diff options
| author |   Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2019-12-23 07:00:09 -0500 |
|---|---|---|
| committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2019-12-23 07:00:09 -0500 |
| commit | 398d999f96bf8e02573b0c7e32896c7812393bc0 (patch) | |
| tree | 839f1616cc205b9a74f07f7b571a603814446de6 | |
| parent | staging: nvec: check return value (diff) | |
| parent | Linux 5.5-rc3 (diff) | |
| download | linux-dev-398d999f96bf8e02573b0c7e32896c7812393bc0.tar.xz linux-dev-398d999f96bf8e02573b0c7e32896c7812393bc0.zip | |
Merge 5.5-rc3 into staging-next
We need the staging fixes in here as well.
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
566 files changed, 6495 insertions, 2976 deletions
@@ -152,6 +152,7 @@ Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@web.de> Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@ascom.ch> Li Yang <leoyang.li@nxp.com> <leo@zh-kernel.org> Li Yang <leoyang.li@nxp.com> <leoli@freescale.com> +Lukasz Luba <lukasz.luba@arm.com> <l.luba@partner.samsung.com> Maciej W. Rozycki <macro@mips.com> <macro@imgtec.com> Marc Zyngier <maz@kernel.org> <marc.zyngier@arm.com> Marcin Nowakowski <marcin.nowakowski@mips.com> <marcin.nowakowski@imgtec.com> @@ -265,6 +266,7 @@ Vinod Koul <vkoul@kernel.org> <vkoul@infradead.org> Viresh Kumar <vireshk@kernel.org> <viresh.kumar@st.com> Viresh Kumar <vireshk@kernel.org> <viresh.linux@gmail.com> Viresh Kumar <vireshk@kernel.org> <viresh.kumar2@arm.com> +Vivien Didelot <vivien.didelot@gmail.com> <vivien.didelot@savoirfairelinux.com> Vlad Dogaru <ddvlad@gmail.com> <vlad.dogaru@intel.com> Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@virtuozzo.com> Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@parallels.com> diff --git a/Documentation/ABI/testing/sysfs-platform-mellanox-bootctl b/Documentation/ABI/testing/sysfs-platform-mellanox-bootctl index c65a80574869..401d202f478b 100644 --- a/Documentation/ABI/testing/sysfs-platform-mellanox-bootctl +++ b/Documentation/ABI/testing/sysfs-platform-mellanox-bootctl @@ -1,4 +1,4 @@ -What: /sys/bus/platform/devices/MLNXBF04:00/driver/lifecycle_state +What: /sys/bus/platform/devices/MLNXBF04:00/lifecycle_state Date: Oct 2019 KernelVersion: 5.5 Contact: "Liming Sun <lsun@mellanox.com>" @@ -10,7 +10,7 @@ Description: GA Non-Secured - Non-Secure chip and not able to change state RMA - Return Merchandise Authorization -What: /sys/bus/platform/devices/MLNXBF04:00/driver/post_reset_wdog +What: /sys/bus/platform/devices/MLNXBF04:00/post_reset_wdog Date: Oct 2019 KernelVersion: 5.5 Contact: "Liming Sun <lsun@mellanox.com>" @@ -19,7 +19,7 @@ Description: to reboot the chip and recover it to the old state if the new boot partition fails. -What: /sys/bus/platform/devices/MLNXBF04:00/driver/reset_action +What: /sys/bus/platform/devices/MLNXBF04:00/reset_action Date: Oct 2019 KernelVersion: 5.5 Contact: "Liming Sun <lsun@mellanox.com>" @@ -30,7 +30,7 @@ Description: emmc - boot from the onchip eMMC emmc_legacy - boot from the onchip eMMC in legacy (slow) mode -What: /sys/bus/platform/devices/MLNXBF04:00/driver/second_reset_action +What: /sys/bus/platform/devices/MLNXBF04:00/second_reset_action Date: Oct 2019 KernelVersion: 5.5 Contact: "Liming Sun <lsun@mellanox.com>" @@ -44,7 +44,7 @@ Description: swap_emmc - swap the primary / secondary boot partition none - cancel the action -What: /sys/bus/platform/devices/MLNXBF04:00/driver/secure_boot_fuse_state +What: /sys/bus/platform/devices/MLNXBF04:00/secure_boot_fuse_state Date: Oct 2019 KernelVersion: 5.5 Contact: "Liming Sun <lsun@mellanox.com>" diff --git a/Documentation/admin-guide/ext4.rst b/Documentation/admin-guide/ext4.rst index 059ddcbe769d..9bc93f0ce0c9 100644 --- a/Documentation/admin-guide/ext4.rst +++ b/Documentation/admin-guide/ext4.rst @@ -181,14 +181,17 @@ When mounting an ext4 filesystem, the following option are accepted: system after its metadata has been committed to the journal. commit=nrsec (*) - Ext4 can be told to sync all its data and metadata every 'nrsec' - seconds. The default value is 5 seconds. This means that if you lose - your power, you will lose as much as the latest 5 seconds of work (your - filesystem will not be damaged though, thanks to the journaling). This - default value (or any low value) will hurt performance, but it's good - for data-safety. Setting it to 0 will have the same effect as leaving - it at the default (5 seconds). Setting it to very large values will - improve performance. + This setting limits the maximum age of the running transaction to + 'nrsec' seconds. The default value is 5 seconds. This means that if + you lose your power, you will lose as much as the latest 5 seconds of + metadata changes (your filesystem will not be damaged though, thanks + to the journaling). This default value (or any low value) will hurt + performance, but it's good for data-safety. Setting it to 0 will have + the same effect as leaving it at the default (5 seconds). Setting it + to very large values will improve performance. Note that due to + delayed allocation even older data can be lost on power failure since + writeback of those data begins only after time set in + /proc/sys/vm/dirty_expire_centisecs. barrier=<0|1(*)>, barrier(*), nobarrier This enables/disables the use of write barriers in the jbd code. diff --git a/Documentation/admin-guide/xfs.rst b/Documentation/admin-guide/xfs.rst index fb5b39f73059..ad911be5b5e9 100644 --- a/Documentation/admin-guide/xfs.rst +++ b/Documentation/admin-guide/xfs.rst @@ -253,7 +253,7 @@ The following sysctls are available for the XFS filesystem: pool. fs.xfs.speculative_prealloc_lifetime - (Units: seconds Min: 1 Default: 300 Max: 86400) + (Units: seconds Min: 1 Default: 300 Max: 86400) The interval at which the background scanning for inodes with unused speculative preallocation runs. The scan removes unused preallocation from clean inodes and releases diff --git a/Documentation/dev-tools/kselftest.rst b/Documentation/dev-tools/kselftest.rst index ecdfdc9d4b03..61ae13c44f91 100644 --- a/Documentation/dev-tools/kselftest.rst +++ b/Documentation/dev-tools/kselftest.rst @@ -203,12 +203,12 @@ Test Module Kselftest tests the kernel from userspace. Sometimes things need testing from within the kernel, one method of doing this is to create a test module. We can tie the module into the kselftest framework by -using a shell script test runner. ``kselftest_module.sh`` is designed +using a shell script test runner. ``kselftest/module.sh`` is designed to facilitate this process. There is also a header file provided to assist writing kernel modules that are for use with kselftest: - ``tools/testing/kselftest/kselftest_module.h`` -- ``tools/testing/kselftest/kselftest_module.sh`` +- ``tools/testing/kselftest/kselftest/module.sh`` How to use ---------- @@ -247,7 +247,7 @@ A bare bones test module might look like this: #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - #include "../tools/testing/selftests/kselftest_module.h" + #include "../tools/testing/selftests/kselftest/module.h" KSTM_MODULE_GLOBALS(); @@ -276,7 +276,7 @@ Example test script #!/bin/bash # SPDX-License-Identifier: GPL-2.0+ - $(dirname $0)/../kselftest_module.sh "foo" test_foo + $(dirname $0)/../kselftest/module.sh "foo" test_foo Test Harness diff --git a/Documentation/dev-tools/kunit/index.rst b/Documentation/dev-tools/kunit/index.rst index 26ffb46bdf99..c60d760a0eed 100644 --- a/Documentation/dev-tools/kunit/index.rst +++ b/Documentation/dev-tools/kunit/index.rst @@ -9,6 +9,7 @@ KUnit - Unit Testing for the Linux Kernel start usage + kunit-tool api/index faq diff --git a/Documentation/dev-tools/kunit/kunit-tool.rst b/Documentation/dev-tools/kunit/kunit-tool.rst new file mode 100644 index 000000000000..50d46394e97e --- /dev/null +++ b/Documentation/dev-tools/kunit/kunit-tool.rst @@ -0,0 +1,57 @@ +.. SPDX-License-Identifier: GPL-2.0 + +================= +kunit_tool How-To +================= + +What is kunit_tool? +=================== + +kunit_tool is a script (``tools/testing/kunit/kunit.py``) that aids in building +the Linux kernel as UML (`User Mode Linux +<http://user-mode-linux.sourceforge.net/>`_), running KUnit tests, parsing +the test results and displaying them in a user friendly manner. + +What is a kunitconfig? +====================== + +It's just a defconfig that kunit_tool looks for in the base directory. +kunit_tool uses it to generate a .config as you might expect. In addition, it +verifies that the generated .config contains the CONFIG options in the +kunitconfig; the reason it does this is so that it is easy to be sure that a +CONFIG that enables a test actually ends up in the .config. + +How do I use kunit_tool? +======================== + +If a kunitconfig is present at the root directory, all you have to do is: + +.. code-block:: bash + + ./tools/testing/kunit/kunit.py run + +However, you most likely want to use it with the following options: + +.. code-block:: bash + + ./tools/testing/kunit/kunit.py run --timeout=30 --jobs=`nproc --all` + +- ``--timeout`` sets a maximum amount of time to allow tests to run. +- ``--jobs`` sets the number of threads to use to build the kernel. + +If you just want to use the defconfig that ships with the kernel, you can +append the ``--defconfig`` flag as well: + +.. code-block:: bash + + ./tools/testing/kunit/kunit.py run --timeout=30 --jobs=`nproc --all` --defconfig + +.. note:: + This command is particularly helpful for getting started because it + just works. No kunitconfig needs to be present. + +For a list of all the flags supported by kunit_tool, you can run: + +.. code-block:: bash + + ./tools/testing/kunit/kunit.py run --help diff --git a/Documentation/dev-tools/kunit/start.rst b/Documentation/dev-tools/kunit/start.rst index aeeddfafeea2..9d6db892c41c 100644 --- a/Documentation/dev-tools/kunit/start.rst +++ b/Documentation/dev-tools/kunit/start.rst @@ -19,11 +19,14 @@ The wrapper can be run with: .. code-block:: bash - ./tools/testing/kunit/kunit.py run + ./tools/testing/kunit/kunit.py run --defconfig + +For more information on this wrapper (also called kunit_tool) checkout the +:doc:`kunit-tool` page. Creating a kunitconfig ====================== -The Python script is a thin wrapper around Kbuild as such, it needs to be +The Python script is a thin wrapper around Kbuild. As such, it needs to be configured with a ``kunitconfig`` file. This file essentially contains the regular Kernel config, with the specific test targets as well. @@ -59,8 +62,8 @@ If everything worked correctly, you should see the following: followed by a list of tests that are run. All of them should be passing. .. note:: - Because it is building a lot of sources for the first time, the ``Building - kunit kernel`` step may take a while. + Because it is building a lot of sources for the first time, the + ``Building KUnit kernel`` step may take a while. Writing your first test ======================= @@ -159,7 +162,7 @@ Now you can run the test: .. code-block:: bash - ./tools/testing/kunit/kunit.py + ./tools/testing/kunit/kunit.py run You should see the following failure: diff --git a/Documentation/dev-tools/kunit/usage.rst b/Documentation/dev-tools/kunit/usage.rst index c6e69634e274..b9a065ab681e 100644 --- a/Documentation/dev-tools/kunit/usage.rst +++ b/Documentation/dev-tools/kunit/usage.rst @@ -16,7 +16,7 @@ Organization of this document ============================= This document is organized into two main sections: Testing and Isolating -Behavior. The first covers what a unit test is and how to use KUnit to write +Behavior. The first covers what unit tests are and how to use KUnit to write them. The second covers how to use KUnit to isolate code and make it possible to unit test code that was otherwise un-unit-testable. @@ -174,13 +174,13 @@ Test Suites ~~~~~~~~~~~ Now obviously one unit test isn't very helpful; the power comes from having -many test cases covering all of your behaviors. Consequently it is common to -have many *similar* tests; in order to reduce duplication in these closely -related tests most unit testing frameworks provide the concept of a *test -suite*, in KUnit we call it a *test suite*; all it is is just a collection of -test cases for a unit of code with a set up function that gets invoked before -every test cases and then a tear down function that gets invoked after every -test case completes. +many test cases covering all of a unit's behaviors. Consequently it is common +to have many *similar* tests; in order to reduce duplication in these closely +related tests most unit testing frameworks - including KUnit - provide the +concept of a *test suite*. A *test suite* is just a collection of test cases +for a unit of code with a set up function that gets invoked before every test +case and then a tear down function that gets invoked after every test case +completes. Example: @@ -211,7 +211,7 @@ KUnit test framework. .. note:: A test case will only be run if it is associated with a test suite. -For a more information on these types of things see the :doc:`api/test`. +For more information on these types of things see the :doc:`api/test`. Isolating Behavior ================== @@ -338,7 +338,7 @@ We can easily test this code by *faking out* the underlying EEPROM: return count; } - ssize_t fake_eeprom_write(struct eeprom *this, size_t offset, const char *buffer, size_t count) + ssize_t fake_eeprom_write(struct eeprom *parent, size_t offset, const char *buffer, size_t count) { struct fake_eeprom *this = container_of(parent, struct fake_eeprom, parent); @@ -454,7 +454,7 @@ 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. @@ -557,7 +557,7 @@ run your tests on your hardware setup just by compiling for your architecture. .. important:: Always prefer tests that run on UML to tests that only run under a particular architecture, and always prefer tests that run under QEMU or another easy - (and monitarily free) to obtain software environment to a specific piece of + (and monetarily free) to obtain software environment to a specific piece of hardware. Nevertheless, there are still valid reasons to write an architecture or hardware diff --git a/Documentation/devicetree/bindings/net/can/tcan4x5x.txt b/Documentation/devicetree/bindings/net/can/tcan4x5x.txt index 27e1b4cebfbd..6bdcc3f84bd3 100644 --- a/Documentation/devicetree/bindings/net/can/tcan4x5x.txt +++ b/Documentation/devicetree/bindings/net/can/tcan4x5x.txt @@ -10,7 +10,6 @@ Required properties: - #size-cells: 0 - spi-max-frequency: Maximum frequency of the SPI bus the chip can operate at should be less than or equal to 18 MHz. - - device-wake-gpios: Wake up GPIO to wake up the TCAN device. - interrupt-parent: the phandle to the interrupt controller which provides the interrupt. - interrupts: interrupt specification for data-ready. @@ -23,6 +22,7 @@ Optional properties: reset. - device-state-gpios: Input GPIO that indicates if the device is in a sleep state or if the device is active. + - device-wake-gpios: Wake up GPIO to wake up the TCAN device. Example: tcan4x5x: tcan4x5x@0 { @@ -36,5 +36,5 @@ tcan4x5x: tcan4x5x@0 { interrupts = <14 GPIO_ACTIVE_LOW>; device-state-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>; device-wake-gpios = <&gpio1 15 GPIO_ACTIVE_HIGH>; - reset-gpios = <&gpio1 27 GPIO_ACTIVE_LOW>; + reset-gpios = <&gpio1 27 GPIO_ACTIVE_HIGH>; }; diff --git a/Documentation/devicetree/bindings/net/snps,dwmac.yaml b/Documentation/devicetree/bindings/net/snps,dwmac.yaml index 4845e29411e4..e08cd4c4d568 100644 --- a/Documentation/devicetree/bindings/net/snps,dwmac.yaml +++ b/Documentation/devicetree/bindings/net/snps,dwmac.yaml @@ -347,6 +347,7 @@ allOf: - st,spear600-gmac then: + properties: snps,tso: $ref: /schemas/types.yaml#definitions/flag description: diff --git a/Documentation/devicetree/bindings/reset/brcm,brcmstb-reset.txt b/Documentation/devicetree/bindings/reset/brcm,brcmstb-reset.txt index 6e5341b4f891..ee59409640f2 100644 --- a/Documentation/devicetree/bindings/reset/brcm,brcmstb-reset.txt +++ b/Documentation/devicetree/bindings/reset/brcm,brcmstb-reset.txt @@ -22,6 +22,6 @@ Example: }; ðernet_switch { - resets = <&reset>; + resets = <&reset 26>; reset-names = "switch"; }; diff --git a/Documentation/kbuild/kconfig-language.rst b/Documentation/kbuild/kconfig-language.rst index 74bef19f69f0..231e6a64957f 100644 --- a/Documentation/kbuild/kconfig-language.rst +++ b/Documentation/kbuild/kconfig-language.rst @@ -196,14 +196,11 @@ applicable everywhere (see syntax). or equal to the first symbol and smaller than or equal to the second symbol. -- help text: "help" or "---help---" +- help text: "help" This defines a help text. The end of the help text is determined by the indentation level, this means it ends at the first line which has a smaller indentation than the first line of the help text. - "---help---" and "help" do not differ in behaviour, "---help---" is - used to help visually separate configuration logic from help within - the file as an aid to developers. - misc options: "option" <symbol>[=<value>] diff --git a/Documentation/kbuild/makefiles.rst b/Documentation/kbuild/makefiles.rst index b9b50553bfc5..d7e6534a8505 100644 --- a/Documentation/kbuild/makefiles.rst +++ b/Documentation/kbuild/makefiles.rst @@ -297,9 +297,19 @@ more details, with real examples. If CONFIG_EXT2_FS is set to either 'y' (built-in) or 'm' (modular) the corresponding obj- variable will be set, and kbuild will descend down in the ext2 directory. - Kbuild only uses this information to decide that it needs to visit - the directory, it is the Makefile in the subdirectory that - specifies what is modular and what is built-in. + + Kbuild uses this information not only to decide that it needs to visit + the directory, but also to decide whether or not to link objects from + the directory into vmlinux. + + When Kbuild descends into the directory with 'y', all built-in objects + from that directory are combined into the built-in.a, which will be + eventually linked into vmlinux. + + When Kbuild descends into the directory with 'm', in contrast, nothing + from that directory will be linked into vmlinux. If the Makefile in + that directory specifies obj-y, those objects will be left orphan. + It is very likely a bug of the Makefile or of dependencies in Kconfig. It is good practice to use a `CONFIG_` variable when assigning directory names. This allows kbuild to totally skip the directory if the diff --git a/Documentation/networking/j1939.rst b/Documentation/networking/j1939.rst index dc60b13fcd09..f5be243d250a 100644 --- a/Documentation/networking/j1939.rst +++ b/Documentation/networking/j1939.rst @@ -339,7 +339,7 @@ To claim an address following code example can be used: .pgn = J1939_PGN_ADDRESS_CLAIMED, .pgn_mask = J1939_PGN_PDU1_MAX, }, { - .pgn = J1939_PGN_ADDRESS_REQUEST, + .pgn = J1939_PGN_REQUEST, .pgn_mask = J1939_PGN_PDU1_MAX, }, { .pgn = J1939_PGN_ADDRESS_COMMANDED, diff --git a/MAINTAINERS b/MAINTAINERS index dc096f4376a2..c80c5919b515 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2272,6 +2272,7 @@ F: drivers/*/*s3c64xx* F: drivers/*/*s5pv210* F: drivers/memory/samsung/ F: drivers/soc/samsung/ +F: drivers/tty/serial/samsung* F: include/linux/soc/samsung/ F: Documentation/arm/samsung/ F: Documentation/devicetree/bindings/arm/samsung/ @@ -5000,7 +5001,7 @@ F: include/linux/dma-mapping.h F: include/linux/dma-noncoherent.h DMC FREQUENCY DRIVER FOR SAMSUNG EXYNOS5422 -M: Lukasz Luba <l.luba@partner.samsung.com> +M: Lukasz Luba <lukasz.luba@arm.com> L: linux-pm@vger.kernel.org L: linux-samsung-soc@vger.kernel.org S: Maintained @@ -6026,6 +6027,7 @@ M: Yash Shah <yash.shah@sifive.com> L: linux-edac@vger.kernel.org S: Supported F: drivers/edac/sifive_edac.c +F: drivers/soc/sifive_l2_cache.c EDAC-SKYLAKE M: Tony Luck <tony.luck@intel.com> @@ -9038,7 +9040,6 @@ F: include/linux/umh.h KERNEL VIRTUAL MACHINE (KVM) M: Paolo Bonzini <pbonzini@redhat.com> -M: Radim Krčmář <rkrcmar@redhat.com> L: kvm@vger.kernel.org W: http://www.linux-kvm.org T: git git://git.kernel.org/pub/scm/virt/kvm/kvm.git @@ -9073,9 +9074,9 @@ F: virt/kvm/arm/ F: include/kvm/arm_* KERNEL VIRTUAL MACHINE FOR MIPS (KVM/mips) -M: James Hogan <jhogan@kernel.org> L: linux-mips@vger.kernel.org -S: Supported +L: kvm@vger.kernel.org +S: Orphan F: arch/mips/include/uapi/asm/kvm* F: arch/mips/include/asm/kvm* F: arch/mips/kvm/ @@ -9110,7 +9111,6 @@ F: tools/testing/selftests/kvm/*/s390x/ KERNEL VIRTUAL MACHINE FOR X86 (KVM/x86) M: Paolo Bonzini <pbonzini@redhat.com> -M: Radim Krčmář <rkrcmar@redhat.com> R: Sean Christopherson <sean.j.christopherson@intel.com> R: Vitaly Kuznetsov <vkuznets@redhat.com> R: Wanpeng Li <wanpengli@tencent.com> @@ -10108,6 +10108,7 @@ S: Maintained F: drivers/media/radio/radio-maxiradio* MCAN MMIO DEVICE DRIVER +M: Dan Murphy <dmurphy@ti.com> M: Sriram Dash <sriram.dash@samsung.com> L: linux-can@vger.kernel.org S: Maintained @@ -13708,6 +13709,15 @@ L: linux-arm-msm@vger.kernel.org S: Maintained F: drivers/iommu/qcom_iommu.c +QUALCOMM RMNET DRIVER +M: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org> +M: Sean Tranchetti <stranche@codeaurora.org> +L: netdev@vger.kernel.org +S: Maintained +F: drivers/net/ethernet/qualcomm/rmnet/ +F: Documentation/networking/device_drivers/qualcomm/rmnet.txt +F: include/linux/if_rmnet.h + QUALCOMM TSENS THERMAL DRIVER M: Amit Kucheria <amit.kucheria@linaro.org> L: linux-pm@vger.kernel.org @@ -16531,6 +16541,13 @@ L: alsa-devel@alsa-project.org (moderated for non-subscribers) S: Odd Fixes F: sound/soc/codecs/tas571x* +TI TCAN4X5X DEVICE DRIVER +M: Dan Murphy <dmurphy@ti.com> +L: linux-can@vger.kernel.org +S: Maintained +F: Documentation/devicetree/bindings/net/can/tcan4x5x.txt +F: drivers/net/can/m_can/tcan4x5x.c + TI TRF7970A NFC DRIVER M: Mark Greer <mgreer@animalcreek.com> L: linux-wireless@vger.kernel.org @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 5 SUBLEVEL = 0 -EXTRAVERSION = -rc2 +EXTRAVERSION = -rc3 NAME = Kleptomaniac Octopus # *DOCUMENTATION* @@ -414,6 +414,7 @@ STRIP = $(CROSS_COMPILE)strip OBJCOPY = $(CROSS_COMPILE)objcopy OBJDUMP = $(CROSS_COMPILE)objdump OBJSIZE = $(CROSS_COMPILE)size +READELF = $(CROSS_COMPILE)readelf PAHOLE = pahole LEX = flex YACC = bison @@ -472,7 +473,7 @@ GCC_PLUGINS_CFLAGS := CLANG_FLAGS := export ARCH SRCARCH CONFIG_SHELL BASH HOSTCC KBUILD_HOSTCFLAGS CROSS_COMPILE AS LD CC -export CPP AR NM STRIP OBJCOPY OBJDUMP OBJSIZE PAHOLE LEX YACC AWK INSTALLKERNEL +export CPP AR NM STRIP OBJCOPY OBJDUMP OBJSIZE READELF PAHOLE LEX YACC AWK INSTALLKERNEL export PERL PYTHON PYTHON2 PYTHON3 CHECK CHECKFLAGS MAKE UTS_MACHINE HOSTCXX export KBUILD_HOSTCXXFLAGS KBUILD_HOSTLDFLAGS KBUILD_HOSTLDLIBS LDFLAGS_MODULE diff --git a/arch/arm/boot/dts/am335x-sancloud-bbe.dts b/arch/arm/boot/dts/am335x-sancloud-bbe.dts index 8678e6e35493..e5fdb7abb0d5 100644 --- a/arch/arm/boot/dts/am335x-sancloud-bbe.dts +++ b/arch/arm/boot/dts/am335x-sancloud-bbe.dts @@ -108,7 +108,7 @@ &cpsw_emac0 { phy-handle = <ðphy0>; - phy-mode = "rgmii-txid"; + phy-mode = "rgmii-id"; }; &i2c0 { diff --git a/arch/arm/boot/dts/am437x-gp-evm.dts b/arch/arm/boot/dts/am437x-gp-evm.dts index cae4500194fe..811c8cae315b 100644 --- a/arch/arm/boot/dts/am437x-gp-evm.dts +++ b/arch/arm/boot/dts/am437x-gp-evm.dts @@ -86,7 +86,7 @@ }; lcd0: display { - compatible = "osddisplays,osd057T0559-34ts", "panel-dpi"; + compatible = "osddisplays,osd070t1718-19ts", "panel-dpi"; label = "lcd"; backlight = <&lcd_bl>; diff --git a/arch/arm/boot/dts/am43x-epos-evm.dts b/arch/arm/boot/dts/am43x-epos-evm.dts index 95314121d111..078cb473fa7d 100644 --- a/arch/arm/boot/dts/am43x-epos-evm.dts +++ b/arch/arm/boot/dts/am43x-epos-evm.dts @@ -42,7 +42,7 @@ }; lcd0: display { - compatible = "osddisplays,osd057T0559-34ts", "panel-dpi"; + compatible = "osddisplays,osd070t1718-19ts", "panel-dpi"; label = "lcd"; backlight = <&lcd_bl>; diff --git a/arch/arm/boot/dts/bcm-cygnus.dtsi b/arch/arm/boot/dts/bcm-cygnus.dtsi index 2dac3efc7640..1bc45cfd5453 100644 --- a/arch/arm/boot/dts/bcm-cygnus.dtsi +++ b/arch/arm/boot/dts/bcm-cygnus.dtsi @@ -174,8 +174,8 @@ mdio: mdio@18002000 { compatible = "brcm,iproc-mdio"; reg = <0x18002000 0x8>; - #size-cells = <1>; - #address-cells = <0>; + #size-cells = <0>; + #address-cells = <1>; status = "disabled"; gphy0: ethernet-phy@0 { diff --git a/arch/arm/boot/dts/bcm2711.dtsi b/arch/arm/boot/dts/bcm2711.dtsi index 961bed832755..e2f6ffb00aa9 100644 --- a/arch/arm/boot/dts/bcm2711.dtsi +++ b/arch/arm/boot/dts/bcm2711.dtsi @@ -43,7 +43,7 @@ <0x7c000000 0x0 0xfc000000 0x02000000>, <0x40000000 0x0 0xff800000 0x00800000>; /* Emulate a contiguous 30-bit address range for DMA */ - dma-ranges = <0xc0000000 0x0 0x00000000 0x3c000000>; + dma-ranges = <0xc0000000 0x0 0x00000000 0x40000000>; /* * This node is the provider for the enable-method for diff --git a/arch/arm/boot/dts/bcm283x.dtsi b/arch/arm/boot/dts/bcm283x.dtsi index 3caaa57eb6c8..839491628e87 100644 --- a/arch/arm/boot/dts/bcm283x.dtsi +++ b/arch/arm/boot/dts/bcm283x.dtsi @@ -37,7 +37,7 @@ trips { cpu-crit { - temperature = <80000>; + temperature = <90000>; hysteresis = <0>; type = "critical"; }; diff --git a/arch/arm/boot/dts/bcm5301x.dtsi b/arch/arm/boot/dts/bcm5301x.dtsi index 372dc1eb88a0..2d9b4dd05830 100644 --- a/arch/arm/boot/dts/bcm5301x.dtsi +++ b/arch/arm/boot/dts/bcm5301x.dtsi @@ -353,8 +353,8 @@ mdio: mdio@18003000 { compatible = "brcm,iproc-mdio"; reg = <0x18003000 0x8>; - #size-cells = <1>; - #address-cells = <0>; + #size-cells = <0>; + #address-cells = <1>; }; mdio-bus-mux@18003000 { diff --git a/arch/arm/boot/dts/e60k02.dtsi b/arch/arm/boot/dts/e60k02.dtsi index 6472b056a001..5a2c5320437d 100644 --- a/arch/arm/boot/dts/e60k02.dtsi +++ b/arch/arm/boot/dts/e60k02.dtsi @@ -265,11 +265,6 @@ regulator-name = "LDORTC1"; regulator-boot-on; }; - - ldortc2_reg: LDORTC2 { - regulator-name = "LDORTC2"; - regulator-boot-on; - }; }; }; }; diff --git a/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi b/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi index 1506eb12b21e..212144511b66 100644 --- a/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi +++ b/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi @@ -30,14 +30,26 @@ enable-active-high; }; - reg_sensors: regulator-sensors { + reg_peri_3v3: regulator-peri-3v3 { compatible = "regulator-fixed"; pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_sensors_reg>; - regulator-name = "sensors-supply"; + pinctrl-0 = <&pinctrl_peri_3v3>; + regulator-name = "VPERI_3V3"; regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; gpio = <&gpio5 2 GPIO_ACTIVE_LOW>; + /* + * If you want to want to make this dynamic please + * check schematics and test all affected peripherals: + * + * - sensors + * - ethernet phy + * - can + * - bluetooth + * - wm8960 audio codec + * - ov5640 camera + */ + regulator-always-on; }; reg_can_3v3: regulator-can-3v3 { @@ -140,6 +152,7 @@ pinctrl-0 = <&pinctrl_enet1>; phy-mode = "rmii"; phy-handle = <ðphy0>; + phy-supply = <®_peri_3v3>; status = "okay"; }; @@ -148,6 +161,7 @@ pinctrl-0 = <&pinctrl_enet2>; phy-mode = "rmii"; phy-handle = <ðphy1>; + phy-supply = <®_peri_3v3>; status = "okay"; mdio { @@ -193,8 +207,8 @@ magnetometer@e { compatible = "fsl,mag3110"; reg = <0x0e>; - vdd-supply = <®_sensors>; - vddio-supply = <®_sensors>; + vdd-supply = <®_peri_3v3>; + vddio-supply = <®_peri_3v3>; }; }; @@ -227,7 +241,7 @@ flash0: n25q256a@0 { #address-cells = <1>; #size-cells = <1>; - compatible = "micron,n25q256a"; + compatible = "micron,n25q256a", "jedec,spi-nor"; spi-max-frequency = <29000000>; spi-rx-bus-width = <4>; spi-tx-bus-width = <4>; @@ -462,7 +476,7 @@ >; }; - pinctrl_sensors_reg: sensorsreggrp { + pinctrl_peri_3v3: peri3v3grp { fsl,pins = < MX6UL_PAD_SNVS_TAMPER2__GPIO5_IO02 0x1b0b0 >; diff --git a/arch/arm/configs/exynos_defconfig b/arch/arm/configs/exynos_defconfig index e7e4bb5ad8d5..fde84f123fbb 100644 --- a/arch/arm/configs/exynos_defconfig +++ b/arch/arm/configs/exynos_defconfig @@ -350,6 +350,7 @@ CONFIG_PRINTK_TIME=y CONFIG_DYNAMIC_DEBUG=y CONFIG_DEBUG_INFO=y CONFIG_MAGIC_SYSRQ=y +CONFIG_DEBUG_FS=y CONFIG_DEBUG_KERNEL=y CONFIG_SOFTLOCKUP_DETECTOR=y # CONFIG_DETECT_HUNG_TASK is not set diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig index 26d6dee67aa6..3608e55eaecd 100644 --- a/arch/arm/configs/imx_v6_v7_defconfig +++ b/arch/arm/configs/imx_v6_v7_defconfig @@ -462,6 +462,7 @@ CONFIG_FONT_8x8=y CONFIG_FONT_8x16=y CONFIG_PRINTK_TIME=y CONFIG_MAGIC_SYSRQ=y +CONFIG_DEBUG_FS=y # CONFIG_SCHED_DEBUG is not set CONFIG_PROVE_LOCKING=y # CONFIG_DEBUG_BUGVERBOSE is not set diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig index 8c37cc8ab6f2..c32c338f7704 100644 --- a/arch/arm/configs/omap2plus_defconfig +++ b/arch/arm/configs/omap2plus_defconfig @@ -92,6 +92,7 @@ CONFIG_IP_PNP_BOOTP=y CONFIG_IP_PNP_RARP=y CONFIG_NETFILTER=y CONFIG_PHONET=m +CONFIG_NET_SWITCHDEV=y CONFIG_CAN=m CONFIG_CAN_C_CAN=m CONFIG_CAN_C_CAN_PLATFORM=m @@ -181,6 +182,7 @@ CONFIG_SMSC911X=y # CONFIG_NET_VENDOR_STMICRO is not set CONFIG_TI_DAVINCI_EMAC=y CONFIG_TI_CPSW=y +CONFIG_TI_CPSW_SWITCHDEV=y CONFIG_TI_CPTS=y # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set @@ -554,6 +556,6 @@ CONFIG_DEBUG_INFO=y CONFIG_DEBUG_INFO_SPLIT=y CONFIG_DEBUG_INFO_DWARF4=y CONFIG_MAGIC_SYSRQ=y +CONFIG_DEBUG_FS=y CONFIG_SCHEDSTATS=y # CONFIG_DEBUG_BUGVERBOSE is not set -CONFIG_TI_CPSW_SWITCHDEV=y diff --git a/arch/arm/configs/shmobile_defconfig b/arch/arm/configs/shmobile_defconfig index bda57cafa2bc..de3830443613 100644 --- a/arch/arm/configs/shmobile_defconfig +++ b/arch/arm/configs/shmobile_defconfig @@ -212,4 +212,5 @@ CONFIG_DMA_CMA=y CONFIG_CMA_SIZE_MBYTES=64 CONFIG_PRINTK_TIME=y # CONFIG_ENABLE_MUST_CHECK is not set +CONFIG_DEBUG_FS=y CONFIG_DEBUG_KERNEL=y diff --git a/arch/arm/mach-bcm/bcm2711.c b/arch/arm/mach-bcm/bcm2711.c index dbe296798647..fa0300d8c79d 100644 --- a/arch/arm/mach-bcm/bcm2711.c +++ b/arch/arm/mach-bcm/bcm2711.c @@ -13,6 +13,7 @@ static const char * const bcm2711_compat[] = { #ifdef CONFIG_ARCH_MULTI_V7 "brcm,bcm2711", #endif + NULL }; DT_MACHINE_START(BCM2711, "BCM2711") diff --git a/arch/arm/mach-imx/cpu.c b/arch/arm/mach-imx/cpu.c index d8118031c51f..871f98342d50 100644 --- a/arch/arm/mach-imx/cpu.c +++ b/arch/arm/mach-imx/cpu.c @@ -84,7 +84,7 @@ struct device * __init imx_soc_device_init(void) const char *ocotp_compat = NULL; struct soc_device *soc_dev; struct device_node *root; - struct regmap *ocotp; + struct regmap *ocotp = NULL; const char *soc_id; u64 soc_uid = 0; u32 val; @@ -148,11 +148,11 @@ struct device * __init imx_soc_device_init(void) soc_id = "i.MX6UL"; break; case MXC_CPU_IMX6ULL: - ocotp_compat = "fsl,imx6ul-ocotp"; + ocotp_compat = "fsl,imx6ull-ocotp"; soc_id = "i.MX6ULL"; break; case MXC_CPU_IMX6ULZ: - ocotp_compat = "fsl,imx6ul-ocotp"; + ocotp_compat = "fsl,imx6ull-ocotp"; soc_id = "i.MX6ULZ"; break; case MXC_CPU_IMX6SLL: @@ -175,7 +175,9 @@ struct device * __init imx_soc_device_init(void) ocotp = syscon_regmap_lookup_by_compatible(ocotp_compat); if (IS_ERR(ocotp)) pr_err("%s: failed to find %s regmap!\n", __func__, ocotp_compat); + } + if (!IS_ERR_OR_NULL(ocotp)) { regmap_read(ocotp, OCOTP_UID_H, &val); soc_uid = val; regmap_read(ocotp, OCOTP_UID_L, &val); diff --git a/arch/arm/mach-mmp/pxa168.h b/arch/arm/mach-mmp/pxa168.h index 0331c58b07a2..dff651b9f252 100644 --- a/arch/arm/mach-mmp/pxa168.h +++ b/arch/arm/mach-mmp/pxa168.h @@ -17,9 +17,9 @@ extern void pxa168_clear_keypad_wakeup(void); #include <linux/platform_data/keypad-pxa27x.h> #include <linux/pxa168_eth.h> #include <linux/platform_data/mv_usb.h> +#include <linux/soc/mmp/cputype.h> #include "devices.h" -#include "cputype.h" extern struct pxa_device_desc pxa168_device_uart1; extern struct pxa_device_desc pxa168_device_uart2; diff --git a/arch/arm/mach-vexpress/spc.c b/arch/arm/mach-vexpress/spc.c index 354e0e7025ae..1da11bdb1dfb 100644 --- a/arch/arm/mach-vexpress/spc.c +++ b/arch/arm/mach-vexpress/spc.c @@ -551,8 +551,9 @@ static struct clk *ve_spc_clk_register(struct device *cpu_dev) static int __init ve_spc_clk_init(void) { - int cpu; + int cpu, cluster; struct clk *clk; + bool init_opp_table[MAX_CLUSTERS] = { false }; if (!info) return 0; /* Continue only if SPC is initialised */ @@ -578,8 +579,17 @@ static int __init ve_spc_clk_init(void) continue; } + cluster = topology_physical_package_id(cpu_dev->id); + if (init_opp_table[cluster]) + continue; + if (ve_init_opp_table(cpu_dev)) pr_warn("failed to initialise cpu%d opp table\n", cpu); + else if (dev_pm_opp_set_sharing_cpus(cpu_dev, + topology_core_cpumask(cpu_dev->id))) + pr_warn("failed to mark OPPs shared for cpu%d\n", cpu); + else + init_opp_table[cluster] = true; } platform_device_register_simple("vexpress-spc-cpufreq", -1, NULL, 0); diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi index 8e8a77eb596a..13a3cbe89b5a 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi @@ -88,7 +88,7 @@ reboot { compatible ="syscon-reboot"; - regmap = <&dcfg>; + regmap = <&rst>; offset = <0xb0>; mask = <0x02>; }; @@ -178,6 +178,12 @@ big-endian; }; + rst: syscon@1e60000 { + compatible = "syscon"; + reg = <0x0 0x1e60000 0x0 0x10000>; + little-endian; + }; + scfg: syscon@1fc0000 { compatible = "fsl,ls1028a-scfg", "syscon"; reg = <0x0 0x1fc0000 0x0 0x10000>; @@ -584,7 +590,7 @@ 0x00010004 0x0000003d 0x00010005 0x00000045 0x00010006 0x0000004d - 0x00010007 0x00000045 + 0x00010007 0x00000055 0x00010008 0x0000005e 0x00010009 0x00000066 0x0001000a 0x0000006e diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 6a09ca7644ea..85f4bec22f6d 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -547,6 +547,7 @@ static const struct midr_range spectre_v2_safe_list[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_A53), MIDR_ALL_VERSIONS(MIDR_CORTEX_A55), MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53), + MIDR_ALL_VERSIONS(MIDR_HISI_TSV110), { /* sentinel */ } }; diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 46822afc57e0..9f2165937f7d 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -2098,9 +2098,9 @@ static void unhandled_cp_access(struct kvm_vcpu *vcpu, WARN_ON(1); } - kvm_err("Unsupported guest CP%d access at: %08lx [%08lx]\n", - cp, *vcpu_pc(vcpu), *vcpu_cpsr(vcpu)); - print_sys_reg_instr(params); + print_sys_reg_msg(params, + "Unsupported guest CP%d access at: %08lx [%08lx]\n", + cp, *vcpu_pc(vcpu), *vcpu_cpsr(vcpu)); kvm_inject_undefined(vcpu); } @@ -2233,6 +2233,12 @@ int kvm_handle_cp14_32(struct kvm_vcpu *vcpu, struct kvm_run *run) NULL, 0); } +static bool is_imp_def_sys_reg(struct sys_reg_params *params) +{ + // See ARM DDI 0487E.a, section D12.3.2 + return params->Op0 == 3 && (params->CRn & 0b1011) == 0b1011; +} + static int emulate_sys_reg(struct kvm_vcpu *vcpu, struct sys_reg_params *params) { @@ -2248,10 +2254,12 @@ static int emulate_sys_reg(struct kvm_vcpu *vcpu, if (likely(r)) { perform_access(vcpu, params, r); + } else if (is_imp_def_sys_reg(params)) { + kvm_inject_undefined(vcpu); } else { - kvm_err("Unsupported guest sys_reg access at: %lx [%08lx]\n", - *vcpu_pc(vcpu), *vcpu_cpsr(vcpu)); - print_sys_reg_instr(params); + print_sys_reg_msg(params, + "Unsupported guest sys_reg access at: %lx [%08lx]\n", + *vcpu_pc(vcpu), *vcpu_cpsr(vcpu)); kvm_inject_undefined(vcpu); } return 1; @@ -2360,8 +2368,11 @@ static const struct sys_reg_desc *index_to_sys_reg_desc(struct kvm_vcpu *vcpu, if ((id & KVM_REG_ARM_COPROC_MASK) != KVM_REG_ARM64_SYSREG) return NULL; + if (!index_to_params(id, ¶ms)) + return NULL; + table = get_target_table(vcpu->arch.target, true, &num); - r = find_reg_by_id(id, ¶ms, table, num); + r = find_reg(¶ms, table, num); if (!r) r = find_reg(¶ms, sys_reg_descs, ARRAY_SIZE(sys_reg_descs)); diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h index 9bca0312d798..5a6fc30f5989 100644 --- a/arch/arm64/kvm/sys_regs.h +++ b/arch/arm64/kvm/sys_regs.h @@ -62,11 +62,24 @@ struct sys_reg_desc { #define REG_HIDDEN_USER (1 << 0) /* hidden from userspace ioctls */ #define REG_HIDDEN_GUEST (1 << 1) /* hidden from guest */ -static inline void print_sys_reg_instr(const struct sys_reg_params *p) +static __printf(2, 3) +inline void print_sys_reg_msg(const struct sys_reg_params *p, + char *fmt, ...) { + va_list va; + + va_start(va, fmt); /* Look, we even formatted it for you to paste into the table! */ - kvm_pr_unimpl(" { Op0(%2u), Op1(%2u), CRn(%2u), CRm(%2u), Op2(%2u), func_%s },\n", + kvm_pr_unimpl("%pV { Op0(%2u), Op1(%2u), CRn(%2u), CRm(%2u), Op2(%2u), func_%s },\n", + &(struct va_format){ fmt, &va }, p->Op0, p->Op1, p->CRn, p->CRm, p->Op2, p->is_write ? "write" : "read"); + va_end(va); +} + +static inline void print_sys_reg_instr(const struct sys_reg_params *p) +{ + /* GCC warns on an empty format string */ + print_sys_reg_msg(p, "%s", ""); } static inline bool ignore_write(struct kvm_vcpu *vcpu, diff --git a/arch/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c index 46b76751f3a5..3ec69d9cbe88 100644 --- a/arch/mips/net/ebpf_jit.c +++ b/arch/mips/net/ebpf_jit.c @@ -604,6 +604,7 @@ static void emit_const_to_reg(struct jit_ctx *ctx, int dst, u64 value) static int emit_bpf_tail_call(struct jit_ctx *ctx, int this_idx) { int off, b_off; + int tcc_reg; ctx->flags |= EBPF_SEEN_TC; /* @@ -616,14 +617,14 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx, int this_idx) b_off = b_imm(this_idx + 1, ctx); emit_instr(ctx, bne, MIPS_R_AT, MIPS_R_ZERO, b_off); /* - * if (--TCC < 0) + * if (TCC-- < 0) * goto out; */ /* Delay slot */ - emit_instr(ctx, daddiu, MIPS_R_T5, - (ctx->flags & EBPF_TCC_IN_V1) ? MIPS_R_V1 : MIPS_R_S4, -1); + tcc_reg = (ctx->flags & EBPF_TCC_IN_V1) ? MIPS_R_V1 : MIPS_R_S4; + emit_instr(ctx, daddiu, MIPS_R_T5, tcc_reg, -1); b_off = b_imm(this_idx + 1, ctx); - emit_instr(ctx, bltz, MIPS_R_T5, b_off); + emit_instr(ctx, bltz, tcc_reg, b_off); /* * prog = array->ptrs[index]; * if (prog == NULL) diff --git a/arch/parisc/include/asm/cmpxchg.h b/arch/parisc/include/asm/cmpxchg.h index f627c37dad9c..ab5c215cf46c 100644 --- a/arch/parisc/include/asm/cmpxchg.h +++ b/arch/parisc/include/asm/cmpxchg.h @@ -44,8 +44,14 @@ __xchg(unsigned long x, __volatile__ void *ptr, int size) ** if (((unsigned long)p & 0xf) == 0) ** return __ldcw(p); */ -#define xchg(ptr, x) \ - ((__typeof__(*(ptr)))__xchg((unsigned long)(x), (ptr), sizeof(*(ptr)))) +#define xchg(ptr, x) \ +({ \ + __typeof__(*(ptr)) __ret; \ + __typeof__(*(ptr)) _x_ = (x); \ + __ret = (__typeof__(*(ptr))) \ + __xchg((unsigned long)_x_, (ptr), sizeof(*(ptr))); \ + __ret; \ +}) /* bug catcher for when unsupported size is used - won't link */ extern void __cmpxchg_called_with_bad_pointer(void); diff --git a/arch/parisc/include/asm/kexec.h b/arch/parisc/include/asm/kexec.h index a99ea747d7ed..87e174006995 100644 --- a/arch/parisc/include/asm/kexec.h +++ b/arch/parisc/include/asm/kexec.h @@ -2,8 +2,6 @@ #ifndef _ASM_PARISC_KEXEC_H #define _ASM_PARISC_KEXEC_H -#ifdef CONFIG_KEXEC - /* Maximum physical address we can use pages from */ #define KEXEC_SOURCE_MEMORY_LIMIT (-1UL) /* Maximum address we can reach in physical address mode */ @@ -32,6 +30,4 @@ static inline void crash_setup_regs(struct pt_regs *newregs, #endif /* __ASSEMBLY__ */ -#endif /* CONFIG_KEXEC */ - #endif /* _ASM_PARISC_KEXEC_H */ diff --git a/arch/parisc/kernel/Makefile b/arch/parisc/kernel/Makefile index 2663c8f8be11..068d90950d93 100644 --- a/arch/parisc/kernel/Makefile +++ b/arch/parisc/kernel/Makefile @@ -37,5 +37,5 @@ obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o obj-$(CONFIG_JUMP_LABEL) += jump_label.o obj-$(CONFIG_KGDB) += kgdb.o obj-$(CONFIG_KPROBES) += kprobes.o -obj-$(CONFIG_KEXEC) += kexec.o relocate_kernel.o +obj-$(CONFIG_KEXEC_CORE) += kexec.o relocate_kernel.o obj-$(CONFIG_KEXEC_FILE) += kexec_file.o diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c index 3b330e58a4f0..a6c9f49c6612 100644 --- a/arch/parisc/kernel/drivers.c +++ b/arch/parisc/kernel/drivers.c @@ -810,7 +810,7 @@ EXPORT_SYMBOL(device_to_hwpath); static void walk_native_bus(unsigned long io_io_low, unsigned long io_io_high, struct device *parent); -static void walk_lower_bus(struct parisc_device *dev) +static void __init walk_lower_bus(struct parisc_device *dev) { unsigned long io_io_low, io_io_high; diff --git a/arch/parisc/kernel/pdt.c b/arch/parisc/kernel/pdt.c index 36434d4da381..749c4579db0d 100644 --- a/arch/parisc/kernel/pdt.c +++ b/arch/parisc/kernel/pdt.c @@ -327,8 +327,7 @@ static int pdt_mainloop(void *unused) ((pde & PDT_ADDR_SINGLE_ERR) == 0)) memory_failure(pde >> PAGE_SHIFT, 0); else - soft_offline_page( - pfn_to_page(pde >> PAGE_SHIFT), 0); + soft_offline_page(pde >> PAGE_SHIFT, 0); #else pr_crit("PDT: memory error at 0x%lx ignored.\n" "Rebuild kernel with CONFIG_MEMORY_FAILURE=y " diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h index e9a960e28f3c..1b55fc08f853 100644 --- a/arch/powerpc/include/asm/spinlock.h +++ b/arch/powerpc/include/asm/spinlock.h @@ -36,10 +36,12 @@ #endif #ifdef CONFIG_PPC_PSERIES +DECLARE_STATIC_KEY_FALSE(shared_processor); + #define vcpu_is_preempted vcpu_is_preempted static inline bool vcpu_is_preempted(int cpu) { - if (!firmware_has_feature(FW_FEATURE_SPLPAR)) + if (!static_branch_unlikely(&shared_processor)) return false; return !!(be32_to_cpu(lppaca_of(cpu).yield_count) & 1); } @@ -110,13 +112,8 @@ static inline void splpar_rw_yield(arch_rwlock_t *lock) {}; static inline bool is_shared_processor(void) { -/* - * LPPACA is only available on Pseries so guard anything LPPACA related to - * allow other platforms (which include this common header) to compile. - */ -#ifdef CONFIG_PPC_PSERIES - return (IS_ENABLED(CONFIG_PPC_SPLPAR) && - lppaca_shared_proc(local_paca->lppaca_ptr)); +#ifdef CONFIG_PPC_SPLPAR + return static_branch_unlikely(&shared_processor); #else return false; #endif diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index 15002b51ff18..c92fe7fe9692 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -401,7 +401,7 @@ copy_to_user_mcsafe(void __user *to, const void *from, unsigned long n) return n; } -extern unsigned long __clear_user(void __user *addr, unsigned long size); +unsigned long __arch_clear_user(void __user *addr, unsigned long size); static inline unsigned long clear_user(void __user *addr, unsigned long size) { @@ -409,12 +409,17 @@ static inline unsigned long clear_user(void __user *addr, unsigned long size) might_fault(); if (likely(access_ok(addr, size))) { allow_write_to_user(addr, size); - ret = __clear_user(addr, size); + ret = __arch_clear_user(addr, size); prevent_write_to_user(addr, size); } return ret; } +static inline unsigned long __clear_user(void __user *addr, unsigned long size) +{ + return clear_user(addr, size); +} + extern long strncpy_from_user(char *dst, const char __user *src, long count); extern __must_check long strnlen_user(const char __user *str, long n); diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 5645bc9cbc09..add67498c126 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -619,8 +619,6 @@ void __do_irq(struct pt_regs *regs) trace_irq_entry(regs); - check_stack_overflow(); - /* * Query the platform PIC for the interrupt & ack it. * @@ -652,6 +650,8 @@ void do_IRQ(struct pt_regs *regs) irqsp = hardirq_ctx[raw_smp_processor_id()]; sirqsp = softirq_ctx[raw_smp_processor_id()]; + check_stack_overflow(); + /* Already there ? */ if (unlikely(cursp == irqsp || cursp == sirqsp)) { __do_irq(regs); diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index dc53578193ee..6ff3f896d908 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -4983,7 +4983,8 @@ static void kvmppc_core_destroy_vm_hv(struct kvm *kvm) if (nesting_enabled(kvm)) kvmhv_release_all_nested(kvm); kvm->arch.process_table = 0; - uv_svm_terminate(kvm->arch.lpid); + if (kvm->arch.secure_guest) + uv_svm_terminate(kvm->arch.lpid); kvmhv_set_ptbl_entry(kvm->arch.lpid, 0, 0); } diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 0496e66aaa56..c6fbbd29bd87 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -1117,7 +1117,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) ld r7, VCPU_GPR(R7)(r4) bne ret_to_ultra - lwz r0, VCPU_CR(r4) + ld r0, VCPU_CR(r4) mtcr r0 ld r0, VCPU_GPR(R0)(r4) @@ -1137,7 +1137,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) * R3 = UV_RETURN */ ret_to_ultra: - lwz r0, VCPU_CR(r4) + ld r0, VCPU_CR(r4) mtcr r0 ld r0, VCPU_GPR(R3)(r4) diff --git a/arch/powerpc/lib/string_32.S b/arch/powerpc/lib/string_32.S index f69a6aab7bfb..1ddb26394e8a 100644 --- a/arch/powerpc/lib/string_32.S +++ b/arch/powerpc/lib/string_32.S @@ -17,7 +17,7 @@ CACHELINE_BYTES = L1_CACHE_BYTES LG_CACHELINE_BYTES = L1_CACHE_SHIFT CACHELINE_MASK = (L1_CACHE_BYTES-1) -_GLOBAL(__clear_user) +_GLOBAL(__arch_clear_user) /* * Use dcbz on the complete cache lines in the destination * to set them to zero. This requires that the destination @@ -87,4 +87,4 @@ _GLOBAL(__clear_user) EX_TABLE(8b, 91b) EX_TABLE(9b, 91b) -EXPORT_SYMBOL(__clear_user) +EXPORT_SYMBOL(__arch_clear_user) diff --git a/arch/powerpc/lib/string_64.S b/arch/powerpc/lib/string_64.S index 507b18b1660e..169872bc0892 100644 --- a/arch/powerpc/lib/string_64.S +++ b/arch/powerpc/lib/string_64.S @@ -17,7 +17,7 @@ PPC64_CACHES: .section ".text" /** - * __clear_user: - Zero a block of memory in user space, with less checking. + * __arch_clear_user: - Zero a block of memory in user space, with less checking. * @to: Destination address, in user space. * @n: Number of bytes to zero. * @@ -58,7 +58,7 @@ err3; stb r0,0(r3) mr r3,r4 blr -_GLOBAL_TOC(__clear_user) +_GLOBAL_TOC(__arch_clear_user) cmpdi r4,32 neg r6,r3 li r0,0 @@ -181,4 +181,4 @@ err1; dcbz 0,r3 cmpdi r4,32 blt .Lshort_clear b .Lmedium_clear -EXPORT_SYMBOL(__clear_user) +EXPORT_SYMBOL(__arch_clear_user) diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 9488b63dfc87..617c2777926f 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -289,6 +289,14 @@ void __init mem_init(void) BUILD_BUG_ON(MMU_PAGE_COUNT > 16); #ifdef CONFIG_SWIOTLB + /* + * Some platforms (e.g. 85xx) limit DMA-able memory way below + * 4G. We force memblock to bottom-up mode to ensure that the + * memory allocated in swiotlb_init() is DMA-able. + * As it's the last memblock allocation, no need to reset it + * back to to-down. + */ + memblock_set_bottom_up(true); swiotlb_init(0); #endif diff --git a/arch/powerpc/mm/nohash/8xx.c b/arch/powerpc/mm/nohash/8xx.c index 090af2d2d3e4..96eb8e43f39b 100644 --- a/arch/powerpc/mm/nohash/8xx.c +++ b/arch/powerpc/mm/nohash/8xx.c @@ -103,7 +103,7 @@ static void mmu_patch_addis(s32 *site, long simm) patch_instruction_site(site, instr); } -void __init mmu_mapin_ram_chunk(unsigned long offset, unsigned long top, pgprot_t prot) +static void mmu_mapin_ram_chunk(unsigned long offset, unsigned long top, pgprot_t prot) { unsigned long s = offset; unsigned long v = PAGE_OFFSET + s; diff --git a/arch/powerpc/platforms/pseries/cmm.c b/arch/powerpc/platforms/pseries/cmm.c index 91571841df8a..9dba7e880885 100644 --- a/arch/powerpc/platforms/pseries/cmm.c +++ b/arch/powerpc/platforms/pseries/cmm.c @@ -539,6 +539,16 @@ static int cmm_migratepage(struct balloon_dev_info *b_dev_info, /* balloon page list reference */ get_page(newpage); + /* + * When we migrate a page to a different zone, we have to fixup the + * count of both involved zones as we adjusted the managed page count + * when inflating. + */ + if (page_zone(page) != page_zone(newpage)) { + adjust_managed_page_count(page, 1); + adjust_managed_page_count(newpage, -1); + } + spin_lock_irqsave(&b_dev_info->pages_lock, flags); balloon_page_insert(b_dev_info, newpage); balloon_page_delete(page); diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 0a40201f315f..0c8421dd01ab 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -74,6 +74,9 @@ #include "pseries.h" #include "../../../../drivers/pci/pci.h" +DEFINE_STATIC_KEY_FALSE(shared_processor); +EXPORT_SYMBOL_GPL(shared_processor); + int CMO_PrPSP = -1; int CMO_SecPSP = -1; unsigned long CMO_PageSize = (ASM_CONST(1) << IOMMU_PAGE_SHIFT_4K); @@ -758,6 +761,10 @@ static void __init pSeries_setup_arch(void) if (firmware_has_feature(FW_FEATURE_LPAR)) { vpa_init(boot_cpuid); + + if (lppaca_shared_proc(get_lppaca())) + static_branch_enable(&shared_processor); + ppc_md.power_save = pseries_lpar_idle; ppc_md.enable_pmcs = pseries_lpar_enable_pmcs; #ifdef CONFIG_PCI_IOV diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 759ffb00267c..d8efbaa78d67 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -154,7 +154,7 @@ config GENERIC_HWEIGHT def_bool y config FIX_EARLYCON_MEM - def_bool CONFIG_MMU + def_bool MMU config PGTABLE_LEVELS int diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 7ff0ed4f292e..36ae01761352 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -90,6 +90,27 @@ extern pgd_t swapper_pg_dir[]; #define __S110 PAGE_SHARED_EXEC #define __S111 PAGE_SHARED_EXEC +#define VMALLOC_SIZE (KERN_VIRT_SIZE >> 1) +#define VMALLOC_END (PAGE_OFFSET - 1) +#define VMALLOC_START (PAGE_OFFSET - VMALLOC_SIZE) + +/* + * Roughly size the vmemmap space to be large enough to fit enough + * struct pages to map half the virtual address space. Then + * position vmemmap directly below the VMALLOC region. + */ +#define VMEMMAP_SHIFT \ + (CONFIG_VA_BITS - PAGE_SHIFT - 1 + STRUCT_PAGE_MAX_SHIFT) +#define VMEMMAP_SIZE BIT(VMEMMAP_SHIFT) +#define VMEMMAP_END (VMALLOC_START - 1) +#define VMEMMAP_START (VMALLOC_START - VMEMMAP_SIZE) + +/* + * Define vmemmap for pfn_to_page & page_to_pfn calls. Needed if kernel + * is configured with CONFIG_SPARSEMEM_VMEMMAP enabled. + */ +#define vmemmap ((struct page *)VMEMMAP_START) + static inline int pmd_present(pmd_t pmd) { return (pmd_val(pmd) & (_PAGE_PRESENT | _PAGE_PROT_NONE)); @@ -400,23 +421,6 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma, #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -#define VMALLOC_SIZE (KERN_VIRT_SIZE >> 1) -#define VMALLOC_END (PAGE_OFFSET - 1) -#define VMALLOC_START (PAGE_OFFSET - VMALLOC_SIZE) - -/* - * Roughly size the vmemmap space to be large enough to fit enough - * struct pages to map half the virtual address space. Then - * position vmemmap directly below the VMALLOC region. - */ -#define VMEMMAP_SHIFT \ - (CONFIG_VA_BITS - PAGE_SHIFT - 1 + STRUCT_PAGE_MAX_SHIFT) -#define VMEMMAP_SIZE BIT(VMEMMAP_SHIFT) -#define VMEMMAP_END (VMALLOC_START - 1) -#define VMEMMAP_START (VMALLOC_START - VMEMMAP_SIZE) - -#define vmemmap ((struct page *)VMEMMAP_START) - #define PCI_IO_SIZE SZ_16M #define PCI_IO_END VMEMMAP_START #define PCI_IO_START (PCI_IO_END - PCI_IO_SIZE) diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index 84a6f0a4b120..797802c73dee 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -246,7 +246,7 @@ ENTRY(reset_regs) li t4, 0 li t5, 0 li t6, 0 - csrw sscratch, 0 + csrw CSR_SCRATCH, 0 #ifdef CONFIG_FPU csrr t0, CSR_MISA diff --git a/arch/riscv/mm/Makefile b/arch/riscv/mm/Makefile index 3c8b33258457..a1bd95c8047a 100644 --- a/arch/riscv/mm/Makefile +++ b/arch/riscv/mm/Makefile @@ -10,7 +10,6 @@ obj-y += extable.o obj-$(CONFIG_MMU) += fault.o obj-y += cacheflush.o obj-y += context.o -obj-y += sifive_l2_cache.o ifeq ($(CONFIG_MMU),y) obj-$(CONFIG_SMP) += tlbflush.o diff --git a/arch/riscv/net/bpf_jit_comp.c b/arch/riscv/net/bpf_jit_comp.c index 5451ef3845f2..7fbf56aab661 100644 --- a/arch/riscv/net/bpf_jit_comp.c +++ b/arch/riscv/net/bpf_jit_comp.c @@ -631,14 +631,14 @@ static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx) return -1; emit(rv_bgeu(RV_REG_A2, RV_REG_T1, off >> 1), ctx); - /* if (--TCC < 0) + /* if (TCC-- < 0) * goto out; */ emit(rv_addi(RV_REG_T1, tcc, -1), ctx); off = (tc_ninsn - (ctx->ninsns - start_insn)) << 2; if (is_13b_check(off, insn)) return -1; - emit(rv_blt(RV_REG_T1, RV_REG_ZERO, off >> 1), ctx); + emit(rv_blt(tcc, RV_REG_ZERO, off >> 1), ctx); /* prog = array->ptrs[index]; * if (!prog) diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h index 6da8885251d6..670f14a228e5 100644 --- a/arch/s390/include/asm/timex.h +++ b/arch/s390/include/asm/timex.h @@ -194,9 +194,9 @@ static inline unsigned long long get_tod_clock_monotonic(void) { unsigned long long tod; - preempt_disable(); + preempt_disable_notrace(); tod = get_tod_clock() - *(unsigned long long *) &tod_clock_base[1]; - preempt_enable(); + preempt_enable_notrace(); return tod; } diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S index 9e1660a6b9db..c3597d2e2ae0 100644 --- a/arch/s390/kernel/mcount.S +++ b/arch/s390/kernel/mcount.S @@ -35,6 +35,7 @@ EXPORT_SYMBOL(_mcount) ENTRY(ftrace_caller) .globl ftrace_regs_caller .set ftrace_regs_caller,ftrace_caller + stg %r14,(__SF_GPRS+8*8)(%r15) # save traced function caller lgr %r1,%r15 #if !(defined(CC_USING_HOTPATCH) || defined(CC_USING_NOP_MCOUNT)) aghi %r0,MCOUNT_RETURN_FIXUP diff --git a/arch/s390/kernel/unwind_bc.c b/arch/s390/kernel/unwind_bc.c index da2d4d4c5b0e..707fd99f6734 100644 --- a/arch/s390/kernel/unwind_bc.c +++ b/arch/s390/kernel/unwind_bc.c @@ -36,10 +36,17 @@ static bool update_stack_info(struct unwind_state *state, unsigned long sp) return true; } -static inline bool is_task_pt_regs(struct unwind_state *state, - struct pt_regs *regs) +static inline bool is_final_pt_regs(struct unwind_state *state, + struct pt_regs *regs) { - return task_pt_regs(state->task) == regs; + /* user mode or kernel thread pt_regs at the bottom of task stack */ + if (task_pt_regs(state->task) == regs) + return true; + + /* user mode pt_regs at the bottom of irq stack */ + return state->stack_info.type == STACK_TYPE_IRQ && + state->stack_info.end - sizeof(struct pt_regs) == (unsigned long)regs && + READ_ONCE_NOCHECK(regs->psw.mask) & PSW_MASK_PSTATE; } bool unwind_next_frame(struct unwind_state *state) @@ -80,7 +87,7 @@ bool unwind_next_frame(struct unwind_state *state) if (!on_stack(info, sp, sizeof(struct pt_regs))) goto out_err; regs = (struct pt_regs *) sp; - if (is_task_pt_regs(state, regs)) + if (is_final_pt_regs(state, regs)) goto out_stop; ip = READ_ONCE_NOCHECK(regs->psw.addr); sp = READ_ONCE_NOCHECK(regs->gprs[15]); diff --git a/arch/s390/purgatory/.gitignore b/arch/s390/purgatory/.gitignore index 04a03433c720..c82157f46b18 100644 --- a/arch/s390/purgatory/.gitignore +++ b/arch/s390/purgatory/.gitignore @@ -1,3 +1,4 @@ purgatory +purgatory.chk purgatory.lds purgatory.ro diff --git a/arch/s390/purgatory/Makefile b/arch/s390/purgatory/Makefile index bc0d7a0d0394..c57f8c40e992 100644 --- a/arch/s390/purgatory/Makefile +++ b/arch/s390/purgatory/Makefile @@ -4,7 +4,7 @@ OBJECT_FILES_NON_STANDARD := y purgatory-y := head.o purgatory.o string.o sha256.o mem.o -targets += $(purgatory-y) purgatory.lds purgatory purgatory.ro +targets += $(purgatory-y) purgatory.lds purgatory purgatory.chk purgatory.ro PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y)) $(obj)/sha256.o: $(srctree)/lib/crypto/sha256.c FORCE @@ -15,8 +15,10 @@ CFLAGS_sha256.o := -D__DISABLE_EXPORTS $(obj)/mem.o: $(srctree)/arch/s390/lib/mem.S FORCE $(call if_changed_rule,as_o_S) -$(obj)/string.o: $(srctree)/arch/s390/lib/string.c FORCE - $(call if_changed_rule,cc_o_c) +KCOV_INSTRUMENT := n +GCOV_PROFILE := n +UBSAN_SANITIZE := n +KASAN_SANITIZE := n KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes KBUILD_CFLAGS += -Wno-pointer-sign -Wno-sign-compare @@ -26,15 +28,22 @@ KBUILD_CFLAGS += $(CLANG_FLAGS) KBUILD_CFLAGS += $(call cc-option,-fno-PIE) KBUILD_AFLAGS := $(filter-out -DCC_USING_EXPOLINE,$(KBUILD_AFLAGS)) -LDFLAGS_purgatory := -r --no-undefined -nostdlib -z nodefaultlib -T +# Since we link purgatory with -r unresolved symbols are not checked, so we +# also link a purgatory.chk binary without -r to check for unresolved symbols. +PURGATORY_LDFLAGS := -nostdlib -z nodefaultlib +LDFLAGS_purgatory := -r $(PURGATORY_LDFLAGS) -T +LDFLAGS_purgatory.chk := -e purgatory_start $(PURGATORY_LDFLAGS) $(obj)/purgatory: $(obj)/purgatory.lds $(PURGATORY_OBJS) FORCE $(call if_changed,ld) +$(obj)/purgatory.chk: $(obj)/purgatory FORCE + $(call if_changed,ld) + OBJCOPYFLAGS_purgatory.ro := -O elf64-s390 OBJCOPYFLAGS_purgatory.ro += --remove-section='*debug*' OBJCOPYFLAGS_purgatory.ro += --remove-section='.comment' OBJCOPYFLAGS_purgatory.ro += --remove-section='.note.*' -$(obj)/purgatory.ro: $(obj)/purgatory FORCE +$(obj)/purgatory.ro: $(obj)/purgatory $(obj)/purgatory.chk FORCE $(call if_changed,objcopy) $(obj)/kexec-purgatory.o: $(obj)/kexec-purgatory.S $(obj)/purgatory.ro FORCE diff --git a/arch/s390/purgatory/string.c b/arch/s390/purgatory/string.c new file mode 100644 index 000000000000..c98c22a72db7 --- /dev/null +++ b/arch/s390/purgatory/string.c @@ -0,0 +1,3 @@ +// SPDX-License-Identifier: GPL-2.0 +#define __HAVE_ARCH_MEMCMP /* arch function */ +#include "../lib/string.c" diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index aa976adb7094..1dac210f7d44 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -103,7 +103,7 @@ vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_thunk_$(BITS).o quiet_cmd_check_data_rel = DATAREL $@ define cmd_check_data_rel for obj in $(filter %.o,$^); do \ - ${CROSS_COMPILE}readelf -S $$obj | grep -qF .rel.local && { \ + $(READELF) -S $$obj | grep -qF .rel.local && { \ echo "error: $$obj has data relocations!" >&2; \ exit 1; \ } || true; \ diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 9a89d98c55bd..f118af9f0718 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -376,7 +376,7 @@ int x86_add_exclusive(unsigned int what) * LBR and BTS are still mutually exclusive. */ if (x86_pmu.lbr_pt_coexist && what == x86_lbr_exclusive_pt) - return 0; + goto out; if (!atomic_inc_not_zero(&x86_pmu.lbr_exclusive[what])) { mutex_lock(&pmc_reserve_mutex); @@ -388,6 +388,7 @@ int x86_add_exclusive(unsigned int what) mutex_unlock(&pmc_reserve_mutex); } +out: atomic_inc(&active_events); return 0; @@ -398,11 +399,15 @@ fail_unlock: void x86_del_exclusive(unsigned int what) { + atomic_dec(&active_events); + + /* + * See the comment in x86_add_exclusive(). + */ if (x86_pmu.lbr_pt_coexist && what == x86_lbr_exclusive_pt) return; atomic_dec(&x86_pmu.lbr_exclusive[what]); - atomic_dec(&active_events); } int x86_setup_perfctr(struct perf_event *event) @@ -1642,9 +1647,12 @@ static struct attribute_group x86_pmu_format_group __ro_after_init = { ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr, char *page) { - struct perf_pmu_events_attr *pmu_attr = \ + struct perf_pmu_events_attr *pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr); - u64 config = x86_pmu.event_map(pmu_attr->id); + u64 config = 0; + + if (pmu_attr->id < x86_pmu.max_events) + config = x86_pmu.event_map(pmu_attr->id); /* string trumps id */ if (pmu_attr->event_str) @@ -1713,6 +1721,9 @@ is_visible(struct kobject *kobj, struct attribute *attr, int idx) { struct perf_pmu_events_attr *pmu_attr; + if (idx >= x86_pmu.max_events) + return 0; + pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr.attr); /* str trumps id */ return pmu_attr->event_str || x86_pmu.event_map(idx) ? attr->mode : 0; diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c index 38de4a7f6752..6a3b599ee0fe 100644 --- a/arch/x86/events/intel/bts.c +++ b/arch/x86/events/intel/bts.c @@ -63,9 +63,17 @@ struct bts_buffer { static struct pmu bts_pmu; +static int buf_nr_pages(struct page *page) +{ + if (!PagePrivate(page)) + return 1; + + return 1 << page_private(page); +} + static size_t buf_size(struct page *page) { - return 1 << (PAGE_SHIFT + page_private(page)); + return buf_nr_pages(page) * PAGE_SIZE; } static void * @@ -83,9 +91,7 @@ bts_buffer_setup_aux(struct perf_event *event, void **pages, /* count all the high order buffers */ for (pg = 0, nbuf = 0; pg < nr_pages;) { page = virt_to_page(pages[pg]); - if (WARN_ON_ONCE(!PagePrivate(page) && nr_pages > 1)) - return NULL; - pg += 1 << page_private(page); + pg += buf_nr_pages(page); nbuf++; } @@ -109,7 +115,7 @@ bts_buffer_setup_aux(struct perf_event *event, void **pages, unsigned int __nr_pages; page = virt_to_page(pages[pg]); - __nr_pages = PagePrivate(page) ? 1 << page_private(page) : 1; + __nr_pages = buf_nr_pages(page); buf->buf[nbuf].page = page; buf->buf[nbuf].offset = offset; buf->buf[nbuf].displacement = (pad ? BTS_RECORD_SIZE - pad : 0); diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 5167bd2bb6b1..d6cf5c18a7e0 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -266,10 +266,10 @@ static void smca_configure(unsigned int bank, unsigned int cpu) smca_set_misc_banks_map(bank, cpu); /* Return early if this bank was already initialized. */ - if (smca_banks[bank].hwid) + if (smca_banks[bank].hwid && smca_banks[bank].hwid->hwid_mcatype != 0) return; - if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_IPID(bank), &low, &high)) { + if (rdmsr_safe(MSR_AMD64_SMCA_MCx_IPID(bank), &low, &high)) { pr_warn("Failed to read MCA_IPID for bank %d\n", bank); return; } diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 5f42f25bac8f..2e2a421c8528 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -819,8 +819,8 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, if (quirk_no_way_out) quirk_no_way_out(i, m, regs); + m->bank = i; if (mce_severity(m, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) { - m->bank = i; mce_read_aux(m, i); *msg = tmp; return 1; diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 4cba91ec8049..2f9ec14be3b1 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -710,8 +710,12 @@ static struct chipset early_qrk[] __initdata = { */ { PCI_VENDOR_ID_INTEL, 0x0f00, PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, + { PCI_VENDOR_ID_INTEL, 0x3e20, + PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, { PCI_VENDOR_ID_INTEL, 0x3ec4, PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, + { PCI_VENDOR_ID_INTEL, 0x8a12, + PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, { PCI_VENDOR_ID_BROADCOM, 0x4331, PCI_CLASS_NETWORK_OTHER, PCI_ANY_ID, 0, apple_airport_reset}, {} diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index cfafa320a8cf..cf55629ff0ff 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -402,7 +402,8 @@ static inline void do_cpuid_7_mask(struct kvm_cpuid_entry2 *entry, int index) entry->edx |= F(SPEC_CTRL); if (boot_cpu_has(X86_FEATURE_STIBP)) entry->edx |= F(INTEL_STIBP); - if (boot_cpu_has(X86_FEATURE_SSBD)) + if (boot_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || + boot_cpu_has(X86_FEATURE_AMD_SSBD)) entry->edx |= F(SPEC_CTRL_SSBD); /* * We emulate ARCH_CAPABILITIES in software even @@ -759,7 +760,8 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, entry->ebx |= F(AMD_IBRS); if (boot_cpu_has(X86_FEATURE_STIBP)) entry->ebx |= F(AMD_STIBP); - if (boot_cpu_has(X86_FEATURE_SSBD)) + if (boot_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || + boot_cpu_has(X86_FEATURE_AMD_SSBD)) entry->ebx |= F(AMD_SSBD); if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS)) entry->ebx |= F(AMD_SSB_NO); diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 7675cf754d90..f8f0220b6a66 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -260,10 +260,6 @@ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size) return; } - /* No need to reserve regions that will never be freed. */ - if (md.attribute & EFI_MEMORY_RUNTIME) - return; - size += addr % EFI_PAGE_SIZE; size = round_up(size, EFI_PAGE_SIZE); addr = round_down(addr, EFI_PAGE_SIZE); @@ -293,6 +289,8 @@ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size) early_memunmap(new, new_size); efi_memmap_install(new_phys, num_entries); + e820__range_update(addr, size, E820_TYPE_RAM, E820_TYPE_RESERVED); + e820__update_table(e820_table); } /* diff --git a/block/blk-core.c b/block/blk-core.c index e0a094fddee5..089e890ab208 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -885,11 +885,14 @@ generic_make_request_checks(struct bio *bio) } /* - * For a REQ_NOWAIT based request, return -EOPNOTSUPP - * if queue is not a request based queue. + * Non-mq queues do not honor REQ_NOWAIT, so complete a bio + * with BLK_STS_AGAIN status in order to catch -EAGAIN and + * to give a chance to the caller to repeat request gracefully. */ - if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_mq(q)) - goto not_supported; + if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_mq(q)) { + status = BLK_STS_AGAIN; + goto end_io; + } if (should_fail_bio(bio)) goto end_io; diff --git a/block/blk-flush.c b/block/blk-flush.c index 1777346baf06..3f977c517960 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -69,6 +69,7 @@ #include <linux/blkdev.h> #include <linux/gfp.h> #include <linux/blk-mq.h> +#include <linux/lockdep.h> #include "blk.h" #include "blk-mq.h" @@ -505,6 +506,9 @@ struct blk_flush_queue *blk_alloc_flush_queue(struct request_queue *q, INIT_LIST_HEAD(&fq->flush_queue[1]); INIT_LIST_HEAD(&fq->flush_data_in_flight); + lockdep_register_key(&fq->key); + lockdep_set_class(&fq->mq_flush_lock, &fq->key); + return fq; fail_rq: @@ -519,6 +523,7 @@ void blk_free_flush_queue(struct blk_flush_queue *fq) if (!fq) return; + lockdep_unregister_key(&fq->key); kfree(fq->flush_rq); kfree(fq); } diff --git a/block/blk-iocost.c b/block/blk-iocost.c index e01267f99183..27ca68621137 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -1212,7 +1212,7 @@ static enum hrtimer_restart iocg_waitq_timer_fn(struct hrtimer *timer) return HRTIMER_NORESTART; } -static void iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now, u64 cost) +static bool iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now, u64 cost) { struct ioc *ioc = iocg->ioc; struct blkcg_gq *blkg = iocg_to_blkg(iocg); @@ -1229,11 +1229,11 @@ static void iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now, u64 cost) /* clear or maintain depending on the overage */ if (time_before_eq64(vtime, now->vnow)) { blkcg_clear_delay(blkg); - return; + return false; } if (!atomic_read(&blkg->use_delay) && time_before_eq64(vtime, now->vnow + vmargin)) - return; + return false; /* use delay */ if (cost) { @@ -1250,10 +1250,11 @@ static void iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now, u64 cost) oexpires = ktime_to_ns(hrtimer_get_softexpires(&iocg->delay_timer)); if (hrtimer_is_queued(&iocg->delay_timer) && abs(oexpires - expires) <= margin_ns / 4) - return; + return true; hrtimer_start_range_ns(&iocg->delay_timer, ns_to_ktime(expires), margin_ns / 4, HRTIMER_MODE_ABS); + return true; } static enum hrtimer_restart iocg_delay_timer_fn(struct hrtimer *timer) @@ -1739,7 +1740,9 @@ static void ioc_rqos_throttle(struct rq_qos *rqos, struct bio *bio) */ if (bio_issue_as_root_blkg(bio) || fatal_signal_pending(current)) { atomic64_add(abs_cost, &iocg->abs_vdebt); - iocg_kick_delay(iocg, &now, cost); + if (iocg_kick_delay(iocg, &now, cost)) + blkcg_schedule_throttle(rqos->q, + (bio->bi_opf & REQ_SWAP) == REQ_SWAP); return; } diff --git a/block/blk-map.c b/block/blk-map.c index 3a62e471d81b..b0790268ed9d 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -151,7 +151,7 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq, return 0; unmap_rq: - __blk_rq_unmap_user(bio); + blk_rq_unmap_user(bio); fail: rq->bio = NULL; return ret; diff --git a/block/blk.h b/block/blk.h index 6842f28c033e..0b8884353f6b 100644 --- a/block/blk.h +++ b/block/blk.h @@ -30,6 +30,7 @@ struct blk_flush_queue { * at the same time */ struct request *orig_rq; + struct lock_class_key key; spinlock_t mq_flush_lock; }; diff --git a/block/bsg-lib.c b/block/bsg-lib.c index 347dda16c2f4..6cbb7926534c 100644 --- a/block/bsg-lib.c +++ b/block/bsg-lib.c @@ -266,7 +266,7 @@ static blk_status_t bsg_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req = bd->rq; struct bsg_set *bset = container_of(q->tag_set, struct bsg_set, tag_set); - int sts = BLK_STS_IOERR; + blk_status_t sts = BLK_STS_IOERR; int ret; blk_mq_start_request(req); diff --git a/crypto/asymmetric_keys/asym_tpm.c b/crypto/asymmetric_keys/asym_tpm.c index d16d893bd195..378b18b9bc34 100644 --- a/crypto/asymmetric_keys/asym_tpm.c +++ b/crypto/asymmetric_keys/asym_tpm.c @@ -470,6 +470,7 @@ static int tpm_key_encrypt(struct tpm_key *tk, if (ret < 0) goto error_free_tfm; + ret = -ENOMEM; req = akcipher_request_alloc(tfm, GFP_KERNEL); if (!req) goto error_free_tfm; diff --git a/crypto/asymmetric_keys/public_key.c b/crypto/asymmetric_keys/public_key.c index 364b9df9d631..d7f43d4ea925 100644 --- a/crypto/asymmetric_keys/public_key.c +++ b/crypto/asymmetric_keys/public_key.c @@ -184,6 +184,7 @@ static int software_key_eds_op(struct kernel_pkey_params *params, if (IS_ERR(tfm)) return PTR_ERR(tfm); + ret = -ENOMEM; req = akcipher_request_alloc(tfm, GFP_KERNEL); if (!req) goto error_free_tfm; diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 57532465fb83..b4607dd96185 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1296,10 +1296,10 @@ static int nbd_start_device_ioctl(struct nbd_device *nbd, struct block_device *b mutex_unlock(&nbd->config_lock); ret = wait_event_interruptible(config->recv_wq, atomic_read(&config->recv_threads) == 0); - if (ret) { + if (ret) sock_shutdown(nbd); - flush_workqueue(nbd->recv_workq); - } + flush_workqueue(nbd->recv_workq); + mutex_lock(&nbd->config_lock); nbd_bdev_reset(bdev); /* user requested, ignore socket errors */ diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c index d6a6adfd5159..4c5d99f87813 100644 --- a/drivers/block/xen-blkback/xenbus.c +++ b/drivers/block/xen-blkback/xenbus.c @@ -190,6 +190,9 @@ static int xen_blkif_map(struct xen_blkif_ring *ring, grant_ref_t *gref, { int err; struct xen_blkif *blkif = ring->blkif; + const struct blkif_common_sring *sring_common; + RING_IDX rsp_prod, req_prod; + unsigned int size; /* Already connected through? */ if (ring->irq) @@ -200,46 +203,62 @@ static int xen_blkif_map(struct xen_blkif_ring *ring, grant_ref_t *gref, if (err < 0) return err; + sring_common = (struct blkif_common_sring *)ring->blk_ring; + rsp_prod = READ_ONCE(sring_common->rsp_prod); + req_prod = READ_ONCE(sring_common->req_prod); + switch (blkif->blk_protocol) { case BLKIF_PROTOCOL_NATIVE: { - struct blkif_sring *sring; - sring = (struct blkif_sring *)ring->blk_ring; - BACK_RING_INIT(&ring->blk_rings.native, sring, - XEN_PAGE_SIZE * nr_grefs); + struct blkif_sring *sring_native = + (struct blkif_sring *)ring->blk_ring; + + BACK_RING_ATTACH(&ring->blk_rings.native, sring_native, + rsp_prod, XEN_PAGE_SIZE * nr_grefs); + size = __RING_SIZE(sring_native, XEN_PAGE_SIZE * nr_grefs); break; } case BLKIF_PROTOCOL_X86_32: { - struct blkif_x86_32_sring *sring_x86_32; - sring_x86_32 = (struct blkif_x86_32_sring *)ring->blk_ring; - BACK_RING_INIT(&ring->blk_rings.x86_32, sring_x86_32, - XEN_PAGE_SIZE * nr_grefs); + struct blkif_x86_32_sring *sring_x86_32 = + (struct blkif_x86_32_sring *)ring->blk_ring; + + BACK_RING_ATTACH(&ring->blk_rings.x86_32, sring_x86_32, + rsp_prod, XEN_PAGE_SIZE * nr_grefs); + size = __RING_SIZE(sring_x86_32, XEN_PAGE_SIZE * nr_grefs); break; } case BLKIF_PROTOCOL_X86_64: { - struct blkif_x86_64_sring *sring_x86_64; - sring_x86_64 = (struct blkif_x86_64_sring *)ring->blk_ring; - BACK_RING_INIT(&ring->blk_rings.x86_64, sring_x86_64, - XEN_PAGE_SIZE * nr_grefs); + struct blkif_x86_64_sring *sring_x86_64 = + (struct blkif_x86_64_sring *)ring->blk_ring; + + BACK_RING_ATTACH(&ring->blk_rings.x86_64, sring_x86_64, + rsp_prod, XEN_PAGE_SIZE * nr_grefs); + size = __RING_SIZE(sring_x86_64, XEN_PAGE_SIZE * nr_grefs); break; } default: BUG(); } + err = -EIO; + if (req_prod - rsp_prod > size) + goto fail; + err = bind_interdomain_evtchn_to_irqhandler(blkif->domid, evtchn, xen_blkif_be_int, 0, "blkif-backend", ring); - if (err < 0) { - xenbus_unmap_ring_vfree(blkif->be->dev, ring->blk_ring); - ring->blk_rings.common.sring = NULL; - return err; - } + if (err < 0) + goto fail; ring->irq = err; return 0; + +fail: + xenbus_unmap_ring_vfree(blkif->be->dev, ring->blk_ring); + ring->blk_rings.common.sring = NULL; + return err; } static int xen_blkif_disconnect(struct xen_blkif *blkif) @@ -1131,7 +1150,8 @@ static struct xenbus_driver xen_blkbk_driver = { .ids = xen_blkbk_ids, .probe = xen_blkbk_probe, .remove = xen_blkbk_remove, - .otherend_changed = frontend_changed + .otherend_changed = frontend_changed, + .allow_rebind = true, }; int xen_blkif_xenbus_init(void) diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index a74d03913822..c02be06c5299 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -1113,8 +1113,8 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity, if (!VDEV_IS_EXTENDED(info->vdevice)) { err = xen_translate_vdev(info->vdevice, &minor, &offset); if (err) - return err; - nr_parts = PARTS_PER_DISK; + return err; + nr_parts = PARTS_PER_DISK; } else { minor = BLKIF_MINOR_EXT(info->vdevice); nr_parts = PARTS_PER_EXT_DISK; diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index 56887c6877a7..f4d1597df0a2 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -981,7 +981,8 @@ static int sysc_disable_module(struct device *dev) return ret; } - if (ddata->cfg.quirks & SYSC_QUIRK_SWSUP_MSTANDBY) + if (ddata->cfg.quirks & (SYSC_QUIRK_SWSUP_MSTANDBY) || + ddata->cfg.quirks & (SYSC_QUIRK_FORCE_MSTANDBY)) best_mode = SYSC_IDLE_FORCE; reg &= ~(SYSC_IDLE_MASK << regbits->midle_shift); @@ -1583,6 +1584,10 @@ static int sysc_reset(struct sysc *ddata) sysc_val |= sysc_mask; sysc_write(ddata, sysc_offset, sysc_val); + if (ddata->cfg.srst_udelay) + usleep_range(ddata->cfg.srst_udelay, + ddata->cfg.srst_udelay * 2); + if (ddata->clk_enable_quirk) ddata->clk_enable_quirk(ddata); diff --git a/drivers/char/random.c b/drivers/char/random.c index 909e0c3d82ea..cda12933a17d 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -2175,6 +2175,7 @@ const struct file_operations urandom_fops = { .read = urandom_read, .write = random_write, .unlocked_ioctl = random_ioctl, + .compat_ioctl = compat_ptr_ioctl, .fasync = random_fasync, .llseek = noop_llseek, }; diff --git a/drivers/char/tpm/tpm-dev-common.c b/drivers/char/tpm/tpm-dev-common.c index 2ec47a69a2a6..b23b0b999232 100644 --- a/drivers/char/tpm/tpm-dev-common.c +++ b/drivers/char/tpm/tpm-dev-common.c @@ -61,6 +61,12 @@ static void tpm_dev_async_work(struct work_struct *work) mutex_lock(&priv->buffer_mutex); priv->command_enqueued = false; + ret = tpm_try_get_ops(priv->chip); + if (ret) { + priv->response_length = ret; + goto out; + } + ret = tpm_dev_transmit(priv->chip, priv->space, priv->data_buffer, sizeof(priv->data_buffer)); tpm_put_ops(priv->chip); @@ -68,6 +74,7 @@ static void tpm_dev_async_work(struct work_struct *work) priv->response_length = ret; mod_timer(&priv->user_read_timer, jiffies + (120 * HZ)); } +out: mutex_unlock(&priv->buffer_mutex); wake_up_interruptible(&priv->async_wait); } @@ -204,6 +211,7 @@ ssize_t tpm_common_write(struct file *file, const char __user *buf, if (file->f_flags & O_NONBLOCK) { priv->command_enqueued = true; queue_work(tpm_dev_wq, &priv->async_work); + tpm_put_ops(priv->chip); mutex_unlock(&priv->buffer_mutex); return size; } diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h index b9e1547be6b5..5620747da0cf 100644 --- a/drivers/char/tpm/tpm.h +++ b/drivers/char/tpm/tpm.h @@ -218,7 +218,6 @@ int tpm2_pcr_read(struct tpm_chip *chip, u32 pcr_idx, int tpm2_pcr_extend(struct tpm_chip *chip, u32 pcr_idx, struct tpm_digest *digests); int tpm2_get_random(struct tpm_chip *chip, u8 *dest, size_t max); -void tpm2_flush_context(struct tpm_chip *chip, u32 handle); ssize_t tpm2_get_tpm_pt(struct tpm_chip *chip, u32 property_id, u32 *value, const char *desc); diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c index fdb457704aa7..13696deceae8 100644 --- a/drivers/char/tpm/tpm2-cmd.c +++ b/drivers/char/tpm/tpm2-cmd.c @@ -362,6 +362,7 @@ void tpm2_flush_context(struct tpm_chip *chip, u32 handle) tpm_transmit_cmd(chip, &buf, 0, "flushing context"); tpm_buf_destroy(&buf); } +EXPORT_SYMBOL_GPL(tpm2_flush_context); struct tpm2_get_cap_out { u8 more_data; diff --git a/drivers/char/tpm/tpm_ftpm_tee.c b/drivers/char/tpm/tpm_ftpm_tee.c index 6640a14dbe48..22bf553ccf9d 100644 --- a/drivers/char/tpm/tpm_ftpm_tee.c +++ b/drivers/char/tpm/tpm_ftpm_tee.c @@ -32,7 +32,7 @@ static const uuid_t ftpm_ta_uuid = 0x82, 0xCB, 0x34, 0x3F, 0xB7, 0xF3, 0x78, 0x96); /** - * ftpm_tee_tpm_op_recv - retrieve fTPM response. + * ftpm_tee_tpm_op_recv() - retrieve fTPM response. * @chip: the tpm_chip description as specified in driver/char/tpm/tpm.h. * @buf: the buffer to store data. * @count: the number of bytes to read. @@ -61,7 +61,7 @@ static int ftpm_tee_tpm_op_recv(struct tpm_chip *chip, u8 *buf, size_t count) } /** - * ftpm_tee_tpm_op_send - send TPM commands through the TEE shared memory. + * ftpm_tee_tpm_op_send() - send TPM commands through the TEE shared memory. * @chip: the tpm_chip description as specified in driver/char/tpm/tpm.h * @buf: the buffer to send. * @len: the number of bytes to send. @@ -208,7 +208,7 @@ static int ftpm_tee_match(struct tee_ioctl_version_data *ver, const void *data) } /** - * ftpm_tee_probe - initialize the fTPM + * ftpm_tee_probe() - initialize the fTPM * @pdev: the platform_device description. * * Return: @@ -298,7 +298,7 @@ out_tee_session: } /** - * ftpm_tee_remove - remove the TPM device + * ftpm_tee_remove() - remove the TPM device * @pdev: the platform_device description. * * Return: @@ -328,6 +328,19 @@ static int ftpm_tee_remove(struct platform_device *pdev) return 0; } +/** + * ftpm_tee_shutdown() - shutdown the TPM device + * @pdev: the platform_device description. + */ +static void ftpm_tee_shutdown(struct platform_device *pdev) +{ + struct ftpm_tee_private *pvt_data = dev_get_drvdata(&pdev->dev); + + tee_shm_free(pvt_data->shm); + tee_client_close_session(pvt_data->ctx, pvt_data->session); + tee_client_close_context(pvt_data->ctx); +} + static const struct of_device_id of_ftpm_tee_ids[] = { { .compatible = "microsoft,ftpm" }, { } @@ -341,6 +354,7 @@ static struct platform_driver ftpm_tee_driver = { }, .probe = ftpm_tee_probe, .remove = ftpm_tee_remove, + .shutdown = ftpm_tee_shutdown, }; module_platform_driver(ftpm_tee_driver); diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c index 8af2cee1a762..bb0343ffd235 100644 --- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -978,13 +978,13 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq, if (wait_startup(chip, 0) != 0) { rc = -ENODEV; - goto out_err; + goto err_start; } /* Take control of the TPM's interrupt hardware and shut it off */ rc = tpm_tis_read32(priv, TPM_INT_ENABLE(priv->locality), &intmask); if (rc < 0) - goto out_err; + goto err_start; intmask |= TPM_INTF_CMD_READY_INT | TPM_INTF_LOCALITY_CHANGE_INT | TPM_INTF_DATA_AVAIL_INT | TPM_INTF_STS_VALID_INT; @@ -993,21 +993,21 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq, rc = tpm_chip_start(chip); if (rc) - goto out_err; + goto err_start; + rc = tpm2_probe(chip); - tpm_chip_stop(chip); if (rc) - goto out_err; + goto err_probe; rc = tpm_tis_read32(priv, TPM_DID_VID(0), &vendor); if (rc < 0) - goto out_err; + goto err_probe; priv->manufacturer_id = vendor; rc = tpm_tis_read8(priv, TPM_RID(0), &rid); if (rc < 0) - goto out_err; + goto err_probe; dev_info(dev, "%s TPM (device-id 0x%X, rev-id %d)\n", (chip->flags & TPM_CHIP_FLAG_TPM2) ? "2.0" : "1.2", @@ -1016,13 +1016,13 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq, probe = probe_itpm(chip); if (probe < 0) { rc = -ENODEV; - goto out_err; + goto err_probe; } /* Figure out the capabilities */ rc = tpm_tis_read32(priv, TPM_INTF_CAPS(priv->locality), &intfcaps); if (rc < 0) - goto out_err; + goto err_probe; dev_dbg(dev, "TPM interface capabilities (0x%x):\n", intfcaps); @@ -1056,10 +1056,9 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq, if (tpm_get_timeouts(chip)) { dev_err(dev, "Could not get TPM timeouts and durations\n"); rc = -ENODEV; - goto out_err; + goto err_probe; } - tpm_chip_start(chip); chip->flags |= TPM_CHIP_FLAG_IRQ; if (irq) { tpm_tis_probe_irq_single(chip, intmask, IRQF_SHARED, @@ -1070,18 +1069,20 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq, } else { tpm_tis_probe_irq(chip, intmask); } - tpm_chip_stop(chip); } + tpm_chip_stop(chip); + rc = tpm_chip_register(chip); if (rc) - goto out_err; - - if (chip->ops->clk_enable != NULL) - chip->ops->clk_enable(chip, false); + goto err_start; return 0; -out_err: + +err_probe: + tpm_chip_stop(chip); + +err_start: if ((chip->ops != NULL) && (chip->ops->clk_enable != NULL)) chip->ops->clk_enable(chip, false); diff --git a/drivers/clk/at91/at91sam9260.c b/drivers/clk/at91/at91sam9260.c index 0aabe49aed09..a9d4234758d7 100644 --- a/drivers/clk/at91/at91sam9260.c +++ b/drivers/clk/at91/at91sam9260.c @@ -348,7 +348,7 @@ static void __init at91sam926x_pmc_setup(struct device_node *np, return; mainxtal_name = of_clk_get_parent_name(np, i); - regmap = syscon_node_to_regmap(np); + regmap = device_node_to_regmap(np); if (IS_ERR(regmap)) return; diff --git a/drivers/clk/at91/at91sam9rl.c b/drivers/clk/at91/at91sam9rl.c index 0ac34cdaa106..77fe83a73bf4 100644 --- a/drivers/clk/at91/at91sam9rl.c +++ b/drivers/clk/at91/at91sam9rl.c @@ -83,7 +83,7 @@ static void __init at91sam9rl_pmc_setup(struct device_node *np) return; mainxtal_name = of_clk_get_parent_name(np, i); - regmap = syscon_node_to_regmap(np); + regmap = device_node_to_regmap(np); if (IS_ERR(regmap)) return; diff --git a/drivers/clk/at91/at91sam9x5.c b/drivers/clk/at91/at91sam9x5.c index 0855f3a80cc7..086cf0b4955c 100644 --- a/drivers/clk/at91/at91sam9x5.c +++ b/drivers/clk/at91/at91sam9x5.c @@ -146,7 +146,7 @@ static void __init at91sam9x5_pmc_setup(struct device_node *np, return; mainxtal_name = of_clk_get_parent_name(np, i); - regmap = syscon_node_to_regmap(np); + regmap = device_node_to_regmap(np); if (IS_ERR(regmap)) return; diff --git a/drivers/clk/at91/pmc.c b/drivers/clk/at91/pmc.c index 0b03cfae3a9d..b71515acdec1 100644 --- a/drivers/clk/at91/pmc.c +++ b/drivers/clk/at91/pmc.c @@ -275,7 +275,7 @@ static int __init pmc_register_ops(void) np = of_find_matching_node(NULL, sama5d2_pmc_dt_ids); - pmcreg = syscon_node_to_regmap(np); + pmcreg = device_node_to_regmap(np); if (IS_ERR(pmcreg)) return PTR_ERR(pmcreg); diff --git a/drivers/clk/at91/sama5d2.c b/drivers/clk/at91/sama5d2.c index 0de1108737db..ff7e3f727082 100644 --- a/drivers/clk/at91/sama5d2.c +++ b/drivers/clk/at91/sama5d2.c @@ -162,7 +162,7 @@ static void __init sama5d2_pmc_setup(struct device_node *np) return; mainxtal_name = of_clk_get_parent_name(np, i); - regmap = syscon_node_to_regmap(np); + regmap = device_node_to_regmap(np); if (IS_ERR(regmap)) return; diff --git a/drivers/clk/at91/sama5d4.c b/drivers/clk/at91/sama5d4.c index 25b156d4e645..a6dee4a3b6e4 100644 --- a/drivers/clk/at91/sama5d4.c +++ b/drivers/clk/at91/sama5d4.c @@ -136,7 +136,7 @@ static void __init sama5d4_pmc_setup(struct device_node *np) return; mainxtal_name = of_clk_get_parent_name(np, i); - regmap = syscon_node_to_regmap(np); + regmap = device_node_to_regmap(np); if (IS_ERR(regmap)) return; diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index b68e200829f2..6a11239ccde3 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -3249,6 +3249,34 @@ static inline void clk_debug_unregister(struct clk_core *core) } #endif +static void clk_core_reparent_orphans_nolock(void) +{ + struct clk_core *orphan; + struct hlist_node *tmp2; + + /* + * walk the list of orphan clocks and reparent any that newly finds a + * parent. + */ + hlist_for_each_entry_safe(orphan, tmp2, &clk_orphan_list, child_node) { + struct clk_core *parent = __clk_init_parent(orphan); + + /* + * We need to use __clk_set_parent_before() and _after() to + * to properly migrate any prepare/enable count of the orphan + * clock. This is important for CLK_IS_CRITICAL clocks, which + * are enabled during init but might not have a parent yet. + */ + if (parent) { + /* update the clk tree topology */ + __clk_set_parent_before(orphan, parent); + __clk_set_parent_after(orphan, parent, NULL); + __clk_recalc_accuracies(orphan); + __clk_recalc_rates(orphan, 0); + } + } +} + /** * __clk_core_init - initialize the data structures in a struct clk_core * @core: clk_core being initialized @@ -3259,8 +3287,6 @@ static inline void clk_debug_unregister(struct clk_core *core) static int __clk_core_init(struct clk_core *core) { int ret; - struct clk_core *orphan; - struct hlist_node *tmp2; unsigned long rate; if (!core) @@ -3407,27 +3433,8 @@ static int __clk_core_init(struct clk_core *core) clk_enable_unlock(flags); } - /* - * walk the list of orphan clocks and reparent any that newly finds a - * parent. - */ - hlist_for_each_entry_safe(orphan, tmp2, &clk_orphan_list, child_node) { - struct clk_core *parent = __clk_init_parent(orphan); + clk_core_reparent_orphans_nolock(); - /* - * We need to use __clk_set_parent_before() and _after() to - * to properly migrate any prepare/enable count of the orphan - * clock. This is important for CLK_IS_CRITICAL clocks, which - * are enabled during init but might not have a parent yet. - */ - if (parent) { - /* update the clk tree topology */ - __clk_set_parent_before(orphan, parent); - __clk_set_parent_after(orphan, parent, NULL); - __clk_recalc_accuracies(orphan); - __clk_recalc_rates(orphan, 0); - } - } kref_init(&core->ref); out: @@ -4179,6 +4186,13 @@ int clk_notifier_unregister(struct clk *clk, struct notifier_block *nb) EXPORT_SYMBOL_GPL(clk_notifier_unregister); #ifdef CONFIG_OF +static void clk_core_reparent_orphans(void) +{ + clk_prepare_lock(); + clk_core_reparent_orphans_nolock(); + clk_prepare_unlock(); +} + /** * struct of_clk_provider - Clock provider registration structure * @link: Entry in global list of clock providers @@ -4274,6 +4288,8 @@ int of_clk_add_provider(struct device_node *np, mutex_unlock(&of_clk_mutex); pr_debug("Added clock from %pOF\n", np); + clk_core_reparent_orphans(); + ret = of_clk_set_defaults(np, true); if (ret < 0) of_clk_del_provider(np); @@ -4309,6 +4325,8 @@ int of_clk_add_hw_provider(struct device_node *np, mutex_unlock(&of_clk_mutex); pr_debug("Added clk_hw provider from %pOF\n", np); + clk_core_reparent_orphans(); + ret = of_clk_set_defaults(np, true); if (ret < 0) of_clk_del_provider(np); diff --git a/drivers/clk/imx/clk-composite-8m.c b/drivers/clk/imx/clk-composite-8m.c index 388bdb94f841..d3486ee79ab5 100644 --- a/drivers/clk/imx/clk-composite-8m.c +++ b/drivers/clk/imx/clk-composite-8m.c @@ -142,6 +142,7 @@ struct clk *imx8m_clk_composite_flags(const char *name, mux->reg = reg; mux->shift = PCG_PCS_SHIFT; mux->mask = PCG_PCS_MASK; + mux->lock = &imx_ccm_lock; div = kzalloc(sizeof(*div), GFP_KERNEL); if (!div) @@ -161,6 +162,7 @@ struct clk *imx8m_clk_composite_flags(const char *name, gate_hw = &gate->hw; gate->reg = reg; gate->bit_idx = PCG_CGC_SHIFT; + gate->lock = &imx_ccm_lock; hw = clk_hw_register_composite(NULL, name, parent_names, num_parents, mux_hw, &clk_mux_ops, div_hw, diff --git a/drivers/clk/imx/clk-imx7ulp.c b/drivers/clk/imx/clk-imx7ulp.c index 3fdf3d494f0a..281191b55b3a 100644 --- a/drivers/clk/imx/clk-imx7ulp.c +++ b/drivers/clk/imx/clk-imx7ulp.c @@ -40,6 +40,7 @@ static const struct clk_div_table ulp_div_table[] = { { .val = 5, .div = 16, }, { .val = 6, .div = 32, }, { .val = 7, .div = 64, }, + { /* sentinel */ }, }; static const int pcc2_uart_clk_ids[] __initconst = { diff --git a/drivers/clk/imx/clk-pll14xx.c b/drivers/clk/imx/clk-pll14xx.c index 5c458199060a..3636c8035c7d 100644 --- a/drivers/clk/imx/clk-pll14xx.c +++ b/drivers/clk/imx/clk-pll14xx.c @@ -159,7 +159,7 @@ static int clk_pll14xx_wait_lock(struct clk_pll14xx *pll) { u32 val; - return readl_poll_timeout(pll->base, val, val & LOCK_TIMEOUT_US, 0, + return readl_poll_timeout(pll->base, val, val & LOCK_STATUS, 0, LOCK_TIMEOUT_US); } diff --git a/drivers/clk/qcom/gcc-sc7180.c b/drivers/clk/qcom/gcc-sc7180.c index 38424e63bcae..7f59fb8da033 100644 --- a/drivers/clk/qcom/gcc-sc7180.c +++ b/drivers/clk/qcom/gcc-sc7180.c @@ -2186,7 +2186,8 @@ static struct gdsc hlos1_vote_mmnoc_mmu_tbu_hf0_gdsc = { .pd = { .name = "hlos1_vote_mmnoc_mmu_tbu_hf0_gdsc", }, - .pwrsts = PWRSTS_OFF_ON | VOTABLE, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE, }; static struct gdsc hlos1_vote_mmnoc_mmu_tbu_sf_gdsc = { @@ -2194,7 +2195,8 @@ static struct gdsc hlos1_vote_mmnoc_mmu_tbu_sf_gdsc = { .pd = { .name = "hlos1_vote_mmnoc_mmu_tbu_sf_gdsc", }, - .pwrsts = PWRSTS_OFF_ON | VOTABLE, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE, }; static struct gdsc *gcc_sc7180_gdscs[] = { diff --git a/drivers/clk/qcom/gpucc-msm8998.c b/drivers/clk/qcom/gpucc-msm8998.c index e5e2492b20c5..9b3923af02a1 100644 --- a/drivers/clk/qcom/gpucc-msm8998.c +++ b/drivers/clk/qcom/gpucc-msm8998.c @@ -242,10 +242,12 @@ static struct clk_branch gfx3d_isense_clk = { static struct gdsc gpu_cx_gdsc = { .gdscr = 0x1004, + .gds_hw_ctrl = 0x1008, .pd = { .name = "gpu_cx", }, .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE, }; static struct gdsc gpu_gx_gdsc = { diff --git a/drivers/cpufreq/vexpress-spc-cpufreq.c b/drivers/cpufreq/vexpress-spc-cpufreq.c index 506e3f2bf53a..83c85d3d67e3 100644 --- a/drivers/cpufreq/vexpress-spc-cpufreq.c +++ b/drivers/cpufreq/vexpress-spc-cpufreq.c @@ -434,7 +434,7 @@ static int ve_spc_cpufreq_init(struct cpufreq_policy *policy) if (cur_cluster < MAX_CLUSTERS) { int cpu; - cpumask_copy(policy->cpus, topology_core_cpumask(policy->cpu)); + dev_pm_opp_get_sharing_cpus(cpu_dev, policy->cpus); for_each_cpu(cpu, policy->cpus) per_cpu(physical_cluster, cpu) = cur_cluster; diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig index 417dad635526..5c8272329a65 100644 --- a/drivers/edac/Kconfig +++ b/drivers/edac/Kconfig @@ -462,7 +462,7 @@ config EDAC_ALTERA_SDMMC config EDAC_SIFIVE bool "Sifive platform EDAC driver" - depends on EDAC=y && RISCV + depends on EDAC=y && SIFIVE_L2 help Support for error detection and correction on the SiFive SoCs. diff --git a/drivers/firmware/efi/earlycon.c b/drivers/firmware/efi/earlycon.c index c9a0efca17b0..d4077db6dc97 100644 --- a/drivers/firmware/efi/earlycon.c +++ b/drivers/firmware/efi/earlycon.c @@ -13,18 +13,57 @@ #include <asm/early_ioremap.h> +static const struct console *earlycon_console __initdata; static const struct font_desc *font; static u32 efi_x, efi_y; static u64 fb_base; static pgprot_t fb_prot; +static void *efi_fb; + +/* + * EFI earlycon needs to use early_memremap() to map the framebuffer. + * But early_memremap() is not usable for 'earlycon=efifb keep_bootcon', + * memremap() should be used instead. memremap() will be available after + * paging_init() which is earlier than initcall callbacks. Thus adding this + * early initcall function early_efi_map_fb() to map the whole EFI framebuffer. + */ +static int __init efi_earlycon_remap_fb(void) +{ + /* bail if there is no bootconsole or it has been disabled already */ + if (!earlycon_console || !(earlycon_console->flags & CON_ENABLED)) + return 0; + + if (pgprot_val(fb_prot) == pgprot_val(PAGE_KERNEL)) + efi_fb = memremap(fb_base, screen_info.lfb_size, MEMREMAP_WB); + else + efi_fb = memremap(fb_base, screen_info.lfb_size, MEMREMAP_WC); + + return efi_fb ? 0 : -ENOMEM; +} +early_initcall(efi_earlycon_remap_fb); + +static int __init efi_earlycon_unmap_fb(void) +{ + /* unmap the bootconsole fb unless keep_bootcon has left it enabled */ + if (efi_fb && !(earlycon_console->flags & CON_ENABLED)) + memunmap(efi_fb); + return 0; +} +late_initcall(efi_earlycon_unmap_fb); static __ref void *efi_earlycon_map(unsigned long start, unsigned long len) { + if (efi_fb) + return efi_fb + start; + return early_memremap_prot(fb_base + start, len, pgprot_val(fb_prot)); } static __ref void efi_earlycon_unmap(void *addr, unsigned long len) { + if (efi_fb) + return; + early_memunmap(addr, len); } @@ -201,6 +240,7 @@ static int __init efi_earlycon_setup(struct earlycon_device *device, efi_earlycon_scroll_up(); device->con->write = efi_earlycon_write; + earlycon_console = device->con; return 0; } EARLYCON_DECLARE(efifb, efi_earlycon_setup); diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 407816da9fcb..2b02cb165f16 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -979,6 +979,24 @@ static int __init efi_memreserve_map_root(void) return 0; } +static int efi_mem_reserve_iomem(phys_addr_t addr, u64 size) +{ + struct resource *res, *parent; + + res = kzalloc(sizeof(struct resource), GFP_ATOMIC); + if (!res) + return -ENOMEM; + + res->name = "reserved"; + res->flags = IORESOURCE_MEM; + res->start = addr; + res->end = addr + size - 1; + + /* we expect a conflict with a 'System RAM' region */ + parent = request_resource_conflict(&iomem_resource, res); + return parent ? request_resource(parent, res) : 0; +} + int __ref efi_mem_reserve_persistent(phys_addr_t addr, u64 size) { struct linux_efi_memreserve *rsv; @@ -1003,7 +1021,7 @@ int __ref efi_mem_reserve_persistent(phys_addr_t addr, u64 size) rsv->entry[index].size = size; memunmap(rsv); - return 0; + return efi_mem_reserve_iomem(addr, size); } memunmap(rsv); } @@ -1013,6 +1031,12 @@ int __ref efi_mem_reserve_persistent(phys_addr_t addr, u64 size) if (!rsv) return -ENOMEM; + rc = efi_mem_reserve_iomem(__pa(rsv), SZ_4K); + if (rc) { + free_page((unsigned long)rsv); + return rc; + } + /* * The memremap() call above assumes that a linux_efi_memreserve entry * never crosses a page boundary, so let's ensure that this remains true @@ -1029,7 +1053,7 @@ int __ref efi_mem_reserve_persistent(phys_addr_t addr, u64 size) efi_memreserve_root->next = __pa(rsv); spin_unlock(&efi_mem_reserve_persistent_lock); - return 0; + return efi_mem_reserve_iomem(addr, size); } static int __init efi_memreserve_root_init(void) diff --git a/drivers/firmware/efi/libstub/gop.c b/drivers/firmware/efi/libstub/gop.c index 0101ca4c13b1..b7bf1e993b8b 100644 --- a/drivers/firmware/efi/libstub/gop.c +++ b/drivers/firmware/efi/libstub/gop.c @@ -84,30 +84,6 @@ setup_pixel_info(struct screen_info *si, u32 pixels_per_scan_line, } static efi_status_t -__gop_query32(efi_system_table_t *sys_table_arg, - struct efi_graphics_output_protocol_32 *gop32, - struct efi_graphics_output_mode_info **info, - unsigned long *size, u64 *fb_base) -{ - struct efi_graphics_output_protocol_mode_32 *mode; - efi_graphics_output_protocol_query_mode query_mode; - efi_status_t status; - unsigned long m; - - m = gop32->mode; - mode = (struct efi_graphics_output_protocol_mode_32 *)m; - query_mode = (void *)(unsigned long)gop32->query_mode; - - status = __efi_call_early(query_mode, (void *)gop32, mode->mode, size, - info); - if (status != EFI_SUCCESS) - return status; - - *fb_base = mode->frame_buffer_base; - return status; -} - -static efi_status_t setup_gop32(efi_system_table_t *sys_table_arg, struct screen_info *si, efi_guid_t *proto, unsigned long size, void **gop_handle) { @@ -119,7 +95,7 @@ setup_gop32(efi_system_table_t *sys_table_arg, struct screen_info *si, u64 fb_base; struct efi_pixel_bitmask pixel_info; int pixel_format; - efi_status_t status = EFI_NOT_FOUND; + efi_status_t status; u32 *handles = (u32 *)(unsigned long)gop_handle; int i; @@ -128,6 +104,7 @@ setup_gop32(efi_system_table_t *sys_table_arg, struct screen_info *si, nr_gops = size / sizeof(u32); for (i = 0; i < nr_gops; i++) { + struct efi_graphics_output_protocol_mode_32 *mode; struct efi_graphics_output_mode_info *info = NULL; efi_guid_t conout_proto = EFI_CONSOLE_OUT_DEVICE_GUID; bool conout_found = false; @@ -145,9 +122,11 @@ setup_gop32(efi_system_table_t *sys_table_arg, struct screen_info *si, if (status == EFI_SUCCESS) conout_found = true; - status = __gop_query32(sys_table_arg, gop32, &info, &size, - ¤t_fb_base); - if (status == EFI_SUCCESS && (!first_gop || conout_found) && + mode = (void *)(unsigned long)gop32->mode; + info = (void *)(unsigned long)mode->info; + current_fb_base = mode->frame_buffer_base; + + if ((!first_gop || conout_found) && info->pixel_format != PIXEL_BLT_ONLY) { /* * Systems that use the UEFI Console Splitter may @@ -175,7 +154,7 @@ setup_gop32(efi_system_table_t *sys_table_arg, struct screen_info *si, /* Did we find any GOPs? */ if (!first_gop) - goto out; + return EFI_NOT_FOUND; /* EFI framebuffer */ si->orig_video_isVGA = VIDEO_TYPE_EFI; @@ -197,32 +176,8 @@ setup_gop32(efi_system_table_t *sys_table_arg, struct screen_info *si, si->lfb_size = si->lfb_linelength * si->lfb_height; si->capabilities |= VIDEO_CAPABILITY_SKIP_QUIRKS; -out: - return status; -} - -static efi_status_t -__gop_query64(efi_system_table_t *sys_table_arg, - struct efi_graphics_output_protocol_64 *gop64, - struct efi_graphics_output_mode_info **info, - unsigned long *size, u64 *fb_base) -{ - struct efi_graphics_output_protocol_mode_64 *mode; - efi_graphics_output_protocol_query_mode query_mode; - efi_status_t status; - unsigned long m; - - m = gop64->mode; - mode = (struct efi_graphics_output_protocol_mode_64 *)m; - query_mode = (void *)(unsigned long)gop64->query_mode; - - status = __efi_call_early(query_mode, (void *)gop64, mode->mode, size, - info); - if (status != EFI_SUCCESS) - return status; - *fb_base = mode->frame_buffer_base; - return status; + return EFI_SUCCESS; } static efi_status_t @@ -237,7 +192,7 @@ setup_gop64(efi_system_table_t *sys_table_arg, struct screen_info *si, u64 fb_base; struct efi_pixel_bitmask pixel_info; int pixel_format; - efi_status_t status = EFI_NOT_FOUND; + efi_status_t status; u64 *handles = (u64 *)(unsigned long)gop_handle; int i; @@ -246,6 +201,7 @@ setup_gop64(efi_system_table_t *sys_table_arg, struct screen_info *si, nr_gops = size / sizeof(u64); for (i = 0; i < nr_gops; i++) { + struct efi_graphics_output_protocol_mode_64 *mode; struct efi_graphics_output_mode_info *info = NULL; efi_guid_t conout_proto = EFI_CONSOLE_OUT_DEVICE_GUID; bool conout_found = false; @@ -263,9 +219,11 @@ setup_gop64(efi_system_table_t *sys_table_arg, struct screen_info *si, if (status == EFI_SUCCESS) conout_found = true; - status = __gop_query64(sys_table_arg, gop64, &info, &size, - ¤t_fb_base); - if (status == EFI_SUCCESS && (!first_gop || conout_found) && + mode = (void *)(unsigned long)gop64->mode; + info = (void *)(unsigned long)mode->info; + current_fb_base = mode->frame_buffer_base; + + if ((!first_gop || conout_found) && info->pixel_format != PIXEL_BLT_ONLY) { /* * Systems that use the UEFI Console Splitter may @@ -293,7 +251,7 @@ setup_gop64(efi_system_table_t *sys_table_arg, struct screen_info *si, /* Did we find any GOPs? */ if (!first_gop) - goto out; + return EFI_NOT_FOUND; /* EFI framebuffer */ si->orig_video_isVGA = VIDEO_TYPE_EFI; @@ -315,8 +273,8 @@ setup_gop64(efi_system_table_t *sys_table_arg, struct screen_info *si, si->lfb_size = si->lfb_linelength * si->lfb_height; si->capabilities |= VIDEO_CAPABILITY_SKIP_QUIRKS; -out: - return status; + + return EFI_SUCCESS; } /* diff --git a/drivers/firmware/efi/rci2-table.c b/drivers/firmware/efi/rci2-table.c index 76b0c354a027..de1a9a1f9f14 100644 --- a/drivers/firmware/efi/rci2-table.c +++ b/drivers/firmware/efi/rci2-table.c @@ -81,6 +81,9 @@ static int __init efi_rci2_sysfs_init(void) struct kobject *tables_kobj; int ret = -ENOMEM; + if (rci2_table_phys == EFI_INVALID_TABLE_ADDR) + return 0; + rci2_base = memremap(rci2_table_phys, sizeof(struct rci2_table_global_hdr), MEMREMAP_WB); diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c index dc27b1a88e93..b696e4598a24 100644 --- a/drivers/gpio/gpiolib-of.c +++ b/drivers/gpio/gpiolib-of.c @@ -23,6 +23,29 @@ #include "gpiolib.h" #include "gpiolib-of.h" +/** + * of_gpio_spi_cs_get_count() - special GPIO counting for SPI + * Some elder GPIO controllers need special quirks. Currently we handle + * the Freescale GPIO controller with bindings that doesn't use the + * established "cs-gpios" for chip selects but instead rely on + * "gpios" for the chip select lines. If we detect this, we redirect + * the counting of "cs-gpios" to count "gpios" transparent to the + * driver. + */ +static int of_gpio_spi_cs_get_count(struct device *dev, const char *con_id) +{ + struct device_node *np = dev->of_node; + + if (!IS_ENABLED(CONFIG_SPI_MASTER)) + return 0; + if (!con_id || strcmp(con_id, "cs")) + return 0; + if (!of_device_is_compatible(np, "fsl,spi") && + !of_device_is_compatible(np, "aeroflexgaisler,spictrl")) + return 0; + return of_gpio_named_count(np, "gpios"); +} + /* * This is used by external users of of_gpio_count() from <linux/of_gpio.h> * @@ -35,6 +58,10 @@ int of_gpio_get_count(struct device *dev, const char *con_id) char propname[32]; unsigned int i; + ret = of_gpio_spi_cs_get_count(dev, con_id); + if (ret > 0) + return ret; + for (i = 0; i < ARRAY_SIZE(gpio_suffixes); i++) { if (con_id) snprintf(propname, sizeof(propname), "%s-%s", diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c index 7ae087b0504d..88b6fcaa20be 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c @@ -1313,6 +1313,7 @@ static int gsc_remove(struct platform_device *pdev) { struct device *dev = &pdev->dev; + component_del(dev, &gsc_component_ops); pm_runtime_dont_use_autosuspend(dev); pm_runtime_disable(dev); diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c index ce1b64f4dd44..12ba74788cce 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power.c +++ b/drivers/gpu/drm/i915/display/intel_display_power.c @@ -3688,6 +3688,151 @@ static const struct i915_power_well_desc icl_power_wells[] = { }, }; +static const struct i915_power_well_desc ehl_power_wells[] = { + { + .name = "always-on", + .always_on = true, + .domains = POWER_DOMAIN_MASK, + .ops = &i9xx_always_on_power_well_ops, + .id = DISP_PW_ID_NONE, + }, + { + .name = "power well 1", + /* Handled by the DMC firmware */ + .always_on = true, + .domains = 0, + .ops = &hsw_power_well_ops, + .id = SKL_DISP_PW_1, + { + .hsw.regs = &hsw_power_well_regs, + .hsw.idx = ICL_PW_CTL_IDX_PW_1, + .hsw.has_fuses = true, + }, + }, + { + .name = "DC off", + .domains = ICL_DISPLAY_DC_OFF_POWER_DOMAINS, + .ops = &gen9_dc_off_power_well_ops, + .id = SKL_DISP_DC_OFF, + }, + { + .name = "power well 2", + .domains = ICL_PW_2_POWER_DOMAINS, + .ops = &hsw_power_well_ops, + .id = SKL_DISP_PW_2, + { + .hsw.regs = &hsw_power_well_regs, + .hsw.idx = ICL_PW_CTL_IDX_PW_2, + .hsw.has_fuses = true, + }, + }, + { + .name = "power well 3", + .domains = ICL_PW_3_POWER_DOMAINS, + .ops = &hsw_power_well_ops, + .id = DISP_PW_ID_NONE, + { + .hsw.regs = &hsw_power_well_regs, + .hsw.idx = ICL_PW_CTL_IDX_PW_3, + .hsw.irq_pipe_mask = BIT(PIPE_B), + .hsw.has_vga = true, + .hsw.has_fuses = true, + }, + }, + { + .name = "DDI A IO", + .domains = ICL_DDI_IO_A_POWER_DOMAINS, + .ops = &hsw_power_well_ops, + .id = DISP_PW_ID_NONE, + { + .hsw.regs = &icl_ddi_power_well_regs, + .hsw.idx = ICL_PW_CTL_IDX_DDI_A, + }, + }, + { + .name = "DDI B IO", + .domains = ICL_DDI_IO_B_POWER_DOMAINS, + .ops = &hsw_power_well_ops, + .id = DISP_PW_ID_NONE, + { + .hsw.regs = &icl_ddi_power_well_regs, + .hsw.idx = ICL_PW_CTL_IDX_DDI_B, + }, + }, + { + .name = "DDI C IO", + .domains = ICL_DDI_IO_C_POWER_DOMAINS, + .ops = &hsw_power_well_ops, + .id = DISP_PW_ID_NONE, + { + .hsw.regs = &icl_ddi_power_well_regs, + .hsw.idx = ICL_PW_CTL_IDX_DDI_C, + }, + }, + { + .name = "DDI D IO", + .domains = ICL_DDI_IO_D_POWER_DOMAINS, + .ops = &hsw_power_well_ops, + .id = DISP_PW_ID_NONE, + { + .hsw.regs = &icl_ddi_power_well_regs, + .hsw.idx = ICL_PW_CTL_IDX_DDI_D, + }, + }, + { + .name = "AUX A", + .domains = ICL_AUX_A_IO_POWER_DOMAINS, + .ops = &hsw_power_well_ops, + .id = DISP_PW_ID_NONE, + { + .hsw.regs = &icl_aux_power_well_regs, + .hsw.idx = ICL_PW_CTL_IDX_AUX_A, + }, + }, + { + .name = "AUX B", + .domains = ICL_AUX_B_IO_POWER_DOMAINS, + .ops = &hsw_power_well_ops, + .id = DISP_PW_ID_NONE, + { + .hsw.regs = &icl_aux_power_well_regs, + .hsw.idx = ICL_PW_CTL_IDX_AUX_B, + }, + }, + { + .name = "AUX C", + .domains = ICL_AUX_C_TC1_IO_POWER_DOMAINS, + .ops = &hsw_power_well_ops, + .id = DISP_PW_ID_NONE, + { + .hsw.regs = &icl_aux_power_well_regs, + .hsw.idx = ICL_PW_CTL_IDX_AUX_C, + }, + }, + { + .name = "AUX D", + .domains = ICL_AUX_D_TC2_IO_POWER_DOMAINS, + .ops = &hsw_power_well_ops, + .id = DISP_PW_ID_NONE, + { + .hsw.regs = &icl_aux_power_well_regs, + .hsw.idx = ICL_PW_CTL_IDX_AUX_D, + }, + }, + { + .name = "power well 4", + .domains = ICL_PW_4_POWER_DOMAINS, + .ops = &hsw_power_well_ops, + .id = DISP_PW_ID_NONE, + { + .hsw.regs = &hsw_power_well_regs, + .hsw.idx = ICL_PW_CTL_IDX_PW_4, + .hsw.has_fuses = true, + .hsw.irq_pipe_mask = BIT(PIPE_C), + }, + }, +}; + static const struct i915_power_well_desc tgl_power_wells[] = { { .name = "always-on", @@ -3832,7 +3977,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = { { .name = "AUX A", .domains = TGL_AUX_A_IO_POWER_DOMAINS, - .ops = &icl_combo_phy_aux_power_well_ops, + .ops = &hsw_power_well_ops, .id = DISP_PW_ID_NONE, { .hsw.regs = &icl_aux_power_well_regs, @@ -3842,7 +3987,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = { { .name = "AUX B", .domains = TGL_AUX_B_IO_POWER_DOMAINS, - .ops = &icl_combo_phy_aux_power_well_ops, + .ops = &hsw_power_well_ops, .id = DISP_PW_ID_NONE, { .hsw.regs = &icl_aux_power_well_regs, @@ -3852,7 +3997,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = { { .name = "AUX C", .domains = TGL_AUX_C_IO_POWER_DOMAINS, - .ops = &icl_combo_phy_aux_power_well_ops, + .ops = &hsw_power_well_ops, .id = DISP_PW_ID_NONE, { .hsw.regs = &icl_aux_power_well_regs, @@ -4162,6 +4307,8 @@ int intel_power_domains_init(struct drm_i915_private *dev_priv) */ if (IS_GEN(dev_priv, 12)) { err = set_power_wells(power_domains, tgl_power_wells); + } else if (IS_ELKHARTLAKE(dev_priv)) { + err = set_power_wells(power_domains, ehl_power_wells); } else if (IS_GEN(dev_priv, 11)) { err = set_power_wells(power_domains, icl_power_wells); } else if (IS_CANNONLAKE(dev_priv)) { diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index 337ba17b1e0e..42385277c684 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -2167,8 +2167,7 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data, ext_data.fpriv = file->driver_priv; if (client_is_banned(ext_data.fpriv)) { DRM_DEBUG("client %s[%d] banned from creating ctx\n", - current->comm, - pid_nr(get_task_pid(current, PIDTYPE_PID))); + current->comm, task_pid_nr(current)); return -EIO; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index f0998f1225af..bc3a67226163 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -2694,6 +2694,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, err = eb_submit(&eb); err_request: add_to_client(eb.request, file); + i915_request_get(eb.request); i915_request_add(eb.request); if (fences) @@ -2709,6 +2710,7 @@ err_request: fput(out_fence->file); } } + i915_request_put(eb.request); err_batch_unpin: if (eb.batch_flags & I915_DISPATCH_SECURE) diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c index e451298d11c3..2477a1e5a166 100644 --- a/drivers/gpu/drm/i915/gvt/dmabuf.c +++ b/drivers/gpu/drm/i915/gvt/dmabuf.c @@ -36,13 +36,32 @@ #define GEN8_DECODE_PTE(pte) (pte & GENMASK_ULL(63, 12)) +static int vgpu_pin_dma_address(struct intel_vgpu *vgpu, + unsigned long size, + dma_addr_t dma_addr) +{ + int ret = 0; + + if (intel_gvt_hypervisor_dma_pin_guest_page(vgpu, dma_addr)) + ret = -EINVAL; + + return ret; +} + +static void vgpu_unpin_dma_address(struct intel_vgpu *vgpu, + dma_addr_t dma_addr) +{ + intel_gvt_hypervisor_dma_unmap_guest_page(vgpu, dma_addr); +} + static int vgpu_gem_get_pages( struct drm_i915_gem_object *obj) { struct drm_i915_private *dev_priv = to_i915(obj->base.dev); + struct intel_vgpu *vgpu; struct sg_table *st; struct scatterlist *sg; - int i, ret; + int i, j, ret; gen8_pte_t __iomem *gtt_entries; struct intel_vgpu_fb_info *fb_info; u32 page_num; @@ -51,6 +70,10 @@ static int vgpu_gem_get_pages( if (WARN_ON(!fb_info)) return -ENODEV; + vgpu = fb_info->obj->vgpu; + if (WARN_ON(!vgpu)) + return -ENODEV; + st = kmalloc(sizeof(*st), GFP_KERNEL); if (unlikely(!st)) return -ENOMEM; @@ -64,21 +87,53 @@ static int vgpu_gem_get_pages( gtt_entries = (gen8_pte_t __iomem *)dev_priv->ggtt.gsm + (fb_info->start >> PAGE_SHIFT); for_each_sg(st->sgl, sg, page_num, i) { + dma_addr_t dma_addr = + GEN8_DECODE_PTE(readq(>t_entries[i])); + if (vgpu_pin_dma_address(vgpu, PAGE_SIZE, dma_addr)) { + ret = -EINVAL; + goto out; + } + sg->offset = 0; sg->length = PAGE_SIZE; - sg_dma_address(sg) = - GEN8_DECODE_PTE(readq(>t_entries[i])); sg_dma_len(sg) = PAGE_SIZE; + sg_dma_address(sg) = dma_addr; } __i915_gem_object_set_pages(obj, st, PAGE_SIZE); +out: + if (ret) { + dma_addr_t dma_addr; + + for_each_sg(st->sgl, sg, i, j) { + dma_addr = sg_dma_address(sg); + if (dma_addr) + vgpu_unpin_dma_address(vgpu, dma_addr); + } + sg_free_table(st); + kfree(st); + } + + return ret; - return 0; } static void vgpu_gem_put_pages(struct drm_i915_gem_object *obj, struct sg_table *pages) { + struct scatterlist *sg; + + if (obj->base.dma_buf) { + struct intel_vgpu_fb_info *fb_info = obj->gvt_info; + struct intel_vgpu_dmabuf_obj *obj = fb_info->obj; + struct intel_vgpu *vgpu = obj->vgpu; + int i; + + for_each_sg(pages->sgl, sg, fb_info->size, i) + vgpu_unpin_dma_address(vgpu, + sg_dma_address(sg)); + } + sg_free_table(pages); kfree(pages); } @@ -163,6 +218,7 @@ static struct drm_i915_gem_object *vgpu_create_gem(struct drm_device *dev, drm_gem_private_object_init(dev, &obj->base, roundup(info->size, PAGE_SIZE)); i915_gem_object_init(obj, &intel_vgpu_gem_ops, &lock_class); + i915_gem_object_set_readonly(obj); obj->read_domains = I915_GEM_DOMAIN_GTT; obj->write_domain = 0; diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index bb9fe6bf5275..1043e6d564df 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -341,6 +341,10 @@ static int gdrst_mmio_write(struct intel_vgpu *vgpu, unsigned int offset, gvt_dbg_mmio("vgpu%d: request VCS2 Reset\n", vgpu->id); engine_mask |= BIT(VCS1); } + if (data & GEN9_GRDOM_GUC) { + gvt_dbg_mmio("vgpu%d: request GUC Reset\n", vgpu->id); + vgpu_vreg_t(vgpu, GUC_STATUS) |= GS_MIA_IN_RESET; + } engine_mask &= INTEL_INFO(vgpu->gvt->dev_priv)->engine_mask; } @@ -1636,6 +1640,16 @@ static int edp_psr_imr_iir_write(struct intel_vgpu *vgpu, return 0; } +static int guc_status_read(struct intel_vgpu *vgpu, + unsigned int offset, void *p_data, + unsigned int bytes) +{ + /* keep MIA_IN_RESET before clearing */ + read_vreg(vgpu, offset, p_data, bytes); + vgpu_vreg(vgpu, offset) &= ~GS_MIA_IN_RESET; + return 0; +} + static int mmio_read_from_hw(struct intel_vgpu *vgpu, unsigned int offset, void *p_data, unsigned int bytes) { @@ -2672,6 +2686,8 @@ static int init_generic_mmio_info(struct intel_gvt *gvt) MMIO_DH(EDP_PSR_IMR, D_BDW_PLUS, NULL, edp_psr_imr_iir_write); MMIO_DH(EDP_PSR_IIR, D_BDW_PLUS, NULL, edp_psr_imr_iir_write); + MMIO_DH(GUC_STATUS, D_ALL, guc_status_read, NULL); + return 0; } diff --git a/drivers/gpu/drm/i915/gvt/hypercall.h b/drivers/gpu/drm/i915/gvt/hypercall.h index 4862fb12778e..b19a3b1ea4c1 100644 --- a/drivers/gpu/drm/i915/gvt/hypercall.h +++ b/drivers/gpu/drm/i915/gvt/hypercall.h @@ -62,6 +62,8 @@ struct intel_gvt_mpt { unsigned long size, dma_addr_t *dma_addr); void (*dma_unmap_guest_page)(unsigned long handle, dma_addr_t dma_addr); + int (*dma_pin_guest_page)(unsigned long handle, dma_addr_t dma_addr); + int (*map_gfn_to_mfn)(unsigned long handle, unsigned long gfn, unsigned long mfn, unsigned int nr, bool map); int (*set_trap_area)(unsigned long handle, u64 start, u64 end, diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index 04a5a0d90823..3259a1fa69e1 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -1916,6 +1916,28 @@ err_unlock: return ret; } +static int kvmgt_dma_pin_guest_page(unsigned long handle, dma_addr_t dma_addr) +{ + struct kvmgt_guest_info *info; + struct gvt_dma *entry; + int ret = 0; + + if (!handle_valid(handle)) + return -ENODEV; + + info = (struct kvmgt_guest_info *)handle; + + mutex_lock(&info->vgpu->vdev.cache_lock); + entry = __gvt_cache_find_dma_addr(info->vgpu, dma_addr); + if (entry) + kref_get(&entry->ref); + else + ret = -ENOMEM; + mutex_unlock(&info->vgpu->vdev.cache_lock); + + return ret; +} + static void __gvt_dma_release(struct kref *ref) { struct gvt_dma *entry = container_of(ref, typeof(*entry), ref); @@ -2027,6 +2049,7 @@ static struct intel_gvt_mpt kvmgt_mpt = { .gfn_to_mfn = kvmgt_gfn_to_pfn, .dma_map_guest_page = kvmgt_dma_map_guest_page, .dma_unmap_guest_page = kvmgt_dma_unmap_guest_page, + .dma_pin_guest_page = kvmgt_dma_pin_guest_page, .set_opregion = kvmgt_set_opregion, .set_edid = kvmgt_set_edid, .get_vfio_device = kvmgt_get_vfio_device, diff --git a/drivers/gpu/drm/i915/gvt/mpt.h b/drivers/gpu/drm/i915/gvt/mpt.h index 0f9440128123..9ad224df9c68 100644 --- a/drivers/gpu/drm/i915/gvt/mpt.h +++ b/drivers/gpu/drm/i915/gvt/mpt.h @@ -255,6 +255,21 @@ static inline void intel_gvt_hypervisor_dma_unmap_guest_page( } /** + * intel_gvt_hypervisor_dma_pin_guest_page - pin guest dma buf + * @vgpu: a vGPU + * @dma_addr: guest dma addr + * + * Returns: + * 0 on success, negative error code if failed. + */ +static inline int +intel_gvt_hypervisor_dma_pin_guest_page(struct intel_vgpu *vgpu, + dma_addr_t dma_addr) +{ + return intel_gvt_host.mpt->dma_pin_guest_page(vgpu->handle, dma_addr); +} + +/** * intel_gvt_hypervisor_map_gfn_to_mfn - map a GFN region to MFN * @vgpu: a vGPU * @gfn: guest PFN diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c index d5a6e4e3d0fd..85bd9bf4f6ee 100644 --- a/drivers/gpu/drm/i915/gvt/vgpu.c +++ b/drivers/gpu/drm/i915/gvt/vgpu.c @@ -212,9 +212,9 @@ static void intel_gvt_update_vgpu_types(struct intel_gvt *gvt) */ void intel_gvt_activate_vgpu(struct intel_vgpu *vgpu) { - mutex_lock(&vgpu->gvt->lock); + mutex_lock(&vgpu->vgpu_lock); vgpu->active = true; - mutex_unlock(&vgpu->gvt->lock); + mutex_unlock(&vgpu->vgpu_lock); } /** diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 73079b503724..4fd3d76db346 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -9405,11 +9405,9 @@ enum skl_power_gate { #define _ICL_AUX_REG_IDX(pw_idx) ((pw_idx) - ICL_PW_CTL_IDX_AUX_A) #define _ICL_AUX_ANAOVRD1_A 0x162398 #define _ICL_AUX_ANAOVRD1_B 0x6C398 -#define _TGL_AUX_ANAOVRD1_C 0x160398 #define ICL_AUX_ANAOVRD1(pw_idx) _MMIO(_PICK(_ICL_AUX_REG_IDX(pw_idx), \ _ICL_AUX_ANAOVRD1_A, \ - _ICL_AUX_ANAOVRD1_B, \ - _TGL_AUX_ANAOVRD1_C)) + _ICL_AUX_ANAOVRD1_B)) #define ICL_AUX_ANAOVRD1_LDO_BYPASS (1 << 7) #define ICL_AUX_ANAOVRD1_ENABLE (1 << 0) @@ -11994,7 +11992,7 @@ enum skl_power_gate { /* This register controls the Display State Buffer (DSB) engines. */ #define _DSBSL_INSTANCE_BASE 0x70B00 #define DSBSL_INSTANCE(pipe, id) (_DSBSL_INSTANCE_BASE + \ - (pipe) * 0x1000 + (id) * 100) + (pipe) * 0x1000 + (id) * 0x100) #define DSB_HEAD(pipe, id) _MMIO(DSBSL_INSTANCE(pipe, id) + 0x0) #define DSB_TAIL(pipe, id) _MMIO(DSBSL_INSTANCE(pipe, id) + 0x4) #define DSB_CTRL(pipe, id) _MMIO(DSBSL_INSTANCE(pipe, id) + 0x8) diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index bbd71af00a91..765bec89fc0d 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -300,11 +300,11 @@ void i915_request_retire_upto(struct i915_request *rq) } static int -__i915_request_await_execution(struct i915_request *rq, - struct i915_request *signal, - void (*hook)(struct i915_request *rq, - struct dma_fence *signal), - gfp_t gfp) +__await_execution(struct i915_request *rq, + struct i915_request *signal, + void (*hook)(struct i915_request *rq, + struct dma_fence *signal), + gfp_t gfp) { struct execute_cb *cb; @@ -341,6 +341,8 @@ __i915_request_await_execution(struct i915_request *rq, } spin_unlock_irq(&signal->lock); + /* Copy across semaphore status as we need the same behaviour */ + rq->sched.flags |= signal->sched.flags; return 0; } @@ -811,31 +813,21 @@ already_busywaiting(struct i915_request *rq) } static int -emit_semaphore_wait(struct i915_request *to, - struct i915_request *from, - gfp_t gfp) +__emit_semaphore_wait(struct i915_request *to, + struct i915_request *from, + u32 seqno) { const int has_token = INTEL_GEN(to->i915) >= 12; u32 hwsp_offset; - int len; + int len, err; u32 *cs; GEM_BUG_ON(INTEL_GEN(to->i915) < 8); - /* Just emit the first semaphore we see as request space is limited. */ - if (already_busywaiting(to) & from->engine->mask) - goto await_fence; - - if (i915_request_await_start(to, from) < 0) - goto await_fence; - - /* Only submit our spinner after the signaler is running! */ - if (__i915_request_await_execution(to, from, NULL, gfp)) - goto await_fence; - /* We need to pin the signaler's HWSP until we are finished reading. */ - if (intel_timeline_read_hwsp(from, to, &hwsp_offset)) - goto await_fence; + err = intel_timeline_read_hwsp(from, to, &hwsp_offset); + if (err) + return err; len = 4; if (has_token) @@ -858,7 +850,7 @@ emit_semaphore_wait(struct i915_request *to, MI_SEMAPHORE_POLL | MI_SEMAPHORE_SAD_GTE_SDD) + has_token; - *cs++ = from->fence.seqno; + *cs++ = seqno; *cs++ = hwsp_offset; *cs++ = 0; if (has_token) { @@ -867,6 +859,28 @@ emit_semaphore_wait(struct i915_request *to, } intel_ring_advance(to, cs); + return 0; +} + +static int +emit_semaphore_wait(struct i915_request *to, + struct i915_request *from, + gfp_t gfp) +{ + /* Just emit the first semaphore we see as request space is limited. */ + if (already_busywaiting(to) & from->engine->mask) + goto await_fence; + + if (i915_request_await_start(to, from) < 0) + goto await_fence; + + /* Only submit our spinner after the signaler is running! */ + if (__await_execution(to, from, NULL, gfp)) + goto await_fence; + + if (__emit_semaphore_wait(to, from, from->fence.seqno)) + goto await_fence; + to->sched.semaphores |= from->engine->mask; to->sched.flags |= I915_SCHED_HAS_SEMAPHORE_CHAIN; return 0; @@ -980,6 +994,57 @@ i915_request_await_dma_fence(struct i915_request *rq, struct dma_fence *fence) return 0; } +static bool intel_timeline_sync_has_start(struct intel_timeline *tl, + struct dma_fence *fence) +{ + return __intel_timeline_sync_is_later(tl, + fence->context, + fence->seqno - 1); +} + +static int intel_timeline_sync_set_start(struct intel_timeline *tl, + const struct dma_fence *fence) +{ + return __intel_timeline_sync_set(tl, fence->context, fence->seqno - 1); +} + +static int +__i915_request_await_execution(struct i915_request *to, + struct i915_request *from, + void (*hook)(struct i915_request *rq, + struct dma_fence *signal)) +{ + int err; + + /* Submit both requests at the same time */ + err = __await_execution(to, from, hook, I915_FENCE_GFP); + if (err) + return err; + + /* Squash repeated depenendices to the same timelines */ + if (intel_timeline_sync_has_start(i915_request_timeline(to), + &from->fence)) + return 0; + + /* Ensure both start together [after all semaphores in signal] */ + if (intel_engine_has_semaphores(to->engine)) + err = __emit_semaphore_wait(to, from, from->fence.seqno - 1); + else + err = i915_request_await_start(to, from); + if (err < 0) + return err; + + /* Couple the dependency tree for PI on this exposed to->fence */ + if (to->engine->schedule) { + err = i915_sched_node_add_dependency(&to->sched, &from->sched); + if (err < 0) + return err; + } + + return intel_timeline_sync_set_start(i915_request_timeline(to), + &from->fence); +} + int i915_request_await_execution(struct i915_request *rq, struct dma_fence *fence, @@ -1013,8 +1078,7 @@ i915_request_await_execution(struct i915_request *rq, if (dma_fence_is_i915(fence)) ret = __i915_request_await_execution(rq, to_request(fence), - hook, - I915_FENCE_GFP); + hook); else ret = i915_sw_fence_await_dma_fence(&rq->submit, fence, I915_FENCE_TIMEOUT, diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c index 010d67f48ad9..247a9671bca5 100644 --- a/drivers/gpu/drm/i915/i915_scheduler.c +++ b/drivers/gpu/drm/i915/i915_scheduler.c @@ -474,7 +474,6 @@ void i915_sched_node_fini(struct i915_sched_node *node) * so we may be called out-of-order. */ list_for_each_entry_safe(dep, tmp, &node->signalers_list, signal_link) { - GEM_BUG_ON(!node_signaled(dep->signaler)); GEM_BUG_ON(!list_empty(&dep->dfs_link)); list_del(&dep->wait_link); diff --git a/drivers/gpu/drm/i915/i915_sw_fence_work.c b/drivers/gpu/drm/i915/i915_sw_fence_work.c index 07552cd544f2..8538ee7a521d 100644 --- a/drivers/gpu/drm/i915/i915_sw_fence_work.c +++ b/drivers/gpu/drm/i915/i915_sw_fence_work.c @@ -78,12 +78,11 @@ static const struct dma_fence_ops fence_ops = { void dma_fence_work_init(struct dma_fence_work *f, const struct dma_fence_work_ops *ops) { + f->ops = ops; spin_lock_init(&f->lock); dma_fence_init(&f->dma, &fence_ops, &f->lock, 0, 0); i915_sw_fence_init(&f->chain, fence_notify); INIT_WORK(&f->work, fence_work); - - f->ops = ops; } int dma_fence_work_chain(struct dma_fence_work *f, struct dma_fence *signal) diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 809bff955b5a..75ae6f495161 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -4291,8 +4291,8 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *crtc_state, &crtc_state->wm.skl.optimal.planes[plane_id]; if (plane_id == PLANE_CURSOR) { - if (WARN_ON(wm->wm[level].min_ddb_alloc > - total[PLANE_CURSOR])) { + if (wm->wm[level].min_ddb_alloc > total[PLANE_CURSOR]) { + WARN_ON(wm->wm[level].min_ddb_alloc != U16_MAX); blocks = U32_MAX; break; } diff --git a/drivers/hwtracing/intel_th/core.c b/drivers/hwtracing/intel_th/core.c index 0dfd97bbde9e..ca232ec565e8 100644 --- a/drivers/hwtracing/intel_th/core.c +++ b/drivers/hwtracing/intel_th/core.c @@ -834,9 +834,6 @@ static irqreturn_t intel_th_irq(int irq, void *data) ret |= d->irq(th->thdev[i]); } - if (ret == IRQ_NONE) - pr_warn_ratelimited("nobody cared for irq\n"); - return ret; } @@ -887,6 +884,7 @@ intel_th_alloc(struct device *dev, struct intel_th_drvdata *drvdata, if (th->irq == -1) th->irq = devres[r].start; + th->num_irqs++; break; default: dev_warn(dev, "Unknown resource type %lx\n", @@ -940,6 +938,9 @@ void intel_th_free(struct intel_th *th) th->num_thdevs = 0; + for (i = 0; i < th->num_irqs; i++) + devm_free_irq(th->dev, th->irq + i, th); + pm_runtime_get_sync(th->dev); pm_runtime_forbid(th->dev); diff --git a/drivers/hwtracing/intel_th/intel_th.h b/drivers/hwtracing/intel_th/intel_th.h index 0df480072b6c..6f4f5486fe6d 100644 --- a/drivers/hwtracing/intel_th/intel_th.h +++ b/drivers/hwtracing/intel_th/intel_th.h @@ -261,6 +261,7 @@ enum th_mmio_idx { * @num_thdevs: number of devices in the @thdev array * @num_resources: number of resources in the @resource array * @irq: irq number + * @num_irqs: number of IRQs is use * @id: this Intel TH controller's device ID in the system * @major: device node major for output devices */ @@ -277,6 +278,7 @@ struct intel_th { unsigned int num_thdevs; unsigned int num_resources; int irq; + int num_irqs; int id; int major; diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c index 6d240dfae9d9..8e48c7458aa3 100644 --- a/drivers/hwtracing/intel_th/msu.c +++ b/drivers/hwtracing/intel_th/msu.c @@ -1676,10 +1676,13 @@ static int intel_th_msc_init(struct msc *msc) return 0; } -static void msc_win_switch(struct msc *msc) +static int msc_win_switch(struct msc *msc) { struct msc_window *first; + if (list_empty(&msc->win_list)) + return -EINVAL; + first = list_first_entry(&msc->win_list, struct msc_window, entry); if (msc_is_last_win(msc->cur_win)) @@ -1691,6 +1694,8 @@ static void msc_win_switch(struct msc *msc) msc->base_addr = msc_win_base_dma(msc->cur_win); intel_th_trace_switch(msc->thdev); + + return 0; } /** @@ -2025,16 +2030,15 @@ win_switch_store(struct device *dev, struct device_attribute *attr, if (val != 1) return -EINVAL; + ret = -EINVAL; mutex_lock(&msc->buf_mutex); /* * Window switch can only happen in the "multi" mode. * If a external buffer is engaged, they have the full * control over window switching. */ - if (msc->mode != MSC_MODE_MULTI || msc->mbuf) - ret = -ENOTSUPP; - else - msc_win_switch(msc); + if (msc->mode == MSC_MODE_MULTI && !msc->mbuf) + ret = msc_win_switch(msc); mutex_unlock(&msc->buf_mutex); return ret ? ret : size; diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c index ebf3e30e989a..e9d90b53bbc4 100644 --- a/drivers/hwtracing/intel_th/pci.c +++ b/drivers/hwtracing/intel_th/pci.c @@ -205,6 +205,11 @@ static const struct pci_device_id intel_th_pci_id_table[] = { .driver_data = (kernel_ulong_t)&intel_th_2x, }, { + /* Comet Lake PCH-V */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa3a6), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, + { /* Ice Lake NNPI */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x45c5), .driver_data = (kernel_ulong_t)&intel_th_2x, @@ -229,6 +234,11 @@ static const struct pci_device_id intel_th_pci_id_table[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x4da6), .driver_data = (kernel_ulong_t)&intel_th_2x, }, + { + /* Elkhart Lake */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x4b26), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, { 0 }, }; diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 0cc702a70a96..c363294b3bb9 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -19,6 +19,7 @@ #include <linux/iova.h> #include <linux/irq.h> #include <linux/mm.h> +#include <linux/mutex.h> #include <linux/pci.h> #include <linux/scatterlist.h> #include <linux/vmalloc.h> @@ -44,7 +45,6 @@ struct iommu_dma_cookie { dma_addr_t msi_iova; }; struct list_head msi_page_list; - spinlock_t msi_lock; /* Domain for flush queue callback; NULL if flush queue not in use */ struct iommu_domain *fq_domain; @@ -63,7 +63,6 @@ static struct iommu_dma_cookie *cookie_alloc(enum iommu_dma_cookie_type type) cookie = kzalloc(sizeof(*cookie), GFP_KERNEL); if (cookie) { - spin_lock_init(&cookie->msi_lock); INIT_LIST_HEAD(&cookie->msi_page_list); cookie->type = type; } @@ -399,7 +398,7 @@ static int dma_info_to_prot(enum dma_data_direction dir, bool coherent, } static dma_addr_t iommu_dma_alloc_iova(struct iommu_domain *domain, - size_t size, dma_addr_t dma_limit, struct device *dev) + size_t size, u64 dma_limit, struct device *dev) { struct iommu_dma_cookie *cookie = domain->iova_cookie; struct iova_domain *iovad = &cookie->iovad; @@ -424,7 +423,7 @@ static dma_addr_t iommu_dma_alloc_iova(struct iommu_domain *domain, dma_limit = min_not_zero(dma_limit, dev->bus_dma_limit); if (domain->geometry.force_aperture) - dma_limit = min(dma_limit, domain->geometry.aperture_end); + dma_limit = min(dma_limit, (u64)domain->geometry.aperture_end); /* Try to get PCI devices a SAC address */ if (dma_limit > DMA_BIT_MASK(32) && dev_is_pci(dev)) @@ -477,7 +476,7 @@ static void __iommu_dma_unmap(struct device *dev, dma_addr_t dma_addr, } static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys, - size_t size, int prot, dma_addr_t dma_mask) + size_t size, int prot, u64 dma_mask) { struct iommu_domain *domain = iommu_get_dma_domain(dev); struct iommu_dma_cookie *cookie = domain->iova_cookie; @@ -1176,7 +1175,7 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev, if (msi_page->phys == msi_addr) return msi_page; - msi_page = kzalloc(sizeof(*msi_page), GFP_ATOMIC); + msi_page = kzalloc(sizeof(*msi_page), GFP_KERNEL); if (!msi_page) return NULL; @@ -1206,7 +1205,7 @@ int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr) struct iommu_domain *domain = iommu_get_domain_for_dev(dev); struct iommu_dma_cookie *cookie; struct iommu_dma_msi_page *msi_page; - unsigned long flags; + static DEFINE_MUTEX(msi_prepare_lock); /* see below */ if (!domain || !domain->iova_cookie) { desc->iommu_cookie = NULL; @@ -1216,13 +1215,13 @@ int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr) cookie = domain->iova_cookie; /* - * We disable IRQs to rule out a possible inversion against - * irq_desc_lock if, say, someone tries to retarget the affinity - * of an MSI from within an IPI handler. + * In fact the whole prepare operation should already be serialised by + * irq_domain_mutex further up the callchain, but that's pretty subtle + * on its own, so consider this locking as failsafe documentation... */ - spin_lock_irqsave(&cookie->msi_lock, flags); + mutex_lock(&msi_prepare_lock); msi_page = iommu_dma_get_msi_page(dev, msi_addr, domain); - spin_unlock_irqrestore(&cookie->msi_lock, flags); + mutex_unlock(&msi_prepare_lock); msi_desc_set_iommu_cookie(desc, msi_page); diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 0c8d81f56a30..42966611a192 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -5478,9 +5478,6 @@ static int intel_iommu_map(struct iommu_domain *domain, int prot = 0; int ret; - if (dmar_domain->flags & DOMAIN_FLAG_LOSE_CHILDREN) - return -EINVAL; - if (iommu_prot & IOMMU_READ) prot |= DMA_PTE_READ; if (iommu_prot & IOMMU_WRITE) @@ -5523,8 +5520,6 @@ static size_t intel_iommu_unmap(struct iommu_domain *domain, /* Cope with horrid API which requires us to unmap more than the size argument if it happens to be a large-page mapping. */ BUG_ON(!pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, &level)); - if (dmar_domain->flags & DOMAIN_FLAG_LOSE_CHILDREN) - return 0; if (size < VTD_PAGE_SIZE << level_to_offset_bits(level)) size = VTD_PAGE_SIZE << level_to_offset_bits(level); @@ -5556,9 +5551,6 @@ static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain, int level = 0; u64 phys = 0; - if (dmar_domain->flags & DOMAIN_FLAG_LOSE_CHILDREN) - return 0; - pte = pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, &level); if (pte) phys = dma_pte_addr(pte); @@ -5736,8 +5728,8 @@ static void intel_iommu_get_resv_regions(struct device *device, struct pci_dev *pdev = to_pci_dev(device); if ((pdev->class >> 8) == PCI_CLASS_BRIDGE_ISA) { - reg = iommu_alloc_resv_region(0, 1UL << 24, 0, - IOMMU_RESV_DIRECT); + reg = iommu_alloc_resv_region(0, 1UL << 24, prot, + IOMMU_RESV_DIRECT_RELAXABLE); if (reg) list_add_tail(®->list, head); } diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c index 9b159132405d..dca88f9fdf29 100644 --- a/drivers/iommu/intel-svm.c +++ b/drivers/iommu/intel-svm.c @@ -104,11 +104,7 @@ static void intel_flush_svm_range_dev (struct intel_svm *svm, struct intel_svm_d { struct qi_desc desc; - /* - * Do PASID granu IOTLB invalidation if page selective capability is - * not available. - */ - if (pages == -1 || !cap_pgsel_inv(svm->iommu->cap)) { + if (pages == -1) { desc.qw0 = QI_EIOTLB_PASID(svm->pasid) | QI_EIOTLB_DID(sdev->did) | QI_EIOTLB_GRAN(QI_GRAN_NONG_PASID) | diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index db7bfd4f2d20..fdd40756dbc1 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -312,8 +312,8 @@ int iommu_insert_resv_region(struct iommu_resv_region *new, list_for_each_entry_safe(iter, tmp, regions, list) { phys_addr_t top_end, iter_end = iter->start + iter->length - 1; - /* no merge needed on elements of different types than @nr */ - if (iter->type != nr->type) { + /* no merge needed on elements of different types than @new */ + if (iter->type != new->type) { list_move_tail(&iter->list, &stack); continue; } @@ -2282,13 +2282,13 @@ request_default_domain_for_dev(struct device *dev, unsigned long type) goto out; } - iommu_group_create_direct_mappings(group, dev); - /* Make the domain the default for this group */ if (group->default_domain) iommu_domain_free(group->default_domain); group->default_domain = domain; + iommu_group_create_direct_mappings(group, dev); + dev_info(dev, "Using iommu %s mapping\n", type == IOMMU_DOMAIN_DMA ? "dma" : "direct"); diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c index 41c605b0058f..c7a914b9bbbc 100644 --- a/drivers/iommu/iova.c +++ b/drivers/iommu/iova.c @@ -233,7 +233,7 @@ static DEFINE_MUTEX(iova_cache_mutex); struct iova *alloc_iova_mem(void) { - return kmem_cache_alloc(iova_cache, GFP_ATOMIC); + return kmem_cache_zalloc(iova_cache, GFP_ATOMIC); } EXPORT_SYMBOL(alloc_iova_mem); diff --git a/drivers/misc/habanalabs/command_submission.c b/drivers/misc/habanalabs/command_submission.c index 8850f475a413..0bf08678431b 100644 --- a/drivers/misc/habanalabs/command_submission.c +++ b/drivers/misc/habanalabs/command_submission.c @@ -824,8 +824,9 @@ int hl_cs_wait_ioctl(struct hl_fpriv *hpriv, void *data) memset(args, 0, sizeof(*args)); if (rc < 0) { - dev_err(hdev->dev, "Error %ld on waiting for CS handle %llu\n", - rc, seq); + dev_err_ratelimited(hdev->dev, + "Error %ld on waiting for CS handle %llu\n", + rc, seq); if (rc == -ERESTARTSYS) { args->out.status = HL_WAIT_CS_STATUS_INTERRUPTED; rc = -EINTR; diff --git a/drivers/misc/habanalabs/context.c b/drivers/misc/habanalabs/context.c index 17db7b3dfb4c..2df6fb87e7ff 100644 --- a/drivers/misc/habanalabs/context.c +++ b/drivers/misc/habanalabs/context.c @@ -176,7 +176,7 @@ struct dma_fence *hl_ctx_get_fence(struct hl_ctx *ctx, u64 seq) spin_lock(&ctx->cs_lock); if (seq >= ctx->cs_sequence) { - dev_notice(hdev->dev, + dev_notice_ratelimited(hdev->dev, "Can't wait on seq %llu because current CS is at seq %llu\n", seq, ctx->cs_sequence); spin_unlock(&ctx->cs_lock); diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index c8d16aa4382c..7344e8a222ae 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -2192,7 +2192,7 @@ static int goya_push_linux_to_device(struct hl_device *hdev) static int goya_pldm_init_cpu(struct hl_device *hdev) { - u32 val, unit_rst_val; + u32 unit_rst_val; int rc; /* Must initialize SRAM scrambler before pushing u-boot to SRAM */ @@ -2200,14 +2200,14 @@ static int goya_pldm_init_cpu(struct hl_device *hdev) /* Put ARM cores into reset */ WREG32(mmCPU_CA53_CFG_ARM_RST_CONTROL, CPU_RESET_ASSERT); - val = RREG32(mmCPU_CA53_CFG_ARM_RST_CONTROL); + RREG32(mmCPU_CA53_CFG_ARM_RST_CONTROL); /* Reset the CA53 MACRO */ unit_rst_val = RREG32(mmPSOC_GLOBAL_CONF_UNIT_RST_N); WREG32(mmPSOC_GLOBAL_CONF_UNIT_RST_N, CA53_RESET); - val = RREG32(mmPSOC_GLOBAL_CONF_UNIT_RST_N); + RREG32(mmPSOC_GLOBAL_CONF_UNIT_RST_N); WREG32(mmPSOC_GLOBAL_CONF_UNIT_RST_N, unit_rst_val); - val = RREG32(mmPSOC_GLOBAL_CONF_UNIT_RST_N); + RREG32(mmPSOC_GLOBAL_CONF_UNIT_RST_N); rc = goya_push_uboot_to_device(hdev); if (rc) @@ -2228,7 +2228,7 @@ static int goya_pldm_init_cpu(struct hl_device *hdev) /* Release ARM core 0 from reset */ WREG32(mmCPU_CA53_CFG_ARM_RST_CONTROL, CPU_RESET_CORE0_DEASSERT); - val = RREG32(mmCPU_CA53_CFG_ARM_RST_CONTROL); + RREG32(mmCPU_CA53_CFG_ARM_RST_CONTROL); return 0; } @@ -2502,13 +2502,12 @@ err: static int goya_hw_init(struct hl_device *hdev) { struct asic_fixed_properties *prop = &hdev->asic_prop; - u32 val; int rc; dev_info(hdev->dev, "Starting initialization of H/W\n"); /* Perform read from the device to make sure device is up */ - val = RREG32(mmPCIE_DBI_DEVICE_ID_VENDOR_ID_REG); + RREG32(mmPCIE_DBI_DEVICE_ID_VENDOR_ID_REG); /* * Let's mark in the H/W that we have reached this point. We check @@ -2560,7 +2559,7 @@ static int goya_hw_init(struct hl_device *hdev) goto disable_queues; /* Perform read from the device to flush all MSI-X configuration */ - val = RREG32(mmPCIE_DBI_DEVICE_ID_VENDOR_ID_REG); + RREG32(mmPCIE_DBI_DEVICE_ID_VENDOR_ID_REG); return 0; diff --git a/drivers/misc/ocxl/context.c b/drivers/misc/ocxl/context.c index 994563a078eb..de8a66b9d76b 100644 --- a/drivers/misc/ocxl/context.c +++ b/drivers/misc/ocxl/context.c @@ -10,18 +10,17 @@ int ocxl_context_alloc(struct ocxl_context **context, struct ocxl_afu *afu, int pasid; struct ocxl_context *ctx; - *context = kzalloc(sizeof(struct ocxl_context), GFP_KERNEL); - if (!*context) + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) return -ENOMEM; - ctx = *context; - ctx->afu = afu; mutex_lock(&afu->contexts_lock); pasid = idr_alloc(&afu->contexts_idr, ctx, afu->pasid_base, afu->pasid_base + afu->pasid_max, GFP_KERNEL); if (pasid < 0) { mutex_unlock(&afu->contexts_lock); + kfree(ctx); return pasid; } afu->pasid_count++; @@ -43,6 +42,7 @@ int ocxl_context_alloc(struct ocxl_context **context, struct ocxl_afu *afu, * duration of the life of the context */ ocxl_afu_get(afu); + *context = ctx; return 0; } EXPORT_SYMBOL_GPL(ocxl_context_alloc); diff --git a/drivers/misc/ocxl/file.c b/drivers/misc/ocxl/file.c index 2870c25da166..4d1b44de1492 100644 --- a/drivers/misc/ocxl/file.c +++ b/drivers/misc/ocxl/file.c @@ -18,18 +18,15 @@ static struct class *ocxl_class; static struct mutex minors_idr_lock; static struct idr minors_idr; -static struct ocxl_file_info *find_file_info(dev_t devno) +static struct ocxl_file_info *find_and_get_file_info(dev_t devno) { struct ocxl_file_info *info; - /* - * We don't declare an RCU critical section here, as our AFU - * is protected by a reference counter on the device. By the time the - * info reference is removed from the idr, the ref count of - * the device is already at 0, so no user API will access that AFU and - * this function can't return it. - */ + mutex_lock(&minors_idr_lock); info = idr_find(&minors_idr, MINOR(devno)); + if (info) + get_device(&info->dev); + mutex_unlock(&minors_idr_lock); return info; } @@ -58,14 +55,16 @@ static int afu_open(struct inode *inode, struct file *file) pr_debug("%s for device %x\n", __func__, inode->i_rdev); - info = find_file_info(inode->i_rdev); + info = find_and_get_file_info(inode->i_rdev); if (!info) return -ENODEV; rc = ocxl_context_alloc(&ctx, info->afu, inode->i_mapping); - if (rc) + if (rc) { + put_device(&info->dev); return rc; - + } + put_device(&info->dev); file->private_data = ctx; return 0; } @@ -487,7 +486,6 @@ static void info_release(struct device *dev) { struct ocxl_file_info *info = container_of(dev, struct ocxl_file_info, dev); - free_minor(info); ocxl_afu_put(info->afu); kfree(info); } @@ -577,6 +575,7 @@ void ocxl_file_unregister_afu(struct ocxl_afu *afu) ocxl_file_make_invisible(info); ocxl_sysfs_unregister_afu(info); + free_minor(info); device_unregister(&info->dev); } diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c index 189e42674d85..010fe29a4888 100644 --- a/drivers/mmc/host/mtk-sd.c +++ b/drivers/mmc/host/mtk-sd.c @@ -228,6 +228,7 @@ #define MSDC_PATCH_BIT_SPCPUSH (0x1 << 29) /* RW */ #define MSDC_PATCH_BIT_DECRCTMO (0x1 << 30) /* RW */ +#define MSDC_PATCH_BIT1_CMDTA (0x7 << 3) /* RW */ #define MSDC_PATCH_BIT1_STOP_DLY (0xf << 8) /* RW */ #define MSDC_PATCH_BIT2_CFGRESP (0x1 << 15) /* RW */ @@ -1881,6 +1882,7 @@ static int hs400_tune_response(struct mmc_host *mmc, u32 opcode) /* select EMMC50 PAD CMD tune */ sdr_set_bits(host->base + PAD_CMD_TUNE, BIT(0)); + sdr_set_field(host->base + MSDC_PATCH_BIT1, MSDC_PATCH_BIT1_CMDTA, 2); if (mmc->ios.timing == MMC_TIMING_MMC_HS200 || mmc->ios.timing == MMC_TIMING_UHS_SDR104) diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c index b75c82d8d6c1..3d0bb5e2e09b 100644 --- a/drivers/mmc/host/sdhci-msm.c +++ b/drivers/mmc/host/sdhci-msm.c @@ -99,7 +99,7 @@ #define CORE_PWRSAVE_DLL BIT(3) -#define DDR_CONFIG_POR_VAL 0x80040853 +#define DDR_CONFIG_POR_VAL 0x80040873 #define INVALID_TUNING_PHASE -1 @@ -148,8 +148,9 @@ struct sdhci_msm_offset { u32 core_ddr_200_cfg; u32 core_vendor_spec3; u32 core_dll_config_2; + u32 core_dll_config_3; + u32 core_ddr_config_old; /* Applicable to sdcc minor ver < 0x49 */ u32 core_ddr_config; - u32 core_ddr_config_2; }; static const struct sdhci_msm_offset sdhci_msm_v5_offset = { @@ -177,8 +178,8 @@ static const struct sdhci_msm_offset sdhci_msm_v5_offset = { .core_ddr_200_cfg = 0x224, .core_vendor_spec3 = 0x250, .core_dll_config_2 = 0x254, - .core_ddr_config = 0x258, - .core_ddr_config_2 = 0x25c, + .core_dll_config_3 = 0x258, + .core_ddr_config = 0x25c, }; static const struct sdhci_msm_offset sdhci_msm_mci_offset = { @@ -207,8 +208,8 @@ static const struct sdhci_msm_offset sdhci_msm_mci_offset = { .core_ddr_200_cfg = 0x184, .core_vendor_spec3 = 0x1b0, .core_dll_config_2 = 0x1b4, - .core_ddr_config = 0x1b8, - .core_ddr_config_2 = 0x1bc, + .core_ddr_config_old = 0x1b8, + .core_ddr_config = 0x1bc, }; struct sdhci_msm_variant_ops { @@ -253,6 +254,7 @@ struct sdhci_msm_host { const struct sdhci_msm_offset *offset; bool use_cdr; u32 transfer_mode; + bool updated_ddr_cfg; }; static const struct sdhci_msm_offset *sdhci_priv_msm_offset(struct sdhci_host *host) @@ -924,8 +926,10 @@ out: static int sdhci_msm_cm_dll_sdc4_calibration(struct sdhci_host *host) { struct mmc_host *mmc = host->mmc; - u32 dll_status, config; + u32 dll_status, config, ddr_cfg_offset; int ret; + struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); + struct sdhci_msm_host *msm_host = sdhci_pltfm_priv(pltfm_host); const struct sdhci_msm_offset *msm_offset = sdhci_priv_msm_offset(host); @@ -938,8 +942,11 @@ static int sdhci_msm_cm_dll_sdc4_calibration(struct sdhci_host *host) * bootloaders. In the future, if this changes, then the desired * values will need to be programmed appropriately. */ - writel_relaxed(DDR_CONFIG_POR_VAL, host->ioaddr + - msm_offset->core_ddr_config); + if (msm_host->updated_ddr_cfg) + ddr_cfg_offset = msm_offset->core_ddr_config; + else + ddr_cfg_offset = msm_offset->core_ddr_config_old; + writel_relaxed(DDR_CONFIG_POR_VAL, host->ioaddr + ddr_cfg_offset); if (mmc->ios.enhanced_strobe) { config = readl_relaxed(host->ioaddr + @@ -1899,6 +1906,9 @@ static int sdhci_msm_probe(struct platform_device *pdev) msm_offset->core_vendor_spec_capabilities0); } + if (core_major == 1 && core_minor >= 0x49) + msm_host->updated_ddr_cfg = true; + /* * Power on reset state may trigger power irq if previous status of * PWRCTL was either BUS_ON or IO_HIGH_V. So before enabling pwr irq diff --git a/drivers/mmc/host/sdhci-of-esdhc.c b/drivers/mmc/host/sdhci-of-esdhc.c index 5cca3fa4610b..500f70a6ee42 100644 --- a/drivers/mmc/host/sdhci-of-esdhc.c +++ b/drivers/mmc/host/sdhci-of-esdhc.c @@ -80,6 +80,7 @@ struct sdhci_esdhc { bool quirk_tuning_erratum_type1; bool quirk_tuning_erratum_type2; bool quirk_ignore_data_inhibit; + bool quirk_delay_before_data_reset; bool in_sw_tuning; unsigned int peripheral_clock; const struct esdhc_clk_fixup *clk_fixup; @@ -759,14 +760,16 @@ static void esdhc_reset(struct sdhci_host *host, u8 mask) struct sdhci_esdhc *esdhc = sdhci_pltfm_priv(pltfm_host); u32 val; + if (esdhc->quirk_delay_before_data_reset && + (mask & SDHCI_RESET_DATA) && + (host->flags & SDHCI_REQ_USE_DMA)) + mdelay(5); + sdhci_reset(host, mask); sdhci_writel(host, host->ier, SDHCI_INT_ENABLE); sdhci_writel(host, host->ier, SDHCI_SIGNAL_ENABLE); - if (of_find_compatible_node(NULL, NULL, "fsl,p2020-esdhc")) - mdelay(5); - if (mask & SDHCI_RESET_ALL) { val = sdhci_readl(host, ESDHC_TBCTL); val &= ~ESDHC_TB_EN; @@ -1221,6 +1224,10 @@ static void esdhc_init(struct platform_device *pdev, struct sdhci_host *host) if (match) esdhc->clk_fixup = match->data; np = pdev->dev.of_node; + + if (of_device_is_compatible(np, "fsl,p2020-esdhc")) + esdhc->quirk_delay_before_data_reset = true; + clk = of_clk_get(np, 0); if (!IS_ERR(clk)) { /* @@ -1303,8 +1310,8 @@ static int sdhci_esdhc_probe(struct platform_device *pdev) host->quirks &= ~SDHCI_QUIRK_NO_BUSY_IRQ; if (of_find_compatible_node(NULL, NULL, "fsl,p2020-esdhc")) { - host->quirks2 |= SDHCI_QUIRK_RESET_AFTER_REQUEST; - host->quirks2 |= SDHCI_QUIRK_BROKEN_TIMEOUT_VAL; + host->quirks |= SDHCI_QUIRK_RESET_AFTER_REQUEST; + host->quirks |= SDHCI_QUIRK_BROKEN_TIMEOUT_VAL; } if (of_device_is_compatible(np, "fsl,p5040-esdhc") || diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c index acefb76b4e15..5091e2c1c0e5 100644 --- a/drivers/mmc/host/sdhci-pci-core.c +++ b/drivers/mmc/host/sdhci-pci-core.c @@ -27,6 +27,7 @@ #include <linux/mmc/slot-gpio.h> #include <linux/mmc/sdhci-pci-data.h> #include <linux/acpi.h> +#include <linux/dmi.h> #ifdef CONFIG_X86 #include <asm/iosf_mbi.h> @@ -783,11 +784,18 @@ static int byt_emmc_probe_slot(struct sdhci_pci_slot *slot) return 0; } +static bool glk_broken_cqhci(struct sdhci_pci_slot *slot) +{ + return slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_GLK_EMMC && + dmi_match(DMI_BIOS_VENDOR, "LENOVO"); +} + static int glk_emmc_probe_slot(struct sdhci_pci_slot *slot) { int ret = byt_emmc_probe_slot(slot); - slot->host->mmc->caps2 |= MMC_CAP2_CQE; + if (!glk_broken_cqhci(slot)) + slot->host->mmc->caps2 |= MMC_CAP2_CQE; if (slot->chip->pdev->device != PCI_DEVICE_ID_INTEL_GLK_EMMC) { slot->host->mmc->caps2 |= MMC_CAP2_HS400_ES, diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index 3140fe2e5dba..1b1c26da3fe0 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -1882,9 +1882,7 @@ void sdhci_set_uhs_signaling(struct sdhci_host *host, unsigned timing) ctrl_2 |= SDHCI_CTRL_UHS_SDR104; else if (timing == MMC_TIMING_UHS_SDR12) ctrl_2 |= SDHCI_CTRL_UHS_SDR12; - else if (timing == MMC_TIMING_SD_HS || - timing == MMC_TIMING_MMC_HS || - timing == MMC_TIMING_UHS_SDR25) + else if (timing == MMC_TIMING_UHS_SDR25) ctrl_2 |= SDHCI_CTRL_UHS_SDR25; else if (timing == MMC_TIMING_UHS_SDR50) ctrl_2 |= SDHCI_CTRL_UHS_SDR50; @@ -2419,8 +2417,8 @@ static int __sdhci_execute_tuning(struct sdhci_host *host, u32 opcode) sdhci_send_tuning(host, opcode); if (!host->tuning_done) { - pr_info("%s: Tuning timeout, falling back to fixed sampling clock\n", - mmc_hostname(host->mmc)); + pr_debug("%s: Tuning timeout, falling back to fixed sampling clock\n", + mmc_hostname(host->mmc)); sdhci_abort_tuning(host, opcode); return -ETIMEDOUT; } @@ -3769,6 +3767,9 @@ int sdhci_setup_host(struct sdhci_host *host) mmc_hostname(mmc), host->version); } + if (host->quirks & SDHCI_QUIRK_BROKEN_CQE) + mmc->caps2 &= ~MMC_CAP2_CQE; + if (host->quirks & SDHCI_QUIRK_FORCE_DMA) host->flags |= SDHCI_USE_SDMA; else if (!(host->caps & SDHCI_CAN_DO_SDMA)) diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h index 0ed3e0eaef5f..fe83ece6965b 100644 --- a/drivers/mmc/host/sdhci.h +++ b/drivers/mmc/host/sdhci.h @@ -409,6 +409,8 @@ struct sdhci_host { #define SDHCI_QUIRK_BROKEN_CARD_DETECTION (1<<15) /* Controller reports inverted write-protect state */ #define SDHCI_QUIRK_INVERTED_WRITE_PROTECT (1<<16) +/* Controller has unusable command queue engine */ +#define SDHCI_QUIRK_BROKEN_CQE (1<<17) /* Controller does not like fast PIO transfers */ #define SDHCI_QUIRK_PIO_NEEDS_DELAY (1<<18) /* Controller does not have a LED */ diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index fcb7c2f7f001..48d5ec770b94 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -2272,9 +2272,6 @@ static void bond_miimon_commit(struct bonding *bond) } else if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { /* make it immediately active */ bond_set_active_slave(slave); - } else if (slave != primary) { - /* prevent it from being the active one */ - bond_set_backup_slave(slave); } slave_info(bond->dev, slave->dev, "link status definitely up, %u Mbps %s duplex\n", @@ -3702,32 +3699,35 @@ static int bond_neigh_init(struct neighbour *n) const struct net_device_ops *slave_ops; struct neigh_parms parms; struct slave *slave; - int ret; + int ret = 0; - slave = bond_first_slave(bond); + rcu_read_lock(); + slave = bond_first_slave_rcu(bond); if (!slave) - return 0; + goto out; slave_ops = slave->dev->netdev_ops; if (!slave_ops->ndo_neigh_setup) - return 0; - - parms.neigh_setup = NULL; - parms.neigh_cleanup = NULL; - ret = slave_ops->ndo_neigh_setup(slave->dev, &parms); - if (ret) - return ret; + goto out; - /* Assign slave's neigh_cleanup to neighbour in case cleanup is called - * after the last slave has been detached. Assumes that all slaves - * utilize the same neigh_cleanup (true at this writing as only user - * is ipoib). + /* TODO: find another way [1] to implement this. + * Passing a zeroed structure is fragile, + * but at least we do not pass garbage. + * + * [1] One way would be that ndo_neigh_setup() never touch + * struct neigh_parms, but propagate the new neigh_setup() + * back to ___neigh_create() / neigh_parms_alloc() */ - n->parms->neigh_cleanup = parms.neigh_cleanup; + memset(&parms, 0, sizeof(parms)); + ret = slave_ops->ndo_neigh_setup(slave->dev, &parms); - if (!parms.neigh_setup) - return 0; + if (ret) + goto out; - return parms.neigh_setup(n); + if (parms.neigh_setup) + ret = parms.neigh_setup(n); +out: + rcu_read_unlock(); + return ret; } /* The bonding ndo_neigh_setup is called at init time beofre any diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c index a929cdda9ab2..94d10ec954a0 100644 --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -389,6 +389,34 @@ static struct flexcan_mb __iomem *flexcan_get_mb(const struct flexcan_priv *priv (&priv->regs->mb[bank][priv->mb_size * mb_index]); } +static int flexcan_low_power_enter_ack(struct flexcan_priv *priv) +{ + struct flexcan_regs __iomem *regs = priv->regs; + unsigned int timeout = FLEXCAN_TIMEOUT_US / 10; + + while (timeout-- && !(priv->read(®s->mcr) & FLEXCAN_MCR_LPM_ACK)) + udelay(10); + + if (!(priv->read(®s->mcr) & FLEXCAN_MCR_LPM_ACK)) + return -ETIMEDOUT; + + return 0; +} + +static int flexcan_low_power_exit_ack(struct flexcan_priv *priv) +{ + struct flexcan_regs __iomem *regs = priv->regs; + unsigned int timeout = FLEXCAN_TIMEOUT_US / 10; + + while (timeout-- && (priv->read(®s->mcr) & FLEXCAN_MCR_LPM_ACK)) + udelay(10); + + if (priv->read(®s->mcr) & FLEXCAN_MCR_LPM_ACK) + return -ETIMEDOUT; + + return 0; +} + static void flexcan_enable_wakeup_irq(struct flexcan_priv *priv, bool enable) { struct flexcan_regs __iomem *regs = priv->regs; @@ -407,7 +435,6 @@ static void flexcan_enable_wakeup_irq(struct flexcan_priv *priv, bool enable) static inline int flexcan_enter_stop_mode(struct flexcan_priv *priv) { struct flexcan_regs __iomem *regs = priv->regs; - unsigned int ackval; u32 reg_mcr; reg_mcr = priv->read(®s->mcr); @@ -418,36 +445,24 @@ static inline int flexcan_enter_stop_mode(struct flexcan_priv *priv) regmap_update_bits(priv->stm.gpr, priv->stm.req_gpr, 1 << priv->stm.req_bit, 1 << priv->stm.req_bit); - /* get stop acknowledgment */ - if (regmap_read_poll_timeout(priv->stm.gpr, priv->stm.ack_gpr, - ackval, ackval & (1 << priv->stm.ack_bit), - 0, FLEXCAN_TIMEOUT_US)) - return -ETIMEDOUT; - - return 0; + return flexcan_low_power_enter_ack(priv); } static inline int flexcan_exit_stop_mode(struct flexcan_priv *priv) { struct flexcan_regs __iomem *regs = priv->regs; - unsigned int ackval; u32 reg_mcr; /* remove stop request */ regmap_update_bits(priv->stm.gpr, priv->stm.req_gpr, 1 << priv->stm.req_bit, 0); - /* get stop acknowledgment */ - if (regmap_read_poll_timeout(priv->stm.gpr, priv->stm.ack_gpr, - ackval, !(ackval & (1 << priv->stm.ack_bit)), - 0, FLEXCAN_TIMEOUT_US)) - return -ETIMEDOUT; reg_mcr = priv->read(®s->mcr); reg_mcr &= ~FLEXCAN_MCR_SLF_WAK; priv->write(reg_mcr, ®s->mcr); - return 0; + return flexcan_low_power_exit_ack(priv); } static inline void flexcan_error_irq_enable(const struct flexcan_priv *priv) @@ -506,39 +521,25 @@ static inline int flexcan_transceiver_disable(const struct flexcan_priv *priv) static int flexcan_chip_enable(struct flexcan_priv *priv) { struct flexcan_regs __iomem *regs = priv->regs; - unsigned int timeout = FLEXCAN_TIMEOUT_US / 10; u32 reg; reg = priv->read(®s->mcr); reg &= ~FLEXCAN_MCR_MDIS; priv->write(reg, ®s->mcr); - while (timeout-- && (priv->read(®s->mcr) & FLEXCAN_MCR_LPM_ACK)) - udelay(10); - - if (priv->read(®s->mcr) & FLEXCAN_MCR_LPM_ACK) - return -ETIMEDOUT; - - return 0; + return flexcan_low_power_exit_ack(priv); } static int flexcan_chip_disable(struct flexcan_priv *priv) { struct flexcan_regs __iomem *regs = priv->regs; - unsigned int timeout = FLEXCAN_TIMEOUT_US / 10; u32 reg; reg = priv->read(®s->mcr); reg |= FLEXCAN_MCR_MDIS; priv->write(reg, ®s->mcr); - while (timeout-- && !(priv->read(®s->mcr) & FLEXCAN_MCR_LPM_ACK)) - udelay(10); - - if (!(priv->read(®s->mcr) & FLEXCAN_MCR_LPM_ACK)) - return -ETIMEDOUT; - - return 0; + return flexcan_low_power_enter_ack(priv); } static int flexcan_chip_freeze(struct flexcan_priv *priv) @@ -1722,6 +1723,9 @@ static int __maybe_unused flexcan_resume(struct device *device) netif_start_queue(dev); if (device_may_wakeup(device)) { disable_irq_wake(dev->irq); + err = flexcan_exit_stop_mode(priv); + if (err) + return err; } else { err = pm_runtime_force_resume(device); if (err) @@ -1767,14 +1771,9 @@ static int __maybe_unused flexcan_noirq_resume(struct device *device) { struct net_device *dev = dev_get_drvdata(device); struct flexcan_priv *priv = netdev_priv(dev); - int err; - if (netif_running(dev) && device_may_wakeup(device)) { + if (netif_running(dev) && device_may_wakeup(device)) flexcan_enable_wakeup_irq(priv, false); - err = flexcan_exit_stop_mode(priv); - if (err) - return err; - } return 0; } diff --git a/drivers/net/can/m_can/tcan4x5x.c b/drivers/net/can/m_can/tcan4x5x.c index 3db619209fe1..4e1789ea2bc3 100644 --- a/drivers/net/can/m_can/tcan4x5x.c +++ b/drivers/net/can/m_can/tcan4x5x.c @@ -101,6 +101,8 @@ #define TCAN4X5X_MODE_STANDBY BIT(6) #define TCAN4X5X_MODE_NORMAL BIT(7) +#define TCAN4X5X_DISABLE_WAKE_MSK (BIT(31) | BIT(30)) + #define TCAN4X5X_SW_RESET BIT(2) #define TCAN4X5X_MCAN_CONFIGURED BIT(5) @@ -338,6 +340,14 @@ static int tcan4x5x_init(struct m_can_classdev *cdev) return ret; } +static int tcan4x5x_disable_wake(struct m_can_classdev *cdev) +{ + struct tcan4x5x_priv *tcan4x5x = cdev->device_data; + + return regmap_update_bits(tcan4x5x->regmap, TCAN4X5X_CONFIG, + TCAN4X5X_DISABLE_WAKE_MSK, 0x00); +} + static int tcan4x5x_parse_config(struct m_can_classdev *cdev) { struct tcan4x5x_priv *tcan4x5x = cdev->device_data; @@ -345,8 +355,10 @@ static int tcan4x5x_parse_config(struct m_can_classdev *cdev) tcan4x5x->device_wake_gpio = devm_gpiod_get(cdev->dev, "device-wake", GPIOD_OUT_HIGH); if (IS_ERR(tcan4x5x->device_wake_gpio)) { - dev_err(cdev->dev, "device-wake gpio not defined\n"); - return -EINVAL; + if (PTR_ERR(tcan4x5x->power) == -EPROBE_DEFER) + return -EPROBE_DEFER; + + tcan4x5x_disable_wake(cdev); } tcan4x5x->reset_gpio = devm_gpiod_get_optional(cdev->dev, "reset", @@ -354,6 +366,8 @@ static int tcan4x5x_parse_config(struct m_can_classdev *cdev) if (IS_ERR(tcan4x5x->reset_gpio)) tcan4x5x->reset_gpio = NULL; + usleep_range(700, 1000); + tcan4x5x->device_state_gpio = devm_gpiod_get_optional(cdev->dev, "device-state", GPIOD_IN); @@ -428,10 +442,6 @@ static int tcan4x5x_can_probe(struct spi_device *spi) spi_set_drvdata(spi, priv); - ret = tcan4x5x_parse_config(mcan_class); - if (ret) - goto out_clk; - /* Configure the SPI bus */ spi->bits_per_word = 32; ret = spi_setup(spi); @@ -441,6 +451,10 @@ static int tcan4x5x_can_probe(struct spi_device *spi) priv->regmap = devm_regmap_init(&spi->dev, &tcan4x5x_bus, &spi->dev, &tcan4x5x_regmap); + ret = tcan4x5x_parse_config(mcan_class); + if (ret) + goto out_clk; + tcan4x5x_power_enable(priv->power, 1); ret = m_can_class_register(mcan_class); diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c index 07d2f3aa2c02..ae4c37e1bb75 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c @@ -608,7 +608,7 @@ static int kvaser_usb_leaf_simple_cmd_async(struct kvaser_usb_net_priv *priv, struct kvaser_cmd *cmd; int err; - cmd = kmalloc(sizeof(*cmd), GFP_ATOMIC); + cmd = kzalloc(sizeof(*cmd), GFP_ATOMIC); if (!cmd) return -ENOMEM; @@ -1140,7 +1140,7 @@ static int kvaser_usb_leaf_set_opt_mode(const struct kvaser_usb_net_priv *priv) struct kvaser_cmd *cmd; int rc; - cmd = kmalloc(sizeof(*cmd), GFP_KERNEL); + cmd = kzalloc(sizeof(*cmd), GFP_KERNEL); if (!cmd) return -ENOMEM; @@ -1206,7 +1206,7 @@ static int kvaser_usb_leaf_flush_queue(struct kvaser_usb_net_priv *priv) struct kvaser_cmd *cmd; int rc; - cmd = kmalloc(sizeof(*cmd), GFP_KERNEL); + cmd = kzalloc(sizeof(*cmd), GFP_KERNEL); if (!cmd) return -ENOMEM; diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c index 464af939cd8a..c1dbab8c896d 100644 --- a/drivers/net/can/xilinx_can.c +++ b/drivers/net/can/xilinx_can.c @@ -60,6 +60,8 @@ enum xcan_reg { XCAN_TXMSG_BASE_OFFSET = 0x0100, /* TX Message Space */ XCAN_RXMSG_BASE_OFFSET = 0x1100, /* RX Message Space */ XCAN_RXMSG_2_BASE_OFFSET = 0x2100, /* RX Message Space */ + XCAN_AFR_2_MASK_OFFSET = 0x0A00, /* Acceptance Filter MASK */ + XCAN_AFR_2_ID_OFFSET = 0x0A04, /* Acceptance Filter ID */ }; #define XCAN_FRAME_ID_OFFSET(frame_base) ((frame_base) + 0x00) @@ -1809,6 +1811,11 @@ static int xcan_probe(struct platform_device *pdev) pm_runtime_put(&pdev->dev); + if (priv->devtype.flags & XCAN_FLAG_CANFD_2) { + priv->write_reg(priv, XCAN_AFR_2_ID_OFFSET, 0x00000000); + priv->write_reg(priv, XCAN_AFR_2_MASK_OFFSET, 0x00000000); + } + netdev_dbg(ndev, "reg_base=0x%p irq=%d clock=%d, tx buffers: actual %d, using %d\n", priv->reg_base, ndev->irq, priv->can.clock.freq, hw_tx_max, priv->tx_max); diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 36828f210030..edacacfc9365 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -347,7 +347,7 @@ static void b53_set_forwarding(struct b53_device *dev, int enable) * frames should be flooded or not. */ b53_read8(dev, B53_CTRL_PAGE, B53_IP_MULTICAST_CTRL, &mgmt); - mgmt |= B53_UC_FWD_EN | B53_MC_FWD_EN; + mgmt |= B53_UC_FWD_EN | B53_MC_FWD_EN | B53_IPMC_FWD_EN; b53_write8(dev, B53_CTRL_PAGE, B53_IP_MULTICAST_CTRL, mgmt); } @@ -526,6 +526,8 @@ int b53_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy) cpu_port = dsa_to_port(ds, port)->cpu_dp->index; + b53_br_egress_floods(ds, port, true, true); + if (dev->ops->irq_enable) ret = dev->ops->irq_enable(dev, port); if (ret) @@ -641,6 +643,8 @@ static void b53_enable_cpu_port(struct b53_device *dev, int port) b53_write8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(port), port_ctrl); b53_brcm_hdr_setup(dev->ds, port); + + b53_br_egress_floods(dev->ds, port, true, true); } static void b53_enable_mib(struct b53_device *dev) @@ -1821,19 +1825,26 @@ int b53_br_egress_floods(struct dsa_switch *ds, int port, struct b53_device *dev = ds->priv; u16 uc, mc; - b53_read16(dev, B53_CTRL_PAGE, B53_UC_FWD_EN, &uc); + b53_read16(dev, B53_CTRL_PAGE, B53_UC_FLOOD_MASK, &uc); if (unicast) uc |= BIT(port); else uc &= ~BIT(port); - b53_write16(dev, B53_CTRL_PAGE, B53_UC_FWD_EN, uc); + b53_write16(dev, B53_CTRL_PAGE, B53_UC_FLOOD_MASK, uc); + + b53_read16(dev, B53_CTRL_PAGE, B53_MC_FLOOD_MASK, &mc); + if (multicast) + mc |= BIT(port); + else + mc &= ~BIT(port); + b53_write16(dev, B53_CTRL_PAGE, B53_MC_FLOOD_MASK, mc); - b53_read16(dev, B53_CTRL_PAGE, B53_MC_FWD_EN, &mc); + b53_read16(dev, B53_CTRL_PAGE, B53_IPMC_FLOOD_MASK, &mc); if (multicast) mc |= BIT(port); else mc &= ~BIT(port); - b53_write16(dev, B53_CTRL_PAGE, B53_MC_FWD_EN, mc); + b53_write16(dev, B53_CTRL_PAGE, B53_IPMC_FLOOD_MASK, mc); return 0; diff --git a/drivers/net/dsa/ocelot/Kconfig b/drivers/net/dsa/ocelot/Kconfig index 0031ca814346..6f9804093150 100644 --- a/drivers/net/dsa/ocelot/Kconfig +++ b/drivers/net/dsa/ocelot/Kconfig @@ -2,6 +2,7 @@ config NET_DSA_MSCC_FELIX tristate "Ocelot / Felix Ethernet switch support" depends on NET_DSA && PCI + depends on NET_VENDOR_MICROSEMI select MSCC_OCELOT_SWITCH select NET_DSA_TAG_OCELOT help diff --git a/drivers/net/ethernet/amazon/ena/ena_com.h b/drivers/net/ethernet/amazon/ena/ena_com.h index 7c941eba0bc9..0ce37d54ed10 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.h +++ b/drivers/net/ethernet/amazon/ena/ena_com.h @@ -72,7 +72,7 @@ /*****************************************************************************/ /* ENA adaptive interrupt moderation settings */ -#define ENA_INTR_INITIAL_TX_INTERVAL_USECS 196 +#define ENA_INTR_INITIAL_TX_INTERVAL_USECS 64 #define ENA_INTR_INITIAL_RX_INTERVAL_USECS 0 #define ENA_DEFAULT_INTR_DELAY_RESOLUTION 1 diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c index a3250dcf7d53..fc96c66b44cb 100644 --- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c +++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c @@ -315,10 +315,9 @@ static int ena_get_coalesce(struct net_device *net_dev, ena_com_get_nonadaptive_moderation_interval_tx(ena_dev) * ena_dev->intr_delay_resolution; - if (!ena_com_get_adaptive_moderation_enabled(ena_dev)) - coalesce->rx_coalesce_usecs = - ena_com_get_nonadaptive_moderation_interval_rx(ena_dev) - * ena_dev->intr_delay_resolution; + coalesce->rx_coalesce_usecs = + ena_com_get_nonadaptive_moderation_interval_rx(ena_dev) + * ena_dev->intr_delay_resolution; coalesce->use_adaptive_rx_coalesce = ena_com_get_adaptive_moderation_enabled(ena_dev); @@ -367,12 +366,6 @@ static int ena_set_coalesce(struct net_device *net_dev, ena_update_tx_rings_intr_moderation(adapter); - if (coalesce->use_adaptive_rx_coalesce) { - if (!ena_com_get_adaptive_moderation_enabled(ena_dev)) - ena_com_enable_adaptive_moderation(ena_dev); - return 0; - } - rc = ena_com_update_nonadaptive_moderation_interval_rx(ena_dev, coalesce->rx_coalesce_usecs); if (rc) @@ -380,10 +373,13 @@ static int ena_set_coalesce(struct net_device *net_dev, ena_update_rx_rings_intr_moderation(adapter); - if (!coalesce->use_adaptive_rx_coalesce) { - if (ena_com_get_adaptive_moderation_enabled(ena_dev)) - ena_com_disable_adaptive_moderation(ena_dev); - } + if (coalesce->use_adaptive_rx_coalesce && + !ena_com_get_adaptive_moderation_enabled(ena_dev)) + ena_com_enable_adaptive_moderation(ena_dev); + + if (!coalesce->use_adaptive_rx_coalesce && + ena_com_get_adaptive_moderation_enabled(ena_dev)) + ena_com_disable_adaptive_moderation(ena_dev); return 0; } diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index d46a912002ff..948583fdcc28 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -1238,8 +1238,8 @@ static int ena_io_poll(struct napi_struct *napi, int budget) struct ena_napi *ena_napi = container_of(napi, struct ena_napi, napi); struct ena_ring *tx_ring, *rx_ring; - u32 tx_work_done; - u32 rx_work_done; + int tx_work_done; + int rx_work_done = 0; int tx_budget; int napi_comp_call = 0; int ret; @@ -1256,7 +1256,11 @@ static int ena_io_poll(struct napi_struct *napi, int budget) } tx_work_done = ena_clean_tx_irq(tx_ring, tx_budget); - rx_work_done = ena_clean_rx_irq(rx_ring, napi, budget); + /* On netpoll the budget is zero and the handler should only clean the + * tx completions. + */ + if (likely(budget)) + rx_work_done = ena_clean_rx_irq(rx_ring, napi, budget); /* If the device is about to reset or down, avoid unmask * the interrupt and return 0 so NAPI won't reschedule diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c index 8f5021091eee..61a334d1b5e6 100644 --- a/drivers/net/ethernet/atheros/ag71xx.c +++ b/drivers/net/ethernet/atheros/ag71xx.c @@ -313,7 +313,7 @@ struct ag71xx { struct ag71xx_desc *stop_desc; dma_addr_t stop_desc_dma; - int phy_if_mode; + phy_interface_t phy_if_mode; struct delayed_work restart_work; struct timer_list oom_timer; @@ -1744,7 +1744,7 @@ static int ag71xx_probe(struct platform_device *pdev) eth_random_addr(ndev->dev_addr); } - err = of_get_phy_mode(np, ag->phy_if_mode); + err = of_get_phy_mode(np, &ag->phy_if_mode); if (err) { netif_err(ag, probe, ndev, "missing phy-mode property in DT\n"); goto err_free; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h index 8b08cb18e363..3f63ffd7561b 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h @@ -1109,7 +1109,7 @@ static inline u8 bnx2x_get_path_func_num(struct bnx2x *bp) for (i = 0; i < E1H_FUNC_MAX / 2; i++) { u32 func_config = MF_CFG_RD(bp, - func_mf_config[BP_PORT(bp) + 2 * i]. + func_mf_config[BP_PATH(bp) + 2 * i]. config); func_num += ((func_config & FUNC_MF_CFG_FUNC_HIDE) ? 0 : 1); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 192ff8d5da32..cff64e43bdd8 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -9976,10 +9976,18 @@ static void bnx2x_recovery_failed(struct bnx2x *bp) */ static void bnx2x_parity_recover(struct bnx2x *bp) { - bool global = false; u32 error_recovered, error_unrecovered; - bool is_parity; + bool is_parity, global = false; +#ifdef CONFIG_BNX2X_SRIOV + int vf_idx; + + for (vf_idx = 0; vf_idx < bp->requested_nr_virtfn; vf_idx++) { + struct bnx2x_virtf *vf = BP_VF(bp, vf_idx); + if (vf) + vf->state = VF_LOST; + } +#endif DP(NETIF_MSG_HW, "Handling parity\n"); while (1) { switch (bp->recovery_state) { diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h index b6ebd92ec565..3a716c015415 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h @@ -139,6 +139,7 @@ struct bnx2x_virtf { #define VF_ACQUIRED 1 /* VF acquired, but not initialized */ #define VF_ENABLED 2 /* VF Enabled */ #define VF_RESET 3 /* VF FLR'd, pending cleanup */ +#define VF_LOST 4 /* Recovery while VFs are loaded */ bool flr_clnup_stage; /* true during flr cleanup */ bool malicious; /* true if FW indicated so, until FLR */ diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c index 0752b7fa4d9c..ea0e9394f898 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c @@ -2107,6 +2107,18 @@ static void bnx2x_vf_mbx_request(struct bnx2x *bp, struct bnx2x_virtf *vf, { int i; + if (vf->state == VF_LOST) { + /* Just ack the FW and return if VFs are lost + * in case of parity error. VFs are supposed to be timedout + * on waiting for PF response. + */ + DP(BNX2X_MSG_IOV, + "VF 0x%x lost, not handling the request\n", vf->abs_vfid); + + storm_memset_vf_mbx_ack(bp, vf->abs_vfid); + return; + } + /* check if tlv type is known */ if (bnx2x_tlv_supported(mbx->first_tlv.tl.type)) { /* Lock the per vf op mutex and note the locker's identity. diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 85983f0e3134..c779f9cf8822 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -2001,6 +2001,9 @@ static int bnxt_async_event_process(struct bnxt *bp, case ASYNC_EVENT_CMPL_EVENT_ID_RESET_NOTIFY: { u32 data1 = le32_to_cpu(cmpl->event_data1); + if (!bp->fw_health) + goto async_event_process_exit; + bp->fw_reset_timestamp = jiffies; bp->fw_reset_min_dsecs = cmpl->timestamp_lo; if (!bp->fw_reset_min_dsecs) @@ -4421,8 +4424,9 @@ int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp, unsigned long *bmap, int bmap_size, FUNC_DRV_RGTR_REQ_ENABLES_ASYNC_EVENT_FWD); req.os_type = cpu_to_le16(FUNC_DRV_RGTR_REQ_OS_TYPE_LINUX); - flags = FUNC_DRV_RGTR_REQ_FLAGS_16BIT_VER_MODE | - FUNC_DRV_RGTR_REQ_FLAGS_HOT_RESET_SUPPORT; + flags = FUNC_DRV_RGTR_REQ_FLAGS_16BIT_VER_MODE; + if (bp->fw_cap & BNXT_FW_CAP_HOT_RESET) + flags |= FUNC_DRV_RGTR_REQ_FLAGS_HOT_RESET_SUPPORT; if (bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY) flags |= FUNC_DRV_RGTR_REQ_FLAGS_ERROR_RECOVERY_SUPPORT | FUNC_DRV_RGTR_REQ_FLAGS_MASTER_SUPPORT; @@ -6186,7 +6190,7 @@ static void bnxt_hwrm_set_coal_params(struct bnxt *bp, tmr = bnxt_usec_to_coal_tmr(bp, hw_coal->coal_ticks_irq); val = clamp_t(u16, tmr, 1, coal_cap->cmpl_aggr_dma_tmr_during_int_max); - req->cmpl_aggr_dma_tmr_during_int = cpu_to_le16(tmr); + req->cmpl_aggr_dma_tmr_during_int = cpu_to_le16(val); req->enables |= cpu_to_le16(BNXT_COAL_CMPL_AGGR_TMR_DURING_INT_ENABLE); } @@ -7115,14 +7119,6 @@ static int bnxt_hwrm_error_recovery_qcfg(struct bnxt *bp) rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (rc) goto err_recovery_out; - if (!fw_health) { - fw_health = kzalloc(sizeof(*fw_health), GFP_KERNEL); - bp->fw_health = fw_health; - if (!fw_health) { - rc = -ENOMEM; - goto err_recovery_out; - } - } fw_health->flags = le32_to_cpu(resp->flags); if ((fw_health->flags & ERROR_RECOVERY_QCFG_RESP_FLAGS_CO_CPU) && !(bp->fw_cap & BNXT_FW_CAP_KONG_MB_CHNL)) { @@ -8796,6 +8792,9 @@ static int bnxt_hwrm_if_change(struct bnxt *bp, bool up) if (fw_reset) { if (!test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) bnxt_ulp_stop(bp); + bnxt_free_ctx_mem(bp); + kfree(bp->ctx); + bp->ctx = NULL; rc = bnxt_fw_init_one(bp); if (rc) { set_bit(BNXT_STATE_ABORT_ERR, &bp->state); @@ -9990,8 +9989,7 @@ static void bnxt_fw_health_check(struct bnxt *bp) struct bnxt_fw_health *fw_health = bp->fw_health; u32 val; - if (!fw_health || !fw_health->enabled || - test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) + if (!fw_health->enabled || test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) return; if (fw_health->tmr_counter) { @@ -10482,6 +10480,23 @@ static void bnxt_init_dflt_coal(struct bnxt *bp) bp->stats_coal_ticks = BNXT_DEF_STATS_COAL_TICKS; } +static void bnxt_alloc_fw_health(struct bnxt *bp) +{ + if (bp->fw_health) + return; + + if (!(bp->fw_cap & BNXT_FW_CAP_HOT_RESET) && + !(bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY)) + return; + + bp->fw_health = kzalloc(sizeof(*bp->fw_health), GFP_KERNEL); + if (!bp->fw_health) { + netdev_warn(bp->dev, "Failed to allocate fw_health\n"); + bp->fw_cap &= ~BNXT_FW_CAP_HOT_RESET; + bp->fw_cap &= ~BNXT_FW_CAP_ERROR_RECOVERY; + } +} + static int bnxt_fw_init_one_p1(struct bnxt *bp) { int rc; @@ -10528,6 +10543,7 @@ static int bnxt_fw_init_one_p2(struct bnxt *bp) netdev_warn(bp->dev, "hwrm query adv flow mgnt failure rc: %d\n", rc); + bnxt_alloc_fw_health(bp); rc = bnxt_hwrm_error_recovery_qcfg(bp); if (rc) netdev_warn(bp->dev, "hwrm query error recovery failure rc: %d\n", @@ -10609,6 +10625,12 @@ static int bnxt_fw_init_one(struct bnxt *bp) rc = bnxt_approve_mac(bp, bp->dev->dev_addr, false); if (rc) return rc; + + /* In case fw capabilities have changed, destroy the unneeded + * reporters and create newly capable ones. + */ + bnxt_dl_fw_reporters_destroy(bp, false); + bnxt_dl_fw_reporters_create(bp); bnxt_fw_init_one_p3(bp); return 0; } @@ -10751,8 +10773,7 @@ static void bnxt_fw_reset_task(struct work_struct *work) bnxt_queue_fw_reset_work(bp, bp->fw_reset_min_dsecs * HZ / 10); return; case BNXT_FW_RESET_STATE_ENABLE_DEV: - if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state) && - bp->fw_health) { + if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state)) { u32 val; val = bnxt_fw_health_readl(bp, @@ -11396,11 +11417,11 @@ static void bnxt_remove_one(struct pci_dev *pdev) struct net_device *dev = pci_get_drvdata(pdev); struct bnxt *bp = netdev_priv(dev); - if (BNXT_PF(bp)) { + if (BNXT_PF(bp)) bnxt_sriov_disable(bp); - bnxt_dl_unregister(bp); - } + bnxt_dl_fw_reporters_destroy(bp, true); + bnxt_dl_unregister(bp); pci_disable_pcie_error_reporting(pdev); unregister_netdev(dev); bnxt_shutdown_tc(bp); @@ -11415,6 +11436,8 @@ static void bnxt_remove_one(struct pci_dev *pdev) bnxt_dcb_free(bp); kfree(bp->edev); bp->edev = NULL; + kfree(bp->fw_health); + bp->fw_health = NULL; bnxt_cleanup_pci(bp); bnxt_free_ctx_mem(bp); kfree(bp->ctx); @@ -11875,8 +11898,8 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (rc) goto init_err_cleanup_tc; - if (BNXT_PF(bp)) - bnxt_dl_register(bp); + bnxt_dl_register(bp); + bnxt_dl_fw_reporters_create(bp); netdev_info(dev, "%s found at mem %lx, node addr %pM\n", board_info[ent->driver_data].name, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c index acb2dd64c023..3eedd4477218 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c @@ -39,11 +39,10 @@ static int bnxt_fw_reporter_diagnose(struct devlink_health_reporter *reporter, struct netlink_ext_ack *extack) { struct bnxt *bp = devlink_health_reporter_priv(reporter); - struct bnxt_fw_health *health = bp->fw_health; u32 val, health_status; int rc; - if (!health || test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) + if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) return 0; val = bnxt_fw_health_readl(bp, BNXT_FW_HEALTH_REG); @@ -126,21 +125,15 @@ struct devlink_health_reporter_ops bnxt_dl_fw_fatal_reporter_ops = { .recover = bnxt_fw_fatal_recover, }; -static void bnxt_dl_fw_reporters_create(struct bnxt *bp) +void bnxt_dl_fw_reporters_create(struct bnxt *bp) { struct bnxt_fw_health *health = bp->fw_health; - if (!health) + if (!bp->dl || !health) return; - health->fw_reporter = - devlink_health_reporter_create(bp->dl, &bnxt_dl_fw_reporter_ops, - 0, false, bp); - if (IS_ERR(health->fw_reporter)) { - netdev_warn(bp->dev, "Failed to create FW health reporter, rc = %ld\n", - PTR_ERR(health->fw_reporter)); - health->fw_reporter = NULL; - } + if (!(bp->fw_cap & BNXT_FW_CAP_HOT_RESET) || health->fw_reset_reporter) + goto err_recovery; health->fw_reset_reporter = devlink_health_reporter_create(bp->dl, @@ -150,8 +143,30 @@ static void bnxt_dl_fw_reporters_create(struct bnxt *bp) netdev_warn(bp->dev, "Failed to create FW fatal health reporter, rc = %ld\n", PTR_ERR(health->fw_reset_reporter)); health->fw_reset_reporter = NULL; + bp->fw_cap &= ~BNXT_FW_CAP_HOT_RESET; + } + +err_recovery: + if (!(bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY)) + return; + + if (!health->fw_reporter) { + health->fw_reporter = + devlink_health_reporter_create(bp->dl, + &bnxt_dl_fw_reporter_ops, + 0, false, bp); + if (IS_ERR(health->fw_reporter)) { + netdev_warn(bp->dev, "Failed to create FW health reporter, rc = %ld\n", + PTR_ERR(health->fw_reporter)); + health->fw_reporter = NULL; + bp->fw_cap &= ~BNXT_FW_CAP_ERROR_RECOVERY; + return; + } } + if (health->fw_fatal_reporter) + return; + health->fw_fatal_reporter = devlink_health_reporter_create(bp->dl, &bnxt_dl_fw_fatal_reporter_ops, @@ -160,24 +175,35 @@ static void bnxt_dl_fw_reporters_create(struct bnxt *bp) netdev_warn(bp->dev, "Failed to create FW fatal health reporter, rc = %ld\n", PTR_ERR(health->fw_fatal_reporter)); health->fw_fatal_reporter = NULL; + bp->fw_cap &= ~BNXT_FW_CAP_ERROR_RECOVERY; } } -static void bnxt_dl_fw_reporters_destroy(struct bnxt *bp) +void bnxt_dl_fw_reporters_destroy(struct bnxt *bp, bool all) { struct bnxt_fw_health *health = bp->fw_health; - if (!health) + if (!bp->dl || !health) return; - if (health->fw_reporter) - devlink_health_reporter_destroy(health->fw_reporter); - - if (health->fw_reset_reporter) + if ((all || !(bp->fw_cap & BNXT_FW_CAP_HOT_RESET)) && + health->fw_reset_reporter) { devlink_health_reporter_destroy(health->fw_reset_reporter); + health->fw_reset_reporter = NULL; + } - if (health->fw_fatal_reporter) + if ((bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY) && !all) + return; + + if (health->fw_reporter) { + devlink_health_reporter_destroy(health->fw_reporter); + health->fw_reporter = NULL; + } + + if (health->fw_fatal_reporter) { devlink_health_reporter_destroy(health->fw_fatal_reporter); + health->fw_fatal_reporter = NULL; + } } void bnxt_devlink_health_report(struct bnxt *bp, unsigned long event) @@ -185,9 +211,6 @@ void bnxt_devlink_health_report(struct bnxt *bp, unsigned long event) struct bnxt_fw_health *fw_health = bp->fw_health; struct bnxt_fw_reporter_ctx fw_reporter_ctx; - if (!fw_health) - return; - fw_reporter_ctx.sp_event = event; switch (event) { case BNXT_FW_RESET_NOTIFY_SP_EVENT: @@ -247,6 +270,8 @@ static const struct devlink_ops bnxt_dl_ops = { .flash_update = bnxt_dl_flash_update, }; +static const struct devlink_ops bnxt_vf_dl_ops; + enum bnxt_dl_param_id { BNXT_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX, BNXT_DEVLINK_PARAM_ID_GRE_VER_CHECK, @@ -460,7 +485,10 @@ int bnxt_dl_register(struct bnxt *bp) return -ENOTSUPP; } - dl = devlink_alloc(&bnxt_dl_ops, sizeof(struct bnxt_dl)); + if (BNXT_PF(bp)) + dl = devlink_alloc(&bnxt_dl_ops, sizeof(struct bnxt_dl)); + else + dl = devlink_alloc(&bnxt_vf_dl_ops, sizeof(struct bnxt_dl)); if (!dl) { netdev_warn(bp->dev, "devlink_alloc failed"); return -ENOMEM; @@ -479,6 +507,9 @@ int bnxt_dl_register(struct bnxt *bp) goto err_dl_free; } + if (!BNXT_PF(bp)) + return 0; + rc = devlink_params_register(dl, bnxt_dl_params, ARRAY_SIZE(bnxt_dl_params)); if (rc) { @@ -506,8 +537,6 @@ int bnxt_dl_register(struct bnxt *bp) devlink_params_publish(dl); - bnxt_dl_fw_reporters_create(bp); - return 0; err_dl_port_unreg: @@ -530,12 +559,14 @@ void bnxt_dl_unregister(struct bnxt *bp) if (!dl) return; - bnxt_dl_fw_reporters_destroy(bp); - devlink_port_params_unregister(&bp->dl_port, bnxt_dl_port_params, - ARRAY_SIZE(bnxt_dl_port_params)); - devlink_port_unregister(&bp->dl_port); - devlink_params_unregister(dl, bnxt_dl_params, - ARRAY_SIZE(bnxt_dl_params)); + if (BNXT_PF(bp)) { + devlink_port_params_unregister(&bp->dl_port, + bnxt_dl_port_params, + ARRAY_SIZE(bnxt_dl_port_params)); + devlink_port_unregister(&bp->dl_port); + devlink_params_unregister(dl, bnxt_dl_params, + ARRAY_SIZE(bnxt_dl_params)); + } devlink_unregister(dl); devlink_free(dl); } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h index 665d4bdcd8c0..6db6c3dac472 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h @@ -58,6 +58,8 @@ struct bnxt_dl_nvm_param { void bnxt_devlink_health_report(struct bnxt *bp, unsigned long event); void bnxt_dl_health_status_update(struct bnxt *bp, bool healthy); +void bnxt_dl_fw_reporters_create(struct bnxt *bp); +void bnxt_dl_fw_reporters_destroy(struct bnxt *bp, bool all); int bnxt_dl_register(struct bnxt *bp); void bnxt_dl_unregister(struct bnxt *bp); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 2ccf79cdcb1e..08d56ec7b68a 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -3071,8 +3071,15 @@ static int bnxt_hwrm_dbg_dma_data(struct bnxt *bp, void *msg, int msg_len, } } - if (info->dest_buf) - memcpy(info->dest_buf + off, dma_buf, len); + if (info->dest_buf) { + if ((info->seg_start + off + len) <= + BNXT_COREDUMP_BUF_LEN(info->buf_len)) { + memcpy(info->dest_buf + off, dma_buf, len); + } else { + rc = -ENOBUFS; + break; + } + } if (cmn_req->req_type == cpu_to_le16(HWRM_DBG_COREDUMP_RETRIEVE)) @@ -3126,7 +3133,7 @@ static int bnxt_hwrm_dbg_coredump_initiate(struct bnxt *bp, u16 component_id, static int bnxt_hwrm_dbg_coredump_retrieve(struct bnxt *bp, u16 component_id, u16 segment_id, u32 *seg_len, - void *buf, u32 offset) + void *buf, u32 buf_len, u32 offset) { struct hwrm_dbg_coredump_retrieve_input req = {0}; struct bnxt_hwrm_dbg_dma_info info = {NULL}; @@ -3141,8 +3148,11 @@ static int bnxt_hwrm_dbg_coredump_retrieve(struct bnxt *bp, u16 component_id, seq_no); info.data_len_off = offsetof(struct hwrm_dbg_coredump_retrieve_output, data_len); - if (buf) + if (buf) { info.dest_buf = buf + offset; + info.buf_len = buf_len; + info.seg_start = offset; + } rc = bnxt_hwrm_dbg_dma_data(bp, &req, sizeof(req), &info); if (!rc) @@ -3232,14 +3242,17 @@ bnxt_fill_coredump_record(struct bnxt *bp, struct bnxt_coredump_record *record, static int bnxt_get_coredump(struct bnxt *bp, void *buf, u32 *dump_len) { u32 ver_get_resp_len = sizeof(struct hwrm_ver_get_output); + u32 offset = 0, seg_hdr_len, seg_record_len, buf_len = 0; struct coredump_segment_record *seg_record = NULL; - u32 offset = 0, seg_hdr_len, seg_record_len; struct bnxt_coredump_segment_hdr seg_hdr; struct bnxt_coredump coredump = {NULL}; time64_t start_time; u16 start_utc; int rc = 0, i; + if (buf) + buf_len = *dump_len; + start_time = ktime_get_real_seconds(); start_utc = sys_tz.tz_minuteswest * 60; seg_hdr_len = sizeof(seg_hdr); @@ -3272,6 +3285,12 @@ static int bnxt_get_coredump(struct bnxt *bp, void *buf, u32 *dump_len) u32 duration = 0, seg_len = 0; unsigned long start, end; + if (buf && ((offset + seg_hdr_len) > + BNXT_COREDUMP_BUF_LEN(buf_len))) { + rc = -ENOBUFS; + goto err; + } + start = jiffies; rc = bnxt_hwrm_dbg_coredump_initiate(bp, comp_id, seg_id); @@ -3284,9 +3303,11 @@ static int bnxt_get_coredump(struct bnxt *bp, void *buf, u32 *dump_len) /* Write segment data into the buffer */ rc = bnxt_hwrm_dbg_coredump_retrieve(bp, comp_id, seg_id, - &seg_len, buf, + &seg_len, buf, buf_len, offset + seg_hdr_len); - if (rc) + if (rc && rc == -ENOBUFS) + goto err; + else if (rc) netdev_err(bp->dev, "Failed to retrieve coredump for seg = %d\n", seg_record->segment_id); @@ -3316,7 +3337,8 @@ err: rc); kfree(coredump.data); *dump_len += sizeof(struct bnxt_coredump_record); - + if (rc == -ENOBUFS) + netdev_err(bp->dev, "Firmware returned large coredump buffer"); return rc; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h index 4428d0abcbc1..3576d951727b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h @@ -31,6 +31,8 @@ struct bnxt_coredump { u16 total_segs; }; +#define BNXT_COREDUMP_BUF_LEN(len) ((len) - sizeof(struct bnxt_coredump_record)) + struct bnxt_hwrm_dbg_dma_info { void *dest_buf; int dest_buf_size; @@ -38,6 +40,8 @@ struct bnxt_hwrm_dbg_dma_info { u16 seq_off; u16 data_len_off; u16 segs; + u32 seg_start; + u32 buf_len; }; struct hwrm_dbg_cmn_input { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c index c601ff7b8f61..4a316c4b3fa8 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c @@ -113,8 +113,10 @@ static int bnxt_req_msix_vecs(struct bnxt_en_dev *edev, int ulp_id, { struct net_device *dev = edev->net; struct bnxt *bp = netdev_priv(dev); + struct bnxt_hw_resc *hw_resc; int max_idx, max_cp_rings; int avail_msix, idx; + int total_vecs; int rc = 0; ASSERT_RTNL(); @@ -142,7 +144,10 @@ static int bnxt_req_msix_vecs(struct bnxt_en_dev *edev, int ulp_id, } edev->ulp_tbl[ulp_id].msix_base = idx; edev->ulp_tbl[ulp_id].msix_requested = avail_msix; - if (bp->total_irqs < (idx + avail_msix)) { + hw_resc = &bp->hw_resc; + total_vecs = idx + avail_msix; + if (bp->total_irqs < total_vecs || + (BNXT_NEW_RM(bp) && hw_resc->resv_irqs < total_vecs)) { if (netif_running(dev)) { bnxt_close_nic(bp, true, false); rc = bnxt_open_nic(bp, true, false); @@ -156,7 +161,6 @@ static int bnxt_req_msix_vecs(struct bnxt_en_dev *edev, int ulp_id, } if (BNXT_NEW_RM(bp)) { - struct bnxt_hw_resc *hw_resc = &bp->hw_resc; int resv_msix; resv_msix = hw_resc->resv_irqs - bp->cp_nr_rings; diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 9c767ee252ac..c5ee363ca5dc 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -664,9 +664,30 @@ static int macb_mii_probe(struct net_device *dev) return 0; } +static int macb_mdiobus_register(struct macb *bp) +{ + struct device_node *child, *np = bp->pdev->dev.of_node; + + /* Only create the PHY from the device tree if at least one PHY is + * described. Otherwise scan the entire MDIO bus. We do this to support + * old device tree that did not follow the best practices and did not + * describe their network PHYs. + */ + for_each_available_child_of_node(np, child) + if (of_mdiobus_child_is_phy(child)) { + /* The loop increments the child refcount, + * decrement it before returning. + */ + of_node_put(child); + + return of_mdiobus_register(bp->mii_bus, np); + } + + return mdiobus_register(bp->mii_bus); +} + static int macb_mii_init(struct macb *bp) { - struct device_node *np; int err = -ENXIO; /* Enable management port */ @@ -688,9 +709,7 @@ static int macb_mii_init(struct macb *bp) dev_set_drvdata(&bp->dev->dev, bp->mii_bus); - np = bp->pdev->dev.of_node; - - err = of_mdiobus_register(bp->mii_bus, np); + err = macb_mdiobus_register(bp); if (err) goto err_out_free_mdiobus; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c index 93868dca186a..aca9f7a20a2a 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c @@ -3048,6 +3048,9 @@ static int sge_queue_entries(const struct adapter *adap) int tot_uld_entries = 0; int i; + if (!is_uld(adap)) + goto lld_only; + mutex_lock(&uld_mutex); for (i = 0; i < CXGB4_TX_MAX; i++) tot_uld_entries += sge_qinfo_uld_txq_entries(adap, i); @@ -3058,6 +3061,7 @@ static int sge_queue_entries(const struct adapter *adap) } mutex_unlock(&uld_mutex); +lld_only: return DIV_ROUND_UP(adap->sge.ethqsets, 4) + (adap->sge.eohw_txq ? DIV_ROUND_UP(adap->sge.eoqsets, 4) : 0) + tot_uld_entries + diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c index 477973d2e341..8971dddcdb7a 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c @@ -145,6 +145,10 @@ static int cxgb4_mqprio_alloc_hw_resources(struct net_device *dev) kfree(adap->sge.eohw_rxq); return -ENOMEM; } + + refcount_set(&adap->tc_mqprio->refcnt, 1); + } else { + refcount_inc(&adap->tc_mqprio->refcnt); } if (!(adap->flags & CXGB4_USING_MSIX)) @@ -205,7 +209,6 @@ static int cxgb4_mqprio_alloc_hw_resources(struct net_device *dev) cxgb4_enable_rx(adap, &eorxq->rspq); } - refcount_inc(&adap->tc_mqprio->refcnt); return 0; out_free_msix: @@ -234,9 +237,10 @@ out_free_queues: t4_sge_free_ethofld_txq(adap, eotxq); } - kfree(adap->sge.eohw_txq); - kfree(adap->sge.eohw_rxq); - + if (refcount_dec_and_test(&adap->tc_mqprio->refcnt)) { + kfree(adap->sge.eohw_txq); + kfree(adap->sge.eohw_rxq); + } return ret; } diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index a8f4c69252ff..2814b96751b4 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -576,6 +576,8 @@ static int gmac_setup_txqs(struct net_device *netdev) if (port->txq_dma_base & ~DMA_Q_BASE_MASK) { dev_warn(geth->dev, "TX queue base is not aligned\n"); + dma_free_coherent(geth->dev, len * sizeof(*desc_ring), + desc_ring, port->txq_dma_base); kfree(skb_tab); return -ENOMEM; } diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c index a9503aea527f..6437fe6b9abf 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c @@ -160,10 +160,10 @@ static int dpaa2_ptp_probe(struct fsl_mc_device *mc_dev) irq = mc_dev->irqs[0]; ptp_qoriq->irq = irq->msi_desc->irq; - err = devm_request_threaded_irq(dev, ptp_qoriq->irq, NULL, - dpaa2_ptp_irq_handler_thread, - IRQF_NO_SUSPEND | IRQF_ONESHOT, - dev_name(dev), ptp_qoriq); + err = request_threaded_irq(ptp_qoriq->irq, NULL, + dpaa2_ptp_irq_handler_thread, + IRQF_NO_SUSPEND | IRQF_ONESHOT, + dev_name(dev), ptp_qoriq); if (err < 0) { dev_err(dev, "devm_request_threaded_irq(): %d\n", err); goto err_free_mc_irq; @@ -173,18 +173,20 @@ static int dpaa2_ptp_probe(struct fsl_mc_device *mc_dev) DPRTC_IRQ_INDEX, 1); if (err < 0) { dev_err(dev, "dprtc_set_irq_enable(): %d\n", err); - goto err_free_mc_irq; + goto err_free_threaded_irq; } err = ptp_qoriq_init(ptp_qoriq, base, &dpaa2_ptp_caps); if (err) - goto err_free_mc_irq; + goto err_free_threaded_irq; dpaa2_phc_index = ptp_qoriq->phc_index; dev_set_drvdata(dev, ptp_qoriq); return 0; +err_free_threaded_irq: + free_irq(ptp_qoriq->irq, ptp_qoriq); err_free_mc_irq: fsl_mc_free_irqs(mc_dev); err_unmap: diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c index 3e9b6d543c77..150a8ccfb8b1 100644 --- a/drivers/net/ethernet/hisilicon/hip04_eth.c +++ b/drivers/net/ethernet/hisilicon/hip04_eth.c @@ -543,9 +543,9 @@ hip04_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev) skb_tx_timestamp(skb); hip04_set_xmit_desc(priv, phys); - priv->tx_head = TX_NEXT(tx_head); count++; netdev_sent_queue(ndev, skb->len); + priv->tx_head = TX_NEXT(tx_head); stats->tx_bytes += skb->len; stats->tx_packets++; diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index c90080781924..830791ab4619 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -184,7 +184,7 @@ static int ibmvnic_wait_for_completion(struct ibmvnic_adapter *adapter, netdev_err(netdev, "Device down!\n"); return -ENODEV; } - if (retry--) + if (!retry--) break; if (wait_for_completion_timeout(comp_done, div_timeout)) return 0; diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index cb6367334ca7..4833187bd259 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -1152,7 +1152,7 @@ void i40e_set_fec_in_flags(u8 fec_cfg, u32 *flags); static inline bool i40e_enabled_xdp_vsi(struct i40e_vsi *vsi) { - return !!vsi->xdp_prog; + return !!READ_ONCE(vsi->xdp_prog); } int i40e_create_queue_channel(struct i40e_vsi *vsi, struct i40e_channel *ch); diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 1ccabeafa44c..2c5af6d4a6b1 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -6823,8 +6823,8 @@ void i40e_down(struct i40e_vsi *vsi) for (i = 0; i < vsi->num_queue_pairs; i++) { i40e_clean_tx_ring(vsi->tx_rings[i]); if (i40e_enabled_xdp_vsi(vsi)) { - /* Make sure that in-progress ndo_xdp_xmit - * calls are completed. + /* Make sure that in-progress ndo_xdp_xmit and + * ndo_xsk_wakeup calls are completed. */ synchronize_rcu(); i40e_clean_tx_ring(vsi->xdp_rings[i]); @@ -12546,8 +12546,12 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi, old_prog = xchg(&vsi->xdp_prog, prog); - if (need_reset) + if (need_reset) { + if (!prog) + /* Wait until ndo_xsk_wakeup completes. */ + synchronize_rcu(); i40e_reset_and_rebuild(pf, true, true); + } for (i = 0; i < vsi->num_queue_pairs; i++) WRITE_ONCE(vsi->rx_rings[i]->xdp_prog, vsi->xdp_prog); diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index d07e1a890428..f73cd917c44f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -787,8 +787,12 @@ int i40e_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags) { struct i40e_netdev_priv *np = netdev_priv(dev); struct i40e_vsi *vsi = np->vsi; + struct i40e_pf *pf = vsi->back; struct i40e_ring *ring; + if (test_bit(__I40E_CONFIG_BUSY, pf->state)) + return -ENETDOWN; + if (test_bit(__I40E_VSI_DOWN, vsi->state)) return -ENETDOWN; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 25c097cd8100..82a30b597cf9 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -10261,7 +10261,12 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog) /* If transitioning XDP modes reconfigure rings */ if (need_reset) { - int err = ixgbe_setup_tc(dev, adapter->hw_tcs); + int err; + + if (!prog) + /* Wait until ndo_xsk_wakeup completes. */ + synchronize_rcu(); + err = ixgbe_setup_tc(dev, adapter->hw_tcs); if (err) { rcu_assign_pointer(adapter->xdp_prog, old_prog); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c index d6feaacfbf89..b43be9f14105 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c @@ -709,10 +709,14 @@ int ixgbe_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags) if (qid >= adapter->num_xdp_queues) return -ENXIO; - if (!adapter->xdp_ring[qid]->xsk_umem) + ring = adapter->xdp_ring[qid]; + + if (test_bit(__IXGBE_TX_DISABLED, &ring->state)) + return -ENETDOWN; + + if (!ring->xsk_umem) return -ENXIO; - ring = adapter->xdp_ring[qid]; if (!napi_if_scheduled_mark_missed(&ring->q_vector->napi)) { u64 eics = BIT_ULL(ring->q_vector->v_idx); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 62dc2f362a16..14e372cda7f4 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -3680,7 +3680,7 @@ static int mvpp2_open(struct net_device *dev) valid = true; } - if (priv->hw_version == MVPP22 && port->link_irq && !port->phylink) { + if (priv->hw_version == MVPP22 && port->link_irq) { err = request_irq(port->link_irq, mvpp2_link_status_isr, 0, dev->name, port); if (err) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 2c16add0b642..9c8427698238 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -760,7 +760,7 @@ enum { MLX5E_STATE_OPENED, MLX5E_STATE_DESTROYING, MLX5E_STATE_XDP_TX_ENABLED, - MLX5E_STATE_XDP_OPEN, + MLX5E_STATE_XDP_ACTIVE, }; struct mlx5e_rqt { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h index 36ac1e3816b9..d7587f40ecae 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h @@ -75,12 +75,18 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, static inline void mlx5e_xdp_tx_enable(struct mlx5e_priv *priv) { set_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state); + + if (priv->channels.params.xdp_prog) + set_bit(MLX5E_STATE_XDP_ACTIVE, &priv->state); } static inline void mlx5e_xdp_tx_disable(struct mlx5e_priv *priv) { + if (priv->channels.params.xdp_prog) + clear_bit(MLX5E_STATE_XDP_ACTIVE, &priv->state); + clear_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state); - /* let other device's napi(s) see our new state */ + /* Let other device's napi(s) and XSK wakeups see our new state. */ synchronize_rcu(); } @@ -89,19 +95,9 @@ static inline bool mlx5e_xdp_tx_is_enabled(struct mlx5e_priv *priv) return test_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state); } -static inline void mlx5e_xdp_set_open(struct mlx5e_priv *priv) -{ - set_bit(MLX5E_STATE_XDP_OPEN, &priv->state); -} - -static inline void mlx5e_xdp_set_closed(struct mlx5e_priv *priv) -{ - clear_bit(MLX5E_STATE_XDP_OPEN, &priv->state); -} - -static inline bool mlx5e_xdp_is_open(struct mlx5e_priv *priv) +static inline bool mlx5e_xdp_is_active(struct mlx5e_priv *priv) { - return test_bit(MLX5E_STATE_XDP_OPEN, &priv->state); + return test_bit(MLX5E_STATE_XDP_ACTIVE, &priv->state); } static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_xdpsq *sq) 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 631af8dee517..c28cbae42331 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c @@ -144,6 +144,7 @@ void mlx5e_close_xsk(struct mlx5e_channel *c) { clear_bit(MLX5E_CHANNEL_STATE_XSK, c->state); napi_synchronize(&c->napi); + synchronize_rcu(); /* Sync with the XSK wakeup. */ mlx5e_close_rq(&c->xskrq); mlx5e_close_cq(&c->xskrq.cq); 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 87827477d38c..fe2d596cb361 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c @@ -14,7 +14,7 @@ int mlx5e_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags) struct mlx5e_channel *c; u16 ix; - if (unlikely(!mlx5e_xdp_is_open(priv))) + if (unlikely(!mlx5e_xdp_is_active(priv))) return -ENETDOWN; if (unlikely(!mlx5e_qid_get_ch_if_in_group(params, qid, MLX5E_RQ_GROUP_XSK, &ix))) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 4980e80a5e85..4997b8a51994 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3000,12 +3000,9 @@ void mlx5e_timestamp_init(struct mlx5e_priv *priv) int mlx5e_open_locked(struct net_device *netdev) { struct mlx5e_priv *priv = netdev_priv(netdev); - bool is_xdp = priv->channels.params.xdp_prog; int err; set_bit(MLX5E_STATE_OPENED, &priv->state); - if (is_xdp) - mlx5e_xdp_set_open(priv); err = mlx5e_open_channels(priv, &priv->channels); if (err) @@ -3020,8 +3017,6 @@ int mlx5e_open_locked(struct net_device *netdev) return 0; err_clear_state_opened_flag: - if (is_xdp) - mlx5e_xdp_set_closed(priv); clear_bit(MLX5E_STATE_OPENED, &priv->state); return err; } @@ -3053,8 +3048,6 @@ int mlx5e_close_locked(struct net_device *netdev) if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) return 0; - if (priv->channels.params.xdp_prog) - mlx5e_xdp_set_closed(priv); clear_bit(MLX5E_STATE_OPENED, &priv->state); netif_carrier_off(priv->netdev); @@ -4371,16 +4364,6 @@ static int mlx5e_xdp_allowed(struct mlx5e_priv *priv, struct bpf_prog *prog) return 0; } -static int mlx5e_xdp_update_state(struct mlx5e_priv *priv) -{ - if (priv->channels.params.xdp_prog) - mlx5e_xdp_set_open(priv); - else - mlx5e_xdp_set_closed(priv); - - return 0; -} - static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog) { struct mlx5e_priv *priv = netdev_priv(netdev); @@ -4415,7 +4398,7 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog) mlx5e_set_rq_type(priv->mdev, &new_channels.params); old_prog = priv->channels.params.xdp_prog; - err = mlx5e_safe_switch_channels(priv, &new_channels, mlx5e_xdp_update_state); + err = mlx5e_safe_switch_channels(priv, &new_channels, NULL); if (err) goto unlock; } else { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 30bfe3880faf..08b7e9f964da 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -5742,8 +5742,13 @@ static void mlxsw_sp_router_fib6_del(struct mlxsw_sp *mlxsw_sp, if (mlxsw_sp_fib6_rt_should_ignore(rt)) return; + /* Multipath routes are first added to the FIB trie and only then + * notified. If we vetoed the addition, we will get a delete + * notification for a route we do not have. Therefore, do not warn if + * route was not found. + */ fib6_entry = mlxsw_sp_fib6_entry_lookup(mlxsw_sp, rt); - if (WARN_ON(!fib6_entry)) + if (!fib6_entry) return; /* If not all the nexthops are deleted, then only reduce the nexthop diff --git a/drivers/net/ethernet/netronome/nfp/flower/metadata.c b/drivers/net/ethernet/netronome/nfp/flower/metadata.c index 7c4a15e967df..5defd31d481c 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/metadata.c +++ b/drivers/net/ethernet/netronome/nfp/flower/metadata.c @@ -65,17 +65,17 @@ static int nfp_get_stats_entry(struct nfp_app *app, u32 *stats_context_id) freed_stats_id = priv->stats_ring_size; /* Check for unallocated entries first. */ if (priv->stats_ids.init_unalloc > 0) { - if (priv->active_mem_unit == priv->total_mem_units) { - priv->stats_ids.init_unalloc--; - priv->active_mem_unit = 0; - } - *stats_context_id = FIELD_PREP(NFP_FL_STAT_ID_STAT, priv->stats_ids.init_unalloc - 1) | FIELD_PREP(NFP_FL_STAT_ID_MU_NUM, priv->active_mem_unit); - priv->active_mem_unit++; + + if (++priv->active_mem_unit == priv->total_mem_units) { + priv->stats_ids.init_unalloc--; + priv->active_mem_unit = 0; + } + return 0; } diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c index d6cfe4ffbaf3..d1ce4531d01a 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_filter.c +++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c @@ -1230,7 +1230,7 @@ qede_configure_mcast_filtering(struct net_device *ndev, netif_addr_lock_bh(ndev); mc_count = netdev_mc_count(ndev); - if (mc_count < 64) { + if (mc_count <= 64) { netdev_for_each_mc_addr(ha, ndev) { ether_addr_copy(temp, ha->addr); temp += ETH_ALEN; diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 481b096e984d..34fa3917eb33 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -1406,6 +1406,7 @@ static int qede_alloc_mem_rxq(struct qede_dev *edev, struct qede_rx_queue *rxq) rxq->rx_buf_seg_size = roundup_pow_of_two(size); } else { rxq->rx_buf_seg_size = PAGE_SIZE; + edev->ndev->features &= ~NETIF_F_GRO_HW; } /* Allocate the parallel driver ring for Rx buffers */ @@ -1450,6 +1451,7 @@ static int qede_alloc_mem_rxq(struct qede_dev *edev, struct qede_rx_queue *rxq) } } + edev->gro_disable = !(edev->ndev->features & NETIF_F_GRO_HW); if (!edev->gro_disable) qede_set_tpa_param(rxq); err: @@ -1702,8 +1704,6 @@ static void qede_init_fp(struct qede_dev *edev) snprintf(fp->name, sizeof(fp->name), "%s-fp-%d", edev->ndev->name, queue_id); } - - edev->gro_disable = !(edev->ndev->features & NETIF_F_GRO_HW); } static int qede_set_real_num_queues(struct qede_dev *edev) diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c index b4b8ba00ee01..986f26578d34 100644 --- a/drivers/net/ethernet/qlogic/qla3xxx.c +++ b/drivers/net/ethernet/qlogic/qla3xxx.c @@ -2756,6 +2756,9 @@ static int ql_alloc_large_buffers(struct ql3_adapter *qdev) int err; for (i = 0; i < qdev->num_large_buffers; i++) { + lrg_buf_cb = &qdev->lrg_buf[i]; + memset(lrg_buf_cb, 0, sizeof(struct ql_rcv_buf_cb)); + skb = netdev_alloc_skb(qdev->ndev, qdev->lrg_buffer_len); if (unlikely(!skb)) { @@ -2766,11 +2769,7 @@ static int ql_alloc_large_buffers(struct ql3_adapter *qdev) ql_free_large_buffers(qdev); return -ENOMEM; } else { - - lrg_buf_cb = &qdev->lrg_buf[i]; - memset(lrg_buf_cb, 0, sizeof(struct ql_rcv_buf_cb)); lrg_buf_cb->index = i; - lrg_buf_cb->skb = skb; /* * We save some space to copy the ethhdr from first * buffer @@ -2792,6 +2791,7 @@ static int ql_alloc_large_buffers(struct ql3_adapter *qdev) return -ENOMEM; } + lrg_buf_cb->skb = skb; dma_unmap_addr_set(lrg_buf_cb, mapaddr, map); dma_unmap_len_set(lrg_buf_cb, maplen, qdev->lrg_buffer_len - diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 992c773620ec..7a38d7f282a1 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -1472,6 +1472,12 @@ static int efx_allocate_msix_channels(struct efx_nic *efx, n_xdp_tx = num_possible_cpus(); n_xdp_ev = DIV_ROUND_UP(n_xdp_tx, EFX_TXQ_TYPES); + vec_count = pci_msix_vec_count(efx->pci_dev); + if (vec_count < 0) + return vec_count; + + max_channels = min_t(unsigned int, vec_count, max_channels); + /* Check resources. * We need a channel per event queue, plus a VI per tx queue. * This may be more pessimistic than it needs to be. @@ -1493,11 +1499,6 @@ static int efx_allocate_msix_channels(struct efx_nic *efx, n_xdp_tx, n_xdp_ev); } - n_channels = min(n_channels, max_channels); - - vec_count = pci_msix_vec_count(efx->pci_dev); - if (vec_count < 0) - return vec_count; if (vec_count < n_channels) { netif_err(efx, drv, efx->net_dev, "WARNING: Insufficient MSI-X vectors available (%d < %u).\n", @@ -1507,11 +1508,9 @@ static int efx_allocate_msix_channels(struct efx_nic *efx, n_channels = vec_count; } - efx->n_channels = n_channels; + n_channels = min(n_channels, max_channels); - /* Do not create the PTP TX queue(s) if PTP uses the MC directly. */ - if (extra_channels && !efx_ptp_use_mac_tx_timestamps(efx)) - n_channels--; + efx->n_channels = n_channels; /* Ignore XDP tx channels when creating rx channels. */ n_channels -= efx->n_xdp_channels; @@ -1531,11 +1530,10 @@ static int efx_allocate_msix_channels(struct efx_nic *efx, efx->n_rx_channels = n_channels; } - if (efx->n_xdp_channels) - efx->xdp_channel_offset = efx->tx_channel_offset + - efx->n_tx_channels; - else - efx->xdp_channel_offset = efx->n_channels; + efx->n_rx_channels = min(efx->n_rx_channels, parallelism); + efx->n_tx_channels = min(efx->n_tx_channels, parallelism); + + efx->xdp_channel_offset = n_channels; netif_dbg(efx, drv, efx->net_dev, "Allocating %u RX channels\n", @@ -1550,6 +1548,7 @@ static int efx_allocate_msix_channels(struct efx_nic *efx, static int efx_probe_interrupts(struct efx_nic *efx) { unsigned int extra_channels = 0; + unsigned int rss_spread; unsigned int i, j; int rc; @@ -1631,8 +1630,7 @@ static int efx_probe_interrupts(struct efx_nic *efx) for (i = 0; i < EFX_MAX_EXTRA_CHANNELS; i++) { if (!efx->extra_channel_type[i]) continue; - if (efx->interrupt_mode != EFX_INT_MODE_MSIX || - efx->n_channels <= extra_channels) { + if (j <= efx->tx_channel_offset + efx->n_tx_channels) { efx->extra_channel_type[i]->handle_no_channel(efx); } else { --j; @@ -1643,16 +1641,17 @@ static int efx_probe_interrupts(struct efx_nic *efx) } } + rss_spread = efx->n_rx_channels; /* RSS might be usable on VFs even if it is disabled on the PF */ #ifdef CONFIG_SFC_SRIOV if (efx->type->sriov_wanted) { - efx->rss_spread = ((efx->n_rx_channels > 1 || + efx->rss_spread = ((rss_spread > 1 || !efx->type->sriov_wanted(efx)) ? - efx->n_rx_channels : efx_vf_size(efx)); + rss_spread : efx_vf_size(efx)); return 0; } #endif - efx->rss_spread = efx->n_rx_channels; + efx->rss_spread = rss_spread; return 0; } diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index 1f88212be085..dfd5182d9e47 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -1533,9 +1533,7 @@ static inline bool efx_channel_is_xdp_tx(struct efx_channel *channel) static inline bool efx_channel_has_tx_queues(struct efx_channel *channel) { - return efx_channel_is_xdp_tx(channel) || - (channel->type && channel->type->want_txqs && - channel->type->want_txqs(channel)); + return true; } static inline struct efx_tx_queue * diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c index ef52b24ad9e7..c29bf862a94c 100644 --- a/drivers/net/ethernet/sfc/rx.c +++ b/drivers/net/ethernet/sfc/rx.c @@ -96,11 +96,12 @@ static inline void efx_sync_rx_buffer(struct efx_nic *efx, void efx_rx_config_page_split(struct efx_nic *efx) { - efx->rx_page_buf_step = ALIGN(efx->rx_dma_len + efx->rx_ip_align, + efx->rx_page_buf_step = ALIGN(efx->rx_dma_len + efx->rx_ip_align + + XDP_PACKET_HEADROOM, EFX_RX_BUF_ALIGNMENT); efx->rx_bufs_per_page = efx->rx_buffer_order ? 1 : ((PAGE_SIZE - sizeof(struct efx_rx_page_state)) / - (efx->rx_page_buf_step + XDP_PACKET_HEADROOM)); + efx->rx_page_buf_step); efx->rx_buffer_truesize = (PAGE_SIZE << efx->rx_buffer_order) / efx->rx_bufs_per_page; efx->rx_pages_per_batch = DIV_ROUND_UP(EFX_RX_PREFERRED_BATCH, @@ -190,14 +191,13 @@ static int efx_init_rx_buffers(struct efx_rx_queue *rx_queue, bool atomic) page_offset = sizeof(struct efx_rx_page_state); do { - page_offset += XDP_PACKET_HEADROOM; - dma_addr += XDP_PACKET_HEADROOM; - index = rx_queue->added_count & rx_queue->ptr_mask; rx_buf = efx_rx_buffer(rx_queue, index); - rx_buf->dma_addr = dma_addr + efx->rx_ip_align; + rx_buf->dma_addr = dma_addr + efx->rx_ip_align + + XDP_PACKET_HEADROOM; rx_buf->page = page; - rx_buf->page_offset = page_offset + efx->rx_ip_align; + rx_buf->page_offset = page_offset + efx->rx_ip_align + + XDP_PACKET_HEADROOM; rx_buf->len = efx->rx_dma_len; rx_buf->flags = 0; ++rx_queue->added_count; diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index b210e987a1db..94f94686cf7d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -365,9 +365,8 @@ struct dma_features { unsigned int arpoffsel; }; -/* GMAC TX FIFO is 8K, Rx FIFO is 16K */ -#define BUF_SIZE_16KiB 16384 -/* RX Buffer size must be < 8191 and multiple of 4/8/16 bytes */ +/* RX Buffer size must be multiple of 4/8/16 bytes */ +#define BUF_SIZE_16KiB 16368 #define BUF_SIZE_8KiB 8188 #define BUF_SIZE_4KiB 4096 #define BUF_SIZE_2KiB 2048 diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h index 3b6e559aa0b9..ef8a07c68ca7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h @@ -343,6 +343,8 @@ #define XGMAC_DMA_CH_RX_CONTROL(x) (0x00003108 + (0x80 * (x))) #define XGMAC_RxPBL GENMASK(21, 16) #define XGMAC_RxPBL_SHIFT 16 +#define XGMAC_RBSZ GENMASK(14, 1) +#define XGMAC_RBSZ_SHIFT 1 #define XGMAC_RXST BIT(0) #define XGMAC_DMA_CH_TxDESC_HADDR(x) (0x00003110 + (0x80 * (x))) #define XGMAC_DMA_CH_TxDESC_LADDR(x) (0x00003114 + (0x80 * (x))) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c index 22a7f0cc1b90..f3f08ccc379b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c @@ -482,7 +482,8 @@ static void dwxgmac2_set_bfsize(void __iomem *ioaddr, int bfsize, u32 chan) u32 value; value = readl(ioaddr + XGMAC_DMA_CH_RX_CONTROL(chan)); - value |= bfsize << 1; + value &= ~XGMAC_RBSZ; + value |= bfsize << XGMAC_RBSZ_SHIFT; writel(value, ioaddr + XGMAC_DMA_CH_RX_CONTROL(chan)); } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index bbc65bd332a8..6f51a265459d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -46,7 +46,7 @@ #include "dwxgmac2.h" #include "hwif.h" -#define STMMAC_ALIGN(x) __ALIGN_KERNEL(x, SMP_CACHE_BYTES) +#define STMMAC_ALIGN(x) ALIGN(ALIGN(x, SMP_CACHE_BYTES), 16) #define TSO_MAX_BUFF_SIZE (SZ_16K - 1) /* Module parameters */ @@ -1109,7 +1109,9 @@ static int stmmac_set_bfsize(int mtu, int bufsize) { int ret = bufsize; - if (mtu >= BUF_SIZE_4KiB) + if (mtu >= BUF_SIZE_8KiB) + ret = BUF_SIZE_16KiB; + else if (mtu >= BUF_SIZE_4KiB) ret = BUF_SIZE_8KiB; else if (mtu >= BUF_SIZE_2KiB) ret = BUF_SIZE_4KiB; @@ -1293,19 +1295,9 @@ static int init_dma_rx_desc_rings(struct net_device *dev, gfp_t flags) struct stmmac_priv *priv = netdev_priv(dev); u32 rx_count = priv->plat->rx_queues_to_use; int ret = -ENOMEM; - int bfsize = 0; int queue; int i; - bfsize = stmmac_set_16kib_bfsize(priv, dev->mtu); - if (bfsize < 0) - bfsize = 0; - - if (bfsize < BUF_SIZE_16KiB) - bfsize = stmmac_set_bfsize(dev->mtu, priv->dma_buf_sz); - - priv->dma_buf_sz = bfsize; - /* RX INITIALIZATION */ netif_dbg(priv, probe, priv->dev, "SKB addresses:\nskb\t\tskb data\tdma data\n"); @@ -1347,8 +1339,6 @@ static int init_dma_rx_desc_rings(struct net_device *dev, gfp_t flags) } } - buf_sz = bfsize; - return 0; err_init_rx_buffers: @@ -2658,6 +2648,7 @@ static void stmmac_hw_teardown(struct net_device *dev) static int stmmac_open(struct net_device *dev) { struct stmmac_priv *priv = netdev_priv(dev); + int bfsize = 0; u32 chan; int ret; @@ -2677,7 +2668,16 @@ static int stmmac_open(struct net_device *dev) memset(&priv->xstats, 0, sizeof(struct stmmac_extra_stats)); priv->xstats.threshold = tc; - priv->dma_buf_sz = STMMAC_ALIGN(buf_sz); + bfsize = stmmac_set_16kib_bfsize(priv, dev->mtu); + if (bfsize < 0) + bfsize = 0; + + if (bfsize < BUF_SIZE_16KiB) + bfsize = stmmac_set_bfsize(dev->mtu, priv->dma_buf_sz); + + priv->dma_buf_sz = bfsize; + buf_sz = bfsize; + priv->rx_copybreak = STMMAC_RX_COPYBREAK; ret = alloc_dma_desc_resources(priv); @@ -3053,8 +3053,6 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) tx_q->tx_count_frames = 0; stmmac_set_tx_ic(priv, desc); priv->xstats.tx_set_ic_bit++; - } else { - stmmac_tx_timer_arm(priv, queue); } /* We've used all descriptors we need for this skb, however, @@ -3125,6 +3123,7 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) tx_q->tx_tail_addr = tx_q->dma_tx_phy + (tx_q->cur_tx * sizeof(*desc)); stmmac_set_tx_tail_ptr(priv, priv->ioaddr, tx_q->tx_tail_addr, queue); + stmmac_tx_timer_arm(priv, queue); return NETDEV_TX_OK; @@ -3276,8 +3275,6 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) tx_q->tx_count_frames = 0; stmmac_set_tx_ic(priv, desc); priv->xstats.tx_set_ic_bit++; - } else { - stmmac_tx_timer_arm(priv, queue); } /* We've used all descriptors we need for this skb, however, @@ -3366,6 +3363,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) tx_q->tx_tail_addr = tx_q->dma_tx_phy + (tx_q->cur_tx * sizeof(*desc)); stmmac_set_tx_tail_ptr(priv, priv->ioaddr, tx_q->tx_tail_addr, queue); + stmmac_tx_timer_arm(priv, queue); return NETDEV_TX_OK; @@ -3646,8 +3644,9 @@ read_again: * feature is always disabled and packets need to be * stripped manually. */ - if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00) || - unlikely(status != llc_snap)) { + if (likely(!(status & rx_not_ls)) && + (likely(priv->synopsys_id >= DWMAC_CORE_4_00) || + unlikely(status != llc_snap))) { if (buf2_len) buf2_len -= ETH_FCS_LEN; else @@ -3829,12 +3828,24 @@ static void stmmac_set_rx_mode(struct net_device *dev) static int stmmac_change_mtu(struct net_device *dev, int new_mtu) { struct stmmac_priv *priv = netdev_priv(dev); + int txfifosz = priv->plat->tx_fifo_size; + + if (txfifosz == 0) + txfifosz = priv->dma_cap.tx_fifo_size; + + txfifosz /= priv->plat->tx_queues_to_use; if (netif_running(dev)) { netdev_err(priv->dev, "must be stopped to change its MTU\n"); return -EBUSY; } + new_mtu = STMMAC_ALIGN(new_mtu); + + /* If condition true, FIFO is too small or MTU too large */ + if ((txfifosz < new_mtu) || (new_mtu > BUF_SIZE_16KiB)) + return -EINVAL; + dev->mtu = new_mtu; netdev_update_features(dev); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index bedaff0c13bd..cc8d7e7bf9ac 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -320,7 +320,7 @@ out: static int stmmac_dt_phy(struct plat_stmmacenet_data *plat, struct device_node *np, struct device *dev) { - bool mdio = true; + bool mdio = false; static const struct of_device_id need_mdio_ids[] = { { .compatible = "snps,dwc-qos-ethernet-4.10" }, {}, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c index f3d8b9336b8e..13227909287c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c @@ -624,6 +624,8 @@ static int stmmac_test_mcfilt(struct stmmac_priv *priv) return -EOPNOTSUPP; if (netdev_uc_count(priv->dev) >= priv->hw->unicast_filter_entries) return -EOPNOTSUPP; + if (netdev_mc_count(priv->dev) >= priv->hw->multicast_filter_bins) + return -EOPNOTSUPP; while (--tries) { /* We only need to check the mc_addr for collisions */ @@ -666,6 +668,8 @@ static int stmmac_test_ucfilt(struct stmmac_priv *priv) if (stmmac_filter_check(priv)) return -EOPNOTSUPP; + if (netdev_uc_count(priv->dev) >= priv->hw->unicast_filter_entries) + return -EOPNOTSUPP; if (netdev_mc_count(priv->dev) >= priv->hw->multicast_filter_bins) return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig index a46f4189fde3..bf98e0fa7d8b 100644 --- a/drivers/net/ethernet/ti/Kconfig +++ b/drivers/net/ethernet/ti/Kconfig @@ -63,6 +63,7 @@ config TI_CPSW_SWITCHDEV tristate "TI CPSW Switch Support with switchdev" depends on ARCH_DAVINCI || ARCH_OMAP2PLUS || COMPILE_TEST depends on NET_SWITCHDEV + select PAGE_POOL select TI_DAVINCI_MDIO select MFD_SYSCON select REGMAP diff --git a/drivers/net/ethernet/ti/Makefile b/drivers/net/ethernet/ti/Makefile index d34df8e5cf94..ecf776ad8689 100644 --- a/drivers/net/ethernet/ti/Makefile +++ b/drivers/net/ethernet/ti/Makefile @@ -5,6 +5,7 @@ obj-$(CONFIG_TI_CPSW) += cpsw-common.o obj-$(CONFIG_TI_DAVINCI_EMAC) += cpsw-common.o +obj-$(CONFIG_TI_CPSW_SWITCHDEV) += cpsw-common.o obj-$(CONFIG_TLAN) += tlan.o obj-$(CONFIG_CPMAC) += cpmac.o diff --git a/drivers/net/ethernet/ti/davinci_cpdma.c b/drivers/net/ethernet/ti/davinci_cpdma.c index 37ba708ac781..6614fa3089b2 100644 --- a/drivers/net/ethernet/ti/davinci_cpdma.c +++ b/drivers/net/ethernet/ti/davinci_cpdma.c @@ -1018,7 +1018,6 @@ static int cpdma_chan_submit_si(struct submit_info *si) struct cpdma_chan *chan = si->chan; struct cpdma_ctlr *ctlr = chan->ctlr; int len = si->len; - int swlen = len; struct cpdma_desc __iomem *desc; dma_addr_t buffer; u32 mode; @@ -1046,7 +1045,6 @@ static int cpdma_chan_submit_si(struct submit_info *si) if (si->data_dma) { buffer = si->data_dma; dma_sync_single_for_device(ctlr->dev, buffer, len, chan->dir); - swlen |= CPDMA_DMA_EXT_MAP; } else { buffer = dma_map_single(ctlr->dev, si->data_virt, len, chan->dir); ret = dma_mapping_error(ctlr->dev, buffer); @@ -1065,7 +1063,8 @@ static int cpdma_chan_submit_si(struct submit_info *si) writel_relaxed(mode | len, &desc->hw_mode); writel_relaxed((uintptr_t)si->token, &desc->sw_token); writel_relaxed(buffer, &desc->sw_buffer); - writel_relaxed(swlen, &desc->sw_len); + writel_relaxed(si->data_dma ? len | CPDMA_DMA_EXT_MAP : len, + &desc->sw_len); desc_read(desc, sw_len); __cpdma_chan_submit(chan, desc); diff --git a/drivers/net/fjes/fjes_main.c b/drivers/net/fjes/fjes_main.c index b517c1af9de0..91a1059517f5 100644 --- a/drivers/net/fjes/fjes_main.c +++ b/drivers/net/fjes/fjes_main.c @@ -166,6 +166,9 @@ static int fjes_acpi_add(struct acpi_device *device) /* create platform_device */ plat_dev = platform_device_register_simple(DRV_NAME, 0, fjes_resource, ARRAY_SIZE(fjes_resource)); + if (IS_ERR(plat_dev)) + return PTR_ERR(plat_dev); + device->driver_data = plat_dev; return 0; diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index ecfe26215935..e5b7d6d2286e 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -38,7 +38,6 @@ struct pdp_ctx { struct hlist_node hlist_addr; union { - u64 tid; struct { u64 tid; u16 flow; @@ -641,9 +640,16 @@ static void gtp_link_setup(struct net_device *dev) } static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize); -static void gtp_hashtable_free(struct gtp_dev *gtp); static int gtp_encap_enable(struct gtp_dev *gtp, struct nlattr *data[]); +static void gtp_destructor(struct net_device *dev) +{ + struct gtp_dev *gtp = netdev_priv(dev); + + kfree(gtp->addr_hash); + kfree(gtp->tid_hash); +} + static int gtp_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) @@ -661,10 +667,13 @@ static int gtp_newlink(struct net *src_net, struct net_device *dev, if (err < 0) return err; - if (!data[IFLA_GTP_PDP_HASHSIZE]) + if (!data[IFLA_GTP_PDP_HASHSIZE]) { hashsize = 1024; - else + } else { hashsize = nla_get_u32(data[IFLA_GTP_PDP_HASHSIZE]); + if (!hashsize) + hashsize = 1024; + } err = gtp_hashtable_new(gtp, hashsize); if (err < 0) @@ -678,13 +687,15 @@ static int gtp_newlink(struct net *src_net, struct net_device *dev, gn = net_generic(dev_net(dev), gtp_net_id); list_add_rcu(>p->list, &gn->gtp_dev_list); + dev->priv_destructor = gtp_destructor; netdev_dbg(dev, "registered new GTP interface\n"); return 0; out_hashtable: - gtp_hashtable_free(gtp); + kfree(gtp->addr_hash); + kfree(gtp->tid_hash); out_encap: gtp_encap_disable(gtp); return err; @@ -693,8 +704,13 @@ out_encap: static void gtp_dellink(struct net_device *dev, struct list_head *head) { struct gtp_dev *gtp = netdev_priv(dev); + struct pdp_ctx *pctx; + int i; + + for (i = 0; i < gtp->hash_size; i++) + hlist_for_each_entry_rcu(pctx, >p->tid_hash[i], hlist_tid) + pdp_context_delete(pctx); - gtp_hashtable_free(gtp); list_del_rcu(>p->list); unregister_netdevice_queue(dev, head); } @@ -772,20 +788,6 @@ err1: return -ENOMEM; } -static void gtp_hashtable_free(struct gtp_dev *gtp) -{ - struct pdp_ctx *pctx; - int i; - - for (i = 0; i < gtp->hash_size; i++) - hlist_for_each_entry_rcu(pctx, >p->tid_hash[i], hlist_tid) - pdp_context_delete(pctx); - - synchronize_rcu(); - kfree(gtp->addr_hash); - kfree(gtp->tid_hash); -} - static struct sock *gtp_encap_enable_socket(int fd, int type, struct gtp_dev *gtp) { @@ -926,24 +928,31 @@ static void ipv4_pdp_fill(struct pdp_ctx *pctx, struct genl_info *info) } } -static int ipv4_pdp_add(struct gtp_dev *gtp, struct sock *sk, - struct genl_info *info) +static int gtp_pdp_add(struct gtp_dev *gtp, struct sock *sk, + struct genl_info *info) { + struct pdp_ctx *pctx, *pctx_tid = NULL; struct net_device *dev = gtp->dev; u32 hash_ms, hash_tid = 0; - struct pdp_ctx *pctx; + unsigned int version; bool found = false; __be32 ms_addr; ms_addr = nla_get_be32(info->attrs[GTPA_MS_ADDRESS]); hash_ms = ipv4_hashfn(ms_addr) % gtp->hash_size; + version = nla_get_u32(info->attrs[GTPA_VERSION]); - hlist_for_each_entry_rcu(pctx, >p->addr_hash[hash_ms], hlist_addr) { - if (pctx->ms_addr_ip4.s_addr == ms_addr) { - found = true; - break; - } - } + pctx = ipv4_pdp_find(gtp, ms_addr); + if (pctx) + found = true; + if (version == GTP_V0) + pctx_tid = gtp0_pdp_find(gtp, + nla_get_u64(info->attrs[GTPA_TID])); + else if (version == GTP_V1) + pctx_tid = gtp1_pdp_find(gtp, + nla_get_u32(info->attrs[GTPA_I_TEI])); + if (pctx_tid) + found = true; if (found) { if (info->nlhdr->nlmsg_flags & NLM_F_EXCL) @@ -951,6 +960,11 @@ static int ipv4_pdp_add(struct gtp_dev *gtp, struct sock *sk, if (info->nlhdr->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; + if (pctx && pctx_tid) + return -EEXIST; + if (!pctx) + pctx = pctx_tid; + ipv4_pdp_fill(pctx, info); if (pctx->gtp_version == GTP_V0) @@ -1074,7 +1088,7 @@ static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info) goto out_unlock; } - err = ipv4_pdp_add(gtp, sk, info); + err = gtp_pdp_add(gtp, sk, info); out_unlock: rcu_read_unlock(); @@ -1232,43 +1246,46 @@ static int gtp_genl_dump_pdp(struct sk_buff *skb, struct netlink_callback *cb) { struct gtp_dev *last_gtp = (struct gtp_dev *)cb->args[2], *gtp; + int i, j, bucket = cb->args[0], skip = cb->args[1]; struct net *net = sock_net(skb->sk); - struct gtp_net *gn = net_generic(net, gtp_net_id); - unsigned long tid = cb->args[1]; - int i, k = cb->args[0], ret; struct pdp_ctx *pctx; + struct gtp_net *gn; + + gn = net_generic(net, gtp_net_id); if (cb->args[4]) return 0; + rcu_read_lock(); list_for_each_entry_rcu(gtp, &gn->gtp_dev_list, list) { if (last_gtp && last_gtp != gtp) continue; else last_gtp = NULL; - for (i = k; i < gtp->hash_size; i++) { - hlist_for_each_entry_rcu(pctx, >p->tid_hash[i], hlist_tid) { - if (tid && tid != pctx->u.tid) - continue; - else - tid = 0; - - ret = gtp_genl_fill_info(skb, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - cb->nlh->nlmsg_type, pctx); - if (ret < 0) { + for (i = bucket; i < gtp->hash_size; i++) { + j = 0; + hlist_for_each_entry_rcu(pctx, >p->tid_hash[i], + hlist_tid) { + if (j >= skip && + gtp_genl_fill_info(skb, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + cb->nlh->nlmsg_type, pctx)) { cb->args[0] = i; - cb->args[1] = pctx->u.tid; + cb->args[1] = j; cb->args[2] = (unsigned long)gtp; goto out; } + j++; } + skip = 0; } + bucket = 0; } cb->args[4] = 1; out: + rcu_read_unlock(); return skb->len; } diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c index 23281aeeb222..71d6629e65c9 100644 --- a/drivers/net/hamradio/6pack.c +++ b/drivers/net/hamradio/6pack.c @@ -654,10 +654,10 @@ static void sixpack_close(struct tty_struct *tty) { struct sixpack *sp; - write_lock_bh(&disc_data_lock); + write_lock_irq(&disc_data_lock); sp = tty->disc_data; tty->disc_data = NULL; - write_unlock_bh(&disc_data_lock); + write_unlock_irq(&disc_data_lock); if (!sp) return; diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c index c5bfa19ddb93..deef14215110 100644 --- a/drivers/net/hamradio/mkiss.c +++ b/drivers/net/hamradio/mkiss.c @@ -773,10 +773,10 @@ static void mkiss_close(struct tty_struct *tty) { struct mkiss *ax; - write_lock_bh(&disc_data_lock); + write_lock_irq(&disc_data_lock); ax = tty->disc_data; tty->disc_data = NULL; - write_unlock_bh(&disc_data_lock); + write_unlock_irq(&disc_data_lock); if (!ax) return; diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index 9caa876ce6e8..dc44819946e6 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -169,7 +169,6 @@ struct rndis_device { u8 hw_mac_adr[ETH_ALEN]; u8 rss_key[NETVSC_HASH_KEYLEN]; - u16 rx_table[ITAB_NUM]; }; @@ -940,6 +939,8 @@ struct net_device_context { u32 tx_table[VRSS_SEND_TAB_SIZE]; + u16 rx_table[ITAB_NUM]; + /* Ethtool settings */ u8 duplex; u32 speed; diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 02e66473f2ed..f3f9eb8a402a 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -1662,7 +1662,7 @@ static int netvsc_get_rxfh(struct net_device *dev, u32 *indir, u8 *key, rndis_dev = ndev->extension; if (indir) { for (i = 0; i < ITAB_NUM; i++) - indir[i] = rndis_dev->rx_table[i]; + indir[i] = ndc->rx_table[i]; } if (key) @@ -1692,7 +1692,7 @@ static int netvsc_set_rxfh(struct net_device *dev, const u32 *indir, return -EINVAL; for (i = 0; i < ITAB_NUM; i++) - rndis_dev->rx_table[i] = indir[i]; + ndc->rx_table[i] = indir[i]; } if (!key) { diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index 206b4e77eaf0..857c4bea451c 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -773,6 +773,7 @@ static int rndis_set_rss_param_msg(struct rndis_device *rdev, const u8 *rss_key, u16 flag) { struct net_device *ndev = rdev->ndev; + struct net_device_context *ndc = netdev_priv(ndev); struct rndis_request *request; struct rndis_set_request *set; struct rndis_set_complete *set_complete; @@ -812,7 +813,7 @@ static int rndis_set_rss_param_msg(struct rndis_device *rdev, /* Set indirection table entries */ itab = (u32 *)(rssp + 1); for (i = 0; i < ITAB_NUM; i++) - itab[i] = rdev->rx_table[i]; + itab[i] = ndc->rx_table[i]; /* Set hask key values */ keyp = (u8 *)((unsigned long)rssp + rssp->hashkey_offset); @@ -1171,6 +1172,9 @@ int rndis_set_subchannel(struct net_device *ndev, wait_event(nvdev->subchan_open, atomic_read(&nvdev->open_chn) == nvdev->num_chn); + for (i = 0; i < VRSS_SEND_TAB_SIZE; i++) + ndev_ctx->tx_table[i] = i % nvdev->num_chn; + /* ignore failures from setting rss parameters, still have channels */ if (dev_info) rndis_filter_set_rss_param(rdev, dev_info->rss_key); @@ -1180,9 +1184,6 @@ int rndis_set_subchannel(struct net_device *ndev, netif_set_real_num_tx_queues(ndev, nvdev->num_chn); netif_set_real_num_rx_queues(ndev, nvdev->num_chn); - for (i = 0; i < VRSS_SEND_TAB_SIZE; i++) - ndev_ctx->tx_table[i] = i % nvdev->num_chn; - return 0; } @@ -1312,6 +1313,7 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev, struct netvsc_device_info *device_info) { struct net_device *net = hv_get_drvdata(dev); + struct net_device_context *ndc = netdev_priv(net); struct netvsc_device *net_device; struct rndis_device *rndis_device; struct ndis_recv_scale_cap rsscap; @@ -1398,9 +1400,11 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev, /* We will use the given number of channels if available. */ net_device->num_chn = min(net_device->max_chn, device_info->num_chn); - for (i = 0; i < ITAB_NUM; i++) - rndis_device->rx_table[i] = ethtool_rxfh_indir_default( + if (!netif_is_rxfh_configured(net)) { + for (i = 0; i < ITAB_NUM; i++) + ndc->rx_table[i] = ethtool_rxfh_indir_default( i, net_device->num_chn); + } atomic_set(&net_device->open_chn, 1); vmbus_set_sc_create_callback(dev->channel, netvsc_sc_open); diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 0887ed2bb050..b13c52873ef5 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -553,7 +553,7 @@ static const struct device_type mdio_bus_phy_type = { .pm = MDIO_BUS_PHY_PM_OPS, }; -static int phy_request_driver_module(struct phy_device *dev, int phy_id) +static int phy_request_driver_module(struct phy_device *dev, u32 phy_id) { int ret; @@ -565,15 +565,15 @@ static int phy_request_driver_module(struct phy_device *dev, int phy_id) * then modprobe isn't available. */ if (IS_ENABLED(CONFIG_MODULES) && ret < 0 && ret != -ENOENT) { - phydev_err(dev, "error %d loading PHY driver module for ID 0x%08x\n", - ret, phy_id); + phydev_err(dev, "error %d loading PHY driver module for ID 0x%08lx\n", + ret, (unsigned long)phy_id); return ret; } return 0; } -struct phy_device *phy_device_create(struct mii_bus *bus, int addr, int phy_id, +struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id, bool is_c45, struct phy_c45_device_ids *c45_ids) { diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 9a616d6bc4eb..1585eebb73fe 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -442,8 +442,7 @@ static void phylink_mac_link_up(struct phylink *pl, pl->cur_interface = link_state.interface; pl->ops->mac_link_up(pl->config, pl->link_an_mode, - pl->phy_state.interface, - pl->phydev); + pl->cur_interface, pl->phydev); if (ndev) netif_carrier_on(ndev); diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index cf1f3f0a4b9b..f940dc6485e5 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -511,7 +511,7 @@ static int lan78xx_read_stats(struct lan78xx_net *dev, } } else { netdev_warn(dev->net, - "Failed to read stat ret = 0x%x", ret); + "Failed to read stat ret = %d", ret); } kfree(stats); @@ -1808,6 +1808,7 @@ static int lan78xx_mdio_init(struct lan78xx_net *dev) dev->mdiobus->read = lan78xx_mdiobus_read; dev->mdiobus->write = lan78xx_mdiobus_write; dev->mdiobus->name = "lan78xx-mdiobus"; + dev->mdiobus->parent = &dev->udev->dev; snprintf(dev->mdiobus->id, MII_BUS_ID_SIZE, "usb-%03d:%03d", dev->udev->bus->busnum, dev->udev->devnum); diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c index 83cc8778ca1e..978f0037ed52 100644 --- a/drivers/net/wireless/ath/ath10k/mac.c +++ b/drivers/net/wireless/ath/ath10k/mac.c @@ -8958,6 +8958,7 @@ int ath10k_mac_register(struct ath10k *ar) wiphy_ext_feature_set(ar->hw->wiphy, NL80211_EXT_FEATURE_VHT_IBSS); wiphy_ext_feature_set(ar->hw->wiphy, NL80211_EXT_FEATURE_SET_SCAN_DWELL); + wiphy_ext_feature_set(ar->hw->wiphy, NL80211_EXT_FEATURE_AQL); if (test_bit(WMI_SERVICE_TX_DATA_ACK_RSSI, ar->wmi.svc_map) || test_bit(WMI_SERVICE_HTT_MGMT_TX_COMP_VALID_FLAGS, ar->wmi.svc_map)) diff --git a/drivers/net/wireless/ath/ath9k/ath9k_pci_owl_loader.c b/drivers/net/wireless/ath/ath9k/ath9k_pci_owl_loader.c index 956fa7828d0c..56d1a7764b9f 100644 --- a/drivers/net/wireless/ath/ath9k/ath9k_pci_owl_loader.c +++ b/drivers/net/wireless/ath/ath9k/ath9k_pci_owl_loader.c @@ -83,7 +83,7 @@ static int ath9k_pci_fixup(struct pci_dev *pdev, const u16 *cal_data, val = swahb32(val); } - __raw_writel(val, mem + reg); + iowrite32(val, mem + reg); usleep_range(100, 120); } diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index 040cec17d3ad..b0b7eca1754e 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -1111,18 +1111,18 @@ static int iwl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* same thing for QuZ... */ if (iwl_trans->hw_rev == CSR_HW_REV_TYPE_QUZ) { - if (iwl_trans->cfg == &iwl_ax101_cfg_qu_hr) - iwl_trans->cfg = &iwl_ax101_cfg_quz_hr; - else if (iwl_trans->cfg == &iwl_ax201_cfg_qu_hr) - iwl_trans->cfg = &iwl_ax201_cfg_quz_hr; - else if (iwl_trans->cfg == &iwl9461_2ac_cfg_qu_b0_jf_b0) - iwl_trans->cfg = &iwl9461_2ac_cfg_quz_a0_jf_b0_soc; - else if (iwl_trans->cfg == &iwl9462_2ac_cfg_qu_b0_jf_b0) - iwl_trans->cfg = &iwl9462_2ac_cfg_quz_a0_jf_b0_soc; - else if (iwl_trans->cfg == &iwl9560_2ac_cfg_qu_b0_jf_b0) - iwl_trans->cfg = &iwl9560_2ac_cfg_quz_a0_jf_b0_soc; - else if (iwl_trans->cfg == &iwl9560_2ac_160_cfg_qu_b0_jf_b0) - iwl_trans->cfg = &iwl9560_2ac_160_cfg_quz_a0_jf_b0_soc; + if (cfg == &iwl_ax101_cfg_qu_hr) + cfg = &iwl_ax101_cfg_quz_hr; + else if (cfg == &iwl_ax201_cfg_qu_hr) + cfg = &iwl_ax201_cfg_quz_hr; + else if (cfg == &iwl9461_2ac_cfg_qu_b0_jf_b0) + cfg = &iwl9461_2ac_cfg_quz_a0_jf_b0_soc; + else if (cfg == &iwl9462_2ac_cfg_qu_b0_jf_b0) + cfg = &iwl9462_2ac_cfg_quz_a0_jf_b0_soc; + else if (cfg == &iwl9560_2ac_cfg_qu_b0_jf_b0) + cfg = &iwl9560_2ac_cfg_quz_a0_jf_b0_soc; + else if (cfg == &iwl9560_2ac_160_cfg_qu_b0_jf_b0) + cfg = &iwl9560_2ac_160_cfg_quz_a0_jf_b0_soc; } #endif diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c index 0252716c0b24..0d8b2a8ffa5d 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c @@ -57,24 +57,6 @@ #include "internal.h" #include "fw/dbg.h" -static int iwl_pcie_gen2_force_power_gating(struct iwl_trans *trans) -{ - iwl_set_bits_prph(trans, HPM_HIPM_GEN_CFG, - HPM_HIPM_GEN_CFG_CR_FORCE_ACTIVE); - udelay(20); - iwl_set_bits_prph(trans, HPM_HIPM_GEN_CFG, - HPM_HIPM_GEN_CFG_CR_PG_EN | - HPM_HIPM_GEN_CFG_CR_SLP_EN); - udelay(20); - iwl_clear_bits_prph(trans, HPM_HIPM_GEN_CFG, - HPM_HIPM_GEN_CFG_CR_FORCE_ACTIVE); - - iwl_trans_sw_reset(trans); - iwl_clear_bit(trans, CSR_GP_CNTRL, CSR_GP_CNTRL_REG_FLAG_INIT_DONE); - - return 0; -} - /* * Start up NIC's basic functionality after it has been reset * (e.g. after platform boot, or shutdown via iwl_pcie_apm_stop()) @@ -110,13 +92,6 @@ int iwl_pcie_gen2_apm_init(struct iwl_trans *trans) iwl_pcie_apm_config(trans); - if (trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_22000 && - trans->cfg->integrated) { - ret = iwl_pcie_gen2_force_power_gating(trans); - if (ret) - return ret; - } - ret = iwl_finish_nic_init(trans, trans->trans_cfg); if (ret) return ret; diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c index af9bc6b64542..a0677131634d 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c @@ -1783,6 +1783,29 @@ static int iwl_trans_pcie_clear_persistence_bit(struct iwl_trans *trans) return 0; } +static int iwl_pcie_gen2_force_power_gating(struct iwl_trans *trans) +{ + int ret; + + ret = iwl_finish_nic_init(trans, trans->trans_cfg); + if (ret < 0) + return ret; + + iwl_set_bits_prph(trans, HPM_HIPM_GEN_CFG, + HPM_HIPM_GEN_CFG_CR_FORCE_ACTIVE); + udelay(20); + iwl_set_bits_prph(trans, HPM_HIPM_GEN_CFG, + HPM_HIPM_GEN_CFG_CR_PG_EN | + HPM_HIPM_GEN_CFG_CR_SLP_EN); + udelay(20); + iwl_clear_bits_prph(trans, HPM_HIPM_GEN_CFG, + HPM_HIPM_GEN_CFG_CR_FORCE_ACTIVE); + + iwl_trans_pcie_sw_reset(trans); + + return 0; +} + static int _iwl_trans_pcie_start_hw(struct iwl_trans *trans) { struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); @@ -1802,6 +1825,13 @@ static int _iwl_trans_pcie_start_hw(struct iwl_trans *trans) iwl_trans_pcie_sw_reset(trans); + if (trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_22000 && + trans->cfg->integrated) { + err = iwl_pcie_gen2_force_power_gating(trans); + if (err) + return err; + } + err = iwl_pcie_apm_init(trans); if (err) return err; diff --git a/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c b/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c index 74e50566db1f..6dd835f1efc2 100644 --- a/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c +++ b/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c @@ -229,6 +229,14 @@ static int mwifiex_process_country_ie(struct mwifiex_private *priv, "11D: skip setting domain info in FW\n"); return 0; } + + if (country_ie_len > + (IEEE80211_COUNTRY_STRING_LEN + MWIFIEX_MAX_TRIPLET_802_11D)) { + mwifiex_dbg(priv->adapter, ERROR, + "11D: country_ie_len overflow!, deauth AP\n"); + return -EINVAL; + } + memcpy(priv->adapter->country_code, &country_ie[2], 2); domain_info->country_code[0] = country_ie[2]; @@ -272,8 +280,9 @@ int mwifiex_bss_start(struct mwifiex_private *priv, struct cfg80211_bss *bss, priv->scan_block = false; if (bss) { - if (adapter->region_code == 0x00) - mwifiex_process_country_ie(priv, bss); + if (adapter->region_code == 0x00 && + mwifiex_process_country_ie(priv, bss)) + return -EINVAL; /* Allocate and fill new bss descriptor */ bss_desc = kzalloc(sizeof(struct mwifiex_bssdescriptor), diff --git a/drivers/net/wireless/marvell/mwifiex/tdls.c b/drivers/net/wireless/marvell/mwifiex/tdls.c index 09313047beed..7caf1d26124a 100644 --- a/drivers/net/wireless/marvell/mwifiex/tdls.c +++ b/drivers/net/wireless/marvell/mwifiex/tdls.c @@ -953,59 +953,117 @@ void mwifiex_process_tdls_action_frame(struct mwifiex_private *priv, switch (*pos) { case WLAN_EID_SUPP_RATES: + if (pos[1] > 32) + return; sta_ptr->tdls_cap.rates_len = pos[1]; for (i = 0; i < pos[1]; i++) sta_ptr->tdls_cap.rates[i] = pos[i + 2]; break; case WLAN_EID_EXT_SUPP_RATES: + if (pos[1] > 32) + return; basic = sta_ptr->tdls_cap.rates_len; + if (pos[1] > 32 - basic) + return; for (i = 0; i < pos[1]; i++) sta_ptr->tdls_cap.rates[basic + i] = pos[i + 2]; sta_ptr->tdls_cap.rates_len += pos[1]; break; case WLAN_EID_HT_CAPABILITY: - memcpy((u8 *)&sta_ptr->tdls_cap.ht_capb, pos, + if (pos > end - sizeof(struct ieee80211_ht_cap) - 2) + return; + if (pos[1] != sizeof(struct ieee80211_ht_cap)) + return; + /* copy the ie's value into ht_capb*/ + memcpy((u8 *)&sta_ptr->tdls_cap.ht_capb, pos + 2, sizeof(struct ieee80211_ht_cap)); sta_ptr->is_11n_enabled = 1; break; case WLAN_EID_HT_OPERATION: - memcpy(&sta_ptr->tdls_cap.ht_oper, pos, + if (pos > end - + sizeof(struct ieee80211_ht_operation) - 2) + return; + if (pos[1] != sizeof(struct ieee80211_ht_operation)) + return; + /* copy the ie's value into ht_oper*/ + memcpy(&sta_ptr->tdls_cap.ht_oper, pos + 2, sizeof(struct ieee80211_ht_operation)); break; case WLAN_EID_BSS_COEX_2040: + if (pos > end - 3) + return; + if (pos[1] != 1) + return; sta_ptr->tdls_cap.coex_2040 = pos[2]; break; case WLAN_EID_EXT_CAPABILITY: + if (pos > end - sizeof(struct ieee_types_header)) + return; + if (pos[1] < sizeof(struct ieee_types_header)) + return; + if (pos[1] > 8) + return; memcpy((u8 *)&sta_ptr->tdls_cap.extcap, pos, sizeof(struct ieee_types_header) + min_t(u8, pos[1], 8)); break; case WLAN_EID_RSN: + if (pos > end - sizeof(struct ieee_types_header)) + return; + if (pos[1] < sizeof(struct ieee_types_header)) + return; + if (pos[1] > IEEE_MAX_IE_SIZE - + sizeof(struct ieee_types_header)) + return; memcpy((u8 *)&sta_ptr->tdls_cap.rsn_ie, pos, sizeof(struct ieee_types_header) + min_t(u8, pos[1], IEEE_MAX_IE_SIZE - sizeof(struct ieee_types_header))); break; case WLAN_EID_QOS_CAPA: + if (pos > end - 3) + return; + if (pos[1] != 1) + return; sta_ptr->tdls_cap.qos_info = pos[2]; break; case WLAN_EID_VHT_OPERATION: - if (priv->adapter->is_hw_11ac_capable) - memcpy(&sta_ptr->tdls_cap.vhtoper, pos, + if (priv->adapter->is_hw_11ac_capable) { + if (pos > end - + sizeof(struct ieee80211_vht_operation) - 2) + return; + if (pos[1] != + sizeof(struct ieee80211_vht_operation)) + return; + /* copy the ie's value into vhtoper*/ + memcpy(&sta_ptr->tdls_cap.vhtoper, pos + 2, sizeof(struct ieee80211_vht_operation)); + } break; case WLAN_EID_VHT_CAPABILITY: if (priv->adapter->is_hw_11ac_capable) { - memcpy((u8 *)&sta_ptr->tdls_cap.vhtcap, pos, + if (pos > end - + sizeof(struct ieee80211_vht_cap) - 2) + return; + if (pos[1] != sizeof(struct ieee80211_vht_cap)) + return; + /* copy the ie's value into vhtcap*/ + memcpy((u8 *)&sta_ptr->tdls_cap.vhtcap, pos + 2, sizeof(struct ieee80211_vht_cap)); sta_ptr->is_11ac_enabled = 1; } break; case WLAN_EID_AID: - if (priv->adapter->is_hw_11ac_capable) + if (priv->adapter->is_hw_11ac_capable) { + if (pos > end - 4) + return; + if (pos[1] != 2) + return; sta_ptr->tdls_cap.aid = get_unaligned_le16((pos + 2)); + } + break; default: break; } diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c index a03e2d01fba7..d1405528b504 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c @@ -342,8 +342,11 @@ int mt76x0_eeprom_init(struct mt76x02_dev *dev) dev_info(dev->mt76.dev, "EEPROM ver:%02hhx fae:%02hhx\n", version, fae); - mt76x02_mac_setaddr(dev, dev->mt76.eeprom.data + MT_EE_MAC_ADDR); + memcpy(dev->mt76.macaddr, (u8 *)dev->mt76.eeprom.data + MT_EE_MAC_ADDR, + ETH_ALEN); mt76_eeprom_override(&dev->mt76); + mt76x02_mac_setaddr(dev, dev->mt76.macaddr); + mt76x0_set_chip_cap(dev); mt76x0_set_freq_offset(dev); mt76x0_set_temp_offset(dev); diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index 68dd7bb07ca6..f15ba3de6195 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -628,18 +628,6 @@ err: static void xenvif_disconnect_queue(struct xenvif_queue *queue) { - if (queue->tx_irq) { - unbind_from_irqhandler(queue->tx_irq, queue); - if (queue->tx_irq == queue->rx_irq) - queue->rx_irq = 0; - queue->tx_irq = 0; - } - - if (queue->rx_irq) { - unbind_from_irqhandler(queue->rx_irq, queue); - queue->rx_irq = 0; - } - if (queue->task) { kthread_stop(queue->task); queue->task = NULL; @@ -655,6 +643,18 @@ static void xenvif_disconnect_queue(struct xenvif_queue *queue) queue->napi.poll = NULL; } + if (queue->tx_irq) { + unbind_from_irqhandler(queue->tx_irq, queue); + if (queue->tx_irq == queue->rx_irq) + queue->rx_irq = 0; + queue->tx_irq = 0; + } + + if (queue->rx_irq) { + unbind_from_irqhandler(queue->rx_irq, queue); + queue->rx_irq = 0; + } + xenvif_unmap_frontend_data_rings(queue); } diff --git a/drivers/nfc/nxp-nci/i2c.c b/drivers/nfc/nxp-nci/i2c.c index 4d1909aecd6c..9f60e4dc5a90 100644 --- a/drivers/nfc/nxp-nci/i2c.c +++ b/drivers/nfc/nxp-nci/i2c.c @@ -278,7 +278,7 @@ static int nxp_nci_i2c_probe(struct i2c_client *client, r = devm_acpi_dev_add_driver_gpios(dev, acpi_nxp_nci_gpios); if (r) - return r; + dev_dbg(dev, "Unable to add GPIO mapping table\n"); phy->gpiod_en = devm_gpiod_get(dev, "enable", GPIOD_OUT_LOW); if (IS_ERR(phy->gpiod_en)) { diff --git a/drivers/nfc/s3fwrn5/firmware.c b/drivers/nfc/s3fwrn5/firmware.c index be110d9cef02..de613c623a2c 100644 --- a/drivers/nfc/s3fwrn5/firmware.c +++ b/drivers/nfc/s3fwrn5/firmware.c @@ -507,7 +507,10 @@ int s3fwrn5_fw_recv_frame(struct nci_dev *ndev, struct sk_buff *skb) struct s3fwrn5_info *info = nci_get_drvdata(ndev); struct s3fwrn5_fw_info *fw_info = &info->fw_info; - BUG_ON(fw_info->rsp); + if (WARN_ON(fw_info->rsp)) { + kfree_skb(skb); + return -EINVAL; + } fw_info->rsp = skb; diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c index c6b87ce2b0cc..fc757ef6eadc 100644 --- a/drivers/of/of_mdio.c +++ b/drivers/of/of_mdio.c @@ -162,7 +162,7 @@ static const struct of_device_id whitelist_phys[] = { * A device which is not a phy is expected to have a compatible string * indicating what sort of device it is. */ -static bool of_mdiobus_child_is_phy(struct device_node *child) +bool of_mdiobus_child_is_phy(struct device_node *child) { u32 phy_id; @@ -187,6 +187,7 @@ static bool of_mdiobus_child_is_phy(struct device_node *child) return false; } +EXPORT_SYMBOL(of_mdiobus_child_is_phy); /** * of_mdiobus_register - Register mii_bus and create PHYs from the device tree diff --git a/drivers/perf/arm_smmuv3_pmu.c b/drivers/perf/arm_smmuv3_pmu.c index 773128f411f1..d704eccc548f 100644 --- a/drivers/perf/arm_smmuv3_pmu.c +++ b/drivers/perf/arm_smmuv3_pmu.c @@ -814,7 +814,7 @@ static int smmu_pmu_probe(struct platform_device *pdev) if (err) { dev_err(dev, "Error %d registering hotplug, PMU @%pa\n", err, &res_0->start); - goto out_cpuhp_err; + return err; } err = perf_pmu_register(&smmu_pmu->pmu, name, -1); @@ -833,8 +833,6 @@ static int smmu_pmu_probe(struct platform_device *pdev) out_unregister: cpuhp_state_remove_instance_nocalls(cpuhp_state_num, &smmu_pmu->node); -out_cpuhp_err: - put_cpu(); return err; } diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig index 3bfbf2ff6e2b..df0ef69dd474 100644 --- a/drivers/pinctrl/Kconfig +++ b/drivers/pinctrl/Kconfig @@ -422,6 +422,7 @@ config PINCTRL_TB10X config PINCTRL_EQUILIBRIUM tristate "Generic pinctrl and GPIO driver for Intel Lightning Mountain SoC" + depends on OF && HAS_IOMEM select PINMUX select PINCONF select GPIOLIB diff --git a/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c b/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c index c6800d220920..bb07024d22ed 100644 --- a/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c +++ b/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c @@ -1088,60 +1088,52 @@ SSSF_PIN_DECL(AF15, GPIOV7, LPCSMI, SIG_DESC_SET(SCU434, 15)); #define AB7 176 SIG_EXPR_LIST_DECL_SESG(AB7, LAD0, LPC, SIG_DESC_SET(SCU434, 16), - SIG_DESC_CLEAR(SCU510, 6)); -SIG_EXPR_LIST_DECL_SESG(AB7, ESPID0, ESPI, SIG_DESC_SET(SCU434, 16), SIG_DESC_SET(SCU510, 6)); +SIG_EXPR_LIST_DECL_SESG(AB7, ESPID0, ESPI, SIG_DESC_SET(SCU434, 16)); PIN_DECL_2(AB7, GPIOW0, LAD0, ESPID0); #define AB8 177 SIG_EXPR_LIST_DECL_SESG(AB8, LAD1, LPC, SIG_DESC_SET(SCU434, 17), - SIG_DESC_CLEAR(SCU510, 6)); -SIG_EXPR_LIST_DECL_SESG(AB8, ESPID1, ESPI, SIG_DESC_SET(SCU434, 17), SIG_DESC_SET(SCU510, 6)); +SIG_EXPR_LIST_DECL_SESG(AB8, ESPID1, ESPI, SIG_DESC_SET(SCU434, 17)); PIN_DECL_2(AB8, GPIOW1, LAD1, ESPID1); #define AC8 178 SIG_EXPR_LIST_DECL_SESG(AC8, LAD2, LPC, SIG_DESC_SET(SCU434, 18), - SIG_DESC_CLEAR(SCU510, 6)); -SIG_EXPR_LIST_DECL_SESG(AC8, ESPID2, ESPI, SIG_DESC_SET(SCU434, 18), SIG_DESC_SET(SCU510, 6)); +SIG_EXPR_LIST_DECL_SESG(AC8, ESPID2, ESPI, SIG_DESC_SET(SCU434, 18)); PIN_DECL_2(AC8, GPIOW2, LAD2, ESPID2); #define AC7 179 SIG_EXPR_LIST_DECL_SESG(AC7, LAD3, LPC, SIG_DESC_SET(SCU434, 19), - SIG_DESC_CLEAR(SCU510, 6)); -SIG_EXPR_LIST_DECL_SESG(AC7, ESPID3, ESPI, SIG_DESC_SET(SCU434, 19), SIG_DESC_SET(SCU510, 6)); +SIG_EXPR_LIST_DECL_SESG(AC7, ESPID3, ESPI, SIG_DESC_SET(SCU434, 19)); PIN_DECL_2(AC7, GPIOW3, LAD3, ESPID3); #define AE7 180 SIG_EXPR_LIST_DECL_SESG(AE7, LCLK, LPC, SIG_DESC_SET(SCU434, 20), - SIG_DESC_CLEAR(SCU510, 6)); -SIG_EXPR_LIST_DECL_SESG(AE7, ESPICK, ESPI, SIG_DESC_SET(SCU434, 20), SIG_DESC_SET(SCU510, 6)); +SIG_EXPR_LIST_DECL_SESG(AE7, ESPICK, ESPI, SIG_DESC_SET(SCU434, 20)); PIN_DECL_2(AE7, GPIOW4, LCLK, ESPICK); #define AF7 181 SIG_EXPR_LIST_DECL_SESG(AF7, LFRAME, LPC, SIG_DESC_SET(SCU434, 21), - SIG_DESC_CLEAR(SCU510, 6)); -SIG_EXPR_LIST_DECL_SESG(AF7, ESPICS, ESPI, SIG_DESC_SET(SCU434, 21), SIG_DESC_SET(SCU510, 6)); +SIG_EXPR_LIST_DECL_SESG(AF7, ESPICS, ESPI, SIG_DESC_SET(SCU434, 21)); PIN_DECL_2(AF7, GPIOW5, LFRAME, ESPICS); #define AD7 182 SIG_EXPR_LIST_DECL_SESG(AD7, LSIRQ, LSIRQ, SIG_DESC_SET(SCU434, 22), - SIG_DESC_CLEAR(SCU510, 6)); -SIG_EXPR_LIST_DECL_SESG(AD7, ESPIALT, ESPIALT, SIG_DESC_SET(SCU434, 22), SIG_DESC_SET(SCU510, 6)); +SIG_EXPR_LIST_DECL_SESG(AD7, ESPIALT, ESPIALT, SIG_DESC_SET(SCU434, 22)); PIN_DECL_2(AD7, GPIOW6, LSIRQ, ESPIALT); FUNC_GROUP_DECL(LSIRQ, AD7); FUNC_GROUP_DECL(ESPIALT, AD7); #define AD8 183 SIG_EXPR_LIST_DECL_SESG(AD8, LPCRST, LPC, SIG_DESC_SET(SCU434, 23), - SIG_DESC_CLEAR(SCU510, 6)); -SIG_EXPR_LIST_DECL_SESG(AD8, ESPIRST, ESPI, SIG_DESC_SET(SCU434, 23), SIG_DESC_SET(SCU510, 6)); +SIG_EXPR_LIST_DECL_SESG(AD8, ESPIRST, ESPI, SIG_DESC_SET(SCU434, 23)); PIN_DECL_2(AD8, GPIOW7, LPCRST, ESPIRST); FUNC_GROUP_DECL(LPC, AB7, AB8, AC8, AC7, AE7, AF7, AD8); diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c index 9ffb22211d2b..55141d5de29e 100644 --- a/drivers/pinctrl/intel/pinctrl-baytrail.c +++ b/drivers/pinctrl/intel/pinctrl-baytrail.c @@ -110,7 +110,6 @@ struct byt_gpio { struct platform_device *pdev; struct pinctrl_dev *pctl_dev; struct pinctrl_desc pctl_desc; - raw_spinlock_t lock; const struct intel_pinctrl_soc_data *soc_data; struct intel_community *communities_copy; struct byt_gpio_pin_context *saved_context; @@ -494,34 +493,34 @@ static const struct intel_pinctrl_soc_data byt_sus_soc_data = { }; static const struct pinctrl_pin_desc byt_ncore_pins[] = { - PINCTRL_PIN(0, "GPIO_NCORE0"), - PINCTRL_PIN(1, "GPIO_NCORE1"), - PINCTRL_PIN(2, "GPIO_NCORE2"), - PINCTRL_PIN(3, "GPIO_NCORE3"), - PINCTRL_PIN(4, "GPIO_NCORE4"), - PINCTRL_PIN(5, "GPIO_NCORE5"), - PINCTRL_PIN(6, "GPIO_NCORE6"), - PINCTRL_PIN(7, "GPIO_NCORE7"), - PINCTRL_PIN(8, "GPIO_NCORE8"), - PINCTRL_PIN(9, "GPIO_NCORE9"), - PINCTRL_PIN(10, "GPIO_NCORE10"), - PINCTRL_PIN(11, "GPIO_NCORE11"), - PINCTRL_PIN(12, "GPIO_NCORE12"), - PINCTRL_PIN(13, "GPIO_NCORE13"), - PINCTRL_PIN(14, "GPIO_NCORE14"), - PINCTRL_PIN(15, "GPIO_NCORE15"), - PINCTRL_PIN(16, "GPIO_NCORE16"), - PINCTRL_PIN(17, "GPIO_NCORE17"), - PINCTRL_PIN(18, "GPIO_NCORE18"), - PINCTRL_PIN(19, "GPIO_NCORE19"), - PINCTRL_PIN(20, "GPIO_NCORE20"), - PINCTRL_PIN(21, "GPIO_NCORE21"), - PINCTRL_PIN(22, "GPIO_NCORE22"), - PINCTRL_PIN(23, "GPIO_NCORE23"), - PINCTRL_PIN(24, "GPIO_NCORE24"), - PINCTRL_PIN(25, "GPIO_NCORE25"), - PINCTRL_PIN(26, "GPIO_NCORE26"), - PINCTRL_PIN(27, "GPIO_NCORE27"), + PINCTRL_PIN(0, "HV_DDI0_HPD"), + PINCTRL_PIN(1, "HV_DDI0_DDC_SDA"), + PINCTRL_PIN(2, "HV_DDI0_DDC_SCL"), + PINCTRL_PIN(3, "PANEL0_VDDEN"), + PINCTRL_PIN(4, "PANEL0_BKLTEN"), + PINCTRL_PIN(5, "PANEL0_BKLTCTL"), + PINCTRL_PIN(6, "HV_DDI1_HPD"), + PINCTRL_PIN(7, "HV_DDI1_DDC_SDA"), + PINCTRL_PIN(8, "HV_DDI1_DDC_SCL"), + PINCTRL_PIN(9, "PANEL1_VDDEN"), + PINCTRL_PIN(10, "PANEL1_BKLTEN"), + PINCTRL_PIN(11, "PANEL1_BKLTCTL"), + PINCTRL_PIN(12, "GP_INTD_DSI_TE1"), + PINCTRL_PIN(13, "HV_DDI2_DDC_SDA"), + PINCTRL_PIN(14, "HV_DDI2_DDC_SCL"), + PINCTRL_PIN(15, "GP_CAMERASB00"), + PINCTRL_PIN(16, "GP_CAMERASB01"), + PINCTRL_PIN(17, "GP_CAMERASB02"), + PINCTRL_PIN(18, "GP_CAMERASB03"), + PINCTRL_PIN(19, "GP_CAMERASB04"), + PINCTRL_PIN(20, "GP_CAMERASB05"), + PINCTRL_PIN(21, "GP_CAMERASB06"), + PINCTRL_PIN(22, "GP_CAMERASB07"), + PINCTRL_PIN(23, "GP_CAMERASB08"), + PINCTRL_PIN(24, "GP_CAMERASB09"), + PINCTRL_PIN(25, "GP_CAMERASB10"), + PINCTRL_PIN(26, "GP_CAMERASB11"), + PINCTRL_PIN(27, "GP_INTD_DSI_TE2"), }; static const unsigned int byt_ncore_pins_map[BYT_NGPIO_NCORE] = { @@ -549,6 +548,8 @@ static const struct intel_pinctrl_soc_data *byt_soc_data[] = { NULL }; +static DEFINE_RAW_SPINLOCK(byt_lock); + static struct intel_community *byt_get_community(struct byt_gpio *vg, unsigned int pin) { @@ -658,7 +659,7 @@ static void byt_set_group_simple_mux(struct byt_gpio *vg, unsigned long flags; int i; - raw_spin_lock_irqsave(&vg->lock, flags); + raw_spin_lock_irqsave(&byt_lock, flags); for (i = 0; i < group.npins; i++) { void __iomem *padcfg0; @@ -678,7 +679,7 @@ static void byt_set_group_simple_mux(struct byt_gpio *vg, writel(value, padcfg0); } - raw_spin_unlock_irqrestore(&vg->lock, flags); + raw_spin_unlock_irqrestore(&byt_lock, flags); } static void byt_set_group_mixed_mux(struct byt_gpio *vg, @@ -688,7 +689,7 @@ static void byt_set_group_mixed_mux(struct byt_gpio *vg, unsigned long flags; int i; - raw_spin_lock_irqsave(&vg->lock, flags); + raw_spin_lock_irqsave(&byt_lock, flags); for (i = 0; i < group.npins; i++) { void __iomem *padcfg0; @@ -708,7 +709,7 @@ static void byt_set_group_mixed_mux(struct byt_gpio *vg, writel(value, padcfg0); } - raw_spin_unlock_irqrestore(&vg->lock, flags); + raw_spin_unlock_irqrestore(&byt_lock, flags); } static int byt_set_mux(struct pinctrl_dev *pctldev, unsigned int func_selector, @@ -749,11 +750,11 @@ static void byt_gpio_clear_triggering(struct byt_gpio *vg, unsigned int offset) unsigned long flags; u32 value; - raw_spin_lock_irqsave(&vg->lock, flags); + raw_spin_lock_irqsave(&byt_lock, flags); value = readl(reg); value &= ~(BYT_TRIG_POS | BYT_TRIG_NEG | BYT_TRIG_LVL); writel(value, reg); - raw_spin_unlock_irqrestore(&vg->lock, flags); + raw_spin_unlock_irqrestore(&byt_lock, flags); } static int byt_gpio_request_enable(struct pinctrl_dev *pctl_dev, @@ -765,7 +766,7 @@ static int byt_gpio_request_enable(struct pinctrl_dev *pctl_dev, u32 value, gpio_mux; unsigned long flags; - raw_spin_lock_irqsave(&vg->lock, flags); + raw_spin_lock_irqsave(&byt_lock, flags); /* * In most cases, func pin mux 000 means GPIO function. @@ -787,7 +788,7 @@ static int byt_gpio_request_enable(struct pinctrl_dev *pctl_dev, "pin %u forcibly re-configured as GPIO\n", offset); } - raw_spin_unlock_irqrestore(&vg->lock, flags); + raw_spin_unlock_irqrestore(&byt_lock, flags); pm_runtime_get(&vg->pdev->dev); @@ -815,7 +816,7 @@ static int byt_gpio_set_direction(struct pinctrl_dev *pctl_dev, unsigned long flags; u32 value; - raw_spin_lock_irqsave(&vg->lock, flags); + raw_spin_lock_irqsave(&byt_lock, flags); value = readl(val_reg); value &= ~BYT_DIR_MASK; @@ -832,7 +833,7 @@ static int byt_gpio_set_direction(struct pinctrl_dev *pctl_dev, "Potential Error: Setting GPIO with direct_irq_en to output"); writel(value, val_reg); - raw_spin_unlock_irqrestore(&vg->lock, flags); + raw_spin_unlock_irqrestore(&byt_lock, flags); return 0; } @@ -901,11 +902,11 @@ static int byt_pin_config_get(struct pinctrl_dev *pctl_dev, unsigned int offset, u32 conf, pull, val, debounce; u16 arg = 0; - raw_spin_lock_irqsave(&vg->lock, flags); + raw_spin_lock_irqsave(&byt_lock, flags); conf = readl(conf_reg); pull = conf & BYT_PULL_ASSIGN_MASK; val = readl(val_reg); - raw_spin_unlock_irqrestore(&vg->lock, flags); + raw_spin_unlock_irqrestore(&byt_lock, flags); switch (param) { case PIN_CONFIG_BIAS_DISABLE: @@ -932,9 +933,9 @@ static int byt_pin_config_get(struct pinctrl_dev *pctl_dev, unsigned int offset, if (!(conf & BYT_DEBOUNCE_EN)) return -EINVAL; - raw_spin_lock_irqsave(&vg->lock, flags); + raw_spin_lock_irqsave(&byt_lock, flags); debounce = readl(db_reg); - raw_spin_unlock_irqrestore(&vg->lock, flags); + raw_spin_unlock_irqrestore(&byt_lock, flags); switch (debounce & BYT_DEBOUNCE_PULSE_MASK) { case BYT_DEBOUNCE_PULSE_375US: @@ -986,7 +987,7 @@ static int byt_pin_config_set(struct pinctrl_dev *pctl_dev, u32 conf, val, debounce; int i, ret = 0; - raw_spin_lock_irqsave(&vg->lock, flags); + raw_spin_lock_irqsave(&byt_lock, flags); conf = readl(conf_reg); val = readl(val_reg); @@ -1094,7 +1095,7 @@ static int byt_pin_config_set(struct pinctrl_dev *pctl_dev, if (!ret) writel(conf, conf_reg); - raw_spin_unlock_irqrestore(&vg->lock, flags); + raw_spin_unlock_irqrestore(&byt_lock, flags); return ret; } @@ -1119,9 +1120,9 @@ static int byt_gpio_get(struct gpio_chip *chip, unsigned int offset) unsigned long flags; u32 val; - raw_spin_lock_irqsave(&vg->lock, flags); + raw_spin_lock_irqsave(&byt_lock, flags); val = readl(reg); - raw_spin_unlock_irqrestore(&vg->lock, flags); + raw_spin_unlock_irqrestore(&byt_lock, flags); return !!(val & BYT_LEVEL); } @@ -1136,13 +1137,13 @@ static void byt_gpio_set(struct gpio_chip *chip, unsigned int offset, int value) if (!reg) return; - raw_spin_lock_irqsave(&vg->lock, flags); + raw_spin_lock_irqsave(&byt_lock, flags); old_val = readl(reg); if (value) writel(old_val | BYT_LEVEL, reg); else writel(old_val & ~BYT_LEVEL, reg); - raw_spin_unlock_irqrestore(&vg->lock, flags); + raw_spin_unlock_irqrestore(&byt_lock, flags); } static int byt_gpio_get_direction(struct gpio_chip *chip, unsigned int offset) @@ -1155,9 +1156,9 @@ static int byt_gpio_get_direction(struct gpio_chip *chip, unsigned int offset) if (!reg) return -EINVAL; - raw_spin_lock_irqsave(&vg->lock, flags); + raw_spin_lock_irqsave(&byt_lock, flags); value = readl(reg); - raw_spin_unlock_irqrestore(&vg->lock, flags); + raw_spin_unlock_irqrestore(&byt_lock, flags); if (!(value & BYT_OUTPUT_EN)) return 0; @@ -1200,14 +1201,14 @@ static void byt_gpio_dbg_show(struct seq_file *s, struct gpio_chip *chip) const char *label; unsigned int pin; - raw_spin_lock_irqsave(&vg->lock, flags); + raw_spin_lock_irqsave(&byt_lock, flags); pin = vg->soc_data->pins[i].number; reg = byt_gpio_reg(vg, pin, BYT_CONF0_REG); if (!reg) { seq_printf(s, "Could not retrieve pin %i conf0 reg\n", pin); - raw_spin_unlock_irqrestore(&vg->lock, flags); + raw_spin_unlock_irqrestore(&byt_lock, flags); continue; } conf0 = readl(reg); @@ -1216,11 +1217,11 @@ static void byt_gpio_dbg_show(struct seq_file *s, struct gpio_chip *chip) if (!reg) { seq_printf(s, "Could not retrieve pin %i val reg\n", pin); - raw_spin_unlock_irqrestore(&vg->lock, flags); + raw_spin_unlock_irqrestore(&byt_lock, flags); continue; } val = readl(reg); - raw_spin_unlock_irqrestore(&vg->lock, flags); + raw_spin_unlock_irqrestore(&byt_lock, flags); comm = byt_get_community(vg, pin); if (!comm) { @@ -1304,9 +1305,9 @@ static void byt_irq_ack(struct irq_data *d) if (!reg) return; - raw_spin_lock(&vg->lock); + raw_spin_lock(&byt_lock); writel(BIT(offset % 32), reg); - raw_spin_unlock(&vg->lock); + raw_spin_unlock(&byt_lock); } static void byt_irq_mask(struct irq_data *d) @@ -1330,7 +1331,7 @@ static void byt_irq_unmask(struct irq_data *d) if (!reg) return; - raw_spin_lock_irqsave(&vg->lock, flags); + raw_spin_lock_irqsave(&byt_lock, flags); value = readl(reg); switch (irqd_get_trigger_type(d)) { @@ -1353,7 +1354,7 @@ static void byt_irq_unmask(struct irq_data *d) writel(value, reg); - raw_spin_unlock_irqrestore(&vg->lock, flags); + raw_spin_unlock_irqrestore(&byt_lock, flags); } static int byt_irq_type(struct irq_data *d, unsigned int type) @@ -1367,7 +1368,7 @@ static int byt_irq_type(struct irq_data *d, unsigned int type) if (!reg || offset >= vg->chip.ngpio) return -EINVAL; - raw_spin_lock_irqsave(&vg->lock, flags); + raw_spin_lock_irqsave(&byt_lock, flags); value = readl(reg); WARN(value & BYT_DIRECT_IRQ_EN, @@ -1389,7 +1390,7 @@ static int byt_irq_type(struct irq_data *d, unsigned int type) else if (type & IRQ_TYPE_LEVEL_MASK) irq_set_handler_locked(d, handle_level_irq); - raw_spin_unlock_irqrestore(&vg->lock, flags); + raw_spin_unlock_irqrestore(&byt_lock, flags); return 0; } @@ -1425,9 +1426,9 @@ static void byt_gpio_irq_handler(struct irq_desc *desc) continue; } - raw_spin_lock(&vg->lock); + raw_spin_lock(&byt_lock); pending = readl(reg); - raw_spin_unlock(&vg->lock); + raw_spin_unlock(&byt_lock); for_each_set_bit(pin, &pending, 32) { virq = irq_find_mapping(vg->chip.irq.domain, base + pin); generic_handle_irq(virq); @@ -1450,9 +1451,9 @@ static void byt_init_irq_valid_mask(struct gpio_chip *chip, */ } -static void byt_gpio_irq_init_hw(struct byt_gpio *vg) +static int byt_gpio_irq_init_hw(struct gpio_chip *chip) { - struct gpio_chip *gc = &vg->chip; + struct byt_gpio *vg = gpiochip_get_data(chip); struct device *dev = &vg->pdev->dev; void __iomem *reg; u32 base, value; @@ -1476,7 +1477,7 @@ static void byt_gpio_irq_init_hw(struct byt_gpio *vg) value = readl(reg); if (value & BYT_DIRECT_IRQ_EN) { - clear_bit(i, gc->irq.valid_mask); + clear_bit(i, chip->irq.valid_mask); dev_dbg(dev, "excluding GPIO %d from IRQ domain\n", i); } else if ((value & BYT_PIN_MUX) == byt_get_gpio_mux(vg, i)) { byt_gpio_clear_triggering(vg, i); @@ -1504,6 +1505,21 @@ static void byt_gpio_irq_init_hw(struct byt_gpio *vg) "GPIO interrupt error, pins misconfigured. INT_STAT%u: 0x%08x\n", base / 32, value); } + + return 0; +} + +static int byt_gpio_add_pin_ranges(struct gpio_chip *chip) +{ + struct byt_gpio *vg = gpiochip_get_data(chip); + struct device *dev = &vg->pdev->dev; + int ret; + + ret = gpiochip_add_pin_range(chip, dev_name(dev), 0, 0, vg->soc_data->npins); + if (ret) + dev_err(dev, "failed to add GPIO pin range\n"); + + return ret; } static int byt_gpio_probe(struct byt_gpio *vg) @@ -1518,6 +1534,7 @@ static int byt_gpio_probe(struct byt_gpio *vg) gc->label = dev_name(&vg->pdev->dev); gc->base = -1; gc->can_sleep = false; + gc->add_pin_ranges = byt_gpio_add_pin_ranges; gc->parent = &vg->pdev->dev; gc->ngpio = vg->soc_data->npins; gc->irq.init_valid_mask = byt_init_irq_valid_mask; @@ -1528,33 +1545,30 @@ static int byt_gpio_probe(struct byt_gpio *vg) if (!vg->saved_context) return -ENOMEM; #endif - ret = devm_gpiochip_add_data(&vg->pdev->dev, gc, vg); - if (ret) { - dev_err(&vg->pdev->dev, "failed adding byt-gpio chip\n"); - return ret; - } - - ret = gpiochip_add_pin_range(&vg->chip, dev_name(&vg->pdev->dev), - 0, 0, vg->soc_data->npins); - if (ret) { - dev_err(&vg->pdev->dev, "failed to add GPIO pin range\n"); - return ret; - } /* set up interrupts */ irq_rc = platform_get_resource(vg->pdev, IORESOURCE_IRQ, 0); if (irq_rc && irq_rc->start) { - byt_gpio_irq_init_hw(vg); - ret = gpiochip_irqchip_add(gc, &byt_irqchip, 0, - handle_bad_irq, IRQ_TYPE_NONE); - if (ret) { - dev_err(&vg->pdev->dev, "failed to add irqchip\n"); - return ret; - } + struct gpio_irq_chip *girq; + + girq = &gc->irq; + girq->chip = &byt_irqchip; + girq->init_hw = byt_gpio_irq_init_hw; + girq->parent_handler = byt_gpio_irq_handler; + girq->num_parents = 1; + girq->parents = devm_kcalloc(&vg->pdev->dev, girq->num_parents, + sizeof(*girq->parents), GFP_KERNEL); + if (!girq->parents) + return -ENOMEM; + girq->parents[0] = (unsigned int)irq_rc->start; + girq->default_type = IRQ_TYPE_NONE; + girq->handler = handle_bad_irq; + } - gpiochip_set_chained_irqchip(gc, &byt_irqchip, - (unsigned)irq_rc->start, - byt_gpio_irq_handler); + ret = devm_gpiochip_add_data(&vg->pdev->dev, gc, vg); + if (ret) { + dev_err(&vg->pdev->dev, "failed adding byt-gpio chip\n"); + return ret; } return ret; @@ -1638,8 +1652,6 @@ static int byt_pinctrl_probe(struct platform_device *pdev) return PTR_ERR(vg->pctl_dev); } - raw_spin_lock_init(&vg->lock); - ret = byt_gpio_probe(vg); if (ret) return ret; @@ -1654,8 +1666,11 @@ static int byt_pinctrl_probe(struct platform_device *pdev) static int byt_gpio_suspend(struct device *dev) { struct byt_gpio *vg = dev_get_drvdata(dev); + unsigned long flags; int i; + raw_spin_lock_irqsave(&byt_lock, flags); + for (i = 0; i < vg->soc_data->npins; i++) { void __iomem *reg; u32 value; @@ -1676,14 +1691,18 @@ static int byt_gpio_suspend(struct device *dev) vg->saved_context[i].val = value; } + raw_spin_unlock_irqrestore(&byt_lock, flags); return 0; } static int byt_gpio_resume(struct device *dev) { struct byt_gpio *vg = dev_get_drvdata(dev); + unsigned long flags; int i; + raw_spin_lock_irqsave(&byt_lock, flags); + for (i = 0; i < vg->soc_data->npins; i++) { void __iomem *reg; u32 value; @@ -1721,6 +1740,7 @@ static int byt_gpio_resume(struct device *dev) } } + raw_spin_unlock_irqrestore(&byt_lock, flags); return 0; } #endif diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c index 582fa8a75559..60527b93a711 100644 --- a/drivers/pinctrl/intel/pinctrl-cherryview.c +++ b/drivers/pinctrl/intel/pinctrl-cherryview.c @@ -149,6 +149,7 @@ struct chv_pin_context { * @chip: GPIO chip in this pin controller * @irqchip: IRQ chip in this pin controller * @regs: MMIO registers + * @irq: Our parent irq * @intr_lines: Stores mapping between 16 HW interrupt wires and GPIO * offset (in GPIO number space) * @community: Community this pinctrl instance represents @@ -165,6 +166,7 @@ struct chv_pinctrl { struct gpio_chip chip; struct irq_chip irqchip; void __iomem *regs; + unsigned int irq; unsigned int intr_lines[16]; const struct chv_community *community; u32 saved_intmask; @@ -1555,39 +1557,9 @@ static void chv_init_irq_valid_mask(struct gpio_chip *chip, } } -static int chv_gpio_probe(struct chv_pinctrl *pctrl, int irq) +static int chv_gpio_irq_init_hw(struct gpio_chip *chip) { - const struct chv_gpio_pinrange *range; - struct gpio_chip *chip = &pctrl->chip; - bool need_valid_mask = !dmi_check_system(chv_no_valid_mask); - const struct chv_community *community = pctrl->community; - int ret, i, irq_base; - - *chip = chv_gpio_chip; - - chip->ngpio = community->pins[community->npins - 1].number + 1; - chip->label = dev_name(pctrl->dev); - chip->parent = pctrl->dev; - chip->base = -1; - if (need_valid_mask) - chip->irq.init_valid_mask = chv_init_irq_valid_mask; - - ret = devm_gpiochip_add_data(pctrl->dev, chip, pctrl); - if (ret) { - dev_err(pctrl->dev, "Failed to register gpiochip\n"); - return ret; - } - - for (i = 0; i < community->ngpio_ranges; i++) { - range = &community->gpio_ranges[i]; - ret = gpiochip_add_pin_range(chip, dev_name(pctrl->dev), - range->base, range->base, - range->npins); - if (ret) { - dev_err(pctrl->dev, "failed to add GPIO pin range\n"); - return ret; - } - } + struct chv_pinctrl *pctrl = gpiochip_get_data(chip); /* * The same set of machines in chv_no_valid_mask[] have incorrectly @@ -1596,7 +1568,7 @@ static int chv_gpio_probe(struct chv_pinctrl *pctrl, int irq) * * See also https://bugzilla.kernel.org/show_bug.cgi?id=197953. */ - if (!need_valid_mask) { + if (!pctrl->chip.irq.init_valid_mask) { /* * Mask all interrupts the community is able to generate * but leave the ones that can only generate GPEs unmasked. @@ -1608,15 +1580,47 @@ static int chv_gpio_probe(struct chv_pinctrl *pctrl, int irq) /* Clear all interrupts */ chv_writel(0xffff, pctrl->regs + CHV_INTSTAT); - if (!need_valid_mask) { - irq_base = devm_irq_alloc_descs(pctrl->dev, -1, 0, - community->npins, NUMA_NO_NODE); - if (irq_base < 0) { - dev_err(pctrl->dev, "Failed to allocate IRQ numbers\n"); - return irq_base; + return 0; +} + +static int chv_gpio_add_pin_ranges(struct gpio_chip *chip) +{ + struct chv_pinctrl *pctrl = gpiochip_get_data(chip); + const struct chv_community *community = pctrl->community; + const struct chv_gpio_pinrange *range; + int ret, i; + + for (i = 0; i < community->ngpio_ranges; i++) { + range = &community->gpio_ranges[i]; + ret = gpiochip_add_pin_range(chip, dev_name(pctrl->dev), + range->base, range->base, + range->npins); + if (ret) { + dev_err(pctrl->dev, "failed to add GPIO pin range\n"); + return ret; } } + return 0; +} + +static int chv_gpio_probe(struct chv_pinctrl *pctrl, int irq) +{ + const struct chv_gpio_pinrange *range; + struct gpio_chip *chip = &pctrl->chip; + bool need_valid_mask = !dmi_check_system(chv_no_valid_mask); + const struct chv_community *community = pctrl->community; + int ret, i, irq_base; + + *chip = chv_gpio_chip; + + chip->ngpio = community->pins[community->npins - 1].number + 1; + chip->label = dev_name(pctrl->dev); + chip->add_pin_ranges = chv_gpio_add_pin_ranges; + chip->parent = pctrl->dev; + chip->base = -1; + + pctrl->irq = irq; pctrl->irqchip.name = "chv-gpio"; pctrl->irqchip.irq_startup = chv_gpio_irq_startup; pctrl->irqchip.irq_ack = chv_gpio_irq_ack; @@ -1625,10 +1629,27 @@ static int chv_gpio_probe(struct chv_pinctrl *pctrl, int irq) pctrl->irqchip.irq_set_type = chv_gpio_irq_type; pctrl->irqchip.flags = IRQCHIP_SKIP_SET_WAKE; - ret = gpiochip_irqchip_add(chip, &pctrl->irqchip, 0, - handle_bad_irq, IRQ_TYPE_NONE); + chip->irq.chip = &pctrl->irqchip; + chip->irq.init_hw = chv_gpio_irq_init_hw; + chip->irq.parent_handler = chv_gpio_irq_handler; + chip->irq.num_parents = 1; + chip->irq.parents = &pctrl->irq; + chip->irq.default_type = IRQ_TYPE_NONE; + chip->irq.handler = handle_bad_irq; + if (need_valid_mask) { + chip->irq.init_valid_mask = chv_init_irq_valid_mask; + } else { + irq_base = devm_irq_alloc_descs(pctrl->dev, -1, 0, + community->npins, NUMA_NO_NODE); + if (irq_base < 0) { + dev_err(pctrl->dev, "Failed to allocate IRQ numbers\n"); + return irq_base; + } + } + + ret = devm_gpiochip_add_data(pctrl->dev, chip, pctrl); if (ret) { - dev_err(pctrl->dev, "failed to add IRQ chip\n"); + dev_err(pctrl->dev, "Failed to register gpiochip\n"); return ret; } @@ -1642,8 +1663,6 @@ static int chv_gpio_probe(struct chv_pinctrl *pctrl, int irq) } } - gpiochip_set_chained_irqchip(chip, &pctrl->irqchip, irq, - chv_gpio_irq_handler); return 0; } diff --git a/drivers/pinctrl/pinctrl-ingenic.c b/drivers/pinctrl/pinctrl-ingenic.c index 24e0e2ef47a4..369e04350e3d 100644 --- a/drivers/pinctrl/pinctrl-ingenic.c +++ b/drivers/pinctrl/pinctrl-ingenic.c @@ -1809,7 +1809,7 @@ static void ingenic_set_bias(struct ingenic_pinctrl *jzpc, static void ingenic_set_output_level(struct ingenic_pinctrl *jzpc, unsigned int pin, bool high) { - if (jzpc->version >= ID_JZ4770) + if (jzpc->version >= ID_JZ4760) ingenic_config_pin(jzpc, pin, JZ4760_GPIO_PAT0, high); else ingenic_config_pin(jzpc, pin, JZ4740_GPIO_DATA, high); diff --git a/drivers/pinctrl/pinmux.c b/drivers/pinctrl/pinmux.c index e914f6efd39e..9503ddf2edc7 100644 --- a/drivers/pinctrl/pinmux.c +++ b/drivers/pinctrl/pinmux.c @@ -85,7 +85,7 @@ bool pinmux_can_be_used_for_gpio(struct pinctrl_dev *pctldev, unsigned pin) const struct pinmux_ops *ops = pctldev->desc->pmxops; /* Can't inspect pin, assume it can be used */ - if (!desc) + if (!desc || !ops) return true; if (ops->strict && desc->mux_usecount) diff --git a/drivers/platform/mellanox/mlxbf-bootctl.c b/drivers/platform/mellanox/mlxbf-bootctl.c index 61753b648506..5d21c6adf1ab 100644 --- a/drivers/platform/mellanox/mlxbf-bootctl.c +++ b/drivers/platform/mellanox/mlxbf-bootctl.c @@ -309,7 +309,7 @@ static struct platform_driver mlxbf_bootctl_driver = { .probe = mlxbf_bootctl_probe, .driver = { .name = "mlxbf-bootctl", - .groups = mlxbf_bootctl_groups, + .dev_groups = mlxbf_bootctl_groups, .acpi_match_table = mlxbf_bootctl_acpi_ids, } }; diff --git a/drivers/platform/x86/hp-wmi.c b/drivers/platform/x86/hp-wmi.c index 9579a706fc08..a881b709af25 100644 --- a/drivers/platform/x86/hp-wmi.c +++ b/drivers/platform/x86/hp-wmi.c @@ -300,7 +300,7 @@ static int __init hp_wmi_bios_2008_later(void) static int __init hp_wmi_bios_2009_later(void) { - int state = 0; + u8 state[128]; int ret = hp_wmi_perform_query(HPWMI_FEATURE2_QUERY, HPWMI_READ, &state, sizeof(state), sizeof(state)); if (!ret) diff --git a/drivers/platform/x86/pcengines-apuv2.c b/drivers/platform/x86/pcengines-apuv2.c index 48b112b4f0b0..9b11ef1a401f 100644 --- a/drivers/platform/x86/pcengines-apuv2.c +++ b/drivers/platform/x86/pcengines-apuv2.c @@ -2,7 +2,7 @@ /* * PC-Engines APUv2/APUv3 board platform driver - * for gpio buttons and LEDs + * for GPIO buttons and LEDs * * Copyright (C) 2018 metux IT consult * Author: Enrico Weigelt <info@metux.net> @@ -23,10 +23,10 @@ /* * NOTE: this driver only supports APUv2/3 - not APUv1, as this one - * has completely different register layouts + * has completely different register layouts. */ -/* register mappings */ +/* Register mappings */ #define APU2_GPIO_REG_LED1 AMD_FCH_GPIO_REG_GPIO57 #define APU2_GPIO_REG_LED2 AMD_FCH_GPIO_REG_GPIO58 #define APU2_GPIO_REG_LED3 AMD_FCH_GPIO_REG_GPIO59_DEVSLP1 @@ -35,7 +35,7 @@ #define APU2_GPIO_REG_MPCIE2 AMD_FCH_GPIO_REG_GPIO59_DEVSLP0 #define APU2_GPIO_REG_MPCIE3 AMD_FCH_GPIO_REG_GPIO51 -/* order in which the gpio lines are defined in the register list */ +/* Order in which the GPIO lines are defined in the register list */ #define APU2_GPIO_LINE_LED1 0 #define APU2_GPIO_LINE_LED2 1 #define APU2_GPIO_LINE_LED3 2 @@ -44,7 +44,7 @@ #define APU2_GPIO_LINE_MPCIE2 5 #define APU2_GPIO_LINE_MPCIE3 6 -/* gpio device */ +/* GPIO device */ static int apu2_gpio_regs[] = { [APU2_GPIO_LINE_LED1] = APU2_GPIO_REG_LED1, @@ -72,7 +72,7 @@ static const struct amd_fch_gpio_pdata board_apu2 = { .gpio_names = apu2_gpio_names, }; -/* gpio leds device */ +/* GPIO LEDs device */ static const struct gpio_led apu2_leds[] = { { .name = "apu:green:1" }, @@ -95,12 +95,12 @@ static struct gpiod_lookup_table gpios_led_table = { NULL, 1, GPIO_ACTIVE_LOW), GPIO_LOOKUP_IDX(AMD_FCH_GPIO_DRIVER_NAME, APU2_GPIO_LINE_LED3, NULL, 2, GPIO_ACTIVE_LOW), - GPIO_LOOKUP_IDX(AMD_FCH_GPIO_DRIVER_NAME, APU2_GPIO_REG_SIMSWAP, + GPIO_LOOKUP_IDX(AMD_FCH_GPIO_DRIVER_NAME, APU2_GPIO_LINE_SIMSWAP, NULL, 3, GPIO_ACTIVE_LOW), } }; -/* gpio keyboard device */ +/* GPIO keyboard device */ static struct gpio_keys_button apu2_keys_buttons[] = { { @@ -129,12 +129,12 @@ static struct gpiod_lookup_table gpios_key_table = { } }; -/* board setup */ +/* Board setup */ -/* note: matching works on string prefix, so "apu2" must come before "apu" */ +/* Note: matching works on string prefix, so "apu2" must come before "apu" */ static const struct dmi_system_id apu_gpio_dmi_table[] __initconst = { - /* APU2 w/ legacy bios < 4.0.8 */ + /* APU2 w/ legacy BIOS < 4.0.8 */ { .ident = "apu2", .matches = { @@ -143,7 +143,7 @@ static const struct dmi_system_id apu_gpio_dmi_table[] __initconst = { }, .driver_data = (void *)&board_apu2, }, - /* APU2 w/ legacy bios >= 4.0.8 */ + /* APU2 w/ legacy BIOS >= 4.0.8 */ { .ident = "apu2", .matches = { @@ -152,7 +152,7 @@ static const struct dmi_system_id apu_gpio_dmi_table[] __initconst = { }, .driver_data = (void *)&board_apu2, }, - /* APU2 w/ maainline bios */ + /* APU2 w/ mainline BIOS */ { .ident = "apu2", .matches = { @@ -162,7 +162,7 @@ static const struct dmi_system_id apu_gpio_dmi_table[] __initconst = { .driver_data = (void *)&board_apu2, }, - /* APU3 w/ legacy bios < 4.0.8 */ + /* APU3 w/ legacy BIOS < 4.0.8 */ { .ident = "apu3", .matches = { @@ -171,7 +171,7 @@ static const struct dmi_system_id apu_gpio_dmi_table[] __initconst = { }, .driver_data = (void *)&board_apu2, }, - /* APU3 w/ legacy bios >= 4.0.8 */ + /* APU3 w/ legacy BIOS >= 4.0.8 */ { .ident = "apu3", .matches = { @@ -180,7 +180,7 @@ static const struct dmi_system_id apu_gpio_dmi_table[] __initconst = { }, .driver_data = (void *)&board_apu2, }, - /* APU3 w/ mainline bios */ + /* APU3 w/ mainline BIOS */ { .ident = "apu3", .matches = { @@ -189,6 +189,33 @@ static const struct dmi_system_id apu_gpio_dmi_table[] __initconst = { }, .driver_data = (void *)&board_apu2, }, + /* APU4 w/ legacy BIOS < 4.0.8 */ + { + .ident = "apu4", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "PC Engines"), + DMI_MATCH(DMI_BOARD_NAME, "APU4") + }, + .driver_data = (void *)&board_apu2, + }, + /* APU4 w/ legacy BIOS >= 4.0.8 */ + { + .ident = "apu4", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "PC Engines"), + DMI_MATCH(DMI_BOARD_NAME, "apu4") + }, + .driver_data = (void *)&board_apu2, + }, + /* APU4 w/ mainline BIOS */ + { + .ident = "apu4", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "PC Engines"), + DMI_MATCH(DMI_BOARD_NAME, "PC Engines apu4") + }, + .driver_data = (void *)&board_apu2, + }, {} }; @@ -223,7 +250,7 @@ static int __init apu_board_init(void) id = dmi_first_match(apu_gpio_dmi_table); if (!id) { - pr_err("failed to detect apu board via dmi\n"); + pr_err("failed to detect APU board via DMI\n"); return -ENODEV; } @@ -262,7 +289,7 @@ module_init(apu_board_init); module_exit(apu_board_exit); MODULE_AUTHOR("Enrico Weigelt, metux IT consult <info@metux.net>"); -MODULE_DESCRIPTION("PC Engines APUv2/APUv3 board GPIO/LED/keys driver"); +MODULE_DESCRIPTION("PC Engines APUv2/APUv3 board GPIO/LEDs/keys driver"); MODULE_LICENSE("GPL"); MODULE_DEVICE_TABLE(dmi, apu_gpio_dmi_table); MODULE_ALIAS("platform:pcengines-apuv2"); diff --git a/drivers/platform/x86/pmc_atom.c b/drivers/platform/x86/pmc_atom.c index 07d1b911e72f..52ef1419b671 100644 --- a/drivers/platform/x86/pmc_atom.c +++ b/drivers/platform/x86/pmc_atom.c @@ -429,6 +429,14 @@ static const struct dmi_system_id critclk_systems[] = { DMI_MATCH(DMI_PRODUCT_VERSION, "6AV7882-0"), }, }, + { + .ident = "CONNECT X300", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "SIEMENS AG"), + DMI_MATCH(DMI_PRODUCT_VERSION, "A5E45074588"), + }, + }, + { /*sentinel*/ } }; diff --git a/drivers/ptp/Kconfig b/drivers/ptp/Kconfig index b45d2b86d8ca..b0d1b8d264fa 100644 --- a/drivers/ptp/Kconfig +++ b/drivers/ptp/Kconfig @@ -121,7 +121,7 @@ config PTP_1588_CLOCK_KVM config PTP_1588_CLOCK_IDTCM tristate "IDT CLOCKMATRIX as PTP clock" - depends on PTP_1588_CLOCK + depends on PTP_1588_CLOCK && I2C default n help This driver adds support for using IDT CLOCKMATRIX(TM) as a PTP diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 679ad3d2ed23..03d79fee2987 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -1198,6 +1198,10 @@ static int machine_constraints_voltage(struct regulator_dev *rdev, return -EINVAL; } + /* no need to loop voltages if range is continuous */ + if (rdev->desc->continuous_voltage_range) + return 0; + /* initial: [cmin..cmax] valid, [min_uV..max_uV] not */ for (i = 0; i < count; i++) { int value; @@ -1938,8 +1942,8 @@ struct regulator *_regulator_get(struct device *dev, const char *id, regulator = create_regulator(rdev, dev, id); if (regulator == NULL) { regulator = ERR_PTR(-ENOMEM); - put_device(&rdev->dev); module_put(rdev->owner); + put_device(&rdev->dev); return regulator; } @@ -2063,13 +2067,13 @@ static void _regulator_put(struct regulator *regulator) rdev->open_count--; rdev->exclusive = 0; - put_device(&rdev->dev); regulator_unlock(rdev); kfree_const(regulator->supply_name); kfree(regulator); module_put(rdev->owner); + put_device(&rdev->dev); } /** @@ -5002,6 +5006,7 @@ regulator_register(const struct regulator_desc *regulator_desc, struct regulator_dev *rdev; bool dangling_cfg_gpiod = false; bool dangling_of_gpiod = false; + bool reg_device_fail = false; struct device *dev; int ret, i; @@ -5187,7 +5192,7 @@ regulator_register(const struct regulator_desc *regulator_desc, dev_set_drvdata(&rdev->dev, rdev); ret = device_register(&rdev->dev); if (ret != 0) { - put_device(&rdev->dev); + reg_device_fail = true; goto unset_supplies; } @@ -5218,7 +5223,10 @@ wash: clean: if (dangling_of_gpiod) gpiod_put(config->ena_gpiod); - kfree(rdev); + if (reg_device_fail) + put_device(&rdev->dev); + else + kfree(rdev); kfree(config); rinse: if (dangling_cfg_gpiod) diff --git a/drivers/regulator/max77650-regulator.c b/drivers/regulator/max77650-regulator.c index e57fc9197d62..ac89a412f665 100644 --- a/drivers/regulator/max77650-regulator.c +++ b/drivers/regulator/max77650-regulator.c @@ -386,9 +386,16 @@ static int max77650_regulator_probe(struct platform_device *pdev) return 0; } +static const struct of_device_id max77650_regulator_of_match[] = { + { .compatible = "maxim,max77650-regulator" }, + { } +}; +MODULE_DEVICE_TABLE(of, max77650_regulator_of_match); + static struct platform_driver max77650_regulator_driver = { .driver = { .name = "max77650-regulator", + .of_match_table = max77650_regulator_of_match, }, .probe = max77650_regulator_probe, }; diff --git a/drivers/regulator/rn5t618-regulator.c b/drivers/regulator/rn5t618-regulator.c index 4a91be0ad5ae..5c12d57be040 100644 --- a/drivers/regulator/rn5t618-regulator.c +++ b/drivers/regulator/rn5t618-regulator.c @@ -148,6 +148,7 @@ static struct platform_driver rn5t618_regulator_driver = { module_platform_driver(rn5t618_regulator_driver); +MODULE_ALIAS("platform:rn5t618-regulator"); MODULE_AUTHOR("Beniamino Galvani <b.galvani@gmail.com>"); MODULE_DESCRIPTION("RN5T618 regulator driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/regulator/s5m8767.c b/drivers/regulator/s5m8767.c index bdc07739e9a2..12d6b8d2e97e 100644 --- a/drivers/regulator/s5m8767.c +++ b/drivers/regulator/s5m8767.c @@ -588,7 +588,7 @@ static int s5m8767_pmic_dt_parse_pdata(struct platform_device *pdev, if (of_property_read_u32(reg_np, "op_mode", &rmode->mode)) { dev_warn(iodev->dev, - "no op_mode property property at %pOF\n", + "no op_mode property at %pOF\n", reg_np); rmode->mode = S5M8767_OPMODE_NORMAL_MODE; diff --git a/drivers/reset/core.c b/drivers/reset/core.c index ca1d49146f61..7597c70e04d5 100644 --- a/drivers/reset/core.c +++ b/drivers/reset/core.c @@ -787,7 +787,7 @@ struct reset_control *__devm_reset_control_get(struct device *dev, return ERR_PTR(-ENOMEM); rstc = __reset_control_get(dev, id, index, shared, optional, acquired); - if (!IS_ERR(rstc)) { + if (!IS_ERR_OR_NULL(rstc)) { *ptr = rstc; devres_add(dev, ptr); } else { @@ -861,8 +861,7 @@ static int of_reset_control_get_count(struct device_node *node) * @acquired: only one reset control may be acquired for a given controller * and ID * - * Returns pointer to allocated reset_control_array on success or - * error on failure + * Returns pointer to allocated reset_control on success or error on failure */ struct reset_control * of_reset_control_array_get(struct device_node *np, bool shared, bool optional, @@ -915,8 +914,7 @@ EXPORT_SYMBOL_GPL(of_reset_control_array_get); * that just have to be asserted or deasserted, without any * requirements on the order. * - * Returns pointer to allocated reset_control_array on success or - * error on failure + * Returns pointer to allocated reset_control on success or error on failure */ struct reset_control * devm_reset_control_array_get(struct device *dev, bool shared, bool optional) @@ -930,7 +928,7 @@ devm_reset_control_array_get(struct device *dev, bool shared, bool optional) return ERR_PTR(-ENOMEM); rstc = of_reset_control_array_get(dev->of_node, shared, optional, true); - if (IS_ERR(rstc)) { + if (IS_ERR_OR_NULL(rstc)) { devres_free(devres); return rstc; } diff --git a/drivers/reset/reset-brcmstb.c b/drivers/reset/reset-brcmstb.c index a608f445dad6..f213264c8567 100644 --- a/drivers/reset/reset-brcmstb.c +++ b/drivers/reset/reset-brcmstb.c @@ -91,12 +91,6 @@ static int brcmstb_reset_probe(struct platform_device *pdev) return -ENOMEM; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!IS_ALIGNED(res->start, SW_INIT_BANK_SIZE) || - !IS_ALIGNED(resource_size(res), SW_INIT_BANK_SIZE)) { - dev_err(kdev, "incorrect register range\n"); - return -EINVAL; - } - priv->base = devm_ioremap_resource(kdev, res); if (IS_ERR(priv->base)) return PTR_ERR(priv->base); diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index c94184d080f8..a28b9ff82378 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -1128,7 +1128,8 @@ static u32 get_fcx_max_data(struct dasd_device *device) { struct dasd_eckd_private *private = device->private; int fcx_in_css, fcx_in_gneq, fcx_in_features; - int tpm, mdc; + unsigned int mdc; + int tpm; if (dasd_nofcx) return 0; @@ -1142,7 +1143,7 @@ static u32 get_fcx_max_data(struct dasd_device *device) return 0; mdc = ccw_device_get_mdc(device->cdev, 0); - if (mdc < 0) { + if (mdc == 0) { dev_warn(&device->cdev->dev, "Detecting the maximum supported data size for zHPF requests failed\n"); return 0; } else { @@ -1153,12 +1154,12 @@ static u32 get_fcx_max_data(struct dasd_device *device) static int verify_fcx_max_data(struct dasd_device *device, __u8 lpm) { struct dasd_eckd_private *private = device->private; - int mdc; + unsigned int mdc; u32 fcx_max_data; if (private->fcx_max_data) { mdc = ccw_device_get_mdc(device->cdev, lpm); - if ((mdc < 0)) { + if (mdc == 0) { dev_warn(&device->cdev->dev, "Detecting the maximum data size for zHPF " "requests failed (rc=%d) for a new path %x\n", @@ -2073,7 +2074,7 @@ out_err2: dasd_free_block(device->block); device->block = NULL; out_err1: - kfree(private->conf_data); + dasd_eckd_clear_conf_data(device); kfree(device->private); device->private = NULL; return rc; @@ -2082,7 +2083,6 @@ out_err1: static void dasd_eckd_uncheck_device(struct dasd_device *device) { struct dasd_eckd_private *private = device->private; - int i; if (!private) return; @@ -2092,21 +2092,7 @@ static void dasd_eckd_uncheck_device(struct dasd_device *device) private->sneq = NULL; private->vdsneq = NULL; private->gneq = NULL; - private->conf_len = 0; - for (i = 0; i < 8; i++) { - kfree(device->path[i].conf_data); - if ((__u8 *)device->path[i].conf_data == - private->conf_data) { - private->conf_data = NULL; - private->conf_len = 0; - } - device->path[i].conf_data = NULL; - device->path[i].cssid = 0; - device->path[i].ssid = 0; - device->path[i].chpid = 0; - } - kfree(private->conf_data); - private->conf_data = NULL; + dasd_eckd_clear_conf_data(device); } static struct dasd_ccw_req * diff --git a/drivers/s390/block/dasd_fba.h b/drivers/s390/block/dasd_fba.h index 8f75df06e893..45ddabec4017 100644 --- a/drivers/s390/block/dasd_fba.h +++ b/drivers/s390/block/dasd_fba.h @@ -2,7 +2,7 @@ /* * Author(s)......: Holger Smolinski <Holger.Smolinski@de.ibm.com> * Bugreports.to..: <Linux390@de.ibm.com> - * Coypright IBM Corp. 1999, 2000 + * Copyright IBM Corp. 1999, 2000 * */ diff --git a/drivers/s390/block/dasd_proc.c b/drivers/s390/block/dasd_proc.c index 1770b99f607e..8d4d69ea5baf 100644 --- a/drivers/s390/block/dasd_proc.c +++ b/drivers/s390/block/dasd_proc.c @@ -5,7 +5,7 @@ * Carsten Otte <Cotte@de.ibm.com> * Martin Schwidefsky <schwidefsky@de.ibm.com> * Bugreports.to..: <Linux390@de.ibm.com> - * Coypright IBM Corp. 1999, 2002 + * Copyright IBM Corp. 1999, 2002 * * /proc interface for the dasd driver. * diff --git a/drivers/s390/cio/device_ops.c b/drivers/s390/cio/device_ops.c index 65841af15748..ccecf6b9504e 100644 --- a/drivers/s390/cio/device_ops.c +++ b/drivers/s390/cio/device_ops.c @@ -635,7 +635,7 @@ EXPORT_SYMBOL(ccw_device_tm_start_timeout); * @mask: mask of paths to use * * Return the number of 64K-bytes blocks all paths at least support - * for a transport command. Return values <= 0 indicate failures. + * for a transport command. Return value 0 indicates failure. */ int ccw_device_get_mdc(struct ccw_device *cdev, u8 mask) { diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 33a62a6692c0..bc4158888af9 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -655,17 +655,17 @@ static int qeth_check_idx_response(struct qeth_card *card, unsigned char *buffer) { QETH_DBF_HEX(CTRL, 2, buffer, QETH_DBF_CTRL_LEN); - if ((buffer[2] & 0xc0) == 0xc0) { + if ((buffer[2] & QETH_IDX_TERMINATE_MASK) == QETH_IDX_TERMINATE) { QETH_DBF_MESSAGE(2, "received an IDX TERMINATE with cause code %#04x\n", buffer[4]); QETH_CARD_TEXT(card, 2, "ckidxres"); QETH_CARD_TEXT(card, 2, " idxterm"); - QETH_CARD_TEXT_(card, 2, " rc%d", -EIO); - if (buffer[4] == 0xf6) { + QETH_CARD_TEXT_(card, 2, "rc%x", buffer[4]); + if (buffer[4] == QETH_IDX_TERM_BAD_TRANSPORT || + buffer[4] == QETH_IDX_TERM_BAD_TRANSPORT_VM) { dev_err(&card->gdev->dev, - "The qeth device is not configured " - "for the OSI layer required by z/VM\n"); - return -EPERM; + "The device does not support the configured transport mode\n"); + return -EPROTONOSUPPORT; } return -EIO; } @@ -742,10 +742,10 @@ static void qeth_issue_next_read_cb(struct qeth_card *card, case 0: break; case -EIO: - qeth_clear_ipacmd_list(card); qeth_schedule_recovery(card); /* fall through */ default: + qeth_clear_ipacmd_list(card); goto out; } diff --git a/drivers/s390/net/qeth_core_mpc.h b/drivers/s390/net/qeth_core_mpc.h index c1ecce95094d..458db34239a7 100644 --- a/drivers/s390/net/qeth_core_mpc.h +++ b/drivers/s390/net/qeth_core_mpc.h @@ -899,6 +899,11 @@ extern unsigned char IDX_ACTIVATE_WRITE[]; #define QETH_IDX_ACT_ERR_AUTH 0x1E #define QETH_IDX_ACT_ERR_AUTH_USER 0x20 +#define QETH_IDX_TERMINATE 0xc0 +#define QETH_IDX_TERMINATE_MASK 0xc0 +#define QETH_IDX_TERM_BAD_TRANSPORT 0x41 +#define QETH_IDX_TERM_BAD_TRANSPORT_VM 0xf6 + #define PDU_ENCAPSULATION(buffer) \ (buffer + *(buffer + (*(buffer + 0x0b)) + \ *(buffer + *(buffer + 0x0b) + 0x11) + 0x07)) diff --git a/drivers/s390/net/qeth_core_sys.c b/drivers/s390/net/qeth_core_sys.c index e81170ab6d9a..7bd86027f559 100644 --- a/drivers/s390/net/qeth_core_sys.c +++ b/drivers/s390/net/qeth_core_sys.c @@ -207,7 +207,7 @@ static ssize_t qeth_dev_prioqing_store(struct device *dev, card->qdio.default_out_queue = QETH_DEFAULT_QUEUE; } else if (sysfs_streq(buf, "prio_queueing_vlan")) { if (IS_LAYER3(card)) { - rc = -ENOTSUPP; + rc = -EOPNOTSUPP; goto out; } card->qdio.do_prio_queueing = QETH_PRIO_Q_ING_VLAN; diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 9086bc04fa6b..8c95e6019bac 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -295,6 +295,7 @@ static void qeth_l2_stop_card(struct qeth_card *card) flush_workqueue(card->event_wq); card->info.mac_bits &= ~QETH_LAYER2_MAC_REGISTERED; + card->info.promisc_mode = 0; } static int qeth_l2_process_inbound_buffer(struct qeth_card *card, diff --git a/drivers/s390/net/qeth_l2_sys.c b/drivers/s390/net/qeth_l2_sys.c index f70c7aac2dcc..7fa325cf6f8d 100644 --- a/drivers/s390/net/qeth_l2_sys.c +++ b/drivers/s390/net/qeth_l2_sys.c @@ -262,7 +262,8 @@ void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card) return; mutex_lock(&card->sbp_lock); - if (card->options.sbp.role != QETH_SBP_ROLE_NONE) { + if (!card->options.sbp.reflect_promisc && + card->options.sbp.role != QETH_SBP_ROLE_NONE) { /* Conditional to avoid spurious error messages */ qeth_bridgeport_setrole(card, card->options.sbp.role); /* Let the callback function refresh the stored role value. */ diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 27126330a4b0..04e301de376f 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -1314,6 +1314,7 @@ static void qeth_l3_stop_card(struct qeth_card *card) } flush_workqueue(card->event_wq); + card->info.promisc_mode = 0; } static void qeth_l3_set_promisc_mode(struct qeth_card *card) diff --git a/drivers/soc/Kconfig b/drivers/soc/Kconfig index 833e04a7835c..1778f8c62861 100644 --- a/drivers/soc/Kconfig +++ b/drivers/soc/Kconfig @@ -14,6 +14,7 @@ source "drivers/soc/qcom/Kconfig" source "drivers/soc/renesas/Kconfig" source "drivers/soc/rockchip/Kconfig" source "drivers/soc/samsung/Kconfig" +source "drivers/soc/sifive/Kconfig" source "drivers/soc/sunxi/Kconfig" source "drivers/soc/tegra/Kconfig" source "drivers/soc/ti/Kconfig" diff --git a/drivers/soc/Makefile b/drivers/soc/Makefile index 2ec355003524..8b49d782a1ab 100644 --- a/drivers/soc/Makefile +++ b/drivers/soc/Makefile @@ -20,6 +20,7 @@ obj-y += qcom/ obj-y += renesas/ obj-$(CONFIG_ARCH_ROCKCHIP) += rockchip/ obj-$(CONFIG_SOC_SAMSUNG) += samsung/ +obj-$(CONFIG_SOC_SIFIVE) += sifive/ obj-y += sunxi/ obj-$(CONFIG_ARCH_TEGRA) += tegra/ obj-y += ti/ diff --git a/drivers/soc/sifive/Kconfig b/drivers/soc/sifive/Kconfig new file mode 100644 index 000000000000..58cf8c40d08d --- /dev/null +++ b/drivers/soc/sifive/Kconfig @@ -0,0 +1,10 @@ +# SPDX-License-Identifier: GPL-2.0 + +if SOC_SIFIVE + +config SIFIVE_L2 + bool "Sifive L2 Cache controller" + help + Support for the L2 cache controller on SiFive platforms. + +endif diff --git a/drivers/soc/sifive/Makefile b/drivers/soc/sifive/Makefile new file mode 100644 index 000000000000..b5caff77938f --- /dev/null +++ b/drivers/soc/sifive/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-$(CONFIG_SIFIVE_L2) += sifive_l2_cache.o diff --git a/arch/riscv/mm/sifive_l2_cache.c b/drivers/soc/sifive/sifive_l2_cache.c index a9ffff3277c7..a9ffff3277c7 100644 --- a/arch/riscv/mm/sifive_l2_cache.c +++ b/drivers/soc/sifive/sifive_l2_cache.c diff --git a/drivers/spi/spi-cadence.c b/drivers/spi/spi-cadence.c index c36587b42e95..82a0ee09cbe1 100644 --- a/drivers/spi/spi-cadence.c +++ b/drivers/spi/spi-cadence.c @@ -168,16 +168,16 @@ static void cdns_spi_init_hw(struct cdns_spi *xspi) /** * cdns_spi_chipselect - Select or deselect the chip select line * @spi: Pointer to the spi_device structure - * @enable: Select (1) or deselect (0) the chip select line + * @is_high: Select(0) or deselect (1) the chip select line */ -static void cdns_spi_chipselect(struct spi_device *spi, bool enable) +static void cdns_spi_chipselect(struct spi_device *spi, bool is_high) { struct cdns_spi *xspi = spi_master_get_devdata(spi->master); u32 ctrl_reg; ctrl_reg = cdns_spi_read(xspi, CDNS_SPI_CR); - if (!enable) { + if (is_high) { /* Deselect the slave */ ctrl_reg |= CDNS_SPI_CR_SSCTRL; } else { diff --git a/drivers/spi/spi-cavium-thunderx.c b/drivers/spi/spi-cavium-thunderx.c index d12e149f1a41..fd6b9caffaf0 100644 --- a/drivers/spi/spi-cavium-thunderx.c +++ b/drivers/spi/spi-cavium-thunderx.c @@ -82,6 +82,7 @@ static int thunderx_spi_probe(struct pci_dev *pdev, error: clk_disable_unprepare(p->clk); + pci_release_regions(pdev); spi_master_put(master); return ret; } @@ -96,6 +97,7 @@ static void thunderx_spi_remove(struct pci_dev *pdev) return; clk_disable_unprepare(p->clk); + pci_release_regions(pdev); /* Put everything in a known state. */ writeq(0, p->register_base + OCTEON_SPI_CFG(p)); } diff --git a/drivers/spi/spi-dw.c b/drivers/spi/spi-dw.c index a92aa5cd4fbe..76d6b94a7597 100644 --- a/drivers/spi/spi-dw.c +++ b/drivers/spi/spi-dw.c @@ -129,10 +129,11 @@ void dw_spi_set_cs(struct spi_device *spi, bool enable) struct dw_spi *dws = spi_controller_get_devdata(spi->controller); struct chip_data *chip = spi_get_ctldata(spi); + /* Chip select logic is inverted from spi_set_cs() */ if (chip && chip->cs_control) - chip->cs_control(enable); + chip->cs_control(!enable); - if (enable) + if (!enable) dw_writel(dws, DW_SPI_SER, BIT(spi->chip_select)); else if (dws->cs_override) dw_writel(dws, DW_SPI_SER, 0); diff --git a/drivers/spi/spi-fsl-spi.c b/drivers/spi/spi-fsl-spi.c index 114801a32371..fb4159ad6bf6 100644 --- a/drivers/spi/spi-fsl-spi.c +++ b/drivers/spi/spi-fsl-spi.c @@ -611,6 +611,7 @@ static struct spi_master * fsl_spi_probe(struct device *dev, master->setup = fsl_spi_setup; master->cleanup = fsl_spi_cleanup; master->transfer_one_message = fsl_spi_do_one_msg; + master->use_gpio_descriptors = true; mpc8xxx_spi = spi_master_get_devdata(master); mpc8xxx_spi->max_bits_per_word = 32; @@ -727,17 +728,27 @@ static int of_fsl_spi_probe(struct platform_device *ofdev) } } #endif - - pdata->cs_control = fsl_spi_cs_control; + /* + * Handle the case where we have one hardwired (always selected) + * device on the first "chipselect". Else we let the core code + * handle any GPIOs or native chip selects and assign the + * appropriate callback for dealing with the CS lines. This isn't + * supported on the GRLIB variant. + */ + ret = gpiod_count(dev, "cs"); + if (ret <= 0) + pdata->max_chipselect = 1; + else + pdata->cs_control = fsl_spi_cs_control; } ret = of_address_to_resource(np, 0, &mem); if (ret) goto err; - irq = irq_of_parse_and_map(np, 0); - if (!irq) { - ret = -EINVAL; + irq = platform_get_irq(ofdev, 0); + if (irq < 0) { + ret = irq; goto err; } @@ -750,7 +761,6 @@ static int of_fsl_spi_probe(struct platform_device *ofdev) return 0; err: - irq_dispose_mapping(irq); return ret; } diff --git a/drivers/spi/spi-nxp-fspi.c b/drivers/spi/spi-nxp-fspi.c index c36bb1bb464e..8c5084a3a617 100644 --- a/drivers/spi/spi-nxp-fspi.c +++ b/drivers/spi/spi-nxp-fspi.c @@ -439,7 +439,7 @@ static bool nxp_fspi_supports_op(struct spi_mem *mem, op->data.nbytes > f->devtype_data->txfifo) return false; - return true; + return spi_mem_default_supports_op(mem, op); } /* Instead of busy looping invoke readl_poll_timeout functionality. */ diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c index 16b6b2ad4e7c..9071333ebdd8 100644 --- a/drivers/spi/spi-pxa2xx.c +++ b/drivers/spi/spi-pxa2xx.c @@ -1443,6 +1443,10 @@ static const struct pci_device_id pxa2xx_spi_pci_compound_match[] = { { PCI_VDEVICE(INTEL, 0x4b2a), LPSS_BXT_SSP }, { PCI_VDEVICE(INTEL, 0x4b2b), LPSS_BXT_SSP }, { PCI_VDEVICE(INTEL, 0x4b37), LPSS_BXT_SSP }, + /* JSL */ + { PCI_VDEVICE(INTEL, 0x4daa), LPSS_CNL_SSP }, + { PCI_VDEVICE(INTEL, 0x4dab), LPSS_CNL_SSP }, + { PCI_VDEVICE(INTEL, 0x4dfb), LPSS_CNL_SSP }, /* APL */ { PCI_VDEVICE(INTEL, 0x5ac2), LPSS_BXT_SSP }, { PCI_VDEVICE(INTEL, 0x5ac4), LPSS_BXT_SSP }, diff --git a/drivers/spi/spi-sprd.c b/drivers/spi/spi-sprd.c index 2ee1feb41681..6678f1cbc566 100644 --- a/drivers/spi/spi-sprd.c +++ b/drivers/spi/spi-sprd.c @@ -678,7 +678,7 @@ static int sprd_spi_init_hw(struct sprd_spi *ss, struct spi_transfer *t) if (d->unit != SPI_DELAY_UNIT_SCK) return -EINVAL; - val = readl_relaxed(ss->base + SPRD_SPI_CTL7); + val = readl_relaxed(ss->base + SPRD_SPI_CTL0); val &= ~(SPRD_SPI_SCK_REV | SPRD_SPI_NG_TX | SPRD_SPI_NG_RX); /* Set default chip selection, clock phase and clock polarity */ val |= ss->hw_mode & SPI_CPHA ? SPRD_SPI_NG_RX : SPRD_SPI_NG_TX; diff --git a/drivers/spi/spi-ti-qspi.c b/drivers/spi/spi-ti-qspi.c index 3cb65371ae3b..66dcb6128539 100644 --- a/drivers/spi/spi-ti-qspi.c +++ b/drivers/spi/spi-ti-qspi.c @@ -62,6 +62,7 @@ struct ti_qspi { u32 dc; bool mmap_enabled; + int current_cs; }; #define QSPI_PID (0x0) @@ -487,6 +488,7 @@ static void ti_qspi_enable_memory_map(struct spi_device *spi) MEM_CS_EN(spi->chip_select)); } qspi->mmap_enabled = true; + qspi->current_cs = spi->chip_select; } static void ti_qspi_disable_memory_map(struct spi_device *spi) @@ -498,6 +500,7 @@ static void ti_qspi_disable_memory_map(struct spi_device *spi) regmap_update_bits(qspi->ctrl_base, qspi->ctrl_reg, MEM_CS_MASK, 0); qspi->mmap_enabled = false; + qspi->current_cs = -1; } static void ti_qspi_setup_mmap_read(struct spi_device *spi, u8 opcode, @@ -543,7 +546,7 @@ static int ti_qspi_exec_mem_op(struct spi_mem *mem, mutex_lock(&qspi->list_lock); - if (!qspi->mmap_enabled) + if (!qspi->mmap_enabled || qspi->current_cs != mem->spi->chip_select) ti_qspi_enable_memory_map(mem->spi); ti_qspi_setup_mmap_read(mem->spi, op->cmd.opcode, op->data.buswidth, op->addr.nbytes, op->dummy.nbytes); @@ -799,6 +802,7 @@ no_dma: } } qspi->mmap_enabled = false; + qspi->current_cs = -1; ret = devm_spi_register_master(&pdev->dev, master); if (!ret) diff --git a/drivers/staging/axis-fifo/Kconfig b/drivers/staging/axis-fifo/Kconfig index 3fffe4d6f327..f180a8e9f58a 100644 --- a/drivers/staging/axis-fifo/Kconfig +++ b/drivers/staging/axis-fifo/Kconfig @@ -4,7 +4,7 @@ # config XIL_AXIS_FIFO tristate "Xilinx AXI-Stream FIFO IP core driver" - depends on OF + depends on OF && HAS_IOMEM help This adds support for the Xilinx AXI-Stream FIFO IP core driver. The AXI Streaming FIFO allows memory mapped access to a AXI Streaming diff --git a/drivers/staging/comedi/drivers/gsc_hpdi.c b/drivers/staging/comedi/drivers/gsc_hpdi.c index 4bdf44d82879..dc62db1ee1dd 100644 --- a/drivers/staging/comedi/drivers/gsc_hpdi.c +++ b/drivers/staging/comedi/drivers/gsc_hpdi.c @@ -623,6 +623,11 @@ static int gsc_hpdi_auto_attach(struct comedi_device *dev, dma_alloc_coherent(&pcidev->dev, DMA_BUFFER_SIZE, &devpriv->dio_buffer_phys_addr[i], GFP_KERNEL); + if (!devpriv->dio_buffer[i]) { + dev_warn(dev->class_dev, + "failed to allocate DMA buffer\n"); + return -ENOMEM; + } } /* allocate dma descriptors */ devpriv->dma_desc = dma_alloc_coherent(&pcidev->dev, @@ -630,6 +635,11 @@ static int gsc_hpdi_auto_attach(struct comedi_device *dev, NUM_DMA_DESCRIPTORS, &devpriv->dma_desc_phys_addr, GFP_KERNEL); + if (!devpriv->dma_desc) { + dev_warn(dev->class_dev, + "failed to allocate DMA descriptors\n"); + return -ENOMEM; + } if (devpriv->dma_desc_phys_addr & 0xf) { dev_warn(dev->class_dev, " dma descriptors not quad-word aligned (bug)\n"); diff --git a/drivers/staging/wfx/sta.c b/drivers/staging/wfx/sta.c index 3296bc3521d5..9a61478d98f8 100644 --- a/drivers/staging/wfx/sta.c +++ b/drivers/staging/wfx/sta.c @@ -1403,6 +1403,7 @@ int wfx_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif) init_completion(&wvif->scan_complete); INIT_WORK(&wvif->scan_work, wfx_hw_scan_work); + INIT_WORK(&wvif->tx_policy_upload_work, wfx_tx_policy_upload_work); mutex_unlock(&wdev->conf_mutex); hif_set_macaddr(wvif, vif->addr); diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c index a8dc8af83f39..1ba9bc667e13 100644 --- a/drivers/tty/serial/atmel_serial.c +++ b/drivers/tty/serial/atmel_serial.c @@ -2270,27 +2270,6 @@ static void atmel_set_termios(struct uart_port *port, struct ktermios *termios, mode |= ATMEL_US_USMODE_NORMAL; } - /* set the mode, clock divisor, parity, stop bits and data size */ - atmel_uart_writel(port, ATMEL_US_MR, mode); - - /* - * when switching the mode, set the RTS line state according to the - * new mode, otherwise keep the former state - */ - if ((old_mode & ATMEL_US_USMODE) != (mode & ATMEL_US_USMODE)) { - unsigned int rts_state; - - if ((mode & ATMEL_US_USMODE) == ATMEL_US_USMODE_HWHS) { - /* let the hardware control the RTS line */ - rts_state = ATMEL_US_RTSDIS; - } else { - /* force RTS line to low level */ - rts_state = ATMEL_US_RTSEN; - } - - atmel_uart_writel(port, ATMEL_US_CR, rts_state); - } - /* * Set the baud rate: * Fractional baudrate allows to setup output frequency more @@ -2317,6 +2296,28 @@ static void atmel_set_termios(struct uart_port *port, struct ktermios *termios, if (!(port->iso7816.flags & SER_ISO7816_ENABLED)) atmel_uart_writel(port, ATMEL_US_BRGR, quot); + + /* set the mode, clock divisor, parity, stop bits and data size */ + atmel_uart_writel(port, ATMEL_US_MR, mode); + + /* + * when switching the mode, set the RTS line state according to the + * new mode, otherwise keep the former state + */ + if ((old_mode & ATMEL_US_USMODE) != (mode & ATMEL_US_USMODE)) { + unsigned int rts_state; + + if ((mode & ATMEL_US_USMODE) == ATMEL_US_USMODE_HWHS) { + /* let the hardware control the RTS line */ + rts_state = ATMEL_US_RTSDIS; + } else { + /* force RTS line to low level */ + rts_state = ATMEL_US_RTSEN; + } + + atmel_uart_writel(port, ATMEL_US_CR, rts_state); + } + atmel_uart_writel(port, ATMEL_US_CR, ATMEL_US_RSTSTA | ATMEL_US_RSTRX); atmel_uart_writel(port, ATMEL_US_CR, ATMEL_US_TXEN | ATMEL_US_RXEN); atmel_port->tx_stopped = false; diff --git a/drivers/tty/serial/msm_serial.c b/drivers/tty/serial/msm_serial.c index 1cbae0768b1f..f6c45a796433 100644 --- a/drivers/tty/serial/msm_serial.c +++ b/drivers/tty/serial/msm_serial.c @@ -1580,6 +1580,7 @@ static void __msm_console_write(struct uart_port *port, const char *s, int num_newlines = 0; bool replaced = false; void __iomem *tf; + int locked = 1; if (is_uartdm) tf = port->membase + UARTDM_TF; @@ -1592,7 +1593,13 @@ static void __msm_console_write(struct uart_port *port, const char *s, num_newlines++; count += num_newlines; - spin_lock(&port->lock); + if (port->sysrq) + locked = 0; + else if (oops_in_progress) + locked = spin_trylock(&port->lock); + else + spin_lock(&port->lock); + if (is_uartdm) msm_reset_dm_count(port, count); @@ -1628,7 +1635,9 @@ static void __msm_console_write(struct uart_port *port, const char *s, iowrite32_rep(tf, buf, 1); i += num_chars; } - spin_unlock(&port->lock); + + if (locked) + spin_unlock(&port->lock); } static void msm_console_write(struct console *co, const char *s, diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index b0a6eb106edb..7c2782785736 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -2834,6 +2834,7 @@ int uart_add_one_port(struct uart_driver *drv, struct uart_port *uport) if (uport->cons && uport->dev) of_console_check(uport->dev->of_node, uport->cons->name, uport->line); + tty_port_link_device(port, drv->tty_driver, uport->line); uart_configure_port(drv, state, uport); port->console = uart_console(uport); diff --git a/drivers/tty/serial/sprd_serial.c b/drivers/tty/serial/sprd_serial.c index 31df23502562..f60a59d9bf27 100644 --- a/drivers/tty/serial/sprd_serial.c +++ b/drivers/tty/serial/sprd_serial.c @@ -679,6 +679,9 @@ static irqreturn_t sprd_handle_irq(int irq, void *dev_id) if (ims & SPRD_IMSR_TIMEOUT) serial_out(port, SPRD_ICLR, SPRD_ICLR_TIMEOUT); + if (ims & SPRD_IMSR_BREAK_DETECT) + serial_out(port, SPRD_ICLR, SPRD_IMSR_BREAK_DETECT); + if (ims & (SPRD_IMSR_RX_FIFO_FULL | SPRD_IMSR_BREAK_DETECT | SPRD_IMSR_TIMEOUT)) sprd_rx(port); diff --git a/drivers/tty/tty_port.c b/drivers/tty/tty_port.c index 044c3cbdcfa4..5023c85ebc6e 100644 --- a/drivers/tty/tty_port.c +++ b/drivers/tty/tty_port.c @@ -89,7 +89,8 @@ void tty_port_link_device(struct tty_port *port, { if (WARN_ON(index >= driver->num)) return; - driver->ports[index] = port; + if (!driver->ports[index]) + driver->ports[index] = port; } EXPORT_SYMBOL_GPL(tty_port_link_device); diff --git a/drivers/usb/host/ehci-q.c b/drivers/usb/host/ehci-q.c index aa2f77f1506d..8a5c9b3ebe1e 100644 --- a/drivers/usb/host/ehci-q.c +++ b/drivers/usb/host/ehci-q.c @@ -27,6 +27,10 @@ /*-------------------------------------------------------------------------*/ +/* PID Codes that are used here, from EHCI specification, Table 3-16. */ +#define PID_CODE_IN 1 +#define PID_CODE_SETUP 2 + /* fill a qtd, returning how much of the buffer we were able to queue up */ static int @@ -190,7 +194,7 @@ static int qtd_copy_status ( int status = -EINPROGRESS; /* count IN/OUT bytes, not SETUP (even short packets) */ - if (likely (QTD_PID (token) != 2)) + if (likely(QTD_PID(token) != PID_CODE_SETUP)) urb->actual_length += length - QTD_LENGTH (token); /* don't modify error codes */ @@ -206,6 +210,13 @@ static int qtd_copy_status ( if (token & QTD_STS_BABBLE) { /* FIXME "must" disable babbling device's port too */ status = -EOVERFLOW; + /* + * When MMF is active and PID Code is IN, queue is halted. + * EHCI Specification, Table 4-13. + */ + } else if ((token & QTD_STS_MMF) && + (QTD_PID(token) == PID_CODE_IN)) { + status = -EPROTO; /* CERR nonzero + halt --> stall */ } else if (QTD_CERR(token)) { status = -EPIPE; diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 2907fe4d78dd..4917c5b033fa 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -519,7 +519,6 @@ static int xhci_pci_resume(struct usb_hcd *hcd, bool hibernated) retval = xhci_resume(xhci, hibernated); return retval; } -#endif /* CONFIG_PM */ static void xhci_pci_shutdown(struct usb_hcd *hcd) { @@ -532,6 +531,7 @@ static void xhci_pci_shutdown(struct usb_hcd *hcd) if (xhci->quirks & XHCI_SPURIOUS_WAKEUP) pci_set_power_state(pdev, PCI_D3hot); } +#endif /* CONFIG_PM */ /*-------------------------------------------------------------------------*/ diff --git a/drivers/usb/typec/tcpm/Kconfig b/drivers/usb/typec/tcpm/Kconfig index 72481bbb2af3..5b986d6c801d 100644 --- a/drivers/usb/typec/tcpm/Kconfig +++ b/drivers/usb/typec/tcpm/Kconfig @@ -32,6 +32,7 @@ endif # TYPEC_TCPCI config TYPEC_FUSB302 tristate "Fairchild FUSB302 Type-C chip driver" depends on I2C + depends on EXTCON || !EXTCON help The Fairchild FUSB302 Type-C chip driver that works with Type-C Port Controller Manager to provide USB PD and USB diff --git a/drivers/usb/usbip/usbip_common.c b/drivers/usb/usbip/usbip_common.c index 6532d68e8808..e4b96674c405 100644 --- a/drivers/usb/usbip/usbip_common.c +++ b/drivers/usb/usbip/usbip_common.c @@ -727,6 +727,9 @@ int usbip_recv_xbuff(struct usbip_device *ud, struct urb *urb) copy -= recv; ret += recv; + + if (!copy) + break; } if (ret != size) diff --git a/drivers/usb/usbip/vhci_rx.c b/drivers/usb/usbip/vhci_rx.c index 33f8972ba842..00fc98741c5d 100644 --- a/drivers/usb/usbip/vhci_rx.c +++ b/drivers/usb/usbip/vhci_rx.c @@ -77,16 +77,21 @@ static void vhci_recv_ret_submit(struct vhci_device *vdev, usbip_pack_pdu(pdu, urb, USBIP_RET_SUBMIT, 0); /* recv transfer buffer */ - if (usbip_recv_xbuff(ud, urb) < 0) - return; + if (usbip_recv_xbuff(ud, urb) < 0) { + urb->status = -EPROTO; + goto error; + } /* recv iso_packet_descriptor */ - if (usbip_recv_iso(ud, urb) < 0) - return; + if (usbip_recv_iso(ud, urb) < 0) { + urb->status = -EPROTO; + goto error; + } /* restore the padding in iso packets */ usbip_pad_iso(ud, urb); +error: if (usbip_dbg_flag_vhci_rx) usbip_dump_urb(urb); diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index 49b381e104ef..7b36b51cdb9f 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -664,7 +664,6 @@ static int grow_gnttab_list(unsigned int more_frames) unsigned int nr_glist_frames, new_nr_glist_frames; unsigned int grefs_per_frame; - BUG_ON(gnttab_interface == NULL); grefs_per_frame = gnttab_interface->grefs_per_grant_frame; new_nr_grant_frames = nr_grant_frames + more_frames; @@ -1160,7 +1159,6 @@ EXPORT_SYMBOL_GPL(gnttab_unmap_refs_sync); static unsigned int nr_status_frames(unsigned int nr_grant_frames) { - BUG_ON(gnttab_interface == NULL); return gnttab_frames(nr_grant_frames, SPP); } @@ -1388,7 +1386,6 @@ static int gnttab_expand(unsigned int req_entries) int rc; unsigned int cur, extra; - BUG_ON(gnttab_interface == NULL); cur = nr_grant_frames; extra = ((req_entries + gnttab_interface->grefs_per_grant_frame - 1) / gnttab_interface->grefs_per_grant_frame); @@ -1423,7 +1420,6 @@ int gnttab_init(void) /* Determine the maximum number of frames required for the * grant reference free list on the current hypervisor. */ - BUG_ON(gnttab_interface == NULL); max_nr_glist_frames = (max_nr_grant_frames * gnttab_interface->grefs_per_grant_frame / RPP); diff --git a/drivers/xen/xenbus/xenbus.h b/drivers/xen/xenbus/xenbus.h index d75a2385b37c..5f5b8a7d5b80 100644 --- a/drivers/xen/xenbus/xenbus.h +++ b/drivers/xen/xenbus/xenbus.h @@ -116,8 +116,6 @@ int xenbus_probe_devices(struct xen_bus_type *bus); void xenbus_dev_changed(const char *node, struct xen_bus_type *bus); -void xenbus_dev_shutdown(struct device *_dev); - int xenbus_dev_suspend(struct device *dev); int xenbus_dev_resume(struct device *dev); int xenbus_dev_cancel(struct device *dev); diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c index c21be6e9d38a..378486b79f96 100644 --- a/drivers/xen/xenbus/xenbus_probe.c +++ b/drivers/xen/xenbus/xenbus_probe.c @@ -255,7 +255,6 @@ fail_put: module_put(drv->driver.owner); fail: xenbus_dev_error(dev, err, "xenbus_dev_probe on %s", dev->nodename); - xenbus_switch_state(dev, XenbusStateClosed); return err; } EXPORT_SYMBOL_GPL(xenbus_dev_probe); @@ -276,34 +275,20 @@ int xenbus_dev_remove(struct device *_dev) free_otherend_details(dev); - xenbus_switch_state(dev, XenbusStateClosed); + /* + * If the toolstack has forced the device state to closing then set + * the state to closed now to allow it to be cleaned up. + * Similarly, if the driver does not support re-bind, set the + * closed. + */ + if (!drv->allow_rebind || + xenbus_read_driver_state(dev->nodename) == XenbusStateClosing) + xenbus_switch_state(dev, XenbusStateClosed); + return 0; } EXPORT_SYMBOL_GPL(xenbus_dev_remove); -void xenbus_dev_shutdown(struct device *_dev) -{ - struct xenbus_device *dev = to_xenbus_device(_dev); - unsigned long timeout = 5*HZ; - - DPRINTK("%s", dev->nodename); - - get_device(&dev->dev); - if (dev->state != XenbusStateConnected) { - pr_info("%s: %s: %s != Connected, skipping\n", - __func__, dev->nodename, xenbus_strstate(dev->state)); - goto out; - } - xenbus_switch_state(dev, XenbusStateClosing); - timeout = wait_for_completion_timeout(&dev->down, timeout); - if (!timeout) - pr_info("%s: %s timeout closing device\n", - __func__, dev->nodename); - out: - put_device(&dev->dev); -} -EXPORT_SYMBOL_GPL(xenbus_dev_shutdown); - int xenbus_register_driver_common(struct xenbus_driver *drv, struct xen_bus_type *bus, struct module *owner, const char *mod_name) diff --git a/drivers/xen/xenbus/xenbus_probe_backend.c b/drivers/xen/xenbus/xenbus_probe_backend.c index b0bed4faf44c..14876faff3b0 100644 --- a/drivers/xen/xenbus/xenbus_probe_backend.c +++ b/drivers/xen/xenbus/xenbus_probe_backend.c @@ -198,7 +198,6 @@ static struct xen_bus_type xenbus_backend = { .uevent = xenbus_uevent_backend, .probe = xenbus_dev_probe, .remove = xenbus_dev_remove, - .shutdown = xenbus_dev_shutdown, .dev_groups = xenbus_dev_groups, }, }; diff --git a/drivers/xen/xenbus/xenbus_probe_frontend.c b/drivers/xen/xenbus/xenbus_probe_frontend.c index a7d90a719cea..8a1650bbe18f 100644 --- a/drivers/xen/xenbus/xenbus_probe_frontend.c +++ b/drivers/xen/xenbus/xenbus_probe_frontend.c @@ -126,6 +126,28 @@ static int xenbus_frontend_dev_probe(struct device *dev) return xenbus_dev_probe(dev); } +static void xenbus_frontend_dev_shutdown(struct device *_dev) +{ + struct xenbus_device *dev = to_xenbus_device(_dev); + unsigned long timeout = 5*HZ; + + DPRINTK("%s", dev->nodename); + + get_device(&dev->dev); + if (dev->state != XenbusStateConnected) { + pr_info("%s: %s: %s != Connected, skipping\n", + __func__, dev->nodename, xenbus_strstate(dev->state)); + goto out; + } + xenbus_switch_state(dev, XenbusStateClosing); + timeout = wait_for_completion_timeout(&dev->down, timeout); + if (!timeout) + pr_info("%s: %s timeout closing device\n", + __func__, dev->nodename); + out: + put_device(&dev->dev); +} + static const struct dev_pm_ops xenbus_pm_ops = { .suspend = xenbus_dev_suspend, .resume = xenbus_frontend_dev_resume, @@ -146,7 +168,7 @@ static struct xen_bus_type xenbus_frontend = { .uevent = xenbus_uevent_frontend, .probe = xenbus_frontend_dev_probe, .remove = xenbus_dev_remove, - .shutdown = xenbus_dev_shutdown, + .shutdown = xenbus_frontend_dev_shutdown, .dev_groups = xenbus_dev_groups, .pm = &xenbus_pm_ops, diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 5b6e86aaf2e1..24658b5a5787 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -379,7 +379,7 @@ void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info, for (node = rb_first(tm_root); node; node = next) { next = rb_next(node); tm = rb_entry(node, struct tree_mod_elem, node); - if (tm->seq > min_seq) + if (tm->seq >= min_seq) continue; rb_erase(node, tm_root); kfree(tm); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index b2e8fd8a8e59..54efb21c2727 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2787,7 +2787,7 @@ struct btrfs_inode_extref *btrfs_find_name_in_ext_backref( /* file-item.c */ struct btrfs_dio_private; int btrfs_del_csums(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, u64 bytenr, u64 len); + struct btrfs_root *root, u64 bytenr, u64 len); blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, u8 *dst); blk_status_t btrfs_lookup_bio_sums_dio(struct inode *inode, struct bio *bio, diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 153f71a5bba9..274318e9114e 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1869,8 +1869,8 @@ static int cleanup_ref_head(struct btrfs_trans_handle *trans, btrfs_pin_extent(fs_info, head->bytenr, head->num_bytes, 1); if (head->is_data) { - ret = btrfs_del_csums(trans, fs_info, head->bytenr, - head->num_bytes); + ret = btrfs_del_csums(trans, fs_info->csum_root, + head->bytenr, head->num_bytes); } } @@ -3175,7 +3175,8 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, btrfs_release_path(path); if (is_data) { - ret = btrfs_del_csums(trans, info, bytenr, num_bytes); + ret = btrfs_del_csums(trans, info->csum_root, bytenr, + num_bytes); if (ret) { btrfs_abort_transaction(trans, ret); goto out; @@ -3799,6 +3800,7 @@ static noinline int find_free_extent(struct btrfs_fs_info *fs_info, u64 flags, int delalloc) { int ret = 0; + int cache_block_group_error = 0; struct btrfs_free_cluster *last_ptr = NULL; struct btrfs_block_group *block_group = NULL; struct find_free_extent_ctl ffe_ctl = {0}; @@ -3958,7 +3960,20 @@ have_block_group: if (unlikely(!ffe_ctl.cached)) { ffe_ctl.have_caching_bg = true; ret = btrfs_cache_block_group(block_group, 0); - BUG_ON(ret < 0); + + /* + * If we get ENOMEM here or something else we want to + * try other block groups, because it may not be fatal. + * However if we can't find anything else we need to + * save our return here so that we return the actual + * error that caused problems, not ENOSPC. + */ + if (ret < 0) { + if (!cache_block_group_error) + cache_block_group_error = ret; + ret = 0; + goto loop; + } ret = 0; } @@ -4045,7 +4060,7 @@ loop: if (ret > 0) goto search; - if (ret == -ENOSPC) { + if (ret == -ENOSPC && !cache_block_group_error) { /* * Use ffe_ctl->total_free_space as fallback if we can't find * any contiguous hole. @@ -4056,6 +4071,8 @@ loop: space_info->max_extent_size = ffe_ctl.max_extent_size; spin_unlock(&space_info->lock); ins->offset = ffe_ctl.max_extent_size; + } else if (ret == -ENOSPC) { + ret = cache_block_group_error; } return ret; } diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index eb8bd0258360..2f4802f405a2 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -5074,12 +5074,14 @@ struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info, return eb; eb = alloc_dummy_extent_buffer(fs_info, start); if (!eb) - return NULL; + return ERR_PTR(-ENOMEM); eb->fs_info = fs_info; again: ret = radix_tree_preload(GFP_NOFS); - if (ret) + if (ret) { + exists = ERR_PTR(ret); goto free_eb; + } spin_lock(&fs_info->buffer_lock); ret = radix_tree_insert(&fs_info->buffer_radix, start >> PAGE_SHIFT, eb); diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index 3270a40b0777..b1bfdc5c1387 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -590,9 +590,9 @@ static noinline void truncate_one_csum(struct btrfs_fs_info *fs_info, * range of bytes. */ int btrfs_del_csums(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, u64 bytenr, u64 len) + struct btrfs_root *root, u64 bytenr, u64 len) { - struct btrfs_root *root = fs_info->csum_root; + struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_path *path; struct btrfs_key key; u64 end_byte = bytenr + len; @@ -602,6 +602,9 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans, u16 csum_size = btrfs_super_csum_size(fs_info->super_copy); int blocksize_bits = fs_info->sb->s_blocksize_bits; + ASSERT(root == fs_info->csum_root || + root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID); + path = btrfs_alloc_path(); if (!path) return -ENOMEM; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 0cb43b682789..8d47c76b7bd1 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2599,8 +2599,8 @@ int btrfs_punch_hole_range(struct inode *inode, struct btrfs_path *path, } } - if (clone_info) { - u64 clone_len = drop_end - cur_offset; + if (clone_info && drop_end > clone_info->file_offset) { + u64 clone_len = drop_end - clone_info->file_offset; ret = btrfs_insert_clone_extent(trans, inode, path, clone_info, clone_len); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 56032c518b26..e3c76645cad7 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -5728,7 +5728,6 @@ static void inode_tree_add(struct inode *inode) static void inode_tree_del(struct inode *inode) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_root *root = BTRFS_I(inode)->root; int empty = 0; @@ -5741,7 +5740,6 @@ static void inode_tree_del(struct inode *inode) spin_unlock(&root->inode_lock); if (empty && btrfs_root_refs(&root->root_item) == 0) { - synchronize_srcu(&fs_info->subvol_srcu); spin_lock(&root->inode_lock); empty = RB_EMPTY_ROOT(&root->inode_tree); spin_unlock(&root->inode_lock); @@ -9556,9 +9554,8 @@ static int btrfs_rename_exchange(struct inode *old_dir, btrfs_init_log_ctx(&ctx_dest, new_inode); /* close the race window with snapshot create/destroy ioctl */ - if (old_ino == BTRFS_FIRST_FREE_OBJECTID) - down_read(&fs_info->subvol_sem); - if (new_ino == BTRFS_FIRST_FREE_OBJECTID) + if (old_ino == BTRFS_FIRST_FREE_OBJECTID || + new_ino == BTRFS_FIRST_FREE_OBJECTID) down_read(&fs_info->subvol_sem); /* @@ -9792,9 +9789,8 @@ out_fail: ret = ret ? ret : ret2; } out_notrans: - if (new_ino == BTRFS_FIRST_FREE_OBJECTID) - up_read(&fs_info->subvol_sem); - if (old_ino == BTRFS_FIRST_FREE_OBJECTID) + if (new_ino == BTRFS_FIRST_FREE_OBJECTID || + old_ino == BTRFS_FIRST_FREE_OBJECTID) up_read(&fs_info->subvol_sem); ASSERT(list_empty(&ctx_root.list)); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index a1ee0b775e65..18e328ce4b54 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -704,11 +704,17 @@ static noinline int create_subvol(struct inode *dir, btrfs_i_size_write(BTRFS_I(dir), dir->i_size + namelen * 2); ret = btrfs_update_inode(trans, root, dir); - BUG_ON(ret); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto fail; + } ret = btrfs_add_root_ref(trans, objectid, root->root_key.objectid, btrfs_ino(BTRFS_I(dir)), index, name, namelen); - BUG_ON(ret); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto fail; + } ret = btrfs_uuid_tree_add(trans, root_item->uuid, BTRFS_UUID_KEY_SUBVOL, objectid); @@ -3720,24 +3726,18 @@ process_slot: ret = 0; if (last_dest_end < destoff + len) { - struct btrfs_clone_extent_info clone_info = { 0 }; /* - * We have an implicit hole (NO_HOLES feature is enabled) that - * fully or partially overlaps our cloning range at its end. + * We have an implicit hole that fully or partially overlaps our + * cloning range at its end. This means that we either have the + * NO_HOLES feature enabled or the implicit hole happened due to + * mixing buffered and direct IO writes against this file. */ btrfs_release_path(path); path->leave_spinning = 0; - /* - * We are dealing with a hole and our clone_info already has a - * disk_offset of 0, we only need to fill the data length and - * file offset. - */ - clone_info.data_len = destoff + len - last_dest_end; - clone_info.file_offset = last_dest_end; ret = btrfs_punch_hole_range(inode, path, last_dest_end, destoff + len - 1, - &clone_info, &trans); + NULL, &trans); if (ret) goto out; diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 93aeb2e539a4..d4282e12f2a6 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -3232,12 +3232,12 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid, if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN)) { btrfs_warn(fs_info, - "qgroup rescan init failed, qgroup is not enabled"); + "qgroup rescan init failed, qgroup rescan is not queued"); ret = -EINVAL; } else if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_ON)) { btrfs_warn(fs_info, - "qgroup rescan init failed, qgroup rescan is not queued"); + "qgroup rescan init failed, qgroup is not enabled"); ret = -EINVAL; } diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index d897a8e5e430..c58245797f30 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -4552,6 +4552,7 @@ int btrfs_recover_relocation(struct btrfs_root *root) fs_root = read_fs_root(fs_info, reloc_root->root_key.offset); if (IS_ERR(fs_root)) { err = PTR_ERR(fs_root); + list_add_tail(&reloc_root->root_list, &reloc_roots); goto out_free; } diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index ae2db5eb1549..091e5bc8c7ea 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -7084,12 +7084,6 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg) spin_unlock(&send_root->root_item_lock); /* - * This is done when we lookup the root, it should already be complete - * by the time we get here. - */ - WARN_ON(send_root->orphan_cleanup_state != ORPHAN_CLEANUP_DONE); - - /* * Userspace tools do the checks and warn the user if it's * not RO. */ diff --git a/fs/btrfs/tests/free-space-tree-tests.c b/fs/btrfs/tests/free-space-tree-tests.c index 1a846bf6e197..914eea5ba6a7 100644 --- a/fs/btrfs/tests/free-space-tree-tests.c +++ b/fs/btrfs/tests/free-space-tree-tests.c @@ -452,9 +452,9 @@ static int run_test(test_func_t test_func, int bitmaps, u32 sectorsize, root->fs_info->tree_root = root; root->node = alloc_test_extent_buffer(root->fs_info, nodesize); - if (!root->node) { + if (IS_ERR(root->node)) { test_std_err(TEST_ALLOC_EXTENT_BUFFER); - ret = -ENOMEM; + ret = PTR_ERR(root->node); goto out; } btrfs_set_header_level(root->node, 0); diff --git a/fs/btrfs/tests/qgroup-tests.c b/fs/btrfs/tests/qgroup-tests.c index 09aaca1efd62..ac035a6fa003 100644 --- a/fs/btrfs/tests/qgroup-tests.c +++ b/fs/btrfs/tests/qgroup-tests.c @@ -484,9 +484,9 @@ int btrfs_test_qgroups(u32 sectorsize, u32 nodesize) * *cough*backref walking code*cough* */ root->node = alloc_test_extent_buffer(root->fs_info, nodesize); - if (!root->node) { + if (IS_ERR(root->node)) { test_err("couldn't allocate dummy buffer"); - ret = -ENOMEM; + ret = PTR_ERR(root->node); goto out; } btrfs_set_header_level(root->node, 0); diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 493d4d9e0f79..97f3520b8d98 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -227,7 +227,7 @@ static int check_extent_data_item(struct extent_buffer *leaf, */ if (item_size < BTRFS_FILE_EXTENT_INLINE_DATA_START) { file_extent_err(leaf, slot, - "invalid item size, have %u expect [%lu, %u)", + "invalid item size, have %u expect [%zu, %u)", item_size, BTRFS_FILE_EXTENT_INLINE_DATA_START, SZ_4K); return -EUCLEAN; @@ -332,7 +332,7 @@ static int check_extent_data_item(struct extent_buffer *leaf, } static int check_csum_item(struct extent_buffer *leaf, struct btrfs_key *key, - int slot) + int slot, struct btrfs_key *prev_key) { struct btrfs_fs_info *fs_info = leaf->fs_info; u32 sectorsize = fs_info->sectorsize; @@ -356,6 +356,20 @@ static int check_csum_item(struct extent_buffer *leaf, struct btrfs_key *key, btrfs_item_size_nr(leaf, slot), csumsize); return -EUCLEAN; } + if (slot > 0 && prev_key->type == BTRFS_EXTENT_CSUM_KEY) { + u64 prev_csum_end; + u32 prev_item_size; + + prev_item_size = btrfs_item_size_nr(leaf, slot - 1); + prev_csum_end = (prev_item_size / csumsize) * sectorsize; + prev_csum_end += prev_key->offset; + if (prev_csum_end > key->offset) { + generic_err(leaf, slot - 1, +"csum end range (%llu) goes beyond the start range (%llu) of the next csum item", + prev_csum_end, key->offset); + return -EUCLEAN; + } + } return 0; } @@ -1355,7 +1369,7 @@ static int check_leaf_item(struct extent_buffer *leaf, ret = check_extent_data_item(leaf, key, slot, prev_key); break; case BTRFS_EXTENT_CSUM_KEY: - ret = check_csum_item(leaf, key, slot); + ret = check_csum_item(leaf, key, slot, prev_key); break; case BTRFS_DIR_ITEM_KEY: case BTRFS_DIR_INDEX_KEY: diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 6f757361db53..d3f115909ff0 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -808,7 +808,8 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, struct btrfs_ordered_sum, list); if (!ret) - ret = btrfs_del_csums(trans, fs_info, + ret = btrfs_del_csums(trans, + fs_info->csum_root, sums->bytenr, sums->len); if (!ret) @@ -3909,6 +3910,28 @@ static int log_inode_item(struct btrfs_trans_handle *trans, return 0; } +static int log_csums(struct btrfs_trans_handle *trans, + struct btrfs_root *log_root, + struct btrfs_ordered_sum *sums) +{ + int ret; + + /* + * Due to extent cloning, we might have logged a csum item that covers a + * subrange of a cloned extent, and later we can end up logging a csum + * item for a larger subrange of the same extent or the entire range. + * This would leave csum items in the log tree that cover the same range + * and break the searches for checksums in the log tree, resulting in + * some checksums missing in the fs/subvolume tree. So just delete (or + * trim and adjust) any existing csum items in the log for this range. + */ + ret = btrfs_del_csums(trans, log_root, sums->bytenr, sums->len); + if (ret) + return ret; + + return btrfs_csum_file_blocks(trans, log_root, sums); +} + static noinline int copy_items(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *dst_path, @@ -4054,7 +4077,7 @@ static noinline int copy_items(struct btrfs_trans_handle *trans, struct btrfs_ordered_sum, list); if (!ret) - ret = btrfs_csum_file_blocks(trans, log, sums); + ret = log_csums(trans, log, sums); list_del(&sums->list); kfree(sums); } @@ -4274,7 +4297,7 @@ static int log_extent_csums(struct btrfs_trans_handle *trans, struct btrfs_ordered_sum, list); if (!ret) - ret = btrfs_csum_file_blocks(trans, log_root, sums); + ret = log_csums(trans, log_root, sums); list_del(&sums->list); kfree(sums); } @@ -6294,9 +6317,28 @@ again: wc.replay_dest = btrfs_read_fs_root_no_name(fs_info, &tmp_key); if (IS_ERR(wc.replay_dest)) { ret = PTR_ERR(wc.replay_dest); + + /* + * We didn't find the subvol, likely because it was + * deleted. This is ok, simply skip this log and go to + * the next one. + * + * We need to exclude the root because we can't have + * other log replays overwriting this log as we'll read + * it back in a few more times. This will keep our + * block from being modified, and we'll just bail for + * each subsequent pass. + */ + if (ret == -ENOENT) + ret = btrfs_pin_extent_for_log_replay(fs_info, + log->node->start, + log->node->len); free_extent_buffer(log->node); free_extent_buffer(log->commit_root); kfree(log); + + if (!ret) + goto next; btrfs_handle_fs_error(fs_info, ret, "Couldn't read target root for tree log recovery."); goto error; @@ -6328,7 +6370,6 @@ again: &root->highest_objectid); } - key.offset = found_key.offset - 1; wc.replay_dest->log_root = NULL; free_extent_buffer(log->node); free_extent_buffer(log->commit_root); @@ -6336,9 +6377,10 @@ again: if (ret) goto error; - +next: if (found_key.offset == 0) break; + key.offset = found_key.offset - 1; } btrfs_release_path(path); diff --git a/fs/btrfs/uuid-tree.c b/fs/btrfs/uuid-tree.c index 91caab63bdf5..76b84f2397b1 100644 --- a/fs/btrfs/uuid-tree.c +++ b/fs/btrfs/uuid-tree.c @@ -324,6 +324,8 @@ again_search_slot: } if (ret < 0 && ret != -ENOENT) goto out; + key.offset++; + goto again_search_slot; } item_size -= sizeof(subid_le); offset += sizeof(subid_le); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index d8e5560db285..a6d3f08bfff3 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -61,7 +61,7 @@ const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = { [BTRFS_RAID_RAID1C3] = { .sub_stripes = 1, .dev_stripes = 1, - .devs_max = 0, + .devs_max = 3, .devs_min = 3, .tolerated_failures = 2, .devs_increment = 3, @@ -73,7 +73,7 @@ const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = { [BTRFS_RAID_RAID1C4] = { .sub_stripes = 1, .dev_stripes = 1, - .devs_max = 0, + .devs_max = 4, .devs_min = 4, .tolerated_failures = 3, .devs_increment = 4, diff --git a/fs/drop_caches.c b/fs/drop_caches.c index d31b6c72b476..dc1a1d5d825b 100644 --- a/fs/drop_caches.c +++ b/fs/drop_caches.c @@ -35,11 +35,11 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused) spin_unlock(&inode->i_lock); spin_unlock(&sb->s_inode_list_lock); - cond_resched(); invalidate_mapping_pages(inode->i_mapping, 0, -1); iput(toput_inode); toput_inode = inode; + cond_resched(); spin_lock(&sb->s_inode_list_lock); } spin_unlock(&sb->s_inode_list_lock); diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c index d4d4fdfac1a6..1ee04e76bbe0 100644 --- a/fs/ext4/block_validity.c +++ b/fs/ext4/block_validity.c @@ -133,10 +133,13 @@ static void debug_print_tree(struct ext4_sb_info *sbi) { struct rb_node *node; struct ext4_system_zone *entry; + struct ext4_system_blocks *system_blks; int first = 1; printk(KERN_INFO "System zones: "); - node = rb_first(&sbi->system_blks->root); + rcu_read_lock(); + system_blks = rcu_dereference(sbi->system_blks); + node = rb_first(&system_blks->root); while (node) { entry = rb_entry(node, struct ext4_system_zone, node); printk(KERN_CONT "%s%llu-%llu", first ? "" : ", ", @@ -144,6 +147,7 @@ static void debug_print_tree(struct ext4_sb_info *sbi) first = 0; node = rb_next(node); } + rcu_read_unlock(); printk(KERN_CONT "\n"); } diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index 9fdd2b269d61..9f00fc0bf21d 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -72,6 +72,7 @@ int __ext4_check_dir_entry(const char *function, unsigned int line, const char *error_msg = NULL; const int rlen = ext4_rec_len_from_disk(de->rec_len, dir->i_sb->s_blocksize); + const int next_offset = ((char *) de - buf) + rlen; if (unlikely(rlen < EXT4_DIR_REC_LEN(1))) error_msg = "rec_len is smaller than minimal"; @@ -79,8 +80,11 @@ int __ext4_check_dir_entry(const char *function, unsigned int line, error_msg = "rec_len % 4 != 0"; else if (unlikely(rlen < EXT4_DIR_REC_LEN(de->name_len))) error_msg = "rec_len is too small for name_len"; - else if (unlikely(((char *) de - buf) + rlen > size)) + else if (unlikely(next_offset > size)) error_msg = "directory entry overrun"; + else if (unlikely(next_offset > size - EXT4_DIR_REC_LEN(1) && + next_offset != size)) + error_msg = "directory entry too close to block end"; else if (unlikely(le32_to_cpu(de->inode) > le32_to_cpu(EXT4_SB(dir->i_sb)->s_es->s_inodes_count))) error_msg = "inode out of bounds"; diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index dc333e8e51e8..8ca4a23129aa 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -921,8 +921,8 @@ repeat_in_this_group: if (!handle) { BUG_ON(nblocks <= 0); handle = __ext4_journal_start_sb(dir->i_sb, line_no, - handle_type, nblocks, - 0, 0); + handle_type, nblocks, 0, + ext4_trans_default_revoke_credits(sb)); if (IS_ERR(handle)) { err = PTR_ERR(handle); ext4_std_error(sb, err); diff --git a/fs/ext4/inode-test.c b/fs/ext4/inode-test.c index 92a9da1774aa..bbce1c328d85 100644 --- a/fs/ext4/inode-test.c +++ b/fs/ext4/inode-test.c @@ -25,7 +25,7 @@ * For constructing the negative timestamp lower bound value. * binary: 10000000 00000000 00000000 00000000 */ -#define LOWER_MSB_1 (-0x80000000L) +#define LOWER_MSB_1 (-(UPPER_MSB_0) - 1L) /* avoid overflow */ /* * For constructing the negative timestamp upper bound value. * binary: 11111111 11111111 11111111 11111111 diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 28f28de0c1b6..629a25d999f0 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5692,7 +5692,7 @@ int ext4_expand_extra_isize(struct inode *inode, error = ext4_journal_get_write_access(handle, iloc->bh); if (error) { brelse(iloc->bh); - goto out_stop; + goto out_unlock; } error = __ext4_expand_extra_isize(inode, new_extra_isize, iloc, @@ -5702,8 +5702,8 @@ int ext4_expand_extra_isize(struct inode *inode, if (!error) error = rc; +out_unlock: ext4_write_unlock_xattr(inode, &no_expand); -out_stop: ext4_journal_stop(handle); return error; } diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index a856997d87b5..1cb42d940784 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2164,7 +2164,9 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, struct buffer_head *bh = NULL; struct ext4_dir_entry_2 *de; struct super_block *sb; +#ifdef CONFIG_UNICODE struct ext4_sb_info *sbi; +#endif struct ext4_filename fname; int retval; int dx_fallback=0; @@ -2176,12 +2178,12 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, csum_size = sizeof(struct ext4_dir_entry_tail); sb = dir->i_sb; - sbi = EXT4_SB(sb); blocksize = sb->s_blocksize; if (!dentry->d_name.len) return -EINVAL; #ifdef CONFIG_UNICODE + sbi = EXT4_SB(sb); if (ext4_has_strict_mode(sbi) && IS_CASEFOLDED(dir) && sbi->s_encoding && utf8_validate(sbi->s_encoding, &dentry->d_name)) return -EINVAL; @@ -2822,7 +2824,7 @@ bool ext4_empty_dir(struct inode *inode) { unsigned int offset; struct buffer_head *bh; - struct ext4_dir_entry_2 *de, *de1; + struct ext4_dir_entry_2 *de; struct super_block *sb; if (ext4_has_inline_data(inode)) { @@ -2847,19 +2849,25 @@ bool ext4_empty_dir(struct inode *inode) return true; de = (struct ext4_dir_entry_2 *) bh->b_data; - de1 = ext4_next_entry(de, sb->s_blocksize); - if (le32_to_cpu(de->inode) != inode->i_ino || - le32_to_cpu(de1->inode) == 0 || - strcmp(".", de->name) || strcmp("..", de1->name)) { - ext4_warning_inode(inode, "directory missing '.' and/or '..'"); + if (ext4_check_dir_entry(inode, NULL, de, bh, bh->b_data, bh->b_size, + 0) || + le32_to_cpu(de->inode) != inode->i_ino || strcmp(".", de->name)) { + ext4_warning_inode(inode, "directory missing '.'"); + brelse(bh); + return true; + } + offset = ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize); + de = ext4_next_entry(de, sb->s_blocksize); + if (ext4_check_dir_entry(inode, NULL, de, bh, bh->b_data, bh->b_size, + offset) || + le32_to_cpu(de->inode) == 0 || strcmp("..", de->name)) { + ext4_warning_inode(inode, "directory missing '..'"); brelse(bh); return true; } - offset = ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize) + - ext4_rec_len_from_disk(de1->rec_len, sb->s_blocksize); - de = ext4_next_entry(de1, sb->s_blocksize); + offset += ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize); while (offset < inode->i_size) { - if ((void *) de >= (void *) (bh->b_data+sb->s_blocksize)) { + if (!(offset & (sb->s_blocksize - 1))) { unsigned int lblock; brelse(bh); lblock = offset >> EXT4_BLOCK_SIZE_BITS(sb); @@ -2870,12 +2878,11 @@ bool ext4_empty_dir(struct inode *inode) } if (IS_ERR(bh)) return true; - de = (struct ext4_dir_entry_2 *) bh->b_data; } + de = (struct ext4_dir_entry_2 *) (bh->b_data + + (offset & (sb->s_blocksize - 1))); if (ext4_check_dir_entry(inode, NULL, de, bh, bh->b_data, bh->b_size, offset)) { - de = (struct ext4_dir_entry_2 *)(bh->b_data + - sb->s_blocksize); offset = (offset | (sb->s_blocksize - 1)) + 1; continue; } @@ -2884,7 +2891,6 @@ bool ext4_empty_dir(struct inode *inode) return false; } offset += ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize); - de = ext4_next_entry(de, sb->s_blocksize); } brelse(bh); return true; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 1d82b56d9b11..2937a8873fe1 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1900,6 +1900,13 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, } sbi->s_commit_interval = HZ * arg; } else if (token == Opt_debug_want_extra_isize) { + if ((arg & 1) || + (arg < 4) || + (arg > (sbi->s_inode_size - EXT4_GOOD_OLD_INODE_SIZE))) { + ext4_msg(sb, KERN_ERR, + "Invalid want_extra_isize %d", arg); + return -1; + } sbi->s_want_extra_isize = arg; } else if (token == Opt_max_batch_time) { sbi->s_max_batch_time = arg; @@ -3554,40 +3561,6 @@ int ext4_calculate_overhead(struct super_block *sb) return 0; } -static void ext4_clamp_want_extra_isize(struct super_block *sb) -{ - struct ext4_sb_info *sbi = EXT4_SB(sb); - struct ext4_super_block *es = sbi->s_es; - unsigned def_extra_isize = sizeof(struct ext4_inode) - - EXT4_GOOD_OLD_INODE_SIZE; - - if (sbi->s_inode_size == EXT4_GOOD_OLD_INODE_SIZE) { - sbi->s_want_extra_isize = 0; - return; - } - if (sbi->s_want_extra_isize < 4) { - sbi->s_want_extra_isize = def_extra_isize; - if (ext4_has_feature_extra_isize(sb)) { - if (sbi->s_want_extra_isize < - le16_to_cpu(es->s_want_extra_isize)) - sbi->s_want_extra_isize = - le16_to_cpu(es->s_want_extra_isize); - if (sbi->s_want_extra_isize < - le16_to_cpu(es->s_min_extra_isize)) - sbi->s_want_extra_isize = - le16_to_cpu(es->s_min_extra_isize); - } - } - /* Check if enough inode space is available */ - if ((sbi->s_want_extra_isize > sbi->s_inode_size) || - (EXT4_GOOD_OLD_INODE_SIZE + sbi->s_want_extra_isize > - sbi->s_inode_size)) { - sbi->s_want_extra_isize = def_extra_isize; - ext4_msg(sb, KERN_INFO, - "required extra inode space not available"); - } -} - static void ext4_set_resv_clusters(struct super_block *sb) { ext4_fsblk_t resv_clusters; @@ -3795,6 +3768,68 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) */ sbi->s_li_wait_mult = EXT4_DEF_LI_WAIT_MULT; + if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV) { + sbi->s_inode_size = EXT4_GOOD_OLD_INODE_SIZE; + sbi->s_first_ino = EXT4_GOOD_OLD_FIRST_INO; + } else { + sbi->s_inode_size = le16_to_cpu(es->s_inode_size); + sbi->s_first_ino = le32_to_cpu(es->s_first_ino); + if (sbi->s_first_ino < EXT4_GOOD_OLD_FIRST_INO) { + ext4_msg(sb, KERN_ERR, "invalid first ino: %u", + sbi->s_first_ino); + goto failed_mount; + } + if ((sbi->s_inode_size < EXT4_GOOD_OLD_INODE_SIZE) || + (!is_power_of_2(sbi->s_inode_size)) || + (sbi->s_inode_size > blocksize)) { + ext4_msg(sb, KERN_ERR, + "unsupported inode size: %d", + sbi->s_inode_size); + goto failed_mount; + } + /* + * i_atime_extra is the last extra field available for + * [acm]times in struct ext4_inode. Checking for that + * field should suffice to ensure we have extra space + * for all three. + */ + if (sbi->s_inode_size >= offsetof(struct ext4_inode, i_atime_extra) + + sizeof(((struct ext4_inode *)0)->i_atime_extra)) { + sb->s_time_gran = 1; + sb->s_time_max = EXT4_EXTRA_TIMESTAMP_MAX; + } else { + sb->s_time_gran = NSEC_PER_SEC; + sb->s_time_max = EXT4_NON_EXTRA_TIMESTAMP_MAX; + } + sb->s_time_min = EXT4_TIMESTAMP_MIN; + } + if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE) { + sbi->s_want_extra_isize = sizeof(struct ext4_inode) - + EXT4_GOOD_OLD_INODE_SIZE; + if (ext4_has_feature_extra_isize(sb)) { + unsigned v, max = (sbi->s_inode_size - + EXT4_GOOD_OLD_INODE_SIZE); + + v = le16_to_cpu(es->s_want_extra_isize); + if (v > max) { + ext4_msg(sb, KERN_ERR, + "bad s_want_extra_isize: %d", v); + goto failed_mount; + } + if (sbi->s_want_extra_isize < v) + sbi->s_want_extra_isize = v; + + v = le16_to_cpu(es->s_min_extra_isize); + if (v > max) { + ext4_msg(sb, KERN_ERR, + "bad s_min_extra_isize: %d", v); + goto failed_mount; + } + if (sbi->s_want_extra_isize < v) + sbi->s_want_extra_isize = v; + } + } + if (sbi->s_es->s_mount_opts[0]) { char *s_mount_opts = kstrndup(sbi->s_es->s_mount_opts, sizeof(sbi->s_es->s_mount_opts), @@ -4033,42 +4068,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) has_huge_files); sb->s_maxbytes = ext4_max_size(sb->s_blocksize_bits, has_huge_files); - if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV) { - sbi->s_inode_size = EXT4_GOOD_OLD_INODE_SIZE; - sbi->s_first_ino = EXT4_GOOD_OLD_FIRST_INO; - } else { - sbi->s_inode_size = le16_to_cpu(es->s_inode_size); - sbi->s_first_ino = le32_to_cpu(es->s_first_ino); - if (sbi->s_first_ino < EXT4_GOOD_OLD_FIRST_INO) { - ext4_msg(sb, KERN_ERR, "invalid first ino: %u", - sbi->s_first_ino); - goto failed_mount; - } - if ((sbi->s_inode_size < EXT4_GOOD_OLD_INODE_SIZE) || - (!is_power_of_2(sbi->s_inode_size)) || - (sbi->s_inode_size > blocksize)) { - ext4_msg(sb, KERN_ERR, - "unsupported inode size: %d", - sbi->s_inode_size); - goto failed_mount; - } - /* - * i_atime_extra is the last extra field available for [acm]times in - * struct ext4_inode. Checking for that field should suffice to ensure - * we have extra space for all three. - */ - if (sbi->s_inode_size >= offsetof(struct ext4_inode, i_atime_extra) + - sizeof(((struct ext4_inode *)0)->i_atime_extra)) { - sb->s_time_gran = 1; - sb->s_time_max = EXT4_EXTRA_TIMESTAMP_MAX; - } else { - sb->s_time_gran = NSEC_PER_SEC; - sb->s_time_max = EXT4_NON_EXTRA_TIMESTAMP_MAX; - } - - sb->s_time_min = EXT4_TIMESTAMP_MIN; - } - sbi->s_desc_size = le16_to_cpu(es->s_desc_size); if (ext4_has_feature_64bit(sb)) { if (sbi->s_desc_size < EXT4_MIN_DESC_SIZE_64BIT || @@ -4517,8 +4516,6 @@ no_journal: } else if (ret) goto failed_mount4a; - ext4_clamp_want_extra_isize(sb); - ext4_set_resv_clusters(sb); err = ext4_setup_system_zone(sb); @@ -5306,8 +5303,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) goto restore_opts; } - ext4_clamp_want_extra_isize(sb); - if ((old_opts.s_mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) ^ test_opt(sb, JOURNAL_CHECKSUM)) { ext4_msg(sb, KERN_ERR, "changing journal_checksum " diff --git a/fs/inode.c b/fs/inode.c index fef457a42882..96d62d97694e 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -676,6 +676,7 @@ int invalidate_inodes(struct super_block *sb, bool kill_dirty) struct inode *inode, *next; LIST_HEAD(dispose); +again: spin_lock(&sb->s_inode_list_lock); list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) { spin_lock(&inode->i_lock); @@ -698,6 +699,12 @@ int invalidate_inodes(struct super_block *sb, bool kill_dirty) inode_lru_list_del(inode); spin_unlock(&inode->i_lock); list_add(&inode->i_lru, &dispose); + if (need_resched()) { + spin_unlock(&sb->s_inode_list_lock); + cond_resched(); + dispose_list(&dispose); + goto again; + } } spin_unlock(&sb->s_inode_list_lock); diff --git a/fs/io-wq.c b/fs/io-wq.c index 90c4978781fb..11e80b7252a8 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -948,7 +948,7 @@ static enum io_wq_cancel io_wqe_cancel_work(struct io_wqe *wqe, /* * Now check if a free (going busy) or busy worker has the work * currently running. If we find it there, we'll return CANCEL_RUNNING - * as an indication that we attempte to signal cancellation. The + * as an indication that we attempt to signal cancellation. The * completion will run normally in this case. */ rcu_read_lock(); diff --git a/fs/io-wq.h b/fs/io-wq.h index fb993b2bd0ef..3f5e356de980 100644 --- a/fs/io-wq.h +++ b/fs/io-wq.h @@ -120,6 +120,10 @@ static inline void io_wq_worker_sleeping(struct task_struct *tsk) static inline void io_wq_worker_running(struct task_struct *tsk) { } -#endif /* CONFIG_IO_WQ */ +#endif -#endif /* INTERNAL_IO_WQ_H */ +static inline bool io_wq_current_is_worker(void) +{ + return in_task() && (current->flags & PF_IO_WORKER); +} +#endif diff --git a/fs/io_uring.c b/fs/io_uring.c index 9b1833fedc5c..6f084e3cf835 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -289,7 +289,10 @@ struct io_ring_ctx { */ struct io_poll_iocb { struct file *file; - struct wait_queue_head *head; + union { + struct wait_queue_head *head; + u64 addr; + }; __poll_t events; bool done; bool canceled; @@ -304,6 +307,31 @@ struct io_timeout_data { u32 seq_offset; }; +struct io_accept { + struct file *file; + struct sockaddr __user *addr; + int __user *addr_len; + int flags; +}; + +struct io_sync { + struct file *file; + loff_t len; + loff_t off; + int flags; +}; + +struct io_cancel { + struct file *file; + u64 addr; +}; + +struct io_timeout { + struct file *file; + u64 addr; + int flags; +}; + struct io_async_connect { struct sockaddr_storage address; }; @@ -343,6 +371,10 @@ struct io_kiocb { struct file *file; struct kiocb rw; struct io_poll_iocb poll; + struct io_accept accept; + struct io_sync sync; + struct io_cancel cancel; + struct io_timeout timeout; }; const struct io_uring_sqe *sqe; @@ -352,6 +384,7 @@ struct io_kiocb { bool has_user; bool in_async; bool needs_fixed_file; + u8 opcode; struct io_ring_ctx *ctx; union { @@ -378,6 +411,7 @@ struct io_kiocb { #define REQ_F_INFLIGHT 16384 /* on inflight list */ #define REQ_F_COMP_LOCKED 32768 /* completion under lock */ #define REQ_F_HARDLINK 65536 /* doesn't sever on completion < 0 */ +#define REQ_F_PREPPED 131072 /* request already opcode prepared */ u64 user_data; u32 result; u32 sequence; @@ -564,12 +598,10 @@ static void __io_commit_cqring(struct io_ring_ctx *ctx) } } -static inline bool io_sqe_needs_user(const struct io_uring_sqe *sqe) +static inline bool io_req_needs_user(struct io_kiocb *req) { - u8 opcode = READ_ONCE(sqe->opcode); - - return !(opcode == IORING_OP_READ_FIXED || - opcode == IORING_OP_WRITE_FIXED); + return !(req->opcode == IORING_OP_READ_FIXED || + req->opcode == IORING_OP_WRITE_FIXED); } static inline bool io_prep_async_work(struct io_kiocb *req, @@ -578,7 +610,7 @@ static inline bool io_prep_async_work(struct io_kiocb *req, bool do_hashed = false; if (req->sqe) { - switch (req->sqe->opcode) { + switch (req->opcode) { case IORING_OP_WRITEV: case IORING_OP_WRITE_FIXED: /* only regular files should be hashed for writes */ @@ -601,7 +633,7 @@ static inline bool io_prep_async_work(struct io_kiocb *req, req->work.flags |= IO_WQ_WORK_UNBOUND; break; } - if (io_sqe_needs_user(req->sqe)) + if (io_req_needs_user(req)) req->work.flags |= IO_WQ_WORK_NEEDS_USER; } @@ -972,7 +1004,7 @@ static void io_fail_links(struct io_kiocb *req) trace_io_uring_fail_link(req, link); if ((req->flags & REQ_F_LINK_TIMEOUT) && - link->sqe->opcode == IORING_OP_LINK_TIMEOUT) { + link->opcode == IORING_OP_LINK_TIMEOUT) { io_link_cancel_timeout(link); } else { io_cqring_fill_event(link, -ECANCELED); @@ -1178,7 +1210,7 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events, } /* - * Poll for a mininum of 'min' events. Note that if min == 0 we consider that a + * Poll for a minimum of 'min' events. Note that if min == 0 we consider that a * non-spinning poll check - we'll still enter the driver poll loop, but only * as a non-spinning completion check. */ @@ -1615,7 +1647,7 @@ static ssize_t io_import_iovec(int rw, struct io_kiocb *req, * for that purpose and instead let the caller pass in the read/write * flag. */ - opcode = READ_ONCE(sqe->opcode); + opcode = req->opcode; if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) { *iovec = NULL; return io_import_fixed(req->ctx, rw, sqe, iter); @@ -1701,7 +1733,7 @@ static ssize_t loop_rw_iter(int rw, struct file *file, struct kiocb *kiocb, return ret; } -static void io_req_map_io(struct io_kiocb *req, ssize_t io_size, +static void io_req_map_rw(struct io_kiocb *req, ssize_t io_size, struct iovec *iovec, struct iovec *fast_iov, struct iov_iter *iter) { @@ -1715,19 +1747,39 @@ static void io_req_map_io(struct io_kiocb *req, ssize_t io_size, } } -static int io_setup_async_io(struct io_kiocb *req, ssize_t io_size, - struct iovec *iovec, struct iovec *fast_iov, - struct iov_iter *iter) +static int io_alloc_async_ctx(struct io_kiocb *req) { req->io = kmalloc(sizeof(*req->io), GFP_KERNEL); if (req->io) { - io_req_map_io(req, io_size, iovec, fast_iov, iter); memcpy(&req->io->sqe, req->sqe, sizeof(req->io->sqe)); req->sqe = &req->io->sqe; return 0; } - return -ENOMEM; + return 1; +} + +static void io_rw_async(struct io_wq_work **workptr) +{ + struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work); + struct iovec *iov = NULL; + + if (req->io->rw.iov != req->io->rw.fast_iov) + iov = req->io->rw.iov; + io_wq_submit_work(workptr); + kfree(iov); +} + +static int io_setup_async_rw(struct io_kiocb *req, ssize_t io_size, + struct iovec *iovec, struct iovec *fast_iov, + struct iov_iter *iter) +{ + if (!req->io && io_alloc_async_ctx(req)) + return -ENOMEM; + + io_req_map_rw(req, io_size, iovec, fast_iov, iter); + req->work.func = io_rw_async; + return 0; } static int io_read_prep(struct io_kiocb *req, struct iovec **iovec, @@ -1765,6 +1817,10 @@ static int io_read(struct io_kiocb *req, struct io_kiocb **nxt, return ret; } + /* Ensure we clear previously set non-block flag */ + if (!force_nonblock) + req->rw.ki_flags &= ~IOCB_NOWAIT; + file = req->file; io_size = ret; if (req->flags & REQ_F_LINK) @@ -1806,7 +1862,7 @@ static int io_read(struct io_kiocb *req, struct io_kiocb **nxt, kiocb_done(kiocb, ret2, nxt, req->in_async); } else { copy_iov: - ret = io_setup_async_io(req, io_size, iovec, + ret = io_setup_async_rw(req, io_size, iovec, inline_vecs, &iter); if (ret) goto out_free; @@ -1814,7 +1870,8 @@ copy_iov: } } out_free: - kfree(iovec); + if (!io_wq_current_is_worker()) + kfree(iovec); return ret; } @@ -1853,6 +1910,10 @@ static int io_write(struct io_kiocb *req, struct io_kiocb **nxt, return ret; } + /* Ensure we clear previously set non-block flag */ + if (!force_nonblock) + req->rw.ki_flags &= ~IOCB_NOWAIT; + file = kiocb->ki_filp; io_size = ret; if (req->flags & REQ_F_LINK) @@ -1900,7 +1961,7 @@ static int io_write(struct io_kiocb *req, struct io_kiocb **nxt, kiocb_done(kiocb, ret2, nxt, req->in_async); } else { copy_iov: - ret = io_setup_async_io(req, io_size, iovec, + ret = io_setup_async_rw(req, io_size, iovec, inline_vecs, &iter); if (ret) goto out_free; @@ -1908,7 +1969,8 @@ copy_iov: } } out_free: - kfree(iovec); + if (!io_wq_current_is_worker()) + kfree(iovec); return ret; } @@ -1927,10 +1989,13 @@ static int io_nop(struct io_kiocb *req) return 0; } -static int io_prep_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe) +static int io_prep_fsync(struct io_kiocb *req) { + const struct io_uring_sqe *sqe = req->sqe; struct io_ring_ctx *ctx = req->ctx; + if (req->flags & REQ_F_PREPPED) + return 0; if (!req->file) return -EBADF; @@ -1939,46 +2004,80 @@ static int io_prep_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index)) return -EINVAL; + req->sync.flags = READ_ONCE(sqe->fsync_flags); + if (unlikely(req->sync.flags & ~IORING_FSYNC_DATASYNC)) + return -EINVAL; + + req->sync.off = READ_ONCE(sqe->off); + req->sync.len = READ_ONCE(sqe->len); + req->flags |= REQ_F_PREPPED; return 0; } -static int io_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe, - struct io_kiocb **nxt, bool force_nonblock) +static bool io_req_cancelled(struct io_kiocb *req) { - loff_t sqe_off = READ_ONCE(sqe->off); - loff_t sqe_len = READ_ONCE(sqe->len); - loff_t end = sqe_off + sqe_len; - unsigned fsync_flags; + if (req->work.flags & IO_WQ_WORK_CANCEL) { + req_set_fail_links(req); + io_cqring_add_event(req, -ECANCELED); + io_put_req(req); + return true; + } + + return false; +} + +static void io_fsync_finish(struct io_wq_work **workptr) +{ + struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work); + loff_t end = req->sync.off + req->sync.len; + struct io_kiocb *nxt = NULL; int ret; - fsync_flags = READ_ONCE(sqe->fsync_flags); - if (unlikely(fsync_flags & ~IORING_FSYNC_DATASYNC)) - return -EINVAL; + if (io_req_cancelled(req)) + return; + + ret = vfs_fsync_range(req->rw.ki_filp, req->sync.off, + end > 0 ? end : LLONG_MAX, + req->sync.flags & IORING_FSYNC_DATASYNC); + if (ret < 0) + req_set_fail_links(req); + io_cqring_add_event(req, ret); + io_put_req_find_next(req, &nxt); + if (nxt) + *workptr = &nxt->work; +} + +static int io_fsync(struct io_kiocb *req, struct io_kiocb **nxt, + bool force_nonblock) +{ + struct io_wq_work *work, *old_work; + int ret; - ret = io_prep_fsync(req, sqe); + ret = io_prep_fsync(req); if (ret) return ret; /* fsync always requires a blocking context */ - if (force_nonblock) + if (force_nonblock) { + io_put_req(req); + req->work.func = io_fsync_finish; return -EAGAIN; + } - ret = vfs_fsync_range(req->rw.ki_filp, sqe_off, - end > 0 ? end : LLONG_MAX, - fsync_flags & IORING_FSYNC_DATASYNC); - - if (ret < 0) - req_set_fail_links(req); - io_cqring_add_event(req, ret); - io_put_req_find_next(req, nxt); + work = old_work = &req->work; + io_fsync_finish(&work); + if (work && work != old_work) + *nxt = container_of(work, struct io_kiocb, work); return 0; } -static int io_prep_sfr(struct io_kiocb *req, const struct io_uring_sqe *sqe) +static int io_prep_sfr(struct io_kiocb *req) { + const struct io_uring_sqe *sqe = req->sqe; struct io_ring_ctx *ctx = req->ctx; - int ret = 0; + if (req->flags & REQ_F_PREPPED) + return 0; if (!req->file) return -EBADF; @@ -1987,39 +2086,68 @@ static int io_prep_sfr(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index)) return -EINVAL; - return ret; + req->sync.off = READ_ONCE(sqe->off); + req->sync.len = READ_ONCE(sqe->len); + req->sync.flags = READ_ONCE(sqe->sync_range_flags); + req->flags |= REQ_F_PREPPED; + return 0; } -static int io_sync_file_range(struct io_kiocb *req, - const struct io_uring_sqe *sqe, - struct io_kiocb **nxt, +static void io_sync_file_range_finish(struct io_wq_work **workptr) +{ + struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work); + struct io_kiocb *nxt = NULL; + int ret; + + if (io_req_cancelled(req)) + return; + + ret = sync_file_range(req->rw.ki_filp, req->sync.off, req->sync.len, + req->sync.flags); + if (ret < 0) + req_set_fail_links(req); + io_cqring_add_event(req, ret); + io_put_req_find_next(req, &nxt); + if (nxt) + *workptr = &nxt->work; +} + +static int io_sync_file_range(struct io_kiocb *req, struct io_kiocb **nxt, bool force_nonblock) { - loff_t sqe_off; - loff_t sqe_len; - unsigned flags; + struct io_wq_work *work, *old_work; int ret; - ret = io_prep_sfr(req, sqe); + ret = io_prep_sfr(req); if (ret) return ret; /* sync_file_range always requires a blocking context */ - if (force_nonblock) + if (force_nonblock) { + io_put_req(req); + req->work.func = io_sync_file_range_finish; return -EAGAIN; + } - sqe_off = READ_ONCE(sqe->off); - sqe_len = READ_ONCE(sqe->len); - flags = READ_ONCE(sqe->sync_range_flags); + work = old_work = &req->work; + io_sync_file_range_finish(&work); + if (work && work != old_work) + *nxt = container_of(work, struct io_kiocb, work); + return 0; +} - ret = sync_file_range(req->rw.ki_filp, sqe_off, sqe_len, flags); +#if defined(CONFIG_NET) +static void io_sendrecv_async(struct io_wq_work **workptr) +{ + struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work); + struct iovec *iov = NULL; - if (ret < 0) - req_set_fail_links(req); - io_cqring_add_event(req, ret); - io_put_req_find_next(req, nxt); - return 0; + if (req->io->rw.iov != req->io->rw.fast_iov) + iov = req->io->msg.iov; + io_wq_submit_work(workptr); + kfree(iov); } +#endif static int io_sendmsg_prep(struct io_kiocb *req, struct io_async_ctx *io) { @@ -2037,10 +2165,12 @@ static int io_sendmsg_prep(struct io_kiocb *req, struct io_async_ctx *io) #endif } -static int io_sendmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe, - struct io_kiocb **nxt, bool force_nonblock) +static int io_sendmsg(struct io_kiocb *req, struct io_kiocb **nxt, + bool force_nonblock) { #if defined(CONFIG_NET) + const struct io_uring_sqe *sqe = req->sqe; + struct io_async_msghdr *kmsg = NULL; struct socket *sock; int ret; @@ -2049,9 +2179,8 @@ static int io_sendmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe, sock = sock_from_file(req->file, &ret); if (sock) { - struct io_async_ctx io, *copy; + struct io_async_ctx io; struct sockaddr_storage addr; - struct msghdr *kmsg; unsigned flags; flags = READ_ONCE(sqe->msg_flags); @@ -2061,34 +2190,37 @@ static int io_sendmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe, flags |= MSG_DONTWAIT; if (req->io) { - kmsg = &req->io->msg.msg; - kmsg->msg_name = &addr; + kmsg = &req->io->msg; + kmsg->msg.msg_name = &addr; + /* if iov is set, it's allocated already */ + if (!kmsg->iov) + kmsg->iov = kmsg->fast_iov; + kmsg->msg.msg_iter.iov = kmsg->iov; } else { - kmsg = &io.msg.msg; - kmsg->msg_name = &addr; + kmsg = &io.msg; + kmsg->msg.msg_name = &addr; ret = io_sendmsg_prep(req, &io); if (ret) goto out; } - ret = __sys_sendmsg_sock(sock, kmsg, flags); + ret = __sys_sendmsg_sock(sock, &kmsg->msg, flags); if (force_nonblock && ret == -EAGAIN) { - copy = kmalloc(sizeof(*copy), GFP_KERNEL); - if (!copy) { - ret = -ENOMEM; - goto out; - } - memcpy(©->msg, &io.msg, sizeof(copy->msg)); - req->io = copy; - memcpy(&req->io->sqe, req->sqe, sizeof(*req->sqe)); - req->sqe = &req->io->sqe; - return ret; + if (req->io) + return -EAGAIN; + if (io_alloc_async_ctx(req)) + return -ENOMEM; + memcpy(&req->io->msg, &io.msg, sizeof(io.msg)); + req->work.func = io_sendrecv_async; + return -EAGAIN; } if (ret == -ERESTARTSYS) ret = -EINTR; } out: + if (!io_wq_current_is_worker() && kmsg && kmsg->iov != kmsg->fast_iov) + kfree(kmsg->iov); io_cqring_add_event(req, ret); if (ret < 0) req_set_fail_links(req); @@ -2116,10 +2248,12 @@ static int io_recvmsg_prep(struct io_kiocb *req, struct io_async_ctx *io) #endif } -static int io_recvmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe, - struct io_kiocb **nxt, bool force_nonblock) +static int io_recvmsg(struct io_kiocb *req, struct io_kiocb **nxt, + bool force_nonblock) { #if defined(CONFIG_NET) + const struct io_uring_sqe *sqe = req->sqe; + struct io_async_msghdr *kmsg = NULL; struct socket *sock; int ret; @@ -2129,9 +2263,8 @@ static int io_recvmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe, sock = sock_from_file(req->file, &ret); if (sock) { struct user_msghdr __user *msg; - struct io_async_ctx io, *copy; + struct io_async_ctx io; struct sockaddr_storage addr; - struct msghdr *kmsg; unsigned flags; flags = READ_ONCE(sqe->msg_flags); @@ -2143,34 +2276,37 @@ static int io_recvmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe, msg = (struct user_msghdr __user *) (unsigned long) READ_ONCE(sqe->addr); if (req->io) { - kmsg = &req->io->msg.msg; - kmsg->msg_name = &addr; + kmsg = &req->io->msg; + kmsg->msg.msg_name = &addr; + /* if iov is set, it's allocated already */ + if (!kmsg->iov) + kmsg->iov = kmsg->fast_iov; + kmsg->msg.msg_iter.iov = kmsg->iov; } else { - kmsg = &io.msg.msg; - kmsg->msg_name = &addr; + kmsg = &io.msg; + kmsg->msg.msg_name = &addr; ret = io_recvmsg_prep(req, &io); if (ret) goto out; } - ret = __sys_recvmsg_sock(sock, kmsg, msg, io.msg.uaddr, flags); + ret = __sys_recvmsg_sock(sock, &kmsg->msg, msg, kmsg->uaddr, flags); if (force_nonblock && ret == -EAGAIN) { - copy = kmalloc(sizeof(*copy), GFP_KERNEL); - if (!copy) { - ret = -ENOMEM; - goto out; - } - memcpy(copy, &io, sizeof(*copy)); - req->io = copy; - memcpy(&req->io->sqe, req->sqe, sizeof(*req->sqe)); - req->sqe = &req->io->sqe; - return ret; + if (req->io) + return -EAGAIN; + if (io_alloc_async_ctx(req)) + return -ENOMEM; + memcpy(&req->io->msg, &io.msg, sizeof(io.msg)); + req->work.func = io_sendrecv_async; + return -EAGAIN; } if (ret == -ERESTARTSYS) ret = -EINTR; } out: + if (!io_wq_current_is_worker() && kmsg && kmsg->iov != kmsg->fast_iov) + kfree(kmsg->iov); io_cqring_add_event(req, ret); if (ret < 0) req_set_fail_links(req); @@ -2181,30 +2317,44 @@ out: #endif } -static int io_accept(struct io_kiocb *req, const struct io_uring_sqe *sqe, - struct io_kiocb **nxt, bool force_nonblock) +static int io_accept_prep(struct io_kiocb *req) { #if defined(CONFIG_NET) - struct sockaddr __user *addr; - int __user *addr_len; - unsigned file_flags; - int flags, ret; + const struct io_uring_sqe *sqe = req->sqe; + struct io_accept *accept = &req->accept; + + if (req->flags & REQ_F_PREPPED) + return 0; if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL))) return -EINVAL; if (sqe->ioprio || sqe->len || sqe->buf_index) return -EINVAL; - addr = (struct sockaddr __user *) (unsigned long) READ_ONCE(sqe->addr); - addr_len = (int __user *) (unsigned long) READ_ONCE(sqe->addr2); - flags = READ_ONCE(sqe->accept_flags); - file_flags = force_nonblock ? O_NONBLOCK : 0; + accept->addr = (struct sockaddr __user *) + (unsigned long) READ_ONCE(sqe->addr); + accept->addr_len = (int __user *) (unsigned long) READ_ONCE(sqe->addr2); + accept->flags = READ_ONCE(sqe->accept_flags); + req->flags |= REQ_F_PREPPED; + return 0; +#else + return -EOPNOTSUPP; +#endif +} - ret = __sys_accept4_file(req->file, file_flags, addr, addr_len, flags); - if (ret == -EAGAIN && force_nonblock) { - req->work.flags |= IO_WQ_WORK_NEEDS_FILES; +#if defined(CONFIG_NET) +static int __io_accept(struct io_kiocb *req, struct io_kiocb **nxt, + bool force_nonblock) +{ + struct io_accept *accept = &req->accept; + unsigned file_flags; + int ret; + + file_flags = force_nonblock ? O_NONBLOCK : 0; + ret = __sys_accept4_file(req->file, file_flags, accept->addr, + accept->addr_len, accept->flags); + if (ret == -EAGAIN && force_nonblock) return -EAGAIN; - } if (ret == -ERESTARTSYS) ret = -EINTR; if (ret < 0) @@ -2212,6 +2362,39 @@ static int io_accept(struct io_kiocb *req, const struct io_uring_sqe *sqe, io_cqring_add_event(req, ret); io_put_req_find_next(req, nxt); return 0; +} + +static void io_accept_finish(struct io_wq_work **workptr) +{ + struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work); + struct io_kiocb *nxt = NULL; + + if (io_req_cancelled(req)) + return; + __io_accept(req, &nxt, false); + if (nxt) + *workptr = &nxt->work; +} +#endif + +static int io_accept(struct io_kiocb *req, struct io_kiocb **nxt, + bool force_nonblock) +{ +#if defined(CONFIG_NET) + int ret; + + ret = io_accept_prep(req); + if (ret) + return ret; + + ret = __io_accept(req, nxt, force_nonblock); + if (ret == -EAGAIN && force_nonblock) { + req->work.func = io_accept_finish; + req->work.flags |= IO_WQ_WORK_NEEDS_FILES; + io_put_req(req); + return -EAGAIN; + } + return 0; #else return -EOPNOTSUPP; #endif @@ -2232,10 +2415,11 @@ static int io_connect_prep(struct io_kiocb *req, struct io_async_ctx *io) #endif } -static int io_connect(struct io_kiocb *req, const struct io_uring_sqe *sqe, - struct io_kiocb **nxt, bool force_nonblock) +static int io_connect(struct io_kiocb *req, struct io_kiocb **nxt, + bool force_nonblock) { #if defined(CONFIG_NET) + const struct io_uring_sqe *sqe = req->sqe; struct io_async_ctx __io, *io; unsigned file_flags; int addr_len, ret; @@ -2260,15 +2444,13 @@ static int io_connect(struct io_kiocb *req, const struct io_uring_sqe *sqe, ret = __sys_connect_file(req->file, &io->connect.address, addr_len, file_flags); if ((ret == -EAGAIN || ret == -EINPROGRESS) && force_nonblock) { - io = kmalloc(sizeof(*io), GFP_KERNEL); - if (!io) { + if (req->io) + return -EAGAIN; + if (io_alloc_async_ctx(req)) { ret = -ENOMEM; goto out; } - memcpy(&io->connect, &__io.connect, sizeof(io->connect)); - req->io = io; - memcpy(&io->sqe, req->sqe, sizeof(*req->sqe)); - req->sqe = &io->sqe; + memcpy(&req->io->connect, &__io.connect, sizeof(__io.connect)); return -EAGAIN; } if (ret == -ERESTARTSYS) @@ -2331,23 +2513,40 @@ static int io_poll_cancel(struct io_ring_ctx *ctx, __u64 sqe_addr) return -ENOENT; } +static int io_poll_remove_prep(struct io_kiocb *req) +{ + const struct io_uring_sqe *sqe = req->sqe; + + if (req->flags & REQ_F_PREPPED) + return 0; + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (sqe->ioprio || sqe->off || sqe->len || sqe->buf_index || + sqe->poll_events) + return -EINVAL; + + req->poll.addr = READ_ONCE(sqe->addr); + req->flags |= REQ_F_PREPPED; + return 0; +} + /* * Find a running poll command that matches one specified in sqe->addr, * and remove it if found. */ -static int io_poll_remove(struct io_kiocb *req, const struct io_uring_sqe *sqe) +static int io_poll_remove(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; + u64 addr; int ret; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (sqe->ioprio || sqe->off || sqe->len || sqe->buf_index || - sqe->poll_events) - return -EINVAL; + ret = io_poll_remove_prep(req); + if (ret) + return ret; + addr = req->poll.addr; spin_lock_irq(&ctx->completion_lock); - ret = io_poll_cancel(ctx, READ_ONCE(sqe->addr)); + ret = io_poll_cancel(ctx, addr); spin_unlock_irq(&ctx->completion_lock); io_cqring_add_event(req, ret); @@ -2482,16 +2681,14 @@ static void io_poll_req_insert(struct io_kiocb *req) hlist_add_head(&req->hash_node, list); } -static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe, - struct io_kiocb **nxt) +static int io_poll_add_prep(struct io_kiocb *req) { + const struct io_uring_sqe *sqe = req->sqe; struct io_poll_iocb *poll = &req->poll; - struct io_ring_ctx *ctx = req->ctx; - struct io_poll_table ipt; - bool cancel = false; - __poll_t mask; u16 events; + if (req->flags & REQ_F_PREPPED) + return 0; if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (sqe->addr || sqe->ioprio || sqe->off || sqe->len || sqe->buf_index) @@ -2499,10 +2696,26 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe, if (!poll->file) return -EBADF; - req->io = NULL; - INIT_IO_WORK(&req->work, io_poll_complete_work); + req->flags |= REQ_F_PREPPED; events = READ_ONCE(sqe->poll_events); poll->events = demangle_poll(events) | EPOLLERR | EPOLLHUP; + return 0; +} + +static int io_poll_add(struct io_kiocb *req, struct io_kiocb **nxt) +{ + struct io_poll_iocb *poll = &req->poll; + struct io_ring_ctx *ctx = req->ctx; + struct io_poll_table ipt; + bool cancel = false; + __poll_t mask; + int ret; + + ret = io_poll_add_prep(req); + if (ret) + return ret; + + INIT_IO_WORK(&req->work, io_poll_complete_work); INIT_HLIST_NODE(&req->hash_node); poll->head = NULL; @@ -2573,7 +2786,7 @@ static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer) /* * Adjust the reqs sequence before the current one because it - * will consume a slot in the cq_ring and the the cq_tail + * will consume a slot in the cq_ring and the cq_tail * pointer will be increased, otherwise other timeout reqs may * return in advance without waiting for enough wait_nr. */ @@ -2619,26 +2832,40 @@ static int io_timeout_cancel(struct io_ring_ctx *ctx, __u64 user_data) return 0; } +static int io_timeout_remove_prep(struct io_kiocb *req) +{ + const struct io_uring_sqe *sqe = req->sqe; + + if (req->flags & REQ_F_PREPPED) + return 0; + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (sqe->flags || sqe->ioprio || sqe->buf_index || sqe->len) + return -EINVAL; + + req->timeout.addr = READ_ONCE(sqe->addr); + req->timeout.flags = READ_ONCE(sqe->timeout_flags); + if (req->timeout.flags) + return -EINVAL; + + req->flags |= REQ_F_PREPPED; + return 0; +} + /* * Remove or update an existing timeout command */ -static int io_timeout_remove(struct io_kiocb *req, - const struct io_uring_sqe *sqe) +static int io_timeout_remove(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; - unsigned flags; int ret; - if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (sqe->flags || sqe->ioprio || sqe->buf_index || sqe->len) - return -EINVAL; - flags = READ_ONCE(sqe->timeout_flags); - if (flags) - return -EINVAL; + ret = io_timeout_remove_prep(req); + if (ret) + return ret; spin_lock_irq(&ctx->completion_lock); - ret = io_timeout_cancel(ctx, READ_ONCE(sqe->addr)); + ret = io_timeout_cancel(ctx, req->timeout.addr); io_cqring_fill_event(req, ret); io_commit_cqring(ctx); @@ -2680,31 +2907,25 @@ static int io_timeout_prep(struct io_kiocb *req, struct io_async_ctx *io, data->mode = HRTIMER_MODE_REL; hrtimer_init(&data->timer, CLOCK_MONOTONIC, data->mode); - req->io = io; return 0; } -static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe) +static int io_timeout(struct io_kiocb *req) { + const struct io_uring_sqe *sqe = req->sqe; unsigned count; struct io_ring_ctx *ctx = req->ctx; struct io_timeout_data *data; - struct io_async_ctx *io; struct list_head *entry; unsigned span = 0; + int ret; - io = req->io; - if (!io) { - int ret; - - io = kmalloc(sizeof(*io), GFP_KERNEL); - if (!io) + if (!req->io) { + if (io_alloc_async_ctx(req)) return -ENOMEM; - ret = io_timeout_prep(req, io, false); - if (ret) { - kfree(io); + ret = io_timeout_prep(req, req->io, false); + if (ret) return ret; - } } data = &req->io->timeout; @@ -2831,38 +3052,79 @@ done: io_put_req_find_next(req, nxt); } -static int io_async_cancel(struct io_kiocb *req, const struct io_uring_sqe *sqe, - struct io_kiocb **nxt) +static int io_async_cancel_prep(struct io_kiocb *req) { - struct io_ring_ctx *ctx = req->ctx; + const struct io_uring_sqe *sqe = req->sqe; - if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) + if (req->flags & REQ_F_PREPPED) + return 0; + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (sqe->flags || sqe->ioprio || sqe->off || sqe->len || sqe->cancel_flags) return -EINVAL; - io_async_find_and_cancel(ctx, req, READ_ONCE(sqe->addr), nxt, 0); + req->flags |= REQ_F_PREPPED; + req->cancel.addr = READ_ONCE(sqe->addr); + return 0; +} + +static int io_async_cancel(struct io_kiocb *req, struct io_kiocb **nxt) +{ + struct io_ring_ctx *ctx = req->ctx; + int ret; + + ret = io_async_cancel_prep(req); + if (ret) + return ret; + + io_async_find_and_cancel(ctx, req, req->cancel.addr, nxt, 0); return 0; } -static int io_req_defer_prep(struct io_kiocb *req, struct io_async_ctx *io) +static int io_req_defer_prep(struct io_kiocb *req) { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; + struct io_async_ctx *io = req->io; struct iov_iter iter; - ssize_t ret; - - memcpy(&io->sqe, req->sqe, sizeof(io->sqe)); - req->sqe = &io->sqe; + ssize_t ret = 0; - switch (io->sqe.opcode) { + switch (req->opcode) { + case IORING_OP_NOP: + break; case IORING_OP_READV: case IORING_OP_READ_FIXED: + /* ensure prep does right import */ + req->io = NULL; ret = io_read_prep(req, &iovec, &iter, true); + req->io = io; + if (ret < 0) + break; + io_req_map_rw(req, ret, iovec, inline_vecs, &iter); + ret = 0; break; case IORING_OP_WRITEV: case IORING_OP_WRITE_FIXED: + /* ensure prep does right import */ + req->io = NULL; ret = io_write_prep(req, &iovec, &iter, true); + req->io = io; + if (ret < 0) + break; + io_req_map_rw(req, ret, iovec, inline_vecs, &iter); + ret = 0; + break; + case IORING_OP_POLL_ADD: + ret = io_poll_add_prep(req); + break; + case IORING_OP_POLL_REMOVE: + ret = io_poll_remove_prep(req); + break; + case IORING_OP_FSYNC: + ret = io_prep_fsync(req); + break; + case IORING_OP_SYNC_FILE_RANGE: + ret = io_prep_sfr(req); break; case IORING_OP_SENDMSG: ret = io_sendmsg_prep(req, io); @@ -2874,41 +3136,45 @@ static int io_req_defer_prep(struct io_kiocb *req, struct io_async_ctx *io) ret = io_connect_prep(req, io); break; case IORING_OP_TIMEOUT: - return io_timeout_prep(req, io, false); + ret = io_timeout_prep(req, io, false); + break; + case IORING_OP_TIMEOUT_REMOVE: + ret = io_timeout_remove_prep(req); + break; + case IORING_OP_ASYNC_CANCEL: + ret = io_async_cancel_prep(req); + break; case IORING_OP_LINK_TIMEOUT: - return io_timeout_prep(req, io, true); + ret = io_timeout_prep(req, io, true); + break; + case IORING_OP_ACCEPT: + ret = io_accept_prep(req); + break; default: - req->io = io; - return 0; + printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n", + req->opcode); + ret = -EINVAL; + break; } - if (ret < 0) - return ret; - - req->io = io; - io_req_map_io(req, ret, iovec, inline_vecs, &iter); - return 0; + return ret; } static int io_req_defer(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; - struct io_async_ctx *io; int ret; /* Still need defer if there is pending req in defer list. */ if (!req_need_defer(req) && list_empty(&ctx->defer_list)) return 0; - io = kmalloc(sizeof(*io), GFP_KERNEL); - if (!io) + if (io_alloc_async_ctx(req)) return -EAGAIN; - ret = io_req_defer_prep(req, io); - if (ret < 0) { - kfree(io); + ret = io_req_defer_prep(req); + if (ret < 0) return ret; - } spin_lock_irq(&ctx->completion_lock); if (!req_need_defer(req) && list_empty(&ctx->defer_list)) { @@ -2926,11 +3192,10 @@ __attribute__((nonnull)) static int io_issue_sqe(struct io_kiocb *req, struct io_kiocb **nxt, bool force_nonblock) { - int ret, opcode; struct io_ring_ctx *ctx = req->ctx; + int ret; - opcode = READ_ONCE(req->sqe->opcode); - switch (opcode) { + switch (req->opcode) { case IORING_OP_NOP: ret = io_nop(req); break; @@ -2951,37 +3216,37 @@ static int io_issue_sqe(struct io_kiocb *req, struct io_kiocb **nxt, ret = io_write(req, nxt, force_nonblock); break; case IORING_OP_FSYNC: - ret = io_fsync(req, req->sqe, nxt, force_nonblock); + ret = io_fsync(req, nxt, force_nonblock); break; case IORING_OP_POLL_ADD: - ret = io_poll_add(req, req->sqe, nxt); + ret = io_poll_add(req, nxt); break; case IORING_OP_POLL_REMOVE: - ret = io_poll_remove(req, req->sqe); + ret = io_poll_remove(req); break; case IORING_OP_SYNC_FILE_RANGE: - ret = io_sync_file_range(req, req->sqe, nxt, force_nonblock); + ret = io_sync_file_range(req, nxt, force_nonblock); break; case IORING_OP_SENDMSG: - ret = io_sendmsg(req, req->sqe, nxt, force_nonblock); + ret = io_sendmsg(req, nxt, force_nonblock); break; case IORING_OP_RECVMSG: - ret = io_recvmsg(req, req->sqe, nxt, force_nonblock); + ret = io_recvmsg(req, nxt, force_nonblock); break; case IORING_OP_TIMEOUT: - ret = io_timeout(req, req->sqe); + ret = io_timeout(req); break; case IORING_OP_TIMEOUT_REMOVE: - ret = io_timeout_remove(req, req->sqe); + ret = io_timeout_remove(req); break; case IORING_OP_ACCEPT: - ret = io_accept(req, req->sqe, nxt, force_nonblock); + ret = io_accept(req, nxt, force_nonblock); break; case IORING_OP_CONNECT: - ret = io_connect(req, req->sqe, nxt, force_nonblock); + ret = io_connect(req, nxt, force_nonblock); break; case IORING_OP_ASYNC_CANCEL: - ret = io_async_cancel(req, req->sqe, nxt); + ret = io_async_cancel(req, nxt); break; default: ret = -EINVAL; @@ -3017,9 +3282,6 @@ static void io_wq_submit_work(struct io_wq_work **workptr) struct io_kiocb *nxt = NULL; int ret = 0; - /* Ensure we clear previously set non-block flag */ - req->rw.ki_flags &= ~IOCB_NOWAIT; - if (work->flags & IO_WQ_WORK_CANCEL) ret = -ECANCELED; @@ -3067,11 +3329,9 @@ static bool io_req_op_valid(int op) return op >= IORING_OP_NOP && op < IORING_OP_LAST; } -static int io_op_needs_file(const struct io_uring_sqe *sqe) +static int io_req_needs_file(struct io_kiocb *req) { - int op = READ_ONCE(sqe->opcode); - - switch (op) { + switch (req->opcode) { case IORING_OP_NOP: case IORING_OP_POLL_REMOVE: case IORING_OP_TIMEOUT: @@ -3080,7 +3340,7 @@ static int io_op_needs_file(const struct io_uring_sqe *sqe) case IORING_OP_LINK_TIMEOUT: return 0; default: - if (io_req_op_valid(op)) + if (io_req_op_valid(req->opcode)) return 1; return -EINVAL; } @@ -3107,7 +3367,7 @@ static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req) if (flags & IOSQE_IO_DRAIN) req->flags |= REQ_F_IO_DRAIN; - ret = io_op_needs_file(req->sqe); + ret = io_req_needs_file(req); if (ret <= 0) return ret; @@ -3227,7 +3487,7 @@ static struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req) nxt = list_first_entry_or_null(&req->link_list, struct io_kiocb, link_list); - if (!nxt || nxt->sqe->opcode != IORING_OP_LINK_TIMEOUT) + if (!nxt || nxt->opcode != IORING_OP_LINK_TIMEOUT) return NULL; req->flags |= REQ_F_LINK_TIMEOUT; @@ -3329,8 +3589,6 @@ static bool io_submit_sqe(struct io_kiocb *req, struct io_submit_state *state, struct io_ring_ctx *ctx = req->ctx; int ret; - req->user_data = req->sqe->user_data; - /* enforce forwards compatibility on users */ if (unlikely(req->sqe->flags & ~SQE_VALID_FLAGS)) { ret = -EINVAL; @@ -3354,7 +3612,6 @@ err_req: */ if (*link) { struct io_kiocb *prev = *link; - struct io_async_ctx *io; if (req->sqe->flags & IOSQE_IO_DRAIN) (*link)->flags |= REQ_F_DRAIN_LINK | REQ_F_IO_DRAIN; @@ -3362,15 +3619,13 @@ err_req: if (req->sqe->flags & IOSQE_IO_HARDLINK) req->flags |= REQ_F_HARDLINK; - io = kmalloc(sizeof(*io), GFP_KERNEL); - if (!io) { + if (io_alloc_async_ctx(req)) { ret = -EAGAIN; goto err_req; } - ret = io_req_defer_prep(req, io); + ret = io_req_defer_prep(req); if (ret) { - kfree(io); /* fail even hard links since we don't submit */ prev->flags |= REQ_F_FAIL_LINK; goto err_req; @@ -3430,7 +3685,7 @@ static void io_commit_sqring(struct io_ring_ctx *ctx) } /* - * Fetch an sqe, if one is available. Note that s->sqe will point to memory + * Fetch an sqe, if one is available. Note that req->sqe will point to memory * that is mapped by userspace. This means that care needs to be taken to * ensure that reads are stable, as we cannot rely on userspace always * being a good citizen. If members of the sqe are validated and then later @@ -3465,6 +3720,8 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct io_kiocb *req) */ req->sequence = ctx->cached_sq_head; req->sqe = &ctx->sq_sqes[head]; + req->opcode = READ_ONCE(req->sqe->opcode); + req->user_data = READ_ONCE(req->sqe->user_data); ctx->cached_sq_head++; return true; } @@ -3510,7 +3767,7 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr, break; } - if (io_sqe_needs_user(req->sqe) && !*mm) { + if (io_req_needs_user(req) && !*mm) { mm_fault = mm_fault || !mmget_not_zero(ctx->sqo_mm); if (!mm_fault) { use_mm(ctx->sqo_mm); @@ -3526,15 +3783,14 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr, req->has_user = *mm != NULL; req->in_async = async; req->needs_fixed_file = async; - trace_io_uring_submit_sqe(ctx, req->sqe->user_data, - true, async); + trace_io_uring_submit_sqe(ctx, req->user_data, true, async); if (!io_submit_sqe(req, statep, &link)) break; /* * If previous wasn't linked and we have a linked command, * that's the end of the chain. Submit the previous link. */ - if (!(sqe_flags & IOSQE_IO_LINK) && link) { + if (!(sqe_flags & (IOSQE_IO_LINK|IOSQE_IO_HARDLINK)) && link) { io_queue_link_head(link); link = NULL; } @@ -3694,7 +3950,7 @@ static inline bool io_should_wake(struct io_wait_queue *iowq, bool noflush) struct io_ring_ctx *ctx = iowq->ctx; /* - * Wake up if we have enough events, or if a timeout occured since we + * Wake up if we have enough events, or if a timeout occurred since we * started waiting. For timeouts, we always want to return to userspace, * regardless of event count. */ @@ -4884,6 +5140,9 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, submitted = io_submit_sqes(ctx, to_submit, f.file, fd, &cur_mm, false); mutex_unlock(&ctx->uring_lock); + + if (submitted != to_submit) + goto out; } if (flags & IORING_ENTER_GETEVENTS) { unsigned nr_events = 0; @@ -4897,6 +5156,7 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, } } +out: percpu_ref_put(&ctx->refs); out_fput: fdput(f); diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index 3e77b728a22b..46f225580009 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -57,6 +57,9 @@ static void fsnotify_unmount_inodes(struct super_block *sb) * doing an __iget/iput with SB_ACTIVE clear would actually * evict all inodes with zero i_count from icache which is * unnecessarily violent and may in fact be illegal to do. + * However, we should have been called /after/ evict_inodes + * removed all zero refcount inodes, in any case. Test to + * be sure. */ if (!atomic_read(&inode->i_count)) { spin_unlock(&inode->i_lock); @@ -77,6 +80,7 @@ static void fsnotify_unmount_inodes(struct super_block *sb) iput_inode = inode; + cond_resched(); spin_lock(&sb->s_inode_list_lock); } spin_unlock(&sb->s_inode_list_lock); diff --git a/fs/pipe.c b/fs/pipe.c index 04d004ee2e8c..57502c3c0fba 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -581,7 +581,7 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) } wait_event_interruptible(pipe->wait, pipe_writable(pipe)); __pipe_lock(pipe); - was_empty = pipe_empty(head, pipe->tail); + was_empty = pipe_empty(pipe->head, pipe->tail); } out: __pipe_unlock(pipe); diff --git a/fs/proc/stat.c b/fs/proc/stat.c index 37bdbec5b402..fd931d3e77be 100644 --- a/fs/proc/stat.c +++ b/fs/proc/stat.c @@ -134,7 +134,7 @@ static int show_stat(struct seq_file *p, void *v) softirq += cpustat[CPUTIME_SOFTIRQ]; steal += cpustat[CPUTIME_STEAL]; guest += cpustat[CPUTIME_GUEST]; - guest_nice += cpustat[CPUTIME_USER]; + guest_nice += cpustat[CPUTIME_GUEST_NICE]; sum += kstat_cpu_irqs_sum(i); sum += arch_irq_stat_cpu(i); @@ -175,7 +175,7 @@ static int show_stat(struct seq_file *p, void *v) softirq = cpustat[CPUTIME_SOFTIRQ]; steal = cpustat[CPUTIME_STEAL]; guest = cpustat[CPUTIME_GUEST]; - guest_nice = cpustat[CPUTIME_USER]; + guest_nice = cpustat[CPUTIME_GUEST_NICE]; seq_printf(p, "cpu%d", i); seq_put_decimal_ull(p, " ", nsec_to_clock_t(user)); seq_put_decimal_ull(p, " ", nsec_to_clock_t(nice)); diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index b0688c02dc90..b6a4f692d345 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -984,6 +984,7 @@ static int add_dquot_ref(struct super_block *sb, int type) * later. */ old_inode = inode; + cond_resched(); spin_lock(&sb->s_inode_list_lock); } spin_unlock(&sb->s_inode_list_lock); diff --git a/fs/super.c b/fs/super.c index cfadab2cbf35..cd352530eca9 100644 --- a/fs/super.c +++ b/fs/super.c @@ -448,10 +448,12 @@ void generic_shutdown_super(struct super_block *sb) sync_filesystem(sb); sb->s_flags &= ~SB_ACTIVE; - fsnotify_sb_delete(sb); cgroup_writeback_umount(); + /* evict all inodes with zero refcount */ evict_inodes(sb); + /* only nonzero refcount inodes can have marks */ + fsnotify_sb_delete(sb); if (sb->s_dio_done_wq) { destroy_workqueue(sb->s_dio_done_wq); diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index c284e10af491..fc93fd88ec89 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -2248,24 +2248,32 @@ xfs_alloc_longest_free_extent( return pag->pagf_flcount > 0 || pag->pagf_longest > 0; } +/* + * Compute the minimum length of the AGFL in the given AG. If @pag is NULL, + * return the largest possible minimum length. + */ unsigned int xfs_alloc_min_freelist( struct xfs_mount *mp, struct xfs_perag *pag) { + /* AG btrees have at least 1 level. */ + static const uint8_t fake_levels[XFS_BTNUM_AGF] = {1, 1, 1}; + const uint8_t *levels = pag ? pag->pagf_levels : fake_levels; unsigned int min_free; + ASSERT(mp->m_ag_maxlevels > 0); + /* space needed by-bno freespace btree */ - min_free = min_t(unsigned int, pag->pagf_levels[XFS_BTNUM_BNOi] + 1, + min_free = min_t(unsigned int, levels[XFS_BTNUM_BNOi] + 1, mp->m_ag_maxlevels); /* space needed by-size freespace btree */ - min_free += min_t(unsigned int, pag->pagf_levels[XFS_BTNUM_CNTi] + 1, + min_free += min_t(unsigned int, levels[XFS_BTNUM_CNTi] + 1, mp->m_ag_maxlevels); /* space needed reverse mapping used space btree */ if (xfs_sb_version_hasrmapbt(&mp->m_sb)) - min_free += min_t(unsigned int, - pag->pagf_levels[XFS_BTNUM_RMAPi] + 1, - mp->m_rmap_maxlevels); + min_free += min_t(unsigned int, levels[XFS_BTNUM_RMAPi] + 1, + mp->m_rmap_maxlevels); return min_free; } diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index a9ad1f991ba3..4c2e046fbfad 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -4561,7 +4561,7 @@ xfs_bmapi_convert_delalloc( struct xfs_mount *mp = ip->i_mount; xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset); struct xfs_bmalloca bma = { NULL }; - u16 flags = 0; + uint16_t flags = 0; struct xfs_trans *tp; int error; @@ -5972,8 +5972,7 @@ xfs_bmap_insert_extents( goto del_cursor; } - if (XFS_IS_CORRUPT(mp, - stop_fsb >= got.br_startoff + got.br_blockcount)) { + if (XFS_IS_CORRUPT(mp, stop_fsb > got.br_startoff)) { error = -EFSCORRUPTED; goto del_cursor; } diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c index 0aa87cbde49e..dd6fcaaea318 100644 --- a/fs/xfs/libxfs/xfs_dir2.c +++ b/fs/xfs/libxfs/xfs_dir2.c @@ -724,3 +724,24 @@ xfs_dir2_namecheck( /* There shouldn't be any slashes or nulls here */ return !memchr(name, '/', length) && !memchr(name, 0, length); } + +xfs_dahash_t +xfs_dir2_hashname( + struct xfs_mount *mp, + struct xfs_name *name) +{ + if (unlikely(xfs_sb_version_hasasciici(&mp->m_sb))) + return xfs_ascii_ci_hashname(name); + return xfs_da_hashname(name->name, name->len); +} + +enum xfs_dacmp +xfs_dir2_compname( + struct xfs_da_args *args, + const unsigned char *name, + int len) +{ + if (unlikely(xfs_sb_version_hasasciici(&args->dp->i_mount->m_sb))) + return xfs_ascii_ci_compname(args, name, len); + return xfs_da_compname(args, name, len); +} diff --git a/fs/xfs/libxfs/xfs_dir2_priv.h b/fs/xfs/libxfs/xfs_dir2_priv.h index c031c53d0f0d..01ee0b926572 100644 --- a/fs/xfs/libxfs/xfs_dir2_priv.h +++ b/fs/xfs/libxfs/xfs_dir2_priv.h @@ -175,6 +175,12 @@ extern int xfs_dir2_sf_lookup(struct xfs_da_args *args); extern int xfs_dir2_sf_removename(struct xfs_da_args *args); extern int xfs_dir2_sf_replace(struct xfs_da_args *args); extern xfs_failaddr_t xfs_dir2_sf_verify(struct xfs_inode *ip); +int xfs_dir2_sf_entsize(struct xfs_mount *mp, + struct xfs_dir2_sf_hdr *hdr, int len); +void xfs_dir2_sf_put_ino(struct xfs_mount *mp, struct xfs_dir2_sf_hdr *hdr, + struct xfs_dir2_sf_entry *sfep, xfs_ino_t ino); +void xfs_dir2_sf_put_ftype(struct xfs_mount *mp, + struct xfs_dir2_sf_entry *sfep, uint8_t ftype); /* xfs_dir2_readdir.c */ extern int xfs_readdir(struct xfs_trans *tp, struct xfs_inode *dp, @@ -194,25 +200,8 @@ xfs_dir2_data_entsize( return round_up(len, XFS_DIR2_DATA_ALIGN); } -static inline xfs_dahash_t -xfs_dir2_hashname( - struct xfs_mount *mp, - struct xfs_name *name) -{ - if (unlikely(xfs_sb_version_hasasciici(&mp->m_sb))) - return xfs_ascii_ci_hashname(name); - return xfs_da_hashname(name->name, name->len); -} - -static inline enum xfs_dacmp -xfs_dir2_compname( - struct xfs_da_args *args, - const unsigned char *name, - int len) -{ - if (unlikely(xfs_sb_version_hasasciici(&args->dp->i_mount->m_sb))) - return xfs_ascii_ci_compname(args, name, len); - return xfs_da_compname(args, name, len); -} +xfs_dahash_t xfs_dir2_hashname(struct xfs_mount *mp, struct xfs_name *name); +enum xfs_dacmp xfs_dir2_compname(struct xfs_da_args *args, + const unsigned char *name, int len); #endif /* __XFS_DIR2_PRIV_H__ */ diff --git a/fs/xfs/libxfs/xfs_dir2_sf.c b/fs/xfs/libxfs/xfs_dir2_sf.c index 8b94d33d232f..7b7f6fb2ea3b 100644 --- a/fs/xfs/libxfs/xfs_dir2_sf.c +++ b/fs/xfs/libxfs/xfs_dir2_sf.c @@ -37,7 +37,7 @@ static void xfs_dir2_sf_check(xfs_da_args_t *args); static void xfs_dir2_sf_toino4(xfs_da_args_t *args); static void xfs_dir2_sf_toino8(xfs_da_args_t *args); -static int +int xfs_dir2_sf_entsize( struct xfs_mount *mp, struct xfs_dir2_sf_hdr *hdr, @@ -84,7 +84,7 @@ xfs_dir2_sf_get_ino( return get_unaligned_be64(from) & XFS_MAXINUMBER; } -static void +void xfs_dir2_sf_put_ino( struct xfs_mount *mp, struct xfs_dir2_sf_hdr *hdr, @@ -145,7 +145,7 @@ xfs_dir2_sf_get_ftype( return XFS_DIR3_FT_UNKNOWN; } -static void +void xfs_dir2_sf_put_ftype( struct xfs_mount *mp, struct xfs_dir2_sf_entry *sfep, diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index 988cde7744e6..5b759af4d165 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -2909,3 +2909,67 @@ xfs_ialloc_setup_geometry( else igeo->ialloc_align = 0; } + +/* Compute the location of the root directory inode that is laid out by mkfs. */ +xfs_ino_t +xfs_ialloc_calc_rootino( + struct xfs_mount *mp, + int sunit) +{ + struct xfs_ino_geometry *igeo = M_IGEO(mp); + xfs_agblock_t first_bno; + + /* + * Pre-calculate the geometry of AG 0. We know what it looks like + * because libxfs knows how to create allocation groups now. + * + * first_bno is the first block in which mkfs could possibly have + * allocated the root directory inode, once we factor in the metadata + * that mkfs formats before it. Namely, the four AG headers... + */ + first_bno = howmany(4 * mp->m_sb.sb_sectsize, mp->m_sb.sb_blocksize); + + /* ...the two free space btree roots... */ + first_bno += 2; + + /* ...the inode btree root... */ + first_bno += 1; + + /* ...the initial AGFL... */ + first_bno += xfs_alloc_min_freelist(mp, NULL); + + /* ...the free inode btree root... */ + if (xfs_sb_version_hasfinobt(&mp->m_sb)) + first_bno++; + + /* ...the reverse mapping btree root... */ + if (xfs_sb_version_hasrmapbt(&mp->m_sb)) + first_bno++; + + /* ...the reference count btree... */ + if (xfs_sb_version_hasreflink(&mp->m_sb)) + first_bno++; + + /* + * ...and the log, if it is allocated in the first allocation group. + * + * This can happen with filesystems that only have a single + * allocation group, or very odd geometries created by old mkfs + * versions on very small filesystems. + */ + if (mp->m_sb.sb_logstart && + XFS_FSB_TO_AGNO(mp, mp->m_sb.sb_logstart) == 0) + first_bno += mp->m_sb.sb_logblocks; + + /* + * Now round first_bno up to whatever allocation alignment is given + * by the filesystem or was passed in. + */ + if (xfs_sb_version_hasdalign(&mp->m_sb) && igeo->ialloc_align > 0) + first_bno = roundup(first_bno, sunit); + else if (xfs_sb_version_hasalign(&mp->m_sb) && + mp->m_sb.sb_inoalignmt > 1) + first_bno = roundup(first_bno, mp->m_sb.sb_inoalignmt); + + return XFS_AGINO_TO_INO(mp, 0, XFS_AGB_TO_AGINO(mp, first_bno)); +} diff --git a/fs/xfs/libxfs/xfs_ialloc.h b/fs/xfs/libxfs/xfs_ialloc.h index 323592d563d5..72b3468b97b1 100644 --- a/fs/xfs/libxfs/xfs_ialloc.h +++ b/fs/xfs/libxfs/xfs_ialloc.h @@ -152,5 +152,6 @@ int xfs_inobt_insert_rec(struct xfs_btree_cur *cur, uint16_t holemask, int xfs_ialloc_cluster_alignment(struct xfs_mount *mp); void xfs_ialloc_setup_geometry(struct xfs_mount *mp); +xfs_ino_t xfs_ialloc_calc_rootino(struct xfs_mount *mp, int sunit); #endif /* __XFS_IALLOC_H__ */ diff --git a/fs/xfs/libxfs/xfs_trans_resv.c b/fs/xfs/libxfs/xfs_trans_resv.c index c55cd9a3dec9..7a9c04920505 100644 --- a/fs/xfs/libxfs/xfs_trans_resv.c +++ b/fs/xfs/libxfs/xfs_trans_resv.c @@ -197,6 +197,24 @@ xfs_calc_inode_chunk_res( } /* + * Per-extent log reservation for the btree changes involved in freeing or + * allocating a realtime extent. We have to be able to log as many rtbitmap + * blocks as needed to mark inuse MAXEXTLEN blocks' worth of realtime extents, + * as well as the realtime summary block. + */ +static unsigned int +xfs_rtalloc_log_count( + struct xfs_mount *mp, + unsigned int num_ops) +{ + unsigned int blksz = XFS_FSB_TO_B(mp, 1); + unsigned int rtbmp_bytes; + + rtbmp_bytes = (MAXEXTLEN / mp->m_sb.sb_rextsize) / NBBY; + return (howmany(rtbmp_bytes, blksz) + 1) * num_ops; +} + +/* * Various log reservation values. * * These are based on the size of the file system block because that is what @@ -218,13 +236,21 @@ xfs_calc_inode_chunk_res( /* * In a write transaction we can allocate a maximum of 2 - * extents. This gives: + * extents. This gives (t1): * the inode getting the new extents: inode size * the inode's bmap btree: max depth * block size * the agfs of the ags from which the extents are allocated: 2 * sector * the superblock free block counter: sector size * the allocation btrees: 2 exts * 2 trees * (2 * max depth - 1) * block size - * And the bmap_finish transaction can free bmap blocks in a join: + * Or, if we're writing to a realtime file (t2): + * the inode getting the new extents: inode size + * the inode's bmap btree: max depth * block size + * the agfs of the ags from which the extents are allocated: 2 * sector + * the superblock free block counter: sector size + * the realtime bitmap: ((MAXEXTLEN / rtextsize) / NBBY) bytes + * the realtime summary: 1 block + * the allocation btrees: 2 trees * (2 * max depth - 1) * block size + * And the bmap_finish transaction can free bmap blocks in a join (t3): * the agfs of the ags containing the blocks: 2 * sector size * the agfls of the ags containing the blocks: 2 * sector size * the super block free block counter: sector size @@ -234,40 +260,72 @@ STATIC uint xfs_calc_write_reservation( struct xfs_mount *mp) { - return XFS_DQUOT_LOGRES(mp) + - max((xfs_calc_inode_res(mp, 1) + + unsigned int t1, t2, t3; + unsigned int blksz = XFS_FSB_TO_B(mp, 1); + + t1 = xfs_calc_inode_res(mp, 1) + + xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK), blksz) + + xfs_calc_buf_res(3, mp->m_sb.sb_sectsize) + + xfs_calc_buf_res(xfs_allocfree_log_count(mp, 2), blksz); + + if (xfs_sb_version_hasrealtime(&mp->m_sb)) { + t2 = xfs_calc_inode_res(mp, 1) + xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK), - XFS_FSB_TO_B(mp, 1)) + + blksz) + xfs_calc_buf_res(3, mp->m_sb.sb_sectsize) + - xfs_calc_buf_res(xfs_allocfree_log_count(mp, 2), - XFS_FSB_TO_B(mp, 1))), - (xfs_calc_buf_res(5, mp->m_sb.sb_sectsize) + - xfs_calc_buf_res(xfs_allocfree_log_count(mp, 2), - XFS_FSB_TO_B(mp, 1)))); + xfs_calc_buf_res(xfs_rtalloc_log_count(mp, 1), blksz) + + xfs_calc_buf_res(xfs_allocfree_log_count(mp, 1), blksz); + } else { + t2 = 0; + } + + t3 = xfs_calc_buf_res(5, mp->m_sb.sb_sectsize) + + xfs_calc_buf_res(xfs_allocfree_log_count(mp, 2), blksz); + + return XFS_DQUOT_LOGRES(mp) + max3(t1, t2, t3); } /* - * In truncating a file we free up to two extents at once. We can modify: + * In truncating a file we free up to two extents at once. We can modify (t1): * the inode being truncated: inode size * the inode's bmap btree: (max depth + 1) * block size - * And the bmap_finish transaction can free the blocks and bmap blocks: + * And the bmap_finish transaction can free the blocks and bmap blocks (t2): * the agf for each of the ags: 4 * sector size * the agfl for each of the ags: 4 * sector size * the super block to reflect the freed blocks: sector size * worst case split in allocation btrees per extent assuming 4 extents: * 4 exts * 2 trees * (2 * max depth - 1) * block size + * Or, if it's a realtime file (t3): + * the agf for each of the ags: 2 * sector size + * the agfl for each of the ags: 2 * sector size + * the super block to reflect the freed blocks: sector size + * the realtime bitmap: 2 exts * ((MAXEXTLEN / rtextsize) / NBBY) bytes + * the realtime summary: 2 exts * 1 block + * worst case split in allocation btrees per extent assuming 2 extents: + * 2 exts * 2 trees * (2 * max depth - 1) * block size */ STATIC uint xfs_calc_itruncate_reservation( struct xfs_mount *mp) { - return XFS_DQUOT_LOGRES(mp) + - max((xfs_calc_inode_res(mp, 1) + - xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) + 1, - XFS_FSB_TO_B(mp, 1))), - (xfs_calc_buf_res(9, mp->m_sb.sb_sectsize) + - xfs_calc_buf_res(xfs_allocfree_log_count(mp, 4), - XFS_FSB_TO_B(mp, 1)))); + unsigned int t1, t2, t3; + unsigned int blksz = XFS_FSB_TO_B(mp, 1); + + t1 = xfs_calc_inode_res(mp, 1) + + xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) + 1, blksz); + + t2 = xfs_calc_buf_res(9, mp->m_sb.sb_sectsize) + + xfs_calc_buf_res(xfs_allocfree_log_count(mp, 4), blksz); + + if (xfs_sb_version_hasrealtime(&mp->m_sb)) { + t3 = xfs_calc_buf_res(5, mp->m_sb.sb_sectsize) + + xfs_calc_buf_res(xfs_rtalloc_log_count(mp, 2), blksz) + + xfs_calc_buf_res(xfs_allocfree_log_count(mp, 2), blksz); + } else { + t3 = 0; + } + + return XFS_DQUOT_LOGRES(mp) + max3(t1, t2, t3); } /* diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 2efd78a9719e..e62fb5216341 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -992,6 +992,7 @@ xfs_prepare_shift( struct xfs_inode *ip, loff_t offset) { + struct xfs_mount *mp = ip->i_mount; int error; /* @@ -1005,6 +1006,17 @@ xfs_prepare_shift( } /* + * Shift operations must stabilize the start block offset boundary along + * with the full range of the operation. If we don't, a COW writeback + * completion could race with an insert, front merge with the start + * extent (after split) during the shift and corrupt the file. Start + * with the block just prior to the start to stabilize the boundary. + */ + offset = round_down(offset, 1 << mp->m_sb.sb_blocklog); + if (offset) + offset -= (1 << mp->m_sb.sb_blocklog); + + /* * Writeback and invalidate cache for the remainder of the file as we're * about to shift down every extent from offset to EOF. */ diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 3458a1264a3f..3984779e5911 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -956,7 +956,7 @@ xfs_buf_item_relse( struct xfs_buf_log_item *bip = bp->b_log_item; trace_xfs_buf_item_relse(bp, _RET_IP_); - ASSERT(!(bip->bli_item.li_flags & XFS_LI_IN_AIL)); + ASSERT(!test_bit(XFS_LI_IN_AIL, &bip->bli_item.li_flags)); bp->b_log_item = NULL; if (list_empty(&bp->b_li_list)) diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index fca65109cf24..56efe140c923 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -31,7 +31,7 @@ #include "xfs_reflink.h" #include "xfs_extent_busy.h" #include "xfs_health.h" - +#include "xfs_trace.h" static DEFINE_MUTEX(xfs_uuid_table_mutex); static int xfs_uuid_table_size; @@ -360,66 +360,119 @@ release_buf: } /* - * Update alignment values based on mount options and sb values + * If the sunit/swidth change would move the precomputed root inode value, we + * must reject the ondisk change because repair will stumble over that. + * However, we allow the mount to proceed because we never rejected this + * combination before. Returns true to update the sb, false otherwise. + */ +static inline int +xfs_check_new_dalign( + struct xfs_mount *mp, + int new_dalign, + bool *update_sb) +{ + struct xfs_sb *sbp = &mp->m_sb; + xfs_ino_t calc_ino; + + calc_ino = xfs_ialloc_calc_rootino(mp, new_dalign); + trace_xfs_check_new_dalign(mp, new_dalign, calc_ino); + + if (sbp->sb_rootino == calc_ino) { + *update_sb = true; + return 0; + } + + xfs_warn(mp, +"Cannot change stripe alignment; would require moving root inode."); + + /* + * XXX: Next time we add a new incompat feature, this should start + * returning -EINVAL to fail the mount. Until then, spit out a warning + * that we're ignoring the administrator's instructions. + */ + xfs_warn(mp, "Skipping superblock stripe alignment update."); + *update_sb = false; + return 0; +} + +/* + * If we were provided with new sunit/swidth values as mount options, make sure + * that they pass basic alignment and superblock feature checks, and convert + * them into the same units (FSB) that everything else expects. This step + * /must/ be done before computing the inode geometry. */ STATIC int -xfs_update_alignment(xfs_mount_t *mp) +xfs_validate_new_dalign( + struct xfs_mount *mp) { - xfs_sb_t *sbp = &(mp->m_sb); + if (mp->m_dalign == 0) + return 0; - if (mp->m_dalign) { + /* + * If stripe unit and stripe width are not multiples + * of the fs blocksize turn off alignment. + */ + if ((BBTOB(mp->m_dalign) & mp->m_blockmask) || + (BBTOB(mp->m_swidth) & mp->m_blockmask)) { + xfs_warn(mp, + "alignment check failed: sunit/swidth vs. blocksize(%d)", + mp->m_sb.sb_blocksize); + return -EINVAL; + } else { /* - * If stripe unit and stripe width are not multiples - * of the fs blocksize turn off alignment. + * Convert the stripe unit and width to FSBs. */ - if ((BBTOB(mp->m_dalign) & mp->m_blockmask) || - (BBTOB(mp->m_swidth) & mp->m_blockmask)) { + mp->m_dalign = XFS_BB_TO_FSBT(mp, mp->m_dalign); + if (mp->m_dalign && (mp->m_sb.sb_agblocks % mp->m_dalign)) { xfs_warn(mp, - "alignment check failed: sunit/swidth vs. blocksize(%d)", - sbp->sb_blocksize); + "alignment check failed: sunit/swidth vs. agsize(%d)", + mp->m_sb.sb_agblocks); return -EINVAL; - } else { - /* - * Convert the stripe unit and width to FSBs. - */ - mp->m_dalign = XFS_BB_TO_FSBT(mp, mp->m_dalign); - if (mp->m_dalign && (sbp->sb_agblocks % mp->m_dalign)) { - xfs_warn(mp, - "alignment check failed: sunit/swidth vs. agsize(%d)", - sbp->sb_agblocks); - return -EINVAL; - } else if (mp->m_dalign) { - mp->m_swidth = XFS_BB_TO_FSBT(mp, mp->m_swidth); - } else { - xfs_warn(mp, - "alignment check failed: sunit(%d) less than bsize(%d)", - mp->m_dalign, sbp->sb_blocksize); - return -EINVAL; - } - } - - /* - * Update superblock with new values - * and log changes - */ - if (xfs_sb_version_hasdalign(sbp)) { - if (sbp->sb_unit != mp->m_dalign) { - sbp->sb_unit = mp->m_dalign; - mp->m_update_sb = true; - } - if (sbp->sb_width != mp->m_swidth) { - sbp->sb_width = mp->m_swidth; - mp->m_update_sb = true; - } + } else if (mp->m_dalign) { + mp->m_swidth = XFS_BB_TO_FSBT(mp, mp->m_swidth); } else { xfs_warn(mp, - "cannot change alignment: superblock does not support data alignment"); + "alignment check failed: sunit(%d) less than bsize(%d)", + mp->m_dalign, mp->m_sb.sb_blocksize); return -EINVAL; } + } + + if (!xfs_sb_version_hasdalign(&mp->m_sb)) { + xfs_warn(mp, +"cannot change alignment: superblock does not support data alignment"); + return -EINVAL; + } + + return 0; +} + +/* Update alignment values based on mount options and sb values. */ +STATIC int +xfs_update_alignment( + struct xfs_mount *mp) +{ + struct xfs_sb *sbp = &mp->m_sb; + + if (mp->m_dalign) { + bool update_sb; + int error; + + if (sbp->sb_unit == mp->m_dalign && + sbp->sb_width == mp->m_swidth) + return 0; + + error = xfs_check_new_dalign(mp, mp->m_dalign, &update_sb); + if (error || !update_sb) + return error; + + sbp->sb_unit = mp->m_dalign; + sbp->sb_width = mp->m_swidth; + mp->m_update_sb = true; } else if ((mp->m_flags & XFS_MOUNT_NOALIGN) != XFS_MOUNT_NOALIGN && xfs_sb_version_hasdalign(&mp->m_sb)) { - mp->m_dalign = sbp->sb_unit; - mp->m_swidth = sbp->sb_width; + mp->m_dalign = sbp->sb_unit; + mp->m_swidth = sbp->sb_width; } return 0; @@ -648,12 +701,12 @@ xfs_mountfs( } /* - * Check if sb_agblocks is aligned at stripe boundary - * If sb_agblocks is NOT aligned turn off m_dalign since - * allocator alignment is within an ag, therefore ag has - * to be aligned at stripe boundary. + * If we were given new sunit/swidth options, do some basic validation + * checks and convert the incore dalign and swidth values to the + * same units (FSB) that everything else uses. This /must/ happen + * before computing the inode geometry. */ - error = xfs_update_alignment(mp); + error = xfs_validate_new_dalign(mp); if (error) goto out; @@ -664,6 +717,17 @@ xfs_mountfs( xfs_rmapbt_compute_maxlevels(mp); xfs_refcountbt_compute_maxlevels(mp); + /* + * Check if sb_agblocks is aligned at stripe boundary. If sb_agblocks + * is NOT aligned turn off m_dalign since allocator alignment is within + * an ag, therefore ag has to be aligned at stripe boundary. Note that + * we must compute the free space and rmap btree geometry before doing + * this. + */ + error = xfs_update_alignment(mp); + if (error) + goto out; + /* enable fail_at_unmount as default */ mp->m_fail_unmount = true; diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index c13bb3655e48..a86be7f807ee 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -3573,6 +3573,27 @@ DEFINE_KMEM_EVENT(kmem_alloc_large); DEFINE_KMEM_EVENT(kmem_realloc); DEFINE_KMEM_EVENT(kmem_zone_alloc); +TRACE_EVENT(xfs_check_new_dalign, + TP_PROTO(struct xfs_mount *mp, int new_dalign, xfs_ino_t calc_rootino), + TP_ARGS(mp, new_dalign, calc_rootino), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(int, new_dalign) + __field(xfs_ino_t, sb_rootino) + __field(xfs_ino_t, calc_rootino) + ), + TP_fast_assign( + __entry->dev = mp->m_super->s_dev; + __entry->new_dalign = new_dalign; + __entry->sb_rootino = mp->m_sb.sb_rootino; + __entry->calc_rootino = calc_rootino; + ), + TP_printk("dev %d:%d new_dalign %d sb_rootino %llu calc_rootino %llu", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->new_dalign, __entry->sb_rootino, + __entry->calc_rootino) +) + #endif /* _TRACE_XFS_H */ #undef TRACE_INCLUDE_PATH diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 169fd25f6bc2..9be71c195d74 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -157,8 +157,8 @@ void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage, struct cgroup *cgroup, enum bpf_attach_type type); void bpf_cgroup_storage_unlink(struct bpf_cgroup_storage *storage); -int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *map); -void bpf_cgroup_storage_release(struct bpf_prog *prog, struct bpf_map *map); +int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *map); +void bpf_cgroup_storage_release(struct bpf_prog_aux *aux, struct bpf_map *map); int bpf_percpu_cgroup_storage_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, @@ -360,9 +360,9 @@ static inline int cgroup_bpf_prog_query(const union bpf_attr *attr, static inline void bpf_cgroup_storage_set( struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]) {} -static inline int bpf_cgroup_storage_assign(struct bpf_prog *prog, +static inline int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *map) { return 0; } -static inline void bpf_cgroup_storage_release(struct bpf_prog *prog, +static inline void bpf_cgroup_storage_release(struct bpf_prog_aux *aux, struct bpf_map *map) {} static inline struct bpf_cgroup_storage *bpf_cgroup_storage_alloc( struct bpf_prog *prog, enum bpf_cgroup_storage_type stype) { return NULL; } diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 35903f148be5..085a59afba85 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -461,6 +461,7 @@ struct bpf_trampoline { struct { struct btf_func_model model; void *addr; + bool ftrace_managed; } func; /* list of BPF programs using this trampoline */ struct hlist_head progs_hlist[BPF_TRAMP_MAX]; @@ -817,6 +818,8 @@ struct bpf_prog * __must_check bpf_prog_inc_not_zero(struct bpf_prog *prog); void bpf_prog_put(struct bpf_prog *prog); int __bpf_prog_charge(struct user_struct *user, u32 pages); void __bpf_prog_uncharge(struct user_struct *user, u32 pages); +void __bpf_free_used_maps(struct bpf_prog_aux *aux, + struct bpf_map **used_maps, u32 len); void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock); void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock); diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 92d5fdc8154e..31b1b0e03df8 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -595,17 +595,6 @@ struct governor_attr { size_t count); }; -static inline bool cpufreq_this_cpu_can_update(struct cpufreq_policy *policy) -{ - /* - * Allow remote callbacks if: - * - dvfs_possible_from_any_cpu flag is set - * - the local and remote CPUs share cpufreq policy - */ - return policy->dvfs_possible_from_any_cpu || - cpumask_test_cpu(smp_processor_id(), policy->cpus); -} - /********************************************************************* * FREQUENCY TABLE HELPERS * *********************************************************************/ diff --git a/include/linux/efi.h b/include/linux/efi.h index 99dfea595c8c..aa54586db7a5 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -824,7 +824,7 @@ typedef struct { __aligned_u64 image_size; unsigned int image_code_type; unsigned int image_data_type; - unsigned long unload; + u32 unload; } efi_loaded_image_32_t; typedef struct { @@ -840,14 +840,14 @@ typedef struct { __aligned_u64 image_size; unsigned int image_code_type; unsigned int image_data_type; - unsigned long unload; + u64 unload; } efi_loaded_image_64_t; typedef struct { u32 revision; - void *parent_handle; + efi_handle_t parent_handle; efi_system_table_t *system_table; - void *device_handle; + efi_handle_t device_handle; void *file_path; void *reserved; u32 load_options_size; @@ -856,7 +856,7 @@ typedef struct { __aligned_u64 image_size; unsigned int image_code_type; unsigned int image_data_type; - unsigned long unload; + efi_status_t (*unload)(efi_handle_t image_handle); } efi_loaded_image_t; diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 29dce6ff6bae..ce44b687d02b 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -457,7 +457,7 @@ struct jbd2_revoke_table_s; * @h_journal: Which journal handle belongs to - used iff h_reserved set. * @h_rsv_handle: Handle reserved for finishing the logical operation. * @h_total_credits: Number of remaining buffers we are allowed to add to - journal. These are dirty buffers and revoke descriptor blocks. + * journal. These are dirty buffers and revoke descriptor blocks. * @h_revoke_credits: Number of remaining revoke records available for handle * @h_ref: Reference count on this handle. * @h_err: Field for caller's use to track errors through large fs operations. diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 4f404c565db1..e18fe54969e9 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -205,20 +205,23 @@ static inline void *kasan_reset_tag(const void *addr) #endif /* CONFIG_KASAN_SW_TAGS */ #ifdef CONFIG_KASAN_VMALLOC -int kasan_populate_vmalloc(unsigned long requested_size, - struct vm_struct *area); -void kasan_poison_vmalloc(void *start, unsigned long size); +int kasan_populate_vmalloc(unsigned long addr, unsigned long size); +void kasan_poison_vmalloc(const void *start, unsigned long size); +void kasan_unpoison_vmalloc(const void *start, unsigned long size); void kasan_release_vmalloc(unsigned long start, unsigned long end, unsigned long free_region_start, unsigned long free_region_end); #else -static inline int kasan_populate_vmalloc(unsigned long requested_size, - struct vm_struct *area) +static inline int kasan_populate_vmalloc(unsigned long start, + unsigned long size) { return 0; } -static inline void kasan_poison_vmalloc(void *start, unsigned long size) {} +static inline void kasan_poison_vmalloc(const void *start, unsigned long size) +{ } +static inline void kasan_unpoison_vmalloc(const void *start, unsigned long size) +{ } static inline void kasan_release_vmalloc(unsigned long start, unsigned long end, unsigned long free_region_start, diff --git a/include/linux/mm.h b/include/linux/mm.h index c97ea3b694e6..80a9162b406c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2621,6 +2621,9 @@ static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) typedef int (*pte_fn_t)(pte_t *pte, unsigned long addr, void *data); extern int apply_to_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); +extern int apply_to_existing_page_range(struct mm_struct *mm, + unsigned long address, unsigned long size, + pte_fn_t fn, void *data); #ifdef CONFIG_PAGE_POISONING extern bool page_poisoning_enabled(void); diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 5714fd35a83c..e3596db077dc 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -587,9 +587,9 @@ struct platform_device_id { #define MDIO_NAME_SIZE 32 #define MDIO_MODULE_PREFIX "mdio:" -#define MDIO_ID_FMT "%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d" +#define MDIO_ID_FMT "%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u" #define MDIO_ID_ARGS(_id) \ - (_id)>>31, ((_id)>>30) & 1, ((_id)>>29) & 1, ((_id)>>28) & 1, \ + ((_id)>>31) & 1, ((_id)>>30) & 1, ((_id)>>29) & 1, ((_id)>>28) & 1, \ ((_id)>>27) & 1, ((_id)>>26) & 1, ((_id)>>25) & 1, ((_id)>>24) & 1, \ ((_id)>>23) & 1, ((_id)>>22) & 1, ((_id)>>21) & 1, ((_id)>>20) & 1, \ ((_id)>>19) & 1, ((_id)>>18) & 1, ((_id)>>17) & 1, ((_id)>>16) & 1, \ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9ef20389622d..ae5e260911e2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1775,7 +1775,7 @@ enum netdev_priv_flags { * for hardware timestamping * @sfp_bus: attached &struct sfp_bus structure. * @qdisc_tx_busylock_key: lockdep class annotating Qdisc->busylock - spinlock + * spinlock * @qdisc_running_key: lockdep class annotating Qdisc->running seqcount * @qdisc_xmit_lock_key: lockdep class annotating * netdev_queue->_xmit_lock spinlock diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index 99cefe6f5edb..79bc82e30c02 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -12,6 +12,7 @@ #include <linux/of.h> #if IS_ENABLED(CONFIG_OF_MDIO) +extern bool of_mdiobus_child_is_phy(struct device_node *child); extern int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np); extern struct phy_device *of_phy_find_device(struct device_node *phy_np); extern struct phy_device *of_phy_connect(struct net_device *dev, @@ -54,6 +55,11 @@ static inline int of_mdio_parse_addr(struct device *dev, } #else /* CONFIG_OF_MDIO */ +static bool of_mdiobus_child_is_phy(struct device_node *child) +{ + return false; +} + static inline int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np) { /* diff --git a/include/linux/phy.h b/include/linux/phy.h index 5032d453ac66..dd4a91f1feaa 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1000,7 +1000,7 @@ int phy_modify_paged_changed(struct phy_device *phydev, int page, u32 regnum, int phy_modify_paged(struct phy_device *phydev, int page, u32 regnum, u16 mask, u16 set); -struct phy_device *phy_device_create(struct mii_bus *bus, int addr, int phy_id, +struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id, bool is_c45, struct phy_c45_device_ids *c45_ids); #if IS_ENABLED(CONFIG_PHYLIB) diff --git a/include/linux/platform_data/ti-sysc.h b/include/linux/platform_data/ti-sysc.h index 0b9380475144..8cfe570fdece 100644 --- a/include/linux/platform_data/ti-sysc.h +++ b/include/linux/platform_data/ti-sysc.h @@ -49,6 +49,7 @@ struct sysc_regbits { s8 emufree_shift; }; +#define SYSC_QUIRK_FORCE_MSTANDBY BIT(20) #define SYSC_MODULE_QUIRK_AESS BIT(19) #define SYSC_MODULE_QUIRK_SGX BIT(18) #define SYSC_MODULE_QUIRK_HDQ1W BIT(17) diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h index bc8206a8f30e..61974c4c566b 100644 --- a/include/linux/rculist_nulls.h +++ b/include/linux/rculist_nulls.h @@ -101,6 +101,43 @@ static inline void hlist_nulls_add_head_rcu(struct hlist_nulls_node *n, } /** + * hlist_nulls_add_tail_rcu + * @n: the element to add to the hash list. + * @h: the list to add to. + * + * Description: + * Adds the specified element to the specified hlist_nulls, + * while permitting racing traversals. + * + * The caller must take whatever precautions are necessary + * (such as holding appropriate locks) to avoid racing + * with another list-mutation primitive, such as hlist_nulls_add_head_rcu() + * or hlist_nulls_del_rcu(), running on this same list. + * However, it is perfectly legal to run concurrently with + * the _rcu list-traversal primitives, such as + * hlist_nulls_for_each_entry_rcu(), used to prevent memory-consistency + * problems on Alpha CPUs. Regardless of the type of CPU, the + * list-traversal primitive must be guarded by rcu_read_lock(). + */ +static inline void hlist_nulls_add_tail_rcu(struct hlist_nulls_node *n, + struct hlist_nulls_head *h) +{ + struct hlist_nulls_node *i, *last = NULL; + + /* Note: write side code, so rcu accessors are not needed. */ + for (i = h->first; !is_a_nulls(i); i = i->next) + last = i; + + if (last) { + n->next = last->next; + n->pprev = &last->next; + rcu_assign_pointer(hlist_next_rcu(last), n); + } else { + hlist_nulls_add_head_rcu(n, h); + } +} + +/** * hlist_nulls_for_each_entry_rcu - iterate over rcu list of given type * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_nulls_node to use as a loop cursor. diff --git a/include/linux/sched/cpufreq.h b/include/linux/sched/cpufreq.h index afa940cd50dc..cc6bcc1e96bc 100644 --- a/include/linux/sched/cpufreq.h +++ b/include/linux/sched/cpufreq.h @@ -12,6 +12,8 @@ #define SCHED_CPUFREQ_MIGRATION (1U << 1) #ifdef CONFIG_CPU_FREQ +struct cpufreq_policy; + struct update_util_data { void (*func)(struct update_util_data *data, u64 time, unsigned int flags); }; @@ -20,6 +22,7 @@ void cpufreq_add_update_util_hook(int cpu, struct update_util_data *data, void (*func)(struct update_util_data *data, u64 time, unsigned int flags)); void cpufreq_remove_update_util_hook(int cpu); +bool cpufreq_this_cpu_can_update(struct cpufreq_policy *policy); static inline unsigned long map_util_freq(unsigned long util, unsigned long freq, unsigned long cap) diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 0d6e949ba315..03e9b184411b 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -403,6 +403,7 @@ extern int tpm_pcr_extend(struct tpm_chip *chip, u32 pcr_idx, extern int tpm_send(struct tpm_chip *chip, void *cmd, size_t buflen); extern int tpm_get_random(struct tpm_chip *chip, u8 *data, size_t max); extern struct tpm_chip *tpm_default_chip(void); +void tpm2_flush_context(struct tpm_chip *chip, u32 handle); #else static inline int tpm_is_tpm2(struct tpm_chip *chip) { diff --git a/include/net/dst.h b/include/net/dst.h index fe62fe2eb781..8224dad2ae94 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -82,7 +82,7 @@ struct dst_entry { struct dst_metrics { u32 metrics[RTAX_MAX]; refcount_t refcnt; -}; +} __aligned(4); /* Low pointer bits contain DST_METRICS_FLAGS */ extern const struct dst_metrics dst_default_metrics; u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old); diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index af2b4c065a04..d0019d3395cf 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -103,13 +103,19 @@ struct inet_bind_hashbucket { struct hlist_head chain; }; -/* - * Sockets can be hashed in established or listening table +/* Sockets can be hashed in established or listening table. + * We must use different 'nulls' end-of-chain value for all hash buckets : + * A socket might transition from ESTABLISH to LISTEN state without + * RCU grace period. A lookup in ehash table needs to handle this case. */ +#define LISTENING_NULLS_BASE (1U << 29) struct inet_listen_hashbucket { spinlock_t lock; unsigned int count; - struct hlist_head head; + union { + struct hlist_head head; + struct hlist_nulls_head nulls_head; + }; }; /* This is for listening sockets, thus all sockets which possess wildcards. */ diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 6ad9ad47a9c5..8ec77bfdc1a4 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -72,7 +72,6 @@ struct neigh_parms { struct net_device *dev; struct list_head list; int (*neigh_setup)(struct neighbour *); - void (*neigh_cleanup)(struct neighbour *); struct neigh_table *tbl; void *sysctl_table; diff --git a/include/net/sock.h b/include/net/sock.h index 80f996406bba..8dff68b4c316 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -722,6 +722,11 @@ static inline void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_h hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list); } +static inline void __sk_nulls_add_node_tail_rcu(struct sock *sk, struct hlist_nulls_head *list) +{ + hlist_nulls_add_tail_rcu(&sk->sk_nulls_node, list); +} + static inline void sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list) { sock_hold(sk); @@ -2583,9 +2588,9 @@ static inline int sk_get_rmem0(const struct sock *sk, const struct proto *proto) */ static inline void sk_pacing_shift_update(struct sock *sk, int val) { - if (!sk || !sk_fullsock(sk) || sk->sk_pacing_shift == val) + if (!sk || !sk_fullsock(sk) || READ_ONCE(sk->sk_pacing_shift) == val) return; - sk->sk_pacing_shift = val; + WRITE_ONCE(sk->sk_pacing_shift, val); } /* if a socket is bound to a device, check that the given device diff --git a/include/net/tcp.h b/include/net/tcp.h index 86b9a8766648..e460ea7f767b 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1766,9 +1766,18 @@ static inline bool tcp_skb_is_last(const struct sock *sk, return skb_queue_is_last(&sk->sk_write_queue, skb); } +/** + * tcp_write_queue_empty - test if any payload (or FIN) is available in write queue + * @sk: socket + * + * Since the write queue can have a temporary empty skb in it, + * we must not use "return skb_queue_empty(&sk->sk_write_queue)" + */ static inline bool tcp_write_queue_empty(const struct sock *sk) { - return skb_queue_empty(&sk->sk_write_queue); + const struct tcp_sock *tp = tcp_sk(sk); + + return tp->write_seq == tp->snd_nxt; } static inline bool tcp_rtx_queue_empty(const struct sock *sk) diff --git a/include/net/x25.h b/include/net/x25.h index ed1acc3044ac..d7d6c2b4ffa7 100644 --- a/include/net/x25.h +++ b/include/net/x25.h @@ -62,7 +62,8 @@ enum { X25_STATE_1, /* Awaiting Call Accepted */ X25_STATE_2, /* Awaiting Clear Confirmation */ X25_STATE_3, /* Data Transfer */ - X25_STATE_4 /* Awaiting Reset Confirmation */ + X25_STATE_4, /* Awaiting Reset Confirmation */ + X25_STATE_5 /* Call Accepted / Call Connected pending */ }; enum { diff --git a/include/sound/soc.h b/include/sound/soc.h index c28a1ed5e8df..262896799826 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -1150,6 +1150,7 @@ struct snd_soc_pcm_runtime { unsigned int num_codecs; struct delayed_work delayed_work; + void (*close_delayed_work_func)(struct snd_soc_pcm_runtime *rtd); #ifdef CONFIG_DEBUG_FS struct dentry *debugfs_dpcm_root; #endif diff --git a/include/uapi/linux/netfilter/xt_sctp.h b/include/uapi/linux/netfilter/xt_sctp.h index 4bc6d1a08781..b4d804a9fccb 100644 --- a/include/uapi/linux/netfilter/xt_sctp.h +++ b/include/uapi/linux/netfilter/xt_sctp.h @@ -41,19 +41,19 @@ struct xt_sctp_info { #define SCTP_CHUNKMAP_SET(chunkmap, type) \ do { \ (chunkmap)[type / bytes(__u32)] |= \ - 1 << (type % bytes(__u32)); \ + 1u << (type % bytes(__u32)); \ } while (0) #define SCTP_CHUNKMAP_CLEAR(chunkmap, type) \ do { \ (chunkmap)[type / bytes(__u32)] &= \ - ~(1 << (type % bytes(__u32))); \ + ~(1u << (type % bytes(__u32))); \ } while (0) #define SCTP_CHUNKMAP_IS_SET(chunkmap, type) \ ({ \ ((chunkmap)[type / bytes (__u32)] & \ - (1 << (type % bytes (__u32)))) ? 1: 0; \ + (1u << (type % bytes (__u32)))) ? 1: 0; \ }) #define SCTP_CHUNKMAP_RESET(chunkmap) \ diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 341e0e8cae46..5eab191607f8 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -5517,6 +5517,10 @@ enum nl80211_feature_flags { * with VLAN tagged frames and separate VLAN-specific netdevs added using * vconfig similarly to the Ethernet case. * + * @NL80211_EXT_FEATURE_AQL: The driver supports the Airtime Queue Limit (AQL) + * feature, which prevents bufferbloat by using the expected transmission + * time to limit the amount of data buffered in the hardware. + * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. */ @@ -5563,6 +5567,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_STA_TX_PWR, NL80211_EXT_FEATURE_SAE_OFFLOAD, NL80211_EXT_FEATURE_VLAN_OFFLOAD, + NL80211_EXT_FEATURE_AQL, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, diff --git a/include/xen/interface/io/ring.h b/include/xen/interface/io/ring.h index 3f40501fc60b..2af7a1cd6658 100644 --- a/include/xen/interface/io/ring.h +++ b/include/xen/interface/io/ring.h @@ -125,35 +125,24 @@ struct __name##_back_ring { \ memset((_s)->pad, 0, sizeof((_s)->pad)); \ } while(0) -#define FRONT_RING_INIT(_r, _s, __size) do { \ - (_r)->req_prod_pvt = 0; \ - (_r)->rsp_cons = 0; \ +#define FRONT_RING_ATTACH(_r, _s, _i, __size) do { \ + (_r)->req_prod_pvt = (_i); \ + (_r)->rsp_cons = (_i); \ (_r)->nr_ents = __RING_SIZE(_s, __size); \ (_r)->sring = (_s); \ } while (0) -#define BACK_RING_INIT(_r, _s, __size) do { \ - (_r)->rsp_prod_pvt = 0; \ - (_r)->req_cons = 0; \ - (_r)->nr_ents = __RING_SIZE(_s, __size); \ - (_r)->sring = (_s); \ -} while (0) +#define FRONT_RING_INIT(_r, _s, __size) FRONT_RING_ATTACH(_r, _s, 0, __size) -/* Initialize to existing shared indexes -- for recovery */ -#define FRONT_RING_ATTACH(_r, _s, __size) do { \ - (_r)->sring = (_s); \ - (_r)->req_prod_pvt = (_s)->req_prod; \ - (_r)->rsp_cons = (_s)->rsp_prod; \ +#define BACK_RING_ATTACH(_r, _s, _i, __size) do { \ + (_r)->rsp_prod_pvt = (_i); \ + (_r)->req_cons = (_i); \ (_r)->nr_ents = __RING_SIZE(_s, __size); \ -} while (0) - -#define BACK_RING_ATTACH(_r, _s, __size) do { \ (_r)->sring = (_s); \ - (_r)->rsp_prod_pvt = (_s)->rsp_prod; \ - (_r)->req_cons = (_s)->req_prod; \ - (_r)->nr_ents = __RING_SIZE(_s, __size); \ } while (0) +#define BACK_RING_INIT(_r, _s, __size) BACK_RING_ATTACH(_r, _s, 0, __size) + /* How big is this ring? */ #define RING_SIZE(_r) \ ((_r)->nr_ents) diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h index 869c816d5f8c..24228a102141 100644 --- a/include/xen/xenbus.h +++ b/include/xen/xenbus.h @@ -93,6 +93,7 @@ struct xenbus_device_id struct xenbus_driver { const char *name; /* defaults to ids[0].devicetype */ const struct xenbus_device_id *ids; + bool allow_rebind; /* avoid setting xenstore closed during remove */ int (*probe)(struct xenbus_device *dev, const struct xenbus_device_id *id); void (*otherend_changed)(struct xenbus_device *dev, diff --git a/init/do_mounts.c b/init/do_mounts.c index f55cbd9cb818..0ae9cc22f2ae 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -391,17 +391,19 @@ static int __init do_mount_root(const char *name, const char *fs, const int flags, const void *data) { struct super_block *s; - char *data_page; - struct page *p; + struct page *p = NULL; + char *data_page = NULL; int ret; - /* do_mount() requires a full page as fifth argument */ - p = alloc_page(GFP_KERNEL); - if (!p) - return -ENOMEM; - - data_page = page_address(p); - strncpy(data_page, data, PAGE_SIZE - 1); + if (data) { + /* do_mount() requires a full page as fifth argument */ + p = alloc_page(GFP_KERNEL); + if (!p) + return -ENOMEM; + data_page = page_address(p); + /* zero-pad. do_mount() will make sure it's terminated */ + strncpy(data_page, data, PAGE_SIZE); + } ret = do_mount(name, "/root", fs, flags, data_page); if (ret) @@ -417,7 +419,8 @@ static int __init do_mount_root(const char *name, const char *fs, MAJOR(ROOT_DEV), MINOR(ROOT_DEV)); out: - put_page(p); + if (p) + put_page(p); return ret; } diff --git a/init/main.c b/init/main.c index ec3a1463ac69..1ecfd43ed464 100644 --- a/init/main.c +++ b/init/main.c @@ -1163,7 +1163,7 @@ void console_on_rootfs(void) /* Open /dev/console in kernelspace, this should never fail */ file = filp_open("/dev/console", O_RDWR, 0); - if (!file) + if (IS_ERR(file)) goto err_out; /* create stdin/stdout/stderr, this should never fail */ diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 7d40da240891..ed2075884724 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3470,6 +3470,7 @@ static u8 bpf_ctx_convert_map[] = { [_id] = __ctx_convert##_id, #include <linux/bpf_types.h> #undef BPF_PROG_TYPE + 0, /* avoid empty array */ }; #undef BPF_MAP_TYPE diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 49e32acad7d8..af6b738cf435 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2043,23 +2043,28 @@ static void bpf_free_cgroup_storage(struct bpf_prog_aux *aux) for_each_cgroup_storage_type(stype) { if (!aux->cgroup_storage[stype]) continue; - bpf_cgroup_storage_release(aux->prog, - aux->cgroup_storage[stype]); + bpf_cgroup_storage_release(aux, aux->cgroup_storage[stype]); } } -static void bpf_free_used_maps(struct bpf_prog_aux *aux) +void __bpf_free_used_maps(struct bpf_prog_aux *aux, + struct bpf_map **used_maps, u32 len) { struct bpf_map *map; - int i; + u32 i; bpf_free_cgroup_storage(aux); - for (i = 0; i < aux->used_map_cnt; i++) { - map = aux->used_maps[i]; + for (i = 0; i < len; i++) { + map = used_maps[i]; if (map->ops->map_poke_untrack) map->ops->map_poke_untrack(map, aux); bpf_map_put(map); } +} + +static void bpf_free_used_maps(struct bpf_prog_aux *aux) +{ + __bpf_free_used_maps(aux, aux->used_maps, aux->used_map_cnt); kfree(aux->used_maps); } diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index 6bd22f6d9f41..33d01866bcc2 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -20,7 +20,7 @@ struct bpf_cgroup_storage_map { struct bpf_map map; spinlock_t lock; - struct bpf_prog *prog; + struct bpf_prog_aux *aux; struct rb_root root; struct list_head list; }; @@ -420,7 +420,7 @@ const struct bpf_map_ops cgroup_storage_map_ops = { .map_seq_show_elem = cgroup_storage_seq_show_elem, }; -int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *_map) +int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *_map) { enum bpf_cgroup_storage_type stype = cgroup_storage_type(_map); struct bpf_cgroup_storage_map *map = map_to_storage(_map); @@ -428,14 +428,14 @@ int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *_map) spin_lock_bh(&map->lock); - if (map->prog && map->prog != prog) + if (map->aux && map->aux != aux) goto unlock; - if (prog->aux->cgroup_storage[stype] && - prog->aux->cgroup_storage[stype] != _map) + if (aux->cgroup_storage[stype] && + aux->cgroup_storage[stype] != _map) goto unlock; - map->prog = prog; - prog->aux->cgroup_storage[stype] = _map; + map->aux = aux; + aux->cgroup_storage[stype] = _map; ret = 0; unlock: spin_unlock_bh(&map->lock); @@ -443,16 +443,16 @@ unlock: return ret; } -void bpf_cgroup_storage_release(struct bpf_prog *prog, struct bpf_map *_map) +void bpf_cgroup_storage_release(struct bpf_prog_aux *aux, struct bpf_map *_map) { enum bpf_cgroup_storage_type stype = cgroup_storage_type(_map); struct bpf_cgroup_storage_map *map = map_to_storage(_map); spin_lock_bh(&map->lock); - if (map->prog == prog) { - WARN_ON(prog->aux->cgroup_storage[stype] != _map); - map->prog = NULL; - prog->aux->cgroup_storage[stype] = NULL; + if (map->aux == aux) { + WARN_ON(aux->cgroup_storage[stype] != _map); + map->aux = NULL; + aux->cgroup_storage[stype] = NULL; } spin_unlock_bh(&map->lock); } diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index 7e89f1f49d77..23b0d5cfd47e 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -3,6 +3,7 @@ #include <linux/hash.h> #include <linux/bpf.h> #include <linux/filter.h> +#include <linux/ftrace.h> /* btf_vmlinux has ~22k attachable functions. 1k htab is enough. */ #define TRAMPOLINE_HASH_BITS 10 @@ -59,6 +60,60 @@ out: return tr; } +static int is_ftrace_location(void *ip) +{ + long addr; + + addr = ftrace_location((long)ip); + if (!addr) + return 0; + if (WARN_ON_ONCE(addr != (long)ip)) + return -EFAULT; + return 1; +} + +static int unregister_fentry(struct bpf_trampoline *tr, void *old_addr) +{ + void *ip = tr->func.addr; + int ret; + + if (tr->func.ftrace_managed) + ret = unregister_ftrace_direct((long)ip, (long)old_addr); + else + ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, old_addr, NULL); + return ret; +} + +static int modify_fentry(struct bpf_trampoline *tr, void *old_addr, void *new_addr) +{ + void *ip = tr->func.addr; + int ret; + + if (tr->func.ftrace_managed) + ret = modify_ftrace_direct((long)ip, (long)old_addr, (long)new_addr); + else + ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, old_addr, new_addr); + return ret; +} + +/* first time registering */ +static int register_fentry(struct bpf_trampoline *tr, void *new_addr) +{ + void *ip = tr->func.addr; + int ret; + + ret = is_ftrace_location(ip); + if (ret < 0) + return ret; + tr->func.ftrace_managed = ret; + + if (tr->func.ftrace_managed) + ret = register_ftrace_direct((long)ip, (long)new_addr); + else + ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, NULL, new_addr); + return ret; +} + /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50 * bytes on x86. Pick a number to fit into PAGE_SIZE / 2 */ @@ -77,8 +132,7 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr) int err; if (fentry_cnt + fexit_cnt == 0) { - err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_CALL, - old_image, NULL); + err = unregister_fentry(tr, old_image); tr->selector = 0; goto out; } @@ -105,12 +159,10 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr) if (tr->selector) /* progs already running at this address */ - err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_CALL, - old_image, new_image); + err = modify_fentry(tr, old_image, new_image); else /* first time registering */ - err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_CALL, NULL, - new_image); + err = register_fentry(tr, new_image); if (err) goto out; tr->selector++; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 034ef81f935b..4983940cbdca 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4134,6 +4134,7 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, struct bpf_map *map = meta->map_ptr; struct tnum range; u64 val; + int err; if (func_id != BPF_FUNC_tail_call) return 0; @@ -4150,6 +4151,10 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, return 0; } + err = mark_chain_precision(env, BPF_REG_3); + if (err) + return err; + val = reg->var_off.value; if (bpf_map_key_unseen(aux)) bpf_map_key_store(aux, val); @@ -8268,7 +8273,7 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) env->used_maps[env->used_map_cnt++] = map; if (bpf_map_is_cgroup_storage(map) && - bpf_cgroup_storage_assign(env->prog, map)) { + bpf_cgroup_storage_assign(env->prog->aux, map)) { verbose(env, "only one cgroup storage of each type is allowed\n"); fdput(f); return -EBUSY; @@ -8298,18 +8303,8 @@ next_insn: /* drop refcnt of maps used by the rejected program */ static void release_maps(struct bpf_verifier_env *env) { - enum bpf_cgroup_storage_type stype; - int i; - - for_each_cgroup_storage_type(stype) { - if (!env->prog->aux->cgroup_storage[stype]) - continue; - bpf_cgroup_storage_release(env->prog, - env->prog->aux->cgroup_storage[stype]); - } - - for (i = 0; i < env->used_map_cnt; i++) - bpf_map_put(env->used_maps[i]); + __bpf_free_used_maps(env->prog->aux, env->used_maps, + env->used_map_cnt); } /* convert pseudo BPF_LD_IMM64 into generic BPF_LD_IMM64 */ @@ -9282,7 +9277,8 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) insn->code = BPF_JMP | BPF_TAIL_CALL; aux = &env->insn_aux_data[i + delta]; - if (prog->jit_requested && !expect_blinding && + if (env->allow_ptr_leaks && !expect_blinding && + prog->jit_requested && !bpf_map_key_poisoned(aux) && !bpf_map_ptr_poisoned(aux) && !bpf_map_ptr_unpriv(aux)) { diff --git a/kernel/events/core.c b/kernel/events/core.c index 4ff86d57f9e5..a1f8bde19b56 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -10523,7 +10523,7 @@ again: goto unlock; } - list_for_each_entry_rcu(pmu, &pmus, entry) { + list_for_each_entry_rcu(pmu, &pmus, entry, lockdep_is_held(&pmus_srcu)) { ret = perf_try_init_event(pmu, event); if (!ret) goto unlock; diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index 54cc5f9286e9..5352ce50a97e 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -733,9 +733,6 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne */ void __sched mutex_unlock(struct mutex *lock) { -#ifdef CONFIG_DEBUG_MUTEXES - WARN_ON(in_interrupt()); -#endif #ifndef CONFIG_DEBUG_LOCK_ALLOC if (__mutex_unlock_fast(lock)) return; @@ -1416,7 +1413,6 @@ int __sched mutex_trylock(struct mutex *lock) #ifdef CONFIG_DEBUG_MUTEXES DEBUG_LOCKS_WARN_ON(lock->magic != lock); - WARN_ON(in_interrupt()); #endif locked = __mutex_trylock(lock); diff --git a/kernel/locking/spinlock_debug.c b/kernel/locking/spinlock_debug.c index 399669f7eba8..472dd462a40c 100644 --- a/kernel/locking/spinlock_debug.c +++ b/kernel/locking/spinlock_debug.c @@ -51,19 +51,19 @@ EXPORT_SYMBOL(__rwlock_init); static void spin_dump(raw_spinlock_t *lock, const char *msg) { - struct task_struct *owner = NULL; + struct task_struct *owner = READ_ONCE(lock->owner); - if (lock->owner && lock->owner != SPINLOCK_OWNER_INIT) - owner = lock->owner; + if (owner == SPINLOCK_OWNER_INIT) + owner = NULL; printk(KERN_EMERG "BUG: spinlock %s on CPU#%d, %s/%d\n", msg, raw_smp_processor_id(), current->comm, task_pid_nr(current)); printk(KERN_EMERG " lock: %pS, .magic: %08x, .owner: %s/%d, " ".owner_cpu: %d\n", - lock, lock->magic, + lock, READ_ONCE(lock->magic), owner ? owner->comm : "<none>", owner ? task_pid_nr(owner) : -1, - lock->owner_cpu); + READ_ONCE(lock->owner_cpu)); dump_stack(); } @@ -80,16 +80,16 @@ static void spin_bug(raw_spinlock_t *lock, const char *msg) static inline void debug_spin_lock_before(raw_spinlock_t *lock) { - SPIN_BUG_ON(lock->magic != SPINLOCK_MAGIC, lock, "bad magic"); - SPIN_BUG_ON(lock->owner == current, lock, "recursion"); - SPIN_BUG_ON(lock->owner_cpu == raw_smp_processor_id(), + SPIN_BUG_ON(READ_ONCE(lock->magic) != SPINLOCK_MAGIC, lock, "bad magic"); + SPIN_BUG_ON(READ_ONCE(lock->owner) == current, lock, "recursion"); + SPIN_BUG_ON(READ_ONCE(lock->owner_cpu) == raw_smp_processor_id(), lock, "cpu recursion"); } static inline void debug_spin_lock_after(raw_spinlock_t *lock) { - lock->owner_cpu = raw_smp_processor_id(); - lock->owner = current; + WRITE_ONCE(lock->owner_cpu, raw_smp_processor_id()); + WRITE_ONCE(lock->owner, current); } static inline void debug_spin_unlock(raw_spinlock_t *lock) @@ -99,8 +99,8 @@ static inline void debug_spin_unlock(raw_spinlock_t *lock) SPIN_BUG_ON(lock->owner != current, lock, "wrong owner"); SPIN_BUG_ON(lock->owner_cpu != raw_smp_processor_id(), lock, "wrong CPU"); - lock->owner = SPINLOCK_OWNER_INIT; - lock->owner_cpu = -1; + WRITE_ONCE(lock->owner, SPINLOCK_OWNER_INIT); + WRITE_ONCE(lock->owner_cpu, -1); } /* @@ -187,8 +187,8 @@ static inline void debug_write_lock_before(rwlock_t *lock) static inline void debug_write_lock_after(rwlock_t *lock) { - lock->owner_cpu = raw_smp_processor_id(); - lock->owner = current; + WRITE_ONCE(lock->owner_cpu, raw_smp_processor_id()); + WRITE_ONCE(lock->owner, current); } static inline void debug_write_unlock(rwlock_t *lock) @@ -197,8 +197,8 @@ static inline void debug_write_unlock(rwlock_t *lock) RWLOCK_BUG_ON(lock->owner != current, lock, "wrong owner"); RWLOCK_BUG_ON(lock->owner_cpu != raw_smp_processor_id(), lock, "wrong CPU"); - lock->owner = SPINLOCK_OWNER_INIT; - lock->owner_cpu = -1; + WRITE_ONCE(lock->owner, SPINLOCK_OWNER_INIT); + WRITE_ONCE(lock->owner_cpu, -1); } void do_raw_write_lock(rwlock_t *lock) diff --git a/kernel/sched/cpufreq.c b/kernel/sched/cpufreq.c index b5dcd1d83c7f..7c2fe50fd76d 100644 --- a/kernel/sched/cpufreq.c +++ b/kernel/sched/cpufreq.c @@ -5,6 +5,8 @@ * Copyright (C) 2016, Intel Corporation * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com> */ +#include <linux/cpufreq.h> + #include "sched.h" DEFINE_PER_CPU(struct update_util_data __rcu *, cpufreq_update_util_data); @@ -57,3 +59,19 @@ void cpufreq_remove_update_util_hook(int cpu) rcu_assign_pointer(per_cpu(cpufreq_update_util_data, cpu), NULL); } EXPORT_SYMBOL_GPL(cpufreq_remove_update_util_hook); + +/** + * cpufreq_this_cpu_can_update - Check if cpufreq policy can be updated. + * @policy: cpufreq policy to check. + * + * Return 'true' if: + * - the local and remote CPUs share @policy, + * - dvfs_possible_from_any_cpu is set in @policy and the local CPU is not going + * offline (in which case it is not expected to run cpufreq updates any more). + */ +bool cpufreq_this_cpu_can_update(struct cpufreq_policy *policy) +{ + return cpumask_test_cpu(smp_processor_id(), policy->cpus) || + (policy->dvfs_possible_from_any_cpu && + rcu_dereference_sched(*this_cpu_ptr(&cpufreq_update_util_data))); +} diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 322ca8860f54..9b8916fd00a2 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -82,12 +82,10 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time) * by the hardware, as calculating the frequency is pointless if * we cannot in fact act on it. * - * For the slow switching platforms, the kthread is always scheduled on - * the right set of CPUs and any CPU can find the next frequency and - * schedule the kthread. + * This is needed on the slow switching platforms too to prevent CPUs + * going offline from leaving stale IRQ work items behind. */ - if (sg_policy->policy->fast_switch_enabled && - !cpufreq_this_cpu_can_update(sg_policy->policy)) + if (!cpufreq_this_cpu_can_update(sg_policy->policy)) return false; if (unlikely(sg_policy->limits_changed)) { diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 08a233e97a01..ba749f579714 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -7328,7 +7328,14 @@ static int detach_tasks(struct lb_env *env) load < 16 && !env->sd->nr_balance_failed) goto next; - if (load/2 > env->imbalance) + /* + * Make sure that we don't migrate too much load. + * Nevertheless, let relax the constraint if + * scheduler fails to find a good waiting task to + * migrate. + */ + if (load/2 > env->imbalance && + env->sd->nr_balance_failed <= env->sd->cache_nice_tries) goto next; env->imbalance -= load; @@ -8417,6 +8424,10 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, if (!idlest) return NULL; + /* The local group has been skipped because of CPU affinity */ + if (!local) + return idlest; + /* * If the local group is idler than the selected idlest group * don't try and push the task. diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 517e3719027e..ce8f6748678a 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -185,7 +185,8 @@ static void group_init(struct psi_group *group) for_each_possible_cpu(cpu) seqcount_init(&per_cpu_ptr(group->pcpu, cpu)->seq); - group->avg_next_update = sched_clock() + psi_period; + group->avg_last_update = sched_clock(); + group->avg_next_update = group->avg_last_update + psi_period; INIT_DELAYED_WORK(&group->avgs_work, psi_avgs_work); mutex_init(&group->avgs_lock); /* Init trigger-related members */ @@ -481,7 +482,7 @@ static u64 window_update(struct psi_window *win, u64 now, u64 value) u32 remaining; remaining = win->size - elapsed; - growth += div_u64(win->prev_growth * remaining, win->size); + growth += div64_u64(win->prev_growth * remaining, win->size); } return growth; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 6c75410f9698..ddb7e7f5fe8d 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4685,6 +4685,10 @@ int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set) int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled) { + if ((mask == TRACE_ITER_RECORD_TGID) || + (mask == TRACE_ITER_RECORD_CMD)) + lockdep_assert_held(&event_mutex); + /* do nothing if flag is already set */ if (!!(tr->trace_flags & mask) == !!enabled) return 0; @@ -4752,6 +4756,7 @@ static int trace_set_options(struct trace_array *tr, char *option) cmp += len; + mutex_lock(&event_mutex); mutex_lock(&trace_types_lock); ret = match_string(trace_options, -1, cmp); @@ -4762,6 +4767,7 @@ static int trace_set_options(struct trace_array *tr, char *option) ret = set_tracer_flag(tr, 1 << ret, !neg); mutex_unlock(&trace_types_lock); + mutex_unlock(&event_mutex); /* * If the first trailing whitespace is replaced with '\0' by strstrip, @@ -8076,9 +8082,11 @@ trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt, if (val != 0 && val != 1) return -EINVAL; + mutex_lock(&event_mutex); mutex_lock(&trace_types_lock); ret = set_tracer_flag(tr, 1 << index, val); mutex_unlock(&trace_types_lock); + mutex_unlock(&event_mutex); if (ret < 0) return ret; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index c6de3cebc127..a5b614cc3887 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -320,7 +320,8 @@ void trace_event_enable_cmd_record(bool enable) struct trace_event_file *file; struct trace_array *tr; - mutex_lock(&event_mutex); + lockdep_assert_held(&event_mutex); + do_for_each_event_file(tr, file) { if (!(file->flags & EVENT_FILE_FL_ENABLED)) @@ -334,7 +335,6 @@ void trace_event_enable_cmd_record(bool enable) clear_bit(EVENT_FILE_FL_RECORDED_CMD_BIT, &file->flags); } } while_for_each_event_file(); - mutex_unlock(&event_mutex); } void trace_event_enable_tgid_record(bool enable) @@ -342,7 +342,8 @@ void trace_event_enable_tgid_record(bool enable) struct trace_event_file *file; struct trace_array *tr; - mutex_lock(&event_mutex); + lockdep_assert_held(&event_mutex); + do_for_each_event_file(tr, file) { if (!(file->flags & EVENT_FILE_FL_ENABLED)) continue; @@ -356,7 +357,6 @@ void trace_event_enable_tgid_record(bool enable) &file->flags); } } while_for_each_event_file(); - mutex_unlock(&event_mutex); } static int __ftrace_event_enable_disable(struct trace_event_file *file, diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index c9a74f82b14a..bf44f6bbd0c3 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -1662,7 +1662,7 @@ static int process_system_preds(struct trace_subsystem_dir *dir, parse_error(pe, FILT_ERR_BAD_SUBSYS_FILTER, 0); return -EINVAL; fail_mem: - kfree(filter); + __free_filter(filter); /* If any call succeeded, we still need to sync */ if (!fail) tracepoint_synchronize_unregister(); diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index f49d1a36d3ae..f62de5f43e79 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -911,7 +911,26 @@ static notrace void trace_event_raw_event_synth(void *__data, strscpy(str_field, str_val, STR_VAR_LEN_MAX); n_u64 += STR_VAR_LEN_MAX / sizeof(u64); } else { - entry->fields[n_u64] = var_ref_vals[var_ref_idx + i]; + struct synth_field *field = event->fields[i]; + u64 val = var_ref_vals[var_ref_idx + i]; + + switch (field->size) { + case 1: + *(u8 *)&entry->fields[n_u64] = (u8)val; + break; + + case 2: + *(u16 *)&entry->fields[n_u64] = (u16)val; + break; + + case 4: + *(u32 *)&entry->fields[n_u64] = (u32)val; + break; + + default: + entry->fields[n_u64] = val; + break; + } n_u64++; } } diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c index 9a1c22310323..9e31bfc818ff 100644 --- a/kernel/trace/tracing_map.c +++ b/kernel/trace/tracing_map.c @@ -148,8 +148,8 @@ static int tracing_map_cmp_atomic64(void *val_a, void *val_b) #define DEFINE_TRACING_MAP_CMP_FN(type) \ static int tracing_map_cmp_##type(void *val_a, void *val_b) \ { \ - type a = *(type *)val_a; \ - type b = *(type *)val_b; \ + type a = (type)(*(u64 *)val_a); \ + type b = (type)(*(u64 *)val_b); \ \ return (a > b) ? 1 : ((a < b) ? -1 : 0); \ } diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index d1842fe756d5..5ffe144c9794 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1483,6 +1483,55 @@ config PROVIDE_OHCI1394_DMA_INIT See Documentation/debugging-via-ohci1394.txt for more information. +source "samples/Kconfig" + +config ARCH_HAS_DEVMEM_IS_ALLOWED + bool + +config STRICT_DEVMEM + bool "Filter access to /dev/mem" + depends on MMU && DEVMEM + depends on ARCH_HAS_DEVMEM_IS_ALLOWED + default y if PPC || X86 || ARM64 + help + If this option is disabled, you allow userspace (root) access to all + of memory, including kernel and userspace memory. Accidental + access to this is obviously disastrous, but specific access can + be used by people debugging the kernel. Note that with PAT support + enabled, even in this case there are restrictions on /dev/mem + use due to the cache aliasing requirements. + + If this option is switched on, and IO_STRICT_DEVMEM=n, the /dev/mem + file only allows userspace access to PCI space and the BIOS code and + data regions. This is sufficient for dosemu and X and all common + users of /dev/mem. + + If in doubt, say Y. + +config IO_STRICT_DEVMEM + bool "Filter I/O access to /dev/mem" + depends on STRICT_DEVMEM + help + If this option is disabled, you allow userspace (root) access to all + io-memory regardless of whether a driver is actively using that + range. Accidental access to this is obviously disastrous, but + specific access can be used by people debugging kernel drivers. + + If this option is switched on, the /dev/mem file only allows + userspace access to *idle* io-memory ranges (see /proc/iomem) This + may break traditional users of /dev/mem (dosemu, legacy X, etc...) + if the driver using a given range cannot be disabled. + + If in doubt, say Y. + +menu "$(SRCARCH) Debugging" + +source "arch/$(SRCARCH)/Kconfig.debug" + +endmenu + +menu "Kernel Testing and Coverage" + source "lib/kunit/Kconfig" config NOTIFIER_ERROR_INJECTION @@ -1643,10 +1692,6 @@ config FAULT_INJECTION_STACKTRACE_FILTER help Provide stacktrace filter for fault-injection capabilities -endmenu # "Kernel Testing and Coverage" - -menu "Kernel Testing and Coverage" - config ARCH_HAS_KCOV bool help @@ -2130,52 +2175,7 @@ config MEMTEST memtest=17, mean do 17 test patterns. If you are unsure how to answer this question, answer N. -source "samples/Kconfig" - -config ARCH_HAS_DEVMEM_IS_ALLOWED - bool - -config STRICT_DEVMEM - bool "Filter access to /dev/mem" - depends on MMU && DEVMEM - depends on ARCH_HAS_DEVMEM_IS_ALLOWED - default y if PPC || X86 || ARM64 - ---help--- - If this option is disabled, you allow userspace (root) access to all - of memory, including kernel and userspace memory. Accidental - access to this is obviously disastrous, but specific access can - be used by people debugging the kernel. Note that with PAT support - enabled, even in this case there are restrictions on /dev/mem - use due to the cache aliasing requirements. - - If this option is switched on, and IO_STRICT_DEVMEM=n, the /dev/mem - file only allows userspace access to PCI space and the BIOS code and - data regions. This is sufficient for dosemu and X and all common - users of /dev/mem. - - If in doubt, say Y. -config IO_STRICT_DEVMEM - bool "Filter I/O access to /dev/mem" - depends on STRICT_DEVMEM - ---help--- - If this option is disabled, you allow userspace (root) access to all - io-memory regardless of whether a driver is actively using that - range. Accidental access to this is obviously disastrous, but - specific access can be used by people debugging kernel drivers. - - If this option is switched on, the /dev/mem file only allows - userspace access to *idle* io-memory ranges (see /proc/iomem) This - may break traditional users of /dev/mem (dosemu, legacy X, etc...) - if the driver using a given range cannot be disabled. - - If in doubt, say Y. - -menu "$(SRCARCH) Debugging" - -source "arch/$(SRCARCH)/Kconfig.debug" - -endmenu config HYPERV_TESTING bool "Microsoft Hyper-V driver testing" @@ -2184,4 +2184,6 @@ config HYPERV_TESTING help Select this option to enable Hyper-V vmbus testing. +endmenu # "Kernel Testing and Coverage" + endmenu # Kernel hacking diff --git a/lib/iov_iter.c b/lib/iov_iter.c index fb29c02c6a3c..51595bf3af85 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -1222,11 +1222,12 @@ EXPORT_SYMBOL(iov_iter_discard); unsigned long iov_iter_alignment(const struct iov_iter *i) { - unsigned int p_mask = i->pipe->ring_size - 1; unsigned long res = 0; size_t size = i->count; if (unlikely(iov_iter_is_pipe(i))) { + unsigned int p_mask = i->pipe->ring_size - 1; + if (size && i->iov_offset && allocated(&i->pipe->bufs[i->head & p_mask])) return size | i->iov_offset; return size; diff --git a/lib/sbitmap.c b/lib/sbitmap.c index 33feec8989f1..af88d1346dd7 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -650,8 +650,8 @@ void sbitmap_add_wait_queue(struct sbitmap_queue *sbq, if (!sbq_wait->sbq) { sbq_wait->sbq = sbq; atomic_inc(&sbq->ws_active); + add_wait_queue(&ws->wait, &sbq_wait->wait); } - add_wait_queue(&ws->wait, &sbq_wait->wait); } EXPORT_SYMBOL_GPL(sbitmap_add_wait_queue); diff --git a/mm/kasan/common.c b/mm/kasan/common.c index 2fa710bb6358..c15d8ae68c96 100644 --- a/mm/kasan/common.c +++ b/mm/kasan/common.c @@ -778,15 +778,17 @@ static int kasan_populate_vmalloc_pte(pte_t *ptep, unsigned long addr, return 0; } -int kasan_populate_vmalloc(unsigned long requested_size, struct vm_struct *area) +int kasan_populate_vmalloc(unsigned long addr, unsigned long size) { unsigned long shadow_start, shadow_end; int ret; - shadow_start = (unsigned long)kasan_mem_to_shadow(area->addr); + if (!is_vmalloc_or_module_addr((void *)addr)) + return 0; + + shadow_start = (unsigned long)kasan_mem_to_shadow((void *)addr); shadow_start = ALIGN_DOWN(shadow_start, PAGE_SIZE); - shadow_end = (unsigned long)kasan_mem_to_shadow(area->addr + - area->size); + shadow_end = (unsigned long)kasan_mem_to_shadow((void *)addr + size); shadow_end = ALIGN(shadow_end, PAGE_SIZE); ret = apply_to_page_range(&init_mm, shadow_start, @@ -797,10 +799,6 @@ int kasan_populate_vmalloc(unsigned long requested_size, struct vm_struct *area) flush_cache_vmap(shadow_start, shadow_end); - kasan_unpoison_shadow(area->addr, requested_size); - - area->flags |= VM_KASAN; - /* * We need to be careful about inter-cpu effects here. Consider: * @@ -843,12 +841,23 @@ int kasan_populate_vmalloc(unsigned long requested_size, struct vm_struct *area) * Poison the shadow for a vmalloc region. Called as part of the * freeing process at the time the region is freed. */ -void kasan_poison_vmalloc(void *start, unsigned long size) +void kasan_poison_vmalloc(const void *start, unsigned long size) { + if (!is_vmalloc_or_module_addr(start)) + return; + size = round_up(size, KASAN_SHADOW_SCALE_SIZE); kasan_poison_shadow(start, size, KASAN_VMALLOC_INVALID); } +void kasan_unpoison_vmalloc(const void *start, unsigned long size) +{ + if (!is_vmalloc_or_module_addr(start)) + return; + + kasan_unpoison_shadow(start, size); +} + static int kasan_depopulate_vmalloc_pte(pte_t *ptep, unsigned long addr, void *unused) { @@ -948,6 +957,7 @@ void kasan_release_vmalloc(unsigned long start, unsigned long end, { void *shadow_start, *shadow_end; unsigned long region_start, region_end; + unsigned long size; region_start = ALIGN(start, PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE); region_end = ALIGN_DOWN(end, PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE); @@ -970,9 +980,11 @@ void kasan_release_vmalloc(unsigned long start, unsigned long end, shadow_end = kasan_mem_to_shadow((void *)region_end); if (shadow_end > shadow_start) { - apply_to_page_range(&init_mm, (unsigned long)shadow_start, - (unsigned long)(shadow_end - shadow_start), - kasan_depopulate_vmalloc_pte, NULL); + size = shadow_end - shadow_start; + apply_to_existing_page_range(&init_mm, + (unsigned long)shadow_start, + size, kasan_depopulate_vmalloc_pte, + NULL); flush_tlb_kernel_range((unsigned long)shadow_start, (unsigned long)shadow_end); } diff --git a/mm/memory.c b/mm/memory.c index 606da187d1de..45442d9a4f52 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2021,26 +2021,34 @@ EXPORT_SYMBOL(vm_iomap_memory); static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, unsigned long end, - pte_fn_t fn, void *data) + pte_fn_t fn, void *data, bool create) { pte_t *pte; - int err; + int err = 0; spinlock_t *uninitialized_var(ptl); - pte = (mm == &init_mm) ? - pte_alloc_kernel(pmd, addr) : - pte_alloc_map_lock(mm, pmd, addr, &ptl); - if (!pte) - return -ENOMEM; + if (create) { + pte = (mm == &init_mm) ? + pte_alloc_kernel(pmd, addr) : + pte_alloc_map_lock(mm, pmd, addr, &ptl); + if (!pte) + return -ENOMEM; + } else { + pte = (mm == &init_mm) ? + pte_offset_kernel(pmd, addr) : + pte_offset_map_lock(mm, pmd, addr, &ptl); + } BUG_ON(pmd_huge(*pmd)); arch_enter_lazy_mmu_mode(); do { - err = fn(pte++, addr, data); - if (err) - break; + if (create || !pte_none(*pte)) { + err = fn(pte++, addr, data); + if (err) + break; + } } while (addr += PAGE_SIZE, addr != end); arch_leave_lazy_mmu_mode(); @@ -2052,77 +2060,95 @@ static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd, static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud, unsigned long addr, unsigned long end, - pte_fn_t fn, void *data) + pte_fn_t fn, void *data, bool create) { pmd_t *pmd; unsigned long next; - int err; + int err = 0; BUG_ON(pud_huge(*pud)); - pmd = pmd_alloc(mm, pud, addr); - if (!pmd) - return -ENOMEM; + if (create) { + pmd = pmd_alloc(mm, pud, addr); + if (!pmd) + return -ENOMEM; + } else { + pmd = pmd_offset(pud, addr); + } do { next = pmd_addr_end(addr, end); - err = apply_to_pte_range(mm, pmd, addr, next, fn, data); - if (err) - break; + if (create || !pmd_none_or_clear_bad(pmd)) { + err = apply_to_pte_range(mm, pmd, addr, next, fn, data, + create); + if (err) + break; + } } while (pmd++, addr = next, addr != end); return err; } static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d, unsigned long addr, unsigned long end, - pte_fn_t fn, void *data) + pte_fn_t fn, void *data, bool create) { pud_t *pud; unsigned long next; - int err; + int err = 0; - pud = pud_alloc(mm, p4d, addr); - if (!pud) - return -ENOMEM; + if (create) { + pud = pud_alloc(mm, p4d, addr); + if (!pud) + return -ENOMEM; + } else { + pud = pud_offset(p4d, addr); + } do { next = pud_addr_end(addr, end); - err = apply_to_pmd_range(mm, pud, addr, next, fn, data); - if (err) - break; + if (create || !pud_none_or_clear_bad(pud)) { + err = apply_to_pmd_range(mm, pud, addr, next, fn, data, + create); + if (err) + break; + } } while (pud++, addr = next, addr != end); return err; } static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd, unsigned long addr, unsigned long end, - pte_fn_t fn, void *data) + pte_fn_t fn, void *data, bool create) { p4d_t *p4d; unsigned long next; - int err; + int err = 0; - p4d = p4d_alloc(mm, pgd, addr); - if (!p4d) - return -ENOMEM; + if (create) { + p4d = p4d_alloc(mm, pgd, addr); + if (!p4d) + return -ENOMEM; + } else { + p4d = p4d_offset(pgd, addr); + } do { next = p4d_addr_end(addr, end); - err = apply_to_pud_range(mm, p4d, addr, next, fn, data); - if (err) - break; + if (create || !p4d_none_or_clear_bad(p4d)) { + err = apply_to_pud_range(mm, p4d, addr, next, fn, data, + create); + if (err) + break; + } } while (p4d++, addr = next, addr != end); return err; } -/* - * Scan a region of virtual memory, filling in page tables as necessary - * and calling a provided function on each leaf page table. - */ -int apply_to_page_range(struct mm_struct *mm, unsigned long addr, - unsigned long size, pte_fn_t fn, void *data) +static int __apply_to_page_range(struct mm_struct *mm, unsigned long addr, + unsigned long size, pte_fn_t fn, + void *data, bool create) { pgd_t *pgd; unsigned long next; unsigned long end = addr + size; - int err; + int err = 0; if (WARN_ON(addr >= end)) return -EINVAL; @@ -2130,16 +2156,42 @@ int apply_to_page_range(struct mm_struct *mm, unsigned long addr, pgd = pgd_offset(mm, addr); do { next = pgd_addr_end(addr, end); - err = apply_to_p4d_range(mm, pgd, addr, next, fn, data); + if (!create && pgd_none_or_clear_bad(pgd)) + continue; + err = apply_to_p4d_range(mm, pgd, addr, next, fn, data, create); if (err) break; } while (pgd++, addr = next, addr != end); return err; } + +/* + * Scan a region of virtual memory, filling in page tables as necessary + * and calling a provided function on each leaf page table. + */ +int apply_to_page_range(struct mm_struct *mm, unsigned long addr, + unsigned long size, pte_fn_t fn, void *data) +{ + return __apply_to_page_range(mm, addr, size, fn, data, true); +} EXPORT_SYMBOL_GPL(apply_to_page_range); /* + * Scan a region of virtual memory, calling a provided function on + * each leaf page table where it exists. + * + * Unlike apply_to_page_range, this does _not_ fill in page tables + * where they are absent. + */ +int apply_to_existing_page_range(struct mm_struct *mm, unsigned long addr, + unsigned long size, pte_fn_t fn, void *data) +{ + return __apply_to_page_range(mm, addr, size, fn, data, false); +} +EXPORT_SYMBOL_GPL(apply_to_existing_page_range); + +/* * handle_pte_fault chooses page fault handler according to an entry which was * read non-atomically. Before making any commitment, on those architectures * or configurations (e.g. i386 with PAE) which might give a mix of unmatched diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 4d3b3d60d893..e9681dc4aa75 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1062,6 +1062,26 @@ __alloc_vmap_area(unsigned long size, unsigned long align, } /* + * Free a region of KVA allocated by alloc_vmap_area + */ +static void free_vmap_area(struct vmap_area *va) +{ + /* + * Remove from the busy tree/list. + */ + spin_lock(&vmap_area_lock); + unlink_va(va, &vmap_area_root); + spin_unlock(&vmap_area_lock); + + /* + * Insert/Merge it back to the free tree/list. + */ + spin_lock(&free_vmap_area_lock); + merge_or_add_vmap_area(va, &free_vmap_area_root, &free_vmap_area_list); + spin_unlock(&free_vmap_area_lock); +} + +/* * Allocate a region of KVA of the specified size and alignment, within the * vstart and vend. */ @@ -1073,6 +1093,7 @@ static struct vmap_area *alloc_vmap_area(unsigned long size, struct vmap_area *va, *pva; unsigned long addr; int purged = 0; + int ret; BUG_ON(!size); BUG_ON(offset_in_page(size)); @@ -1139,6 +1160,7 @@ retry: va->va_end = addr + size; va->vm = NULL; + spin_lock(&vmap_area_lock); insert_vmap_area(va, &vmap_area_root, &vmap_area_list); spin_unlock(&vmap_area_lock); @@ -1147,6 +1169,12 @@ retry: BUG_ON(va->va_start < vstart); BUG_ON(va->va_end > vend); + ret = kasan_populate_vmalloc(addr, size); + if (ret) { + free_vmap_area(va); + return ERR_PTR(ret); + } + return va; overflow: @@ -1186,26 +1214,6 @@ int unregister_vmap_purge_notifier(struct notifier_block *nb) EXPORT_SYMBOL_GPL(unregister_vmap_purge_notifier); /* - * Free a region of KVA allocated by alloc_vmap_area - */ -static void free_vmap_area(struct vmap_area *va) -{ - /* - * Remove from the busy tree/list. - */ - spin_lock(&vmap_area_lock); - unlink_va(va, &vmap_area_root); - spin_unlock(&vmap_area_lock); - - /* - * Insert/Merge it back to the free tree/list. - */ - spin_lock(&free_vmap_area_lock); - merge_or_add_vmap_area(va, &free_vmap_area_root, &free_vmap_area_list); - spin_unlock(&free_vmap_area_lock); -} - -/* * Clear the pagetable entries of a given vmap_area */ static void unmap_vmap_area(struct vmap_area *va) @@ -1771,6 +1779,8 @@ void vm_unmap_ram(const void *mem, unsigned int count) BUG_ON(addr > VMALLOC_END); BUG_ON(!PAGE_ALIGNED(addr)); + kasan_poison_vmalloc(mem, size); + if (likely(count <= VMAP_MAX_ALLOC)) { debug_check_no_locks_freed(mem, size); vb_free(mem, size); @@ -1821,6 +1831,9 @@ void *vm_map_ram(struct page **pages, unsigned int count, int node, pgprot_t pro addr = va->va_start; mem = (void *)addr; } + + kasan_unpoison_vmalloc(mem, size); + if (vmap_page_range(addr, addr + size, prot, pages) < 0) { vm_unmap_ram(mem, count); return NULL; @@ -2075,6 +2088,7 @@ static struct vm_struct *__get_vm_area_node(unsigned long size, { struct vmap_area *va; struct vm_struct *area; + unsigned long requested_size = size; BUG_ON(in_interrupt()); size = PAGE_ALIGN(size); @@ -2098,23 +2112,9 @@ static struct vm_struct *__get_vm_area_node(unsigned long size, return NULL; } - setup_vmalloc_vm(area, va, flags, caller); + kasan_unpoison_vmalloc((void *)va->va_start, requested_size); - /* - * For KASAN, if we are in vmalloc space, we need to cover the shadow - * area with real memory. If we come here through VM_ALLOC, this is - * done by a higher level function that has access to the true size, - * which might not be a full page. - * - * We assume module space comes via VM_ALLOC path. - */ - if (is_vmalloc_addr(area->addr) && !(area->flags & VM_ALLOC)) { - if (kasan_populate_vmalloc(area->size, area)) { - unmap_vmap_area(va); - kfree(area); - return NULL; - } - } + setup_vmalloc_vm(area, va, flags, caller); return area; } @@ -2293,8 +2293,7 @@ static void __vunmap(const void *addr, int deallocate_pages) debug_check_no_locks_freed(area->addr, get_vm_area_size(area)); debug_check_no_obj_freed(area->addr, get_vm_area_size(area)); - if (area->flags & VM_KASAN) - kasan_poison_vmalloc(area->addr, area->size); + kasan_poison_vmalloc(area->addr, area->size); vm_remove_mappings(area, deallocate_pages); @@ -2539,7 +2538,7 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align, if (!size || (size >> PAGE_SHIFT) > totalram_pages()) goto fail; - area = __get_vm_area_node(size, align, VM_ALLOC | VM_UNINITIALIZED | + area = __get_vm_area_node(real_size, align, VM_ALLOC | VM_UNINITIALIZED | vm_flags, start, end, node, gfp_mask, caller); if (!area) goto fail; @@ -2548,11 +2547,6 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align, if (!addr) return NULL; - if (is_vmalloc_or_module_addr(area->addr)) { - if (kasan_populate_vmalloc(real_size, area)) - return NULL; - } - /* * In this function, newly allocated vm_struct has VM_UNINITIALIZED * flag. It means that vm_struct is not fully initialized. @@ -3294,7 +3288,7 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, struct vmap_area **vas, *va; struct vm_struct **vms; int area, area2, last_area, term_area; - unsigned long base, start, size, end, last_end; + unsigned long base, start, size, end, last_end, orig_start, orig_end; bool purged = false; enum fit_type type; @@ -3424,6 +3418,15 @@ retry: spin_unlock(&free_vmap_area_lock); + /* populate the kasan shadow space */ + for (area = 0; area < nr_vms; area++) { + if (kasan_populate_vmalloc(vas[area]->va_start, sizes[area])) + goto err_free_shadow; + + kasan_unpoison_vmalloc((void *)vas[area]->va_start, + sizes[area]); + } + /* insert all vm's */ spin_lock(&vmap_area_lock); for (area = 0; area < nr_vms; area++) { @@ -3434,12 +3437,6 @@ retry: } spin_unlock(&vmap_area_lock); - /* populate the shadow space outside of the lock */ - for (area = 0; area < nr_vms; area++) { - /* assume success here */ - kasan_populate_vmalloc(sizes[area], vms[area]); - } - kfree(vas); return vms; @@ -3451,8 +3448,12 @@ recovery: * and when pcpu_get_vm_areas() is success. */ while (area--) { - merge_or_add_vmap_area(vas[area], &free_vmap_area_root, - &free_vmap_area_list); + orig_start = vas[area]->va_start; + orig_end = vas[area]->va_end; + va = merge_or_add_vmap_area(vas[area], &free_vmap_area_root, + &free_vmap_area_list); + kasan_release_vmalloc(orig_start, orig_end, + va->va_start, va->va_end); vas[area] = NULL; } @@ -3487,6 +3488,28 @@ err_free2: kfree(vas); kfree(vms); return NULL; + +err_free_shadow: + spin_lock(&free_vmap_area_lock); + /* + * We release all the vmalloc shadows, even the ones for regions that + * hadn't been successfully added. This relies on kasan_release_vmalloc + * being able to tolerate this case. + */ + for (area = 0; area < nr_vms; area++) { + orig_start = vas[area]->va_start; + orig_end = vas[area]->va_end; + va = merge_or_add_vmap_area(vas[area], &free_vmap_area_root, + &free_vmap_area_list); + kasan_release_vmalloc(orig_start, orig_end, + va->va_start, va->va_end); + vas[area] = NULL; + kfree(vms[area]); + } + spin_unlock(&free_vmap_area_lock); + kfree(vas); + kfree(vms); + return NULL; } /** diff --git a/mm/vmscan.c b/mm/vmscan.c index 74e8edce83ca..572fb17c6273 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -387,7 +387,7 @@ void register_shrinker_prepared(struct shrinker *shrinker) { down_write(&shrinker_rwsem); list_add_tail(&shrinker->list, &shrinker_list); -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG if (shrinker->flags & SHRINKER_MEMCG_AWARE) idr_replace(&shrinker_idr, shrinker, shrinker->id); #endif diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index af7800103e51..59980ecfc962 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -662,6 +662,9 @@ static unsigned int br_nf_forward_arp(void *priv, nf_bridge_pull_encap_header(skb); } + if (unlikely(!pskb_may_pull(skb, sizeof(struct arphdr)))) + return NF_DROP; + if (arp_hdr(skb)->ar_pln != 4) { if (is_vlan_arp(skb, state->net)) nf_bridge_push_encap_header(skb); diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index de09b0a65791..f7587428febd 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -423,9 +423,9 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len) { struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; struct j1939_sock *jsk = j1939_sk(sock->sk); - struct j1939_priv *priv = jsk->priv; - struct sock *sk = sock->sk; - struct net *net = sock_net(sk); + struct j1939_priv *priv; + struct sock *sk; + struct net *net; int ret = 0; ret = j1939_sk_sanity_check(addr, len); @@ -434,6 +434,10 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len) lock_sock(sock->sk); + priv = jsk->priv; + sk = sock->sk; + net = sock_net(sk); + /* Already bound to an interface? */ if (jsk->state & J1939_SOCK_BOUND) { /* A re-bind() to a different interface is not diff --git a/net/core/filter.c b/net/core/filter.c index c19dd0973e0c..28b3c258188c 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2055,6 +2055,7 @@ static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb) } skb->dev = dev; + skb->tstamp = 0; dev_xmit_recursion_inc(); ret = dev_queue_xmit(skb); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 652da6369037..920784a9b7ff 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -98,9 +98,6 @@ static int neigh_blackhole(struct neighbour *neigh, struct sk_buff *skb) static void neigh_cleanup_and_release(struct neighbour *neigh) { - if (neigh->parms->neigh_cleanup) - neigh->parms->neigh_cleanup(neigh); - trace_neigh_cleanup_and_release(neigh, 0); __neigh_notify(neigh, RTM_DELNEIGH, 0, 0); call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, neigh); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 5c4624298996..4c826b8bf9b1 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -919,14 +919,17 @@ static int rx_queue_add_kobject(struct net_device *dev, int index) struct kobject *kobj = &queue->kobj; int error = 0; + /* Kobject_put later will trigger rx_queue_release call which + * decreases dev refcount: Take that reference here + */ + dev_hold(queue->dev); + kobj->kset = dev->queues_kset; error = kobject_init_and_add(kobj, &rx_queue_ktype, NULL, "rx-%u", index); if (error) goto err; - dev_hold(queue->dev); - if (dev->sysfs_rx_queue_group) { error = sysfs_create_group(kobj, dev->sysfs_rx_queue_group); if (error) diff --git a/net/core/sock.c b/net/core/sock.c index 043db3ce023e..8459ad579f73 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2916,7 +2916,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_max_pacing_rate = ~0UL; sk->sk_pacing_rate = ~0UL; - sk->sk_pacing_shift = 10; + WRITE_ONCE(sk->sk_pacing_shift, 10); sk->sk_incoming_cpu = -1; sk_rx_queue_clear(sk); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index eb29e5adc84d..9f9e00ba3ad7 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -288,6 +288,7 @@ static int proc_dointvec_minmax_bpf_enable(struct ctl_table *table, int write, return ret; } +# ifdef CONFIG_HAVE_EBPF_JIT static int proc_dointvec_minmax_bpf_restricted(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, @@ -298,6 +299,7 @@ proc_dointvec_minmax_bpf_restricted(struct ctl_table *table, int write, return proc_dointvec_minmax(table, write, buffer, lenp, ppos); } +# endif /* CONFIG_HAVE_EBPF_JIT */ static int proc_dolongvec_minmax_bpf_restricted(struct ctl_table *table, int write, diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 9ef2caa13f27..c66abbed4daf 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -124,7 +124,8 @@ static struct dsa_port *dsa_tree_find_port_by_node(struct dsa_switch_tree *dst, return NULL; } -struct dsa_link *dsa_link_touch(struct dsa_port *dp, struct dsa_port *link_dp) +static struct dsa_link *dsa_link_touch(struct dsa_port *dp, + struct dsa_port *link_dp) { struct dsa_switch *ds = dp->ds; struct dsa_switch_tree *dst; diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index 73605bcbb385..90d055c4df9e 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -84,8 +84,6 @@ static struct sk_buff *ksz_common_rcv(struct sk_buff *skb, * (eg, 0x00=port1, 0x02=port3, 0x06=port7) */ -#define KSZ8795_INGRESS_TAG_LEN 1 - #define KSZ8795_TAIL_TAG_OVERRIDE BIT(6) #define KSZ8795_TAIL_TAG_LOOKUP BIT(7) @@ -96,12 +94,12 @@ static struct sk_buff *ksz8795_xmit(struct sk_buff *skb, struct net_device *dev) u8 *tag; u8 *addr; - nskb = ksz_common_xmit(skb, dev, KSZ8795_INGRESS_TAG_LEN); + nskb = ksz_common_xmit(skb, dev, KSZ_INGRESS_TAG_LEN); if (!nskb) return NULL; /* Tag encoding */ - tag = skb_put(nskb, KSZ8795_INGRESS_TAG_LEN); + tag = skb_put(nskb, KSZ_INGRESS_TAG_LEN); addr = skb_mac_header(nskb); *tag = 1 << dp->index; @@ -124,7 +122,7 @@ static const struct dsa_device_ops ksz8795_netdev_ops = { .proto = DSA_TAG_PROTO_KSZ8795, .xmit = ksz8795_xmit, .rcv = ksz8795_rcv, - .overhead = KSZ8795_INGRESS_TAG_LEN, + .overhead = KSZ_INGRESS_TAG_LEN, }; DSA_TAG_DRIVER(ksz8795_netdev_ops); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index af154977904c..f11e997e517b 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -911,11 +911,12 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb, for (i = s_i; i < INET_LHTABLE_SIZE; i++) { struct inet_listen_hashbucket *ilb; + struct hlist_nulls_node *node; num = 0; ilb = &hashinfo->listening_hash[i]; spin_lock(&ilb->lock); - sk_for_each(sk, &ilb->head) { + sk_nulls_for_each(sk, node, &ilb->nulls_head) { struct inet_sock *inet = inet_sk(sk); if (!net_eq(sock_net(sk), net)) diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 83fb00153018..2bbaaf0c7176 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -516,10 +516,11 @@ static int inet_reuseport_add_sock(struct sock *sk, struct inet_listen_hashbucket *ilb) { struct inet_bind_bucket *tb = inet_csk(sk)->icsk_bind_hash; + const struct hlist_nulls_node *node; struct sock *sk2; kuid_t uid = sock_i_uid(sk); - sk_for_each_rcu(sk2, &ilb->head) { + sk_nulls_for_each_rcu(sk2, node, &ilb->nulls_head) { if (sk2 != sk && sk2->sk_family == sk->sk_family && ipv6_only_sock(sk2) == ipv6_only_sock(sk) && @@ -555,9 +556,9 @@ int __inet_hash(struct sock *sk, struct sock *osk) } if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport && sk->sk_family == AF_INET6) - hlist_add_tail_rcu(&sk->sk_node, &ilb->head); + __sk_nulls_add_node_tail_rcu(sk, &ilb->nulls_head); else - hlist_add_head_rcu(&sk->sk_node, &ilb->head); + __sk_nulls_add_node_rcu(sk, &ilb->nulls_head); inet_hash2(hashinfo, sk); ilb->count++; sock_set_flag(sk, SOCK_RCU_FREE); @@ -606,11 +607,9 @@ void inet_unhash(struct sock *sk) reuseport_detach_sock(sk); if (ilb) { inet_unhash2(hashinfo, sk); - __sk_del_node_init(sk); - ilb->count--; - } else { - __sk_nulls_del_node_init_rcu(sk); + ilb->count--; } + __sk_nulls_del_node_init_rcu(sk); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); unlock: spin_unlock_bh(lock); @@ -750,7 +749,8 @@ void inet_hashinfo_init(struct inet_hashinfo *h) for (i = 0; i < INET_LHTABLE_SIZE; i++) { spin_lock_init(&h->listening_hash[i].lock); - INIT_HLIST_HEAD(&h->listening_hash[i].head); + INIT_HLIST_NULLS_HEAD(&h->listening_hash[i].nulls_head, + i + LISTENING_NULLS_BASE); h->listening_hash[i].count = 0; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 3e50ac24fe41..d885ba868822 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1087,8 +1087,7 @@ do_error: goto out; out_err: /* make sure we wake any epoll edge trigger waiter */ - if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 && - err == -EAGAIN)) { + if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) { sk->sk_write_space(sk); tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED); } @@ -1419,8 +1418,7 @@ out_err: sock_zerocopy_put_abort(uarg, true); err = sk_stream_error(sk, flags, err); /* make sure we wake any epoll edge trigger waiter */ - if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 && - err == -EAGAIN)) { + if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) { sk->sk_write_space(sk); tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED); } diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 32772d6ded4e..a6545ef0d27b 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -306,7 +306,8 @@ static u32 bbr_tso_segs_goal(struct sock *sk) /* Sort of tcp_tso_autosize() but ignoring * driver provided sk_gso_max_size. */ - bytes = min_t(unsigned long, sk->sk_pacing_rate >> sk->sk_pacing_shift, + bytes = min_t(unsigned long, + sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift), GSO_MAX_SIZE - 1 - MAX_TCP_HEADER); segs = max_t(u32, bytes / tp->mss_cache, bbr_min_tso_segs(sk)); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 92282f98dc82..1c7326e04f9b 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2147,13 +2147,14 @@ static void *listening_get_next(struct seq_file *seq, void *cur) struct tcp_iter_state *st = seq->private; struct net *net = seq_file_net(seq); struct inet_listen_hashbucket *ilb; + struct hlist_nulls_node *node; struct sock *sk = cur; if (!sk) { get_head: ilb = &tcp_hashinfo.listening_hash[st->bucket]; spin_lock(&ilb->lock); - sk = sk_head(&ilb->head); + sk = sk_nulls_head(&ilb->nulls_head); st->offset = 0; goto get_sk; } @@ -2161,9 +2162,9 @@ get_head: ++st->num; ++st->offset; - sk = sk_next(sk); + sk = sk_nulls_next(sk); get_sk: - sk_for_each_from(sk) { + sk_nulls_for_each_from(sk, node) { if (!net_eq(sock_net(sk), net)) continue; if (sk->sk_family == afinfo->family) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index b184f03d7437..1f7735ca8f22 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1725,7 +1725,7 @@ static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now, u32 bytes, segs; bytes = min_t(unsigned long, - sk->sk_pacing_rate >> sk->sk_pacing_shift, + sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift), sk->sk_gso_max_size - 1 - MAX_TCP_HEADER); /* Goal is to send at least one packet per ms, @@ -2260,7 +2260,7 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, limit = max_t(unsigned long, 2 * skb->truesize, - sk->sk_pacing_rate >> sk->sk_pacing_shift); + sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift)); if (sk->sk_pacing_status == SK_PACING_NONE) limit = min_t(unsigned long, limit, sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes); @@ -2438,6 +2438,14 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, if (tcp_small_queue_check(sk, skb, 0)) break; + /* Argh, we hit an empty skb(), presumably a thread + * is sleeping in sendmsg()/sk_stream_wait_memory(). + * We do not want to send a pure-ack packet and have + * a strange looking rtx queue with empty packet(s). + */ + if (TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq) + break; + if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp))) break; @@ -3121,7 +3129,7 @@ void sk_forced_mem_schedule(struct sock *sk, int size) */ void tcp_send_fin(struct sock *sk) { - struct sk_buff *skb, *tskb = tcp_write_queue_tail(sk); + struct sk_buff *skb, *tskb, *tail = tcp_write_queue_tail(sk); struct tcp_sock *tp = tcp_sk(sk); /* Optimization, tack on the FIN if we have one skb in write queue and @@ -3129,6 +3137,7 @@ void tcp_send_fin(struct sock *sk) * Note: in the latter case, FIN packet will be sent after a timeout, * as TCP stack thinks it has already been transmitted. */ + tskb = tail; if (!tskb && tcp_under_memory_pressure(sk)) tskb = skb_rb_last(&sk->tcp_rtx_queue); @@ -3136,7 +3145,7 @@ void tcp_send_fin(struct sock *sk) TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN; TCP_SKB_CB(tskb)->end_seq++; tp->write_seq++; - if (tcp_write_queue_empty(sk)) { + if (!tail) { /* This means tskb was already sent. * Pretend we included the FIN on previous transmit. * We need to set tp->snd_nxt to the value it would have diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 98d82305d6de..39d861d00377 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5231,16 +5231,16 @@ static int inet6_rtm_valid_getaddr_req(struct sk_buff *skb, return -EINVAL; } + if (!netlink_strict_get_check(skb)) + return nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX, + ifa_ipv6_policy, extack); + ifm = nlmsg_data(nlh); if (ifm->ifa_prefixlen || ifm->ifa_flags || ifm->ifa_scope) { NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for get address request"); return -EINVAL; } - if (!netlink_strict_get_check(skb)) - return nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX, - ifa_ipv6_policy, extack); - err = nlmsg_parse_deprecated_strict(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy, extack); if (err) diff --git a/net/llc/llc_station.c b/net/llc/llc_station.c index 204a8351efff..c29170e767a8 100644 --- a/net/llc/llc_station.c +++ b/net/llc/llc_station.c @@ -32,7 +32,7 @@ static int llc_stat_ev_rx_null_dsap_xid_c(struct sk_buff *skb) return LLC_PDU_IS_CMD(pdu) && /* command PDU */ LLC_PDU_TYPE_IS_U(pdu) && /* U type PDU */ LLC_U_PDU_CMD(pdu) == LLC_1_PDU_CMD_XID && - !pdu->dsap ? 0 : 1; /* NULL DSAP value */ + !pdu->dsap; /* NULL DSAP value */ } static int llc_stat_ev_rx_null_dsap_test_c(struct sk_buff *skb) @@ -42,7 +42,7 @@ static int llc_stat_ev_rx_null_dsap_test_c(struct sk_buff *skb) return LLC_PDU_IS_CMD(pdu) && /* command PDU */ LLC_PDU_TYPE_IS_U(pdu) && /* U type PDU */ LLC_U_PDU_CMD(pdu) == LLC_1_PDU_CMD_TEST && - !pdu->dsap ? 0 : 1; /* NULL DSAP */ + !pdu->dsap; /* NULL DSAP */ } static int llc_station_ac_send_xid_r(struct sk_buff *skb) diff --git a/net/mac80211/airtime.c b/net/mac80211/airtime.c index 63cb0028b02d..9fc2968856c0 100644 --- a/net/mac80211/airtime.c +++ b/net/mac80211/airtime.c @@ -442,7 +442,7 @@ u32 ieee80211_calc_rx_airtime(struct ieee80211_hw *hw, return 0; sband = hw->wiphy->bands[status->band]; - if (!sband || status->rate_idx > sband->n_bitrates) + if (!sband || status->rate_idx >= sband->n_bitrates) return 0; rate = &sband->bitrates[status->rate_idx]; diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index b3c9001d1f43..c80b1e163ea4 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -201,8 +201,6 @@ static ssize_t sta_airtime_read(struct file *file, char __user *userbuf, char *buf = kzalloc(bufsz, GFP_KERNEL), *p = buf; u64 rx_airtime = 0, tx_airtime = 0; s64 deficit[IEEE80211_NUM_ACS]; - u32 q_depth[IEEE80211_NUM_ACS]; - u32 q_limit_l[IEEE80211_NUM_ACS], q_limit_h[IEEE80211_NUM_ACS]; ssize_t rv; int ac; @@ -214,6 +212,56 @@ static ssize_t sta_airtime_read(struct file *file, char __user *userbuf, rx_airtime += sta->airtime[ac].rx_airtime; tx_airtime += sta->airtime[ac].tx_airtime; deficit[ac] = sta->airtime[ac].deficit; + spin_unlock_bh(&local->active_txq_lock[ac]); + } + + p += scnprintf(p, bufsz + buf - p, + "RX: %llu us\nTX: %llu us\nWeight: %u\n" + "Deficit: VO: %lld us VI: %lld us BE: %lld us BK: %lld us\n", + rx_airtime, tx_airtime, sta->airtime_weight, + deficit[0], deficit[1], deficit[2], deficit[3]); + + rv = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); + kfree(buf); + return rv; +} + +static ssize_t sta_airtime_write(struct file *file, const char __user *userbuf, + size_t count, loff_t *ppos) +{ + struct sta_info *sta = file->private_data; + struct ieee80211_local *local = sta->sdata->local; + int ac; + + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { + spin_lock_bh(&local->active_txq_lock[ac]); + sta->airtime[ac].rx_airtime = 0; + sta->airtime[ac].tx_airtime = 0; + sta->airtime[ac].deficit = sta->airtime_weight; + spin_unlock_bh(&local->active_txq_lock[ac]); + } + + return count; +} +STA_OPS_RW(airtime); + +static ssize_t sta_aql_read(struct file *file, char __user *userbuf, + size_t count, loff_t *ppos) +{ + struct sta_info *sta = file->private_data; + struct ieee80211_local *local = sta->sdata->local; + size_t bufsz = 400; + char *buf = kzalloc(bufsz, GFP_KERNEL), *p = buf; + u32 q_depth[IEEE80211_NUM_ACS]; + u32 q_limit_l[IEEE80211_NUM_ACS], q_limit_h[IEEE80211_NUM_ACS]; + ssize_t rv; + int ac; + + if (!buf) + return -ENOMEM; + + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { + spin_lock_bh(&local->active_txq_lock[ac]); q_limit_l[ac] = sta->airtime[ac].aql_limit_low; q_limit_h[ac] = sta->airtime[ac].aql_limit_high; spin_unlock_bh(&local->active_txq_lock[ac]); @@ -221,12 +269,8 @@ static ssize_t sta_airtime_read(struct file *file, char __user *userbuf, } p += scnprintf(p, bufsz + buf - p, - "RX: %llu us\nTX: %llu us\nWeight: %u\n" - "Deficit: VO: %lld us VI: %lld us BE: %lld us BK: %lld us\n" "Q depth: VO: %u us VI: %u us BE: %u us BK: %u us\n" "Q limit[low/high]: VO: %u/%u VI: %u/%u BE: %u/%u BK: %u/%u\n", - rx_airtime, tx_airtime, sta->airtime_weight, - deficit[0], deficit[1], deficit[2], deficit[3], q_depth[0], q_depth[1], q_depth[2], q_depth[3], q_limit_l[0], q_limit_h[0], q_limit_l[1], q_limit_h[1], q_limit_l[2], q_limit_h[2], q_limit_l[3], q_limit_h[3]), @@ -236,11 +280,10 @@ static ssize_t sta_airtime_read(struct file *file, char __user *userbuf, return rv; } -static ssize_t sta_airtime_write(struct file *file, const char __user *userbuf, +static ssize_t sta_aql_write(struct file *file, const char __user *userbuf, size_t count, loff_t *ppos) { struct sta_info *sta = file->private_data; - struct ieee80211_local *local = sta->sdata->local; u32 ac, q_limit_l, q_limit_h; char _buf[100] = {}, *buf = _buf; @@ -251,7 +294,7 @@ static ssize_t sta_airtime_write(struct file *file, const char __user *userbuf, return -EFAULT; buf[sizeof(_buf) - 1] = '\0'; - if (sscanf(buf, "queue limit %u %u %u", &ac, &q_limit_l, &q_limit_h) + if (sscanf(buf, "limit %u %u %u", &ac, &q_limit_l, &q_limit_h) != 3) return -EINVAL; @@ -261,17 +304,10 @@ static ssize_t sta_airtime_write(struct file *file, const char __user *userbuf, sta->airtime[ac].aql_limit_low = q_limit_l; sta->airtime[ac].aql_limit_high = q_limit_h; - for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { - spin_lock_bh(&local->active_txq_lock[ac]); - sta->airtime[ac].rx_airtime = 0; - sta->airtime[ac].tx_airtime = 0; - sta->airtime[ac].deficit = sta->airtime_weight; - spin_unlock_bh(&local->active_txq_lock[ac]); - } - return count; } -STA_OPS_RW(airtime); +STA_OPS_RW(aql); + static ssize_t sta_agg_status_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) @@ -996,6 +1032,10 @@ void ieee80211_sta_debugfs_add(struct sta_info *sta) NL80211_EXT_FEATURE_AIRTIME_FAIRNESS)) DEBUGFS_ADD(airtime); + if (wiphy_ext_feature_isset(local->hw.wiphy, + NL80211_EXT_FEATURE_AQL)) + DEBUGFS_ADD(aql); + debugfs_create_xul("driver_buffered_tids", 0400, sta->debugfs_dir, &sta->driver_buffered_tids); diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 6cca0853f183..4c2b5ba3ac09 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -672,9 +672,7 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, IEEE80211_DEFAULT_AQL_TXQ_LIMIT_H; } - local->airtime_flags = AIRTIME_USE_TX | - AIRTIME_USE_RX | - AIRTIME_USE_AQL; + local->airtime_flags = AIRTIME_USE_TX | AIRTIME_USE_RX; local->aql_threshold = IEEE80211_AQL_THRESHOLD; atomic_set(&local->aql_total_pending_airtime, 0); diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 8eafd81e97b4..0f5f40678885 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -1916,6 +1916,9 @@ void ieee80211_sta_update_pending_airtime(struct ieee80211_local *local, { int tx_pending; + if (!wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) + return; + if (!tx_completed) { if (sta) atomic_add(tx_airtime, diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index ad5d8a4ae56d..c00e28585f9d 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -127,7 +127,6 @@ enum ieee80211_agg_stop_reason { /* Debugfs flags to enable/disable use of RX/TX airtime in scheduler */ #define AIRTIME_USE_TX BIT(0) #define AIRTIME_USE_RX BIT(1) -#define AIRTIME_USE_AQL BIT(2) struct airtime_info { u64 rx_airtime; diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index b696b9136f4c..a8a7306a1f56 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -2256,6 +2256,15 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, payload[7]); } + /* + * Initialize skb->priority for QoS frames. This is put in the TID field + * of the frame before passing it to the driver. + */ + if (ieee80211_is_data_qos(hdr->frame_control)) { + u8 *p = ieee80211_get_qos_ctl(hdr); + skb->priority = *p & IEEE80211_QOS_CTL_TAG1D_MASK; + } + memset(info, 0, sizeof(*info)); info->flags = IEEE80211_TX_CTL_REQ_TX_STATUS | @@ -3668,7 +3677,7 @@ begin: IEEE80211_SKB_CB(skb)->control.vif = vif; - if (local->airtime_flags & AIRTIME_USE_AQL) { + if (wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) { u32 airtime; airtime = ieee80211_calc_expected_tx_airtime(hw, vif, txq->sta, @@ -3790,7 +3799,7 @@ bool ieee80211_txq_airtime_check(struct ieee80211_hw *hw, struct sta_info *sta; struct ieee80211_local *local = hw_to_local(hw); - if (!(local->airtime_flags & AIRTIME_USE_AQL)) + if (!wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) return true; if (!txq->sta) diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 0af1898af2b8..f475fec84536 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -895,9 +895,10 @@ static void nf_ct_acct_merge(struct nf_conn *ct, enum ip_conntrack_info ctinfo, } /* Resolve race on insertion if this protocol allows this. */ -static int nf_ct_resolve_clash(struct net *net, struct sk_buff *skb, - enum ip_conntrack_info ctinfo, - struct nf_conntrack_tuple_hash *h) +static __cold noinline int +nf_ct_resolve_clash(struct net *net, struct sk_buff *skb, + enum ip_conntrack_info ctinfo, + struct nf_conntrack_tuple_hash *h) { /* This is the conntrack entry already in hashes that won race. */ struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index d8d33ef52ce0..6a1c8f1f6171 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -3626,6 +3626,9 @@ static void __net_exit ctnetlink_net_exit_batch(struct list_head *net_exit_list) list_for_each_entry(net, net_exit_list, exit_list) ctnetlink_net_exit(net); + + /* wait for other cpus until they are done with ctnl_notifiers */ + synchronize_rcu(); } static struct pernet_operations ctnetlink_net_ops = { diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index c54c9a6cc981..de7a0d1e15c8 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -28,6 +28,7 @@ struct nf_flow_key { struct flow_dissector_key_basic basic; union { struct flow_dissector_key_ipv4_addrs ipv4; + struct flow_dissector_key_ipv6_addrs ipv6; }; struct flow_dissector_key_tcp tcp; struct flow_dissector_key_ports tp; @@ -57,6 +58,7 @@ static int nf_flow_rule_match(struct nf_flow_match *match, NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_CONTROL, control); NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_BASIC, basic); NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4); + NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6); NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_TCP, tcp); NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_PORTS, tp); @@ -69,9 +71,18 @@ static int nf_flow_rule_match(struct nf_flow_match *match, key->ipv4.dst = tuple->dst_v4.s_addr; mask->ipv4.dst = 0xffffffff; break; + case AF_INET6: + key->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; + key->basic.n_proto = htons(ETH_P_IPV6); + key->ipv6.src = tuple->src_v6; + memset(&mask->ipv6.src, 0xff, sizeof(mask->ipv6.src)); + key->ipv6.dst = tuple->dst_v6; + memset(&mask->ipv6.dst, 0xff, sizeof(mask->ipv6.dst)); + break; default: return -EOPNOTSUPP; } + match->dissector.used_keys |= BIT(key->control.addr_type); mask->basic.n_proto = 0xffff; switch (tuple->l4proto) { @@ -96,14 +107,13 @@ static int nf_flow_rule_match(struct nf_flow_match *match, match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_CONTROL) | BIT(FLOW_DISSECTOR_KEY_BASIC) | - BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | BIT(FLOW_DISSECTOR_KEY_PORTS); return 0; } static void flow_offload_mangle(struct flow_action_entry *entry, - enum flow_action_mangle_base htype, - u32 offset, u8 *value, u8 *mask) + enum flow_action_mangle_base htype, u32 offset, + const __be32 *value, const __be32 *mask) { entry->id = FLOW_ACTION_MANGLE; entry->mangle.htype = htype; @@ -140,12 +150,12 @@ static int flow_offload_eth_src(struct net *net, memcpy(&val16, dev->dev_addr, 2); val = val16 << 16; flow_offload_mangle(entry0, FLOW_ACT_MANGLE_HDR_TYPE_ETH, 4, - (u8 *)&val, (u8 *)&mask); + &val, &mask); mask = ~0xffffffff; memcpy(&val, dev->dev_addr + 2, 4); flow_offload_mangle(entry1, FLOW_ACT_MANGLE_HDR_TYPE_ETH, 8, - (u8 *)&val, (u8 *)&mask); + &val, &mask); dev_put(dev); return 0; @@ -170,13 +180,13 @@ static int flow_offload_eth_dst(struct net *net, mask = ~0xffffffff; memcpy(&val, n->ha, 4); flow_offload_mangle(entry0, FLOW_ACT_MANGLE_HDR_TYPE_ETH, 0, - (u8 *)&val, (u8 *)&mask); + &val, &mask); mask = ~0x0000ffff; memcpy(&val16, n->ha + 4, 2); val = val16; flow_offload_mangle(entry1, FLOW_ACT_MANGLE_HDR_TYPE_ETH, 4, - (u8 *)&val, (u8 *)&mask); + &val, &mask); neigh_release(n); return 0; @@ -206,7 +216,7 @@ static void flow_offload_ipv4_snat(struct net *net, } flow_offload_mangle(entry, FLOW_ACT_MANGLE_HDR_TYPE_IP4, offset, - (u8 *)&addr, (u8 *)&mask); + &addr, &mask); } static void flow_offload_ipv4_dnat(struct net *net, @@ -233,12 +243,12 @@ static void flow_offload_ipv4_dnat(struct net *net, } flow_offload_mangle(entry, FLOW_ACT_MANGLE_HDR_TYPE_IP4, offset, - (u8 *)&addr, (u8 *)&mask); + &addr, &mask); } static void flow_offload_ipv6_mangle(struct nf_flow_rule *flow_rule, unsigned int offset, - u8 *addr, u8 *mask) + const __be32 *addr, const __be32 *mask) { struct flow_action_entry *entry; int i; @@ -246,8 +256,7 @@ static void flow_offload_ipv6_mangle(struct nf_flow_rule *flow_rule, for (i = 0; i < sizeof(struct in6_addr) / sizeof(u32); i += sizeof(u32)) { entry = flow_action_entry_next(flow_rule); flow_offload_mangle(entry, FLOW_ACT_MANGLE_HDR_TYPE_IP6, - offset + i, - &addr[i], mask); + offset + i, &addr[i], mask); } } @@ -257,23 +266,23 @@ static void flow_offload_ipv6_snat(struct net *net, struct nf_flow_rule *flow_rule) { u32 mask = ~htonl(0xffffffff); - const u8 *addr; + const __be32 *addr; u32 offset; switch (dir) { case FLOW_OFFLOAD_DIR_ORIGINAL: - addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v6.s6_addr; + addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v6.s6_addr32; offset = offsetof(struct ipv6hdr, saddr); break; case FLOW_OFFLOAD_DIR_REPLY: - addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v6.s6_addr; + addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v6.s6_addr32; offset = offsetof(struct ipv6hdr, daddr); break; default: return; } - flow_offload_ipv6_mangle(flow_rule, offset, (u8 *)addr, (u8 *)&mask); + flow_offload_ipv6_mangle(flow_rule, offset, addr, &mask); } static void flow_offload_ipv6_dnat(struct net *net, @@ -282,23 +291,23 @@ static void flow_offload_ipv6_dnat(struct net *net, struct nf_flow_rule *flow_rule) { u32 mask = ~htonl(0xffffffff); - const u8 *addr; + const __be32 *addr; u32 offset; switch (dir) { case FLOW_OFFLOAD_DIR_ORIGINAL: - addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v6.s6_addr; + addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v6.s6_addr32; offset = offsetof(struct ipv6hdr, daddr); break; case FLOW_OFFLOAD_DIR_REPLY: - addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v6.s6_addr; + addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v6.s6_addr32; offset = offsetof(struct ipv6hdr, saddr); break; default: return; } - flow_offload_ipv6_mangle(flow_rule, offset, (u8 *)addr, (u8 *)&mask); + flow_offload_ipv6_mangle(flow_rule, offset, addr, &mask); } static int flow_offload_l4proto(const struct flow_offload *flow) @@ -326,25 +335,24 @@ static void flow_offload_port_snat(struct net *net, struct nf_flow_rule *flow_rule) { struct flow_action_entry *entry = flow_action_entry_next(flow_rule); - u32 mask = ~htonl(0xffff0000); - __be16 port; + u32 mask = ~htonl(0xffff0000), port; u32 offset; switch (dir) { case FLOW_OFFLOAD_DIR_ORIGINAL: - port = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port; + port = ntohs(flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port); offset = 0; /* offsetof(struct tcphdr, source); */ break; case FLOW_OFFLOAD_DIR_REPLY: - port = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port; + port = ntohs(flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port); offset = 0; /* offsetof(struct tcphdr, dest); */ break; default: - break; + return; } - + port = htonl(port << 16); flow_offload_mangle(entry, flow_offload_l4proto(flow), offset, - (u8 *)&port, (u8 *)&mask); + &port, &mask); } static void flow_offload_port_dnat(struct net *net, @@ -353,25 +361,24 @@ static void flow_offload_port_dnat(struct net *net, struct nf_flow_rule *flow_rule) { struct flow_action_entry *entry = flow_action_entry_next(flow_rule); - u32 mask = ~htonl(0xffff); - __be16 port; + u32 mask = ~htonl(0xffff), port; u32 offset; switch (dir) { case FLOW_OFFLOAD_DIR_ORIGINAL: - port = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port; + port = ntohs(flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port); offset = 0; /* offsetof(struct tcphdr, source); */ break; case FLOW_OFFLOAD_DIR_REPLY: - port = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port; + port = ntohs(flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port); offset = 0; /* offsetof(struct tcphdr, dest); */ break; default: - break; + return; } - + port = htonl(port); flow_offload_mangle(entry, flow_offload_l4proto(flow), offset, - (u8 *)&port, (u8 *)&mask); + &port, &mask); } static void flow_offload_ipv4_checksum(struct net *net, @@ -574,7 +581,7 @@ static int flow_offload_tuple_add(struct flow_offload_work *offload, cls_flow.rule = flow_rule->rule; list_for_each_entry(block_cb, &flowtable->flow_block.cb_list, list) { - err = block_cb->cb(TC_SETUP_FT, &cls_flow, + err = block_cb->cb(TC_SETUP_CLSFLOWER, &cls_flow, block_cb->cb_priv); if (err < 0) continue; @@ -599,7 +606,7 @@ static void flow_offload_tuple_del(struct flow_offload_work *offload, &offload->flow->tuplehash[dir].tuple, &extack); list_for_each_entry(block_cb, &flowtable->flow_block.cb_list, list) - block_cb->cb(TC_SETUP_FT, &cls_flow, block_cb->cb_priv); + block_cb->cb(TC_SETUP_CLSFLOWER, &cls_flow, block_cb->cb_priv); offload->flow->flags |= FLOW_OFFLOAD_HW_DEAD; } @@ -656,7 +663,7 @@ static void flow_offload_tuple_stats(struct flow_offload_work *offload, &offload->flow->tuplehash[dir].tuple, &extack); list_for_each_entry(block_cb, &flowtable->flow_block.cb_list, list) - block_cb->cb(TC_SETUP_FT, &cls_flow, block_cb->cb_priv); + block_cb->cb(TC_SETUP_CLSFLOWER, &cls_flow, block_cb->cb_priv); memcpy(stats, &cls_flow.stats, sizeof(*stats)); } @@ -822,7 +829,7 @@ int nf_flow_table_offload_setup(struct nf_flowtable *flowtable, bo.extack = &extack; INIT_LIST_HEAD(&bo.cb_list); - err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo); + err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_FT, &bo); if (err < 0) return err; diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index a2b58de82600..f8f52ff99cfb 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -189,7 +189,7 @@ static int __nf_queue(struct sk_buff *skb, const struct nf_hook_state *state, goto err; } - if (!skb_dst_force(skb) && state->hook != NF_INET_PRE_ROUTING) { + if (skb_dst(skb) && !skb_dst_force(skb)) { status = -ENETDOWN; goto err; } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index c26a5663795e..273f3838318b 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4519,8 +4519,10 @@ static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set, return err; err = -EINVAL; - if (desc.type != NFT_DATA_VALUE || desc.len != set->klen) + if (desc.type != NFT_DATA_VALUE || desc.len != set->klen) { + nft_data_release(&elem.key.val, desc.type); return err; + } priv = set->ops->get(ctx->net, set, &elem, flags); if (IS_ERR(priv)) @@ -4756,14 +4758,20 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (nla[NFTA_SET_ELEM_DATA] == NULL && !(flags & NFT_SET_ELEM_INTERVAL_END)) return -EINVAL; - if (nla[NFTA_SET_ELEM_DATA] != NULL && - flags & NFT_SET_ELEM_INTERVAL_END) - return -EINVAL; } else { if (nla[NFTA_SET_ELEM_DATA] != NULL) return -EINVAL; } + if ((flags & NFT_SET_ELEM_INTERVAL_END) && + (nla[NFTA_SET_ELEM_DATA] || + nla[NFTA_SET_ELEM_OBJREF] || + nla[NFTA_SET_ELEM_TIMEOUT] || + nla[NFTA_SET_ELEM_EXPIRATION] || + nla[NFTA_SET_ELEM_USERDATA] || + nla[NFTA_SET_ELEM_EXPR])) + return -EINVAL; + timeout = 0; if (nla[NFTA_SET_ELEM_TIMEOUT] != NULL) { if (!(set->flags & NFT_SET_TIMEOUT)) @@ -5476,7 +5484,7 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; - type = nft_obj_type_get(net, objtype); + type = __nft_obj_type_get(objtype); nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla); return nf_tables_updobj(&ctx, type, nla[NFTA_OBJ_DATA], obj); diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index 431f3b803bfb..a9ea29afb09f 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -44,6 +44,9 @@ struct nft_flow_rule *nft_flow_rule_create(struct net *net, expr = nft_expr_next(expr); } + if (num_actions == 0) + return ERR_PTR(-EOPNOTSUPP); + flow = nft_flow_rule_alloc(num_actions); if (!flow) return ERR_PTR(-ENOMEM); @@ -577,6 +580,9 @@ static int nft_offload_netdev_event(struct notifier_block *this, struct net *net = dev_net(dev); struct nft_chain *chain; + if (event != NETDEV_UNREGISTER) + return NOTIFY_DONE; + mutex_lock(&net->nft.commit_mutex); chain = __nft_offload_get_chain(dev); if (chain) diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c index 02afa752dd2e..10e9d50e4e19 100644 --- a/net/netfilter/nft_bitwise.c +++ b/net/netfilter/nft_bitwise.c @@ -80,7 +80,7 @@ static int nft_bitwise_init(const struct nft_ctx *ctx, tb[NFTA_BITWISE_MASK]); if (err < 0) return err; - if (d1.len != priv->len) { + if (d1.type != NFT_DATA_VALUE || d1.len != priv->len) { err = -EINVAL; goto err1; } @@ -89,7 +89,7 @@ static int nft_bitwise_init(const struct nft_ctx *ctx, tb[NFTA_BITWISE_XOR]); if (err < 0) goto err1; - if (d2.len != priv->len) { + if (d2.type != NFT_DATA_VALUE || d2.len != priv->len) { err = -EINVAL; goto err2; } diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c index b8092069f868..8a28c127effc 100644 --- a/net/netfilter/nft_cmp.c +++ b/net/netfilter/nft_cmp.c @@ -81,6 +81,12 @@ static int nft_cmp_init(const struct nft_ctx *ctx, const struct nft_expr *expr, if (err < 0) return err; + if (desc.type != NFT_DATA_VALUE) { + err = -EINVAL; + nft_data_release(&priv->data, desc.type); + return err; + } + priv->sreg = nft_parse_register(tb[NFTA_CMP_SREG]); err = nft_validate_register_load(priv->sreg, desc.len); if (err < 0) diff --git a/net/netfilter/nft_range.c b/net/netfilter/nft_range.c index 4701fa8a45e7..89efcc5a533d 100644 --- a/net/netfilter/nft_range.c +++ b/net/netfilter/nft_range.c @@ -66,11 +66,21 @@ static int nft_range_init(const struct nft_ctx *ctx, const struct nft_expr *expr if (err < 0) return err; + if (desc_from.type != NFT_DATA_VALUE) { + err = -EINVAL; + goto err1; + } + err = nft_data_init(NULL, &priv->data_to, sizeof(priv->data_to), &desc_to, tb[NFTA_RANGE_TO_DATA]); if (err < 0) goto err1; + if (desc_to.type != NFT_DATA_VALUE) { + err = -EINVAL; + goto err2; + } + if (desc_from.len != desc_to.len) { err = -EINVAL; goto err2; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 57123259452f..a9f804f7a04a 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -74,8 +74,13 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set parent = rcu_dereference_raw(parent->rb_left); continue; } - if (nft_rbtree_interval_end(rbe)) - goto out; + if (nft_rbtree_interval_end(rbe)) { + if (nft_set_is_anonymous(set)) + return false; + parent = rcu_dereference_raw(parent->rb_left); + interval = NULL; + continue; + } *ext = &rbe->ext; return true; @@ -88,7 +93,7 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set *ext = &interval->ext; return true; } -out: + return false; } @@ -139,8 +144,10 @@ static bool __nft_rbtree_get(const struct net *net, const struct nft_set *set, if (flags & NFT_SET_ELEM_INTERVAL_END) interval = rbe; } else { - if (!nft_set_elem_active(&rbe->ext, genmask)) + if (!nft_set_elem_active(&rbe->ext, genmask)) { parent = rcu_dereference_raw(parent->rb_left); + continue; + } if (!nft_set_ext_exists(&rbe->ext, NFT_SET_EXT_FLAGS) || (*nft_set_ext_flags(&rbe->ext) & NFT_SET_ELEM_INTERVAL_END) == @@ -148,7 +155,11 @@ static bool __nft_rbtree_get(const struct net *net, const struct nft_set *set, *elem = rbe; return true; } - return false; + + if (nft_rbtree_interval_end(rbe)) + interval = NULL; + + parent = rcu_dereference_raw(parent->rb_left); } } diff --git a/net/nfc/nci/uart.c b/net/nfc/nci/uart.c index 78fe622eba65..11b554ce07ff 100644 --- a/net/nfc/nci/uart.c +++ b/net/nfc/nci/uart.c @@ -346,7 +346,7 @@ static int nci_uart_default_recv_buf(struct nci_uart *nu, const u8 *data, nu->rx_packet_len = -1; nu->rx_skb = nci_skb_alloc(nu->ndev, NCI_MAX_PACKET_SIZE, - GFP_KERNEL); + GFP_ATOMIC); if (!nu->rx_skb) return -ENOMEM; } diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 53c1d41fb1c9..118cd66b7516 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -544,7 +544,8 @@ static int prb_calc_retire_blk_tmo(struct packet_sock *po, msec = 1; div = ecmd.base.speed / 1000; } - } + } else + return DEFAULT_PRB_RETIRE_TOV; mbits = (blk_size_in_bytes * 8) / (1024 * 1024); diff --git a/net/rfkill/core.c b/net/rfkill/core.c index 461d75274fb3..971c73c7d34c 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -1002,10 +1002,13 @@ static void rfkill_sync_work(struct work_struct *work) int __must_check rfkill_register(struct rfkill *rfkill) { static unsigned long rfkill_no; - struct device *dev = &rfkill->dev; + struct device *dev; int error; - BUG_ON(!rfkill); + if (!rfkill) + return -EINVAL; + + dev = &rfkill->dev; mutex_lock(&rfkill_global_mutex); diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index a0e6fac613de..66c6bcec16cb 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -1108,10 +1108,33 @@ erridr: return err; } +static bool u32_hnode_empty(struct tc_u_hnode *ht, bool *non_root_ht) +{ + int i; + + if (!ht) + return true; + if (!ht->is_root) { + *non_root_ht = true; + return false; + } + if (*non_root_ht) + return false; + if (ht->refcnt < 2) + return true; + + for (i = 0; i <= ht->divisor; i++) { + if (rtnl_dereference(ht->ht[i])) + return false; + } + return true; +} + static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg, bool rtnl_held) { struct tc_u_common *tp_c = tp->data; + bool non_root_ht = false; struct tc_u_hnode *ht; struct tc_u_knode *n; unsigned int h; @@ -1124,6 +1147,8 @@ static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg, ht = rtnl_dereference(ht->next)) { if (ht->prio != tp->prio) continue; + if (u32_hnode_empty(ht, &non_root_ht)) + return; if (arg->count >= arg->skip) { if (arg->fn(tp, ht, arg) < 0) { arg->stop = 1; diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index fbbf19128c2d..78af2fcf90cc 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -227,6 +227,7 @@ static void sctp_v4_from_skb(union sctp_addr *addr, struct sk_buff *skb, sa->sin_port = sh->dest; sa->sin_addr.s_addr = ip_hdr(skb)->daddr; } + memset(sa->sin_zero, 0, sizeof(sa->sin_zero)); } /* Initialize an sctp_addr from a socket. */ @@ -235,6 +236,7 @@ static void sctp_v4_from_sk(union sctp_addr *addr, struct sock *sk) addr->v4.sin_family = AF_INET; addr->v4.sin_port = 0; addr->v4.sin_addr.s_addr = inet_sk(sk)->inet_rcv_saddr; + memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero)); } /* Initialize sk->sk_rcv_saddr from sctp_addr. */ @@ -257,6 +259,7 @@ static void sctp_v4_from_addr_param(union sctp_addr *addr, addr->v4.sin_family = AF_INET; addr->v4.sin_port = port; addr->v4.sin_addr.s_addr = param->v4.addr.s_addr; + memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero)); } /* Initialize an address parameter from a sctp_addr and return the length @@ -281,6 +284,7 @@ static void sctp_v4_dst_saddr(union sctp_addr *saddr, struct flowi4 *fl4, saddr->v4.sin_family = AF_INET; saddr->v4.sin_port = port; saddr->v4.sin_addr.s_addr = fl4->saddr; + memset(saddr->v4.sin_zero, 0, sizeof(saddr->v4.sin_zero)); } /* Compare two addresses exactly. */ @@ -303,6 +307,7 @@ static void sctp_v4_inaddr_any(union sctp_addr *addr, __be16 port) addr->v4.sin_family = AF_INET; addr->v4.sin_addr.s_addr = htonl(INADDR_ANY); addr->v4.sin_port = port; + memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero)); } /* Is this a wildcard address? */ diff --git a/net/sctp/stream.c b/net/sctp/stream.c index e83cdaa2ab76..6a30392068a0 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -84,8 +84,10 @@ static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt, return 0; ret = genradix_prealloc(&stream->out, outcnt, gfp); - if (ret) + if (ret) { + genradix_free(&stream->out); return ret; + } stream->outcnt = outcnt; return 0; @@ -100,8 +102,10 @@ static int sctp_stream_alloc_in(struct sctp_stream *stream, __u16 incnt, return 0; ret = genradix_prealloc(&stream->in, incnt, gfp); - if (ret) + if (ret) { + genradix_free(&stream->in); return ret; + } stream->incnt = incnt; return 0; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index b997072c72e5..cee5bf4a9bb9 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -857,6 +857,8 @@ static int smc_connect(struct socket *sock, struct sockaddr *addr, goto out; sock_hold(&smc->sk); /* sock put in passive closing */ + if (smc->use_fallback) + goto out; if (flags & O_NONBLOCK) { if (schedule_work(&smc->connect_work)) smc->connect_nonblock = 1; @@ -1721,8 +1723,6 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, sk->sk_err = smc->clcsock->sk->sk_err; sk->sk_error_report(sk); } - if (rc) - return rc; if (optlen < sizeof(int)) return -EINVAL; @@ -1730,6 +1730,8 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, return -EFAULT; lock_sock(sk); + if (rc || smc->use_fallback) + goto out; switch (optname) { case TCP_ULP: case TCP_FASTOPEN: @@ -1741,15 +1743,14 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, smc_switch_to_fallback(smc); smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP; } else { - if (!smc->use_fallback) - rc = -EINVAL; + rc = -EINVAL; } break; case TCP_NODELAY: if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_CLOSED) { - if (val && !smc->use_fallback) + if (val) mod_delayed_work(system_wq, &smc->conn.tx_work, 0); } @@ -1758,7 +1759,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_CLOSED) { - if (!val && !smc->use_fallback) + if (!val) mod_delayed_work(system_wq, &smc->conn.tx_work, 0); } @@ -1769,6 +1770,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, default: break; } +out: release_sock(sk); return rc; diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index bb92c7c6214c..e419ff277e55 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -1287,7 +1287,7 @@ static int smc_core_reboot_event(struct notifier_block *this, unsigned long event, void *ptr) { smc_lgrs_shutdown(); - + smc_ib_unregister_client(); return 0; } diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 55aeba681cf4..656ebc79c64e 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -305,17 +305,17 @@ static int tipc_rcast_xmit(struct net *net, struct sk_buff_head *pkts, * @skb: socket buffer to copy * @method: send method to be used * @dests: destination nodes for message. - * @cong_link_cnt: returns number of encountered congested destination links * Returns 0 if success, otherwise errno */ static int tipc_mcast_send_sync(struct net *net, struct sk_buff *skb, struct tipc_mc_method *method, - struct tipc_nlist *dests, - u16 *cong_link_cnt) + struct tipc_nlist *dests) { struct tipc_msg *hdr, *_hdr; struct sk_buff_head tmpq; struct sk_buff *_skb; + u16 cong_link_cnt; + int rc = 0; /* Is a cluster supporting with new capabilities ? */ if (!(tipc_net(net)->capabilities & TIPC_MCAST_RBCTL)) @@ -343,18 +343,19 @@ static int tipc_mcast_send_sync(struct net *net, struct sk_buff *skb, _hdr = buf_msg(_skb); msg_set_size(_hdr, MCAST_H_SIZE); msg_set_is_rcast(_hdr, !msg_is_rcast(hdr)); + msg_set_errcode(_hdr, TIPC_ERR_NO_PORT); __skb_queue_head_init(&tmpq); __skb_queue_tail(&tmpq, _skb); if (method->rcast) - tipc_bcast_xmit(net, &tmpq, cong_link_cnt); + rc = tipc_bcast_xmit(net, &tmpq, &cong_link_cnt); else - tipc_rcast_xmit(net, &tmpq, dests, cong_link_cnt); + rc = tipc_rcast_xmit(net, &tmpq, dests, &cong_link_cnt); /* This queue should normally be empty by now */ __skb_queue_purge(&tmpq); - return 0; + return rc; } /* tipc_mcast_xmit - deliver message to indicated destination nodes @@ -396,9 +397,14 @@ int tipc_mcast_xmit(struct net *net, struct sk_buff_head *pkts, msg_set_is_rcast(hdr, method->rcast); /* Switch method ? */ - if (rcast != method->rcast) - tipc_mcast_send_sync(net, skb, method, - dests, cong_link_cnt); + if (rcast != method->rcast) { + rc = tipc_mcast_send_sync(net, skb, method, dests); + if (unlikely(rc)) { + pr_err("Unable to send SYN: method %d, rc %d\n", + rcast, rc); + goto exit; + } + } if (method->rcast) rc = tipc_rcast_xmit(net, pkts, dests, cong_link_cnt); diff --git a/net/tipc/discover.c b/net/tipc/discover.c index b043e8c6397a..bfe43da127c0 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -194,6 +194,7 @@ void tipc_disc_rcv(struct net *net, struct sk_buff *skb, { struct tipc_net *tn = tipc_net(net); struct tipc_msg *hdr = buf_msg(skb); + u32 pnet_hash = msg_peer_net_hash(hdr); u16 caps = msg_node_capabilities(hdr); bool legacy = tn->legacy_addr_format; u32 sugg = msg_sugg_node_addr(hdr); @@ -242,9 +243,8 @@ void tipc_disc_rcv(struct net *net, struct sk_buff *skb, return; if (!tipc_in_scope(legacy, b->domain, src)) return; - tipc_node_check_dest(net, src, peer_id, b, caps, signature, - msg_peer_net_hash(hdr), &maddr, &respond, - &dupl_addr); + tipc_node_check_dest(net, src, peer_id, b, caps, signature, pnet_hash, + &maddr, &respond, &dupl_addr); if (dupl_addr) disc_dupl_alert(b, src, &maddr); if (!respond) diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index 92d04dc2a44b..359b2bc888cf 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -36,6 +36,7 @@ #include <net/sock.h> #include <linux/list_sort.h> +#include <linux/rbtree_augmented.h> #include "core.h" #include "netlink.h" #include "name_table.h" @@ -51,6 +52,7 @@ * @lower: service range lower bound * @upper: service range upper bound * @tree_node: member of service range RB tree + * @max: largest 'upper' in this node subtree * @local_publ: list of identical publications made from this node * Used by closest_first lookup and multicast lookup algorithm * @all_publ: all publications identical to this one, whatever node and scope @@ -60,6 +62,7 @@ struct service_range { u32 lower; u32 upper; struct rb_node tree_node; + u32 max; struct list_head local_publ; struct list_head all_publ; }; @@ -84,6 +87,130 @@ struct tipc_service { struct rcu_head rcu; }; +#define service_range_upper(sr) ((sr)->upper) +RB_DECLARE_CALLBACKS_MAX(static, sr_callbacks, + struct service_range, tree_node, u32, max, + service_range_upper) + +#define service_range_entry(rbtree_node) \ + (container_of(rbtree_node, struct service_range, tree_node)) + +#define service_range_overlap(sr, start, end) \ + ((sr)->lower <= (end) && (sr)->upper >= (start)) + +/** + * service_range_foreach_match - iterate over tipc service rbtree for each + * range match + * @sr: the service range pointer as a loop cursor + * @sc: the pointer to tipc service which holds the service range rbtree + * @start, end: the range (end >= start) for matching + */ +#define service_range_foreach_match(sr, sc, start, end) \ + for (sr = service_range_match_first((sc)->ranges.rb_node, \ + start, \ + end); \ + sr; \ + sr = service_range_match_next(&(sr)->tree_node, \ + start, \ + end)) + +/** + * service_range_match_first - find first service range matching a range + * @n: the root node of service range rbtree for searching + * @start, end: the range (end >= start) for matching + * + * Return: the leftmost service range node in the rbtree that overlaps the + * specific range if any. Otherwise, returns NULL. + */ +static struct service_range *service_range_match_first(struct rb_node *n, + u32 start, u32 end) +{ + struct service_range *sr; + struct rb_node *l, *r; + + /* Non overlaps in tree at all? */ + if (!n || service_range_entry(n)->max < start) + return NULL; + + while (n) { + l = n->rb_left; + if (l && service_range_entry(l)->max >= start) { + /* A leftmost overlap range node must be one in the left + * subtree. If not, it has lower > end, then nodes on + * the right side cannot satisfy the condition either. + */ + n = l; + continue; + } + + /* No one in the left subtree can match, return if this node is + * an overlap i.e. leftmost. + */ + sr = service_range_entry(n); + if (service_range_overlap(sr, start, end)) + return sr; + + /* Ok, try to lookup on the right side */ + r = n->rb_right; + if (sr->lower <= end && + r && service_range_entry(r)->max >= start) { + n = r; + continue; + } + break; + } + + return NULL; +} + +/** + * service_range_match_next - find next service range matching a range + * @n: a node in service range rbtree from which the searching starts + * @start, end: the range (end >= start) for matching + * + * Return: the next service range node to the given node in the rbtree that + * overlaps the specific range if any. Otherwise, returns NULL. + */ +static struct service_range *service_range_match_next(struct rb_node *n, + u32 start, u32 end) +{ + struct service_range *sr; + struct rb_node *p, *r; + + while (n) { + r = n->rb_right; + if (r && service_range_entry(r)->max >= start) + /* A next overlap range node must be one in the right + * subtree. If not, it has lower > end, then any next + * successor (- an ancestor) of this node cannot + * satisfy the condition either. + */ + return service_range_match_first(r, start, end); + + /* No one in the right subtree can match, go up to find an + * ancestor of this node which is parent of a left-hand child. + */ + while ((p = rb_parent(n)) && n == p->rb_right) + n = p; + if (!p) + break; + + /* Return if this ancestor is an overlap */ + sr = service_range_entry(p); + if (service_range_overlap(sr, start, end)) + return sr; + + /* Ok, try to lookup more from this ancestor */ + if (sr->lower <= end) { + n = p; + continue; + } + break; + } + + return NULL; +} + static int hash(int x) { return x & (TIPC_NAMETBL_SIZE - 1); @@ -139,84 +266,51 @@ static struct tipc_service *tipc_service_create(u32 type, struct hlist_head *hd) return service; } -/** - * tipc_service_first_range - find first service range in tree matching instance - * - * Very time-critical, so binary search through range rb tree - */ -static struct service_range *tipc_service_first_range(struct tipc_service *sc, - u32 instance) -{ - struct rb_node *n = sc->ranges.rb_node; - struct service_range *sr; - - while (n) { - sr = container_of(n, struct service_range, tree_node); - if (sr->lower > instance) - n = n->rb_left; - else if (sr->upper < instance) - n = n->rb_right; - else - return sr; - } - return NULL; -} - /* tipc_service_find_range - find service range matching publication parameters */ static struct service_range *tipc_service_find_range(struct tipc_service *sc, u32 lower, u32 upper) { - struct rb_node *n = sc->ranges.rb_node; struct service_range *sr; - sr = tipc_service_first_range(sc, lower); - if (!sr) - return NULL; - - /* Look for exact match */ - for (n = &sr->tree_node; n; n = rb_next(n)) { - sr = container_of(n, struct service_range, tree_node); - if (sr->upper == upper) - break; + service_range_foreach_match(sr, sc, lower, upper) { + /* Look for exact match */ + if (sr->lower == lower && sr->upper == upper) + return sr; } - if (!n || sr->lower != lower || sr->upper != upper) - return NULL; - return sr; + return NULL; } static struct service_range *tipc_service_create_range(struct tipc_service *sc, u32 lower, u32 upper) { struct rb_node **n, *parent = NULL; - struct service_range *sr, *tmp; + struct service_range *sr; n = &sc->ranges.rb_node; while (*n) { - tmp = container_of(*n, struct service_range, tree_node); parent = *n; - tmp = container_of(parent, struct service_range, tree_node); - if (lower < tmp->lower) - n = &(*n)->rb_left; - else if (lower > tmp->lower) - n = &(*n)->rb_right; - else if (upper < tmp->upper) - n = &(*n)->rb_left; - else if (upper > tmp->upper) - n = &(*n)->rb_right; + sr = service_range_entry(parent); + if (lower == sr->lower && upper == sr->upper) + return sr; + if (sr->max < upper) + sr->max = upper; + if (lower <= sr->lower) + n = &parent->rb_left; else - return tmp; + n = &parent->rb_right; } sr = kzalloc(sizeof(*sr), GFP_ATOMIC); if (!sr) return NULL; sr->lower = lower; sr->upper = upper; + sr->max = upper; INIT_LIST_HEAD(&sr->local_publ); INIT_LIST_HEAD(&sr->all_publ); rb_link_node(&sr->tree_node, parent, n); - rb_insert_color(&sr->tree_node, &sc->ranges); + rb_insert_augmented(&sr->tree_node, &sc->ranges, &sr_callbacks); return sr; } @@ -310,7 +404,6 @@ static void tipc_service_subscribe(struct tipc_service *service, struct list_head publ_list; struct service_range *sr; struct tipc_name_seq ns; - struct rb_node *n; u32 filter; ns.type = tipc_sub_read(sb, seq.type); @@ -325,13 +418,7 @@ static void tipc_service_subscribe(struct tipc_service *service, return; INIT_LIST_HEAD(&publ_list); - for (n = rb_first(&service->ranges); n; n = rb_next(n)) { - sr = container_of(n, struct service_range, tree_node); - if (sr->lower > ns.upper) - break; - if (!tipc_sub_check_overlap(&ns, sr->lower, sr->upper)) - continue; - + service_range_foreach_match(sr, service, ns.lower, ns.upper) { first = NULL; list_for_each_entry(p, &sr->all_publ, all_publ) { if (filter & TIPC_SUB_PORTS) @@ -425,7 +512,7 @@ struct publication *tipc_nametbl_remove_publ(struct net *net, u32 type, /* Remove service range item if this was its last publication */ if (list_empty(&sr->all_publ)) { - rb_erase(&sr->tree_node, &sc->ranges); + rb_erase_augmented(&sr->tree_node, &sc->ranges, &sr_callbacks); kfree(sr); } @@ -473,34 +560,39 @@ u32 tipc_nametbl_translate(struct net *net, u32 type, u32 instance, u32 *dnode) rcu_read_lock(); sc = tipc_service_find(net, type); if (unlikely(!sc)) - goto not_found; + goto exit; spin_lock_bh(&sc->lock); - sr = tipc_service_first_range(sc, instance); - if (unlikely(!sr)) - goto no_match; - - /* Select lookup algorithm: local, closest-first or round-robin */ - if (*dnode == self) { - list = &sr->local_publ; - if (list_empty(list)) - goto no_match; - p = list_first_entry(list, struct publication, local_publ); - list_move_tail(&p->local_publ, &sr->local_publ); - } else if (legacy && !*dnode && !list_empty(&sr->local_publ)) { - list = &sr->local_publ; - p = list_first_entry(list, struct publication, local_publ); - list_move_tail(&p->local_publ, &sr->local_publ); - } else { - list = &sr->all_publ; - p = list_first_entry(list, struct publication, all_publ); - list_move_tail(&p->all_publ, &sr->all_publ); + service_range_foreach_match(sr, sc, instance, instance) { + /* Select lookup algo: local, closest-first or round-robin */ + if (*dnode == self) { + list = &sr->local_publ; + if (list_empty(list)) + continue; + p = list_first_entry(list, struct publication, + local_publ); + list_move_tail(&p->local_publ, &sr->local_publ); + } else if (legacy && !*dnode && !list_empty(&sr->local_publ)) { + list = &sr->local_publ; + p = list_first_entry(list, struct publication, + local_publ); + list_move_tail(&p->local_publ, &sr->local_publ); + } else { + list = &sr->all_publ; + p = list_first_entry(list, struct publication, + all_publ); + list_move_tail(&p->all_publ, &sr->all_publ); + } + port = p->port; + node = p->node; + /* Todo: as for legacy, pick the first matching range only, a + * "true" round-robin will be performed as needed. + */ + break; } - port = p->port; - node = p->node; -no_match: spin_unlock_bh(&sc->lock); -not_found: + +exit: rcu_read_unlock(); *dnode = node; return port; @@ -523,7 +615,8 @@ bool tipc_nametbl_lookup(struct net *net, u32 type, u32 instance, u32 scope, spin_lock_bh(&sc->lock); - sr = tipc_service_first_range(sc, instance); + /* Todo: a full search i.e. service_range_foreach_match() instead? */ + sr = service_range_match_first(sc->ranges.rb_node, instance, instance); if (!sr) goto no_match; @@ -552,7 +645,6 @@ void tipc_nametbl_mc_lookup(struct net *net, u32 type, u32 lower, u32 upper, struct service_range *sr; struct tipc_service *sc; struct publication *p; - struct rb_node *n; rcu_read_lock(); sc = tipc_service_find(net, type); @@ -560,13 +652,7 @@ void tipc_nametbl_mc_lookup(struct net *net, u32 type, u32 lower, u32 upper, goto exit; spin_lock_bh(&sc->lock); - - for (n = rb_first(&sc->ranges); n; n = rb_next(n)) { - sr = container_of(n, struct service_range, tree_node); - if (sr->upper < lower) - continue; - if (sr->lower > upper) - break; + service_range_foreach_match(sr, sc, lower, upper) { list_for_each_entry(p, &sr->local_publ, local_publ) { if (p->scope == scope || (!exact && p->scope < scope)) tipc_dest_push(dports, 0, p->port); @@ -587,7 +673,6 @@ void tipc_nametbl_lookup_dst_nodes(struct net *net, u32 type, u32 lower, struct service_range *sr; struct tipc_service *sc; struct publication *p; - struct rb_node *n; rcu_read_lock(); sc = tipc_service_find(net, type); @@ -595,13 +680,7 @@ void tipc_nametbl_lookup_dst_nodes(struct net *net, u32 type, u32 lower, goto exit; spin_lock_bh(&sc->lock); - - for (n = rb_first(&sc->ranges); n; n = rb_next(n)) { - sr = container_of(n, struct service_range, tree_node); - if (sr->upper < lower) - continue; - if (sr->lower > upper) - break; + service_range_foreach_match(sr, sc, lower, upper) { list_for_each_entry(p, &sr->all_publ, all_publ) { tipc_nlist_add(nodes, p->node); } @@ -799,7 +878,7 @@ static void tipc_service_delete(struct net *net, struct tipc_service *sc) tipc_service_remove_publ(sr, p->node, p->key); kfree_rcu(p, rcu); } - rb_erase(&sr->tree_node, &sc->ranges); + rb_erase_augmented(&sr->tree_node, &sc->ranges, &sr_callbacks); kfree(sr); } hlist_del_init_rcu(&sc->service_list); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 41688da233ab..6552f986774c 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1364,8 +1364,8 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) struct tipc_msg *hdr = &tsk->phdr; struct tipc_name_seq *seq; struct sk_buff_head pkts; - u32 dport, dnode = 0; - u32 type, inst; + u32 dport = 0, dnode = 0; + u32 type = 0, inst = 0; int mtu, rc; if (unlikely(dlen > TIPC_MAX_USER_MSG_SIZE)) @@ -1418,23 +1418,11 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) type = dest->addr.name.name.type; inst = dest->addr.name.name.instance; dnode = dest->addr.name.domain; - msg_set_type(hdr, TIPC_NAMED_MSG); - msg_set_hdr_sz(hdr, NAMED_H_SIZE); - msg_set_nametype(hdr, type); - msg_set_nameinst(hdr, inst); - msg_set_lookup_scope(hdr, tipc_node2scope(dnode)); dport = tipc_nametbl_translate(net, type, inst, &dnode); - msg_set_destnode(hdr, dnode); - msg_set_destport(hdr, dport); if (unlikely(!dport && !dnode)) return -EHOSTUNREACH; } else if (dest->addrtype == TIPC_ADDR_ID) { dnode = dest->addr.id.node; - msg_set_type(hdr, TIPC_DIRECT_MSG); - msg_set_lookup_scope(hdr, 0); - msg_set_destnode(hdr, dnode); - msg_set_destport(hdr, dest->addr.id.ref); - msg_set_hdr_sz(hdr, BASIC_H_SIZE); } else { return -EINVAL; } @@ -1445,6 +1433,22 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) if (unlikely(rc)) return rc; + if (dest->addrtype == TIPC_ADDR_NAME) { + msg_set_type(hdr, TIPC_NAMED_MSG); + msg_set_hdr_sz(hdr, NAMED_H_SIZE); + msg_set_nametype(hdr, type); + msg_set_nameinst(hdr, inst); + msg_set_lookup_scope(hdr, tipc_node2scope(dnode)); + msg_set_destnode(hdr, dnode); + msg_set_destport(hdr, dport); + } else { /* TIPC_ADDR_ID */ + msg_set_type(hdr, TIPC_DIRECT_MSG); + msg_set_lookup_scope(hdr, 0); + msg_set_destnode(hdr, dnode); + msg_set_destport(hdr, dest->addr.id.ref); + msg_set_hdr_sz(hdr, BASIC_H_SIZE); + } + __skb_queue_head_init(&pkts); mtu = tipc_node_get_mtu(net, dnode, tsk->portid, false); rc = tipc_msg_build(hdr, m, 0, dlen, mtu, &pkts); diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index e5ea29c6bca7..6abec3fc81d1 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -34,6 +34,9 @@ virtio_transport_get_ops(struct vsock_sock *vsk) { const struct vsock_transport *t = vsock_core_get_transport(vsk); + if (WARN_ON(!t)) + return NULL; + return container_of(t, struct virtio_transport, transport); } @@ -161,15 +164,25 @@ void virtio_transport_deliver_tap_pkt(struct virtio_vsock_pkt *pkt) } EXPORT_SYMBOL_GPL(virtio_transport_deliver_tap_pkt); +/* This function can only be used on connecting/connected sockets, + * since a socket assigned to a transport is required. + * + * Do not use on listener sockets! + */ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, struct virtio_vsock_pkt_info *info) { u32 src_cid, src_port, dst_cid, dst_port; + const struct virtio_transport *t_ops; struct virtio_vsock_sock *vvs; struct virtio_vsock_pkt *pkt; u32 pkt_len = info->pkt_len; - src_cid = virtio_transport_get_ops(vsk)->transport.get_local_cid(); + t_ops = virtio_transport_get_ops(vsk); + if (unlikely(!t_ops)) + return -EFAULT; + + src_cid = t_ops->transport.get_local_cid(); src_port = vsk->local_addr.svm_port; if (!info->remote_cid) { dst_cid = vsk->remote_addr.svm_cid; @@ -202,7 +215,7 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, virtio_transport_inc_tx_pkt(vvs, pkt); - return virtio_transport_get_ops(vsk)->send_pkt(pkt); + return t_ops->send_pkt(pkt); } static bool virtio_transport_inc_rx_pkt(struct virtio_vsock_sock *vvs, @@ -1021,18 +1034,18 @@ virtio_transport_recv_listen(struct sock *sk, struct virtio_vsock_pkt *pkt, int ret; if (le16_to_cpu(pkt->hdr.op) != VIRTIO_VSOCK_OP_REQUEST) { - virtio_transport_reset(vsk, pkt); + virtio_transport_reset_no_sock(t, pkt); return -EINVAL; } if (sk_acceptq_is_full(sk)) { - virtio_transport_reset(vsk, pkt); + virtio_transport_reset_no_sock(t, pkt); return -ENOMEM; } child = vsock_create_connected(sk); if (!child) { - virtio_transport_reset(vsk, pkt); + virtio_transport_reset_no_sock(t, pkt); return -ENOMEM; } @@ -1054,7 +1067,7 @@ virtio_transport_recv_listen(struct sock *sk, struct virtio_vsock_pkt *pkt, */ if (ret || vchild->transport != &t->transport) { release_sock(child); - virtio_transport_reset(vsk, pkt); + virtio_transport_reset_no_sock(t, pkt); sock_put(child); return ret; } diff --git a/net/wireless/core.c b/net/wireless/core.c index 350513744575..3e25229a059d 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1102,6 +1102,7 @@ static void __cfg80211_unregister_wdev(struct wireless_dev *wdev, bool sync) #ifdef CONFIG_CFG80211_WEXT kzfree(wdev->wext.keys); + wdev->wext.keys = NULL; #endif /* only initialized if we have a netdev */ if (wdev->netdev) diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index c34f7d077604..2efe44a34644 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -659,6 +659,12 @@ static int x25_release(struct socket *sock) sock_set_flag(sk, SOCK_DEAD); sock_set_flag(sk, SOCK_DESTROY); break; + + case X25_STATE_5: + x25_write_internal(sk, X25_CLEAR_REQUEST); + x25_disconnect(sk, 0, 0, 0); + __x25_destroy_socket(sk); + goto out; } sock_orphan(sk); @@ -1054,6 +1060,8 @@ int x25_rx_call_request(struct sk_buff *skb, struct x25_neigh *nb, if (test_bit(X25_ACCPT_APPRV_FLAG, &makex25->flags)) { x25_write_internal(make, X25_CALL_ACCEPTED); makex25->state = X25_STATE_3; + } else { + makex25->state = X25_STATE_5; } /* diff --git a/net/x25/x25_in.c b/net/x25/x25_in.c index f97c43344e95..4d3bb46aaae0 100644 --- a/net/x25/x25_in.c +++ b/net/x25/x25_in.c @@ -382,6 +382,35 @@ out_clear: return 0; } +/* + * State machine for state 5, Call Accepted / Call Connected pending (X25_ACCPT_APPRV_FLAG). + * The handling of the timer(s) is in file x25_timer.c + * Handling of state 0 and connection release is in af_x25.c. + */ +static int x25_state5_machine(struct sock *sk, struct sk_buff *skb, int frametype) +{ + struct x25_sock *x25 = x25_sk(sk); + + switch (frametype) { + case X25_CLEAR_REQUEST: + if (!pskb_may_pull(skb, X25_STD_MIN_LEN + 2)) { + x25_write_internal(sk, X25_CLEAR_REQUEST); + x25->state = X25_STATE_2; + x25_start_t23timer(sk); + return 0; + } + + x25_write_internal(sk, X25_CLEAR_CONFIRMATION); + x25_disconnect(sk, 0, skb->data[3], skb->data[4]); + break; + + default: + break; + } + + return 0; +} + /* Higher level upcall for a LAPB frame */ int x25_process_rx_frame(struct sock *sk, struct sk_buff *skb) { @@ -406,6 +435,9 @@ int x25_process_rx_frame(struct sock *sk, struct sk_buff *skb) case X25_STATE_4: queued = x25_state4_machine(sk, skb, frametype); break; + case X25_STATE_5: + queued = x25_state5_machine(sk, skb, frametype); + break; } x25_kick(sk); diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 956793893c9d..328f661b83b2 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -334,12 +334,21 @@ out: } EXPORT_SYMBOL(xsk_umem_consume_tx); -static int xsk_zc_xmit(struct xdp_sock *xs) +static int xsk_wakeup(struct xdp_sock *xs, u8 flags) { struct net_device *dev = xs->dev; + int err; + + rcu_read_lock(); + err = dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, flags); + rcu_read_unlock(); + + return err; +} - return dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, - XDP_WAKEUP_TX); +static int xsk_zc_xmit(struct xdp_sock *xs) +{ + return xsk_wakeup(xs, XDP_WAKEUP_TX); } static void xsk_destruct_skb(struct sk_buff *skb) @@ -453,19 +462,16 @@ static __poll_t xsk_poll(struct file *file, struct socket *sock, __poll_t mask = datagram_poll(file, sock, wait); struct sock *sk = sock->sk; struct xdp_sock *xs = xdp_sk(sk); - struct net_device *dev; struct xdp_umem *umem; if (unlikely(!xsk_is_bound(xs))) return mask; - dev = xs->dev; umem = xs->umem; if (umem->need_wakeup) { - if (dev->netdev_ops->ndo_xsk_wakeup) - dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, - umem->need_wakeup); + if (xs->zc) + xsk_wakeup(xs, umem->need_wakeup); else /* Poll needs to drive Tx also in copy mode */ __xsk_sendmsg(sk); diff --git a/samples/bpf/syscall_tp_kern.c b/samples/bpf/syscall_tp_kern.c index 1d78819ffef1..630ce8c4d5a2 100644 --- a/samples/bpf/syscall_tp_kern.c +++ b/samples/bpf/syscall_tp_kern.c @@ -47,13 +47,27 @@ static __always_inline void count(void *map) SEC("tracepoint/syscalls/sys_enter_open") int trace_enter_open(struct syscalls_enter_open_args *ctx) { - count((void *)&enter_open_map); + count(&enter_open_map); + return 0; +} + +SEC("tracepoint/syscalls/sys_enter_openat") +int trace_enter_open_at(struct syscalls_enter_open_args *ctx) +{ + count(&enter_open_map); return 0; } SEC("tracepoint/syscalls/sys_exit_open") int trace_enter_exit(struct syscalls_exit_open_args *ctx) { - count((void *)&exit_open_map); + count(&exit_open_map); + return 0; +} + +SEC("tracepoint/syscalls/sys_exit_openat") +int trace_enter_exit_at(struct syscalls_exit_open_args *ctx) +{ + count(&exit_open_map); return 0; } diff --git a/samples/bpf/trace_event_user.c b/samples/bpf/trace_event_user.c index 16a16eadd509..749a50f2f9f3 100644 --- a/samples/bpf/trace_event_user.c +++ b/samples/bpf/trace_event_user.c @@ -37,9 +37,9 @@ static void print_ksym(__u64 addr) } printf("%s;", sym->name); - if (!strcmp(sym->name, "sys_read")) + if (!strstr(sym->name, "sys_read")) sys_read_seen = true; - else if (!strcmp(sym->name, "sys_write")) + else if (!strstr(sym->name, "sys_write")) sys_write_seen = true; } diff --git a/samples/trace_printk/trace-printk.c b/samples/trace_printk/trace-printk.c index 7affc3b50b61..cfc159580263 100644 --- a/samples/trace_printk/trace-printk.c +++ b/samples/trace_printk/trace-printk.c @@ -36,6 +36,7 @@ static int __init trace_printk_init(void) /* Kick off printing in irq context */ irq_work_queue(&irqwork); + irq_work_sync(&irqwork); trace_printk("This is a %s that will use trace_bprintk()\n", "static string"); diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c index fb55f262f42d..94153732ec00 100644 --- a/scripts/kallsyms.c +++ b/scripts/kallsyms.c @@ -310,6 +310,15 @@ static void output_label(const char *label) printf("%s:\n", label); } +/* Provide proper symbols relocatability by their '_text' relativeness. */ +static void output_address(unsigned long long addr) +{ + if (_text <= addr) + printf("\tPTR\t_text + %#llx\n", addr - _text); + else + printf("\tPTR\t_text - %#llx\n", _text - addr); +} + /* uncompress a compressed symbol. When this function is called, the best table * might still be compressed itself, so the function needs to be recursive */ static int expand_symbol(const unsigned char *data, int len, char *result) @@ -360,19 +369,6 @@ static void write_src(void) printf("\t.section .rodata, \"a\"\n"); - /* Provide proper symbols relocatability by their relativeness - * to a fixed anchor point in the runtime image, either '_text' - * for absolute address tables, in which case the linker will - * emit the final addresses at build time. Otherwise, use the - * offset relative to the lowest value encountered of all relative - * symbols, and emit non-relocatable fixed offsets that will be fixed - * up at runtime. - * - * The symbol names cannot be used to construct normal symbol - * references as the list of symbols contains symbols that are - * declared static and are private to their .o files. This prevents - * .tmp_kallsyms.o or any other object from referencing them. - */ if (!base_relative) output_label("kallsyms_addresses"); else @@ -380,6 +376,13 @@ static void write_src(void) for (i = 0; i < table_cnt; i++) { if (base_relative) { + /* + * Use the offset relative to the lowest value + * encountered of all relative symbols, and emit + * non-relocatable fixed offsets that will be fixed + * up at runtime. + */ + long long offset; int overflow; @@ -402,12 +405,7 @@ static void write_src(void) } printf("\t.long\t%#x\n", (int)offset); } else if (!symbol_absolute(&table[i])) { - if (_text <= table[i].addr) - printf("\tPTR\t_text + %#llx\n", - table[i].addr - _text); - else - printf("\tPTR\t_text - %#llx\n", - _text - table[i].addr); + output_address(table[i].addr); } else { printf("\tPTR\t%#llx\n", table[i].addr); } @@ -416,7 +414,7 @@ static void write_src(void) if (base_relative) { output_label("kallsyms_relative_base"); - printf("\tPTR\t_text - %#llx\n", _text - relative_base); + output_address(relative_base); printf("\n"); } diff --git a/scripts/kconfig/expr.c b/scripts/kconfig/expr.c index 77ffff3a053c..9f1de58e9f0c 100644 --- a/scripts/kconfig/expr.c +++ b/scripts/kconfig/expr.c @@ -254,6 +254,13 @@ static int expr_eq(struct expr *e1, struct expr *e2) { int res, old_count; + /* + * A NULL expr is taken to be yes, but there's also a different way to + * represent yes. expr_is_yes() checks for either representation. + */ + if (!e1 || !e2) + return expr_is_yes(e1) && expr_is_yes(e2); + if (e1->type != e2->type) return 0; switch (e1->type) { diff --git a/scripts/mkcompile_h b/scripts/mkcompile_h index d1d757c6edf4..3a5a4b210c86 100755 --- a/scripts/mkcompile_h +++ b/scripts/mkcompile_h @@ -55,12 +55,10 @@ CONFIG_FLAGS="" if [ -n "$SMP" ] ; then CONFIG_FLAGS="SMP"; fi if [ -n "$PREEMPT" ] ; then CONFIG_FLAGS="$CONFIG_FLAGS PREEMPT"; fi if [ -n "$PREEMPT_RT" ] ; then CONFIG_FLAGS="$CONFIG_FLAGS PREEMPT_RT"; fi -UTS_VERSION="$UTS_VERSION $CONFIG_FLAGS $TIMESTAMP" # Truncate to maximum length - UTS_LEN=64 -UTS_TRUNCATE="cut -b -$UTS_LEN" +UTS_VERSION="$(echo $UTS_VERSION $CONFIG_FLAGS $TIMESTAMP | cut -b -$UTS_LEN)" # Generate a temporary compile.h @@ -69,10 +67,10 @@ UTS_TRUNCATE="cut -b -$UTS_LEN" echo \#define UTS_MACHINE \"$ARCH\" - echo \#define UTS_VERSION \"`echo $UTS_VERSION | $UTS_TRUNCATE`\" + echo \#define UTS_VERSION \"$UTS_VERSION\" - echo \#define LINUX_COMPILE_BY \"`echo $LINUX_COMPILE_BY | $UTS_TRUNCATE`\" - echo \#define LINUX_COMPILE_HOST \"`echo $LINUX_COMPILE_HOST | $UTS_TRUNCATE`\" + printf '#define LINUX_COMPILE_BY "%s"\n' "$LINUX_COMPILE_BY" + echo \#define LINUX_COMPILE_HOST \"$LINUX_COMPILE_HOST\" echo \#define LINUX_COMPILER \"`$CC -v 2>&1 | grep ' version ' | sed 's/[[:space:]]*$//'`\" } > .tmpcompile diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian index e0750b70453f..7c230016b08d 100755 --- a/scripts/package/mkdebian +++ b/scripts/package/mkdebian @@ -174,7 +174,7 @@ Source: $sourcename Section: kernel Priority: optional Maintainer: $maintainer -Build-Depends: bc, kmod, cpio, bison, flex | flex:native $extra_build_depends +Build-Depends: bc, rsync, kmod, cpio, bison, flex | flex:native $extra_build_depends Homepage: http://www.kernel.org/ Package: $packagename diff --git a/security/keys/Kconfig b/security/keys/Kconfig index dd313438fecf..47c041563d41 100644 --- a/security/keys/Kconfig +++ b/security/keys/Kconfig @@ -21,10 +21,6 @@ config KEYS If you are unsure as to whether this is required, answer N. -config KEYS_COMPAT - def_bool y - depends on COMPAT && KEYS - config KEYS_REQUEST_CACHE bool "Enable temporary caching of the last request_key() result" depends on KEYS diff --git a/security/keys/Makefile b/security/keys/Makefile index 074f27538f55..5f40807f05b3 100644 --- a/security/keys/Makefile +++ b/security/keys/Makefile @@ -17,7 +17,7 @@ obj-y := \ request_key_auth.o \ user_defined.o compat-obj-$(CONFIG_KEY_DH_OPERATIONS) += compat_dh.o -obj-$(CONFIG_KEYS_COMPAT) += compat.o $(compat-obj-y) +obj-$(CONFIG_COMPAT) += compat.o $(compat-obj-y) obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_SYSCTL) += sysctl.o obj-$(CONFIG_PERSISTENT_KEYRINGS) += persistent.o diff --git a/security/keys/compat.c b/security/keys/compat.c index 9bcc404131aa..b975f8f11124 100644 --- a/security/keys/compat.c +++ b/security/keys/compat.c @@ -46,11 +46,6 @@ static long compat_keyctl_instantiate_key_iov( /* * The key control system call, 32-bit compatibility version for 64-bit archs - * - * This should only be called if the 64-bit arch uses weird pointers in 32-bit - * mode or doesn't guarantee that the top 32-bits of the argument registers on - * taking a 32-bit syscall are zero. If you can, you should call sys_keyctl() - * directly. */ COMPAT_SYSCALL_DEFINE5(keyctl, u32, option, u32, arg2, u32, arg3, u32, arg4, u32, arg5) diff --git a/security/keys/internal.h b/security/keys/internal.h index c039373488bd..ba3e2da14cef 100644 --- a/security/keys/internal.h +++ b/security/keys/internal.h @@ -264,7 +264,7 @@ extern long keyctl_dh_compute(struct keyctl_dh_params __user *, char __user *, size_t, struct keyctl_kdf_params __user *); extern long __keyctl_dh_compute(struct keyctl_dh_params __user *, char __user *, size_t, struct keyctl_kdf_params *); -#ifdef CONFIG_KEYS_COMPAT +#ifdef CONFIG_COMPAT extern long compat_keyctl_dh_compute(struct keyctl_dh_params __user *params, char __user *buffer, size_t buflen, struct compat_keyctl_kdf_params __user *kdf); @@ -279,7 +279,7 @@ static inline long keyctl_dh_compute(struct keyctl_dh_params __user *params, return -EOPNOTSUPP; } -#ifdef CONFIG_KEYS_COMPAT +#ifdef CONFIG_COMPAT static inline long compat_keyctl_dh_compute( struct keyctl_dh_params __user *params, char __user *buffer, size_t buflen, diff --git a/security/keys/trusted-keys/trusted_tpm2.c b/security/keys/trusted-keys/trusted_tpm2.c index a9810ac2776f..08ec7f48f01d 100644 --- a/security/keys/trusted-keys/trusted_tpm2.c +++ b/security/keys/trusted-keys/trusted_tpm2.c @@ -309,6 +309,7 @@ int tpm2_unseal_trusted(struct tpm_chip *chip, return rc; rc = tpm2_unseal_cmd(chip, payload, options, blob_handle); + tpm2_flush_context(chip, blob_handle); return rc; } diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 1fe581167b7b..d083225344a0 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -739,6 +739,10 @@ static int snd_pcm_hw_params(struct snd_pcm_substream *substream, while (runtime->boundary * 2 <= LONG_MAX - runtime->buffer_size) runtime->boundary *= 2; + /* clear the buffer for avoiding possible kernel info leaks */ + if (runtime->dma_area && !substream->ops->copy_user) + memset(runtime->dma_area, 0, runtime->dma_bytes); + snd_pcm_timer_resolution_change(substream); snd_pcm_set_state(substream, SNDRV_PCM_STATE_SETUP); diff --git a/sound/hda/hdac_stream.c b/sound/hda/hdac_stream.c index f9707fb05efe..682ed39f79b0 100644 --- a/sound/hda/hdac_stream.c +++ b/sound/hda/hdac_stream.c @@ -120,10 +120,8 @@ void snd_hdac_stream_clear(struct hdac_stream *azx_dev) snd_hdac_stream_updateb(azx_dev, SD_CTL, SD_CTL_DMA_START | SD_INT_MASK, 0); snd_hdac_stream_writeb(azx_dev, SD_STS, SD_INT_MASK); /* to be sure */ - if (azx_dev->stripe) { + if (azx_dev->stripe) snd_hdac_stream_updateb(azx_dev, SD_CTL_3B, SD_CTL_STRIPE_MASK, 0); - azx_dev->stripe = 0; - } azx_dev->running = false; } EXPORT_SYMBOL_GPL(snd_hdac_stream_clear); diff --git a/sound/pci/hda/hda_controller.c b/sound/pci/hda/hda_controller.c index 2f3b7a35f2d9..ba56b59b3e17 100644 --- a/sound/pci/hda/hda_controller.c +++ b/sound/pci/hda/hda_controller.c @@ -883,7 +883,7 @@ static int azx_rirb_get_response(struct hdac_bus *bus, unsigned int addr, return -EAGAIN; /* give a chance to retry */ } - dev_WARN(chip->card->dev, + dev_err(chip->card->dev, "azx_get_response timeout, switching to single_cmd mode: last cmd=0x%08x\n", bus->last_cmd[addr]); chip->single_cmd = 1; diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c index b7a1abb3e231..32ed46464af7 100644 --- a/sound/pci/hda/patch_ca0132.c +++ b/sound/pci/hda/patch_ca0132.c @@ -1809,13 +1809,14 @@ struct scp_msg { static void dspio_clear_response_queue(struct hda_codec *codec) { + unsigned long timeout = jiffies + msecs_to_jiffies(1000); unsigned int dummy = 0; - int status = -1; + int status; /* clear all from the response queue */ do { status = dspio_read(codec, &dummy); - } while (status == 0); + } while (status == 0 && time_before(jiffies, timeout)); } static int dspio_get_response_data(struct hda_codec *codec) @@ -7588,12 +7589,14 @@ static void ca0132_process_dsp_response(struct hda_codec *codec, struct ca0132_spec *spec = codec->spec; codec_dbg(codec, "ca0132_process_dsp_response\n"); + snd_hda_power_up_pm(codec); if (spec->wait_scp) { if (dspio_get_response_data(codec) >= 0) spec->wait_scp = 0; } dspio_clear_response_queue(codec); + snd_hda_power_down_pm(codec); } static void hp_callback(struct hda_codec *codec, struct hda_jack_callback *cb) @@ -7604,11 +7607,10 @@ static void hp_callback(struct hda_codec *codec, struct hda_jack_callback *cb) /* Delay enabling the HP amp, to let the mic-detection * state machine run. */ - cancel_delayed_work(&spec->unsol_hp_work); - schedule_delayed_work(&spec->unsol_hp_work, msecs_to_jiffies(500)); tbl = snd_hda_jack_tbl_get(codec, cb->nid); if (tbl) tbl->block_report = 1; + schedule_delayed_work(&spec->unsol_hp_work, msecs_to_jiffies(500)); } static void amic_callback(struct hda_codec *codec, struct hda_jack_callback *cb) @@ -8454,12 +8456,25 @@ static void ca0132_reboot_notify(struct hda_codec *codec) codec->patch_ops.free(codec); } +#ifdef CONFIG_PM +static int ca0132_suspend(struct hda_codec *codec) +{ + struct ca0132_spec *spec = codec->spec; + + cancel_delayed_work_sync(&spec->unsol_hp_work); + return 0; +} +#endif + static const struct hda_codec_ops ca0132_patch_ops = { .build_controls = ca0132_build_controls, .build_pcms = ca0132_build_pcms, .init = ca0132_init, .free = ca0132_free, .unsol_event = snd_hda_jack_unsol_event, +#ifdef CONFIG_PM + .suspend = ca0132_suspend, +#endif .reboot_notify = ca0132_reboot_notify, }; diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 78647ee02339..630b1f5c276d 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -2021,6 +2021,8 @@ static int hdmi_pcm_close(struct hda_pcm_stream *hinfo, per_cvt->assigned = 0; hinfo->nid = 0; + azx_stream(get_azx_dev(substream))->stripe = 0; + mutex_lock(&spec->pcm_lock); snd_hda_spdif_ctls_unassign(codec, pcm_idx); clear_bit(pcm_idx, &spec->pcm_in_use); diff --git a/sound/soc/amd/acp-da7219-max98357a.c b/sound/soc/amd/acp-da7219-max98357a.c index f4ee6798154a..7a5621e5e233 100644 --- a/sound/soc/amd/acp-da7219-max98357a.c +++ b/sound/soc/amd/acp-da7219-max98357a.c @@ -96,14 +96,19 @@ static int cz_da7219_init(struct snd_soc_pcm_runtime *rtd) return 0; } -static int da7219_clk_enable(struct snd_pcm_substream *substream, - int wclk_rate, int bclk_rate) +static int da7219_clk_enable(struct snd_pcm_substream *substream) { int ret = 0; struct snd_soc_pcm_runtime *rtd = substream->private_data; - clk_set_rate(da7219_dai_wclk, wclk_rate); - clk_set_rate(da7219_dai_bclk, bclk_rate); + /* + * Set wclk to 48000 because the rate constraint of this driver is + * 48000. ADAU7002 spec: "The ADAU7002 requires a BCLK rate that is + * minimum of 64x the LRCLK sample rate." DA7219 is the only clk + * source so for all codecs we have to limit bclk to 64X lrclk. + */ + clk_set_rate(da7219_dai_wclk, 48000); + clk_set_rate(da7219_dai_bclk, 48000 * 64); ret = clk_prepare_enable(da7219_dai_bclk); if (ret < 0) { dev_err(rtd->dev, "can't enable master clock %d\n", ret); @@ -156,7 +161,7 @@ static int cz_da7219_play_startup(struct snd_pcm_substream *substream) &constraints_rates); machine->play_i2s_instance = I2S_SP_INSTANCE; - return 0; + return da7219_clk_enable(substream); } static int cz_da7219_cap_startup(struct snd_pcm_substream *substream) @@ -178,7 +183,7 @@ static int cz_da7219_cap_startup(struct snd_pcm_substream *substream) machine->cap_i2s_instance = I2S_SP_INSTANCE; machine->capture_channel = CAP_CHANNEL1; - return 0; + return da7219_clk_enable(substream); } static int cz_max_startup(struct snd_pcm_substream *substream) @@ -199,7 +204,7 @@ static int cz_max_startup(struct snd_pcm_substream *substream) &constraints_rates); machine->play_i2s_instance = I2S_BT_INSTANCE; - return 0; + return da7219_clk_enable(substream); } static int cz_dmic0_startup(struct snd_pcm_substream *substream) @@ -220,7 +225,7 @@ static int cz_dmic0_startup(struct snd_pcm_substream *substream) &constraints_rates); machine->cap_i2s_instance = I2S_BT_INSTANCE; - return 0; + return da7219_clk_enable(substream); } static int cz_dmic1_startup(struct snd_pcm_substream *substream) @@ -242,25 +247,7 @@ static int cz_dmic1_startup(struct snd_pcm_substream *substream) machine->cap_i2s_instance = I2S_SP_INSTANCE; machine->capture_channel = CAP_CHANNEL0; - return 0; -} - -static int cz_da7219_params(struct snd_pcm_substream *substream, - struct snd_pcm_hw_params *params) -{ - int wclk, bclk; - - wclk = params_rate(params); - bclk = wclk * params_channels(params) * - snd_pcm_format_width(params_format(params)); - /* ADAU7002 spec: "The ADAU7002 requires a BCLK rate - * that is minimum of 64x the LRCLK sample rate." - * DA7219 is the only clk source so for all codecs - * we have to limit bclk to 64X lrclk. - */ - if (bclk < (wclk * 64)) - bclk = wclk * 64; - return da7219_clk_enable(substream, wclk, bclk); + return da7219_clk_enable(substream); } static void cz_da7219_shutdown(struct snd_pcm_substream *substream) @@ -271,31 +258,26 @@ static void cz_da7219_shutdown(struct snd_pcm_substream *substream) static const struct snd_soc_ops cz_da7219_play_ops = { .startup = cz_da7219_play_startup, .shutdown = cz_da7219_shutdown, - .hw_params = cz_da7219_params, }; static const struct snd_soc_ops cz_da7219_cap_ops = { .startup = cz_da7219_cap_startup, .shutdown = cz_da7219_shutdown, - .hw_params = cz_da7219_params, }; static const struct snd_soc_ops cz_max_play_ops = { .startup = cz_max_startup, .shutdown = cz_da7219_shutdown, - .hw_params = cz_da7219_params, }; static const struct snd_soc_ops cz_dmic0_cap_ops = { .startup = cz_dmic0_startup, .shutdown = cz_da7219_shutdown, - .hw_params = cz_da7219_params, }; static const struct snd_soc_ops cz_dmic1_cap_ops = { .startup = cz_dmic1_startup, .shutdown = cz_da7219_shutdown, - .hw_params = cz_da7219_params, }; SND_SOC_DAILINK_DEF(designware1, diff --git a/sound/soc/codecs/max98090.c b/sound/soc/codecs/max98090.c index f6bf4cfbea23..e46b6ada13b1 100644 --- a/sound/soc/codecs/max98090.c +++ b/sound/soc/codecs/max98090.c @@ -2103,26 +2103,40 @@ static void max98090_pll_det_disable_work(struct work_struct *work) M98090_IULK_MASK, 0); } -static void max98090_pll_work(struct work_struct *work) +static void max98090_pll_work(struct max98090_priv *max98090) { - struct max98090_priv *max98090 = - container_of(work, struct max98090_priv, pll_work); struct snd_soc_component *component = max98090->component; + unsigned int pll; + int i; if (!snd_soc_component_is_active(component)) return; dev_info_ratelimited(component->dev, "PLL unlocked\n"); + /* + * As the datasheet suggested, the maximum PLL lock time should be + * 7 msec. The workaround resets the codec softly by toggling SHDN + * off and on if PLL failed to lock for 10 msec. Notably, there is + * no suggested hold time for SHDN off. + */ + /* Toggle shutdown OFF then ON */ snd_soc_component_update_bits(component, M98090_REG_DEVICE_SHUTDOWN, M98090_SHDNN_MASK, 0); - msleep(10); snd_soc_component_update_bits(component, M98090_REG_DEVICE_SHUTDOWN, M98090_SHDNN_MASK, M98090_SHDNN_MASK); - /* Give PLL time to lock */ - msleep(10); + for (i = 0; i < 10; ++i) { + /* Give PLL time to lock */ + usleep_range(1000, 1200); + + /* Check lock status */ + pll = snd_soc_component_read32( + component, M98090_REG_DEVICE_STATUS); + if (!(pll & M98090_ULK_MASK)) + break; + } } static void max98090_jack_work(struct work_struct *work) @@ -2259,7 +2273,7 @@ static irqreturn_t max98090_interrupt(int irq, void *data) if (active & M98090_ULK_MASK) { dev_dbg(component->dev, "M98090_ULK_MASK\n"); - schedule_work(&max98090->pll_work); + max98090_pll_work(max98090); } if (active & M98090_JDET_MASK) { @@ -2422,7 +2436,6 @@ static int max98090_probe(struct snd_soc_component *component) max98090_pll_det_enable_work); INIT_WORK(&max98090->pll_det_disable_work, max98090_pll_det_disable_work); - INIT_WORK(&max98090->pll_work, max98090_pll_work); /* Enable jack detection */ snd_soc_component_write(component, M98090_REG_JACK_DETECT, @@ -2475,7 +2488,6 @@ static void max98090_remove(struct snd_soc_component *component) cancel_delayed_work_sync(&max98090->jack_work); cancel_delayed_work_sync(&max98090->pll_det_enable_work); cancel_work_sync(&max98090->pll_det_disable_work); - cancel_work_sync(&max98090->pll_work); max98090->component = NULL; } diff --git a/sound/soc/codecs/max98090.h b/sound/soc/codecs/max98090.h index 57965cd678b4..a197114b0dad 100644 --- a/sound/soc/codecs/max98090.h +++ b/sound/soc/codecs/max98090.h @@ -1530,7 +1530,6 @@ struct max98090_priv { struct delayed_work jack_work; struct delayed_work pll_det_enable_work; struct work_struct pll_det_disable_work; - struct work_struct pll_work; struct snd_soc_jack *jack; unsigned int dai_fmt; int tdm_slots; diff --git a/sound/soc/codecs/rt5677-spi.h b/sound/soc/codecs/rt5677-spi.h index 3af36ec928e9..088b77931727 100644 --- a/sound/soc/codecs/rt5677-spi.h +++ b/sound/soc/codecs/rt5677-spi.h @@ -9,9 +9,25 @@ #ifndef __RT5677_SPI_H__ #define __RT5677_SPI_H__ +#if IS_ENABLED(CONFIG_SND_SOC_RT5677_SPI) int rt5677_spi_read(u32 addr, void *rxbuf, size_t len); int rt5677_spi_write(u32 addr, const void *txbuf, size_t len); int rt5677_spi_write_firmware(u32 addr, const struct firmware *fw); void rt5677_spi_hotword_detected(void); +#else +static inline int rt5677_spi_read(u32 addr, void *rxbuf, size_t len) +{ + return -EINVAL; +} +static inline int rt5677_spi_write(u32 addr, const void *txbuf, size_t len) +{ + return -EINVAL; +} +static inline int rt5677_spi_write_firmware(u32 addr, const struct firmware *fw) +{ + return -EINVAL; +} +static inline void rt5677_spi_hotword_detected(void){} +#endif #endif /* __RT5677_SPI_H__ */ diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c index b1713fffa3eb..ae6f6121bc1b 100644 --- a/sound/soc/codecs/rt5682.c +++ b/sound/soc/codecs/rt5682.c @@ -73,6 +73,7 @@ struct rt5682_priv { static const struct reg_sequence patch_list[] = { {RT5682_HP_IMP_SENS_CTRL_19, 0x1000}, {RT5682_DAC_ADC_DIG_VOL1, 0xa020}, + {RT5682_I2C_CTRL, 0x000f}, }; static const struct reg_default rt5682_reg[] = { @@ -2474,6 +2475,7 @@ static void rt5682_calibrate(struct rt5682_priv *rt5682) mutex_lock(&rt5682->calibrate_mutex); rt5682_reset(rt5682->regmap); + regmap_write(rt5682->regmap, RT5682_I2C_CTRL, 0x000f); regmap_write(rt5682->regmap, RT5682_PWR_ANLG_1, 0xa2af); usleep_range(15000, 20000); regmap_write(rt5682->regmap, RT5682_PWR_ANLG_1, 0xf2af); diff --git a/sound/soc/codecs/wm8904.c b/sound/soc/codecs/wm8904.c index 7d7ea15d73e0..5ffbaddd6e49 100644 --- a/sound/soc/codecs/wm8904.c +++ b/sound/soc/codecs/wm8904.c @@ -1806,6 +1806,12 @@ static int wm8904_set_sysclk(struct snd_soc_dai *dai, int clk_id, switch (clk_id) { case WM8904_CLK_AUTO: + /* We don't have any rate constraints, so just ignore the + * request to disable constraining. + */ + if (!freq) + return 0; + mclk_freq = clk_get_rate(priv->mclk); /* enable FLL if a different sysclk is desired */ if (mclk_freq != freq) { diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c index 3e5c69fbc33a..d9d59f45833f 100644 --- a/sound/soc/codecs/wm8962.c +++ b/sound/soc/codecs/wm8962.c @@ -2788,7 +2788,7 @@ static int fll_factors(struct _fll_div *fll_div, unsigned int Fref, if (target % Fref == 0) { fll_div->theta = 0; - fll_div->lambda = 0; + fll_div->lambda = 1; } else { gcd_fll = gcd(target, fratio * Fref); @@ -2858,7 +2858,7 @@ static int wm8962_set_fll(struct snd_soc_component *component, int fll_id, int s return -EINVAL; } - if (fll_div.theta || fll_div.lambda) + if (fll_div.theta) fll1 |= WM8962_FLL_FRAC; /* Stop the FLL while we reconfigure */ diff --git a/sound/soc/generic/simple-card.c b/sound/soc/generic/simple-card.c index 10b82bf043d1..55e9f8800b3e 100644 --- a/sound/soc/generic/simple-card.c +++ b/sound/soc/generic/simple-card.c @@ -371,6 +371,7 @@ static int simple_for_each_link(struct asoc_simple_priv *priv, do { struct asoc_simple_data adata; struct device_node *codec; + struct device_node *plat; struct device_node *np; int num = of_get_child_count(node); @@ -381,6 +382,9 @@ static int simple_for_each_link(struct asoc_simple_priv *priv, ret = -ENODEV; goto error; } + /* get platform */ + plat = of_get_child_by_name(node, is_top ? + PREFIX "plat" : "plat"); /* get convert-xxx property */ memset(&adata, 0, sizeof(adata)); @@ -389,6 +393,8 @@ static int simple_for_each_link(struct asoc_simple_priv *priv, /* loop for all CPU/Codec node */ for_each_child_of_node(node, np) { + if (plat == np) + continue; /* * It is DPCM * if it has many CPUs, diff --git a/sound/soc/intel/atom/sst/sst.c b/sound/soc/intel/atom/sst/sst.c index fbecbb74350b..68bcec5241f7 100644 --- a/sound/soc/intel/atom/sst/sst.c +++ b/sound/soc/intel/atom/sst/sst.c @@ -14,6 +14,7 @@ #include <linux/module.h> #include <linux/fs.h> #include <linux/interrupt.h> +#include <linux/io.h> #include <linux/firmware.h> #include <linux/pm_runtime.h> #include <linux/pm_qos.h> diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c index dd2b5ad08659..243f683bc02a 100644 --- a/sound/soc/intel/boards/bytcr_rt5640.c +++ b/sound/soc/intel/boards/bytcr_rt5640.c @@ -707,13 +707,17 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = { BYT_RT5640_MCLK_EN), }, { + /* Teclast X89 */ .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "TECLAST"), DMI_MATCH(DMI_BOARD_NAME, "tPAD"), }, .driver_data = (void *)(BYT_RT5640_IN3_MAP | - BYT_RT5640_MCLK_EN | - BYT_RT5640_SSP0_AIF1), + BYT_RT5640_JD_SRC_JD1_IN4P | + BYT_RT5640_OVCD_TH_2000UA | + BYT_RT5640_OVCD_SF_1P0 | + BYT_RT5640_SSP0_AIF1 | + BYT_RT5640_MCLK_EN), }, { /* Toshiba Satellite Click Mini L9W-B */ .matches = { diff --git a/sound/soc/intel/common/soc-acpi-intel-cml-match.c b/sound/soc/intel/common/soc-acpi-intel-cml-match.c index 5d08ae066738..fb9ba8819706 100644 --- a/sound/soc/intel/common/soc-acpi-intel-cml-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-cml-match.c @@ -9,45 +9,52 @@ #include <sound/soc-acpi.h> #include <sound/soc-acpi-intel-match.h> -static struct snd_soc_acpi_codecs cml_codecs = { +static struct snd_soc_acpi_codecs rt1011_spk_codecs = { .num_codecs = 1, - .codecs = {"10EC5682"} + .codecs = {"10EC1011"} }; -static struct snd_soc_acpi_codecs cml_spk_codecs = { +static struct snd_soc_acpi_codecs max98357a_spk_codecs = { .num_codecs = 1, .codecs = {"MX98357A"} }; +/* + * The order of the three entries with .id = "10EC5682" matters + * here, because DSDT tables expose an ACPI HID for the MAX98357A + * speaker amplifier which is not populated on the board. + */ struct snd_soc_acpi_mach snd_soc_acpi_intel_cml_machines[] = { { - .id = "DLGS7219", - .drv_name = "cml_da7219_max98357a", - .quirk_data = &cml_spk_codecs, + .id = "10EC5682", + .drv_name = "cml_rt1011_rt5682", + .machine_quirk = snd_soc_acpi_codec_list, + .quirk_data = &rt1011_spk_codecs, .sof_fw_filename = "sof-cml.ri", - .sof_tplg_filename = "sof-cml-da7219-max98357a.tplg", + .sof_tplg_filename = "sof-cml-rt1011-rt5682.tplg", }, { - .id = "MX98357A", + .id = "10EC5682", .drv_name = "sof_rt5682", - .quirk_data = &cml_codecs, + .machine_quirk = snd_soc_acpi_codec_list, + .quirk_data = &max98357a_spk_codecs, .sof_fw_filename = "sof-cml.ri", .sof_tplg_filename = "sof-cml-rt5682-max98357a.tplg", }, { - .id = "10EC1011", - .drv_name = "cml_rt1011_rt5682", - .quirk_data = &cml_codecs, - .sof_fw_filename = "sof-cml.ri", - .sof_tplg_filename = "sof-cml-rt1011-rt5682.tplg", - }, - { .id = "10EC5682", .drv_name = "sof_rt5682", .sof_fw_filename = "sof-cml.ri", .sof_tplg_filename = "sof-cml-rt5682.tplg", }, - + { + .id = "DLGS7219", + .drv_name = "cml_da7219_max98357a", + .machine_quirk = snd_soc_acpi_codec_list, + .quirk_data = &max98357a_spk_codecs, + .sof_fw_filename = "sof-cml.ri", + .sof_tplg_filename = "sof-cml-da7219-max98357a.tplg", + }, {}, }; EXPORT_SYMBOL_GPL(snd_soc_acpi_intel_cml_machines); diff --git a/sound/soc/soc-compress.c b/sound/soc/soc-compress.c index 61f230324164..6615ef64c7f5 100644 --- a/sound/soc/soc-compress.c +++ b/sound/soc/soc-compress.c @@ -214,10 +214,8 @@ be_err: * This is to ensure there are no pops or clicks in between any music tracks * due to DAPM power cycling. */ -static void close_delayed_work(struct work_struct *work) +static void close_delayed_work(struct snd_soc_pcm_runtime *rtd) { - struct snd_soc_pcm_runtime *rtd = - container_of(work, struct snd_soc_pcm_runtime, delayed_work.work); struct snd_soc_dai *codec_dai = rtd->codec_dai; mutex_lock_nested(&rtd->card->pcm_mutex, rtd->card->pcm_subclass); @@ -929,7 +927,7 @@ int snd_soc_new_compress(struct snd_soc_pcm_runtime *rtd, int num) } /* DAPM dai link stream work */ - INIT_DELAYED_WORK(&rtd->delayed_work, close_delayed_work); + rtd->close_delayed_work_func = close_delayed_work; rtd->compr = compr; compr->private_data = rtd; diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index 062653ab03a3..1c84ff1a5bf9 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -419,7 +419,8 @@ static void soc_free_pcm_runtime(struct snd_soc_pcm_runtime *rtd) list_del(&rtd->list); - flush_delayed_work(&rtd->delayed_work); + if (delayed_work_pending(&rtd->delayed_work)) + flush_delayed_work(&rtd->delayed_work); snd_soc_pcm_component_free(rtd); /* @@ -435,6 +436,15 @@ static void soc_free_pcm_runtime(struct snd_soc_pcm_runtime *rtd) device_unregister(rtd->dev); } +static void close_delayed_work(struct work_struct *work) { + struct snd_soc_pcm_runtime *rtd = + container_of(work, struct snd_soc_pcm_runtime, + delayed_work.work); + + if (rtd->close_delayed_work_func) + rtd->close_delayed_work_func(rtd); +} + static struct snd_soc_pcm_runtime *soc_new_pcm_runtime( struct snd_soc_card *card, struct snd_soc_dai_link *dai_link) { @@ -470,6 +480,7 @@ static struct snd_soc_pcm_runtime *soc_new_pcm_runtime( rtd->dev = dev; dev_set_drvdata(dev, rtd); + INIT_DELAYED_WORK(&rtd->delayed_work, close_delayed_work); /* * for rtd->codec_dais diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index 76b7ee637e86..01e7bc03d92f 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -637,10 +637,8 @@ out: * This is to ensure there are no pops or clicks in between any music tracks * due to DAPM power cycling. */ -static void close_delayed_work(struct work_struct *work) +static void close_delayed_work(struct snd_soc_pcm_runtime *rtd) { - struct snd_soc_pcm_runtime *rtd = - container_of(work, struct snd_soc_pcm_runtime, delayed_work.work); struct snd_soc_dai *codec_dai = rtd->codec_dais[0]; mutex_lock_nested(&rtd->card->pcm_mutex, rtd->card->pcm_subclass); @@ -660,7 +658,7 @@ static void close_delayed_work(struct work_struct *work) mutex_unlock(&rtd->card->pcm_mutex); } -static void codec2codec_close_delayed_work(struct work_struct *work) +static void codec2codec_close_delayed_work(struct snd_soc_pcm_runtime *rtd) { /* * Currently nothing to do for c2c links @@ -2974,10 +2972,9 @@ int soc_new_pcm(struct snd_soc_pcm_runtime *rtd, int num) /* DAPM dai link stream work */ if (rtd->dai_link->params) - INIT_DELAYED_WORK(&rtd->delayed_work, - codec2codec_close_delayed_work); + rtd->close_delayed_work_func = codec2codec_close_delayed_work; else - INIT_DELAYED_WORK(&rtd->delayed_work, close_delayed_work); + rtd->close_delayed_work_func = close_delayed_work; pcm->nonatomic = rtd->dai_link->nonatomic; rtd->pcm = pcm; diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c index 81d2af000a5c..b28613149b0c 100644 --- a/sound/soc/soc-topology.c +++ b/sound/soc/soc-topology.c @@ -1933,11 +1933,13 @@ static int soc_tplg_fe_link_create(struct soc_tplg *tplg, ret = soc_tplg_dai_link_load(tplg, link, NULL); if (ret < 0) { dev_err(tplg->comp->dev, "ASoC: FE link loading failed\n"); - kfree(link->name); - kfree(link->stream_name); - kfree(link->cpus->dai_name); - kfree(link); - return ret; + goto err; + } + + ret = snd_soc_add_dai_link(tplg->comp->card, link); + if (ret < 0) { + dev_err(tplg->comp->dev, "ASoC: adding FE link failed\n"); + goto err; } link->dobj.index = tplg->index; @@ -1945,8 +1947,13 @@ static int soc_tplg_fe_link_create(struct soc_tplg *tplg, link->dobj.type = SND_SOC_DOBJ_DAI_LINK; list_add(&link->dobj.list, &tplg->comp->dobj_list); - snd_soc_add_dai_link(tplg->comp->card, link); return 0; +err: + kfree(link->name); + kfree(link->stream_name); + kfree(link->cpus->dai_name); + kfree(link); + return ret; } /* create a FE DAI and DAI link from the PCM object */ @@ -2039,6 +2046,7 @@ static int soc_tplg_pcm_elems_load(struct soc_tplg *tplg, int size; int i; bool abi_match; + int ret; count = le32_to_cpu(hdr->count); @@ -2080,7 +2088,12 @@ static int soc_tplg_pcm_elems_load(struct soc_tplg *tplg, } /* create the FE DAIs and DAI links */ - soc_tplg_pcm_create(tplg, _pcm); + ret = soc_tplg_pcm_create(tplg, _pcm); + if (ret < 0) { + if (!abi_match) + kfree(_pcm); + return ret; + } /* offset by version-specific struct size and * real priv data size diff --git a/sound/soc/sof/intel/byt.c b/sound/soc/sof/intel/byt.c index 2abf80b3eb52..92ef6a796fd5 100644 --- a/sound/soc/sof/intel/byt.c +++ b/sound/soc/sof/intel/byt.c @@ -24,7 +24,8 @@ #define DRAM_OFFSET 0x100000 #define DRAM_SIZE (160 * 1024) #define SHIM_OFFSET 0x140000 -#define SHIM_SIZE 0x100 +#define SHIM_SIZE_BYT 0x100 +#define SHIM_SIZE_CHT 0x118 #define MBOX_OFFSET 0x144000 #define MBOX_SIZE 0x1000 #define EXCEPT_OFFSET 0x800 @@ -75,7 +76,7 @@ static const struct snd_sof_debugfs_map byt_debugfs[] = { SOF_DEBUGFS_ACCESS_D0_ONLY}, {"dram", BYT_DSP_BAR, DRAM_OFFSET, DRAM_SIZE, SOF_DEBUGFS_ACCESS_D0_ONLY}, - {"shim", BYT_DSP_BAR, SHIM_OFFSET, SHIM_SIZE, + {"shim", BYT_DSP_BAR, SHIM_OFFSET, SHIM_SIZE_BYT, SOF_DEBUGFS_ACCESS_ALWAYS}, }; @@ -102,7 +103,7 @@ static const struct snd_sof_debugfs_map cht_debugfs[] = { SOF_DEBUGFS_ACCESS_D0_ONLY}, {"dram", BYT_DSP_BAR, DRAM_OFFSET, DRAM_SIZE, SOF_DEBUGFS_ACCESS_D0_ONLY}, - {"shim", BYT_DSP_BAR, SHIM_OFFSET, SHIM_SIZE, + {"shim", BYT_DSP_BAR, SHIM_OFFSET, SHIM_SIZE_CHT, SOF_DEBUGFS_ACCESS_ALWAYS}, }; @@ -145,33 +146,33 @@ static void byt_dump(struct snd_sof_dev *sdev, u32 flags) struct sof_ipc_dsp_oops_xtensa xoops; struct sof_ipc_panic_info panic_info; u32 stack[BYT_STACK_DUMP_SIZE]; - u32 status, panic, imrd, imrx; + u64 status, panic, imrd, imrx; /* now try generic SOF status messages */ - status = snd_sof_dsp_read(sdev, BYT_DSP_BAR, SHIM_IPCD); - panic = snd_sof_dsp_read(sdev, BYT_DSP_BAR, SHIM_IPCX); + status = snd_sof_dsp_read64(sdev, BYT_DSP_BAR, SHIM_IPCD); + panic = snd_sof_dsp_read64(sdev, BYT_DSP_BAR, SHIM_IPCX); byt_get_registers(sdev, &xoops, &panic_info, stack, BYT_STACK_DUMP_SIZE); snd_sof_get_status(sdev, status, panic, &xoops, &panic_info, stack, BYT_STACK_DUMP_SIZE); /* provide some context for firmware debug */ - imrx = snd_sof_dsp_read(sdev, BYT_DSP_BAR, SHIM_IMRX); - imrd = snd_sof_dsp_read(sdev, BYT_DSP_BAR, SHIM_IMRD); + imrx = snd_sof_dsp_read64(sdev, BYT_DSP_BAR, SHIM_IMRX); + imrd = snd_sof_dsp_read64(sdev, BYT_DSP_BAR, SHIM_IMRD); dev_err(sdev->dev, - "error: ipc host -> DSP: pending %s complete %s raw 0x%8.8x\n", + "error: ipc host -> DSP: pending %s complete %s raw 0x%llx\n", (panic & SHIM_IPCX_BUSY) ? "yes" : "no", (panic & SHIM_IPCX_DONE) ? "yes" : "no", panic); dev_err(sdev->dev, - "error: mask host: pending %s complete %s raw 0x%8.8x\n", + "error: mask host: pending %s complete %s raw 0x%llx\n", (imrx & SHIM_IMRX_BUSY) ? "yes" : "no", (imrx & SHIM_IMRX_DONE) ? "yes" : "no", imrx); dev_err(sdev->dev, - "error: ipc DSP -> host: pending %s complete %s raw 0x%8.8x\n", + "error: ipc DSP -> host: pending %s complete %s raw 0x%llx\n", (status & SHIM_IPCD_BUSY) ? "yes" : "no", (status & SHIM_IPCD_DONE) ? "yes" : "no", status); dev_err(sdev->dev, - "error: mask DSP: pending %s complete %s raw 0x%8.8x\n", + "error: mask DSP: pending %s complete %s raw 0x%llx\n", (imrd & SHIM_IMRD_BUSY) ? "yes" : "no", (imrd & SHIM_IMRD_DONE) ? "yes" : "no", imrd); diff --git a/sound/soc/sof/loader.c b/sound/soc/sof/loader.c index 9a9a381a908d..432d12bd4937 100644 --- a/sound/soc/sof/loader.c +++ b/sound/soc/sof/loader.c @@ -50,8 +50,7 @@ int snd_sof_fw_parse_ext_data(struct snd_sof_dev *sdev, u32 bar, u32 offset) while (ext_hdr->hdr.cmd == SOF_IPC_FW_READY) { /* read in ext structure */ - offset += sizeof(*ext_hdr); - snd_sof_dsp_block_read(sdev, bar, offset, + snd_sof_dsp_block_read(sdev, bar, offset + sizeof(*ext_hdr), (void *)((u8 *)ext_data + sizeof(*ext_hdr)), ext_hdr->hdr.size - sizeof(*ext_hdr)); @@ -61,11 +60,15 @@ int snd_sof_fw_parse_ext_data(struct snd_sof_dev *sdev, u32 bar, u32 offset) /* process structure data */ switch (ext_hdr->type) { case SOF_IPC_EXT_DMA_BUFFER: + ret = 0; break; case SOF_IPC_EXT_WINDOW: ret = get_ext_windows(sdev, ext_hdr); break; default: + dev_warn(sdev->dev, "warning: unknown ext header type %d size 0x%x\n", + ext_hdr->type, ext_hdr->hdr.size); + ret = 0; break; } diff --git a/sound/soc/sof/topology.c b/sound/soc/sof/topology.c index d82ab981e840..e20b806ec80f 100644 --- a/sound/soc/sof/topology.c +++ b/sound/soc/sof/topology.c @@ -3132,7 +3132,9 @@ found: case SOF_DAI_INTEL_SSP: case SOF_DAI_INTEL_DMIC: case SOF_DAI_INTEL_ALH: - /* no resource needs to be released for SSP, DMIC and ALH */ + case SOF_DAI_IMX_SAI: + case SOF_DAI_IMX_ESAI: + /* no resource needs to be released for all cases above */ break; case SOF_DAI_INTEL_HDA: ret = sof_link_hda_unload(sdev, link); diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h index 2769360f195c..03cd7c19a683 100644 --- a/tools/arch/arm/include/uapi/asm/kvm.h +++ b/tools/arch/arm/include/uapi/asm/kvm.h @@ -131,8 +131,9 @@ struct kvm_vcpu_events { struct { __u8 serror_pending; __u8 serror_has_esr; + __u8 ext_dabt_pending; /* Align it to 8 bytes */ - __u8 pad[6]; + __u8 pad[5]; __u64 serror_esr; } exception; __u32 reserved[12]; diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index 67c21f9bdbad..820e5751ada7 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -164,8 +164,9 @@ struct kvm_vcpu_events { struct { __u8 serror_pending; __u8 serror_has_esr; + __u8 ext_dabt_pending; /* Align it to 8 bytes */ - __u8 pad[6]; + __u8 pad[5]; __u64 serror_esr; } exception; __u32 reserved[12]; @@ -323,6 +324,8 @@ struct kvm_vcpu_events { #define KVM_ARM_VCPU_TIMER_CTRL 1 #define KVM_ARM_VCPU_TIMER_IRQ_VTIMER 0 #define KVM_ARM_VCPU_TIMER_IRQ_PTIMER 1 +#define KVM_ARM_VCPU_PVTIME_CTRL 2 +#define KVM_ARM_VCPU_PVTIME_IPA 0 /* KVM_IRQ_LINE irq field index values */ #define KVM_ARM_IRQ_VCPU2_SHIFT 28 diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h index b0f72dea8b11..264e266a85bf 100644 --- a/tools/arch/powerpc/include/uapi/asm/kvm.h +++ b/tools/arch/powerpc/include/uapi/asm/kvm.h @@ -667,6 +667,8 @@ struct kvm_ppc_cpu_char { /* PPC64 eXternal Interrupt Controller Specification */ #define KVM_DEV_XICS_GRP_SOURCES 1 /* 64-bit source attributes */ +#define KVM_DEV_XICS_GRP_CTRL 2 +#define KVM_DEV_XICS_NR_SERVERS 1 /* Layout of 64-bit source attribute values */ #define KVM_XICS_DESTINATION_SHIFT 0 @@ -683,6 +685,7 @@ struct kvm_ppc_cpu_char { #define KVM_DEV_XIVE_GRP_CTRL 1 #define KVM_DEV_XIVE_RESET 1 #define KVM_DEV_XIVE_EQ_SYNC 2 +#define KVM_DEV_XIVE_NR_SERVERS 3 #define KVM_DEV_XIVE_GRP_SOURCE 2 /* 64-bit source identifier */ #define KVM_DEV_XIVE_GRP_SOURCE_CONFIG 3 /* 64-bit source identifier */ #define KVM_DEV_XIVE_GRP_EQ_CONFIG 4 /* 64-bit EQ identifier */ diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 0652d3eed9bd..e9b62498fe75 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -292,6 +292,7 @@ #define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */ #define X86_FEATURE_IRPERF (13*32+ 1) /* Instructions Retired Count */ #define X86_FEATURE_XSAVEERPTR (13*32+ 2) /* Always save/restore FP error pointers */ +#define X86_FEATURE_RDPRU (13*32+ 4) /* Read processor register at user level */ #define X86_FEATURE_WBNOINVD (13*32+ 9) /* WBNOINVD instruction */ #define X86_FEATURE_AMD_IBPB (13*32+12) /* "" Indirect Branch Prediction Barrier */ #define X86_FEATURE_AMD_IBRS (13*32+14) /* "" Indirect Branch Restricted Speculation */ @@ -399,5 +400,7 @@ #define X86_BUG_MDS X86_BUG(19) /* CPU is affected by Microarchitectural data sampling */ #define X86_BUG_MSBDS_ONLY X86_BUG(20) /* CPU is only affected by the MSDBS variant of BUG_MDS */ #define X86_BUG_SWAPGS X86_BUG(21) /* CPU is affected by speculation through SWAPGS */ +#define X86_BUG_TAA X86_BUG(22) /* CPU is affected by TSX Async Abort(TAA) */ +#define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index 20ce682a2540..084e98da04a7 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -93,6 +93,18 @@ * Microarchitectural Data * Sampling (MDS) vulnerabilities. */ +#define ARCH_CAP_PSCHANGE_MC_NO BIT(6) /* + * The processor is not susceptible to a + * machine check error due to modifying the + * code page size along with either the + * physical address or cache type + * without TLB invalidation. + */ +#define ARCH_CAP_TSX_CTRL_MSR BIT(7) /* MSR for TSX control is available. */ +#define ARCH_CAP_TAA_NO BIT(8) /* + * Not susceptible to + * TSX Async Abort (TAA) vulnerabilities. + */ #define MSR_IA32_FLUSH_CMD 0x0000010b #define L1D_FLUSH BIT(0) /* @@ -103,6 +115,10 @@ #define MSR_IA32_BBL_CR_CTL 0x00000119 #define MSR_IA32_BBL_CR_CTL3 0x0000011e +#define MSR_IA32_TSX_CTRL 0x00000122 +#define TSX_CTRL_RTM_DISABLE BIT(0) /* Disable RTM feature */ +#define TSX_CTRL_CPUID_CLEAR BIT(1) /* Disable TSX enumeration */ + #define MSR_IA32_SYSENTER_CS 0x00000174 #define MSR_IA32_SYSENTER_ESP 0x00000175 #define MSR_IA32_SYSENTER_EIP 0x00000176 @@ -393,6 +409,8 @@ #define MSR_AMD_PSTATE_DEF_BASE 0xc0010064 #define MSR_AMD64_OSVW_ID_LENGTH 0xc0010140 #define MSR_AMD64_OSVW_STATUS 0xc0010141 +#define MSR_AMD_PPIN_CTL 0xc00102f0 +#define MSR_AMD_PPIN 0xc00102f1 #define MSR_AMD64_LS_CFG 0xc0011020 #define MSR_AMD64_DC_CFG 0xc0011022 #define MSR_AMD64_BU_CFG2 0xc001102a diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S index 92748660ba51..df767afc690f 100644 --- a/tools/arch/x86/lib/memcpy_64.S +++ b/tools/arch/x86/lib/memcpy_64.S @@ -28,8 +28,8 @@ * Output: * rax original destination */ -ENTRY(__memcpy) -ENTRY(memcpy) +SYM_FUNC_START_ALIAS(__memcpy) +SYM_FUNC_START_LOCAL(memcpy) ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \ "jmp memcpy_erms", X86_FEATURE_ERMS @@ -41,8 +41,8 @@ ENTRY(memcpy) movl %edx, %ecx rep movsb ret -ENDPROC(memcpy) -ENDPROC(__memcpy) +SYM_FUNC_END(memcpy) +SYM_FUNC_END_ALIAS(__memcpy) EXPORT_SYMBOL(memcpy) EXPORT_SYMBOL(__memcpy) @@ -50,14 +50,14 @@ EXPORT_SYMBOL(__memcpy) * memcpy_erms() - enhanced fast string memcpy. This is faster and * simpler than memcpy. Use memcpy_erms when possible. */ -ENTRY(memcpy_erms) +SYM_FUNC_START(memcpy_erms) movq %rdi, %rax movq %rdx, %rcx rep movsb ret -ENDPROC(memcpy_erms) +SYM_FUNC_END(memcpy_erms) -ENTRY(memcpy_orig) +SYM_FUNC_START(memcpy_orig) movq %rdi, %rax cmpq $0x20, %rdx @@ -182,7 +182,7 @@ ENTRY(memcpy_orig) .Lend: retq -ENDPROC(memcpy_orig) +SYM_FUNC_END(memcpy_orig) #ifndef CONFIG_UML @@ -193,7 +193,7 @@ MCSAFE_TEST_CTL * Note that we only catch machine checks when reading the source addresses. * Writes to target are posted and don't generate machine checks. */ -ENTRY(__memcpy_mcsafe) +SYM_FUNC_START(__memcpy_mcsafe) cmpl $8, %edx /* Less than 8 bytes? Go to byte copy loop */ jb .L_no_whole_words @@ -260,7 +260,7 @@ ENTRY(__memcpy_mcsafe) xorl %eax, %eax .L_done: ret -ENDPROC(__memcpy_mcsafe) +SYM_FUNC_END(__memcpy_mcsafe) EXPORT_SYMBOL_GPL(__memcpy_mcsafe) .section .fixup, "ax" diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S index f8f3dc0a6690..fd5d25a474b7 100644 --- a/tools/arch/x86/lib/memset_64.S +++ b/tools/arch/x86/lib/memset_64.S @@ -18,8 +18,8 @@ * * rax original destination */ -ENTRY(memset) -ENTRY(__memset) +SYM_FUNC_START_ALIAS(memset) +SYM_FUNC_START(__memset) /* * Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended * to use it when possible. If not available, use fast string instructions. @@ -42,8 +42,8 @@ ENTRY(__memset) rep stosb movq %r9,%rax ret -ENDPROC(memset) -ENDPROC(__memset) +SYM_FUNC_END(__memset) +SYM_FUNC_END_ALIAS(memset) /* * ISO C memset - set a memory block to a byte value. This function uses @@ -56,16 +56,16 @@ ENDPROC(__memset) * * rax original destination */ -ENTRY(memset_erms) +SYM_FUNC_START(memset_erms) movq %rdi,%r9 movb %sil,%al movq %rdx,%rcx rep stosb movq %r9,%rax ret -ENDPROC(memset_erms) +SYM_FUNC_END(memset_erms) -ENTRY(memset_orig) +SYM_FUNC_START(memset_orig) movq %rdi,%r10 /* expand byte value */ @@ -136,4 +136,4 @@ ENTRY(memset_orig) subq %r8,%rdx jmp .Lafter_bad_alignment .Lfinal: -ENDPROC(memset_orig) +SYM_FUNC_END(memset_orig) diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 4535c863d2cd..2ce9c5ba1934 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -493,7 +493,7 @@ static int do_dump(int argc, char **argv) info = &info_linear->info; if (mode == DUMP_JITED) { - if (info->jited_prog_len == 0) { + if (info->jited_prog_len == 0 || !info->jited_prog_insns) { p_info("no instructions returned"); goto err_free; } diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c index 494d7ae3614d..5b91ee65a080 100644 --- a/tools/bpf/bpftool/xlated_dumper.c +++ b/tools/bpf/bpftool/xlated_dumper.c @@ -174,7 +174,7 @@ static const char *print_call(void *private_data, struct kernel_sym *sym; if (insn->src_reg == BPF_PSEUDO_CALL && - (__u32) insn->imm < dd->nr_jited_ksyms) + (__u32) insn->imm < dd->nr_jited_ksyms && dd->jited_ksyms) address = dd->jited_ksyms[insn->imm]; sym = kernel_syms_search(dd, address); diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h index 8a5b2f8f8eb9..868bf7996c0f 100644 --- a/tools/include/uapi/drm/drm.h +++ b/tools/include/uapi/drm/drm.h @@ -778,11 +778,12 @@ struct drm_syncobj_array { __u32 pad; }; +#define DRM_SYNCOBJ_QUERY_FLAGS_LAST_SUBMITTED (1 << 0) /* last available point on timeline syncobj */ struct drm_syncobj_timeline_array { __u64 handles; __u64 points; __u32 count_handles; - __u32 pad; + __u32 flags; }; diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index 469dc512cca3..5400d7e057f1 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -611,6 +611,13 @@ typedef struct drm_i915_irq_wait { * See I915_EXEC_FENCE_OUT and I915_EXEC_FENCE_SUBMIT. */ #define I915_PARAM_HAS_EXEC_SUBMIT_FENCE 53 + +/* + * Revision of the i915-perf uAPI. The value returned helps determine what + * i915-perf features are available. See drm_i915_perf_property_id. + */ +#define I915_PARAM_PERF_REVISION 54 + /* Must be kept compact -- no holes and well documented */ typedef struct drm_i915_getparam { @@ -1565,6 +1572,21 @@ struct drm_i915_gem_context_param { * i915_context_engines_bond (I915_CONTEXT_ENGINES_EXT_BOND) */ #define I915_CONTEXT_PARAM_ENGINES 0xa + +/* + * I915_CONTEXT_PARAM_PERSISTENCE: + * + * Allow the context and active rendering to survive the process until + * completion. Persistence allows fire-and-forget clients to queue up a + * bunch of work, hand the output over to a display server and then quit. + * If the context is marked as not persistent, upon closing (either via + * an explicit DRM_I915_GEM_CONTEXT_DESTROY or implicitly from file closure + * or process termination), the context and any outstanding requests will be + * cancelled (and exported fences for cancelled requests marked as -EIO). + * + * By default, new contexts allow persistence. + */ +#define I915_CONTEXT_PARAM_PERSISTENCE 0xb /* Must be kept compact -- no holes and well documented */ __u64 value; @@ -1844,23 +1866,31 @@ enum drm_i915_perf_property_id { * Open the stream for a specific context handle (as used with * execbuffer2). A stream opened for a specific context this way * won't typically require root privileges. + * + * This property is available in perf revision 1. */ DRM_I915_PERF_PROP_CTX_HANDLE = 1, /** * A value of 1 requests the inclusion of raw OA unit reports as * part of stream samples. + * + * This property is available in perf revision 1. */ DRM_I915_PERF_PROP_SAMPLE_OA, /** * The value specifies which set of OA unit metrics should be * be configured, defining the contents of any OA unit reports. + * + * This property is available in perf revision 1. */ DRM_I915_PERF_PROP_OA_METRICS_SET, /** * The value specifies the size and layout of OA unit reports. + * + * This property is available in perf revision 1. */ DRM_I915_PERF_PROP_OA_FORMAT, @@ -1870,9 +1900,22 @@ enum drm_i915_perf_property_id { * from this exponent as follows: * * 80ns * 2^(period_exponent + 1) + * + * This property is available in perf revision 1. */ DRM_I915_PERF_PROP_OA_EXPONENT, + /** + * Specifying this property is only valid when specify a context to + * filter with DRM_I915_PERF_PROP_CTX_HANDLE. Specifying this property + * will hold preemption of the particular context we want to gather + * performance data about. The execbuf2 submissions must include a + * drm_i915_gem_execbuffer_ext_perf parameter for this to apply. + * + * This property is available in perf revision 3. + */ + DRM_I915_PERF_PROP_HOLD_PREEMPTION, + DRM_I915_PERF_PROP_MAX /* non-ABI */ }; @@ -1901,6 +1944,8 @@ struct drm_i915_perf_open_param { * to close and re-open a stream with the same configuration. * * It's undefined whether any pending data for the stream will be lost. + * + * This ioctl is available in perf revision 1. */ #define I915_PERF_IOCTL_ENABLE _IO('i', 0x0) @@ -1908,10 +1953,25 @@ struct drm_i915_perf_open_param { * Disable data capture for a stream. * * It is an error to try and read a stream that is disabled. + * + * This ioctl is available in perf revision 1. */ #define I915_PERF_IOCTL_DISABLE _IO('i', 0x1) /** + * Change metrics_set captured by a stream. + * + * If the stream is bound to a specific context, the configuration change + * will performed inline with that context such that it takes effect before + * the next execbuf submission. + * + * Returns the previously bound metrics set id, or a negative error code. + * + * This ioctl is available in perf revision 2. + */ +#define I915_PERF_IOCTL_CONFIG _IO('i', 0x2) + +/** * Common to all i915 perf records */ struct drm_i915_perf_record_header { @@ -1984,6 +2044,7 @@ struct drm_i915_query_item { __u64 query_id; #define DRM_I915_QUERY_TOPOLOGY_INFO 1 #define DRM_I915_QUERY_ENGINE_INFO 2 +#define DRM_I915_QUERY_PERF_CONFIG 3 /* Must be kept compact -- no holes and well documented */ /* @@ -1995,9 +2056,18 @@ struct drm_i915_query_item { __s32 length; /* - * Unused for now. Must be cleared to zero. + * When query_id == DRM_I915_QUERY_TOPOLOGY_INFO, must be 0. + * + * When query_id == DRM_I915_QUERY_PERF_CONFIG, must be one of the + * following : + * - DRM_I915_QUERY_PERF_CONFIG_LIST + * - DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID + * - DRM_I915_QUERY_PERF_CONFIG_FOR_UUID */ __u32 flags; +#define DRM_I915_QUERY_PERF_CONFIG_LIST 1 +#define DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID 2 +#define DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_ID 3 /* * Data will be written at the location pointed by data_ptr when the @@ -2033,8 +2103,10 @@ struct drm_i915_query { * (data[X / 8] >> (X % 8)) & 1 * * - the subslice mask for each slice with one bit per subslice telling - * whether a subslice is available. The availability of subslice Y in slice - * X can be queried with the following formula : + * whether a subslice is available. Gen12 has dual-subslices, which are + * similar to two gen11 subslices. For gen12, this array represents dual- + * subslices. The availability of subslice Y in slice X can be queried + * with the following formula : * * (data[subslice_offset + * X * subslice_stride + @@ -2123,6 +2195,56 @@ struct drm_i915_query_engine_info { struct drm_i915_engine_info engines[]; }; +/* + * Data written by the kernel with query DRM_I915_QUERY_PERF_CONFIG. + */ +struct drm_i915_query_perf_config { + union { + /* + * When query_item.flags == DRM_I915_QUERY_PERF_CONFIG_LIST, i915 sets + * this fields to the number of configurations available. + */ + __u64 n_configs; + + /* + * When query_id == DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_ID, + * i915 will use the value in this field as configuration + * identifier to decide what data to write into config_ptr. + */ + __u64 config; + + /* + * When query_id == DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID, + * i915 will use the value in this field as configuration + * identifier to decide what data to write into config_ptr. + * + * String formatted like "%08x-%04x-%04x-%04x-%012x" + */ + char uuid[36]; + }; + + /* + * Unused for now. Must be cleared to zero. + */ + __u32 flags; + + /* + * When query_item.flags == DRM_I915_QUERY_PERF_CONFIG_LIST, i915 will + * write an array of __u64 of configuration identifiers. + * + * When query_item.flags == DRM_I915_QUERY_PERF_CONFIG_DATA, i915 will + * write a struct drm_i915_perf_oa_config. If the following fields of + * drm_i915_perf_oa_config are set not set to 0, i915 will write into + * the associated pointers the values of submitted when the + * configuration was created : + * + * - n_mux_regs + * - n_boolean_regs + * - n_flex_regs + */ + __u8 data[]; +}; + #if defined(__cplusplus) } #endif diff --git a/tools/include/uapi/linux/fscrypt.h b/tools/include/uapi/linux/fscrypt.h index 39ccfe9311c3..1beb174ad950 100644 --- a/tools/include/uapi/linux/fscrypt.h +++ b/tools/include/uapi/linux/fscrypt.h @@ -17,7 +17,8 @@ #define FSCRYPT_POLICY_FLAGS_PAD_32 0x03 #define FSCRYPT_POLICY_FLAGS_PAD_MASK 0x03 #define FSCRYPT_POLICY_FLAG_DIRECT_KEY 0x04 -#define FSCRYPT_POLICY_FLAGS_VALID 0x07 +#define FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64 0x08 +#define FSCRYPT_POLICY_FLAGS_VALID 0x0F /* Encryption algorithms */ #define FSCRYPT_MODE_AES_256_XTS 1 diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 52641d8ca9e8..f0a16b4adbbd 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -235,6 +235,7 @@ struct kvm_hyperv_exit { #define KVM_EXIT_S390_STSI 25 #define KVM_EXIT_IOAPIC_EOI 26 #define KVM_EXIT_HYPERV 27 +#define KVM_EXIT_ARM_NISV 28 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -394,6 +395,11 @@ struct kvm_run { } eoi; /* KVM_EXIT_HYPERV */ struct kvm_hyperv_exit hyperv; + /* KVM_EXIT_ARM_NISV */ + struct { + __u64 esr_iss; + __u64 fault_ipa; + } arm_nisv; /* Fix the size of the union. */ char padding[256]; }; @@ -1000,6 +1006,9 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_PMU_EVENT_FILTER 173 #define KVM_CAP_ARM_IRQ_LINE_LAYOUT_2 174 #define KVM_CAP_HYPERV_DIRECT_TLBFLUSH 175 +#define KVM_CAP_PPC_GUEST_DEBUG_SSTEP 176 +#define KVM_CAP_ARM_NISV_TO_USER 177 +#define KVM_CAP_ARM_INJECT_EXT_DABT 178 #ifdef KVM_CAP_IRQ_ROUTING @@ -1227,6 +1236,8 @@ enum kvm_device_type { #define KVM_DEV_TYPE_ARM_VGIC_ITS KVM_DEV_TYPE_ARM_VGIC_ITS KVM_DEV_TYPE_XIVE, #define KVM_DEV_TYPE_XIVE KVM_DEV_TYPE_XIVE + KVM_DEV_TYPE_ARM_PV_TIME, +#define KVM_DEV_TYPE_ARM_PV_TIME KVM_DEV_TYPE_ARM_PV_TIME KVM_DEV_TYPE_MAX, }; @@ -1337,6 +1348,7 @@ struct kvm_s390_ucas_mapping { #define KVM_PPC_GET_CPU_CHAR _IOR(KVMIO, 0xb1, struct kvm_ppc_cpu_char) /* Available with KVM_CAP_PMU_EVENT_FILTER */ #define KVM_SET_PMU_EVENT_FILTER _IOW(KVMIO, 0xb2, struct kvm_pmu_event_filter) +#define KVM_PPC_SVM_OFF _IO(KVMIO, 0xb3) /* ioctl for vm fd */ #define KVM_CREATE_DEVICE _IOWR(KVMIO, 0xe0, struct kvm_create_device) diff --git a/tools/include/uapi/linux/sched.h b/tools/include/uapi/linux/sched.h index 99335e1f4a27..4a0217832464 100644 --- a/tools/include/uapi/linux/sched.h +++ b/tools/include/uapi/linux/sched.h @@ -33,27 +33,48 @@ #define CLONE_NEWNET 0x40000000 /* New network namespace */ #define CLONE_IO 0x80000000 /* Clone io context */ +/* Flags for the clone3() syscall. */ +#define CLONE_CLEAR_SIGHAND 0x100000000ULL /* Clear any signal handler and reset to SIG_DFL. */ + #ifndef __ASSEMBLY__ /** * struct clone_args - arguments for the clone3 syscall - * @flags: Flags for the new process as listed above. - * All flags are valid except for CSIGNAL and - * CLONE_DETACHED. - * @pidfd: If CLONE_PIDFD is set, a pidfd will be - * returned in this argument. - * @child_tid: If CLONE_CHILD_SETTID is set, the TID of the - * child process will be returned in the child's - * memory. - * @parent_tid: If CLONE_PARENT_SETTID is set, the TID of - * the child process will be returned in the - * parent's memory. - * @exit_signal: The exit_signal the parent process will be - * sent when the child exits. - * @stack: Specify the location of the stack for the - * child process. - * @stack_size: The size of the stack for the child process. - * @tls: If CLONE_SETTLS is set, the tls descriptor - * is set to tls. + * @flags: Flags for the new process as listed above. + * All flags are valid except for CSIGNAL and + * CLONE_DETACHED. + * @pidfd: If CLONE_PIDFD is set, a pidfd will be + * returned in this argument. + * @child_tid: If CLONE_CHILD_SETTID is set, the TID of the + * child process will be returned in the child's + * memory. + * @parent_tid: If CLONE_PARENT_SETTID is set, the TID of + * the child process will be returned in the + * parent's memory. + * @exit_signal: The exit_signal the parent process will be + * sent when the child exits. + * @stack: Specify the location of the stack for the + * child process. + * Note, @stack is expected to point to the + * lowest address. The stack direction will be + * determined by the kernel and set up + * appropriately based on @stack_size. + * @stack_size: The size of the stack for the child process. + * @tls: If CLONE_SETTLS is set, the tls descriptor + * is set to tls. + * @set_tid: Pointer to an array of type *pid_t. The size + * of the array is defined using @set_tid_size. + * This array is used to select PIDs/TIDs for + * newly created processes. The first element in + * this defines the PID in the most nested PID + * namespace. Each additional element in the array + * defines the PID in the parent PID namespace of + * the original PID namespace. If the array has + * less entries than the number of currently + * nested PID namespaces only the PIDs in the + * corresponding namespaces are set. + * @set_tid_size: This defines the size of the array referenced + * in @set_tid. This cannot be larger than the + * kernel's limit of nested PID namespaces. * * The structure is versioned by size and thus extensible. * New struct members must go at the end of the struct and @@ -68,10 +89,13 @@ struct clone_args { __aligned_u64 stack; __aligned_u64 stack_size; __aligned_u64 tls; + __aligned_u64 set_tid; + __aligned_u64 set_tid_size; }; #endif #define CLONE_ARGS_SIZE_VER0 64 /* sizeof first published struct */ +#define CLONE_ARGS_SIZE_VER1 80 /* sizeof second published struct */ /* * Scheduling policies diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h index 7b35e98d3c58..ad80a5c885d5 100644 --- a/tools/include/uapi/linux/stat.h +++ b/tools/include/uapi/linux/stat.h @@ -167,8 +167,8 @@ struct statx { #define STATX_ATTR_APPEND 0x00000020 /* [I] File is append-only */ #define STATX_ATTR_NODUMP 0x00000040 /* [I] File is not to be dumped */ #define STATX_ATTR_ENCRYPTED 0x00000800 /* [I] File requires key to decrypt in fs */ - #define STATX_ATTR_AUTOMOUNT 0x00001000 /* Dir: Automount trigger */ +#define STATX_ATTR_VERITY 0x00100000 /* [I] Verity protected file */ #endif /* _UAPI_LINUX_STAT_H */ diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile index cbb429f55062..c874c017c636 100644 --- a/tools/lib/traceevent/Makefile +++ b/tools/lib/traceevent/Makefile @@ -39,11 +39,12 @@ DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))' LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1) ifeq ($(LP64), 1) - libdir_relative = lib64 + libdir_relative_temp = lib64 else - libdir_relative = lib + libdir_relative_temp = lib endif +libdir_relative ?= $(libdir_relative_temp) prefix ?= /usr/local libdir = $(prefix)/$(libdir_relative) man_dir = $(prefix)/share/man @@ -97,6 +98,7 @@ EVENT_PARSE_VERSION = $(EP_VERSION).$(EP_PATCHLEVEL).$(EP_EXTRAVERSION) LIB_TARGET = libtraceevent.a libtraceevent.so.$(EVENT_PARSE_VERSION) LIB_INSTALL = libtraceevent.a libtraceevent.so* +LIB_INSTALL := $(addprefix $(OUTPUT),$(LIB_INSTALL)) INCLUDES = -I. -I $(srctree)/tools/include $(CONFIG_INCLUDES) @@ -207,10 +209,11 @@ define do_install $(INSTALL) $(if $3,-m $3,) $1 '$(DESTDIR_SQ)$2' endef -PKG_CONFIG_FILE = libtraceevent.pc +PKG_CONFIG_SOURCE_FILE = libtraceevent.pc +PKG_CONFIG_FILE := $(addprefix $(OUTPUT),$(PKG_CONFIG_SOURCE_FILE)) define do_install_pkgconfig_file if [ -n "${pkgconfig_dir}" ]; then \ - cp -f ${PKG_CONFIG_FILE}.template ${PKG_CONFIG_FILE}; \ + cp -f ${PKG_CONFIG_SOURCE_FILE}.template ${PKG_CONFIG_FILE}; \ sed -i "s|INSTALL_PREFIX|${1}|g" ${PKG_CONFIG_FILE}; \ sed -i "s|LIB_VERSION|${EVENT_PARSE_VERSION}|g" ${PKG_CONFIG_FILE}; \ sed -i "s|LIB_DIR|${libdir}|g" ${PKG_CONFIG_FILE}; \ diff --git a/tools/lib/traceevent/plugins/Makefile b/tools/lib/traceevent/plugins/Makefile index f440989fa55e..349bb81482ab 100644 --- a/tools/lib/traceevent/plugins/Makefile +++ b/tools/lib/traceevent/plugins/Makefile @@ -32,11 +32,12 @@ DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))' LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1) ifeq ($(LP64), 1) - libdir_relative = lib64 + libdir_relative_tmp = lib64 else - libdir_relative = lib + libdir_relative_tmp = lib endif +libdir_relative ?= $(libdir_relative_tmp) prefix ?= /usr/local libdir = $(prefix)/$(libdir_relative) diff --git a/tools/perf/Documentation/perf-kvm.txt b/tools/perf/Documentation/perf-kvm.txt index 6a5bb2b17039..cf95baef7b61 100644 --- a/tools/perf/Documentation/perf-kvm.txt +++ b/tools/perf/Documentation/perf-kvm.txt @@ -68,10 +68,11 @@ OPTIONS ------- -i:: --input=<path>:: - Input file name. + Input file name, for the 'report', 'diff' and 'buildid-list' subcommands. -o:: --output=<path>:: - Output file name. + Output file name, for the 'record' subcommand. Doesn't work with 'report', + just redirect the output to a file when using 'report'. --host:: Collect host side performance profile. --guest:: diff --git a/tools/perf/arch/arm/tests/regs_load.S b/tools/perf/arch/arm/tests/regs_load.S index 6e2495cc4517..4284307d7822 100644 --- a/tools/perf/arch/arm/tests/regs_load.S +++ b/tools/perf/arch/arm/tests/regs_load.S @@ -37,7 +37,7 @@ .text .type perf_regs_load,%function -ENTRY(perf_regs_load) +SYM_FUNC_START(perf_regs_load) str r0, [r0, #R0] str r1, [r0, #R1] str r2, [r0, #R2] @@ -56,4 +56,4 @@ ENTRY(perf_regs_load) str lr, [r0, #PC] // store pc as lr in order to skip the call // to this function mov pc, lr -ENDPROC(perf_regs_load) +SYM_FUNC_END(perf_regs_load) diff --git a/tools/perf/arch/arm64/tests/regs_load.S b/tools/perf/arch/arm64/tests/regs_load.S index 07042511dca9..d49de40b6818 100644 --- a/tools/perf/arch/arm64/tests/regs_load.S +++ b/tools/perf/arch/arm64/tests/regs_load.S @@ -7,7 +7,7 @@ #define LDR_REG(r) ldr x##r, [x0, 8 * r] #define SP (8 * 31) #define PC (8 * 32) -ENTRY(perf_regs_load) +SYM_FUNC_START(perf_regs_load) STR_REG(0) STR_REG(1) STR_REG(2) @@ -44,4 +44,4 @@ ENTRY(perf_regs_load) str x30, [x0, #PC] LDR_REG(1) ret -ENDPROC(perf_regs_load) +SYM_FUNC_END(perf_regs_load) diff --git a/tools/perf/arch/x86/tests/regs_load.S b/tools/perf/arch/x86/tests/regs_load.S index bbe5a0d16e51..80f14f52e3f6 100644 --- a/tools/perf/arch/x86/tests/regs_load.S +++ b/tools/perf/arch/x86/tests/regs_load.S @@ -28,7 +28,7 @@ .text #ifdef HAVE_ARCH_X86_64_SUPPORT -ENTRY(perf_regs_load) +SYM_FUNC_START(perf_regs_load) movq %rax, AX(%rdi) movq %rbx, BX(%rdi) movq %rcx, CX(%rdi) @@ -60,9 +60,9 @@ ENTRY(perf_regs_load) movq %r14, R14(%rdi) movq %r15, R15(%rdi) ret -ENDPROC(perf_regs_load) +SYM_FUNC_END(perf_regs_load) #else -ENTRY(perf_regs_load) +SYM_FUNC_START(perf_regs_load) push %edi movl 8(%esp), %edi movl %eax, AX(%edi) @@ -88,7 +88,7 @@ ENTRY(perf_regs_load) movl $0, FS(%edi) movl $0, GS(%edi) ret -ENDPROC(perf_regs_load) +SYM_FUNC_END(perf_regs_load) #endif /* diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 9664a72a089d..7e124a7b8bfd 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -403,17 +403,6 @@ static int perf_event__repipe_tracing_data(struct perf_session *session, return err; } -static int perf_event__repipe_id_index(struct perf_session *session, - union perf_event *event) -{ - int err; - - perf_event__repipe_synth(session->tool, event); - err = perf_event__process_id_index(session, event); - - return err; -} - static int dso__read_build_id(struct dso *dso) { if (dso->has_build_id) @@ -651,7 +640,7 @@ static int __cmd_inject(struct perf_inject *inject) inject->tool.comm = perf_event__repipe_comm; inject->tool.namespaces = perf_event__repipe_namespaces; inject->tool.exit = perf_event__repipe_exit; - inject->tool.id_index = perf_event__repipe_id_index; + inject->tool.id_index = perf_event__process_id_index; inject->tool.auxtrace_info = perf_event__process_auxtrace_info; inject->tool.auxtrace = perf_event__process_auxtrace; inject->tool.aux = perf_event__drop_aux; diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index b5063d3b6fd0..fb19ef63cc35 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -832,7 +832,7 @@ try_again: if ((errno == EINVAL || errno == EBADF) && pos->leader != pos && pos->weak_group) { - pos = perf_evlist__reset_weak_group(evlist, pos); + pos = perf_evlist__reset_weak_group(evlist, pos, true); goto try_again; } rc = -errno; diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 830d563de889..387311c67264 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -388,6 +388,14 @@ static int report__setup_sample_type(struct report *rep) } } + if (sort__mode == SORT_MODE__MEMORY) { + if (!is_pipe && !(sample_type & PERF_SAMPLE_DATA_SRC)) { + ui__error("Selected --mem-mode but no mem data. " + "Did you call perf record without -d?\n"); + return -1; + } + } + if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain) { if ((sample_type & PERF_SAMPLE_REGS_USER) && (sample_type & PERF_SAMPLE_STACK_USER)) { diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 0a15253b438c..a098c2ebf4ea 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -65,6 +65,7 @@ #include "util/target.h" #include "util/time-utils.h" #include "util/top.h" +#include "util/affinity.h" #include "asm/bug.h" #include <linux/time64.h> @@ -265,15 +266,10 @@ static int read_single_counter(struct evsel *counter, int cpu, * Read out the results of a single counter: * do not aggregate counts across CPUs in system-wide mode */ -static int read_counter(struct evsel *counter, struct timespec *rs) +static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu) { int nthreads = perf_thread_map__nr(evsel_list->core.threads); - int ncpus, cpu, thread; - - if (target__has_cpu(&target) && !target__has_per_thread(&target)) - ncpus = perf_evsel__nr_cpus(counter); - else - ncpus = 1; + int thread; if (!counter->supported) return -ENOENT; @@ -282,40 +278,38 @@ static int read_counter(struct evsel *counter, struct timespec *rs) nthreads = 1; for (thread = 0; thread < nthreads; thread++) { - for (cpu = 0; cpu < ncpus; cpu++) { - struct perf_counts_values *count; - - count = perf_counts(counter->counts, cpu, thread); - - /* - * The leader's group read loads data into its group members - * (via perf_evsel__read_counter) and sets threir count->loaded. - */ - if (!perf_counts__is_loaded(counter->counts, cpu, thread) && - read_single_counter(counter, cpu, thread, rs)) { - counter->counts->scaled = -1; - perf_counts(counter->counts, cpu, thread)->ena = 0; - perf_counts(counter->counts, cpu, thread)->run = 0; - return -1; - } + struct perf_counts_values *count; - perf_counts__set_loaded(counter->counts, cpu, thread, false); + count = perf_counts(counter->counts, cpu, thread); - if (STAT_RECORD) { - if (perf_evsel__write_stat_event(counter, cpu, thread, count)) { - pr_err("failed to write stat event\n"); - return -1; - } - } + /* + * The leader's group read loads data into its group members + * (via perf_evsel__read_counter()) and sets their count->loaded. + */ + if (!perf_counts__is_loaded(counter->counts, cpu, thread) && + read_single_counter(counter, cpu, thread, rs)) { + counter->counts->scaled = -1; + perf_counts(counter->counts, cpu, thread)->ena = 0; + perf_counts(counter->counts, cpu, thread)->run = 0; + return -1; + } + + perf_counts__set_loaded(counter->counts, cpu, thread, false); - if (verbose > 1) { - fprintf(stat_config.output, - "%s: %d: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n", - perf_evsel__name(counter), - cpu, - count->val, count->ena, count->run); + if (STAT_RECORD) { + if (perf_evsel__write_stat_event(counter, cpu, thread, count)) { + pr_err("failed to write stat event\n"); + return -1; } } + + if (verbose > 1) { + fprintf(stat_config.output, + "%s: %d: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n", + perf_evsel__name(counter), + cpu, + count->val, count->ena, count->run); + } } return 0; @@ -324,15 +318,37 @@ static int read_counter(struct evsel *counter, struct timespec *rs) static void read_counters(struct timespec *rs) { struct evsel *counter; - int ret; + struct affinity affinity; + int i, ncpus, cpu; + + if (affinity__setup(&affinity) < 0) + return; + + ncpus = perf_cpu_map__nr(evsel_list->core.all_cpus); + if (!target__has_cpu(&target) || target__has_per_thread(&target)) + ncpus = 1; + evlist__for_each_cpu(evsel_list, i, cpu) { + if (i >= ncpus) + break; + affinity__set(&affinity, cpu); + + evlist__for_each_entry(evsel_list, counter) { + if (evsel__cpu_iter_skip(counter, cpu)) + continue; + if (!counter->err) { + counter->err = read_counter_cpu(counter, rs, + counter->cpu_iter - 1); + } + } + } + affinity__cleanup(&affinity); evlist__for_each_entry(evsel_list, counter) { - ret = read_counter(counter, rs); - if (ret) + if (counter->err) pr_debug("failed to read counter %s\n", counter->name); - - if (ret == 0 && perf_stat_process_counter(&stat_config, counter)) + if (counter->err == 0 && perf_stat_process_counter(&stat_config, counter)) pr_warning("failed to process counter %s\n", counter->name); + counter->err = 0; } } @@ -420,6 +436,62 @@ static bool is_target_alive(struct target *_target, return false; } +enum counter_recovery { + COUNTER_SKIP, + COUNTER_RETRY, + COUNTER_FATAL, +}; + +static enum counter_recovery stat_handle_error(struct evsel *counter) +{ + char msg[BUFSIZ]; + /* + * PPC returns ENXIO for HW counters until 2.6.37 + * (behavior changed with commit b0a873e). + */ + if (errno == EINVAL || errno == ENOSYS || + errno == ENOENT || errno == EOPNOTSUPP || + errno == ENXIO) { + if (verbose > 0) + ui__warning("%s event is not supported by the kernel.\n", + perf_evsel__name(counter)); + counter->supported = false; + /* + * errored is a sticky flag that means one of the counter's + * cpu event had a problem and needs to be reexamined. + */ + counter->errored = true; + + if ((counter->leader != counter) || + !(counter->leader->core.nr_members > 1)) + return COUNTER_SKIP; + } else if (perf_evsel__fallback(counter, errno, msg, sizeof(msg))) { + if (verbose > 0) + ui__warning("%s\n", msg); + return COUNTER_RETRY; + } else if (target__has_per_thread(&target) && + evsel_list->core.threads && + evsel_list->core.threads->err_thread != -1) { + /* + * For global --per-thread case, skip current + * error thread. + */ + if (!thread_map__remove(evsel_list->core.threads, + evsel_list->core.threads->err_thread)) { + evsel_list->core.threads->err_thread = -1; + return COUNTER_RETRY; + } + } + + perf_evsel__open_strerror(counter, &target, + errno, msg, sizeof(msg)); + ui__error("%s\n", msg); + + if (child_pid != -1) + kill(child_pid, SIGTERM); + return COUNTER_FATAL; +} + static int __run_perf_stat(int argc, const char **argv, int run_idx) { int interval = stat_config.interval; @@ -433,6 +505,9 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx) int status = 0; const bool forks = (argc > 0); bool is_pipe = STAT_RECORD ? perf_stat.data.is_pipe : false; + struct affinity affinity; + int i, cpu; + bool second_pass = false; if (interval) { ts.tv_sec = interval / USEC_PER_MSEC; @@ -457,61 +532,104 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx) if (group) perf_evlist__set_leader(evsel_list); - evlist__for_each_entry(evsel_list, counter) { + if (affinity__setup(&affinity) < 0) + return -1; + + evlist__for_each_cpu (evsel_list, i, cpu) { + affinity__set(&affinity, cpu); + + evlist__for_each_entry(evsel_list, counter) { + if (evsel__cpu_iter_skip(counter, cpu)) + continue; + if (counter->reset_group || counter->errored) + continue; try_again: - if (create_perf_stat_counter(counter, &stat_config, &target) < 0) { - - /* Weak group failed. Reset the group. */ - if ((errno == EINVAL || errno == EBADF) && - counter->leader != counter && - counter->weak_group) { - counter = perf_evlist__reset_weak_group(evsel_list, counter); - goto try_again; - } + if (create_perf_stat_counter(counter, &stat_config, &target, + counter->cpu_iter - 1) < 0) { - /* - * PPC returns ENXIO for HW counters until 2.6.37 - * (behavior changed with commit b0a873e). - */ - if (errno == EINVAL || errno == ENOSYS || - errno == ENOENT || errno == EOPNOTSUPP || - errno == ENXIO) { - if (verbose > 0) - ui__warning("%s event is not supported by the kernel.\n", - perf_evsel__name(counter)); - counter->supported = false; - - if ((counter->leader != counter) || - !(counter->leader->core.nr_members > 1)) - continue; - } else if (perf_evsel__fallback(counter, errno, msg, sizeof(msg))) { - if (verbose > 0) - ui__warning("%s\n", msg); - goto try_again; - } else if (target__has_per_thread(&target) && - evsel_list->core.threads && - evsel_list->core.threads->err_thread != -1) { /* - * For global --per-thread case, skip current - * error thread. + * Weak group failed. We cannot just undo this here + * because earlier CPUs might be in group mode, and the kernel + * doesn't support mixing group and non group reads. Defer + * it to later. + * Don't close here because we're in the wrong affinity. */ - if (!thread_map__remove(evsel_list->core.threads, - evsel_list->core.threads->err_thread)) { - evsel_list->core.threads->err_thread = -1; + if ((errno == EINVAL || errno == EBADF) && + counter->leader != counter && + counter->weak_group) { + perf_evlist__reset_weak_group(evsel_list, counter, false); + assert(counter->reset_group); + second_pass = true; + continue; + } + + switch (stat_handle_error(counter)) { + case COUNTER_FATAL: + return -1; + case COUNTER_RETRY: goto try_again; + case COUNTER_SKIP: + continue; + default: + break; } + } + counter->supported = true; + } + } - perf_evsel__open_strerror(counter, &target, - errno, msg, sizeof(msg)); - ui__error("%s\n", msg); + if (second_pass) { + /* + * Now redo all the weak group after closing them, + * and also close errored counters. + */ - if (child_pid != -1) - kill(child_pid, SIGTERM); + evlist__for_each_cpu(evsel_list, i, cpu) { + affinity__set(&affinity, cpu); + /* First close errored or weak retry */ + evlist__for_each_entry(evsel_list, counter) { + if (!counter->reset_group && !counter->errored) + continue; + if (evsel__cpu_iter_skip_no_inc(counter, cpu)) + continue; + perf_evsel__close_cpu(&counter->core, counter->cpu_iter); + } + /* Now reopen weak */ + evlist__for_each_entry(evsel_list, counter) { + if (!counter->reset_group && !counter->errored) + continue; + if (evsel__cpu_iter_skip(counter, cpu)) + continue; + if (!counter->reset_group) + continue; +try_again_reset: + pr_debug2("reopening weak %s\n", perf_evsel__name(counter)); + if (create_perf_stat_counter(counter, &stat_config, &target, + counter->cpu_iter - 1) < 0) { + + switch (stat_handle_error(counter)) { + case COUNTER_FATAL: + return -1; + case COUNTER_RETRY: + goto try_again_reset; + case COUNTER_SKIP: + continue; + default: + break; + } + } + counter->supported = true; + } + } + } + affinity__cleanup(&affinity); - return -1; + evlist__for_each_entry(evsel_list, counter) { + if (!counter->supported) { + perf_evsel__free_fd(&counter->core); + continue; } - counter->supported = true; l = strlen(counter->unit); if (l > stat_config.unit_width) diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index dc80044bc46f..795e353de095 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1568,9 +1568,13 @@ int cmd_top(int argc, const char **argv) */ status = perf_env__read_cpuid(&perf_env); if (status) { - pr_err("Couldn't read the cpuid for this machine: %s\n", - str_error_r(errno, errbuf, sizeof(errbuf))); - goto out_delete_evlist; + /* + * Some arches do not provide a get_cpuid(), so just use pr_debug, otherwise + * warn the user explicitely. + */ + eprintf(status == ENOSYS ? 1 : 0, verbose, + "Couldn't read the cpuid for this machine: %s\n", + str_error_r(errno, errbuf, sizeof(errbuf))); } top.evlist->env = &perf_env; diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index a1dc16724352..68039a96c1dc 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -110,8 +110,8 @@ for i in $FILES; do done # diff with extra ignore lines -check arch/x86/lib/memcpy_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"' -check arch/x86/lib/memset_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"' +check arch/x86/lib/memcpy_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memcpy_\(erms\|orig\))"' +check arch/x86/lib/memset_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memset_\(erms\|orig\))"' check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common\(-tools\)*.h>"' check include/uapi/linux/mman.h '-I "^#include <\(uapi/\)*asm/mman.h>"' check include/linux/ctype.h '-I "isdigit("' diff --git a/tools/perf/lib/cpumap.c b/tools/perf/lib/cpumap.c index 2ca1fafa620d..f93f4e703e4c 100644 --- a/tools/perf/lib/cpumap.c +++ b/tools/perf/lib/cpumap.c @@ -68,14 +68,28 @@ static struct perf_cpu_map *cpu_map__default_new(void) return cpus; } +static int cmp_int(const void *a, const void *b) +{ + return *(const int *)a - *(const int*)b; +} + static struct perf_cpu_map *cpu_map__trim_new(int nr_cpus, int *tmp_cpus) { size_t payload_size = nr_cpus * sizeof(int); struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + payload_size); + int i, j; if (cpus != NULL) { - cpus->nr = nr_cpus; memcpy(cpus->map, tmp_cpus, payload_size); + qsort(cpus->map, nr_cpus, sizeof(int), cmp_int); + /* Remove dups */ + j = 0; + for (i = 0; i < nr_cpus; i++) { + if (i == 0 || cpus->map[i] != cpus->map[i - 1]) + cpus->map[j++] = cpus->map[i]; + } + cpus->nr = j; + assert(j <= nr_cpus); refcount_set(&cpus->refcnt, 1); } @@ -272,3 +286,60 @@ int perf_cpu_map__max(struct perf_cpu_map *map) return max; } + +/* + * Merge two cpumaps + * + * orig either gets freed and replaced with a new map, or reused + * with no reference count change (similar to "realloc") + * other has its reference count increased. + */ + +struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig, + struct perf_cpu_map *other) +{ + int *tmp_cpus; + int tmp_len; + int i, j, k; + struct perf_cpu_map *merged; + + if (!orig && !other) + return NULL; + if (!orig) { + perf_cpu_map__get(other); + return other; + } + if (!other) + return orig; + if (orig->nr == other->nr && + !memcmp(orig->map, other->map, orig->nr * sizeof(int))) + return orig; + + tmp_len = orig->nr + other->nr; + tmp_cpus = malloc(tmp_len * sizeof(int)); + if (!tmp_cpus) + return NULL; + + /* Standard merge algorithm from wikipedia */ + i = j = k = 0; + while (i < orig->nr && j < other->nr) { + if (orig->map[i] <= other->map[j]) { + if (orig->map[i] == other->map[j]) + j++; + tmp_cpus[k++] = orig->map[i++]; + } else + tmp_cpus[k++] = other->map[j++]; + } + + while (i < orig->nr) + tmp_cpus[k++] = orig->map[i++]; + + while (j < other->nr) + tmp_cpus[k++] = other->map[j++]; + assert(k <= tmp_len); + + merged = cpu_map__trim_new(k, tmp_cpus); + free(tmp_cpus); + perf_cpu_map__put(orig); + return merged; +} diff --git a/tools/perf/lib/evlist.c b/tools/perf/lib/evlist.c index 205ddbb80bc1..ae9e65aa2491 100644 --- a/tools/perf/lib/evlist.c +++ b/tools/perf/lib/evlist.c @@ -54,6 +54,7 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist, perf_thread_map__put(evsel->threads); evsel->threads = perf_thread_map__get(evlist->threads); + evlist->all_cpus = perf_cpu_map__merge(evlist->all_cpus, evsel->cpus); } static void perf_evlist__propagate_maps(struct perf_evlist *evlist) diff --git a/tools/perf/lib/evsel.c b/tools/perf/lib/evsel.c index 5a89857b0381..4dc06289f4c7 100644 --- a/tools/perf/lib/evsel.c +++ b/tools/perf/lib/evsel.c @@ -114,16 +114,23 @@ int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus, return err; } +static void perf_evsel__close_fd_cpu(struct perf_evsel *evsel, int cpu) +{ + int thread; + + for (thread = 0; thread < xyarray__max_y(evsel->fd); ++thread) { + if (FD(evsel, cpu, thread) >= 0) + close(FD(evsel, cpu, thread)); + FD(evsel, cpu, thread) = -1; + } +} + void perf_evsel__close_fd(struct perf_evsel *evsel) { - int cpu, thread; + int cpu; for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) - for (thread = 0; thread < xyarray__max_y(evsel->fd); ++thread) { - if (FD(evsel, cpu, thread) >= 0) - close(FD(evsel, cpu, thread)); - FD(evsel, cpu, thread) = -1; - } + perf_evsel__close_fd_cpu(evsel, cpu); } void perf_evsel__free_fd(struct perf_evsel *evsel) @@ -141,6 +148,14 @@ void perf_evsel__close(struct perf_evsel *evsel) perf_evsel__free_fd(evsel); } +void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu) +{ + if (evsel->fd == NULL) + return; + + perf_evsel__close_fd_cpu(evsel, cpu); +} + int perf_evsel__read_size(struct perf_evsel *evsel) { u64 read_format = evsel->attr.read_format; @@ -183,38 +198,61 @@ int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread, } static int perf_evsel__run_ioctl(struct perf_evsel *evsel, - int ioc, void *arg) + int ioc, void *arg, + int cpu) { - int cpu, thread; + int thread; - for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) { - for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) { - int fd = FD(evsel, cpu, thread), - err = ioctl(fd, ioc, arg); + for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) { + int fd = FD(evsel, cpu, thread), + err = ioctl(fd, ioc, arg); - if (err) - return err; - } + if (err) + return err; } return 0; } +int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu) +{ + return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, NULL, cpu); +} + int perf_evsel__enable(struct perf_evsel *evsel) { - return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, 0); + int i; + int err = 0; + + for (i = 0; i < xyarray__max_x(evsel->fd) && !err; i++) + err = perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, NULL, i); + return err; +} + +int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu) +{ + return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, NULL, cpu); } int perf_evsel__disable(struct perf_evsel *evsel) { - return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, 0); + int i; + int err = 0; + + for (i = 0; i < xyarray__max_x(evsel->fd) && !err; i++) + err = perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, NULL, i); + return err; } int perf_evsel__apply_filter(struct perf_evsel *evsel, const char *filter) { - return perf_evsel__run_ioctl(evsel, + int err = 0, i; + + for (i = 0; i < evsel->cpus->nr && !err; i++) + err = perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_SET_FILTER, - (void *)filter); + (void *)filter, i); + return err; } struct perf_cpu_map *perf_evsel__cpus(struct perf_evsel *evsel) diff --git a/tools/perf/lib/include/internal/evlist.h b/tools/perf/lib/include/internal/evlist.h index a2fbccf1922f..74dc8c3f0b66 100644 --- a/tools/perf/lib/include/internal/evlist.h +++ b/tools/perf/lib/include/internal/evlist.h @@ -18,6 +18,7 @@ struct perf_evlist { int nr_entries; bool has_user_cpus; struct perf_cpu_map *cpus; + struct perf_cpu_map *all_cpus; struct perf_thread_map *threads; int nr_mmaps; size_t mmap_len; diff --git a/tools/perf/lib/include/perf/cpumap.h b/tools/perf/lib/include/perf/cpumap.h index ac9aa497f84a..6a17ad730cbc 100644 --- a/tools/perf/lib/include/perf/cpumap.h +++ b/tools/perf/lib/include/perf/cpumap.h @@ -12,6 +12,8 @@ LIBPERF_API struct perf_cpu_map *perf_cpu_map__dummy_new(void); LIBPERF_API struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list); LIBPERF_API struct perf_cpu_map *perf_cpu_map__read(FILE *file); LIBPERF_API struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map); +LIBPERF_API struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig, + struct perf_cpu_map *other); LIBPERF_API void perf_cpu_map__put(struct perf_cpu_map *map); LIBPERF_API int perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx); LIBPERF_API int perf_cpu_map__nr(const struct perf_cpu_map *cpus); diff --git a/tools/perf/lib/include/perf/evsel.h b/tools/perf/lib/include/perf/evsel.h index 557f5815a9c9..c82ec39a4ad0 100644 --- a/tools/perf/lib/include/perf/evsel.h +++ b/tools/perf/lib/include/perf/evsel.h @@ -26,10 +26,13 @@ LIBPERF_API void perf_evsel__delete(struct perf_evsel *evsel); LIBPERF_API int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus, struct perf_thread_map *threads); LIBPERF_API void perf_evsel__close(struct perf_evsel *evsel); +LIBPERF_API void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu); LIBPERF_API int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread, struct perf_counts_values *count); LIBPERF_API int perf_evsel__enable(struct perf_evsel *evsel); +LIBPERF_API int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu); LIBPERF_API int perf_evsel__disable(struct perf_evsel *evsel); +LIBPERF_API int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu); LIBPERF_API struct perf_cpu_map *perf_evsel__cpus(struct perf_evsel *evsel); LIBPERF_API struct perf_thread_map *perf_evsel__threads(struct perf_evsel *evsel); LIBPERF_API struct perf_event_attr *perf_evsel__attr(struct perf_evsel *evsel); diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/extended.json b/tools/perf/pmu-events/arch/s390/cf_z13/extended.json index 436ce33f1182..5da8296b667e 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z13/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_z13/extended.json @@ -32,7 +32,7 @@ "EventCode": "132", "EventName": "DTLB1_GPAGE_WRITES", "BriefDescription": "DTLB1 Two-Gigabyte Page Writes", - "PublicDescription": "Counter:132 Name:DTLB1_GPAGE_WRITES A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a two-gigabyte page." + "PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a two-gigabyte page." }, { "Unit": "CPU-M-CF", diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json index 68618152ea2c..89e070727e1b 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json @@ -4,7 +4,7 @@ "EventCode": "128", "EventName": "L1D_RO_EXCL_WRITES", "BriefDescription": "L1D Read-only Exclusive Writes", - "PublicDescription": "L1D_RO_EXCL_WRITES A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line" + "PublicDescription": "A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line" }, { "Unit": "CPU-M-CF", diff --git a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json index bc7151d639d7..45a34ce4fe89 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json @@ -297,7 +297,7 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json index 49c5f123d811..961fe4395758 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json @@ -115,7 +115,7 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json index 113d19e92678..746734ce09be 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json @@ -297,7 +297,7 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, 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 2ba32af9bc36..f94653229dd4 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json @@ -315,7 +315,7 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, diff --git a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json index c80f16fde6d0..5402cd3120f9 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json +++ b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json @@ -267,7 +267,7 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, diff --git a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json index e501729c3dd1..832f3cb40b34 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json @@ -267,7 +267,7 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json index e2446966b651..d69b2a8fc0bc 100644 --- a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json +++ b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json @@ -285,7 +285,7 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, diff --git a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json index 9294769dec64..5f465fd81315 100644 --- a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json +++ b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json @@ -285,7 +285,7 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, diff --git a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json index 603ff9c2e9a1..3e909b306003 100644 --- a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json +++ b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json @@ -171,7 +171,7 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json index c6b485b3a2cb..50c053235752 100644 --- a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json +++ b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json @@ -171,7 +171,7 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, diff --git a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json index 0ca539bb60f6..e7feb60f9fa9 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json @@ -303,7 +303,7 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, 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 047d7e11aa6f..21d7a0c2c2e8 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json @@ -315,7 +315,7 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build index a3c595fba943..1692529639b0 100644 --- a/tools/perf/tests/Build +++ b/tools/perf/tests/Build @@ -54,6 +54,7 @@ perf-y += unit_number__scnprintf.o perf-y += mem2node.o perf-y += maps.o perf-y += time-utils-test.o +perf-y += genelf.o $(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build $(call rule_mkdir) diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index 7115aa32a51e..5f05db75cdd8 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -260,6 +260,11 @@ static struct test generic_tests[] = { .func = test__cpu_map_print, }, { + .desc = "Merge cpu map", + .func = test__cpu_map_merge, + }, + + { .desc = "Probe SDT events", .func = test__sdt_event, }, @@ -297,6 +302,10 @@ static struct test generic_tests[] = { .func = test__time_utils, }, { + .desc = "Test jit_write_elf", + .func = test__jit_write_elf, + }, + { .desc = "maps__merge_in", .func = test__maps__merge_in, }, diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c index 8a0d236202b0..4ac56741ac5f 100644 --- a/tools/perf/tests/cpumap.c +++ b/tools/perf/tests/cpumap.c @@ -120,3 +120,19 @@ int test__cpu_map_print(struct test *test __maybe_unused, int subtest __maybe_un TEST_ASSERT_VAL("failed to convert map", cpu_map_print("1-10,12-20,22-30,32-40")); return 0; } + +int test__cpu_map_merge(struct test *test __maybe_unused, int subtest __maybe_unused) +{ + struct perf_cpu_map *a = perf_cpu_map__new("4,2,1"); + struct perf_cpu_map *b = perf_cpu_map__new("4,5,7"); + struct perf_cpu_map *c = perf_cpu_map__merge(a, b); + char buf[100]; + + TEST_ASSERT_VAL("failed to merge map: bad nr", c->nr == 5); + cpu_map__snprint(c, buf, sizeof(buf)); + TEST_ASSERT_VAL("failed to merge map: bad result", !strcmp(buf, "1-2,4-5,7")); + perf_cpu_map__put(a); + perf_cpu_map__put(b); + perf_cpu_map__put(c); + return 0; +} diff --git a/tools/perf/tests/event-times.c b/tools/perf/tests/event-times.c index 1ee8704e2284..1e8a9f5c356d 100644 --- a/tools/perf/tests/event-times.c +++ b/tools/perf/tests/event-times.c @@ -125,7 +125,7 @@ static int attach__cpu_disabled(struct evlist *evlist) evsel->core.attr.disabled = 1; - err = perf_evsel__open_per_cpu(evsel, cpus); + err = perf_evsel__open_per_cpu(evsel, cpus, -1); if (err) { if (err == -EACCES) return TEST_SKIP; @@ -152,7 +152,7 @@ static int attach__cpu_enabled(struct evlist *evlist) return -1; } - err = perf_evsel__open_per_cpu(evsel, cpus); + err = perf_evsel__open_per_cpu(evsel, cpus, -1); if (err == -EACCES) return TEST_SKIP; diff --git a/tools/perf/tests/genelf.c b/tools/perf/tests/genelf.c new file mode 100644 index 000000000000..f797f9823e89 --- /dev/null +++ b/tools/perf/tests/genelf.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <limits.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <linux/compiler.h> + +#include "debug.h" +#include "tests.h" + +#ifdef HAVE_JITDUMP +#include <libelf.h> +#include "../util/genelf.h" +#endif + +#define TEMPL "/tmp/perf-test-XXXXXX" + +int test__jit_write_elf(struct test *test __maybe_unused, + int subtest __maybe_unused) +{ +#ifdef HAVE_JITDUMP + static unsigned char x86_code[] = { + 0xBB, 0x2A, 0x00, 0x00, 0x00, /* movl $42, %ebx */ + 0xB8, 0x01, 0x00, 0x00, 0x00, /* movl $1, %eax */ + 0xCD, 0x80 /* int $0x80 */ + }; + char path[PATH_MAX]; + int fd, ret; + + strcpy(path, TEMPL); + + fd = mkstemp(path); + if (fd < 0) { + perror("mkstemp failed"); + return TEST_FAIL; + } + + pr_info("Writing jit code to: %s\n", path); + + ret = jit_write_elf(fd, 0, "main", x86_code, sizeof(x86_code), + NULL, 0, NULL, 0, 0); + close(fd); + + unlink(path); + + return ret ? TEST_FAIL : 0; +#else + return TEST_SKIP; +#endif +} diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index 25aea387e2bf..9a160fef47c9 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -98,6 +98,7 @@ int test__event_update(struct test *test, int subtest); int test__event_times(struct test *test, int subtest); int test__backward_ring_buffer(struct test *test, int subtest); int test__cpu_map_print(struct test *test, int subtest); +int test__cpu_map_merge(struct test *test, int subtest); int test__sdt_event(struct test *test, int subtest); int test__is_printable_array(struct test *test, int subtest); int test__bitmap_print(struct test *test, int subtest); @@ -109,6 +110,7 @@ int test__unit_number__scnprint(struct test *test, int subtest); int test__mem2node(struct test *t, int subtest); int test__maps__merge_in(struct test *t, int subtest); int test__time_utils(struct test *t, int subtest); +int test__jit_write_elf(struct test *test, int subtest); bool test__bp_signal_is_supported(void); bool test__bp_account_is_supported(void); diff --git a/tools/perf/trace/beauty/clone.c b/tools/perf/trace/beauty/clone.c index 1a8d3be2030e..062ca849c8fd 100644 --- a/tools/perf/trace/beauty/clone.c +++ b/tools/perf/trace/beauty/clone.c @@ -45,6 +45,7 @@ static size_t clone__scnprintf_flags(unsigned long flags, char *bf, size_t size, P_FLAG(NEWPID); P_FLAG(NEWNET); P_FLAG(IO); + P_FLAG(CLEAR_SIGHAND); #undef P_FLAG if (flags) diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h index 57943f3685f8..3a442f021468 100644 --- a/tools/perf/util/cpumap.h +++ b/tools/perf/util/cpumap.h @@ -63,4 +63,5 @@ int cpu_map__build_map(struct perf_cpu_map *cpus, struct perf_cpu_map **res, int cpu_map__cpu(struct perf_cpu_map *cpus, int idx); bool cpu_map__has(struct perf_cpu_map *cpus, int cpu); + #endif /* __PERF_CPUMAP_H */ diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index fdce590d2278..1548237b6558 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -18,6 +18,7 @@ #include "debug.h" #include "units.h" #include <internal/lib.h> // page_size +#include "affinity.h" #include "../perf.h" #include "asm/bug.h" #include "bpf-event.h" @@ -342,14 +343,63 @@ static int perf_evlist__nr_threads(struct evlist *evlist, return perf_thread_map__nr(evlist->core.threads); } +void evlist__cpu_iter_start(struct evlist *evlist) +{ + struct evsel *pos; + + /* + * Reset the per evsel cpu_iter. This is needed because + * each evsel's cpumap may have a different index space, + * and some operations need the index to modify + * the FD xyarray (e.g. open, close) + */ + evlist__for_each_entry(evlist, pos) + pos->cpu_iter = 0; +} + +bool evsel__cpu_iter_skip_no_inc(struct evsel *ev, int cpu) +{ + if (ev->cpu_iter >= ev->core.cpus->nr) + return true; + if (cpu >= 0 && ev->core.cpus->map[ev->cpu_iter] != cpu) + return true; + return false; +} + +bool evsel__cpu_iter_skip(struct evsel *ev, int cpu) +{ + if (!evsel__cpu_iter_skip_no_inc(ev, cpu)) { + ev->cpu_iter++; + return false; + } + return true; +} + void evlist__disable(struct evlist *evlist) { struct evsel *pos; + struct affinity affinity; + int cpu, i; + + if (affinity__setup(&affinity) < 0) + return; + evlist__for_each_cpu(evlist, i, cpu) { + affinity__set(&affinity, cpu); + + evlist__for_each_entry(evlist, pos) { + if (evsel__cpu_iter_skip(pos, cpu)) + continue; + if (pos->disabled || !perf_evsel__is_group_leader(pos) || !pos->core.fd) + continue; + evsel__disable_cpu(pos, pos->cpu_iter - 1); + } + } + affinity__cleanup(&affinity); evlist__for_each_entry(evlist, pos) { - if (pos->disabled || !perf_evsel__is_group_leader(pos) || !pos->core.fd) + if (!perf_evsel__is_group_leader(pos) || !pos->core.fd) continue; - evsel__disable(pos); + pos->disabled = true; } evlist->enabled = false; @@ -358,11 +408,28 @@ void evlist__disable(struct evlist *evlist) void evlist__enable(struct evlist *evlist) { struct evsel *pos; + struct affinity affinity; + int cpu, i; + + if (affinity__setup(&affinity) < 0) + return; + evlist__for_each_cpu(evlist, i, cpu) { + affinity__set(&affinity, cpu); + + evlist__for_each_entry(evlist, pos) { + if (evsel__cpu_iter_skip(pos, cpu)) + continue; + if (!perf_evsel__is_group_leader(pos) || !pos->core.fd) + continue; + evsel__enable_cpu(pos, pos->cpu_iter - 1); + } + } + affinity__cleanup(&affinity); evlist__for_each_entry(evlist, pos) { if (!perf_evsel__is_group_leader(pos) || !pos->core.fd) continue; - evsel__enable(pos); + pos->disabled = false; } evlist->enabled = true; @@ -1137,9 +1204,35 @@ void perf_evlist__set_selected(struct evlist *evlist, void evlist__close(struct evlist *evlist) { struct evsel *evsel; + struct affinity affinity; + int cpu, i; - evlist__for_each_entry_reverse(evlist, evsel) - evsel__close(evsel); + /* + * With perf record core.cpus is usually NULL. + * Use the old method to handle this for now. + */ + if (!evlist->core.cpus) { + evlist__for_each_entry_reverse(evlist, evsel) + evsel__close(evsel); + return; + } + + if (affinity__setup(&affinity) < 0) + return; + evlist__for_each_cpu(evlist, i, cpu) { + affinity__set(&affinity, cpu); + + evlist__for_each_entry_reverse(evlist, evsel) { + if (evsel__cpu_iter_skip(evsel, cpu)) + continue; + perf_evsel__close_cpu(&evsel->core, evsel->cpu_iter - 1); + } + } + affinity__cleanup(&affinity); + evlist__for_each_entry_reverse(evlist, evsel) { + perf_evsel__free_fd(&evsel->core); + perf_evsel__free_id(&evsel->core); + } } static int perf_evlist__create_syswide_maps(struct evlist *evlist) @@ -1577,7 +1670,8 @@ void perf_evlist__force_leader(struct evlist *evlist) } struct evsel *perf_evlist__reset_weak_group(struct evlist *evsel_list, - struct evsel *evsel) + struct evsel *evsel, + bool close) { struct evsel *c2, *leader; bool is_open = true; @@ -1594,10 +1688,15 @@ struct evsel *perf_evlist__reset_weak_group(struct evlist *evsel_list, if (c2 == evsel) is_open = false; if (c2->leader == leader) { - if (is_open) + if (is_open && close) perf_evsel__close(&c2->core); c2->leader = c2; c2->core.nr_members = 0; + /* + * Set this for all former members of the group + * to indicate they get reopened. + */ + c2->reset_group = true; } } return leader; diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 3655b9ebb147..f5bd5c386df1 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -334,9 +334,17 @@ void perf_evlist__to_front(struct evlist *evlist, #define evlist__for_each_entry_safe(evlist, tmp, evsel) \ __evlist__for_each_entry_safe(&(evlist)->core.entries, tmp, evsel) +#define evlist__for_each_cpu(evlist, index, cpu) \ + evlist__cpu_iter_start(evlist); \ + perf_cpu_map__for_each_cpu (cpu, index, (evlist)->core.all_cpus) + void perf_evlist__set_tracking_event(struct evlist *evlist, struct evsel *tracking_evsel); +void evlist__cpu_iter_start(struct evlist *evlist); +bool evsel__cpu_iter_skip(struct evsel *ev, int cpu); +bool evsel__cpu_iter_skip_no_inc(struct evsel *ev, int cpu); + struct evsel * perf_evlist__find_evsel_by_str(struct evlist *evlist, const char *str); @@ -348,5 +356,6 @@ bool perf_evlist__exclude_kernel(struct evlist *evlist); void perf_evlist__force_leader(struct evlist *evlist); struct evsel *perf_evlist__reset_weak_group(struct evlist *evlist, - struct evsel *evsel); + struct evsel *evsel, + bool close); #endif /* __PERF_EVLIST_H */ diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index f4dea055b080..a69e64236120 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -1223,16 +1223,27 @@ int perf_evsel__append_addr_filter(struct evsel *evsel, const char *filter) return perf_evsel__append_filter(evsel, "%s,%s", filter); } +/* Caller has to clear disabled after going through all CPUs. */ +int evsel__enable_cpu(struct evsel *evsel, int cpu) +{ + return perf_evsel__enable_cpu(&evsel->core, cpu); +} + int evsel__enable(struct evsel *evsel) { int err = perf_evsel__enable(&evsel->core); if (!err) evsel->disabled = false; - return err; } +/* Caller has to set disabled after going through all CPUs. */ +int evsel__disable_cpu(struct evsel *evsel, int cpu) +{ + return perf_evsel__disable_cpu(&evsel->core, cpu); +} + int evsel__disable(struct evsel *evsel) { int err = perf_evsel__disable(&evsel->core); @@ -1587,8 +1598,9 @@ static int perf_event_open(struct evsel *evsel, return fd; } -int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus, - struct perf_thread_map *threads) +static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, + struct perf_thread_map *threads, + int start_cpu, int end_cpu) { int cpu, thread, nthreads; unsigned long flags = PERF_FLAG_FD_CLOEXEC; @@ -1665,7 +1677,7 @@ retry_sample_id: display_attr(&evsel->core.attr); - for (cpu = 0; cpu < cpus->nr; cpu++) { + for (cpu = start_cpu; cpu < end_cpu; cpu++) { for (thread = 0; thread < nthreads; thread++) { int fd, group_fd; @@ -1843,6 +1855,12 @@ out_close: return err; } +int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus, + struct perf_thread_map *threads) +{ + return evsel__open_cpu(evsel, cpus, threads, 0, cpus ? cpus->nr : 1); +} + void evsel__close(struct evsel *evsel) { perf_evsel__close(&evsel->core); @@ -1850,9 +1868,14 @@ void evsel__close(struct evsel *evsel) } int perf_evsel__open_per_cpu(struct evsel *evsel, - struct perf_cpu_map *cpus) + struct perf_cpu_map *cpus, + int cpu) { - return evsel__open(evsel, cpus, NULL); + if (cpu == -1) + return evsel__open_cpu(evsel, cpus, NULL, 0, + cpus ? cpus->nr : 1); + + return evsel__open_cpu(evsel, cpus, NULL, cpu, cpu + 1); } int perf_evsel__open_per_thread(struct evsel *evsel, diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index ddc5ee6f6592..dc14f4a823cd 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -86,6 +86,7 @@ struct evsel { struct list_head config_terms; struct bpf_object *bpf_obj; int bpf_fd; + int err; bool auto_merge_stats; bool merged_stat; const char * metric_expr; @@ -94,7 +95,10 @@ struct evsel { struct evsel *metric_leader; bool collect_stat; bool weak_group; + bool reset_group; + bool errored; bool percore; + int cpu_iter; const char *pmu_name; struct { perf_evsel__sb_cb_t *cb; @@ -218,11 +222,14 @@ int perf_evsel__set_filter(struct evsel *evsel, const char *filter); int perf_evsel__append_tp_filter(struct evsel *evsel, const char *filter); int perf_evsel__append_addr_filter(struct evsel *evsel, const char *filter); +int evsel__enable_cpu(struct evsel *evsel, int cpu); int evsel__enable(struct evsel *evsel); int evsel__disable(struct evsel *evsel); +int evsel__disable_cpu(struct evsel *evsel, int cpu); int perf_evsel__open_per_cpu(struct evsel *evsel, - struct perf_cpu_map *cpus); + struct perf_cpu_map *cpus, + int cpu); int perf_evsel__open_per_thread(struct evsel *evsel, struct perf_thread_map *threads); int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus, diff --git a/tools/perf/util/genelf.c b/tools/perf/util/genelf.c index f9f18b8b1df9..aed49806a09b 100644 --- a/tools/perf/util/genelf.c +++ b/tools/perf/util/genelf.c @@ -8,15 +8,12 @@ */ #include <sys/types.h> -#include <stdio.h> -#include <getopt.h> #include <stddef.h> #include <libelf.h> #include <string.h> #include <stdlib.h> #include <unistd.h> #include <inttypes.h> -#include <limits.h> #include <fcntl.h> #include <err.h> #ifdef HAVE_DWARF_SUPPORT @@ -31,8 +28,6 @@ #define NT_GNU_BUILD_ID 3 #endif -#define JVMTI - #define BUILD_ID_URANDOM /* different uuid for each run */ #ifdef HAVE_LIBCRYPTO @@ -511,44 +506,3 @@ error: return retval; } - -#ifndef JVMTI - -static unsigned char x86_code[] = { - 0xBB, 0x2A, 0x00, 0x00, 0x00, /* movl $42, %ebx */ - 0xB8, 0x01, 0x00, 0x00, 0x00, /* movl $1, %eax */ - 0xCD, 0x80 /* int $0x80 */ -}; - -static struct options options; - -int main(int argc, char **argv) -{ - int c, fd, ret; - - while ((c = getopt(argc, argv, "o:h")) != -1) { - switch (c) { - case 'o': - options.output = optarg; - break; - case 'h': - printf("Usage: genelf -o output_file [-h]\n"); - return 0; - default: - errx(1, "unknown option"); - } - } - - fd = open(options.output, O_CREAT|O_TRUNC|O_RDWR, 0666); - if (fd == -1) - err(1, "cannot create file %s", options.output); - - ret = jit_write_elf(fd, "main", x86_code, sizeof(x86_code)); - close(fd); - - if (ret != 0) - unlink(options.output); - - return ret; -} -#endif diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index becc2d109423..93ad27830e2b 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -850,7 +850,7 @@ int __weak strcmp_cpuid_str(const char *mapcpuid, const char *cpuid) */ int __weak get_cpuid(char *buffer __maybe_unused, size_t sz __maybe_unused) { - return -1; + return ENOSYS; /* Not implemented */ } static int write_cpuid(struct feat_fd *ff, @@ -1089,21 +1089,18 @@ static void cpu_cache_level__fprintf(FILE *out, struct cpu_cache_level *c) fprintf(out, "L%d %-15s %8s [%s]\n", c->level, c->type, c->size, c->map); } -static int build_caches(struct cpu_cache_level caches[], u32 size, u32 *cntp) +#define MAX_CACHE_LVL 4 + +static int build_caches(struct cpu_cache_level caches[], u32 *cntp) { u32 i, cnt = 0; - long ncpus; u32 nr, cpu; u16 level; - ncpus = sysconf(_SC_NPROCESSORS_CONF); - if (ncpus < 0) - return -1; - - nr = (u32)(ncpus & UINT_MAX); + nr = cpu__max_cpu(); for (cpu = 0; cpu < nr; cpu++) { - for (level = 0; level < 10; level++) { + for (level = 0; level < MAX_CACHE_LVL; level++) { struct cpu_cache_level c; int err; @@ -1123,18 +1120,12 @@ static int build_caches(struct cpu_cache_level caches[], u32 size, u32 *cntp) caches[cnt++] = c; else cpu_cache_level__free(&c); - - if (WARN_ONCE(cnt == size, "way too many cpu caches..")) - goto out; } } - out: *cntp = cnt; return 0; } -#define MAX_CACHE_LVL 4 - static int write_cache(struct feat_fd *ff, struct evlist *evlist __maybe_unused) { @@ -1143,7 +1134,7 @@ static int write_cache(struct feat_fd *ff, u32 cnt = 0, i, version = 1; int ret; - ret = build_caches(caches, max_caches, &cnt); + ret = build_caches(caches, &cnt); if (ret) goto out; diff --git a/tools/perf/util/include/linux/linkage.h b/tools/perf/util/include/linux/linkage.h index f01d48a8d707..b8a5159361b4 100644 --- a/tools/perf/util/include/linux/linkage.h +++ b/tools/perf/util/include/linux/linkage.h @@ -5,10 +5,93 @@ /* linkage.h ... for including arch/x86/lib/memcpy_64.S */ -#define ENTRY(name) \ - .globl name; \ +/* Some toolchains use other characters (e.g. '`') to mark new line in macro */ +#ifndef ASM_NL +#define ASM_NL ; +#endif + +#ifndef __ALIGN +#define __ALIGN .align 4,0x90 +#define __ALIGN_STR ".align 4,0x90" +#endif + +/* SYM_T_FUNC -- type used by assembler to mark functions */ +#ifndef SYM_T_FUNC +#define SYM_T_FUNC STT_FUNC +#endif + +/* SYM_A_* -- align the symbol? */ +#define SYM_A_ALIGN ALIGN + +/* SYM_L_* -- linkage of symbols */ +#define SYM_L_GLOBAL(name) .globl name +#define SYM_L_LOCAL(name) /* nothing */ + +#define ALIGN __ALIGN + +/* === generic annotations === */ + +/* SYM_ENTRY -- use only if you have to for non-paired symbols */ +#ifndef SYM_ENTRY +#define SYM_ENTRY(name, linkage, align...) \ + linkage(name) ASM_NL \ + align ASM_NL \ name: +#endif + +/* SYM_START -- use only if you have to */ +#ifndef SYM_START +#define SYM_START(name, linkage, align...) \ + SYM_ENTRY(name, linkage, align) +#endif + +/* SYM_END -- use only if you have to */ +#ifndef SYM_END +#define SYM_END(name, sym_type) \ + .type name sym_type ASM_NL \ + .size name, .-name +#endif + +/* + * SYM_FUNC_START_ALIAS -- use where there are two global names for one + * function + */ +#ifndef SYM_FUNC_START_ALIAS +#define SYM_FUNC_START_ALIAS(name) \ + SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) +#endif + +/* SYM_FUNC_START -- use for global functions */ +#ifndef SYM_FUNC_START +/* + * The same as SYM_FUNC_START_ALIAS, but we will need to distinguish these two + * later. + */ +#define SYM_FUNC_START(name) \ + SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) +#endif + +/* SYM_FUNC_START_LOCAL -- use for local functions */ +#ifndef SYM_FUNC_START_LOCAL +/* the same as SYM_FUNC_START_LOCAL_ALIAS, see comment near SYM_FUNC_START */ +#define SYM_FUNC_START_LOCAL(name) \ + SYM_START(name, SYM_L_LOCAL, SYM_A_ALIGN) +#endif + +/* SYM_FUNC_END_ALIAS -- the end of LOCAL_ALIASed or ALIASed function */ +#ifndef SYM_FUNC_END_ALIAS +#define SYM_FUNC_END_ALIAS(name) \ + SYM_END(name, SYM_T_FUNC) +#endif -#define ENDPROC(name) +/* + * SYM_FUNC_END -- the end of SYM_FUNC_START_LOCAL, SYM_FUNC_START, + * SYM_FUNC_START_WEAK, ... + */ +#ifndef SYM_FUNC_END +/* the same as SYM_FUNC_END_ALIAS, see comment near SYM_FUNC_START */ +#define SYM_FUNC_END(name) \ + SYM_END(name, SYM_T_FUNC) +#endif #endif /* PERF_LINUX_LINKAGE_H_ */ diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 416d174d223c..c8c5410315e8 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -2446,6 +2446,7 @@ static int append_inlines(struct callchain_cursor *cursor, struct map_symbol *ms list_for_each_entry(ilist, &inline_node->val, list) { struct map_symbol ilist_ms = { + .maps = ms->maps, .map = map, .sym = ilist->symbol, }; diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index 6a4d350d5cdb..02aee946b6c1 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -103,8 +103,11 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist, if (!strcmp(ev->name, ids[i])) { if (!metric_events[i]) metric_events[i] = ev; + i++; + if (i == idnum) + break; } else { - if (++i == idnum) { + if (i + 1 == idnum) { /* Discard the whole match and start again */ i = 0; memset(metric_events, 0, @@ -124,7 +127,7 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist, } } - if (i != idnum - 1) { + if (i != idnum) { /* Not whole match */ return NULL; } diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 345b5ccc90f6..9fcba2872130 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -2681,12 +2681,12 @@ static int setup_sort_list(struct perf_hpp_list *list, char *str, ret = sort_dimension__add(list, tok, evlist, level); if (ret == -EINVAL) { if (!cacheline_size() && !strncasecmp(tok, "dcacheline", strlen(tok))) - pr_err("The \"dcacheline\" --sort key needs to know the cacheline size and it couldn't be determined on this system"); + ui__error("The \"dcacheline\" --sort key needs to know the cacheline size and it couldn't be determined on this system"); else - pr_err("Invalid --sort key: `%s'", tok); + ui__error("Invalid --sort key: `%s'", tok); break; } else if (ret == -ESRCH) { - pr_err("Unknown --sort key: `%s'", tok); + ui__error("Unknown --sort key: `%s'", tok); break; } } @@ -2743,7 +2743,7 @@ static int setup_sort_order(struct evlist *evlist) return 0; if (sort_order[1] == '\0') { - pr_err("Invalid --sort key: `+'"); + ui__error("Invalid --sort key: `+'"); return -EINVAL; } @@ -2959,6 +2959,9 @@ int output_field_add(struct perf_hpp_list *list, char *tok) if (strncasecmp(tok, sd->name, strlen(tok))) continue; + if (sort__mode != SORT_MODE__MEMORY) + return -EINVAL; + return __sort_dimension__add_output(list, sd); } @@ -2968,6 +2971,9 @@ int output_field_add(struct perf_hpp_list *list, char *tok) if (strncasecmp(tok, sd->name, strlen(tok))) continue; + if (sort__mode != SORT_MODE__BRANCH) + return -EINVAL; + return __sort_dimension__add_output(list, sd); } @@ -3034,7 +3040,7 @@ static int __setup_output_field(void) strp++; if (!strlen(strp)) { - pr_err("Invalid --fields key: `+'"); + ui__error("Invalid --fields key: `+'"); goto out; } diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 332cb730785b..5f26137b8d60 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -464,7 +464,8 @@ size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp) int create_perf_stat_counter(struct evsel *evsel, struct perf_stat_config *config, - struct target *target) + struct target *target, + int cpu) { struct perf_event_attr *attr = &evsel->core.attr; struct evsel *leader = evsel->leader; @@ -518,7 +519,7 @@ int create_perf_stat_counter(struct evsel *evsel, } if (target__has_cpu(target) && !target__has_per_thread(target)) - return perf_evsel__open_per_cpu(evsel, evsel__cpus(evsel)); + return perf_evsel__open_per_cpu(evsel, evsel__cpus(evsel), cpu); return perf_evsel__open_per_thread(evsel, evsel->core.threads); } diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index bfa9aaf36ce6..fb990efa54a8 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -214,7 +214,8 @@ size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp); int create_perf_stat_counter(struct evsel *evsel, struct perf_stat_config *config, - struct target *target); + struct target *target, + int cpu); void perf_evlist__print_counters(struct evlist *evlist, struct perf_stat_config *config, diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py index 4a12baa0cd4e..a2a8ea6beae3 100755 --- a/tools/testing/kunit/kunit_tool_test.py +++ b/tools/testing/kunit/kunit_tool_test.py @@ -199,7 +199,7 @@ class KUnitMainTest(unittest.TestCase): timeout = 3453 kunit.main(['run', '--timeout', str(timeout)], self.linux_source_mock) assert self.linux_source_mock.build_reconfig.call_count == 1 - self.linux_source_mock.run_kernel.assert_called_once_with(timeout=timeout) + self.linux_source_mock.run_kernel.assert_called_once_with(build_dir=None, timeout=timeout) self.print_mock.assert_any_call(StrContains('Testing complete.')) if __name__ == '__main__': diff --git a/tools/testing/nvdimm/Kbuild b/tools/testing/nvdimm/Kbuild index c4a9196d794c..6aca8d5be159 100644 --- a/tools/testing/nvdimm/Kbuild +++ b/tools/testing/nvdimm/Kbuild @@ -5,6 +5,7 @@ ldflags-y += --wrap=devm_ioremap_nocache ldflags-y += --wrap=devm_memremap ldflags-y += --wrap=devm_memunmap ldflags-y += --wrap=ioremap_nocache +ldflags-y += --wrap=ioremap ldflags-y += --wrap=iounmap ldflags-y += --wrap=memunmap ldflags-y += --wrap=__devm_request_region diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c index 3f55f2f99112..6271ac757a4b 100644 --- a/tools/testing/nvdimm/test/iomap.c +++ b/tools/testing/nvdimm/test/iomap.c @@ -193,6 +193,12 @@ void __iomem *__wrap_ioremap_nocache(resource_size_t offset, unsigned long size) } EXPORT_SYMBOL(__wrap_ioremap_nocache); +void __iomem *__wrap_ioremap(resource_size_t offset, unsigned long size) +{ + return __nfit_test_ioremap(offset, size, ioremap); +} +EXPORT_SYMBOL(__wrap_ioremap); + void __iomem *__wrap_ioremap_wc(resource_size_t offset, unsigned long size) { return __nfit_test_ioremap(offset, size, ioremap_wc); diff --git a/tools/testing/selftests/bpf/test_ftrace.sh b/tools/testing/selftests/bpf/test_ftrace.sh new file mode 100755 index 000000000000..20de7bb873bc --- /dev/null +++ b/tools/testing/selftests/bpf/test_ftrace.sh @@ -0,0 +1,39 @@ +#!/bin/bash + +TR=/sys/kernel/debug/tracing/ +clear_trace() { # reset trace output + echo > $TR/trace +} + +disable_tracing() { # stop trace recording + echo 0 > $TR/tracing_on +} + +enable_tracing() { # start trace recording + echo 1 > $TR/tracing_on +} + +reset_tracer() { # reset the current tracer + echo nop > $TR/current_tracer +} + +disable_tracing +clear_trace + +echo "" > $TR/set_ftrace_filter +echo '*printk* *console* *wake* *serial* *lock*' > $TR/set_ftrace_notrace + +echo "bpf_prog_test*" > $TR/set_graph_function +echo "" > $TR/set_graph_notrace + +echo function_graph > $TR/current_tracer + +enable_tracing +./test_progs -t fentry +./test_progs -t fexit +disable_tracing +clear_trace + +reset_tracer + +exit 0 diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index d27fd929abb9..87eaa49609a0 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -408,10 +408,10 @@ static void update_map(int fd, int index) assert(!bpf_map_update_elem(fd, &index, &value, 0)); } -static int create_prog_dummy1(enum bpf_prog_type prog_type) +static int create_prog_dummy_simple(enum bpf_prog_type prog_type, int ret) { struct bpf_insn prog[] = { - BPF_MOV64_IMM(BPF_REG_0, 42), + BPF_MOV64_IMM(BPF_REG_0, ret), BPF_EXIT_INSN(), }; @@ -419,14 +419,15 @@ static int create_prog_dummy1(enum bpf_prog_type prog_type) ARRAY_SIZE(prog), "GPL", 0, NULL, 0); } -static int create_prog_dummy2(enum bpf_prog_type prog_type, int mfd, int idx) +static int create_prog_dummy_loop(enum bpf_prog_type prog_type, int mfd, + int idx, int ret) { struct bpf_insn prog[] = { BPF_MOV64_IMM(BPF_REG_3, idx), BPF_LD_MAP_FD(BPF_REG_2, mfd), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call), - BPF_MOV64_IMM(BPF_REG_0, 41), + BPF_MOV64_IMM(BPF_REG_0, ret), BPF_EXIT_INSN(), }; @@ -435,10 +436,9 @@ static int create_prog_dummy2(enum bpf_prog_type prog_type, int mfd, int idx) } static int create_prog_array(enum bpf_prog_type prog_type, uint32_t max_elem, - int p1key) + int p1key, int p2key, int p3key) { - int p2key = 1; - int mfd, p1fd, p2fd; + int mfd, p1fd, p2fd, p3fd; mfd = bpf_create_map(BPF_MAP_TYPE_PROG_ARRAY, sizeof(int), sizeof(int), max_elem, 0); @@ -449,23 +449,24 @@ static int create_prog_array(enum bpf_prog_type prog_type, uint32_t max_elem, return -1; } - p1fd = create_prog_dummy1(prog_type); - p2fd = create_prog_dummy2(prog_type, mfd, p2key); - if (p1fd < 0 || p2fd < 0) - goto out; + p1fd = create_prog_dummy_simple(prog_type, 42); + p2fd = create_prog_dummy_loop(prog_type, mfd, p2key, 41); + p3fd = create_prog_dummy_simple(prog_type, 24); + if (p1fd < 0 || p2fd < 0 || p3fd < 0) + goto err; if (bpf_map_update_elem(mfd, &p1key, &p1fd, BPF_ANY) < 0) - goto out; + goto err; if (bpf_map_update_elem(mfd, &p2key, &p2fd, BPF_ANY) < 0) - goto out; + goto err; + if (bpf_map_update_elem(mfd, &p3key, &p3fd, BPF_ANY) < 0) { +err: + close(mfd); + mfd = -1; + } + close(p3fd); close(p2fd); close(p1fd); - return mfd; -out: - close(p2fd); - close(p1fd); - close(mfd); - return -1; } static int create_map_in_map(void) @@ -684,7 +685,7 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, } if (*fixup_prog1) { - map_fds[4] = create_prog_array(prog_type, 4, 0); + map_fds[4] = create_prog_array(prog_type, 4, 0, 1, 2); do { prog[*fixup_prog1].imm = map_fds[4]; fixup_prog1++; @@ -692,7 +693,7 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, } if (*fixup_prog2) { - map_fds[5] = create_prog_array(prog_type, 8, 7); + map_fds[5] = create_prog_array(prog_type, 8, 7, 1, 2); do { prog[*fixup_prog2].imm = map_fds[5]; fixup_prog2++; diff --git a/tools/testing/selftests/bpf/verifier/ref_tracking.c b/tools/testing/selftests/bpf/verifier/ref_tracking.c index ebcbf154c460..604b46151736 100644 --- a/tools/testing/selftests/bpf/verifier/ref_tracking.c +++ b/tools/testing/selftests/bpf/verifier/ref_tracking.c @@ -455,7 +455,7 @@ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 7), /* bpf_tail_call() */ - BPF_MOV64_IMM(BPF_REG_3, 2), + BPF_MOV64_IMM(BPF_REG_3, 3), BPF_LD_MAP_FD(BPF_REG_2, 0), BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call), @@ -478,7 +478,7 @@ BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1), BPF_EMIT_CALL(BPF_FUNC_sk_release), /* bpf_tail_call() */ - BPF_MOV64_IMM(BPF_REG_3, 2), + BPF_MOV64_IMM(BPF_REG_3, 3), BPF_LD_MAP_FD(BPF_REG_2, 0), BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call), @@ -497,7 +497,7 @@ BPF_SK_LOOKUP(sk_lookup_tcp), /* bpf_tail_call() */ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), - BPF_MOV64_IMM(BPF_REG_3, 2), + BPF_MOV64_IMM(BPF_REG_3, 3), BPF_LD_MAP_FD(BPF_REG_2, 0), BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call), diff --git a/tools/testing/selftests/bpf/verifier/runtime_jit.c b/tools/testing/selftests/bpf/verifier/runtime_jit.c index a9a8f620e71c..94c399d1faca 100644 --- a/tools/testing/selftests/bpf/verifier/runtime_jit.c +++ b/tools/testing/selftests/bpf/verifier/runtime_jit.c @@ -27,6 +27,19 @@ { "runtime/jit: tail_call within bounds, no prog", .insns = { + BPF_MOV64_IMM(BPF_REG_3, 3), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_prog1 = { 1 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "runtime/jit: tail_call within bounds, key 2", + .insns = { BPF_MOV64_IMM(BPF_REG_3, 2), BPF_LD_MAP_FD(BPF_REG_2, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call), @@ -35,9 +48,147 @@ }, .fixup_prog1 = { 1 }, .result = ACCEPT, + .retval = 24, +}, +{ + "runtime/jit: tail_call within bounds, key 2 / key 2, first branch", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 13), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[0])), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[0])), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 13, 4), + BPF_MOV64_IMM(BPF_REG_3, 2), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_JMP_IMM(BPF_JA, 0, 0, 3), + BPF_MOV64_IMM(BPF_REG_3, 2), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_prog1 = { 5, 9 }, + .result = ACCEPT, + .retval = 24, +}, +{ + "runtime/jit: tail_call within bounds, key 2 / key 2, second branch", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 14), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[0])), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[0])), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 13, 4), + BPF_MOV64_IMM(BPF_REG_3, 2), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_JMP_IMM(BPF_JA, 0, 0, 3), + BPF_MOV64_IMM(BPF_REG_3, 2), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_prog1 = { 5, 9 }, + .result = ACCEPT, + .retval = 24, +}, +{ + "runtime/jit: tail_call within bounds, key 0 / key 2, first branch", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 13), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[0])), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[0])), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 13, 4), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_JMP_IMM(BPF_JA, 0, 0, 3), + BPF_MOV64_IMM(BPF_REG_3, 2), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_prog1 = { 5, 9 }, + .result = ACCEPT, + .retval = 24, +}, +{ + "runtime/jit: tail_call within bounds, key 0 / key 2, second branch", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 14), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[0])), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[0])), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 13, 4), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_JMP_IMM(BPF_JA, 0, 0, 3), + BPF_MOV64_IMM(BPF_REG_3, 2), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_prog1 = { 5, 9 }, + .result = ACCEPT, + .retval = 42, +}, +{ + "runtime/jit: tail_call within bounds, different maps, first branch", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 13), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[0])), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[0])), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 13, 4), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_JMP_IMM(BPF_JA, 0, 0, 3), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_prog1 = { 5 }, + .fixup_prog2 = { 9 }, + .result_unpriv = REJECT, + .errstr_unpriv = "tail_call abusing map_ptr", + .result = ACCEPT, .retval = 1, }, { + "runtime/jit: tail_call within bounds, different maps, second branch", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 14), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[0])), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[0])), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 13, 4), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_JMP_IMM(BPF_JA, 0, 0, 3), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_prog1 = { 5 }, + .fixup_prog2 = { 9 }, + .result_unpriv = REJECT, + .errstr_unpriv = "tail_call abusing map_ptr", + .result = ACCEPT, + .retval = 42, +}, +{ "runtime/jit: tail_call out of bounds", .insns = { BPF_MOV64_IMM(BPF_REG_3, 256), 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 36fb59f886ea..1a52f2883fe0 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 @@ -3,6 +3,8 @@ # description: ftrace - stacktrace filter command # flags: instance +[ ! -f set_ftrace_filter ] && exit_unsupported + echo _do_fork:stacktrace >> set_ftrace_filter grep -q "_do_fork:stacktrace:unlimited" set_ftrace_filter diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_cpumask.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_cpumask.tc index 86a1f07ef2ca..71fa3f49e35e 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func_cpumask.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_cpumask.tc @@ -15,6 +15,11 @@ if [ $NP -eq 1 ] ;then exit_unresolved fi +if ! grep -q "function" available_tracers ; then + echo "Function trace is not enabled" + exit_unsupported +fi + ORIG_CPUMASK=`cat tracing_cpumask` do_reset() { diff --git a/tools/testing/selftests/ftrace/test.d/functions b/tools/testing/selftests/ftrace/test.d/functions index 86986c4bba54..5d4550591ff9 100644 --- a/tools/testing/selftests/ftrace/test.d/functions +++ b/tools/testing/selftests/ftrace/test.d/functions @@ -46,6 +46,9 @@ reset_events_filter() { # reset all current setting filters } reset_ftrace_filter() { # reset all triggers in set_ftrace_filter + if [ ! -f set_ftrace_filter ]; then + return 0 + fi echo > set_ftrace_filter grep -v '^#' set_ftrace_filter | while read t; do tr=`echo $t | cut -d: -f2` @@ -93,7 +96,7 @@ initialize_ftrace() { # Reset ftrace to initial-state disable_events [ -f set_event_pid ] && echo > set_event_pid [ -f set_ftrace_pid ] && echo > set_ftrace_pid - [ -f set_ftrace_filter ] && echo | tee set_ftrace_* + [ -f set_ftrace_notrace ] && echo > set_ftrace_notrace [ -f set_graph_function ] && echo | tee set_graph_* [ -f stack_trace_filter ] && echo > stack_trace_filter [ -f kprobe_events ] && echo > kprobe_events diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc b/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc index 5862eee91e1d..6e3dbe5f96b7 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc @@ -20,9 +20,9 @@ while read i; do test $N -eq 256 && break done -L=`wc -l kprobe_events` -if [ $L -ne $N ]; then - echo "The number of kprobes events ($L) is not $N" +L=`cat kprobe_events | wc -l` +if [ $L -ne 256 ]; then + echo "The number of kprobes events ($L) is not 256" exit_fail fi diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-action-hist-xfail.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-action-hist-xfail.tc index 1221240f8cf6..3f2aee115f6e 100644 --- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-action-hist-xfail.tc +++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-action-hist-xfail.tc @@ -21,10 +21,10 @@ grep -q "snapshot()" README || exit_unsupported # version issue echo "Test expected snapshot action failure" -echo 'hist:keys=comm:onmatch(sched.sched_wakeup).snapshot()' >> /sys/kernel/debug/tracing/events/sched/sched_waking/trigger && exit_fail +echo 'hist:keys=comm:onmatch(sched.sched_wakeup).snapshot()' >> events/sched/sched_waking/trigger && exit_fail echo "Test expected save action failure" -echo 'hist:keys=comm:onmatch(sched.sched_wakeup).save(comm,prio)' >> /sys/kernel/debug/tracing/events/sched/sched_waking/trigger && exit_fail +echo 'hist:keys=comm:onmatch(sched.sched_wakeup).save(comm,prio)' >> events/sched/sched_waking/trigger && exit_fail exit_xfail diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onchange-action-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onchange-action-hist.tc index 064a284e4e75..c80007aa9f86 100644 --- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onchange-action-hist.tc +++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onchange-action-hist.tc @@ -16,7 +16,7 @@ grep -q "onchange(var)" README || exit_unsupported # version issue echo "Test onchange action" -echo 'hist:keys=comm:newprio=prio:onchange($newprio).save(comm,prio) if comm=="ping"' >> /sys/kernel/debug/tracing/events/sched/sched_waking/trigger +echo 'hist:keys=comm:newprio=prio:onchange($newprio).save(comm,prio) if comm=="ping"' >> events/sched/sched_waking/trigger ping $LOCALHOST -c 3 nice -n 1 ping $LOCALHOST -c 3 diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-snapshot-action-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-snapshot-action-hist.tc index 18fff69fc433..f546c1b66a9b 100644 --- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-snapshot-action-hist.tc +++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-snapshot-action-hist.tc @@ -23,9 +23,9 @@ grep -q "snapshot()" README || exit_unsupported # version issue echo "Test snapshot action" -echo 1 > /sys/kernel/debug/tracing/events/sched/enable +echo 1 > events/sched/enable -echo 'hist:keys=comm:newprio=prio:onchange($newprio).save(comm,prio):onchange($newprio).snapshot() if comm=="ping"' >> /sys/kernel/debug/tracing/events/sched/sched_waking/trigger +echo 'hist:keys=comm:newprio=prio:onchange($newprio).save(comm,prio):onchange($newprio).snapshot() if comm=="ping"' >> events/sched/sched_waking/trigger ping $LOCALHOST -c 3 nice -n 1 ping $LOCALHOST -c 3 diff --git a/tools/testing/selftests/kselftest/module.sh b/tools/testing/selftests/kselftest/module.sh index 18e1c7992d30..fb4733faff12 100755 --- a/tools/testing/selftests/kselftest/module.sh +++ b/tools/testing/selftests/kselftest/module.sh @@ -9,7 +9,7 @@ # # #!/bin/sh # SPDX-License-Identifier: GPL-2.0+ -# $(dirname $0)/../kselftest_module.sh "description" module_name +# $(dirname $0)/../kselftest/module.sh "description" module_name # # Example: tools/testing/selftests/lib/printf.sh diff --git a/tools/testing/selftests/kselftest/prefix.pl b/tools/testing/selftests/kselftest/prefix.pl index ec7e48118183..31f7c2a0a8bd 100755 --- a/tools/testing/selftests/kselftest/prefix.pl +++ b/tools/testing/selftests/kselftest/prefix.pl @@ -3,6 +3,7 @@ # Prefix all lines with "# ", unbuffered. Command being piped in may need # to have unbuffering forced with "stdbuf -i0 -o0 -e0 $cmd". use strict; +use IO::Handle; binmode STDIN; binmode STDOUT; diff --git a/tools/testing/selftests/kselftest/runner.sh b/tools/testing/selftests/kselftest/runner.sh index 84de7bc74f2c..a8d20cbb711c 100644 --- a/tools/testing/selftests/kselftest/runner.sh +++ b/tools/testing/selftests/kselftest/runner.sh @@ -79,6 +79,7 @@ run_one() if [ $rc -eq $skip_rc ]; then \ echo "not ok $test_num $TEST_HDR_MSG # SKIP" elif [ $rc -eq $timeout_rc ]; then \ + echo "#" echo "not ok $test_num $TEST_HDR_MSG # TIMEOUT" else echo "not ok $test_num $TEST_HDR_MSG # exit=$rc" diff --git a/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh b/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh index fef88eb4b873..fa6a88c50750 100755 --- a/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh +++ b/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh @@ -36,7 +36,7 @@ h2_destroy() { ip -6 route del 2001:db8:1::/64 vrf v$h2 ip -4 route del 192.0.2.0/28 vrf v$h2 - simple_if_fini $h2 192.0.2.130/28 + simple_if_fini $h2 192.0.2.130/28 2001:db8:2::2/64 } router_create() diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index d697815d2785..71a62e7e35b1 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -11,9 +11,9 @@ # R1 and R2 (also implemented with namespaces), with different MTUs: # # segment a_r1 segment b_r1 a_r1: 2000 -# .--------------R1--------------. a_r2: 1500 -# A B a_r3: 2000 -# '--------------R2--------------' a_r4: 1400 +# .--------------R1--------------. b_r1: 1400 +# A B a_r2: 2000 +# '--------------R2--------------' b_r2: 1500 # segment a_r2 segment b_r2 # # Check that PMTU exceptions with the correct PMTU are created. Then diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 13e5ef615026..0ea44d975b6c 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -722,34 +722,6 @@ TEST_F(tls, recv_lowat) EXPECT_EQ(memcmp(send_mem, recv_mem + 10, 5), 0); } -TEST_F(tls, recv_rcvbuf) -{ - char send_mem[4096]; - char recv_mem[4096]; - int rcv_buf = 1024; - - memset(send_mem, 0x1c, sizeof(send_mem)); - - EXPECT_EQ(setsockopt(self->cfd, SOL_SOCKET, SO_RCVBUF, - &rcv_buf, sizeof(rcv_buf)), 0); - - EXPECT_EQ(send(self->fd, send_mem, 512, 0), 512); - memset(recv_mem, 0, sizeof(recv_mem)); - EXPECT_EQ(recv(self->cfd, recv_mem, sizeof(recv_mem), 0), 512); - EXPECT_EQ(memcmp(send_mem, recv_mem, 512), 0); - - if (self->notls) - return; - - EXPECT_EQ(send(self->fd, send_mem, 4096, 0), 4096); - memset(recv_mem, 0, sizeof(recv_mem)); - EXPECT_EQ(recv(self->cfd, recv_mem, sizeof(recv_mem), 0), -1); - EXPECT_EQ(errno, EMSGSIZE); - - EXPECT_EQ(recv(self->cfd, recv_mem, sizeof(recv_mem), 0), -1); - EXPECT_EQ(errno, EMSGSIZE); -} - TEST_F(tls, bidir) { char const *test_str = "test_read"; diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh index 1be55e705780..d7e07f4c3d7f 100755 --- a/tools/testing/selftests/netfilter/nft_nat.sh +++ b/tools/testing/selftests/netfilter/nft_nat.sh @@ -8,9 +8,14 @@ ksft_skip=4 ret=0 test_inet_nat=true +sfx=$(mktemp -u "XXXXXXXX") +ns0="ns0-$sfx" +ns1="ns1-$sfx" +ns2="ns2-$sfx" + cleanup() { - for i in 0 1 2; do ip netns del ns$i;done + for i in 0 1 2; do ip netns del ns$i-"$sfx";done } nft --version > /dev/null 2>&1 @@ -25,40 +30,49 @@ if [ $? -ne 0 ];then exit $ksft_skip fi -ip netns add ns0 +ip netns add "$ns0" if [ $? -ne 0 ];then - echo "SKIP: Could not create net namespace" + echo "SKIP: Could not create net namespace $ns0" exit $ksft_skip fi trap cleanup EXIT -ip netns add ns1 -ip netns add ns2 +ip netns add "$ns1" +if [ $? -ne 0 ];then + echo "SKIP: Could not create net namespace $ns1" + exit $ksft_skip +fi + +ip netns add "$ns2" +if [ $? -ne 0 ];then + echo "SKIP: Could not create net namespace $ns2" + exit $ksft_skip +fi -ip link add veth0 netns ns0 type veth peer name eth0 netns ns1 > /dev/null 2>&1 +ip link add veth0 netns "$ns0" type veth peer name eth0 netns "$ns1" > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: No virtual ethernet pair device support in kernel" exit $ksft_skip fi -ip link add veth1 netns ns0 type veth peer name eth0 netns ns2 +ip link add veth1 netns "$ns0" type veth peer name eth0 netns "$ns2" -ip -net ns0 link set lo up -ip -net ns0 link set veth0 up -ip -net ns0 addr add 10.0.1.1/24 dev veth0 -ip -net ns0 addr add dead:1::1/64 dev veth0 +ip -net "$ns0" link set lo up +ip -net "$ns0" link set veth0 up +ip -net "$ns0" addr add 10.0.1.1/24 dev veth0 +ip -net "$ns0" addr add dead:1::1/64 dev veth0 -ip -net ns0 link set veth1 up -ip -net ns0 addr add 10.0.2.1/24 dev veth1 -ip -net ns0 addr add dead:2::1/64 dev veth1 +ip -net "$ns0" link set veth1 up +ip -net "$ns0" addr add 10.0.2.1/24 dev veth1 +ip -net "$ns0" addr add dead:2::1/64 dev veth1 for i in 1 2; do - ip -net ns$i link set lo up - ip -net ns$i link set eth0 up - ip -net ns$i addr add 10.0.$i.99/24 dev eth0 - ip -net ns$i route add default via 10.0.$i.1 - ip -net ns$i addr add dead:$i::99/64 dev eth0 - ip -net ns$i route add default via dead:$i::1 + ip -net ns$i-$sfx link set lo up + ip -net ns$i-$sfx link set eth0 up + ip -net ns$i-$sfx addr add 10.0.$i.99/24 dev eth0 + ip -net ns$i-$sfx route add default via 10.0.$i.1 + ip -net ns$i-$sfx addr add dead:$i::99/64 dev eth0 + ip -net ns$i-$sfx route add default via dead:$i::1 done bad_counter() @@ -66,8 +80,9 @@ bad_counter() local ns=$1 local counter=$2 local expect=$3 + local tag=$4 - echo "ERROR: $counter counter in $ns has unexpected value (expected $expect)" 1>&2 + echo "ERROR: $counter counter in $ns has unexpected value (expected $expect) at $tag" 1>&2 ip netns exec $ns nft list counter inet filter $counter 1>&2 } @@ -78,24 +93,24 @@ check_counters() cnt=$(ip netns exec $ns nft list counter inet filter ns0in | grep -q "packets 1 bytes 84") if [ $? -ne 0 ]; then - bad_counter $ns ns0in "packets 1 bytes 84" + bad_counter $ns ns0in "packets 1 bytes 84" "check_counters 1" lret=1 fi cnt=$(ip netns exec $ns nft list counter inet filter ns0out | grep -q "packets 1 bytes 84") if [ $? -ne 0 ]; then - bad_counter $ns ns0out "packets 1 bytes 84" + bad_counter $ns ns0out "packets 1 bytes 84" "check_counters 2" lret=1 fi expect="packets 1 bytes 104" cnt=$(ip netns exec $ns nft list counter inet filter ns0in6 | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter $ns ns0in6 "$expect" + bad_counter $ns ns0in6 "$expect" "check_counters 3" lret=1 fi cnt=$(ip netns exec $ns nft list counter inet filter ns0out6 | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter $ns ns0out6 "$expect" + bad_counter $ns ns0out6 "$expect" "check_counters 4" lret=1 fi @@ -107,41 +122,41 @@ check_ns0_counters() local ns=$1 local lret=0 - cnt=$(ip netns exec ns0 nft list counter inet filter ns0in | grep -q "packets 0 bytes 0") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns0in | grep -q "packets 0 bytes 0") if [ $? -ne 0 ]; then - bad_counter ns0 ns0in "packets 0 bytes 0" + bad_counter "$ns0" ns0in "packets 0 bytes 0" "check_ns0_counters 1" lret=1 fi - cnt=$(ip netns exec ns0 nft list counter inet filter ns0in6 | grep -q "packets 0 bytes 0") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns0in6 | grep -q "packets 0 bytes 0") if [ $? -ne 0 ]; then - bad_counter ns0 ns0in6 "packets 0 bytes 0" + bad_counter "$ns0" ns0in6 "packets 0 bytes 0" lret=1 fi - cnt=$(ip netns exec ns0 nft list counter inet filter ns0out | grep -q "packets 0 bytes 0") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns0out | grep -q "packets 0 bytes 0") if [ $? -ne 0 ]; then - bad_counter ns0 ns0out "packets 0 bytes 0" + bad_counter "$ns0" ns0out "packets 0 bytes 0" "check_ns0_counters 2" lret=1 fi - cnt=$(ip netns exec ns0 nft list counter inet filter ns0out6 | grep -q "packets 0 bytes 0") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns0out6 | grep -q "packets 0 bytes 0") if [ $? -ne 0 ]; then - bad_counter ns0 ns0out6 "packets 0 bytes 0" + bad_counter "$ns0" ns0out6 "packets 0 bytes 0" "check_ns0_counters3 " lret=1 fi for dir in "in" "out" ; do expect="packets 1 bytes 84" - cnt=$(ip netns exec ns0 nft list counter inet filter ${ns}${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ${ns}${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns0 $ns$dir "$expect" + bad_counter "$ns0" $ns$dir "$expect" "check_ns0_counters 4" lret=1 fi expect="packets 1 bytes 104" - cnt=$(ip netns exec ns0 nft list counter inet filter ${ns}${dir}6 | grep -q "$expect") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ${ns}${dir}6 | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns0 $ns$dir6 "$expect" + bad_counter "$ns0" $ns$dir6 "$expect" "check_ns0_counters 5" lret=1 fi done @@ -152,7 +167,7 @@ check_ns0_counters() reset_counters() { for i in 0 1 2;do - ip netns exec ns$i nft reset counters inet > /dev/null + ip netns exec ns$i-$sfx nft reset counters inet > /dev/null done } @@ -166,7 +181,7 @@ test_local_dnat6() IPF="ip6" fi -ip netns exec ns0 nft -f - <<EOF +ip netns exec "$ns0" nft -f /dev/stdin <<EOF table $family nat { chain output { type nat hook output priority 0; policy accept; @@ -180,7 +195,7 @@ EOF fi # ping netns1, expect rewrite to netns2 - ip netns exec ns0 ping -q -c 1 dead:1::99 > /dev/null + ip netns exec "$ns0" ping -q -c 1 dead:1::99 > /dev/null if [ $? -ne 0 ]; then lret=1 echo "ERROR: ping6 failed" @@ -189,18 +204,18 @@ EOF expect="packets 0 bytes 0" for dir in "in6" "out6" ; do - cnt=$(ip netns exec ns0 nft list counter inet filter ns1${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns1${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns0 ns1$dir "$expect" + bad_counter "$ns0" ns1$dir "$expect" "test_local_dnat6 1" lret=1 fi done expect="packets 1 bytes 104" for dir in "in6" "out6" ; do - cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns2${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns0 ns2$dir "$expect" + bad_counter "$ns0" ns2$dir "$expect" "test_local_dnat6 2" lret=1 fi done @@ -208,9 +223,9 @@ EOF # expect 0 count in ns1 expect="packets 0 bytes 0" for dir in "in6" "out6" ; do - cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns0${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns0$dir "$expect" + bad_counter "$ns1" ns0$dir "$expect" "test_local_dnat6 3" lret=1 fi done @@ -218,15 +233,15 @@ EOF # expect 1 packet in ns2 expect="packets 1 bytes 104" for dir in "in6" "out6" ; do - cnt=$(ip netns exec ns2 nft list counter inet filter ns0${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns2" nft list counter inet filter ns0${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns2 ns0$dir "$expect" + bad_counter "$ns2" ns0$dir "$expect" "test_local_dnat6 4" lret=1 fi done - test $lret -eq 0 && echo "PASS: ipv6 ping to ns1 was $family NATted to ns2" - ip netns exec ns0 nft flush chain ip6 nat output + test $lret -eq 0 && echo "PASS: ipv6 ping to $ns1 was $family NATted to $ns2" + ip netns exec "$ns0" nft flush chain ip6 nat output return $lret } @@ -241,7 +256,7 @@ test_local_dnat() IPF="ip" fi -ip netns exec ns0 nft -f - <<EOF 2>/dev/null +ip netns exec "$ns0" nft -f /dev/stdin <<EOF 2>/dev/null table $family nat { chain output { type nat hook output priority 0; policy accept; @@ -260,7 +275,7 @@ EOF fi # ping netns1, expect rewrite to netns2 - ip netns exec ns0 ping -q -c 1 10.0.1.99 > /dev/null + ip netns exec "$ns0" ping -q -c 1 10.0.1.99 > /dev/null if [ $? -ne 0 ]; then lret=1 echo "ERROR: ping failed" @@ -269,18 +284,18 @@ EOF expect="packets 0 bytes 0" for dir in "in" "out" ; do - cnt=$(ip netns exec ns0 nft list counter inet filter ns1${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns1${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns0 ns1$dir "$expect" + bad_counter "$ns0" ns1$dir "$expect" "test_local_dnat 1" lret=1 fi done expect="packets 1 bytes 84" for dir in "in" "out" ; do - cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns2${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns0 ns2$dir "$expect" + bad_counter "$ns0" ns2$dir "$expect" "test_local_dnat 2" lret=1 fi done @@ -288,9 +303,9 @@ EOF # expect 0 count in ns1 expect="packets 0 bytes 0" for dir in "in" "out" ; do - cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns0${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns0$dir "$expect" + bad_counter "$ns1" ns0$dir "$expect" "test_local_dnat 3" lret=1 fi done @@ -298,19 +313,19 @@ EOF # expect 1 packet in ns2 expect="packets 1 bytes 84" for dir in "in" "out" ; do - cnt=$(ip netns exec ns2 nft list counter inet filter ns0${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns2" nft list counter inet filter ns0${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns2 ns0$dir "$expect" + bad_counter "$ns2" ns0$dir "$expect" "test_local_dnat 4" lret=1 fi done - test $lret -eq 0 && echo "PASS: ping to ns1 was $family NATted to ns2" + test $lret -eq 0 && echo "PASS: ping to $ns1 was $family NATted to $ns2" - ip netns exec ns0 nft flush chain $family nat output + ip netns exec "$ns0" nft flush chain $family nat output reset_counters - ip netns exec ns0 ping -q -c 1 10.0.1.99 > /dev/null + ip netns exec "$ns0" ping -q -c 1 10.0.1.99 > /dev/null if [ $? -ne 0 ]; then lret=1 echo "ERROR: ping failed" @@ -319,17 +334,17 @@ EOF expect="packets 1 bytes 84" for dir in "in" "out" ; do - cnt=$(ip netns exec ns0 nft list counter inet filter ns1${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns1${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns1$dir "$expect" + bad_counter "$ns1" ns1$dir "$expect" "test_local_dnat 5" lret=1 fi done expect="packets 0 bytes 0" for dir in "in" "out" ; do - cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns2${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns0 ns2$dir "$expect" + bad_counter "$ns0" ns2$dir "$expect" "test_local_dnat 6" lret=1 fi done @@ -337,9 +352,9 @@ EOF # expect 1 count in ns1 expect="packets 1 bytes 84" for dir in "in" "out" ; do - cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns0${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns0 ns0$dir "$expect" + bad_counter "$ns0" ns0$dir "$expect" "test_local_dnat 7" lret=1 fi done @@ -347,14 +362,14 @@ EOF # expect 0 packet in ns2 expect="packets 0 bytes 0" for dir in "in" "out" ; do - cnt=$(ip netns exec ns2 nft list counter inet filter ns0${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns2" nft list counter inet filter ns0${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns2 ns2$dir "$expect" + bad_counter "$ns2" ns0$dir "$expect" "test_local_dnat 8" lret=1 fi done - test $lret -eq 0 && echo "PASS: ping to ns1 OK after $family nat output chain flush" + test $lret -eq 0 && echo "PASS: ping to $ns1 OK after $family nat output chain flush" return $lret } @@ -366,26 +381,26 @@ test_masquerade6() local natflags=$2 local lret=0 - ip netns exec ns0 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null + ip netns exec "$ns0" sysctl net.ipv6.conf.all.forwarding=1 > /dev/null - ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 + ip netns exec "$ns2" ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: cannot ping ns1 from ns2 via ipv6" + echo "ERROR: cannot ping $ns1 from $ns2 via ipv6" return 1 lret=1 fi expect="packets 1 bytes 104" for dir in "in6" "out6" ; do - cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns2$dir "$expect" + bad_counter "$ns1" ns2$dir "$expect" "test_masquerade6 1" lret=1 fi - cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns2" nft list counter inet filter ns1${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns2 ns1$dir "$expect" + bad_counter "$ns2" ns1$dir "$expect" "test_masquerade6 2" lret=1 fi done @@ -393,7 +408,7 @@ test_masquerade6() reset_counters # add masquerading rule -ip netns exec ns0 nft -f - <<EOF +ip netns exec "$ns0" nft -f /dev/stdin <<EOF table $family nat { chain postrouting { type nat hook postrouting priority 0; policy accept; @@ -406,24 +421,24 @@ EOF return $ksft_skip fi - ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 + ip netns exec "$ns2" ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: cannot ping ns1 from ns2 with active $family masquerade $natflags" + echo "ERROR: cannot ping $ns1 from $ns2 with active $family masquerade $natflags" lret=1 fi # ns1 should have seen packets from ns0, due to masquerade expect="packets 1 bytes 104" for dir in "in6" "out6" ; do - cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns0${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns0$dir "$expect" + bad_counter "$ns1" ns0$dir "$expect" "test_masquerade6 3" lret=1 fi - cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns2" nft list counter inet filter ns1${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns2 ns1$dir "$expect" + bad_counter "$ns2" ns1$dir "$expect" "test_masquerade6 4" lret=1 fi done @@ -431,32 +446,32 @@ EOF # ns1 should not have seen packets from ns2, due to masquerade expect="packets 0 bytes 0" for dir in "in6" "out6" ; do - cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns0$dir "$expect" + bad_counter "$ns1" ns0$dir "$expect" "test_masquerade6 5" lret=1 fi - cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns1${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns2 ns1$dir "$expect" + bad_counter "$ns0" ns1$dir "$expect" "test_masquerade6 6" lret=1 fi done - ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 + ip netns exec "$ns2" ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: cannot ping ns1 from ns2 with active ipv6 masquerade $natflags (attempt 2)" + echo "ERROR: cannot ping $ns1 from $ns2 with active ipv6 masquerade $natflags (attempt 2)" lret=1 fi - ip netns exec ns0 nft flush chain $family nat postrouting + ip netns exec "$ns0" nft flush chain $family nat postrouting if [ $? -ne 0 ]; then echo "ERROR: Could not flush $family nat postrouting" 1>&2 lret=1 fi - test $lret -eq 0 && echo "PASS: $family IPv6 masquerade $natflags for ns2" + test $lret -eq 0 && echo "PASS: $family IPv6 masquerade $natflags for $ns2" return $lret } @@ -467,26 +482,26 @@ test_masquerade() local natflags=$2 local lret=0 - ip netns exec ns0 sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null - ip netns exec ns0 sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null + ip netns exec "$ns0" sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null + ip netns exec "$ns0" sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null - ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 + ip netns exec "$ns2" ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: cannot ping ns1 from ns2 $natflags" + echo "ERROR: cannot ping $ns1 from "$ns2" $natflags" lret=1 fi expect="packets 1 bytes 84" for dir in "in" "out" ; do - cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns2$dir "$expect" + bad_counter "$ns1" ns2$dir "$expect" "test_masquerade 1" lret=1 fi - cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns2" nft list counter inet filter ns1${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns2 ns1$dir "$expect" + bad_counter "$ns2" ns1$dir "$expect" "test_masquerade 2" lret=1 fi done @@ -494,7 +509,7 @@ test_masquerade() reset_counters # add masquerading rule -ip netns exec ns0 nft -f - <<EOF +ip netns exec "$ns0" nft -f /dev/stdin <<EOF table $family nat { chain postrouting { type nat hook postrouting priority 0; policy accept; @@ -507,24 +522,24 @@ EOF return $ksft_skip fi - ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 + ip netns exec "$ns2" ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: cannot ping ns1 from ns2 with active $family masquerade $natflags" + echo "ERROR: cannot ping $ns1 from $ns2 with active $family masquerade $natflags" lret=1 fi # ns1 should have seen packets from ns0, due to masquerade expect="packets 1 bytes 84" for dir in "in" "out" ; do - cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns0${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns0$dir "$expect" + bad_counter "$ns1" ns0$dir "$expect" "test_masquerade 3" lret=1 fi - cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns2" nft list counter inet filter ns1${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns2 ns1$dir "$expect" + bad_counter "$ns2" ns1$dir "$expect" "test_masquerade 4" lret=1 fi done @@ -532,32 +547,32 @@ EOF # ns1 should not have seen packets from ns2, due to masquerade expect="packets 0 bytes 0" for dir in "in" "out" ; do - cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns0$dir "$expect" + bad_counter "$ns1" ns0$dir "$expect" "test_masquerade 5" lret=1 fi - cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns1${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns2 ns1$dir "$expect" + bad_counter "$ns0" ns1$dir "$expect" "test_masquerade 6" lret=1 fi done - ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 + ip netns exec "$ns2" ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: cannot ping ns1 from ns2 with active ip masquerade $natflags (attempt 2)" + echo "ERROR: cannot ping $ns1 from $ns2 with active ip masquerade $natflags (attempt 2)" lret=1 fi - ip netns exec ns0 nft flush chain $family nat postrouting + ip netns exec "$ns0" nft flush chain $family nat postrouting if [ $? -ne 0 ]; then echo "ERROR: Could not flush $family nat postrouting" 1>&2 lret=1 fi - test $lret -eq 0 && echo "PASS: $family IP masquerade $natflags for ns2" + test $lret -eq 0 && echo "PASS: $family IP masquerade $natflags for $ns2" return $lret } @@ -567,25 +582,25 @@ test_redirect6() local family=$1 local lret=0 - ip netns exec ns0 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null + ip netns exec "$ns0" sysctl net.ipv6.conf.all.forwarding=1 > /dev/null - ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 + ip netns exec "$ns2" ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: cannnot ping ns1 from ns2 via ipv6" + echo "ERROR: cannnot ping $ns1 from $ns2 via ipv6" lret=1 fi expect="packets 1 bytes 104" for dir in "in6" "out6" ; do - cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns2$dir "$expect" + bad_counter "$ns1" ns2$dir "$expect" "test_redirect6 1" lret=1 fi - cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns2" nft list counter inet filter ns1${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns2 ns1$dir "$expect" + bad_counter "$ns2" ns1$dir "$expect" "test_redirect6 2" lret=1 fi done @@ -593,7 +608,7 @@ test_redirect6() reset_counters # add redirect rule -ip netns exec ns0 nft -f - <<EOF +ip netns exec "$ns0" nft -f /dev/stdin <<EOF table $family nat { chain prerouting { type nat hook prerouting priority 0; policy accept; @@ -606,18 +621,18 @@ EOF return $ksft_skip fi - ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 + ip netns exec "$ns2" ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: cannot ping ns1 from ns2 via ipv6 with active $family redirect" + echo "ERROR: cannot ping $ns1 from $ns2 via ipv6 with active $family redirect" lret=1 fi # ns1 should have seen no packets from ns2, due to redirection expect="packets 0 bytes 0" for dir in "in6" "out6" ; do - cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns0$dir "$expect" + bad_counter "$ns1" ns0$dir "$expect" "test_redirect6 3" lret=1 fi done @@ -625,20 +640,20 @@ EOF # ns0 should have seen packets from ns2, due to masquerade expect="packets 1 bytes 104" for dir in "in6" "out6" ; do - cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns2${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns0$dir "$expect" + bad_counter "$ns1" ns0$dir "$expect" "test_redirect6 4" lret=1 fi done - ip netns exec ns0 nft delete table $family nat + ip netns exec "$ns0" nft delete table $family nat if [ $? -ne 0 ]; then echo "ERROR: Could not delete $family nat table" 1>&2 lret=1 fi - test $lret -eq 0 && echo "PASS: $family IPv6 redirection for ns2" + test $lret -eq 0 && echo "PASS: $family IPv6 redirection for $ns2" return $lret } @@ -648,26 +663,26 @@ test_redirect() local family=$1 local lret=0 - ip netns exec ns0 sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null - ip netns exec ns0 sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null + ip netns exec "$ns0" sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null + ip netns exec "$ns0" sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null - ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 + ip netns exec "$ns2" ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: cannot ping ns1 from ns2" + echo "ERROR: cannot ping $ns1 from $ns2" lret=1 fi expect="packets 1 bytes 84" for dir in "in" "out" ; do - cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns2$dir "$expect" + bad_counter "$ns1" $ns2$dir "$expect" "test_redirect 1" lret=1 fi - cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns2" nft list counter inet filter ns1${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns2 ns1$dir "$expect" + bad_counter "$ns2" ns1$dir "$expect" "test_redirect 2" lret=1 fi done @@ -675,7 +690,7 @@ test_redirect() reset_counters # add redirect rule -ip netns exec ns0 nft -f - <<EOF +ip netns exec "$ns0" nft -f /dev/stdin <<EOF table $family nat { chain prerouting { type nat hook prerouting priority 0; policy accept; @@ -688,9 +703,9 @@ EOF return $ksft_skip fi - ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 + ip netns exec "$ns2" ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: cannot ping ns1 from ns2 with active $family ip redirect" + echo "ERROR: cannot ping $ns1 from $ns2 with active $family ip redirect" lret=1 fi @@ -698,9 +713,9 @@ EOF expect="packets 0 bytes 0" for dir in "in" "out" ; do - cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns0$dir "$expect" + bad_counter "$ns1" ns0$dir "$expect" "test_redirect 3" lret=1 fi done @@ -708,28 +723,28 @@ EOF # ns0 should have seen packets from ns2, due to masquerade expect="packets 1 bytes 84" for dir in "in" "out" ; do - cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns2${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns0$dir "$expect" + bad_counter "$ns0" ns0$dir "$expect" "test_redirect 4" lret=1 fi done - ip netns exec ns0 nft delete table $family nat + ip netns exec "$ns0" nft delete table $family nat if [ $? -ne 0 ]; then echo "ERROR: Could not delete $family nat table" 1>&2 lret=1 fi - test $lret -eq 0 && echo "PASS: $family IP redirection for ns2" + test $lret -eq 0 && echo "PASS: $family IP redirection for $ns2" return $lret } -# ip netns exec ns0 ping -c 1 -q 10.0.$i.99 +# ip netns exec "$ns0" ping -c 1 -q 10.0.$i.99 for i in 0 1 2; do -ip netns exec ns$i nft -f - <<EOF +ip netns exec ns$i-$sfx nft -f /dev/stdin <<EOF table inet filter { counter ns0in {} counter ns1in {} @@ -796,18 +811,18 @@ done sleep 3 # test basic connectivity for i in 1 2; do - ip netns exec ns0 ping -c 1 -q 10.0.$i.99 > /dev/null + ip netns exec "$ns0" ping -c 1 -q 10.0.$i.99 > /dev/null if [ $? -ne 0 ];then echo "ERROR: Could not reach other namespace(s)" 1>&2 ret=1 fi - ip netns exec ns0 ping -c 1 -q dead:$i::99 > /dev/null + ip netns exec "$ns0" ping -c 1 -q dead:$i::99 > /dev/null if [ $? -ne 0 ];then echo "ERROR: Could not reach other namespace(s) via ipv6" 1>&2 ret=1 fi - check_counters ns$i + check_counters ns$i-$sfx if [ $? -ne 0 ]; then ret=1 fi @@ -820,7 +835,7 @@ for i in 1 2; do done if [ $ret -eq 0 ];then - echo "PASS: netns routing/connectivity: ns0 can reach ns1 and ns2" + echo "PASS: netns routing/connectivity: $ns0 can reach $ns1 and $ns2" fi reset_counters @@ -846,4 +861,9 @@ reset_counters $test_inet_nat && test_redirect inet $test_inet_nat && test_redirect6 inet +if [ $ret -ne 0 ];then + echo -n "FAIL: " + nft --version +fi + exit $ret diff --git a/tools/testing/selftests/safesetid/Makefile b/tools/testing/selftests/safesetid/Makefile index 98da7a504737..fa02c4d5ec13 100644 --- a/tools/testing/selftests/safesetid/Makefile +++ b/tools/testing/selftests/safesetid/Makefile @@ -1,8 +1,9 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for mount selftests. -CFLAGS = -Wall -lcap -O2 +CFLAGS = -Wall -O2 +LDLIBS = -lcap -TEST_PROGS := run_tests.sh +TEST_PROGS := safesetid-test.sh TEST_GEN_FILES := safesetid-test include ../lib.mk diff --git a/tools/testing/selftests/safesetid/safesetid-test.c b/tools/testing/selftests/safesetid/safesetid-test.c index 8f40c6ecdad1..0c4d50644c13 100644 --- a/tools/testing/selftests/safesetid/safesetid-test.c +++ b/tools/testing/selftests/safesetid/safesetid-test.c @@ -213,7 +213,8 @@ static void test_setuid(uid_t child_uid, bool expect_success) } if (cpid == 0) { /* Code executed by child */ - setuid(child_uid); + if (setuid(child_uid) < 0) + exit(EXIT_FAILURE); if (getuid() == child_uid) exit(EXIT_SUCCESS); else @@ -291,8 +292,10 @@ int main(int argc, char **argv) // First test to make sure we can write userns mappings from a user // that doesn't have any restrictions (as long as it has CAP_SETUID); - setuid(NO_POLICY_USER); - setgid(NO_POLICY_USER); + if (setuid(NO_POLICY_USER) < 0) + die("Error with set uid(%d)\n", NO_POLICY_USER); + if (setgid(NO_POLICY_USER) < 0) + die("Error with set gid(%d)\n", NO_POLICY_USER); // Take away all but setid caps drop_caps(true); @@ -306,8 +309,10 @@ int main(int argc, char **argv) die("test_userns failed when it should work\n"); } - setuid(RESTRICTED_PARENT); - setgid(RESTRICTED_PARENT); + if (setuid(RESTRICTED_PARENT) < 0) + die("Error with set uid(%d)\n", RESTRICTED_PARENT); + if (setgid(RESTRICTED_PARENT) < 0) + die("Error with set gid(%d)\n", RESTRICTED_PARENT); test_setuid(ROOT_USER, false); test_setuid(ALLOWED_CHILD1, true); diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json b/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json index 76ae03a64506..2e361cea63bc 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json @@ -152,7 +152,7 @@ ] }, { - "id": "6f5e", + "id": "b99c", "name": "Add basic filter with cmp ematch u8/transport layer and default action", "category": [ "filter", 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 0f89cd50a94b..8877f7b2b809 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json @@ -1,27 +1,5 @@ [ { - "id": "e9a3", - "name": "Add u32 with source match", - "category": [ - "filter", - "u32" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DEV1 ingress" - ], - "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: protocol ip prio 1 u32 match ip src 127.0.0.1/32 flowid 1:1 action ok", - "expExitCode": "0", - "verifyCmd": "$TC filter show dev $DEV1 parent ffff:", - "matchPattern": "match 7f000001/ffffffff at 12", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DEV1 ingress" - ] - }, - { "id": "2638", "name": "Add matchall and try to get it", "category": [ diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json b/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json new file mode 100644 index 000000000000..e09d3c0e307f --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json @@ -0,0 +1,205 @@ +[ + { + "id": "afa9", + "name": "Add u32 with source match", + "category": [ + "filter", + "u32" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 ingress protocol ip prio 1 u32 match ip src 127.0.0.1/32 flowid 1:1 action ok", + "expExitCode": "0", + "verifyCmd": "$TC filter show dev $DEV1 ingress", + "matchPattern": "filter protocol ip pref 1 u32 chain (0[ ]+$|0 fh 800: ht divisor 1|0 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:1.*match 7f000001/ffffffff at 12)", + "matchCount": "3", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "6aa7", + "name": "Add/Replace u32 with source match and invalid indev", + "category": [ + "filter", + "u32" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter replace dev $DEV1 ingress protocol ip prio 1 u32 match ip src 127.0.0.1/32 indev notexist20 flowid 1:1 action ok", + "expExitCode": "2", + "verifyCmd": "$TC filter show dev $DEV1 ingress", + "matchPattern": "filter protocol ip pref 1 u32 chain 0", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "bc4d", + "name": "Replace valid u32 with source match and invalid indev", + "category": [ + "filter", + "u32" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress", + "$TC filter add dev $DEV1 ingress protocol ip prio 1 u32 match ip src 127.0.0.3/32 flowid 1:3 action ok" + ], + "cmdUnderTest": "$TC filter replace dev $DEV1 ingress protocol ip prio 1 u32 match ip src 127.0.0.2/32 indev notexist20 flowid 1:2 action ok", + "expExitCode": "2", + "verifyCmd": "$TC filter show dev $DEV1 ingress", + "matchPattern": "filter protocol ip pref 1 u32 chain (0[ ]+$|0 fh 800: ht divisor 1|0 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:3.*match 7f000003/ffffffff at 12)", + "matchCount": "3", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "648b", + "name": "Add u32 with custom hash table", + "category": [ + "filter", + "u32" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 ingress prio 99 handle 42: u32 divisor 256", + "expExitCode": "0", + "verifyCmd": "$TC filter show dev $DEV1 ingress", + "matchPattern": "pref 99 u32 chain (0[ ]+$|0 fh 42: ht divisor 256|0 fh 800: ht divisor 1)", + "matchCount": "3", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "6658", + "name": "Add/Replace u32 with custom hash table and invalid handle", + "category": [ + "filter", + "u32" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter replace dev $DEV1 ingress prio 99 handle 42:42 u32 divisor 256", + "expExitCode": "2", + "verifyCmd": "$TC filter show dev $DEV1 ingress", + "matchPattern": "pref 99 u32 chain 0", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "9d0a", + "name": "Replace valid u32 with custom hash table and invalid handle", + "category": [ + "filter", + "u32" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress", + "$TC filter add dev $DEV1 ingress prio 99 handle 42: u32 divisor 256" + ], + "cmdUnderTest": "$TC filter replace dev $DEV1 ingress prio 99 handle 42:42 u32 divisor 128", + "expExitCode": "2", + "verifyCmd": "$TC filter show dev $DEV1 ingress", + "matchPattern": "pref 99 u32 chain (0[ ]+$|0 fh 42: ht divisor 256|0 fh 800: ht divisor 1)", + "matchCount": "3", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "1644", + "name": "Add u32 filter that links to a custom hash table", + "category": [ + "filter", + "u32" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress", + "$TC filter add dev $DEV1 ingress prio 99 handle 43: u32 divisor 256" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 ingress protocol ip prio 98 u32 link 43: hashkey mask 0x0000ff00 at 12 match ip src 192.168.0.0/16", + "expExitCode": "0", + "verifyCmd": "$TC filter show dev $DEV1 ingress", + "matchPattern": "filter protocol ip pref 98 u32 chain (0[ ]+$|0 fh 801: ht divisor 1|0 fh 801::800 order 2048 key ht 801 bkt 0 link 43:.*match c0a80000/ffff0000 at 12.*hash mask 0000ff00 at 12)", + "matchCount": "3", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "74c2", + "name": "Add/Replace u32 filter with invalid hash table id", + "category": [ + "filter", + "u32" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter replace dev $DEV1 ingress protocol ip prio 20 u32 ht 47:47 action drop", + "expExitCode": "2", + "verifyCmd": "$TC filter show dev $DEV1 ingress", + "matchPattern": "filter protocol ip pref 20 u32 chain 0", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "1fe6", + "name": "Replace valid u32 filter with invalid hash table id", + "category": [ + "filter", + "u32" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress", + "$TC filter add dev $DEV1 ingress protocol ip prio 99 handle 43: u32 divisor 1", + "$TC filter add dev $DEV1 ingress protocol ip prio 98 u32 ht 43: match tcp src 22 FFFF classid 1:3" + ], + "cmdUnderTest": "$TC filter replace dev $DEV1 ingress protocol ip prio 98 u32 ht 43:1 match tcp src 23 FFFF classid 1:4", + "expExitCode": "2", + "verifyCmd": "$TC filter show dev $DEV1 ingress", + "matchPattern": "filter protocol ip pref 99 u32 chain (0[ ]+$|0 fh (43|800): ht divisor 1|0 fh 43::800 order 2048 key ht 43 bkt 0 flowid 1:3.*match 00160000/ffff0000 at nexthdr\\+0)", + "matchCount": "4", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + } +] diff --git a/tools/testing/selftests/tpm2/test_smoke.sh b/tools/testing/selftests/tpm2/test_smoke.sh index 80521d46220c..8155c2ea7ccb 100755 --- a/tools/testing/selftests/tpm2/test_smoke.sh +++ b/tools/testing/selftests/tpm2/test_smoke.sh @@ -2,3 +2,9 @@ # SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) python -m unittest -v tpm2_tests.SmokeTest +python -m unittest -v tpm2_tests.AsyncTest + +CLEAR_CMD=$(which tpm2_clear) +if [ -n $CLEAR_CMD ]; then + tpm2_clear -T device +fi diff --git a/tools/testing/selftests/tpm2/tpm2.py b/tools/testing/selftests/tpm2/tpm2.py index 828c18584624..d0fcb66a88a6 100644 --- a/tools/testing/selftests/tpm2/tpm2.py +++ b/tools/testing/selftests/tpm2/tpm2.py @@ -6,8 +6,8 @@ import socket import struct import sys import unittest -from fcntl import ioctl - +import fcntl +import select TPM2_ST_NO_SESSIONS = 0x8001 TPM2_ST_SESSIONS = 0x8002 @@ -352,6 +352,7 @@ def hex_dump(d): class Client: FLAG_DEBUG = 0x01 FLAG_SPACE = 0x02 + FLAG_NONBLOCK = 0x04 TPM_IOC_NEW_SPACE = 0xa200 def __init__(self, flags = 0): @@ -362,13 +363,27 @@ class Client: else: self.tpm = open('/dev/tpmrm0', 'r+b', buffering=0) + if (self.flags & Client.FLAG_NONBLOCK): + flags = fcntl.fcntl(self.tpm, fcntl.F_GETFL) + flags |= os.O_NONBLOCK + fcntl.fcntl(self.tpm, fcntl.F_SETFL, flags) + self.tpm_poll = select.poll() + def close(self): self.tpm.close() def send_cmd(self, cmd): self.tpm.write(cmd) + + if (self.flags & Client.FLAG_NONBLOCK): + self.tpm_poll.register(self.tpm, select.POLLIN) + self.tpm_poll.poll(10000) + rsp = self.tpm.read() + if (self.flags & Client.FLAG_NONBLOCK): + self.tpm_poll.unregister(self.tpm) + if (self.flags & Client.FLAG_DEBUG) != 0: sys.stderr.write('cmd' + os.linesep) sys.stderr.write(hex_dump(cmd) + os.linesep) diff --git a/tools/testing/selftests/tpm2/tpm2_tests.py b/tools/testing/selftests/tpm2/tpm2_tests.py index d4973be53493..728be7c69b76 100644 --- a/tools/testing/selftests/tpm2/tpm2_tests.py +++ b/tools/testing/selftests/tpm2/tpm2_tests.py @@ -288,3 +288,16 @@ class SpaceTest(unittest.TestCase): self.assertEqual(rc, tpm2.TPM2_RC_COMMAND_CODE | tpm2.TSS2_RESMGR_TPM_RC_LAYER) + +class AsyncTest(unittest.TestCase): + def setUp(self): + logging.basicConfig(filename='AsyncTest.log', level=logging.DEBUG) + + def test_async(self): + log = logging.getLogger(__name__) + log.debug(sys._getframe().f_code.co_name) + + async_client = tpm2.Client(tpm2.Client.FLAG_NONBLOCK) + log.debug("Calling get_cap in a NON_BLOCKING mode") + async_client.get_cap(tpm2.TPM2_CAP_HANDLES, tpm2.HR_LOADED_SESSION) + async_client.close() diff --git a/usr/include/Makefile b/usr/include/Makefile index 4a753a48767b..84598469e6ff 100644 --- a/usr/include/Makefile +++ b/usr/include/Makefile @@ -91,7 +91,7 @@ endif # asm-generic/*.h is used by asm/*.h, and should not be included directly header-test- += asm-generic/% -extra-y := $(patsubst $(obj)/%.h,%.hdrtest, $(shell find $(obj) -name '*.h')) +extra-y := $(patsubst $(obj)/%.h,%.hdrtest, $(shell find $(obj) -name '*.h' 2>/dev/null)) quiet_cmd_hdrtest = HDRTEST $< cmd_hdrtest = \ diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index 12e0280291ce..8de4daf25097 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -1352,7 +1352,7 @@ long kvm_arch_vm_ioctl(struct file *filp, } } -static void cpu_init_hyp_mode(void *dummy) +static void cpu_init_hyp_mode(void) { phys_addr_t pgd_ptr; unsigned long hyp_stack_ptr; @@ -1386,7 +1386,7 @@ static void cpu_hyp_reinit(void) if (is_kernel_in_hyp_mode()) kvm_timer_init_vhe(); else - cpu_init_hyp_mode(NULL); + cpu_init_hyp_mode(); kvm_arm_init_debug(); diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c index 38b4c910b6c3..0b32a904a1bb 100644 --- a/virt/kvm/arm/mmu.c +++ b/virt/kvm/arm/mmu.c @@ -38,6 +38,11 @@ static unsigned long io_map_base; #define KVM_S2PTE_FLAG_IS_IOMAP (1UL << 0) #define KVM_S2_FLAG_LOGGING_ACTIVE (1UL << 1) +static bool is_iomap(unsigned long flags) +{ + return flags & KVM_S2PTE_FLAG_IS_IOMAP; +} + static bool memslot_is_logging(struct kvm_memory_slot *memslot) { return memslot->dirty_bitmap && !(memslot->flags & KVM_MEM_READONLY); @@ -1698,6 +1703,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, vma_pagesize = vma_kernel_pagesize(vma); if (logging_active || + (vma->vm_flags & VM_PFNMAP) || !fault_supports_stage2_huge_mapping(memslot, hva, vma_pagesize)) { force_pte = true; vma_pagesize = PAGE_SIZE; @@ -1760,6 +1766,9 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, writable = false; } + if (exec_fault && is_iomap(flags)) + return -ENOEXEC; + spin_lock(&kvm->mmu_lock); if (mmu_notifier_retry(kvm, mmu_seq)) goto out_unlock; @@ -1781,7 +1790,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, if (writable) kvm_set_pfn_dirty(pfn); - if (fault_status != FSC_PERM) + if (fault_status != FSC_PERM && !is_iomap(flags)) clean_dcache_guest_page(pfn, vma_pagesize); if (exec_fault) @@ -1948,9 +1957,8 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run) if (kvm_is_error_hva(hva) || (write_fault && !writable)) { if (is_iabt) { /* Prefetch Abort on I/O address */ - kvm_inject_pabt(vcpu, kvm_vcpu_get_hfar(vcpu)); - ret = 1; - goto out_unlock; + ret = -ENOEXEC; + goto out; } /* @@ -1992,6 +2000,11 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run) ret = user_mem_abort(vcpu, fault_ipa, memslot, hva, fault_status); if (ret == 0) ret = 1; +out: + if (ret == -ENOEXEC) { + kvm_inject_pabt(vcpu, kvm_vcpu_get_hfar(vcpu)); + ret = 1; + } out_unlock: srcu_read_unlock(&vcpu->kvm->srcu, idx); return ret; @@ -2302,15 +2315,6 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, break; /* - * Mapping a read-only VMA is only allowed if the - * memory region is configured as read-only. - */ - if (writable && !(vma->vm_flags & VM_WRITE)) { - ret = -EPERM; - break; - } - - /* * Take the intersection of this VMA with the memory region */ vm_start = max(hva, vma->vm_start); diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c index b3c5de48064c..a963b9d766b7 100644 --- a/virt/kvm/arm/vgic/vgic-init.c +++ b/virt/kvm/arm/vgic/vgic-init.c @@ -70,7 +70,7 @@ void kvm_vgic_early_init(struct kvm *kvm) */ int kvm_vgic_create(struct kvm *kvm, u32 type) { - int i, vcpu_lock_idx = -1, ret; + int i, ret; struct kvm_vcpu *vcpu; if (irqchip_in_kernel(kvm)) @@ -86,17 +86,9 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) !kvm_vgic_global_state.can_emulate_gicv2) return -ENODEV; - /* - * Any time a vcpu is run, vcpu_load is called which tries to grab the - * vcpu->mutex. By grabbing the vcpu->mutex of all VCPUs we ensure - * that no other VCPUs are run while we create the vgic. - */ ret = -EBUSY; - kvm_for_each_vcpu(i, vcpu, kvm) { - if (!mutex_trylock(&vcpu->mutex)) - goto out_unlock; - vcpu_lock_idx = i; - } + if (!lock_all_vcpus(kvm)) + return ret; kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu->arch.has_run_once) @@ -125,10 +117,7 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) INIT_LIST_HEAD(&kvm->arch.vgic.rd_regions); out_unlock: - for (; vcpu_lock_idx >= 0; vcpu_lock_idx--) { - vcpu = kvm_get_vcpu(kvm, vcpu_lock_idx); - mutex_unlock(&vcpu->mutex); - } + unlock_all_vcpus(kvm); return ret; } @@ -177,6 +166,7 @@ static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis) break; default: kfree(dist->spis); + dist->spis = NULL; return -EINVAL; } } |