diff options
1166 files changed, 13967 insertions, 6412 deletions
@@ -82,7 +82,10 @@ Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@gmail.com> Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@imgtec.com> Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@mips.com> <dev.kurt@vandijck-laurijssen.be> <kurt.van.dijck@eia.be> -Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> +Dmitry Baryshkov <dbaryshkov@gmail.com> +Dmitry Baryshkov <dbaryshkov@gmail.com> <[dbaryshkov@gmail.com]> +Dmitry Baryshkov <dbaryshkov@gmail.com> <dmitry_baryshkov@mentor.com> +Dmitry Baryshkov <dbaryshkov@gmail.com> <dmitry_eremin@mentor.com> Dmitry Safonov <0x7f454c46@gmail.com> <dima@arista.com> Dmitry Safonov <0x7f454c46@gmail.com> <d.safonov@partner.samsung.com> Dmitry Safonov <0x7f454c46@gmail.com> <dsafonov@virtuozzo.com> @@ -98,7 +98,7 @@ N: Erik Andersen E: andersen@codepoet.org W: https://www.codepoet.org/ P: 1024D/30D39057 1BC4 2742 E885 E4DE 9301 0C82 5F9B 643E 30D3 9057 -D: Maintainer of ide-cd and Uniform CD-ROM driver, +D: Maintainer of ide-cd and Uniform CD-ROM driver, D: ATAPI CD-Changer support, Major 2.1.x CD-ROM update. S: 352 North 525 East S: Springville, Utah 84663 @@ -263,7 +263,7 @@ N: Paul Barton-Davis E: pbd@op.net D: Driver for WaveFront soundcards (Turtle Beach Maui, Tropez, Tropez+) D: Various bugfixes and changes to sound drivers -S: USA +S: USA N: Carlos Henrique Bauer E: chbauer@acm.org @@ -849,6 +849,12 @@ D: trivial hack to add variable address length routing to Rose. D: AX25-HOWTO, HAM-HOWTO, IPX-HOWTO, NET-2-HOWTO D: ax25-utils maintainer. +N: Kamil Debski +E: kamil@wypas.org +D: Samsung S5P 2D graphics acceleration and Multi Format Codec drivers +D: Samsung USB2 phy drivers +D: PWM fan driver + N: Helge Deller E: deller@gmx.de W: http://www.parisc-linux.org/ @@ -1199,7 +1205,7 @@ N: Daniel J. Frasnelli E: dfrasnel@alphalinux.org W: http://www.alphalinux.org/ P: 1024/3EF87611 B9 F1 44 50 D3 E8 C2 80 DA E5 55 AA 56 7C 42 DA -D: DEC Alpha hacker +D: DEC Alpha hacker D: Miscellaneous bug squisher N: Jim Freeman @@ -1299,7 +1305,7 @@ S: P.O. Box 76, Epping S: New South Wales, 2121 S: Australia -N: Carlos E. Gorges +N: Carlos E. Gorges E: carlos@techlinux.com.br D: fix smp support on cmpci driver P: 2048G/EA3C4B19 FF31 33A6 0362 4915 B7EB E541 17D0 0379 EA3C 4B19 @@ -1340,7 +1346,7 @@ E: wgreathouse@smva.com E: wgreathouse@myfavoritei.com D: Current Belkin USB Serial Adapter F5U103 hacker D: Kernel hacker, embedded systems -S: 7802 Fitzwater Road +S: 7802 Fitzwater Road S: Brecksville, OH 44141-1334 S: USA @@ -1381,7 +1387,7 @@ N: Grant Guenther E: grant@torque.net W: http://www.torque.net/linux-pp.html D: original author of ppa driver for parallel port ZIP drive -D: original architect of the parallel-port sharing scheme +D: original architect of the parallel-port sharing scheme D: PARIDE subsystem: drivers for parallel port IDE & ATAPI devices S: 44 St. Joseph Street, Suite 506 S: Toronto, Ontario, M4Y 2W4 @@ -1523,7 +1529,7 @@ N: Benjamin Herrenschmidt E: benh@kernel.crashing.org D: Various parts of PPC/PPC64 & PowerMac S: 312/107 Canberra Avenue -S: Griffith, ACT 2603 +S: Griffith, ACT 2603 S: Australia N: Andreas Herrmann @@ -1825,7 +1831,7 @@ S: Hungary N: Bernhard Kaindl E: bkaindl@netway.at E: edv@bartelt.via.at -D: Author of a menu based configuration tool, kmenu, which +D: Author of a menu based configuration tool, kmenu, which D: is the predecessor of 'make menuconfig' and 'make xconfig'. D: digiboard driver update(modularisation work and 2.1.x upd) S: Tallak 95 @@ -2016,7 +2022,7 @@ W: http://www.xos.nl/ D: IP transparent proxy support S: X/OS Experts in Open Systems BV S: Kruislaan 419 -S: 1098 VA Amsterdam +S: 1098 VA Amsterdam S: The Netherlands N: Goran Koruga @@ -2088,7 +2094,7 @@ S: Germany N: Andrzej M. Krzysztofowicz E: ankry@mif.pg.gda.pl -D: Some 8-bit XT disk driver and devfs hacking +D: Some 8-bit XT disk driver and devfs hacking D: Aladdin 1533/1543(C) chipset IDE D: PIIX chipset IDE S: ul. Matemblewska 1B/10 @@ -2463,7 +2469,7 @@ E: mge@EZ-Darmstadt.Telekom.de D: Logical Volume Manager S: Bartningstr. 12 S: 64289 Darmstadt -S: Germany +S: Germany N: Mark W. McClelland E: mmcclell@bigfoot.com @@ -2547,7 +2553,7 @@ E: meskes@debian.org P: 1024/04B6E8F5 6C 77 33 CA CC D6 22 03 AB AB 15 A3 AE AD 39 7D D: Kernel hacker. PostgreSQL hacker. Software watchdog daemon. D: Maintainer of several Debian packages -S: Th.-Heuss-Str. 61 +S: Th.-Heuss-Str. 61 S: D-41812 Erkelenz S: Germany @@ -2785,7 +2791,7 @@ E: neuffer@goofy.zdv.uni-mainz.de W: http://www.i-Connect.Net/~mike/ D: Developer and maintainer of the EATA-DMA SCSI driver D: Co-developer EATA-PIO SCSI driver -D: /proc/scsi and assorted other snippets +D: /proc/scsi and assorted other snippets S: Zum Schiersteiner Grund 2 S: 55127 Mainz S: Germany @@ -2852,6 +2858,10 @@ D: IPX development and support N: Venkatesh Pallipadi (Venki) D: x86/HPET +N: Kyungmin Park +E: kyungmin.park@samsung.com +D: Samsung S5Pv210 and Exynos4210 mobile platforms + N: David Parsons E: orc@pell.chi.il.us D: improved memory detection code. @@ -3019,7 +3029,7 @@ D: Embedded PowerPC 4xx/6xx/7xx/74xx support S: Chandler, Arizona 85249 S: USA -N: Frederic Potter +N: Frederic Potter E: fpotter@cirpack.com D: Some PCI kernel support @@ -3452,21 +3462,21 @@ S: Klosterweg 28 / i309 S: 76131 Karlsruhe S: Germany -N: James Simmons +N: James Simmons E: jsimmons@infradead.org -E: jsimmons@users.sf.net +E: jsimmons@users.sf.net D: Frame buffer device maintainer D: input layer development D: tty/console layer -D: various mipsel devices -S: 115 Carmel Avenue +D: various mipsel devices +S: 115 Carmel Avenue S: El Cerrito CA 94530 -S: USA +S: USA N: Jaspreet Singh E: jaspreet@sangoma.com W: www.sangoma.com -D: WANPIPE drivers & API Support for Sangoma S508/FT1 cards +D: WANPIPE drivers & API Support for Sangoma S508/FT1 cards S: Sangoma Technologies Inc., S: 1001 Denison Street S: Suite 101 @@ -3490,7 +3500,7 @@ N: Craig Small E: csmall@triode.apana.org.au E: vk2xlz@gonzo.vk2xlz.ampr.org (packet radio) D: Gracilis PackeTwin device driver -D: RSPF daemon +D: RSPF daemon S: 10 Stockalls Place S: Minto, NSW, 2566 S: Australia @@ -3700,7 +3710,7 @@ N: Tsu-Sheng Tsao E: tsusheng@scf.usc.edu D: IGMP(Internet Group Management Protocol) version 2 S: 2F 14 ALY 31 LN 166 SEC 1 SHIH-PEI RD -S: Taipei +S: Taipei S: Taiwan 112 S: Republic of China S: 24335 Delta Drive @@ -3861,7 +3871,7 @@ D: Produced the Slackware distribution, updated the SVGAlib D: patches for ghostscript, worked on color 'ls', etc. S: 301 15th Street S. S: Moorhead, Minnesota 56560 -S: USA +S: USA N: Jos Vos E: jos@xos.nl @@ -3869,7 +3879,7 @@ W: http://www.xos.nl/ D: Various IP firewall updates, ipfwadm S: X/OS Experts in Open Systems BV S: Kruislaan 419 -S: 1098 VA Amsterdam +S: 1098 VA Amsterdam S: The Netherlands N: Jeroen Vreeken @@ -4107,7 +4117,7 @@ S: People's Repulic of China N: Victor Yodaiken E: yodaiken@fsmlabs.com D: RTLinux (RealTime Linux) -S: POB 1822 +S: POB 1822 S: Socorro NM, 87801 S: USA @@ -4205,7 +4215,7 @@ D: EISA/sysfs subsystem S: France # Don't add your name here, unless you really _are_ after Marc -# alphabetically. Leonard used to be very proud of being the +# alphabetically. Leonard used to be very proud of being the # last entry, and he'll get positively pissed if he can't even # be second-to-last. (and this file really _is_ supposed to be # in alphabetic order) diff --git a/Documentation/ABI/stable/sysfs-driver-dma-ioatdma b/Documentation/ABI/stable/sysfs-driver-dma-ioatdma index 420c1d09e42f..3a4e2cd0ddcc 100644 --- a/Documentation/ABI/stable/sysfs-driver-dma-ioatdma +++ b/Documentation/ABI/stable/sysfs-driver-dma-ioatdma @@ -1,29 +1,29 @@ -What: sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/cap +What: /sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/cap Date: December 3, 2009 KernelVersion: 2.6.32 Contact: dmaengine@vger.kernel.org Description: Capabilities the DMA supports.Currently there are DMA_PQ, DMA_PQ_VAL, DMA_XOR,DMA_XOR_VAL,DMA_INTERRUPT. -What: sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/ring_active +What: /sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/ring_active Date: December 3, 2009 KernelVersion: 2.6.32 Contact: dmaengine@vger.kernel.org Description: The number of descriptors active in the ring. -What: sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/ring_size +What: /sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/ring_size Date: December 3, 2009 KernelVersion: 2.6.32 Contact: dmaengine@vger.kernel.org Description: Descriptor ring size, total number of descriptors available. -What: sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/version +What: /sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/version Date: December 3, 2009 KernelVersion: 2.6.32 Contact: dmaengine@vger.kernel.org Description: Version of ioatdma device. -What: sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/intr_coalesce +What: /sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/intr_coalesce Date: August 8, 2017 KernelVersion: 4.14 Contact: dmaengine@vger.kernel.org diff --git a/Documentation/ABI/testing/sysfs-bus-iio-timer-stm32 b/Documentation/ABI/testing/sysfs-bus-iio-timer-stm32 index a10a4de3e5fe..c4a4497c249a 100644 --- a/Documentation/ABI/testing/sysfs-bus-iio-timer-stm32 +++ b/Documentation/ABI/testing/sysfs-bus-iio-timer-stm32 @@ -109,30 +109,6 @@ Description: When counting down the counter start from preset value and fire event when reach 0. -What: /sys/bus/iio/devices/iio:deviceX/in_count_quadrature_mode_available -KernelVersion: 4.12 -Contact: benjamin.gaignard@st.com -Description: - Reading returns the list possible quadrature modes. - -What: /sys/bus/iio/devices/iio:deviceX/in_count0_quadrature_mode -KernelVersion: 4.12 -Contact: benjamin.gaignard@st.com -Description: - Configure the device counter quadrature modes: - - channel_A: - Encoder A input servers as the count input and B as - the UP/DOWN direction control input. - - channel_B: - Encoder B input serves as the count input and A as - the UP/DOWN direction control input. - - quadrature: - Encoder A and B inputs are mixed to get direction - and count with a scale of 0.25. - What: /sys/bus/iio/devices/iio:deviceX/in_count_enable_mode_available KernelVersion: 4.12 Contact: benjamin.gaignard@st.com diff --git a/Documentation/ABI/testing/sysfs-class-net b/Documentation/ABI/testing/sysfs-class-net index 7670012ae9b6..1f2002df5ba2 100644 --- a/Documentation/ABI/testing/sysfs-class-net +++ b/Documentation/ABI/testing/sysfs-class-net @@ -152,7 +152,7 @@ Description: When an interface is under test, it cannot be expected to pass packets as normal. -What: /sys/clas/net/<iface>/duplex +What: /sys/class/net/<iface>/duplex Date: October 2009 KernelVersion: 2.6.33 Contact: netdev@vger.kernel.org diff --git a/Documentation/Makefile b/Documentation/Makefile index 6a59a13d3c53..61a7310b49e0 100644 --- a/Documentation/Makefile +++ b/Documentation/Makefile @@ -26,6 +26,10 @@ BUILDDIR = $(obj)/output PDFLATEX = xelatex LATEXOPTS = -interaction=batchmode +ifeq ($(KBUILD_VERBOSE),0) +SPHINXOPTS += "-q" +endif + # User-friendly check for sphinx-build HAVE_SPHINX := $(shell if which $(SPHINXBUILD) >/dev/null 2>&1; then echo 1; else echo 0; fi) diff --git a/Documentation/admin-guide/LSM/SafeSetID.rst b/Documentation/admin-guide/LSM/SafeSetID.rst index 17996c9070e2..0ec34863c674 100644 --- a/Documentation/admin-guide/LSM/SafeSetID.rst +++ b/Documentation/admin-guide/LSM/SafeSetID.rst @@ -107,7 +107,7 @@ for a UID/GID will prevent that UID/GID from obtaining auxiliary setid privileges, such as allowing a user to set up user namespace UID/GID mappings. Note on GID policies and setgroups() -================== +==================================== In v5.9 we are adding support for limiting CAP_SETGID privileges as was done previously for CAP_SETUID. However, for compatibility with common sandboxing related code conventions in userspace, we currently allow arbitrary diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 526d65d8573a..44fde25bb221 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2858,6 +2858,8 @@ mds=off [X86] tsx_async_abort=off [X86] kvm.nx_huge_pages=off [X86] + no_entry_flush [PPC] + no_uaccess_flush [PPC] Exceptions: This does not have any effect on @@ -3186,6 +3188,8 @@ noefi Disable EFI runtime services support. + no_entry_flush [PPC] Don't flush the L1-D cache when entering the kernel. + noexec [IA-64] noexec [X86] @@ -3235,6 +3239,9 @@ nospec_store_bypass_disable [HW] Disable all mitigations for the Speculative Store Bypass vulnerability + no_uaccess_flush + [PPC] Don't flush the L1-D cache after accessing user data. + noxsave [BUGS=X86] Disables x86 extended register state save and restore using xsave. The kernel will fallback to enabling legacy floating-point and sse state. diff --git a/Documentation/admin-guide/pm/cpuidle.rst b/Documentation/admin-guide/pm/cpuidle.rst index 37940a0584ec..10fde58d0869 100644 --- a/Documentation/admin-guide/pm/cpuidle.rst +++ b/Documentation/admin-guide/pm/cpuidle.rst @@ -478,7 +478,7 @@ order to ask the hardware to enter that state. Also, for each statistics of the given idle state. That information is exposed by the kernel via ``sysfs``. -For each CPU in the system, there is a :file:`/sys/devices/system/cpu<N>/cpuidle/` +For each CPU in the system, there is a :file:`/sys/devices/system/cpu/cpu<N>/cpuidle/` directory in ``sysfs``, where the number ``<N>`` is assigned to the given CPU at the initialization time. That directory contains a set of subdirectories called :file:`state0`, :file:`state1` and so on, up to the number of idle state @@ -494,7 +494,7 @@ object corresponding to it, as follows: residency. ``below`` - Total number of times this idle state had been asked for, but cerainly + Total number of times this idle state had been asked for, but certainly a deeper idle state would have been a better match for the observed idle duration. diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst index 57fd6ce68fe0..f2ab8a5b6a4b 100644 --- a/Documentation/admin-guide/sysctl/net.rst +++ b/Documentation/admin-guide/sysctl/net.rst @@ -300,6 +300,7 @@ Note: 0: 0 1 2 3 4 5 6 7 RSS hash key: 84:50:f4:00:a8:15:d1:a7:e9:7f:1d:60:35:c7:47:25:42:97:74:ca:56:bb:b6:a1:d8:43:e3:c9:0c:fd:17:55:c2:3a:4d:69:ed:f1:42:89 + netdev_tstamp_prequeue ---------------------- diff --git a/Documentation/arm/sunxi.rst b/Documentation/arm/sunxi.rst index 62b533d0ba94..0c536ae1d7c2 100644 --- a/Documentation/arm/sunxi.rst +++ b/Documentation/arm/sunxi.rst @@ -148,3 +148,13 @@ SunXi family * User Manual http://dl.linux-sunxi.org/A64/Allwinner%20A64%20User%20Manual%20v1.0.pdf + + - Allwinner H6 + + * Datasheet + + https://linux-sunxi.org/images/5/5c/Allwinner_H6_V200_Datasheet_V1.1.pdf + + * User Manual + + https://linux-sunxi.org/images/4/46/Allwinner_H6_V200_User_Manual_V1.1.pdf diff --git a/Documentation/conf.py b/Documentation/conf.py index 1e44983853a2..ed2b43ec7754 100644 --- a/Documentation/conf.py +++ b/Documentation/conf.py @@ -51,7 +51,7 @@ if major >= 3: support for Sphinx v3.0 and above is brand new. Be prepared for possible issues in the generated output. ''') - if minor > 0 or patch >= 2: + if (major > 3) or (minor > 0 or patch >= 2): # Sphinx c function parser is more pedantic with regards to type # checking. Due to that, having macros at c:function cause problems. # Those needed to be scaped by using c_id_attributes[] array diff --git a/Documentation/dev-tools/kasan.rst b/Documentation/dev-tools/kasan.rst index c09c9ca2ff1c..2b68addaadcd 100644 --- a/Documentation/dev-tools/kasan.rst +++ b/Documentation/dev-tools/kasan.rst @@ -295,11 +295,13 @@ print the number of the test and the status of the test: pass:: ok 28 - kmalloc_double_kzfree + or, if kmalloc failed:: # kmalloc_large_oob_right: ASSERTION FAILED at lib/test_kasan.c:163 Expected ptr is not null, but is not ok 4 - kmalloc_large_oob_right + or, if a KASAN report was expected, but not found:: # kmalloc_double_kzfree: EXPECTATION FAILED at lib/test_kasan.c:629 diff --git a/Documentation/dev-tools/kunit/faq.rst b/Documentation/dev-tools/kunit/faq.rst index 1628862e7024..8d5029ad210a 100644 --- a/Documentation/dev-tools/kunit/faq.rst +++ b/Documentation/dev-tools/kunit/faq.rst @@ -90,7 +90,7 @@ things to try. re-run kunit_tool. 5. Try to run ``make ARCH=um defconfig`` before running ``kunit.py run``. This may help clean up any residual config items which could be causing problems. -6. Finally, try running KUnit outside UML. KUnit and KUnit tests can run be +6. Finally, try running KUnit outside UML. KUnit and KUnit tests can be built into any kernel, or can be built as a module and loaded at runtime. Doing so should allow you to determine if UML is causing the issue you're seeing. When tests are built-in, they will execute when the kernel boots, and diff --git a/Documentation/dev-tools/kunit/start.rst b/Documentation/dev-tools/kunit/start.rst index d23385e3e159..454f307813ea 100644 --- a/Documentation/dev-tools/kunit/start.rst +++ b/Documentation/dev-tools/kunit/start.rst @@ -197,7 +197,7 @@ Now add the following to ``drivers/misc/Kconfig``: config MISC_EXAMPLE_TEST bool "Test for my example" - depends on MISC_EXAMPLE && KUNIT + depends on MISC_EXAMPLE && KUNIT=y and the following to ``drivers/misc/Makefile``: diff --git a/Documentation/dev-tools/kunit/style.rst b/Documentation/dev-tools/kunit/style.rst index da1d6f0ed6bc..8dbcdc552606 100644 --- a/Documentation/dev-tools/kunit/style.rst +++ b/Documentation/dev-tools/kunit/style.rst @@ -175,17 +175,17 @@ An example Kconfig entry: .. code-block:: none - config FOO_KUNIT_TEST - tristate "KUnit test for foo" if !KUNIT_ALL_TESTS - depends on KUNIT - default KUNIT_ALL_TESTS - help - This builds unit tests for foo. + config FOO_KUNIT_TEST + tristate "KUnit test for foo" if !KUNIT_ALL_TESTS + depends on KUNIT + default KUNIT_ALL_TESTS + help + This builds unit tests for foo. - For more information on KUnit and unit tests in general, please refer - to the KUnit documentation in Documentation/dev-tools/kunit + For more information on KUnit and unit tests in general, please refer + to the KUnit documentation in Documentation/dev-tools/kunit/. - If unsure, say N + If unsure, say N. Test File and Module Names diff --git a/Documentation/dev-tools/kunit/usage.rst b/Documentation/dev-tools/kunit/usage.rst index 961d3ea3ca19..9c28c518e6a3 100644 --- a/Documentation/dev-tools/kunit/usage.rst +++ b/Documentation/dev-tools/kunit/usage.rst @@ -92,7 +92,7 @@ behavior of a function called ``add``; the first parameter is always of type the second parameter, in this case, is what the value is expected to be; the last value is what the value actually is. If ``add`` passes all of these expectations, the test case, ``add_test_basic`` will pass; if any one of these -expectations fail, the test case will fail. +expectations fails, the test case will fail. It is important to understand that a test case *fails* when any expectation is violated; however, the test will continue running, potentially trying other @@ -202,7 +202,7 @@ Example: kunit_test_suite(example_test_suite); In the above example the test suite, ``example_test_suite``, would run the test -cases ``example_test_foo``, ``example_test_bar``, and ``example_test_baz``, +cases ``example_test_foo``, ``example_test_bar``, and ``example_test_baz``; each would have ``example_test_init`` called immediately before it and would have ``example_test_exit`` called immediately after it. ``kunit_test_suite(example_test_suite)`` registers the test suite with the @@ -229,7 +229,7 @@ through some sort of indirection where a function is exposed as part of an API such that the definition of that function can be changed without affecting the rest of the code base. In the kernel this primarily comes from two constructs, classes, structs that contain function pointers that are provided by the -implementer, and architecture specific functions which have definitions selected +implementer, and architecture-specific functions which have definitions selected at compile time. Classes @@ -459,7 +459,7 @@ KUnit on non-UML architectures By default KUnit uses UML as a way to provide dependencies for code under test. Under most circumstances KUnit's usage of UML should be treated as an implementation detail of how KUnit works under the hood. Nevertheless, there -are instances where being able to run architecture specific code or test +are instances where being able to run architecture-specific code or test against real hardware is desirable. For these reasons KUnit supports running on other architectures. @@ -561,6 +561,11 @@ Once the kernel is built and installed, a simple ...will run the tests. +.. note:: + Note that you should make sure your test depends on ``KUNIT=y`` in Kconfig + if the test does not support module build. Otherwise, it will trigger + compile errors if ``CONFIG_KUNIT`` is ``m``. + Writing new tests for other architectures ----------------------------------------- @@ -594,7 +599,7 @@ writing normal KUnit tests. One special caveat is that you have to reset hardware state in between test cases; if this is not possible, you may only be able to run one test case per invocation. -.. TODO(brendanhiggins@google.com): Add an actual example of an architecture +.. TODO(brendanhiggins@google.com): Add an actual example of an architecture- dependent KUnit test. KUnit debugfs representation diff --git a/Documentation/devicetree/bindings/clock/hi6220-clock.txt b/Documentation/devicetree/bindings/clock/hi6220-clock.txt index ef3deb7b86ea..17ac4a3dd26a 100644 --- a/Documentation/devicetree/bindings/clock/hi6220-clock.txt +++ b/Documentation/devicetree/bindings/clock/hi6220-clock.txt @@ -4,7 +4,7 @@ Clock control registers reside in different Hi6220 system controllers, please refer the following document to know more about the binding rules for these system controllers: -Documentation/devicetree/bindings/arm/hisilicon/hisilicon.txt +Documentation/devicetree/bindings/arm/hisilicon/hisilicon.yaml Required Properties: diff --git a/Documentation/devicetree/bindings/clock/imx5-clock.yaml b/Documentation/devicetree/bindings/clock/imx5-clock.yaml index 4d9e7c73dce9..90775c2669b8 100644 --- a/Documentation/devicetree/bindings/clock/imx5-clock.yaml +++ b/Documentation/devicetree/bindings/clock/imx5-clock.yaml @@ -57,7 +57,7 @@ examples: }; can@53fc8000 { - compatible = "fsl,imx53-flexcan", "fsl,p1010-flexcan"; + compatible = "fsl,imx53-flexcan", "fsl,imx25-flexcan"; reg = <0x53fc8000 0x4000>; interrupts = <82>; clocks = <&clks IMX5_CLK_CAN1_IPG_GATE>, <&clks IMX5_CLK_CAN1_SERIAL_GATE>; diff --git a/Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.yaml b/Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.yaml index f6c3fcc4bdfd..b5af12011499 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.yaml @@ -32,6 +32,11 @@ description: | | | vint | bit | | 0 |.....|63| vintx | | +--------------+ +------------+ | | | + | Unmap | + | +--------------+ | + Unmapped events ---->| | umapidx |-------------------------> Globalevents + | +--------------+ | + | | +-----------------------------------------+ Configuration of these Intmap registers that maps global events to vint is @@ -70,6 +75,11 @@ properties: - description: | "limit" specifies the limit for translation + ti,unmapped-event-sources: + $ref: /schemas/types.yaml#definitions/phandle-array + description: + Array of phandles to DMA controllers where the unmapped events originate. + required: - compatible - reg diff --git a/Documentation/devicetree/bindings/net/can/can-controller.yaml b/Documentation/devicetree/bindings/net/can/can-controller.yaml new file mode 100644 index 000000000000..9cf2ae097156 --- /dev/null +++ b/Documentation/devicetree/bindings/net/can/can-controller.yaml @@ -0,0 +1,18 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/can/can-controller.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: CAN Controller Generic Binding + +maintainers: + - Marc Kleine-Budde <mkl@pengutronix.de> + +properties: + $nodename: + pattern: "^can(@.*)?$" + +additionalProperties: true + +... diff --git a/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml b/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml new file mode 100644 index 000000000000..13875eab2ed6 --- /dev/null +++ b/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml @@ -0,0 +1,139 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/can/fsl,flexcan.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: + Flexcan CAN controller on Freescale's ARM and PowerPC system-on-a-chip (SOC). + +maintainers: + - Marc Kleine-Budde <mkl@pengutronix.de> + +allOf: + - $ref: can-controller.yaml# + +properties: + compatible: + oneOf: + - enum: + - fsl,imx8qm-flexcan + - fsl,imx8mp-flexcan + - fsl,imx6q-flexcan + - fsl,imx28-flexcan + - fsl,imx25-flexcan + - fsl,p1010-flexcan + - fsl,vf610-flexcan + - fsl,ls1021ar2-flexcan + - fsl,lx2160ar1-flexcan + - items: + - enum: + - fsl,imx53-flexcan + - fsl,imx35-flexcan + - const: fsl,imx25-flexcan + - items: + - enum: + - fsl,imx7d-flexcan + - fsl,imx6ul-flexcan + - fsl,imx6sx-flexcan + - const: fsl,imx6q-flexcan + - items: + - enum: + - fsl,ls1028ar1-flexcan + - const: fsl,lx2160ar1-flexcan + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + clocks: + maxItems: 2 + + clock-names: + items: + - const: ipg + - const: per + + clock-frequency: + description: | + The oscillator frequency driving the flexcan device, filled in by the + boot loader. This property should only be used the used operating system + doesn't support the clocks and clock-names property. + + xceiver-supply: + description: Regulator that powers the CAN transceiver. + + big-endian: + $ref: /schemas/types.yaml#/definitions/flag + description: | + This means the registers of FlexCAN controller are big endian. This is + optional property.i.e. if this property is not present in device tree + node then controller is assumed to be little endian. If this property is + present then controller is assumed to be big endian. + + fsl,stop-mode: + description: | + Register bits of stop mode control. + + The format should be as follows: + <gpr req_gpr req_bit> + gpr is the phandle to general purpose register node. + req_gpr is the gpr register offset of CAN stop request. + req_bit is the bit offset of CAN stop request. + $ref: /schemas/types.yaml#/definitions/phandle-array + items: + items: + - description: The 'gpr' is the phandle to general purpose register node. + - description: The 'req_gpr' is the gpr register offset of CAN stop request. + maximum: 0xff + - description: The 'req_bit' is the bit offset of CAN stop request. + maximum: 0x1f + + fsl,clk-source: + description: | + Select the clock source to the CAN Protocol Engine (PE). It's SoC + implementation dependent. Refer to RM for detailed definition. If this + property is not set in device tree node then driver selects clock source 1 + by default. + 0: clock source 0 (oscillator clock) + 1: clock source 1 (peripheral clock) + $ref: /schemas/types.yaml#/definitions/uint32 + default: 1 + minimum: 0 + maximum: 1 + + wakeup-source: + $ref: /schemas/types.yaml#/definitions/flag + description: + Enable CAN remote wakeup. + +required: + - compatible + - reg + - interrupts + +additionalProperties: false + +examples: + - | + can@1c000 { + compatible = "fsl,p1010-flexcan"; + reg = <0x1c000 0x1000>; + interrupts = <48 0x2>; + interrupt-parent = <&mpic>; + clock-frequency = <200000000>; + fsl,clk-source = <0>; + }; + - | + #include <dt-bindings/interrupt-controller/irq.h> + + can@2090000 { + compatible = "fsl,imx6q-flexcan"; + reg = <0x02090000 0x4000>; + interrupts = <0 110 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clks 1>, <&clks 2>; + clock-names = "ipg", "per"; + fsl,stop-mode = <&gpr 0x34 28>; + }; diff --git a/Documentation/devicetree/bindings/net/can/fsl-flexcan.txt b/Documentation/devicetree/bindings/net/can/fsl-flexcan.txt deleted file mode 100644 index e10b6eb955e1..000000000000 --- a/Documentation/devicetree/bindings/net/can/fsl-flexcan.txt +++ /dev/null @@ -1,57 +0,0 @@ -Flexcan CAN controller on Freescale's ARM and PowerPC system-on-a-chip (SOC). - -Required properties: - -- compatible : Should be "fsl,<processor>-flexcan" - - where <processor> is imx8qm, imx6q, imx28, imx53, imx35, imx25, p1010, - vf610, ls1021ar2, lx2160ar1, ls1028ar1. - - The ls1028ar1 must be followed by lx2160ar1, e.g. - - "fsl,ls1028ar1-flexcan", "fsl,lx2160ar1-flexcan" - - An implementation should also claim any of the following compatibles - that it is fully backwards compatible with: - - - fsl,p1010-flexcan - -- reg : Offset and length of the register set for this device -- interrupts : Interrupt tuple for this device - -Optional properties: - -- clock-frequency : The oscillator frequency driving the flexcan device - -- xceiver-supply: Regulator that powers the CAN transceiver - -- big-endian: This means the registers of FlexCAN controller are big endian. - This is optional property.i.e. if this property is not present in - device tree node then controller is assumed to be little endian. - if this property is present then controller is assumed to be big - endian. - -- fsl,stop-mode: register bits of stop mode control, the format is - <&gpr req_gpr req_bit>. - gpr is the phandle to general purpose register node. - req_gpr is the gpr register offset of CAN stop request. - req_bit is the bit offset of CAN stop request. - -- fsl,clk-source: Select the clock source to the CAN Protocol Engine (PE). - It's SoC Implementation dependent. Refer to RM for detailed - definition. If this property is not set in device tree node - then driver selects clock source 1 by default. - 0: clock source 0 (oscillator clock) - 1: clock source 1 (peripheral clock) - -- wakeup-source: enable CAN remote wakeup - -Example: - - can@1c000 { - compatible = "fsl,p1010-flexcan"; - reg = <0x1c000 0x1000>; - interrupts = <48 0x2>; - interrupt-parent = <&mpic>; - clock-frequency = <200000000>; // filled in by bootloader - fsl,clk-source = <0>; // select clock source 0 for PE - }; diff --git a/Documentation/devicetree/bindings/sound/rt1015.txt b/Documentation/devicetree/bindings/sound/rt1015.txt index fcfd02d8d32f..e498966d436f 100644 --- a/Documentation/devicetree/bindings/sound/rt1015.txt +++ b/Documentation/devicetree/bindings/sound/rt1015.txt @@ -8,10 +8,16 @@ Required properties: - reg : The I2C address of the device. +Optional properties: + +- realtek,power-up-delay-ms + Set a delay time for flush work to be completed, + this value is adjustable depending on platform. Example: rt1015: codec@28 { compatible = "realtek,rt1015"; reg = <0x28>; + realtek,power-up-delay-ms = <50>; }; diff --git a/Documentation/filesystems/api-summary.rst b/Documentation/filesystems/api-summary.rst index bbb0c1c0e5cf..a94f17d9b836 100644 --- a/Documentation/filesystems/api-summary.rst +++ b/Documentation/filesystems/api-summary.rst @@ -86,9 +86,6 @@ Other Functions .. kernel-doc:: fs/dax.c :export: -.. kernel-doc:: fs/direct-io.c - :export: - .. kernel-doc:: fs/libfs.c :export: diff --git a/Documentation/filesystems/ext4/journal.rst b/Documentation/filesystems/ext4/journal.rst index 805a1e9ea3a5..849d5b119eb8 100644 --- a/Documentation/filesystems/ext4/journal.rst +++ b/Documentation/filesystems/ext4/journal.rst @@ -256,6 +256,10 @@ which is 1024 bytes long: - s\_padding2 - * - 0x54 + - \_\_be32 + - s\_num\_fc\_blocks + - Number of fast commit blocks in the journal. + * - 0x58 - \_\_u32 - s\_padding[42] - @@ -310,6 +314,8 @@ The journal incompat features are any combination of the following: - This journal uses v3 of the checksum on-disk format. This is the same as v2, but the journal block tag size is fixed regardless of the size of block numbers. (JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3) + * - 0x20 + - Journal has fast commit blocks. (JBD2\_FEATURE\_INCOMPAT\_FAST\_COMMIT) .. _jbd2_checksum_type: diff --git a/Documentation/filesystems/ext4/super.rst b/Documentation/filesystems/ext4/super.rst index 93e55d7c1d40..2eb1ab20498d 100644 --- a/Documentation/filesystems/ext4/super.rst +++ b/Documentation/filesystems/ext4/super.rst @@ -596,6 +596,13 @@ following: - Sparse Super Block, v2. If this flag is set, the SB field s\_backup\_bgs points to the two block groups that contain backup superblocks (COMPAT\_SPARSE\_SUPER2). + * - 0x400 + - Fast commits supported. Although fast commits blocks are + backward incompatible, fast commit blocks are not always + present in the journal. If fast commit blocks are present in + the journal, JBD2 incompat feature + (JBD2\_FEATURE\_INCOMPAT\_FAST\_COMMIT) gets + set (COMPAT\_FAST\_COMMIT). .. _super_incompat: diff --git a/Documentation/filesystems/journalling.rst b/Documentation/filesystems/journalling.rst index 5a5f70b4063e..e18f90ffc6fd 100644 --- a/Documentation/filesystems/journalling.rst +++ b/Documentation/filesystems/journalling.rst @@ -136,10 +136,8 @@ Fast commits ~~~~~~~~~~~~ JBD2 to also allows you to perform file-system specific delta commits known as -fast commits. In order to use fast commits, you first need to call -:c:func:`jbd2_fc_init` and tell how many blocks at the end of journal -area should be reserved for fast commits. Along with that, you will also need -to set following callbacks that perform correspodning work: +fast commits. In order to use fast commits, you will need to set following +callbacks that perform correspodning work: `journal->j_fc_cleanup_cb`: Cleanup function called after every full commit and fast commit. diff --git a/Documentation/firmware-guide/acpi/acpi-lid.rst b/Documentation/firmware-guide/acpi/acpi-lid.rst index 874ce0ed340d..71b9af13a048 100644 --- a/Documentation/firmware-guide/acpi/acpi-lid.rst +++ b/Documentation/firmware-guide/acpi/acpi-lid.rst @@ -19,9 +19,9 @@ report the "current" state of the lid as either "opened" or "closed". For most platforms, both the _LID method and the lid notifications are reliable. However, there are exceptions. In order to work with these -exceptional buggy platforms, special restrictions and expections should be +exceptional buggy platforms, special restrictions and exceptions should be taken into account. This document describes the restrictions and the -expections of the Linux ACPI lid device driver. +exceptions of the Linux ACPI lid device driver. Restrictions of the returning value of the _LID control method @@ -46,7 +46,7 @@ state is changed to "closed". The "closed" notification is normally used to trigger some system power saving operations on Windows. Since it is fully tested, it is reliable from all AML tables. -Expections for the userspace users of the ACPI lid device driver +Exceptions for the userspace users of the ACPI lid device driver ================================================================ The ACPI button driver exports the lid state to the userspace via the @@ -100,7 +100,7 @@ use the following kernel parameter: C. button.lid_init_state=ignore: When this option is specified, the ACPI button driver never reports the initial lid state and there is a compensation mechanism implemented to - ensure that the reliable "closed" notifications can always be delievered + ensure that the reliable "closed" notifications can always be delivered to the userspace by always pairing "closed" input events with complement "opened" input events. But there is still no guarantee that the "opened" notifications can be delivered to the userspace when the lid is actually diff --git a/Documentation/firmware-guide/acpi/gpio-properties.rst b/Documentation/firmware-guide/acpi/gpio-properties.rst index bb6d74f23ee0..59aad6138b6e 100644 --- a/Documentation/firmware-guide/acpi/gpio-properties.rst +++ b/Documentation/firmware-guide/acpi/gpio-properties.rst @@ -20,9 +20,9 @@ index, like the ASL example below shows:: Name (_CRS, ResourceTemplate () { - GpioIo (Exclusive, PullUp, 0, 0, IoRestrictionInputOnly, + GpioIo (Exclusive, PullUp, 0, 0, IoRestrictionOutputOnly, "\\_SB.GPO0", 0, ResourceConsumer) {15} - GpioIo (Exclusive, PullUp, 0, 0, IoRestrictionInputOnly, + GpioIo (Exclusive, PullUp, 0, 0, IoRestrictionOutputOnly, "\\_SB.GPO0", 0, ResourceConsumer) {27, 31} }) @@ -49,15 +49,41 @@ index pin Pin in the GpioIo()/GpioInt() resource. Typically this is zero. active_low - If 1 the GPIO is marked as active_low. + If 1, the GPIO is marked as active_low. Since ACPI GpioIo() resource does not have a field saying whether it is active low or high, the "active_low" argument can be used here. Setting it to 1 marks the GPIO as active low. +Note, active_low in _DSD does not make sense for GpioInt() resource and +must be 0. GpioInt() resource has its own means of defining it. + In our Bluetooth example the "reset-gpios" refers to the second GpioIo() resource, second pin in that resource with the GPIO number of 31. +The GpioIo() resource unfortunately doesn't explicitly provide an initial +state of the output pin which driver should use during its initialization. + +Linux tries to use common sense here and derives the state from the bias +and polarity settings. The table below shows the expectations: + +========= ============= ============== +Pull Bias Polarity Requested... +========= ============= ============== +Implicit x AS IS (assumed firmware configured for us) +Explicit x (no _DSD) as Pull Bias (Up == High, Down == Low), + assuming non-active (Polarity = !Pull Bias) +Down Low as low, assuming active +Down High as low, assuming non-active +Up Low as high, assuming non-active +Up High as high, assuming active +========= ============= ============== + +That said, for our above example the both GPIOs, since the bias setting +is explicit and _DSD is present, will be treated as active with a high +polarity and Linux will configure the pins in this state until a driver +reprograms them differently. + It is possible to leave holes in the array of GPIOs. This is useful in cases like with SPI host controllers where some chip selects may be implemented as GPIOs and some as native signals. For example a SPI host @@ -112,8 +138,8 @@ Example:: Package () { "gpio-line-names", Package () { - "SPI0_CS_N", "EXP2_INT", "MUX6_IO", "UART0_RXD", "MUX7_IO", - "LVL_C_A1", "MUX0_IO", "SPI1_MISO" + "SPI0_CS_N", "EXP2_INT", "MUX6_IO", "UART0_RXD", + "MUX7_IO", "LVL_C_A1", "MUX0_IO", "SPI1_MISO", } } @@ -137,7 +163,7 @@ to the GPIO lines it is going to use and provide the GPIO subsystem with a mapping between those names and the ACPI GPIO resources corresponding to them. To do that, the driver needs to define a mapping table as a NULL-terminated -array of struct acpi_gpio_mapping objects that each contain a name, a pointer +array of struct acpi_gpio_mapping objects that each contains a name, a pointer to an array of line data (struct acpi_gpio_params) objects and the size of that array. Each struct acpi_gpio_params object consists of three fields, crs_entry_index, line_index, active_low, representing the index of the target @@ -154,13 +180,14 @@ question would look like this:: static const struct acpi_gpio_mapping bluetooth_acpi_gpios[] = { { "reset-gpios", &reset_gpio, 1 }, { "shutdown-gpios", &shutdown_gpio, 1 }, - { }, + { } }; Next, the mapping table needs to be passed as the second argument to -acpi_dev_add_driver_gpios() that will register it with the ACPI device object -pointed to by its first argument. That should be done in the driver's .probe() -routine. On removal, the driver should unregister its GPIO mapping table by +acpi_dev_add_driver_gpios() or its managed analogue that will +register it with the ACPI device object pointed to by its first +argument. That should be done in the driver's .probe() routine. +On removal, the driver should unregister its GPIO mapping table by calling acpi_dev_remove_driver_gpios() on the ACPI device object where that table was previously registered. @@ -191,12 +218,12 @@ The driver might expect to get the right GPIO when it does:: but since there is no way to know the mapping between "reset" and the GpioIo() in _CRS desc will hold ERR_PTR(-ENOENT). -The driver author can solve this by passing the mapping explictly -(the recommended way and documented in the above chapter). +The driver author can solve this by passing the mapping explicitly +(this is the recommended way and it's documented in the above chapter). The ACPI GPIO mapping tables should not contaminate drivers that are not knowing about which exact device they are servicing on. It implies that -the ACPI GPIO mapping tables are hardly linked to ACPI ID and certain +the ACPI GPIO mapping tables are hardly linked to an ACPI ID and certain objects, as listed in the above chapter, of the device in question. Getting GPIO descriptor @@ -229,5 +256,5 @@ Case 2 explicitly tells GPIO core to look for resources in _CRS. Be aware that gpiod_get_index() in cases 1 and 2, assuming that there are two versions of ACPI device description provided and no mapping is present in the driver, will return different resources. That's why a -certain driver has to handle them carefully as explained in previous +certain driver has to handle them carefully as explained in the previous chapter. diff --git a/Documentation/firmware-guide/acpi/method-tracing.rst b/Documentation/firmware-guide/acpi/method-tracing.rst index 0aa7e2c5d32a..6ab6c0964042 100644 --- a/Documentation/firmware-guide/acpi/method-tracing.rst +++ b/Documentation/firmware-guide/acpi/method-tracing.rst @@ -98,7 +98,7 @@ subject to change:: [ 0.188903] exdebug-0398 ex_trace_point : Method End [0xf58394d8:\_SB.PCI0.LPCB.ECOK] execution. Developers can utilize these special log entries to track the AML -interpretion, thus can aid issue debugging and performance tuning. Note +interpretation, thus can aid issue debugging and performance tuning. Note that, as the "AML tracer" logs are implemented via ACPI_DEBUG_PRINT() macro, CONFIG_ACPI_DEBUG is also required to be enabled for enabling "AML tracer" logs. diff --git a/Documentation/gpu/amdgpu.rst b/Documentation/gpu/amdgpu.rst index 1f9ea8221f80..2062a6023678 100644 --- a/Documentation/gpu/amdgpu.rst +++ b/Documentation/gpu/amdgpu.rst @@ -83,10 +83,6 @@ AMDGPU XGMI Support =================== .. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c - :doc: AMDGPU XGMI Support - -.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c - :internal: AMDGPU RAS Support ================== @@ -124,9 +120,6 @@ RAS VRAM Bad Pages sysfs Interface .. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c :doc: AMDGPU RAS sysfs gpu_vram_bad_pages Interface -.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c - :internal: - Sample Code ----------- Sample code for testing error injection can be found here: diff --git a/Documentation/hwmon/adm1266.rst b/Documentation/hwmon/adm1266.rst index 9257f8a48650..2b877011cfdf 100644 --- a/Documentation/hwmon/adm1266.rst +++ b/Documentation/hwmon/adm1266.rst @@ -20,7 +20,7 @@ ADM1266 is a sequencer that features voltage readback from 17 channels via an integrated 12 bit SAR ADC, accessed using a PMBus interface. The driver is a client driver to the core PMBus driver. Please see -Documentation/hwmon/pmbus for details on PMBus client drivers. +Documentation/hwmon/pmbus.rst for details on PMBus client drivers. Sysfs entries diff --git a/Documentation/hwmon/index.rst b/Documentation/hwmon/index.rst index e6b91ab12978..b797db738225 100644 --- a/Documentation/hwmon/index.rst +++ b/Documentation/hwmon/index.rst @@ -132,6 +132,7 @@ Hardware Monitoring Kernel Drivers mcp3021 menf21bmc mlxreg-fan + mp2975 nct6683 nct6775 nct7802 diff --git a/Documentation/hwmon/mp2975.rst b/Documentation/hwmon/mp2975.rst index 5b0609c62f48..81d816b71490 100644 --- a/Documentation/hwmon/mp2975.rst +++ b/Documentation/hwmon/mp2975.rst @@ -20,6 +20,7 @@ This driver implements support for Monolithic Power Systems, Inc. (MPS) vendor dual-loop, digital, multi-phase controller MP2975. This device: + - Supports up to two power rail. - Provides 8 pulse-width modulations (PWMs), and can be configured up to 8-phase operation for rail 1 and up to 4-phase operation for rail @@ -32,10 +33,12 @@ This device: 10-mV DAC, IMVP9 mode with 5-mV DAC. Device supports: + - SVID interface. - AVSBus interface. Device complaint with: + - PMBus rev 1.3 interface. Device supports direct format for reading output current, output voltage, @@ -45,11 +48,14 @@ Device supports VID and direct formats for reading output voltage. The below VID modes are supported: VR12, VR13, IMVP9. The driver provides the next attributes for the current: + - for current in: input, maximum alarm; - for current out input, maximum alarm and highest values; - for phase current: input and label. -attributes. + attributes. + The driver exports the following attributes via the 'sysfs' files, where + - 'n' is number of telemetry pages (from 1 to 2); - 'k' is number of configured phases (from 1 to 8); - indexes 1, 1*n for "iin"; @@ -65,11 +71,14 @@ The driver exports the following attributes via the 'sysfs' files, where **curr[1-{2n+k}]_label** The driver provides the next attributes for the voltage: + - for voltage in: input, high critical threshold, high critical alarm, all only from page 0; - for voltage out: input, low and high critical thresholds, low and high critical alarms, from pages 0 and 1; + The driver exports the following attributes via the 'sysfs' files, where + - 'n' is number of telemetry pages (from 1 to 2); - indexes 1 for "iin"; - indexes n+1, n+2 for "vout"; @@ -87,9 +96,12 @@ The driver exports the following attributes via the 'sysfs' files, where **in[2-{n+1}1_lcrit_alarm** The driver provides the next attributes for the power: + - for power in alarm and input. - for power out: highest and input. + The driver exports the following attributes via the 'sysfs' files, where + - 'n' is number of telemetry pages (from 1 to 2); - indexes 1 for "pin"; - indexes n+1, n+2 for "pout"; diff --git a/Documentation/leds/index.rst b/Documentation/leds/index.rst index 53e6090454af..e5d63b940045 100644 --- a/Documentation/leds/index.rst +++ b/Documentation/leds/index.rst @@ -25,3 +25,4 @@ LEDs leds-lp5562 leds-lp55xx leds-mlxcpld + leds-sc27xx diff --git a/Documentation/locking/lockdep-design.rst b/Documentation/locking/lockdep-design.rst index cec03bd1294a..9f3cfca9f8a4 100644 --- a/Documentation/locking/lockdep-design.rst +++ b/Documentation/locking/lockdep-design.rst @@ -42,6 +42,7 @@ The validator tracks lock-class usage history and divides the usage into (4 usages * n STATEs + 1) categories: where the 4 usages can be: + - 'ever held in STATE context' - 'ever held as readlock in STATE context' - 'ever held with STATE enabled' @@ -49,10 +50,12 @@ where the 4 usages can be: where the n STATEs are coded in kernel/locking/lockdep_states.h and as of now they include: + - hardirq - softirq where the last 1 category is: + - 'ever used' [ == !unused ] When locking rules are violated, these usage bits are presented in the @@ -96,9 +99,9 @@ exact case is for the lock as of the reporting time. +--------------+-------------+--------------+ | | irq enabled | irq disabled | +--------------+-------------+--------------+ - | ever in irq | ? | - | + | ever in irq | '?' | '-' | +--------------+-------------+--------------+ - | never in irq | + | . | + | never in irq | '+' | '.' | +--------------+-------------+--------------+ The character '-' suggests irq is disabled because if otherwise the @@ -216,7 +219,7 @@ looks like this:: BD_MUTEX_PARTITION }; -mutex_lock_nested(&bdev->bd_contains->bd_mutex, BD_MUTEX_PARTITION); + mutex_lock_nested(&bdev->bd_contains->bd_mutex, BD_MUTEX_PARTITION); In this case the locking is done on a bdev object that is known to be a partition. @@ -334,7 +337,7 @@ Troubleshooting: ---------------- The validator tracks a maximum of MAX_LOCKDEP_KEYS number of lock classes. -Exceeding this number will trigger the following lockdep warning: +Exceeding this number will trigger the following lockdep warning:: (DEBUG_LOCKS_WARN_ON(id >= MAX_LOCKDEP_KEYS)) @@ -420,7 +423,8 @@ the critical section of another reader of the same lock instance. The difference between recursive readers and non-recursive readers is because: recursive readers get blocked only by a write lock *holder*, while non-recursive -readers could get blocked by a write lock *waiter*. Considering the follow example: +readers could get blocked by a write lock *waiter*. Considering the follow +example:: TASK A: TASK B: @@ -448,20 +452,22 @@ There are simply four block conditions: Block condition matrix, Y means the row blocks the column, and N means otherwise. - | E | r | R | +---+---+---+---+ - E | Y | Y | Y | + | | E | r | R | + +---+---+---+---+ + | E | Y | Y | Y | + +---+---+---+---+ + | r | Y | Y | N | +---+---+---+---+ - r | Y | Y | N | + | R | Y | Y | N | +---+---+---+---+ - R | Y | Y | N | (W: writers, r: non-recursive readers, R: recursive readers) acquired recursively. Unlike non-recursive read locks, recursive read locks only get blocked by current write lock *holders* other than write lock -*waiters*, for example: +*waiters*, for example:: TASK A: TASK B: @@ -491,7 +497,7 @@ Recursive locks don't block each other, while non-recursive locks do (this is even true for two non-recursive read locks). A non-recursive lock can block the corresponding recursive lock, and vice versa. -A deadlock case with recursive locks involved is as follow: +A deadlock case with recursive locks involved is as follow:: TASK A: TASK B: @@ -510,7 +516,7 @@ because there are 3 types for lockers, there are, in theory, 9 types of lock dependencies, but we can show that 4 types of lock dependencies are enough for deadlock detection. -For each lock dependency: +For each lock dependency:: L1 -> L2 @@ -525,20 +531,25 @@ same types). With the above combination for simplification, there are 4 types of dependency edges in the lockdep graph: -1) -(ER)->: exclusive writer to recursive reader dependency, "X -(ER)-> Y" means +1) -(ER)->: + exclusive writer to recursive reader dependency, "X -(ER)-> Y" means X -> Y and X is a writer and Y is a recursive reader. -2) -(EN)->: exclusive writer to non-recursive locker dependency, "X -(EN)-> Y" means +2) -(EN)->: + exclusive writer to non-recursive locker dependency, "X -(EN)-> Y" means X -> Y and X is a writer and Y is either a writer or non-recursive reader. -3) -(SR)->: shared reader to recursive reader dependency, "X -(SR)-> Y" means +3) -(SR)->: + shared reader to recursive reader dependency, "X -(SR)-> Y" means X -> Y and X is a reader (recursive or not) and Y is a recursive reader. -4) -(SN)->: shared reader to non-recursive locker dependency, "X -(SN)-> Y" means +4) -(SN)->: + shared reader to non-recursive locker dependency, "X -(SN)-> Y" means X -> Y and X is a reader (recursive or not) and Y is either a writer or non-recursive reader. -Note that given two locks, they may have multiple dependencies between them, for example: +Note that given two locks, they may have multiple dependencies between them, +for example:: TASK A: @@ -592,11 +603,11 @@ circles that won't cause deadlocks. Proof for sufficiency (Lemma 1): -Let's say we have a strong circle: +Let's say we have a strong circle:: L1 -> L2 ... -> Ln -> L1 -, which means we have dependencies: +, which means we have dependencies:: L1 -> L2 L2 -> L3 @@ -633,7 +644,7 @@ a lock held by P2, and P2 is waiting for a lock held by P3, ... and Pn is waitin for a lock held by P1. Let's name the lock Px is waiting as Lx, so since P1 is waiting for L1 and holding Ln, so we will have Ln -> L1 in the dependency graph. Similarly, we have L1 -> L2, L2 -> L3, ..., Ln-1 -> Ln in the dependency graph, which means we -have a circle: +have a circle:: Ln -> L1 -> L2 -> ... -> Ln diff --git a/Documentation/misc-devices/index.rst b/Documentation/misc-devices/index.rst index 46072ce3d7ef..64420b3314fe 100644 --- a/Documentation/misc-devices/index.rst +++ b/Documentation/misc-devices/index.rst @@ -24,7 +24,6 @@ fit into other categories. isl29003 lis3lv02d max6875 - mic/index pci-endpoint-test spear-pcie-gadget uacce diff --git a/Documentation/networking/devlink/ice.rst b/Documentation/networking/devlink/ice.rst index b165181d5d4d..a432dc419fa4 100644 --- a/Documentation/networking/devlink/ice.rst +++ b/Documentation/networking/devlink/ice.rst @@ -70,6 +70,7 @@ The ``ice`` driver reports the following versions that both the name (as reported by ``fw.app.name``) and version are required to uniquely identify the package. * - ``fw.app.bundle_id`` + - running - 0xc0000001 - Unique identifier for the DDP package loaded in the device. Also referred to as the DDP Track ID. Can be used to uniquely identify diff --git a/Documentation/networking/j1939.rst b/Documentation/networking/j1939.rst index f5be243d250a..0a4b73b03b99 100644 --- a/Documentation/networking/j1939.rst +++ b/Documentation/networking/j1939.rst @@ -10,9 +10,9 @@ Overview / What Is J1939 SAE J1939 defines a higher layer protocol on CAN. It implements a more sophisticated addressing scheme and extends the maximum packet size above 8 bytes. Several derived specifications exist, which differ from the original -J1939 on the application level, like MilCAN A, NMEA2000 and especially +J1939 on the application level, like MilCAN A, NMEA2000, and especially ISO-11783 (ISOBUS). This last one specifies the so-called ETP (Extended -Transport Protocol) which is has been included in this implementation. This +Transport Protocol), which has been included in this implementation. This results in a maximum packet size of ((2 ^ 24) - 1) * 7 bytes == 111 MiB. Specifications used @@ -32,15 +32,15 @@ sockets, we found some reasons to justify a kernel implementation for the addressing and transport methods used by J1939. * **Addressing:** when a process on an ECU communicates via J1939, it should - not necessarily know its source address. Although at least one process per + not necessarily know its source address. Although, at least one process per ECU should know the source address. Other processes should be able to reuse that address. This way, address parameters for different processes cooperating for the same ECU, are not duplicated. This way of working is - closely related to the UNIX concept where programs do just one thing, and do + closely related to the UNIX concept, where programs do just one thing and do it well. * **Dynamic addressing:** Address Claiming in J1939 is time critical. - Furthermore data transport should be handled properly during the address + Furthermore, data transport should be handled properly during the address negotiation. Putting this functionality in the kernel eliminates it as a requirement for _every_ user space process that communicates via J1939. This results in a consistent J1939 bus with proper addressing. @@ -58,7 +58,7 @@ Therefore, these parts are left to user space. The J1939 sockets operate on CAN network devices (see SocketCAN). Any J1939 user space library operating on CAN raw sockets will still operate properly. -Since such library does not communicate with the in-kernel implementation, care +Since such a library does not communicate with the in-kernel implementation, care must be taken that these two do not interfere. In practice, this means they cannot share ECU addresses. A single ECU (or virtual ECU) address is used by the library exclusively, or by the in-kernel system exclusively. @@ -77,13 +77,13 @@ is composed as follows: 8 bits : PS (PDU Specific) In J1939-21 distinction is made between PDU1 format (where PF < 240) and PDU2 -format (where PF >= 240). Furthermore, when using PDU2 format, the PS-field +format (where PF >= 240). Furthermore, when using the PDU2 format, the PS-field contains a so-called Group Extension, which is part of the PGN. When using PDU2 format, the Group Extension is set in the PS-field. On the other hand, when using PDU1 format, the PS-field contains a so-called Destination Address, which is _not_ part of the PGN. When communicating a PGN -from user space to kernel (or visa versa) and PDU2 format is used, the PS-field +from user space to kernel (or vice versa) and PDU2 format is used, the PS-field of the PGN shall be set to zero. The Destination Address shall be set elsewhere. @@ -96,15 +96,15 @@ Addressing Both static and dynamic addressing methods can be used. -For static addresses, no extra checks are made by the kernel, and provided +For static addresses, no extra checks are made by the kernel and provided addresses are considered right. This responsibility is for the OEM or system integrator. For dynamic addressing, so-called Address Claiming, extra support is foreseen -in the kernel. In J1939 any ECU is known by it's 64-bit NAME. At the moment of +in the kernel. In J1939 any ECU is known by its 64-bit NAME. At the moment of a successful address claim, the kernel keeps track of both NAME and source address being claimed. This serves as a base for filter schemes. By default, -packets with a destination that is not locally, will be rejected. +packets with a destination that is not locally will be rejected. Mixed mode packets (from a static to a dynamic address or vice versa) are allowed. The BSD sockets define separate API calls for getting/setting the @@ -131,31 +131,31 @@ API Calls --------- On CAN, you first need to open a socket for communicating over a CAN network. -To use J1939, #include <linux/can/j1939.h>. From there, <linux/can.h> will be +To use J1939, ``#include <linux/can/j1939.h>``. From there, ``<linux/can.h>`` will be included too. To open a socket, use: .. code-block:: C s = socket(PF_CAN, SOCK_DGRAM, CAN_J1939); -J1939 does use SOCK_DGRAM sockets. In the J1939 specification, connections are +J1939 does use ``SOCK_DGRAM`` sockets. In the J1939 specification, connections are mentioned in the context of transport protocol sessions. These still deliver -packets to the other end (using several CAN packets). SOCK_STREAM is not +packets to the other end (using several CAN packets). ``SOCK_STREAM`` is not supported. -After the successful creation of the socket, you would normally use the bind(2) -and/or connect(2) system call to bind the socket to a CAN interface. After -binding and/or connecting the socket, you can read(2) and write(2) from/to the -socket or use send(2), sendto(2), sendmsg(2) and the recv*() counterpart +After the successful creation of the socket, you would normally use the ``bind(2)`` +and/or ``connect(2)`` system call to bind the socket to a CAN interface. After +binding and/or connecting the socket, you can ``read(2)`` and ``write(2)`` from/to the +socket or use ``send(2)``, ``sendto(2)``, ``sendmsg(2)`` and the ``recv*()`` counterpart operations on the socket as usual. There are also J1939 specific socket options described below. -In order to send data, a bind(2) must have been successful. bind(2) assigns a +In order to send data, a ``bind(2)`` must have been successful. ``bind(2)`` assigns a local address to a socket. -Different from CAN is that the payload data is just the data that get send, -without it's header info. The header info is derived from the sockaddr supplied -to bind(2), connect(2), sendto(2) and recvfrom(2). A write(2) with size 4 will +Different from CAN is that the payload data is just the data that get sends, +without its header info. The header info is derived from the sockaddr supplied +to ``bind(2)``, ``connect(2)``, ``sendto(2)`` and ``recvfrom(2)``. A ``write(2)`` with size 4 will result in a packet with 4 bytes. The sockaddr structure has extensions for use with J1939 as specified below: @@ -180,47 +180,47 @@ The sockaddr structure has extensions for use with J1939 as specified below: } can_addr; } -can_family & can_ifindex serve the same purpose as for other SocketCAN sockets. +``can_family`` & ``can_ifindex`` serve the same purpose as for other SocketCAN sockets. -can_addr.j1939.pgn specifies the PGN (max 0x3ffff). Individual bits are +``can_addr.j1939.pgn`` specifies the PGN (max 0x3ffff). Individual bits are specified above. -can_addr.j1939.name contains the 64-bit J1939 NAME. +``can_addr.j1939.name`` contains the 64-bit J1939 NAME. -can_addr.j1939.addr contains the address. +``can_addr.j1939.addr`` contains the address. -The bind(2) system call assigns the local address, i.e. the source address when -sending packages. If a PGN during bind(2) is set, it's used as a RX filter. -I.e. only packets with a matching PGN are received. If an ADDR or NAME is set +The ``bind(2)`` system call assigns the local address, i.e. the source address when +sending packages. If a PGN during ``bind(2)`` is set, it's used as a RX filter. +I.e. only packets with a matching PGN are received. If an ADDR or NAME is set it is used as a receive filter, too. It will match the destination NAME or ADDR of the incoming packet. The NAME filter will work only if appropriate Address Claiming for this name was done on the CAN bus and registered/cached by the kernel. -On the other hand connect(2) assigns the remote address, i.e. the destination -address. The PGN from connect(2) is used as the default PGN when sending +On the other hand ``connect(2)`` assigns the remote address, i.e. the destination +address. The PGN from ``connect(2)`` is used as the default PGN when sending packets. If ADDR or NAME is set it will be used as the default destination ADDR -or NAME. Further a set ADDR or NAME during connect(2) is used as a receive +or NAME. Further a set ADDR or NAME during ``connect(2)`` is used as a receive filter. It will match the source NAME or ADDR of the incoming packet. -Both write(2) and send(2) will send a packet with local address from bind(2) and -the remote address from connect(2). Use sendto(2) to overwrite the destination +Both ``write(2)`` and ``send(2)`` will send a packet with local address from ``bind(2)`` and the +remote address from ``connect(2)``. Use ``sendto(2)`` to overwrite the destination address. -If can_addr.j1939.name is set (!= 0) the NAME is looked up by the kernel and -the corresponding ADDR is used. If can_addr.j1939.name is not set (== 0), -can_addr.j1939.addr is used. +If ``can_addr.j1939.name`` is set (!= 0) the NAME is looked up by the kernel and +the corresponding ADDR is used. If ``can_addr.j1939.name`` is not set (== 0), +``can_addr.j1939.addr`` is used. When creating a socket, reasonable defaults are set. Some options can be -modified with setsockopt(2) & getsockopt(2). +modified with ``setsockopt(2)`` & ``getsockopt(2)``. RX path related options: -- SO_J1939_FILTER - configure array of filters -- SO_J1939_PROMISC - disable filters set by bind(2) and connect(2) +- ``SO_J1939_FILTER`` - configure array of filters +- ``SO_J1939_PROMISC`` - disable filters set by ``bind(2)`` and ``connect(2)`` By default no broadcast packets can be send or received. To enable sending or -receiving broadcast packets use the socket option SO_BROADCAST: +receiving broadcast packets use the socket option ``SO_BROADCAST``: .. code-block:: C @@ -261,26 +261,26 @@ The following diagram illustrates the RX path: +---------------------------+ TX path related options: -SO_J1939_SEND_PRIO - change default send priority for the socket +``SO_J1939_SEND_PRIO`` - change default send priority for the socket Message Flags during send() and Related System Calls ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ -send(2), sendto(2) and sendmsg(2) take a 'flags' argument. Currently +``send(2)``, ``sendto(2)`` and ``sendmsg(2)`` take a 'flags' argument. Currently supported flags are: -* MSG_DONTWAIT, i.e. non-blocking operation. +* ``MSG_DONTWAIT``, i.e. non-blocking operation. recvmsg(2) ^^^^^^^^^^ -In most cases recvmsg(2) is needed if you want to extract more information than -recvfrom(2) can provide. For example package priority and timestamp. The +In most cases ``recvmsg(2)`` is needed if you want to extract more information than +``recvfrom(2)`` can provide. For example package priority and timestamp. The Destination Address, name and packet priority (if applicable) are attached to -the msghdr in the recvmsg(2) call. They can be extracted using cmsg(3) macros, -with cmsg_level == SOL_J1939 && cmsg_type == SCM_J1939_DEST_ADDR, -SCM_J1939_DEST_NAME or SCM_J1939_PRIO. The returned data is a uint8_t for -priority and dst_addr, and uint64_t for dst_name. +the msghdr in the ``recvmsg(2)`` call. They can be extracted using ``cmsg(3)`` macros, +with ``cmsg_level == SOL_J1939 && cmsg_type == SCM_J1939_DEST_ADDR``, +``SCM_J1939_DEST_NAME`` or ``SCM_J1939_PRIO``. The returned data is a ``uint8_t`` for +``priority`` and ``dst_addr``, and ``uint64_t`` for ``dst_name``. .. code-block:: C @@ -305,12 +305,12 @@ Dynamic Addressing Distinction has to be made between using the claimed address and doing an address claim. To use an already claimed address, one has to fill in the -j1939.name member and provide it to bind(2). If the name had claimed an address +``j1939.name`` member and provide it to ``bind(2)``. If the name had claimed an address earlier, all further messages being sent will use that address. And the -j1939.addr member will be ignored. +``j1939.addr`` member will be ignored. An exception on this is PGN 0x0ee00. This is the "Address Claim/Cannot Claim -Address" message and the kernel will use the j1939.addr member for that PGN if +Address" message and the kernel will use the ``j1939.addr`` member for that PGN if necessary. To claim an address following code example can be used: @@ -371,12 +371,12 @@ NAME can send packets. If another ECU claims the address, the kernel will mark the NAME-SA expired. No socket bound to the NAME can send packets (other than address claims). To -claim another address, some socket bound to NAME, must bind(2) again, but with -only j1939.addr changed to the new SA, and must then send a valid address claim +claim another address, some socket bound to NAME, must ``bind(2)`` again, but with +only ``j1939.addr`` changed to the new SA, and must then send a valid address claim packet. This restarts the state machine in the kernel (and any other participant on the bus) for this NAME. -can-utils also include the jacd tool, so it can be used as code example or as +``can-utils`` also include the ``j1939acd`` tool, so it can be used as code example or as default Address Claiming daemon. Send Examples @@ -403,8 +403,8 @@ Bind: bind(sock, (struct sockaddr *)&baddr, sizeof(baddr)); -Now, the socket 'sock' is bound to the SA 0x20. Since no connect(2) was called, -at this point we can use only sendto(2) or sendmsg(2). +Now, the socket 'sock' is bound to the SA 0x20. Since no ``connect(2)`` was called, +at this point we can use only ``sendto(2)`` or ``sendmsg(2)``. Send: @@ -414,8 +414,8 @@ Send: .can_family = AF_CAN, .can_addr.j1939 = { .name = J1939_NO_NAME; - .pgn = 0x30, - .addr = 0x12300, + .addr = 0x30, + .pgn = 0x12300, }, }; diff --git a/Documentation/networking/netdev-FAQ.rst b/Documentation/networking/netdev-FAQ.rst index d5c9320901c3..21537766be4d 100644 --- a/Documentation/networking/netdev-FAQ.rst +++ b/Documentation/networking/netdev-FAQ.rst @@ -110,7 +110,7 @@ Q: I sent a patch and I'm wondering what happened to it? Q: How can I tell whether it got merged? A: Start by looking at the main patchworks queue for netdev: - http://patchwork.ozlabs.org/project/netdev/list/ + https://patchwork.kernel.org/project/netdevbpf/list/ The "State" field will tell you exactly where things are at with your patch. @@ -152,7 +152,7 @@ networking subsystem, and then hands them off to Greg. There is a patchworks queue that you can see here: - http://patchwork.ozlabs.org/bundle/davem/stable/?state=* + https://patchwork.kernel.org/bundle/netdev/stable/?state=* It contains the patches which Dave has selected, but not yet handed off to Greg. If Greg already has the patch, then it will be here: diff --git a/Documentation/networking/phy.rst b/Documentation/networking/phy.rst index 256106054c8c..b2f7ec794bc8 100644 --- a/Documentation/networking/phy.rst +++ b/Documentation/networking/phy.rst @@ -247,8 +247,8 @@ Some of the interface modes are described below: speeds (see below.) ``PHY_INTERFACE_MODE_2500BASEX`` - This defines a variant of 1000BASE-X which is clocked 2.5 times faster, - than the 802.3 standard giving a fixed bit rate of 3.125Gbaud. + This defines a variant of 1000BASE-X which is clocked 2.5 times as fast + as the 802.3 standard, giving a fixed bit rate of 3.125Gbaud. ``PHY_INTERFACE_MODE_SGMII`` This is used for Cisco SGMII, which is a modification of 1000BASE-X diff --git a/Documentation/networking/statistics.rst b/Documentation/networking/statistics.rst index 8e15bc98830b..234abedc29b2 100644 --- a/Documentation/networking/statistics.rst +++ b/Documentation/networking/statistics.rst @@ -175,5 +175,4 @@ The following structures are internal to the kernel, their members are translated to netlink attributes when dumped. Drivers must not overwrite the statistics they don't report with 0. -.. kernel-doc:: include/linux/ethtool.h - :identifiers: ethtool_pause_stats +- ethtool_pause_stats() diff --git a/Documentation/process/stable-kernel-rules.rst b/Documentation/process/stable-kernel-rules.rst index 06f743b612c4..3973556250e1 100644 --- a/Documentation/process/stable-kernel-rules.rst +++ b/Documentation/process/stable-kernel-rules.rst @@ -39,7 +39,7 @@ Procedure for submitting patches to the -stable tree submission guidelines as described in :ref:`Documentation/networking/netdev-FAQ.rst <netdev-FAQ>` after first checking the stable networking queue at - https://patchwork.ozlabs.org/bundle/davem/stable/?series=&submitter=&state=*&q=&archive= + https://patchwork.kernel.org/bundle/netdev/stable/?state=* to ensure the requested patch is not already queued up. - Security patches should not be handled (solely) by the -stable review process but should follow the procedures in diff --git a/Documentation/sphinx/automarkup.py b/Documentation/sphinx/automarkup.py index 409dbc4100de..3e81ebab26ed 100644 --- a/Documentation/sphinx/automarkup.py +++ b/Documentation/sphinx/automarkup.py @@ -16,28 +16,36 @@ import re from itertools import chain # +# Python 2 lacks re.ASCII... +# +try: + ascii_p3 = re.ASCII +except AttributeError: + ascii_p3 = 0 + +# # Regex nastiness. Of course. # Try to identify "function()" that's not already marked up some # other way. Sphinx doesn't like a lot of stuff right after a # :c:func: block (i.e. ":c:func:`mmap()`s" flakes out), so the last # bit tries to restrict matches to things that won't create trouble. # -RE_function = re.compile(r'\b(([a-zA-Z_]\w+)\(\))', flags=re.ASCII) +RE_function = re.compile(r'\b(([a-zA-Z_]\w+)\(\))', flags=ascii_p3) # # Sphinx 2 uses the same :c:type role for struct, union, enum and typedef # RE_generic_type = re.compile(r'\b(struct|union|enum|typedef)\s+([a-zA-Z_]\w+)', - flags=re.ASCII) + flags=ascii_p3) # # Sphinx 3 uses a different C role for each one of struct, union, enum and # typedef # -RE_struct = re.compile(r'\b(struct)\s+([a-zA-Z_]\w+)', flags=re.ASCII) -RE_union = re.compile(r'\b(union)\s+([a-zA-Z_]\w+)', flags=re.ASCII) -RE_enum = re.compile(r'\b(enum)\s+([a-zA-Z_]\w+)', flags=re.ASCII) -RE_typedef = re.compile(r'\b(typedef)\s+([a-zA-Z_]\w+)', flags=re.ASCII) +RE_struct = re.compile(r'\b(struct)\s+([a-zA-Z_]\w+)', flags=ascii_p3) +RE_union = re.compile(r'\b(union)\s+([a-zA-Z_]\w+)', flags=ascii_p3) +RE_enum = re.compile(r'\b(enum)\s+([a-zA-Z_]\w+)', flags=ascii_p3) +RE_typedef = re.compile(r'\b(typedef)\s+([a-zA-Z_]\w+)', flags=ascii_p3) # # Detects a reference to a documentation page of the form Documentation/... with diff --git a/Documentation/translations/it_IT/process/stable-kernel-rules.rst b/Documentation/translations/it_IT/process/stable-kernel-rules.rst index 4f206cee31a7..283d62541c4f 100644 --- a/Documentation/translations/it_IT/process/stable-kernel-rules.rst +++ b/Documentation/translations/it_IT/process/stable-kernel-rules.rst @@ -46,7 +46,7 @@ Procedura per sottomettere patch per i sorgenti -stable :ref:`Documentation/translations/it_IT/networking/netdev-FAQ.rst <it_netdev-FAQ>`; ma solo dopo aver verificato al seguente indirizzo che la patch non sia già in coda: - https://patchwork.ozlabs.org/bundle/davem/stable/?series=&submitter=&state=*&q=&archive= + https://patchwork.kernel.org/bundle/netdev/stable/?state=* - Una patch di sicurezza non dovrebbero essere gestite (solamente) dal processo di revisione -stable, ma dovrebbe seguire le procedure descritte in :ref:`Documentation/translations/it_IT/admin-guide/security-bugs.rst <it_securitybugs>`. diff --git a/Documentation/userspace-api/index.rst b/Documentation/userspace-api/index.rst index 69fc5167e648..acd2cc2a538d 100644 --- a/Documentation/userspace-api/index.rst +++ b/Documentation/userspace-api/index.rst @@ -22,6 +22,7 @@ place where this information is gathered. spec_ctrl accelerators/ocxl ioctl/index + iommu media/index .. only:: subproject and html diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 36d5f1f3c6dd..e00a66d72372 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -6367,7 +6367,7 @@ accesses that would usually trigger a #GP by KVM into the guest will instead get bounced to user space through the KVM_EXIT_X86_RDMSR and KVM_EXIT_X86_WRMSR exit notifications. -8.25 KVM_X86_SET_MSR_FILTER +8.27 KVM_X86_SET_MSR_FILTER --------------------------- :Architectures: x86 @@ -6381,8 +6381,7 @@ In combination with KVM_CAP_X86_USER_SPACE_MSR, this allows user space to trap and emulate MSRs that are outside of the scope of KVM as well as limit the attack surface on KVM's MSR emulation code. - -8.26 KVM_CAP_ENFORCE_PV_CPUID +8.28 KVM_CAP_ENFORCE_PV_CPUID ----------------------------- Architectures: x86 diff --git a/Documentation/xtensa/mmu.rst b/Documentation/xtensa/mmu.rst index e52a12960fdc..450573afa31a 100644 --- a/Documentation/xtensa/mmu.rst +++ b/Documentation/xtensa/mmu.rst @@ -82,7 +82,8 @@ Default MMUv2-compatible layout:: +------------------+ | VMALLOC area | VMALLOC_START 0xc0000000 128MB - 64KB +------------------+ VMALLOC_END - | Cache aliasing | TLBTEMP_BASE_1 0xc7ff0000 DCACHE_WAY_SIZE + +------------------+ + | Cache aliasing | TLBTEMP_BASE_1 0xc8000000 DCACHE_WAY_SIZE | remap area 1 | +------------------+ | Cache aliasing | TLBTEMP_BASE_2 DCACHE_WAY_SIZE @@ -124,7 +125,8 @@ Default MMUv2-compatible layout:: +------------------+ | VMALLOC area | VMALLOC_START 0xa0000000 128MB - 64KB +------------------+ VMALLOC_END - | Cache aliasing | TLBTEMP_BASE_1 0xa7ff0000 DCACHE_WAY_SIZE + +------------------+ + | Cache aliasing | TLBTEMP_BASE_1 0xa8000000 DCACHE_WAY_SIZE | remap area 1 | +------------------+ | Cache aliasing | TLBTEMP_BASE_2 DCACHE_WAY_SIZE @@ -167,7 +169,8 @@ Default MMUv2-compatible layout:: +------------------+ | VMALLOC area | VMALLOC_START 0x90000000 128MB - 64KB +------------------+ VMALLOC_END - | Cache aliasing | TLBTEMP_BASE_1 0x97ff0000 DCACHE_WAY_SIZE + +------------------+ + | Cache aliasing | TLBTEMP_BASE_1 0x98000000 DCACHE_WAY_SIZE | remap area 1 | +------------------+ | Cache aliasing | TLBTEMP_BASE_2 DCACHE_WAY_SIZE diff --git a/MAINTAINERS b/MAINTAINERS index b516bb34a8d5..a008b70f3c16 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -934,7 +934,7 @@ M: Evan Quan <evan.quan@amd.com> L: amd-gfx@lists.freedesktop.org S: Supported T: git git://people.freedesktop.org/~agd5f/linux -F: drivers/gpu/drm/amd/powerplay/ +F: drivers/gpu/drm/amd/pm/powerplay/ AMD SEATTLE DEVICE TREE SUPPORT M: Brijesh Singh <brijeshkumar.singh@amd.com> @@ -978,7 +978,7 @@ M: Michael Hennerich <Michael.Hennerich@analog.com> L: linux-iio@vger.kernel.org S: Supported W: http://ez.analog.com/community/linux-device-drivers -F: Documentation/devicetree/bindings/iio/adc/adi,ad7768-1.txt +F: Documentation/devicetree/bindings/iio/adc/adi,ad7768-1.yaml F: drivers/iio/adc/ad7768-1.c ANALOG DEVICES INC AD7780 DRIVER @@ -1279,7 +1279,7 @@ M: Igor Russkikh <irusskikh@marvell.com> L: netdev@vger.kernel.org S: Supported W: https://www.marvell.com/ -Q: http://patchwork.ozlabs.org/project/netdev/list/ +Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: Documentation/networking/device_drivers/ethernet/aquantia/atlantic.rst F: drivers/net/ethernet/aquantia/atlantic/ @@ -1546,6 +1546,7 @@ F: drivers/clk/sunxi/ ARM/Allwinner sunXi SoC support M: Maxime Ripard <mripard@kernel.org> M: Chen-Yu Tsai <wens@csie.org> +R: Jernej Skrabec <jernej.skrabec@siol.net> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/sunxi/linux.git @@ -2374,7 +2375,7 @@ F: drivers/i2c/busses/i2c-rk3x.c F: sound/soc/rockchip/ N: rockchip -ARM/SAMSUNG EXYNOS ARM ARCHITECTURES +ARM/SAMSUNG S3C, S5P AND EXYNOS ARM ARCHITECTURES M: Krzysztof Kozlowski <krzk@kernel.org> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: linux-samsung-soc@vger.kernel.org @@ -2403,15 +2404,7 @@ N: s3c2410 N: s3c64xx N: s5pv210 -ARM/SAMSUNG MOBILE MACHINE SUPPORT -M: Kyungmin Park <kyungmin.park@samsung.com> -L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) -S: Maintained -F: arch/arm/mach-s5pv210/ - ARM/SAMSUNG S5P SERIES 2D GRAPHICS ACCELERATION (G2D) SUPPORT -M: Kyungmin Park <kyungmin.park@samsung.com> -M: Kamil Debski <kamil@wypas.org> M: Andrzej Hajda <a.hajda@samsung.com> L: linux-arm-kernel@lists.infradead.org L: linux-media@vger.kernel.org @@ -2436,9 +2429,6 @@ S: Maintained F: drivers/media/platform/s5p-jpeg/ ARM/SAMSUNG S5P SERIES Multi Format Codec (MFC) SUPPORT -M: Kyungmin Park <kyungmin.park@samsung.com> -M: Kamil Debski <kamil@wypas.org> -M: Jeongtae Park <jtp.park@samsung.com> M: Andrzej Hajda <a.hajda@samsung.com> L: linux-arm-kernel@lists.infradead.org L: linux-media@vger.kernel.org @@ -3243,10 +3233,10 @@ F: drivers/iio/accel/bma400* BPF (Safe dynamic programs and tools) M: Alexei Starovoitov <ast@kernel.org> M: Daniel Borkmann <daniel@iogearbox.net> +M: Andrii Nakryiko <andrii@kernel.org> R: Martin KaFai Lau <kafai@fb.com> R: Song Liu <songliubraving@fb.com> R: Yonghong Song <yhs@fb.com> -R: Andrii Nakryiko <andrii@kernel.org> R: John Fastabend <john.fastabend@gmail.com> R: KP Singh <kpsingh@chromium.org> L: netdev@vger.kernel.org @@ -3857,7 +3847,7 @@ M: Roger Quadros <rogerq@ti.com> L: linux-usb@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/peter.chen/usb.git -F: Documentation/devicetree/bindings/usb/cdns-usb3.txt +F: Documentation/devicetree/bindings/usb/cdns,usb3.yaml F: drivers/usb/cdns3/ CADET FM/AM RADIO RECEIVER DRIVER @@ -4710,7 +4700,7 @@ T: git git://linuxtv.org/anttip/media_tree.git F: drivers/media/dvb-frontends/cxd2820r* CXGB3 ETHERNET DRIVER (CXGB3) -M: Vishal Kulkarni <vishal@chelsio.com> +M: Raju Rangoju <rajur@chelsio.com> L: netdev@vger.kernel.org S: Supported W: http://www.chelsio.com @@ -4742,7 +4732,7 @@ W: http://www.chelsio.com F: drivers/net/ethernet/chelsio/inline_crypto/ CXGB4 ETHERNET DRIVER (CXGB4) -M: Vishal Kulkarni <vishal@chelsio.com> +M: Raju Rangoju <rajur@chelsio.com> L: netdev@vger.kernel.org S: Supported W: http://www.chelsio.com @@ -4764,7 +4754,7 @@ F: drivers/infiniband/hw/cxgb4/ F: include/uapi/rdma/cxgb4-abi.h CXGB4VF ETHERNET DRIVER (CXGB4VF) -M: Vishal Kulkarni <vishal@gmail.com> +M: Raju Rangoju <rajur@chelsio.com> L: netdev@vger.kernel.org S: Supported W: http://www.chelsio.com @@ -6614,6 +6604,7 @@ Q: http://patchwork.ozlabs.org/project/linux-ext4/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4.git F: Documentation/filesystems/ext4/ F: fs/ext4/ +F: include/trace/events/ext4.h Extended Verification Module (EVM) M: Mimi Zohar <zohar@linux.ibm.com> @@ -7916,7 +7907,7 @@ HISILICON LPC BUS DRIVER M: john.garry@huawei.com S: Maintained W: http://www.hisilicon.com -F: Documentation/devicetree/bindings/arm/hisilicon/hisilicon-low-pin-count.txt +F: Documentation/devicetree/bindings/arm/hisilicon/low-pin-count.yaml F: drivers/bus/hisi_lpc.c HISILICON NETWORK SUBSYSTEM 3 DRIVER (HNS3) @@ -8829,8 +8820,8 @@ S: Supported W: http://www.intel.com/support/feedback.htm W: http://e1000.sourceforge.net/ Q: http://patchwork.ozlabs.org/project/intel-wired-lan/list/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/net-queue.git -T: git git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/net-queue.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue.git F: Documentation/networking/device_drivers/ethernet/intel/ F: drivers/net/ethernet/intel/ F: drivers/net/ethernet/intel/*/ @@ -9171,6 +9162,7 @@ F: include/linux/iomap.h IOMMU DRIVERS M: Joerg Roedel <joro@8bytes.org> +M: Will Deacon <will@kernel.org> L: iommu@lists.linux-foundation.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git @@ -9842,13 +9834,6 @@ S: Maintained F: arch/mips/lantiq F: drivers/soc/lantiq -LAPB module -L: linux-x25@vger.kernel.org -S: Orphan -F: Documentation/networking/lapb-module.rst -F: include/*/lapb.h -F: net/lapb/ - LASI 53c700 driver for PARISC M: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com> L: linux-scsi@vger.kernel.org @@ -11163,7 +11148,7 @@ F: Documentation/devicetree/bindings/input/touchscreen/melfas_mip4.txt F: drivers/input/touchscreen/melfas_mip4.c MELLANOX BLUEFIELD I2C DRIVER -M: Khalil Blaiech <kblaiech@mellanox.com> +M: Khalil Blaiech <kblaiech@nvidia.com> L: linux-i2c@vger.kernel.org S: Supported F: drivers/i2c/busses/i2c-mlxbf.c @@ -11173,7 +11158,7 @@ M: Tariq Toukan <tariqt@nvidia.com> L: netdev@vger.kernel.org S: Supported W: http://www.mellanox.com -Q: http://patchwork.ozlabs.org/project/netdev/list/ +Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: drivers/net/ethernet/mellanox/mlx4/en_* MELLANOX ETHERNET DRIVER (mlx5e) @@ -11181,7 +11166,7 @@ M: Saeed Mahameed <saeedm@nvidia.com> L: netdev@vger.kernel.org S: Supported W: http://www.mellanox.com -Q: http://patchwork.ozlabs.org/project/netdev/list/ +Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: drivers/net/ethernet/mellanox/mlx5/core/en_* MELLANOX ETHERNET INNOVA DRIVERS @@ -11189,7 +11174,7 @@ R: Boris Pismenny <borisp@nvidia.com> L: netdev@vger.kernel.org S: Supported W: http://www.mellanox.com -Q: http://patchwork.ozlabs.org/project/netdev/list/ +Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: drivers/net/ethernet/mellanox/mlx5/core/accel/* F: drivers/net/ethernet/mellanox/mlx5/core/en_accel/* F: drivers/net/ethernet/mellanox/mlx5/core/fpga/* @@ -11201,7 +11186,7 @@ M: Ido Schimmel <idosch@nvidia.com> L: netdev@vger.kernel.org S: Supported W: http://www.mellanox.com -Q: http://patchwork.ozlabs.org/project/netdev/list/ +Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: drivers/net/ethernet/mellanox/mlxsw/ F: tools/testing/selftests/drivers/net/mlxsw/ @@ -11210,7 +11195,7 @@ M: mlxsw@nvidia.com L: netdev@vger.kernel.org S: Supported W: http://www.mellanox.com -Q: http://patchwork.ozlabs.org/project/netdev/list/ +Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: drivers/net/ethernet/mellanox/mlxfw/ MELLANOX HARDWARE PLATFORM SUPPORT @@ -11229,7 +11214,7 @@ L: netdev@vger.kernel.org L: linux-rdma@vger.kernel.org S: Supported W: http://www.mellanox.com -Q: http://patchwork.ozlabs.org/project/netdev/list/ +Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: drivers/net/ethernet/mellanox/mlx4/ F: include/linux/mlx4/ @@ -11250,7 +11235,7 @@ L: netdev@vger.kernel.org L: linux-rdma@vger.kernel.org S: Supported W: http://www.mellanox.com -Q: http://patchwork.ozlabs.org/project/netdev/list/ +Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: Documentation/networking/device_drivers/ethernet/mellanox/ F: drivers/net/ethernet/mellanox/mlx5/core/ F: include/linux/mlx5/ @@ -12130,7 +12115,7 @@ M: Jakub Kicinski <kuba@kernel.org> L: netdev@vger.kernel.org S: Maintained W: http://www.linuxfoundation.org/en/Net -Q: http://patchwork.ozlabs.org/project/netdev/list/ +Q: https://patchwork.kernel.org/project/netdevbpf/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git F: Documentation/devicetree/bindings/net/ @@ -12175,7 +12160,7 @@ M: Jakub Kicinski <kuba@kernel.org> L: netdev@vger.kernel.org S: Maintained W: http://www.linuxfoundation.org/en/Net -Q: http://patchwork.ozlabs.org/project/netdev/list/ +Q: https://patchwork.kernel.org/project/netdevbpf/list/ B: mailto:netdev@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git @@ -14210,7 +14195,6 @@ F: drivers/media/usb/pwc/* F: include/trace/events/pwc.h PWM FAN DRIVER -M: Kamil Debski <kamil@wypas.org> M: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> L: linux-hwmon@vger.kernel.org S: Supported @@ -14527,6 +14511,14 @@ F: Documentation/devicetree/bindings/mailbox/qcom-ipcc.yaml F: drivers/mailbox/qcom-ipcc.c F: include/dt-bindings/mailbox/qcom-ipcc.h +QUALCOMM IPQ4019 VQMMC REGULATOR DRIVER +M: Robert Marko <robert.marko@sartura.hr> +M: Luka Perkov <luka.perkov@sartura.hr> +L: linux-arm-msm@vger.kernel.org +S: Maintained +F: Documentation/devicetree/bindings/regulator/vqmmc-ipq4019-regulator.yaml +F: drivers/regulator/vqmmc-ipq4019-regulator.c + QUALCOMM RMNET DRIVER M: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org> M: Sean Tranchetti <stranche@codeaurora.org> @@ -14882,7 +14874,6 @@ RENESAS ETHERNET DRIVERS R: Sergei Shtylyov <sergei.shtylyov@gmail.com> L: netdev@vger.kernel.org L: linux-renesas-soc@vger.kernel.org -F: Documentation/devicetree/bindings/net/renesas,*.txt F: Documentation/devicetree/bindings/net/renesas,*.yaml F: drivers/net/ethernet/renesas/ F: include/linux/sh_eth.h @@ -15239,7 +15230,6 @@ F: drivers/iommu/s390-iommu.c S390 IUCV NETWORK LAYER M: Julian Wiedmann <jwi@linux.ibm.com> M: Karsten Graul <kgraul@linux.ibm.com> -M: Ursula Braun <ubraun@linux.ibm.com> L: linux-s390@vger.kernel.org S: Supported W: http://www.ibm.com/developerworks/linux/linux390/ @@ -15250,7 +15240,6 @@ F: net/iucv/ S390 NETWORK DRIVERS M: Julian Wiedmann <jwi@linux.ibm.com> M: Karsten Graul <kgraul@linux.ibm.com> -M: Ursula Braun <ubraun@linux.ibm.com> L: linux-s390@vger.kernel.org S: Supported W: http://www.ibm.com/developerworks/linux/linux390/ @@ -15419,14 +15408,12 @@ F: Documentation/devicetree/bindings/net/nfc/samsung,s3fwrn5.yaml F: drivers/nfc/s3fwrn5 SAMSUNG S5C73M3 CAMERA DRIVER -M: Kyungmin Park <kyungmin.park@samsung.com> M: Andrzej Hajda <a.hajda@samsung.com> L: linux-media@vger.kernel.org S: Supported F: drivers/media/i2c/s5c73m3/* SAMSUNG S5K5BAF CAMERA DRIVER -M: Kyungmin Park <kyungmin.park@samsung.com> M: Andrzej Hajda <a.hajda@samsung.com> L: linux-media@vger.kernel.org S: Supported @@ -15444,7 +15431,6 @@ F: Documentation/devicetree/bindings/crypto/samsung-sss.yaml F: drivers/crypto/s5p-sss.c SAMSUNG S5P/EXYNOS4 SOC SERIES CAMERA SUBSYSTEM DRIVERS -M: Kyungmin Park <kyungmin.park@samsung.com> M: Sylwester Nawrocki <s.nawrocki@samsung.com> L: linux-media@vger.kernel.org S: Supported @@ -15492,7 +15478,6 @@ T: git https://github.com/lmajewski/linux-samsung-thermal.git F: drivers/thermal/samsung/ SAMSUNG USB2 PHY DRIVER -M: Kamil Debski <kamil@wypas.org> M: Sylwester Nawrocki <s.nawrocki@samsung.com> L: linux-kernel@vger.kernel.org S: Supported @@ -15821,7 +15806,6 @@ S: Maintained F: drivers/misc/sgi-xp/ SHARED MEMORY COMMUNICATIONS (SMC) SOCKETS -M: Ursula Braun <ubraun@linux.ibm.com> M: Karsten Graul <kgraul@linux.ibm.com> L: linux-s390@vger.kernel.org S: Supported @@ -18083,7 +18067,7 @@ M: Yu Chen <chenyu56@huawei.com> M: Binghui Wang <wangbinghui@hisilicon.com> L: linux-usb@vger.kernel.org S: Maintained -F: Documentation/devicetree/bindings/phy/phy-hi3660-usb3.txt +F: Documentation/devicetree/bindings/phy/hisilicon,hi3660-usb3.yaml F: drivers/phy/hisilicon/phy-hi3660-usb3.c USB ISP116X DRIVER @@ -18168,6 +18152,14 @@ L: linux-usb@vger.kernel.org S: Supported F: drivers/usb/class/usblp.c +USB RAW GADGET DRIVER +R: Andrey Konovalov <andreyknvl@gmail.com> +L: linux-usb@vger.kernel.org +S: Maintained +F: Documentation/usb/raw-gadget.rst +F: drivers/usb/gadget/legacy/raw_gadget.c +F: include/uapi/linux/usb/raw_gadget.h + USB QMI WWAN NETWORK DRIVER M: Bjørn Mork <bjorn@mork.no> L: netdev@vger.kernel.org @@ -18993,12 +18985,18 @@ L: linux-kernel@vger.kernel.org S: Maintained N: axp[128] -X.25 NETWORK LAYER -M: Andrew Hendry <andrew.hendry@gmail.com> +X.25 STACK +M: Martin Schiller <ms@dev.tdt.de> L: linux-x25@vger.kernel.org -S: Odd Fixes +S: Maintained +F: Documentation/networking/lapb-module.rst F: Documentation/networking/x25* +F: drivers/net/wan/hdlc_x25.c +F: drivers/net/wan/lapbether.c +F: include/*/lapb.h F: include/net/x25* +F: include/uapi/linux/x25.h +F: net/lapb/ F: net/x25/ X86 ARCHITECTURE (32-BIT AND 64-BIT) @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 10 SUBLEVEL = 0 -EXTRAVERSION = -rc2 +EXTRAVERSION = -rc5 NAME = Kleptomaniac Octopus # *DOCUMENTATION* diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S index 17fd1ed700cc..9152782444b5 100644 --- a/arch/arc/kernel/head.S +++ b/arch/arc/kernel/head.S @@ -67,7 +67,22 @@ sr r5, [ARC_REG_LPB_CTRL] 1: #endif /* CONFIG_ARC_LPB_DISABLE */ -#endif + + /* On HSDK, CCMs need to remapped super early */ +#ifdef CONFIG_ARC_SOC_HSDK + mov r6, 0x60000000 + lr r5, [ARC_REG_ICCM_BUILD] + breq r5, 0, 1f + sr r6, [ARC_REG_AUX_ICCM] +1: + lr r5, [ARC_REG_DCCM_BUILD] + breq r5, 0, 2f + sr r6, [ARC_REG_AUX_DCCM] +2: +#endif /* CONFIG_ARC_SOC_HSDK */ + +#endif /* CONFIG_ISA_ARCV2 */ + ; Config DSP_CTRL properly, so kernel may use integer multiply, ; multiply-accumulate, and divide operations DSP_EARLY_INIT diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c index feba91c9d969..b23986f98450 100644 --- a/arch/arc/kernel/stacktrace.c +++ b/arch/arc/kernel/stacktrace.c @@ -112,7 +112,7 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs, int (*consumer_fn) (unsigned int, void *), void *arg) { #ifdef CONFIG_ARC_DW2_UNWIND - int ret = 0; + int ret = 0, cnt = 0; unsigned int address; struct unwind_frame_info frame_info; @@ -132,6 +132,11 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs, break; frame_info.regs.r63 = frame_info.regs.r31; + + if (cnt++ > 128) { + printk("unwinder looping too long, aborting !\n"); + return 0; + } } return address; /* return the last address it saw */ diff --git a/arch/arc/plat-hsdk/platform.c b/arch/arc/plat-hsdk/platform.c index 0b63fc095b99..b3ea1fa11f87 100644 --- a/arch/arc/plat-hsdk/platform.c +++ b/arch/arc/plat-hsdk/platform.c @@ -17,22 +17,6 @@ int arc_hsdk_axi_dmac_coherent __section(".data") = 0; #define ARC_CCM_UNUSED_ADDR 0x60000000 -static void __init hsdk_init_per_cpu(unsigned int cpu) -{ - /* - * By default ICCM is mapped to 0x7z while this area is used for - * kernel virtual mappings, so move it to currently unused area. - */ - if (cpuinfo_arc700[cpu].iccm.sz) - write_aux_reg(ARC_REG_AUX_ICCM, ARC_CCM_UNUSED_ADDR); - - /* - * By default DCCM is mapped to 0x8z while this area is used by kernel, - * so move it to currently unused area. - */ - if (cpuinfo_arc700[cpu].dccm.sz) - write_aux_reg(ARC_REG_AUX_DCCM, ARC_CCM_UNUSED_ADDR); -} #define ARC_PERIPHERAL_BASE 0xf0000000 #define CREG_BASE (ARC_PERIPHERAL_BASE + 0x1000) @@ -339,5 +323,4 @@ static const char *hsdk_compat[] __initconst = { MACHINE_START(SIMULATION, "hsdk") .dt_compat = hsdk_compat, .init_early = hsdk_init_early, - .init_per_cpu = hsdk_init_per_cpu, MACHINE_END diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index 2e04ec5b5446..caa27322a0ab 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -1472,6 +1472,9 @@ ENTRY(efi_enter_kernel) @ issued from HYP mode take us to the correct handler code. We @ will disable the MMU before jumping to the kernel proper. @ + ARM( bic r1, r1, #(1 << 30) ) @ clear HSCTLR.TE + THUMB( orr r1, r1, #(1 << 30) ) @ set HSCTLR.TE + mcr p15, 4, r1, c1, c0, 0 adr r0, __hyp_reentry_vectors mcr p15, 4, r0, c12, c0, 0 @ set HYP vector base (HVBAR) isb diff --git a/arch/arm/boot/dts/exynos4412-odroid-common.dtsi b/arch/arm/boot/dts/exynos4412-odroid-common.dtsi index ab291cec650a..2983e91bc7dd 100644 --- a/arch/arm/boot/dts/exynos4412-odroid-common.dtsi +++ b/arch/arm/boot/dts/exynos4412-odroid-common.dtsi @@ -122,7 +122,6 @@ }; &clock { - clocks = <&clock CLK_XUSBXTI>; assigned-clocks = <&clock CLK_FOUT_EPLL>; assigned-clock-rates = <45158401>; }; diff --git a/arch/arm/boot/dts/imx50-evk.dts b/arch/arm/boot/dts/imx50-evk.dts index 878e89c20190..4ea5c23f181b 100644 --- a/arch/arm/boot/dts/imx50-evk.dts +++ b/arch/arm/boot/dts/imx50-evk.dts @@ -59,7 +59,7 @@ MX50_PAD_CSPI_MISO__CSPI_MISO 0x00 MX50_PAD_CSPI_MOSI__CSPI_MOSI 0x00 MX50_PAD_CSPI_SS0__GPIO4_11 0xc4 - MX50_PAD_ECSPI1_MOSI__CSPI_SS1 0xf4 + MX50_PAD_ECSPI1_MOSI__GPIO4_13 0x84 >; }; diff --git a/arch/arm/boot/dts/imx6q-prti6q.dts b/arch/arm/boot/dts/imx6q-prti6q.dts index d112b50f8c5d..b4605edfd2ab 100644 --- a/arch/arm/boot/dts/imx6q-prti6q.dts +++ b/arch/arm/boot/dts/imx6q-prti6q.dts @@ -213,8 +213,8 @@ #size-cells = <0>; /* Microchip KSZ9031RNX PHY */ - rgmii_phy: ethernet-phy@4 { - reg = <4>; + rgmii_phy: ethernet-phy@0 { + reg = <0>; interrupts-extended = <&gpio1 28 IRQ_TYPE_LEVEL_LOW>; reset-gpios = <&gpio1 25 GPIO_ACTIVE_LOW>; reset-assert-us = <10000>; diff --git a/arch/arm/boot/dts/imx6qdl-udoo.dtsi b/arch/arm/boot/dts/imx6qdl-udoo.dtsi index 828dd20cd27d..d07d8f83456d 100644 --- a/arch/arm/boot/dts/imx6qdl-udoo.dtsi +++ b/arch/arm/boot/dts/imx6qdl-udoo.dtsi @@ -98,7 +98,7 @@ &fec { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enet>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi index 5dff24e39af8..8456f172d4b1 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi @@ -46,6 +46,16 @@ linux,code = <KEY_A>; gpios = <&gpiof 3 GPIO_ACTIVE_LOW>; }; + + /* + * The EXTi IRQ line 0 is shared with PMIC, + * so mark this as polled GPIO key. + */ + button-2 { + label = "TA3-GPIO-C"; + linux,code = <KEY_C>; + gpios = <&gpiog 0 GPIO_ACTIVE_LOW>; + }; }; gpio-keys { @@ -59,13 +69,6 @@ wakeup-source; }; - button-2 { - label = "TA3-GPIO-C"; - linux,code = <KEY_C>; - gpios = <&gpioi 11 GPIO_ACTIVE_LOW>; - wakeup-source; - }; - button-3 { label = "TA4-GPIO-D"; linux,code = <KEY_D>; @@ -79,7 +82,7 @@ led-0 { label = "green:led5"; - gpios = <&gpiog 2 GPIO_ACTIVE_HIGH>; + gpios = <&gpioc 6 GPIO_ACTIVE_HIGH>; default-state = "off"; }; diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi index b4b52cf634af..f796a6150313 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi @@ -68,6 +68,7 @@ gpio = <&gpiog 3 GPIO_ACTIVE_LOW>; regulator-always-on; regulator-boot-on; + vin-supply = <&vdd>; }; }; @@ -202,6 +203,7 @@ vdda: ldo1 { regulator-name = "vdda"; + regulator-always-on; regulator-min-microvolt = <2900000>; regulator-max-microvolt = <2900000>; interrupts = <IT_CURLIM_LDO1 0>; diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi index 04fbb324a541..803eb8bc9c85 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi @@ -21,6 +21,10 @@ }; }; +&dts { + status = "okay"; +}; + &i2c4 { pinctrl-names = "default"; pinctrl-0 = <&i2c4_pins_a>; diff --git a/arch/arm/boot/dts/sun6i-a31-hummingbird.dts b/arch/arm/boot/dts/sun6i-a31-hummingbird.dts index 049e6ab3cf56..73de34ae37fd 100644 --- a/arch/arm/boot/dts/sun6i-a31-hummingbird.dts +++ b/arch/arm/boot/dts/sun6i-a31-hummingbird.dts @@ -154,7 +154,7 @@ pinctrl-names = "default"; pinctrl-0 = <&gmac_rgmii_pins>; phy-handle = <&phy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; diff --git a/arch/arm/boot/dts/sun7i-a20-bananapi-m1-plus.dts b/arch/arm/boot/dts/sun7i-a20-bananapi-m1-plus.dts index 32d5d45a35c0..8945dbb114a2 100644 --- a/arch/arm/boot/dts/sun7i-a20-bananapi-m1-plus.dts +++ b/arch/arm/boot/dts/sun7i-a20-bananapi-m1-plus.dts @@ -130,7 +130,7 @@ pinctrl-names = "default"; pinctrl-0 = <&gmac_rgmii_pins>; phy-handle = <&phy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-supply = <®_gmac_3v3>; status = "okay"; }; diff --git a/arch/arm/boot/dts/sun7i-a20-cubietruck.dts b/arch/arm/boot/dts/sun7i-a20-cubietruck.dts index 8c8dee6ea461..9109ca0919ad 100644 --- a/arch/arm/boot/dts/sun7i-a20-cubietruck.dts +++ b/arch/arm/boot/dts/sun7i-a20-cubietruck.dts @@ -151,7 +151,7 @@ pinctrl-names = "default"; pinctrl-0 = <&gmac_rgmii_pins>; phy-handle = <&phy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; diff --git a/arch/arm/boot/dts/sun8i-a83t-bananapi-m3.dts b/arch/arm/boot/dts/sun8i-a83t-bananapi-m3.dts index 9d34eabba121..431f70234d36 100644 --- a/arch/arm/boot/dts/sun8i-a83t-bananapi-m3.dts +++ b/arch/arm/boot/dts/sun8i-a83t-bananapi-m3.dts @@ -131,7 +131,7 @@ pinctrl-0 = <&emac_rgmii_pins>; phy-supply = <®_sw>; phy-handle = <&rgmii_phy>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; allwinner,rx-delay-ps = <700>; allwinner,tx-delay-ps = <700>; status = "okay"; diff --git a/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts b/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts index d9be511f054f..d8326a5c681d 100644 --- a/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts +++ b/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts @@ -183,7 +183,7 @@ pinctrl-0 = <&emac_rgmii_pins>; phy-supply = <®_dldo4>; phy-handle = <&rgmii_phy>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; diff --git a/arch/arm/boot/dts/sun8i-h3-orangepi-pc-plus.dts b/arch/arm/boot/dts/sun8i-h3-orangepi-pc-plus.dts index 71fb73208939..babf4cf1b2f6 100644 --- a/arch/arm/boot/dts/sun8i-h3-orangepi-pc-plus.dts +++ b/arch/arm/boot/dts/sun8i-h3-orangepi-pc-plus.dts @@ -53,11 +53,6 @@ }; }; -&emac { - /* LEDs changed to active high on the plus */ - /delete-property/ allwinner,leds-active-low; -}; - &mmc1 { vmmc-supply = <®_vcc3v3>; bus-width = <4>; diff --git a/arch/arm/boot/dts/sun8i-h3-orangepi-plus2e.dts b/arch/arm/boot/dts/sun8i-h3-orangepi-plus2e.dts index 6dbf7b2e0c13..b6ca45d18e51 100644 --- a/arch/arm/boot/dts/sun8i-h3-orangepi-plus2e.dts +++ b/arch/arm/boot/dts/sun8i-h3-orangepi-plus2e.dts @@ -67,7 +67,7 @@ pinctrl-0 = <&emac_rgmii_pins>; phy-supply = <®_gmac_3v3>; phy-handle = <&ext_rgmii_phy>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; diff --git a/arch/arm/boot/dts/sun8i-r40-bananapi-m2-ultra.dts b/arch/arm/boot/dts/sun8i-r40-bananapi-m2-ultra.dts index 2fc62ef0cb3e..a6a1087a0c9b 100644 --- a/arch/arm/boot/dts/sun8i-r40-bananapi-m2-ultra.dts +++ b/arch/arm/boot/dts/sun8i-r40-bananapi-m2-ultra.dts @@ -129,7 +129,7 @@ pinctrl-names = "default"; pinctrl-0 = <&gmac_rgmii_pins>; phy-handle = <&phy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-supply = <®_dc1sw>; status = "okay"; }; diff --git a/arch/arm/boot/dts/sun9i-a80-cubieboard4.dts b/arch/arm/boot/dts/sun9i-a80-cubieboard4.dts index d3b337b043a1..484b93df20cb 100644 --- a/arch/arm/boot/dts/sun9i-a80-cubieboard4.dts +++ b/arch/arm/boot/dts/sun9i-a80-cubieboard4.dts @@ -129,7 +129,7 @@ pinctrl-names = "default"; pinctrl-0 = <&gmac_rgmii_pins>; phy-handle = <&phy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-supply = <®_cldo1>; status = "okay"; }; diff --git a/arch/arm/boot/dts/sun9i-a80-optimus.dts b/arch/arm/boot/dts/sun9i-a80-optimus.dts index bbc6335e5631..5c3580d712e4 100644 --- a/arch/arm/boot/dts/sun9i-a80-optimus.dts +++ b/arch/arm/boot/dts/sun9i-a80-optimus.dts @@ -124,7 +124,7 @@ pinctrl-names = "default"; pinctrl-0 = <&gmac_rgmii_pins>; phy-handle = <&phy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-supply = <®_cldo1>; status = "okay"; }; diff --git a/arch/arm/boot/dts/sunxi-bananapi-m2-plus.dtsi b/arch/arm/boot/dts/sunxi-bananapi-m2-plus.dtsi index 39263e74fbb5..8e5cb3b3fd68 100644 --- a/arch/arm/boot/dts/sunxi-bananapi-m2-plus.dtsi +++ b/arch/arm/boot/dts/sunxi-bananapi-m2-plus.dtsi @@ -126,7 +126,7 @@ pinctrl-0 = <&emac_rgmii_pins>; phy-supply = <®_gmac_3v3>; phy-handle = <&ext_rgmii_phy>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; diff --git a/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts b/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts index e500911ce0a5..6f1e0f0d4f0a 100644 --- a/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts +++ b/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts @@ -406,6 +406,9 @@ }; }; +&mdio1 { + clock-frequency = <5000000>; +}; &iomuxc { pinctrl_gpio_e6185_eeprom_sel: pinctrl-gpio-e6185-eeprom-spi0 { diff --git a/arch/arm/include/asm/kprobes.h b/arch/arm/include/asm/kprobes.h index 213607a1f45c..e26a278d301a 100644 --- a/arch/arm/include/asm/kprobes.h +++ b/arch/arm/include/asm/kprobes.h @@ -44,20 +44,20 @@ int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *data); /* optinsn template addresses */ -extern __visible kprobe_opcode_t optprobe_template_entry; -extern __visible kprobe_opcode_t optprobe_template_val; -extern __visible kprobe_opcode_t optprobe_template_call; -extern __visible kprobe_opcode_t optprobe_template_end; -extern __visible kprobe_opcode_t optprobe_template_sub_sp; -extern __visible kprobe_opcode_t optprobe_template_add_sp; -extern __visible kprobe_opcode_t optprobe_template_restore_begin; -extern __visible kprobe_opcode_t optprobe_template_restore_orig_insn; -extern __visible kprobe_opcode_t optprobe_template_restore_end; +extern __visible kprobe_opcode_t optprobe_template_entry[]; +extern __visible kprobe_opcode_t optprobe_template_val[]; +extern __visible kprobe_opcode_t optprobe_template_call[]; +extern __visible kprobe_opcode_t optprobe_template_end[]; +extern __visible kprobe_opcode_t optprobe_template_sub_sp[]; +extern __visible kprobe_opcode_t optprobe_template_add_sp[]; +extern __visible kprobe_opcode_t optprobe_template_restore_begin[]; +extern __visible kprobe_opcode_t optprobe_template_restore_orig_insn[]; +extern __visible kprobe_opcode_t optprobe_template_restore_end[]; #define MAX_OPTIMIZED_LENGTH 4 #define MAX_OPTINSN_SIZE \ - ((unsigned long)&optprobe_template_end - \ - (unsigned long)&optprobe_template_entry) + ((unsigned long)optprobe_template_end - \ + (unsigned long)optprobe_template_entry) #define RELATIVEJUMP_SIZE 4 struct arch_optimized_insn { diff --git a/arch/arm/kernel/perf_regs.c b/arch/arm/kernel/perf_regs.c index 05fe92aa7d98..0529f90395c9 100644 --- a/arch/arm/kernel/perf_regs.c +++ b/arch/arm/kernel/perf_regs.c @@ -32,8 +32,7 @@ u64 perf_reg_abi(struct task_struct *task) } void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { regs_user->regs = task_pt_regs(current); regs_user->abi = perf_reg_abi(current); diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index d57112a276f5..c23dbf8bebee 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -354,8 +354,8 @@ static void __init free_highpages(void) /* set highmem page free */ for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &range_start, &range_end, NULL) { - unsigned long start = PHYS_PFN(range_start); - unsigned long end = PHYS_PFN(range_end); + unsigned long start = PFN_UP(range_start); + unsigned long end = PFN_DOWN(range_end); /* Ignore complete lowmem entries */ if (end <= max_low) diff --git a/arch/arm/probes/kprobes/opt-arm.c b/arch/arm/probes/kprobes/opt-arm.c index 7a449df0b359..c78180172120 100644 --- a/arch/arm/probes/kprobes/opt-arm.c +++ b/arch/arm/probes/kprobes/opt-arm.c @@ -85,21 +85,21 @@ asm ( "optprobe_template_end:\n"); #define TMPL_VAL_IDX \ - ((unsigned long *)&optprobe_template_val - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_val - (unsigned long *)optprobe_template_entry) #define TMPL_CALL_IDX \ - ((unsigned long *)&optprobe_template_call - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_call - (unsigned long *)optprobe_template_entry) #define TMPL_END_IDX \ - ((unsigned long *)&optprobe_template_end - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_end - (unsigned long *)optprobe_template_entry) #define TMPL_ADD_SP \ - ((unsigned long *)&optprobe_template_add_sp - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_add_sp - (unsigned long *)optprobe_template_entry) #define TMPL_SUB_SP \ - ((unsigned long *)&optprobe_template_sub_sp - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_sub_sp - (unsigned long *)optprobe_template_entry) #define TMPL_RESTORE_BEGIN \ - ((unsigned long *)&optprobe_template_restore_begin - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_restore_begin - (unsigned long *)optprobe_template_entry) #define TMPL_RESTORE_ORIGN_INSN \ - ((unsigned long *)&optprobe_template_restore_orig_insn - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_restore_orig_insn - (unsigned long *)optprobe_template_entry) #define TMPL_RESTORE_END \ - ((unsigned long *)&optprobe_template_restore_end - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_restore_end - (unsigned long *)optprobe_template_entry) /* * ARM can always optimize an instruction when using ARM ISA, except @@ -234,7 +234,7 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, struct kprobe *or } /* Copy arch-dep-instance from template. */ - memcpy(code, (unsigned long *)&optprobe_template_entry, + memcpy(code, (unsigned long *)optprobe_template_entry, TMPL_END_IDX * sizeof(kprobe_opcode_t)); /* Adjust buffer according to instruction. */ diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 1d466addb078..1515f6f153a0 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1002,7 +1002,7 @@ config NUMA config NODES_SHIFT int "Maximum NUMA Nodes (as a power of 2)" range 1 10 - default "2" + default "4" depends on NEED_MULTIPLE_NODES help Specify the maximum number of NUMA Nodes available on the target diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts index 3ea5182ca489..e5e840b9fbb4 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts @@ -105,7 +105,7 @@ &emac { pinctrl-names = "default"; pinctrl-0 = <&rgmii_pins>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-handle = <&ext_rgmii_phy>; phy-supply = <®_dc1sw>; status = "okay"; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts index d894ec5fa8a1..70e31743f0ba 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts @@ -120,7 +120,7 @@ &emac { pinctrl-names = "default"; pinctrl-0 = <&rgmii_pins>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-handle = <&ext_rgmii_phy>; phy-supply = <®_gmac_3v3>; status = "okay"; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts index b26181cf9095..b54099b654c8 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts @@ -13,7 +13,7 @@ &emac { pinctrl-names = "default"; pinctrl-0 = <&rgmii_pins>; - phy-mode = "rgmii"; + phy-mode = "rgmii-txid"; phy-handle = <&ext_rgmii_phy>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-pinetab.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-pinetab.dts index 3ab0f0347bc9..0494bfaf2ffa 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-pinetab.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-pinetab.dts @@ -122,9 +122,6 @@ status = "okay"; port { - #address-cells = <1>; - #size-cells = <0>; - csi_ep: endpoint { remote-endpoint = <&ov5640_ep>; bus-width = <8>; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-libretech-all-h5-cc.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-libretech-all-h5-cc.dts index df1b9263ad0e..6e30a564c87f 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h5-libretech-all-h5-cc.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-libretech-all-h5-cc.dts @@ -36,7 +36,7 @@ pinctrl-0 = <&emac_rgmii_pins>; phy-supply = <®_gmac_3v3>; phy-handle = <&ext_rgmii_phy>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; /delete-property/ allwinner,leds-active-low; status = "okay"; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts index 7d7aad18f078..8bf2db9dcbda 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts @@ -123,7 +123,7 @@ pinctrl-0 = <&emac_rgmii_pins>; phy-supply = <®_gmac_3v3>; phy-handle = <&ext_rgmii_phy>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts index cb44bfa5981f..33ab44072e6d 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts @@ -124,7 +124,7 @@ pinctrl-0 = <&emac_rgmii_pins>; phy-supply = <®_gmac_3v3>; phy-handle = <&ext_rgmii_phy>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts b/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts index 3f7ceeb1a767..7c9dbde645b5 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts @@ -97,7 +97,7 @@ &emac { pinctrl-names = "default"; pinctrl-0 = <&ext_rgmii_pins>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-handle = <&ext_rgmii_phy>; phy-supply = <®_aldo2>; status = "okay"; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts b/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts index af85b2074867..961732c52aa0 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts @@ -100,7 +100,7 @@ &emac { pinctrl-names = "default"; pinctrl-0 = <&ext_rgmii_pins>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-handle = <&ext_rgmii_phy>; phy-supply = <®_gmac_3v3>; allwinner,rx-delay-ps = <200>; diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts index feadd21bc0dc..46e558ab7729 100644 --- a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts +++ b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts @@ -159,7 +159,7 @@ flash@0 { #address-cells = <1>; #size-cells = <1>; - compatible = "n25q00a"; + compatible = "micron,mt25qu02g", "jedec,spi-nor"; reg = <0>; spi-max-frequency = <100000000>; diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts index c07966740e14..f9b4a39683cf 100644 --- a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts +++ b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts @@ -192,7 +192,7 @@ flash@0 { #address-cells = <1>; #size-cells = <1>; - compatible = "n25q00a"; + compatible = "micron,mt25qu02g", "jedec,spi-nor"; reg = <0>; spi-max-frequency = <100000000>; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28.dts b/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28.dts index f46eb47cfa4d..8161dd237971 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28.dts @@ -75,6 +75,7 @@ &enetc_port0 { phy-handle = <&phy0>; phy-connection-type = "sgmii"; + managed = "in-band-status"; status = "okay"; mdio { diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi index 73e4f9466887..7a6fb7e1fb82 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi @@ -1012,6 +1012,7 @@ compatible = "fsl,ls1028a-rcpm", "fsl,qoriq-rcpm-2.1+"; reg = <0x0 0x1e34040 0x0 0x1c>; #fsl,rcpm-wakeup-cells = <7>; + little-endian; }; ftm_alarm0: timer@2800000 { diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi index ff5805206a28..692d8f4a206d 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi @@ -805,6 +805,7 @@ compatible = "fsl,ls1088a-rcpm", "fsl,qoriq-rcpm-2.1+"; reg = <0x0 0x1e34040 0x0 0x18>; #fsl,rcpm-wakeup-cells = <6>; + little-endian; }; ftm_alarm0: timer@2800000 { diff --git a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi index bf72918fe545..e7abb74bd816 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi @@ -892,6 +892,7 @@ compatible = "fsl,ls208xa-rcpm", "fsl,qoriq-rcpm-2.1+"; reg = <0x0 0x1e34040 0x0 0x18>; #fsl,rcpm-wakeup-cells = <6>; + little-endian; }; ftm_alarm0: timer@2800000 { diff --git a/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi index 6de86a4f0ec4..b88c3c99b007 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi @@ -72,6 +72,7 @@ pmic@4b { compatible = "rohm,bd71847"; reg = <0x4b>; + pinctrl-names = "default"; pinctrl-0 = <&pinctrl_pmic>; interrupt-parent = <&gpio1>; interrupts = <3 IRQ_TYPE_LEVEL_LOW>; @@ -210,6 +211,7 @@ host-wakeup-gpios = <&gpio2 8 GPIO_ACTIVE_HIGH>; device-wakeup-gpios = <&gpio2 7 GPIO_ACTIVE_HIGH>; clocks = <&osc_32k>; + max-speed = <4000000>; clock-names = "extclk"; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi index f305a530ff6f..521eb3a5a12e 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi @@ -121,6 +121,7 @@ pmic@4b { compatible = "rohm,bd71847"; reg = <0x4b>; + pinctrl-names = "default"; pinctrl-0 = <&pinctrl_pmic>; interrupt-parent = <&gpio1>; interrupts = <3 IRQ_TYPE_LEVEL_LOW>; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi index 4107fe914d08..49082529764f 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi @@ -135,13 +135,10 @@ pmic@4b { compatible = "rohm,bd71847"; reg = <0x4b>; + pinctrl-names = "default"; pinctrl-0 = <&pinctrl_pmic>; interrupt-parent = <&gpio2>; - /* - * The interrupt is not correct. It should be level low, - * however with internal pull up this causes IRQ storm. - */ - interrupts = <8 IRQ_TYPE_EDGE_RISING>; + interrupts = <8 IRQ_TYPE_LEVEL_LOW>; rohm,reset-snvs-powered; #clock-cells = <0>; @@ -398,7 +395,7 @@ pinctrl_pmic: pmicirqgrp { fsl,pins = < - MX8MM_IOMUXC_SD1_DATA6_GPIO2_IO8 0x41 + MX8MM_IOMUXC_SD1_DATA6_GPIO2_IO8 0x141 >; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm.dtsi b/arch/arm64/boot/dts/freescale/imx8mm.dtsi index b83f400def8b..05ee062548e4 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm.dtsi @@ -129,7 +129,7 @@ opp-1600000000 { opp-hz = /bits/ 64 <1600000000>; - opp-microvolt = <900000>; + opp-microvolt = <950000>; opp-supported-hw = <0xc>, <0x7>; clock-latency-ns = <150000>; opp-suspend; diff --git a/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts b/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts index 46e76cf32b2f..7dfee715a2c4 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts @@ -53,6 +53,7 @@ pmic@4b { compatible = "rohm,bd71847"; reg = <0x4b>; + pinctrl-names = "default"; pinctrl-0 = <&pinctrl_pmic>; interrupt-parent = <&gpio1>; interrupts = <3 IRQ_TYPE_LEVEL_LOW>; diff --git a/arch/arm64/boot/dts/freescale/imx8mn-evk.dts b/arch/arm64/boot/dts/freescale/imx8mn-evk.dts index 707d8486b4d8..8311b95dee49 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx8mn-evk.dts @@ -18,6 +18,7 @@ pmic: pmic@25 { compatible = "nxp,pca9450b"; reg = <0x25>; + pinctrl-names = "default"; pinctrl-0 = <&pinctrl_pmic>; interrupt-parent = <&gpio1>; interrupts = <3 IRQ_TYPE_LEVEL_LOW>; diff --git a/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi index a2d0190921e4..7f356edf9f91 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi @@ -116,13 +116,10 @@ pmic@4b { compatible = "rohm,bd71847"; reg = <0x4b>; + pinctrl-names = "default"; pinctrl-0 = <&pinctrl_pmic>; interrupt-parent = <&gpio2>; - /* - * The interrupt is not correct. It should be level low, - * however with internal pull up this causes IRQ storm. - */ - interrupts = <8 IRQ_TYPE_EDGE_RISING>; + interrupts = <8 IRQ_TYPE_LEVEL_LOW>; rohm,reset-snvs-powered; regulators { @@ -388,7 +385,7 @@ pinctrl_pmic: pmicirqgrp { fsl,pins = < - MX8MN_IOMUXC_SD1_DATA6_GPIO2_IO8 0x101 + MX8MN_IOMUXC_SD1_DATA6_GPIO2_IO8 0x141 >; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mn.dtsi b/arch/arm64/boot/dts/freescale/imx8mn.dtsi index 746faf1cf2fb..16c7202885d7 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn.dtsi @@ -790,28 +790,6 @@ #index-cells = <1>; reg = <0x32e40200 0x200>; }; - - usbotg2: usb@32e50000 { - compatible = "fsl,imx8mn-usb", "fsl,imx7d-usb"; - reg = <0x32e50000 0x200>; - interrupts = <GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&clk IMX8MN_CLK_USB1_CTRL_ROOT>; - clock-names = "usb1_ctrl_root_clk"; - assigned-clocks = <&clk IMX8MN_CLK_USB_BUS>, - <&clk IMX8MN_CLK_USB_CORE_REF>; - assigned-clock-parents = <&clk IMX8MN_SYS_PLL2_500M>, - <&clk IMX8MN_SYS_PLL1_100M>; - fsl,usbphy = <&usbphynop2>; - fsl,usbmisc = <&usbmisc2 0>; - status = "disabled"; - }; - - usbmisc2: usbmisc@32e50200 { - compatible = "fsl,imx8mn-usbmisc", "fsl,imx7d-usbmisc"; - #index-cells = <1>; - reg = <0x32e50200 0x200>; - }; - }; dma_apbh: dma-controller@33000000 { @@ -876,12 +854,4 @@ assigned-clock-parents = <&clk IMX8MN_SYS_PLL1_100M>; clock-names = "main_clk"; }; - - usbphynop2: usbphynop2 { - compatible = "usb-nop-xceiv"; - clocks = <&clk IMX8MN_CLK_USB_PHY_REF>; - assigned-clocks = <&clk IMX8MN_CLK_USB_PHY_REF>; - assigned-clock-parents = <&clk IMX8MN_SYS_PLL1_100M>; - clock-names = "main_clk"; - }; }; diff --git a/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi b/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi index 8bc6caa9167d..4338db14c5da 100644 --- a/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi +++ b/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi @@ -19,6 +19,7 @@ fman0: fman@1a00000 { clock-names = "fmanclk"; fsl,qman-channel-range = <0x800 0x10>; ptimer-handle = <&ptp_timer0>; + dma-coherent; muram@0 { compatible = "fsl,fman-muram"; diff --git a/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts b/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts index 96c50d48289d..a7a83f29f00b 100644 --- a/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts +++ b/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts @@ -110,7 +110,7 @@ flash@0 { #address-cells = <1>; #size-cells = <1>; - compatible = "mt25qu02g"; + compatible = "micron,mt25qu02g", "jedec,spi-nor"; reg = <0>; spi-max-frequency = <100000000>; diff --git a/arch/arm64/boot/dts/renesas/r8a774e1.dtsi b/arch/arm64/boot/dts/renesas/r8a774e1.dtsi index 9cbf963aa068..c29643442e91 100644 --- a/arch/arm64/boot/dts/renesas/r8a774e1.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a774e1.dtsi @@ -28,6 +28,12 @@ clock-frequency = <0>; }; + audio_clk_b: audio_clk_b { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <0>; + }; + audio_clk_c: audio_clk_c { compatible = "fixed-clock"; #clock-cells = <0>; diff --git a/arch/arm64/include/asm/brk-imm.h b/arch/arm64/include/asm/brk-imm.h index e3d47b52161d..ec7720dbe2c8 100644 --- a/arch/arm64/include/asm/brk-imm.h +++ b/arch/arm64/include/asm/brk-imm.h @@ -10,6 +10,7 @@ * #imm16 values used for BRK instruction generation * 0x004: for installing kprobes * 0x005: for installing uprobes + * 0x006: for kprobe software single-step * Allowed values for kgdb are 0x400 - 0x7ff * 0x100: for triggering a fault on purpose (reserved) * 0x400: for dynamic BRK instruction @@ -19,6 +20,7 @@ */ #define KPROBES_BRK_IMM 0x004 #define UPROBES_BRK_IMM 0x005 +#define KPROBES_BRK_SS_IMM 0x006 #define FAULT_BRK_IMM 0x100 #define KGDB_DYN_DBG_BRK_IMM 0x400 #define KGDB_COMPILED_DBG_BRK_IMM 0x401 diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 97244d4feca9..da250e4741bd 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -268,6 +268,8 @@ extern struct arm64_ftr_reg arm64_ftr_reg_ctrel0; /* * CPU feature detected at boot time based on feature of one or more CPUs. * All possible conflicts for a late CPU are ignored. + * NOTE: this means that a late CPU with the feature will *not* cause the + * capability to be advertised by cpus_have_*cap()! */ #define ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE \ (ARM64_CPUCAP_SCOPE_LOCAL_CPU | \ diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 9e2e9a63c7b6..ef5b040dee44 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -86,6 +86,8 @@ #define QCOM_CPU_PART_FALKOR_V1 0x800 #define QCOM_CPU_PART_FALKOR 0xC00 #define QCOM_CPU_PART_KRYO 0x200 +#define QCOM_CPU_PART_KRYO_2XX_GOLD 0x800 +#define QCOM_CPU_PART_KRYO_2XX_SILVER 0x801 #define QCOM_CPU_PART_KRYO_3XX_SILVER 0x803 #define QCOM_CPU_PART_KRYO_4XX_GOLD 0x804 #define QCOM_CPU_PART_KRYO_4XX_SILVER 0x805 @@ -116,6 +118,8 @@ #define MIDR_QCOM_FALKOR_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR_V1) #define MIDR_QCOM_FALKOR MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR) #define MIDR_QCOM_KRYO MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO) +#define MIDR_QCOM_KRYO_2XX_GOLD MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_2XX_GOLD) +#define MIDR_QCOM_KRYO_2XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_2XX_SILVER) #define MIDR_QCOM_KRYO_3XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_3XX_SILVER) #define MIDR_QCOM_KRYO_4XX_GOLD MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_GOLD) #define MIDR_QCOM_KRYO_4XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_SILVER) diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h index 0b298f48f5bf..657c921fd784 100644 --- a/arch/arm64/include/asm/debug-monitors.h +++ b/arch/arm64/include/asm/debug-monitors.h @@ -53,6 +53,7 @@ /* kprobes BRK opcodes with ESR encoding */ #define BRK64_OPCODE_KPROBES (AARCH64_BREAK_MON | (KPROBES_BRK_IMM << 5)) +#define BRK64_OPCODE_KPROBES_SS (AARCH64_BREAK_MON | (KPROBES_BRK_SS_IMM << 5)) /* uprobes BRK opcodes with ESR encoding */ #define BRK64_OPCODE_UPROBES (AARCH64_BREAK_MON | (UPROBES_BRK_IMM << 5)) diff --git a/arch/arm64/include/asm/kprobes.h b/arch/arm64/include/asm/kprobes.h index 97e511d645a2..8699ce30f587 100644 --- a/arch/arm64/include/asm/kprobes.h +++ b/arch/arm64/include/asm/kprobes.h @@ -16,7 +16,7 @@ #include <linux/percpu.h> #define __ARCH_WANT_KPROBES_INSN_SLOT -#define MAX_INSN_SIZE 1 +#define MAX_INSN_SIZE 2 #define flush_insn_slot(p) do { } while (0) #define kretprobe_blacklist_size 0 diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 781d029b8aa8..0cd9f0f75c13 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -118,6 +118,8 @@ struct kvm_arch { */ unsigned long *pmu_filter; unsigned int pmuver; + + u8 pfr0_csv2; }; struct kvm_vcpu_fault_info { diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 174817ba119c..e2ef4c2edf06 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -372,6 +372,8 @@ #define SYS_CONTEXTIDR_EL1 sys_reg(3, 0, 13, 0, 1) #define SYS_TPIDR_EL1 sys_reg(3, 0, 13, 0, 4) +#define SYS_SCXTNUM_EL1 sys_reg(3, 0, 13, 0, 7) + #define SYS_CNTKCTL_EL1 sys_reg(3, 0, 14, 1, 0) #define SYS_CCSIDR_EL1 sys_reg(3, 1, 0, 0, 0) @@ -404,6 +406,8 @@ #define SYS_TPIDR_EL0 sys_reg(3, 3, 13, 0, 2) #define SYS_TPIDRRO_EL0 sys_reg(3, 3, 13, 0, 3) +#define SYS_SCXTNUM_EL0 sys_reg(3, 3, 13, 0, 7) + /* Definitions for system register interface to AMU for ARMv8.4 onwards */ #define SYS_AM_EL0(crm, op2) sys_reg(3, 3, 13, (crm), (op2)) #define SYS_AMCR_EL0 SYS_AM_EL0(2, 0) diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 61314fd70f13..cafaf0da05b7 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -299,6 +299,8 @@ static const struct midr_range erratum_845719_list[] = { MIDR_REV_RANGE(MIDR_CORTEX_A53, 0, 0, 4), /* Brahma-B53 r0p[0] */ MIDR_REV(MIDR_BRAHMA_B53, 0, 0), + /* Kryo2XX Silver rAp4 */ + MIDR_REV(MIDR_QCOM_KRYO_2XX_SILVER, 0xa, 0x4), {}, }; #endif diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index dcc165b3fc04..6f36c4f62f69 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1337,6 +1337,8 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry, MIDR_ALL_VERSIONS(MIDR_CORTEX_A73), MIDR_ALL_VERSIONS(MIDR_HISI_TSV110), MIDR_ALL_VERSIONS(MIDR_NVIDIA_CARMEL), + MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_2XX_GOLD), + MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_2XX_SILVER), MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER), MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER), { /* sentinel */ } diff --git a/arch/arm64/kernel/kexec_image.c b/arch/arm64/kernel/kexec_image.c index af9987c154ca..9ec34690e255 100644 --- a/arch/arm64/kernel/kexec_image.c +++ b/arch/arm64/kernel/kexec_image.c @@ -43,7 +43,7 @@ static void *image_load(struct kimage *image, u64 flags, value; bool be_image, be_kernel; struct kexec_buf kbuf; - unsigned long text_offset; + unsigned long text_offset, kernel_segment_number; struct kexec_segment *kernel_segment; int ret; @@ -88,11 +88,37 @@ static void *image_load(struct kimage *image, /* Adjust kernel segment with TEXT_OFFSET */ kbuf.memsz += text_offset; - ret = kexec_add_buffer(&kbuf); - if (ret) + kernel_segment_number = image->nr_segments; + + /* + * The location of the kernel segment may make it impossible to satisfy + * the other segment requirements, so we try repeatedly to find a + * location that will work. + */ + while ((ret = kexec_add_buffer(&kbuf)) == 0) { + /* Try to load additional data */ + kernel_segment = &image->segment[kernel_segment_number]; + ret = load_other_segments(image, kernel_segment->mem, + kernel_segment->memsz, initrd, + initrd_len, cmdline); + if (!ret) + break; + + /* + * We couldn't find space for the other segments; erase the + * kernel segment and try the next available hole. + */ + image->nr_segments -= 1; + kbuf.buf_min = kernel_segment->mem + kernel_segment->memsz; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; + } + + if (ret) { + pr_err("Could not find any suitable kernel location!"); return ERR_PTR(ret); + } - kernel_segment = &image->segment[image->nr_segments - 1]; + kernel_segment = &image->segment[kernel_segment_number]; kernel_segment->mem += text_offset; kernel_segment->memsz -= text_offset; image->start = kernel_segment->mem; @@ -101,12 +127,7 @@ static void *image_load(struct kimage *image, kernel_segment->mem, kbuf.bufsz, kernel_segment->memsz); - /* Load additional data */ - ret = load_other_segments(image, - kernel_segment->mem, kernel_segment->memsz, - initrd, initrd_len, cmdline); - - return ERR_PTR(ret); + return NULL; } #ifdef CONFIG_KEXEC_IMAGE_VERIFY_SIG diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c index 5b0e67b93cdc..03210f644790 100644 --- a/arch/arm64/kernel/machine_kexec_file.c +++ b/arch/arm64/kernel/machine_kexec_file.c @@ -240,6 +240,11 @@ static int prepare_elf_headers(void **addr, unsigned long *sz) return ret; } +/* + * Tries to add the initrd and DTB to the image. If it is not possible to find + * valid locations, this function will undo changes to the image and return non + * zero. + */ int load_other_segments(struct kimage *image, unsigned long kernel_load_addr, unsigned long kernel_size, @@ -248,7 +253,8 @@ int load_other_segments(struct kimage *image, { struct kexec_buf kbuf; void *headers, *dtb = NULL; - unsigned long headers_sz, initrd_load_addr = 0, dtb_len; + unsigned long headers_sz, initrd_load_addr = 0, dtb_len, + orig_segments = image->nr_segments; int ret = 0; kbuf.image = image; @@ -334,6 +340,7 @@ int load_other_segments(struct kimage *image, return 0; out_err: + image->nr_segments = orig_segments; vfree(dtb); return ret; } diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c index 94e8718e7229..f6f58e6265df 100644 --- a/arch/arm64/kernel/perf_regs.c +++ b/arch/arm64/kernel/perf_regs.c @@ -73,8 +73,7 @@ u64 perf_reg_abi(struct task_struct *task) } void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { regs_user->regs = task_pt_regs(current); regs_user->abi = perf_reg_abi(current); diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index deba738142ed..f11a1a1f7026 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -36,25 +36,16 @@ DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); static void __kprobes post_kprobe_handler(struct kprobe_ctlblk *, struct pt_regs *); -static int __kprobes patch_text(kprobe_opcode_t *addr, u32 opcode) -{ - void *addrs[1]; - u32 insns[1]; - - addrs[0] = addr; - insns[0] = opcode; - - return aarch64_insn_patch_text(addrs, insns, 1); -} - static void __kprobes arch_prepare_ss_slot(struct kprobe *p) { + kprobe_opcode_t *addr = p->ainsn.api.insn; + void *addrs[] = {addr, addr + 1}; + u32 insns[] = {p->opcode, BRK64_OPCODE_KPROBES_SS}; + /* prepare insn slot */ - patch_text(p->ainsn.api.insn, p->opcode); + aarch64_insn_patch_text(addrs, insns, 2); - flush_icache_range((uintptr_t) (p->ainsn.api.insn), - (uintptr_t) (p->ainsn.api.insn) + - MAX_INSN_SIZE * sizeof(kprobe_opcode_t)); + flush_icache_range((uintptr_t)addr, (uintptr_t)(addr + MAX_INSN_SIZE)); /* * Needs restoring of return address after stepping xol. @@ -128,13 +119,18 @@ void *alloc_insn_page(void) /* arm kprobe: install breakpoint in text */ void __kprobes arch_arm_kprobe(struct kprobe *p) { - patch_text(p->addr, BRK64_OPCODE_KPROBES); + void *addr = p->addr; + u32 insn = BRK64_OPCODE_KPROBES; + + aarch64_insn_patch_text(&addr, &insn, 1); } /* disarm kprobe: remove breakpoint from text */ void __kprobes arch_disarm_kprobe(struct kprobe *p) { - patch_text(p->addr, p->opcode); + void *addr = p->addr; + + aarch64_insn_patch_text(&addr, &p->opcode, 1); } void __kprobes arch_remove_kprobe(struct kprobe *p) @@ -163,20 +159,15 @@ static void __kprobes set_current_kprobe(struct kprobe *p) } /* - * Interrupts need to be disabled before single-step mode is set, and not - * reenabled until after single-step mode ends. - * Without disabling interrupt on local CPU, there is a chance of - * interrupt occurrence in the period of exception return and start of - * out-of-line single-step, that result in wrongly single stepping - * into the interrupt handler. + * Mask all of DAIF while executing the instruction out-of-line, to keep things + * simple and avoid nesting exceptions. Interrupts do have to be disabled since + * the kprobe state is per-CPU and doesn't get migrated. */ static void __kprobes kprobes_save_local_irqflag(struct kprobe_ctlblk *kcb, struct pt_regs *regs) { kcb->saved_irqflag = regs->pstate & DAIF_MASK; - regs->pstate |= PSR_I_BIT; - /* Unmask PSTATE.D for enabling software step exceptions. */ - regs->pstate &= ~PSR_D_BIT; + regs->pstate |= DAIF_MASK; } static void __kprobes kprobes_restore_local_irqflag(struct kprobe_ctlblk *kcb, @@ -219,10 +210,7 @@ static void __kprobes setup_singlestep(struct kprobe *p, slot = (unsigned long)p->ainsn.api.insn; set_ss_context(kcb, slot); /* mark pending ss */ - - /* IRQs and single stepping do not mix well. */ kprobes_save_local_irqflag(kcb, regs); - kernel_enable_single_step(regs); instruction_pointer_set(regs, slot); } else { /* insn simulation */ @@ -273,12 +261,8 @@ post_kprobe_handler(struct kprobe_ctlblk *kcb, struct pt_regs *regs) } /* call post handler */ kcb->kprobe_status = KPROBE_HIT_SSDONE; - if (cur->post_handler) { - /* post_handler can hit breakpoint and single step - * again, so we enable D-flag for recursive exception. - */ + if (cur->post_handler) cur->post_handler(cur, regs, 0); - } reset_current_kprobe(); } @@ -302,8 +286,6 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr) if (!instruction_pointer(regs)) BUG(); - kernel_disable_single_step(); - if (kcb->kprobe_status == KPROBE_REENTER) restore_previous_kprobe(kcb); else @@ -365,10 +347,6 @@ static void __kprobes kprobe_handler(struct pt_regs *regs) * pre-handler and it returned non-zero, it will * modify the execution path and no need to single * stepping. Let's just reset current kprobe and exit. - * - * pre_handler can hit a breakpoint and can step thru - * before return, keep PSTATE D-flag enabled until - * pre_handler return back. */ if (!p->pre_handler || !p->pre_handler(p, regs)) { setup_singlestep(p, regs, kcb, 0); @@ -399,7 +377,7 @@ kprobe_ss_hit(struct kprobe_ctlblk *kcb, unsigned long addr) } static int __kprobes -kprobe_single_step_handler(struct pt_regs *regs, unsigned int esr) +kprobe_breakpoint_ss_handler(struct pt_regs *regs, unsigned int esr) { struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); int retval; @@ -409,16 +387,15 @@ kprobe_single_step_handler(struct pt_regs *regs, unsigned int esr) if (retval == DBG_HOOK_HANDLED) { kprobes_restore_local_irqflag(kcb, regs); - kernel_disable_single_step(); - post_kprobe_handler(kcb, regs); } return retval; } -static struct step_hook kprobes_step_hook = { - .fn = kprobe_single_step_handler, +static struct break_hook kprobes_break_ss_hook = { + .imm = KPROBES_BRK_SS_IMM, + .fn = kprobe_breakpoint_ss_handler, }; static int __kprobes @@ -486,7 +463,7 @@ int __kprobes arch_trampoline_kprobe(struct kprobe *p) int __init arch_init_kprobes(void) { register_kernel_break_hook(&kprobes_break_hook); - register_kernel_step_hook(&kprobes_step_hook); + register_kernel_break_hook(&kprobes_break_ss_hook); return 0; } diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 4784011cecac..a47a40ec6ad9 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -522,14 +522,13 @@ static void erratum_1418040_thread_switch(struct task_struct *prev, bool prev32, next32; u64 val; - if (!(IS_ENABLED(CONFIG_ARM64_ERRATUM_1418040) && - cpus_have_const_cap(ARM64_WORKAROUND_1418040))) + if (!IS_ENABLED(CONFIG_ARM64_ERRATUM_1418040)) return; prev32 = is_compat_thread(task_thread_info(prev)); next32 = is_compat_thread(task_thread_info(next)); - if (prev32 == next32) + if (prev32 == next32 || !this_cpu_has_cap(ARM64_WORKAROUND_1418040)) return; val = read_sysreg(cntkctl_el1); diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index c18eb7d41274..f6e4e3737405 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -118,6 +118,7 @@ static enum mitigation_state spectre_v2_get_cpu_hw_mitigation_state(void) MIDR_ALL_VERSIONS(MIDR_CORTEX_A55), MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53), MIDR_ALL_VERSIONS(MIDR_HISI_TSV110), + MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_2XX_SILVER), MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER), MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER), { /* sentinel */ } diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c index 43ae4e0c968f..62d2bda7adb8 100644 --- a/arch/arm64/kernel/psci.c +++ b/arch/arm64/kernel/psci.c @@ -66,7 +66,6 @@ static int cpu_psci_cpu_disable(unsigned int cpu) static void cpu_psci_cpu_die(unsigned int cpu) { - int ret; /* * There are no known implementations of PSCI actually using the * power state field, pass a sensible default for now. @@ -74,9 +73,7 @@ static void cpu_psci_cpu_die(unsigned int cpu) u32 state = PSCI_POWER_STATE_TYPE_POWER_DOWN << PSCI_0_2_POWER_STATE_TYPE_SHIFT; - ret = psci_ops.cpu_off(state); - - pr_crit("unable to power off CPU%u (%d)\n", cpu, ret); + psci_ops.cpu_off(state); } static int cpu_psci_cpu_kill(unsigned int cpu) diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 09c96f57818c..18e9727d3f64 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -413,6 +413,7 @@ void cpu_die_early(void) /* Mark this CPU absent */ set_cpu_present(cpu, 0); + rcu_report_dead(cpu); if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) { update_cpu_boot_status(CPU_KILL_ME); diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 5750ec34960e..c0ffb019ca8b 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -102,6 +102,20 @@ static int kvm_arm_default_max_vcpus(void) return vgic_present ? kvm_vgic_get_max_vcpus() : KVM_MAX_VCPUS; } +static void set_default_csv2(struct kvm *kvm) +{ + /* + * The default is to expose CSV2 == 1 if the HW isn't affected. + * Although this is a per-CPU feature, we make it global because + * asymmetric systems are just a nuisance. + * + * Userspace can override this as long as it doesn't promise + * the impossible. + */ + if (arm64_get_spectre_v2_state() == SPECTRE_UNAFFECTED) + kvm->arch.pfr0_csv2 = 1; +} + /** * kvm_arch_init_vm - initializes a VM data structure * @kvm: pointer to the KVM struct @@ -127,6 +141,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) /* The maximum number of VCPUs is limited by the host's GIC model */ kvm->arch.max_vcpus = kvm_arm_default_max_vcpus(); + set_default_csv2(kvm); + return ret; out_free_stage2_pgd: kvm_free_stage2_pgd(&kvm->arch.mmu); diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 57972bdb213a..1a01da9fdc99 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -788,10 +788,12 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, } switch (vma_shift) { +#ifndef __PAGETABLE_PMD_FOLDED case PUD_SHIFT: if (fault_supports_stage2_huge_mapping(memslot, hva, PUD_SIZE)) break; fallthrough; +#endif case CONT_PMD_SHIFT: vma_shift = PMD_SHIFT; fallthrough; diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index fb12d3ef423a..c1fac9836af1 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1038,8 +1038,8 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, { SYS_DESC(SYS_PMEVTYPERn_EL0(n)), \ access_pmu_evtyper, reset_unknown, (PMEVTYPER0_EL0 + n), } -static bool access_amu(struct kvm_vcpu *vcpu, struct sys_reg_params *p, - const struct sys_reg_desc *r) +static bool undef_access(struct kvm_vcpu *vcpu, struct sys_reg_params *p, + const struct sys_reg_desc *r) { kvm_inject_undefined(vcpu); @@ -1047,33 +1047,25 @@ static bool access_amu(struct kvm_vcpu *vcpu, struct sys_reg_params *p, } /* Macro to expand the AMU counter and type registers*/ -#define AMU_AMEVCNTR0_EL0(n) { SYS_DESC(SYS_AMEVCNTR0_EL0(n)), access_amu } -#define AMU_AMEVTYPER0_EL0(n) { SYS_DESC(SYS_AMEVTYPER0_EL0(n)), access_amu } -#define AMU_AMEVCNTR1_EL0(n) { SYS_DESC(SYS_AMEVCNTR1_EL0(n)), access_amu } -#define AMU_AMEVTYPER1_EL0(n) { SYS_DESC(SYS_AMEVTYPER1_EL0(n)), access_amu } - -static bool trap_ptrauth(struct kvm_vcpu *vcpu, - struct sys_reg_params *p, - const struct sys_reg_desc *rd) -{ - /* - * If we land here, that is because we didn't fixup the access on exit - * by allowing the PtrAuth sysregs. The only way this happens is when - * the guest does not have PtrAuth support enabled. - */ - kvm_inject_undefined(vcpu); - - return false; -} +#define AMU_AMEVCNTR0_EL0(n) { SYS_DESC(SYS_AMEVCNTR0_EL0(n)), undef_access } +#define AMU_AMEVTYPER0_EL0(n) { SYS_DESC(SYS_AMEVTYPER0_EL0(n)), undef_access } +#define AMU_AMEVCNTR1_EL0(n) { SYS_DESC(SYS_AMEVCNTR1_EL0(n)), undef_access } +#define AMU_AMEVTYPER1_EL0(n) { SYS_DESC(SYS_AMEVTYPER1_EL0(n)), undef_access } static unsigned int ptrauth_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { - return vcpu_has_ptrauth(vcpu) ? 0 : REG_HIDDEN_USER | REG_HIDDEN_GUEST; + return vcpu_has_ptrauth(vcpu) ? 0 : REG_HIDDEN; } +/* + * If we land here on a PtrAuth access, that is because we didn't + * fixup the access on exit by allowing the PtrAuth sysregs. The only + * way this happens is when the guest does not have PtrAuth support + * enabled. + */ #define __PTRAUTH_KEY(k) \ - { SYS_DESC(SYS_## k), trap_ptrauth, reset_unknown, k, \ + { SYS_DESC(SYS_## k), undef_access, reset_unknown, k, \ .visibility = ptrauth_visibility} #define PTRAUTH_KEY(k) \ @@ -1128,9 +1120,8 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu, if (!vcpu_has_sve(vcpu)) val &= ~(0xfUL << ID_AA64PFR0_SVE_SHIFT); val &= ~(0xfUL << ID_AA64PFR0_AMU_SHIFT); - if (!(val & (0xfUL << ID_AA64PFR0_CSV2_SHIFT)) && - arm64_get_spectre_v2_state() == SPECTRE_UNAFFECTED) - val |= (1UL << ID_AA64PFR0_CSV2_SHIFT); + val &= ~(0xfUL << ID_AA64PFR0_CSV2_SHIFT); + val |= ((u64)vcpu->kvm->arch.pfr0_csv2 << ID_AA64PFR0_CSV2_SHIFT); } else if (id == SYS_ID_AA64PFR1_EL1) { val &= ~(0xfUL << ID_AA64PFR1_MTE_SHIFT); } else if (id == SYS_ID_AA64ISAR1_EL1 && !vcpu_has_ptrauth(vcpu)) { @@ -1153,6 +1144,22 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu, return val; } +static unsigned int id_visibility(const struct kvm_vcpu *vcpu, + const struct sys_reg_desc *r) +{ + u32 id = sys_reg((u32)r->Op0, (u32)r->Op1, + (u32)r->CRn, (u32)r->CRm, (u32)r->Op2); + + switch (id) { + case SYS_ID_AA64ZFR0_EL1: + if (!vcpu_has_sve(vcpu)) + return REG_RAZ; + break; + } + + return 0; +} + /* cpufeature ID register access trap handlers */ static bool __access_id_reg(struct kvm_vcpu *vcpu, @@ -1171,7 +1178,9 @@ static bool access_id_reg(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { - return __access_id_reg(vcpu, p, r, false); + bool raz = sysreg_visible_as_raz(vcpu, r); + + return __access_id_reg(vcpu, p, r, raz); } static bool access_raz_id_reg(struct kvm_vcpu *vcpu, @@ -1192,71 +1201,40 @@ static unsigned int sve_visibility(const struct kvm_vcpu *vcpu, if (vcpu_has_sve(vcpu)) return 0; - return REG_HIDDEN_USER | REG_HIDDEN_GUEST; -} - -/* Visibility overrides for SVE-specific ID registers */ -static unsigned int sve_id_visibility(const struct kvm_vcpu *vcpu, - const struct sys_reg_desc *rd) -{ - if (vcpu_has_sve(vcpu)) - return 0; - - return REG_HIDDEN_USER; + return REG_HIDDEN; } -/* Generate the emulated ID_AA64ZFR0_EL1 value exposed to the guest */ -static u64 guest_id_aa64zfr0_el1(const struct kvm_vcpu *vcpu) -{ - if (!vcpu_has_sve(vcpu)) - return 0; - - return read_sanitised_ftr_reg(SYS_ID_AA64ZFR0_EL1); -} - -static bool access_id_aa64zfr0_el1(struct kvm_vcpu *vcpu, - struct sys_reg_params *p, - const struct sys_reg_desc *rd) -{ - if (p->is_write) - return write_to_read_only(vcpu, p, rd); - - p->regval = guest_id_aa64zfr0_el1(vcpu); - return true; -} - -static int get_id_aa64zfr0_el1(struct kvm_vcpu *vcpu, - const struct sys_reg_desc *rd, - const struct kvm_one_reg *reg, void __user *uaddr) -{ - u64 val; - - if (WARN_ON(!vcpu_has_sve(vcpu))) - return -ENOENT; - - val = guest_id_aa64zfr0_el1(vcpu); - return reg_to_user(uaddr, &val, reg->id); -} - -static int set_id_aa64zfr0_el1(struct kvm_vcpu *vcpu, - const struct sys_reg_desc *rd, - const struct kvm_one_reg *reg, void __user *uaddr) +static int set_id_aa64pfr0_el1(struct kvm_vcpu *vcpu, + const struct sys_reg_desc *rd, + const struct kvm_one_reg *reg, void __user *uaddr) { const u64 id = sys_reg_to_index(rd); int err; u64 val; - - if (WARN_ON(!vcpu_has_sve(vcpu))) - return -ENOENT; + u8 csv2; err = reg_from_user(&val, uaddr, id); if (err) return err; - /* This is what we mean by invariant: you can't change it. */ - if (val != guest_id_aa64zfr0_el1(vcpu)) + /* + * Allow AA64PFR0_EL1.CSV2 to be set from userspace as long as + * it doesn't promise more than what is actually provided (the + * guest could otherwise be covered in ectoplasmic residue). + */ + csv2 = cpuid_feature_extract_unsigned_field(val, ID_AA64PFR0_CSV2_SHIFT); + if (csv2 > 1 || + (csv2 && arm64_get_spectre_v2_state() != SPECTRE_UNAFFECTED)) return -EINVAL; + /* We can only differ with CSV2, and anything else is an error */ + val ^= read_id_reg(vcpu, rd, false); + val &= ~(0xFUL << ID_AA64PFR0_CSV2_SHIFT); + if (val) + return -EINVAL; + + vcpu->kvm->arch.pfr0_csv2 = csv2; + return 0; } @@ -1299,13 +1277,17 @@ static int __set_id_reg(const struct kvm_vcpu *vcpu, static int get_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - return __get_id_reg(vcpu, rd, uaddr, false); + bool raz = sysreg_visible_as_raz(vcpu, rd); + + return __get_id_reg(vcpu, rd, uaddr, raz); } static int set_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - return __set_id_reg(vcpu, rd, uaddr, false); + bool raz = sysreg_visible_as_raz(vcpu, rd); + + return __set_id_reg(vcpu, rd, uaddr, raz); } static int get_raz_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, @@ -1384,19 +1366,13 @@ static bool access_ccsidr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, return true; } -static bool access_mte_regs(struct kvm_vcpu *vcpu, struct sys_reg_params *p, - const struct sys_reg_desc *r) -{ - kvm_inject_undefined(vcpu); - return false; -} - /* sys_reg_desc initialiser for known cpufeature ID registers */ #define ID_SANITISED(name) { \ SYS_DESC(SYS_##name), \ .access = access_id_reg, \ .get_user = get_id_reg, \ .set_user = set_id_reg, \ + .visibility = id_visibility, \ } /* @@ -1514,11 +1490,12 @@ static const struct sys_reg_desc sys_reg_descs[] = { /* AArch64 ID registers */ /* CRm=4 */ - ID_SANITISED(ID_AA64PFR0_EL1), + { SYS_DESC(SYS_ID_AA64PFR0_EL1), .access = access_id_reg, + .get_user = get_id_reg, .set_user = set_id_aa64pfr0_el1, }, ID_SANITISED(ID_AA64PFR1_EL1), ID_UNALLOCATED(4,2), ID_UNALLOCATED(4,3), - { SYS_DESC(SYS_ID_AA64ZFR0_EL1), access_id_aa64zfr0_el1, .get_user = get_id_aa64zfr0_el1, .set_user = set_id_aa64zfr0_el1, .visibility = sve_id_visibility }, + ID_SANITISED(ID_AA64ZFR0_EL1), ID_UNALLOCATED(4,5), ID_UNALLOCATED(4,6), ID_UNALLOCATED(4,7), @@ -1557,8 +1534,8 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_ACTLR_EL1), access_actlr, reset_actlr, ACTLR_EL1 }, { SYS_DESC(SYS_CPACR_EL1), NULL, reset_val, CPACR_EL1, 0 }, - { SYS_DESC(SYS_RGSR_EL1), access_mte_regs }, - { SYS_DESC(SYS_GCR_EL1), access_mte_regs }, + { SYS_DESC(SYS_RGSR_EL1), undef_access }, + { SYS_DESC(SYS_GCR_EL1), undef_access }, { SYS_DESC(SYS_ZCR_EL1), NULL, reset_val, ZCR_EL1, 0, .visibility = sve_visibility }, { SYS_DESC(SYS_TTBR0_EL1), access_vm_reg, reset_unknown, TTBR0_EL1 }, @@ -1584,8 +1561,8 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_ERXMISC0_EL1), trap_raz_wi }, { SYS_DESC(SYS_ERXMISC1_EL1), trap_raz_wi }, - { SYS_DESC(SYS_TFSR_EL1), access_mte_regs }, - { SYS_DESC(SYS_TFSRE0_EL1), access_mte_regs }, + { SYS_DESC(SYS_TFSR_EL1), undef_access }, + { SYS_DESC(SYS_TFSRE0_EL1), undef_access }, { SYS_DESC(SYS_FAR_EL1), access_vm_reg, reset_unknown, FAR_EL1 }, { SYS_DESC(SYS_PAR_EL1), NULL, reset_unknown, PAR_EL1 }, @@ -1621,6 +1598,8 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_CONTEXTIDR_EL1), access_vm_reg, reset_val, CONTEXTIDR_EL1, 0 }, { SYS_DESC(SYS_TPIDR_EL1), NULL, reset_unknown, TPIDR_EL1 }, + { SYS_DESC(SYS_SCXTNUM_EL1), undef_access }, + { SYS_DESC(SYS_CNTKCTL_EL1), NULL, reset_val, CNTKCTL_EL1, 0}, { SYS_DESC(SYS_CCSIDR_EL1), access_ccsidr }, @@ -1649,14 +1628,16 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_TPIDR_EL0), NULL, reset_unknown, TPIDR_EL0 }, { SYS_DESC(SYS_TPIDRRO_EL0), NULL, reset_unknown, TPIDRRO_EL0 }, - { SYS_DESC(SYS_AMCR_EL0), access_amu }, - { SYS_DESC(SYS_AMCFGR_EL0), access_amu }, - { SYS_DESC(SYS_AMCGCR_EL0), access_amu }, - { SYS_DESC(SYS_AMUSERENR_EL0), access_amu }, - { SYS_DESC(SYS_AMCNTENCLR0_EL0), access_amu }, - { SYS_DESC(SYS_AMCNTENSET0_EL0), access_amu }, - { SYS_DESC(SYS_AMCNTENCLR1_EL0), access_amu }, - { SYS_DESC(SYS_AMCNTENSET1_EL0), access_amu }, + { SYS_DESC(SYS_SCXTNUM_EL0), undef_access }, + + { SYS_DESC(SYS_AMCR_EL0), undef_access }, + { SYS_DESC(SYS_AMCFGR_EL0), undef_access }, + { SYS_DESC(SYS_AMCGCR_EL0), undef_access }, + { SYS_DESC(SYS_AMUSERENR_EL0), undef_access }, + { SYS_DESC(SYS_AMCNTENCLR0_EL0), undef_access }, + { SYS_DESC(SYS_AMCNTENSET0_EL0), undef_access }, + { SYS_DESC(SYS_AMCNTENCLR1_EL0), undef_access }, + { SYS_DESC(SYS_AMCNTENSET1_EL0), undef_access }, AMU_AMEVCNTR0_EL0(0), AMU_AMEVCNTR0_EL0(1), AMU_AMEVCNTR0_EL0(2), @@ -2185,7 +2166,7 @@ static void perform_access(struct kvm_vcpu *vcpu, trace_kvm_sys_access(*vcpu_pc(vcpu), params, r); /* Check for regs disabled by runtime config */ - if (sysreg_hidden_from_guest(vcpu, r)) { + if (sysreg_hidden(vcpu, r)) { kvm_inject_undefined(vcpu); return; } @@ -2684,7 +2665,7 @@ int kvm_arm_sys_reg_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg return get_invariant_sys_reg(reg->id, uaddr); /* Check for regs disabled by runtime config */ - if (sysreg_hidden_from_user(vcpu, r)) + if (sysreg_hidden(vcpu, r)) return -ENOENT; if (r->get_user) @@ -2709,7 +2690,7 @@ int kvm_arm_sys_reg_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg return set_invariant_sys_reg(reg->id, uaddr); /* Check for regs disabled by runtime config */ - if (sysreg_hidden_from_user(vcpu, r)) + if (sysreg_hidden(vcpu, r)) return -ENOENT; if (r->set_user) @@ -2780,7 +2761,7 @@ static int walk_one_sys_reg(const struct kvm_vcpu *vcpu, if (!(rd->reg || rd->get_user)) return 0; - if (sysreg_hidden_from_user(vcpu, rd)) + if (sysreg_hidden(vcpu, rd)) return 0; if (!copy_reg_to_user(rd, uind)) diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h index 5a6fc30f5989..0f95964339b1 100644 --- a/arch/arm64/kvm/sys_regs.h +++ b/arch/arm64/kvm/sys_regs.h @@ -59,8 +59,8 @@ struct sys_reg_desc { const struct sys_reg_desc *rd); }; -#define REG_HIDDEN_USER (1 << 0) /* hidden from userspace ioctls */ -#define REG_HIDDEN_GUEST (1 << 1) /* hidden from guest */ +#define REG_HIDDEN (1 << 0) /* hidden from userspace and guest */ +#define REG_RAZ (1 << 1) /* RAZ from userspace and guest */ static __printf(2, 3) inline void print_sys_reg_msg(const struct sys_reg_params *p, @@ -111,22 +111,22 @@ static inline void reset_val(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r __vcpu_sys_reg(vcpu, r->reg) = r->val; } -static inline bool sysreg_hidden_from_guest(const struct kvm_vcpu *vcpu, - const struct sys_reg_desc *r) +static inline bool sysreg_hidden(const struct kvm_vcpu *vcpu, + const struct sys_reg_desc *r) { if (likely(!r->visibility)) return false; - return r->visibility(vcpu, r) & REG_HIDDEN_GUEST; + return r->visibility(vcpu, r) & REG_HIDDEN; } -static inline bool sysreg_hidden_from_user(const struct kvm_vcpu *vcpu, - const struct sys_reg_desc *r) +static inline bool sysreg_visible_as_raz(const struct kvm_vcpu *vcpu, + const struct sys_reg_desc *r) { if (likely(!r->visibility)) return false; - return r->visibility(vcpu, r) & REG_HIDDEN_USER; + return r->visibility(vcpu, r) & REG_RAZ; } static inline int cmp_sys_reg(const struct sys_reg_desc *i1, diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 1c0f3e02f731..ca692a815731 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -1444,11 +1444,28 @@ static void __remove_pgd_mapping(pgd_t *pgdir, unsigned long start, u64 size) free_empty_tables(start, end, PAGE_OFFSET, PAGE_END); } +static bool inside_linear_region(u64 start, u64 size) +{ + /* + * Linear mapping region is the range [PAGE_OFFSET..(PAGE_END - 1)] + * accommodating both its ends but excluding PAGE_END. Max physical + * range which can be mapped inside this linear mapping range, must + * also be derived from its end points. + */ + return start >= __pa(_PAGE_OFFSET(vabits_actual)) && + (start + size - 1) <= __pa(PAGE_END - 1); +} + int arch_add_memory(int nid, u64 start, u64 size, struct mhp_params *params) { int ret, flags = 0; + if (!inside_linear_region(start, size)) { + pr_err("[%llx %llx] is outside linear mapping region\n", start, start + size); + return -EINVAL; + } + if (rodata_full || debug_pagealloc_enabled()) flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS; diff --git a/arch/csky/kernel/perf_regs.c b/arch/csky/kernel/perf_regs.c index eb32838b8210..09b7f88a2d6a 100644 --- a/arch/csky/kernel/perf_regs.c +++ b/arch/csky/kernel/perf_regs.c @@ -32,8 +32,7 @@ u64 perf_reg_abi(struct task_struct *task) } void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { regs_user->regs = task_pt_regs(current); regs_user->abi = perf_reg_abi(current); diff --git a/arch/ia64/include/asm/sparsemem.h b/arch/ia64/include/asm/sparsemem.h index 336d0570e1fa..dd8c166ffd7b 100644 --- a/arch/ia64/include/asm/sparsemem.h +++ b/arch/ia64/include/asm/sparsemem.h @@ -18,4 +18,10 @@ #endif #endif /* CONFIG_SPARSEMEM */ + +#ifdef CONFIG_MEMORY_HOTPLUG +int memory_add_physaddr_to_nid(u64 addr); +#define memory_add_physaddr_to_nid memory_add_physaddr_to_nid +#endif + #endif /* _ASM_IA64_SPARSEMEM_H */ diff --git a/arch/mips/alchemy/common/clock.c b/arch/mips/alchemy/common/clock.c index a95a894aceaf..f0c830337104 100644 --- a/arch/mips/alchemy/common/clock.c +++ b/arch/mips/alchemy/common/clock.c @@ -152,6 +152,7 @@ static struct clk __init *alchemy_clk_setup_cpu(const char *parent_name, { struct clk_init_data id; struct clk_hw *h; + struct clk *clk; h = kzalloc(sizeof(*h), GFP_KERNEL); if (!h) @@ -164,7 +165,13 @@ static struct clk __init *alchemy_clk_setup_cpu(const char *parent_name, id.ops = &alchemy_clkops_cpu; h->init = &id; - return clk_register(NULL, h); + clk = clk_register(NULL, h); + if (IS_ERR(clk)) { + pr_err("failed to register clock\n"); + kfree(h); + } + + return clk; } /* AUXPLLs ************************************************************/ diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 0d4253208bde..ca579deef939 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -262,8 +262,8 @@ static void __init bootmem_init(void) static void __init bootmem_init(void) { phys_addr_t ramstart, ramend; - phys_addr_t start, end; - u64 i; + unsigned long start, end; + int i; ramstart = memblock_start_of_DRAM(); ramend = memblock_end_of_DRAM(); @@ -300,7 +300,7 @@ static void __init bootmem_init(void) min_low_pfn = ARCH_PFN_OFFSET; max_pfn = PFN_DOWN(ramend); - for_each_mem_range(i, &start, &end) { + for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, NULL) { /* * Skip highmem here so we get an accurate max_low_pfn if low * memory stops short of high memory. diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c index 38e2894d5fa3..1b939abbe4ca 100644 --- a/arch/mips/mm/tlb-r4k.c +++ b/arch/mips/mm/tlb-r4k.c @@ -438,6 +438,7 @@ int has_transparent_hugepage(void) } return mask == PM_HUGE_MASK; } +EXPORT_SYMBOL(has_transparent_hugepage); #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ diff --git a/arch/powerpc/include/asm/book3s/64/kup-radix.h b/arch/powerpc/include/asm/book3s/64/kup-radix.h index 3ee1ec60be84..28716e2f13e3 100644 --- a/arch/powerpc/include/asm/book3s/64/kup-radix.h +++ b/arch/powerpc/include/asm/book3s/64/kup-radix.h @@ -27,6 +27,7 @@ #endif .endm +#ifdef CONFIG_PPC_KUAP .macro kuap_check_amr gpr1, gpr2 #ifdef CONFIG_PPC_KUAP_DEBUG BEGIN_MMU_FTR_SECTION_NESTED(67) @@ -38,6 +39,7 @@ END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_RADIX_KUAP, 67) #endif .endm +#endif .macro kuap_save_amr_and_lock gpr1, gpr2, use_cr, msr_pr_cr #ifdef CONFIG_PPC_KUAP @@ -61,6 +63,8 @@ #else /* !__ASSEMBLY__ */ +DECLARE_STATIC_KEY_FALSE(uaccess_flush_key); + #ifdef CONFIG_PPC_KUAP #include <asm/mmu.h> @@ -103,8 +107,16 @@ static inline void kuap_check_amr(void) static inline unsigned long get_kuap(void) { + /* + * We return AMR_KUAP_BLOCKED when we don't support KUAP because + * prevent_user_access_return needs to return AMR_KUAP_BLOCKED to + * cause restore_user_access to do a flush. + * + * This has no effect in terms of actually blocking things on hash, + * so it doesn't break anything. + */ if (!early_mmu_has_feature(MMU_FTR_RADIX_KUAP)) - return 0; + return AMR_KUAP_BLOCKED; return mfspr(SPRN_AMR); } @@ -123,6 +135,29 @@ static inline void set_kuap(unsigned long value) isync(); } +static inline bool +bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) +{ + return WARN(mmu_has_feature(MMU_FTR_RADIX_KUAP) && + (regs->kuap & (is_write ? AMR_KUAP_BLOCK_WRITE : AMR_KUAP_BLOCK_READ)), + "Bug: %s fault blocked by AMR!", is_write ? "Write" : "Read"); +} +#else /* CONFIG_PPC_KUAP */ +static inline void kuap_restore_amr(struct pt_regs *regs, unsigned long amr) { } + +static inline unsigned long kuap_get_and_check_amr(void) +{ + return 0UL; +} + +static inline unsigned long get_kuap(void) +{ + return AMR_KUAP_BLOCKED; +} + +static inline void set_kuap(unsigned long value) { } +#endif /* !CONFIG_PPC_KUAP */ + static __always_inline void allow_user_access(void __user *to, const void __user *from, unsigned long size, unsigned long dir) { @@ -142,6 +177,8 @@ static inline void prevent_user_access(void __user *to, const void __user *from, unsigned long size, unsigned long dir) { set_kuap(AMR_KUAP_BLOCKED); + if (static_branch_unlikely(&uaccess_flush_key)) + do_uaccess_flush(); } static inline unsigned long prevent_user_access_return(void) @@ -149,6 +186,8 @@ static inline unsigned long prevent_user_access_return(void) unsigned long flags = get_kuap(); set_kuap(AMR_KUAP_BLOCKED); + if (static_branch_unlikely(&uaccess_flush_key)) + do_uaccess_flush(); return flags; } @@ -156,30 +195,9 @@ static inline unsigned long prevent_user_access_return(void) static inline void restore_user_access(unsigned long flags) { set_kuap(flags); + if (static_branch_unlikely(&uaccess_flush_key) && flags == AMR_KUAP_BLOCKED) + do_uaccess_flush(); } - -static inline bool -bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) -{ - return WARN(mmu_has_feature(MMU_FTR_RADIX_KUAP) && - (regs->kuap & (is_write ? AMR_KUAP_BLOCK_WRITE : AMR_KUAP_BLOCK_READ)), - "Bug: %s fault blocked by AMR!", is_write ? "Write" : "Read"); -} -#else /* CONFIG_PPC_KUAP */ -static inline void kuap_restore_amr(struct pt_regs *regs, unsigned long amr) -{ -} - -static inline void kuap_check_amr(void) -{ -} - -static inline unsigned long kuap_get_and_check_amr(void) -{ - return 0; -} -#endif /* CONFIG_PPC_KUAP */ - #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_BOOK3S_64_KUP_RADIX_H */ diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index ebe95aa04d53..1d32b174ab6a 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -57,11 +57,18 @@ nop; \ nop +#define ENTRY_FLUSH_SLOT \ + ENTRY_FLUSH_FIXUP_SECTION; \ + nop; \ + nop; \ + nop; + /* * r10 must be free to use, r13 must be paca */ #define INTERRUPT_TO_KERNEL \ - STF_ENTRY_BARRIER_SLOT + STF_ENTRY_BARRIER_SLOT; \ + ENTRY_FLUSH_SLOT /* * Macros for annotating the expected destination of (h)rfid @@ -137,6 +144,9 @@ RFSCV; \ b rfscv_flush_fallback +#else /* __ASSEMBLY__ */ +/* Prototype for function defined in exceptions-64s.S */ +void do_uaccess_flush(void); #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_EXCEPTION_H */ diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h index b0af97add751..fbd406cd6916 100644 --- a/arch/powerpc/include/asm/feature-fixups.h +++ b/arch/powerpc/include/asm/feature-fixups.h @@ -205,6 +205,22 @@ label##3: \ FTR_ENTRY_OFFSET 955b-956b; \ .popsection; +#define UACCESS_FLUSH_FIXUP_SECTION \ +959: \ + .pushsection __uaccess_flush_fixup,"a"; \ + .align 2; \ +960: \ + FTR_ENTRY_OFFSET 959b-960b; \ + .popsection; + +#define ENTRY_FLUSH_FIXUP_SECTION \ +957: \ + .pushsection __entry_flush_fixup,"a"; \ + .align 2; \ +958: \ + FTR_ENTRY_OFFSET 957b-958b; \ + .popsection; + #define RFI_FLUSH_FIXUP_SECTION \ 951: \ .pushsection __rfi_flush_fixup,"a"; \ @@ -237,8 +253,11 @@ label##3: \ #include <linux/types.h> extern long stf_barrier_fallback; +extern long entry_flush_fallback; extern long __start___stf_entry_barrier_fixup, __stop___stf_entry_barrier_fixup; extern long __start___stf_exit_barrier_fixup, __stop___stf_exit_barrier_fixup; +extern long __start___uaccess_flush_fixup, __stop___uaccess_flush_fixup; +extern long __start___entry_flush_fixup, __stop___entry_flush_fixup; extern long __start___rfi_flush_fixup, __stop___rfi_flush_fixup; extern long __start___barrier_nospec_fixup, __stop___barrier_nospec_fixup; extern long __start__btb_flush_fixup, __stop__btb_flush_fixup; diff --git a/arch/powerpc/include/asm/kup.h b/arch/powerpc/include/asm/kup.h index 1d0f7d838b2e..0d93331d0fab 100644 --- a/arch/powerpc/include/asm/kup.h +++ b/arch/powerpc/include/asm/kup.h @@ -14,7 +14,7 @@ #define KUAP_CURRENT_WRITE 8 #define KUAP_CURRENT (KUAP_CURRENT_READ | KUAP_CURRENT_WRITE) -#ifdef CONFIG_PPC64 +#ifdef CONFIG_PPC_BOOK3S_64 #include <asm/book3s/64/kup-radix.h> #endif #ifdef CONFIG_PPC_8xx @@ -35,6 +35,9 @@ .macro kuap_check current, gpr .endm +.macro kuap_check_amr gpr1, gpr2 +.endm + #endif #else /* !__ASSEMBLY__ */ @@ -53,17 +56,28 @@ static inline void setup_kuep(bool disabled) { } void setup_kuap(bool disabled); #else static inline void setup_kuap(bool disabled) { } + +static inline bool +bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) +{ + return false; +} + +static inline void kuap_check_amr(void) { } + +/* + * book3s/64/kup-radix.h defines these functions for the !KUAP case to flush + * the L1D cache after user accesses. Only include the empty stubs for other + * platforms. + */ +#ifndef CONFIG_PPC_BOOK3S_64 static inline void allow_user_access(void __user *to, const void __user *from, unsigned long size, unsigned long dir) { } static inline void prevent_user_access(void __user *to, const void __user *from, unsigned long size, unsigned long dir) { } static inline unsigned long prevent_user_access_return(void) { return 0UL; } static inline void restore_user_access(unsigned long flags) { } -static inline bool -bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) -{ - return false; -} +#endif /* CONFIG_PPC_BOOK3S_64 */ #endif /* CONFIG_PPC_KUAP */ static inline void allow_read_from_user(const void __user *from, unsigned long size) diff --git a/arch/powerpc/include/asm/mmzone.h b/arch/powerpc/include/asm/mmzone.h index 91c69ff53a8a..6cda76b57c5d 100644 --- a/arch/powerpc/include/asm/mmzone.h +++ b/arch/powerpc/include/asm/mmzone.h @@ -46,5 +46,10 @@ u64 memory_hotplug_max(void); #define __HAVE_ARCH_RESERVED_KERNEL_PAGES #endif +#ifdef CONFIG_MEMORY_HOTPLUG +extern int create_section_mapping(unsigned long start, unsigned long end, + int nid, pgprot_t prot); +#endif + #endif /* __KERNEL__ */ #endif /* _ASM_MMZONE_H_ */ diff --git a/arch/powerpc/include/asm/nohash/32/kup-8xx.h b/arch/powerpc/include/asm/nohash/32/kup-8xx.h index 85ed2390fb99..567cdc557402 100644 --- a/arch/powerpc/include/asm/nohash/32/kup-8xx.h +++ b/arch/powerpc/include/asm/nohash/32/kup-8xx.h @@ -63,7 +63,7 @@ static inline void restore_user_access(unsigned long flags) static inline bool bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) { - return WARN(!((regs->kuap ^ MD_APG_KUAP) & 0xf0000000), + return WARN(!((regs->kuap ^ MD_APG_KUAP) & 0xff000000), "Bug: fault blocked by AP register !"); } diff --git a/arch/powerpc/include/asm/nohash/32/mmu-8xx.h b/arch/powerpc/include/asm/nohash/32/mmu-8xx.h index 1d9ac0f9c794..0bd1b144eb76 100644 --- a/arch/powerpc/include/asm/nohash/32/mmu-8xx.h +++ b/arch/powerpc/include/asm/nohash/32/mmu-8xx.h @@ -33,19 +33,18 @@ * respectively NA for All or X for Supervisor and no access for User. * Then we use the APG to say whether accesses are according to Page rules or * "all Supervisor" rules (Access to all) - * Therefore, we define 2 APG groups. lsb is _PMD_USER - * 0 => Kernel => 01 (all accesses performed according to page definition) - * 1 => User => 00 (all accesses performed as supervisor iaw page definition) - * 2-15 => Not Used - */ -#define MI_APG_INIT 0x40000000 - -/* - * 0 => Kernel => 01 (all accesses performed according to page definition) - * 1 => User => 10 (all accesses performed according to swaped page definition) - * 2-15 => Not Used - */ -#define MI_APG_KUEP 0x60000000 + * _PAGE_ACCESSED is also managed via APG. When _PAGE_ACCESSED is not set, say + * "all User" rules, that will lead to NA for all. + * Therefore, we define 4 APG groups. lsb is _PAGE_ACCESSED + * 0 => Kernel => 11 (all accesses performed according as user iaw page definition) + * 1 => Kernel+Accessed => 01 (all accesses performed according to page definition) + * 2 => User => 11 (all accesses performed according as user iaw page definition) + * 3 => User+Accessed => 00 (all accesses performed as supervisor iaw page definition) for INIT + * => 10 (all accesses performed according to swaped page definition) for KUEP + * 4-15 => Not Used + */ +#define MI_APG_INIT 0xdc000000 +#define MI_APG_KUEP 0xde000000 /* The effective page number register. When read, contains the information * about the last instruction TLB miss. When MI_RPN is written, bits in @@ -106,25 +105,9 @@ #define MD_Ks 0x80000000 /* Should not be set */ #define MD_Kp 0x40000000 /* Should always be set */ -/* - * All pages' PP data bits are set to either 000 or 011 or 001, which means - * respectively RW for Supervisor and no access for User, or RO for - * Supervisor and no access for user and NA for ALL. - * Then we use the APG to say whether accesses are according to Page rules or - * "all Supervisor" rules (Access to all) - * Therefore, we define 2 APG groups. lsb is _PMD_USER - * 0 => Kernel => 01 (all accesses performed according to page definition) - * 1 => User => 00 (all accesses performed as supervisor iaw page definition) - * 2-15 => Not Used - */ -#define MD_APG_INIT 0x40000000 - -/* - * 0 => No user => 01 (all accesses performed according to page definition) - * 1 => User => 10 (all accesses performed according to swaped page definition) - * 2-15 => Not Used - */ -#define MD_APG_KUAP 0x60000000 +/* See explanation above at the definition of MI_APG_INIT */ +#define MD_APG_INIT 0xdc000000 +#define MD_APG_KUAP 0xde000000 /* The effective page number register. When read, contains the information * about the last instruction TLB miss. When MD_RPN is written, bits in diff --git a/arch/powerpc/include/asm/nohash/32/pte-8xx.h b/arch/powerpc/include/asm/nohash/32/pte-8xx.h index 66f403a7da44..1581204467e1 100644 --- a/arch/powerpc/include/asm/nohash/32/pte-8xx.h +++ b/arch/powerpc/include/asm/nohash/32/pte-8xx.h @@ -39,9 +39,9 @@ * into the TLB. */ #define _PAGE_GUARDED 0x0010 /* Copied to L1 G entry in DTLB */ -#define _PAGE_SPECIAL 0x0020 /* SW entry */ +#define _PAGE_ACCESSED 0x0020 /* Copied to L1 APG 1 entry in I/DTLB */ #define _PAGE_EXEC 0x0040 /* Copied to PP (bit 21) in ITLB */ -#define _PAGE_ACCESSED 0x0080 /* software: page referenced */ +#define _PAGE_SPECIAL 0x0080 /* SW entry */ #define _PAGE_NA 0x0200 /* Supervisor NA, User no access */ #define _PAGE_RO 0x0600 /* Supervisor RO, User no access */ @@ -59,11 +59,12 @@ #define _PMD_PRESENT 0x0001 #define _PMD_PRESENT_MASK _PMD_PRESENT -#define _PMD_BAD 0x0fd0 +#define _PMD_BAD 0x0f90 #define _PMD_PAGE_MASK 0x000c #define _PMD_PAGE_8M 0x000c #define _PMD_PAGE_512K 0x0004 -#define _PMD_USER 0x0020 /* APG 1 */ +#define _PMD_ACCESSED 0x0020 /* APG 1 */ +#define _PMD_USER 0x0040 /* APG 2 */ #define _PTE_NONE_MASK 0 diff --git a/arch/powerpc/include/asm/security_features.h b/arch/powerpc/include/asm/security_features.h index fbb8fa32150f..b774a4477d5f 100644 --- a/arch/powerpc/include/asm/security_features.h +++ b/arch/powerpc/include/asm/security_features.h @@ -86,12 +86,19 @@ static inline bool security_ftr_enabled(u64 feature) // Software required to flush link stack on context switch #define SEC_FTR_FLUSH_LINK_STACK 0x0000000000001000ull +// The L1-D cache should be flushed when entering the kernel +#define SEC_FTR_L1D_FLUSH_ENTRY 0x0000000000004000ull + +// The L1-D cache should be flushed after user accesses from the kernel +#define SEC_FTR_L1D_FLUSH_UACCESS 0x0000000000008000ull // Features enabled by default #define SEC_FTR_DEFAULT \ (SEC_FTR_L1D_FLUSH_HV | \ SEC_FTR_L1D_FLUSH_PR | \ SEC_FTR_BNDS_CHK_SPEC_BAR | \ + SEC_FTR_L1D_FLUSH_ENTRY | \ + SEC_FTR_L1D_FLUSH_UACCESS | \ SEC_FTR_FAVOUR_SECURITY) #endif /* _ASM_POWERPC_SECURITY_FEATURES_H */ diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h index 9efbddee2bca..a466749703f1 100644 --- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -52,12 +52,16 @@ enum l1d_flush_type { }; void setup_rfi_flush(enum l1d_flush_type, bool enable); +void setup_entry_flush(bool enable); +void setup_uaccess_flush(bool enable); void do_rfi_flush_fixups(enum l1d_flush_type types); #ifdef CONFIG_PPC_BARRIER_NOSPEC void setup_barrier_nospec(void); #else static inline void setup_barrier_nospec(void) { }; #endif +void do_uaccess_flush_fixups(enum l1d_flush_type types); +void do_entry_flush_fixups(enum l1d_flush_type types); void do_barrier_nospec_fixups(bool enable); extern bool barrier_nospec_enabled; diff --git a/arch/powerpc/include/asm/sparsemem.h b/arch/powerpc/include/asm/sparsemem.h index 1e6fa371cc38..d072866842e4 100644 --- a/arch/powerpc/include/asm/sparsemem.h +++ b/arch/powerpc/include/asm/sparsemem.h @@ -13,9 +13,9 @@ #endif /* CONFIG_SPARSEMEM */ #ifdef CONFIG_MEMORY_HOTPLUG -extern int create_section_mapping(unsigned long start, unsigned long end, - int nid, pgprot_t prot); extern int remove_section_mapping(unsigned long start, unsigned long end); +extern int memory_add_physaddr_to_nid(u64 start); +#define memory_add_physaddr_to_nid memory_add_physaddr_to_nid #ifdef CONFIG_NUMA extern int hot_add_scn_to_nid(unsigned long scn_addr); @@ -26,6 +26,5 @@ static inline int hot_add_scn_to_nid(unsigned long scn_addr) } #endif /* CONFIG_NUMA */ #endif /* CONFIG_MEMORY_HOTPLUG */ - #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_SPARSEMEM_H */ diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index 8728590f514a..3beeb030cd78 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -6,6 +6,7 @@ struct device; struct device_node; +struct drmem_lmb; #ifdef CONFIG_NUMA @@ -61,6 +62,9 @@ static inline int early_cpu_to_node(int cpu) */ return (nid < 0) ? 0 : nid; } + +int of_drconf_to_nid_single(struct drmem_lmb *lmb); + #else static inline int early_cpu_to_node(int cpu) { return 0; } @@ -84,10 +88,12 @@ static inline int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc) return 0; } -#endif /* CONFIG_NUMA */ +static inline int of_drconf_to_nid_single(struct drmem_lmb *lmb) +{ + return first_online_node; +} -struct drmem_lmb; -int of_drconf_to_nid_single(struct drmem_lmb *lmb); +#endif /* CONFIG_NUMA */ #if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR) extern int find_and_online_cpu_nid(int cpu); diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index ef5bbb705c08..501c9a79038c 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -178,7 +178,7 @@ do { \ * are no aliasing issues. */ #define __put_user_asm_goto(x, addr, label, op) \ - asm volatile goto( \ + asm_volatile_goto( \ "1: " op "%U1%X1 %0,%1 # put_user\n" \ EX_TABLE(1b, %l2) \ : \ @@ -191,7 +191,7 @@ do { \ __put_user_asm_goto(x, ptr, label, "std") #else /* __powerpc64__ */ #define __put_user_asm2_goto(x, addr, label) \ - asm volatile goto( \ + asm_volatile_goto( \ "1: stw%X1 %0, %1\n" \ "2: stw%X1 %L0, %L1\n" \ EX_TABLE(1b, %l2) \ diff --git a/arch/powerpc/kernel/eeh_cache.c b/arch/powerpc/kernel/eeh_cache.c index 6b50bf15d8c1..bf3270426d82 100644 --- a/arch/powerpc/kernel/eeh_cache.c +++ b/arch/powerpc/kernel/eeh_cache.c @@ -264,8 +264,9 @@ static int eeh_addr_cache_show(struct seq_file *s, void *v) { struct pci_io_addr_range *piar; struct rb_node *n; + unsigned long flags; - spin_lock(&pci_io_addr_cache_root.piar_lock); + spin_lock_irqsave(&pci_io_addr_cache_root.piar_lock, flags); for (n = rb_first(&pci_io_addr_cache_root.rb_root); n; n = rb_next(n)) { piar = rb_entry(n, struct pci_io_addr_range, rb_node); @@ -273,7 +274,7 @@ static int eeh_addr_cache_show(struct seq_file *s, void *v) (piar->flags & IORESOURCE_IO) ? "i/o" : "mem", &piar->addr_lo, &piar->addr_hi, pci_name(piar->pcidev)); } - spin_unlock(&pci_io_addr_cache_root.piar_lock); + spin_unlock_irqrestore(&pci_io_addr_cache_root.piar_lock, flags); return 0; } diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index f7d748b88705..f63a3d3bca3d 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -2951,15 +2951,8 @@ TRAMP_REAL_BEGIN(stf_barrier_fallback) .endr blr -TRAMP_REAL_BEGIN(rfi_flush_fallback) - SET_SCRATCH0(r13); - GET_PACA(r13); - std r1,PACA_EXRFI+EX_R12(r13) - ld r1,PACAKSAVE(r13) - std r9,PACA_EXRFI+EX_R9(r13) - std r10,PACA_EXRFI+EX_R10(r13) - std r11,PACA_EXRFI+EX_R11(r13) - mfctr r9 +/* Clobbers r10, r11, ctr */ +.macro L1D_DISPLACEMENT_FLUSH ld r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13) ld r11,PACA_L1D_FLUSH_SIZE(r13) srdi r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */ @@ -2970,7 +2963,7 @@ TRAMP_REAL_BEGIN(rfi_flush_fallback) sync /* - * The load adresses are at staggered offsets within cachelines, + * The load addresses are at staggered offsets within cachelines, * which suits some pipelines better (on others it should not * hurt). */ @@ -2985,7 +2978,30 @@ TRAMP_REAL_BEGIN(rfi_flush_fallback) ld r11,(0x80 + 8)*7(r10) addi r10,r10,0x80*8 bdnz 1b +.endm + +TRAMP_REAL_BEGIN(entry_flush_fallback) + std r9,PACA_EXRFI+EX_R9(r13) + std r10,PACA_EXRFI+EX_R10(r13) + std r11,PACA_EXRFI+EX_R11(r13) + mfctr r9 + L1D_DISPLACEMENT_FLUSH + mtctr r9 + ld r9,PACA_EXRFI+EX_R9(r13) + ld r10,PACA_EXRFI+EX_R10(r13) + ld r11,PACA_EXRFI+EX_R11(r13) + blr +TRAMP_REAL_BEGIN(rfi_flush_fallback) + SET_SCRATCH0(r13); + GET_PACA(r13); + std r1,PACA_EXRFI+EX_R12(r13) + ld r1,PACAKSAVE(r13) + std r9,PACA_EXRFI+EX_R9(r13) + std r10,PACA_EXRFI+EX_R10(r13) + std r11,PACA_EXRFI+EX_R11(r13) + mfctr r9 + L1D_DISPLACEMENT_FLUSH mtctr r9 ld r9,PACA_EXRFI+EX_R9(r13) ld r10,PACA_EXRFI+EX_R10(r13) @@ -3003,32 +3019,7 @@ TRAMP_REAL_BEGIN(hrfi_flush_fallback) std r10,PACA_EXRFI+EX_R10(r13) std r11,PACA_EXRFI+EX_R11(r13) mfctr r9 - ld r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13) - ld r11,PACA_L1D_FLUSH_SIZE(r13) - srdi r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */ - mtctr r11 - DCBT_BOOK3S_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */ - - /* order ld/st prior to dcbt stop all streams with flushing */ - sync - - /* - * The load adresses are at staggered offsets within cachelines, - * which suits some pipelines better (on others it should not - * hurt). - */ -1: - ld r11,(0x80 + 8)*0(r10) - ld r11,(0x80 + 8)*1(r10) - ld r11,(0x80 + 8)*2(r10) - ld r11,(0x80 + 8)*3(r10) - ld r11,(0x80 + 8)*4(r10) - ld r11,(0x80 + 8)*5(r10) - ld r11,(0x80 + 8)*6(r10) - ld r11,(0x80 + 8)*7(r10) - addi r10,r10,0x80*8 - bdnz 1b - + L1D_DISPLACEMENT_FLUSH mtctr r9 ld r9,PACA_EXRFI+EX_R9(r13) ld r10,PACA_EXRFI+EX_R10(r13) @@ -3079,8 +3070,21 @@ TRAMP_REAL_BEGIN(rfscv_flush_fallback) RFSCV USE_TEXT_SECTION() - MASKED_INTERRUPT - MASKED_INTERRUPT hsrr=1 + +_GLOBAL(do_uaccess_flush) + UACCESS_FLUSH_FIXUP_SECTION + nop + nop + nop + blr + L1D_DISPLACEMENT_FLUSH + blr +_ASM_NOKPROBE_SYMBOL(do_uaccess_flush) +EXPORT_SYMBOL(do_uaccess_flush) + + +MASKED_INTERRUPT +MASKED_INTERRUPT hsrr=1 #ifdef CONFIG_KVM_BOOK3S_64_HANDLER kvmppc_skip_interrupt: diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S index 44c9018aed1b..a1ae00689e0f 100644 --- a/arch/powerpc/kernel/head_40x.S +++ b/arch/powerpc/kernel/head_40x.S @@ -284,11 +284,7 @@ _ENTRY(saved_ksp_limit) rlwimi r11, r10, 22, 20, 29 /* Compute PTE address */ lwz r11, 0(r11) /* Get Linux PTE */ -#ifdef CONFIG_SWAP li r9, _PAGE_PRESENT | _PAGE_ACCESSED -#else - li r9, _PAGE_PRESENT -#endif andc. r9, r9, r11 /* Check permission */ bne 5f @@ -369,11 +365,7 @@ _ENTRY(saved_ksp_limit) rlwimi r11, r10, 22, 20, 29 /* Compute PTE address */ lwz r11, 0(r11) /* Get Linux PTE */ -#ifdef CONFIG_SWAP li r9, _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC -#else - li r9, _PAGE_PRESENT | _PAGE_EXEC -#endif andc. r9, r9, r11 /* Check permission */ bne 5f diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 9f359d3fba74..ee0bfebc375f 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -202,9 +202,7 @@ SystemCall: InstructionTLBMiss: mtspr SPRN_SPRG_SCRATCH0, r10 -#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_SWAP) || defined(CONFIG_HUGETLBFS) mtspr SPRN_SPRG_SCRATCH1, r11 -#endif /* If we are faulting a kernel address, we have to use the * kernel page tables. @@ -224,25 +222,13 @@ InstructionTLBMiss: 3: mtcr r11 #endif -#if defined(CONFIG_HUGETLBFS) || !defined(CONFIG_PIN_TLB_TEXT) lwz r11, (swapper_pg_dir-PAGE_OFFSET)@l(r10) /* Get level 1 entry */ mtspr SPRN_MD_TWC, r11 -#else - lwz r10, (swapper_pg_dir-PAGE_OFFSET)@l(r10) /* Get level 1 entry */ - mtspr SPRN_MI_TWC, r10 /* Set segment attributes */ - mtspr SPRN_MD_TWC, r10 -#endif mfspr r10, SPRN_MD_TWC lwz r10, 0(r10) /* Get the pte */ -#if defined(CONFIG_HUGETLBFS) || !defined(CONFIG_PIN_TLB_TEXT) + rlwimi r11, r10, 0, _PAGE_GUARDED | _PAGE_ACCESSED rlwimi r11, r10, 32 - 9, _PMD_PAGE_512K mtspr SPRN_MI_TWC, r11 -#endif -#ifdef CONFIG_SWAP - rlwinm r11, r10, 32-5, _PAGE_PRESENT - and r11, r11, r10 - rlwimi r10, r11, 0, _PAGE_PRESENT -#endif /* The Linux PTE won't go exactly into the MMU TLB. * Software indicator bits 20 and 23 must be clear. * Software indicator bits 22, 24, 25, 26, and 27 must be @@ -256,9 +242,7 @@ InstructionTLBMiss: /* Restore registers */ 0: mfspr r10, SPRN_SPRG_SCRATCH0 -#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_SWAP) || defined(CONFIG_HUGETLBFS) mfspr r11, SPRN_SPRG_SCRATCH1 -#endif rfi patch_site 0b, patch__itlbmiss_exit_1 @@ -268,9 +252,7 @@ InstructionTLBMiss: addi r10, r10, 1 stw r10, (itlb_miss_counter - PAGE_OFFSET)@l(0) mfspr r10, SPRN_SPRG_SCRATCH0 -#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_SWAP) mfspr r11, SPRN_SPRG_SCRATCH1 -#endif rfi #endif @@ -297,30 +279,16 @@ DataStoreTLBMiss: mfspr r10, SPRN_MD_TWC lwz r10, 0(r10) /* Get the pte */ - /* Insert the Guarded flag into the TWC from the Linux PTE. + /* Insert Guarded and Accessed flags into the TWC from the Linux PTE. * It is bit 27 of both the Linux PTE and the TWC (at least * I got that right :-). It will be better when we can put * this into the Linux pgd/pmd and load it in the operation * above. */ - rlwimi r11, r10, 0, _PAGE_GUARDED + rlwimi r11, r10, 0, _PAGE_GUARDED | _PAGE_ACCESSED rlwimi r11, r10, 32 - 9, _PMD_PAGE_512K mtspr SPRN_MD_TWC, r11 - /* Both _PAGE_ACCESSED and _PAGE_PRESENT has to be set. - * We also need to know if the insn is a load/store, so: - * Clear _PAGE_PRESENT and load that which will - * trap into DTLB Error with store bit set accordinly. - */ - /* PRESENT=0x1, ACCESSED=0x20 - * r11 = ((r10 & PRESENT) & ((r10 & ACCESSED) >> 5)); - * r10 = (r10 & ~PRESENT) | r11; - */ -#ifdef CONFIG_SWAP - rlwinm r11, r10, 32-5, _PAGE_PRESENT - and r11, r11, r10 - rlwimi r10, r11, 0, _PAGE_PRESENT -#endif /* The Linux PTE won't go exactly into the MMU TLB. * Software indicator bits 24, 25, 26, and 27 must be * set. All other Linux PTE bits control the behavior @@ -711,7 +679,7 @@ initial_mmu: li r9, 4 /* up to 4 pages of 8M */ mtctr r9 lis r9, KERNELBASE@h /* Create vaddr for TLB */ - li r10, MI_PS8MEG | MI_SVALID /* Set 8M byte page */ + li r10, MI_PS8MEG | _PMD_ACCESSED | MI_SVALID li r11, MI_BOOTINIT /* Create RPN for address 0 */ 1: mtspr SPRN_MI_CTR, r8 /* Set instruction MMU control */ @@ -775,7 +743,7 @@ _GLOBAL(mmu_pin_tlb) #ifdef CONFIG_PIN_TLB_TEXT LOAD_REG_IMMEDIATE(r5, 28 << 8) LOAD_REG_IMMEDIATE(r6, PAGE_OFFSET) - LOAD_REG_IMMEDIATE(r7, MI_SVALID | MI_PS8MEG) + LOAD_REG_IMMEDIATE(r7, MI_SVALID | MI_PS8MEG | _PMD_ACCESSED) LOAD_REG_IMMEDIATE(r8, 0xf0 | _PAGE_RO | _PAGE_SPS | _PAGE_SH | _PAGE_PRESENT) LOAD_REG_ADDR(r9, _sinittext) li r0, 4 @@ -797,7 +765,7 @@ _GLOBAL(mmu_pin_tlb) LOAD_REG_IMMEDIATE(r5, 28 << 8 | MD_TWAM) #ifdef CONFIG_PIN_TLB_DATA LOAD_REG_IMMEDIATE(r6, PAGE_OFFSET) - LOAD_REG_IMMEDIATE(r7, MI_SVALID | MI_PS8MEG) + LOAD_REG_IMMEDIATE(r7, MI_SVALID | MI_PS8MEG | _PMD_ACCESSED) #ifdef CONFIG_PIN_TLB_IMMR li r0, 3 #else @@ -834,7 +802,7 @@ _GLOBAL(mmu_pin_tlb) #endif #ifdef CONFIG_PIN_TLB_IMMR LOAD_REG_IMMEDIATE(r0, VIRT_IMMR_BASE | MD_EVALID) - LOAD_REG_IMMEDIATE(r7, MD_SVALID | MD_PS512K | MD_GUARDED) + LOAD_REG_IMMEDIATE(r7, MD_SVALID | MD_PS512K | MD_GUARDED | _PMD_ACCESSED) mfspr r8, SPRN_IMMR rlwinm r8, r8, 0, 0xfff80000 ori r8, r8, 0xf0 | _PAGE_DIRTY | _PAGE_SPS | _PAGE_SH | \ diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S index 5eb9eedac920..2aa16d5368e1 100644 --- a/arch/powerpc/kernel/head_book3s_32.S +++ b/arch/powerpc/kernel/head_book3s_32.S @@ -457,11 +457,7 @@ InstructionTLBMiss: cmplw 0,r1,r3 #endif mfspr r2, SPRN_SPRG_PGDIR -#ifdef CONFIG_SWAP li r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC -#else - li r1,_PAGE_PRESENT | _PAGE_EXEC -#endif #if defined(CONFIG_MODULES) || defined(CONFIG_DEBUG_PAGEALLOC) bgt- 112f lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */ @@ -523,11 +519,7 @@ DataLoadTLBMiss: lis r1, TASK_SIZE@h /* check if kernel address */ cmplw 0,r1,r3 mfspr r2, SPRN_SPRG_PGDIR -#ifdef CONFIG_SWAP li r1, _PAGE_PRESENT | _PAGE_ACCESSED -#else - li r1, _PAGE_PRESENT -#endif bgt- 112f lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */ addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */ @@ -603,11 +595,7 @@ DataStoreTLBMiss: lis r1, TASK_SIZE@h /* check if kernel address */ cmplw 0,r1,r3 mfspr r2, SPRN_SPRG_PGDIR -#ifdef CONFIG_SWAP li r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT | _PAGE_ACCESSED -#else - li r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT -#endif bgt- 112f lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */ addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */ diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index bb9cab3641d7..74fd47f46fa5 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -945,7 +945,13 @@ early_initcall(disable_hardlockup_detector); static enum l1d_flush_type enabled_flush_types; static void *l1d_flush_fallback_area; static bool no_rfi_flush; +static bool no_entry_flush; +static bool no_uaccess_flush; bool rfi_flush; +bool entry_flush; +bool uaccess_flush; +DEFINE_STATIC_KEY_FALSE(uaccess_flush_key); +EXPORT_SYMBOL(uaccess_flush_key); static int __init handle_no_rfi_flush(char *p) { @@ -955,6 +961,22 @@ static int __init handle_no_rfi_flush(char *p) } early_param("no_rfi_flush", handle_no_rfi_flush); +static int __init handle_no_entry_flush(char *p) +{ + pr_info("entry-flush: disabled on command line."); + no_entry_flush = true; + return 0; +} +early_param("no_entry_flush", handle_no_entry_flush); + +static int __init handle_no_uaccess_flush(char *p) +{ + pr_info("uaccess-flush: disabled on command line."); + no_uaccess_flush = true; + return 0; +} +early_param("no_uaccess_flush", handle_no_uaccess_flush); + /* * The RFI flush is not KPTI, but because users will see doco that says to use * nopti we hijack that option here to also disable the RFI flush. @@ -986,6 +1008,32 @@ void rfi_flush_enable(bool enable) rfi_flush = enable; } +void entry_flush_enable(bool enable) +{ + if (enable) { + do_entry_flush_fixups(enabled_flush_types); + on_each_cpu(do_nothing, NULL, 1); + } else { + do_entry_flush_fixups(L1D_FLUSH_NONE); + } + + entry_flush = enable; +} + +void uaccess_flush_enable(bool enable) +{ + if (enable) { + do_uaccess_flush_fixups(enabled_flush_types); + static_branch_enable(&uaccess_flush_key); + on_each_cpu(do_nothing, NULL, 1); + } else { + static_branch_disable(&uaccess_flush_key); + do_uaccess_flush_fixups(L1D_FLUSH_NONE); + } + + uaccess_flush = enable; +} + static void __ref init_fallback_flush(void) { u64 l1d_size, limit; @@ -1044,10 +1092,28 @@ void setup_rfi_flush(enum l1d_flush_type types, bool enable) enabled_flush_types = types; - if (!no_rfi_flush && !cpu_mitigations_off()) + if (!cpu_mitigations_off() && !no_rfi_flush) rfi_flush_enable(enable); } +void setup_entry_flush(bool enable) +{ + if (cpu_mitigations_off()) + return; + + if (!no_entry_flush) + entry_flush_enable(enable); +} + +void setup_uaccess_flush(bool enable) +{ + if (cpu_mitigations_off()) + return; + + if (!no_uaccess_flush) + uaccess_flush_enable(enable); +} + #ifdef CONFIG_DEBUG_FS static int rfi_flush_set(void *data, u64 val) { @@ -1075,9 +1141,63 @@ static int rfi_flush_get(void *data, u64 *val) DEFINE_SIMPLE_ATTRIBUTE(fops_rfi_flush, rfi_flush_get, rfi_flush_set, "%llu\n"); +static int entry_flush_set(void *data, u64 val) +{ + bool enable; + + if (val == 1) + enable = true; + else if (val == 0) + enable = false; + else + return -EINVAL; + + /* Only do anything if we're changing state */ + if (enable != entry_flush) + entry_flush_enable(enable); + + return 0; +} + +static int entry_flush_get(void *data, u64 *val) +{ + *val = entry_flush ? 1 : 0; + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(fops_entry_flush, entry_flush_get, entry_flush_set, "%llu\n"); + +static int uaccess_flush_set(void *data, u64 val) +{ + bool enable; + + if (val == 1) + enable = true; + else if (val == 0) + enable = false; + else + return -EINVAL; + + /* Only do anything if we're changing state */ + if (enable != uaccess_flush) + uaccess_flush_enable(enable); + + return 0; +} + +static int uaccess_flush_get(void *data, u64 *val) +{ + *val = uaccess_flush ? 1 : 0; + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(fops_uaccess_flush, uaccess_flush_get, uaccess_flush_set, "%llu\n"); + static __init int rfi_flush_debugfs_init(void) { debugfs_create_file("rfi_flush", 0600, powerpc_debugfs_root, NULL, &fops_rfi_flush); + debugfs_create_file("entry_flush", 0600, powerpc_debugfs_root, NULL, &fops_entry_flush); + debugfs_create_file("uaccess_flush", 0600, powerpc_debugfs_root, NULL, &fops_uaccess_flush); return 0; } device_initcall(rfi_flush_debugfs_init); diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 3c6b9822f978..8c2857cbd960 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -1393,13 +1393,14 @@ static void add_cpu_to_masks(int cpu) /* Activate a secondary processor. */ void start_secondary(void *unused) { - unsigned int cpu = smp_processor_id(); + unsigned int cpu = raw_smp_processor_id(); mmgrab(&init_mm); current->active_mm = &init_mm; smp_store_cpu_info(cpu); set_dec(tb_ticks_per_jiffy); + rcu_cpu_starting(cpu); preempt_disable(); cpu_callin_map[cpu] = 1; diff --git a/arch/powerpc/kernel/syscall_64.c b/arch/powerpc/kernel/syscall_64.c index 8e50818aa50b..310bcd768cd5 100644 --- a/arch/powerpc/kernel/syscall_64.c +++ b/arch/powerpc/kernel/syscall_64.c @@ -2,7 +2,7 @@ #include <linux/err.h> #include <asm/asm-prototypes.h> -#include <asm/book3s/64/kup-radix.h> +#include <asm/kup.h> #include <asm/cputime.h> #include <asm/hw_irq.h> #include <asm/kprobes.h> diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index e0548b4950de..6db90cdf11da 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -132,6 +132,20 @@ SECTIONS } . = ALIGN(8); + __uaccess_flush_fixup : AT(ADDR(__uaccess_flush_fixup) - LOAD_OFFSET) { + __start___uaccess_flush_fixup = .; + *(__uaccess_flush_fixup) + __stop___uaccess_flush_fixup = .; + } + + . = ALIGN(8); + __entry_flush_fixup : AT(ADDR(__entry_flush_fixup) - LOAD_OFFSET) { + __start___entry_flush_fixup = .; + *(__entry_flush_fixup) + __stop___entry_flush_fixup = .; + } + + . = ALIGN(8); __stf_exit_barrier_fixup : AT(ADDR(__stf_exit_barrier_fixup) - LOAD_OFFSET) { __start___stf_exit_barrier_fixup = .; *(__stf_exit_barrier_fixup) diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c index 4c0a7ee9fa00..321c12a9ef6b 100644 --- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -234,6 +234,110 @@ void do_stf_barrier_fixups(enum stf_barrier_type types) do_stf_exit_barrier_fixups(types); } +void do_uaccess_flush_fixups(enum l1d_flush_type types) +{ + unsigned int instrs[4], *dest; + long *start, *end; + int i; + + start = PTRRELOC(&__start___uaccess_flush_fixup); + end = PTRRELOC(&__stop___uaccess_flush_fixup); + + instrs[0] = 0x60000000; /* nop */ + instrs[1] = 0x60000000; /* nop */ + instrs[2] = 0x60000000; /* nop */ + instrs[3] = 0x4e800020; /* blr */ + + i = 0; + if (types == L1D_FLUSH_FALLBACK) { + instrs[3] = 0x60000000; /* nop */ + /* fallthrough to fallback flush */ + } + + if (types & L1D_FLUSH_ORI) { + instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */ + instrs[i++] = 0x63de0000; /* ori 30,30,0 L1d flush*/ + } + + if (types & L1D_FLUSH_MTTRIG) + instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */ + + for (i = 0; start < end; start++, i++) { + dest = (void *)start + *start; + + pr_devel("patching dest %lx\n", (unsigned long)dest); + + patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0])); + + patch_instruction((struct ppc_inst *)(dest + 1), ppc_inst(instrs[1])); + patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2])); + patch_instruction((struct ppc_inst *)(dest + 3), ppc_inst(instrs[3])); + } + + printk(KERN_DEBUG "uaccess-flush: patched %d locations (%s flush)\n", i, + (types == L1D_FLUSH_NONE) ? "no" : + (types == L1D_FLUSH_FALLBACK) ? "fallback displacement" : + (types & L1D_FLUSH_ORI) ? (types & L1D_FLUSH_MTTRIG) + ? "ori+mttrig type" + : "ori type" : + (types & L1D_FLUSH_MTTRIG) ? "mttrig type" + : "unknown"); +} + +void do_entry_flush_fixups(enum l1d_flush_type types) +{ + unsigned int instrs[3], *dest; + long *start, *end; + int i; + + start = PTRRELOC(&__start___entry_flush_fixup); + end = PTRRELOC(&__stop___entry_flush_fixup); + + instrs[0] = 0x60000000; /* nop */ + instrs[1] = 0x60000000; /* nop */ + instrs[2] = 0x60000000; /* nop */ + + i = 0; + if (types == L1D_FLUSH_FALLBACK) { + instrs[i++] = 0x7d4802a6; /* mflr r10 */ + instrs[i++] = 0x60000000; /* branch patched below */ + instrs[i++] = 0x7d4803a6; /* mtlr r10 */ + } + + if (types & L1D_FLUSH_ORI) { + instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */ + instrs[i++] = 0x63de0000; /* ori 30,30,0 L1d flush*/ + } + + if (types & L1D_FLUSH_MTTRIG) + instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */ + + for (i = 0; start < end; start++, i++) { + dest = (void *)start + *start; + + pr_devel("patching dest %lx\n", (unsigned long)dest); + + patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0])); + + if (types == L1D_FLUSH_FALLBACK) + patch_branch((struct ppc_inst *)(dest + 1), (unsigned long)&entry_flush_fallback, + BRANCH_SET_LINK); + else + patch_instruction((struct ppc_inst *)(dest + 1), ppc_inst(instrs[1])); + + patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2])); + } + + printk(KERN_DEBUG "entry-flush: patched %d locations (%s flush)\n", i, + (types == L1D_FLUSH_NONE) ? "no" : + (types == L1D_FLUSH_FALLBACK) ? "fallback displacement" : + (types & L1D_FLUSH_ORI) ? (types & L1D_FLUSH_MTTRIG) + ? "ori+mttrig type" + : "ori type" : + (types & L1D_FLUSH_MTTRIG) ? "mttrig type" + : "unknown"); +} + void do_rfi_flush_fixups(enum l1d_flush_type types) { unsigned int instrs[3], *dest; diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 01ec2a252f09..3fc325bebe4d 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -50,6 +50,7 @@ #include <asm/rtas.h> #include <asm/kasan.h> #include <asm/svm.h> +#include <asm/mmzone.h> #include <mm/mmu_decl.h> diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c index 9ed4fcccf8a9..7b25548ec42b 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -1336,7 +1336,7 @@ static void dump_trace_imc_data(struct perf_event *event) /* If this is a valid record, create the sample */ struct perf_output_handle handle; - if (perf_output_begin(&handle, event, header.size)) + if (perf_output_begin(&handle, &data, event, header.size)) return; perf_output_sample(&handle, &header, &data, event); diff --git a/arch/powerpc/perf/perf_regs.c b/arch/powerpc/perf/perf_regs.c index 8e53f2fc3fe0..6f681b105eec 100644 --- a/arch/powerpc/perf/perf_regs.c +++ b/arch/powerpc/perf/perf_regs.c @@ -144,8 +144,7 @@ u64 perf_reg_abi(struct task_struct *task) } void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { regs_user->regs = task_pt_regs(current); regs_user->abi = (regs_user->regs) ? perf_reg_abi(current) : diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index 9acaa0f131b9..46115231a3b2 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -98,7 +98,7 @@ static void init_fw_feat_flags(struct device_node *np) security_ftr_clear(SEC_FTR_BNDS_CHK_SPEC_BAR); } -static void pnv_setup_rfi_flush(void) +static void pnv_setup_security_mitigations(void) { struct device_node *np, *fw_features; enum l1d_flush_type type; @@ -122,12 +122,31 @@ static void pnv_setup_rfi_flush(void) type = L1D_FLUSH_ORI; } + /* + * If we are non-Power9 bare metal, we don't need to flush on kernel + * entry or after user access: they fix a P9 specific vulnerability. + */ + if (!pvr_version_is(PVR_POWER9)) { + security_ftr_clear(SEC_FTR_L1D_FLUSH_ENTRY); + security_ftr_clear(SEC_FTR_L1D_FLUSH_UACCESS); + } + enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && \ (security_ftr_enabled(SEC_FTR_L1D_FLUSH_PR) || \ security_ftr_enabled(SEC_FTR_L1D_FLUSH_HV)); setup_rfi_flush(type, enable); setup_count_cache_flush(); + + enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && + security_ftr_enabled(SEC_FTR_L1D_FLUSH_ENTRY); + setup_entry_flush(enable); + + enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && + security_ftr_enabled(SEC_FTR_L1D_FLUSH_UACCESS); + setup_uaccess_flush(enable); + + setup_stf_barrier(); } static void __init pnv_check_guarded_cores(void) @@ -156,8 +175,7 @@ static void __init pnv_setup_arch(void) { set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT); - pnv_setup_rfi_flush(); - setup_stf_barrier(); + pnv_setup_security_mitigations(); /* Initialize SMP */ pnv_smp_init(); diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index d6f4162478a5..2f73cb5bf12d 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -349,8 +349,8 @@ void post_mobility_fixup(void) cpus_read_unlock(); - /* Possibly switch to a new RFI flush type */ - pseries_setup_rfi_flush(); + /* Possibly switch to a new L1 flush type */ + pseries_setup_security_mitigations(); /* Reinitialise system information for hv-24x7 */ read_24x7_sys_info(); diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h index 13fa370a87e4..593840847cd3 100644 --- a/arch/powerpc/platforms/pseries/pseries.h +++ b/arch/powerpc/platforms/pseries/pseries.h @@ -111,7 +111,7 @@ static inline unsigned long cmo_get_page_size(void) int dlpar_workqueue_init(void); -void pseries_setup_rfi_flush(void); +void pseries_setup_security_mitigations(void); void pseries_lpar_read_hblkrm_characteristics(void); #endif /* _PSERIES_PSERIES_H */ diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 633c45ec406d..090c13f6c881 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -542,7 +542,7 @@ static void init_cpu_char_feature_flags(struct h_cpu_char_result *result) security_ftr_clear(SEC_FTR_BNDS_CHK_SPEC_BAR); } -void pseries_setup_rfi_flush(void) +void pseries_setup_security_mitigations(void) { struct h_cpu_char_result result; enum l1d_flush_type types; @@ -579,6 +579,16 @@ void pseries_setup_rfi_flush(void) setup_rfi_flush(types, enable); setup_count_cache_flush(); + + enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && + security_ftr_enabled(SEC_FTR_L1D_FLUSH_ENTRY); + setup_entry_flush(enable); + + enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && + security_ftr_enabled(SEC_FTR_L1D_FLUSH_UACCESS); + setup_uaccess_flush(enable); + + setup_stf_barrier(); } #ifdef CONFIG_PCI_IOV @@ -768,8 +778,7 @@ static void __init pSeries_setup_arch(void) fwnmi_init(); - pseries_setup_rfi_flush(); - setup_stf_barrier(); + pseries_setup_security_mitigations(); pseries_lpar_read_hblkrm_characteristics(); /* By default, only probe PCI (can be overridden by rtas_pci) */ diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h index c47e6b35c551..824b2c9da75b 100644 --- a/arch/riscv/include/asm/uaccess.h +++ b/arch/riscv/include/asm/uaccess.h @@ -476,7 +476,7 @@ do { \ do { \ long __kr_err; \ \ - __put_user_nocheck(*((type *)(dst)), (type *)(src), __kr_err); \ + __put_user_nocheck(*((type *)(src)), (type *)(dst), __kr_err); \ if (unlikely(__kr_err)) \ goto err_label; \ } while (0) diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c index 99e12faa5498..765b62434f30 100644 --- a/arch/riscv/kernel/ftrace.c +++ b/arch/riscv/kernel/ftrace.c @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2013 Linaro Limited * Author: AKASHI Takahiro <takahiro.akashi@linaro.org> diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index 11e2a4fe66e0..7e849797c9c3 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -35,6 +35,10 @@ ENTRY(_start) .word 0 #endif .balign 8 +#ifdef CONFIG_RISCV_M_MODE + /* Image load offset (0MB) from start of RAM for M-mode */ + .dword 0 +#else #if __riscv_xlen == 64 /* Image load offset(2MB) from start of RAM */ .dword 0x200000 @@ -42,6 +46,7 @@ ENTRY(_start) /* Image load offset(4MB) from start of RAM */ .dword 0x400000 #endif +#endif /* Effective size of kernel image */ .dword _end - _start .dword __HEAD_FLAGS diff --git a/arch/riscv/kernel/perf_regs.c b/arch/riscv/kernel/perf_regs.c index 04a38fbeb9c7..fd304a248de6 100644 --- a/arch/riscv/kernel/perf_regs.c +++ b/arch/riscv/kernel/perf_regs.c @@ -36,8 +36,7 @@ u64 perf_reg_abi(struct task_struct *task) } void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { regs_user->regs = task_pt_regs(current); regs_user->abi = perf_reg_abi(current); diff --git a/arch/riscv/kernel/vdso/.gitignore b/arch/riscv/kernel/vdso/.gitignore index 11ebee9e4c1d..3a19def868ec 100644 --- a/arch/riscv/kernel/vdso/.gitignore +++ b/arch/riscv/kernel/vdso/.gitignore @@ -1,3 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only vdso.lds *.tmp +vdso-syms.S diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile index 7d6a94d45ec9..cb8f9e4cfcbf 100644 --- a/arch/riscv/kernel/vdso/Makefile +++ b/arch/riscv/kernel/vdso/Makefile @@ -43,19 +43,14 @@ $(obj)/vdso.o: $(obj)/vdso.so SYSCFLAGS_vdso.so.dbg = $(c_flags) $(obj)/vdso.so.dbg: $(src)/vdso.lds $(obj-vdso) FORCE $(call if_changed,vdsold) +SYSCFLAGS_vdso.so.dbg = -shared -s -Wl,-soname=linux-vdso.so.1 \ + -Wl,--build-id -Wl,--hash-style=both # We also create a special relocatable object that should mirror the symbol # table and layout of the linked DSO. With ld --just-symbols we can then # refer to these symbols in the kernel code rather than hand-coded addresses. - -SYSCFLAGS_vdso.so.dbg = -shared -s -Wl,-soname=linux-vdso.so.1 \ - -Wl,--build-id=sha1 -Wl,--hash-style=both -$(obj)/vdso-dummy.o: $(src)/vdso.lds $(obj)/rt_sigreturn.o FORCE - $(call if_changed,vdsold) - -LDFLAGS_vdso-syms.o := -r --just-symbols -$(obj)/vdso-syms.o: $(obj)/vdso-dummy.o FORCE - $(call if_changed,ld) +$(obj)/vdso-syms.S: $(obj)/vdso.so FORCE + $(call if_changed,so2s) # strip rule for the .so file $(obj)/%.so: OBJCOPYFLAGS := -S @@ -73,6 +68,11 @@ quiet_cmd_vdsold = VDSOLD $@ $(patsubst %, -G __vdso_%, $(vdso-syms)) $@.tmp $@ && \ rm $@.tmp +# Extracts symbol offsets from the VDSO, converting them into an assembly file +# that contains the same symbols at the same offsets. +quiet_cmd_so2s = SO2S $@ + cmd_so2s = $(NM) -D $< | $(srctree)/$(src)/so2s.sh > $@ + # install commands for the unstripped file quiet_cmd_vdso_install = INSTALL $@ cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@ diff --git a/arch/riscv/kernel/vdso/so2s.sh b/arch/riscv/kernel/vdso/so2s.sh new file mode 100755 index 000000000000..e64cb6d9440e --- /dev/null +++ b/arch/riscv/kernel/vdso/so2s.sh @@ -0,0 +1,6 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0+ +# Copyright 2020 Palmer Dabbelt <palmerdabbelt@google.com> + +sed 's!\([0-9a-f]*\) T \([a-z0-9_]*\)\(@@LINUX_4.15\)*!.global \2\n.set \2,0x\1!' \ +| grep '^\.' diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 1359e21c0c62..3c8b9e433c67 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -86,6 +86,7 @@ static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long a pmd_t *pmd, *pmd_k; pte_t *pte_k; int index; + unsigned long pfn; /* User mode accesses just cause a SIGSEGV */ if (user_mode(regs)) @@ -100,7 +101,8 @@ static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long a * of a task switch. */ index = pgd_index(addr); - pgd = (pgd_t *)pfn_to_virt(csr_read(CSR_SATP)) + index; + pfn = csr_read(CSR_SATP) & SATP_PPN; + pgd = (pgd_t *)pfn_to_virt(pfn) + index; pgd_k = init_mm.pgd + index; if (!pgd_present(*pgd_k)) { diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index ea933b789a88..8e577f14f120 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -154,9 +154,8 @@ disable: void __init setup_bootmem(void) { - phys_addr_t mem_size = 0; - phys_addr_t total_mem = 0; - phys_addr_t mem_start, start, end = 0; + phys_addr_t mem_start = 0; + phys_addr_t start, end = 0; phys_addr_t vmlinux_end = __pa_symbol(&_end); phys_addr_t vmlinux_start = __pa_symbol(&_start); u64 i; @@ -164,21 +163,18 @@ void __init setup_bootmem(void) /* Find the memory region containing the kernel */ for_each_mem_range(i, &start, &end) { phys_addr_t size = end - start; - if (!total_mem) + if (!mem_start) mem_start = start; if (start <= vmlinux_start && vmlinux_end <= end) BUG_ON(size == 0); - total_mem = total_mem + size; } /* - * Remove memblock from the end of usable area to the - * end of region + * The maximal physical memory size is -PAGE_OFFSET. + * Make sure that any memory beyond mem_start + (-PAGE_OFFSET) is removed + * as it is unusable by kernel. */ - mem_size = min(total_mem, (phys_addr_t)-PAGE_OFFSET); - if (mem_start + mem_size < end) - memblock_remove(mem_start + mem_size, - end - mem_start - mem_size); + memblock_enforce_memory_limit(mem_start - PAGE_OFFSET); /* Reserve from the start of the kernel to the end of the kernel */ memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start); @@ -297,6 +293,7 @@ pmd_t fixmap_pmd[PTRS_PER_PMD] __page_aligned_bss; #define NUM_EARLY_PMDS (1UL + MAX_EARLY_MAPPING_SIZE / PGDIR_SIZE) #endif pmd_t early_pmd[PTRS_PER_PMD * NUM_EARLY_PMDS] __initdata __aligned(PAGE_SIZE); +pmd_t early_dtb_pmd[PTRS_PER_PMD] __initdata __aligned(PAGE_SIZE); static pmd_t *__init get_pmd_virt_early(phys_addr_t pa) { @@ -494,6 +491,18 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) load_pa + (va - PAGE_OFFSET), map_size, PAGE_KERNEL_EXEC); +#ifndef __PAGETABLE_PMD_FOLDED + /* Setup early PMD for DTB */ + create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA, + (uintptr_t)early_dtb_pmd, PGDIR_SIZE, PAGE_TABLE); + /* Create two consecutive PMD mappings for FDT early scan */ + pa = dtb_pa & ~(PMD_SIZE - 1); + create_pmd_mapping(early_dtb_pmd, DTB_EARLY_BASE_VA, + pa, PMD_SIZE, PAGE_KERNEL); + create_pmd_mapping(early_dtb_pmd, DTB_EARLY_BASE_VA + PMD_SIZE, + pa + PMD_SIZE, PMD_SIZE, PAGE_KERNEL); + dtb_early_va = (void *)DTB_EARLY_BASE_VA + (dtb_pa & (PMD_SIZE - 1)); +#else /* Create two consecutive PGD mappings for FDT early scan */ pa = dtb_pa & ~(PGDIR_SIZE - 1); create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA, @@ -501,6 +510,7 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA + PGDIR_SIZE, pa + PGDIR_SIZE, PGDIR_SIZE, PAGE_KERNEL); dtb_early_va = (void *)DTB_EARLY_BASE_VA + (dtb_pa & (PGDIR_SIZE - 1)); +#endif dtb_early_pa = dtb_pa; /* diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 0784bf3caf43..fe6f529ac82c 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -1,3 +1,4 @@ +CONFIG_UAPI_HEADER_TEST=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_WATCH_QUEUE=y @@ -93,9 +94,10 @@ CONFIG_CLEANCACHE=y CONFIG_FRONTSWAP=y CONFIG_CMA_DEBUG=y CONFIG_CMA_DEBUGFS=y +CONFIG_CMA_AREAS=7 CONFIG_MEM_SOFT_DIRTY=y CONFIG_ZSWAP=y -CONFIG_ZSMALLOC=m +CONFIG_ZSMALLOC=y CONFIG_ZSMALLOC_STAT=y CONFIG_DEFERRED_STRUCT_PAGE_INIT=y CONFIG_IDLE_PAGE_TRACKING=y @@ -378,7 +380,6 @@ CONFIG_NETLINK_DIAG=m CONFIG_CGROUP_NET_PRIO=y CONFIG_BPF_JIT=y CONFIG_NET_PKTGEN=m -# CONFIG_NET_DROP_MONITOR is not set CONFIG_PCI=y # CONFIG_PCIEASPM is not set CONFIG_PCI_DEBUG=y @@ -386,7 +387,7 @@ CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_S390=y CONFIG_DEVTMPFS=y CONFIG_CONNECTOR=y -CONFIG_ZRAM=m +CONFIG_ZRAM=y CONFIG_BLK_DEV_LOOP=m CONFIG_BLK_DEV_CRYPTOLOOP=m CONFIG_BLK_DEV_DRBD=m @@ -689,6 +690,7 @@ CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m +CONFIG_CRYPTO_SM2=m CONFIG_CRYPTO_CURVE25519=m CONFIG_CRYPTO_GCM=y CONFIG_CRYPTO_CHACHA20POLY1305=m @@ -709,7 +711,6 @@ CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_RMD256=m CONFIG_CRYPTO_RMD320=m CONFIG_CRYPTO_SHA3=m -CONFIG_CRYPTO_SM3=m CONFIG_CRYPTO_TGR192=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_AES_TI=m @@ -753,6 +754,7 @@ CONFIG_CRYPTO_DES_S390=m CONFIG_CRYPTO_AES_S390=m CONFIG_CRYPTO_GHASH_S390=m CONFIG_CRYPTO_CRC32_S390=y +CONFIG_CRYPTO_DEV_VIRTIO=m CONFIG_CORDIC=m CONFIG_CRC32_SELFTEST=y CONFIG_CRC4=m @@ -829,6 +831,7 @@ CONFIG_NETDEV_NOTIFIER_ERROR_INJECT=m CONFIG_FAULT_INJECTION=y CONFIG_FAILSLAB=y CONFIG_FAIL_PAGE_ALLOC=y +CONFIG_FAULT_INJECTION_USERCOPY=y CONFIG_FAIL_MAKE_REQUEST=y CONFIG_FAIL_IO_TIMEOUT=y CONFIG_FAIL_FUTEX=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 905bc8c4cfaf..17d5df2c1eff 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -87,9 +87,10 @@ CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y CONFIG_CLEANCACHE=y CONFIG_FRONTSWAP=y +CONFIG_CMA_AREAS=7 CONFIG_MEM_SOFT_DIRTY=y CONFIG_ZSWAP=y -CONFIG_ZSMALLOC=m +CONFIG_ZSMALLOC=y CONFIG_ZSMALLOC_STAT=y CONFIG_DEFERRED_STRUCT_PAGE_INIT=y CONFIG_IDLE_PAGE_TRACKING=y @@ -371,7 +372,6 @@ CONFIG_NETLINK_DIAG=m CONFIG_CGROUP_NET_PRIO=y CONFIG_BPF_JIT=y CONFIG_NET_PKTGEN=m -# CONFIG_NET_DROP_MONITOR is not set CONFIG_PCI=y # CONFIG_PCIEASPM is not set CONFIG_HOTPLUG_PCI=y @@ -379,7 +379,7 @@ CONFIG_HOTPLUG_PCI_S390=y CONFIG_UEVENT_HELPER=y CONFIG_DEVTMPFS=y CONFIG_CONNECTOR=y -CONFIG_ZRAM=m +CONFIG_ZRAM=y CONFIG_BLK_DEV_LOOP=m CONFIG_BLK_DEV_CRYPTOLOOP=m CONFIG_BLK_DEV_DRBD=m @@ -680,6 +680,7 @@ CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m +CONFIG_CRYPTO_SM2=m CONFIG_CRYPTO_CURVE25519=m CONFIG_CRYPTO_GCM=y CONFIG_CRYPTO_CHACHA20POLY1305=m @@ -701,7 +702,6 @@ CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_RMD256=m CONFIG_CRYPTO_RMD320=m CONFIG_CRYPTO_SHA3=m -CONFIG_CRYPTO_SM3=m CONFIG_CRYPTO_TGR192=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_AES_TI=m @@ -745,6 +745,7 @@ CONFIG_CRYPTO_DES_S390=m CONFIG_CRYPTO_AES_S390=m CONFIG_CRYPTO_GHASH_S390=m CONFIG_CRYPTO_CRC32_S390=y +CONFIG_CRYPTO_DEV_VIRTIO=m CONFIG_CORDIC=m CONFIG_PRIME_NUMBERS=m CONFIG_CRC4=m diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index 8f67c55625f9..a302630341ef 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -17,11 +17,11 @@ CONFIG_HZ_100=y # CONFIG_CHSC_SCH is not set # CONFIG_SCM_BUS is not set CONFIG_CRASH_DUMP=y -# CONFIG_SECCOMP is not set # CONFIG_PFAULT is not set # CONFIG_S390_HYPFS_FS is not set # CONFIG_VIRTUALIZATION is not set # CONFIG_S390_GUEST is not set +# CONFIG_SECCOMP is not set CONFIG_PARTITION_ADVANCED=y CONFIG_IBM_PARTITION=y # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 6b8d8c69b1a1..b5dbae78969b 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -692,16 +692,6 @@ static inline int pud_large(pud_t pud) return !!(pud_val(pud) & _REGION3_ENTRY_LARGE); } -static inline unsigned long pud_pfn(pud_t pud) -{ - unsigned long origin_mask; - - origin_mask = _REGION_ENTRY_ORIGIN; - if (pud_large(pud)) - origin_mask = _REGION3_ENTRY_ORIGIN_LARGE; - return (pud_val(pud) & origin_mask) >> PAGE_SHIFT; -} - #define pmd_leaf pmd_large static inline int pmd_large(pmd_t pmd) { @@ -747,16 +737,6 @@ static inline int pmd_none(pmd_t pmd) return pmd_val(pmd) == _SEGMENT_ENTRY_EMPTY; } -static inline unsigned long pmd_pfn(pmd_t pmd) -{ - unsigned long origin_mask; - - origin_mask = _SEGMENT_ENTRY_ORIGIN; - if (pmd_large(pmd)) - origin_mask = _SEGMENT_ENTRY_ORIGIN_LARGE; - return (pmd_val(pmd) & origin_mask) >> PAGE_SHIFT; -} - #define pmd_write pmd_write static inline int pmd_write(pmd_t pmd) { @@ -1238,11 +1218,39 @@ static inline pte_t mk_pte(struct page *page, pgprot_t pgprot) #define pud_index(address) (((address) >> PUD_SHIFT) & (PTRS_PER_PUD-1)) #define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1)) -#define pmd_deref(pmd) (pmd_val(pmd) & _SEGMENT_ENTRY_ORIGIN) -#define pud_deref(pud) (pud_val(pud) & _REGION_ENTRY_ORIGIN) #define p4d_deref(pud) (p4d_val(pud) & _REGION_ENTRY_ORIGIN) #define pgd_deref(pgd) (pgd_val(pgd) & _REGION_ENTRY_ORIGIN) +static inline unsigned long pmd_deref(pmd_t pmd) +{ + unsigned long origin_mask; + + origin_mask = _SEGMENT_ENTRY_ORIGIN; + if (pmd_large(pmd)) + origin_mask = _SEGMENT_ENTRY_ORIGIN_LARGE; + return pmd_val(pmd) & origin_mask; +} + +static inline unsigned long pmd_pfn(pmd_t pmd) +{ + return pmd_deref(pmd) >> PAGE_SHIFT; +} + +static inline unsigned long pud_deref(pud_t pud) +{ + unsigned long origin_mask; + + origin_mask = _REGION_ENTRY_ORIGIN; + if (pud_large(pud)) + origin_mask = _REGION3_ENTRY_ORIGIN_LARGE; + return pud_val(pud) & origin_mask; +} + +static inline unsigned long pud_pfn(pud_t pud) +{ + return pud_deref(pud) >> PAGE_SHIFT; +} + /* * The pgd_offset function *always* adds the index for the top-level * region/segment table. This is done to get a sequence like the diff --git a/arch/s390/include/asm/vdso/vdso.h b/arch/s390/include/asm/vdso/vdso.h deleted file mode 100644 index e69de29bb2d1..000000000000 --- a/arch/s390/include/asm/vdso/vdso.h +++ /dev/null diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index ece58f2217cb..2012c1cf0853 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -61,14 +61,6 @@ int main(void) BLANK(); OFFSET(__VDSO_GETCPU_VAL, vdso_per_cpu_data, getcpu_val); BLANK(); - /* constants used by the vdso */ - DEFINE(__CLOCK_REALTIME, CLOCK_REALTIME); - DEFINE(__CLOCK_MONOTONIC, CLOCK_MONOTONIC); - DEFINE(__CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE); - DEFINE(__CLOCK_MONOTONIC_COARSE, CLOCK_MONOTONIC_COARSE); - DEFINE(__CLOCK_THREAD_CPUTIME_ID, CLOCK_THREAD_CPUTIME_ID); - DEFINE(__CLOCK_COARSE_RES, LOW_RES_NSEC); - BLANK(); /* idle data offsets */ OFFSET(__CLOCK_IDLE_ENTER, s390_idle_data, clock_idle_enter); OFFSET(__CLOCK_IDLE_EXIT, s390_idle_data, clock_idle_exit); diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 86235919c2d1..5346545b9860 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -422,6 +422,7 @@ ENTRY(system_call) #endif LOCKDEP_SYS_EXIT .Lsysc_tif: + DISABLE_INTS TSTMSK __PT_FLAGS(%r11),_PIF_WORK jnz .Lsysc_work TSTMSK __TI_flags(%r12),_TIF_WORK @@ -444,6 +445,7 @@ ENTRY(system_call) # One of the work bits is on. Find out which one. # .Lsysc_work: + ENABLE_INTS TSTMSK __TI_flags(%r12),_TIF_NEED_RESCHED jo .Lsysc_reschedule TSTMSK __PT_FLAGS(%r11),_PIF_SYSCALL_RESTART diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index 4f9e4626df55..19cd7b961c45 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -672,7 +672,7 @@ static void cpumsf_output_event_pid(struct perf_event *event, rcu_read_lock(); perf_prepare_sample(&header, data, event, regs); - if (perf_output_begin(&handle, event, header.size)) + if (perf_output_begin(&handle, data, event, header.size)) goto out; /* Update the process ID (see also kernel/events/core.c) */ @@ -2228,4 +2228,4 @@ out: } arch_initcall(init_cpum_sampling_pmu); -core_param(cpum_sfb_size, CPUM_SF_MAX_SDB, sfb_size, 0640); +core_param(cpum_sfb_size, CPUM_SF_MAX_SDB, sfb_size, 0644); diff --git a/arch/s390/kernel/perf_regs.c b/arch/s390/kernel/perf_regs.c index 4352a504f235..6e9e5d5e927e 100644 --- a/arch/s390/kernel/perf_regs.c +++ b/arch/s390/kernel/perf_regs.c @@ -53,8 +53,7 @@ u64 perf_reg_abi(struct task_struct *task) } void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { /* * Use the regs from the first interruption and let diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index ebfe86d097f0..390d97daa2b3 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -855,13 +855,14 @@ void __init smp_detect_cpus(void) static void smp_init_secondary(void) { - int cpu = smp_processor_id(); + int cpu = raw_smp_processor_id(); S390_lowcore.last_update_clock = get_tod_clock(); restore_access_regs(S390_lowcore.access_regs_save_area); set_cpu_flag(CIF_ASCE_PRIMARY); set_cpu_flag(CIF_ASCE_SECONDARY); cpu_init(); + rcu_cpu_starting(cpu); preempt_disable(); init_cpu_timer(); vtime_init(); diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index d33f21545dfd..9a6bae503fe6 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -101,6 +101,10 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) if (ret) break; + /* the PCI function will be scanned once function 0 appears */ + if (!zdev->zbus->bus) + break; + pdev = pci_scan_single_device(zdev->zbus->bus, zdev->devfn); if (!pdev) break; diff --git a/arch/um/include/asm/pgalloc.h b/arch/um/include/asm/pgalloc.h index 5393e13e07e0..2bbf28cf3aa9 100644 --- a/arch/um/include/asm/pgalloc.h +++ b/arch/um/include/asm/pgalloc.h @@ -33,7 +33,13 @@ do { \ } while (0) #ifdef CONFIG_3_LEVEL_PGTABLES -#define __pmd_free_tlb(tlb,x, address) tlb_remove_page((tlb),virt_to_page(x)) + +#define __pmd_free_tlb(tlb, pmd, address) \ +do { \ + pgtable_pmd_page_dtor(virt_to_page(pmd)); \ + tlb_remove_page((tlb),virt_to_page(pmd)); \ +} while (0) \ + #endif #endif diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index a5e5db6ada3c..39b2eded7bc2 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -164,6 +164,7 @@ void initialize_identity_maps(void *rmode) add_identity_map(cmdline, cmdline + COMMAND_LINE_SIZE); /* Load the new page-table. */ + sev_verify_cbit(top_level_pgt); write_cr3(top_level_pgt); } diff --git a/arch/x86/boot/compressed/mem_encrypt.S b/arch/x86/boot/compressed/mem_encrypt.S index dd07e7b41b11..aa561795efd1 100644 --- a/arch/x86/boot/compressed/mem_encrypt.S +++ b/arch/x86/boot/compressed/mem_encrypt.S @@ -68,6 +68,9 @@ SYM_FUNC_START(get_sev_encryption_bit) SYM_FUNC_END(get_sev_encryption_bit) .code64 + +#include "../../kernel/sev_verify_cbit.S" + SYM_FUNC_START(set_sev_encryption_mask) #ifdef CONFIG_AMD_MEM_ENCRYPT push %rbp @@ -81,6 +84,19 @@ SYM_FUNC_START(set_sev_encryption_mask) bts %rax, sme_me_mask(%rip) /* Create the encryption mask */ + /* + * Read MSR_AMD64_SEV again and store it to sev_status. Can't do this in + * get_sev_encryption_bit() because this function is 32-bit code and + * shared between 64-bit and 32-bit boot path. + */ + movl $MSR_AMD64_SEV, %ecx /* Read the SEV MSR */ + rdmsr + + /* Store MSR value in sev_status */ + shlq $32, %rdx + orq %rdx, %rax + movq %rax, sev_status(%rip) + .Lno_sev_mask: movq %rbp, %rsp /* Restore original stack pointer */ @@ -96,5 +112,7 @@ SYM_FUNC_END(set_sev_encryption_mask) #ifdef CONFIG_AMD_MEM_ENCRYPT .balign 8 -SYM_DATA(sme_me_mask, .quad 0) +SYM_DATA(sme_me_mask, .quad 0) +SYM_DATA(sev_status, .quad 0) +SYM_DATA(sev_check_data, .quad 0) #endif diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 6d31f1b4c4d1..d9a631c5973c 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -159,4 +159,6 @@ void boot_page_fault(void); void boot_stage1_vc(void); void boot_stage2_vc(void); +unsigned long sev_verify_cbit(unsigned long cr3); + #endif /* BOOT_COMPRESSED_MISC_H */ diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index f1926e9f2143..af457f8cb29d 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2630,7 +2630,7 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status) u64 pebs_enabled = cpuc->pebs_enabled; handled++; - x86_pmu.drain_pebs(regs); + x86_pmu.drain_pebs(regs, &data); status &= x86_pmu.intel_ctrl | GLOBAL_STATUS_TRACE_TOPAPMI; /* @@ -4987,6 +4987,12 @@ __init int intel_pmu_init(void) x86_add_quirk(intel_arch_events_quirk); /* Install first, so it runs last */ + if (version >= 5) { + x86_pmu.intel_cap.anythread_deprecated = edx.split.anythread_deprecated; + if (x86_pmu.intel_cap.anythread_deprecated) + pr_cont(" AnyThread deprecated, "); + } + /* * Install the hw-cache-events table: */ @@ -5512,6 +5518,10 @@ __init int intel_pmu_init(void) x86_pmu.intel_ctrl |= ((1LL << x86_pmu.num_counters_fixed)-1) << INTEL_PMC_IDX_FIXED; + /* AnyThread may be deprecated on arch perfmon v5 or later */ + if (x86_pmu.intel_cap.anythread_deprecated) + x86_pmu.format_attrs = intel_arch_formats_attr; + if (x86_pmu.event_constraints) { /* * event on fixed counter2 (REF_CYCLES) only works on this diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 442e1ed4acd4..4eb7ee5fed72 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -107,14 +107,14 @@ MODULE_LICENSE("GPL"); #define DEFINE_CSTATE_FORMAT_ATTR(_var, _name, _format) \ -static ssize_t __cstate_##_var##_show(struct kobject *kobj, \ - struct kobj_attribute *attr, \ +static ssize_t __cstate_##_var##_show(struct device *dev, \ + struct device_attribute *attr, \ char *page) \ { \ BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ return sprintf(page, _format "\n"); \ } \ -static struct kobj_attribute format_attr_##_var = \ +static struct device_attribute format_attr_##_var = \ __ATTR(_name, 0444, __cstate_##_var##_show, NULL) static ssize_t cstate_get_attr_cpumask(struct device *dev, diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 404315df1e16..b47cc4226934 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -642,8 +642,8 @@ int intel_pmu_drain_bts_buffer(void) rcu_read_lock(); perf_prepare_sample(&header, &data, event, ®s); - if (perf_output_begin(&handle, event, header.size * - (top - base - skip))) + if (perf_output_begin(&handle, &data, event, + header.size * (top - base - skip))) goto unlock; for (at = base; at < top; at++) { @@ -670,7 +670,9 @@ unlock: static inline void intel_pmu_drain_pebs_buffer(void) { - x86_pmu.drain_pebs(NULL); + struct perf_sample_data data; + + x86_pmu.drain_pebs(NULL, &data); } /* @@ -1719,23 +1721,24 @@ intel_pmu_save_and_restart_reload(struct perf_event *event, int count) return 0; } -static void __intel_pmu_pebs_event(struct perf_event *event, - struct pt_regs *iregs, - void *base, void *top, - int bit, int count, - void (*setup_sample)(struct perf_event *, - struct pt_regs *, - void *, - struct perf_sample_data *, - struct pt_regs *)) +static __always_inline void +__intel_pmu_pebs_event(struct perf_event *event, + struct pt_regs *iregs, + struct perf_sample_data *data, + void *base, void *top, + int bit, int count, + void (*setup_sample)(struct perf_event *, + struct pt_regs *, + void *, + struct perf_sample_data *, + struct pt_regs *)) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; - struct perf_sample_data data; struct x86_perf_regs perf_regs; struct pt_regs *regs = &perf_regs.regs; void *at = get_next_pebs_record_by_bit(base, top, bit); - struct pt_regs dummy_iregs; + static struct pt_regs dummy_iregs; if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) { /* @@ -1752,14 +1755,14 @@ static void __intel_pmu_pebs_event(struct perf_event *event, iregs = &dummy_iregs; while (count > 1) { - setup_sample(event, iregs, at, &data, regs); - perf_event_output(event, &data, regs); + setup_sample(event, iregs, at, data, regs); + perf_event_output(event, data, regs); at += cpuc->pebs_record_size; at = get_next_pebs_record_by_bit(at, top, bit); count--; } - setup_sample(event, iregs, at, &data, regs); + setup_sample(event, iregs, at, data, regs); if (iregs == &dummy_iregs) { /* * The PEBS records may be drained in the non-overflow context, @@ -1767,18 +1770,18 @@ static void __intel_pmu_pebs_event(struct perf_event *event, * last record the same as other PEBS records, and doesn't * invoke the generic overflow handler. */ - perf_event_output(event, &data, regs); + perf_event_output(event, data, regs); } else { /* * All but the last records are processed. * The last one is left to be able to call the overflow handler. */ - if (perf_event_overflow(event, &data, regs)) + if (perf_event_overflow(event, data, regs)) x86_pmu_stop(event, 0); } } -static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) +static void intel_pmu_drain_pebs_core(struct pt_regs *iregs, struct perf_sample_data *data) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct debug_store *ds = cpuc->ds; @@ -1812,7 +1815,7 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) return; } - __intel_pmu_pebs_event(event, iregs, at, top, 0, n, + __intel_pmu_pebs_event(event, iregs, data, at, top, 0, n, setup_pebs_fixed_sample_data); } @@ -1835,7 +1838,7 @@ static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, int } } -static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) +static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_data *data) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct debug_store *ds = cpuc->ds; @@ -1942,14 +1945,14 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) } if (counts[bit]) { - __intel_pmu_pebs_event(event, iregs, base, + __intel_pmu_pebs_event(event, iregs, data, base, top, bit, counts[bit], setup_pebs_fixed_sample_data); } } } -static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs) +static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_data *data) { short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {}; struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); @@ -1997,7 +2000,7 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs) if (WARN_ON_ONCE(!event->attr.precise_ip)) continue; - __intel_pmu_pebs_event(event, iregs, base, + __intel_pmu_pebs_event(event, iregs, data, base, top, bit, counts[bit], setup_pebs_adaptive_sample_data); } diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 86d012b3e0b4..80d52cbe2fde 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -94,8 +94,8 @@ end: return map; } -ssize_t uncore_event_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf) +ssize_t uncore_event_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct uncore_event_desc *event = container_of(attr, struct uncore_event_desc, attr); diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index 83d2a7d490e0..9efea154349d 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -157,7 +157,7 @@ struct intel_uncore_box { #define UNCORE_BOX_FLAG_CFL8_CBOX_MSR_OFFS 2 struct uncore_event_desc { - struct kobj_attribute attr; + struct device_attribute attr; const char *config; }; @@ -179,8 +179,8 @@ struct pci2phy_map { struct pci2phy_map *__find_pci2phy_map(int segment); int uncore_pcibus_to_physid(struct pci_bus *bus); -ssize_t uncore_event_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf); +ssize_t uncore_event_show(struct device *dev, + struct device_attribute *attr, char *buf); static inline struct intel_uncore_pmu *dev_to_uncore_pmu(struct device *dev) { @@ -201,14 +201,14 @@ extern int __uncore_max_dies; } #define DEFINE_UNCORE_FORMAT_ATTR(_var, _name, _format) \ -static ssize_t __uncore_##_var##_show(struct kobject *kobj, \ - struct kobj_attribute *attr, \ +static ssize_t __uncore_##_var##_show(struct device *dev, \ + struct device_attribute *attr, \ char *page) \ { \ BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ return sprintf(page, _format "\n"); \ } \ -static struct kobj_attribute format_attr_##_var = \ +static struct device_attribute format_attr_##_var = \ __ATTR(_name, 0444, __uncore_##_var##_show, NULL) static inline bool uncore_pmc_fixed(int idx) diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index 39e632ed6ca9..bbd1120ae161 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -475,7 +475,7 @@ enum perf_snb_uncore_imc_freerunning_types { static struct freerunning_counters snb_uncore_imc_freerunning[] = { [SNB_PCI_UNCORE_IMC_DATA_READS] = { SNB_UNCORE_PCI_IMC_DATA_READS_BASE, 0x0, 0x0, 1, 32 }, - [SNB_PCI_UNCORE_IMC_DATA_READS] = { SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE, + [SNB_PCI_UNCORE_IMC_DATA_WRITES] = { SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE, 0x0, 0x0, 1, 32 }, [SNB_PCI_UNCORE_IMC_GT_REQUESTS] = { SNB_UNCORE_PCI_IMC_GT_REQUESTS_BASE, 0x0, 0x0, 1, 32 }, diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index ee2b9b9fc2a5..6a8edfe59b09 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -585,6 +585,7 @@ union perf_capabilities { u64 pebs_baseline:1; u64 perf_metrics:1; u64 pebs_output_pt_available:1; + u64 anythread_deprecated:1; }; u64 capabilities; }; @@ -727,7 +728,7 @@ struct x86_pmu { int pebs_record_size; int pebs_buffer_size; int max_pebs_events; - void (*drain_pebs)(struct pt_regs *regs); + void (*drain_pebs)(struct pt_regs *regs, struct perf_sample_data *data); struct event_constraint *pebs_constraints; void (*pebs_aliases)(struct perf_event *event); unsigned long large_pebs_flags; diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c index 7c0120e2e957..7dbbeaacd995 100644 --- a/arch/x86/events/rapl.c +++ b/arch/x86/events/rapl.c @@ -93,18 +93,6 @@ static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = { * any other bit is reserved */ #define RAPL_EVENT_MASK 0xFFULL - -#define DEFINE_RAPL_FORMAT_ATTR(_var, _name, _format) \ -static ssize_t __rapl_##_var##_show(struct kobject *kobj, \ - struct kobj_attribute *attr, \ - char *page) \ -{ \ - BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ - return sprintf(page, _format "\n"); \ -} \ -static struct kobj_attribute format_attr_##_var = \ - __ATTR(_name, 0444, __rapl_##_var##_show, NULL) - #define RAPL_CNTR_WIDTH 32 #define RAPL_EVENT_ATTR_STR(_name, v, str) \ @@ -441,7 +429,7 @@ static struct attribute_group rapl_pmu_events_group = { .attrs = attrs_empty, }; -DEFINE_RAPL_FORMAT_ATTR(event, event, "config:0-7"); +PMU_FORMAT_ATTR(event, "config:0-7"); static struct attribute *rapl_formats_attr[] = { &format_attr_event.attr, NULL, diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c index 40e0e322161d..284e73661a18 100644 --- a/arch/x86/hyperv/hv_apic.c +++ b/arch/x86/hyperv/hv_apic.c @@ -273,11 +273,15 @@ void __init hv_apic_init(void) pr_info("Hyper-V: Using enlightened APIC (%s mode)", x2apic_enabled() ? "x2apic" : "xapic"); /* - * With x2apic, architectural x2apic MSRs are equivalent to the - * respective synthetic MSRs, so there's no need to override - * the apic accessors. The only exception is - * hv_apic_eoi_write, because it benefits from lazy EOI when - * available, but it works for both xapic and x2apic modes. + * When in x2apic mode, don't use the Hyper-V specific APIC + * accessors since the field layout in the ICR register is + * different in x2apic mode. Furthermore, the architectural + * x2apic MSRs function just as well as the Hyper-V + * synthetic APIC MSRs, so there's no benefit in having + * separate Hyper-V accessors for x2apic mode. The only + * exception is hv_apic_eoi_write, because it benefits from + * lazy EOI when available, but the same accessor works for + * both xapic and x2apic because the field layout is the same. */ apic_set_eoi_write(hv_apic_eoi_write); if (!x2apic_enabled()) { diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index d44858b69353..324ddd7fd0aa 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -639,6 +639,7 @@ struct kvm_vcpu_arch { int cpuid_nent; struct kvm_cpuid_entry2 *cpuid_entries; + unsigned long cr3_lm_rsvd_bits; int maxphyaddr; int max_tdp_level; diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 6960cd6d1f23..b9a7fd0a27e2 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -137,7 +137,9 @@ union cpuid10_edx { struct { unsigned int num_counters_fixed:5; unsigned int bit_width_fixed:8; - unsigned int reserved:19; + unsigned int reserved1:2; + unsigned int anythread_deprecated:1; + unsigned int reserved2:16; } split; unsigned int full; }; diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h index 6bfc878f6771..6a9ccc1b2be5 100644 --- a/arch/x86/include/asm/sparsemem.h +++ b/arch/x86/include/asm/sparsemem.h @@ -28,4 +28,14 @@ #endif #endif /* CONFIG_SPARSEMEM */ + +#ifndef __ASSEMBLY__ +#ifdef CONFIG_NUMA_KEEP_MEMINFO +extern int phys_to_target_node(phys_addr_t start); +#define phys_to_target_node phys_to_target_node +extern int memory_add_physaddr_to_nid(u64 start); +#define memory_add_physaddr_to_nid memory_add_physaddr_to_nid +#endif +#endif /* __ASSEMBLY__ */ + #endif /* _ASM_X86_SPARSEMEM_H */ diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h index 172d3e4a9e4b..648eb23fe7f0 100644 --- a/arch/x86/include/asm/uv/uv.h +++ b/arch/x86/include/asm/uv/uv.h @@ -2,14 +2,8 @@ #ifndef _ASM_X86_UV_UV_H #define _ASM_X86_UV_UV_H -#include <asm/tlbflush.h> - enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC}; -struct cpumask; -struct mm_struct; -struct flush_tlb_info; - #ifdef CONFIG_X86_UV #include <linux/efi.h> @@ -44,10 +38,6 @@ static inline int is_uv_system(void) { return 0; } static inline int is_uv_hubbed(int uv) { return 0; } static inline void uv_cpu_init(void) { } static inline void uv_system_init(void) { } -static inline const struct cpumask * -uv_flush_tlb_others(const struct cpumask *cpumask, - const struct flush_tlb_info *info) -{ return cpumask; } #endif /* X86_UV */ diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 714233cee0b5..1b98f8c12b96 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -33,7 +33,7 @@ static union uvh_apicid uvh_apicid; static int uv_node_id; /* Unpack AT/OEM/TABLE ID's to be NULL terminated strings */ -static u8 uv_archtype[UV_AT_SIZE]; +static u8 uv_archtype[UV_AT_SIZE + 1]; static u8 oem_id[ACPI_OEM_ID_SIZE + 1]; static u8 oem_table_id[ACPI_OEM_TABLE_ID_SIZE + 1]; @@ -290,6 +290,9 @@ static void __init uv_stringify(int len, char *to, char *from) { /* Relies on 'to' being NULL chars so result will be NULL terminated */ strncpy(to, from, len-1); + + /* Trim trailing spaces */ + (void)strim(to); } /* Find UV arch type entry in UVsystab */ @@ -317,7 +320,7 @@ static int __init decode_arch_type(unsigned long ptr) if (n > 0 && n < sizeof(uv_ate->archtype)) { pr_info("UV: UVarchtype received from BIOS\n"); - uv_stringify(UV_AT_SIZE, uv_archtype, uv_ate->archtype); + uv_stringify(sizeof(uv_archtype), uv_archtype, uv_ate->archtype); return 1; } return 0; @@ -366,7 +369,7 @@ static int __init early_get_arch_type(void) return ret; } -static int __init uv_set_system_type(char *_oem_id) +static int __init uv_set_system_type(char *_oem_id, char *_oem_table_id) { /* Save OEM_ID passed from ACPI MADT */ uv_stringify(sizeof(oem_id), oem_id, _oem_id); @@ -375,7 +378,7 @@ static int __init uv_set_system_type(char *_oem_id) if (!early_get_arch_type()) /* If not use OEM ID for UVarchtype */ - uv_stringify(UV_AT_SIZE, uv_archtype, _oem_id); + uv_stringify(sizeof(uv_archtype), uv_archtype, oem_id); /* Check if not hubbed */ if (strncmp(uv_archtype, "SGI", 3) != 0) { @@ -386,13 +389,23 @@ static int __init uv_set_system_type(char *_oem_id) /* (Not hubless), not a UV */ return 0; + /* Is UV hubless system */ + uv_hubless_system = 0x01; + + /* UV5 Hubless */ + if (strncmp(uv_archtype, "NSGI5", 5) == 0) + uv_hubless_system |= 0x20; + /* UV4 Hubless: CH */ - if (strncmp(uv_archtype, "NSGI4", 5) == 0) - uv_hubless_system = 0x11; + else if (strncmp(uv_archtype, "NSGI4", 5) == 0) + uv_hubless_system |= 0x10; /* UV3 Hubless: UV300/MC990X w/o hub */ else - uv_hubless_system = 0x9; + uv_hubless_system |= 0x8; + + /* Copy APIC type */ + uv_stringify(sizeof(oem_table_id), oem_table_id, _oem_table_id); pr_info("UV: OEM IDs %s/%s, SystemType %d, HUBLESS ID %x\n", oem_id, oem_table_id, uv_system_type, uv_hubless_system); @@ -456,7 +469,7 @@ static int __init uv_acpi_madt_oem_check(char *_oem_id, char *_oem_table_id) uv_cpu_info->p_uv_hub_info = &uv_hub_info_node0; /* If not UV, return. */ - if (likely(uv_set_system_type(_oem_id) == 0)) + if (uv_set_system_type(_oem_id, _oem_table_id) == 0) return 0; /* Save and Decode OEM Table ID */ diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index d3f0db463f96..581fb7223ad0 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1254,6 +1254,14 @@ static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl) return 0; } +static bool is_spec_ib_user_controlled(void) +{ + return spectre_v2_user_ibpb == SPECTRE_V2_USER_PRCTL || + spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP || + spectre_v2_user_stibp == SPECTRE_V2_USER_PRCTL || + spectre_v2_user_stibp == SPECTRE_V2_USER_SECCOMP; +} + static int ib_prctl_set(struct task_struct *task, unsigned long ctrl) { switch (ctrl) { @@ -1261,16 +1269,26 @@ static int ib_prctl_set(struct task_struct *task, unsigned long ctrl) if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE && spectre_v2_user_stibp == SPECTRE_V2_USER_NONE) return 0; + /* - * Indirect branch speculation is always disabled in strict - * mode. It can neither be enabled if it was force-disabled - * by a previous prctl call. + * With strict mode for both IBPB and STIBP, the instruction + * code paths avoid checking this task flag and instead, + * unconditionally run the instruction. However, STIBP and IBPB + * are independent and either can be set to conditionally + * enabled regardless of the mode of the other. + * + * If either is set to conditional, allow the task flag to be + * updated, unless it was force-disabled by a previous prctl + * call. Currently, this is possible on an AMD CPU which has the + * feature X86_FEATURE_AMD_STIBP_ALWAYS_ON. In this case, if the + * kernel is booted with 'spectre_v2_user=seccomp', then + * spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP and + * spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED. */ - if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT || - spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || - spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED || + if (!is_spec_ib_user_controlled() || task_spec_ib_force_disable(task)) return -EPERM; + task_clear_spec_ib_disable(task); task_update_spec_tif(task); break; @@ -1283,10 +1301,10 @@ static int ib_prctl_set(struct task_struct *task, unsigned long ctrl) if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE && spectre_v2_user_stibp == SPECTRE_V2_USER_NONE) return -EPERM; - if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT || - spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || - spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED) + + if (!is_spec_ib_user_controlled()) return 0; + task_set_spec_ib_disable(task); if (ctrl == PR_SPEC_FORCE_DISABLE) task_set_spec_ib_force_disable(task); @@ -1351,20 +1369,17 @@ static int ib_prctl_get(struct task_struct *task) if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE && spectre_v2_user_stibp == SPECTRE_V2_USER_NONE) return PR_SPEC_ENABLE; - else if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT || - spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || - spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED) - return PR_SPEC_DISABLE; - else if (spectre_v2_user_ibpb == SPECTRE_V2_USER_PRCTL || - spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP || - spectre_v2_user_stibp == SPECTRE_V2_USER_PRCTL || - spectre_v2_user_stibp == SPECTRE_V2_USER_SECCOMP) { + else if (is_spec_ib_user_controlled()) { if (task_spec_ib_force_disable(task)) return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE; if (task_spec_ib_disable(task)) return PR_SPEC_PRCTL | PR_SPEC_DISABLE; return PR_SPEC_PRCTL | PR_SPEC_ENABLE; - } else + } else if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED) + return PR_SPEC_DISABLE; + else return PR_SPEC_NOT_AFFECTED; } diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 6a99535d7f37..7e8e07bddd5f 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -100,53 +100,6 @@ static int has_newer_microcode(void *mc, unsigned int csig, int cpf, int new_rev return find_matching_signature(mc, csig, cpf); } -/* - * Given CPU signature and a microcode patch, this function finds if the - * microcode patch has matching family and model with the CPU. - * - * %true - if there's a match - * %false - otherwise - */ -static bool microcode_matches(struct microcode_header_intel *mc_header, - unsigned long sig) -{ - unsigned long total_size = get_totalsize(mc_header); - unsigned long data_size = get_datasize(mc_header); - struct extended_sigtable *ext_header; - unsigned int fam_ucode, model_ucode; - struct extended_signature *ext_sig; - unsigned int fam, model; - int ext_sigcount, i; - - fam = x86_family(sig); - model = x86_model(sig); - - fam_ucode = x86_family(mc_header->sig); - model_ucode = x86_model(mc_header->sig); - - if (fam == fam_ucode && model == model_ucode) - return true; - - /* Look for ext. headers: */ - if (total_size <= data_size + MC_HEADER_SIZE) - return false; - - ext_header = (void *) mc_header + data_size + MC_HEADER_SIZE; - ext_sig = (void *)ext_header + EXT_HEADER_SIZE; - ext_sigcount = ext_header->count; - - for (i = 0; i < ext_sigcount; i++) { - fam_ucode = x86_family(ext_sig->sig); - model_ucode = x86_model(ext_sig->sig); - - if (fam == fam_ucode && model == model_ucode) - return true; - - ext_sig++; - } - return false; -} - static struct ucode_patch *memdup_patch(void *data, unsigned int size) { struct ucode_patch *p; @@ -164,7 +117,7 @@ static struct ucode_patch *memdup_patch(void *data, unsigned int size) return p; } -static void save_microcode_patch(void *data, unsigned int size) +static void save_microcode_patch(struct ucode_cpu_info *uci, void *data, unsigned int size) { struct microcode_header_intel *mc_hdr, *mc_saved_hdr; struct ucode_patch *iter, *tmp, *p = NULL; @@ -210,6 +163,9 @@ static void save_microcode_patch(void *data, unsigned int size) if (!p) return; + if (!find_matching_signature(p->data, uci->cpu_sig.sig, uci->cpu_sig.pf)) + return; + /* * Save for early loading. On 32-bit, that needs to be a physical * address as the APs are running from physical addresses, before @@ -344,13 +300,14 @@ scan_microcode(void *data, size_t size, struct ucode_cpu_info *uci, bool save) size -= mc_size; - if (!microcode_matches(mc_header, uci->cpu_sig.sig)) { + if (!find_matching_signature(data, uci->cpu_sig.sig, + uci->cpu_sig.pf)) { data += mc_size; continue; } if (save) { - save_microcode_patch(data, mc_size); + save_microcode_patch(uci, data, mc_size); goto next; } @@ -483,14 +440,14 @@ static void show_saved_mc(void) * Save this microcode patch. It will be loaded early when a CPU is * hot-added or resumes. */ -static void save_mc_for_early(u8 *mc, unsigned int size) +static void save_mc_for_early(struct ucode_cpu_info *uci, u8 *mc, unsigned int size) { /* Synchronization during CPU hotplug. */ static DEFINE_MUTEX(x86_cpu_microcode_mutex); mutex_lock(&x86_cpu_microcode_mutex); - save_microcode_patch(mc, size); + save_microcode_patch(uci, mc, size); show_saved_mc(); mutex_unlock(&x86_cpu_microcode_mutex); @@ -935,7 +892,7 @@ static enum ucode_state generic_load_microcode(int cpu, struct iov_iter *iter) * permanent memory. So it will be loaded early when a CPU is hot added * or resumes. */ - save_mc_for_early(new_mc, new_mc_size); + save_mc_for_early(uci, new_mc, new_mc_size); pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n", cpu, new_rev, uci->cpu_sig.rev); diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 25c06b67e7e0..97aa900386cb 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -78,6 +78,9 @@ static int copy_code(struct pt_regs *regs, u8 *buf, unsigned long src, if (!user_mode(regs)) return copy_from_kernel_nofault(buf, (u8 *)src, nbytes); + /* The user space code from other tasks cannot be accessed. */ + if (regs != task_pt_regs(current)) + return -EPERM; /* * Make sure userspace isn't trying to trick us into dumping kernel * memory by pointing the userspace instruction pointer at it. @@ -85,6 +88,12 @@ static int copy_code(struct pt_regs *regs, u8 *buf, unsigned long src, if (__chk_range_not_ok(src, nbytes, TASK_SIZE_MAX)) return -EINVAL; + /* + * Even if named copy_from_user_nmi() this can be invoked from + * other contexts and will not try to resolve a pagefault, which is + * the correct thing to do here as this code can be called from any + * context. + */ return copy_from_user_nmi(buf, (void __user *)src, nbytes); } @@ -115,13 +124,19 @@ void show_opcodes(struct pt_regs *regs, const char *loglvl) u8 opcodes[OPCODE_BUFSIZE]; unsigned long prologue = regs->ip - PROLOGUE_SIZE; - if (copy_code(regs, opcodes, prologue, sizeof(opcodes))) { - printk("%sCode: Unable to access opcode bytes at RIP 0x%lx.\n", - loglvl, prologue); - } else { + switch (copy_code(regs, opcodes, prologue, sizeof(opcodes))) { + case 0: printk("%sCode: %" __stringify(PROLOGUE_SIZE) "ph <%02x> %" __stringify(EPILOGUE_SIZE) "ph\n", loglvl, opcodes, opcodes[PROLOGUE_SIZE], opcodes + PROLOGUE_SIZE + 1); + break; + case -EPERM: + /* No access to the user space stack of other tasks. Ignore. */ + break; + default: + printk("%sCode: Unable to access opcode bytes at RIP 0x%lx.\n", + loglvl, prologue); + break; } } diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 7eb2a1c87969..3c417734790f 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -161,6 +161,21 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) /* Setup early boot stage 4-/5-level pagetables. */ addq phys_base(%rip), %rax + + /* + * For SEV guests: Verify that the C-bit is correct. A malicious + * hypervisor could lie about the C-bit position to perform a ROP + * attack on the guest by writing to the unencrypted stack and wait for + * the next RET instruction. + * %rsi carries pointer to realmode data and is callee-clobbered. Save + * and restore it. + */ + pushq %rsi + movq %rax, %rdi + call sev_verify_cbit + popq %rsi + + /* Switch to new page-table */ movq %rax, %cr3 /* Ensure I am executing from virtual addresses */ @@ -279,6 +294,7 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) SYM_CODE_END(secondary_startup_64) #include "verify_cpu.S" +#include "sev_verify_cbit.S" #ifdef CONFIG_HOTPLUG_CPU /* diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c index bb7e1132290b..f9e5352b3bef 100644 --- a/arch/x86/kernel/perf_regs.c +++ b/arch/x86/kernel/perf_regs.c @@ -101,8 +101,7 @@ u64 perf_reg_abi(struct task_struct *task) } void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { regs_user->regs = task_pt_regs(current); regs_user->abi = perf_reg_abi(current); @@ -129,12 +128,20 @@ u64 perf_reg_abi(struct task_struct *task) return PERF_SAMPLE_REGS_ABI_64; } +static DEFINE_PER_CPU(struct pt_regs, nmi_user_regs); + void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { + struct pt_regs *regs_user_copy = this_cpu_ptr(&nmi_user_regs); struct pt_regs *user_regs = task_pt_regs(current); + if (!in_nmi()) { + regs_user->regs = user_regs; + regs_user->abi = perf_reg_abi(current); + return; + } + /* * If we're in an NMI that interrupted task_pt_regs setup, then * we can't sample user regs at all. This check isn't really diff --git a/arch/x86/kernel/sev-es-shared.c b/arch/x86/kernel/sev-es-shared.c index 5f83ccaab877..7d04b356d44d 100644 --- a/arch/x86/kernel/sev-es-shared.c +++ b/arch/x86/kernel/sev-es-shared.c @@ -178,6 +178,32 @@ void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code) goto fail; regs->dx = val >> 32; + /* + * This is a VC handler and the #VC is only raised when SEV-ES is + * active, which means SEV must be active too. Do sanity checks on the + * CPUID results to make sure the hypervisor does not trick the kernel + * into the no-sev path. This could map sensitive data unencrypted and + * make it accessible to the hypervisor. + * + * In particular, check for: + * - Hypervisor CPUID bit + * - Availability of CPUID leaf 0x8000001f + * - SEV CPUID bit. + * + * The hypervisor might still report the wrong C-bit position, but this + * can't be checked here. + */ + + if ((fn == 1 && !(regs->cx & BIT(31)))) + /* Hypervisor bit */ + goto fail; + else if (fn == 0x80000000 && (regs->ax < 0x8000001f)) + /* SEV leaf check */ + goto fail; + else if ((fn == 0x8000001f && !(regs->ax & BIT(1)))) + /* SEV bit */ + goto fail; + /* Skip over the CPUID two-byte opcode */ regs->ip += 2; diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 4a96726fbaf8..0bd1a0fc587e 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -374,8 +374,8 @@ fault: return ES_EXCEPTION; } -static bool vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt, - unsigned long vaddr, phys_addr_t *paddr) +static enum es_result vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt, + unsigned long vaddr, phys_addr_t *paddr) { unsigned long va = (unsigned long)vaddr; unsigned int level; @@ -394,15 +394,19 @@ static bool vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt, if (user_mode(ctxt->regs)) ctxt->fi.error_code |= X86_PF_USER; - return false; + return ES_EXCEPTION; } + if (WARN_ON_ONCE(pte_val(*pte) & _PAGE_ENC)) + /* Emulated MMIO to/from encrypted memory not supported */ + return ES_UNSUPPORTED; + pa = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT; pa |= va & ~page_level_mask(level); *paddr = pa; - return true; + return ES_OK; } /* Include code shared with pre-decompression boot stage */ @@ -731,6 +735,7 @@ static enum es_result vc_do_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt, { u64 exit_code, exit_info_1, exit_info_2; unsigned long ghcb_pa = __pa(ghcb); + enum es_result res; phys_addr_t paddr; void __user *ref; @@ -740,11 +745,12 @@ static enum es_result vc_do_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt, exit_code = read ? SVM_VMGEXIT_MMIO_READ : SVM_VMGEXIT_MMIO_WRITE; - if (!vc_slow_virt_to_phys(ghcb, ctxt, (unsigned long)ref, &paddr)) { - if (!read) + res = vc_slow_virt_to_phys(ghcb, ctxt, (unsigned long)ref, &paddr); + if (res != ES_OK) { + if (res == ES_EXCEPTION && !read) ctxt->fi.error_code |= X86_PF_WRITE; - return ES_EXCEPTION; + return res; } exit_info_1 = paddr; diff --git a/arch/x86/kernel/sev_verify_cbit.S b/arch/x86/kernel/sev_verify_cbit.S new file mode 100644 index 000000000000..ee04941a6546 --- /dev/null +++ b/arch/x86/kernel/sev_verify_cbit.S @@ -0,0 +1,89 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * sev_verify_cbit.S - Code for verification of the C-bit position reported + * by the Hypervisor when running with SEV enabled. + * + * Copyright (c) 2020 Joerg Roedel (jroedel@suse.de) + * + * sev_verify_cbit() is called before switching to a new long-mode page-table + * at boot. + * + * Verify that the C-bit position is correct by writing a random value to + * an encrypted memory location while on the current page-table. Then it + * switches to the new page-table to verify the memory content is still the + * same. After that it switches back to the current page-table and when the + * check succeeded it returns. If the check failed the code invalidates the + * stack pointer and goes into a hlt loop. The stack-pointer is invalidated to + * make sure no interrupt or exception can get the CPU out of the hlt loop. + * + * New page-table pointer is expected in %rdi (first parameter) + * + */ +SYM_FUNC_START(sev_verify_cbit) +#ifdef CONFIG_AMD_MEM_ENCRYPT + /* First check if a C-bit was detected */ + movq sme_me_mask(%rip), %rsi + testq %rsi, %rsi + jz 3f + + /* sme_me_mask != 0 could mean SME or SEV - Check also for SEV */ + movq sev_status(%rip), %rsi + testq %rsi, %rsi + jz 3f + + /* Save CR4 in %rsi */ + movq %cr4, %rsi + + /* Disable Global Pages */ + movq %rsi, %rdx + andq $(~X86_CR4_PGE), %rdx + movq %rdx, %cr4 + + /* + * Verified that running under SEV - now get a random value using + * RDRAND. This instruction is mandatory when running as an SEV guest. + * + * Don't bail out of the loop if RDRAND returns errors. It is better to + * prevent forward progress than to work with a non-random value here. + */ +1: rdrand %rdx + jnc 1b + + /* Store value to memory and keep it in %rdx */ + movq %rdx, sev_check_data(%rip) + + /* Backup current %cr3 value to restore it later */ + movq %cr3, %rcx + + /* Switch to new %cr3 - This might unmap the stack */ + movq %rdi, %cr3 + + /* + * Compare value in %rdx with memory location. If C-bit is incorrect + * this would read the encrypted data and make the check fail. + */ + cmpq %rdx, sev_check_data(%rip) + + /* Restore old %cr3 */ + movq %rcx, %cr3 + + /* Restore previous CR4 */ + movq %rsi, %cr4 + + /* Check CMPQ result */ + je 3f + + /* + * The check failed, prevent any forward progress to prevent ROP + * attacks, invalidate the stack and go into a hlt loop. + */ + xorq %rsp, %rsp + subq $0x1000, %rsp +2: hlt + jmp 2b +3: +#endif + /* Return page-table pointer */ + movq %rdi, %rax + ret +SYM_FUNC_END(sev_verify_cbit) diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index 992fb1415c0f..420be871d9d4 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -514,9 +514,6 @@ int tboot_force_iommu(void) if (!tboot_enabled()) return 0; - if (intel_iommu_tboot_noforce) - return 1; - if (no_iommu || swiotlb || dmar_disabled) pr_warn("Forcing Intel-IOMMU to enabled\n"); diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 06a278b3701d..83637a2ff605 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -90,6 +90,20 @@ static int kvm_check_cpuid(struct kvm_cpuid_entry2 *entries, int nent) return 0; } +void kvm_update_pv_runtime(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, KVM_CPUID_FEATURES, 0); + + /* + * save the feature bitmap to avoid cpuid lookup for every PV + * operation + */ + if (best) + vcpu->arch.pv_cpuid.features = best->eax; +} + void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; @@ -124,13 +138,6 @@ void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu) (best->eax & (1 << KVM_FEATURE_PV_UNHALT))) best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT); - /* - * save the feature bitmap to avoid cpuid lookup for every PV - * operation - */ - if (best) - vcpu->arch.pv_cpuid.features = best->eax; - if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT)) { best = kvm_find_cpuid_entry(vcpu, 0x1, 0); if (best) @@ -162,6 +169,8 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) vcpu->arch.guest_supported_xcr0 = (best->eax | ((u64)best->edx << 32)) & supported_xcr0; + kvm_update_pv_runtime(vcpu); + vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); kvm_mmu_reset_context(vcpu); @@ -169,6 +178,8 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) vcpu->arch.cr4_guest_rsvd_bits = __cr4_reserved_bits(guest_cpuid_has, vcpu); + vcpu->arch.cr3_lm_rsvd_bits = rsvd_bits(cpuid_maxphyaddr(vcpu), 63); + /* Invoke the vendor callback only after the above state is updated. */ kvm_x86_ops.vcpu_after_set_cpuid(vcpu); } @@ -672,7 +683,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) edx.split.num_counters_fixed = min(cap.num_counters_fixed, MAX_FIXED_COUNTERS); edx.split.bit_width_fixed = cap.bit_width_fixed; - edx.split.reserved = 0; + edx.split.anythread_deprecated = 1; + edx.split.reserved1 = 0; + edx.split.reserved2 = 0; entry->eax = eax.full; entry->ebx = cap.events_mask; diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index bf8577947ed2..f7a6e8f83783 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -11,6 +11,7 @@ extern u32 kvm_cpu_caps[NCAPINTS] __read_mostly; void kvm_set_cpu_caps(void); void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu); +void kvm_update_pv_runtime(struct kvm_vcpu *vcpu); struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, u32 function, u32 index); int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid, diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 0d917eb70319..56cae1ff9e3f 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -4046,6 +4046,12 @@ static int em_clflush(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } +static int em_clflushopt(struct x86_emulate_ctxt *ctxt) +{ + /* emulating clflushopt regardless of cpuid */ + return X86EMUL_CONTINUE; +} + static int em_movsxd(struct x86_emulate_ctxt *ctxt) { ctxt->dst.val = (s32) ctxt->src.val; @@ -4585,7 +4591,7 @@ static const struct opcode group11[] = { }; static const struct gprefix pfx_0f_ae_7 = { - I(SrcMem | ByteOp, em_clflush), N, N, N, + I(SrcMem | ByteOp, em_clflush), I(SrcMem | ByteOp, em_clflushopt), N, N, }; static const struct group_dual group15 = { { diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 1f96adff8dc4..5bb1939b65d8 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -856,12 +856,14 @@ static int pte_list_add(struct kvm_vcpu *vcpu, u64 *spte, } else { rmap_printk("pte_list_add: %p %llx many->many\n", spte, *spte); desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); - while (desc->sptes[PTE_LIST_EXT-1] && desc->more) { - desc = desc->more; + while (desc->sptes[PTE_LIST_EXT-1]) { count += PTE_LIST_EXT; - } - if (desc->sptes[PTE_LIST_EXT-1]) { - desc->more = mmu_alloc_pte_list_desc(vcpu); + + if (!desc->more) { + desc->more = mmu_alloc_pte_list_desc(vcpu); + desc = desc->more; + break; + } desc = desc->more; } for (i = 0; desc->sptes[i]; ++i) diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 27e381c9da6c..ff28a5c6abd6 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -49,7 +49,14 @@ bool is_tdp_mmu_root(struct kvm *kvm, hpa_t hpa) { struct kvm_mmu_page *sp; + if (!kvm->arch.tdp_mmu_enabled) + return false; + if (WARN_ON(!VALID_PAGE(hpa))) + return false; + sp = to_shadow_page(hpa); + if (WARN_ON(!sp)) + return false; return sp->tdp_mmu_page && sp->root_count; } diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 2f32fd09e259..1e81cfebd491 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3741,6 +3741,7 @@ static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + struct kvm_cpuid_entry2 *best; vcpu->arch.xsaves_enabled = guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && boot_cpu_has(X86_FEATURE_XSAVE) && @@ -3753,6 +3754,13 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) /* Check again if INVPCID interception if required */ svm_check_invpcid(svm); + /* For sev guests, the memory encryption bit is not reserved in CR3. */ + if (sev_guest(vcpu->kvm)) { + best = kvm_find_cpuid_entry(vcpu, 0x8000001F, 0); + if (best) + vcpu->arch.cr3_lm_rsvd_bits &= ~(1UL << (best->ebx & 0x3f)); + } + if (!kvm_vcpu_apicv_active(vcpu)) return; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index f5ede41bf9e6..078a39d489fe 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -255,11 +255,10 @@ static struct kmem_cache *x86_emulator_cache; /* * When called, it means the previous get/set msr reached an invalid msr. - * Return 0 if we want to ignore/silent this failed msr access, or 1 if we want - * to fail the caller. + * Return true if we want to ignore/silent this failed msr access. */ -static int kvm_msr_ignored_check(struct kvm_vcpu *vcpu, u32 msr, - u64 data, bool write) +static bool kvm_msr_ignored_check(struct kvm_vcpu *vcpu, u32 msr, + u64 data, bool write) { const char *op = write ? "wrmsr" : "rdmsr"; @@ -268,11 +267,11 @@ static int kvm_msr_ignored_check(struct kvm_vcpu *vcpu, u32 msr, kvm_pr_unimpl("ignored %s: 0x%x data 0x%llx\n", op, msr, data); /* Mask the error */ - return 0; + return true; } else { kvm_debug_ratelimited("unhandled %s: 0x%x data 0x%llx\n", op, msr, data); - return -ENOENT; + return false; } } @@ -1042,7 +1041,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) } if (is_long_mode(vcpu) && - (cr3 & rsvd_bits(cpuid_maxphyaddr(vcpu), 63))) + (cr3 & vcpu->arch.cr3_lm_rsvd_bits)) return 1; else if (is_pae_paging(vcpu) && !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) @@ -1416,7 +1415,8 @@ static int do_get_msr_feature(struct kvm_vcpu *vcpu, unsigned index, u64 *data) if (r == KVM_MSR_RET_INVALID) { /* Unconditionally clear the output for simplicity */ *data = 0; - r = kvm_msr_ignored_check(vcpu, index, 0, false); + if (kvm_msr_ignored_check(vcpu, index, 0, false)) + r = 0; } if (r) @@ -1540,7 +1540,7 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data, struct msr_data msr; if (!host_initiated && !kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_WRITE)) - return -EPERM; + return KVM_MSR_RET_FILTERED; switch (index) { case MSR_FS_BASE: @@ -1581,7 +1581,8 @@ static int kvm_set_msr_ignored_check(struct kvm_vcpu *vcpu, int ret = __kvm_set_msr(vcpu, index, data, host_initiated); if (ret == KVM_MSR_RET_INVALID) - ret = kvm_msr_ignored_check(vcpu, index, data, true); + if (kvm_msr_ignored_check(vcpu, index, data, true)) + ret = 0; return ret; } @@ -1599,7 +1600,7 @@ int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, int ret; if (!host_initiated && !kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_READ)) - return -EPERM; + return KVM_MSR_RET_FILTERED; msr.index = index; msr.host_initiated = host_initiated; @@ -1618,7 +1619,8 @@ static int kvm_get_msr_ignored_check(struct kvm_vcpu *vcpu, if (ret == KVM_MSR_RET_INVALID) { /* Unconditionally clear *data for simplicity */ *data = 0; - ret = kvm_msr_ignored_check(vcpu, index, 0, false); + if (kvm_msr_ignored_check(vcpu, index, 0, false)) + ret = 0; } return ret; @@ -1662,9 +1664,9 @@ static int complete_emulated_wrmsr(struct kvm_vcpu *vcpu) static u64 kvm_msr_reason(int r) { switch (r) { - case -ENOENT: + case KVM_MSR_RET_INVALID: return KVM_MSR_EXIT_REASON_UNKNOWN; - case -EPERM: + case KVM_MSR_RET_FILTERED: return KVM_MSR_EXIT_REASON_FILTER; default: return KVM_MSR_EXIT_REASON_INVAL; @@ -1965,7 +1967,7 @@ static void kvm_write_system_time(struct kvm_vcpu *vcpu, gpa_t system_time, struct kvm_arch *ka = &vcpu->kvm->arch; if (vcpu->vcpu_id == 0 && !host_initiated) { - if (ka->boot_vcpu_runs_old_kvmclock && old_msr) + if (ka->boot_vcpu_runs_old_kvmclock != old_msr) kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu); ka->boot_vcpu_runs_old_kvmclock = old_msr; @@ -3063,9 +3065,9 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) /* Values other than LBR and BTF are vendor-specific, thus reserved and should throw a #GP */ return 1; - } - vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n", - __func__, data); + } else if (report_ignored_msrs) + vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n", + __func__, data); break; case 0x200 ... 0x2ff: return kvm_mtrr_set_msr(vcpu, msr, data); @@ -3463,29 +3465,63 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vcpu->arch.efer; break; case MSR_KVM_WALL_CLOCK: + if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE)) + return 1; + + msr_info->data = vcpu->kvm->arch.wall_clock; + break; case MSR_KVM_WALL_CLOCK_NEW: + if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2)) + return 1; + msr_info->data = vcpu->kvm->arch.wall_clock; break; case MSR_KVM_SYSTEM_TIME: + if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE)) + return 1; + + msr_info->data = vcpu->arch.time; + break; case MSR_KVM_SYSTEM_TIME_NEW: + if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2)) + return 1; + msr_info->data = vcpu->arch.time; break; case MSR_KVM_ASYNC_PF_EN: + if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF)) + return 1; + msr_info->data = vcpu->arch.apf.msr_en_val; break; case MSR_KVM_ASYNC_PF_INT: + if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT)) + return 1; + msr_info->data = vcpu->arch.apf.msr_int_val; break; case MSR_KVM_ASYNC_PF_ACK: + if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF)) + return 1; + msr_info->data = 0; break; case MSR_KVM_STEAL_TIME: + if (!guest_pv_has(vcpu, KVM_FEATURE_STEAL_TIME)) + return 1; + msr_info->data = vcpu->arch.st.msr_val; break; case MSR_KVM_PV_EOI_EN: + if (!guest_pv_has(vcpu, KVM_FEATURE_PV_EOI)) + return 1; + msr_info->data = vcpu->arch.pv_eoi.msr_val; break; case MSR_KVM_POLL_CONTROL: + if (!guest_pv_has(vcpu, KVM_FEATURE_POLL_CONTROL)) + return 1; + msr_info->data = vcpu->arch.msr_kvm_poll_control; break; case MSR_IA32_P5_MC_ADDR: @@ -4575,6 +4611,8 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, case KVM_CAP_ENFORCE_PV_FEATURE_CPUID: vcpu->arch.pv_cpuid.enforce = cap->args[0]; + if (vcpu->arch.pv_cpuid.enforce) + kvm_update_pv_runtime(vcpu); return 0; diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 3900ab0c6004..e7ca622a468f 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -376,7 +376,13 @@ int kvm_handle_memory_failure(struct kvm_vcpu *vcpu, int r, int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva); bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type); -#define KVM_MSR_RET_INVALID 2 +/* + * Internal error codes that are used to indicate that MSR emulation encountered + * an error that should result in #GP in the guest, unless userspace + * handles it. + */ +#define KVM_MSR_RET_INVALID 2 /* in-kernel MSR emulation #GP condition */ +#define KVM_MSR_RET_FILTERED 3 /* #GP due to userspace MSR filter */ #define __cr4_reserved_bits(__cpu_has, __c) \ ({ \ diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index 037faac46b0c..1e299ac73c86 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -16,8 +16,6 @@ * to a jmp to memcpy_erms which does the REP; MOVSB mem copy. */ -.weak memcpy - /* * memcpy - Copy a memory block. * @@ -30,7 +28,7 @@ * rax original destination */ SYM_FUNC_START_ALIAS(__memcpy) -SYM_FUNC_START_LOCAL(memcpy) +SYM_FUNC_START_WEAK(memcpy) ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \ "jmp memcpy_erms", X86_FEATURE_ERMS diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S index 7ff00ea64e4f..41902fe8b859 100644 --- a/arch/x86/lib/memmove_64.S +++ b/arch/x86/lib/memmove_64.S @@ -24,9 +24,7 @@ * Output: * rax: dest */ -.weak memmove - -SYM_FUNC_START_ALIAS(memmove) +SYM_FUNC_START_WEAK(memmove) SYM_FUNC_START(__memmove) mov %rdi, %rax diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S index 9ff15ee404a4..0bfd26e4ca9e 100644 --- a/arch/x86/lib/memset_64.S +++ b/arch/x86/lib/memset_64.S @@ -6,8 +6,6 @@ #include <asm/alternative-asm.h> #include <asm/export.h> -.weak memset - /* * ISO C memset - set a memory block to a byte value. This function uses fast * string to get better performance than the original function. The code is @@ -19,7 +17,7 @@ * * rax original destination */ -SYM_FUNC_START_ALIAS(memset) +SYM_FUNC_START_WEAK(memset) SYM_FUNC_START(__memset) /* * Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index efbb3de472df..bc0833713be9 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -39,6 +39,7 @@ */ u64 sme_me_mask __section(".data") = 0; u64 sev_status __section(".data") = 0; +u64 sev_check_data __section(".data") = 0; EXPORT_SYMBOL(sme_me_mask); DEFINE_STATIC_KEY_FALSE(sev_enable_key); EXPORT_SYMBOL_GPL(sev_enable_key); diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 44148691d78b..5eb4dc2b97da 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -938,6 +938,7 @@ int phys_to_target_node(phys_addr_t start) return meminfo_to_nid(&numa_reserved_meminfo, start); } +EXPORT_SYMBOL_GPL(phys_to_target_node); int memory_add_physaddr_to_nid(u64 start) { @@ -947,4 +948,5 @@ int memory_add_physaddr_to_nid(u64 start) nid = numa_meminfo.blk[0].nid; return nid; } +EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); #endif diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 8f5759df7776..e1e8d4e3a213 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -78,28 +78,30 @@ int __init efi_alloc_page_tables(void) gfp_mask = GFP_KERNEL | __GFP_ZERO; efi_pgd = (pgd_t *)__get_free_pages(gfp_mask, PGD_ALLOCATION_ORDER); if (!efi_pgd) - return -ENOMEM; + goto fail; pgd = efi_pgd + pgd_index(EFI_VA_END); p4d = p4d_alloc(&init_mm, pgd, EFI_VA_END); - if (!p4d) { - free_page((unsigned long)efi_pgd); - return -ENOMEM; - } + if (!p4d) + goto free_pgd; pud = pud_alloc(&init_mm, p4d, EFI_VA_END); - if (!pud) { - if (pgtable_l5_enabled()) - free_page((unsigned long) pgd_page_vaddr(*pgd)); - free_pages((unsigned long)efi_pgd, PGD_ALLOCATION_ORDER); - return -ENOMEM; - } + if (!pud) + goto free_p4d; efi_mm.pgd = efi_pgd; mm_init_cpumask(&efi_mm); init_new_context(NULL, &efi_mm); return 0; + +free_p4d: + if (pgtable_l5_enabled()) + free_page((unsigned long)pgd_page_vaddr(*pgd)); +free_pgd: + free_pages((unsigned long)efi_pgd, PGD_ALLOCATION_ORDER); +fail: + return -ENOMEM; } /* diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index 799f4eba0a62..043c73dfd2c9 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -93,10 +93,20 @@ void xen_init_lock_cpu(int cpu) void xen_uninit_lock_cpu(int cpu) { + int irq; + if (!xen_pvspin) return; - unbind_from_irqhandler(per_cpu(lock_kicker_irq, cpu), NULL); + /* + * When booting the kernel with 'mitigations=auto,nosmt', the secondary + * CPUs are not activated, and lock_kicker_irq is not initialized. + */ + irq = per_cpu(lock_kicker_irq, cpu); + if (irq == -1) + return; + + unbind_from_irqhandler(irq, NULL); per_cpu(lock_kicker_irq, cpu) = -1; kfree(per_cpu(irq_name, cpu)); per_cpu(irq_name, cpu) = NULL; diff --git a/arch/xtensa/include/asm/pgtable.h b/arch/xtensa/include/asm/pgtable.h index fa054a1772e1..4dc04e6c01d7 100644 --- a/arch/xtensa/include/asm/pgtable.h +++ b/arch/xtensa/include/asm/pgtable.h @@ -69,7 +69,7 @@ */ #define VMALLOC_START (XCHAL_KSEG_CACHED_VADDR - 0x10000000) #define VMALLOC_END (VMALLOC_START + 0x07FEFFFF) -#define TLBTEMP_BASE_1 (VMALLOC_END + 1) +#define TLBTEMP_BASE_1 (VMALLOC_START + 0x08000000) #define TLBTEMP_BASE_2 (TLBTEMP_BASE_1 + DCACHE_WAY_SIZE) #if 2 * DCACHE_WAY_SIZE > ICACHE_WAY_SIZE #define TLBTEMP_SIZE (2 * DCACHE_WAY_SIZE) diff --git a/arch/xtensa/include/asm/uaccess.h b/arch/xtensa/include/asm/uaccess.h index b9758119feca..5c9fb8005aa8 100644 --- a/arch/xtensa/include/asm/uaccess.h +++ b/arch/xtensa/include/asm/uaccess.h @@ -302,7 +302,7 @@ strncpy_from_user(char *dst, const char __user *src, long count) return -EFAULT; } #else -long strncpy_from_user(char *dst, const char *src, long count); +long strncpy_from_user(char *dst, const char __user *src, long count); #endif /* diff --git a/arch/xtensa/mm/cache.c b/arch/xtensa/mm/cache.c index 5835406b3cec..085b8c77b9d9 100644 --- a/arch/xtensa/mm/cache.c +++ b/arch/xtensa/mm/cache.c @@ -70,8 +70,10 @@ static inline void kmap_invalidate_coherent(struct page *page, kvaddr = TLBTEMP_BASE_1 + (page_to_phys(page) & DCACHE_ALIAS_MASK); + preempt_disable(); __invalidate_dcache_page_alias(kvaddr, page_to_phys(page)); + preempt_enable(); } } } @@ -156,6 +158,7 @@ void flush_dcache_page(struct page *page) if (!alias && !mapping) return; + preempt_disable(); virt = TLBTEMP_BASE_1 + (phys & DCACHE_ALIAS_MASK); __flush_invalidate_dcache_page_alias(virt, phys); @@ -166,6 +169,7 @@ void flush_dcache_page(struct page *page) if (mapping) __invalidate_icache_page_alias(virt, phys); + preempt_enable(); } /* There shouldn't be an entry in the cache for this page anymore. */ @@ -199,8 +203,10 @@ void local_flush_cache_page(struct vm_area_struct *vma, unsigned long address, unsigned long phys = page_to_phys(pfn_to_page(pfn)); unsigned long virt = TLBTEMP_BASE_1 + (address & DCACHE_ALIAS_MASK); + preempt_disable(); __flush_invalidate_dcache_page_alias(virt, phys); __invalidate_icache_page_alias(virt, phys); + preempt_enable(); } EXPORT_SYMBOL(local_flush_cache_page); @@ -227,11 +233,13 @@ update_mmu_cache(struct vm_area_struct * vma, unsigned long addr, pte_t *ptep) unsigned long phys = page_to_phys(page); unsigned long tmp; + preempt_disable(); tmp = TLBTEMP_BASE_1 + (phys & DCACHE_ALIAS_MASK); __flush_invalidate_dcache_page_alias(tmp, phys); tmp = TLBTEMP_BASE_1 + (addr & DCACHE_ALIAS_MASK); __flush_invalidate_dcache_page_alias(tmp, phys); __invalidate_icache_page_alias(tmp, phys); + preempt_enable(); clear_bit(PG_arch_1, &page->flags); } @@ -265,7 +273,9 @@ void copy_to_user_page(struct vm_area_struct *vma, struct page *page, if (alias) { unsigned long t = TLBTEMP_BASE_1 + (vaddr & DCACHE_ALIAS_MASK); + preempt_disable(); __flush_invalidate_dcache_page_alias(t, phys); + preempt_enable(); } /* Copy data */ @@ -280,9 +290,11 @@ void copy_to_user_page(struct vm_area_struct *vma, struct page *page, if (alias) { unsigned long t = TLBTEMP_BASE_1 + (vaddr & DCACHE_ALIAS_MASK); + preempt_disable(); __flush_invalidate_dcache_range((unsigned long) dst, len); if ((vma->vm_flags & VM_EXEC) != 0) __invalidate_icache_page_alias(t, phys); + preempt_enable(); } else if ((vma->vm_flags & VM_EXEC) != 0) { __flush_dcache_range((unsigned long)dst,len); @@ -304,7 +316,9 @@ extern void copy_from_user_page(struct vm_area_struct *vma, struct page *page, if (alias) { unsigned long t = TLBTEMP_BASE_1 + (vaddr & DCACHE_ALIAS_MASK); + preempt_disable(); __flush_invalidate_dcache_page_alias(t, phys); + preempt_enable(); } memcpy(dst, src, len); diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c index c6fc83efee0c..8731b7ad9308 100644 --- a/arch/xtensa/mm/init.c +++ b/arch/xtensa/mm/init.c @@ -89,8 +89,8 @@ static void __init free_highpages(void) /* set highmem page free */ for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &range_start, &range_end, NULL) { - unsigned long start = PHYS_PFN(range_start); - unsigned long end = PHYS_PFN(range_end); + unsigned long start = PFN_UP(range_start); + unsigned long end = PFN_DOWN(range_end); /* Ignore complete lowmem entries */ if (end <= max_low) diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index c68bdf58c9a6..54fbe1e80cc4 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -849,6 +849,7 @@ static void blkcg_fill_root_iostats(void) blkg_iostat_set(&blkg->iostat.cur, &tmp); u64_stats_update_end(&blkg->iostat.sync); } + disk_put_part(part); } } diff --git a/block/blk-flush.c b/block/blk-flush.c index e32958f0b687..fd5cee9f1a3b 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -225,13 +225,18 @@ static void flush_end_io(struct request *flush_rq, blk_status_t error) /* release the tag's ownership to the req cloned from */ spin_lock_irqsave(&fq->mq_flush_lock, flags); - WRITE_ONCE(flush_rq->state, MQ_RQ_IDLE); if (!refcount_dec_and_test(&flush_rq->ref)) { fq->rq_status = error; spin_unlock_irqrestore(&fq->mq_flush_lock, flags); return; } + /* + * Flush request has to be marked as IDLE when it is really ended + * because its .end_io() is called from timeout code path too for + * avoiding use-after-free. + */ + WRITE_ONCE(flush_rq->state, MQ_RQ_IDLE); if (fq->rq_status != BLK_STS_OK) error = fq->rq_status; diff --git a/block/genhd.c b/block/genhd.c index 0a273211fec2..9387f050c248 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -49,7 +49,7 @@ static void disk_release_events(struct gendisk *disk); * Set disk capacity and notify if the size is not currently * zero and will not be set to zero */ -void set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size, +bool set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size, bool update_bdev) { sector_t capacity = get_capacity(disk); @@ -62,7 +62,10 @@ void set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size, char *envp[] = { "RESIZE=1", NULL }; kobject_uevent_env(&disk_to_dev(disk)->kobj, KOBJ_CHANGE, envp); + return true; } + + return false; } EXPORT_SYMBOL_GPL(set_capacity_revalidate_and_notify); diff --git a/drivers/accessibility/speakup/main.c b/drivers/accessibility/speakup/main.c index be79b2135fac..48019660a096 100644 --- a/drivers/accessibility/speakup/main.c +++ b/drivers/accessibility/speakup/main.c @@ -357,7 +357,6 @@ static void speakup_cut(struct vc_data *vc) mark_cut_flag = 0; synth_printf("%s\n", spk_msg_get(MSG_CUT)); - speakup_clear_selection(); ret = speakup_set_selection(tty); switch (ret) { diff --git a/drivers/accessibility/speakup/selection.c b/drivers/accessibility/speakup/selection.c index 032f3264fba1..7df7afad5ab4 100644 --- a/drivers/accessibility/speakup/selection.c +++ b/drivers/accessibility/speakup/selection.c @@ -22,13 +22,6 @@ struct speakup_selection_work { struct tty_struct *tty; }; -void speakup_clear_selection(void) -{ - console_lock(); - clear_selection(); - console_unlock(); -} - static void __speakup_set_selection(struct work_struct *work) { struct speakup_selection_work *ssw = @@ -51,6 +44,10 @@ static void __speakup_set_selection(struct work_struct *work) goto unref; } + console_lock(); + clear_selection(); + console_unlock(); + set_selection_kernel(&sel, tty); unref: diff --git a/drivers/accessibility/speakup/speakup.h b/drivers/accessibility/speakup/speakup.h index 74fe49c2c511..33594f5a7983 100644 --- a/drivers/accessibility/speakup/speakup.h +++ b/drivers/accessibility/speakup/speakup.h @@ -70,7 +70,6 @@ void spk_do_flush(void); void speakup_start_ttys(void); void synth_buffer_add(u16 ch); void synth_buffer_clear(void); -void speakup_clear_selection(void); int speakup_set_selection(struct tty_struct *tty); void speakup_cancel_selection(void); int speakup_paste_selection(struct tty_struct *tty); diff --git a/drivers/accessibility/speakup/spk_ttyio.c b/drivers/accessibility/speakup/spk_ttyio.c index a831ff64f8ba..669392f31d4e 100644 --- a/drivers/accessibility/speakup/spk_ttyio.c +++ b/drivers/accessibility/speakup/spk_ttyio.c @@ -49,15 +49,25 @@ static int spk_ttyio_ldisc_open(struct tty_struct *tty) if (!tty->ops->write) return -EOPNOTSUPP; + + mutex_lock(&speakup_tty_mutex); + if (speakup_tty) { + mutex_unlock(&speakup_tty_mutex); + return -EBUSY; + } speakup_tty = tty; ldisc_data = kmalloc(sizeof(*ldisc_data), GFP_KERNEL); - if (!ldisc_data) + if (!ldisc_data) { + speakup_tty = NULL; + mutex_unlock(&speakup_tty_mutex); return -ENOMEM; + } init_completion(&ldisc_data->completion); ldisc_data->buf_free = true; speakup_tty->disc_data = ldisc_data; + mutex_unlock(&speakup_tty_mutex); return 0; } @@ -298,11 +308,13 @@ static unsigned char ttyio_in(int timeout) struct spk_ldisc_data *ldisc_data = speakup_tty->disc_data; char rv; - if (wait_for_completion_timeout(&ldisc_data->completion, + if (!timeout) { + if (!try_wait_for_completion(&ldisc_data->completion)) + return 0xff; + } else if (wait_for_completion_timeout(&ldisc_data->completion, usecs_to_jiffies(timeout)) == 0) { - if (timeout) - pr_warn("spk_ttyio: timeout (%d) while waiting for input\n", - timeout); + pr_warn("spk_ttyio: timeout (%d) while waiting for input\n", + timeout); return 0xff; } diff --git a/drivers/accessibility/speakup/spk_types.h b/drivers/accessibility/speakup/spk_types.h index 7398f1196e10..91fca3033a45 100644 --- a/drivers/accessibility/speakup/spk_types.h +++ b/drivers/accessibility/speakup/spk_types.h @@ -32,6 +32,10 @@ enum { E_NEW_DEFAULT, }; +/* + * Note: add new members at the end, speakupmap.h depends on the values of the + * enum starting from SPELL_DELAY (see inc_dec_var) + */ enum var_id_t { VERSION = 0, SYNTH, SILENT, SYNTH_DIRECT, KEYMAP, CHARS, @@ -42,9 +46,9 @@ enum var_id_t { SAY_CONTROL, SAY_WORD_CTL, NO_INTERRUPT, KEY_ECHO, SPELL_DELAY, PUNC_LEVEL, READING_PUNC, ATTRIB_BLEEP, BLEEPS, - RATE, PITCH, INFLECTION, VOL, TONE, PUNCT, VOICE, FREQUENCY, LANG, + RATE, PITCH, VOL, TONE, PUNCT, VOICE, FREQUENCY, LANG, DIRECT, PAUSE, - CAPS_START, CAPS_STOP, CHARTAB, + CAPS_START, CAPS_STOP, CHARTAB, INFLECTION, MAXVARS }; diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c index bc96457c9e25..a322a7bd286b 100644 --- a/drivers/acpi/acpi_video.c +++ b/drivers/acpi/acpi_video.c @@ -578,7 +578,7 @@ acpi_video_bqc_value_to_level(struct acpi_video_device *device, ACPI_VIDEO_FIRST_LEVEL - 1 - bqc_value; level = device->brightness->levels[bqc_value + - ACPI_VIDEO_FIRST_LEVEL]; + ACPI_VIDEO_FIRST_LEVEL]; } else { level = bqc_value; } @@ -990,8 +990,8 @@ set_level: goto out_free_levels; ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "found %d brightness levels\n", - br->count - ACPI_VIDEO_FIRST_LEVEL)); + "found %d brightness levels\n", + br->count - ACPI_VIDEO_FIRST_LEVEL)); return 0; out_free_levels: diff --git a/drivers/acpi/apei/apei-base.c b/drivers/acpi/apei/apei-base.c index 552fd9ffaca4..3294cc8dc073 100644 --- a/drivers/acpi/apei/apei-base.c +++ b/drivers/acpi/apei/apei-base.c @@ -633,6 +633,10 @@ int apei_map_generic_address(struct acpi_generic_address *reg) if (rc) return rc; + /* IO space doesn't need mapping */ + if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_IO) + return 0; + if (!acpi_os_map_generic_address(reg)) return -ENXIO; diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c index cab4af532f36..08ee1c7b12e0 100644 --- a/drivers/acpi/battery.c +++ b/drivers/acpi/battery.c @@ -987,7 +987,7 @@ static int acpi_battery_update(struct acpi_battery *battery, bool resume) */ if ((battery->state & ACPI_BATTERY_STATE_CRITICAL) || (test_bit(ACPI_BATTERY_ALARM_PRESENT, &battery->flags) && - (battery->capacity_now <= battery->alarm))) + (battery->capacity_now <= battery->alarm))) acpi_pm_wakeup_event(&battery->device->dev); return result; diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c index 0761529cac05..0d93a5ef4d07 100644 --- a/drivers/acpi/button.c +++ b/drivers/acpi/button.c @@ -89,7 +89,18 @@ static const struct dmi_system_id dmi_lid_quirks[] = { */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "MEDION"), - DMI_MATCH(DMI_PRODUCT_NAME, "E2215T MD60198"), + DMI_MATCH(DMI_PRODUCT_NAME, "E2215T"), + }, + .driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_OPEN, + }, + { + /* + * Medion Akoya E2228T, notification of the LID device only + * happens on close, not on open and _LID always returns closed. + */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "MEDION"), + DMI_MATCH(DMI_PRODUCT_NAME, "E2228T"), }, .driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_OPEN, }, diff --git a/drivers/acpi/dptf/dptf_pch_fivr.c b/drivers/acpi/dptf/dptf_pch_fivr.c index 4c1992fce150..5fca18296bf6 100644 --- a/drivers/acpi/dptf/dptf_pch_fivr.c +++ b/drivers/acpi/dptf/dptf_pch_fivr.c @@ -106,6 +106,7 @@ static int pch_fivr_remove(struct platform_device *pdev) static const struct acpi_device_id pch_fivr_device_ids[] = { {"INTC1045", 0}, + {"INTC1049", 0}, {"", 0}, }; MODULE_DEVICE_TABLE(acpi, pch_fivr_device_ids); diff --git a/drivers/acpi/dptf/dptf_power.c b/drivers/acpi/dptf/dptf_power.c index 06741305fc77..a24d5d7aa117 100644 --- a/drivers/acpi/dptf/dptf_power.c +++ b/drivers/acpi/dptf/dptf_power.c @@ -229,6 +229,8 @@ static const struct acpi_device_id int3407_device_ids[] = { {"INT3532", 0}, {"INTC1047", 0}, {"INTC1050", 0}, + {"INTC1060", 0}, + {"INTC1061", 0}, {"", 0}, }; MODULE_DEVICE_TABLE(acpi, int3407_device_ids); diff --git a/drivers/acpi/dptf/int340x_thermal.c b/drivers/acpi/dptf/int340x_thermal.c index 8d420c7e7178..d14025a85ce8 100644 --- a/drivers/acpi/dptf/int340x_thermal.c +++ b/drivers/acpi/dptf/int340x_thermal.c @@ -25,10 +25,16 @@ static const struct acpi_device_id int340x_thermal_device_ids[] = { {"INT340A"}, {"INT340B"}, {"INTC1040"}, + {"INTC1041"}, {"INTC1043"}, {"INTC1044"}, {"INTC1045"}, + {"INTC1046"}, {"INTC1047"}, + {"INTC1048"}, + {"INTC1049"}, + {"INTC1060"}, + {"INTC1061"}, {""}, }; diff --git a/drivers/acpi/event.c b/drivers/acpi/event.c index 170643927044..92e59f45329b 100644 --- a/drivers/acpi/event.c +++ b/drivers/acpi/event.c @@ -31,7 +31,7 @@ int acpi_notifier_call_chain(struct acpi_device *dev, u32 type, u32 data) event.type = type; event.data = data; return (blocking_notifier_call_chain(&acpi_chain_head, 0, (void *)&event) - == NOTIFY_BAD) ? -EINVAL : 0; + == NOTIFY_BAD) ? -EINVAL : 0; } EXPORT_SYMBOL(acpi_notifier_call_chain); diff --git a/drivers/acpi/evged.c b/drivers/acpi/evged.c index b1a7f8d6965e..fe6b6792c8bb 100644 --- a/drivers/acpi/evged.c +++ b/drivers/acpi/evged.c @@ -101,7 +101,7 @@ static acpi_status acpi_ged_request_interrupt(struct acpi_resource *ares, switch (gsi) { case 0 ... 255: - sprintf(ev_name, "_%c%02hhX", + sprintf(ev_name, "_%c%02X", trigger == ACPI_EDGE_SENSITIVE ? 'E' : 'L', gsi); if (ACPI_SUCCESS(acpi_get_handle(handle, ev_name, &evt_handle))) diff --git a/drivers/acpi/fan.c b/drivers/acpi/fan.c index 62873388b24f..66c3983f0ccc 100644 --- a/drivers/acpi/fan.c +++ b/drivers/acpi/fan.c @@ -27,6 +27,7 @@ static const struct acpi_device_id fan_device_ids[] = { {"PNP0C0B", 0}, {"INT3404", 0}, {"INTC1044", 0}, + {"INTC1048", 0}, {"", 0}, }; MODULE_DEVICE_TABLE(acpi, fan_device_ids); @@ -351,6 +352,7 @@ static int acpi_fan_get_fps(struct acpi_device *device) struct acpi_fan_fps *fps = &fan->fps[i]; snprintf(fps->name, ACPI_FPS_NAME_LEN, "state%d", i); + sysfs_attr_init(&fps->dev_attr.attr); fps->dev_attr.show = show_state; fps->dev_attr.store = NULL; fps->dev_attr.attr.name = fps->name; diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h index 43411a7457cd..e3638bafb941 100644 --- a/drivers/acpi/internal.h +++ b/drivers/acpi/internal.h @@ -134,7 +134,7 @@ int acpi_add_power_resource(acpi_handle handle); void acpi_power_add_remove_device(struct acpi_device *adev, bool add); int acpi_power_wakeup_list_init(struct list_head *list, int *system_level); int acpi_device_sleep_wake(struct acpi_device *dev, - int enable, int sleep_state, int dev_state); + int enable, int sleep_state, int dev_state); int acpi_power_get_inferred_state(struct acpi_device *device, int *state); int acpi_power_on_resources(struct acpi_device *device, int state); int acpi_power_transition(struct acpi_device *device, int state); diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 3a3c209ed3d3..442608220b5c 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -2175,10 +2175,10 @@ static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc) * these commands. */ enum nfit_aux_cmds { - NFIT_CMD_TRANSLATE_SPA = 5, - NFIT_CMD_ARS_INJECT_SET = 7, - NFIT_CMD_ARS_INJECT_CLEAR = 8, - NFIT_CMD_ARS_INJECT_GET = 9, + NFIT_CMD_TRANSLATE_SPA = 5, + NFIT_CMD_ARS_INJECT_SET = 7, + NFIT_CMD_ARS_INJECT_CLEAR = 8, + NFIT_CMD_ARS_INJECT_GET = 9, }; static void acpi_nfit_init_dsms(struct acpi_nfit_desc *acpi_desc) @@ -2632,7 +2632,7 @@ static int acpi_nfit_blk_region_enable(struct nvdimm_bus *nvdimm_bus, nfit_blk->bdw_offset = nfit_mem->bdw->offset; mmio = &nfit_blk->mmio[BDW]; mmio->addr.base = devm_nvdimm_memremap(dev, nfit_mem->spa_bdw->address, - nfit_mem->spa_bdw->length, nd_blk_memremap_flags(ndbr)); + nfit_mem->spa_bdw->length, nd_blk_memremap_flags(ndbr)); if (!mmio->addr.base) { dev_dbg(dev, "%s failed to map bdw\n", nvdimm_name(nvdimm)); diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c index dea8a60e18a4..14ee631cb7cf 100644 --- a/drivers/acpi/pci_irq.c +++ b/drivers/acpi/pci_irq.c @@ -175,7 +175,7 @@ static int acpi_pci_irq_check_entry(acpi_handle handle, struct pci_dev *dev, * configure the IRQ assigned to this slot|dev|pin. The 'source_index' * indicates which resource descriptor in the resource template (of * the link device) this interrupt is allocated from. - * + * * NOTE: Don't query the Link Device for IRQ information at this time * because Link Device enumeration may not have occurred yet * (e.g. exists somewhere 'below' this _PRT entry in the ACPI diff --git a/drivers/acpi/pci_link.c b/drivers/acpi/pci_link.c index 606da5d77ad3..fb4c5632a232 100644 --- a/drivers/acpi/pci_link.c +++ b/drivers/acpi/pci_link.c @@ -6,8 +6,8 @@ * Copyright (C) 2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com> * Copyright (C) 2002 Dominik Brodowski <devel@brodo.de> * - * TBD: - * 1. Support more than one IRQ resource entry per link device (index). + * TBD: + * 1. Support more than one IRQ resource entry per link device (index). * 2. Implement start/stop mechanism and use ACPI Bus Driver facilities * for IRQ management (e.g. start()->_SRS). */ @@ -249,8 +249,8 @@ static int acpi_pci_link_get_current(struct acpi_pci_link *link) } } - /* - * Query and parse _CRS to get the current IRQ assignment. + /* + * Query and parse _CRS to get the current IRQ assignment. */ status = acpi_walk_resources(link->device->handle, METHOD_NAME__CRS, @@ -396,7 +396,7 @@ static int acpi_pci_link_set(struct acpi_pci_link *link, int irq) /* * "acpi_irq_balance" (default in APIC mode) enables ACPI to use PIC Interrupt * Link Devices to move the PIRQs around to minimize sharing. - * + * * "acpi_irq_nobalance" (default in PIC mode) tells ACPI not to move any PIC IRQs * that the BIOS has already set to active. This is necessary because * ACPI has no automatic means of knowing what ISA IRQs are used. Note that @@ -414,7 +414,7 @@ static int acpi_pci_link_set(struct acpi_pci_link *link, int irq) * * Note that PCI IRQ routers have a list of possible IRQs, * which may not include the IRQs this table says are available. - * + * * Since this heuristic can't tell the difference between a link * that no device will attach to, vs. a link which may be shared * by multiple active devices -- it is not optimal. diff --git a/drivers/acpi/pci_mcfg.c b/drivers/acpi/pci_mcfg.c index 7ddd57abadd1..95f23acd5b80 100644 --- a/drivers/acpi/pci_mcfg.c +++ b/drivers/acpi/pci_mcfg.c @@ -173,7 +173,7 @@ static int pci_mcfg_quirk_matches(struct mcfg_fixup *f, u16 segment, { if (!memcmp(f->oem_id, mcfg_oem_id, ACPI_OEM_ID_SIZE) && !memcmp(f->oem_table_id, mcfg_oem_table_id, - ACPI_OEM_TABLE_ID_SIZE) && + ACPI_OEM_TABLE_ID_SIZE) && f->oem_revision == mcfg_oem_revision && f->segment == segment && resource_contains(&f->bus_range, bus_range)) diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c index 837b875d075e..8048da85b7e0 100644 --- a/drivers/acpi/power.c +++ b/drivers/acpi/power.c @@ -13,7 +13,7 @@ * 1. via "Device Specific (D-State) Control" * 2. via "Power Resource Control". * The code below deals with ACPI Power Resources control. - * + * * An ACPI "power resource object" represents a software controllable power * plane, clock plane, or other resource depended on by a device. * @@ -645,7 +645,7 @@ int acpi_power_wakeup_list_init(struct list_head *list, int *system_level_p) * -ENODEV if the execution of either _DSW or _PSW has failed */ int acpi_device_sleep_wake(struct acpi_device *dev, - int enable, int sleep_state, int dev_state) + int enable, int sleep_state, int dev_state) { union acpi_object in_arg[3]; struct acpi_object_list arg_list = { 3, in_arg }; @@ -690,7 +690,7 @@ int acpi_device_sleep_wake(struct acpi_device *dev, /* * Prepare a wakeup device, two steps (Ref ACPI 2.0:P229): - * 1. Power on the power resources required for the wakeup device + * 1. Power on the power resources required for the wakeup device * 2. Execute _DSW (Device Sleep Wake) or (deprecated in ACPI 3.0) _PSW (Power * State Wake) for the device, if present */ diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c index 5909e8fa4013..b04a68950ff1 100644 --- a/drivers/acpi/processor_perflib.c +++ b/drivers/acpi/processor_perflib.c @@ -354,7 +354,7 @@ static int acpi_processor_get_performance_states(struct acpi_processor *pr) (u32) px->control, (u32) px->status)); /* - * Check that ACPI's u64 MHz will be valid as u32 KHz in cpufreq + * Check that ACPI's u64 MHz will be valid as u32 KHz in cpufreq */ if (!px->core_frequency || ((u32)(px->core_frequency * 1000) != @@ -627,7 +627,7 @@ int acpi_processor_preregister_performance( goto err_ret; /* - * Now that we have _PSD data from all CPUs, lets setup P-state + * Now that we have _PSD data from all CPUs, lets setup P-state * domain info. */ for_each_possible_cpu(i) { @@ -693,7 +693,7 @@ int acpi_processor_preregister_performance( if (match_pdomain->domain != pdomain->domain) continue; - match_pr->performance->shared_type = + match_pr->performance->shared_type = pr->performance->shared_type; cpumask_copy(match_pr->performance->shared_cpu_map, pr->performance->shared_cpu_map); diff --git a/drivers/acpi/sbs.c b/drivers/acpi/sbs.c index f158b8c30113..e6d9f4de2800 100644 --- a/drivers/acpi/sbs.c +++ b/drivers/acpi/sbs.c @@ -366,7 +366,7 @@ static int acpi_battery_get_state(struct acpi_battery *battery) state_readers[i].mode, ACPI_SBS_BATTERY, state_readers[i].command, - (u8 *)battery + + (u8 *)battery + state_readers[i].offset); if (result) goto end; diff --git a/drivers/acpi/sbshc.c b/drivers/acpi/sbshc.c index 87b74e9015e5..53c2862c4c75 100644 --- a/drivers/acpi/sbshc.c +++ b/drivers/acpi/sbshc.c @@ -176,7 +176,7 @@ int acpi_smbus_write(struct acpi_smb_hc *hc, u8 protocol, u8 address, EXPORT_SYMBOL_GPL(acpi_smbus_write); int acpi_smbus_register_callback(struct acpi_smb_hc *hc, - smbus_alarm_callback callback, void *context) + smbus_alarm_callback callback, void *context) { mutex_lock(&hc->lock); hc->callback = callback; diff --git a/drivers/acpi/sbshc.h b/drivers/acpi/sbshc.h index c3522bb82792..695c390e2884 100644 --- a/drivers/acpi/sbshc.h +++ b/drivers/acpi/sbshc.h @@ -24,9 +24,9 @@ enum acpi_sbs_device_addr { typedef void (*smbus_alarm_callback)(void *context); extern int acpi_smbus_read(struct acpi_smb_hc *hc, u8 protocol, u8 address, - u8 command, u8 * data); + u8 command, u8 *data); extern int acpi_smbus_write(struct acpi_smb_hc *hc, u8 protocol, u8 slave_address, - u8 command, u8 * data, u8 length); + u8 command, u8 *data, u8 length); extern int acpi_smbus_register_callback(struct acpi_smb_hc *hc, - smbus_alarm_callback callback, void *context); + smbus_alarm_callback callback, void *context); extern int acpi_smbus_unregister_callback(struct acpi_smb_hc *hc); diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index a896e5e87c93..bc6a79e33220 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -1453,7 +1453,7 @@ int acpi_dma_get_range(struct device *dev, u64 *dma_addr, u64 *offset, } /** - * acpi_dma_configure - Set-up DMA configuration for the device. + * acpi_dma_configure_id - Set-up DMA configuration for the device. * @dev: The pointer to the device * @attr: device dma attributes * @input_id: input device id const value pointer diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index 3a032afd9d05..4f5463b2a217 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -178,14 +178,14 @@ static const struct dmi_system_id video_detect_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X201s"), }, }, - { - .callback = video_detect_force_video, - .ident = "ThinkPad X201T", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X201T"), - }, - }, + { + .callback = video_detect_force_video, + .ident = "ThinkPad X201T", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X201T"), + }, + }, /* The native backlight controls do not work on some older machines */ { diff --git a/drivers/acpi/wakeup.c b/drivers/acpi/wakeup.c index f89dd9a99e6e..b02bf770aead 100644 --- a/drivers/acpi/wakeup.c +++ b/drivers/acpi/wakeup.c @@ -44,7 +44,7 @@ void acpi_enable_wakeup_devices(u8 sleep_state) if (!dev->wakeup.flags.valid || sleep_state > (u32) dev->wakeup.sleep_state || !(device_may_wakeup(&dev->dev) - || dev->wakeup.prepare_count)) + || dev->wakeup.prepare_count)) continue; if (device_may_wakeup(&dev->dev)) @@ -69,7 +69,7 @@ void acpi_disable_wakeup_devices(u8 sleep_state) if (!dev->wakeup.flags.valid || sleep_state > (u32) dev->wakeup.sleep_state || !(device_may_wakeup(&dev->dev) - || dev->wakeup.prepare_count)) + || dev->wakeup.prepare_count)) continue; acpi_set_gpe_wake_mask(dev->wakeup.gpe_device, dev->wakeup.gpe_number, diff --git a/drivers/atm/nicstar.c b/drivers/atm/nicstar.c index 7af74fb450a0..09ad73361879 100644 --- a/drivers/atm/nicstar.c +++ b/drivers/atm/nicstar.c @@ -1706,6 +1706,8 @@ static int ns_send(struct atm_vcc *vcc, struct sk_buff *skb) if (push_scqe(card, vc, scq, &scqe, skb) != 0) { atomic_inc(&vcc->stats->tx_err); + dma_unmap_single(&card->pcidev->dev, NS_PRV_DMA(skb), skb->len, + DMA_TO_DEVICE); dev_kfree_skb_any(skb); return -EIO; } diff --git a/drivers/base/core.c b/drivers/base/core.c index 78114ddac755..d661ada1518f 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -773,8 +773,7 @@ static void __device_link_del(struct kref *kref) dev_dbg(link->consumer, "Dropping the link to %s\n", dev_name(link->supplier)); - if (link->flags & DL_FLAG_PM_RUNTIME) - pm_runtime_drop_link(link->consumer); + pm_runtime_drop_link(link); list_del_rcu(&link->s_node); list_del_rcu(&link->c_node); @@ -788,8 +787,7 @@ static void __device_link_del(struct kref *kref) dev_info(link->consumer, "Dropping the link to %s\n", dev_name(link->supplier)); - if (link->flags & DL_FLAG_PM_RUNTIME) - pm_runtime_drop_link(link->consumer); + pm_runtime_drop_link(link); list_del(&link->s_node); list_del(&link->c_node); diff --git a/drivers/base/dd.c b/drivers/base/dd.c index b42229b74fd6..148e81969e04 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -1117,6 +1117,8 @@ static void __device_release_driver(struct device *dev, struct device *parent) drv = dev->driver; if (drv) { + pm_runtime_get_sync(dev); + while (device_links_busy(dev)) { __device_driver_unlock(dev, parent); @@ -1128,13 +1130,12 @@ static void __device_release_driver(struct device *dev, struct device *parent) * have released the driver successfully while this one * was waiting, so check for that. */ - if (dev->driver != drv) + if (dev->driver != drv) { + pm_runtime_put(dev); return; + } } - pm_runtime_get_sync(dev); - pm_runtime_clean_up_links(dev); - driver_sysfs_remove(dev); if (dev->bus) diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index 6f605f7820bb..bfda153b1a41 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -1643,42 +1643,6 @@ void pm_runtime_remove(struct device *dev) } /** - * pm_runtime_clean_up_links - Prepare links to consumers for driver removal. - * @dev: Device whose driver is going to be removed. - * - * Check links from this device to any consumers and if any of them have active - * runtime PM references to the device, drop the usage counter of the device - * (as many times as needed). - * - * Links with the DL_FLAG_MANAGED flag unset are ignored. - * - * Since the device is guaranteed to be runtime-active at the point this is - * called, nothing else needs to be done here. - * - * Moreover, this is called after device_links_busy() has returned 'false', so - * the status of each link is guaranteed to be DL_STATE_SUPPLIER_UNBIND and - * therefore rpm_active can't be manipulated concurrently. - */ -void pm_runtime_clean_up_links(struct device *dev) -{ - struct device_link *link; - int idx; - - idx = device_links_read_lock(); - - list_for_each_entry_rcu(link, &dev->links.consumers, s_node, - device_links_read_lock_held()) { - if (!(link->flags & DL_FLAG_MANAGED)) - continue; - - while (refcount_dec_not_one(&link->rpm_active)) - pm_runtime_put_noidle(dev); - } - - device_links_read_unlock(idx); -} - -/** * pm_runtime_get_suppliers - Resume and reference-count supplier devices. * @dev: Consumer device. */ @@ -1729,7 +1693,7 @@ void pm_runtime_new_link(struct device *dev) spin_unlock_irq(&dev->power.lock); } -void pm_runtime_drop_link(struct device *dev) +static void pm_runtime_drop_link_count(struct device *dev) { spin_lock_irq(&dev->power.lock); WARN_ON(dev->power.links_count == 0); @@ -1737,6 +1701,25 @@ void pm_runtime_drop_link(struct device *dev) spin_unlock_irq(&dev->power.lock); } +/** + * pm_runtime_drop_link - Prepare for device link removal. + * @link: Device link going away. + * + * Drop the link count of the consumer end of @link and decrement the supplier + * device's runtime PM usage counter as many times as needed to drop all of the + * PM runtime reference to it from the consumer. + */ +void pm_runtime_drop_link(struct device_link *link) +{ + if (!(link->flags & DL_FLAG_PM_RUNTIME)) + return; + + pm_runtime_drop_link_count(link->consumer); + + while (refcount_dec_not_one(&link->rpm_active)) + pm_runtime_put(link->supplier); +} + static bool pm_runtime_need_not_resume(struct device *dev) { return atomic_read(&dev->power.usage_count) <= 1 && diff --git a/drivers/block/loop.c b/drivers/block/loop.c index cb1191d6e945..a58084c2ed7c 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -255,7 +255,8 @@ static void loop_set_size(struct loop_device *lo, loff_t size) bd_set_nr_sectors(bdev, size); - set_capacity_revalidate_and_notify(lo->lo_disk, size, false); + if (!set_capacity_revalidate_and_notify(lo->lo_disk, size, false)) + kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE); } static inline int diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index c4f9ccf5cc2a..aaae9220f3a0 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1518,6 +1518,7 @@ static void nbd_release(struct gendisk *disk, fmode_t mode) if (test_bit(NBD_RT_DISCONNECT_ON_CLOSE, &nbd->config->runtime_flags) && bdev->bd_openers == 0) nbd_disconnect_and_put(nbd); + bdput(bdev); nbd_config_put(nbd); nbd_put(nbd); diff --git a/drivers/block/null_blk.h b/drivers/block/null_blk.h index cfd00ad40355..c24d9b5ad81a 100644 --- a/drivers/block/null_blk.h +++ b/drivers/block/null_blk.h @@ -47,7 +47,7 @@ struct nullb_device { unsigned int nr_zones_closed; struct blk_zone *zones; sector_t zone_size_sects; - spinlock_t zone_dev_lock; + spinlock_t zone_lock; unsigned long *zone_locks; unsigned long size; /* device size in MB */ diff --git a/drivers/block/null_blk_zoned.c b/drivers/block/null_blk_zoned.c index 8775acbb4f8f..beb34b4f76b0 100644 --- a/drivers/block/null_blk_zoned.c +++ b/drivers/block/null_blk_zoned.c @@ -46,11 +46,20 @@ int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q) if (!dev->zones) return -ENOMEM; - spin_lock_init(&dev->zone_dev_lock); - dev->zone_locks = bitmap_zalloc(dev->nr_zones, GFP_KERNEL); - if (!dev->zone_locks) { - kvfree(dev->zones); - return -ENOMEM; + /* + * With memory backing, the zone_lock spinlock needs to be temporarily + * released to avoid scheduling in atomic context. To guarantee zone + * information protection, use a bitmap to lock zones with + * wait_on_bit_lock_io(). Sleeping on the lock is OK as memory backing + * implies that the queue is marked with BLK_MQ_F_BLOCKING. + */ + spin_lock_init(&dev->zone_lock); + if (dev->memory_backed) { + dev->zone_locks = bitmap_zalloc(dev->nr_zones, GFP_KERNEL); + if (!dev->zone_locks) { + kvfree(dev->zones); + return -ENOMEM; + } } if (dev->zone_nr_conv >= dev->nr_zones) { @@ -137,12 +146,17 @@ void null_free_zoned_dev(struct nullb_device *dev) static inline void null_lock_zone(struct nullb_device *dev, unsigned int zno) { - wait_on_bit_lock_io(dev->zone_locks, zno, TASK_UNINTERRUPTIBLE); + if (dev->memory_backed) + wait_on_bit_lock_io(dev->zone_locks, zno, TASK_UNINTERRUPTIBLE); + spin_lock_irq(&dev->zone_lock); } static inline void null_unlock_zone(struct nullb_device *dev, unsigned int zno) { - clear_and_wake_up_bit(zno, dev->zone_locks); + spin_unlock_irq(&dev->zone_lock); + + if (dev->memory_backed) + clear_and_wake_up_bit(zno, dev->zone_locks); } int null_report_zones(struct gendisk *disk, sector_t sector, @@ -322,7 +336,6 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector, return null_process_cmd(cmd, REQ_OP_WRITE, sector, nr_sectors); null_lock_zone(dev, zno); - spin_lock(&dev->zone_dev_lock); switch (zone->cond) { case BLK_ZONE_COND_FULL: @@ -375,9 +388,17 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector, if (zone->cond != BLK_ZONE_COND_EXP_OPEN) zone->cond = BLK_ZONE_COND_IMP_OPEN; - spin_unlock(&dev->zone_dev_lock); + /* + * Memory backing allocation may sleep: release the zone_lock spinlock + * to avoid scheduling in atomic context. Zone operation atomicity is + * still guaranteed through the zone_locks bitmap. + */ + if (dev->memory_backed) + spin_unlock_irq(&dev->zone_lock); ret = null_process_cmd(cmd, REQ_OP_WRITE, sector, nr_sectors); - spin_lock(&dev->zone_dev_lock); + if (dev->memory_backed) + spin_lock_irq(&dev->zone_lock); + if (ret != BLK_STS_OK) goto unlock; @@ -392,7 +413,6 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector, ret = BLK_STS_OK; unlock: - spin_unlock(&dev->zone_dev_lock); null_unlock_zone(dev, zno); return ret; @@ -516,9 +536,7 @@ static blk_status_t null_zone_mgmt(struct nullb_cmd *cmd, enum req_opf op, null_lock_zone(dev, i); zone = &dev->zones[i]; if (zone->cond != BLK_ZONE_COND_EMPTY) { - spin_lock(&dev->zone_dev_lock); null_reset_zone(dev, zone); - spin_unlock(&dev->zone_dev_lock); trace_nullb_zone_op(cmd, i, zone->cond); } null_unlock_zone(dev, i); @@ -530,7 +548,6 @@ static blk_status_t null_zone_mgmt(struct nullb_cmd *cmd, enum req_opf op, zone = &dev->zones[zone_no]; null_lock_zone(dev, zone_no); - spin_lock(&dev->zone_dev_lock); switch (op) { case REQ_OP_ZONE_RESET: @@ -550,8 +567,6 @@ static blk_status_t null_zone_mgmt(struct nullb_cmd *cmd, enum req_opf op, break; } - spin_unlock(&dev->zone_dev_lock); - if (ret == BLK_STS_OK) trace_nullb_zone_op(cmd, zone_no, zone->cond); diff --git a/drivers/char/tpm/eventlog/efi.c b/drivers/char/tpm/eventlog/efi.c index 6bb023de17f1..35229e5143ca 100644 --- a/drivers/char/tpm/eventlog/efi.c +++ b/drivers/char/tpm/eventlog/efi.c @@ -41,6 +41,11 @@ int tpm_read_log_efi(struct tpm_chip *chip) log_size = log_tbl->size; memunmap(log_tbl); + if (!log_size) { + pr_warn("UEFI TPM log area empty\n"); + return -EIO; + } + log_tbl = memremap(efi.tpm_log, sizeof(*log_tbl) + log_size, MEMREMAP_WB); if (!log_tbl) { diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c index 0b214963539d..4ed6e660273a 100644 --- a/drivers/char/tpm/tpm_tis.c +++ b/drivers/char/tpm/tpm_tis.c @@ -27,6 +27,7 @@ #include <linux/of.h> #include <linux/of_device.h> #include <linux/kernel.h> +#include <linux/dmi.h> #include "tpm.h" #include "tpm_tis_core.h" @@ -49,8 +50,8 @@ static inline struct tpm_tis_tcg_phy *to_tpm_tis_tcg_phy(struct tpm_tis_data *da return container_of(data, struct tpm_tis_tcg_phy, priv); } -static bool interrupts = true; -module_param(interrupts, bool, 0444); +static int interrupts = -1; +module_param(interrupts, int, 0444); MODULE_PARM_DESC(interrupts, "Enable interrupts"); static bool itpm; @@ -63,6 +64,28 @@ module_param(force, bool, 0444); MODULE_PARM_DESC(force, "Force device probe rather than using ACPI entry"); #endif +static int tpm_tis_disable_irq(const struct dmi_system_id *d) +{ + if (interrupts == -1) { + pr_notice("tpm_tis: %s detected: disabling interrupts.\n", d->ident); + interrupts = 0; + } + + return 0; +} + +static const struct dmi_system_id tpm_tis_dmi_table[] = { + { + .callback = tpm_tis_disable_irq, + .ident = "ThinkPad T490s", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T490s"), + }, + }, + {} +}; + #if defined(CONFIG_PNP) && defined(CONFIG_ACPI) static int has_hid(struct acpi_device *dev, const char *hid) { @@ -192,6 +215,8 @@ static int tpm_tis_init(struct device *dev, struct tpm_info *tpm_info) int irq = -1; int rc; + dmi_check_system(tpm_tis_dmi_table); + rc = check_acpi_tpm2(dev); if (rc) return rc; diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index a2da8f768b94..1836cc56e357 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -435,12 +435,12 @@ static struct port_buffer *alloc_buf(struct virtio_device *vdev, size_t buf_size /* * Allocate DMA memory from ancestor. When a virtio * device is created by remoteproc, the DMA memory is - * associated with the grandparent device: - * vdev => rproc => platform-dev. + * associated with the parent device: + * virtioY => remoteprocX#vdevYbuffer. */ - if (!vdev->dev.parent || !vdev->dev.parent->parent) + buf->dev = vdev->dev.parent; + if (!buf->dev) goto free_buf; - buf->dev = vdev->dev.parent->parent; /* Increase device refcnt to avoid freeing it */ get_device(buf->dev); diff --git a/drivers/clk/imx/clk-imx8mm.c b/drivers/clk/imx/clk-imx8mm.c index 0de0be0cf548..f358ad907299 100644 --- a/drivers/clk/imx/clk-imx8mm.c +++ b/drivers/clk/imx/clk-imx8mm.c @@ -443,9 +443,9 @@ static int imx8mm_clocks_probe(struct platform_device *pdev) hws[IMX8MM_CLK_A53_CORE] = imx_clk_hw_mux2("arm_a53_core", base + 0x9880, 24, 1, imx8mm_a53_core_sels, ARRAY_SIZE(imx8mm_a53_core_sels)); /* BUS */ - hws[IMX8MM_CLK_MAIN_AXI] = imx8m_clk_hw_composite_critical("main_axi", imx8mm_main_axi_sels, base + 0x8800); + hws[IMX8MM_CLK_MAIN_AXI] = imx8m_clk_hw_composite_bus_critical("main_axi", imx8mm_main_axi_sels, base + 0x8800); hws[IMX8MM_CLK_ENET_AXI] = imx8m_clk_hw_composite_bus("enet_axi", imx8mm_enet_axi_sels, base + 0x8880); - hws[IMX8MM_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite_critical("nand_usdhc_bus", imx8mm_nand_usdhc_sels, base + 0x8900); + hws[IMX8MM_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite_bus_critical("nand_usdhc_bus", imx8mm_nand_usdhc_sels, base + 0x8900); hws[IMX8MM_CLK_VPU_BUS] = imx8m_clk_hw_composite_bus("vpu_bus", imx8mm_vpu_bus_sels, base + 0x8980); hws[IMX8MM_CLK_DISP_AXI] = imx8m_clk_hw_composite_bus("disp_axi", imx8mm_disp_axi_sels, base + 0x8a00); hws[IMX8MM_CLK_DISP_APB] = imx8m_clk_hw_composite_bus("disp_apb", imx8mm_disp_apb_sels, base + 0x8a80); @@ -453,11 +453,11 @@ static int imx8mm_clocks_probe(struct platform_device *pdev) hws[IMX8MM_CLK_USB_BUS] = imx8m_clk_hw_composite_bus("usb_bus", imx8mm_usb_bus_sels, base + 0x8b80); hws[IMX8MM_CLK_GPU_AXI] = imx8m_clk_hw_composite_bus("gpu_axi", imx8mm_gpu_axi_sels, base + 0x8c00); hws[IMX8MM_CLK_GPU_AHB] = imx8m_clk_hw_composite_bus("gpu_ahb", imx8mm_gpu_ahb_sels, base + 0x8c80); - hws[IMX8MM_CLK_NOC] = imx8m_clk_hw_composite_critical("noc", imx8mm_noc_sels, base + 0x8d00); - hws[IMX8MM_CLK_NOC_APB] = imx8m_clk_hw_composite_critical("noc_apb", imx8mm_noc_apb_sels, base + 0x8d80); + hws[IMX8MM_CLK_NOC] = imx8m_clk_hw_composite_bus_critical("noc", imx8mm_noc_sels, base + 0x8d00); + hws[IMX8MM_CLK_NOC_APB] = imx8m_clk_hw_composite_bus_critical("noc_apb", imx8mm_noc_apb_sels, base + 0x8d80); /* AHB */ - hws[IMX8MM_CLK_AHB] = imx8m_clk_hw_composite_critical("ahb", imx8mm_ahb_sels, base + 0x9000); + hws[IMX8MM_CLK_AHB] = imx8m_clk_hw_composite_bus_critical("ahb", imx8mm_ahb_sels, base + 0x9000); hws[IMX8MM_CLK_AUDIO_AHB] = imx8m_clk_hw_composite_bus("audio_ahb", imx8mm_audio_ahb_sels, base + 0x9100); /* IPG */ diff --git a/drivers/clk/imx/clk-imx8mn.c b/drivers/clk/imx/clk-imx8mn.c index e984de543f0b..f3c5e6cf55dd 100644 --- a/drivers/clk/imx/clk-imx8mn.c +++ b/drivers/clk/imx/clk-imx8mn.c @@ -431,7 +431,7 @@ static int imx8mn_clocks_probe(struct platform_device *pdev) hws[IMX8MN_CLK_A53_CORE] = imx_clk_hw_mux2("arm_a53_core", base + 0x9880, 24, 1, imx8mn_a53_core_sels, ARRAY_SIZE(imx8mn_a53_core_sels)); /* BUS */ - hws[IMX8MN_CLK_MAIN_AXI] = imx8m_clk_hw_composite_critical("main_axi", imx8mn_main_axi_sels, base + 0x8800); + hws[IMX8MN_CLK_MAIN_AXI] = imx8m_clk_hw_composite_bus_critical("main_axi", imx8mn_main_axi_sels, base + 0x8800); hws[IMX8MN_CLK_ENET_AXI] = imx8m_clk_hw_composite_bus("enet_axi", imx8mn_enet_axi_sels, base + 0x8880); hws[IMX8MN_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite_bus("nand_usdhc_bus", imx8mn_nand_usdhc_sels, base + 0x8900); hws[IMX8MN_CLK_DISP_AXI] = imx8m_clk_hw_composite_bus("disp_axi", imx8mn_disp_axi_sels, base + 0x8a00); @@ -439,9 +439,9 @@ static int imx8mn_clocks_probe(struct platform_device *pdev) hws[IMX8MN_CLK_USB_BUS] = imx8m_clk_hw_composite_bus("usb_bus", imx8mn_usb_bus_sels, base + 0x8b80); hws[IMX8MN_CLK_GPU_AXI] = imx8m_clk_hw_composite_bus("gpu_axi", imx8mn_gpu_axi_sels, base + 0x8c00); hws[IMX8MN_CLK_GPU_AHB] = imx8m_clk_hw_composite_bus("gpu_ahb", imx8mn_gpu_ahb_sels, base + 0x8c80); - hws[IMX8MN_CLK_NOC] = imx8m_clk_hw_composite_critical("noc", imx8mn_noc_sels, base + 0x8d00); + hws[IMX8MN_CLK_NOC] = imx8m_clk_hw_composite_bus_critical("noc", imx8mn_noc_sels, base + 0x8d00); - hws[IMX8MN_CLK_AHB] = imx8m_clk_hw_composite_critical("ahb", imx8mn_ahb_sels, base + 0x9000); + hws[IMX8MN_CLK_AHB] = imx8m_clk_hw_composite_bus_critical("ahb", imx8mn_ahb_sels, base + 0x9000); hws[IMX8MN_CLK_AUDIO_AHB] = imx8m_clk_hw_composite_bus("audio_ahb", imx8mn_audio_ahb_sels, base + 0x9100); hws[IMX8MN_CLK_IPG_ROOT] = imx_clk_hw_divider2("ipg_root", "ahb", base + 0x9080, 0, 1); hws[IMX8MN_CLK_IPG_AUDIO_ROOT] = imx_clk_hw_divider2("ipg_audio_root", "audio_ahb", base + 0x9180, 0, 1); diff --git a/drivers/clk/imx/clk-imx8mp.c b/drivers/clk/imx/clk-imx8mp.c index 12ce4770f702..48e212477f52 100644 --- a/drivers/clk/imx/clk-imx8mp.c +++ b/drivers/clk/imx/clk-imx8mp.c @@ -557,9 +557,9 @@ static int imx8mp_clocks_probe(struct platform_device *pdev) /* CORE SEL */ hws[IMX8MP_CLK_A53_CORE] = imx_clk_hw_mux2("arm_a53_core", ccm_base + 0x9880, 24, 1, imx8mp_a53_core_sels, ARRAY_SIZE(imx8mp_a53_core_sels)); - hws[IMX8MP_CLK_MAIN_AXI] = imx8m_clk_hw_composite_critical("main_axi", imx8mp_main_axi_sels, ccm_base + 0x8800); + hws[IMX8MP_CLK_MAIN_AXI] = imx8m_clk_hw_composite_bus_critical("main_axi", imx8mp_main_axi_sels, ccm_base + 0x8800); hws[IMX8MP_CLK_ENET_AXI] = imx8m_clk_hw_composite_bus("enet_axi", imx8mp_enet_axi_sels, ccm_base + 0x8880); - hws[IMX8MP_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite_critical("nand_usdhc_bus", imx8mp_nand_usdhc_sels, ccm_base + 0x8900); + hws[IMX8MP_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite_bus_critical("nand_usdhc_bus", imx8mp_nand_usdhc_sels, ccm_base + 0x8900); hws[IMX8MP_CLK_VPU_BUS] = imx8m_clk_hw_composite_bus("vpu_bus", imx8mp_vpu_bus_sels, ccm_base + 0x8980); hws[IMX8MP_CLK_MEDIA_AXI] = imx8m_clk_hw_composite_bus("media_axi", imx8mp_media_axi_sels, ccm_base + 0x8a00); hws[IMX8MP_CLK_MEDIA_APB] = imx8m_clk_hw_composite_bus("media_apb", imx8mp_media_apb_sels, ccm_base + 0x8a80); @@ -567,12 +567,12 @@ static int imx8mp_clocks_probe(struct platform_device *pdev) hws[IMX8MP_CLK_HDMI_AXI] = imx8m_clk_hw_composite_bus("hdmi_axi", imx8mp_media_axi_sels, ccm_base + 0x8b80); hws[IMX8MP_CLK_GPU_AXI] = imx8m_clk_hw_composite_bus("gpu_axi", imx8mp_gpu_axi_sels, ccm_base + 0x8c00); hws[IMX8MP_CLK_GPU_AHB] = imx8m_clk_hw_composite_bus("gpu_ahb", imx8mp_gpu_ahb_sels, ccm_base + 0x8c80); - hws[IMX8MP_CLK_NOC] = imx8m_clk_hw_composite_critical("noc", imx8mp_noc_sels, ccm_base + 0x8d00); - hws[IMX8MP_CLK_NOC_IO] = imx8m_clk_hw_composite_critical("noc_io", imx8mp_noc_io_sels, ccm_base + 0x8d80); + hws[IMX8MP_CLK_NOC] = imx8m_clk_hw_composite_bus_critical("noc", imx8mp_noc_sels, ccm_base + 0x8d00); + hws[IMX8MP_CLK_NOC_IO] = imx8m_clk_hw_composite_bus_critical("noc_io", imx8mp_noc_io_sels, ccm_base + 0x8d80); hws[IMX8MP_CLK_ML_AXI] = imx8m_clk_hw_composite_bus("ml_axi", imx8mp_ml_axi_sels, ccm_base + 0x8e00); hws[IMX8MP_CLK_ML_AHB] = imx8m_clk_hw_composite_bus("ml_ahb", imx8mp_ml_ahb_sels, ccm_base + 0x8e80); - hws[IMX8MP_CLK_AHB] = imx8m_clk_hw_composite_critical("ahb_root", imx8mp_ahb_sels, ccm_base + 0x9000); + hws[IMX8MP_CLK_AHB] = imx8m_clk_hw_composite_bus_critical("ahb_root", imx8mp_ahb_sels, ccm_base + 0x9000); hws[IMX8MP_CLK_AUDIO_AHB] = imx8m_clk_hw_composite_bus("audio_ahb", imx8mp_audio_ahb_sels, ccm_base + 0x9100); hws[IMX8MP_CLK_MIPI_DSI_ESC_RX] = imx8m_clk_hw_composite_bus("mipi_dsi_esc_rx", imx8mp_mipi_dsi_esc_rx_sels, ccm_base + 0x9200); diff --git a/drivers/clk/imx/clk-imx8mq.c b/drivers/clk/imx/clk-imx8mq.c index 8265d1d48af4..06292d4a98ff 100644 --- a/drivers/clk/imx/clk-imx8mq.c +++ b/drivers/clk/imx/clk-imx8mq.c @@ -431,7 +431,7 @@ static int imx8mq_clocks_probe(struct platform_device *pdev) hws[IMX8MQ_CLK_A53_CORE] = imx_clk_hw_mux2("arm_a53_core", base + 0x9880, 24, 1, imx8mq_a53_core_sels, ARRAY_SIZE(imx8mq_a53_core_sels)); /* BUS */ - hws[IMX8MQ_CLK_MAIN_AXI] = imx8m_clk_hw_composite_critical("main_axi", imx8mq_main_axi_sels, base + 0x8800); + hws[IMX8MQ_CLK_MAIN_AXI] = imx8m_clk_hw_composite_bus_critical("main_axi", imx8mq_main_axi_sels, base + 0x8800); hws[IMX8MQ_CLK_ENET_AXI] = imx8m_clk_hw_composite_bus("enet_axi", imx8mq_enet_axi_sels, base + 0x8880); hws[IMX8MQ_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite_bus("nand_usdhc_bus", imx8mq_nand_usdhc_sels, base + 0x8900); hws[IMX8MQ_CLK_VPU_BUS] = imx8m_clk_hw_composite_bus("vpu_bus", imx8mq_vpu_bus_sels, base + 0x8980); @@ -441,12 +441,12 @@ static int imx8mq_clocks_probe(struct platform_device *pdev) hws[IMX8MQ_CLK_USB_BUS] = imx8m_clk_hw_composite_bus("usb_bus", imx8mq_usb_bus_sels, base + 0x8b80); hws[IMX8MQ_CLK_GPU_AXI] = imx8m_clk_hw_composite_bus("gpu_axi", imx8mq_gpu_axi_sels, base + 0x8c00); hws[IMX8MQ_CLK_GPU_AHB] = imx8m_clk_hw_composite_bus("gpu_ahb", imx8mq_gpu_ahb_sels, base + 0x8c80); - hws[IMX8MQ_CLK_NOC] = imx8m_clk_hw_composite_critical("noc", imx8mq_noc_sels, base + 0x8d00); - hws[IMX8MQ_CLK_NOC_APB] = imx8m_clk_hw_composite_critical("noc_apb", imx8mq_noc_apb_sels, base + 0x8d80); + hws[IMX8MQ_CLK_NOC] = imx8m_clk_hw_composite_bus_critical("noc", imx8mq_noc_sels, base + 0x8d00); + hws[IMX8MQ_CLK_NOC_APB] = imx8m_clk_hw_composite_bus_critical("noc_apb", imx8mq_noc_apb_sels, base + 0x8d80); /* AHB */ /* AHB clock is used by the AHB bus therefore marked as critical */ - hws[IMX8MQ_CLK_AHB] = imx8m_clk_hw_composite_critical("ahb", imx8mq_ahb_sels, base + 0x9000); + hws[IMX8MQ_CLK_AHB] = imx8m_clk_hw_composite_bus_critical("ahb", imx8mq_ahb_sels, base + 0x9000); hws[IMX8MQ_CLK_AUDIO_AHB] = imx8m_clk_hw_composite_bus("audio_ahb", imx8mq_audio_ahb_sels, base + 0x9100); /* IPG */ diff --git a/drivers/clk/imx/clk.h b/drivers/clk/imx/clk.h index 3b796b3da249..1d7be0c86538 100644 --- a/drivers/clk/imx/clk.h +++ b/drivers/clk/imx/clk.h @@ -549,6 +549,11 @@ struct clk_hw *imx8m_clk_hw_composite_flags(const char *name, IMX_COMPOSITE_BUS, \ CLK_SET_RATE_NO_REPARENT | CLK_OPS_PARENT_ENABLE) +#define imx8m_clk_hw_composite_bus_critical(name, parent_names, reg) \ + imx8m_clk_hw_composite_flags(name, parent_names, ARRAY_SIZE(parent_names), reg, \ + IMX_COMPOSITE_BUS, \ + CLK_SET_RATE_NO_REPARENT | CLK_OPS_PARENT_ENABLE | CLK_IS_CRITICAL) + #define imx8m_clk_hw_composite_core(name, parent_names, reg) \ imx8m_clk_hw_composite_flags(name, parent_names, \ ARRAY_SIZE(parent_names), reg, \ diff --git a/drivers/clk/meson/clk-regmap.h b/drivers/clk/meson/clk-regmap.h index c4a39604cffd..e365312da54e 100644 --- a/drivers/clk/meson/clk-regmap.h +++ b/drivers/clk/meson/clk-regmap.h @@ -26,7 +26,10 @@ struct clk_regmap { void *data; }; -#define to_clk_regmap(_hw) container_of(_hw, struct clk_regmap, hw) +static inline struct clk_regmap *to_clk_regmap(struct clk_hw *hw) +{ + return container_of(hw, struct clk_regmap, hw); +} /** * struct clk_regmap_gate_data - regmap backed gate specific data diff --git a/drivers/clk/qcom/clk-regmap.h b/drivers/clk/qcom/clk-regmap.h index 6cfc1bccb255..14ec659a3a77 100644 --- a/drivers/clk/qcom/clk-regmap.h +++ b/drivers/clk/qcom/clk-regmap.h @@ -24,7 +24,11 @@ struct clk_regmap { unsigned int enable_mask; bool enable_is_inverted; }; -#define to_clk_regmap(_hw) container_of(_hw, struct clk_regmap, hw) + +static inline struct clk_regmap *to_clk_regmap(struct clk_hw *hw) +{ + return container_of(hw, struct clk_regmap, hw); +} int clk_is_enabled_regmap(struct clk_hw *hw); int clk_enable_regmap(struct clk_hw *hw); diff --git a/drivers/counter/ti-eqep.c b/drivers/counter/ti-eqep.c index e27771df8e23..a60aee1a1a29 100644 --- a/drivers/counter/ti-eqep.c +++ b/drivers/counter/ti-eqep.c @@ -368,7 +368,7 @@ static const struct regmap_config ti_eqep_regmap32_config = { .reg_bits = 32, .val_bits = 32, .reg_stride = 4, - .max_register = 0x24, + .max_register = QUPRD, }; static const struct regmap_config ti_eqep_regmap16_config = { @@ -376,7 +376,7 @@ static const struct regmap_config ti_eqep_regmap16_config = { .reg_bits = 16, .val_bits = 16, .reg_stride = 2, - .max_register = 0x1e, + .max_register = QCPRDLAT, }; static int ti_eqep_probe(struct platform_device *pdev) diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 336b5e94cbc8..1e7e3f2ff09f 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -2254,7 +2254,7 @@ static int cpufreq_init_governor(struct cpufreq_policy *policy) return -EINVAL; /* Platform doesn't want dynamic frequency switching ? */ - if (policy->governor->dynamic_switching && + if (policy->governor->flags & CPUFREQ_GOV_DYNAMIC_SWITCHING && cpufreq_driver->flags & CPUFREQ_NO_AUTO_DYNAMIC_SWITCHING) { struct cpufreq_governor *gov = cpufreq_fallback_governor(); @@ -2280,6 +2280,8 @@ static int cpufreq_init_governor(struct cpufreq_policy *policy) } } + policy->strict_target = !!(policy->governor->flags & CPUFREQ_GOV_STRICT_TARGET); + return 0; } diff --git a/drivers/cpufreq/cpufreq_governor.h b/drivers/cpufreq/cpufreq_governor.h index c56773c25757..bab8e6140377 100644 --- a/drivers/cpufreq/cpufreq_governor.h +++ b/drivers/cpufreq/cpufreq_governor.h @@ -156,7 +156,7 @@ void cpufreq_dbs_governor_limits(struct cpufreq_policy *policy); #define CPUFREQ_DBS_GOVERNOR_INITIALIZER(_name_) \ { \ .name = _name_, \ - .dynamic_switching = true, \ + .flags = CPUFREQ_GOV_DYNAMIC_SWITCHING, \ .owner = THIS_MODULE, \ .init = cpufreq_dbs_governor_init, \ .exit = cpufreq_dbs_governor_exit, \ diff --git a/drivers/cpufreq/cpufreq_performance.c b/drivers/cpufreq/cpufreq_performance.c index 71c1d9aba772..addd93f2a420 100644 --- a/drivers/cpufreq/cpufreq_performance.c +++ b/drivers/cpufreq/cpufreq_performance.c @@ -20,6 +20,7 @@ static void cpufreq_gov_performance_limits(struct cpufreq_policy *policy) static struct cpufreq_governor cpufreq_gov_performance = { .name = "performance", .owner = THIS_MODULE, + .flags = CPUFREQ_GOV_STRICT_TARGET, .limits = cpufreq_gov_performance_limits, }; diff --git a/drivers/cpufreq/cpufreq_powersave.c b/drivers/cpufreq/cpufreq_powersave.c index 7749522355b5..8d830d860e91 100644 --- a/drivers/cpufreq/cpufreq_powersave.c +++ b/drivers/cpufreq/cpufreq_powersave.c @@ -21,6 +21,7 @@ static struct cpufreq_governor cpufreq_gov_powersave = { .name = "powersave", .limits = cpufreq_gov_powersave_limits, .owner = THIS_MODULE, + .flags = CPUFREQ_GOV_STRICT_TARGET, }; MODULE_AUTHOR("Dominik Brodowski <linux@brodo.de>"); diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index b7a9779250aa..36a3ccfe6d3d 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -2527,7 +2527,7 @@ static void intel_cpufreq_trace(struct cpudata *cpu, unsigned int trace_type, in } static void intel_cpufreq_adjust_hwp(struct cpudata *cpu, u32 target_pstate, - bool fast_switch) + bool strict, bool fast_switch) { u64 prev = READ_ONCE(cpu->hwp_req_cached), value = prev; @@ -2539,7 +2539,7 @@ static void intel_cpufreq_adjust_hwp(struct cpudata *cpu, u32 target_pstate, * field in it, so opportunistically update the max too if needed. */ value &= ~HWP_MAX_PERF(~0L); - value |= HWP_MAX_PERF(cpu->max_perf_ratio); + value |= HWP_MAX_PERF(strict ? target_pstate : cpu->max_perf_ratio); if (value == prev) return; @@ -2562,14 +2562,16 @@ static void intel_cpufreq_adjust_perf_ctl(struct cpudata *cpu, pstate_funcs.get_val(cpu, target_pstate)); } -static int intel_cpufreq_update_pstate(struct cpudata *cpu, int target_pstate, - bool fast_switch) +static int intel_cpufreq_update_pstate(struct cpufreq_policy *policy, + int target_pstate, bool fast_switch) { + struct cpudata *cpu = all_cpu_data[policy->cpu]; int old_pstate = cpu->pstate.current_pstate; target_pstate = intel_pstate_prepare_request(cpu, target_pstate); if (hwp_active) { - intel_cpufreq_adjust_hwp(cpu, target_pstate, fast_switch); + intel_cpufreq_adjust_hwp(cpu, target_pstate, + policy->strict_target, fast_switch); cpu->pstate.current_pstate = target_pstate; } else if (target_pstate != old_pstate) { intel_cpufreq_adjust_perf_ctl(cpu, target_pstate, fast_switch); @@ -2609,7 +2611,7 @@ static int intel_cpufreq_target(struct cpufreq_policy *policy, break; } - target_pstate = intel_cpufreq_update_pstate(cpu, target_pstate, false); + target_pstate = intel_cpufreq_update_pstate(policy, target_pstate, false); freqs.new = target_pstate * cpu->pstate.scaling; @@ -2628,7 +2630,7 @@ static unsigned int intel_cpufreq_fast_switch(struct cpufreq_policy *policy, target_pstate = DIV_ROUND_UP(target_freq, cpu->pstate.scaling); - target_pstate = intel_cpufreq_update_pstate(cpu, target_pstate, true); + target_pstate = intel_cpufreq_update_pstate(policy, target_pstate, true); return target_pstate * cpu->pstate.scaling; } diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c index e855e8612a67..78318508a6d6 100644 --- a/drivers/cpufreq/scmi-cpufreq.c +++ b/drivers/cpufreq/scmi-cpufreq.c @@ -8,6 +8,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/clk-provider.h> #include <linux/cpu.h> #include <linux/cpufreq.h> #include <linux/cpumask.h> @@ -228,12 +229,17 @@ static struct cpufreq_driver scmi_cpufreq_driver = { static int scmi_cpufreq_probe(struct scmi_device *sdev) { int ret; + struct device *dev = &sdev->dev; handle = sdev->handle; if (!handle || !handle->perf_ops) return -ENODEV; + /* dummy clock provider as needed by OPP if clocks property is used */ + if (of_find_property(dev->of_node, "#clock-cells", NULL)) + devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get, NULL); + ret = cpufreq_register_driver(&scmi_cpufreq_driver); if (ret) { dev_err(&sdev->dev, "%s: registering cpufreq failed, err: %d\n", diff --git a/drivers/cpufreq/tegra186-cpufreq.c b/drivers/cpufreq/tegra186-cpufreq.c index 4b4079f51559..7eb2c56c65de 100644 --- a/drivers/cpufreq/tegra186-cpufreq.c +++ b/drivers/cpufreq/tegra186-cpufreq.c @@ -42,6 +42,8 @@ static const struct tegra186_cpufreq_cluster_info tegra186_clusters[] = { struct tegra186_cpufreq_cluster { const struct tegra186_cpufreq_cluster_info *info; struct cpufreq_frequency_table *table; + u32 ref_clk_khz; + u32 div; }; struct tegra186_cpufreq_data { @@ -94,7 +96,7 @@ static int tegra186_cpufreq_set_target(struct cpufreq_policy *policy, static unsigned int tegra186_cpufreq_get(unsigned int cpu) { - struct cpufreq_frequency_table *tbl; + struct tegra186_cpufreq_data *data = cpufreq_get_driver_data(); struct cpufreq_policy *policy; void __iomem *edvd_reg; unsigned int i, freq = 0; @@ -104,17 +106,23 @@ static unsigned int tegra186_cpufreq_get(unsigned int cpu) if (!policy) return 0; - tbl = policy->freq_table; edvd_reg = policy->driver_data; ndiv = readl(edvd_reg) & EDVD_CORE_VOLT_FREQ_F_MASK; - for (i = 0; tbl[i].frequency != CPUFREQ_TABLE_END; i++) { - if ((tbl[i].driver_data & EDVD_CORE_VOLT_FREQ_F_MASK) == ndiv) { - freq = tbl[i].frequency; - break; + for (i = 0; i < data->num_clusters; i++) { + struct tegra186_cpufreq_cluster *cluster = &data->clusters[i]; + int core; + + for (core = 0; core < ARRAY_SIZE(cluster->info->cpus); core++) { + if (cluster->info->cpus[core] != policy->cpu) + continue; + + freq = (cluster->ref_clk_khz * ndiv) / cluster->div; + goto out; } } +out: cpufreq_cpu_put(policy); return freq; @@ -133,7 +141,7 @@ static struct cpufreq_driver tegra186_cpufreq_driver = { static struct cpufreq_frequency_table *init_vhint_table( struct platform_device *pdev, struct tegra_bpmp *bpmp, - unsigned int cluster_id) + struct tegra186_cpufreq_cluster *cluster) { struct cpufreq_frequency_table *table; struct mrq_cpu_vhint_request req; @@ -152,7 +160,7 @@ static struct cpufreq_frequency_table *init_vhint_table( memset(&req, 0, sizeof(req)); req.addr = phys; - req.cluster_id = cluster_id; + req.cluster_id = cluster->info->bpmp_cluster_id; memset(&msg, 0, sizeof(msg)); msg.mrq = MRQ_CPU_VHINT; @@ -185,6 +193,9 @@ static struct cpufreq_frequency_table *init_vhint_table( goto free; } + cluster->ref_clk_khz = data->ref_clk_hz / 1000; + cluster->div = data->pdiv * data->mdiv; + for (i = data->vfloor, j = 0; i <= data->vceil; i++) { struct cpufreq_frequency_table *point; u16 ndiv = data->ndiv[i]; @@ -202,8 +213,7 @@ static struct cpufreq_frequency_table *init_vhint_table( point = &table[j++]; point->driver_data = edvd_val; - point->frequency = data->ref_clk_hz * ndiv / data->pdiv / - data->mdiv / 1000; + point->frequency = (cluster->ref_clk_khz * ndiv) / cluster->div; } table[j].frequency = CPUFREQ_TABLE_END; @@ -245,8 +255,7 @@ static int tegra186_cpufreq_probe(struct platform_device *pdev) struct tegra186_cpufreq_cluster *cluster = &data->clusters[i]; cluster->info = &tegra186_clusters[i]; - cluster->table = init_vhint_table( - pdev, bpmp, cluster->info->bpmp_cluster_id); + cluster->table = init_vhint_table(pdev, bpmp, cluster); if (IS_ERR(cluster->table)) { err = PTR_ERR(cluster->table); goto put_bpmp; diff --git a/drivers/cpuidle/cpuidle-tegra.c b/drivers/cpuidle/cpuidle-tegra.c index e8956706a291..191966dc8d02 100644 --- a/drivers/cpuidle/cpuidle-tegra.c +++ b/drivers/cpuidle/cpuidle-tegra.c @@ -189,7 +189,7 @@ static int tegra_cpuidle_state_enter(struct cpuidle_device *dev, } local_fiq_disable(); - tegra_pm_set_cpu_in_lp2(); + RCU_NONIDLE(tegra_pm_set_cpu_in_lp2()); cpu_pm_enter(); switch (index) { @@ -207,7 +207,7 @@ static int tegra_cpuidle_state_enter(struct cpuidle_device *dev, } cpu_pm_exit(); - tegra_pm_clear_cpu_in_lp2(); + RCU_NONIDLE(tegra_pm_clear_cpu_in_lp2()); local_fiq_enable(); return err ?: index; diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c index fa2f1b4fad7b..a94bf28f858a 100644 --- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c +++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c @@ -7,7 +7,7 @@ * * This file add support for MD5 and SHA1/SHA224/SHA256/SHA384/SHA512. * - * You could find the datasheet in Documentation/arm/sunxi/README + * You could find the datasheet in Documentation/arm/sunxi.rst */ #include <linux/dma-mapping.h> #include <linux/pm_runtime.h> diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-prng.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-prng.c index 78503006949c..cfde9ee4356b 100644 --- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-prng.c +++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-prng.c @@ -7,7 +7,7 @@ * * This file handle the PRNG * - * You could find a link for the datasheet in Documentation/arm/sunxi/README + * You could find a link for the datasheet in Documentation/arm/sunxi.rst */ #include "sun8i-ce.h" #include <linux/dma-mapping.h> diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-trng.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-trng.c index 654328160d19..5b7af4498bd5 100644 --- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-trng.c +++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-trng.c @@ -7,7 +7,7 @@ * * This file handle the TRNG * - * You could find a link for the datasheet in Documentation/arm/sunxi/README + * You could find a link for the datasheet in Documentation/arm/sunxi.rst */ #include "sun8i-ce.h" #include <linux/dma-mapping.h> diff --git a/drivers/dax/Kconfig b/drivers/dax/Kconfig index 567428e10b7b..d2834c2cfa10 100644 --- a/drivers/dax/Kconfig +++ b/drivers/dax/Kconfig @@ -50,7 +50,6 @@ config DEV_DAX_HMEM Say M if unsure. config DEV_DAX_HMEM_DEVICES - depends on NUMA_KEEP_MEMINFO # for phys_to_target_node() depends on DEV_DAX_HMEM && DAX=y def_bool y diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index 7974fa0400d8..962cbb5e5f7f 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -1039,16 +1039,15 @@ static int get_dma_id(struct dma_device *device) static int __dma_async_device_channel_register(struct dma_device *device, struct dma_chan *chan) { - int rc = 0; + int rc; chan->local = alloc_percpu(typeof(*chan->local)); if (!chan->local) - goto err_out; + return -ENOMEM; chan->dev = kzalloc(sizeof(*chan->dev), GFP_KERNEL); if (!chan->dev) { - free_percpu(chan->local); - chan->local = NULL; - goto err_out; + rc = -ENOMEM; + goto err_free_local; } /* @@ -1061,7 +1060,8 @@ static int __dma_async_device_channel_register(struct dma_device *device, if (chan->chan_id < 0) { pr_err("%s: unable to alloc ida for chan: %d\n", __func__, chan->chan_id); - goto err_out; + rc = chan->chan_id; + goto err_free_dev; } chan->dev->device.class = &dma_devclass; @@ -1082,9 +1082,10 @@ static int __dma_async_device_channel_register(struct dma_device *device, mutex_lock(&device->chan_mutex); ida_free(&device->chan_ida, chan->chan_id); mutex_unlock(&device->chan_mutex); - err_out: - free_percpu(chan->local); + err_free_dev: kfree(chan->dev); + err_free_local: + free_percpu(chan->local); return rc; } diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c index 200b9109cacf..663344987e3f 100644 --- a/drivers/dma/idxd/device.c +++ b/drivers/dma/idxd/device.c @@ -271,7 +271,7 @@ int idxd_wq_map_portal(struct idxd_wq *wq) resource_size_t start; start = pci_resource_start(pdev, IDXD_WQ_BAR); - start = start + wq->id * IDXD_PORTAL_SIZE; + start += idxd_get_wq_portal_full_offset(wq->id, IDXD_PORTAL_LIMITED); wq->dportal = devm_ioremap(dev, start, IDXD_PORTAL_SIZE); if (!wq->dportal) @@ -295,7 +295,7 @@ void idxd_wq_disable_cleanup(struct idxd_wq *wq) int i, wq_offset; lockdep_assert_held(&idxd->dev_lock); - memset(&wq->wqcfg, 0, sizeof(wq->wqcfg)); + memset(wq->wqcfg, 0, idxd->wqcfg_size); wq->type = IDXD_WQT_NONE; wq->size = 0; wq->group = NULL; @@ -304,8 +304,8 @@ void idxd_wq_disable_cleanup(struct idxd_wq *wq) clear_bit(WQ_FLAG_DEDICATED, &wq->flags); memset(wq->name, 0, WQ_NAME_SIZE); - for (i = 0; i < 8; i++) { - wq_offset = idxd->wqcfg_offset + wq->id * 32 + i * sizeof(u32); + for (i = 0; i < WQCFG_STRIDES(idxd); i++) { + wq_offset = WQCFG_OFFSET(idxd, wq->id, i); iowrite32(0, idxd->reg_base + wq_offset); dev_dbg(dev, "WQ[%d][%d][%#x]: %#x\n", wq->id, i, wq_offset, @@ -539,10 +539,10 @@ static int idxd_wq_config_write(struct idxd_wq *wq) if (!wq->group) return 0; - memset(&wq->wqcfg, 0, sizeof(union wqcfg)); + memset(wq->wqcfg, 0, idxd->wqcfg_size); /* byte 0-3 */ - wq->wqcfg.wq_size = wq->size; + wq->wqcfg->wq_size = wq->size; if (wq->size == 0) { dev_warn(dev, "Incorrect work queue size: 0\n"); @@ -550,22 +550,21 @@ static int idxd_wq_config_write(struct idxd_wq *wq) } /* bytes 4-7 */ - wq->wqcfg.wq_thresh = wq->threshold; + wq->wqcfg->wq_thresh = wq->threshold; /* byte 8-11 */ - wq->wqcfg.priv = !!(wq->type == IDXD_WQT_KERNEL); - wq->wqcfg.mode = 1; - - wq->wqcfg.priority = wq->priority; + wq->wqcfg->priv = !!(wq->type == IDXD_WQT_KERNEL); + wq->wqcfg->mode = 1; + wq->wqcfg->priority = wq->priority; /* bytes 12-15 */ - wq->wqcfg.max_xfer_shift = ilog2(wq->max_xfer_bytes); - wq->wqcfg.max_batch_shift = ilog2(wq->max_batch_size); + wq->wqcfg->max_xfer_shift = ilog2(wq->max_xfer_bytes); + wq->wqcfg->max_batch_shift = ilog2(wq->max_batch_size); dev_dbg(dev, "WQ %d CFGs\n", wq->id); - for (i = 0; i < 8; i++) { - wq_offset = idxd->wqcfg_offset + wq->id * 32 + i * sizeof(u32); - iowrite32(wq->wqcfg.bits[i], idxd->reg_base + wq_offset); + for (i = 0; i < WQCFG_STRIDES(idxd); i++) { + wq_offset = WQCFG_OFFSET(idxd, wq->id, i); + iowrite32(wq->wqcfg->bits[i], idxd->reg_base + wq_offset); dev_dbg(dev, "WQ[%d][%d][%#x]: %#x\n", wq->id, i, wq_offset, ioread32(idxd->reg_base + wq_offset)); diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h index c64df197e724..d48f193daacc 100644 --- a/drivers/dma/idxd/idxd.h +++ b/drivers/dma/idxd/idxd.h @@ -103,7 +103,7 @@ struct idxd_wq { u32 priority; enum idxd_wq_state state; unsigned long flags; - union wqcfg wqcfg; + union wqcfg *wqcfg; u32 vec_ptr; /* interrupt steering */ struct dsa_hw_desc **hw_descs; int num_descs; @@ -183,6 +183,7 @@ struct idxd_device { int max_wq_size; int token_limit; int nr_tokens; /* non-reserved tokens */ + unsigned int wqcfg_size; union sw_err_reg sw_err; wait_queue_head_t cmd_waitq; diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index 11e5ce168177..0a4432b063b5 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -178,6 +178,9 @@ static int idxd_setup_internals(struct idxd_device *idxd) wq->idxd_cdev.minor = -1; wq->max_xfer_bytes = idxd->max_xfer_bytes; wq->max_batch_size = idxd->max_batch_size; + wq->wqcfg = devm_kzalloc(dev, idxd->wqcfg_size, GFP_KERNEL); + if (!wq->wqcfg) + return -ENOMEM; } for (i = 0; i < idxd->max_engines; i++) { @@ -251,6 +254,8 @@ static void idxd_read_caps(struct idxd_device *idxd) dev_dbg(dev, "total workqueue size: %u\n", idxd->max_wq_size); idxd->max_wqs = idxd->hw.wq_cap.num_wqs; dev_dbg(dev, "max workqueues: %u\n", idxd->max_wqs); + idxd->wqcfg_size = 1 << (idxd->hw.wq_cap.wqcfg_size + IDXD_WQCFG_MIN); + dev_dbg(dev, "wqcfg size: %u\n", idxd->wqcfg_size); /* reading operation capabilities */ for (i = 0; i < 4; i++) { diff --git a/drivers/dma/idxd/registers.h b/drivers/dma/idxd/registers.h index a39e7ae6b3d9..54390334c243 100644 --- a/drivers/dma/idxd/registers.h +++ b/drivers/dma/idxd/registers.h @@ -8,7 +8,7 @@ #define IDXD_MMIO_BAR 0 #define IDXD_WQ_BAR 2 -#define IDXD_PORTAL_SIZE 0x4000 +#define IDXD_PORTAL_SIZE PAGE_SIZE /* MMIO Device BAR0 Registers */ #define IDXD_VER_OFFSET 0x00 @@ -43,7 +43,8 @@ union wq_cap_reg { struct { u64 total_wq_size:16; u64 num_wqs:8; - u64 rsvd:24; + u64 wqcfg_size:4; + u64 rsvd:20; u64 shared_mode:1; u64 dedicated_mode:1; u64 rsvd2:1; @@ -55,6 +56,7 @@ union wq_cap_reg { u64 bits; } __packed; #define IDXD_WQCAP_OFFSET 0x20 +#define IDXD_WQCFG_MIN 5 union group_cap_reg { struct { @@ -333,4 +335,23 @@ union wqcfg { }; u32 bits[8]; } __packed; + +/* + * This macro calculates the offset into the WQCFG register + * idxd - struct idxd * + * n - wq id + * ofs - the index of the 32b dword for the config register + * + * The WQCFG register block is divided into groups per each wq. The n index + * allows us to move to the register group that's for that particular wq. + * Each register is 32bits. The ofs gives us the number of register to access. + */ +#define WQCFG_OFFSET(_idxd_dev, n, ofs) \ +({\ + typeof(_idxd_dev) __idxd_dev = (_idxd_dev); \ + (__idxd_dev)->wqcfg_offset + (n) * (__idxd_dev)->wqcfg_size + sizeof(u32) * (ofs); \ +}) + +#define WQCFG_STRIDES(_idxd_dev) ((_idxd_dev)->wqcfg_size / sizeof(u32)) + #endif diff --git a/drivers/dma/idxd/submit.c b/drivers/dma/idxd/submit.c index 156a1ee233aa..417048e3c42a 100644 --- a/drivers/dma/idxd/submit.c +++ b/drivers/dma/idxd/submit.c @@ -74,7 +74,7 @@ int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc) if (idxd->state != IDXD_DEV_ENABLED) return -EIO; - portal = wq->dportal + idxd_get_wq_portal_offset(IDXD_PORTAL_UNLIMITED); + portal = wq->dportal; /* * The wmb() flushes writes to coherent DMA data before possibly * triggering a DMA read. The wmb() is necessary even on UP because diff --git a/drivers/dma/ioat/dca.c b/drivers/dma/ioat/dca.c index 0be385587c4c..289c59ed74b9 100644 --- a/drivers/dma/ioat/dca.c +++ b/drivers/dma/ioat/dca.c @@ -40,16 +40,6 @@ #define DCA2_TAG_MAP_BYTE3 0x82 #define DCA2_TAG_MAP_BYTE4 0x82 -/* verify if tag map matches expected values */ -static inline int dca2_tag_map_valid(u8 *tag_map) -{ - return ((tag_map[0] == DCA2_TAG_MAP_BYTE0) && - (tag_map[1] == DCA2_TAG_MAP_BYTE1) && - (tag_map[2] == DCA2_TAG_MAP_BYTE2) && - (tag_map[3] == DCA2_TAG_MAP_BYTE3) && - (tag_map[4] == DCA2_TAG_MAP_BYTE4)); -} - /* * "Legacy" DCA systems do not implement the DCA register set in the * I/OAT device. Software needs direct support for their tag mappings. diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c index e9f0101d92fa..0f5c19370f6d 100644 --- a/drivers/dma/pl330.c +++ b/drivers/dma/pl330.c @@ -2799,7 +2799,7 @@ pl330_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dst, * If burst size is smaller than bus width then make sure we only * transfer one at a time to avoid a burst stradling an MFIFO entry. */ - if (desc->rqcfg.brst_size * 8 < pl330->pcfg.data_bus_width) + if (burst * 8 < pl330->pcfg.data_bus_width) desc->rqcfg.brst_len = 1; desc->bytes_requested = len; diff --git a/drivers/dma/ti/k3-udma-private.c b/drivers/dma/ti/k3-udma-private.c index aa24e554f7b4..8563a392f30b 100644 --- a/drivers/dma/ti/k3-udma-private.c +++ b/drivers/dma/ti/k3-udma-private.c @@ -83,7 +83,7 @@ EXPORT_SYMBOL(xudma_rflow_is_gp); #define XUDMA_GET_PUT_RESOURCE(res) \ struct udma_##res *xudma_##res##_get(struct udma_dev *ud, int id) \ { \ - return __udma_reserve_##res(ud, false, id); \ + return __udma_reserve_##res(ud, UDMA_TP_NORMAL, id); \ } \ EXPORT_SYMBOL(xudma_##res##_get); \ \ diff --git a/drivers/dma/ti/omap-dma.c b/drivers/dma/ti/omap-dma.c index c9fe5e3a6b55..268a08058714 100644 --- a/drivers/dma/ti/omap-dma.c +++ b/drivers/dma/ti/omap-dma.c @@ -1522,29 +1522,38 @@ static void omap_dma_free(struct omap_dmadev *od) } } +/* Currently used by omap2 & 3 to block deeper SoC idle states */ +static bool omap_dma_busy(struct omap_dmadev *od) +{ + struct omap_chan *c; + int lch = -1; + + while (1) { + lch = find_next_bit(od->lch_bitmap, od->lch_count, lch + 1); + if (lch >= od->lch_count) + break; + c = od->lch_map[lch]; + if (!c) + continue; + if (omap_dma_chan_read(c, CCR) & CCR_ENABLE) + return true; + } + + return false; +} + /* Currently only used for omap2. For omap1, also a check for lcd_dma is needed */ static int omap_dma_busy_notifier(struct notifier_block *nb, unsigned long cmd, void *v) { struct omap_dmadev *od; - struct omap_chan *c; - int lch = -1; od = container_of(nb, struct omap_dmadev, nb); switch (cmd) { case CPU_CLUSTER_PM_ENTER: - while (1) { - lch = find_next_bit(od->lch_bitmap, od->lch_count, - lch + 1); - if (lch >= od->lch_count) - break; - c = od->lch_map[lch]; - if (!c) - continue; - if (omap_dma_chan_read(c, CCR) & CCR_ENABLE) - return NOTIFY_BAD; - } + if (omap_dma_busy(od)) + return NOTIFY_BAD; break; case CPU_CLUSTER_PM_ENTER_FAILED: case CPU_CLUSTER_PM_EXIT: @@ -1595,6 +1604,8 @@ static int omap_dma_context_notifier(struct notifier_block *nb, switch (cmd) { case CPU_CLUSTER_PM_ENTER: + if (omap_dma_busy(od)) + return NOTIFY_BAD; omap_dma_context_save(od); break; case CPU_CLUSTER_PM_ENTER_FAILED: diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c index ecff35402860..22faea653ea8 100644 --- a/drivers/dma/xilinx/xilinx_dma.c +++ b/drivers/dma/xilinx/xilinx_dma.c @@ -517,8 +517,8 @@ struct xilinx_dma_device { #define to_dma_tx_descriptor(tx) \ container_of(tx, struct xilinx_dma_tx_descriptor, async_tx) #define xilinx_dma_poll_timeout(chan, reg, val, cond, delay_us, timeout_us) \ - readl_poll_timeout(chan->xdev->regs + chan->ctrl_offset + reg, val, \ - cond, delay_us, timeout_us) + readl_poll_timeout_atomic(chan->xdev->regs + chan->ctrl_offset + reg, \ + val, cond, delay_us, timeout_us) /* IO accessors */ static inline u32 dma_read(struct xilinx_dma_chan *chan, u32 reg) @@ -948,8 +948,10 @@ static u32 xilinx_dma_get_residue(struct xilinx_dma_chan *chan, { struct xilinx_cdma_tx_segment *cdma_seg; struct xilinx_axidma_tx_segment *axidma_seg; + struct xilinx_aximcdma_tx_segment *aximcdma_seg; struct xilinx_cdma_desc_hw *cdma_hw; struct xilinx_axidma_desc_hw *axidma_hw; + struct xilinx_aximcdma_desc_hw *aximcdma_hw; struct list_head *entry; u32 residue = 0; @@ -961,13 +963,23 @@ static u32 xilinx_dma_get_residue(struct xilinx_dma_chan *chan, cdma_hw = &cdma_seg->hw; residue += (cdma_hw->control - cdma_hw->status) & chan->xdev->max_buffer_len; - } else { + } else if (chan->xdev->dma_config->dmatype == + XDMA_TYPE_AXIDMA) { axidma_seg = list_entry(entry, struct xilinx_axidma_tx_segment, node); axidma_hw = &axidma_seg->hw; residue += (axidma_hw->control - axidma_hw->status) & chan->xdev->max_buffer_len; + } else { + aximcdma_seg = + list_entry(entry, + struct xilinx_aximcdma_tx_segment, + node); + aximcdma_hw = &aximcdma_seg->hw; + residue += + (aximcdma_hw->control - aximcdma_hw->status) & + chan->xdev->max_buffer_len; } } @@ -1135,7 +1147,7 @@ static int xilinx_dma_alloc_chan_resources(struct dma_chan *dchan) upper_32_bits(chan->seg_p + sizeof(*chan->seg_mv) * ((i + 1) % XILINX_DMA_NUM_DESCS)); chan->seg_mv[i].phys = chan->seg_p + - sizeof(*chan->seg_v) * i; + sizeof(*chan->seg_mv) * i; list_add_tail(&chan->seg_mv[i].node, &chan->free_seg_list); } @@ -1560,7 +1572,7 @@ static void xilinx_dma_start_transfer(struct xilinx_dma_chan *chan) static void xilinx_mcdma_start_transfer(struct xilinx_dma_chan *chan) { struct xilinx_dma_tx_descriptor *head_desc, *tail_desc; - struct xilinx_axidma_tx_segment *tail_segment; + struct xilinx_aximcdma_tx_segment *tail_segment; u32 reg; /* @@ -1582,7 +1594,7 @@ static void xilinx_mcdma_start_transfer(struct xilinx_dma_chan *chan) tail_desc = list_last_entry(&chan->pending_list, struct xilinx_dma_tx_descriptor, node); tail_segment = list_last_entry(&tail_desc->segments, - struct xilinx_axidma_tx_segment, node); + struct xilinx_aximcdma_tx_segment, node); reg = dma_ctrl_read(chan, XILINX_MCDMA_CHAN_CR_OFFSET(chan->tdest)); @@ -1864,6 +1876,7 @@ static void append_desc_queue(struct xilinx_dma_chan *chan, struct xilinx_vdma_tx_segment *tail_segment; struct xilinx_dma_tx_descriptor *tail_desc; struct xilinx_axidma_tx_segment *axidma_tail_segment; + struct xilinx_aximcdma_tx_segment *aximcdma_tail_segment; struct xilinx_cdma_tx_segment *cdma_tail_segment; if (list_empty(&chan->pending_list)) @@ -1885,11 +1898,17 @@ static void append_desc_queue(struct xilinx_dma_chan *chan, struct xilinx_cdma_tx_segment, node); cdma_tail_segment->hw.next_desc = (u32)desc->async_tx.phys; - } else { + } else if (chan->xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA) { axidma_tail_segment = list_last_entry(&tail_desc->segments, struct xilinx_axidma_tx_segment, node); axidma_tail_segment->hw.next_desc = (u32)desc->async_tx.phys; + } else { + aximcdma_tail_segment = + list_last_entry(&tail_desc->segments, + struct xilinx_aximcdma_tx_segment, + node); + aximcdma_tail_segment->hw.next_desc = (u32)desc->async_tx.phys; } /* @@ -2836,10 +2855,11 @@ static int xilinx_dma_chan_probe(struct xilinx_dma_device *xdev, chan->stop_transfer = xilinx_dma_stop_transfer; } - /* check if SG is enabled (only for AXIDMA and CDMA) */ + /* check if SG is enabled (only for AXIDMA, AXIMCDMA, and CDMA) */ if (xdev->dma_config->dmatype != XDMA_TYPE_VDMA) { - if (dma_ctrl_read(chan, XILINX_DMA_REG_DMASR) & - XILINX_DMA_DMASR_SG_MASK) + if (xdev->dma_config->dmatype == XDMA_TYPE_AXIMCDMA || + dma_ctrl_read(chan, XILINX_DMA_REG_DMASR) & + XILINX_DMA_DMASR_SG_MASK) chan->has_sg = true; dev_dbg(chan->dev, "ch %d: SG %s\n", chan->id, chan->has_sg ? "enabled" : "disabled"); diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c index 8d1ff2454e2e..efb8a66efc68 100644 --- a/drivers/firmware/xilinx/zynqmp.c +++ b/drivers/firmware/xilinx/zynqmp.c @@ -147,6 +147,9 @@ static int zynqmp_pm_feature(u32 api_id) return 0; /* Return value if feature is already checked */ + if (api_id > ARRAY_SIZE(zynqmp_pm_features)) + return PM_FEATURE_INVALID; + if (zynqmp_pm_features[api_id] != PM_FEATURE_UNCHECKED) return zynqmp_pm_features[api_id]; diff --git a/drivers/gpio/gpio-aspeed.c b/drivers/gpio/gpio-aspeed.c index e44d5de2a120..b966f5e28ebf 100644 --- a/drivers/gpio/gpio-aspeed.c +++ b/drivers/gpio/gpio-aspeed.c @@ -1114,6 +1114,7 @@ static const struct aspeed_gpio_config ast2500_config = static const struct aspeed_bank_props ast2600_bank_props[] = { /* input output */ + {4, 0xffffffff, 0x00ffffff}, /* Q/R/S/T */ {5, 0xffffffff, 0xffffff00}, /* U/V/W/X */ {6, 0x0000ffff, 0x0000ffff}, /* Y/Z */ { }, diff --git a/drivers/gpio/gpio-dwapb.c b/drivers/gpio/gpio-dwapb.c index a5b326754124..2a9046c0fb16 100644 --- a/drivers/gpio/gpio-dwapb.c +++ b/drivers/gpio/gpio-dwapb.c @@ -343,8 +343,8 @@ static int dwapb_irq_set_type(struct irq_data *d, u32 type) #ifdef CONFIG_PM_SLEEP static int dwapb_irq_set_wake(struct irq_data *d, unsigned int enable) { - struct irq_chip_generic *igc = irq_data_get_irq_chip_data(d); - struct dwapb_gpio *gpio = igc->private; + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct dwapb_gpio *gpio = to_dwapb_gpio(gc); struct dwapb_context *ctx = gpio->ports[0].ctx; irq_hw_number_t bit = irqd_to_hwirq(d); diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c index 6d59e3a43761..f7ceb2b11afc 100644 --- a/drivers/gpio/gpio-omap.c +++ b/drivers/gpio/gpio-omap.c @@ -1114,13 +1114,23 @@ static void omap_gpio_idle(struct gpio_bank *bank, bool may_lose_context) { struct device *dev = bank->chip.parent; void __iomem *base = bank->base; - u32 nowake; + u32 mask, nowake; bank->saved_datain = readl_relaxed(base + bank->regs->datain); if (!bank->enabled_non_wakeup_gpios) goto update_gpio_context_count; + /* Check for pending EDGE_FALLING, ignore EDGE_BOTH */ + mask = bank->enabled_non_wakeup_gpios & bank->context.fallingdetect; + mask &= ~bank->context.risingdetect; + bank->saved_datain |= mask; + + /* Check for pending EDGE_RISING, ignore EDGE_BOTH */ + mask = bank->enabled_non_wakeup_gpios & bank->context.risingdetect; + mask &= ~bank->context.fallingdetect; + bank->saved_datain &= ~mask; + if (!may_lose_context) goto update_gpio_context_count; diff --git a/drivers/gpio/gpio-pcie-idio-24.c b/drivers/gpio/gpio-pcie-idio-24.c index a68941d19ac6..2a07fd96707e 100644 --- a/drivers/gpio/gpio-pcie-idio-24.c +++ b/drivers/gpio/gpio-pcie-idio-24.c @@ -28,6 +28,47 @@ #include <linux/spinlock.h> #include <linux/types.h> +/* + * PLX PEX8311 PCI LCS_INTCSR Interrupt Control/Status + * + * Bit: Description + * 0: Enable Interrupt Sources (Bit 0) + * 1: Enable Interrupt Sources (Bit 1) + * 2: Generate Internal PCI Bus Internal SERR# Interrupt + * 3: Mailbox Interrupt Enable + * 4: Power Management Interrupt Enable + * 5: Power Management Interrupt + * 6: Slave Read Local Data Parity Check Error Enable + * 7: Slave Read Local Data Parity Check Error Status + * 8: Internal PCI Wire Interrupt Enable + * 9: PCI Express Doorbell Interrupt Enable + * 10: PCI Abort Interrupt Enable + * 11: Local Interrupt Input Enable + * 12: Retry Abort Enable + * 13: PCI Express Doorbell Interrupt Active + * 14: PCI Abort Interrupt Active + * 15: Local Interrupt Input Active + * 16: Local Interrupt Output Enable + * 17: Local Doorbell Interrupt Enable + * 18: DMA Channel 0 Interrupt Enable + * 19: DMA Channel 1 Interrupt Enable + * 20: Local Doorbell Interrupt Active + * 21: DMA Channel 0 Interrupt Active + * 22: DMA Channel 1 Interrupt Active + * 23: Built-In Self-Test (BIST) Interrupt Active + * 24: Direct Master was the Bus Master during a Master or Target Abort + * 25: DMA Channel 0 was the Bus Master during a Master or Target Abort + * 26: DMA Channel 1 was the Bus Master during a Master or Target Abort + * 27: Target Abort after internal 256 consecutive Master Retrys + * 28: PCI Bus wrote data to LCS_MBOX0 + * 29: PCI Bus wrote data to LCS_MBOX1 + * 30: PCI Bus wrote data to LCS_MBOX2 + * 31: PCI Bus wrote data to LCS_MBOX3 + */ +#define PLX_PEX8311_PCI_LCS_INTCSR 0x68 +#define INTCSR_INTERNAL_PCI_WIRE BIT(8) +#define INTCSR_LOCAL_INPUT BIT(11) + /** * struct idio_24_gpio_reg - GPIO device registers structure * @out0_7: Read: FET Outputs 0-7 @@ -92,6 +133,7 @@ struct idio_24_gpio_reg { struct idio_24_gpio { struct gpio_chip chip; raw_spinlock_t lock; + __u8 __iomem *plx; struct idio_24_gpio_reg __iomem *reg; unsigned long irq_mask; }; @@ -334,13 +376,13 @@ static void idio_24_irq_mask(struct irq_data *data) unsigned long flags; const unsigned long bit_offset = irqd_to_hwirq(data) - 24; unsigned char new_irq_mask; - const unsigned long bank_offset = bit_offset/8 * 8; + const unsigned long bank_offset = bit_offset / 8; unsigned char cos_enable_state; raw_spin_lock_irqsave(&idio24gpio->lock, flags); - idio24gpio->irq_mask &= BIT(bit_offset); - new_irq_mask = idio24gpio->irq_mask >> bank_offset; + idio24gpio->irq_mask &= ~BIT(bit_offset); + new_irq_mask = idio24gpio->irq_mask >> bank_offset * 8; if (!new_irq_mask) { cos_enable_state = ioread8(&idio24gpio->reg->cos_enable); @@ -363,12 +405,12 @@ static void idio_24_irq_unmask(struct irq_data *data) unsigned long flags; unsigned char prev_irq_mask; const unsigned long bit_offset = irqd_to_hwirq(data) - 24; - const unsigned long bank_offset = bit_offset/8 * 8; + const unsigned long bank_offset = bit_offset / 8; unsigned char cos_enable_state; raw_spin_lock_irqsave(&idio24gpio->lock, flags); - prev_irq_mask = idio24gpio->irq_mask >> bank_offset; + prev_irq_mask = idio24gpio->irq_mask >> bank_offset * 8; idio24gpio->irq_mask |= BIT(bit_offset); if (!prev_irq_mask) { @@ -455,6 +497,7 @@ static int idio_24_probe(struct pci_dev *pdev, const struct pci_device_id *id) struct device *const dev = &pdev->dev; struct idio_24_gpio *idio24gpio; int err; + const size_t pci_plx_bar_index = 1; const size_t pci_bar_index = 2; const char *const name = pci_name(pdev); struct gpio_irq_chip *girq; @@ -469,12 +512,13 @@ static int idio_24_probe(struct pci_dev *pdev, const struct pci_device_id *id) return err; } - err = pcim_iomap_regions(pdev, BIT(pci_bar_index), name); + err = pcim_iomap_regions(pdev, BIT(pci_plx_bar_index) | BIT(pci_bar_index), name); if (err) { dev_err(dev, "Unable to map PCI I/O addresses (%d)\n", err); return err; } + idio24gpio->plx = pcim_iomap_table(pdev)[pci_plx_bar_index]; idio24gpio->reg = pcim_iomap_table(pdev)[pci_bar_index]; idio24gpio->chip.label = name; @@ -504,6 +548,12 @@ static int idio_24_probe(struct pci_dev *pdev, const struct pci_device_id *id) /* Software board reset */ iowrite8(0, &idio24gpio->reg->soft_reset); + /* + * enable PLX PEX8311 internal PCI wire interrupt and local interrupt + * input + */ + iowrite8((INTCSR_INTERNAL_PCI_WIRE | INTCSR_LOCAL_INPUT) >> 8, + idio24gpio->plx + PLX_PEX8311_PCI_LCS_INTCSR + 1); err = devm_gpiochip_add_data(dev, &idio24gpio->chip, idio24gpio); if (err) { diff --git a/drivers/gpio/gpio-sifive.c b/drivers/gpio/gpio-sifive.c index c54dd08f2cbf..d5eb9ca11901 100644 --- a/drivers/gpio/gpio-sifive.c +++ b/drivers/gpio/gpio-sifive.c @@ -183,7 +183,7 @@ static int sifive_gpio_probe(struct platform_device *pdev) return PTR_ERR(chip->regs); ngpio = of_irq_count(node); - if (ngpio >= SIFIVE_GPIO_MAX) { + if (ngpio > SIFIVE_GPIO_MAX) { dev_err(dev, "Too many GPIO interrupts (max=%d)\n", SIFIVE_GPIO_MAX); return -ENXIO; diff --git a/drivers/gpio/gpiolib-cdev.h b/drivers/gpio/gpiolib-cdev.h index cb41dd757338..b42644cbffb8 100644 --- a/drivers/gpio/gpiolib-cdev.h +++ b/drivers/gpio/gpiolib-cdev.h @@ -7,22 +7,7 @@ struct gpio_device; -#ifdef CONFIG_GPIO_CDEV - int gpiolib_cdev_register(struct gpio_device *gdev, dev_t devt); void gpiolib_cdev_unregister(struct gpio_device *gdev); -#else - -static inline int gpiolib_cdev_register(struct gpio_device *gdev, dev_t devt) -{ - return 0; -} - -static inline void gpiolib_cdev_unregister(struct gpio_device *gdev) -{ -} - -#endif /* CONFIG_GPIO_CDEV */ - #endif /* GPIOLIB_CDEV_H */ diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 3cdf9effc13a..089ddcaa9bc6 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -480,11 +480,23 @@ static void gpiodevice_release(struct device *dev) kfree(gdev); } +#ifdef CONFIG_GPIO_CDEV +#define gcdev_register(gdev, devt) gpiolib_cdev_register((gdev), (devt)) +#define gcdev_unregister(gdev) gpiolib_cdev_unregister((gdev)) +#else +/* + * gpiolib_cdev_register() indirectly calls device_add(), which is still + * required even when cdev is not selected. + */ +#define gcdev_register(gdev, devt) device_add(&(gdev)->dev) +#define gcdev_unregister(gdev) device_del(&(gdev)->dev) +#endif + static int gpiochip_setup_dev(struct gpio_device *gdev) { int ret; - ret = gpiolib_cdev_register(gdev, gpio_devt); + ret = gcdev_register(gdev, gpio_devt); if (ret) return ret; @@ -500,7 +512,7 @@ static int gpiochip_setup_dev(struct gpio_device *gdev) return 0; err_remove_device: - gpiolib_cdev_unregister(gdev); + gcdev_unregister(gdev); return ret; } @@ -825,7 +837,7 @@ void gpiochip_remove(struct gpio_chip *gc) * be removed, else it will be dangling until the last user is * gone. */ - gpiolib_cdev_unregister(gdev); + gcdev_unregister(gdev); put_device(&gdev->dev); } EXPORT_SYMBOL_GPL(gpiochip_remove); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 37da3537ba2e..026789b466db 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -80,6 +80,7 @@ MODULE_FIRMWARE("amdgpu/renoir_gpu_info.bin"); MODULE_FIRMWARE("amdgpu/navi10_gpu_info.bin"); MODULE_FIRMWARE("amdgpu/navi14_gpu_info.bin"); MODULE_FIRMWARE("amdgpu/navi12_gpu_info.bin"); +MODULE_FIRMWARE("amdgpu/green_sardine_gpu_info.bin"); #define AMDGPU_RESUME_MS 2000 @@ -239,9 +240,11 @@ bool amdgpu_device_supports_baco(struct drm_device *dev) return amdgpu_asic_supports_baco(adev); } +/* + * VRAM access helper functions + */ + /** - * VRAM access helper functions. - * * amdgpu_device_vram_access - read/write a buffer in vram * * @adev: amdgpu_device pointer @@ -705,7 +708,7 @@ void amdgpu_device_indirect_wreg64(struct amdgpu_device *adev, /** * amdgpu_invalid_rreg - dummy reg read function * - * @adev: amdgpu device pointer + * @adev: amdgpu_device pointer * @reg: offset of register * * Dummy register read function. Used for register blocks @@ -722,7 +725,7 @@ static uint32_t amdgpu_invalid_rreg(struct amdgpu_device *adev, uint32_t reg) /** * amdgpu_invalid_wreg - dummy reg write function * - * @adev: amdgpu device pointer + * @adev: amdgpu_device pointer * @reg: offset of register * @v: value to write to the register * @@ -739,7 +742,7 @@ static void amdgpu_invalid_wreg(struct amdgpu_device *adev, uint32_t reg, uint32 /** * amdgpu_invalid_rreg64 - dummy 64 bit reg read function * - * @adev: amdgpu device pointer + * @adev: amdgpu_device pointer * @reg: offset of register * * Dummy register read function. Used for register blocks @@ -756,7 +759,7 @@ static uint64_t amdgpu_invalid_rreg64(struct amdgpu_device *adev, uint32_t reg) /** * amdgpu_invalid_wreg64 - dummy reg write function * - * @adev: amdgpu device pointer + * @adev: amdgpu_device pointer * @reg: offset of register * @v: value to write to the register * @@ -773,7 +776,7 @@ static void amdgpu_invalid_wreg64(struct amdgpu_device *adev, uint32_t reg, uint /** * amdgpu_block_invalid_rreg - dummy reg read function * - * @adev: amdgpu device pointer + * @adev: amdgpu_device pointer * @block: offset of instance * @reg: offset of register * @@ -793,7 +796,7 @@ static uint32_t amdgpu_block_invalid_rreg(struct amdgpu_device *adev, /** * amdgpu_block_invalid_wreg - dummy reg write function * - * @adev: amdgpu device pointer + * @adev: amdgpu_device pointer * @block: offset of instance * @reg: offset of register * @v: value to write to the register @@ -813,7 +816,7 @@ static void amdgpu_block_invalid_wreg(struct amdgpu_device *adev, /** * amdgpu_device_asic_init - Wrapper for atom asic_init * - * @dev: drm_device pointer + * @adev: amdgpu_device pointer * * Does any asic specific work and then calls atom asic init. */ @@ -827,7 +830,7 @@ static int amdgpu_device_asic_init(struct amdgpu_device *adev) /** * amdgpu_device_vram_scratch_init - allocate the VRAM scratch page * - * @adev: amdgpu device pointer + * @adev: amdgpu_device pointer * * Allocates a scratch page of VRAM for use by various things in the * driver. @@ -844,7 +847,7 @@ static int amdgpu_device_vram_scratch_init(struct amdgpu_device *adev) /** * amdgpu_device_vram_scratch_fini - Free the VRAM scratch page * - * @adev: amdgpu device pointer + * @adev: amdgpu_device pointer * * Frees the VRAM scratch page. */ @@ -1803,7 +1806,10 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev) chip_name = "arcturus"; break; case CHIP_RENOIR: - chip_name = "renoir"; + if (adev->apu_flags & AMD_APU_IS_RENOIR) + chip_name = "renoir"; + else + chip_name = "green_sardine"; break; case CHIP_NAVI10: chip_name = "navi10"; @@ -3011,7 +3017,7 @@ bool amdgpu_device_asic_has_dc_support(enum amd_asic_type asic_type) /** * amdgpu_device_has_dc_support - check if dc is supported * - * @adev: amdgpu_device_pointer + * @adev: amdgpu_device pointer * * Returns true for supported, false for not supported */ @@ -4045,7 +4051,7 @@ static int amdgpu_device_recover_vram(struct amdgpu_device *adev) /** * amdgpu_device_reset_sriov - reset ASIC for SR-IOV vf * - * @adev: amdgpu device pointer + * @adev: amdgpu_device pointer * @from_hypervisor: request from hypervisor * * do VF FLR and reinitialize Asic @@ -4100,7 +4106,7 @@ error: /** * amdgpu_device_has_job_running - check if there is any job in mirror list * - * @adev: amdgpu device pointer + * @adev: amdgpu_device pointer * * check if there is any job in mirror list */ @@ -4128,7 +4134,7 @@ bool amdgpu_device_has_job_running(struct amdgpu_device *adev) /** * amdgpu_device_should_recover_gpu - check if we should try GPU recovery * - * @adev: amdgpu device pointer + * @adev: amdgpu_device pointer * * Check amdgpu_gpu_recovery and SRIOV status to see if we should try to recover * a hung GPU. @@ -4477,7 +4483,7 @@ static int amdgpu_device_suspend_display_audio(struct amdgpu_device *adev) /** * amdgpu_device_gpu_recover - reset the asic and recover scheduler * - * @adev: amdgpu device pointer + * @adev: amdgpu_device pointer * @job: which job trigger hang * * Attempt to reset the GPU if it has hung (all asics). @@ -4497,7 +4503,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, bool need_emergency_restart = false; bool audio_suspended = false; - /** + /* * Special case: RAS triggered and full reset isn't supported */ need_emergency_restart = amdgpu_ras_need_emergency_restart(adev); @@ -4846,7 +4852,7 @@ int amdgpu_device_baco_enter(struct drm_device *dev) if (!amdgpu_device_supports_baco(adev_to_drm(adev))) return -ENOTSUPP; - if (ras && ras->supported) + if (ras && ras->supported && adev->nbio.funcs->enable_doorbell_interrupt) adev->nbio.funcs->enable_doorbell_interrupt(adev, false); return amdgpu_dpm_baco_enter(adev); @@ -4865,7 +4871,7 @@ int amdgpu_device_baco_exit(struct drm_device *dev) if (ret) return ret; - if (ras && ras->supported) + if (ras && ras->supported && adev->nbio.funcs->enable_doorbell_interrupt) adev->nbio.funcs->enable_doorbell_interrupt(adev, true); return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 42d9748921f5..8e988f07f085 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -1055,10 +1055,10 @@ static const struct pci_device_id pciidlist[] = { {0x1002, 0x15dd, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RAVEN|AMD_IS_APU}, {0x1002, 0x15d8, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RAVEN|AMD_IS_APU}, /* Arcturus */ - {0x1002, 0x738C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS|AMD_EXP_HW_SUPPORT}, - {0x1002, 0x7388, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS|AMD_EXP_HW_SUPPORT}, - {0x1002, 0x738E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS|AMD_EXP_HW_SUPPORT}, - {0x1002, 0x7390, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS|AMD_EXP_HW_SUPPORT}, + {0x1002, 0x738C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS}, + {0x1002, 0x7388, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS}, + {0x1002, 0x738E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS}, + {0x1002, 0x7390, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS}, /* Navi10 */ {0x1002, 0x7310, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10}, {0x1002, 0x7312, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10}, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c index f203e4a6a3f2..731f3aa2e6ba 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c @@ -81,8 +81,8 @@ static const struct ttm_resource_manager_func amdgpu_gtt_mgr_func; /** * amdgpu_gtt_mgr_init - init GTT manager and DRM MM * - * @man: TTM memory type manager - * @p_size: maximum size of GTT + * @adev: amdgpu_device pointer + * @gtt_size: maximum size of GTT * * Allocate and initialize the GTT manager. */ @@ -123,7 +123,7 @@ int amdgpu_gtt_mgr_init(struct amdgpu_device *adev, uint64_t gtt_size) /** * amdgpu_gtt_mgr_fini - free and destroy GTT manager * - * @man: TTM memory type manager + * @adev: amdgpu_device pointer * * Destroy and free the GTT manager, returns -EBUSY if ranges are still * allocated inside it. diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 96a9699f87ba..a6dbe4b83533 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -2524,6 +2524,7 @@ int parse_ta_bin_descriptor(struct psp_context *psp, psp->asd_feature_version = le32_to_cpu(desc->fw_version); psp->asd_ucode_size = le32_to_cpu(desc->size_bytes); psp->asd_start_addr = ucode_start_addr; + psp->asd_fw = psp->ta_fw; break; case TA_FW_TYPE_PSP_XGMI: psp->ta_xgmi_ucode_version = le32_to_cpu(desc->fw_version); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 8039d2399584..a0248d78190f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -69,10 +69,10 @@ static int amdgpu_ttm_backend_bind(struct ttm_bo_device *bdev, static int amdgpu_ttm_init_on_chip(struct amdgpu_device *adev, unsigned int type, - uint64_t size) + uint64_t size_in_page) { return ttm_range_man_init(&adev->mman.bdev, type, - false, size >> PAGE_SHIFT); + false, size_in_page); } /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h index 5eb63288d157..edbb8194ee81 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h @@ -67,6 +67,7 @@ struct amdgpu_uvd { unsigned harvest_config; /* store image width to adjust nb memory state */ unsigned decode_image_width; + uint32_t keyselect; }; int amdgpu_uvd_sw_init(struct amdgpu_device *adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c index f3b7287e84c4..a563328e3dae 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c @@ -39,6 +39,7 @@ #define FIRMWARE_RAVEN2 "amdgpu/raven2_vcn.bin" #define FIRMWARE_ARCTURUS "amdgpu/arcturus_vcn.bin" #define FIRMWARE_RENOIR "amdgpu/renoir_vcn.bin" +#define FIRMWARE_GREEN_SARDINE "amdgpu/green_sardine_vcn.bin" #define FIRMWARE_NAVI10 "amdgpu/navi10_vcn.bin" #define FIRMWARE_NAVI14 "amdgpu/navi14_vcn.bin" #define FIRMWARE_NAVI12 "amdgpu/navi12_vcn.bin" @@ -50,6 +51,7 @@ MODULE_FIRMWARE(FIRMWARE_PICASSO); MODULE_FIRMWARE(FIRMWARE_RAVEN2); MODULE_FIRMWARE(FIRMWARE_ARCTURUS); MODULE_FIRMWARE(FIRMWARE_RENOIR); +MODULE_FIRMWARE(FIRMWARE_GREEN_SARDINE); MODULE_FIRMWARE(FIRMWARE_NAVI10); MODULE_FIRMWARE(FIRMWARE_NAVI14); MODULE_FIRMWARE(FIRMWARE_NAVI12); @@ -89,7 +91,11 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev) adev->vcn.indirect_sram = true; break; case CHIP_RENOIR: - fw_name = FIRMWARE_RENOIR; + if (adev->apu_flags & AMD_APU_IS_RENOIR) + fw_name = FIRMWARE_RENOIR; + else + fw_name = FIRMWARE_GREEN_SARDINE; + if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) && (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)) adev->vcn.indirect_sram = true; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c index 01c1171afbe0..0c6b7c5ecfec 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c @@ -168,8 +168,7 @@ static const struct ttm_resource_manager_func amdgpu_vram_mgr_func; /** * amdgpu_vram_mgr_init - init VRAM manager and DRM MM * - * @man: TTM memory type manager - * @p_size: maximum size of VRAM + * @adev: amdgpu_device pointer * * Allocate and initialize the VRAM manager. */ @@ -199,7 +198,7 @@ int amdgpu_vram_mgr_init(struct amdgpu_device *adev) /** * amdgpu_vram_mgr_fini - free and destroy VRAM manager * - * @man: TTM memory type manager + * @adev: amdgpu_device pointer * * Destroy and free the VRAM manager, returns -EBUSY if ranges are still * allocated inside it. @@ -229,7 +228,7 @@ void amdgpu_vram_mgr_fini(struct amdgpu_device *adev) /** * amdgpu_vram_mgr_vis_size - Calculate visible node size * - * @adev: amdgpu device structure + * @adev: amdgpu_device pointer * @node: MM node structure * * Calculate how many bytes of the MM node are inside visible VRAM diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c index 03ff8bd1fee8..5442df094102 100644 --- a/drivers/gpu/drm/amd/amdgpu/cik.c +++ b/drivers/gpu/drm/amd/amdgpu/cik.c @@ -1336,11 +1336,13 @@ cik_asic_reset_method(struct amdgpu_device *adev) switch (adev->asic_type) { case CHIP_BONAIRE: - case CHIP_HAWAII: /* disable baco reset until it works */ /* smu7_asic_get_baco_capability(adev, &baco_reset); */ baco_reset = false; break; + case CHIP_HAWAII: + baco_reset = cik_asic_supports_baco(adev); + break; default: baco_reset = false; break; diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c index 20f108818b2b..a3c3fe96515f 100644 --- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c @@ -1071,22 +1071,19 @@ static int cik_sdma_soft_reset(void *handle) { u32 srbm_soft_reset = 0; struct amdgpu_device *adev = (struct amdgpu_device *)handle; - u32 tmp = RREG32(mmSRBM_STATUS2); + u32 tmp; - if (tmp & SRBM_STATUS2__SDMA_BUSY_MASK) { - /* sdma0 */ - tmp = RREG32(mmSDMA0_F32_CNTL + SDMA0_REGISTER_OFFSET); - tmp |= SDMA0_F32_CNTL__HALT_MASK; - WREG32(mmSDMA0_F32_CNTL + SDMA0_REGISTER_OFFSET, tmp); - srbm_soft_reset |= SRBM_SOFT_RESET__SOFT_RESET_SDMA_MASK; - } - if (tmp & SRBM_STATUS2__SDMA1_BUSY_MASK) { - /* sdma1 */ - tmp = RREG32(mmSDMA0_F32_CNTL + SDMA1_REGISTER_OFFSET); - tmp |= SDMA0_F32_CNTL__HALT_MASK; - WREG32(mmSDMA0_F32_CNTL + SDMA1_REGISTER_OFFSET, tmp); - srbm_soft_reset |= SRBM_SOFT_RESET__SOFT_RESET_SDMA1_MASK; - } + /* sdma0 */ + tmp = RREG32(mmSDMA0_F32_CNTL + SDMA0_REGISTER_OFFSET); + tmp |= SDMA0_F32_CNTL__HALT_MASK; + WREG32(mmSDMA0_F32_CNTL + SDMA0_REGISTER_OFFSET, tmp); + srbm_soft_reset |= SRBM_SOFT_RESET__SOFT_RESET_SDMA_MASK; + + /* sdma1 */ + tmp = RREG32(mmSDMA0_F32_CNTL + SDMA1_REGISTER_OFFSET); + tmp |= SDMA0_F32_CNTL__HALT_MASK; + WREG32(mmSDMA0_F32_CNTL + SDMA1_REGISTER_OFFSET, tmp); + srbm_soft_reset |= SRBM_SOFT_RESET__SOFT_RESET_SDMA1_MASK; if (srbm_soft_reset) { tmp = RREG32(mmSRBM_SOFT_RESET); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 56fdbe626d30..55f4b8c3b933 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -128,6 +128,9 @@ #define PA_SC_ENHANCE_3__FORCE_PBB_WORKLOAD_MODE_TO_ZERO__SHIFT 0x3 #define PA_SC_ENHANCE_3__FORCE_PBB_WORKLOAD_MODE_TO_ZERO_MASK 0x00000008L +#define mmCGTT_SPI_CS_CLK_CTRL 0x507c +#define mmCGTT_SPI_CS_CLK_CTRL_BASE_IDX 1 + MODULE_FIRMWARE("amdgpu/navi10_ce.bin"); MODULE_FIRMWARE("amdgpu/navi10_pfp.bin"); MODULE_FIRMWARE("amdgpu/navi10_me.bin"); @@ -3094,6 +3097,7 @@ static const struct soc15_reg_golden golden_settings_gc_rlc_spm_10_1_2_nv12[] = static const struct soc15_reg_golden golden_settings_gc_10_3[] = { + SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CS_CLK_CTRL, 0x78000000, 0x78000100), SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_PS_CLK_CTRL, 0xff7f0fff, 0x78000100), SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_RA0_CLK_CTRL, 0xff7f0fff, 0x30000100), SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_RA1_CLK_CTRL, 0xff7f0fff, 0x7e000100), @@ -3101,6 +3105,8 @@ static const struct soc15_reg_golden golden_settings_gc_10_3[] = SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0xffffffff, 0x00000280), SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x00800000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_EXCEPTION_CONTROL, 0x7fff0f1f, 0x00b80000), + SOC15_REG_GOLDEN_VALUE(GC, 0 ,mmGCEA_SDP_TAG_RESERVE0, 0xffffffff, 0x10100100), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCEA_SDP_TAG_RESERVE1, 0xffffffff, 0x17000088), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL_Sienna_Cichlid, 0x1ff1ffff, 0x00000500), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGE_PC_CNTL, 0x003fffff, 0x00280400), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2A_ADDR_MATCH_MASK, 0xffffffff, 0xffffffcf), diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 6959aebae6d4..0d8e203b10ef 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -117,6 +117,13 @@ MODULE_FIRMWARE("amdgpu/renoir_mec.bin"); MODULE_FIRMWARE("amdgpu/renoir_mec2.bin"); MODULE_FIRMWARE("amdgpu/renoir_rlc.bin"); +MODULE_FIRMWARE("amdgpu/green_sardine_ce.bin"); +MODULE_FIRMWARE("amdgpu/green_sardine_pfp.bin"); +MODULE_FIRMWARE("amdgpu/green_sardine_me.bin"); +MODULE_FIRMWARE("amdgpu/green_sardine_mec.bin"); +MODULE_FIRMWARE("amdgpu/green_sardine_mec2.bin"); +MODULE_FIRMWARE("amdgpu/green_sardine_rlc.bin"); + #define mmTCP_CHAN_STEER_0_ARCT 0x0b03 #define mmTCP_CHAN_STEER_0_ARCT_BASE_IDX 0 #define mmTCP_CHAN_STEER_1_ARCT 0x0b04 @@ -1630,7 +1637,10 @@ static int gfx_v9_0_init_microcode(struct amdgpu_device *adev) chip_name = "arcturus"; break; case CHIP_RENOIR: - chip_name = "renoir"; + if (adev->apu_flags & AMD_APU_IS_RENOIR) + chip_name = "renoir"; + else + chip_name = "green_sardine"; break; default: BUG(); diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c index 03462c857498..8eeba8096493 100644 --- a/drivers/gpu/drm/amd/amdgpu/nv.c +++ b/drivers/gpu/drm/amd/amdgpu/nv.c @@ -455,10 +455,11 @@ void nv_set_virt_ops(struct amdgpu_device *adev) adev->virt.ops = &xgpu_nv_virt_ops; } -static bool nv_is_blockchain_sku(struct pci_dev *pdev) +static bool nv_is_headless_sku(struct pci_dev *pdev) { - if (pdev->device == 0x731E && - (pdev->revision == 0xC6 || pdev->revision == 0xC7)) + if ((pdev->device == 0x731E && + (pdev->revision == 0xC6 || pdev->revision == 0xC7)) || + (pdev->device == 0x7340 && pdev->revision == 0xC9)) return true; return false; } @@ -491,8 +492,7 @@ int nv_set_ip_blocks(struct amdgpu_device *adev) if (adev->enable_virtual_display || amdgpu_sriov_vf(adev)) amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block); #if defined(CONFIG_DRM_AMD_DC) - else if (amdgpu_device_has_dc_support(adev) && - !nv_is_blockchain_sku(adev->pdev)) + else if (amdgpu_device_has_dc_support(adev)) amdgpu_device_ip_block_add(adev, &dm_ip_block); #endif amdgpu_device_ip_block_add(adev, &gfx_v10_0_ip_block); @@ -500,7 +500,7 @@ int nv_set_ip_blocks(struct amdgpu_device *adev) if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT && !amdgpu_sriov_vf(adev)) amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block); - if (!nv_is_blockchain_sku(adev->pdev)) + if (!nv_is_headless_sku(adev->pdev)) amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block); amdgpu_device_ip_block_add(adev, &jpeg_v2_0_ip_block); if (adev->enable_mes) diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c index 75489313dbad..c4828bd3264b 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c @@ -39,6 +39,8 @@ MODULE_FIRMWARE("amdgpu/renoir_asd.bin"); MODULE_FIRMWARE("amdgpu/renoir_ta.bin"); +MODULE_FIRMWARE("amdgpu/green_sardine_asd.bin"); +MODULE_FIRMWARE("amdgpu/green_sardine_ta.bin"); /* address block */ #define smnMP1_FIRMWARE_FLAGS 0x3010024 @@ -54,7 +56,10 @@ static int psp_v12_0_init_microcode(struct psp_context *psp) switch (adev->asic_type) { case CHIP_RENOIR: - chip_name = "renoir"; + if (adev->apu_flags & AMD_APU_IS_RENOIR) + chip_name = "renoir"; + else + chip_name = "green_sardine"; break; default: BUG(); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index 86fb1eddf5a6..e82f49f62f6e 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -69,6 +69,7 @@ MODULE_FIRMWARE("amdgpu/picasso_sdma.bin"); MODULE_FIRMWARE("amdgpu/raven2_sdma.bin"); MODULE_FIRMWARE("amdgpu/arcturus_sdma.bin"); MODULE_FIRMWARE("amdgpu/renoir_sdma.bin"); +MODULE_FIRMWARE("amdgpu/green_sardine_sdma.bin"); #define SDMA0_POWER_CNTL__ON_OFF_CONDITION_HOLD_TIME_MASK 0x000000F8L #define SDMA0_POWER_CNTL__ON_OFF_STATUS_DURATION_TIME_MASK 0xFC000000L @@ -619,7 +620,10 @@ static int sdma_v4_0_init_microcode(struct amdgpu_device *adev) chip_name = "arcturus"; break; case CHIP_RENOIR: - chip_name = "renoir"; + if (adev->apu_flags & AMD_APU_IS_RENOIR) + chip_name = "renoir"; + else + chip_name = "green_sardine"; break; default: BUG(); diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index afcccc6c0fc6..f57c5f57efa8 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -1195,8 +1195,7 @@ static int soc15_common_early_init(void *handle) adev->pg_flags = AMD_PG_SUPPORT_SDMA | AMD_PG_SUPPORT_MMHUB | - AMD_PG_SUPPORT_VCN | - AMD_PG_SUPPORT_VCN_DPG; + AMD_PG_SUPPORT_VCN; } else { adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG | AMD_CG_SUPPORT_GFX_MGLS | @@ -1243,7 +1242,15 @@ static int soc15_common_early_init(void *handle) break; case CHIP_RENOIR: adev->asic_funcs = &soc15_asic_funcs; - adev->apu_flags |= AMD_APU_IS_RENOIR; + if (adev->pdev->device == 0x1636) + adev->apu_flags |= AMD_APU_IS_RENOIR; + else + adev->apu_flags |= AMD_APU_IS_GREEN_SARDINE; + + if (adev->apu_flags & AMD_APU_IS_RENOIR) + adev->external_rev_id = adev->rev_id + 0x91; + else + adev->external_rev_id = adev->rev_id + 0xa1; adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG | AMD_CG_SUPPORT_GFX_MGLS | AMD_CG_SUPPORT_GFX_3D_CGCG | @@ -1268,7 +1275,6 @@ static int soc15_common_early_init(void *handle) AMD_PG_SUPPORT_VCN | AMD_PG_SUPPORT_JPEG | AMD_PG_SUPPORT_VCN_DPG; - adev->external_rev_id = adev->rev_id + 0x91; break; default: /* FIXME: not supported yet */ diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c b/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c index 7cf4b11a65c5..41800fcad410 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c @@ -277,15 +277,8 @@ static void uvd_v3_1_mc_resume(struct amdgpu_device *adev) */ static int uvd_v3_1_fw_validate(struct amdgpu_device *adev) { - void *ptr; - uint32_t ucode_len, i; - uint32_t keysel; - - ptr = adev->uvd.inst[0].cpu_addr; - ptr += 192 + 16; - memcpy(&ucode_len, ptr, 4); - ptr += ucode_len; - memcpy(&keysel, ptr, 4); + int i; + uint32_t keysel = adev->uvd.keyselect; WREG32(mmUVD_FW_START, keysel); @@ -550,6 +543,8 @@ static int uvd_v3_1_sw_init(void *handle) struct amdgpu_ring *ring; struct amdgpu_device *adev = (struct amdgpu_device *)handle; int r; + void *ptr; + uint32_t ucode_len; /* UVD TRAP */ r = amdgpu_irq_add_id(adev, AMDGPU_IRQ_CLIENTID_LEGACY, 124, &adev->uvd.inst->irq); @@ -571,6 +566,13 @@ static int uvd_v3_1_sw_init(void *handle) if (r) return r; + /* Retrieval firmware validate key */ + ptr = adev->uvd.inst[0].cpu_addr; + ptr += 192 + 16; + memcpy(&ucode_len, ptr, 4); + ptr += ucode_len; + memcpy(&adev->uvd.keyselect, ptr, 4); + r = amdgpu_uvd_entity_init(adev); return r; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c index 5e2254b9e931..3de5e14c5ae3 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c @@ -798,10 +798,10 @@ int kfd_create_crat_image_acpi(void **crat_image, size_t *size) } pcrat_image = kvmalloc(crat_table->length, GFP_KERNEL); - memcpy(pcrat_image, crat_table, crat_table->length); if (!pcrat_image) return -ENOMEM; + memcpy(pcrat_image, crat_table, crat_table->length); *crat_image = pcrat_image; *size = crat_table->length; 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 e2b23486ba4c..9b6809f309f4 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -100,6 +100,8 @@ MODULE_FIRMWARE(FIRMWARE_SIENNA_CICHLID_DMUB); #define FIRMWARE_NAVY_FLOUNDER_DMUB "amdgpu/navy_flounder_dmcub.bin" MODULE_FIRMWARE(FIRMWARE_NAVY_FLOUNDER_DMUB); #endif +#define FIRMWARE_GREEN_SARDINE_DMUB "amdgpu/green_sardine_dmcub.bin" +MODULE_FIRMWARE(FIRMWARE_GREEN_SARDINE_DMUB); #define FIRMWARE_RAVEN_DMCU "amdgpu/raven_dmcu.bin" MODULE_FIRMWARE(FIRMWARE_RAVEN_DMCU); @@ -583,7 +585,7 @@ static void amdgpu_dm_fbc_init(struct drm_connector *connector) { struct drm_device *dev = connector->dev; struct amdgpu_device *adev = drm_to_adev(dev); - struct dm_comressor_info *compressor = &adev->dm.compressor; + struct dm_compressor_info *compressor = &adev->dm.compressor; struct amdgpu_dm_connector *aconn = to_amdgpu_dm_connector(connector); struct drm_display_mode *mode; unsigned long max_size = 0; @@ -973,6 +975,8 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) case CHIP_RAVEN: case CHIP_RENOIR: init_data.flags.gpu_vm_support = true; + if (ASICREV_IS_GREEN_SARDINE(adev->external_rev_id)) + init_data.flags.disable_dmcu = true; break; default: break; @@ -1037,7 +1041,7 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) amdgpu_dm_init_color_mod(); #ifdef CONFIG_DRM_AMD_DC_HDCP - if (adev->asic_type >= CHIP_RAVEN) { + if (adev->dm.dc->caps.max_links > 0 && adev->asic_type >= CHIP_RAVEN) { adev->dm.hdcp_workqueue = hdcp_create_workqueue(adev, &init_params.cp_psp, adev->dm.dc); if (!adev->dm.hdcp_workqueue) @@ -1267,6 +1271,8 @@ static int dm_dmub_sw_init(struct amdgpu_device *adev) case CHIP_RENOIR: dmub_asic = DMUB_ASIC_DCN21; fw_name_dmub = FIRMWARE_RENOIR_DMUB; + if (ASICREV_IS_GREEN_SARDINE(adev->external_rev_id)) + fw_name_dmub = FIRMWARE_GREEN_SARDINE_DMUB; break; #if defined(CONFIG_DRM_AMD_DC_DCN3_0) case CHIP_SIENNA_CICHLID: @@ -7500,7 +7506,6 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) bool mode_set_reset_required = false; drm_atomic_helper_update_legacy_modeset_state(dev, state); - drm_atomic_helper_calc_timestamping_constants(state); dm_state = dm_atomic_get_new_state(state); if (dm_state && dm_state->context) { @@ -7527,6 +7532,8 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) } } + drm_atomic_helper_calc_timestamping_constants(state); + /* update changed items */ for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h index 34f6369bf51f..a8a0e8cb1a11 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h @@ -86,7 +86,7 @@ struct irq_list_head { * @bo_ptr: Pointer to the buffer object * @gpu_addr: MMIO gpu addr */ -struct dm_comressor_info { +struct dm_compressor_info { void *cpu_addr; struct amdgpu_bo *bo_ptr; uint64_t gpu_addr; @@ -148,7 +148,7 @@ struct amdgpu_dm_backlight_caps { * @soc_bounding_box: SOC bounding box values provided by gpu_info FW * @cached_state: Caches device atomic state for suspend/resume * @cached_dc_state: Cached state of content streams - * @compressor: Frame buffer compression buffer. See &struct dm_comressor_info + * @compressor: Frame buffer compression buffer. See &struct dm_compressor_info * @force_timing_sync: set via debugfs. When set, indicates that all connected * displays will be forced to synchronize. */ @@ -324,7 +324,7 @@ struct amdgpu_display_manager { struct drm_atomic_state *cached_state; struct dc_state *cached_dc_state; - struct dm_comressor_info compressor; + struct dm_compressor_info compressor; const struct firmware *fw_dmcu; uint32_t dmcu_fw_version; diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c index efb909ef7a0f..857f156e4985 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c @@ -166,6 +166,11 @@ struct clk_mgr *dc_clk_mgr_create(struct dc_context *ctx, struct pp_smu_funcs *p rn_clk_mgr_construct(ctx, clk_mgr, pp_smu, dccg); break; } + + if (ASICREV_IS_GREEN_SARDINE(asic_id.hw_internal_rev)) { + rn_clk_mgr_construct(ctx, clk_mgr, pp_smu, dccg); + break; + } if (ASICREV_IS_RAVEN2(asic_id.hw_internal_rev)) { rv2_clk_mgr_construct(ctx, clk_mgr, pp_smu); break; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index e430148e47cf..59d48cf819ea 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -120,6 +120,8 @@ enum dce_version resource_parse_asic_id(struct hw_asic_id asic_id) dc_version = DCN_VERSION_1_01; if (ASICREV_IS_RENOIR(asic_id.hw_internal_rev)) dc_version = DCN_VERSION_2_1; + if (ASICREV_IS_GREEN_SARDINE(asic_id.hw_internal_rev)) + dc_version = DCN_VERSION_2_1; break; #endif diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c b/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c index 2a1fea501f8c..3f1e7a196a23 100644 --- a/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c +++ b/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c @@ -299,8 +299,8 @@ irq_source_info_dcn20[DAL_IRQ_SOURCES_NUMBER] = { pflip_int_entry(1), pflip_int_entry(2), pflip_int_entry(3), - [DC_IRQ_SOURCE_PFLIP5] = dummy_irq_entry(), - [DC_IRQ_SOURCE_PFLIP6] = dummy_irq_entry(), + pflip_int_entry(4), + pflip_int_entry(5), [DC_IRQ_SOURCE_PFLIP_UNDERLAY0] = dummy_irq_entry(), gpio_pad_int_entry(0), gpio_pad_int_entry(1), diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn30/irq_service_dcn30.c b/drivers/gpu/drm/amd/display/dc/irq/dcn30/irq_service_dcn30.c index 49689f71f4f1..0effbb2bd74a 100644 --- a/drivers/gpu/drm/amd/display/dc/irq/dcn30/irq_service_dcn30.c +++ b/drivers/gpu/drm/amd/display/dc/irq/dcn30/irq_service_dcn30.c @@ -306,8 +306,8 @@ irq_source_info_dcn30[DAL_IRQ_SOURCES_NUMBER] = { pflip_int_entry(1), pflip_int_entry(2), pflip_int_entry(3), - [DC_IRQ_SOURCE_PFLIP5] = dummy_irq_entry(), - [DC_IRQ_SOURCE_PFLIP6] = dummy_irq_entry(), + pflip_int_entry(4), + pflip_int_entry(5), [DC_IRQ_SOURCE_PFLIP_UNDERLAY0] = dummy_irq_entry(), gpio_pad_int_entry(0), gpio_pad_int_entry(1), diff --git a/drivers/gpu/drm/amd/display/include/dal_asic_id.h b/drivers/gpu/drm/amd/display/include/dal_asic_id.h index b267987aed06..ffcb059297d3 100644 --- a/drivers/gpu/drm/amd/display/include/dal_asic_id.h +++ b/drivers/gpu/drm/amd/display/include/dal_asic_id.h @@ -205,6 +205,10 @@ enum { #if defined(CONFIG_DRM_AMD_DC_DCN3_0) #define ASICREV_IS_SIENNA_CICHLID_P(eChipRev) ((eChipRev >= NV_SIENNA_CICHLID_P_A0)) #endif +#define GREEN_SARDINE_A0 0xA1 +#ifndef ASICREV_IS_GREEN_SARDINE +#define ASICREV_IS_GREEN_SARDINE(eChipRev) ((eChipRev >= GREEN_SARDINE_A0) && (eChipRev < 0xFF)) +#endif /* * ASIC chip ID diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h index 10dc481ecbc4..06c1aabf10ce 100644 --- a/drivers/gpu/drm/amd/include/amd_shared.h +++ b/drivers/gpu/drm/amd/include/amd_shared.h @@ -45,6 +45,7 @@ enum amd_apu_flags { AMD_APU_IS_RAVEN2 = 0x00000002UL, AMD_APU_IS_PICASSO = 0x00000004UL, AMD_APU_IS_RENOIR = 0x00000008UL, + AMD_APU_IS_GREEN_SARDINE = 0x00000010UL, }; /** diff --git a/drivers/gpu/drm/amd/pm/inc/hwmgr.h b/drivers/gpu/drm/amd/pm/inc/hwmgr.h index 3898a95ec28b..518796a26eda 100644 --- a/drivers/gpu/drm/amd/pm/inc/hwmgr.h +++ b/drivers/gpu/drm/amd/pm/inc/hwmgr.h @@ -229,6 +229,7 @@ struct pp_smumgr_func { bool (*is_hw_avfs_present)(struct pp_hwmgr *hwmgr); int (*update_dpm_settings)(struct pp_hwmgr *hwmgr, void *profile_setting); int (*smc_table_manager)(struct pp_hwmgr *hwmgr, uint8_t *table, uint16_t table_id, bool rw); /*rw: true for read, false for write */ + int (*stop_smc)(struct pp_hwmgr *hwmgr); }; struct pp_hwmgr_func { diff --git a/drivers/gpu/drm/amd/pm/inc/smumgr.h b/drivers/gpu/drm/amd/pm/inc/smumgr.h index ad100b533d04..5f46f1a4f38e 100644 --- a/drivers/gpu/drm/amd/pm/inc/smumgr.h +++ b/drivers/gpu/drm/amd/pm/inc/smumgr.h @@ -113,4 +113,6 @@ extern int smum_update_dpm_settings(struct pp_hwmgr *hwmgr, void *profile_settin extern int smum_smc_table_manager(struct pp_hwmgr *hwmgr, uint8_t *table, uint16_t table_id, bool rw); +extern int smum_stop_smc(struct pp_hwmgr *hwmgr); + #endif diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ci_baco.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ci_baco.c index 3be40114e63d..45f608838f6e 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ci_baco.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ci_baco.c @@ -142,12 +142,12 @@ static const struct baco_cmd_entry exit_baco_tbl[] = { CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_BCLK_OFF_MASK, BACO_CNTL__BACO_BCLK_OFF__SHIFT, 0, 0x00 }, { CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_POWER_OFF_MASK, BACO_CNTL__BACO_POWER_OFF__SHIFT, 0, 0x00 }, { CMD_DELAY_MS, 0, 0, 0, 20, 0 }, - { CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__PWRGOOD_BF_MASK, 0, 0xffffffff, 0x20 }, + { CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__PWRGOOD_BF_MASK, 0, 0xffffffff, 0x200 }, { CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_ISO_DIS_MASK, BACO_CNTL__BACO_ISO_DIS__SHIFT, 0, 0x01 }, - { CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__PWRGOOD_MASK, 0, 5, 0x1c }, + { CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__PWRGOOD_MASK, 0, 5, 0x1c00 }, { CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_ANA_ISO_DIS_MASK, BACO_CNTL__BACO_ANA_ISO_DIS__SHIFT, 0, 0x01 }, { CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_RESET_EN_MASK, BACO_CNTL__BACO_RESET_EN__SHIFT, 0, 0x00 }, - { CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__RCU_BIF_CONFIG_DONE_MASK, 0, 5, 0x10 }, + { CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__RCU_BIF_CONFIG_DONE_MASK, 0, 5, 0x100 }, { CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_EN_MASK, BACO_CNTL__BACO_EN__SHIFT, 0, 0x00 }, { CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__BACO_MODE_MASK, 0, 0xffffffff, 0x00 } }; @@ -155,6 +155,7 @@ static const struct baco_cmd_entry exit_baco_tbl[] = static const struct baco_cmd_entry clean_baco_tbl[] = { { CMD_WRITE, mmBIOS_SCRATCH_6, 0, 0, 0, 0 }, + { CMD_WRITE, mmBIOS_SCRATCH_7, 0, 0, 0, 0 }, { CMD_WRITE, mmCP_PFP_UCODE_ADDR, 0, 0, 0, 0 } }; diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c index 1e8919b0acdb..35629140fc7a 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c @@ -1541,6 +1541,10 @@ static int smu7_disable_dpm_tasks(struct pp_hwmgr *hwmgr) PP_ASSERT_WITH_CODE((tmp_result == 0), "Failed to reset to default!", result = tmp_result); + tmp_result = smum_stop_smc(hwmgr); + PP_ASSERT_WITH_CODE((tmp_result == 0), + "Failed to stop smc!", result = tmp_result); + tmp_result = smu7_force_switch_to_arbf0(hwmgr); PP_ASSERT_WITH_CODE((tmp_result == 0), "Failed to force to switch arbf0!", result = tmp_result); @@ -1585,18 +1589,24 @@ static void smu7_init_dpm_defaults(struct pp_hwmgr *hwmgr) data->current_profile_setting.sclk_down_hyst = 100; data->current_profile_setting.sclk_activity = SMU7_SCLK_TARGETACTIVITY_DFLT; data->current_profile_setting.bupdate_mclk = 1; - if (adev->gmc.vram_width == 256) { - data->current_profile_setting.mclk_up_hyst = 10; - data->current_profile_setting.mclk_down_hyst = 60; - data->current_profile_setting.mclk_activity = 25; - } else if (adev->gmc.vram_width == 128) { - data->current_profile_setting.mclk_up_hyst = 5; - data->current_profile_setting.mclk_down_hyst = 16; - data->current_profile_setting.mclk_activity = 20; - } else if (adev->gmc.vram_width == 64) { - data->current_profile_setting.mclk_up_hyst = 3; - data->current_profile_setting.mclk_down_hyst = 16; - data->current_profile_setting.mclk_activity = 20; + if (hwmgr->chip_id >= CHIP_POLARIS10) { + if (adev->gmc.vram_width == 256) { + data->current_profile_setting.mclk_up_hyst = 10; + data->current_profile_setting.mclk_down_hyst = 60; + data->current_profile_setting.mclk_activity = 25; + } else if (adev->gmc.vram_width == 128) { + data->current_profile_setting.mclk_up_hyst = 5; + data->current_profile_setting.mclk_down_hyst = 16; + data->current_profile_setting.mclk_activity = 20; + } else if (adev->gmc.vram_width == 64) { + data->current_profile_setting.mclk_up_hyst = 3; + data->current_profile_setting.mclk_down_hyst = 16; + data->current_profile_setting.mclk_activity = 20; + } + } else { + data->current_profile_setting.mclk_up_hyst = 0; + data->current_profile_setting.mclk_down_hyst = 100; + data->current_profile_setting.mclk_activity = SMU7_MCLK_TARGETACTIVITY_DFLT; } hwmgr->workload_mask = 1 << hwmgr->workload_prority[PP_SMC_POWER_PROFILE_FULLSCREEN3D]; hwmgr->power_profile_mode = PP_SMC_POWER_PROFILE_FULLSCREEN3D; diff --git a/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c index e4d1f3d66ef4..329bf4d44bbc 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c @@ -2726,10 +2726,7 @@ static int ci_initialize_mc_reg_table(struct pp_hwmgr *hwmgr) static bool ci_is_dpm_running(struct pp_hwmgr *hwmgr) { - return (1 == PHM_READ_INDIRECT_FIELD(hwmgr->device, - CGS_IND_REG__SMC, FEATURE_STATUS, - VOLTAGE_CONTROLLER_ON)) - ? true : false; + return ci_is_smc_ram_running(hwmgr); } static int ci_smu_init(struct pp_hwmgr *hwmgr) @@ -2939,6 +2936,29 @@ static int ci_update_smc_table(struct pp_hwmgr *hwmgr, uint32_t type) return 0; } +static void ci_reset_smc(struct pp_hwmgr *hwmgr) +{ + PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, + SMC_SYSCON_RESET_CNTL, + rst_reg, 1); +} + + +static void ci_stop_smc_clock(struct pp_hwmgr *hwmgr) +{ + PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, + SMC_SYSCON_CLOCK_CNTL_0, + ck_disable, 1); +} + +static int ci_stop_smc(struct pp_hwmgr *hwmgr) +{ + ci_reset_smc(hwmgr); + ci_stop_smc_clock(hwmgr); + + return 0; +} + const struct pp_smumgr_func ci_smu_funcs = { .name = "ci_smu", .smu_init = ci_smu_init, @@ -2964,4 +2984,5 @@ const struct pp_smumgr_func ci_smu_funcs = { .is_dpm_running = ci_is_dpm_running, .update_dpm_settings = ci_update_dpm_settings, .update_smc_table = ci_update_smc_table, + .stop_smc = ci_stop_smc, }; diff --git a/drivers/gpu/drm/amd/pm/powerplay/smumgr/smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/smumgr.c index b6fb48066841..b6921db3c130 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/smumgr/smumgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/smumgr.c @@ -245,3 +245,11 @@ int smum_smc_table_manager(struct pp_hwmgr *hwmgr, uint8_t *table, uint16_t tabl return -EINVAL; } + +int smum_stop_smc(struct pp_hwmgr *hwmgr) +{ + if (hwmgr->smumgr_funcs->stop_smc) + return hwmgr->smumgr_funcs->stop_smc(hwmgr); + + return 0; +} diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index fc4f95fa87cf..b1e5ec01527b 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -1029,17 +1029,6 @@ static int smu_smc_hw_setup(struct smu_context *smu) return ret; } - /* - * Set initialized values (get from vbios) to dpm tables context such as - * gfxclk, memclk, dcefclk, and etc. And enable the DPM feature for each - * type of clks. - */ - ret = smu_set_default_dpm_table(smu); - if (ret) { - dev_err(adev->dev, "Failed to setup default dpm clock tables!\n"); - return ret; - } - ret = smu_notify_display_change(smu); if (ret) return ret; diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c index 50cad0e4a92e..375c79e23ca5 100644 --- a/drivers/gpu/drm/drm_gem_vram_helper.c +++ b/drivers/gpu/drm/drm_gem_vram_helper.c @@ -140,7 +140,7 @@ static void drm_gem_vram_placement(struct drm_gem_vram_object *gbo, unsigned int c = 0; if (pl_flag & DRM_GEM_VRAM_PL_FLAG_TOPDOWN) - pl_flag = TTM_PL_FLAG_TOPDOWN; + invariant_flags = TTM_PL_FLAG_TOPDOWN; gbo->placement.placement = gbo->placements; gbo->placement.busy_placement = gbo->placements; diff --git a/drivers/gpu/drm/exynos/Kconfig b/drivers/gpu/drm/exynos/Kconfig index 6417f374b923..951d5f708e92 100644 --- a/drivers/gpu/drm/exynos/Kconfig +++ b/drivers/gpu/drm/exynos/Kconfig @@ -1,7 +1,8 @@ # SPDX-License-Identifier: GPL-2.0-only config DRM_EXYNOS tristate "DRM Support for Samsung SoC Exynos Series" - depends on OF && DRM && (ARCH_S3C64XX || ARCH_S5PV210 || ARCH_EXYNOS || ARCH_MULTIPLATFORM || COMPILE_TEST) + depends on OF && DRM && COMMON_CLK + depends on ARCH_S3C64XX || ARCH_S5PV210 || ARCH_EXYNOS || ARCH_MULTIPLATFORM || COMPILE_TEST depends on MMU select DRM_KMS_HELPER select VIDEOMODE_HELPERS diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 31337d2a2cde..99e682563d47 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -12878,10 +12878,11 @@ compute_sink_pipe_bpp(const struct drm_connector_state *conn_state, case 10 ... 11: bpp = 10 * 3; break; - case 12: + case 12 ... 16: bpp = 12 * 3; break; default: + MISSING_CASE(conn_state->max_bpc); return -EINVAL; } diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c index 8a9d0bdde1bf..40e9cb29233d 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.c +++ b/drivers/gpu/drm/i915/display/intel_psr.c @@ -1754,7 +1754,7 @@ void intel_psr_atomic_check(struct drm_connector *connector, return; intel_connector = to_intel_connector(connector); - dig_port = enc_to_dig_port(intel_attached_encoder(intel_connector)); + dig_port = enc_to_dig_port(to_intel_encoder(new_state->best_encoder)); if (dev_priv->psr.dp != &dig_port->dp) return; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_domain.c b/drivers/gpu/drm/i915/gem/i915_gem_domain.c index 7c90a63c273d..fcce6909f201 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_domain.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_domain.c @@ -509,21 +509,6 @@ i915_gem_set_domain_ioctl(struct drm_device *dev, void *data, return -ENOENT; /* - * Already in the desired write domain? Nothing for us to do! - * - * We apply a little bit of cunning here to catch a broader set of - * no-ops. If obj->write_domain is set, we must be in the same - * obj->read_domains, and only that domain. Therefore, if that - * obj->write_domain matches the request read_domains, we are - * already in the same read/write domain and can skip the operation, - * without having to further check the requested write_domain. - */ - if (READ_ONCE(obj->write_domain) == read_domains) { - err = 0; - goto out; - } - - /* * Try to flush the object off the GPU without holding the lock. * We will repeat the flush holding the lock in the normal manner * to catch cases where we are gazumped. @@ -560,6 +545,19 @@ i915_gem_set_domain_ioctl(struct drm_device *dev, void *data, if (err) goto out; + /* + * Already in the desired write domain? Nothing for us to do! + * + * We apply a little bit of cunning here to catch a broader set of + * no-ops. If obj->write_domain is set, we must be in the same + * obj->read_domains, and only that domain. Therefore, if that + * obj->write_domain matches the request read_domains, we are + * already in the same read/write domain and can skip the operation, + * without having to further check the requested write_domain. + */ + if (READ_ONCE(obj->write_domain) == read_domains) + goto out_unpin; + err = i915_gem_object_lock_interruptible(obj, NULL); if (err) goto out_unpin; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h index b5c15557cc87..d6711caa7f39 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h @@ -56,6 +56,8 @@ struct drm_i915_gem_object_ops { void (*truncate)(struct drm_i915_gem_object *obj); void (*writeback)(struct drm_i915_gem_object *obj); + int (*pread)(struct drm_i915_gem_object *obj, + const struct drm_i915_gem_pread *arg); int (*pwrite)(struct drm_i915_gem_object *obj, const struct drm_i915_gem_pwrite *arg); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_phys.c b/drivers/gpu/drm/i915/gem/i915_gem_phys.c index 28147aab47b9..3a4dfe2ef1da 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_phys.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_phys.c @@ -134,6 +134,58 @@ i915_gem_object_put_pages_phys(struct drm_i915_gem_object *obj, vaddr, dma); } +static int +phys_pwrite(struct drm_i915_gem_object *obj, + const struct drm_i915_gem_pwrite *args) +{ + void *vaddr = sg_page(obj->mm.pages->sgl) + args->offset; + char __user *user_data = u64_to_user_ptr(args->data_ptr); + int err; + + err = i915_gem_object_wait(obj, + I915_WAIT_INTERRUPTIBLE | + I915_WAIT_ALL, + MAX_SCHEDULE_TIMEOUT); + if (err) + return err; + + /* + * We manually control the domain here and pretend that it + * remains coherent i.e. in the GTT domain, like shmem_pwrite. + */ + i915_gem_object_invalidate_frontbuffer(obj, ORIGIN_CPU); + + if (copy_from_user(vaddr, user_data, args->size)) + return -EFAULT; + + drm_clflush_virt_range(vaddr, args->size); + intel_gt_chipset_flush(&to_i915(obj->base.dev)->gt); + + i915_gem_object_flush_frontbuffer(obj, ORIGIN_CPU); + return 0; +} + +static int +phys_pread(struct drm_i915_gem_object *obj, + const struct drm_i915_gem_pread *args) +{ + void *vaddr = sg_page(obj->mm.pages->sgl) + args->offset; + char __user *user_data = u64_to_user_ptr(args->data_ptr); + int err; + + err = i915_gem_object_wait(obj, + I915_WAIT_INTERRUPTIBLE, + MAX_SCHEDULE_TIMEOUT); + if (err) + return err; + + drm_clflush_virt_range(vaddr, args->size); + if (copy_to_user(user_data, vaddr, args->size)) + return -EFAULT; + + return 0; +} + static void phys_release(struct drm_i915_gem_object *obj) { fput(obj->base.filp); @@ -144,6 +196,9 @@ static const struct drm_i915_gem_object_ops i915_gem_phys_ops = { .get_pages = i915_gem_object_get_pages_phys, .put_pages = i915_gem_object_put_pages_phys, + .pread = phys_pread, + .pwrite = phys_pwrite, + .release = phys_release, }; diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c index d8b206e53660..cf6e05ea4d8f 100644 --- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c +++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c @@ -30,18 +30,21 @@ #include "i915_trace.h" #include "intel_breadcrumbs.h" #include "intel_context.h" +#include "intel_engine_pm.h" #include "intel_gt_pm.h" #include "intel_gt_requests.h" -static void irq_enable(struct intel_engine_cs *engine) +static bool irq_enable(struct intel_engine_cs *engine) { if (!engine->irq_enable) - return; + return false; /* Caller disables interrupts */ spin_lock(&engine->gt->irq_lock); engine->irq_enable(engine); spin_unlock(&engine->gt->irq_lock); + + return true; } static void irq_disable(struct intel_engine_cs *engine) @@ -57,12 +60,11 @@ static void irq_disable(struct intel_engine_cs *engine) static void __intel_breadcrumbs_arm_irq(struct intel_breadcrumbs *b) { - lockdep_assert_held(&b->irq_lock); - - if (!b->irq_engine || b->irq_armed) - return; - - if (!intel_gt_pm_get_if_awake(b->irq_engine->gt)) + /* + * Since we are waiting on a request, the GPU should be busy + * and should have its own rpm reference. + */ + if (GEM_WARN_ON(!intel_gt_pm_get_if_awake(b->irq_engine->gt))) return; /* @@ -73,25 +75,24 @@ static void __intel_breadcrumbs_arm_irq(struct intel_breadcrumbs *b) */ WRITE_ONCE(b->irq_armed, true); - /* - * Since we are waiting on a request, the GPU should be busy - * and should have its own rpm reference. This is tracked - * by i915->gt.awake, we can forgo holding our own wakref - * for the interrupt as before i915->gt.awake is released (when - * the driver is idle) we disarm the breadcrumbs. - */ - - if (!b->irq_enabled++) - irq_enable(b->irq_engine); + /* Requests may have completed before we could enable the interrupt. */ + if (!b->irq_enabled++ && irq_enable(b->irq_engine)) + irq_work_queue(&b->irq_work); } -static void __intel_breadcrumbs_disarm_irq(struct intel_breadcrumbs *b) +static void intel_breadcrumbs_arm_irq(struct intel_breadcrumbs *b) { - lockdep_assert_held(&b->irq_lock); - - if (!b->irq_engine || !b->irq_armed) + if (!b->irq_engine) return; + spin_lock(&b->irq_lock); + if (!b->irq_armed) + __intel_breadcrumbs_arm_irq(b); + spin_unlock(&b->irq_lock); +} + +static void __intel_breadcrumbs_disarm_irq(struct intel_breadcrumbs *b) +{ GEM_BUG_ON(!b->irq_enabled); if (!--b->irq_enabled) irq_disable(b->irq_engine); @@ -105,8 +106,6 @@ static void add_signaling_context(struct intel_breadcrumbs *b, { intel_context_get(ce); list_add_tail(&ce->signal_link, &b->signalers); - if (list_is_first(&ce->signal_link, &b->signalers)) - __intel_breadcrumbs_arm_irq(b); } static void remove_signaling_context(struct intel_breadcrumbs *b, @@ -174,34 +173,65 @@ static void add_retire(struct intel_breadcrumbs *b, struct intel_timeline *tl) intel_engine_add_retire(b->irq_engine, tl); } -static bool __signal_request(struct i915_request *rq, struct list_head *signals) +static bool __signal_request(struct i915_request *rq) { - clear_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags); - if (!__dma_fence_signal(&rq->fence)) { i915_request_put(rq); return false; } - list_add_tail(&rq->signal_link, signals); return true; } +static struct llist_node * +slist_add(struct llist_node *node, struct llist_node *head) +{ + node->next = head; + return node; +} + static void signal_irq_work(struct irq_work *work) { struct intel_breadcrumbs *b = container_of(work, typeof(*b), irq_work); const ktime_t timestamp = ktime_get(); + struct llist_node *signal, *sn; struct intel_context *ce, *cn; struct list_head *pos, *next; - LIST_HEAD(signal); + + signal = NULL; + if (unlikely(!llist_empty(&b->signaled_requests))) + signal = llist_del_all(&b->signaled_requests); spin_lock(&b->irq_lock); - if (list_empty(&b->signalers)) + /* + * Keep the irq armed until the interrupt after all listeners are gone. + * + * Enabling/disabling the interrupt is rather costly, roughly a couple + * of hundred microseconds. If we are proactive and enable/disable + * the interrupt around every request that wants a breadcrumb, we + * quickly drown in the extra orders of magnitude of latency imposed + * on request submission. + * + * So we try to be lazy, and keep the interrupts enabled until no + * more listeners appear within a breadcrumb interrupt interval (that + * is until a request completes that no one cares about). The + * observation is that listeners come in batches, and will often + * listen to a bunch of requests in succession. Though note on icl+, + * interrupts are always enabled due to concerns with rc6 being + * dysfunctional with per-engine interrupt masking. + * + * We also try to avoid raising too many interrupts, as they may + * be generated by userspace batches and it is unfortunately rather + * too easy to drown the CPU under a flood of GPU interrupts. Thus + * whenever no one appears to be listening, we turn off the interrupts. + * Fewer interrupts should conserve power -- at the very least, fewer + * interrupt draw less ire from other users of the system and tools + * like powertop. + */ + if (!signal && b->irq_armed && list_empty(&b->signalers)) __intel_breadcrumbs_disarm_irq(b); - list_splice_init(&b->signaled_requests, &signal); - list_for_each_entry_safe(ce, cn, &b->signalers, signal_link) { GEM_BUG_ON(list_empty(&ce->signals)); @@ -218,7 +248,10 @@ static void signal_irq_work(struct irq_work *work) * spinlock as the callback chain may end up adding * more signalers to the same context or engine. */ - __signal_request(rq, &signal); + clear_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags); + if (__signal_request(rq)) + /* We own signal_node now, xfer to local list */ + signal = slist_add(&rq->signal_node, signal); } /* @@ -238,9 +271,9 @@ static void signal_irq_work(struct irq_work *work) spin_unlock(&b->irq_lock); - list_for_each_safe(pos, next, &signal) { + llist_for_each_safe(signal, sn, signal) { struct i915_request *rq = - list_entry(pos, typeof(*rq), signal_link); + llist_entry(signal, typeof(*rq), signal_node); struct list_head cb_list; spin_lock(&rq->lock); @@ -251,6 +284,9 @@ static void signal_irq_work(struct irq_work *work) i915_request_put(rq); } + + if (!READ_ONCE(b->irq_armed) && !list_empty(&b->signalers)) + intel_breadcrumbs_arm_irq(b); } struct intel_breadcrumbs * @@ -264,7 +300,7 @@ intel_breadcrumbs_create(struct intel_engine_cs *irq_engine) spin_lock_init(&b->irq_lock); INIT_LIST_HEAD(&b->signalers); - INIT_LIST_HEAD(&b->signaled_requests); + init_llist_head(&b->signaled_requests); init_irq_work(&b->irq_work, signal_irq_work); @@ -292,21 +328,22 @@ void intel_breadcrumbs_reset(struct intel_breadcrumbs *b) void intel_breadcrumbs_park(struct intel_breadcrumbs *b) { - unsigned long flags; - - if (!READ_ONCE(b->irq_armed)) - return; - - spin_lock_irqsave(&b->irq_lock, flags); - __intel_breadcrumbs_disarm_irq(b); - spin_unlock_irqrestore(&b->irq_lock, flags); - - if (!list_empty(&b->signalers)) - irq_work_queue(&b->irq_work); + /* Kick the work once more to drain the signalers */ + irq_work_sync(&b->irq_work); + while (unlikely(READ_ONCE(b->irq_armed))) { + local_irq_disable(); + signal_irq_work(&b->irq_work); + local_irq_enable(); + cond_resched(); + } + GEM_BUG_ON(!list_empty(&b->signalers)); } void intel_breadcrumbs_free(struct intel_breadcrumbs *b) { + irq_work_sync(&b->irq_work); + GEM_BUG_ON(!list_empty(&b->signalers)); + GEM_BUG_ON(b->irq_armed); kfree(b); } @@ -327,7 +364,8 @@ static void insert_breadcrumb(struct i915_request *rq, * its signal completion. */ if (__request_completed(rq)) { - if (__signal_request(rq, &b->signaled_requests)) + if (__signal_request(rq) && + llist_add(&rq->signal_node, &b->signaled_requests)) irq_work_queue(&b->irq_work); return; } @@ -362,9 +400,12 @@ static void insert_breadcrumb(struct i915_request *rq, GEM_BUG_ON(!check_signal_order(ce, rq)); set_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags); - /* Check after attaching to irq, interrupt may have already fired. */ - if (__request_completed(rq)) - irq_work_queue(&b->irq_work); + /* + * Defer enabling the interrupt to after HW submission and recheck + * the request as it may have completed and raised the interrupt as + * we were attaching it into the lists. + */ + irq_work_queue(&b->irq_work); } bool i915_request_enable_breadcrumb(struct i915_request *rq) diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h b/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h index 8e53b9942695..3fa19820b37a 100644 --- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h +++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h @@ -35,7 +35,7 @@ struct intel_breadcrumbs { struct intel_engine_cs *irq_engine; struct list_head signalers; - struct list_head signaled_requests; + struct llist_head signaled_requests; struct irq_work irq_work; /* for use from inside irq_lock */ diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h index 7c3a1012e702..760fefdfe392 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine.h +++ b/drivers/gpu/drm/i915/gt/intel_engine.h @@ -245,22 +245,14 @@ static inline u32 *gen12_emit_pipe_control(u32 *batch, u32 flags0, u32 flags1, u } static inline u32 * -__gen8_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset, u32 flags0, u32 flags1) +__gen8_emit_write_rcs(u32 *cs, u32 value, u32 offset, u32 flags0, u32 flags1) { - /* We're using qword write, offset should be aligned to 8 bytes. */ - GEM_BUG_ON(!IS_ALIGNED(gtt_offset, 8)); - - /* w/a for post sync ops following a GPGPU operation we - * need a prior CS_STALL, which is emitted by the flush - * following the batch. - */ *cs++ = GFX_OP_PIPE_CONTROL(6) | flags0; - *cs++ = flags1 | PIPE_CONTROL_QW_WRITE | PIPE_CONTROL_GLOBAL_GTT_IVB; - *cs++ = gtt_offset; + *cs++ = flags1 | PIPE_CONTROL_QW_WRITE; + *cs++ = offset; *cs++ = 0; *cs++ = value; - /* We're thrashing one dword of HWS. */ - *cs++ = 0; + *cs++ = 0; /* We're thrashing one extra dword. */ return cs; } @@ -268,13 +260,38 @@ __gen8_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset, u32 flags0, u32 f static inline u32* gen8_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset, u32 flags) { - return __gen8_emit_ggtt_write_rcs(cs, value, gtt_offset, 0, flags); + /* We're using qword write, offset should be aligned to 8 bytes. */ + GEM_BUG_ON(!IS_ALIGNED(gtt_offset, 8)); + + return __gen8_emit_write_rcs(cs, + value, + gtt_offset, + 0, + flags | PIPE_CONTROL_GLOBAL_GTT_IVB); } static inline u32* gen12_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset, u32 flags0, u32 flags1) { - return __gen8_emit_ggtt_write_rcs(cs, value, gtt_offset, flags0, flags1); + /* We're using qword write, offset should be aligned to 8 bytes. */ + GEM_BUG_ON(!IS_ALIGNED(gtt_offset, 8)); + + return __gen8_emit_write_rcs(cs, + value, + gtt_offset, + flags0, + flags1 | PIPE_CONTROL_GLOBAL_GTT_IVB); +} + +static inline u32 * +__gen8_emit_flush_dw(u32 *cs, u32 value, u32 gtt_offset, u32 flags) +{ + *cs++ = (MI_FLUSH_DW + 1) | flags; + *cs++ = gtt_offset; + *cs++ = 0; + *cs++ = value; + + return cs; } static inline u32 * @@ -285,12 +302,10 @@ gen8_emit_ggtt_write(u32 *cs, u32 value, u32 gtt_offset, u32 flags) /* Offset should be aligned to 8 bytes for both (QW/DW) write types */ GEM_BUG_ON(!IS_ALIGNED(gtt_offset, 8)); - *cs++ = (MI_FLUSH_DW + 1) | MI_FLUSH_DW_OP_STOREDW | flags; - *cs++ = gtt_offset | MI_FLUSH_DW_USE_GTT; - *cs++ = 0; - *cs++ = value; - - return cs; + return __gen8_emit_flush_dw(cs, + value, + gtt_offset | MI_FLUSH_DW_USE_GTT, + flags | MI_FLUSH_DW_OP_STOREDW); } static inline void __intel_engine_reset(struct intel_engine_cs *engine, diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index 5bfb5f7ed02c..efdeb7b7b2a0 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -371,7 +371,8 @@ static void __setup_engine_capabilities(struct intel_engine_cs *engine) * instances. */ if ((INTEL_GEN(i915) >= 11 && - engine->gt->info.vdbox_sfc_access & engine->mask) || + (engine->gt->info.vdbox_sfc_access & + BIT(engine->instance))) || (INTEL_GEN(i915) >= 9 && engine->instance == 0)) engine->uabi_capabilities |= I915_VIDEO_AND_ENHANCE_CLASS_CAPABILITY_SFC; diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index a32aabce7901..0952bf157234 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -182,6 +182,7 @@ struct virtual_engine { struct intel_engine_cs base; struct intel_context context; + struct rcu_work rcu; /* * We allow only a single request through the virtual engine at a time @@ -3547,6 +3548,19 @@ static const struct intel_context_ops execlists_context_ops = { .destroy = execlists_context_destroy, }; +static u32 hwsp_offset(const struct i915_request *rq) +{ + const struct intel_timeline_cacheline *cl; + + /* Before the request is executed, the timeline/cachline is fixed */ + + cl = rcu_dereference_protected(rq->hwsp_cacheline, 1); + if (cl) + return cl->ggtt_offset; + + return rcu_dereference_protected(rq->timeline, 1)->hwsp_offset; +} + static int gen8_emit_init_breadcrumb(struct i915_request *rq) { u32 *cs; @@ -3569,7 +3583,7 @@ static int gen8_emit_init_breadcrumb(struct i915_request *rq) *cs++ = MI_NOOP; *cs++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT; - *cs++ = i915_request_timeline(rq)->hwsp_offset; + *cs++ = hwsp_offset(rq); *cs++ = 0; *cs++ = rq->fence.seqno - 1; @@ -4886,11 +4900,9 @@ gen8_emit_fini_breadcrumb_tail(struct i915_request *request, u32 *cs) return gen8_emit_wa_tail(request, cs); } -static u32 *emit_xcs_breadcrumb(struct i915_request *request, u32 *cs) +static u32 *emit_xcs_breadcrumb(struct i915_request *rq, u32 *cs) { - u32 addr = i915_request_active_timeline(request)->hwsp_offset; - - return gen8_emit_ggtt_write(cs, request->fence.seqno, addr, 0); + return gen8_emit_ggtt_write(cs, rq->fence.seqno, hwsp_offset(rq), 0); } static u32 *gen8_emit_fini_breadcrumb(struct i915_request *rq, u32 *cs) @@ -4909,7 +4921,7 @@ static u32 *gen8_emit_fini_breadcrumb_rcs(struct i915_request *request, u32 *cs) /* XXX flush+write+CS_STALL all in one upsets gem_concurrent_blt:kbl */ cs = gen8_emit_ggtt_write_rcs(cs, request->fence.seqno, - i915_request_active_timeline(request)->hwsp_offset, + hwsp_offset(request), PIPE_CONTROL_FLUSH_ENABLE | PIPE_CONTROL_CS_STALL); @@ -4921,7 +4933,7 @@ gen11_emit_fini_breadcrumb_rcs(struct i915_request *request, u32 *cs) { cs = gen8_emit_ggtt_write_rcs(cs, request->fence.seqno, - i915_request_active_timeline(request)->hwsp_offset, + hwsp_offset(request), PIPE_CONTROL_CS_STALL | PIPE_CONTROL_TILE_CACHE_FLUSH | PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH | @@ -4983,7 +4995,9 @@ gen12_emit_fini_breadcrumb_tail(struct i915_request *request, u32 *cs) static u32 *gen12_emit_fini_breadcrumb(struct i915_request *rq, u32 *cs) { - return gen12_emit_fini_breadcrumb_tail(rq, emit_xcs_breadcrumb(rq, cs)); + /* XXX Stalling flush before seqno write; post-sync not */ + cs = emit_xcs_breadcrumb(rq, __gen8_emit_flush_dw(cs, 0, 0, 0)); + return gen12_emit_fini_breadcrumb_tail(rq, cs); } static u32 * @@ -4991,7 +5005,7 @@ gen12_emit_fini_breadcrumb_rcs(struct i915_request *request, u32 *cs) { cs = gen12_emit_ggtt_write_rcs(cs, request->fence.seqno, - i915_request_active_timeline(request)->hwsp_offset, + hwsp_offset(request), PIPE_CONTROL0_HDC_PIPELINE_FLUSH, PIPE_CONTROL_CS_STALL | PIPE_CONTROL_TILE_CACHE_FLUSH | @@ -5412,44 +5426,90 @@ static struct list_head *virtual_queue(struct virtual_engine *ve) return &ve->base.execlists.default_priolist.requests[0]; } -static void virtual_context_destroy(struct kref *kref) +static void rcu_virtual_context_destroy(struct work_struct *wrk) { struct virtual_engine *ve = - container_of(kref, typeof(*ve), context.ref); + container_of(wrk, typeof(*ve), rcu.work); unsigned int n; - GEM_BUG_ON(!list_empty(virtual_queue(ve))); - GEM_BUG_ON(ve->request); GEM_BUG_ON(ve->context.inflight); + /* Preempt-to-busy may leave a stale request behind. */ + if (unlikely(ve->request)) { + struct i915_request *old; + + spin_lock_irq(&ve->base.active.lock); + + old = fetch_and_zero(&ve->request); + if (old) { + GEM_BUG_ON(!i915_request_completed(old)); + __i915_request_submit(old); + i915_request_put(old); + } + + spin_unlock_irq(&ve->base.active.lock); + } + + /* + * Flush the tasklet in case it is still running on another core. + * + * This needs to be done before we remove ourselves from the siblings' + * rbtrees as in the case it is running in parallel, it may reinsert + * the rb_node into a sibling. + */ + tasklet_kill(&ve->base.execlists.tasklet); + + /* Decouple ourselves from the siblings, no more access allowed. */ for (n = 0; n < ve->num_siblings; n++) { struct intel_engine_cs *sibling = ve->siblings[n]; struct rb_node *node = &ve->nodes[sibling->id].rb; - unsigned long flags; if (RB_EMPTY_NODE(node)) continue; - spin_lock_irqsave(&sibling->active.lock, flags); + spin_lock_irq(&sibling->active.lock); /* Detachment is lazily performed in the execlists tasklet */ if (!RB_EMPTY_NODE(node)) rb_erase_cached(node, &sibling->execlists.virtual); - spin_unlock_irqrestore(&sibling->active.lock, flags); + spin_unlock_irq(&sibling->active.lock); } GEM_BUG_ON(__tasklet_is_scheduled(&ve->base.execlists.tasklet)); + GEM_BUG_ON(!list_empty(virtual_queue(ve))); if (ve->context.state) __execlists_context_fini(&ve->context); intel_context_fini(&ve->context); + intel_breadcrumbs_free(ve->base.breadcrumbs); intel_engine_free_request_pool(&ve->base); kfree(ve->bonds); kfree(ve); } +static void virtual_context_destroy(struct kref *kref) +{ + struct virtual_engine *ve = + container_of(kref, typeof(*ve), context.ref); + + GEM_BUG_ON(!list_empty(&ve->context.signals)); + + /* + * When destroying the virtual engine, we have to be aware that + * it may still be in use from an hardirq/softirq context causing + * the resubmission of a completed request (background completion + * due to preempt-to-busy). Before we can free the engine, we need + * to flush the submission code and tasklets that are still potentially + * accessing the engine. Flushing the tasklets requires process context, + * and since we can guard the resubmit onto the engine with an RCU read + * lock, we can delegate the free of the engine to an RCU worker. + */ + INIT_RCU_WORK(&ve->rcu, rcu_virtual_context_destroy); + queue_rcu_work(system_wq, &ve->rcu); +} + static void virtual_engine_initial_hint(struct virtual_engine *ve) { int swp; diff --git a/drivers/gpu/drm/i915/gt/intel_mocs.c b/drivers/gpu/drm/i915/gt/intel_mocs.c index b8f56e62158e..313e51e7d4f7 100644 --- a/drivers/gpu/drm/i915/gt/intel_mocs.c +++ b/drivers/gpu/drm/i915/gt/intel_mocs.c @@ -243,8 +243,9 @@ static const struct drm_i915_mocs_entry tgl_mocs_table[] = { * only, __init_mocs_table() take care to program unused index with * this entry. */ - MOCS_ENTRY(1, LE_3_WB | LE_TC_1_LLC | LE_LRUM(3), - L3_3_WB), + MOCS_ENTRY(I915_MOCS_PTE, + LE_0_PAGETABLE | LE_TC_0_PAGETABLE, + L3_1_UC), GEN11_MOCS_ENTRIES, /* Implicitly enable L1 - HDC:L1 + L3 + LLC */ diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.c b/drivers/gpu/drm/i915/gt/intel_rc6.c index ab675d35030d..d7b8e4457fc2 100644 --- a/drivers/gpu/drm/i915/gt/intel_rc6.c +++ b/drivers/gpu/drm/i915/gt/intel_rc6.c @@ -56,9 +56,12 @@ static inline void set(struct intel_uncore *uncore, i915_reg_t reg, u32 val) static void gen11_rc6_enable(struct intel_rc6 *rc6) { - struct intel_uncore *uncore = rc6_to_uncore(rc6); + struct intel_gt *gt = rc6_to_gt(rc6); + struct intel_uncore *uncore = gt->uncore; struct intel_engine_cs *engine; enum intel_engine_id id; + u32 pg_enable; + int i; /* 2b: Program RC6 thresholds.*/ set(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 54 << 16 | 85); @@ -102,10 +105,19 @@ static void gen11_rc6_enable(struct intel_rc6 *rc6) GEN6_RC_CTL_RC6_ENABLE | GEN6_RC_CTL_EI_MODE(1); - set(uncore, GEN9_PG_ENABLE, - GEN9_RENDER_PG_ENABLE | - GEN9_MEDIA_PG_ENABLE | - GEN11_MEDIA_SAMPLER_PG_ENABLE); + pg_enable = + GEN9_RENDER_PG_ENABLE | + GEN9_MEDIA_PG_ENABLE | + GEN11_MEDIA_SAMPLER_PG_ENABLE; + + if (INTEL_GEN(gt->i915) >= 12) { + for (i = 0; i < I915_MAX_VCS; i++) + if (HAS_ENGINE(gt, _VCS(i))) + pg_enable |= (VDN_HCP_POWERGATE_ENABLE(i) | + VDN_MFX_POWERGATE_ENABLE(i)); + } + + set(uncore, GEN9_PG_ENABLE, pg_enable); } static void gen9_rc6_enable(struct intel_rc6 *rc6) diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c index a2f74cefe4c3..7ea94d201fe6 100644 --- a/drivers/gpu/drm/i915/gt/intel_timeline.c +++ b/drivers/gpu/drm/i915/gt/intel_timeline.c @@ -188,10 +188,14 @@ cacheline_alloc(struct intel_timeline_hwsp *hwsp, unsigned int cacheline) return cl; } -static void cacheline_acquire(struct intel_timeline_cacheline *cl) +static void cacheline_acquire(struct intel_timeline_cacheline *cl, + u32 ggtt_offset) { - if (cl) - i915_active_acquire(&cl->active); + if (!cl) + return; + + cl->ggtt_offset = ggtt_offset; + i915_active_acquire(&cl->active); } static void cacheline_release(struct intel_timeline_cacheline *cl) @@ -340,7 +344,7 @@ int intel_timeline_pin(struct intel_timeline *tl, struct i915_gem_ww_ctx *ww) GT_TRACE(tl->gt, "timeline:%llx using HWSP offset:%x\n", tl->fence_context, tl->hwsp_offset); - cacheline_acquire(tl->hwsp_cacheline); + cacheline_acquire(tl->hwsp_cacheline, tl->hwsp_offset); if (atomic_fetch_inc(&tl->pin_count)) { cacheline_release(tl->hwsp_cacheline); __i915_vma_unpin(tl->hwsp_ggtt); @@ -515,7 +519,7 @@ __intel_timeline_get_seqno(struct intel_timeline *tl, GT_TRACE(tl->gt, "timeline:%llx using HWSP offset:%x\n", tl->fence_context, tl->hwsp_offset); - cacheline_acquire(cl); + cacheline_acquire(cl, tl->hwsp_offset); tl->hwsp_cacheline = cl; *seqno = timeline_advance(tl); @@ -573,9 +577,7 @@ int intel_timeline_read_hwsp(struct i915_request *from, if (err) goto out; - *hwsp = i915_ggtt_offset(cl->hwsp->vma) + - ptr_unmask_bits(cl->vaddr, CACHELINE_BITS) * CACHELINE_BYTES; - + *hwsp = cl->ggtt_offset; out: i915_active_release(&cl->active); return err; diff --git a/drivers/gpu/drm/i915/gt/intel_timeline_types.h b/drivers/gpu/drm/i915/gt/intel_timeline_types.h index 02181c5020db..4474f487f589 100644 --- a/drivers/gpu/drm/i915/gt/intel_timeline_types.h +++ b/drivers/gpu/drm/i915/gt/intel_timeline_types.h @@ -94,6 +94,8 @@ struct intel_timeline_cacheline { struct intel_timeline_hwsp *hwsp; void *vaddr; + u32 ggtt_offset; + struct rcu_head rcu; }; diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index 6c580d0d9ea8..4a3bde7c9f21 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -131,8 +131,10 @@ static void _wa_add(struct i915_wa_list *wal, const struct i915_wa *wa) return; } - if (wal->list) + if (wal->list) { memcpy(list, wal->list, sizeof(*wa) * wal->count); + kfree(wal->list); + } wal->list = list; } diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c index 7ba16ddfe75f..d7898e87791f 100644 --- a/drivers/gpu/drm/i915/gvt/display.c +++ b/drivers/gpu/drm/i915/gvt/display.c @@ -164,7 +164,7 @@ static unsigned char virtual_dp_monitor_edid[GVT_EDID_NUM][EDID_SIZE] = { /* let the virtual display supports DP1.2 */ static u8 dpcd_fix_data[DPCD_HEADER_SIZE] = { - 0x12, 0x014, 0x04, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 + 0x12, 0x014, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }; static void emulate_monitor_status_change(struct intel_vgpu *vgpu) diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h index 9831361f181e..a81cf0f01e78 100644 --- a/drivers/gpu/drm/i915/gvt/gvt.h +++ b/drivers/gpu/drm/i915/gvt/gvt.h @@ -255,7 +255,7 @@ struct intel_gvt_mmio { #define F_CMD_ACCESS (1 << 3) /* This reg has been accessed by a VM */ #define F_ACCESSED (1 << 4) -/* This reg has been accessed through GPU commands */ +/* This reg could be accessed by unaligned address */ #define F_UNALIGN (1 << 6) /* This reg is in GVT's mmio save-restor list and in hardware * logical context image diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index 3be37e6fe33d..eb342a759943 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -1489,7 +1489,8 @@ static int hws_pga_write(struct intel_vgpu *vgpu, unsigned int offset, const struct intel_engine_cs *engine = intel_gvt_render_mmio_to_engine(vgpu->gvt, offset); - if (!intel_gvt_ggtt_validate_range(vgpu, value, I915_GTT_PAGE_SIZE)) { + if (value != 0 && + !intel_gvt_ggtt_validate_range(vgpu, value, I915_GTT_PAGE_SIZE)) { gvt_vgpu_err("write invalid HWSP address, reg:0x%x, value:0x%x\n", offset, value); return -EINVAL; @@ -1650,6 +1651,34 @@ static int edp_psr_imr_iir_write(struct intel_vgpu *vgpu, return 0; } +/** + * FixMe: + * If guest fills non-priv batch buffer on ApolloLake/Broxton as Mesa i965 did: + * 717e7539124d (i965: Use a WC map and memcpy for the batch instead of pwrite.) + * Due to the missing flush of bb filled by VM vCPU, host GPU hangs on executing + * these MI_BATCH_BUFFER. + * Temporarily workaround this by setting SNOOP bit for PAT3 used by PPGTT + * PML4 PTE: PAT(0) PCD(1) PWT(1). + * The performance is still expected to be low, will need further improvement. + */ +static int bxt_ppat_low_write(struct intel_vgpu *vgpu, unsigned int offset, + void *p_data, unsigned int bytes) +{ + u64 pat = + GEN8_PPAT(0, CHV_PPAT_SNOOP) | + GEN8_PPAT(1, 0) | + GEN8_PPAT(2, 0) | + GEN8_PPAT(3, CHV_PPAT_SNOOP) | + GEN8_PPAT(4, CHV_PPAT_SNOOP) | + GEN8_PPAT(5, CHV_PPAT_SNOOP) | + GEN8_PPAT(6, CHV_PPAT_SNOOP) | + GEN8_PPAT(7, CHV_PPAT_SNOOP); + + vgpu_vreg(vgpu, offset) = lower_32_bits(pat); + + return 0; +} + static int guc_status_read(struct intel_vgpu *vgpu, unsigned int offset, void *p_data, unsigned int bytes) @@ -2812,7 +2841,7 @@ static int init_bdw_mmio_info(struct intel_gvt *gvt) MMIO_DH(GEN6_PCODE_MAILBOX, D_BDW_PLUS, NULL, mailbox_write); - MMIO_D(GEN8_PRIVATE_PAT_LO, D_BDW_PLUS); + MMIO_D(GEN8_PRIVATE_PAT_LO, D_BDW_PLUS & ~D_BXT); MMIO_D(GEN8_PRIVATE_PAT_HI, D_BDW_PLUS); MMIO_D(GAMTARBMODE, D_BDW_PLUS); @@ -3139,7 +3168,7 @@ static int init_skl_mmio_info(struct intel_gvt *gvt) NULL, NULL); MMIO_DFH(GAMT_CHKN_BIT_REG, D_KBL | D_CFL, F_CMD_ACCESS, NULL, NULL); - MMIO_D(GEN9_CTX_PREEMPT_REG, D_SKL_PLUS); + MMIO_D(GEN9_CTX_PREEMPT_REG, D_SKL_PLUS & ~D_BXT); return 0; } @@ -3313,9 +3342,21 @@ static int init_bxt_mmio_info(struct intel_gvt *gvt) MMIO_D(GEN8_PUSHBUS_SHIFT, D_BXT); MMIO_D(GEN6_GFXPAUSE, D_BXT); MMIO_DFH(GEN8_L3SQCREG1, D_BXT, F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(GEN8_L3CNTLREG, D_BXT, F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(_MMIO(0x20D8), D_BXT, F_CMD_ACCESS, NULL, NULL); + MMIO_F(GEN8_RING_CS_GPR(RENDER_RING_BASE, 0), 0x40, F_CMD_ACCESS, + 0, 0, D_BXT, NULL, NULL); + MMIO_F(GEN8_RING_CS_GPR(GEN6_BSD_RING_BASE, 0), 0x40, F_CMD_ACCESS, + 0, 0, D_BXT, NULL, NULL); + MMIO_F(GEN8_RING_CS_GPR(BLT_RING_BASE, 0), 0x40, F_CMD_ACCESS, + 0, 0, D_BXT, NULL, NULL); + MMIO_F(GEN8_RING_CS_GPR(VEBOX_RING_BASE, 0), 0x40, F_CMD_ACCESS, + 0, 0, D_BXT, NULL, NULL); MMIO_DFH(GEN9_CTX_PREEMPT_REG, D_BXT, F_CMD_ACCESS, NULL, NULL); + MMIO_DH(GEN8_PRIVATE_PAT_LO, D_BXT, NULL, bxt_ppat_low_write); + return 0; } diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index ad8a9df49f29..778eb8cab610 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -829,8 +829,10 @@ static int intel_vgpu_open(struct mdev_device *mdev) /* Take a module reference as mdev core doesn't take * a reference for vendor driver. */ - if (!try_module_get(THIS_MODULE)) + if (!try_module_get(THIS_MODULE)) { + ret = -ENODEV; goto undo_group; + } ret = kvmgt_guest_init(mdev); if (ret) diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index 1570eb8aa978..aed2ef6466a2 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -1277,7 +1277,7 @@ void intel_vgpu_clean_submission(struct intel_vgpu *vgpu) i915_context_ppgtt_root_restore(s, i915_vm_to_ppgtt(s->shadow[0]->vm)); for_each_engine(engine, vgpu->gvt->gt, id) - intel_context_unpin(s->shadow[id]); + intel_context_put(s->shadow[id]); kmem_cache_destroy(s->workloads); } @@ -1369,11 +1369,6 @@ int intel_vgpu_setup_submission(struct intel_vgpu *vgpu) ce->ring = __intel_context_ring_size(ring_size); } - ret = intel_context_pin(ce); - intel_context_put(ce); - if (ret) - goto out_shadow_ctx; - s->shadow[i] = ce; } @@ -1405,7 +1400,6 @@ out_shadow_ctx: if (IS_ERR(s->shadow[i])) break; - intel_context_unpin(s->shadow[i]); intel_context_put(s->shadow[i]); } i915_vm_put(&ppgtt->vm); @@ -1479,6 +1473,7 @@ void intel_vgpu_destroy_workload(struct intel_vgpu_workload *workload) { struct intel_vgpu_submission *s = &workload->vgpu->submission; + intel_context_unpin(s->shadow[workload->engine->id]); release_shadow_batch_buffer(workload); release_shadow_wa_ctx(&workload->wa_ctx); @@ -1724,6 +1719,12 @@ intel_vgpu_create_workload(struct intel_vgpu *vgpu, return ERR_PTR(ret); } + ret = intel_context_pin(s->shadow[engine->id]); + if (ret) { + intel_vgpu_destroy_workload(workload); + return ERR_PTR(ret); + } + return workload; } diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c index f6d7e33c7099..399582aeeefb 100644 --- a/drivers/gpu/drm/i915/gvt/vgpu.c +++ b/drivers/gpu/drm/i915/gvt/vgpu.c @@ -439,7 +439,8 @@ static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt, if (IS_BROADWELL(dev_priv)) ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_B); - else + /* FixMe: Re-enable APL/BXT once vfio_edid enabled */ + else if (!IS_BROXTON(dev_priv)) ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_D); if (ret) goto out_clean_sched_policy; diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index bb0c12975f38..58276694c848 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -180,30 +180,6 @@ try_again: } static int -i915_gem_phys_pwrite(struct drm_i915_gem_object *obj, - struct drm_i915_gem_pwrite *args, - struct drm_file *file) -{ - void *vaddr = sg_page(obj->mm.pages->sgl) + args->offset; - char __user *user_data = u64_to_user_ptr(args->data_ptr); - - /* - * We manually control the domain here and pretend that it - * remains coherent i.e. in the GTT domain, like shmem_pwrite. - */ - i915_gem_object_invalidate_frontbuffer(obj, ORIGIN_CPU); - - if (copy_from_user(vaddr, user_data, args->size)) - return -EFAULT; - - drm_clflush_virt_range(vaddr, args->size); - intel_gt_chipset_flush(&to_i915(obj->base.dev)->gt); - - i915_gem_object_flush_frontbuffer(obj, ORIGIN_CPU); - return 0; -} - -static int i915_gem_create(struct drm_file *file, struct intel_memory_region *mr, u64 *size_p, @@ -527,6 +503,12 @@ i915_gem_pread_ioctl(struct drm_device *dev, void *data, trace_i915_gem_object_pread(obj, args->offset, args->size); + ret = -ENODEV; + if (obj->ops->pread) + ret = obj->ops->pread(obj, args); + if (ret != -ENODEV) + goto out; + ret = i915_gem_object_wait(obj, I915_WAIT_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); @@ -866,8 +848,6 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data, if (ret == -EFAULT || ret == -ENOSPC) { if (i915_gem_object_has_struct_page(obj)) ret = i915_gem_shmem_pwrite(obj, args); - else - ret = i915_gem_phys_pwrite(obj, args, file); } i915_gem_object_unpin_pages(obj); diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index e94976976571..3640d0e229d2 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -909,8 +909,13 @@ static int gen8_oa_read(struct i915_perf_stream *stream, DRM_I915_PERF_RECORD_OA_REPORT_LOST); if (ret) return ret; - intel_uncore_write(uncore, oastatus_reg, - oastatus & ~GEN8_OASTATUS_REPORT_LOST); + + intel_uncore_rmw(uncore, oastatus_reg, + GEN8_OASTATUS_COUNTER_OVERFLOW | + GEN8_OASTATUS_REPORT_LOST, + IS_GEN_RANGE(uncore->i915, 8, 10) ? + (GEN8_OASTATUS_HEAD_POINTER_WRAP | + GEN8_OASTATUS_TAIL_POINTER_WRAP) : 0); } return gen8_append_oa_reports(stream, buf, count, offset); diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index d805d4da6181..5cd83eac940c 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -676,6 +676,8 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define GEN7_OASTATUS2_MEM_SELECT_GGTT (1 << 0) /* 0: PPGTT, 1: GGTT */ #define GEN8_OASTATUS _MMIO(0x2b08) +#define GEN8_OASTATUS_TAIL_POINTER_WRAP (1 << 17) +#define GEN8_OASTATUS_HEAD_POINTER_WRAP (1 << 16) #define GEN8_OASTATUS_OVERRUN_STATUS (1 << 3) #define GEN8_OASTATUS_COUNTER_OVERFLOW (1 << 2) #define GEN8_OASTATUS_OABUFFER_OVERFLOW (1 << 1) @@ -8971,10 +8973,6 @@ enum { #define GEN9_PWRGT_MEDIA_STATUS_MASK (1 << 0) #define GEN9_PWRGT_RENDER_STATUS_MASK (1 << 1) -#define POWERGATE_ENABLE _MMIO(0xa210) -#define VDN_HCP_POWERGATE_ENABLE(n) BIT(((n) * 2) + 3) -#define VDN_MFX_POWERGATE_ENABLE(n) BIT(((n) * 2) + 4) - #define GTFIFODBG _MMIO(0x120000) #define GT_FIFO_SBDEDICATE_FREE_ENTRY_CHV (0x1f << 20) #define GT_FIFO_FREE_ENTRIES_CHV (0x7f << 13) @@ -9114,9 +9112,11 @@ enum { #define GEN9_MEDIA_PG_IDLE_HYSTERESIS _MMIO(0xA0C4) #define GEN9_RENDER_PG_IDLE_HYSTERESIS _MMIO(0xA0C8) #define GEN9_PG_ENABLE _MMIO(0xA210) -#define GEN9_RENDER_PG_ENABLE REG_BIT(0) -#define GEN9_MEDIA_PG_ENABLE REG_BIT(1) -#define GEN11_MEDIA_SAMPLER_PG_ENABLE REG_BIT(2) +#define GEN9_RENDER_PG_ENABLE REG_BIT(0) +#define GEN9_MEDIA_PG_ENABLE REG_BIT(1) +#define GEN11_MEDIA_SAMPLER_PG_ENABLE REG_BIT(2) +#define VDN_HCP_POWERGATE_ENABLE(n) REG_BIT(3 + 2 * (n)) +#define VDN_MFX_POWERGATE_ENABLE(n) REG_BIT(4 + 2 * (n)) #define GEN8_PUSHBUS_CONTROL _MMIO(0xA248) #define GEN8_PUSHBUS_ENABLE _MMIO(0xA250) #define GEN8_PUSHBUS_SHIFT _MMIO(0xA25C) diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h index 16b721080195..874af6db6103 100644 --- a/drivers/gpu/drm/i915/i915_request.h +++ b/drivers/gpu/drm/i915/i915_request.h @@ -176,7 +176,11 @@ struct i915_request { struct intel_context *context; struct intel_ring *ring; struct intel_timeline __rcu *timeline; - struct list_head signal_link; + + union { + struct list_head signal_link; + struct llist_node signal_node; + }; /* * The rcu epoch of when this request was allocated. Used to judiciously diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index ffb5287e055a..caa9b041616b 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -314,8 +314,10 @@ static void __vma_release(struct dma_fence_work *work) { struct i915_vma_work *vw = container_of(work, typeof(*vw), base); - if (vw->pinned) + if (vw->pinned) { __i915_gem_object_unpin_pages(vw->pinned); + i915_gem_object_put(vw->pinned); + } i915_vm_free_pt_stash(vw->vm, &vw->stash); i915_vm_put(vw->vm); @@ -431,7 +433,7 @@ int i915_vma_bind(struct i915_vma *vma, if (vma->obj) { __i915_gem_object_pin_pages(vma->obj); - work->pinned = vma->obj; + work->pinned = i915_gem_object_get(vma->obj); } } else { vma->ops->bind_vma(vma->vm, NULL, vma, cache_level, bind_flags); diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 34e0d22d456b..cfb806767fc5 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -7118,23 +7118,10 @@ static void icl_init_clock_gating(struct drm_i915_private *dev_priv) static void tgl_init_clock_gating(struct drm_i915_private *dev_priv) { - u32 vd_pg_enable = 0; - unsigned int i; - /* Wa_1409120013:tgl */ I915_WRITE(ILK_DPFC_CHICKEN, ILK_DPFC_CHICKEN_COMP_DUMMY_PIXEL); - /* This is not a WA. Enable VD HCP & MFX_ENC powergate */ - for (i = 0; i < I915_MAX_VCS; i++) { - if (HAS_ENGINE(&dev_priv->gt, _VCS(i))) - vd_pg_enable |= VDN_HCP_POWERGATE_ENABLE(i) | - VDN_MFX_POWERGATE_ENABLE(i); - } - - I915_WRITE(POWERGATE_ENABLE, - I915_READ(POWERGATE_ENABLE) | vd_pg_enable); - /* Wa_1409825376:tgl (pre-prod)*/ if (IS_TGL_DISP_REVID(dev_priv, TGL_REVID_A0, TGL_REVID_B1)) I915_WRITE(GEN9_CLKGATE_DIS_3, I915_READ(GEN9_CLKGATE_DIS_3) | diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c index 64bbb8288249..e424a6d1a68c 100644 --- a/drivers/gpu/drm/i915/selftests/i915_request.c +++ b/drivers/gpu/drm/i915/selftests/i915_request.c @@ -2293,8 +2293,10 @@ static int perf_request_latency(void *arg) struct intel_context *ce; ce = intel_context_create(engine); - if (IS_ERR(ce)) + if (IS_ERR(ce)) { + err = PTR_ERR(ce); goto out; + } err = intel_context_pin(ce); if (err) { @@ -2467,8 +2469,10 @@ static int perf_series_engines(void *arg) struct intel_context *ce; ce = intel_context_create(engine); - if (IS_ERR(ce)) + if (IS_ERR(ce)) { + err = PTR_ERR(ce); goto out; + } err = intel_context_pin(ce); if (err) { diff --git a/drivers/gpu/drm/imx/dw_hdmi-imx.c b/drivers/gpu/drm/imx/dw_hdmi-imx.c index 71d84c7a5378..d07b39b8afd2 100644 --- a/drivers/gpu/drm/imx/dw_hdmi-imx.c +++ b/drivers/gpu/drm/imx/dw_hdmi-imx.c @@ -111,10 +111,6 @@ static int dw_hdmi_imx_parse_dt(struct imx_hdmi *hdmi) return 0; } -static void dw_hdmi_imx_encoder_disable(struct drm_encoder *encoder) -{ -} - static void dw_hdmi_imx_encoder_enable(struct drm_encoder *encoder) { struct imx_hdmi *hdmi = enc_to_imx_hdmi(encoder); @@ -140,7 +136,6 @@ static int dw_hdmi_imx_atomic_check(struct drm_encoder *encoder, static const struct drm_encoder_helper_funcs dw_hdmi_imx_encoder_helper_funcs = { .enable = dw_hdmi_imx_encoder_enable, - .disable = dw_hdmi_imx_encoder_disable, .atomic_check = dw_hdmi_imx_atomic_check, }; @@ -219,15 +214,9 @@ static int dw_hdmi_imx_bind(struct device *dev, struct device *master, hdmi->dev = &pdev->dev; encoder = &hdmi->encoder; - encoder->possible_crtcs = drm_of_find_possible_crtcs(drm, dev->of_node); - /* - * If we failed to find the CRTC(s) which this encoder is - * supposed to be connected to, it's because the CRTC has - * not been registered yet. Defer probing, and hope that - * the required CRTC is added later. - */ - if (encoder->possible_crtcs == 0) - return -EPROBE_DEFER; + ret = imx_drm_encoder_parse_of(drm, encoder, dev->of_node); + if (ret) + return ret; ret = dw_hdmi_imx_parse_dt(hdmi); if (ret < 0) diff --git a/drivers/gpu/drm/imx/imx-drm-core.c b/drivers/gpu/drm/imx/imx-drm-core.c index 7d00c49fd5a5..9bf5ad6d18a2 100644 --- a/drivers/gpu/drm/imx/imx-drm-core.c +++ b/drivers/gpu/drm/imx/imx-drm-core.c @@ -20,6 +20,7 @@ #include <drm/drm_fb_helper.h> #include <drm/drm_gem_cma_helper.h> #include <drm/drm_gem_framebuffer_helper.h> +#include <drm/drm_managed.h> #include <drm/drm_of.h> #include <drm/drm_plane_helper.h> #include <drm/drm_probe_helper.h> @@ -212,7 +213,9 @@ static int imx_drm_bind(struct device *dev) drm->mode_config.allow_fb_modifiers = true; drm->mode_config.normalize_zpos = true; - drm_mode_config_init(drm); + ret = drmm_mode_config_init(drm); + if (ret) + return ret; ret = drm_vblank_init(drm, MAX_CRTC); if (ret) @@ -251,7 +254,6 @@ err_poll_fini: drm_kms_helper_poll_fini(drm); component_unbind_all(drm->dev, drm); err_kms: - drm_mode_config_cleanup(drm); drm_dev_put(drm); return ret; @@ -267,11 +269,9 @@ static void imx_drm_unbind(struct device *dev) component_unbind_all(drm->dev, drm); - drm_mode_config_cleanup(drm); + drm_dev_put(drm); dev_set_drvdata(dev, NULL); - - drm_dev_put(drm); } static const struct component_master_ops imx_drm_ops = { diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c index af757d1e21fe..41e2978cb1eb 100644 --- a/drivers/gpu/drm/imx/imx-ldb.c +++ b/drivers/gpu/drm/imx/imx-ldb.c @@ -62,7 +62,6 @@ struct imx_ldb_channel { struct i2c_adapter *ddc; int chno; void *edid; - int edid_len; struct drm_display_mode mode; int mode_valid; u32 bus_format; @@ -536,15 +535,14 @@ static int imx_ldb_panel_ddc(struct device *dev, } if (!channel->ddc) { + int edid_len; + /* if no DDC available, fallback to hardcoded EDID */ dev_dbg(dev, "no ddc available\n"); - edidp = of_get_property(child, "edid", - &channel->edid_len); + edidp = of_get_property(child, "edid", &edid_len); if (edidp) { - channel->edid = kmemdup(edidp, - channel->edid_len, - GFP_KERNEL); + channel->edid = kmemdup(edidp, edid_len, GFP_KERNEL); } else if (!channel->panel) { /* fallback to display-timings node */ ret = of_get_drm_display_mode(child, diff --git a/drivers/gpu/drm/imx/imx-tve.c b/drivers/gpu/drm/imx/imx-tve.c index 813bb6156a68..2a8d2e32e7b4 100644 --- a/drivers/gpu/drm/imx/imx-tve.c +++ b/drivers/gpu/drm/imx/imx-tve.c @@ -13,7 +13,6 @@ #include <linux/platform_device.h> #include <linux/regmap.h> #include <linux/regulator/consumer.h> -#include <linux/spinlock.h> #include <linux/videodev2.h> #include <video/imx-ipu-v3.h> @@ -104,8 +103,6 @@ struct imx_tve { struct drm_connector connector; struct drm_encoder encoder; struct device *dev; - spinlock_t lock; /* register lock */ - bool enabled; int mode; int di_hsync_pin; int di_vsync_pin; @@ -129,30 +126,10 @@ static inline struct imx_tve *enc_to_tve(struct drm_encoder *e) return container_of(e, struct imx_tve, encoder); } -static void tve_lock(void *__tve) -__acquires(&tve->lock) -{ - struct imx_tve *tve = __tve; - - spin_lock(&tve->lock); -} - -static void tve_unlock(void *__tve) -__releases(&tve->lock) -{ - struct imx_tve *tve = __tve; - - spin_unlock(&tve->lock); -} - static void tve_enable(struct imx_tve *tve) { - if (!tve->enabled) { - tve->enabled = true; - clk_prepare_enable(tve->clk); - regmap_update_bits(tve->regmap, TVE_COM_CONF_REG, - TVE_EN, TVE_EN); - } + clk_prepare_enable(tve->clk); + regmap_update_bits(tve->regmap, TVE_COM_CONF_REG, TVE_EN, TVE_EN); /* clear interrupt status register */ regmap_write(tve->regmap, TVE_STAT_REG, 0xffffffff); @@ -169,11 +146,8 @@ static void tve_enable(struct imx_tve *tve) static void tve_disable(struct imx_tve *tve) { - if (tve->enabled) { - tve->enabled = false; - regmap_update_bits(tve->regmap, TVE_COM_CONF_REG, TVE_EN, 0); - clk_disable_unprepare(tve->clk); - } + regmap_update_bits(tve->regmap, TVE_COM_CONF_REG, TVE_EN, 0); + clk_disable_unprepare(tve->clk); } static int tve_setup_tvout(struct imx_tve *tve) @@ -500,8 +474,7 @@ static struct regmap_config tve_regmap_config = { .readable_reg = imx_tve_readable_reg, - .lock = tve_lock, - .unlock = tve_unlock, + .fast_io = true, .max_register = 0xdc, }; @@ -511,7 +484,7 @@ static const char * const imx_tve_modes[] = { [TVE_MODE_VGA] = "vga", }; -static const int of_get_tve_mode(struct device_node *np) +static int of_get_tve_mode(struct device_node *np) { const char *bm; int ret, i; @@ -544,7 +517,6 @@ static int imx_tve_bind(struct device *dev, struct device *master, void *data) memset(tve, 0, sizeof(*tve)); tve->dev = dev; - spin_lock_init(&tve->lock); ddc_node = of_parse_phandle(np, "ddc-i2c-bus", 0); if (ddc_node) { diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c index 8232f512b9ed..2eb8df4697df 100644 --- a/drivers/gpu/drm/imx/parallel-display.c +++ b/drivers/gpu/drm/imx/parallel-display.c @@ -28,7 +28,6 @@ struct imx_parallel_display { struct drm_bridge bridge; struct device *dev; void *edid; - int edid_len; u32 bus_format; u32 bus_flags; struct drm_display_mode mode; @@ -41,11 +40,6 @@ static inline struct imx_parallel_display *con_to_imxpd(struct drm_connector *c) return container_of(c, struct imx_parallel_display, connector); } -static inline struct imx_parallel_display *enc_to_imxpd(struct drm_encoder *e) -{ - return container_of(e, struct imx_parallel_display, encoder); -} - static inline struct imx_parallel_display *bridge_to_imxpd(struct drm_bridge *b) { return container_of(b, struct imx_parallel_display, bridge); @@ -310,6 +304,7 @@ static int imx_pd_bind(struct device *dev, struct device *master, void *data) struct device_node *np = dev->of_node; const u8 *edidp; struct imx_parallel_display *imxpd; + int edid_len; int ret; u32 bus_format = 0; const char *fmt; @@ -323,9 +318,9 @@ static int imx_pd_bind(struct device *dev, struct device *master, void *data) if (ret && ret != -ENODEV) return ret; - edidp = of_get_property(np, "edid", &imxpd->edid_len); + edidp = of_get_property(np, "edid", &edid_len); if (edidp) - imxpd->edid = kmemdup(edidp, imxpd->edid_len, GFP_KERNEL); + imxpd->edid = devm_kmemdup(dev, edidp, edid_len, GFP_KERNEL); ret = of_property_read_string(np, "interface-pix-fmt", &fmt); if (!ret) { @@ -349,17 +344,8 @@ static int imx_pd_bind(struct device *dev, struct device *master, void *data) return 0; } -static void imx_pd_unbind(struct device *dev, struct device *master, - void *data) -{ - struct imx_parallel_display *imxpd = dev_get_drvdata(dev); - - kfree(imxpd->edid); -} - static const struct component_ops imx_pd_ops = { .bind = imx_pd_bind, - .unbind = imx_pd_unbind, }; static int imx_pd_probe(struct platform_device *pdev) diff --git a/drivers/gpu/drm/mediatek/mtk_dpi.c b/drivers/gpu/drm/mediatek/mtk_dpi.c index cf11c4850b40..52f11a63a330 100644 --- a/drivers/gpu/drm/mediatek/mtk_dpi.c +++ b/drivers/gpu/drm/mediatek/mtk_dpi.c @@ -522,15 +522,6 @@ static int mtk_dpi_set_display_mode(struct mtk_dpi *dpi, return 0; } -static void mtk_dpi_encoder_destroy(struct drm_encoder *encoder) -{ - drm_encoder_cleanup(encoder); -} - -static const struct drm_encoder_funcs mtk_dpi_encoder_funcs = { - .destroy = mtk_dpi_encoder_destroy, -}; - static int mtk_dpi_bridge_attach(struct drm_bridge *bridge, enum drm_bridge_attach_flags flags) { diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c index 4a188a942c38..65fd99c528af 100644 --- a/drivers/gpu/drm/mediatek/mtk_dsi.c +++ b/drivers/gpu/drm/mediatek/mtk_dsi.c @@ -444,7 +444,10 @@ static void mtk_dsi_config_vdo_timing(struct mtk_dsi *dsi) u32 horizontal_sync_active_byte; u32 horizontal_backporch_byte; u32 horizontal_frontporch_byte; + u32 horizontal_front_back_byte; + u32 data_phy_cycles_byte; u32 dsi_tmp_buf_bpp, data_phy_cycles; + u32 delta; struct mtk_phy_timing *timing = &dsi->phy_timing; struct videomode *vm = &dsi->vm; @@ -466,50 +469,30 @@ static void mtk_dsi_config_vdo_timing(struct mtk_dsi *dsi) horizontal_sync_active_byte = (vm->hsync_len * dsi_tmp_buf_bpp - 10); if (dsi->mode_flags & MIPI_DSI_MODE_VIDEO_SYNC_PULSE) - horizontal_backporch_byte = vm->hback_porch * dsi_tmp_buf_bpp; + horizontal_backporch_byte = vm->hback_porch * dsi_tmp_buf_bpp - 10; else horizontal_backporch_byte = (vm->hback_porch + vm->hsync_len) * - dsi_tmp_buf_bpp; + dsi_tmp_buf_bpp - 10; data_phy_cycles = timing->lpx + timing->da_hs_prepare + - timing->da_hs_zero + timing->da_hs_exit; - - if (dsi->mode_flags & MIPI_DSI_MODE_VIDEO_BURST) { - if ((vm->hfront_porch + vm->hback_porch) * dsi_tmp_buf_bpp > - data_phy_cycles * dsi->lanes + 18) { - horizontal_frontporch_byte = - vm->hfront_porch * dsi_tmp_buf_bpp - - (data_phy_cycles * dsi->lanes + 18) * - vm->hfront_porch / - (vm->hfront_porch + vm->hback_porch); - - horizontal_backporch_byte = - horizontal_backporch_byte - - (data_phy_cycles * dsi->lanes + 18) * - vm->hback_porch / - (vm->hfront_porch + vm->hback_porch); - } else { - DRM_WARN("HFP less than d-phy, FPS will under 60Hz\n"); - horizontal_frontporch_byte = vm->hfront_porch * - dsi_tmp_buf_bpp; - } + timing->da_hs_zero + timing->da_hs_exit + 3; + + delta = dsi->mode_flags & MIPI_DSI_MODE_VIDEO_BURST ? 18 : 12; + + horizontal_frontporch_byte = vm->hfront_porch * dsi_tmp_buf_bpp; + horizontal_front_back_byte = horizontal_frontporch_byte + horizontal_backporch_byte; + data_phy_cycles_byte = data_phy_cycles * dsi->lanes + delta; + + if (horizontal_front_back_byte > data_phy_cycles_byte) { + horizontal_frontporch_byte -= data_phy_cycles_byte * + horizontal_frontporch_byte / + horizontal_front_back_byte; + + horizontal_backporch_byte -= data_phy_cycles_byte * + horizontal_backporch_byte / + horizontal_front_back_byte; } else { - if ((vm->hfront_porch + vm->hback_porch) * dsi_tmp_buf_bpp > - data_phy_cycles * dsi->lanes + 12) { - horizontal_frontporch_byte = - vm->hfront_porch * dsi_tmp_buf_bpp - - (data_phy_cycles * dsi->lanes + 12) * - vm->hfront_porch / - (vm->hfront_porch + vm->hback_porch); - horizontal_backporch_byte = horizontal_backporch_byte - - (data_phy_cycles * dsi->lanes + 12) * - vm->hback_porch / - (vm->hfront_porch + vm->hback_porch); - } else { - DRM_WARN("HFP less than d-phy, FPS will under 60Hz\n"); - horizontal_frontporch_byte = vm->hfront_porch * - dsi_tmp_buf_bpp; - } + DRM_WARN("HFP + HBP less than d-phy, FPS will under 60Hz\n"); } writel(horizontal_sync_active_byte, dsi->regs + DSI_HSA_WC); diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index b111fe24a06b..36d6b6093d16 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -455,7 +455,7 @@ nv50_outp_get_old_connector(struct nouveau_encoder *outp, * DAC *****************************************************************************/ static void -nv50_dac_disable(struct drm_encoder *encoder) +nv50_dac_disable(struct drm_encoder *encoder, struct drm_atomic_state *state) { struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); struct nv50_core *core = nv50_disp(encoder->dev)->core; @@ -467,7 +467,7 @@ nv50_dac_disable(struct drm_encoder *encoder) } static void -nv50_dac_enable(struct drm_encoder *encoder) +nv50_dac_enable(struct drm_encoder *encoder, struct drm_atomic_state *state) { struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); struct nouveau_crtc *nv_crtc = nouveau_crtc(encoder->crtc); @@ -525,8 +525,8 @@ nv50_dac_detect(struct drm_encoder *encoder, struct drm_connector *connector) static const struct drm_encoder_helper_funcs nv50_dac_help = { .atomic_check = nv50_outp_atomic_check, - .enable = nv50_dac_enable, - .disable = nv50_dac_disable, + .atomic_enable = nv50_dac_enable, + .atomic_disable = nv50_dac_disable, .detect = nv50_dac_detect }; @@ -1055,7 +1055,7 @@ nv50_dp_bpc_to_depth(unsigned int bpc) } static void -nv50_msto_enable(struct drm_encoder *encoder) +nv50_msto_enable(struct drm_encoder *encoder, struct drm_atomic_state *state) { struct nv50_head *head = nv50_head(encoder->crtc); struct nv50_head_atom *armh = nv50_head_atom(head->base.base.state); @@ -1101,7 +1101,7 @@ nv50_msto_enable(struct drm_encoder *encoder) } static void -nv50_msto_disable(struct drm_encoder *encoder) +nv50_msto_disable(struct drm_encoder *encoder, struct drm_atomic_state *state) { struct nv50_msto *msto = nv50_msto(encoder); struct nv50_mstc *mstc = msto->mstc; @@ -1118,8 +1118,8 @@ nv50_msto_disable(struct drm_encoder *encoder) static const struct drm_encoder_helper_funcs nv50_msto_help = { - .disable = nv50_msto_disable, - .enable = nv50_msto_enable, + .atomic_disable = nv50_msto_disable, + .atomic_enable = nv50_msto_enable, .atomic_check = nv50_msto_atomic_check, }; @@ -1645,8 +1645,7 @@ nv50_sor_disable(struct drm_encoder *encoder, } static void -nv50_sor_enable(struct drm_encoder *encoder, - struct drm_atomic_state *state) +nv50_sor_enable(struct drm_encoder *encoder, struct drm_atomic_state *state) { struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); struct nouveau_crtc *nv_crtc = nouveau_crtc(encoder->crtc); @@ -1873,7 +1872,7 @@ nv50_pior_atomic_check(struct drm_encoder *encoder, } static void -nv50_pior_disable(struct drm_encoder *encoder) +nv50_pior_disable(struct drm_encoder *encoder, struct drm_atomic_state *state) { struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); struct nv50_core *core = nv50_disp(encoder->dev)->core; @@ -1885,7 +1884,7 @@ nv50_pior_disable(struct drm_encoder *encoder) } static void -nv50_pior_enable(struct drm_encoder *encoder) +nv50_pior_enable(struct drm_encoder *encoder, struct drm_atomic_state *state) { struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); struct nouveau_crtc *nv_crtc = nouveau_crtc(encoder->crtc); @@ -1921,14 +1920,14 @@ nv50_pior_enable(struct drm_encoder *encoder) } core->func->pior->ctrl(core, nv_encoder->or, ctrl, asyh); - nv_encoder->crtc = encoder->crtc; + nv_encoder->crtc = &nv_crtc->base; } static const struct drm_encoder_helper_funcs nv50_pior_help = { .atomic_check = nv50_pior_atomic_check, - .enable = nv50_pior_enable, - .disable = nv50_pior_disable, + .atomic_enable = nv50_pior_enable, + .atomic_disable = nv50_pior_disable, }; static void diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 2ee75646ad6f..56b335a55966 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -350,14 +350,13 @@ set_placement_list(struct nouveau_drm *drm, struct ttm_place *pl, unsigned *n, if (domain & NOUVEAU_GEM_DOMAIN_VRAM) { struct nvif_mmu *mmu = &drm->client.mmu; - const u8 type = mmu->type[drm->ttm.type_vram].type; pl[*n].mem_type = TTM_PL_VRAM; pl[*n].flags = flags & ~TTM_PL_FLAG_CACHED; /* Some BARs do not support being ioremapped WC */ if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_TESLA && - type & NVIF_MEM_UNCACHED) + mmu->type[drm->ttm.type_vram].type & NVIF_MEM_UNCACHED) pl[*n].flags &= ~TTM_PL_FLAG_WC; (*n)++; diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c index 6f21f36719fc..8b4b3688c7ae 100644 --- a/drivers/gpu/drm/nouveau/nouveau_connector.c +++ b/drivers/gpu/drm/nouveau/nouveau_connector.c @@ -532,11 +532,13 @@ static void nouveau_connector_set_edid(struct nouveau_connector *nv_connector, struct edid *edid) { - struct edid *old_edid = nv_connector->edid; + if (nv_connector->edid != edid) { + struct edid *old_edid = nv_connector->edid; - drm_connector_update_edid_property(&nv_connector->base, edid); - kfree(old_edid); - nv_connector->edid = edid; + drm_connector_update_edid_property(&nv_connector->base, edid); + kfree(old_edid); + nv_connector->edid = edid; + } } static enum drm_connector_status @@ -669,8 +671,10 @@ nouveau_connector_detect_lvds(struct drm_connector *connector, bool force) /* Try retrieving EDID via DDC */ if (!drm->vbios.fp_no_ddc) { status = nouveau_connector_detect(connector, force); - if (status == connector_status_connected) + if (status == connector_status_connected) { + edid = nv_connector->edid; goto out; + } } /* On some laptops (Sony, i'm looking at you) there appears to diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c index b3dae9ec1a38..d166ee262ce4 100644 --- a/drivers/gpu/ipu-v3/ipu-common.c +++ b/drivers/gpu/ipu-v3/ipu-common.c @@ -133,73 +133,6 @@ enum ipu_color_space ipu_pixelformat_to_colorspace(u32 pixelformat) } EXPORT_SYMBOL_GPL(ipu_pixelformat_to_colorspace); -bool ipu_pixelformat_is_planar(u32 pixelformat) -{ - switch (pixelformat) { - case V4L2_PIX_FMT_YUV420: - case V4L2_PIX_FMT_YVU420: - case V4L2_PIX_FMT_YUV422P: - case V4L2_PIX_FMT_NV12: - case V4L2_PIX_FMT_NV21: - case V4L2_PIX_FMT_NV16: - case V4L2_PIX_FMT_NV61: - return true; - } - - return false; -} -EXPORT_SYMBOL_GPL(ipu_pixelformat_is_planar); - -enum ipu_color_space ipu_mbus_code_to_colorspace(u32 mbus_code) -{ - switch (mbus_code & 0xf000) { - case 0x1000: - return IPUV3_COLORSPACE_RGB; - case 0x2000: - return IPUV3_COLORSPACE_YUV; - default: - return IPUV3_COLORSPACE_UNKNOWN; - } -} -EXPORT_SYMBOL_GPL(ipu_mbus_code_to_colorspace); - -int ipu_stride_to_bytes(u32 pixel_stride, u32 pixelformat) -{ - switch (pixelformat) { - case V4L2_PIX_FMT_YUV420: - case V4L2_PIX_FMT_YVU420: - case V4L2_PIX_FMT_YUV422P: - case V4L2_PIX_FMT_NV12: - case V4L2_PIX_FMT_NV21: - case V4L2_PIX_FMT_NV16: - case V4L2_PIX_FMT_NV61: - /* - * for the planar YUV formats, the stride passed to - * cpmem must be the stride in bytes of the Y plane. - * And all the planar YUV formats have an 8-bit - * Y component. - */ - return (8 * pixel_stride) >> 3; - case V4L2_PIX_FMT_RGB565: - case V4L2_PIX_FMT_YUYV: - case V4L2_PIX_FMT_UYVY: - return (16 * pixel_stride) >> 3; - case V4L2_PIX_FMT_BGR24: - case V4L2_PIX_FMT_RGB24: - return (24 * pixel_stride) >> 3; - case V4L2_PIX_FMT_BGR32: - case V4L2_PIX_FMT_RGB32: - case V4L2_PIX_FMT_XBGR32: - case V4L2_PIX_FMT_XRGB32: - return (32 * pixel_stride) >> 3; - default: - break; - } - - return -EINVAL; -} -EXPORT_SYMBOL_GPL(ipu_stride_to_bytes); - int ipu_degrees_to_rot_mode(enum ipu_rotate_mode *mode, int degrees, bool hflip, bool vflip) { diff --git a/drivers/hid/hid-cypress.c b/drivers/hid/hid-cypress.c index a50ba4a4a1d7..b88f889b3932 100644 --- a/drivers/hid/hid-cypress.c +++ b/drivers/hid/hid-cypress.c @@ -23,19 +23,17 @@ #define CP_2WHEEL_MOUSE_HACK 0x02 #define CP_2WHEEL_MOUSE_HACK_ON 0x04 +#define VA_INVAL_LOGICAL_BOUNDARY 0x08 + /* * Some USB barcode readers from cypress have usage min and usage max in * the wrong order */ -static __u8 *cp_report_fixup(struct hid_device *hdev, __u8 *rdesc, +static __u8 *cp_rdesc_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { - unsigned long quirks = (unsigned long)hid_get_drvdata(hdev); unsigned int i; - if (!(quirks & CP_RDESC_SWAPPED_MIN_MAX)) - return rdesc; - if (*rsize < 4) return rdesc; @@ -48,6 +46,40 @@ static __u8 *cp_report_fixup(struct hid_device *hdev, __u8 *rdesc, return rdesc; } +static __u8 *va_logical_boundary_fixup(struct hid_device *hdev, __u8 *rdesc, + unsigned int *rsize) +{ + /* + * Varmilo VA104M (with VID Cypress and device ID 07B1) incorrectly + * reports Logical Minimum of its Consumer Control device as 572 + * (0x02 0x3c). Fix this by setting its Logical Minimum to zero. + */ + if (*rsize == 25 && + rdesc[0] == 0x05 && rdesc[1] == 0x0c && + rdesc[2] == 0x09 && rdesc[3] == 0x01 && + rdesc[6] == 0x19 && rdesc[7] == 0x00 && + rdesc[11] == 0x16 && rdesc[12] == 0x3c && rdesc[13] == 0x02) { + hid_info(hdev, + "fixing up varmilo VA104M consumer control report descriptor\n"); + rdesc[12] = 0x00; + rdesc[13] = 0x00; + } + return rdesc; +} + +static __u8 *cp_report_fixup(struct hid_device *hdev, __u8 *rdesc, + unsigned int *rsize) +{ + unsigned long quirks = (unsigned long)hid_get_drvdata(hdev); + + if (quirks & CP_RDESC_SWAPPED_MIN_MAX) + rdesc = cp_rdesc_fixup(hdev, rdesc, rsize); + if (quirks & VA_INVAL_LOGICAL_BOUNDARY) + rdesc = va_logical_boundary_fixup(hdev, rdesc, rsize); + + return rdesc; +} + static int cp_input_mapped(struct hid_device *hdev, struct hid_input *hi, struct hid_field *field, struct hid_usage *usage, unsigned long **bit, int *max) @@ -128,6 +160,8 @@ static const struct hid_device_id cp_devices[] = { .driver_data = CP_RDESC_SWAPPED_MIN_MAX }, { HID_USB_DEVICE(USB_VENDOR_ID_CYPRESS, USB_DEVICE_ID_CYPRESS_MOUSE), .driver_data = CP_2WHEEL_MOUSE_HACK }, + { HID_USB_DEVICE(USB_VENDOR_ID_CYPRESS, USB_DEVICE_ID_CYPRESS_VARMILO_VA104M_07B1), + .driver_data = VA_INVAL_LOGICAL_BOUNDARY }, { } }; MODULE_DEVICE_TABLE(hid, cp_devices); diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index d69842f79fc6..f170feaac40b 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -331,6 +331,8 @@ #define USB_DEVICE_ID_CYPRESS_BARCODE_4 0xed81 #define USB_DEVICE_ID_CYPRESS_TRUETOUCH 0xc001 +#define USB_DEVICE_ID_CYPRESS_VARMILO_VA104M_07B1 0X07b1 + #define USB_VENDOR_ID_DATA_MODUL 0x7374 #define USB_VENDOR_ID_DATA_MODUL_EASYMAXTOUCH 0x1201 @@ -443,6 +445,10 @@ #define USB_VENDOR_ID_FRUCTEL 0x25B6 #define USB_DEVICE_ID_GAMETEL_MT_MODE 0x0002 +#define USB_VENDOR_ID_GAMEVICE 0x27F8 +#define USB_DEVICE_ID_GAMEVICE_GV186 0x0BBE +#define USB_DEVICE_ID_GAMEVICE_KISHI 0x0BBF + #define USB_VENDOR_ID_GAMERON 0x0810 #define USB_DEVICE_ID_GAMERON_DUAL_PSX_ADAPTOR 0x0001 #define USB_DEVICE_ID_GAMERON_DUAL_PCS_ADAPTOR 0x0002 @@ -485,6 +491,7 @@ #define USB_DEVICE_ID_PENPOWER 0x00f4 #define USB_VENDOR_ID_GREENASIA 0x0e8f +#define USB_DEVICE_ID_GREENASIA_DUAL_SAT_ADAPTOR 0x3010 #define USB_DEVICE_ID_GREENASIA_DUAL_USB_JOYPAD 0x3013 #define USB_VENDOR_ID_GRETAGMACBETH 0x0971 @@ -743,6 +750,7 @@ #define USB_VENDOR_ID_LOGITECH 0x046d #define USB_DEVICE_ID_LOGITECH_AUDIOHUB 0x0a0e #define USB_DEVICE_ID_LOGITECH_T651 0xb00c +#define USB_DEVICE_ID_LOGITECH_DINOVO_EDGE_KBD 0xb309 #define USB_DEVICE_ID_LOGITECH_C007 0xc007 #define USB_DEVICE_ID_LOGITECH_C077 0xc077 #define USB_DEVICE_ID_LOGITECH_RECEIVER 0xc101 @@ -1298,6 +1306,7 @@ #define USB_VENDOR_ID_UGTIZER 0x2179 #define USB_DEVICE_ID_UGTIZER_TABLET_GP0610 0x0053 +#define USB_DEVICE_ID_UGTIZER_TABLET_GT5040 0x0077 #define USB_VENDOR_ID_VIEWSONIC 0x0543 #define USB_DEVICE_ID_VIEWSONIC_PD1011 0xe621 diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index 9770db624bfa..4dca11392459 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -319,6 +319,9 @@ static const struct hid_device_id hid_battery_quirks[] = { { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_ASUSTEK, USB_DEVICE_ID_ASUSTEK_T100CHI_KEYBOARD), HID_BATTERY_QUIRK_IGNORE }, + { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, + USB_DEVICE_ID_LOGITECH_DINOVO_EDGE_KBD), + HID_BATTERY_QUIRK_IGNORE }, {} }; diff --git a/drivers/hid/hid-ite.c b/drivers/hid/hid-ite.c index 044a93f3c117..742c052b0110 100644 --- a/drivers/hid/hid-ite.c +++ b/drivers/hid/hid-ite.c @@ -11,6 +11,48 @@ #include "hid-ids.h" +#define QUIRK_TOUCHPAD_ON_OFF_REPORT BIT(0) + +static __u8 *ite_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) +{ + unsigned long quirks = (unsigned long)hid_get_drvdata(hdev); + + if (quirks & QUIRK_TOUCHPAD_ON_OFF_REPORT) { + if (*rsize == 188 && rdesc[162] == 0x81 && rdesc[163] == 0x02) { + hid_info(hdev, "Fixing up ITE keyboard report descriptor\n"); + rdesc[163] = HID_MAIN_ITEM_RELATIVE; + } + } + + return rdesc; +} + +static int ite_input_mapping(struct hid_device *hdev, + struct hid_input *hi, struct hid_field *field, + struct hid_usage *usage, unsigned long **bit, + int *max) +{ + + unsigned long quirks = (unsigned long)hid_get_drvdata(hdev); + + if ((quirks & QUIRK_TOUCHPAD_ON_OFF_REPORT) && + (usage->hid & HID_USAGE_PAGE) == 0x00880000) { + if (usage->hid == 0x00880078) { + /* Touchpad on, userspace expects F22 for this */ + hid_map_usage_clear(hi, usage, bit, max, EV_KEY, KEY_F22); + return 1; + } + if (usage->hid == 0x00880079) { + /* Touchpad off, userspace expects F23 for this */ + hid_map_usage_clear(hi, usage, bit, max, EV_KEY, KEY_F23); + return 1; + } + return -1; + } + + return 0; +} + static int ite_event(struct hid_device *hdev, struct hid_field *field, struct hid_usage *usage, __s32 value) { @@ -37,13 +79,27 @@ static int ite_event(struct hid_device *hdev, struct hid_field *field, return 0; } +static int ite_probe(struct hid_device *hdev, const struct hid_device_id *id) +{ + int ret; + + hid_set_drvdata(hdev, (void *)id->driver_data); + + ret = hid_open_report(hdev); + if (ret) + return ret; + + return hid_hw_start(hdev, HID_CONNECT_DEFAULT); +} + static const struct hid_device_id ite_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_ITE, USB_DEVICE_ID_ITE8595) }, { HID_USB_DEVICE(USB_VENDOR_ID_258A, USB_DEVICE_ID_258A_6A88) }, /* ITE8595 USB kbd ctlr, with Synaptics touchpad connected to it. */ { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_SYNAPTICS, - USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_012) }, + USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_012), + .driver_data = QUIRK_TOUCHPAD_ON_OFF_REPORT }, /* ITE8910 USB kbd ctlr, with Synaptics touchpad connected to it. */ { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_SYNAPTICS, @@ -55,6 +111,9 @@ MODULE_DEVICE_TABLE(hid, ite_devices); static struct hid_driver ite_driver = { .name = "itetech", .id_table = ite_devices, + .probe = ite_probe, + .report_fixup = ite_report_fixup, + .input_mapping = ite_input_mapping, .event = ite_event, }; module_hid_driver(ite_driver); diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c index 72fb6e54a50a..1ffcfc9a1e03 100644 --- a/drivers/hid/hid-logitech-dj.c +++ b/drivers/hid/hid-logitech-dj.c @@ -328,7 +328,7 @@ static const char mse_bluetooth_descriptor[] = { 0x25, 0x01, /* LOGICAL_MAX (1) */ 0x75, 0x01, /* REPORT_SIZE (1) */ 0x95, 0x04, /* REPORT_COUNT (4) */ - 0x81, 0x06, /* INPUT */ + 0x81, 0x02, /* INPUT (Data,Var,Abs) */ 0xC0, /* END_COLLECTION */ 0xC0, /* END_COLLECTION */ }; @@ -866,11 +866,24 @@ static void logi_dj_recv_queue_notification(struct dj_receiver_dev *djrcv_dev, schedule_work(&djrcv_dev->work); } +/* + * Some quad/bluetooth keyboards have a builtin touchpad in this case we see + * only 1 paired device with a device_type of REPORT_TYPE_KEYBOARD. For the + * touchpad to work we must also forward mouse input reports to the dj_hiddev + * created for the keyboard (instead of forwarding them to a second paired + * device with a device_type of REPORT_TYPE_MOUSE as we normally would). + */ +static const u16 kbd_builtin_touchpad_ids[] = { + 0xb309, /* Dinovo Edge */ + 0xb30c, /* Dinovo Mini */ +}; + static void logi_hidpp_dev_conn_notif_equad(struct hid_device *hdev, struct hidpp_event *hidpp_report, struct dj_workitem *workitem) { struct dj_receiver_dev *djrcv_dev = hid_get_drvdata(hdev); + int i, id; workitem->type = WORKITEM_TYPE_PAIRED; workitem->device_type = hidpp_report->params[HIDPP_PARAM_DEVICE_INFO] & @@ -882,6 +895,13 @@ static void logi_hidpp_dev_conn_notif_equad(struct hid_device *hdev, workitem->reports_supported |= STD_KEYBOARD | MULTIMEDIA | POWER_KEYS | MEDIA_CENTER | HIDPP; + id = (workitem->quad_id_msb << 8) | workitem->quad_id_lsb; + for (i = 0; i < ARRAY_SIZE(kbd_builtin_touchpad_ids); i++) { + if (id == kbd_builtin_touchpad_ids[i]) { + workitem->reports_supported |= STD_MOUSE; + break; + } + } break; case REPORT_TYPE_MOUSE: workitem->reports_supported |= STD_MOUSE | HIDPP; diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index b8b53dc95e86..0ca723119547 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -93,6 +93,8 @@ MODULE_PARM_DESC(disable_tap_to_click, #define HIDPP_CAPABILITY_BATTERY_LEVEL_STATUS BIT(3) #define HIDPP_CAPABILITY_BATTERY_VOLTAGE BIT(4) +#define lg_map_key_clear(c) hid_map_usage_clear(hi, usage, bit, max, EV_KEY, (c)) + /* * There are two hidpp protocols in use, the first version hidpp10 is known * as register access protocol or RAP, the second version hidpp20 is known as @@ -2951,6 +2953,26 @@ static int g920_get_config(struct hidpp_device *hidpp, } /* -------------------------------------------------------------------------- */ +/* Logitech Dinovo Mini keyboard with builtin touchpad */ +/* -------------------------------------------------------------------------- */ +#define DINOVO_MINI_PRODUCT_ID 0xb30c + +static int lg_dinovo_input_mapping(struct hid_device *hdev, struct hid_input *hi, + struct hid_field *field, struct hid_usage *usage, + unsigned long **bit, int *max) +{ + if ((usage->hid & HID_USAGE_PAGE) != HID_UP_LOGIVENDOR) + return 0; + + switch (usage->hid & HID_USAGE) { + case 0x00d: lg_map_key_clear(KEY_MEDIA); break; + default: + return 0; + } + return 1; +} + +/* -------------------------------------------------------------------------- */ /* HID++1.0 devices which use HID++ reports for their wheels */ /* -------------------------------------------------------------------------- */ static int hidpp10_wheel_connect(struct hidpp_device *hidpp) @@ -3185,6 +3207,9 @@ static int hidpp_input_mapping(struct hid_device *hdev, struct hid_input *hi, field->application != HID_GD_MOUSE) return m560_input_mapping(hdev, hi, field, usage, bit, max); + if (hdev->product == DINOVO_MINI_PRODUCT_ID) + return lg_dinovo_input_mapping(hdev, hi, field, usage, bit, max); + return 0; } @@ -3947,6 +3972,7 @@ static const struct hid_device_id hidpp_devices[] = { LDJ_DEVICE(0x405e), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 }, { /* Mouse Logitech MX Anywhere 2 */ LDJ_DEVICE(0x404a), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 }, + { LDJ_DEVICE(0x4072), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 }, { LDJ_DEVICE(0xb013), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 }, { LDJ_DEVICE(0xb018), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 }, { LDJ_DEVICE(0xb01f), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 }, @@ -3971,6 +3997,9 @@ static const struct hid_device_id hidpp_devices[] = { { /* Keyboard MX5000 (Bluetooth-receiver in HID proxy mode) */ LDJ_DEVICE(0xb305), .driver_data = HIDPP_QUIRK_HIDPP_CONSUMER_VENDOR_KEYS }, + { /* Dinovo Edge (Bluetooth-receiver in HID proxy mode) */ + LDJ_DEVICE(0xb309), + .driver_data = HIDPP_QUIRK_HIDPP_CONSUMER_VENDOR_KEYS }, { /* Keyboard MX5500 (Bluetooth-receiver in HID proxy mode) */ LDJ_DEVICE(0xb30b), .driver_data = HIDPP_QUIRK_HIDPP_CONSUMER_VENDOR_KEYS }, @@ -4013,6 +4042,9 @@ static const struct hid_device_id hidpp_devices[] = { { /* MX5000 keyboard over Bluetooth */ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb305), .driver_data = HIDPP_QUIRK_HIDPP_CONSUMER_VENDOR_KEYS }, + { /* Dinovo Edge keyboard over Bluetooth */ + HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb309), + .driver_data = HIDPP_QUIRK_HIDPP_CONSUMER_VENDOR_KEYS }, { /* MX5500 keyboard over Bluetooth */ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb30b), .driver_data = HIDPP_QUIRK_HIDPP_CONSUMER_VENDOR_KEYS }, diff --git a/drivers/hid/hid-mcp2221.c b/drivers/hid/hid-mcp2221.c index 0d27ccb55dd9..4211b9839209 100644 --- a/drivers/hid/hid-mcp2221.c +++ b/drivers/hid/hid-mcp2221.c @@ -49,6 +49,36 @@ enum { MCP2221_ALT_F_NOT_GPIOD = 0xEF, }; +/* MCP GPIO direction encoding */ +enum { + MCP2221_DIR_OUT = 0x00, + MCP2221_DIR_IN = 0x01, +}; + +#define MCP_NGPIO 4 + +/* MCP GPIO set command layout */ +struct mcp_set_gpio { + u8 cmd; + u8 dummy; + struct { + u8 change_value; + u8 value; + u8 change_direction; + u8 direction; + } gpio[MCP_NGPIO]; +} __packed; + +/* MCP GPIO get command layout */ +struct mcp_get_gpio { + u8 cmd; + u8 dummy; + struct { + u8 direction; + u8 value; + } gpio[MCP_NGPIO]; +} __packed; + /* * There is no way to distinguish responses. Therefore next command * is sent only after response to previous has been received. Mutex @@ -542,7 +572,7 @@ static int mcp_gpio_get(struct gpio_chip *gc, mcp->txbuf[0] = MCP2221_GPIO_GET; - mcp->gp_idx = (offset + 1) * 2; + mcp->gp_idx = offsetof(struct mcp_get_gpio, gpio[offset].value); mutex_lock(&mcp->lock); ret = mcp_send_data_req_status(mcp, mcp->txbuf, 1); @@ -559,7 +589,7 @@ static void mcp_gpio_set(struct gpio_chip *gc, memset(mcp->txbuf, 0, 18); mcp->txbuf[0] = MCP2221_GPIO_SET; - mcp->gp_idx = ((offset + 1) * 4) - 1; + mcp->gp_idx = offsetof(struct mcp_set_gpio, gpio[offset].value); mcp->txbuf[mcp->gp_idx - 1] = 1; mcp->txbuf[mcp->gp_idx] = !!value; @@ -575,7 +605,7 @@ static int mcp_gpio_dir_set(struct mcp2221 *mcp, memset(mcp->txbuf, 0, 18); mcp->txbuf[0] = MCP2221_GPIO_SET; - mcp->gp_idx = (offset + 1) * 5; + mcp->gp_idx = offsetof(struct mcp_set_gpio, gpio[offset].direction); mcp->txbuf[mcp->gp_idx - 1] = 1; mcp->txbuf[mcp->gp_idx] = val; @@ -590,7 +620,7 @@ static int mcp_gpio_direction_input(struct gpio_chip *gc, struct mcp2221 *mcp = gpiochip_get_data(gc); mutex_lock(&mcp->lock); - ret = mcp_gpio_dir_set(mcp, offset, 0); + ret = mcp_gpio_dir_set(mcp, offset, MCP2221_DIR_IN); mutex_unlock(&mcp->lock); return ret; @@ -603,7 +633,7 @@ static int mcp_gpio_direction_output(struct gpio_chip *gc, struct mcp2221 *mcp = gpiochip_get_data(gc); mutex_lock(&mcp->lock); - ret = mcp_gpio_dir_set(mcp, offset, 1); + ret = mcp_gpio_dir_set(mcp, offset, MCP2221_DIR_OUT); mutex_unlock(&mcp->lock); /* Can't configure as output, bailout early */ @@ -623,7 +653,7 @@ static int mcp_gpio_get_direction(struct gpio_chip *gc, mcp->txbuf[0] = MCP2221_GPIO_GET; - mcp->gp_idx = (offset + 1) * 2; + mcp->gp_idx = offsetof(struct mcp_get_gpio, gpio[offset].direction); mutex_lock(&mcp->lock); ret = mcp_send_data_req_status(mcp, mcp->txbuf, 1); @@ -632,7 +662,7 @@ static int mcp_gpio_get_direction(struct gpio_chip *gc, if (ret) return ret; - if (mcp->gpio_dir) + if (mcp->gpio_dir == MCP2221_DIR_IN) return GPIO_LINE_DIRECTION_IN; return GPIO_LINE_DIRECTION_OUT; @@ -758,7 +788,7 @@ static int mcp2221_raw_event(struct hid_device *hdev, mcp->status = -ENOENT; } else { mcp->status = !!data[mcp->gp_idx]; - mcp->gpio_dir = !!data[mcp->gp_idx + 1]; + mcp->gpio_dir = data[mcp->gp_idx + 1]; } break; default: @@ -860,7 +890,7 @@ static int mcp2221_probe(struct hid_device *hdev, mcp->gc->get_direction = mcp_gpio_get_direction; mcp->gc->set = mcp_gpio_set; mcp->gc->get = mcp_gpio_get; - mcp->gc->ngpio = 4; + mcp->gc->ngpio = MCP_NGPIO; mcp->gc->base = -1; mcp->gc->can_sleep = 1; mcp->gc->parent = &hdev->dev; diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index 7a2be0205dfd..bf7ecab5d9e5 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -83,7 +83,12 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_FORMOSA, USB_DEVICE_ID_FORMOSA_IR_RECEIVER), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_FREESCALE, USB_DEVICE_ID_FREESCALE_MX28), HID_QUIRK_NOGET }, { HID_USB_DEVICE(USB_VENDOR_ID_FUTABA, USB_DEVICE_ID_LED_DISPLAY), HID_QUIRK_NO_INIT_REPORTS }, + { HID_USB_DEVICE(USB_VENDOR_ID_GREENASIA, USB_DEVICE_ID_GREENASIA_DUAL_SAT_ADAPTOR), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_GREENASIA, USB_DEVICE_ID_GREENASIA_DUAL_USB_JOYPAD), HID_QUIRK_MULTI_INPUT }, + { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_GAMEVICE, USB_DEVICE_ID_GAMEVICE_GV186), + HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE }, + { HID_USB_DEVICE(USB_VENDOR_ID_GAMEVICE, USB_DEVICE_ID_GAMEVICE_KISHI), + HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE }, { HID_USB_DEVICE(USB_VENDOR_ID_HAPP, USB_DEVICE_ID_UGCI_DRIVING), HID_QUIRK_BADPAD | HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_HAPP, USB_DEVICE_ID_UGCI_FIGHTING), HID_QUIRK_BADPAD | HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_HAPP, USB_DEVICE_ID_UGCI_FLYING), HID_QUIRK_BADPAD | HID_QUIRK_MULTI_INPUT }, diff --git a/drivers/hid/hid-sensor-hub.c b/drivers/hid/hid-sensor-hub.c index 94c7398b5c27..3dd7d3246737 100644 --- a/drivers/hid/hid-sensor-hub.c +++ b/drivers/hid/hid-sensor-hub.c @@ -483,7 +483,8 @@ static int sensor_hub_raw_event(struct hid_device *hdev, return 1; ptr = raw_data; - ptr++; /* Skip report id */ + if (report->id) + ptr++; /* Skip report id */ spin_lock_irqsave(&pdata->lock, flags); diff --git a/drivers/hid/hid-uclogic-core.c b/drivers/hid/hid-uclogic-core.c index 86b568037cb8..8e9c9e646cb7 100644 --- a/drivers/hid/hid-uclogic-core.c +++ b/drivers/hid/hid-uclogic-core.c @@ -385,6 +385,8 @@ static const struct hid_device_id uclogic_devices[] = { USB_DEVICE_ID_UCLOGIC_DRAWIMAGE_G3) }, { HID_USB_DEVICE(USB_VENDOR_ID_UGTIZER, USB_DEVICE_ID_UGTIZER_TABLET_GP0610) }, + { HID_USB_DEVICE(USB_VENDOR_ID_UGTIZER, + USB_DEVICE_ID_UGTIZER_TABLET_GT5040) }, { HID_USB_DEVICE(USB_VENDOR_ID_UGEE, USB_DEVICE_ID_UGEE_TABLET_G5) }, { HID_USB_DEVICE(USB_VENDOR_ID_UGEE, diff --git a/drivers/hid/hid-uclogic-params.c b/drivers/hid/hid-uclogic-params.c index 7d20d1fcf8d2..d26d8cd98efc 100644 --- a/drivers/hid/hid-uclogic-params.c +++ b/drivers/hid/hid-uclogic-params.c @@ -997,6 +997,8 @@ int uclogic_params_init(struct uclogic_params *params, break; case VID_PID(USB_VENDOR_ID_UGTIZER, USB_DEVICE_ID_UGTIZER_TABLET_GP0610): + case VID_PID(USB_VENDOR_ID_UGTIZER, + USB_DEVICE_ID_UGTIZER_TABLET_GT5040): case VID_PID(USB_VENDOR_ID_UGEE, USB_DEVICE_ID_UGEE_XPPEN_TABLET_G540): case VID_PID(USB_VENDOR_ID_UGEE, diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c index 786e3e9af1c9..aeff1ffb0c8b 100644 --- a/drivers/hid/i2c-hid/i2c-hid-core.c +++ b/drivers/hid/i2c-hid/i2c-hid-core.c @@ -943,6 +943,11 @@ static void i2c_hid_acpi_enable_wakeup(struct device *dev) } } +static void i2c_hid_acpi_shutdown(struct device *dev) +{ + acpi_device_set_power(ACPI_COMPANION(dev), ACPI_STATE_D3_COLD); +} + static const struct acpi_device_id i2c_hid_acpi_match[] = { {"ACPI0C50", 0 }, {"PNP0C50", 0 }, @@ -959,6 +964,8 @@ static inline int i2c_hid_acpi_pdata(struct i2c_client *client, static inline void i2c_hid_acpi_fix_up_power(struct device *dev) {} static inline void i2c_hid_acpi_enable_wakeup(struct device *dev) {} + +static inline void i2c_hid_acpi_shutdown(struct device *dev) {} #endif #ifdef CONFIG_OF @@ -1175,6 +1182,8 @@ static void i2c_hid_shutdown(struct i2c_client *client) i2c_hid_set_power(client, I2C_HID_PWR_SLEEP); free_irq(client->irq, ihid); + + i2c_hid_acpi_shutdown(&client->dev); } #ifdef CONFIG_PM_SLEEP diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c index 0cde10fe0e71..f202ac7f4b3d 100644 --- a/drivers/hv/hv.c +++ b/drivers/hv/hv.c @@ -244,9 +244,13 @@ int hv_synic_cleanup(unsigned int cpu) /* * Hyper-V does not provide a way to change the connect CPU once - * it is set; we must prevent the connect CPU from going offline. + * it is set; we must prevent the connect CPU from going offline + * while the VM is running normally. But in the panic or kexec() + * path where the vmbus is already disconnected, the CPU must be + * allowed to shut down. */ - if (cpu == VMBUS_CONNECT_CPU) + if (cpu == VMBUS_CONNECT_CPU && + vmbus_connection.conn_state == CONNECTED) return -EBUSY; /* diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c index b64d2efbefe7..eb56e09ae15f 100644 --- a/drivers/hv/hv_balloon.c +++ b/drivers/hv/hv_balloon.c @@ -1275,7 +1275,7 @@ static void balloon_up(struct work_struct *dummy) /* Refuse to balloon below the floor. */ if (avail_pages < num_pages || avail_pages - num_pages < floor) { - pr_warn("Balloon request will be partially fulfilled. %s\n", + pr_info("Balloon request will be partially fulfilled. %s\n", avail_pages < num_pages ? "Not enough memory." : "Balloon floor reached."); diff --git a/drivers/hwmon/amd_energy.c b/drivers/hwmon/amd_energy.c index d06597303d5a..3197cda7bcd9 100644 --- a/drivers/hwmon/amd_energy.c +++ b/drivers/hwmon/amd_energy.c @@ -171,7 +171,7 @@ static umode_t amd_energy_is_visible(const void *_data, enum hwmon_sensor_types type, u32 attr, int channel) { - return 0444; + return 0440; } static int energy_accumulator(void *p) diff --git a/drivers/hwmon/applesmc.c b/drivers/hwmon/applesmc.c index a18887990f4a..79b498f816fe 100644 --- a/drivers/hwmon/applesmc.c +++ b/drivers/hwmon/applesmc.c @@ -32,6 +32,7 @@ #include <linux/hwmon.h> #include <linux/workqueue.h> #include <linux/err.h> +#include <linux/bits.h> /* data port used by Apple SMC */ #define APPLESMC_DATA_PORT 0x300 @@ -42,10 +43,13 @@ #define APPLESMC_MAX_DATA_LENGTH 32 -/* wait up to 128 ms for a status change. */ -#define APPLESMC_MIN_WAIT 0x0010 -#define APPLESMC_RETRY_WAIT 0x0100 -#define APPLESMC_MAX_WAIT 0x20000 +/* Apple SMC status bits */ +#define SMC_STATUS_AWAITING_DATA BIT(0) /* SMC has data waiting to be read */ +#define SMC_STATUS_IB_CLOSED BIT(1) /* Will ignore any input */ +#define SMC_STATUS_BUSY BIT(2) /* Command in progress */ + +/* Initial wait is 8us */ +#define APPLESMC_MIN_WAIT 0x0008 #define APPLESMC_READ_CMD 0x10 #define APPLESMC_WRITE_CMD 0x11 @@ -151,65 +155,84 @@ static unsigned int key_at_index; static struct workqueue_struct *applesmc_led_wq; /* - * wait_read - Wait for a byte to appear on SMC port. Callers must - * hold applesmc_lock. + * Wait for specific status bits with a mask on the SMC. + * Used before all transactions. + * This does 10 fast loops of 8us then exponentially backs off for a + * minimum total wait of 262ms. Depending on usleep_range this could + * run out past 500ms. */ -static int wait_read(void) + +static int wait_status(u8 val, u8 mask) { - unsigned long end = jiffies + (APPLESMC_MAX_WAIT * HZ) / USEC_PER_SEC; u8 status; int us; + int i; - for (us = APPLESMC_MIN_WAIT; us < APPLESMC_MAX_WAIT; us <<= 1) { - usleep_range(us, us * 16); + us = APPLESMC_MIN_WAIT; + for (i = 0; i < 24 ; i++) { status = inb(APPLESMC_CMD_PORT); - /* read: wait for smc to settle */ - if (status & 0x01) + if ((status & mask) == val) return 0; - /* timeout: give up */ - if (time_after(jiffies, end)) - break; + usleep_range(us, us * 2); + if (i > 9) + us <<= 1; } - - pr_warn("wait_read() fail: 0x%02x\n", status); return -EIO; } -/* - * send_byte - Write to SMC port, retrying when necessary. Callers - * must hold applesmc_lock. - */ +/* send_byte - Write to SMC data port. Callers must hold applesmc_lock. */ + static int send_byte(u8 cmd, u16 port) { - u8 status; - int us; - unsigned long end = jiffies + (APPLESMC_MAX_WAIT * HZ) / USEC_PER_SEC; + int status; + + status = wait_status(0, SMC_STATUS_IB_CLOSED); + if (status) + return status; + /* + * This needs to be a separate read looking for bit 0x04 + * after bit 0x02 falls. If consolidated with the wait above + * this extra read may not happen if status returns both + * simultaneously and this would appear to be required. + */ + status = wait_status(SMC_STATUS_BUSY, SMC_STATUS_BUSY); + if (status) + return status; outb(cmd, port); - for (us = APPLESMC_MIN_WAIT; us < APPLESMC_MAX_WAIT; us <<= 1) { - usleep_range(us, us * 16); - status = inb(APPLESMC_CMD_PORT); - /* write: wait for smc to settle */ - if (status & 0x02) - continue; - /* ready: cmd accepted, return */ - if (status & 0x04) - return 0; - /* timeout: give up */ - if (time_after(jiffies, end)) - break; - /* busy: long wait and resend */ - udelay(APPLESMC_RETRY_WAIT); - outb(cmd, port); - } - - pr_warn("send_byte(0x%02x, 0x%04x) fail: 0x%02x\n", cmd, port, status); - return -EIO; + return 0; } +/* send_command - Write a command to the SMC. Callers must hold applesmc_lock. */ + static int send_command(u8 cmd) { - return send_byte(cmd, APPLESMC_CMD_PORT); + int ret; + + ret = wait_status(0, SMC_STATUS_IB_CLOSED); + if (ret) + return ret; + outb(cmd, APPLESMC_CMD_PORT); + return 0; +} + +/* + * Based on logic from the Apple driver. This is issued before any interaction + * If busy is stuck high, issue a read command to reset the SMC state machine. + * If busy is stuck high after the command then the SMC is jammed. + */ + +static int smc_sane(void) +{ + int ret; + + ret = wait_status(0, SMC_STATUS_BUSY); + if (!ret) + return ret; + ret = send_command(APPLESMC_READ_CMD); + if (ret) + return ret; + return wait_status(0, SMC_STATUS_BUSY); } static int send_argument(const char *key) @@ -226,6 +249,11 @@ static int read_smc(u8 cmd, const char *key, u8 *buffer, u8 len) { u8 status, data = 0; int i; + int ret; + + ret = smc_sane(); + if (ret) + return ret; if (send_command(cmd) || send_argument(key)) { pr_warn("%.4s: read arg fail\n", key); @@ -239,7 +267,8 @@ static int read_smc(u8 cmd, const char *key, u8 *buffer, u8 len) } for (i = 0; i < len; i++) { - if (wait_read()) { + if (wait_status(SMC_STATUS_AWAITING_DATA | SMC_STATUS_BUSY, + SMC_STATUS_AWAITING_DATA | SMC_STATUS_BUSY)) { pr_warn("%.4s: read data[%d] fail\n", key, i); return -EIO; } @@ -250,19 +279,24 @@ static int read_smc(u8 cmd, const char *key, u8 *buffer, u8 len) for (i = 0; i < 16; i++) { udelay(APPLESMC_MIN_WAIT); status = inb(APPLESMC_CMD_PORT); - if (!(status & 0x01)) + if (!(status & SMC_STATUS_AWAITING_DATA)) break; data = inb(APPLESMC_DATA_PORT); } if (i) pr_warn("flushed %d bytes, last value is: %d\n", i, data); - return 0; + return wait_status(0, SMC_STATUS_BUSY); } static int write_smc(u8 cmd, const char *key, const u8 *buffer, u8 len) { int i; + int ret; + + ret = smc_sane(); + if (ret) + return ret; if (send_command(cmd) || send_argument(key)) { pr_warn("%s: write arg fail\n", key); @@ -281,7 +315,7 @@ static int write_smc(u8 cmd, const char *key, const u8 *buffer, u8 len) } } - return 0; + return wait_status(0, SMC_STATUS_BUSY); } static int read_register_count(unsigned int *count) diff --git a/drivers/hwmon/pmbus/max20730.c b/drivers/hwmon/pmbus/max20730.c index 57923d72490c..be83b98411c7 100644 --- a/drivers/hwmon/pmbus/max20730.c +++ b/drivers/hwmon/pmbus/max20730.c @@ -122,8 +122,8 @@ static ssize_t max20730_debugfs_read(struct file *file, char __user *buf, switch (idx) { case MAX20730_DEBUGFS_VOUT_MIN: ret = VOLT_FROM_REG(data->mfr_voutmin * 10000); - len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d.%d\n", - ret / 10000, ret % 10000); + len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d.%d\n", + ret / 10000, ret % 10000); break; case MAX20730_DEBUGFS_FREQUENCY: val = (data->mfr_devset1 & MAX20730_MFR_DEVSET1_FSW_MASK) @@ -141,7 +141,7 @@ static ssize_t max20730_debugfs_read(struct file *file, char __user *buf, ret = 800; else ret = 900; - len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); + len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); break; case MAX20730_DEBUGFS_PG_DELAY: val = (data->mfr_devset1 & MAX20730_MFR_DEVSET1_TSTAT_MASK) @@ -223,7 +223,7 @@ static ssize_t max20730_debugfs_read(struct file *file, char __user *buf, case MAX20730_DEBUGFS_OC_PROTECT_MODE: ret = (data->mfr_devset2 & MAX20730_MFR_DEVSET2_OCPM_MASK) >> MAX20730_MFR_DEVSET2_OCPM_BIT_POS; - len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); + len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); break; case MAX20730_DEBUGFS_SS_TIMING: val = (data->mfr_devset2 & MAX20730_MFR_DEVSET2_SS_MASK) @@ -241,32 +241,32 @@ static ssize_t max20730_debugfs_read(struct file *file, char __user *buf, case MAX20730_DEBUGFS_IMAX: ret = (data->mfr_devset2 & MAX20730_MFR_DEVSET2_IMAX_MASK) >> MAX20730_MFR_DEVSET2_IMAX_BIT_POS; - len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); + len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); break; case MAX20730_DEBUGFS_OPERATION: ret = i2c_smbus_read_byte_data(psu->client, PMBUS_OPERATION); if (ret < 0) return ret; - len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); + len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); break; case MAX20730_DEBUGFS_ON_OFF_CONFIG: ret = i2c_smbus_read_byte_data(psu->client, PMBUS_ON_OFF_CONFIG); if (ret < 0) return ret; - len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); + len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); break; case MAX20730_DEBUGFS_SMBALERT_MASK: ret = i2c_smbus_read_word_data(psu->client, PMBUS_SMB_ALERT_MASK); if (ret < 0) return ret; - len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); + len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); break; case MAX20730_DEBUGFS_VOUT_MODE: ret = i2c_smbus_read_byte_data(psu->client, PMBUS_VOUT_MODE); if (ret < 0) return ret; - len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); + len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); break; case MAX20730_DEBUGFS_VOUT_COMMAND: ret = i2c_smbus_read_word_data(psu->client, PMBUS_VOUT_COMMAND); @@ -274,8 +274,8 @@ static ssize_t max20730_debugfs_read(struct file *file, char __user *buf, return ret; ret = VOLT_FROM_REG(ret * 10000); - len = snprintf(tbuf, DEBUG_FS_DATA_MAX, - "%d.%d\n", ret / 10000, ret % 10000); + len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, + "%d.%d\n", ret / 10000, ret % 10000); break; case MAX20730_DEBUGFS_VOUT_MAX: ret = i2c_smbus_read_word_data(psu->client, PMBUS_VOUT_MAX); @@ -283,8 +283,8 @@ static ssize_t max20730_debugfs_read(struct file *file, char __user *buf, return ret; ret = VOLT_FROM_REG(ret * 10000); - len = snprintf(tbuf, DEBUG_FS_DATA_MAX, - "%d.%d\n", ret / 10000, ret % 10000); + len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, + "%d.%d\n", ret / 10000, ret % 10000); break; default: len = strlcpy(tbuf, "Invalid\n", DEBUG_FS_DATA_MAX); diff --git a/drivers/hwmon/pmbus/pmbus_core.c b/drivers/hwmon/pmbus/pmbus_core.c index 170a9f82ca61..b0e2820a2d57 100644 --- a/drivers/hwmon/pmbus/pmbus_core.c +++ b/drivers/hwmon/pmbus/pmbus_core.c @@ -941,12 +941,16 @@ static ssize_t pmbus_show_sensor(struct device *dev, struct i2c_client *client = to_i2c_client(dev->parent); struct pmbus_sensor *sensor = to_pmbus_sensor(devattr); struct pmbus_data *data = i2c_get_clientdata(client); + ssize_t ret; + mutex_lock(&data->update_lock); pmbus_update_sensor_data(client, sensor); if (sensor->data < 0) - return sensor->data; - - return snprintf(buf, PAGE_SIZE, "%lld\n", pmbus_reg2data(data, sensor)); + ret = sensor->data; + else + ret = snprintf(buf, PAGE_SIZE, "%lld\n", pmbus_reg2data(data, sensor)); + mutex_unlock(&data->update_lock); + return ret; } static ssize_t pmbus_set_sensor(struct device *dev, @@ -2012,8 +2016,11 @@ static ssize_t pmbus_show_samples(struct device *dev, int val; struct i2c_client *client = to_i2c_client(dev->parent); struct pmbus_samples_reg *reg = to_samples_reg(devattr); + struct pmbus_data *data = i2c_get_clientdata(client); + mutex_lock(&data->update_lock); val = _pmbus_read_word_data(client, reg->page, 0xff, reg->attr->reg); + mutex_unlock(&data->update_lock); if (val < 0) return val; diff --git a/drivers/hwmon/pwm-fan.c b/drivers/hwmon/pwm-fan.c index bdba2143021a..1f63807c0399 100644 --- a/drivers/hwmon/pwm-fan.c +++ b/drivers/hwmon/pwm-fan.c @@ -54,16 +54,18 @@ static irqreturn_t pulse_handler(int irq, void *dev_id) static void sample_timer(struct timer_list *t) { struct pwm_fan_ctx *ctx = from_timer(ctx, t, rpm_timer); + unsigned int delta = ktime_ms_delta(ktime_get(), ctx->sample_start); int pulses; - u64 tmp; - pulses = atomic_read(&ctx->pulses); - atomic_sub(pulses, &ctx->pulses); - tmp = (u64)pulses * ktime_ms_delta(ktime_get(), ctx->sample_start) * 60; - do_div(tmp, ctx->pulses_per_revolution * 1000); - ctx->rpm = tmp; + if (delta) { + pulses = atomic_read(&ctx->pulses); + atomic_sub(pulses, &ctx->pulses); + ctx->rpm = (unsigned int)(pulses * 1000 * 60) / + (ctx->pulses_per_revolution * delta); + + ctx->sample_start = ktime_get(); + } - ctx->sample_start = ktime_get(); mod_timer(&ctx->rpm_timer, jiffies + HZ); } diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig index a4f473ef4e5c..a97a9d058198 100644 --- a/drivers/i2c/busses/Kconfig +++ b/drivers/i2c/busses/Kconfig @@ -733,7 +733,7 @@ config I2C_LPC2K config I2C_MLXBF tristate "Mellanox BlueField I2C controller" - depends on ARM64 + depends on MELLANOX_PLATFORM && ARM64 help Enabling this option will add I2C SMBus support for Mellanox BlueField system. diff --git a/drivers/i2c/busses/i2c-designware-slave.c b/drivers/i2c/busses/i2c-designware-slave.c index 44974b53a626..0d15f4c1e9f7 100644 --- a/drivers/i2c/busses/i2c-designware-slave.c +++ b/drivers/i2c/busses/i2c-designware-slave.c @@ -159,7 +159,6 @@ static int i2c_dw_irq_handler_slave(struct dw_i2c_dev *dev) u32 raw_stat, stat, enabled, tmp; u8 val = 0, slave_activity; - regmap_read(dev->map, DW_IC_INTR_STAT, &stat); regmap_read(dev->map, DW_IC_ENABLE, &enabled); regmap_read(dev->map, DW_IC_RAW_INTR_STAT, &raw_stat); regmap_read(dev->map, DW_IC_STATUS, &tmp); @@ -168,32 +167,30 @@ static int i2c_dw_irq_handler_slave(struct dw_i2c_dev *dev) if (!enabled || !(raw_stat & ~DW_IC_INTR_ACTIVITY) || !dev->slave) return 0; + stat = i2c_dw_read_clear_intrbits_slave(dev); dev_dbg(dev->dev, "%#x STATUS SLAVE_ACTIVITY=%#x : RAW_INTR_STAT=%#x : INTR_STAT=%#x\n", enabled, slave_activity, raw_stat, stat); - if ((stat & DW_IC_INTR_RX_FULL) && (stat & DW_IC_INTR_STOP_DET)) - i2c_slave_event(dev->slave, I2C_SLAVE_WRITE_REQUESTED, &val); + if (stat & DW_IC_INTR_RX_FULL) { + if (dev->status != STATUS_WRITE_IN_PROGRESS) { + dev->status = STATUS_WRITE_IN_PROGRESS; + i2c_slave_event(dev->slave, I2C_SLAVE_WRITE_REQUESTED, + &val); + } + + regmap_read(dev->map, DW_IC_DATA_CMD, &tmp); + val = tmp; + if (!i2c_slave_event(dev->slave, I2C_SLAVE_WRITE_RECEIVED, + &val)) + dev_vdbg(dev->dev, "Byte %X acked!", val); + } if (stat & DW_IC_INTR_RD_REQ) { if (slave_activity) { - if (stat & DW_IC_INTR_RX_FULL) { - regmap_read(dev->map, DW_IC_DATA_CMD, &tmp); - val = tmp; - - if (!i2c_slave_event(dev->slave, - I2C_SLAVE_WRITE_RECEIVED, - &val)) { - dev_vdbg(dev->dev, "Byte %X acked!", - val); - } - regmap_read(dev->map, DW_IC_CLR_RD_REQ, &tmp); - stat = i2c_dw_read_clear_intrbits_slave(dev); - } else { - regmap_read(dev->map, DW_IC_CLR_RD_REQ, &tmp); - regmap_read(dev->map, DW_IC_CLR_RX_UNDER, &tmp); - stat = i2c_dw_read_clear_intrbits_slave(dev); - } + regmap_read(dev->map, DW_IC_CLR_RD_REQ, &tmp); + + dev->status = STATUS_READ_IN_PROGRESS; if (!i2c_slave_event(dev->slave, I2C_SLAVE_READ_REQUESTED, &val)) @@ -205,21 +202,11 @@ static int i2c_dw_irq_handler_slave(struct dw_i2c_dev *dev) if (!i2c_slave_event(dev->slave, I2C_SLAVE_READ_PROCESSED, &val)) regmap_read(dev->map, DW_IC_CLR_RX_DONE, &tmp); - - i2c_slave_event(dev->slave, I2C_SLAVE_STOP, &val); - stat = i2c_dw_read_clear_intrbits_slave(dev); - return 1; } - if (stat & DW_IC_INTR_RX_FULL) { - regmap_read(dev->map, DW_IC_DATA_CMD, &tmp); - val = tmp; - if (!i2c_slave_event(dev->slave, I2C_SLAVE_WRITE_RECEIVED, - &val)) - dev_vdbg(dev->dev, "Byte %X acked!", val); - } else { + if (stat & DW_IC_INTR_STOP_DET) { + dev->status = STATUS_IDLE; i2c_slave_event(dev->slave, I2C_SLAVE_STOP, &val); - stat = i2c_dw_read_clear_intrbits_slave(dev); } return 1; @@ -230,7 +217,6 @@ static irqreturn_t i2c_dw_isr_slave(int this_irq, void *dev_id) struct dw_i2c_dev *dev = dev_id; int ret; - i2c_dw_read_clear_intrbits_slave(dev); ret = i2c_dw_irq_handler_slave(dev); if (ret > 0) complete(&dev->cmd_complete); diff --git a/drivers/i2c/busses/i2c-mlxbf.c b/drivers/i2c/busses/i2c-mlxbf.c index ee59e0da082d..33574d40ea9c 100644 --- a/drivers/i2c/busses/i2c-mlxbf.c +++ b/drivers/i2c/busses/i2c-mlxbf.c @@ -62,10 +62,8 @@ * Master. Default value is set to 400MHz. */ #define MLXBF_I2C_TYU_PLL_OUT_FREQ (400 * 1000 * 1000) -/* Reference clock for Bluefield 1 - 156 MHz. */ -#define MLXBF_I2C_TYU_PLL_IN_FREQ (156 * 1000 * 1000) -/* Reference clock for BlueField 2 - 200 MHz. */ -#define MLXBF_I2C_YU_PLL_IN_FREQ (200 * 1000 * 1000) +/* Reference clock for Bluefield - 156 MHz. */ +#define MLXBF_I2C_PLL_IN_FREQ (156 * 1000 * 1000) /* Constant used to determine the PLL frequency. */ #define MLNXBF_I2C_COREPLL_CONST 16384 @@ -489,44 +487,6 @@ static struct mutex mlxbf_i2c_bus_lock; #define MLXBF_I2C_FREQUENCY_1GHZ 1000000000 -static void mlxbf_i2c_write(void __iomem *io, int reg, u32 val) -{ - writel(val, io + reg); -} - -static u32 mlxbf_i2c_read(void __iomem *io, int reg) -{ - return readl(io + reg); -} - -/* - * This function is used to read data from Master GW Data Descriptor. - * Data bytes in the Master GW Data Descriptor are shifted left so the - * data starts at the MSB of the descriptor registers as set by the - * underlying hardware. TYU_READ_DATA enables byte swapping while - * reading data bytes, and MUST be called by the SMBus read routines - * to copy data from the 32 * 32-bit HW Data registers a.k.a Master GW - * Data Descriptor. - */ -static u32 mlxbf_i2c_read_data(void __iomem *io, int reg) -{ - return (u32)be32_to_cpu(mlxbf_i2c_read(io, reg)); -} - -/* - * This function is used to write data to the Master GW Data Descriptor. - * Data copied to the Master GW Data Descriptor MUST be shifted left so - * the data starts at the MSB of the descriptor registers as required by - * the underlying hardware. TYU_WRITE_DATA enables byte swapping when - * writing data bytes, and MUST be called by the SMBus write routines to - * copy data to the 32 * 32-bit HW Data registers a.k.a Master GW Data - * Descriptor. - */ -static void mlxbf_i2c_write_data(void __iomem *io, int reg, u32 val) -{ - mlxbf_i2c_write(io, reg, (u32)cpu_to_be32(val)); -} - /* * Function to poll a set of bits at a specific address; it checks whether * the bits are equal to zero when eq_zero is set to 'true', and not equal @@ -541,7 +501,7 @@ static u32 mlxbf_smbus_poll(void __iomem *io, u32 addr, u32 mask, timeout = (timeout / MLXBF_I2C_POLL_FREQ_IN_USEC) + 1; do { - bits = mlxbf_i2c_read(io, addr) & mask; + bits = readl(io + addr) & mask; if (eq_zero ? bits == 0 : bits != 0) return eq_zero ? 1 : bits; udelay(MLXBF_I2C_POLL_FREQ_IN_USEC); @@ -609,16 +569,16 @@ static int mlxbf_i2c_smbus_check_status(struct mlxbf_i2c_priv *priv) MLXBF_I2C_SMBUS_TIMEOUT); /* Read cause status bits. */ - cause_status_bits = mlxbf_i2c_read(priv->mst_cause->io, - MLXBF_I2C_CAUSE_ARBITER); + cause_status_bits = readl(priv->mst_cause->io + + MLXBF_I2C_CAUSE_ARBITER); cause_status_bits &= MLXBF_I2C_CAUSE_MASTER_ARBITER_BITS_MASK; /* * Parse both Cause and Master GW bits, then return transaction status. */ - master_status_bits = mlxbf_i2c_read(priv->smbus->io, - MLXBF_I2C_SMBUS_MASTER_STATUS); + master_status_bits = readl(priv->smbus->io + + MLXBF_I2C_SMBUS_MASTER_STATUS); master_status_bits &= MLXBF_I2C_SMBUS_MASTER_STATUS_MASK; if (mlxbf_i2c_smbus_transaction_success(master_status_bits, @@ -649,10 +609,17 @@ static void mlxbf_i2c_smbus_write_data(struct mlxbf_i2c_priv *priv, aligned_length = round_up(length, 4); - /* Copy data bytes from 4-byte aligned source buffer. */ + /* + * Copy data bytes from 4-byte aligned source buffer. + * Data copied to the Master GW Data Descriptor MUST be shifted + * left so the data starts at the MSB of the descriptor registers + * as required by the underlying hardware. Enable byte swapping + * when writing data bytes to the 32 * 32-bit HW Data registers + * a.k.a Master GW Data Descriptor. + */ for (offset = 0; offset < aligned_length; offset += sizeof(u32)) { data32 = *((u32 *)(data + offset)); - mlxbf_i2c_write_data(priv->smbus->io, addr + offset, data32); + iowrite32be(data32, priv->smbus->io + addr + offset); } } @@ -664,15 +631,23 @@ static void mlxbf_i2c_smbus_read_data(struct mlxbf_i2c_priv *priv, mask = sizeof(u32) - 1; + /* + * Data bytes in the Master GW Data Descriptor are shifted left + * so the data starts at the MSB of the descriptor registers as + * set by the underlying hardware. Enable byte swapping while + * reading data bytes from the 32 * 32-bit HW Data registers + * a.k.a Master GW Data Descriptor. + */ + for (offset = 0; offset < (length & ~mask); offset += sizeof(u32)) { - data32 = mlxbf_i2c_read_data(priv->smbus->io, addr + offset); + data32 = ioread32be(priv->smbus->io + addr + offset); *((u32 *)(data + offset)) = data32; } if (!(length & mask)) return; - data32 = mlxbf_i2c_read_data(priv->smbus->io, addr + offset); + data32 = ioread32be(priv->smbus->io + addr + offset); for (byte = 0; byte < (length & mask); byte++) { data[offset + byte] = data32 & GENMASK(7, 0); @@ -698,16 +673,16 @@ static int mlxbf_i2c_smbus_enable(struct mlxbf_i2c_priv *priv, u8 slave, command |= rol32(pec_en, MLXBF_I2C_MASTER_SEND_PEC_SHIFT); /* Clear status bits. */ - mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_MASTER_STATUS, 0x0); + writel(0x0, priv->smbus->io + MLXBF_I2C_SMBUS_MASTER_STATUS); /* Set the cause data. */ - mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_CAUSE_OR_CLEAR, ~0x0); + writel(~0x0, priv->smbus->io + MLXBF_I2C_CAUSE_OR_CLEAR); /* Zero PEC byte. */ - mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_MASTER_PEC, 0x0); + writel(0x0, priv->smbus->io + MLXBF_I2C_SMBUS_MASTER_PEC); /* Zero byte count. */ - mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_RS_BYTES, 0x0); + writel(0x0, priv->smbus->io + MLXBF_I2C_SMBUS_RS_BYTES); /* GW activation. */ - mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_MASTER_GW, command); + writel(command, priv->smbus->io + MLXBF_I2C_SMBUS_MASTER_GW); /* * Poll master status and check status bits. An ACK is sent when @@ -823,8 +798,8 @@ mlxbf_i2c_smbus_start_transaction(struct mlxbf_i2c_priv *priv, * needs to be 'manually' reset. This should be removed in * next tag integration. */ - mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_MASTER_FSM, - MLXBF_I2C_SMBUS_MASTER_FSM_PS_STATE_MASK); + writel(MLXBF_I2C_SMBUS_MASTER_FSM_PS_STATE_MASK, + priv->smbus->io + MLXBF_I2C_SMBUS_MASTER_FSM); } return ret; @@ -1113,8 +1088,8 @@ static void mlxbf_i2c_set_timings(struct mlxbf_i2c_priv *priv, timer |= mlxbf_i2c_set_timer(priv, timings->scl_low, false, MLXBF_I2C_MASK_16, MLXBF_I2C_SHIFT_16); - mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_TIMER_SCL_LOW_SCL_HIGH, - timer); + writel(timer, priv->smbus->io + + MLXBF_I2C_SMBUS_TIMER_SCL_LOW_SCL_HIGH); timer = mlxbf_i2c_set_timer(priv, timings->sda_rise, false, MLXBF_I2C_MASK_8, MLXBF_I2C_SHIFT_0); @@ -1124,37 +1099,34 @@ static void mlxbf_i2c_set_timings(struct mlxbf_i2c_priv *priv, MLXBF_I2C_MASK_8, MLXBF_I2C_SHIFT_16); timer |= mlxbf_i2c_set_timer(priv, timings->scl_fall, false, MLXBF_I2C_MASK_8, MLXBF_I2C_SHIFT_24); - mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_TIMER_FALL_RISE_SPIKE, - timer); + writel(timer, priv->smbus->io + + MLXBF_I2C_SMBUS_TIMER_FALL_RISE_SPIKE); timer = mlxbf_i2c_set_timer(priv, timings->hold_start, true, MLXBF_I2C_MASK_16, MLXBF_I2C_SHIFT_0); timer |= mlxbf_i2c_set_timer(priv, timings->hold_data, true, MLXBF_I2C_MASK_16, MLXBF_I2C_SHIFT_16); - mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_TIMER_THOLD, timer); + writel(timer, priv->smbus->io + MLXBF_I2C_SMBUS_TIMER_THOLD); timer = mlxbf_i2c_set_timer(priv, timings->setup_start, true, MLXBF_I2C_MASK_16, MLXBF_I2C_SHIFT_0); timer |= mlxbf_i2c_set_timer(priv, timings->setup_stop, true, MLXBF_I2C_MASK_16, MLXBF_I2C_SHIFT_16); - mlxbf_i2c_write(priv->smbus->io, - MLXBF_I2C_SMBUS_TIMER_TSETUP_START_STOP, timer); + writel(timer, priv->smbus->io + + MLXBF_I2C_SMBUS_TIMER_TSETUP_START_STOP); timer = mlxbf_i2c_set_timer(priv, timings->setup_data, true, MLXBF_I2C_MASK_16, MLXBF_I2C_SHIFT_0); - mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_TIMER_TSETUP_DATA, - timer); + writel(timer, priv->smbus->io + MLXBF_I2C_SMBUS_TIMER_TSETUP_DATA); timer = mlxbf_i2c_set_timer(priv, timings->buf, false, MLXBF_I2C_MASK_16, MLXBF_I2C_SHIFT_0); timer |= mlxbf_i2c_set_timer(priv, timings->thigh_max, false, MLXBF_I2C_MASK_16, MLXBF_I2C_SHIFT_16); - mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_THIGH_MAX_TBUF, - timer); + writel(timer, priv->smbus->io + MLXBF_I2C_SMBUS_THIGH_MAX_TBUF); timer = timings->timeout; - mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_SCL_LOW_TIMEOUT, - timer); + writel(timer, priv->smbus->io + MLXBF_I2C_SMBUS_SCL_LOW_TIMEOUT); } enum mlxbf_i2c_timings_config { @@ -1426,19 +1398,15 @@ static int mlxbf_i2c_init_master(struct platform_device *pdev, * platform firmware; disabling the bus might compromise the system * functionality. */ - config_reg = mlxbf_i2c_read(gpio_res->io, - MLXBF_I2C_GPIO_0_FUNC_EN_0); + config_reg = readl(gpio_res->io + MLXBF_I2C_GPIO_0_FUNC_EN_0); config_reg = MLXBF_I2C_GPIO_SMBUS_GW_ASSERT_PINS(priv->bus, config_reg); - mlxbf_i2c_write(gpio_res->io, MLXBF_I2C_GPIO_0_FUNC_EN_0, - config_reg); + writel(config_reg, gpio_res->io + MLXBF_I2C_GPIO_0_FUNC_EN_0); - config_reg = mlxbf_i2c_read(gpio_res->io, - MLXBF_I2C_GPIO_0_FORCE_OE_EN); + config_reg = readl(gpio_res->io + MLXBF_I2C_GPIO_0_FORCE_OE_EN); config_reg = MLXBF_I2C_GPIO_SMBUS_GW_RESET_PINS(priv->bus, config_reg); - mlxbf_i2c_write(gpio_res->io, MLXBF_I2C_GPIO_0_FORCE_OE_EN, - config_reg); + writel(config_reg, gpio_res->io + MLXBF_I2C_GPIO_0_FORCE_OE_EN); mutex_unlock(gpio_res->lock); @@ -1452,10 +1420,9 @@ static u64 mlxbf_calculate_freq_from_tyu(struct mlxbf_i2c_resource *corepll_res) u32 corepll_val; u16 core_f; - pad_frequency = MLXBF_I2C_TYU_PLL_IN_FREQ; + pad_frequency = MLXBF_I2C_PLL_IN_FREQ; - corepll_val = mlxbf_i2c_read(corepll_res->io, - MLXBF_I2C_CORE_PLL_REG1); + corepll_val = readl(corepll_res->io + MLXBF_I2C_CORE_PLL_REG1); /* Get Core PLL configuration bits. */ core_f = rol32(corepll_val, MLXBF_I2C_COREPLL_CORE_F_TYU_SHIFT) & @@ -1488,12 +1455,10 @@ static u64 mlxbf_calculate_freq_from_yu(struct mlxbf_i2c_resource *corepll_res) u8 core_od, core_r; u32 core_f; - pad_frequency = MLXBF_I2C_YU_PLL_IN_FREQ; + pad_frequency = MLXBF_I2C_PLL_IN_FREQ; - corepll_reg1_val = mlxbf_i2c_read(corepll_res->io, - MLXBF_I2C_CORE_PLL_REG1); - corepll_reg2_val = mlxbf_i2c_read(corepll_res->io, - MLXBF_I2C_CORE_PLL_REG2); + corepll_reg1_val = readl(corepll_res->io + MLXBF_I2C_CORE_PLL_REG1); + corepll_reg2_val = readl(corepll_res->io + MLXBF_I2C_CORE_PLL_REG2); /* Get Core PLL configuration bits */ core_f = rol32(corepll_reg1_val, MLXBF_I2C_COREPLL_CORE_F_YU_SHIFT) & @@ -1585,7 +1550,7 @@ static int mlxbf_slave_enable(struct mlxbf_i2c_priv *priv, u8 addr) * (7-bit address, 1 status bit (1 if enabled, 0 if not)). */ for (reg = 0; reg < reg_cnt; reg++) { - slave_reg = mlxbf_i2c_read(priv->smbus->io, + slave_reg = readl(priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_ADDR_CFG + reg * 0x4); /* * Each register holds 4 slave addresses. So, we have to keep @@ -1643,8 +1608,8 @@ static int mlxbf_slave_enable(struct mlxbf_i2c_priv *priv, u8 addr) /* Enable the slave address and update the register. */ slave_reg |= (1 << MLXBF_I2C_SMBUS_SLAVE_ADDR_EN_BIT) << (byte * 8); - mlxbf_i2c_write(priv->smbus->io, - MLXBF_I2C_SMBUS_SLAVE_ADDR_CFG + reg * 0x4, slave_reg); + writel(slave_reg, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_ADDR_CFG + + reg * 0x4); return 0; } @@ -1668,7 +1633,7 @@ static int mlxbf_slave_disable(struct mlxbf_i2c_priv *priv) * (7-bit address, 1 status bit (1 if enabled, 0 if not)). */ for (reg = 0; reg < reg_cnt; reg++) { - slave_reg = mlxbf_i2c_read(priv->smbus->io, + slave_reg = readl(priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_ADDR_CFG + reg * 0x4); /* Check whether the address slots are empty. */ @@ -1708,8 +1673,8 @@ static int mlxbf_slave_disable(struct mlxbf_i2c_priv *priv) /* Cleanup the slave address slot. */ slave_reg &= ~(GENMASK(7, 0) << (slave_byte * 8)); - mlxbf_i2c_write(priv->smbus->io, - MLXBF_I2C_SMBUS_SLAVE_ADDR_CFG + reg * 0x4, slave_reg); + writel(slave_reg, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_ADDR_CFG + + reg * 0x4); return 0; } @@ -1801,7 +1766,7 @@ static int mlxbf_i2c_init_slave(struct platform_device *pdev, int ret; /* Reset FSM. */ - mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_SLAVE_FSM, 0); + writel(0, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_FSM); /* * Enable slave cause interrupt bits. Drive @@ -1810,15 +1775,13 @@ static int mlxbf_i2c_init_slave(struct platform_device *pdev, * masters issue a Read and Write, respectively. But, clear all * interrupts first. */ - mlxbf_i2c_write(priv->slv_cause->io, - MLXBF_I2C_CAUSE_OR_CLEAR, ~0); + writel(~0, priv->slv_cause->io + MLXBF_I2C_CAUSE_OR_CLEAR); int_reg = MLXBF_I2C_CAUSE_READ_WAIT_FW_RESPONSE; int_reg |= MLXBF_I2C_CAUSE_WRITE_SUCCESS; - mlxbf_i2c_write(priv->slv_cause->io, - MLXBF_I2C_CAUSE_OR_EVTEN0, int_reg); + writel(int_reg, priv->slv_cause->io + MLXBF_I2C_CAUSE_OR_EVTEN0); /* Finally, set the 'ready' bit to start handling transactions. */ - mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_SLAVE_READY, 0x1); + writel(0x1, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_READY); /* Initialize the cause coalesce resource. */ ret = mlxbf_i2c_init_coalesce(pdev, priv); @@ -1844,23 +1807,21 @@ static bool mlxbf_i2c_has_coalesce(struct mlxbf_i2c_priv *priv, bool *read, MLXBF_I2C_CAUSE_YU_SLAVE_BIT : priv->bus + MLXBF_I2C_CAUSE_TYU_SLAVE_BIT; - coalesce0_reg = mlxbf_i2c_read(priv->coalesce->io, - MLXBF_I2C_CAUSE_COALESCE_0); + coalesce0_reg = readl(priv->coalesce->io + MLXBF_I2C_CAUSE_COALESCE_0); is_set = coalesce0_reg & (1 << slave_shift); if (!is_set) return false; /* Check the source of the interrupt, i.e. whether a Read or Write. */ - cause_reg = mlxbf_i2c_read(priv->slv_cause->io, - MLXBF_I2C_CAUSE_ARBITER); + cause_reg = readl(priv->slv_cause->io + MLXBF_I2C_CAUSE_ARBITER); if (cause_reg & MLXBF_I2C_CAUSE_READ_WAIT_FW_RESPONSE) *read = true; else if (cause_reg & MLXBF_I2C_CAUSE_WRITE_SUCCESS) *write = true; /* Clear cause bits. */ - mlxbf_i2c_write(priv->slv_cause->io, MLXBF_I2C_CAUSE_OR_CLEAR, ~0x0); + writel(~0x0, priv->slv_cause->io + MLXBF_I2C_CAUSE_OR_CLEAR); return true; } @@ -1900,8 +1861,8 @@ static int mlxbf_smbus_irq_send(struct mlxbf_i2c_priv *priv, u8 recv_bytes) * address, if supplied. */ if (recv_bytes > 0) { - data32 = mlxbf_i2c_read_data(priv->smbus->io, - MLXBF_I2C_SLAVE_DATA_DESC_ADDR); + data32 = ioread32be(priv->smbus->io + + MLXBF_I2C_SLAVE_DATA_DESC_ADDR); /* Parse the received bytes. */ switch (recv_bytes) { @@ -1966,7 +1927,7 @@ static int mlxbf_smbus_irq_send(struct mlxbf_i2c_priv *priv, u8 recv_bytes) control32 |= rol32(write_size, MLXBF_I2C_SLAVE_WRITE_BYTES_SHIFT); control32 |= rol32(pec_en, MLXBF_I2C_SLAVE_SEND_PEC_SHIFT); - mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_SLAVE_GW, control32); + writel(control32, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_GW); /* * Wait until the transfer is completed; the driver will wait @@ -1975,10 +1936,9 @@ static int mlxbf_smbus_irq_send(struct mlxbf_i2c_priv *priv, u8 recv_bytes) mlxbf_smbus_slave_wait_for_idle(priv, MLXBF_I2C_SMBUS_TIMEOUT); /* Release the Slave GW. */ - mlxbf_i2c_write(priv->smbus->io, - MLXBF_I2C_SMBUS_SLAVE_RS_MASTER_BYTES, 0x0); - mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_SLAVE_PEC, 0x0); - mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_SLAVE_READY, 0x1); + writel(0x0, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_RS_MASTER_BYTES); + writel(0x0, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_PEC); + writel(0x1, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_READY); return 0; } @@ -2023,10 +1983,9 @@ static int mlxbf_smbus_irq_recv(struct mlxbf_i2c_priv *priv, u8 recv_bytes) i2c_slave_event(slave, I2C_SLAVE_STOP, &value); /* Release the Slave GW. */ - mlxbf_i2c_write(priv->smbus->io, - MLXBF_I2C_SMBUS_SLAVE_RS_MASTER_BYTES, 0x0); - mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_SLAVE_PEC, 0x0); - mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_SLAVE_READY, 0x1); + writel(0x0, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_RS_MASTER_BYTES); + writel(0x0, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_PEC); + writel(0x1, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_READY); return ret; } @@ -2061,8 +2020,8 @@ static irqreturn_t mlxbf_smbus_irq(int irq, void *ptr) * slave, if the higher 8 bits are sent then the slave expect N bytes * from the master. */ - rw_bytes_reg = mlxbf_i2c_read(priv->smbus->io, - MLXBF_I2C_SMBUS_SLAVE_RS_MASTER_BYTES); + rw_bytes_reg = readl(priv->smbus->io + + MLXBF_I2C_SMBUS_SLAVE_RS_MASTER_BYTES); recv_bytes = (rw_bytes_reg >> 8) & GENMASK(7, 0); /* @@ -2264,6 +2223,7 @@ static const struct of_device_id mlxbf_i2c_dt_ids[] = { MODULE_DEVICE_TABLE(of, mlxbf_i2c_dt_ids); +#ifdef CONFIG_ACPI static const struct acpi_device_id mlxbf_i2c_acpi_ids[] = { { "MLNXBF03", (kernel_ulong_t)&mlxbf_i2c_chip[MLXBF_I2C_CHIP_TYPE_1] }, { "MLNXBF23", (kernel_ulong_t)&mlxbf_i2c_chip[MLXBF_I2C_CHIP_TYPE_2] }, @@ -2305,6 +2265,12 @@ static int mlxbf_i2c_acpi_probe(struct device *dev, struct mlxbf_i2c_priv *priv) return ret; } +#else +static int mlxbf_i2c_acpi_probe(struct device *dev, struct mlxbf_i2c_priv *priv) +{ + return -ENOENT; +} +#endif /* CONFIG_ACPI */ static int mlxbf_i2c_of_probe(struct device *dev, struct mlxbf_i2c_priv *priv) { @@ -2473,7 +2439,9 @@ static struct platform_driver mlxbf_i2c_driver = { .driver = { .name = "i2c-mlxbf", .of_match_table = mlxbf_i2c_dt_ids, +#ifdef CONFIG_ACPI .acpi_match_table = ACPI_PTR(mlxbf_i2c_acpi_ids), +#endif /* CONFIG_ACPI */ }, }; @@ -2502,5 +2470,5 @@ static void __exit mlxbf_i2c_exit(void) module_exit(mlxbf_i2c_exit); MODULE_DESCRIPTION("Mellanox BlueField I2C bus driver"); -MODULE_AUTHOR("Khalil Blaiech <kblaiech@mellanox.com>"); +MODULE_AUTHOR("Khalil Blaiech <kblaiech@nvidia.com>"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/i2c/busses/i2c-mt65xx.c b/drivers/i2c/busses/i2c-mt65xx.c index 0cbdfbe605b5..33de99b7bc20 100644 --- a/drivers/i2c/busses/i2c-mt65xx.c +++ b/drivers/i2c/busses/i2c-mt65xx.c @@ -475,6 +475,10 @@ static void mtk_i2c_init_hw(struct mtk_i2c *i2c) { u16 control_reg; + writel(I2C_DMA_HARD_RST, i2c->pdmabase + OFFSET_RST); + udelay(50); + writel(I2C_DMA_CLR_FLAG, i2c->pdmabase + OFFSET_RST); + mtk_i2c_writew(i2c, I2C_SOFT_RST, OFFSET_SOFTRESET); /* Set ioconfig */ @@ -529,10 +533,6 @@ static void mtk_i2c_init_hw(struct mtk_i2c *i2c) mtk_i2c_writew(i2c, control_reg, OFFSET_CONTROL); mtk_i2c_writew(i2c, I2C_DELAY_LEN, OFFSET_DELAY_LEN); - - writel(I2C_DMA_HARD_RST, i2c->pdmabase + OFFSET_RST); - udelay(50); - writel(I2C_DMA_CLR_FLAG, i2c->pdmabase + OFFSET_RST); } static const struct i2c_spec_values *mtk_i2c_get_spec(unsigned int speed) diff --git a/drivers/i2c/busses/i2c-sh_mobile.c b/drivers/i2c/busses/i2c-sh_mobile.c index cab725559999..bdd60770779a 100644 --- a/drivers/i2c/busses/i2c-sh_mobile.c +++ b/drivers/i2c/busses/i2c-sh_mobile.c @@ -129,6 +129,7 @@ struct sh_mobile_i2c_data { int sr; bool send_stop; bool stop_after_dma; + bool atomic_xfer; struct resource *res; struct dma_chan *dma_tx; @@ -330,13 +331,15 @@ static unsigned char i2c_op(struct sh_mobile_i2c_data *pd, enum sh_mobile_i2c_op ret = iic_rd(pd, ICDR); break; case OP_RX_STOP: /* enable DTE interrupt, issue stop */ - iic_wr(pd, ICIC, - ICIC_DTEE | ICIC_WAITE | ICIC_ALE | ICIC_TACKE); + if (!pd->atomic_xfer) + iic_wr(pd, ICIC, + ICIC_DTEE | ICIC_WAITE | ICIC_ALE | ICIC_TACKE); iic_wr(pd, ICCR, ICCR_ICE | ICCR_RACK); break; case OP_RX_STOP_DATA: /* enable DTE interrupt, read data, issue stop */ - iic_wr(pd, ICIC, - ICIC_DTEE | ICIC_WAITE | ICIC_ALE | ICIC_TACKE); + if (!pd->atomic_xfer) + iic_wr(pd, ICIC, + ICIC_DTEE | ICIC_WAITE | ICIC_ALE | ICIC_TACKE); ret = iic_rd(pd, ICDR); iic_wr(pd, ICCR, ICCR_ICE | ICCR_RACK); break; @@ -429,7 +432,8 @@ static irqreturn_t sh_mobile_i2c_isr(int irq, void *dev_id) if (wakeup) { pd->sr |= SW_DONE; - wake_up(&pd->wait); + if (!pd->atomic_xfer) + wake_up(&pd->wait); } /* defeat write posting to avoid spurious WAIT interrupts */ @@ -581,6 +585,9 @@ static void start_ch(struct sh_mobile_i2c_data *pd, struct i2c_msg *usr_msg, pd->pos = -1; pd->sr = 0; + if (pd->atomic_xfer) + return; + pd->dma_buf = i2c_get_dma_safe_msg_buf(pd->msg, 8); if (pd->dma_buf) sh_mobile_i2c_xfer_dma(pd); @@ -637,15 +644,13 @@ static int poll_busy(struct sh_mobile_i2c_data *pd) return i ? 0 : -ETIMEDOUT; } -static int sh_mobile_i2c_xfer(struct i2c_adapter *adapter, - struct i2c_msg *msgs, - int num) +static int sh_mobile_xfer(struct sh_mobile_i2c_data *pd, + struct i2c_msg *msgs, int num) { - struct sh_mobile_i2c_data *pd = i2c_get_adapdata(adapter); struct i2c_msg *msg; int err = 0; int i; - long timeout; + long time_left; /* Wake up device and enable clock */ pm_runtime_get_sync(pd->dev); @@ -662,15 +667,35 @@ static int sh_mobile_i2c_xfer(struct i2c_adapter *adapter, if (do_start) i2c_op(pd, OP_START); - /* The interrupt handler takes care of the rest... */ - timeout = wait_event_timeout(pd->wait, - pd->sr & (ICSR_TACK | SW_DONE), - adapter->timeout); - - /* 'stop_after_dma' tells if DMA transfer was complete */ - i2c_put_dma_safe_msg_buf(pd->dma_buf, pd->msg, pd->stop_after_dma); + if (pd->atomic_xfer) { + unsigned long j = jiffies + pd->adap.timeout; + + time_left = time_before_eq(jiffies, j); + while (time_left && + !(pd->sr & (ICSR_TACK | SW_DONE))) { + unsigned char sr = iic_rd(pd, ICSR); + + if (sr & (ICSR_AL | ICSR_TACK | + ICSR_WAIT | ICSR_DTE)) { + sh_mobile_i2c_isr(0, pd); + udelay(150); + } else { + cpu_relax(); + } + time_left = time_before_eq(jiffies, j); + } + } else { + /* The interrupt handler takes care of the rest... */ + time_left = wait_event_timeout(pd->wait, + pd->sr & (ICSR_TACK | SW_DONE), + pd->adap.timeout); + + /* 'stop_after_dma' tells if DMA xfer was complete */ + i2c_put_dma_safe_msg_buf(pd->dma_buf, pd->msg, + pd->stop_after_dma); + } - if (!timeout) { + if (!time_left) { dev_err(pd->dev, "Transfer request timed out\n"); if (pd->dma_direction != DMA_NONE) sh_mobile_i2c_cleanup_dma(pd); @@ -696,14 +721,35 @@ static int sh_mobile_i2c_xfer(struct i2c_adapter *adapter, return err ?: num; } +static int sh_mobile_i2c_xfer(struct i2c_adapter *adapter, + struct i2c_msg *msgs, + int num) +{ + struct sh_mobile_i2c_data *pd = i2c_get_adapdata(adapter); + + pd->atomic_xfer = false; + return sh_mobile_xfer(pd, msgs, num); +} + +static int sh_mobile_i2c_xfer_atomic(struct i2c_adapter *adapter, + struct i2c_msg *msgs, + int num) +{ + struct sh_mobile_i2c_data *pd = i2c_get_adapdata(adapter); + + pd->atomic_xfer = true; + return sh_mobile_xfer(pd, msgs, num); +} + static u32 sh_mobile_i2c_func(struct i2c_adapter *adapter) { return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL | I2C_FUNC_PROTOCOL_MANGLING; } static const struct i2c_algorithm sh_mobile_i2c_algorithm = { - .functionality = sh_mobile_i2c_func, - .master_xfer = sh_mobile_i2c_xfer, + .functionality = sh_mobile_i2c_func, + .master_xfer = sh_mobile_i2c_xfer, + .master_xfer_atomic = sh_mobile_i2c_xfer_atomic, }; static const struct i2c_adapter_quirks sh_mobile_i2c_quirks = { diff --git a/drivers/iio/accel/kxcjk-1013.c b/drivers/iio/accel/kxcjk-1013.c index beb38d9d607d..560a3373ff20 100644 --- a/drivers/iio/accel/kxcjk-1013.c +++ b/drivers/iio/accel/kxcjk-1013.c @@ -126,6 +126,12 @@ enum kx_chipset { KX_MAX_CHIPS /* this must be last */ }; +enum kx_acpi_type { + ACPI_GENERIC, + ACPI_SMO8500, + ACPI_KIOX010A, +}; + struct kxcjk1013_data { struct i2c_client *client; struct iio_trigger *dready_trig; @@ -143,7 +149,7 @@ struct kxcjk1013_data { bool motion_trigger_on; int64_t timestamp; enum kx_chipset chipset; - bool is_smo8500_device; + enum kx_acpi_type acpi_type; }; enum kxcjk1013_axis { @@ -270,6 +276,32 @@ static const struct { {19163, 1, 0}, {38326, 0, 1} }; +#ifdef CONFIG_ACPI +enum kiox010a_fn_index { + KIOX010A_SET_LAPTOP_MODE = 1, + KIOX010A_SET_TABLET_MODE = 2, +}; + +static int kiox010a_dsm(struct device *dev, int fn_index) +{ + acpi_handle handle = ACPI_HANDLE(dev); + guid_t kiox010a_dsm_guid; + union acpi_object *obj; + + if (!handle) + return -ENODEV; + + guid_parse("1f339696-d475-4e26-8cad-2e9f8e6d7a91", &kiox010a_dsm_guid); + + obj = acpi_evaluate_dsm(handle, &kiox010a_dsm_guid, 1, fn_index, NULL); + if (!obj) + return -EIO; + + ACPI_FREE(obj); + return 0; +} +#endif + static int kxcjk1013_set_mode(struct kxcjk1013_data *data, enum kxcjk1013_mode mode) { @@ -347,6 +379,13 @@ static int kxcjk1013_chip_init(struct kxcjk1013_data *data) { int ret; +#ifdef CONFIG_ACPI + if (data->acpi_type == ACPI_KIOX010A) { + /* Make sure the kbd and touchpad on 2-in-1s using 2 KXCJ91008-s work */ + kiox010a_dsm(&data->client->dev, KIOX010A_SET_LAPTOP_MODE); + } +#endif + ret = i2c_smbus_read_byte_data(data->client, KXCJK1013_REG_WHO_AM_I); if (ret < 0) { dev_err(&data->client->dev, "Error reading who_am_i\n"); @@ -1247,7 +1286,7 @@ static irqreturn_t kxcjk1013_data_rdy_trig_poll(int irq, void *private) static const char *kxcjk1013_match_acpi_device(struct device *dev, enum kx_chipset *chipset, - bool *is_smo8500_device) + enum kx_acpi_type *acpi_type) { const struct acpi_device_id *id; @@ -1256,7 +1295,9 @@ static const char *kxcjk1013_match_acpi_device(struct device *dev, return NULL; if (strcmp(id->id, "SMO8500") == 0) - *is_smo8500_device = true; + *acpi_type = ACPI_SMO8500; + else if (strcmp(id->id, "KIOX010A") == 0) + *acpi_type = ACPI_KIOX010A; *chipset = (enum kx_chipset)id->driver_data; @@ -1299,7 +1340,7 @@ static int kxcjk1013_probe(struct i2c_client *client, } else if (ACPI_HANDLE(&client->dev)) { name = kxcjk1013_match_acpi_device(&client->dev, &data->chipset, - &data->is_smo8500_device); + &data->acpi_type); } else return -ENODEV; @@ -1316,7 +1357,7 @@ static int kxcjk1013_probe(struct i2c_client *client, indio_dev->modes = INDIO_DIRECT_MODE; indio_dev->info = &kxcjk1013_info; - if (client->irq > 0 && !data->is_smo8500_device) { + if (client->irq > 0 && data->acpi_type != ACPI_SMO8500) { ret = devm_request_threaded_irq(&client->dev, client->irq, kxcjk1013_data_rdy_trig_poll, kxcjk1013_event_handler, diff --git a/drivers/iio/adc/ingenic-adc.c b/drivers/iio/adc/ingenic-adc.c index 92b25083e23f..1aafbe2cfe67 100644 --- a/drivers/iio/adc/ingenic-adc.c +++ b/drivers/iio/adc/ingenic-adc.c @@ -71,7 +71,7 @@ #define JZ4725B_ADC_BATTERY_HIGH_VREF_BITS 10 #define JZ4740_ADC_BATTERY_HIGH_VREF (7500 * 0.986) #define JZ4740_ADC_BATTERY_HIGH_VREF_BITS 12 -#define JZ4770_ADC_BATTERY_VREF 6600 +#define JZ4770_ADC_BATTERY_VREF 1200 #define JZ4770_ADC_BATTERY_VREF_BITS 12 #define JZ_ADC_IRQ_AUX BIT(0) @@ -177,13 +177,12 @@ static void ingenic_adc_set_config(struct ingenic_adc *adc, mutex_unlock(&adc->lock); } -static void ingenic_adc_enable(struct ingenic_adc *adc, - int engine, - bool enabled) +static void ingenic_adc_enable_unlocked(struct ingenic_adc *adc, + int engine, + bool enabled) { u8 val; - mutex_lock(&adc->lock); val = readb(adc->base + JZ_ADC_REG_ENABLE); if (enabled) @@ -192,20 +191,41 @@ static void ingenic_adc_enable(struct ingenic_adc *adc, val &= ~BIT(engine); writeb(val, adc->base + JZ_ADC_REG_ENABLE); +} + +static void ingenic_adc_enable(struct ingenic_adc *adc, + int engine, + bool enabled) +{ + mutex_lock(&adc->lock); + ingenic_adc_enable_unlocked(adc, engine, enabled); mutex_unlock(&adc->lock); } static int ingenic_adc_capture(struct ingenic_adc *adc, int engine) { + u32 cfg; u8 val; int ret; - ingenic_adc_enable(adc, engine, true); + /* + * Disable CMD_SEL temporarily, because it causes wrong VBAT readings, + * probably due to the switch of VREF. We must keep the lock here to + * avoid races with the buffer enable/disable functions. + */ + mutex_lock(&adc->lock); + cfg = readl(adc->base + JZ_ADC_REG_CFG); + writel(cfg & ~JZ_ADC_REG_CFG_CMD_SEL, adc->base + JZ_ADC_REG_CFG); + + ingenic_adc_enable_unlocked(adc, engine, true); ret = readb_poll_timeout(adc->base + JZ_ADC_REG_ENABLE, val, !(val & BIT(engine)), 250, 1000); if (ret) - ingenic_adc_enable(adc, engine, false); + ingenic_adc_enable_unlocked(adc, engine, false); + + writel(cfg, adc->base + JZ_ADC_REG_CFG); + mutex_unlock(&adc->lock); return ret; } diff --git a/drivers/iio/adc/mt6577_auxadc.c b/drivers/iio/adc/mt6577_auxadc.c index ac415cb089cd..79c1dd68b909 100644 --- a/drivers/iio/adc/mt6577_auxadc.c +++ b/drivers/iio/adc/mt6577_auxadc.c @@ -9,9 +9,9 @@ #include <linux/err.h> #include <linux/kernel.h> #include <linux/module.h> -#include <linux/of.h> -#include <linux/of_device.h> +#include <linux/mod_devicetable.h> #include <linux/platform_device.h> +#include <linux/property.h> #include <linux/iopoll.h> #include <linux/io.h> #include <linux/iio/iio.h> @@ -276,6 +276,8 @@ static int mt6577_auxadc_probe(struct platform_device *pdev) goto err_disable_clk; } + adc_dev->dev_comp = device_get_match_data(&pdev->dev); + mutex_init(&adc_dev->lock); mt6577_auxadc_mod_reg(adc_dev->reg_base + MT6577_AUXADC_MISC, diff --git a/drivers/iio/adc/stm32-adc-core.c b/drivers/iio/adc/stm32-adc-core.c index cd870c089182..a83199b212a4 100644 --- a/drivers/iio/adc/stm32-adc-core.c +++ b/drivers/iio/adc/stm32-adc-core.c @@ -41,18 +41,16 @@ * struct stm32_adc_common_regs - stm32 common registers * @csr: common status register offset * @ccr: common control register offset - * @eoc1_msk: adc1 end of conversion flag in @csr - * @eoc2_msk: adc2 end of conversion flag in @csr - * @eoc3_msk: adc3 end of conversion flag in @csr + * @eoc_msk: array of eoc (end of conversion flag) masks in csr for adc1..n + * @ovr_msk: array of ovr (overrun flag) masks in csr for adc1..n * @ier: interrupt enable register offset for each adc * @eocie_msk: end of conversion interrupt enable mask in @ier */ struct stm32_adc_common_regs { u32 csr; u32 ccr; - u32 eoc1_msk; - u32 eoc2_msk; - u32 eoc3_msk; + u32 eoc_msk[STM32_ADC_MAX_ADCS]; + u32 ovr_msk[STM32_ADC_MAX_ADCS]; u32 ier; u32 eocie_msk; }; @@ -282,21 +280,20 @@ out: static const struct stm32_adc_common_regs stm32f4_adc_common_regs = { .csr = STM32F4_ADC_CSR, .ccr = STM32F4_ADC_CCR, - .eoc1_msk = STM32F4_EOC1 | STM32F4_OVR1, - .eoc2_msk = STM32F4_EOC2 | STM32F4_OVR2, - .eoc3_msk = STM32F4_EOC3 | STM32F4_OVR3, + .eoc_msk = { STM32F4_EOC1, STM32F4_EOC2, STM32F4_EOC3}, + .ovr_msk = { STM32F4_OVR1, STM32F4_OVR2, STM32F4_OVR3}, .ier = STM32F4_ADC_CR1, - .eocie_msk = STM32F4_EOCIE | STM32F4_OVRIE, + .eocie_msk = STM32F4_EOCIE, }; /* STM32H7 common registers definitions */ static const struct stm32_adc_common_regs stm32h7_adc_common_regs = { .csr = STM32H7_ADC_CSR, .ccr = STM32H7_ADC_CCR, - .eoc1_msk = STM32H7_EOC_MST | STM32H7_OVR_MST, - .eoc2_msk = STM32H7_EOC_SLV | STM32H7_OVR_SLV, + .eoc_msk = { STM32H7_EOC_MST, STM32H7_EOC_SLV}, + .ovr_msk = { STM32H7_OVR_MST, STM32H7_OVR_SLV}, .ier = STM32H7_ADC_IER, - .eocie_msk = STM32H7_EOCIE | STM32H7_OVRIE, + .eocie_msk = STM32H7_EOCIE, }; static const unsigned int stm32_adc_offset[STM32_ADC_MAX_ADCS] = { @@ -318,6 +315,7 @@ static void stm32_adc_irq_handler(struct irq_desc *desc) { struct stm32_adc_priv *priv = irq_desc_get_handler_data(desc); struct irq_chip *chip = irq_desc_get_chip(desc); + int i; u32 status; chained_irq_enter(chip, desc); @@ -335,17 +333,12 @@ static void stm32_adc_irq_handler(struct irq_desc *desc) * before invoking the interrupt handler (e.g. call ISR only for * IRQ-enabled ADCs). */ - if (status & priv->cfg->regs->eoc1_msk && - stm32_adc_eoc_enabled(priv, 0)) - generic_handle_irq(irq_find_mapping(priv->domain, 0)); - - if (status & priv->cfg->regs->eoc2_msk && - stm32_adc_eoc_enabled(priv, 1)) - generic_handle_irq(irq_find_mapping(priv->domain, 1)); - - if (status & priv->cfg->regs->eoc3_msk && - stm32_adc_eoc_enabled(priv, 2)) - generic_handle_irq(irq_find_mapping(priv->domain, 2)); + for (i = 0; i < priv->cfg->num_irqs; i++) { + if ((status & priv->cfg->regs->eoc_msk[i] && + stm32_adc_eoc_enabled(priv, i)) || + (status & priv->cfg->regs->ovr_msk[i])) + generic_handle_irq(irq_find_mapping(priv->domain, i)); + } chained_irq_exit(chip, desc); }; diff --git a/drivers/iio/adc/stm32-adc.c b/drivers/iio/adc/stm32-adc.c index b3f31f147347..16c02c30dec7 100644 --- a/drivers/iio/adc/stm32-adc.c +++ b/drivers/iio/adc/stm32-adc.c @@ -154,6 +154,7 @@ struct stm32_adc; * @start_conv: routine to start conversions * @stop_conv: routine to stop conversions * @unprepare: optional unprepare routine (disable, power-down) + * @irq_clear: routine to clear irqs * @smp_cycles: programmable sampling time (ADC clock cycles) */ struct stm32_adc_cfg { @@ -166,6 +167,7 @@ struct stm32_adc_cfg { void (*start_conv)(struct iio_dev *, bool dma); void (*stop_conv)(struct iio_dev *); void (*unprepare)(struct iio_dev *); + void (*irq_clear)(struct iio_dev *indio_dev, u32 msk); const unsigned int *smp_cycles; }; @@ -621,6 +623,13 @@ static void stm32f4_adc_stop_conv(struct iio_dev *indio_dev) STM32F4_ADON | STM32F4_DMA | STM32F4_DDS); } +static void stm32f4_adc_irq_clear(struct iio_dev *indio_dev, u32 msk) +{ + struct stm32_adc *adc = iio_priv(indio_dev); + + stm32_adc_clr_bits(adc, adc->cfg->regs->isr_eoc.reg, msk); +} + static void stm32h7_adc_start_conv(struct iio_dev *indio_dev, bool dma) { struct stm32_adc *adc = iio_priv(indio_dev); @@ -659,6 +668,13 @@ static void stm32h7_adc_stop_conv(struct iio_dev *indio_dev) stm32_adc_clr_bits(adc, STM32H7_ADC_CFGR, STM32H7_DMNGT_MASK); } +static void stm32h7_adc_irq_clear(struct iio_dev *indio_dev, u32 msk) +{ + struct stm32_adc *adc = iio_priv(indio_dev); + /* On STM32H7 IRQs are cleared by writing 1 into ISR register */ + stm32_adc_set_bits(adc, adc->cfg->regs->isr_eoc.reg, msk); +} + static int stm32h7_adc_exit_pwr_down(struct iio_dev *indio_dev) { struct stm32_adc *adc = iio_priv(indio_dev); @@ -1235,17 +1251,40 @@ static int stm32_adc_read_raw(struct iio_dev *indio_dev, } } +static void stm32_adc_irq_clear(struct iio_dev *indio_dev, u32 msk) +{ + struct stm32_adc *adc = iio_priv(indio_dev); + + adc->cfg->irq_clear(indio_dev, msk); +} + static irqreturn_t stm32_adc_threaded_isr(int irq, void *data) { struct iio_dev *indio_dev = data; struct stm32_adc *adc = iio_priv(indio_dev); const struct stm32_adc_regspec *regs = adc->cfg->regs; u32 status = stm32_adc_readl(adc, regs->isr_eoc.reg); + u32 mask = stm32_adc_readl(adc, regs->ier_eoc.reg); - if (status & regs->isr_ovr.mask) + /* Check ovr status right now, as ovr mask should be already disabled */ + if (status & regs->isr_ovr.mask) { + /* + * Clear ovr bit to avoid subsequent calls to IRQ handler. + * This requires to stop ADC first. OVR bit state in ISR, + * is propaged to CSR register by hardware. + */ + adc->cfg->stop_conv(indio_dev); + stm32_adc_irq_clear(indio_dev, regs->isr_ovr.mask); dev_err(&indio_dev->dev, "Overrun, stopping: restart needed\n"); + return IRQ_HANDLED; + } - return IRQ_HANDLED; + if (!(status & mask)) + dev_err_ratelimited(&indio_dev->dev, + "Unexpected IRQ: IER=0x%08x, ISR=0x%08x\n", + mask, status); + + return IRQ_NONE; } static irqreturn_t stm32_adc_isr(int irq, void *data) @@ -1254,6 +1293,10 @@ static irqreturn_t stm32_adc_isr(int irq, void *data) struct stm32_adc *adc = iio_priv(indio_dev); const struct stm32_adc_regspec *regs = adc->cfg->regs; u32 status = stm32_adc_readl(adc, regs->isr_eoc.reg); + u32 mask = stm32_adc_readl(adc, regs->ier_eoc.reg); + + if (!(status & mask)) + return IRQ_WAKE_THREAD; if (status & regs->isr_ovr.mask) { /* @@ -2046,6 +2089,7 @@ static const struct stm32_adc_cfg stm32f4_adc_cfg = { .start_conv = stm32f4_adc_start_conv, .stop_conv = stm32f4_adc_stop_conv, .smp_cycles = stm32f4_adc_smp_cycles, + .irq_clear = stm32f4_adc_irq_clear, }; static const struct stm32_adc_cfg stm32h7_adc_cfg = { @@ -2057,6 +2101,7 @@ static const struct stm32_adc_cfg stm32h7_adc_cfg = { .prepare = stm32h7_adc_prepare, .unprepare = stm32h7_adc_unprepare, .smp_cycles = stm32h7_adc_smp_cycles, + .irq_clear = stm32h7_adc_irq_clear, }; static const struct stm32_adc_cfg stm32mp1_adc_cfg = { @@ -2069,6 +2114,7 @@ static const struct stm32_adc_cfg stm32mp1_adc_cfg = { .prepare = stm32h7_adc_prepare, .unprepare = stm32h7_adc_unprepare, .smp_cycles = stm32h7_adc_smp_cycles, + .irq_clear = stm32h7_adc_irq_clear, }; static const struct of_device_id stm32_adc_of_match[] = { diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c index c62cacc04672..e3f507771f17 100644 --- a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c +++ b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c @@ -256,7 +256,7 @@ int cros_ec_sensors_core_init(struct platform_device *pdev, struct cros_ec_sensorhub *sensor_hub = dev_get_drvdata(dev->parent); struct cros_ec_dev *ec = sensor_hub->ec; struct cros_ec_sensor_platform *sensor_platform = dev_get_platdata(dev); - u32 ver_mask; + u32 ver_mask, temp; int frequencies[ARRAY_SIZE(state->frequencies) / 2] = { 0 }; int ret, i; @@ -311,10 +311,16 @@ int cros_ec_sensors_core_init(struct platform_device *pdev, &frequencies[2], &state->fifo_max_event_count); } else { - frequencies[1] = state->resp->info_3.min_frequency; - frequencies[2] = state->resp->info_3.max_frequency; - state->fifo_max_event_count = - state->resp->info_3.fifo_max_event_count; + if (state->resp->info_3.max_frequency == 0) { + get_default_min_max_freq(state->resp->info.type, + &frequencies[1], + &frequencies[2], + &temp); + } else { + frequencies[1] = state->resp->info_3.min_frequency; + frequencies[2] = state->resp->info_3.max_frequency; + } + state->fifo_max_event_count = state->resp->info_3.fifo_max_event_count; } for (i = 0; i < ARRAY_SIZE(frequencies); i++) { state->frequencies[2 * i] = frequencies[i] / 1000; diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_shub.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_shub.c index 8c8d8870ca07..99562ba85ee4 100644 --- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_shub.c +++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_shub.c @@ -156,11 +156,13 @@ static const struct st_lsm6dsx_ext_dev_settings st_lsm6dsx_ext_dev_table[] = { static void st_lsm6dsx_shub_wait_complete(struct st_lsm6dsx_hw *hw) { struct st_lsm6dsx_sensor *sensor; - u32 odr; + u32 odr, timeout; sensor = iio_priv(hw->iio_devs[ST_LSM6DSX_ID_ACC]); odr = (hw->enable_mask & BIT(ST_LSM6DSX_ID_ACC)) ? sensor->odr : 12500; - msleep((2000000U / odr) + 1); + /* set 10ms as minimum timeout for i2c slave configuration */ + timeout = max_t(u32, 2000000U / odr + 1, 10); + msleep(timeout); } /* diff --git a/drivers/iio/light/Kconfig b/drivers/iio/light/Kconfig index cade6dc0305b..33ad4dd0b5c7 100644 --- a/drivers/iio/light/Kconfig +++ b/drivers/iio/light/Kconfig @@ -544,6 +544,7 @@ config VCNL4000 config VCNL4035 tristate "VCNL4035 combined ALS and proximity sensor" + select IIO_BUFFER select IIO_TRIGGERED_BUFFER select REGMAP_I2C depends on I2C diff --git a/drivers/infiniband/Kconfig b/drivers/infiniband/Kconfig index 32a51432ec4f..9325e189a215 100644 --- a/drivers/infiniband/Kconfig +++ b/drivers/infiniband/Kconfig @@ -73,6 +73,9 @@ config INFINIBAND_ADDR_TRANS_CONFIGFS This allows the user to config the default GID type that the CM uses for each device, when initiaing new connections. +config INFINIBAND_VIRT_DMA + def_bool !HIGHMEM + if INFINIBAND_USER_ACCESS || !INFINIBAND_USER_ACCESS source "drivers/infiniband/hw/mthca/Kconfig" source "drivers/infiniband/hw/qib/Kconfig" diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index 5740d1ba3568..012156624b82 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -859,8 +859,8 @@ static struct cm_id_private *cm_alloc_id_priv(struct ib_device *device, atomic_set(&cm_id_priv->work_count, -1); refcount_set(&cm_id_priv->refcount, 1); - ret = xa_alloc_cyclic_irq(&cm.local_id_table, &id, NULL, xa_limit_32b, - &cm.local_id_next, GFP_KERNEL); + ret = xa_alloc_cyclic(&cm.local_id_table, &id, NULL, xa_limit_32b, + &cm.local_id_next, GFP_KERNEL); if (ret < 0) goto error; cm_id_priv->id.local_id = (__force __be32)id ^ cm.random_id_operand; @@ -878,8 +878,8 @@ error: */ static void cm_finalize_id(struct cm_id_private *cm_id_priv) { - xa_store_irq(&cm.local_id_table, cm_local_id(cm_id_priv->id.local_id), - cm_id_priv, GFP_KERNEL); + xa_store(&cm.local_id_table, cm_local_id(cm_id_priv->id.local_id), + cm_id_priv, GFP_ATOMIC); } struct ib_cm_id *ib_create_cm_id(struct ib_device *device, @@ -1169,7 +1169,7 @@ retest: spin_unlock(&cm.lock); spin_unlock_irq(&cm_id_priv->lock); - xa_erase_irq(&cm.local_id_table, cm_local_id(cm_id->local_id)); + xa_erase(&cm.local_id_table, cm_local_id(cm_id->local_id)); cm_deref_id(cm_id_priv); wait_for_completion(&cm_id_priv->comp); while ((work = cm_dequeue_work(cm_id_priv)) != NULL) @@ -4482,7 +4482,7 @@ static int __init ib_cm_init(void) cm.remote_id_table = RB_ROOT; cm.remote_qp_table = RB_ROOT; cm.remote_sidr_table = RB_ROOT; - xa_init_flags(&cm.local_id_table, XA_FLAGS_ALLOC | XA_FLAGS_LOCK_IRQ); + xa_init_flags(&cm.local_id_table, XA_FLAGS_ALLOC); get_random_bytes(&cm.random_id_operand, sizeof cm.random_id_operand); INIT_LIST_HEAD(&cm.timewait_list); diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c index 7eaf99538216..c87b94ea2939 100644 --- a/drivers/infiniband/hw/hfi1/chip.c +++ b/drivers/infiniband/hw/hfi1/chip.c @@ -15245,7 +15245,8 @@ int hfi1_init_dd(struct hfi1_devdata *dd) & CCE_REVISION_SW_MASK); /* alloc netdev data */ - if (hfi1_netdev_alloc(dd)) + ret = hfi1_netdev_alloc(dd); + if (ret) goto bail_cleanup; ret = set_up_context_variables(dd); diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c index fa2a3fa0c3e4..6895bac53990 100644 --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c @@ -266,7 +266,7 @@ static int pvrdma_register_device(struct pvrdma_dev *dev) } ret = ib_device_set_netdev(&dev->ib_dev, dev->netdev, 1); if (ret) - return ret; + goto err_srq_free; spin_lock_init(&dev->srq_tbl_lock); rdma_set_device_sysfs_group(&dev->ib_dev, &pvrdma_attr_group); diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h index f0e5ffba2d51..97ed8f952f6e 100644 --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h @@ -176,7 +176,7 @@ struct pvrdma_port_attr { u8 subnet_timeout; u8 init_type_reply; u8 active_width; - u16 active_speed; + u8 active_speed; u8 phys_state; u8 reserved[2]; }; diff --git a/drivers/infiniband/sw/rdmavt/Kconfig b/drivers/infiniband/sw/rdmavt/Kconfig index 9ef5f5ce1ff6..c8e268082952 100644 --- a/drivers/infiniband/sw/rdmavt/Kconfig +++ b/drivers/infiniband/sw/rdmavt/Kconfig @@ -1,7 +1,8 @@ # SPDX-License-Identifier: GPL-2.0-only config INFINIBAND_RDMAVT tristate "RDMA verbs transport library" - depends on X86_64 && ARCH_DMA_ADDR_T_64BIT + depends on INFINIBAND_VIRT_DMA + depends on X86_64 depends on PCI select DMA_VIRT_OPS help diff --git a/drivers/infiniband/sw/rdmavt/vt.c b/drivers/infiniband/sw/rdmavt/vt.c index 52218684ad4a..670a9623b46e 100644 --- a/drivers/infiniband/sw/rdmavt/vt.c +++ b/drivers/infiniband/sw/rdmavt/vt.c @@ -524,6 +524,7 @@ static noinline int check_support(struct rvt_dev_info *rdi, int verb) int rvt_register_device(struct rvt_dev_info *rdi) { int ret = 0, i; + u64 dma_mask; if (!rdi) return -EINVAL; @@ -580,8 +581,10 @@ int rvt_register_device(struct rvt_dev_info *rdi) /* DMA Operations */ rdi->ibdev.dev.dma_parms = rdi->ibdev.dev.parent->dma_parms; - dma_set_coherent_mask(&rdi->ibdev.dev, - rdi->ibdev.dev.parent->coherent_dma_mask); + dma_mask = IS_ENABLED(CONFIG_64BIT) ? DMA_BIT_MASK(64) : DMA_BIT_MASK(32); + ret = dma_coerce_mask_and_coherent(&rdi->ibdev.dev, dma_mask); + if (ret) + goto bail_wss; /* Protection Domain */ spin_lock_init(&rdi->n_pds_lock); diff --git a/drivers/infiniband/sw/rxe/Kconfig b/drivers/infiniband/sw/rxe/Kconfig index a0c6c7dfc181..8810bfa68049 100644 --- a/drivers/infiniband/sw/rxe/Kconfig +++ b/drivers/infiniband/sw/rxe/Kconfig @@ -2,7 +2,7 @@ config RDMA_RXE tristate "Software RDMA over Ethernet (RoCE) driver" depends on INET && PCI && INFINIBAND - depends on !64BIT || ARCH_DMA_ADDR_T_64BIT + depends on INFINIBAND_VIRT_DMA select NET_UDP_TUNNEL select CRYPTO_CRC32 select DMA_VIRT_OPS diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c index 1fc022362fbe..f9c832e82552 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.c +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c @@ -1118,6 +1118,7 @@ int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name) int err; struct ib_device *dev = &rxe->ib_dev; struct crypto_shash *tfm; + u64 dma_mask; strlcpy(dev->node_desc, "rxe", sizeof(dev->node_desc)); @@ -1130,7 +1131,10 @@ int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name) rxe->ndev->dev_addr); dev->dev.dma_parms = &rxe->dma_parms; dma_set_max_seg_size(&dev->dev, UINT_MAX); - dma_set_coherent_mask(&dev->dev, dma_get_required_mask(&dev->dev)); + dma_mask = IS_ENABLED(CONFIG_64BIT) ? DMA_BIT_MASK(64) : DMA_BIT_MASK(32); + err = dma_coerce_mask_and_coherent(&dev->dev, dma_mask); + if (err) + return err; dev->uverbs_cmd_mask = BIT_ULL(IB_USER_VERBS_CMD_GET_CONTEXT) | BIT_ULL(IB_USER_VERBS_CMD_CREATE_COMP_CHANNEL) diff --git a/drivers/infiniband/sw/siw/Kconfig b/drivers/infiniband/sw/siw/Kconfig index b622fc62f2cd..3450ba5081df 100644 --- a/drivers/infiniband/sw/siw/Kconfig +++ b/drivers/infiniband/sw/siw/Kconfig @@ -1,6 +1,7 @@ config RDMA_SIW tristate "Software RDMA over TCP/IP (iWARP) driver" depends on INET && INFINIBAND && LIBCRC32C + depends on INFINIBAND_VIRT_DMA select DMA_VIRT_OPS help This driver implements the iWARP RDMA transport over diff --git a/drivers/infiniband/sw/siw/siw_main.c b/drivers/infiniband/sw/siw/siw_main.c index ca8bc7296867..181e06c1c43d 100644 --- a/drivers/infiniband/sw/siw/siw_main.c +++ b/drivers/infiniband/sw/siw/siw_main.c @@ -306,6 +306,7 @@ static struct siw_device *siw_device_create(struct net_device *netdev) struct siw_device *sdev = NULL; struct ib_device *base_dev; struct device *parent = netdev->dev.parent; + u64 dma_mask; int rv; if (!parent) { @@ -384,8 +385,10 @@ static struct siw_device *siw_device_create(struct net_device *netdev) base_dev->dev.parent = parent; base_dev->dev.dma_parms = &sdev->dma_parms; dma_set_max_seg_size(&base_dev->dev, UINT_MAX); - dma_set_coherent_mask(&base_dev->dev, - dma_get_required_mask(&base_dev->dev)); + dma_mask = IS_ENABLED(CONFIG_64BIT) ? DMA_BIT_MASK(64) : DMA_BIT_MASK(32); + if (dma_coerce_mask_and_coherent(&base_dev->dev, dma_mask)) + goto error; + base_dev->num_comp_vectors = num_possible_cpus(); xa_init_flags(&sdev->qp_xa, XA_FLAGS_ALLOC1); diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index 0065eb17ae36..53a8becac827 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -622,10 +622,11 @@ static int srpt_refresh_port(struct srpt_port *sport) /** * srpt_unregister_mad_agent - unregister MAD callback functions * @sdev: SRPT HCA pointer. + * @port_cnt: number of ports with registered MAD * * Note: It is safe to call this function more than once for the same device. */ -static void srpt_unregister_mad_agent(struct srpt_device *sdev) +static void srpt_unregister_mad_agent(struct srpt_device *sdev, int port_cnt) { struct ib_port_modify port_modify = { .clr_port_cap_mask = IB_PORT_DEVICE_MGMT_SUP, @@ -633,7 +634,7 @@ static void srpt_unregister_mad_agent(struct srpt_device *sdev) struct srpt_port *sport; int i; - for (i = 1; i <= sdev->device->phys_port_cnt; i++) { + for (i = 1; i <= port_cnt; i++) { sport = &sdev->port[i - 1]; WARN_ON(sport->port != i); if (sport->mad_agent) { @@ -3185,7 +3186,8 @@ static int srpt_add_one(struct ib_device *device) if (ret) { pr_err("MAD registration failed for %s-%d.\n", dev_name(&sdev->device->dev), i); - goto err_event; + i--; + goto err_port; } } @@ -3197,7 +3199,8 @@ static int srpt_add_one(struct ib_device *device) pr_debug("added %s.\n", dev_name(&device->dev)); return 0; -err_event: +err_port: + srpt_unregister_mad_agent(sdev, i); ib_unregister_event_handler(&sdev->event_handler); err_cm: if (sdev->cm_id) @@ -3221,7 +3224,7 @@ static void srpt_remove_one(struct ib_device *device, void *client_data) struct srpt_device *sdev = client_data; int i; - srpt_unregister_mad_agent(sdev); + srpt_unregister_mad_agent(sdev, sdev->device->phys_port_cnt); ib_unregister_event_handler(&sdev->event_handler); diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.h b/drivers/infiniband/ulp/srpt/ib_srpt.h index 41435a699b53..bdeb010efee6 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.h +++ b/drivers/infiniband/ulp/srpt/ib_srpt.h @@ -256,6 +256,7 @@ enum rdma_ch_state { * @rdma_cm: See below. * @rdma_cm.cm_id: RDMA CM ID associated with the channel. * @cq: IB completion queue for this channel. + * @cq_size: Number of CQEs in @cq. * @zw_cqe: Zero-length write CQE. * @rcu: RCU head. * @kref: kref for this channel. diff --git a/drivers/input/keyboard/sunkbd.c b/drivers/input/keyboard/sunkbd.c index 27126e621eb6..d450f11b98a7 100644 --- a/drivers/input/keyboard/sunkbd.c +++ b/drivers/input/keyboard/sunkbd.c @@ -99,7 +99,8 @@ static irqreturn_t sunkbd_interrupt(struct serio *serio, switch (data) { case SUNKBD_RET_RESET: - schedule_work(&sunkbd->tq); + if (sunkbd->enabled) + schedule_work(&sunkbd->tq); sunkbd->reset = -1; break; @@ -200,16 +201,12 @@ static int sunkbd_initialize(struct sunkbd *sunkbd) } /* - * sunkbd_reinit() sets leds and beeps to a state the computer remembers they - * were in. + * sunkbd_set_leds_beeps() sets leds and beeps to a state the computer remembers + * they were in. */ -static void sunkbd_reinit(struct work_struct *work) +static void sunkbd_set_leds_beeps(struct sunkbd *sunkbd) { - struct sunkbd *sunkbd = container_of(work, struct sunkbd, tq); - - wait_event_interruptible_timeout(sunkbd->wait, sunkbd->reset >= 0, HZ); - serio_write(sunkbd->serio, SUNKBD_CMD_SETLED); serio_write(sunkbd->serio, (!!test_bit(LED_CAPSL, sunkbd->dev->led) << 3) | @@ -222,11 +219,39 @@ static void sunkbd_reinit(struct work_struct *work) SUNKBD_CMD_BELLOFF - !!test_bit(SND_BELL, sunkbd->dev->snd)); } + +/* + * sunkbd_reinit() wait for the keyboard reset to complete and restores state + * of leds and beeps. + */ + +static void sunkbd_reinit(struct work_struct *work) +{ + struct sunkbd *sunkbd = container_of(work, struct sunkbd, tq); + + /* + * It is OK that we check sunkbd->enabled without pausing serio, + * as we only want to catch true->false transition that will + * happen once and we will be woken up for it. + */ + wait_event_interruptible_timeout(sunkbd->wait, + sunkbd->reset >= 0 || !sunkbd->enabled, + HZ); + + if (sunkbd->reset >= 0 && sunkbd->enabled) + sunkbd_set_leds_beeps(sunkbd); +} + static void sunkbd_enable(struct sunkbd *sunkbd, bool enable) { serio_pause_rx(sunkbd->serio); sunkbd->enabled = enable; serio_continue_rx(sunkbd->serio); + + if (!enable) { + wake_up_interruptible(&sunkbd->wait); + cancel_work_sync(&sunkbd->tq); + } } /* diff --git a/drivers/input/misc/adxl34x.c b/drivers/input/misc/adxl34x.c index 5fe92d4ba3f0..4cc4e8ff42b3 100644 --- a/drivers/input/misc/adxl34x.c +++ b/drivers/input/misc/adxl34x.c @@ -696,7 +696,7 @@ struct adxl34x *adxl34x_probe(struct device *dev, int irq, struct input_dev *input_dev; const struct adxl34x_platform_data *pdata; int err, range, i; - unsigned char revid; + int revid; if (!irq) { dev_err(dev, "no IRQ?\n"); diff --git a/drivers/input/mouse/elan_i2c.h b/drivers/input/mouse/elan_i2c.h index c75b00c45d75..36e3cd908671 100644 --- a/drivers/input/mouse/elan_i2c.h +++ b/drivers/input/mouse/elan_i2c.h @@ -78,7 +78,7 @@ struct elan_transport_ops { int (*iap_reset)(struct i2c_client *client); int (*prepare_fw_update)(struct i2c_client *client, u16 ic_type, - u8 iap_version); + u8 iap_version, u16 fw_page_size); int (*write_fw_block)(struct i2c_client *client, u16 fw_page_size, const u8 *page, u16 checksum, int idx); int (*finish_fw_update)(struct i2c_client *client, diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c index c599e21a8478..61ed3f5ca219 100644 --- a/drivers/input/mouse/elan_i2c_core.c +++ b/drivers/input/mouse/elan_i2c_core.c @@ -497,7 +497,8 @@ static int __elan_update_firmware(struct elan_tp_data *data, u16 sw_checksum = 0, fw_checksum = 0; error = data->ops->prepare_fw_update(client, data->ic_type, - data->iap_version); + data->iap_version, + data->fw_page_size); if (error) return error; diff --git a/drivers/input/mouse/elan_i2c_i2c.c b/drivers/input/mouse/elan_i2c_i2c.c index 5a496d4ffa49..13dc097eb6c6 100644 --- a/drivers/input/mouse/elan_i2c_i2c.c +++ b/drivers/input/mouse/elan_i2c_i2c.c @@ -517,7 +517,7 @@ static int elan_i2c_set_flash_key(struct i2c_client *client) return 0; } -static int elan_read_write_iap_type(struct i2c_client *client) +static int elan_read_write_iap_type(struct i2c_client *client, u16 fw_page_size) { int error; u16 constant; @@ -526,7 +526,7 @@ static int elan_read_write_iap_type(struct i2c_client *client) do { error = elan_i2c_write_cmd(client, ETP_I2C_IAP_TYPE_CMD, - ETP_I2C_IAP_TYPE_REG); + fw_page_size / 2); if (error) { dev_err(&client->dev, "cannot write iap type: %d\n", error); @@ -543,7 +543,7 @@ static int elan_read_write_iap_type(struct i2c_client *client) constant = le16_to_cpup((__le16 *)val); dev_dbg(&client->dev, "iap type reg: 0x%04x\n", constant); - if (constant == ETP_I2C_IAP_TYPE_REG) + if (constant == fw_page_size / 2) return 0; } while (--retry > 0); @@ -553,7 +553,7 @@ static int elan_read_write_iap_type(struct i2c_client *client) } static int elan_i2c_prepare_fw_update(struct i2c_client *client, u16 ic_type, - u8 iap_version) + u8 iap_version, u16 fw_page_size) { struct device *dev = &client->dev; int error; @@ -594,7 +594,7 @@ static int elan_i2c_prepare_fw_update(struct i2c_client *client, u16 ic_type, } if (ic_type >= 0x0D && iap_version >= 1) { - error = elan_read_write_iap_type(client); + error = elan_read_write_iap_type(client, fw_page_size); if (error) return error; } diff --git a/drivers/input/mouse/elan_i2c_smbus.c b/drivers/input/mouse/elan_i2c_smbus.c index 8ff823751f3b..1820f1cfc1dc 100644 --- a/drivers/input/mouse/elan_i2c_smbus.c +++ b/drivers/input/mouse/elan_i2c_smbus.c @@ -340,7 +340,7 @@ static int elan_smbus_set_flash_key(struct i2c_client *client) } static int elan_smbus_prepare_fw_update(struct i2c_client *client, u16 ic_type, - u8 iap_version) + u8 iap_version, u16 fw_page_size) { struct device *dev = &client->dev; int len; diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c index d3eda48032e3..944cbb519c6d 100644 --- a/drivers/input/serio/i8042.c +++ b/drivers/input/serio/i8042.c @@ -122,6 +122,7 @@ module_param_named(unmask_kbd_data, i8042_unmask_kbd_data, bool, 0600); MODULE_PARM_DESC(unmask_kbd_data, "Unconditional enable (may reveal sensitive data) of normally sanitize-filtered kbd data traffic debug log [pre-condition: i8042.debug=1 enabled]"); #endif +static bool i8042_present; static bool i8042_bypass_aux_irq_test; static char i8042_kbd_firmware_id[128]; static char i8042_aux_firmware_id[128]; @@ -343,6 +344,9 @@ int i8042_command(unsigned char *param, int command) unsigned long flags; int retval; + if (!i8042_present) + return -1; + spin_lock_irqsave(&i8042_lock, flags); retval = __i8042_command(param, command); spin_unlock_irqrestore(&i8042_lock, flags); @@ -1612,12 +1616,15 @@ static int __init i8042_init(void) err = i8042_platform_init(); if (err) - return err; + return (err == -ENODEV) ? 0 : err; err = i8042_controller_check(); if (err) goto err_platform_exit; + /* Set this before creating the dev to allow i8042_command to work right away */ + i8042_present = true; + pdev = platform_create_bundle(&i8042_driver, i8042_probe, NULL, 0, NULL, 0); if (IS_ERR(pdev)) { err = PTR_ERR(pdev); @@ -1636,6 +1643,9 @@ static int __init i8042_init(void) static void __exit i8042_exit(void) { + if (!i8042_present) + return; + platform_device_unregister(i8042_platform_device); platform_driver_unregister(&i8042_driver); i8042_platform_exit(); diff --git a/drivers/input/touchscreen/Kconfig b/drivers/input/touchscreen/Kconfig index f012fe746df0..cc18f54ea887 100644 --- a/drivers/input/touchscreen/Kconfig +++ b/drivers/input/touchscreen/Kconfig @@ -96,6 +96,7 @@ config TOUCHSCREEN_AD7879_SPI config TOUCHSCREEN_ADC tristate "Generic ADC based resistive touchscreen" depends on IIO + select IIO_BUFFER select IIO_BUFFER_CB help Say Y here if you want to use the generic ADC diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h index f696ac7c5f89..89647700bab2 100644 --- a/drivers/iommu/amd/amd_iommu_types.h +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -409,7 +409,11 @@ extern bool amd_iommu_np_cache; /* Only true if all IOMMUs support device IOTLBs */ extern bool amd_iommu_iotlb_sup; -#define MAX_IRQS_PER_TABLE 256 +/* + * AMD IOMMU hardware only support 512 IRTEs despite + * the architectural limitation of 2048 entries. + */ +#define MAX_IRQS_PER_TABLE 512 #define IRQ_TABLE_ALIGNMENT 128 struct irq_remap_table { diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index 404b40af31cb..11319e4dce4a 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -333,6 +333,13 @@ static void dmar_pci_bus_del_dev(struct dmar_pci_notify_info *info) dmar_iommu_notify_scope_dev(info); } +static inline void vf_inherit_msi_domain(struct pci_dev *pdev) +{ + struct pci_dev *physfn = pci_physfn(pdev); + + dev_set_msi_domain(&pdev->dev, dev_get_msi_domain(&physfn->dev)); +} + static int dmar_pci_bus_notifier(struct notifier_block *nb, unsigned long action, void *data) { @@ -342,8 +349,20 @@ static int dmar_pci_bus_notifier(struct notifier_block *nb, /* Only care about add/remove events for physical functions. * For VFs we actually do the lookup based on the corresponding * PF in device_to_iommu() anyway. */ - if (pdev->is_virtfn) + if (pdev->is_virtfn) { + /* + * Ensure that the VF device inherits the irq domain of the + * PF device. Ideally the device would inherit the domain + * from the bus, but DMAR can have multiple units per bus + * which makes this impossible. The VF 'bus' could inherit + * from the PF device, but that's yet another x86'sism to + * inflict on everybody else. + */ + if (action == BUS_NOTIFY_ADD_DEVICE) + vf_inherit_msi_domain(pdev); return NOTIFY_DONE; + } + if (action != BUS_NOTIFY_ADD_DEVICE && action != BUS_NOTIFY_REMOVED_DEVICE) return NOTIFY_DONE; diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 8651f6d4dfa0..c71a9c279a33 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -179,7 +179,7 @@ static int rwbf_quirk; * (used when kernel is launched w/ TXT) */ static int force_on = 0; -int intel_iommu_tboot_noforce; +static int intel_iommu_tboot_noforce; static int no_platform_optin; #define ROOT_ENTRY_NR (VTD_PAGE_SIZE/sizeof(struct root_entry)) @@ -2525,6 +2525,9 @@ struct dmar_domain *find_domain(struct device *dev) { struct device_domain_info *info; + if (unlikely(!dev || !dev->iommu)) + return NULL; + if (unlikely(attach_deferred(dev))) return NULL; @@ -3815,9 +3818,8 @@ bounce_map_single(struct device *dev, phys_addr_t paddr, size_t size, * page aligned, we don't need to use a bounce page. */ if (!IS_ALIGNED(paddr | size, VTD_PAGE_SIZE)) { - tlb_addr = swiotlb_tbl_map_single(dev, - phys_to_dma_unencrypted(dev, io_tlb_start), - paddr, size, aligned_size, dir, attrs); + tlb_addr = swiotlb_tbl_map_single(dev, paddr, size, + aligned_size, dir, attrs); if (tlb_addr == DMA_MAPPING_ERROR) { goto swiotlb_error; } else { @@ -4882,7 +4884,8 @@ int __init intel_iommu_init(void) * Intel IOMMU is required for a TXT/tboot launch or platform * opt in, so enforce that. */ - force_on = tboot_force_iommu() || platform_optin_force_iommu(); + force_on = (!intel_iommu_tboot_noforce && tboot_force_iommu()) || + platform_optin_force_iommu(); if (iommu_init_mempool()) { if (force_on) diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c index f1861fa3d0e4..3242ebd0bca3 100644 --- a/drivers/iommu/intel/svm.c +++ b/drivers/iommu/intel/svm.c @@ -279,6 +279,7 @@ int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev, struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL); struct intel_svm_dev *sdev = NULL; struct dmar_domain *dmar_domain; + struct device_domain_info *info; struct intel_svm *svm = NULL; int ret = 0; @@ -310,6 +311,10 @@ int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev, if (data->hpasid <= 0 || data->hpasid >= PASID_MAX) return -EINVAL; + info = get_domain_info(dev); + if (!info) + return -EINVAL; + dmar_domain = to_dmar_domain(domain); mutex_lock(&pasid_mutex); @@ -357,6 +362,7 @@ int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev, goto out; } sdev->dev = dev; + sdev->sid = PCI_DEVID(info->bus, info->devfn); /* Only count users if device has aux domains */ if (iommu_dev_feature_enabled(dev, IOMMU_DEV_FEAT_AUX)) @@ -1029,7 +1035,7 @@ no_pasid: resp.qw0 = QI_PGRP_PASID(req->pasid) | QI_PGRP_DID(req->rid) | QI_PGRP_PASID_P(req->pasid_present) | - QI_PGRP_PDP(req->pasid_present) | + QI_PGRP_PDP(req->priv_data_present) | QI_PGRP_RESP_CODE(result) | QI_PGRP_RESP_TYPE; resp.qw1 = QI_PGRP_IDX(req->prg_index) | diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 8c470f451a32..b53446bb8c6b 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -2071,7 +2071,7 @@ EXPORT_SYMBOL_GPL(iommu_uapi_cache_invalidate); static int iommu_check_bind_data(struct iommu_gpasid_bind_data *data) { - u32 mask; + u64 mask; int i; if (data->version != IOMMU_GPASID_BIND_VERSION_1) diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig index c6098eee0c7c..2aa79c32ee22 100644 --- a/drivers/irqchip/Kconfig +++ b/drivers/irqchip/Kconfig @@ -180,7 +180,6 @@ config IRQ_MIPS_CPU select GENERIC_IRQ_CHIP select GENERIC_IRQ_IPI if SYS_SUPPORTS_MULTITHREADING select IRQ_DOMAIN - select IRQ_DOMAIN_HIERARCHY if GENERIC_IRQ_IPI select GENERIC_IRQ_EFFECTIVE_AFF_MASK config CLPS711X_IRQCHIP @@ -315,7 +314,6 @@ config KEYSTONE_IRQ config MIPS_GIC bool select GENERIC_IRQ_IPI - select IRQ_DOMAIN_HIERARCHY select MIPS_CM config INGENIC_IRQ @@ -591,6 +589,7 @@ config LOONGSON_PCH_MSI config MST_IRQ bool "MStar Interrupt Controller" + depends on ARCH_MEDIATEK || ARCH_MSTARV7 || COMPILE_TEST default ARCH_MEDIATEK select IRQ_DOMAIN select IRQ_DOMAIN_HIERARCHY diff --git a/drivers/irqchip/irq-bcm2836.c b/drivers/irqchip/irq-bcm2836.c index 97838eb705f9..cbc7c740e4dc 100644 --- a/drivers/irqchip/irq-bcm2836.c +++ b/drivers/irqchip/irq-bcm2836.c @@ -244,7 +244,7 @@ static int bcm2836_cpu_dying(unsigned int cpu) #define BITS_PER_MBOX 32 -static void bcm2836_arm_irqchip_smp_init(void) +static void __init bcm2836_arm_irqchip_smp_init(void) { struct irq_fwspec ipi_fwspec = { .fwnode = intc.domain->fwnode, diff --git a/drivers/irqchip/irq-mst-intc.c b/drivers/irqchip/irq-mst-intc.c index 4be077591898..143657b0cf28 100644 --- a/drivers/irqchip/irq-mst-intc.c +++ b/drivers/irqchip/irq-mst-intc.c @@ -154,8 +154,8 @@ static const struct irq_domain_ops mst_intc_domain_ops = { .free = irq_domain_free_irqs_common, }; -int __init -mst_intc_of_init(struct device_node *dn, struct device_node *parent) +static int __init mst_intc_of_init(struct device_node *dn, + struct device_node *parent) { struct irq_domain *domain, *domain_parent; struct mst_intc_chip_data *cd; diff --git a/drivers/irqchip/irq-renesas-intc-irqpin.c b/drivers/irqchip/irq-renesas-intc-irqpin.c index 3819185bfd02..cb7f60b3b4a9 100644 --- a/drivers/irqchip/irq-renesas-intc-irqpin.c +++ b/drivers/irqchip/irq-renesas-intc-irqpin.c @@ -71,8 +71,7 @@ struct intc_irqpin_priv { }; struct intc_irqpin_config { - unsigned int irlm_bit; - unsigned needs_irlm:1; + int irlm_bit; /* -1 if non-existent */ }; static unsigned long intc_irqpin_read32(void __iomem *iomem) @@ -349,11 +348,10 @@ static const struct irq_domain_ops intc_irqpin_irq_domain_ops = { static const struct intc_irqpin_config intc_irqpin_irlm_r8a777x = { .irlm_bit = 23, /* ICR0.IRLM0 */ - .needs_irlm = 1, }; static const struct intc_irqpin_config intc_irqpin_rmobile = { - .needs_irlm = 0, + .irlm_bit = -1, }; static const struct of_device_id intc_irqpin_dt_ids[] = { @@ -470,7 +468,7 @@ static int intc_irqpin_probe(struct platform_device *pdev) } /* configure "individual IRQ mode" where needed */ - if (config && config->needs_irlm) { + if (config && config->irlm_bit >= 0) { if (io[INTC_IRQPIN_REG_IRLM]) intc_irqpin_read_modify_write(p, INTC_IRQPIN_REG_IRLM, config->irlm_bit, 1, 1); diff --git a/drivers/irqchip/irq-sifive-plic.c b/drivers/irqchip/irq-sifive-plic.c index eaa3e9fe54e9..6f432d2a5ceb 100644 --- a/drivers/irqchip/irq-sifive-plic.c +++ b/drivers/irqchip/irq-sifive-plic.c @@ -99,7 +99,7 @@ static inline void plic_irq_toggle(const struct cpumask *mask, struct irq_data *d, int enable) { int cpu; - struct plic_priv *priv = irq_get_chip_data(d->irq); + struct plic_priv *priv = irq_data_get_irq_chip_data(d); writel(enable, priv->regs + PRIORITY_BASE + d->hwirq * PRIORITY_PER_ID); for_each_cpu(cpu, mask) { @@ -115,7 +115,7 @@ static void plic_irq_unmask(struct irq_data *d) { struct cpumask amask; unsigned int cpu; - struct plic_priv *priv = irq_get_chip_data(d->irq); + struct plic_priv *priv = irq_data_get_irq_chip_data(d); cpumask_and(&amask, &priv->lmask, cpu_online_mask); cpu = cpumask_any_and(irq_data_get_affinity_mask(d), @@ -127,7 +127,7 @@ static void plic_irq_unmask(struct irq_data *d) static void plic_irq_mask(struct irq_data *d) { - struct plic_priv *priv = irq_get_chip_data(d->irq); + struct plic_priv *priv = irq_data_get_irq_chip_data(d); plic_irq_toggle(&priv->lmask, d, 0); } @@ -138,7 +138,7 @@ static int plic_set_affinity(struct irq_data *d, { unsigned int cpu; struct cpumask amask; - struct plic_priv *priv = irq_get_chip_data(d->irq); + struct plic_priv *priv = irq_data_get_irq_chip_data(d); cpumask_and(&amask, &priv->lmask, mask_val); @@ -151,7 +151,7 @@ static int plic_set_affinity(struct irq_data *d, return -EINVAL; plic_irq_toggle(&priv->lmask, d, 0); - plic_irq_toggle(cpumask_of(cpu), d, 1); + plic_irq_toggle(cpumask_of(cpu), d, !irqd_irq_masked(d)); irq_data_update_effective_affinity(d, cpumask_of(cpu)); diff --git a/drivers/irqchip/irq-stm32-exti.c b/drivers/irqchip/irq-stm32-exti.c index 0c2c61db26b4..8662d7b7b262 100644 --- a/drivers/irqchip/irq-stm32-exti.c +++ b/drivers/irqchip/irq-stm32-exti.c @@ -195,6 +195,10 @@ static const struct stm32_desc_irq stm32mp1_desc_irq[] = { { .exti = 25, .irq_parent = 107, .chip = &stm32_exti_h_chip_direct }, { .exti = 30, .irq_parent = 52, .chip = &stm32_exti_h_chip_direct }, { .exti = 47, .irq_parent = 93, .chip = &stm32_exti_h_chip_direct }, + { .exti = 48, .irq_parent = 138, .chip = &stm32_exti_h_chip_direct }, + { .exti = 50, .irq_parent = 139, .chip = &stm32_exti_h_chip_direct }, + { .exti = 52, .irq_parent = 140, .chip = &stm32_exti_h_chip_direct }, + { .exti = 53, .irq_parent = 141, .chip = &stm32_exti_h_chip_direct }, { .exti = 54, .irq_parent = 135, .chip = &stm32_exti_h_chip_direct }, { .exti = 61, .irq_parent = 100, .chip = &stm32_exti_h_chip_direct }, { .exti = 65, .irq_parent = 144, .chip = &stm32_exti_h_chip }, diff --git a/drivers/irqchip/irq-ti-sci-inta.c b/drivers/irqchip/irq-ti-sci-inta.c index e0cceb81c648..b2ab8db439d9 100644 --- a/drivers/irqchip/irq-ti-sci-inta.c +++ b/drivers/irqchip/irq-ti-sci-inta.c @@ -85,6 +85,17 @@ struct ti_sci_inta_vint_desc { * @base: Base address of the memory mapped IO registers * @pdev: Pointer to platform device. * @ti_sci_id: TI-SCI device identifier + * @unmapped_cnt: Number of @unmapped_dev_ids entries + * @unmapped_dev_ids: Pointer to an array of TI-SCI device identifiers of + * unmapped event sources. + * Unmapped Events are not part of the Global Event Map and + * they are converted to Global event within INTA to be + * received by the same INTA to generate an interrupt. + * In case an interrupt request comes for a device which is + * generating Unmapped Event, we must use the INTA's TI-SCI + * device identifier in place of the source device + * identifier to let sysfw know where it has to program the + * Global Event number. */ struct ti_sci_inta_irq_domain { const struct ti_sci_handle *sci; @@ -96,11 +107,37 @@ struct ti_sci_inta_irq_domain { void __iomem *base; struct platform_device *pdev; u32 ti_sci_id; + + int unmapped_cnt; + u16 *unmapped_dev_ids; }; #define to_vint_desc(e, i) container_of(e, struct ti_sci_inta_vint_desc, \ events[i]) +static u16 ti_sci_inta_get_dev_id(struct ti_sci_inta_irq_domain *inta, u32 hwirq) +{ + u16 dev_id = HWIRQ_TO_DEVID(hwirq); + int i; + + if (inta->unmapped_cnt == 0) + return dev_id; + + /* + * For devices sending Unmapped Events we must use the INTA's TI-SCI + * device identifier number to be able to convert it to a Global Event + * and map it to an interrupt. + */ + for (i = 0; i < inta->unmapped_cnt; i++) { + if (dev_id == inta->unmapped_dev_ids[i]) { + dev_id = inta->ti_sci_id; + break; + } + } + + return dev_id; +} + /** * ti_sci_inta_irq_handler() - Chained IRQ handler for the vint irqs * @desc: Pointer to irq_desc corresponding to the irq @@ -251,7 +288,7 @@ static struct ti_sci_inta_event_desc *ti_sci_inta_alloc_event(struct ti_sci_inta u16 dev_id, dev_index; int err; - dev_id = HWIRQ_TO_DEVID(hwirq); + dev_id = ti_sci_inta_get_dev_id(inta, hwirq); dev_index = HWIRQ_TO_IRQID(hwirq); event_desc = &vint_desc->events[free_bit]; @@ -352,14 +389,15 @@ static void ti_sci_inta_free_irq(struct ti_sci_inta_event_desc *event_desc, { struct ti_sci_inta_vint_desc *vint_desc; struct ti_sci_inta_irq_domain *inta; + u16 dev_id; vint_desc = to_vint_desc(event_desc, event_desc->vint_bit); inta = vint_desc->domain->host_data; + dev_id = ti_sci_inta_get_dev_id(inta, hwirq); /* free event irq */ mutex_lock(&inta->vint_mutex); inta->sci->ops.rm_irq_ops.free_event_map(inta->sci, - HWIRQ_TO_DEVID(hwirq), - HWIRQ_TO_IRQID(hwirq), + dev_id, HWIRQ_TO_IRQID(hwirq), inta->ti_sci_id, vint_desc->vint_id, event_desc->global_event, @@ -574,6 +612,41 @@ static struct msi_domain_info ti_sci_inta_msi_domain_info = { .chip = &ti_sci_inta_msi_irq_chip, }; +static int ti_sci_inta_get_unmapped_sources(struct ti_sci_inta_irq_domain *inta) +{ + struct device *dev = &inta->pdev->dev; + struct device_node *node = dev_of_node(dev); + struct of_phandle_iterator it; + int count, err, ret, i; + + count = of_count_phandle_with_args(node, "ti,unmapped-event-sources", NULL); + if (count <= 0) + return 0; + + inta->unmapped_dev_ids = devm_kcalloc(dev, count, + sizeof(*inta->unmapped_dev_ids), + GFP_KERNEL); + if (!inta->unmapped_dev_ids) + return -ENOMEM; + + i = 0; + of_for_each_phandle(&it, err, node, "ti,unmapped-event-sources", NULL, 0) { + u32 dev_id; + + ret = of_property_read_u32(it.node, "ti,sci-dev-id", &dev_id); + if (ret) { + dev_err(dev, "ti,sci-dev-id read failure for %pOFf\n", it.node); + of_node_put(it.node); + return ret; + } + inta->unmapped_dev_ids[i++] = dev_id; + } + + inta->unmapped_cnt = count; + + return 0; +} + static int ti_sci_inta_irq_domain_probe(struct platform_device *pdev) { struct irq_domain *parent_domain, *domain, *msi_domain; @@ -629,6 +702,10 @@ static int ti_sci_inta_irq_domain_probe(struct platform_device *pdev) if (IS_ERR(inta->base)) return PTR_ERR(inta->base); + ret = ti_sci_inta_get_unmapped_sources(inta); + if (ret) + return ret; + domain = irq_domain_add_linear(dev_of_node(dev), ti_sci_get_num_resources(inta->vint), &ti_sci_inta_irq_domain_ops, inta); diff --git a/drivers/misc/habanalabs/common/command_buffer.c b/drivers/misc/habanalabs/common/command_buffer.c index 901e213daf40..ada570f35a41 100644 --- a/drivers/misc/habanalabs/common/command_buffer.c +++ b/drivers/misc/habanalabs/common/command_buffer.c @@ -142,11 +142,10 @@ static void cb_fini(struct hl_device *hdev, struct hl_cb *cb) { if (cb->is_internal) gen_pool_free(hdev->internal_cb_pool, - cb->kernel_address, cb->size); + (uintptr_t)cb->kernel_address, cb->size); else hdev->asic_funcs->asic_dma_free_coherent(hdev, cb->size, - (void *) (uintptr_t) cb->kernel_address, - cb->bus_address); + cb->kernel_address, cb->bus_address); kfree(cb); } @@ -230,7 +229,7 @@ static struct hl_cb *hl_cb_alloc(struct hl_device *hdev, u32 cb_size, return NULL; } - cb->kernel_address = (u64) (uintptr_t) p; + cb->kernel_address = p; cb->size = cb_size; return cb; @@ -509,7 +508,7 @@ int hl_cb_mmap(struct hl_fpriv *hpriv, struct vm_area_struct *vma) vma->vm_private_data = cb; - rc = hdev->asic_funcs->cb_mmap(hdev, vma, (void *) cb->kernel_address, + rc = hdev->asic_funcs->cb_mmap(hdev, vma, cb->kernel_address, cb->bus_address, cb->size); if (rc) { spin_lock(&cb->lock); diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h index 80d4d7385ffe..6ed974d2def0 100644 --- a/drivers/misc/habanalabs/common/habanalabs.h +++ b/drivers/misc/habanalabs/common/habanalabs.h @@ -452,7 +452,7 @@ struct hl_cb { struct list_head pool_list; struct list_head va_block_list; u64 id; - u64 kernel_address; + void *kernel_address; dma_addr_t bus_address; u32 mmap_size; u32 size; @@ -515,7 +515,7 @@ struct hl_hw_queue { struct hl_hw_sob hw_sob[HL_RSVD_SOBS]; struct hl_cs_job **shadow_queue; enum hl_queue_type queue_type; - u64 kernel_address; + void *kernel_address; dma_addr_t bus_address; u32 pi; atomic_t ci; @@ -544,7 +544,7 @@ struct hl_hw_queue { */ struct hl_cq { struct hl_device *hdev; - u64 kernel_address; + void *kernel_address; dma_addr_t bus_address; u32 cq_idx; u32 hw_queue_id; @@ -562,7 +562,7 @@ struct hl_cq { */ struct hl_eq { struct hl_device *hdev; - u64 kernel_address; + void *kernel_address; dma_addr_t bus_address; u32 ci; }; @@ -757,7 +757,7 @@ struct hl_asic_funcs { u32 (*get_dma_desc_list_size)(struct hl_device *hdev, struct sg_table *sgt); void (*add_end_of_cb_packets)(struct hl_device *hdev, - u64 kernel_address, u32 len, + void *kernel_address, u32 len, u64 cq_addr, u32 cq_val, u32 msix_num, bool eb); void (*update_eq_ci)(struct hl_device *hdev, u32 val); @@ -1382,13 +1382,13 @@ void hl_wreg(struct hl_device *hdev, u32 reg, u32 val); for (;;) { \ /* Verify we read updates done by other cores or by device */ \ mb(); \ - (val) = *((u32 *) (uintptr_t) (addr)); \ + (val) = *((u32 *)(addr)); \ if (mem_written_by_device) \ (val) = le32_to_cpu(*(__le32 *) &(val)); \ if (cond) \ break; \ if (timeout_us && ktime_compare(ktime_get(), __timeout) > 0) { \ - (val) = *((u32 *) (uintptr_t) (addr)); \ + (val) = *((u32 *)(addr)); \ if (mem_written_by_device) \ (val) = le32_to_cpu(*(__le32 *) &(val)); \ break; \ diff --git a/drivers/misc/habanalabs/common/hw_queue.c b/drivers/misc/habanalabs/common/hw_queue.c index 5e66c98fb0d3..250cf9cefc06 100644 --- a/drivers/misc/habanalabs/common/hw_queue.c +++ b/drivers/misc/habanalabs/common/hw_queue.c @@ -75,7 +75,7 @@ static void ext_and_hw_queue_submit_bd(struct hl_device *hdev, { struct hl_bd *bd; - bd = (struct hl_bd *) (uintptr_t) q->kernel_address; + bd = q->kernel_address; bd += hl_pi_2_offset(q->pi); bd->ctl = cpu_to_le32(ctl); bd->len = cpu_to_le32(len); @@ -335,8 +335,7 @@ static void int_queue_schedule_job(struct hl_cs_job *job) bd.len = cpu_to_le32(job->job_cb_size); bd.ptr = cpu_to_le64((u64) (uintptr_t) job->user_cb); - pi = (__le64 *) (uintptr_t) (q->kernel_address + - ((q->pi & (q->int_queue_len - 1)) * sizeof(bd))); + pi = q->kernel_address + (q->pi & (q->int_queue_len - 1)) * sizeof(bd); q->pi++; q->pi &= ((q->int_queue_len << 1) - 1); @@ -630,7 +629,7 @@ static int ext_and_cpu_queue_init(struct hl_device *hdev, struct hl_hw_queue *q, if (!p) return -ENOMEM; - q->kernel_address = (u64) (uintptr_t) p; + q->kernel_address = p; q->shadow_queue = kmalloc_array(HL_QUEUE_LENGTH, sizeof(*q->shadow_queue), @@ -653,11 +652,11 @@ free_queue: if (is_cpu_queue) hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev, HL_QUEUE_SIZE_IN_BYTES, - (void *) (uintptr_t) q->kernel_address); + q->kernel_address); else hdev->asic_funcs->asic_dma_free_coherent(hdev, HL_QUEUE_SIZE_IN_BYTES, - (void *) (uintptr_t) q->kernel_address, + q->kernel_address, q->bus_address); return rc; @@ -676,7 +675,7 @@ static int int_queue_init(struct hl_device *hdev, struct hl_hw_queue *q) return -EFAULT; } - q->kernel_address = (u64) (uintptr_t) p; + q->kernel_address = p; q->pi = 0; atomic_set(&q->ci, 0); @@ -704,7 +703,7 @@ static int hw_queue_init(struct hl_device *hdev, struct hl_hw_queue *q) if (!p) return -ENOMEM; - q->kernel_address = (u64) (uintptr_t) p; + q->kernel_address = p; /* Make sure read/write pointers are initialized to start of queue */ atomic_set(&q->ci, 0); @@ -839,11 +838,11 @@ static void queue_fini(struct hl_device *hdev, struct hl_hw_queue *q) if (q->queue_type == QUEUE_TYPE_CPU) hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev, HL_QUEUE_SIZE_IN_BYTES, - (void *) (uintptr_t) q->kernel_address); + q->kernel_address); else hdev->asic_funcs->asic_dma_free_coherent(hdev, HL_QUEUE_SIZE_IN_BYTES, - (void *) (uintptr_t) q->kernel_address, + q->kernel_address, q->bus_address); } diff --git a/drivers/misc/habanalabs/common/irq.c b/drivers/misc/habanalabs/common/irq.c index d20e40a53d70..de53fb5f978a 100644 --- a/drivers/misc/habanalabs/common/irq.c +++ b/drivers/misc/habanalabs/common/irq.c @@ -90,7 +90,7 @@ irqreturn_t hl_irq_handler_cq(int irq, void *arg) return IRQ_HANDLED; } - cq_base = (struct hl_cq_entry *) (uintptr_t) cq->kernel_address; + cq_base = cq->kernel_address; while (1) { bool entry_ready = ((le32_to_cpu(cq_base[cq->ci].data) & @@ -152,7 +152,7 @@ irqreturn_t hl_irq_handler_eq(int irq, void *arg) struct hl_eq_entry *eq_base; struct hl_eqe_work *handle_eqe_work; - eq_base = (struct hl_eq_entry *) (uintptr_t) eq->kernel_address; + eq_base = eq->kernel_address; while (1) { bool entry_ready = @@ -221,7 +221,7 @@ int hl_cq_init(struct hl_device *hdev, struct hl_cq *q, u32 hw_queue_id) return -ENOMEM; q->hdev = hdev; - q->kernel_address = (u64) (uintptr_t) p; + q->kernel_address = p; q->hw_queue_id = hw_queue_id; q->ci = 0; q->pi = 0; @@ -242,7 +242,8 @@ int hl_cq_init(struct hl_device *hdev, struct hl_cq *q, u32 hw_queue_id) void hl_cq_fini(struct hl_device *hdev, struct hl_cq *q) { hdev->asic_funcs->asic_dma_free_coherent(hdev, HL_CQ_SIZE_IN_BYTES, - (void *) (uintptr_t) q->kernel_address, q->bus_address); + q->kernel_address, + q->bus_address); } void hl_cq_reset(struct hl_device *hdev, struct hl_cq *q) @@ -259,7 +260,7 @@ void hl_cq_reset(struct hl_device *hdev, struct hl_cq *q) * when the device is operational again */ - memset((void *) (uintptr_t) q->kernel_address, 0, HL_CQ_SIZE_IN_BYTES); + memset(q->kernel_address, 0, HL_CQ_SIZE_IN_BYTES); } /** @@ -282,7 +283,7 @@ int hl_eq_init(struct hl_device *hdev, struct hl_eq *q) return -ENOMEM; q->hdev = hdev; - q->kernel_address = (u64) (uintptr_t) p; + q->kernel_address = p; q->ci = 0; return 0; @@ -302,7 +303,7 @@ void hl_eq_fini(struct hl_device *hdev, struct hl_eq *q) hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev, HL_EQ_SIZE_IN_BYTES, - (void *) (uintptr_t) q->kernel_address); + q->kernel_address); } void hl_eq_reset(struct hl_device *hdev, struct hl_eq *q) @@ -316,5 +317,5 @@ void hl_eq_reset(struct hl_device *hdev, struct hl_eq *q) * when the device is operational again */ - memset((void *) (uintptr_t) q->kernel_address, 0, HL_EQ_SIZE_IN_BYTES); + memset(q->kernel_address, 0, HL_EQ_SIZE_IN_BYTES); } diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c index 5f65a1691551..2519a34e25b7 100644 --- a/drivers/misc/habanalabs/gaudi/gaudi.c +++ b/drivers/misc/habanalabs/gaudi/gaudi.c @@ -680,8 +680,7 @@ static int _gaudi_init_tpc_mem(struct hl_device *hdev, if (!cb) return -EFAULT; - init_tpc_mem_pkt = (struct packet_lin_dma *) (uintptr_t) - cb->kernel_address; + init_tpc_mem_pkt = cb->kernel_address; cb_size = sizeof(*init_tpc_mem_pkt); memset(init_tpc_mem_pkt, 0, cb_size); @@ -3811,8 +3810,7 @@ static int gaudi_validate_cb(struct hl_device *hdev, u16 pkt_size; struct gaudi_packet *user_pkt; - user_pkt = (struct gaudi_packet *) (uintptr_t) - (parser->user_cb->kernel_address + cb_parsed_length); + user_pkt = parser->user_cb->kernel_address + cb_parsed_length; pkt_id = (enum packet_id) ( (le64_to_cpu(user_pkt->header) & @@ -4035,11 +4033,9 @@ static int gaudi_patch_cb(struct hl_device *hdev, u32 new_pkt_size = 0; struct gaudi_packet *user_pkt, *kernel_pkt; - user_pkt = (struct gaudi_packet *) (uintptr_t) - (parser->user_cb->kernel_address + cb_parsed_length); - kernel_pkt = (struct gaudi_packet *) (uintptr_t) - (parser->patched_cb->kernel_address + - cb_patched_cur_length); + user_pkt = parser->user_cb->kernel_address + cb_parsed_length; + kernel_pkt = parser->patched_cb->kernel_address + + cb_patched_cur_length; pkt_id = (enum packet_id) ( (le64_to_cpu(user_pkt->header) & @@ -4155,8 +4151,8 @@ static int gaudi_parse_cb_mmu(struct hl_device *hdev, * The check that parser->user_cb_size <= parser->user_cb->size was done * in validate_queue_index(). */ - memcpy((void *) (uintptr_t) parser->patched_cb->kernel_address, - (void *) (uintptr_t) parser->user_cb->kernel_address, + memcpy(parser->patched_cb->kernel_address, + parser->user_cb->kernel_address, parser->user_cb_size); patched_cb_size = parser->patched_cb_size; @@ -4290,7 +4286,7 @@ static int gaudi_cs_parser(struct hl_device *hdev, struct hl_cs_parser *parser) } static void gaudi_add_end_of_cb_packets(struct hl_device *hdev, - u64 kernel_address, u32 len, + void *kernel_address, u32 len, u64 cq_addr, u32 cq_val, u32 msi_vec, bool eb) { @@ -4298,8 +4294,7 @@ static void gaudi_add_end_of_cb_packets(struct hl_device *hdev, struct packet_msg_prot *cq_pkt; u32 tmp; - cq_pkt = (struct packet_msg_prot *) (uintptr_t) - (kernel_address + len - (sizeof(struct packet_msg_prot) * 2)); + cq_pkt = kernel_address + len - (sizeof(struct packet_msg_prot) * 2); tmp = FIELD_PREP(GAUDI_PKT_CTL_OPCODE_MASK, PACKET_MSG_PROT); tmp |= FIELD_PREP(GAUDI_PKT_CTL_MB_MASK, 1); @@ -4342,7 +4337,7 @@ static int gaudi_memset_device_memory(struct hl_device *hdev, u64 addr, if (!cb) return -EFAULT; - lin_dma_pkt = (struct packet_lin_dma *) (uintptr_t) cb->kernel_address; + lin_dma_pkt = cb->kernel_address; memset(lin_dma_pkt, 0, sizeof(*lin_dma_pkt)); cb_size = sizeof(*lin_dma_pkt); @@ -4747,7 +4742,7 @@ static void gaudi_write_pte(struct hl_device *hdev, u64 addr, u64 val) (addr - gaudi->hbm_bar_cur_addr)); } -static void gaudi_mmu_prepare_reg(struct hl_device *hdev, u64 reg, u32 asid) +void gaudi_mmu_prepare_reg(struct hl_device *hdev, u64 reg, u32 asid) { /* mask to zero the MMBP and ASID bits */ WREG32_AND(reg, ~0x7FF); @@ -4915,9 +4910,6 @@ static void gaudi_mmu_prepare(struct hl_device *hdev, u32 asid) gaudi_mmu_prepare_reg(hdev, mmMME2_ACC_WBC, asid); gaudi_mmu_prepare_reg(hdev, mmMME3_ACC_WBC, asid); - gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_ARUSER, asid); - gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_AWUSER, asid); - hdev->asic_funcs->set_clock_gating(hdev); mutex_unlock(&gaudi->clk_gate_mutex); @@ -4954,8 +4946,8 @@ static int gaudi_send_job_on_qman0(struct hl_device *hdev, cb = job->patched_cb; - fence_pkt = (struct packet_msg_prot *) (uintptr_t) (cb->kernel_address + - job->job_cb_size - sizeof(struct packet_msg_prot)); + fence_pkt = cb->kernel_address + + job->job_cb_size - sizeof(struct packet_msg_prot); tmp = FIELD_PREP(GAUDI_PKT_CTL_OPCODE_MASK, PACKET_MSG_PROT); tmp |= FIELD_PREP(GAUDI_PKT_CTL_EB_MASK, 1); @@ -6386,7 +6378,7 @@ static void gaudi_gen_signal_cb(struct hl_device *hdev, void *data, u16 sob_id) struct packet_msg_short *pkt; u32 value, ctl; - pkt = (struct packet_msg_short *) (uintptr_t) cb->kernel_address; + pkt = cb->kernel_address; memset(pkt, 0, sizeof(*pkt)); /* Inc by 1, Mode ADD */ @@ -6478,7 +6470,7 @@ static void gaudi_gen_wait_cb(struct hl_device *hdev, void *data, u16 sob_id, u16 sob_val, u16 mon_id, u32 q_idx) { struct hl_cb *cb = (struct hl_cb *) data; - void *buf = (void *) (uintptr_t) cb->kernel_address; + void *buf = cb->kernel_address; u64 monitor_base, fence_addr = 0; u32 size = 0; u16 msg_addr_offset; diff --git a/drivers/misc/habanalabs/gaudi/gaudiP.h b/drivers/misc/habanalabs/gaudi/gaudiP.h index 83ad2b0a3a61..8eb598db81b2 100644 --- a/drivers/misc/habanalabs/gaudi/gaudiP.h +++ b/drivers/misc/habanalabs/gaudi/gaudiP.h @@ -271,5 +271,6 @@ void gaudi_set_pll_profile(struct hl_device *hdev, enum hl_pll_frequency freq); int gaudi_debug_coresight(struct hl_device *hdev, void *data); void gaudi_halt_coresight(struct hl_device *hdev); int gaudi_get_clk_rate(struct hl_device *hdev, u32 *cur_clk, u32 *max_clk); +void gaudi_mmu_prepare_reg(struct hl_device *hdev, u64 reg, u32 asid); #endif /* GAUDIP_H_ */ diff --git a/drivers/misc/habanalabs/gaudi/gaudi_coresight.c b/drivers/misc/habanalabs/gaudi/gaudi_coresight.c index 881531d4d9da..3d2b0f0f4650 100644 --- a/drivers/misc/habanalabs/gaudi/gaudi_coresight.c +++ b/drivers/misc/habanalabs/gaudi/gaudi_coresight.c @@ -623,6 +623,11 @@ static int gaudi_config_etr(struct hl_device *hdev, return -EINVAL; } + gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_ARUSER, + hdev->compute_ctx->asid); + gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_AWUSER, + hdev->compute_ctx->asid); + msb = upper_32_bits(input->buffer_address) >> 8; msb &= PSOC_GLOBAL_CONF_TRACE_ADDR_MSB_MASK; WREG32(mmPSOC_GLOBAL_CONF_TRACE_ADDR, msb); diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index 5db52064ed9e..235d47b2420f 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -2882,8 +2882,8 @@ static int goya_send_job_on_qman0(struct hl_device *hdev, struct hl_cs_job *job) cb = job->patched_cb; - fence_pkt = (struct packet_msg_prot *) (uintptr_t) (cb->kernel_address + - job->job_cb_size - sizeof(struct packet_msg_prot)); + fence_pkt = cb->kernel_address + + job->job_cb_size - sizeof(struct packet_msg_prot); tmp = (PACKET_MSG_PROT << GOYA_PKT_CTL_OPCODE_SHIFT) | (1 << GOYA_PKT_CTL_EB_SHIFT) | @@ -3475,8 +3475,7 @@ static int goya_validate_cb(struct hl_device *hdev, u16 pkt_size; struct goya_packet *user_pkt; - user_pkt = (struct goya_packet *) (uintptr_t) - (parser->user_cb->kernel_address + cb_parsed_length); + user_pkt = parser->user_cb->kernel_address + cb_parsed_length; pkt_id = (enum packet_id) ( (le64_to_cpu(user_pkt->header) & @@ -3713,11 +3712,9 @@ static int goya_patch_cb(struct hl_device *hdev, u32 new_pkt_size = 0; struct goya_packet *user_pkt, *kernel_pkt; - user_pkt = (struct goya_packet *) (uintptr_t) - (parser->user_cb->kernel_address + cb_parsed_length); - kernel_pkt = (struct goya_packet *) (uintptr_t) - (parser->patched_cb->kernel_address + - cb_patched_cur_length); + user_pkt = parser->user_cb->kernel_address + cb_parsed_length; + kernel_pkt = parser->patched_cb->kernel_address + + cb_patched_cur_length; pkt_id = (enum packet_id) ( (le64_to_cpu(user_pkt->header) & @@ -3841,8 +3838,8 @@ static int goya_parse_cb_mmu(struct hl_device *hdev, * The check that parser->user_cb_size <= parser->user_cb->size was done * in validate_queue_index(). */ - memcpy((void *) (uintptr_t) parser->patched_cb->kernel_address, - (void *) (uintptr_t) parser->user_cb->kernel_address, + memcpy(parser->patched_cb->kernel_address, + parser->user_cb->kernel_address, parser->user_cb_size); patched_cb_size = parser->patched_cb_size; @@ -3974,15 +3971,14 @@ int goya_cs_parser(struct hl_device *hdev, struct hl_cs_parser *parser) return goya_parse_cb_no_mmu(hdev, parser); } -void goya_add_end_of_cb_packets(struct hl_device *hdev, u64 kernel_address, +void goya_add_end_of_cb_packets(struct hl_device *hdev, void *kernel_address, u32 len, u64 cq_addr, u32 cq_val, u32 msix_vec, bool eb) { struct packet_msg_prot *cq_pkt; u32 tmp; - cq_pkt = (struct packet_msg_prot *) (uintptr_t) - (kernel_address + len - (sizeof(struct packet_msg_prot) * 2)); + cq_pkt = kernel_address + len - (sizeof(struct packet_msg_prot) * 2); tmp = (PACKET_MSG_PROT << GOYA_PKT_CTL_OPCODE_SHIFT) | (1 << GOYA_PKT_CTL_EB_SHIFT) | @@ -4746,7 +4742,7 @@ static int goya_memset_device_memory(struct hl_device *hdev, u64 addr, u64 size, if (!cb) return -ENOMEM; - lin_dma_pkt = (struct packet_lin_dma *) (uintptr_t) cb->kernel_address; + lin_dma_pkt = cb->kernel_address; do { memset(lin_dma_pkt, 0, sizeof(*lin_dma_pkt)); diff --git a/drivers/misc/habanalabs/goya/goyaP.h b/drivers/misc/habanalabs/goya/goyaP.h index 09b4006d4dc3..def86c75e035 100644 --- a/drivers/misc/habanalabs/goya/goyaP.h +++ b/drivers/misc/habanalabs/goya/goyaP.h @@ -217,7 +217,7 @@ int goya_resume(struct hl_device *hdev); void goya_handle_eqe(struct hl_device *hdev, struct hl_eq_entry *eq_entry); void *goya_get_events_stat(struct hl_device *hdev, bool aggregate, u32 *size); -void goya_add_end_of_cb_packets(struct hl_device *hdev, u64 kernel_address, +void goya_add_end_of_cb_packets(struct hl_device *hdev, void *kernel_address, u32 len, u64 cq_addr, u32 cq_val, u32 msix_vec, bool eb); int goya_cs_parser(struct hl_device *hdev, struct hl_cs_parser *parser); diff --git a/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h b/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h index f395721060bd..46aed13f16b1 100644 --- a/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h +++ b/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h @@ -421,7 +421,6 @@ enum axi_id { #define QM_ARB_ERR_MSG_EN_MASK (\ QM_ARB_ERR_MSG_EN_CHOISE_OVF_MASK |\ - QM_ARB_ERR_MSG_EN_CHOISE_WDT_MASK |\ QM_ARB_ERR_MSG_EN_AXI_LBW_ERR_MASK) #define PCIE_AUX_FLR_CTRL_HW_CTRL_MASK 0x1 diff --git a/drivers/misc/mei/client.h b/drivers/misc/mei/client.h index 64143d4ec758..9e08a9843bba 100644 --- a/drivers/misc/mei/client.h +++ b/drivers/misc/mei/client.h @@ -182,11 +182,11 @@ static inline u8 mei_cl_me_id(const struct mei_cl *cl) * * @cl: host client * - * Return: mtu + * Return: mtu or 0 if client is not connected */ static inline size_t mei_cl_mtu(const struct mei_cl *cl) { - return cl->me_cl->props.max_msg_length; + return cl->me_cl ? cl->me_cl->props.max_msg_length : 0; } /** diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c index 414314151d0a..acb9c81a4e45 100644 --- a/drivers/mmc/host/renesas_sdhi_core.c +++ b/drivers/mmc/host/renesas_sdhi_core.c @@ -572,17 +572,6 @@ static void renesas_sdhi_reset(struct tmio_mmc_host *host) TMIO_MASK_INIT_RCAR2); } -/* - * This is a temporary workaround! This driver used 'hw_reset' wrongly and the - * fix for that showed a regression. So, we mimic the old behaviour until the - * proper solution is found. - */ -static void renesas_sdhi_hw_reset(struct mmc_host *mmc) -{ - struct tmio_mmc_host *host = mmc_priv(mmc); - renesas_sdhi_reset(host); -} - #define SH_MOBILE_SDHI_MIN_TAP_ROW 3 static int renesas_sdhi_select_tuning(struct tmio_mmc_host *host) @@ -1020,8 +1009,6 @@ int renesas_sdhi_probe(struct platform_device *pdev, if (of_data && of_data->scc_offset) { priv->scc_ctl = host->ctl + of_data->scc_offset; host->reset = renesas_sdhi_reset; - host->ops.hw_reset = renesas_sdhi_hw_reset; - host->mmc->caps |= MMC_CAP_HW_RESET; } } @@ -1160,6 +1147,7 @@ int renesas_sdhi_remove(struct platform_device *pdev) tmio_mmc_host_remove(host); renesas_sdhi_clk_disable(host); + tmio_mmc_host_free(host); return 0; } diff --git a/drivers/mmc/host/sdhci-of-arasan.c b/drivers/mmc/host/sdhci-of-arasan.c index 829ccef87426..d25a4b50c2f3 100644 --- a/drivers/mmc/host/sdhci-of-arasan.c +++ b/drivers/mmc/host/sdhci-of-arasan.c @@ -30,7 +30,10 @@ #define SDHCI_ARASAN_VENDOR_REGISTER 0x78 #define SDHCI_ARASAN_ITAPDLY_REGISTER 0xF0F8 +#define SDHCI_ARASAN_ITAPDLY_SEL_MASK 0xFF + #define SDHCI_ARASAN_OTAPDLY_REGISTER 0xF0FC +#define SDHCI_ARASAN_OTAPDLY_SEL_MASK 0x3F #define SDHCI_ARASAN_CQE_BASE_ADDR 0x200 #define VENDOR_ENHANCED_STROBE BIT(0) @@ -600,14 +603,8 @@ static int sdhci_zynqmp_sdcardclk_set_phase(struct clk_hw *hw, int degrees) u8 tap_delay, tap_max = 0; int ret; - /* - * This is applicable for SDHCI_SPEC_300 and above - * ZynqMP does not set phase for <=25MHz clock. - * If degrees is zero, no need to do anything. - */ - if (host->version < SDHCI_SPEC_300 || - host->timing == MMC_TIMING_LEGACY || - host->timing == MMC_TIMING_UHS_SDR12 || !degrees) + /* This is applicable for SDHCI_SPEC_300 and above */ + if (host->version < SDHCI_SPEC_300) return 0; switch (host->timing) { @@ -638,6 +635,9 @@ static int sdhci_zynqmp_sdcardclk_set_phase(struct clk_hw *hw, int degrees) if (ret) pr_err("Error setting Output Tap Delay\n"); + /* Release DLL Reset */ + zynqmp_pm_sd_dll_reset(node_id, PM_DLL_RESET_RELEASE); + return ret; } @@ -668,16 +668,13 @@ static int sdhci_zynqmp_sampleclk_set_phase(struct clk_hw *hw, int degrees) u8 tap_delay, tap_max = 0; int ret; - /* - * This is applicable for SDHCI_SPEC_300 and above - * ZynqMP does not set phase for <=25MHz clock. - * If degrees is zero, no need to do anything. - */ - if (host->version < SDHCI_SPEC_300 || - host->timing == MMC_TIMING_LEGACY || - host->timing == MMC_TIMING_UHS_SDR12 || !degrees) + /* This is applicable for SDHCI_SPEC_300 and above */ + if (host->version < SDHCI_SPEC_300) return 0; + /* Assert DLL Reset */ + zynqmp_pm_sd_dll_reset(node_id, PM_DLL_RESET_ASSERT); + switch (host->timing) { case MMC_TIMING_MMC_HS: case MMC_TIMING_SD_HS: @@ -733,14 +730,8 @@ static int sdhci_versal_sdcardclk_set_phase(struct clk_hw *hw, int degrees) struct sdhci_host *host = sdhci_arasan->host; u8 tap_delay, tap_max = 0; - /* - * This is applicable for SDHCI_SPEC_300 and above - * Versal does not set phase for <=25MHz clock. - * If degrees is zero, no need to do anything. - */ - if (host->version < SDHCI_SPEC_300 || - host->timing == MMC_TIMING_LEGACY || - host->timing == MMC_TIMING_UHS_SDR12 || !degrees) + /* This is applicable for SDHCI_SPEC_300 and above */ + if (host->version < SDHCI_SPEC_300) return 0; switch (host->timing) { @@ -773,6 +764,7 @@ static int sdhci_versal_sdcardclk_set_phase(struct clk_hw *hw, int degrees) regval = sdhci_readl(host, SDHCI_ARASAN_OTAPDLY_REGISTER); regval |= SDHCI_OTAPDLY_ENABLE; sdhci_writel(host, regval, SDHCI_ARASAN_OTAPDLY_REGISTER); + regval &= ~SDHCI_ARASAN_OTAPDLY_SEL_MASK; regval |= tap_delay; sdhci_writel(host, regval, SDHCI_ARASAN_OTAPDLY_REGISTER); } @@ -804,14 +796,8 @@ static int sdhci_versal_sampleclk_set_phase(struct clk_hw *hw, int degrees) struct sdhci_host *host = sdhci_arasan->host; u8 tap_delay, tap_max = 0; - /* - * This is applicable for SDHCI_SPEC_300 and above - * Versal does not set phase for <=25MHz clock. - * If degrees is zero, no need to do anything. - */ - if (host->version < SDHCI_SPEC_300 || - host->timing == MMC_TIMING_LEGACY || - host->timing == MMC_TIMING_UHS_SDR12 || !degrees) + /* This is applicable for SDHCI_SPEC_300 and above */ + if (host->version < SDHCI_SPEC_300) return 0; switch (host->timing) { @@ -846,6 +832,7 @@ static int sdhci_versal_sampleclk_set_phase(struct clk_hw *hw, int degrees) sdhci_writel(host, regval, SDHCI_ARASAN_ITAPDLY_REGISTER); regval |= SDHCI_ITAPDLY_ENABLE; sdhci_writel(host, regval, SDHCI_ARASAN_ITAPDLY_REGISTER); + regval &= ~SDHCI_ARASAN_ITAPDLY_SEL_MASK; regval |= tap_delay; sdhci_writel(host, regval, SDHCI_ARASAN_ITAPDLY_REGISTER); regval &= ~SDHCI_ITAPDLY_CHGWIN; diff --git a/drivers/mmc/host/sdhci-of-esdhc.c b/drivers/mmc/host/sdhci-of-esdhc.c index bb094459196a..ab5ab969f711 100644 --- a/drivers/mmc/host/sdhci-of-esdhc.c +++ b/drivers/mmc/host/sdhci-of-esdhc.c @@ -1324,6 +1324,8 @@ static struct soc_device_attribute soc_fixup_sdhc_clkdivs[] = { static struct soc_device_attribute soc_unreliable_pulse_detection[] = { { .family = "QorIQ LX2160A", .revision = "1.0", }, + { .family = "QorIQ LX2160A", .revision = "2.0", }, + { .family = "QorIQ LS1028A", .revision = "1.0", }, { }, }; diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c index 23da7f7fe093..9552708846ca 100644 --- a/drivers/mmc/host/sdhci-pci-core.c +++ b/drivers/mmc/host/sdhci-pci-core.c @@ -665,6 +665,15 @@ static void sdhci_intel_set_power(struct sdhci_host *host, unsigned char mode, } } +static void sdhci_intel_set_uhs_signaling(struct sdhci_host *host, + unsigned int timing) +{ + /* Set UHS timing to SDR25 for High Speed mode */ + if (timing == MMC_TIMING_MMC_HS || timing == MMC_TIMING_SD_HS) + timing = MMC_TIMING_UHS_SDR25; + sdhci_set_uhs_signaling(host, timing); +} + #define INTEL_HS400_ES_REG 0x78 #define INTEL_HS400_ES_BIT BIT(0) @@ -721,7 +730,7 @@ static const struct sdhci_ops sdhci_intel_byt_ops = { .enable_dma = sdhci_pci_enable_dma, .set_bus_width = sdhci_set_bus_width, .reset = sdhci_reset, - .set_uhs_signaling = sdhci_set_uhs_signaling, + .set_uhs_signaling = sdhci_intel_set_uhs_signaling, .hw_reset = sdhci_pci_hw_reset, }; @@ -731,7 +740,7 @@ static const struct sdhci_ops sdhci_intel_glk_ops = { .enable_dma = sdhci_pci_enable_dma, .set_bus_width = sdhci_set_bus_width, .reset = sdhci_cqhci_reset, - .set_uhs_signaling = sdhci_set_uhs_signaling, + .set_uhs_signaling = sdhci_intel_set_uhs_signaling, .hw_reset = sdhci_pci_hw_reset, .irq = sdhci_cqhci_irq, }; diff --git a/drivers/mmc/host/tmio_mmc_core.c b/drivers/mmc/host/tmio_mmc_core.c index 2fce0518632d..cb4149fd12e0 100644 --- a/drivers/mmc/host/tmio_mmc_core.c +++ b/drivers/mmc/host/tmio_mmc_core.c @@ -175,6 +175,8 @@ static void tmio_mmc_reset(struct tmio_mmc_host *host) if (host->reset) host->reset(host); + tmio_mmc_abort_dma(host); + if (host->pdata->flags & TMIO_MMC_SDIO_IRQ) { sd_ctrl_write16(host, CTL_SDIO_IRQ_MASK, host->sdio_irq_mask); sd_ctrl_write16(host, CTL_TRANSACTION_CTL, 0x0001); @@ -223,8 +225,6 @@ static void tmio_mmc_reset_work(struct work_struct *work) /* Ready for new calls */ host->mrq = NULL; - - tmio_mmc_abort_dma(host); mmc_request_done(host->mmc, mrq); } @@ -927,6 +927,9 @@ static void tmio_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) switch (ios->power_mode) { case MMC_POWER_OFF: tmio_mmc_power_off(host); + /* Downgrade ensures a sane state for tuning HW (e.g. SCC) */ + if (host->mmc->ops->hs400_downgrade) + host->mmc->ops->hs400_downgrade(host->mmc); host->set_clock(host, 0); break; case MMC_POWER_UP: diff --git a/drivers/mtd/nand/raw/fsl_ifc_nand.c b/drivers/mtd/nand/raw/fsl_ifc_nand.c index 0e7a9b64301e..e345f9d9f8e8 100644 --- a/drivers/mtd/nand/raw/fsl_ifc_nand.c +++ b/drivers/mtd/nand/raw/fsl_ifc_nand.c @@ -707,6 +707,30 @@ static int fsl_ifc_attach_chip(struct nand_chip *chip) { struct mtd_info *mtd = nand_to_mtd(chip); struct fsl_ifc_mtd *priv = nand_get_controller_data(chip); + struct fsl_ifc_ctrl *ctrl = priv->ctrl; + struct fsl_ifc_global __iomem *ifc_global = ctrl->gregs; + u32 csor; + + csor = ifc_in32(&ifc_global->csor_cs[priv->bank].csor); + + /* Must also set CSOR_NAND_ECC_ENC_EN if DEC_EN set */ + if (csor & CSOR_NAND_ECC_DEC_EN) { + chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST; + mtd_set_ooblayout(mtd, &fsl_ifc_ooblayout_ops); + + /* Hardware generates ECC per 512 Bytes */ + chip->ecc.size = 512; + if ((csor & CSOR_NAND_ECC_MODE_MASK) == CSOR_NAND_ECC_MODE_4) { + chip->ecc.bytes = 8; + chip->ecc.strength = 4; + } else { + chip->ecc.bytes = 16; + chip->ecc.strength = 8; + } + } else { + chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; + chip->ecc.algo = NAND_ECC_ALGO_HAMMING; + } dev_dbg(priv->dev, "%s: nand->numchips = %d\n", __func__, nanddev_ntargets(&chip->base)); @@ -910,25 +934,6 @@ static int fsl_ifc_chip_init(struct fsl_ifc_mtd *priv) return -ENODEV; } - /* Must also set CSOR_NAND_ECC_ENC_EN if DEC_EN set */ - if (csor & CSOR_NAND_ECC_DEC_EN) { - chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST; - mtd_set_ooblayout(mtd, &fsl_ifc_ooblayout_ops); - - /* Hardware generates ECC per 512 Bytes */ - chip->ecc.size = 512; - if ((csor & CSOR_NAND_ECC_MODE_MASK) == CSOR_NAND_ECC_MODE_4) { - chip->ecc.bytes = 8; - chip->ecc.strength = 4; - } else { - chip->ecc.bytes = 16; - chip->ecc.strength = 8; - } - } else { - chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - chip->ecc.algo = NAND_ECC_ALGO_HAMMING; - } - ret = fsl_ifc_sram_init(priv); if (ret) return ret; diff --git a/drivers/mtd/nand/raw/mxc_nand.c b/drivers/mtd/nand/raw/mxc_nand.c index d4200eb2ad32..684c51e5e60d 100644 --- a/drivers/mtd/nand/raw/mxc_nand.c +++ b/drivers/mtd/nand/raw/mxc_nand.c @@ -1681,6 +1681,11 @@ static int mxcnd_attach_chip(struct nand_chip *chip) struct mxc_nand_host *host = nand_get_controller_data(chip); struct device *dev = mtd->dev.parent; + chip->ecc.bytes = host->devtype_data->eccbytes; + host->eccsize = host->devtype_data->eccsize; + chip->ecc.size = 512; + mtd_set_ooblayout(mtd, host->devtype_data->ooblayout); + switch (chip->ecc.engine_type) { case NAND_ECC_ENGINE_TYPE_ON_HOST: chip->ecc.read_page = mxc_nand_read_page; @@ -1836,19 +1841,7 @@ static int mxcnd_probe(struct platform_device *pdev) if (host->devtype_data->axi_offset) host->regs_axi = host->base + host->devtype_data->axi_offset; - this->ecc.bytes = host->devtype_data->eccbytes; - host->eccsize = host->devtype_data->eccsize; - this->legacy.select_chip = host->devtype_data->select_chip; - this->ecc.size = 512; - mtd_set_ooblayout(mtd, host->devtype_data->ooblayout); - - if (host->pdata.hw_ecc) { - this->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST; - } else { - this->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - this->ecc.algo = NAND_ECC_ALGO_HAMMING; - } /* NAND bus width determines access functions used by upper layer */ if (host->pdata.width == 2) diff --git a/drivers/mtd/nand/raw/stm32_fmc2_nand.c b/drivers/mtd/nand/raw/stm32_fmc2_nand.c index b31a5818234d..550bda4d1415 100644 --- a/drivers/mtd/nand/raw/stm32_fmc2_nand.c +++ b/drivers/mtd/nand/raw/stm32_fmc2_nand.c @@ -1708,6 +1708,13 @@ static int stm32_fmc2_nfc_attach_chip(struct nand_chip *chip) return -EINVAL; } + /* Default ECC settings in case they are not set in the device tree */ + if (!chip->ecc.size) + chip->ecc.size = FMC2_ECC_STEP_SIZE; + + if (!chip->ecc.strength) + chip->ecc.strength = FMC2_ECC_BCH8; + ret = nand_ecc_choose_conf(chip, &stm32_fmc2_nfc_ecc_caps, mtd->oobsize - FMC2_BBM_LEN); if (ret) { @@ -1727,8 +1734,7 @@ static int stm32_fmc2_nfc_attach_chip(struct nand_chip *chip) mtd_set_ooblayout(mtd, &stm32_fmc2_nfc_ooblayout_ops); - if (chip->options & NAND_BUSWIDTH_16) - stm32_fmc2_nfc_set_buswidth_16(nfc, true); + stm32_fmc2_nfc_setup(chip); return 0; } @@ -1952,11 +1958,6 @@ static int stm32_fmc2_nfc_probe(struct platform_device *pdev) chip->options |= NAND_BUSWIDTH_AUTO | NAND_NO_SUBPAGE_WRITE | NAND_USES_DMA; - /* Default ECC settings */ - chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST; - chip->ecc.size = FMC2_ECC_STEP_SIZE; - chip->ecc.strength = FMC2_ECC_BCH8; - /* Scan to find existence of the device */ ret = nand_scan(chip, nand->ncs); if (ret) diff --git a/drivers/mtd/spi-nor/core.c b/drivers/mtd/spi-nor/core.c index 0369d98b2d12..f0ae7a01703a 100644 --- a/drivers/mtd/spi-nor/core.c +++ b/drivers/mtd/spi-nor/core.c @@ -2701,11 +2701,10 @@ static void spi_nor_sfdp_init_params(struct spi_nor *nor) memcpy(&sfdp_params, nor->params, sizeof(sfdp_params)); - if (spi_nor_parse_sfdp(nor, &sfdp_params)) { + if (spi_nor_parse_sfdp(nor, nor->params)) { + memcpy(nor->params, &sfdp_params, sizeof(*nor->params)); nor->addr_width = 0; nor->flags &= ~SNOR_F_4B_OPCODES; - } else { - memcpy(nor->params, &sfdp_params, sizeof(*nor->params)); } } @@ -3009,13 +3008,15 @@ static int spi_nor_set_addr_width(struct spi_nor *nor) /* already configured from SFDP */ } else if (nor->info->addr_width) { nor->addr_width = nor->info->addr_width; - } else if (nor->mtd.size > 0x1000000) { - /* enable 4-byte addressing if the device exceeds 16MiB */ - nor->addr_width = 4; } else { nor->addr_width = 3; } + if (nor->addr_width == 3 && nor->mtd.size > 0x1000000) { + /* enable 4-byte addressing if the device exceeds 16MiB */ + nor->addr_width = 4; + } + if (nor->addr_width > SPI_NOR_MAX_ADDR_WIDTH) { dev_dbg(nor->dev, "address width is too large: %u\n", nor->addr_width); diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c index b70ded3760f2..81e39d7507d8 100644 --- a/drivers/net/can/dev.c +++ b/drivers/net/can/dev.c @@ -512,9 +512,13 @@ __can_get_echo_skb(struct net_device *dev, unsigned int idx, u8 *len_ptr) */ struct sk_buff *skb = priv->echo_skb[idx]; struct canfd_frame *cf = (struct canfd_frame *)skb->data; - u8 len = cf->len; - *len_ptr = len; + /* get the real payload length for netdev statistics */ + if (cf->can_id & CAN_RTR_FLAG) + *len_ptr = 0; + else + *len_ptr = cf->len; + priv->echo_skb[idx] = NULL; return skb; @@ -538,7 +542,11 @@ unsigned int can_get_echo_skb(struct net_device *dev, unsigned int idx) if (!skb) return 0; - netif_rx(skb); + skb_get(skb); + if (netif_rx(skb) == NET_RX_SUCCESS) + dev_consume_skb_any(skb); + else + dev_kfree_skb_any(skb); return len; } @@ -584,7 +592,7 @@ static void can_restart(struct net_device *dev) cf->can_id |= CAN_ERR_RESTARTED; - netif_rx(skb); + netif_rx_ni(skb); stats->rx_packets++; stats->rx_bytes += cf->can_dlc; diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c index 4d594e977497..99e5f272205d 100644 --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -217,7 +217,7 @@ * MX8MP FlexCAN3 03.00.17.01 yes yes no yes yes yes * VF610 FlexCAN3 ? no yes no yes yes? no * LS1021A FlexCAN2 03.00.04.00 no yes no no yes no - * LX2160A FlexCAN3 03.00.23.00 no yes no no yes yes + * LX2160A FlexCAN3 03.00.23.00 no yes no yes yes yes * * Some SOCs do not have the RX_WARN & TX_WARN interrupt line connected. */ @@ -400,19 +400,19 @@ static struct flexcan_devtype_data fsl_imx8mp_devtype_data = { static const struct flexcan_devtype_data fsl_vf610_devtype_data = { .quirks = FLEXCAN_QUIRK_DISABLE_RXFG | FLEXCAN_QUIRK_ENABLE_EACEN_RRS | FLEXCAN_QUIRK_DISABLE_MECR | FLEXCAN_QUIRK_USE_OFF_TIMESTAMP | - FLEXCAN_QUIRK_BROKEN_PERR_STATE, + FLEXCAN_QUIRK_BROKEN_PERR_STATE | FLEXCAN_QUIRK_SUPPORT_ECC, }; static const struct flexcan_devtype_data fsl_ls1021a_r2_devtype_data = { .quirks = FLEXCAN_QUIRK_DISABLE_RXFG | FLEXCAN_QUIRK_ENABLE_EACEN_RRS | - FLEXCAN_QUIRK_DISABLE_MECR | FLEXCAN_QUIRK_BROKEN_PERR_STATE | - FLEXCAN_QUIRK_USE_OFF_TIMESTAMP, + FLEXCAN_QUIRK_BROKEN_PERR_STATE | FLEXCAN_QUIRK_USE_OFF_TIMESTAMP, }; static const struct flexcan_devtype_data fsl_lx2160a_r1_devtype_data = { .quirks = FLEXCAN_QUIRK_DISABLE_RXFG | FLEXCAN_QUIRK_ENABLE_EACEN_RRS | FLEXCAN_QUIRK_DISABLE_MECR | FLEXCAN_QUIRK_BROKEN_PERR_STATE | - FLEXCAN_QUIRK_USE_OFF_TIMESTAMP | FLEXCAN_QUIRK_SUPPORT_FD, + FLEXCAN_QUIRK_USE_OFF_TIMESTAMP | FLEXCAN_QUIRK_SUPPORT_FD | + FLEXCAN_QUIRK_SUPPORT_ECC, }; static const struct can_bittiming_const flexcan_bittiming_const = { @@ -728,8 +728,10 @@ static int flexcan_get_berr_counter(const struct net_device *dev, int err; err = pm_runtime_get_sync(priv->dev); - if (err < 0) + if (err < 0) { + pm_runtime_put_noidle(priv->dev); return err; + } err = __flexcan_get_berr_counter(dev, bec); @@ -1565,14 +1567,10 @@ static int flexcan_chip_start(struct net_device *dev) priv->write(reg_ctrl2, ®s->ctrl2); } - err = flexcan_transceiver_enable(priv); - if (err) - goto out_chip_disable; - /* synchronize with the can bus */ err = flexcan_chip_unfreeze(priv); if (err) - goto out_transceiver_disable; + goto out_chip_disable; priv->can.state = CAN_STATE_ERROR_ACTIVE; @@ -1590,8 +1588,6 @@ static int flexcan_chip_start(struct net_device *dev) return 0; - out_transceiver_disable: - flexcan_transceiver_disable(priv); out_chip_disable: flexcan_chip_disable(priv); return err; @@ -1621,7 +1617,6 @@ static int __flexcan_chip_stop(struct net_device *dev, bool disable_on_error) priv->write(priv->reg_ctrl_default & ~FLEXCAN_CTRL_ERR_ALL, ®s->ctrl); - flexcan_transceiver_disable(priv); priv->can.state = CAN_STATE_STOPPED; return 0; @@ -1654,17 +1649,23 @@ static int flexcan_open(struct net_device *dev) } err = pm_runtime_get_sync(priv->dev); - if (err < 0) + if (err < 0) { + pm_runtime_put_noidle(priv->dev); return err; + } err = open_candev(dev); if (err) goto out_runtime_put; - err = request_irq(dev->irq, flexcan_irq, IRQF_SHARED, dev->name, dev); + err = flexcan_transceiver_enable(priv); if (err) goto out_close; + err = request_irq(dev->irq, flexcan_irq, IRQF_SHARED, dev->name, dev); + if (err) + goto out_transceiver_disable; + if (priv->can.ctrlmode & CAN_CTRLMODE_FD) priv->mb_size = sizeof(struct flexcan_mb) + CANFD_MAX_DLEN; else @@ -1716,6 +1717,8 @@ static int flexcan_open(struct net_device *dev) can_rx_offload_del(&priv->offload); out_free_irq: free_irq(dev->irq, dev); + out_transceiver_disable: + flexcan_transceiver_disable(priv); out_close: close_candev(dev); out_runtime_put: @@ -1734,6 +1737,7 @@ static int flexcan_close(struct net_device *dev) can_rx_offload_del(&priv->offload); free_irq(dev->irq, dev); + flexcan_transceiver_disable(priv); close_candev(dev); pm_runtime_put(priv->dev); @@ -1852,7 +1856,7 @@ static int flexcan_setup_stop_mode(struct platform_device *pdev) return -EINVAL; /* stop mode property format is: - * <&gpr req_gpr>. + * <&gpr req_gpr req_bit>. */ ret = of_property_read_u32_array(np, "fsl,stop-mode", out_val, ARRAY_SIZE(out_val)); @@ -2062,6 +2066,8 @@ static int flexcan_remove(struct platform_device *pdev) { struct net_device *dev = platform_get_drvdata(pdev); + device_set_wakeup_enable(&pdev->dev, false); + device_set_wakeup_capable(&pdev->dev, false); unregister_flexcandev(dev); pm_runtime_disable(&pdev->dev); free_candev(dev); diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c index 6f766918211a..72acd1ba162d 100644 --- a/drivers/net/can/kvaser_pciefd.c +++ b/drivers/net/can/kvaser_pciefd.c @@ -287,12 +287,12 @@ struct kvaser_pciefd_tx_packet { static const struct can_bittiming_const kvaser_pciefd_bittiming_const = { .name = KVASER_PCIEFD_DRV_NAME, .tseg1_min = 1, - .tseg1_max = 255, + .tseg1_max = 512, .tseg2_min = 1, .tseg2_max = 32, .sjw_max = 16, .brp_min = 1, - .brp_max = 4096, + .brp_max = 8192, .brp_inc = 1, }; diff --git a/drivers/net/can/m_can/Kconfig b/drivers/net/can/m_can/Kconfig index 48be627c85c2..5f9f8192dd0b 100644 --- a/drivers/net/can/m_can/Kconfig +++ b/drivers/net/can/m_can/Kconfig @@ -16,7 +16,8 @@ config CAN_M_CAN_PLATFORM config CAN_M_CAN_TCAN4X5X depends on CAN_M_CAN - depends on REGMAP_SPI + depends on SPI + select REGMAP_SPI tristate "TCAN4X5X M_CAN device" help Say Y here if you want support for Texas Instruments TCAN4x5x diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index 02c5795b7393..f3fc37e96b08 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -665,7 +665,7 @@ static int m_can_handle_state_change(struct net_device *dev, unsigned int ecr; switch (new_state) { - case CAN_STATE_ERROR_ACTIVE: + case CAN_STATE_ERROR_WARNING: /* error warning state */ cdev->can.can_stats.error_warning++; cdev->can.state = CAN_STATE_ERROR_WARNING; @@ -694,7 +694,7 @@ static int m_can_handle_state_change(struct net_device *dev, __m_can_get_berr_counter(dev, &bec); switch (new_state) { - case CAN_STATE_ERROR_ACTIVE: + case CAN_STATE_ERROR_WARNING: /* error warning state */ cf->can_id |= CAN_ERR_CRTL; cf->data[1] = (bec.txerr > bec.rxerr) ? @@ -956,6 +956,8 @@ static irqreturn_t m_can_isr(int irq, void *dev_id) struct net_device_stats *stats = &dev->stats; u32 ir; + if (pm_runtime_suspended(cdev->dev)) + return IRQ_NONE; ir = m_can_read(cdev, M_CAN_IR); if (!ir) return IRQ_NONE; @@ -1414,6 +1416,9 @@ static void m_can_stop(struct net_device *dev) /* disable all interrupts */ m_can_disable_all_interrupts(cdev); + /* Set init mode to disengage from the network */ + m_can_config_endisable(cdev, true); + /* set the state as STOPPED */ cdev->can.state = CAN_STATE_STOPPED; } @@ -1812,6 +1817,12 @@ out: } EXPORT_SYMBOL_GPL(m_can_class_allocate_dev); +void m_can_class_free_dev(struct net_device *net) +{ + free_candev(net); +} +EXPORT_SYMBOL_GPL(m_can_class_free_dev); + int m_can_class_register(struct m_can_classdev *m_can_dev) { int ret; @@ -1850,7 +1861,6 @@ pm_runtime_fail: if (ret) { if (m_can_dev->pm_clock_support) pm_runtime_disable(m_can_dev->dev); - free_candev(m_can_dev->net); } return ret; @@ -1908,8 +1918,6 @@ void m_can_class_unregister(struct m_can_classdev *m_can_dev) unregister_candev(m_can_dev->net); m_can_clk_stop(m_can_dev); - - free_candev(m_can_dev->net); } EXPORT_SYMBOL_GPL(m_can_class_unregister); diff --git a/drivers/net/can/m_can/m_can.h b/drivers/net/can/m_can/m_can.h index 49f42b50627a..b2699a7c9997 100644 --- a/drivers/net/can/m_can/m_can.h +++ b/drivers/net/can/m_can/m_can.h @@ -99,6 +99,7 @@ struct m_can_classdev { }; struct m_can_classdev *m_can_class_allocate_dev(struct device *dev); +void m_can_class_free_dev(struct net_device *net); int m_can_class_register(struct m_can_classdev *cdev); void m_can_class_unregister(struct m_can_classdev *cdev); int m_can_class_get_clocks(struct m_can_classdev *cdev); diff --git a/drivers/net/can/m_can/m_can_platform.c b/drivers/net/can/m_can/m_can_platform.c index e6d0cb9ee02f..161cb9be018c 100644 --- a/drivers/net/can/m_can/m_can_platform.c +++ b/drivers/net/can/m_can/m_can_platform.c @@ -67,32 +67,36 @@ static int m_can_plat_probe(struct platform_device *pdev) return -ENOMEM; priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL); - if (!priv) - return -ENOMEM; + if (!priv) { + ret = -ENOMEM; + goto probe_fail; + } mcan_class->device_data = priv; - m_can_class_get_clocks(mcan_class); + ret = m_can_class_get_clocks(mcan_class); + if (ret) + goto probe_fail; res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "m_can"); addr = devm_ioremap_resource(&pdev->dev, res); irq = platform_get_irq_byname(pdev, "int0"); if (IS_ERR(addr) || irq < 0) { ret = -EINVAL; - goto failed_ret; + goto probe_fail; } /* message ram could be shared */ res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "message_ram"); if (!res) { ret = -ENODEV; - goto failed_ret; + goto probe_fail; } mram_addr = devm_ioremap(&pdev->dev, res->start, resource_size(res)); if (!mram_addr) { ret = -ENOMEM; - goto failed_ret; + goto probe_fail; } priv->base = addr; @@ -111,9 +115,10 @@ static int m_can_plat_probe(struct platform_device *pdev) m_can_init_ram(mcan_class); - ret = m_can_class_register(mcan_class); + return m_can_class_register(mcan_class); -failed_ret: +probe_fail: + m_can_class_free_dev(mcan_class->net); return ret; } @@ -134,6 +139,8 @@ static int m_can_plat_remove(struct platform_device *pdev) m_can_class_unregister(mcan_class); + m_can_class_free_dev(mcan_class->net); + platform_set_drvdata(pdev, NULL); return 0; diff --git a/drivers/net/can/m_can/tcan4x5x.c b/drivers/net/can/m_can/tcan4x5x.c index eacd428e07e9..e5d7d85e0b6d 100644 --- a/drivers/net/can/m_can/tcan4x5x.c +++ b/drivers/net/can/m_can/tcan4x5x.c @@ -440,14 +440,18 @@ static int tcan4x5x_can_probe(struct spi_device *spi) return -ENOMEM; priv = devm_kzalloc(&spi->dev, sizeof(*priv), GFP_KERNEL); - if (!priv) - return -ENOMEM; + if (!priv) { + ret = -ENOMEM; + goto out_m_can_class_free_dev; + } priv->power = devm_regulator_get_optional(&spi->dev, "vsup"); - if (PTR_ERR(priv->power) == -EPROBE_DEFER) - return -EPROBE_DEFER; - else + if (PTR_ERR(priv->power) == -EPROBE_DEFER) { + ret = -EPROBE_DEFER; + goto out_m_can_class_free_dev; + } else { priv->power = NULL; + } mcan_class->device_data = priv; @@ -460,8 +464,10 @@ static int tcan4x5x_can_probe(struct spi_device *spi) } /* Sanity check */ - if (freq < 20000000 || freq > TCAN4X5X_EXT_CLK_DEF) - return -ERANGE; + if (freq < 20000000 || freq > TCAN4X5X_EXT_CLK_DEF) { + ret = -ERANGE; + goto out_m_can_class_free_dev; + } priv->reg_offset = TCAN4X5X_MCAN_OFFSET; priv->mram_start = TCAN4X5X_MRAM_START; @@ -487,6 +493,10 @@ static int tcan4x5x_can_probe(struct spi_device *spi) priv->regmap = devm_regmap_init(&spi->dev, &tcan4x5x_bus, &spi->dev, &tcan4x5x_regmap); + if (IS_ERR(priv->regmap)) { + ret = PTR_ERR(priv->regmap); + goto out_clk; + } ret = tcan4x5x_power_enable(priv->power, 1); if (ret) @@ -514,8 +524,10 @@ out_clk: clk_disable_unprepare(mcan_class->cclk); clk_disable_unprepare(mcan_class->hclk); } - + out_m_can_class_free_dev: + m_can_class_free_dev(mcan_class->net); dev_err(&spi->dev, "Probe failed, err=%d\n", ret); + return ret; } @@ -523,9 +535,11 @@ static int tcan4x5x_can_remove(struct spi_device *spi) { struct tcan4x5x_priv *priv = spi_get_drvdata(spi); + m_can_class_unregister(priv->mcan_dev); + tcan4x5x_power_enable(priv->power, 0); - m_can_class_unregister(priv->mcan_dev); + m_can_class_free_dev(priv->mcan_dev->net); return 0; } diff --git a/drivers/net/can/peak_canfd/peak_canfd.c b/drivers/net/can/peak_canfd/peak_canfd.c index 10aa3e457c33..40c33b8a5fda 100644 --- a/drivers/net/can/peak_canfd/peak_canfd.c +++ b/drivers/net/can/peak_canfd/peak_canfd.c @@ -262,8 +262,7 @@ static int pucan_handle_can_rx(struct peak_canfd_priv *priv, cf_len = get_can_dlc(pucan_msg_get_dlc(msg)); /* if this frame is an echo, */ - if ((rx_msg_flags & PUCAN_MSG_LOOPED_BACK) && - !(rx_msg_flags & PUCAN_MSG_SELF_RECEIVE)) { + if (rx_msg_flags & PUCAN_MSG_LOOPED_BACK) { unsigned long flags; spin_lock_irqsave(&priv->echo_lock, flags); @@ -277,7 +276,13 @@ static int pucan_handle_can_rx(struct peak_canfd_priv *priv, netif_wake_queue(priv->ndev); spin_unlock_irqrestore(&priv->echo_lock, flags); - return 0; + + /* if this frame is only an echo, stop here. Otherwise, + * continue to push this application self-received frame into + * its own rx queue. + */ + if (!(rx_msg_flags & PUCAN_MSG_SELF_RECEIVE)) + return 0; } /* otherwise, it should be pushed into rx fifo */ diff --git a/drivers/net/can/rx-offload.c b/drivers/net/can/rx-offload.c index 3b180269a92d..6e95193b215b 100644 --- a/drivers/net/can/rx-offload.c +++ b/drivers/net/can/rx-offload.c @@ -245,7 +245,7 @@ int can_rx_offload_queue_sorted(struct can_rx_offload *offload, if (skb_queue_len(&offload->skb_queue) > offload->skb_queue_len_max) { - kfree_skb(skb); + dev_kfree_skb_any(skb); return -ENOBUFS; } @@ -290,7 +290,7 @@ int can_rx_offload_queue_tail(struct can_rx_offload *offload, { if (skb_queue_len(&offload->skb_queue) > offload->skb_queue_len_max) { - kfree_skb(skb); + dev_kfree_skb_any(skb); return -ENOBUFS; } diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c index c3f49543ff26..9c215f7c5f81 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c @@ -75,11 +75,11 @@ static const char *__mcp251xfd_get_model_str(enum mcp251xfd_model model) { switch (model) { case MCP251XFD_MODEL_MCP2517FD: - return "MCP2517FD"; break; + return "MCP2517FD"; case MCP251XFD_MODEL_MCP2518FD: - return "MCP2518FD"; break; + return "MCP2518FD"; case MCP251XFD_MODEL_MCP251XFD: - return "MCP251xFD"; break; + return "MCP251xFD"; } return "<unknown>"; @@ -95,21 +95,21 @@ static const char *mcp251xfd_get_mode_str(const u8 mode) { switch (mode) { case MCP251XFD_REG_CON_MODE_MIXED: - return "Mixed (CAN FD/CAN 2.0)"; break; + return "Mixed (CAN FD/CAN 2.0)"; case MCP251XFD_REG_CON_MODE_SLEEP: - return "Sleep"; break; + return "Sleep"; case MCP251XFD_REG_CON_MODE_INT_LOOPBACK: - return "Internal Loopback"; break; + return "Internal Loopback"; case MCP251XFD_REG_CON_MODE_LISTENONLY: - return "Listen Only"; break; + return "Listen Only"; case MCP251XFD_REG_CON_MODE_CONFIG: - return "Configuration"; break; + return "Configuration"; case MCP251XFD_REG_CON_MODE_EXT_LOOPBACK: - return "External Loopback"; break; + return "External Loopback"; case MCP251XFD_REG_CON_MODE_CAN2_0: - return "CAN 2.0"; break; + return "CAN 2.0"; case MCP251XFD_REG_CON_MODE_RESTRICTED: - return "Restricted Operation"; break; + return "Restricted Operation"; } return "<unknown>"; diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-regmap.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-regmap.c index ba25902dd78c..314f868b3465 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-regmap.c +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-regmap.c @@ -173,7 +173,7 @@ mcp251xfd_regmap_nocrc_read(void *context, memcpy(&buf_tx->cmd, reg, sizeof(buf_tx->cmd)); if (MCP251XFD_SANITIZE_SPI) memset(buf_tx->data, 0x0, val_len); - }; + } err = spi_sync(spi, &msg); if (err) @@ -330,17 +330,17 @@ mcp251xfd_regmap_crc_read(void *context, goto out; } - netdev_dbg(priv->ndev, - "CRC read error at address 0x%04x (length=%zd, data=%*ph, CRC=0x%04x) retrying.\n", - reg, val_len, (int)val_len, buf_rx->data, - get_unaligned_be16(buf_rx->data + val_len)); - } - - if (err) { netdev_info(priv->ndev, - "CRC read error at address 0x%04x (length=%zd, data=%*ph, CRC=0x%04x).\n", + "CRC read error at address 0x%04x (length=%zd, data=%*ph, CRC=0x%04x) retrying.\n", reg, val_len, (int)val_len, buf_rx->data, get_unaligned_be16(buf_rx->data + val_len)); + } + + if (err) { + netdev_err(priv->ndev, + "CRC read error at address 0x%04x (length=%zd, data=%*ph, CRC=0x%04x).\n", + reg, val_len, (int)val_len, buf_rx->data, + get_unaligned_be16(buf_rx->data + val_len)); return err; } diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c index 1d63006c97bc..2c22f40e12bd 100644 --- a/drivers/net/can/ti_hecc.c +++ b/drivers/net/can/ti_hecc.c @@ -881,7 +881,8 @@ static int ti_hecc_probe(struct platform_device *pdev) priv->base = devm_platform_ioremap_resource_byname(pdev, "hecc"); if (IS_ERR(priv->base)) { dev_err(&pdev->dev, "hecc ioremap failed\n"); - return PTR_ERR(priv->base); + err = PTR_ERR(priv->base); + goto probe_exit_candev; } /* handle hecc-ram memory */ @@ -889,20 +890,22 @@ static int ti_hecc_probe(struct platform_device *pdev) "hecc-ram"); if (IS_ERR(priv->hecc_ram)) { dev_err(&pdev->dev, "hecc-ram ioremap failed\n"); - return PTR_ERR(priv->hecc_ram); + err = PTR_ERR(priv->hecc_ram); + goto probe_exit_candev; } /* handle mbx memory */ priv->mbx = devm_platform_ioremap_resource_byname(pdev, "mbx"); if (IS_ERR(priv->mbx)) { dev_err(&pdev->dev, "mbx ioremap failed\n"); - return PTR_ERR(priv->mbx); + err = PTR_ERR(priv->mbx); + goto probe_exit_candev; } irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0); if (!irq) { dev_err(&pdev->dev, "No irq resource\n"); - goto probe_exit; + goto probe_exit_candev; } priv->ndev = ndev; @@ -933,7 +936,7 @@ static int ti_hecc_probe(struct platform_device *pdev) err = clk_prepare_enable(priv->clk); if (err) { dev_err(&pdev->dev, "clk_prepare_enable() failed\n"); - goto probe_exit_clk; + goto probe_exit_release_clk; } priv->offload.mailbox_read = ti_hecc_mailbox_read; @@ -942,7 +945,7 @@ static int ti_hecc_probe(struct platform_device *pdev) err = can_rx_offload_add_timestamp(ndev, &priv->offload); if (err) { dev_err(&pdev->dev, "can_rx_offload_add_timestamp() failed\n"); - goto probe_exit_clk; + goto probe_exit_disable_clk; } err = register_candev(ndev); @@ -960,11 +963,13 @@ static int ti_hecc_probe(struct platform_device *pdev) probe_exit_offload: can_rx_offload_del(&priv->offload); -probe_exit_clk: +probe_exit_disable_clk: + clk_disable_unprepare(priv->clk); +probe_exit_release_clk: clk_put(priv->clk); probe_exit_candev: free_candev(ndev); -probe_exit: + return err; } diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c index 7ab87a758754..218fadc91155 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c @@ -367,7 +367,7 @@ static const struct can_bittiming_const kvaser_usb_hydra_kcan_bittiming_c = { .tseg2_max = 32, .sjw_max = 16, .brp_min = 1, - .brp_max = 4096, + .brp_max = 8192, .brp_inc = 1, }; diff --git a/drivers/net/can/usb/mcba_usb.c b/drivers/net/can/usb/mcba_usb.c index 5857b37dcd96..e97f2e0da6b0 100644 --- a/drivers/net/can/usb/mcba_usb.c +++ b/drivers/net/can/usb/mcba_usb.c @@ -326,8 +326,6 @@ static netdev_tx_t mcba_usb_start_xmit(struct sk_buff *skb, if (!ctx) return NETDEV_TX_BUSY; - can_put_echo_skb(skb, priv->netdev, ctx->ndx); - if (cf->can_id & CAN_EFF_FLAG) { /* SIDH | SIDL | EIDH | EIDL * 28 - 21 | 20 19 18 x x x 17 16 | 15 - 8 | 7 - 0 @@ -357,6 +355,8 @@ static netdev_tx_t mcba_usb_start_xmit(struct sk_buff *skb, if (cf->can_id & CAN_RTR_FLAG) usb_msg.dlc |= MCBA_DLC_RTR_MASK; + can_put_echo_skb(skb, priv->netdev, ctx->ndx); + err = mcba_usb_xmit(priv, (struct mcba_usb_msg *)&usb_msg, ctx); if (err) goto xmit_failed; diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c index d91df34e7fa8..204ccb27d6d9 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c @@ -130,14 +130,55 @@ void peak_usb_get_ts_time(struct peak_time_ref *time_ref, u32 ts, ktime_t *time) /* protect from getting time before setting now */ if (ktime_to_ns(time_ref->tv_host)) { u64 delta_us; + s64 delta_ts = 0; + + /* General case: dev_ts_1 < dev_ts_2 < ts, with: + * + * - dev_ts_1 = previous sync timestamp + * - dev_ts_2 = last sync timestamp + * - ts = event timestamp + * - ts_period = known sync period (theoretical) + * ~ dev_ts2 - dev_ts1 + * *but*: + * + * - time counters wrap (see adapter->ts_used_bits) + * - sometimes, dev_ts_1 < ts < dev_ts2 + * + * "normal" case (sync time counters increase): + * must take into account case when ts wraps (tsw) + * + * < ts_period > < > + * | | | + * ---+--------+----+-------0-+--+--> + * ts_dev_1 | ts_dev_2 | + * ts tsw + */ + if (time_ref->ts_dev_1 < time_ref->ts_dev_2) { + /* case when event time (tsw) wraps */ + if (ts < time_ref->ts_dev_1) + delta_ts = BIT_ULL(time_ref->adapter->ts_used_bits); + + /* Otherwise, sync time counter (ts_dev_2) has wrapped: + * handle case when event time (tsn) hasn't. + * + * < ts_period > < > + * | | | + * ---+--------+--0-+---------+--+--> + * ts_dev_1 | ts_dev_2 | + * tsn ts + */ + } else if (time_ref->ts_dev_1 < ts) { + delta_ts = -BIT_ULL(time_ref->adapter->ts_used_bits); + } - delta_us = ts - time_ref->ts_dev_2; - if (ts < time_ref->ts_dev_2) - delta_us &= (1 << time_ref->adapter->ts_used_bits) - 1; + /* add delay between last sync and event timestamps */ + delta_ts += (signed int)(ts - time_ref->ts_dev_2); - delta_us += time_ref->ts_total; + /* add time from beginning to last sync */ + delta_ts += time_ref->ts_total; - delta_us *= time_ref->adapter->us_per_ts_scale; + /* convert ticks number into microseconds */ + delta_us = delta_ts * time_ref->adapter->us_per_ts_scale; delta_us >>= time_ref->adapter->us_per_ts_shift; *time = ktime_add_us(time_ref->tv_host_0, delta_us); diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c index ab63fd9eb982..d29d20525588 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c @@ -468,12 +468,18 @@ static int pcan_usb_fd_decode_canmsg(struct pcan_usb_fd_if *usb_if, struct pucan_msg *rx_msg) { struct pucan_rx_msg *rm = (struct pucan_rx_msg *)rx_msg; - struct peak_usb_device *dev = usb_if->dev[pucan_msg_get_channel(rm)]; - struct net_device *netdev = dev->netdev; + struct peak_usb_device *dev; + struct net_device *netdev; struct canfd_frame *cfd; struct sk_buff *skb; const u16 rx_msg_flags = le16_to_cpu(rm->flags); + if (pucan_msg_get_channel(rm) >= ARRAY_SIZE(usb_if->dev)) + return -ENOMEM; + + dev = usb_if->dev[pucan_msg_get_channel(rm)]; + netdev = dev->netdev; + if (rx_msg_flags & PUCAN_MSG_EXT_DATA_LEN) { /* CANFD frame case */ skb = alloc_canfd_skb(netdev, &cfd); @@ -519,15 +525,21 @@ static int pcan_usb_fd_decode_status(struct pcan_usb_fd_if *usb_if, struct pucan_msg *rx_msg) { struct pucan_status_msg *sm = (struct pucan_status_msg *)rx_msg; - struct peak_usb_device *dev = usb_if->dev[pucan_stmsg_get_channel(sm)]; - struct pcan_usb_fd_device *pdev = - container_of(dev, struct pcan_usb_fd_device, dev); + struct pcan_usb_fd_device *pdev; enum can_state new_state = CAN_STATE_ERROR_ACTIVE; enum can_state rx_state, tx_state; - struct net_device *netdev = dev->netdev; + struct peak_usb_device *dev; + struct net_device *netdev; struct can_frame *cf; struct sk_buff *skb; + if (pucan_stmsg_get_channel(sm) >= ARRAY_SIZE(usb_if->dev)) + return -ENOMEM; + + dev = usb_if->dev[pucan_stmsg_get_channel(sm)]; + pdev = container_of(dev, struct pcan_usb_fd_device, dev); + netdev = dev->netdev; + /* nothing should be sent while in BUS_OFF state */ if (dev->can.state == CAN_STATE_BUS_OFF) return 0; @@ -579,9 +591,14 @@ static int pcan_usb_fd_decode_error(struct pcan_usb_fd_if *usb_if, struct pucan_msg *rx_msg) { struct pucan_error_msg *er = (struct pucan_error_msg *)rx_msg; - struct peak_usb_device *dev = usb_if->dev[pucan_ermsg_get_channel(er)]; - struct pcan_usb_fd_device *pdev = - container_of(dev, struct pcan_usb_fd_device, dev); + struct pcan_usb_fd_device *pdev; + struct peak_usb_device *dev; + + if (pucan_ermsg_get_channel(er) >= ARRAY_SIZE(usb_if->dev)) + return -EINVAL; + + dev = usb_if->dev[pucan_ermsg_get_channel(er)]; + pdev = container_of(dev, struct pcan_usb_fd_device, dev); /* keep a trace of tx and rx error counters for later use */ pdev->bec.txerr = er->tx_err_cnt; @@ -595,11 +612,17 @@ static int pcan_usb_fd_decode_overrun(struct pcan_usb_fd_if *usb_if, struct pucan_msg *rx_msg) { struct pcan_ufd_ovr_msg *ov = (struct pcan_ufd_ovr_msg *)rx_msg; - struct peak_usb_device *dev = usb_if->dev[pufd_omsg_get_channel(ov)]; - struct net_device *netdev = dev->netdev; + struct peak_usb_device *dev; + struct net_device *netdev; struct can_frame *cf; struct sk_buff *skb; + if (pufd_omsg_get_channel(ov) >= ARRAY_SIZE(usb_if->dev)) + return -EINVAL; + + dev = usb_if->dev[pufd_omsg_get_channel(ov)]; + netdev = dev->netdev; + /* allocate an skb to store the error frame */ skb = alloc_can_err_skb(netdev, &cf); if (!skb) @@ -716,6 +739,9 @@ static int pcan_usb_fd_encode_msg(struct peak_usb_device *dev, u16 tx_msg_size, tx_msg_flags; u8 can_dlc; + if (cfd->len > CANFD_MAX_DLEN) + return -EINVAL; + tx_msg_size = ALIGN(sizeof(struct pucan_tx_msg) + cfd->len, 4); tx_msg->size = cpu_to_le16(tx_msg_size); tx_msg->type = cpu_to_le16(PUCAN_MSG_CAN_TX); diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c index 6c4d00d2dbdc..48d746e18f30 100644 --- a/drivers/net/can/xilinx_can.c +++ b/drivers/net/can/xilinx_can.c @@ -1395,7 +1395,7 @@ static int xcan_open(struct net_device *ndev) if (ret < 0) { netdev_err(ndev, "%s: pm_runtime_get failed(%d)\n", __func__, ret); - return ret; + goto err; } ret = request_irq(ndev->irq, xcan_interrupt, priv->irq_flags, @@ -1479,6 +1479,7 @@ static int xcan_get_berr_counter(const struct net_device *ndev, if (ret < 0) { netdev_err(ndev, "%s: pm_runtime_get failed(%d)\n", __func__, ret); + pm_runtime_put(priv->dev); return ret; } @@ -1793,7 +1794,7 @@ static int xcan_probe(struct platform_device *pdev) if (ret < 0) { netdev_err(ndev, "%s: pm_runtime_get failed(%d)\n", __func__, ret); - goto err_pmdisable; + goto err_disableclks; } if (priv->read_reg(priv, XCAN_SR_OFFSET) != XCAN_SR_CONFIG_MASK) { @@ -1828,7 +1829,6 @@ static int xcan_probe(struct platform_device *pdev) err_disableclks: pm_runtime_put(priv->dev); -err_pmdisable: pm_runtime_disable(&pdev->dev); err_free: free_candev(ndev); diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c index 74db81dafee3..09701c17f3f6 100644 --- a/drivers/net/dsa/lantiq_gswip.c +++ b/drivers/net/dsa/lantiq_gswip.c @@ -26,6 +26,7 @@ */ #include <linux/clk.h> +#include <linux/delay.h> #include <linux/etherdevice.h> #include <linux/firmware.h> #include <linux/if_bridge.h> @@ -1837,6 +1838,16 @@ static int gswip_gphy_fw_list(struct gswip_priv *priv, i++; } + /* The standalone PHY11G requires 300ms to be fully + * initialized and ready for any MDIO communication after being + * taken out of reset. For the SoC-internal GPHY variant there + * is no (known) documentation for the minimum time after a + * reset. Use the same value as for the standalone variant as + * some users have reported internal PHYs not being detected + * without any delay. + */ + msleep(300); + return 0; remove_gphy: diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index bd297ae7cf9e..34cca0a4b31c 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -2297,6 +2297,8 @@ static void mv88e6xxx_hardware_reset(struct mv88e6xxx_chip *chip) usleep_range(10000, 20000); gpiod_set_value_cansleep(gpiod, 0); usleep_range(10000, 20000); + + mv88e6xxx_g1_wait_eeprom_done(chip); } } diff --git a/drivers/net/dsa/mv88e6xxx/devlink.c b/drivers/net/dsa/mv88e6xxx/devlink.c index 10cd1bfd81a0..ade04c036fd9 100644 --- a/drivers/net/dsa/mv88e6xxx/devlink.c +++ b/drivers/net/dsa/mv88e6xxx/devlink.c @@ -393,8 +393,10 @@ static int mv88e6xxx_region_atu_snapshot(struct devlink *dl, mv88e6xxx_reg_lock(chip); err = mv88e6xxx_fid_map(chip, fid_bitmap); - if (err) + if (err) { + kfree(table); goto out; + } while (1) { fid = find_next_bit(fid_bitmap, MV88E6XXX_N_FID, fid + 1); diff --git a/drivers/net/dsa/mv88e6xxx/global1.c b/drivers/net/dsa/mv88e6xxx/global1.c index f62aa83ca08d..33d443a37efc 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.c +++ b/drivers/net/dsa/mv88e6xxx/global1.c @@ -75,6 +75,37 @@ static int mv88e6xxx_g1_wait_init_ready(struct mv88e6xxx_chip *chip) return mv88e6xxx_g1_wait_bit(chip, MV88E6XXX_G1_STS, bit, 1); } +void mv88e6xxx_g1_wait_eeprom_done(struct mv88e6xxx_chip *chip) +{ + const unsigned long timeout = jiffies + 1 * HZ; + u16 val; + int err; + + /* Wait up to 1 second for the switch to finish reading the + * EEPROM. + */ + while (time_before(jiffies, timeout)) { + err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_STS, &val); + if (err) { + dev_err(chip->dev, "Error reading status"); + return; + } + + /* If the switch is still resetting, it may not + * respond on the bus, and so MDIO read returns + * 0xffff. Differentiate between that, and waiting for + * the EEPROM to be done by bit 0 being set. + */ + if (val != 0xffff && + val & BIT(MV88E6XXX_G1_STS_IRQ_EEPROM_DONE)) + return; + + usleep_range(1000, 2000); + } + + dev_err(chip->dev, "Timeout waiting for EEPROM done"); +} + /* Offset 0x01: Switch MAC Address Register Bytes 0 & 1 * Offset 0x02: Switch MAC Address Register Bytes 2 & 3 * Offset 0x03: Switch MAC Address Register Bytes 4 & 5 diff --git a/drivers/net/dsa/mv88e6xxx/global1.h b/drivers/net/dsa/mv88e6xxx/global1.h index 1e3546f8b072..e05abe61fa11 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.h +++ b/drivers/net/dsa/mv88e6xxx/global1.h @@ -278,6 +278,7 @@ int mv88e6xxx_g1_set_switch_mac(struct mv88e6xxx_chip *chip, u8 *addr); int mv88e6185_g1_reset(struct mv88e6xxx_chip *chip); int mv88e6352_g1_reset(struct mv88e6xxx_chip *chip); int mv88e6250_g1_reset(struct mv88e6xxx_chip *chip); +void mv88e6xxx_g1_wait_eeprom_done(struct mv88e6xxx_chip *chip); int mv88e6185_g1_ppu_enable(struct mv88e6xxx_chip *chip); int mv88e6185_g1_ppu_disable(struct mv88e6xxx_chip *chip); diff --git a/drivers/net/dsa/mv88e6xxx/global1_vtu.c b/drivers/net/dsa/mv88e6xxx/global1_vtu.c index 48390b7b18ad..1048509a849b 100644 --- a/drivers/net/dsa/mv88e6xxx/global1_vtu.c +++ b/drivers/net/dsa/mv88e6xxx/global1_vtu.c @@ -125,11 +125,9 @@ static int mv88e6xxx_g1_vtu_vid_write(struct mv88e6xxx_chip *chip, * Offset 0x08: VTU/STU Data Register 2 * Offset 0x09: VTU/STU Data Register 3 */ - -static int mv88e6185_g1_vtu_data_read(struct mv88e6xxx_chip *chip, - struct mv88e6xxx_vtu_entry *entry) +static int mv88e6185_g1_vtu_stu_data_read(struct mv88e6xxx_chip *chip, + u16 *regs) { - u16 regs[3]; int i; /* Read all 3 VTU/STU Data registers */ @@ -142,12 +140,45 @@ static int mv88e6185_g1_vtu_data_read(struct mv88e6xxx_chip *chip, return err; } - /* Extract MemberTag and PortState data */ + return 0; +} + +static int mv88e6185_g1_vtu_data_read(struct mv88e6xxx_chip *chip, + struct mv88e6xxx_vtu_entry *entry) +{ + u16 regs[3]; + int err; + int i; + + err = mv88e6185_g1_vtu_stu_data_read(chip, regs); + if (err) + return err; + + /* Extract MemberTag data */ for (i = 0; i < mv88e6xxx_num_ports(chip); ++i) { unsigned int member_offset = (i % 4) * 4; - unsigned int state_offset = member_offset + 2; entry->member[i] = (regs[i / 4] >> member_offset) & 0x3; + } + + return 0; +} + +static int mv88e6185_g1_stu_data_read(struct mv88e6xxx_chip *chip, + struct mv88e6xxx_vtu_entry *entry) +{ + u16 regs[3]; + int err; + int i; + + err = mv88e6185_g1_vtu_stu_data_read(chip, regs); + if (err) + return err; + + /* Extract PortState data */ + for (i = 0; i < mv88e6xxx_num_ports(chip); ++i) { + unsigned int state_offset = (i % 4) * 4 + 2; + entry->state[i] = (regs[i / 4] >> state_offset) & 0x3; } @@ -349,6 +380,10 @@ int mv88e6185_g1_vtu_getnext(struct mv88e6xxx_chip *chip, if (err) return err; + err = mv88e6185_g1_stu_data_read(chip, entry); + if (err) + return err; + /* VTU DBNum[3:0] are located in VTU Operation 3:0 * VTU DBNum[7:4] are located in VTU Operation 11:8 */ @@ -374,16 +409,20 @@ int mv88e6352_g1_vtu_getnext(struct mv88e6xxx_chip *chip, return err; if (entry->valid) { - /* Fetch (and mask) VLAN PortState data from the STU */ - err = mv88e6xxx_g1_vtu_stu_get(chip, entry); + err = mv88e6185_g1_vtu_data_read(chip, entry); if (err) return err; - err = mv88e6185_g1_vtu_data_read(chip, entry); + err = mv88e6xxx_g1_vtu_fid_read(chip, entry); if (err) return err; - err = mv88e6xxx_g1_vtu_fid_read(chip, entry); + /* Fetch VLAN PortState data from the STU */ + err = mv88e6xxx_g1_vtu_stu_get(chip, entry); + if (err) + return err; + + err = mv88e6185_g1_stu_data_read(chip, entry); if (err) return err; } diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c index 53064e0e1618..5bdac669a339 100644 --- a/drivers/net/dsa/qca8k.c +++ b/drivers/net/dsa/qca8k.c @@ -1219,8 +1219,8 @@ qca8k_port_change_mtu(struct dsa_switch *ds, int port, int new_mtu) priv->port_mtu[port] = new_mtu; for (i = 0; i < QCA8K_NUM_PORTS; i++) - if (priv->port_mtu[port] > mtu) - mtu = priv->port_mtu[port]; + if (priv->port_mtu[i] > mtu) + mtu = priv->port_mtu[i]; /* Include L2 header / FCS length */ qca8k_write(priv, QCA8K_MAX_FRAME_SIZE, mtu + ETH_HLEN + ETH_FCS_LEN); diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c index 0c12cf7bda50..3f65f2b370c5 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c +++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c @@ -2543,8 +2543,8 @@ static int atl1c_probe(struct pci_dev *pdev, const struct pci_device_id *ent) * various kernel subsystems to support the mechanics required by a * fixed-high-32-bit system. */ - if ((dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)) != 0) || - (dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32)) != 0)) { + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (err) { dev_err(&pdev->dev, "No usable DMA configuration,aborting\n"); goto err_dma; } diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c index 098b0328e3cb..ff9f96de74b8 100644 --- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c +++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c @@ -2312,8 +2312,8 @@ static int atl1e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) * various kernel subsystems to support the mechanics required by a * fixed-high-32-bit system. */ - if ((dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)) != 0) || - (dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32)) != 0)) { + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (err) { dev_err(&pdev->dev, "No usable DMA configuration,aborting\n"); goto err_dma; } diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c index 74c1778d841e..b455b60a5434 100644 --- a/drivers/net/ethernet/broadcom/b44.c +++ b/drivers/net/ethernet/broadcom/b44.c @@ -2383,7 +2383,8 @@ static int b44_init_one(struct ssb_device *sdev, goto err_out_free_dev; } - if (dma_set_mask_and_coherent(sdev->dma_dev, DMA_BIT_MASK(30))) { + err = dma_set_mask_and_coherent(sdev->dma_dev, DMA_BIT_MASK(30)); + if (err) { dev_err(sdev->dev, "Required 30BIT DMA mask unsupported by the system\n"); goto err_out_powerdown; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 7975f59735d6..7c21aaa8b9af 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -4099,7 +4099,8 @@ static void bnxt_free_mem(struct bnxt *bp, bool irq_re_init) bnxt_free_ntp_fltrs(bp, irq_re_init); if (irq_re_init) { bnxt_free_ring_stats(bp); - if (!(bp->fw_cap & BNXT_FW_CAP_PORT_STATS_NO_RESET)) + if (!(bp->fw_cap & BNXT_FW_CAP_PORT_STATS_NO_RESET) || + test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) bnxt_free_port_stats(bp); bnxt_free_ring_grps(bp); bnxt_free_vnics(bp); @@ -7757,6 +7758,7 @@ static void bnxt_add_one_ctr(u64 hw, u64 *sw, u64 mask) { u64 sw_tmp; + hw &= mask; sw_tmp = (*sw & ~mask) | hw; if (hw < (*sw & mask)) sw_tmp += mask + 1; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 53687bc7fcf5..1471c9a36238 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -2079,6 +2079,9 @@ int bnxt_hwrm_nvm_get_dev_info(struct bnxt *bp, struct hwrm_nvm_get_dev_info_input req = {0}; int rc; + if (BNXT_VF(bp)) + return -EOPNOTSUPP; + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_NVM_GET_DEV_INFO, -1, -1); mutex_lock(&bp->hwrm_cmd_lock); rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); @@ -2997,7 +3000,7 @@ static int bnxt_get_module_eeprom(struct net_device *dev, /* Read A2 portion of the EEPROM */ if (length) { start -= ETH_MODULE_SFF_8436_LEN; - rc = bnxt_read_sfp_module_eeprom_info(bp, I2C_DEV_ADDR_A2, 1, + rc = bnxt_read_sfp_module_eeprom_info(bp, I2C_DEV_ADDR_A2, 0, start, length, data); } return rc; diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 883e47c5b1a7..286f0341bdf8 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -1929,7 +1929,8 @@ static inline int macb_clear_csum(struct sk_buff *skb) static int macb_pad_and_fcs(struct sk_buff **skb, struct net_device *ndev) { - bool cloned = skb_cloned(*skb) || skb_header_cloned(*skb); + bool cloned = skb_cloned(*skb) || skb_header_cloned(*skb) || + skb_is_nonlinear(*skb); int padlen = ETH_ZLEN - (*skb)->len; int headroom = skb_headroom(*skb); int tailroom = skb_tailroom(*skb); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index 3352dad6ca99..27308600da15 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -2124,6 +2124,9 @@ void cxgb4_inline_tx_skb(const struct sk_buff *skb, const struct sge_txq *q, void cxgb4_write_sgl(const struct sk_buff *skb, struct sge_txq *q, struct ulptx_sgl *sgl, u64 *end, unsigned int start, const dma_addr_t *addr); +void cxgb4_write_partial_sgl(const struct sk_buff *skb, struct sge_txq *q, + struct ulptx_sgl *sgl, u64 *end, + const dma_addr_t *addr, u32 start, u32 send_len); void cxgb4_ring_tx_db(struct adapter *adap, struct sge_txq *q, int n); int t4_set_vlan_acl(struct adapter *adap, unsigned int mbox, unsigned int vf, u16 vlan); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c index 0273f40b85f7..17410fe86626 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c @@ -3573,6 +3573,8 @@ static int chcr_stats_show(struct seq_file *seq, void *v) atomic64_read(&adap->ch_ktls_stats.ktls_tx_complete_pkts)); seq_printf(seq, "TX trim pkts : %20llu\n", atomic64_read(&adap->ch_ktls_stats.ktls_tx_trimmed_pkts)); + seq_printf(seq, "TX sw fallback : %20llu\n", + atomic64_read(&adap->ch_ktls_stats.ktls_tx_fallback)); while (i < MAX_NPORTS) { ktls_port = &adap->ch_ktls_stats.ktls_port[i]; seq_printf(seq, "Port %d\n", i); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index a952fe198eb9..7fd264a6d085 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -1176,6 +1176,7 @@ static u16 cxgb_select_queue(struct net_device *dev, struct sk_buff *skb, txq = netdev_pick_tx(dev, skb, sb_dev); if (xfrm_offload(skb) || is_ptp_enabled(skb, dev) || skb->encapsulation || + cxgb4_is_ktls_skb(skb) || (proto != IPPROTO_TCP && proto != IPPROTO_UDP)) txq = txq % pi->nqsets; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h index b169776ab484..1b49f2fa9b18 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h @@ -388,6 +388,7 @@ struct ch_ktls_stats_debug { atomic64_t ktls_tx_retransmit_pkts; atomic64_t ktls_tx_complete_pkts; atomic64_t ktls_tx_trimmed_pkts; + atomic64_t ktls_tx_fallback; }; #endif @@ -493,6 +494,11 @@ struct cxgb4_uld_info { #endif }; +static inline bool cxgb4_is_ktls_skb(struct sk_buff *skb) +{ + return skb->sk && tls_is_sk_tx_device_offloaded(skb->sk); +} + void cxgb4_uld_enable(struct adapter *adap); void cxgb4_register_uld(enum cxgb4_uld type, const struct cxgb4_uld_info *p); int cxgb4_unregister_uld(enum cxgb4_uld type); diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index a9e9c7ae565d..196652a114c5 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -890,6 +890,114 @@ void cxgb4_write_sgl(const struct sk_buff *skb, struct sge_txq *q, } EXPORT_SYMBOL(cxgb4_write_sgl); +/* cxgb4_write_partial_sgl - populate SGL for partial packet + * @skb: the packet + * @q: the Tx queue we are writing into + * @sgl: starting location for writing the SGL + * @end: points right after the end of the SGL + * @addr: the list of bus addresses for the SGL elements + * @start: start offset in the SKB where partial data starts + * @len: length of data from @start to send out + * + * This API will handle sending out partial data of a skb if required. + * Unlike cxgb4_write_sgl, @start can be any offset into the skb data, + * and @len will decide how much data after @start offset to send out. + */ +void cxgb4_write_partial_sgl(const struct sk_buff *skb, struct sge_txq *q, + struct ulptx_sgl *sgl, u64 *end, + const dma_addr_t *addr, u32 start, u32 len) +{ + struct ulptx_sge_pair buf[MAX_SKB_FRAGS / 2 + 1] = {0}, *to; + u32 frag_size, skb_linear_data_len = skb_headlen(skb); + struct skb_shared_info *si = skb_shinfo(skb); + u8 i = 0, frag_idx = 0, nfrags = 0; + skb_frag_t *frag; + + /* Fill the first SGL either from linear data or from partial + * frag based on @start. + */ + if (unlikely(start < skb_linear_data_len)) { + frag_size = min(len, skb_linear_data_len - start); + sgl->len0 = htonl(frag_size); + sgl->addr0 = cpu_to_be64(addr[0] + start); + len -= frag_size; + nfrags++; + } else { + start -= skb_linear_data_len; + frag = &si->frags[frag_idx]; + frag_size = skb_frag_size(frag); + /* find the first frag */ + while (start >= frag_size) { + start -= frag_size; + frag_idx++; + frag = &si->frags[frag_idx]; + frag_size = skb_frag_size(frag); + } + + frag_size = min(len, skb_frag_size(frag) - start); + sgl->len0 = cpu_to_be32(frag_size); + sgl->addr0 = cpu_to_be64(addr[frag_idx + 1] + start); + len -= frag_size; + nfrags++; + frag_idx++; + } + + /* If the entire partial data fit in one SGL, then send it out + * now. + */ + if (!len) + goto done; + + /* Most of the complexity below deals with the possibility we hit the + * end of the queue in the middle of writing the SGL. For this case + * only we create the SGL in a temporary buffer and then copy it. + */ + to = (u8 *)end > (u8 *)q->stat ? buf : sgl->sge; + + /* If the skb couldn't fit in first SGL completely, fill the + * rest of the frags in subsequent SGLs. Note that each SGL + * pair can store 2 frags. + */ + while (len) { + frag_size = min(len, skb_frag_size(&si->frags[frag_idx])); + to->len[i & 1] = cpu_to_be32(frag_size); + to->addr[i & 1] = cpu_to_be64(addr[frag_idx + 1]); + if (i && (i & 1)) + to++; + nfrags++; + frag_idx++; + i++; + len -= frag_size; + } + + /* If we ended in an odd boundary, then set the second SGL's + * length in the pair to 0. + */ + if (i & 1) + to->len[1] = cpu_to_be32(0); + + /* Copy from temporary buffer to Tx ring, in case we hit the + * end of the queue in the middle of writing the SGL. + */ + if (unlikely((u8 *)end > (u8 *)q->stat)) { + u32 part0 = (u8 *)q->stat - (u8 *)sgl->sge, part1; + + if (likely(part0)) + memcpy(sgl->sge, buf, part0); + part1 = (u8 *)end - (u8 *)q->stat; + memcpy(q->desc, (u8 *)buf + part0, part1); + end = (void *)q->desc + part1; + } + + /* 0-pad to multiple of 16 */ + if ((uintptr_t)end & 8) + *end = 0; +done: + sgl->cmd_nsge = htonl(ULPTX_CMD_V(ULP_TX_SC_DSGL) | + ULPTX_NSGE_V(nfrags)); +} +EXPORT_SYMBOL(cxgb4_write_partial_sgl); + /* This function copies 64 byte coalesced work request to * memory mapped BAR2 space. For coalesced WR SGE fetches * data from the FIFO instead of from Host. @@ -1422,7 +1530,8 @@ static netdev_tx_t cxgb4_eth_xmit(struct sk_buff *skb, struct net_device *dev) #endif /* CHELSIO_IPSEC_INLINE */ #if IS_ENABLED(CONFIG_CHELSIO_TLS_DEVICE) - if (skb->decrypted) + if (cxgb4_is_ktls_skb(skb) && + (skb->len - (skb_transport_offset(skb) + tcp_hdrlen(skb)))) return adap->uld[CXGB4_ULD_KTLS].tx_handler(skb, dev); #endif /* CHELSIO_TLS_DEVICE */ diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c index 5195f692f14d..c24485c0d512 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c @@ -14,6 +14,50 @@ static LIST_HEAD(uld_ctx_list); static DEFINE_MUTEX(dev_mutex); +/* chcr_get_nfrags_to_send: get the remaining nfrags after start offset + * @skb: skb + * @start: start offset. + * @len: how much data to send after @start + */ +static int chcr_get_nfrags_to_send(struct sk_buff *skb, u32 start, u32 len) +{ + struct skb_shared_info *si = skb_shinfo(skb); + u32 frag_size, skb_linear_data_len = skb_headlen(skb); + u8 nfrags = 0, frag_idx = 0; + skb_frag_t *frag; + + /* if its a linear skb then return 1 */ + if (!skb_is_nonlinear(skb)) + return 1; + + if (unlikely(start < skb_linear_data_len)) { + frag_size = min(len, skb_linear_data_len - start); + start = 0; + } else { + start -= skb_linear_data_len; + + frag = &si->frags[frag_idx]; + frag_size = skb_frag_size(frag); + while (start >= frag_size) { + start -= frag_size; + frag_idx++; + frag = &si->frags[frag_idx]; + frag_size = skb_frag_size(frag); + } + frag_size = min(len, skb_frag_size(frag) - start); + } + len -= frag_size; + nfrags++; + + while (len) { + frag_size = min(len, skb_frag_size(&si->frags[frag_idx])); + len -= frag_size; + nfrags++; + frag_idx++; + } + return nfrags; +} + static int chcr_init_tcb_fields(struct chcr_ktls_info *tx_info); /* * chcr_ktls_save_keys: calculate and save crypto keys. @@ -689,7 +733,8 @@ static int chcr_ktls_cpl_set_tcb_rpl(struct adapter *adap, unsigned char *input) } static void *__chcr_write_cpl_set_tcb_ulp(struct chcr_ktls_info *tx_info, - u32 tid, void *pos, u16 word, u64 mask, + u32 tid, void *pos, u16 word, + struct sge_eth_txq *q, u64 mask, u64 val, u32 reply) { struct cpl_set_tcb_field_core *cpl; @@ -698,7 +743,10 @@ static void *__chcr_write_cpl_set_tcb_ulp(struct chcr_ktls_info *tx_info, /* ULP_TXPKT */ txpkt = pos; - txpkt->cmd_dest = htonl(ULPTX_CMD_V(ULP_TX_PKT) | ULP_TXPKT_DEST_V(0)); + txpkt->cmd_dest = htonl(ULPTX_CMD_V(ULP_TX_PKT) | + ULP_TXPKT_CHANNELID_V(tx_info->port_id) | + ULP_TXPKT_FID_V(q->q.cntxt_id) | + ULP_TXPKT_RO_F); txpkt->len = htonl(DIV_ROUND_UP(CHCR_SET_TCB_FIELD_LEN, 16)); /* ULPTX_IDATA sub-command */ @@ -753,7 +801,7 @@ static void *chcr_write_cpl_set_tcb_ulp(struct chcr_ktls_info *tx_info, } else { u8 buf[48] = {0}; - __chcr_write_cpl_set_tcb_ulp(tx_info, tid, buf, word, + __chcr_write_cpl_set_tcb_ulp(tx_info, tid, buf, word, q, mask, val, reply); return chcr_copy_to_txd(buf, &q->q, pos, @@ -761,7 +809,7 @@ static void *chcr_write_cpl_set_tcb_ulp(struct chcr_ktls_info *tx_info, } } - pos = __chcr_write_cpl_set_tcb_ulp(tx_info, tid, pos, word, + pos = __chcr_write_cpl_set_tcb_ulp(tx_info, tid, pos, word, q, mask, val, reply); /* check again if we are at the end of the queue */ @@ -783,11 +831,11 @@ static void *chcr_write_cpl_set_tcb_ulp(struct chcr_ktls_info *tx_info, */ static int chcr_ktls_xmit_tcb_cpls(struct chcr_ktls_info *tx_info, struct sge_eth_txq *q, u64 tcp_seq, - u64 tcp_ack, u64 tcp_win) + u64 tcp_ack, u64 tcp_win, bool offset) { bool first_wr = ((tx_info->prev_ack == 0) && (tx_info->prev_win == 0)); struct ch_ktls_port_stats_debug *port_stats; - u32 len, cpl = 0, ndesc, wr_len; + u32 len, cpl = 0, ndesc, wr_len, wr_mid = 0; struct fw_ulptx_wr *wr; int credits; void *pos; @@ -803,6 +851,11 @@ static int chcr_ktls_xmit_tcb_cpls(struct chcr_ktls_info *tx_info, return NETDEV_TX_BUSY; } + if (unlikely(credits < ETHTXQ_STOP_THRES)) { + chcr_eth_txq_stop(q); + wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F; + } + pos = &q->q.desc[q->q.pidx]; /* make space for WR, we'll fill it later when we know all the cpls * being sent out and have complete length. @@ -818,7 +871,7 @@ static int chcr_ktls_xmit_tcb_cpls(struct chcr_ktls_info *tx_info, cpl++; } /* reset snd una if it's a re-transmit pkt */ - if (tcp_seq != tx_info->prev_seq) { + if (tcp_seq != tx_info->prev_seq || offset) { /* reset snd_una */ port_stats = &tx_info->adap->ch_ktls_stats.ktls_port[tx_info->port_id]; @@ -827,7 +880,8 @@ static int chcr_ktls_xmit_tcb_cpls(struct chcr_ktls_info *tx_info, TCB_SND_UNA_RAW_V (TCB_SND_UNA_RAW_M), TCB_SND_UNA_RAW_V(0), 0); - atomic64_inc(&port_stats->ktls_tx_ooo); + if (tcp_seq != tx_info->prev_seq) + atomic64_inc(&port_stats->ktls_tx_ooo); cpl++; } /* update ack */ @@ -856,7 +910,8 @@ static int chcr_ktls_xmit_tcb_cpls(struct chcr_ktls_info *tx_info, wr->op_to_compl = htonl(FW_WR_OP_V(FW_ULPTX_WR)); wr->cookie = 0; /* fill len in wr field */ - wr->flowid_len16 = htonl(FW_WR_LEN16_V(DIV_ROUND_UP(len, 16))); + wr->flowid_len16 = htonl(wr_mid | + FW_WR_LEN16_V(DIV_ROUND_UP(len, 16))); ndesc = DIV_ROUND_UP(len, 64); chcr_txq_advance(&q->q, ndesc); @@ -866,34 +921,14 @@ static int chcr_ktls_xmit_tcb_cpls(struct chcr_ktls_info *tx_info, } /* - * chcr_ktls_skb_copy - * @nskb - new skb where the frags to be added. - * @skb - old skb from which frags will be copied. - */ -static void chcr_ktls_skb_copy(struct sk_buff *skb, struct sk_buff *nskb) -{ - int i; - - for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - skb_shinfo(nskb)->frags[i] = skb_shinfo(skb)->frags[i]; - __skb_frag_ref(&skb_shinfo(nskb)->frags[i]); - } - - skb_shinfo(nskb)->nr_frags = skb_shinfo(skb)->nr_frags; - nskb->len += skb->data_len; - nskb->data_len = skb->data_len; - nskb->truesize += skb->data_len; -} - -/* * chcr_ktls_get_tx_flits * returns number of flits to be sent out, it includes key context length, WR * size and skb fragments. */ static unsigned int -chcr_ktls_get_tx_flits(const struct sk_buff *skb, unsigned int key_ctx_len) +chcr_ktls_get_tx_flits(u32 nr_frags, unsigned int key_ctx_len) { - return chcr_sgl_len(skb_shinfo(skb)->nr_frags) + + return chcr_sgl_len(nr_frags) + DIV_ROUND_UP(key_ctx_len + CHCR_KTLS_WR_SIZE, 8); } @@ -957,8 +992,10 @@ chcr_ktls_write_tcp_options(struct chcr_ktls_info *tx_info, struct sk_buff *skb, struct tcphdr *tcp; int len16, pktlen; struct iphdr *ip; + u32 wr_mid = 0; int credits; u8 buf[150]; + u64 cntrl1; void *pos; iplen = skb_network_header_len(skb); @@ -967,7 +1004,7 @@ chcr_ktls_write_tcp_options(struct chcr_ktls_info *tx_info, struct sk_buff *skb, /* packet length = eth hdr len + ip hdr len + tcp hdr len * (including options). */ - pktlen = skb->len - skb->data_len; + pktlen = skb_transport_offset(skb) + tcp_hdrlen(skb); ctrl = sizeof(*cpl) + pktlen; len16 = DIV_ROUND_UP(sizeof(*wr) + ctrl, 16); @@ -980,6 +1017,11 @@ chcr_ktls_write_tcp_options(struct chcr_ktls_info *tx_info, struct sk_buff *skb, return NETDEV_TX_BUSY; } + if (unlikely(credits < ETHTXQ_STOP_THRES)) { + chcr_eth_txq_stop(q); + wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F; + } + pos = &q->q.desc[q->q.pidx]; wr = pos; @@ -987,7 +1029,7 @@ chcr_ktls_write_tcp_options(struct chcr_ktls_info *tx_info, struct sk_buff *skb, wr->op_immdlen = htonl(FW_WR_OP_V(FW_ETH_TX_PKT_WR) | FW_WR_IMMDLEN_V(ctrl)); - wr->equiq_to_len16 = htonl(FW_WR_LEN16_V(len16)); + wr->equiq_to_len16 = htonl(wr_mid | FW_WR_LEN16_V(len16)); wr->r3 = 0; cpl = (void *)(wr + 1); @@ -997,22 +1039,28 @@ chcr_ktls_write_tcp_options(struct chcr_ktls_info *tx_info, struct sk_buff *skb, TXPKT_PF_V(tx_info->adap->pf)); cpl->pack = 0; cpl->len = htons(pktlen); - /* checksum offload */ - cpl->ctrl1 = 0; - - pos = cpl + 1; memcpy(buf, skb->data, pktlen); if (tx_info->ip_family == AF_INET) { /* we need to correct ip header len */ ip = (struct iphdr *)(buf + maclen); ip->tot_len = htons(pktlen - maclen); + cntrl1 = TXPKT_CSUM_TYPE_V(TX_CSUM_TCPIP); #if IS_ENABLED(CONFIG_IPV6) } else { ip6 = (struct ipv6hdr *)(buf + maclen); ip6->payload_len = htons(pktlen - maclen - iplen); + cntrl1 = TXPKT_CSUM_TYPE_V(TX_CSUM_TCPIP6); #endif } + + cntrl1 |= T6_TXPKT_ETHHDR_LEN_V(maclen - ETH_HLEN) | + TXPKT_IPHDR_LEN_V(iplen); + /* checksum offload */ + cpl->ctrl1 = cpu_to_be64(cntrl1); + + pos = cpl + 1; + /* now take care of the tcp header, if fin is not set then clear push * bit as well, and if fin is set, it will be sent at the last so we * need to update the tcp sequence number as per the last packet. @@ -1031,71 +1079,6 @@ chcr_ktls_write_tcp_options(struct chcr_ktls_info *tx_info, struct sk_buff *skb, return 0; } -/* chcr_ktls_skb_shift - Shifts request length paged data from skb to another. - * @tgt- buffer into which tail data gets added - * @skb- buffer from which the paged data comes from - * @shiftlen- shift up to this many bytes - */ -static int chcr_ktls_skb_shift(struct sk_buff *tgt, struct sk_buff *skb, - int shiftlen) -{ - skb_frag_t *fragfrom, *fragto; - int from, to, todo; - - WARN_ON(shiftlen > skb->data_len); - - todo = shiftlen; - from = 0; - to = 0; - fragfrom = &skb_shinfo(skb)->frags[from]; - - while ((todo > 0) && (from < skb_shinfo(skb)->nr_frags)) { - fragfrom = &skb_shinfo(skb)->frags[from]; - fragto = &skb_shinfo(tgt)->frags[to]; - - if (todo >= skb_frag_size(fragfrom)) { - *fragto = *fragfrom; - todo -= skb_frag_size(fragfrom); - from++; - to++; - - } else { - __skb_frag_ref(fragfrom); - skb_frag_page_copy(fragto, fragfrom); - skb_frag_off_copy(fragto, fragfrom); - skb_frag_size_set(fragto, todo); - - skb_frag_off_add(fragfrom, todo); - skb_frag_size_sub(fragfrom, todo); - todo = 0; - - to++; - break; - } - } - - /* Ready to "commit" this state change to tgt */ - skb_shinfo(tgt)->nr_frags = to; - - /* Reposition in the original skb */ - to = 0; - while (from < skb_shinfo(skb)->nr_frags) - skb_shinfo(skb)->frags[to++] = skb_shinfo(skb)->frags[from++]; - - skb_shinfo(skb)->nr_frags = to; - - WARN_ON(todo > 0 && !skb_shinfo(skb)->nr_frags); - - skb->len -= shiftlen; - skb->data_len -= shiftlen; - skb->truesize -= shiftlen; - tgt->len += shiftlen; - tgt->data_len += shiftlen; - tgt->truesize += shiftlen; - - return shiftlen; -} - /* * chcr_ktls_xmit_wr_complete: This sends out the complete record. If an skb * received has partial end part of the record, send out the complete record, so @@ -1111,6 +1094,8 @@ static int chcr_ktls_skb_shift(struct sk_buff *tgt, struct sk_buff *skb, static int chcr_ktls_xmit_wr_complete(struct sk_buff *skb, struct chcr_ktls_info *tx_info, struct sge_eth_txq *q, u32 tcp_seq, + bool is_last_wr, u32 data_len, + u32 skb_offset, u32 nfrags, bool tcp_push, u32 mss) { u32 len16, wr_mid = 0, flits = 0, ndesc, cipher_start; @@ -1126,7 +1111,7 @@ static int chcr_ktls_xmit_wr_complete(struct sk_buff *skb, u64 *end; /* get the number of flits required */ - flits = chcr_ktls_get_tx_flits(skb, tx_info->key_ctx_len); + flits = chcr_ktls_get_tx_flits(nfrags, tx_info->key_ctx_len); /* number of descriptors */ ndesc = chcr_flits_to_desc(flits); /* check if enough credits available */ @@ -1155,6 +1140,9 @@ static int chcr_ktls_xmit_wr_complete(struct sk_buff *skb, return NETDEV_TX_BUSY; } + if (!is_last_wr) + skb_get(skb); + pos = &q->q.desc[q->q.pidx]; end = (u64 *)pos + flits; /* FW_ULPTX_WR */ @@ -1187,7 +1175,7 @@ static int chcr_ktls_xmit_wr_complete(struct sk_buff *skb, CPL_TX_SEC_PDU_CPLLEN_V(CHCR_CPL_TX_SEC_PDU_LEN_64BIT) | CPL_TX_SEC_PDU_PLACEHOLDER_V(1) | CPL_TX_SEC_PDU_IVINSRTOFST_V(TLS_HEADER_SIZE + 1)); - cpl->pldlen = htonl(skb->data_len); + cpl->pldlen = htonl(data_len); /* encryption should start after tls header size + iv size */ cipher_start = TLS_HEADER_SIZE + tx_info->iv_size + 1; @@ -1229,7 +1217,7 @@ static int chcr_ktls_xmit_wr_complete(struct sk_buff *skb, /* CPL_TX_DATA */ tx_data = (void *)pos; OPCODE_TID(tx_data) = htonl(MK_OPCODE_TID(CPL_TX_DATA, tx_info->tid)); - tx_data->len = htonl(TX_DATA_MSS_V(mss) | TX_LENGTH_V(skb->data_len)); + tx_data->len = htonl(TX_DATA_MSS_V(mss) | TX_LENGTH_V(data_len)); tx_data->rsvd = htonl(tcp_seq); @@ -1249,8 +1237,8 @@ static int chcr_ktls_xmit_wr_complete(struct sk_buff *skb, } /* send the complete packet except the header */ - cxgb4_write_sgl(skb, &q->q, pos, end, skb->len - skb->data_len, - sgl_sdesc->addr); + cxgb4_write_partial_sgl(skb, &q->q, pos, end, sgl_sdesc->addr, + skb_offset, data_len); sgl_sdesc->skb = skb; chcr_txq_advance(&q->q, ndesc); @@ -1282,10 +1270,11 @@ static int chcr_ktls_xmit_wr_short(struct sk_buff *skb, struct sge_eth_txq *q, u32 tcp_seq, bool tcp_push, u32 mss, u32 tls_rec_offset, u8 *prior_data, - u32 prior_data_len) + u32 prior_data_len, u32 data_len, + u32 skb_offset) { + u32 len16, wr_mid = 0, cipher_start, nfrags; struct adapter *adap = tx_info->adap; - u32 len16, wr_mid = 0, cipher_start; unsigned int flits = 0, ndesc; int credits, left, last_desc; struct tx_sw_desc *sgl_sdesc; @@ -1298,10 +1287,11 @@ static int chcr_ktls_xmit_wr_short(struct sk_buff *skb, void *pos; u64 *end; + nfrags = chcr_get_nfrags_to_send(skb, skb_offset, data_len); /* get the number of flits required, it's a partial record so 2 flits * (AES_BLOCK_SIZE) will be added. */ - flits = chcr_ktls_get_tx_flits(skb, tx_info->key_ctx_len) + 2; + flits = chcr_ktls_get_tx_flits(nfrags, tx_info->key_ctx_len) + 2; /* get the correct 8 byte IV of this record */ iv_record = cpu_to_be64(tx_info->iv + tx_info->record_no); /* If it's a middle record and not 16 byte aligned to run AES CTR, need @@ -1373,7 +1363,7 @@ static int chcr_ktls_xmit_wr_short(struct sk_buff *skb, htonl(CPL_TX_SEC_PDU_OPCODE_V(CPL_TX_SEC_PDU) | CPL_TX_SEC_PDU_CPLLEN_V(CHCR_CPL_TX_SEC_PDU_LEN_64BIT) | CPL_TX_SEC_PDU_IVINSRTOFST_V(1)); - cpl->pldlen = htonl(skb->data_len + AES_BLOCK_LEN + prior_data_len); + cpl->pldlen = htonl(data_len + AES_BLOCK_LEN + prior_data_len); cpl->aadstart_cipherstop_hi = htonl(CPL_TX_SEC_PDU_CIPHERSTART_V(cipher_start)); cpl->cipherstop_lo_authinsert = 0; @@ -1404,7 +1394,7 @@ static int chcr_ktls_xmit_wr_short(struct sk_buff *skb, tx_data = (void *)pos; OPCODE_TID(tx_data) = htonl(MK_OPCODE_TID(CPL_TX_DATA, tx_info->tid)); tx_data->len = htonl(TX_DATA_MSS_V(mss) | - TX_LENGTH_V(skb->data_len + prior_data_len)); + TX_LENGTH_V(data_len + prior_data_len)); tx_data->rsvd = htonl(tcp_seq); tx_data->flags = htonl(TX_BYPASS_F); if (tcp_push) @@ -1437,8 +1427,8 @@ static int chcr_ktls_xmit_wr_short(struct sk_buff *skb, if (prior_data_len) pos = chcr_copy_to_txd(prior_data, &q->q, pos, 16); /* send the complete packet except the header */ - cxgb4_write_sgl(skb, &q->q, pos, end, skb->len - skb->data_len, - sgl_sdesc->addr); + cxgb4_write_partial_sgl(skb, &q->q, pos, end, sgl_sdesc->addr, + skb_offset, data_len); sgl_sdesc->skb = skb; chcr_txq_advance(&q->q, ndesc); @@ -1466,6 +1456,7 @@ static int chcr_ktls_tx_plaintxt(struct chcr_ktls_info *tx_info, struct sk_buff *skb, u32 tcp_seq, u32 mss, bool tcp_push, struct sge_eth_txq *q, u32 port_id, u8 *prior_data, + u32 data_len, u32 skb_offset, u32 prior_data_len) { int credits, left, len16, last_desc; @@ -1475,14 +1466,16 @@ static int chcr_ktls_tx_plaintxt(struct chcr_ktls_info *tx_info, struct ulptx_idata *idata; struct ulp_txpkt *ulptx; struct fw_ulptx_wr *wr; - u32 wr_mid = 0; + u32 wr_mid = 0, nfrags; void *pos; u64 *end; flits = DIV_ROUND_UP(CHCR_PLAIN_TX_DATA_LEN, 8); - flits += chcr_sgl_len(skb_shinfo(skb)->nr_frags); + nfrags = chcr_get_nfrags_to_send(skb, skb_offset, data_len); + flits += chcr_sgl_len(nfrags); if (prior_data_len) flits += 2; + /* WR will need len16 */ len16 = DIV_ROUND_UP(flits, 2); /* check how many descriptors needed */ @@ -1535,7 +1528,7 @@ static int chcr_ktls_tx_plaintxt(struct chcr_ktls_info *tx_info, tx_data = (struct cpl_tx_data *)(idata + 1); OPCODE_TID(tx_data) = htonl(MK_OPCODE_TID(CPL_TX_DATA, tx_info->tid)); tx_data->len = htonl(TX_DATA_MSS_V(mss) | - TX_LENGTH_V(skb->data_len + prior_data_len)); + TX_LENGTH_V(data_len + prior_data_len)); /* set tcp seq number */ tx_data->rsvd = htonl(tcp_seq); tx_data->flags = htonl(TX_BYPASS_F); @@ -1559,8 +1552,8 @@ static int chcr_ktls_tx_plaintxt(struct chcr_ktls_info *tx_info, end = pos + left; } /* send the complete packet including the header */ - cxgb4_write_sgl(skb, &q->q, pos, end, skb->len - skb->data_len, - sgl_sdesc->addr); + cxgb4_write_partial_sgl(skb, &q->q, pos, end, sgl_sdesc->addr, + skb_offset, data_len); sgl_sdesc->skb = skb; chcr_txq_advance(&q->q, ndesc); @@ -1568,12 +1561,96 @@ static int chcr_ktls_tx_plaintxt(struct chcr_ktls_info *tx_info, return 0; } +static int chcr_ktls_tunnel_pkt(struct chcr_ktls_info *tx_info, + struct sk_buff *skb, + struct sge_eth_txq *q) +{ + u32 ctrl, iplen, maclen, wr_mid = 0, len16; + struct tx_sw_desc *sgl_sdesc; + struct fw_eth_tx_pkt_wr *wr; + struct cpl_tx_pkt_core *cpl; + unsigned int flits, ndesc; + int credits, last_desc; + u64 cntrl1, *end; + void *pos; + + ctrl = sizeof(*cpl); + flits = DIV_ROUND_UP(sizeof(*wr) + ctrl, 8); + + flits += chcr_sgl_len(skb_shinfo(skb)->nr_frags + 1); + len16 = DIV_ROUND_UP(flits, 2); + /* check how many descriptors needed */ + ndesc = DIV_ROUND_UP(flits, 8); + + credits = chcr_txq_avail(&q->q) - ndesc; + if (unlikely(credits < 0)) { + chcr_eth_txq_stop(q); + return -ENOMEM; + } + + if (unlikely(credits < ETHTXQ_STOP_THRES)) { + chcr_eth_txq_stop(q); + wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F; + } + + last_desc = q->q.pidx + ndesc - 1; + if (last_desc >= q->q.size) + last_desc -= q->q.size; + sgl_sdesc = &q->q.sdesc[last_desc]; + + if (unlikely(cxgb4_map_skb(tx_info->adap->pdev_dev, skb, + sgl_sdesc->addr) < 0)) { + memset(sgl_sdesc->addr, 0, sizeof(sgl_sdesc->addr)); + q->mapping_err++; + return -ENOMEM; + } + + iplen = skb_network_header_len(skb); + maclen = skb_mac_header_len(skb); + + pos = &q->q.desc[q->q.pidx]; + end = (u64 *)pos + flits; + wr = pos; + + /* Firmware work request header */ + wr->op_immdlen = htonl(FW_WR_OP_V(FW_ETH_TX_PKT_WR) | + FW_WR_IMMDLEN_V(ctrl)); + + wr->equiq_to_len16 = htonl(wr_mid | FW_WR_LEN16_V(len16)); + wr->r3 = 0; + + cpl = (void *)(wr + 1); + + /* CPL header */ + cpl->ctrl0 = htonl(TXPKT_OPCODE_V(CPL_TX_PKT) | + TXPKT_INTF_V(tx_info->tx_chan) | + TXPKT_PF_V(tx_info->adap->pf)); + cpl->pack = 0; + cntrl1 = TXPKT_CSUM_TYPE_V(tx_info->ip_family == AF_INET ? + TX_CSUM_TCPIP : TX_CSUM_TCPIP6); + cntrl1 |= T6_TXPKT_ETHHDR_LEN_V(maclen - ETH_HLEN) | + TXPKT_IPHDR_LEN_V(iplen); + /* checksum offload */ + cpl->ctrl1 = cpu_to_be64(cntrl1); + cpl->len = htons(skb->len); + + pos = cpl + 1; + + cxgb4_write_sgl(skb, &q->q, pos, end, 0, sgl_sdesc->addr); + sgl_sdesc->skb = skb; + chcr_txq_advance(&q->q, ndesc); + cxgb4_ring_tx_db(tx_info->adap, &q->q, ndesc); + return 0; +} + /* * chcr_ktls_copy_record_in_skb * @nskb - new skb where the frags to be added. + * @skb - old skb, to copy socket and destructor details. * @record - specific record which has complete 16k record in frags. */ static void chcr_ktls_copy_record_in_skb(struct sk_buff *nskb, + struct sk_buff *skb, struct tls_record_info *record) { int i = 0; @@ -1588,6 +1665,9 @@ static void chcr_ktls_copy_record_in_skb(struct sk_buff *nskb, nskb->data_len = record->len; nskb->len += record->len; nskb->truesize += record->len; + nskb->sk = skb->sk; + nskb->destructor = skb->destructor; + refcount_add(nskb->truesize, &nskb->sk->sk_wmem_alloc); } /* @@ -1659,7 +1739,7 @@ static int chcr_end_part_handler(struct chcr_ktls_info *tx_info, struct sk_buff *skb, struct tls_record_info *record, u32 tcp_seq, int mss, bool tcp_push_no_fin, - struct sge_eth_txq *q, + struct sge_eth_txq *q, u32 skb_offset, u32 tls_end_offset, bool last_wr) { struct sk_buff *nskb = NULL; @@ -1668,30 +1748,37 @@ static int chcr_end_part_handler(struct chcr_ktls_info *tx_info, nskb = skb; atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_complete_pkts); } else { - dev_kfree_skb_any(skb); - - nskb = alloc_skb(0, GFP_KERNEL); - if (!nskb) + nskb = alloc_skb(0, GFP_ATOMIC); + if (!nskb) { + dev_kfree_skb_any(skb); return NETDEV_TX_BUSY; + } + /* copy complete record in skb */ - chcr_ktls_copy_record_in_skb(nskb, record); + chcr_ktls_copy_record_in_skb(nskb, skb, record); /* packet is being sent from the beginning, update the tcp_seq * accordingly. */ tcp_seq = tls_record_start_seq(record); - /* reset snd una, so the middle record won't send the already - * sent part. - */ - if (chcr_ktls_update_snd_una(tx_info, q)) - goto out; + /* reset skb offset */ + skb_offset = 0; + + if (last_wr) + dev_kfree_skb_any(skb); + + last_wr = true; + atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_end_pkts); } if (chcr_ktls_xmit_wr_complete(nskb, tx_info, q, tcp_seq, + last_wr, record->len, skb_offset, + record->num_frags, (last_wr && tcp_push_no_fin), mss)) { goto out; } + tx_info->prev_seq = record->end_seq; return 0; out: dev_kfree_skb_any(nskb); @@ -1723,41 +1810,47 @@ static int chcr_short_record_handler(struct chcr_ktls_info *tx_info, struct sk_buff *skb, struct tls_record_info *record, u32 tcp_seq, int mss, bool tcp_push_no_fin, + u32 data_len, u32 skb_offset, struct sge_eth_txq *q, u32 tls_end_offset) { u32 tls_rec_offset = tcp_seq - tls_record_start_seq(record); u8 prior_data[16] = {0}; u32 prior_data_len = 0; - u32 data_len; /* check if the skb is ending in middle of tag/HASH, its a big * trouble, send the packet before the HASH. */ - int remaining_record = tls_end_offset - skb->data_len; + int remaining_record = tls_end_offset - data_len; if (remaining_record > 0 && remaining_record < TLS_CIPHER_AES_GCM_128_TAG_SIZE) { - int trimmed_len = skb->data_len - - (TLS_CIPHER_AES_GCM_128_TAG_SIZE - remaining_record); - struct sk_buff *tmp_skb = NULL; - /* don't process the pkt if it is only a partial tag */ - if (skb->data_len < TLS_CIPHER_AES_GCM_128_TAG_SIZE) - goto out; + int trimmed_len = 0; - WARN_ON(trimmed_len > skb->data_len); + if (tls_end_offset > TLS_CIPHER_AES_GCM_128_TAG_SIZE) + trimmed_len = data_len - + (TLS_CIPHER_AES_GCM_128_TAG_SIZE - + remaining_record); + if (!trimmed_len) + return FALLBACK; - /* shift to those many bytes */ - tmp_skb = alloc_skb(0, GFP_KERNEL); - if (unlikely(!tmp_skb)) - goto out; + WARN_ON(trimmed_len > data_len); - chcr_ktls_skb_shift(tmp_skb, skb, trimmed_len); - /* free the last trimmed portion */ - dev_kfree_skb_any(skb); - skb = tmp_skb; + data_len = trimmed_len; atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_trimmed_pkts); } - data_len = skb->data_len; + + /* check if it is only the header part. */ + if (tls_rec_offset + data_len <= (TLS_HEADER_SIZE + tx_info->iv_size)) { + if (chcr_ktls_tx_plaintxt(tx_info, skb, tcp_seq, mss, + tcp_push_no_fin, q, + tx_info->port_id, prior_data, + data_len, skb_offset, prior_data_len)) + goto out; + + tx_info->prev_seq = tcp_seq + data_len; + return 0; + } + /* check if the middle record's start point is 16 byte aligned. CTR * needs 16 byte aligned start point to start encryption. */ @@ -1818,9 +1911,6 @@ static int chcr_short_record_handler(struct chcr_ktls_info *tx_info, } /* reset tcp_seq as per the prior_data_required len */ tcp_seq -= prior_data_len; - /* include prio_data_len for further calculation. - */ - data_len += prior_data_len; } /* reset snd una, so the middle record won't send the already * sent part. @@ -1829,37 +1919,54 @@ static int chcr_short_record_handler(struct chcr_ktls_info *tx_info, goto out; atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_middle_pkts); } else { - /* Else means, its a partial first part of the record. Check if - * its only the header, don't need to send for encryption then. - */ - if (data_len <= TLS_HEADER_SIZE + tx_info->iv_size) { - if (chcr_ktls_tx_plaintxt(tx_info, skb, tcp_seq, mss, - tcp_push_no_fin, q, - tx_info->port_id, - prior_data, - prior_data_len)) { - goto out; - } - return 0; - } atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_start_pkts); } if (chcr_ktls_xmit_wr_short(skb, tx_info, q, tcp_seq, tcp_push_no_fin, mss, tls_rec_offset, prior_data, - prior_data_len)) { + prior_data_len, data_len, skb_offset)) { goto out; } + tx_info->prev_seq = tcp_seq + data_len + prior_data_len; return 0; out: dev_kfree_skb_any(skb); return NETDEV_TX_BUSY; } +static int chcr_ktls_sw_fallback(struct sk_buff *skb, + struct chcr_ktls_info *tx_info, + struct sge_eth_txq *q) +{ + u32 data_len, skb_offset; + struct sk_buff *nskb; + struct tcphdr *th; + + nskb = tls_encrypt_skb(skb); + + if (!nskb) + return 0; + + th = tcp_hdr(nskb); + skb_offset = skb_transport_offset(nskb) + tcp_hdrlen(nskb); + data_len = nskb->len - skb_offset; + skb_tx_timestamp(nskb); + + if (chcr_ktls_tunnel_pkt(tx_info, nskb, q)) + goto out; + + tx_info->prev_seq = ntohl(th->seq) + data_len; + atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_fallback); + return 0; +out: + dev_kfree_skb_any(nskb); + return 0; +} /* nic tls TX handler */ static int chcr_ktls_xmit(struct sk_buff *skb, struct net_device *dev) { + u32 tls_end_offset, tcp_seq, skb_data_len, skb_offset; struct ch_ktls_port_stats_debug *port_stats; struct chcr_ktls_ofld_ctx_tx *tx_ctx; struct ch_ktls_stats_debug *stats; @@ -1867,20 +1974,17 @@ static int chcr_ktls_xmit(struct sk_buff *skb, struct net_device *dev) int data_len, qidx, ret = 0, mss; struct tls_record_info *record; struct chcr_ktls_info *tx_info; - u32 tls_end_offset, tcp_seq; struct tls_context *tls_ctx; - struct sk_buff *local_skb; struct sge_eth_txq *q; struct adapter *adap; unsigned long flags; tcp_seq = ntohl(th->seq); + skb_offset = skb_transport_offset(skb) + tcp_hdrlen(skb); + skb_data_len = skb->len - skb_offset; + data_len = skb_data_len; - mss = skb_is_gso(skb) ? skb_shinfo(skb)->gso_size : skb->data_len; - - /* check if we haven't set it for ktls offload */ - if (!skb->sk || !tls_is_sk_tx_device_offloaded(skb->sk)) - goto out; + mss = skb_is_gso(skb) ? skb_shinfo(skb)->gso_size : data_len; tls_ctx = tls_get_ctx(skb->sk); if (unlikely(tls_ctx->netdev != dev)) @@ -1892,14 +1996,6 @@ static int chcr_ktls_xmit(struct sk_buff *skb, struct net_device *dev) if (unlikely(!tx_info)) goto out; - /* don't touch the original skb, make a new skb to extract each records - * and send them separately. - */ - local_skb = alloc_skb(0, GFP_KERNEL); - - if (unlikely(!local_skb)) - return NETDEV_TX_BUSY; - adap = tx_info->adap; stats = &adap->ch_ktls_stats; port_stats = &stats->ktls_port[tx_info->port_id]; @@ -1914,20 +2010,7 @@ static int chcr_ktls_xmit(struct sk_buff *skb, struct net_device *dev) if (ret) return NETDEV_TX_BUSY; } - /* update tcb */ - ret = chcr_ktls_xmit_tcb_cpls(tx_info, q, ntohl(th->seq), - ntohl(th->ack_seq), - ntohs(th->window)); - if (ret) { - dev_kfree_skb_any(local_skb); - return NETDEV_TX_BUSY; - } - /* copy skb contents into local skb */ - chcr_ktls_skb_copy(skb, local_skb); - - /* go through the skb and send only one record at a time. */ - data_len = skb->data_len; /* TCP segments can be in received either complete or partial. * chcr_end_part_handler will handle cases if complete record or end * part of the record is received. Incase of partial end part of record, @@ -1952,10 +2035,64 @@ static int chcr_ktls_xmit(struct sk_buff *skb, struct net_device *dev) goto out; } + tls_end_offset = record->end_seq - tcp_seq; + + pr_debug("seq 0x%x, end_seq 0x%x prev_seq 0x%x, datalen 0x%x\n", + tcp_seq, record->end_seq, tx_info->prev_seq, data_len); + /* update tcb for the skb */ + if (skb_data_len == data_len) { + u32 tx_max = tcp_seq; + + if (!tls_record_is_start_marker(record) && + tls_end_offset < TLS_CIPHER_AES_GCM_128_TAG_SIZE) + tx_max = record->end_seq - + TLS_CIPHER_AES_GCM_128_TAG_SIZE; + + ret = chcr_ktls_xmit_tcb_cpls(tx_info, q, tx_max, + ntohl(th->ack_seq), + ntohs(th->window), + tls_end_offset != + record->len); + if (ret) { + spin_unlock_irqrestore(&tx_ctx->base.lock, + flags); + goto out; + } + + if (th->fin) + skb_get(skb); + } + if (unlikely(tls_record_is_start_marker(record))) { - spin_unlock_irqrestore(&tx_ctx->base.lock, flags); atomic64_inc(&port_stats->ktls_tx_skip_no_sync_data); - goto out; + /* If tls_end_offset < data_len, means there is some + * data after start marker, which needs encryption, send + * plaintext first and take skb refcount. else send out + * complete pkt as plaintext. + */ + if (tls_end_offset < data_len) + skb_get(skb); + else + tls_end_offset = data_len; + + ret = chcr_ktls_tx_plaintxt(tx_info, skb, tcp_seq, mss, + (!th->fin && th->psh), q, + tx_info->port_id, NULL, + tls_end_offset, skb_offset, + 0); + + spin_unlock_irqrestore(&tx_ctx->base.lock, flags); + if (ret) { + /* free the refcount taken earlier */ + if (tls_end_offset < data_len) + dev_kfree_skb_any(skb); + goto out; + } + + data_len -= tls_end_offset; + tcp_seq = record->end_seq; + skb_offset += tls_end_offset; + continue; } /* increase page reference count of the record, so that there @@ -1967,73 +2104,64 @@ static int chcr_ktls_xmit(struct sk_buff *skb, struct net_device *dev) /* lock cleared */ spin_unlock_irqrestore(&tx_ctx->base.lock, flags); - tls_end_offset = record->end_seq - tcp_seq; - pr_debug("seq 0x%x, end_seq 0x%x prev_seq 0x%x, datalen 0x%x\n", - tcp_seq, record->end_seq, tx_info->prev_seq, data_len); /* if a tls record is finishing in this SKB */ if (tls_end_offset <= data_len) { - struct sk_buff *nskb = NULL; - - if (tls_end_offset < data_len) { - nskb = alloc_skb(0, GFP_KERNEL); - if (unlikely(!nskb)) { - ret = -ENOMEM; - goto clear_ref; - } - - chcr_ktls_skb_shift(nskb, local_skb, - tls_end_offset); - } else { - /* its the only record in this skb, directly - * point it. - */ - nskb = local_skb; - } - ret = chcr_end_part_handler(tx_info, nskb, record, + ret = chcr_end_part_handler(tx_info, skb, record, tcp_seq, mss, (!th->fin && th->psh), q, + skb_offset, tls_end_offset, - (nskb == local_skb)); - - if (ret && nskb != local_skb) - dev_kfree_skb_any(local_skb); + skb_offset + + tls_end_offset == skb->len); data_len -= tls_end_offset; /* tcp_seq increment is required to handle next record. */ tcp_seq += tls_end_offset; + skb_offset += tls_end_offset; } else { - ret = chcr_short_record_handler(tx_info, local_skb, + ret = chcr_short_record_handler(tx_info, skb, record, tcp_seq, mss, (!th->fin && th->psh), + data_len, skb_offset, q, tls_end_offset); data_len = 0; } -clear_ref: + /* clear the frag ref count which increased locally before */ for (i = 0; i < record->num_frags; i++) { /* clear the frag ref count */ __skb_frag_unref(&record->frags[i]); } /* if any failure, come out from the loop. */ - if (ret) - goto out; + if (ret) { + if (th->fin) + dev_kfree_skb_any(skb); + + if (ret == FALLBACK) + return chcr_ktls_sw_fallback(skb, tx_info, q); + + return NETDEV_TX_OK; + } + /* length should never be less than 0 */ WARN_ON(data_len < 0); } while (data_len > 0); - tx_info->prev_seq = ntohl(th->seq) + skb->data_len; atomic64_inc(&port_stats->ktls_tx_encrypted_packets); - atomic64_add(skb->data_len, &port_stats->ktls_tx_encrypted_bytes); + atomic64_add(skb_data_len, &port_stats->ktls_tx_encrypted_bytes); /* tcp finish is set, send a separate tcp msg including all the options * as well. */ - if (th->fin) + if (th->fin) { chcr_ktls_write_tcp_options(tx_info, skb, q, tx_info->tx_chan); + dev_kfree_skb_any(skb); + } + return NETDEV_TX_OK; out: dev_kfree_skb_any(skb); return NETDEV_TX_OK; diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.h b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.h index c1651b1431a0..18b3b1f02415 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.h +++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.h @@ -26,6 +26,7 @@ #define CHCR_KTLS_WR_SIZE (CHCR_PLAIN_TX_DATA_LEN +\ sizeof(struct cpl_tx_sec_pdu)) +#define FALLBACK 35 enum ch_ktls_open_state { CH_KTLS_OPEN_SUCCESS = 0, diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c index d581c4e623f8..96d561653496 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c @@ -212,7 +212,7 @@ static struct sk_buff *alloc_ctrl_skb(struct sk_buff *skb, int len) { if (likely(skb && !skb_shared(skb) && !skb_cloned(skb))) { __skb_trim(skb, 0); - refcount_add(2, &skb->users); + refcount_inc(&skb->users); } else { skb = alloc_skb(len, GFP_KERNEL | __GFP_NOFAIL); } diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_hw.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_hw.c index f1820aca0d33..62c829023da5 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_hw.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_hw.c @@ -383,6 +383,9 @@ int chtls_setkey(struct chtls_sock *csk, u32 keylen, if (ret) goto out_notcb; + if (unlikely(csk_flag(sk, CSK_ABORT_SHUTDOWN))) + goto out_notcb; + set_wr_txq(skb, CPL_PRIORITY_DATA, csk->tlshws.txqid); csk->wr_credits -= DIV_ROUND_UP(len, 16); csk->wr_unacked += DIV_ROUND_UP(len, 16); diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index 00024dd41147..80fb1f537bb3 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -1907,6 +1907,8 @@ err_register_netdev: clk_disable_unprepare(priv->rclk); clk_disable_unprepare(priv->clk); err_ncsi_dev: + if (priv->ndev) + ncsi_unregister_dev(priv->ndev); ftgmac100_destroy_mdio(netdev); err_setup_mdio: iounmap(priv->base); @@ -1926,6 +1928,8 @@ static int ftgmac100_remove(struct platform_device *pdev) netdev = platform_get_drvdata(pdev); priv = netdev_priv(netdev); + if (priv->ndev) + ncsi_unregister_dev(priv->ndev); unregister_netdev(netdev); clk_disable_unprepare(priv->rclk); diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index 06cc863f4dd6..d9c285948fc2 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -174,12 +174,17 @@ MODULE_PARM_DESC(tx_timeout, "The Tx timeout in ms"); #define DPAA_PARSE_RESULTS_SIZE sizeof(struct fman_prs_result) #define DPAA_TIME_STAMP_SIZE 8 #define DPAA_HASH_RESULTS_SIZE 8 +#define DPAA_HWA_SIZE (DPAA_PARSE_RESULTS_SIZE + DPAA_TIME_STAMP_SIZE \ + + DPAA_HASH_RESULTS_SIZE) +#define DPAA_RX_PRIV_DATA_DEFAULT_SIZE (DPAA_TX_PRIV_DATA_SIZE + \ + dpaa_rx_extra_headroom) #ifdef CONFIG_DPAA_ERRATUM_A050385 -#define DPAA_RX_PRIV_DATA_SIZE (DPAA_A050385_ALIGN - (DPAA_PARSE_RESULTS_SIZE\ - + DPAA_TIME_STAMP_SIZE + DPAA_HASH_RESULTS_SIZE)) +#define DPAA_RX_PRIV_DATA_A050385_SIZE (DPAA_A050385_ALIGN - DPAA_HWA_SIZE) +#define DPAA_RX_PRIV_DATA_SIZE (fman_has_errata_a050385() ? \ + DPAA_RX_PRIV_DATA_A050385_SIZE : \ + DPAA_RX_PRIV_DATA_DEFAULT_SIZE) #else -#define DPAA_RX_PRIV_DATA_SIZE (u16)(DPAA_TX_PRIV_DATA_SIZE + \ - dpaa_rx_extra_headroom) +#define DPAA_RX_PRIV_DATA_SIZE DPAA_RX_PRIV_DATA_DEFAULT_SIZE #endif #define DPAA_ETH_PCD_RXQ_NUM 128 @@ -2840,7 +2845,8 @@ out_error: return err; } -static inline u16 dpaa_get_headroom(struct dpaa_buffer_layout *bl) +static u16 dpaa_get_headroom(struct dpaa_buffer_layout *bl, + enum port_type port) { u16 headroom; @@ -2854,10 +2860,12 @@ static inline u16 dpaa_get_headroom(struct dpaa_buffer_layout *bl) * * Also make sure the headroom is a multiple of data_align bytes */ - headroom = (u16)(bl->priv_data_size + DPAA_PARSE_RESULTS_SIZE + - DPAA_TIME_STAMP_SIZE + DPAA_HASH_RESULTS_SIZE); + headroom = (u16)(bl[port].priv_data_size + DPAA_HWA_SIZE); - return ALIGN(headroom, DPAA_FD_DATA_ALIGNMENT); + if (port == RX) + return ALIGN(headroom, DPAA_FD_RX_DATA_ALIGNMENT); + else + return ALIGN(headroom, DPAA_FD_DATA_ALIGNMENT); } static int dpaa_eth_probe(struct platform_device *pdev) @@ -3025,8 +3033,8 @@ static int dpaa_eth_probe(struct platform_device *pdev) goto free_dpaa_fqs; } - priv->tx_headroom = dpaa_get_headroom(&priv->buf_layout[TX]); - priv->rx_headroom = dpaa_get_headroom(&priv->buf_layout[RX]); + priv->tx_headroom = dpaa_get_headroom(priv->buf_layout, TX); + priv->rx_headroom = dpaa_get_headroom(priv->buf_layout, RX); /* All real interfaces need their ports initialized */ err = dpaa_eth_init_ports(mac_dev, dpaa_bp, &port_fqs, diff --git a/drivers/net/ethernet/freescale/enetc/Kconfig b/drivers/net/ethernet/freescale/enetc/Kconfig index 0fa18b00c49b..d99ea0f4e4a6 100644 --- a/drivers/net/ethernet/freescale/enetc/Kconfig +++ b/drivers/net/ethernet/freescale/enetc/Kconfig @@ -16,6 +16,7 @@ config FSL_ENETC config FSL_ENETC_VF tristate "ENETC VF driver" depends on PCI && PCI_MSI + select FSL_ENETC_MDIO select PHYLINK select DIMLIB help diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 52be6e315752..fc2075ea57fe 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -33,7 +33,10 @@ netdev_tx_t enetc_xmit(struct sk_buff *skb, struct net_device *ndev) return NETDEV_TX_BUSY; } + enetc_lock_mdio(); count = enetc_map_tx_buffs(tx_ring, skb, priv->active_offloads); + enetc_unlock_mdio(); + if (unlikely(!count)) goto drop_packet_err; @@ -239,7 +242,7 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb, skb_tx_timestamp(skb); /* let H/W know BD ring has been updated */ - enetc_wr_reg(tx_ring->tpir, i); /* includes wmb() */ + enetc_wr_reg_hot(tx_ring->tpir, i); /* includes wmb() */ return count; @@ -262,12 +265,16 @@ static irqreturn_t enetc_msix(int irq, void *data) struct enetc_int_vector *v = data; int i; + enetc_lock_mdio(); + /* disable interrupts */ - enetc_wr_reg(v->rbier, 0); - enetc_wr_reg(v->ricr1, v->rx_ictt); + enetc_wr_reg_hot(v->rbier, 0); + enetc_wr_reg_hot(v->ricr1, v->rx_ictt); for_each_set_bit(i, &v->tx_rings_map, ENETC_MAX_NUM_TXQS) - enetc_wr_reg(v->tbier_base + ENETC_BDR_OFF(i), 0); + enetc_wr_reg_hot(v->tbier_base + ENETC_BDR_OFF(i), 0); + + enetc_unlock_mdio(); napi_schedule(&v->napi); @@ -334,19 +341,23 @@ static int enetc_poll(struct napi_struct *napi, int budget) v->rx_napi_work = false; + enetc_lock_mdio(); + /* enable interrupts */ - enetc_wr_reg(v->rbier, ENETC_RBIER_RXTIE); + enetc_wr_reg_hot(v->rbier, ENETC_RBIER_RXTIE); for_each_set_bit(i, &v->tx_rings_map, ENETC_MAX_NUM_TXQS) - enetc_wr_reg(v->tbier_base + ENETC_BDR_OFF(i), - ENETC_TBIER_TXTIE); + enetc_wr_reg_hot(v->tbier_base + ENETC_BDR_OFF(i), + ENETC_TBIER_TXTIE); + + enetc_unlock_mdio(); return work_done; } static int enetc_bd_ready_count(struct enetc_bdr *tx_ring, int ci) { - int pi = enetc_rd_reg(tx_ring->tcir) & ENETC_TBCIR_IDX_MASK; + int pi = enetc_rd_reg_hot(tx_ring->tcir) & ENETC_TBCIR_IDX_MASK; return pi >= ci ? pi - ci : tx_ring->bd_count - ci + pi; } @@ -386,7 +397,10 @@ static bool enetc_clean_tx_ring(struct enetc_bdr *tx_ring, int napi_budget) i = tx_ring->next_to_clean; tx_swbd = &tx_ring->tx_swbd[i]; + + enetc_lock_mdio(); bds_to_clean = enetc_bd_ready_count(tx_ring, i); + enetc_unlock_mdio(); do_tstamp = false; @@ -429,16 +443,20 @@ static bool enetc_clean_tx_ring(struct enetc_bdr *tx_ring, int napi_budget) tx_swbd = tx_ring->tx_swbd; } + enetc_lock_mdio(); + /* BD iteration loop end */ if (is_eof) { tx_frm_cnt++; /* re-arm interrupt source */ - enetc_wr_reg(tx_ring->idr, BIT(tx_ring->index) | - BIT(16 + tx_ring->index)); + enetc_wr_reg_hot(tx_ring->idr, BIT(tx_ring->index) | + BIT(16 + tx_ring->index)); } if (unlikely(!bds_to_clean)) bds_to_clean = enetc_bd_ready_count(tx_ring, i); + + enetc_unlock_mdio(); } tx_ring->next_to_clean = i; @@ -515,8 +533,6 @@ static int enetc_refill_rx_ring(struct enetc_bdr *rx_ring, const int buff_cnt) if (likely(j)) { rx_ring->next_to_alloc = i; /* keep track from page reuse */ rx_ring->next_to_use = i; - /* update ENETC's consumer index */ - enetc_wr_reg(rx_ring->rcir, i); } return j; @@ -534,8 +550,8 @@ static void enetc_get_rx_tstamp(struct net_device *ndev, u64 tstamp; if (le16_to_cpu(rxbd->r.flags) & ENETC_RXBD_FLAG_TSTMP) { - lo = enetc_rd(hw, ENETC_SICTR0); - hi = enetc_rd(hw, ENETC_SICTR1); + lo = enetc_rd_reg_hot(hw->reg + ENETC_SICTR0); + hi = enetc_rd_reg_hot(hw->reg + ENETC_SICTR1); rxbd = enetc_rxbd_ext(rxbd); tstamp_lo = le32_to_cpu(rxbd->ext.tstamp); if (lo <= tstamp_lo) @@ -684,23 +700,31 @@ static int enetc_clean_rx_ring(struct enetc_bdr *rx_ring, u32 bd_status; u16 size; + enetc_lock_mdio(); + if (cleaned_cnt >= ENETC_RXBD_BUNDLE) { int count = enetc_refill_rx_ring(rx_ring, cleaned_cnt); + /* update ENETC's consumer index */ + enetc_wr_reg_hot(rx_ring->rcir, rx_ring->next_to_use); cleaned_cnt -= count; } rxbd = enetc_rxbd(rx_ring, i); bd_status = le32_to_cpu(rxbd->r.lstatus); - if (!bd_status) + if (!bd_status) { + enetc_unlock_mdio(); break; + } - enetc_wr_reg(rx_ring->idr, BIT(rx_ring->index)); + enetc_wr_reg_hot(rx_ring->idr, BIT(rx_ring->index)); dma_rmb(); /* for reading other rxbd fields */ size = le16_to_cpu(rxbd->r.buf_len); skb = enetc_map_rx_buff_to_skb(rx_ring, i, size); - if (!skb) + if (!skb) { + enetc_unlock_mdio(); break; + } enetc_get_offloads(rx_ring, rxbd, skb); @@ -712,6 +736,7 @@ static int enetc_clean_rx_ring(struct enetc_bdr *rx_ring, if (unlikely(bd_status & ENETC_RXBD_LSTATUS(ENETC_RXBD_ERR_MASK))) { + enetc_unlock_mdio(); dev_kfree_skb(skb); while (!(bd_status & ENETC_RXBD_LSTATUS_F)) { dma_rmb(); @@ -751,6 +776,8 @@ static int enetc_clean_rx_ring(struct enetc_bdr *rx_ring, enetc_process_skb(rx_ring, skb); + enetc_unlock_mdio(); + napi_gro_receive(napi, skb); rx_frm_cnt++; @@ -1225,6 +1252,7 @@ static void enetc_setup_rxbdr(struct enetc_hw *hw, struct enetc_bdr *rx_ring) rx_ring->idr = hw->reg + ENETC_SIRXIDR; enetc_refill_rx_ring(rx_ring, enetc_bd_unused(rx_ring)); + enetc_wr(hw, ENETC_SIRXIDR, rx_ring->next_to_use); /* enable ring */ enetc_rxbdr_wr(hw, idx, ENETC_RBMR, rbmr); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h index 17cf7c94fdb5..eb6bbf1113c7 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h +++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h @@ -324,14 +324,100 @@ struct enetc_hw { void __iomem *global; }; -/* general register accessors */ -#define enetc_rd_reg(reg) ioread32((reg)) -#define enetc_wr_reg(reg, val) iowrite32((val), (reg)) +/* ENETC register accessors */ + +/* MDIO issue workaround (on LS1028A) - + * Due to a hardware issue, an access to MDIO registers + * that is concurrent with other ENETC register accesses + * may lead to the MDIO access being dropped or corrupted. + * To protect the MDIO accesses a readers-writers locking + * scheme is used, where the MDIO register accesses are + * protected by write locks to insure exclusivity, while + * the remaining ENETC registers are accessed under read + * locks since they only compete with MDIO accesses. + */ +extern rwlock_t enetc_mdio_lock; + +/* use this locking primitive only on the fast datapath to + * group together multiple non-MDIO register accesses to + * minimize the overhead of the lock + */ +static inline void enetc_lock_mdio(void) +{ + read_lock(&enetc_mdio_lock); +} + +static inline void enetc_unlock_mdio(void) +{ + read_unlock(&enetc_mdio_lock); +} + +/* use these accessors only on the fast datapath under + * the enetc_lock_mdio() locking primitive to minimize + * the overhead of the lock + */ +static inline u32 enetc_rd_reg_hot(void __iomem *reg) +{ + lockdep_assert_held(&enetc_mdio_lock); + + return ioread32(reg); +} + +static inline void enetc_wr_reg_hot(void __iomem *reg, u32 val) +{ + lockdep_assert_held(&enetc_mdio_lock); + + iowrite32(val, reg); +} + +/* internal helpers for the MDIO w/a */ +static inline u32 _enetc_rd_reg_wa(void __iomem *reg) +{ + u32 val; + + enetc_lock_mdio(); + val = ioread32(reg); + enetc_unlock_mdio(); + + return val; +} + +static inline void _enetc_wr_reg_wa(void __iomem *reg, u32 val) +{ + enetc_lock_mdio(); + iowrite32(val, reg); + enetc_unlock_mdio(); +} + +static inline u32 _enetc_rd_mdio_reg_wa(void __iomem *reg) +{ + unsigned long flags; + u32 val; + + write_lock_irqsave(&enetc_mdio_lock, flags); + val = ioread32(reg); + write_unlock_irqrestore(&enetc_mdio_lock, flags); + + return val; +} + +static inline void _enetc_wr_mdio_reg_wa(void __iomem *reg, u32 val) +{ + unsigned long flags; + + write_lock_irqsave(&enetc_mdio_lock, flags); + iowrite32(val, reg); + write_unlock_irqrestore(&enetc_mdio_lock, flags); +} + #ifdef ioread64 -#define enetc_rd_reg64(reg) ioread64((reg)) +static inline u64 _enetc_rd_reg64(void __iomem *reg) +{ + return ioread64(reg); +} #else /* using this to read out stats on 32b systems */ -static inline u64 enetc_rd_reg64(void __iomem *reg) +static inline u64 _enetc_rd_reg64(void __iomem *reg) { u32 low, high, tmp; @@ -345,12 +431,29 @@ static inline u64 enetc_rd_reg64(void __iomem *reg) } #endif +static inline u64 _enetc_rd_reg64_wa(void __iomem *reg) +{ + u64 val; + + enetc_lock_mdio(); + val = _enetc_rd_reg64(reg); + enetc_unlock_mdio(); + + return val; +} + +/* general register accessors */ +#define enetc_rd_reg(reg) _enetc_rd_reg_wa((reg)) +#define enetc_wr_reg(reg, val) _enetc_wr_reg_wa((reg), (val)) #define enetc_rd(hw, off) enetc_rd_reg((hw)->reg + (off)) #define enetc_wr(hw, off, val) enetc_wr_reg((hw)->reg + (off), val) -#define enetc_rd64(hw, off) enetc_rd_reg64((hw)->reg + (off)) +#define enetc_rd64(hw, off) _enetc_rd_reg64_wa((hw)->reg + (off)) /* port register accessors - PF only */ #define enetc_port_rd(hw, off) enetc_rd_reg((hw)->port + (off)) #define enetc_port_wr(hw, off, val) enetc_wr_reg((hw)->port + (off), val) +#define enetc_port_rd_mdio(hw, off) _enetc_rd_mdio_reg_wa((hw)->port + (off)) +#define enetc_port_wr_mdio(hw, off, val) _enetc_wr_mdio_reg_wa(\ + (hw)->port + (off), val) /* global register accessors - PF only */ #define enetc_global_rd(hw, off) enetc_rd_reg((hw)->global + (off)) #define enetc_global_wr(hw, off, val) enetc_wr_reg((hw)->global + (off), val) diff --git a/drivers/net/ethernet/freescale/enetc/enetc_mdio.c b/drivers/net/ethernet/freescale/enetc/enetc_mdio.c index 48c32a171afa..ee0116ed4738 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_mdio.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_mdio.c @@ -16,13 +16,13 @@ static inline u32 _enetc_mdio_rd(struct enetc_mdio_priv *mdio_priv, int off) { - return enetc_port_rd(mdio_priv->hw, mdio_priv->mdio_base + off); + return enetc_port_rd_mdio(mdio_priv->hw, mdio_priv->mdio_base + off); } static inline void _enetc_mdio_wr(struct enetc_mdio_priv *mdio_priv, int off, u32 val) { - enetc_port_wr(mdio_priv->hw, mdio_priv->mdio_base + off, val); + enetc_port_wr_mdio(mdio_priv->hw, mdio_priv->mdio_base + off, val); } #define enetc_mdio_rd(mdio_priv, off) \ @@ -174,3 +174,7 @@ struct enetc_hw *enetc_hw_alloc(struct device *dev, void __iomem *port_regs) return hw; } EXPORT_SYMBOL_GPL(enetc_hw_alloc); + +/* Lock for MDIO access errata on LS1028A */ +DEFINE_RWLOCK(enetc_mdio_lock); +EXPORT_SYMBOL_GPL(enetc_mdio_lock); diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h index 832a2175636d..c527f4ee1d3a 100644 --- a/drivers/net/ethernet/freescale/fec.h +++ b/drivers/net/ethernet/freescale/fec.h @@ -456,6 +456,12 @@ struct bufdesc_ex { */ #define FEC_QUIRK_HAS_FRREG (1 << 16) +/* Some FEC hardware blocks need the MMFR cleared at setup time to avoid + * the generation of an MII event. This must be avoided in the older + * FEC blocks where it will stop MII events being generated. + */ +#define FEC_QUIRK_CLEAR_SETUP_MII (1 << 17) + struct bufdesc_prop { int qid; /* Address of Rx and Tx buffers */ diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 8f7eca1e7716..04f24c66cf36 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -100,14 +100,14 @@ static const struct fec_devinfo fec_imx27_info = { static const struct fec_devinfo fec_imx28_info = { .quirks = FEC_QUIRK_ENET_MAC | FEC_QUIRK_SWAP_FRAME | FEC_QUIRK_SINGLE_MDIO | FEC_QUIRK_HAS_RACC | - FEC_QUIRK_HAS_FRREG, + FEC_QUIRK_HAS_FRREG | FEC_QUIRK_CLEAR_SETUP_MII, }; static const struct fec_devinfo fec_imx6q_info = { .quirks = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT | FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM | FEC_QUIRK_HAS_VLAN | FEC_QUIRK_ERR006358 | - FEC_QUIRK_HAS_RACC, + FEC_QUIRK_HAS_RACC | FEC_QUIRK_CLEAR_SETUP_MII, }; static const struct fec_devinfo fec_mvf600_info = { @@ -119,7 +119,8 @@ static const struct fec_devinfo fec_imx6x_info = { FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM | FEC_QUIRK_HAS_VLAN | FEC_QUIRK_HAS_AVB | FEC_QUIRK_ERR007885 | FEC_QUIRK_BUG_CAPTURE | - FEC_QUIRK_HAS_RACC | FEC_QUIRK_HAS_COALESCE, + FEC_QUIRK_HAS_RACC | FEC_QUIRK_HAS_COALESCE | + FEC_QUIRK_CLEAR_SETUP_MII, }; static const struct fec_devinfo fec_imx6ul_info = { @@ -127,7 +128,7 @@ static const struct fec_devinfo fec_imx6ul_info = { FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM | FEC_QUIRK_HAS_VLAN | FEC_QUIRK_ERR007885 | FEC_QUIRK_BUG_CAPTURE | FEC_QUIRK_HAS_RACC | - FEC_QUIRK_HAS_COALESCE, + FEC_QUIRK_HAS_COALESCE | FEC_QUIRK_CLEAR_SETUP_MII, }; static struct platform_device_id fec_devtype[] = { @@ -1807,7 +1808,7 @@ static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum) int ret = 0, frame_start, frame_addr, frame_op; bool is_c45 = !!(regnum & MII_ADDR_C45); - ret = pm_runtime_get_sync(dev); + ret = pm_runtime_resume_and_get(dev); if (ret < 0) return ret; @@ -1866,11 +1867,9 @@ static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum, int ret, frame_start, frame_addr; bool is_c45 = !!(regnum & MII_ADDR_C45); - ret = pm_runtime_get_sync(dev); + ret = pm_runtime_resume_and_get(dev); if (ret < 0) return ret; - else - ret = 0; if (is_c45) { frame_start = FEC_MMFR_ST_C45; @@ -2134,15 +2133,17 @@ static int fec_enet_mii_init(struct platform_device *pdev) if (suppress_preamble) fep->phy_speed |= BIT(7); - /* Clear MMFR to avoid to generate MII event by writing MSCR. - * MII event generation condition: - * - writing MSCR: - * - mmfr[31:0]_not_zero & mscr[7:0]_is_zero & - * mscr_reg_data_in[7:0] != 0 - * - writing MMFR: - * - mscr[7:0]_not_zero - */ - writel(0, fep->hwp + FEC_MII_DATA); + if (fep->quirks & FEC_QUIRK_CLEAR_SETUP_MII) { + /* Clear MMFR to avoid to generate MII event by writing MSCR. + * MII event generation condition: + * - writing MSCR: + * - mmfr[31:0]_not_zero & mscr[7:0]_is_zero & + * mscr_reg_data_in[7:0] != 0 + * - writing MMFR: + * - mscr[7:0]_not_zero + */ + writel(0, fep->hwp + FEC_MII_DATA); + } writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED); @@ -2272,7 +2273,7 @@ static void fec_enet_get_regs(struct net_device *ndev, u32 i, off; int ret; - ret = pm_runtime_get_sync(dev); + ret = pm_runtime_resume_and_get(dev); if (ret < 0) return; @@ -2973,7 +2974,7 @@ fec_enet_open(struct net_device *ndev) int ret; bool reset_again; - ret = pm_runtime_get_sync(&fep->pdev->dev); + ret = pm_runtime_resume_and_get(&fep->pdev->dev); if (ret < 0) return ret; @@ -3767,7 +3768,7 @@ fec_drv_remove(struct platform_device *pdev) struct device_node *np = pdev->dev.of_node; int ret; - ret = pm_runtime_get_sync(&pdev->dev); + ret = pm_runtime_resume_and_get(&pdev->dev); if (ret < 0) return ret; diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index 41dd3d0f3452..d391a45cebb6 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -1829,20 +1829,12 @@ static netdev_tx_t gfar_start_xmit(struct sk_buff *skb, struct net_device *dev) fcb_len = GMAC_FCB_LEN + GMAC_TXPAL_LEN; /* make space for additional header when fcb is needed */ - if (fcb_len && unlikely(skb_headroom(skb) < fcb_len)) { - struct sk_buff *skb_new; - - skb_new = skb_realloc_headroom(skb, fcb_len); - if (!skb_new) { + if (fcb_len) { + if (unlikely(skb_cow_head(skb, fcb_len))) { dev->stats.tx_errors++; dev_kfree_skb_any(skb); return NETDEV_TX_OK; } - - if (skb->sk) - skb_set_owner_w(skb_new, skb->sk); - dev_consume_skb_any(skb); - skb = skb_new; } /* total number of fragments in the SKB */ @@ -3380,7 +3372,7 @@ static int gfar_probe(struct platform_device *ofdev) if (dev->features & NETIF_F_IP_CSUM || priv->device_flags & FSL_GIANFAR_DEV_HAS_TIMER) - dev->needed_headroom = GMAC_FCB_LEN; + dev->needed_headroom = GMAC_FCB_LEN + GMAC_TXPAL_LEN; /* Initializing some of the rx/tx queue level parameters */ for (i = 0; i < priv->num_tx_queues; i++) { diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index af4dfbe28d56..da15913879f8 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -1185,18 +1185,27 @@ static int ibmvnic_open(struct net_device *netdev) if (adapter->state != VNIC_CLOSED) { rc = ibmvnic_login(netdev); if (rc) - return rc; + goto out; rc = init_resources(adapter); if (rc) { netdev_err(netdev, "failed to initialize resources\n"); release_resources(adapter); - return rc; + goto out; } } rc = __ibmvnic_open(netdev); +out: + /* + * If open fails due to a pending failover, set device state and + * return. Device operation will be handled by reset routine. + */ + if (rc && adapter->failover_pending) { + adapter->state = VNIC_OPEN; + rc = 0; + } return rc; } @@ -1922,6 +1931,13 @@ static int do_reset(struct ibmvnic_adapter *adapter, rwi->reset_reason); rtnl_lock(); + /* + * Now that we have the rtnl lock, clear any pending failover. + * This will ensure ibmvnic_open() has either completed or will + * block until failover is complete. + */ + if (rwi->reset_reason == VNIC_RESET_FAILOVER) + adapter->failover_pending = false; netif_carrier_off(netdev); adapter->reset_reason = rwi->reset_reason; @@ -2202,6 +2218,13 @@ static void __ibmvnic_reset(struct work_struct *work) /* CHANGE_PARAM requestor holds rtnl_lock */ rc = do_change_param_reset(adapter, rwi, reset_state); } else if (adapter->force_reset_recovery) { + /* + * Since we are doing a hard reset now, clear the + * failover_pending flag so we don't ignore any + * future MOBILITY or other resets. + */ + adapter->failover_pending = false; + /* Transport event occurred during previous reset */ if (adapter->wait_for_reset) { /* Previous was CHANGE_PARAM; caller locked */ @@ -2266,9 +2289,15 @@ static int ibmvnic_reset(struct ibmvnic_adapter *adapter, unsigned long flags; int ret; + /* + * If failover is pending don't schedule any other reset. + * Instead let the failover complete. If there is already a + * a failover reset scheduled, we will detect and drop the + * duplicate reset when walking the ->rwi_list below. + */ if (adapter->state == VNIC_REMOVING || adapter->state == VNIC_REMOVED || - adapter->failover_pending) { + (adapter->failover_pending && reason != VNIC_RESET_FAILOVER)) { ret = EBUSY; netdev_dbg(netdev, "Adapter removing or pending failover, skipping reset\n"); goto err; @@ -4713,7 +4742,6 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq, case IBMVNIC_CRQ_INIT: dev_info(dev, "Partner initialized\n"); adapter->from_passive_init = true; - adapter->failover_pending = false; if (!completion_done(&adapter->init_done)) { complete(&adapter->init_done); adapter->init_done_rc = -EIO; diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index c96e2f2d4cba..4919d22d7b6b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -2713,6 +2713,10 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg) spin_unlock_bh(&vsi->mac_filter_hash_lock); goto error_param; } + if (is_valid_ether_addr(al->list[i].addr) && + is_zero_ether_addr(vf->default_lan_addr.addr)) + ether_addr_copy(vf->default_lan_addr.addr, + al->list[i].addr); } } spin_unlock_bh(&vsi->mac_filter_hash_lock); @@ -2740,6 +2744,7 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg) { struct virtchnl_ether_addr_list *al = (struct virtchnl_ether_addr_list *)msg; + bool was_unimac_deleted = false; struct i40e_pf *pf = vf->pf; struct i40e_vsi *vsi = NULL; i40e_status ret = 0; @@ -2759,6 +2764,8 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg) ret = I40E_ERR_INVALID_MAC_ADDR; goto error_param; } + if (ether_addr_equal(al->list[i].addr, vf->default_lan_addr.addr)) + was_unimac_deleted = true; } vsi = pf->vsi[vf->lan_vsi_idx]; @@ -2779,10 +2786,25 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg) dev_err(&pf->pdev->dev, "Unable to program VF %d MAC filters, error %d\n", vf->vf_id, ret); + if (vf->trusted && was_unimac_deleted) { + struct i40e_mac_filter *f; + struct hlist_node *h; + u8 *macaddr = NULL; + int bkt; + + /* set last unicast mac address as default */ + spin_lock_bh(&vsi->mac_filter_hash_lock); + hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) { + if (is_valid_ether_addr(f->macaddr)) + macaddr = f->macaddr; + } + if (macaddr) + ether_addr_copy(vf->default_lan_addr.addr, macaddr); + spin_unlock_bh(&vsi->mac_filter_hash_lock); + } error_param: /* send the response to the VF */ - return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_DEL_ETH_ADDR, - ret); + return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_DEL_ETH_ADDR, ret); } /** diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 6acede0acdca..567fd67e900e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -281,8 +281,8 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) unsigned int total_rx_bytes = 0, total_rx_packets = 0; u16 cleaned_count = I40E_DESC_UNUSED(rx_ring); unsigned int xdp_res, xdp_xmit = 0; + bool failure = false; struct sk_buff *skb; - bool failure; while (likely(total_rx_packets < (unsigned int)budget)) { union i40e_rx_desc *rx_desc; diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 9112dff075cf..b673ac1199bb 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -3891,21 +3891,23 @@ static int igc_change_mtu(struct net_device *netdev, int new_mtu) } /** - * igc_get_stats - Get System Network Statistics + * igc_get_stats64 - Get System Network Statistics * @netdev: network interface device structure + * @stats: rtnl_link_stats64 pointer * * Returns the address of the device statistics structure. * The statistics are updated here and also from the timer callback. */ -static struct net_device_stats *igc_get_stats(struct net_device *netdev) +static void igc_get_stats64(struct net_device *netdev, + struct rtnl_link_stats64 *stats) { struct igc_adapter *adapter = netdev_priv(netdev); + spin_lock(&adapter->stats64_lock); if (!test_bit(__IGC_RESETTING, &adapter->state)) igc_update_stats(adapter); - - /* only return the current stats */ - return &netdev->stats; + memcpy(stats, &adapter->stats64, sizeof(*stats)); + spin_unlock(&adapter->stats64_lock); } static netdev_features_t igc_fix_features(struct net_device *netdev, @@ -4855,7 +4857,7 @@ static const struct net_device_ops igc_netdev_ops = { .ndo_set_rx_mode = igc_set_rx_mode, .ndo_set_mac_address = igc_set_mac, .ndo_change_mtu = igc_change_mtu, - .ndo_get_stats = igc_get_stats, + .ndo_get_stats64 = igc_get_stats64, .ndo_fix_features = igc_fix_features, .ndo_set_features = igc_set_features, .ndo_features_check = igc_features_check, diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 54b0bf574c05..4a9041ee1b39 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -2287,6 +2287,7 @@ mvneta_swbm_add_rx_fragment(struct mvneta_port *pp, dma_sync_single_for_cpu(dev->dev.parent, rx_desc->buf_phys_addr, len, dma_dir); + rx_desc->buf_phys_addr = 0; if (data_len > 0 && sinfo->nr_frags < MAX_SKB_FRAGS) { skb_frag_t *frag = &sinfo->frags[sinfo->nr_frags]; @@ -2295,8 +2296,8 @@ mvneta_swbm_add_rx_fragment(struct mvneta_port *pp, skb_frag_size_set(frag, data_len); __skb_frag_set_page(frag, page); sinfo->nr_frags++; - - rx_desc->buf_phys_addr = 0; + } else { + page_pool_put_full_page(rxq->page_pool, page, true); } *size -= len; } diff --git a/drivers/net/ethernet/marvell/prestera/Kconfig b/drivers/net/ethernet/marvell/prestera/Kconfig index b1fcc44f566a..b6f20e2034c6 100644 --- a/drivers/net/ethernet/marvell/prestera/Kconfig +++ b/drivers/net/ethernet/marvell/prestera/Kconfig @@ -6,6 +6,7 @@ config PRESTERA tristate "Marvell Prestera Switch ASICs support" depends on NET_SWITCHDEV && VLAN_8021Q + depends on BRIDGE || BRIDGE=n select NET_DEVLINK help This driver supports Marvell Prestera Switch ASICs family. diff --git a/drivers/net/ethernet/marvell/prestera/prestera_pci.c b/drivers/net/ethernet/marvell/prestera/prestera_pci.c index 1b97adae542e..be5677623455 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_pci.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_pci.c @@ -676,7 +676,8 @@ static int prestera_pci_probe(struct pci_dev *pdev, if (err) return err; - if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(30))) { + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(30)); + if (err) { dev_err(&pdev->dev, "fail to set DMA mask\n"); goto err_dma_mask; } @@ -702,8 +703,10 @@ static int prestera_pci_probe(struct pci_dev *pdev, dev_info(fw->dev.dev, "Prestera FW is ready\n"); fw->wq = alloc_workqueue("prestera_fw_wq", WQ_HIGHPRI, 1); - if (!fw->wq) + if (!fw->wq) { + err = -ENOMEM; goto err_wq_alloc; + } INIT_WORK(&fw->evt_work, prestera_fw_evt_work_fn); diff --git a/drivers/net/ethernet/mediatek/mtk_star_emac.c b/drivers/net/ethernet/mediatek/mtk_star_emac.c index 13250553263b..a8641a407c06 100644 --- a/drivers/net/ethernet/mediatek/mtk_star_emac.c +++ b/drivers/net/ethernet/mediatek/mtk_star_emac.c @@ -966,6 +966,7 @@ static int mtk_star_enable(struct net_device *ndev) mtk_star_adjust_link, 0, priv->phy_intf); if (!priv->phydev) { netdev_err(ndev, "failed to connect to PHY\n"); + ret = -ENODEV; goto err_free_irq; } @@ -1053,7 +1054,7 @@ static int mtk_star_netdev_start_xmit(struct sk_buff *skb, err_drop_packet: dev_kfree_skb(skb); ndev->stats.tx_dropped++; - return NETDEV_TX_BUSY; + return NETDEV_TX_OK; } /* Returns the number of bytes sent or a negative number on the first diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index f6ff9620a137..f6cfec81ccc3 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -1864,8 +1864,8 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param) #define INIT_HCA_LOG_RD_OFFSET (INIT_HCA_QPC_OFFSET + 0x77) #define INIT_HCA_MCAST_OFFSET 0x0c0 #define INIT_HCA_MC_BASE_OFFSET (INIT_HCA_MCAST_OFFSET + 0x00) -#define INIT_HCA_LOG_MC_ENTRY_SZ_OFFSET (INIT_HCA_MCAST_OFFSET + 0x12) -#define INIT_HCA_LOG_MC_HASH_SZ_OFFSET (INIT_HCA_MCAST_OFFSET + 0x16) +#define INIT_HCA_LOG_MC_ENTRY_SZ_OFFSET (INIT_HCA_MCAST_OFFSET + 0x13) +#define INIT_HCA_LOG_MC_HASH_SZ_OFFSET (INIT_HCA_MCAST_OFFSET + 0x17) #define INIT_HCA_UC_STEERING_OFFSET (INIT_HCA_MCAST_OFFSET + 0x18) #define INIT_HCA_LOG_MC_TABLE_SZ_OFFSET (INIT_HCA_MCAST_OFFSET + 0x1b) #define INIT_HCA_DEVICE_MANAGED_FLOW_STEERING_EN 0x6 @@ -1873,7 +1873,7 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param) #define INIT_HCA_DRIVER_VERSION_SZ 0x40 #define INIT_HCA_FS_PARAM_OFFSET 0x1d0 #define INIT_HCA_FS_BASE_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x00) -#define INIT_HCA_FS_LOG_ENTRY_SZ_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x12) +#define INIT_HCA_FS_LOG_ENTRY_SZ_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x13) #define INIT_HCA_FS_A0_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x18) #define INIT_HCA_FS_LOG_TABLE_SZ_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x1b) #define INIT_HCA_FS_ETH_BITS_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x21) diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h index 650ae08c71de..8f020f26ebf5 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.h +++ b/drivers/net/ethernet/mellanox/mlx4/fw.h @@ -182,8 +182,8 @@ struct mlx4_init_hca_param { u64 cmpt_base; u64 mtt_base; u64 global_caps; - u16 log_mc_entry_sz; - u16 log_mc_hash_sz; + u8 log_mc_entry_sz; + u8 log_mc_hash_sz; u16 hca_core_clock; /* Internal Clock Frequency (in MHz) */ u8 log_num_qps; u8 log_num_srqs; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c index 3e44e4d820c5..95f2b26a3ee3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c @@ -187,7 +187,7 @@ static bool mlx5e_rep_is_lag_netdev(struct net_device *netdev) struct mlx5e_priv *priv; /* A given netdev is not a representor or not a slave of LAG configuration */ - if (!mlx5e_eswitch_rep(netdev) || !bond_slave_get_rtnl(netdev)) + if (!mlx5e_eswitch_rep(netdev) || !netif_is_lag_port(netdev)) return false; priv = netdev_priv(netdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c index e36e505d38ad..d29af7b9c695 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c @@ -107,12 +107,16 @@ void mlx5e_rep_update_flows(struct mlx5e_priv *priv, mlx5e_tc_encap_flows_del(priv, e, &flow_list); if (neigh_connected && !(e->flags & MLX5_ENCAP_ENTRY_VALID)) { + struct net_device *route_dev; + ether_addr_copy(e->h_dest, ha); ether_addr_copy(eth->h_dest, ha); /* Update the encap source mac, in case that we delete * the flows when encap source mac changed. */ - ether_addr_copy(eth->h_source, e->route_dev->dev_addr); + route_dev = __dev_get_by_index(dev_net(priv->netdev), e->route_dev_ifindex); + if (route_dev) + ether_addr_copy(eth->h_source, route_dev->dev_addr); mlx5e_tc_encap_flows_add(priv, e, &flow_list); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index 7cce85faa16f..90930e54b6f2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -77,13 +77,13 @@ static int get_route_and_out_devs(struct mlx5e_priv *priv, return 0; } -static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv, - struct net_device *mirred_dev, - struct net_device **out_dev, - struct net_device **route_dev, - struct flowi4 *fl4, - struct neighbour **out_n, - u8 *out_ttl) +static int mlx5e_route_lookup_ipv4_get(struct mlx5e_priv *priv, + struct net_device *mirred_dev, + struct net_device **out_dev, + struct net_device **route_dev, + struct flowi4 *fl4, + struct neighbour **out_n, + u8 *out_ttl) { struct neighbour *n; struct rtable *rt; @@ -117,18 +117,28 @@ static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv, ip_rt_put(rt); return ret; } + dev_hold(*route_dev); if (!(*out_ttl)) *out_ttl = ip4_dst_hoplimit(&rt->dst); n = dst_neigh_lookup(&rt->dst, &fl4->daddr); ip_rt_put(rt); - if (!n) + if (!n) { + dev_put(*route_dev); return -ENOMEM; + } *out_n = n; return 0; } +static void mlx5e_route_lookup_ipv4_put(struct net_device *route_dev, + struct neighbour *n) +{ + neigh_release(n); + dev_put(route_dev); +} + static const char *mlx5e_netdev_kind(struct net_device *dev) { if (dev->rtnl_link_ops) @@ -193,8 +203,8 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv, fl4.saddr = tun_key->u.ipv4.src; ttl = tun_key->ttl; - err = mlx5e_route_lookup_ipv4(priv, mirred_dev, &out_dev, &route_dev, - &fl4, &n, &ttl); + err = mlx5e_route_lookup_ipv4_get(priv, mirred_dev, &out_dev, &route_dev, + &fl4, &n, &ttl); if (err) return err; @@ -223,7 +233,7 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv, e->m_neigh.family = n->ops->family; memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len); e->out_dev = out_dev; - e->route_dev = route_dev; + e->route_dev_ifindex = route_dev->ifindex; /* It's important to add the neigh to the hash table before checking * the neigh validity state. So if we'll get a notification, in case the @@ -278,7 +288,7 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv, e->flags |= MLX5_ENCAP_ENTRY_VALID; mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev)); - neigh_release(n); + mlx5e_route_lookup_ipv4_put(route_dev, n); return err; destroy_neigh_entry: @@ -286,18 +296,18 @@ destroy_neigh_entry: free_encap: kfree(encap_header); release_neigh: - neigh_release(n); + mlx5e_route_lookup_ipv4_put(route_dev, n); return err; } #if IS_ENABLED(CONFIG_INET) && IS_ENABLED(CONFIG_IPV6) -static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv, - struct net_device *mirred_dev, - struct net_device **out_dev, - struct net_device **route_dev, - struct flowi6 *fl6, - struct neighbour **out_n, - u8 *out_ttl) +static int mlx5e_route_lookup_ipv6_get(struct mlx5e_priv *priv, + struct net_device *mirred_dev, + struct net_device **out_dev, + struct net_device **route_dev, + struct flowi6 *fl6, + struct neighbour **out_n, + u8 *out_ttl) { struct dst_entry *dst; struct neighbour *n; @@ -318,15 +328,25 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv, return ret; } + dev_hold(*route_dev); n = dst_neigh_lookup(dst, &fl6->daddr); dst_release(dst); - if (!n) + if (!n) { + dev_put(*route_dev); return -ENOMEM; + } *out_n = n; return 0; } +static void mlx5e_route_lookup_ipv6_put(struct net_device *route_dev, + struct neighbour *n) +{ + neigh_release(n); + dev_put(route_dev); +} + int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, struct net_device *mirred_dev, struct mlx5e_encap_entry *e) @@ -348,8 +368,8 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, fl6.daddr = tun_key->u.ipv6.dst; fl6.saddr = tun_key->u.ipv6.src; - err = mlx5e_route_lookup_ipv6(priv, mirred_dev, &out_dev, &route_dev, - &fl6, &n, &ttl); + err = mlx5e_route_lookup_ipv6_get(priv, mirred_dev, &out_dev, &route_dev, + &fl6, &n, &ttl); if (err) return err; @@ -378,7 +398,7 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, e->m_neigh.family = n->ops->family; memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len); e->out_dev = out_dev; - e->route_dev = route_dev; + e->route_dev_ifindex = route_dev->ifindex; /* It's importent to add the neigh to the hash table before checking * the neigh validity state. So if we'll get a notification, in case the @@ -433,7 +453,7 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, e->flags |= MLX5_ENCAP_ENTRY_VALID; mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev)); - neigh_release(n); + mlx5e_route_lookup_ipv6_put(route_dev, n); return err; destroy_neigh_entry: @@ -441,7 +461,7 @@ destroy_neigh_entry: free_encap: kfree(encap_header); release_neigh: - neigh_release(n); + mlx5e_route_lookup_ipv6_put(route_dev, n); return err; } #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c index 4e574ac73019..be3465ba38ca 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c @@ -122,9 +122,9 @@ void mlx5e_activate_xsk(struct mlx5e_channel *c) set_bit(MLX5E_RQ_STATE_ENABLED, &c->xskrq.state); /* TX queue is created active. */ - spin_lock(&c->async_icosq_lock); + spin_lock_bh(&c->async_icosq_lock); mlx5e_trigger_irq(&c->async_icosq); - spin_unlock(&c->async_icosq_lock); + spin_unlock_bh(&c->async_icosq_lock); } void mlx5e_deactivate_xsk(struct mlx5e_channel *c) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c index fb671a457129..8e96260fce1d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c @@ -36,9 +36,9 @@ int mlx5e_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags) if (test_and_set_bit(MLX5E_SQ_STATE_PENDING_XSK_TX, &c->async_icosq.state)) return 0; - spin_lock(&c->async_icosq_lock); + spin_lock_bh(&c->async_icosq_lock); mlx5e_trigger_irq(&c->async_icosq); - spin_unlock(&c->async_icosq_lock); + spin_unlock_bh(&c->async_icosq_lock); } return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c index 0e45590662a8..381a9c8c9da9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c @@ -64,13 +64,13 @@ static int rx_err_add_rule(struct mlx5e_priv *priv, if (!spec) return -ENOMEM; - /* Action to copy 7 bit ipsec_syndrome to regB[0:6] */ + /* Action to copy 7 bit ipsec_syndrome to regB[24:30] */ MLX5_SET(copy_action_in, action, action_type, MLX5_ACTION_TYPE_COPY); MLX5_SET(copy_action_in, action, src_field, MLX5_ACTION_IN_FIELD_IPSEC_SYNDROME); MLX5_SET(copy_action_in, action, src_offset, 0); MLX5_SET(copy_action_in, action, length, 7); MLX5_SET(copy_action_in, action, dst_field, MLX5_ACTION_IN_FIELD_METADATA_REG_B); - MLX5_SET(copy_action_in, action, dst_offset, 0); + MLX5_SET(copy_action_in, action, dst_offset, 24); modify_hdr = mlx5_modify_header_alloc(mdev, MLX5_FLOW_NAMESPACE_KERNEL, 1, action); @@ -488,13 +488,13 @@ static int rx_add_rule(struct mlx5e_priv *priv, setup_fte_common(attrs, ipsec_obj_id, spec, &flow_act); - /* Set 1 bit ipsec marker */ - /* Set 24 bit ipsec_obj_id */ + /* Set bit[31] ipsec marker */ + /* Set bit[23-0] ipsec_obj_id */ MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET); MLX5_SET(set_action_in, action, field, MLX5_ACTION_IN_FIELD_METADATA_REG_B); - MLX5_SET(set_action_in, action, data, (ipsec_obj_id << 1) | 0x1); - MLX5_SET(set_action_in, action, offset, 7); - MLX5_SET(set_action_in, action, length, 25); + MLX5_SET(set_action_in, action, data, (ipsec_obj_id | BIT(31))); + MLX5_SET(set_action_in, action, offset, 0); + MLX5_SET(set_action_in, action, length, 32); modify_hdr = mlx5_modify_header_alloc(priv->mdev, MLX5_FLOW_NAMESPACE_KERNEL, 1, action); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c index 11e31a3db2be..a9b45606dbdb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c @@ -453,7 +453,6 @@ void mlx5e_ipsec_offload_handle_rx_skb(struct net_device *netdev, struct mlx5_cqe64 *cqe) { u32 ipsec_meta_data = be32_to_cpu(cqe->ft_metadata); - u8 ipsec_syndrome = ipsec_meta_data & 0xFF; struct mlx5e_priv *priv; struct xfrm_offload *xo; struct xfrm_state *xs; @@ -481,7 +480,7 @@ void mlx5e_ipsec_offload_handle_rx_skb(struct net_device *netdev, xo = xfrm_offload(skb); xo->flags = CRYPTO_DONE; - switch (ipsec_syndrome & MLX5_IPSEC_METADATA_SYNDROM_MASK) { + switch (MLX5_IPSEC_METADATA_SYNDROM(ipsec_meta_data)) { case MLX5E_IPSEC_OFFLOAD_RX_SYNDROME_DECRYPTED: xo->status = CRYPTO_SUCCESS; if (WARN_ON_ONCE(priv->ipsec->no_trailer)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h index 056dacb612b0..9df9b9a8e09b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h @@ -39,9 +39,10 @@ #include "en.h" #include "en/txrx.h" -#define MLX5_IPSEC_METADATA_MARKER_MASK (0x80) -#define MLX5_IPSEC_METADATA_SYNDROM_MASK (0x7F) -#define MLX5_IPSEC_METADATA_HANDLE(metadata) (((metadata) >> 8) & 0xFF) +/* Bit31: IPsec marker, Bit30-24: IPsec syndrome, Bit23-0: IPsec obj id */ +#define MLX5_IPSEC_METADATA_MARKER(metadata) (((metadata) >> 31) & 0x1) +#define MLX5_IPSEC_METADATA_SYNDROM(metadata) (((metadata) >> 24) & GENMASK(6, 0)) +#define MLX5_IPSEC_METADATA_HANDLE(metadata) ((metadata) & GENMASK(23, 0)) struct mlx5e_accel_tx_ipsec_state { struct xfrm_offload *xo; @@ -78,7 +79,7 @@ static inline unsigned int mlx5e_ipsec_tx_ids_len(struct mlx5e_accel_tx_ipsec_st static inline bool mlx5_ipsec_is_rx_flow(struct mlx5_cqe64 *cqe) { - return !!(MLX5_IPSEC_METADATA_MARKER_MASK & be32_to_cpu(cqe->ft_metadata)); + return MLX5_IPSEC_METADATA_MARKER(be32_to_cpu(cqe->ft_metadata)); } static inline bool mlx5e_ipsec_is_tx_flow(struct mlx5e_accel_tx_ipsec_state *ipsec_st) 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 ccaccb9fc2f7..6a1d82503ef8 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 @@ -188,7 +188,7 @@ static int post_rx_param_wqes(struct mlx5e_channel *c, err = 0; sq = &c->async_icosq; - spin_lock(&c->async_icosq_lock); + spin_lock_bh(&c->async_icosq_lock); cseg = post_static_params(sq, priv_rx); if (IS_ERR(cseg)) @@ -199,7 +199,7 @@ static int post_rx_param_wqes(struct mlx5e_channel *c, mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, cseg); unlock: - spin_unlock(&c->async_icosq_lock); + spin_unlock_bh(&c->async_icosq_lock); return err; @@ -265,10 +265,10 @@ resync_post_get_progress_params(struct mlx5e_icosq *sq, BUILD_BUG_ON(MLX5E_KTLS_GET_PROGRESS_WQEBBS != 1); - spin_lock(&sq->channel->async_icosq_lock); + spin_lock_bh(&sq->channel->async_icosq_lock); if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, 1))) { - spin_unlock(&sq->channel->async_icosq_lock); + spin_unlock_bh(&sq->channel->async_icosq_lock); err = -ENOSPC; goto err_dma_unmap; } @@ -299,7 +299,7 @@ resync_post_get_progress_params(struct mlx5e_icosq *sq, icosq_fill_wi(sq, pi, &wi); sq->pc++; mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, cseg); - spin_unlock(&sq->channel->async_icosq_lock); + spin_unlock_bh(&sq->channel->async_icosq_lock); return 0; @@ -360,7 +360,7 @@ static int resync_handle_seq_match(struct mlx5e_ktls_offload_context_rx *priv_rx err = 0; sq = &c->async_icosq; - spin_lock(&c->async_icosq_lock); + spin_lock_bh(&c->async_icosq_lock); cseg = post_static_params(sq, priv_rx); if (IS_ERR(cseg)) { @@ -372,7 +372,7 @@ static int resync_handle_seq_match(struct mlx5e_ktls_offload_context_rx *priv_rx mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, cseg); priv_rx->stats->tls_resync_res_ok++; unlock: - spin_unlock(&c->async_icosq_lock); + spin_unlock_bh(&c->async_icosq_lock); return err; } @@ -476,19 +476,22 @@ static void resync_update_sn(struct mlx5e_rq *rq, struct sk_buff *skb) depth += sizeof(struct tcphdr); - if (unlikely(!sk || sk->sk_state == TCP_TIME_WAIT)) + if (unlikely(!sk)) return; - if (unlikely(!resync_queue_get_psv(sk))) - return; + if (unlikely(sk->sk_state == TCP_TIME_WAIT)) + goto unref; - skb->sk = sk; - skb->destructor = sock_edemux; + if (unlikely(!resync_queue_get_psv(sk))) + goto unref; seq = th->seq; datalen = skb->len - depth; tls_offload_rx_resync_async_request_start(sk, seq, datalen); rq->stats->tls_resync_req_start++; + +unref: + sock_gen_put(sk); } void mlx5e_ktls_rx_resync(struct net_device *netdev, struct sock *sk, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index b3f02aac7f26..ebce97921e03 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -5253,6 +5253,7 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv) mlx5e_disable_async_events(priv); mlx5_lag_remove(mdev); + mlx5_vxlan_reset_to_default(mdev->vxlan); } int mlx5e_update_nic_rx(struct mlx5e_priv *priv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h index 9020d1419bcf..8932c387d46a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h @@ -186,7 +186,7 @@ struct mlx5e_encap_entry { unsigned char h_dest[ETH_ALEN]; /* destination eth addr */ struct net_device *out_dev; - struct net_device *route_dev; + int route_dev_ifindex; struct mlx5e_tc_tunnel *tunnel; int reformat_type; u8 flags; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 599f5b5ebc97..6628a0197b4e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -1584,7 +1584,7 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) } while ((++work_done < budget) && (cqe = mlx5_cqwq_get_cqe(cqwq))); out: - if (rq->xdp_prog) + if (rcu_access_pointer(rq->xdp_prog)) mlx5e_xdp_rx_poll_complete(rq); mlx5_cqwq_update_db_record(cqwq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index e3a968e9e2a0..ce710f22b1ff 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -4658,6 +4658,7 @@ __mlx5e_add_fdb_flow(struct mlx5e_priv *priv, return flow; err_free: + dealloc_mod_hdr_actions(&parse_attr->mod_hdr_acts); mlx5e_flow_put(priv, flow); out: return ERR_PTR(err); @@ -4802,6 +4803,7 @@ mlx5e_add_nic_flow(struct mlx5e_priv *priv, return 0; err_free: + dealloc_mod_hdr_actions(&parse_attr->mod_hdr_acts); mlx5e_flow_put(priv, flow); out: return err; @@ -5227,8 +5229,10 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv) tc->ct = mlx5_tc_ct_init(priv, tc->chains, &priv->fs.tc.mod_hdr, MLX5_FLOW_NAMESPACE_KERNEL); - if (IS_ERR(tc->ct)) + if (IS_ERR(tc->ct)) { + err = PTR_ERR(tc->ct); goto err_ct; + } tc->netdevice_nb.notifier_call = mlx5e_tc_netdev_event; err = register_netdevice_notifier_dev_net(priv->netdev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h index 3b979008143d..4a2ce241522e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h @@ -283,6 +283,9 @@ static inline bool mlx5e_cqe_regb_chain(struct mlx5_cqe64 *cqe) reg_b = be32_to_cpu(cqe->ft_metadata); + if (reg_b >> (MLX5E_TC_TABLE_CHAIN_TAG_BITS + ZONE_RESTORE_BITS)) + return false; + chain = reg_b & MLX5E_TC_TABLE_CHAIN_TAG_MASK; if (chain) return true; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 82b4419af9d4..6dd3ea3cbbed 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -144,7 +144,9 @@ static inline void mlx5e_insert_vlan(void *start, struct sk_buff *skb, u16 ihs) memcpy(&vhdr->h_vlan_encapsulated_proto, skb->data + cpy1_sz, cpy2_sz); } -/* RM 2311217: no L4 inner checksum for IPsec tunnel type packet */ +/* If packet is not IP's CHECKSUM_PARTIAL (e.g. icmd packet), + * need to set L3 checksum flag for IPsec + */ static void ipsec_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg) @@ -154,7 +156,6 @@ ipsec_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, eseg->cs_flags |= MLX5_ETH_WQE_L3_INNER_CSUM; sq->stats->csum_partial_inner++; } else { - eseg->cs_flags |= MLX5_ETH_WQE_L4_CSUM; sq->stats->csum_partial++; } } @@ -162,11 +163,6 @@ ipsec_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, static inline void mlx5e_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg) { - if (unlikely(eseg->flow_table_metadata & cpu_to_be32(MLX5_ETH_WQE_FT_META_IPSEC))) { - ipsec_txwqe_build_eseg_csum(sq, skb, eseg); - return; - } - if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) { eseg->cs_flags = MLX5_ETH_WQE_L3_CSUM; if (skb->encapsulation) { @@ -177,6 +173,9 @@ mlx5e_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, struct eseg->cs_flags |= MLX5_ETH_WQE_L4_CSUM; sq->stats->csum_partial++; } + } else if (unlikely(eseg->flow_table_metadata & cpu_to_be32(MLX5_ETH_WQE_FT_META_IPSEC))) { + ipsec_txwqe_build_eseg_csum(sq, skb, eseg); + } else sq->stats->csum_none++; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 6e6a9a563992..d4ee0a9c03db 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1142,6 +1142,10 @@ int mlx5_esw_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num, struct mlx5_vport *vport; vport = mlx5_eswitch_get_vport(esw, vport_num); + + if (!vport->qos.enabled) + return -EOPNOTSUPP; + MLX5_SET(scheduling_context, ctx, max_average_bw, rate_mbps); return mlx5_modify_scheduling_element_cmd(esw->dev, @@ -1408,6 +1412,7 @@ static void mlx5_eswitch_clear_vf_vports_info(struct mlx5_eswitch *esw) int i; mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs) { + memset(&vport->qos, 0, sizeof(vport->qos)); memset(&vport->info, 0, sizeof(vport->info)); vport->info.link_state = MLX5_VPORT_ADMIN_STATE_AUTO; } @@ -1902,8 +1907,6 @@ int mlx5_devlink_port_function_hw_addr_get(struct devlink *devlink, ether_addr_copy(hw_addr, vport->info.mac); *hw_addr_len = ETH_ALEN; err = 0; - } else { - NL_SET_ERR_MSG_MOD(extack, "Eswitch vport is disabled"); } mutex_unlock(&esw->state_lock); return err; @@ -2223,12 +2226,15 @@ static u32 calculate_vports_min_rate_divider(struct mlx5_eswitch *esw) max_guarantee = evport->info.min_rate; } - return max_t(u32, max_guarantee / fw_max_bw_share, 1); + if (max_guarantee) + return max_t(u32, max_guarantee / fw_max_bw_share, 1); + return 0; } -static int normalize_vports_min_rate(struct mlx5_eswitch *esw, u32 divider) +static int normalize_vports_min_rate(struct mlx5_eswitch *esw) { u32 fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share); + u32 divider = calculate_vports_min_rate_divider(esw); struct mlx5_vport *evport; u32 vport_max_rate; u32 vport_min_rate; @@ -2241,9 +2247,9 @@ static int normalize_vports_min_rate(struct mlx5_eswitch *esw, u32 divider) continue; vport_min_rate = evport->info.min_rate; vport_max_rate = evport->info.max_rate; - bw_share = MLX5_MIN_BW_SHARE; + bw_share = 0; - if (vport_min_rate) + if (divider) bw_share = MLX5_RATE_TO_BW_SHARE(vport_min_rate, divider, fw_max_bw_share); @@ -2268,7 +2274,6 @@ int mlx5_eswitch_set_vport_rate(struct mlx5_eswitch *esw, u16 vport, struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport); u32 fw_max_bw_share; u32 previous_min_rate; - u32 divider; bool min_rate_supported; bool max_rate_supported; int err = 0; @@ -2293,8 +2298,7 @@ int mlx5_eswitch_set_vport_rate(struct mlx5_eswitch *esw, u16 vport, previous_min_rate = evport->info.min_rate; evport->info.min_rate = min_rate; - divider = calculate_vports_min_rate_divider(esw); - err = normalize_vports_min_rate(esw, divider); + err = normalize_vports_min_rate(esw); if (err) { evport->info.min_rate = previous_min_rate; goto unlock; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 16091838bfcf..9fdd99272e31 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -534,6 +534,13 @@ static void del_sw_hw_rule(struct fs_node *node) goto out; } + if (rule->dest_attr.type == MLX5_FLOW_DESTINATION_TYPE_PORT && + --fte->dests_size) { + fte->modify_mask |= BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION); + fte->action.action &= ~MLX5_FLOW_CONTEXT_ACTION_ALLOW; + goto out; + } + if ((fte->action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) && --fte->dests_size) { fte->modify_mask |= @@ -2010,10 +2017,11 @@ void mlx5_del_flow_rules(struct mlx5_flow_handle *handle) down_write_ref_node(&fte->node, false); for (i = handle->num_rules - 1; i >= 0; i--) tree_remove_node(&handle->rule[i]->node, true); - if (fte->modify_mask && fte->dests_size) { - modify_fte(fte); + if (fte->dests_size) { + if (fte->modify_mask) + modify_fte(fte); up_write_ref_node(&fte->node, false); - } else { + } else if (list_empty(&fte->node.children)) { del_hw_fte(&fte->node); /* Avoid double call to del_hw_fte */ fte->node.del_hw_func = NULL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c index 3315afe2f8dc..38084400ee8f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c @@ -168,6 +168,17 @@ struct mlx5_vxlan *mlx5_vxlan_create(struct mlx5_core_dev *mdev) void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan) { + if (!mlx5_vxlan_allowed(vxlan)) + return; + + mlx5_vxlan_del_port(vxlan, IANA_VXLAN_UDP_PORT); + WARN_ON(!hash_empty(vxlan->htable)); + + kfree(vxlan); +} + +void mlx5_vxlan_reset_to_default(struct mlx5_vxlan *vxlan) +{ struct mlx5_vxlan_port *vxlanp; struct hlist_node *tmp; int bkt; @@ -175,12 +186,12 @@ void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan) if (!mlx5_vxlan_allowed(vxlan)) return; - /* Lockless since we are the only hash table consumers*/ hash_for_each_safe(vxlan->htable, bkt, tmp, vxlanp, hlist) { - hash_del(&vxlanp->hlist); - mlx5_vxlan_core_del_port_cmd(vxlan->mdev, vxlanp->udp_port); - kfree(vxlanp); + /* Don't delete default UDP port added by the HW. + * Remove only user configured ports + */ + if (vxlanp->udp_port == IANA_VXLAN_UDP_PORT) + continue; + mlx5_vxlan_del_port(vxlan, vxlanp->udp_port); } - - kfree(vxlan); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h index ec766529f49b..34ef662da35e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h @@ -56,6 +56,7 @@ void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan); int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port); int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port); bool mlx5_vxlan_lookup_port(struct mlx5_vxlan *vxlan, u16 port); +void mlx5_vxlan_reset_to_default(struct mlx5_vxlan *vxlan); #else static inline struct mlx5_vxlan* mlx5_vxlan_create(struct mlx5_core_dev *mdev) { return ERR_PTR(-EOPNOTSUPP); } @@ -63,6 +64,7 @@ static inline void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan) { return; } static inline int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port) { return -EOPNOTSUPP; } static inline int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port) { return -EOPNOTSUPP; } static inline bool mlx5_vxlan_lookup_port(struct mlx5_vxlan *vxlan, u16 port) { return false; } +static inline void mlx5_vxlan_reset_to_default(struct mlx5_vxlan *vxlan) { return; } #endif #endif /* __MLX5_VXLAN_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlxsw/Kconfig b/drivers/net/ethernet/mellanox/mlxsw/Kconfig index 872e9910bb7c..a619d90559f7 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/Kconfig +++ b/drivers/net/ethernet/mellanox/mlxsw/Kconfig @@ -6,6 +6,7 @@ config MLXSW_CORE tristate "Mellanox Technologies Switch ASICs support" select NET_DEVLINK + select MLXFW help This driver supports Mellanox Technologies Switch ASICs family. @@ -82,7 +83,6 @@ config MLXSW_SPECTRUM select GENERIC_ALLOCATOR select PARMAN select OBJAGG - select MLXFW imply PTP_1588_CLOCK select NET_PTP_CLASSIFY if PTP_1588_CLOCK default m diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 937b8e46f8c7..1a86535c4968 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -571,7 +571,8 @@ static void mlxsw_emad_trans_timeout_schedule(struct mlxsw_reg_trans *trans) if (trans->core->fw_flash_in_progress) timeout = msecs_to_jiffies(MLXSW_EMAD_TIMEOUT_DURING_FW_FLASH_MS); - queue_delayed_work(trans->core->emad_wq, &trans->timeout_dw, timeout); + queue_delayed_work(trans->core->emad_wq, &trans->timeout_dw, + timeout << trans->retries); } static int mlxsw_emad_transmit(struct mlxsw_core *mlxsw_core, diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index a1938842f828..b319c22c211c 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -148,7 +148,8 @@ static void lan743x_intr_software_isr(void *context) int_sts = lan743x_csr_read(adapter, INT_STS); if (int_sts & INT_BIT_SW_GP_) { - lan743x_csr_write(adapter, INT_STS, INT_BIT_SW_GP_); + /* disable the interrupt to prevent repeated re-triggering */ + lan743x_csr_write(adapter, INT_EN_CLR, INT_BIT_SW_GP_); intr->software_isr_flag = 1; } } @@ -674,14 +675,12 @@ clean_up: static int lan743x_dp_write(struct lan743x_adapter *adapter, u32 select, u32 addr, u32 length, u32 *buf) { - int ret = -EIO; u32 dp_sel; int i; - mutex_lock(&adapter->dp_lock); if (lan743x_csr_wait_for_bit(adapter, DP_SEL, DP_SEL_DPRDY_, 1, 40, 100, 100)) - goto unlock; + return -EIO; dp_sel = lan743x_csr_read(adapter, DP_SEL); dp_sel &= ~DP_SEL_MASK_; dp_sel |= select; @@ -693,13 +692,10 @@ static int lan743x_dp_write(struct lan743x_adapter *adapter, lan743x_csr_write(adapter, DP_CMD, DP_CMD_WRITE_); if (lan743x_csr_wait_for_bit(adapter, DP_SEL, DP_SEL_DPRDY_, 1, 40, 100, 100)) - goto unlock; + return -EIO; } - ret = 0; -unlock: - mutex_unlock(&adapter->dp_lock); - return ret; + return 0; } static u32 lan743x_mac_mii_access(u16 id, u16 index, int read) @@ -1019,16 +1015,16 @@ static void lan743x_phy_close(struct lan743x_adapter *adapter) static int lan743x_phy_open(struct lan743x_adapter *adapter) { struct lan743x_phy *phy = &adapter->phy; + struct phy_device *phydev = NULL; struct device_node *phynode; - struct phy_device *phydev; struct net_device *netdev; int ret = -EIO; netdev = adapter->netdev; phynode = of_node_get(adapter->pdev->dev.of_node); - adapter->phy_mode = PHY_INTERFACE_MODE_GMII; if (phynode) { + /* try devicetree phy, or fixed link */ of_get_phy_mode(phynode, &adapter->phy_mode); if (of_phy_is_fixed_link(phynode)) { @@ -1044,13 +1040,15 @@ static int lan743x_phy_open(struct lan743x_adapter *adapter) lan743x_phy_link_status_change, 0, adapter->phy_mode); of_node_put(phynode); - if (!phydev) - goto return_error; - } else { + } + + if (!phydev) { + /* try internal phy */ phydev = phy_find_first(adapter->mdiobus); if (!phydev) goto return_error; + adapter->phy_mode = PHY_INTERFACE_MODE_GMII; ret = phy_connect_direct(netdev, phydev, lan743x_phy_link_status_change, adapter->phy_mode); @@ -1310,13 +1308,13 @@ clean_up_data_descriptor: goto clear_active; if (!(buffer_info->flags & TX_BUFFER_INFO_FLAG_TIMESTAMP_REQUESTED)) { - dev_kfree_skb(buffer_info->skb); + dev_kfree_skb_any(buffer_info->skb); goto clear_skb; } if (cleanup) { lan743x_ptp_unrequest_tx_timestamp(tx->adapter); - dev_kfree_skb(buffer_info->skb); + dev_kfree_skb_any(buffer_info->skb); } else { ignore_sync = (buffer_info->flags & TX_BUFFER_INFO_FLAG_IGNORE_SYNC) != 0; @@ -1626,7 +1624,7 @@ static netdev_tx_t lan743x_tx_xmit_frame(struct lan743x_tx *tx, if (required_number_of_descriptors > lan743x_tx_get_avail_desc(tx)) { if (required_number_of_descriptors > (tx->ring_size - 1)) { - dev_kfree_skb(skb); + dev_kfree_skb_irq(skb); } else { /* save to overflow buffer */ tx->overflow_skb = skb; @@ -1659,7 +1657,7 @@ static netdev_tx_t lan743x_tx_xmit_frame(struct lan743x_tx *tx, start_frame_length, do_timestamp, skb->ip_summed == CHECKSUM_PARTIAL)) { - dev_kfree_skb(skb); + dev_kfree_skb_irq(skb); goto unlock; } @@ -1678,7 +1676,7 @@ static netdev_tx_t lan743x_tx_xmit_frame(struct lan743x_tx *tx, * frame assembler clean up was performed inside * lan743x_tx_frame_add_fragment */ - dev_kfree_skb(skb); + dev_kfree_skb_irq(skb); goto unlock; } } @@ -2733,7 +2731,6 @@ static int lan743x_hardware_init(struct lan743x_adapter *adapter, adapter->intr.irq = adapter->pdev->irq; lan743x_csr_write(adapter, INT_EN_CLR, 0xFFFFFFFF); - mutex_init(&adapter->dp_lock); ret = lan743x_gpio_init(adapter); if (ret) diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h index c61a40411317..a536f4a4994d 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.h +++ b/drivers/net/ethernet/microchip/lan743x_main.h @@ -712,9 +712,6 @@ struct lan743x_adapter { struct lan743x_csr csr; struct lan743x_intr intr; - /* lock, used to prevent concurrent access to data port */ - struct mutex dp_lock; - struct lan743x_gpio gpio; struct lan743x_ptp ptp; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c index ed9808fc743b..35c72d4a78b3 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c @@ -126,6 +126,11 @@ static int ionic_get_link_ksettings(struct net_device *netdev, ethtool_link_ksettings_zero_link_mode(ks, supported); + if (!idev->port_info) { + netdev_err(netdev, "port_info not initialized\n"); + return -EOPNOTSUPP; + } + /* The port_info data is found in a DMA space that the NIC keeps * up-to-date, so there's no need to request the data from the * NIC, we already have it in our memory space. diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c index 0e4cd8890cff..0a22f8ce9a2c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c +++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c @@ -1647,9 +1647,9 @@ static void qed_src_init_pf(struct qed_hwfn *p_hwfn) ilog2(rounded_conn_num)); STORE_RT_REG_AGG(p_hwfn, SRC_REG_FIRSTFREE_RT_OFFSET, - p_hwfn->p_cxt_mngr->first_free); + p_hwfn->p_cxt_mngr->src_t2.first_free); STORE_RT_REG_AGG(p_hwfn, SRC_REG_LASTFREE_RT_OFFSET, - p_hwfn->p_cxt_mngr->last_free); + p_hwfn->p_cxt_mngr->src_t2.last_free); } /* Timers PF */ diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.h b/drivers/net/ethernet/qlogic/qed/qed_cxt.h index 8b64495f8745..056e79620a0e 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_cxt.h +++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.h @@ -326,9 +326,6 @@ struct qed_cxt_mngr { /* SRC T2 */ struct qed_src_t2 src_t2; - u32 t2_num_pages; - u64 first_free; - u64 last_free; /* total number of SRQ's for this hwfn */ u32 srq_count; diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c index 512cbef24097..a99861124630 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c @@ -2754,14 +2754,18 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn, iwarp_info->partial_fpdus = kcalloc((u16)p_hwfn->p_rdma_info->num_qps, sizeof(*iwarp_info->partial_fpdus), GFP_KERNEL); - if (!iwarp_info->partial_fpdus) + if (!iwarp_info->partial_fpdus) { + rc = -ENOMEM; goto err; + } iwarp_info->max_num_partial_fpdus = (u16)p_hwfn->p_rdma_info->num_qps; iwarp_info->mpa_intermediate_buf = kzalloc(buff_size, GFP_KERNEL); - if (!iwarp_info->mpa_intermediate_buf) + if (!iwarp_info->mpa_intermediate_buf) { + rc = -ENOMEM; goto err; + } /* The mpa_bufs array serves for pending RX packets received on the * mpa ll2 that don't have place on the tx ring and require later @@ -2771,8 +2775,10 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn, iwarp_info->mpa_bufs = kcalloc(data.input.rx_num_desc, sizeof(*iwarp_info->mpa_bufs), GFP_KERNEL); - if (!iwarp_info->mpa_bufs) + if (!iwarp_info->mpa_bufs) { + rc = -ENOMEM; goto err; + } INIT_LIST_HEAD(&iwarp_info->mpa_buf_pending_list); INIT_LIST_HEAD(&iwarp_info->mpa_buf_list); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c index b8af59fc1aa4..d2c190732d3e 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c @@ -2231,7 +2231,8 @@ static int qlcnic_83xx_restart_hw(struct qlcnic_adapter *adapter) /* Boot either flash image or firmware image from host file system */ if (qlcnic_load_fw_file == 1) { - if (qlcnic_83xx_load_fw_image_from_host(adapter)) + err = qlcnic_83xx_load_fw_image_from_host(adapter); + if (err) return err; } else { QLC_SHARED_REG_WR32(adapter, QLCNIC_FW_IMG_VALID, diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c index 29a7bfa2584d..3d7d3ab383f8 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c @@ -188,6 +188,11 @@ rx_handler_result_t rmnet_rx_handler(struct sk_buff **pskb) dev = skb->dev; port = rmnet_get_port_rcu(dev); + if (unlikely(!port)) { + atomic_long_inc(&skb->dev->rx_nohandler); + kfree_skb(skb); + goto done; + } switch (port->rmnet_mode) { case RMNET_EPMODE_VND: diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 00f13805c6f7..85d9c3e30c69 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -4080,9 +4080,17 @@ err_out: return -EIO; } -static bool rtl_test_hw_pad_bug(struct rtl8169_private *tp, struct sk_buff *skb) +static bool rtl_test_hw_pad_bug(struct rtl8169_private *tp) { - return skb->len < ETH_ZLEN && tp->mac_version == RTL_GIGA_MAC_VER_34; + switch (tp->mac_version) { + case RTL_GIGA_MAC_VER_34: + case RTL_GIGA_MAC_VER_60: + case RTL_GIGA_MAC_VER_61: + case RTL_GIGA_MAC_VER_63: + return true; + default: + return false; + } } static void rtl8169_tso_csum_v1(struct sk_buff *skb, u32 *opts) @@ -4154,8 +4162,9 @@ static bool rtl8169_tso_csum_v2(struct rtl8169_private *tp, opts[1] |= transport_offset << TCPHO_SHIFT; } else { - if (unlikely(rtl_test_hw_pad_bug(tp, skb))) - return !eth_skb_pad(skb); + if (unlikely(skb->len < ETH_ZLEN && rtl_test_hw_pad_bug(tp))) + /* eth_skb_pad would free the skb on error */ + return !__skb_put_padto(skb, ETH_ZLEN, false); } return true; @@ -4334,18 +4343,9 @@ static netdev_features_t rtl8169_features_check(struct sk_buff *skb, rtl_chip_supports_csum_v2(tp)) features &= ~NETIF_F_ALL_TSO; } else if (skb->ip_summed == CHECKSUM_PARTIAL) { - if (skb->len < ETH_ZLEN) { - switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_11: - case RTL_GIGA_MAC_VER_12: - case RTL_GIGA_MAC_VER_17: - case RTL_GIGA_MAC_VER_34: - features &= ~NETIF_F_CSUM_MASK; - break; - default: - break; - } - } + /* work around hw bug on some chip versions */ + if (skb->len < ETH_ZLEN) + features &= ~NETIF_F_CSUM_MASK; if (transport_offset > TCPHO_MAX && rtl_chip_supports_csum_v2(tp)) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c index f61cb997a8f6..82b1c7a5a7a9 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c @@ -113,8 +113,10 @@ static int intel_eth_plat_probe(struct platform_device *pdev) /* Enable TX clock */ if (dwmac->data->tx_clk_en) { dwmac->tx_clk = devm_clk_get(&pdev->dev, "tx_clk"); - if (IS_ERR(dwmac->tx_clk)) + if (IS_ERR(dwmac->tx_clk)) { + ret = PTR_ERR(dwmac->tx_clk); goto err_remove_config_dt; + } clk_prepare_enable(dwmac->tx_clk); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c index b6e5e3e36b63..81ee0a071b4e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c @@ -625,13 +625,6 @@ static int intel_eth_pci_probe(struct pci_dev *pdev, if (ret) return ret; - if (plat->eee_usecs_rate > 0) { - u32 tx_lpi_usec; - - tx_lpi_usec = (plat->eee_usecs_rate / 1000000) - 1; - writel(tx_lpi_usec, res.addr + GMAC_1US_TIC_COUNTER); - } - ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES); if (ret < 0) return ret; @@ -641,6 +634,13 @@ static int intel_eth_pci_probe(struct pci_dev *pdev, res.wol_irq = pci_irq_vector(pdev, 0); res.irq = pci_irq_vector(pdev, 0); + if (plat->eee_usecs_rate > 0) { + u32 tx_lpi_usec; + + tx_lpi_usec = (plat->eee_usecs_rate / 1000000) - 1; + writel(tx_lpi_usec, res.addr + GMAC_1US_TIC_COUNTER); + } + ret = stmmac_dvr_probe(&pdev->dev, plat, &res); if (ret) { pci_free_irq_vectors(pdev); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c index cb87d31a99df..57a53a600aa5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c @@ -23,7 +23,7 @@ int dwmac_dma_reset(void __iomem *ioaddr) return readl_poll_timeout(ioaddr + DMA_BUS_MODE, value, !(value & DMA_BUS_MODE_SFT_RESET), - 10000, 100000); + 10000, 200000); } /* CSR1 enables the transmit DMA to check for new descriptor */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 220626a8d499..ba45fe237512 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -4757,6 +4757,7 @@ static void stmmac_napi_add(struct net_device *dev) ch->priv_data = priv; ch->index = queue; + spin_lock_init(&ch->lock); if (queue < priv->plat->rx_queues_to_use) { netif_napi_add(dev, &ch->rx_napi, stmmac_napi_poll_rx, @@ -5246,6 +5247,7 @@ int stmmac_resume(struct device *dev) return ret; } + rtnl_lock(); mutex_lock(&priv->lock); stmmac_reset_queues_param(priv); @@ -5261,6 +5263,7 @@ int stmmac_resume(struct device *dev) stmmac_enable_all_queues(priv); mutex_unlock(&priv->lock); + rtnl_unlock(); if (!device_may_wakeup(priv->device) || !priv->plat->pmt) { rtnl_lock(); diff --git a/drivers/net/ethernet/ti/am65-cpts.c b/drivers/net/ethernet/ti/am65-cpts.c index 75056c14b161..5dc60ecabe56 100644 --- a/drivers/net/ethernet/ti/am65-cpts.c +++ b/drivers/net/ethernet/ti/am65-cpts.c @@ -1001,8 +1001,7 @@ struct am65_cpts *am65_cpts_create(struct device *dev, void __iomem *regs, if (IS_ERR_OR_NULL(cpts->ptp_clock)) { dev_err(dev, "Failed to register ptp clk %ld\n", PTR_ERR(cpts->ptp_clock)); - if (!cpts->ptp_clock) - ret = -ENODEV; + ret = cpts->ptp_clock ? PTR_ERR(cpts->ptp_clock) : -ENODEV; goto refclk_disable; } cpts->phc_index = ptp_clock_index(cpts->ptp_clock); diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 9fd1f77190ad..b0f00b4edd94 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -838,9 +838,12 @@ static int cpsw_ndo_open(struct net_device *ndev) if (ret < 0) goto err_cleanup; - if (cpts_register(cpsw->cpts)) - dev_err(priv->dev, "error registering cpts device\n"); - + if (cpsw->cpts) { + if (cpts_register(cpsw->cpts)) + dev_err(priv->dev, "error registering cpts device\n"); + else + writel(0x10, &cpsw->wr_regs->misc_en); + } } cpsw_restore(priv); @@ -1631,6 +1634,7 @@ static int cpsw_probe(struct platform_device *pdev) CPSW_MAX_QUEUES, CPSW_MAX_QUEUES); if (!ndev) { dev_err(dev, "error allocating net_device\n"); + ret = -ENOMEM; goto clean_cpts; } @@ -1716,7 +1720,6 @@ static int cpsw_probe(struct platform_device *pdev) /* Enable misc CPTS evnt_pend IRQ */ cpts_set_irqpoll(cpsw->cpts, false); - writel(0x10, &cpsw->wr_regs->misc_en); skip_cpts: cpsw_notice(priv, probe, diff --git a/drivers/net/ethernet/ti/cpsw_ethtool.c b/drivers/net/ethernet/ti/cpsw_ethtool.c index 4d02c5135611..4619c3a950b0 100644 --- a/drivers/net/ethernet/ti/cpsw_ethtool.c +++ b/drivers/net/ethernet/ti/cpsw_ethtool.c @@ -728,7 +728,6 @@ int cpsw_get_ts_info(struct net_device *ndev, struct ethtool_ts_info *info) (1 << HWTSTAMP_TX_ON); info->rx_filters = (1 << HWTSTAMP_FILTER_NONE) | - (1 << HWTSTAMP_FILTER_PTP_V1_L4_EVENT) | (1 << HWTSTAMP_FILTER_PTP_V2_EVENT); return 0; } diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index f779d2e1b5c5..2f5e0ad23ad7 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -873,8 +873,12 @@ static int cpsw_ndo_open(struct net_device *ndev) if (ret < 0) goto err_cleanup; - if (cpts_register(cpsw->cpts)) - dev_err(priv->dev, "error registering cpts device\n"); + if (cpsw->cpts) { + if (cpts_register(cpsw->cpts)) + dev_err(priv->dev, "error registering cpts device\n"); + else + writel(0x10, &cpsw->wr_regs->misc_en); + } napi_enable(&cpsw->napi_rx); napi_enable(&cpsw->napi_tx); @@ -2006,7 +2010,6 @@ static int cpsw_probe(struct platform_device *pdev) /* Enable misc CPTS evnt_pend IRQ */ cpts_set_irqpoll(cpsw->cpts, false); - writel(0x10, &cpsw->wr_regs->misc_en); skip_cpts: ret = cpsw_register_notifiers(cpsw); diff --git a/drivers/net/ethernet/ti/cpsw_priv.c b/drivers/net/ethernet/ti/cpsw_priv.c index 51cc29f39038..31c5e36ff706 100644 --- a/drivers/net/ethernet/ti/cpsw_priv.c +++ b/drivers/net/ethernet/ti/cpsw_priv.c @@ -639,13 +639,10 @@ static int cpsw_hwtstamp_set(struct net_device *dev, struct ifreq *ifr) break; case HWTSTAMP_FILTER_ALL: case HWTSTAMP_FILTER_NTP_ALL: - return -ERANGE; case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: - priv->rx_ts_enabled = HWTSTAMP_FILTER_PTP_V1_L4_EVENT; - cfg.rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT; - break; + return -ERANGE; case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index d07008a818df..1426bfc009bc 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -224,8 +224,7 @@ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs, if (ip_tunnel_collect_metadata() || gs->collect_md) { __be16 flags; - flags = TUNNEL_KEY | TUNNEL_GENEVE_OPT | - (gnvh->oam ? TUNNEL_OAM : 0) | + flags = TUNNEL_KEY | (gnvh->oam ? TUNNEL_OAM : 0) | (gnvh->critical ? TUNNEL_CRIT_OPT : 0); tun_dst = udp_tun_rx_dst(skb, geneve_get_sk_family(gs), flags, diff --git a/drivers/net/ipa/gsi_trans.c b/drivers/net/ipa/gsi_trans.c index 92642030e735..e8599bb948c0 100644 --- a/drivers/net/ipa/gsi_trans.c +++ b/drivers/net/ipa/gsi_trans.c @@ -362,22 +362,31 @@ struct gsi_trans *gsi_channel_trans_alloc(struct gsi *gsi, u32 channel_id, return trans; } -/* Free a previously-allocated transaction (used only in case of error) */ +/* Free a previously-allocated transaction */ void gsi_trans_free(struct gsi_trans *trans) { + refcount_t *refcount = &trans->refcount; struct gsi_trans_info *trans_info; + bool last; - if (!refcount_dec_and_test(&trans->refcount)) + /* We must hold the lock to release the last reference */ + if (refcount_dec_not_one(refcount)) return; trans_info = &trans->gsi->channel[trans->channel_id].trans_info; spin_lock_bh(&trans_info->spinlock); - list_del(&trans->links); + /* Reference might have been added before we got the lock */ + last = refcount_dec_and_test(refcount); + if (last) + list_del(&trans->links); spin_unlock_bh(&trans_info->spinlock); + if (!last) + return; + ipa_gsi_trans_release(trans); /* Releasing the reserved TREs implicitly frees the sgl[] and diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index d07061417675..e7972e88ffe0 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -96,6 +96,7 @@ static const struct file_operations nsim_dev_take_snapshot_fops = { .open = simple_open, .write = nsim_dev_take_snapshot_write, .llseek = generic_file_llseek, + .owner = THIS_MODULE, }; static ssize_t nsim_dev_trap_fa_cookie_read(struct file *file, @@ -188,6 +189,7 @@ static const struct file_operations nsim_dev_trap_fa_cookie_fops = { .read = nsim_dev_trap_fa_cookie_read, .write = nsim_dev_trap_fa_cookie_write, .llseek = generic_file_llseek, + .owner = THIS_MODULE, }; static int nsim_dev_debugfs_init(struct nsim_dev *nsim_dev) diff --git a/drivers/net/netdevsim/health.c b/drivers/net/netdevsim/health.c index 62958b238d50..21e2974660e7 100644 --- a/drivers/net/netdevsim/health.c +++ b/drivers/net/netdevsim/health.c @@ -261,6 +261,7 @@ static const struct file_operations nsim_dev_health_break_fops = { .open = simple_open, .write = nsim_dev_health_break_write, .llseek = generic_file_llseek, + .owner = THIS_MODULE, }; int nsim_dev_health_init(struct nsim_dev *nsim_dev, struct devlink *devlink) diff --git a/drivers/net/netdevsim/udp_tunnels.c b/drivers/net/netdevsim/udp_tunnels.c index 6ab023acefd6..02dc3123eb6c 100644 --- a/drivers/net/netdevsim/udp_tunnels.c +++ b/drivers/net/netdevsim/udp_tunnels.c @@ -124,6 +124,7 @@ static const struct file_operations nsim_udp_tunnels_info_reset_fops = { .open = simple_open, .write = nsim_udp_tunnels_info_reset_write, .llseek = generic_file_llseek, + .owner = THIS_MODULE, }; int nsim_udp_tunnels_info_create(struct nsim_dev *nsim_dev, diff --git a/drivers/net/phy/mscc/mscc_macsec.c b/drivers/net/phy/mscc/mscc_macsec.c index 6cf9b798b710..10be266e48e8 100644 --- a/drivers/net/phy/mscc/mscc_macsec.c +++ b/drivers/net/phy/mscc/mscc_macsec.c @@ -981,7 +981,6 @@ int vsc8584_macsec_init(struct phy_device *phydev) switch (phydev->phy_id & phydev->drv->phy_id_mask) { case PHY_ID_VSC856X: - case PHY_ID_VSC8575: case PHY_ID_VSC8582: case PHY_ID_VSC8584: INIT_LIST_HEAD(&vsc8531->macsec_flows); diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index fb1db713b7fb..575580d3ffe0 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -551,6 +551,8 @@ static struct phy_driver realtek_drvs[] = { { PHY_ID_MATCH_EXACT(0x00008201), .name = "RTL8201CP Ethernet", + .read_page = rtl821x_read_page, + .write_page = rtl821x_write_page, }, { PHY_ID_MATCH_EXACT(0x001cc816), .name = "RTL8201F Fast Ethernet", diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index 1d18c10e8f82..34aa196b7465 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -2389,7 +2389,8 @@ static int sfp_probe(struct platform_device *pdev) continue; sfp->gpio_irq[i] = gpiod_to_irq(sfp->gpio[i]); - if (!sfp->gpio_irq[i]) { + if (sfp->gpio_irq[i] < 0) { + sfp->gpio_irq[i] = 0; sfp->need_poll = true; continue; } diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c index ec97669be5c2..0fc39ac5ca88 100644 --- a/drivers/net/phy/smsc.c +++ b/drivers/net/phy/smsc.c @@ -291,8 +291,10 @@ static int smsc_phy_probe(struct phy_device *phydev) return ret; ret = clk_set_rate(priv->refclk, 50 * 1000 * 1000); - if (ret) + if (ret) { + clk_disable_unprepare(priv->refclk); return ret; + } return 0; } diff --git a/drivers/net/usb/cx82310_eth.c b/drivers/net/usb/cx82310_eth.c index ca89d8258dd3..c4568a491dc4 100644 --- a/drivers/net/usb/cx82310_eth.c +++ b/drivers/net/usb/cx82310_eth.c @@ -197,7 +197,8 @@ static int cx82310_bind(struct usbnet *dev, struct usb_interface *intf) } /* enable ethernet mode (?) */ - if (cx82310_enable_ethernet(dev)) + ret = cx82310_enable_ethernet(dev); + if (ret) goto err; /* get the MAC address */ diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index a322f51873d0..fc378ff56775 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1070,7 +1070,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x05c6, 0x9011, 4)}, {QMI_FIXED_INTF(0x05c6, 0x9021, 1)}, {QMI_FIXED_INTF(0x05c6, 0x9022, 2)}, - {QMI_FIXED_INTF(0x05c6, 0x9025, 4)}, /* Alcatel-sbell ASB TL131 TDD LTE (China Mobile) */ + {QMI_QUIRK_SET_DTR(0x05c6, 0x9025, 4)}, /* Alcatel-sbell ASB TL131 TDD LTE (China Mobile) */ {QMI_FIXED_INTF(0x05c6, 0x9026, 3)}, {QMI_FIXED_INTF(0x05c6, 0x902e, 5)}, {QMI_FIXED_INTF(0x05c6, 0x9031, 5)}, @@ -1309,6 +1309,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x1bc7, 0x1101, 3)}, /* Telit ME910 dual modem */ {QMI_FIXED_INTF(0x1bc7, 0x1200, 5)}, /* Telit LE920 */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1201, 2)}, /* Telit LE920, LE920A4 */ + {QMI_QUIRK_SET_DTR(0x1bc7, 0x1230, 2)}, /* Telit LE910Cx */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1260, 2)}, /* Telit LE910Cx */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1261, 2)}, /* Telit LE910Cx */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1900, 1)}, /* Telit LN940 series */ diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 60c1aadece89..f2793ffde191 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -608,8 +608,7 @@ static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev) return ret; } -static int vrf_finish_direct(struct net *net, struct sock *sk, - struct sk_buff *skb) +static void vrf_finish_direct(struct sk_buff *skb) { struct net_device *vrf_dev = skb->dev; @@ -628,7 +627,8 @@ static int vrf_finish_direct(struct net *net, struct sock *sk, skb_pull(skb, ETH_HLEN); } - return 1; + /* reset skb device */ + nf_reset_ct(skb); } #if IS_ENABLED(CONFIG_IPV6) @@ -707,15 +707,41 @@ static struct sk_buff *vrf_ip6_out_redirect(struct net_device *vrf_dev, return skb; } +static int vrf_output6_direct_finish(struct net *net, struct sock *sk, + struct sk_buff *skb) +{ + vrf_finish_direct(skb); + + return vrf_ip6_local_out(net, sk, skb); +} + static int vrf_output6_direct(struct net *net, struct sock *sk, struct sk_buff *skb) { + int err = 1; + skb->protocol = htons(ETH_P_IPV6); - return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, - net, sk, skb, NULL, skb->dev, - vrf_finish_direct, - !(IPCB(skb)->flags & IPSKB_REROUTED)); + if (!(IPCB(skb)->flags & IPSKB_REROUTED)) + err = nf_hook(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, sk, skb, + NULL, skb->dev, vrf_output6_direct_finish); + + if (likely(err == 1)) + vrf_finish_direct(skb); + + return err; +} + +static int vrf_ip6_out_direct_finish(struct net *net, struct sock *sk, + struct sk_buff *skb) +{ + int err; + + err = vrf_output6_direct(net, sk, skb); + if (likely(err == 1)) + err = vrf_ip6_local_out(net, sk, skb); + + return err; } static struct sk_buff *vrf_ip6_out_direct(struct net_device *vrf_dev, @@ -728,18 +754,15 @@ static struct sk_buff *vrf_ip6_out_direct(struct net_device *vrf_dev, skb->dev = vrf_dev; err = nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, - skb, NULL, vrf_dev, vrf_output6_direct); + skb, NULL, vrf_dev, vrf_ip6_out_direct_finish); if (likely(err == 1)) err = vrf_output6_direct(net, sk, skb); - /* reset skb device */ if (likely(err == 1)) - nf_reset_ct(skb); - else - skb = NULL; + return skb; - return skb; + return NULL; } static struct sk_buff *vrf_ip6_out(struct net_device *vrf_dev, @@ -919,15 +942,41 @@ static struct sk_buff *vrf_ip_out_redirect(struct net_device *vrf_dev, return skb; } +static int vrf_output_direct_finish(struct net *net, struct sock *sk, + struct sk_buff *skb) +{ + vrf_finish_direct(skb); + + return vrf_ip_local_out(net, sk, skb); +} + static int vrf_output_direct(struct net *net, struct sock *sk, struct sk_buff *skb) { + int err = 1; + skb->protocol = htons(ETH_P_IP); - return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, - net, sk, skb, NULL, skb->dev, - vrf_finish_direct, - !(IPCB(skb)->flags & IPSKB_REROUTED)); + if (!(IPCB(skb)->flags & IPSKB_REROUTED)) + err = nf_hook(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, skb, + NULL, skb->dev, vrf_output_direct_finish); + + if (likely(err == 1)) + vrf_finish_direct(skb); + + return err; +} + +static int vrf_ip_out_direct_finish(struct net *net, struct sock *sk, + struct sk_buff *skb) +{ + int err; + + err = vrf_output_direct(net, sk, skb); + if (likely(err == 1)) + err = vrf_ip_local_out(net, sk, skb); + + return err; } static struct sk_buff *vrf_ip_out_direct(struct net_device *vrf_dev, @@ -940,18 +989,15 @@ static struct sk_buff *vrf_ip_out_direct(struct net_device *vrf_dev, skb->dev = vrf_dev; err = nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk, - skb, NULL, vrf_dev, vrf_output_direct); + skb, NULL, vrf_dev, vrf_ip_out_direct_finish); if (likely(err == 1)) err = vrf_output_direct(net, sk, skb); - /* reset skb device */ if (likely(err == 1)) - nf_reset_ct(skb); - else - skb = NULL; + return skb; - return skb; + return NULL; } static struct sk_buff *vrf_ip_out(struct net_device *vrf_dev, diff --git a/drivers/net/wan/cosa.c b/drivers/net/wan/cosa.c index f8aed0696d77..2369ca250cd6 100644 --- a/drivers/net/wan/cosa.c +++ b/drivers/net/wan/cosa.c @@ -889,6 +889,7 @@ static ssize_t cosa_write(struct file *file, chan->tx_status = 1; spin_unlock_irqrestore(&cosa->lock, flags); up(&chan->wsem); + kfree(kbuf); return -ERESTARTSYS; } } diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 376096bfc54a..9a270e49df17 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2060,8 +2060,6 @@ static void nvme_update_disk_info(struct gendisk *disk, if (id->nsattr & NVME_NS_ATTR_RO) set_disk_ro(disk, true); - else - set_disk_ro(disk, false); } static inline bool nvme_first_scan(struct gendisk *disk) @@ -2931,7 +2929,7 @@ int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp, u8 csi, static int nvme_get_effects_log(struct nvme_ctrl *ctrl, u8 csi, struct nvme_effects_log **log) { - struct nvme_cel *cel = xa_load(&ctrl->cels, csi); + struct nvme_effects_log *cel = xa_load(&ctrl->cels, csi); int ret; if (cel) @@ -2942,16 +2940,15 @@ static int nvme_get_effects_log(struct nvme_ctrl *ctrl, u8 csi, return -ENOMEM; ret = nvme_get_log(ctrl, 0x00, NVME_LOG_CMD_EFFECTS, 0, csi, - &cel->log, sizeof(cel->log), 0); + cel, sizeof(*cel), 0); if (ret) { kfree(cel); return ret; } - cel->csi = csi; - xa_store(&ctrl->cels, cel->csi, cel, GFP_KERNEL); + xa_store(&ctrl->cels, csi, cel, GFP_KERNEL); out: - *log = &cel->log; + *log = cel; return 0; } @@ -4376,6 +4373,19 @@ void nvme_uninit_ctrl(struct nvme_ctrl *ctrl) } EXPORT_SYMBOL_GPL(nvme_uninit_ctrl); +static void nvme_free_cels(struct nvme_ctrl *ctrl) +{ + struct nvme_effects_log *cel; + unsigned long i; + + xa_for_each (&ctrl->cels, i, cel) { + xa_erase(&ctrl->cels, i); + kfree(cel); + } + + xa_destroy(&ctrl->cels); +} + static void nvme_free_ctrl(struct device *dev) { struct nvme_ctrl *ctrl = @@ -4385,8 +4395,7 @@ static void nvme_free_ctrl(struct device *dev) if (!subsys || ctrl->instance != subsys->instance) ida_simple_remove(&nvme_instance_ida, ctrl->instance); - xa_destroy(&ctrl->cels); - + nvme_free_cels(ctrl); nvme_mpath_uninit(ctrl); __free_page(ctrl->discard_page); @@ -4582,8 +4591,7 @@ void nvme_start_queues(struct nvme_ctrl *ctrl) } EXPORT_SYMBOL_GPL(nvme_start_queues); - -void nvme_sync_queues(struct nvme_ctrl *ctrl) +void nvme_sync_io_queues(struct nvme_ctrl *ctrl) { struct nvme_ns *ns; @@ -4591,7 +4599,12 @@ void nvme_sync_queues(struct nvme_ctrl *ctrl) list_for_each_entry(ns, &ctrl->namespaces, list) blk_sync_queue(ns->queue); up_read(&ctrl->namespaces_rwsem); +} +EXPORT_SYMBOL_GPL(nvme_sync_io_queues); +void nvme_sync_queues(struct nvme_ctrl *ctrl) +{ + nvme_sync_io_queues(ctrl); if (ctrl->admin_q) blk_sync_queue(ctrl->admin_q); } diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index cc111136a981..567f7ad18a91 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -226,12 +226,6 @@ struct nvme_fault_inject { #endif }; -struct nvme_cel { - struct list_head entry; - struct nvme_effects_log log; - u8 csi; -}; - struct nvme_ctrl { bool comp_seen; enum nvme_ctrl_state state; @@ -602,6 +596,7 @@ void nvme_stop_queues(struct nvme_ctrl *ctrl); void nvme_start_queues(struct nvme_ctrl *ctrl); void nvme_kill_queues(struct nvme_ctrl *ctrl); void nvme_sync_queues(struct nvme_ctrl *ctrl); +void nvme_sync_io_queues(struct nvme_ctrl *ctrl); void nvme_unfreeze(struct nvme_ctrl *ctrl); void nvme_wait_freeze(struct nvme_ctrl *ctrl); int nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout); diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index df8f3612107f..3be352403839 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -198,6 +198,7 @@ struct nvme_queue { u32 q_depth; u16 cq_vector; u16 sq_tail; + u16 last_sq_tail; u16 cq_head; u16 qid; u8 cq_phase; @@ -291,9 +292,21 @@ static void nvme_dbbuf_init(struct nvme_dev *dev, nvmeq->dbbuf_cq_ei = &dev->dbbuf_eis[cq_idx(qid, dev->db_stride)]; } +static void nvme_dbbuf_free(struct nvme_queue *nvmeq) +{ + if (!nvmeq->qid) + return; + + nvmeq->dbbuf_sq_db = NULL; + nvmeq->dbbuf_cq_db = NULL; + nvmeq->dbbuf_sq_ei = NULL; + nvmeq->dbbuf_cq_ei = NULL; +} + static void nvme_dbbuf_set(struct nvme_dev *dev) { struct nvme_command c; + unsigned int i; if (!dev->dbbuf_dbs) return; @@ -307,6 +320,9 @@ static void nvme_dbbuf_set(struct nvme_dev *dev) dev_warn(dev->ctrl.device, "unable to set dbbuf\n"); /* Free memory and continue on */ nvme_dbbuf_dma_free(dev); + + for (i = 1; i <= dev->online_queues; i++) + nvme_dbbuf_free(&dev->queues[i]); } } @@ -455,11 +471,24 @@ static int nvme_pci_map_queues(struct blk_mq_tag_set *set) return 0; } -static inline void nvme_write_sq_db(struct nvme_queue *nvmeq) +/* + * Write sq tail if we are asked to, or if the next command would wrap. + */ +static inline void nvme_write_sq_db(struct nvme_queue *nvmeq, bool write_sq) { + if (!write_sq) { + u16 next_tail = nvmeq->sq_tail + 1; + + if (next_tail == nvmeq->q_depth) + next_tail = 0; + if (next_tail != nvmeq->last_sq_tail) + return; + } + if (nvme_dbbuf_update_and_check_event(nvmeq->sq_tail, nvmeq->dbbuf_sq_db, nvmeq->dbbuf_sq_ei)) writel(nvmeq->sq_tail, nvmeq->q_db); + nvmeq->last_sq_tail = nvmeq->sq_tail; } /** @@ -476,8 +505,7 @@ static void nvme_submit_cmd(struct nvme_queue *nvmeq, struct nvme_command *cmd, cmd, sizeof(*cmd)); if (++nvmeq->sq_tail == nvmeq->q_depth) nvmeq->sq_tail = 0; - if (write_sq) - nvme_write_sq_db(nvmeq); + nvme_write_sq_db(nvmeq, write_sq); spin_unlock(&nvmeq->sq_lock); } @@ -486,7 +514,8 @@ static void nvme_commit_rqs(struct blk_mq_hw_ctx *hctx) struct nvme_queue *nvmeq = hctx->driver_data; spin_lock(&nvmeq->sq_lock); - nvme_write_sq_db(nvmeq); + if (nvmeq->sq_tail != nvmeq->last_sq_tail) + nvme_write_sq_db(nvmeq, true); spin_unlock(&nvmeq->sq_lock); } @@ -1496,6 +1525,7 @@ static void nvme_init_queue(struct nvme_queue *nvmeq, u16 qid) struct nvme_dev *dev = nvmeq->dev; nvmeq->sq_tail = 0; + nvmeq->last_sq_tail = 0; nvmeq->cq_head = 0; nvmeq->cq_phase = 1; nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride]; diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 541b0cba6d80..65e3d0ef36e1 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -122,7 +122,6 @@ struct nvme_rdma_ctrl { struct sockaddr_storage src_addr; struct nvme_ctrl ctrl; - struct mutex teardown_lock; bool use_inline_data; u32 io_queues[HCTX_MAX_TYPES]; }; @@ -1010,8 +1009,8 @@ out_free_io_queues: static void nvme_rdma_teardown_admin_queue(struct nvme_rdma_ctrl *ctrl, bool remove) { - mutex_lock(&ctrl->teardown_lock); blk_mq_quiesce_queue(ctrl->ctrl.admin_q); + blk_sync_queue(ctrl->ctrl.admin_q); nvme_rdma_stop_queue(&ctrl->queues[0]); if (ctrl->ctrl.admin_tagset) { blk_mq_tagset_busy_iter(ctrl->ctrl.admin_tagset, @@ -1021,16 +1020,15 @@ static void nvme_rdma_teardown_admin_queue(struct nvme_rdma_ctrl *ctrl, if (remove) blk_mq_unquiesce_queue(ctrl->ctrl.admin_q); nvme_rdma_destroy_admin_queue(ctrl, remove); - mutex_unlock(&ctrl->teardown_lock); } static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl, bool remove) { - mutex_lock(&ctrl->teardown_lock); if (ctrl->ctrl.queue_count > 1) { nvme_start_freeze(&ctrl->ctrl); nvme_stop_queues(&ctrl->ctrl); + nvme_sync_io_queues(&ctrl->ctrl); nvme_rdma_stop_io_queues(ctrl); if (ctrl->ctrl.tagset) { blk_mq_tagset_busy_iter(ctrl->ctrl.tagset, @@ -1041,7 +1039,6 @@ static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl, nvme_start_queues(&ctrl->ctrl); nvme_rdma_destroy_io_queues(ctrl, remove); } - mutex_unlock(&ctrl->teardown_lock); } static void nvme_rdma_free_ctrl(struct nvme_ctrl *nctrl) @@ -1976,16 +1973,12 @@ static void nvme_rdma_complete_timed_out(struct request *rq) { struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq); struct nvme_rdma_queue *queue = req->queue; - struct nvme_rdma_ctrl *ctrl = queue->ctrl; - /* fence other contexts that may complete the command */ - mutex_lock(&ctrl->teardown_lock); nvme_rdma_stop_queue(queue); - if (!blk_mq_request_completed(rq)) { + if (blk_mq_request_started(rq) && !blk_mq_request_completed(rq)) { nvme_req(rq)->status = NVME_SC_HOST_ABORTED_CMD; blk_mq_complete_request(rq); } - mutex_unlock(&ctrl->teardown_lock); } static enum blk_eh_timer_return @@ -2320,7 +2313,6 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev, return ERR_PTR(-ENOMEM); ctrl->ctrl.opts = opts; INIT_LIST_HEAD(&ctrl->list); - mutex_init(&ctrl->teardown_lock); if (!(opts->mask & NVMF_OPT_TRSVCID)) { opts->trsvcid = diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index d6a3e1487354..c0c33320fe65 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -124,7 +124,6 @@ struct nvme_tcp_ctrl { struct sockaddr_storage src_addr; struct nvme_ctrl ctrl; - struct mutex teardown_lock; struct work_struct err_work; struct delayed_work connect_work; struct nvme_tcp_request async_req; @@ -1886,8 +1885,8 @@ out_free_queue: static void nvme_tcp_teardown_admin_queue(struct nvme_ctrl *ctrl, bool remove) { - mutex_lock(&to_tcp_ctrl(ctrl)->teardown_lock); blk_mq_quiesce_queue(ctrl->admin_q); + blk_sync_queue(ctrl->admin_q); nvme_tcp_stop_queue(ctrl, 0); if (ctrl->admin_tagset) { blk_mq_tagset_busy_iter(ctrl->admin_tagset, @@ -1897,18 +1896,17 @@ static void nvme_tcp_teardown_admin_queue(struct nvme_ctrl *ctrl, if (remove) blk_mq_unquiesce_queue(ctrl->admin_q); nvme_tcp_destroy_admin_queue(ctrl, remove); - mutex_unlock(&to_tcp_ctrl(ctrl)->teardown_lock); } static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl, bool remove) { - mutex_lock(&to_tcp_ctrl(ctrl)->teardown_lock); if (ctrl->queue_count <= 1) - goto out; + return; blk_mq_quiesce_queue(ctrl->admin_q); nvme_start_freeze(ctrl); nvme_stop_queues(ctrl); + nvme_sync_io_queues(ctrl); nvme_tcp_stop_io_queues(ctrl); if (ctrl->tagset) { blk_mq_tagset_busy_iter(ctrl->tagset, @@ -1918,8 +1916,6 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl, if (remove) nvme_start_queues(ctrl); nvme_tcp_destroy_io_queues(ctrl, remove); -out: - mutex_unlock(&to_tcp_ctrl(ctrl)->teardown_lock); } static void nvme_tcp_reconnect_or_remove(struct nvme_ctrl *ctrl) @@ -2171,14 +2167,11 @@ static void nvme_tcp_complete_timed_out(struct request *rq) struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq); struct nvme_ctrl *ctrl = &req->queue->ctrl->ctrl; - /* fence other contexts that may complete the command */ - mutex_lock(&to_tcp_ctrl(ctrl)->teardown_lock); nvme_tcp_stop_queue(ctrl, nvme_tcp_queue_id(req->queue)); - if (!blk_mq_request_completed(rq)) { + if (blk_mq_request_started(rq) && !blk_mq_request_completed(rq)) { nvme_req(rq)->status = NVME_SC_HOST_ABORTED_CMD; blk_mq_complete_request(rq); } - mutex_unlock(&to_tcp_ctrl(ctrl)->teardown_lock); } static enum blk_eh_timer_return @@ -2455,7 +2448,6 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev, nvme_tcp_reconnect_ctrl_work); INIT_WORK(&ctrl->err_work, nvme_tcp_error_recovery_work); INIT_WORK(&ctrl->ctrl.reset_work, nvme_reset_ctrl_work); - mutex_init(&ctrl->teardown_lock); if (!(opts->mask & NVMF_OPT_TRSVCID)) { opts->trsvcid = diff --git a/drivers/of/address.c b/drivers/of/address.c index eb9ab4f1e80b..1c3257a2d4e3 100644 --- a/drivers/of/address.c +++ b/drivers/of/address.c @@ -1034,11 +1034,13 @@ out: */ bool of_dma_is_coherent(struct device_node *np) { - struct device_node *node = of_node_get(np); + struct device_node *node; if (IS_ENABLED(CONFIG_OF_DMA_DEFAULT_COHERENT)) return true; + node = of_node_get(np); + while (node) { if (of_property_read_bool(node, "dma-coherent")) { of_node_put(node); diff --git a/drivers/of/device.c b/drivers/of/device.c index 3a469c79e6b0..aedfaaafd3e7 100644 --- a/drivers/of/device.c +++ b/drivers/of/device.c @@ -112,7 +112,7 @@ int of_dma_configure_id(struct device *dev, struct device_node *np, u64 dma_end = 0; /* Determine the overall bounds of all DMA regions */ - for (dma_start = ~0ULL; r->size; r++) { + for (dma_start = ~0; r->size; r++) { /* Take lower and upper limits */ if (r->dma_start < dma_start) dma_start = r->dma_start; diff --git a/drivers/opp/core.c b/drivers/opp/core.c index 2483e765318a..0e0a5269dc82 100644 --- a/drivers/opp/core.c +++ b/drivers/opp/core.c @@ -1181,6 +1181,10 @@ static void _opp_table_kref_release(struct kref *kref) struct opp_device *opp_dev, *temp; int i; + /* Drop the lock as soon as we can */ + list_del(&opp_table->node); + mutex_unlock(&opp_table_lock); + _of_clear_opp_table(opp_table); /* Release clk */ @@ -1208,10 +1212,7 @@ static void _opp_table_kref_release(struct kref *kref) mutex_destroy(&opp_table->genpd_virt_dev_lock); mutex_destroy(&opp_table->lock); - list_del(&opp_table->node); kfree(opp_table); - - mutex_unlock(&opp_table_lock); } void dev_pm_opp_put_opp_table(struct opp_table *opp_table) @@ -1930,7 +1931,7 @@ struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev, return ERR_PTR(-EINVAL); opp_table = dev_pm_opp_get_opp_table(dev); - if (!IS_ERR(opp_table)) + if (IS_ERR(opp_table)) return opp_table; /* This should be called before OPPs are initialized */ diff --git a/drivers/opp/of.c b/drivers/opp/of.c index 874b58756220..9faeb83e4b32 100644 --- a/drivers/opp/of.c +++ b/drivers/opp/of.c @@ -944,6 +944,8 @@ static int _of_add_opp_table_v1(struct device *dev, struct opp_table *opp_table) nr -= 2; } + return 0; + remove_static_opp: _opp_remove_all_static(opp_table); diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c index 674f32db85ca..44c2a6572199 100644 --- a/drivers/pci/controller/dwc/pcie-designware-host.c +++ b/drivers/pci/controller/dwc/pcie-designware-host.c @@ -586,8 +586,12 @@ void dw_pcie_setup_rc(struct pcie_port *pp) * ATU, so we should not program the ATU here. */ if (pp->bridge->child_ops == &dw_child_pcie_ops) { - struct resource_entry *entry = - resource_list_first_type(&pp->bridge->windows, IORESOURCE_MEM); + struct resource_entry *tmp, *entry = NULL; + + /* Get last memory resource entry */ + resource_list_for_each_entry(tmp, &pp->bridge->windows) + if (resource_type(tmp->res) == IORESOURCE_MEM) + entry = tmp; dw_pcie_prog_outbound_atu(pci, PCIE_ATU_REGION_INDEX0, PCIE_ATU_TYPE_MEM, entry->res->start, diff --git a/drivers/pci/controller/pci-mvebu.c b/drivers/pci/controller/pci-mvebu.c index eee82838f4ba..ed13e81cd691 100644 --- a/drivers/pci/controller/pci-mvebu.c +++ b/drivers/pci/controller/pci-mvebu.c @@ -958,25 +958,16 @@ static void mvebu_pcie_powerdown(struct mvebu_pcie_port *port) } /* - * We can't use devm_of_pci_get_host_bridge_resources() because we - * need to parse our special DT properties encoding the MEM and IO - * apertures. + * devm_of_pci_get_host_bridge_resources() only sets up translateable resources, + * so we need extra resource setup parsing our special DT properties encoding + * the MEM and IO apertures. */ static int mvebu_pcie_parse_request_resources(struct mvebu_pcie *pcie) { struct device *dev = &pcie->pdev->dev; - struct device_node *np = dev->of_node; struct pci_host_bridge *bridge = pci_host_bridge_from_priv(pcie); int ret; - /* Get the bus range */ - ret = of_pci_parse_bus_range(np, &pcie->busn); - if (ret) { - dev_err(dev, "failed to parse bus-range property: %d\n", ret); - return ret; - } - pci_add_resource(&bridge->windows, &pcie->busn); - /* Get the PCIe memory aperture */ mvebu_mbus_get_pcie_mem_aperture(&pcie->mem); if (resource_size(&pcie->mem) == 0) { @@ -986,6 +977,9 @@ static int mvebu_pcie_parse_request_resources(struct mvebu_pcie *pcie) pcie->mem.name = "PCI MEM"; pci_add_resource(&bridge->windows, &pcie->mem); + ret = devm_request_resource(dev, &iomem_resource, &pcie->mem); + if (ret) + return ret; /* Get the PCIe IO aperture */ mvebu_mbus_get_pcie_io_aperture(&pcie->io); @@ -999,9 +993,12 @@ static int mvebu_pcie_parse_request_resources(struct mvebu_pcie *pcie) pcie->realio.name = "PCI I/O"; pci_add_resource(&bridge->windows, &pcie->realio); + ret = devm_request_resource(dev, &ioport_resource, &pcie->realio); + if (ret) + return ret; } - return devm_request_pci_bus_resources(dev, &bridge->windows); + return 0; } /* diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 6d4d5a2f923d..e578d34095e9 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -3516,8 +3516,13 @@ void pci_acs_init(struct pci_dev *dev) { dev->acs_cap = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ACS); - if (dev->acs_cap) - pci_enable_acs(dev); + /* + * Attempt to enable ACS regardless of capability because some Root + * Ports (e.g. those quirked with *_intel_pch_acs_*) do not have + * the standard ACS capability but still support ACS via those + * quirks. + */ + pci_enable_acs(dev); } /** diff --git a/drivers/pinctrl/aspeed/pinctrl-aspeed.c b/drivers/pinctrl/aspeed/pinctrl-aspeed.c index 6a94eaecf638..d6b849552a1e 100644 --- a/drivers/pinctrl/aspeed/pinctrl-aspeed.c +++ b/drivers/pinctrl/aspeed/pinctrl-aspeed.c @@ -286,13 +286,14 @@ int aspeed_pinmux_set_mux(struct pinctrl_dev *pctldev, unsigned int function, static bool aspeed_expr_is_gpio(const struct aspeed_sig_expr *expr) { /* - * The signal type is GPIO if the signal name has "GPIO" as a prefix. + * The signal type is GPIO if the signal name has "GPI" as a prefix. * strncmp (rather than strcmp) is used to implement the prefix * requirement. * - * expr->signal might look like "GPIOT3" in the GPIO case. + * expr->signal might look like "GPIOB1" in the GPIO case. + * expr->signal might look like "GPIT0" in the GPI case. */ - return strncmp(expr->signal, "GPIO", 4) == 0; + return strncmp(expr->signal, "GPI", 3) == 0; } static bool aspeed_gpio_in_exprs(const struct aspeed_sig_expr **exprs) diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c index 154ce3f908cd..1c10ab184783 100644 --- a/drivers/pinctrl/intel/pinctrl-intel.c +++ b/drivers/pinctrl/intel/pinctrl-intel.c @@ -62,10 +62,10 @@ #define PADCFG1_TERM_UP BIT(13) #define PADCFG1_TERM_SHIFT 10 #define PADCFG1_TERM_MASK GENMASK(12, 10) -#define PADCFG1_TERM_20K 4 -#define PADCFG1_TERM_2K 3 -#define PADCFG1_TERM_5K 2 -#define PADCFG1_TERM_1K 1 +#define PADCFG1_TERM_20K BIT(2) +#define PADCFG1_TERM_5K BIT(1) +#define PADCFG1_TERM_1K BIT(0) +#define PADCFG1_TERM_833 (BIT(1) | BIT(0)) #define PADCFG2 0x008 #define PADCFG2_DEBEN BIT(0) @@ -549,12 +549,12 @@ static int intel_config_get_pull(struct intel_pinctrl *pctrl, unsigned int pin, return -EINVAL; switch (term) { + case PADCFG1_TERM_833: + *arg = 833; + break; case PADCFG1_TERM_1K: *arg = 1000; break; - case PADCFG1_TERM_2K: - *arg = 2000; - break; case PADCFG1_TERM_5K: *arg = 5000; break; @@ -570,6 +570,11 @@ static int intel_config_get_pull(struct intel_pinctrl *pctrl, unsigned int pin, return -EINVAL; switch (term) { + case PADCFG1_TERM_833: + if (!(community->features & PINCTRL_FEATURE_1K_PD)) + return -EINVAL; + *arg = 833; + break; case PADCFG1_TERM_1K: if (!(community->features & PINCTRL_FEATURE_1K_PD)) return -EINVAL; @@ -678,6 +683,10 @@ static int intel_config_set_pull(struct intel_pinctrl *pctrl, unsigned int pin, value |= PADCFG1_TERM_UP; + /* Set default strength value in case none is given */ + if (arg == 1) + arg = 5000; + switch (arg) { case 20000: value |= PADCFG1_TERM_20K << PADCFG1_TERM_SHIFT; @@ -685,12 +694,12 @@ static int intel_config_set_pull(struct intel_pinctrl *pctrl, unsigned int pin, case 5000: value |= PADCFG1_TERM_5K << PADCFG1_TERM_SHIFT; break; - case 2000: - value |= PADCFG1_TERM_2K << PADCFG1_TERM_SHIFT; - break; case 1000: value |= PADCFG1_TERM_1K << PADCFG1_TERM_SHIFT; break; + case 833: + value |= PADCFG1_TERM_833 << PADCFG1_TERM_SHIFT; + break; default: ret = -EINVAL; } @@ -700,6 +709,10 @@ static int intel_config_set_pull(struct intel_pinctrl *pctrl, unsigned int pin, case PIN_CONFIG_BIAS_PULL_DOWN: value &= ~(PADCFG1_TERM_UP | PADCFG1_TERM_MASK); + /* Set default strength value in case none is given */ + if (arg == 1) + arg = 5000; + switch (arg) { case 20000: value |= PADCFG1_TERM_20K << PADCFG1_TERM_SHIFT; @@ -714,6 +727,13 @@ static int intel_config_set_pull(struct intel_pinctrl *pctrl, unsigned int pin, } value |= PADCFG1_TERM_1K << PADCFG1_TERM_SHIFT; break; + case 833: + if (!(community->features & PINCTRL_FEATURE_1K_PD)) { + ret = -EINVAL; + break; + } + value |= PADCFG1_TERM_833 << PADCFG1_TERM_SHIFT; + break; default: ret = -EINVAL; } diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index 9a760f5cd7ed..4aea3e05e8c6 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -156,7 +156,7 @@ static int amd_gpio_set_debounce(struct gpio_chip *gc, unsigned offset, pin_reg |= BIT(DB_TMR_OUT_UNIT_OFF); pin_reg &= ~BIT(DB_TMR_LARGE_OFF); } else if (debounce < 250000) { - time = debounce / 15600; + time = debounce / 15625; pin_reg |= time & DB_TMR_OUT_MASK; pin_reg &= ~BIT(DB_TMR_OUT_UNIT_OFF); pin_reg |= BIT(DB_TMR_LARGE_OFF); @@ -166,14 +166,14 @@ static int amd_gpio_set_debounce(struct gpio_chip *gc, unsigned offset, pin_reg |= BIT(DB_TMR_OUT_UNIT_OFF); pin_reg |= BIT(DB_TMR_LARGE_OFF); } else { - pin_reg &= ~DB_CNTRl_MASK; + pin_reg &= ~(DB_CNTRl_MASK << DB_CNTRL_OFF); ret = -EINVAL; } } else { pin_reg &= ~BIT(DB_TMR_OUT_UNIT_OFF); pin_reg &= ~BIT(DB_TMR_LARGE_OFF); pin_reg &= ~DB_TMR_OUT_MASK; - pin_reg &= ~DB_CNTRl_MASK; + pin_reg &= ~(DB_CNTRl_MASK << DB_CNTRL_OFF); } writel(pin_reg, gpio_dev->base + offset * 4); raw_spin_unlock_irqrestore(&gpio_dev->lock, flags); diff --git a/drivers/pinctrl/pinctrl-ingenic.c b/drivers/pinctrl/pinctrl-ingenic.c index c8e50a58a5e5..621909b01deb 100644 --- a/drivers/pinctrl/pinctrl-ingenic.c +++ b/drivers/pinctrl/pinctrl-ingenic.c @@ -635,44 +635,44 @@ static int jz4770_uart3_data_pins[] = { 0x6c, 0x85, }; static int jz4770_uart3_hwflow_pins[] = { 0x88, 0x89, }; static int jz4770_ssi0_dt_a_pins[] = { 0x15, }; static int jz4770_ssi0_dt_b_pins[] = { 0x35, }; -static int jz4770_ssi0_dt_d_pins[] = { 0x55, }; -static int jz4770_ssi0_dt_e_pins[] = { 0x71, }; +static int jz4770_ssi0_dt_d_pins[] = { 0x75, }; +static int jz4770_ssi0_dt_e_pins[] = { 0x91, }; static int jz4770_ssi0_dr_a_pins[] = { 0x14, }; static int jz4770_ssi0_dr_b_pins[] = { 0x34, }; -static int jz4770_ssi0_dr_d_pins[] = { 0x54, }; -static int jz4770_ssi0_dr_e_pins[] = { 0x6e, }; +static int jz4770_ssi0_dr_d_pins[] = { 0x74, }; +static int jz4770_ssi0_dr_e_pins[] = { 0x8e, }; static int jz4770_ssi0_clk_a_pins[] = { 0x12, }; static int jz4770_ssi0_clk_b_pins[] = { 0x3c, }; -static int jz4770_ssi0_clk_d_pins[] = { 0x58, }; -static int jz4770_ssi0_clk_e_pins[] = { 0x6f, }; +static int jz4770_ssi0_clk_d_pins[] = { 0x78, }; +static int jz4770_ssi0_clk_e_pins[] = { 0x8f, }; static int jz4770_ssi0_gpc_b_pins[] = { 0x3e, }; -static int jz4770_ssi0_gpc_d_pins[] = { 0x56, }; -static int jz4770_ssi0_gpc_e_pins[] = { 0x73, }; +static int jz4770_ssi0_gpc_d_pins[] = { 0x76, }; +static int jz4770_ssi0_gpc_e_pins[] = { 0x93, }; static int jz4770_ssi0_ce0_a_pins[] = { 0x13, }; static int jz4770_ssi0_ce0_b_pins[] = { 0x3d, }; -static int jz4770_ssi0_ce0_d_pins[] = { 0x59, }; -static int jz4770_ssi0_ce0_e_pins[] = { 0x70, }; +static int jz4770_ssi0_ce0_d_pins[] = { 0x79, }; +static int jz4770_ssi0_ce0_e_pins[] = { 0x90, }; static int jz4770_ssi0_ce1_b_pins[] = { 0x3f, }; -static int jz4770_ssi0_ce1_d_pins[] = { 0x57, }; -static int jz4770_ssi0_ce1_e_pins[] = { 0x72, }; +static int jz4770_ssi0_ce1_d_pins[] = { 0x77, }; +static int jz4770_ssi0_ce1_e_pins[] = { 0x92, }; static int jz4770_ssi1_dt_b_pins[] = { 0x35, }; -static int jz4770_ssi1_dt_d_pins[] = { 0x55, }; -static int jz4770_ssi1_dt_e_pins[] = { 0x71, }; +static int jz4770_ssi1_dt_d_pins[] = { 0x75, }; +static int jz4770_ssi1_dt_e_pins[] = { 0x91, }; static int jz4770_ssi1_dr_b_pins[] = { 0x34, }; -static int jz4770_ssi1_dr_d_pins[] = { 0x54, }; -static int jz4770_ssi1_dr_e_pins[] = { 0x6e, }; +static int jz4770_ssi1_dr_d_pins[] = { 0x74, }; +static int jz4770_ssi1_dr_e_pins[] = { 0x8e, }; static int jz4770_ssi1_clk_b_pins[] = { 0x3c, }; -static int jz4770_ssi1_clk_d_pins[] = { 0x58, }; -static int jz4770_ssi1_clk_e_pins[] = { 0x6f, }; +static int jz4770_ssi1_clk_d_pins[] = { 0x78, }; +static int jz4770_ssi1_clk_e_pins[] = { 0x8f, }; static int jz4770_ssi1_gpc_b_pins[] = { 0x3e, }; -static int jz4770_ssi1_gpc_d_pins[] = { 0x56, }; -static int jz4770_ssi1_gpc_e_pins[] = { 0x73, }; +static int jz4770_ssi1_gpc_d_pins[] = { 0x76, }; +static int jz4770_ssi1_gpc_e_pins[] = { 0x93, }; static int jz4770_ssi1_ce0_b_pins[] = { 0x3d, }; -static int jz4770_ssi1_ce0_d_pins[] = { 0x59, }; -static int jz4770_ssi1_ce0_e_pins[] = { 0x70, }; +static int jz4770_ssi1_ce0_d_pins[] = { 0x79, }; +static int jz4770_ssi1_ce0_e_pins[] = { 0x90, }; static int jz4770_ssi1_ce1_b_pins[] = { 0x3f, }; -static int jz4770_ssi1_ce1_d_pins[] = { 0x57, }; -static int jz4770_ssi1_ce1_e_pins[] = { 0x72, }; +static int jz4770_ssi1_ce1_d_pins[] = { 0x77, }; +static int jz4770_ssi1_ce1_e_pins[] = { 0x92, }; static int jz4770_mmc0_1bit_a_pins[] = { 0x12, 0x13, 0x14, }; static int jz4770_mmc0_4bit_a_pins[] = { 0x15, 0x16, 0x17, }; static int jz4770_mmc0_1bit_e_pins[] = { 0x9c, 0x9d, 0x94, }; @@ -1050,35 +1050,35 @@ static int jz4780_ssi0_dt_a_19_pins[] = { 0x13, }; static int jz4780_ssi0_dt_a_21_pins[] = { 0x15, }; static int jz4780_ssi0_dt_a_28_pins[] = { 0x1c, }; static int jz4780_ssi0_dt_b_pins[] = { 0x3d, }; -static int jz4780_ssi0_dt_d_pins[] = { 0x59, }; +static int jz4780_ssi0_dt_d_pins[] = { 0x79, }; static int jz4780_ssi0_dr_a_20_pins[] = { 0x14, }; static int jz4780_ssi0_dr_a_27_pins[] = { 0x1b, }; static int jz4780_ssi0_dr_b_pins[] = { 0x34, }; -static int jz4780_ssi0_dr_d_pins[] = { 0x54, }; +static int jz4780_ssi0_dr_d_pins[] = { 0x74, }; static int jz4780_ssi0_clk_a_pins[] = { 0x12, }; static int jz4780_ssi0_clk_b_5_pins[] = { 0x25, }; static int jz4780_ssi0_clk_b_28_pins[] = { 0x3c, }; -static int jz4780_ssi0_clk_d_pins[] = { 0x58, }; +static int jz4780_ssi0_clk_d_pins[] = { 0x78, }; static int jz4780_ssi0_gpc_b_pins[] = { 0x3e, }; -static int jz4780_ssi0_gpc_d_pins[] = { 0x56, }; +static int jz4780_ssi0_gpc_d_pins[] = { 0x76, }; static int jz4780_ssi0_ce0_a_23_pins[] = { 0x17, }; static int jz4780_ssi0_ce0_a_25_pins[] = { 0x19, }; static int jz4780_ssi0_ce0_b_pins[] = { 0x3f, }; -static int jz4780_ssi0_ce0_d_pins[] = { 0x57, }; +static int jz4780_ssi0_ce0_d_pins[] = { 0x77, }; static int jz4780_ssi0_ce1_b_pins[] = { 0x35, }; -static int jz4780_ssi0_ce1_d_pins[] = { 0x55, }; +static int jz4780_ssi0_ce1_d_pins[] = { 0x75, }; static int jz4780_ssi1_dt_b_pins[] = { 0x3d, }; -static int jz4780_ssi1_dt_d_pins[] = { 0x59, }; +static int jz4780_ssi1_dt_d_pins[] = { 0x79, }; static int jz4780_ssi1_dr_b_pins[] = { 0x34, }; -static int jz4780_ssi1_dr_d_pins[] = { 0x54, }; +static int jz4780_ssi1_dr_d_pins[] = { 0x74, }; static int jz4780_ssi1_clk_b_pins[] = { 0x3c, }; -static int jz4780_ssi1_clk_d_pins[] = { 0x58, }; +static int jz4780_ssi1_clk_d_pins[] = { 0x78, }; static int jz4780_ssi1_gpc_b_pins[] = { 0x3e, }; -static int jz4780_ssi1_gpc_d_pins[] = { 0x56, }; +static int jz4780_ssi1_gpc_d_pins[] = { 0x76, }; static int jz4780_ssi1_ce0_b_pins[] = { 0x3f, }; -static int jz4780_ssi1_ce0_d_pins[] = { 0x57, }; +static int jz4780_ssi1_ce0_d_pins[] = { 0x77, }; static int jz4780_ssi1_ce1_b_pins[] = { 0x35, }; -static int jz4780_ssi1_ce1_d_pins[] = { 0x55, }; +static int jz4780_ssi1_ce1_d_pins[] = { 0x75, }; static int jz4780_mmc0_8bit_a_pins[] = { 0x04, 0x05, 0x06, 0x07, 0x18, }; static int jz4780_i2c3_pins[] = { 0x6a, 0x6b, }; static int jz4780_i2c4_e_pins[] = { 0x8c, 0x8d, }; diff --git a/drivers/pinctrl/pinctrl-mcp23s08_spi.c b/drivers/pinctrl/pinctrl-mcp23s08_spi.c index 1f47a661b0a7..9ae10318f6f3 100644 --- a/drivers/pinctrl/pinctrl-mcp23s08_spi.c +++ b/drivers/pinctrl/pinctrl-mcp23s08_spi.c @@ -119,13 +119,15 @@ static int mcp23s08_spi_regmap_init(struct mcp23s08 *mcp, struct device *dev, return -EINVAL; } - copy = devm_kmemdup(dev, &config, sizeof(config), GFP_KERNEL); + copy = devm_kmemdup(dev, config, sizeof(*config), GFP_KERNEL); if (!copy) return -ENOMEM; copy->name = name; mcp->regmap = devm_regmap_init(dev, &mcp23sxx_spi_regmap, mcp, copy); + if (IS_ERR(mcp->regmap)) + dev_err(dev, "regmap init failed for %s\n", mcp->chip.label); return PTR_ERR_OR_ZERO(mcp->regmap); } diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c index 0401c1da79dd..aa1a1c850d05 100644 --- a/drivers/pinctrl/pinctrl-rockchip.c +++ b/drivers/pinctrl/pinctrl-rockchip.c @@ -3155,7 +3155,9 @@ static int rockchip_gpio_to_irq(struct gpio_chip *gc, unsigned offset) if (!bank->domain) return -ENXIO; + clk_enable(bank->clk); virq = irq_create_mapping(bank->domain, offset); + clk_disable(bank->clk); return (virq) ? : -ENXIO; } @@ -3194,7 +3196,7 @@ static void rockchip_irq_demux(struct irq_desc *desc) irq = __ffs(pend); pend &= ~BIT(irq); - virq = irq_linear_revmap(bank->domain, irq); + virq = irq_find_mapping(bank->domain, irq); if (!virq) { dev_err(bank->drvdata->dev, "unmapped irq %d\n", irq); @@ -3373,7 +3375,7 @@ static int rockchip_interrupts_register(struct platform_device *pdev, unsigned int clr = IRQ_NOREQUEST | IRQ_NOPROBE | IRQ_NOAUTOEN; struct irq_chip_generic *gc; int ret; - int i, j; + int i; for (i = 0; i < ctrl->nr_banks; ++i, ++bank) { if (!bank->valid) { @@ -3400,7 +3402,7 @@ static int rockchip_interrupts_register(struct platform_device *pdev, ret = irq_alloc_domain_generic_chips(bank->domain, 32, 1, "rockchip_gpio_irq", handle_level_irq, - clr, 0, IRQ_GC_INIT_MASK_CACHE); + clr, 0, 0); if (ret) { dev_err(&pdev->dev, "could not alloc generic chips for bank %s\n", bank->name); @@ -3409,14 +3411,6 @@ static int rockchip_interrupts_register(struct platform_device *pdev, continue; } - /* - * Linux assumes that all interrupts start out disabled/masked. - * Our driver only uses the concept of masked and always keeps - * things enabled, so for us that's all masked and all enabled. - */ - writel_relaxed(0xffffffff, bank->reg_base + GPIO_INTMASK); - writel_relaxed(0xffffffff, bank->reg_base + GPIO_INTEN); - gc = irq_get_domain_generic_chip(bank->domain, 0); gc->reg_base = bank->reg_base; gc->private = bank; @@ -3433,13 +3427,17 @@ static int rockchip_interrupts_register(struct platform_device *pdev, gc->chip_types[0].chip.irq_set_type = rockchip_irq_set_type; gc->wake_enabled = IRQ_MSK(bank->nr_pins); + /* + * Linux assumes that all interrupts start out disabled/masked. + * Our driver only uses the concept of masked and always keeps + * things enabled, so for us that's all masked and all enabled. + */ + writel_relaxed(0xffffffff, bank->reg_base + GPIO_INTMASK); + writel_relaxed(0xffffffff, bank->reg_base + GPIO_INTEN); + gc->mask_cache = 0xffffffff; + irq_set_chained_handler_and_data(bank->irq, rockchip_irq_demux, bank); - - /* map the gpio irqs here, when the clock is still running */ - for (j = 0 ; j < 32 ; j++) - irq_create_mapping(bank->domain, j); - clk_disable(bank->clk); } diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c index c4bcda90aac4..77a25bdf0da7 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm.c +++ b/drivers/pinctrl/qcom/pinctrl-msm.c @@ -815,21 +815,14 @@ static void msm_gpio_irq_clear_unmask(struct irq_data *d, bool status_clear) static void msm_gpio_irq_enable(struct irq_data *d) { - /* - * Clear the interrupt that may be pending before we enable - * the line. - * This is especially a problem with the GPIOs routed to the - * PDC. These GPIOs are direct-connect interrupts to the GIC. - * Disabling the interrupt line at the PDC does not prevent - * the interrupt from being latched at the GIC. The state at - * GIC needs to be cleared before enabling. - */ - if (d->parent_data) { - irq_chip_set_parent_state(d, IRQCHIP_STATE_PENDING, 0); + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct msm_pinctrl *pctrl = gpiochip_get_data(gc); + + if (d->parent_data) irq_chip_enable_parent(d); - } - msm_gpio_irq_clear_unmask(d, true); + if (!test_bit(d->hwirq, pctrl->skip_wake_irqs)) + msm_gpio_irq_clear_unmask(d, true); } static void msm_gpio_irq_disable(struct irq_data *d) @@ -1104,6 +1097,19 @@ static int msm_gpio_irq_reqres(struct irq_data *d) ret = -EINVAL; goto out; } + + /* + * Clear the interrupt that may be pending before we enable + * the line. + * This is especially a problem with the GPIOs routed to the + * PDC. These GPIOs are direct-connect interrupts to the GIC. + * Disabling the interrupt line at the PDC does not prevent + * the interrupt from being latched at the GIC. The state at + * GIC needs to be cleared before enabling. + */ + if (d->parent_data && test_bit(d->hwirq, pctrl->skip_wake_irqs)) + irq_chip_set_parent_state(d, IRQCHIP_STATE_PENDING, 0); + return 0; out: module_put(gc->owner); diff --git a/drivers/pinctrl/qcom/pinctrl-sm8250.c b/drivers/pinctrl/qcom/pinctrl-sm8250.c index 826df0d637ea..af144e724bd9 100644 --- a/drivers/pinctrl/qcom/pinctrl-sm8250.c +++ b/drivers/pinctrl/qcom/pinctrl-sm8250.c @@ -1313,6 +1313,22 @@ static const struct msm_pingroup sm8250_groups[] = { [183] = SDC_PINGROUP(sdc2_data, 0xb7000, 9, 0), }; +static const struct msm_gpio_wakeirq_map sm8250_pdc_map[] = { + { 0, 79 }, { 1, 84 }, { 2, 80 }, { 3, 82 }, { 4, 107 }, { 7, 43 }, + { 11, 42 }, { 14, 44 }, { 15, 52 }, { 19, 67 }, { 23, 68 }, { 24, 105 }, + { 27, 92 }, { 28, 106 }, { 31, 69 }, { 35, 70 }, { 39, 37 }, + { 40, 108 }, { 43, 71 }, { 45, 72 }, { 47, 83 }, { 51, 74 }, { 55, 77 }, + { 59, 78 }, { 63, 75 }, { 64, 81 }, { 65, 87 }, { 66, 88 }, { 67, 89 }, + { 68, 54 }, { 70, 85 }, { 77, 46 }, { 80, 90 }, { 81, 91 }, { 83, 97 }, + { 84, 98 }, { 86, 99 }, { 87, 100 }, { 88, 101 }, { 89, 102 }, + { 92, 103 }, { 93, 104 }, { 100, 53 }, { 103, 47 }, { 104, 48 }, + { 108, 49 }, { 109, 94 }, { 110, 95 }, { 111, 96 }, { 112, 55 }, + { 113, 56 }, { 118, 50 }, { 121, 51 }, { 122, 57 }, { 123, 58 }, + { 124, 45 }, { 126, 59 }, { 128, 76 }, { 129, 86 }, { 132, 93 }, + { 133, 65 }, { 134, 66 }, { 136, 62 }, { 137, 63 }, { 138, 64 }, + { 142, 60 }, { 143, 61 } +}; + static const struct msm_pinctrl_soc_data sm8250_pinctrl = { .pins = sm8250_pins, .npins = ARRAY_SIZE(sm8250_pins), @@ -1323,6 +1339,8 @@ static const struct msm_pinctrl_soc_data sm8250_pinctrl = { .ngpios = 181, .tiles = sm8250_tiles, .ntiles = ARRAY_SIZE(sm8250_tiles), + .wakeirq_map = sm8250_pdc_map, + .nwakeirq_map = ARRAY_SIZE(sm8250_pdc_map), }; static int sm8250_pinctrl_probe(struct platform_device *pdev) diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c index 0b2830efc574..70d6d52bc1e2 100644 --- a/drivers/powercap/intel_rapl_common.c +++ b/drivers/powercap/intel_rapl_common.c @@ -620,7 +620,7 @@ static u64 rapl_unit_xlate(struct rapl_domain *rd, enum unit_type type, case ARBITRARY_UNIT: default: return value; - }; + } if (to_raw) return div64_u64(value, units) * scale; diff --git a/drivers/powercap/powercap_sys.c b/drivers/powercap/powercap_sys.c index f808c5fa9838..3f0b8e2ef3d4 100644 --- a/drivers/powercap/powercap_sys.c +++ b/drivers/powercap/powercap_sys.c @@ -367,9 +367,9 @@ static void create_power_zone_common_attributes( &dev_attr_max_energy_range_uj.attr; if (power_zone->ops->get_energy_uj) { if (power_zone->ops->reset_energy_uj) - dev_attr_energy_uj.attr.mode = S_IWUSR | S_IRUGO; + dev_attr_energy_uj.attr.mode = S_IWUSR | S_IRUSR; else - dev_attr_energy_uj.attr.mode = S_IRUGO; + dev_attr_energy_uj.attr.mode = S_IRUSR; power_zone->zone_dev_attrs[count++] = &dev_attr_energy_uj.attr; } diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index a4ffd71696da..42bbd99a36ac 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -1315,7 +1315,6 @@ static int _regulator_do_enable(struct regulator_dev *rdev); /** * set_machine_constraints - sets regulator constraints * @rdev: regulator source - * @constraints: constraints to apply * * Allows platform initialisation code to define and constrain * regulator circuits e.g. valid voltage/current ranges, etc. NOTE: @@ -1323,21 +1322,11 @@ static int _regulator_do_enable(struct regulator_dev *rdev); * regulator operations to proceed i.e. set_voltage, set_current_limit, * set_mode. */ -static int set_machine_constraints(struct regulator_dev *rdev, - const struct regulation_constraints *constraints) +static int set_machine_constraints(struct regulator_dev *rdev) { int ret = 0; const struct regulator_ops *ops = rdev->desc->ops; - if (constraints) - rdev->constraints = kmemdup(constraints, sizeof(*constraints), - GFP_KERNEL); - else - rdev->constraints = kzalloc(sizeof(*constraints), - GFP_KERNEL); - if (!rdev->constraints) - return -ENOMEM; - ret = machine_constraints_voltage(rdev, rdev->constraints); if (ret != 0) return ret; @@ -1852,6 +1841,15 @@ static int regulator_resolve_supply(struct regulator_dev *rdev) } } + if (r == rdev) { + dev_err(dev, "Supply for %s (%s) resolved to itself\n", + rdev->desc->name, rdev->supply_name); + if (!have_full_constraints()) + return -EINVAL; + r = dummy_regulator_rdev; + get_device(&r->dev); + } + /* * If the supply's parent device is not the same as the * regulator's parent device, then ensure the parent device @@ -4165,6 +4163,8 @@ int regulator_get_voltage_rdev(struct regulator_dev *rdev) ret = rdev->desc->fixed_uV; } else if (rdev->supply) { ret = regulator_get_voltage_rdev(rdev->supply->rdev); + } else if (rdev->supply_name) { + return -EPROBE_DEFER; } else { return -EINVAL; } @@ -5144,7 +5144,6 @@ struct regulator_dev * regulator_register(const struct regulator_desc *regulator_desc, const struct regulator_config *cfg) { - const struct regulation_constraints *constraints = NULL; const struct regulator_init_data *init_data; struct regulator_config *config = NULL; static atomic_t regulator_no = ATOMIC_INIT(-1); @@ -5283,14 +5282,23 @@ regulator_register(const struct regulator_desc *regulator_desc, /* set regulator constraints */ if (init_data) - constraints = &init_data->constraints; + rdev->constraints = kmemdup(&init_data->constraints, + sizeof(*rdev->constraints), + GFP_KERNEL); + else + rdev->constraints = kzalloc(sizeof(*rdev->constraints), + GFP_KERNEL); + if (!rdev->constraints) { + ret = -ENOMEM; + goto wash; + } if (init_data && init_data->supply_regulator) rdev->supply_name = init_data->supply_regulator; else if (regulator_desc->supply_name) rdev->supply_name = regulator_desc->supply_name; - ret = set_machine_constraints(rdev, constraints); + ret = set_machine_constraints(rdev); if (ret == -EPROBE_DEFER) { /* Regulator might be in bypass mode and so needs its supply * to set the constraints */ @@ -5299,7 +5307,7 @@ regulator_register(const struct regulator_desc *regulator_desc, * that is just being created */ ret = regulator_resolve_supply(rdev); if (!ret) - ret = set_machine_constraints(rdev, constraints); + ret = set_machine_constraints(rdev); else rdev_dbg(rdev, "unable to resolve supply early: %pe\n", ERR_PTR(ret)); @@ -5841,13 +5849,14 @@ static int regulator_late_cleanup(struct device *dev, void *data) if (rdev->use_count) goto unlock; - /* If we can't read the status assume it's on. */ + /* If we can't read the status assume it's always on. */ if (ops->is_enabled) enabled = ops->is_enabled(rdev); else enabled = 1; - if (!enabled) + /* But if reading the status failed, assume that it's off. */ + if (enabled <= 0) goto unlock; if (have_full_constraints()) { diff --git a/drivers/regulator/pfuze100-regulator.c b/drivers/regulator/pfuze100-regulator.c index 7e8ba9246167..01a12cfcea7c 100644 --- a/drivers/regulator/pfuze100-regulator.c +++ b/drivers/regulator/pfuze100-regulator.c @@ -836,11 +836,14 @@ static int pfuze100_regulator_probe(struct i2c_client *client, * the switched regulator till yet. */ if (pfuze_chip->flags & PFUZE_FLAG_DISABLE_SW) { - if (pfuze_chip->regulator_descs[i].sw_reg) { - desc->ops = &pfuze100_sw_disable_regulator_ops; - desc->enable_val = 0x8; - desc->disable_val = 0x0; - desc->enable_time = 500; + if (pfuze_chip->chip_id == PFUZE100 || + pfuze_chip->chip_id == PFUZE200) { + if (pfuze_chip->regulator_descs[i].sw_reg) { + desc->ops = &pfuze100_sw_disable_regulator_ops; + desc->enable_val = 0x8; + desc->disable_val = 0x0; + desc->enable_time = 500; + } } } diff --git a/drivers/regulator/ti-abb-regulator.c b/drivers/regulator/ti-abb-regulator.c index 3e60bff76194..9f0a4d50cead 100644 --- a/drivers/regulator/ti-abb-regulator.c +++ b/drivers/regulator/ti-abb-regulator.c @@ -342,8 +342,17 @@ static int ti_abb_set_voltage_sel(struct regulator_dev *rdev, unsigned sel) return ret; } - /* If data is exactly the same, then just update index, no change */ info = &abb->info[sel]; + /* + * When Linux kernel is starting up, we are'nt sure of the + * Bias configuration that bootloader has configured. + * So, we get to know the actual setting the first time + * we are asked to transition. + */ + if (abb->current_info_idx == -EINVAL) + goto just_set_abb; + + /* If data is exactly the same, then just update index, no change */ oinfo = &abb->info[abb->current_info_idx]; if (!memcmp(info, oinfo, sizeof(*info))) { dev_dbg(dev, "%s: Same data new idx=%d, old idx=%d\n", __func__, @@ -351,6 +360,7 @@ static int ti_abb_set_voltage_sel(struct regulator_dev *rdev, unsigned sel) goto out; } +just_set_abb: ret = ti_abb_set_opp(rdev, abb, info); out: diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index eb17fea8075c..217a7b84abdf 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -2980,6 +2980,12 @@ static int _dasd_requeue_request(struct dasd_ccw_req *cqr) if (!block) return -EINVAL; + /* + * If the request is an ERP request there is nothing to requeue. + * This will be done with the remaining original request. + */ + if (cqr->refers) + return 0; spin_lock_irq(&cqr->dq->lock); req = (struct request *) cqr->callback_data; blk_mq_requeue_request(req, false); diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index 485cbfcbf06e..ef738b42a092 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -680,7 +680,10 @@ static int ap_device_probe(struct device *dev) { struct ap_device *ap_dev = to_ap_dev(dev); struct ap_driver *ap_drv = to_ap_drv(dev->driver); - int card, queue, devres, drvres, rc; + int card, queue, devres, drvres, rc = -ENODEV; + + if (!get_device(dev)) + return rc; if (is_queue_dev(dev)) { /* @@ -697,7 +700,7 @@ static int ap_device_probe(struct device *dev) mutex_unlock(&ap_perms_mutex); drvres = ap_drv->flags & AP_DRIVER_FLAG_DEFAULT; if (!!devres != !!drvres) - return -ENODEV; + goto out; } /* Add queue/card to list of active queues/cards */ @@ -718,6 +721,9 @@ static int ap_device_probe(struct device *dev) ap_dev->drv = NULL; } +out: + if (rc) + put_device(dev); return rc; } @@ -744,6 +750,8 @@ static int ap_device_remove(struct device *dev) hash_del(&to_ap_queue(dev)->hnode); spin_unlock_bh(&ap_queues_lock); + put_device(dev); + return 0; } @@ -1371,6 +1379,8 @@ static inline void ap_scan_domains(struct ap_card *ac) __func__, ac->id, dom); goto put_dev_and_continue; } + /* get it and thus adjust reference counter */ + get_device(dev); if (decfg) AP_DBF_INFO("%s(%d,%d) new (decfg) queue device created\n", __func__, ac->id, dom); diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c index 99cb60ea663d..dd84995049b9 100644 --- a/drivers/s390/crypto/pkey_api.c +++ b/drivers/s390/crypto/pkey_api.c @@ -35,9 +35,6 @@ MODULE_DESCRIPTION("s390 protected key interface"); #define PROTKEYBLOBBUFSIZE 256 /* protected key buffer size used internal */ #define MAXAPQNSINLIST 64 /* max 64 apqns within a apqn list */ -/* mask of available pckmo subfunctions, fetched once at module init */ -static cpacf_mask_t pckmo_functions; - /* * debug feature data and functions */ @@ -91,6 +88,9 @@ static int pkey_clr2protkey(u32 keytype, const struct pkey_clrkey *clrkey, struct pkey_protkey *protkey) { + /* mask of available pckmo subfunctions */ + static cpacf_mask_t pckmo_functions; + long fc; int keysize; u8 paramblock[64]; @@ -114,11 +114,13 @@ static int pkey_clr2protkey(u32 keytype, return -EINVAL; } - /* - * Check if the needed pckmo subfunction is available. - * These subfunctions can be enabled/disabled by customers - * in the LPAR profile or may even change on the fly. - */ + /* Did we already check for PCKMO ? */ + if (!pckmo_functions.bytes[0]) { + /* no, so check now */ + if (!cpacf_query(CPACF_PCKMO, &pckmo_functions)) + return -ENODEV; + } + /* check for the pckmo subfunction we need now */ if (!cpacf_test_func(&pckmo_functions, fc)) { DEBUG_ERR("%s pckmo functions not available\n", __func__); return -ENODEV; @@ -2058,7 +2060,7 @@ static struct miscdevice pkey_dev = { */ static int __init pkey_init(void) { - cpacf_mask_t kmc_functions; + cpacf_mask_t func_mask; /* * The pckmo instruction should be available - even if we don't @@ -2066,15 +2068,15 @@ static int __init pkey_init(void) * is also the minimum level for the kmc instructions which * are able to work with protected keys. */ - if (!cpacf_query(CPACF_PCKMO, &pckmo_functions)) + if (!cpacf_query(CPACF_PCKMO, &func_mask)) return -ENODEV; /* check for kmc instructions available */ - if (!cpacf_query(CPACF_KMC, &kmc_functions)) + if (!cpacf_query(CPACF_KMC, &func_mask)) return -ENODEV; - if (!cpacf_test_func(&kmc_functions, CPACF_KMC_PAES_128) || - !cpacf_test_func(&kmc_functions, CPACF_KMC_PAES_192) || - !cpacf_test_func(&kmc_functions, CPACF_KMC_PAES_256)) + if (!cpacf_test_func(&func_mask, CPACF_KMC_PAES_128) || + !cpacf_test_func(&func_mask, CPACF_KMC_PAES_192) || + !cpacf_test_func(&func_mask, CPACF_KMC_PAES_256)) return -ENODEV; pkey_debug_init(); diff --git a/drivers/s390/crypto/zcrypt_card.c b/drivers/s390/crypto/zcrypt_card.c index e342eb86acd1..33b23884b133 100644 --- a/drivers/s390/crypto/zcrypt_card.c +++ b/drivers/s390/crypto/zcrypt_card.c @@ -157,11 +157,6 @@ int zcrypt_card_register(struct zcrypt_card *zc) { int rc; - rc = sysfs_create_group(&zc->card->ap_dev.device.kobj, - &zcrypt_card_attr_group); - if (rc) - return rc; - spin_lock(&zcrypt_list_lock); list_add_tail(&zc->list, &zcrypt_card_list); spin_unlock(&zcrypt_list_lock); @@ -170,6 +165,14 @@ int zcrypt_card_register(struct zcrypt_card *zc) ZCRYPT_DBF(DBF_INFO, "card=%02x register online=1\n", zc->card->id); + rc = sysfs_create_group(&zc->card->ap_dev.device.kobj, + &zcrypt_card_attr_group); + if (rc) { + spin_lock(&zcrypt_list_lock); + list_del_init(&zc->list); + spin_unlock(&zcrypt_list_lock); + } + return rc; } EXPORT_SYMBOL(zcrypt_card_register); diff --git a/drivers/s390/crypto/zcrypt_queue.c b/drivers/s390/crypto/zcrypt_queue.c index 3c207066313c..5062eae73d4a 100644 --- a/drivers/s390/crypto/zcrypt_queue.c +++ b/drivers/s390/crypto/zcrypt_queue.c @@ -180,7 +180,6 @@ int zcrypt_queue_register(struct zcrypt_queue *zq) &zcrypt_queue_attr_group); if (rc) goto out; - get_device(&zq->queue->ap_dev.device); if (zq->ops->rng) { rc = zcrypt_rng_device_add(); @@ -192,7 +191,6 @@ int zcrypt_queue_register(struct zcrypt_queue *zq) out_unregister: sysfs_remove_group(&zq->queue->ap_dev.device.kobj, &zcrypt_queue_attr_group); - put_device(&zq->queue->ap_dev.device); out: spin_lock(&zcrypt_list_lock); list_del_init(&zq->list); @@ -220,12 +218,10 @@ void zcrypt_queue_unregister(struct zcrypt_queue *zq) list_del_init(&zq->list); zcrypt_device_count--; spin_unlock(&zcrypt_list_lock); - zcrypt_card_put(zc); if (zq->ops->rng) zcrypt_rng_device_remove(); sysfs_remove_group(&zq->queue->ap_dev.device.kobj, &zcrypt_queue_attr_group); - put_device(&zq->queue->ap_dev.device); - zcrypt_queue_put(zq); + zcrypt_card_put(zc); } EXPORT_SYMBOL(zcrypt_queue_unregister); diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c index f32da0ca529e..308bda2e9c00 100644 --- a/drivers/scsi/device_handler/scsi_dh_alua.c +++ b/drivers/scsi/device_handler/scsi_dh_alua.c @@ -658,8 +658,8 @@ static int alua_rtpg(struct scsi_device *sdev, struct alua_port_group *pg) rcu_read_lock(); list_for_each_entry_rcu(h, &tmp_pg->dh_list, node) { - /* h->sdev should always be valid */ - BUG_ON(!h->sdev); + if (!h->sdev) + continue; h->sdev->access_state = desc[0]; } rcu_read_unlock(); @@ -705,7 +705,8 @@ static int alua_rtpg(struct scsi_device *sdev, struct alua_port_group *pg) pg->expiry = 0; rcu_read_lock(); list_for_each_entry_rcu(h, &pg->dh_list, node) { - BUG_ON(!h->sdev); + if (!h->sdev) + continue; h->sdev->access_state = (pg->state & SCSI_ACCESS_STATE_MASK); if (pg->pref) @@ -1147,7 +1148,6 @@ static void alua_bus_detach(struct scsi_device *sdev) spin_lock(&h->pg_lock); pg = rcu_dereference_protected(h->pg, lockdep_is_held(&h->pg_lock)); rcu_assign_pointer(h->pg, NULL); - h->sdev = NULL; spin_unlock(&h->pg_lock); if (pg) { spin_lock_irq(&pg->lock); @@ -1156,6 +1156,7 @@ static void alua_bus_detach(struct scsi_device *sdev) kref_put(&pg->kref, release_port_group); } sdev->handler_data = NULL; + synchronize_rcu(); kfree(h); } diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index 83ce4f11a589..8df70c92911d 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -8855,7 +8855,7 @@ reinit_after_soft_reset: /* hook into SCSI subsystem */ rc = hpsa_scsi_add_host(h); if (rc) - goto clean7; /* perf, sg, cmd, irq, shost, pci, lu, aer/h */ + goto clean8; /* lastlogicals, perf, sg, cmd, irq, shost, pci, lu, aer/h */ /* Monitor the controller for firmware lockups */ h->heartbeat_sample_interval = HEARTBEAT_SAMPLE_INTERVAL; @@ -8870,6 +8870,8 @@ reinit_after_soft_reset: HPSA_EVENT_MONITOR_INTERVAL); return 0; +clean8: /* lastlogicals, perf, sg, cmd, irq, shost, pci, lu, aer/h */ + kfree(h->lastlogicals); clean7: /* perf, sg, cmd, irq, shost, pci, lu, aer/h */ hpsa_free_performant_mode(h); h->access.set_intr_mask(h, HPSA_INTR_OFF); diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index 1e9c3171fa9f..f9314f1393fb 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -533,8 +533,8 @@ static void iscsi_complete_task(struct iscsi_task *task, int state) if (conn->task == task) conn->task = NULL; - if (conn->ping_task == task) - conn->ping_task = NULL; + if (READ_ONCE(conn->ping_task) == task) + WRITE_ONCE(conn->ping_task, NULL); /* release get from queueing */ __iscsi_put_task(task); @@ -738,6 +738,9 @@ __iscsi_conn_send_pdu(struct iscsi_conn *conn, struct iscsi_hdr *hdr, task->conn->session->age); } + if (unlikely(READ_ONCE(conn->ping_task) == INVALID_SCSI_TASK)) + WRITE_ONCE(conn->ping_task, task); + if (!ihost->workq) { if (iscsi_prep_mgmt_task(conn, task)) goto free_task; @@ -941,8 +944,11 @@ static int iscsi_send_nopout(struct iscsi_conn *conn, struct iscsi_nopin *rhdr) struct iscsi_nopout hdr; struct iscsi_task *task; - if (!rhdr && conn->ping_task) - return -EINVAL; + if (!rhdr) { + if (READ_ONCE(conn->ping_task)) + return -EINVAL; + WRITE_ONCE(conn->ping_task, INVALID_SCSI_TASK); + } memset(&hdr, 0, sizeof(struct iscsi_nopout)); hdr.opcode = ISCSI_OP_NOOP_OUT | ISCSI_OP_IMMEDIATE; @@ -957,11 +963,12 @@ static int iscsi_send_nopout(struct iscsi_conn *conn, struct iscsi_nopin *rhdr) task = __iscsi_conn_send_pdu(conn, (struct iscsi_hdr *)&hdr, NULL, 0); if (!task) { + if (!rhdr) + WRITE_ONCE(conn->ping_task, NULL); iscsi_conn_printk(KERN_ERR, conn, "Could not send nopout\n"); return -EIO; } else if (!rhdr) { /* only track our nops */ - conn->ping_task = task; conn->last_ping = jiffies; } @@ -984,7 +991,7 @@ static int iscsi_nop_out_rsp(struct iscsi_task *task, struct iscsi_conn *conn = task->conn; int rc = 0; - if (conn->ping_task != task) { + if (READ_ONCE(conn->ping_task) != task) { /* * If this is not in response to one of our * nops then it must be from userspace. @@ -1923,7 +1930,7 @@ static void iscsi_start_tx(struct iscsi_conn *conn) */ static int iscsi_has_ping_timed_out(struct iscsi_conn *conn) { - if (conn->ping_task && + if (READ_ONCE(conn->ping_task) && time_before_eq(conn->last_recv + (conn->recv_timeout * HZ) + (conn->ping_timeout * HZ), jiffies)) return 1; @@ -2058,7 +2065,7 @@ enum blk_eh_timer_return iscsi_eh_cmd_timed_out(struct scsi_cmnd *sc) * Checking the transport already or nop from a cmd timeout still * running */ - if (conn->ping_task) { + if (READ_ONCE(conn->ping_task)) { task->have_checked_conn = true; rc = BLK_EH_RESET_TIMER; goto done; diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 93230cd1982f..e4cc92bc4d94 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -1740,6 +1740,13 @@ _base_irqpoll(struct irq_poll *irqpoll, int budget) reply_q->irq_poll_scheduled = false; reply_q->irq_line_enable = true; enable_irq(reply_q->os_irq); + /* + * Go for one more round of processing the + * reply descriptor post queue incase if HBA + * Firmware has posted some reply descriptors + * while reenabling the IRQ. + */ + _base_process_reply_queue(reply_q); } return num_entries; diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index b8f573a02713..7a160b86adc6 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -1627,12 +1627,12 @@ start: */ fallthrough; case CLKS_OFF: - ufshcd_scsi_block_requests(hba); hba->clk_gating.state = REQ_CLKS_ON; trace_ufshcd_clk_gating(dev_name(hba->dev), hba->clk_gating.state); - queue_work(hba->clk_gating.clk_gating_workq, - &hba->clk_gating.ungate_work); + if (queue_work(hba->clk_gating.clk_gating_workq, + &hba->clk_gating.ungate_work)) + ufshcd_scsi_block_requests(hba); /* * fall through to check if we should wait for this * work to be done or not. @@ -2115,10 +2115,20 @@ ufshcd_wait_for_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd) unsigned long flags; if (wait_for_completion_timeout(&uic_cmd->done, - msecs_to_jiffies(UIC_CMD_TIMEOUT))) + msecs_to_jiffies(UIC_CMD_TIMEOUT))) { ret = uic_cmd->argument2 & MASK_UIC_COMMAND_RESULT; - else + } else { ret = -ETIMEDOUT; + dev_err(hba->dev, + "uic cmd 0x%x with arg3 0x%x completion timeout\n", + uic_cmd->command, uic_cmd->argument3); + + if (!uic_cmd->cmd_active) { + dev_err(hba->dev, "%s: UIC cmd has been completed, return the result\n", + __func__); + ret = uic_cmd->argument2 & MASK_UIC_COMMAND_RESULT; + } + } spin_lock_irqsave(hba->host->host_lock, flags); hba->active_uic_cmd = NULL; @@ -2150,6 +2160,7 @@ __ufshcd_send_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd, if (completion) init_completion(&uic_cmd->done); + uic_cmd->cmd_active = 1; ufshcd_dispatch_uic_cmd(hba, uic_cmd); return 0; @@ -3807,10 +3818,18 @@ static int ufshcd_uic_pwr_ctrl(struct ufs_hba *hba, struct uic_command *cmd) dev_err(hba->dev, "pwr ctrl cmd 0x%x with mode 0x%x completion timeout\n", cmd->command, cmd->argument3); + + if (!cmd->cmd_active) { + dev_err(hba->dev, "%s: Power Mode Change operation has been completed, go check UPMCRS\n", + __func__); + goto check_upmcrs; + } + ret = -ETIMEDOUT; goto out; } +check_upmcrs: status = ufshcd_get_upmcrs(hba); if (status != PWR_LOCAL) { dev_err(hba->dev, @@ -4902,11 +4921,14 @@ static irqreturn_t ufshcd_uic_cmd_compl(struct ufs_hba *hba, u32 intr_status) ufshcd_get_uic_cmd_result(hba); hba->active_uic_cmd->argument3 = ufshcd_get_dme_attr_val(hba); + if (!hba->uic_async_done) + hba->active_uic_cmd->cmd_active = 0; complete(&hba->active_uic_cmd->done); retval = IRQ_HANDLED; } if ((intr_status & UFSHCD_UIC_PWR_MASK) && hba->uic_async_done) { + hba->active_uic_cmd->cmd_active = 0; complete(hba->uic_async_done); retval = IRQ_HANDLED; } @@ -8906,6 +8928,7 @@ void ufshcd_remove(struct ufs_hba *hba) blk_mq_free_tag_set(&hba->tmf_tag_set); blk_cleanup_queue(hba->cmd_queue); scsi_remove_host(hba->host); + destroy_workqueue(hba->eh_wq); /* disable interrupts */ ufshcd_disable_intr(hba, hba->intr_mask); ufshcd_hba_stop(hba); @@ -9206,6 +9229,7 @@ out_remove_scsi_host: exit_gating: ufshcd_exit_clk_scaling(hba); ufshcd_exit_clk_gating(hba); + destroy_workqueue(hba->eh_wq); out_disable: hba->is_irq_enabled = false; ufshcd_hba_exit(hba); diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h index 47eb1430274c..e0f00a42371c 100644 --- a/drivers/scsi/ufs/ufshcd.h +++ b/drivers/scsi/ufs/ufshcd.h @@ -64,6 +64,7 @@ enum dev_cmd_type { * @argument1: UIC command argument 1 * @argument2: UIC command argument 2 * @argument3: UIC command argument 3 + * @cmd_active: Indicate if UIC command is outstanding * @done: UIC command completion */ struct uic_command { @@ -71,6 +72,7 @@ struct uic_command { u32 argument1; u32 argument2; u32 argument3; + int cmd_active; struct completion done; }; diff --git a/drivers/spi/spi-bcm-qspi.c b/drivers/spi/spi-bcm-qspi.c index 14c9d0133bce..c028446c7460 100644 --- a/drivers/spi/spi-bcm-qspi.c +++ b/drivers/spi/spi-bcm-qspi.c @@ -1327,7 +1327,7 @@ int bcm_qspi_probe(struct platform_device *pdev, data = of_id->data; - master = spi_alloc_master(dev, sizeof(struct bcm_qspi)); + master = devm_spi_alloc_master(dev, sizeof(struct bcm_qspi)); if (!master) { dev_err(dev, "error allocating spi_master\n"); return -ENOMEM; @@ -1367,21 +1367,17 @@ int bcm_qspi_probe(struct platform_device *pdev, if (res) { qspi->base[MSPI] = devm_ioremap_resource(dev, res); - if (IS_ERR(qspi->base[MSPI])) { - ret = PTR_ERR(qspi->base[MSPI]); - goto qspi_resource_err; - } + if (IS_ERR(qspi->base[MSPI])) + return PTR_ERR(qspi->base[MSPI]); } else { - goto qspi_resource_err; + return 0; } res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "bspi"); if (res) { qspi->base[BSPI] = devm_ioremap_resource(dev, res); - if (IS_ERR(qspi->base[BSPI])) { - ret = PTR_ERR(qspi->base[BSPI]); - goto qspi_resource_err; - } + if (IS_ERR(qspi->base[BSPI])) + return PTR_ERR(qspi->base[BSPI]); qspi->bspi_mode = true; } else { qspi->bspi_mode = false; @@ -1392,18 +1388,14 @@ int bcm_qspi_probe(struct platform_device *pdev, res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "cs_reg"); if (res) { qspi->base[CHIP_SELECT] = devm_ioremap_resource(dev, res); - if (IS_ERR(qspi->base[CHIP_SELECT])) { - ret = PTR_ERR(qspi->base[CHIP_SELECT]); - goto qspi_resource_err; - } + if (IS_ERR(qspi->base[CHIP_SELECT])) + return PTR_ERR(qspi->base[CHIP_SELECT]); } qspi->dev_ids = kcalloc(num_irqs, sizeof(struct bcm_qspi_dev_id), GFP_KERNEL); - if (!qspi->dev_ids) { - ret = -ENOMEM; - goto qspi_resource_err; - } + if (!qspi->dev_ids) + return -ENOMEM; for (val = 0; val < num_irqs; val++) { irq = -1; @@ -1484,7 +1476,7 @@ int bcm_qspi_probe(struct platform_device *pdev, qspi->xfer_mode.addrlen = -1; qspi->xfer_mode.hp = -1; - ret = devm_spi_register_master(&pdev->dev, master); + ret = spi_register_master(master); if (ret < 0) { dev_err(dev, "can't register master\n"); goto qspi_reg_err; @@ -1497,8 +1489,6 @@ qspi_reg_err: clk_disable_unprepare(qspi->clk); qspi_probe_err: kfree(qspi->dev_ids); -qspi_resource_err: - spi_master_put(master); return ret; } /* probe function to be called by SoC specific platform driver probe */ @@ -1508,10 +1498,10 @@ int bcm_qspi_remove(struct platform_device *pdev) { struct bcm_qspi *qspi = platform_get_drvdata(pdev); + spi_unregister_master(qspi->master); bcm_qspi_hw_uninit(qspi); clk_disable_unprepare(qspi->clk); kfree(qspi->dev_ids); - spi_unregister_master(qspi->master); return 0; } diff --git a/drivers/spi/spi-bcm2835.c b/drivers/spi/spi-bcm2835.c index b87116e9b413..197485f2c2b2 100644 --- a/drivers/spi/spi-bcm2835.c +++ b/drivers/spi/spi-bcm2835.c @@ -1193,7 +1193,6 @@ static int bcm2835_spi_setup(struct spi_device *spi) struct spi_controller *ctlr = spi->controller; struct bcm2835_spi *bs = spi_controller_get_devdata(ctlr); struct gpio_chip *chip; - enum gpio_lookup_flags lflags; u32 cs; /* @@ -1259,21 +1258,9 @@ static int bcm2835_spi_setup(struct spi_device *spi) if (!chip) return 0; - /* - * Retrieve the corresponding GPIO line used for CS. - * The inversion semantics will be handled by the GPIO core - * code, so we pass GPIOD_OUT_LOW for "unasserted" and - * the correct flag for inversion semantics. The SPI_CS_HIGH - * on spi->mode cannot be checked for polarity in this case - * as the flag use_gpio_descriptors enforces SPI_CS_HIGH. - */ - if (of_property_read_bool(spi->dev.of_node, "spi-cs-high")) - lflags = GPIO_ACTIVE_HIGH; - else - lflags = GPIO_ACTIVE_LOW; spi->cs_gpiod = gpiochip_request_own_desc(chip, 8 - spi->chip_select, DRV_NAME, - lflags, + GPIO_LOOKUP_FLAGS_DEFAULT, GPIOD_OUT_LOW); if (IS_ERR(spi->cs_gpiod)) return PTR_ERR(spi->cs_gpiod); @@ -1291,7 +1278,7 @@ static int bcm2835_spi_probe(struct platform_device *pdev) struct bcm2835_spi *bs; int err; - ctlr = spi_alloc_master(&pdev->dev, ALIGN(sizeof(*bs), + ctlr = devm_spi_alloc_master(&pdev->dev, ALIGN(sizeof(*bs), dma_get_cache_alignment())); if (!ctlr) return -ENOMEM; @@ -1312,23 +1299,17 @@ static int bcm2835_spi_probe(struct platform_device *pdev) bs->ctlr = ctlr; bs->regs = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(bs->regs)) { - err = PTR_ERR(bs->regs); - goto out_controller_put; - } + if (IS_ERR(bs->regs)) + return PTR_ERR(bs->regs); bs->clk = devm_clk_get(&pdev->dev, NULL); - if (IS_ERR(bs->clk)) { - err = dev_err_probe(&pdev->dev, PTR_ERR(bs->clk), - "could not get clk\n"); - goto out_controller_put; - } + if (IS_ERR(bs->clk)) + return dev_err_probe(&pdev->dev, PTR_ERR(bs->clk), + "could not get clk\n"); bs->irq = platform_get_irq(pdev, 0); - if (bs->irq <= 0) { - err = bs->irq ? bs->irq : -ENODEV; - goto out_controller_put; - } + if (bs->irq <= 0) + return bs->irq ? bs->irq : -ENODEV; clk_prepare_enable(bs->clk); @@ -1362,8 +1343,6 @@ out_dma_release: bcm2835_dma_release(ctlr, bs); out_clk_disable: clk_disable_unprepare(bs->clk); -out_controller_put: - spi_controller_put(ctlr); return err; } diff --git a/drivers/spi/spi-bcm2835aux.c b/drivers/spi/spi-bcm2835aux.c index 03b034c15d2b..1a26865c42f8 100644 --- a/drivers/spi/spi-bcm2835aux.c +++ b/drivers/spi/spi-bcm2835aux.c @@ -494,7 +494,7 @@ static int bcm2835aux_spi_probe(struct platform_device *pdev) unsigned long clk_hz; int err; - master = spi_alloc_master(&pdev->dev, sizeof(*bs)); + master = devm_spi_alloc_master(&pdev->dev, sizeof(*bs)); if (!master) return -ENOMEM; @@ -524,29 +524,25 @@ static int bcm2835aux_spi_probe(struct platform_device *pdev) /* the main area */ bs->regs = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(bs->regs)) { - err = PTR_ERR(bs->regs); - goto out_master_put; - } + if (IS_ERR(bs->regs)) + return PTR_ERR(bs->regs); bs->clk = devm_clk_get(&pdev->dev, NULL); if (IS_ERR(bs->clk)) { err = PTR_ERR(bs->clk); dev_err(&pdev->dev, "could not get clk: %d\n", err); - goto out_master_put; + return err; } bs->irq = platform_get_irq(pdev, 0); - if (bs->irq <= 0) { - err = bs->irq ? bs->irq : -ENODEV; - goto out_master_put; - } + if (bs->irq <= 0) + return bs->irq ? bs->irq : -ENODEV; /* this also enables the HW block */ err = clk_prepare_enable(bs->clk); if (err) { dev_err(&pdev->dev, "could not prepare clock: %d\n", err); - goto out_master_put; + return err; } /* just checking if the clock returns a sane value */ @@ -581,8 +577,6 @@ static int bcm2835aux_spi_probe(struct platform_device *pdev) out_clk_disable: clk_disable_unprepare(bs->clk); -out_master_put: - spi_master_put(master); return err; } diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c index 40938cf3806d..ba7d40c2922f 100644 --- a/drivers/spi/spi-cadence-quadspi.c +++ b/drivers/spi/spi-cadence-quadspi.c @@ -1260,12 +1260,14 @@ static int cqspi_probe(struct platform_device *pdev) /* Obtain QSPI reset control */ rstc = devm_reset_control_get_optional_exclusive(dev, "qspi"); if (IS_ERR(rstc)) { + ret = PTR_ERR(rstc); dev_err(dev, "Cannot get QSPI reset.\n"); goto probe_reset_failed; } rstc_ocp = devm_reset_control_get_optional_exclusive(dev, "qspi-ocp"); if (IS_ERR(rstc_ocp)) { + ret = PTR_ERR(rstc_ocp); dev_err(dev, "Cannot get QSPI OCP reset.\n"); goto probe_reset_failed; } diff --git a/drivers/spi/spi-dw-core.c b/drivers/spi/spi-dw-core.c index 2e50cc0a9291..0b2236ade412 100644 --- a/drivers/spi/spi-dw-core.c +++ b/drivers/spi/spi-dw-core.c @@ -357,11 +357,11 @@ static void dw_spi_irq_setup(struct dw_spi *dws) dw_writel(dws, DW_SPI_TXFTLR, level); dw_writel(dws, DW_SPI_RXFTLR, level - 1); + dws->transfer_handler = dw_spi_transfer_handler; + imask = SPI_INT_TXEI | SPI_INT_TXOI | SPI_INT_RXUI | SPI_INT_RXOI | SPI_INT_RXFI; spi_umask_intr(dws, imask); - - dws->transfer_handler = dw_spi_transfer_handler; } /* diff --git a/drivers/spi/spi-fsi.c b/drivers/spi/spi-fsi.c index 8a440c7078ef..3920cd3286d8 100644 --- a/drivers/spi/spi-fsi.c +++ b/drivers/spi/spi-fsi.c @@ -477,7 +477,7 @@ static int fsi_spi_transfer_one_message(struct spi_controller *ctlr, rc = fsi_spi_check_mux(ctx->fsi, ctx->dev); if (rc) - return rc; + goto error; list_for_each_entry(transfer, &mesg->transfers, transfer_list) { struct fsi_spi_sequence seq; diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c index 3967afa465f0..1a08c1d584ab 100644 --- a/drivers/spi/spi-fsl-dspi.c +++ b/drivers/spi/spi-fsl-dspi.c @@ -1080,12 +1080,11 @@ MODULE_DEVICE_TABLE(of, fsl_dspi_dt_ids); #ifdef CONFIG_PM_SLEEP static int dspi_suspend(struct device *dev) { - struct spi_controller *ctlr = dev_get_drvdata(dev); - struct fsl_dspi *dspi = spi_controller_get_devdata(ctlr); + struct fsl_dspi *dspi = dev_get_drvdata(dev); if (dspi->irq) disable_irq(dspi->irq); - spi_controller_suspend(ctlr); + spi_controller_suspend(dspi->ctlr); clk_disable_unprepare(dspi->clk); pinctrl_pm_select_sleep_state(dev); @@ -1095,8 +1094,7 @@ static int dspi_suspend(struct device *dev) static int dspi_resume(struct device *dev) { - struct spi_controller *ctlr = dev_get_drvdata(dev); - struct fsl_dspi *dspi = spi_controller_get_devdata(ctlr); + struct fsl_dspi *dspi = dev_get_drvdata(dev); int ret; pinctrl_pm_select_default_state(dev); @@ -1104,7 +1102,7 @@ static int dspi_resume(struct device *dev) ret = clk_prepare_enable(dspi->clk); if (ret) return ret; - spi_controller_resume(ctlr); + spi_controller_resume(dspi->ctlr); if (dspi->irq) enable_irq(dspi->irq); diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c index 986b9793fd3c..a2886ee44e4c 100644 --- a/drivers/spi/spi-fsl-lpspi.c +++ b/drivers/spi/spi-fsl-lpspi.c @@ -938,9 +938,6 @@ static int fsl_lpspi_remove(struct platform_device *pdev) spi_controller_get_devdata(controller); pm_runtime_disable(fsl_lpspi->dev); - - spi_master_put(controller); - return 0; } diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c index 060b1f5c9b04..4b80e27ecdbf 100644 --- a/drivers/spi/spi-imx.c +++ b/drivers/spi/spi-imx.c @@ -1676,15 +1676,18 @@ static int spi_imx_probe(struct platform_device *pdev) goto out_master_put; } - pm_runtime_enable(spi_imx->dev); + ret = clk_prepare_enable(spi_imx->clk_per); + if (ret) + goto out_master_put; + + ret = clk_prepare_enable(spi_imx->clk_ipg); + if (ret) + goto out_put_per; + pm_runtime_set_autosuspend_delay(spi_imx->dev, MXC_RPM_TIMEOUT); pm_runtime_use_autosuspend(spi_imx->dev); - - ret = pm_runtime_get_sync(spi_imx->dev); - if (ret < 0) { - dev_err(spi_imx->dev, "failed to enable clock\n"); - goto out_runtime_pm_put; - } + pm_runtime_set_active(spi_imx->dev); + pm_runtime_enable(spi_imx->dev); spi_imx->spi_clk = clk_get_rate(spi_imx->clk_per); /* @@ -1722,8 +1725,12 @@ out_bitbang_start: spi_imx_sdma_exit(spi_imx); out_runtime_pm_put: pm_runtime_dont_use_autosuspend(spi_imx->dev); - pm_runtime_put_sync(spi_imx->dev); + pm_runtime_set_suspended(&pdev->dev); pm_runtime_disable(spi_imx->dev); + + clk_disable_unprepare(spi_imx->clk_ipg); +out_put_per: + clk_disable_unprepare(spi_imx->clk_per); out_master_put: spi_master_put(master); diff --git a/drivers/spi/spi-npcm-fiu.c b/drivers/spi/spi-npcm-fiu.c index 341f7cffeaac..1cb9329de945 100644 --- a/drivers/spi/spi-npcm-fiu.c +++ b/drivers/spi/spi-npcm-fiu.c @@ -679,7 +679,7 @@ static int npcm_fiu_probe(struct platform_device *pdev) struct resource *res; int id; - ctrl = spi_alloc_master(dev, sizeof(*fiu)); + ctrl = devm_spi_alloc_master(dev, sizeof(*fiu)); if (!ctrl) return -ENOMEM; diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 0cab239d8e7f..05c75f890ace 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -812,18 +812,16 @@ static void spi_set_cs(struct spi_device *spi, bool enable) enable = !enable; if (spi->cs_gpiod || gpio_is_valid(spi->cs_gpio)) { - /* - * Honour the SPI_NO_CS flag and invert the enable line, as - * active low is default for SPI. Execution paths that handle - * polarity inversion in gpiolib (such as device tree) will - * enforce active high using the SPI_CS_HIGH resulting in a - * double inversion through the code above. - */ if (!(spi->mode & SPI_NO_CS)) { if (spi->cs_gpiod) + /* polarity handled by gpiolib */ gpiod_set_value_cansleep(spi->cs_gpiod, - !enable); + enable1); else + /* + * invert the enable line, as active low is + * default for SPI. + */ gpio_set_value_cansleep(spi->cs_gpio, !enable); } /* Some SPI masters need both GPIO CS & slave_select */ @@ -1992,15 +1990,6 @@ static int of_spi_parse_dt(struct spi_controller *ctlr, struct spi_device *spi, } spi->chip_select = value; - /* - * For descriptors associated with the device, polarity inversion is - * handled in the gpiolib, so all gpio chip selects are "active high" - * in the logical sense, the gpiolib will invert the line if need be. - */ - if ((ctlr->use_gpio_descriptors) && ctlr->cs_gpiods && - ctlr->cs_gpiods[spi->chip_select]) - spi->mode |= SPI_CS_HIGH; - /* Device speed */ if (!of_property_read_u32(nc, "spi-max-frequency", &value)) spi->max_speed_hz = value; @@ -2453,6 +2442,49 @@ struct spi_controller *__spi_alloc_controller(struct device *dev, } EXPORT_SYMBOL_GPL(__spi_alloc_controller); +static void devm_spi_release_controller(struct device *dev, void *ctlr) +{ + spi_controller_put(*(struct spi_controller **)ctlr); +} + +/** + * __devm_spi_alloc_controller - resource-managed __spi_alloc_controller() + * @dev: physical device of SPI controller + * @size: how much zeroed driver-private data to allocate + * @slave: whether to allocate an SPI master (false) or SPI slave (true) + * Context: can sleep + * + * Allocate an SPI controller and automatically release a reference on it + * when @dev is unbound from its driver. Drivers are thus relieved from + * having to call spi_controller_put(). + * + * The arguments to this function are identical to __spi_alloc_controller(). + * + * Return: the SPI controller structure on success, else NULL. + */ +struct spi_controller *__devm_spi_alloc_controller(struct device *dev, + unsigned int size, + bool slave) +{ + struct spi_controller **ptr, *ctlr; + + ptr = devres_alloc(devm_spi_release_controller, sizeof(*ptr), + GFP_KERNEL); + if (!ptr) + return NULL; + + ctlr = __spi_alloc_controller(dev, size, slave); + if (ctlr) { + *ptr = ctlr; + devres_add(dev, ptr); + } else { + devres_free(ptr); + } + + return ctlr; +} +EXPORT_SYMBOL_GPL(__devm_spi_alloc_controller); + #ifdef CONFIG_OF static int of_spi_get_gpio_numbers(struct spi_controller *ctlr) { @@ -2789,6 +2821,11 @@ int devm_spi_register_controller(struct device *dev, } EXPORT_SYMBOL_GPL(devm_spi_register_controller); +static int devm_spi_match_controller(struct device *dev, void *res, void *ctlr) +{ + return *(struct spi_controller **)res == ctlr; +} + static int __unregister(struct device *dev, void *null) { spi_unregister_device(to_spi_device(dev)); @@ -2830,7 +2867,15 @@ void spi_unregister_controller(struct spi_controller *ctlr) list_del(&ctlr->list); mutex_unlock(&board_lock); - device_unregister(&ctlr->dev); + 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 (!devres_find(ctlr->dev.parent, devm_spi_release_controller, + devm_spi_match_controller, ctlr)) + put_device(&ctlr->dev); + /* free bus id */ mutex_lock(&board_lock); if (found == ctlr) diff --git a/drivers/staging/mt7621-pci/pci-mt7621.c b/drivers/staging/mt7621-pci/pci-mt7621.c index f961b353c22e..8831db383fad 100644 --- a/drivers/staging/mt7621-pci/pci-mt7621.c +++ b/drivers/staging/mt7621-pci/pci-mt7621.c @@ -653,16 +653,11 @@ static int mt7621_pcie_init_virtual_bridges(struct mt7621_pcie *pcie) return 0; } -static int mt7621_pcie_request_resources(struct mt7621_pcie *pcie, - struct list_head *res) +static void mt7621_pcie_add_resources(struct mt7621_pcie *pcie, + struct list_head *res) { - struct device *dev = pcie->dev; - pci_add_resource_offset(res, &pcie->io, pcie->offset.io); pci_add_resource_offset(res, &pcie->mem, pcie->offset.mem); - pci_add_resource(res, &pcie->busn); - - return devm_request_pci_bus_resources(dev, res); } static int mt7621_pcie_register_host(struct pci_host_bridge *host, @@ -738,11 +733,7 @@ static int mt7621_pci_probe(struct platform_device *pdev) setup_cm_memory_region(pcie); - err = mt7621_pcie_request_resources(pcie, &res); - if (err) { - dev_err(dev, "Error requesting resources\n"); - return err; - } + mt7621_pcie_add_resources(pcie, &res); err = mt7621_pcie_register_host(bridge, &res); if (err) { diff --git a/drivers/staging/ralink-gdma/Kconfig b/drivers/staging/ralink-gdma/Kconfig index 54e8029e6b1a..0017376234e2 100644 --- a/drivers/staging/ralink-gdma/Kconfig +++ b/drivers/staging/ralink-gdma/Kconfig @@ -2,6 +2,7 @@ config DMA_RALINK tristate "RALINK DMA support" depends on RALINK && !SOC_RT288X + depends on DMADEVICES select DMA_ENGINE select DMA_VIRTUAL_CHANNELS diff --git a/drivers/staging/rtl8723bs/os_dep/sdio_intf.c b/drivers/staging/rtl8723bs/os_dep/sdio_intf.c index 79b55ec827a4..b2208e5f190a 100644 --- a/drivers/staging/rtl8723bs/os_dep/sdio_intf.c +++ b/drivers/staging/rtl8723bs/os_dep/sdio_intf.c @@ -20,6 +20,7 @@ static const struct sdio_device_id sdio_ids[] = { { SDIO_DEVICE(0x024c, 0x0525), }, { SDIO_DEVICE(0x024c, 0x0623), }, { SDIO_DEVICE(0x024c, 0x0626), }, + { SDIO_DEVICE(0x024c, 0x0627), }, { SDIO_DEVICE(0x024c, 0xb723), }, { /* end: all zeroes */ }, }; diff --git a/drivers/staging/wfx/Documentation/devicetree/bindings/net/wireless/silabs,wfx.yaml b/drivers/staging/wfx/Documentation/devicetree/bindings/net/wireless/silabs,wfx.yaml index 43b5630c0407..510edd12ed19 100644 --- a/drivers/staging/wfx/Documentation/devicetree/bindings/net/wireless/silabs,wfx.yaml +++ b/drivers/staging/wfx/Documentation/devicetree/bindings/net/wireless/silabs,wfx.yaml @@ -24,7 +24,7 @@ description: In addition, it is recommended to declare a mmc-pwrseq on SDIO host above WFx. Without it, you may encounter issues with warm boot. The mmc-pwrseq should be compatible with mmc-pwrseq-simple. Please consult - Documentation/devicetree/bindings/mmc/mmc-pwrseq-simple.txt for more + Documentation/devicetree/bindings/mmc/mmc-pwrseq-simple.yaml for more information. For SPI':' diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index f77e5eee6b80..518fac4864cf 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -483,8 +483,7 @@ EXPORT_SYMBOL(iscsit_queue_rsp); void iscsit_aborted_task(struct iscsi_conn *conn, struct iscsi_cmd *cmd) { spin_lock_bh(&conn->cmd_lock); - if (!list_empty(&cmd->i_conn_node) && - !(cmd->se_cmd.transport_state & CMD_T_FABRIC_STOP)) + if (!list_empty(&cmd->i_conn_node)) list_del_init(&cmd->i_conn_node); spin_unlock_bh(&conn->cmd_lock); @@ -4083,12 +4082,22 @@ static void iscsit_release_commands_from_conn(struct iscsi_conn *conn) spin_lock_bh(&conn->cmd_lock); list_splice_init(&conn->conn_cmd_list, &tmp_list); - list_for_each_entry(cmd, &tmp_list, i_conn_node) { + list_for_each_entry_safe(cmd, cmd_tmp, &tmp_list, i_conn_node) { struct se_cmd *se_cmd = &cmd->se_cmd; if (se_cmd->se_tfo != NULL) { spin_lock_irq(&se_cmd->t_state_lock); - se_cmd->transport_state |= CMD_T_FABRIC_STOP; + if (se_cmd->transport_state & CMD_T_ABORTED) { + /* + * LIO's abort path owns the cleanup for this, + * so put it back on the list and let + * aborted_task handle it. + */ + list_move_tail(&cmd->i_conn_node, + &conn->conn_cmd_list); + } else { + se_cmd->transport_state |= CMD_T_FABRIC_STOP; + } spin_unlock_irq(&se_cmd->t_state_lock); } } diff --git a/drivers/tee/amdtee/amdtee_private.h b/drivers/tee/amdtee/amdtee_private.h index d7f798c3394b..337c8d82f74e 100644 --- a/drivers/tee/amdtee/amdtee_private.h +++ b/drivers/tee/amdtee/amdtee_private.h @@ -64,9 +64,13 @@ struct amdtee_session { /** * struct amdtee_context_data - AMD-TEE driver context data * @sess_list: Keeps track of sessions opened in current TEE context + * @shm_list: Keeps track of buffers allocated and mapped in current TEE + * context */ struct amdtee_context_data { struct list_head sess_list; + struct list_head shm_list; + struct mutex shm_mutex; /* synchronizes access to @shm_list */ }; struct amdtee_driver_data { @@ -89,10 +93,6 @@ struct amdtee_shm_data { u32 buf_id; }; -struct amdtee_shm_context { - struct list_head shmdata_list; -}; - #define LOWER_TWO_BYTE_MASK 0x0000FFFF /** diff --git a/drivers/tee/amdtee/core.c b/drivers/tee/amdtee/core.c index 27b4cd77d0db..8a6a8f30bb42 100644 --- a/drivers/tee/amdtee/core.c +++ b/drivers/tee/amdtee/core.c @@ -20,7 +20,6 @@ static struct amdtee_driver_data *drv_data; static DEFINE_MUTEX(session_list_mutex); -static struct amdtee_shm_context shmctx; static void amdtee_get_version(struct tee_device *teedev, struct tee_ioctl_version_data *vers) @@ -42,7 +41,8 @@ static int amdtee_open(struct tee_context *ctx) return -ENOMEM; INIT_LIST_HEAD(&ctxdata->sess_list); - INIT_LIST_HEAD(&shmctx.shmdata_list); + INIT_LIST_HEAD(&ctxdata->shm_list); + mutex_init(&ctxdata->shm_mutex); ctx->data = ctxdata; return 0; @@ -86,6 +86,7 @@ static void amdtee_release(struct tee_context *ctx) list_del(&sess->list_node); release_session(sess); } + mutex_destroy(&ctxdata->shm_mutex); kfree(ctxdata); ctx->data = NULL; @@ -152,14 +153,17 @@ static struct amdtee_session *find_session(struct amdtee_context_data *ctxdata, u32 get_buffer_id(struct tee_shm *shm) { - u32 buf_id = 0; + struct amdtee_context_data *ctxdata = shm->ctx->data; struct amdtee_shm_data *shmdata; + u32 buf_id = 0; - list_for_each_entry(shmdata, &shmctx.shmdata_list, shm_node) + mutex_lock(&ctxdata->shm_mutex); + list_for_each_entry(shmdata, &ctxdata->shm_list, shm_node) if (shmdata->kaddr == shm->kaddr) { buf_id = shmdata->buf_id; break; } + mutex_unlock(&ctxdata->shm_mutex); return buf_id; } @@ -333,8 +337,9 @@ int amdtee_close_session(struct tee_context *ctx, u32 session) int amdtee_map_shmem(struct tee_shm *shm) { - struct shmem_desc shmem; + struct amdtee_context_data *ctxdata; struct amdtee_shm_data *shmnode; + struct shmem_desc shmem; int rc, count; u32 buf_id; @@ -362,7 +367,10 @@ int amdtee_map_shmem(struct tee_shm *shm) shmnode->kaddr = shm->kaddr; shmnode->buf_id = buf_id; - list_add(&shmnode->shm_node, &shmctx.shmdata_list); + ctxdata = shm->ctx->data; + mutex_lock(&ctxdata->shm_mutex); + list_add(&shmnode->shm_node, &ctxdata->shm_list); + mutex_unlock(&ctxdata->shm_mutex); pr_debug("buf_id :[%x] kaddr[%p]\n", shmnode->buf_id, shmnode->kaddr); @@ -371,6 +379,7 @@ int amdtee_map_shmem(struct tee_shm *shm) void amdtee_unmap_shmem(struct tee_shm *shm) { + struct amdtee_context_data *ctxdata; struct amdtee_shm_data *shmnode; u32 buf_id; @@ -381,12 +390,15 @@ void amdtee_unmap_shmem(struct tee_shm *shm) /* Unmap the shared memory from TEE */ handle_unmap_shmem(buf_id); - list_for_each_entry(shmnode, &shmctx.shmdata_list, shm_node) + ctxdata = shm->ctx->data; + mutex_lock(&ctxdata->shm_mutex); + list_for_each_entry(shmnode, &ctxdata->shm_list, shm_node) if (buf_id == shmnode->buf_id) { list_del(&shmnode->shm_node); kfree(shmnode); break; } + mutex_unlock(&ctxdata->shm_mutex); } int amdtee_invoke_func(struct tee_context *ctx, diff --git a/drivers/thermal/ti-soc-thermal/ti-bandgap.c b/drivers/thermal/ti-soc-thermal/ti-bandgap.c index 5e596168ba73..dcac99f327b0 100644 --- a/drivers/thermal/ti-soc-thermal/ti-bandgap.c +++ b/drivers/thermal/ti-soc-thermal/ti-bandgap.c @@ -20,6 +20,7 @@ #include <linux/err.h> #include <linux/types.h> #include <linux/spinlock.h> +#include <linux/sys_soc.h> #include <linux/reboot.h> #include <linux/of_device.h> #include <linux/of_platform.h> @@ -864,6 +865,17 @@ static struct ti_bandgap *ti_bandgap_build(struct platform_device *pdev) return bgp; } +/* + * List of SoCs on which the CPU PM notifier can cause erros on the DTEMP + * readout. + * Enabled notifier on these machines results in erroneous, random values which + * could trigger unexpected thermal shutdown. + */ +static const struct soc_device_attribute soc_no_cpu_notifier[] = { + { .machine = "OMAP4430" }, + { /* sentinel */ }, +}; + /*** Device driver call backs ***/ static @@ -1020,7 +1032,8 @@ int ti_bandgap_probe(struct platform_device *pdev) #ifdef CONFIG_PM_SLEEP bgp->nb.notifier_call = bandgap_omap_cpu_notifier; - cpu_pm_register_notifier(&bgp->nb); + if (!soc_device_match(soc_no_cpu_notifier)) + cpu_pm_register_notifier(&bgp->nb); #endif return 0; @@ -1056,7 +1069,8 @@ int ti_bandgap_remove(struct platform_device *pdev) struct ti_bandgap *bgp = platform_get_drvdata(pdev); int i; - cpu_pm_unregister_notifier(&bgp->nb); + if (!soc_device_match(soc_no_cpu_notifier)) + cpu_pm_unregister_notifier(&bgp->nb); /* Remove sensor interfaces */ for (i = 0; i < bgp->conf->sensor_count; i++) { diff --git a/drivers/thunderbolt/debugfs.c b/drivers/thunderbolt/debugfs.c index 3680b2784ea1..ed65d2b13964 100644 --- a/drivers/thunderbolt/debugfs.c +++ b/drivers/thunderbolt/debugfs.c @@ -9,6 +9,7 @@ #include <linux/debugfs.h> #include <linux/pm_runtime.h> +#include <linux/uaccess.h> #include "tb.h" diff --git a/drivers/thunderbolt/icm.c b/drivers/thunderbolt/icm.c index b51fc3f62b1f..977ba91f4d0e 100644 --- a/drivers/thunderbolt/icm.c +++ b/drivers/thunderbolt/icm.c @@ -2284,6 +2284,8 @@ struct tb *icm_probe(struct tb_nhi *nhi) case PCI_DEVICE_ID_INTEL_TGL_NHI0: case PCI_DEVICE_ID_INTEL_TGL_NHI1: + case PCI_DEVICE_ID_INTEL_TGL_H_NHI0: + case PCI_DEVICE_ID_INTEL_TGL_H_NHI1: icm->is_supported = icm_tgl_is_supported; icm->driver_ready = icm_icl_driver_ready; icm->set_uuid = icm_icl_set_uuid; diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c index 3f79baa54829..db80dc5dfeba 100644 --- a/drivers/thunderbolt/nhi.c +++ b/drivers/thunderbolt/nhi.c @@ -406,12 +406,23 @@ static int ring_request_msix(struct tb_ring *ring, bool no_suspend) ring->vector = ret; - ring->irq = pci_irq_vector(ring->nhi->pdev, ring->vector); - if (ring->irq < 0) - return ring->irq; + ret = pci_irq_vector(ring->nhi->pdev, ring->vector); + if (ret < 0) + goto err_ida_remove; + + ring->irq = ret; irqflags = no_suspend ? IRQF_NO_SUSPEND : 0; - return request_irq(ring->irq, ring_msix, irqflags, "thunderbolt", ring); + ret = request_irq(ring->irq, ring_msix, irqflags, "thunderbolt", ring); + if (ret) + goto err_ida_remove; + + return 0; + +err_ida_remove: + ida_simple_remove(&nhi->msix_ida, ring->vector); + + return ret; } static void ring_release_msix(struct tb_ring *ring) @@ -1334,6 +1345,10 @@ static struct pci_device_id nhi_ids[] = { .driver_data = (kernel_ulong_t)&icl_nhi_ops }, { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_TGL_NHI1), .driver_data = (kernel_ulong_t)&icl_nhi_ops }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_TGL_H_NHI0), + .driver_data = (kernel_ulong_t)&icl_nhi_ops }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_TGL_H_NHI1), + .driver_data = (kernel_ulong_t)&icl_nhi_ops }, /* Any USB4 compliant host */ { PCI_DEVICE_CLASS(PCI_CLASS_SERIAL_USB_USB4, ~0) }, diff --git a/drivers/thunderbolt/nhi.h b/drivers/thunderbolt/nhi.h index 80162e4b013f..4e0861d75072 100644 --- a/drivers/thunderbolt/nhi.h +++ b/drivers/thunderbolt/nhi.h @@ -75,6 +75,8 @@ extern const struct tb_nhi_ops icl_nhi_ops; #define PCI_DEVICE_ID_INTEL_ICL_NHI0 0x8a17 #define PCI_DEVICE_ID_INTEL_TGL_NHI0 0x9a1b #define PCI_DEVICE_ID_INTEL_TGL_NHI1 0x9a1d +#define PCI_DEVICE_ID_INTEL_TGL_H_NHI0 0x9a1f +#define PCI_DEVICE_ID_INTEL_TGL_H_NHI1 0x9a21 #define PCI_CLASS_SERIAL_USB_USB4 0x0c0340 diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index a9995e21b916..8ea360b0ff77 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -784,6 +784,8 @@ static inline bool tb_switch_is_tiger_lake(const struct tb_switch *sw) switch (sw->config.device_id) { case PCI_DEVICE_ID_INTEL_TGL_NHI0: case PCI_DEVICE_ID_INTEL_TGL_NHI1: + case PCI_DEVICE_ID_INTEL_TGL_H_NHI0: + case PCI_DEVICE_ID_INTEL_TGL_H_NHI1: return true; } } diff --git a/drivers/thunderbolt/usb4.c b/drivers/thunderbolt/usb4.c index 40f13579a3fe..f2583b4053e4 100644 --- a/drivers/thunderbolt/usb4.c +++ b/drivers/thunderbolt/usb4.c @@ -421,8 +421,12 @@ int usb4_switch_set_wake(struct tb_switch *sw, unsigned int flags) * upstream USB4 port. */ tb_switch_for_each_port(sw, port) { + if (!tb_port_is_null(port)) + continue; if (!route && tb_is_upstream_port(port)) continue; + if (!port->cap_usb4) + continue; ret = tb_port_read(port, &val, TB_CFG_PORT, port->cap_usb4 + PORT_CS_19, 1); diff --git a/drivers/thunderbolt/xdomain.c b/drivers/thunderbolt/xdomain.c index 48907853732a..c00ad817042e 100644 --- a/drivers/thunderbolt/xdomain.c +++ b/drivers/thunderbolt/xdomain.c @@ -881,6 +881,7 @@ static void enumerate_services(struct tb_xdomain *xd) id = ida_simple_get(&xd->service_ids, 0, 0, GFP_KERNEL); if (id < 0) { + kfree(svc->key); kfree(svc); break; } diff --git a/drivers/tty/serial/8250/8250_mtk.c b/drivers/tty/serial/8250/8250_mtk.c index 41f4120abdf2..fa876e2c13e5 100644 --- a/drivers/tty/serial/8250/8250_mtk.c +++ b/drivers/tty/serial/8250/8250_mtk.c @@ -317,7 +317,7 @@ mtk8250_set_termios(struct uart_port *port, struct ktermios *termios, */ baud = tty_termios_baud_rate(termios); - serial8250_do_set_termios(port, termios, old); + serial8250_do_set_termios(port, termios, NULL); tty_termios_encode_baud_rate(termios, baud, baud); diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig index 1044fc387691..28f22e58639c 100644 --- a/drivers/tty/serial/Kconfig +++ b/drivers/tty/serial/Kconfig @@ -522,6 +522,7 @@ config SERIAL_IMX_EARLYCON depends on OF select SERIAL_EARLYCON select SERIAL_CORE_CONSOLE + default y if SERIAL_IMX_CONSOLE help If you have enabled the earlycon on the Freescale IMX CPU you can make it the earlycon by answering Y to this option. diff --git a/drivers/tty/serial/ar933x_uart.c b/drivers/tty/serial/ar933x_uart.c index 0c80a79d7442..c2be7cf91399 100644 --- a/drivers/tty/serial/ar933x_uart.c +++ b/drivers/tty/serial/ar933x_uart.c @@ -789,8 +789,10 @@ static int ar933x_uart_probe(struct platform_device *pdev) goto err_disable_clk; up->gpios = mctrl_gpio_init(port, 0); - if (IS_ERR(up->gpios) && PTR_ERR(up->gpios) != -ENOSYS) - return PTR_ERR(up->gpios); + if (IS_ERR(up->gpios) && PTR_ERR(up->gpios) != -ENOSYS) { + ret = PTR_ERR(up->gpios); + goto err_disable_clk; + } up->rts_gpiod = mctrl_gpio_to_gpiod(up->gpios, UART_GPIO_RTS); diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c index 1731d9728865..cacf7266a262 100644 --- a/drivers/tty/serial/imx.c +++ b/drivers/tty/serial/imx.c @@ -942,8 +942,14 @@ static irqreturn_t imx_uart_int(int irq, void *dev_id) struct imx_port *sport = dev_id; unsigned int usr1, usr2, ucr1, ucr2, ucr3, ucr4; irqreturn_t ret = IRQ_NONE; + unsigned long flags = 0; - spin_lock(&sport->port.lock); + /* + * IRQs might not be disabled upon entering this interrupt handler, + * e.g. when interrupt handlers are forced to be threaded. To support + * this scenario as well, disable IRQs when acquiring the spinlock. + */ + spin_lock_irqsave(&sport->port.lock, flags); usr1 = imx_uart_readl(sport, USR1); usr2 = imx_uart_readl(sport, USR2); @@ -1013,7 +1019,7 @@ static irqreturn_t imx_uart_int(int irq, void *dev_id) ret = IRQ_HANDLED; } - spin_unlock(&sport->port.lock); + spin_unlock_irqrestore(&sport->port.lock, flags); return ret; } @@ -2002,16 +2008,6 @@ imx_uart_console_write(struct console *co, const char *s, unsigned int count) unsigned int ucr1; unsigned long flags = 0; int locked = 1; - int retval; - - retval = clk_enable(sport->clk_per); - if (retval) - return; - retval = clk_enable(sport->clk_ipg); - if (retval) { - clk_disable(sport->clk_per); - return; - } if (sport->port.sysrq) locked = 0; @@ -2047,9 +2043,6 @@ imx_uart_console_write(struct console *co, const char *s, unsigned int count) if (locked) spin_unlock_irqrestore(&sport->port.lock, flags); - - clk_disable(sport->clk_ipg); - clk_disable(sport->clk_per); } /* @@ -2150,15 +2143,14 @@ imx_uart_console_setup(struct console *co, char *options) retval = uart_set_options(&sport->port, co, baud, parity, bits, flow); - clk_disable(sport->clk_ipg); if (retval) { - clk_unprepare(sport->clk_ipg); + clk_disable_unprepare(sport->clk_ipg); goto error_console; } - retval = clk_prepare(sport->clk_per); + retval = clk_prepare_enable(sport->clk_per); if (retval) - clk_unprepare(sport->clk_ipg); + clk_disable_unprepare(sport->clk_ipg); error_console: return retval; diff --git a/drivers/tty/serial/serial_txx9.c b/drivers/tty/serial/serial_txx9.c index b4d89e31730e..7a07e7272de1 100644 --- a/drivers/tty/serial/serial_txx9.c +++ b/drivers/tty/serial/serial_txx9.c @@ -1280,6 +1280,9 @@ static int __init serial_txx9_init(void) #ifdef ENABLE_SERIAL_TXX9_PCI ret = pci_register_driver(&serial_txx9_pci_driver); + if (ret) { + platform_driver_unregister(&serial_txx9_plat_driver); + } #endif if (ret == 0) goto out; diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 7a4c02548fb3..9f8b9a567b35 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -1515,10 +1515,12 @@ static void release_tty(struct tty_struct *tty, int idx) tty->ops->shutdown(tty); tty_save_termios(tty); tty_driver_remove_tty(tty->driver, tty); - tty->port->itty = NULL; + if (tty->port) + tty->port->itty = NULL; if (tty->link) tty->link->port->itty = NULL; - tty_buffer_cancel_work(tty->port); + if (tty->port) + tty_buffer_cancel_work(tty->port); if (tty->link) tty_buffer_cancel_work(tty->link->port); diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 9506a76f3ab6..d04a162939a4 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -4704,27 +4704,6 @@ static int con_font_default(struct vc_data *vc, struct console_font_op *op) return rc; } -static int con_font_copy(struct vc_data *vc, struct console_font_op *op) -{ - int con = op->height; - int rc; - - - console_lock(); - if (vc->vc_mode != KD_TEXT) - rc = -EINVAL; - else if (!vc->vc_sw->con_font_copy) - rc = -ENOSYS; - else if (con < 0 || !vc_cons_allocated(con)) - rc = -ENOTTY; - else if (con == vc->vc_num) /* nothing to do */ - rc = 0; - else - rc = vc->vc_sw->con_font_copy(vc, con); - console_unlock(); - return rc; -} - int con_font_op(struct vc_data *vc, struct console_font_op *op) { switch (op->op) { @@ -4735,7 +4714,8 @@ int con_font_op(struct vc_data *vc, struct console_font_op *op) case KD_FONT_OP_SET_DEFAULT: return con_font_default(vc, op); case KD_FONT_OP_COPY: - return con_font_copy(vc, op); + /* was buggy and never really used */ + return -EINVAL; } return -ENOSYS; } diff --git a/drivers/tty/vt/vt_ioctl.c b/drivers/tty/vt/vt_ioctl.c index 2321775ef098..5f61b25a9aaa 100644 --- a/drivers/tty/vt/vt_ioctl.c +++ b/drivers/tty/vt/vt_ioctl.c @@ -484,7 +484,7 @@ static int vt_k_ioctl(struct tty_struct *tty, unsigned int cmd, return 0; } -static inline int do_fontx_ioctl(int cmd, +static inline int do_fontx_ioctl(struct vc_data *vc, int cmd, struct consolefontdesc __user *user_cfd, struct console_font_op *op) { @@ -502,15 +502,16 @@ static inline int do_fontx_ioctl(int cmd, op->height = cfdarg.charheight; op->charcount = cfdarg.charcount; op->data = cfdarg.chardata; - return con_font_op(vc_cons[fg_console].d, op); - case GIO_FONTX: { + return con_font_op(vc, op); + + case GIO_FONTX: op->op = KD_FONT_OP_GET; op->flags = KD_FONT_FLAG_OLD; op->width = 8; op->height = cfdarg.charheight; op->charcount = cfdarg.charcount; op->data = cfdarg.chardata; - i = con_font_op(vc_cons[fg_console].d, op); + i = con_font_op(vc, op); if (i) return i; cfdarg.charheight = op->height; @@ -518,12 +519,11 @@ static inline int do_fontx_ioctl(int cmd, if (copy_to_user(user_cfd, &cfdarg, sizeof(struct consolefontdesc))) return -EFAULT; return 0; - } } return -EINVAL; } -static int vt_io_fontreset(struct console_font_op *op) +static int vt_io_fontreset(struct vc_data *vc, struct console_font_op *op) { int ret; @@ -537,12 +537,12 @@ static int vt_io_fontreset(struct console_font_op *op) op->op = KD_FONT_OP_SET_DEFAULT; op->data = NULL; - ret = con_font_op(vc_cons[fg_console].d, op); + ret = con_font_op(vc, op); if (ret) return ret; console_lock(); - con_set_default_unimap(vc_cons[fg_console].d); + con_set_default_unimap(vc); console_unlock(); return 0; @@ -584,7 +584,7 @@ static int vt_io_ioctl(struct vc_data *vc, unsigned int cmd, void __user *up, op.height = 0; op.charcount = 256; op.data = up; - return con_font_op(vc_cons[fg_console].d, &op); + return con_font_op(vc, &op); case GIO_FONT: op.op = KD_FONT_OP_GET; @@ -593,7 +593,7 @@ static int vt_io_ioctl(struct vc_data *vc, unsigned int cmd, void __user *up, op.height = 32; op.charcount = 256; op.data = up; - return con_font_op(vc_cons[fg_console].d, &op); + return con_font_op(vc, &op); case PIO_CMAP: if (!perm) @@ -609,13 +609,13 @@ static int vt_io_ioctl(struct vc_data *vc, unsigned int cmd, void __user *up, fallthrough; case GIO_FONTX: - return do_fontx_ioctl(cmd, up, &op); + return do_fontx_ioctl(vc, cmd, up, &op); case PIO_FONTRESET: if (!perm) return -EPERM; - return vt_io_fontreset(&op); + return vt_io_fontreset(vc, &op); case PIO_SCRNMAP: if (!perm) @@ -1066,8 +1066,9 @@ struct compat_consolefontdesc { }; static inline int -compat_fontx_ioctl(int cmd, struct compat_consolefontdesc __user *user_cfd, - int perm, struct console_font_op *op) +compat_fontx_ioctl(struct vc_data *vc, int cmd, + struct compat_consolefontdesc __user *user_cfd, + int perm, struct console_font_op *op) { struct compat_consolefontdesc cfdarg; int i; @@ -1085,7 +1086,8 @@ compat_fontx_ioctl(int cmd, struct compat_consolefontdesc __user *user_cfd, op->height = cfdarg.charheight; op->charcount = cfdarg.charcount; op->data = compat_ptr(cfdarg.chardata); - return con_font_op(vc_cons[fg_console].d, op); + return con_font_op(vc, op); + case GIO_FONTX: op->op = KD_FONT_OP_GET; op->flags = KD_FONT_FLAG_OLD; @@ -1093,7 +1095,7 @@ compat_fontx_ioctl(int cmd, struct compat_consolefontdesc __user *user_cfd, op->height = cfdarg.charheight; op->charcount = cfdarg.charcount; op->data = compat_ptr(cfdarg.chardata); - i = con_font_op(vc_cons[fg_console].d, op); + i = con_font_op(vc, op); if (i) return i; cfdarg.charheight = op->height; @@ -1183,7 +1185,7 @@ long vt_compat_ioctl(struct tty_struct *tty, */ case PIO_FONTX: case GIO_FONTX: - return compat_fontx_ioctl(cmd, up, perm, &op); + return compat_fontx_ioctl(vc, cmd, up, perm, &op); case KDFONTOP: return compat_kdfontop_ioctl(up, perm, &op, vc); diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c index 6dca744e39e9..be06f1a961c2 100644 --- a/drivers/uio/uio.c +++ b/drivers/uio/uio.c @@ -413,10 +413,10 @@ static int uio_get_minor(struct uio_device *idev) return retval; } -static void uio_free_minor(struct uio_device *idev) +static void uio_free_minor(unsigned long minor) { mutex_lock(&minor_lock); - idr_remove(&uio_idr, idev->minor); + idr_remove(&uio_idr, minor); mutex_unlock(&minor_lock); } @@ -990,7 +990,7 @@ err_request_irq: err_uio_dev_add_attributes: device_del(&idev->dev); err_device_create: - uio_free_minor(idev); + uio_free_minor(idev->minor); put_device(&idev->dev); return ret; } @@ -1042,11 +1042,13 @@ EXPORT_SYMBOL_GPL(__devm_uio_register_device); void uio_unregister_device(struct uio_info *info) { struct uio_device *idev; + unsigned long minor; if (!info || !info->uio_dev) return; idev = info->uio_dev; + minor = idev->minor; mutex_lock(&idev->info_lock); uio_dev_del_attributes(idev); @@ -1062,7 +1064,7 @@ void uio_unregister_device(struct uio_info *info) device_unregister(&idev->dev); - uio_free_minor(idev); + uio_free_minor(minor); return; } diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 1e7568867910..f52f1bc0559f 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -1693,6 +1693,15 @@ static const struct usb_device_id acm_ids[] = { { USB_DEVICE(0x0870, 0x0001), /* Metricom GS Modem */ .driver_info = NO_UNION_NORMAL, /* has no union descriptor */ }, + { USB_DEVICE(0x045b, 0x023c), /* Renesas USB Download mode */ + .driver_info = DISABLE_ECHO, /* Don't echo banner */ + }, + { USB_DEVICE(0x045b, 0x0248), /* Renesas USB Download mode */ + .driver_info = DISABLE_ECHO, /* Don't echo banner */ + }, + { USB_DEVICE(0x045b, 0x024D), /* Renesas USB Download mode */ + .driver_info = DISABLE_ECHO, /* Don't echo banner */ + }, { USB_DEVICE(0x0e8d, 0x0003), /* FIREFLY, MediaTek Inc; andrey.arapov@gmail.com */ .driver_info = NO_UNION_NORMAL, /* has no union descriptor */ }, diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 10574fa3f927..a1e3a037a289 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -378,6 +378,9 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x0926, 0x3333), .driver_info = USB_QUIRK_CONFIG_INTF_STRINGS }, + /* Kingston DataTraveler 3.0 */ + { USB_DEVICE(0x0951, 0x1666), .driver_info = USB_QUIRK_NO_LPM }, + /* X-Rite/Gretag-Macbeth Eye-One Pro display colorimeter */ { USB_DEVICE(0x0971, 0x2000), .driver_info = USB_QUIRK_NO_SET_INTF }, diff --git a/drivers/usb/dwc2/platform.c b/drivers/usb/dwc2/platform.c index e2820676beb1..5f18acac7406 100644 --- a/drivers/usb/dwc2/platform.c +++ b/drivers/usb/dwc2/platform.c @@ -608,10 +608,13 @@ static int dwc2_driver_probe(struct platform_device *dev) #endif /* CONFIG_USB_DWC2_PERIPHERAL || CONFIG_USB_DWC2_DUAL_ROLE */ return 0; +#if IS_ENABLED(CONFIG_USB_DWC2_PERIPHERAL) || \ + IS_ENABLED(CONFIG_USB_DWC2_DUAL_ROLE) error_debugfs: dwc2_debugfs_exit(hsotg); if (hsotg->hcd_enabled) dwc2_hcd_remove(hsotg); +#endif error_drd: dwc2_drd_exit(hsotg); diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c index 242b6210380a..bae6a70664c8 100644 --- a/drivers/usb/dwc3/dwc3-pci.c +++ b/drivers/usb/dwc3/dwc3-pci.c @@ -40,6 +40,7 @@ #define PCI_DEVICE_ID_INTEL_TGPLP 0xa0ee #define PCI_DEVICE_ID_INTEL_TGPH 0x43ee #define PCI_DEVICE_ID_INTEL_JSP 0x4dee +#define PCI_DEVICE_ID_INTEL_ADLS 0x7ae1 #define PCI_INTEL_BXT_DSM_GUID "732b85d5-b7a7-4a1b-9ba0-4bbd00ffd511" #define PCI_INTEL_BXT_FUNC_PMU_PWR 4 @@ -367,6 +368,9 @@ static const struct pci_device_id dwc3_pci_id_table[] = { { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_JSP), (kernel_ulong_t) &dwc3_pci_intel_properties, }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ADLS), + (kernel_ulong_t) &dwc3_pci_intel_properties, }, + { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_NL_USB), (kernel_ulong_t) &dwc3_pci_amd_properties, }, { } /* Terminating Entry */ diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c index 7be3903cb842..8b668ef46f7f 100644 --- a/drivers/usb/dwc3/ep0.c +++ b/drivers/usb/dwc3/ep0.c @@ -1058,10 +1058,11 @@ void dwc3_ep0_send_delayed_status(struct dwc3 *dwc) { unsigned int direction = !dwc->ep0_expect_in; + dwc->delayed_status = false; + if (dwc->ep0state != EP0_STATUS_PHASE) return; - dwc->delayed_status = false; __dwc3_ep0_do_control_status(dwc, dwc->eps[direction]); } diff --git a/drivers/usb/gadget/legacy/raw_gadget.c b/drivers/usb/gadget/legacy/raw_gadget.c index e01e366d89cd..062dfac30399 100644 --- a/drivers/usb/gadget/legacy/raw_gadget.c +++ b/drivers/usb/gadget/legacy/raw_gadget.c @@ -564,9 +564,12 @@ static int raw_ioctl_event_fetch(struct raw_dev *dev, unsigned long value) return -ENODEV; } length = min(arg.length, event->length); - if (copy_to_user((void __user *)value, event, sizeof(*event) + length)) + if (copy_to_user((void __user *)value, event, sizeof(*event) + length)) { + kfree(event); return -EFAULT; + } + kfree(event); return 0; } diff --git a/drivers/usb/gadget/udc/fsl_udc_core.c b/drivers/usb/gadget/udc/fsl_udc_core.c index de528e3b0662..ad6ff9c4188e 100644 --- a/drivers/usb/gadget/udc/fsl_udc_core.c +++ b/drivers/usb/gadget/udc/fsl_udc_core.c @@ -1051,7 +1051,7 @@ static int fsl_ep_fifo_status(struct usb_ep *_ep) u32 bitmask; struct ep_queue_head *qh; - if (!_ep || _ep->desc || !(_ep->desc->bEndpointAddress&0xF)) + if (!_ep || !_ep->desc || !(_ep->desc->bEndpointAddress&0xF)) return -ENODEV; ep = container_of(_ep, struct fsl_ep, ep); diff --git a/drivers/usb/gadget/udc/goku_udc.c b/drivers/usb/gadget/udc/goku_udc.c index 25c1d6ab5adb..3e1267d38774 100644 --- a/drivers/usb/gadget/udc/goku_udc.c +++ b/drivers/usb/gadget/udc/goku_udc.c @@ -1760,6 +1760,7 @@ static int goku_probe(struct pci_dev *pdev, const struct pci_device_id *id) goto err; } + pci_set_drvdata(pdev, dev); spin_lock_init(&dev->lock); dev->pdev = pdev; dev->gadget.ops = &goku_ops; @@ -1793,7 +1794,6 @@ static int goku_probe(struct pci_dev *pdev, const struct pci_device_id *id) } dev->regs = (struct goku_udc_regs __iomem *) base; - pci_set_drvdata(pdev, dev); INFO(dev, "%s\n", driver_desc); INFO(dev, "version: " DRIVER_VERSION " %s\n", dmastr()); INFO(dev, "irq %d, pci mem %p\n", pdev->irq, base); diff --git a/drivers/usb/host/xhci-histb.c b/drivers/usb/host/xhci-histb.c index 5546e7e013a8..08369857686e 100644 --- a/drivers/usb/host/xhci-histb.c +++ b/drivers/usb/host/xhci-histb.c @@ -240,7 +240,7 @@ static int xhci_histb_probe(struct platform_device *pdev) /* Initialize dma_mask and coherent_dma_mask to 32-bits */ ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32)); if (ret) - return ret; + goto disable_pm; hcd = usb_create_hcd(driver, dev, dev_name(dev)); if (!hcd) { diff --git a/drivers/usb/misc/apple-mfi-fastcharge.c b/drivers/usb/misc/apple-mfi-fastcharge.c index 579d8c84de42..9de0171b5177 100644 --- a/drivers/usb/misc/apple-mfi-fastcharge.c +++ b/drivers/usb/misc/apple-mfi-fastcharge.c @@ -120,8 +120,10 @@ static int apple_mfi_fc_set_property(struct power_supply *psy, dev_dbg(&mfi->udev->dev, "prop: %d\n", psp); ret = pm_runtime_get_sync(&mfi->udev->dev); - if (ret < 0) + if (ret < 0) { + pm_runtime_put_noidle(&mfi->udev->dev); return ret; + } switch (psp) { case POWER_SUPPLY_PROP_CHARGE_TYPE: diff --git a/drivers/usb/mtu3/mtu3_gadget.c b/drivers/usb/mtu3/mtu3_gadget.c index 1de5c9a1d20a..38f17d66d5bc 100644 --- a/drivers/usb/mtu3/mtu3_gadget.c +++ b/drivers/usb/mtu3/mtu3_gadget.c @@ -564,6 +564,7 @@ static int mtu3_gadget_stop(struct usb_gadget *g) spin_unlock_irqrestore(&mtu->lock, flags); + synchronize_irq(mtu->irq); return 0; } diff --git a/drivers/usb/musb/musb_dsps.c b/drivers/usb/musb/musb_dsps.c index 30085b2be7b9..5892f3ce0cdc 100644 --- a/drivers/usb/musb/musb_dsps.c +++ b/drivers/usb/musb/musb_dsps.c @@ -429,10 +429,12 @@ static int dsps_musb_init(struct musb *musb) struct platform_device *parent = to_platform_device(dev->parent); const struct dsps_musb_wrapper *wrp = glue->wrp; void __iomem *reg_base; + struct resource *r; u32 rev, val; int ret; - reg_base = devm_platform_ioremap_resource_byname(parent, "control"); + r = platform_get_resource_byname(parent, IORESOURCE_MEM, "control"); + reg_base = devm_ioremap_resource(dev, r); if (IS_ERR(reg_base)) return PTR_ERR(reg_base); musb->ctrl_base = reg_base; diff --git a/drivers/usb/serial/cyberjack.c b/drivers/usb/serial/cyberjack.c index 821970609695..2e40908963da 100644 --- a/drivers/usb/serial/cyberjack.c +++ b/drivers/usb/serial/cyberjack.c @@ -357,11 +357,12 @@ static void cyberjack_write_bulk_callback(struct urb *urb) struct device *dev = &port->dev; int status = urb->status; unsigned long flags; + bool resubmitted = false; - set_bit(0, &port->write_urbs_free); if (status) { dev_dbg(dev, "%s - nonzero write bulk status received: %d\n", __func__, status); + set_bit(0, &port->write_urbs_free); return; } @@ -394,6 +395,8 @@ static void cyberjack_write_bulk_callback(struct urb *urb) goto exit; } + resubmitted = true; + dev_dbg(dev, "%s - priv->wrsent=%d\n", __func__, priv->wrsent); dev_dbg(dev, "%s - priv->wrfilled=%d\n", __func__, priv->wrfilled); @@ -410,6 +413,8 @@ static void cyberjack_write_bulk_callback(struct urb *urb) exit: spin_unlock_irqrestore(&priv->lock, flags); + if (!resubmitted) + set_bit(0, &port->write_urbs_free); usb_serial_port_softint(port); } diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 2a3bfd6f867e..54ca85cc920d 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -250,6 +250,7 @@ static void option_instat_callback(struct urb *urb); #define QUECTEL_PRODUCT_EP06 0x0306 #define QUECTEL_PRODUCT_EM12 0x0512 #define QUECTEL_PRODUCT_RM500Q 0x0800 +#define QUECTEL_PRODUCT_EC200T 0x6026 #define CMOTECH_VENDOR_ID 0x16d8 #define CMOTECH_PRODUCT_6001 0x6001 @@ -1117,6 +1118,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0xff, 0x10), .driver_info = ZLP }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200T, 0xff, 0, 0) }, { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6001) }, { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CMU_300) }, @@ -1189,6 +1191,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(0) | RSVD(1) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1054, 0xff), /* Telit FT980-KS */ .driver_info = NCTRL(2) | RSVD(3) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1055, 0xff), /* Telit FN980 (PCIe) */ + .driver_info = NCTRL(0) | RSVD(1) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910), .driver_info = NCTRL(0) | RSVD(1) | RSVD(3) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910_DUAL_MODEM), @@ -1201,6 +1205,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(0) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910), .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1203, 0xff), /* Telit LE910Cx (RNDIS) */ + .driver_info = NCTRL(2) | RSVD(3) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910_USBCFG4), .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) | RSVD(3) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920), @@ -1215,6 +1221,10 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920A4_1213, 0xff) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920A4_1214), .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) | RSVD(3) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1230, 0xff), /* Telit LE910Cx (rmnet) */ + .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1231, 0xff), /* Telit LE910Cx (RNDIS) */ + .driver_info = NCTRL(2) | RSVD(3) }, { USB_DEVICE(TELIT_VENDOR_ID, 0x1260), .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) }, { USB_DEVICE(TELIT_VENDOR_ID, 0x1261), diff --git a/drivers/usb/typec/ucsi/psy.c b/drivers/usb/typec/ucsi/psy.c index 26ed0b520749..571a51e16234 100644 --- a/drivers/usb/typec/ucsi/psy.c +++ b/drivers/usb/typec/ucsi/psy.c @@ -238,4 +238,13 @@ void ucsi_unregister_port_psy(struct ucsi_connector *con) return; power_supply_unregister(con->psy); + con->psy = NULL; +} + +void ucsi_port_psy_changed(struct ucsi_connector *con) +{ + if (IS_ERR_OR_NULL(con->psy)) + return; + + power_supply_changed(con->psy); } diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index 758b988ac518..51a570d40a42 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -643,8 +643,10 @@ static void ucsi_handle_connector_change(struct work_struct *work) role = !!(con->status.flags & UCSI_CONSTAT_PWR_DIR); if (con->status.change & UCSI_CONSTAT_POWER_OPMODE_CHANGE || - con->status.change & UCSI_CONSTAT_POWER_LEVEL_CHANGE) + con->status.change & UCSI_CONSTAT_POWER_LEVEL_CHANGE) { ucsi_pwr_opmode_change(con); + ucsi_port_psy_changed(con); + } if (con->status.change & UCSI_CONSTAT_POWER_DIR_CHANGE) { typec_set_pwr_role(con->port, role); @@ -674,6 +676,8 @@ static void ucsi_handle_connector_change(struct work_struct *work) ucsi_register_partner(con); else ucsi_unregister_partner(con); + + ucsi_port_psy_changed(con); } if (con->status.change & UCSI_CONSTAT_CAM_CHANGE) { @@ -994,6 +998,7 @@ static int ucsi_register_port(struct ucsi *ucsi, int index) !!(con->status.flags & UCSI_CONSTAT_PWR_DIR)); ucsi_pwr_opmode_change(con); ucsi_register_partner(con); + ucsi_port_psy_changed(con); } if (con->partner) { diff --git a/drivers/usb/typec/ucsi/ucsi.h b/drivers/usb/typec/ucsi/ucsi.h index cba6f77bea61..b7a92f246050 100644 --- a/drivers/usb/typec/ucsi/ucsi.h +++ b/drivers/usb/typec/ucsi/ucsi.h @@ -340,9 +340,11 @@ int ucsi_resume(struct ucsi *ucsi); #if IS_ENABLED(CONFIG_POWER_SUPPLY) int ucsi_register_port_psy(struct ucsi_connector *con); void ucsi_unregister_port_psy(struct ucsi_connector *con); +void ucsi_port_psy_changed(struct ucsi_connector *con); #else static inline int ucsi_register_port_psy(struct ucsi_connector *con) { return 0; } static inline void ucsi_unregister_port_psy(struct ucsi_connector *con) { } +static inline void ucsi_port_psy_changed(struct ucsi_connector *con) { } #endif /* CONFIG_POWER_SUPPLY */ #if IS_ENABLED(CONFIG_TYPEC_DP_ALTMODE) diff --git a/drivers/vdpa/Kconfig b/drivers/vdpa/Kconfig index d7d32b656102..358f6048dd3c 100644 --- a/drivers/vdpa/Kconfig +++ b/drivers/vdpa/Kconfig @@ -13,6 +13,7 @@ config VDPA_SIM depends on RUNTIME_TESTING_MENU && HAS_DMA select DMA_OPS select VHOST_RING + select GENERIC_NET_UTILS default n help vDPA networking device simulator which loop TX traffic back diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc.c b/drivers/vfio/fsl-mc/vfio_fsl_mc.c index 0113a980f974..f27e25112c40 100644 --- a/drivers/vfio/fsl-mc/vfio_fsl_mc.c +++ b/drivers/vfio/fsl-mc/vfio_fsl_mc.c @@ -248,7 +248,9 @@ static long vfio_fsl_mc_ioctl(void *device_data, unsigned int cmd, info.size = vdev->regions[info.index].size; info.flags = vdev->regions[info.index].flags; - return copy_to_user((void __user *)arg, &info, minsz); + if (copy_to_user((void __user *)arg, &info, minsz)) + return -EFAULT; + return 0; } case VFIO_DEVICE_GET_IRQ_INFO: { @@ -267,7 +269,9 @@ static long vfio_fsl_mc_ioctl(void *device_data, unsigned int cmd, info.flags = VFIO_IRQ_INFO_EVENTFD; info.count = 1; - return copy_to_user((void __user *)arg, &info, minsz); + if (copy_to_user((void __user *)arg, &info, minsz)) + return -EFAULT; + return 0; } case VFIO_DEVICE_SET_IRQS: { @@ -468,7 +472,7 @@ static int vfio_fsl_mc_mmap(void *device_data, struct vm_area_struct *vma) { struct vfio_fsl_mc_device *vdev = device_data; struct fsl_mc_device *mc_dev = vdev->mc_dev; - int index; + unsigned int index; index = vma->vm_pgoff >> (VFIO_FSL_MC_OFFSET_SHIFT - PAGE_SHIFT); diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c b/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c index c80dceb46f79..0d9f3002df7f 100644 --- a/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c +++ b/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c @@ -13,7 +13,7 @@ #include "linux/fsl/mc.h" #include "vfio_fsl_mc_private.h" -int vfio_fsl_mc_irqs_allocate(struct vfio_fsl_mc_device *vdev) +static int vfio_fsl_mc_irqs_allocate(struct vfio_fsl_mc_device *vdev) { struct fsl_mc_device *mc_dev = vdev->mc_dev; struct vfio_fsl_mc_irq *mc_irq; diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index fbd2b3404184..e6190173482c 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -385,7 +385,7 @@ static int vfio_pci_enable(struct vfio_pci_device *vdev) pdev->vendor == PCI_VENDOR_ID_INTEL && IS_ENABLED(CONFIG_VFIO_PCI_IGD)) { ret = vfio_pci_igd_init(vdev); - if (ret) { + if (ret && ret != -ENODEV) { pci_warn(pdev, "Failed to setup Intel IGD regions\n"); goto disable_exit; } diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c index 9e353c484ace..a0b5fc8e46f4 100644 --- a/drivers/vfio/pci/vfio_pci_rdwr.c +++ b/drivers/vfio/pci/vfio_pci_rdwr.c @@ -356,34 +356,60 @@ ssize_t vfio_pci_vga_rw(struct vfio_pci_device *vdev, char __user *buf, return done; } -static int vfio_pci_ioeventfd_handler(void *opaque, void *unused) +static void vfio_pci_ioeventfd_do_write(struct vfio_pci_ioeventfd *ioeventfd, + bool test_mem) { - struct vfio_pci_ioeventfd *ioeventfd = opaque; - switch (ioeventfd->count) { case 1: - vfio_pci_iowrite8(ioeventfd->vdev, ioeventfd->test_mem, + vfio_pci_iowrite8(ioeventfd->vdev, test_mem, ioeventfd->data, ioeventfd->addr); break; case 2: - vfio_pci_iowrite16(ioeventfd->vdev, ioeventfd->test_mem, + vfio_pci_iowrite16(ioeventfd->vdev, test_mem, ioeventfd->data, ioeventfd->addr); break; case 4: - vfio_pci_iowrite32(ioeventfd->vdev, ioeventfd->test_mem, + vfio_pci_iowrite32(ioeventfd->vdev, test_mem, ioeventfd->data, ioeventfd->addr); break; #ifdef iowrite64 case 8: - vfio_pci_iowrite64(ioeventfd->vdev, ioeventfd->test_mem, + vfio_pci_iowrite64(ioeventfd->vdev, test_mem, ioeventfd->data, ioeventfd->addr); break; #endif } +} + +static int vfio_pci_ioeventfd_handler(void *opaque, void *unused) +{ + struct vfio_pci_ioeventfd *ioeventfd = opaque; + struct vfio_pci_device *vdev = ioeventfd->vdev; + + if (ioeventfd->test_mem) { + if (!down_read_trylock(&vdev->memory_lock)) + return 1; /* Lock contended, use thread */ + if (!__vfio_pci_memory_enabled(vdev)) { + up_read(&vdev->memory_lock); + return 0; + } + } + + vfio_pci_ioeventfd_do_write(ioeventfd, false); + + if (ioeventfd->test_mem) + up_read(&vdev->memory_lock); return 0; } +static void vfio_pci_ioeventfd_thread(void *opaque, void *unused) +{ + struct vfio_pci_ioeventfd *ioeventfd = opaque; + + vfio_pci_ioeventfd_do_write(ioeventfd, ioeventfd->test_mem); +} + long vfio_pci_ioeventfd(struct vfio_pci_device *vdev, loff_t offset, uint64_t data, int count, int fd) { @@ -457,7 +483,8 @@ long vfio_pci_ioeventfd(struct vfio_pci_device *vdev, loff_t offset, ioeventfd->test_mem = vdev->pdev->resource[bar].flags & IORESOURCE_MEM; ret = vfio_virqfd_enable(ioeventfd, vfio_pci_ioeventfd_handler, - NULL, NULL, &ioeventfd->virqfd, fd); + vfio_pci_ioeventfd_thread, NULL, + &ioeventfd->virqfd, fd); if (ret) { kfree(ioeventfd); goto out_unlock; diff --git a/drivers/vfio/platform/vfio_platform_common.c b/drivers/vfio/platform/vfio_platform_common.c index c0771a9567fb..fb4b385191f2 100644 --- a/drivers/vfio/platform/vfio_platform_common.c +++ b/drivers/vfio/platform/vfio_platform_common.c @@ -267,7 +267,7 @@ static int vfio_platform_open(void *device_data) ret = pm_runtime_get_sync(vdev->device); if (ret < 0) - goto err_pm; + goto err_rst; ret = vfio_platform_call_reset(vdev, &extra_dbg); if (ret && vdev->reset_required) { @@ -284,7 +284,6 @@ static int vfio_platform_open(void *device_data) err_rst: pm_runtime_put(vdev->device); -err_pm: vfio_platform_irq_cleanup(vdev); err_irq: vfio_platform_regions_cleanup(vdev); diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index bb2684cc245e..67e827638995 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -1993,6 +1993,7 @@ static void vfio_iommu_iova_insert_copy(struct vfio_iommu *iommu, list_splice_tail(iova_copy, iova); } + static int vfio_iommu_type1_attach_group(void *iommu_data, struct iommu_group *iommu_group) { @@ -2009,18 +2010,10 @@ static int vfio_iommu_type1_attach_group(void *iommu_data, mutex_lock(&iommu->lock); - list_for_each_entry(d, &iommu->domain_list, next) { - if (find_iommu_group(d, iommu_group)) { - mutex_unlock(&iommu->lock); - return -EINVAL; - } - } - - if (iommu->external_domain) { - if (find_iommu_group(iommu->external_domain, iommu_group)) { - mutex_unlock(&iommu->lock); - return -EINVAL; - } + /* Check for duplicates */ + if (vfio_iommu_find_iommu_group(iommu, iommu_group)) { + mutex_unlock(&iommu->lock); + return -EINVAL; } group = kzalloc(sizeof(*group), GFP_KERNEL); diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index b22adf03f584..f22fce549862 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -52,7 +52,6 @@ #define VHOST_SCSI_VERSION "v0.1" #define VHOST_SCSI_NAMELEN 256 #define VHOST_SCSI_MAX_CDB_SIZE 32 -#define VHOST_SCSI_DEFAULT_TAGS 256 #define VHOST_SCSI_PREALLOC_SGLS 2048 #define VHOST_SCSI_PREALLOC_UPAGES 2048 #define VHOST_SCSI_PREALLOC_PROT_SGLS 2048 @@ -140,6 +139,7 @@ struct vhost_scsi_tpg { struct se_portal_group se_tpg; /* Pointer back to vhost_scsi, protected by tv_tpg_mutex */ struct vhost_scsi *vhost_scsi; + struct list_head tmf_queue; }; struct vhost_scsi_tport { @@ -189,6 +189,9 @@ struct vhost_scsi_virtqueue { * Writers must also take dev mutex and flush under it. */ int inflight_idx; + struct vhost_scsi_cmd *scsi_cmds; + struct sbitmap scsi_tags; + int max_cmds; }; struct vhost_scsi { @@ -209,6 +212,20 @@ struct vhost_scsi { int vs_events_nr; /* num of pending events, protected by vq->mutex */ }; +struct vhost_scsi_tmf { + struct vhost_work vwork; + struct vhost_scsi_tpg *tpg; + struct vhost_scsi *vhost; + struct vhost_scsi_virtqueue *svq; + struct list_head queue_entry; + + struct se_cmd se_cmd; + struct vhost_scsi_inflight *inflight; + struct iovec resp_iov; + int in_iovs; + int vq_desc; +}; + /* * Context for processing request and control queue operations. */ @@ -320,11 +337,13 @@ static u32 vhost_scsi_tpg_get_inst_index(struct se_portal_group *se_tpg) return 1; } -static void vhost_scsi_release_cmd(struct se_cmd *se_cmd) +static void vhost_scsi_release_cmd_res(struct se_cmd *se_cmd) { struct vhost_scsi_cmd *tv_cmd = container_of(se_cmd, struct vhost_scsi_cmd, tvc_se_cmd); - struct se_session *se_sess = tv_cmd->tvc_nexus->tvn_se_sess; + struct vhost_scsi_virtqueue *svq = container_of(tv_cmd->tvc_vq, + struct vhost_scsi_virtqueue, vq); + struct vhost_scsi_inflight *inflight = tv_cmd->inflight; int i; if (tv_cmd->tvc_sgl_count) { @@ -336,8 +355,36 @@ static void vhost_scsi_release_cmd(struct se_cmd *se_cmd) put_page(sg_page(&tv_cmd->tvc_prot_sgl[i])); } - vhost_scsi_put_inflight(tv_cmd->inflight); - target_free_tag(se_sess, se_cmd); + sbitmap_clear_bit(&svq->scsi_tags, se_cmd->map_tag); + vhost_scsi_put_inflight(inflight); +} + +static void vhost_scsi_release_tmf_res(struct vhost_scsi_tmf *tmf) +{ + struct vhost_scsi_tpg *tpg = tmf->tpg; + struct vhost_scsi_inflight *inflight = tmf->inflight; + + mutex_lock(&tpg->tv_tpg_mutex); + list_add_tail(&tpg->tmf_queue, &tmf->queue_entry); + mutex_unlock(&tpg->tv_tpg_mutex); + vhost_scsi_put_inflight(inflight); +} + +static void vhost_scsi_release_cmd(struct se_cmd *se_cmd) +{ + if (se_cmd->se_cmd_flags & SCF_SCSI_TMR_CDB) { + struct vhost_scsi_tmf *tmf = container_of(se_cmd, + struct vhost_scsi_tmf, se_cmd); + + vhost_work_queue(&tmf->vhost->dev, &tmf->vwork); + } else { + struct vhost_scsi_cmd *cmd = container_of(se_cmd, + struct vhost_scsi_cmd, tvc_se_cmd); + struct vhost_scsi *vs = cmd->tvc_vhost; + + llist_add(&cmd->tvc_completion_list, &vs->vs_completion_list); + vhost_work_queue(&vs->dev, &vs->vs_completion_work); + } } static u32 vhost_scsi_sess_get_index(struct se_session *se_sess) @@ -362,34 +409,24 @@ static int vhost_scsi_get_cmd_state(struct se_cmd *se_cmd) return 0; } -static void vhost_scsi_complete_cmd(struct vhost_scsi_cmd *cmd) -{ - struct vhost_scsi *vs = cmd->tvc_vhost; - - llist_add(&cmd->tvc_completion_list, &vs->vs_completion_list); - - vhost_work_queue(&vs->dev, &vs->vs_completion_work); -} - static int vhost_scsi_queue_data_in(struct se_cmd *se_cmd) { - struct vhost_scsi_cmd *cmd = container_of(se_cmd, - struct vhost_scsi_cmd, tvc_se_cmd); - vhost_scsi_complete_cmd(cmd); + transport_generic_free_cmd(se_cmd, 0); return 0; } static int vhost_scsi_queue_status(struct se_cmd *se_cmd) { - struct vhost_scsi_cmd *cmd = container_of(se_cmd, - struct vhost_scsi_cmd, tvc_se_cmd); - vhost_scsi_complete_cmd(cmd); + transport_generic_free_cmd(se_cmd, 0); return 0; } static void vhost_scsi_queue_tm_rsp(struct se_cmd *se_cmd) { - return; + struct vhost_scsi_tmf *tmf = container_of(se_cmd, struct vhost_scsi_tmf, + se_cmd); + + transport_generic_free_cmd(&tmf->se_cmd, 0); } static void vhost_scsi_aborted_task(struct se_cmd *se_cmd) @@ -429,15 +466,6 @@ vhost_scsi_allocate_evt(struct vhost_scsi *vs, return evt; } -static void vhost_scsi_free_cmd(struct vhost_scsi_cmd *cmd) -{ - struct se_cmd *se_cmd = &cmd->tvc_se_cmd; - - /* TODO locking against target/backend threads? */ - transport_generic_free_cmd(se_cmd, 0); - -} - static int vhost_scsi_check_stop_free(struct se_cmd *se_cmd) { return target_put_sess_cmd(se_cmd); @@ -556,7 +584,7 @@ static void vhost_scsi_complete_cmd_work(struct vhost_work *work) } else pr_err("Faulted on virtio_scsi_cmd_resp\n"); - vhost_scsi_free_cmd(cmd); + vhost_scsi_release_cmd_res(se_cmd); } vq = -1; @@ -566,31 +594,31 @@ static void vhost_scsi_complete_cmd_work(struct vhost_work *work) } static struct vhost_scsi_cmd * -vhost_scsi_get_tag(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg, +vhost_scsi_get_cmd(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg, unsigned char *cdb, u64 scsi_tag, u16 lun, u8 task_attr, u32 exp_data_len, int data_direction) { + struct vhost_scsi_virtqueue *svq = container_of(vq, + struct vhost_scsi_virtqueue, vq); struct vhost_scsi_cmd *cmd; struct vhost_scsi_nexus *tv_nexus; - struct se_session *se_sess; struct scatterlist *sg, *prot_sg; struct page **pages; - int tag, cpu; + int tag; tv_nexus = tpg->tpg_nexus; if (!tv_nexus) { pr_err("Unable to locate active struct vhost_scsi_nexus\n"); return ERR_PTR(-EIO); } - se_sess = tv_nexus->tvn_se_sess; - tag = sbitmap_queue_get(&se_sess->sess_tag_pool, &cpu); + tag = sbitmap_get(&svq->scsi_tags, 0, false); if (tag < 0) { pr_err("Unable to obtain tag for vhost_scsi_cmd\n"); return ERR_PTR(-ENOMEM); } - cmd = &((struct vhost_scsi_cmd *)se_sess->sess_cmd_map)[tag]; + cmd = &svq->scsi_cmds[tag]; sg = cmd->tvc_sgl; prot_sg = cmd->tvc_prot_sgl; pages = cmd->tvc_upages; @@ -599,7 +627,6 @@ vhost_scsi_get_tag(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg, cmd->tvc_prot_sgl = prot_sg; cmd->tvc_upages = pages; cmd->tvc_se_cmd.map_tag = tag; - cmd->tvc_se_cmd.map_cpu = cpu; cmd->tvc_tag = scsi_tag; cmd->tvc_lun = lun; cmd->tvc_task_attr = task_attr; @@ -907,6 +934,11 @@ vhost_scsi_get_req(struct vhost_virtqueue *vq, struct vhost_scsi_ctx *vc, return ret; } +static u16 vhost_buf_to_lun(u8 *lun_buf) +{ + return ((lun_buf[2] << 8) | lun_buf[3]) & 0x3FFF; +} + static void vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) { @@ -1045,12 +1077,12 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) tag = vhost64_to_cpu(vq, v_req_pi.tag); task_attr = v_req_pi.task_attr; cdb = &v_req_pi.cdb[0]; - lun = ((v_req_pi.lun[2] << 8) | v_req_pi.lun[3]) & 0x3FFF; + lun = vhost_buf_to_lun(v_req_pi.lun); } else { tag = vhost64_to_cpu(vq, v_req.tag); task_attr = v_req.task_attr; cdb = &v_req.cdb[0]; - lun = ((v_req.lun[2] << 8) | v_req.lun[3]) & 0x3FFF; + lun = vhost_buf_to_lun(v_req.lun); } /* * Check that the received CDB size does not exceeded our @@ -1065,11 +1097,11 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) scsi_command_size(cdb), VHOST_SCSI_MAX_CDB_SIZE); goto err; } - cmd = vhost_scsi_get_tag(vq, tpg, cdb, tag, lun, task_attr, + cmd = vhost_scsi_get_cmd(vq, tpg, cdb, tag, lun, task_attr, exp_data_len + prot_bytes, data_direction); if (IS_ERR(cmd)) { - vq_err(vq, "vhost_scsi_get_tag failed %ld\n", + vq_err(vq, "vhost_scsi_get_cmd failed %ld\n", PTR_ERR(cmd)); goto err; } @@ -1088,7 +1120,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) &prot_iter, exp_data_len, &data_iter))) { vq_err(vq, "Failed to map iov to sgl\n"); - vhost_scsi_release_cmd(&cmd->tvc_se_cmd); + vhost_scsi_release_cmd_res(&cmd->tvc_se_cmd); goto err; } } @@ -1124,9 +1156,9 @@ out: } static void -vhost_scsi_send_tmf_reject(struct vhost_scsi *vs, - struct vhost_virtqueue *vq, - struct vhost_scsi_ctx *vc) +vhost_scsi_send_tmf_resp(struct vhost_scsi *vs, struct vhost_virtqueue *vq, + int in_iovs, int vq_desc, struct iovec *resp_iov, + int tmf_resp_code) { struct virtio_scsi_ctrl_tmf_resp rsp; struct iov_iter iov_iter; @@ -1134,17 +1166,87 @@ vhost_scsi_send_tmf_reject(struct vhost_scsi *vs, pr_debug("%s\n", __func__); memset(&rsp, 0, sizeof(rsp)); - rsp.response = VIRTIO_SCSI_S_FUNCTION_REJECTED; + rsp.response = tmf_resp_code; - iov_iter_init(&iov_iter, READ, &vq->iov[vc->out], vc->in, sizeof(rsp)); + iov_iter_init(&iov_iter, READ, resp_iov, in_iovs, sizeof(rsp)); ret = copy_to_iter(&rsp, sizeof(rsp), &iov_iter); if (likely(ret == sizeof(rsp))) - vhost_add_used_and_signal(&vs->dev, vq, vc->head, 0); + vhost_add_used_and_signal(&vs->dev, vq, vq_desc, 0); else pr_err("Faulted on virtio_scsi_ctrl_tmf_resp\n"); } +static void vhost_scsi_tmf_resp_work(struct vhost_work *work) +{ + struct vhost_scsi_tmf *tmf = container_of(work, struct vhost_scsi_tmf, + vwork); + int resp_code; + + if (tmf->se_cmd.se_tmr_req->response == TMR_FUNCTION_COMPLETE) + resp_code = VIRTIO_SCSI_S_FUNCTION_SUCCEEDED; + else + resp_code = VIRTIO_SCSI_S_FUNCTION_REJECTED; + + vhost_scsi_send_tmf_resp(tmf->vhost, &tmf->svq->vq, tmf->in_iovs, + tmf->vq_desc, &tmf->resp_iov, resp_code); + vhost_scsi_release_tmf_res(tmf); +} + +static void +vhost_scsi_handle_tmf(struct vhost_scsi *vs, struct vhost_scsi_tpg *tpg, + struct vhost_virtqueue *vq, + struct virtio_scsi_ctrl_tmf_req *vtmf, + struct vhost_scsi_ctx *vc) +{ + struct vhost_scsi_virtqueue *svq = container_of(vq, + struct vhost_scsi_virtqueue, vq); + struct vhost_scsi_tmf *tmf; + + if (vhost32_to_cpu(vq, vtmf->subtype) != + VIRTIO_SCSI_T_TMF_LOGICAL_UNIT_RESET) + goto send_reject; + + if (!tpg->tpg_nexus || !tpg->tpg_nexus->tvn_se_sess) { + pr_err("Unable to locate active struct vhost_scsi_nexus for LUN RESET.\n"); + goto send_reject; + } + + mutex_lock(&tpg->tv_tpg_mutex); + if (list_empty(&tpg->tmf_queue)) { + pr_err("Missing reserve TMF. Could not handle LUN RESET.\n"); + mutex_unlock(&tpg->tv_tpg_mutex); + goto send_reject; + } + + tmf = list_first_entry(&tpg->tmf_queue, struct vhost_scsi_tmf, + queue_entry); + list_del_init(&tmf->queue_entry); + mutex_unlock(&tpg->tv_tpg_mutex); + + tmf->tpg = tpg; + tmf->vhost = vs; + tmf->svq = svq; + tmf->resp_iov = vq->iov[vc->out]; + tmf->vq_desc = vc->head; + tmf->in_iovs = vc->in; + tmf->inflight = vhost_scsi_get_inflight(vq); + + if (target_submit_tmr(&tmf->se_cmd, tpg->tpg_nexus->tvn_se_sess, NULL, + vhost_buf_to_lun(vtmf->lun), NULL, + TMR_LUN_RESET, GFP_KERNEL, 0, + TARGET_SCF_ACK_KREF) < 0) { + vhost_scsi_release_tmf_res(tmf); + goto send_reject; + } + + return; + +send_reject: + vhost_scsi_send_tmf_resp(vs, vq, vc->in, vc->head, &vq->iov[vc->out], + VIRTIO_SCSI_S_FUNCTION_REJECTED); +} + static void vhost_scsi_send_an_resp(struct vhost_scsi *vs, struct vhost_virtqueue *vq, @@ -1170,6 +1272,7 @@ vhost_scsi_send_an_resp(struct vhost_scsi *vs, static void vhost_scsi_ctl_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) { + struct vhost_scsi_tpg *tpg; union { __virtio32 type; struct virtio_scsi_ctrl_an_req an; @@ -1251,12 +1354,12 @@ vhost_scsi_ctl_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) vc.req += typ_size; vc.req_size -= typ_size; - ret = vhost_scsi_get_req(vq, &vc, NULL); + ret = vhost_scsi_get_req(vq, &vc, &tpg); if (ret) goto err; if (v_req.type == VIRTIO_SCSI_T_TMF) - vhost_scsi_send_tmf_reject(vs, vq, &vc); + vhost_scsi_handle_tmf(vs, tpg, vq, &v_req.tmf, &vc); else vhost_scsi_send_an_resp(vs, vq, &vc); err: @@ -1373,6 +1476,83 @@ static void vhost_scsi_flush(struct vhost_scsi *vs) wait_for_completion(&old_inflight[i]->comp); } +static void vhost_scsi_destroy_vq_cmds(struct vhost_virtqueue *vq) +{ + struct vhost_scsi_virtqueue *svq = container_of(vq, + struct vhost_scsi_virtqueue, vq); + struct vhost_scsi_cmd *tv_cmd; + unsigned int i; + + if (!svq->scsi_cmds) + return; + + for (i = 0; i < svq->max_cmds; i++) { + tv_cmd = &svq->scsi_cmds[i]; + + kfree(tv_cmd->tvc_sgl); + kfree(tv_cmd->tvc_prot_sgl); + kfree(tv_cmd->tvc_upages); + } + + sbitmap_free(&svq->scsi_tags); + kfree(svq->scsi_cmds); + svq->scsi_cmds = NULL; +} + +static int vhost_scsi_setup_vq_cmds(struct vhost_virtqueue *vq, int max_cmds) +{ + struct vhost_scsi_virtqueue *svq = container_of(vq, + struct vhost_scsi_virtqueue, vq); + struct vhost_scsi_cmd *tv_cmd; + unsigned int i; + + if (svq->scsi_cmds) + return 0; + + if (sbitmap_init_node(&svq->scsi_tags, max_cmds, -1, GFP_KERNEL, + NUMA_NO_NODE)) + return -ENOMEM; + svq->max_cmds = max_cmds; + + svq->scsi_cmds = kcalloc(max_cmds, sizeof(*tv_cmd), GFP_KERNEL); + if (!svq->scsi_cmds) { + sbitmap_free(&svq->scsi_tags); + return -ENOMEM; + } + + for (i = 0; i < max_cmds; i++) { + tv_cmd = &svq->scsi_cmds[i]; + + tv_cmd->tvc_sgl = kcalloc(VHOST_SCSI_PREALLOC_SGLS, + sizeof(struct scatterlist), + GFP_KERNEL); + if (!tv_cmd->tvc_sgl) { + pr_err("Unable to allocate tv_cmd->tvc_sgl\n"); + goto out; + } + + tv_cmd->tvc_upages = kcalloc(VHOST_SCSI_PREALLOC_UPAGES, + sizeof(struct page *), + GFP_KERNEL); + if (!tv_cmd->tvc_upages) { + pr_err("Unable to allocate tv_cmd->tvc_upages\n"); + goto out; + } + + tv_cmd->tvc_prot_sgl = kcalloc(VHOST_SCSI_PREALLOC_PROT_SGLS, + sizeof(struct scatterlist), + GFP_KERNEL); + if (!tv_cmd->tvc_prot_sgl) { + pr_err("Unable to allocate tv_cmd->tvc_prot_sgl\n"); + goto out; + } + } + return 0; +out: + vhost_scsi_destroy_vq_cmds(vq); + return -ENOMEM; +} + /* * Called from vhost_scsi_ioctl() context to walk the list of available * vhost_scsi_tpg with an active struct vhost_scsi_nexus @@ -1427,10 +1607,9 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs, if (!strcmp(tv_tport->tport_name, t->vhost_wwpn)) { if (vs->vs_tpg && vs->vs_tpg[tpg->tport_tpgt]) { - kfree(vs_tpg); mutex_unlock(&tpg->tv_tpg_mutex); ret = -EEXIST; - goto out; + goto undepend; } /* * In order to ensure individual vhost-scsi configfs @@ -1442,9 +1621,8 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs, ret = target_depend_item(&se_tpg->tpg_group.cg_item); if (ret) { pr_warn("target_depend_item() failed: %d\n", ret); - kfree(vs_tpg); mutex_unlock(&tpg->tv_tpg_mutex); - goto out; + goto undepend; } tpg->tv_tpg_vhost_count++; tpg->vhost_scsi = vs; @@ -1457,6 +1635,16 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs, if (match) { memcpy(vs->vs_vhost_wwpn, t->vhost_wwpn, sizeof(vs->vs_vhost_wwpn)); + + for (i = VHOST_SCSI_VQ_IO; i < VHOST_SCSI_MAX_VQ; i++) { + vq = &vs->vqs[i].vq; + if (!vhost_vq_is_setup(vq)) + continue; + + if (vhost_scsi_setup_vq_cmds(vq, vq->num)) + goto destroy_vq_cmds; + } + for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) { vq = &vs->vqs[i].vq; mutex_lock(&vq->mutex); @@ -1476,7 +1664,22 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs, vhost_scsi_flush(vs); kfree(vs->vs_tpg); vs->vs_tpg = vs_tpg; + goto out; +destroy_vq_cmds: + for (i--; i >= VHOST_SCSI_VQ_IO; i--) { + if (!vhost_vq_get_backend(&vs->vqs[i].vq)) + vhost_scsi_destroy_vq_cmds(&vs->vqs[i].vq); + } +undepend: + for (i = 0; i < VHOST_SCSI_MAX_TARGET; i++) { + tpg = vs_tpg[i]; + if (tpg) { + tpg->tv_tpg_vhost_count--; + target_undepend_item(&tpg->se_tpg.tpg_group.cg_item); + } + } + kfree(vs_tpg); out: mutex_unlock(&vs->dev.mutex); mutex_unlock(&vhost_scsi_mutex); @@ -1549,6 +1752,12 @@ vhost_scsi_clear_endpoint(struct vhost_scsi *vs, mutex_lock(&vq->mutex); vhost_vq_set_backend(vq, NULL); mutex_unlock(&vq->mutex); + /* + * Make sure cmds are not running before tearing them + * down. + */ + vhost_scsi_flush(vs); + vhost_scsi_destroy_vq_cmds(vq); } } /* @@ -1811,11 +2020,19 @@ static int vhost_scsi_port_link(struct se_portal_group *se_tpg, { struct vhost_scsi_tpg *tpg = container_of(se_tpg, struct vhost_scsi_tpg, se_tpg); + struct vhost_scsi_tmf *tmf; + + tmf = kzalloc(sizeof(*tmf), GFP_KERNEL); + if (!tmf) + return -ENOMEM; + INIT_LIST_HEAD(&tmf->queue_entry); + vhost_work_init(&tmf->vwork, vhost_scsi_tmf_resp_work); mutex_lock(&vhost_scsi_mutex); mutex_lock(&tpg->tv_tpg_mutex); tpg->tv_tpg_port_count++; + list_add_tail(&tmf->queue_entry, &tpg->tmf_queue); mutex_unlock(&tpg->tv_tpg_mutex); vhost_scsi_hotplug(tpg, lun); @@ -1830,11 +2047,16 @@ static void vhost_scsi_port_unlink(struct se_portal_group *se_tpg, { struct vhost_scsi_tpg *tpg = container_of(se_tpg, struct vhost_scsi_tpg, se_tpg); + struct vhost_scsi_tmf *tmf; mutex_lock(&vhost_scsi_mutex); mutex_lock(&tpg->tv_tpg_mutex); tpg->tv_tpg_port_count--; + tmf = list_first_entry(&tpg->tmf_queue, struct vhost_scsi_tmf, + queue_entry); + list_del(&tmf->queue_entry); + kfree(tmf); mutex_unlock(&tpg->tv_tpg_mutex); vhost_scsi_hotunplug(tpg, lun); @@ -1842,23 +2064,6 @@ static void vhost_scsi_port_unlink(struct se_portal_group *se_tpg, mutex_unlock(&vhost_scsi_mutex); } -static void vhost_scsi_free_cmd_map_res(struct se_session *se_sess) -{ - struct vhost_scsi_cmd *tv_cmd; - unsigned int i; - - if (!se_sess->sess_cmd_map) - return; - - for (i = 0; i < VHOST_SCSI_DEFAULT_TAGS; i++) { - tv_cmd = &((struct vhost_scsi_cmd *)se_sess->sess_cmd_map)[i]; - - kfree(tv_cmd->tvc_sgl); - kfree(tv_cmd->tvc_prot_sgl); - kfree(tv_cmd->tvc_upages); - } -} - static ssize_t vhost_scsi_tpg_attrib_fabric_prot_type_store( struct config_item *item, const char *page, size_t count) { @@ -1898,45 +2103,6 @@ static struct configfs_attribute *vhost_scsi_tpg_attrib_attrs[] = { NULL, }; -static int vhost_scsi_nexus_cb(struct se_portal_group *se_tpg, - struct se_session *se_sess, void *p) -{ - struct vhost_scsi_cmd *tv_cmd; - unsigned int i; - - for (i = 0; i < VHOST_SCSI_DEFAULT_TAGS; i++) { - tv_cmd = &((struct vhost_scsi_cmd *)se_sess->sess_cmd_map)[i]; - - tv_cmd->tvc_sgl = kcalloc(VHOST_SCSI_PREALLOC_SGLS, - sizeof(struct scatterlist), - GFP_KERNEL); - if (!tv_cmd->tvc_sgl) { - pr_err("Unable to allocate tv_cmd->tvc_sgl\n"); - goto out; - } - - tv_cmd->tvc_upages = kcalloc(VHOST_SCSI_PREALLOC_UPAGES, - sizeof(struct page *), - GFP_KERNEL); - if (!tv_cmd->tvc_upages) { - pr_err("Unable to allocate tv_cmd->tvc_upages\n"); - goto out; - } - - tv_cmd->tvc_prot_sgl = kcalloc(VHOST_SCSI_PREALLOC_PROT_SGLS, - sizeof(struct scatterlist), - GFP_KERNEL); - if (!tv_cmd->tvc_prot_sgl) { - pr_err("Unable to allocate tv_cmd->tvc_prot_sgl\n"); - goto out; - } - } - return 0; -out: - vhost_scsi_free_cmd_map_res(se_sess); - return -ENOMEM; -} - static int vhost_scsi_make_nexus(struct vhost_scsi_tpg *tpg, const char *name) { @@ -1960,12 +2126,9 @@ static int vhost_scsi_make_nexus(struct vhost_scsi_tpg *tpg, * struct se_node_acl for the vhost_scsi struct se_portal_group with * the SCSI Initiator port name of the passed configfs group 'name'. */ - tv_nexus->tvn_se_sess = target_setup_session(&tpg->se_tpg, - VHOST_SCSI_DEFAULT_TAGS, - sizeof(struct vhost_scsi_cmd), + tv_nexus->tvn_se_sess = target_setup_session(&tpg->se_tpg, 0, 0, TARGET_PROT_DIN_PASS | TARGET_PROT_DOUT_PASS, - (unsigned char *)name, tv_nexus, - vhost_scsi_nexus_cb); + (unsigned char *)name, tv_nexus, NULL); if (IS_ERR(tv_nexus->tvn_se_sess)) { mutex_unlock(&tpg->tv_tpg_mutex); kfree(tv_nexus); @@ -2015,7 +2178,6 @@ static int vhost_scsi_drop_nexus(struct vhost_scsi_tpg *tpg) " %s Initiator Port: %s\n", vhost_scsi_dump_proto_id(tpg->tport), tv_nexus->tvn_se_sess->se_node_acl->initiatorname); - vhost_scsi_free_cmd_map_res(se_sess); /* * Release the SCSI I_T Nexus to the emulated vhost Target Port */ @@ -2155,6 +2317,7 @@ vhost_scsi_make_tpg(struct se_wwn *wwn, const char *name) } mutex_init(&tpg->tv_tpg_mutex); INIT_LIST_HEAD(&tpg->tv_tpg_list); + INIT_LIST_HEAD(&tpg->tmf_queue); tpg->tport = tport; tpg->tport_tpgt = tpgt; diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 5c835a292783..a262e12c6dc2 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -304,6 +304,12 @@ static void vhost_vring_call_reset(struct vhost_vring_call *call_ctx) memset(&call_ctx->producer, 0x0, sizeof(struct irq_bypass_producer)); } +bool vhost_vq_is_setup(struct vhost_virtqueue *vq) +{ + return vq->avail && vq->desc && vq->used && vhost_vq_access_ok(vq); +} +EXPORT_SYMBOL_GPL(vhost_vq_is_setup); + static void vhost_vq_reset(struct vhost_dev *dev, struct vhost_virtqueue *vq) { diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index e016cd3fa02f..b063324c7669 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -190,6 +190,7 @@ int vhost_get_vq_desc(struct vhost_virtqueue *, struct vhost_log *log, unsigned int *log_num); void vhost_discard_vq_desc(struct vhost_virtqueue *, int n); +bool vhost_vq_is_setup(struct vhost_virtqueue *vq); int vhost_vq_init_access(struct vhost_virtqueue *); int vhost_add_used(struct vhost_virtqueue *, unsigned int head, int len); int vhost_add_used_n(struct vhost_virtqueue *, struct vring_used_elem *heads, diff --git a/drivers/virt/nitro_enclaves/ne_misc_dev.c b/drivers/virt/nitro_enclaves/ne_misc_dev.c index f06622b48d69..f1964ea4b826 100644 --- a/drivers/virt/nitro_enclaves/ne_misc_dev.c +++ b/drivers/virt/nitro_enclaves/ne_misc_dev.c @@ -1505,10 +1505,8 @@ static __poll_t ne_enclave_poll(struct file *file, poll_table *wait) poll_wait(file, &ne_enclave->eventq, wait); - if (!ne_enclave->has_event) - return mask; - - mask = POLLHUP; + if (ne_enclave->has_event) + mask |= EPOLLHUP; return mask; } diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index 71ce1b7a23d1..2b385c1b4a99 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -395,8 +395,7 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page, */ trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force); - map = swiotlb_tbl_map_single(dev, virt_to_phys(xen_io_tlb_start), - phys, size, size, dir, attrs); + map = swiotlb_tbl_map_single(dev, phys, size, size, dir, attrs); if (map == (phys_addr_t)DMA_MAPPING_ERROR) return DMA_MAPPING_ERROR; diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 1bb5b9d7f0a2..9068d5578a26 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -823,6 +823,7 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry, vp->cb_break_before = afs_calc_vnode_cb_break(vnode); vp->vnode = vnode; vp->put_vnode = true; + vp->speculative = true; /* vnode not locked */ } } } diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 0fe8844b4bee..b0d7b892090d 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -294,6 +294,13 @@ void afs_vnode_commit_status(struct afs_operation *op, struct afs_vnode_param *v op->flags &= ~AFS_OPERATION_DIR_CONFLICT; } } else if (vp->scb.have_status) { + if (vp->dv_before + vp->dv_delta != vp->scb.status.data_version && + vp->speculative) + /* Ignore the result of a speculative bulk status fetch + * if it splits around a modification op, thereby + * appearing to regress the data version. + */ + goto out; afs_apply_status(op, vp); if (vp->scb.have_cb) afs_apply_callback(op, vp); @@ -305,6 +312,7 @@ void afs_vnode_commit_status(struct afs_operation *op, struct afs_vnode_param *v } } +out: write_sequnlock(&vnode->cb_lock); if (vp->scb.have_status) diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 14d5d75f4b6e..0d150a29e39e 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -755,6 +755,7 @@ struct afs_vnode_param { bool update_ctime:1; /* Need to update the ctime */ bool set_size:1; /* Must update i_size */ bool op_unlinked:1; /* True if file was unlinked by op */ + bool speculative:1; /* T if speculative status fetch (no vnode lock) */ }; /* diff --git a/fs/afs/write.c b/fs/afs/write.c index 50371207f327..c9195fc67fd8 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -169,11 +169,14 @@ int afs_write_end(struct file *file, struct address_space *mapping, unsigned int f, from = pos & (PAGE_SIZE - 1); unsigned int t, to = from + copied; loff_t i_size, maybe_i_size; - int ret; + int ret = 0; _enter("{%llx:%llu},{%lx}", vnode->fid.vid, vnode->fid.vnode, page->index); + if (copied == 0) + goto out; + maybe_i_size = pos + copied; i_size = i_size_read(&vnode->vfs_inode); diff --git a/fs/afs/xattr.c b/fs/afs/xattr.c index 38884d6c57cd..95c573dcda11 100644 --- a/fs/afs/xattr.c +++ b/fs/afs/xattr.c @@ -148,11 +148,6 @@ static const struct xattr_handler afs_xattr_afs_acl_handler = { .set = afs_xattr_set_acl, }; -static void yfs_acl_put(struct afs_operation *op) -{ - yfs_free_opaque_acl(op->yacl); -} - static const struct afs_operation_ops yfs_fetch_opaque_acl_operation = { .issue_yfs_rpc = yfs_fs_fetch_opaque_acl, .success = afs_acl_success, @@ -246,7 +241,7 @@ error: static const struct afs_operation_ops yfs_store_opaque_acl2_operation = { .issue_yfs_rpc = yfs_fs_store_opaque_acl2, .success = afs_acl_success, - .put = yfs_acl_put, + .put = afs_acl_put, }; /* diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c index 3b1239b7e90d..bd787e71a657 100644 --- a/fs/afs/yfsclient.c +++ b/fs/afs/yfsclient.c @@ -1990,6 +1990,7 @@ void yfs_fs_store_opaque_acl2(struct afs_operation *op) memcpy(bp, acl->data, acl->size); if (acl->size != size) memset((void *)bp + acl->size, 0, size - acl->size); + bp += size / sizeof(__be32); yfs_check_req(call, bp); trace_afs_make_fs_call(call, &vp->fid); @@ -1572,7 +1572,7 @@ static int aio_write(struct kiocb *req, const struct iocb *iocb, * we return to userspace. */ if (S_ISREG(file_inode(file)->i_mode)) { - __sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, true); + sb_start_write(file_inode(file)->i_sb); __sb_writers_release(file_inode(file)->i_sb, SB_FREEZE_WRITE); } req->ki_flags |= IOCB_WRITE; diff --git a/fs/btrfs/block-rsv.c b/fs/btrfs/block-rsv.c index 7e1549a84fcc..bc920afe23bf 100644 --- a/fs/btrfs/block-rsv.c +++ b/fs/btrfs/block-rsv.c @@ -511,7 +511,8 @@ again: /*DEFAULT_RATELIMIT_BURST*/ 1); if (__ratelimit(&_rs)) WARN(1, KERN_DEBUG - "BTRFS: block rsv returned %d\n", ret); + "BTRFS: block rsv %d returned %d\n", + block_rsv->type, ret); } try_reserve: ret = btrfs_reserve_metadata_bytes(root, block_rsv, blocksize, diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 5b9e3f3ace22..10638537b9ef 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -91,6 +91,17 @@ int btrfs_init_dev_replace(struct btrfs_fs_info *fs_info) ret = btrfs_search_slot(NULL, dev_root, &key, path, 0, 0); if (ret) { no_valid_dev_replace_entry_found: + /* + * We don't have a replace item or it's corrupted. If there is + * a replace target, fail the mount. + */ + if (btrfs_find_device(fs_info->fs_devices, + BTRFS_DEV_REPLACE_DEVID, NULL, NULL, false)) { + btrfs_err(fs_info, + "found replace target device without a valid replace item"); + ret = -EUCLEAN; + goto out; + } ret = 0; dev_replace->replace_state = BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED; @@ -143,8 +154,19 @@ no_valid_dev_replace_entry_found: case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED: case BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED: case BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED: - dev_replace->srcdev = NULL; - dev_replace->tgtdev = NULL; + /* + * We don't have an active replace item but if there is a + * replace target, fail the mount. + */ + if (btrfs_find_device(fs_info->fs_devices, + BTRFS_DEV_REPLACE_DEVID, NULL, NULL, false)) { + btrfs_err(fs_info, + "replace devid present without an active replace item"); + ret = -EUCLEAN; + } else { + dev_replace->srcdev = NULL; + dev_replace->tgtdev = NULL; + } break; case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED: case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED: diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index ab408a23ba32..69a384145dc6 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1274,6 +1274,7 @@ static int cluster_pages_for_defrag(struct inode *inode, u64 page_start; u64 page_end; u64 page_cnt; + u64 start = (u64)start_index << PAGE_SHIFT; int ret; int i; int i_done; @@ -1290,8 +1291,7 @@ static int cluster_pages_for_defrag(struct inode *inode, page_cnt = min_t(u64, (u64)num_pages, (u64)file_end - start_index + 1); ret = btrfs_delalloc_reserve_space(BTRFS_I(inode), &data_reserved, - start_index << PAGE_SHIFT, - page_cnt << PAGE_SHIFT); + start, page_cnt << PAGE_SHIFT); if (ret) return ret; i_done = 0; @@ -1380,8 +1380,7 @@ again: btrfs_mod_outstanding_extents(BTRFS_I(inode), 1); spin_unlock(&BTRFS_I(inode)->lock); btrfs_delalloc_release_space(BTRFS_I(inode), data_reserved, - start_index << PAGE_SHIFT, - (page_cnt - i_done) << PAGE_SHIFT, true); + start, (page_cnt - i_done) << PAGE_SHIFT, true); } @@ -1408,8 +1407,7 @@ out: put_page(pages[i]); } btrfs_delalloc_release_space(BTRFS_I(inode), data_reserved, - start_index << PAGE_SHIFT, - page_cnt << PAGE_SHIFT, true); + start, page_cnt << PAGE_SHIFT, true); btrfs_delalloc_release_extents(BTRFS_I(inode), page_cnt << PAGE_SHIFT); extent_changeset_free(data_reserved); return ret; diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index c54ea6586632..77c54749f432 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -3435,24 +3435,20 @@ static int qgroup_unreserve_range(struct btrfs_inode *inode, { struct rb_node *node; struct rb_node *next; - struct ulist_node *entry = NULL; + struct ulist_node *entry; int ret = 0; node = reserved->range_changed.root.rb_node; + if (!node) + return 0; while (node) { entry = rb_entry(node, struct ulist_node, rb_node); if (entry->val < start) node = node->rb_right; - else if (entry) - node = node->rb_left; else - break; + node = node->rb_left; } - /* Empty changeset */ - if (!entry) - return 0; - if (entry->val > start && rb_prev(&entry->rb_node)) entry = rb_entry(rb_prev(&entry->rb_node), struct ulist_node, rb_node); diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c index 7f03dbe5b609..78693d3dd15b 100644 --- a/fs/btrfs/ref-verify.c +++ b/fs/btrfs/ref-verify.c @@ -860,6 +860,7 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info, "dropping a ref for a root that doesn't have a ref on the block"); dump_block_entry(fs_info, be); dump_ref_action(fs_info, ra); + kfree(ref); kfree(ra); goto out_unlock; } diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 3602806d71bd..9ba92d86da0b 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -1648,6 +1648,7 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc, struct btrfs_root_item *root_item; struct btrfs_path *path; struct extent_buffer *leaf; + int reserve_level; int level; int max_level; int replaced = 0; @@ -1696,7 +1697,8 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc, * Thus the needed metadata size is at most root_level * nodesize, * and * 2 since we have two trees to COW. */ - min_reserved = fs_info->nodesize * btrfs_root_level(root_item) * 2; + reserve_level = max_t(int, 1, btrfs_root_level(root_item)); + min_reserved = fs_info->nodesize * reserve_level * 2; memset(&next_key, 0, sizeof(next_key)); while (1) { diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index cf63f1e27a27..e71e7586e9eb 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -3866,8 +3866,9 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, if (!is_dev_replace && !readonly && !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state)) { mutex_unlock(&fs_info->fs_devices->device_list_mutex); - btrfs_err_in_rcu(fs_info, "scrub: device %s is not writable", - rcu_str_deref(dev->name)); + btrfs_err_in_rcu(fs_info, + "scrub on devid %llu: filesystem on %s is not writable", + devid, rcu_str_deref(dev->name)); ret = -EROFS; goto out; } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index b1e48078c318..a6406b3b8c2b 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1056,22 +1056,13 @@ static void __btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices, continue; } - if (device->devid == BTRFS_DEV_REPLACE_DEVID) { - /* - * In the first step, keep the device which has - * the correct fsid and the devid that is used - * for the dev_replace procedure. - * In the second step, the dev_replace state is - * read from the device tree and it is known - * whether the procedure is really active or - * not, which means whether this device is - * used or whether it should be removed. - */ - if (step == 0 || test_bit(BTRFS_DEV_STATE_REPLACE_TGT, - &device->dev_state)) { - continue; - } - } + /* + * We have already validated the presence of BTRFS_DEV_REPLACE_DEVID, + * in btrfs_init_dev_replace() so just continue. + */ + if (device->devid == BTRFS_DEV_REPLACE_DEVID) + continue; + if (device->bdev) { blkdev_put(device->bdev, device->mode); device->bdev = NULL; @@ -1080,9 +1071,6 @@ static void __btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices, if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) { list_del_init(&device->dev_alloc_list); clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state); - if (!test_bit(BTRFS_DEV_STATE_REPLACE_TGT, - &device->dev_state)) - fs_devices->rw_devices--; } list_del_init(&device->dev_list); fs_devices->num_devices--; diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 5027bbdca419..ded4229c314a 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -4074,7 +4074,7 @@ void ceph_handle_caps(struct ceph_mds_session *session, vino.snap, inode); mutex_lock(&session->s_mutex); - session->s_seq++; + inc_session_sequence(session); dout(" mds%d seq %lld cap seq %u\n", session->s_mds, session->s_seq, (unsigned)seq); diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 08f1c0c31dc2..8f1d7500a7ec 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -4231,7 +4231,7 @@ static void handle_lease(struct ceph_mds_client *mdsc, dname.len, dname.name); mutex_lock(&session->s_mutex); - session->s_seq++; + inc_session_sequence(session); if (!inode) { dout("handle_lease no inode %llx\n", vino.ino); @@ -4385,29 +4385,49 @@ static void maybe_recover_session(struct ceph_mds_client *mdsc) bool check_session_state(struct ceph_mds_session *s) { - if (s->s_state == CEPH_MDS_SESSION_CLOSING) { - dout("resending session close request for mds%d\n", - s->s_mds); - request_close_session(s); - return false; - } - if (s->s_ttl && time_after(jiffies, s->s_ttl)) { - if (s->s_state == CEPH_MDS_SESSION_OPEN) { + switch (s->s_state) { + case CEPH_MDS_SESSION_OPEN: + if (s->s_ttl && time_after(jiffies, s->s_ttl)) { s->s_state = CEPH_MDS_SESSION_HUNG; pr_info("mds%d hung\n", s->s_mds); } - } - if (s->s_state == CEPH_MDS_SESSION_NEW || - s->s_state == CEPH_MDS_SESSION_RESTARTING || - s->s_state == CEPH_MDS_SESSION_CLOSED || - s->s_state == CEPH_MDS_SESSION_REJECTED) - /* this mds is failed or recovering, just wait */ + break; + case CEPH_MDS_SESSION_CLOSING: + /* Should never reach this when we're unmounting */ + WARN_ON_ONCE(true); + fallthrough; + case CEPH_MDS_SESSION_NEW: + case CEPH_MDS_SESSION_RESTARTING: + case CEPH_MDS_SESSION_CLOSED: + case CEPH_MDS_SESSION_REJECTED: return false; + } return true; } /* + * If the sequence is incremented while we're waiting on a REQUEST_CLOSE reply, + * then we need to retransmit that request. + */ +void inc_session_sequence(struct ceph_mds_session *s) +{ + lockdep_assert_held(&s->s_mutex); + + s->s_seq++; + + if (s->s_state == CEPH_MDS_SESSION_CLOSING) { + int ret; + + dout("resending session close request for mds%d\n", s->s_mds); + ret = request_close_session(s); + if (ret < 0) + pr_err("unable to close session to mds%d: %d\n", + s->s_mds, ret); + } +} + +/* * delayed work -- periodically trim expired leases, renew caps with mds */ static void schedule_delayed(struct ceph_mds_client *mdsc) diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index cbf8af437140..f5adbebcb38e 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -480,6 +480,7 @@ struct ceph_mds_client { extern const char *ceph_mds_op_name(int op); extern bool check_session_state(struct ceph_mds_session *s); +void inc_session_sequence(struct ceph_mds_session *s); extern struct ceph_mds_session * __ceph_lookup_mds_session(struct ceph_mds_client *, int mds); diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c index 83cb4f26b689..9b785f11e95a 100644 --- a/fs/ceph/quota.c +++ b/fs/ceph/quota.c @@ -53,7 +53,7 @@ void ceph_handle_quota(struct ceph_mds_client *mdsc, /* increment msg sequence number */ mutex_lock(&session->s_mutex); - session->s_seq++; + inc_session_sequence(session); mutex_unlock(&session->s_mutex); /* lookup inode */ diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index 0da39c16dab4..b611f829cb61 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -873,7 +873,7 @@ void ceph_handle_snap(struct ceph_mds_client *mdsc, ceph_snap_op_name(op), split, trace_len); mutex_lock(&session->s_mutex); - session->s_seq++; + inc_session_sequence(session); mutex_unlock(&session->s_mutex); down_write(&mdsc->snap_rwsem); diff --git a/fs/crypto/inline_crypt.c b/fs/crypto/inline_crypt.c index 89bffa82ed74..c57bebfa48fe 100644 --- a/fs/crypto/inline_crypt.c +++ b/fs/crypto/inline_crypt.c @@ -74,7 +74,7 @@ int fscrypt_select_encryption_impl(struct fscrypt_info *ci) int i; /* The file must need contents encryption, not filenames encryption */ - if (!fscrypt_needs_contents_encryption(inode)) + if (!S_ISREG(inode->i_mode)) return 0; /* The crypto mode must have a blk-crypto counterpart */ diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c index d3c3e5d9b41f..d595abb8ef90 100644 --- a/fs/crypto/keysetup.c +++ b/fs/crypto/keysetup.c @@ -269,9 +269,7 @@ unlock: * New inodes may not have an inode number assigned yet. * Hashing their inode number is delayed until later. */ - if (ci->ci_inode->i_ino == 0) - WARN_ON(!(ci->ci_inode->i_state & I_CREATING)); - else + if (ci->ci_inode->i_ino) fscrypt_hash_inode_number(ci, mk); return 0; } diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index 15880a68faad..f943fd0b0699 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -21,6 +21,7 @@ LIST_HEAD(efivarfs_list); static void efivarfs_evict_inode(struct inode *inode) { clear_inode(inode); + kfree(inode->i_private); } static const struct super_operations efivarfs_ops = { diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c index 139d0bed42f8..3e21c0e8adae 100644 --- a/fs/erofs/inode.c +++ b/fs/erofs/inode.c @@ -107,11 +107,9 @@ static struct page *erofs_read_inode(struct inode *inode, i_gid_write(inode, le32_to_cpu(die->i_gid)); set_nlink(inode, le32_to_cpu(die->i_nlink)); - /* ns timestamp */ - inode->i_mtime.tv_sec = inode->i_ctime.tv_sec = - le64_to_cpu(die->i_ctime); - inode->i_mtime.tv_nsec = inode->i_ctime.tv_nsec = - le32_to_cpu(die->i_ctime_nsec); + /* extended inode has its own timestamp */ + inode->i_ctime.tv_sec = le64_to_cpu(die->i_ctime); + inode->i_ctime.tv_nsec = le32_to_cpu(die->i_ctime_nsec); inode->i_size = le64_to_cpu(die->i_size); @@ -149,11 +147,9 @@ static struct page *erofs_read_inode(struct inode *inode, i_gid_write(inode, le16_to_cpu(dic->i_gid)); set_nlink(inode, le16_to_cpu(dic->i_nlink)); - /* use build time to derive all file time */ - inode->i_mtime.tv_sec = inode->i_ctime.tv_sec = - sbi->build_time; - inode->i_mtime.tv_nsec = inode->i_ctime.tv_nsec = - sbi->build_time_nsec; + /* use build time for compact inodes */ + inode->i_ctime.tv_sec = sbi->build_time; + inode->i_ctime.tv_nsec = sbi->build_time_nsec; inode->i_size = le32_to_cpu(dic->i_size); if (erofs_inode_is_data_compressed(vi->datalayout)) @@ -167,6 +163,11 @@ static struct page *erofs_read_inode(struct inode *inode, goto err_out; } + inode->i_mtime.tv_sec = inode->i_ctime.tv_sec; + inode->i_atime.tv_sec = inode->i_ctime.tv_sec; + inode->i_mtime.tv_nsec = inode->i_ctime.tv_nsec; + inode->i_atime.tv_nsec = inode->i_ctime.tv_nsec; + if (!nblks) /* measure inode.i_blocks as generic filesystems */ inode->i_blocks = roundup(inode->i_size, EROFS_BLKSIZ) >> 9; diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 50912a5420b4..86fd3bf62af6 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -1078,8 +1078,11 @@ out_allocpage: cond_resched(); goto repeat; } - set_page_private(page, (unsigned long)pcl); - SetPagePrivate(page); + + if (tocache) { + set_page_private(page, (unsigned long)pcl); + SetPagePrivate(page); + } out: /* the only exit (for tracing and debugging) */ return page; } diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 45fcdbf538d1..65ecaf96d0a4 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1028,9 +1028,6 @@ struct ext4_inode_info { * protected by sbi->s_fc_lock. */ - /* Fast commit subtid when this inode was committed */ - unsigned int i_fc_committed_subtid; - /* Start of lblk range that needs to be committed in this fast commit */ ext4_lblk_t i_fc_lblk_start; @@ -1234,13 +1231,13 @@ struct ext4_inode_info { blocks */ #define EXT4_MOUNT2_HURD_COMPAT 0x00000004 /* Support HURD-castrated file systems */ -#define EXT4_MOUNT2_DAX_NEVER 0x00000008 /* Do not allow Direct Access */ -#define EXT4_MOUNT2_DAX_INODE 0x00000010 /* For printing options only */ - #define EXT4_MOUNT2_EXPLICIT_JOURNAL_CHECKSUM 0x00000008 /* User explicitly specified journal checksum */ #define EXT4_MOUNT2_JOURNAL_FAST_COMMIT 0x00000010 /* Journal fast commit */ +#define EXT4_MOUNT2_DAX_NEVER 0x00000020 /* Do not allow Direct Access */ +#define EXT4_MOUNT2_DAX_INODE 0x00000040 /* For printing options only */ + #define clear_opt(sb, opt) EXT4_SB(sb)->s_mount_opt &= \ ~EXT4_MOUNT_##opt @@ -1422,16 +1419,6 @@ struct ext4_super_block { #ifdef __KERNEL__ -/* - * run-time mount flags - */ -#define EXT4_MF_MNTDIR_SAMPLED 0x0001 -#define EXT4_MF_FS_ABORTED 0x0002 /* Fatal error detected */ -#define EXT4_MF_FC_INELIGIBLE 0x0004 /* Fast commit ineligible */ -#define EXT4_MF_FC_COMMITTING 0x0008 /* File system underoing a fast - * commit. - */ - #ifdef CONFIG_FS_ENCRYPTION #define DUMMY_ENCRYPTION_ENABLED(sbi) ((sbi)->s_dummy_enc_policy.policy != NULL) #else @@ -1466,7 +1453,7 @@ struct ext4_sb_info { struct buffer_head * __rcu *s_group_desc; unsigned int s_mount_opt; unsigned int s_mount_opt2; - unsigned int s_mount_flags; + unsigned long s_mount_flags; unsigned int s_def_mount_opt; ext4_fsblk_t s_sb_block; atomic64_t s_resv_clusters; @@ -1695,6 +1682,34 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) }) /* + * run-time mount flags + */ +enum { + EXT4_MF_MNTDIR_SAMPLED, + EXT4_MF_FS_ABORTED, /* Fatal error detected */ + EXT4_MF_FC_INELIGIBLE, /* Fast commit ineligible */ + EXT4_MF_FC_COMMITTING /* File system underoing a fast + * commit. + */ +}; + +static inline void ext4_set_mount_flag(struct super_block *sb, int bit) +{ + set_bit(bit, &EXT4_SB(sb)->s_mount_flags); +} + +static inline void ext4_clear_mount_flag(struct super_block *sb, int bit) +{ + clear_bit(bit, &EXT4_SB(sb)->s_mount_flags); +} + +static inline int ext4_test_mount_flag(struct super_block *sb, int bit) +{ + return test_bit(bit, &EXT4_SB(sb)->s_mount_flags); +} + + +/* * Simulate_fail codes */ #define EXT4_SIM_BBITMAP_EIO 1 @@ -1863,6 +1878,13 @@ static inline bool ext4_verity_in_progress(struct inode *inode) #define EXT4_FEATURE_COMPAT_RESIZE_INODE 0x0010 #define EXT4_FEATURE_COMPAT_DIR_INDEX 0x0020 #define EXT4_FEATURE_COMPAT_SPARSE_SUPER2 0x0200 +/* + * The reason why "FAST_COMMIT" is a compat feature is that, FS becomes + * incompatible only if fast commit blocks are present in the FS. Since we + * clear the journal (and thus the fast commit blocks), we don't mark FS as + * incompatible. We also have a JBD2 incompat feature, which gets set when + * there are fast commit blocks present in the journal. + */ #define EXT4_FEATURE_COMPAT_FAST_COMMIT 0x0400 #define EXT4_FEATURE_COMPAT_STABLE_INODES 0x0800 @@ -2673,7 +2695,8 @@ void ext4_insert_dentry(struct inode *inode, struct ext4_filename *fname); static inline void ext4_update_dx_flag(struct inode *inode) { - if (!ext4_has_feature_dir_index(inode->i_sb)) { + if (!ext4_has_feature_dir_index(inode->i_sb) && + ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) { /* ext4_iget() should have caught this... */ WARN_ON_ONCE(ext4_has_feature_metadata_csum(inode->i_sb)); ext4_clear_inode_flag(inode, EXT4_INODE_INDEX); @@ -2731,12 +2754,16 @@ extern void ext4_end_bitmap_read(struct buffer_head *bh, int uptodate); int ext4_fc_info_show(struct seq_file *seq, void *v); void ext4_fc_init(struct super_block *sb, journal_t *journal); void ext4_fc_init_inode(struct inode *inode); -void ext4_fc_track_range(struct inode *inode, ext4_lblk_t start, +void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t start, ext4_lblk_t end); -void ext4_fc_track_unlink(struct inode *inode, struct dentry *dentry); -void ext4_fc_track_link(struct inode *inode, struct dentry *dentry); -void ext4_fc_track_create(struct inode *inode, struct dentry *dentry); -void ext4_fc_track_inode(struct inode *inode); +void __ext4_fc_track_unlink(handle_t *handle, struct inode *inode, + struct dentry *dentry); +void __ext4_fc_track_link(handle_t *handle, struct inode *inode, + struct dentry *dentry); +void ext4_fc_track_unlink(handle_t *handle, struct dentry *dentry); +void ext4_fc_track_link(handle_t *handle, struct dentry *dentry); +void ext4_fc_track_create(handle_t *handle, struct dentry *dentry); +void ext4_fc_track_inode(handle_t *handle, struct inode *inode); void ext4_fc_mark_ineligible(struct super_block *sb, int reason); void ext4_fc_start_ineligible(struct super_block *sb, int reason); void ext4_fc_stop_ineligible(struct super_block *sb); @@ -3452,7 +3479,7 @@ extern int ext4_handle_dirty_dirblock(handle_t *handle, struct inode *inode, extern int ext4_ci_compare(const struct inode *parent, const struct qstr *fname, const struct qstr *entry, bool quick); -extern int __ext4_unlink(struct inode *dir, const struct qstr *d_name, +extern int __ext4_unlink(handle_t *handle, struct inode *dir, const struct qstr *d_name, struct inode *inode); extern int __ext4_link(struct inode *dir, struct inode *inode, struct dentry *dentry); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 57cfa28919a9..17d7096b3212 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3724,7 +3724,6 @@ static int ext4_convert_unwritten_extents_endio(handle_t *handle, err = ext4_ext_dirty(handle, inode, path + path->p_depth); out: ext4_ext_show_leaf(inode, path); - ext4_fc_track_range(inode, ee_block, ee_block + ee_len - 1); return err; } @@ -3796,7 +3795,6 @@ convert_initialized_extent(handle_t *handle, struct inode *inode, if (*allocated > map->m_len) *allocated = map->m_len; map->m_len = *allocated; - ext4_fc_track_range(inode, ee_block, ee_block + ee_len - 1); return 0; } @@ -4329,7 +4327,6 @@ got_allocated_blocks: map->m_len = ar.len; allocated = map->m_len; ext4_ext_show_leaf(inode, path); - ext4_fc_track_range(inode, map->m_lblk, map->m_lblk + map->m_len - 1); out: ext4_ext_drop_refs(path); kfree(path); @@ -4602,7 +4599,7 @@ static long ext4_zero_range(struct file *file, loff_t offset, ret = ext4_mark_inode_dirty(handle, inode); if (unlikely(ret)) goto out_handle; - ext4_fc_track_range(inode, offset >> inode->i_sb->s_blocksize_bits, + ext4_fc_track_range(handle, inode, offset >> inode->i_sb->s_blocksize_bits, (offset + len - 1) >> inode->i_sb->s_blocksize_bits); /* Zero out partial block at the edges of the range */ ret = ext4_zero_partial_blocks(handle, inode, offset, len); @@ -4651,8 +4648,6 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE | FALLOC_FL_INSERT_RANGE)) return -EOPNOTSUPP; - ext4_fc_track_range(inode, offset >> blkbits, - (offset + len - 1) >> blkbits); ext4_fc_start_update(inode); diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index 8d43058386c3..f2033e13a273 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -83,7 +83,7 @@ * * Atomicity of commits * -------------------- - * In order to gaurantee atomicity during the commit operation, fast commit + * In order to guarantee atomicity during the commit operation, fast commit * uses "EXT4_FC_TAG_TAIL" tag that marks a fast commit as complete. Tail * tag contains CRC of the contents and TID of the transaction after which * this fast commit should be applied. Recovery code replays fast commit @@ -152,7 +152,31 @@ void ext4_fc_init_inode(struct inode *inode) INIT_LIST_HEAD(&ei->i_fc_list); init_waitqueue_head(&ei->i_fc_wait); atomic_set(&ei->i_fc_updates, 0); - ei->i_fc_committed_subtid = 0; +} + +/* This function must be called with sbi->s_fc_lock held. */ +static void ext4_fc_wait_committing_inode(struct inode *inode) +__releases(&EXT4_SB(inode->i_sb)->s_fc_lock) +{ + wait_queue_head_t *wq; + struct ext4_inode_info *ei = EXT4_I(inode); + +#if (BITS_PER_LONG < 64) + DEFINE_WAIT_BIT(wait, &ei->i_state_flags, + EXT4_STATE_FC_COMMITTING); + wq = bit_waitqueue(&ei->i_state_flags, + EXT4_STATE_FC_COMMITTING); +#else + DEFINE_WAIT_BIT(wait, &ei->i_flags, + EXT4_STATE_FC_COMMITTING); + wq = bit_waitqueue(&ei->i_flags, + EXT4_STATE_FC_COMMITTING); +#endif + lockdep_assert_held(&EXT4_SB(inode->i_sb)->s_fc_lock); + prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); + spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock); + schedule(); + finish_wait(wq, &wait.wq_entry); } /* @@ -176,22 +200,7 @@ restart: goto out; if (ext4_test_inode_state(inode, EXT4_STATE_FC_COMMITTING)) { - wait_queue_head_t *wq; -#if (BITS_PER_LONG < 64) - DEFINE_WAIT_BIT(wait, &ei->i_state_flags, - EXT4_STATE_FC_COMMITTING); - wq = bit_waitqueue(&ei->i_state_flags, - EXT4_STATE_FC_COMMITTING); -#else - DEFINE_WAIT_BIT(wait, &ei->i_flags, - EXT4_STATE_FC_COMMITTING); - wq = bit_waitqueue(&ei->i_flags, - EXT4_STATE_FC_COMMITTING); -#endif - prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); - spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock); - schedule(); - finish_wait(wq, &wait.wq_entry); + ext4_fc_wait_committing_inode(inode); goto restart; } out: @@ -234,26 +243,10 @@ restart: } if (ext4_test_inode_state(inode, EXT4_STATE_FC_COMMITTING)) { - wait_queue_head_t *wq; -#if (BITS_PER_LONG < 64) - DEFINE_WAIT_BIT(wait, &ei->i_state_flags, - EXT4_STATE_FC_COMMITTING); - wq = bit_waitqueue(&ei->i_state_flags, - EXT4_STATE_FC_COMMITTING); -#else - DEFINE_WAIT_BIT(wait, &ei->i_flags, - EXT4_STATE_FC_COMMITTING); - wq = bit_waitqueue(&ei->i_flags, - EXT4_STATE_FC_COMMITTING); -#endif - prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); - spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock); - schedule(); - finish_wait(wq, &wait.wq_entry); + ext4_fc_wait_committing_inode(inode); goto restart; } - if (!list_empty(&ei->i_fc_list)) - list_del_init(&ei->i_fc_list); + list_del_init(&ei->i_fc_list); spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock); } @@ -269,7 +262,7 @@ void ext4_fc_mark_ineligible(struct super_block *sb, int reason) (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY)) return; - sbi->s_mount_flags |= EXT4_MF_FC_INELIGIBLE; + ext4_set_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); WARN_ON(reason >= EXT4_FC_REASON_MAX); sbi->s_fc_stats.fc_ineligible_reason_count[reason]++; } @@ -302,14 +295,14 @@ void ext4_fc_stop_ineligible(struct super_block *sb) (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY)) return; - EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FC_INELIGIBLE; + ext4_set_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); atomic_dec(&EXT4_SB(sb)->s_fc_ineligible_updates); } static inline int ext4_fc_is_ineligible(struct super_block *sb) { - return (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FC_INELIGIBLE) || - atomic_read(&EXT4_SB(sb)->s_fc_ineligible_updates); + return (ext4_test_mount_flag(sb, EXT4_MF_FC_INELIGIBLE) || + atomic_read(&EXT4_SB(sb)->s_fc_ineligible_updates)); } /* @@ -323,13 +316,14 @@ static inline int ext4_fc_is_ineligible(struct super_block *sb) * If enqueue is set, this function enqueues the inode in fast commit list. */ static int ext4_fc_track_template( - struct inode *inode, int (*__fc_track_fn)(struct inode *, void *, bool), + handle_t *handle, struct inode *inode, + int (*__fc_track_fn)(struct inode *, void *, bool), void *args, int enqueue) { - tid_t running_txn_tid; bool update = false; struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + tid_t tid = 0; int ret; if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) || @@ -339,15 +333,13 @@ static int ext4_fc_track_template( if (ext4_fc_is_ineligible(inode->i_sb)) return -EINVAL; - running_txn_tid = sbi->s_journal ? - sbi->s_journal->j_commit_sequence + 1 : 0; - + tid = handle->h_transaction->t_tid; mutex_lock(&ei->i_fc_lock); - if (running_txn_tid == ei->i_sync_tid) { + if (tid == ei->i_sync_tid) { update = true; } else { ext4_fc_reset_inode(inode); - ei->i_sync_tid = running_txn_tid; + ei->i_sync_tid = tid; } ret = __fc_track_fn(inode, args, update); mutex_unlock(&ei->i_fc_lock); @@ -358,7 +350,7 @@ static int ext4_fc_track_template( spin_lock(&sbi->s_fc_lock); if (list_empty(&EXT4_I(inode)->i_fc_list)) list_add_tail(&EXT4_I(inode)->i_fc_list, - (sbi->s_mount_flags & EXT4_MF_FC_COMMITTING) ? + (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_COMMITTING)) ? &sbi->s_fc_q[FC_Q_STAGING] : &sbi->s_fc_q[FC_Q_MAIN]); spin_unlock(&sbi->s_fc_lock); @@ -384,7 +376,7 @@ static int __track_dentry_update(struct inode *inode, void *arg, bool update) mutex_unlock(&ei->i_fc_lock); node = kmem_cache_alloc(ext4_fc_dentry_cachep, GFP_NOFS); if (!node) { - ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_MEM); + ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM); mutex_lock(&ei->i_fc_lock); return -ENOMEM; } @@ -397,7 +389,7 @@ static int __track_dentry_update(struct inode *inode, void *arg, bool update) if (!node->fcd_name.name) { kmem_cache_free(ext4_fc_dentry_cachep, node); ext4_fc_mark_ineligible(inode->i_sb, - EXT4_FC_REASON_MEM); + EXT4_FC_REASON_NOMEM); mutex_lock(&ei->i_fc_lock); return -ENOMEM; } @@ -411,7 +403,7 @@ static int __track_dentry_update(struct inode *inode, void *arg, bool update) node->fcd_name.len = dentry->d_name.len; spin_lock(&sbi->s_fc_lock); - if (sbi->s_mount_flags & EXT4_MF_FC_COMMITTING) + if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_COMMITTING)) list_add_tail(&node->fcd_list, &sbi->s_fc_dentry_q[FC_Q_STAGING]); else @@ -422,7 +414,8 @@ static int __track_dentry_update(struct inode *inode, void *arg, bool update) return 0; } -void ext4_fc_track_unlink(struct inode *inode, struct dentry *dentry) +void __ext4_fc_track_unlink(handle_t *handle, + struct inode *inode, struct dentry *dentry) { struct __track_dentry_update_args args; int ret; @@ -430,12 +423,18 @@ void ext4_fc_track_unlink(struct inode *inode, struct dentry *dentry) args.dentry = dentry; args.op = EXT4_FC_TAG_UNLINK; - ret = ext4_fc_track_template(inode, __track_dentry_update, + ret = ext4_fc_track_template(handle, inode, __track_dentry_update, (void *)&args, 0); trace_ext4_fc_track_unlink(inode, dentry, ret); } -void ext4_fc_track_link(struct inode *inode, struct dentry *dentry) +void ext4_fc_track_unlink(handle_t *handle, struct dentry *dentry) +{ + __ext4_fc_track_unlink(handle, d_inode(dentry), dentry); +} + +void __ext4_fc_track_link(handle_t *handle, + struct inode *inode, struct dentry *dentry) { struct __track_dentry_update_args args; int ret; @@ -443,20 +442,26 @@ void ext4_fc_track_link(struct inode *inode, struct dentry *dentry) args.dentry = dentry; args.op = EXT4_FC_TAG_LINK; - ret = ext4_fc_track_template(inode, __track_dentry_update, + ret = ext4_fc_track_template(handle, inode, __track_dentry_update, (void *)&args, 0); trace_ext4_fc_track_link(inode, dentry, ret); } -void ext4_fc_track_create(struct inode *inode, struct dentry *dentry) +void ext4_fc_track_link(handle_t *handle, struct dentry *dentry) +{ + __ext4_fc_track_link(handle, d_inode(dentry), dentry); +} + +void ext4_fc_track_create(handle_t *handle, struct dentry *dentry) { struct __track_dentry_update_args args; + struct inode *inode = d_inode(dentry); int ret; args.dentry = dentry; args.op = EXT4_FC_TAG_CREAT; - ret = ext4_fc_track_template(inode, __track_dentry_update, + ret = ext4_fc_track_template(handle, inode, __track_dentry_update, (void *)&args, 0); trace_ext4_fc_track_create(inode, dentry, ret); } @@ -472,14 +477,20 @@ static int __track_inode(struct inode *inode, void *arg, bool update) return 0; } -void ext4_fc_track_inode(struct inode *inode) +void ext4_fc_track_inode(handle_t *handle, struct inode *inode) { int ret; if (S_ISDIR(inode->i_mode)) return; - ret = ext4_fc_track_template(inode, __track_inode, NULL, 1); + if (ext4_should_journal_data(inode)) { + ext4_fc_mark_ineligible(inode->i_sb, + EXT4_FC_REASON_INODE_JOURNAL_DATA); + return; + } + + ret = ext4_fc_track_template(handle, inode, __track_inode, NULL, 1); trace_ext4_fc_track_inode(inode, ret); } @@ -515,7 +526,7 @@ static int __track_range(struct inode *inode, void *arg, bool update) return 0; } -void ext4_fc_track_range(struct inode *inode, ext4_lblk_t start, +void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t start, ext4_lblk_t end) { struct __track_range_args args; @@ -527,7 +538,7 @@ void ext4_fc_track_range(struct inode *inode, ext4_lblk_t start, args.start = start; args.end = end; - ret = ext4_fc_track_template(inode, __track_range, &args, 1); + ret = ext4_fc_track_template(handle, inode, __track_range, &args, 1); trace_ext4_fc_track_range(inode, start, end, ret); } @@ -537,10 +548,11 @@ static void ext4_fc_submit_bh(struct super_block *sb) int write_flags = REQ_SYNC; struct buffer_head *bh = EXT4_SB(sb)->s_fc_bh; + /* TODO: REQ_FUA | REQ_PREFLUSH is unnecessarily expensive. */ if (test_opt(sb, BARRIER)) write_flags |= REQ_FUA | REQ_PREFLUSH; lock_buffer(bh); - clear_buffer_dirty(bh); + set_buffer_dirty(bh); set_buffer_uptodate(bh); bh->b_end_io = ext4_end_buffer_io_sync; submit_bh(REQ_OP_WRITE, write_flags, bh); @@ -846,7 +858,7 @@ static int ext4_fc_submit_inode_data_all(journal_t *journal) int ret = 0; spin_lock(&sbi->s_fc_lock); - sbi->s_mount_flags |= EXT4_MF_FC_COMMITTING; + ext4_set_mount_flag(sb, EXT4_MF_FC_COMMITTING); list_for_each(pos, &sbi->s_fc_q[FC_Q_MAIN]) { ei = list_entry(pos, struct ext4_inode_info, i_fc_list); ext4_set_inode_state(&ei->vfs_inode, EXT4_STATE_FC_COMMITTING); @@ -900,6 +912,8 @@ static int ext4_fc_wait_inode_data_all(journal_t *journal) /* Commit all the directory entry updates */ static int ext4_fc_commit_dentry_updates(journal_t *journal, u32 *crc) +__acquires(&sbi->s_fc_lock) +__releases(&sbi->s_fc_lock) { struct super_block *sb = (struct super_block *)(journal->j_private); struct ext4_sb_info *sbi = EXT4_SB(sb); @@ -996,6 +1010,13 @@ static int ext4_fc_perform_commit(journal_t *journal) if (ret) return ret; + /* + * If file system device is different from journal device, issue a cache + * flush before we start writing fast commit blocks. + */ + if (journal->j_fs_dev != journal->j_dev) + blkdev_issue_flush(journal->j_fs_dev, GFP_NOFS); + blk_start_plug(&plug); if (sbi->s_fc_bytes == 0) { /* @@ -1031,8 +1052,6 @@ static int ext4_fc_perform_commit(journal_t *journal) if (ret) goto out; spin_lock(&sbi->s_fc_lock); - EXT4_I(inode)->i_fc_committed_subtid = - atomic_read(&sbi->s_fc_subtid); } spin_unlock(&sbi->s_fc_lock); @@ -1131,7 +1150,7 @@ out: "Fast commit ended with blks = %d, reason = %d, subtid - %d", nblks, reason, subtid); if (reason == EXT4_FC_REASON_FC_FAILED) - return jbd2_fc_end_commit_fallback(journal, commit_tid); + return jbd2_fc_end_commit_fallback(journal); if (reason == EXT4_FC_REASON_FC_START_FAILED || reason == EXT4_FC_REASON_INELIGIBLE) return jbd2_complete_transaction(journal, commit_tid); @@ -1190,8 +1209,8 @@ static void ext4_fc_cleanup(journal_t *journal, int full) list_splice_init(&sbi->s_fc_q[FC_Q_STAGING], &sbi->s_fc_q[FC_Q_STAGING]); - sbi->s_mount_flags &= ~EXT4_MF_FC_COMMITTING; - sbi->s_mount_flags &= ~EXT4_MF_FC_INELIGIBLE; + ext4_clear_mount_flag(sb, EXT4_MF_FC_COMMITTING); + ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); if (full) sbi->s_fc_bytes = 0; @@ -1263,7 +1282,7 @@ static int ext4_fc_replay_unlink(struct super_block *sb, struct ext4_fc_tl *tl) return 0; } - ret = __ext4_unlink(old_parent, &entry, inode); + ret = __ext4_unlink(NULL, old_parent, &entry, inode); /* -ENOENT ok coz it might not exist anymore. */ if (ret == -ENOENT) ret = 0; @@ -2079,8 +2098,6 @@ static int ext4_fc_replay(journal_t *journal, struct buffer_head *bh, void ext4_fc_init(struct super_block *sb, journal_t *journal) { - int num_fc_blocks; - /* * We set replay callback even if fast commit disabled because we may * could still have fast commit blocks that need to be replayed even if @@ -2090,21 +2107,9 @@ void ext4_fc_init(struct super_block *sb, journal_t *journal) if (!test_opt2(sb, JOURNAL_FAST_COMMIT)) return; journal->j_fc_cleanup_callback = ext4_fc_cleanup; - if (!buffer_uptodate(journal->j_sb_buffer) - && ext4_read_bh_lock(journal->j_sb_buffer, REQ_META | REQ_PRIO, - true)) { - ext4_msg(sb, KERN_ERR, "I/O error on journal"); - return; - } - num_fc_blocks = be32_to_cpu(journal->j_superblock->s_num_fc_blks); - if (jbd2_fc_init(journal, num_fc_blocks ? num_fc_blocks : - EXT4_NUM_FC_BLKS)) { - pr_warn("Error while enabling fast commits, turning off."); - ext4_clear_feature_fast_commit(sb); - } } -const char *fc_ineligible_reasons[] = { +static const char *fc_ineligible_reasons[] = { "Extended attributes changed", "Cross rename", "Journal flag changed", @@ -2113,6 +2118,7 @@ const char *fc_ineligible_reasons[] = { "Resize", "Dir renamed", "Falloc range op", + "Data journalling", "FC Commit Failed" }; diff --git a/fs/ext4/fast_commit.h b/fs/ext4/fast_commit.h index 06907d485989..3a6e5a1fa1b8 100644 --- a/fs/ext4/fast_commit.h +++ b/fs/ext4/fast_commit.h @@ -3,9 +3,6 @@ #ifndef __FAST_COMMIT_H__ #define __FAST_COMMIT_H__ -/* Number of blocks in journal area to allocate for fast commits */ -#define EXT4_NUM_FC_BLKS 256 - /* Fast commit tags */ #define EXT4_FC_TAG_ADD_RANGE 0x0001 #define EXT4_FC_TAG_DEL_RANGE 0x0002 @@ -100,11 +97,12 @@ enum { EXT4_FC_REASON_XATTR = 0, EXT4_FC_REASON_CROSS_RENAME, EXT4_FC_REASON_JOURNAL_FLAG_CHANGE, - EXT4_FC_REASON_MEM, + EXT4_FC_REASON_NOMEM, EXT4_FC_REASON_SWAP_BOOT, EXT4_FC_REASON_RESIZE, EXT4_FC_REASON_RENAME_DIR, EXT4_FC_REASON_FALLOC_RANGE, + EXT4_FC_REASON_INODE_JOURNAL_DATA, EXT4_FC_COMMIT_FAILED, EXT4_FC_REASON_MAX }; diff --git a/fs/ext4/file.c b/fs/ext4/file.c index d85412d12e3a..3ed8c048fb12 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -761,7 +761,6 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma) if (!daxdev_mapping_supported(vma, dax_dev)) return -EOPNOTSUPP; - ext4_fc_start_update(inode); file_accessed(file); if (IS_DAX(file_inode(file))) { vma->vm_ops = &ext4_dax_vm_ops; @@ -769,7 +768,6 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma) } else { vma->vm_ops = &ext4_file_vm_ops; } - ext4_fc_stop_update(inode); return 0; } @@ -782,13 +780,13 @@ static int ext4_sample_last_mounted(struct super_block *sb, handle_t *handle; int err; - if (likely(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED)) + if (likely(ext4_test_mount_flag(sb, EXT4_MF_MNTDIR_SAMPLED))) return 0; if (sb_rdonly(sb) || !sb_start_intwrite_trylock(sb)) return 0; - sbi->s_mount_flags |= EXT4_MF_MNTDIR_SAMPLED; + ext4_set_mount_flag(sb, EXT4_MF_MNTDIR_SAMPLED); /* * Sample where the filesystem has been mounted and * store it in the superblock for sysadmin convenience diff --git a/fs/ext4/fsmap.c b/fs/ext4/fsmap.c index b232c2767534..4c2a9fe30067 100644 --- a/fs/ext4/fsmap.c +++ b/fs/ext4/fsmap.c @@ -280,7 +280,7 @@ static int ext4_getfsmap_logdev(struct super_block *sb, struct ext4_fsmap *keys, /* Fabricate an rmap entry for the external log device. */ irec.fmr_physical = journal->j_blk_offset; - irec.fmr_length = journal->j_maxlen; + irec.fmr_length = journal->j_total_len; irec.fmr_owner = EXT4_FMR_OWN_LOG; irec.fmr_flags = 0; diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index 81a545fd14a3..a42ca95840f2 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -143,7 +143,7 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) if (sb_rdonly(inode->i_sb)) { /* Make sure that we read updated s_mount_flags value */ smp_rmb(); - if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) + if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FS_ABORTED)) ret = -EROFS; goto out; } diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index caa51473207d..b41512d1badc 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -1880,6 +1880,7 @@ int ext4_inline_data_truncate(struct inode *inode, int *has_inline) ext4_write_lock_xattr(inode, &no_expand); if (!ext4_has_inline_data(inode)) { + ext4_write_unlock_xattr(inode, &no_expand); *has_inline = 0; ext4_journal_stop(handle); return 0; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index b96a18679a27..0d8385aea898 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -327,6 +327,8 @@ stop_handle: ext4_xattr_inode_array_free(ea_inode_array); return; no_delete: + if (!list_empty(&EXT4_I(inode)->i_fc_list)) + ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM); ext4_clear_inode(inode); /* We must guarantee clearing of inode... */ } @@ -730,7 +732,7 @@ out_sem: if (ret) return ret; } - ext4_fc_track_range(inode, map->m_lblk, + ext4_fc_track_range(handle, inode, map->m_lblk, map->m_lblk + map->m_len - 1); } @@ -2440,7 +2442,7 @@ static int mpage_map_and_submit_extent(handle_t *handle, struct super_block *sb = inode->i_sb; if (ext4_forced_shutdown(EXT4_SB(sb)) || - EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED) + ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED)) goto invalidate_dirty_pages; /* * Let the uper layers retry transient errors. @@ -2674,7 +2676,7 @@ static int ext4_writepages(struct address_space *mapping, * the stack trace. */ if (unlikely(ext4_forced_shutdown(EXT4_SB(mapping->host->i_sb)) || - sbi->s_mount_flags & EXT4_MF_FS_ABORTED)) { + ext4_test_mount_flag(inode->i_sb, EXT4_MF_FS_ABORTED))) { ret = -EROFS; goto out_writepages; } @@ -3310,8 +3312,7 @@ static bool ext4_inode_datasync_dirty(struct inode *inode) EXT4_I(inode)->i_datasync_tid)) return false; if (test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT)) - return atomic_read(&EXT4_SB(inode->i_sb)->s_fc_subtid) < - EXT4_I(inode)->i_fc_committed_subtid; + return !list_empty(&EXT4_I(inode)->i_fc_list); return true; } @@ -4109,7 +4110,7 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) up_write(&EXT4_I(inode)->i_data_sem); } - ext4_fc_track_range(inode, first_block, stop_block); + ext4_fc_track_range(handle, inode, first_block, stop_block); if (IS_SYNC(inode)) ext4_handle_sync(handle); @@ -5442,14 +5443,14 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) } if (shrink) - ext4_fc_track_range(inode, + ext4_fc_track_range(handle, inode, (attr->ia_size > 0 ? attr->ia_size - 1 : 0) >> inode->i_sb->s_blocksize_bits, (oldsize > 0 ? oldsize - 1 : 0) >> inode->i_sb->s_blocksize_bits); else ext4_fc_track_range( - inode, + handle, inode, (oldsize > 0 ? oldsize - 1 : oldsize) >> inode->i_sb->s_blocksize_bits, (attr->ia_size > 0 ? attr->ia_size - 1 : 0) >> @@ -5699,7 +5700,7 @@ int ext4_mark_iloc_dirty(handle_t *handle, put_bh(iloc->bh); return -EIO; } - ext4_fc_track_inode(inode); + ext4_fc_track_inode(handle, inode); if (IS_I_VERSION(inode)) inode_inc_iversion(inode); diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 85abbfb98cbe..24af9ed5c3e5 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -4477,7 +4477,7 @@ static inline void ext4_mb_show_pa(struct super_block *sb) { ext4_group_t i, ngroups; - if (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED) + if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED)) return; ngroups = ext4_get_groups_count(sb); @@ -4508,7 +4508,7 @@ static void ext4_mb_show_ac(struct ext4_allocation_context *ac) { struct super_block *sb = ac->ac_sb; - if (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED) + if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED)) return; mb_debug(sb, "Can't allocate:" @@ -5167,7 +5167,7 @@ static ext4_fsblk_t ext4_mb_new_blocks_simple(handle_t *handle, struct super_block *sb = ar->inode->i_sb; ext4_group_t group; ext4_grpblk_t blkoff; - int i; + int i = sb->s_blocksize; ext4_fsblk_t goal, block; struct ext4_super_block *es = EXT4_SB(sb)->s_es; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index f458d1d81d96..33509266f5a0 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2606,7 +2606,7 @@ static int ext4_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { handle_t *handle; - struct inode *inode, *inode_save; + struct inode *inode; int err, credits, retries = 0; err = dquot_initialize(dir); @@ -2624,11 +2624,9 @@ retry: inode->i_op = &ext4_file_inode_operations; inode->i_fop = &ext4_file_operations; ext4_set_aops(inode); - inode_save = inode; - ihold(inode_save); err = ext4_add_nondir(handle, dentry, &inode); - ext4_fc_track_create(inode_save, dentry); - iput(inode_save); + if (!err) + ext4_fc_track_create(handle, dentry); } if (handle) ext4_journal_stop(handle); @@ -2643,7 +2641,7 @@ static int ext4_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) { handle_t *handle; - struct inode *inode, *inode_save; + struct inode *inode; int err, credits, retries = 0; err = dquot_initialize(dir); @@ -2660,12 +2658,9 @@ retry: if (!IS_ERR(inode)) { init_special_inode(inode, inode->i_mode, rdev); inode->i_op = &ext4_special_inode_operations; - inode_save = inode; - ihold(inode_save); err = ext4_add_nondir(handle, dentry, &inode); if (!err) - ext4_fc_track_create(inode_save, dentry); - iput(inode_save); + ext4_fc_track_create(handle, dentry); } if (handle) ext4_journal_stop(handle); @@ -2829,7 +2824,6 @@ out_clear_inode: iput(inode); goto out_retry; } - ext4_fc_track_create(inode, dentry); ext4_inc_count(dir); ext4_update_dx_flag(dir); @@ -2837,6 +2831,7 @@ out_clear_inode: if (err) goto out_clear_inode; d_instantiate_new(dentry, inode); + ext4_fc_track_create(handle, dentry); if (IS_DIRSYNC(dir)) ext4_handle_sync(handle); @@ -3171,7 +3166,7 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry) goto end_rmdir; ext4_dec_count(dir); ext4_update_dx_flag(dir); - ext4_fc_track_unlink(inode, dentry); + ext4_fc_track_unlink(handle, dentry); retval = ext4_mark_inode_dirty(handle, dir); #ifdef CONFIG_UNICODE @@ -3192,13 +3187,12 @@ end_rmdir: return retval; } -int __ext4_unlink(struct inode *dir, const struct qstr *d_name, +int __ext4_unlink(handle_t *handle, struct inode *dir, const struct qstr *d_name, struct inode *inode) { int retval = -ENOENT; struct buffer_head *bh; struct ext4_dir_entry_2 *de; - handle_t *handle = NULL; int skip_remove_dentry = 0; bh = ext4_find_entry(dir, d_name, &de, NULL); @@ -3217,14 +3211,7 @@ int __ext4_unlink(struct inode *dir, const struct qstr *d_name, if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) skip_remove_dentry = 1; else - goto out_bh; - } - - handle = ext4_journal_start(dir, EXT4_HT_DIR, - EXT4_DATA_TRANS_BLOCKS(dir->i_sb)); - if (IS_ERR(handle)) { - retval = PTR_ERR(handle); - goto out_bh; + goto out; } if (IS_DIRSYNC(dir)) @@ -3233,12 +3220,12 @@ int __ext4_unlink(struct inode *dir, const struct qstr *d_name, if (!skip_remove_dentry) { retval = ext4_delete_entry(handle, dir, de, bh); if (retval) - goto out_handle; + goto out; dir->i_ctime = dir->i_mtime = current_time(dir); ext4_update_dx_flag(dir); retval = ext4_mark_inode_dirty(handle, dir); if (retval) - goto out_handle; + goto out; } else { retval = 0; } @@ -3252,15 +3239,14 @@ int __ext4_unlink(struct inode *dir, const struct qstr *d_name, inode->i_ctime = current_time(inode); retval = ext4_mark_inode_dirty(handle, inode); -out_handle: - ext4_journal_stop(handle); -out_bh: +out: brelse(bh); return retval; } static int ext4_unlink(struct inode *dir, struct dentry *dentry) { + handle_t *handle; int retval; if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb)))) @@ -3278,9 +3264,16 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry) if (retval) goto out_trace; - retval = __ext4_unlink(dir, &dentry->d_name, d_inode(dentry)); + handle = ext4_journal_start(dir, EXT4_HT_DIR, + EXT4_DATA_TRANS_BLOCKS(dir->i_sb)); + if (IS_ERR(handle)) { + retval = PTR_ERR(handle); + goto out_trace; + } + + retval = __ext4_unlink(handle, dir, &dentry->d_name, d_inode(dentry)); if (!retval) - ext4_fc_track_unlink(d_inode(dentry), dentry); + ext4_fc_track_unlink(handle, dentry); #ifdef CONFIG_UNICODE /* VFS negative dentries are incompatible with Encoding and * Case-insensitiveness. Eventually we'll want avoid @@ -3291,6 +3284,8 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry) if (IS_CASEFOLDED(dir)) d_invalidate(dentry); #endif + if (handle) + ext4_journal_stop(handle); out_trace: trace_ext4_unlink_exit(dentry, retval); @@ -3447,7 +3442,6 @@ retry: err = ext4_add_entry(handle, dentry, inode); if (!err) { - ext4_fc_track_link(inode, dentry); err = ext4_mark_inode_dirty(handle, inode); /* this can happen only for tmpfile being * linked the first time @@ -3455,6 +3449,7 @@ retry: if (inode->i_nlink == 1) ext4_orphan_del(handle, inode); d_instantiate(dentry, inode); + ext4_fc_track_link(handle, dentry); } else { drop_nlink(inode); iput(inode); @@ -3915,9 +3910,9 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, EXT4_FC_REASON_RENAME_DIR); } else { if (new.inode) - ext4_fc_track_unlink(new.inode, new.dentry); - ext4_fc_track_link(old.inode, new.dentry); - ext4_fc_track_unlink(old.inode, old.dentry); + ext4_fc_track_unlink(handle, new.dentry); + __ext4_fc_track_link(handle, old.inode, new.dentry); + __ext4_fc_track_unlink(handle, old.inode, old.dentry); } if (new.inode) { diff --git a/fs/ext4/super.c b/fs/ext4/super.c index ef4734b40e2a..94472044f4c1 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -289,18 +289,7 @@ void ext4_superblock_csum_set(struct super_block *sb) if (!ext4_has_metadata_csum(sb)) return; - /* - * Locking the superblock prevents the scenario - * where: - * 1) a first thread pauses during checksum calculation. - * 2) a second thread updates the superblock, recalculates - * the checksum, and updates s_checksum - * 3) the first thread resumes and finishes its checksum calculation - * and updates s_checksum with a potentially stale or torn value. - */ - lock_buffer(EXT4_SB(sb)->s_sbh); es->s_checksum = ext4_superblock_csum(sb, es); - unlock_buffer(EXT4_SB(sb)->s_sbh); } ext4_fsblk_t ext4_block_bitmap(struct super_block *sb, @@ -686,7 +675,7 @@ static void ext4_handle_error(struct super_block *sb) if (!test_opt(sb, ERRORS_CONT)) { journal_t *journal = EXT4_SB(sb)->s_journal; - EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED; + ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED); if (journal) jbd2_journal_abort(journal, -EIO); } @@ -904,7 +893,7 @@ void __ext4_abort(struct super_block *sb, const char *function, va_end(args); if (sb_rdonly(sb) == 0) { - EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED; + ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED); if (EXT4_SB(sb)->s_journal) jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO); @@ -1716,11 +1705,10 @@ enum { Opt_dioread_nolock, Opt_dioread_lock, Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable, Opt_max_dir_size_kb, Opt_nojournal_checksum, Opt_nombcache, - Opt_prefetch_block_bitmaps, Opt_no_fc, + Opt_prefetch_block_bitmaps, #ifdef CONFIG_EXT4_DEBUG - Opt_fc_debug_max_replay, + Opt_fc_debug_max_replay, Opt_fc_debug_force #endif - Opt_fc_debug_force }; static const match_table_t tokens = { @@ -1807,9 +1795,8 @@ static const match_table_t tokens = { {Opt_init_itable, "init_itable=%u"}, {Opt_init_itable, "init_itable"}, {Opt_noinit_itable, "noinit_itable"}, - {Opt_no_fc, "no_fc"}, - {Opt_fc_debug_force, "fc_debug_force"}, #ifdef CONFIG_EXT4_DEBUG + {Opt_fc_debug_force, "fc_debug_force"}, {Opt_fc_debug_max_replay, "fc_debug_max_replay=%u"}, #endif {Opt_max_dir_size_kb, "max_dir_size_kb=%u"}, @@ -2027,8 +2014,8 @@ static const struct mount_opts { {Opt_noquota, (EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA | EXT4_MOUNT_GRPQUOTA | EXT4_MOUNT_PRJQUOTA), MOPT_CLEAR | MOPT_Q}, - {Opt_usrjquota, 0, MOPT_Q}, - {Opt_grpjquota, 0, MOPT_Q}, + {Opt_usrjquota, 0, MOPT_Q | MOPT_STRING}, + {Opt_grpjquota, 0, MOPT_Q | MOPT_STRING}, {Opt_offusrjquota, 0, MOPT_Q}, {Opt_offgrpjquota, 0, MOPT_Q}, {Opt_jqfmt_vfsold, QFMT_VFS_OLD, MOPT_QFMT}, @@ -2039,11 +2026,9 @@ static const struct mount_opts { {Opt_nombcache, EXT4_MOUNT_NO_MBCACHE, MOPT_SET}, {Opt_prefetch_block_bitmaps, EXT4_MOUNT_PREFETCH_BLOCK_BITMAPS, MOPT_SET}, - {Opt_no_fc, EXT4_MOUNT2_JOURNAL_FAST_COMMIT, - MOPT_CLEAR | MOPT_2 | MOPT_EXT4_ONLY}, +#ifdef CONFIG_EXT4_DEBUG {Opt_fc_debug_force, EXT4_MOUNT2_JOURNAL_FAST_COMMIT, MOPT_SET | MOPT_2 | MOPT_EXT4_ONLY}, -#ifdef CONFIG_EXT4_DEBUG {Opt_fc_debug_max_replay, 0, MOPT_GTE0}, #endif {Opt_err, 0, 0} @@ -2153,7 +2138,7 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, ext4_msg(sb, KERN_WARNING, "Ignoring removed %s option", opt); return 1; case Opt_abort: - sbi->s_mount_flags |= EXT4_MF_FS_ABORTED; + ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED); return 1; case Opt_i_version: sb->s_flags |= SB_I_VERSION; @@ -2653,10 +2638,6 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb, } else if (test_opt2(sb, DAX_INODE)) { SEQ_OPTS_PUTS("dax=inode"); } - - if (test_opt2(sb, JOURNAL_FAST_COMMIT)) - SEQ_OPTS_PUTS("fast_commit"); - ext4_show_quota_options(seq, sb); return 0; } @@ -3976,7 +3957,7 @@ int ext4_calculate_overhead(struct super_block *sb) * loaded or not */ if (sbi->s_journal && !sbi->s_journal_bdev) - overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_maxlen); + overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_total_len); else if (ext4_has_feature_journal(sb) && !sbi->s_journal && j_inum) { /* j_inum for internal journal is non-zero */ j_inode = ext4_get_journal_inode(sb, j_inum); @@ -4340,9 +4321,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) #endif if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) { - printk_once(KERN_WARNING "EXT4-fs: Warning: mounting with data=journal disables delayed allocation, dioread_nolock, and O_DIRECT support!\n"); + printk_once(KERN_WARNING "EXT4-fs: Warning: mounting with data=journal disables delayed allocation, dioread_nolock, O_DIRECT and fast_commit support!\n"); /* can't mount with both data=journal and dioread_nolock. */ clear_opt(sb, DIOREAD_NOLOCK); + clear_opt2(sb, JOURNAL_FAST_COMMIT); if (test_opt2(sb, EXPLICIT_DELALLOC)) { ext4_msg(sb, KERN_ERR, "can't mount with " "both data=journal and delalloc"); @@ -4777,8 +4759,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) INIT_LIST_HEAD(&sbi->s_fc_dentry_q[FC_Q_MAIN]); INIT_LIST_HEAD(&sbi->s_fc_dentry_q[FC_Q_STAGING]); sbi->s_fc_bytes = 0; - sbi->s_mount_flags &= ~EXT4_MF_FC_INELIGIBLE; - sbi->s_mount_flags &= ~EXT4_MF_FC_COMMITTING; + ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); + ext4_clear_mount_flag(sb, EXT4_MF_FC_COMMITTING); spin_lock_init(&sbi->s_fc_lock); memset(&sbi->s_fc_stats, 0, sizeof(sbi->s_fc_stats)); sbi->s_fc_replay_state.fc_regions = NULL; @@ -4857,6 +4839,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount_wq; } + if (test_opt2(sb, JOURNAL_FAST_COMMIT) && + !jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0, + JBD2_FEATURE_INCOMPAT_FAST_COMMIT)) { + ext4_msg(sb, KERN_ERR, + "Failed to set fast commit journal feature"); + goto failed_mount_wq; + } + /* We have now updated the journal if required, so we can * validate the data journaling mode. */ switch (test_opt(sb, DATA_FLAGS)) { @@ -5872,7 +5862,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) goto restore_opts; } - if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) + if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED)) ext4_abort(sb, EXT4_ERR_ESHUTDOWN, "Abort forced by user"); sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | @@ -5886,7 +5876,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) } if ((bool)(*flags & SB_RDONLY) != sb_rdonly(sb)) { - if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) { + if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED)) { err = -EROFS; goto restore_opts; } @@ -6560,10 +6550,6 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type, brelse(bh); out: if (inode->i_size < off + len) { - ext4_fc_track_range(inode, - (inode->i_size > 0 ? inode->i_size - 1 : 0) - >> inode->i_sb->s_blocksize_bits, - (off + len) >> inode->i_sb->s_blocksize_bits); i_size_write(inode, off + len); EXT4_I(inode)->i_disksize = inode->i_size; err2 = ext4_mark_inode_dirty(handle, inode); diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 9cd2ecad07db..cc4f987687f3 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -77,7 +77,7 @@ static int gfs2_get_block_noalloc(struct inode *inode, sector_t lblock, if (error) return error; if (!buffer_mapped(bh_result)) - return -EIO; + return -ENODATA; return 0; } diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 8dff9cbd0a87..62d9081d1e26 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -1301,12 +1301,8 @@ int gfs2_block_map(struct inode *inode, sector_t lblock, trace_gfs2_bmap(ip, bh_map, lblock, create, 1); ret = gfs2_iomap_get(inode, pos, length, flags, &iomap, &mp); - if (!ret && iomap.type == IOMAP_HOLE) { - if (create) - ret = gfs2_iomap_alloc(inode, &iomap, &mp); - else - ret = -ENODATA; - } + if (create && !ret && iomap.type == IOMAP_HOLE) + ret = gfs2_iomap_alloc(inode, &iomap, &mp); release_metapath(&mp); if (ret) goto out; diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 5441c17562c5..d98a2e5dab9f 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -1078,7 +1078,8 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number, out_free: kfree(gl->gl_lksb.sb_lvbptr); kmem_cache_free(cachep, gl); - atomic_dec(&sdp->sd_glock_disposal); + if (atomic_dec_and_test(&sdp->sd_glock_disposal)) + wake_up(&sdp->sd_glock_wait); out: return ret; diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index aa3f5236befb..67f2921ae8d4 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -165,6 +165,31 @@ void gfs2_ail_flush(struct gfs2_glock *gl, bool fsync) } /** + * gfs2_rgrp_metasync - sync out the metadata of a resource group + * @gl: the glock protecting the resource group + * + */ + +static int gfs2_rgrp_metasync(struct gfs2_glock *gl) +{ + struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; + struct address_space *metamapping = &sdp->sd_aspace; + struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl); + const unsigned bsize = sdp->sd_sb.sb_bsize; + loff_t start = (rgd->rd_addr * bsize) & PAGE_MASK; + loff_t end = PAGE_ALIGN((rgd->rd_addr + rgd->rd_length) * bsize) - 1; + int error; + + filemap_fdatawrite_range(metamapping, start, end); + error = filemap_fdatawait_range(metamapping, start, end); + WARN_ON_ONCE(error && !gfs2_withdrawn(sdp)); + mapping_set_error(metamapping, error); + if (error) + gfs2_io_error(sdp); + return error; +} + +/** * rgrp_go_sync - sync out the metadata for this glock * @gl: the glock * @@ -176,11 +201,7 @@ void gfs2_ail_flush(struct gfs2_glock *gl, bool fsync) static int rgrp_go_sync(struct gfs2_glock *gl) { struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; - struct address_space *mapping = &sdp->sd_aspace; struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl); - const unsigned bsize = sdp->sd_sb.sb_bsize; - loff_t start = (rgd->rd_addr * bsize) & PAGE_MASK; - loff_t end = PAGE_ALIGN((rgd->rd_addr + rgd->rd_length) * bsize) - 1; int error; if (!test_and_clear_bit(GLF_DIRTY, &gl->gl_flags)) @@ -189,10 +210,7 @@ static int rgrp_go_sync(struct gfs2_glock *gl) gfs2_log_flush(sdp, gl, GFS2_LOG_HEAD_FLUSH_NORMAL | GFS2_LFC_RGRP_GO_SYNC); - filemap_fdatawrite_range(mapping, start, end); - error = filemap_fdatawait_range(mapping, start, end); - WARN_ON_ONCE(error && !gfs2_withdrawn(sdp)); - mapping_set_error(mapping, error); + error = gfs2_rgrp_metasync(gl); if (!error) error = gfs2_ail_empty_gl(gl); gfs2_free_clones(rgd); @@ -266,7 +284,24 @@ static void gfs2_clear_glop_pending(struct gfs2_inode *ip) } /** - * inode_go_sync - Sync the dirty data and/or metadata for an inode glock + * gfs2_inode_metasync - sync out the metadata of an inode + * @gl: the glock protecting the inode + * + */ +int gfs2_inode_metasync(struct gfs2_glock *gl) +{ + struct address_space *metamapping = gfs2_glock2aspace(gl); + int error; + + filemap_fdatawrite(metamapping); + error = filemap_fdatawait(metamapping); + if (error) + gfs2_io_error(gl->gl_name.ln_sbd); + return error; +} + +/** + * inode_go_sync - Sync the dirty metadata of an inode * @gl: the glock protecting the inode * */ @@ -297,8 +332,7 @@ static int inode_go_sync(struct gfs2_glock *gl) error = filemap_fdatawait(mapping); mapping_set_error(mapping, error); } - ret = filemap_fdatawait(metamapping); - mapping_set_error(metamapping, ret); + ret = gfs2_inode_metasync(gl); if (!error) error = ret; gfs2_ail_empty_gl(gl); @@ -537,7 +571,18 @@ static int freeze_go_sync(struct gfs2_glock *gl) int error = 0; struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; - if (gl->gl_req == LM_ST_EXCLUSIVE && !gfs2_withdrawn(sdp)) { + /* + * We need to check gl_state == LM_ST_SHARED here and not gl_req == + * LM_ST_EXCLUSIVE. That's because when any node does a freeze, + * all the nodes should have the freeze glock in SH mode and they all + * call do_xmote: One for EX and the others for UN. They ALL must + * freeze locally, and they ALL must queue freeze work. The freeze_work + * calls freeze_func, which tries to reacquire the freeze glock in SH, + * effectively waiting for the thaw on the node who holds it in EX. + * Once thawed, the work func acquires the freeze glock in + * SH and everybody goes back to thawed. + */ + if (gl->gl_state == LM_ST_SHARED && !gfs2_withdrawn(sdp)) { atomic_set(&sdp->sd_freeze_state, SFS_STARTING_FREEZE); error = freeze_super(sdp->sd_vfs); if (error) { diff --git a/fs/gfs2/glops.h b/fs/gfs2/glops.h index 2dd192e85618..695898afcaf1 100644 --- a/fs/gfs2/glops.h +++ b/fs/gfs2/glops.h @@ -22,6 +22,7 @@ extern const struct gfs2_glock_operations gfs2_quota_glops; extern const struct gfs2_glock_operations gfs2_journal_glops; extern const struct gfs2_glock_operations *gfs2_glops_list[]; +extern int gfs2_inode_metasync(struct gfs2_glock *gl); extern void gfs2_ail_flush(struct gfs2_glock *gl, bool fsync); #endif /* __GLOPS_DOT_H__ */ diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 6774865f5b5b..077ccb1b3ccc 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -180,7 +180,8 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh); if (unlikely(error)) goto fail; - gfs2_cancel_delete_work(ip->i_iopen_gh.gh_gl); + if (blktype != GFS2_BLKST_UNLINKED) + gfs2_cancel_delete_work(ip->i_iopen_gh.gh_gl); glock_set_object(ip->i_iopen_gh.gh_gl, ip); gfs2_glock_put(io_gl); io_gl = NULL; diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 9133b3178677..2e9314091c81 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -132,6 +132,8 @@ __acquires(&sdp->sd_ail_lock) spin_unlock(&sdp->sd_ail_lock); ret = generic_writepages(mapping, wbc); spin_lock(&sdp->sd_ail_lock); + if (ret == -ENODATA) /* if a jdata write into a new hole */ + ret = 0; /* ignore it */ if (ret || wbc->nr_to_write <= 0) break; return -EBUSY; diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index ed69298dd824..3922b26264f5 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -22,6 +22,7 @@ #include "incore.h" #include "inode.h" #include "glock.h" +#include "glops.h" #include "log.h" #include "lops.h" #include "meta_io.h" @@ -817,41 +818,19 @@ static int buf_lo_scan_elements(struct gfs2_jdesc *jd, u32 start, return error; } -/** - * gfs2_meta_sync - Sync all buffers associated with a glock - * @gl: The glock - * - */ - -void gfs2_meta_sync(struct gfs2_glock *gl) -{ - struct address_space *mapping = gfs2_glock2aspace(gl); - struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; - int error; - - if (mapping == NULL) - mapping = &sdp->sd_aspace; - - filemap_fdatawrite(mapping); - error = filemap_fdatawait(mapping); - - if (error) - gfs2_io_error(gl->gl_name.ln_sbd); -} - static void buf_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass) { struct gfs2_inode *ip = GFS2_I(jd->jd_inode); struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode); if (error) { - gfs2_meta_sync(ip->i_gl); + gfs2_inode_metasync(ip->i_gl); return; } if (pass != 1) return; - gfs2_meta_sync(ip->i_gl); + gfs2_inode_metasync(ip->i_gl); fs_info(sdp, "jid=%u: Replayed %u of %u blocks\n", jd->jd_jid, jd->jd_replayed_blocks, jd->jd_found_blocks); @@ -1060,14 +1039,14 @@ static void databuf_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass) struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode); if (error) { - gfs2_meta_sync(ip->i_gl); + gfs2_inode_metasync(ip->i_gl); return; } if (pass != 1) return; /* data sync? */ - gfs2_meta_sync(ip->i_gl); + gfs2_inode_metasync(ip->i_gl); fs_info(sdp, "jid=%u: Replayed %u of %u data blocks\n", jd->jd_jid, jd->jd_replayed_blocks, jd->jd_found_blocks); diff --git a/fs/gfs2/lops.h b/fs/gfs2/lops.h index 4a3d8aecdf82..fbdbb08dcec6 100644 --- a/fs/gfs2/lops.h +++ b/fs/gfs2/lops.h @@ -27,8 +27,6 @@ extern void gfs2_log_submit_bio(struct bio **biop, int opf); extern void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh); extern int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head, bool keep_cache); -extern void gfs2_meta_sync(struct gfs2_glock *gl); - static inline unsigned int buf_limit(struct gfs2_sbd *sdp) { unsigned int limit; diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 7a7e3c10a9a9..61fce59cb4d3 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -633,8 +633,10 @@ static int init_statfs(struct gfs2_sbd *sdp) if (IS_ERR(sdp->sd_statfs_inode)) { error = PTR_ERR(sdp->sd_statfs_inode); fs_err(sdp, "can't read in statfs inode: %d\n", error); - goto fail; + goto out; } + if (sdp->sd_args.ar_spectator) + goto out; pn = gfs2_lookup_simple(master, "per_node"); if (IS_ERR(pn)) { @@ -682,15 +684,17 @@ free_local: iput(pn); put_statfs: iput(sdp->sd_statfs_inode); -fail: +out: return error; } /* Uninitialize and free up memory used by the list of statfs inodes */ static void uninit_statfs(struct gfs2_sbd *sdp) { - gfs2_glock_dq_uninit(&sdp->sd_sc_gh); - free_local_statfs_inodes(sdp); + if (!sdp->sd_args.ar_spectator) { + gfs2_glock_dq_uninit(&sdp->sd_sc_gh); + free_local_statfs_inodes(sdp); + } iput(sdp->sd_statfs_inode); } @@ -704,7 +708,7 @@ static int init_journal(struct gfs2_sbd *sdp, int undo) if (undo) { jindex = 0; - goto fail_jinode_gh; + goto fail_statfs; } sdp->sd_jindex = gfs2_lookup_simple(master, "jindex"); diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c index b5cbe21efdfb..c26c68ebd29d 100644 --- a/fs/gfs2/recovery.c +++ b/fs/gfs2/recovery.c @@ -349,7 +349,7 @@ static int update_statfs_inode(struct gfs2_jdesc *jd, mark_buffer_dirty(bh); brelse(bh); - gfs2_meta_sync(ip->i_gl); + gfs2_inode_metasync(ip->i_gl); out: return error; diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index ee491bb9c1cc..f7addc6197ed 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -719,9 +719,9 @@ void gfs2_clear_rgrpd(struct gfs2_sbd *sdp) } gfs2_free_clones(rgd); + return_all_reservations(rgd); kfree(rgd->rd_bits); rgd->rd_bits = NULL; - return_all_reservations(rgd); kmem_cache_free(gfs2_rgrpd_cachep, rgd); } } @@ -1370,6 +1370,9 @@ int gfs2_fitrim(struct file *filp, void __user *argp) if (!capable(CAP_SYS_ADMIN)) return -EPERM; + if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) + return -EROFS; + if (!blk_queue_discard(q)) return -EOPNOTSUPP; @@ -2526,13 +2529,13 @@ int gfs2_check_blk_type(struct gfs2_sbd *sdp, u64 no_addr, unsigned int type) rbm.rgd = rgd; error = gfs2_rbm_from_block(&rbm, no_addr); - if (WARN_ON_ONCE(error)) - goto fail; - - if (gfs2_testbit(&rbm, false) != type) - error = -ESTALE; + if (!WARN_ON_ONCE(error)) { + if (gfs2_testbit(&rbm, false) != type) + error = -ESTALE; + } gfs2_glock_dq_uninit(&rgd_gh); + fail: return error; } diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index b285192bd6b3..b3d951ab8068 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -738,6 +738,7 @@ restart: gfs2_jindex_free(sdp); /* Take apart glock structures and buffer lists */ gfs2_gl_hash_clear(sdp); + truncate_inode_pages_final(&sdp->sd_aspace); gfs2_delete_debugfs_file(sdp); /* Unmount the locking protocol */ gfs2_lm_unmount(sdp); diff --git a/fs/io-wq.c b/fs/io-wq.c index 02894df7656d..b53c055bea6a 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -482,6 +482,10 @@ static void io_impersonate_work(struct io_worker *worker, current->files = work->identity->files; current->nsproxy = work->identity->nsproxy; task_unlock(current); + if (!work->identity->files) { + /* failed grabbing files, ensure work gets cancelled */ + work->flags |= IO_WQ_WORK_CANCEL; + } } if ((work->flags & IO_WQ_WORK_FS) && current->fs != work->identity->fs) current->fs = work->identity->fs; diff --git a/fs/io_uring.c b/fs/io_uring.c index a7429c977eb3..a8c136a1cf4e 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -205,6 +205,7 @@ struct fixed_file_ref_node { struct list_head file_list; struct fixed_file_data *file_data; struct llist_node llist; + bool done; }; struct fixed_file_data { @@ -478,6 +479,7 @@ struct io_sr_msg { struct io_open { struct file *file; int dfd; + bool ignore_nonblock; struct filename *filename; struct open_how how; unsigned long nofile; @@ -995,20 +997,33 @@ static void io_sq_thread_drop_mm(void) if (mm) { kthread_unuse_mm(mm); mmput(mm); + current->mm = NULL; } } static int __io_sq_thread_acquire_mm(struct io_ring_ctx *ctx) { - if (!current->mm) { - if (unlikely(!(ctx->flags & IORING_SETUP_SQPOLL) || - !ctx->sqo_task->mm || - !mmget_not_zero(ctx->sqo_task->mm))) - return -EFAULT; - kthread_use_mm(ctx->sqo_task->mm); + struct mm_struct *mm; + + if (current->mm) + return 0; + + /* Should never happen */ + if (unlikely(!(ctx->flags & IORING_SETUP_SQPOLL))) + return -EFAULT; + + task_lock(ctx->sqo_task); + mm = ctx->sqo_task->mm; + if (unlikely(!mm || !mmget_not_zero(mm))) + mm = NULL; + task_unlock(ctx->sqo_task); + + if (mm) { + kthread_use_mm(mm); + return 0; } - return 0; + return -EFAULT; } static int io_sq_thread_acquire_mm(struct io_ring_ctx *ctx, @@ -1274,9 +1289,12 @@ static bool io_identity_cow(struct io_kiocb *req) /* add one for this request */ refcount_inc(&id->count); - /* drop old identity, assign new one. one ref for req, one for tctx */ - if (req->work.identity != tctx->identity && - refcount_sub_and_test(2, &req->work.identity->count)) + /* drop tctx and req identity references, if needed */ + if (tctx->identity != &tctx->__identity && + refcount_dec_and_test(&tctx->identity->count)) + kfree(tctx->identity); + if (req->work.identity != &tctx->__identity && + refcount_dec_and_test(&req->work.identity->count)) kfree(req->work.identity); req->work.identity = id; @@ -1577,14 +1595,29 @@ static void io_cqring_mark_overflow(struct io_ring_ctx *ctx) } } -static inline bool io_match_files(struct io_kiocb *req, - struct files_struct *files) +static inline bool __io_match_files(struct io_kiocb *req, + struct files_struct *files) { + return ((req->flags & REQ_F_WORK_INITIALIZED) && + (req->work.flags & IO_WQ_WORK_FILES)) && + req->work.identity->files == files; +} + +static bool io_match_files(struct io_kiocb *req, + struct files_struct *files) +{ + struct io_kiocb *link; + if (!files) return true; - if ((req->flags & REQ_F_WORK_INITIALIZED) && - (req->work.flags & IO_WQ_WORK_FILES)) - return req->work.identity->files == files; + if (__io_match_files(req, files)) + return true; + if (req->flags & REQ_F_LINK_HEAD) { + list_for_each_entry(link, &req->link_list, link_list) { + if (__io_match_files(link, files)) + return true; + } + } return false; } @@ -1668,7 +1701,8 @@ static void __io_cqring_fill_event(struct io_kiocb *req, long res, long cflags) WRITE_ONCE(cqe->user_data, req->user_data); WRITE_ONCE(cqe->res, res); WRITE_ONCE(cqe->flags, cflags); - } else if (ctx->cq_overflow_flushed || req->task->io_uring->in_idle) { + } else if (ctx->cq_overflow_flushed || + atomic_read(&req->task->io_uring->in_idle)) { /* * If we're in ring overflow flush mode, or in task cancel mode, * then we cannot store the request for later flushing, we need @@ -1838,7 +1872,7 @@ static void __io_free_req(struct io_kiocb *req) io_dismantle_req(req); percpu_counter_dec(&tctx->inflight); - if (tctx->in_idle) + if (atomic_read(&tctx->in_idle)) wake_up(&tctx->wait); put_task_struct(req->task); @@ -2545,7 +2579,6 @@ static bool io_resubmit_prep(struct io_kiocb *req, int error) } end_req: req_set_fail_links(req); - io_req_complete(req, ret); return false; } #endif @@ -3515,8 +3548,7 @@ static int io_write(struct io_kiocb *req, bool force_nonblock, * we return to userspace. */ if (req->flags & REQ_F_ISREG) { - __sb_start_write(file_inode(req->file)->i_sb, - SB_FREEZE_WRITE, true); + sb_start_write(file_inode(req->file)->i_sb); __sb_writers_release(file_inode(req->file)->i_sb, SB_FREEZE_WRITE); } @@ -3764,6 +3796,7 @@ static int __io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe return ret; } req->open.nofile = rlimit(RLIMIT_NOFILE); + req->open.ignore_nonblock = false; req->flags |= REQ_F_NEED_CLEANUP; return 0; } @@ -3807,7 +3840,7 @@ static int io_openat2(struct io_kiocb *req, bool force_nonblock) struct file *file; int ret; - if (force_nonblock) + if (force_nonblock && !req->open.ignore_nonblock) return -EAGAIN; ret = build_open_flags(&req->open.how, &op); @@ -3822,6 +3855,21 @@ static int io_openat2(struct io_kiocb *req, bool force_nonblock) if (IS_ERR(file)) { put_unused_fd(ret); ret = PTR_ERR(file); + /* + * A work-around to ensure that /proc/self works that way + * that it should - if we get -EOPNOTSUPP back, then assume + * that proc_self_get_link() failed us because we're in async + * context. We should be safe to retry this from the task + * itself with force_nonblock == false set, as it should not + * block on lookup. Would be nice to know this upfront and + * avoid the async dance, but doesn't seem feasible. + */ + if (ret == -EOPNOTSUPP && io_wq_current_is_worker()) { + req->open.ignore_nonblock = true; + refcount_inc(&req->refs); + io_req_task_queue(req); + return 0; + } } else { fsnotify_open(file); fd_install(ret, file); @@ -6926,9 +6974,7 @@ static int io_sqe_files_unregister(struct io_ring_ctx *ctx) return -ENXIO; spin_lock(&data->lock); - if (!list_empty(&data->ref_list)) - ref_node = list_first_entry(&data->ref_list, - struct fixed_file_ref_node, node); + ref_node = data->node; spin_unlock(&data->lock); if (ref_node) percpu_ref_kill(&ref_node->refs); @@ -7277,10 +7323,6 @@ static void __io_file_put_work(struct fixed_file_ref_node *ref_node) kfree(pfile); } - spin_lock(&file_data->lock); - list_del(&ref_node->node); - spin_unlock(&file_data->lock); - percpu_ref_exit(&ref_node->refs); kfree(ref_node); percpu_ref_put(&file_data->refs); @@ -7307,17 +7349,32 @@ static void io_file_put_work(struct work_struct *work) static void io_file_data_ref_zero(struct percpu_ref *ref) { struct fixed_file_ref_node *ref_node; + struct fixed_file_data *data; struct io_ring_ctx *ctx; - bool first_add; + bool first_add = false; int delay = HZ; ref_node = container_of(ref, struct fixed_file_ref_node, refs); - ctx = ref_node->file_data->ctx; + data = ref_node->file_data; + ctx = data->ctx; + + spin_lock(&data->lock); + ref_node->done = true; + + while (!list_empty(&data->ref_list)) { + ref_node = list_first_entry(&data->ref_list, + struct fixed_file_ref_node, node); + /* recycle ref nodes in order */ + if (!ref_node->done) + break; + list_del(&ref_node->node); + first_add |= llist_add(&ref_node->llist, &ctx->file_put_llist); + } + spin_unlock(&data->lock); - if (percpu_ref_is_dying(&ctx->file_data->refs)) + if (percpu_ref_is_dying(&data->refs)) delay = 0; - first_add = llist_add(&ref_node->llist, &ctx->file_put_llist); if (!delay) mod_delayed_work(system_wq, &ctx->file_put_work, 0); else if (first_add) @@ -7341,6 +7398,7 @@ static struct fixed_file_ref_node *alloc_fixed_file_ref_node( INIT_LIST_HEAD(&ref_node->node); INIT_LIST_HEAD(&ref_node->file_list); ref_node->file_data = ctx->file_data; + ref_node->done = false; return ref_node; } @@ -7436,7 +7494,7 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, file_data->node = ref_node; spin_lock(&file_data->lock); - list_add(&ref_node->node, &file_data->ref_list); + list_add_tail(&ref_node->node, &file_data->ref_list); spin_unlock(&file_data->lock); percpu_ref_get(&file_data->refs); return ret; @@ -7595,7 +7653,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, if (needs_switch) { percpu_ref_kill(&data->node->refs); spin_lock(&data->lock); - list_add(&ref_node->node, &data->ref_list); + list_add_tail(&ref_node->node, &data->ref_list); data->node = ref_node; spin_unlock(&data->lock); percpu_ref_get(&ctx->file_data->refs); @@ -7695,7 +7753,8 @@ static int io_uring_alloc_task_context(struct task_struct *task) xa_init(&tctx->xa); init_waitqueue_head(&tctx->wait); tctx->last = NULL; - tctx->in_idle = 0; + atomic_set(&tctx->in_idle, 0); + tctx->sqpoll = false; io_init_identity(&tctx->__identity); tctx->identity = &tctx->__identity; task->io_uring = tctx; @@ -8388,22 +8447,6 @@ static bool io_match_link(struct io_kiocb *preq, struct io_kiocb *req) return false; } -static bool io_match_link_files(struct io_kiocb *req, - struct files_struct *files) -{ - struct io_kiocb *link; - - if (io_match_files(req, files)) - return true; - if (req->flags & REQ_F_LINK_HEAD) { - list_for_each_entry(link, &req->link_list, link_list) { - if (io_match_files(link, files)) - return true; - } - } - return false; -} - /* * We're looking to cancel 'req' because it's holding on to our files, but * 'req' could be a link to another request. See if it is, and cancel that @@ -8453,7 +8496,21 @@ static bool io_timeout_remove_link(struct io_ring_ctx *ctx, static bool io_cancel_link_cb(struct io_wq_work *work, void *data) { - return io_match_link(container_of(work, struct io_kiocb, work), data); + struct io_kiocb *req = container_of(work, struct io_kiocb, work); + bool ret; + + if (req->flags & REQ_F_LINK_TIMEOUT) { + unsigned long flags; + struct io_ring_ctx *ctx = req->ctx; + + /* protect against races with linked timeouts */ + spin_lock_irqsave(&ctx->completion_lock, flags); + ret = io_match_link(req, data); + spin_unlock_irqrestore(&ctx->completion_lock, flags); + } else { + ret = io_match_link(req, data); + } + return ret; } static void io_attempt_cancel(struct io_ring_ctx *ctx, struct io_kiocb *req) @@ -8479,6 +8536,7 @@ static void io_attempt_cancel(struct io_ring_ctx *ctx, struct io_kiocb *req) } static void io_cancel_defer_files(struct io_ring_ctx *ctx, + struct task_struct *task, struct files_struct *files) { struct io_defer_entry *de = NULL; @@ -8486,7 +8544,8 @@ static void io_cancel_defer_files(struct io_ring_ctx *ctx, spin_lock_irq(&ctx->completion_lock); list_for_each_entry_reverse(de, &ctx->defer_list, list) { - if (io_match_link_files(de->req, files)) { + if (io_task_match(de->req, task) && + io_match_files(de->req, files)) { list_cut_position(&list, &ctx->defer_list, &de->list); break; } @@ -8512,7 +8571,6 @@ static bool io_uring_cancel_files(struct io_ring_ctx *ctx, if (list_empty_careful(&ctx->inflight_list)) return false; - io_cancel_defer_files(ctx, files); /* cancel all at once, should be faster than doing it one by one*/ io_wq_cancel_cb(ctx->io_wq, io_wq_files_match, files, true); @@ -8598,8 +8656,16 @@ static void io_uring_cancel_task_requests(struct io_ring_ctx *ctx, { struct task_struct *task = current; - if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data) + if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data) { task = ctx->sq_data->thread; + atomic_inc(&task->io_uring->in_idle); + io_sq_thread_park(ctx->sq_data); + } + + if (files) + io_cancel_defer_files(ctx, NULL, files); + else + io_cancel_defer_files(ctx, task, NULL); io_cqring_overflow_flush(ctx, true, task, files); @@ -8607,12 +8673,23 @@ static void io_uring_cancel_task_requests(struct io_ring_ctx *ctx, io_run_task_work(); cond_resched(); } + + if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data) { + atomic_dec(&task->io_uring->in_idle); + /* + * If the files that are going away are the ones in the thread + * identity, clear them out. + */ + if (task->io_uring->identity->files == files) + task->io_uring->identity->files = NULL; + io_sq_thread_unpark(ctx->sq_data); + } } /* * Note that this task has used io_uring. We use it for cancelation purposes. */ -static int io_uring_add_task_file(struct file *file) +static int io_uring_add_task_file(struct io_ring_ctx *ctx, struct file *file) { struct io_uring_task *tctx = current->io_uring; @@ -8634,6 +8711,14 @@ static int io_uring_add_task_file(struct file *file) tctx->last = file; } + /* + * This is race safe in that the task itself is doing this, hence it + * cannot be going through the exit/cancel paths at the same time. + * This cannot be modified while exit/cancel is running. + */ + if (!tctx->sqpoll && (ctx->flags & IORING_SETUP_SQPOLL)) + tctx->sqpoll = true; + return 0; } @@ -8675,7 +8760,7 @@ void __io_uring_files_cancel(struct files_struct *files) unsigned long index; /* make sure overflow events are dropped */ - tctx->in_idle = true; + atomic_inc(&tctx->in_idle); xa_for_each(&tctx->xa, index, file) { struct io_ring_ctx *ctx = file->private_data; @@ -8684,6 +8769,35 @@ void __io_uring_files_cancel(struct files_struct *files) if (files) io_uring_del_task_file(file); } + + atomic_dec(&tctx->in_idle); +} + +static s64 tctx_inflight(struct io_uring_task *tctx) +{ + unsigned long index; + struct file *file; + s64 inflight; + + inflight = percpu_counter_sum(&tctx->inflight); + if (!tctx->sqpoll) + return inflight; + + /* + * If we have SQPOLL rings, then we need to iterate and find them, and + * add the pending count for those. + */ + xa_for_each(&tctx->xa, index, file) { + struct io_ring_ctx *ctx = file->private_data; + + if (ctx->flags & IORING_SETUP_SQPOLL) { + struct io_uring_task *__tctx = ctx->sqo_task->io_uring; + + inflight += percpu_counter_sum(&__tctx->inflight); + } + } + + return inflight; } /* @@ -8697,11 +8811,11 @@ void __io_uring_task_cancel(void) s64 inflight; /* make sure overflow events are dropped */ - tctx->in_idle = true; + atomic_inc(&tctx->in_idle); do { /* read completions before cancelations */ - inflight = percpu_counter_sum(&tctx->inflight); + inflight = tctx_inflight(tctx); if (!inflight) break; __io_uring_files_cancel(NULL); @@ -8712,13 +8826,13 @@ void __io_uring_task_cancel(void) * If we've seen completions, retry. This avoids a race where * a completion comes in before we did prepare_to_wait(). */ - if (inflight != percpu_counter_sum(&tctx->inflight)) + if (inflight != tctx_inflight(tctx)) continue; schedule(); } while (1); finish_wait(&tctx->wait, &wait); - tctx->in_idle = false; + atomic_dec(&tctx->in_idle); } static int io_uring_flush(struct file *file, void *data) @@ -8863,7 +8977,7 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, io_sqpoll_wait_sq(ctx); submitted = to_submit; } else if (to_submit) { - ret = io_uring_add_task_file(f.file); + ret = io_uring_add_task_file(ctx, f.file); if (unlikely(ret)) goto out; mutex_lock(&ctx->uring_lock); @@ -8900,7 +9014,8 @@ out_fput: #ifdef CONFIG_PROC_FS static int io_uring_show_cred(int id, void *p, void *data) { - const struct cred *cred = p; + struct io_identity *iod = p; + const struct cred *cred = iod->creds; struct seq_file *m = data; struct user_namespace *uns = seq_user_ns(m); struct group_info *gi; @@ -9092,7 +9207,7 @@ err_fd: #if defined(CONFIG_UNIX) ctx->ring_sock->file = file; #endif - if (unlikely(io_uring_add_task_file(file))) { + if (unlikely(io_uring_add_task_file(ctx, file))) { file = ERR_PTR(-ENOMEM); goto err_fd; } @@ -9137,6 +9252,7 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, * to a power-of-two, if it isn't already. We do NOT impose * any cq vs sq ring sizing. */ + p->cq_entries = roundup_pow_of_two(p->cq_entries); if (p->cq_entries < p->sq_entries) return -EINVAL; if (p->cq_entries > IORING_MAX_CQ_ENTRIES) { @@ -9144,7 +9260,6 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, return -EINVAL; p->cq_entries = IORING_MAX_CQ_ENTRIES; } - p->cq_entries = roundup_pow_of_two(p->cq_entries); } else { p->cq_entries = 2 * p->sq_entries; } diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 8180061b9e16..10cc7979ce38 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -1374,6 +1374,7 @@ iomap_writepage_map(struct iomap_writepage_ctx *wpc, WARN_ON_ONCE(!wpc->ioend && !list_empty(&submit_list)); WARN_ON_ONCE(!PageLocked(page)); WARN_ON_ONCE(PageWriteback(page)); + WARN_ON_ONCE(PageDirty(page)); /* * We cannot cancel the ioend directly here on error. We may have @@ -1382,33 +1383,22 @@ iomap_writepage_map(struct iomap_writepage_ctx *wpc, * appropriately. */ if (unlikely(error)) { + /* + * Let the filesystem know what portion of the current page + * failed to map. If the page wasn't been added to ioend, it + * won't be affected by I/O completion and we must unlock it + * now. + */ + if (wpc->ops->discard_page) + wpc->ops->discard_page(page, file_offset); if (!count) { - /* - * If the current page hasn't been added to ioend, it - * won't be affected by I/O completions and we must - * discard and unlock it right here. - */ - if (wpc->ops->discard_page) - wpc->ops->discard_page(page); ClearPageUptodate(page); unlock_page(page); goto done; } - - /* - * If the page was not fully cleaned, we need to ensure that the - * higher layers come back to it correctly. That means we need - * to keep the page dirty, and for WB_SYNC_ALL writeback we need - * to ensure the PAGECACHE_TAG_TOWRITE index mark is not removed - * so another attempt to write this page in this writeback sweep - * will be made. - */ - set_page_writeback_keepwrite(page); - } else { - clear_page_dirty_for_io(page); - set_page_writeback(page); } + set_page_writeback(page); unlock_page(page); /* diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 263f02ad8ebf..472932b9e6bc 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -106,6 +106,8 @@ static int __try_to_free_cp_buf(struct journal_head *jh) * for a checkpoint to free up some space in the log. */ void __jbd2_log_wait_for_space(journal_t *journal) +__acquires(&journal->j_state_lock) +__releases(&journal->j_state_lock) { int nblocks, space_left; /* assert_spin_locked(&journal->j_state_lock); */ diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index fa688e163a80..b121d7d434c6 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -450,6 +450,15 @@ void jbd2_journal_commit_transaction(journal_t *journal) schedule(); write_lock(&journal->j_state_lock); finish_wait(&journal->j_fc_wait, &wait); + /* + * TODO: by blocking fast commits here, we are increasing + * fsync() latency slightly. Strictly speaking, we don't need + * to block fast commits until the transaction enters T_FLUSH + * state. So an optimization is possible where we block new fast + * commits here and wait for existing ones to complete + * just before we enter T_FLUSH. That way, the existing fast + * commits and this full commit can proceed parallely. + */ } write_unlock(&journal->j_state_lock); @@ -801,7 +810,7 @@ start_journal_io: if (first_block < journal->j_tail) freed += journal->j_last - journal->j_first; /* Update tail only if we free significant amount of space */ - if (freed < journal->j_maxlen / 4) + if (freed < jbd2_journal_get_max_txn_bufs(journal)) update_tail = 0; } J_ASSERT(commit_transaction->t_state == T_COMMIT); diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 0c7c42bd530f..188f79d76988 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -566,12 +566,14 @@ static int __jbd2_journal_force_commit(journal_t *journal) } /** - * Force and wait upon a commit if the calling process is not within - * transaction. This is used for forcing out undo-protected data which contains - * bitmaps, when the fs is running out of space. + * jbd2_journal_force_commit_nested - Force and wait upon a commit if the + * calling process is not within transaction. * * @journal: journal to force * Returns true if progress was made. + * + * This is used for forcing out undo-protected data which contains + * bitmaps, when the fs is running out of space. */ int jbd2_journal_force_commit_nested(journal_t *journal) { @@ -582,7 +584,7 @@ int jbd2_journal_force_commit_nested(journal_t *journal) } /** - * int journal_force_commit() - force any uncommitted transactions + * jbd2_journal_force_commit() - force any uncommitted transactions * @journal: journal to force * * Caller want unconditional commit. We can only force the running transaction @@ -727,6 +729,8 @@ int jbd2_log_wait_commit(journal_t *journal, tid_t tid) */ int jbd2_fc_begin_commit(journal_t *journal, tid_t tid) { + if (unlikely(is_journal_aborted(journal))) + return -EIO; /* * Fast commits only allowed if at least one full commit has * been processed. @@ -734,10 +738,12 @@ int jbd2_fc_begin_commit(journal_t *journal, tid_t tid) if (!journal->j_stats.ts_tid) return -EINVAL; - if (tid <= journal->j_commit_sequence) + write_lock(&journal->j_state_lock); + if (tid <= journal->j_commit_sequence) { + write_unlock(&journal->j_state_lock); return -EALREADY; + } - write_lock(&journal->j_state_lock); if (journal->j_flags & JBD2_FULL_COMMIT_ONGOING || (journal->j_flags & JBD2_FAST_COMMIT_ONGOING)) { DEFINE_WAIT(wait); @@ -777,13 +783,19 @@ static int __jbd2_fc_end_commit(journal_t *journal, tid_t tid, bool fallback) int jbd2_fc_end_commit(journal_t *journal) { - return __jbd2_fc_end_commit(journal, 0, 0); + return __jbd2_fc_end_commit(journal, 0, false); } EXPORT_SYMBOL(jbd2_fc_end_commit); -int jbd2_fc_end_commit_fallback(journal_t *journal, tid_t tid) +int jbd2_fc_end_commit_fallback(journal_t *journal) { - return __jbd2_fc_end_commit(journal, tid, 1); + tid_t tid; + + read_lock(&journal->j_state_lock); + tid = journal->j_running_transaction ? + journal->j_running_transaction->t_tid : 0; + read_unlock(&journal->j_state_lock); + return __jbd2_fc_end_commit(journal, tid, true); } EXPORT_SYMBOL(jbd2_fc_end_commit_fallback); @@ -865,7 +877,6 @@ int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out) int fc_off; *bh_out = NULL; - write_lock(&journal->j_state_lock); if (journal->j_fc_off + journal->j_fc_first < journal->j_fc_last) { fc_off = journal->j_fc_off; @@ -874,7 +885,6 @@ int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out) } else { ret = -EINVAL; } - write_unlock(&journal->j_state_lock); if (ret) return ret; @@ -887,11 +897,7 @@ int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out) if (!bh) return -ENOMEM; - lock_buffer(bh); - clear_buffer_uptodate(bh); - set_buffer_dirty(bh); - unlock_buffer(bh); journal->j_fc_wbuf[fc_off] = bh; *bh_out = bh; @@ -909,9 +915,7 @@ int jbd2_fc_wait_bufs(journal_t *journal, int num_blks) struct buffer_head *bh; int i, j_fc_off; - read_lock(&journal->j_state_lock); j_fc_off = journal->j_fc_off; - read_unlock(&journal->j_state_lock); /* * Wait in reverse order to minimize chances of us being woken up before @@ -939,9 +943,7 @@ int jbd2_fc_release_bufs(journal_t *journal) struct buffer_head *bh; int i, j_fc_off; - read_lock(&journal->j_state_lock); j_fc_off = journal->j_fc_off; - read_unlock(&journal->j_state_lock); /* * Wait in reverse order to minimize chances of us being woken up before @@ -1348,23 +1350,16 @@ static journal_t *journal_init_common(struct block_device *bdev, journal->j_dev = bdev; journal->j_fs_dev = fs_dev; journal->j_blk_offset = start; - journal->j_maxlen = len; + journal->j_total_len = len; /* We need enough buffers to write out full descriptor block. */ n = journal->j_blocksize / jbd2_min_tag_size(); journal->j_wbufsize = n; + journal->j_fc_wbuf = NULL; journal->j_wbuf = kmalloc_array(n, sizeof(struct buffer_head *), GFP_KERNEL); if (!journal->j_wbuf) goto err_cleanup; - if (journal->j_fc_wbufsize > 0) { - journal->j_fc_wbuf = kmalloc_array(journal->j_fc_wbufsize, - sizeof(struct buffer_head *), - GFP_KERNEL); - if (!journal->j_fc_wbuf) - goto err_cleanup; - } - bh = getblk_unmovable(journal->j_dev, start, journal->j_blocksize); if (!bh) { pr_err("%s: Cannot get buffer for journal superblock\n", @@ -1378,23 +1373,11 @@ static journal_t *journal_init_common(struct block_device *bdev, err_cleanup: kfree(journal->j_wbuf); - kfree(journal->j_fc_wbuf); jbd2_journal_destroy_revoke(journal); kfree(journal); return NULL; } -int jbd2_fc_init(journal_t *journal, int num_fc_blks) -{ - journal->j_fc_wbufsize = num_fc_blks; - journal->j_fc_wbuf = kmalloc_array(journal->j_fc_wbufsize, - sizeof(struct buffer_head *), GFP_KERNEL); - if (!journal->j_fc_wbuf) - return -ENOMEM; - return 0; -} -EXPORT_SYMBOL(jbd2_fc_init); - /* jbd2_journal_init_dev and jbd2_journal_init_inode: * * Create a journal structure assigned some fixed set of disk blocks to @@ -1512,16 +1495,7 @@ static int journal_reset(journal_t *journal) } journal->j_first = first; - - if (jbd2_has_feature_fast_commit(journal) && - journal->j_fc_wbufsize > 0) { - journal->j_fc_last = last; - journal->j_last = last - journal->j_fc_wbufsize; - journal->j_fc_first = journal->j_last + 1; - journal->j_fc_off = 0; - } else { - journal->j_last = last; - } + journal->j_last = last; journal->j_head = journal->j_first; journal->j_tail = journal->j_first; @@ -1531,7 +1505,14 @@ static int journal_reset(journal_t *journal) journal->j_commit_sequence = journal->j_transaction_sequence - 1; journal->j_commit_request = journal->j_commit_sequence; - journal->j_max_transaction_buffers = journal->j_maxlen / 4; + journal->j_max_transaction_buffers = jbd2_journal_get_max_txn_bufs(journal); + + /* + * Now that journal recovery is done, turn fast commits off here. This + * way, if fast commit was enabled before the crash but if now FS has + * disabled it, we don't enable fast commits. + */ + jbd2_clear_feature_fast_commit(journal); /* * As a special case, if the on-disk copy is already marked as needing @@ -1792,15 +1773,15 @@ static int journal_get_superblock(journal_t *journal) goto out; } - if (be32_to_cpu(sb->s_maxlen) < journal->j_maxlen) - journal->j_maxlen = be32_to_cpu(sb->s_maxlen); - else if (be32_to_cpu(sb->s_maxlen) > journal->j_maxlen) { + if (be32_to_cpu(sb->s_maxlen) < journal->j_total_len) + journal->j_total_len = be32_to_cpu(sb->s_maxlen); + else if (be32_to_cpu(sb->s_maxlen) > journal->j_total_len) { printk(KERN_WARNING "JBD2: journal file too short\n"); goto out; } if (be32_to_cpu(sb->s_first) == 0 || - be32_to_cpu(sb->s_first) >= journal->j_maxlen) { + be32_to_cpu(sb->s_first) >= journal->j_total_len) { printk(KERN_WARNING "JBD2: Invalid start block of journal: %u\n", be32_to_cpu(sb->s_first)); @@ -1872,6 +1853,7 @@ static int load_superblock(journal_t *journal) { int err; journal_superblock_t *sb; + int num_fc_blocks; err = journal_get_superblock(journal); if (err) @@ -1883,15 +1865,17 @@ static int load_superblock(journal_t *journal) journal->j_tail = be32_to_cpu(sb->s_start); journal->j_first = be32_to_cpu(sb->s_first); journal->j_errno = be32_to_cpu(sb->s_errno); + journal->j_last = be32_to_cpu(sb->s_maxlen); - if (jbd2_has_feature_fast_commit(journal) && - journal->j_fc_wbufsize > 0) { + if (jbd2_has_feature_fast_commit(journal)) { journal->j_fc_last = be32_to_cpu(sb->s_maxlen); - journal->j_last = journal->j_fc_last - journal->j_fc_wbufsize; + num_fc_blocks = be32_to_cpu(sb->s_num_fc_blks); + if (!num_fc_blocks) + num_fc_blocks = JBD2_MIN_FC_BLOCKS; + if (journal->j_last - num_fc_blocks >= JBD2_MIN_JOURNAL_BLOCKS) + journal->j_last = journal->j_fc_last - num_fc_blocks; journal->j_fc_first = journal->j_last + 1; journal->j_fc_off = 0; - } else { - journal->j_last = be32_to_cpu(sb->s_maxlen); } return 0; @@ -1899,7 +1883,7 @@ static int load_superblock(journal_t *journal) /** - * int jbd2_journal_load() - Read journal from disk. + * jbd2_journal_load() - Read journal from disk. * @journal: Journal to act on. * * Given a journal_t structure which tells us which disk blocks contain @@ -1954,9 +1938,6 @@ int jbd2_journal_load(journal_t *journal) */ journal->j_flags &= ~JBD2_ABORT; - if (journal->j_fc_wbufsize > 0) - jbd2_journal_set_features(journal, 0, 0, - JBD2_FEATURE_INCOMPAT_FAST_COMMIT); /* OK, we've finished with the dynamic journal bits: * reinitialise the dynamic contents of the superblock in memory * and reset them on disk. */ @@ -1972,7 +1953,7 @@ recovery_error: } /** - * void jbd2_journal_destroy() - Release a journal_t structure. + * jbd2_journal_destroy() - Release a journal_t structure. * @journal: Journal to act on. * * Release a journal_t structure once it is no longer in use by the @@ -2040,8 +2021,7 @@ int jbd2_journal_destroy(journal_t *journal) jbd2_journal_destroy_revoke(journal); if (journal->j_chksum_driver) crypto_free_shash(journal->j_chksum_driver); - if (journal->j_fc_wbufsize > 0) - kfree(journal->j_fc_wbuf); + kfree(journal->j_fc_wbuf); kfree(journal->j_wbuf); kfree(journal); @@ -2050,7 +2030,7 @@ int jbd2_journal_destroy(journal_t *journal) /** - *int jbd2_journal_check_used_features() - Check if features specified are used. + * jbd2_journal_check_used_features() - Check if features specified are used. * @journal: Journal to check. * @compat: bitmask of compatible features * @ro: bitmask of features that force read-only mount @@ -2085,7 +2065,7 @@ int jbd2_journal_check_used_features(journal_t *journal, unsigned long compat, } /** - * int jbd2_journal_check_available_features() - Check feature set in journalling layer + * jbd2_journal_check_available_features() - Check feature set in journalling layer * @journal: Journal to check. * @compat: bitmask of compatible features * @ro: bitmask of features that force read-only mount @@ -2116,8 +2096,39 @@ int jbd2_journal_check_available_features(journal_t *journal, unsigned long comp return 0; } +static int +jbd2_journal_initialize_fast_commit(journal_t *journal) +{ + journal_superblock_t *sb = journal->j_superblock; + unsigned long long num_fc_blks; + + num_fc_blks = be32_to_cpu(sb->s_num_fc_blks); + if (num_fc_blks == 0) + num_fc_blks = JBD2_MIN_FC_BLOCKS; + if (journal->j_last - num_fc_blks < JBD2_MIN_JOURNAL_BLOCKS) + return -ENOSPC; + + /* Are we called twice? */ + WARN_ON(journal->j_fc_wbuf != NULL); + journal->j_fc_wbuf = kmalloc_array(num_fc_blks, + sizeof(struct buffer_head *), GFP_KERNEL); + if (!journal->j_fc_wbuf) + return -ENOMEM; + + journal->j_fc_wbufsize = num_fc_blks; + journal->j_fc_last = journal->j_last; + journal->j_last = journal->j_fc_last - num_fc_blks; + journal->j_fc_first = journal->j_last + 1; + journal->j_fc_off = 0; + journal->j_free = journal->j_last - journal->j_first; + journal->j_max_transaction_buffers = + jbd2_journal_get_max_txn_bufs(journal); + + return 0; +} + /** - * int jbd2_journal_set_features() - Mark a given journal feature in the superblock + * jbd2_journal_set_features() - Mark a given journal feature in the superblock * @journal: Journal to act on. * @compat: bitmask of compatible features * @ro: bitmask of features that force read-only mount @@ -2159,6 +2170,13 @@ int jbd2_journal_set_features(journal_t *journal, unsigned long compat, sb = journal->j_superblock; + if (incompat & JBD2_FEATURE_INCOMPAT_FAST_COMMIT) { + if (jbd2_journal_initialize_fast_commit(journal)) { + pr_err("JBD2: Cannot enable fast commits.\n"); + return 0; + } + } + /* Load the checksum driver if necessary */ if ((journal->j_chksum_driver == NULL) && INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V3)) { @@ -2201,7 +2219,7 @@ int jbd2_journal_set_features(journal_t *journal, unsigned long compat, } /* - * jbd2_journal_clear_features () - Clear a given journal feature in the + * jbd2_journal_clear_features() - Clear a given journal feature in the * superblock * @journal: Journal to act on. * @compat: bitmask of compatible features @@ -2230,7 +2248,7 @@ void jbd2_journal_clear_features(journal_t *journal, unsigned long compat, EXPORT_SYMBOL(jbd2_journal_clear_features); /** - * int jbd2_journal_flush () - Flush journal + * jbd2_journal_flush() - Flush journal * @journal: Journal to act on. * * Flush all data for a given journal to disk and empty the journal. @@ -2305,7 +2323,7 @@ out: } /** - * int jbd2_journal_wipe() - Wipe journal contents + * jbd2_journal_wipe() - Wipe journal contents * @journal: Journal to act on. * @write: flag (see below) * @@ -2346,7 +2364,7 @@ int jbd2_journal_wipe(journal_t *journal, int write) } /** - * void jbd2_journal_abort () - Shutdown the journal immediately. + * jbd2_journal_abort () - Shutdown the journal immediately. * @journal: the journal to shutdown. * @errno: an error number to record in the journal indicating * the reason for the shutdown. @@ -2437,7 +2455,7 @@ void jbd2_journal_abort(journal_t *journal, int errno) } /** - * int jbd2_journal_errno () - returns the journal's error state. + * jbd2_journal_errno() - returns the journal's error state. * @journal: journal to examine. * * This is the errno number set with jbd2_journal_abort(), the last @@ -2461,7 +2479,7 @@ int jbd2_journal_errno(journal_t *journal) } /** - * int jbd2_journal_clear_err () - clears the journal's error state + * jbd2_journal_clear_err() - clears the journal's error state * @journal: journal to act on. * * An error must be cleared or acked to take a FS out of readonly @@ -2481,7 +2499,7 @@ int jbd2_journal_clear_err(journal_t *journal) } /** - * void jbd2_journal_ack_err() - Ack journal err. + * jbd2_journal_ack_err() - Ack journal err. * @journal: journal to act on. * * An error must be cleared or acked to take a FS out of readonly diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c index eb2606133cd8..dc0694fcfcd1 100644 --- a/fs/jbd2/recovery.c +++ b/fs/jbd2/recovery.c @@ -74,8 +74,8 @@ static int do_readahead(journal_t *journal, unsigned int start) /* Do up to 128K of readahead */ max = start + (128 * 1024 / journal->j_blocksize); - if (max > journal->j_maxlen) - max = journal->j_maxlen; + if (max > journal->j_total_len) + max = journal->j_total_len; /* Do the readahead itself. We'll submit MAXBUF buffer_heads at * a time to the block device IO layer. */ @@ -134,7 +134,7 @@ static int jread(struct buffer_head **bhp, journal_t *journal, *bhp = NULL; - if (offset >= journal->j_maxlen) { + if (offset >= journal->j_total_len) { printk(KERN_ERR "JBD2: corrupted journal superblock\n"); return -EFSCORRUPTED; } diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 43985738aa86..9396666b7314 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -195,8 +195,10 @@ static void wait_transaction_switching(journal_t *journal) DEFINE_WAIT(wait); if (WARN_ON(!journal->j_running_transaction || - journal->j_running_transaction->t_state != T_SWITCH)) + journal->j_running_transaction->t_state != T_SWITCH)) { + read_unlock(&journal->j_state_lock); return; + } prepare_to_wait(&journal->j_wait_transaction_locked, &wait, TASK_UNINTERRUPTIBLE); read_unlock(&journal->j_state_lock); @@ -517,7 +519,7 @@ EXPORT_SYMBOL(jbd2__journal_start); /** - * handle_t *jbd2_journal_start() - Obtain a new handle. + * jbd2_journal_start() - Obtain a new handle. * @journal: Journal to start transaction on. * @nblocks: number of block buffer we might modify * @@ -564,7 +566,7 @@ void jbd2_journal_free_reserved(handle_t *handle) EXPORT_SYMBOL(jbd2_journal_free_reserved); /** - * int jbd2_journal_start_reserved() - start reserved handle + * jbd2_journal_start_reserved() - start reserved handle * @handle: handle to start * @type: for handle statistics * @line_no: for handle statistics @@ -618,7 +620,7 @@ int jbd2_journal_start_reserved(handle_t *handle, unsigned int type, EXPORT_SYMBOL(jbd2_journal_start_reserved); /** - * int jbd2_journal_extend() - extend buffer credits. + * jbd2_journal_extend() - extend buffer credits. * @handle: handle to 'extend' * @nblocks: nr blocks to try to extend by. * @revoke_records: number of revoke records to try to extend by. @@ -743,7 +745,7 @@ static void stop_this_handle(handle_t *handle) } /** - * int jbd2_journal_restart() - restart a handle . + * jbd2__journal_restart() - restart a handle . * @handle: handle to restart * @nblocks: nr credits requested * @revoke_records: number of revoke record credits requested @@ -813,7 +815,7 @@ int jbd2_journal_restart(handle_t *handle, int nblocks) EXPORT_SYMBOL(jbd2_journal_restart); /** - * void jbd2_journal_lock_updates () - establish a transaction barrier. + * jbd2_journal_lock_updates () - establish a transaction barrier. * @journal: Journal to establish a barrier on. * * This locks out any further updates from being started, and blocks @@ -872,7 +874,7 @@ void jbd2_journal_lock_updates(journal_t *journal) } /** - * void jbd2_journal_unlock_updates (journal_t* journal) - release barrier + * jbd2_journal_unlock_updates () - release barrier * @journal: Journal to release the barrier on. * * Release a transaction barrier obtained with jbd2_journal_lock_updates(). @@ -1180,7 +1182,8 @@ out: } /** - * int jbd2_journal_get_write_access() - notify intent to modify a buffer for metadata (not data) update. + * jbd2_journal_get_write_access() - notify intent to modify a buffer + * for metadata (not data) update. * @handle: transaction to add buffer modifications to * @bh: bh to be used for metadata writes * @@ -1224,7 +1227,7 @@ int jbd2_journal_get_write_access(handle_t *handle, struct buffer_head *bh) * unlocked buffer beforehand. */ /** - * int jbd2_journal_get_create_access () - notify intent to use newly created bh + * jbd2_journal_get_create_access () - notify intent to use newly created bh * @handle: transaction to new buffer to * @bh: new buffer. * @@ -1304,7 +1307,7 @@ out: } /** - * int jbd2_journal_get_undo_access() - Notify intent to modify metadata with + * jbd2_journal_get_undo_access() - Notify intent to modify metadata with * non-rewindable consequences * @handle: transaction * @bh: buffer to undo @@ -1381,7 +1384,7 @@ out: } /** - * void jbd2_journal_set_triggers() - Add triggers for commit writeout + * jbd2_journal_set_triggers() - Add triggers for commit writeout * @bh: buffer to trigger on * @type: struct jbd2_buffer_trigger_type containing the trigger(s). * @@ -1423,7 +1426,7 @@ void jbd2_buffer_abort_trigger(struct journal_head *jh, } /** - * int jbd2_journal_dirty_metadata() - mark a buffer as containing dirty metadata + * jbd2_journal_dirty_metadata() - mark a buffer as containing dirty metadata * @handle: transaction to add buffer to. * @bh: buffer to mark * @@ -1591,7 +1594,7 @@ out: } /** - * void jbd2_journal_forget() - bforget() for potentially-journaled buffers. + * jbd2_journal_forget() - bforget() for potentially-journaled buffers. * @handle: transaction handle * @bh: bh to 'forget' * @@ -1760,7 +1763,7 @@ drop: } /** - * int jbd2_journal_stop() - complete a transaction + * jbd2_journal_stop() - complete a transaction * @handle: transaction to complete. * * All done for a particular handle. @@ -2078,7 +2081,7 @@ out: } /** - * int jbd2_journal_try_to_free_buffers() - try to free page buffers. + * jbd2_journal_try_to_free_buffers() - try to free page buffers. * @journal: journal for operation * @page: to try and free * @@ -2409,7 +2412,7 @@ zap_buffer_unlocked: } /** - * void jbd2_journal_invalidatepage() + * jbd2_journal_invalidatepage() * @journal: journal to use for flush... * @page: page to flush * @offset: start of the range to invalidate diff --git a/fs/libfs.c b/fs/libfs.c index fc34361c1489..7124c2e8df2f 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -959,7 +959,7 @@ ssize_t simple_attr_write(struct file *file, const char __user *buf, size_t len, loff_t *ppos) { struct simple_attr *attr; - u64 val; + unsigned long long val; size_t size; ssize_t ret; @@ -977,7 +977,9 @@ ssize_t simple_attr_write(struct file *file, const char __user *buf, goto out; attr->set_buf[size] = '\0'; - val = simple_strtoll(attr->set_buf, NULL, 0); + ret = kstrtoull(attr->set_buf, 0, &val); + if (ret) + goto out; ret = attr->set(attr->data, val); if (ret == 0) ret = len; /* on success, claim we got the whole input */ diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index cb52db9a0cfb..4e011adaf967 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -955,7 +955,6 @@ out: static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence) { - struct inode *inode = file_inode(filp); struct nfs_open_dir_context *dir_ctx = filp->private_data; dfprintk(FILE, "NFS: llseek dir(%pD2, %lld, %d)\n", @@ -967,15 +966,15 @@ static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence) case SEEK_SET: if (offset < 0) return -EINVAL; - inode_lock(inode); + spin_lock(&filp->f_lock); break; case SEEK_CUR: if (offset == 0) return filp->f_pos; - inode_lock(inode); + spin_lock(&filp->f_lock); offset += filp->f_pos; if (offset < 0) { - inode_unlock(inode); + spin_unlock(&filp->f_lock); return -EINVAL; } } @@ -987,7 +986,7 @@ static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence) dir_ctx->dir_cookie = 0; dir_ctx->duped = 0; } - inode_unlock(inode); + spin_unlock(&filp->f_lock); return offset; } @@ -998,13 +997,9 @@ static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence) static int nfs_fsync_dir(struct file *filp, loff_t start, loff_t end, int datasync) { - struct inode *inode = file_inode(filp); - dfprintk(FILE, "NFS: fsync dir(%pD2) datasync %d\n", filp, datasync); - inode_lock(inode); - nfs_inc_stats(inode, NFSIOS_VFSFSYNC); - inode_unlock(inode); + nfs_inc_stats(file_inode(filp), NFSIOS_VFSFSYNC); return 0; } diff --git a/fs/nfs/nfs42xattr.c b/fs/nfs/nfs42xattr.c index b51424ff8159..6c2ce799150f 100644 --- a/fs/nfs/nfs42xattr.c +++ b/fs/nfs/nfs42xattr.c @@ -1047,8 +1047,10 @@ out4: void nfs4_xattr_cache_exit(void) { + unregister_shrinker(&nfs4_xattr_large_entry_shrinker); unregister_shrinker(&nfs4_xattr_entry_shrinker); unregister_shrinker(&nfs4_xattr_cache_shrinker); + list_lru_destroy(&nfs4_xattr_large_entry_lru); list_lru_destroy(&nfs4_xattr_entry_lru); list_lru_destroy(&nfs4_xattr_cache_lru); kmem_cache_destroy(nfs4_xattr_cache_cachep); diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c index 0dc31ad2362e..6e060a88f98c 100644 --- a/fs/nfs/nfs42xdr.c +++ b/fs/nfs/nfs42xdr.c @@ -196,7 +196,7 @@ 1 + nfs4_xattr_name_maxsz + 1) #define decode_setxattr_maxsz (op_decode_hdr_maxsz + decode_change_info_maxsz) #define encode_listxattrs_maxsz (op_encode_hdr_maxsz + 2 + 1) -#define decode_listxattrs_maxsz (op_decode_hdr_maxsz + 2 + 1 + 1) +#define decode_listxattrs_maxsz (op_decode_hdr_maxsz + 2 + 1 + 1 + 1) #define encode_removexattr_maxsz (op_encode_hdr_maxsz + 1 + \ nfs4_xattr_name_maxsz) #define decode_removexattr_maxsz (op_decode_hdr_maxsz + \ @@ -531,7 +531,7 @@ static void encode_listxattrs(struct xdr_stream *xdr, { __be32 *p; - encode_op_hdr(xdr, OP_LISTXATTRS, decode_listxattrs_maxsz + 1, hdr); + encode_op_hdr(xdr, OP_LISTXATTRS, decode_listxattrs_maxsz, hdr); p = reserve_space(xdr, 12); if (unlikely(!p)) diff --git a/fs/nfs/nfsroot.c b/fs/nfs/nfsroot.c index 8d3278805602..fa148308822c 100644 --- a/fs/nfs/nfsroot.c +++ b/fs/nfs/nfsroot.c @@ -88,7 +88,13 @@ #define NFS_ROOT "/tftpboot/%s" /* Default NFSROOT mount options. */ +#if defined(CONFIG_NFS_V2) #define NFS_DEF_OPTIONS "vers=2,tcp,rsize=4096,wsize=4096" +#elif defined(CONFIG_NFS_V3) +#define NFS_DEF_OPTIONS "vers=3,tcp,rsize=4096,wsize=4096" +#else +#define NFS_DEF_OPTIONS "vers=4,tcp,rsize=4096,wsize=4096" +#endif /* Parameters passed from the kernel command line */ static char nfs_root_parms[NFS_MAXPATHLEN + 1] __initdata = ""; diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index 14468613d150..a633044b0dc1 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -316,10 +316,6 @@ nfsd3_proc_mknod(struct svc_rqst *rqstp) fh_copy(&resp->dirfh, &argp->fh); fh_init(&resp->fh, NFS3_FHSIZE); - if (argp->ftype == 0 || argp->ftype >= NF3BAD) { - resp->status = nfserr_inval; - goto out; - } if (argp->ftype == NF3CHR || argp->ftype == NF3BLK) { rdev = MKDEV(argp->major, argp->minor); if (MAJOR(rdev) != argp->major || @@ -328,7 +324,7 @@ nfsd3_proc_mknod(struct svc_rqst *rqstp) goto out; } } else if (argp->ftype != NF3SOCK && argp->ftype != NF3FIFO) { - resp->status = nfserr_inval; + resp->status = nfserr_badtype; goto out; } diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 9c23b6acf234..2277f83da250 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -1114,6 +1114,7 @@ nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, __be32 *p) { struct nfsd3_pathconfres *resp = rqstp->rq_resp; + *p++ = resp->status; *p++ = xdr_zero; /* no post_op_attr */ if (resp->status == 0) { diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index ad2fa1a8e7ad..e83b21778816 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1299,7 +1299,7 @@ nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct nfsd_file *src, struct nfsd_file *dst) { nfs42_ssc_close(src->nf_file); - nfsd_file_put(src); + /* 'src' is freed by nfsd4_do_async_copy */ nfsd_file_put(dst); mntput(ss_mnt); } @@ -1486,6 +1486,7 @@ do_callback: cb_copy = kzalloc(sizeof(struct nfsd4_copy), GFP_KERNEL); if (!cb_copy) goto out; + refcount_set(&cb_copy->refcount, 1); memcpy(&cb_copy->cp_res, ©->cp_res, sizeof(copy->cp_res)); cb_copy->cp_clp = copy->cp_clp; cb_copy->nfserr = copy->nfserr; diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index a960ec3a569a..8d3ad5ef2925 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -178,6 +178,7 @@ int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, struct inode *inode = d_inode(dentry); struct dentry *parent; bool parent_watched = dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED; + bool parent_needed, parent_interested; __u32 p_mask; struct inode *p_inode = NULL; struct name_snapshot name; @@ -193,7 +194,8 @@ int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, return 0; parent = NULL; - if (!parent_watched && !fsnotify_event_needs_parent(inode, mnt, mask)) + parent_needed = fsnotify_event_needs_parent(inode, mnt, mask); + if (!parent_watched && !parent_needed) goto notify; /* Does parent inode care about events on children? */ @@ -205,17 +207,17 @@ int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, /* * Include parent/name in notification either if some notification - * groups require parent info (!parent_watched case) or the parent is - * interested in this event. + * groups require parent info or the parent is interested in this event. */ - if (!parent_watched || (mask & p_mask & ALL_FSNOTIFY_EVENTS)) { + parent_interested = mask & p_mask & ALL_FSNOTIFY_EVENTS; + if (parent_needed || parent_interested) { /* When notifying parent, child should be passed as data */ WARN_ON_ONCE(inode != fsnotify_data_inode(data, data_type)); /* Notify both parent and child with child name info */ take_dentry_name_snapshot(&name, dentry); file_name = &name.name; - if (parent_watched) + if (parent_interested) mask |= FS_EVENT_ON_CHILD; } diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index b9a9d69dde7e..db52e843002a 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -877,7 +877,7 @@ int ocfs2_journal_init(struct ocfs2_journal *journal, int *dirty) goto done; } - trace_ocfs2_journal_init_maxlen(j_journal->j_maxlen); + trace_ocfs2_journal_init_maxlen(j_journal->j_total_len); *dirty = (le32_to_cpu(di->id1.journal1.ij_flags) & OCFS2_JOURNAL_DIRTY_FL); diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 1d91dd1e8711..2febc76e9de7 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1713,6 +1713,7 @@ static void ocfs2_inode_init_once(void *data) oi->ip_blkno = 0ULL; oi->ip_clusters = 0; + oi->ip_next_orphan = NULL; ocfs2_resv_init_once(&oi->ip_la_data_resv); diff --git a/fs/proc/base.c b/fs/proc/base.c index 0f707003dda5..b362523a9829 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1049,6 +1049,8 @@ static ssize_t oom_adj_read(struct file *file, char __user *buf, size_t count, oom_adj = (task->signal->oom_score_adj * -OOM_DISABLE) / OOM_SCORE_ADJ_MAX; put_task_struct(task); + if (oom_adj > OOM_ADJUST_MAX) + oom_adj = OOM_ADJUST_MAX; len = snprintf(buffer, sizeof(buffer), "%d\n", oom_adj); return simple_read_from_buffer(buf, count, ppos, buffer, len); } diff --git a/fs/proc/cpuinfo.c b/fs/proc/cpuinfo.c index d0989a443c77..419760fd77bd 100644 --- a/fs/proc/cpuinfo.c +++ b/fs/proc/cpuinfo.c @@ -19,7 +19,7 @@ static int cpuinfo_open(struct inode *inode, struct file *file) static const struct proc_ops cpuinfo_proc_ops = { .proc_flags = PROC_ENTRY_PERMANENT, .proc_open = cpuinfo_open, - .proc_read = seq_read, + .proc_read_iter = seq_read_iter, .proc_lseek = seq_lseek, .proc_release = seq_release, }; diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 2f9fa179194d..b84663252add 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -590,7 +590,7 @@ static int proc_seq_release(struct inode *inode, struct file *file) static const struct proc_ops proc_seq_ops = { /* not permanent -- can call into arbitrary seq_operations */ .proc_open = proc_seq_open, - .proc_read = seq_read, + .proc_read_iter = seq_read_iter, .proc_lseek = seq_lseek, .proc_release = proc_seq_release, }; @@ -621,7 +621,7 @@ static int proc_single_open(struct inode *inode, struct file *file) static const struct proc_ops proc_single_ops = { /* not permanent -- can call into arbitrary ->single_show */ .proc_open = proc_single_open, - .proc_read = seq_read, + .proc_read_iter = seq_read_iter, .proc_lseek = seq_lseek, .proc_release = single_release, }; diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 58c075e2a452..bde6b6f69852 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -597,6 +597,7 @@ static const struct file_operations proc_iter_file_ops = { .llseek = proc_reg_llseek, .read_iter = proc_reg_read_iter, .write = proc_reg_write, + .splice_read = generic_file_splice_read, .poll = proc_reg_poll, .unlocked_ioctl = proc_reg_unlocked_ioctl, .mmap = proc_reg_mmap, @@ -622,6 +623,7 @@ static const struct file_operations proc_reg_file_ops_compat = { static const struct file_operations proc_iter_file_ops_compat = { .llseek = proc_reg_llseek, .read_iter = proc_reg_read_iter, + .splice_read = generic_file_splice_read, .write = proc_reg_write, .poll = proc_reg_poll, .unlocked_ioctl = proc_reg_unlocked_ioctl, diff --git a/fs/proc/self.c b/fs/proc/self.c index 72cd69bcaf4a..cc71ce3466dc 100644 --- a/fs/proc/self.c +++ b/fs/proc/self.c @@ -16,6 +16,13 @@ static const char *proc_self_get_link(struct dentry *dentry, pid_t tgid = task_tgid_nr_ns(current, ns); char *name; + /* + * Not currently supported. Once we can inherit all of struct pid, + * we can allow this. + */ + if (current->flags & PF_KTHREAD) + return ERR_PTR(-EOPNOTSUPP); + if (!tgid) return ERR_PTR(-ENOENT); /* max length of unsigned int in decimal + NULL term */ diff --git a/fs/proc/stat.c b/fs/proc/stat.c index 46b3293015fe..4695b6de3151 100644 --- a/fs/proc/stat.c +++ b/fs/proc/stat.c @@ -226,7 +226,7 @@ static int stat_open(struct inode *inode, struct file *file) static const struct proc_ops stat_proc_ops = { .proc_flags = PROC_ENTRY_PERMANENT, .proc_open = stat_open, - .proc_read = seq_read, + .proc_read_iter = seq_read_iter, .proc_lseek = seq_lseek, .proc_release = single_release, }; diff --git a/fs/seq_file.c b/fs/seq_file.c index 31219c1db17d..3b20e21604e7 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -18,6 +18,7 @@ #include <linux/mm.h> #include <linux/printk.h> #include <linux/string_helpers.h> +#include <linux/uio.h> #include <linux/uaccess.h> #include <asm/page.h> @@ -146,7 +147,28 @@ Eoverflow: */ ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos) { - struct seq_file *m = file->private_data; + struct iovec iov = { .iov_base = buf, .iov_len = size}; + struct kiocb kiocb; + struct iov_iter iter; + ssize_t ret; + + init_sync_kiocb(&kiocb, file); + iov_iter_init(&iter, READ, &iov, 1, size); + + kiocb.ki_pos = *ppos; + ret = seq_read_iter(&kiocb, &iter); + *ppos = kiocb.ki_pos; + return ret; +} +EXPORT_SYMBOL(seq_read); + +/* + * Ready-made ->f_op->read_iter() + */ +ssize_t seq_read_iter(struct kiocb *iocb, struct iov_iter *iter) +{ + struct seq_file *m = iocb->ki_filp->private_data; + size_t size = iov_iter_count(iter); size_t copied = 0; size_t n; void *p; @@ -158,14 +180,14 @@ ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos) * if request is to read from zero offset, reset iterator to first * record as it might have been already advanced by previous requests */ - if (*ppos == 0) { + if (iocb->ki_pos == 0) { m->index = 0; m->count = 0; } - /* Don't assume *ppos is where we left it */ - if (unlikely(*ppos != m->read_pos)) { - while ((err = traverse(m, *ppos)) == -EAGAIN) + /* Don't assume ki_pos is where we left it */ + if (unlikely(iocb->ki_pos != m->read_pos)) { + while ((err = traverse(m, iocb->ki_pos)) == -EAGAIN) ; if (err) { /* With prejudice... */ @@ -174,7 +196,7 @@ ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos) m->count = 0; goto Done; } else { - m->read_pos = *ppos; + m->read_pos = iocb->ki_pos; } } @@ -187,13 +209,11 @@ ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos) /* if not empty - flush it first */ if (m->count) { n = min(m->count, size); - err = copy_to_user(buf, m->buf + m->from, n); - if (err) + if (copy_to_iter(m->buf + m->from, n, iter) != n) goto Efault; m->count -= n; m->from += n; size -= n; - buf += n; copied += n; if (!size) goto Done; @@ -254,8 +274,7 @@ Fill: } m->op->stop(m, p); n = min(m->count, size); - err = copy_to_user(buf, m->buf, n); - if (err) + if (copy_to_iter(m->buf, n, iter) != n) goto Efault; copied += n; m->count -= n; @@ -264,7 +283,7 @@ Done: if (!copied) copied = err; else { - *ppos += copied; + iocb->ki_pos += copied; m->read_pos += copied; } mutex_unlock(&m->lock); @@ -276,7 +295,7 @@ Efault: err = -EFAULT; goto Done; } -EXPORT_SYMBOL(seq_read); +EXPORT_SYMBOL(seq_read_iter); /** * seq_lseek - ->llseek() method for sequential files. diff --git a/fs/super.c b/fs/super.c index a51c2083cd6b..98bb0629ee10 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1631,55 +1631,6 @@ int super_setup_bdi(struct super_block *sb) } EXPORT_SYMBOL(super_setup_bdi); -/* - * This is an internal function, please use sb_end_{write,pagefault,intwrite} - * instead. - */ -void __sb_end_write(struct super_block *sb, int level) -{ - percpu_up_read(sb->s_writers.rw_sem + level-1); -} -EXPORT_SYMBOL(__sb_end_write); - -/* - * This is an internal function, please use sb_start_{write,pagefault,intwrite} - * instead. - */ -int __sb_start_write(struct super_block *sb, int level, bool wait) -{ - bool force_trylock = false; - int ret = 1; - -#ifdef CONFIG_LOCKDEP - /* - * We want lockdep to tell us about possible deadlocks with freezing - * but it's it bit tricky to properly instrument it. Getting a freeze - * protection works as getting a read lock but there are subtle - * problems. XFS for example gets freeze protection on internal level - * twice in some cases, which is OK only because we already hold a - * freeze protection also on higher level. Due to these cases we have - * to use wait == F (trylock mode) which must not fail. - */ - if (wait) { - int i; - - for (i = 0; i < level - 1; i++) - if (percpu_rwsem_is_held(sb->s_writers.rw_sem + i)) { - force_trylock = true; - break; - } - } -#endif - if (wait && !force_trylock) - percpu_down_read(sb->s_writers.rw_sem + level-1); - else - ret = percpu_down_read_trylock(sb->s_writers.rw_sem + level-1); - - WARN_ON(force_trylock && !ret); - return ret; -} -EXPORT_SYMBOL(__sb_start_write); - /** * sb_wait_write - wait until all writers to given file system finish * @sb: the super for which we wait diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 852b536551b5..15640015be9d 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -2467,6 +2467,7 @@ xfs_defer_agfl_block( new->xefi_startblock = XFS_AGB_TO_FSB(mp, agno, agbno); new->xefi_blockcount = 1; new->xefi_oinfo = *oinfo; + new->xefi_skip_discard = false; trace_xfs_agfl_free_defer(mp, agno, 0, agbno, 1); diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index bb128db220ac..d6ef69ab1c67 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -515,7 +515,7 @@ xfs_attr_copy_value( *========================================================================*/ /* - * Query whether the requested number of additional bytes of extended + * Query whether the total requested number of attr fork bytes of extended * attribute space will be able to fit inline. * * Returns zero if not, else the di_forkoff fork offset to be used in the @@ -535,6 +535,12 @@ xfs_attr_shortform_bytesfit( int maxforkoff; int offset; + /* + * Check if the new size could fit at all first: + */ + if (bytes > XFS_LITINO(mp)) + return 0; + /* rounded down */ offset = (XFS_LITINO(mp) - bytes) >> 3; diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h index e1bd484e5548..6747e97a7949 100644 --- a/fs/xfs/libxfs/xfs_bmap.h +++ b/fs/xfs/libxfs/xfs_bmap.h @@ -52,9 +52,9 @@ struct xfs_extent_free_item { xfs_fsblock_t xefi_startblock;/* starting fs block number */ xfs_extlen_t xefi_blockcount;/* number of blocks in extent */ + bool xefi_skip_discard; struct list_head xefi_list; struct xfs_owner_info xefi_oinfo; /* extent owner */ - bool xefi_skip_discard; }; #define XFS_BMAP_MAX_NMAP 4 diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c index 340c83f76c80..2668ebe02865 100644 --- a/fs/xfs/libxfs/xfs_rmap.c +++ b/fs/xfs/libxfs/xfs_rmap.c @@ -1514,7 +1514,7 @@ xfs_rmap_convert_shared( * record for our insertion point. This will also give us the record for * start block contiguity tests. */ - error = xfs_rmap_lookup_le_range(cur, bno, owner, offset, flags, + error = xfs_rmap_lookup_le_range(cur, bno, owner, offset, oldext, &PREV, &i); if (error) goto done; diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c index 955302e7cdde..fed56d213a3f 100644 --- a/fs/xfs/scrub/bmap.c +++ b/fs/xfs/scrub/bmap.c @@ -113,6 +113,8 @@ xchk_bmap_get_rmap( if (info->whichfork == XFS_ATTR_FORK) rflags |= XFS_RMAP_ATTR_FORK; + if (irec->br_state == XFS_EXT_UNWRITTEN) + rflags |= XFS_RMAP_UNWRITTEN; /* * CoW staging extents are owned (on disk) by the refcountbt, so @@ -216,13 +218,13 @@ xchk_bmap_xref_rmap( * which doesn't track unwritten state. */ if (owner != XFS_RMAP_OWN_COW && - irec->br_state == XFS_EXT_UNWRITTEN && - !(rmap.rm_flags & XFS_RMAP_UNWRITTEN)) + !!(irec->br_state == XFS_EXT_UNWRITTEN) != + !!(rmap.rm_flags & XFS_RMAP_UNWRITTEN)) xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, irec->br_startoff); - if (info->whichfork == XFS_ATTR_FORK && - !(rmap.rm_flags & XFS_RMAP_ATTR_FORK)) + if (!!(info->whichfork == XFS_ATTR_FORK) != + !!(rmap.rm_flags & XFS_RMAP_ATTR_FORK)) xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, irec->br_startoff); if (rmap.rm_flags & XFS_RMAP_BMBT_BLOCK) diff --git a/fs/xfs/scrub/btree.c b/fs/xfs/scrub/btree.c index f52a7b8256f9..debf392e0515 100644 --- a/fs/xfs/scrub/btree.c +++ b/fs/xfs/scrub/btree.c @@ -452,32 +452,41 @@ xchk_btree_check_minrecs( int level, struct xfs_btree_block *block) { - unsigned int numrecs; - int ok_level; - - numrecs = be16_to_cpu(block->bb_numrecs); + struct xfs_btree_cur *cur = bs->cur; + unsigned int root_level = cur->bc_nlevels - 1; + unsigned int numrecs = be16_to_cpu(block->bb_numrecs); /* More records than minrecs means the block is ok. */ - if (numrecs >= bs->cur->bc_ops->get_minrecs(bs->cur, level)) + if (numrecs >= cur->bc_ops->get_minrecs(cur, level)) return; /* - * Certain btree blocks /can/ have fewer than minrecs records. Any - * level greater than or equal to the level of the highest dedicated - * btree block are allowed to violate this constraint. - * - * For a btree rooted in a block, the btree root can have fewer than - * minrecs records. If the btree is rooted in an inode and does not - * store records in the root, the direct children of the root and the - * root itself can have fewer than minrecs records. + * For btrees rooted in the inode, it's possible that the root block + * contents spilled into a regular ondisk block because there wasn't + * enough space in the inode root. The number of records in that + * child block might be less than the standard minrecs, but that's ok + * provided that there's only one direct child of the root. */ - ok_level = bs->cur->bc_nlevels - 1; - if (bs->cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) - ok_level--; - if (level >= ok_level) + if ((cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) && + level == cur->bc_nlevels - 2) { + struct xfs_btree_block *root_block; + struct xfs_buf *root_bp; + int root_maxrecs; + + root_block = xfs_btree_get_block(cur, root_level, &root_bp); + root_maxrecs = cur->bc_ops->get_dmaxrecs(cur, root_level); + if (be16_to_cpu(root_block->bb_numrecs) != 1 || + numrecs <= root_maxrecs) + xchk_btree_set_corrupt(bs->sc, cur, level); return; + } - xchk_btree_set_corrupt(bs->sc, bs->cur, level); + /* + * Otherwise, only the root level is allowed to have fewer than minrecs + * records or keyptrs. + */ + if (level < root_level) + xchk_btree_set_corrupt(bs->sc, cur, level); } /* diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c index 7c432997edad..b045e95c2ea7 100644 --- a/fs/xfs/scrub/dir.c +++ b/fs/xfs/scrub/dir.c @@ -558,14 +558,27 @@ xchk_directory_leaf1_bestfree( /* Check all the bestfree entries. */ for (i = 0; i < bestcount; i++, bestp++) { best = be16_to_cpu(*bestp); - if (best == NULLDATAOFF) - continue; error = xfs_dir3_data_read(sc->tp, sc->ip, - i * args->geo->fsbcount, 0, &dbp); + xfs_dir2_db_to_da(args->geo, i), + XFS_DABUF_MAP_HOLE_OK, + &dbp); if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, lblk, &error)) break; - xchk_directory_check_freesp(sc, lblk, dbp, best); + + if (!dbp) { + if (best != NULLDATAOFF) { + xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, + lblk); + break; + } + continue; + } + + if (best == NULLDATAOFF) + xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk); + else + xchk_directory_check_freesp(sc, lblk, dbp, best); xfs_trans_brelse(sc->tp, dbp); if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) break; diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c index 3aa85b64de36..bb25ff1b770d 100644 --- a/fs/xfs/scrub/inode.c +++ b/fs/xfs/scrub/inode.c @@ -121,8 +121,7 @@ xchk_inode_flags( goto bad; /* rt flags require rt device */ - if ((flags & (XFS_DIFLAG_REALTIME | XFS_DIFLAG_RTINHERIT)) && - !mp->m_rtdev_targp) + if ((flags & XFS_DIFLAG_REALTIME) && !mp->m_rtdev_targp) goto bad; /* new rt bitmap flag only valid for rbmino */ diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c index beaeb6fa3119..dd672e6bbc75 100644 --- a/fs/xfs/scrub/refcount.c +++ b/fs/xfs/scrub/refcount.c @@ -170,7 +170,6 @@ xchk_refcountbt_process_rmap_fragments( */ INIT_LIST_HEAD(&worklist); rbno = NULLAGBLOCK; - nr = 1; /* Make sure the fragments actually /are/ in agbno order. */ bno = 0; @@ -184,15 +183,14 @@ xchk_refcountbt_process_rmap_fragments( * Find all the rmaps that start at or before the refc extent, * and put them on the worklist. */ + nr = 0; list_for_each_entry_safe(frag, n, &refchk->fragments, list) { - if (frag->rm.rm_startblock > refchk->bno) - goto done; + if (frag->rm.rm_startblock > refchk->bno || nr > target_nr) + break; bno = frag->rm.rm_startblock + frag->rm.rm_blockcount; if (bno < rbno) rbno = bno; list_move_tail(&frag->list, &worklist); - if (nr == target_nr) - break; nr++; } diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 55d126d4e096..4304c6416fbb 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -346,8 +346,8 @@ xfs_map_blocks( ssize_t count = i_blocksize(inode); xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset); xfs_fileoff_t end_fsb = XFS_B_TO_FSB(mp, offset + count); - xfs_fileoff_t cow_fsb = NULLFILEOFF; - int whichfork = XFS_DATA_FORK; + xfs_fileoff_t cow_fsb; + int whichfork; struct xfs_bmbt_irec imap; struct xfs_iext_cursor icur; int retries = 0; @@ -381,6 +381,8 @@ xfs_map_blocks( * landed in a hole and we skip the block. */ retry: + cow_fsb = NULLFILEOFF; + whichfork = XFS_DATA_FORK; xfs_ilock(ip, XFS_ILOCK_SHARED); ASSERT(ip->i_df.if_format != XFS_DINODE_FMT_BTREE || (ip->i_df.if_flags & XFS_IFEXTENTS)); @@ -527,13 +529,15 @@ xfs_prepare_ioend( */ static void xfs_discard_page( - struct page *page) + struct page *page, + loff_t fileoff) { struct inode *inode = page->mapping->host; struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; - loff_t offset = page_offset(page); - xfs_fileoff_t start_fsb = XFS_B_TO_FSBT(mp, offset); + unsigned int pageoff = offset_in_page(fileoff); + xfs_fileoff_t start_fsb = XFS_B_TO_FSBT(mp, fileoff); + xfs_fileoff_t pageoff_fsb = XFS_B_TO_FSBT(mp, pageoff); int error; if (XFS_FORCED_SHUTDOWN(mp)) @@ -541,14 +545,14 @@ xfs_discard_page( xfs_alert_ratelimited(mp, "page discard on page "PTR_FMT", inode 0x%llx, offset %llu.", - page, ip->i_ino, offset); + page, ip->i_ino, fileoff); error = xfs_bmap_punch_delalloc_range(ip, start_fsb, - i_blocks_per_page(inode, page)); + i_blocks_per_page(inode, page) - pageoff_fsb); if (error && !XFS_FORCED_SHUTDOWN(mp)) xfs_alert(mp, "page discard unable to remove delalloc mapping."); out_invalidate: - iomap_invalidatepage(page, 0, PAGE_SIZE); + iomap_invalidatepage(page, pageoff, PAGE_SIZE - pageoff); } static const struct iomap_writeback_ops xfs_writeback_ops = { diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 3abb8b9d6f4c..7b9ff824e82d 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -706,6 +706,23 @@ relock: return 0; } +/* + * Check that the imap we are going to return to the caller spans the entire + * range that the caller requested for the IO. + */ +static bool +imap_spans_range( + struct xfs_bmbt_irec *imap, + xfs_fileoff_t offset_fsb, + xfs_fileoff_t end_fsb) +{ + if (imap->br_startoff > offset_fsb) + return false; + if (imap->br_startoff + imap->br_blockcount < end_fsb) + return false; + return true; +} + static int xfs_direct_write_iomap_begin( struct inode *inode, @@ -766,6 +783,18 @@ xfs_direct_write_iomap_begin( if (imap_needs_alloc(inode, flags, &imap, nimaps)) goto allocate_blocks; + /* + * NOWAIT IO needs to span the entire requested IO with a single map so + * that we avoid partial IO failures due to the rest of the IO range not + * covered by this map triggering an EAGAIN condition when it is + * subsequently mapped and aborting the IO. + */ + if ((flags & IOMAP_NOWAIT) && + !imap_spans_range(&imap, offset_fsb, end_fsb)) { + error = -EAGAIN; + goto out_unlock; + } + xfs_iunlock(ip, lockmode); trace_xfs_iomap_found(ip, offset, length, XFS_DATA_FORK, &imap); return xfs_bmbt_to_iomap(ip, iomap, &imap, iomap_flags); diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 5e165456da68..1414ab79eacf 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -911,6 +911,16 @@ xfs_setattr_size( error = iomap_zero_range(inode, oldsize, newsize - oldsize, &did_zeroing, &xfs_buffered_write_iomap_ops); } else { + /* + * iomap won't detect a dirty page over an unwritten block (or a + * cow block over a hole) and subsequently skips zeroing the + * newly post-EOF portion of the page. Flush the new EOF to + * convert the block before the pagecache truncate. + */ + error = filemap_write_and_wait_range(inode->i_mapping, newsize, + newsize); + if (error) + return error; error = iomap_truncate_page(inode, newsize, &did_zeroing, &xfs_buffered_write_iomap_ops); } diff --git a/fs/xfs/xfs_iwalk.c b/fs/xfs/xfs_iwalk.c index 233dcc8784db..2a45138831e3 100644 --- a/fs/xfs/xfs_iwalk.c +++ b/fs/xfs/xfs_iwalk.c @@ -55,6 +55,9 @@ struct xfs_iwalk_ag { /* Where do we start the traversal? */ xfs_ino_t startino; + /* What was the last inode number we saw when iterating the inobt? */ + xfs_ino_t lastino; + /* Array of inobt records we cache. */ struct xfs_inobt_rec_incore *recs; @@ -301,6 +304,9 @@ xfs_iwalk_ag_start( if (XFS_IS_CORRUPT(mp, *has_more != 1)) return -EFSCORRUPTED; + iwag->lastino = XFS_AGINO_TO_INO(mp, agno, + irec->ir_startino + XFS_INODES_PER_CHUNK - 1); + /* * If the LE lookup yielded an inobt record before the cursor position, * skip it and see if there's another one after it. @@ -347,15 +353,17 @@ xfs_iwalk_run_callbacks( struct xfs_mount *mp = iwag->mp; struct xfs_trans *tp = iwag->tp; struct xfs_inobt_rec_incore *irec; - xfs_agino_t restart; + xfs_agino_t next_agino; int error; + next_agino = XFS_INO_TO_AGINO(mp, iwag->lastino) + 1; + ASSERT(iwag->nr_recs > 0); /* Delete cursor but remember the last record we cached... */ xfs_iwalk_del_inobt(tp, curpp, agi_bpp, 0); irec = &iwag->recs[iwag->nr_recs - 1]; - restart = irec->ir_startino + XFS_INODES_PER_CHUNK - 1; + ASSERT(next_agino == irec->ir_startino + XFS_INODES_PER_CHUNK); error = xfs_iwalk_ag_recs(iwag); if (error) @@ -372,7 +380,7 @@ xfs_iwalk_run_callbacks( if (error) return error; - return xfs_inobt_lookup(*curpp, restart, XFS_LOOKUP_GE, has_more); + return xfs_inobt_lookup(*curpp, next_agino, XFS_LOOKUP_GE, has_more); } /* Walk all inodes in a single AG, from @iwag->startino to the end of the AG. */ @@ -396,6 +404,7 @@ xfs_iwalk_ag( while (!error && has_more) { struct xfs_inobt_rec_incore *irec; + xfs_ino_t rec_fsino; cond_resched(); if (xfs_pwork_want_abort(&iwag->pwork)) @@ -407,6 +416,15 @@ xfs_iwalk_ag( if (error || !has_more) break; + /* Make sure that we always move forward. */ + rec_fsino = XFS_AGINO_TO_INO(mp, agno, irec->ir_startino); + if (iwag->lastino != NULLFSINO && + XFS_IS_CORRUPT(mp, iwag->lastino >= rec_fsino)) { + error = -EFSCORRUPTED; + goto out; + } + iwag->lastino = rec_fsino + XFS_INODES_PER_CHUNK - 1; + /* No allocated inodes in this chunk; skip it. */ if (iwag->skip_empty && irec->ir_freecount == irec->ir_count) { error = xfs_btree_increment(cur, 0, &has_more); @@ -535,6 +553,7 @@ xfs_iwalk( .trim_start = 1, .skip_empty = 1, .pwork = XFS_PWORK_SINGLE_THREADED, + .lastino = NULLFSINO, }; xfs_agnumber_t agno = XFS_INO_TO_AGNO(mp, startino); int error; @@ -623,6 +642,7 @@ xfs_iwalk_threaded( iwag->data = data; iwag->startino = startino; iwag->sz_recs = xfs_iwalk_prefetch(inode_records); + iwag->lastino = NULLFSINO; xfs_pwork_queue(&pctl, &iwag->pwork); startino = XFS_AGINO_TO_INO(mp, agno + 1, 0); if (flags & XFS_INOBT_WALK_SAME_AG) @@ -696,6 +716,7 @@ xfs_inobt_walk( .startino = startino, .sz_recs = xfs_inobt_walk_prefetch(inobt_records), .pwork = XFS_PWORK_SINGLE_THREADED, + .lastino = NULLFSINO, }; xfs_agnumber_t agno = XFS_INO_TO_AGNO(mp, startino); int error; diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 150ee5cb8645..7110507a2b6b 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -194,20 +194,25 @@ xfs_initialize_perag( } pag = kmem_zalloc(sizeof(*pag), KM_MAYFAIL); - if (!pag) + if (!pag) { + error = -ENOMEM; goto out_unwind_new_pags; + } pag->pag_agno = index; pag->pag_mount = mp; spin_lock_init(&pag->pag_ici_lock); INIT_RADIX_TREE(&pag->pag_ici_root, GFP_ATOMIC); - if (xfs_buf_hash_init(pag)) + + error = xfs_buf_hash_init(pag); + if (error) goto out_free_pag; init_waitqueue_head(&pag->pagb_wait); spin_lock_init(&pag->pagb_lock); pag->pagb_count = 0; pag->pagb_tree = RB_ROOT; - if (radix_tree_preload(GFP_NOFS)) + error = radix_tree_preload(GFP_NOFS); + if (error) goto out_hash_destroy; spin_lock(&mp->m_perag_lock); diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c index b101feb2aab4..f3082a957d5e 100644 --- a/fs/xfs/xfs_pnfs.c +++ b/fs/xfs/xfs_pnfs.c @@ -134,7 +134,7 @@ xfs_fs_map_blocks( goto out_unlock; error = invalidate_inode_pages2(inode->i_mapping); if (WARN_ON_ONCE(error)) - return error; + goto out_unlock; end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + length); offset_fsb = XFS_B_TO_FSBT(mp, offset); diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 16098dc42add..6fa05fb78189 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -1502,7 +1502,8 @@ xfs_reflink_unshare( &xfs_buffered_write_iomap_ops); if (error) goto out; - error = filemap_write_and_wait(inode->i_mapping); + + error = filemap_write_and_wait_range(inode->i_mapping, offset, len); if (error) goto out; diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h index 798027bb89be..640f09479bdf 100644 --- a/include/asm-generic/barrier.h +++ b/include/asm-generic/barrier.h @@ -13,6 +13,7 @@ #ifndef __ASSEMBLY__ +#include <linux/compiler.h> #include <asm/rwonce.h> #ifndef nop diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h index 35e4a53b83e6..6432a7fade91 100644 --- a/include/asm-generic/percpu.h +++ b/include/asm-generic/percpu.h @@ -114,21 +114,21 @@ do { \ #define __this_cpu_generic_read_nopreempt(pcp) \ ({ \ - typeof(pcp) __ret; \ + typeof(pcp) ___ret; \ preempt_disable_notrace(); \ - __ret = READ_ONCE(*raw_cpu_ptr(&(pcp))); \ + ___ret = READ_ONCE(*raw_cpu_ptr(&(pcp))); \ preempt_enable_notrace(); \ - __ret; \ + ___ret; \ }) #define __this_cpu_generic_read_noirq(pcp) \ ({ \ - typeof(pcp) __ret; \ - unsigned long __flags; \ - raw_local_irq_save(__flags); \ - __ret = raw_cpu_generic_read(pcp); \ - raw_local_irq_restore(__flags); \ - __ret; \ + typeof(pcp) ___ret; \ + unsigned long ___flags; \ + raw_local_irq_save(___flags); \ + ___ret = raw_cpu_generic_read(pcp); \ + raw_local_irq_restore(___flags); \ + ___ret; \ }) #define this_cpu_generic_read(pcp) \ diff --git a/include/kunit/test.h b/include/kunit/test.h index 9197da792336..df60be7e22ca 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -252,13 +252,14 @@ static inline int kunit_run_all_tests(void) } #endif /* IS_BUILTIN(CONFIG_KUNIT) */ +#ifdef MODULE /** - * kunit_test_suites() - used to register one or more &struct kunit_suite - * with KUnit. + * kunit_test_suites_for_module() - used to register one or more + * &struct kunit_suite with KUnit. * - * @suites_list...: a statically allocated list of &struct kunit_suite. + * @__suites: a statically allocated list of &struct kunit_suite. * - * Registers @suites_list with the test framework. See &struct kunit_suite for + * Registers @__suites with the test framework. See &struct kunit_suite for * more information. * * If a test suite is built-in, module_init() gets translated into @@ -267,7 +268,6 @@ static inline int kunit_run_all_tests(void) * module_{init|exit} functions for the builtin case when registering * suites via kunit_test_suites() below. */ -#ifdef MODULE #define kunit_test_suites_for_module(__suites) \ static int __init kunit_test_suites_init(void) \ { \ @@ -294,7 +294,7 @@ static inline int kunit_run_all_tests(void) * kunit_test_suites() - used to register one or more &struct kunit_suite * with KUnit. * - * @suites: a statically allocated list of &struct kunit_suite. + * @__suites: a statically allocated list of &struct kunit_suite. * * Registers @suites with the test framework. See &struct kunit_suite for * more information. @@ -308,10 +308,10 @@ static inline int kunit_run_all_tests(void) * module. * */ -#define kunit_test_suites(...) \ +#define kunit_test_suites(__suites...) \ __kunit_test_suites(__UNIQUE_ID(array), \ __UNIQUE_ID(suites), \ - __VA_ARGS__) + ##__suites) #define kunit_test_suite(suite) kunit_test_suites(&suite) @@ -1105,7 +1105,7 @@ do { \ KUNIT_ASSERTION(test, \ strcmp(__left, __right) op 0, \ kunit_binary_str_assert, \ - KUNIT_INIT_BINARY_ASSERT_STRUCT(test, \ + KUNIT_INIT_BINARY_STR_ASSERT_STRUCT(test, \ assert_type, \ #op, \ #left, \ diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index b23eeca4d677..794b2a33a2c3 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -235,6 +235,8 @@ enum hctx_type { * @flags: Zero or more BLK_MQ_F_* flags. * @driver_data: Pointer to data owned by the block driver that created this * tag set. + * @active_queues_shared_sbitmap: + * number of active request queues per tag set. * @__bitmap_tags: A shared tags sbitmap, used over all hctx's * @__breserved_tags: * A shared reserved tags sbitmap, used over all hctx's diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h index 900b9f4e0605..fc61cf4eff1c 100644 --- a/include/linux/can/skb.h +++ b/include/linux/can/skb.h @@ -61,21 +61,17 @@ static inline void can_skb_set_owner(struct sk_buff *skb, struct sock *sk) */ static inline struct sk_buff *can_create_echo_skb(struct sk_buff *skb) { - if (skb_shared(skb)) { - struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC); + struct sk_buff *nskb; - if (likely(nskb)) { - can_skb_set_owner(nskb, skb->sk); - consume_skb(skb); - return nskb; - } else { - kfree_skb(skb); - return NULL; - } + nskb = skb_clone(skb, GFP_ATOMIC); + if (unlikely(!nskb)) { + kfree_skb(skb); + return NULL; } - /* we can assume to have an unshared skb with proper owner */ - return skb; + can_skb_set_owner(nskb, skb->sk); + consume_skb(skb); + return nskb; } #endif /* !_CAN_SKB_H */ diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index 230604e7f057..98cff1b4b088 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -8,8 +8,10 @@ + __clang_patchlevel__) #if CLANG_VERSION < 100001 +#ifndef __BPF_TRACING__ # error Sorry, your version of Clang is too old - please use 10.0.1 or newer. #endif +#endif /* Compiler specific definitions for Clang compiler */ @@ -60,12 +62,6 @@ #define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 #endif -/* The following are for compatibility with GCC, from compiler-gcc.h, - * and may be redefined here because they should not be shared with other - * compilers, like ICC. - */ -#define barrier() __asm__ __volatile__("" : : : "memory") - #if __has_feature(shadow_call_stack) # define __noscs __attribute__((__no_sanitize__("shadow-call-stack"))) #endif diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index d1e3c6896b71..74c6c0486eed 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -15,25 +15,6 @@ # error Sorry, your version of GCC is too old - please use 4.9 or newer. #endif -/* Optimization barrier */ - -/* The "volatile" is due to gcc bugs */ -#define barrier() __asm__ __volatile__("": : :"memory") -/* - * This version is i.e. to prevent dead stores elimination on @ptr - * where gcc and llvm may behave differently when otherwise using - * normal barrier(): while gcc behavior gets along with a normal - * barrier(), llvm needs an explicit input variable to be assumed - * clobbered. The issue is as follows: while the inline asm might - * access any memory it wants, the compiler could have fit all of - * @ptr into memory registers instead, and since @ptr never escaped - * from that, it proved that the inline asm wasn't touching any of - * it. This version works well with both compilers, i.e. we're telling - * the compiler that the inline asm absolutely may see the contents - * of @ptr. See also: https://llvm.org/bugs/show_bug.cgi?id=15495 - */ -#define barrier_data(ptr) __asm__ __volatile__("": :"r"(ptr) :"memory") - /* * This macro obfuscates arithmetic on a variable address so that gcc * shouldn't recognize the original var, and make assumptions about it. @@ -175,5 +156,3 @@ #else #define __diag_GCC_8(s) #endif - -#define __no_fgcse __attribute__((optimize("-fno-gcse"))) diff --git a/include/linux/compiler.h b/include/linux/compiler.h index e512f5505dad..b8fe0c23cfff 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -80,11 +80,25 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, /* Optimization barrier */ #ifndef barrier -# define barrier() __memory_barrier() +/* The "volatile" is due to gcc bugs */ +# define barrier() __asm__ __volatile__("": : :"memory") #endif #ifndef barrier_data -# define barrier_data(ptr) barrier() +/* + * This version is i.e. to prevent dead stores elimination on @ptr + * where gcc and llvm may behave differently when otherwise using + * normal barrier(): while gcc behavior gets along with a normal + * barrier(), llvm needs an explicit input variable to be assumed + * clobbered. The issue is as follows: while the inline asm might + * access any memory it wants, the compiler could have fit all of + * @ptr into memory registers instead, and since @ptr never escaped + * from that, it proved that the inline asm wasn't touching any of + * it. This version works well with both compilers, i.e. we're telling + * the compiler that the inline asm absolutely may see the contents + * of @ptr. See also: https://llvm.org/bugs/show_bug.cgi?id=15495 + */ +# define barrier_data(ptr) __asm__ __volatile__("": :"r"(ptr) :"memory") #endif /* workaround for GCC PR82365 if needed */ diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 6e390d58a9f8..ac3fa37a84f9 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -247,10 +247,6 @@ struct ftrace_likely_data { #define asm_inline asm #endif -#ifndef __no_fgcse -# define __no_fgcse -#endif - /* Are two types/vars the same type (ignoring qualifiers)? */ #define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b)) diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 1eaa04f1bae6..acbad3b36322 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -110,6 +110,12 @@ struct cpufreq_policy { bool fast_switch_enabled; /* + * Set if the CPUFREQ_GOV_STRICT_TARGET flag is set for the current + * governor. + */ + bool strict_target; + + /* * Preferred average time interval between consecutive invocations of * the driver to set the frequency for this policy. To be set by the * scaling driver (0, which is the default, means no preference). @@ -570,12 +576,20 @@ struct cpufreq_governor { char *buf); int (*store_setspeed) (struct cpufreq_policy *policy, unsigned int freq); - /* For governors which change frequency dynamically by themselves */ - bool dynamic_switching; struct list_head governor_list; struct module *owner; + u8 flags; }; +/* Governor flags */ + +/* For governors which change frequency dynamically by themselves */ +#define CPUFREQ_GOV_DYNAMIC_SWITCHING BIT(0) + +/* For governors wanting the target frequency to be set exactly */ +#define CPUFREQ_GOV_STRICT_TARGET BIT(1) + + /* Pass a target to the cpufreq driver */ unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy, unsigned int target_freq); diff --git a/include/linux/filter.h b/include/linux/filter.h index 72d62cbc1578..1b62397bd124 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -558,21 +558,21 @@ struct sk_filter { DECLARE_STATIC_KEY_FALSE(bpf_stats_enabled_key); #define __BPF_PROG_RUN(prog, ctx, dfunc) ({ \ - u32 ret; \ + u32 __ret; \ cant_migrate(); \ if (static_branch_unlikely(&bpf_stats_enabled_key)) { \ - struct bpf_prog_stats *stats; \ - u64 start = sched_clock(); \ - ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func); \ - stats = this_cpu_ptr(prog->aux->stats); \ - u64_stats_update_begin(&stats->syncp); \ - stats->cnt++; \ - stats->nsecs += sched_clock() - start; \ - u64_stats_update_end(&stats->syncp); \ + struct bpf_prog_stats *__stats; \ + u64 __start = sched_clock(); \ + __ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func); \ + __stats = this_cpu_ptr(prog->aux->stats); \ + u64_stats_update_begin(&__stats->syncp); \ + __stats->cnt++; \ + __stats->nsecs += sched_clock() - __start; \ + u64_stats_update_end(&__stats->syncp); \ } else { \ - ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func); \ + __ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func); \ } \ - ret; }) + __ret; }) #define BPF_PROG_RUN(prog, ctx) \ __BPF_PROG_RUN(prog, ctx, bpf_dispatcher_nop_func) diff --git a/include/linux/fs.h b/include/linux/fs.h index 21cc971fd960..8667d0cdc71e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1580,8 +1580,24 @@ extern struct timespec64 current_time(struct inode *inode); * Snapshotting support. */ -void __sb_end_write(struct super_block *sb, int level); -int __sb_start_write(struct super_block *sb, int level, bool wait); +/* + * These are internal functions, please use sb_start_{write,pagefault,intwrite} + * instead. + */ +static inline void __sb_end_write(struct super_block *sb, int level) +{ + percpu_up_read(sb->s_writers.rw_sem + level-1); +} + +static inline void __sb_start_write(struct super_block *sb, int level) +{ + percpu_down_read(sb->s_writers.rw_sem + level - 1); +} + +static inline bool __sb_start_write_trylock(struct super_block *sb, int level) +{ + return percpu_down_read_trylock(sb->s_writers.rw_sem + level - 1); +} #define __sb_writers_acquired(sb, lev) \ percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_) @@ -1645,12 +1661,12 @@ static inline void sb_end_intwrite(struct super_block *sb) */ static inline void sb_start_write(struct super_block *sb) { - __sb_start_write(sb, SB_FREEZE_WRITE, true); + __sb_start_write(sb, SB_FREEZE_WRITE); } -static inline int sb_start_write_trylock(struct super_block *sb) +static inline bool sb_start_write_trylock(struct super_block *sb) { - return __sb_start_write(sb, SB_FREEZE_WRITE, false); + return __sb_start_write_trylock(sb, SB_FREEZE_WRITE); } /** @@ -1674,7 +1690,7 @@ static inline int sb_start_write_trylock(struct super_block *sb) */ static inline void sb_start_pagefault(struct super_block *sb) { - __sb_start_write(sb, SB_FREEZE_PAGEFAULT, true); + __sb_start_write(sb, SB_FREEZE_PAGEFAULT); } /* @@ -1692,12 +1708,12 @@ static inline void sb_start_pagefault(struct super_block *sb) */ static inline void sb_start_intwrite(struct super_block *sb) { - __sb_start_write(sb, SB_FREEZE_FS, true); + __sb_start_write(sb, SB_FREEZE_FS); } -static inline int sb_start_intwrite_trylock(struct super_block *sb) +static inline bool sb_start_intwrite_trylock(struct super_block *sb) { - return __sb_start_write(sb, SB_FREEZE_FS, false); + return __sb_start_write_trylock(sb, SB_FREEZE_FS); } @@ -2756,14 +2772,14 @@ static inline void file_start_write(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return; - __sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, true); + sb_start_write(file_inode(file)->i_sb); } static inline bool file_start_write_trylock(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return true; - return __sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, false); + return sb_start_write_trylock(file_inode(file)->i_sb); } static inline void file_end_write(struct file *file) diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 38f23d757013..03da3f603d30 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -315,7 +315,7 @@ static inline int get_disk_ro(struct gendisk *disk) extern void disk_block_events(struct gendisk *disk); extern void disk_unblock_events(struct gendisk *disk); extern void disk_flush_events(struct gendisk *disk, unsigned int mask); -void set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size, +bool set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size, bool update_bdev); /* drivers/char/random.c */ diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index fbf5b3e7707e..d956987ed032 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -798,7 +798,6 @@ extern int iommu_calculate_agaw(struct intel_iommu *iommu); extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu); extern int dmar_disabled; extern int intel_iommu_enabled; -extern int intel_iommu_tboot_noforce; extern int intel_iommu_gfx_mapped; #else static inline int iommu_calculate_agaw(struct intel_iommu *iommu) diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 868364cea3b7..35b2d845704d 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -30,7 +30,8 @@ struct io_uring_task { struct percpu_counter inflight; struct io_identity __identity; struct io_identity *identity; - bool in_idle; + atomic_t in_idle; + bool sqpoll; }; #if defined(CONFIG_IO_URING) diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 172b3397a1a3..5bd3cac4df9c 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -221,7 +221,7 @@ struct iomap_writeback_ops { * Optional, allows the file system to discard state on a page where * we failed to submit any I/O. */ - void (*discard_page)(struct page *page); + void (*discard_page)(struct page *page, loff_t fileoff); }; struct iomap_writepage_ctx { diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 1d5566af48ac..578ff196b3ce 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -68,6 +68,7 @@ extern void *jbd2_alloc(size_t size, gfp_t flags); extern void jbd2_free(void *ptr, size_t size); #define JBD2_MIN_JOURNAL_BLOCKS 1024 +#define JBD2_MIN_FC_BLOCKS 256 #ifdef __KERNEL__ @@ -400,7 +401,7 @@ static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh) #define JI_WAIT_DATA (1 << __JI_WAIT_DATA) /** - * struct jbd_inode - The jbd_inode type is the structure linking inodes in + * struct jbd2_inode - The jbd_inode type is the structure linking inodes in * ordered mode present in a transaction so that we can sync them during commit. */ struct jbd2_inode { @@ -944,8 +945,9 @@ struct journal_s /** * @j_fc_off: * - * Number of fast commit blocks currently allocated. - * [j_state_lock]. + * Number of fast commit blocks currently allocated. Accessed only + * during fast commit. Currently only process can do fast commit, so + * this field is not protected by any lock. */ unsigned long j_fc_off; @@ -988,9 +990,9 @@ struct journal_s struct block_device *j_fs_dev; /** - * @j_maxlen: Total maximum capacity of the journal region on disk. + * @j_total_len: Total maximum capacity of the journal region on disk. */ - unsigned int j_maxlen; + unsigned int j_total_len; /** * @j_reserved_credits: @@ -1108,8 +1110,9 @@ struct journal_s struct buffer_head **j_wbuf; /** - * @j_fc_wbuf: Array of fast commit bhs for - * jbd2_journal_commit_transaction. + * @j_fc_wbuf: Array of fast commit bhs for fast commit. Accessed only + * during a fast commit. Currently only process can do fast commit, so + * this field is not protected by any lock. */ struct buffer_head **j_fc_wbuf; @@ -1614,16 +1617,20 @@ extern void __jbd2_journal_drop_transaction(journal_t *, transaction_t *); extern int jbd2_cleanup_journal_tail(journal_t *); /* Fast commit related APIs */ -int jbd2_fc_init(journal_t *journal, int num_fc_blks); int jbd2_fc_begin_commit(journal_t *journal, tid_t tid); int jbd2_fc_end_commit(journal_t *journal); -int jbd2_fc_end_commit_fallback(journal_t *journal, tid_t tid); +int jbd2_fc_end_commit_fallback(journal_t *journal); int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out); int jbd2_submit_inode_data(struct jbd2_inode *jinode); int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode); int jbd2_fc_wait_bufs(journal_t *journal, int num_blks); int jbd2_fc_release_bufs(journal_t *journal); +static inline int jbd2_journal_get_max_txn_bufs(journal_t *journal) +{ + return (journal->j_total_len - journal->j_fc_wbufsize) / 4; +} + /* * is_journal_abort * diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index e391e3c56de5..a80c59af2c60 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -900,12 +900,19 @@ static inline void count_memcg_event_mm(struct mm_struct *mm, static inline void memcg_memory_event(struct mem_cgroup *memcg, enum memcg_memory_event event) { + bool swap_event = event == MEMCG_SWAP_HIGH || event == MEMCG_SWAP_MAX || + event == MEMCG_SWAP_FAIL; + atomic_long_inc(&memcg->memory_events_local[event]); - cgroup_file_notify(&memcg->events_local_file); + if (!swap_event) + cgroup_file_notify(&memcg->events_local_file); do { atomic_long_inc(&memcg->memory_events[event]); - cgroup_file_notify(&memcg->events_file); + if (swap_event) + cgroup_file_notify(&memcg->swap_events_file); + else + cgroup_file_notify(&memcg->events_file); if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) break; diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index d65c6fdc5cfc..551093b74596 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -281,20 +281,6 @@ static inline bool movable_node_is_enabled(void) } #endif /* ! CONFIG_MEMORY_HOTPLUG */ -#ifdef CONFIG_NUMA -extern int memory_add_physaddr_to_nid(u64 start); -extern int phys_to_target_node(u64 start); -#else -static inline int memory_add_physaddr_to_nid(u64 start) -{ - return 0; -} -static inline int phys_to_target_node(u64 start) -{ - return 0; -} -#endif - #if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT) /* * pgdat resizing functions diff --git a/include/linux/mm.h b/include/linux/mm.h index ef360fe70aaf..db6ae4d3fb4e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2759,6 +2759,15 @@ static inline vm_fault_t vmf_insert_page(struct vm_area_struct *vma, return VM_FAULT_NOPAGE; } +#ifndef io_remap_pfn_range +static inline int io_remap_pfn_range(struct vm_area_struct *vma, + unsigned long addr, unsigned long pfn, + unsigned long size, pgprot_t prot) +{ + return remap_pfn_range(vma, addr, pfn, size, pgprot_decrypted(prot)); +} +#endif + static inline vm_fault_t vmf_error(int err) { if (err == -ENOMEM) diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 89016d08f6a2..f6267e2883f2 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -24,6 +24,12 @@ struct nfnl_callback { const u_int16_t attr_count; /* number of nlattr's */ }; +enum nfnl_abort_action { + NFNL_ABORT_NONE = 0, + NFNL_ABORT_AUTOLOAD, + NFNL_ABORT_VALIDATE, +}; + struct nfnetlink_subsystem { const char *name; __u8 subsys_id; /* nfnetlink subsystem ID */ @@ -31,7 +37,8 @@ struct nfnetlink_subsystem { const struct nfnl_callback *cb; /* callback for individual types */ struct module *owner; int (*commit)(struct net *net, struct sk_buff *skb); - int (*abort)(struct net *net, struct sk_buff *skb, bool autoload); + int (*abort)(struct net *net, struct sk_buff *skb, + enum nfnl_abort_action action); void (*cleanup)(struct net *net); bool (*valid_genid)(struct net *net, u32 genid); }; diff --git a/include/linux/netfilter_ipv4.h b/include/linux/netfilter_ipv4.h index 082e2c41b7ff..5b70ca868bb1 100644 --- a/include/linux/netfilter_ipv4.h +++ b/include/linux/netfilter_ipv4.h @@ -16,7 +16,7 @@ struct ip_rt_info { u_int32_t mark; }; -int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned addr_type); +int ip_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned addr_type); struct nf_queue_entry; diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index 9b67394471e1..48314ade1506 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -42,7 +42,7 @@ struct nf_ipv6_ops { #if IS_MODULE(CONFIG_IPV6) int (*chk_addr)(struct net *net, const struct in6_addr *addr, const struct net_device *dev, int strict); - int (*route_me_harder)(struct net *net, struct sk_buff *skb); + int (*route_me_harder)(struct net *net, struct sock *sk, struct sk_buff *skb); int (*dev_get_saddr)(struct net *net, const struct net_device *dev, const struct in6_addr *daddr, unsigned int srcprefs, struct in6_addr *saddr); @@ -143,9 +143,9 @@ static inline int nf_br_ip6_fragment(struct net *net, struct sock *sk, #endif } -int ip6_route_me_harder(struct net *net, struct sk_buff *skb); +int ip6_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb); -static inline int nf_ip6_route_me_harder(struct net *net, struct sk_buff *skb) +static inline int nf_ip6_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb) { #if IS_MODULE(CONFIG_IPV6) const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops(); @@ -153,9 +153,9 @@ static inline int nf_ip6_route_me_harder(struct net *net, struct sk_buff *skb) if (!v6_ops) return -EHOSTUNREACH; - return v6_ops->route_me_harder(net, skb); + return v6_ops->route_me_harder(net, sk, skb); #elif IS_BUILTIN(CONFIG_IPV6) - return ip6_route_me_harder(net, skb); + return ip6_route_me_harder(net, sk, skb); #else return -EHOSTUNREACH; #endif diff --git a/include/linux/numa.h b/include/linux/numa.h index 8cb33ccfb671..cb44cfe2b725 100644 --- a/include/linux/numa.h +++ b/include/linux/numa.h @@ -21,13 +21,41 @@ #endif #ifdef CONFIG_NUMA +#include <linux/printk.h> +#include <asm/sparsemem.h> + /* Generic implementation available */ int numa_map_to_online_node(int node); -#else + +#ifndef memory_add_physaddr_to_nid +static inline int memory_add_physaddr_to_nid(u64 start) +{ + pr_info_once("Unknown online node for memory at 0x%llx, assuming node 0\n", + start); + return 0; +} +#endif +#ifndef phys_to_target_node +static inline int phys_to_target_node(u64 start) +{ + pr_info_once("Unknown target node for memory at 0x%llx, assuming node 0\n", + start); + return 0; +} +#endif +#else /* !CONFIG_NUMA */ static inline int numa_map_to_online_node(int node) { return NUMA_NO_NODE; } +static inline int memory_add_physaddr_to_nid(u64 start) +{ + return 0; +} +static inline int phys_to_target_node(u64 start) +{ + return 0; +} #endif #endif /* _LINUX_NUMA_H */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index c77b7c31b2e4..d5570deff400 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -344,9 +344,9 @@ static inline struct page *find_get_page_flags(struct address_space *mapping, /** * find_lock_page - locate, pin and lock a pagecache page * @mapping: the address_space to search - * @offset: the page index + * @index: the page index * - * Looks up the page cache entry at @mapping & @offset. If there is a + * Looks up the page cache entry at @mapping & @index. If there is a * page cache page, it is returned locked and with an increased * refcount. * @@ -363,9 +363,9 @@ static inline struct page *find_lock_page(struct address_space *mapping, /** * find_lock_head - Locate, pin and lock a pagecache page. * @mapping: The address_space to search. - * @offset: The page index. + * @index: The page index. * - * Looks up the page cache entry at @mapping & @offset. If there is a + * Looks up the page cache entry at @mapping & @index. If there is a * page cache page, its head page is returned locked and with an increased * refcount. * @@ -906,6 +906,8 @@ static inline unsigned int __readahead_batch(struct readahead_control *rac, xas_set(&xas, rac->_index); rcu_read_lock(); xas_for_each(&xas, page, rac->_index + rac->_nr_pages - 1) { + if (xas_retry(&xas, page)) + continue; VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(PageTail(page), page); array[i++] = page; diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 0c19d279b97f..96450f6fb1de 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1022,13 +1022,7 @@ struct perf_sample_data { struct perf_callchain_entry *callchain; u64 aux_size; - /* - * regs_user may point to task_pt_regs or to regs_user_copy, depending - * on arch details. - */ struct perf_regs regs_user; - struct pt_regs regs_user_copy; - struct perf_regs regs_intr; u64 stack_user_size; @@ -1400,11 +1394,14 @@ perf_event_addr_filters(struct perf_event *event) extern void perf_event_addr_filters_sync(struct perf_event *event); extern int perf_output_begin(struct perf_output_handle *handle, + struct perf_sample_data *data, struct perf_event *event, unsigned int size); extern int perf_output_begin_forward(struct perf_output_handle *handle, - struct perf_event *event, - unsigned int size); + struct perf_sample_data *data, + struct perf_event *event, + unsigned int size); extern int perf_output_begin_backward(struct perf_output_handle *handle, + struct perf_sample_data *data, struct perf_event *event, unsigned int size); diff --git a/include/linux/perf_regs.h b/include/linux/perf_regs.h index 2d12e97d5e7b..f632c5725f16 100644 --- a/include/linux/perf_regs.h +++ b/include/linux/perf_regs.h @@ -20,8 +20,7 @@ u64 perf_reg_value(struct pt_regs *regs, int idx); int perf_reg_validate(u64 mask); u64 perf_reg_abi(struct task_struct *task); void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy); + struct pt_regs *regs); #else #define PERF_REG_EXTENDED_MASK 0 @@ -42,8 +41,7 @@ static inline u64 perf_reg_abi(struct task_struct *task) } static inline void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { regs_user->regs = task_pt_regs(current); regs_user->abi = perf_reg_abi(current); diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 38c33eabea89..71125a4676c4 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1427,10 +1427,6 @@ typedef unsigned int pgtbl_mod_mask; #endif /* !__ASSEMBLY__ */ -#ifndef io_remap_pfn_range -#define io_remap_pfn_range remap_pfn_range -#endif - #ifndef has_transparent_hugepage #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define has_transparent_hugepage() 1 diff --git a/include/linux/phy.h b/include/linux/phy.h index eb3cb1a98b45..56563e5e0dc7 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -147,16 +147,8 @@ typedef enum { PHY_INTERFACE_MODE_MAX, } phy_interface_t; -/** +/* * phy_supported_speeds - return all speeds currently supported by a PHY device - * @phy: The PHY device to return supported speeds of. - * @speeds: buffer to store supported speeds in. - * @size: size of speeds buffer. - * - * Description: Returns the number of supported speeds, and fills - * the speeds buffer with the supported speeds. If speeds buffer is - * too small to contain all currently supported speeds, will return as - * many speeds as can fit. */ unsigned int phy_supported_speeds(struct phy_device *phy, unsigned int *speeds, @@ -1022,14 +1014,9 @@ static inline int __phy_modify_changed(struct phy_device *phydev, u32 regnum, regnum, mask, set); } -/** +/* * phy_read_mmd - Convenience function for reading a register * from an MMD on a given PHY. - * @phydev: The phy_device struct - * @devad: The MMD to read from - * @regnum: The register on the MMD to read - * - * Same rules as for phy_read(); */ int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum); @@ -1064,38 +1051,21 @@ int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum); __ret; \ }) -/** +/* * __phy_read_mmd - Convenience function for reading a register * from an MMD on a given PHY. - * @phydev: The phy_device struct - * @devad: The MMD to read from - * @regnum: The register on the MMD to read - * - * Same rules as for __phy_read(); */ int __phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum); -/** +/* * phy_write_mmd - Convenience function for writing a register * on an MMD on a given PHY. - * @phydev: The phy_device struct - * @devad: The MMD to write to - * @regnum: The register on the MMD to read - * @val: value to write to @regnum - * - * Same rules as for phy_write(); */ int phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val); -/** +/* * __phy_write_mmd - Convenience function for writing a register * on an MMD on a given PHY. - * @phydev: The phy_device struct - * @devad: The MMD to write to - * @regnum: The register on the MMD to read - * @val: value to write to @regnum - * - * Same rules as for __phy_write(); */ int __phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val); diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 18b02dcc168e..b492ae00cc90 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -54,11 +54,10 @@ extern u64 pm_runtime_autosuspend_expiration(struct device *dev); extern void pm_runtime_update_max_time_suspended(struct device *dev, s64 delta_ns); extern void pm_runtime_set_memalloc_noio(struct device *dev, bool enable); -extern void pm_runtime_clean_up_links(struct device *dev); extern void pm_runtime_get_suppliers(struct device *dev); extern void pm_runtime_put_suppliers(struct device *dev); extern void pm_runtime_new_link(struct device *dev); -extern void pm_runtime_drop_link(struct device *dev); +extern void pm_runtime_drop_link(struct device_link *link); /** * pm_runtime_get_if_in_use - Conditionally bump up runtime PM usage counter. @@ -276,11 +275,10 @@ static inline u64 pm_runtime_autosuspend_expiration( struct device *dev) { return 0; } static inline void pm_runtime_set_memalloc_noio(struct device *dev, bool enable){} -static inline void pm_runtime_clean_up_links(struct device *dev) {} static inline void pm_runtime_get_suppliers(struct device *dev) {} static inline void pm_runtime_put_suppliers(struct device *dev) {} static inline void pm_runtime_new_link(struct device *dev) {} -static inline void pm_runtime_drop_link(struct device *dev) {} +static inline void pm_runtime_drop_link(struct device_link *link) {} #endif /* !CONFIG_PM */ @@ -389,6 +387,27 @@ static inline int pm_runtime_get_sync(struct device *dev) } /** + * pm_runtime_resume_and_get - Bump up usage counter of a device and resume it. + * @dev: Target device. + * + * Resume @dev synchronously and if that is successful, increment its runtime + * PM usage counter. Return 0 if the runtime PM usage counter of @dev has been + * incremented or a negative error code otherwise. + */ +static inline int pm_runtime_resume_and_get(struct device *dev) +{ + int ret; + + ret = __pm_runtime_resume(dev, RPM_GET_PUT); + if (ret < 0) { + pm_runtime_put_noidle(dev); + return ret; + } + + return 0; +} + +/** * pm_runtime_put - Drop device usage counter and queue up "idle check" if 0. * @dev: Target device. * diff --git a/include/linux/refcount.h b/include/linux/refcount.h index 7fabb1af18e0..497990c69b0b 100644 --- a/include/linux/refcount.h +++ b/include/linux/refcount.h @@ -147,24 +147,6 @@ static inline unsigned int refcount_read(const refcount_t *r) return atomic_read(&r->refs); } -/** - * refcount_add_not_zero - add a value to a refcount unless it is 0 - * @i: the value to add to the refcount - * @r: the refcount - * - * Will saturate at REFCOUNT_SATURATED and WARN. - * - * Provides no memory ordering, it is assumed the caller has guaranteed the - * object memory to be stable (RCU, etc.). It does provide a control dependency - * and thereby orders future stores. See the comment on top. - * - * Use of this function is not recommended for the normal reference counting - * use case in which references are taken and released one at a time. In these - * cases, refcount_inc(), or one of its variants, should instead be used to - * increment a reference count. - * - * Return: false if the passed refcount is 0, true otherwise - */ static inline __must_check bool __refcount_add_not_zero(int i, refcount_t *r, int *oldp) { int old = refcount_read(r); @@ -183,17 +165,12 @@ static inline __must_check bool __refcount_add_not_zero(int i, refcount_t *r, in return old; } -static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r) -{ - return __refcount_add_not_zero(i, r, NULL); -} - /** - * refcount_add - add a value to a refcount + * refcount_add_not_zero - add a value to a refcount unless it is 0 * @i: the value to add to the refcount * @r: the refcount * - * Similar to atomic_add(), but will saturate at REFCOUNT_SATURATED and WARN. + * Will saturate at REFCOUNT_SATURATED and WARN. * * Provides no memory ordering, it is assumed the caller has guaranteed the * object memory to be stable (RCU, etc.). It does provide a control dependency @@ -203,7 +180,14 @@ static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r) * use case in which references are taken and released one at a time. In these * cases, refcount_inc(), or one of its variants, should instead be used to * increment a reference count. + * + * Return: false if the passed refcount is 0, true otherwise */ +static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r) +{ + return __refcount_add_not_zero(i, r, NULL); +} + static inline void __refcount_add(int i, refcount_t *r, int *oldp) { int old = atomic_fetch_add_relaxed(i, &r->refs); @@ -217,11 +201,32 @@ static inline void __refcount_add(int i, refcount_t *r, int *oldp) refcount_warn_saturate(r, REFCOUNT_ADD_OVF); } +/** + * refcount_add - add a value to a refcount + * @i: the value to add to the refcount + * @r: the refcount + * + * Similar to atomic_add(), but will saturate at REFCOUNT_SATURATED and WARN. + * + * Provides no memory ordering, it is assumed the caller has guaranteed the + * object memory to be stable (RCU, etc.). It does provide a control dependency + * and thereby orders future stores. See the comment on top. + * + * Use of this function is not recommended for the normal reference counting + * use case in which references are taken and released one at a time. In these + * cases, refcount_inc(), or one of its variants, should instead be used to + * increment a reference count. + */ static inline void refcount_add(int i, refcount_t *r) { __refcount_add(i, r, NULL); } +static inline __must_check bool __refcount_inc_not_zero(refcount_t *r, int *oldp) +{ + return __refcount_add_not_zero(1, r, oldp); +} + /** * refcount_inc_not_zero - increment a refcount unless it is 0 * @r: the refcount to increment @@ -235,14 +240,14 @@ static inline void refcount_add(int i, refcount_t *r) * * Return: true if the increment was successful, false otherwise */ -static inline __must_check bool __refcount_inc_not_zero(refcount_t *r, int *oldp) +static inline __must_check bool refcount_inc_not_zero(refcount_t *r) { - return __refcount_add_not_zero(1, r, oldp); + return __refcount_inc_not_zero(r, NULL); } -static inline __must_check bool refcount_inc_not_zero(refcount_t *r) +static inline void __refcount_inc(refcount_t *r, int *oldp) { - return __refcount_inc_not_zero(r, NULL); + __refcount_add(1, r, oldp); } /** @@ -257,14 +262,27 @@ static inline __must_check bool refcount_inc_not_zero(refcount_t *r) * Will WARN if the refcount is 0, as this represents a possible use-after-free * condition. */ -static inline void __refcount_inc(refcount_t *r, int *oldp) +static inline void refcount_inc(refcount_t *r) { - __refcount_add(1, r, oldp); + __refcount_inc(r, NULL); } -static inline void refcount_inc(refcount_t *r) +static inline __must_check bool __refcount_sub_and_test(int i, refcount_t *r, int *oldp) { - __refcount_inc(r, NULL); + int old = atomic_fetch_sub_release(i, &r->refs); + + if (oldp) + *oldp = old; + + if (old == i) { + smp_acquire__after_ctrl_dep(); + return true; + } + + if (unlikely(old < 0 || old - i < 0)) + refcount_warn_saturate(r, REFCOUNT_SUB_UAF); + + return false; } /** @@ -287,27 +305,14 @@ static inline void refcount_inc(refcount_t *r) * * Return: true if the resulting refcount is 0, false otherwise */ -static inline __must_check bool __refcount_sub_and_test(int i, refcount_t *r, int *oldp) +static inline __must_check bool refcount_sub_and_test(int i, refcount_t *r) { - int old = atomic_fetch_sub_release(i, &r->refs); - - if (oldp) - *oldp = old; - - if (old == i) { - smp_acquire__after_ctrl_dep(); - return true; - } - - if (unlikely(old < 0 || old - i < 0)) - refcount_warn_saturate(r, REFCOUNT_SUB_UAF); - - return false; + return __refcount_sub_and_test(i, r, NULL); } -static inline __must_check bool refcount_sub_and_test(int i, refcount_t *r) +static inline __must_check bool __refcount_dec_and_test(refcount_t *r, int *oldp) { - return __refcount_sub_and_test(i, r, NULL); + return __refcount_sub_and_test(1, r, oldp); } /** @@ -323,26 +328,11 @@ static inline __must_check bool refcount_sub_and_test(int i, refcount_t *r) * * Return: true if the resulting refcount is 0, false otherwise */ -static inline __must_check bool __refcount_dec_and_test(refcount_t *r, int *oldp) -{ - return __refcount_sub_and_test(1, r, oldp); -} - static inline __must_check bool refcount_dec_and_test(refcount_t *r) { return __refcount_dec_and_test(r, NULL); } -/** - * refcount_dec - decrement a refcount - * @r: the refcount - * - * Similar to atomic_dec(), it will WARN on underflow and fail to decrement - * when saturated at REFCOUNT_SATURATED. - * - * Provides release memory ordering, such that prior loads and stores are done - * before. - */ static inline void __refcount_dec(refcount_t *r, int *oldp) { int old = atomic_fetch_sub_release(1, &r->refs); @@ -354,6 +344,16 @@ static inline void __refcount_dec(refcount_t *r, int *oldp) refcount_warn_saturate(r, REFCOUNT_DEC_LEAK); } +/** + * refcount_dec - decrement a refcount + * @r: the refcount + * + * Similar to atomic_dec(), it will WARN on underflow and fail to decrement + * when saturated at REFCOUNT_SATURATED. + * + * Provides release memory ordering, such that prior loads and stores are done + * before. + */ static inline void refcount_dec(refcount_t *r) { __refcount_dec(r, NULL); diff --git a/include/linux/sched.h b/include/linux/sched.h index 063cd120b459..76cd21fa5501 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -552,7 +552,6 @@ struct sched_dl_entity { * overruns. */ unsigned int dl_throttled : 1; - unsigned int dl_boosted : 1; unsigned int dl_yielded : 1; unsigned int dl_non_contending : 1; unsigned int dl_overrun : 1; @@ -571,6 +570,15 @@ struct sched_dl_entity { * time. */ struct hrtimer inactive_timer; + +#ifdef CONFIG_RT_MUTEXES + /* + * Priority Inheritance. When a DEADLINE scheduling entity is boosted + * pi_se points to the donor, otherwise points to the dl_se it belongs + * to (the original one/itself). + */ + struct sched_dl_entity *pi_se; +#endif }; #ifdef CONFIG_UCLAMP_TASK @@ -770,7 +778,6 @@ struct task_struct { unsigned sched_reset_on_fork:1; unsigned sched_contributes_to_load:1; unsigned sched_migrated:1; - unsigned sched_remote_wakeup:1; #ifdef CONFIG_PSI unsigned sched_psi_wake_requeue:1; #endif @@ -780,6 +787,21 @@ struct task_struct { /* Unserialized, strictly 'current' */ + /* + * This field must not be in the scheduler word above due to wakelist + * queueing no longer being serialized by p->on_cpu. However: + * + * p->XXX = X; ttwu() + * schedule() if (p->on_rq && ..) // false + * smp_mb__after_spinlock(); if (smp_load_acquire(&p->on_cpu) && //true + * deactivate_task() ttwu_queue_wakelist()) + * p->on_rq = 0; p->sched_remote_wakeup = Y; + * + * guarantees all stores of 'current' are visible before + * ->sched_remote_wakeup gets used, so it can be in this word. + */ + unsigned sched_remote_wakeup:1; + /* Bit to tell LSMs we're in execve(): */ unsigned in_execve:1; unsigned in_iowait:1; diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 813614d4b71f..b83b3ae3c877 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -107,6 +107,7 @@ void seq_pad(struct seq_file *m, char c); char *mangle_path(char *s, const char *p, const char *esc); int seq_open(struct file *, const struct seq_operations *); ssize_t seq_read(struct file *, char __user *, size_t, loff_t *); +ssize_t seq_read_iter(struct kiocb *iocb, struct iov_iter *iter); loff_t seq_lseek(struct file *, loff_t, int); int seq_release(struct inode *, struct file *); int seq_write(struct seq_file *seq, const void *data, size_t len); diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 99380c0825db..b390fdac1587 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -734,6 +734,25 @@ static inline struct spi_controller *spi_alloc_slave(struct device *host, return __spi_alloc_controller(host, size, true); } +struct spi_controller *__devm_spi_alloc_controller(struct device *dev, + unsigned int size, + bool slave); + +static inline struct spi_controller *devm_spi_alloc_master(struct device *dev, + unsigned int size) +{ + return __devm_spi_alloc_controller(dev, size, false); +} + +static inline struct spi_controller *devm_spi_alloc_slave(struct device *dev, + unsigned int size) +{ + if (!IS_ENABLED(CONFIG_SPI_SLAVE)) + return NULL; + + return __devm_spi_alloc_controller(dev, size, true); +} + extern int spi_register_controller(struct spi_controller *ctlr); extern int devm_spi_register_controller(struct device *dev, struct spi_controller *ctlr); diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 513913ff7486..fbdc65782195 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -5,6 +5,7 @@ #include <linux/dma-direction.h> #include <linux/init.h> #include <linux/types.h> +#include <linux/limits.h> struct device; struct page; @@ -45,13 +46,9 @@ enum dma_sync_target { SYNC_FOR_DEVICE = 1, }; -extern phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, - dma_addr_t tbl_dma_addr, - phys_addr_t phys, - size_t mapping_size, - size_t alloc_size, - enum dma_data_direction dir, - unsigned long attrs); +phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys, + size_t mapping_size, size_t alloc_size, + enum dma_data_direction dir, unsigned long attrs); extern void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 661edfc8722e..d5ab8d99739f 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1444,7 +1444,7 @@ int cfg80211_check_station_change(struct wiphy *wiphy, enum cfg80211_station_type statype); /** - * enum station_info_rate_flags - bitrate info flags + * enum rate_info_flags - bitrate info flags * * Used by the driver to indicate the specific rate transmission * type for 802.11n transmissions. @@ -1517,7 +1517,7 @@ struct rate_info { }; /** - * enum station_info_rate_flags - bitrate info flags + * enum bss_param_flags - bitrate info flags * * Used by the driver to indicate the specific rate transmission * type for 802.11n transmissions. @@ -6467,7 +6467,8 @@ void cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid, struct ieee80211_channel *channel, gfp_t gfp); /** - * cfg80211_notify_new_candidate - notify cfg80211 of a new mesh peer candidate + * cfg80211_notify_new_peer_candidate - notify cfg80211 of a new mesh peer + * candidate * * @dev: network device * @macaddr: the MAC address of the new candidate @@ -7606,7 +7607,7 @@ u32 cfg80211_calculate_bitrate(struct rate_info *rate); void cfg80211_unregister_wdev(struct wireless_dev *wdev); /** - * struct cfg80211_ft_event - FT Information Elements + * struct cfg80211_ft_event_params - FT Information Elements * @ies: FT IEs * @ies_len: length of the FT IE in bytes * @target_ap: target AP's MAC address diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 02ccd32542d0..61620677b034 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -478,9 +478,11 @@ static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info, const void *from, int len, __be16 flags) { - memcpy(ip_tunnel_info_opts(info), from, len); info->options_len = len; - info->key.tun_flags |= flags; + if (len > 0) { + memcpy(ip_tunnel_info_opts(info), from, len); + info->key.tun_flags |= flags; + } } static inline struct ip_tunnel_info *lwt_tun_info(struct lwtunnel_state *lwtstate) @@ -526,7 +528,6 @@ static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info, __be16 flags) { info->options_len = 0; - info->key.tun_flags |= flags; } #endif /* CONFIG_INET */ diff --git a/include/net/ipv6_frag.h b/include/net/ipv6_frag.h index a21e8b1381a1..851029ecff13 100644 --- a/include/net/ipv6_frag.h +++ b/include/net/ipv6_frag.h @@ -108,5 +108,35 @@ out_rcu_unlock: rcu_read_unlock(); inet_frag_put(&fq->q); } + +/* Check if the upper layer header is truncated in the first fragment. */ +static inline bool +ipv6frag_thdr_truncated(struct sk_buff *skb, int start, u8 *nexthdrp) +{ + u8 nexthdr = *nexthdrp; + __be16 frag_off; + int offset; + + offset = ipv6_skip_exthdr(skb, start, &nexthdr, &frag_off); + if (offset < 0 || (frag_off & htons(IP6_OFFSET))) + return false; + switch (nexthdr) { + case NEXTHDR_TCP: + offset += sizeof(struct tcphdr); + break; + case NEXTHDR_UDP: + offset += sizeof(struct udphdr); + break; + case NEXTHDR_ICMP: + offset += sizeof(struct icmp6hdr); + break; + default: + offset += 1; + } + if (offset > skb->len) + return true; + return false; +} + #endif #endif diff --git a/include/net/mac80211.h b/include/net/mac80211.h index e8e295dae744..dcdba96814a2 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -3311,7 +3311,7 @@ enum ieee80211_roc_type { }; /** - * enum ieee80211_reconfig_complete_type - reconfig type + * enum ieee80211_reconfig_type - reconfig type * * This enum is used by the reconfig_complete() callback to indicate what * reconfiguration type was completed. @@ -6334,7 +6334,8 @@ bool ieee80211_tx_prepare_skb(struct ieee80211_hw *hw, int band, struct ieee80211_sta **sta); /** - * Sanity-check and parse the radiotap header of injected frames + * ieee80211_parse_tx_radiotap - Sanity-check and parse the radiotap header + * of injected frames * @skb: packet injected by userspace * @dev: the &struct device of this 802.11 device */ @@ -6389,7 +6390,7 @@ int ieee80211_parse_p2p_noa(const struct ieee80211_p2p_noa_attr *attr, void ieee80211_update_p2p_noa(struct ieee80211_noa_data *data, u32 tsf); /** - * ieee80211_tdls_oper - request userspace to perform a TDLS operation + * ieee80211_tdls_oper_request - request userspace to perform a TDLS operation * @vif: virtual interface * @peer: the peer's destination address * @oper: the requested TDLS operation diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 81ee17594c32..22ced1381ede 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -204,6 +204,7 @@ struct neigh_table { int (*pconstructor)(struct pneigh_entry *); void (*pdestructor)(struct pneigh_entry *); void (*proxy_redo)(struct sk_buff *skb); + int (*is_multicast)(const void *pkey); bool (*allow_add)(const struct net_device *dev, struct netlink_ext_ack *extack); char *id; diff --git a/include/net/tls.h b/include/net/tls.h index baf1e99d8193..cf1473099453 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -300,7 +300,8 @@ enum tls_offload_sync_type { #define TLS_DEVICE_RESYNC_ASYNC_LOGMAX 13 struct tls_offload_resync_async { atomic64_t req; - u32 loglen; + u16 loglen; + u16 rcd_delta; u32 log[TLS_DEVICE_RESYNC_ASYNC_LOGMAX]; }; @@ -471,6 +472,18 @@ static inline bool tls_bigint_increment(unsigned char *seq, int len) return (i == -1); } +static inline void tls_bigint_subtract(unsigned char *seq, int n) +{ + u64 rcd_sn; + __be64 *p; + + BUILD_BUG_ON(TLS_MAX_REC_SEQ_SIZE != 8); + + p = (__be64 *)seq; + rcd_sn = be64_to_cpu(*p); + *p = cpu_to_be64(rcd_sn - n); +} + static inline struct tls_context *tls_get_ctx(const struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -639,6 +652,7 @@ tls_offload_rx_resync_async_request_start(struct sock *sk, __be32 seq, u16 len) atomic64_set(&rx_ctx->resync_async->req, ((u64)ntohl(seq) << 32) | ((u64)len << 16) | RESYNC_REQ | RESYNC_REQ_ASYNC); rx_ctx->resync_async->loglen = 0; + rx_ctx->resync_async->rcd_delta = 0; } static inline void diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index 0140d086dc84..01755b838c74 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -86,7 +86,7 @@ int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_umem *umem, void xp_destroy(struct xsk_buff_pool *pool); void xp_release(struct xdp_buff_xsk *xskb); void xp_get_pool(struct xsk_buff_pool *pool); -void xp_put_pool(struct xsk_buff_pool *pool); +bool xp_put_pool(struct xsk_buff_pool *pool); void xp_clear_dev(struct xsk_buff_pool *pool); void xp_add_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs); void xp_del_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs); diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h index c25fb86ffae9..b3bbd10eb3f0 100644 --- a/include/scsi/libiscsi.h +++ b/include/scsi/libiscsi.h @@ -132,6 +132,9 @@ struct iscsi_task { void *dd_data; /* driver/transport data */ }; +/* invalid scsi_task pointer */ +#define INVALID_SCSI_TASK (struct iscsi_task *)-1l + static inline int iscsi_task_has_unsol_data(struct iscsi_task *task) { return task->unsol_r2t.data_length > task->unsol_r2t.sent; diff --git a/include/sound/control.h b/include/sound/control.h index e128cff10dfa..77d9fa10812d 100644 --- a/include/sound/control.h +++ b/include/sound/control.h @@ -42,7 +42,7 @@ struct snd_kcontrol_new { snd_ctl_elem_iface_t iface; /* interface identifier */ unsigned int device; /* device/client number */ unsigned int subdevice; /* subdevice (substream) number */ - const unsigned char *name; /* ASCII name of item */ + const char *name; /* ASCII name of item */ unsigned int index; /* index of item */ unsigned int access; /* access rights */ unsigned int count; /* count of same elements */ diff --git a/include/sound/core.h b/include/sound/core.h index 381a010a1bd4..0462c577d7a3 100644 --- a/include/sound/core.h +++ b/include/sound/core.h @@ -332,7 +332,8 @@ void __snd_printk(unsigned int level, const char *file, int line, #define snd_BUG() WARN(1, "BUG?\n") /** - * Suppress high rates of output when CONFIG_SND_DEBUG is enabled. + * snd_printd_ratelimit - Suppress high rates of output when + * CONFIG_SND_DEBUG is enabled. */ #define snd_printd_ratelimit() printk_ratelimit() diff --git a/include/sound/pcm.h b/include/sound/pcm.h index 2ba5df2c9e23..2336bf9243e1 100644 --- a/include/sound/pcm.h +++ b/include/sound/pcm.h @@ -1284,8 +1284,8 @@ snd_pcm_sgbuf_get_ptr(struct snd_pcm_substream *substream, unsigned int ofs) } /** - * snd_pcm_sgbuf_chunk_size - Compute the max size that fits within the contig. - * page from the given size + * snd_pcm_sgbuf_get_chunk_size - Compute the max size that fits within the + * contig. page from the given size * @substream: PCM substream * @ofs: byte offset * @size: byte size to examine diff --git a/include/sound/rt1015.h b/include/sound/rt1015.h new file mode 100644 index 000000000000..70a7538d4c89 --- /dev/null +++ b/include/sound/rt1015.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * linux/sound/rt1015.h -- Platform data for RT1015 + * + * Copyright 2020 Realtek Microelectronics + */ + +#ifndef __LINUX_SND_RT1015_H +#define __LINUX_SND_RT1015_H + +struct rt1015_platform_data { + unsigned int power_up_delay_ms; +}; + +#endif diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index b14314fcf732..70ae5497b73a 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -100,11 +100,12 @@ TRACE_DEFINE_ENUM(ES_REFERENCED_B); { EXT4_FC_REASON_XATTR, "XATTR"}, \ { EXT4_FC_REASON_CROSS_RENAME, "CROSS_RENAME"}, \ { EXT4_FC_REASON_JOURNAL_FLAG_CHANGE, "JOURNAL_FLAG_CHANGE"}, \ - { EXT4_FC_REASON_MEM, "NO_MEM"}, \ + { EXT4_FC_REASON_NOMEM, "NO_MEM"}, \ { EXT4_FC_REASON_SWAP_BOOT, "SWAP_BOOT"}, \ { EXT4_FC_REASON_RESIZE, "RESIZE"}, \ { EXT4_FC_REASON_RENAME_DIR, "RENAME_DIR"}, \ - { EXT4_FC_REASON_FALLOC_RANGE, "FALLOC_RANGE"}) + { EXT4_FC_REASON_FALLOC_RANGE, "FALLOC_RANGE"}, \ + { EXT4_FC_REASON_INODE_JOURNAL_DATA, "INODE_JOURNAL_DATA"}) TRACE_EVENT(ext4_other_inode_update_time, TP_PROTO(struct inode *inode, ino_t orig_ino), @@ -2917,17 +2918,18 @@ TRACE_EVENT(ext4_fc_stats, ), TP_printk("dev %d:%d fc ineligible reasons:\n" - "%s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s,%d; " + "%s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d; " "num_commits:%ld, ineligible: %ld, numblks: %ld", MAJOR(__entry->dev), MINOR(__entry->dev), FC_REASON_NAME_STAT(EXT4_FC_REASON_XATTR), FC_REASON_NAME_STAT(EXT4_FC_REASON_CROSS_RENAME), FC_REASON_NAME_STAT(EXT4_FC_REASON_JOURNAL_FLAG_CHANGE), - FC_REASON_NAME_STAT(EXT4_FC_REASON_MEM), + FC_REASON_NAME_STAT(EXT4_FC_REASON_NOMEM), FC_REASON_NAME_STAT(EXT4_FC_REASON_SWAP_BOOT), FC_REASON_NAME_STAT(EXT4_FC_REASON_RESIZE), FC_REASON_NAME_STAT(EXT4_FC_REASON_RENAME_DIR), FC_REASON_NAME_STAT(EXT4_FC_REASON_FALLOC_RANGE), + FC_REASON_NAME_STAT(EXT4_FC_REASON_INODE_JOURNAL_DATA), __entry->sbi->s_fc_stats.fc_num_commits, __entry->sbi->s_fc_stats.fc_ineligible_commits, __entry->sbi->s_fc_stats.fc_numblks) diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index f45b3c01370c..2a03263b5f9d 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -68,7 +68,8 @@ DECLARE_EVENT_CLASS(rpc_xdr_buf_class, TP_fast_assign( __entry->task_id = task->tk_pid; - __entry->client_id = task->tk_client->cl_clid; + __entry->client_id = task->tk_client ? + task->tk_client->cl_clid : -1; __entry->head_base = xdr->head[0].iov_base; __entry->head_len = xdr->head[0].iov_len; __entry->tail_base = xdr->tail[0].iov_base; @@ -655,10 +656,10 @@ TRACE_EVENT(rpc_xdr_overflow, __field(size_t, tail_len) __field(unsigned int, page_len) __field(unsigned int, len) - __string(progname, - xdr->rqst->rq_task->tk_client->cl_program->name) - __string(procedure, - xdr->rqst->rq_task->tk_msg.rpc_proc->p_name) + __string(progname, xdr->rqst ? + xdr->rqst->rq_task->tk_client->cl_program->name : "unknown") + __string(procedure, xdr->rqst ? + xdr->rqst->rq_task->tk_msg.rpc_proc->p_name : "unknown") ), TP_fast_assign( diff --git a/include/uapi/linux/gpio.h b/include/uapi/linux/gpio.h index 07865c601099..2072c260f5d0 100644 --- a/include/uapi/linux/gpio.h +++ b/include/uapi/linux/gpio.h @@ -26,7 +26,7 @@ * struct gpiochip_info - Information about a certain GPIO chip * @name: the Linux kernel name of this GPIO chip * @label: a functional name for this GPIO chip, such as a product - * number, may be empty + * number, may be empty (i.e. label[0] == '\0') * @lines: number of GPIO lines on this chip */ struct gpiochip_info { @@ -98,7 +98,7 @@ struct gpio_v2_line_values { * identifying which field of the attribute union is in use. * @GPIO_V2_LINE_ATTR_ID_FLAGS: flags field is in use * @GPIO_V2_LINE_ATTR_ID_OUTPUT_VALUES: values field is in use - * @GPIO_V2_LINE_ATTR_ID_DEBOUNCE: debounce_period_us is in use + * @GPIO_V2_LINE_ATTR_ID_DEBOUNCE: debounce_period_us field is in use */ enum gpio_v2_line_attr_id { GPIO_V2_LINE_ATTR_ID_FLAGS = 1, @@ -110,17 +110,17 @@ enum gpio_v2_line_attr_id { * struct gpio_v2_line_attribute - a configurable attribute of a line * @id: attribute identifier with value from &enum gpio_v2_line_attr_id * @padding: reserved for future use and must be zero filled - * @flags: if id is GPIO_V2_LINE_ATTR_ID_FLAGS, the flags for the GPIO - * line, with values from enum gpio_v2_line_flag, such as - * GPIO_V2_LINE_FLAG_ACTIVE_LOW, GPIO_V2_LINE_FLAG_OUTPUT etc, OR:ed + * @flags: if id is %GPIO_V2_LINE_ATTR_ID_FLAGS, the flags for the GPIO + * line, with values from &enum gpio_v2_line_flag, such as + * %GPIO_V2_LINE_FLAG_ACTIVE_LOW, %GPIO_V2_LINE_FLAG_OUTPUT etc, added * together. This overrides the default flags contained in the &struct * gpio_v2_line_config for the associated line. - * @values: if id is GPIO_V2_LINE_ATTR_ID_OUTPUT_VALUES, a bitmap + * @values: if id is %GPIO_V2_LINE_ATTR_ID_OUTPUT_VALUES, a bitmap * containing the values to which the lines will be set, with each bit * number corresponding to the index into &struct * gpio_v2_line_request.offsets. - * @debounce_period_us: if id is GPIO_V2_LINE_ATTR_ID_DEBOUNCE, the desired - * debounce period, in microseconds + * @debounce_period_us: if id is %GPIO_V2_LINE_ATTR_ID_DEBOUNCE, the + * desired debounce period, in microseconds */ struct gpio_v2_line_attribute { __u32 id; @@ -147,12 +147,12 @@ struct gpio_v2_line_config_attribute { /** * struct gpio_v2_line_config - Configuration for GPIO lines - * @flags: flags for the GPIO lines, with values from enum - * gpio_v2_line_flag, such as GPIO_V2_LINE_FLAG_ACTIVE_LOW, - * GPIO_V2_LINE_FLAG_OUTPUT etc, OR:ed together. This is the default for + * @flags: flags for the GPIO lines, with values from &enum + * gpio_v2_line_flag, such as %GPIO_V2_LINE_FLAG_ACTIVE_LOW, + * %GPIO_V2_LINE_FLAG_OUTPUT etc, added together. This is the default for * all requested lines but may be overridden for particular lines using - * attrs. - * @num_attrs: the number of attributes in attrs + * @attrs. + * @num_attrs: the number of attributes in @attrs * @padding: reserved for future use and must be zero filled * @attrs: the configuration attributes associated with the requested * lines. Any attribute should only be associated with a particular line @@ -175,17 +175,17 @@ struct gpio_v2_line_config { * "my-bitbanged-relay" * @config: requested configuration for the lines. * @num_lines: number of lines requested in this request, i.e. the number - * of valid fields in the GPIO_V2_LINES_MAX sized arrays, set to 1 to + * of valid fields in the %GPIO_V2_LINES_MAX sized arrays, set to 1 to * request a single line * @event_buffer_size: a suggested minimum number of line events that the * kernel should buffer. This is only relevant if edge detection is * enabled in the configuration. Note that this is only a suggested value * and the kernel may allocate a larger buffer or cap the size of the * buffer. If this field is zero then the buffer size defaults to a minimum - * of num_lines*16. + * of @num_lines * 16. * @padding: reserved for future use and must be zero filled * @fd: if successful this field will contain a valid anonymous file handle - * after a GPIO_GET_LINE_IOCTL operation, zero or negative value means + * after a %GPIO_GET_LINE_IOCTL operation, zero or negative value means * error */ struct gpio_v2_line_request { @@ -203,15 +203,16 @@ struct gpio_v2_line_request { * struct gpio_v2_line_info - Information about a certain GPIO line * @name: the name of this GPIO line, such as the output pin of the line on * the chip, a rail or a pin header name on a board, as specified by the - * GPIO chip, may be empty + * GPIO chip, may be empty (i.e. name[0] == '\0') * @consumer: a functional name for the consumer of this GPIO line as set * by whatever is using it, will be empty if there is no current user but * may also be empty if the consumer doesn't set this up - * @flags: flags for the GPIO line, such as GPIO_V2_LINE_FLAG_ACTIVE_LOW, - * GPIO_V2_LINE_FLAG_OUTPUT etc, OR:ed together * @offset: the local offset on this GPIO chip, fill this in when * requesting the line information from the kernel - * @num_attrs: the number of attributes in attrs + * @num_attrs: the number of attributes in @attrs + * @flags: flags for the GPIO lines, with values from &enum + * gpio_v2_line_flag, such as %GPIO_V2_LINE_FLAG_ACTIVE_LOW, + * %GPIO_V2_LINE_FLAG_OUTPUT etc, added together. * @attrs: the configuration attributes associated with the line * @padding: reserved for future use */ @@ -244,7 +245,7 @@ enum gpio_v2_line_changed_type { * of a GPIO line * @info: updated line information * @timestamp_ns: estimate of time of status change occurrence, in nanoseconds - * @event_type: the type of change with a value from enum + * @event_type: the type of change with a value from &enum * gpio_v2_line_changed_type * @padding: reserved for future use */ @@ -269,10 +270,10 @@ enum gpio_v2_line_event_id { /** * struct gpio_v2_line_event - The actual event being pushed to userspace * @timestamp_ns: best estimate of time of event occurrence, in nanoseconds. - * The timestamp_ns is read from CLOCK_MONOTONIC and is intended to allow the - * accurate measurement of the time between events. It does not provide + * The @timestamp_ns is read from %CLOCK_MONOTONIC and is intended to allow + * the accurate measurement of the time between events. It does not provide * the wall-clock time. - * @id: event identifier with value from enum gpio_v2_line_event_id + * @id: event identifier with value from &enum gpio_v2_line_event_id * @offset: the offset of the line that triggered the event * @seqno: the sequence number for this event in the sequence of events for * all the lines in this line request @@ -291,7 +292,7 @@ struct gpio_v2_line_event { }; /* - * ABI v1 + * ABI v1 * * This version of the ABI is deprecated. * Use the latest version of the ABI, defined above, instead. @@ -314,13 +315,13 @@ struct gpio_v2_line_event { * @flags: various flags for this line * @name: the name of this GPIO line, such as the output pin of the line on the * chip, a rail or a pin header name on a board, as specified by the gpio - * chip, may be empty + * chip, may be empty (i.e. name[0] == '\0') * @consumer: a functional name for the consumer of this GPIO line as set by * whatever is using it, will be empty if there is no current user but may * also be empty if the consumer doesn't set this up * - * This struct is part of ABI v1 and is deprecated. - * Use struct gpio_v2_line_info instead. + * Note: This struct is part of ABI v1 and is deprecated. + * Use &struct gpio_v2_line_info instead. */ struct gpioline_info { __u32 line_offset; @@ -344,17 +345,18 @@ enum { * of a GPIO line * @info: updated line information * @timestamp: estimate of time of status change occurrence, in nanoseconds - * @event_type: one of GPIOLINE_CHANGED_REQUESTED, GPIOLINE_CHANGED_RELEASED - * and GPIOLINE_CHANGED_CONFIG + * @event_type: one of %GPIOLINE_CHANGED_REQUESTED, + * %GPIOLINE_CHANGED_RELEASED and %GPIOLINE_CHANGED_CONFIG + * @padding: reserved for future use * - * Note: struct gpioline_info embedded here has 32-bit alignment on its own, + * The &struct gpioline_info embedded here has 32-bit alignment on its own, * but it works fine with 64-bit alignment too. With its 72 byte size, we can * guarantee there are no implicit holes between it and subsequent members. * The 20-byte padding at the end makes sure we don't add any implicit padding * at the end of the structure on 64-bit architectures. * - * This struct is part of ABI v1 and is deprecated. - * Use struct gpio_v2_line_info_changed instead. + * Note: This struct is part of ABI v1 and is deprecated. + * Use &struct gpio_v2_line_info_changed instead. */ struct gpioline_info_changed { struct gpioline_info info; @@ -378,13 +380,13 @@ struct gpioline_info_changed { * @lineoffsets: an array of desired lines, specified by offset index for the * associated GPIO device * @flags: desired flags for the desired GPIO lines, such as - * GPIOHANDLE_REQUEST_OUTPUT, GPIOHANDLE_REQUEST_ACTIVE_LOW etc, OR:ed + * %GPIOHANDLE_REQUEST_OUTPUT, %GPIOHANDLE_REQUEST_ACTIVE_LOW etc, added * together. Note that even if multiple lines are requested, the same flags * must be applicable to all of them, if you want lines with individual * flags set, request them one by one. It is possible to select * a batch of input or output lines, but they must all have the same * characteristics, i.e. all inputs or all outputs, all active low etc - * @default_values: if the GPIOHANDLE_REQUEST_OUTPUT is set for a requested + * @default_values: if the %GPIOHANDLE_REQUEST_OUTPUT is set for a requested * line, this specifies the default output value, should be 0 (low) or * 1 (high), anything else than 0 or 1 will be interpreted as 1 (high) * @consumer_label: a desired consumer label for the selected GPIO line(s) @@ -392,11 +394,11 @@ struct gpioline_info_changed { * @lines: number of lines requested in this request, i.e. the number of * valid fields in the above arrays, set to 1 to request a single line * @fd: if successful this field will contain a valid anonymous file handle - * after a GPIO_GET_LINEHANDLE_IOCTL operation, zero or negative value + * after a %GPIO_GET_LINEHANDLE_IOCTL operation, zero or negative value * means error * - * This struct is part of ABI v1 and is deprecated. - * Use struct gpio_v2_line_request instead. + * Note: This struct is part of ABI v1 and is deprecated. + * Use &struct gpio_v2_line_request instead. */ struct gpiohandle_request { __u32 lineoffsets[GPIOHANDLES_MAX]; @@ -410,15 +412,15 @@ struct gpiohandle_request { /** * struct gpiohandle_config - Configuration for a GPIO handle request * @flags: updated flags for the requested GPIO lines, such as - * GPIOHANDLE_REQUEST_OUTPUT, GPIOHANDLE_REQUEST_ACTIVE_LOW etc, OR:ed + * %GPIOHANDLE_REQUEST_OUTPUT, %GPIOHANDLE_REQUEST_ACTIVE_LOW etc, added * together - * @default_values: if the GPIOHANDLE_REQUEST_OUTPUT is set in flags, + * @default_values: if the %GPIOHANDLE_REQUEST_OUTPUT is set in flags, * this specifies the default output value, should be 0 (low) or * 1 (high), anything else than 0 or 1 will be interpreted as 1 (high) * @padding: reserved for future use and should be zero filled * - * This struct is part of ABI v1 and is deprecated. - * Use struct gpio_v2_line_config instead. + * Note: This struct is part of ABI v1 and is deprecated. + * Use &struct gpio_v2_line_config instead. */ struct gpiohandle_config { __u32 flags; @@ -432,8 +434,8 @@ struct gpiohandle_config { * state of a line, when setting the state of lines these should contain * the desired target state * - * This struct is part of ABI v1 and is deprecated. - * Use struct gpio_v2_line_values instead. + * Note: This struct is part of ABI v1 and is deprecated. + * Use &struct gpio_v2_line_values instead. */ struct gpiohandle_data { __u8 values[GPIOHANDLES_MAX]; @@ -449,17 +451,17 @@ struct gpiohandle_data { * @lineoffset: the desired line to subscribe to events from, specified by * offset index for the associated GPIO device * @handleflags: desired handle flags for the desired GPIO line, such as - * GPIOHANDLE_REQUEST_ACTIVE_LOW or GPIOHANDLE_REQUEST_OPEN_DRAIN + * %GPIOHANDLE_REQUEST_ACTIVE_LOW or %GPIOHANDLE_REQUEST_OPEN_DRAIN * @eventflags: desired flags for the desired GPIO event line, such as - * GPIOEVENT_REQUEST_RISING_EDGE or GPIOEVENT_REQUEST_FALLING_EDGE + * %GPIOEVENT_REQUEST_RISING_EDGE or %GPIOEVENT_REQUEST_FALLING_EDGE * @consumer_label: a desired consumer label for the selected GPIO line(s) * such as "my-listener" * @fd: if successful this field will contain a valid anonymous file handle - * after a GPIO_GET_LINEEVENT_IOCTL operation, zero or negative value + * after a %GPIO_GET_LINEEVENT_IOCTL operation, zero or negative value * means error * - * This struct is part of ABI v1 and is deprecated. - * Use struct gpio_v2_line_request instead. + * Note: This struct is part of ABI v1 and is deprecated. + * Use &struct gpio_v2_line_request instead. */ struct gpioevent_request { __u32 lineoffset; @@ -469,7 +471,7 @@ struct gpioevent_request { int fd; }; -/** +/* * GPIO event types */ #define GPIOEVENT_EVENT_RISING_EDGE 0x01 @@ -480,8 +482,8 @@ struct gpioevent_request { * @timestamp: best estimate of time of event occurrence, in nanoseconds * @id: event identifier * - * This struct is part of ABI v1 and is deprecated. - * Use struct gpio_v2_line_event instead. + * Note: This struct is part of ABI v1 and is deprecated. + * Use &struct gpio_v2_line_event instead. */ struct gpioevent_data { __u64 timestamp; diff --git a/include/uapi/linux/icmpv6.h b/include/uapi/linux/icmpv6.h index c1661febc2dc..0564fd7ccde4 100644 --- a/include/uapi/linux/icmpv6.h +++ b/include/uapi/linux/icmpv6.h @@ -138,6 +138,7 @@ struct icmp6hdr { #define ICMPV6_HDR_FIELD 0 #define ICMPV6_UNK_NEXTHDR 1 #define ICMPV6_UNK_OPTION 2 +#define ICMPV6_HDR_INCOMP 3 /* * constants for (set|get)sockopt diff --git a/include/uapi/sound/compress_offload.h b/include/uapi/sound/compress_offload.h index 7184265c0b0d..9555f31c8425 100644 --- a/include/uapi/sound/compress_offload.h +++ b/include/uapi/sound/compress_offload.h @@ -144,7 +144,7 @@ struct snd_compr_metadata { __u32 value[8]; } __attribute__((packed, aligned(4))); -/** +/* * compress path ioctl definitions * SNDRV_COMPRESS_GET_CAPS: Query capability of DSP * SNDRV_COMPRESS_GET_CODEC_CAPS: Query capability of a codec diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h index 06b0b57e996c..d1b3889f74d8 100644 --- a/include/video/imx-ipu-v3.h +++ b/include/video/imx-ipu-v3.h @@ -484,9 +484,6 @@ int ipu_smfc_set_watermark(struct ipu_smfc *smfc, u32 set_level, u32 clr_level); enum ipu_color_space ipu_drm_fourcc_to_colorspace(u32 drm_fourcc); enum ipu_color_space ipu_pixelformat_to_colorspace(u32 pixelformat); -enum ipu_color_space ipu_mbus_code_to_colorspace(u32 mbus_code); -int ipu_stride_to_bytes(u32 pixel_stride, u32 pixelformat); -bool ipu_pixelformat_is_planar(u32 pixelformat); int ipu_degrees_to_rot_mode(enum ipu_rotate_mode *mode, int degrees, bool hflip, bool vflip); int ipu_rot_mode_to_degrees(int *degrees, enum ipu_rotate_mode mode, diff --git a/init/main.c b/init/main.c index 130376ec10ba..20baced721ad 100644 --- a/init/main.c +++ b/init/main.c @@ -269,14 +269,24 @@ static void * __init get_boot_config_from_initrd(u32 *_size, u32 *_csum) u32 size, csum; char *data; u32 *hdr; + int i; if (!initrd_end) return NULL; data = (char *)initrd_end - BOOTCONFIG_MAGIC_LEN; - if (memcmp(data, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN)) - return NULL; + /* + * Since Grub may align the size of initrd to 4, we must + * check the preceding 3 bytes as well. + */ + for (i = 0; i < 4; i++) { + if (!memcmp(data, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN)) + goto found; + data--; + } + return NULL; +found: hdr = (u32 *)(data - 8); size = hdr[0]; csum = hdr[1]; diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index bdc8cd1b6767..c1b9f71ee6aa 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -1,6 +1,10 @@ # SPDX-License-Identifier: GPL-2.0 obj-y := core.o -CFLAGS_core.o += $(call cc-disable-warning, override-init) +ifneq ($(CONFIG_BPF_JIT_ALWAYS_ON),y) +# ___bpf_prog_run() needs GCSE disabled on x86; see 3193c0836f203 for details +cflags-nogcse-$(CONFIG_X86)$(CONFIG_CC_IS_GCC) := -fno-gcse +endif +CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy) obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o map_iter.o task_iter.o prog_iter.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index 78ea8a7bd27f..56cc5a915f67 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -13,6 +13,7 @@ #include <linux/bpf_verifier.h> #include <net/bpf_sk_storage.h> #include <linux/bpf_local_storage.h> +#include <linux/btf_ids.h> /* For every LSM hook that allows attachment of BPF programs, declare a nop * function where a BPF program can be attached. @@ -26,7 +27,11 @@ noinline RET bpf_lsm_##NAME(__VA_ARGS__) \ #include <linux/lsm_hook_defs.h> #undef LSM_HOOK -#define BPF_LSM_SYM_PREFX "bpf_lsm_" +#define LSM_HOOK(RET, DEFAULT, NAME, ...) BTF_ID(func, bpf_lsm_##NAME) +BTF_SET_START(bpf_lsm_hooks) +#include <linux/lsm_hook_defs.h> +#undef LSM_HOOK +BTF_SET_END(bpf_lsm_hooks) int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog, const struct bpf_prog *prog) @@ -37,8 +42,7 @@ int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog, return -EINVAL; } - if (strncmp(BPF_LSM_SYM_PREFX, prog->aux->attach_func_name, - sizeof(BPF_LSM_SYM_PREFX) - 1)) { + if (!btf_id_set_contains(&bpf_lsm_hooks, prog->aux->attach_btf_id)) { bpf_log(vlog, "attach_btf_id %u points to wrong type name %s\n", prog->aux->attach_btf_id, prog->aux->attach_func_name); return -EINVAL; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 9268d77898b7..55454d2278b1 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1369,7 +1369,7 @@ u64 __weak bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr) * * Decode and execute eBPF instructions. */ -static u64 __no_fgcse ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack) +static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack) { #define BPF_INSN_2_LBL(x, y) [BPF_##x | BPF_##y] = &&x##_##y #define BPF_INSN_3_LBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = &&x##_##y##_##z diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 1815e97d4c9c..1fccba6e88c4 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -821,6 +821,32 @@ static void pcpu_copy_value(struct bpf_htab *htab, void __percpu *pptr, } } +static void pcpu_init_value(struct bpf_htab *htab, void __percpu *pptr, + void *value, bool onallcpus) +{ + /* When using prealloc and not setting the initial value on all cpus, + * zero-fill element values for other cpus (just as what happens when + * not using prealloc). Otherwise, bpf program has no way to ensure + * known initial values for cpus other than current one + * (onallcpus=false always when coming from bpf prog). + */ + if (htab_is_prealloc(htab) && !onallcpus) { + u32 size = round_up(htab->map.value_size, 8); + int current_cpu = raw_smp_processor_id(); + int cpu; + + for_each_possible_cpu(cpu) { + if (cpu == current_cpu) + bpf_long_memcpy(per_cpu_ptr(pptr, cpu), value, + size); + else + memset(per_cpu_ptr(pptr, cpu), 0, size); + } + } else { + pcpu_copy_value(htab, pptr, value, onallcpus); + } +} + static bool fd_htab_map_needs_adjust(const struct bpf_htab *htab) { return htab->map.map_type == BPF_MAP_TYPE_HASH_OF_MAPS && @@ -891,7 +917,7 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, } } - pcpu_copy_value(htab, pptr, value, onallcpus); + pcpu_init_value(htab, pptr, value, onallcpus); if (!prealloc) htab_elem_set_ptr(l_new, key_size, pptr); @@ -1183,7 +1209,7 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, pcpu_copy_value(htab, htab_elem_get_ptr(l_old, key_size), value, onallcpus); } else { - pcpu_copy_value(htab, htab_elem_get_ptr(l_new, key_size), + pcpu_init_value(htab, htab_elem_get_ptr(l_new, key_size), value, onallcpus); hlist_nulls_add_head_rcu(&l_new->hash_node, head); l_new = NULL; diff --git a/kernel/bpf/preload/Kconfig b/kernel/bpf/preload/Kconfig index ace49111d3a3..26bced262473 100644 --- a/kernel/bpf/preload/Kconfig +++ b/kernel/bpf/preload/Kconfig @@ -6,6 +6,7 @@ config USERMODE_DRIVER menuconfig BPF_PRELOAD bool "Preload BPF file system with kernel specific program and map iterators" depends on BPF + depends on BPF_SYSCALL # The dependency on !COMPILE_TEST prevents it from being enabled # in allmodconfig or allyesconfig configurations depends on !COMPILE_TEST diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 6200519582a6..1388bf733071 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -7786,9 +7786,11 @@ static int check_return_code(struct bpf_verifier_env *env) struct tnum range = tnum_range(0, 1); enum bpf_prog_type prog_type = resolve_prog_type(env->prog); int err; + const bool is_subprog = env->cur_state->frame[0]->subprogno; /* LSM and struct_ops func-ptr's return type could be "void" */ - if ((prog_type == BPF_PROG_TYPE_STRUCT_OPS || + if (!is_subprog && + (prog_type == BPF_PROG_TYPE_STRUCT_OPS || prog_type == BPF_PROG_TYPE_LSM) && !prog->aux->attach_func_proto->type) return 0; @@ -7808,6 +7810,16 @@ static int check_return_code(struct bpf_verifier_env *env) return -EACCES; } + reg = cur_regs(env) + BPF_REG_0; + if (is_subprog) { + if (reg->type != SCALAR_VALUE) { + verbose(env, "At subprogram exit the register R0 is not a scalar value (%s)\n", + reg_type_str[reg->type]); + return -EINVAL; + } + return 0; + } + switch (prog_type) { case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: if (env->prog->expected_attach_type == BPF_CGROUP_UDP4_RECVMSG || @@ -7861,7 +7873,6 @@ static int check_return_code(struct bpf_verifier_env *env) return 0; } - reg = cur_regs(env) + BPF_REG_0; if (reg->type != SCALAR_VALUE) { verbose(env, "At program exit the register R0 is not a known value (%s)\n", reg_type_str[reg->type]); @@ -9572,12 +9583,13 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env, struct bpf_insn *insn, struct bpf_insn_aux_data *aux) { - u32 datasec_id, type, id = insn->imm; const struct btf_var_secinfo *vsi; const struct btf_type *datasec; const struct btf_type *t; const char *sym_name; bool percpu = false; + u32 type, id = insn->imm; + s32 datasec_id; u64 addr; int i; diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index b4eea0abc3f0..781b9dca197c 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -229,6 +229,7 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) io_tlb_orig_addr[i] = INVALID_PHYS_ADDR; } io_tlb_index = 0; + no_iotlb_memory = false; if (verbose) swiotlb_print_info(); @@ -260,9 +261,11 @@ swiotlb_init(int verbose) if (vstart && !swiotlb_init_with_tbl(vstart, io_tlb_nslabs, verbose)) return; - if (io_tlb_start) + if (io_tlb_start) { memblock_free_early(io_tlb_start, PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT)); + io_tlb_start = 0; + } pr_warn("Cannot allocate buffer"); no_iotlb_memory = true; } @@ -360,6 +363,7 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) io_tlb_orig_addr[i] = INVALID_PHYS_ADDR; } io_tlb_index = 0; + no_iotlb_memory = false; swiotlb_print_info(); @@ -441,14 +445,11 @@ static void swiotlb_bounce(phys_addr_t orig_addr, phys_addr_t tlb_addr, } } -phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, - dma_addr_t tbl_dma_addr, - phys_addr_t orig_addr, - size_t mapping_size, - size_t alloc_size, - enum dma_data_direction dir, - unsigned long attrs) +phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t orig_addr, + size_t mapping_size, size_t alloc_size, + enum dma_data_direction dir, unsigned long attrs) { + dma_addr_t tbl_dma_addr = phys_to_dma_unencrypted(hwdev, io_tlb_start); unsigned long flags; phys_addr_t tlb_addr; unsigned int nslots, stride, index, wrap; @@ -667,9 +668,8 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size, trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size, swiotlb_force); - swiotlb_addr = swiotlb_tbl_map_single(dev, - phys_to_dma_unencrypted(dev, io_tlb_start), - paddr, size, size, dir, attrs); + swiotlb_addr = swiotlb_tbl_map_single(dev, paddr, size, size, dir, + attrs); if (swiotlb_addr == (phys_addr_t)DMA_MAPPING_ERROR) return DMA_MAPPING_ERROR; diff --git a/kernel/entry/common.c b/kernel/entry/common.c index 2b8366693d5c..e9e2df3f3f9e 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -337,10 +337,10 @@ noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs) * already contains a warning when RCU is not watching, so no point * in having another one here. */ + lockdep_hardirqs_off(CALLER_ADDR0); instrumentation_begin(); rcu_irq_enter_check_tick(); - /* Use the combo lockdep/tracing function */ - trace_hardirqs_off(); + trace_hardirqs_off_finish(); instrumentation_end(); return ret; diff --git a/kernel/events/core.c b/kernel/events/core.c index da467e1dd49a..dc568ca295bd 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2312,9 +2312,6 @@ group_sched_out(struct perf_event *group_event, event_sched_out(event, cpuctx, ctx); perf_pmu_enable(ctx->pmu); - - if (group_event->attr.exclusive) - cpuctx->exclusive = 0; } #define DETACH_GROUP 0x01UL @@ -2583,11 +2580,8 @@ group_sched_in(struct perf_event *group_event, pmu->start_txn(pmu, PERF_PMU_TXN_ADD); - if (event_sched_in(group_event, cpuctx, ctx)) { - pmu->cancel_txn(pmu); - perf_mux_hrtimer_restart(cpuctx); - return -EAGAIN; - } + if (event_sched_in(group_event, cpuctx, ctx)) + goto error; /* * Schedule in siblings as one group (if any): @@ -2616,10 +2610,8 @@ group_error: } event_sched_out(group_event, cpuctx, ctx); +error: pmu->cancel_txn(pmu); - - perf_mux_hrtimer_restart(cpuctx); - return -EAGAIN; } @@ -2645,7 +2637,7 @@ static int group_can_go_on(struct perf_event *event, * If this group is exclusive and there are already * events on the CPU, it can't go on. */ - if (event->attr.exclusive && cpuctx->active_oncpu) + if (event->attr.exclusive && !list_empty(get_event_list(event))) return 0; /* * Otherwise, try to add it if all previous groups were able @@ -3679,6 +3671,7 @@ static int merge_sched_in(struct perf_event *event, void *data) *can_add_hw = 0; ctx->rotate_necessary = 1; + perf_mux_hrtimer_restart(cpuctx); } return 0; @@ -6374,14 +6367,13 @@ perf_output_sample_regs(struct perf_output_handle *handle, } static void perf_sample_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { if (user_mode(regs)) { regs_user->abi = perf_reg_abi(current); regs_user->regs = regs; } else if (!(current->flags & PF_KTHREAD)) { - perf_get_regs_user(regs_user, regs, regs_user_copy); + perf_get_regs_user(regs_user, regs); } else { regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE; regs_user->regs = NULL; @@ -7083,8 +7075,7 @@ void perf_prepare_sample(struct perf_event_header *header, } if (sample_type & (PERF_SAMPLE_REGS_USER | PERF_SAMPLE_STACK_USER)) - perf_sample_regs_user(&data->regs_user, regs, - &data->regs_user_copy); + perf_sample_regs_user(&data->regs_user, regs); if (sample_type & PERF_SAMPLE_REGS_USER) { /* regs dump ABI info */ @@ -7186,6 +7177,7 @@ __perf_event_output(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs, int (*output_begin)(struct perf_output_handle *, + struct perf_sample_data *, struct perf_event *, unsigned int)) { @@ -7198,7 +7190,7 @@ __perf_event_output(struct perf_event *event, perf_prepare_sample(&header, data, event, regs); - err = output_begin(&handle, event, header.size); + err = output_begin(&handle, data, event, header.size); if (err) goto exit; @@ -7264,7 +7256,7 @@ perf_event_read_event(struct perf_event *event, int ret; perf_event_header__init_id(&read_event.header, &sample, event); - ret = perf_output_begin(&handle, event, read_event.header.size); + ret = perf_output_begin(&handle, &sample, event, read_event.header.size); if (ret) return; @@ -7533,7 +7525,7 @@ static void perf_event_task_output(struct perf_event *event, perf_event_header__init_id(&task_event->event_id.header, &sample, event); - ret = perf_output_begin(&handle, event, + ret = perf_output_begin(&handle, &sample, event, task_event->event_id.header.size); if (ret) goto out; @@ -7636,7 +7628,7 @@ static void perf_event_comm_output(struct perf_event *event, return; perf_event_header__init_id(&comm_event->event_id.header, &sample, event); - ret = perf_output_begin(&handle, event, + ret = perf_output_begin(&handle, &sample, event, comm_event->event_id.header.size); if (ret) @@ -7736,7 +7728,7 @@ static void perf_event_namespaces_output(struct perf_event *event, perf_event_header__init_id(&namespaces_event->event_id.header, &sample, event); - ret = perf_output_begin(&handle, event, + ret = perf_output_begin(&handle, &sample, event, namespaces_event->event_id.header.size); if (ret) goto out; @@ -7863,7 +7855,7 @@ static void perf_event_cgroup_output(struct perf_event *event, void *data) perf_event_header__init_id(&cgroup_event->event_id.header, &sample, event); - ret = perf_output_begin(&handle, event, + ret = perf_output_begin(&handle, &sample, event, cgroup_event->event_id.header.size); if (ret) goto out; @@ -7989,7 +7981,7 @@ static void perf_event_mmap_output(struct perf_event *event, } perf_event_header__init_id(&mmap_event->event_id.header, &sample, event); - ret = perf_output_begin(&handle, event, + ret = perf_output_begin(&handle, &sample, event, mmap_event->event_id.header.size); if (ret) goto out; @@ -8299,7 +8291,7 @@ void perf_event_aux_event(struct perf_event *event, unsigned long head, int ret; perf_event_header__init_id(&rec.header, &sample, event); - ret = perf_output_begin(&handle, event, rec.header.size); + ret = perf_output_begin(&handle, &sample, event, rec.header.size); if (ret) return; @@ -8333,7 +8325,7 @@ void perf_log_lost_samples(struct perf_event *event, u64 lost) perf_event_header__init_id(&lost_samples_event.header, &sample, event); - ret = perf_output_begin(&handle, event, + ret = perf_output_begin(&handle, &sample, event, lost_samples_event.header.size); if (ret) return; @@ -8388,7 +8380,7 @@ static void perf_event_switch_output(struct perf_event *event, void *data) perf_event_header__init_id(&se->event_id.header, &sample, event); - ret = perf_output_begin(&handle, event, se->event_id.header.size); + ret = perf_output_begin(&handle, &sample, event, se->event_id.header.size); if (ret) return; @@ -8463,7 +8455,7 @@ static void perf_log_throttle(struct perf_event *event, int enable) perf_event_header__init_id(&throttle_event.header, &sample, event); - ret = perf_output_begin(&handle, event, + ret = perf_output_begin(&handle, &sample, event, throttle_event.header.size); if (ret) return; @@ -8506,7 +8498,7 @@ static void perf_event_ksymbol_output(struct perf_event *event, void *data) perf_event_header__init_id(&ksymbol_event->event_id.header, &sample, event); - ret = perf_output_begin(&handle, event, + ret = perf_output_begin(&handle, &sample, event, ksymbol_event->event_id.header.size); if (ret) return; @@ -8596,7 +8588,7 @@ static void perf_event_bpf_output(struct perf_event *event, void *data) perf_event_header__init_id(&bpf_event->event_id.header, &sample, event); - ret = perf_output_begin(&handle, event, + ret = perf_output_begin(&handle, data, event, bpf_event->event_id.header.size); if (ret) return; @@ -8705,7 +8697,8 @@ static void perf_event_text_poke_output(struct perf_event *event, void *data) perf_event_header__init_id(&text_poke_event->event_id.header, &sample, event); - ret = perf_output_begin(&handle, event, text_poke_event->event_id.header.size); + ret = perf_output_begin(&handle, &sample, event, + text_poke_event->event_id.header.size); if (ret) return; @@ -8786,7 +8779,7 @@ static void perf_log_itrace_start(struct perf_event *event) rec.tid = perf_event_tid(event, current); perf_event_header__init_id(&rec.header, &sample, event); - ret = perf_output_begin(&handle, event, rec.header.size); + ret = perf_output_begin(&handle, &sample, event, rec.header.size); if (ret) return; @@ -10085,6 +10078,7 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr, if (token == IF_SRC_FILE || token == IF_SRC_FILEADDR) { int fpos = token == IF_SRC_FILE ? 2 : 1; + kfree(filename); filename = match_strdup(&args[fpos]); if (!filename) { ret = -ENOMEM; @@ -10131,16 +10125,13 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr, */ ret = -EOPNOTSUPP; if (!event->ctx->task) - goto fail_free_name; + goto fail; /* look up the path and grab its inode */ ret = kern_path(filename, LOOKUP_FOLLOW, &filter->path); if (ret) - goto fail_free_name; - - kfree(filename); - filename = NULL; + goto fail; ret = -EINVAL; if (!filter->path.dentry || @@ -10160,13 +10151,13 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr, if (state != IF_STATE_ACTION) goto fail; + kfree(filename); kfree(orig); return 0; -fail_free_name: - kfree(filename); fail: + kfree(filename); free_filters_list(filters); kfree(orig); diff --git a/kernel/events/internal.h b/kernel/events/internal.h index fcbf5616a441..228801e20788 100644 --- a/kernel/events/internal.h +++ b/kernel/events/internal.h @@ -205,16 +205,12 @@ DEFINE_OUTPUT_COPY(__output_copy_user, arch_perf_out_copy_user) static inline int get_recursion_context(int *recursion) { - int rctx; - - if (unlikely(in_nmi())) - rctx = 3; - else if (in_irq()) - rctx = 2; - else if (in_softirq()) - rctx = 1; - else - rctx = 0; + unsigned int pc = preempt_count(); + unsigned char rctx = 0; + + rctx += !!(pc & (NMI_MASK)); + rctx += !!(pc & (NMI_MASK | HARDIRQ_MASK)); + rctx += !!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET)); if (recursion[rctx]) return -1; diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 192b8abc6330..ef91ae75ca56 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -147,6 +147,7 @@ ring_buffer_has_space(unsigned long head, unsigned long tail, static __always_inline int __perf_output_begin(struct perf_output_handle *handle, + struct perf_sample_data *data, struct perf_event *event, unsigned int size, bool backward) { @@ -237,18 +238,16 @@ __perf_output_begin(struct perf_output_handle *handle, handle->size = (1UL << page_shift) - offset; if (unlikely(have_lost)) { - struct perf_sample_data sample_data; - lost_event.header.size = sizeof(lost_event); lost_event.header.type = PERF_RECORD_LOST; lost_event.header.misc = 0; lost_event.id = event->id; lost_event.lost = local_xchg(&rb->lost, 0); - perf_event_header__init_id(&lost_event.header, - &sample_data, event); + /* XXX mostly redundant; @data is already fully initializes */ + perf_event_header__init_id(&lost_event.header, data, event); perf_output_put(handle, lost_event); - perf_event__output_id_sample(event, handle, &sample_data); + perf_event__output_id_sample(event, handle, data); } return 0; @@ -263,22 +262,25 @@ out: } int perf_output_begin_forward(struct perf_output_handle *handle, - struct perf_event *event, unsigned int size) + struct perf_sample_data *data, + struct perf_event *event, unsigned int size) { - return __perf_output_begin(handle, event, size, false); + return __perf_output_begin(handle, data, event, size, false); } int perf_output_begin_backward(struct perf_output_handle *handle, + struct perf_sample_data *data, struct perf_event *event, unsigned int size) { - return __perf_output_begin(handle, event, size, true); + return __perf_output_begin(handle, data, event, size, true); } int perf_output_begin(struct perf_output_handle *handle, + struct perf_sample_data *data, struct perf_event *event, unsigned int size) { - return __perf_output_begin(handle, event, size, + return __perf_output_begin(handle, data, event, size, unlikely(is_write_backward(event))); } diff --git a/kernel/exit.c b/kernel/exit.c index 87a2d515de0d..1f236ed375f8 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -454,7 +454,10 @@ static void exit_mm(void) mmap_read_unlock(mm); self.task = current; - self.next = xchg(&core_state->dumper.next, &self); + if (self.task->flags & PF_SIGNALED) + self.next = xchg(&core_state->dumper.next, &self); + else + self.task = NULL; /* * Implies mb(), the result of xchg() must be visible * to core_state->dumper. diff --git a/kernel/fail_function.c b/kernel/fail_function.c index 63b349168da7..b0b1ad93fa95 100644 --- a/kernel/fail_function.c +++ b/kernel/fail_function.c @@ -253,7 +253,7 @@ static ssize_t fei_write(struct file *file, const char __user *buffer, if (copy_from_user(buf, buffer, count)) { ret = -EFAULT; - goto out; + goto out_free; } buf[count] = '\0'; sym = strstrip(buf); @@ -307,8 +307,9 @@ static ssize_t fei_write(struct file *file, const char __user *buffer, ret = count; } out: - kfree(buf); mutex_unlock(&fei_lock); +out_free: + kfree(buf); return ret; } diff --git a/kernel/fork.c b/kernel/fork.c index 32083db7a2a2..6d266388d380 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2167,14 +2167,9 @@ static __latent_entropy struct task_struct *copy_process( /* ok, now we should be set up.. */ p->pid = pid_nr(pid); if (clone_flags & CLONE_THREAD) { - p->exit_signal = -1; p->group_leader = current->group_leader; p->tgid = current->tgid; } else { - if (clone_flags & CLONE_PARENT) - p->exit_signal = current->group_leader->exit_signal; - else - p->exit_signal = args->exit_signal; p->group_leader = p; p->tgid = p->pid; } @@ -2218,9 +2213,14 @@ static __latent_entropy struct task_struct *copy_process( if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) { p->real_parent = current->real_parent; p->parent_exec_id = current->parent_exec_id; + if (clone_flags & CLONE_THREAD) + p->exit_signal = -1; + else + p->exit_signal = current->group_leader->exit_signal; } else { p->real_parent = current; p->parent_exec_id = current->self_exec_id; + p->exit_signal = args->exit_signal; } klp_copy_process(p); diff --git a/kernel/futex.c b/kernel/futex.c index f8614ef4ff31..00259c7e288e 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -788,8 +788,9 @@ static void put_pi_state(struct futex_pi_state *pi_state) */ if (pi_state->owner) { struct task_struct *owner; + unsigned long flags; - raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); + raw_spin_lock_irqsave(&pi_state->pi_mutex.wait_lock, flags); owner = pi_state->owner; if (owner) { raw_spin_lock(&owner->pi_lock); @@ -797,7 +798,7 @@ static void put_pi_state(struct futex_pi_state *pi_state) raw_spin_unlock(&owner->pi_lock); } rt_mutex_proxy_unlock(&pi_state->pi_mutex, owner); - raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); + raw_spin_unlock_irqrestore(&pi_state->pi_mutex.wait_lock, flags); } if (current->pi_state_cache) { @@ -2380,10 +2381,22 @@ retry: } /* - * Since we just failed the trylock; there must be an owner. + * The trylock just failed, so either there is an owner or + * there is a higher priority waiter than this one. */ newowner = rt_mutex_owner(&pi_state->pi_mutex); - BUG_ON(!newowner); + /* + * If the higher priority waiter has not yet taken over the + * rtmutex then newowner is NULL. We can't return here with + * that state because it's inconsistent vs. the user space + * state. So drop the locks and try again. It's a valid + * situation and not any different from the other retry + * conditions. + */ + if (unlikely(!newowner)) { + err = -EAGAIN; + goto handle_err; + } } else { WARN_ON_ONCE(argowner != current); if (oldowner == current) { diff --git a/kernel/hung_task.c b/kernel/hung_task.c index ce76f490126c..396ebaebea3f 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -225,8 +225,7 @@ static long hung_timeout_jiffies(unsigned long last_checked, * Process updating of timeout sysctl */ int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, - void __user *buffer, - size_t *lenp, loff_t *ppos) + void *buffer, size_t *lenp, loff_t *ppos) { int ret; diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index 10a5aff4eecc..164a031cfdb6 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -82,6 +82,7 @@ config IRQ_FASTEOI_HIERARCHY_HANDLERS # Generic IRQ IPI support config GENERIC_IRQ_IPI bool + select IRQ_DOMAIN_HIERARCHY # Generic MSI interrupt support config GENERIC_MSI_IRQ diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 8a12a25fa40d..41fdbb7953c6 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1249,7 +1249,13 @@ __acquires(hlist_lock) *head = &kretprobe_inst_table[hash]; hlist_lock = kretprobe_table_lock_ptr(hash); - raw_spin_lock_irqsave(hlist_lock, *flags); + /* + * Nested is a workaround that will soon not be needed. + * There's other protections that make sure the same lock + * is not taken on the same CPU that lockdep is unaware of. + * Differentiate when it is taken in NMI context. + */ + raw_spin_lock_irqsave_nested(hlist_lock, *flags, !!in_nmi()); } NOKPROBE_SYMBOL(kretprobe_hash_lock); @@ -1258,7 +1264,13 @@ static void kretprobe_table_lock(unsigned long hash, __acquires(hlist_lock) { raw_spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash); - raw_spin_lock_irqsave(hlist_lock, *flags); + /* + * Nested is a workaround that will soon not be needed. + * There's other protections that make sure the same lock + * is not taken on the same CPU that lockdep is unaware of. + * Differentiate when it is taken in NMI context. + */ + raw_spin_lock_irqsave_nested(hlist_lock, *flags, !!in_nmi()); } NOKPROBE_SYMBOL(kretprobe_table_lock); @@ -2028,7 +2040,12 @@ static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs) /* TODO: consider to only swap the RA after the last pre_handler fired */ hash = hash_ptr(current, KPROBE_HASH_BITS); - raw_spin_lock_irqsave(&rp->lock, flags); + /* + * Nested is a workaround that will soon not be needed. + * There's other protections that make sure the same lock + * is not taken on the same CPU that lockdep is unaware of. + */ + raw_spin_lock_irqsave_nested(&rp->lock, flags, 1); if (!hlist_empty(&rp->free_instances)) { ri = hlist_entry(rp->free_instances.first, struct kretprobe_instance, hlist); @@ -2039,7 +2056,7 @@ static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs) ri->task = current; if (rp->entry_handler && rp->entry_handler(ri, regs)) { - raw_spin_lock_irqsave(&rp->lock, flags); + raw_spin_lock_irqsave_nested(&rp->lock, flags, 1); hlist_add_head(&ri->hlist, &rp->free_instances); raw_spin_unlock_irqrestore(&rp->lock, flags); return 0; diff --git a/kernel/kthread.c b/kernel/kthread.c index e29773c82b70..933a625621b8 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -897,7 +897,8 @@ void kthread_delayed_work_timer_fn(struct timer_list *t) /* Move the work from worker->delayed_work_list. */ WARN_ON_ONCE(list_empty(&work->node)); list_del_init(&work->node); - kthread_insert_work(worker, work, &worker->work_list); + if (!work->canceling) + kthread_insert_work(worker, work, &worker->work_list); raw_spin_unlock_irqrestore(&worker->lock, flags); } diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index b71ad8d9f1c9..c1418b47f625 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -108,19 +108,21 @@ static inline void lockdep_lock(void) { DEBUG_LOCKS_WARN_ON(!irqs_disabled()); + __this_cpu_inc(lockdep_recursion); arch_spin_lock(&__lock); __owner = current; - __this_cpu_inc(lockdep_recursion); } static inline void lockdep_unlock(void) { + DEBUG_LOCKS_WARN_ON(!irqs_disabled()); + if (debug_locks && DEBUG_LOCKS_WARN_ON(__owner != current)) return; - __this_cpu_dec(lockdep_recursion); __owner = NULL; arch_spin_unlock(&__lock); + __this_cpu_dec(lockdep_recursion); } static inline bool lockdep_assert_locked(void) @@ -2765,7 +2767,9 @@ print_deadlock_bug(struct task_struct *curr, struct held_lock *prev, * (Note that this has to be done separately, because the graph cannot * detect such classes of deadlocks.) * - * Returns: 0 on deadlock detected, 1 on OK, 2 on recursive read + * Returns: 0 on deadlock detected, 1 on OK, 2 if another lock with the same + * lock class is held but nest_lock is also held, i.e. we rely on the + * nest_lock to avoid the deadlock. */ static int check_deadlock(struct task_struct *curr, struct held_lock *next) @@ -2788,7 +2792,7 @@ check_deadlock(struct task_struct *curr, struct held_lock *next) * lock class (i.e. read_lock(lock)+read_lock(lock)): */ if ((next->read == 2) && prev->read) - return 2; + continue; /* * We're holding the nest_lock, which serializes this lock's @@ -3593,15 +3597,12 @@ static int validate_chain(struct task_struct *curr, if (!ret) return 0; /* - * Mark recursive read, as we jump over it when - * building dependencies (just like we jump over - * trylock entries): - */ - if (ret == 2) - hlock->read = 2; - /* * Add dependency only if this lock is not the head - * of the chain, and if it's not a secondary read-lock: + * of the chain, and if the new lock introduces no more + * lock dependency (because we already hold a lock with the + * same lock class) nor deadlock (because the nest_lock + * serializes nesting locks), see the comments for + * check_deadlock(). */ if (!chain_head && ret != 2) { if (!check_prevs_add(curr, hlock)) diff --git a/kernel/panic.c b/kernel/panic.c index 396142ee43fd..332736a72a58 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -605,7 +605,8 @@ void __warn(const char *file, int line, void *caller, unsigned taint, panic("panic_on_warn set ...\n"); } - dump_stack(); + if (!regs) + dump_stack(); print_irqtrace_events(current); diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 43d6179508d6..79de1294f8eb 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -264,17 +264,11 @@ static int ptrace_check_attach(struct task_struct *child, bool ignore_state) return ret; } -static bool ptrace_has_cap(const struct cred *cred, struct user_namespace *ns, - unsigned int mode) +static bool ptrace_has_cap(struct user_namespace *ns, unsigned int mode) { - int ret; - if (mode & PTRACE_MODE_NOAUDIT) - ret = security_capable(cred, ns, CAP_SYS_PTRACE, CAP_OPT_NOAUDIT); - else - ret = security_capable(cred, ns, CAP_SYS_PTRACE, CAP_OPT_NONE); - - return ret == 0; + return ns_capable_noaudit(ns, CAP_SYS_PTRACE); + return ns_capable(ns, CAP_SYS_PTRACE); } /* Returns 0 on success, -errno on denial. */ @@ -326,7 +320,7 @@ static int __ptrace_may_access(struct task_struct *task, unsigned int mode) gid_eq(caller_gid, tcred->sgid) && gid_eq(caller_gid, tcred->gid)) goto ok; - if (ptrace_has_cap(cred, tcred->user_ns, mode)) + if (ptrace_has_cap(tcred->user_ns, mode)) goto ok; rcu_read_unlock(); return -EPERM; @@ -345,7 +339,7 @@ ok: mm = task->mm; if (mm && ((get_dumpable(mm) != SUID_DUMP_USER) && - !ptrace_has_cap(cred, mm->user_ns, mode))) + !ptrace_has_cap(mm->user_ns, mode))) return -EPERM; return security_ptrace_access_check(task, mode); diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 2a52f42f64b6..bd04b09b84b3 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -4077,7 +4077,6 @@ void rcu_cpu_starting(unsigned int cpu) smp_mb(); /* Ensure RCU read-side usage follows above initialization. */ } -#ifdef CONFIG_HOTPLUG_CPU /* * The outgoing function has no further need of RCU, so remove it from * the rcu_node tree's ->qsmaskinitnext bit masks. @@ -4117,6 +4116,7 @@ void rcu_report_dead(unsigned int cpu) rdp->cpu_started = false; } +#ifdef CONFIG_HOTPLUG_CPU /* * The outgoing CPU has just passed through the dying-idle state, and we * are being invoked from the CPU that was IPIed to continue the offline diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h index 0fde39b8daab..ca21d28a0f98 100644 --- a/kernel/rcu/tree_stall.h +++ b/kernel/rcu/tree_stall.h @@ -249,13 +249,16 @@ static bool check_slow_task(struct task_struct *t, void *arg) /* * Scan the current list of tasks blocked within RCU read-side critical - * sections, printing out the tid of each. + * sections, printing out the tid of each of the first few of them. */ -static int rcu_print_task_stall(struct rcu_node *rnp) +static int rcu_print_task_stall(struct rcu_node *rnp, unsigned long flags) + __releases(rnp->lock) { + int i = 0; int ndetected = 0; struct rcu_stall_chk_rdr rscr; struct task_struct *t; + struct task_struct *ts[8]; if (!rcu_preempt_blocked_readers_cgp(rnp)) return 0; @@ -264,6 +267,14 @@ static int rcu_print_task_stall(struct rcu_node *rnp) t = list_entry(rnp->gp_tasks->prev, struct task_struct, rcu_node_entry); list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) { + get_task_struct(t); + ts[i++] = t; + if (i >= ARRAY_SIZE(ts)) + break; + } + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + for (i--; i; i--) { + t = ts[i]; if (!try_invoke_on_locked_down_task(t, check_slow_task, &rscr)) pr_cont(" P%d", t->pid); else @@ -273,6 +284,7 @@ static int rcu_print_task_stall(struct rcu_node *rnp) ".q"[rscr.rs.b.need_qs], ".e"[rscr.rs.b.exp_hint], ".l"[rscr.on_blkd_list]); + put_task_struct(t); ndetected++; } pr_cont("\n"); @@ -293,8 +305,9 @@ static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp) * Because preemptible RCU does not exist, we never have to check for * tasks blocked within RCU read-side critical sections. */ -static int rcu_print_task_stall(struct rcu_node *rnp) +static int rcu_print_task_stall(struct rcu_node *rnp, unsigned long flags) { + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return 0; } #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ @@ -472,7 +485,6 @@ static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps) pr_err("INFO: %s detected stalls on CPUs/tasks:\n", rcu_state.name); rcu_for_each_leaf_node(rnp) { raw_spin_lock_irqsave_rcu_node(rnp, flags); - ndetected += rcu_print_task_stall(rnp); if (rnp->qsmask != 0) { for_each_leaf_node_possible_cpu(rnp, cpu) if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu)) { @@ -480,7 +492,7 @@ static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps) ndetected++; } } - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + ndetected += rcu_print_task_stall(rnp, flags); // Releases rnp->lock. } for_each_possible_cpu(cpu) diff --git a/kernel/reboot.c b/kernel/reboot.c index e7b78d5ae1ab..af6f23d8bea1 100644 --- a/kernel/reboot.c +++ b/kernel/reboot.c @@ -551,22 +551,22 @@ static int __init reboot_setup(char *str) break; case 's': - { - int rc; - - if (isdigit(*(str+1))) { - rc = kstrtoint(str+1, 0, &reboot_cpu); - if (rc) - return rc; - } else if (str[1] == 'm' && str[2] == 'p' && - isdigit(*(str+3))) { - rc = kstrtoint(str+3, 0, &reboot_cpu); - if (rc) - return rc; - } else + if (isdigit(*(str+1))) + reboot_cpu = simple_strtoul(str+1, NULL, 0); + else if (str[1] == 'm' && str[2] == 'p' && + isdigit(*(str+3))) + reboot_cpu = simple_strtoul(str+3, NULL, 0); + else *mode = REBOOT_SOFT; + if (reboot_cpu >= num_possible_cpus()) { + pr_err("Ignoring the CPU number in reboot= option. " + "CPU %d exceeds possible cpu number %d\n", + reboot_cpu, num_possible_cpus()); + reboot_cpu = 0; + break; + } break; - } + case 'g': *mode = REBOOT_GPIO; break; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index d2003a7d5ab5..e7e453492cff 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2501,7 +2501,12 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags, #ifdef CONFIG_SMP if (wake_flags & WF_MIGRATED) en_flags |= ENQUEUE_MIGRATED; + else #endif + if (p->in_iowait) { + delayacct_blkio_end(p); + atomic_dec(&task_rq(p)->nr_iowait); + } activate_task(rq, p, en_flags); ttwu_do_wakeup(rq, p, wake_flags, rf); @@ -2888,11 +2893,6 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) if (READ_ONCE(p->on_rq) && ttwu_runnable(p, wake_flags)) goto unlock; - if (p->in_iowait) { - delayacct_blkio_end(p); - atomic_dec(&task_rq(p)->nr_iowait); - } - #ifdef CONFIG_SMP /* * Ensure we load p->on_cpu _after_ p->on_rq, otherwise it would be @@ -2963,6 +2963,11 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags); if (task_cpu(p) != cpu) { + if (p->in_iowait) { + delayacct_blkio_end(p); + atomic_dec(&task_rq(p)->nr_iowait); + } + wake_flags |= WF_MIGRATED; psi_ttwu_dequeue(p); set_task_cpu(p, cpu); @@ -4907,20 +4912,21 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task) if (!dl_prio(p->normal_prio) || (pi_task && dl_prio(pi_task->prio) && dl_entity_preempt(&pi_task->dl, &p->dl))) { - p->dl.dl_boosted = 1; + p->dl.pi_se = pi_task->dl.pi_se; queue_flag |= ENQUEUE_REPLENISH; - } else - p->dl.dl_boosted = 0; + } else { + p->dl.pi_se = &p->dl; + } p->sched_class = &dl_sched_class; } else if (rt_prio(prio)) { if (dl_prio(oldprio)) - p->dl.dl_boosted = 0; + p->dl.pi_se = &p->dl; if (oldprio < prio) queue_flag |= ENQUEUE_HEAD; p->sched_class = &rt_sched_class; } else { if (dl_prio(oldprio)) - p->dl.dl_boosted = 0; + p->dl.pi_se = &p->dl; if (rt_prio(oldprio)) p->rt.timeout = 0; p->sched_class = &fair_sched_class; diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index c03a5775d019..97d318b0cd0c 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -102,9 +102,12 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time) static bool sugov_update_next_freq(struct sugov_policy *sg_policy, u64 time, unsigned int next_freq) { - if (sg_policy->next_freq == next_freq && - !cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS)) - return false; + if (!sg_policy->need_freq_update) { + if (sg_policy->next_freq == next_freq) + return false; + } else { + sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS); + } sg_policy->next_freq = next_freq; sg_policy->last_freq_update_time = time; @@ -162,11 +165,9 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy, freq = map_util_freq(util, freq, max); - if (freq == sg_policy->cached_raw_freq && !sg_policy->need_freq_update && - !cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS)) + if (freq == sg_policy->cached_raw_freq && !sg_policy->need_freq_update) return sg_policy->next_freq; - sg_policy->need_freq_update = false; sg_policy->cached_raw_freq = freq; return cpufreq_driver_resolve_freq(policy, freq); } @@ -442,7 +443,6 @@ static void sugov_update_single(struct update_util_data *hook, u64 time, struct sugov_policy *sg_policy = sg_cpu->sg_policy; unsigned long util, max; unsigned int next_f; - bool busy; unsigned int cached_freq = sg_policy->cached_raw_freq; sugov_iowait_boost(sg_cpu, time, flags); @@ -453,9 +453,6 @@ static void sugov_update_single(struct update_util_data *hook, u64 time, if (!sugov_should_update_freq(sg_policy, time)) return; - /* Limits may have changed, don't skip frequency update */ - busy = !sg_policy->need_freq_update && sugov_cpu_is_busy(sg_cpu); - util = sugov_get_util(sg_cpu); max = sg_cpu->max; util = sugov_iowait_apply(sg_cpu, time, util, max); @@ -464,7 +461,7 @@ static void sugov_update_single(struct update_util_data *hook, u64 time, * Do not reduce the frequency if the CPU has not been idle * recently, as the reduction is likely to be premature then. */ - if (busy && next_f < sg_policy->next_freq) { + if (sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq) { next_f = sg_policy->next_freq; /* Restore cached freq as next_freq has changed */ @@ -829,9 +826,10 @@ static int sugov_start(struct cpufreq_policy *policy) sg_policy->next_freq = 0; sg_policy->work_in_progress = false; sg_policy->limits_changed = false; - sg_policy->need_freq_update = false; sg_policy->cached_raw_freq = 0; + sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS); + for_each_cpu(cpu, policy->cpus) { struct sugov_cpu *sg_cpu = &per_cpu(sugov_cpu, cpu); @@ -883,7 +881,7 @@ static void sugov_limits(struct cpufreq_policy *policy) struct cpufreq_governor schedutil_gov = { .name = "schedutil", .owner = THIS_MODULE, - .dynamic_switching = true, + .flags = CPUFREQ_GOV_DYNAMIC_SWITCHING, .init = sugov_init, .exit = sugov_exit, .start = sugov_start, diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index f232305dcefe..1d3c97268ec0 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -43,6 +43,28 @@ static inline int on_dl_rq(struct sched_dl_entity *dl_se) return !RB_EMPTY_NODE(&dl_se->rb_node); } +#ifdef CONFIG_RT_MUTEXES +static inline struct sched_dl_entity *pi_of(struct sched_dl_entity *dl_se) +{ + return dl_se->pi_se; +} + +static inline bool is_dl_boosted(struct sched_dl_entity *dl_se) +{ + return pi_of(dl_se) != dl_se; +} +#else +static inline struct sched_dl_entity *pi_of(struct sched_dl_entity *dl_se) +{ + return dl_se; +} + +static inline bool is_dl_boosted(struct sched_dl_entity *dl_se) +{ + return false; +} +#endif + #ifdef CONFIG_SMP static inline struct dl_bw *dl_bw_of(int i) { @@ -698,7 +720,7 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se) struct dl_rq *dl_rq = dl_rq_of_se(dl_se); struct rq *rq = rq_of_dl_rq(dl_rq); - WARN_ON(dl_se->dl_boosted); + WARN_ON(is_dl_boosted(dl_se)); WARN_ON(dl_time_before(rq_clock(rq), dl_se->deadline)); /* @@ -736,21 +758,20 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se) * could happen are, typically, a entity voluntarily trying to overcome its * runtime, or it just underestimated it during sched_setattr(). */ -static void replenish_dl_entity(struct sched_dl_entity *dl_se, - struct sched_dl_entity *pi_se) +static void replenish_dl_entity(struct sched_dl_entity *dl_se) { struct dl_rq *dl_rq = dl_rq_of_se(dl_se); struct rq *rq = rq_of_dl_rq(dl_rq); - BUG_ON(pi_se->dl_runtime <= 0); + BUG_ON(pi_of(dl_se)->dl_runtime <= 0); /* * This could be the case for a !-dl task that is boosted. * Just go with full inherited parameters. */ if (dl_se->dl_deadline == 0) { - dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; - dl_se->runtime = pi_se->dl_runtime; + dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline; + dl_se->runtime = pi_of(dl_se)->dl_runtime; } if (dl_se->dl_yielded && dl_se->runtime > 0) @@ -763,8 +784,8 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se, * arbitrary large. */ while (dl_se->runtime <= 0) { - dl_se->deadline += pi_se->dl_period; - dl_se->runtime += pi_se->dl_runtime; + dl_se->deadline += pi_of(dl_se)->dl_period; + dl_se->runtime += pi_of(dl_se)->dl_runtime; } /* @@ -778,8 +799,8 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se, */ if (dl_time_before(dl_se->deadline, rq_clock(rq))) { printk_deferred_once("sched: DL replenish lagged too much\n"); - dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; - dl_se->runtime = pi_se->dl_runtime; + dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline; + dl_se->runtime = pi_of(dl_se)->dl_runtime; } if (dl_se->dl_yielded) @@ -812,8 +833,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se, * task with deadline equal to period this is the same of using * dl_period instead of dl_deadline in the equation above. */ -static bool dl_entity_overflow(struct sched_dl_entity *dl_se, - struct sched_dl_entity *pi_se, u64 t) +static bool dl_entity_overflow(struct sched_dl_entity *dl_se, u64 t) { u64 left, right; @@ -835,9 +855,9 @@ static bool dl_entity_overflow(struct sched_dl_entity *dl_se, * of anything below microseconds resolution is actually fiction * (but still we want to give the user that illusion >;). */ - left = (pi_se->dl_deadline >> DL_SCALE) * (dl_se->runtime >> DL_SCALE); + left = (pi_of(dl_se)->dl_deadline >> DL_SCALE) * (dl_se->runtime >> DL_SCALE); right = ((dl_se->deadline - t) >> DL_SCALE) * - (pi_se->dl_runtime >> DL_SCALE); + (pi_of(dl_se)->dl_runtime >> DL_SCALE); return dl_time_before(right, left); } @@ -922,24 +942,23 @@ static inline bool dl_is_implicit(struct sched_dl_entity *dl_se) * Please refer to the comments update_dl_revised_wakeup() function to find * more about the Revised CBS rule. */ -static void update_dl_entity(struct sched_dl_entity *dl_se, - struct sched_dl_entity *pi_se) +static void update_dl_entity(struct sched_dl_entity *dl_se) { struct dl_rq *dl_rq = dl_rq_of_se(dl_se); struct rq *rq = rq_of_dl_rq(dl_rq); if (dl_time_before(dl_se->deadline, rq_clock(rq)) || - dl_entity_overflow(dl_se, pi_se, rq_clock(rq))) { + dl_entity_overflow(dl_se, rq_clock(rq))) { if (unlikely(!dl_is_implicit(dl_se) && !dl_time_before(dl_se->deadline, rq_clock(rq)) && - !dl_se->dl_boosted)){ + !is_dl_boosted(dl_se))) { update_dl_revised_wakeup(dl_se, rq); return; } - dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; - dl_se->runtime = pi_se->dl_runtime; + dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline; + dl_se->runtime = pi_of(dl_se)->dl_runtime; } } @@ -1038,7 +1057,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) * The task might have been boosted by someone else and might be in the * boosting/deboosting path, its not throttled. */ - if (dl_se->dl_boosted) + if (is_dl_boosted(dl_se)) goto unlock; /* @@ -1066,7 +1085,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) * but do not enqueue -- wait for our wakeup to do that. */ if (!task_on_rq_queued(p)) { - replenish_dl_entity(dl_se, dl_se); + replenish_dl_entity(dl_se); goto unlock; } @@ -1156,7 +1175,7 @@ static inline void dl_check_constrained_dl(struct sched_dl_entity *dl_se) if (dl_time_before(dl_se->deadline, rq_clock(rq)) && dl_time_before(rq_clock(rq), dl_next_period(dl_se))) { - if (unlikely(dl_se->dl_boosted || !start_dl_timer(p))) + if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(p))) return; dl_se->dl_throttled = 1; if (dl_se->runtime > 0) @@ -1287,7 +1306,7 @@ throttle: dl_se->dl_overrun = 1; __dequeue_task_dl(rq, curr, 0); - if (unlikely(dl_se->dl_boosted || !start_dl_timer(curr))) + if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(curr))) enqueue_task_dl(rq, curr, ENQUEUE_REPLENISH); if (!is_leftmost(curr, &rq->dl)) @@ -1481,8 +1500,7 @@ static void __dequeue_dl_entity(struct sched_dl_entity *dl_se) } static void -enqueue_dl_entity(struct sched_dl_entity *dl_se, - struct sched_dl_entity *pi_se, int flags) +enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags) { BUG_ON(on_dl_rq(dl_se)); @@ -1493,9 +1511,9 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se, */ if (flags & ENQUEUE_WAKEUP) { task_contending(dl_se, flags); - update_dl_entity(dl_se, pi_se); + update_dl_entity(dl_se); } else if (flags & ENQUEUE_REPLENISH) { - replenish_dl_entity(dl_se, pi_se); + replenish_dl_entity(dl_se); } else if ((flags & ENQUEUE_RESTORE) && dl_time_before(dl_se->deadline, rq_clock(rq_of_dl_rq(dl_rq_of_se(dl_se))))) { @@ -1512,19 +1530,7 @@ static void dequeue_dl_entity(struct sched_dl_entity *dl_se) static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) { - struct task_struct *pi_task = rt_mutex_get_top_task(p); - struct sched_dl_entity *pi_se = &p->dl; - - /* - * Use the scheduling parameters of the top pi-waiter task if: - * - we have a top pi-waiter which is a SCHED_DEADLINE task AND - * - our dl_boosted is set (i.e. the pi-waiter's (absolute) deadline is - * smaller than our deadline OR we are a !SCHED_DEADLINE task getting - * boosted due to a SCHED_DEADLINE pi-waiter). - * Otherwise we keep our runtime and deadline. - */ - if (pi_task && dl_prio(pi_task->normal_prio) && p->dl.dl_boosted) { - pi_se = &pi_task->dl; + if (is_dl_boosted(&p->dl)) { /* * Because of delays in the detection of the overrun of a * thread's runtime, it might be the case that a thread @@ -1557,7 +1563,7 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) * the throttle. */ p->dl.dl_throttled = 0; - BUG_ON(!p->dl.dl_boosted || flags != ENQUEUE_REPLENISH); + BUG_ON(!is_dl_boosted(&p->dl) || flags != ENQUEUE_REPLENISH); return; } @@ -1594,7 +1600,7 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) return; } - enqueue_dl_entity(&p->dl, pi_se, flags); + enqueue_dl_entity(&p->dl, flags); if (!task_current(rq, p) && p->nr_cpus_allowed > 1) enqueue_pushable_dl_task(rq, p); @@ -2787,11 +2793,14 @@ void __dl_clear_params(struct task_struct *p) dl_se->dl_bw = 0; dl_se->dl_density = 0; - dl_se->dl_boosted = 0; dl_se->dl_throttled = 0; dl_se->dl_yielded = 0; dl_se->dl_non_contending = 0; dl_se->dl_overrun = 0; + +#ifdef CONFIG_RT_MUTEXES + dl_se->pi_se = dl_se; +#endif } bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr) diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 0655524700d2..2357921580f9 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -251,7 +251,7 @@ static int sd_ctl_doflags(struct ctl_table *table, int write, unsigned long flags = *(unsigned long *)table->data; size_t data_size = 0; size_t len = 0; - char *tmp; + char *tmp, *buf; int idx; if (write) @@ -269,17 +269,17 @@ static int sd_ctl_doflags(struct ctl_table *table, int write, return 0; } - tmp = kcalloc(data_size + 1, sizeof(*tmp), GFP_KERNEL); - if (!tmp) + buf = kcalloc(data_size + 1, sizeof(*buf), GFP_KERNEL); + if (!buf) return -ENOMEM; for_each_set_bit(idx, &flags, __SD_FLAG_CNT) { char *name = sd_flag_debug[idx].name; - len += snprintf(tmp + len, strlen(name) + 2, "%s ", name); + len += snprintf(buf + len, strlen(name) + 2, "%s ", name); } - tmp += *ppos; + tmp = buf + *ppos; len -= *ppos; if (len > *lenp) @@ -294,7 +294,7 @@ static int sd_ctl_doflags(struct ctl_table *table, int write, *lenp = len; *ppos += len; - kfree(tmp); + kfree(buf); return 0; } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 290f9e38378c..ae7ceba8fd4f 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5477,6 +5477,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) struct cfs_rq *cfs_rq; struct sched_entity *se = &p->se; int idle_h_nr_running = task_has_idle_policy(p); + int task_new = !(flags & ENQUEUE_WAKEUP); /* * The code below (indirectly) updates schedutil which looks at @@ -5549,7 +5550,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) * into account, but that is not straightforward to implement, * and the following generally works well enough in practice. */ - if (flags & ENQUEUE_WAKEUP) + if (!task_new) update_overutilized_status(rq); enqueue_throttle: @@ -6172,21 +6173,21 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t static int select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target) { - unsigned long best_cap = 0; + unsigned long task_util, best_cap = 0; int cpu, best_cpu = -1; struct cpumask *cpus; - sync_entity_load_avg(&p->se); - cpus = this_cpu_cpumask_var_ptr(select_idle_mask); cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr); + task_util = uclamp_task_util(p); + for_each_cpu_wrap(cpu, cpus, target) { unsigned long cpu_cap = capacity_of(cpu); if (!available_idle_cpu(cpu) && !sched_idle_cpu(cpu)) continue; - if (task_fits_capacity(p, cpu_cap)) + if (fits_capacity(task_util, cpu_cap)) return cpu; if (cpu_cap > best_cap) { @@ -6198,44 +6199,42 @@ select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target) return best_cpu; } +static inline bool asym_fits_capacity(int task_util, int cpu) +{ + if (static_branch_unlikely(&sched_asym_cpucapacity)) + return fits_capacity(task_util, capacity_of(cpu)); + + return true; +} + /* * Try and locate an idle core/thread in the LLC cache domain. */ static int select_idle_sibling(struct task_struct *p, int prev, int target) { struct sched_domain *sd; + unsigned long task_util; int i, recent_used_cpu; /* - * For asymmetric CPU capacity systems, our domain of interest is - * sd_asym_cpucapacity rather than sd_llc. + * On asymmetric system, update task utilization because we will check + * that the task fits with cpu's capacity. */ if (static_branch_unlikely(&sched_asym_cpucapacity)) { - sd = rcu_dereference(per_cpu(sd_asym_cpucapacity, target)); - /* - * On an asymmetric CPU capacity system where an exclusive - * cpuset defines a symmetric island (i.e. one unique - * capacity_orig value through the cpuset), the key will be set - * but the CPUs within that cpuset will not have a domain with - * SD_ASYM_CPUCAPACITY. These should follow the usual symmetric - * capacity path. - */ - if (!sd) - goto symmetric; - - i = select_idle_capacity(p, sd, target); - return ((unsigned)i < nr_cpumask_bits) ? i : target; + sync_entity_load_avg(&p->se); + task_util = uclamp_task_util(p); } -symmetric: - if (available_idle_cpu(target) || sched_idle_cpu(target)) + if ((available_idle_cpu(target) || sched_idle_cpu(target)) && + asym_fits_capacity(task_util, target)) return target; /* * If the previous CPU is cache affine and idle, don't be stupid: */ if (prev != target && cpus_share_cache(prev, target) && - (available_idle_cpu(prev) || sched_idle_cpu(prev))) + (available_idle_cpu(prev) || sched_idle_cpu(prev)) && + asym_fits_capacity(task_util, prev)) return prev; /* @@ -6258,7 +6257,8 @@ symmetric: recent_used_cpu != target && cpus_share_cache(recent_used_cpu, target) && (available_idle_cpu(recent_used_cpu) || sched_idle_cpu(recent_used_cpu)) && - cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr)) { + cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr) && + asym_fits_capacity(task_util, recent_used_cpu)) { /* * Replace recent_used_cpu with prev as it is a potential * candidate for the next wake: @@ -6267,6 +6267,26 @@ symmetric: return recent_used_cpu; } + /* + * For asymmetric CPU capacity systems, our domain of interest is + * sd_asym_cpucapacity rather than sd_llc. + */ + if (static_branch_unlikely(&sched_asym_cpucapacity)) { + sd = rcu_dereference(per_cpu(sd_asym_cpucapacity, target)); + /* + * On an asymmetric CPU capacity system where an exclusive + * cpuset defines a symmetric island (i.e. one unique + * capacity_orig value through the cpuset), the key will be set + * but the CPUs within that cpuset will not have a domain with + * SD_ASYM_CPUCAPACITY. These should follow the usual symmetric + * capacity path. + */ + if (sd) { + i = select_idle_capacity(p, sd, target); + return ((unsigned)i < nr_cpumask_bits) ? i : target; + } + } + sd = rcu_dereference(per_cpu(sd_llc, target)); if (!sd) return target; @@ -9031,7 +9051,8 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s * emptying busiest. */ if (local->group_type == group_has_spare) { - if (busiest->group_type > group_fully_busy) { + if ((busiest->group_type > group_fully_busy) && + !(env->sd->flags & SD_SHARE_PKG_RESOURCES)) { /* * If busiest is overloaded, try to fill spare * capacity. This might end up creating spare capacity diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 8ad7a293255a..53a7d1512dd7 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -38,7 +38,7 @@ #include <linux/filter.h> #include <linux/pid.h> #include <linux/ptrace.h> -#include <linux/security.h> +#include <linux/capability.h> #include <linux/tracehook.h> #include <linux/uaccess.h> #include <linux/anon_inodes.h> @@ -558,8 +558,7 @@ static struct seccomp_filter *seccomp_prepare_filter(struct sock_fprog *fprog) * behavior of privileged children. */ if (!task_no_new_privs(current) && - security_capable(current_cred(), current_user_ns(), - CAP_SYS_ADMIN, CAP_OPT_NOAUDIT) != 0) + !ns_capable_noaudit(current_user_ns(), CAP_SYS_ADMIN)) return ERR_PTR(-EACCES); /* Allocate a new seccomp_filter */ diff --git a/kernel/signal.c b/kernel/signal.c index a38b3edc6851..ef8f2a28d37c 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -391,16 +391,17 @@ static bool task_participate_group_stop(struct task_struct *task) void task_join_group_stop(struct task_struct *task) { + unsigned long mask = current->jobctl & JOBCTL_STOP_SIGMASK; + struct signal_struct *sig = current->signal; + + if (sig->group_stop_count) { + sig->group_stop_count++; + mask |= JOBCTL_STOP_CONSUME; + } else if (!(sig->flags & SIGNAL_STOP_STOPPED)) + return; + /* Have the new thread join an on-going signal group stop */ - unsigned long jobctl = current->jobctl; - if (jobctl & JOBCTL_STOP_PENDING) { - struct signal_struct *sig = current->signal; - unsigned long signr = jobctl & JOBCTL_STOP_SIGMASK; - unsigned long gstop = JOBCTL_STOP_PENDING | JOBCTL_STOP_CONSUME; - if (task_set_jobctl_pending(task, signr | gstop)) { - sig->group_stop_count++; - } - } + task_set_jobctl_pending(task, mask | JOBCTL_STOP_PENDING); } /* diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 4517c8b66518..048c655315f1 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -181,6 +181,16 @@ bpf_probe_read_user_str_common(void *dst, u32 size, { int ret; + /* + * NB: We rely on strncpy_from_user() not copying junk past the NUL + * terminator into `dst`. + * + * strncpy_from_user() does long-sized strides in the fast path. If the + * strncpy does not mask out the bytes after the NUL in `unsafe_ptr`, + * then there could be junk after the NUL in `dst`. If user takes `dst` + * and keys a hash map with it, then semantically identical strings can + * occupy multiple entries in the map. + */ ret = strncpy_from_user_nofault(dst, unsafe_ptr, size); if (unlikely(ret < 0)) memset(dst, 0, size); @@ -1198,7 +1208,7 @@ static int bpf_btf_printf_prepare(struct btf_ptr *ptr, u32 btf_ptr_size, *btf = bpf_get_btf_vmlinux(); if (IS_ERR_OR_NULL(*btf)) - return PTR_ERR(*btf); + return IS_ERR(*btf) ? PTR_ERR(*btf) : -EINVAL; if (ptr->type_id > 0) *btf_id = ptr->type_id; diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 7f45fd9d5a45..dc83b3fa9fe7 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -438,14 +438,16 @@ enum { }; /* * Used for which event context the event is in. - * NMI = 0 - * IRQ = 1 - * SOFTIRQ = 2 - * NORMAL = 3 + * TRANSITION = 0 + * NMI = 1 + * IRQ = 2 + * SOFTIRQ = 3 + * NORMAL = 4 * * See trace_recursive_lock() comment below for more details. */ enum { + RB_CTX_TRANSITION, RB_CTX_NMI, RB_CTX_IRQ, RB_CTX_SOFTIRQ, @@ -3014,10 +3016,10 @@ rb_wakeups(struct trace_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer) * a bit of overhead in something as critical as function tracing, * we use a bitmask trick. * - * bit 0 = NMI context - * bit 1 = IRQ context - * bit 2 = SoftIRQ context - * bit 3 = normal context. + * bit 1 = NMI context + * bit 2 = IRQ context + * bit 3 = SoftIRQ context + * bit 4 = normal context. * * This works because this is the order of contexts that can * preempt other contexts. A SoftIRQ never preempts an IRQ @@ -3040,6 +3042,30 @@ rb_wakeups(struct trace_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer) * The least significant bit can be cleared this way, and it * just so happens that it is the same bit corresponding to * the current context. + * + * Now the TRANSITION bit breaks the above slightly. The TRANSITION bit + * is set when a recursion is detected at the current context, and if + * the TRANSITION bit is already set, it will fail the recursion. + * This is needed because there's a lag between the changing of + * interrupt context and updating the preempt count. In this case, + * a false positive will be found. To handle this, one extra recursion + * is allowed, and this is done by the TRANSITION bit. If the TRANSITION + * bit is already set, then it is considered a recursion and the function + * ends. Otherwise, the TRANSITION bit is set, and that bit is returned. + * + * On the trace_recursive_unlock(), the TRANSITION bit will be the first + * to be cleared. Even if it wasn't the context that set it. That is, + * if an interrupt comes in while NORMAL bit is set and the ring buffer + * is called before preempt_count() is updated, since the check will + * be on the NORMAL bit, the TRANSITION bit will then be set. If an + * NMI then comes in, it will set the NMI bit, but when the NMI code + * does the trace_recursive_unlock() it will clear the TRANSTION bit + * and leave the NMI bit set. But this is fine, because the interrupt + * code that set the TRANSITION bit will then clear the NMI bit when it + * calls trace_recursive_unlock(). If another NMI comes in, it will + * set the TRANSITION bit and continue. + * + * Note: The TRANSITION bit only handles a single transition between context. */ static __always_inline int @@ -3055,8 +3081,16 @@ trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer) bit = pc & NMI_MASK ? RB_CTX_NMI : pc & HARDIRQ_MASK ? RB_CTX_IRQ : RB_CTX_SOFTIRQ; - if (unlikely(val & (1 << (bit + cpu_buffer->nest)))) - return 1; + if (unlikely(val & (1 << (bit + cpu_buffer->nest)))) { + /* + * It is possible that this was called by transitioning + * between interrupt context, and preempt_count() has not + * been updated yet. In this case, use the TRANSITION bit. + */ + bit = RB_CTX_TRANSITION; + if (val & (1 << (bit + cpu_buffer->nest))) + return 1; + } val |= (1 << (bit + cpu_buffer->nest)); cpu_buffer->current_context = val; @@ -3071,8 +3105,8 @@ trace_recursive_unlock(struct ring_buffer_per_cpu *cpu_buffer) cpu_buffer->current_context - (1 << cpu_buffer->nest); } -/* The recursive locking above uses 4 bits */ -#define NESTED_BITS 4 +/* The recursive locking above uses 5 bits */ +#define NESTED_BITS 5 /** * ring_buffer_nest_start - Allow to trace while nested diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 528971714fc6..410cfeb16db5 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2750,7 +2750,7 @@ trace_event_buffer_lock_reserve(struct trace_buffer **current_rb, /* * If tracing is off, but we have triggers enabled * we still need to look at the event data. Use the temp_buffer - * to store the trace event for the tigger to use. It's recusive + * to store the trace event for the trigger to use. It's recursive * safe and will not be recorded anywhere. */ if (!entry && trace_file->flags & EVENT_FILE_FL_TRIGGER_COND) { @@ -2952,7 +2952,7 @@ static void __ftrace_trace_stack(struct trace_buffer *buffer, stackidx = __this_cpu_inc_return(ftrace_stack_reserve) - 1; /* This should never happen. If it does, yell once and skip */ - if (WARN_ON_ONCE(stackidx > FTRACE_KSTACK_NESTING)) + if (WARN_ON_ONCE(stackidx >= FTRACE_KSTACK_NESTING)) goto out; /* @@ -3132,7 +3132,7 @@ static char *get_trace_buf(void) /* Interrupts must see nesting incremented before we use the buffer */ barrier(); - return &buffer->buffer[buffer->nesting][0]; + return &buffer->buffer[buffer->nesting - 1][0]; } static void put_trace_buf(void) diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index f3f5e77123ad..1dadef445cd1 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -637,6 +637,12 @@ enum { * function is called to clear it. */ TRACE_GRAPH_NOTRACE_BIT, + + /* + * When transitioning between context, the preempt_count() may + * not be correct. Allow for a single recursion to cover this case. + */ + TRACE_TRANSITION_BIT, }; #define trace_recursion_set(bit) do { (current)->trace_recursion |= (1<<(bit)); } while (0) @@ -691,14 +697,27 @@ static __always_inline int trace_test_and_set_recursion(int start, int max) return 0; bit = trace_get_context_bit() + start; - if (unlikely(val & (1 << bit))) - return -1; + if (unlikely(val & (1 << bit))) { + /* + * It could be that preempt_count has not been updated during + * a switch between contexts. Allow for a single recursion. + */ + bit = TRACE_TRANSITION_BIT; + if (trace_recursion_test(bit)) + return -1; + trace_recursion_set(bit); + barrier(); + return bit + 1; + } + + /* Normal check passed, clear the transition to allow it again */ + trace_recursion_clear(TRACE_TRANSITION_BIT); val |= 1 << bit; current->trace_recursion = val; barrier(); - return bit; + return bit + 1; } static __always_inline void trace_clear_recursion(int bit) @@ -708,6 +727,7 @@ static __always_inline void trace_clear_recursion(int bit) if (!bit) return; + bit--; bit = 1 << bit; val &= ~bit; diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c index 84b7cab55291..881df991742a 100644 --- a/kernel/trace/trace_events_synth.c +++ b/kernel/trace/trace_events_synth.c @@ -584,7 +584,7 @@ static struct synth_field *parse_synth_field(int argc, const char **argv, { struct synth_field *field; const char *prefix = NULL, *field_type = argv[0], *field_name, *array; - int len, ret = 0; + int len, ret = -ENOMEM; struct seq_buf s; ssize_t size; @@ -617,10 +617,9 @@ static struct synth_field *parse_synth_field(int argc, const char **argv, len--; field->name = kmemdup_nul(field_name, len, GFP_KERNEL); - if (!field->name) { - ret = -ENOMEM; + if (!field->name) goto free; - } + if (!is_good_name(field->name)) { synth_err(SYNTH_ERR_BAD_NAME, errpos(field_name)); ret = -EINVAL; @@ -638,10 +637,9 @@ static struct synth_field *parse_synth_field(int argc, const char **argv, len += strlen(prefix); field->type = kzalloc(len, GFP_KERNEL); - if (!field->type) { - ret = -ENOMEM; + if (!field->type) goto free; - } + seq_buf_init(&s, field->type, len); if (prefix) seq_buf_puts(&s, prefix); @@ -653,6 +651,7 @@ static struct synth_field *parse_synth_field(int argc, const char **argv, } if (WARN_ON_ONCE(!seq_buf_buffer_left(&s))) goto free; + s.buffer[s.len] = '\0'; size = synth_field_size(field->type); @@ -666,10 +665,8 @@ static struct synth_field *parse_synth_field(int argc, const char **argv, len = sizeof("__data_loc ") + strlen(field->type) + 1; type = kzalloc(len, GFP_KERNEL); - if (!type) { - ret = -ENOMEM; + if (!type) goto free; - } seq_buf_init(&s, type, len); seq_buf_puts(&s, "__data_loc "); diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index b5e3496cf803..4738ad48a667 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -492,8 +492,13 @@ trace_selftest_function_recursion(void) unregister_ftrace_function(&test_rec_probe); ret = -1; - if (trace_selftest_recursion_cnt != 1) { - pr_cont("*callback not called once (%d)* ", + /* + * Recursion allows for transitions between context, + * and may call the callback twice. + */ + if (trace_selftest_recursion_cnt != 1 && + trace_selftest_recursion_cnt != 2) { + pr_cont("*callback not called once (or twice) (%d)* ", trace_selftest_recursion_cnt); goto out; } diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 5abb5b22ad13..71109065bd8e 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -44,8 +44,6 @@ int __read_mostly soft_watchdog_user_enabled = 1; int __read_mostly watchdog_thresh = 10; static int __read_mostly nmi_watchdog_available; -static struct cpumask watchdog_allowed_mask __read_mostly; - struct cpumask watchdog_cpumask __read_mostly; unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask); @@ -162,6 +160,8 @@ static void lockup_detector_update_enable(void) int __read_mostly sysctl_softlockup_all_cpu_backtrace; #endif +static struct cpumask watchdog_allowed_mask __read_mostly; + /* Global variables, exported for sysctl */ unsigned int __read_mostly softlockup_panic = CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE; diff --git a/lib/crc32test.c b/lib/crc32test.c index 97d6a57cefcc..61ddce2cff77 100644 --- a/lib/crc32test.c +++ b/lib/crc32test.c @@ -683,7 +683,6 @@ static int __init crc32c_test(void) /* reduce OS noise */ local_irq_save(flags); - local_irq_disable(); nsec = ktime_get_ns(); for (i = 0; i < 100; i++) { @@ -694,7 +693,6 @@ static int __init crc32c_test(void) nsec = ktime_get_ns() - nsec; local_irq_restore(flags); - local_irq_enable(); pr_info("crc32c: CRC_LE_BITS = %d\n", CRC_LE_BITS); @@ -768,7 +766,6 @@ static int __init crc32_test(void) /* reduce OS noise */ local_irq_save(flags); - local_irq_disable(); nsec = ktime_get_ns(); for (i = 0; i < 100; i++) { @@ -783,7 +780,6 @@ static int __init crc32_test(void) nsec = ktime_get_ns() - nsec; local_irq_restore(flags); - local_irq_enable(); pr_info("crc32: CRC_LE_BITS = %d, CRC_BE BITS = %d\n", CRC_LE_BITS, CRC_BE_BITS); diff --git a/lib/strncpy_from_user.c b/lib/strncpy_from_user.c index e6d5fcc2cdf3..122d8d0e253c 100644 --- a/lib/strncpy_from_user.c +++ b/lib/strncpy_from_user.c @@ -35,17 +35,32 @@ static inline long do_strncpy_from_user(char *dst, const char __user *src, goto byte_at_a_time; while (max >= sizeof(unsigned long)) { - unsigned long c, data; + unsigned long c, data, mask; /* Fall back to byte-at-a-time if we get a page fault */ unsafe_get_user(c, (unsigned long __user *)(src+res), byte_at_a_time); - *(unsigned long *)(dst+res) = c; + /* + * Note that we mask out the bytes following the NUL. This is + * important to do because string oblivious code may read past + * the NUL. For those routines, we don't want to give them + * potentially random bytes after the NUL in `src`. + * + * One example of such code is BPF map keys. BPF treats map keys + * as an opaque set of bytes. Without the post-NUL mask, any BPF + * maps keyed by strings returned from strncpy_from_user() may + * have multiple entries for semantically identical strings. + */ if (has_zero(c, &data, &constants)) { data = prep_zero_mask(c, data, &constants); data = create_zero_mask(data); + mask = zero_bytemask(data); + *(unsigned long *)(dst+res) = c & mask; return res + find_zero(data); } + + *(unsigned long *)(dst+res) = c; + res += sizeof(unsigned long); max -= sizeof(unsigned long); } diff --git a/lib/test_kasan.c b/lib/test_kasan.c index 63c26171a791..662f862702fc 100644 --- a/lib/test_kasan.c +++ b/lib/test_kasan.c @@ -216,6 +216,12 @@ static void kmalloc_oob_16(struct kunit *test) u64 words[2]; } *ptr1, *ptr2; + /* This test is specifically crafted for the generic mode. */ + if (!IS_ENABLED(CONFIG_KASAN_GENERIC)) { + kunit_info(test, "CONFIG_KASAN_GENERIC required\n"); + return; + } + ptr1 = kmalloc(sizeof(*ptr1) - 3, GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr1); @@ -227,6 +233,23 @@ static void kmalloc_oob_16(struct kunit *test) kfree(ptr2); } +static void kmalloc_uaf_16(struct kunit *test) +{ + struct { + u64 words[2]; + } *ptr1, *ptr2; + + ptr1 = kmalloc(sizeof(*ptr1), GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr1); + + ptr2 = kmalloc(sizeof(*ptr2), GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr2); + kfree(ptr2); + + KUNIT_EXPECT_KASAN_FAIL(test, *ptr1 = *ptr2); + kfree(ptr1); +} + static void kmalloc_oob_memset_2(struct kunit *test) { char *ptr; @@ -429,6 +452,12 @@ static void kasan_global_oob(struct kunit *test) volatile int i = 3; char *p = &global_array[ARRAY_SIZE(global_array) + i]; + /* Only generic mode instruments globals. */ + if (!IS_ENABLED(CONFIG_KASAN_GENERIC)) { + kunit_info(test, "CONFIG_KASAN_GENERIC required"); + return; + } + KUNIT_EXPECT_KASAN_FAIL(test, *(volatile char *)p); } @@ -467,6 +496,12 @@ static void kasan_alloca_oob_left(struct kunit *test) char alloca_array[i]; char *p = alloca_array - 1; + /* Only generic mode instruments dynamic allocas. */ + if (!IS_ENABLED(CONFIG_KASAN_GENERIC)) { + kunit_info(test, "CONFIG_KASAN_GENERIC required"); + return; + } + if (!IS_ENABLED(CONFIG_KASAN_STACK)) { kunit_info(test, "CONFIG_KASAN_STACK is not enabled"); return; @@ -481,6 +516,12 @@ static void kasan_alloca_oob_right(struct kunit *test) char alloca_array[i]; char *p = alloca_array + i; + /* Only generic mode instruments dynamic allocas. */ + if (!IS_ENABLED(CONFIG_KASAN_GENERIC)) { + kunit_info(test, "CONFIG_KASAN_GENERIC required"); + return; + } + if (!IS_ENABLED(CONFIG_KASAN_STACK)) { kunit_info(test, "CONFIG_KASAN_STACK is not enabled"); return; @@ -551,6 +592,9 @@ static void kasan_memchr(struct kunit *test) return; } + if (OOB_TAG_OFF) + size = round_up(size, OOB_TAG_OFF); + ptr = kmalloc(size, GFP_KERNEL | __GFP_ZERO); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr); @@ -573,6 +617,9 @@ static void kasan_memcmp(struct kunit *test) return; } + if (OOB_TAG_OFF) + size = round_up(size, OOB_TAG_OFF); + ptr = kmalloc(size, GFP_KERNEL | __GFP_ZERO); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr); memset(arr, 0, sizeof(arr)); @@ -619,13 +666,50 @@ static void kasan_strings(struct kunit *test) KUNIT_EXPECT_KASAN_FAIL(test, kasan_int_result = strnlen(ptr, 1)); } -static void kasan_bitops(struct kunit *test) +static void kasan_bitops_modify(struct kunit *test, int nr, void *addr) +{ + KUNIT_EXPECT_KASAN_FAIL(test, set_bit(nr, addr)); + KUNIT_EXPECT_KASAN_FAIL(test, __set_bit(nr, addr)); + KUNIT_EXPECT_KASAN_FAIL(test, clear_bit(nr, addr)); + KUNIT_EXPECT_KASAN_FAIL(test, __clear_bit(nr, addr)); + KUNIT_EXPECT_KASAN_FAIL(test, clear_bit_unlock(nr, addr)); + KUNIT_EXPECT_KASAN_FAIL(test, __clear_bit_unlock(nr, addr)); + KUNIT_EXPECT_KASAN_FAIL(test, change_bit(nr, addr)); + KUNIT_EXPECT_KASAN_FAIL(test, __change_bit(nr, addr)); +} + +static void kasan_bitops_test_and_modify(struct kunit *test, int nr, void *addr) +{ + KUNIT_EXPECT_KASAN_FAIL(test, test_and_set_bit(nr, addr)); + KUNIT_EXPECT_KASAN_FAIL(test, __test_and_set_bit(nr, addr)); + KUNIT_EXPECT_KASAN_FAIL(test, test_and_set_bit_lock(nr, addr)); + KUNIT_EXPECT_KASAN_FAIL(test, test_and_clear_bit(nr, addr)); + KUNIT_EXPECT_KASAN_FAIL(test, __test_and_clear_bit(nr, addr)); + KUNIT_EXPECT_KASAN_FAIL(test, test_and_change_bit(nr, addr)); + KUNIT_EXPECT_KASAN_FAIL(test, __test_and_change_bit(nr, addr)); + KUNIT_EXPECT_KASAN_FAIL(test, kasan_int_result = test_bit(nr, addr)); + +#if defined(clear_bit_unlock_is_negative_byte) + KUNIT_EXPECT_KASAN_FAIL(test, kasan_int_result = + clear_bit_unlock_is_negative_byte(nr, addr)); +#endif +} + +static void kasan_bitops_generic(struct kunit *test) { + long *bits; + + /* This test is specifically crafted for the generic mode. */ + if (!IS_ENABLED(CONFIG_KASAN_GENERIC)) { + kunit_info(test, "CONFIG_KASAN_GENERIC required\n"); + return; + } + /* * Allocate 1 more byte, which causes kzalloc to round up to 16-bytes; * this way we do not actually corrupt other memory. */ - long *bits = kzalloc(sizeof(*bits) + 1, GFP_KERNEL); + bits = kzalloc(sizeof(*bits) + 1, GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, bits); /* @@ -633,55 +717,34 @@ static void kasan_bitops(struct kunit *test) * below accesses are still out-of-bounds, since bitops are defined to * operate on the whole long the bit is in. */ - KUNIT_EXPECT_KASAN_FAIL(test, set_bit(BITS_PER_LONG, bits)); - - KUNIT_EXPECT_KASAN_FAIL(test, __set_bit(BITS_PER_LONG, bits)); - - KUNIT_EXPECT_KASAN_FAIL(test, clear_bit(BITS_PER_LONG, bits)); - - KUNIT_EXPECT_KASAN_FAIL(test, __clear_bit(BITS_PER_LONG, bits)); - - KUNIT_EXPECT_KASAN_FAIL(test, clear_bit_unlock(BITS_PER_LONG, bits)); - - KUNIT_EXPECT_KASAN_FAIL(test, __clear_bit_unlock(BITS_PER_LONG, bits)); - - KUNIT_EXPECT_KASAN_FAIL(test, change_bit(BITS_PER_LONG, bits)); - - KUNIT_EXPECT_KASAN_FAIL(test, __change_bit(BITS_PER_LONG, bits)); + kasan_bitops_modify(test, BITS_PER_LONG, bits); /* * Below calls try to access bit beyond allocated memory. */ - KUNIT_EXPECT_KASAN_FAIL(test, - test_and_set_bit(BITS_PER_LONG + BITS_PER_BYTE, bits)); - - KUNIT_EXPECT_KASAN_FAIL(test, - __test_and_set_bit(BITS_PER_LONG + BITS_PER_BYTE, bits)); - - KUNIT_EXPECT_KASAN_FAIL(test, - test_and_set_bit_lock(BITS_PER_LONG + BITS_PER_BYTE, bits)); + kasan_bitops_test_and_modify(test, BITS_PER_LONG + BITS_PER_BYTE, bits); - KUNIT_EXPECT_KASAN_FAIL(test, - test_and_clear_bit(BITS_PER_LONG + BITS_PER_BYTE, bits)); + kfree(bits); +} - KUNIT_EXPECT_KASAN_FAIL(test, - __test_and_clear_bit(BITS_PER_LONG + BITS_PER_BYTE, bits)); +static void kasan_bitops_tags(struct kunit *test) +{ + long *bits; - KUNIT_EXPECT_KASAN_FAIL(test, - test_and_change_bit(BITS_PER_LONG + BITS_PER_BYTE, bits)); + /* This test is specifically crafted for the tag-based mode. */ + if (IS_ENABLED(CONFIG_KASAN_GENERIC)) { + kunit_info(test, "CONFIG_KASAN_SW_TAGS required\n"); + return; + } - KUNIT_EXPECT_KASAN_FAIL(test, - __test_and_change_bit(BITS_PER_LONG + BITS_PER_BYTE, bits)); + /* Allocation size will be rounded to up granule size, which is 16. */ + bits = kzalloc(sizeof(*bits), GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, bits); - KUNIT_EXPECT_KASAN_FAIL(test, - kasan_int_result = - test_bit(BITS_PER_LONG + BITS_PER_BYTE, bits)); + /* Do the accesses past the 16 allocated bytes. */ + kasan_bitops_modify(test, BITS_PER_LONG, &bits[1]); + kasan_bitops_test_and_modify(test, BITS_PER_LONG + BITS_PER_BYTE, &bits[1]); -#if defined(clear_bit_unlock_is_negative_byte) - KUNIT_EXPECT_KASAN_FAIL(test, - kasan_int_result = clear_bit_unlock_is_negative_byte( - BITS_PER_LONG + BITS_PER_BYTE, bits)); -#endif kfree(bits); } @@ -728,6 +791,7 @@ static struct kunit_case kasan_kunit_test_cases[] = { KUNIT_CASE(kmalloc_oob_krealloc_more), KUNIT_CASE(kmalloc_oob_krealloc_less), KUNIT_CASE(kmalloc_oob_16), + KUNIT_CASE(kmalloc_uaf_16), KUNIT_CASE(kmalloc_oob_in_memset), KUNIT_CASE(kmalloc_oob_memset_2), KUNIT_CASE(kmalloc_oob_memset_4), @@ -751,7 +815,8 @@ static struct kunit_case kasan_kunit_test_cases[] = { KUNIT_CASE(kasan_memchr), KUNIT_CASE(kasan_memcmp), KUNIT_CASE(kasan_strings), - KUNIT_CASE(kasan_bitops), + KUNIT_CASE(kasan_bitops_generic), + KUNIT_CASE(kasan_bitops_tags), KUNIT_CASE(kmalloc_double_kzfree), KUNIT_CASE(vmalloc_oob), {} diff --git a/mm/compaction.c b/mm/compaction.c index 6e0ee5641788..13cb7a961b31 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -817,6 +817,10 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, * delay for some time until fewer pages are isolated */ while (unlikely(too_many_isolated(pgdat))) { + /* stop isolation if there are still pages not migrated */ + if (cc->nr_migratepages) + return 0; + /* async migration should just abort */ if (cc->mode == MIGRATE_ASYNC) return 0; @@ -1012,8 +1016,8 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, isolate_success: list_add(&page->lru, &cc->migratepages); - cc->nr_migratepages++; - nr_isolated++; + cc->nr_migratepages += compound_nr(page); + nr_isolated += compound_nr(page); /* * Avoid isolating too much unless this block is being @@ -1021,7 +1025,7 @@ isolate_success: * or a lock is contended. For contention, isolate quickly to * potentially remove one source of contention. */ - if (cc->nr_migratepages == COMPACT_CLUSTER_MAX && + if (cc->nr_migratepages >= COMPACT_CLUSTER_MAX && !cc->rescan && !cc->contended) { ++low_pfn; break; @@ -1132,7 +1136,7 @@ isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn, if (!pfn) break; - if (cc->nr_migratepages == COMPACT_CLUSTER_MAX) + if (cc->nr_migratepages >= COMPACT_CLUSTER_MAX) break; } diff --git a/mm/filemap.c b/mm/filemap.c index d5e7c2029d16..3ebbe64a0106 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2347,10 +2347,15 @@ page_ok: page_not_up_to_date: /* Get exclusive access to the page ... */ - if (iocb->ki_flags & IOCB_WAITQ) + if (iocb->ki_flags & IOCB_WAITQ) { + if (written) { + put_page(page); + goto out; + } error = lock_page_async(page, iocb->ki_waitq); - else + } else { error = lock_page_killable(page); + } if (unlikely(error)) goto readpage_error; @@ -2393,10 +2398,15 @@ readpage: } if (!PageUptodate(page)) { - if (iocb->ki_flags & IOCB_WAITQ) + if (iocb->ki_flags & IOCB_WAITQ) { + if (written) { + put_page(page); + goto out; + } error = lock_page_async(page, iocb->ki_waitq); - else + } else { error = lock_page_killable(page); + } if (unlikely(error)) goto readpage_error; @@ -1647,8 +1647,11 @@ check_again: /* * drop the above get_user_pages reference. */ - for (i = 0; i < nr_pages; i++) - put_page(pages[i]); + if (gup_flags & FOLL_PIN) + unpin_user_pages(pages, nr_pages); + else + for (i = 0; i < nr_pages; i++) + put_page(pages[i]); if (migrate_pages(&cma_page_list, alloc_migration_target, NULL, (unsigned long)&mtc, MIGRATE_SYNC, MR_CONTIG_RANGE)) { @@ -1728,8 +1731,11 @@ static long __gup_longterm_locked(struct mm_struct *mm, goto out; if (check_dax_vmas(vmas_tmp, rc)) { - for (i = 0; i < rc; i++) - put_page(pages[i]); + if (gup_flags & FOLL_PIN) + unpin_user_pages(pages, rc); + else + for (i = 0; i < rc; i++) + put_page(pages[i]); rc = -EOPNOTSUPP; goto out; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 9474dbc150ed..ec2bb93f7431 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -710,7 +710,6 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) transparent_hugepage_use_zero_page()) { pgtable_t pgtable; struct page *zero_page; - bool set; vm_fault_t ret; pgtable = pte_alloc_one(vma->vm_mm); if (unlikely(!pgtable)) @@ -723,25 +722,25 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) } vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); ret = 0; - set = false; if (pmd_none(*vmf->pmd)) { ret = check_stable_address_space(vma->vm_mm); if (ret) { spin_unlock(vmf->ptl); + pte_free(vma->vm_mm, pgtable); } else if (userfaultfd_missing(vma)) { spin_unlock(vmf->ptl); + pte_free(vma->vm_mm, pgtable); ret = handle_userfault(vmf, VM_UFFD_MISSING); VM_BUG_ON(ret & VM_FAULT_FALLBACK); } else { set_huge_zero_page(pgtable, vma->vm_mm, vma, haddr, vmf->pmd, zero_page); spin_unlock(vmf->ptl); - set = true; } - } else + } else { spin_unlock(vmf->ptl); - if (!set) pte_free(vma->vm_mm, pgtable); + } return ret; } gfp = alloc_hugepage_direct_gfpmask(vma); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index fe76f8fd5a73..37f15c3c24dc 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -648,6 +648,8 @@ retry: } del += t - f; + hugetlb_cgroup_uncharge_file_region( + resv, rg, t - f); /* New entry for end of split region */ nrg->from = t; @@ -660,9 +662,6 @@ retry: /* Original entry is trimmed */ rg->to = f; - hugetlb_cgroup_uncharge_file_region( - resv, rg, nrg->to - nrg->from); - list_add(&nrg->link, &rg->link); nrg = NULL; break; @@ -678,17 +677,17 @@ retry: } if (f <= rg->from) { /* Trim beginning of region */ - del += t - rg->from; - rg->from = t; - hugetlb_cgroup_uncharge_file_region(resv, rg, t - rg->from); - } else { /* Trim end of region */ - del += rg->to - f; - rg->to = f; + del += t - rg->from; + rg->from = t; + } else { /* Trim end of region */ hugetlb_cgroup_uncharge_file_region(resv, rg, rg->to - f); + + del += rg->to - f; + rg->to = f; } } @@ -1569,103 +1568,23 @@ int PageHeadHuge(struct page *page_head) } /* - * Find address_space associated with hugetlbfs page. - * Upon entry page is locked and page 'was' mapped although mapped state - * could change. If necessary, use anon_vma to find vma and associated - * address space. The returned mapping may be stale, but it can not be - * invalid as page lock (which is held) is required to destroy mapping. - */ -static struct address_space *_get_hugetlb_page_mapping(struct page *hpage) -{ - struct anon_vma *anon_vma; - pgoff_t pgoff_start, pgoff_end; - struct anon_vma_chain *avc; - struct address_space *mapping = page_mapping(hpage); - - /* Simple file based mapping */ - if (mapping) - return mapping; - - /* - * Even anonymous hugetlbfs mappings are associated with an - * underlying hugetlbfs file (see hugetlb_file_setup in mmap - * code). Find a vma associated with the anonymous vma, and - * use the file pointer to get address_space. - */ - anon_vma = page_lock_anon_vma_read(hpage); - if (!anon_vma) - return mapping; /* NULL */ - - /* Use first found vma */ - pgoff_start = page_to_pgoff(hpage); - pgoff_end = pgoff_start + pages_per_huge_page(page_hstate(hpage)) - 1; - anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, - pgoff_start, pgoff_end) { - struct vm_area_struct *vma = avc->vma; - - mapping = vma->vm_file->f_mapping; - break; - } - - anon_vma_unlock_read(anon_vma); - return mapping; -} - -/* * Find and lock address space (mapping) in write mode. * - * Upon entry, the page is locked which allows us to find the mapping - * even in the case of an anon page. However, locking order dictates - * the i_mmap_rwsem be acquired BEFORE the page lock. This is hugetlbfs - * specific. So, we first try to lock the sema while still holding the - * page lock. If this works, great! If not, then we need to drop the - * page lock and then acquire i_mmap_rwsem and reacquire page lock. Of - * course, need to revalidate state along the way. + * Upon entry, the page is locked which means that page_mapping() is + * stable. Due to locking order, we can only trylock_write. If we can + * not get the lock, simply return NULL to caller. */ struct address_space *hugetlb_page_mapping_lock_write(struct page *hpage) { - struct address_space *mapping, *mapping2; + struct address_space *mapping = page_mapping(hpage); - mapping = _get_hugetlb_page_mapping(hpage); -retry: if (!mapping) return mapping; - /* - * If no contention, take lock and return - */ if (i_mmap_trylock_write(mapping)) return mapping; - /* - * Must drop page lock and wait on mapping sema. - * Note: Once page lock is dropped, mapping could become invalid. - * As a hack, increase map count until we lock page again. - */ - atomic_inc(&hpage->_mapcount); - unlock_page(hpage); - i_mmap_lock_write(mapping); - lock_page(hpage); - atomic_add_negative(-1, &hpage->_mapcount); - - /* verify page is still mapped */ - if (!page_mapped(hpage)) { - i_mmap_unlock_write(mapping); - return NULL; - } - - /* - * Get address space again and verify it is the same one - * we locked. If not, drop lock and retry. - */ - mapping2 = _get_hugetlb_page_mapping(hpage); - if (mapping2 != mapping) { - i_mmap_unlock_write(mapping); - mapping = mapping2; - goto retry; - } - - return mapping; + return NULL; } pgoff_t __basepage_index(struct page *page) @@ -2443,6 +2362,9 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, rsv_adjust = hugepage_subpool_put_pages(spool, 1); hugetlb_acct_memory(h, -rsv_adjust); + if (deferred_reserve) + hugetlb_cgroup_uncharge_page_rsvd(hstate_index(h), + pages_per_huge_page(h), page); } return page; diff --git a/mm/madvise.c b/mm/madvise.c index 416a56b8e757..a8d8d48a57fe 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -226,7 +226,7 @@ static void force_shm_swapin_readahead(struct vm_area_struct *vma, struct address_space *mapping) { XA_STATE(xas, &mapping->i_pages, linear_page_index(vma, start)); - pgoff_t end_index = end / PAGE_SIZE; + pgoff_t end_index = linear_page_index(vma, end + PAGE_SIZE - 1); struct page *page; rcu_read_lock(); @@ -1231,8 +1231,6 @@ SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec, ret = total_len - iov_iter_count(&iter); mmput(mm); - return ret; - release_task: put_task_struct(task); put_pid: diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 3a24e3b619f5..29459a6ce1c7 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -867,8 +867,13 @@ void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val) rcu_read_lock(); memcg = mem_cgroup_from_obj(p); - /* Untracked pages have no memcg, no lruvec. Update only the node */ - if (!memcg || memcg == root_mem_cgroup) { + /* + * Untracked pages have no memcg, no lruvec. Update only the + * node. If we reparent the slab objects to the root memcg, + * when we free the slab object, we need to update the per-memcg + * vmstats to keep it correct for the root memcg. + */ + if (!memcg) { __mod_node_page_state(pgdat, idx, val); } else { lruvec = mem_cgroup_lruvec(memcg, pgdat); @@ -4110,11 +4115,17 @@ static int memcg_stat_show(struct seq_file *m, void *v) (u64)memsw * PAGE_SIZE); for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) { + unsigned long nr; + if (memcg1_stats[i] == MEMCG_SWAP && !do_memsw_account()) continue; + nr = memcg_page_state(memcg, memcg1_stats[i]); +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + if (memcg1_stats[i] == NR_ANON_THPS) + nr *= HPAGE_PMD_NR; +#endif seq_printf(m, "total_%s %llu\n", memcg1_stat_names[i], - (u64)memcg_page_state(memcg, memcg1_stats[i]) * - PAGE_SIZE); + (u64)nr * PAGE_SIZE); } for (i = 0; i < ARRAY_SIZE(memcg1_events); i++) @@ -5339,17 +5350,22 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) memcg->swappiness = mem_cgroup_swappiness(parent); memcg->oom_kill_disable = parent->oom_kill_disable; } - if (parent && parent->use_hierarchy) { + if (!parent) { + page_counter_init(&memcg->memory, NULL); + page_counter_init(&memcg->swap, NULL); + page_counter_init(&memcg->kmem, NULL); + page_counter_init(&memcg->tcpmem, NULL); + } else if (parent->use_hierarchy) { memcg->use_hierarchy = true; page_counter_init(&memcg->memory, &parent->memory); page_counter_init(&memcg->swap, &parent->swap); page_counter_init(&memcg->kmem, &parent->kmem); page_counter_init(&memcg->tcpmem, &parent->tcpmem); } else { - page_counter_init(&memcg->memory, NULL); - page_counter_init(&memcg->swap, NULL); - page_counter_init(&memcg->kmem, NULL); - page_counter_init(&memcg->tcpmem, NULL); + page_counter_init(&memcg->memory, &root_mem_cgroup->memory); + page_counter_init(&memcg->swap, &root_mem_cgroup->swap); + page_counter_init(&memcg->kmem, &root_mem_cgroup->kmem); + page_counter_init(&memcg->tcpmem, &root_mem_cgroup->tcpmem); /* * Deeper hierachy with use_hierarchy == false doesn't make * much sense so let cgroup subsystem know about this diff --git a/mm/memory-failure.c b/mm/memory-failure.c index c0bb186bba62..5d880d4eb9a2 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1057,27 +1057,25 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, if (!PageHuge(hpage)) { unmap_success = try_to_unmap(hpage, ttu); } else { - /* - * For hugetlb pages, try_to_unmap could potentially call - * huge_pmd_unshare. Because of this, take semaphore in - * write mode here and set TTU_RMAP_LOCKED to indicate we - * have taken the lock at this higer level. - * - * Note that the call to hugetlb_page_mapping_lock_write - * is necessary even if mapping is already set. It handles - * ugliness of potentially having to drop page lock to obtain - * i_mmap_rwsem. - */ - mapping = hugetlb_page_mapping_lock_write(hpage); - - if (mapping) { - unmap_success = try_to_unmap(hpage, + if (!PageAnon(hpage)) { + /* + * For hugetlb pages in shared mappings, try_to_unmap + * could potentially call huge_pmd_unshare. Because of + * this, take semaphore in write mode here and set + * TTU_RMAP_LOCKED to indicate we have taken the lock + * at this higer level. + */ + mapping = hugetlb_page_mapping_lock_write(hpage); + if (mapping) { + unmap_success = try_to_unmap(hpage, ttu|TTU_RMAP_LOCKED); - i_mmap_unlock_write(mapping); + i_mmap_unlock_write(mapping); + } else { + pr_info("Memory failure: %#lx: could not lock mapping for mapped huge page\n", pfn); + unmap_success = false; + } } else { - pr_info("Memory failure: %#lx: could not find mapping for mapped huge page\n", - pfn); - unmap_success = false; + unmap_success = try_to_unmap(hpage, ttu); } } if (!unmap_success) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index b44d4c7ba73b..63b2e46b6555 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -350,24 +350,6 @@ int __ref __add_pages(int nid, unsigned long pfn, unsigned long nr_pages, return err; } -#ifdef CONFIG_NUMA -int __weak memory_add_physaddr_to_nid(u64 start) -{ - pr_info_once("Unknown online node for memory at 0x%llx, assuming node 0\n", - start); - return 0; -} -EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); - -int __weak phys_to_target_node(u64 start) -{ - pr_info_once("Unknown target node for memory at 0x%llx, assuming node 0\n", - start); - return 0; -} -EXPORT_SYMBOL_GPL(phys_to_target_node); -#endif - /* find the smallest valid pfn in the range [start_pfn, end_pfn) */ static unsigned long find_smallest_section_pfn(int nid, struct zone *zone, unsigned long start_pfn, diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 3fde772ef5ef..3ca4898f3f24 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -525,7 +525,7 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, unsigned long flags = qp->flags; int ret; bool has_unmovable = false; - pte_t *pte; + pte_t *pte, *mapped_pte; spinlock_t *ptl; ptl = pmd_trans_huge_lock(pmd, vma); @@ -539,7 +539,7 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, if (pmd_trans_unstable(pmd)) return 0; - pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); + mapped_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); for (; addr != end; pte++, addr += PAGE_SIZE) { if (!pte_present(*pte)) continue; @@ -571,7 +571,7 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, } else break; } - pte_unmap_unlock(pte - 1, ptl); + pte_unmap_unlock(mapped_pte, ptl); cond_resched(); if (has_unmovable) diff --git a/mm/memremap.c b/mm/memremap.c index 73a206d0f645..16b2fb482da1 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -41,28 +41,24 @@ EXPORT_SYMBOL_GPL(memremap_compat_align); DEFINE_STATIC_KEY_FALSE(devmap_managed_key); EXPORT_SYMBOL(devmap_managed_key); -static void devmap_managed_enable_put(void) +static void devmap_managed_enable_put(struct dev_pagemap *pgmap) { - static_branch_dec(&devmap_managed_key); + if (pgmap->type == MEMORY_DEVICE_PRIVATE || + pgmap->type == MEMORY_DEVICE_FS_DAX) + static_branch_dec(&devmap_managed_key); } -static int devmap_managed_enable_get(struct dev_pagemap *pgmap) +static void devmap_managed_enable_get(struct dev_pagemap *pgmap) { - if (pgmap->type == MEMORY_DEVICE_PRIVATE && - (!pgmap->ops || !pgmap->ops->page_free)) { - WARN(1, "Missing page_free method\n"); - return -EINVAL; - } - - static_branch_inc(&devmap_managed_key); - return 0; + if (pgmap->type == MEMORY_DEVICE_PRIVATE || + pgmap->type == MEMORY_DEVICE_FS_DAX) + static_branch_inc(&devmap_managed_key); } #else -static int devmap_managed_enable_get(struct dev_pagemap *pgmap) +static void devmap_managed_enable_get(struct dev_pagemap *pgmap) { - return -EINVAL; } -static void devmap_managed_enable_put(void) +static void devmap_managed_enable_put(struct dev_pagemap *pgmap) { } #endif /* CONFIG_DEV_PAGEMAP_OPS */ @@ -169,7 +165,7 @@ void memunmap_pages(struct dev_pagemap *pgmap) pageunmap_range(pgmap, i); WARN_ONCE(pgmap->altmap.alloc, "failed to free all reserved pages\n"); - devmap_managed_enable_put(); + devmap_managed_enable_put(pgmap); } EXPORT_SYMBOL_GPL(memunmap_pages); @@ -307,7 +303,6 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid) .pgprot = PAGE_KERNEL, }; const int nr_range = pgmap->nr_range; - bool need_devmap_managed = true; int error, i; if (WARN_ONCE(!nr_range, "nr_range must be specified\n")) @@ -323,6 +318,10 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid) WARN(1, "Missing migrate_to_ram method\n"); return ERR_PTR(-EINVAL); } + if (!pgmap->ops->page_free) { + WARN(1, "Missing page_free method\n"); + return ERR_PTR(-EINVAL); + } if (!pgmap->owner) { WARN(1, "Missing owner\n"); return ERR_PTR(-EINVAL); @@ -336,11 +335,9 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid) } break; case MEMORY_DEVICE_GENERIC: - need_devmap_managed = false; break; case MEMORY_DEVICE_PCI_P2PDMA: params.pgprot = pgprot_noncached(params.pgprot); - need_devmap_managed = false; break; default: WARN(1, "Invalid pgmap type %d\n", pgmap->type); @@ -364,11 +361,7 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid) } } - if (need_devmap_managed) { - error = devmap_managed_enable_get(pgmap); - if (error) - return ERR_PTR(error); - } + devmap_managed_enable_get(pgmap); /* * Clear the pgmap nr_range as it will be incremented for each diff --git a/mm/migrate.c b/mm/migrate.c index 5ca5842df5db..5795cb82e27c 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1328,34 +1328,38 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, goto put_anon; if (page_mapped(hpage)) { - /* - * try_to_unmap could potentially call huge_pmd_unshare. - * Because of this, take semaphore in write mode here and - * set TTU_RMAP_LOCKED to let lower levels know we have - * taken the lock. - */ - mapping = hugetlb_page_mapping_lock_write(hpage); - if (unlikely(!mapping)) - goto unlock_put_anon; + bool mapping_locked = false; + enum ttu_flags ttu = TTU_MIGRATION|TTU_IGNORE_MLOCK| + TTU_IGNORE_ACCESS; + + if (!PageAnon(hpage)) { + /* + * In shared mappings, try_to_unmap could potentially + * call huge_pmd_unshare. Because of this, take + * semaphore in write mode here and set TTU_RMAP_LOCKED + * to let lower levels know we have taken the lock. + */ + mapping = hugetlb_page_mapping_lock_write(hpage); + if (unlikely(!mapping)) + goto unlock_put_anon; + + mapping_locked = true; + ttu |= TTU_RMAP_LOCKED; + } - try_to_unmap(hpage, - TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS| - TTU_RMAP_LOCKED); + try_to_unmap(hpage, ttu); page_was_mapped = 1; - /* - * Leave mapping locked until after subsequent call to - * remove_migration_ptes() - */ + + if (mapping_locked) + i_mmap_unlock_write(mapping); } if (!page_mapped(hpage)) rc = move_to_new_page(new_hpage, hpage, mode); - if (page_was_mapped) { + if (page_was_mapped) remove_migration_ptes(hpage, - rc == MIGRATEPAGE_SUCCESS ? new_hpage : hpage, true); - i_mmap_unlock_write(mapping); - } + rc == MIGRATEPAGE_SUCCESS ? new_hpage : hpage, false); unlock_put_anon: unlock_page(new_hpage); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 23f5066bd4a5..eaa227a479e4 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5103,6 +5103,11 @@ refill: if (!page_ref_sub_and_test(page, nc->pagecnt_bias)) goto refill; + if (unlikely(nc->pfmemalloc)) { + free_the_page(page, compound_order(page)); + goto refill; + } + #if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) /* if size can vary use size else just use PAGE_SIZE */ size = nc->size; diff --git a/mm/percpu.c b/mm/percpu.c index 66a93f096394..ad7a37ee74ef 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -1315,8 +1315,8 @@ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr, region_size = ALIGN(start_offset + map_size, lcm_align); /* allocate chunk */ - alloc_size = sizeof(struct pcpu_chunk) + - BITS_TO_LONGS(region_size >> PAGE_SHIFT) * sizeof(unsigned long); + alloc_size = struct_size(chunk, populated, + BITS_TO_LONGS(region_size >> PAGE_SHIFT)); chunk = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!chunk) panic("%s: Failed to allocate %zu bytes\n", __func__, @@ -2521,8 +2521,8 @@ void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, pcpu_unit_pages = ai->unit_size >> PAGE_SHIFT; pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT; pcpu_atom_size = ai->atom_size; - pcpu_chunk_struct_size = sizeof(struct pcpu_chunk) + - BITS_TO_LONGS(pcpu_unit_pages) * sizeof(unsigned long); + pcpu_chunk_struct_size = struct_size(chunk, populated, + BITS_TO_LONGS(pcpu_unit_pages)); pcpu_stats_save_ai(ai); diff --git a/mm/rmap.c b/mm/rmap.c index 1b84945d655c..31b29321adfe 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1413,9 +1413,6 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, /* * If sharing is possible, start and end will be adjusted * accordingly. - * - * If called for a huge page, caller must hold i_mmap_rwsem - * in write mode as it is possible to call huge_pmd_unshare. */ adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); @@ -1462,7 +1459,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte); address = pvmw.address; - if (PageHuge(page)) { + if (PageHuge(page) && !PageAnon(page)) { /* * To call huge_pmd_unshare, i_mmap_rwsem must be * held in write mode. Caller needs to explicitly diff --git a/mm/slub.c b/mm/slub.c index b30be2385d1c..34dcc09e2ec9 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2852,7 +2852,7 @@ redo: object = c->freelist; page = c->page; - if (unlikely(!object || !node_match(page, node))) { + if (unlikely(!object || !page || !node_match(page, node))) { object = __slab_alloc(s, gfpflags, node, addr, c); } else { void *next_object = get_freepointer_safe(s, object); diff --git a/mm/truncate.c b/mm/truncate.c index 18cec39a9f53..960edf5803ca 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -528,7 +528,7 @@ void truncate_inode_pages_final(struct address_space *mapping) } EXPORT_SYMBOL(truncate_inode_pages_final); -unsigned long __invalidate_mapping_pages(struct address_space *mapping, +static unsigned long __invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end, unsigned long *nr_pagevec) { pgoff_t indices[PAGEVEC_SIZE]; diff --git a/mm/vmscan.c b/mm/vmscan.c index 1b8f0e059767..7b4e31eac2cf 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1516,7 +1516,8 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone, nr_reclaimed = shrink_page_list(&clean_pages, zone->zone_pgdat, &sc, TTU_IGNORE_ACCESS, &stat, true); list_splice(&clean_pages, page_list); - mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -nr_reclaimed); + mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, + -(long)nr_reclaimed); /* * Since lazyfree pages are isolated from file LRU from the beginning, * they will rotate back to anonymous LRU in the end if it failed to @@ -1526,7 +1527,7 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone, mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_ANON, stat.nr_lazyfree_fail); mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, - -stat.nr_lazyfree_fail); + -(long)stat.nr_lazyfree_fail); return nr_reclaimed; } diff --git a/net/atm/lec.c b/net/atm/lec.c index dbabb65d8b67..7226c784dbe0 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -954,9 +954,8 @@ static void *lec_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct lec_state *state = seq->private; - v = lec_get_idx(state, 1); - *pos += !!PTR_ERR(v); - return v; + ++*pos; + return lec_get_idx(state, 1); } static int lec_seq_show(struct seq_file *seq, void *v) diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 6f742fee874a..7730c8f3cb53 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -207,6 +207,7 @@ static void br_get_stats64(struct net_device *dev, { struct net_bridge *br = netdev_priv(dev); + netdev_stats_to_stats64(stats, &dev->stats); dev_fetch_sw_netstats(stats, br->stats); } diff --git a/net/can/Kconfig b/net/can/Kconfig index 224e5e0283a9..7c9958df91d3 100644 --- a/net/can/Kconfig +++ b/net/can/Kconfig @@ -62,8 +62,9 @@ config CAN_ISOTP communication between CAN nodes via two defined CAN Identifiers. As CAN frames can only transport a small amount of data bytes (max. 8 bytes for 'classic' CAN and max. 64 bytes for CAN FD) this - segmentation is needed to transport longer PDUs as needed e.g. for - vehicle diagnosis (UDS, ISO 14229) or IP-over-CAN traffic. + segmentation is needed to transport longer Protocol Data Units (PDU) + as needed e.g. for vehicle diagnosis (UDS, ISO 14229) or IP-over-CAN + traffic. This protocol driver implements data transfers according to ISO 15765-2:2016 for 'classic' CAN and CAN FD frame types. If you want to perform automotive vehicle diagnostic services (UDS), diff --git a/net/can/af_can.c b/net/can/af_can.c index 6373ab9c5507..5d124c155904 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -677,16 +677,25 @@ static int can_rcv(struct sk_buff *skb, struct net_device *dev, { struct canfd_frame *cfd = (struct canfd_frame *)skb->data; - if (unlikely(dev->type != ARPHRD_CAN || skb->len != CAN_MTU || - cfd->len > CAN_MAX_DLEN)) { - pr_warn_once("PF_CAN: dropped non conform CAN skbuf: dev type %d, len %d, datalen %d\n", + if (unlikely(dev->type != ARPHRD_CAN || skb->len != CAN_MTU)) { + pr_warn_once("PF_CAN: dropped non conform CAN skbuff: dev type %d, len %d\n", + dev->type, skb->len); + goto free_skb; + } + + /* This check is made separately since cfd->len would be uninitialized if skb->len = 0. */ + if (unlikely(cfd->len > CAN_MAX_DLEN)) { + pr_warn_once("PF_CAN: dropped non conform CAN skbuff: dev type %d, len %d, datalen %d\n", dev->type, skb->len, cfd->len); - kfree_skb(skb); - return NET_RX_DROP; + goto free_skb; } can_receive(skb, dev); return NET_RX_SUCCESS; + +free_skb: + kfree_skb(skb); + return NET_RX_DROP; } static int canfd_rcv(struct sk_buff *skb, struct net_device *dev, @@ -694,16 +703,25 @@ static int canfd_rcv(struct sk_buff *skb, struct net_device *dev, { struct canfd_frame *cfd = (struct canfd_frame *)skb->data; - if (unlikely(dev->type != ARPHRD_CAN || skb->len != CANFD_MTU || - cfd->len > CANFD_MAX_DLEN)) { - pr_warn_once("PF_CAN: dropped non conform CAN FD skbuf: dev type %d, len %d, datalen %d\n", + if (unlikely(dev->type != ARPHRD_CAN || skb->len != CANFD_MTU)) { + pr_warn_once("PF_CAN: dropped non conform CAN FD skbuff: dev type %d, len %d\n", + dev->type, skb->len); + goto free_skb; + } + + /* This check is made separately since cfd->len would be uninitialized if skb->len = 0. */ + if (unlikely(cfd->len > CANFD_MAX_DLEN)) { + pr_warn_once("PF_CAN: dropped non conform CAN FD skbuff: dev type %d, len %d, datalen %d\n", dev->type, skb->len, cfd->len); - kfree_skb(skb); - return NET_RX_DROP; + goto free_skb; } can_receive(skb, dev); return NET_RX_SUCCESS; + +free_skb: + kfree_skb(skb); + return NET_RX_DROP; } /* af_can protocol functions */ diff --git a/net/can/isotp.c b/net/can/isotp.c index 4c2062875893..d78ab13bd8be 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -252,14 +252,16 @@ static void isotp_rcv_skb(struct sk_buff *skb, struct sock *sk) static u8 padlen(u8 datalen) { - const u8 plen[] = {8, 8, 8, 8, 8, 8, 8, 8, 8, /* 0 - 8 */ - 12, 12, 12, 12, /* 9 - 12 */ - 16, 16, 16, 16, /* 13 - 16 */ - 20, 20, 20, 20, /* 17 - 20 */ - 24, 24, 24, 24, /* 21 - 24 */ - 32, 32, 32, 32, 32, 32, 32, 32, /* 25 - 32 */ - 48, 48, 48, 48, 48, 48, 48, 48, /* 33 - 40 */ - 48, 48, 48, 48, 48, 48, 48, 48}; /* 41 - 48 */ + static const u8 plen[] = { + 8, 8, 8, 8, 8, 8, 8, 8, 8, /* 0 - 8 */ + 12, 12, 12, 12, /* 9 - 12 */ + 16, 16, 16, 16, /* 13 - 16 */ + 20, 20, 20, 20, /* 17 - 20 */ + 24, 24, 24, 24, /* 21 - 24 */ + 32, 32, 32, 32, 32, 32, 32, 32, /* 25 - 32 */ + 48, 48, 48, 48, 48, 48, 48, 48, /* 33 - 40 */ + 48, 48, 48, 48, 48, 48, 48, 48 /* 41 - 48 */ + }; if (datalen > 48) return 64; @@ -569,10 +571,6 @@ static int isotp_rcv_cf(struct sock *sk, struct canfd_frame *cf, int ae, return 0; } - /* no creation of flow control frames */ - if (so->opt.flags & CAN_ISOTP_LISTEN_MODE) - return 0; - /* perform blocksize handling, if enabled */ if (!so->rxfc.bs || ++so->rx.bs < so->rxfc.bs) { /* start rx timeout watchdog */ @@ -581,6 +579,10 @@ static int isotp_rcv_cf(struct sock *sk, struct canfd_frame *cf, int ae, return 0; } + /* no creation of flow control frames */ + if (so->opt.flags & CAN_ISOTP_LISTEN_MODE) + return 0; + /* we reached the specified blocksize so->rxfc.bs */ isotp_send_fc(sk, ae, ISOTP_FC_CTS); return 0; diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index 1be4c898b2fa..f23966526a88 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -475,6 +475,12 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len) goto out_release_sock; } + if (!(ndev->flags & IFF_UP)) { + dev_put(ndev); + ret = -ENETDOWN; + goto out_release_sock; + } + priv = j1939_netdev_start(ndev); dev_put(ndev); if (IS_ERR(priv)) { diff --git a/net/can/proc.c b/net/can/proc.c index 550928b8b8a2..5ea8695f507e 100644 --- a/net/can/proc.c +++ b/net/can/proc.c @@ -462,6 +462,9 @@ void can_init_proc(struct net *net) */ void can_remove_proc(struct net *net) { + if (!net->can.proc_dir) + return; + if (net->can.pde_stats) remove_proc_entry(CAN_PROC_STATS, net->can.proc_dir); @@ -486,6 +489,5 @@ void can_remove_proc(struct net *net) if (net->can.pde_rcvlist_sff) remove_proc_entry(CAN_PROC_RCVLIST_SFF, net->can.proc_dir); - if (net->can.proc_dir) - remove_proc_entry("can", net->proc_net); + remove_proc_entry("can", net->proc_net); } diff --git a/net/core/devlink.c b/net/core/devlink.c index a932d95be798..4b0211590aac 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -1448,7 +1448,7 @@ static int devlink_nl_sb_port_pool_fill(struct sk_buff *msg, err = ops->sb_occ_port_pool_get(devlink_port, devlink_sb->index, pool_index, &cur, &max); if (err && err != -EOPNOTSUPP) - return err; + goto sb_occ_get_failure; if (!err) { if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_CUR, cur)) goto nla_put_failure; @@ -1461,8 +1461,10 @@ static int devlink_nl_sb_port_pool_fill(struct sk_buff *msg, return 0; nla_put_failure: + err = -EMSGSIZE; +sb_occ_get_failure: genlmsg_cancel(msg, hdr); - return -EMSGSIZE; + return err; } static int devlink_nl_cmd_sb_port_pool_get_doit(struct sk_buff *skb, @@ -8254,8 +8256,6 @@ static int __devlink_port_attrs_set(struct devlink_port *devlink_port, { struct devlink_port_attrs *attrs = &devlink_port->attrs; - if (WARN_ON(devlink_port->registered)) - return -EEXIST; devlink_port->attrs_set = true; attrs->flavour = flavour; if (attrs->switch_id.id_len) { @@ -8279,6 +8279,8 @@ void devlink_port_attrs_set(struct devlink_port *devlink_port, { int ret; + if (WARN_ON(devlink_port->registered)) + return; devlink_port->attrs = *attrs; ret = __devlink_port_attrs_set(devlink_port, attrs->flavour); if (ret) @@ -8301,6 +8303,8 @@ void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u32 contro struct devlink_port_attrs *attrs = &devlink_port->attrs; int ret; + if (WARN_ON(devlink_port->registered)) + return; ret = __devlink_port_attrs_set(devlink_port, DEVLINK_PORT_FLAVOUR_PCI_PF); if (ret) @@ -8326,6 +8330,8 @@ void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 contro struct devlink_port_attrs *attrs = &devlink_port->attrs; int ret; + if (WARN_ON(devlink_port->registered)) + return; ret = __devlink_port_attrs_set(devlink_port, DEVLINK_PORT_FLAVOUR_PCI_VF); if (ret) diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 8e39e28b0a8d..9500d28a43b0 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -235,6 +235,8 @@ static int neigh_forced_gc(struct neigh_table *tbl) write_lock(&n->lock); if ((n->nud_state == NUD_FAILED) || + (tbl->is_multicast && + tbl->is_multicast(n->primary_key)) || time_after(tref, n->updated)) remove = true; write_unlock(&n->lock); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index c310c7c1cef7..960948290001 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -29,6 +29,7 @@ #include <linux/slab.h> #include <linux/export.h> #include <linux/if_vlan.h> +#include <net/dsa.h> #include <net/tcp.h> #include <net/udp.h> #include <net/addrconf.h> @@ -657,15 +658,15 @@ EXPORT_SYMBOL_GPL(__netpoll_setup); int netpoll_setup(struct netpoll *np) { - struct net_device *ndev = NULL; + struct net_device *ndev = NULL, *dev = NULL; + struct net *net = current->nsproxy->net_ns; struct in_device *in_dev; int err; rtnl_lock(); - if (np->dev_name[0]) { - struct net *net = current->nsproxy->net_ns; + if (np->dev_name[0]) ndev = __dev_get_by_name(net, np->dev_name); - } + if (!ndev) { np_err(np, "%s doesn't exist, aborting\n", np->dev_name); err = -ENODEV; @@ -673,6 +674,19 @@ int netpoll_setup(struct netpoll *np) } dev_hold(ndev); + /* bring up DSA management network devices up first */ + for_each_netdev(net, dev) { + if (!netdev_uses_dsa(dev)) + continue; + + err = dev_change_flags(dev, dev->flags | IFF_UP, NULL); + if (err < 0) { + np_err(np, "%s failed to open %s\n", + np->dev_name, dev->name); + goto put; + } + } + if (netdev_master_upper_dev_get(ndev)) { np_err(np, "%s is a slave device, aborting\n", np->dev_name); err = -EBUSY; diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 654182ecf87b..25cdbb20f3a0 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -170,10 +170,12 @@ static int sk_msg_free_elem(struct sock *sk, struct sk_msg *msg, u32 i, struct scatterlist *sge = sk_msg_elem(msg, i); u32 len = sge->length; - if (charge) - sk_mem_uncharge(sk, len); - if (!msg->skb) + /* When the skb owns the memory we free it from consume_skb path. */ + if (!msg->skb) { + if (charge) + sk_mem_uncharge(sk, len); put_page(sg_page(sge)); + } memset(sge, 0, sizeof(*sge)); return len; } @@ -397,28 +399,45 @@ out: } EXPORT_SYMBOL_GPL(sk_msg_memcopy_from_iter); -static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) +static struct sk_msg *sk_psock_create_ingress_msg(struct sock *sk, + struct sk_buff *skb) { - struct sock *sk = psock->sk; - int copied = 0, num_sge; struct sk_msg *msg; + if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf) + return NULL; + + if (!sk_rmem_schedule(sk, skb, skb->truesize)) + return NULL; + msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC); if (unlikely(!msg)) - return -EAGAIN; - if (!sk_rmem_schedule(sk, skb, skb->len)) { - kfree(msg); - return -EAGAIN; - } + return NULL; sk_msg_init(msg); + return msg; +} + +static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb, + struct sk_psock *psock, + struct sock *sk, + struct sk_msg *msg) +{ + int num_sge, copied; + + /* skb linearize may fail with ENOMEM, but lets simply try again + * later if this happens. Under memory pressure we don't want to + * drop the skb. We need to linearize the skb so that the mapping + * in skb_to_sgvec can not error. + */ + if (skb_linearize(skb)) + return -EAGAIN; num_sge = skb_to_sgvec(skb, msg->sg.data, 0, skb->len); if (unlikely(num_sge < 0)) { kfree(msg); return num_sge; } - sk_mem_charge(sk, skb->len); copied = skb->len; msg->sg.start = 0; msg->sg.size = copied; @@ -430,6 +449,48 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) return copied; } +static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb); + +static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) +{ + struct sock *sk = psock->sk; + struct sk_msg *msg; + + /* If we are receiving on the same sock skb->sk is already assigned, + * skip memory accounting and owner transition seeing it already set + * correctly. + */ + if (unlikely(skb->sk == sk)) + return sk_psock_skb_ingress_self(psock, skb); + msg = sk_psock_create_ingress_msg(sk, skb); + if (!msg) + return -EAGAIN; + + /* This will transition ownership of the data from the socket where + * the BPF program was run initiating the redirect to the socket + * we will eventually receive this data on. The data will be released + * from skb_consume found in __tcp_bpf_recvmsg() after its been copied + * into user buffers. + */ + skb_set_owner_r(skb, sk); + return sk_psock_skb_ingress_enqueue(skb, psock, sk, msg); +} + +/* Puts an skb on the ingress queue of the socket already assigned to the + * skb. In this case we do not need to check memory limits or skb_set_owner_r + * because the skb is already accounted for here. + */ +static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb) +{ + struct sk_msg *msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC); + struct sock *sk = psock->sk; + + if (unlikely(!msg)) + return -EAGAIN; + sk_msg_init(msg); + return sk_psock_skb_ingress_enqueue(skb, psock, sk, msg); +} + static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb, u32 off, u32 len, bool ingress) { @@ -789,7 +850,7 @@ static void sk_psock_verdict_apply(struct sk_psock *psock, * retrying later from workqueue. */ if (skb_queue_empty(&psock->ingress_skb)) { - err = sk_psock_skb_ingress(psock, skb); + err = sk_psock_skb_ingress_self(psock, skb); } if (err < 0) { skb_queue_tail(&psock->ingress_skb, skb); diff --git a/net/ethtool/features.c b/net/ethtool/features.c index 8ee4cdbd6b82..1c9f4df273bd 100644 --- a/net/ethtool/features.c +++ b/net/ethtool/features.c @@ -280,7 +280,7 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info) active_diff_mask, compact); } if (mod) - ethtool_notify(dev, ETHTOOL_MSG_FEATURES_NTF, NULL); + netdev_features_change(dev); out_rtnl: rtnl_unlock(); diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 687971d83b4e..922dd73e5740 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -125,6 +125,7 @@ static int arp_constructor(struct neighbour *neigh); static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb); static void arp_error_report(struct neighbour *neigh, struct sk_buff *skb); static void parp_redo(struct sk_buff *skb); +static int arp_is_multicast(const void *pkey); static const struct neigh_ops arp_generic_ops = { .family = AF_INET, @@ -156,6 +157,7 @@ struct neigh_table arp_tbl = { .key_eq = arp_key_eq, .constructor = arp_constructor, .proxy_redo = parp_redo, + .is_multicast = arp_is_multicast, .id = "arp_cache", .parms = { .tbl = &arp_tbl, @@ -928,6 +930,10 @@ static void parp_redo(struct sk_buff *skb) arp_process(dev_net(skb->dev), NULL, skb); } +static int arp_is_multicast(const void *pkey) +{ + return ipv4_is_multicast(*((__be32 *)pkey)); +} /* * Receive an arp request from the device layer. diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 86a23e4a6a50..b87140a1fa28 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -696,7 +696,7 @@ int fib_gw_from_via(struct fib_config *cfg, struct nlattr *nla, cfg->fc_gw4 = *((__be32 *)via->rtvia_addr); break; case AF_INET6: -#ifdef CONFIG_IPV6 +#if IS_ENABLED(CONFIG_IPV6) if (alen != sizeof(struct in6_addr)) { NL_SET_ERR_MSG(extack, "Invalid IPv6 address in RTA_VIA"); return -EINVAL; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 366a4507b5a3..93474b1bea4e 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -479,8 +479,10 @@ static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb, r->idiag_inode = 0; if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, - inet_rsk(reqsk)->ir_mark)) + inet_rsk(reqsk)->ir_mark)) { + nlmsg_cancel(skb, nlh); return -EMSGSIZE; + } nlmsg_end(skb, nlh); return 0; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 8b04d1dcfec4..ee65c9225178 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -608,9 +608,6 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, ttl = ip4_dst_hoplimit(&rt->dst); } - if (!df && skb->protocol == htons(ETH_P_IP)) - df = inner_iph->frag_off & htons(IP_DF); - headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len; if (headroom > dev->needed_headroom) dev->needed_headroom = headroom; diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 25f1caf5abf9..e25be2d01a7a 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -263,7 +263,7 @@ static int iptunnel_pmtud_check_icmp(struct sk_buff *skb, int mtu) const struct icmphdr *icmph = icmp_hdr(skb); const struct iphdr *iph = ip_hdr(skb); - if (mtu <= 576 || iph->frag_off != htons(IP_DF)) + if (mtu < 576 || iph->frag_off != htons(IP_DF)) return 0; if (ipv4_is_lbcast(iph->daddr) || ipv4_is_multicast(iph->daddr) || @@ -359,7 +359,7 @@ static int iptunnel_pmtud_check_icmpv6(struct sk_buff *skb, int mtu) __be16 frag_off; int offset; - if (mtu <= IPV6_MIN_MTU) + if (mtu < IPV6_MIN_MTU) return 0; if (stype == IPV6_ADDR_ANY || stype == IPV6_ADDR_MULTICAST || diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index a058213b77a7..7c841037c533 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -17,17 +17,19 @@ #include <net/netfilter/nf_queue.h> /* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */ -int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned int addr_type) +int ip_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int addr_type) { const struct iphdr *iph = ip_hdr(skb); struct rtable *rt; struct flowi4 fl4 = {}; __be32 saddr = iph->saddr; - const struct sock *sk = skb_to_full_sk(skb); - __u8 flags = sk ? inet_sk_flowi_flags(sk) : 0; + __u8 flags; struct net_device *dev = skb_dst(skb)->dev; unsigned int hh_len; + sk = sk_to_full_sk(sk); + flags = sk ? inet_sk_flowi_flags(sk) : 0; + if (addr_type == RTN_UNSPEC) addr_type = inet_addr_type_dev_table(net, dev, saddr); if (addr_type == RTN_LOCAL || addr_type == RTN_UNICAST) diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index f703a717ab1d..833079589273 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -62,7 +62,7 @@ ipt_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state) iph->daddr != daddr || skb->mark != mark || iph->tos != tos) { - err = ip_route_me_harder(state->net, skb, RTN_UNSPEC); + err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC); if (err < 0) ret = NF_DROP_ERR(err); } diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c index 9dcfa4e461b6..93b07739807b 100644 --- a/net/ipv4/netfilter/nf_reject_ipv4.c +++ b/net/ipv4/netfilter/nf_reject_ipv4.c @@ -145,7 +145,7 @@ void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook) ip4_dst_hoplimit(skb_dst(nskb))); nf_reject_ip_tcphdr_put(nskb, oldskb, oth); - if (ip_route_me_harder(net, nskb, RTN_UNSPEC)) + if (ip_route_me_harder(net, nskb->sk, nskb, RTN_UNSPEC)) goto free_nskb; niph = ip_hdr(nskb); diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 6ac473b47f30..00dc3f943c80 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -331,7 +331,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) __u32 cookie = ntohl(th->ack_seq) - 1; struct sock *ret = sk; struct request_sock *req; - int mss; + int full_space, mss; struct rtable *rt; __u8 rcv_wscale; struct flowi4 fl4; @@ -427,8 +427,13 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) /* Try to redo what tcp_v4_send_synack did. */ req->rsk_window_clamp = tp->window_clamp ? :dst_metric(&rt->dst, RTAX_WINDOW); + /* limit the window selection if the user enforce a smaller rx buffer */ + full_space = tcp_full_space(sk); + if (sk->sk_userlocks & SOCK_RCVBUF_LOCK && + (req->rsk_window_clamp > full_space || req->rsk_window_clamp == 0)) + req->rsk_window_clamp = full_space; - tcp_select_initial_window(sk, tcp_full_space(sk), req->mss, + tcp_select_initial_window(sk, full_space, req->mss, &req->rsk_rcv_wnd, &req->rsk_window_clamp, ireq->wscale_ok, &rcv_wscale, dst_metric(&rt->dst, RTAX_INITRWND)); diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 6c4d79baff26..6ea3dc2e4219 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -945,7 +945,7 @@ static void bbr_update_min_rtt(struct sock *sk, const struct rate_sample *rs) filter_expired = after(tcp_jiffies32, bbr->min_rtt_stamp + bbr_min_rtt_win_sec * HZ); if (rs->rtt_us >= 0 && - (rs->rtt_us <= bbr->min_rtt_us || + (rs->rtt_us < bbr->min_rtt_us || (filter_expired && !rs->is_ack_delayed))) { bbr->min_rtt_us = rs->rtt_us; bbr->min_rtt_stamp = tcp_jiffies32; diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 37f4cb2bba5c..bc7d2a586e18 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -15,8 +15,8 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, { struct iov_iter *iter = &msg->msg_iter; int peek = flags & MSG_PEEK; - int i, ret, copied = 0; struct sk_msg *msg_rx; + int i, copied = 0; msg_rx = list_first_entry_or_null(&psock->ingress_msg, struct sk_msg, list); @@ -37,17 +37,16 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, page = sg_page(sge); if (copied + copy > len) copy = len - copied; - ret = copy_page_to_iter(page, sge->offset, copy, iter); - if (ret != copy) { - msg_rx->sg.start = i; - return -EFAULT; - } + copy = copy_page_to_iter(page, sge->offset, copy, iter); + if (!copy) + return copied ? copied : -EFAULT; copied += copy; if (likely(!peek)) { sge->offset += copy; sge->length -= copy; - sk_mem_uncharge(sk, copy); + if (!msg_rx->skb) + sk_mem_uncharge(sk, copy); msg_rx->sg.size -= copy; if (!sge->length) { @@ -56,6 +55,11 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, put_page(page); } } else { + /* Lets not optimize peek case if copy_page_to_iter + * didn't copy the entire length lets just break. + */ + if (copy != sge->length) + return copied; sk_msg_iter_var_next(i); } diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index e67a66fbf27b..c62805cd3131 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -366,7 +366,7 @@ out: static struct sk_buff *udp_gro_receive_segment(struct list_head *head, struct sk_buff *skb) { - struct udphdr *uh = udp_hdr(skb); + struct udphdr *uh = udp_gro_udphdr(skb); struct sk_buff *pp = NULL; struct udphdr *uh2; struct sk_buff *p; @@ -500,12 +500,22 @@ out: } EXPORT_SYMBOL(udp_gro_receive); +static struct sock *udp4_gro_lookup_skb(struct sk_buff *skb, __be16 sport, + __be16 dport) +{ + const struct iphdr *iph = skb_gro_network_header(skb); + + return __udp4_lib_lookup(dev_net(skb->dev), iph->saddr, sport, + iph->daddr, dport, inet_iif(skb), + inet_sdif(skb), &udp_table, NULL); +} + INDIRECT_CALLABLE_SCOPE struct sk_buff *udp4_gro_receive(struct list_head *head, struct sk_buff *skb) { struct udphdr *uh = udp_gro_udphdr(skb); + struct sock *sk = NULL; struct sk_buff *pp; - struct sock *sk; if (unlikely(!uh)) goto flush; @@ -523,7 +533,10 @@ struct sk_buff *udp4_gro_receive(struct list_head *head, struct sk_buff *skb) skip: NAPI_GRO_CB(skb)->is_ipv6 = 0; rcu_read_lock(); - sk = static_branch_unlikely(&udp_encap_needed_key) ? udp4_lib_lookup_skb(skb, uh->source, uh->dest) : NULL; + + if (static_branch_unlikely(&udp_encap_needed_key)) + sk = udp4_gro_lookup_skb(skb, uh->source, uh->dest); + pp = udp_gro_receive(head, skb, uh, sk); rcu_read_unlock(); return pp; diff --git a/net/ipv4/xfrm4_tunnel.c b/net/ipv4/xfrm4_tunnel.c index dc19aff7c2e0..fb0648e7fb32 100644 --- a/net/ipv4/xfrm4_tunnel.c +++ b/net/ipv4/xfrm4_tunnel.c @@ -64,14 +64,14 @@ static int xfrm_tunnel_err(struct sk_buff *skb, u32 info) static struct xfrm_tunnel xfrm_tunnel_handler __read_mostly = { .handler = xfrm_tunnel_rcv, .err_handler = xfrm_tunnel_err, - .priority = 3, + .priority = 4, }; #if IS_ENABLED(CONFIG_IPV6) static struct xfrm_tunnel xfrm64_tunnel_handler __read_mostly = { .handler = xfrm_tunnel_rcv, .err_handler = xfrm_tunnel_err, - .priority = 2, + .priority = 3, }; #endif diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 01146b66d666..8b6eb384bac7 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5022,8 +5022,10 @@ static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, return -EMSGSIZE; if (args->netnsid >= 0 && - nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) + nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) { + nlmsg_cancel(skb, nlh); return -EMSGSIZE; + } put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex); if (nla_put_in6_addr(skb, IFA_MULTICAST, &ifmca->mca_addr) < 0 || @@ -5054,8 +5056,10 @@ static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca, return -EMSGSIZE; if (args->netnsid >= 0 && - nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) + nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) { + nlmsg_cancel(skb, nlh); return -EMSGSIZE; + } put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex); if (nla_put_in6_addr(skb, IFA_ANYCAST, &ifaca->aca_addr) < 0 || diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index d88d97617f7e..440080da805b 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -588,7 +588,8 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len); memset(ah->auth_data, 0, ahp->icv_trunc_len); - if (ipv6_clear_mutable_options(ip6h, hdr_len, XFRM_POLICY_IN)) + err = ipv6_clear_mutable_options(ip6h, hdr_len, XFRM_POLICY_IN); + if (err) goto out_free; ip6h->priority = 0; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index ec448b71bf9a..8956144ea65e 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -158,7 +158,13 @@ static bool is_ineligible(const struct sk_buff *skb) tp = skb_header_pointer(skb, ptr+offsetof(struct icmp6hdr, icmp6_type), sizeof(_type), &_type); - if (!tp || !(*tp & ICMPV6_INFOMSG_MASK)) + + /* Based on RFC 8200, Section 4.5 Fragment Header, return + * false if this is a fragment packet with no icmp header info. + */ + if (!tp && frag_off != 0) + return false; + else if (!tp || !(*tp & ICMPV6_INFOMSG_MASK)) return true; } return false; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index a0217e5bf3bc..648db3fe508f 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1271,6 +1271,8 @@ route_lookup: if (max_headroom > dev->needed_headroom) dev->needed_headroom = max_headroom; + skb_set_inner_ipproto(skb, proto); + err = ip6_tnl_encap(skb, t, &proto, fl6); if (err) return err; @@ -1280,8 +1282,6 @@ route_lookup: ipv6_push_frag_opts(skb, &opt.ops, &proto); } - skb_set_inner_ipproto(skb, proto); - skb_push(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); ipv6h = ipv6_hdr(skb); diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 27f29b957ee7..76717478f173 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -81,6 +81,7 @@ static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb); static int pndisc_constructor(struct pneigh_entry *n); static void pndisc_destructor(struct pneigh_entry *n); static void pndisc_redo(struct sk_buff *skb); +static int ndisc_is_multicast(const void *pkey); static const struct neigh_ops ndisc_generic_ops = { .family = AF_INET6, @@ -115,6 +116,7 @@ struct neigh_table nd_tbl = { .pconstructor = pndisc_constructor, .pdestructor = pndisc_destructor, .proxy_redo = pndisc_redo, + .is_multicast = ndisc_is_multicast, .allow_add = ndisc_allow_add, .id = "ndisc_cache", .parms = { @@ -1706,6 +1708,11 @@ static void pndisc_redo(struct sk_buff *skb) kfree_skb(skb); } +static int ndisc_is_multicast(const void *pkey) +{ + return ipv6_addr_is_multicast((struct in6_addr *)pkey); +} + static bool ndisc_suppress_frag_ndisc(struct sk_buff *skb) { struct inet6_dev *idev = __in6_dev_get(skb->dev); diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 6d0e942d082d..ab9a279dd6d4 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -20,10 +20,10 @@ #include <net/netfilter/ipv6/nf_defrag_ipv6.h> #include "../bridge/br_private.h" -int ip6_route_me_harder(struct net *net, struct sk_buff *skb) +int ip6_route_me_harder(struct net *net, struct sock *sk_partial, struct sk_buff *skb) { const struct ipv6hdr *iph = ipv6_hdr(skb); - struct sock *sk = sk_to_full_sk(skb->sk); + struct sock *sk = sk_to_full_sk(sk_partial); unsigned int hh_len; struct dst_entry *dst; int strict = (ipv6_addr_type(&iph->daddr) & @@ -84,7 +84,7 @@ static int nf_ip6_reroute(struct sk_buff *skb, if (!ipv6_addr_equal(&iph->daddr, &rt_info->daddr) || !ipv6_addr_equal(&iph->saddr, &rt_info->saddr) || skb->mark != rt_info->mark) - return ip6_route_me_harder(entry->state.net, skb); + return ip6_route_me_harder(entry->state.net, entry->state.sk, skb); } return 0; } diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index 1a2748611e00..cee74803d7a1 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -57,7 +57,7 @@ ip6t_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state) skb->mark != mark || ipv6_hdr(skb)->hop_limit != hop_limit || flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) { - err = ip6_route_me_harder(state->net, skb); + err = ip6_route_me_harder(state->net, state->sk, skb); if (err < 0) ret = NF_DROP_ERR(err); } diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 054d287eb13d..c129ad334eb3 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -440,6 +440,7 @@ find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff) int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) { u16 savethdr = skb->transport_header; + u8 nexthdr = NEXTHDR_FRAGMENT; int fhoff, nhoff, ret; struct frag_hdr *fhdr; struct frag_queue *fq; @@ -455,6 +456,14 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) if (find_prev_fhdr(skb, &prevhdr, &nhoff, &fhoff) < 0) return 0; + /* Discard the first fragment if it does not include all headers + * RFC 8200, Section 4.5 + */ + if (ipv6frag_thdr_truncated(skb, fhoff, &nexthdr)) { + pr_debug("Drop incomplete fragment\n"); + return 0; + } + if (!pskb_may_pull(skb, fhoff + sizeof(*fhdr))) return -ENOMEM; diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 1f5d4d196dcc..47a0dc46cbdb 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -42,6 +42,8 @@ #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/export.h> +#include <linux/tcp.h> +#include <linux/udp.h> #include <net/sock.h> #include <net/snmp.h> @@ -322,6 +324,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb) struct frag_queue *fq; const struct ipv6hdr *hdr = ipv6_hdr(skb); struct net *net = dev_net(skb_dst(skb)->dev); + u8 nexthdr; int iif; if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED) @@ -351,6 +354,20 @@ static int ipv6_frag_rcv(struct sk_buff *skb) return 1; } + /* RFC 8200, Section 4.5 Fragment Header: + * If the first fragment does not include all headers through an + * Upper-Layer header, then that fragment should be discarded and + * an ICMP Parameter Problem, Code 3, message should be sent to + * the source of the fragment, with the Pointer field set to zero. + */ + nexthdr = hdr->nexthdr; + if (ipv6frag_thdr_truncated(skb, skb_transport_offset(skb), &nexthdr)) { + __IP6_INC_STATS(net, __in6_dev_get_safely(skb->dev), + IPSTATS_MIB_INHDRERRORS); + icmpv6_param_prob(skb, ICMPV6_HDR_INCOMP, 0); + return -1; + } + iif = skb->dev ? skb->dev->ifindex : 0; fq = fq_find(net, fhdr->identification, hdr, iif); if (fq) { diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 5e2c34c0ac97..5e7983cb6154 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1128,7 +1128,6 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev) if (tdev && !netif_is_l3_master(tdev)) { int t_hlen = tunnel->hlen + sizeof(struct iphdr); - dev->hard_header_len = tdev->hard_header_len + sizeof(struct iphdr); dev->mtu = tdev->mtu - t_hlen; if (dev->mtu < IPV6_MIN_MTU) dev->mtu = IPV6_MIN_MTU; @@ -1426,7 +1425,6 @@ static void ipip6_tunnel_setup(struct net_device *dev) dev->priv_destructor = ipip6_dev_free; dev->type = ARPHRD_SIT; - dev->hard_header_len = LL_MAX_HEADER + t_hlen; dev->mtu = ETH_DATA_LEN - t_hlen; dev->min_mtu = IPV6_MIN_MTU; dev->max_mtu = IP6_MAX_MTU - t_hlen; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index e796a64be308..9b6cae1e49d9 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -136,7 +136,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) __u32 cookie = ntohl(th->ack_seq) - 1; struct sock *ret = sk; struct request_sock *req; - int mss; + int full_space, mss; struct dst_entry *dst; __u8 rcv_wscale; u32 tsoff = 0; @@ -241,7 +241,13 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) } req->rsk_window_clamp = tp->window_clamp ? :dst_metric(dst, RTAX_WINDOW); - tcp_select_initial_window(sk, tcp_full_space(sk), req->mss, + /* limit the window selection if the user enforce a smaller rx buffer */ + full_space = tcp_full_space(sk); + if (sk->sk_userlocks & SOCK_RCVBUF_LOCK && + (req->rsk_window_clamp > full_space || req->rsk_window_clamp == 0)) + req->rsk_window_clamp = full_space; + + tcp_select_initial_window(sk, full_space, req->mss, &req->rsk_rcv_wnd, &req->rsk_window_clamp, ireq->wscale_ok, &rcv_wscale, dst_metric(dst, RTAX_INITRWND)); diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index 584157a07759..f9e888d1b9af 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -111,12 +111,22 @@ out: return segs; } +static struct sock *udp6_gro_lookup_skb(struct sk_buff *skb, __be16 sport, + __be16 dport) +{ + const struct ipv6hdr *iph = skb_gro_network_header(skb); + + return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport, + &iph->daddr, dport, inet6_iif(skb), + inet6_sdif(skb), &udp_table, NULL); +} + INDIRECT_CALLABLE_SCOPE struct sk_buff *udp6_gro_receive(struct list_head *head, struct sk_buff *skb) { struct udphdr *uh = udp_gro_udphdr(skb); + struct sock *sk = NULL; struct sk_buff *pp; - struct sock *sk; if (unlikely(!uh)) goto flush; @@ -135,7 +145,10 @@ struct sk_buff *udp6_gro_receive(struct list_head *head, struct sk_buff *skb) skip: NAPI_GRO_CB(skb)->is_ipv6 = 1; rcu_read_lock(); - sk = static_branch_unlikely(&udpv6_encap_needed_key) ? udp6_lib_lookup_skb(skb, uh->source, uh->dest) : NULL; + + if (static_branch_unlikely(&udpv6_encap_needed_key)) + sk = udp6_gro_lookup_skb(skb, uh->source, uh->dest); + pp = udp_gro_receive(head, skb, uh, sk); rcu_read_unlock(); return pp; diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index 25b7ebda2fab..f696d46e6910 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -303,13 +303,13 @@ static const struct xfrm_type xfrm6_tunnel_type = { static struct xfrm6_tunnel xfrm6_tunnel_handler __read_mostly = { .handler = xfrm6_tunnel_rcv, .err_handler = xfrm6_tunnel_err, - .priority = 2, + .priority = 3, }; static struct xfrm6_tunnel xfrm46_tunnel_handler __read_mostly = { .handler = xfrm6_tunnel_rcv, .err_handler = xfrm6_tunnel_err, - .priority = 2, + .priority = 3, }; static int __net_init xfrm6_tunnel_net_init(struct net *net) diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index d80572074667..047238f01ba6 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -1434,7 +1434,8 @@ static int iucv_sock_shutdown(struct socket *sock, int how) break; } - if (how == SEND_SHUTDOWN || how == SHUTDOWN_MASK) { + if ((how == SEND_SHUTDOWN || how == SHUTDOWN_MASK) && + sk->sk_state == IUCV_CONNECTED) { if (iucv->transport == AF_IUCV_TRANS_IUCV) { txmsg.class = 0; txmsg.tag = 0; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index f400240a556f..6adfcb9c06dc 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -5464,6 +5464,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, struct cfg80211_assoc_request *req) { bool is_6ghz = req->bss->channel->band == NL80211_BAND_6GHZ; + bool is_5ghz = req->bss->channel->band == NL80211_BAND_5GHZ; struct ieee80211_local *local = sdata->local; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_bss *bss = (void *)req->bss->priv; @@ -5616,7 +5617,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, if (vht_ie && vht_ie[1] >= sizeof(struct ieee80211_vht_cap)) memcpy(&assoc_data->ap_vht_cap, vht_ie + 2, sizeof(struct ieee80211_vht_cap)); - else if (!is_6ghz) + else if (is_5ghz) ifmgd->flags |= IEEE80211_STA_DISABLE_VHT | IEEE80211_STA_DISABLE_HE; rcu_read_unlock(); diff --git a/net/mac80211/rc80211_minstrel.c b/net/mac80211/rc80211_minstrel.c index 86bc469a28bc..b13b1da19386 100644 --- a/net/mac80211/rc80211_minstrel.c +++ b/net/mac80211/rc80211_minstrel.c @@ -274,7 +274,7 @@ minstrel_tx_status(void *priv, struct ieee80211_supported_band *sband, success = !!(info->flags & IEEE80211_TX_STAT_ACK); for (i = 0; i < IEEE80211_TX_MAX_RATES; i++) { - if (ar[i].idx < 0) + if (ar[i].idx < 0 || !ar[i].count) break; ndx = rix_to_ndx(mi, ar[i].idx); @@ -287,12 +287,6 @@ minstrel_tx_status(void *priv, struct ieee80211_supported_band *sband, mi->r[ndx].stats.success += success; } - if ((info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE) && (i >= 0)) - mi->sample_packets++; - - if (mi->sample_deferred > 0) - mi->sample_deferred--; - if (time_after(jiffies, mi->last_stats_update + mp->update_interval / (mp->new_avg ? 2 : 1))) minstrel_update_stats(mp, mi); @@ -367,7 +361,7 @@ minstrel_get_rate(void *priv, struct ieee80211_sta *sta, return; delta = (mi->total_packets * sampling_ratio / 100) - - (mi->sample_packets + mi->sample_deferred / 2); + mi->sample_packets; /* delta < 0: no sampling required */ prev_sample = mi->prev_sample; @@ -376,7 +370,6 @@ minstrel_get_rate(void *priv, struct ieee80211_sta *sta, return; if (mi->total_packets >= 10000) { - mi->sample_deferred = 0; mi->sample_packets = 0; mi->total_packets = 0; } else if (delta > mi->n_rates * 2) { @@ -401,19 +394,8 @@ minstrel_get_rate(void *priv, struct ieee80211_sta *sta, * rate sampling method should be used. * Respect such rates that are not sampled for 20 interations. */ - if (mrr_capable && - msr->perfect_tx_time > mr->perfect_tx_time && - msr->stats.sample_skipped < 20) { - /* Only use IEEE80211_TX_CTL_RATE_CTRL_PROBE to mark - * packets that have the sampling rate deferred to the - * second MRR stage. Increase the sample counter only - * if the deferred sample rate was actually used. - * Use the sample_deferred counter to make sure that - * the sampling is not done in large bursts */ - info->flags |= IEEE80211_TX_CTL_RATE_CTRL_PROBE; - rate++; - mi->sample_deferred++; - } else { + if (msr->perfect_tx_time < mr->perfect_tx_time || + msr->stats.sample_skipped >= 20) { if (!msr->sample_limit) return; @@ -433,6 +415,7 @@ minstrel_get_rate(void *priv, struct ieee80211_sta *sta, rate->idx = mi->r[ndx].rix; rate->count = minstrel_get_retry_count(&mi->r[ndx], info); + info->flags |= IEEE80211_TX_CTL_RATE_CTRL_PROBE; } diff --git a/net/mac80211/rc80211_minstrel.h b/net/mac80211/rc80211_minstrel.h index dbb43bcd3c45..86cd80b3ffde 100644 --- a/net/mac80211/rc80211_minstrel.h +++ b/net/mac80211/rc80211_minstrel.h @@ -126,7 +126,6 @@ struct minstrel_sta_info { u8 max_prob_rate; unsigned int total_packets; unsigned int sample_packets; - int sample_deferred; unsigned int sample_row; unsigned int sample_column; diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index fb4f2b9b294f..ec6973ee88ef 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -258,6 +258,24 @@ struct sta_info *sta_info_get_by_idx(struct ieee80211_sub_if_data *sdata, */ void sta_info_free(struct ieee80211_local *local, struct sta_info *sta) { + /* + * If we had used sta_info_pre_move_state() then we might not + * have gone through the state transitions down again, so do + * it here now (and warn if it's inserted). + * + * This will clear state such as fast TX/RX that may have been + * allocated during state transitions. + */ + while (sta->sta_state > IEEE80211_STA_NONE) { + int ret; + + WARN_ON_ONCE(test_sta_flag(sta, WLAN_STA_INSERTED)); + + ret = sta_info_move_state(sta, sta->sta_state - 1); + if (WARN_ONCE(ret, "sta_info_move_state() returned %d\n", ret)) + break; + } + if (sta->rate_ctrl) rate_control_free_sta(sta); @@ -687,7 +705,7 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) out_drop_sta: local->num_sta--; synchronize_net(); - __cleanup_single_sta(sta); + cleanup_single_sta(sta); out_err: mutex_unlock(&local->sta_mtx); kfree(sinfo); @@ -706,19 +724,13 @@ int sta_info_insert_rcu(struct sta_info *sta) __acquires(RCU) err = sta_info_insert_check(sta); if (err) { + sta_info_free(local, sta); mutex_unlock(&local->sta_mtx); rcu_read_lock(); - goto out_free; + return err; } - err = sta_info_insert_finish(sta); - if (err) - goto out_free; - - return 0; - out_free: - sta_info_free(local, sta); - return err; + return sta_info_insert_finish(sta); } int sta_info_insert(struct sta_info *sta) diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 00ae81e9e1a1..7afd07636b81 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -785,7 +785,7 @@ int sta_info_init(struct ieee80211_local *local); void sta_info_stop(struct ieee80211_local *local); /** - * sta_info_flush - flush matching STA entries from the STA table + * __sta_info_flush - flush matching STA entries from the STA table * * Returns the number of removed STA entries. * @@ -794,6 +794,13 @@ void sta_info_stop(struct ieee80211_local *local); */ int __sta_info_flush(struct ieee80211_sub_if_data *sdata, bool vlans); +/** + * sta_info_flush - flush matching STA entries from the STA table + * + * Returns the number of removed STA entries. + * + * @sdata: sdata to remove all stations from + */ static inline int sta_info_flush(struct ieee80211_sub_if_data *sdata) { return __sta_info_flush(sdata, false); diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 6feb45135020..3485610755ef 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -49,7 +49,8 @@ static void ieee80211_handle_filtered_frame(struct ieee80211_local *local, int ac; if (info->flags & (IEEE80211_TX_CTL_NO_PS_BUFFER | - IEEE80211_TX_CTL_AMPDU)) { + IEEE80211_TX_CTL_AMPDU | + IEEE80211_TX_CTL_HW_80211_ENCAP)) { ieee80211_free_txskb(&local->hw, skb); return; } @@ -915,15 +916,6 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw, ieee80211_mpsp_trigger_process( ieee80211_get_qos_ctl(hdr), sta, true, acked); - if (!acked && test_sta_flag(sta, WLAN_STA_PS_STA)) { - /* - * The STA is in power save mode, so assume - * that this TX packet failed because of that. - */ - ieee80211_handle_filtered_frame(local, sta, skb); - return; - } - if (ieee80211_hw_check(&local->hw, HAS_RATE_CONTROL) && (ieee80211_is_data(hdr->frame_control)) && (rates_idx != -1)) @@ -1150,6 +1142,12 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw, -info->status.ack_signal); } } else if (test_sta_flag(sta, WLAN_STA_PS_STA)) { + /* + * The STA is in power save mode, so assume + * that this TX packet failed because of that. + */ + if (skb) + ieee80211_handle_filtered_frame(local, sta, skb); return; } else if (noack_success) { /* nothing to do here, do not account as lost */ diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 8ba10a48ded4..56a4d0d20a26 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1942,19 +1942,24 @@ static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata, /* device xmit handlers */ +enum ieee80211_encrypt { + ENCRYPT_NO, + ENCRYPT_MGMT, + ENCRYPT_DATA, +}; + static int ieee80211_skb_resize(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, - int head_need, bool may_encrypt) + int head_need, + enum ieee80211_encrypt encrypt) { struct ieee80211_local *local = sdata->local; - struct ieee80211_hdr *hdr; bool enc_tailroom; int tail_need = 0; - hdr = (struct ieee80211_hdr *) skb->data; - enc_tailroom = may_encrypt && - (sdata->crypto_tx_tailroom_needed_cnt || - ieee80211_is_mgmt(hdr->frame_control)); + enc_tailroom = encrypt == ENCRYPT_MGMT || + (encrypt == ENCRYPT_DATA && + sdata->crypto_tx_tailroom_needed_cnt); if (enc_tailroom) { tail_need = IEEE80211_ENCRYPT_TAILROOM; @@ -1985,23 +1990,29 @@ void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, { struct ieee80211_local *local = sdata->local; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); - struct ieee80211_hdr *hdr; + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; int headroom; - bool may_encrypt; + enum ieee80211_encrypt encrypt; - may_encrypt = !(info->flags & IEEE80211_TX_INTFL_DONT_ENCRYPT); + if (info->flags & IEEE80211_TX_INTFL_DONT_ENCRYPT) + encrypt = ENCRYPT_NO; + else if (ieee80211_is_mgmt(hdr->frame_control)) + encrypt = ENCRYPT_MGMT; + else + encrypt = ENCRYPT_DATA; headroom = local->tx_headroom; - if (may_encrypt) + if (encrypt != ENCRYPT_NO) headroom += sdata->encrypt_headroom; headroom -= skb_headroom(skb); headroom = max_t(int, 0, headroom); - if (ieee80211_skb_resize(sdata, skb, headroom, may_encrypt)) { + if (ieee80211_skb_resize(sdata, skb, headroom, encrypt)) { ieee80211_free_txskb(&local->hw, skb); return; } + /* reload after potential resize */ hdr = (struct ieee80211_hdr *) skb->data; info->control.vif = &sdata->vif; @@ -2828,7 +2839,7 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata, head_need += sdata->encrypt_headroom; head_need += local->tx_headroom; head_need = max_t(int, 0, head_need); - if (ieee80211_skb_resize(sdata, skb, head_need, true)) { + if (ieee80211_skb_resize(sdata, skb, head_need, ENCRYPT_DATA)) { ieee80211_free_txskb(&local->hw, skb); skb = NULL; return ERR_PTR(-ENOMEM); @@ -3502,7 +3513,7 @@ static bool ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata, if (unlikely(ieee80211_skb_resize(sdata, skb, max_t(int, extra_head + hw_headroom - skb_headroom(skb), 0), - false))) { + ENCRYPT_NO))) { kfree_skb(skb); return true; } @@ -3619,13 +3630,14 @@ begin: tx.skb = skb; tx.sdata = vif_to_sdata(info->control.vif); - if (txq->sta && !(info->flags & IEEE80211_TX_CTL_INJECTED)) { + if (txq->sta) { tx.sta = container_of(txq->sta, struct sta_info, sta); /* * Drop unicast frames to unauthorised stations unless they are - * EAPOL frames from the local station. + * injected frames or EAPOL frames from the local station. */ - if (unlikely(ieee80211_is_data(hdr->frame_control) && + if (unlikely(!(info->flags & IEEE80211_TX_CTL_INJECTED) && + ieee80211_is_data(hdr->frame_control) && !ieee80211_vif_is_mesh(&tx.sdata->vif) && tx.sdata->vif.type != NL80211_IFTYPE_OCB && !is_multicast_ether_addr(hdr->addr1) && diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index e7419fd15d84..88f2a7a0ccb8 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2467,6 +2467,7 @@ static struct proto mptcp_prot = { .memory_pressure = &tcp_memory_pressure, .stream_memory_free = mptcp_memory_free, .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_tcp_wmem), + .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_tcp_rmem), .sysctl_mem = sysctl_tcp_mem, .obj_size = sizeof(struct mptcp_sock), .slab_flags = SLAB_TYPESAFE_BY_RCU, diff --git a/net/mptcp/token.c b/net/mptcp/token.c index 8b47c4bb1c6b..feb4b9ffd462 100644 --- a/net/mptcp/token.c +++ b/net/mptcp/token.c @@ -291,7 +291,7 @@ struct mptcp_sock *mptcp_token_iter_next(const struct net *net, long *s_slot, { struct mptcp_sock *ret = NULL; struct hlist_nulls_node *pos; - int slot, num; + int slot, num = 0; for (slot = *s_slot; slot <= token_mask; *s_num = 0, slot++) { struct token_bucket *bucket = &token_hash[slot]; diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c index f1be3e3f6425..a9cb355324d1 100644 --- a/net/ncsi/ncsi-manage.c +++ b/net/ncsi/ncsi-manage.c @@ -1726,9 +1726,6 @@ struct ncsi_dev *ncsi_register_dev(struct net_device *dev, ndp->ptype.dev = dev; dev_add_pack(&ndp->ptype); - /* Set up generic netlink interface */ - ncsi_init_netlink(dev); - pdev = to_platform_device(dev->dev.parent); if (pdev) { np = pdev->dev.of_node; @@ -1892,8 +1889,6 @@ void ncsi_unregister_dev(struct ncsi_dev *nd) list_del_rcu(&ndp->node); spin_unlock_irqrestore(&ncsi_dev_lock, flags); - ncsi_unregister_netlink(nd->dev); - kfree(ndp); } EXPORT_SYMBOL_GPL(ncsi_unregister_dev); diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c index adddc7707aa4..bb5f1650f11c 100644 --- a/net/ncsi/ncsi-netlink.c +++ b/net/ncsi/ncsi-netlink.c @@ -766,24 +766,8 @@ static struct genl_family ncsi_genl_family __ro_after_init = { .n_small_ops = ARRAY_SIZE(ncsi_ops), }; -int ncsi_init_netlink(struct net_device *dev) +static int __init ncsi_init_netlink(void) { - int rc; - - rc = genl_register_family(&ncsi_genl_family); - if (rc) - netdev_err(dev, "ncsi: failed to register netlink family\n"); - - return rc; -} - -int ncsi_unregister_netlink(struct net_device *dev) -{ - int rc; - - rc = genl_unregister_family(&ncsi_genl_family); - if (rc) - netdev_err(dev, "ncsi: failed to unregister netlink family\n"); - - return rc; + return genl_register_family(&ncsi_genl_family); } +subsys_initcall(ncsi_init_netlink); diff --git a/net/ncsi/ncsi-netlink.h b/net/ncsi/ncsi-netlink.h index 7502723fba83..39a1a9d7bf77 100644 --- a/net/ncsi/ncsi-netlink.h +++ b/net/ncsi/ncsi-netlink.h @@ -22,7 +22,4 @@ int ncsi_send_netlink_err(struct net_device *dev, struct nlmsghdr *nlhdr, int err); -int ncsi_init_netlink(struct net_device *dev); -int ncsi_unregister_netlink(struct net_device *dev); - #endif /* __NCSI_NETLINK_H__ */ diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 6f35832f0de3..7cff6e5e7445 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -637,13 +637,14 @@ ip_set_match_extensions(struct ip_set *set, const struct ip_set_ext *ext, if (SET_WITH_COUNTER(set)) { struct ip_set_counter *counter = ext_counter(data, set); + ip_set_update_counter(counter, ext, flags); + if (flags & IPSET_FLAG_MATCH_COUNTERS && !(ip_set_match_counter(ip_set_get_packets(counter), mext->packets, mext->packets_op) && ip_set_match_counter(ip_set_get_bytes(counter), mext->bytes, mext->bytes_op))) return false; - ip_set_update_counter(counter, ext, flags); } if (SET_WITH_SKBINFO(set)) ip_set_get_skbinfo(ext_skbinfo(data, set), diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index cc3c275934f4..c0b8215ab3d4 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -742,12 +742,12 @@ static int ip_vs_route_me_harder(struct netns_ipvs *ipvs, int af, struct dst_entry *dst = skb_dst(skb); if (dst->dev && !(dst->dev->flags & IFF_LOOPBACK) && - ip6_route_me_harder(ipvs->net, skb) != 0) + ip6_route_me_harder(ipvs->net, skb->sk, skb) != 0) return 1; } else #endif if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL) && - ip_route_me_harder(ipvs->net, skb, RTN_LOCAL) != 0) + ip_route_me_harder(ipvs->net, skb->sk, skb, RTN_LOCAL) != 0) return 1; return 0; diff --git a/net/netfilter/nf_nat_proto.c b/net/netfilter/nf_nat_proto.c index 59151dc07fdc..e87b6bd6b3cd 100644 --- a/net/netfilter/nf_nat_proto.c +++ b/net/netfilter/nf_nat_proto.c @@ -715,7 +715,7 @@ nf_nat_ipv4_local_fn(void *priv, struct sk_buff *skb, if (ct->tuplehash[dir].tuple.dst.u3.ip != ct->tuplehash[!dir].tuple.src.u3.ip) { - err = ip_route_me_harder(state->net, skb, RTN_UNSPEC); + err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC); if (err < 0) ret = NF_DROP_ERR(err); } @@ -953,7 +953,7 @@ nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb, if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3, &ct->tuplehash[!dir].tuple.src.u3)) { - err = nf_ip6_route_me_harder(state->net, skb); + err = nf_ip6_route_me_harder(state->net, state->sk, skb); if (err < 0) ret = NF_DROP_ERR(err); } diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index 9cca35d22927..d7d34a62d3bf 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -446,7 +446,7 @@ synproxy_send_tcp(struct net *net, skb_dst_set_noref(nskb, skb_dst(skb)); nskb->protocol = htons(ETH_P_IP); - if (ip_route_me_harder(net, nskb, RTN_UNSPEC)) + if (ip_route_me_harder(net, nskb->sk, nskb, RTN_UNSPEC)) goto free_nskb; if (nfct) { diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 65cb8e3c13d9..0f58e98542be 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -7137,7 +7137,7 @@ static void nf_tables_flowtable_notify(struct nft_ctx *ctx, GFP_KERNEL); kfree(buf); - if (ctx->report && + if (!ctx->report && !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES)) return; @@ -7259,7 +7259,7 @@ static void nf_tables_gen_notify(struct net *net, struct sk_buff *skb, audit_log_nfcfg("?:0;?:0", 0, net->nft.base_seq, AUDIT_NFT_OP_GEN_REGISTER, GFP_KERNEL); - if (nlmsg_report(nlh) && + if (!nlmsg_report(nlh) && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES)) return; @@ -8053,12 +8053,16 @@ static void nf_tables_abort_release(struct nft_trans *trans) kfree(trans); } -static int __nf_tables_abort(struct net *net, bool autoload) +static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) { struct nft_trans *trans, *next; struct nft_trans_elem *te; struct nft_hook *hook; + if (action == NFNL_ABORT_VALIDATE && + nf_tables_validate(net) < 0) + return -EAGAIN; + list_for_each_entry_safe_reverse(trans, next, &net->nft.commit_list, list) { switch (trans->msg_type) { @@ -8190,7 +8194,7 @@ static int __nf_tables_abort(struct net *net, bool autoload) nf_tables_abort_release(trans); } - if (autoload) + if (action == NFNL_ABORT_AUTOLOAD) nf_tables_module_autoload(net); else nf_tables_module_autoload_cleanup(net); @@ -8203,9 +8207,10 @@ static void nf_tables_cleanup(struct net *net) nft_validate_state_update(net, NFT_VALIDATE_SKIP); } -static int nf_tables_abort(struct net *net, struct sk_buff *skb, bool autoload) +static int nf_tables_abort(struct net *net, struct sk_buff *skb, + enum nfnl_abort_action action) { - int ret = __nf_tables_abort(net, autoload); + int ret = __nf_tables_abort(net, action); mutex_unlock(&net->nft.commit_mutex); @@ -8836,7 +8841,7 @@ static void __net_exit nf_tables_exit_net(struct net *net) { mutex_lock(&net->nft.commit_mutex); if (!list_empty(&net->nft.commit_list)) - __nf_tables_abort(net, false); + __nf_tables_abort(net, NFNL_ABORT_NONE); __nft_release_tables(net); mutex_unlock(&net->nft.commit_mutex); WARN_ON_ONCE(!list_empty(&net->nft.tables)); diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 2daa1f6ae344..d3df66a39b5e 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -333,7 +333,7 @@ static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh, return netlink_ack(skb, nlh, -EINVAL, NULL); replay: status = 0; - +replay_abort: skb = netlink_skb_clone(oskb, GFP_KERNEL); if (!skb) return netlink_ack(oskb, nlh, -ENOMEM, NULL); @@ -499,7 +499,7 @@ ack: } done: if (status & NFNL_BATCH_REPLAY) { - ss->abort(net, oskb, true); + ss->abort(net, oskb, NFNL_ABORT_AUTOLOAD); nfnl_err_reset(&err_list); kfree_skb(skb); module_put(ss->owner); @@ -510,11 +510,25 @@ done: status |= NFNL_BATCH_REPLAY; goto done; } else if (err) { - ss->abort(net, oskb, false); + ss->abort(net, oskb, NFNL_ABORT_NONE); netlink_ack(oskb, nlmsg_hdr(oskb), err, NULL); } } else { - ss->abort(net, oskb, false); + enum nfnl_abort_action abort_action; + + if (status & NFNL_BATCH_FAILURE) + abort_action = NFNL_ABORT_NONE; + else + abort_action = NFNL_ABORT_VALIDATE; + + err = ss->abort(net, oskb, abort_action); + if (err == -EAGAIN) { + nfnl_err_reset(&err_list); + kfree_skb(skb); + module_put(ss->owner); + status |= NFNL_BATCH_FAILURE; + goto replay_abort; + } } if (ss->cleanup) ss->cleanup(net); diff --git a/net/netfilter/nft_chain_route.c b/net/netfilter/nft_chain_route.c index 8826bbe71136..edd02cda57fc 100644 --- a/net/netfilter/nft_chain_route.c +++ b/net/netfilter/nft_chain_route.c @@ -42,7 +42,7 @@ static unsigned int nf_route_table_hook4(void *priv, iph->daddr != daddr || skb->mark != mark || iph->tos != tos) { - err = ip_route_me_harder(state->net, skb, RTN_UNSPEC); + err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC); if (err < 0) ret = NF_DROP_ERR(err); } @@ -92,7 +92,7 @@ static unsigned int nf_route_table_hook6(void *priv, skb->mark != mark || ipv6_hdr(skb)->hop_limit != hop_limit || flowlabel != *((u32 *)ipv6_hdr(skb)))) { - err = nf_ip6_route_me_harder(state->net, skb); + err = nf_ip6_route_me_harder(state->net, state->sk, skb); if (err < 0) ret = NF_DROP_ERR(err); } diff --git a/net/netfilter/utils.c b/net/netfilter/utils.c index cedf47ab3c6f..2182d361e273 100644 --- a/net/netfilter/utils.c +++ b/net/netfilter/utils.c @@ -191,8 +191,8 @@ static int nf_ip_reroute(struct sk_buff *skb, const struct nf_queue_entry *entry skb->mark == rt_info->mark && iph->daddr == rt_info->daddr && iph->saddr == rt_info->saddr)) - return ip_route_me_harder(entry->state.net, skb, - RTN_UNSPEC); + return ip_route_me_harder(entry->state.net, entry->state.sk, + skb, RTN_UNSPEC); } #endif return 0; diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index 2e8e3f7b2111..ccb491642811 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -1166,12 +1166,13 @@ static int netlbl_unlabel_staticlist(struct sk_buff *skb, struct netlbl_unlhsh_walk_arg cb_arg; u32 skip_bkt = cb->args[0]; u32 skip_chain = cb->args[1]; - u32 iter_bkt; - u32 iter_chain = 0, iter_addr4 = 0, iter_addr6 = 0; + u32 skip_addr4 = cb->args[2]; + u32 iter_bkt, iter_chain = 0, iter_addr4 = 0, iter_addr6 = 0; struct netlbl_unlhsh_iface *iface; struct list_head *iter_list; struct netlbl_af4list *addr4; #if IS_ENABLED(CONFIG_IPV6) + u32 skip_addr6 = cb->args[3]; struct netlbl_af6list *addr6; #endif @@ -1182,7 +1183,7 @@ static int netlbl_unlabel_staticlist(struct sk_buff *skb, rcu_read_lock(); for (iter_bkt = skip_bkt; iter_bkt < rcu_dereference(netlbl_unlhsh)->size; - iter_bkt++, iter_chain = 0, iter_addr4 = 0, iter_addr6 = 0) { + iter_bkt++) { iter_list = &rcu_dereference(netlbl_unlhsh)->tbl[iter_bkt]; list_for_each_entry_rcu(iface, iter_list, list) { if (!iface->valid || @@ -1190,7 +1191,7 @@ static int netlbl_unlabel_staticlist(struct sk_buff *skb, continue; netlbl_af4list_foreach_rcu(addr4, &iface->addr4_list) { - if (iter_addr4++ < cb->args[2]) + if (iter_addr4++ < skip_addr4) continue; if (netlbl_unlabel_staticlist_gen( NLBL_UNLABEL_C_STATICLIST, @@ -1203,10 +1204,12 @@ static int netlbl_unlabel_staticlist(struct sk_buff *skb, goto unlabel_staticlist_return; } } + iter_addr4 = 0; + skip_addr4 = 0; #if IS_ENABLED(CONFIG_IPV6) netlbl_af6list_foreach_rcu(addr6, &iface->addr6_list) { - if (iter_addr6++ < cb->args[3]) + if (iter_addr6++ < skip_addr6) continue; if (netlbl_unlabel_staticlist_gen( NLBL_UNLABEL_C_STATICLIST, @@ -1219,8 +1222,12 @@ static int netlbl_unlabel_staticlist(struct sk_buff *skb, goto unlabel_staticlist_return; } } + iter_addr6 = 0; + skip_addr6 = 0; #endif /* IPv6 */ } + iter_chain = 0; + skip_chain = 0; } unlabel_staticlist_return: diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 832f898edb6a..9d6ef6cb9b26 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -1703,13 +1703,13 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) parms.port_no = OVSP_LOCAL; parms.upcall_portids = a[OVS_DP_ATTR_UPCALL_PID]; - err = ovs_dp_change(dp, a); - if (err) - goto err_destroy_meters; - /* So far only local changes have been made, now need the lock. */ ovs_lock(); + err = ovs_dp_change(dp, a); + if (err) + goto err_unlock_and_destroy_meters; + vport = new_vport(&parms); if (IS_ERR(vport)) { err = PTR_ERR(vport); @@ -1725,8 +1725,7 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) ovs_dp_reset_user_features(skb, info); } - ovs_unlock(); - goto err_destroy_meters; + goto err_unlock_and_destroy_meters; } err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid, @@ -1741,7 +1740,8 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) ovs_notify(&dp_datapath_genl_family, reply, info); return 0; -err_destroy_meters: +err_unlock_and_destroy_meters: + ovs_unlock(); ovs_meters_exit(dp); err_destroy_ports: kfree(dp->ports); diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c index f3486a37361a..c89c8da99f1a 100644 --- a/net/openvswitch/flow_table.c +++ b/net/openvswitch/flow_table.c @@ -390,7 +390,7 @@ static struct mask_cache *tbl_mask_cache_alloc(u32 size) } int ovs_flow_tbl_masks_cache_resize(struct flow_table *table, u32 size) { - struct mask_cache *mc = rcu_dereference(table->mask_cache); + struct mask_cache *mc = rcu_dereference_ovsl(table->mask_cache); struct mask_cache *new; if (size == mc->cache_size) diff --git a/net/rfkill/core.c b/net/rfkill/core.c index 971c73c7d34c..97101c55763d 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -876,6 +876,9 @@ static int rfkill_resume(struct device *dev) rfkill->suspended = false; + if (!rfkill->registered) + return 0; + if (!rfkill->persistent) { cur = !!(rfkill->state & RFKILL_BLOCK_SW); rfkill_set_block(rfkill, cur); diff --git a/net/sctp/input.c b/net/sctp/input.c index 55d4fc6f371d..d508f6f3dd08 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -449,7 +449,7 @@ void sctp_icmp_proto_unreachable(struct sock *sk, else { if (!mod_timer(&t->proto_unreach_timer, jiffies + (HZ/20))) - sctp_association_hold(asoc); + sctp_transport_hold(t); } } else { struct net *net = sock_net(sk); @@ -458,7 +458,7 @@ void sctp_icmp_proto_unreachable(struct sock *sk, "encountered!\n", __func__); if (del_timer(&t->proto_unreach_timer)) - sctp_association_put(asoc); + sctp_transport_put(t); sctp_do_sm(net, SCTP_EVENT_T_OTHER, SCTP_ST_OTHER(SCTP_EVENT_ICMP_PROTO_UNREACH), diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index aa821e71f05e..0948f14ce221 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -419,7 +419,7 @@ void sctp_generate_proto_unreach_event(struct timer_list *t) /* Try again later. */ if (!mod_timer(&transport->proto_unreach_timer, jiffies + (HZ/20))) - sctp_association_hold(asoc); + sctp_transport_hold(transport); goto out_unlock; } @@ -435,7 +435,7 @@ void sctp_generate_proto_unreach_event(struct timer_list *t) out_unlock: bh_unlock_sock(sk); - sctp_association_put(asoc); + sctp_transport_put(transport); } /* Handle the timeout of the RE-CONFIG timer. */ @@ -1601,12 +1601,12 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type, break; case SCTP_CMD_INIT_FAILED: - sctp_cmd_init_failed(commands, asoc, cmd->obj.u32); + sctp_cmd_init_failed(commands, asoc, cmd->obj.u16); break; case SCTP_CMD_ASSOC_FAILED: sctp_cmd_assoc_failed(commands, asoc, event_type, - subtype, chunk, cmd->obj.u32); + subtype, chunk, cmd->obj.u16); break; case SCTP_CMD_INIT_COUNTER_INC: diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 806af58f4375..60fcf31cdcfb 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -133,7 +133,7 @@ void sctp_transport_free(struct sctp_transport *transport) /* Delete the ICMP proto unreachable timer if it's active. */ if (del_timer(&transport->proto_unreach_timer)) - sctp_association_put(transport->asoc); + sctp_transport_put(transport); sctp_transport_put(transport); } diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index e9f487c8c6d5..5dd4faaf7d6e 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -979,7 +979,8 @@ static int __smc_connect(struct smc_sock *smc) /* check if smc modes and versions of CLC proposal and accept match */ rc = smc_connect_check_aclc(ini, aclc); - version = aclc->hdr.version == SMC_V1 ? SMC_V1 : version; + version = aclc->hdr.version == SMC_V1 ? SMC_V1 : SMC_V2; + ini->smcd_version = version; if (rc) goto vlan_cleanup; diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 2b19863f7171..af96f813c075 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -1309,7 +1309,8 @@ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini) ini->ism_peer_gid[ini->ism_selected]) : smcr_lgr_match(lgr, ini->ib_lcl, role, ini->ib_clcqpn)) && !lgr->sync_err && - lgr->vlan_id == ini->vlan_id && + (ini->smcd_version == SMC_V2 || + lgr->vlan_id == ini->vlan_id) && (role == SMC_CLNT || ini->is_smcd || lgr->conns_num < SMC_RMBS_PER_LGR_MAX)) { /* link group found */ diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index 1c314dbdc7fa..fc766b537ac7 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -198,9 +198,9 @@ int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport, rcu_read_lock(); ndev = rdma_read_gid_attr_ndev_rcu(attr); if (!IS_ERR(ndev) && - ((!vlan_id && !is_vlan_dev(attr->ndev)) || - (vlan_id && is_vlan_dev(attr->ndev) && - vlan_dev_vlan_id(attr->ndev) == vlan_id)) && + ((!vlan_id && !is_vlan_dev(ndev)) || + (vlan_id && is_vlan_dev(ndev) && + vlan_dev_vlan_id(ndev) == vlan_id)) && attr->gid_type == IB_GID_TYPE_ROCE) { rcu_read_unlock(); if (gid) diff --git a/net/sunrpc/sysctl.c b/net/sunrpc/sysctl.c index a18b36b5422d..3aad6ef18504 100644 --- a/net/sunrpc/sysctl.c +++ b/net/sunrpc/sysctl.c @@ -63,19 +63,20 @@ static int proc_do_xprt(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { char tmpbuf[256]; - size_t len; + ssize_t len; - if ((*ppos && !write) || !*lenp) { + if (write || *ppos) { *lenp = 0; return 0; } len = svc_print_xprts(tmpbuf, sizeof(tmpbuf)); - *lenp = memory_read_from_buffer(buffer, *lenp, ppos, tmpbuf, len); + len = memory_read_from_buffer(buffer, *lenp, ppos, tmpbuf, len); - if (*lenp < 0) { + if (len < 0) { *lenp = 0; return -EINVAL; } + *lenp = len; return 0; } diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index 5f6f86051c83..13f3143609f9 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -664,12 +664,18 @@ static int tipc_topsrv_start(struct net *net) ret = tipc_topsrv_work_start(srv); if (ret < 0) - return ret; + goto err_start; ret = tipc_topsrv_create_listener(srv); if (ret < 0) - tipc_topsrv_work_stop(srv); + goto err_create; + return 0; + +err_create: + tipc_topsrv_work_stop(srv); +err_start: + kfree(srv); return ret; } diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index cec86229a6a0..54d3e161d198 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -694,36 +694,51 @@ static void tls_device_resync_rx(struct tls_context *tls_ctx, static bool tls_device_rx_resync_async(struct tls_offload_resync_async *resync_async, - s64 resync_req, u32 *seq) + s64 resync_req, u32 *seq, u16 *rcd_delta) { u32 is_async = resync_req & RESYNC_REQ_ASYNC; u32 req_seq = resync_req >> 32; u32 req_end = req_seq + ((resync_req >> 16) & 0xffff); + u16 i; + + *rcd_delta = 0; if (is_async) { + /* shouldn't get to wraparound: + * too long in async stage, something bad happened + */ + if (WARN_ON_ONCE(resync_async->rcd_delta == USHRT_MAX)) + return false; + /* asynchronous stage: log all headers seq such that * req_seq <= seq <= end_seq, and wait for real resync request */ - if (between(*seq, req_seq, req_end) && + if (before(*seq, req_seq)) + return false; + if (!after(*seq, req_end) && resync_async->loglen < TLS_DEVICE_RESYNC_ASYNC_LOGMAX) resync_async->log[resync_async->loglen++] = *seq; + resync_async->rcd_delta++; + return false; } /* synchronous stage: check against the logged entries and * proceed to check the next entries if no match was found */ - while (resync_async->loglen) { - if (req_seq == resync_async->log[resync_async->loglen - 1] && - atomic64_try_cmpxchg(&resync_async->req, - &resync_req, 0)) { - resync_async->loglen = 0; + for (i = 0; i < resync_async->loglen; i++) + if (req_seq == resync_async->log[i] && + atomic64_try_cmpxchg(&resync_async->req, &resync_req, 0)) { + *rcd_delta = resync_async->rcd_delta - i; *seq = req_seq; + resync_async->loglen = 0; + resync_async->rcd_delta = 0; return true; } - resync_async->loglen--; - } + + resync_async->loglen = 0; + resync_async->rcd_delta = 0; if (req_seq == *seq && atomic64_try_cmpxchg(&resync_async->req, @@ -741,6 +756,7 @@ void tls_device_rx_resync_new_rec(struct sock *sk, u32 rcd_len, u32 seq) u32 sock_data, is_req_pending; struct tls_prot_info *prot; s64 resync_req; + u16 rcd_delta; u32 req_seq; if (tls_ctx->rx_conf != TLS_HW) @@ -786,8 +802,9 @@ void tls_device_rx_resync_new_rec(struct sock *sk, u32 rcd_len, u32 seq) return; if (!tls_device_rx_resync_async(rx_ctx->resync_async, - resync_req, &seq)) + resync_req, &seq, &rcd_delta)) return; + tls_bigint_subtract(rcd_sn, rcd_delta); break; } diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 95ab5545a931..2fe9e2cf8659 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1913,7 +1913,7 @@ pick_next_record: * another message type */ msg->msg_flags |= MSG_EOR; - if (ctx->control != TLS_RECORD_TYPE_DATA) + if (control != TLS_RECORD_TYPE_DATA) goto recv_end; } else { break; diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index b4d7b8aba003..d10916ab4526 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -438,7 +438,7 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) case SOCK_STREAM: if (vsock_use_local_transport(remote_cid)) new_transport = transport_local; - else if (remote_cid <= VMADDR_CID_HOST) + else if (remote_cid <= VMADDR_CID_HOST || !transport_h2g) new_transport = transport_g2h; else new_transport = transport_h2g; diff --git a/net/wireless/core.c b/net/wireless/core.c index 9f23923e8d29..240282c083aa 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1250,8 +1250,7 @@ void cfg80211_stop_iface(struct wiphy *wiphy, struct wireless_dev *wdev, } EXPORT_SYMBOL(cfg80211_stop_iface); -void cfg80211_init_wdev(struct cfg80211_registered_device *rdev, - struct wireless_dev *wdev) +void cfg80211_init_wdev(struct wireless_dev *wdev) { mutex_init(&wdev->mtx); INIT_LIST_HEAD(&wdev->event_list); @@ -1262,6 +1261,30 @@ void cfg80211_init_wdev(struct cfg80211_registered_device *rdev, spin_lock_init(&wdev->pmsr_lock); INIT_WORK(&wdev->pmsr_free_wk, cfg80211_pmsr_free_wk); +#ifdef CONFIG_CFG80211_WEXT + wdev->wext.default_key = -1; + wdev->wext.default_mgmt_key = -1; + wdev->wext.connect.auth_type = NL80211_AUTHTYPE_AUTOMATIC; +#endif + + if (wdev->wiphy->flags & WIPHY_FLAG_PS_ON_BY_DEFAULT) + wdev->ps = true; + else + wdev->ps = false; + /* allow mac80211 to determine the timeout */ + wdev->ps_timeout = -1; + + if ((wdev->iftype == NL80211_IFTYPE_STATION || + wdev->iftype == NL80211_IFTYPE_P2P_CLIENT || + wdev->iftype == NL80211_IFTYPE_ADHOC) && !wdev->use_4addr) + wdev->netdev->priv_flags |= IFF_DONT_BRIDGE; + + INIT_WORK(&wdev->disconnect_wk, cfg80211_autodisconnect_wk); +} + +void cfg80211_register_wdev(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev) +{ /* * We get here also when the interface changes network namespaces, * as it's registered into the new one, but we don't want it to @@ -1295,6 +1318,11 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, switch (state) { case NETDEV_POST_INIT: SET_NETDEV_DEVTYPE(dev, &wiphy_type); + wdev->netdev = dev; + /* can only change netns with wiphy */ + dev->features |= NETIF_F_NETNS_LOCAL; + + cfg80211_init_wdev(wdev); break; case NETDEV_REGISTER: /* @@ -1302,35 +1330,12 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, * called within code protected by it when interfaces * are added with nl80211. */ - /* can only change netns with wiphy */ - dev->features |= NETIF_F_NETNS_LOCAL; - if (sysfs_create_link(&dev->dev.kobj, &rdev->wiphy.dev.kobj, "phy80211")) { pr_err("failed to add phy80211 symlink to netdev!\n"); } - wdev->netdev = dev; -#ifdef CONFIG_CFG80211_WEXT - wdev->wext.default_key = -1; - wdev->wext.default_mgmt_key = -1; - wdev->wext.connect.auth_type = NL80211_AUTHTYPE_AUTOMATIC; -#endif - - if (wdev->wiphy->flags & WIPHY_FLAG_PS_ON_BY_DEFAULT) - wdev->ps = true; - else - wdev->ps = false; - /* allow mac80211 to determine the timeout */ - wdev->ps_timeout = -1; - - if ((wdev->iftype == NL80211_IFTYPE_STATION || - wdev->iftype == NL80211_IFTYPE_P2P_CLIENT || - wdev->iftype == NL80211_IFTYPE_ADHOC) && !wdev->use_4addr) - dev->priv_flags |= IFF_DONT_BRIDGE; - - INIT_WORK(&wdev->disconnect_wk, cfg80211_autodisconnect_wk); - cfg80211_init_wdev(rdev, wdev); + cfg80211_register_wdev(rdev, wdev); break; case NETDEV_GOING_DOWN: cfg80211_leave(rdev, wdev); diff --git a/net/wireless/core.h b/net/wireless/core.h index e1ec9ac8e608..e3e9686859d4 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -209,8 +209,9 @@ struct wiphy *wiphy_idx_to_wiphy(int wiphy_idx); int cfg80211_switch_netns(struct cfg80211_registered_device *rdev, struct net *net); -void cfg80211_init_wdev(struct cfg80211_registered_device *rdev, - struct wireless_dev *wdev); +void cfg80211_init_wdev(struct wireless_dev *wdev); +void cfg80211_register_wdev(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev); static inline void wdev_lock(struct wireless_dev *wdev) __acquires(wdev) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 554796a6c6fe..a77174b99b07 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -3885,7 +3885,8 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info) * P2P Device and NAN do not have a netdev, so don't go * through the netdev notifier and must be added here */ - cfg80211_init_wdev(rdev, wdev); + cfg80211_init_wdev(wdev); + cfg80211_register_wdev(rdev, wdev); break; default: break; diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 3dab859641e1..a04fdfb35f07 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -3616,7 +3616,7 @@ static void print_rd_rules(const struct ieee80211_regdomain *rd) power_rule = ®_rule->power_rule; if (reg_rule->flags & NL80211_RRF_AUTO_BW) - snprintf(bw, sizeof(bw), "%d KHz, %d KHz AUTO", + snprintf(bw, sizeof(bw), "%d KHz, %u KHz AUTO", freq_range->max_bandwidth_khz, reg_get_max_bandwidth(rd, reg_rule)); else diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 0bbb283f23c9..a10487e7574c 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -825,7 +825,7 @@ static int x25_connect(struct socket *sock, struct sockaddr *uaddr, sock->state = SS_CONNECTED; rc = 0; out_put_neigh: - if (rc) { + if (rc && x25->neighbour) { read_lock_bh(&x25_list_lock); x25_neigh_put(x25->neighbour); x25->neighbour = NULL; @@ -1050,6 +1050,7 @@ int x25_rx_call_request(struct sk_buff *skb, struct x25_neigh *nb, makex25->lci = lci; makex25->dest_addr = dest_addr; makex25->source_addr = source_addr; + x25_neigh_hold(nb); makex25->neighbour = nb; makex25->facilities = facilities; makex25->dte_facilities= dte_facilities; diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index b71a32eeae65..cfbec3989a76 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -1146,7 +1146,8 @@ static void xsk_destruct(struct sock *sk) if (!sock_flag(sk, SOCK_DEAD)) return; - xp_put_pool(xs->pool); + if (!xp_put_pool(xs->pool)) + xdp_put_umem(xs->umem); sk_refcnt_debug_dec(sk); } diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index 64c9e55d4d4e..8a3bf4e1318e 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -251,15 +251,18 @@ void xp_get_pool(struct xsk_buff_pool *pool) refcount_inc(&pool->users); } -void xp_put_pool(struct xsk_buff_pool *pool) +bool xp_put_pool(struct xsk_buff_pool *pool) { if (!pool) - return; + return false; if (refcount_dec_and_test(&pool->users)) { INIT_WORK(&pool->work, xp_release_deferred); schedule_work(&pool->work); + return true; } + + return false; } static struct xsk_dma_map *xp_find_dma_map(struct xsk_buff_pool *pool) diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c index aa4cdcf69d47..9b8e292a7c6a 100644 --- a/net/xfrm/xfrm_interface.c +++ b/net/xfrm/xfrm_interface.c @@ -803,14 +803,14 @@ static struct xfrm6_tunnel xfrmi_ipv6_handler __read_mostly = { .handler = xfrmi6_rcv_tunnel, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi6_err, - .priority = -1, + .priority = 2, }; static struct xfrm6_tunnel xfrmi_ip6ip_handler __read_mostly = { .handler = xfrmi6_rcv_tunnel, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi6_err, - .priority = -1, + .priority = 2, }; #endif @@ -848,14 +848,14 @@ static struct xfrm_tunnel xfrmi_ipip_handler __read_mostly = { .handler = xfrmi4_rcv_tunnel, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi4_err, - .priority = -1, + .priority = 3, }; static struct xfrm_tunnel xfrmi_ipip6_handler __read_mostly = { .handler = xfrmi4_rcv_tunnel, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi4_err, - .priority = -1, + .priority = 2, }; #endif diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index bbd4643d7e82..a77da7aae6fe 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -2004,6 +2004,7 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high) int err = -ENOENT; __be32 minspi = htonl(low); __be32 maxspi = htonl(high); + __be32 newspi = 0; u32 mark = x->mark.v & x->mark.m; spin_lock_bh(&x->lock); @@ -2022,21 +2023,22 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high) xfrm_state_put(x0); goto unlock; } - x->id.spi = minspi; + newspi = minspi; } else { u32 spi = 0; for (h = 0; h < high-low+1; h++) { spi = low + prandom_u32()%(high-low+1); x0 = xfrm_state_lookup(net, mark, &x->id.daddr, htonl(spi), x->id.proto, x->props.family); if (x0 == NULL) { - x->id.spi = htonl(spi); + newspi = htonl(spi); break; } xfrm_state_put(x0); } } - if (x->id.spi) { + if (newspi) { spin_lock_bh(&net->xfrm.xfrm_state_lock); + x->id.spi = newspi; h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, x->props.family); hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h); spin_unlock_bh(&net->xfrm.xfrm_state_lock); diff --git a/samples/bpf/task_fd_query_user.c b/samples/bpf/task_fd_query_user.c index 4a74531dc403..b68bd2f8fdc9 100644 --- a/samples/bpf/task_fd_query_user.c +++ b/samples/bpf/task_fd_query_user.c @@ -290,7 +290,7 @@ static int test_debug_fs_uprobe(char *binary_path, long offset, bool is_return) int main(int argc, char **argv) { - struct rlimit r = {1024*1024, RLIM_INFINITY}; + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; extern char __executable_start; char filename[256], buf[256]; __u64 uprobe_file_offset; diff --git a/samples/bpf/tracex2_user.c b/samples/bpf/tracex2_user.c index 3e36b3e4e3ef..3d6eab711d23 100644 --- a/samples/bpf/tracex2_user.c +++ b/samples/bpf/tracex2_user.c @@ -116,7 +116,7 @@ static void int_exit(int sig) int main(int ac, char **argv) { - struct rlimit r = {1024*1024, RLIM_INFINITY}; + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; long key, next_key, value; struct bpf_link *links[2]; struct bpf_program *prog; diff --git a/samples/bpf/tracex3_user.c b/samples/bpf/tracex3_user.c index 70e987775c15..83e0fecbb01a 100644 --- a/samples/bpf/tracex3_user.c +++ b/samples/bpf/tracex3_user.c @@ -107,7 +107,7 @@ static void print_hist(int fd) int main(int ac, char **argv) { - struct rlimit r = {1024*1024, RLIM_INFINITY}; + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_link *links[2]; struct bpf_program *prog; struct bpf_object *obj; diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c index 6fb8dbde62c5..f78cb18319aa 100644 --- a/samples/bpf/xdp_redirect_cpu_user.c +++ b/samples/bpf/xdp_redirect_cpu_user.c @@ -765,7 +765,7 @@ static int load_cpumap_prog(char *file_name, char *prog_name, int main(int argc, char **argv) { - struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY}; + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; char *prog_name = "xdp_cpu_map5_lb_hash_ip_pairs"; char *mprog_filename = "xdp_redirect_kern.o"; char *redir_interface = NULL, *redir_map = NULL; diff --git a/samples/bpf/xdp_rxq_info_user.c b/samples/bpf/xdp_rxq_info_user.c index caa4e7ffcfc7..93fa1bc54f13 100644 --- a/samples/bpf/xdp_rxq_info_user.c +++ b/samples/bpf/xdp_rxq_info_user.c @@ -450,7 +450,7 @@ static void stats_poll(int interval, int action, __u32 cfg_opt) int main(int argc, char **argv) { __u32 cfg_options= NO_TOUCH ; /* Default: Don't touch packet memory */ - struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY}; + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_prog_load_attr prog_load_attr = { .prog_type = BPF_PROG_TYPE_XDP, }; diff --git a/scripts/bpf_helpers_doc.py b/scripts/bpf_helpers_doc.py index 6769caae142f..31484377b8b1 100755 --- a/scripts/bpf_helpers_doc.py +++ b/scripts/bpf_helpers_doc.py @@ -408,6 +408,7 @@ class PrinterHelpers(Printer): 'struct bpf_perf_event_data', 'struct bpf_perf_event_value', 'struct bpf_pidns_info', + 'struct bpf_redir_neigh', 'struct bpf_sock', 'struct bpf_sock_addr', 'struct bpf_sock_ops', diff --git a/scripts/get_abi.pl b/scripts/get_abi.pl index 2cb592f8eba4..68dab828a722 100755 --- a/scripts/get_abi.pl +++ b/scripts/get_abi.pl @@ -287,6 +287,8 @@ my $bondary = qr { (?<![\w\/\`\{])(?=[\w\/\`\{])|(?<=[\w\/\`\{])(?![\w\/\`\{]) } sub output_rest { create_labels(); + my $part = ""; + foreach my $what (sort { ($data{$a}->{type} eq "File") cmp ($data{$b}->{type} eq "File") || $a cmp $b @@ -306,6 +308,21 @@ sub output_rest { $w =~ s/([\(\)\_\-\*\=\^\~\\])/\\$1/g; if ($type ne "File") { + my $cur_part = $what; + if ($what =~ '/') { + if ($what =~ m#^(\/?(?:[\w\-]+\/?){1,2})#) { + $cur_part = "Symbols under $1"; + $cur_part =~ s,/$,,; + } + } + + if ($cur_part ne "" && $part ne $cur_part) { + $part = $cur_part; + my $bar = $part; + $bar =~ s/./-/g; + print "$part\n$bar\n\n"; + } + printf ".. _%s:\n\n", $data{$what}->{label}; my @names = split /, /,$w; @@ -352,6 +369,12 @@ sub output_rest { if (!($desc =~ /^\s*$/)) { if ($description_is_rst) { + # Remove title markups from the description + # Having titles inside ABI files will only work if extra + # care would be taken in order to strictly follow the same + # level order for each markup. + $desc =~ s/\n[\-\*\=\^\~]+\n/\n\n/g; + # Enrich text by creating cross-references $desc =~ s,Documentation/(?!devicetree)(\S+)\.rst,:doc:`/$1`,g; diff --git a/scripts/kernel-doc b/scripts/kernel-doc index c8f6b11d5da1..f699cf05d409 100755 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -1092,7 +1092,11 @@ sub output_struct_rst(%) { print "\n\n.. c:type:: " . $name . "\n\n"; } else { my $name = $args{'struct'}; - print "\n\n.. c:struct:: " . $name . "\n\n"; + if ($args{'type'} eq 'union') { + print "\n\n.. c:union:: " . $name . "\n\n"; + } else { + print "\n\n.. c:struct:: " . $name . "\n\n"; + } } print_lineno($declaration_start_line); $lineprefix = " "; @@ -1427,20 +1431,25 @@ sub dump_enum($$) { } } +my $typedef_type = qr { ((?:\s+[\w\*]+){1,8})\s* }x; +my $typedef_ident = qr { \*?\s*(\w\S+)\s* }x; +my $typedef_args = qr { \s*\((.*)\); }x; + +my $typedef1 = qr { typedef$typedef_type\($typedef_ident\)$typedef_args }x; +my $typedef2 = qr { typedef$typedef_type$typedef_ident$typedef_args }x; + sub dump_typedef($$) { my $x = shift; my $file = shift; $x =~ s@/\*.*?\*/@@gos; # strip comments. - # Parse function prototypes - if ($x =~ /typedef\s+(\w+)\s*\(\*\s*(\w\S+)\s*\)\s*\((.*)\);/ || - $x =~ /typedef\s+(\w+)\s*(\w\S+)\s*\s*\((.*)\);/) { - - # Function typedefs + # Parse function typedef prototypes + if ($x =~ $typedef1 || $x =~ $typedef2) { $return_type = $1; $declaration_name = $2; my $args = $3; + $return_type =~ s/^\s+//; create_parameterlist($args, ',', $file, $declaration_name); diff --git a/security/selinux/ibpkey.c b/security/selinux/ibpkey.c index f68a7617cfb9..3a63a989e55e 100644 --- a/security/selinux/ibpkey.c +++ b/security/selinux/ibpkey.c @@ -151,8 +151,10 @@ static int sel_ib_pkey_sid_slow(u64 subnet_prefix, u16 pkey_num, u32 *sid) * is valid, it just won't be added to the cache. */ new = kzalloc(sizeof(*new), GFP_ATOMIC); - if (!new) + if (!new) { + ret = -ENOMEM; goto out; + } new->psec.subnet_prefix = subnet_prefix; new->psec.pkey = pkey_num; diff --git a/sound/core/control.c b/sound/core/control.c index 421ddc76f264..3b44378b9dec 100644 --- a/sound/core/control.c +++ b/sound/core/control.c @@ -1539,7 +1539,7 @@ static int snd_ctl_elem_add(struct snd_ctl_file *file, unlock: up_write(&card->controls_rwsem); - return 0; + return err; } static int snd_ctl_elem_add_user(struct snd_ctl_file *file, @@ -1925,8 +1925,8 @@ EXPORT_SYMBOL(snd_ctl_unregister_ioctl); #ifdef CONFIG_COMPAT /** - * snd_ctl_unregister_ioctl - de-register the device-specific compat 32bit - * control-ioctls + * snd_ctl_unregister_ioctl_compat - de-register the device-specific compat + * 32bit control-ioctls * @fcn: ioctl callback function to unregister */ int snd_ctl_unregister_ioctl_compat(snd_kctl_ioctl_func_t fcn) diff --git a/sound/core/pcm_dmaengine.c b/sound/core/pcm_dmaengine.c index 4d059ff2b2e4..4d0e8fe535a1 100644 --- a/sound/core/pcm_dmaengine.c +++ b/sound/core/pcm_dmaengine.c @@ -356,7 +356,8 @@ int snd_dmaengine_pcm_close(struct snd_pcm_substream *substream) EXPORT_SYMBOL_GPL(snd_dmaengine_pcm_close); /** - * snd_dmaengine_pcm_release_chan_close - Close a dmaengine based PCM substream and release channel + * snd_dmaengine_pcm_close_release_chan - Close a dmaengine based PCM + * substream and release channel * @substream: PCM substream * * Releases the DMA channel associated with the PCM substream. diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c index d531e1bc2b81..bda3514c7b2d 100644 --- a/sound/core/pcm_lib.c +++ b/sound/core/pcm_lib.c @@ -490,7 +490,7 @@ void snd_pcm_set_ops(struct snd_pcm *pcm, int direction, EXPORT_SYMBOL(snd_pcm_set_ops); /** - * snd_pcm_sync - set the PCM sync id + * snd_pcm_set_sync - set the PCM sync id * @substream: the pcm substream * * Sets the PCM sync identifier for the card. diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 9e0b2d73faf6..47b155a49226 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -112,7 +112,7 @@ void snd_pcm_stream_lock(struct snd_pcm_substream *substream) EXPORT_SYMBOL_GPL(snd_pcm_stream_lock); /** - * snd_pcm_stream_lock - Unlock the PCM stream + * snd_pcm_stream_unlock - Unlock the PCM stream * @substream: PCM substream * * This unlocks the PCM stream that has been locked via snd_pcm_stream_lock(). @@ -595,7 +595,7 @@ static void snd_pcm_sync_stop(struct snd_pcm_substream *substream) } /** - * snd_pcm_hw_param_choose - choose a configuration defined by @params + * snd_pcm_hw_params_choose - choose a configuration defined by @params * @pcm: PCM instance * @params: the hw_params instance * diff --git a/sound/firewire/fireworks/fireworks_transaction.c b/sound/firewire/fireworks/fireworks_transaction.c index 0f533f5bd960..9f8c53b39f95 100644 --- a/sound/firewire/fireworks/fireworks_transaction.c +++ b/sound/firewire/fireworks/fireworks_transaction.c @@ -123,7 +123,7 @@ copy_resp_to_buf(struct snd_efw *efw, void *data, size_t length, int *rcode) t = (struct snd_efw_transaction *)data; length = min_t(size_t, be32_to_cpu(t->length) * sizeof(u32), length); - spin_lock_irq(&efw->lock); + spin_lock(&efw->lock); if (efw->push_ptr < efw->pull_ptr) capacity = (unsigned int)(efw->pull_ptr - efw->push_ptr); @@ -190,7 +190,7 @@ handle_resp_for_user(struct fw_card *card, int generation, int source, copy_resp_to_buf(efw, data, length, rcode); end: - spin_unlock_irq(&instances_lock); + spin_unlock(&instances_lock); } static void diff --git a/sound/hda/ext/hdac_ext_controller.c b/sound/hda/ext/hdac_ext_controller.c index 4d060d5b1db6..b0c0ef824d7d 100644 --- a/sound/hda/ext/hdac_ext_controller.c +++ b/sound/hda/ext/hdac_ext_controller.c @@ -148,6 +148,8 @@ struct hdac_ext_link *snd_hdac_ext_bus_get_link(struct hdac_bus *bus, return NULL; if (bus->idx != bus_idx) return NULL; + if (addr < 0 || addr > 31) + return NULL; list_for_each_entry(hlink, &bus->hlink_list, list) { for (i = 0; i < HDA_MAX_CODECS; i++) { diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index a356c21edb90..4bb58e8b08a8 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -2934,7 +2934,7 @@ static void hda_call_codec_resume(struct hda_codec *codec) snd_hdac_leave_pm(&codec->core); } -static int hda_codec_runtime_suspend(struct device *dev) +static int hda_codec_suspend(struct device *dev) { struct hda_codec *codec = dev_to_hda_codec(dev); unsigned int state; @@ -2953,7 +2953,7 @@ static int hda_codec_runtime_suspend(struct device *dev) return 0; } -static int hda_codec_runtime_resume(struct device *dev) +static int hda_codec_resume(struct device *dev) { struct hda_codec *codec = dev_to_hda_codec(dev); @@ -2967,57 +2967,70 @@ static int hda_codec_runtime_resume(struct device *dev) pm_runtime_mark_last_busy(dev); return 0; } + +static int hda_codec_runtime_suspend(struct device *dev) +{ + return hda_codec_suspend(dev); +} + +static int hda_codec_runtime_resume(struct device *dev) +{ + return hda_codec_resume(dev); +} + #endif /* CONFIG_PM */ #ifdef CONFIG_PM_SLEEP -static int hda_codec_force_resume(struct device *dev) +static int hda_codec_pm_prepare(struct device *dev) +{ + return pm_runtime_suspended(dev); +} + +static void hda_codec_pm_complete(struct device *dev) { struct hda_codec *codec = dev_to_hda_codec(dev); - int ret; - ret = pm_runtime_force_resume(dev); - /* schedule jackpoll work for jack detection update */ - if (codec->jackpoll_interval || - (pm_runtime_suspended(dev) && hda_codec_need_resume(codec))) - schedule_delayed_work(&codec->jackpoll_work, - codec->jackpoll_interval); - return ret; + if (pm_runtime_suspended(dev) && (codec->jackpoll_interval || + hda_codec_need_resume(codec) || codec->forced_resume)) + pm_request_resume(dev); } static int hda_codec_pm_suspend(struct device *dev) { dev->power.power_state = PMSG_SUSPEND; - return pm_runtime_force_suspend(dev); + return hda_codec_suspend(dev); } static int hda_codec_pm_resume(struct device *dev) { dev->power.power_state = PMSG_RESUME; - return hda_codec_force_resume(dev); + return hda_codec_resume(dev); } static int hda_codec_pm_freeze(struct device *dev) { dev->power.power_state = PMSG_FREEZE; - return pm_runtime_force_suspend(dev); + return hda_codec_suspend(dev); } static int hda_codec_pm_thaw(struct device *dev) { dev->power.power_state = PMSG_THAW; - return hda_codec_force_resume(dev); + return hda_codec_resume(dev); } static int hda_codec_pm_restore(struct device *dev) { dev->power.power_state = PMSG_RESTORE; - return hda_codec_force_resume(dev); + return hda_codec_resume(dev); } #endif /* CONFIG_PM_SLEEP */ /* referred in hda_bind.c */ const struct dev_pm_ops hda_codec_driver_pm = { #ifdef CONFIG_PM_SLEEP + .prepare = hda_codec_pm_prepare, + .complete = hda_codec_pm_complete, .suspend = hda_codec_pm_suspend, .resume = hda_codec_pm_resume, .freeze = hda_codec_pm_freeze, diff --git a/sound/pci/hda/hda_controller.h b/sound/pci/hda/hda_controller.h index be63ead8161f..68f9668788ea 100644 --- a/sound/pci/hda/hda_controller.h +++ b/sound/pci/hda/hda_controller.h @@ -41,7 +41,7 @@ /* 24 unused */ #define AZX_DCAPS_COUNT_LPIB_DELAY (1 << 25) /* Take LPIB as delay */ #define AZX_DCAPS_PM_RUNTIME (1 << 26) /* runtime PM support */ -#define AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP (1 << 27) /* Workaround for spurious wakeups after suspend */ +/* 27 unused */ #define AZX_DCAPS_CORBRP_SELF_CLEAR (1 << 28) /* CORBRP clears itself after reset */ #define AZX_DCAPS_NO_MSI64 (1 << 29) /* Stick to 32-bit MSIs */ #define AZX_DCAPS_SEPARATE_STREAM_TAG (1 << 30) /* capture and playback use separate stream tag */ @@ -143,6 +143,7 @@ struct azx { unsigned int align_buffer_size:1; unsigned int region_requested:1; unsigned int disabled:1; /* disabled by vga_switcheroo */ + unsigned int pm_prepared:1; /* GTS present */ unsigned int gts_present:1; diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 749b88090970..6852668f1bcb 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -297,8 +297,7 @@ enum { /* PCH for HSW/BDW; with runtime PM */ /* no i915 binding for this as HSW/BDW has another controller for HDMI */ #define AZX_DCAPS_INTEL_PCH \ - (AZX_DCAPS_INTEL_PCH_BASE | AZX_DCAPS_PM_RUNTIME |\ - AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP) + (AZX_DCAPS_INTEL_PCH_BASE | AZX_DCAPS_PM_RUNTIME) /* HSW HDMI */ #define AZX_DCAPS_INTEL_HASWELL \ @@ -985,7 +984,7 @@ static void __azx_runtime_suspend(struct azx *chip) display_power(chip, false); } -static void __azx_runtime_resume(struct azx *chip, bool from_rt) +static void __azx_runtime_resume(struct azx *chip) { struct hda_intel *hda = container_of(chip, struct hda_intel, chip); struct hdac_bus *bus = azx_bus(chip); @@ -1002,7 +1001,8 @@ static void __azx_runtime_resume(struct azx *chip, bool from_rt) azx_init_pci(chip); hda_intel_init_chip(chip, true); - if (from_rt) { + /* Avoid codec resume if runtime resume is for system suspend */ + if (!chip->pm_prepared) { list_for_each_codec(codec, &chip->bus) { if (codec->relaxed_resume) continue; @@ -1018,6 +1018,29 @@ static void __azx_runtime_resume(struct azx *chip, bool from_rt) } #ifdef CONFIG_PM_SLEEP +static int azx_prepare(struct device *dev) +{ + struct snd_card *card = dev_get_drvdata(dev); + struct azx *chip; + + chip = card->private_data; + chip->pm_prepared = 1; + + /* HDA controller always requires different WAKEEN for runtime suspend + * and system suspend, so don't use direct-complete here. + */ + return 0; +} + +static void azx_complete(struct device *dev) +{ + struct snd_card *card = dev_get_drvdata(dev); + struct azx *chip; + + chip = card->private_data; + chip->pm_prepared = 0; +} + static int azx_suspend(struct device *dev) { struct snd_card *card = dev_get_drvdata(dev); @@ -1029,15 +1052,7 @@ static int azx_suspend(struct device *dev) chip = card->private_data; bus = azx_bus(chip); - snd_power_change_state(card, SNDRV_CTL_POWER_D3hot); - /* An ugly workaround: direct call of __azx_runtime_suspend() and - * __azx_runtime_resume() for old Intel platforms that suffer from - * spurious wakeups after S3 suspend - */ - if (chip->driver_caps & AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP) - __azx_runtime_suspend(chip); - else - pm_runtime_force_suspend(dev); + __azx_runtime_suspend(chip); if (bus->irq >= 0) { free_irq(bus->irq, chip); bus->irq = -1; @@ -1066,11 +1081,7 @@ static int azx_resume(struct device *dev) if (azx_acquire_irq(chip, 1) < 0) return -EIO; - if (chip->driver_caps & AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP) - __azx_runtime_resume(chip, false); - else - pm_runtime_force_resume(dev); - snd_power_change_state(card, SNDRV_CTL_POWER_D0); + __azx_runtime_resume(chip); trace_azx_resume(chip); return 0; @@ -1118,10 +1129,7 @@ static int azx_runtime_suspend(struct device *dev) chip = card->private_data; /* enable controller wake up event */ - if (snd_power_get_state(card) == SNDRV_CTL_POWER_D0) { - azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) | - STATESTS_INT_MASK); - } + azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) | STATESTS_INT_MASK); __azx_runtime_suspend(chip); trace_azx_runtime_suspend(chip); @@ -1132,18 +1140,14 @@ static int azx_runtime_resume(struct device *dev) { struct snd_card *card = dev_get_drvdata(dev); struct azx *chip; - bool from_rt = snd_power_get_state(card) == SNDRV_CTL_POWER_D0; if (!azx_is_pm_ready(card)) return 0; chip = card->private_data; - __azx_runtime_resume(chip, from_rt); + __azx_runtime_resume(chip); /* disable controller Wake Up event*/ - if (from_rt) { - azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) & - ~STATESTS_INT_MASK); - } + azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) & ~STATESTS_INT_MASK); trace_azx_runtime_resume(chip); return 0; @@ -1177,6 +1181,8 @@ static int azx_runtime_idle(struct device *dev) static const struct dev_pm_ops azx_pm = { SET_SYSTEM_SLEEP_PM_OPS(azx_suspend, azx_resume) #ifdef CONFIG_PM_SLEEP + .prepare = azx_prepare, + .complete = azx_complete, .freeze_noirq = azx_freeze_noirq, .thaw_noirq = azx_thaw_noirq, #endif @@ -2356,6 +2362,7 @@ static int azx_probe_continue(struct azx *chip) if (azx_has_pm_runtime(chip)) { pm_runtime_use_autosuspend(&pci->dev); + pm_runtime_allow(&pci->dev); pm_runtime_put_autosuspend(&pci->dev); } @@ -2499,6 +2506,9 @@ static const struct pci_device_id azx_ids[] = { /* DG1 */ { PCI_DEVICE(0x8086, 0x490d), .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, + /* Alderlake-S */ + { PCI_DEVICE(0x8086, 0x7ad0), + .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, /* Elkhart Lake */ { PCI_DEVICE(0x8086, 0x4b55), .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c index e0c38f2735c6..d8370a417e3d 100644 --- a/sound/pci/hda/patch_ca0132.c +++ b/sound/pci/hda/patch_ca0132.c @@ -9183,6 +9183,8 @@ static void ca0132_mmio_init(struct hda_codec *codec) case QUIRK_AE5: ca0132_mmio_init_ae5(codec); break; + default: + break; } } diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index ccd1df059654..b0068f8ca46d 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -4274,6 +4274,7 @@ HDA_CODEC_ENTRY(0x8086280d, "Geminilake HDMI", patch_i915_glk_hdmi), HDA_CODEC_ENTRY(0x8086280f, "Icelake HDMI", patch_i915_icl_hdmi), HDA_CODEC_ENTRY(0x80862812, "Tigerlake HDMI", patch_i915_tgl_hdmi), HDA_CODEC_ENTRY(0x80862814, "DG1 HDMI", patch_i915_tgl_hdmi), +HDA_CODEC_ENTRY(0x80862815, "Alderlake HDMI", patch_i915_tgl_hdmi), HDA_CODEC_ENTRY(0x80862816, "Rocketlake HDMI", patch_i915_tgl_hdmi), HDA_CODEC_ENTRY(0x8086281a, "Jasperlake HDMI", patch_i915_icl_hdmi), HDA_CODEC_ENTRY(0x8086281b, "Elkhartlake HDMI", patch_i915_icl_hdmi), diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index f2398721ac1e..739dbaf54517 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -2522,13 +2522,23 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK_VENDOR(0x1462, "MSI", ALC882_FIXUP_GPIO3), SND_PCI_QUIRK(0x147b, 0x107a, "Abit AW9D-MAX", ALC882_FIXUP_ABIT_AW9D_MAX), SND_PCI_QUIRK(0x1558, 0x9501, "Clevo P950HR", ALC1220_FIXUP_CLEVO_P950), + SND_PCI_QUIRK(0x1558, 0x9506, "Clevo P955HQ", ALC1220_FIXUP_CLEVO_P950), + SND_PCI_QUIRK(0x1558, 0x950A, "Clevo P955H[PR]", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1558, 0x95e1, "Clevo P95xER", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1558, 0x95e2, "Clevo P950ER", ALC1220_FIXUP_CLEVO_P950), + SND_PCI_QUIRK(0x1558, 0x95e3, "Clevo P955[ER]T", ALC1220_FIXUP_CLEVO_P950), + SND_PCI_QUIRK(0x1558, 0x95e4, "Clevo P955ER", ALC1220_FIXUP_CLEVO_P950), + SND_PCI_QUIRK(0x1558, 0x95e5, "Clevo P955EE6", ALC1220_FIXUP_CLEVO_P950), + SND_PCI_QUIRK(0x1558, 0x95e6, "Clevo P950R[CDF]", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1558, 0x96e1, "Clevo P960[ER][CDFN]-K", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1558, 0x97e1, "Clevo P970[ER][CDFN]", ALC1220_FIXUP_CLEVO_P950), + SND_PCI_QUIRK(0x1558, 0x97e2, "Clevo P970RC-M", ALC1220_FIXUP_CLEVO_P950), + SND_PCI_QUIRK(0x1558, 0x50d3, "Clevo PC50[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x65d1, "Clevo PB51[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), + SND_PCI_QUIRK(0x1558, 0x65d2, "Clevo PB51R[CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), + SND_PCI_QUIRK(0x1558, 0x65e1, "Clevo PB51[ED][DF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x67d1, "Clevo PB71[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), - SND_PCI_QUIRK(0x1558, 0x50d3, "Clevo PC50[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), + SND_PCI_QUIRK(0x1558, 0x67e1, "Clevo PB71[DE][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x70d1, "Clevo PC70[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x7714, "Clevo X170", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK_VENDOR(0x1558, "Clevo laptop", ALC882_FIXUP_EAPD), @@ -4216,6 +4226,12 @@ static void alc286_fixup_hp_gpio_led(struct hda_codec *codec, alc_fixup_hp_gpio_led(codec, action, 0x02, 0x20); } +static void alc287_fixup_hp_gpio_led(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + alc_fixup_hp_gpio_led(codec, action, 0x10, 0); +} + /* turn on/off mic-mute LED per capture hook via VREF change */ static int vref_micmute_led_set(struct led_classdev *led_cdev, enum led_brightness brightness) @@ -6008,6 +6024,27 @@ static void alc285_fixup_invalidate_dacs(struct hda_codec *codec, snd_hda_override_wcaps(codec, 0x03, 0); } +static void alc_combo_jack_hp_jd_restart(struct hda_codec *codec) +{ + switch (codec->core.vendor_id) { + case 0x10ec0274: + case 0x10ec0294: + case 0x10ec0225: + case 0x10ec0295: + case 0x10ec0299: + alc_update_coef_idx(codec, 0x4a, 0x8000, 1 << 15); /* Reset HP JD */ + alc_update_coef_idx(codec, 0x4a, 0x8000, 0 << 15); + break; + case 0x10ec0235: + case 0x10ec0236: + case 0x10ec0255: + case 0x10ec0256: + alc_update_coef_idx(codec, 0x1b, 0x8000, 1 << 15); /* Reset HP JD */ + alc_update_coef_idx(codec, 0x1b, 0x8000, 0 << 15); + break; + } +} + static void alc295_fixup_chromebook(struct hda_codec *codec, const struct hda_fixup *fix, int action) { @@ -6018,16 +6055,7 @@ static void alc295_fixup_chromebook(struct hda_codec *codec, spec->ultra_low_power = true; break; case HDA_FIXUP_ACT_INIT: - switch (codec->core.vendor_id) { - case 0x10ec0295: - alc_update_coef_idx(codec, 0x4a, 0x8000, 1 << 15); /* Reset HP JD */ - alc_update_coef_idx(codec, 0x4a, 0x8000, 0 << 15); - break; - case 0x10ec0236: - alc_update_coef_idx(codec, 0x1b, 0x8000, 1 << 15); /* Reset HP JD */ - alc_update_coef_idx(codec, 0x1b, 0x8000, 0 << 15); - break; - } + alc_combo_jack_hp_jd_restart(codec); break; } } @@ -6083,6 +6111,16 @@ static void alc285_fixup_hp_gpio_amp_init(struct hda_codec *codec, alc_write_coef_idx(codec, 0x65, 0x0); } +static void alc274_fixup_hp_headset_mic(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + switch (action) { + case HDA_FIXUP_ACT_INIT: + alc_combo_jack_hp_jd_restart(codec); + break; + } +} + /* for hda_fixup_thinkpad_acpi() */ #include "thinkpad_helper.c" @@ -6277,6 +6315,11 @@ enum { ALC256_FIXUP_INTEL_NUC8_RUGGED, ALC255_FIXUP_XIAOMI_HEADSET_MIC, ALC274_FIXUP_HP_MIC, + ALC274_FIXUP_HP_HEADSET_MIC, + ALC256_FIXUP_ASUS_HPE, + ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK, + ALC287_FIXUP_HP_GPIO_LED, + ALC256_FIXUP_HP_HEADSET_MIC, }; static const struct hda_fixup alc269_fixups[] = { @@ -7664,6 +7707,37 @@ static const struct hda_fixup alc269_fixups[] = { { } }, }, + [ALC274_FIXUP_HP_HEADSET_MIC] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc274_fixup_hp_headset_mic, + .chained = true, + .chain_id = ALC274_FIXUP_HP_MIC + }, + [ALC256_FIXUP_ASUS_HPE] = { + .type = HDA_FIXUP_VERBS, + .v.verbs = (const struct hda_verb[]) { + /* Set EAPD high */ + { 0x20, AC_VERB_SET_COEF_INDEX, 0x0f }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x7778 }, + { } + }, + .chained = true, + .chain_id = ALC294_FIXUP_ASUS_HEADSET_MIC + }, + [ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_headset_jack, + .chained = true, + .chain_id = ALC269_FIXUP_THINKPAD_ACPI + }, + [ALC287_FIXUP_HP_GPIO_LED] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc287_fixup_hp_gpio_led, + }, + [ALC256_FIXUP_HP_HEADSET_MIC] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc274_fixup_hp_headset_mic, + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -7815,10 +7889,11 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x869d, "HP", ALC236_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x8729, "HP", ALC285_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8736, "HP", ALC285_FIXUP_HP_GPIO_AMP_INIT), - SND_PCI_QUIRK(0x103c, 0x874e, "HP", ALC274_FIXUP_HP_MIC), SND_PCI_QUIRK(0x103c, 0x8760, "HP", ALC285_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x877a, "HP", ALC285_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x877d, "HP", ALC236_FIXUP_HP_MUTE_LED), + SND_PCI_QUIRK(0x103c, 0x87f4, "HP", ALC287_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x87f5, "HP", ALC287_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300), SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), @@ -7848,6 +7923,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1bbd, "ASUS Z550MA", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x1c23, "Asus X55U", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x1043, 0x1ccd, "ASUS X555UB", ALC256_FIXUP_ASUS_MIC), + SND_PCI_QUIRK(0x1043, 0x1d4e, "ASUS TM420", ALC256_FIXUP_ASUS_HPE), SND_PCI_QUIRK(0x1043, 0x1e11, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA502), SND_PCI_QUIRK(0x1043, 0x1f11, "ASUS Zephyrus G14", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1881, "ASUS Zephyrus S/M", ALC294_FIXUP_ASUS_GX502_PINS), @@ -7883,11 +7959,49 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1462, 0xb120, "MSI Cubi MS-B120", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1462, 0xb171, "Cubi N 8GL (MS-B171)", ALC283_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x1558, 0x1323, "Clevo N130ZU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x1325, "System76 Darter Pro (darp5)", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x1401, "Clevo L140[CZ]U", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x1403, "Clevo N140CU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x1404, "Clevo N150CU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x14a1, "Clevo L141MU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x4018, "Clevo NV40M[BE]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x4019, "Clevo NV40MZ", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x4020, "Clevo NV40MB", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x40a1, "Clevo NL40GU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x40c1, "Clevo NL40[CZ]U", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x40d1, "Clevo NL41DU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x50a3, "Clevo NJ51GU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x50b3, "Clevo NK50S[BEZ]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x50b6, "Clevo NK50S5", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x50b8, "Clevo NK50SZ", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x50d5, "Clevo NP50D5", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x50f0, "Clevo NH50A[CDF]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x50f3, "Clevo NH58DPQ", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x5101, "Clevo S510WU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x5157, "Clevo W517GU1", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x51a1, "Clevo NS50MU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x70a1, "Clevo NB70T[HJK]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x70b3, "Clevo NK70SB", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x8228, "Clevo NR40BU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x8520, "Clevo NH50D[CD]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x8521, "Clevo NH77D[CD]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x8535, "Clevo NH50D[BE]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x8536, "Clevo NH79D[BE]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x8550, "System76 Gazelle (gaze14)", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x8551, "System76 Gazelle (gaze14)", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x8560, "System76 Gazelle (gaze14)", ALC269_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1558, 0x8561, "System76 Gazelle (gaze14)", ALC269_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x1558, 0x8668, "Clevo NP50B[BE]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x8680, "Clevo NJ50LU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x8686, "Clevo NH50[CZ]U", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x8a20, "Clevo NH55DCQ-Y", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x8a51, "Clevo NH70RCQ-Y", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x8d50, "Clevo NH55RCQ-M", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x951d, "Clevo N950T[CDF]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x961d, "Clevo N960S[CDF]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x971d, "Clevo N970T[CDF]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0xa500, "Clevo NL53RU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x17aa, 0x1036, "Lenovo P520", ALC233_FIXUP_LENOVO_MULTI_CODECS), SND_PCI_QUIRK(0x17aa, 0x1048, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x17aa, 0x20f2, "Thinkpad SL410/510", ALC269_FIXUP_SKU_IGNORE), @@ -7925,6 +8039,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x225d, "Thinkpad T480", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x17aa, 0x2292, "Thinkpad X1 Carbon 7th", ALC285_FIXUP_THINKPAD_HEADSET_JACK), SND_PCI_QUIRK(0x17aa, 0x22be, "Thinkpad X1 Carbon 8th", ALC285_FIXUP_THINKPAD_HEADSET_JACK), + SND_PCI_QUIRK(0x17aa, 0x22c1, "Thinkpad P1 Gen 3", ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK), + SND_PCI_QUIRK(0x17aa, 0x22c2, "Thinkpad X1 Extreme Gen 3", ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK), SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), SND_PCI_QUIRK(0x17aa, 0x30e2, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), SND_PCI_QUIRK(0x17aa, 0x310c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION), @@ -8237,6 +8353,10 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x19, 0x02a11020}, {0x1a, 0x02a11030}, {0x21, 0x0221101f}), + SND_HDA_PIN_QUIRK(0x10ec0236, 0x103c, "HP", ALC256_FIXUP_HP_HEADSET_MIC, + {0x14, 0x90170110}, + {0x19, 0x02a11020}, + {0x21, 0x02211030}), SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL2_MIC_NO_PRESENCE, {0x14, 0x90170110}, {0x21, 0x02211020}), @@ -8339,6 +8459,14 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x1a, 0x90a70130}, {0x1b, 0x90170110}, {0x21, 0x03211020}), + SND_HDA_PIN_QUIRK(0x10ec0256, 0x103c, "HP", ALC256_FIXUP_HP_HEADSET_MIC, + {0x14, 0x90170110}, + {0x19, 0x02a11020}, + {0x21, 0x0221101f}), + SND_HDA_PIN_QUIRK(0x10ec0274, 0x103c, "HP", ALC274_FIXUP_HP_HEADSET_MIC, + {0x17, 0x90170110}, + {0x19, 0x03a11030}, + {0x21, 0x03211020}), SND_HDA_PIN_QUIRK(0x10ec0280, 0x103c, "HP", ALC280_FIXUP_HP_GPIO4, {0x12, 0x90a60130}, {0x14, 0x90170110}, diff --git a/sound/pci/mixart/mixart_core.c b/sound/pci/mixart/mixart_core.c index 0bdd33b0af65..fb8895af0363 100644 --- a/sound/pci/mixart/mixart_core.c +++ b/sound/pci/mixart/mixart_core.c @@ -70,7 +70,6 @@ static int get_msg(struct mixart_mgr *mgr, struct mixart_msg *resp, unsigned int i; #endif - mutex_lock(&mgr->msg_lock); err = 0; /* copy message descriptor from miXart to driver */ @@ -119,8 +118,6 @@ static int get_msg(struct mixart_mgr *mgr, struct mixart_msg *resp, writel_be(headptr, MIXART_MEM(mgr, MSG_OUTBOUND_FREE_HEAD)); _clean_exit: - mutex_unlock(&mgr->msg_lock); - return err; } @@ -258,7 +255,9 @@ int snd_mixart_send_msg(struct mixart_mgr *mgr, struct mixart_msg *request, int resp.data = resp_data; resp.size = max_resp_size; + mutex_lock(&mgr->msg_lock); err = get_msg(mgr, &resp, msg_frame); + mutex_unlock(&mgr->msg_lock); if( request->message_id != resp.message_id ) dev_err(&mgr->pci->dev, "RESPONSE ERROR!\n"); diff --git a/sound/soc/atmel/mchp-spdiftx.c b/sound/soc/atmel/mchp-spdiftx.c index 82c1eecd2528..3bd350afb743 100644 --- a/sound/soc/atmel/mchp-spdiftx.c +++ b/sound/soc/atmel/mchp-spdiftx.c @@ -487,7 +487,6 @@ static int mchp_spdiftx_hw_params(struct snd_pcm_substream *substream, } mchp_spdiftx_channel_status_write(dev); spin_unlock_irqrestore(&ctrl->lock, flags); - mr |= SPDIFTX_MR_VALID1 | SPDIFTX_MR_VALID2; if (dev->gclk_enabled) { clk_disable_unprepare(dev->gclk); diff --git a/sound/soc/codecs/cs42l51.c b/sound/soc/codecs/cs42l51.c index 097c4e8d9950..c61b17dc2af8 100644 --- a/sound/soc/codecs/cs42l51.c +++ b/sound/soc/codecs/cs42l51.c @@ -254,8 +254,28 @@ static const struct snd_soc_dapm_widget cs42l51_dapm_widgets[] = { &cs42l51_adcr_mux_controls), }; +static int mclk_event(struct snd_soc_dapm_widget *w, + struct snd_kcontrol *kcontrol, int event) +{ + struct snd_soc_component *comp = snd_soc_dapm_to_component(w->dapm); + struct cs42l51_private *cs42l51 = snd_soc_component_get_drvdata(comp); + + switch (event) { + case SND_SOC_DAPM_PRE_PMU: + return clk_prepare_enable(cs42l51->mclk_handle); + case SND_SOC_DAPM_POST_PMD: + /* Delay mclk shutdown to fulfill power-down sequence requirements */ + msleep(20); + clk_disable_unprepare(cs42l51->mclk_handle); + break; + } + + return 0; +} + static const struct snd_soc_dapm_widget cs42l51_dapm_mclk_widgets[] = { - SND_SOC_DAPM_CLOCK_SUPPLY("MCLK") + SND_SOC_DAPM_SUPPLY("MCLK", SND_SOC_NOPM, 0, 0, mclk_event, + SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMD), }; static const struct snd_soc_dapm_route cs42l51_routes[] = { diff --git a/sound/soc/codecs/rt1015.c b/sound/soc/codecs/rt1015.c index 25fe2ddedd54..3db07293c70b 100644 --- a/sound/soc/codecs/rt1015.c +++ b/sound/soc/codecs/rt1015.c @@ -27,10 +27,15 @@ #include <sound/soc-dapm.h> #include <sound/soc.h> #include <sound/tlv.h> +#include <sound/rt1015.h> #include "rl6231.h" #include "rt1015.h" +static const struct rt1015_platform_data i2s_default_platform_data = { + .power_up_delay_ms = 50, +}; + static const struct reg_default rt1015_reg[] = { { 0x0000, 0x0000 }, { 0x0004, 0xa000 }, @@ -539,7 +544,7 @@ static void rt1015_flush_work(struct work_struct *work) struct rt1015_priv *rt1015 = container_of(work, struct rt1015_priv, flush_work.work); struct snd_soc_component *component = rt1015->component; - unsigned int val, i = 0, count = 20; + unsigned int val, i = 0, count = 200; while (i < count) { usleep_range(1000, 1500); @@ -650,6 +655,7 @@ static int rt1015_amp_drv_event(struct snd_soc_dapm_widget *w, case SND_SOC_DAPM_POST_PMU: if (rt1015->hw_config == RT1015_HW_28) schedule_delayed_work(&rt1015->flush_work, msecs_to_jiffies(10)); + msleep(rt1015->pdata.power_up_delay_ms); break; default: break; @@ -1067,9 +1073,16 @@ static struct acpi_device_id rt1015_acpi_match[] = { MODULE_DEVICE_TABLE(acpi, rt1015_acpi_match); #endif +static void rt1015_parse_dt(struct rt1015_priv *rt1015, struct device *dev) +{ + device_property_read_u32(dev, "realtek,power-up-delay-ms", + &rt1015->pdata.power_up_delay_ms); +} + static int rt1015_i2c_probe(struct i2c_client *i2c, const struct i2c_device_id *id) { + struct rt1015_platform_data *pdata = dev_get_platdata(&i2c->dev); struct rt1015_priv *rt1015; int ret; unsigned int val; @@ -1081,6 +1094,13 @@ static int rt1015_i2c_probe(struct i2c_client *i2c, i2c_set_clientdata(i2c, rt1015); + rt1015->pdata = i2s_default_platform_data; + + if (pdata) + rt1015->pdata = *pdata; + else + rt1015_parse_dt(rt1015, &i2c->dev); + rt1015->regmap = devm_regmap_init_i2c(i2c, &rt1015_regmap); if (IS_ERR(rt1015->regmap)) { ret = PTR_ERR(rt1015->regmap); diff --git a/sound/soc/codecs/rt1015.h b/sound/soc/codecs/rt1015.h index d3fdd30aca6d..15cadb361ec3 100644 --- a/sound/soc/codecs/rt1015.h +++ b/sound/soc/codecs/rt1015.h @@ -12,6 +12,7 @@ #ifndef __RT1015_H__ #define __RT1015_H__ +#include <sound/rt1015.h> #define RT1015_DEVICE_ID_VAL 0x1011 #define RT1015_DEVICE_ID_VAL2 0x1015 @@ -380,6 +381,7 @@ enum { struct rt1015_priv { struct snd_soc_component *component; + struct rt1015_platform_data pdata; struct regmap *regmap; int sysclk; int sysclk_src; diff --git a/sound/soc/codecs/wcd9335.c b/sound/soc/codecs/wcd9335.c index f2d9d52ee171..4d2b1ec7c03b 100644 --- a/sound/soc/codecs/wcd9335.c +++ b/sound/soc/codecs/wcd9335.c @@ -618,7 +618,7 @@ static const char * const sb_tx8_mux_text[] = { "ZERO", "RX_MIX_TX8", "DEC8", "DEC8_192" }; -static const DECLARE_TLV_DB_SCALE(digital_gain, 0, 1, 0); +static const DECLARE_TLV_DB_SCALE(digital_gain, -8400, 100, -8400); static const DECLARE_TLV_DB_SCALE(line_gain, 0, 7, 1); static const DECLARE_TLV_DB_SCALE(analog_gain, 0, 25, 1); static const DECLARE_TLV_DB_SCALE(ear_pa_gain, 0, 150, 0); diff --git a/sound/soc/codecs/wcd934x.c b/sound/soc/codecs/wcd934x.c index 35697b072367..40f682f5dab8 100644 --- a/sound/soc/codecs/wcd934x.c +++ b/sound/soc/codecs/wcd934x.c @@ -551,7 +551,7 @@ struct wcd_iir_filter_ctl { struct soc_bytes_ext bytes_ext; }; -static const DECLARE_TLV_DB_SCALE(digital_gain, 0, 1, 0); +static const DECLARE_TLV_DB_SCALE(digital_gain, -8400, 100, -8400); static const DECLARE_TLV_DB_SCALE(line_gain, 0, 7, 1); static const DECLARE_TLV_DB_SCALE(analog_gain, 0, 25, 1); static const DECLARE_TLV_DB_SCALE(ear_pa_gain, 0, 150, 0); diff --git a/sound/soc/codecs/wsa881x.c b/sound/soc/codecs/wsa881x.c index 68e774e69c85..4530b74f5921 100644 --- a/sound/soc/codecs/wsa881x.c +++ b/sound/soc/codecs/wsa881x.c @@ -1026,6 +1026,8 @@ static struct snd_soc_dai_driver wsa881x_dais[] = { .id = 0, .playback = { .stream_name = "SPKR Playback", + .rates = SNDRV_PCM_RATE_48000, + .formats = SNDRV_PCM_FMTBIT_S16_LE, .rate_max = 48000, .rate_min = 48000, .channels_min = 1, diff --git a/sound/soc/intel/Kconfig b/sound/soc/intel/Kconfig index d5bae5d1ab6f..a5b446d5af19 100644 --- a/sound/soc/intel/Kconfig +++ b/sound/soc/intel/Kconfig @@ -15,22 +15,6 @@ config SND_SOC_INTEL_SST_TOPLEVEL if SND_SOC_INTEL_SST_TOPLEVEL -config SND_SST_IPC - tristate - # This option controls the IPC core for HiFi2 platforms - -config SND_SST_IPC_PCI - tristate - select SND_SST_IPC - # This option controls the PCI-based IPC for HiFi2 platforms - # (Medfield, Merrifield). - -config SND_SST_IPC_ACPI - tristate - select SND_SST_IPC - # This option controls the ACPI-based IPC for HiFi2 platforms - # (Baytrail, Cherrytrail) - config SND_SOC_INTEL_SST tristate @@ -57,7 +41,6 @@ config SND_SST_ATOM_HIFI2_PLATFORM config SND_SST_ATOM_HIFI2_PLATFORM_PCI tristate "PCI HiFi2 (Merrifield) Platforms" depends on X86 && PCI - select SND_SST_IPC_PCI select SND_SST_ATOM_HIFI2_PLATFORM help If you have a Intel Merrifield/Edison platform, then @@ -70,7 +53,6 @@ config SND_SST_ATOM_HIFI2_PLATFORM_ACPI tristate "ACPI HiFi2 (Baytrail, Cherrytrail) Platforms" default ACPI depends on X86 && ACPI && PCI - select SND_SST_IPC_ACPI select SND_SST_ATOM_HIFI2_PLATFORM select SND_SOC_ACPI_INTEL_MATCH select IOSF_MBI diff --git a/sound/soc/intel/atom/Makefile b/sound/soc/intel/atom/Makefile index a9326d5ec44c..c66f03f5d8d6 100644 --- a/sound/soc/intel/atom/Makefile +++ b/sound/soc/intel/atom/Makefile @@ -6,4 +6,4 @@ snd-soc-sst-atom-hifi2-platform-objs := sst-mfld-platform-pcm.o \ obj-$(CONFIG_SND_SST_ATOM_HIFI2_PLATFORM) += snd-soc-sst-atom-hifi2-platform.o # DSP driver -obj-$(CONFIG_SND_SST_IPC) += sst/ +obj-$(CONFIG_SND_SST_ATOM_HIFI2_PLATFORM) += sst/ diff --git a/sound/soc/intel/atom/sst/Makefile b/sound/soc/intel/atom/sst/Makefile index f17c905df3e2..5761d30a5f9d 100644 --- a/sound/soc/intel/atom/sst/Makefile +++ b/sound/soc/intel/atom/sst/Makefile @@ -3,6 +3,6 @@ snd-intel-sst-core-objs := sst.o sst_ipc.o sst_stream.o sst_drv_interface.o sst_ snd-intel-sst-pci-objs += sst_pci.o snd-intel-sst-acpi-objs += sst_acpi.o -obj-$(CONFIG_SND_SST_IPC) += snd-intel-sst-core.o -obj-$(CONFIG_SND_SST_IPC_PCI) += snd-intel-sst-pci.o -obj-$(CONFIG_SND_SST_IPC_ACPI) += snd-intel-sst-acpi.o +obj-$(CONFIG_SND_SST_ATOM_HIFI2_PLATFORM) += snd-intel-sst-core.o +obj-$(CONFIG_SND_SST_ATOM_HIFI2_PLATFORM_PCI) += snd-intel-sst-pci.o +obj-$(CONFIG_SND_SST_ATOM_HIFI2_PLATFORM_ACPI) += snd-intel-sst-acpi.o diff --git a/sound/soc/intel/boards/kbl_rt5663_max98927.c b/sound/soc/intel/boards/kbl_rt5663_max98927.c index 3ea4602dfb3e..9a4b3d0973f6 100644 --- a/sound/soc/intel/boards/kbl_rt5663_max98927.c +++ b/sound/soc/intel/boards/kbl_rt5663_max98927.c @@ -401,17 +401,40 @@ static int kabylake_ssp_fixup(struct snd_soc_pcm_runtime *rtd, struct snd_interval *chan = hw_param_interval(params, SNDRV_PCM_HW_PARAM_CHANNELS); struct snd_mask *fmt = hw_param_mask(params, SNDRV_PCM_HW_PARAM_FORMAT); - struct snd_soc_dpcm *dpcm = container_of( - params, struct snd_soc_dpcm, hw_params); - struct snd_soc_dai_link *fe_dai_link = dpcm->fe->dai_link; - struct snd_soc_dai_link *be_dai_link = dpcm->be->dai_link; + struct snd_soc_dpcm *dpcm, *rtd_dpcm = NULL; + + /* + * The following loop will be called only for playback stream + * In this platform, there is only one playback device on every SSP + */ + for_each_dpcm_fe(rtd, SNDRV_PCM_STREAM_PLAYBACK, dpcm) { + rtd_dpcm = dpcm; + break; + } + + /* + * This following loop will be called only for capture stream + * In this platform, there is only one capture device on every SSP + */ + for_each_dpcm_fe(rtd, SNDRV_PCM_STREAM_CAPTURE, dpcm) { + rtd_dpcm = dpcm; + break; + } + + if (!rtd_dpcm) + return -EINVAL; + + /* + * The above 2 loops are mutually exclusive based on the stream direction, + * thus rtd_dpcm variable will never be overwritten + */ /* * The ADSP will convert the FE rate to 48k, stereo, 24 bit */ - if (!strcmp(fe_dai_link->name, "Kbl Audio Port") || - !strcmp(fe_dai_link->name, "Kbl Audio Headset Playback") || - !strcmp(fe_dai_link->name, "Kbl Audio Capture Port")) { + if (!strcmp(rtd_dpcm->fe->dai_link->name, "Kbl Audio Port") || + !strcmp(rtd_dpcm->fe->dai_link->name, "Kbl Audio Headset Playback") || + !strcmp(rtd_dpcm->fe->dai_link->name, "Kbl Audio Capture Port")) { rate->min = rate->max = 48000; chan->min = chan->max = 2; snd_mask_none(fmt); @@ -421,7 +444,7 @@ static int kabylake_ssp_fixup(struct snd_soc_pcm_runtime *rtd, * The speaker on the SSP0 supports S16_LE and not S24_LE. * thus changing the mask here */ - if (!strcmp(be_dai_link->name, "SSP0-Codec")) + if (!strcmp(rtd_dpcm->be->dai_link->name, "SSP0-Codec")) snd_mask_set_format(fmt, SNDRV_PCM_FORMAT_S16_LE); return 0; diff --git a/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c b/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c index 922cd0176e1f..f95546c184aa 100644 --- a/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c +++ b/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c @@ -700,6 +700,8 @@ static int kabylake_set_bias_level(struct snd_soc_card *card, switch (level) { case SND_SOC_BIAS_PREPARE: if (dapm->bias_level == SND_SOC_BIAS_ON) { + if (!__clk_is_enabled(priv->mclk)) + return 0; dev_dbg(card->dev, "Disable mclk"); clk_disable_unprepare(priv->mclk); } else { diff --git a/sound/soc/intel/catpt/dsp.c b/sound/soc/intel/catpt/dsp.c index 7d2968571951..9e807b941732 100644 --- a/sound/soc/intel/catpt/dsp.c +++ b/sound/soc/intel/catpt/dsp.c @@ -267,9 +267,12 @@ static int catpt_dsp_select_lpclock(struct catpt_dev *cdev, bool lp, bool waiti) reg, (reg & CATPT_ISD_DCPWM), 500, 10000); if (ret) { - dev_err(cdev->dev, "await WAITI timeout\n"); - mutex_unlock(&cdev->clk_mutex); - return ret; + dev_warn(cdev->dev, "await WAITI timeout\n"); + /* no signal - only high clock selection allowed */ + if (lp) { + mutex_unlock(&cdev->clk_mutex); + return 0; + } } } diff --git a/sound/soc/intel/catpt/pcm.c b/sound/soc/intel/catpt/pcm.c index f78018c857b8..408e64e3b5fb 100644 --- a/sound/soc/intel/catpt/pcm.c +++ b/sound/soc/intel/catpt/pcm.c @@ -458,10 +458,6 @@ static int catpt_dai_prepare(struct snd_pcm_substream *substream, if (ret) return CATPT_IPC_ERROR(ret); - ret = catpt_dsp_update_lpclock(cdev); - if (ret) - return ret; - ret = catpt_dai_apply_usettings(dai, stream); if (ret) return ret; @@ -500,6 +496,7 @@ static int catpt_dai_trigger(struct snd_pcm_substream *substream, int cmd, case SNDRV_PCM_TRIGGER_RESUME: case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: resume_stream: + catpt_dsp_update_lpclock(cdev); ret = catpt_ipc_resume_stream(cdev, stream->info.stream_hw_id); if (ret) return CATPT_IPC_ERROR(ret); @@ -507,11 +504,11 @@ static int catpt_dai_trigger(struct snd_pcm_substream *substream, int cmd, case SNDRV_PCM_TRIGGER_STOP: stream->prepared = false; - catpt_dsp_update_lpclock(cdev); fallthrough; case SNDRV_PCM_TRIGGER_SUSPEND: case SNDRV_PCM_TRIGGER_PAUSE_PUSH: ret = catpt_ipc_pause_stream(cdev, stream->info.stream_hw_id); + catpt_dsp_update_lpclock(cdev); if (ret) return CATPT_IPC_ERROR(ret); break; @@ -534,6 +531,8 @@ void catpt_stream_update_position(struct catpt_dev *cdev, dsppos = bytes_to_frames(r, pos->stream_position); + if (!stream->prepared) + goto exit; /* only offload is set_write_pos driven */ if (stream->template->type != CATPT_STRM_TYPE_RENDER) goto exit; @@ -667,7 +666,17 @@ static int catpt_dai_pcm_new(struct snd_soc_pcm_runtime *rtm, break; } + /* see if this is a new configuration */ + if (!memcmp(&cdev->devfmt[devfmt.iface], &devfmt, sizeof(devfmt))) + return 0; + + pm_runtime_get_sync(cdev->dev); + ret = catpt_ipc_set_device_format(cdev, &devfmt); + + pm_runtime_mark_last_busy(cdev->dev); + pm_runtime_put_autosuspend(cdev->dev); + if (ret) return CATPT_IPC_ERROR(ret); diff --git a/sound/soc/intel/keembay/kmb_platform.c b/sound/soc/intel/keembay/kmb_platform.c index f54b710ee1c2..291a686568c2 100644 --- a/sound/soc/intel/keembay/kmb_platform.c +++ b/sound/soc/intel/keembay/kmb_platform.c @@ -487,9 +487,9 @@ static int kmb_dai_hw_params(struct snd_pcm_substream *substream, kmb_i2s->xfer_resolution = 0x02; break; case SNDRV_PCM_FORMAT_S24_LE: - config->data_width = 24; - kmb_i2s->ccr = 0x08; - kmb_i2s->xfer_resolution = 0x04; + config->data_width = 32; + kmb_i2s->ccr = 0x14; + kmb_i2s->xfer_resolution = 0x05; break; case SNDRV_PCM_FORMAT_S32_LE: config->data_width = 32; diff --git a/sound/soc/mediatek/mt8183/mt8183-da7219-max98357.c b/sound/soc/mediatek/mt8183/mt8183-da7219-max98357.c index c2c1eb16fcc0..26e7d9a7198f 100644 --- a/sound/soc/mediatek/mt8183/mt8183-da7219-max98357.c +++ b/sound/soc/mediatek/mt8183/mt8183-da7219-max98357.c @@ -630,15 +630,34 @@ static struct snd_soc_codec_conf mt8183_da7219_rt1015_codec_conf[] = { }, }; +static const struct snd_kcontrol_new mt8183_da7219_rt1015_snd_controls[] = { + SOC_DAPM_PIN_SWITCH("Left Spk"), + SOC_DAPM_PIN_SWITCH("Right Spk"), +}; + +static const +struct snd_soc_dapm_widget mt8183_da7219_rt1015_dapm_widgets[] = { + SND_SOC_DAPM_SPK("Left Spk", NULL), + SND_SOC_DAPM_SPK("Right Spk", NULL), + SND_SOC_DAPM_PINCTRL("TDM_OUT_PINCTRL", + "aud_tdm_out_on", "aud_tdm_out_off"), +}; + +static const struct snd_soc_dapm_route mt8183_da7219_rt1015_dapm_routes[] = { + {"Left Spk", NULL, "Left SPO"}, + {"Right Spk", NULL, "Right SPO"}, + {"I2S Playback", NULL, "TDM_OUT_PINCTRL"}, +}; + static struct snd_soc_card mt8183_da7219_rt1015_card = { .name = "mt8183_da7219_rt1015", .owner = THIS_MODULE, - .controls = mt8183_da7219_max98357_snd_controls, - .num_controls = ARRAY_SIZE(mt8183_da7219_max98357_snd_controls), - .dapm_widgets = mt8183_da7219_max98357_dapm_widgets, - .num_dapm_widgets = ARRAY_SIZE(mt8183_da7219_max98357_dapm_widgets), - .dapm_routes = mt8183_da7219_max98357_dapm_routes, - .num_dapm_routes = ARRAY_SIZE(mt8183_da7219_max98357_dapm_routes), + .controls = mt8183_da7219_rt1015_snd_controls, + .num_controls = ARRAY_SIZE(mt8183_da7219_rt1015_snd_controls), + .dapm_widgets = mt8183_da7219_rt1015_dapm_widgets, + .num_dapm_widgets = ARRAY_SIZE(mt8183_da7219_rt1015_dapm_widgets), + .dapm_routes = mt8183_da7219_rt1015_dapm_routes, + .num_dapm_routes = ARRAY_SIZE(mt8183_da7219_rt1015_dapm_routes), .dai_link = mt8183_da7219_dai_links, .num_links = ARRAY_SIZE(mt8183_da7219_dai_links), .aux_dev = &mt8183_da7219_max98357_headset_dev, diff --git a/sound/soc/qcom/lpass-cpu.c b/sound/soc/qcom/lpass-cpu.c index ba2aca301a9b..9d17c87445a9 100644 --- a/sound/soc/qcom/lpass-cpu.c +++ b/sound/soc/qcom/lpass-cpu.c @@ -80,6 +80,12 @@ static int lpass_cpu_daiops_startup(struct snd_pcm_substream *substream, dev_err(dai->dev, "error in enabling mi2s osr clk: %d\n", ret); return ret; } + ret = clk_prepare(drvdata->mi2s_bit_clk[dai->driver->id]); + if (ret) { + dev_err(dai->dev, "error in enabling mi2s bit clk: %d\n", ret); + clk_disable_unprepare(drvdata->mi2s_osr_clk[dai->driver->id]); + return ret; + } return 0; } @@ -88,9 +94,8 @@ static void lpass_cpu_daiops_shutdown(struct snd_pcm_substream *substream, { struct lpass_data *drvdata = snd_soc_dai_get_drvdata(dai); - clk_disable_unprepare(drvdata->mi2s_bit_clk[dai->driver->id]); - clk_disable_unprepare(drvdata->mi2s_osr_clk[dai->driver->id]); + clk_unprepare(drvdata->mi2s_bit_clk[dai->driver->id]); } static int lpass_cpu_daiops_hw_params(struct snd_pcm_substream *substream, @@ -303,10 +308,10 @@ static int lpass_cpu_daiops_trigger(struct snd_pcm_substream *substream, dev_err(dai->dev, "error writing to i2sctl reg: %d\n", ret); - ret = clk_prepare_enable(drvdata->mi2s_bit_clk[id]); + ret = clk_enable(drvdata->mi2s_bit_clk[id]); if (ret) { dev_err(dai->dev, "error in enabling mi2s bit clk: %d\n", ret); - clk_disable_unprepare(drvdata->mi2s_osr_clk[id]); + clk_disable(drvdata->mi2s_osr_clk[id]); return ret; } @@ -324,6 +329,7 @@ static int lpass_cpu_daiops_trigger(struct snd_pcm_substream *substream, if (ret) dev_err(dai->dev, "error writing to i2sctl reg: %d\n", ret); + clk_disable(drvdata->mi2s_bit_clk[dai->driver->id]); break; } diff --git a/sound/soc/qcom/lpass-platform.c b/sound/soc/qcom/lpass-platform.c index 36d1512ffd1f..7a3fdf89968a 100644 --- a/sound/soc/qcom/lpass-platform.c +++ b/sound/soc/qcom/lpass-platform.c @@ -122,8 +122,10 @@ static int lpass_platform_pcmops_open(struct snd_soc_component *component, else dma_ch = 0; - if (dma_ch < 0) + if (dma_ch < 0) { + kfree(data); return dma_ch; + } if (cpu_dai->driver->id == LPASS_DP_RX) { map = drvdata->hdmiif_map; @@ -147,6 +149,7 @@ static int lpass_platform_pcmops_open(struct snd_soc_component *component, ret = snd_pcm_hw_constraint_integer(runtime, SNDRV_PCM_HW_PARAM_PERIODS); if (ret < 0) { + kfree(data); dev_err(soc_runtime->dev, "setting constraints failed: %d\n", ret); return -EINVAL; diff --git a/sound/soc/qcom/lpass-sc7180.c b/sound/soc/qcom/lpass-sc7180.c index c6292f9e613f..bc998d501600 100644 --- a/sound/soc/qcom/lpass-sc7180.c +++ b/sound/soc/qcom/lpass-sc7180.c @@ -188,7 +188,7 @@ static struct lpass_variant sc7180_data = { .micmode = REG_FIELD_ID(0x1000, 4, 8, 3, 0x1000), .micmono = REG_FIELD_ID(0x1000, 3, 3, 3, 0x1000), .wssrc = REG_FIELD_ID(0x1000, 2, 2, 3, 0x1000), - .bitwidth = REG_FIELD_ID(0x1000, 0, 0, 3, 0x1000), + .bitwidth = REG_FIELD_ID(0x1000, 0, 1, 3, 0x1000), .rdma_dyncclk = REG_FIELD_ID(0xC000, 21, 21, 5, 0x1000), .rdma_bursten = REG_FIELD_ID(0xC000, 20, 20, 5, 0x1000), diff --git a/sound/soc/qcom/sdm845.c b/sound/soc/qcom/sdm845.c index ab1bf23c21a6..6c2760e27ea6 100644 --- a/sound/soc/qcom/sdm845.c +++ b/sound/soc/qcom/sdm845.c @@ -17,6 +17,7 @@ #include "qdsp6/q6afe.h" #include "../codecs/rt5663.h" +#define DRIVER_NAME "sdm845" #define DEFAULT_SAMPLE_RATE_48K 48000 #define DEFAULT_MCLK_RATE 24576000 #define TDM_BCLK_RATE 6144000 @@ -552,6 +553,7 @@ static int sdm845_snd_platform_probe(struct platform_device *pdev) if (!data) return -ENOMEM; + card->driver_name = DRIVER_NAME; card->dapm_widgets = sdm845_snd_widgets; card->num_dapm_widgets = ARRAY_SIZE(sdm845_snd_widgets); card->dev = dev; diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index ea3986a46c12..05a085f6dc7c 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -2341,7 +2341,7 @@ struct snd_soc_dai *snd_soc_register_dai(struct snd_soc_component *component, } /** - * snd_soc_unregister_dai - Unregister DAIs from the ASoC core + * snd_soc_unregister_dais - Unregister DAIs from the ASoC core * * @component: The component for which the DAIs should be unregistered */ diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index 980f2c330b87..7f87b449f950 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -1276,7 +1276,7 @@ static int is_connected_input_ep(struct snd_soc_dapm_widget *widget, } /** - * snd_soc_dapm_get_connected_widgets - query audio path and it's widgets. + * snd_soc_dapm_dai_get_connected_widgets - query audio path and it's widgets. * @dai: the soc DAI. * @stream: stream direction. * @list: list of active widgets for this stream. diff --git a/sound/soc/sof/loader.c b/sound/soc/sof/loader.c index 68ed454f7ddf..ba9ed66f98bc 100644 --- a/sound/soc/sof/loader.c +++ b/sound/soc/sof/loader.c @@ -118,6 +118,11 @@ int snd_sof_fw_parse_ext_data(struct snd_sof_dev *sdev, u32 bar, u32 offset) case SOF_IPC_EXT_CC_INFO: ret = get_cc_info(sdev, ext_hdr); break; + case SOF_IPC_EXT_UNUSED: + case SOF_IPC_EXT_PROBE_INFO: + case SOF_IPC_EXT_USER_ABI_INFO: + /* They are supported but we don't do anything here */ + break; default: dev_warn(sdev->dev, "warning: unknown ext header type %d size 0x%x\n", ext_hdr->type, ext_hdr->hdr.size); diff --git a/sound/usb/card.c b/sound/usb/card.c index fa764b61fe9c..4457214a3ae6 100644 --- a/sound/usb/card.c +++ b/sound/usb/card.c @@ -379,6 +379,10 @@ static const struct usb_audio_device_name usb_audio_names[] = { DEVICE_NAME(0x046d, 0x0990, "Logitech, Inc.", "QuickCam Pro 9000"), + /* ASUS ROG Strix */ + PROFILE_NAME(0x0b05, 0x1917, + "Realtek", "ALC1220-VB-DT", "Realtek-ALC1220-VB-Desktop"), + /* Dell WD15 Dock */ PROFILE_NAME(0x0bda, 0x4014, "Dell", "WD15 Dock", "Dell-WD15-Dock"), /* Dell WD19 Dock */ diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c index c369c81e74c4..a7212f16660e 100644 --- a/sound/usb/mixer_maps.c +++ b/sound/usb/mixer_maps.c @@ -561,7 +561,8 @@ static const struct usbmix_ctl_map usbmix_ctl_maps[] = { }, { /* ASUS ROG Strix */ .id = USB_ID(0x0b05, 0x1917), - .map = asus_rog_map, + .map = trx40_mobo_map, + .connector_map = trx40_mobo_connector_map, }, { /* MSI TRX40 Creator */ .id = USB_ID(0x0db0, 0x0d64), diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c index b401ee894e1b..a860303cc522 100644 --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -336,6 +336,7 @@ static int set_sync_ep_implicit_fb_quirk(struct snd_usb_substream *subs, switch (subs->stream->chip->usb_id) { case USB_ID(0x0763, 0x2030): /* M-Audio Fast Track C400 */ case USB_ID(0x0763, 0x2031): /* M-Audio Fast Track C600 */ + case USB_ID(0x22f0, 0x0006): /* Allen&Heath Qu-16 */ ep = 0x81; ifnum = 3; goto add_sync_ep_from_ifnum; @@ -345,6 +346,7 @@ static int set_sync_ep_implicit_fb_quirk(struct snd_usb_substream *subs, ifnum = 2; goto add_sync_ep_from_ifnum; case USB_ID(0x2466, 0x8003): /* Fractal Audio Axe-Fx II */ + case USB_ID(0x0499, 0x172a): /* Yamaha MODX */ ep = 0x86; ifnum = 2; goto add_sync_ep_from_ifnum; @@ -352,6 +354,10 @@ static int set_sync_ep_implicit_fb_quirk(struct snd_usb_substream *subs, ep = 0x81; ifnum = 2; goto add_sync_ep_from_ifnum; + case USB_ID(0x1686, 0xf029): /* Zoom UAC-2 */ + ep = 0x82; + ifnum = 2; + goto add_sync_ep_from_ifnum; case USB_ID(0x1397, 0x0001): /* Behringer UFX1604 */ case USB_ID(0x1397, 0x0002): /* Behringer UFX1204 */ ep = 0x81; diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index b4fa80ef730d..c50be2f75f70 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1672,13 +1672,13 @@ void snd_usb_ctl_msg_quirk(struct usb_device *dev, unsigned int pipe, && (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) msleep(20); - /* Zoom R16/24, Logitech H650e/H570e, Jabra 550a, Kingston HyperX - * needs a tiny delay here, otherwise requests like get/set - * frequency return as failed despite actually succeeding. + /* Zoom R16/24, many Logitech(at least H650e/H570e/BCC950), + * Jabra 550a, Kingston HyperX needs a tiny delay here, + * otherwise requests like get/set frequency return + * as failed despite actually succeeding. */ if ((chip->usb_id == USB_ID(0x1686, 0x00dd) || - chip->usb_id == USB_ID(0x046d, 0x0a46) || - chip->usb_id == USB_ID(0x046d, 0x0a56) || + USB_ID_VENDOR(chip->usb_id) == 0x046d || /* Logitech */ chip->usb_id == USB_ID(0x0b0e, 0x0349) || chip->usb_id == USB_ID(0x0951, 0x16ad)) && (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) @@ -1800,6 +1800,7 @@ u64 snd_usb_interface_dsd_format_quirks(struct snd_usb_audio *chip, case 0x278b: /* Rotel? */ case 0x292b: /* Gustard/Ess based devices */ case 0x2ab6: /* T+A devices */ + case 0x3353: /* Khadas devices */ case 0x3842: /* EVGA */ case 0xc502: /* HiBy devices */ if (fp->dsd_raw) diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index ba85bb23f060..1c17c3a24411 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -159,6 +159,21 @@ struct kvm_sync_regs { struct kvm_arch_memory_slot { }; +/* + * PMU filter structure. Describe a range of events with a particular + * action. To be used with KVM_ARM_VCPU_PMU_V3_FILTER. + */ +struct kvm_pmu_event_filter { + __u16 base_event; + __u16 nevents; + +#define KVM_PMU_EVENT_ALLOW 0 +#define KVM_PMU_EVENT_DENY 1 + + __u8 action; + __u8 pad[3]; +}; + /* for KVM_GET/SET_VCPU_EVENTS */ struct kvm_vcpu_events { struct { @@ -242,6 +257,15 @@ struct kvm_vcpu_events { #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL 0 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL 1 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED 2 + +/* + * Only two states can be presented by the host kernel: + * - NOT_REQUIRED: the guest doesn't need to do anything + * - NOT_AVAIL: the guest isn't mitigated (it can still use SSBS if available) + * + * All the other values are deprecated. The host still accepts all + * values (they are ABI), but will narrow them to the above two. + */ #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2 KVM_REG_ARM_FW_REG(2) #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL 0 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN 1 @@ -329,6 +353,7 @@ struct kvm_vcpu_events { #define KVM_ARM_VCPU_PMU_V3_CTRL 0 #define KVM_ARM_VCPU_PMU_V3_IRQ 0 #define KVM_ARM_VCPU_PMU_V3_INIT 1 +#define KVM_ARM_VCPU_PMU_V3_FILTER 2 #define KVM_ARM_VCPU_TIMER_CTRL 1 #define KVM_ARM_VCPU_TIMER_IRQ_VTIMER 0 #define KVM_ARM_VCPU_TIMER_IRQ_PTIMER 1 diff --git a/tools/arch/s390/include/uapi/asm/sie.h b/tools/arch/s390/include/uapi/asm/sie.h index 6ca1e68d7103..ede318653c87 100644 --- a/tools/arch/s390/include/uapi/asm/sie.h +++ b/tools/arch/s390/include/uapi/asm/sie.h @@ -29,7 +29,7 @@ { 0x13, "SIGP conditional emergency signal" }, \ { 0x15, "SIGP sense running" }, \ { 0x16, "SIGP set multithreading"}, \ - { 0x17, "SIGP store additional status ait address"} + { 0x17, "SIGP store additional status at address"} #define icpt_prog_codes \ { 0x0001, "Prog Operation" }, \ diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 2901d5df4366..dad350d42ecf 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -96,7 +96,7 @@ #define X86_FEATURE_SYSCALL32 ( 3*32+14) /* "" syscall in IA32 userspace */ #define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in IA32 userspace */ #define X86_FEATURE_REP_GOOD ( 3*32+16) /* REP microcode works well */ -/* free ( 3*32+17) */ +#define X86_FEATURE_SME_COHERENT ( 3*32+17) /* "" AMD hardware-enforced cache coherency */ #define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" LFENCE synchronizes RDTSC */ #define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */ #define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */ @@ -236,6 +236,7 @@ #define X86_FEATURE_EPT_AD ( 8*32+17) /* Intel Extended Page Table access-dirty bit */ #define X86_FEATURE_VMCALL ( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */ #define X86_FEATURE_VMW_VMMCALL ( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */ +#define X86_FEATURE_SEV_ES ( 8*32+20) /* AMD Secure Encrypted Virtualization - Encrypted State */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */ #define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/ @@ -288,6 +289,7 @@ #define X86_FEATURE_FENCE_SWAPGS_USER (11*32+ 4) /* "" LFENCE in user entry SWAPGS path */ #define X86_FEATURE_FENCE_SWAPGS_KERNEL (11*32+ 5) /* "" LFENCE in kernel entry SWAPGS path */ #define X86_FEATURE_SPLIT_LOCK_DETECT (11*32+ 6) /* #AC for split lock */ +#define X86_FEATURE_PER_THREAD_MBA (11*32+ 7) /* "" Per-thread Memory Bandwidth Allocation */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ @@ -353,6 +355,7 @@ #define X86_FEATURE_CLDEMOTE (16*32+25) /* CLDEMOTE instruction */ #define X86_FEATURE_MOVDIRI (16*32+27) /* MOVDIRI instruction */ #define X86_FEATURE_MOVDIR64B (16*32+28) /* MOVDIR64B instruction */ +#define X86_FEATURE_ENQCMD (16*32+29) /* ENQCMD and ENQCMDS instructions */ /* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */ #define X86_FEATURE_OVERFLOW_RECOV (17*32+ 0) /* MCA overflow recovery support */ @@ -368,6 +371,7 @@ #define X86_FEATURE_MD_CLEAR (18*32+10) /* VERW clears CPU buffers */ #define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */ #define X86_FEATURE_SERIALIZE (18*32+14) /* SERIALIZE instruction */ +#define X86_FEATURE_TSXLDTRK (18*32+16) /* TSX Suspend Load Address Tracking */ #define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */ #define X86_FEATURE_ARCH_LBR (18*32+19) /* Intel ARCH LBR */ #define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */ diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index 4ea8584682f9..5861d34f9771 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -56,6 +56,12 @@ # define DISABLE_PTI (1 << (X86_FEATURE_PTI & 31)) #endif +#ifdef CONFIG_IOMMU_SUPPORT +# define DISABLE_ENQCMD 0 +#else +# define DISABLE_ENQCMD (1 << (X86_FEATURE_ENQCMD & 31)) +#endif + /* * Make sure to add features to the correct mask */ @@ -75,7 +81,8 @@ #define DISABLED_MASK13 0 #define DISABLED_MASK14 0 #define DISABLED_MASK15 0 -#define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP) +#define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP| \ + DISABLE_ENQCMD) #define DISABLED_MASK17 0 #define DISABLED_MASK18 0 #define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19) diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index 2859ee4f39a8..972a34d93505 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -257,6 +257,9 @@ #define MSR_IA32_LASTINTFROMIP 0x000001dd #define MSR_IA32_LASTINTTOIP 0x000001de +#define MSR_IA32_PASID 0x00000d93 +#define MSR_IA32_PASID_VALID BIT_ULL(31) + /* DEBUGCTLMSR bits (others vary by model): */ #define DEBUGCTLMSR_LBR (1UL << 0) /* last branch recording */ #define DEBUGCTLMSR_BTF_SHIFT 1 @@ -464,11 +467,15 @@ #define MSR_AMD64_IBSOP_REG_MASK ((1UL<<MSR_AMD64_IBSOP_REG_COUNT)-1) #define MSR_AMD64_IBSCTL 0xc001103a #define MSR_AMD64_IBSBRTARGET 0xc001103b +#define MSR_AMD64_ICIBSEXTDCTL 0xc001103c #define MSR_AMD64_IBSOPDATA4 0xc001103d #define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */ +#define MSR_AMD64_SEV_ES_GHCB 0xc0010130 #define MSR_AMD64_SEV 0xc0010131 #define MSR_AMD64_SEV_ENABLED_BIT 0 +#define MSR_AMD64_SEV_ES_ENABLED_BIT 1 #define MSR_AMD64_SEV_ENABLED BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT) +#define MSR_AMD64_SEV_ES_ENABLED BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT) #define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f @@ -857,11 +864,14 @@ #define MSR_CORE_PERF_FIXED_CTR0 0x00000309 #define MSR_CORE_PERF_FIXED_CTR1 0x0000030a #define MSR_CORE_PERF_FIXED_CTR2 0x0000030b +#define MSR_CORE_PERF_FIXED_CTR3 0x0000030c #define MSR_CORE_PERF_FIXED_CTR_CTRL 0x0000038d #define MSR_CORE_PERF_GLOBAL_STATUS 0x0000038e #define MSR_CORE_PERF_GLOBAL_CTRL 0x0000038f #define MSR_CORE_PERF_GLOBAL_OVF_CTRL 0x00000390 +#define MSR_PERF_METRICS 0x00000329 + /* PERF_GLOBAL_OVF_CTL bits */ #define MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI_BIT 55 #define MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI (1ULL << MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI_BIT) diff --git a/tools/arch/x86/include/asm/required-features.h b/tools/arch/x86/include/asm/required-features.h index 6847d85400a8..3ff0d48469f2 100644 --- a/tools/arch/x86/include/asm/required-features.h +++ b/tools/arch/x86/include/asm/required-features.h @@ -54,7 +54,7 @@ #endif #ifdef CONFIG_X86_64 -#ifdef CONFIG_PARAVIRT +#ifdef CONFIG_PARAVIRT_XXL /* Paravirtualized systems may not have PSE or PGE available */ #define NEED_PSE 0 #define NEED_PGE 0 diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index 0780f97c1850..89e5f3d1bba8 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -192,6 +192,26 @@ struct kvm_msr_list { __u32 indices[0]; }; +/* Maximum size of any access bitmap in bytes */ +#define KVM_MSR_FILTER_MAX_BITMAP_SIZE 0x600 + +/* for KVM_X86_SET_MSR_FILTER */ +struct kvm_msr_filter_range { +#define KVM_MSR_FILTER_READ (1 << 0) +#define KVM_MSR_FILTER_WRITE (1 << 1) + __u32 flags; + __u32 nmsrs; /* number of msrs in bitmap */ + __u32 base; /* MSR index the bitmap starts at */ + __u8 *bitmap; /* a 1 bit allows the operations in flags, 0 denies */ +}; + +#define KVM_MSR_FILTER_MAX_RANGES 16 +struct kvm_msr_filter { +#define KVM_MSR_FILTER_DEFAULT_ALLOW (0 << 0) +#define KVM_MSR_FILTER_DEFAULT_DENY (1 << 0) + __u32 flags; + struct kvm_msr_filter_range ranges[KVM_MSR_FILTER_MAX_RANGES]; +}; struct kvm_cpuid_entry { __u32 function; diff --git a/tools/arch/x86/include/uapi/asm/svm.h b/tools/arch/x86/include/uapi/asm/svm.h index 2e8a30f06c74..f1d8307454e0 100644 --- a/tools/arch/x86/include/uapi/asm/svm.h +++ b/tools/arch/x86/include/uapi/asm/svm.h @@ -29,6 +29,7 @@ #define SVM_EXIT_WRITE_DR6 0x036 #define SVM_EXIT_WRITE_DR7 0x037 #define SVM_EXIT_EXCP_BASE 0x040 +#define SVM_EXIT_LAST_EXCP 0x05f #define SVM_EXIT_INTR 0x060 #define SVM_EXIT_NMI 0x061 #define SVM_EXIT_SMI 0x062 @@ -76,10 +77,21 @@ #define SVM_EXIT_MWAIT_COND 0x08c #define SVM_EXIT_XSETBV 0x08d #define SVM_EXIT_RDPRU 0x08e +#define SVM_EXIT_INVPCID 0x0a2 #define SVM_EXIT_NPF 0x400 #define SVM_EXIT_AVIC_INCOMPLETE_IPI 0x401 #define SVM_EXIT_AVIC_UNACCELERATED_ACCESS 0x402 +/* SEV-ES software-defined VMGEXIT events */ +#define SVM_VMGEXIT_MMIO_READ 0x80000001 +#define SVM_VMGEXIT_MMIO_WRITE 0x80000002 +#define SVM_VMGEXIT_NMI_COMPLETE 0x80000003 +#define SVM_VMGEXIT_AP_HLT_LOOP 0x80000004 +#define SVM_VMGEXIT_AP_JUMP_TABLE 0x80000005 +#define SVM_VMGEXIT_SET_AP_JUMP_TABLE 0 +#define SVM_VMGEXIT_GET_AP_JUMP_TABLE 1 +#define SVM_VMGEXIT_UNSUPPORTED_EVENT 0x8000ffff + #define SVM_EXIT_ERR -1 #define SVM_EXIT_REASONS \ @@ -171,6 +183,7 @@ { SVM_EXIT_MONITOR, "monitor" }, \ { SVM_EXIT_MWAIT, "mwait" }, \ { SVM_EXIT_XSETBV, "xsetbv" }, \ + { SVM_EXIT_INVPCID, "invpcid" }, \ { SVM_EXIT_NPF, "npf" }, \ { SVM_EXIT_AVIC_INCOMPLETE_IPI, "avic_incomplete_ipi" }, \ { SVM_EXIT_AVIC_UNACCELERATED_ACCESS, "avic_unaccelerated_access" }, \ diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S index 0b5b8ae56bd9..1e299ac73c86 100644 --- a/tools/arch/x86/lib/memcpy_64.S +++ b/tools/arch/x86/lib/memcpy_64.S @@ -16,8 +16,6 @@ * to a jmp to memcpy_erms which does the REP; MOVSB mem copy. */ -.weak memcpy - /* * memcpy - Copy a memory block. * @@ -30,7 +28,7 @@ * rax original destination */ SYM_FUNC_START_ALIAS(__memcpy) -SYM_FUNC_START_LOCAL(memcpy) +SYM_FUNC_START_WEAK(memcpy) ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \ "jmp memcpy_erms", X86_FEATURE_ERMS @@ -51,14 +49,14 @@ EXPORT_SYMBOL(__memcpy) * memcpy_erms() - enhanced fast string memcpy. This is faster and * simpler than memcpy. Use memcpy_erms when possible. */ -SYM_FUNC_START(memcpy_erms) +SYM_FUNC_START_LOCAL(memcpy_erms) movq %rdi, %rax movq %rdx, %rcx rep movsb ret SYM_FUNC_END(memcpy_erms) -SYM_FUNC_START(memcpy_orig) +SYM_FUNC_START_LOCAL(memcpy_orig) movq %rdi, %rax cmpq $0x20, %rdx diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S index fd5d25a474b7..0bfd26e4ca9e 100644 --- a/tools/arch/x86/lib/memset_64.S +++ b/tools/arch/x86/lib/memset_64.S @@ -4,8 +4,7 @@ #include <linux/linkage.h> #include <asm/cpufeatures.h> #include <asm/alternative-asm.h> - -.weak memset +#include <asm/export.h> /* * ISO C memset - set a memory block to a byte value. This function uses fast @@ -18,7 +17,7 @@ * * rax original destination */ -SYM_FUNC_START_ALIAS(memset) +SYM_FUNC_START_WEAK(memset) SYM_FUNC_START(__memset) /* * Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended @@ -44,6 +43,8 @@ SYM_FUNC_START(__memset) ret SYM_FUNC_END(__memset) SYM_FUNC_END_ALIAS(memset) +EXPORT_SYMBOL(memset) +EXPORT_SYMBOL(__memset) /* * ISO C memset - set a memory block to a byte value. This function uses @@ -56,7 +57,7 @@ SYM_FUNC_END_ALIAS(memset) * * rax original destination */ -SYM_FUNC_START(memset_erms) +SYM_FUNC_START_LOCAL(memset_erms) movq %rdi,%r9 movb %sil,%al movq %rdx,%rcx @@ -65,7 +66,7 @@ SYM_FUNC_START(memset_erms) ret SYM_FUNC_END(memset_erms) -SYM_FUNC_START(memset_orig) +SYM_FUNC_START_LOCAL(memset_orig) movq %rdi,%r10 /* expand byte value */ diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c index a43a6f10b564..359960a8f1de 100644 --- a/tools/bpf/bpftool/feature.c +++ b/tools/bpf/bpftool/feature.c @@ -843,9 +843,14 @@ static int handle_perms(void) else p_err("missing %s%s%s%s%s%s%s%srequired for full feature probing; run as root or use 'unprivileged'", capability_msg(bpf_caps, 0), +#ifdef CAP_BPF capability_msg(bpf_caps, 1), capability_msg(bpf_caps, 2), - capability_msg(bpf_caps, 3)); + capability_msg(bpf_caps, 3) +#else + "", "", "", "", "", "" +#endif /* CAP_BPF */ + ); goto exit_free; } diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c index 910e7bac6e9e..3fae61ef6339 100644 --- a/tools/bpf/bpftool/net.c +++ b/tools/bpf/bpftool/net.c @@ -578,8 +578,8 @@ static int do_attach(int argc, char **argv) ifindex = net_parse_dev(&argc, &argv); if (ifindex < 1) { - close(progfd); - return -EINVAL; + err = -EINVAL; + goto cleanup; } if (argc) { @@ -587,8 +587,8 @@ static int do_attach(int argc, char **argv) overwrite = true; } else { p_err("expected 'overwrite', got: '%s'?", *argv); - close(progfd); - return -EINVAL; + err = -EINVAL; + goto cleanup; } } @@ -596,17 +596,17 @@ static int do_attach(int argc, char **argv) if (is_prefix("xdp", attach_type_strings[attach_type])) err = do_attach_detach_xdp(progfd, attach_type, ifindex, overwrite); - - if (err < 0) { + if (err) { p_err("interface %s attach failed: %s", attach_type_strings[attach_type], strerror(-err)); - return err; + goto cleanup; } if (json_output) jsonw_null(json_wtr); - - return 0; +cleanup: + close(progfd); + return err; } static int do_detach(int argc, char **argv) diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index d942c1e3372c..acdb2c245f0a 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -940,7 +940,7 @@ static int parse_attach_detach_args(int argc, char **argv, int *progfd, } if (*attach_type == BPF_FLOW_DISSECTOR) { - *mapfd = -1; + *mapfd = 0; return 0; } diff --git a/tools/bpf/bpftool/skeleton/profiler.bpf.c b/tools/bpf/bpftool/skeleton/profiler.bpf.c index 4e3512f700c0..ce5b65e07ab1 100644 --- a/tools/bpf/bpftool/skeleton/profiler.bpf.c +++ b/tools/bpf/bpftool/skeleton/profiler.bpf.c @@ -70,7 +70,7 @@ int BPF_PROG(fentry_XXX) static inline void fexit_update_maps(u32 id, struct bpf_perf_event_value *after) { - struct bpf_perf_event_value *before, diff, *accum; + struct bpf_perf_event_value *before, diff; before = bpf_map_lookup_elem(&fentry_readings, &id); /* only account samples with a valid fentry_reading */ @@ -95,7 +95,7 @@ int BPF_PROG(fexit_XXX) { struct bpf_perf_event_value readings[MAX_NUM_MATRICS]; u32 cpu = bpf_get_smp_processor_id(); - u32 i, one = 1, zero = 0; + u32 i, zero = 0; int err; u64 *count; diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c index a04e81321c66..464873883396 100644 --- a/tools/build/feature/test-all.c +++ b/tools/build/feature/test-all.c @@ -185,7 +185,6 @@ int main(int argc, char *argv[]) main_test_libperl(); main_test_hello(); main_test_libelf(); - main_test_libelf_mmap(); main_test_get_current_dir_name(); main_test_gettid(); main_test_glibc(); diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h index b9d4322e1e65..95c072b70d0e 100644 --- a/tools/include/linux/compiler-gcc.h +++ b/tools/include/linux/compiler-gcc.h @@ -27,18 +27,6 @@ #define __pure __attribute__((pure)) #endif #define noinline __attribute__((noinline)) -#ifdef __has_attribute -#if __has_attribute(disable_tail_calls) -#define __no_tail_call __attribute__((disable_tail_calls)) -#endif -#endif -#ifndef __no_tail_call -#if GCC_VERSION > 40201 -#define __no_tail_call __attribute__((optimize("no-optimize-sibling-calls"))) -#else -#define __no_tail_call -#endif -#endif #ifndef __packed #define __packed __attribute__((packed)) #endif diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h index 2b3f7353e891..d22a974372c0 100644 --- a/tools/include/linux/compiler.h +++ b/tools/include/linux/compiler.h @@ -47,9 +47,6 @@ #ifndef noinline #define noinline #endif -#ifndef __no_tail_call -#define __no_tail_call -#endif /* Are two types/vars the same type (ignoring qualifiers)? */ #ifndef __same_type diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index f2b5d72a46c2..2056318988f7 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -857,9 +857,11 @@ __SYSCALL(__NR_openat2, sys_openat2) __SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd) #define __NR_faccessat2 439 __SYSCALL(__NR_faccessat2, sys_faccessat2) +#define __NR_process_madvise 440 +__SYSCALL(__NR_process_madvise, sys_process_madvise) #undef __NR_syscalls -#define __NR_syscalls 440 +#define __NR_syscalls 441 /* * 32 bit systems traditionally used different diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index 00546062e023..fa1f3d62f9a6 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -619,6 +619,12 @@ typedef struct drm_i915_irq_wait { */ #define I915_PARAM_PERF_REVISION 54 +/* Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying an array of + * timeline syncobj through drm_i915_gem_execbuffer_ext_timeline_fences. See + * I915_EXEC_USE_EXTENSIONS. + */ +#define I915_PARAM_HAS_EXEC_TIMELINE_FENCES 55 + /* Must be kept compact -- no holes and well documented */ typedef struct drm_i915_getparam { @@ -1046,6 +1052,38 @@ struct drm_i915_gem_exec_fence { __u32 flags; }; +/** + * See drm_i915_gem_execbuffer_ext_timeline_fences. + */ +#define DRM_I915_GEM_EXECBUFFER_EXT_TIMELINE_FENCES 0 + +/** + * This structure describes an array of drm_syncobj and associated points for + * timeline variants of drm_syncobj. It is invalid to append this structure to + * the execbuf if I915_EXEC_FENCE_ARRAY is set. + */ +struct drm_i915_gem_execbuffer_ext_timeline_fences { + struct i915_user_extension base; + + /** + * Number of element in the handles_ptr & value_ptr arrays. + */ + __u64 fence_count; + + /** + * Pointer to an array of struct drm_i915_gem_exec_fence of length + * fence_count. + */ + __u64 handles_ptr; + + /** + * Pointer to an array of u64 values of length fence_count. Values + * must be 0 for a binary drm_syncobj. A Value of 0 for a timeline + * drm_syncobj is invalid as it turns a drm_syncobj into a binary one. + */ + __u64 values_ptr; +}; + struct drm_i915_gem_execbuffer2 { /** * List of gem_exec_object2 structs @@ -1062,8 +1100,14 @@ struct drm_i915_gem_execbuffer2 { __u32 num_cliprects; /** * This is a struct drm_clip_rect *cliprects if I915_EXEC_FENCE_ARRAY - * is not set. If I915_EXEC_FENCE_ARRAY is set, then this is a - * struct drm_i915_gem_exec_fence *fences. + * & I915_EXEC_USE_EXTENSIONS are not set. + * + * If I915_EXEC_FENCE_ARRAY is set, then this is a pointer to an array + * of struct drm_i915_gem_exec_fence and num_cliprects is the length + * of the array. + * + * If I915_EXEC_USE_EXTENSIONS is set, then this is a pointer to a + * single struct i915_user_extension and num_cliprects is 0. */ __u64 cliprects_ptr; #define I915_EXEC_RING_MASK (0x3f) @@ -1181,7 +1225,16 @@ struct drm_i915_gem_execbuffer2 { */ #define I915_EXEC_FENCE_SUBMIT (1 << 20) -#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_SUBMIT << 1)) +/* + * Setting I915_EXEC_USE_EXTENSIONS implies that + * drm_i915_gem_execbuffer2.cliprects_ptr is treated as a pointer to an linked + * list of i915_user_extension. Each i915_user_extension node is the base of a + * larger structure. The list of supported structures are listed in the + * drm_i915_gem_execbuffer_ext enum. + */ +#define I915_EXEC_USE_EXTENSIONS (1 << 21) + +#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_USE_EXTENSIONS << 1)) #define I915_EXEC_CONTEXT_ID_MASK (0xffffffff) #define i915_execbuffer2_set_context_id(eb2, context) \ diff --git a/tools/include/uapi/linux/fscrypt.h b/tools/include/uapi/linux/fscrypt.h index 7875709ccfeb..e5de60336938 100644 --- a/tools/include/uapi/linux/fscrypt.h +++ b/tools/include/uapi/linux/fscrypt.h @@ -45,7 +45,6 @@ struct fscrypt_policy_v1 { __u8 flags; __u8 master_key_descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE]; }; -#define fscrypt_policy fscrypt_policy_v1 /* * Process-subscribed "logon" key description prefix and payload format. @@ -156,9 +155,9 @@ struct fscrypt_get_key_status_arg { __u32 __out_reserved[13]; }; -#define FS_IOC_SET_ENCRYPTION_POLICY _IOR('f', 19, struct fscrypt_policy) +#define FS_IOC_SET_ENCRYPTION_POLICY _IOR('f', 19, struct fscrypt_policy_v1) #define FS_IOC_GET_ENCRYPTION_PWSALT _IOW('f', 20, __u8[16]) -#define FS_IOC_GET_ENCRYPTION_POLICY _IOW('f', 21, struct fscrypt_policy) +#define FS_IOC_GET_ENCRYPTION_POLICY _IOW('f', 21, struct fscrypt_policy_v1) #define FS_IOC_GET_ENCRYPTION_POLICY_EX _IOWR('f', 22, __u8[9]) /* size + version */ #define FS_IOC_ADD_ENCRYPTION_KEY _IOWR('f', 23, struct fscrypt_add_key_arg) #define FS_IOC_REMOVE_ENCRYPTION_KEY _IOWR('f', 24, struct fscrypt_remove_key_arg) @@ -170,6 +169,7 @@ struct fscrypt_get_key_status_arg { /* old names; don't add anything new here! */ #ifndef __KERNEL__ +#define fscrypt_policy fscrypt_policy_v1 #define FS_KEY_DESCRIPTOR_SIZE FSCRYPT_KEY_DESCRIPTOR_SIZE #define FS_POLICY_FLAGS_PAD_4 FSCRYPT_POLICY_FLAGS_PAD_4 #define FS_POLICY_FLAGS_PAD_8 FSCRYPT_POLICY_FLAGS_PAD_8 diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 7d8eced6f459..ca41220b40b8 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -248,6 +248,8 @@ struct kvm_hyperv_exit { #define KVM_EXIT_IOAPIC_EOI 26 #define KVM_EXIT_HYPERV 27 #define KVM_EXIT_ARM_NISV 28 +#define KVM_EXIT_X86_RDMSR 29 +#define KVM_EXIT_X86_WRMSR 30 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -413,6 +415,17 @@ struct kvm_run { __u64 esr_iss; __u64 fault_ipa; } arm_nisv; + /* KVM_EXIT_X86_RDMSR / KVM_EXIT_X86_WRMSR */ + struct { + __u8 error; /* user -> kernel */ + __u8 pad[7]; +#define KVM_MSR_EXIT_REASON_INVAL (1 << 0) +#define KVM_MSR_EXIT_REASON_UNKNOWN (1 << 1) +#define KVM_MSR_EXIT_REASON_FILTER (1 << 2) + __u32 reason; /* kernel -> user */ + __u32 index; /* kernel -> user */ + __u64 data; /* kernel <-> user */ + } msr; /* Fix the size of the union. */ char padding[256]; }; @@ -1037,6 +1050,9 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_SMALLER_MAXPHYADDR 185 #define KVM_CAP_S390_DIAG318 186 #define KVM_CAP_STEAL_TIME 187 +#define KVM_CAP_X86_USER_SPACE_MSR 188 +#define KVM_CAP_X86_MSR_FILTER 189 +#define KVM_CAP_ENFORCE_PV_FEATURE_CPUID 190 #ifdef KVM_CAP_IRQ_ROUTING @@ -1538,6 +1554,9 @@ struct kvm_pv_cmd { /* Available with KVM_CAP_S390_PROTECTED */ #define KVM_S390_PV_COMMAND _IOWR(KVMIO, 0xc5, struct kvm_pv_cmd) +/* Available with KVM_CAP_X86_MSR_FILTER */ +#define KVM_X86_SET_MSR_FILTER _IOW(KVMIO, 0xc6, struct kvm_msr_filter) + /* Secure Encrypted Virtualization command */ enum sev_cmd_id { /* Guest initialization commands */ diff --git a/tools/include/uapi/linux/mman.h b/tools/include/uapi/linux/mman.h index 923cc162609c..f55bc680b5b0 100644 --- a/tools/include/uapi/linux/mman.h +++ b/tools/include/uapi/linux/mman.h @@ -27,6 +27,7 @@ #define MAP_HUGE_SHIFT HUGETLB_FLAG_ENCODE_SHIFT #define MAP_HUGE_MASK HUGETLB_FLAG_ENCODE_MASK +#define MAP_HUGE_16KB HUGETLB_FLAG_ENCODE_16KB #define MAP_HUGE_64KB HUGETLB_FLAG_ENCODE_64KB #define MAP_HUGE_512KB HUGETLB_FLAG_ENCODE_512KB #define MAP_HUGE_1MB HUGETLB_FLAG_ENCODE_1MB diff --git a/tools/include/uapi/linux/mount.h b/tools/include/uapi/linux/mount.h index 96a0240f23fe..dd8306ea336c 100644 --- a/tools/include/uapi/linux/mount.h +++ b/tools/include/uapi/linux/mount.h @@ -16,6 +16,7 @@ #define MS_REMOUNT 32 /* Alter flags of a mounted FS */ #define MS_MANDLOCK 64 /* Allow mandatory locks on an FS */ #define MS_DIRSYNC 128 /* Directory modifications are synchronous */ +#define MS_NOSYMFOLLOW 256 /* Do not follow symlinks */ #define MS_NOATIME 1024 /* Do not update access times. */ #define MS_NODIRATIME 2048 /* Do not update directory access times */ #define MS_BIND 4096 diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index 3e5dcdd48a49..b95d3c485d27 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -1196,7 +1196,7 @@ union perf_mem_data_src { #define PERF_MEM_SNOOPX_FWD 0x01 /* forward */ /* 1 free */ -#define PERF_MEM_SNOOPX_SHIFT 38 +#define PERF_MEM_SNOOPX_SHIFT 38 /* locked instruction */ #define PERF_MEM_LOCK_NA 0x01 /* not available */ diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index 07b4f8131e36..7f0827705c9a 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -233,6 +233,15 @@ struct prctl_mm_map { #define PR_SET_TAGGED_ADDR_CTRL 55 #define PR_GET_TAGGED_ADDR_CTRL 56 # define PR_TAGGED_ADDR_ENABLE (1UL << 0) +/* MTE tag check fault modes */ +# define PR_MTE_TCF_SHIFT 1 +# define PR_MTE_TCF_NONE (0UL << PR_MTE_TCF_SHIFT) +# define PR_MTE_TCF_SYNC (1UL << PR_MTE_TCF_SHIFT) +# define PR_MTE_TCF_ASYNC (2UL << PR_MTE_TCF_SHIFT) +# define PR_MTE_TCF_MASK (3UL << PR_MTE_TCF_SHIFT) +/* MTE tag inclusion mask */ +# define PR_MTE_TAG_SHIFT 3 +# define PR_MTE_TAG_MASK (0xffffUL << PR_MTE_TAG_SHIFT) /* Control reclaim behavior when allocating memory */ #define PR_SET_IO_FLUSHER 57 diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h index 75232185324a..c998860d7bbc 100644 --- a/tools/include/uapi/linux/vhost.h +++ b/tools/include/uapi/linux/vhost.h @@ -146,4 +146,8 @@ /* Set event fd for config interrupt*/ #define VHOST_VDPA_SET_CONFIG_CALL _IOW(VHOST_VIRTIO, 0x77, int) + +/* Get the valid iova range */ +#define VHOST_VDPA_GET_IOVA_RANGE _IOR(VHOST_VIRTIO, 0x78, \ + struct vhost_vdpa_iova_range) #endif diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index 5f9abed3e226..55bd78b3496f 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -146,6 +146,7 @@ GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN_SHARED) | \ awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}' | \ sort -u | wc -l) VERSIONED_SYM_COUNT = $(shell readelf --dyn-syms --wide $(OUTPUT)libbpf.so | \ + sed 's/\[.*\]//' | \ awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}' | \ grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | sort -u | wc -l) @@ -214,6 +215,7 @@ check_abi: $(OUTPUT)libbpf.so awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}'| \ sort -u > $(OUTPUT)libbpf_global_syms.tmp; \ readelf --dyn-syms --wide $(OUTPUT)libbpf.so | \ + sed 's/\[.*\]//' | \ awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}'| \ grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | \ sort -u > $(OUTPUT)libbpf_versioned_syms.tmp; \ diff --git a/tools/lib/bpf/hashmap.h b/tools/lib/bpf/hashmap.h index d9b385fe808c..10a4c4cd13cf 100644 --- a/tools/lib/bpf/hashmap.h +++ b/tools/lib/bpf/hashmap.h @@ -15,6 +15,9 @@ static inline size_t hash_bits(size_t h, int bits) { /* shuffle bits and return requested number of upper bits */ + if (bits == 0) + return 0; + #if (__SIZEOF_SIZE_T__ == __SIZEOF_LONG_LONG__) /* LP64 case */ return (h * 11400714819323198485llu) >> (__SIZEOF_LONG_LONG__ * 8 - bits); @@ -174,17 +177,17 @@ bool hashmap__find(const struct hashmap *map, const void *key, void **value); * @key: key to iterate entries for */ #define hashmap__for_each_key_entry(map, cur, _key) \ - for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\ - map->cap_bits); \ - map->buckets ? map->buckets[bkt] : NULL; }); \ + for (cur = map->buckets \ + ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \ + : NULL; \ cur; \ cur = cur->next) \ if (map->equal_fn(cur->key, (_key), map->ctx)) #define hashmap__for_each_key_entry_safe(map, cur, tmp, _key) \ - for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\ - map->cap_bits); \ - cur = map->buckets ? map->buckets[bkt] : NULL; }); \ + for (cur = map->buckets \ + ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \ + : NULL; \ cur && ({ tmp = cur->next; true; }); \ cur = tmp) \ if (map->equal_fn(cur->key, (_key), map->ctx)) diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 313034117070..28baee7ba1ca 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -560,8 +560,6 @@ bpf_object__init_prog(struct bpf_object *obj, struct bpf_program *prog, const char *name, size_t sec_idx, const char *sec_name, size_t sec_off, void *insn_data, size_t insn_data_sz) { - int i; - if (insn_data_sz == 0 || insn_data_sz % BPF_INSN_SZ || sec_off % BPF_INSN_SZ) { pr_warn("sec '%s': corrupted program '%s', offset %zu, size %zu\n", sec_name, name, sec_off, insn_data_sz); @@ -600,13 +598,6 @@ bpf_object__init_prog(struct bpf_object *obj, struct bpf_program *prog, goto errout; memcpy(prog->insns, insn_data, insn_data_sz); - for (i = 0; i < prog->insns_cnt; i++) { - if (insn_is_subprog_call(&prog->insns[i])) { - obj->has_subcalls = true; - break; - } - } - return 0; errout: pr_warn("sec '%s': failed to allocate memory for prog '%s'\n", sec_name, name); @@ -3280,7 +3271,19 @@ bpf_object__find_program_by_title(const struct bpf_object *obj, static bool prog_is_subprog(const struct bpf_object *obj, const struct bpf_program *prog) { - return prog->sec_idx == obj->efile.text_shndx && obj->has_subcalls; + /* For legacy reasons, libbpf supports an entry-point BPF programs + * without SEC() attribute, i.e., those in the .text section. But if + * there are 2 or more such programs in the .text section, they all + * must be subprograms called from entry-point BPF programs in + * designated SEC()'tions, otherwise there is no way to distinguish + * which of those programs should be loaded vs which are a subprogram. + * Similarly, if there is a function/program in .text and at least one + * other BPF program with custom SEC() attribute, then we just assume + * .text programs are subprograms (even if they are not called from + * other programs), because libbpf never explicitly supported mixing + * SEC()-designated BPF programs and .text entry-point BPF programs. + */ + return prog->sec_idx == obj->efile.text_shndx && obj->nr_programs > 1; } struct bpf_program * diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index e3c98c007825..9bc537d0b92d 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -891,13 +891,16 @@ int xsk_umem__delete(struct xsk_umem *umem) void xsk_socket__delete(struct xsk_socket *xsk) { size_t desc_sz = sizeof(struct xdp_desc); - struct xsk_ctx *ctx = xsk->ctx; struct xdp_mmap_offsets off; + struct xsk_umem *umem; + struct xsk_ctx *ctx; int err; if (!xsk) return; + ctx = xsk->ctx; + umem = ctx->umem; if (ctx->prog_fd != -1) { xsk_delete_bpf_maps(xsk); close(ctx->prog_fd); @@ -917,11 +920,11 @@ void xsk_socket__delete(struct xsk_socket *xsk) xsk_put_ctx(ctx); - ctx->umem->refcount--; + umem->refcount--; /* Do not close an fd that also has an associated umem connected * to it. */ - if (xsk->fd != ctx->umem->fd) + if (xsk->fd != umem->fd) close(xsk->fd); free(xsk); } diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 6890fc4b063a..ce8516e4de34 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -749,6 +749,7 @@ else PERL_EMBED_LIBADD = $(call grep-libs,$(PERL_EMBED_LDOPTS)) PERL_EMBED_CCOPTS = $(shell perl -MExtUtils::Embed -e ccopts 2>/dev/null) PERL_EMBED_CCOPTS := $(filter-out -specs=%,$(PERL_EMBED_CCOPTS)) + PERL_EMBED_CCOPTS := $(filter-out -flto=auto -ffat-lto-objects, $(PERL_EMBED_CCOPTS)) PERL_EMBED_LDOPTS := $(filter-out -specs=%,$(PERL_EMBED_LDOPTS)) FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS) diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index 347809649ba2..379819244b91 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -361,12 +361,13 @@ 437 common openat2 sys_openat2 438 common pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 +440 common process_madvise sys_process_madvise # -# x32-specific system call numbers start at 512 to avoid cache impact -# for native 64-bit operation. The __x32_compat_sys stubs are created -# on-the-fly for compat_sys_*() compatibility system calls if X86_X32 -# is defined. +# Due to a historical design error, certain syscalls are numbered differently +# in x32 as compared to native x86_64. These syscalls have numbers 512-547. +# Do not add new syscalls to this range. Numbers 548 and above are available +# for non-x32 use. # 512 x32 rt_sigaction compat_sys_rt_sigaction 513 x32 rt_sigreturn compat_sys_x32_rt_sigreturn @@ -404,3 +405,5 @@ 545 x32 execveat compat_sys_execveat 546 x32 preadv2 compat_sys_preadv64v2 547 x32 pwritev2 compat_sys_pwritev64v2 +# This is the end of the legacy x32 range. Numbers 548 and above are +# not special and are not to be used for x32-specific syscalls. diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c index 4e40402a4f81..478078fb0f22 100644 --- a/tools/perf/arch/x86/tests/dwarf-unwind.c +++ b/tools/perf/arch/x86/tests/dwarf-unwind.c @@ -38,6 +38,13 @@ static int sample_ustack(struct perf_sample *sample, stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size; memcpy(buf, (void *) sp, stack_size); +#ifdef MEMORY_SANITIZER + /* + * Copying the stack may copy msan poison, avoid false positives in the + * unwinder by removing the poison here. + */ + __msan_unpoison(buf, stack_size); +#endif stack->data = (char *) buf; stack->size = stack_size; return 0; diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S index 9ad015a1e202..6eb45a2aa8db 100644 --- a/tools/perf/bench/mem-memcpy-x86-64-asm.S +++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S @@ -2,6 +2,9 @@ /* Various wrappers to make the kernel .S file build in user-space: */ +// memcpy_orig and memcpy_erms are being defined as SYM_L_LOCAL but we need it +#define SYM_FUNC_START_LOCAL(name) \ + SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) #define memcpy MEMCPY /* don't hide glibc's memcpy() */ #define altinstr_replacement text #define globl p2align 4; .globl diff --git a/tools/perf/bench/mem-memset-x86-64-asm.S b/tools/perf/bench/mem-memset-x86-64-asm.S index d550bd526162..6f093c483842 100644 --- a/tools/perf/bench/mem-memset-x86-64-asm.S +++ b/tools/perf/bench/mem-memset-x86-64-asm.S @@ -1,4 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ +// memset_orig and memset_erms are being defined as SYM_L_LOCAL but we need it +#define SYM_FUNC_START_LOCAL(name) \ + SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) #define memset MEMSET /* don't hide glibc's memset() */ #define altinstr_replacement text #define globl p2align 4; .globl diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 452a75fe68e5..0462dc8db2e3 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -779,25 +779,15 @@ static int __cmd_inject(struct perf_inject *inject) dsos__hit_all(session); /* * The AUX areas have been removed and replaced with - * synthesized hardware events, so clear the feature flag and - * remove the evsel. + * synthesized hardware events, so clear the feature flag. */ if (inject->itrace_synth_opts.set) { - struct evsel *evsel; - perf_header__clear_feat(&session->header, HEADER_AUXTRACE); if (inject->itrace_synth_opts.last_branch || inject->itrace_synth_opts.add_last_branch) perf_header__set_feat(&session->header, HEADER_BRANCH_STACK); - evsel = perf_evlist__id2evsel_strict(session->evlist, - inject->aux_id); - if (evsel) { - pr_debug("Deleting %s\n", evsel__name(evsel)); - evlist__remove(session->evlist, evsel); - evsel__delete(evsel); - } } session->header.data_offset = output_data_offset; session->header.data_size = inject->bytes_written; diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index f0a1dbacb46c..a2f1e53f37a7 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -406,7 +406,7 @@ static int report_lock_acquire_event(struct evsel *evsel, struct lock_seq_stat *seq; const char *name = evsel__strval(evsel, sample, "name"); u64 tmp = evsel__intval(evsel, sample, "lockdep_addr"); - int flag = evsel__intval(evsel, sample, "flag"); + int flag = evsel__intval(evsel, sample, "flags"); memcpy(&addr, &tmp, sizeof(void *)); @@ -621,7 +621,7 @@ static int report_lock_release_event(struct evsel *evsel, case SEQ_STATE_READ_ACQUIRED: seq->read_count--; BUG_ON(seq->read_count < 0); - if (!seq->read_count) { + if (seq->read_count) { ls->nr_release++; goto end; } diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 44a75f234db1..de80534473af 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -4639,9 +4639,9 @@ do_concat: err = 0; if (lists[0]) { - struct option o = OPT_CALLBACK('e', "event", &trace->evlist, "event", - "event selector. use 'perf list' to list available events", - parse_events_option); + struct option o = { + .value = &trace->evlist, + }; err = parse_events_option(&o, lists[0], 0); } out: @@ -4655,9 +4655,12 @@ static int trace__parse_cgroups(const struct option *opt, const char *str, int u { struct trace *trace = opt->value; - if (!list_empty(&trace->evlist->core.entries)) - return parse_cgroups(opt, str, unset); - + if (!list_empty(&trace->evlist->core.entries)) { + struct option o = { + .value = &trace->evlist, + }; + return parse_cgroups(&o, str, unset); + } trace->cgroup = evlist__findnew_cgroup(trace->evlist, str); return 0; diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json index de3193552277..00f4fcffa815 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json @@ -329,7 +329,7 @@ }, { "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time", + "MetricExpr": "( ( ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) * 1048576 ) / 1000000000 ) / duration_time", "MetricGroup": "Memory_BW;SoC", "MetricName": "DRAM_BW_Use" }, diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json index f31794d3b926..0dd8b13b5cfb 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json @@ -323,7 +323,7 @@ }, { "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time", + "MetricExpr": "( ( ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) * 1048576 ) / 1000000000 ) / duration_time", "MetricGroup": "Memory_BW;SoC", "MetricName": "DRAM_BW_Use" }, diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c index 2491d167bf76..83638097c3bc 100644 --- a/tools/perf/tests/dwarf-unwind.c +++ b/tools/perf/tests/dwarf-unwind.c @@ -95,7 +95,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) return strcmp((const char *) symbol, funcs[idx]); } -__no_tail_call noinline int test_dwarf_unwind__thread(struct thread *thread) +noinline int test_dwarf_unwind__thread(struct thread *thread) { struct perf_sample sample; unsigned long cnt = 0; @@ -126,7 +126,7 @@ __no_tail_call noinline int test_dwarf_unwind__thread(struct thread *thread) static int global_unwind_retval = -INT_MAX; -__no_tail_call noinline int test_dwarf_unwind__compare(void *p1, void *p2) +noinline int test_dwarf_unwind__compare(void *p1, void *p2) { /* Any possible value should be 'thread' */ struct thread *thread = *(struct thread **)p1; @@ -145,7 +145,7 @@ __no_tail_call noinline int test_dwarf_unwind__compare(void *p1, void *p2) return p1 - p2; } -__no_tail_call noinline int test_dwarf_unwind__krava_3(struct thread *thread) +noinline int test_dwarf_unwind__krava_3(struct thread *thread) { struct thread *array[2] = {thread, thread}; void *fp = &bsearch; @@ -164,12 +164,12 @@ __no_tail_call noinline int test_dwarf_unwind__krava_3(struct thread *thread) return global_unwind_retval; } -__no_tail_call noinline int test_dwarf_unwind__krava_2(struct thread *thread) +noinline int test_dwarf_unwind__krava_2(struct thread *thread) { return test_dwarf_unwind__krava_3(thread); } -__no_tail_call noinline int test_dwarf_unwind__krava_1(struct thread *thread) +noinline int test_dwarf_unwind__krava_1(struct thread *thread) { return test_dwarf_unwind__krava_2(thread); } diff --git a/tools/perf/tests/shell/test_arm_coresight.sh b/tools/perf/tests/shell/test_arm_coresight.sh index 8d84fdbed6a6..18fde2f179cd 100755 --- a/tools/perf/tests/shell/test_arm_coresight.sh +++ b/tools/perf/tests/shell/test_arm_coresight.sh @@ -44,7 +44,7 @@ perf_script_branch_samples() { # touch 6512 1 branches:u: ffffb22082e0 strcmp+0xa0 (/lib/aarch64-linux-gnu/ld-2.27.so) # touch 6512 1 branches:u: ffffb2208320 strcmp+0xe0 (/lib/aarch64-linux-gnu/ld-2.27.so) perf script -F,-time -i ${perfdata} | \ - egrep " +$1 +[0-9]+ .* +branches:([u|k]:)? +" + egrep " +$1 +[0-9]+ .* +branches:(.*:)? +" } perf_report_branch_samples() { @@ -105,7 +105,7 @@ arm_cs_iterate_devices() { # `> device_name = 'tmc_etf0' device_name=$(basename $path) - if is_device_sink $path $devce_name; then + if is_device_sink $path $device_name; then record_touch_file $device_name $2 && perf_script_branch_samples touch && diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index a07626f07208..b0e1880cf992 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -2963,7 +2963,7 @@ static int perf_evsel__hists_browse(struct evsel *evsel, int nr_events, struct popup_action actions[MAX_OPTIONS]; int nr_options = 0; int key = -1; - char buf[64]; + char buf[128]; int delay_secs = hbt ? hbt->refresh : 0; #define HIST_BROWSER_HELP_COMMON \ diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 8763772f1095..6b410c3d52dc 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -102,6 +102,8 @@ int build_id__sprintf(const struct build_id *build_id, char *bf) const u8 *raw = build_id->data; size_t i; + bf[0] = 0x0; + for (i = 0; i < build_id->size; ++i) { sprintf(bid, "%02x", *raw); ++raw; diff --git a/tools/perf/util/hashmap.c b/tools/perf/util/hashmap.c index a405dad068f5..3c20b126d60d 100644 --- a/tools/perf/util/hashmap.c +++ b/tools/perf/util/hashmap.c @@ -15,6 +15,9 @@ /* make sure libbpf doesn't use kernel-only integer typedefs */ #pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 +/* prevent accidental re-addition of reallocarray() */ +#pragma GCC poison reallocarray + /* start with 4 buckets */ #define HASHMAP_MIN_CAP_BITS 2 diff --git a/tools/perf/util/hashmap.h b/tools/perf/util/hashmap.h index e0af36b0e5d8..d9b385fe808c 100644 --- a/tools/perf/util/hashmap.h +++ b/tools/perf/util/hashmap.h @@ -25,6 +25,18 @@ static inline size_t hash_bits(size_t h, int bits) #endif } +/* generic C-string hashing function */ +static inline size_t str_hash(const char *s) +{ + size_t h = 0; + + while (*s) { + h = h * 31 + *s; + s++; + } + return h; +} + typedef size_t (*hashmap_hash_fn)(const void *key, void *ctx); typedef bool (*hashmap_equal_fn)(const void *key1, const void *key2, void *ctx); diff --git a/tools/perf/util/include/linux/linkage.h b/tools/perf/util/include/linux/linkage.h index b8a5159361b4..5acf053fca7d 100644 --- a/tools/perf/util/include/linux/linkage.h +++ b/tools/perf/util/include/linux/linkage.h @@ -25,6 +25,7 @@ /* SYM_L_* -- linkage of symbols */ #define SYM_L_GLOBAL(name) .globl name +#define SYM_L_WEAK(name) .weak name #define SYM_L_LOCAL(name) /* nothing */ #define ALIGN __ALIGN @@ -84,6 +85,12 @@ SYM_END(name, SYM_T_FUNC) #endif +/* SYM_FUNC_START_WEAK -- use for weak functions */ +#ifndef SYM_FUNC_START_WEAK +#define SYM_FUNC_START_WEAK(name) \ + SYM_START(name, SYM_L_WEAK, SYM_A_ALIGN) +#endif + /* * SYM_FUNC_END -- the end of SYM_FUNC_START_LOCAL, SYM_FUNC_START, * SYM_FUNC_START_WEAK, ... diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 7d4194ffc5b0..15385ea00190 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -786,11 +786,20 @@ static int machine__process_ksymbol_unregister(struct machine *machine, union perf_event *event, struct perf_sample *sample __maybe_unused) { + struct symbol *sym; struct map *map; map = maps__find(&machine->kmaps, event->ksymbol.addr); - if (map) + if (!map) + return 0; + + if (map != machine->vmlinux_map) maps__remove(&machine->kmaps, map); + else { + sym = dso__find_symbol(map->dso, map->map_ip(map, map->start)); + if (sym) + dso__delete_symbol(map->dso, sym); + } return 0; } diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 7cbd024e3e63..c83c2c6564e0 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -1592,7 +1592,6 @@ static void _free_command_line(wchar_t **command_line, int num) static int python_start_script(const char *script, int argc, const char **argv) { struct tables *tables = &tables_global; - PyMODINIT_FUNC (*initfunc)(void); #if PY_MAJOR_VERSION < 3 const char **command_line; #else @@ -1607,20 +1606,18 @@ static int python_start_script(const char *script, int argc, const char **argv) FILE *fp; #if PY_MAJOR_VERSION < 3 - initfunc = initperf_trace_context; command_line = malloc((argc + 1) * sizeof(const char *)); command_line[0] = script; for (i = 1; i < argc + 1; i++) command_line[i] = argv[i - 1]; + PyImport_AppendInittab(name, initperf_trace_context); #else - initfunc = PyInit_perf_trace_context; command_line = malloc((argc + 1) * sizeof(wchar_t *)); command_line[0] = Py_DecodeLocale(script, NULL); for (i = 1; i < argc + 1; i++) command_line[i] = Py_DecodeLocale(argv[i - 1], NULL); + PyImport_AppendInittab(name, PyInit_perf_trace_context); #endif - - PyImport_AppendInittab(name, initfunc); Py_Initialize(); #if PY_MAJOR_VERSION < 3 diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 7a5f03764702..098080287c68 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -595,6 +595,7 @@ static void perf_event__mmap2_swap(union perf_event *event, event->mmap2.maj = bswap_32(event->mmap2.maj); event->mmap2.min = bswap_32(event->mmap2.min); event->mmap2.ino = bswap_64(event->mmap2.ino); + event->mmap2.ino_generation = bswap_64(event->mmap2.ino_generation); if (sample_id_all) { void *data = &event->mmap2.filename; @@ -710,6 +711,18 @@ static void perf_event__namespaces_swap(union perf_event *event, swap_sample_id_all(event, &event->namespaces.link_info[i]); } +static void perf_event__cgroup_swap(union perf_event *event, bool sample_id_all) +{ + event->cgroup.id = bswap_64(event->cgroup.id); + + if (sample_id_all) { + void *data = &event->cgroup.path; + + data += PERF_ALIGN(strlen(data) + 1, sizeof(u64)); + swap_sample_id_all(event, data); + } +} + static u8 revbyte(u8 b) { int rev = (b >> 4) | ((b & 0xf) << 4); @@ -952,6 +965,7 @@ static perf_event__swap_op perf_event__swap_ops[] = { [PERF_RECORD_SWITCH] = perf_event__switch_swap, [PERF_RECORD_SWITCH_CPU_WIDE] = perf_event__switch_swap, [PERF_RECORD_NAMESPACES] = perf_event__namespaces_swap, + [PERF_RECORD_CGROUP] = perf_event__cgroup_swap, [PERF_RECORD_TEXT_POKE] = perf_event__text_poke_swap, [PERF_RECORD_HEADER_ATTR] = perf_event__hdr_attr_swap, [PERF_RECORD_HEADER_EVENT_TYPE] = perf_event__event_type_swap, diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 6138866665df..0d14abdf3d72 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -515,6 +515,13 @@ void dso__insert_symbol(struct dso *dso, struct symbol *sym) } } +void dso__delete_symbol(struct dso *dso, struct symbol *sym) +{ + rb_erase_cached(&sym->rb_node, &dso->symbols); + symbol__delete(sym); + dso__reset_find_symbol_cache(dso); +} + struct symbol *dso__find_symbol(struct dso *dso, u64 addr) { if (dso->last_find_result.addr != addr || dso->last_find_result.symbol == NULL) { diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index f4801c488def..954d6a049ee2 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -131,6 +131,8 @@ int dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map); void dso__insert_symbol(struct dso *dso, struct symbol *sym); +void dso__delete_symbol(struct dso *dso, + struct symbol *sym); struct symbol *dso__find_symbol(struct dso *dso, u64 addr); struct symbol *dso__find_symbol_by_name(struct dso *dso, const char *name); diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile index 2b6551269e43..f3e3c94ab9bd 100644 --- a/tools/power/x86/turbostat/Makefile +++ b/tools/power/x86/turbostat/Makefile @@ -12,11 +12,12 @@ turbostat : turbostat.c override CFLAGS += -O2 -Wall -I../../../include override CFLAGS += -DMSRHEADER='"../../../../arch/x86/include/asm/msr-index.h"' override CFLAGS += -DINTEL_FAMILY_HEADER='"../../../../arch/x86/include/asm/intel-family.h"' +override CFLAGS += -D_FILE_OFFSET_BITS=64 override CFLAGS += -D_FORTIFY_SOURCE=2 %: %.c @mkdir -p $(BUILD_OUTPUT) - $(CC) $(CFLAGS) $< -o $(BUILD_OUTPUT)/$@ $(LDFLAGS) -lcap + $(CC) $(CFLAGS) $< -o $(BUILD_OUTPUT)/$@ $(LDFLAGS) -lcap -lrt .PHONY : clean clean : diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8 index a6db83a88e85..f6b7e85b121c 100644 --- a/tools/power/x86/turbostat/turbostat.8 +++ b/tools/power/x86/turbostat/turbostat.8 @@ -335,7 +335,7 @@ that they count at TSC rate, which is true on all processors tested to date. .SH REFERENCES Volume 3B: System Programming Guide" -http://www.intel.com/products/processor/manuals/ +https://www.intel.com/products/processor/manuals/ .SH FILES .ta diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 33b370865d16..f3a1746f7f45 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -79,6 +79,7 @@ unsigned long long gfx_cur_rc6_ms; unsigned long long cpuidle_cur_cpu_lpi_us; unsigned long long cpuidle_cur_sys_lpi_us; unsigned int gfx_cur_mhz; +unsigned int gfx_act_mhz; unsigned int tcc_activation_temp; unsigned int tcc_activation_temp_override; double rapl_power_units, rapl_time_units; @@ -210,13 +211,14 @@ struct pkg_data { unsigned long long pkg_both_core_gfxe_c0; long long gfx_rc6_ms; unsigned int gfx_mhz; + unsigned int gfx_act_mhz; unsigned int package_id; - unsigned int energy_pkg; /* MSR_PKG_ENERGY_STATUS */ - unsigned int energy_dram; /* MSR_DRAM_ENERGY_STATUS */ - unsigned int energy_cores; /* MSR_PP0_ENERGY_STATUS */ - unsigned int energy_gfx; /* MSR_PP1_ENERGY_STATUS */ - unsigned int rapl_pkg_perf_status; /* MSR_PKG_PERF_STATUS */ - unsigned int rapl_dram_perf_status; /* MSR_DRAM_PERF_STATUS */ + unsigned long long energy_pkg; /* MSR_PKG_ENERGY_STATUS */ + unsigned long long energy_dram; /* MSR_DRAM_ENERGY_STATUS */ + unsigned long long energy_cores; /* MSR_PP0_ENERGY_STATUS */ + unsigned long long energy_gfx; /* MSR_PP1_ENERGY_STATUS */ + unsigned long long rapl_pkg_perf_status; /* MSR_PKG_PERF_STATUS */ + unsigned long long rapl_dram_perf_status; /* MSR_DRAM_PERF_STATUS */ unsigned int pkg_temp_c; unsigned long long counter[MAX_ADDED_COUNTERS]; } *package_even, *package_odd; @@ -259,6 +261,113 @@ struct msr_counter { #define SYSFS_PERCPU (1 << 1) }; +/* + * The accumulated sum of MSR is defined as a monotonic + * increasing MSR, it will be accumulated periodically, + * despite its register's bit width. + */ +enum { + IDX_PKG_ENERGY, + IDX_DRAM_ENERGY, + IDX_PP0_ENERGY, + IDX_PP1_ENERGY, + IDX_PKG_PERF, + IDX_DRAM_PERF, + IDX_COUNT, +}; + +int get_msr_sum(int cpu, off_t offset, unsigned long long *msr); + +struct msr_sum_array { + /* get_msr_sum() = sum + (get_msr() - last) */ + struct { + /*The accumulated MSR value is updated by the timer*/ + unsigned long long sum; + /*The MSR footprint recorded in last timer*/ + unsigned long long last; + } entries[IDX_COUNT]; +}; + +/* The percpu MSR sum array.*/ +struct msr_sum_array *per_cpu_msr_sum; + +int idx_to_offset(int idx) +{ + int offset; + + switch (idx) { + case IDX_PKG_ENERGY: + offset = MSR_PKG_ENERGY_STATUS; + break; + case IDX_DRAM_ENERGY: + offset = MSR_DRAM_ENERGY_STATUS; + break; + case IDX_PP0_ENERGY: + offset = MSR_PP0_ENERGY_STATUS; + break; + case IDX_PP1_ENERGY: + offset = MSR_PP1_ENERGY_STATUS; + break; + case IDX_PKG_PERF: + offset = MSR_PKG_PERF_STATUS; + break; + case IDX_DRAM_PERF: + offset = MSR_DRAM_PERF_STATUS; + break; + default: + offset = -1; + } + return offset; +} + +int offset_to_idx(int offset) +{ + int idx; + + switch (offset) { + case MSR_PKG_ENERGY_STATUS: + idx = IDX_PKG_ENERGY; + break; + case MSR_DRAM_ENERGY_STATUS: + idx = IDX_DRAM_ENERGY; + break; + case MSR_PP0_ENERGY_STATUS: + idx = IDX_PP0_ENERGY; + break; + case MSR_PP1_ENERGY_STATUS: + idx = IDX_PP1_ENERGY; + break; + case MSR_PKG_PERF_STATUS: + idx = IDX_PKG_PERF; + break; + case MSR_DRAM_PERF_STATUS: + idx = IDX_DRAM_PERF; + break; + default: + idx = -1; + } + return idx; +} + +int idx_valid(int idx) +{ + switch (idx) { + case IDX_PKG_ENERGY: + return do_rapl & RAPL_PKG; + case IDX_DRAM_ENERGY: + return do_rapl & RAPL_DRAM; + case IDX_PP0_ENERGY: + return do_rapl & RAPL_CORES_ENERGY_STATUS; + case IDX_PP1_ENERGY: + return do_rapl & RAPL_GFX; + case IDX_PKG_PERF: + return do_rapl & RAPL_PKG_PERF_STATUS; + case IDX_DRAM_PERF: + return do_rapl & RAPL_DRAM_PERF_STATUS; + default: + return 0; + } +} struct sys_counters { unsigned int added_thread_counters; unsigned int added_core_counters; @@ -451,6 +560,7 @@ struct msr_counter bic[] = { { 0x0, "APIC" }, { 0x0, "X2APIC" }, { 0x0, "Die" }, + { 0x0, "GFXAMHz" }, }; #define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter)) @@ -505,6 +615,7 @@ struct msr_counter bic[] = { #define BIC_APIC (1ULL << 48) #define BIC_X2APIC (1ULL << 49) #define BIC_Die (1ULL << 50) +#define BIC_GFXACTMHz (1ULL << 51) #define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC) @@ -724,6 +835,9 @@ void print_header(char *delim) if (DO_BIC(BIC_GFXMHz)) outp += sprintf(outp, "%sGFXMHz", (printed++ ? delim : "")); + if (DO_BIC(BIC_GFXACTMHz)) + outp += sprintf(outp, "%sGFXAMHz", (printed++ ? delim : "")); + if (DO_BIC(BIC_Totl_c0)) outp += sprintf(outp, "%sTotl%%C0", (printed++ ? delim : "")); if (DO_BIC(BIC_Any_c0)) @@ -858,13 +972,13 @@ int dump_counters(struct thread_data *t, struct core_data *c, outp += sprintf(outp, "pc10: %016llX\n", p->pc10); outp += sprintf(outp, "cpu_lpi: %016llX\n", p->cpu_lpi); outp += sprintf(outp, "sys_lpi: %016llX\n", p->sys_lpi); - outp += sprintf(outp, "Joules PKG: %0X\n", p->energy_pkg); - outp += sprintf(outp, "Joules COR: %0X\n", p->energy_cores); - outp += sprintf(outp, "Joules GFX: %0X\n", p->energy_gfx); - outp += sprintf(outp, "Joules RAM: %0X\n", p->energy_dram); - outp += sprintf(outp, "Throttle PKG: %0X\n", + outp += sprintf(outp, "Joules PKG: %0llX\n", p->energy_pkg); + outp += sprintf(outp, "Joules COR: %0llX\n", p->energy_cores); + outp += sprintf(outp, "Joules GFX: %0llX\n", p->energy_gfx); + outp += sprintf(outp, "Joules RAM: %0llX\n", p->energy_dram); + outp += sprintf(outp, "Throttle PKG: %0llX\n", p->rapl_pkg_perf_status); - outp += sprintf(outp, "Throttle RAM: %0X\n", + outp += sprintf(outp, "Throttle RAM: %0llX\n", p->rapl_dram_perf_status); outp += sprintf(outp, "PTM: %dC\n", p->pkg_temp_c); @@ -1062,14 +1176,7 @@ int format_counters(struct thread_data *t, struct core_data *c, } } - /* - * If measurement interval exceeds minimum RAPL Joule Counter range, - * indicate that results are suspect by printing "**" in fraction place. - */ - if (interval_float < rapl_joule_counter_range) - fmt8 = "%s%.2f"; - else - fmt8 = "%6.0f**"; + fmt8 = "%s%.2f"; if (DO_BIC(BIC_CorWatt) && (do_rapl & RAPL_PER_CORE_ENERGY)) outp += sprintf(outp, fmt8, (printed++ ? delim : ""), c->core_energy * rapl_energy_units / interval_float); @@ -1098,6 +1205,10 @@ int format_counters(struct thread_data *t, struct core_data *c, if (DO_BIC(BIC_GFXMHz)) outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->gfx_mhz); + /* GFXACTMHz */ + if (DO_BIC(BIC_GFXACTMHz)) + outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->gfx_act_mhz); + /* Totl%C0, Any%C0 GFX%C0 CPUGFX% */ if (DO_BIC(BIC_Totl_c0)) outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pkg_wtd_core_c0/tsc); @@ -1210,11 +1321,7 @@ void format_all_counters(struct thread_data *t, struct core_data *c, struct pkg_ } #define DELTA_WRAP32(new, old) \ - if (new > old) { \ - old = new - old; \ - } else { \ - old = 0x100000000 + new - old; \ - } + old = ((((unsigned long long)new << 32) - ((unsigned long long)old << 32)) >> 32); int delta_package(struct pkg_data *new, struct pkg_data *old) @@ -1253,13 +1360,14 @@ delta_package(struct pkg_data *new, struct pkg_data *old) old->gfx_rc6_ms = new->gfx_rc6_ms - old->gfx_rc6_ms; old->gfx_mhz = new->gfx_mhz; + old->gfx_act_mhz = new->gfx_act_mhz; - DELTA_WRAP32(new->energy_pkg, old->energy_pkg); - DELTA_WRAP32(new->energy_cores, old->energy_cores); - DELTA_WRAP32(new->energy_gfx, old->energy_gfx); - DELTA_WRAP32(new->energy_dram, old->energy_dram); - DELTA_WRAP32(new->rapl_pkg_perf_status, old->rapl_pkg_perf_status); - DELTA_WRAP32(new->rapl_dram_perf_status, old->rapl_dram_perf_status); + old->energy_pkg = new->energy_pkg - old->energy_pkg; + old->energy_cores = new->energy_cores - old->energy_cores; + old->energy_gfx = new->energy_gfx - old->energy_gfx; + old->energy_dram = new->energy_dram - old->energy_dram; + old->rapl_pkg_perf_status = new->rapl_pkg_perf_status - old->rapl_pkg_perf_status; + old->rapl_dram_perf_status = new->rapl_dram_perf_status - old->rapl_dram_perf_status; for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) { if (mp->format == FORMAT_RAW) @@ -1469,6 +1577,7 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data p->gfx_rc6_ms = 0; p->gfx_mhz = 0; + p->gfx_act_mhz = 0; for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) t->counter[i] = 0; @@ -1564,6 +1673,7 @@ int sum_counters(struct thread_data *t, struct core_data *c, average.packages.gfx_rc6_ms = p->gfx_rc6_ms; average.packages.gfx_mhz = p->gfx_mhz; + average.packages.gfx_act_mhz = p->gfx_act_mhz; average.packages.pkg_temp_c = MAX(average.packages.pkg_temp_c, p->pkg_temp_c); @@ -1784,7 +1894,7 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) int i; if (cpu_migrate(cpu)) { - fprintf(outf, "Could not migrate to CPU %d\n", cpu); + fprintf(outf, "get_counters: Could not migrate to CPU %d\n", cpu); return -1; } @@ -1966,39 +2076,39 @@ retry: p->sys_lpi = cpuidle_cur_sys_lpi_us; if (do_rapl & RAPL_PKG) { - if (get_msr(cpu, MSR_PKG_ENERGY_STATUS, &msr)) + if (get_msr_sum(cpu, MSR_PKG_ENERGY_STATUS, &msr)) return -13; - p->energy_pkg = msr & 0xFFFFFFFF; + p->energy_pkg = msr; } if (do_rapl & RAPL_CORES_ENERGY_STATUS) { - if (get_msr(cpu, MSR_PP0_ENERGY_STATUS, &msr)) + if (get_msr_sum(cpu, MSR_PP0_ENERGY_STATUS, &msr)) return -14; - p->energy_cores = msr & 0xFFFFFFFF; + p->energy_cores = msr; } if (do_rapl & RAPL_DRAM) { - if (get_msr(cpu, MSR_DRAM_ENERGY_STATUS, &msr)) + if (get_msr_sum(cpu, MSR_DRAM_ENERGY_STATUS, &msr)) return -15; - p->energy_dram = msr & 0xFFFFFFFF; + p->energy_dram = msr; } if (do_rapl & RAPL_GFX) { - if (get_msr(cpu, MSR_PP1_ENERGY_STATUS, &msr)) + if (get_msr_sum(cpu, MSR_PP1_ENERGY_STATUS, &msr)) return -16; - p->energy_gfx = msr & 0xFFFFFFFF; + p->energy_gfx = msr; } if (do_rapl & RAPL_PKG_PERF_STATUS) { - if (get_msr(cpu, MSR_PKG_PERF_STATUS, &msr)) + if (get_msr_sum(cpu, MSR_PKG_PERF_STATUS, &msr)) return -16; - p->rapl_pkg_perf_status = msr & 0xFFFFFFFF; + p->rapl_pkg_perf_status = msr; } if (do_rapl & RAPL_DRAM_PERF_STATUS) { - if (get_msr(cpu, MSR_DRAM_PERF_STATUS, &msr)) + if (get_msr_sum(cpu, MSR_DRAM_PERF_STATUS, &msr)) return -16; - p->rapl_dram_perf_status = msr & 0xFFFFFFFF; + p->rapl_dram_perf_status = msr; } if (do_rapl & RAPL_AMD_F17H) { - if (get_msr(cpu, MSR_PKG_ENERGY_STAT, &msr)) + if (get_msr_sum(cpu, MSR_PKG_ENERGY_STAT, &msr)) return -13; - p->energy_pkg = msr & 0xFFFFFFFF; + p->energy_pkg = msr; } if (DO_BIC(BIC_PkgTmp)) { if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_STATUS, &msr)) @@ -2012,6 +2122,9 @@ retry: if (DO_BIC(BIC_GFXMHz)) p->gfx_mhz = gfx_cur_mhz; + if (DO_BIC(BIC_GFXACTMHz)) + p->gfx_act_mhz = gfx_act_mhz; + for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) { if (get_mp(cpu, mp, &p->counter[i])) return -10; @@ -2173,6 +2286,7 @@ int has_turbo_ratio_group_limits(int family, int model) case INTEL_FAM6_ATOM_GOLDMONT: case INTEL_FAM6_SKYLAKE_X: case INTEL_FAM6_ATOM_GOLDMONT_D: + case INTEL_FAM6_ATOM_TREMONT_D: return 1; } return 0; @@ -2650,7 +2764,12 @@ int get_thread_siblings(struct cpu_topology *thiscpu) sprintf(path, "/sys/devices/system/cpu/cpu%d/topology/thread_siblings", cpu); - filep = fopen_or_die(path, "r"); + filep = fopen(path, "r"); + + if (!filep) { + warnx("%s: open failed", path); + return -1; + } do { offset -= BITMASK_SIZE; if (fscanf(filep, "%lx%c", &map, &character) != 2) @@ -2763,18 +2882,25 @@ void re_initialize(void) { free_all_buffers(); setup_all_buffers(); - printf("turbostat: re-initialized with num_cpus %d\n", topo.num_cpus); + fprintf(outf, "turbostat: re-initialized with num_cpus %d\n", topo.num_cpus); } void set_max_cpu_num(void) { FILE *filep; + int base_cpu; unsigned long dummy; + char pathname[64]; + + base_cpu = sched_getcpu(); + if (base_cpu < 0) + err(1, "cannot find calling cpu ID"); + sprintf(pathname, + "/sys/devices/system/cpu/cpu%d/topology/thread_siblings", + base_cpu); + filep = fopen_or_die(pathname, "r"); topo.max_cpu_num = 0; - filep = fopen_or_die( - "/sys/devices/system/cpu/cpu0/topology/thread_siblings", - "r"); while (fscanf(filep, "%lx,", &dummy) == 1) topo.max_cpu_num += BITMASK_SIZE; fclose(filep); @@ -2916,6 +3042,33 @@ int snapshot_gfx_mhz(void) } /* + * snapshot_gfx_cur_mhz() + * + * record snapshot of + * /sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz + * + * return 1 if config change requires a restart, else return 0 + */ +int snapshot_gfx_act_mhz(void) +{ + static FILE *fp; + int retval; + + if (fp == NULL) + fp = fopen_or_die("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", "r"); + else { + rewind(fp); + fflush(fp); + } + + retval = fscanf(fp, "%d", &gfx_act_mhz); + if (retval != 1) + err(1, "GFX ACT MHz"); + + return 0; +} + +/* * snapshot_cpu_lpi() * * record snapshot of @@ -2980,6 +3133,9 @@ int snapshot_proc_sysfs_files(void) if (DO_BIC(BIC_GFXMHz)) snapshot_gfx_mhz(); + if (DO_BIC(BIC_GFXACTMHz)) + snapshot_gfx_act_mhz(); + if (DO_BIC(BIC_CPU_LPI)) snapshot_cpu_lpi_us(); @@ -3057,6 +3213,111 @@ void do_sleep(void) } } +int get_msr_sum(int cpu, off_t offset, unsigned long long *msr) +{ + int ret, idx; + unsigned long long msr_cur, msr_last; + + if (!per_cpu_msr_sum) + return 1; + + idx = offset_to_idx(offset); + if (idx < 0) + return idx; + /* get_msr_sum() = sum + (get_msr() - last) */ + ret = get_msr(cpu, offset, &msr_cur); + if (ret) + return ret; + msr_last = per_cpu_msr_sum[cpu].entries[idx].last; + DELTA_WRAP32(msr_cur, msr_last); + *msr = msr_last + per_cpu_msr_sum[cpu].entries[idx].sum; + + return 0; +} + +timer_t timerid; + +/* Timer callback, update the sum of MSRs periodically. */ +static int update_msr_sum(struct thread_data *t, struct core_data *c, struct pkg_data *p) +{ + int i, ret; + int cpu = t->cpu_id; + + for (i = IDX_PKG_ENERGY; i < IDX_COUNT; i++) { + unsigned long long msr_cur, msr_last; + int offset; + + if (!idx_valid(i)) + continue; + offset = idx_to_offset(i); + if (offset < 0) + continue; + ret = get_msr(cpu, offset, &msr_cur); + if (ret) { + fprintf(outf, "Can not update msr(0x%x)\n", offset); + continue; + } + + msr_last = per_cpu_msr_sum[cpu].entries[i].last; + per_cpu_msr_sum[cpu].entries[i].last = msr_cur & 0xffffffff; + + DELTA_WRAP32(msr_cur, msr_last); + per_cpu_msr_sum[cpu].entries[i].sum += msr_last; + } + return 0; +} + +static void +msr_record_handler(union sigval v) +{ + for_all_cpus(update_msr_sum, EVEN_COUNTERS); +} + +void msr_sum_record(void) +{ + struct itimerspec its; + struct sigevent sev; + + per_cpu_msr_sum = calloc(topo.max_cpu_num + 1, sizeof(struct msr_sum_array)); + if (!per_cpu_msr_sum) { + fprintf(outf, "Can not allocate memory for long time MSR.\n"); + return; + } + /* + * Signal handler might be restricted, so use thread notifier instead. + */ + memset(&sev, 0, sizeof(struct sigevent)); + sev.sigev_notify = SIGEV_THREAD; + sev.sigev_notify_function = msr_record_handler; + + sev.sigev_value.sival_ptr = &timerid; + if (timer_create(CLOCK_REALTIME, &sev, &timerid) == -1) { + fprintf(outf, "Can not create timer.\n"); + goto release_msr; + } + + its.it_value.tv_sec = 0; + its.it_value.tv_nsec = 1; + /* + * A wraparound time has been calculated early. + * Some sources state that the peak power for a + * microprocessor is usually 1.5 times the TDP rating, + * use 2 * TDP for safety. + */ + its.it_interval.tv_sec = rapl_joule_counter_range / 2; + its.it_interval.tv_nsec = 0; + + if (timer_settime(timerid, 0, &its, NULL) == -1) { + fprintf(outf, "Can not set timer.\n"); + goto release_timer; + } + return; + + release_timer: + timer_delete(timerid); + release_msr: + free(per_cpu_msr_sum); +} void turbostat_loop() { @@ -3075,7 +3336,7 @@ restart: if (retval < -1) { exit(retval); } else if (retval == -1) { - if (restarted > 1) { + if (restarted > 10) { exit(retval); } re_initialize(); @@ -3279,6 +3540,7 @@ int probe_nhm_msrs(unsigned int family, unsigned int model) case INTEL_FAM6_ATOM_GOLDMONT_PLUS: case INTEL_FAM6_ATOM_GOLDMONT_D: /* DNV */ case INTEL_FAM6_ATOM_TREMONT: /* EHL */ + case INTEL_FAM6_ATOM_TREMONT_D: /* JVL */ pkg_cstate_limits = glm_pkg_cstate_limits; break; default: @@ -3361,6 +3623,17 @@ int is_ehl(unsigned int family, unsigned int model) } return 0; } +int is_jvl(unsigned int family, unsigned int model) +{ + if (!genuine_intel) + return 0; + + switch (model) { + case INTEL_FAM6_ATOM_TREMONT_D: + return 1; + } + return 0; +} int has_turbo_ratio_limit(unsigned int family, unsigned int model) { @@ -3475,6 +3748,20 @@ int has_config_tdp(unsigned int family, unsigned int model) } static void +remove_underbar(char *s) +{ + char *to = s; + + while (*s) { + if (*s != '_') + *to++ = *s; + s++; + } + + *to = 0; +} + +static void dump_cstate_pstate_config_info(unsigned int family, unsigned int model) { if (!do_nhm_platform_info) @@ -3530,9 +3817,6 @@ dump_sysfs_cstate_config(void) int state; char *sp; - if (!DO_BIC(BIC_sysfs)) - return; - if (access("/sys/devices/system/cpu/cpuidle", R_OK)) { fprintf(outf, "cpuidle not loaded\n"); return; @@ -3559,6 +3843,8 @@ dump_sysfs_cstate_config(void) *sp = '\0'; fclose(input); + remove_underbar(name_buf); + sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/desc", base_cpu, state); input = fopen(path, "r"); @@ -3645,7 +3931,7 @@ int print_epb(struct thread_data *t, struct core_data *c, struct pkg_data *p) return 0; if (cpu_migrate(cpu)) { - fprintf(outf, "Could not migrate to CPU %d\n", cpu); + fprintf(outf, "print_epb: Could not migrate to CPU %d\n", cpu); return -1; } @@ -3689,7 +3975,7 @@ int print_hwp(struct thread_data *t, struct core_data *c, struct pkg_data *p) return 0; if (cpu_migrate(cpu)) { - fprintf(outf, "Could not migrate to CPU %d\n", cpu); + fprintf(outf, "print_hwp: Could not migrate to CPU %d\n", cpu); return -1; } @@ -3777,7 +4063,7 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data return 0; if (cpu_migrate(cpu)) { - fprintf(outf, "Could not migrate to CPU %d\n", cpu); + fprintf(outf, "print_perf_limit: Could not migrate to CPU %d\n", cpu); return -1; } @@ -3881,13 +4167,8 @@ double get_tdp_intel(unsigned int model) double get_tdp_amd(unsigned int family) { - switch (family) { - case 0x17: - case 0x18: - default: - /* This is the max stock TDP of HEDT/Server Fam17h chips */ - return 250.0; - } + /* This is the max stock TDP of HEDT/Server Fam17h+ chips */ + return 280.0; } /* @@ -3959,6 +4240,14 @@ void rapl_probe_intel(unsigned int family, unsigned int model) BIC_PRESENT(BIC_GFXWatt); } break; + case INTEL_FAM6_ATOM_TREMONT_D: /* JVL */ + do_rapl = RAPL_PKG | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO; + BIC_PRESENT(BIC_PKG__); + if (rapl_joules) + BIC_PRESENT(BIC_Pkg_J); + else + BIC_PRESENT(BIC_PkgWatt); + break; case INTEL_FAM6_SKYLAKE_L: /* SKL */ case INTEL_FAM6_CANNONLAKE_L: /* CNL */ do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_GFX | RAPL_PKG_POWER_INFO; @@ -4069,27 +4358,20 @@ void rapl_probe_amd(unsigned int family, unsigned int model) if (max_extended_level >= 0x80000007) { __cpuid(0x80000007, eax, ebx, ecx, edx); - /* RAPL (Fam 17h) */ + /* RAPL (Fam 17h+) */ has_rapl = edx & (1 << 14); } - if (!has_rapl) + if (!has_rapl || family < 0x17) return; - switch (family) { - case 0x17: /* Zen, Zen+ */ - case 0x18: /* Hygon Dhyana */ - do_rapl = RAPL_AMD_F17H | RAPL_PER_CORE_ENERGY; - if (rapl_joules) { - BIC_PRESENT(BIC_Pkg_J); - BIC_PRESENT(BIC_Cor_J); - } else { - BIC_PRESENT(BIC_PkgWatt); - BIC_PRESENT(BIC_CorWatt); - } - break; - default: - return; + do_rapl = RAPL_AMD_F17H | RAPL_PER_CORE_ENERGY; + if (rapl_joules) { + BIC_PRESENT(BIC_Pkg_J); + BIC_PRESENT(BIC_Cor_J); + } else { + BIC_PRESENT(BIC_PkgWatt); + BIC_PRESENT(BIC_CorWatt); } if (get_msr(base_cpu, MSR_RAPL_PWR_UNIT, &msr)) @@ -4162,7 +4444,7 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p return 0; if (cpu_migrate(cpu)) { - fprintf(outf, "Could not migrate to CPU %d\n", cpu); + fprintf(outf, "print_thermal: Could not migrate to CPU %d\n", cpu); return -1; } @@ -4234,7 +4516,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p) cpu = t->cpu_id; if (cpu_migrate(cpu)) { - fprintf(outf, "Could not migrate to CPU %d\n", cpu); + fprintf(outf, "print_rapl: Could not migrate to CPU %d\n", cpu); return -1; } @@ -4361,6 +4643,7 @@ int has_snb_msrs(unsigned int family, unsigned int model) case INTEL_FAM6_ATOM_GOLDMONT_PLUS: case INTEL_FAM6_ATOM_GOLDMONT_D: /* DNV */ case INTEL_FAM6_ATOM_TREMONT: /* EHL */ + case INTEL_FAM6_ATOM_TREMONT_D: /* JVL */ return 1; } return 0; @@ -4507,12 +4790,33 @@ double discover_bclk(unsigned int family, unsigned int model) * below this value, including the Digital Thermal Sensor (DTS), * Package Thermal Management Sensor (PTM), and thermal event thresholds. */ -int set_temperature_target(struct thread_data *t, struct core_data *c, struct pkg_data *p) +int read_tcc_activation_temp() { unsigned long long msr; - unsigned int target_c_local; - int cpu; + unsigned int tcc, target_c, offset_c; + /* Temperature Target MSR is Nehalem and newer only */ + if (!do_nhm_platform_info) + return 0; + + if (get_msr(base_cpu, MSR_IA32_TEMPERATURE_TARGET, &msr)) + return 0; + + target_c = (msr >> 16) & 0xFF; + + offset_c = (msr >> 24) & 0xF; + + tcc = target_c - offset_c; + + if (!quiet) + fprintf(outf, "cpu%d: MSR_IA32_TEMPERATURE_TARGET: 0x%08llx (%d C) (%d default - %d offset)\n", + base_cpu, msr, tcc, target_c, offset_c); + + return tcc; +} + +int set_temperature_target(struct thread_data *t, struct core_data *c, struct pkg_data *p) +{ /* tcc_activation_temp is used only for dts or ptm */ if (!(do_dts || do_ptm)) return 0; @@ -4521,43 +4825,18 @@ int set_temperature_target(struct thread_data *t, struct core_data *c, struct pk if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE) || !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE)) return 0; - cpu = t->cpu_id; - if (cpu_migrate(cpu)) { - fprintf(outf, "Could not migrate to CPU %d\n", cpu); - return -1; - } - if (tcc_activation_temp_override != 0) { tcc_activation_temp = tcc_activation_temp_override; - fprintf(outf, "cpu%d: Using cmdline TCC Target (%d C)\n", - cpu, tcc_activation_temp); + fprintf(outf, "Using cmdline TCC Target (%d C)\n", tcc_activation_temp); return 0; } - /* Temperature Target MSR is Nehalem and newer only */ - if (!do_nhm_platform_info) - goto guess; - - if (get_msr(base_cpu, MSR_IA32_TEMPERATURE_TARGET, &msr)) - goto guess; - - target_c_local = (msr >> 16) & 0xFF; - - if (!quiet) - fprintf(outf, "cpu%d: MSR_IA32_TEMPERATURE_TARGET: 0x%08llx (%d C)\n", - cpu, msr, target_c_local); - - if (!target_c_local) - goto guess; - - tcc_activation_temp = target_c_local; - - return 0; + tcc_activation_temp = read_tcc_activation_temp(); + if (tcc_activation_temp) + return 0; -guess: tcc_activation_temp = TJMAX_DEFAULT; - fprintf(outf, "cpu%d: Guessing tjMax %d C, Please use -T to specify\n", - cpu, tcc_activation_temp); + fprintf(outf, "Guessing tjMax %d C, Please use -T to specify\n", tcc_activation_temp); return 0; } @@ -4685,19 +4964,46 @@ unsigned int intel_model_duplicates(unsigned int model) case INTEL_FAM6_ICELAKE_NNPI: case INTEL_FAM6_TIGERLAKE_L: case INTEL_FAM6_TIGERLAKE: + case INTEL_FAM6_ROCKETLAKE: + case INTEL_FAM6_LAKEFIELD: + case INTEL_FAM6_ALDERLAKE: return INTEL_FAM6_CANNONLAKE_L; - case INTEL_FAM6_ATOM_TREMONT_D: - return INTEL_FAM6_ATOM_GOLDMONT_D; - case INTEL_FAM6_ATOM_TREMONT_L: return INTEL_FAM6_ATOM_TREMONT; case INTEL_FAM6_ICELAKE_X: + case INTEL_FAM6_SAPPHIRERAPIDS_X: return INTEL_FAM6_SKYLAKE_X; } return model; } + +void print_dev_latency(void) +{ + char *path = "/dev/cpu_dma_latency"; + int fd; + int value; + int retval; + + fd = open(path, O_RDONLY); + if (fd < 0) { + warn("fopen %s\n", path); + return; + } + + retval = read(fd, (void *)&value, sizeof(int)); + if (retval != sizeof(int)) { + warn("read %s\n", path); + close(fd); + return; + } + fprintf(outf, "/dev/cpu_dma_latency: %d usec (%s)\n", + value, value == 2000000000 ? "default" : "constrained"); + + close(fd); +} + void process_cpuid() { unsigned int eax, ebx, ecx, edx; @@ -4916,6 +5222,14 @@ void process_cpuid() BIC_PRESENT(BIC_Mod_c6); use_c1_residency_msr = 1; } + if (is_jvl(family, model)) { + BIC_NOT_PRESENT(BIC_CPU_c3); + BIC_NOT_PRESENT(BIC_CPU_c7); + BIC_NOT_PRESENT(BIC_Pkgpc2); + BIC_NOT_PRESENT(BIC_Pkgpc3); + BIC_NOT_PRESENT(BIC_Pkgpc6); + BIC_NOT_PRESENT(BIC_Pkgpc7); + } if (is_dnv(family, model)) { BIC_PRESENT(BIC_CPU_c1); BIC_NOT_PRESENT(BIC_CPU_c3); @@ -4935,9 +5249,12 @@ void process_cpuid() BIC_NOT_PRESENT(BIC_Pkgpc7); } if (has_c8910_msrs(family, model)) { - BIC_PRESENT(BIC_Pkgpc8); - BIC_PRESENT(BIC_Pkgpc9); - BIC_PRESENT(BIC_Pkgpc10); + if (pkg_cstate_limit >= PCL__8) + BIC_PRESENT(BIC_Pkgpc8); + if (pkg_cstate_limit >= PCL__9) + BIC_PRESENT(BIC_Pkgpc9); + if (pkg_cstate_limit >= PCL_10) + BIC_PRESENT(BIC_Pkgpc10); } do_irtl_hsw = has_c8910_msrs(family, model); if (has_skl_msrs(family, model)) { @@ -4967,6 +5284,8 @@ void process_cpuid() dump_cstate_pstate_config_info(family, model); if (!quiet) + print_dev_latency(); + if (!quiet) dump_sysfs_cstate_config(); if (!quiet) dump_sysfs_pstate_config(); @@ -4980,6 +5299,9 @@ void process_cpuid() if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK)) BIC_PRESENT(BIC_GFXMHz); + if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", R_OK)) + BIC_PRESENT(BIC_GFXACTMHz); + if (!access("/sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us", R_OK)) BIC_PRESENT(BIC_CPU_LPI); else @@ -5390,7 +5712,7 @@ int get_and_dump_counters(void) } void print_version() { - fprintf(outf, "turbostat version 20.03.20" + fprintf(outf, "turbostat version 20.09.30" " - Len Brown <lenb@kernel.org>\n"); } @@ -5597,6 +5919,8 @@ void probe_sysfs(void) *sp = '%'; *(sp + 1) = '\0'; + remove_underbar(name_buf); + fclose(input); sprintf(path, "cpuidle/state%d/time", state); @@ -5624,6 +5948,8 @@ void probe_sysfs(void) *sp = '\0'; fclose(input); + remove_underbar(name_buf); + sprintf(path, "cpuidle/state%d/usage", state); if (is_deferred_skip(name_buf)) @@ -5868,6 +6194,7 @@ int main(int argc, char **argv) return 0; } + msr_sum_record(); /* * if any params left, it must be a command to fork */ diff --git a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c index 3fe1eed900d4..ff6c6661f075 100644 --- a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c +++ b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c @@ -622,6 +622,57 @@ void cmdline(int argc, char **argv) } } +/* + * Open a file, and exit on failure + */ +FILE *fopen_or_die(const char *path, const char *mode) +{ + FILE *filep = fopen(path, "r"); + + if (!filep) + err(1, "%s: open failed", path); + return filep; +} + +void err_on_hypervisor(void) +{ + FILE *cpuinfo; + char *flags, *hypervisor; + char *buffer; + + /* On VMs /proc/cpuinfo contains a "flags" entry for hypervisor */ + cpuinfo = fopen_or_die("/proc/cpuinfo", "ro"); + + buffer = malloc(4096); + if (!buffer) { + fclose(cpuinfo); + err(-ENOMEM, "buffer malloc fail"); + } + + if (!fread(buffer, 1024, 1, cpuinfo)) { + fclose(cpuinfo); + free(buffer); + err(1, "Reading /proc/cpuinfo failed"); + } + + flags = strstr(buffer, "flags"); + rewind(cpuinfo); + fseek(cpuinfo, flags - buffer, SEEK_SET); + if (!fgets(buffer, 4096, cpuinfo)) { + fclose(cpuinfo); + free(buffer); + err(1, "Reading /proc/cpuinfo failed"); + } + fclose(cpuinfo); + + hypervisor = strstr(buffer, "hypervisor"); + + free(buffer); + + if (hypervisor) + err(-1, + "not supported on this virtual machine"); +} int get_msr(int cpu, int offset, unsigned long long *msr) { @@ -635,8 +686,10 @@ int get_msr(int cpu, int offset, unsigned long long *msr) err(-1, "%s open failed, try chown or chmod +r /dev/cpu/*/msr, or run as root", pathname); retval = pread(fd, msr, sizeof(*msr), offset); - if (retval != sizeof(*msr)) + if (retval != sizeof(*msr)) { + err_on_hypervisor(); err(-1, "%s offset 0x%llx read failed", pathname, (unsigned long long)offset); + } if (debug > 1) fprintf(stderr, "get_msr(cpu%d, 0x%X, 0x%llX)\n", cpu, offset, *msr); @@ -1086,18 +1139,6 @@ int update_cpu_msrs(int cpu) return 0; } -/* - * Open a file, and exit on failure - */ -FILE *fopen_or_die(const char *path, const char *mode) -{ - FILE *filep = fopen(path, "r"); - - if (!filep) - err(1, "%s: open failed", path); - return filep; -} - unsigned int get_pkg_num(int cpu) { FILE *fp; diff --git a/tools/testing/kunit/.gitattributes b/tools/testing/kunit/.gitattributes deleted file mode 100644 index 5b7da1fc3b8f..000000000000 --- a/tools/testing/kunit/.gitattributes +++ /dev/null @@ -1 +0,0 @@ -test_data/* binary diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py index ebf5f5763dee..d4f7846d0745 100755 --- a/tools/testing/kunit/kunit.py +++ b/tools/testing/kunit/kunit.py @@ -11,7 +11,6 @@ import argparse import sys import os import time -import shutil from collections import namedtuple from enum import Enum, auto @@ -44,11 +43,6 @@ class KunitStatus(Enum): BUILD_FAILURE = auto() TEST_FAILURE = auto() -def create_default_kunitconfig(): - if not os.path.exists(kunit_kernel.kunitconfig_path): - shutil.copyfile('arch/um/configs/kunit_defconfig', - kunit_kernel.kunitconfig_path) - def get_kernel_root_path(): parts = sys.argv[0] if not __file__ else __file__ parts = os.path.realpath(parts).split('tools/testing/kunit') @@ -61,7 +55,6 @@ def config_tests(linux: kunit_kernel.LinuxSourceTree, kunit_parser.print_with_timestamp('Configuring KUnit Kernel ...') config_start = time.time() - create_default_kunitconfig() success = linux.build_reconfig(request.build_dir, request.make_options) config_end = time.time() if not success: @@ -262,12 +255,12 @@ def main(argv, linux=None): if not os.path.exists(cli_args.build_dir): os.mkdir(cli_args.build_dir) - if not os.path.exists(kunit_kernel.kunitconfig_path): - create_default_kunitconfig() - if not linux: linux = kunit_kernel.LinuxSourceTree() + linux.create_kunitconfig(cli_args.build_dir) + linux.read_kunitconfig(cli_args.build_dir) + request = KunitRequest(cli_args.raw_output, cli_args.timeout, cli_args.jobs, @@ -283,12 +276,12 @@ def main(argv, linux=None): not os.path.exists(cli_args.build_dir)): os.mkdir(cli_args.build_dir) - if not os.path.exists(kunit_kernel.kunitconfig_path): - create_default_kunitconfig() - if not linux: linux = kunit_kernel.LinuxSourceTree() + linux.create_kunitconfig(cli_args.build_dir) + linux.read_kunitconfig(cli_args.build_dir) + request = KunitConfigRequest(cli_args.build_dir, cli_args.make_options) result = config_tests(linux, request) @@ -301,6 +294,9 @@ def main(argv, linux=None): if not linux: linux = kunit_kernel.LinuxSourceTree() + linux.create_kunitconfig(cli_args.build_dir) + linux.read_kunitconfig(cli_args.build_dir) + request = KunitBuildRequest(cli_args.jobs, cli_args.build_dir, cli_args.alltests, @@ -315,6 +311,9 @@ def main(argv, linux=None): if not linux: linux = kunit_kernel.LinuxSourceTree() + linux.create_kunitconfig(cli_args.build_dir) + linux.read_kunitconfig(cli_args.build_dir) + exec_request = KunitExecRequest(cli_args.timeout, cli_args.build_dir, cli_args.alltests) @@ -337,7 +336,7 @@ def main(argv, linux=None): kunit_output = f.read().splitlines() request = KunitParseRequest(cli_args.raw_output, kunit_output, - cli_args.build_dir, + None, cli_args.json) result = parse_tests(request) if result.status != KunitStatus.SUCCESS: diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py index b557b1e93f98..2e3cc0fac726 100644 --- a/tools/testing/kunit/kunit_kernel.py +++ b/tools/testing/kunit/kunit_kernel.py @@ -6,10 +6,10 @@ # Author: Felix Guo <felixguoxiuping@gmail.com> # Author: Brendan Higgins <brendanhiggins@google.com> - import logging import subprocess import os +import shutil import signal from contextlib import ExitStack @@ -18,8 +18,10 @@ import kunit_config import kunit_parser KCONFIG_PATH = '.config' -kunitconfig_path = '.kunitconfig' +KUNITCONFIG_PATH = '.kunitconfig' +DEFAULT_KUNITCONFIG_PATH = 'arch/um/configs/kunit_defconfig' BROKEN_ALLCONFIG_PATH = 'tools/testing/kunit/configs/broken_on_uml.config' +OUTFILE_PATH = 'test.log' class ConfigError(Exception): """Represents an error trying to configure the Linux kernel.""" @@ -82,36 +84,51 @@ class LinuxSourceTreeOperations(object): if build_dir: command += ['O=' + build_dir] try: - subprocess.check_output(command, stderr=subprocess.STDOUT) + proc = subprocess.Popen(command, + stderr=subprocess.PIPE, + stdout=subprocess.DEVNULL) except OSError as e: - raise BuildError('Could not call execute make: ' + str(e)) - except subprocess.CalledProcessError as e: - raise BuildError(e.output.decode()) - - def linux_bin(self, params, timeout, build_dir, outfile): + raise BuildError('Could not call make command: ' + str(e)) + _, stderr = proc.communicate() + if proc.returncode != 0: + raise BuildError(stderr.decode()) + if stderr: # likely only due to build warnings + print(stderr.decode()) + + def linux_bin(self, params, timeout, build_dir): """Runs the Linux UML binary. Must be named 'linux'.""" linux_bin = './linux' if build_dir: linux_bin = os.path.join(build_dir, 'linux') + outfile = get_outfile_path(build_dir) with open(outfile, 'w') as output: process = subprocess.Popen([linux_bin] + params, stdout=output, stderr=subprocess.STDOUT) process.wait(timeout) - def get_kconfig_path(build_dir): kconfig_path = KCONFIG_PATH if build_dir: kconfig_path = os.path.join(build_dir, KCONFIG_PATH) return kconfig_path +def get_kunitconfig_path(build_dir): + kunitconfig_path = KUNITCONFIG_PATH + if build_dir: + kunitconfig_path = os.path.join(build_dir, KUNITCONFIG_PATH) + return kunitconfig_path + +def get_outfile_path(build_dir): + outfile_path = OUTFILE_PATH + if build_dir: + outfile_path = os.path.join(build_dir, OUTFILE_PATH) + return outfile_path + class LinuxSourceTree(object): """Represents a Linux kernel source tree with KUnit tests.""" def __init__(self): - self._kconfig = kunit_config.Kconfig() - self._kconfig.read_from_file(kunitconfig_path) self._ops = LinuxSourceTreeOperations() signal.signal(signal.SIGINT, self.signal_handler) @@ -123,6 +140,16 @@ class LinuxSourceTree(object): return False return True + def create_kunitconfig(self, build_dir, defconfig=DEFAULT_KUNITCONFIG_PATH): + kunitconfig_path = get_kunitconfig_path(build_dir) + if not os.path.exists(kunitconfig_path): + shutil.copyfile(defconfig, kunitconfig_path) + + def read_kunitconfig(self, build_dir): + kunitconfig_path = get_kunitconfig_path(build_dir) + self._kconfig = kunit_config.Kconfig() + self._kconfig.read_from_file(kunitconfig_path) + def validate_config(self, build_dir): kconfig_path = get_kconfig_path(build_dir) validated_kconfig = kunit_config.Kconfig() @@ -178,8 +205,8 @@ class LinuxSourceTree(object): def run_kernel(self, args=[], build_dir='', timeout=None): args.extend(['mem=1G']) - outfile = 'test.log' - self._ops.linux_bin(args, timeout, build_dir, outfile) + self._ops.linux_bin(args, timeout, build_dir) + outfile = get_outfile_path(build_dir) subprocess.call(['stty', 'sane']) with open(outfile, 'r') as file: for line in file: diff --git a/tools/testing/kunit/kunit_parser.py b/tools/testing/kunit/kunit_parser.py index 8019e3dd4c32..bbfe1b4e4c1c 100644 --- a/tools/testing/kunit/kunit_parser.py +++ b/tools/testing/kunit/kunit_parser.py @@ -12,7 +12,7 @@ from collections import namedtuple from datetime import datetime from enum import Enum, auto from functools import reduce -from typing import List +from typing import List, Optional, Tuple TestResult = namedtuple('TestResult', ['status','suites','log']) @@ -54,6 +54,7 @@ kunit_end_re = re.compile('(List of all partitions:|' def isolate_kunit_output(kernel_output): started = False for line in kernel_output: + line = line.rstrip() # line always has a trailing \n if kunit_start_re.search(line): prefix_len = len(line.split('TAP version')[0]) started = True @@ -65,8 +66,7 @@ def isolate_kunit_output(kernel_output): def raw_output(kernel_output): for line in kernel_output: - print(line) - yield line + print(line.rstrip()) DIVIDER = '=' * 60 @@ -152,7 +152,7 @@ def parse_diagnostic(lines: List[str], test_case: TestCase) -> bool: else: return False -def parse_test_case(lines: List[str]) -> TestCase: +def parse_test_case(lines: List[str]) -> Optional[TestCase]: test_case = TestCase() save_non_diagnositic(lines, test_case) while parse_diagnostic(lines, test_case): @@ -164,7 +164,7 @@ def parse_test_case(lines: List[str]) -> TestCase: SUBTEST_HEADER = re.compile(r'^[\s]+# Subtest: (.*)$') -def parse_subtest_header(lines: List[str]) -> str: +def parse_subtest_header(lines: List[str]) -> Optional[str]: consume_non_diagnositic(lines) if not lines: return None @@ -177,7 +177,7 @@ def parse_subtest_header(lines: List[str]) -> str: SUBTEST_PLAN = re.compile(r'[\s]+[0-9]+\.\.([0-9]+)') -def parse_subtest_plan(lines: List[str]) -> int: +def parse_subtest_plan(lines: List[str]) -> Optional[int]: consume_non_diagnositic(lines) match = SUBTEST_PLAN.match(lines[0]) if match: @@ -231,7 +231,7 @@ def bubble_up_test_case_errors(test_suite: TestSuite) -> TestStatus: max_test_case_status = bubble_up_errors(lambda x: x.status, test_suite.cases) return max_status(max_test_case_status, test_suite.status) -def parse_test_suite(lines: List[str], expected_suite_index: int) -> TestSuite: +def parse_test_suite(lines: List[str], expected_suite_index: int) -> Optional[TestSuite]: if not lines: return None consume_non_diagnositic(lines) @@ -242,7 +242,7 @@ def parse_test_suite(lines: List[str], expected_suite_index: int) -> TestSuite: return None test_suite.name = name expected_test_case_num = parse_subtest_plan(lines) - if not expected_test_case_num: + if expected_test_case_num is None: return None while expected_test_case_num > 0: test_case = parse_test_case(lines) @@ -272,7 +272,7 @@ def parse_tap_header(lines: List[str]) -> bool: TEST_PLAN = re.compile(r'[0-9]+\.\.([0-9]+)') -def parse_test_plan(lines: List[str]) -> int: +def parse_test_plan(lines: List[str]) -> Optional[int]: consume_non_diagnositic(lines) match = TEST_PLAN.match(lines[0]) if match: @@ -311,7 +311,7 @@ def parse_test_result(lines: List[str]) -> TestResult: else: return TestResult(TestStatus.NO_TESTS, [], lines) -def print_and_count_results(test_result: TestResult) -> None: +def print_and_count_results(test_result: TestResult) -> Tuple[int, int, int]: total_tests = 0 failed_tests = 0 crashed_tests = 0 diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py index 99c3c5671ea4..497ab51bc170 100755 --- a/tools/testing/kunit/kunit_tool_test.py +++ b/tools/testing/kunit/kunit_tool_test.py @@ -102,7 +102,7 @@ class KUnitParserTest(unittest.TestCase): 'test_data/test_output_isolated_correctly.log') file = open(log_path) result = kunit_parser.isolate_kunit_output(file.readlines()) - self.assertContains('TAP version 14\n', result) + self.assertContains('TAP version 14', result) self.assertContains(' # Subtest: example', result) self.assertContains(' 1..2', result) self.assertContains(' ok 1 - example_simple_test', result) @@ -115,7 +115,7 @@ class KUnitParserTest(unittest.TestCase): 'test_data/test_pound_sign.log') with open(log_path) as file: result = kunit_parser.isolate_kunit_output(file.readlines()) - self.assertContains('TAP version 14\n', result) + self.assertContains('TAP version 14', result) self.assertContains(' # Subtest: kunit-resource-test', result) self.assertContains(' 1..5', result) self.assertContains(' ok 1 - kunit_resource_test_init_resources', result) @@ -179,7 +179,7 @@ class KUnitParserTest(unittest.TestCase): print_mock = mock.patch('builtins.print').start() result = kunit_parser.parse_run_tests( kunit_parser.isolate_kunit_output(file.readlines())) - print_mock.assert_any_call(StrContains("no kunit output detected")) + print_mock.assert_any_call(StrContains('no tests run!')) print_mock.stop() file.close() @@ -198,39 +198,57 @@ class KUnitParserTest(unittest.TestCase): 'test_data/test_config_printk_time.log') with open(prefix_log) as file: result = kunit_parser.parse_run_tests(file.readlines()) - self.assertEqual('kunit-resource-test', result.suites[0].name) + self.assertEqual( + kunit_parser.TestStatus.SUCCESS, + result.status) + self.assertEqual('kunit-resource-test', result.suites[0].name) def test_ignores_multiple_prefixes(self): prefix_log = get_absolute_path( 'test_data/test_multiple_prefixes.log') with open(prefix_log) as file: result = kunit_parser.parse_run_tests(file.readlines()) - self.assertEqual('kunit-resource-test', result.suites[0].name) + self.assertEqual( + kunit_parser.TestStatus.SUCCESS, + result.status) + self.assertEqual('kunit-resource-test', result.suites[0].name) def test_prefix_mixed_kernel_output(self): mixed_prefix_log = get_absolute_path( 'test_data/test_interrupted_tap_output.log') with open(mixed_prefix_log) as file: result = kunit_parser.parse_run_tests(file.readlines()) - self.assertEqual('kunit-resource-test', result.suites[0].name) + self.assertEqual( + kunit_parser.TestStatus.SUCCESS, + result.status) + self.assertEqual('kunit-resource-test', result.suites[0].name) def test_prefix_poundsign(self): pound_log = get_absolute_path('test_data/test_pound_sign.log') with open(pound_log) as file: result = kunit_parser.parse_run_tests(file.readlines()) - self.assertEqual('kunit-resource-test', result.suites[0].name) + self.assertEqual( + kunit_parser.TestStatus.SUCCESS, + result.status) + self.assertEqual('kunit-resource-test', result.suites[0].name) def test_kernel_panic_end(self): panic_log = get_absolute_path('test_data/test_kernel_panic_interrupt.log') with open(panic_log) as file: result = kunit_parser.parse_run_tests(file.readlines()) - self.assertEqual('kunit-resource-test', result.suites[0].name) + self.assertEqual( + kunit_parser.TestStatus.TEST_CRASHED, + result.status) + self.assertEqual('kunit-resource-test', result.suites[0].name) def test_pound_no_prefix(self): pound_log = get_absolute_path('test_data/test_pound_no_prefix.log') with open(pound_log) as file: result = kunit_parser.parse_run_tests(file.readlines()) - self.assertEqual('kunit-resource-test', result.suites[0].name) + self.assertEqual( + kunit_parser.TestStatus.SUCCESS, + result.status) + self.assertEqual('kunit-resource-test', result.suites[0].name) class KUnitJsonTest(unittest.TestCase): diff --git a/tools/testing/kunit/test_data/test_config_printk_time.log b/tools/testing/kunit/test_data/test_config_printk_time.log index c02ca773946d..6bdb57f76eac 100644 --- a/tools/testing/kunit/test_data/test_config_printk_time.log +++ b/tools/testing/kunit/test_data/test_config_printk_time.log @@ -1,6 +1,7 @@ [ 0.060000] printk: console [mc-1] enabled [ 0.060000] random: get_random_bytes called from init_oops_id+0x35/0x40 with crng_init=0 [ 0.060000] TAP version 14 +[ 0.060000] 1..3 [ 0.060000] # Subtest: kunit-resource-test [ 0.060000] 1..5 [ 0.060000] ok 1 - kunit_resource_test_init_resources @@ -28,4 +29,4 @@ [ 0.060000] Stack: [ 0.060000] 602086f8 601bc260 705c0000 705c0000 [ 0.060000] 602086f8 6005fcec 705c0000 6002c6ab -[ 0.060000] 6005fcec 601bc260 705c0000 3000000010
\ No newline at end of file +[ 0.060000] 6005fcec 601bc260 705c0000 3000000010 diff --git a/tools/testing/kunit/test_data/test_interrupted_tap_output.log b/tools/testing/kunit/test_data/test_interrupted_tap_output.log index 5c73fb3a1c6f..1fb677728abe 100644 --- a/tools/testing/kunit/test_data/test_interrupted_tap_output.log +++ b/tools/testing/kunit/test_data/test_interrupted_tap_output.log @@ -1,6 +1,7 @@ [ 0.060000] printk: console [mc-1] enabled [ 0.060000] random: get_random_bytes called from init_oops_id+0x35/0x40 with crng_init=0 [ 0.060000] TAP version 14 +[ 0.060000] 1..3 [ 0.060000] # Subtest: kunit-resource-test [ 0.060000] 1..5 [ 0.060000] ok 1 - kunit_resource_test_init_resources @@ -34,4 +35,4 @@ [ 0.060000] Stack: [ 0.060000] 602086f8 601bc260 705c0000 705c0000 [ 0.060000] 602086f8 6005fcec 705c0000 6002c6ab -[ 0.060000] 6005fcec 601bc260 705c0000 3000000010
\ No newline at end of file +[ 0.060000] 6005fcec 601bc260 705c0000 3000000010 diff --git a/tools/testing/kunit/test_data/test_kernel_panic_interrupt.log b/tools/testing/kunit/test_data/test_kernel_panic_interrupt.log index c045eee75f27..a014ffe9725e 100644 --- a/tools/testing/kunit/test_data/test_kernel_panic_interrupt.log +++ b/tools/testing/kunit/test_data/test_kernel_panic_interrupt.log @@ -1,6 +1,7 @@ [ 0.060000] printk: console [mc-1] enabled [ 0.060000] random: get_random_bytes called from init_oops_id+0x35/0x40 with crng_init=0 [ 0.060000] TAP version 14 +[ 0.060000] 1..3 [ 0.060000] # Subtest: kunit-resource-test [ 0.060000] 1..5 [ 0.060000] ok 1 - kunit_resource_test_init_resources @@ -22,4 +23,4 @@ [ 0.060000] Stack: [ 0.060000] 602086f8 601bc260 705c0000 705c0000 [ 0.060000] 602086f8 6005fcec 705c0000 6002c6ab -[ 0.060000] 6005fcec 601bc260 705c0000 3000000010
\ No newline at end of file +[ 0.060000] 6005fcec 601bc260 705c0000 3000000010 diff --git a/tools/testing/kunit/test_data/test_multiple_prefixes.log b/tools/testing/kunit/test_data/test_multiple_prefixes.log index bc48407dcc36..0ad78481a0b4 100644 --- a/tools/testing/kunit/test_data/test_multiple_prefixes.log +++ b/tools/testing/kunit/test_data/test_multiple_prefixes.log @@ -1,6 +1,7 @@ [ 0.060000][ T1] printk: console [mc-1] enabled [ 0.060000][ T1] random: get_random_bytes called from init_oops_id+0x35/0x40 with crng_init=0 [ 0.060000][ T1] TAP version 14 +[ 0.060000][ T1] 1..3 [ 0.060000][ T1] # Subtest: kunit-resource-test [ 0.060000][ T1] 1..5 [ 0.060000][ T1] ok 1 - kunit_resource_test_init_resources @@ -28,4 +29,4 @@ [ 0.060000][ T1] Stack: [ 0.060000][ T1] 602086f8 601bc260 705c0000 705c0000 [ 0.060000][ T1] 602086f8 6005fcec 705c0000 6002c6ab -[ 0.060000][ T1] 6005fcec 601bc260 705c0000 3000000010
\ No newline at end of file +[ 0.060000][ T1] 6005fcec 601bc260 705c0000 3000000010 diff --git a/tools/testing/kunit/test_data/test_pound_no_prefix.log b/tools/testing/kunit/test_data/test_pound_no_prefix.log index 2ceb360be7d5..dc4cf09a96d0 100644 --- a/tools/testing/kunit/test_data/test_pound_no_prefix.log +++ b/tools/testing/kunit/test_data/test_pound_no_prefix.log @@ -1,6 +1,7 @@ printk: console [mc-1] enabled random: get_random_bytes called from init_oops_id+0x35/0x40 with crng_init=0 TAP version 14 + 1..3 # Subtest: kunit-resource-test 1..5 ok 1 - kunit_resource_test_init_resources @@ -30,4 +31,4 @@ Stack: 602086f8 601bc260 705c0000 705c0000 602086f8 6005fcec 705c0000 6002c6ab - 6005fcec 601bc260 705c0000 3000000010
\ No newline at end of file + 6005fcec 601bc260 705c0000 3000000010 diff --git a/tools/testing/kunit/test_data/test_pound_sign.log b/tools/testing/kunit/test_data/test_pound_sign.log index 28ffa5ba03bf..3f358e3a7ba0 100644 --- a/tools/testing/kunit/test_data/test_pound_sign.log +++ b/tools/testing/kunit/test_data/test_pound_sign.log @@ -1,6 +1,7 @@ [ 0.060000] printk: console [mc-1] enabled [ 0.060000] random: get_random_bytes called from init_oops_id+0x35/0x40 with crng_init=0 [ 0.060000] TAP version 14 +[ 0.060000] 1..3 [ 0.060000] # Subtest: kunit-resource-test [ 0.060000] 1..5 [ 0.060000] ok 1 - kunit_resource_test_init_resources diff --git a/tools/testing/scatterlist/linux/mm.h b/tools/testing/scatterlist/linux/mm.h index 6ae907f375d2..f9a12005fcea 100644 --- a/tools/testing/scatterlist/linux/mm.h +++ b/tools/testing/scatterlist/linux/mm.h @@ -33,6 +33,7 @@ typedef unsigned long dma_addr_t; #define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1) #define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask)) #define ALIGN(x, a) __ALIGN_KERNEL((x), (a)) +#define ALIGN_DOWN(x, a) __ALIGN_KERNEL((x) - ((a) - 1), (a)) #define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE) diff --git a/tools/testing/scatterlist/main.c b/tools/testing/scatterlist/main.c index b2c7e9f7b8d3..f561aed7c657 100644 --- a/tools/testing/scatterlist/main.c +++ b/tools/testing/scatterlist/main.c @@ -52,9 +52,9 @@ int main(void) { const unsigned int sgmax = SCATTERLIST_MAX_SEGMENT; struct test *test, tests[] = { - { -EINVAL, 1, pfn(0), PAGE_SIZE, PAGE_SIZE + 1, 1 }, { -EINVAL, 1, pfn(0), PAGE_SIZE, 0, 1 }, - { -EINVAL, 1, pfn(0), PAGE_SIZE, sgmax + 1, 1 }, + { 0, 1, pfn(0), PAGE_SIZE, PAGE_SIZE + 1, 1 }, + { 0, 1, pfn(0), PAGE_SIZE, sgmax + 1, 1 }, { 0, 1, pfn(0), PAGE_SIZE, sgmax, 1 }, { 0, 1, pfn(0), 1, sgmax, 1 }, { 0, 2, pfn(0, 1), 2 * PAGE_SIZE, sgmax, 1 }, diff --git a/tools/testing/selftests/bpf/prog_tests/map_init.c b/tools/testing/selftests/bpf/prog_tests/map_init.c new file mode 100644 index 000000000000..14a31109dd0e --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/map_init.c @@ -0,0 +1,214 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2020 Tessares SA <http://www.tessares.net> */ + +#include <test_progs.h> +#include "test_map_init.skel.h" + +#define TEST_VALUE 0x1234 +#define FILL_VALUE 0xdeadbeef + +static int nr_cpus; +static int duration; + +typedef unsigned long long map_key_t; +typedef unsigned long long map_value_t; +typedef struct { + map_value_t v; /* padding */ +} __bpf_percpu_val_align pcpu_map_value_t; + + +static int map_populate(int map_fd, int num) +{ + pcpu_map_value_t value[nr_cpus]; + int i, err; + map_key_t key; + + for (i = 0; i < nr_cpus; i++) + bpf_percpu(value, i) = FILL_VALUE; + + for (key = 1; key <= num; key++) { + err = bpf_map_update_elem(map_fd, &key, value, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem")) + return -1; + } + + return 0; +} + +static struct test_map_init *setup(enum bpf_map_type map_type, int map_sz, + int *map_fd, int populate) +{ + struct test_map_init *skel; + int err; + + skel = test_map_init__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + return NULL; + + err = bpf_map__set_type(skel->maps.hashmap1, map_type); + if (!ASSERT_OK(err, "bpf_map__set_type")) + goto error; + + err = bpf_map__set_max_entries(skel->maps.hashmap1, map_sz); + if (!ASSERT_OK(err, "bpf_map__set_max_entries")) + goto error; + + err = test_map_init__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto error; + + *map_fd = bpf_map__fd(skel->maps.hashmap1); + if (CHECK(*map_fd < 0, "bpf_map__fd", "failed\n")) + goto error; + + err = map_populate(*map_fd, populate); + if (!ASSERT_OK(err, "map_populate")) + goto error_map; + + return skel; + +error_map: + close(*map_fd); +error: + test_map_init__destroy(skel); + return NULL; +} + +/* executes bpf program that updates map with key, value */ +static int prog_run_insert_elem(struct test_map_init *skel, map_key_t key, + map_value_t value) +{ + struct test_map_init__bss *bss; + + bss = skel->bss; + + bss->inKey = key; + bss->inValue = value; + bss->inPid = getpid(); + + if (!ASSERT_OK(test_map_init__attach(skel), "skel_attach")) + return -1; + + /* Let tracepoint trigger */ + syscall(__NR_getpgid); + + test_map_init__detach(skel); + + return 0; +} + +static int check_values_one_cpu(pcpu_map_value_t *value, map_value_t expected) +{ + int i, nzCnt = 0; + map_value_t val; + + for (i = 0; i < nr_cpus; i++) { + val = bpf_percpu(value, i); + if (val) { + if (CHECK(val != expected, "map value", + "unexpected for cpu %d: 0x%llx\n", i, val)) + return -1; + nzCnt++; + } + } + + if (CHECK(nzCnt != 1, "map value", "set for %d CPUs instead of 1!\n", + nzCnt)) + return -1; + + return 0; +} + +/* Add key=1 elem with values set for all CPUs + * Delete elem key=1 + * Run bpf prog that inserts new key=1 elem with value=0x1234 + * (bpf prog can only set value for current CPU) + * Lookup Key=1 and check value is as expected for all CPUs: + * value set by bpf prog for one CPU, 0 for all others + */ +static void test_pcpu_map_init(void) +{ + pcpu_map_value_t value[nr_cpus]; + struct test_map_init *skel; + int map_fd, err; + map_key_t key; + + /* max 1 elem in map so insertion is forced to reuse freed entry */ + skel = setup(BPF_MAP_TYPE_PERCPU_HASH, 1, &map_fd, 1); + if (!ASSERT_OK_PTR(skel, "prog_setup")) + return; + + /* delete element so the entry can be re-used*/ + key = 1; + err = bpf_map_delete_elem(map_fd, &key); + if (!ASSERT_OK(err, "bpf_map_delete_elem")) + goto cleanup; + + /* run bpf prog that inserts new elem, re-using the slot just freed */ + err = prog_run_insert_elem(skel, key, TEST_VALUE); + if (!ASSERT_OK(err, "prog_run_insert_elem")) + goto cleanup; + + /* check that key=1 was re-created by bpf prog */ + err = bpf_map_lookup_elem(map_fd, &key, value); + if (!ASSERT_OK(err, "bpf_map_lookup_elem")) + goto cleanup; + + /* and has expected values */ + check_values_one_cpu(value, TEST_VALUE); + +cleanup: + test_map_init__destroy(skel); +} + +/* Add key=1 and key=2 elems with values set for all CPUs + * Run bpf prog that inserts new key=3 elem + * (only for current cpu; other cpus should have initial value = 0) + * Lookup Key=1 and check value is as expected for all CPUs + */ +static void test_pcpu_lru_map_init(void) +{ + pcpu_map_value_t value[nr_cpus]; + struct test_map_init *skel; + int map_fd, err; + map_key_t key; + + /* Set up LRU map with 2 elements, values filled for all CPUs. + * With these 2 elements, the LRU map is full + */ + skel = setup(BPF_MAP_TYPE_LRU_PERCPU_HASH, 2, &map_fd, 2); + if (!ASSERT_OK_PTR(skel, "prog_setup")) + return; + + /* run bpf prog that inserts new key=3 element, re-using LRU slot */ + key = 3; + err = prog_run_insert_elem(skel, key, TEST_VALUE); + if (!ASSERT_OK(err, "prog_run_insert_elem")) + goto cleanup; + + /* check that key=3 replaced one of earlier elements */ + err = bpf_map_lookup_elem(map_fd, &key, value); + if (!ASSERT_OK(err, "bpf_map_lookup_elem")) + goto cleanup; + + /* and has expected values */ + check_values_one_cpu(value, TEST_VALUE); + +cleanup: + test_map_init__destroy(skel); +} + +void test_map_init(void) +{ + nr_cpus = bpf_num_possible_cpus(); + if (nr_cpus <= 1) { + printf("%s:SKIP: >1 cpu needed for this test\n", __func__); + test__skip(); + return; + } + + if (test__start_subtest("pcpu_map_init")) + test_pcpu_map_init(); + if (test__start_subtest("pcpu_lru_map_init")) + test_pcpu_lru_map_init(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/probe_read_user_str.c b/tools/testing/selftests/bpf/prog_tests/probe_read_user_str.c new file mode 100644 index 000000000000..e419298132b5 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/probe_read_user_str.c @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include "test_probe_read_user_str.skel.h" + +static const char str1[] = "mestring"; +static const char str2[] = "mestringalittlebigger"; +static const char str3[] = "mestringblubblubblubblubblub"; + +static int test_one_str(struct test_probe_read_user_str *skel, const char *str, + size_t len) +{ + int err, duration = 0; + char buf[256]; + + /* Ensure bytes after string are ones */ + memset(buf, 1, sizeof(buf)); + memcpy(buf, str, len); + + /* Give prog our userspace pointer */ + skel->bss->user_ptr = buf; + + /* Trigger tracepoint */ + usleep(1); + + /* Did helper fail? */ + if (CHECK(skel->bss->ret < 0, "prog_ret", "prog returned: %ld\n", + skel->bss->ret)) + return 1; + + /* Check that string was copied correctly */ + err = memcmp(skel->bss->buf, str, len); + if (CHECK(err, "memcmp", "prog copied wrong string")) + return 1; + + /* Now check that no extra trailing bytes were copied */ + memset(buf, 0, sizeof(buf)); + err = memcmp(skel->bss->buf + len, buf, sizeof(buf) - len); + if (CHECK(err, "memcmp", "trailing bytes were not stripped")) + return 1; + + return 0; +} + +void test_probe_read_user_str(void) +{ + struct test_probe_read_user_str *skel; + int err, duration = 0; + + skel = test_probe_read_user_str__open_and_load(); + if (CHECK(!skel, "test_probe_read_user_str__open_and_load", + "skeleton open and load failed\n")) + return; + + /* Give pid to bpf prog so it doesn't read from anyone else */ + skel->bss->pid = getpid(); + + err = test_probe_read_user_str__attach(skel); + if (CHECK(err, "test_probe_read_user_str__attach", + "skeleton attach failed: %d\n", err)) + goto out; + + if (test_one_str(skel, str1, sizeof(str1))) + goto out; + if (test_one_str(skel, str2, sizeof(str2))) + goto out; + if (test_one_str(skel, str3, sizeof(str3))) + goto out; + +out: + test_probe_read_user_str__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c b/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c index 29188d6f5c8d..51fac975b316 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c @@ -138,7 +138,8 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, */ buf = 0x40; - if (setsockopt(sock_fd, SOL_IP, IP_TOS, &buf, 1) < 0) { + err = setsockopt(sock_fd, SOL_IP, IP_TOS, &buf, 1); + if (err < 0) { log_err("Failed to call setsockopt(IP_TOS)"); goto detach; } diff --git a/tools/testing/selftests/bpf/prog_tests/subprogs.c b/tools/testing/selftests/bpf/prog_tests/subprogs.c index a00abf58c037..3f3d2ac4dd57 100644 --- a/tools/testing/selftests/bpf/prog_tests/subprogs.c +++ b/tools/testing/selftests/bpf/prog_tests/subprogs.c @@ -3,12 +3,14 @@ #include <test_progs.h> #include <time.h> #include "test_subprogs.skel.h" +#include "test_subprogs_unused.skel.h" static int duration; void test_subprogs(void) { struct test_subprogs *skel; + struct test_subprogs_unused *skel2; int err; skel = test_subprogs__open_and_load(); @@ -26,6 +28,10 @@ void test_subprogs(void) CHECK(skel->bss->res3 != 19, "res3", "got %d, exp %d\n", skel->bss->res3, 19); CHECK(skel->bss->res4 != 36, "res4", "got %d, exp %d\n", skel->bss->res4, 36); + skel2 = test_subprogs_unused__open_and_load(); + ASSERT_OK_PTR(skel2, "unused_progs_skel"); + test_subprogs_unused__destroy(skel2); + cleanup: test_subprogs__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c index 193002b14d7f..32e4348b714b 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c +++ b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c @@ -60,6 +60,7 @@ void test_test_global_funcs(void) { "test_global_func5.o" , "expected pointer to ctx, but got PTR" }, { "test_global_func6.o" , "modified ctx ptr R2" }, { "test_global_func7.o" , "foo() doesn't return scalar" }, + { "test_global_func8.o" }, }; libbpf_print_fn_t old_print_fn = NULL; int err, i, duration = 0; diff --git a/tools/testing/selftests/bpf/progs/profiler.inc.h b/tools/testing/selftests/bpf/progs/profiler.inc.h index 00578311a423..30982a7e4d0f 100644 --- a/tools/testing/selftests/bpf/progs/profiler.inc.h +++ b/tools/testing/selftests/bpf/progs/profiler.inc.h @@ -243,7 +243,10 @@ static ino_t get_inode_from_kernfs(struct kernfs_node* node) } } -int pids_cgrp_id = 1; +extern bool CONFIG_CGROUP_PIDS __kconfig __weak; +enum cgroup_subsys_id___local { + pids_cgrp_id___local = 123, /* value doesn't matter */ +}; static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data, struct task_struct* task, @@ -253,7 +256,9 @@ static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data, BPF_CORE_READ(task, nsproxy, cgroup_ns, root_cset, dfl_cgrp, kn); struct kernfs_node* proc_kernfs = BPF_CORE_READ(task, cgroups, dfl_cgrp, kn); - if (ENABLE_CGROUP_V1_RESOLVER) { + if (ENABLE_CGROUP_V1_RESOLVER && CONFIG_CGROUP_PIDS) { + int cgrp_id = bpf_core_enum_value(enum cgroup_subsys_id___local, + pids_cgrp_id___local); #ifdef UNROLL #pragma unroll #endif @@ -262,7 +267,7 @@ static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data, BPF_CORE_READ(task, cgroups, subsys[i]); if (subsys != NULL) { int subsys_id = BPF_CORE_READ(subsys, ss, id); - if (subsys_id == pids_cgrp_id) { + if (subsys_id == cgrp_id) { proc_kernfs = BPF_CORE_READ(subsys, cgroup, kn); root_kernfs = BPF_CORE_READ(subsys, ss, root, kf_root, kn); break; diff --git a/tools/testing/selftests/bpf/progs/test_global_func8.c b/tools/testing/selftests/bpf/progs/test_global_func8.c new file mode 100644 index 000000000000..d55a6544b1ab --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_func8.c @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2020 Facebook */ +#include <stddef.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +__noinline int foo(struct __sk_buff *skb) +{ + return bpf_get_prandom_u32(); +} + +SEC("cgroup_skb/ingress") +int test_cls(struct __sk_buff *skb) +{ + if (!foo(skb)) + return 0; + + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/test_map_init.c b/tools/testing/selftests/bpf/progs/test_map_init.c new file mode 100644 index 000000000000..c89d28ead673 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_map_init.c @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Tessares SA <http://www.tessares.net> */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +__u64 inKey = 0; +__u64 inValue = 0; +__u32 inPid = 0; + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_HASH); + __uint(max_entries, 2); + __type(key, __u64); + __type(value, __u64); +} hashmap1 SEC(".maps"); + + +SEC("tp/syscalls/sys_enter_getpgid") +int sysenter_getpgid(const void *ctx) +{ + /* Just do it for once, when called from our own test prog. This + * ensures the map value is only updated for a single CPU. + */ + int cur_pid = bpf_get_current_pid_tgid() >> 32; + + if (cur_pid == inPid) + bpf_map_update_elem(&hashmap1, &inKey, &inValue, BPF_NOEXIST); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_probe_read_user_str.c b/tools/testing/selftests/bpf/progs/test_probe_read_user_str.c new file mode 100644 index 000000000000..3ae398b75dcd --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_probe_read_user_str.c @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#include <sys/types.h> + +pid_t pid = 0; +long ret = 0; +void *user_ptr = 0; +char buf[256] = {}; + +SEC("tracepoint/syscalls/sys_enter_nanosleep") +int on_write(void *ctx) +{ + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + ret = bpf_probe_read_user_str(buf, sizeof(buf), user_ptr); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_subprogs_unused.c b/tools/testing/selftests/bpf/progs/test_subprogs_unused.c new file mode 100644 index 000000000000..bc49e050d342 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_subprogs_unused.c @@ -0,0 +1,21 @@ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> + +const char LICENSE[] SEC("license") = "GPL"; + +__attribute__((unused)) __noinline int unused1(int x) +{ + return x + 1; +} + +static __attribute__((unused)) __noinline int unused2(int x) +{ + return x + 2; +} + +SEC("raw_tp/sys_enter") +int main_prog(void *ctx) +{ + return 0; +} diff --git a/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c b/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c index 55bd387ce7ec..52d3f0364bda 100644 --- a/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c +++ b/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c @@ -145,7 +145,7 @@ TEST(clone3_cap_checkpoint_restore) test_clone3_supported(); EXPECT_EQ(getuid(), 0) - XFAIL(return, "Skipping all tests as non-root\n"); + SKIP(return, "Skipping all tests as non-root"); memset(&set_tid, 0, sizeof(set_tid)); diff --git a/tools/testing/selftests/core/close_range_test.c b/tools/testing/selftests/core/close_range_test.c index c99b98b0d461..575b391ddc78 100644 --- a/tools/testing/selftests/core/close_range_test.c +++ b/tools/testing/selftests/core/close_range_test.c @@ -44,7 +44,7 @@ TEST(close_range) fd = open("/dev/null", O_RDONLY | O_CLOEXEC); ASSERT_GE(fd, 0) { if (errno == ENOENT) - XFAIL(return, "Skipping test since /dev/null does not exist"); + SKIP(return, "Skipping test since /dev/null does not exist"); } open_fds[i] = fd; @@ -52,7 +52,7 @@ TEST(close_range) EXPECT_EQ(-1, sys_close_range(open_fds[0], open_fds[100], -1)) { if (errno == ENOSYS) - XFAIL(return, "close_range() syscall not supported"); + SKIP(return, "close_range() syscall not supported"); } EXPECT_EQ(0, sys_close_range(open_fds[0], open_fds[50], 0)); @@ -108,7 +108,7 @@ TEST(close_range_unshare) fd = open("/dev/null", O_RDONLY | O_CLOEXEC); ASSERT_GE(fd, 0) { if (errno == ENOENT) - XFAIL(return, "Skipping test since /dev/null does not exist"); + SKIP(return, "Skipping test since /dev/null does not exist"); } open_fds[i] = fd; @@ -197,7 +197,7 @@ TEST(close_range_unshare_capped) fd = open("/dev/null", O_RDONLY | O_CLOEXEC); ASSERT_GE(fd, 0) { if (errno == ENOENT) - XFAIL(return, "Skipping test since /dev/null does not exist"); + SKIP(return, "Skipping test since /dev/null does not exist"); } open_fds[i] = fd; diff --git a/tools/testing/selftests/filesystems/binderfs/binderfs_test.c b/tools/testing/selftests/filesystems/binderfs/binderfs_test.c index 1d27f52c61e6..477cbb042f5b 100644 --- a/tools/testing/selftests/filesystems/binderfs/binderfs_test.c +++ b/tools/testing/selftests/filesystems/binderfs/binderfs_test.c @@ -74,7 +74,7 @@ static int __do_binderfs_test(struct __test_metadata *_metadata) ret = mount(NULL, binderfs_mntpt, "binder", 0, 0); EXPECT_EQ(ret, 0) { if (errno == ENODEV) - XFAIL(goto out, "binderfs missing"); + SKIP(goto out, "binderfs missing"); TH_LOG("%s - Failed to mount binderfs", strerror(errno)); goto rmdir; } @@ -475,10 +475,10 @@ TEST(binderfs_stress) TEST(binderfs_test_privileged) { if (geteuid() != 0) - XFAIL(return, "Tests are not run as root. Skipping privileged tests"); + SKIP(return, "Tests are not run as root. Skipping privileged tests"); if (__do_binderfs_test(_metadata)) - XFAIL(return, "The Android binderfs filesystem is not available"); + SKIP(return, "The Android binderfs filesystem is not available"); } TEST(binderfs_test_unprivileged) @@ -511,7 +511,7 @@ TEST(binderfs_test_unprivileged) ret = wait_for_pid(pid); if (ret) { if (ret == 2) - XFAIL(return, "The Android binderfs filesystem is not available"); + SKIP(return, "The Android binderfs filesystem is not available"); ASSERT_EQ(ret, 0) { TH_LOG("wait_for_pid() failed"); } diff --git a/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c b/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c index d979ff14775a..8f82f99f7748 100644 --- a/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c +++ b/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c @@ -3282,4 +3282,99 @@ TEST(epoll60) close(ctx.epfd); } +struct epoll61_ctx { + int epfd; + int evfd; +}; + +static void *epoll61_write_eventfd(void *ctx_) +{ + struct epoll61_ctx *ctx = ctx_; + int64_t l = 1; + + usleep(10950); + write(ctx->evfd, &l, sizeof(l)); + return NULL; +} + +static void *epoll61_epoll_with_timeout(void *ctx_) +{ + struct epoll61_ctx *ctx = ctx_; + struct epoll_event events[1]; + int n; + + n = epoll_wait(ctx->epfd, events, 1, 11); + /* + * If epoll returned the eventfd, write on the eventfd to wake up the + * blocking poller. + */ + if (n == 1) { + int64_t l = 1; + + write(ctx->evfd, &l, sizeof(l)); + } + return NULL; +} + +static void *epoll61_blocking_epoll(void *ctx_) +{ + struct epoll61_ctx *ctx = ctx_; + struct epoll_event events[1]; + + epoll_wait(ctx->epfd, events, 1, -1); + return NULL; +} + +TEST(epoll61) +{ + struct epoll61_ctx ctx; + struct epoll_event ev; + int i, r; + + ctx.epfd = epoll_create1(0); + ASSERT_GE(ctx.epfd, 0); + ctx.evfd = eventfd(0, EFD_NONBLOCK); + ASSERT_GE(ctx.evfd, 0); + + ev.events = EPOLLIN | EPOLLET | EPOLLERR | EPOLLHUP; + ev.data.ptr = NULL; + r = epoll_ctl(ctx.epfd, EPOLL_CTL_ADD, ctx.evfd, &ev); + ASSERT_EQ(r, 0); + + /* + * We are testing a race. Repeat the test case 1000 times to make it + * more likely to fail in case of a bug. + */ + for (i = 0; i < 1000; i++) { + pthread_t threads[3]; + int n; + + /* + * Start 3 threads: + * Thread 1 sleeps for 10.9ms and writes to the evenfd. + * Thread 2 calls epoll with a timeout of 11ms. + * Thread 3 calls epoll with a timeout of -1. + * + * The eventfd write by Thread 1 should either wakeup Thread 2 + * or Thread 3. If it wakes up Thread 2, Thread 2 writes on the + * eventfd to wake up Thread 3. + * + * If no events are missed, all three threads should eventually + * be joinable. + */ + ASSERT_EQ(pthread_create(&threads[0], NULL, + epoll61_write_eventfd, &ctx), 0); + ASSERT_EQ(pthread_create(&threads[1], NULL, + epoll61_epoll_with_timeout, &ctx), 0); + ASSERT_EQ(pthread_create(&threads[2], NULL, + epoll61_blocking_epoll, &ctx), 0); + + for (n = 0; n < ARRAY_SIZE(threads); ++n) + ASSERT_EQ(pthread_join(threads[n], NULL), 0); + } + + close(ctx.epfd); + close(ctx.evfd); +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_kprobe.tc b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_kprobe.tc index 3bcd4c3624ee..b4da41d126d5 100644 --- a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_kprobe.tc +++ b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_kprobe.tc @@ -6,7 +6,7 @@ echo 0 > events/enable echo > dynamic_events -PLACE=kernel_clone +PLACE=$FUNCTION_FORK echo "p:myevent1 $PLACE" >> dynamic_events echo "r:myevent2 $PLACE" >> dynamic_events diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/clear_select_events.tc b/tools/testing/selftests/ftrace/test.d/dynevent/clear_select_events.tc index 438961971b7e..3a0e2885fff5 100644 --- a/tools/testing/selftests/ftrace/test.d/dynevent/clear_select_events.tc +++ b/tools/testing/selftests/ftrace/test.d/dynevent/clear_select_events.tc @@ -6,7 +6,7 @@ echo 0 > events/enable echo > dynamic_events -PLACE=kernel_clone +PLACE=$FUNCTION_FORK setup_events() { echo "p:myevent1 $PLACE" >> dynamic_events diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/generic_clear_event.tc b/tools/testing/selftests/ftrace/test.d/dynevent/generic_clear_event.tc index a8603bd23e0d..d3e138e8377f 100644 --- a/tools/testing/selftests/ftrace/test.d/dynevent/generic_clear_event.tc +++ b/tools/testing/selftests/ftrace/test.d/dynevent/generic_clear_event.tc @@ -6,7 +6,7 @@ echo 0 > events/enable echo > dynamic_events -PLACE=kernel_clone +PLACE=$FUNCTION_FORK setup_events() { echo "p:myevent1 $PLACE" >> dynamic_events diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-notrace-pid.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-notrace-pid.tc index acb17ce543d2..80541964b927 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-notrace-pid.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-notrace-pid.tc @@ -39,7 +39,7 @@ do_test() { disable_tracing echo do_execve* > set_ftrace_filter - echo *do_fork >> set_ftrace_filter + echo $FUNCTION_FORK >> set_ftrace_filter echo $PID > set_ftrace_notrace_pid echo function > current_tracer diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc index 9f0a9687c773..2f7211254529 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc @@ -39,7 +39,7 @@ do_test() { disable_tracing echo do_execve* > set_ftrace_filter - echo *do_fork >> set_ftrace_filter + echo $FUNCTION_FORK >> set_ftrace_filter echo $PID > set_ftrace_pid echo function > current_tracer diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc index 98305d76bd04..191d116b7883 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc @@ -4,9 +4,9 @@ # requires: set_ftrace_filter # flags: instance -echo kernel_clone:stacktrace >> set_ftrace_filter +echo $FUNCTION_FORK:stacktrace >> set_ftrace_filter -grep -q "kernel_clone:stacktrace:unlimited" set_ftrace_filter +grep -q "$FUNCTION_FORK:stacktrace:unlimited" set_ftrace_filter (echo "forked"; sleep 1) diff --git a/tools/testing/selftests/ftrace/test.d/functions b/tools/testing/selftests/ftrace/test.d/functions index c5dec55b7d95..a6fac927ee82 100644 --- a/tools/testing/selftests/ftrace/test.d/functions +++ b/tools/testing/selftests/ftrace/test.d/functions @@ -133,6 +133,13 @@ yield() { ping $LOCALHOST -c 1 || sleep .001 || usleep 1 || sleep 1 } +# The fork function in the kernel was renamed from "_do_fork" to +# "kernel_fork". As older tests should still work with older kernels +# as well as newer kernels, check which version of fork is used on this +# kernel so that the tests can use the fork function for the running kernel. +FUNCTION_FORK=`(if grep '\bkernel_clone\b' /proc/kallsyms > /dev/null; then + echo kernel_clone; else echo '_do_fork'; fi)` + # Since probe event command may include backslash, explicitly use printf "%s" # to NOT interpret it. ftrace_errlog_check() { # err-prefix command-with-error-pos-by-^ command-file diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc b/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc index 9737cd0578a7..2428a3ed78c9 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc @@ -3,7 +3,7 @@ # description: Kprobe dynamic event - adding and removing # requires: kprobe_events -echo p:myevent kernel_clone > kprobe_events +echo p:myevent $FUNCTION_FORK > kprobe_events grep myevent kprobe_events test -d events/kprobes/myevent echo > kprobe_events diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc b/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc index f9a40af76888..010a8b1d6c1d 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc @@ -3,7 +3,7 @@ # description: Kprobe dynamic event - busy event check # requires: kprobe_events -echo p:myevent kernel_clone > kprobe_events +echo p:myevent $FUNCTION_FORK > kprobe_events test -d events/kprobes/myevent echo 1 > events/kprobes/myevent/enable echo > kprobe_events && exit_fail # this must fail diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc index eb543d3cfe5f..a96a1dc7014f 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc @@ -3,13 +3,13 @@ # description: Kprobe dynamic event with arguments # requires: kprobe_events -echo 'p:testprobe kernel_clone $stack $stack0 +0($stack)' > kprobe_events +echo "p:testprobe $FUNCTION_FORK \$stack \$stack0 +0(\$stack)" > kprobe_events grep testprobe kprobe_events | grep -q 'arg1=\$stack arg2=\$stack0 arg3=+0(\$stack)' test -d events/kprobes/testprobe echo 1 > events/kprobes/testprobe/enable ( echo "forked") -grep testprobe trace | grep 'kernel_clone' | \ +grep testprobe trace | grep "$FUNCTION_FORK" | \ grep -q 'arg1=0x[[:xdigit:]]* arg2=0x[[:xdigit:]]* arg3=0x[[:xdigit:]]*$' echo 0 > events/kprobes/testprobe/enable diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_comm.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_comm.tc index 4e5b63be51c9..a053ee2e7d77 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_comm.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_comm.tc @@ -5,7 +5,7 @@ grep -A1 "fetcharg:" README | grep -q "\$comm" || exit_unsupported # this is too old -echo 'p:testprobe kernel_clone comm=$comm ' > kprobe_events +echo "p:testprobe $FUNCTION_FORK comm=\$comm " > kprobe_events grep testprobe kprobe_events | grep -q 'comm=$comm' test -d events/kprobes/testprobe diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc index a1d70588ab21..84285a6f60b0 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc @@ -30,13 +30,13 @@ esac : "Test get argument (1)" echo "p:testprobe tracefs_create_dir arg1=+0(${ARG1}):string" > kprobe_events echo 1 > events/kprobes/testprobe/enable -echo "p:test kernel_clone" >> kprobe_events +echo "p:test $FUNCTION_FORK" >> kprobe_events grep -qe "testprobe.* arg1=\"test\"" trace echo 0 > events/kprobes/testprobe/enable : "Test get argument (2)" echo "p:testprobe tracefs_create_dir arg1=+0(${ARG1}):string arg2=+0(${ARG1}):string" > kprobe_events echo 1 > events/kprobes/testprobe/enable -echo "p:test kernel_clone" >> kprobe_events +echo "p:test $FUNCTION_FORK" >> kprobe_events grep -qe "testprobe.* arg1=\"test\" arg2=\"test\"" trace diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_symbol.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_symbol.tc index bd25dd0ba0d0..717130ed4feb 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_symbol.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_symbol.tc @@ -14,12 +14,12 @@ elif ! grep "$SYMBOL\$" /proc/kallsyms; then fi : "Test get basic types symbol argument" -echo "p:testprobe_u kernel_clone arg1=@linux_proc_banner:u64 arg2=@linux_proc_banner:u32 arg3=@linux_proc_banner:u16 arg4=@linux_proc_banner:u8" > kprobe_events -echo "p:testprobe_s kernel_clone arg1=@linux_proc_banner:s64 arg2=@linux_proc_banner:s32 arg3=@linux_proc_banner:s16 arg4=@linux_proc_banner:s8" >> kprobe_events +echo "p:testprobe_u $FUNCTION_FORK arg1=@linux_proc_banner:u64 arg2=@linux_proc_banner:u32 arg3=@linux_proc_banner:u16 arg4=@linux_proc_banner:u8" > kprobe_events +echo "p:testprobe_s $FUNCTION_FORK arg1=@linux_proc_banner:s64 arg2=@linux_proc_banner:s32 arg3=@linux_proc_banner:s16 arg4=@linux_proc_banner:s8" >> kprobe_events if grep -q "x8/16/32/64" README; then - echo "p:testprobe_x kernel_clone arg1=@linux_proc_banner:x64 arg2=@linux_proc_banner:x32 arg3=@linux_proc_banner:x16 arg4=@linux_proc_banner:x8" >> kprobe_events + echo "p:testprobe_x $FUNCTION_FORK arg1=@linux_proc_banner:x64 arg2=@linux_proc_banner:x32 arg3=@linux_proc_banner:x16 arg4=@linux_proc_banner:x8" >> kprobe_events fi -echo "p:testprobe_bf kernel_clone arg1=@linux_proc_banner:b8@4/32" >> kprobe_events +echo "p:testprobe_bf $FUNCTION_FORK arg1=@linux_proc_banner:b8@4/32" >> kprobe_events echo 1 > events/kprobes/enable (echo "forked") echo 0 > events/kprobes/enable @@ -27,7 +27,7 @@ grep "testprobe_[usx]:.* arg1=.* arg2=.* arg3=.* arg4=.*" trace grep "testprobe_bf:.* arg1=.*" trace : "Test get string symbol argument" -echo "p:testprobe_str kernel_clone arg1=@linux_proc_banner:string" > kprobe_events +echo "p:testprobe_str $FUNCTION_FORK arg1=@linux_proc_banner:string" > kprobe_events echo 1 > events/kprobes/enable (echo "forked") echo 0 > events/kprobes/enable diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc index 91fcce1c241c..25b7708eb559 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc @@ -4,7 +4,7 @@ # requires: kprobe_events "x8/16/32/64":README gen_event() { # Bitsize - echo "p:testprobe kernel_clone \$stack0:s$1 \$stack0:u$1 \$stack0:x$1 \$stack0:b4@4/$1" + echo "p:testprobe $FUNCTION_FORK \$stack0:s$1 \$stack0:u$1 \$stack0:x$1 \$stack0:b4@4/$1" } check_types() { # s-type u-type x-type bf-type width diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_user.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_user.tc index a30a9c07290d..d25d01a19778 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_user.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_user.tc @@ -9,12 +9,16 @@ grep -A10 "fetcharg:" README | grep -q '\[u\]<offset>' || exit_unsupported :;: "user-memory access syntax and ustring working on user memory";: echo 'p:myevent do_sys_open path=+0($arg2):ustring path2=+u0($arg2):string' \ > kprobe_events +echo 'p:myevent2 do_sys_openat2 path=+0($arg2):ustring path2=+u0($arg2):string' \ + >> kprobe_events grep myevent kprobe_events | \ grep -q 'path=+0($arg2):ustring path2=+u0($arg2):string' echo 1 > events/kprobes/myevent/enable +echo 1 > events/kprobes/myevent2/enable echo > /dev/null echo 0 > events/kprobes/myevent/enable +echo 0 > events/kprobes/myevent2/enable grep myevent trace | grep -q 'path="/dev/null" path2="/dev/null"' diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc index 0d179094191f..5556292601a4 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc @@ -5,29 +5,29 @@ # prepare echo nop > current_tracer -echo kernel_clone > set_ftrace_filter -echo 'p:testprobe kernel_clone' > kprobe_events +echo $FUNCTION_FORK > set_ftrace_filter +echo "p:testprobe $FUNCTION_FORK" > kprobe_events # kprobe on / ftrace off echo 1 > events/kprobes/testprobe/enable echo > trace ( echo "forked") grep testprobe trace -! grep 'kernel_clone <-' trace +! grep "$FUNCTION_FORK <-" trace # kprobe on / ftrace on echo function > current_tracer echo > trace ( echo "forked") grep testprobe trace -grep 'kernel_clone <-' trace +grep "$FUNCTION_FORK <-" trace # kprobe off / ftrace on echo 0 > events/kprobes/testprobe/enable echo > trace ( echo "forked") ! grep testprobe trace -grep 'kernel_clone <-' trace +grep "$FUNCTION_FORK <-" trace # kprobe on / ftrace on echo 1 > events/kprobes/testprobe/enable @@ -35,11 +35,11 @@ echo function > current_tracer echo > trace ( echo "forked") grep testprobe trace -grep 'kernel_clone <-' trace +grep "$FUNCTION_FORK <-" trace # kprobe on / ftrace off echo nop > current_tracer echo > trace ( echo "forked") grep testprobe trace -! grep 'kernel_clone <-' trace +! grep "$FUNCTION_FORK <-" trace diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_multiprobe.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_multiprobe.tc index 45d90b6c763d..f0d5b7777ed7 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_multiprobe.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_multiprobe.tc @@ -4,7 +4,7 @@ # requires: kprobe_events "Create/append/":README # Choose 2 symbols for target -SYM1=kernel_clone +SYM1=$FUNCTION_FORK SYM2=do_exit EVENT_NAME=kprobes/testevent diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc index 1b5550ef8a9b..fa928b431555 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc @@ -86,15 +86,15 @@ esac # multiprobe errors if grep -q "Create/append/" README && grep -q "imm-value" README; then -echo 'p:kprobes/testevent kernel_clone' > kprobe_events +echo "p:kprobes/testevent $FUNCTION_FORK" > kprobe_events check_error '^r:kprobes/testevent do_exit' # DIFF_PROBE_TYPE # Explicitly use printf "%s" to not interpret \1 -printf "%s" 'p:kprobes/testevent kernel_clone abcd=\1' > kprobe_events -check_error 'p:kprobes/testevent kernel_clone ^bcd=\1' # DIFF_ARG_TYPE -check_error 'p:kprobes/testevent kernel_clone ^abcd=\1:u8' # DIFF_ARG_TYPE -check_error 'p:kprobes/testevent kernel_clone ^abcd=\"foo"' # DIFF_ARG_TYPE -check_error '^p:kprobes/testevent kernel_clone abcd=\1' # SAME_PROBE +printf "%s" "p:kprobes/testevent $FUNCTION_FORK abcd=\\1" > kprobe_events +check_error "p:kprobes/testevent $FUNCTION_FORK ^bcd=\\1" # DIFF_ARG_TYPE +check_error "p:kprobes/testevent $FUNCTION_FORK ^abcd=\\1:u8" # DIFF_ARG_TYPE +check_error "p:kprobes/testevent $FUNCTION_FORK ^abcd=\\\"foo\"" # DIFF_ARG_TYPE +check_error "^p:kprobes/testevent $FUNCTION_FORK abcd=\\1" # SAME_PROBE fi # %return suffix errors diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc index 7ae492c204a4..197cc2afd404 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc @@ -4,14 +4,14 @@ # requires: kprobe_events # Add new kretprobe event -echo 'r:testprobe2 kernel_clone $retval' > kprobe_events +echo "r:testprobe2 $FUNCTION_FORK \$retval" > kprobe_events grep testprobe2 kprobe_events | grep -q 'arg1=\$retval' test -d events/kprobes/testprobe2 echo 1 > events/kprobes/testprobe2/enable ( echo "forked") -cat trace | grep testprobe2 | grep -q '<- kernel_clone' +cat trace | grep testprobe2 | grep -q "<- $FUNCTION_FORK" echo 0 > events/kprobes/testprobe2/enable echo '-:testprobe2' >> kprobe_events diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/profile.tc b/tools/testing/selftests/ftrace/test.d/kprobe/profile.tc index c4093fc1a773..98166fa3eb91 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/profile.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/profile.tc @@ -4,7 +4,7 @@ # requires: kprobe_events ! grep -q 'myevent' kprobe_profile -echo p:myevent kernel_clone > kprobe_events +echo "p:myevent $FUNCTION_FORK" > kprobe_events grep -q 'myevent[[:space:]]*0[[:space:]]*0$' kprobe_profile echo 1 > events/kprobes/myevent/enable ( echo "forked" ) diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index f19804df244c..edce85420d19 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -126,7 +126,7 @@ snprintf(_metadata->results->reason, \ sizeof(_metadata->results->reason), fmt, ##__VA_ARGS__); \ if (TH_LOG_ENABLED) { \ - fprintf(TH_LOG_STREAM, "# SKIP %s\n", \ + fprintf(TH_LOG_STREAM, "# SKIP %s\n", \ _metadata->results->reason); \ } \ _metadata->passed = 1; \ @@ -432,7 +432,7 @@ */ /** - * ASSERT_EQ(expected, seen) + * ASSERT_EQ() * * @expected: expected value * @seen: measured value @@ -443,7 +443,7 @@ __EXPECT(expected, #expected, seen, #seen, ==, 1) /** - * ASSERT_NE(expected, seen) + * ASSERT_NE() * * @expected: expected value * @seen: measured value @@ -454,7 +454,7 @@ __EXPECT(expected, #expected, seen, #seen, !=, 1) /** - * ASSERT_LT(expected, seen) + * ASSERT_LT() * * @expected: expected value * @seen: measured value @@ -465,7 +465,7 @@ __EXPECT(expected, #expected, seen, #seen, <, 1) /** - * ASSERT_LE(expected, seen) + * ASSERT_LE() * * @expected: expected value * @seen: measured value @@ -476,7 +476,7 @@ __EXPECT(expected, #expected, seen, #seen, <=, 1) /** - * ASSERT_GT(expected, seen) + * ASSERT_GT() * * @expected: expected value * @seen: measured value @@ -487,7 +487,7 @@ __EXPECT(expected, #expected, seen, #seen, >, 1) /** - * ASSERT_GE(expected, seen) + * ASSERT_GE() * * @expected: expected value * @seen: measured value @@ -498,7 +498,7 @@ __EXPECT(expected, #expected, seen, #seen, >=, 1) /** - * ASSERT_NULL(seen) + * ASSERT_NULL() * * @seen: measured value * @@ -508,7 +508,7 @@ __EXPECT(NULL, "NULL", seen, #seen, ==, 1) /** - * ASSERT_TRUE(seen) + * ASSERT_TRUE() * * @seen: measured value * @@ -518,7 +518,7 @@ __EXPECT(0, "0", seen, #seen, !=, 1) /** - * ASSERT_FALSE(seen) + * ASSERT_FALSE() * * @seen: measured value * @@ -528,7 +528,7 @@ __EXPECT(0, "0", seen, #seen, ==, 1) /** - * ASSERT_STREQ(expected, seen) + * ASSERT_STREQ() * * @expected: expected value * @seen: measured value @@ -539,7 +539,7 @@ __EXPECT_STR(expected, seen, ==, 1) /** - * ASSERT_STRNE(expected, seen) + * ASSERT_STRNE() * * @expected: expected value * @seen: measured value @@ -550,7 +550,7 @@ __EXPECT_STR(expected, seen, !=, 1) /** - * EXPECT_EQ(expected, seen) + * EXPECT_EQ() * * @expected: expected value * @seen: measured value @@ -561,7 +561,7 @@ __EXPECT(expected, #expected, seen, #seen, ==, 0) /** - * EXPECT_NE(expected, seen) + * EXPECT_NE() * * @expected: expected value * @seen: measured value @@ -572,7 +572,7 @@ __EXPECT(expected, #expected, seen, #seen, !=, 0) /** - * EXPECT_LT(expected, seen) + * EXPECT_LT() * * @expected: expected value * @seen: measured value @@ -583,7 +583,7 @@ __EXPECT(expected, #expected, seen, #seen, <, 0) /** - * EXPECT_LE(expected, seen) + * EXPECT_LE() * * @expected: expected value * @seen: measured value @@ -594,7 +594,7 @@ __EXPECT(expected, #expected, seen, #seen, <=, 0) /** - * EXPECT_GT(expected, seen) + * EXPECT_GT() * * @expected: expected value * @seen: measured value @@ -605,7 +605,7 @@ __EXPECT(expected, #expected, seen, #seen, >, 0) /** - * EXPECT_GE(expected, seen) + * EXPECT_GE() * * @expected: expected value * @seen: measured value @@ -616,7 +616,7 @@ __EXPECT(expected, #expected, seen, #seen, >=, 0) /** - * EXPECT_NULL(seen) + * EXPECT_NULL() * * @seen: measured value * @@ -626,7 +626,7 @@ __EXPECT(NULL, "NULL", seen, #seen, ==, 0) /** - * EXPECT_TRUE(seen) + * EXPECT_TRUE() * * @seen: measured value * @@ -636,7 +636,7 @@ __EXPECT(0, "0", seen, #seen, !=, 0) /** - * EXPECT_FALSE(seen) + * EXPECT_FALSE() * * @seen: measured value * @@ -646,7 +646,7 @@ __EXPECT(0, "0", seen, #seen, ==, 0) /** - * EXPECT_STREQ(expected, seen) + * EXPECT_STREQ() * * @expected: expected value * @seen: measured value @@ -657,7 +657,7 @@ __EXPECT_STR(expected, seen, ==, 0) /** - * EXPECT_STRNE(expected, seen) + * EXPECT_STRNE() * * @expected: expected value * @seen: measured value diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index d2c2d6205008..7a2c242b7152 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -1,10 +1,13 @@ # SPDX-License-Identifier: GPL-2.0-only +/aarch64/get-reg-list +/aarch64/get-reg-list-sve /s390x/memop /s390x/resets /s390x/sync_regs_test /x86_64/cr4_cpuid_sync_test /x86_64/debug_regs /x86_64/evmcs_test +/x86_64/kvm_pv_test /x86_64/hyperv_cpuid /x86_64/mmio_warning_test /x86_64/platform_info_test @@ -24,6 +27,7 @@ /clear_dirty_log_test /demand_paging_test /dirty_log_test +/dirty_log_perf_test /kvm_create_max_vcpus /set_memory_region_test /steal_time diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 30afbad36cd5..3d14ef77755e 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -34,13 +34,14 @@ ifeq ($(ARCH),s390) endif LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c lib/test_util.c -LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c +LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c lib/x86_64/handlers.S LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c TEST_GEN_PROGS_x86_64 = x86_64/cr4_cpuid_sync_test TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid +TEST_GEN_PROGS_x86_64 += x86_64/kvm_pv_test TEST_GEN_PROGS_x86_64 += x86_64/mmio_warning_test TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test @@ -58,14 +59,15 @@ TEST_GEN_PROGS_x86_64 += x86_64/xss_msr_test TEST_GEN_PROGS_x86_64 += x86_64/debug_regs TEST_GEN_PROGS_x86_64 += x86_64/tsc_msrs_test TEST_GEN_PROGS_x86_64 += x86_64/user_msr_test -TEST_GEN_PROGS_x86_64 += clear_dirty_log_test TEST_GEN_PROGS_x86_64 += demand_paging_test TEST_GEN_PROGS_x86_64 += dirty_log_test +TEST_GEN_PROGS_x86_64 += dirty_log_perf_test TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus TEST_GEN_PROGS_x86_64 += set_memory_region_test TEST_GEN_PROGS_x86_64 += steal_time -TEST_GEN_PROGS_aarch64 += clear_dirty_log_test +TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list +TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list-sve TEST_GEN_PROGS_aarch64 += demand_paging_test TEST_GEN_PROGS_aarch64 += dirty_log_test TEST_GEN_PROGS_aarch64 += kvm_create_max_vcpus @@ -111,14 +113,21 @@ LDFLAGS += -pthread $(no-pie-option) $(pgste-option) include ../lib.mk STATIC_LIBS := $(OUTPUT)/libkvm.a -LIBKVM_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM)) -EXTRA_CLEAN += $(LIBKVM_OBJ) $(STATIC_LIBS) cscope.* +LIBKVM_C := $(filter %.c,$(LIBKVM)) +LIBKVM_S := $(filter %.S,$(LIBKVM)) +LIBKVM_C_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_C)) +LIBKVM_S_OBJ := $(patsubst %.S, $(OUTPUT)/%.o, $(LIBKVM_S)) +EXTRA_CLEAN += $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ) $(STATIC_LIBS) cscope.* + +x := $(shell mkdir -p $(sort $(dir $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ)))) +$(LIBKVM_C_OBJ): $(OUTPUT)/%.o: %.c + $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@ -x := $(shell mkdir -p $(sort $(dir $(LIBKVM_OBJ)))) -$(LIBKVM_OBJ): $(OUTPUT)/%.o: %.c +$(LIBKVM_S_OBJ): $(OUTPUT)/%.o: %.S $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@ -$(OUTPUT)/libkvm.a: $(LIBKVM_OBJ) +LIBKVM_OBJS = $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ) +$(OUTPUT)/libkvm.a: $(LIBKVM_OBJS) $(AR) crs $@ $^ x := $(shell mkdir -p $(sort $(dir $(TEST_GEN_PROGS)))) diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list-sve.c b/tools/testing/selftests/kvm/aarch64/get-reg-list-sve.c new file mode 100644 index 000000000000..efba76682b4b --- /dev/null +++ b/tools/testing/selftests/kvm/aarch64/get-reg-list-sve.c @@ -0,0 +1,3 @@ +// SPDX-License-Identifier: GPL-2.0 +#define REG_LIST_SVE +#include "get-reg-list.c" diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c new file mode 100644 index 000000000000..33218a395d9f --- /dev/null +++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c @@ -0,0 +1,841 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Check for KVM_GET_REG_LIST regressions. + * + * Copyright (C) 2020, Red Hat, Inc. + * + * When attempting to migrate from a host with an older kernel to a host + * with a newer kernel we allow the newer kernel on the destination to + * list new registers with get-reg-list. We assume they'll be unused, at + * least until the guest reboots, and so they're relatively harmless. + * However, if the destination host with the newer kernel is missing + * registers which the source host with the older kernel has, then that's + * a regression in get-reg-list. This test checks for that regression by + * checking the current list against a blessed list. We should never have + * missing registers, but if new ones appear then they can probably be + * added to the blessed list. A completely new blessed list can be created + * by running the test with the --list command line argument. + * + * Note, the blessed list should be created from the oldest possible + * kernel. We can't go older than v4.15, though, because that's the first + * release to expose the ID system registers in KVM_GET_REG_LIST, see + * commit 93390c0a1b20 ("arm64: KVM: Hide unsupported AArch64 CPU features + * from guests"). Also, one must use the --core-reg-fixup command line + * option when running on an older kernel that doesn't include df205b5c6328 + * ("KVM: arm64: Filter out invalid core register IDs in KVM_GET_REG_LIST") + */ +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include "kvm_util.h" +#include "test_util.h" +#include "processor.h" + +#ifdef REG_LIST_SVE +#define reg_list_sve() (true) +#else +#define reg_list_sve() (false) +#endif + +#define REG_MASK (KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_COPROC_MASK) + +#define for_each_reg(i) \ + for ((i) = 0; (i) < reg_list->n; ++(i)) + +#define for_each_missing_reg(i) \ + for ((i) = 0; (i) < blessed_n; ++(i)) \ + if (!find_reg(reg_list->reg, reg_list->n, blessed_reg[i])) + +#define for_each_new_reg(i) \ + for ((i) = 0; (i) < reg_list->n; ++(i)) \ + if (!find_reg(blessed_reg, blessed_n, reg_list->reg[i])) + + +static struct kvm_reg_list *reg_list; + +static __u64 base_regs[], vregs[], sve_regs[], rejects_set[]; +static __u64 base_regs_n, vregs_n, sve_regs_n, rejects_set_n; +static __u64 *blessed_reg, blessed_n; + +static bool find_reg(__u64 regs[], __u64 nr_regs, __u64 reg) +{ + int i; + + for (i = 0; i < nr_regs; ++i) + if (reg == regs[i]) + return true; + return false; +} + +static const char *str_with_index(const char *template, __u64 index) +{ + char *str, *p; + int n; + + str = strdup(template); + p = strstr(str, "##"); + n = sprintf(p, "%lld", index); + strcat(p + n, strstr(template, "##") + 2); + + return (const char *)str; +} + +#define CORE_REGS_XX_NR_WORDS 2 +#define CORE_SPSR_XX_NR_WORDS 2 +#define CORE_FPREGS_XX_NR_WORDS 4 + +static const char *core_id_to_str(__u64 id) +{ + __u64 core_off = id & ~REG_MASK, idx; + + /* + * core_off is the offset into struct kvm_regs + */ + switch (core_off) { + case KVM_REG_ARM_CORE_REG(regs.regs[0]) ... + KVM_REG_ARM_CORE_REG(regs.regs[30]): + idx = (core_off - KVM_REG_ARM_CORE_REG(regs.regs[0])) / CORE_REGS_XX_NR_WORDS; + TEST_ASSERT(idx < 31, "Unexpected regs.regs index: %lld", idx); + return str_with_index("KVM_REG_ARM_CORE_REG(regs.regs[##])", idx); + case KVM_REG_ARM_CORE_REG(regs.sp): + return "KVM_REG_ARM_CORE_REG(regs.sp)"; + case KVM_REG_ARM_CORE_REG(regs.pc): + return "KVM_REG_ARM_CORE_REG(regs.pc)"; + case KVM_REG_ARM_CORE_REG(regs.pstate): + return "KVM_REG_ARM_CORE_REG(regs.pstate)"; + case KVM_REG_ARM_CORE_REG(sp_el1): + return "KVM_REG_ARM_CORE_REG(sp_el1)"; + case KVM_REG_ARM_CORE_REG(elr_el1): + return "KVM_REG_ARM_CORE_REG(elr_el1)"; + case KVM_REG_ARM_CORE_REG(spsr[0]) ... + KVM_REG_ARM_CORE_REG(spsr[KVM_NR_SPSR - 1]): + idx = (core_off - KVM_REG_ARM_CORE_REG(spsr[0])) / CORE_SPSR_XX_NR_WORDS; + TEST_ASSERT(idx < KVM_NR_SPSR, "Unexpected spsr index: %lld", idx); + return str_with_index("KVM_REG_ARM_CORE_REG(spsr[##])", idx); + case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ... + KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]): + idx = (core_off - KVM_REG_ARM_CORE_REG(fp_regs.vregs[0])) / CORE_FPREGS_XX_NR_WORDS; + TEST_ASSERT(idx < 32, "Unexpected fp_regs.vregs index: %lld", idx); + return str_with_index("KVM_REG_ARM_CORE_REG(fp_regs.vregs[##])", idx); + case KVM_REG_ARM_CORE_REG(fp_regs.fpsr): + return "KVM_REG_ARM_CORE_REG(fp_regs.fpsr)"; + case KVM_REG_ARM_CORE_REG(fp_regs.fpcr): + return "KVM_REG_ARM_CORE_REG(fp_regs.fpcr)"; + } + + TEST_FAIL("Unknown core reg id: 0x%llx", id); + return NULL; +} + +static const char *sve_id_to_str(__u64 id) +{ + __u64 sve_off, n, i; + + if (id == KVM_REG_ARM64_SVE_VLS) + return "KVM_REG_ARM64_SVE_VLS"; + + sve_off = id & ~(REG_MASK | ((1ULL << 5) - 1)); + i = id & (KVM_ARM64_SVE_MAX_SLICES - 1); + + TEST_ASSERT(i == 0, "Currently we don't expect slice > 0, reg id 0x%llx", id); + + switch (sve_off) { + case KVM_REG_ARM64_SVE_ZREG_BASE ... + KVM_REG_ARM64_SVE_ZREG_BASE + (1ULL << 5) * KVM_ARM64_SVE_NUM_ZREGS - 1: + n = (id >> 5) & (KVM_ARM64_SVE_NUM_ZREGS - 1); + TEST_ASSERT(id == KVM_REG_ARM64_SVE_ZREG(n, 0), + "Unexpected bits set in SVE ZREG id: 0x%llx", id); + return str_with_index("KVM_REG_ARM64_SVE_ZREG(##, 0)", n); + case KVM_REG_ARM64_SVE_PREG_BASE ... + KVM_REG_ARM64_SVE_PREG_BASE + (1ULL << 5) * KVM_ARM64_SVE_NUM_PREGS - 1: + n = (id >> 5) & (KVM_ARM64_SVE_NUM_PREGS - 1); + TEST_ASSERT(id == KVM_REG_ARM64_SVE_PREG(n, 0), + "Unexpected bits set in SVE PREG id: 0x%llx", id); + return str_with_index("KVM_REG_ARM64_SVE_PREG(##, 0)", n); + case KVM_REG_ARM64_SVE_FFR_BASE: + TEST_ASSERT(id == KVM_REG_ARM64_SVE_FFR(0), + "Unexpected bits set in SVE FFR id: 0x%llx", id); + return "KVM_REG_ARM64_SVE_FFR(0)"; + } + + return NULL; +} + +static void print_reg(__u64 id) +{ + unsigned op0, op1, crn, crm, op2; + const char *reg_size = NULL; + + TEST_ASSERT((id & KVM_REG_ARCH_MASK) == KVM_REG_ARM64, + "KVM_REG_ARM64 missing in reg id: 0x%llx", id); + + switch (id & KVM_REG_SIZE_MASK) { + case KVM_REG_SIZE_U8: + reg_size = "KVM_REG_SIZE_U8"; + break; + case KVM_REG_SIZE_U16: + reg_size = "KVM_REG_SIZE_U16"; + break; + case KVM_REG_SIZE_U32: + reg_size = "KVM_REG_SIZE_U32"; + break; + case KVM_REG_SIZE_U64: + reg_size = "KVM_REG_SIZE_U64"; + break; + case KVM_REG_SIZE_U128: + reg_size = "KVM_REG_SIZE_U128"; + break; + case KVM_REG_SIZE_U256: + reg_size = "KVM_REG_SIZE_U256"; + break; + case KVM_REG_SIZE_U512: + reg_size = "KVM_REG_SIZE_U512"; + break; + case KVM_REG_SIZE_U1024: + reg_size = "KVM_REG_SIZE_U1024"; + break; + case KVM_REG_SIZE_U2048: + reg_size = "KVM_REG_SIZE_U2048"; + break; + default: + TEST_FAIL("Unexpected reg size: 0x%llx in reg id: 0x%llx", + (id & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT, id); + } + + switch (id & KVM_REG_ARM_COPROC_MASK) { + case KVM_REG_ARM_CORE: + printf("\tKVM_REG_ARM64 | %s | KVM_REG_ARM_CORE | %s,\n", reg_size, core_id_to_str(id)); + break; + case KVM_REG_ARM_DEMUX: + TEST_ASSERT(!(id & ~(REG_MASK | KVM_REG_ARM_DEMUX_ID_MASK | KVM_REG_ARM_DEMUX_VAL_MASK)), + "Unexpected bits set in DEMUX reg id: 0x%llx", id); + printf("\tKVM_REG_ARM64 | %s | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | %lld,\n", + reg_size, id & KVM_REG_ARM_DEMUX_VAL_MASK); + break; + case KVM_REG_ARM64_SYSREG: + op0 = (id & KVM_REG_ARM64_SYSREG_OP0_MASK) >> KVM_REG_ARM64_SYSREG_OP0_SHIFT; + op1 = (id & KVM_REG_ARM64_SYSREG_OP1_MASK) >> KVM_REG_ARM64_SYSREG_OP1_SHIFT; + crn = (id & KVM_REG_ARM64_SYSREG_CRN_MASK) >> KVM_REG_ARM64_SYSREG_CRN_SHIFT; + crm = (id & KVM_REG_ARM64_SYSREG_CRM_MASK) >> KVM_REG_ARM64_SYSREG_CRM_SHIFT; + op2 = (id & KVM_REG_ARM64_SYSREG_OP2_MASK) >> KVM_REG_ARM64_SYSREG_OP2_SHIFT; + TEST_ASSERT(id == ARM64_SYS_REG(op0, op1, crn, crm, op2), + "Unexpected bits set in SYSREG reg id: 0x%llx", id); + printf("\tARM64_SYS_REG(%d, %d, %d, %d, %d),\n", op0, op1, crn, crm, op2); + break; + case KVM_REG_ARM_FW: + TEST_ASSERT(id == KVM_REG_ARM_FW_REG(id & 0xffff), + "Unexpected bits set in FW reg id: 0x%llx", id); + printf("\tKVM_REG_ARM_FW_REG(%lld),\n", id & 0xffff); + break; + case KVM_REG_ARM64_SVE: + if (reg_list_sve()) + printf("\t%s,\n", sve_id_to_str(id)); + else + TEST_FAIL("KVM_REG_ARM64_SVE is an unexpected coproc type in reg id: 0x%llx", id); + break; + default: + TEST_FAIL("Unexpected coproc type: 0x%llx in reg id: 0x%llx", + (id & KVM_REG_ARM_COPROC_MASK) >> KVM_REG_ARM_COPROC_SHIFT, id); + } +} + +/* + * Older kernels listed each 32-bit word of CORE registers separately. + * For 64 and 128-bit registers we need to ignore the extra words. We + * also need to fixup the sizes, because the older kernels stated all + * registers were 64-bit, even when they weren't. + */ +static void core_reg_fixup(void) +{ + struct kvm_reg_list *tmp; + __u64 id, core_off; + int i; + + tmp = calloc(1, sizeof(*tmp) + reg_list->n * sizeof(__u64)); + + for (i = 0; i < reg_list->n; ++i) { + id = reg_list->reg[i]; + + if ((id & KVM_REG_ARM_COPROC_MASK) != KVM_REG_ARM_CORE) { + tmp->reg[tmp->n++] = id; + continue; + } + + core_off = id & ~REG_MASK; + + switch (core_off) { + case 0x52: case 0xd2: case 0xd6: + /* + * These offsets are pointing at padding. + * We need to ignore them too. + */ + continue; + case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ... + KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]): + if (core_off & 3) + continue; + id &= ~KVM_REG_SIZE_MASK; + id |= KVM_REG_SIZE_U128; + tmp->reg[tmp->n++] = id; + continue; + case KVM_REG_ARM_CORE_REG(fp_regs.fpsr): + case KVM_REG_ARM_CORE_REG(fp_regs.fpcr): + id &= ~KVM_REG_SIZE_MASK; + id |= KVM_REG_SIZE_U32; + tmp->reg[tmp->n++] = id; + continue; + default: + if (core_off & 1) + continue; + tmp->reg[tmp->n++] = id; + break; + } + } + + free(reg_list); + reg_list = tmp; +} + +static void prepare_vcpu_init(struct kvm_vcpu_init *init) +{ + if (reg_list_sve()) + init->features[0] |= 1 << KVM_ARM_VCPU_SVE; +} + +static void finalize_vcpu(struct kvm_vm *vm, uint32_t vcpuid) +{ + int feature; + + if (reg_list_sve()) { + feature = KVM_ARM_VCPU_SVE; + vcpu_ioctl(vm, vcpuid, KVM_ARM_VCPU_FINALIZE, &feature); + } +} + +static void check_supported(void) +{ + if (reg_list_sve() && !kvm_check_cap(KVM_CAP_ARM_SVE)) { + fprintf(stderr, "SVE not available, skipping tests\n"); + exit(KSFT_SKIP); + } +} + +int main(int ac, char **av) +{ + struct kvm_vcpu_init init = { .target = -1, }; + int new_regs = 0, missing_regs = 0, i; + int failed_get = 0, failed_set = 0, failed_reject = 0; + bool print_list = false, fixup_core_regs = false; + struct kvm_vm *vm; + __u64 *vec_regs; + + check_supported(); + + for (i = 1; i < ac; ++i) { + if (strcmp(av[i], "--core-reg-fixup") == 0) + fixup_core_regs = true; + else if (strcmp(av[i], "--list") == 0) + print_list = true; + else + fprintf(stderr, "Ignoring unknown option: %s\n", av[i]); + } + + vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR); + prepare_vcpu_init(&init); + aarch64_vcpu_add_default(vm, 0, &init, NULL); + finalize_vcpu(vm, 0); + + reg_list = vcpu_get_reg_list(vm, 0); + + if (fixup_core_regs) + core_reg_fixup(); + + if (print_list) { + putchar('\n'); + for_each_reg(i) + print_reg(reg_list->reg[i]); + putchar('\n'); + return 0; + } + + /* + * We only test that we can get the register and then write back the + * same value. Some registers may allow other values to be written + * back, but others only allow some bits to be changed, and at least + * for ID registers set will fail if the value does not exactly match + * what was returned by get. If registers that allow other values to + * be written need to have the other values tested, then we should + * create a new set of tests for those in a new independent test + * executable. + */ + for_each_reg(i) { + uint8_t addr[2048 / 8]; + struct kvm_one_reg reg = { + .id = reg_list->reg[i], + .addr = (__u64)&addr, + }; + int ret; + + ret = _vcpu_ioctl(vm, 0, KVM_GET_ONE_REG, ®); + if (ret) { + puts("Failed to get "); + print_reg(reg.id); + putchar('\n'); + ++failed_get; + } + + /* rejects_set registers are rejected after KVM_ARM_VCPU_FINALIZE */ + if (find_reg(rejects_set, rejects_set_n, reg.id)) { + ret = _vcpu_ioctl(vm, 0, KVM_SET_ONE_REG, ®); + if (ret != -1 || errno != EPERM) { + printf("Failed to reject (ret=%d, errno=%d) ", ret, errno); + print_reg(reg.id); + putchar('\n'); + ++failed_reject; + } + continue; + } + + ret = _vcpu_ioctl(vm, 0, KVM_SET_ONE_REG, ®); + if (ret) { + puts("Failed to set "); + print_reg(reg.id); + putchar('\n'); + ++failed_set; + } + } + + if (reg_list_sve()) { + blessed_n = base_regs_n + sve_regs_n; + vec_regs = sve_regs; + } else { + blessed_n = base_regs_n + vregs_n; + vec_regs = vregs; + } + + blessed_reg = calloc(blessed_n, sizeof(__u64)); + for (i = 0; i < base_regs_n; ++i) + blessed_reg[i] = base_regs[i]; + for (i = 0; i < blessed_n - base_regs_n; ++i) + blessed_reg[base_regs_n + i] = vec_regs[i]; + + for_each_new_reg(i) + ++new_regs; + + for_each_missing_reg(i) + ++missing_regs; + + if (new_regs || missing_regs) { + printf("Number blessed registers: %5lld\n", blessed_n); + printf("Number registers: %5lld\n", reg_list->n); + } + + if (new_regs) { + printf("\nThere are %d new registers.\n" + "Consider adding them to the blessed reg " + "list with the following lines:\n\n", new_regs); + for_each_new_reg(i) + print_reg(reg_list->reg[i]); + putchar('\n'); + } + + if (missing_regs) { + printf("\nThere are %d missing registers.\n" + "The following lines are missing registers:\n\n", missing_regs); + for_each_missing_reg(i) + print_reg(blessed_reg[i]); + putchar('\n'); + } + + TEST_ASSERT(!missing_regs && !failed_get && !failed_set && !failed_reject, + "There are %d missing registers; " + "%d registers failed get; %d registers failed set; %d registers failed reject", + missing_regs, failed_get, failed_set, failed_reject); + + return 0; +} + +/* + * The current blessed list was primed with the output of kernel version + * v4.15 with --core-reg-fixup and then later updated with new registers. + */ +static __u64 base_regs[] = { + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[0]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[1]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[2]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[3]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[4]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[5]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[6]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[7]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[8]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[9]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[10]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[11]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[12]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[13]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[14]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[15]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[16]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[17]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[18]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[19]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[20]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[21]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[22]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[23]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[24]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[25]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[26]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[27]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[28]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[29]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[30]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.sp), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.pc), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.pstate), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(sp_el1), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(elr_el1), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[0]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[1]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[2]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[3]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[4]), + KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.fpsr), + KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.fpcr), + KVM_REG_ARM_FW_REG(0), + KVM_REG_ARM_FW_REG(1), + KVM_REG_ARM_FW_REG(2), + ARM64_SYS_REG(3, 3, 14, 3, 1), /* CNTV_CTL_EL0 */ + ARM64_SYS_REG(3, 3, 14, 3, 2), /* CNTV_CVAL_EL0 */ + ARM64_SYS_REG(3, 3, 14, 0, 2), + ARM64_SYS_REG(3, 0, 0, 0, 0), /* MIDR_EL1 */ + ARM64_SYS_REG(3, 0, 0, 0, 6), /* REVIDR_EL1 */ + ARM64_SYS_REG(3, 1, 0, 0, 1), /* CLIDR_EL1 */ + ARM64_SYS_REG(3, 1, 0, 0, 7), /* AIDR_EL1 */ + ARM64_SYS_REG(3, 3, 0, 0, 1), /* CTR_EL0 */ + ARM64_SYS_REG(2, 0, 0, 0, 4), + ARM64_SYS_REG(2, 0, 0, 0, 5), + ARM64_SYS_REG(2, 0, 0, 0, 6), + ARM64_SYS_REG(2, 0, 0, 0, 7), + ARM64_SYS_REG(2, 0, 0, 1, 4), + ARM64_SYS_REG(2, 0, 0, 1, 5), + ARM64_SYS_REG(2, 0, 0, 1, 6), + ARM64_SYS_REG(2, 0, 0, 1, 7), + ARM64_SYS_REG(2, 0, 0, 2, 0), /* MDCCINT_EL1 */ + ARM64_SYS_REG(2, 0, 0, 2, 2), /* MDSCR_EL1 */ + ARM64_SYS_REG(2, 0, 0, 2, 4), + ARM64_SYS_REG(2, 0, 0, 2, 5), + ARM64_SYS_REG(2, 0, 0, 2, 6), + ARM64_SYS_REG(2, 0, 0, 2, 7), + ARM64_SYS_REG(2, 0, 0, 3, 4), + ARM64_SYS_REG(2, 0, 0, 3, 5), + ARM64_SYS_REG(2, 0, 0, 3, 6), + ARM64_SYS_REG(2, 0, 0, 3, 7), + ARM64_SYS_REG(2, 0, 0, 4, 4), + ARM64_SYS_REG(2, 0, 0, 4, 5), + ARM64_SYS_REG(2, 0, 0, 4, 6), + ARM64_SYS_REG(2, 0, 0, 4, 7), + ARM64_SYS_REG(2, 0, 0, 5, 4), + ARM64_SYS_REG(2, 0, 0, 5, 5), + ARM64_SYS_REG(2, 0, 0, 5, 6), + ARM64_SYS_REG(2, 0, 0, 5, 7), + ARM64_SYS_REG(2, 0, 0, 6, 4), + ARM64_SYS_REG(2, 0, 0, 6, 5), + ARM64_SYS_REG(2, 0, 0, 6, 6), + ARM64_SYS_REG(2, 0, 0, 6, 7), + ARM64_SYS_REG(2, 0, 0, 7, 4), + ARM64_SYS_REG(2, 0, 0, 7, 5), + ARM64_SYS_REG(2, 0, 0, 7, 6), + ARM64_SYS_REG(2, 0, 0, 7, 7), + ARM64_SYS_REG(2, 0, 0, 8, 4), + ARM64_SYS_REG(2, 0, 0, 8, 5), + ARM64_SYS_REG(2, 0, 0, 8, 6), + ARM64_SYS_REG(2, 0, 0, 8, 7), + ARM64_SYS_REG(2, 0, 0, 9, 4), + ARM64_SYS_REG(2, 0, 0, 9, 5), + ARM64_SYS_REG(2, 0, 0, 9, 6), + ARM64_SYS_REG(2, 0, 0, 9, 7), + ARM64_SYS_REG(2, 0, 0, 10, 4), + ARM64_SYS_REG(2, 0, 0, 10, 5), + ARM64_SYS_REG(2, 0, 0, 10, 6), + ARM64_SYS_REG(2, 0, 0, 10, 7), + ARM64_SYS_REG(2, 0, 0, 11, 4), + ARM64_SYS_REG(2, 0, 0, 11, 5), + ARM64_SYS_REG(2, 0, 0, 11, 6), + ARM64_SYS_REG(2, 0, 0, 11, 7), + ARM64_SYS_REG(2, 0, 0, 12, 4), + ARM64_SYS_REG(2, 0, 0, 12, 5), + ARM64_SYS_REG(2, 0, 0, 12, 6), + ARM64_SYS_REG(2, 0, 0, 12, 7), + ARM64_SYS_REG(2, 0, 0, 13, 4), + ARM64_SYS_REG(2, 0, 0, 13, 5), + ARM64_SYS_REG(2, 0, 0, 13, 6), + ARM64_SYS_REG(2, 0, 0, 13, 7), + ARM64_SYS_REG(2, 0, 0, 14, 4), + ARM64_SYS_REG(2, 0, 0, 14, 5), + ARM64_SYS_REG(2, 0, 0, 14, 6), + ARM64_SYS_REG(2, 0, 0, 14, 7), + ARM64_SYS_REG(2, 0, 0, 15, 4), + ARM64_SYS_REG(2, 0, 0, 15, 5), + ARM64_SYS_REG(2, 0, 0, 15, 6), + ARM64_SYS_REG(2, 0, 0, 15, 7), + ARM64_SYS_REG(2, 4, 0, 7, 0), /* DBGVCR32_EL2 */ + ARM64_SYS_REG(3, 0, 0, 0, 5), /* MPIDR_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 0), /* ID_PFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 1), /* ID_PFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 2), /* ID_DFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 3), /* ID_AFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 4), /* ID_MMFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 5), /* ID_MMFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 6), /* ID_MMFR2_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 7), /* ID_MMFR3_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 0), /* ID_ISAR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 1), /* ID_ISAR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 2), /* ID_ISAR2_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 3), /* ID_ISAR3_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 4), /* ID_ISAR4_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 5), /* ID_ISAR5_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 6), /* ID_MMFR4_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 7), /* ID_ISAR6_EL1 */ + ARM64_SYS_REG(3, 0, 0, 3, 0), /* MVFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 3, 1), /* MVFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 3, 2), /* MVFR2_EL1 */ + ARM64_SYS_REG(3, 0, 0, 3, 3), + ARM64_SYS_REG(3, 0, 0, 3, 4), /* ID_PFR2_EL1 */ + ARM64_SYS_REG(3, 0, 0, 3, 5), /* ID_DFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 3, 6), /* ID_MMFR5_EL1 */ + ARM64_SYS_REG(3, 0, 0, 3, 7), + ARM64_SYS_REG(3, 0, 0, 4, 0), /* ID_AA64PFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 4, 1), /* ID_AA64PFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 4, 2), + ARM64_SYS_REG(3, 0, 0, 4, 3), + ARM64_SYS_REG(3, 0, 0, 4, 4), /* ID_AA64ZFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 4, 5), + ARM64_SYS_REG(3, 0, 0, 4, 6), + ARM64_SYS_REG(3, 0, 0, 4, 7), + ARM64_SYS_REG(3, 0, 0, 5, 0), /* ID_AA64DFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 5, 1), /* ID_AA64DFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 5, 2), + ARM64_SYS_REG(3, 0, 0, 5, 3), + ARM64_SYS_REG(3, 0, 0, 5, 4), /* ID_AA64AFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 5, 5), /* ID_AA64AFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 5, 6), + ARM64_SYS_REG(3, 0, 0, 5, 7), + ARM64_SYS_REG(3, 0, 0, 6, 0), /* ID_AA64ISAR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 6, 1), /* ID_AA64ISAR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 6, 2), + ARM64_SYS_REG(3, 0, 0, 6, 3), + ARM64_SYS_REG(3, 0, 0, 6, 4), + ARM64_SYS_REG(3, 0, 0, 6, 5), + ARM64_SYS_REG(3, 0, 0, 6, 6), + ARM64_SYS_REG(3, 0, 0, 6, 7), + ARM64_SYS_REG(3, 0, 0, 7, 0), /* ID_AA64MMFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 7, 1), /* ID_AA64MMFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 7, 2), /* ID_AA64MMFR2_EL1 */ + ARM64_SYS_REG(3, 0, 0, 7, 3), + ARM64_SYS_REG(3, 0, 0, 7, 4), + ARM64_SYS_REG(3, 0, 0, 7, 5), + ARM64_SYS_REG(3, 0, 0, 7, 6), + ARM64_SYS_REG(3, 0, 0, 7, 7), + ARM64_SYS_REG(3, 0, 1, 0, 0), /* SCTLR_EL1 */ + ARM64_SYS_REG(3, 0, 1, 0, 1), /* ACTLR_EL1 */ + ARM64_SYS_REG(3, 0, 1, 0, 2), /* CPACR_EL1 */ + ARM64_SYS_REG(3, 0, 2, 0, 0), /* TTBR0_EL1 */ + ARM64_SYS_REG(3, 0, 2, 0, 1), /* TTBR1_EL1 */ + ARM64_SYS_REG(3, 0, 2, 0, 2), /* TCR_EL1 */ + ARM64_SYS_REG(3, 0, 5, 1, 0), /* AFSR0_EL1 */ + ARM64_SYS_REG(3, 0, 5, 1, 1), /* AFSR1_EL1 */ + ARM64_SYS_REG(3, 0, 5, 2, 0), /* ESR_EL1 */ + ARM64_SYS_REG(3, 0, 6, 0, 0), /* FAR_EL1 */ + ARM64_SYS_REG(3, 0, 7, 4, 0), /* PAR_EL1 */ + ARM64_SYS_REG(3, 0, 9, 14, 1), /* PMINTENSET_EL1 */ + ARM64_SYS_REG(3, 0, 9, 14, 2), /* PMINTENCLR_EL1 */ + ARM64_SYS_REG(3, 0, 10, 2, 0), /* MAIR_EL1 */ + ARM64_SYS_REG(3, 0, 10, 3, 0), /* AMAIR_EL1 */ + ARM64_SYS_REG(3, 0, 12, 0, 0), /* VBAR_EL1 */ + ARM64_SYS_REG(3, 0, 12, 1, 1), /* DISR_EL1 */ + ARM64_SYS_REG(3, 0, 13, 0, 1), /* CONTEXTIDR_EL1 */ + ARM64_SYS_REG(3, 0, 13, 0, 4), /* TPIDR_EL1 */ + ARM64_SYS_REG(3, 0, 14, 1, 0), /* CNTKCTL_EL1 */ + ARM64_SYS_REG(3, 2, 0, 0, 0), /* CSSELR_EL1 */ + ARM64_SYS_REG(3, 3, 9, 12, 0), /* PMCR_EL0 */ + ARM64_SYS_REG(3, 3, 9, 12, 1), /* PMCNTENSET_EL0 */ + ARM64_SYS_REG(3, 3, 9, 12, 2), /* PMCNTENCLR_EL0 */ + ARM64_SYS_REG(3, 3, 9, 12, 3), /* PMOVSCLR_EL0 */ + ARM64_SYS_REG(3, 3, 9, 12, 4), /* PMSWINC_EL0 */ + ARM64_SYS_REG(3, 3, 9, 12, 5), /* PMSELR_EL0 */ + ARM64_SYS_REG(3, 3, 9, 13, 0), /* PMCCNTR_EL0 */ + ARM64_SYS_REG(3, 3, 9, 14, 0), /* PMUSERENR_EL0 */ + ARM64_SYS_REG(3, 3, 9, 14, 3), /* PMOVSSET_EL0 */ + ARM64_SYS_REG(3, 3, 13, 0, 2), /* TPIDR_EL0 */ + ARM64_SYS_REG(3, 3, 13, 0, 3), /* TPIDRRO_EL0 */ + ARM64_SYS_REG(3, 3, 14, 8, 0), + ARM64_SYS_REG(3, 3, 14, 8, 1), + ARM64_SYS_REG(3, 3, 14, 8, 2), + ARM64_SYS_REG(3, 3, 14, 8, 3), + ARM64_SYS_REG(3, 3, 14, 8, 4), + ARM64_SYS_REG(3, 3, 14, 8, 5), + ARM64_SYS_REG(3, 3, 14, 8, 6), + ARM64_SYS_REG(3, 3, 14, 8, 7), + ARM64_SYS_REG(3, 3, 14, 9, 0), + ARM64_SYS_REG(3, 3, 14, 9, 1), + ARM64_SYS_REG(3, 3, 14, 9, 2), + ARM64_SYS_REG(3, 3, 14, 9, 3), + ARM64_SYS_REG(3, 3, 14, 9, 4), + ARM64_SYS_REG(3, 3, 14, 9, 5), + ARM64_SYS_REG(3, 3, 14, 9, 6), + ARM64_SYS_REG(3, 3, 14, 9, 7), + ARM64_SYS_REG(3, 3, 14, 10, 0), + ARM64_SYS_REG(3, 3, 14, 10, 1), + ARM64_SYS_REG(3, 3, 14, 10, 2), + ARM64_SYS_REG(3, 3, 14, 10, 3), + ARM64_SYS_REG(3, 3, 14, 10, 4), + ARM64_SYS_REG(3, 3, 14, 10, 5), + ARM64_SYS_REG(3, 3, 14, 10, 6), + ARM64_SYS_REG(3, 3, 14, 10, 7), + ARM64_SYS_REG(3, 3, 14, 11, 0), + ARM64_SYS_REG(3, 3, 14, 11, 1), + ARM64_SYS_REG(3, 3, 14, 11, 2), + ARM64_SYS_REG(3, 3, 14, 11, 3), + ARM64_SYS_REG(3, 3, 14, 11, 4), + ARM64_SYS_REG(3, 3, 14, 11, 5), + ARM64_SYS_REG(3, 3, 14, 11, 6), + ARM64_SYS_REG(3, 3, 14, 12, 0), + ARM64_SYS_REG(3, 3, 14, 12, 1), + ARM64_SYS_REG(3, 3, 14, 12, 2), + ARM64_SYS_REG(3, 3, 14, 12, 3), + ARM64_SYS_REG(3, 3, 14, 12, 4), + ARM64_SYS_REG(3, 3, 14, 12, 5), + ARM64_SYS_REG(3, 3, 14, 12, 6), + ARM64_SYS_REG(3, 3, 14, 12, 7), + ARM64_SYS_REG(3, 3, 14, 13, 0), + ARM64_SYS_REG(3, 3, 14, 13, 1), + ARM64_SYS_REG(3, 3, 14, 13, 2), + ARM64_SYS_REG(3, 3, 14, 13, 3), + ARM64_SYS_REG(3, 3, 14, 13, 4), + ARM64_SYS_REG(3, 3, 14, 13, 5), + ARM64_SYS_REG(3, 3, 14, 13, 6), + ARM64_SYS_REG(3, 3, 14, 13, 7), + ARM64_SYS_REG(3, 3, 14, 14, 0), + ARM64_SYS_REG(3, 3, 14, 14, 1), + ARM64_SYS_REG(3, 3, 14, 14, 2), + ARM64_SYS_REG(3, 3, 14, 14, 3), + ARM64_SYS_REG(3, 3, 14, 14, 4), + ARM64_SYS_REG(3, 3, 14, 14, 5), + ARM64_SYS_REG(3, 3, 14, 14, 6), + ARM64_SYS_REG(3, 3, 14, 14, 7), + ARM64_SYS_REG(3, 3, 14, 15, 0), + ARM64_SYS_REG(3, 3, 14, 15, 1), + ARM64_SYS_REG(3, 3, 14, 15, 2), + ARM64_SYS_REG(3, 3, 14, 15, 3), + ARM64_SYS_REG(3, 3, 14, 15, 4), + ARM64_SYS_REG(3, 3, 14, 15, 5), + ARM64_SYS_REG(3, 3, 14, 15, 6), + ARM64_SYS_REG(3, 3, 14, 15, 7), /* PMCCFILTR_EL0 */ + ARM64_SYS_REG(3, 4, 3, 0, 0), /* DACR32_EL2 */ + ARM64_SYS_REG(3, 4, 5, 0, 1), /* IFSR32_EL2 */ + ARM64_SYS_REG(3, 4, 5, 3, 0), /* FPEXC32_EL2 */ + KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | 0, + KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | 1, + KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | 2, +}; +static __u64 base_regs_n = ARRAY_SIZE(base_regs); + +static __u64 vregs[] = { + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[1]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[2]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[3]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[4]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[5]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[6]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[7]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[8]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[9]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[10]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[11]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[12]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[13]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[14]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[15]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[16]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[17]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[18]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[19]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[20]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[21]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[22]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[23]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[24]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[25]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[26]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[27]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[28]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[29]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[30]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]), +}; +static __u64 vregs_n = ARRAY_SIZE(vregs); + +static __u64 sve_regs[] = { + KVM_REG_ARM64_SVE_VLS, + KVM_REG_ARM64_SVE_ZREG(0, 0), + KVM_REG_ARM64_SVE_ZREG(1, 0), + KVM_REG_ARM64_SVE_ZREG(2, 0), + KVM_REG_ARM64_SVE_ZREG(3, 0), + KVM_REG_ARM64_SVE_ZREG(4, 0), + KVM_REG_ARM64_SVE_ZREG(5, 0), + KVM_REG_ARM64_SVE_ZREG(6, 0), + KVM_REG_ARM64_SVE_ZREG(7, 0), + KVM_REG_ARM64_SVE_ZREG(8, 0), + KVM_REG_ARM64_SVE_ZREG(9, 0), + KVM_REG_ARM64_SVE_ZREG(10, 0), + KVM_REG_ARM64_SVE_ZREG(11, 0), + KVM_REG_ARM64_SVE_ZREG(12, 0), + KVM_REG_ARM64_SVE_ZREG(13, 0), + KVM_REG_ARM64_SVE_ZREG(14, 0), + KVM_REG_ARM64_SVE_ZREG(15, 0), + KVM_REG_ARM64_SVE_ZREG(16, 0), + KVM_REG_ARM64_SVE_ZREG(17, 0), + KVM_REG_ARM64_SVE_ZREG(18, 0), + KVM_REG_ARM64_SVE_ZREG(19, 0), + KVM_REG_ARM64_SVE_ZREG(20, 0), + KVM_REG_ARM64_SVE_ZREG(21, 0), + KVM_REG_ARM64_SVE_ZREG(22, 0), + KVM_REG_ARM64_SVE_ZREG(23, 0), + KVM_REG_ARM64_SVE_ZREG(24, 0), + KVM_REG_ARM64_SVE_ZREG(25, 0), + KVM_REG_ARM64_SVE_ZREG(26, 0), + KVM_REG_ARM64_SVE_ZREG(27, 0), + KVM_REG_ARM64_SVE_ZREG(28, 0), + KVM_REG_ARM64_SVE_ZREG(29, 0), + KVM_REG_ARM64_SVE_ZREG(30, 0), + KVM_REG_ARM64_SVE_ZREG(31, 0), + KVM_REG_ARM64_SVE_PREG(0, 0), + KVM_REG_ARM64_SVE_PREG(1, 0), + KVM_REG_ARM64_SVE_PREG(2, 0), + KVM_REG_ARM64_SVE_PREG(3, 0), + KVM_REG_ARM64_SVE_PREG(4, 0), + KVM_REG_ARM64_SVE_PREG(5, 0), + KVM_REG_ARM64_SVE_PREG(6, 0), + KVM_REG_ARM64_SVE_PREG(7, 0), + KVM_REG_ARM64_SVE_PREG(8, 0), + KVM_REG_ARM64_SVE_PREG(9, 0), + KVM_REG_ARM64_SVE_PREG(10, 0), + KVM_REG_ARM64_SVE_PREG(11, 0), + KVM_REG_ARM64_SVE_PREG(12, 0), + KVM_REG_ARM64_SVE_PREG(13, 0), + KVM_REG_ARM64_SVE_PREG(14, 0), + KVM_REG_ARM64_SVE_PREG(15, 0), + KVM_REG_ARM64_SVE_FFR(0), + ARM64_SYS_REG(3, 0, 1, 2, 0), /* ZCR_EL1 */ +}; +static __u64 sve_regs_n = ARRAY_SIZE(sve_regs); + +static __u64 rejects_set[] = { +#ifdef REG_LIST_SVE + KVM_REG_ARM64_SVE_VLS, +#endif +}; +static __u64 rejects_set_n = ARRAY_SIZE(rejects_set); diff --git a/tools/testing/selftests/kvm/clear_dirty_log_test.c b/tools/testing/selftests/kvm/clear_dirty_log_test.c deleted file mode 100644 index 11672ec6f74e..000000000000 --- a/tools/testing/selftests/kvm/clear_dirty_log_test.c +++ /dev/null @@ -1,6 +0,0 @@ -#define USE_CLEAR_DIRTY_LOG -#define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (1 << 0) -#define KVM_DIRTY_LOG_INITIALLY_SET (1 << 1) -#define KVM_DIRTY_LOG_MANUAL_CAPS (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \ - KVM_DIRTY_LOG_INITIALLY_SET) -#include "dirty_log_test.c" diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c index 360cd3ea4cd6..3d96a7bfaff3 100644 --- a/tools/testing/selftests/kvm/demand_paging_test.c +++ b/tools/testing/selftests/kvm/demand_paging_test.c @@ -21,20 +21,12 @@ #include <linux/bitops.h> #include <linux/userfaultfd.h> -#include "test_util.h" -#include "kvm_util.h" +#include "perf_test_util.h" #include "processor.h" +#include "test_util.h" #ifdef __NR_userfaultfd -/* The memory slot index demand page */ -#define TEST_MEM_SLOT_INDEX 1 - -/* Default guest test virtual memory offset */ -#define DEFAULT_GUEST_TEST_MEM 0xc0000000 - -#define DEFAULT_GUEST_TEST_MEM_SIZE (1 << 30) /* 1G */ - #ifdef PRINT_PER_PAGE_UPDATES #define PER_PAGE_DEBUG(...) printf(__VA_ARGS__) #else @@ -47,77 +39,17 @@ #define PER_VCPU_DEBUG(...) _no_printf(__VA_ARGS__) #endif -#define MAX_VCPUS 512 - -/* - * Guest/Host shared variables. Ensure addr_gva2hva() and/or - * sync_global_to/from_guest() are used when accessing from - * the host. READ/WRITE_ONCE() should also be used with anything - * that may change. - */ -static uint64_t host_page_size; -static uint64_t guest_page_size; - static char *guest_data_prototype; -/* - * Guest physical memory offset of the testing memory slot. - * This will be set to the topmost valid physical address minus - * the test memory size. - */ -static 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_args { - uint64_t gva; - uint64_t pages; - - /* Only used by the host userspace part of the vCPU thread */ - int vcpu_id; - struct kvm_vm *vm; -}; - -static struct vcpu_args vcpu_args[MAX_VCPUS]; - -/* - * Continuously write to the first 8 bytes of each page in the demand paging - * memory region. - */ -static void guest_code(uint32_t vcpu_id) -{ - uint64_t gva; - uint64_t pages; - int i; - - /* Make sure vCPU args data structure is not corrupt. */ - GUEST_ASSERT(vcpu_args[vcpu_id].vcpu_id == vcpu_id); - - gva = vcpu_args[vcpu_id].gva; - pages = vcpu_args[vcpu_id].pages; - - for (i = 0; i < pages; i++) { - uint64_t addr = gva + (i * guest_page_size); - - addr &= ~(host_page_size - 1); - *(uint64_t *)addr = 0x0123456789ABCDEF; - } - - GUEST_SYNC(1); -} - static void *vcpu_worker(void *data) { int ret; - struct vcpu_args *args = (struct vcpu_args *)data; - struct kvm_vm *vm = args->vm; - int vcpu_id = args->vcpu_id; + struct vcpu_args *vcpu_args = (struct vcpu_args *)data; + int vcpu_id = vcpu_args->vcpu_id; + struct kvm_vm *vm = perf_test_args.vm; struct kvm_run *run; - struct timespec start, end, ts_diff; + struct timespec start; + struct timespec ts_diff; vcpu_args_set(vm, vcpu_id, 1, vcpu_id); run = vcpu_state(vm, vcpu_id); @@ -133,52 +65,18 @@ static void *vcpu_worker(void *data) exit_reason_str(run->exit_reason)); } - clock_gettime(CLOCK_MONOTONIC, &end); - ts_diff = timespec_sub(end, start); + ts_diff = timespec_diff_now(start); PER_VCPU_DEBUG("vCPU %d execution time: %ld.%.9lds\n", vcpu_id, ts_diff.tv_sec, ts_diff.tv_nsec); return NULL; } -#define PAGE_SHIFT_4K 12 -#define PTES_PER_4K_PT 512 - -static struct kvm_vm *create_vm(enum vm_guest_mode mode, int vcpus, - uint64_t vcpu_memory_bytes) -{ - struct kvm_vm *vm; - uint64_t pages = DEFAULT_GUEST_PHY_PAGES; - - /* Account for a few pages per-vCPU for stacks */ - pages += DEFAULT_STACK_PGS * vcpus; - - /* - * Reserve twice the ammount of memory needed to map the test region and - * the page table / stacks region, at 4k, for page tables. Do the - * calculation with 4K page size: the smallest of all archs. (e.g., 64K - * page size guest will need even less memory for page tables). - */ - pages += (2 * pages) / PTES_PER_4K_PT; - pages += ((2 * vcpus * vcpu_memory_bytes) >> PAGE_SHIFT_4K) / - PTES_PER_4K_PT; - pages = vm_adjust_num_guest_pages(mode, pages); - - pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode)); - - vm = _vm_create(mode, pages, O_RDWR); - kvm_vm_elf_load(vm, program_invocation_name, 0, 0); -#ifdef __x86_64__ - vm_create_irqchip(vm); -#endif - return vm; -} - static int handle_uffd_page_request(int uffd, uint64_t addr) { pid_t tid; struct timespec start; - struct timespec end; + struct timespec ts_diff; struct uffdio_copy copy; int r; @@ -186,7 +84,7 @@ static int handle_uffd_page_request(int uffd, uint64_t addr) copy.src = (uint64_t)guest_data_prototype; copy.dst = addr; - copy.len = host_page_size; + copy.len = perf_test_args.host_page_size; copy.mode = 0; clock_gettime(CLOCK_MONOTONIC, &start); @@ -198,12 +96,12 @@ static int handle_uffd_page_request(int uffd, uint64_t addr) return r; } - clock_gettime(CLOCK_MONOTONIC, &end); + ts_diff = timespec_diff_now(start); PER_PAGE_DEBUG("UFFDIO_COPY %d \t%ld ns\n", tid, - timespec_to_ns(timespec_sub(end, start))); + timespec_to_ns(ts_diff)); PER_PAGE_DEBUG("Paged in %ld bytes at 0x%lx from thread %d\n", - host_page_size, addr, tid); + perf_test_args.host_page_size, addr, tid); return 0; } @@ -223,7 +121,8 @@ static void *uffd_handler_thread_fn(void *arg) int pipefd = uffd_args->pipefd; useconds_t delay = uffd_args->delay; int64_t pages = 0; - struct timespec start, end, ts_diff; + struct timespec start; + struct timespec ts_diff; clock_gettime(CLOCK_MONOTONIC, &start); while (!quit_uffd_thread) { @@ -292,8 +191,7 @@ static void *uffd_handler_thread_fn(void *arg) pages++; } - clock_gettime(CLOCK_MONOTONIC, &end); - ts_diff = timespec_sub(end, start); + ts_diff = timespec_diff_now(start); PER_VCPU_DEBUG("userfaulted %ld pages over %ld.%.9lds. (%f/sec)\n", pages, ts_diff.tv_sec, ts_diff.tv_nsec, pages / ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0)); @@ -351,99 +249,54 @@ static int setup_demand_paging(struct kvm_vm *vm, } static void run_test(enum vm_guest_mode mode, bool use_uffd, - useconds_t uffd_delay, int vcpus, - uint64_t vcpu_memory_bytes) + useconds_t uffd_delay) { pthread_t *vcpu_threads; pthread_t *uffd_handler_threads = NULL; struct uffd_handler_args *uffd_args = NULL; - struct timespec start, end, ts_diff; + struct timespec start; + struct timespec ts_diff; int *pipefds = NULL; struct kvm_vm *vm; - uint64_t guest_num_pages; int vcpu_id; int r; - vm = create_vm(mode, vcpus, vcpu_memory_bytes); - - guest_page_size = vm_get_page_size(vm); - - TEST_ASSERT(vcpu_memory_bytes % guest_page_size == 0, - "Guest memory size is not guest page size aligned."); - - guest_num_pages = (vcpus * vcpu_memory_bytes) / guest_page_size; - guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages); - - /* - * If there should be more memory in the guest test region than there - * can be pages in the guest, it will definitely cause problems. - */ - TEST_ASSERT(guest_num_pages < vm_get_max_gfn(vm), - "Requested more guest memory than address space allows.\n" - " guest pages: %lx max gfn: %x vcpus: %d wss: %lx]\n", - guest_num_pages, vm_get_max_gfn(vm), vcpus, - vcpu_memory_bytes); - - host_page_size = getpagesize(); - TEST_ASSERT(vcpu_memory_bytes % host_page_size == 0, - "Guest memory size is not host page size aligned."); + vm = create_vm(mode, nr_vcpus, guest_percpu_mem_size); - guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) * - guest_page_size; - guest_test_phys_mem &= ~(host_page_size - 1); + perf_test_args.wr_fract = 1; -#ifdef __s390x__ - /* Align to 1M (segment size) */ - guest_test_phys_mem &= ~((1 << 20) - 1); -#endif - - pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem); - - /* Add an extra memory slot for testing demand paging */ - vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, - guest_test_phys_mem, - TEST_MEM_SLOT_INDEX, - guest_num_pages, 0); - - /* Do mapping for the demand paging memory slot */ - virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages, 0); - - ucall_init(vm, NULL); - - guest_data_prototype = malloc(host_page_size); + guest_data_prototype = malloc(perf_test_args.host_page_size); TEST_ASSERT(guest_data_prototype, "Failed to allocate buffer for guest data pattern"); - memset(guest_data_prototype, 0xAB, host_page_size); + memset(guest_data_prototype, 0xAB, perf_test_args.host_page_size); - vcpu_threads = malloc(vcpus * sizeof(*vcpu_threads)); + vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads)); TEST_ASSERT(vcpu_threads, "Memory allocation failed"); + add_vcpus(vm, nr_vcpus, guest_percpu_mem_size); + if (use_uffd) { uffd_handler_threads = - malloc(vcpus * sizeof(*uffd_handler_threads)); + malloc(nr_vcpus * sizeof(*uffd_handler_threads)); TEST_ASSERT(uffd_handler_threads, "Memory allocation failed"); - uffd_args = malloc(vcpus * sizeof(*uffd_args)); + uffd_args = malloc(nr_vcpus * sizeof(*uffd_args)); TEST_ASSERT(uffd_args, "Memory allocation failed"); - pipefds = malloc(sizeof(int) * vcpus * 2); + pipefds = malloc(sizeof(int) * nr_vcpus * 2); TEST_ASSERT(pipefds, "Unable to allocate memory for pipefd"); - } - - for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { - vm_paddr_t vcpu_gpa; - void *vcpu_hva; - vm_vcpu_add_default(vm, vcpu_id, guest_code); + for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { + vm_paddr_t vcpu_gpa; + void *vcpu_hva; - vcpu_gpa = guest_test_phys_mem + (vcpu_id * vcpu_memory_bytes); - PER_VCPU_DEBUG("Added VCPU %d with test mem gpa [%lx, %lx)\n", - vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_memory_bytes); + vcpu_gpa = guest_test_phys_mem + (vcpu_id * guest_percpu_mem_size); + PER_VCPU_DEBUG("Added VCPU %d with test mem gpa [%lx, %lx)\n", + vcpu_id, vcpu_gpa, vcpu_gpa + guest_percpu_mem_size); - /* Cache the HVA pointer of the region */ - vcpu_hva = addr_gpa2hva(vm, vcpu_gpa); + /* Cache the HVA pointer of the region */ + vcpu_hva = addr_gpa2hva(vm, vcpu_gpa); - if (use_uffd) { /* * Set up user fault fd to handle demand paging * requests. @@ -456,53 +309,41 @@ static void run_test(enum vm_guest_mode mode, bool use_uffd, &uffd_handler_threads[vcpu_id], pipefds[vcpu_id * 2], uffd_delay, &uffd_args[vcpu_id], - vcpu_hva, vcpu_memory_bytes); + vcpu_hva, guest_percpu_mem_size); if (r < 0) exit(-r); } - -#ifdef __x86_64__ - vcpu_set_cpuid(vm, vcpu_id, kvm_get_supported_cpuid()); -#endif - - vcpu_args[vcpu_id].vm = vm; - vcpu_args[vcpu_id].vcpu_id = vcpu_id; - vcpu_args[vcpu_id].gva = guest_test_virt_mem + - (vcpu_id * vcpu_memory_bytes); - vcpu_args[vcpu_id].pages = vcpu_memory_bytes / guest_page_size; } /* Export the shared variables to the guest */ - sync_global_to_guest(vm, host_page_size); - sync_global_to_guest(vm, guest_page_size); - sync_global_to_guest(vm, vcpu_args); + 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 < vcpus; vcpu_id++) { + for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker, - &vcpu_args[vcpu_id]); + &perf_test_args.vcpu_args[vcpu_id]); } pr_info("Started all vCPUs\n"); /* Wait for the vcpu threads to quit */ - for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { + 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); } - pr_info("All vCPU threads joined\n"); + ts_diff = timespec_diff_now(start); - clock_gettime(CLOCK_MONOTONIC, &end); + pr_info("All vCPU threads joined\n"); if (use_uffd) { char c; /* Tell the user fault fd handler threads to quit */ - for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { + for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { r = write(pipefds[vcpu_id * 2 + 1], &c, 1); TEST_ASSERT(r == 1, "Unable to write to pipefd"); @@ -510,11 +351,11 @@ static void run_test(enum vm_guest_mode mode, bool use_uffd, } } - ts_diff = timespec_sub(end, start); pr_info("Total guest execution time: %ld.%.9lds\n", ts_diff.tv_sec, ts_diff.tv_nsec); pr_info("Overall demand paging rate: %f pgs/sec\n", - guest_num_pages / ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0)); + perf_test_args.vcpu_args[0].pages * nr_vcpus / + ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0)); ucall_uninit(vm); kvm_vm_free(vm); @@ -568,9 +409,8 @@ static void help(char *name) int main(int argc, char *argv[]) { + int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS); bool mode_selected = false; - uint64_t vcpu_memory_bytes = DEFAULT_GUEST_TEST_MEM_SIZE; - int vcpus = 1; unsigned int mode; int opt, i; bool use_uffd = false; @@ -619,15 +459,12 @@ int main(int argc, char *argv[]) "A negative UFFD delay is not supported."); break; case 'b': - vcpu_memory_bytes = parse_size(optarg); + guest_percpu_mem_size = parse_size(optarg); break; case 'v': - vcpus = atoi(optarg); - TEST_ASSERT(vcpus > 0, - "Must have a positive number of vCPUs"); - TEST_ASSERT(vcpus <= MAX_VCPUS, - "This test does not currently support\n" - "more than %d vCPUs.", MAX_VCPUS); + nr_vcpus = atoi(optarg); + TEST_ASSERT(nr_vcpus > 0 && nr_vcpus <= max_vcpus, + "Invalid number of vcpus, must be between 1 and %d", max_vcpus); break; case 'h': default: @@ -642,7 +479,7 @@ int main(int argc, char *argv[]) TEST_ASSERT(guest_modes[i].supported, "Guest mode ID %d (%s) not supported.", i, vm_guest_mode_string(i)); - run_test(i, use_uffd, uffd_delay, vcpus, vcpu_memory_bytes); + run_test(i, use_uffd, uffd_delay); } return 0; diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c new file mode 100644 index 000000000000..85c9b8f73142 --- /dev/null +++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c @@ -0,0 +1,376 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KVM dirty page logging performance test + * + * Based on dirty_log_test.c + * + * Copyright (C) 2018, Red Hat, Inc. + * Copyright (C) 2020, Google, Inc. + */ + +#define _GNU_SOURCE /* for program_invocation_name */ + +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <time.h> +#include <pthread.h> +#include <linux/bitmap.h> +#include <linux/bitops.h> + +#include "kvm_util.h" +#include "perf_test_util.h" +#include "processor.h" +#include "test_util.h" + +/* How many host loops to run by default (one KVM_GET_DIRTY_LOG for each loop)*/ +#define TEST_HOST_LOOP_N 2UL + +/* Host variables */ +static bool host_quit; +static uint64_t iteration; +static uint64_t vcpu_last_completed_iteration[MAX_VCPUS]; + +static void *vcpu_worker(void *data) +{ + int ret; + struct kvm_vm *vm = perf_test_args.vm; + uint64_t pages_count = 0; + struct kvm_run *run; + struct timespec start; + struct timespec ts_diff; + struct timespec total = (struct timespec){0}; + struct timespec avg; + struct vcpu_args *vcpu_args = (struct vcpu_args *)data; + int vcpu_id = vcpu_args->vcpu_id; + + vcpu_args_set(vm, vcpu_id, 1, vcpu_id); + run = vcpu_state(vm, vcpu_id); + + while (!READ_ONCE(host_quit)) { + uint64_t current_iteration = READ_ONCE(iteration); + + clock_gettime(CLOCK_MONOTONIC, &start); + ret = _vcpu_run(vm, vcpu_id); + ts_diff = timespec_diff_now(start); + + TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret); + TEST_ASSERT(get_ucall(vm, vcpu_id, NULL) == UCALL_SYNC, + "Invalid guest sync status: exit_reason=%s\n", + exit_reason_str(run->exit_reason)); + + pr_debug("Got sync event from vCPU %d\n", vcpu_id); + vcpu_last_completed_iteration[vcpu_id] = current_iteration; + pr_debug("vCPU %d updated last completed iteration to %lu\n", + vcpu_id, vcpu_last_completed_iteration[vcpu_id]); + + if (current_iteration) { + pages_count += vcpu_args->pages; + total = timespec_add(total, ts_diff); + pr_debug("vCPU %d iteration %lu dirty memory time: %ld.%.9lds\n", + vcpu_id, current_iteration, ts_diff.tv_sec, + ts_diff.tv_nsec); + } else { + pr_debug("vCPU %d iteration %lu populate memory time: %ld.%.9lds\n", + vcpu_id, current_iteration, ts_diff.tv_sec, + ts_diff.tv_nsec); + } + + while (current_iteration == READ_ONCE(iteration) && + !READ_ONCE(host_quit)) {} + } + + avg = timespec_div(total, vcpu_last_completed_iteration[vcpu_id]); + pr_debug("\nvCPU %d dirtied 0x%lx pages over %lu 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; +} + +#ifdef USE_CLEAR_DIRTY_LOG +static u64 dirty_log_manual_caps; +#endif + +static void run_test(enum vm_guest_mode mode, unsigned long iterations, + uint64_t phys_offset, int wr_fract) +{ + pthread_t *vcpu_threads; + struct kvm_vm *vm; + unsigned long *bmap; + uint64_t guest_num_pages; + uint64_t host_num_pages; + int vcpu_id; + struct timespec start; + struct timespec ts_diff; + struct timespec get_dirty_log_total = (struct timespec){0}; + struct timespec vcpu_dirty_total = (struct timespec){0}; + struct timespec avg; +#ifdef USE_CLEAR_DIRTY_LOG + struct kvm_enable_cap cap = {}; + struct timespec clear_dirty_log_total = (struct timespec){0}; +#endif + + vm = create_vm(mode, nr_vcpus, guest_percpu_mem_size); + + perf_test_args.wr_fract = 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); + host_num_pages = vm_num_host_pages(mode, guest_num_pages); + bmap = bitmap_alloc(host_num_pages); + +#ifdef USE_CLEAR_DIRTY_LOG + cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2; + cap.args[0] = dirty_log_manual_caps; + vm_enable_cap(vm, &cap); +#endif + + vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads)); + TEST_ASSERT(vcpu_threads, "Memory allocation failed"); + + add_vcpus(vm, nr_vcpus, guest_percpu_mem_size); + + 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++) { + pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker, + &perf_test_args.vcpu_args[vcpu_id]); + } + + /* Allow the vCPU to populate memory */ + pr_debug("Starting iteration %lu - Populating\n", iteration); + while (READ_ONCE(vcpu_last_completed_iteration[vcpu_id]) != iteration) + pr_debug("Waiting for vcpu_last_completed_iteration == %lu\n", + iteration); + + ts_diff = timespec_diff_now(start); + pr_info("Populate memory time: %ld.%.9lds\n", + ts_diff.tv_sec, ts_diff.tv_nsec); + + /* Enable dirty logging */ + clock_gettime(CLOCK_MONOTONIC, &start); + vm_mem_region_set_flags(vm, TEST_MEM_SLOT_INDEX, + KVM_MEM_LOG_DIRTY_PAGES); + ts_diff = timespec_diff_now(start); + pr_info("Enabling dirty logging time: %ld.%.9lds\n\n", + ts_diff.tv_sec, ts_diff.tv_nsec); + + while (iteration < iterations) { + /* + * Incrementing the iteration number will start the vCPUs + * dirtying memory again. + */ + clock_gettime(CLOCK_MONOTONIC, &start); + iteration++; + + pr_debug("Starting iteration %lu\n", iteration); + for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { + while (READ_ONCE(vcpu_last_completed_iteration[vcpu_id]) != iteration) + pr_debug("Waiting for vCPU %d vcpu_last_completed_iteration == %lu\n", + vcpu_id, iteration); + } + + ts_diff = timespec_diff_now(start); + vcpu_dirty_total = timespec_add(vcpu_dirty_total, ts_diff); + pr_info("Iteration %lu dirty memory time: %ld.%.9lds\n", + iteration, ts_diff.tv_sec, ts_diff.tv_nsec); + + clock_gettime(CLOCK_MONOTONIC, &start); + kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap); + + ts_diff = timespec_diff_now(start); + get_dirty_log_total = timespec_add(get_dirty_log_total, + ts_diff); + pr_info("Iteration %lu get dirty log time: %ld.%.9lds\n", + iteration, ts_diff.tv_sec, ts_diff.tv_nsec); + +#ifdef USE_CLEAR_DIRTY_LOG + clock_gettime(CLOCK_MONOTONIC, &start); + kvm_vm_clear_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap, 0, + host_num_pages); + + ts_diff = timespec_diff_now(start); + clear_dirty_log_total = timespec_add(clear_dirty_log_total, + ts_diff); + pr_info("Iteration %lu clear dirty log time: %ld.%.9lds\n", + iteration, ts_diff.tv_sec, ts_diff.tv_nsec); +#endif + } + + /* 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); + + /* Disable dirty logging */ + clock_gettime(CLOCK_MONOTONIC, &start); + vm_mem_region_set_flags(vm, TEST_MEM_SLOT_INDEX, 0); + ts_diff = timespec_diff_now(start); + pr_info("Disabling dirty logging time: %ld.%.9lds\n", + ts_diff.tv_sec, ts_diff.tv_nsec); + + avg = timespec_div(get_dirty_log_total, iterations); + pr_info("Get dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n", + iterations, get_dirty_log_total.tv_sec, + get_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec); + +#ifdef USE_CLEAR_DIRTY_LOG + avg = timespec_div(clear_dirty_log_total, iterations); + pr_info("Clear dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n", + iterations, clear_dirty_log_total.tv_sec, + clear_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec); +#endif + + free(bmap); + free(vcpu_threads); + ucall_uninit(vm); + kvm_vm_free(vm); +} + +struct guest_mode { + bool supported; + bool enabled; +}; +static struct guest_mode guest_modes[NUM_VM_MODES]; + +#define guest_mode_init(mode, supported, enabled) ({ \ + guest_modes[mode] = (struct guest_mode){ supported, enabled }; \ +}) + +static void help(char *name) +{ + int i; + + puts(""); + printf("usage: %s [-h] [-i iterations] [-p offset] " + "[-m mode] [-b vcpu bytes] [-v vcpus]\n", name); + puts(""); + printf(" -i: specify iteration counts (default: %"PRIu64")\n", + TEST_HOST_LOOP_N); + printf(" -p: specify guest physical test memory offset\n" + " Warning: a low offset can conflict with the loaded test code.\n"); + printf(" -m: specify the guest mode ID to test " + "(default: test all supported modes)\n" + " This option may be used multiple times.\n" + " Guest mode IDs:\n"); + for (i = 0; i < NUM_VM_MODES; ++i) { + printf(" %d: %s%s\n", i, vm_guest_mode_string(i), + guest_modes[i].supported ? " (supported)" : ""); + } + printf(" -b: specify the size of the memory region which should be\n" + " dirtied by each vCPU. e.g. 10M or 3G.\n" + " (default: 1G)\n"); + printf(" -f: specify the fraction of pages which should be written to\n" + " as opposed to simply read, in the form\n" + " 1/<fraction of pages to write>.\n" + " (default: 1 i.e. all pages are written to.)\n"); + printf(" -v: specify the number of vCPUs to run.\n"); + puts(""); + exit(0); +} + +int main(int argc, char *argv[]) +{ + unsigned long iterations = TEST_HOST_LOOP_N; + bool mode_selected = false; + uint64_t phys_offset = 0; + unsigned int mode; + int opt, i; + int wr_fract = 1; + +#ifdef USE_CLEAR_DIRTY_LOG + dirty_log_manual_caps = + kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2); + if (!dirty_log_manual_caps) { + print_skip("KVM_CLEAR_DIRTY_LOG not available"); + exit(KSFT_SKIP); + } + dirty_log_manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | + KVM_DIRTY_LOG_INITIALLY_SET); +#endif + +#ifdef __x86_64__ + guest_mode_init(VM_MODE_PXXV48_4K, true, true); +#endif +#ifdef __aarch64__ + guest_mode_init(VM_MODE_P40V48_4K, true, true); + guest_mode_init(VM_MODE_P40V48_64K, true, true); + + { + unsigned int limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE); + + if (limit >= 52) + guest_mode_init(VM_MODE_P52V48_64K, true, true); + if (limit >= 48) { + guest_mode_init(VM_MODE_P48V48_4K, true, true); + guest_mode_init(VM_MODE_P48V48_64K, true, true); + } + } +#endif +#ifdef __s390x__ + guest_mode_init(VM_MODE_P40V48_4K, true, true); +#endif + + while ((opt = getopt(argc, argv, "hi:p:m:b:f:v:")) != -1) { + switch (opt) { + case 'i': + iterations = strtol(optarg, NULL, 10); + break; + case 'p': + phys_offset = strtoull(optarg, NULL, 0); + break; + case 'm': + if (!mode_selected) { + for (i = 0; i < NUM_VM_MODES; ++i) + guest_modes[i].enabled = false; + mode_selected = true; + } + mode = strtoul(optarg, NULL, 10); + TEST_ASSERT(mode < NUM_VM_MODES, + "Guest mode ID %d too big", mode); + guest_modes[mode].enabled = true; + break; + case 'b': + guest_percpu_mem_size = parse_size(optarg); + break; + case 'f': + wr_fract = atoi(optarg); + TEST_ASSERT(wr_fract >= 1, + "Write fraction cannot be less than one"); + break; + case 'v': + nr_vcpus = atoi(optarg); + TEST_ASSERT(nr_vcpus > 0, + "Must have a positive number of vCPUs"); + TEST_ASSERT(nr_vcpus <= MAX_VCPUS, + "This test does not currently support\n" + "more than %d vCPUs.", MAX_VCPUS); + break; + case 'h': + default: + help(argv[0]); + break; + } + } + + TEST_ASSERT(iterations >= 2, "The test should have at least two iterations"); + + pr_info("Test iterations: %"PRIu64"\n", iterations); + + for (i = 0; i < NUM_VM_MODES; ++i) { + if (!guest_modes[i].enabled) + continue; + TEST_ASSERT(guest_modes[i].supported, + "Guest mode ID %d (%s) not supported.", + i, vm_guest_mode_string(i)); + run_test(i, iterations, phys_offset, wr_fract); + } + + return 0; +} diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c index 752ec158ac59..54da9cc20db4 100644 --- a/tools/testing/selftests/kvm/dirty_log_test.c +++ b/tools/testing/selftests/kvm/dirty_log_test.c @@ -128,6 +128,78 @@ static uint64_t host_dirty_count; static uint64_t host_clear_count; static uint64_t host_track_next_count; +enum log_mode_t { + /* Only use KVM_GET_DIRTY_LOG for logging */ + LOG_MODE_DIRTY_LOG = 0, + + /* Use both KVM_[GET|CLEAR]_DIRTY_LOG for logging */ + LOG_MODE_CLEAR_LOG = 1, + + LOG_MODE_NUM, + + /* Run all supported modes */ + LOG_MODE_ALL = LOG_MODE_NUM, +}; + +/* Mode of logging to test. Default is to run all supported modes */ +static enum log_mode_t host_log_mode_option = LOG_MODE_ALL; +/* Logging mode for current run */ +static enum log_mode_t host_log_mode; + +static bool clear_log_supported(void) +{ + return kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2); +} + +static void clear_log_create_vm_done(struct kvm_vm *vm) +{ + struct kvm_enable_cap cap = {}; + u64 manual_caps; + + manual_caps = kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2); + TEST_ASSERT(manual_caps, "MANUAL_CAPS is zero!"); + manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | + KVM_DIRTY_LOG_INITIALLY_SET); + cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2; + cap.args[0] = manual_caps; + vm_enable_cap(vm, &cap); +} + +static void dirty_log_collect_dirty_pages(struct kvm_vm *vm, int slot, + void *bitmap, uint32_t num_pages) +{ + kvm_vm_get_dirty_log(vm, slot, bitmap); +} + +static void clear_log_collect_dirty_pages(struct kvm_vm *vm, int slot, + void *bitmap, uint32_t num_pages) +{ + kvm_vm_get_dirty_log(vm, slot, bitmap); + kvm_vm_clear_dirty_log(vm, slot, bitmap, 0, num_pages); +} + +struct log_mode { + const char *name; + /* Return true if this mode is supported, otherwise false */ + bool (*supported)(void); + /* Hook when the vm creation is done (before vcpu creation) */ + void (*create_vm_done)(struct kvm_vm *vm); + /* Hook to collect the dirty pages into the bitmap provided */ + void (*collect_dirty_pages) (struct kvm_vm *vm, int slot, + void *bitmap, uint32_t num_pages); +} log_modes[LOG_MODE_NUM] = { + { + .name = "dirty-log", + .collect_dirty_pages = dirty_log_collect_dirty_pages, + }, + { + .name = "clear-log", + .supported = clear_log_supported, + .create_vm_done = clear_log_create_vm_done, + .collect_dirty_pages = clear_log_collect_dirty_pages, + }, +}; + /* * We use this bitmap to track some pages that should have its dirty * bit set in the _next_ iteration. For example, if we detected the @@ -137,6 +209,44 @@ static uint64_t host_track_next_count; */ static unsigned long *host_bmap_track; +static void log_modes_dump(void) +{ + int i; + + printf("all"); + for (i = 0; i < LOG_MODE_NUM; i++) + printf(", %s", log_modes[i].name); + printf("\n"); +} + +static bool log_mode_supported(void) +{ + struct log_mode *mode = &log_modes[host_log_mode]; + + if (mode->supported) + return mode->supported(); + + return true; +} + +static void log_mode_create_vm_done(struct kvm_vm *vm) +{ + struct log_mode *mode = &log_modes[host_log_mode]; + + if (mode->create_vm_done) + mode->create_vm_done(vm); +} + +static void log_mode_collect_dirty_pages(struct kvm_vm *vm, int slot, + void *bitmap, uint32_t num_pages) +{ + struct log_mode *mode = &log_modes[host_log_mode]; + + TEST_ASSERT(mode->collect_dirty_pages != NULL, + "collect_dirty_pages() is required for any log mode!"); + mode->collect_dirty_pages(vm, slot, bitmap, num_pages); +} + static void generate_random_array(uint64_t *guest_array, uint64_t size) { uint64_t i; @@ -195,7 +305,7 @@ static void vm_dirty_log_verify(enum vm_guest_mode mode, unsigned long *bmap) page); } - if (test_bit_le(page, bmap)) { + if (test_and_clear_bit_le(page, bmap)) { host_dirty_count++; /* * If the bit is set, the value written onto @@ -252,11 +362,12 @@ static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid, pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode)); - vm = _vm_create(mode, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR); + vm = vm_create(mode, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR); kvm_vm_elf_load(vm, program_invocation_name, 0, 0); #ifdef __x86_64__ vm_create_irqchip(vm); #endif + log_mode_create_vm_done(vm); vm_vcpu_add_default(vm, vcpuid, guest_code); return vm; } @@ -264,10 +375,6 @@ static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid, #define DIRTY_MEM_BITS 30 /* 1G */ #define PAGE_SHIFT_4K 12 -#ifdef USE_CLEAR_DIRTY_LOG -static u64 dirty_log_manual_caps; -#endif - static void run_test(enum vm_guest_mode mode, unsigned long iterations, unsigned long interval, uint64_t phys_offset) { @@ -275,6 +382,12 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, struct kvm_vm *vm; unsigned long *bmap; + if (!log_mode_supported()) { + print_skip("Log mode '%s' not supported", + log_modes[host_log_mode].name); + return; + } + /* * We reserve page table for 2 times of extra dirty mem which * will definitely cover the original (1G+) test range. Here @@ -317,14 +430,6 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, bmap = bitmap_alloc(host_num_pages); host_bmap_track = bitmap_alloc(host_num_pages); -#ifdef USE_CLEAR_DIRTY_LOG - struct kvm_enable_cap cap = {}; - - cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2; - cap.args[0] = dirty_log_manual_caps; - vm_enable_cap(vm, &cap); -#endif - /* Add an extra memory slot for testing dirty logging */ vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, guest_test_phys_mem, @@ -362,11 +467,8 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, while (iteration < iterations) { /* Give the vcpu thread some time to dirty some pages */ usleep(interval * 1000); - kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap); -#ifdef USE_CLEAR_DIRTY_LOG - kvm_vm_clear_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap, 0, - host_num_pages); -#endif + log_mode_collect_dirty_pages(vm, TEST_MEM_SLOT_INDEX, + bmap, host_num_pages); vm_dirty_log_verify(mode, bmap); iteration++; sync_global_to_guest(vm, iteration); @@ -410,6 +512,9 @@ static void help(char *name) TEST_HOST_LOOP_INTERVAL); printf(" -p: specify guest physical test memory offset\n" " Warning: a low offset can conflict with the loaded test code.\n"); + printf(" -M: specify the host logging mode " + "(default: run all log modes). Supported modes: \n\t"); + log_modes_dump(); printf(" -m: specify the guest mode ID to test " "(default: test all supported modes)\n" " This option may be used multiple times.\n" @@ -429,18 +534,7 @@ int main(int argc, char *argv[]) bool mode_selected = false; uint64_t phys_offset = 0; unsigned int mode; - int opt, i; - -#ifdef USE_CLEAR_DIRTY_LOG - dirty_log_manual_caps = - kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2); - if (!dirty_log_manual_caps) { - print_skip("KVM_CLEAR_DIRTY_LOG not available"); - exit(KSFT_SKIP); - } - dirty_log_manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | - KVM_DIRTY_LOG_INITIALLY_SET); -#endif + int opt, i, j; #ifdef __x86_64__ guest_mode_init(VM_MODE_PXXV48_4K, true, true); @@ -464,7 +558,7 @@ int main(int argc, char *argv[]) guest_mode_init(VM_MODE_P40V48_4K, true, true); #endif - while ((opt = getopt(argc, argv, "hi:I:p:m:")) != -1) { + while ((opt = getopt(argc, argv, "hi:I:p:m:M:")) != -1) { switch (opt) { case 'i': iterations = strtol(optarg, NULL, 10); @@ -486,6 +580,26 @@ int main(int argc, char *argv[]) "Guest mode ID %d too big", mode); guest_modes[mode].enabled = true; break; + case 'M': + if (!strcmp(optarg, "all")) { + host_log_mode_option = LOG_MODE_ALL; + break; + } + for (i = 0; i < LOG_MODE_NUM; i++) { + if (!strcmp(optarg, log_modes[i].name)) { + pr_info("Setting log mode to: '%s'\n", + optarg); + host_log_mode_option = i; + break; + } + } + if (i == LOG_MODE_NUM) { + printf("Log mode '%s' invalid. Please choose " + "from: ", optarg); + log_modes_dump(); + exit(1); + } + break; case 'h': default: help(argv[0]); @@ -507,7 +621,18 @@ int main(int argc, char *argv[]) TEST_ASSERT(guest_modes[i].supported, "Guest mode ID %d (%s) not supported.", i, vm_guest_mode_string(i)); - run_test(i, iterations, interval, phys_offset); + if (host_log_mode_option == LOG_MODE_ALL) { + /* Run each log mode */ + for (j = 0; j < LOG_MODE_NUM; j++) { + pr_info("Testing Log Mode '%s'\n", + log_modes[j].name); + host_log_mode = j; + run_test(i, iterations, interval, phys_offset); + } + } else { + host_log_mode = host_log_mode_option; + run_test(i, iterations, interval, phys_offset); + } } return 0; diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index 919e161dd289..7d29aa786959 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -63,9 +63,11 @@ enum vm_mem_backing_src_type { int kvm_check_cap(long cap); int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap); +int vcpu_enable_cap(struct kvm_vm *vm, uint32_t vcpu_id, + struct kvm_enable_cap *cap); +void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size); struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm); -struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm); void kvm_vm_free(struct kvm_vm *vmp); void kvm_vm_restart(struct kvm_vm *vmp, int perm); void kvm_vm_release(struct kvm_vm *vmp); @@ -149,6 +151,7 @@ void vcpu_set_guest_debug(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_guest_debug *debug); void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_mp_state *mp_state); +struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vm *vm, uint32_t vcpuid); void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs); void vcpu_regs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs); @@ -294,6 +297,8 @@ int vm_create_device(struct kvm_vm *vm, struct kvm_create_device *cd); memcpy(&(g), _p, sizeof(g)); \ }) +void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid); + /* Common ucalls */ enum { UCALL_NONE, diff --git a/tools/testing/selftests/kvm/include/perf_test_util.h b/tools/testing/selftests/kvm/include/perf_test_util.h new file mode 100644 index 000000000000..2618052057b1 --- /dev/null +++ b/tools/testing/selftests/kvm/include/perf_test_util.h @@ -0,0 +1,198 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * tools/testing/selftests/kvm/include/perf_test_util.h + * + * Copyright (C) 2020, Google LLC. + */ + +#ifndef SELFTEST_KVM_PERF_TEST_UTIL_H +#define SELFTEST_KVM_PERF_TEST_UTIL_H + +#include "kvm_util.h" +#include "processor.h" + +#define MAX_VCPUS 512 + +#define PAGE_SHIFT_4K 12 +#define PTES_PER_4K_PT 512 + +#define TEST_MEM_SLOT_INDEX 1 + +/* Default guest test virtual memory offset */ +#define DEFAULT_GUEST_TEST_MEM 0xc0000000 + +#define DEFAULT_PER_VCPU_MEM_SIZE (1 << 30) /* 1G */ + +/* + * Guest physical memory offset of the testing memory slot. + * This will be set to the topmost valid physical address minus + * the test memory size. + */ +static 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; +static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE; + +/* Number of VCPUs for the test */ +static int nr_vcpus = 1; + +struct vcpu_args { + uint64_t gva; + uint64_t pages; + + /* Only used by the host userspace part of the vCPU thread */ + int vcpu_id; +}; + +struct perf_test_args { + struct kvm_vm *vm; + uint64_t host_page_size; + uint64_t guest_page_size; + int wr_fract; + + struct vcpu_args vcpu_args[MAX_VCPUS]; +}; + +static struct perf_test_args perf_test_args; + +/* + * Continuously write to the first 8 bytes of each page in the + * specified region. + */ +static void guest_code(uint32_t vcpu_id) +{ + struct vcpu_args *vcpu_args = &perf_test_args.vcpu_args[vcpu_id]; + uint64_t gva; + uint64_t pages; + int i; + + /* Make sure vCPU args data structure is not corrupt. */ + GUEST_ASSERT(vcpu_args->vcpu_id == vcpu_id); + + gva = vcpu_args->gva; + pages = vcpu_args->pages; + + while (true) { + for (i = 0; i < pages; i++) { + uint64_t addr = gva + (i * perf_test_args.guest_page_size); + + if (i % perf_test_args.wr_fract == 0) + *(uint64_t *)addr = 0x0123456789ABCDEF; + else + READ_ONCE(*(uint64_t *)addr); + } + + GUEST_SYNC(1); + } +} + +static struct kvm_vm *create_vm(enum vm_guest_mode mode, int vcpus, + uint64_t vcpu_memory_bytes) +{ + struct kvm_vm *vm; + uint64_t pages = DEFAULT_GUEST_PHY_PAGES; + uint64_t guest_num_pages; + + /* Account for a few pages per-vCPU for stacks */ + pages += DEFAULT_STACK_PGS * vcpus; + + /* + * Reserve twice the ammount of memory needed to map the test region and + * the page table / stacks region, at 4k, for page tables. Do the + * calculation with 4K page size: the smallest of all archs. (e.g., 64K + * page size guest will need even less memory for page tables). + */ + pages += (2 * pages) / PTES_PER_4K_PT; + pages += ((2 * vcpus * vcpu_memory_bytes) >> PAGE_SHIFT_4K) / + PTES_PER_4K_PT; + pages = vm_adjust_num_guest_pages(mode, pages); + + pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode)); + + vm = vm_create(mode, pages, O_RDWR); + kvm_vm_elf_load(vm, program_invocation_name, 0, 0); +#ifdef __x86_64__ + vm_create_irqchip(vm); +#endif + + perf_test_args.vm = vm; + perf_test_args.guest_page_size = vm_get_page_size(vm); + perf_test_args.host_page_size = getpagesize(); + + TEST_ASSERT(vcpu_memory_bytes % perf_test_args.guest_page_size == 0, + "Guest memory size is not guest page size aligned."); + + guest_num_pages = (vcpus * vcpu_memory_bytes) / + perf_test_args.guest_page_size; + guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages); + + /* + * If there should be more memory in the guest test region than there + * can be pages in the guest, it will definitely cause problems. + */ + TEST_ASSERT(guest_num_pages < vm_get_max_gfn(vm), + "Requested more guest memory than address space allows.\n" + " guest pages: %lx max gfn: %x vcpus: %d wss: %lx]\n", + guest_num_pages, vm_get_max_gfn(vm), vcpus, + vcpu_memory_bytes); + + TEST_ASSERT(vcpu_memory_bytes % perf_test_args.host_page_size == 0, + "Guest memory size is not host page size aligned."); + + 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); + +#ifdef __s390x__ + /* Align to 1M (segment size) */ + guest_test_phys_mem &= ~((1 << 20) - 1); +#endif + + pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem); + + /* Add an extra memory slot for testing */ + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, + guest_test_phys_mem, + TEST_MEM_SLOT_INDEX, + guest_num_pages, 0); + + /* Do mapping for the demand paging memory slot */ + virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages, 0); + + ucall_init(vm, NULL); + + return vm; +} + +static void add_vcpus(struct kvm_vm *vm, int vcpus, uint64_t vcpu_memory_bytes) +{ + vm_paddr_t vcpu_gpa; + struct vcpu_args *vcpu_args; + int vcpu_id; + + for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { + vcpu_args = &perf_test_args.vcpu_args[vcpu_id]; + + vm_vcpu_add_default(vm, vcpu_id, guest_code); + +#ifdef __x86_64__ + vcpu_set_cpuid(vm, vcpu_id, kvm_get_supported_cpuid()); +#endif + + vcpu_args->vcpu_id = vcpu_id; + 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); + pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n", + vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_memory_bytes); + } +} + +#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 5eb01bf51b86..ffffa560436b 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -64,5 +64,7 @@ int64_t timespec_to_ns(struct timespec ts); struct timespec timespec_add_ns(struct timespec ts, int64_t ns); struct timespec timespec_add(struct timespec ts1, struct timespec ts2); struct timespec timespec_sub(struct timespec ts1, struct timespec ts2); +struct timespec timespec_diff_now(struct timespec start); +struct timespec timespec_div(struct timespec ts, int divisor); #endif /* SELFTEST_KVM_TEST_UTIL_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 82b7fe16a824..8e61340b3911 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -36,6 +36,8 @@ #define X86_CR4_SMAP (1ul << 21) #define X86_CR4_PKE (1ul << 22) +#define UNEXPECTED_VECTOR_PORT 0xfff0u + /* General Registers in 64-Bit Mode */ struct gpr64_regs { u64 rax; @@ -59,7 +61,7 @@ struct gpr64_regs { struct desc64 { uint16_t limit0; uint16_t base0; - unsigned base1:8, s:1, type:4, dpl:2, p:1; + unsigned base1:8, type:4, s:1, dpl:2, p:1; unsigned limit1:4, avl:1, l:1, db:1, g:1, base2:8; uint32_t base3; uint32_t zero1; @@ -239,6 +241,11 @@ static inline struct desc_ptr get_idt(void) return idt; } +static inline void outl(uint16_t port, uint32_t value) +{ + __asm__ __volatile__("outl %%eax, %%dx" : : "d"(port), "a"(value)); +} + #define SET_XMM(__var, __xmm) \ asm volatile("movq %0, %%"#__xmm : : "r"(__var) : #__xmm) @@ -338,6 +345,35 @@ uint32_t kvm_get_cpuid_max_basic(void); uint32_t kvm_get_cpuid_max_extended(void); void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits); +struct ex_regs { + uint64_t rax, rcx, rdx, rbx; + uint64_t rbp, rsi, rdi; + uint64_t r8, r9, r10, r11; + uint64_t r12, r13, r14, r15; + uint64_t vector; + uint64_t error_code; + uint64_t rip; + uint64_t cs; + uint64_t rflags; +}; + +void vm_init_descriptor_tables(struct kvm_vm *vm); +void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid); +void vm_handle_exception(struct kvm_vm *vm, int vector, + void (*handler)(struct ex_regs *)); + +/* + * set_cpuid() - overwrites a matching cpuid entry with the provided value. + * matches based on ent->function && ent->index. returns true + * if a match was found and successfully overwritten. + * @cpuid: the kvm cpuid list to modify. + * @ent: cpuid entry to insert + */ +bool set_cpuid(struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 *ent); + +uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2, + uint64_t a3); + /* * Basic CPU control in CR0 */ diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c index 2afa6618b396..d6c32c328e9a 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/processor.c +++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c @@ -350,3 +350,7 @@ void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...) va_end(ap); } + +void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid) +{ +} diff --git a/tools/testing/selftests/kvm/lib/aarch64/ucall.c b/tools/testing/selftests/kvm/lib/aarch64/ucall.c index c8e0ec20d3bf..2f37b90ee1a9 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/ucall.c +++ b/tools/testing/selftests/kvm/lib/aarch64/ucall.c @@ -94,6 +94,9 @@ uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc) struct kvm_run *run = vcpu_state(vm, vcpu_id); struct ucall ucall = {}; + if (uc) + memset(uc, 0, sizeof(*uc)); + if (run->exit_reason == KVM_EXIT_MMIO && run->mmio.phys_addr == (uint64_t)ucall_exit_mmio_addr) { vm_vaddr_t gva; diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 3327cebc1095..126c6727a6b0 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -86,6 +86,34 @@ int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap) return ret; } +/* VCPU Enable Capability + * + * Input Args: + * vm - Virtual Machine + * vcpu_id - VCPU + * cap - Capability + * + * Output Args: None + * + * Return: On success, 0. On failure a TEST_ASSERT failure is produced. + * + * Enables a capability (KVM_CAP_*) on the VCPU. + */ +int vcpu_enable_cap(struct kvm_vm *vm, uint32_t vcpu_id, + struct kvm_enable_cap *cap) +{ + struct vcpu *vcpu = vcpu_find(vm, vcpu_id); + int r; + + TEST_ASSERT(vcpu, "cannot find vcpu %d", vcpu_id); + + r = ioctl(vcpu->fd, KVM_ENABLE_CAP, cap); + TEST_ASSERT(!r, "KVM_ENABLE_CAP vCPU ioctl failed,\n" + " rc: %i, errno: %i", r, errno); + + return r; +} + static void vm_open(struct kvm_vm *vm, int perm) { vm->kvm_fd = open(KVM_DEV_PATH, perm); @@ -152,7 +180,7 @@ _Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) * descriptor to control the created VM is created with the permissions * given by perm (e.g. O_RDWR). */ -struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) +struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) { struct kvm_vm *vm; @@ -243,11 +271,6 @@ struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) return vm; } -struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) -{ - return _vm_create(mode, phy_pages, perm); -} - /* * VM Restart * @@ -1204,6 +1227,9 @@ int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid) do { rc = ioctl(vcpu->fd, KVM_RUN, NULL); } while (rc == -1 && errno == EINTR); + + assert_on_unhandled_exception(vm, vcpuid); + return rc; } @@ -1261,6 +1287,35 @@ void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid, } /* + * VM VCPU Get Reg List + * + * Input Args: + * vm - Virtual Machine + * vcpuid - VCPU ID + * + * Output Args: + * None + * + * Return: + * A pointer to an allocated struct kvm_reg_list + * + * Get the list of guest registers which are supported for + * KVM_GET_ONE_REG/KVM_SET_ONE_REG calls + */ +struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vm *vm, uint32_t vcpuid) +{ + struct kvm_reg_list reg_list_n = { .n = 0 }, *reg_list; + int ret; + + ret = _vcpu_ioctl(vm, vcpuid, KVM_GET_REG_LIST, ®_list_n); + TEST_ASSERT(ret == -1 && errno == E2BIG, "KVM_GET_REG_LIST n=0"); + reg_list = calloc(1, sizeof(*reg_list) + reg_list_n.n * sizeof(__u64)); + reg_list->n = reg_list_n.n; + vcpu_ioctl(vm, vcpuid, KVM_GET_REG_LIST, reg_list); + return reg_list; +} + +/* * VM VCPU Regs Get * * Input Args: diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h index 2ef446520748..f07d383d03a1 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h +++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h @@ -50,6 +50,8 @@ struct kvm_vm { vm_paddr_t pgd; vm_vaddr_t gdt; vm_vaddr_t tss; + vm_vaddr_t idt; + vm_vaddr_t handlers; }; struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid); diff --git a/tools/testing/selftests/kvm/lib/s390x/processor.c b/tools/testing/selftests/kvm/lib/s390x/processor.c index a88c5d665725..7349bb2e1a24 100644 --- a/tools/testing/selftests/kvm/lib/s390x/processor.c +++ b/tools/testing/selftests/kvm/lib/s390x/processor.c @@ -241,3 +241,7 @@ void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent) fprintf(stream, "%*spstate: psw: 0x%.16llx:0x%.16llx\n", indent, "", vcpu->state->psw_mask, vcpu->state->psw_addr); } + +void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid) +{ +} diff --git a/tools/testing/selftests/kvm/lib/s390x/ucall.c b/tools/testing/selftests/kvm/lib/s390x/ucall.c index fd589dc9bfab..9d3b0f15249a 100644 --- a/tools/testing/selftests/kvm/lib/s390x/ucall.c +++ b/tools/testing/selftests/kvm/lib/s390x/ucall.c @@ -38,6 +38,9 @@ uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc) struct kvm_run *run = vcpu_state(vm, vcpu_id); struct ucall ucall = {}; + if (uc) + memset(uc, 0, sizeof(*uc)); + if (run->exit_reason == KVM_EXIT_S390_SIEIC && run->s390_sieic.icptcode == 4 && (run->s390_sieic.ipa >> 8) == 0x83 && /* 0x83 means DIAGNOSE */ diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c index 689e97c27ee2..8e04c0b1608e 100644 --- a/tools/testing/selftests/kvm/lib/test_util.c +++ b/tools/testing/selftests/kvm/lib/test_util.c @@ -4,10 +4,13 @@ * * Copyright (C) 2020, Google LLC. */ -#include <stdlib.h> + +#include <assert.h> #include <ctype.h> #include <limits.h> -#include <assert.h> +#include <stdlib.h> +#include <time.h> + #include "test_util.h" /* @@ -81,6 +84,21 @@ struct timespec timespec_sub(struct timespec ts1, struct timespec ts2) return timespec_add_ns((struct timespec){0}, ns1 - ns2); } +struct timespec timespec_diff_now(struct timespec start) +{ + struct timespec end; + + clock_gettime(CLOCK_MONOTONIC, &end); + return timespec_sub(end, start); +} + +struct timespec timespec_div(struct timespec ts, int divisor) +{ + int64_t ns = timespec_to_ns(ts) / divisor; + + return timespec_add_ns((struct timespec){0}, ns); +} + void print_skip(const char *fmt, ...) { va_list ap; diff --git a/tools/testing/selftests/kvm/lib/x86_64/handlers.S b/tools/testing/selftests/kvm/lib/x86_64/handlers.S new file mode 100644 index 000000000000..aaf7bc7d2ce1 --- /dev/null +++ b/tools/testing/selftests/kvm/lib/x86_64/handlers.S @@ -0,0 +1,81 @@ +handle_exception: + push %r15 + push %r14 + push %r13 + push %r12 + push %r11 + push %r10 + push %r9 + push %r8 + + push %rdi + push %rsi + push %rbp + push %rbx + push %rdx + push %rcx + push %rax + mov %rsp, %rdi + + call route_exception + + pop %rax + pop %rcx + pop %rdx + pop %rbx + pop %rbp + pop %rsi + pop %rdi + pop %r8 + pop %r9 + pop %r10 + pop %r11 + pop %r12 + pop %r13 + pop %r14 + pop %r15 + + /* Discard vector and error code. */ + add $16, %rsp + iretq + +/* + * Build the handle_exception wrappers which push the vector/error code on the + * stack and an array of pointers to those wrappers. + */ +.pushsection .rodata +.globl idt_handlers +idt_handlers: +.popsection + +.macro HANDLERS has_error from to + vector = \from + .rept \to - \from + 1 + .align 8 + + /* Fetch current address and append it to idt_handlers. */ + current_handler = . +.pushsection .rodata +.quad current_handler +.popsection + + .if ! \has_error + pushq $0 + .endif + pushq $vector + jmp handle_exception + vector = vector + 1 + .endr +.endm + +.global idt_handler_code +idt_handler_code: + HANDLERS has_error=0 from=0 to=7 + HANDLERS has_error=1 from=8 to=8 + HANDLERS has_error=0 from=9 to=9 + HANDLERS has_error=1 from=10 to=14 + HANDLERS has_error=0 from=15 to=16 + HANDLERS has_error=1 from=17 to=17 + HANDLERS has_error=0 from=18 to=255 + +.section .note.GNU-stack, "", %progbits diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index f6eb34eaa0d2..d10c5c05bdf0 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -12,9 +12,18 @@ #include "../kvm_util_internal.h" #include "processor.h" +#ifndef NUM_INTERRUPTS +#define NUM_INTERRUPTS 256 +#endif + +#define DEFAULT_CODE_SELECTOR 0x8 +#define DEFAULT_DATA_SELECTOR 0x10 + /* Minimum physical address used for virtual translation tables. */ #define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000 +vm_vaddr_t exception_handlers; + /* Virtual translation table structure declarations */ struct pageMapL4Entry { uint64_t present:1; @@ -392,11 +401,12 @@ static void kvm_seg_fill_gdt_64bit(struct kvm_vm *vm, struct kvm_segment *segp) desc->limit0 = segp->limit & 0xFFFF; desc->base0 = segp->base & 0xFFFF; desc->base1 = segp->base >> 16; - desc->s = segp->s; desc->type = segp->type; + desc->s = segp->s; desc->dpl = segp->dpl; desc->p = segp->present; desc->limit1 = segp->limit >> 16; + desc->avl = segp->avl; desc->l = segp->l; desc->db = segp->db; desc->g = segp->g; @@ -556,9 +566,9 @@ static void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_m sregs.efer |= (EFER_LME | EFER_LMA | EFER_NX); kvm_seg_set_unusable(&sregs.ldt); - kvm_seg_set_kernel_code_64bit(vm, 0x8, &sregs.cs); - kvm_seg_set_kernel_data_64bit(vm, 0x10, &sregs.ds); - kvm_seg_set_kernel_data_64bit(vm, 0x10, &sregs.es); + kvm_seg_set_kernel_code_64bit(vm, DEFAULT_CODE_SELECTOR, &sregs.cs); + kvm_seg_set_kernel_data_64bit(vm, DEFAULT_DATA_SELECTOR, &sregs.ds); + kvm_seg_set_kernel_data_64bit(vm, DEFAULT_DATA_SELECTOR, &sregs.es); kvm_setup_tss_64bit(vm, &sregs.tr, 0x18, gdt_memslot, pgd_memslot); break; @@ -1118,3 +1128,131 @@ void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits) *va_bits = (entry->eax >> 8) & 0xff; } } + +struct idt_entry { + uint16_t offset0; + uint16_t selector; + uint16_t ist : 3; + uint16_t : 5; + uint16_t type : 4; + uint16_t : 1; + uint16_t dpl : 2; + uint16_t p : 1; + uint16_t offset1; + uint32_t offset2; uint32_t reserved; +}; + +static void set_idt_entry(struct kvm_vm *vm, int vector, unsigned long addr, + int dpl, unsigned short selector) +{ + struct idt_entry *base = + (struct idt_entry *)addr_gva2hva(vm, vm->idt); + struct idt_entry *e = &base[vector]; + + memset(e, 0, sizeof(*e)); + e->offset0 = addr; + e->selector = selector; + e->ist = 0; + e->type = 14; + e->dpl = dpl; + e->p = 1; + e->offset1 = addr >> 16; + e->offset2 = addr >> 32; +} + +void kvm_exit_unexpected_vector(uint32_t value) +{ + outl(UNEXPECTED_VECTOR_PORT, value); +} + +void route_exception(struct ex_regs *regs) +{ + typedef void(*handler)(struct ex_regs *); + handler *handlers = (handler *)exception_handlers; + + if (handlers && handlers[regs->vector]) { + handlers[regs->vector](regs); + return; + } + + kvm_exit_unexpected_vector(regs->vector); +} + +void vm_init_descriptor_tables(struct kvm_vm *vm) +{ + extern void *idt_handlers; + int i; + + vm->idt = vm_vaddr_alloc(vm, getpagesize(), 0x2000, 0, 0); + vm->handlers = vm_vaddr_alloc(vm, 256 * sizeof(void *), 0x2000, 0, 0); + /* Handlers have the same address in both address spaces.*/ + for (i = 0; i < NUM_INTERRUPTS; i++) + set_idt_entry(vm, i, (unsigned long)(&idt_handlers)[i], 0, + DEFAULT_CODE_SELECTOR); +} + +void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid) +{ + struct kvm_sregs sregs; + + vcpu_sregs_get(vm, vcpuid, &sregs); + sregs.idt.base = vm->idt; + sregs.idt.limit = NUM_INTERRUPTS * sizeof(struct idt_entry) - 1; + sregs.gdt.base = vm->gdt; + sregs.gdt.limit = getpagesize() - 1; + kvm_seg_set_kernel_data_64bit(NULL, DEFAULT_DATA_SELECTOR, &sregs.gs); + vcpu_sregs_set(vm, vcpuid, &sregs); + *(vm_vaddr_t *)addr_gva2hva(vm, (vm_vaddr_t)(&exception_handlers)) = vm->handlers; +} + +void vm_handle_exception(struct kvm_vm *vm, int vector, + void (*handler)(struct ex_regs *)) +{ + vm_vaddr_t *handlers = (vm_vaddr_t *)addr_gva2hva(vm, vm->handlers); + + handlers[vector] = (vm_vaddr_t)handler; +} + +void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid) +{ + if (vcpu_state(vm, vcpuid)->exit_reason == KVM_EXIT_IO + && vcpu_state(vm, vcpuid)->io.port == UNEXPECTED_VECTOR_PORT + && vcpu_state(vm, vcpuid)->io.size == 4) { + /* Grab pointer to io data */ + uint32_t *data = (void *)vcpu_state(vm, vcpuid) + + vcpu_state(vm, vcpuid)->io.data_offset; + + TEST_ASSERT(false, + "Unexpected vectored event in guest (vector:0x%x)", + *data); + } +} + +bool set_cpuid(struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 *ent) +{ + int i; + + for (i = 0; i < cpuid->nent; i++) { + struct kvm_cpuid_entry2 *cur = &cpuid->entries[i]; + + if (cur->function != ent->function || cur->index != ent->index) + continue; + + memcpy(cur, ent, sizeof(struct kvm_cpuid_entry2)); + return true; + } + + return false; +} + +uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2, + uint64_t a3) +{ + uint64_t r; + + asm volatile("vmcall" + : "=a"(r) + : "b"(a0), "c"(a1), "d"(a2), "S"(a3)); + return r; +} diff --git a/tools/testing/selftests/kvm/lib/x86_64/ucall.c b/tools/testing/selftests/kvm/lib/x86_64/ucall.c index da4d89ad5419..a3489973e290 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/ucall.c +++ b/tools/testing/selftests/kvm/lib/x86_64/ucall.c @@ -40,6 +40,9 @@ uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc) struct kvm_run *run = vcpu_state(vm, vcpu_id); struct ucall ucall = {}; + if (uc) + memset(uc, 0, sizeof(*uc)); + if (run->exit_reason == KVM_EXIT_IO && run->io.port == UCALL_PIO_PORT) { struct kvm_regs regs; diff --git a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c new file mode 100644 index 000000000000..b10a27485bad --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c @@ -0,0 +1,234 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020, Google LLC. + * + * Tests for KVM paravirtual feature disablement + */ +#include <asm/kvm_para.h> +#include <linux/kvm_para.h> +#include <stdint.h> + +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" + +extern unsigned char rdmsr_start; +extern unsigned char rdmsr_end; + +static u64 do_rdmsr(u32 idx) +{ + u32 lo, hi; + + asm volatile("rdmsr_start: rdmsr;" + "rdmsr_end:" + : "=a"(lo), "=c"(hi) + : "c"(idx)); + + return (((u64) hi) << 32) | lo; +} + +extern unsigned char wrmsr_start; +extern unsigned char wrmsr_end; + +static void do_wrmsr(u32 idx, u64 val) +{ + u32 lo, hi; + + lo = val; + hi = val >> 32; + + asm volatile("wrmsr_start: wrmsr;" + "wrmsr_end:" + : : "a"(lo), "c"(idx), "d"(hi)); +} + +static int nr_gp; + +static void guest_gp_handler(struct ex_regs *regs) +{ + unsigned char *rip = (unsigned char *)regs->rip; + bool r, w; + + r = rip == &rdmsr_start; + w = rip == &wrmsr_start; + GUEST_ASSERT(r || w); + + nr_gp++; + + if (r) + regs->rip = (uint64_t)&rdmsr_end; + else + regs->rip = (uint64_t)&wrmsr_end; +} + +struct msr_data { + uint32_t idx; + const char *name; +}; + +#define TEST_MSR(msr) { .idx = msr, .name = #msr } +#define UCALL_PR_MSR 0xdeadbeef +#define PR_MSR(msr) ucall(UCALL_PR_MSR, 1, msr) + +/* + * KVM paravirtual msrs to test. Expect a #GP if any of these msrs are read or + * written, as the KVM_CPUID_FEATURES leaf is cleared. + */ +static struct msr_data msrs_to_test[] = { + TEST_MSR(MSR_KVM_SYSTEM_TIME), + TEST_MSR(MSR_KVM_SYSTEM_TIME_NEW), + TEST_MSR(MSR_KVM_WALL_CLOCK), + TEST_MSR(MSR_KVM_WALL_CLOCK_NEW), + TEST_MSR(MSR_KVM_ASYNC_PF_EN), + TEST_MSR(MSR_KVM_STEAL_TIME), + TEST_MSR(MSR_KVM_PV_EOI_EN), + TEST_MSR(MSR_KVM_POLL_CONTROL), + TEST_MSR(MSR_KVM_ASYNC_PF_INT), + TEST_MSR(MSR_KVM_ASYNC_PF_ACK), +}; + +static void test_msr(struct msr_data *msr) +{ + PR_MSR(msr); + do_rdmsr(msr->idx); + GUEST_ASSERT(READ_ONCE(nr_gp) == 1); + + nr_gp = 0; + do_wrmsr(msr->idx, 0); + GUEST_ASSERT(READ_ONCE(nr_gp) == 1); + nr_gp = 0; +} + +struct hcall_data { + uint64_t nr; + const char *name; +}; + +#define TEST_HCALL(hc) { .nr = hc, .name = #hc } +#define UCALL_PR_HCALL 0xdeadc0de +#define PR_HCALL(hc) ucall(UCALL_PR_HCALL, 1, hc) + +/* + * KVM hypercalls to test. Expect -KVM_ENOSYS when called, as the corresponding + * features have been cleared in KVM_CPUID_FEATURES. + */ +static struct hcall_data hcalls_to_test[] = { + TEST_HCALL(KVM_HC_KICK_CPU), + TEST_HCALL(KVM_HC_SEND_IPI), + TEST_HCALL(KVM_HC_SCHED_YIELD), +}; + +static void test_hcall(struct hcall_data *hc) +{ + uint64_t r; + + PR_HCALL(hc); + r = kvm_hypercall(hc->nr, 0, 0, 0, 0); + GUEST_ASSERT(r == -KVM_ENOSYS); +} + +static void guest_main(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(msrs_to_test); i++) { + test_msr(&msrs_to_test[i]); + } + + for (i = 0; i < ARRAY_SIZE(hcalls_to_test); i++) { + test_hcall(&hcalls_to_test[i]); + } + + GUEST_DONE(); +} + +static void clear_kvm_cpuid_features(struct kvm_cpuid2 *cpuid) +{ + struct kvm_cpuid_entry2 ent = {0}; + + ent.function = KVM_CPUID_FEATURES; + TEST_ASSERT(set_cpuid(cpuid, &ent), + "failed to clear KVM_CPUID_FEATURES leaf"); +} + +static void pr_msr(struct ucall *uc) +{ + struct msr_data *msr = (struct msr_data *)uc->args[0]; + + pr_info("testing msr: %s (%#x)\n", msr->name, msr->idx); +} + +static void pr_hcall(struct ucall *uc) +{ + struct hcall_data *hc = (struct hcall_data *)uc->args[0]; + + pr_info("testing hcall: %s (%lu)\n", hc->name, hc->nr); +} + +static void handle_abort(struct ucall *uc) +{ + TEST_FAIL("%s at %s:%ld", (const char *)uc->args[0], + __FILE__, uc->args[1]); +} + +#define VCPU_ID 0 + +static void enter_guest(struct kvm_vm *vm) +{ + struct kvm_run *run; + struct ucall uc; + int r; + + run = vcpu_state(vm, VCPU_ID); + + while (true) { + r = _vcpu_run(vm, VCPU_ID); + TEST_ASSERT(!r, "vcpu_run failed: %d\n", r); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "unexpected exit reason: %u (%s)", + run->exit_reason, exit_reason_str(run->exit_reason)); + + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_PR_MSR: + pr_msr(&uc); + break; + case UCALL_PR_HCALL: + pr_hcall(&uc); + break; + case UCALL_ABORT: + handle_abort(&uc); + return; + case UCALL_DONE: + return; + } + } +} + +int main(void) +{ + struct kvm_enable_cap cap = {0}; + struct kvm_cpuid2 *best; + struct kvm_vm *vm; + + if (!kvm_check_cap(KVM_CAP_ENFORCE_PV_FEATURE_CPUID)) { + pr_info("will skip kvm paravirt restriction tests.\n"); + return 0; + } + + vm = vm_create_default(VCPU_ID, 0, guest_main); + + cap.cap = KVM_CAP_ENFORCE_PV_FEATURE_CPUID; + cap.args[0] = 1; + vcpu_enable_cap(vm, VCPU_ID, &cap); + + best = kvm_get_supported_cpuid(); + clear_kvm_cpuid_features(best); + vcpu_set_cpuid(vm, VCPU_ID, best); + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vm, VCPU_ID); + vm_handle_exception(vm, GP_VECTOR, guest_gp_handler); + + enter_guest(vm); + kvm_vm_free(vm); +} diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index 30848ca36555..a5ce26d548e4 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -136,7 +136,7 @@ endif ifeq ($(OVERRIDE_TARGETS),) LOCAL_HDRS := $(selfdir)/kselftest_harness.h $(selfdir)/kselftest.h $(OUTPUT)/%:%.c $(LOCAL_HDRS) - $(LINK.c) $^ $(LDLIBS) -o $@ + $(LINK.c) $(filter-out $(LOCAL_HDRS),$^) $(LDLIBS) -o $@ $(OUTPUT)/%.o:%.S $(COMPILE.S) $^ -o $@ diff --git a/tools/testing/selftests/pidfd/config b/tools/testing/selftests/pidfd/config index bb11de90c0c9..f6f2965e17af 100644 --- a/tools/testing/selftests/pidfd/config +++ b/tools/testing/selftests/pidfd/config @@ -4,3 +4,4 @@ CONFIG_USER_NS=y CONFIG_PID_NS=y CONFIG_NET_NS=y CONFIG_CGROUPS=y +CONFIG_CHECKPOINT_RESTORE=y diff --git a/tools/testing/selftests/pidfd/pidfd_getfd_test.c b/tools/testing/selftests/pidfd/pidfd_getfd_test.c index 7758c98be015..0930e2411dfb 100644 --- a/tools/testing/selftests/pidfd/pidfd_getfd_test.c +++ b/tools/testing/selftests/pidfd/pidfd_getfd_test.c @@ -204,7 +204,10 @@ TEST_F(child, fetch_fd) fd = sys_pidfd_getfd(self->pidfd, self->remote_fd, 0); ASSERT_GE(fd, 0); - EXPECT_EQ(0, sys_kcmp(getpid(), self->pid, KCMP_FILE, fd, self->remote_fd)); + ret = sys_kcmp(getpid(), self->pid, KCMP_FILE, fd, self->remote_fd); + if (ret < 0 && errno == ENOSYS) + SKIP(return, "kcmp() syscall not supported"); + EXPECT_EQ(ret, 0); ret = fcntl(fd, F_GETFD); ASSERT_GE(ret, 0); diff --git a/tools/testing/selftests/pidfd/pidfd_open_test.c b/tools/testing/selftests/pidfd/pidfd_open_test.c index b9fe75fc3e51..8a59438ccc78 100644 --- a/tools/testing/selftests/pidfd/pidfd_open_test.c +++ b/tools/testing/selftests/pidfd/pidfd_open_test.c @@ -6,7 +6,6 @@ #include <inttypes.h> #include <limits.h> #include <linux/types.h> -#include <linux/wait.h> #include <sched.h> #include <signal.h> #include <stdbool.h> diff --git a/tools/testing/selftests/pidfd/pidfd_poll_test.c b/tools/testing/selftests/pidfd/pidfd_poll_test.c index 4b115444dfe9..610811275357 100644 --- a/tools/testing/selftests/pidfd/pidfd_poll_test.c +++ b/tools/testing/selftests/pidfd/pidfd_poll_test.c @@ -3,7 +3,6 @@ #define _GNU_SOURCE #include <errno.h> #include <linux/types.h> -#include <linux/wait.h> #include <poll.h> #include <signal.h> #include <stdbool.h> diff --git a/tools/testing/selftests/pidfd/pidfd_setns_test.c b/tools/testing/selftests/pidfd/pidfd_setns_test.c index 1f085b922c6e..6e2f2cd400ca 100644 --- a/tools/testing/selftests/pidfd/pidfd_setns_test.c +++ b/tools/testing/selftests/pidfd/pidfd_setns_test.c @@ -16,7 +16,6 @@ #include <unistd.h> #include <sys/socket.h> #include <sys/stat.h> -#include <linux/kcmp.h> #include "pidfd.h" #include "../clone3/clone3_selftests.h" diff --git a/tools/testing/selftests/pidfd/pidfd_test.c b/tools/testing/selftests/pidfd/pidfd_test.c index c585aaa2acd8..529eb700ac26 100644 --- a/tools/testing/selftests/pidfd/pidfd_test.c +++ b/tools/testing/selftests/pidfd/pidfd_test.c @@ -330,7 +330,7 @@ static int test_pidfd_send_signal_recycled_pid_fail(void) ksft_exit_fail_msg("%s test: Failed to recycle pid %d\n", test_name, PID_RECYCLE); case PIDFD_SKIP: - ksft_print_msg("%s test: Skipping test\n", test_name); + ksft_test_result_skip("%s test: Skipping test\n", test_name); ret = 0; break; case PIDFD_XFAIL: diff --git a/tools/testing/selftests/powerpc/include/utils.h b/tools/testing/selftests/powerpc/include/utils.h index 052b5a775dc2..b7d188fc87c7 100644 --- a/tools/testing/selftests/powerpc/include/utils.h +++ b/tools/testing/selftests/powerpc/include/utils.h @@ -42,6 +42,11 @@ int perf_event_enable(int fd); int perf_event_disable(int fd); int perf_event_reset(int fd); +struct perf_event_read { + __u64 nr; + __u64 l1d_misses; +}; + #if !defined(__GLIBC_PREREQ) || !__GLIBC_PREREQ(2, 30) #include <unistd.h> #include <sys/syscall.h> diff --git a/tools/testing/selftests/powerpc/security/.gitignore b/tools/testing/selftests/powerpc/security/.gitignore index f795e06f5ae3..4257a1f156bb 100644 --- a/tools/testing/selftests/powerpc/security/.gitignore +++ b/tools/testing/selftests/powerpc/security/.gitignore @@ -1,2 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only rfi_flush +entry_flush diff --git a/tools/testing/selftests/powerpc/security/Makefile b/tools/testing/selftests/powerpc/security/Makefile index eadbbff50be6..f25e854fe370 100644 --- a/tools/testing/selftests/powerpc/security/Makefile +++ b/tools/testing/selftests/powerpc/security/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0+ -TEST_GEN_PROGS := rfi_flush spectre_v2 +TEST_GEN_PROGS := rfi_flush entry_flush spectre_v2 top_srcdir = ../../../../.. CFLAGS += -I../../../../../usr/include @@ -11,3 +11,5 @@ $(TEST_GEN_PROGS): ../harness.c ../utils.c $(OUTPUT)/spectre_v2: CFLAGS += -m64 $(OUTPUT)/spectre_v2: ../pmu/event.c branch_loops.S +$(OUTPUT)/rfi_flush: flush_utils.c +$(OUTPUT)/entry_flush: flush_utils.c diff --git a/tools/testing/selftests/powerpc/security/entry_flush.c b/tools/testing/selftests/powerpc/security/entry_flush.c new file mode 100644 index 000000000000..78cf914fa321 --- /dev/null +++ b/tools/testing/selftests/powerpc/security/entry_flush.c @@ -0,0 +1,139 @@ +// SPDX-License-Identifier: GPL-2.0+ + +/* + * Copyright 2018 IBM Corporation. + */ + +#define __SANE_USERSPACE_TYPES__ + +#include <sys/types.h> +#include <stdint.h> +#include <malloc.h> +#include <unistd.h> +#include <signal.h> +#include <stdlib.h> +#include <string.h> +#include <stdio.h> +#include "utils.h" +#include "flush_utils.h" + +int entry_flush_test(void) +{ + char *p; + int repetitions = 10; + int fd, passes = 0, iter, rc = 0; + struct perf_event_read v; + __u64 l1d_misses_total = 0; + unsigned long iterations = 100000, zero_size = 24 * 1024; + unsigned long l1d_misses_expected; + int rfi_flush_orig; + int entry_flush, entry_flush_orig; + + SKIP_IF(geteuid() != 0); + + // The PMU event we use only works on Power7 or later + SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06)); + + if (read_debugfs_file("powerpc/rfi_flush", &rfi_flush_orig) < 0) { + perror("Unable to read powerpc/rfi_flush debugfs file"); + SKIP_IF(1); + } + + if (read_debugfs_file("powerpc/entry_flush", &entry_flush_orig) < 0) { + perror("Unable to read powerpc/entry_flush debugfs file"); + SKIP_IF(1); + } + + if (rfi_flush_orig != 0) { + if (write_debugfs_file("powerpc/rfi_flush", 0) < 0) { + perror("error writing to powerpc/rfi_flush debugfs file"); + FAIL_IF(1); + } + } + + entry_flush = entry_flush_orig; + + fd = perf_event_open_counter(PERF_TYPE_RAW, /* L1d miss */ 0x400f0, -1); + FAIL_IF(fd < 0); + + p = (char *)memalign(zero_size, CACHELINE_SIZE); + + FAIL_IF(perf_event_enable(fd)); + + // disable L1 prefetching + set_dscr(1); + + iter = repetitions; + + /* + * We expect to see l1d miss for each cacheline access when entry_flush + * is set. Allow a small variation on this. + */ + l1d_misses_expected = iterations * (zero_size / CACHELINE_SIZE - 2); + +again: + FAIL_IF(perf_event_reset(fd)); + + syscall_loop(p, iterations, zero_size); + + FAIL_IF(read(fd, &v, sizeof(v)) != sizeof(v)); + + if (entry_flush && v.l1d_misses >= l1d_misses_expected) + passes++; + else if (!entry_flush && v.l1d_misses < (l1d_misses_expected / 2)) + passes++; + + l1d_misses_total += v.l1d_misses; + + while (--iter) + goto again; + + if (passes < repetitions) { + printf("FAIL (L1D misses with entry_flush=%d: %llu %c %lu) [%d/%d failures]\n", + entry_flush, l1d_misses_total, entry_flush ? '<' : '>', + entry_flush ? repetitions * l1d_misses_expected : + repetitions * l1d_misses_expected / 2, + repetitions - passes, repetitions); + rc = 1; + } else { + printf("PASS (L1D misses with entry_flush=%d: %llu %c %lu) [%d/%d pass]\n", + entry_flush, l1d_misses_total, entry_flush ? '>' : '<', + entry_flush ? repetitions * l1d_misses_expected : + repetitions * l1d_misses_expected / 2, + passes, repetitions); + } + + if (entry_flush == entry_flush_orig) { + entry_flush = !entry_flush_orig; + if (write_debugfs_file("powerpc/entry_flush", entry_flush) < 0) { + perror("error writing to powerpc/entry_flush debugfs file"); + return 1; + } + iter = repetitions; + l1d_misses_total = 0; + passes = 0; + goto again; + } + + perf_event_disable(fd); + close(fd); + + set_dscr(0); + + if (write_debugfs_file("powerpc/rfi_flush", rfi_flush_orig) < 0) { + perror("unable to restore original value of powerpc/rfi_flush debugfs file"); + return 1; + } + + if (write_debugfs_file("powerpc/entry_flush", entry_flush_orig) < 0) { + perror("unable to restore original value of powerpc/entry_flush debugfs file"); + return 1; + } + + return rc; +} + +int main(int argc, char *argv[]) +{ + return test_harness(entry_flush_test, "entry_flush_test"); +} diff --git a/tools/testing/selftests/powerpc/security/flush_utils.c b/tools/testing/selftests/powerpc/security/flush_utils.c new file mode 100644 index 000000000000..0c3c4c40c7fb --- /dev/null +++ b/tools/testing/selftests/powerpc/security/flush_utils.c @@ -0,0 +1,70 @@ +// SPDX-License-Identifier: GPL-2.0+ + +/* + * Copyright 2018 IBM Corporation. + */ + +#define __SANE_USERSPACE_TYPES__ + +#include <sys/types.h> +#include <stdint.h> +#include <unistd.h> +#include <signal.h> +#include <stdlib.h> +#include <string.h> +#include <stdio.h> +#include "utils.h" +#include "flush_utils.h" + +static inline __u64 load(void *addr) +{ + __u64 tmp; + + asm volatile("ld %0,0(%1)" : "=r"(tmp) : "b"(addr)); + + return tmp; +} + +void syscall_loop(char *p, unsigned long iterations, + unsigned long zero_size) +{ + for (unsigned long i = 0; i < iterations; i++) { + for (unsigned long j = 0; j < zero_size; j += CACHELINE_SIZE) + load(p + j); + getppid(); + } +} + +static void sigill_handler(int signr, siginfo_t *info, void *unused) +{ + static int warned; + ucontext_t *ctx = (ucontext_t *)unused; + unsigned long *pc = &UCONTEXT_NIA(ctx); + + /* mtspr 3,RS to check for move to DSCR below */ + if ((*((unsigned int *)*pc) & 0xfc1fffff) == 0x7c0303a6) { + if (!warned++) + printf("WARNING: Skipping over dscr setup. Consider running 'ppc64_cpu --dscr=1' manually.\n"); + *pc += 4; + } else { + printf("SIGILL at %p\n", pc); + abort(); + } +} + +void set_dscr(unsigned long val) +{ + static int init; + struct sigaction sa; + + if (!init) { + memset(&sa, 0, sizeof(sa)); + sa.sa_sigaction = sigill_handler; + sa.sa_flags = SA_SIGINFO; + if (sigaction(SIGILL, &sa, NULL)) + perror("sigill_handler"); + init = 1; + } + + asm volatile("mtspr %1,%0" : : "r" (val), "i" (SPRN_DSCR)); +} diff --git a/tools/testing/selftests/powerpc/security/flush_utils.h b/tools/testing/selftests/powerpc/security/flush_utils.h new file mode 100644 index 000000000000..07a5eb301466 --- /dev/null +++ b/tools/testing/selftests/powerpc/security/flush_utils.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ + +/* + * Copyright 2018 IBM Corporation. + */ + +#ifndef _SELFTESTS_POWERPC_SECURITY_FLUSH_UTILS_H +#define _SELFTESTS_POWERPC_SECURITY_FLUSH_UTILS_H + +#define CACHELINE_SIZE 128 + +void syscall_loop(char *p, unsigned long iterations, + unsigned long zero_size); + +void set_dscr(unsigned long val); + +#endif /* _SELFTESTS_POWERPC_SECURITY_FLUSH_UTILS_H */ diff --git a/tools/testing/selftests/powerpc/security/rfi_flush.c b/tools/testing/selftests/powerpc/security/rfi_flush.c index 93a65bd1f231..7565fd786640 100644 --- a/tools/testing/selftests/powerpc/security/rfi_flush.c +++ b/tools/testing/selftests/powerpc/security/rfi_flush.c @@ -10,71 +10,12 @@ #include <stdint.h> #include <malloc.h> #include <unistd.h> -#include <signal.h> #include <stdlib.h> #include <string.h> #include <stdio.h> #include "utils.h" +#include "flush_utils.h" -#define CACHELINE_SIZE 128 - -struct perf_event_read { - __u64 nr; - __u64 l1d_misses; -}; - -static inline __u64 load(void *addr) -{ - __u64 tmp; - - asm volatile("ld %0,0(%1)" : "=r"(tmp) : "b"(addr)); - - return tmp; -} - -static void syscall_loop(char *p, unsigned long iterations, - unsigned long zero_size) -{ - for (unsigned long i = 0; i < iterations; i++) { - for (unsigned long j = 0; j < zero_size; j += CACHELINE_SIZE) - load(p + j); - getppid(); - } -} - -static void sigill_handler(int signr, siginfo_t *info, void *unused) -{ - static int warned = 0; - ucontext_t *ctx = (ucontext_t *)unused; - unsigned long *pc = &UCONTEXT_NIA(ctx); - - /* mtspr 3,RS to check for move to DSCR below */ - if ((*((unsigned int *)*pc) & 0xfc1fffff) == 0x7c0303a6) { - if (!warned++) - printf("WARNING: Skipping over dscr setup. Consider running 'ppc64_cpu --dscr=1' manually.\n"); - *pc += 4; - } else { - printf("SIGILL at %p\n", pc); - abort(); - } -} - -static void set_dscr(unsigned long val) -{ - static int init = 0; - struct sigaction sa; - - if (!init) { - memset(&sa, 0, sizeof(sa)); - sa.sa_sigaction = sigill_handler; - sa.sa_flags = SA_SIGINFO; - if (sigaction(SIGILL, &sa, NULL)) - perror("sigill_handler"); - init = 1; - } - - asm volatile("mtspr %1,%0" : : "r" (val), "i" (SPRN_DSCR)); -} int rfi_flush_test(void) { @@ -85,19 +26,33 @@ int rfi_flush_test(void) __u64 l1d_misses_total = 0; unsigned long iterations = 100000, zero_size = 24 * 1024; unsigned long l1d_misses_expected; - int rfi_flush_org, rfi_flush; + int rfi_flush_orig, rfi_flush; + int have_entry_flush, entry_flush_orig; SKIP_IF(geteuid() != 0); // The PMU event we use only works on Power7 or later SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06)); - if (read_debugfs_file("powerpc/rfi_flush", &rfi_flush_org)) { + if (read_debugfs_file("powerpc/rfi_flush", &rfi_flush_orig) < 0) { perror("Unable to read powerpc/rfi_flush debugfs file"); SKIP_IF(1); } - rfi_flush = rfi_flush_org; + if (read_debugfs_file("powerpc/entry_flush", &entry_flush_orig) < 0) { + have_entry_flush = 0; + } else { + have_entry_flush = 1; + + if (entry_flush_orig != 0) { + if (write_debugfs_file("powerpc/entry_flush", 0) < 0) { + perror("error writing to powerpc/entry_flush debugfs file"); + return 1; + } + } + } + + rfi_flush = rfi_flush_orig; fd = perf_event_open_counter(PERF_TYPE_RAW, /* L1d miss */ 0x400f0, -1); FAIL_IF(fd < 0); @@ -106,6 +61,7 @@ int rfi_flush_test(void) FAIL_IF(perf_event_enable(fd)); + // disable L1 prefetching set_dscr(1); iter = repetitions; @@ -147,8 +103,8 @@ again: repetitions * l1d_misses_expected / 2, passes, repetitions); - if (rfi_flush == rfi_flush_org) { - rfi_flush = !rfi_flush_org; + if (rfi_flush == rfi_flush_orig) { + rfi_flush = !rfi_flush_orig; if (write_debugfs_file("powerpc/rfi_flush", rfi_flush) < 0) { perror("error writing to powerpc/rfi_flush debugfs file"); return 1; @@ -164,11 +120,19 @@ again: set_dscr(0); - if (write_debugfs_file("powerpc/rfi_flush", rfi_flush_org) < 0) { + if (write_debugfs_file("powerpc/rfi_flush", rfi_flush_orig) < 0) { perror("unable to restore original value of powerpc/rfi_flush debugfs file"); return 1; } + if (have_entry_flush) { + if (write_debugfs_file("powerpc/entry_flush", entry_flush_orig) < 0) { + perror("unable to restore original value of powerpc/entry_flush " + "debugfs file"); + return 1; + } + } + return rc; } diff --git a/tools/testing/selftests/proc/proc-loadavg-001.c b/tools/testing/selftests/proc/proc-loadavg-001.c index 471e2aa28077..fb4fe9188806 100644 --- a/tools/testing/selftests/proc/proc-loadavg-001.c +++ b/tools/testing/selftests/proc/proc-loadavg-001.c @@ -14,7 +14,6 @@ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. */ /* Test that /proc/loadavg correctly reports last pid in pid namespace. */ -#define _GNU_SOURCE #include <errno.h> #include <sched.h> #include <sys/types.h> diff --git a/tools/testing/selftests/proc/proc-self-syscall.c b/tools/testing/selftests/proc/proc-self-syscall.c index 9f6d000c0245..8511dcfe67c7 100644 --- a/tools/testing/selftests/proc/proc-self-syscall.c +++ b/tools/testing/selftests/proc/proc-self-syscall.c @@ -13,7 +13,6 @@ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. */ -#define _GNU_SOURCE #include <unistd.h> #include <sys/syscall.h> #include <sys/types.h> diff --git a/tools/testing/selftests/proc/proc-uptime-002.c b/tools/testing/selftests/proc/proc-uptime-002.c index 30e2b7849089..e7ceabed7f51 100644 --- a/tools/testing/selftests/proc/proc-uptime-002.c +++ b/tools/testing/selftests/proc/proc-uptime-002.c @@ -15,7 +15,6 @@ */ // Test that values in /proc/uptime increment monotonically // while shifting across CPUs. -#define _GNU_SOURCE #undef NDEBUG #include <assert.h> #include <unistd.h> diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 4a180439ee9e..26c72f2b61b1 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -1758,10 +1758,10 @@ TEST_F(TRACE_poke, getpid_runs_normally) * and the code is stored as a positive value. \ */ \ if (_result < 0) { \ - SYSCALL_RET(_regs) = -result; \ + SYSCALL_RET(_regs) = -_result; \ (_regs).ccr |= 0x10000000; \ } else { \ - SYSCALL_RET(_regs) = result; \ + SYSCALL_RET(_regs) = _result; \ (_regs).ccr &= ~0x10000000; \ } \ } while (0) @@ -1804,8 +1804,8 @@ TEST_F(TRACE_poke, getpid_runs_normally) #define SYSCALL_RET(_regs) (_regs).a[(_regs).windowbase * 4 + 2] #elif defined(__sh__) # define ARCH_REGS struct pt_regs -# define SYSCALL_NUM(_regs) (_regs).gpr[3] -# define SYSCALL_RET(_regs) (_regs).gpr[0] +# define SYSCALL_NUM(_regs) (_regs).regs[3] +# define SYSCALL_RET(_regs) (_regs).regs[0] #else # error "Do not know how to find your architecture's registers and syscalls" #endif diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json index bb543bf69d69..361235ad574b 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json @@ -100,7 +100,7 @@ ], "cmdUnderTest": "$TC filter add dev $DEV2 protocol ip pref 1 ingress flower dst_mac e4:11:22:11:4a:51 action drop", "expExitCode": "0", - "verifyCmd": "$TC filter show terse dev $DEV2 ingress", + "verifyCmd": "$TC -br filter show dev $DEV2 ingress", "matchPattern": "filter protocol ip pref 1 flower.*handle", "matchCount": "1", "teardown": [ @@ -119,7 +119,7 @@ ], "cmdUnderTest": "$TC filter add dev $DEV2 protocol ip pref 1 ingress flower dst_mac e4:11:22:11:4a:51 action drop", "expExitCode": "0", - "verifyCmd": "$TC filter show terse dev $DEV2 ingress", + "verifyCmd": "$TC -br filter show dev $DEV2 ingress", "matchPattern": " dst_mac e4:11:22:11:4a:51", "matchCount": "0", "teardown": [ diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh index d77f4829f1e0..74c69b75f6f5 100755 --- a/tools/testing/selftests/wireguard/netns.sh +++ b/tools/testing/selftests/wireguard/netns.sh @@ -316,6 +316,14 @@ pp sleep 3 n2 ping -W 1 -c 1 192.168.241.1 n1 wg set wg0 peer "$pub2" persistent-keepalive 0 +# Test that sk_bound_dev_if works +n1 ping -I wg0 -c 1 -W 1 192.168.241.2 +# What about when the mark changes and the packet must be rerouted? +n1 iptables -t mangle -I OUTPUT -j MARK --set-xmark 1 +n1 ping -c 1 -W 1 192.168.241.2 # First the boring case +n1 ping -I wg0 -c 1 -W 1 192.168.241.2 # Then the sk_bound_dev_if case +n1 iptables -t mangle -D OUTPUT -j MARK --set-xmark 1 + # Test that onion routing works, even when it loops n1 wg set wg0 peer "$pub3" allowed-ips 192.168.242.2/32 endpoint 192.168.241.2:5 ip1 addr add 192.168.242.1/24 dev wg0 diff --git a/tools/testing/selftests/wireguard/qemu/kernel.config b/tools/testing/selftests/wireguard/qemu/kernel.config index d531de13c95b..4eecb432a66c 100644 --- a/tools/testing/selftests/wireguard/qemu/kernel.config +++ b/tools/testing/selftests/wireguard/qemu/kernel.config @@ -18,10 +18,12 @@ CONFIG_NF_NAT=y CONFIG_NETFILTER_XTABLES=y CONFIG_NETFILTER_XT_NAT=y CONFIG_NETFILTER_XT_MATCH_LENGTH=y +CONFIG_NETFILTER_XT_MARK=y CONFIG_NF_CONNTRACK_IPV4=y CONFIG_NF_NAT_IPV4=y CONFIG_IP_NF_IPTABLES=y CONFIG_IP_NF_FILTER=y +CONFIG_IP_NF_MANGLE=y CONFIG_IP_NF_NAT=y CONFIG_IP_ADVANCED_ROUTER=y CONFIG_IP_MULTIPLE_TABLES=y |