; i < tcon->ses->chan_count; i++) {
- spin_lock(&GlobalMid_Lock);
- if (tcon->ses->chans[i].server->tcpStatus != CifsExiting)
- tcon->ses->chans[i].server->tcpStatus = CifsNeedReconnect;
- spin_unlock(&GlobalMid_Lock);
- }
-}
-
/* Update dfs referral path of superblock */
static int update_server_fullpath(struct TCP_Server_Info *server, struct cifs_sb_info *cifs_sb,
const char *target)
@@ -4299,7 +4289,7 @@
*/
if (rc && server->current_fullpath != server->origin_fullpath) {
server->current_fullpath = server->origin_fullpath;
- mark_tcon_tcp_ses_for_reconnect(tcon);
+ cifs_ses_mark_for_reconnect(tcon->ses);
}
dfs_cache_free_tgts(tl);
diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c
index 5c1259d..e9b0fa2 100644
--- a/fs/cifs/dfs_cache.c
+++ b/fs/cifs/dfs_cache.c
@@ -1355,12 +1355,7 @@
}
cifs_dbg(FYI, "%s: no cached or matched targets. mark dfs share for reconnect.\n", __func__);
- for (i = 0; i < tcon->ses->chan_count; i++) {
- spin_lock(&GlobalMid_Lock);
- if (tcon->ses->chans[i].server->tcpStatus != CifsExiting)
- tcon->ses->chans[i].server->tcpStatus = CifsNeedReconnect;
- spin_unlock(&GlobalMid_Lock);
- }
+ cifs_ses_mark_for_reconnect(tcon->ses);
}
/* Refresh dfs referral of tcon and mark it for reconnect if needed */
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index 2c10b18..8ad2993 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -95,9 +95,9 @@
}
if (!(ses->server->capabilities & SMB2_GLOBAL_CAP_MULTI_CHANNEL)) {
- cifs_dbg(VFS, "server %s does not support multichannel\n", ses->server->hostname);
ses->chan_max = 1;
spin_unlock(&ses->chan_lock);
+ cifs_dbg(VFS, "server %s does not support multichannel\n", ses->server->hostname);
return 0;
}
spin_unlock(&ses->chan_lock);
@@ -318,6 +318,19 @@
return rc;
}
+/* Mark all session channels for reconnect */
+void cifs_ses_mark_for_reconnect(struct cifs_ses *ses)
+{
+ int i;
+
+ for (i = 0; i < ses->chan_count; i++) {
+ spin_lock(&GlobalMid_Lock);
+ if (ses->chans[i].server->tcpStatus != CifsExiting)
+ ses->chans[i].server->tcpStatus = CifsNeedReconnect;
+ spin_unlock(&GlobalMid_Lock);
+ }
+}
+
static __u32 cifs_ssetup_hdr(struct cifs_ses *ses, SESSION_SETUP_ANDX *pSMB)
{
__u32 capabilities = 0;
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 7235d53..d671084 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -940,7 +940,7 @@
else if (height == ip->i_height)
ret = gfs2_hole_size(inode, lblock, len, mp, iomap);
else
- iomap->length = size - pos;
+ iomap->length = size - iomap->offset;
} else if (flags & IOMAP_WRITE) {
u64 alloc_size;
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index adafaaf..3e718cf 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -773,8 +773,8 @@
size_t *prev_count,
size_t *window_size)
{
- char __user *p = i->iov[0].iov_base + i->iov_offset;
size_t count = iov_iter_count(i);
+ char __user *p;
int pages = 1;
if (likely(!count))
@@ -787,14 +787,14 @@
if (*prev_count != count || !*window_size) {
int pages, nr_dirtied;
- pages = min_t(int, BIO_MAX_VECS,
- DIV_ROUND_UP(iov_iter_count(i), PAGE_SIZE));
+ pages = min_t(int, BIO_MAX_VECS, DIV_ROUND_UP(count, PAGE_SIZE));
nr_dirtied = max(current->nr_dirtied_pause -
current->nr_dirtied, 1);
pages = min(pages, nr_dirtied);
}
*prev_count = count;
+ p = i->iov[0].iov_base + i->iov_offset;
*window_size = (size_t)PAGE_SIZE * pages - offset_in_page(p);
return true;
}
@@ -1013,6 +1013,7 @@
struct gfs2_sbd *sdp = GFS2_SB(inode);
struct gfs2_holder *statfs_gh = NULL;
size_t prev_count = 0, window_size = 0;
+ size_t orig_count = iov_iter_count(from);
size_t read = 0;
ssize_t ret;
@@ -1057,6 +1058,7 @@
if (inode == sdp->sd_rindex)
gfs2_glock_dq_uninit(statfs_gh);
+ from->count = orig_count - read;
if (should_fault_in_pages(ret, from, &prev_count, &window_size)) {
size_t leftover;
@@ -1064,6 +1066,7 @@
leftover = fault_in_iov_iter_readable(from, window_size);
gfs2_holder_disallow_demote(gh);
if (leftover != window_size) {
+ from->count = min(from->count, window_size - leftover);
if (!gfs2_holder_queued(gh)) {
if (read)
goto out_uninit;
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 19f38ae..8dbd6fe 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -411,14 +411,14 @@
static void demote_incompat_holders(struct gfs2_glock *gl,
struct gfs2_holder *new_gh)
{
- struct gfs2_holder *gh;
+ struct gfs2_holder *gh, *tmp;
/*
* Demote incompatible holders before we make ourselves eligible.
* (This holder may or may not allow auto-demoting, but we don't want
* to demote the new holder before it's even granted.)
*/
- list_for_each_entry(gh, &gl->gl_holders, gh_list) {
+ list_for_each_entry_safe(gh, tmp, &gl->gl_holders, gh_list) {
/*
* Since holders are at the front of the list, we stop when we
* find the first non-holder.
@@ -496,7 +496,7 @@
* Since we unlock the lockref lock, we set a flag to indicate
* instantiate is in progress.
*/
- if (test_bit(GLF_INSTANTIATE_IN_PROG, &gl->gl_flags)) {
+ if (test_and_set_bit(GLF_INSTANTIATE_IN_PROG, &gl->gl_flags)) {
wait_on_bit(&gl->gl_flags, GLF_INSTANTIATE_IN_PROG,
TASK_UNINTERRUPTIBLE);
/*
@@ -509,14 +509,10 @@
goto again;
}
- set_bit(GLF_INSTANTIATE_IN_PROG, &gl->gl_flags);
-
ret = glops->go_instantiate(gh);
if (!ret)
clear_bit(GLF_INSTANTIATE_NEEDED, &gl->gl_flags);
- clear_bit(GLF_INSTANTIATE_IN_PROG, &gl->gl_flags);
- smp_mb__after_atomic();
- wake_up_bit(&gl->gl_flags, GLF_INSTANTIATE_IN_PROG);
+ clear_and_wake_up_bit(GLF_INSTANTIATE_IN_PROG, &gl->gl_flags);
return ret;
}
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 5b12137..0f93e8b 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -1402,13 +1402,6 @@
gfs2_ordered_del_inode(ip);
clear_inode(inode);
gfs2_dir_hash_inval(ip);
- if (ip->i_gl) {
- glock_clear_object(ip->i_gl, ip);
- wait_on_bit_io(&ip->i_flags, GIF_GLOP_PENDING, TASK_UNINTERRUPTIBLE);
- gfs2_glock_add_to_lru(ip->i_gl);
- gfs2_glock_put_eventually(ip->i_gl);
- ip->i_gl = NULL;
- }
if (gfs2_holder_initialized(&ip->i_iopen_gh)) {
struct gfs2_glock *gl = ip->i_iopen_gh.gh_gl;
@@ -1421,6 +1414,13 @@
gfs2_holder_uninit(&ip->i_iopen_gh);
gfs2_glock_put_eventually(gl);
}
+ if (ip->i_gl) {
+ glock_clear_object(ip->i_gl, ip);
+ wait_on_bit_io(&ip->i_flags, GIF_GLOP_PENDING, TASK_UNINTERRUPTIBLE);
+ gfs2_glock_add_to_lru(ip->i_gl);
+ gfs2_glock_put_eventually(ip->i_gl);
+ ip->i_gl = NULL;
+ }
}
static struct inode *gfs2_alloc_inode(struct super_block *sb)
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index b2a1d96..5a93a5d 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -288,11 +288,8 @@
p = xdr_inline_decode(argp->xdr, count << 2);
if (!p)
return nfserr_bad_xdr;
- i = 0;
- while (i < count)
- bmval[i++] = be32_to_cpup(p++);
- while (i < bmlen)
- bmval[i++] = 0;
+ for (i = 0; i < bmlen; i++)
+ bmval[i] = (i < count) ? be32_to_cpup(p++) : 0;
return nfs_ok;
}
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 30a3b66..509f851 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -154,9 +154,13 @@
nr_bytes = count;
/* If pfn is not ram, return zeros for sparse dump files */
- if (!pfn_is_ram(pfn))
- memset(buf, 0, nr_bytes);
- else {
+ if (!pfn_is_ram(pfn)) {
+ tmp = 0;
+ if (!userbuf)
+ memset(buf, 0, nr_bytes);
+ else if (clear_user(buf, nr_bytes))
+ tmp = -EFAULT;
+ } else {
if (encrypted)
tmp = copy_oldmem_page_encrypted(pfn, buf,
nr_bytes,
@@ -165,12 +169,12 @@
else
tmp = copy_oldmem_page(pfn, buf, nr_bytes,
offset, userbuf);
-
- if (tmp < 0) {
- up_read(&vmcore_cb_rwsem);
- return tmp;
- }
}
+ if (tmp < 0) {
+ up_read(&vmcore_cb_rwsem);
+ return tmp;
+ }
+
*ppos += nr_bytes;
count -= nr_bytes;
buf += nr_bytes;
diff --git a/fs/pstore/Kconfig b/fs/pstore/Kconfig
index 328da35..8adabde 100644
--- a/fs/pstore/Kconfig
+++ b/fs/pstore/Kconfig
@@ -173,7 +173,6 @@
tristate "Log panic/oops to a block device"
depends on PSTORE
depends on BLOCK
- depends on BROKEN
select PSTORE_ZONE
default n
help
diff --git a/fs/pstore/blk.c b/fs/pstore/blk.c
index 5d1fbaf..4ae0cfc 100644
--- a/fs/pstore/blk.c
+++ b/fs/pstore/blk.c
@@ -309,7 +309,7 @@
if (ret)
kfree(best_effort_dev);
else
- pr_info("attached %s (%zu) (no dedicated panic_write!)\n",
+ pr_info("attached %s (%lu) (no dedicated panic_write!)\n",
blkdev, best_effort_dev->zone.total_size);
return ret;
diff --git a/fs/udf/dir.c b/fs/udf/dir.c
index 70abdfa..42e3e55 100644
--- a/fs/udf/dir.c
+++ b/fs/udf/dir.c
@@ -31,6 +31,7 @@
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/bio.h>
+#include <linux/iversion.h>
#include "udf_i.h"
#include "udf_sb.h"
@@ -43,7 +44,7 @@
struct fileIdentDesc *fi = NULL;
struct fileIdentDesc cfi;
udf_pblk_t block, iblock;
- loff_t nf_pos;
+ loff_t nf_pos, emit_pos = 0;
int flen;
unsigned char *fname = NULL, *copy_name = NULL;
unsigned char *nameptr;
@@ -57,6 +58,7 @@
int i, num, ret = 0;
struct extent_position epos = { NULL, 0, {0, 0} };
struct super_block *sb = dir->i_sb;
+ bool pos_valid = false;
if (ctx->pos == 0) {
if (!dir_emit_dot(file, ctx))
@@ -67,6 +69,21 @@
if (nf_pos >= size)
goto out;
+ /*
+ * Something changed since last readdir (either lseek was called or dir
+ * changed)? We need to verify the position correctly points at the
+ * beginning of some dir entry so that the directory parsing code does
+ * not get confused. Since UDF does not have any reliable way of
+ * identifying beginning of dir entry (names are under user control),
+ * we need to scan the directory from the beginning.
+ */
+ if (!inode_eq_iversion(dir, file->f_version)) {
+ emit_pos = nf_pos;
+ nf_pos = 0;
+ } else {
+ pos_valid = true;
+ }
+
fname = kmalloc(UDF_NAME_LEN, GFP_NOFS);
if (!fname) {
ret = -ENOMEM;
@@ -122,13 +139,21 @@
while (nf_pos < size) {
struct kernel_lb_addr tloc;
+ loff_t cur_pos = nf_pos;
- ctx->pos = (nf_pos >> 2) + 1;
+ /* Update file position only if we got past the current one */
+ if (nf_pos >= emit_pos) {
+ ctx->pos = (nf_pos >> 2) + 1;
+ pos_valid = true;
+ }
fi = udf_fileident_read(dir, &nf_pos, &fibh, &cfi, &epos, &eloc,
&elen, &offset);
if (!fi)
goto out;
+ /* Still not at offset where user asked us to read from? */
+ if (cur_pos < emit_pos)
+ continue;
liu = le16_to_cpu(cfi.lengthOfImpUse);
lfi = cfi.lengthFileIdent;
@@ -186,8 +211,11 @@
} /* end while */
ctx->pos = (nf_pos >> 2) + 1;
+ pos_valid = true;
out:
+ if (pos_valid)
+ file->f_version = inode_query_iversion(dir);
if (fibh.sbh != fibh.ebh)
brelse(fibh.ebh);
brelse(fibh.sbh);
diff --git a/fs/udf/namei.c b/fs/udf/namei.c
index caeef08..0ed4861 100644
--- a/fs/udf/namei.c
+++ b/fs/udf/namei.c
@@ -30,6 +30,7 @@
#include <linux/sched.h>
#include <linux/crc-itu-t.h>
#include <linux/exportfs.h>
+#include <linux/iversion.h>
static inline int udf_match(int len1, const unsigned char *name1, int len2,
const unsigned char *name2)
@@ -134,6 +135,8 @@
mark_buffer_dirty_inode(fibh->ebh, inode);
mark_buffer_dirty_inode(fibh->sbh, inode);
}
+ inode_inc_iversion(inode);
+
return 0;
}
diff --git a/fs/udf/super.c b/fs/udf/super.c
index 34247fb..f26b5e0 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -57,6 +57,7 @@
#include <linux/crc-itu-t.h>
#include <linux/log2.h>
#include <asm/byteorder.h>
+#include <linux/iversion.h>
#include "udf_sb.h"
#include "udf_i.h"
@@ -149,6 +150,7 @@
init_rwsem(&ei->i_data_sem);
ei->cached_extent.lstart = -1;
spin_lock_init(&ei->i_extent_cache_lock);
+ inode_set_iversion(&ei->vfs_inode, 1);
return &ei->vfs_inode;
}
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 143ce7e..668d007 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -974,6 +974,15 @@
return -ENODEV;
}
+static inline int acpi_register_wakeup_handler(int wake_irq,
+ bool (*wakeup)(void *context), void *context)
+{
+ return -ENXIO;
+}
+
+static inline void acpi_unregister_wakeup_handler(
+ bool (*wakeup)(void *context), void *context) { }
+
#endif /* !CONFIG_ACPI */
#ifdef CONFIG_ACPI_HOTPLUG_IOAPIC
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f715e88..e7a163a 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -193,7 +193,7 @@
atomic64_t usercnt;
struct work_struct work;
struct mutex freeze_mutex;
- u64 writecnt; /* writable mmap cnt; protected by freeze_mutex */
+ atomic64_t writecnt;
};
static inline bool map_value_has_spin_lock(const struct bpf_map *map)
@@ -1419,6 +1419,7 @@
void *bpf_map_area_alloc(u64 size, int numa_node);
void *bpf_map_area_mmapable_alloc(u64 size, int numa_node);
void bpf_map_area_free(void *base);
+bool bpf_map_write_active(const struct bpf_map *map);
void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr);
int generic_map_lookup_batch(struct bpf_map *map,
const union bpf_attr *attr,
diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h
index c137396..ba025ae 100644
--- a/include/linux/hugetlb_cgroup.h
+++ b/include/linux/hugetlb_cgroup.h
@@ -128,6 +128,13 @@
css_get(resv_map->css);
}
+static inline void resv_map_put_hugetlb_cgroup_uncharge_info(
+ struct resv_map *resv_map)
+{
+ if (resv_map->css)
+ css_put(resv_map->css);
+}
+
extern int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages,
struct hugetlb_cgroup **ptr);
extern int hugetlb_cgroup_charge_cgroup_rsvd(int idx, unsigned long nr_pages,
@@ -211,6 +218,11 @@
{
}
+static inline void resv_map_put_hugetlb_cgroup_uncharge_info(
+ struct resv_map *resv_map)
+{
+}
+
static inline int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages,
struct hugetlb_cgroup **ptr)
{
diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h
index 05e2277..b75395e 100644
--- a/include/linux/ipc_namespace.h
+++ b/include/linux/ipc_namespace.h
@@ -131,6 +131,16 @@
return ns;
}
+static inline struct ipc_namespace *get_ipc_ns_not_zero(struct ipc_namespace *ns)
+{
+ if (ns) {
+ if (refcount_inc_not_zero(&ns->ns.count))
+ return ns;
+ }
+
+ return NULL;
+}
+
extern void put_ipc_ns(struct ipc_namespace *ns);
#else
static inline struct ipc_namespace *copy_ipcs(unsigned long flags,
@@ -147,6 +157,11 @@
return ns;
}
+static inline struct ipc_namespace *get_ipc_ns_not_zero(struct ipc_namespace *ns)
+{
+ return ns;
+}
+
static inline void put_ipc_ns(struct ipc_namespace *ns)
{
}
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 9e0667e..c310648 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -874,7 +874,7 @@
void kvm_set_pfn_dirty(kvm_pfn_t pfn);
void kvm_set_pfn_accessed(kvm_pfn_t pfn);
-void kvm_release_pfn(kvm_pfn_t pfn, bool dirty, struct gfn_to_pfn_cache *cache);
+void kvm_release_pfn(kvm_pfn_t pfn, bool dirty);
int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset,
int len);
int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len);
@@ -950,12 +950,8 @@
kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn);
kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn);
int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map);
-int kvm_map_gfn(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map,
- struct gfn_to_pfn_cache *cache, bool atomic);
struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn);
void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty);
-int kvm_unmap_gfn(struct kvm_vcpu *vcpu, struct kvm_host_map *map,
- struct gfn_to_pfn_cache *cache, bool dirty, bool atomic);
unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn);
unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable);
int kvm_vcpu_read_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, void *data, int offset,
diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h
index 2237abb..234eab0 100644
--- a/include/linux/kvm_types.h
+++ b/include/linux/kvm_types.h
@@ -53,13 +53,6 @@
struct kvm_memory_slot *memslot;
};
-struct gfn_to_pfn_cache {
- u64 generation;
- gfn_t gfn;
- kvm_pfn_t pfn;
- bool dirty;
-};
-
#ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE
/*
* Memory caches are used to preallocate memory ahead of various MMU flows,
diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h
index 97afcea..8b18fe9 100644
--- a/include/linux/mlx5/eswitch.h
+++ b/include/linux/mlx5/eswitch.h
@@ -145,13 +145,13 @@
GENMASK(31 - ESW_TUN_ID_BITS - ESW_RESERVED_BITS, \
ESW_TUN_OPTS_OFFSET + 1)
-u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev);
+u8 mlx5_eswitch_mode(const struct mlx5_core_dev *dev);
u16 mlx5_eswitch_get_total_vports(const struct mlx5_core_dev *dev);
struct mlx5_core_dev *mlx5_eswitch_get_core_dev(struct mlx5_eswitch *esw);
#else /* CONFIG_MLX5_ESWITCH */
-static inline u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev)
+static inline u8 mlx5_eswitch_mode(const struct mlx5_core_dev *dev)
{
return MLX5_ESWITCH_NONE;
}
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index bb8c6f5..c3a6e62 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -105,7 +105,18 @@
struct page_pool *pp;
unsigned long _pp_mapping_pad;
unsigned long dma_addr;
- atomic_long_t pp_frag_count;
+ union {
+ /**
+ * dma_addr_upper: might require a 64-bit
+ * value on 32-bit architectures.
+ */
+ unsigned long dma_addr_upper;
+ /**
+ * For frag page support, not supported in
+ * 32-bit architectures with 64-bit DMA.
+ */
+ atomic_long_t pp_frag_count;
+ };
};
struct { /* slab, slob and slub */
union {
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 98a9371..ae4004e 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -6,7 +6,6 @@
#include <linux/preempt.h>
#include <linux/smp.h>
#include <linux/cpumask.h>
-#include <linux/printk.h>
#include <linux/pfn.h>
#include <linux/init.h>
diff --git a/include/linux/printk.h b/include/linux/printk.h
index 85b656f..9497f6b 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -198,6 +198,7 @@
void show_regs_print_info(const char *log_lvl);
extern asmlinkage void dump_stack_lvl(const char *log_lvl) __cold;
extern asmlinkage void dump_stack(void) __cold;
+void printk_trigger_flush(void);
#else
static inline __printf(1, 0)
int vprintk(const char *s, va_list args)
@@ -274,6 +275,9 @@
static inline void dump_stack(void)
{
}
+static inline void printk_trigger_flush(void)
+{
+}
#endif
#ifdef CONFIG_SMP
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 2350539..33a5064 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -352,6 +352,7 @@
extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent);
extern void force_sig(int);
extern void force_fatal_sig(int);
+extern void force_exit_sig(int);
extern int send_sig(int, struct task_struct *, int);
extern int zap_other_threads(struct task_struct *p);
extern struct sigqueue *sigqueue_alloc(void);
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index ba88a69..058d7f3 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -158,7 +158,7 @@
* Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring
* subscriptions and synchronises with wait4(). Also used in procfs. Also
* pins the final release of task.io_context. Also protects ->cpuset and
- * ->cgroup.subsys[]. And ->vfork_done.
+ * ->cgroup.subsys[]. And ->vfork_done. And ->sysvshm.shm_clist.
*
* Nests both inside and outside of read_lock(&tasklist_lock).
* It must not be nested with write_lock_irq(&tasklist_lock),
diff --git a/include/linux/sdb.h b/include/linux/sdb.h
deleted file mode 100644
index a2404a2..0000000
--- a/include/linux/sdb.h
+++ /dev/null
@@ -1,160 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * This is the official version 1.1 of sdb.h
- */
-#ifndef __SDB_H__
-#define __SDB_H__
-#ifdef __KERNEL__
-#include <linux/types.h>
-#else
-#include <stdint.h>
-#endif
-
-/*
- * All structures are 64 bytes long and are expected
- * to live in an array, one for each interconnect.
- * Most fields of the structures are shared among the
- * various types, and most-specific fields are at the
- * beginning (for alignment reasons, and to keep the
- * magic number at the head of the interconnect record
- */
-
-/* Product, 40 bytes at offset 24, 8-byte aligned
- *
- * device_id is vendor-assigned; version is device-specific,
- * date is hex (e.g 0x20120501), name is UTF-8, blank-filled
- * and not terminated with a 0 byte.
- */
-struct sdb_product {
- uint64_t vendor_id; /* 0x18..0x1f */
- uint32_t device_id; /* 0x20..0x23 */
- uint32_t version; /* 0x24..0x27 */
- uint32_t date; /* 0x28..0x2b */
- uint8_t name[19]; /* 0x2c..0x3e */
- uint8_t record_type; /* 0x3f */
-};
-
-/*
- * Component, 56 bytes at offset 8, 8-byte aligned
- *
- * The address range is first to last, inclusive
- * (for example 0x100000 - 0x10ffff)
- */
-struct sdb_component {
- uint64_t addr_first; /* 0x08..0x0f */
- uint64_t addr_last; /* 0x10..0x17 */
- struct sdb_product product; /* 0x18..0x3f */
-};
-
-/* Type of the SDB record */
-enum sdb_record_type {
- sdb_type_interconnect = 0x00,
- sdb_type_device = 0x01,
- sdb_type_bridge = 0x02,
- sdb_type_integration = 0x80,
- sdb_type_repo_url = 0x81,
- sdb_type_synthesis = 0x82,
- sdb_type_empty = 0xFF,
-};
-
-/* Type 0: interconnect (first of the array)
- *
- * sdb_records is the length of the table including this first
- * record, version is 1. The bus type is enumerated later.
- */
-#define SDB_MAGIC 0x5344422d /* "SDB-" */
-struct sdb_interconnect {
- uint32_t sdb_magic; /* 0x00-0x03 */
- uint16_t sdb_records; /* 0x04-0x05 */
- uint8_t sdb_version; /* 0x06 */
- uint8_t sdb_bus_type; /* 0x07 */
- struct sdb_component sdb_component; /* 0x08-0x3f */
-};
-
-/* Type 1: device
- *
- * class is 0 for "custom device", other values are
- * to be standardized; ABI version is for the driver,
- * bus-specific bits are defined by each bus (see below)
- */
-struct sdb_device {
- uint16_t abi_class; /* 0x00-0x01 */
- uint8_t abi_ver_major; /* 0x02 */
- uint8_t abi_ver_minor; /* 0x03 */
- uint32_t bus_specific; /* 0x04-0x07 */
- struct sdb_component sdb_component; /* 0x08-0x3f */
-};
-
-/* Type 2: bridge
- *
- * child is the address of the nested SDB table
- */
-struct sdb_bridge {
- uint64_t sdb_child; /* 0x00-0x07 */
- struct sdb_component sdb_component; /* 0x08-0x3f */
-};
-
-/* Type 0x80: integration
- *
- * all types with bit 7 set are meta-information, so
- * software can ignore the types it doesn't know. Here we
- * just provide product information for an aggregate device
- */
-struct sdb_integration {
- uint8_t reserved[24]; /* 0x00-0x17 */
- struct sdb_product product; /* 0x08-0x3f */
-};
-
-/* Type 0x81: Top module repository url
- *
- * again, an informative field that software can ignore
- */
-struct sdb_repo_url {
- uint8_t repo_url[63]; /* 0x00-0x3e */
- uint8_t record_type; /* 0x3f */
-};
-
-/* Type 0x82: Synthesis tool information
- *
- * this informative record
- */
-struct sdb_synthesis {
- uint8_t syn_name[16]; /* 0x00-0x0f */
- uint8_t commit_id[16]; /* 0x10-0x1f */
- uint8_t tool_name[8]; /* 0x20-0x27 */
- uint32_t tool_version; /* 0x28-0x2b */
- uint32_t date; /* 0x2c-0x2f */
- uint8_t user_name[15]; /* 0x30-0x3e */
- uint8_t record_type; /* 0x3f */
-};
-
-/* Type 0xff: empty
- *
- * this allows keeping empty slots during development,
- * so they can be filled later with minimal efforts and
- * no misleading description is ever shipped -- hopefully.
- * It can also be used to pad a table to a desired length.
- */
-struct sdb_empty {
- uint8_t reserved[63]; /* 0x00-0x3e */
- uint8_t record_type; /* 0x3f */
-};
-
-/* The type of bus, for bus-specific flags */
-enum sdb_bus_type {
- sdb_wishbone = 0x00,
- sdb_data = 0x01,
-};
-
-#define SDB_WB_WIDTH_MASK 0x0f
-#define SDB_WB_ACCESS8 0x01
-#define SDB_WB_ACCESS16 0x02
-#define SDB_WB_ACCESS32 0x04
-#define SDB_WB_ACCESS64 0x08
-#define SDB_WB_LITTLE_ENDIAN 0x80
-
-#define SDB_DATA_READ 0x04
-#define SDB_DATA_WRITE 0x02
-#define SDB_DATA_EXEC 0x01
-
-#endif /* __SDB_H__ */
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 686a666..c8cb7e6 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -4226,7 +4226,7 @@
return;
}
- if (unlikely(skb->ip_summed != CHECKSUM_COMPLETE)) {
+ if (unlikely(skb->ip_summed != CHECKSUM_COMPLETE)) {
__skb_checksum_complete(skb);
skb_postpull_rcsum(skb, skb->data, ptr - (void *)skb->data);
}
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 50453b2..2d167ac 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -673,7 +673,7 @@
#define PERF_MAX_TRACE_SIZE 8192
-#define MAX_FILTER_STR_VAL 256 /* Should handle KSYM_SYMBOL_LEN */
+#define MAX_FILTER_STR_VAL 256U /* Should handle KSYM_SYMBOL_LEN */
enum event_trigger_type {
ETT_NONE = (0),
diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index b465f8f..04e87f4b 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -120,10 +120,15 @@
if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
u16 gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size);
+ unsigned int nh_off = p_off;
struct skb_shared_info *shinfo = skb_shinfo(skb);
+ /* UFO may not include transport header in gso_size. */
+ if (gso_type & SKB_GSO_UDP)
+ nh_off -= thlen;
+
/* Too small packets are not really GSO ones. */
- if (skb->len - p_off > gso_size) {
+ if (skb->len - nh_off > gso_size) {
shinfo->gso_size = gso_size;
shinfo->gso_type = gso_type;
diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h
index a964dae..ea85956 100644
--- a/include/net/nfc/nci_core.h
+++ b/include/net/nfc/nci_core.h
@@ -30,6 +30,7 @@
NCI_UP,
NCI_DATA_EXCHANGE,
NCI_DATA_EXCHANGE_TO,
+ NCI_UNREG,
};
/* NCI device states */
diff --git a/include/net/page_pool.h b/include/net/page_pool.h
index 3855f06..a408240 100644
--- a/include/net/page_pool.h
+++ b/include/net/page_pool.h
@@ -216,14 +216,24 @@
page_pool_put_full_page(pool, page, true);
}
+#define PAGE_POOL_DMA_USE_PP_FRAG_COUNT \
+ (sizeof(dma_addr_t) > sizeof(unsigned long))
+
static inline dma_addr_t page_pool_get_dma_addr(struct page *page)
{
- return page->dma_addr;
+ dma_addr_t ret = page->dma_addr;
+
+ if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT)
+ ret |= (dma_addr_t)page->dma_addr_upper << 16 << 16;
+
+ return ret;
}
static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t addr)
{
page->dma_addr = addr;
+ if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT)
+ page->dma_addr_upper = upper_32_bits(addr);
}
static inline void page_pool_set_frag_count(struct page *page, long nr)
diff --git a/include/rdma/rdma_netlink.h b/include/rdma/rdma_netlink.h
index 2758d9d..c2a79ae 100644
--- a/include/rdma/rdma_netlink.h
+++ b/include/rdma/rdma_netlink.h
@@ -30,7 +30,7 @@
* constant as well and the compiler checks they are the same.
*/
#define MODULE_ALIAS_RDMA_NETLINK(_index, _val) \
- static inline void __chk_##_index(void) \
+ static inline void __maybe_unused __chk_##_index(void) \
{ \
BUILD_BUG_ON(_index != _val); \
} \
diff --git a/ipc/shm.c b/ipc/shm.c
index 4942bdd..b3048eb 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -62,9 +62,18 @@
struct pid *shm_lprid;
struct ucounts *mlock_ucounts;
- /* The task created the shm object. NULL if the task is dead. */
+ /*
+ * The task created the shm object, for
+ * task_lock(shp->shm_creator)
+ */
struct task_struct *shm_creator;
- struct list_head shm_clist; /* list by creator */
+
+ /*
+ * List by creator. task_lock(->shm_creator) required for read/write.
+ * If list_empty(), then the creator is dead already.
+ */
+ struct list_head shm_clist;
+ struct ipc_namespace *ns;
} __randomize_layout;
/* shm_mode upper byte flags */
@@ -115,6 +124,7 @@
struct shmid_kernel *shp;
shp = container_of(ipcp, struct shmid_kernel, shm_perm);
+ WARN_ON(ns != shp->ns);
if (shp->shm_nattch) {
shp->shm_perm.mode |= SHM_DEST;
@@ -225,10 +235,43 @@
kfree(shp);
}
-static inline void shm_rmid(struct ipc_namespace *ns, struct shmid_kernel *s)
+/*
+ * It has to be called with shp locked.
+ * It must be called before ipc_rmid()
+ */
+static inline void shm_clist_rm(struct shmid_kernel *shp)
{
- list_del(&s->shm_clist);
- ipc_rmid(&shm_ids(ns), &s->shm_perm);
+ struct task_struct *creator;
+
+ /* ensure that shm_creator does not disappear */
+ rcu_read_lock();
+
+ /*
+ * A concurrent exit_shm may do a list_del_init() as well.
+ * Just do nothing if exit_shm already did the work
+ */
+ if (!list_empty(&shp->shm_clist)) {
+ /*
+ * shp->shm_creator is guaranteed to be valid *only*
+ * if shp->shm_clist is not empty.
+ */
+ creator = shp->shm_creator;
+
+ task_lock(creator);
+ /*
+ * list_del_init() is a nop if the entry was already removed
+ * from the list.
+ */
+ list_del_init(&shp->shm_clist);
+ task_unlock(creator);
+ }
+ rcu_read_unlock();
+}
+
+static inline void shm_rmid(struct shmid_kernel *s)
+{
+ shm_clist_rm(s);
+ ipc_rmid(&shm_ids(s->ns), &s->shm_perm);
}
@@ -283,7 +326,7 @@
shm_file = shp->shm_file;
shp->shm_file = NULL;
ns->shm_tot -= (shp->shm_segsz + PAGE_SIZE - 1) >> PAGE_SHIFT;
- shm_rmid(ns, shp);
+ shm_rmid(shp);
shm_unlock(shp);
if (!is_file_hugepages(shm_file))
shmem_lock(shm_file, 0, shp->mlock_ucounts);
@@ -303,10 +346,10 @@
*
* 2) sysctl kernel.shm_rmid_forced is set to 1.
*/
-static bool shm_may_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
+static bool shm_may_destroy(struct shmid_kernel *shp)
{
return (shp->shm_nattch == 0) &&
- (ns->shm_rmid_forced ||
+ (shp->ns->shm_rmid_forced ||
(shp->shm_perm.mode & SHM_DEST));
}
@@ -337,7 +380,7 @@
ipc_update_pid(&shp->shm_lprid, task_tgid(current));
shp->shm_dtim = ktime_get_real_seconds();
shp->shm_nattch--;
- if (shm_may_destroy(ns, shp))
+ if (shm_may_destroy(shp))
shm_destroy(ns, shp);
else
shm_unlock(shp);
@@ -358,10 +401,10 @@
*
* As shp->* are changed under rwsem, it's safe to skip shp locking.
*/
- if (shp->shm_creator != NULL)
+ if (!list_empty(&shp->shm_clist))
return 0;
- if (shm_may_destroy(ns, shp)) {
+ if (shm_may_destroy(shp)) {
shm_lock_by_ptr(shp);
shm_destroy(ns, shp);
}
@@ -379,48 +422,97 @@
/* Locking assumes this will only be called with task == current */
void exit_shm(struct task_struct *task)
{
- struct ipc_namespace *ns = task->nsproxy->ipc_ns;
- struct shmid_kernel *shp, *n;
+ for (;;) {
+ struct shmid_kernel *shp;
+ struct ipc_namespace *ns;
- if (list_empty(&task->sysvshm.shm_clist))
- return;
+ task_lock(task);
- /*
- * If kernel.shm_rmid_forced is not set then only keep track of
- * which shmids are orphaned, so that a later set of the sysctl
- * can clean them up.
- */
- if (!ns->shm_rmid_forced) {
- down_read(&shm_ids(ns).rwsem);
- list_for_each_entry(shp, &task->sysvshm.shm_clist, shm_clist)
- shp->shm_creator = NULL;
- /*
- * Only under read lock but we are only called on current
- * so no entry on the list will be shared.
- */
- list_del(&task->sysvshm.shm_clist);
- up_read(&shm_ids(ns).rwsem);
- return;
- }
-
- /*
- * Destroy all already created segments, that were not yet mapped,
- * and mark any mapped as orphan to cover the sysctl toggling.
- * Destroy is skipped if shm_may_destroy() returns false.
- */
- down_write(&shm_ids(ns).rwsem);
- list_for_each_entry_safe(shp, n, &task->sysvshm.shm_clist, shm_clist) {
- shp->shm_creator = NULL;
-
- if (shm_may_destroy(ns, shp)) {
- shm_lock_by_ptr(shp);
- shm_destroy(ns, shp);
+ if (list_empty(&task->sysvshm.shm_clist)) {
+ task_unlock(task);
+ break;
}
- }
- /* Remove the list head from any segments still attached. */
- list_del(&task->sysvshm.shm_clist);
- up_write(&shm_ids(ns).rwsem);
+ shp = list_first_entry(&task->sysvshm.shm_clist, struct shmid_kernel,
+ shm_clist);
+
+ /*
+ * 1) Get pointer to the ipc namespace. It is worth to say
+ * that this pointer is guaranteed to be valid because
+ * shp lifetime is always shorter than namespace lifetime
+ * in which shp lives.
+ * We taken task_lock it means that shp won't be freed.
+ */
+ ns = shp->ns;
+
+ /*
+ * 2) If kernel.shm_rmid_forced is not set then only keep track of
+ * which shmids are orphaned, so that a later set of the sysctl
+ * can clean them up.
+ */
+ if (!ns->shm_rmid_forced)
+ goto unlink_continue;
+
+ /*
+ * 3) get a reference to the namespace.
+ * The refcount could be already 0. If it is 0, then
+ * the shm objects will be free by free_ipc_work().
+ */
+ ns = get_ipc_ns_not_zero(ns);
+ if (!ns) {
+unlink_continue:
+ list_del_init(&shp->shm_clist);
+ task_unlock(task);
+ continue;
+ }
+
+ /*
+ * 4) get a reference to shp.
+ * This cannot fail: shm_clist_rm() is called before
+ * ipc_rmid(), thus the refcount cannot be 0.
+ */
+ WARN_ON(!ipc_rcu_getref(&shp->shm_perm));
+
+ /*
+ * 5) unlink the shm segment from the list of segments
+ * created by current.
+ * This must be done last. After unlinking,
+ * only the refcounts obtained above prevent IPC_RMID
+ * from destroying the segment or the namespace.
+ */
+ list_del_init(&shp->shm_clist);
+
+ task_unlock(task);
+
+ /*
+ * 6) we have all references
+ * Thus lock & if needed destroy shp.
+ */
+ down_write(&shm_ids(ns).rwsem);
+ shm_lock_by_ptr(shp);
+ /*
+ * rcu_read_lock was implicitly taken in shm_lock_by_ptr, it's
+ * safe to call ipc_rcu_putref here
+ */
+ ipc_rcu_putref(&shp->shm_perm, shm_rcu_free);
+
+ if (ipc_valid_object(&shp->shm_perm)) {
+ if (shm_may_destroy(shp))
+ shm_destroy(ns, shp);
+ else
+ shm_unlock(shp);
+ } else {
+ /*
+ * Someone else deleted the shp from namespace
+ * idr/kht while we have waited.
+ * Just unlock and continue.
+ */
+ shm_unlock(shp);
+ }
+
+ up_write(&shm_ids(ns).rwsem);
+ put_ipc_ns(ns); /* paired with get_ipc_ns_not_zero */
+ }
}
static vm_fault_t shm_fault(struct vm_fault *vmf)
@@ -676,7 +768,11 @@
if (error < 0)
goto no_id;
+ shp->ns = ns;
+
+ task_lock(current);
list_add(&shp->shm_clist, ¤t->sysvshm.shm_clist);
+ task_unlock(current);
/*
* shmid gets reported as "inode#" in /proc/pid/maps.
@@ -1567,7 +1663,8 @@
down_write(&shm_ids(ns).rwsem);
shp = shm_lock(ns, shmid);
shp->shm_nattch--;
- if (shm_may_destroy(ns, shp))
+
+ if (shm_may_destroy(shp))
shm_destroy(ns, shp);
else
shm_unlock(shp);
diff --git a/ipc/util.c b/ipc/util.c
index d48d8cf..fa2d86e 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -447,8 +447,8 @@
static void ipc_kht_remove(struct ipc_ids *ids, struct kern_ipc_perm *ipcp)
{
if (ipcp->key != IPC_PRIVATE)
- rhashtable_remove_fast(&ids->key_ht, &ipcp->khtnode,
- ipc_kht_params);
+ WARN_ON_ONCE(rhashtable_remove_fast(&ids->key_ht, &ipcp->khtnode,
+ ipc_kht_params));
}
/**
@@ -498,7 +498,7 @@
{
int idx = ipcid_to_idx(ipcp->id);
- idr_remove(&ids->ipcs_idr, idx);
+ WARN_ON_ONCE(idr_remove(&ids->ipcs_idr, idx) != ipcp);
ipc_kht_remove(ids, ipcp);
ids->in_use--;
ipcp->deleted = true;
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 2ca643a..43eb350 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -1809,6 +1809,8 @@
return &bpf_sysctl_get_new_value_proto;
case BPF_FUNC_sysctl_set_new_value:
return &bpf_sysctl_set_new_value_proto;
+ case BPF_FUNC_ktime_get_coarse_ns:
+ return &bpf_ktime_get_coarse_ns_proto;
default:
return cgroup_base_func_proto(func_id, prog);
}
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 1ffd469..649f076 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -1364,8 +1364,6 @@
return &bpf_ktime_get_ns_proto;
case BPF_FUNC_ktime_get_boot_ns:
return &bpf_ktime_get_boot_ns_proto;
- case BPF_FUNC_ktime_get_coarse_ns:
- return &bpf_ktime_get_coarse_ns_proto;
case BPF_FUNC_ringbuf_output:
return &bpf_ringbuf_output_proto;
case BPF_FUNC_ringbuf_reserve:
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 50f96ea..1033ee8 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -132,6 +132,21 @@
return map;
}
+static void bpf_map_write_active_inc(struct bpf_map *map)
+{
+ atomic64_inc(&map->writecnt);
+}
+
+static void bpf_map_write_active_dec(struct bpf_map *map)
+{
+ atomic64_dec(&map->writecnt);
+}
+
+bool bpf_map_write_active(const struct bpf_map *map)
+{
+ return atomic64_read(&map->writecnt) != 0;
+}
+
static u32 bpf_map_value_size(const struct bpf_map *map)
{
if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
@@ -601,11 +616,8 @@
{
struct bpf_map *map = vma->vm_file->private_data;
- if (vma->vm_flags & VM_MAYWRITE) {
- mutex_lock(&map->freeze_mutex);
- map->writecnt++;
- mutex_unlock(&map->freeze_mutex);
- }
+ if (vma->vm_flags & VM_MAYWRITE)
+ bpf_map_write_active_inc(map);
}
/* called for all unmapped memory region (including initial) */
@@ -613,11 +625,8 @@
{
struct bpf_map *map = vma->vm_file->private_data;
- if (vma->vm_flags & VM_MAYWRITE) {
- mutex_lock(&map->freeze_mutex);
- map->writecnt--;
- mutex_unlock(&map->freeze_mutex);
- }
+ if (vma->vm_flags & VM_MAYWRITE)
+ bpf_map_write_active_dec(map);
}
static const struct vm_operations_struct bpf_map_default_vmops = {
@@ -668,7 +677,7 @@
goto out;
if (vma->vm_flags & VM_MAYWRITE)
- map->writecnt++;
+ bpf_map_write_active_inc(map);
out:
mutex_unlock(&map->freeze_mutex);
return err;
@@ -1139,6 +1148,7 @@
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
+ bpf_map_write_active_inc(map);
if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
err = -EPERM;
goto err_put;
@@ -1174,6 +1184,7 @@
free_key:
kvfree(key);
err_put:
+ bpf_map_write_active_dec(map);
fdput(f);
return err;
}
@@ -1196,6 +1207,7 @@
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
+ bpf_map_write_active_inc(map);
if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
err = -EPERM;
goto err_put;
@@ -1226,6 +1238,7 @@
out:
kvfree(key);
err_put:
+ bpf_map_write_active_dec(map);
fdput(f);
return err;
}
@@ -1533,6 +1546,7 @@
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
+ bpf_map_write_active_inc(map);
if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ) ||
!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
err = -EPERM;
@@ -1597,6 +1611,7 @@
free_key:
kvfree(key);
err_put:
+ bpf_map_write_active_dec(map);
fdput(f);
return err;
}
@@ -1624,8 +1639,7 @@
}
mutex_lock(&map->freeze_mutex);
-
- if (map->writecnt) {
+ if (bpf_map_write_active(map)) {
err = -EBUSY;
goto err_put;
}
@@ -4171,6 +4185,9 @@
union bpf_attr __user *uattr,
int cmd)
{
+ bool has_read = cmd == BPF_MAP_LOOKUP_BATCH ||
+ cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH;
+ bool has_write = cmd != BPF_MAP_LOOKUP_BATCH;
struct bpf_map *map;
int err, ufd;
struct fd f;
@@ -4183,16 +4200,13 @@
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
-
- if ((cmd == BPF_MAP_LOOKUP_BATCH ||
- cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH) &&
- !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) {
+ if (has_write)
+ bpf_map_write_active_inc(map);
+ if (has_read && !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) {
err = -EPERM;
goto err_put;
}
-
- if (cmd != BPF_MAP_LOOKUP_BATCH &&
- !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
+ if (has_write && !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
err = -EPERM;
goto err_put;
}
@@ -4205,8 +4219,9 @@
BPF_DO_BATCH(map->ops->map_update_batch);
else
BPF_DO_BATCH(map->ops->map_delete_batch);
-
err_put:
+ if (has_write)
+ bpf_map_write_active_dec(map);
fdput(f);
return err;
}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 890b3ec..50efda5 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1151,7 +1151,8 @@
/* transfer reg's id which is unique for every map_lookup_elem
* as UID of the inner map.
*/
- reg->map_uid = reg->id;
+ if (map_value_has_timer(map->inner_map_meta))
+ reg->map_uid = reg->id;
} else if (map->map_type == BPF_MAP_TYPE_XSKMAP) {
reg->type = PTR_TO_XDP_SOCK;
} else if (map->map_type == BPF_MAP_TYPE_SOCKMAP ||
@@ -4055,7 +4056,22 @@
static bool bpf_map_is_rdonly(const struct bpf_map *map)
{
- return (map->map_flags & BPF_F_RDONLY_PROG) && map->frozen;
+ /* A map is considered read-only if the following condition are true:
+ *
+ * 1) BPF program side cannot change any of the map content. The
+ * BPF_F_RDONLY_PROG flag is throughout the lifetime of a map
+ * and was set at map creation time.
+ * 2) The map value(s) have been initialized from user space by a
+ * loader and then "frozen", such that no new map update/delete
+ * operations from syscall side are possible for the rest of
+ * the map's lifetime from that point onwards.
+ * 3) Any parallel/pending map update/delete operations from syscall
+ * side have been completed. Only after that point, it's safe to
+ * assume that map value(s) are immutable.
+ */
+ return (map->map_flags & BPF_F_RDONLY_PROG) &&
+ READ_ONCE(map->frozen) &&
+ !bpf_map_write_active(map);
}
static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val)
@@ -11631,6 +11647,13 @@
}
}
+ if (map_value_has_timer(map)) {
+ if (is_tracing_prog_type(prog_type)) {
+ verbose(env, "tracing progs cannot use bpf_timer yet\n");
+ return -EINVAL;
+ }
+ }
+
if ((bpf_prog_is_dev_bound(prog->aux) || bpf_map_is_dev_bound(map)) &&
!bpf_offload_prog_map_match(prog, map)) {
verbose(env, "offload device mismatch between prog and map\n");
diff --git a/kernel/entry/syscall_user_dispatch.c b/kernel/entry/syscall_user_dispatch.c
index 4508201..0b6379a 100644
--- a/kernel/entry/syscall_user_dispatch.c
+++ b/kernel/entry/syscall_user_dispatch.c
@@ -48,7 +48,7 @@
* the selector is loaded by userspace.
*/
if (unlikely(__get_user(state, sd->selector))) {
- force_fatal_sig(SIGSEGV);
+ force_exit_sig(SIGSEGV);
return true;
}
@@ -56,7 +56,7 @@
return false;
if (state != SYSCALL_DISPATCH_FILTER_BLOCK) {
- force_fatal_sig(SIGSYS);
+ force_exit_sig(SIGSYS);
return true;
}
}
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 013bfd6..57b132b 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -3253,6 +3253,11 @@
preempt_enable();
}
+void printk_trigger_flush(void)
+{
+ defer_console_output();
+}
+
int vprintk_deferred(const char *fmt, va_list args)
{
int r;
diff --git a/kernel/signal.c b/kernel/signal.c
index 7c4b7ae..a629b11 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1298,6 +1298,12 @@
return ret;
}
+enum sig_handler {
+ HANDLER_CURRENT, /* If reachable use the current handler */
+ HANDLER_SIG_DFL, /* Always use SIG_DFL handler semantics */
+ HANDLER_EXIT, /* Only visible as the process exit code */
+};
+
/*
* Force a signal that the process can't ignore: if necessary
* we unblock the signal and change any SIG_IGN to SIG_DFL.
@@ -1310,7 +1316,8 @@
* that is why we also clear SIGNAL_UNKILLABLE.
*/
static int
-force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t, bool sigdfl)
+force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t,
+ enum sig_handler handler)
{
unsigned long int flags;
int ret, blocked, ignored;
@@ -1321,9 +1328,10 @@
action = &t->sighand->action[sig-1];
ignored = action->sa.sa_handler == SIG_IGN;
blocked = sigismember(&t->blocked, sig);
- if (blocked || ignored || sigdfl) {
+ if (blocked || ignored || (handler != HANDLER_CURRENT)) {
action->sa.sa_handler = SIG_DFL;
- action->sa.sa_flags |= SA_IMMUTABLE;
+ if (handler == HANDLER_EXIT)
+ action->sa.sa_flags |= SA_IMMUTABLE;
if (blocked) {
sigdelset(&t->blocked, sig);
recalc_sigpending_and_wake(t);
@@ -1343,7 +1351,7 @@
int force_sig_info(struct kernel_siginfo *info)
{
- return force_sig_info_to_task(info, current, false);
+ return force_sig_info_to_task(info, current, HANDLER_CURRENT);
}
/*
@@ -1660,7 +1668,20 @@
info.si_code = SI_KERNEL;
info.si_pid = 0;
info.si_uid = 0;
- force_sig_info_to_task(&info, current, true);
+ force_sig_info_to_task(&info, current, HANDLER_SIG_DFL);
+}
+
+void force_exit_sig(int sig)
+{
+ struct kernel_siginfo info;
+
+ clear_siginfo(&info);
+ info.si_signo = sig;
+ info.si_errno = 0;
+ info.si_code = SI_KERNEL;
+ info.si_pid = 0;
+ info.si_uid = 0;
+ force_sig_info_to_task(&info, current, HANDLER_EXIT);
}
/*
@@ -1693,7 +1714,7 @@
info.si_flags = flags;
info.si_isr = isr;
#endif
- return force_sig_info_to_task(&info, t, false);
+ return force_sig_info_to_task(&info, t, HANDLER_CURRENT);
}
int force_sig_fault(int sig, int code, void __user *addr
@@ -1813,7 +1834,8 @@
info.si_errno = reason;
info.si_arch = syscall_get_arch(current);
info.si_syscall = syscall;
- return force_sig_info_to_task(&info, current, force_coredump);
+ return force_sig_info_to_task(&info, current,
+ force_coredump ? HANDLER_EXIT : HANDLER_CURRENT);
}
/* For the crazy architectures that include trap information in
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 7396488..ae97550 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1111,8 +1111,6 @@
return &bpf_ktime_get_ns_proto;
case BPF_FUNC_ktime_get_boot_ns:
return &bpf_ktime_get_boot_ns_proto;
- case BPF_FUNC_ktime_get_coarse_ns:
- return &bpf_ktime_get_coarse_ns_proto;
case BPF_FUNC_tail_call:
return &bpf_tail_call_proto;
case BPF_FUNC_get_current_pid_tgid:
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index f9139dc..88de94d 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3812,6 +3812,18 @@
iter->fmt[i] = '\0';
trace_seq_vprintf(&iter->seq, iter->fmt, ap);
+ /*
+ * If iter->seq is full, the above call no longer guarantees
+ * that ap is in sync with fmt processing, and further calls
+ * to va_arg() can return wrong positional arguments.
+ *
+ * Ensure that ap is no longer used in this case.
+ */
+ if (iter->seq.full) {
+ p = "";
+ break;
+ }
+
if (star)
len = va_arg(ap, int);
@@ -6706,9 +6718,7 @@
cnt = PAGE_SIZE - 1;
/* reset all but tr, trace, and overruns */
- memset(&iter->seq, 0,
- sizeof(struct trace_iterator) -
- offsetof(struct trace_iterator, seq));
+ memset_startat(iter, 0, seq);
cpumask_clear(iter->started);
trace_seq_init(&iter->seq);
iter->pos = -1;
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 8a10046..9555b8e 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -2576,28 +2576,27 @@
/* Split the expression string at the root operator */
if (!sep)
- goto free;
+ return ERR_PTR(-EINVAL);
+
*sep = '\0';
operand1_str = str;
str = sep+1;
/* Binary operator requires both operands */
if (*operand1_str == '\0' || *str == '\0')
- goto free;
+ return ERR_PTR(-EINVAL);
operand_flags = 0;
/* LHS of string is an expression e.g. a+b in a+b+c */
operand1 = parse_expr(hist_data, file, operand1_str, operand_flags, NULL, n_subexprs);
- if (IS_ERR(operand1)) {
- ret = PTR_ERR(operand1);
- operand1 = NULL;
- goto free;
- }
+ if (IS_ERR(operand1))
+ return ERR_CAST(operand1);
+
if (operand1->flags & HIST_FIELD_FL_STRING) {
hist_err(file->tr, HIST_ERR_INVALID_STR_OPERAND, errpos(operand1_str));
ret = -EINVAL;
- goto free;
+ goto free_op1;
}
/* RHS of string is another expression e.g. c in a+b+c */
@@ -2605,13 +2604,12 @@
operand2 = parse_expr(hist_data, file, str, operand_flags, NULL, n_subexprs);
if (IS_ERR(operand2)) {
ret = PTR_ERR(operand2);
- operand2 = NULL;
- goto free;
+ goto free_op1;
}
if (operand2->flags & HIST_FIELD_FL_STRING) {
hist_err(file->tr, HIST_ERR_INVALID_STR_OPERAND, errpos(str));
ret = -EINVAL;
- goto free;
+ goto free_operands;
}
switch (field_op) {
@@ -2629,12 +2627,12 @@
break;
default:
ret = -EINVAL;
- goto free;
+ goto free_operands;
}
ret = check_expr_operands(file->tr, operand1, operand2, &var1, &var2);
if (ret)
- goto free;
+ goto free_operands;
operand_flags = var1 ? var1->flags : operand1->flags;
operand2_flags = var2 ? var2->flags : operand2->flags;
@@ -2653,12 +2651,13 @@
expr = create_hist_field(hist_data, NULL, flags, var_name);
if (!expr) {
ret = -ENOMEM;
- goto free;
+ goto free_operands;
}
operand1->read_once = true;
operand2->read_once = true;
+ /* The operands are now owned and free'd by 'expr' */
expr->operands[0] = operand1;
expr->operands[1] = operand2;
@@ -2669,7 +2668,7 @@
if (!divisor) {
hist_err(file->tr, HIST_ERR_DIVISION_BY_ZERO, errpos(str));
ret = -EDOM;
- goto free;
+ goto free_expr;
}
/*
@@ -2709,18 +2708,22 @@
expr->type = kstrdup_const(operand1->type, GFP_KERNEL);
if (!expr->type) {
ret = -ENOMEM;
- goto free;
+ goto free_expr;
}
expr->name = expr_str(expr, 0);
}
return expr;
-free:
- destroy_hist_field(operand1, 0);
- destroy_hist_field(operand2, 0);
- destroy_hist_field(expr, 0);
+free_operands:
+ destroy_hist_field(operand2, 0);
+free_op1:
+ destroy_hist_field(operand1, 0);
+ return ERR_PTR(ret);
+
+free_expr:
+ destroy_hist_field(expr, 0);
return ERR_PTR(ret);
}
@@ -3026,8 +3029,10 @@
if (val->flags & HIST_FIELD_FL_STRING) {
char *str = elt_data->field_var_str[j++];
char *val_str = (char *)(uintptr_t)var_val;
+ unsigned int size;
- strscpy(str, val_str, val->size);
+ size = min(val->size, STR_VAR_LEN_MAX);
+ strscpy(str, val_str, size);
var_val = (u64)(uintptr_t)str;
}
tracing_map_set_var(elt, var_idx, var_val);
@@ -4914,6 +4919,7 @@
if (hist_field->flags & HIST_FIELD_FL_STRING) {
unsigned int str_start, var_str_idx, idx;
char *str, *val_str;
+ unsigned int size;
str_start = hist_data->n_field_var_str +
hist_data->n_save_var_str;
@@ -4922,7 +4928,9 @@
str = elt_data->field_var_str[idx];
val_str = (char *)(uintptr_t)hist_val;
- strscpy(str, val_str, hist_field->size);
+
+ size = min(hist_field->size, STR_VAR_LEN_MAX);
+ strscpy(str, val_str, size);
hist_val = (u64)(uintptr_t)str;
}
diff --git a/lib/nmi_backtrace.c b/lib/nmi_backtrace.c
index f9e8900..199ab20 100644
--- a/lib/nmi_backtrace.c
+++ b/lib/nmi_backtrace.c
@@ -75,6 +75,12 @@
touch_softlockup_watchdog();
}
+ /*
+ * Force flush any remote buffers that might be stuck in IRQ context
+ * and therefore could not run their irq_work.
+ */
+ printk_trigger_flush();
+
clear_bit_unlock(0, &backtrace_flag);
put_cpu();
}
diff --git a/lib/test_kasan.c b/lib/test_kasan.c
index 67ed689..0643573 100644
--- a/lib/test_kasan.c
+++ b/lib/test_kasan.c
@@ -869,6 +869,7 @@
ptr = kmalloc(size, GFP_KERNEL | __GFP_ZERO);
KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
+ OPTIMIZER_HIDE_VAR(size);
KUNIT_EXPECT_KASAN_FAIL(test,
kasan_ptr_result = memchr(ptr, '1', size + 1));
@@ -894,6 +895,7 @@
KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
memset(arr, 0, sizeof(arr));
+ OPTIMIZER_HIDE_VAR(size);
KUNIT_EXPECT_KASAN_FAIL(test,
kasan_int_result = memcmp(ptr, arr, size+1));
kfree(ptr);
diff --git a/lib/zstd/Makefile b/lib/zstd/Makefile
index 65218ec..fc45339 100644
--- a/lib/zstd/Makefile
+++ b/lib/zstd/Makefile
@@ -11,8 +11,6 @@
obj-$(CONFIG_ZSTD_COMPRESS) += zstd_compress.o
obj-$(CONFIG_ZSTD_DECOMPRESS) += zstd_decompress.o
-ccflags-y += -O3
-
zstd_compress-y := \
zstd_compress_module.o \
common/debug.o \
diff --git a/lib/zstd/common/compiler.h b/lib/zstd/common/compiler.h
index a1a051e..f5a9c70 100644
--- a/lib/zstd/common/compiler.h
+++ b/lib/zstd/common/compiler.h
@@ -16,6 +16,7 @@
*********************************************************/
/* force inlining */
+#if !defined(ZSTD_NO_INLINE)
#if (defined(__GNUC__) && !defined(__STRICT_ANSI__)) || defined(__cplusplus) || defined(__STDC_VERSION__) && __STDC_VERSION__ >= 199901L /* C99 */
# define INLINE_KEYWORD inline
#else
@@ -24,6 +25,12 @@
#define FORCE_INLINE_ATTR __attribute__((always_inline))
+#else
+
+#define INLINE_KEYWORD
+#define FORCE_INLINE_ATTR
+
+#endif
/*
On MSVC qsort requires that functions passed into it use the __cdecl calling conversion(CC).
diff --git a/lib/zstd/compress/zstd_compress_superblock.c b/lib/zstd/compress/zstd_compress_superblock.c
index ee03e0a..b0610b2 100644
--- a/lib/zstd/compress/zstd_compress_superblock.c
+++ b/lib/zstd/compress/zstd_compress_superblock.c
@@ -411,6 +411,8 @@
const seqDef* sp = sstart;
size_t matchLengthSum = 0;
size_t litLengthSum = 0;
+ /* Only used by assert(), suppress unused variable warnings in production. */
+ (void)litLengthSum;
while (send-sp > 0) {
ZSTD_sequenceLength const seqLen = ZSTD_getSequenceLength(seqStore, sp);
litLengthSum += seqLen.litLength;
diff --git a/lib/zstd/compress/zstd_opt.c b/lib/zstd/compress/zstd_opt.c
index 0433705..dfc55e3 100644
--- a/lib/zstd/compress/zstd_opt.c
+++ b/lib/zstd/compress/zstd_opt.c
@@ -8,6 +8,18 @@
* You may select, at your option, one of the above-listed licenses.
*/
+/*
+ * Disable inlining for the optimal parser for the kernel build.
+ * It is unlikely to be used in the kernel, and where it is used
+ * latency shouldn't matter because it is very slow to begin with.
+ * We prefer a ~180KB binary size win over faster optimal parsing.
+ *
+ * TODO(https://github.com/facebook/zstd/issues/2862):
+ * Improve the code size of the optimal parser in general, so we
+ * don't need this hack for the kernel build.
+ */
+#define ZSTD_NO_INLINE 1
+
#include "zstd_compress_internal.h"
#include "hist.h"
#include "zstd_opt.h"
diff --git a/mm/Kconfig b/mm/Kconfig
index 068ce59..28edafc 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -890,6 +890,9 @@
config KMAP_LOCAL
bool
+config KMAP_LOCAL_NON_LINEAR_PTE_ARRAY
+ bool
+
# struct io_mapping based helper. Selected by drivers that need them
config IO_MAPPING
bool
diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c
index eccc14b..9b520bb 100644
--- a/mm/damon/dbgfs.c
+++ b/mm/damon/dbgfs.c
@@ -32,7 +32,7 @@
if (*ppos)
return ERR_PTR(-EINVAL);
- kbuf = kmalloc(count + 1, GFP_KERNEL);
+ kbuf = kmalloc(count + 1, GFP_KERNEL | __GFP_NOWARN);
if (!kbuf)
return ERR_PTR(-ENOMEM);
@@ -133,7 +133,7 @@
char *kbuf;
ssize_t len;
- kbuf = kmalloc(count, GFP_KERNEL);
+ kbuf = kmalloc(count, GFP_KERNEL | __GFP_NOWARN);
if (!kbuf)
return -ENOMEM;
@@ -452,7 +452,7 @@
char *kbuf;
ssize_t len;
- kbuf = kmalloc(count, GFP_KERNEL);
+ kbuf = kmalloc(count, GFP_KERNEL | __GFP_NOWARN);
if (!kbuf)
return -ENOMEM;
@@ -578,7 +578,7 @@
char *kbuf;
ssize_t len;
- kbuf = kmalloc(count, GFP_KERNEL);
+ kbuf = kmalloc(count, GFP_KERNEL | __GFP_NOWARN);
if (!kbuf)
return -ENOMEM;
@@ -877,12 +877,14 @@
return -EINVAL;
}
+ mutex_lock(&damon_dbgfs_lock);
if (!strncmp(kbuf, "on", count)) {
int i;
for (i = 0; i < dbgfs_nr_ctxs; i++) {
if (damon_targets_empty(dbgfs_ctxs[i])) {
kfree(kbuf);
+ mutex_unlock(&damon_dbgfs_lock);
return -EINVAL;
}
}
@@ -892,6 +894,7 @@
} else {
ret = -EINVAL;
}
+ mutex_unlock(&damon_dbgfs_lock);
if (!ret)
ret = count;
@@ -944,15 +947,16 @@
static int __init damon_dbgfs_init(void)
{
- int rc;
+ int rc = -ENOMEM;
+ mutex_lock(&damon_dbgfs_lock);
dbgfs_ctxs = kmalloc(sizeof(*dbgfs_ctxs), GFP_KERNEL);
if (!dbgfs_ctxs)
- return -ENOMEM;
+ goto out;
dbgfs_ctxs[0] = dbgfs_new_ctx();
if (!dbgfs_ctxs[0]) {
kfree(dbgfs_ctxs);
- return -ENOMEM;
+ goto out;
}
dbgfs_nr_ctxs = 1;
@@ -963,6 +967,8 @@
pr_err("%s: dbgfs init failed\n", __func__);
}
+out:
+ mutex_unlock(&damon_dbgfs_lock);
return rc;
}
diff --git a/mm/highmem.c b/mm/highmem.c
index 88f65f1..ca9fa8c 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -503,16 +503,22 @@
static pte_t *__kmap_pte;
-static pte_t *kmap_get_pte(void)
+static pte_t *kmap_get_pte(unsigned long vaddr, int idx)
{
+ if (IS_ENABLED(CONFIG_KMAP_LOCAL_NON_LINEAR_PTE_ARRAY))
+ /*
+ * Set by the arch if __kmap_pte[-idx] does not produce
+ * the correct entry.
+ */
+ return virt_to_kpte(vaddr);
if (!__kmap_pte)
__kmap_pte = virt_to_kpte(__fix_to_virt(FIX_KMAP_BEGIN));
- return __kmap_pte;
+ return &__kmap_pte[-idx];
}
void *__kmap_local_pfn_prot(unsigned long pfn, pgprot_t prot)
{
- pte_t pteval, *kmap_pte = kmap_get_pte();
+ pte_t pteval, *kmap_pte;
unsigned long vaddr;
int idx;
@@ -524,9 +530,10 @@
preempt_disable();
idx = arch_kmap_local_map_idx(kmap_local_idx_push(), pfn);
vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
- BUG_ON(!pte_none(*(kmap_pte - idx)));
+ kmap_pte = kmap_get_pte(vaddr, idx);
+ BUG_ON(!pte_none(*kmap_pte));
pteval = pfn_pte(pfn, prot);
- arch_kmap_local_set_pte(&init_mm, vaddr, kmap_pte - idx, pteval);
+ arch_kmap_local_set_pte(&init_mm, vaddr, kmap_pte, pteval);
arch_kmap_local_post_map(vaddr, pteval);
current->kmap_ctrl.pteval[kmap_local_idx()] = pteval;
preempt_enable();
@@ -559,7 +566,7 @@
void kunmap_local_indexed(void *vaddr)
{
unsigned long addr = (unsigned long) vaddr & PAGE_MASK;
- pte_t *kmap_pte = kmap_get_pte();
+ pte_t *kmap_pte;
int idx;
if (addr < __fix_to_virt(FIX_KMAP_END) ||
@@ -584,8 +591,9 @@
idx = arch_kmap_local_unmap_idx(kmap_local_idx(), addr);
WARN_ON_ONCE(addr != __fix_to_virt(FIX_KMAP_BEGIN + idx));
+ kmap_pte = kmap_get_pte(addr, idx);
arch_kmap_local_pre_unmap(addr);
- pte_clear(&init_mm, addr, kmap_pte - idx);
+ pte_clear(&init_mm, addr, kmap_pte);
arch_kmap_local_post_unmap(addr);
current->kmap_ctrl.pteval[kmap_local_idx()] = __pte(0);
kmap_local_idx_pop();
@@ -607,7 +615,7 @@
void __kmap_local_sched_out(void)
{
struct task_struct *tsk = current;
- pte_t *kmap_pte = kmap_get_pte();
+ pte_t *kmap_pte;
int i;
/* Clear kmaps */
@@ -634,8 +642,9 @@
idx = arch_kmap_local_map_idx(i, pte_pfn(pteval));
addr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
+ kmap_pte = kmap_get_pte(addr, idx);
arch_kmap_local_pre_unmap(addr);
- pte_clear(&init_mm, addr, kmap_pte - idx);
+ pte_clear(&init_mm, addr, kmap_pte);
arch_kmap_local_post_unmap(addr);
}
}
@@ -643,7 +652,7 @@
void __kmap_local_sched_in(void)
{
struct task_struct *tsk = current;
- pte_t *kmap_pte = kmap_get_pte();
+ pte_t *kmap_pte;
int i;
/* Restore kmaps */
@@ -663,7 +672,8 @@
/* See comment in __kmap_local_sched_out() */
idx = arch_kmap_local_map_idx(i, pte_pfn(pteval));
addr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
- set_pte_at(&init_mm, addr, kmap_pte - idx, pteval);
+ kmap_pte = kmap_get_pte(addr, idx);
+ set_pte_at(&init_mm, addr, kmap_pte, pteval);
arch_kmap_local_post_map(addr, pteval);
}
}
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index e09159c..f025d23 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1037,8 +1037,10 @@
*/
struct resv_map *reservations = vma_resv_map(vma);
- if (reservations && is_vma_resv_set(vma, HPAGE_RESV_OWNER))
+ if (reservations && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
+ resv_map_put_hugetlb_cgroup_uncharge_info(reservations);
kref_put(&reservations->refs, resv_map_release);
+ }
reset_vma_resv_huge_pages(vma);
}
@@ -5734,13 +5736,14 @@
int ret = -ENOMEM;
struct page *page;
int writable;
- bool new_pagecache_page = false;
+ bool page_in_pagecache = false;
if (is_continue) {
ret = -EFAULT;
page = find_lock_page(mapping, idx);
if (!page)
goto out;
+ page_in_pagecache = true;
} else if (!*pagep) {
/* If a page already exists, then it's UFFDIO_COPY for
* a non-missing case. Return -EEXIST.
@@ -5828,7 +5831,7 @@
ret = huge_add_to_page_cache(page, mapping, idx);
if (ret)
goto out_release_nounlock;
- new_pagecache_page = true;
+ page_in_pagecache = true;
}
ptl = huge_pte_lockptr(h, dst_mm, dst_pte);
@@ -5892,7 +5895,7 @@
if (vm_shared || is_continue)
unlock_page(page);
out_release_nounlock:
- if (!new_pagecache_page)
+ if (!page_in_pagecache)
restore_reserve_on_error(h, dst_vma, dst_addr, page);
put_page(page);
goto out;
diff --git a/mm/slab.c b/mm/slab.c
index da132a9..ca4822f 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -3733,14 +3733,13 @@
if (!cachep)
return;
+ trace_kmem_cache_free(_RET_IP_, objp, cachep->name);
local_irq_save(flags);
debug_check_no_locks_freed(objp, cachep->object_size);
if (!(cachep->flags & SLAB_DEBUG_OBJECTS))
debug_check_no_obj_freed(objp, cachep->object_size);
__cache_free(cachep, objp, _RET_IP_);
local_irq_restore(flags);
-
- trace_kmem_cache_free(_RET_IP_, objp, cachep->name);
}
EXPORT_SYMBOL(kmem_cache_free);
diff --git a/mm/slab.h b/mm/slab.h
index 58c01a3..56ad7ee 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -147,7 +147,7 @@
#define SLAB_CACHE_FLAGS (SLAB_NOLEAKTRACE | SLAB_RECLAIM_ACCOUNT | \
SLAB_TEMPORARY | SLAB_ACCOUNT)
#else
-#define SLAB_CACHE_FLAGS (0)
+#define SLAB_CACHE_FLAGS (SLAB_NOLEAKTRACE)
#endif
/* Common flags available with current configuration */
diff --git a/mm/slob.c b/mm/slob.c
index 74d3f6e..03deee1 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -666,6 +666,7 @@
void kmem_cache_free(struct kmem_cache *c, void *b)
{
kmemleak_free_recursive(b, c->flags);
+ trace_kmem_cache_free(_RET_IP_, b, c->name);
if (unlikely(c->flags & SLAB_TYPESAFE_BY_RCU)) {
struct slob_rcu *slob_rcu;
slob_rcu = b + (c->size - sizeof(struct slob_rcu));
@@ -674,8 +675,6 @@
} else {
__kmem_cache_free(b, c->size);
}
-
- trace_kmem_cache_free(_RET_IP_, b, c->name);
}
EXPORT_SYMBOL(kmem_cache_free);
diff --git a/mm/slub.c b/mm/slub.c
index f7368bf..a862682 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -3526,8 +3526,8 @@
s = cache_from_obj(s, x);
if (!s)
return;
- slab_free(s, virt_to_head_page(x), x, NULL, 1, _RET_IP_);
trace_kmem_cache_free(_RET_IP_, x, s->name);
+ slab_free(s, virt_to_head_page(x), x, NULL, 1, _RET_IP_);
}
EXPORT_SYMBOL(kmem_cache_free);
diff --git a/mm/swap.c b/mm/swap.c
index 1841c24..e8c9dc6 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -156,6 +156,7 @@
}
free_unref_page_list(pages);
+ INIT_LIST_HEAD(pages);
}
EXPORT_SYMBOL(put_pages_list);
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 5ba4f94..5ad72db 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -4229,7 +4229,9 @@
WARN_ON(cmd != DEVLINK_CMD_FLASH_UPDATE &&
cmd != DEVLINK_CMD_FLASH_UPDATE_END &&
cmd != DEVLINK_CMD_FLASH_UPDATE_STATUS);
- WARN_ON(!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED));
+
+ if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED))
+ return;
msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
if (!msg)
diff --git a/net/core/filter.c b/net/core/filter.c
index e471c9b..6102f09 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -7162,6 +7162,8 @@
#endif
case BPF_FUNC_sk_storage_get:
return &bpf_sk_storage_get_cg_sock_proto;
+ case BPF_FUNC_ktime_get_coarse_ns:
+ return &bpf_ktime_get_coarse_ns_proto;
default:
return bpf_base_func_proto(func_id);
}
@@ -10327,6 +10329,8 @@
return &sk_reuseport_load_bytes_relative_proto;
case BPF_FUNC_get_socket_cookie:
return &bpf_get_socket_ptr_cookie_proto;
+ case BPF_FUNC_ktime_get_coarse_ns:
+ return &bpf_ktime_get_coarse_ns_proto;
default:
return bpf_base_func_proto(func_id);
}
@@ -10833,6 +10837,8 @@
case BPF_FUNC_skc_to_unix_sock:
func = &bpf_skc_to_unix_sock_proto;
break;
+ case BPF_FUNC_ktime_get_coarse_ns:
+ return &bpf_ktime_get_coarse_ns_proto;
default:
return bpf_base_func_proto(func_id);
}
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 9b60e43..1a69784 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -49,12 +49,6 @@
* which is the XDP_TX use-case.
*/
if (pool->p.flags & PP_FLAG_DMA_MAP) {
- /* DMA-mapping is not supported on 32-bit systems with
- * 64-bit DMA mapping.
- */
- if (sizeof(dma_addr_t) > sizeof(unsigned long))
- return -EOPNOTSUPP;
-
if ((pool->p.dma_dir != DMA_FROM_DEVICE) &&
(pool->p.dma_dir != DMA_BIDIRECTIONAL))
return -EINVAL;
@@ -75,6 +69,10 @@
*/
}
+ if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT &&
+ pool->p.flags & PP_FLAG_PAGE_FRAG)
+ return -EINVAL;
+
if (ptr_ring_init(&pool->ring, ring_qsize, GFP_KERNEL) < 0)
return -ENOMEM;
diff --git a/net/core/sock.c b/net/core/sock.c
index 8f2b2f2..41e91d0 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2124,8 +2124,10 @@
newsk->sk_prot_creator = prot;
/* SANITY */
- if (likely(newsk->sk_net_refcnt))
+ if (likely(newsk->sk_net_refcnt)) {
get_net(sock_net(newsk));
+ sock_inuse_add(sock_net(newsk), 1);
+ }
sk_node_init(&newsk->sk_node);
sock_lock_init(newsk);
bh_lock_sock(newsk);
@@ -2197,8 +2199,6 @@
newsk->sk_err_soft = 0;
newsk->sk_priority = 0;
newsk->sk_incoming_cpu = raw_smp_processor_id();
- if (likely(newsk->sk_net_refcnt))
- sock_inuse_add(sock_net(newsk), 1);
/* Before updating sk_refcnt, we must commit prior changes to memory
* (Documentation/RCU/rculist_nulls.rst for details)
diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
index 2cf02b4..4bb9401 100644
--- a/net/ipv4/bpf_tcp_ca.c
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -205,6 +205,8 @@
offsetof(struct tcp_congestion_ops, release))
return &bpf_sk_getsockopt_proto;
return NULL;
+ case BPF_FUNC_ktime_get_coarse_ns:
+ return &bpf_ktime_get_coarse_ns_proto;
default:
return bpf_base_func_proto(func_id);
}
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index ec73a0d..323e622 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -2591,7 +2591,7 @@
free:
kfree(t);
out:
- return -ENOBUFS;
+ return -ENOMEM;
}
static void __devinet_sysctl_unregister(struct net *net,
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index b7796b4..bbb3d39 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1758,6 +1758,9 @@
{
skb_frag_t *frag;
+ if (unlikely(offset_skb >= skb->len))
+ return NULL;
+
offset_skb -= skb_headlen(skb);
if ((int)offset_skb < 0 || skb_has_frag_list(skb))
return NULL;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 319dd7b..8bcecdd 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1807,6 +1807,17 @@
skb = skb_recv_udp(sk, 0, 1, &err);
if (!skb)
return err;
+
+ if (udp_lib_checksum_complete(skb)) {
+ __UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS,
+ IS_UDPLITE(sk));
+ __UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS,
+ IS_UDPLITE(sk));
+ atomic_inc(&sk->sk_drops);
+ kfree_skb(skb);
+ continue;
+ }
+
used = recv_actor(desc, skb, 0, skb->len);
if (used <= 0) {
if (!copied)
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index ed2f061..f0bac6f 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -808,6 +808,12 @@
struct tcphdr *th;
offset = ipv6_skip_exthdr(skb, offset, &nexthdr, &frag_off);
+
+ if (offset < 0) {
+ err = -EINVAL;
+ goto out;
+ }
+
uh = (void *)(skb->data + offset);
th = (void *)(skb->data + offset);
hdr_len += offset;
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index e2b791c..bd3d319 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -80,7 +80,8 @@
}
/* also validate MU-MIMO change */
- monitor_sdata = rtnl_dereference(local->monitor_sdata);
+ monitor_sdata = wiphy_dereference(local->hw.wiphy,
+ local->monitor_sdata);
if (!monitor_sdata &&
(params->vht_mumimo_groups || params->vht_mumimo_follow_addr))
@@ -840,7 +841,8 @@
mutex_lock(&local->mtx);
if (local->use_chanctx) {
- sdata = rtnl_dereference(local->monitor_sdata);
+ sdata = wiphy_dereference(local->hw.wiphy,
+ local->monitor_sdata);
if (sdata) {
ieee80211_vif_release_channel(sdata);
ret = ieee80211_vif_use_channel(sdata, chandef,
@@ -2707,7 +2709,8 @@
sdata = IEEE80211_WDEV_TO_SUB_IF(wdev);
if (sdata->vif.type == NL80211_IFTYPE_MONITOR) {
- sdata = rtnl_dereference(local->monitor_sdata);
+ sdata = wiphy_dereference(local->hw.wiphy,
+ local->monitor_sdata);
if (!sdata)
return -EOPNOTSUPP;
}
@@ -2767,7 +2770,8 @@
mutex_unlock(&local->iflist_mtx);
if (has_monitor) {
- sdata = rtnl_dereference(local->monitor_sdata);
+ sdata = wiphy_dereference(local->hw.wiphy,
+ local->monitor_sdata);
if (sdata) {
sdata->user_power_level = local->user_power_level;
if (txp_type != sdata->vif.bss_conf.txpower_type)
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 9a2145c..20aa5cc 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -588,7 +588,7 @@
*/
if (local->suspended) {
WARN_ON(local->wowlan);
- WARN_ON(rtnl_dereference(local->monitor_sdata));
+ WARN_ON(rcu_access_pointer(local->monitor_sdata));
return;
}
@@ -961,6 +961,7 @@
return 0;
ASSERT_RTNL();
+ lockdep_assert_wiphy(local->hw.wiphy);
if (local->monitor_sdata)
return 0;
@@ -1028,6 +1029,7 @@
return;
ASSERT_RTNL();
+ lockdep_assert_wiphy(local->hw.wiphy);
mutex_lock(&local->iflist_mtx);
diff --git a/net/mac80211/led.h b/net/mac80211/led.h
index fb3aaa3..b71a142 100644
--- a/net/mac80211/led.h
+++ b/net/mac80211/led.h
@@ -72,19 +72,19 @@
#endif
static inline void
-ieee80211_tpt_led_trig_tx(struct ieee80211_local *local, __le16 fc, int bytes)
+ieee80211_tpt_led_trig_tx(struct ieee80211_local *local, int bytes)
{
#ifdef CONFIG_MAC80211_LEDS
- if (ieee80211_is_data(fc) && atomic_read(&local->tpt_led_active))
+ if (atomic_read(&local->tpt_led_active))
local->tpt_led_trigger->tx_bytes += bytes;
#endif
}
static inline void
-ieee80211_tpt_led_trig_rx(struct ieee80211_local *local, __le16 fc, int bytes)
+ieee80211_tpt_led_trig_rx(struct ieee80211_local *local, int bytes)
{
#ifdef CONFIG_MAC80211_LEDS
- if (ieee80211_is_data(fc) && atomic_read(&local->tpt_led_active))
+ if (atomic_read(&local->tpt_led_active))
local->tpt_led_trigger->rx_bytes += bytes;
#endif
}
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index fc5c608..9541a4c 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -364,7 +364,7 @@
* the compiler to think we have walked past the end of the
* struct member.
*/
- pos = (void *)&rthdr->it_optional[it_present - rthdr->it_optional];
+ pos = (void *)&rthdr->it_optional[it_present + 1 - rthdr->it_optional];
/* the order of the following fields is important */
@@ -1952,7 +1952,8 @@
int keyid = rx->sta->ptk_idx;
sta_ptk = rcu_dereference(rx->sta->ptk[keyid]);
- if (ieee80211_has_protected(fc)) {
+ if (ieee80211_has_protected(fc) &&
+ !(status->flag & RX_FLAG_IV_STRIPPED)) {
cs = rx->sta->cipher_scheme;
keyid = ieee80211_get_keyid(rx->skb, cs);
@@ -4863,6 +4864,7 @@
struct ieee80211_rate *rate = NULL;
struct ieee80211_supported_band *sband;
struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
+ struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
WARN_ON_ONCE(softirq_count() == 0);
@@ -4959,9 +4961,9 @@
if (!(status->flag & RX_FLAG_8023))
skb = ieee80211_rx_monitor(local, skb, rate);
if (skb) {
- ieee80211_tpt_led_trig_rx(local,
- ((struct ieee80211_hdr *)skb->data)->frame_control,
- skb->len);
+ if ((status->flag & RX_FLAG_8023) ||
+ ieee80211_is_data_present(hdr->frame_control))
+ ieee80211_tpt_led_trig_rx(local, skb->len);
if (status->flag & RX_FLAG_8023)
__ieee80211_rx_handle_8023(hw, pubsta, skb, list);
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index a756a19..278945e 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -1721,21 +1721,19 @@
* Returns false if the frame couldn't be transmitted but was queued instead.
*/
static bool __ieee80211_tx(struct ieee80211_local *local,
- struct sk_buff_head *skbs, int led_len,
- struct sta_info *sta, bool txpending)
+ struct sk_buff_head *skbs, struct sta_info *sta,
+ bool txpending)
{
struct ieee80211_tx_info *info;
struct ieee80211_sub_if_data *sdata;
struct ieee80211_vif *vif;
struct sk_buff *skb;
bool result;
- __le16 fc;
if (WARN_ON(skb_queue_empty(skbs)))
return true;
skb = skb_peek(skbs);
- fc = ((struct ieee80211_hdr *)skb->data)->frame_control;
info = IEEE80211_SKB_CB(skb);
sdata = vif_to_sdata(info->control.vif);
if (sta && !sta->uploaded)
@@ -1769,8 +1767,6 @@
result = ieee80211_tx_frags(local, vif, sta, skbs, txpending);
- ieee80211_tpt_led_trig_tx(local, fc, led_len);
-
WARN_ON_ONCE(!skb_queue_empty(skbs));
return result;
@@ -1920,7 +1916,6 @@
ieee80211_tx_result res_prepare;
struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
bool result = true;
- int led_len;
if (unlikely(skb->len < 10)) {
dev_kfree_skb(skb);
@@ -1928,7 +1923,6 @@
}
/* initialises tx */
- led_len = skb->len;
res_prepare = ieee80211_tx_prepare(sdata, &tx, sta, skb);
if (unlikely(res_prepare == TX_DROP)) {
@@ -1951,8 +1945,7 @@
return true;
if (!invoke_tx_handlers_late(&tx))
- result = __ieee80211_tx(local, &tx.skbs, led_len,
- tx.sta, txpending);
+ result = __ieee80211_tx(local, &tx.skbs, tx.sta, txpending);
return result;
}
@@ -4175,6 +4168,7 @@
struct ieee80211_local *local = sdata->local;
struct sta_info *sta;
struct sk_buff *next;
+ int len = skb->len;
if (unlikely(skb->len < ETH_HLEN)) {
kfree_skb(skb);
@@ -4221,10 +4215,8 @@
}
} else {
/* we cannot process non-linear frames on this path */
- if (skb_linearize(skb)) {
- kfree_skb(skb);
- goto out;
- }
+ if (skb_linearize(skb))
+ goto out_free;
/* the frame could be fragmented, software-encrypted, and other
* things so we cannot really handle checksum offload with it -
@@ -4258,7 +4250,10 @@
goto out;
out_free:
kfree_skb(skb);
+ len = 0;
out:
+ if (len)
+ ieee80211_tpt_led_trig_tx(local, len);
rcu_read_unlock();
}
@@ -4396,8 +4391,7 @@
}
static bool ieee80211_tx_8023(struct ieee80211_sub_if_data *sdata,
- struct sk_buff *skb, int led_len,
- struct sta_info *sta,
+ struct sk_buff *skb, struct sta_info *sta,
bool txpending)
{
struct ieee80211_local *local = sdata->local;
@@ -4410,6 +4404,8 @@
if (sta)
sk_pacing_shift_update(skb->sk, local->hw.tx_sk_pacing_shift);
+ ieee80211_tpt_led_trig_tx(local, skb->len);
+
if (ieee80211_queue_skb(local, sdata, sta, skb))
return true;
@@ -4498,7 +4494,7 @@
if (key)
info->control.hw_key = &key->conf;
- ieee80211_tx_8023(sdata, skb, skb->len, sta, false);
+ ieee80211_tx_8023(sdata, skb, sta, false);
return;
@@ -4637,7 +4633,7 @@
if (IS_ERR(sta) || (sta && !sta->uploaded))
sta = NULL;
- result = ieee80211_tx_8023(sdata, skb, skb->len, sta, true);
+ result = ieee80211_tx_8023(sdata, skb, sta, true);
} else {
struct sk_buff_head skbs;
@@ -4647,7 +4643,7 @@
hdr = (struct ieee80211_hdr *)skb->data;
sta = sta_info_get(sdata, hdr->addr1);
- result = __ieee80211_tx(local, &skbs, skb->len, sta, true);
+ result = __ieee80211_tx(local, &skbs, sta, true);
}
return result;
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 39fa2a5..43df2f0 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -796,7 +796,7 @@
sdata = rcu_dereference_check(local->monitor_sdata,
lockdep_is_held(&local->iflist_mtx) ||
- lockdep_rtnl_is_held());
+ lockdep_is_held(&local->hw.wiphy->mtx));
if (sdata &&
(iter_flags & IEEE80211_IFACE_ITER_RESUME_ALL || !active_only ||
sdata->flags & IEEE80211_SDATA_IN_DRIVER))
@@ -2381,7 +2381,7 @@
IEEE80211_TPT_LEDTRIG_FL_RADIO, 0);
/* add interfaces */
- sdata = rtnl_dereference(local->monitor_sdata);
+ sdata = wiphy_dereference(local->hw.wiphy, local->monitor_sdata);
if (sdata) {
/* in HW restart it exists already */
WARN_ON(local->resuming);
@@ -2426,7 +2426,8 @@
WARN_ON(drv_add_chanctx(local, ctx));
mutex_unlock(&local->chanctx_mtx);
- sdata = rtnl_dereference(local->monitor_sdata);
+ sdata = wiphy_dereference(local->hw.wiphy,
+ local->monitor_sdata);
if (sdata && ieee80211_sdata_running(sdata))
ieee80211_assign_chanctx(local, sdata);
}
diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c
index 9ea6004..62c6733 100644
--- a/net/mac80211/wme.c
+++ b/net/mac80211/wme.c
@@ -143,7 +143,6 @@
u16 __ieee80211_select_queue(struct ieee80211_sub_if_data *sdata,
struct sta_info *sta, struct sk_buff *skb)
{
- struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
struct mac80211_qos_map *qos_map;
bool qos;
@@ -156,7 +155,7 @@
else
qos = false;
- if (!qos || (info->control.flags & IEEE80211_TX_CTRL_DONT_REORDER)) {
+ if (!qos) {
skb->priority = 0; /* required for correct WPA/11i MIC */
return IEEE80211_AC_BE;
}
diff --git a/net/nfc/core.c b/net/nfc/core.c
index 3c645c1..dc7a240 100644
--- a/net/nfc/core.c
+++ b/net/nfc/core.c
@@ -94,13 +94,13 @@
device_lock(&dev->dev);
- if (dev->rfkill && rfkill_blocked(dev->rfkill)) {
- rc = -ERFKILL;
+ if (!device_is_registered(&dev->dev)) {
+ rc = -ENODEV;
goto error;
}
- if (!device_is_registered(&dev->dev)) {
- rc = -ENODEV;
+ if (dev->rfkill && rfkill_blocked(dev->rfkill)) {
+ rc = -ERFKILL;
goto error;
}
@@ -1125,11 +1125,7 @@
if (rc)
pr_err("Could not register llcp device\n");
- rc = nfc_genl_device_added(dev);
- if (rc)
- pr_debug("The userspace won't be notified that the device %s was added\n",
- dev_name(&dev->dev));
-
+ device_lock(&dev->dev);
dev->rfkill = rfkill_alloc(dev_name(&dev->dev), &dev->dev,
RFKILL_TYPE_NFC, &nfc_rfkill_ops, dev);
if (dev->rfkill) {
@@ -1138,6 +1134,12 @@
dev->rfkill = NULL;
}
}
+ device_unlock(&dev->dev);
+
+ rc = nfc_genl_device_added(dev);
+ if (rc)
+ pr_debug("The userspace won't be notified that the device %s was added\n",
+ dev_name(&dev->dev));
return 0;
}
@@ -1154,10 +1156,17 @@
pr_debug("dev_name=%s\n", dev_name(&dev->dev));
+ rc = nfc_genl_device_removed(dev);
+ if (rc)
+ pr_debug("The userspace won't be notified that the device %s "
+ "was removed\n", dev_name(&dev->dev));
+
+ device_lock(&dev->dev);
if (dev->rfkill) {
rfkill_unregister(dev->rfkill);
rfkill_destroy(dev->rfkill);
}
+ device_unlock(&dev->dev);
if (dev->ops->check_presence) {
device_lock(&dev->dev);
@@ -1167,11 +1176,6 @@
cancel_work_sync(&dev->check_pres_work);
}
- rc = nfc_genl_device_removed(dev);
- if (rc)
- pr_debug("The userspace won't be notified that the device %s "
- "was removed\n", dev_name(&dev->dev));
-
nfc_llcp_unregister_device(dev);
mutex_lock(&nfc_devlist_mutex);
diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index 6fd873a..d253738 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -144,12 +144,15 @@
{
int rc;
- if (!test_bit(NCI_UP, &ndev->flags))
- return -ENETDOWN;
-
/* Serialize all requests */
mutex_lock(&ndev->req_lock);
- rc = __nci_request(ndev, req, opt, timeout);
+ /* check the state after obtaing the lock against any races
+ * from nci_close_device when the device gets removed.
+ */
+ if (test_bit(NCI_UP, &ndev->flags))
+ rc = __nci_request(ndev, req, opt, timeout);
+ else
+ rc = -ENETDOWN;
mutex_unlock(&ndev->req_lock);
return rc;
@@ -473,6 +476,11 @@
mutex_lock(&ndev->req_lock);
+ if (test_bit(NCI_UNREG, &ndev->flags)) {
+ rc = -ENODEV;
+ goto done;
+ }
+
if (test_bit(NCI_UP, &ndev->flags)) {
rc = -EALREADY;
goto done;
@@ -545,6 +553,10 @@
static int nci_close_device(struct nci_dev *ndev)
{
nci_req_cancel(ndev, ENODEV);
+
+ /* This mutex needs to be held as a barrier for
+ * caller nci_unregister_device
+ */
mutex_lock(&ndev->req_lock);
if (!test_and_clear_bit(NCI_UP, &ndev->flags)) {
@@ -582,8 +594,8 @@
del_timer_sync(&ndev->cmd_timer);
- /* Clear flags */
- ndev->flags = 0;
+ /* Clear flags except NCI_UNREG */
+ ndev->flags &= BIT(NCI_UNREG);
mutex_unlock(&ndev->req_lock);
@@ -1266,6 +1278,12 @@
{
struct nci_conn_info *conn_info, *n;
+ /* This set_bit is not protected with specialized barrier,
+ * However, it is fine because the mutex_lock(&ndev->req_lock);
+ * in nci_close_device() will help to emit one.
+ */
+ set_bit(NCI_UNREG, &ndev->flags);
+
nci_close_device(ndev);
destroy_workqueue(ndev->cmd_wq);
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index d64b0ee..efc963a 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -19,6 +19,7 @@
#include <linux/if_arp.h>
#include <net/net_namespace.h>
#include <net/netlink.h>
+#include <net/dst.h>
#include <net/pkt_sched.h>
#include <net/pkt_cls.h>
#include <linux/tc_act/tc_mirred.h>
@@ -228,6 +229,7 @@
bool want_ingress;
bool is_redirect;
bool expects_nh;
+ bool at_ingress;
int m_eaction;
int mac_len;
bool at_nh;
@@ -263,7 +265,8 @@
* ingress - that covers the TC S/W datapath.
*/
is_redirect = tcf_mirred_is_act_redirect(m_eaction);
- use_reinsert = skb_at_tc_ingress(skb) && is_redirect &&
+ at_ingress = skb_at_tc_ingress(skb);
+ use_reinsert = at_ingress && is_redirect &&
tcf_mirred_can_reinsert(retval);
if (!use_reinsert) {
skb2 = skb_clone(skb, GFP_ATOMIC);
@@ -271,10 +274,12 @@
goto out;
}
+ want_ingress = tcf_mirred_act_wants_ingress(m_eaction);
+
/* All mirred/redirected skbs should clear previous ct info */
nf_reset_ct(skb2);
-
- want_ingress = tcf_mirred_act_wants_ingress(m_eaction);
+ if (want_ingress && !at_ingress) /* drop dst for egress -> ingress */
+ skb_dst_drop(skb2);
expects_nh = want_ingress || !m_mac_header_xmit;
at_nh = skb->data == skb_network_header(skb);
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 59284da..b61c802 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -566,6 +566,10 @@
static void smc_switch_to_fallback(struct smc_sock *smc, int reason_code)
{
+ wait_queue_head_t *smc_wait = sk_sleep(&smc->sk);
+ wait_queue_head_t *clc_wait = sk_sleep(smc->clcsock->sk);
+ unsigned long flags;
+
smc->use_fallback = true;
smc->fallback_rsn = reason_code;
smc_stat_fallback(smc);
@@ -575,6 +579,16 @@
smc->clcsock->file->private_data = smc->clcsock;
smc->clcsock->wq.fasync_list =
smc->sk.sk_socket->wq.fasync_list;
+
+ /* There may be some entries remaining in
+ * smc socket->wq, which should be removed
+ * to clcsocket->wq during the fallback.
+ */
+ spin_lock_irqsave(&smc_wait->lock, flags);
+ spin_lock(&clc_wait->lock);
+ list_splice_init(&smc_wait->head, &clc_wait->head);
+ spin_unlock(&clc_wait->lock);
+ spin_unlock_irqrestore(&smc_wait->lock, flags);
}
}
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 49b8ba3..25ebd30 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -708,13 +708,14 @@
int i;
while (1) {
+again:
link_id = ++lgr->next_link_id;
if (!link_id) /* skip zero as link_id */
link_id = ++lgr->next_link_id;
for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
if (smc_link_usable(&lgr->lnk[i]) &&
lgr->lnk[i].link_id == link_id)
- continue;
+ goto again;
}
break;
}
diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c
index dc60c32..b4d9419 100644
--- a/net/tipc/crypto.c
+++ b/net/tipc/crypto.c
@@ -524,7 +524,7 @@
return -EEXIST;
/* Allocate a new AEAD */
- tmp = kzalloc(sizeof(*tmp), GFP_ATOMIC);
+ tmp = kzalloc(sizeof(*tmp), GFP_KERNEL);
if (unlikely(!tmp))
return -ENOMEM;
@@ -597,6 +597,10 @@
tmp->cloned = NULL;
tmp->authsize = TIPC_AES_GCM_TAG_SIZE;
tmp->key = kmemdup(ukey, tipc_aead_key_size(ukey), GFP_KERNEL);
+ if (!tmp->key) {
+ tipc_aead_free(&tmp->rcu);
+ return -ENOMEM;
+ }
memcpy(&tmp->salt, ukey->key + keylen, TIPC_AES_GCM_SALT_SIZE);
atomic_set(&tmp->users, 0);
atomic64_set(&tmp->seqno, 0);
@@ -1470,7 +1474,7 @@
return -EEXIST;
/* Allocate crypto */
- c = kzalloc(sizeof(*c), GFP_ATOMIC);
+ c = kzalloc(sizeof(*c), GFP_KERNEL);
if (!c)
return -ENOMEM;
@@ -1484,7 +1488,7 @@
}
/* Allocate statistic structure */
- c->stats = alloc_percpu_gfp(struct tipc_crypto_stats, GFP_ATOMIC);
+ c->stats = alloc_percpu(struct tipc_crypto_stats);
if (!c->stats) {
if (c->wq)
destroy_workqueue(c->wq);
@@ -2457,7 +2461,7 @@
}
/* Lets duplicate it first */
- skey = kmemdup(aead->key, tipc_aead_key_size(aead->key), GFP_ATOMIC);
+ skey = kmemdup(aead->key, tipc_aead_key_size(aead->key), GFP_KERNEL);
rcu_read_unlock();
/* Now, generate new key, initiate & distribute it */
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 1b7a487..09ae844 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -1298,8 +1298,11 @@
return false;
#ifdef CONFIG_TIPC_CRYPTO
case MSG_CRYPTO:
- tipc_crypto_msg_rcv(l->net, skb);
- return true;
+ if (TIPC_SKB_CB(skb)->decrypted) {
+ tipc_crypto_msg_rcv(l->net, skb);
+ return true;
+ }
+ fallthrough;
#endif
default:
pr_warn("Dropping received illegal msg type\n");
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 81232b7..a27b3b5 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -936,33 +936,37 @@
[NL80211_PKTPAT_OFFSET] = { .type = NLA_U32 },
};
-int nl80211_prepare_wdev_dump(struct netlink_callback *cb,
- struct cfg80211_registered_device **rdev,
- struct wireless_dev **wdev)
+static int nl80211_prepare_wdev_dump(struct netlink_callback *cb,
+ struct cfg80211_registered_device **rdev,
+ struct wireless_dev **wdev,
+ struct nlattr **attrbuf)
{
int err;
if (!cb->args[0]) {
- struct nlattr **attrbuf;
+ struct nlattr **attrbuf_free = NULL;
- attrbuf = kcalloc(NUM_NL80211_ATTR, sizeof(*attrbuf),
- GFP_KERNEL);
- if (!attrbuf)
- return -ENOMEM;
+ if (!attrbuf) {
+ attrbuf = kcalloc(NUM_NL80211_ATTR, sizeof(*attrbuf),
+ GFP_KERNEL);
+ if (!attrbuf)
+ return -ENOMEM;
+ attrbuf_free = attrbuf;
+ }
err = nlmsg_parse_deprecated(cb->nlh,
GENL_HDRLEN + nl80211_fam.hdrsize,
attrbuf, nl80211_fam.maxattr,
nl80211_policy, NULL);
if (err) {
- kfree(attrbuf);
+ kfree(attrbuf_free);
return err;
}
rtnl_lock();
*wdev = __cfg80211_wdev_from_attrs(NULL, sock_net(cb->skb->sk),
attrbuf);
- kfree(attrbuf);
+ kfree(attrbuf_free);
if (IS_ERR(*wdev)) {
rtnl_unlock();
return PTR_ERR(*wdev);
@@ -6197,7 +6201,7 @@
int sta_idx = cb->args[2];
int err;
- err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev);
+ err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev, NULL);
if (err)
return err;
/* nl80211_prepare_wdev_dump acquired it in the successful case */
@@ -7092,7 +7096,7 @@
int path_idx = cb->args[2];
int err;
- err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev);
+ err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev, NULL);
if (err)
return err;
/* nl80211_prepare_wdev_dump acquired it in the successful case */
@@ -7292,7 +7296,7 @@
int path_idx = cb->args[2];
int err;
- err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev);
+ err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev, NULL);
if (err)
return err;
/* nl80211_prepare_wdev_dump acquired it in the successful case */
@@ -9718,7 +9722,7 @@
int start = cb->args[2], idx = 0;
int err;
- err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev);
+ err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev, NULL);
if (err)
return err;
/* nl80211_prepare_wdev_dump acquired it in the successful case */
@@ -9851,7 +9855,7 @@
if (!attrbuf)
return -ENOMEM;
- res = nl80211_prepare_wdev_dump(cb, &rdev, &wdev);
+ res = nl80211_prepare_wdev_dump(cb, &rdev, &wdev, attrbuf);
if (res) {
kfree(attrbuf);
return res;
diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h
index a3f3877..d642e3b 100644
--- a/net/wireless/nl80211.h
+++ b/net/wireless/nl80211.h
@@ -1,7 +1,7 @@
/* SPDX-License-Identifier: GPL-2.0 */
/*
* Portions of this file
- * Copyright (C) 2018, 2020 Intel Corporation
+ * Copyright (C) 2018, 2020-2021 Intel Corporation
*/
#ifndef __NET_WIRELESS_NL80211_H
#define __NET_WIRELESS_NL80211_H
@@ -22,10 +22,6 @@
((u64)wiphy_to_rdev(wdev->wiphy)->wiphy_idx << 32);
}
-int nl80211_prepare_wdev_dump(struct netlink_callback *cb,
- struct cfg80211_registered_device **rdev,
- struct wireless_dev **wdev);
-
int nl80211_parse_chandef(struct cfg80211_registered_device *rdev,
struct genl_info *info,
struct cfg80211_chan_def *chandef);
diff --git a/net/wireless/util.c b/net/wireless/util.c
index 5ff1f872..41ea65d 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -1046,6 +1046,7 @@
switch (otype) {
case NL80211_IFTYPE_AP:
+ case NL80211_IFTYPE_P2P_GO:
cfg80211_stop_ap(rdev, dev, true);
break;
case NL80211_IFTYPE_ADHOC:
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index 90c4e1e..bc4ad48 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -500,7 +500,7 @@
pool->free_list_cnt--;
xskb = list_first_entry(&pool->free_list, struct xdp_buff_xsk,
free_list_node);
- list_del(&xskb->free_list_node);
+ list_del_init(&xskb->free_list_node);
}
xskb->xdp.data = xskb->xdp.data_hard_start + XDP_PACKET_HEADROOM;
@@ -568,7 +568,7 @@
i = nb_entries;
while (i--) {
xskb = list_first_entry(&pool->free_list, struct xdp_buff_xsk, free_list_node);
- list_del(&xskb->free_list_node);
+ list_del_init(&xskb->free_list_node);
*xdp = &xskb->xdp;
xdp++;
@@ -615,6 +615,9 @@
void xp_free(struct xdp_buff_xsk *xskb)
{
+ if (!list_empty(&xskb->free_list_node))
+ return;
+
xskb->pool->free_list_cnt++;
list_add(&xskb->free_list_node, &xskb->pool->free_list);
}
diff --git a/samples/Kconfig b/samples/Kconfig
index bec3528..43d2e9a 100644
--- a/samples/Kconfig
+++ b/samples/Kconfig
@@ -31,6 +31,15 @@
This builds an ftrace direct function example
that hooks to wake_up_process and prints the parameters.
+config SAMPLE_FTRACE_DIRECT_MULTI
+ tristate "Build register_ftrace_direct_multi() example"
+ depends on DYNAMIC_FTRACE_WITH_DIRECT_CALLS && m
+ depends on HAVE_SAMPLE_FTRACE_DIRECT_MULTI
+ help
+ This builds an ftrace direct function example
+ that hooks to wake_up_process and schedule, and prints
+ the function addresses.
+
config SAMPLE_TRACE_ARRAY
tristate "Build sample module for kernel access to Ftrace instancess"
depends on EVENT_TRACING && m
@@ -237,5 +246,5 @@
config HAVE_SAMPLE_FTRACE_DIRECT
bool
-config HAVE_SAMPLE_FTRACE_MULTI_DIRECT
+config HAVE_SAMPLE_FTRACE_DIRECT_MULTI
bool
diff --git a/samples/Makefile b/samples/Makefile
index b7b9830..4bcd6b9 100644
--- a/samples/Makefile
+++ b/samples/Makefile
@@ -22,7 +22,7 @@
obj-$(CONFIG_SAMPLE_TRACE_EVENTS) += trace_events/
obj-$(CONFIG_SAMPLE_TRACE_PRINTK) += trace_printk/
obj-$(CONFIG_SAMPLE_FTRACE_DIRECT) += ftrace/
-obj-$(CONFIG_SAMPLE_FTRACE_MULTI_DIRECT) += ftrace/
+obj-$(CONFIG_SAMPLE_FTRACE_DIRECT_MULTI) += ftrace/
obj-$(CONFIG_SAMPLE_TRACE_ARRAY) += ftrace/
subdir-$(CONFIG_SAMPLE_UHID) += uhid
obj-$(CONFIG_VIDEO_PCI_SKELETON) += v4l/
diff --git a/samples/bpf/hbm_kern.h b/samples/bpf/hbm_kern.h
index 722b3fa..1752a46 100644
--- a/samples/bpf/hbm_kern.h
+++ b/samples/bpf/hbm_kern.h
@@ -9,8 +9,6 @@
* Include file for sample Host Bandwidth Manager (HBM) BPF programs
*/
#define KBUILD_MODNAME "foo"
-#include <stddef.h>
-#include <stdbool.h>
#include <uapi/linux/bpf.h>
#include <uapi/linux/if_ether.h>
#include <uapi/linux/if_packet.h>
diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c
index d84e694..a81704d 100644
--- a/samples/bpf/xdp_redirect_cpu_user.c
+++ b/samples/bpf/xdp_redirect_cpu_user.c
@@ -309,7 +309,6 @@
const char *mprog_filename = NULL, *mprog_name = NULL;
struct xdp_redirect_cpu *skel;
struct bpf_map_info info = {};
- char ifname_buf[IF_NAMESIZE];
struct bpf_cpumap_val value;
__u32 infosz = sizeof(info);
int ret = EXIT_FAIL_OPTION;
@@ -390,10 +389,10 @@
case 'd':
if (strlen(optarg) >= IF_NAMESIZE) {
fprintf(stderr, "-d/--dev name too long\n");
+ usage(argv, long_options, __doc__, mask, true, skel->obj);
goto end_cpu;
}
- safe_strncpy(ifname_buf, optarg, strlen(ifname_buf));
- ifindex = if_nametoindex(ifname_buf);
+ ifindex = if_nametoindex(optarg);
if (!ifindex)
ifindex = strtoul(optarg, NULL, 0);
if (!ifindex) {
diff --git a/samples/bpf/xdp_sample_user.c b/samples/bpf/xdp_sample_user.c
index b32d821..8740838 100644
--- a/samples/bpf/xdp_sample_user.c
+++ b/samples/bpf/xdp_sample_user.c
@@ -120,7 +120,10 @@
__u64 xmit;
} totals;
struct {
- __u64 pps;
+ union {
+ __u64 pps;
+ __u64 num;
+ };
__u64 drop;
__u64 err;
} rx_cnt;
@@ -1322,7 +1325,7 @@
static void sample_summary_print(void)
{
- double period = sample_out.rx_cnt.pps;
+ double num = sample_out.rx_cnt.num;
if (sample_out.totals.rx) {
double pkts = sample_out.totals.rx;
@@ -1330,7 +1333,7 @@
print_always(" Packets received : %'-10llu\n",
sample_out.totals.rx);
print_always(" Average packets/s : %'-10.0f\n",
- sample_round(pkts / period));
+ sample_round(pkts / num));
}
if (sample_out.totals.redir) {
double pkts = sample_out.totals.redir;
@@ -1338,7 +1341,7 @@
print_always(" Packets redirected : %'-10llu\n",
sample_out.totals.redir);
print_always(" Average redir/s : %'-10.0f\n",
- sample_round(pkts / period));
+ sample_round(pkts / num));
}
if (sample_out.totals.drop)
print_always(" Rx dropped : %'-10llu\n",
@@ -1355,7 +1358,7 @@
print_always(" Packets transmitted : %'-10llu\n",
sample_out.totals.xmit);
print_always(" Average transmit/s : %'-10.0f\n",
- sample_round(pkts / period));
+ sample_round(pkts / num));
}
}
@@ -1422,7 +1425,7 @@
return 0;
}
-static void sample_summary_update(struct sample_output *out, int interval)
+static void sample_summary_update(struct sample_output *out)
{
sample_out.totals.rx += out->totals.rx;
sample_out.totals.redir += out->totals.redir;
@@ -1430,12 +1433,11 @@
sample_out.totals.drop_xmit += out->totals.drop_xmit;
sample_out.totals.err += out->totals.err;
sample_out.totals.xmit += out->totals.xmit;
- sample_out.rx_cnt.pps += interval;
+ sample_out.rx_cnt.num++;
}
static void sample_stats_print(int mask, struct stats_record *cur,
- struct stats_record *prev, char *prog_name,
- int interval)
+ struct stats_record *prev, char *prog_name)
{
struct sample_output out = {};
@@ -1452,7 +1454,7 @@
else if (mask & SAMPLE_DEVMAP_XMIT_CNT_MULTI)
stats_get_devmap_xmit_multi(cur, prev, 0, &out,
mask & SAMPLE_DEVMAP_XMIT_CNT);
- sample_summary_update(&out, interval);
+ sample_summary_update(&out);
stats_print(prog_name, mask, cur, prev, &out);
}
@@ -1495,7 +1497,7 @@
}
static int sample_timer_cb(int timerfd, struct stats_record **rec,
- struct stats_record **prev, int interval)
+ struct stats_record **prev)
{
char line[64] = "Summary";
int ret;
@@ -1524,7 +1526,7 @@
snprintf(line, sizeof(line), "%s->%s", f ?: "?", t ?: "?");
}
- sample_stats_print(sample_mask, *rec, *prev, line, interval);
+ sample_stats_print(sample_mask, *rec, *prev, line);
return 0;
}
@@ -1579,7 +1581,7 @@
if (pfd[0].revents & POLLIN)
ret = sample_signal_cb();
else if (pfd[1].revents & POLLIN)
- ret = sample_timer_cb(timerfd, &rec, &prev, interval);
+ ret = sample_timer_cb(timerfd, &rec, &prev);
if (ret)
break;
diff --git a/samples/ftrace/Makefile b/samples/ftrace/Makefile
index e8a3f85..b9198e2 100644
--- a/samples/ftrace/Makefile
+++ b/samples/ftrace/Makefile
@@ -3,7 +3,7 @@
obj-$(CONFIG_SAMPLE_FTRACE_DIRECT) += ftrace-direct.o
obj-$(CONFIG_SAMPLE_FTRACE_DIRECT) += ftrace-direct-too.o
obj-$(CONFIG_SAMPLE_FTRACE_DIRECT) += ftrace-direct-modify.o
-obj-$(CONFIG_SAMPLE_FTRACE_MULTI_DIRECT) += ftrace-direct-multi.o
+obj-$(CONFIG_SAMPLE_FTRACE_DIRECT_MULTI) += ftrace-direct-multi.o
CFLAGS_sample-trace-array.o := -I$(src)
obj-$(CONFIG_SAMPLE_TRACE_ARRAY) += sample-trace-array.o
diff --git a/samples/ftrace/ftrace-direct-multi.c b/samples/ftrace/ftrace-direct-multi.c
index b6d7806..2fafc9a 100644
--- a/samples/ftrace/ftrace-direct-multi.c
+++ b/samples/ftrace/ftrace-direct-multi.c
@@ -4,6 +4,7 @@
#include <linux/mm.h> /* for handle_mm_fault() */
#include <linux/ftrace.h>
#include <linux/sched/stat.h>
+#include <asm/asm-offsets.h>
extern void my_direct_func(unsigned long ip);
@@ -14,6 +15,8 @@
extern void my_tramp(void *);
+#ifdef CONFIG_X86_64
+
asm (
" .pushsection .text, \"ax\", @progbits\n"
" .type my_tramp, @function\n"
@@ -31,6 +34,33 @@
" .popsection\n"
);
+#endif /* CONFIG_X86_64 */
+
+#ifdef CONFIG_S390
+
+asm (
+" .pushsection .text, \"ax\", @progbits\n"
+" .type my_tramp, @function\n"
+" .globl my_tramp\n"
+" my_tramp:"
+" lgr %r1,%r15\n"
+" stmg %r0,%r5,"__stringify(__SF_GPRS)"(%r15)\n"
+" stg %r14,"__stringify(__SF_GPRS+8*8)"(%r15)\n"
+" aghi %r15,"__stringify(-STACK_FRAME_OVERHEAD)"\n"
+" stg %r1,"__stringify(__SF_BACKCHAIN)"(%r15)\n"
+" lgr %r2,%r0\n"
+" brasl %r14,my_direct_func\n"
+" aghi %r15,"__stringify(STACK_FRAME_OVERHEAD)"\n"
+" lmg %r0,%r5,"__stringify(__SF_GPRS)"(%r15)\n"
+" lg %r14,"__stringify(__SF_GPRS+8*8)"(%r15)\n"
+" lgr %r1,%r0\n"
+" br %r1\n"
+" .size my_tramp, .-my_tramp\n"
+" .popsection\n"
+);
+
+#endif /* CONFIG_S390 */
+
static struct ftrace_ops direct;
static int __init ftrace_direct_multi_init(void)
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index d0ce5cf..d5b5f2a 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -277,6 +277,7 @@
#define X86_FEATURE_XSAVEC (10*32+ 1) /* XSAVEC instruction */
#define X86_FEATURE_XGETBV1 (10*32+ 2) /* XGETBV with ECX = 1 instruction */
#define X86_FEATURE_XSAVES (10*32+ 3) /* XSAVES/XRSTORS instructions */
+#define X86_FEATURE_XFD (10*32+ 4) /* "" eXtended Feature Disabling */
/*
* Extended auxiliary flags: Linux defined - for features scattered in various
@@ -298,6 +299,7 @@
/* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
#define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */
#define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */
+#define X86_FEATURE_AMX_TILE (18*32+24) /* AMX tile Support */
/* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
#define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 2ef1f65..5a776a0 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -504,4 +504,8 @@
#define KVM_PMU_EVENT_ALLOW 0
#define KVM_PMU_EVENT_DENY 1
+/* for KVM_{GET,SET,HAS}_DEVICE_ATTR */
+#define KVM_VCPU_TSC_CTRL 0 /* control group for the timestamp counter (TSC) */
+#define KVM_VCPU_TSC_OFFSET 0 /* attribute for the TSC offset */
+
#endif /* _ASM_X86_KVM_H */
diff --git a/tools/bpf/runqslower/Makefile b/tools/bpf/runqslower/Makefile
index bbd1150..8791d0e 100644
--- a/tools/bpf/runqslower/Makefile
+++ b/tools/bpf/runqslower/Makefile
@@ -88,5 +88,4 @@
$(DEFAULT_BPFTOOL): $(BPFOBJ) | $(BPFTOOL_OUTPUT)
$(Q)$(MAKE) $(submake_extras) -C ../bpftool OUTPUT=$(BPFTOOL_OUTPUT) \
- LIBBPF_OUTPUT=$(BPFOBJ_OUTPUT) \
- LIBBPF_DESTDIR=$(BPF_DESTDIR) CC=$(HOSTCC) LD=$(HOSTLD)
+ CC=$(HOSTCC) LD=$(HOSTLD)
diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c
index 9204395..0b243ce8 100644
--- a/tools/build/feature/test-all.c
+++ b/tools/build/feature/test-all.c
@@ -200,7 +200,6 @@
main_test_timerfd();
main_test_stackprotector_all();
main_test_libdw_dwarf_unwind();
- main_test_sync_compare_and_swap(argc, argv);
main_test_zlib();
main_test_pthread_attr_setaffinity_np();
main_test_pthread_barrier();
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index a067410..1daa452 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -269,6 +269,7 @@
#define KVM_EXIT_AP_RESET_HOLD 32
#define KVM_EXIT_X86_BUS_LOCK 33
#define KVM_EXIT_XEN 34
+#define KVM_EXIT_RISCV_SBI 35
/* For KVM_EXIT_INTERNAL_ERROR */
/* Emulate instruction failed. */
@@ -397,13 +398,23 @@
* "ndata" is correct, that new fields are enumerated in "flags",
* and that each flag enumerates fields that are 64-bit aligned
* and sized (so that ndata+internal.data[] is valid/accurate).
+ *
+ * Space beyond the defined fields may be used to store arbitrary
+ * debug information relating to the emulation failure. It is
+ * accounted for in "ndata" but the format is unspecified and is
+ * not represented in "flags". Any such information is *not* ABI!
*/
struct {
__u32 suberror;
__u32 ndata;
__u64 flags;
- __u8 insn_size;
- __u8 insn_bytes[15];
+ union {
+ struct {
+ __u8 insn_size;
+ __u8 insn_bytes[15];
+ };
+ };
+ /* Arbitrary debug data may follow. */
} emulation_failure;
/* KVM_EXIT_OSI */
struct {
@@ -469,6 +480,13 @@
} msr;
/* KVM_EXIT_XEN */
struct kvm_xen_exit xen;
+ /* KVM_EXIT_RISCV_SBI */
+ struct {
+ unsigned long extension_id;
+ unsigned long function_id;
+ unsigned long args[6];
+ unsigned long ret[2];
+ } riscv_sbi;
/* Fix the size of the union. */
char padding[256];
};
@@ -1112,6 +1130,7 @@
#define KVM_CAP_BINARY_STATS_FD 203
#define KVM_CAP_EXIT_ON_EMULATION_FAILURE 204
#define KVM_CAP_ARM_MTE 205
+#define KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM 206
#ifdef KVM_CAP_IRQ_ROUTING
@@ -1223,11 +1242,16 @@
/* Do not use 1, KVM_CHECK_EXTENSION returned it before we had flags. */
#define KVM_CLOCK_TSC_STABLE 2
+#define KVM_CLOCK_REALTIME (1 << 2)
+#define KVM_CLOCK_HOST_TSC (1 << 3)
struct kvm_clock_data {
__u64 clock;
__u32 flags;
- __u32 pad[9];
+ __u32 pad0;
+ __u64 realtime;
+ __u64 host_tsc;
+ __u32 pad[4];
};
/* For KVM_CAP_SW_TLB */
diff --git a/tools/lib/bpf/bpf_gen_internal.h b/tools/lib/bpf/bpf_gen_internal.h
index d26e547..6f3df00 100644
--- a/tools/lib/bpf/bpf_gen_internal.h
+++ b/tools/lib/bpf/bpf_gen_internal.h
@@ -45,8 +45,8 @@
int nr_fd_array;
};
-void bpf_gen__init(struct bpf_gen *gen, int log_level);
-int bpf_gen__finish(struct bpf_gen *gen);
+void bpf_gen__init(struct bpf_gen *gen, int log_level, int nr_progs, int nr_maps);
+int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps);
void bpf_gen__free(struct bpf_gen *gen);
void bpf_gen__load_btf(struct bpf_gen *gen, const void *raw_data, __u32 raw_size);
void bpf_gen__map_create(struct bpf_gen *gen, struct bpf_create_map_params *map_attr, int map_idx);
diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c
index 502dea5..9934851 100644
--- a/tools/lib/bpf/gen_loader.c
+++ b/tools/lib/bpf/gen_loader.c
@@ -18,7 +18,7 @@
#define MAX_USED_MAPS 64
#define MAX_USED_PROGS 32
#define MAX_KFUNC_DESCS 256
-#define MAX_FD_ARRAY_SZ (MAX_USED_PROGS + MAX_KFUNC_DESCS)
+#define MAX_FD_ARRAY_SZ (MAX_USED_MAPS + MAX_KFUNC_DESCS)
/* The following structure describes the stack layout of the loader program.
* In addition R6 contains the pointer to context.
@@ -33,8 +33,8 @@
*/
struct loader_stack {
__u32 btf_fd;
- __u32 prog_fd[MAX_USED_PROGS];
__u32 inner_map_fd;
+ __u32 prog_fd[MAX_USED_PROGS];
};
#define stack_off(field) \
@@ -42,6 +42,11 @@
#define attr_field(attr, field) (attr + offsetof(union bpf_attr, field))
+static int blob_fd_array_off(struct bpf_gen *gen, int index)
+{
+ return gen->fd_array + index * sizeof(int);
+}
+
static int realloc_insn_buf(struct bpf_gen *gen, __u32 size)
{
size_t off = gen->insn_cur - gen->insn_start;
@@ -102,11 +107,15 @@
emit(gen, insn2);
}
-void bpf_gen__init(struct bpf_gen *gen, int log_level)
+static int add_data(struct bpf_gen *gen, const void *data, __u32 size);
+static void emit_sys_close_blob(struct bpf_gen *gen, int blob_off);
+
+void bpf_gen__init(struct bpf_gen *gen, int log_level, int nr_progs, int nr_maps)
{
- size_t stack_sz = sizeof(struct loader_stack);
+ size_t stack_sz = sizeof(struct loader_stack), nr_progs_sz;
int i;
+ gen->fd_array = add_data(gen, NULL, MAX_FD_ARRAY_SZ * sizeof(int));
gen->log_level = log_level;
/* save ctx pointer into R6 */
emit(gen, BPF_MOV64_REG(BPF_REG_6, BPF_REG_1));
@@ -118,19 +127,27 @@
emit(gen, BPF_MOV64_IMM(BPF_REG_3, 0));
emit(gen, BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel));
+ /* amount of stack actually used, only used to calculate iterations, not stack offset */
+ nr_progs_sz = offsetof(struct loader_stack, prog_fd[nr_progs]);
/* jump over cleanup code */
emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0,
- /* size of cleanup code below */
- (stack_sz / 4) * 3 + 2));
+ /* size of cleanup code below (including map fd cleanup) */
+ (nr_progs_sz / 4) * 3 + 2 +
+ /* 6 insns for emit_sys_close_blob,
+ * 6 insns for debug_regs in emit_sys_close_blob
+ */
+ nr_maps * (6 + (gen->log_level ? 6 : 0))));
/* remember the label where all error branches will jump to */
gen->cleanup_label = gen->insn_cur - gen->insn_start;
/* emit cleanup code: close all temp FDs */
- for (i = 0; i < stack_sz; i += 4) {
+ for (i = 0; i < nr_progs_sz; i += 4) {
emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_10, -stack_sz + i));
emit(gen, BPF_JMP_IMM(BPF_JSLE, BPF_REG_1, 0, 1));
emit(gen, BPF_EMIT_CALL(BPF_FUNC_sys_close));
}
+ for (i = 0; i < nr_maps; i++)
+ emit_sys_close_blob(gen, blob_fd_array_off(gen, i));
/* R7 contains the error code from sys_bpf. Copy it into R0 and exit. */
emit(gen, BPF_MOV64_REG(BPF_REG_0, BPF_REG_7));
emit(gen, BPF_EXIT_INSN());
@@ -160,8 +177,6 @@
*/
static int add_map_fd(struct bpf_gen *gen)
{
- if (!gen->fd_array)
- gen->fd_array = add_data(gen, NULL, MAX_FD_ARRAY_SZ * sizeof(int));
if (gen->nr_maps == MAX_USED_MAPS) {
pr_warn("Total maps exceeds %d\n", MAX_USED_MAPS);
gen->error = -E2BIG;
@@ -174,8 +189,6 @@
{
int cur;
- if (!gen->fd_array)
- gen->fd_array = add_data(gen, NULL, MAX_FD_ARRAY_SZ * sizeof(int));
if (gen->nr_fd_array == MAX_KFUNC_DESCS) {
cur = add_data(gen, NULL, sizeof(int));
return (cur - gen->fd_array) / sizeof(int);
@@ -183,11 +196,6 @@
return MAX_USED_MAPS + gen->nr_fd_array++;
}
-static int blob_fd_array_off(struct bpf_gen *gen, int index)
-{
- return gen->fd_array + index * sizeof(int);
-}
-
static int insn_bytes_to_bpf_size(__u32 sz)
{
switch (sz) {
@@ -359,10 +367,15 @@
__emit_sys_close(gen);
}
-int bpf_gen__finish(struct bpf_gen *gen)
+int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps)
{
int i;
+ if (nr_progs != gen->nr_progs || nr_maps != gen->nr_maps) {
+ pr_warn("progs/maps mismatch\n");
+ gen->error = -EFAULT;
+ return gen->error;
+ }
emit_sys_close_stack(gen, stack_off(btf_fd));
for (i = 0; i < gen->nr_progs; i++)
move_stack2ctx(gen,
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index a1bea19..7c74342 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -7258,7 +7258,7 @@
}
if (obj->gen_loader)
- bpf_gen__init(obj->gen_loader, attr->log_level);
+ bpf_gen__init(obj->gen_loader, attr->log_level, obj->nr_programs, obj->nr_maps);
err = bpf_object__probe_loading(obj);
err = err ? : bpf_object__load_vmlinux_btf(obj, false);
@@ -7277,7 +7277,7 @@
for (i = 0; i < obj->nr_maps; i++)
obj->maps[i].fd = -1;
if (!err)
- err = bpf_gen__finish(obj->gen_loader);
+ err = bpf_gen__finish(obj->gen_loader, obj->nr_programs, obj->nr_maps);
}
/* clean up fd_array */
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 07e65a0..afd1447 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -1010,6 +1010,9 @@
ifndef NO_AUXTRACE
$(call detected,CONFIG_AUXTRACE)
CFLAGS += -DHAVE_AUXTRACE_SUPPORT
+ ifeq ($(feature-reallocarray), 0)
+ CFLAGS += -DCOMPAT_NEED_REALLOCARRAY
+ endif
endif
endif
diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
index 1ca7bc3..e2c481f 100644
--- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
+++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
@@ -363,3 +363,4 @@
446 n64 landlock_restrict_self sys_landlock_restrict_self
# 447 reserved for memfd_secret
448 n64 process_mrelease sys_process_mrelease
+449 n64 futex_waitv sys_futex_waitv
diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c
index 488f6e6..fa0ff4c 100644
--- a/tools/perf/bench/sched-messaging.c
+++ b/tools/perf/bench/sched-messaging.c
@@ -223,6 +223,8 @@
snd_ctx->out_fds[i] = fds[1];
if (!thread_mode)
close(fds[0]);
+
+ free(ctx);
}
/* Now we have all the fds, fork the senders */
@@ -239,6 +241,8 @@
for (i = 0; i < num_fds; i++)
close(snd_ctx->out_fds[i]);
+ free(snd_ctx);
+
/* Return number of children to reap */
return num_fds * 2;
}
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 8167ebf..8ae4004 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -619,14 +619,17 @@
int ret;
struct perf_session *session = rep->session;
struct evlist *evlist = session->evlist;
- const char *help = perf_tip(system_path(TIPDIR));
+ char *help = NULL, *path = NULL;
- if (help == NULL) {
+ path = system_path(TIPDIR);
+ if (perf_tip(&help, path) || help == NULL) {
/* fallback for people who don't install perf ;-) */
- help = perf_tip(DOCDIR);
- if (help == NULL)
- help = "Cannot load tips.txt file, please install perf!";
+ free(path);
+ path = system_path(DOCDIR);
+ if (perf_tip(&help, path) || help == NULL)
+ help = strdup("Cannot load tips.txt file, please install perf!");
}
+ free(path);
switch (use_browser) {
case 1:
@@ -651,7 +654,7 @@
ret = evlist__tty_browse_hists(evlist, rep, help);
break;
}
-
+ free(help);
return ret;
}
diff --git a/tools/perf/tests/event_update.c b/tools/perf/tests/event_update.c
index fbb68de..d01532d 100644
--- a/tools/perf/tests/event_update.c
+++ b/tools/perf/tests/event_update.c
@@ -88,7 +88,6 @@
struct evsel *evsel;
struct event_name tmp;
struct evlist *evlist = evlist__new_default();
- char *unit = strdup("KRAVA");
TEST_ASSERT_VAL("failed to get evlist", evlist);
@@ -99,7 +98,8 @@
perf_evlist__id_add(&evlist->core, &evsel->core, 0, 0, 123);
- evsel->unit = unit;
+ free((char *)evsel->unit);
+ evsel->unit = strdup("KRAVA");
TEST_ASSERT_VAL("failed to synthesize attr update unit",
!perf_event__synthesize_event_update_unit(NULL, evsel, process_event_unit));
@@ -119,7 +119,6 @@
TEST_ASSERT_VAL("failed to synthesize attr update cpus",
!perf_event__synthesize_event_update_cpus(&tmp.tool, evsel, process_event_cpus));
- free(unit);
evlist__delete(evlist);
return 0;
}
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index b669d22..07f2411 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -36,7 +36,7 @@
* These are based on the input value (213) specified
* in branch_stack variable.
*/
-#define BS_EXPECTED_BE 0xa00d000000000000
+#define BS_EXPECTED_BE 0xa000d00000000000
#define BS_EXPECTED_LE 0xd5000000
#define FLAG(s) s->branch_stack->entries[i].flags
diff --git a/tools/perf/tests/wp.c b/tools/perf/tests/wp.c
index 820d942..9d4c451 100644
--- a/tools/perf/tests/wp.c
+++ b/tools/perf/tests/wp.c
@@ -21,6 +21,7 @@
volatile u64 data1;
volatile u8 data2[3];
+#ifndef __s390x__
static int wp_read(int fd, long long *count, int size)
{
int ret = read(fd, count, size);
@@ -48,7 +49,6 @@
attr->exclude_hv = 1;
}
-#ifndef __s390x__
static int __event(int wp_type, void *wp_addr, unsigned long wp_len)
{
int fd;
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index c1f24d0..5075ece 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -535,6 +535,18 @@
#undef __HPP_SORT_ACC_FN
#undef __HPP_SORT_RAW_FN
+static void fmt_free(struct perf_hpp_fmt *fmt)
+{
+ /*
+ * At this point fmt should be completely
+ * unhooked, if not it's a bug.
+ */
+ BUG_ON(!list_empty(&fmt->list));
+ BUG_ON(!list_empty(&fmt->sort_list));
+
+ if (fmt->free)
+ fmt->free(fmt);
+}
void perf_hpp__init(void)
{
@@ -598,9 +610,10 @@
list_add(&format->sort_list, &list->sorts);
}
-void perf_hpp__column_unregister(struct perf_hpp_fmt *format)
+static void perf_hpp__column_unregister(struct perf_hpp_fmt *format)
{
list_del_init(&format->list);
+ fmt_free(format);
}
void perf_hpp__cancel_cumulate(void)
@@ -672,19 +685,6 @@
}
-static void fmt_free(struct perf_hpp_fmt *fmt)
-{
- /*
- * At this point fmt should be completely
- * unhooked, if not it's a bug.
- */
- BUG_ON(!list_empty(&fmt->list));
- BUG_ON(!list_empty(&fmt->sort_list));
-
- if (fmt->free)
- fmt->free(fmt);
-}
-
void perf_hpp__reset_output_field(struct perf_hpp_list *list)
{
struct perf_hpp_fmt *fmt, *tmp;
diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index 4748bcf..fccac06 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -51,6 +51,7 @@
u8 timeless_decoding;
u8 data_queued;
+ u64 sample_type;
u8 sample_flc;
u8 sample_llc;
u8 sample_tlb;
@@ -287,6 +288,12 @@
event->sample.header.size = sizeof(struct perf_event_header);
}
+static int arm_spe__inject_event(union perf_event *event, struct perf_sample *sample, u64 type)
+{
+ event->header.size = perf_event__sample_event_size(sample, type, 0);
+ return perf_event__synthesize_sample(event, type, 0, sample);
+}
+
static inline int
arm_spe_deliver_synth_event(struct arm_spe *spe,
struct arm_spe_queue *speq __maybe_unused,
@@ -295,6 +302,12 @@
{
int ret;
+ if (spe->synth_opts.inject) {
+ ret = arm_spe__inject_event(event, sample, spe->sample_type);
+ if (ret)
+ return ret;
+ }
+
ret = perf_session__deliver_synth_event(spe->session, event, sample);
if (ret)
pr_err("ARM SPE: failed to deliver event, error %d\n", ret);
@@ -986,6 +999,8 @@
else
attr.sample_type |= PERF_SAMPLE_TIME;
+ spe->sample_type = attr.sample_type;
+
attr.exclude_user = evsel->core.attr.exclude_user;
attr.exclude_kernel = evsel->core.attr.exclude_kernel;
attr.exclude_hv = evsel->core.attr.exclude_hv;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index a59fb2e..ac0127b 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -241,7 +241,7 @@
{
perf_evsel__init(&evsel->core, attr, idx);
evsel->tracking = !idx;
- evsel->unit = "";
+ evsel->unit = strdup("");
evsel->scale = 1.0;
evsel->max_events = ULONG_MAX;
evsel->evlist = NULL;
@@ -276,13 +276,8 @@
}
if (evsel__is_clock(evsel)) {
- /*
- * The evsel->unit points to static alias->unit
- * so it's ok to use static string in here.
- */
- static const char *unit = "msec";
-
- evsel->unit = unit;
+ free((char *)evsel->unit);
+ evsel->unit = strdup("msec");
evsel->scale = 1e-6;
}
@@ -420,7 +415,11 @@
evsel->max_events = orig->max_events;
evsel->tool_event = orig->tool_event;
- evsel->unit = orig->unit;
+ free((char *)evsel->unit);
+ evsel->unit = strdup(orig->unit);
+ if (evsel->unit == NULL)
+ goto out_err;
+
evsel->scale = orig->scale;
evsel->snapshot = orig->snapshot;
evsel->per_pkg = orig->per_pkg;
@@ -1441,6 +1440,7 @@
zfree(&evsel->group_name);
zfree(&evsel->name);
zfree(&evsel->pmu_name);
+ zfree(&evsel->unit);
zfree(&evsel->metric_id);
evsel__zero_per_pkg(evsel);
hashmap__free(evsel->per_pkg_mask);
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index fda8d14..79cce21 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -4257,9 +4257,11 @@
switch (ev->type) {
case PERF_EVENT_UPDATE__UNIT:
+ free((char *)evsel->unit);
evsel->unit = strdup(ev->data);
break;
case PERF_EVENT_UPDATE__NAME:
+ free(evsel->name);
evsel->name = strdup(ev->data);
break;
case PERF_EVENT_UPDATE__SCALE:
@@ -4268,11 +4270,11 @@
break;
case PERF_EVENT_UPDATE__CPUS:
ev_cpus = (struct perf_record_event_update_cpus *)ev->data;
-
map = cpu_map__new_data(&ev_cpus->cpus);
- if (map)
+ if (map) {
+ perf_cpu_map__put(evsel->core.own_cpus);
evsel->core.own_cpus = map;
- else
+ } else
pr_err("failed to get event_update cpus\n");
default:
break;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 65fe65b..b776465 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -289,15 +289,10 @@
return htime;
}
-static void he_stat__add_period(struct he_stat *he_stat, u64 period,
- u64 weight, u64 ins_lat, u64 p_stage_cyc)
+static void he_stat__add_period(struct he_stat *he_stat, u64 period)
{
-
he_stat->period += period;
- he_stat->weight += weight;
he_stat->nr_events += 1;
- he_stat->ins_lat += ins_lat;
- he_stat->p_stage_cyc += p_stage_cyc;
}
static void he_stat__add_stat(struct he_stat *dest, struct he_stat *src)
@@ -308,9 +303,6 @@
dest->period_guest_sys += src->period_guest_sys;
dest->period_guest_us += src->period_guest_us;
dest->nr_events += src->nr_events;
- dest->weight += src->weight;
- dest->ins_lat += src->ins_lat;
- dest->p_stage_cyc += src->p_stage_cyc;
}
static void he_stat__decay(struct he_stat *he_stat)
@@ -598,9 +590,6 @@
struct hist_entry *he;
int64_t cmp;
u64 period = entry->stat.period;
- u64 weight = entry->stat.weight;
- u64 ins_lat = entry->stat.ins_lat;
- u64 p_stage_cyc = entry->stat.p_stage_cyc;
bool leftmost = true;
p = &hists->entries_in->rb_root.rb_node;
@@ -619,11 +608,11 @@
if (!cmp) {
if (sample_self) {
- he_stat__add_period(&he->stat, period, weight, ins_lat, p_stage_cyc);
+ he_stat__add_period(&he->stat, period);
hist_entry__add_callchain_period(he, period);
}
if (symbol_conf.cumulate_callchain)
- he_stat__add_period(he->stat_acc, period, weight, ins_lat, p_stage_cyc);
+ he_stat__add_period(he->stat_acc, period);
/*
* This mem info was allocated from sample__resolve_mem
@@ -733,9 +722,6 @@
.stat = {
.nr_events = 1,
.period = sample->period,
- .weight = sample->weight,
- .ins_lat = sample->ins_lat,
- .p_stage_cyc = sample->p_stage_cyc,
},
.parent = sym_parent,
.filtered = symbol__parent_filter(sym_parent) | al->filtered,
@@ -748,6 +734,9 @@
.raw_size = sample->raw_size,
.ops = ops,
.time = hist_time(sample->time),
+ .weight = sample->weight,
+ .ins_lat = sample->ins_lat,
+ .p_stage_cyc = sample->p_stage_cyc,
}, *he = hists__findnew_entry(hists, &entry, al, sample_self);
if (!hists->has_callchains && he && he->callchain_size != 0)
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 5343b62..621f35a 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -369,7 +369,6 @@
};
void perf_hpp__init(void);
-void perf_hpp__column_unregister(struct perf_hpp_fmt *format);
void perf_hpp__cancel_cumulate(void);
void perf_hpp__setup_output_field(struct perf_hpp_list *list);
void perf_hpp__reset_output_field(struct perf_hpp_list *list);
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 5bfb6f8..ba74fdf 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -402,8 +402,10 @@
if (!evsel)
return -ENOMEM;
evsel->tool_event = tool_event;
- if (tool_event == PERF_TOOL_DURATION_TIME)
- evsel->unit = "ns";
+ if (tool_event == PERF_TOOL_DURATION_TIME) {
+ free((char *)evsel->unit);
+ evsel->unit = strdup("ns");
+ }
return 0;
}
@@ -1630,7 +1632,8 @@
if (parse_state->fake_pmu)
return 0;
- evsel->unit = info.unit;
+ free((char *)evsel->unit);
+ evsel->unit = strdup(info.unit);
evsel->scale = info.scale;
evsel->per_pkg = info.per_pkg;
evsel->snapshot = info.snapshot;
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 568a88c..a111065b 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1325,88 +1325,68 @@
.se_width_idx = HISTC_MISPREDICT,
};
-static u64 he_weight(struct hist_entry *he)
-{
- return he->stat.nr_events ? he->stat.weight / he->stat.nr_events : 0;
-}
-
static int64_t
-sort__local_weight_cmp(struct hist_entry *left, struct hist_entry *right)
+sort__weight_cmp(struct hist_entry *left, struct hist_entry *right)
{
- return he_weight(left) - he_weight(right);
+ return left->weight - right->weight;
}
static int hist_entry__local_weight_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
- return repsep_snprintf(bf, size, "%-*llu", width, he_weight(he));
+ return repsep_snprintf(bf, size, "%-*llu", width, he->weight);
}
struct sort_entry sort_local_weight = {
.se_header = "Local Weight",
- .se_cmp = sort__local_weight_cmp,
+ .se_cmp = sort__weight_cmp,
.se_snprintf = hist_entry__local_weight_snprintf,
.se_width_idx = HISTC_LOCAL_WEIGHT,
};
-static int64_t
-sort__global_weight_cmp(struct hist_entry *left, struct hist_entry *right)
-{
- return left->stat.weight - right->stat.weight;
-}
-
static int hist_entry__global_weight_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
- return repsep_snprintf(bf, size, "%-*llu", width, he->stat.weight);
+ return repsep_snprintf(bf, size, "%-*llu", width,
+ he->weight * he->stat.nr_events);
}
struct sort_entry sort_global_weight = {
.se_header = "Weight",
- .se_cmp = sort__global_weight_cmp,
+ .se_cmp = sort__weight_cmp,
.se_snprintf = hist_entry__global_weight_snprintf,
.se_width_idx = HISTC_GLOBAL_WEIGHT,
};
-static u64 he_ins_lat(struct hist_entry *he)
-{
- return he->stat.nr_events ? he->stat.ins_lat / he->stat.nr_events : 0;
-}
-
static int64_t
-sort__local_ins_lat_cmp(struct hist_entry *left, struct hist_entry *right)
+sort__ins_lat_cmp(struct hist_entry *left, struct hist_entry *right)
{
- return he_ins_lat(left) - he_ins_lat(right);
+ return left->ins_lat - right->ins_lat;
}
static int hist_entry__local_ins_lat_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
- return repsep_snprintf(bf, size, "%-*u", width, he_ins_lat(he));
+ return repsep_snprintf(bf, size, "%-*u", width, he->ins_lat);
}
struct sort_entry sort_local_ins_lat = {
.se_header = "Local INSTR Latency",
- .se_cmp = sort__local_ins_lat_cmp,
+ .se_cmp = sort__ins_lat_cmp,
.se_snprintf = hist_entry__local_ins_lat_snprintf,
.se_width_idx = HISTC_LOCAL_INS_LAT,
};
-static int64_t
-sort__global_ins_lat_cmp(struct hist_entry *left, struct hist_entry *right)
-{
- return left->stat.ins_lat - right->stat.ins_lat;
-}
-
static int hist_entry__global_ins_lat_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
- return repsep_snprintf(bf, size, "%-*u", width, he->stat.ins_lat);
+ return repsep_snprintf(bf, size, "%-*u", width,
+ he->ins_lat * he->stat.nr_events);
}
struct sort_entry sort_global_ins_lat = {
.se_header = "INSTR Latency",
- .se_cmp = sort__global_ins_lat_cmp,
+ .se_cmp = sort__ins_lat_cmp,
.se_snprintf = hist_entry__global_ins_lat_snprintf,
.se_width_idx = HISTC_GLOBAL_INS_LAT,
};
@@ -1414,13 +1394,13 @@
static int64_t
sort__global_p_stage_cyc_cmp(struct hist_entry *left, struct hist_entry *right)
{
- return left->stat.p_stage_cyc - right->stat.p_stage_cyc;
+ return left->p_stage_cyc - right->p_stage_cyc;
}
static int hist_entry__p_stage_cyc_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
- return repsep_snprintf(bf, size, "%-*u", width, he->stat.p_stage_cyc);
+ return repsep_snprintf(bf, size, "%-*u", width, he->p_stage_cyc);
}
struct sort_entry sort_p_stage_cyc = {
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index b67c469..7b71455 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -49,9 +49,6 @@
u64 period_us;
u64 period_guest_sys;
u64 period_guest_us;
- u64 weight;
- u64 ins_lat;
- u64 p_stage_cyc;
u32 nr_events;
};
@@ -109,6 +106,9 @@
s32 socket;
s32 cpu;
u64 code_page_size;
+ u64 weight;
+ u64 ins_lat;
+ u64 p_stage_cyc;
u8 cpumode;
u8 depth;
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 37a9492..df3c467 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -379,32 +379,32 @@
return 0;
}
-const char *perf_tip(const char *dirpath)
+int perf_tip(char **strp, const char *dirpath)
{
struct strlist *tips;
struct str_node *node;
- char *tip = NULL;
struct strlist_config conf = {
.dirname = dirpath,
.file_only = true,
};
+ int ret = 0;
+ *strp = NULL;
tips = strlist__new("tips.txt", &conf);
if (tips == NULL)
- return errno == ENOENT ? NULL :
- "Tip: check path of tips.txt or get more memory! ;-p";
+ return -errno;
if (strlist__nr_entries(tips) == 0)
goto out;
node = strlist__entry(tips, random() % strlist__nr_entries(tips));
- if (asprintf(&tip, "Tip: %s", node->s) < 0)
- tip = (char *)"Tip: get more memory! ;-)";
+ if (asprintf(strp, "Tip: %s", node->s) < 0)
+ ret = -ENOMEM;
out:
strlist__delete(tips);
- return tip;
+ return ret;
}
char *perf_exe(char *buf, int len)
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index ad73705..9f0d36b 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -39,7 +39,7 @@
#define KVER_FMT "%d.%d.%d"
#define KVER_PARAM(x) KVER_VERSION(x), KVER_PATCHLEVEL(x), KVER_SUBLEVEL(x)
-const char *perf_tip(const char *dirpath);
+int perf_tip(char **strp, const char *dirpath);
#ifndef HAVE_SCHED_GETCPU_SUPPORT
int sched_getcpu(void);
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 54b0a41..62fafbe 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -187,7 +187,7 @@
$(OUTPUT)/runqslower: $(BPFOBJ) | $(DEFAULT_BPFTOOL) $(RUNQSLOWER_OUTPUT)
$(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/runqslower \
OUTPUT=$(RUNQSLOWER_OUTPUT) VMLINUX_BTF=$(VMLINUX_BTF) \
- BPFTOOL_OUTPUT=$(BUILD_DIR)/bpftool/ \
+ BPFTOOL_OUTPUT=$(HOST_BUILD_DIR)/bpftool/ \
BPFOBJ_OUTPUT=$(BUILD_DIR)/libbpf \
BPFOBJ=$(BPFOBJ) BPF_INCLUDE=$(INCLUDE_DIR) && \
cp $(RUNQSLOWER_OUTPUT)runqslower $@
diff --git a/tools/testing/selftests/bpf/prog_tests/helper_restricted.c b/tools/testing/selftests/bpf/prog_tests/helper_restricted.c
new file mode 100644
index 0000000..e1de5f8
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/helper_restricted.c
@@ -0,0 +1,33 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "test_helper_restricted.skel.h"
+
+void test_helper_restricted(void)
+{
+ int prog_i = 0, prog_cnt;
+ int duration = 0;
+
+ do {
+ struct test_helper_restricted *test;
+ int maybeOK;
+
+ test = test_helper_restricted__open();
+ if (!ASSERT_OK_PTR(test, "open"))
+ return;
+
+ prog_cnt = test->skeleton->prog_cnt;
+
+ for (int j = 0; j < prog_cnt; ++j) {
+ struct bpf_program *prog = *test->skeleton->progs[j].prog;
+
+ maybeOK = bpf_program__set_autoload(prog, prog_i == j);
+ ASSERT_OK(maybeOK, "set autoload");
+ }
+
+ maybeOK = test_helper_restricted__load(test);
+ CHECK(!maybeOK, test->skeleton->progs[prog_i].name, "helper isn't restricted");
+
+ test_helper_restricted__destroy(test);
+ } while (++prog_i < prog_cnt);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_helper_restricted.c b/tools/testing/selftests/bpf/progs/test_helper_restricted.c
new file mode 100644
index 0000000..68d64c3
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_helper_restricted.c
@@ -0,0 +1,123 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <time.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+struct timer {
+ struct bpf_timer t;
+};
+
+struct lock {
+ struct bpf_spin_lock l;
+};
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __uint(max_entries, 1);
+ __type(key, __u32);
+ __type(value, struct timer);
+} timers SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __uint(max_entries, 1);
+ __type(key, __u32);
+ __type(value, struct lock);
+} locks SEC(".maps");
+
+static int timer_cb(void *map, int *key, struct timer *timer)
+{
+ return 0;
+}
+
+static void timer_work(void)
+{
+ struct timer *timer;
+ const int key = 0;
+
+ timer = bpf_map_lookup_elem(&timers, &key);
+ if (timer) {
+ bpf_timer_init(&timer->t, &timers, CLOCK_MONOTONIC);
+ bpf_timer_set_callback(&timer->t, timer_cb);
+ bpf_timer_start(&timer->t, 10E9, 0);
+ bpf_timer_cancel(&timer->t);
+ }
+}
+
+static void spin_lock_work(void)
+{
+ const int key = 0;
+ struct lock *lock;
+
+ lock = bpf_map_lookup_elem(&locks, &key);
+ if (lock) {
+ bpf_spin_lock(&lock->l);
+ bpf_spin_unlock(&lock->l);
+ }
+}
+
+SEC("raw_tp/sys_enter")
+int raw_tp_timer(void *ctx)
+{
+ timer_work();
+
+ return 0;
+}
+
+SEC("tp/syscalls/sys_enter_nanosleep")
+int tp_timer(void *ctx)
+{
+ timer_work();
+
+ return 0;
+}
+
+SEC("kprobe/sys_nanosleep")
+int kprobe_timer(void *ctx)
+{
+ timer_work();
+
+ return 0;
+}
+
+SEC("perf_event")
+int perf_event_timer(void *ctx)
+{
+ timer_work();
+
+ return 0;
+}
+
+SEC("raw_tp/sys_enter")
+int raw_tp_spin_lock(void *ctx)
+{
+ spin_lock_work();
+
+ return 0;
+}
+
+SEC("tp/syscalls/sys_enter_nanosleep")
+int tp_spin_lock(void *ctx)
+{
+ spin_lock_work();
+
+ return 0;
+}
+
+SEC("kprobe/sys_nanosleep")
+int kprobe_spin_lock(void *ctx)
+{
+ spin_lock_work();
+
+ return 0;
+}
+
+SEC("perf_event")
+int perf_event_spin_lock(void *ctx)
+{
+ spin_lock_work();
+
+ return 0;
+}
+
+const char LICENSE[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 25afe42..465ef3f 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -92,6 +92,7 @@
int fixup_map_event_output[MAX_FIXUPS];
int fixup_map_reuseport_array[MAX_FIXUPS];
int fixup_map_ringbuf[MAX_FIXUPS];
+ int fixup_map_timer[MAX_FIXUPS];
/* Expected verifier log output for result REJECT or VERBOSE_ACCEPT.
* Can be a tab-separated sequence of expected strings. An empty string
* means no log verification.
@@ -604,8 +605,15 @@
* int cnt;
* struct bpf_spin_lock l;
* };
+ * struct bpf_timer {
+ * __u64 :64;
+ * __u64 :64;
+ * } __attribute__((aligned(8)));
+ * struct timer {
+ * struct bpf_timer t;
+ * };
*/
-static const char btf_str_sec[] = "\0bpf_spin_lock\0val\0cnt\0l";
+static const char btf_str_sec[] = "\0bpf_spin_lock\0val\0cnt\0l\0bpf_timer\0timer\0t";
static __u32 btf_raw_types[] = {
/* int */
BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
@@ -616,6 +624,11 @@
BTF_TYPE_ENC(15, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8),
BTF_MEMBER_ENC(19, 1, 0), /* int cnt; */
BTF_MEMBER_ENC(23, 2, 32),/* struct bpf_spin_lock l; */
+ /* struct bpf_timer */ /* [4] */
+ BTF_TYPE_ENC(25, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 0), 16),
+ /* struct timer */ /* [5] */
+ BTF_TYPE_ENC(35, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), 16),
+ BTF_MEMBER_ENC(41, 4, 0), /* struct bpf_timer t; */
};
static int load_btf(void)
@@ -696,6 +709,29 @@
return fd;
}
+static int create_map_timer(void)
+{
+ struct bpf_create_map_attr attr = {
+ .name = "test_map",
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .key_size = 4,
+ .value_size = 16,
+ .max_entries = 1,
+ .btf_key_type_id = 1,
+ .btf_value_type_id = 5,
+ };
+ int fd, btf_fd;
+
+ btf_fd = load_btf();
+ if (btf_fd < 0)
+ return -1;
+ attr.btf_fd = btf_fd;
+ fd = bpf_create_map_xattr(&attr);
+ if (fd < 0)
+ printf("Failed to create map with timer\n");
+ return fd;
+}
+
static char bpf_vlog[UINT_MAX >> 8];
static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type,
@@ -722,6 +758,7 @@
int *fixup_map_event_output = test->fixup_map_event_output;
int *fixup_map_reuseport_array = test->fixup_map_reuseport_array;
int *fixup_map_ringbuf = test->fixup_map_ringbuf;
+ int *fixup_map_timer = test->fixup_map_timer;
if (test->fill_helper) {
test->fill_insns = calloc(MAX_TEST_INSNS, sizeof(struct bpf_insn));
@@ -907,6 +944,13 @@
fixup_map_ringbuf++;
} while (*fixup_map_ringbuf);
}
+ if (*fixup_map_timer) {
+ map_fds[21] = create_map_timer();
+ do {
+ prog[*fixup_map_timer].imm = map_fds[21];
+ fixup_map_timer++;
+ } while (*fixup_map_timer);
+ }
}
struct libcap {
diff --git a/tools/testing/selftests/bpf/verifier/helper_restricted.c b/tools/testing/selftests/bpf/verifier/helper_restricted.c
new file mode 100644
index 0000000..a067b70
--- /dev/null
+++ b/tools/testing/selftests/bpf/verifier/helper_restricted.c
@@ -0,0 +1,196 @@
+{
+ "bpf_ktime_get_coarse_ns is forbidden in BPF_PROG_TYPE_KPROBE",
+ .insns = {
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ktime_get_coarse_ns),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "unknown func bpf_ktime_get_coarse_ns",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_KPROBE,
+},
+{
+ "bpf_ktime_get_coarse_ns is forbidden in BPF_PROG_TYPE_TRACEPOINT",
+ .insns = {
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ktime_get_coarse_ns),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "unknown func bpf_ktime_get_coarse_ns",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+},
+{
+ "bpf_ktime_get_coarse_ns is forbidden in BPF_PROG_TYPE_PERF_EVENT",
+ .insns = {
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ktime_get_coarse_ns),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "unknown func bpf_ktime_get_coarse_ns",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_PERF_EVENT,
+},
+{
+ "bpf_ktime_get_coarse_ns is forbidden in BPF_PROG_TYPE_RAW_TRACEPOINT",
+ .insns = {
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ktime_get_coarse_ns),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "unknown func bpf_ktime_get_coarse_ns",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT,
+},
+{
+ "bpf_timer_init isn restricted in BPF_PROG_TYPE_KPROBE",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_LD_MAP_FD(BPF_REG_2, 0),
+ BPF_MOV64_IMM(BPF_REG_3, 1),
+ BPF_EMIT_CALL(BPF_FUNC_timer_init),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_timer = { 3, 8 },
+ .errstr = "tracing progs cannot use bpf_timer yet",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_KPROBE,
+},
+{
+ "bpf_timer_init is forbidden in BPF_PROG_TYPE_PERF_EVENT",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_LD_MAP_FD(BPF_REG_2, 0),
+ BPF_MOV64_IMM(BPF_REG_3, 1),
+ BPF_EMIT_CALL(BPF_FUNC_timer_init),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_timer = { 3, 8 },
+ .errstr = "tracing progs cannot use bpf_timer yet",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_PERF_EVENT,
+},
+{
+ "bpf_timer_init is forbidden in BPF_PROG_TYPE_TRACEPOINT",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_LD_MAP_FD(BPF_REG_2, 0),
+ BPF_MOV64_IMM(BPF_REG_3, 1),
+ BPF_EMIT_CALL(BPF_FUNC_timer_init),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_timer = { 3, 8 },
+ .errstr = "tracing progs cannot use bpf_timer yet",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+},
+{
+ "bpf_timer_init is forbidden in BPF_PROG_TYPE_RAW_TRACEPOINT",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_LD_MAP_FD(BPF_REG_2, 0),
+ BPF_MOV64_IMM(BPF_REG_3, 1),
+ BPF_EMIT_CALL(BPF_FUNC_timer_init),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_timer = { 3, 8 },
+ .errstr = "tracing progs cannot use bpf_timer yet",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT,
+},
+{
+ "bpf_spin_lock is forbidden in BPF_PROG_TYPE_KPROBE",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_EMIT_CALL(BPF_FUNC_spin_lock),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_spin_lock = { 3 },
+ .errstr = "tracing progs cannot use bpf_spin_lock yet",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_KPROBE,
+},
+{
+ "bpf_spin_lock is forbidden in BPF_PROG_TYPE_TRACEPOINT",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_EMIT_CALL(BPF_FUNC_spin_lock),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_spin_lock = { 3 },
+ .errstr = "tracing progs cannot use bpf_spin_lock yet",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+},
+{
+ "bpf_spin_lock is forbidden in BPF_PROG_TYPE_PERF_EVENT",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_EMIT_CALL(BPF_FUNC_spin_lock),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_spin_lock = { 3 },
+ .errstr = "tracing progs cannot use bpf_spin_lock yet",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_PERF_EVENT,
+},
+{
+ "bpf_spin_lock is forbidden in BPF_PROG_TYPE_RAW_TRACEPOINT",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_EMIT_CALL(BPF_FUNC_spin_lock),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_spin_lock = { 3 },
+ .errstr = "tracing progs cannot use bpf_spin_lock yet",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT,
+},
diff --git a/tools/testing/selftests/bpf/verifier/map_in_map.c b/tools/testing/selftests/bpf/verifier/map_in_map.c
index 2798927..128a348 100644
--- a/tools/testing/selftests/bpf/verifier/map_in_map.c
+++ b/tools/testing/selftests/bpf/verifier/map_in_map.c
@@ -19,6 +19,40 @@
.result = ACCEPT,
},
{
+ "map in map state pruning",
+ .insns = {
+ BPF_ST_MEM(0, BPF_REG_10, -4, 0),
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -4),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_6),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_6),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 11),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_6),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_6),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+ BPF_EXIT_INSN(),
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_in_map = { 4, 14 },
+ .flags = BPF_F_TEST_STATE_FREQ,
+ .result = VERBOSE_ACCEPT,
+ .errstr = "processed 25 insns",
+ .prog_type = BPF_PROG_TYPE_XDP,
+},
+{
"invalid inner map pointer",
.insns = {
BPF_ST_MEM(0, BPF_REG_10, -4, 0),
diff --git a/tools/testing/selftests/gpio/Makefile b/tools/testing/selftests/gpio/Makefile
index 39f2bbe..d7b312b 100644
--- a/tools/testing/selftests/gpio/Makefile
+++ b/tools/testing/selftests/gpio/Makefile
@@ -3,5 +3,6 @@
TEST_PROGS := gpio-mockup.sh
TEST_FILES := gpio-mockup-sysfs.sh
TEST_GEN_PROGS_EXTENDED := gpio-mockup-cdev
+CFLAGS += -O2 -g -Wall -I../../../../usr/include/
include ../lib.mk
diff --git a/tools/testing/selftests/gpio/gpio-mockup-cdev.c b/tools/testing/selftests/gpio/gpio-mockup-cdev.c
index e83eac7..d1640f4 100644
--- a/tools/testing/selftests/gpio/gpio-mockup-cdev.c
+++ b/tools/testing/selftests/gpio/gpio-mockup-cdev.c
@@ -117,7 +117,7 @@
{
char *chip;
int opt, ret, cfd, lfd;
- unsigned int offset, val, abiv;
+ unsigned int offset, val = 0, abiv;
uint32_t flags_v1;
uint64_t flags_v2;
diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index d4a8301..3763105 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -23,6 +23,7 @@
/x86_64/platform_info_test
/x86_64/set_boot_cpu_id
/x86_64/set_sregs_test
+/x86_64/sev_migrate_tests
/x86_64/smm_test
/x86_64/state_test
/x86_64/svm_vmcall_test
diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c
index 5d95113..d890903 100644
--- a/tools/testing/selftests/kvm/access_tracking_perf_test.c
+++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c
@@ -47,7 +47,7 @@
#include "guest_modes.h"
/* Global variable used to synchronize all of the vCPU threads. */
-static int iteration = -1;
+static int iteration;
/* Defines what vCPU threads should do during a given iteration. */
static enum {
@@ -215,12 +215,11 @@
return true;
}
-static void *vcpu_thread_main(void *arg)
+static void vcpu_thread_main(struct perf_test_vcpu_args *vcpu_args)
{
- struct perf_test_vcpu_args *vcpu_args = arg;
struct kvm_vm *vm = perf_test_args.vm;
int vcpu_id = vcpu_args->vcpu_id;
- int current_iteration = -1;
+ int current_iteration = 0;
while (spin_wait_for_next_iteration(¤t_iteration)) {
switch (READ_ONCE(iteration_work)) {
@@ -235,8 +234,6 @@
vcpu_last_completed_iteration[vcpu_id] = current_iteration;
}
-
- return NULL;
}
static void spin_wait_for_vcpu(int vcpu_id, int target_iteration)
@@ -277,8 +274,7 @@
static void access_memory(struct kvm_vm *vm, int vcpus, enum access_type access,
const char *description)
{
- perf_test_args.wr_fract = (access == ACCESS_READ) ? INT_MAX : 1;
- sync_global_to_guest(vm, perf_test_args);
+ perf_test_set_wr_fract(vm, (access == ACCESS_READ) ? INT_MAX : 1);
iteration_work = ITERATION_ACCESS_MEMORY;
run_iteration(vm, vcpus, description);
}
@@ -296,48 +292,16 @@
run_iteration(vm, vcpus, "Mark memory idle");
}
-static pthread_t *create_vcpu_threads(int vcpus)
-{
- pthread_t *vcpu_threads;
- int i;
-
- vcpu_threads = malloc(vcpus * sizeof(vcpu_threads[0]));
- TEST_ASSERT(vcpu_threads, "Failed to allocate vcpu_threads.");
-
- for (i = 0; i < vcpus; i++) {
- vcpu_last_completed_iteration[i] = iteration;
- pthread_create(&vcpu_threads[i], NULL, vcpu_thread_main,
- &perf_test_args.vcpu_args[i]);
- }
-
- return vcpu_threads;
-}
-
-static void terminate_vcpu_threads(pthread_t *vcpu_threads, int vcpus)
-{
- int i;
-
- /* Set done to signal the vCPU threads to exit */
- done = true;
-
- for (i = 0; i < vcpus; i++)
- pthread_join(vcpu_threads[i], NULL);
-}
-
static void run_test(enum vm_guest_mode mode, void *arg)
{
struct test_params *params = arg;
struct kvm_vm *vm;
- pthread_t *vcpu_threads;
int vcpus = params->vcpus;
vm = perf_test_create_vm(mode, vcpus, params->vcpu_memory_bytes, 1,
- params->backing_src);
+ params->backing_src, !overlap_memory_access);
- perf_test_setup_vcpus(vm, vcpus, params->vcpu_memory_bytes,
- !overlap_memory_access);
-
- vcpu_threads = create_vcpu_threads(vcpus);
+ perf_test_start_vcpu_threads(vcpus, vcpu_thread_main);
pr_info("\n");
access_memory(vm, vcpus, ACCESS_WRITE, "Populating memory");
@@ -352,8 +316,10 @@
mark_memory_idle(vm, vcpus);
access_memory(vm, vcpus, ACCESS_READ, "Reading from idle memory");
- terminate_vcpu_threads(vcpu_threads, vcpus);
- free(vcpu_threads);
+ /* Set done to signal the vCPU threads to exit */
+ done = true;
+
+ perf_test_join_vcpu_threads(vcpus);
perf_test_destroy_vm(vm);
}
diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c
index 1510b21..6a719d0 100644
--- a/tools/testing/selftests/kvm/demand_paging_test.c
+++ b/tools/testing/selftests/kvm/demand_paging_test.c
@@ -42,10 +42,9 @@
static size_t demand_paging_size;
static char *guest_data_prototype;
-static void *vcpu_worker(void *data)
+static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args)
{
int ret;
- struct perf_test_vcpu_args *vcpu_args = (struct perf_test_vcpu_args *)data;
int vcpu_id = vcpu_args->vcpu_id;
struct kvm_vm *vm = perf_test_args.vm;
struct kvm_run *run;
@@ -68,8 +67,6 @@
ts_diff = timespec_elapsed(start);
PER_VCPU_DEBUG("vCPU %d execution time: %ld.%.9lds\n", vcpu_id,
ts_diff.tv_sec, ts_diff.tv_nsec);
-
- return NULL;
}
static int handle_uffd_page_request(int uffd_mode, int uffd, uint64_t addr)
@@ -282,7 +279,6 @@
static void run_test(enum vm_guest_mode mode, void *arg)
{
struct test_params *p = arg;
- pthread_t *vcpu_threads;
pthread_t *uffd_handler_threads = NULL;
struct uffd_handler_args *uffd_args = NULL;
struct timespec start;
@@ -293,9 +289,7 @@
int r;
vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1,
- p->src_type);
-
- perf_test_args.wr_fract = 1;
+ p->src_type, p->partition_vcpu_memory_access);
demand_paging_size = get_backing_src_pagesz(p->src_type);
@@ -304,12 +298,6 @@
"Failed to allocate buffer for guest data pattern");
memset(guest_data_prototype, 0xAB, demand_paging_size);
- vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
- TEST_ASSERT(vcpu_threads, "Memory allocation failed");
-
- perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size,
- p->partition_vcpu_memory_access);
-
if (p->uffd_mode) {
uffd_handler_threads =
malloc(nr_vcpus * sizeof(*uffd_handler_threads));
@@ -322,26 +310,15 @@
TEST_ASSERT(pipefds, "Unable to allocate memory for pipefd");
for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
- vm_paddr_t vcpu_gpa;
+ struct perf_test_vcpu_args *vcpu_args;
void *vcpu_hva;
void *vcpu_alias;
- uint64_t vcpu_mem_size;
-
- if (p->partition_vcpu_memory_access) {
- vcpu_gpa = guest_test_phys_mem +
- (vcpu_id * guest_percpu_mem_size);
- vcpu_mem_size = guest_percpu_mem_size;
- } else {
- vcpu_gpa = guest_test_phys_mem;
- vcpu_mem_size = guest_percpu_mem_size * nr_vcpus;
- }
- PER_VCPU_DEBUG("Added VCPU %d with test mem gpa [%lx, %lx)\n",
- vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_mem_size);
+ vcpu_args = &perf_test_args.vcpu_args[vcpu_id];
/* Cache the host addresses of the region */
- vcpu_hva = addr_gpa2hva(vm, vcpu_gpa);
- vcpu_alias = addr_gpa2alias(vm, vcpu_gpa);
+ vcpu_hva = addr_gpa2hva(vm, vcpu_args->gpa);
+ vcpu_alias = addr_gpa2alias(vm, vcpu_args->gpa);
/*
* Set up user fault fd to handle demand paging
@@ -355,32 +332,18 @@
pipefds[vcpu_id * 2], p->uffd_mode,
p->uffd_delay, &uffd_args[vcpu_id],
vcpu_hva, vcpu_alias,
- vcpu_mem_size);
+ vcpu_args->pages * perf_test_args.guest_page_size);
}
}
- /* Export the shared variables to the guest */
- sync_global_to_guest(vm, perf_test_args);
-
pr_info("Finished creating vCPUs and starting uffd threads\n");
clock_gettime(CLOCK_MONOTONIC, &start);
-
- for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
- pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker,
- &perf_test_args.vcpu_args[vcpu_id]);
- }
-
+ perf_test_start_vcpu_threads(nr_vcpus, vcpu_worker);
pr_info("Started all vCPUs\n");
- /* Wait for the vcpu threads to quit */
- for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
- pthread_join(vcpu_threads[vcpu_id], NULL);
- PER_VCPU_DEBUG("Joined thread for vCPU %d\n", vcpu_id);
- }
-
+ perf_test_join_vcpu_threads(nr_vcpus);
ts_diff = timespec_elapsed(start);
-
pr_info("All vCPU threads joined\n");
if (p->uffd_mode) {
@@ -404,7 +367,6 @@
perf_test_destroy_vm(vm);
free(guest_data_prototype);
- free(vcpu_threads);
if (p->uffd_mode) {
free(uffd_handler_threads);
free(uffd_args);
diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c
index 7ffab5b..1954b96 100644
--- a/tools/testing/selftests/kvm/dirty_log_perf_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c
@@ -31,7 +31,7 @@
static int iteration;
static int vcpu_last_completed_iteration[KVM_MAX_VCPUS];
-static void *vcpu_worker(void *data)
+static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args)
{
int ret;
struct kvm_vm *vm = perf_test_args.vm;
@@ -41,7 +41,6 @@
struct timespec ts_diff;
struct timespec total = (struct timespec){0};
struct timespec avg;
- struct perf_test_vcpu_args *vcpu_args = (struct perf_test_vcpu_args *)data;
int vcpu_id = vcpu_args->vcpu_id;
run = vcpu_state(vm, vcpu_id);
@@ -83,8 +82,6 @@
pr_debug("\nvCPU %d dirtied 0x%lx pages over %d iterations in %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
vcpu_id, pages_count, vcpu_last_completed_iteration[vcpu_id],
total.tv_sec, total.tv_nsec, avg.tv_sec, avg.tv_nsec);
-
- return NULL;
}
struct test_params {
@@ -170,7 +167,6 @@
static void run_test(enum vm_guest_mode mode, void *arg)
{
struct test_params *p = arg;
- pthread_t *vcpu_threads;
struct kvm_vm *vm;
unsigned long **bitmaps;
uint64_t guest_num_pages;
@@ -186,9 +182,10 @@
struct timespec clear_dirty_log_total = (struct timespec){0};
vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size,
- p->slots, p->backing_src);
+ p->slots, p->backing_src,
+ p->partition_vcpu_memory_access);
- perf_test_args.wr_fract = p->wr_fract;
+ perf_test_set_wr_fract(vm, p->wr_fract);
guest_num_pages = (nr_vcpus * guest_percpu_mem_size) >> vm_get_page_shift(vm);
guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages);
@@ -203,25 +200,15 @@
vm_enable_cap(vm, &cap);
}
- vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
- TEST_ASSERT(vcpu_threads, "Memory allocation failed");
-
- perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size,
- p->partition_vcpu_memory_access);
-
- sync_global_to_guest(vm, perf_test_args);
-
/* Start the iterations */
iteration = 0;
host_quit = false;
clock_gettime(CLOCK_MONOTONIC, &start);
- for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
+ for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++)
vcpu_last_completed_iteration[vcpu_id] = -1;
- pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker,
- &perf_test_args.vcpu_args[vcpu_id]);
- }
+ perf_test_start_vcpu_threads(nr_vcpus, vcpu_worker);
/* Allow the vCPUs to populate memory */
pr_debug("Starting iteration %d - Populating\n", iteration);
@@ -290,8 +277,7 @@
/* Tell the vcpu thread to quit */
host_quit = true;
- for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++)
- pthread_join(vcpu_threads[vcpu_id], NULL);
+ perf_test_join_vcpu_threads(nr_vcpus);
avg = timespec_div(get_dirty_log_total, p->iterations);
pr_info("Get dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
@@ -306,7 +292,6 @@
}
free_bitmaps(bitmaps, p->slots);
- free(vcpu_threads);
perf_test_destroy_vm(vm);
}
diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index 792c60e1..3fcd89e 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -115,7 +115,7 @@
addr = guest_test_virt_mem;
addr += (READ_ONCE(random_array[i]) % guest_num_pages)
* guest_page_size;
- addr &= ~(host_page_size - 1);
+ addr = align_down(addr, host_page_size);
*(uint64_t *)addr = READ_ONCE(iteration);
}
@@ -737,14 +737,14 @@
if (!p->phys_offset) {
guest_test_phys_mem = (vm_get_max_gfn(vm) -
guest_num_pages) * guest_page_size;
- guest_test_phys_mem &= ~(host_page_size - 1);
+ guest_test_phys_mem = align_down(guest_test_phys_mem, host_page_size);
} else {
guest_test_phys_mem = p->phys_offset;
}
#ifdef __s390x__
/* Align to 1M (segment size) */
- guest_test_phys_mem &= ~((1 << 20) - 1);
+ guest_test_phys_mem = align_down(guest_test_phys_mem, 1 << 20);
#endif
pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem);
diff --git a/tools/testing/selftests/kvm/include/perf_test_util.h b/tools/testing/selftests/kvm/include/perf_test_util.h
index df9f1a3..a86f953 100644
--- a/tools/testing/selftests/kvm/include/perf_test_util.h
+++ b/tools/testing/selftests/kvm/include/perf_test_util.h
@@ -8,6 +8,8 @@
#ifndef SELFTEST_KVM_PERF_TEST_UTIL_H
#define SELFTEST_KVM_PERF_TEST_UTIL_H
+#include <pthread.h>
+
#include "kvm_util.h"
/* Default guest test virtual memory offset */
@@ -18,6 +20,7 @@
#define PERF_TEST_MEM_SLOT_INDEX 1
struct perf_test_vcpu_args {
+ uint64_t gpa;
uint64_t gva;
uint64_t pages;
@@ -27,7 +30,7 @@
struct perf_test_args {
struct kvm_vm *vm;
- uint64_t host_page_size;
+ uint64_t gpa;
uint64_t guest_page_size;
int wr_fract;
@@ -36,19 +39,15 @@
extern struct perf_test_args perf_test_args;
-/*
- * Guest physical memory offset of the testing memory slot.
- * This will be set to the topmost valid physical address minus
- * the test memory size.
- */
-extern uint64_t guest_test_phys_mem;
-
struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
uint64_t vcpu_memory_bytes, int slots,
- enum vm_mem_backing_src_type backing_src);
+ enum vm_mem_backing_src_type backing_src,
+ bool partition_vcpu_memory_access);
void perf_test_destroy_vm(struct kvm_vm *vm);
-void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus,
- uint64_t vcpu_memory_bytes,
- bool partition_vcpu_memory_access);
+
+void perf_test_set_wr_fract(struct kvm_vm *vm, int wr_fract);
+
+void perf_test_start_vcpu_threads(int vcpus, void (*vcpu_fn)(struct perf_test_vcpu_args *));
+void perf_test_join_vcpu_threads(int vcpus);
#endif /* SELFTEST_KVM_PERF_TEST_UTIL_H */
diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
index f8fddc8..99e0dcd 100644
--- a/tools/testing/selftests/kvm/include/test_util.h
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -104,6 +104,7 @@
size_t get_def_hugetlb_pagesz(void);
const struct vm_mem_backing_src_alias *vm_mem_backing_src_alias(uint32_t i);
size_t get_backing_src_pagesz(uint32_t i);
+bool is_backing_src_hugetlb(uint32_t i);
void backing_src_help(const char *flag);
enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name);
long get_run_delay(void);
@@ -117,4 +118,29 @@
return vm_mem_backing_src_alias(t)->flag & MAP_SHARED;
}
+/* Aligns x up to the next multiple of size. Size must be a power of 2. */
+static inline uint64_t align_up(uint64_t x, uint64_t size)
+{
+ uint64_t mask = size - 1;
+
+ TEST_ASSERT(size != 0 && !(size & (size - 1)),
+ "size not a power of 2: %lu", size);
+ return ((x + mask) & ~mask);
+}
+
+static inline uint64_t align_down(uint64_t x, uint64_t size)
+{
+ uint64_t x_aligned_up = align_up(x, size);
+
+ if (x == x_aligned_up)
+ return x;
+ else
+ return x_aligned_up - size;
+}
+
+static inline void *align_ptr_up(void *x, size_t size)
+{
+ return (void *)align_up((unsigned long)x, size);
+}
+
#endif /* SELFTEST_KVM_TEST_UTIL_H */
diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c
index 36407cb..3836322 100644
--- a/tools/testing/selftests/kvm/kvm_page_table_test.c
+++ b/tools/testing/selftests/kvm/kvm_page_table_test.c
@@ -280,7 +280,7 @@
#ifdef __s390x__
alignment = max(0x100000, alignment);
#endif
- guest_test_phys_mem &= ~(alignment - 1);
+ guest_test_phys_mem = align_down(guest_test_virt_mem, alignment);
/* Set up the shared data structure test_args */
test_args.vm = vm;
diff --git a/tools/testing/selftests/kvm/lib/elf.c b/tools/testing/selftests/kvm/lib/elf.c
index eac44f5..13e8e3d 100644
--- a/tools/testing/selftests/kvm/lib/elf.c
+++ b/tools/testing/selftests/kvm/lib/elf.c
@@ -157,8 +157,7 @@
"memsize of 0,\n"
" phdr index: %u p_memsz: 0x%" PRIx64,
n1, (uint64_t) phdr.p_memsz);
- vm_vaddr_t seg_vstart = phdr.p_vaddr;
- seg_vstart &= ~(vm_vaddr_t)(vm->page_size - 1);
+ vm_vaddr_t seg_vstart = align_down(phdr.p_vaddr, vm->page_size);
vm_vaddr_t seg_vend = phdr.p_vaddr + phdr.p_memsz - 1;
seg_vend |= vm->page_size - 1;
size_t seg_size = seg_vend - seg_vstart + 1;
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 14bb4d5..8f2e0bb1 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -22,15 +22,6 @@
static int vcpu_mmap_sz(void);
-/* Aligns x up to the next multiple of size. Size must be a power of 2. */
-static void *align(void *x, size_t size)
-{
- size_t mask = size - 1;
- TEST_ASSERT(size != 0 && !(size & (size - 1)),
- "size not a power of 2: %lu", size);
- return (void *) (((size_t) x + mask) & ~mask);
-}
-
int open_path_or_exit(const char *path, int flags)
{
int fd;
@@ -191,15 +182,15 @@
}
const struct vm_guest_mode_params vm_guest_mode_params[] = {
- { 52, 48, 0x1000, 12 },
- { 52, 48, 0x10000, 16 },
- { 48, 48, 0x1000, 12 },
- { 48, 48, 0x10000, 16 },
- { 40, 48, 0x1000, 12 },
- { 40, 48, 0x10000, 16 },
- { 0, 0, 0x1000, 12 },
- { 47, 64, 0x1000, 12 },
- { 44, 64, 0x1000, 12 },
+ [VM_MODE_P52V48_4K] = { 52, 48, 0x1000, 12 },
+ [VM_MODE_P52V48_64K] = { 52, 48, 0x10000, 16 },
+ [VM_MODE_P48V48_4K] = { 48, 48, 0x1000, 12 },
+ [VM_MODE_P48V48_64K] = { 48, 48, 0x10000, 16 },
+ [VM_MODE_P40V48_4K] = { 40, 48, 0x1000, 12 },
+ [VM_MODE_P40V48_64K] = { 40, 48, 0x10000, 16 },
+ [VM_MODE_PXXV48_4K] = { 0, 0, 0x1000, 12 },
+ [VM_MODE_P47V64_4K] = { 47, 64, 0x1000, 12 },
+ [VM_MODE_P44V64_4K] = { 44, 64, 0x1000, 12 },
};
_Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES,
"Missing new mode params?");
@@ -879,9 +870,17 @@
alignment = 1;
#endif
+ /*
+ * When using THP mmap is not guaranteed to returned a hugepage aligned
+ * address so we have to pad the mmap. Padding is not needed for HugeTLB
+ * because mmap will always return an address aligned to the HugeTLB
+ * page size.
+ */
if (src_type == VM_MEM_SRC_ANONYMOUS_THP)
alignment = max(backing_src_pagesz, alignment);
+ ASSERT_EQ(guest_paddr, align_up(guest_paddr, backing_src_pagesz));
+
/* Add enough memory to align up if necessary */
if (alignment > 1)
region->mmap_size += alignment;
@@ -914,8 +913,13 @@
"test_malloc failed, mmap_start: %p errno: %i",
region->mmap_start, errno);
+ TEST_ASSERT(!is_backing_src_hugetlb(src_type) ||
+ region->mmap_start == align_ptr_up(region->mmap_start, backing_src_pagesz),
+ "mmap_start %p is not aligned to HugeTLB page size 0x%lx",
+ region->mmap_start, backing_src_pagesz);
+
/* Align host address */
- region->host_mem = align(region->mmap_start, alignment);
+ region->host_mem = align_ptr_up(region->mmap_start, alignment);
/* As needed perform madvise */
if ((src_type == VM_MEM_SRC_ANONYMOUS ||
@@ -958,7 +962,7 @@
"mmap of alias failed, errno: %i", errno);
/* Align host alias address */
- region->host_alias = align(region->mmap_alias, alignment);
+ region->host_alias = align_ptr_up(region->mmap_alias, alignment);
}
}
diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c
index 0ef80db..722df3a 100644
--- a/tools/testing/selftests/kvm/lib/perf_test_util.c
+++ b/tools/testing/selftests/kvm/lib/perf_test_util.c
@@ -10,21 +10,40 @@
struct perf_test_args perf_test_args;
-uint64_t guest_test_phys_mem;
-
/*
* Guest virtual memory offset of the testing memory slot.
* Must not conflict with identity mapped test code.
*/
static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM;
+struct vcpu_thread {
+ /* The id of the vCPU. */
+ int vcpu_id;
+
+ /* The pthread backing the vCPU. */
+ pthread_t thread;
+
+ /* Set to true once the vCPU thread is up and running. */
+ bool running;
+};
+
+/* The vCPU threads involved in this test. */
+static struct vcpu_thread vcpu_threads[KVM_MAX_VCPUS];
+
+/* The function run by each vCPU thread, as provided by the test. */
+static void (*vcpu_thread_fn)(struct perf_test_vcpu_args *);
+
+/* Set to true once all vCPU threads are up and running. */
+static bool all_vcpu_threads_running;
+
/*
* Continuously write to the first 8 bytes of each page in the
* specified region.
*/
static void guest_code(uint32_t vcpu_id)
{
- struct perf_test_vcpu_args *vcpu_args = &perf_test_args.vcpu_args[vcpu_id];
+ struct perf_test_args *pta = &perf_test_args;
+ struct perf_test_vcpu_args *vcpu_args = &pta->vcpu_args[vcpu_id];
uint64_t gva;
uint64_t pages;
int i;
@@ -37,9 +56,9 @@
while (true) {
for (i = 0; i < pages; i++) {
- uint64_t addr = gva + (i * perf_test_args.guest_page_size);
+ uint64_t addr = gva + (i * pta->guest_page_size);
- if (i % perf_test_args.wr_fract == 0)
+ if (i % pta->wr_fract == 0)
*(uint64_t *)addr = 0x0123456789ABCDEF;
else
READ_ONCE(*(uint64_t *)addr);
@@ -49,35 +68,81 @@
}
}
+void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus,
+ uint64_t vcpu_memory_bytes,
+ bool partition_vcpu_memory_access)
+{
+ struct perf_test_args *pta = &perf_test_args;
+ struct perf_test_vcpu_args *vcpu_args;
+ int vcpu_id;
+
+ for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+ vcpu_args = &pta->vcpu_args[vcpu_id];
+
+ vcpu_args->vcpu_id = vcpu_id;
+ if (partition_vcpu_memory_access) {
+ vcpu_args->gva = guest_test_virt_mem +
+ (vcpu_id * vcpu_memory_bytes);
+ vcpu_args->pages = vcpu_memory_bytes /
+ pta->guest_page_size;
+ vcpu_args->gpa = pta->gpa + (vcpu_id * vcpu_memory_bytes);
+ } else {
+ vcpu_args->gva = guest_test_virt_mem;
+ vcpu_args->pages = (vcpus * vcpu_memory_bytes) /
+ pta->guest_page_size;
+ vcpu_args->gpa = pta->gpa;
+ }
+
+ vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
+
+ pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n",
+ vcpu_id, vcpu_args->gpa, vcpu_args->gpa +
+ (vcpu_args->pages * pta->guest_page_size));
+ }
+}
+
struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
uint64_t vcpu_memory_bytes, int slots,
- enum vm_mem_backing_src_type backing_src)
+ enum vm_mem_backing_src_type backing_src,
+ bool partition_vcpu_memory_access)
{
+ struct perf_test_args *pta = &perf_test_args;
struct kvm_vm *vm;
uint64_t guest_num_pages;
+ uint64_t backing_src_pagesz = get_backing_src_pagesz(backing_src);
int i;
pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
- perf_test_args.host_page_size = getpagesize();
- perf_test_args.guest_page_size = vm_guest_mode_params[mode].page_size;
+ /* By default vCPUs will write to memory. */
+ pta->wr_fract = 1;
+
+ /*
+ * Snapshot the non-huge page size. This is used by the guest code to
+ * access/dirty pages at the logging granularity.
+ */
+ pta->guest_page_size = vm_guest_mode_params[mode].page_size;
guest_num_pages = vm_adjust_num_guest_pages(mode,
- (vcpus * vcpu_memory_bytes) / perf_test_args.guest_page_size);
+ (vcpus * vcpu_memory_bytes) / pta->guest_page_size);
- TEST_ASSERT(vcpu_memory_bytes % perf_test_args.host_page_size == 0,
+ TEST_ASSERT(vcpu_memory_bytes % getpagesize() == 0,
"Guest memory size is not host page size aligned.");
- TEST_ASSERT(vcpu_memory_bytes % perf_test_args.guest_page_size == 0,
+ TEST_ASSERT(vcpu_memory_bytes % pta->guest_page_size == 0,
"Guest memory size is not guest page size aligned.");
TEST_ASSERT(guest_num_pages % slots == 0,
"Guest memory cannot be evenly divided into %d slots.",
slots);
+ /*
+ * Pass guest_num_pages to populate the page tables for test memory.
+ * The memory is also added to memslot 0, but that's a benign side
+ * effect as KVM allows aliasing HVAs in meslots.
+ */
vm = vm_create_with_vcpus(mode, vcpus, DEFAULT_GUEST_PHY_PAGES,
- (vcpus * vcpu_memory_bytes) / perf_test_args.guest_page_size,
- 0, guest_code, NULL);
+ guest_num_pages, 0, guest_code, NULL);
- perf_test_args.vm = vm;
+ pta->vm = vm;
/*
* If there should be more memory in the guest test region than there
@@ -90,20 +155,18 @@
guest_num_pages, vm_get_max_gfn(vm), vcpus,
vcpu_memory_bytes);
- guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) *
- perf_test_args.guest_page_size;
- guest_test_phys_mem &= ~(perf_test_args.host_page_size - 1);
+ pta->gpa = (vm_get_max_gfn(vm) - guest_num_pages) * pta->guest_page_size;
+ pta->gpa = align_down(pta->gpa, backing_src_pagesz);
#ifdef __s390x__
/* Align to 1M (segment size) */
- guest_test_phys_mem &= ~((1 << 20) - 1);
+ pta->gpa = align_down(pta->gpa, 1 << 20);
#endif
- pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem);
+ pr_info("guest physical test memory offset: 0x%lx\n", pta->gpa);
/* Add extra memory slots for testing */
for (i = 0; i < slots; i++) {
uint64_t region_pages = guest_num_pages / slots;
- vm_paddr_t region_start = guest_test_phys_mem +
- region_pages * perf_test_args.guest_page_size * i;
+ vm_paddr_t region_start = pta->gpa + region_pages * pta->guest_page_size * i;
vm_userspace_mem_region_add(vm, backing_src, region_start,
PERF_TEST_MEM_SLOT_INDEX + i,
@@ -111,10 +174,15 @@
}
/* Do mapping for the demand paging memory slot */
- virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages);
+ virt_map(vm, guest_test_virt_mem, pta->gpa, guest_num_pages);
+
+ perf_test_setup_vcpus(vm, vcpus, vcpu_memory_bytes, partition_vcpu_memory_access);
ucall_init(vm, NULL);
+ /* Export the shared variables to the guest. */
+ sync_global_to_guest(vm, perf_test_args);
+
return vm;
}
@@ -124,36 +192,60 @@
kvm_vm_free(vm);
}
-void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus,
- uint64_t vcpu_memory_bytes,
- bool partition_vcpu_memory_access)
+void perf_test_set_wr_fract(struct kvm_vm *vm, int wr_fract)
{
- vm_paddr_t vcpu_gpa;
- struct perf_test_vcpu_args *vcpu_args;
+ perf_test_args.wr_fract = wr_fract;
+ sync_global_to_guest(vm, perf_test_args);
+}
+
+static void *vcpu_thread_main(void *data)
+{
+ struct vcpu_thread *vcpu = data;
+
+ WRITE_ONCE(vcpu->running, true);
+
+ /*
+ * Wait for all vCPU threads to be up and running before calling the test-
+ * provided vCPU thread function. This prevents thread creation (which
+ * requires taking the mmap_sem in write mode) from interfering with the
+ * guest faulting in its memory.
+ */
+ while (!READ_ONCE(all_vcpu_threads_running))
+ ;
+
+ vcpu_thread_fn(&perf_test_args.vcpu_args[vcpu->vcpu_id]);
+
+ return NULL;
+}
+
+void perf_test_start_vcpu_threads(int vcpus, void (*vcpu_fn)(struct perf_test_vcpu_args *))
+{
int vcpu_id;
+ vcpu_thread_fn = vcpu_fn;
+ WRITE_ONCE(all_vcpu_threads_running, false);
+
for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
- vcpu_args = &perf_test_args.vcpu_args[vcpu_id];
+ struct vcpu_thread *vcpu = &vcpu_threads[vcpu_id];
- vcpu_args->vcpu_id = vcpu_id;
- if (partition_vcpu_memory_access) {
- vcpu_args->gva = guest_test_virt_mem +
- (vcpu_id * vcpu_memory_bytes);
- vcpu_args->pages = vcpu_memory_bytes /
- perf_test_args.guest_page_size;
- vcpu_gpa = guest_test_phys_mem +
- (vcpu_id * vcpu_memory_bytes);
- } else {
- vcpu_args->gva = guest_test_virt_mem;
- vcpu_args->pages = (vcpus * vcpu_memory_bytes) /
- perf_test_args.guest_page_size;
- vcpu_gpa = guest_test_phys_mem;
- }
+ vcpu->vcpu_id = vcpu_id;
+ WRITE_ONCE(vcpu->running, false);
- vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
-
- pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n",
- vcpu_id, vcpu_gpa, vcpu_gpa +
- (vcpu_args->pages * perf_test_args.guest_page_size));
+ pthread_create(&vcpu->thread, NULL, vcpu_thread_main, vcpu);
}
+
+ for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+ while (!READ_ONCE(vcpu_threads[vcpu_id].running))
+ ;
+ }
+
+ WRITE_ONCE(all_vcpu_threads_running, true);
+}
+
+void perf_test_join_vcpu_threads(int vcpus)
+{
+ int vcpu_id;
+
+ for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++)
+ pthread_join(vcpu_threads[vcpu_id].thread, NULL);
}
diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c
index b724291..6d23878 100644
--- a/tools/testing/selftests/kvm/lib/test_util.c
+++ b/tools/testing/selftests/kvm/lib/test_util.c
@@ -283,6 +283,11 @@
}
}
+bool is_backing_src_hugetlb(uint32_t i)
+{
+ return !!(vm_mem_backing_src_alias(i)->flag & MAP_HUGETLB);
+}
+
static void print_available_backing_src_types(const char *prefix)
{
int i;
diff --git a/tools/testing/selftests/kvm/memslot_modification_stress_test.c b/tools/testing/selftests/kvm/memslot_modification_stress_test.c
index 4cfcafe..1410d0a 100644
--- a/tools/testing/selftests/kvm/memslot_modification_stress_test.c
+++ b/tools/testing/selftests/kvm/memslot_modification_stress_test.c
@@ -36,11 +36,9 @@
static bool run_vcpus = true;
-static void *vcpu_worker(void *data)
+static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args)
{
int ret;
- struct perf_test_vcpu_args *vcpu_args =
- (struct perf_test_vcpu_args *)data;
int vcpu_id = vcpu_args->vcpu_id;
struct kvm_vm *vm = perf_test_args.vm;
struct kvm_run *run;
@@ -59,8 +57,6 @@
"Invalid guest sync status: exit_reason=%s\n",
exit_reason_str(run->exit_reason));
}
-
- return NULL;
}
struct memslot_antagonist_args {
@@ -80,7 +76,7 @@
* Add the dummy memslot just below the perf_test_util memslot, which is
* at the top of the guest physical address space.
*/
- gpa = guest_test_phys_mem - pages * vm_get_page_size(vm);
+ gpa = perf_test_args.gpa - pages * vm_get_page_size(vm);
for (i = 0; i < nr_modifications; i++) {
usleep(delay);
@@ -100,29 +96,15 @@
static void run_test(enum vm_guest_mode mode, void *arg)
{
struct test_params *p = arg;
- pthread_t *vcpu_threads;
struct kvm_vm *vm;
- int vcpu_id;
vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1,
- VM_MEM_SRC_ANONYMOUS);
-
- perf_test_args.wr_fract = 1;
-
- vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
- TEST_ASSERT(vcpu_threads, "Memory allocation failed");
-
- perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size,
- p->partition_vcpu_memory_access);
-
- /* Export the shared variables to the guest */
- sync_global_to_guest(vm, perf_test_args);
+ VM_MEM_SRC_ANONYMOUS,
+ p->partition_vcpu_memory_access);
pr_info("Finished creating vCPUs\n");
- for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++)
- pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker,
- &perf_test_args.vcpu_args[vcpu_id]);
+ perf_test_start_vcpu_threads(nr_vcpus, vcpu_worker);
pr_info("Started all vCPUs\n");
@@ -131,16 +113,10 @@
run_vcpus = false;
- /* Wait for the vcpu threads to quit */
- for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++)
- pthread_join(vcpu_threads[vcpu_id], NULL);
-
+ perf_test_join_vcpu_threads(nr_vcpus);
pr_info("All vCPU threads joined\n");
- ucall_uninit(vm);
- kvm_vm_free(vm);
-
- free(vcpu_threads);
+ perf_test_destroy_vm(vm);
}
static void help(char *name)
diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
index eda0d2a..a0699f0 100644
--- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
@@ -24,8 +24,12 @@
#define PVTIME_ADDR (SHINFO_REGION_GPA + PAGE_SIZE)
#define RUNSTATE_ADDR (SHINFO_REGION_GPA + PAGE_SIZE + 0x20)
+#define VCPU_INFO_ADDR (SHINFO_REGION_GPA + 0x40)
#define RUNSTATE_VADDR (SHINFO_REGION_GVA + PAGE_SIZE + 0x20)
+#define VCPU_INFO_VADDR (SHINFO_REGION_GVA + 0x40)
+
+#define EVTCHN_VECTOR 0x10
static struct kvm_vm *vm;
@@ -56,15 +60,44 @@
uint64_t time[4];
};
+struct arch_vcpu_info {
+ unsigned long cr2;
+ unsigned long pad; /* sizeof(vcpu_info_t) == 64 */
+};
+
+struct vcpu_info {
+ uint8_t evtchn_upcall_pending;
+ uint8_t evtchn_upcall_mask;
+ unsigned long evtchn_pending_sel;
+ struct arch_vcpu_info arch;
+ struct pvclock_vcpu_time_info time;
+}; /* 64 bytes (x86) */
+
#define RUNSTATE_running 0
#define RUNSTATE_runnable 1
#define RUNSTATE_blocked 2
#define RUNSTATE_offline 3
+static void evtchn_handler(struct ex_regs *regs)
+{
+ struct vcpu_info *vi = (void *)VCPU_INFO_VADDR;
+ vi->evtchn_upcall_pending = 0;
+
+ GUEST_SYNC(0x20);
+}
+
static void guest_code(void)
{
struct vcpu_runstate_info *rs = (void *)RUNSTATE_VADDR;
+ __asm__ __volatile__(
+ "sti\n"
+ "nop\n"
+ );
+
+ /* Trigger an interrupt injection */
+ GUEST_SYNC(0);
+
/* Test having the host set runstates manually */
GUEST_SYNC(RUNSTATE_runnable);
GUEST_ASSERT(rs->time[RUNSTATE_runnable] != 0);
@@ -153,7 +186,7 @@
struct kvm_xen_vcpu_attr vi = {
.type = KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO,
- .u.gpa = SHINFO_REGION_GPA + 0x40,
+ .u.gpa = VCPU_INFO_ADDR,
};
vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &vi);
@@ -163,6 +196,16 @@
};
vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &pvclock);
+ struct kvm_xen_hvm_attr vec = {
+ .type = KVM_XEN_ATTR_TYPE_UPCALL_VECTOR,
+ .u.vector = EVTCHN_VECTOR,
+ };
+ vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &vec);
+
+ vm_init_descriptor_tables(vm);
+ vcpu_init_descriptor_tables(vm, VCPU_ID);
+ vm_install_exception_handler(vm, EVTCHN_VECTOR, evtchn_handler);
+
if (do_runstate_tests) {
struct kvm_xen_vcpu_attr st = {
.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR,
@@ -171,9 +214,14 @@
vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &st);
}
+ struct vcpu_info *vinfo = addr_gpa2hva(vm, VCPU_INFO_VADDR);
+ vinfo->evtchn_upcall_pending = 0;
+
struct vcpu_runstate_info *rs = addr_gpa2hva(vm, RUNSTATE_ADDR);
rs->state = 0x5a;
+ bool evtchn_irq_expected = false;
+
for (;;) {
volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID);
struct ucall uc;
@@ -193,16 +241,21 @@
struct kvm_xen_vcpu_attr rst;
long rundelay;
- /* If no runstate support, bail out early */
- if (!do_runstate_tests)
- goto done;
-
- TEST_ASSERT(rs->state_entry_time == rs->time[0] +
- rs->time[1] + rs->time[2] + rs->time[3],
- "runstate times don't add up");
+ if (do_runstate_tests)
+ TEST_ASSERT(rs->state_entry_time == rs->time[0] +
+ rs->time[1] + rs->time[2] + rs->time[3],
+ "runstate times don't add up");
switch (uc.args[1]) {
- case RUNSTATE_running...RUNSTATE_offline:
+ case 0:
+ evtchn_irq_expected = true;
+ vinfo->evtchn_upcall_pending = 1;
+ break;
+
+ case RUNSTATE_runnable...RUNSTATE_offline:
+ TEST_ASSERT(!evtchn_irq_expected, "Event channel IRQ not seen");
+ if (!do_runstate_tests)
+ goto done;
rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT;
rst.u.runstate.state = uc.args[1];
vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &rst);
@@ -236,6 +289,10 @@
sched_yield();
} while (get_run_delay() < rundelay);
break;
+ case 0x20:
+ TEST_ASSERT(evtchn_irq_expected, "Unexpected event channel IRQ");
+ evtchn_irq_expected = false;
+ break;
}
break;
}
diff --git a/tools/testing/selftests/net/forwarding/config b/tools/testing/selftests/net/forwarding/config
index a4bd1b0..697994a 100644
--- a/tools/testing/selftests/net/forwarding/config
+++ b/tools/testing/selftests/net/forwarding/config
@@ -6,6 +6,7 @@
CONFIG_NET_VRF=m
CONFIG_BPF_SYSCALL=y
CONFIG_CGROUP_BPF=y
+CONFIG_NET_ACT_CT=m
CONFIG_NET_ACT_MIRRED=m
CONFIG_NET_ACT_MPLS=m
CONFIG_NET_ACT_VLAN=m
diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh
index d9eca22..de19eb6 100755
--- a/tools/testing/selftests/net/forwarding/tc_actions.sh
+++ b/tools/testing/selftests/net/forwarding/tc_actions.sh
@@ -3,7 +3,7 @@
ALL_TESTS="gact_drop_and_ok_test mirred_egress_redirect_test \
mirred_egress_mirror_test matchall_mirred_egress_mirror_test \
- gact_trap_test"
+ gact_trap_test mirred_egress_to_ingress_test"
NUM_NETIFS=4
source tc_common.sh
source lib.sh
@@ -13,10 +13,12 @@
h1_create()
{
simple_if_init $h1 192.0.2.1/24
+ tc qdisc add dev $h1 clsact
}
h1_destroy()
{
+ tc qdisc del dev $h1 clsact
simple_if_fini $h1 192.0.2.1/24
}
@@ -153,6 +155,49 @@
log_test "trap ($tcflags)"
}
+mirred_egress_to_ingress_test()
+{
+ RET=0
+
+ tc filter add dev $h1 protocol ip pref 100 handle 100 egress flower \
+ ip_proto icmp src_ip 192.0.2.1 dst_ip 192.0.2.2 type 8 action \
+ ct commit nat src addr 192.0.2.2 pipe \
+ ct clear pipe \
+ ct commit nat dst addr 192.0.2.1 pipe \
+ mirred ingress redirect dev $h1
+
+ tc filter add dev $swp1 protocol ip pref 11 handle 111 ingress flower \
+ ip_proto icmp src_ip 192.0.2.1 dst_ip 192.0.2.2 type 8 action drop
+ tc filter add dev $swp1 protocol ip pref 12 handle 112 ingress flower \
+ ip_proto icmp src_ip 192.0.2.1 dst_ip 192.0.2.2 type 0 action pass
+
+ $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+ -t icmp "ping,id=42,seq=10" -q
+
+ tc_check_packets "dev $h1 egress" 100 1
+ check_err $? "didn't mirror first packet"
+
+ tc_check_packets "dev $swp1 ingress" 111 1
+ check_fail $? "didn't redirect first packet"
+ tc_check_packets "dev $swp1 ingress" 112 1
+ check_err $? "didn't receive reply to first packet"
+
+ ping 192.0.2.2 -I$h1 -c1 -w1 -q 1>/dev/null 2>&1
+
+ tc_check_packets "dev $h1 egress" 100 2
+ check_err $? "didn't mirror second packet"
+ tc_check_packets "dev $swp1 ingress" 111 1
+ check_fail $? "didn't redirect second packet"
+ tc_check_packets "dev $swp1 ingress" 112 2
+ check_err $? "didn't receive reply to second packet"
+
+ tc filter del dev $h1 egress protocol ip pref 100 handle 100 flower
+ tc filter del dev $swp1 ingress protocol ip pref 11 handle 111 flower
+ tc filter del dev $swp1 ingress protocol ip pref 12 handle 112 flower
+
+ log_test "mirred_egress_to_ingress ($tcflags)"
+}
+
setup_prepare()
{
h1=${NETIFS[p1]}
diff --git a/tools/testing/selftests/net/gre_gso.sh b/tools/testing/selftests/net/gre_gso.sh
index fdeb44d..3224651 100755
--- a/tools/testing/selftests/net/gre_gso.sh
+++ b/tools/testing/selftests/net/gre_gso.sh
@@ -118,16 +118,18 @@
local addr=$2
local proto=$3
- $NS_EXEC nc $proto -kl $port >/dev/null &
+ [ "$proto" == 6 ] && addr="[$addr]"
+
+ $NS_EXEC socat - tcp${proto}-listen:$port,reuseaddr,fork >/dev/null &
PID=$!
while ! $NS_EXEC ss -ltn | grep -q $port; do ((i++)); sleep 0.01; done
- cat $TMPFILE | timeout 1 nc $proto -N $addr $port
+ cat $TMPFILE | timeout 1 socat -u STDIN TCP:$addr:$port
log_test $? 0 "$name - copy file w/ TSO"
ethtool -K veth0 tso off
- cat $TMPFILE | timeout 1 nc $proto -N $addr $port
+ cat $TMPFILE | timeout 1 socat -u STDIN TCP:$addr:$port
log_test $? 0 "$name - copy file w/ GSO"
ethtool -K veth0 tso on
@@ -155,8 +157,8 @@
sleep 2
- gre_gst_test_checks GREv6/v4 172.16.2.2
- gre_gst_test_checks GREv6/v6 2001:db8:1::2 -6
+ gre_gst_test_checks GREv6/v4 172.16.2.2 4
+ gre_gst_test_checks GREv6/v6 2001:db8:1::2 6
cleanup
}
@@ -212,8 +214,8 @@
exit $ksft_skip
fi
-if [ ! -x "$(command -v nc)" ]; then
- echo "SKIP: Could not run test without nc tool"
+if [ ! -x "$(command -v socat)" ]; then
+ echo "SKIP: Could not run test without socat tool"
exit $ksft_skip
fi
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index d317245..9646bb9 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2548,72 +2548,36 @@
}
EXPORT_SYMBOL_GPL(gfn_to_page);
-void kvm_release_pfn(kvm_pfn_t pfn, bool dirty, struct gfn_to_pfn_cache *cache)
+void kvm_release_pfn(kvm_pfn_t pfn, bool dirty)
{
if (pfn == 0)
return;
- if (cache)
- cache->pfn = cache->gfn = 0;
-
if (dirty)
kvm_release_pfn_dirty(pfn);
else
kvm_release_pfn_clean(pfn);
}
-static void kvm_cache_gfn_to_pfn(struct kvm_memory_slot *slot, gfn_t gfn,
- struct gfn_to_pfn_cache *cache, u64 gen)
-{
- kvm_release_pfn(cache->pfn, cache->dirty, cache);
-
- cache->pfn = gfn_to_pfn_memslot(slot, gfn);
- cache->gfn = gfn;
- cache->dirty = false;
- cache->generation = gen;
-}
-
-static int __kvm_map_gfn(struct kvm_memslots *slots, gfn_t gfn,
- struct kvm_host_map *map,
- struct gfn_to_pfn_cache *cache,
- bool atomic)
+int kvm_vcpu_map(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map)
{
kvm_pfn_t pfn;
void *hva = NULL;
struct page *page = KVM_UNMAPPED_PAGE;
- struct kvm_memory_slot *slot = __gfn_to_memslot(slots, gfn);
- u64 gen = slots->generation;
if (!map)
return -EINVAL;
- if (cache) {
- if (!cache->pfn || cache->gfn != gfn ||
- cache->generation != gen) {
- if (atomic)
- return -EAGAIN;
- kvm_cache_gfn_to_pfn(slot, gfn, cache, gen);
- }
- pfn = cache->pfn;
- } else {
- if (atomic)
- return -EAGAIN;
- pfn = gfn_to_pfn_memslot(slot, gfn);
- }
+ pfn = gfn_to_pfn(vcpu->kvm, gfn);
if (is_error_noslot_pfn(pfn))
return -EINVAL;
if (pfn_valid(pfn)) {
page = pfn_to_page(pfn);
- if (atomic)
- hva = kmap_atomic(page);
- else
- hva = kmap(page);
+ hva = kmap(page);
#ifdef CONFIG_HAS_IOMEM
- } else if (!atomic) {
- hva = memremap(pfn_to_hpa(pfn), PAGE_SIZE, MEMREMAP_WB);
} else {
- return -EINVAL;
+ hva = memremap(pfn_to_hpa(pfn), PAGE_SIZE, MEMREMAP_WB);
#endif
}
@@ -2627,27 +2591,9 @@
return 0;
}
-
-int kvm_map_gfn(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map,
- struct gfn_to_pfn_cache *cache, bool atomic)
-{
- return __kvm_map_gfn(kvm_memslots(vcpu->kvm), gfn, map,
- cache, atomic);
-}
-EXPORT_SYMBOL_GPL(kvm_map_gfn);
-
-int kvm_vcpu_map(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map)
-{
- return __kvm_map_gfn(kvm_vcpu_memslots(vcpu), gfn, map,
- NULL, false);
-}
EXPORT_SYMBOL_GPL(kvm_vcpu_map);
-static void __kvm_unmap_gfn(struct kvm *kvm,
- struct kvm_memory_slot *memslot,
- struct kvm_host_map *map,
- struct gfn_to_pfn_cache *cache,
- bool dirty, bool atomic)
+void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty)
{
if (!map)
return;
@@ -2655,45 +2601,21 @@
if (!map->hva)
return;
- if (map->page != KVM_UNMAPPED_PAGE) {
- if (atomic)
- kunmap_atomic(map->hva);
- else
- kunmap(map->page);
- }
+ if (map->page != KVM_UNMAPPED_PAGE)
+ kunmap(map->page);
#ifdef CONFIG_HAS_IOMEM
- else if (!atomic)
- memunmap(map->hva);
else
- WARN_ONCE(1, "Unexpected unmapping in atomic context");
+ memunmap(map->hva);
#endif
if (dirty)
- mark_page_dirty_in_slot(kvm, memslot, map->gfn);
+ kvm_vcpu_mark_page_dirty(vcpu, map->gfn);
- if (cache)
- cache->dirty |= dirty;
- else
- kvm_release_pfn(map->pfn, dirty, NULL);
+ kvm_release_pfn(map->pfn, dirty);
map->hva = NULL;
map->page = NULL;
}
-
-int kvm_unmap_gfn(struct kvm_vcpu *vcpu, struct kvm_host_map *map,
- struct gfn_to_pfn_cache *cache, bool dirty, bool atomic)
-{
- __kvm_unmap_gfn(vcpu->kvm, gfn_to_memslot(vcpu->kvm, map->gfn), map,
- cache, dirty, atomic);
- return 0;
-}
-EXPORT_SYMBOL_GPL(kvm_unmap_gfn);
-
-void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty)
-{
- __kvm_unmap_gfn(vcpu->kvm, kvm_vcpu_gfn_to_memslot(vcpu, map->gfn),
- map, NULL, dirty, false);
-}
EXPORT_SYMBOL_GPL(kvm_vcpu_unmap);
struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn)
